From 8cc4ccf58379935f3ad456cc34e61c4e4c921d0e Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 17 Aug 2018 21:09:47 +0200
Subject: netfilter: ipset: Allow matching on destination MAC address for mac
 and ipmac sets

There doesn't seem to be any reason to restrict MAC address
matching to source MAC addresses in set types bitmap:ipmac,
hash:ipmac and hash:mac. With this patch, and this setup:

  ip netns add A
  ip link add veth1 type veth peer name veth2 netns A
  ip addr add 192.0.2.1/24 dev veth1
  ip -net A addr add 192.0.2.2/24 dev veth2
  ip link set veth1 up
  ip -net A link set veth2 up

  ip netns exec A ipset create test hash:mac
  dst=$(ip netns exec A cat /sys/class/net/veth2/address)
  ip netns exec A ipset add test ${dst}
  ip netns exec A iptables -P INPUT DROP
  ip netns exec A iptables -I INPUT -m set --match-set test dst -j ACCEPT

ipset will match packets based on destination MAC address:

  # ping -c1 192.0.2.2 >/dev/null
  # echo $?
  0

Reported-by: Yi Chen <yiche@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 net/netfilter/ipset/ip_set_bitmap_ipmac.c | 10 +++++-----
 net/netfilter/ipset/ip_set_hash_ipmac.c   | 16 ++++++++++------
 net/netfilter/ipset/ip_set_hash_mac.c     | 10 +++++-----
 3 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index c00b6a2e8e3c..13ade5782847 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -219,10 +219,6 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 	u32 ip;
 
-	/* MAC can be src only */
-	if (!(opt->flags & IPSET_DIM_TWO_SRC))
-		return 0;
-
 	ip = ntohl(ip4addr(skb, opt->flags & IPSET_DIM_ONE_SRC));
 	if (ip < map->first_ip || ip > map->last_ip)
 		return -IPSET_ERR_BITMAP_RANGE;
@@ -233,7 +229,11 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb,
 		return -EINVAL;
 
 	e.id = ip_to_id(map, ip);
-	memcpy(e.ether, eth_hdr(skb)->h_source, ETH_ALEN);
+
+	if (opt->flags & IPSET_DIM_ONE_SRC)
+		ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
+	else
+		ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
 
 	return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
 }
diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c
index 1ab5ed2f6839..fd87de3ed55b 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmac.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmac.c
@@ -103,7 +103,11 @@ hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	    (skb_mac_header(skb) + ETH_HLEN) > skb->data)
 		return -EINVAL;
 
-	memcpy(e.ether, eth_hdr(skb)->h_source, ETH_ALEN);
+	if (opt->flags & IPSET_DIM_ONE_SRC)
+		ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
+	else
+		ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
+
 	if (ether_addr_equal(e.ether, invalid_ether))
 		return -EINVAL;
 
@@ -211,15 +215,15 @@ hash_ipmac6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	};
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
-	 /* MAC can be src only */
-	if (!(opt->flags & IPSET_DIM_TWO_SRC))
-		return 0;
-
 	if (skb_mac_header(skb) < skb->head ||
 	    (skb_mac_header(skb) + ETH_HLEN) > skb->data)
 		return -EINVAL;
 
-	memcpy(e.ether, eth_hdr(skb)->h_source, ETH_ALEN);
+	if (opt->flags & IPSET_DIM_ONE_SRC)
+		ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
+	else
+		ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
+
 	if (ether_addr_equal(e.ether, invalid_ether))
 		return -EINVAL;
 
diff --git a/net/netfilter/ipset/ip_set_hash_mac.c b/net/netfilter/ipset/ip_set_hash_mac.c
index f9d5a2a1e3d0..4fe5f243d0a3 100644
--- a/net/netfilter/ipset/ip_set_hash_mac.c
+++ b/net/netfilter/ipset/ip_set_hash_mac.c
@@ -81,15 +81,15 @@ hash_mac4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct hash_mac4_elem e = { { .foo[0] = 0, .foo[1] = 0 } };
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
-	 /* MAC can be src only */
-	if (!(opt->flags & IPSET_DIM_ONE_SRC))
-		return 0;
-
 	if (skb_mac_header(skb) < skb->head ||
 	    (skb_mac_header(skb) + ETH_HLEN) > skb->data)
 		return -EINVAL;
 
-	ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
+	if (opt->flags & IPSET_DIM_ONE_SRC)
+		ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
+	else
+		ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
+
 	if (is_zero_ether_addr(e.ether))
 		return -EINVAL;
 	return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
-- 
cgit v1.2.3


From 29edbc3ebdb0faa934114f14bf12fc0b784d4f1b Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 17 Aug 2018 21:09:48 +0200
Subject: netfilter: ipset: Make invalid MAC address checks consistent

Set types bitmap:ipmac and hash:ipmac check that MAC addresses
are not all zeroes.

Introduce one missing check, and make the remaining ones
consistent, using is_zero_ether_addr() instead of comparing
against an array containing zeroes.

This was already done for hash:mac sets in commit 26c97c5d8dac
("netfilter: ipset: Use is_zero_ether_addr instead of static and
memcmp").

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 net/netfilter/ipset/ip_set_bitmap_ipmac.c |  3 +++
 net/netfilter/ipset/ip_set_hash_ipmac.c   | 11 ++++-------
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 13ade5782847..980000fc3b50 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -235,6 +235,9 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb,
 	else
 		ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
 
+	if (is_zero_ether_addr(e.ether))
+		return -EINVAL;
+
 	return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
 }
 
diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c
index fd87de3ed55b..c830c68142ff 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmac.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmac.c
@@ -36,9 +36,6 @@ MODULE_ALIAS("ip_set_hash:ip,mac");
 /* Type specific function prefix */
 #define HTYPE		hash_ipmac
 
-/* Zero valued element is not supported */
-static const unsigned char invalid_ether[ETH_ALEN] = { 0 };
-
 /* IPv4 variant */
 
 /* Member elements */
@@ -108,7 +105,7 @@ hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	else
 		ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
 
-	if (ether_addr_equal(e.ether, invalid_ether))
+	if (is_zero_ether_addr(e.ether))
 		return -EINVAL;
 
 	ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
@@ -144,7 +141,7 @@ hash_ipmac4_uadt(struct ip_set *set, struct nlattr *tb[],
 	if (ret)
 		return ret;
 	memcpy(e.ether, nla_data(tb[IPSET_ATTR_ETHER]), ETH_ALEN);
-	if (ether_addr_equal(e.ether, invalid_ether))
+	if (is_zero_ether_addr(e.ether))
 		return -IPSET_ERR_HASH_ELEM;
 
 	return adtfn(set, &e, &ext, &ext, flags);
@@ -224,7 +221,7 @@ hash_ipmac6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	else
 		ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
 
-	if (ether_addr_equal(e.ether, invalid_ether))
+	if (is_zero_ether_addr(e.ether))
 		return -EINVAL;
 
 	ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
@@ -264,7 +261,7 @@ hash_ipmac6_uadt(struct ip_set *set, struct nlattr *tb[],
 		return ret;
 
 	memcpy(e.ether, nla_data(tb[IPSET_ATTR_ETHER]), ETH_ALEN);
-	if (ether_addr_equal(e.ether, invalid_ether))
+	if (is_zero_ether_addr(e.ether))
 		return -IPSET_ERR_HASH_ELEM;
 
 	return adtfn(set, &e, &ext, &ext, flags);
-- 
cgit v1.2.3


From 23c42a403a9cfdbad6004a556c927be7dd61a8ee Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Sat, 27 Oct 2018 15:07:40 +0200
Subject: netfilter: ipset: Introduction of new commands and protocol version 7

Two new commands (IPSET_CMD_GET_BYNAME, IPSET_CMD_GET_BYINDEX) are
introduced. The new commands makes possible to eliminate the getsockopt
operation (in iptables set/SET match/target) and thus use only netlink
communication between userspace and kernel for ipset. With the new
protocol version, userspace can exactly know which functionality is
supported by the running kernel.

Both the kernel and userspace is fully backward compatible.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h      |   2 +-
 include/uapi/linux/netfilter/ipset/ip_set.h |  19 ++--
 net/netfilter/ipset/ip_set_core.c           | 164 +++++++++++++++++++++++++---
 3 files changed, 160 insertions(+), 25 deletions(-)

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 34fc80f3eb90..c4ce07402c24 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -303,11 +303,11 @@ ip_set_put_flags(struct sk_buff *skb, struct ip_set *set)
 /* Netlink CB args */
 enum {
 	IPSET_CB_NET = 0,	/* net namespace */
+	IPSET_CB_PROTO,		/* ipset protocol */
 	IPSET_CB_DUMP,		/* dump single set/all sets */
 	IPSET_CB_INDEX,		/* set index */
 	IPSET_CB_PRIVATE,	/* set private data */
 	IPSET_CB_ARG0,		/* type specific */
-	IPSET_CB_ARG1,
 };
 
 /* register and unregister set references */
diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h
index 60236f694143..ea69ca21ff23 100644
--- a/include/uapi/linux/netfilter/ipset/ip_set.h
+++ b/include/uapi/linux/netfilter/ipset/ip_set.h
@@ -13,8 +13,9 @@
 
 #include <linux/types.h>
 
-/* The protocol version */
-#define IPSET_PROTOCOL		6
+/* The protocol versions */
+#define IPSET_PROTOCOL		7
+#define IPSET_PROTOCOL_MIN	6
 
 /* The max length of strings including NUL: set and type identifiers */
 #define IPSET_MAXNAMELEN	32
@@ -38,17 +39,19 @@ enum ipset_cmd {
 	IPSET_CMD_TEST,		/* 11: Test an element in a set */
 	IPSET_CMD_HEADER,	/* 12: Get set header data only */
 	IPSET_CMD_TYPE,		/* 13: Get set type */
+	IPSET_CMD_GET_BYNAME,	/* 14: Get set index by name */
+	IPSET_CMD_GET_BYINDEX,	/* 15: Get set name by index */
 	IPSET_MSG_MAX,		/* Netlink message commands */
 
 	/* Commands in userspace: */
-	IPSET_CMD_RESTORE = IPSET_MSG_MAX, /* 14: Enter restore mode */
-	IPSET_CMD_HELP,		/* 15: Get help */
-	IPSET_CMD_VERSION,	/* 16: Get program version */
-	IPSET_CMD_QUIT,		/* 17: Quit from interactive mode */
+	IPSET_CMD_RESTORE = IPSET_MSG_MAX, /* 16: Enter restore mode */
+	IPSET_CMD_HELP,		/* 17: Get help */
+	IPSET_CMD_VERSION,	/* 18: Get program version */
+	IPSET_CMD_QUIT,		/* 19: Quit from interactive mode */
 
 	IPSET_CMD_MAX,
 
-	IPSET_CMD_COMMIT = IPSET_CMD_MAX, /* 18: Commit buffered commands */
+	IPSET_CMD_COMMIT = IPSET_CMD_MAX, /* 20: Commit buffered commands */
 };
 
 /* Attributes at command level */
@@ -66,6 +69,7 @@ enum {
 	IPSET_ATTR_LINENO,	/* 9: Restore lineno */
 	IPSET_ATTR_PROTOCOL_MIN, /* 10: Minimal supported version number */
 	IPSET_ATTR_REVISION_MIN	= IPSET_ATTR_PROTOCOL_MIN, /* type rev min */
+	IPSET_ATTR_INDEX,	/* 11: Kernel index of set */
 	__IPSET_ATTR_CMD_MAX,
 };
 #define IPSET_ATTR_CMD_MAX	(__IPSET_ATTR_CMD_MAX - 1)
@@ -223,6 +227,7 @@ enum ipset_adt {
 
 /* Sets are identified by an index in kernel space. Tweak with ip_set_id_t
  * and IPSET_INVALID_ID if you want to increase the max number of sets.
+ * Also, IPSET_ATTR_INDEX must be changed.
  */
 typedef __u16 ip_set_id_t;
 
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index bc4bd247bb7d..847f764b2aeb 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -768,11 +768,21 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_put);
  * The commands are serialized by the nfnl mutex.
  */
 
+static inline u8 protocol(const struct nlattr * const tb[])
+{
+	return nla_get_u8(tb[IPSET_ATTR_PROTOCOL]);
+}
+
 static inline bool
 protocol_failed(const struct nlattr * const tb[])
 {
-	return !tb[IPSET_ATTR_PROTOCOL] ||
-	       nla_get_u8(tb[IPSET_ATTR_PROTOCOL]) != IPSET_PROTOCOL;
+	return !tb[IPSET_ATTR_PROTOCOL] || protocol(tb) != IPSET_PROTOCOL;
+}
+
+static inline bool
+protocol_min_failed(const struct nlattr * const tb[])
+{
+	return !tb[IPSET_ATTR_PROTOCOL] || protocol(tb) < IPSET_PROTOCOL_MIN;
 }
 
 static inline u32
@@ -886,7 +896,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl,
 	u32 flags = flag_exist(nlh);
 	int ret = 0;
 
-	if (unlikely(protocol_failed(attr) ||
+	if (unlikely(protocol_min_failed(attr) ||
 		     !attr[IPSET_ATTR_SETNAME] ||
 		     !attr[IPSET_ATTR_TYPENAME] ||
 		     !attr[IPSET_ATTR_REVISION] ||
@@ -1024,7 +1034,7 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl,
 	ip_set_id_t i;
 	int ret = 0;
 
-	if (unlikely(protocol_failed(attr)))
+	if (unlikely(protocol_min_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
 	/* Must wait for flush to be really finished in list:set */
@@ -1102,7 +1112,7 @@ static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	struct ip_set *s;
 	ip_set_id_t i;
 
-	if (unlikely(protocol_failed(attr)))
+	if (unlikely(protocol_min_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
 	if (!attr[IPSET_ATTR_SETNAME]) {
@@ -1144,7 +1154,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl,
 	ip_set_id_t i;
 	int ret = 0;
 
-	if (unlikely(protocol_failed(attr) ||
+	if (unlikely(protocol_min_failed(attr) ||
 		     !attr[IPSET_ATTR_SETNAME] ||
 		     !attr[IPSET_ATTR_SETNAME2]))
 		return -IPSET_ERR_PROTOCOL;
@@ -1193,7 +1203,7 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	ip_set_id_t from_id, to_id;
 	char from_name[IPSET_MAXNAMELEN];
 
-	if (unlikely(protocol_failed(attr) ||
+	if (unlikely(protocol_min_failed(attr) ||
 		     !attr[IPSET_ATTR_SETNAME] ||
 		     !attr[IPSET_ATTR_SETNAME2]))
 		return -IPSET_ERR_PROTOCOL;
@@ -1288,6 +1298,7 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
 	nla_parse(cda, IPSET_ATTR_CMD_MAX, attr, nlh->nlmsg_len - min_len,
 		  ip_set_setname_policy, NULL);
 
+	cb->args[IPSET_CB_PROTO] = nla_get_u8(cda[IPSET_ATTR_PROTOCOL]);
 	if (cda[IPSET_ATTR_SETNAME]) {
 		struct ip_set *set;
 
@@ -1389,7 +1400,8 @@ dump_last:
 			ret = -EMSGSIZE;
 			goto release_refcount;
 		}
-		if (nla_put_u8(skb, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL) ||
+		if (nla_put_u8(skb, IPSET_ATTR_PROTOCOL,
+			       cb->args[IPSET_CB_PROTO]) ||
 		    nla_put_string(skb, IPSET_ATTR_SETNAME, set->name))
 			goto nla_put_failure;
 		if (dump_flags & IPSET_FLAG_LIST_SETNAME)
@@ -1404,6 +1416,9 @@ dump_last:
 			    nla_put_u8(skb, IPSET_ATTR_REVISION,
 				       set->revision))
 				goto nla_put_failure;
+			if (cb->args[IPSET_CB_PROTO] > IPSET_PROTOCOL_MIN &&
+			    nla_put_net16(skb, IPSET_ATTR_INDEX, htons(index)))
+				goto nla_put_failure;
 			ret = set->variant->head(set, skb);
 			if (ret < 0)
 				goto release_refcount;
@@ -1463,7 +1478,7 @@ static int ip_set_dump(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 		       const struct nlattr * const attr[],
 		       struct netlink_ext_ack *extack)
 {
-	if (unlikely(protocol_failed(attr)))
+	if (unlikely(protocol_min_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
 	{
@@ -1557,7 +1572,7 @@ static int ip_set_uadd(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	bool use_lineno;
 	int ret = 0;
 
-	if (unlikely(protocol_failed(attr) ||
+	if (unlikely(protocol_min_failed(attr) ||
 		     !attr[IPSET_ATTR_SETNAME] ||
 		     !((attr[IPSET_ATTR_DATA] != NULL) ^
 		       (attr[IPSET_ATTR_ADT] != NULL)) ||
@@ -1612,7 +1627,7 @@ static int ip_set_udel(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	bool use_lineno;
 	int ret = 0;
 
-	if (unlikely(protocol_failed(attr) ||
+	if (unlikely(protocol_min_failed(attr) ||
 		     !attr[IPSET_ATTR_SETNAME] ||
 		     !((attr[IPSET_ATTR_DATA] != NULL) ^
 		       (attr[IPSET_ATTR_ADT] != NULL)) ||
@@ -1664,7 +1679,7 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	struct nlattr *tb[IPSET_ATTR_ADT_MAX + 1] = {};
 	int ret = 0;
 
-	if (unlikely(protocol_failed(attr) ||
+	if (unlikely(protocol_min_failed(attr) ||
 		     !attr[IPSET_ATTR_SETNAME] ||
 		     !attr[IPSET_ATTR_DATA] ||
 		     !flag_nested(attr[IPSET_ATTR_DATA])))
@@ -1701,7 +1716,7 @@ static int ip_set_header(struct net *net, struct sock *ctnl,
 	struct nlmsghdr *nlh2;
 	int ret = 0;
 
-	if (unlikely(protocol_failed(attr) ||
+	if (unlikely(protocol_min_failed(attr) ||
 		     !attr[IPSET_ATTR_SETNAME]))
 		return -IPSET_ERR_PROTOCOL;
 
@@ -1717,7 +1732,7 @@ static int ip_set_header(struct net *net, struct sock *ctnl,
 			 IPSET_CMD_HEADER);
 	if (!nlh2)
 		goto nlmsg_failure;
-	if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL) ||
+	if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL, protocol(attr)) ||
 	    nla_put_string(skb2, IPSET_ATTR_SETNAME, set->name) ||
 	    nla_put_string(skb2, IPSET_ATTR_TYPENAME, set->type->name) ||
 	    nla_put_u8(skb2, IPSET_ATTR_FAMILY, set->family) ||
@@ -1758,7 +1773,7 @@ static int ip_set_type(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	const char *typename;
 	int ret = 0;
 
-	if (unlikely(protocol_failed(attr) ||
+	if (unlikely(protocol_min_failed(attr) ||
 		     !attr[IPSET_ATTR_TYPENAME] ||
 		     !attr[IPSET_ATTR_FAMILY]))
 		return -IPSET_ERR_PROTOCOL;
@@ -1777,7 +1792,7 @@ static int ip_set_type(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 			 IPSET_CMD_TYPE);
 	if (!nlh2)
 		goto nlmsg_failure;
-	if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL) ||
+	if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL, protocol(attr)) ||
 	    nla_put_string(skb2, IPSET_ATTR_TYPENAME, typename) ||
 	    nla_put_u8(skb2, IPSET_ATTR_FAMILY, family) ||
 	    nla_put_u8(skb2, IPSET_ATTR_REVISION, max) ||
@@ -1828,6 +1843,111 @@ static int ip_set_protocol(struct net *net, struct sock *ctnl,
 		goto nlmsg_failure;
 	if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL))
 		goto nla_put_failure;
+	if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL_MIN, IPSET_PROTOCOL_MIN))
+		goto nla_put_failure;
+	nlmsg_end(skb2, nlh2);
+
+	ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+
+nla_put_failure:
+	nlmsg_cancel(skb2, nlh2);
+nlmsg_failure:
+	kfree_skb(skb2);
+	return -EMSGSIZE;
+}
+
+/* Get set by name or index, from userspace */
+
+static int ip_set_byname(struct net *net, struct sock *ctnl,
+			 struct sk_buff *skb, const struct nlmsghdr *nlh,
+			 const struct nlattr * const attr[],
+			 struct netlink_ext_ack *extack)
+{
+	struct ip_set_net *inst = ip_set_pernet(net);
+	struct sk_buff *skb2;
+	struct nlmsghdr *nlh2;
+	ip_set_id_t id = IPSET_INVALID_ID;
+	const struct ip_set *set;
+	int ret = 0;
+
+	if (unlikely(protocol_failed(attr) ||
+		     !attr[IPSET_ATTR_SETNAME]))
+		return -IPSET_ERR_PROTOCOL;
+
+	set = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &id);
+	if (id == IPSET_INVALID_ID)
+		return -ENOENT;
+
+	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!skb2)
+		return -ENOMEM;
+
+	nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
+			 IPSET_CMD_GET_BYNAME);
+	if (!nlh2)
+		goto nlmsg_failure;
+	if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL, protocol(attr)) ||
+	    nla_put_u8(skb2, IPSET_ATTR_FAMILY, set->family) ||
+	    nla_put_net16(skb2, IPSET_ATTR_INDEX, htons(id)))
+		goto nla_put_failure;
+	nlmsg_end(skb2, nlh2);
+
+	ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+
+nla_put_failure:
+	nlmsg_cancel(skb2, nlh2);
+nlmsg_failure:
+	kfree_skb(skb2);
+	return -EMSGSIZE;
+}
+
+static const struct nla_policy ip_set_index_policy[IPSET_ATTR_CMD_MAX + 1] = {
+	[IPSET_ATTR_PROTOCOL]	= { .type = NLA_U8 },
+	[IPSET_ATTR_INDEX]	= { .type = NLA_U16 },
+};
+
+static int ip_set_byindex(struct net *net, struct sock *ctnl,
+			  struct sk_buff *skb, const struct nlmsghdr *nlh,
+			  const struct nlattr * const attr[],
+			  struct netlink_ext_ack *extack)
+{
+	struct ip_set_net *inst = ip_set_pernet(net);
+	struct sk_buff *skb2;
+	struct nlmsghdr *nlh2;
+	ip_set_id_t id = IPSET_INVALID_ID;
+	const struct ip_set *set;
+	int ret = 0;
+
+	if (unlikely(protocol_failed(attr) ||
+		     !attr[IPSET_ATTR_INDEX]))
+		return -IPSET_ERR_PROTOCOL;
+
+	id = ip_set_get_h16(attr[IPSET_ATTR_INDEX]);
+	if (id >= inst->ip_set_max)
+		return -ENOENT;
+	set = ip_set(inst, id);
+	if (set == NULL)
+		return -ENOENT;
+
+	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!skb2)
+		return -ENOMEM;
+
+	nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
+			 IPSET_CMD_GET_BYINDEX);
+	if (!nlh2)
+		goto nlmsg_failure;
+	if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL, protocol(attr)) ||
+	    nla_put_string(skb, IPSET_ATTR_SETNAME, set->name))
+		goto nla_put_failure;
 	nlmsg_end(skb2, nlh2);
 
 	ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT);
@@ -1913,6 +2033,16 @@ static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = {
 		.attr_count	= IPSET_ATTR_CMD_MAX,
 		.policy		= ip_set_protocol_policy,
 	},
+	[IPSET_CMD_GET_BYNAME]	= {
+		.call		= ip_set_byname,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_setname_policy,
+	},
+	[IPSET_CMD_GET_BYINDEX]	= {
+		.call		= ip_set_byindex,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_index_policy,
+	},
 };
 
 static struct nfnetlink_subsystem ip_set_netlink_subsys __read_mostly = {
@@ -1958,7 +2088,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 			goto done;
 		}
 
-		if (req_version->version != IPSET_PROTOCOL) {
+		if (req_version->version < IPSET_PROTOCOL_MIN) {
 			ret = -EPROTO;
 			goto done;
 		}
-- 
cgit v1.2.3


From 0e622f67e0413ad12c2481d47353031ddb185620 Mon Sep 17 00:00:00 2001
From: Surabhi Vishnoi <svishnoi@codeaurora.org>
Date: Fri, 12 Oct 2018 11:23:39 +0530
Subject: ath10k: add support for WCN3990 firmware crash recovery

Whenever the WCN3990 firmware becomes unavailable,
the host driver receives a FW down indication, post
which all the direct hardware register access should
be avoided, in order to prevent improper behavior in
the host driver.

Set the crash_flush flag when the host driver receives
a FW_DOWN_IND via qmi, in order to stop the untimely
hardware register access. Also handle the case, where
we need to do core register only for the first FW_READY
indication, which is when we initialize the host driver.
All the subsequent FW_READY indication will be received
in subsystem recovery case and we only need to do the
restart work. The state of driver is maintained using
flags to distinguish between first and subsequent FW_READY
indication received.

Tested HW: WCN3990
Tested FW: WLAN.HL.2.0-01188-QCAHLSWMTPLZ-1

Signed-off-by: Surabhi Vishnoi <svishnoi@codeaurora.org>
Signed-off-by: Rakesh Pillai <pillair@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/core.c |  3 +++
 drivers/net/wireless/ath/ath10k/core.h |  1 +
 drivers/net/wireless/ath/ath10k/snoc.c | 39 +++++++++++++++++++++++++++++++---
 drivers/net/wireless/ath/ath10k/snoc.h |  7 ++++++
 4 files changed, 47 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index da607febfd82..0126e0ad45f4 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -2183,6 +2183,8 @@ static void ath10k_core_restart(struct work_struct *work)
 	if (ret)
 		ath10k_warn(ar, "failed to send firmware crash dump via devcoredump: %d",
 			    ret);
+
+	complete(&ar->driver_recovery);
 }
 
 static void ath10k_core_set_coverage_class_work(struct work_struct *work)
@@ -3046,6 +3048,7 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 	init_completion(&ar->scan.completed);
 	init_completion(&ar->scan.on_channel);
 	init_completion(&ar->target_suspend);
+	init_completion(&ar->driver_recovery);
 	init_completion(&ar->wow.wakeup_completed);
 
 	init_completion(&ar->install_key_done);
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 042418097cf9..009a4936a7ed 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -960,6 +960,7 @@ struct ath10k {
 	} hif;
 
 	struct completion target_suspend;
+	struct completion driver_recovery;
 
 	const struct ath10k_hw_regs *regs;
 	const struct ath10k_hw_ce_regs *hw_ce_regs;
diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 8d3d9bca410f..98724d04baef 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -918,7 +918,9 @@ static void ath10k_snoc_buffer_cleanup(struct ath10k *ar)
 
 static void ath10k_snoc_hif_stop(struct ath10k *ar)
 {
-	ath10k_snoc_irq_disable(ar);
+	if (!test_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags))
+		ath10k_snoc_irq_disable(ar);
+
 	napi_synchronize(&ar->napi);
 	napi_disable(&ar->napi);
 	ath10k_snoc_buffer_cleanup(ar);
@@ -927,10 +929,14 @@ static void ath10k_snoc_hif_stop(struct ath10k *ar)
 
 static int ath10k_snoc_hif_start(struct ath10k *ar)
 {
+	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
+
 	napi_enable(&ar->napi);
 	ath10k_snoc_irq_enable(ar);
 	ath10k_snoc_rx_post(ar);
 
+	clear_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags);
+
 	ath10k_dbg(ar, ATH10K_DBG_BOOT, "boot hif start\n");
 
 	return 0;
@@ -994,7 +1000,8 @@ static int ath10k_snoc_wlan_enable(struct ath10k *ar)
 
 static void ath10k_snoc_wlan_disable(struct ath10k *ar)
 {
-	ath10k_qmi_wlan_disable(ar);
+	if (!test_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags))
+		ath10k_qmi_wlan_disable(ar);
 }
 
 static void ath10k_snoc_hif_power_down(struct ath10k *ar)
@@ -1091,6 +1098,11 @@ static int ath10k_snoc_napi_poll(struct napi_struct *ctx, int budget)
 	struct ath10k *ar = container_of(ctx, struct ath10k, napi);
 	int done = 0;
 
+	if (test_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags)) {
+		napi_complete(ctx);
+		return done;
+	}
+
 	ath10k_ce_per_engine_service_any(ar);
 	done = ath10k_htt_txrx_compl_task(ar, budget);
 
@@ -1187,17 +1199,29 @@ int ath10k_snoc_fw_indication(struct ath10k *ar, u64 type)
 	struct ath10k_bus_params bus_params;
 	int ret;
 
+	if (test_bit(ATH10K_SNOC_FLAG_UNREGISTERING, &ar_snoc->flags))
+		return 0;
+
 	switch (type) {
 	case ATH10K_QMI_EVENT_FW_READY_IND:
+		if (test_bit(ATH10K_SNOC_FLAG_REGISTERED, &ar_snoc->flags)) {
+			queue_work(ar->workqueue, &ar->restart_work);
+			break;
+		}
+
 		bus_params.dev_type = ATH10K_DEV_TYPE_LL;
 		bus_params.chip_id = ar_snoc->target_info.soc_version;
 		ret = ath10k_core_register(ar, &bus_params);
 		if (ret) {
-			ath10k_err(ar, "failed to register driver core: %d\n",
+			ath10k_err(ar, "Failed to register driver core: %d\n",
 				   ret);
+			return ret;
 		}
+		set_bit(ATH10K_SNOC_FLAG_REGISTERED, &ar_snoc->flags);
 		break;
 	case ATH10K_QMI_EVENT_FW_DOWN_IND:
+		set_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags);
+		set_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags);
 		break;
 	default:
 		ath10k_err(ar, "invalid fw indication: %llx\n", type);
@@ -1628,8 +1652,17 @@ err_core_destroy:
 static int ath10k_snoc_remove(struct platform_device *pdev)
 {
 	struct ath10k *ar = platform_get_drvdata(pdev);
+	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
 
 	ath10k_dbg(ar, ATH10K_DBG_SNOC, "snoc remove\n");
+
+	reinit_completion(&ar->driver_recovery);
+
+	if (test_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags))
+		wait_for_completion_timeout(&ar->driver_recovery, 3 * HZ);
+
+	set_bit(ATH10K_SNOC_FLAG_UNREGISTERING, &ar_snoc->flags);
+
 	ath10k_core_unregister(ar);
 	ath10k_hw_power_off(ar);
 	ath10k_snoc_free_irq(ar);
diff --git a/drivers/net/wireless/ath/ath10k/snoc.h b/drivers/net/wireless/ath/ath10k/snoc.h
index e1d2d6675556..3a44e30696bc 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.h
+++ b/drivers/net/wireless/ath/ath10k/snoc.h
@@ -70,6 +70,12 @@ struct ath10k_wcn3990_clk_info {
 	bool required;
 };
 
+enum ath10k_snoc_flags {
+	ATH10K_SNOC_FLAG_REGISTERED,
+	ATH10K_SNOC_FLAG_UNREGISTERING,
+	ATH10K_SNOC_FLAG_RECOVERY,
+};
+
 struct ath10k_snoc {
 	struct platform_device *dev;
 	struct ath10k *ar;
@@ -84,6 +90,7 @@ struct ath10k_snoc {
 	struct ath10k_wcn3990_vreg_info *vreg;
 	struct ath10k_wcn3990_clk_info *clk;
 	struct ath10k_qmi *qmi;
+	unsigned long int flags;
 };
 
 static inline struct ath10k_snoc *ath10k_snoc_priv(struct ath10k *ar)
-- 
cgit v1.2.3


From e88975ca37d10a486cf3a3c7199a669eb393c123 Mon Sep 17 00:00:00 2001
From: Anilkumar Kolli <akolli@codeaurora.org>
Date: Fri, 12 Oct 2018 11:33:28 +0530
Subject: ath10k: dump tx stats in rate table format

This patch adds the tx statistics pkts/bytes dump
in rate table format.

Dump format table is similar to http://mcsindex.com/

Tested on QCA9984/QCA4019/QCA988x
Firmware: 10.4-3.5.3-00057
	  10.2.4-1.0-00037
command:
cat /sys/kernel/debug/ieee80211/phy0/netdev\:wlan0/
    stations/<MACADDR>/tx_stats

Signed-off-by: Anilkumar Kolli <akolli@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/core.h        |  1 +
 drivers/net/wireless/ath/ath10k/debugfs_sta.c | 12 +++++++++++-
 drivers/net/wireless/ath/ath10k/htt_rx.c      | 17 ++++++++++++++++-
 drivers/net/wireless/ath/ath10k/wmi.h         |  1 +
 4 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 009a4936a7ed..7d8d4e004e31 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -474,6 +474,7 @@ struct ath10k_htt_data_stats {
 	u64 bw[ATH10K_COUNTER_TYPE_MAX][ATH10K_BW_NUM];
 	u64 nss[ATH10K_COUNTER_TYPE_MAX][ATH10K_NSS_NUM];
 	u64 gi[ATH10K_COUNTER_TYPE_MAX][ATH10K_GI_NUM];
+	u64 rate_table[ATH10K_COUNTER_TYPE_MAX][ATH10K_RATE_TABLE_NUM];
 };
 
 struct ath10k_htt_tx_stats {
diff --git a/drivers/net/wireless/ath/ath10k/debugfs_sta.c b/drivers/net/wireless/ath/ath10k/debugfs_sta.c
index b09cdc699c69..0f3fd65a459e 100644
--- a/drivers/net/wireless/ath/ath10k/debugfs_sta.c
+++ b/drivers/net/wireless/ath/ath10k/debugfs_sta.c
@@ -665,7 +665,7 @@ static ssize_t ath10k_dbg_sta_dump_tx_stats(struct file *file,
 						       "retry", "ampdu"};
 	const char *str[ATH10K_COUNTER_TYPE_MAX] = {"bytes", "packets"};
 	int len = 0, i, j, k, retval = 0;
-	const int size = 2 * 4096;
+	const int size = 16 * 4096;
 	char *buf;
 
 	buf = kzalloc(size, GFP_KERNEL);
@@ -719,6 +719,16 @@ static ssize_t ath10k_dbg_sta_dump_tx_stats(struct file *file,
 				len += scnprintf(buf + len, size - len, "%llu ",
 						 stats->legacy[j][i]);
 			len += scnprintf(buf + len, size - len, "\n");
+			len += scnprintf(buf + len, size - len,
+					 " Rate table %s (1,2 ... Mbps)\n  ",
+					 str[j]);
+			for (i = 0; i < ATH10K_RATE_TABLE_NUM; i++) {
+				len += scnprintf(buf + len, size - len, "%llu ",
+						 stats->rate_table[j][i]);
+				if (!((i + 1) % 8))
+					len +=
+					scnprintf(buf + len, size - len, "\n  ");
+			}
 		}
 	}
 
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index ffec98f7be50..984b0458d077 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -2650,7 +2650,7 @@ ath10k_accumulate_per_peer_tx_stats(struct ath10k *ar,
 {
 	struct rate_info *txrate = &arsta->txrate;
 	struct ath10k_htt_tx_stats *tx_stats;
-	int ht_idx, gi, mcs, bw, nss;
+	int idx, ht_idx, gi, mcs, bw, nss;
 
 	if (!arsta->tx_stats)
 		return;
@@ -2661,6 +2661,8 @@ ath10k_accumulate_per_peer_tx_stats(struct ath10k *ar,
 	mcs = txrate->mcs;
 	bw = txrate->bw;
 	nss = txrate->nss;
+	idx = mcs * 8 + 8 * 10 * nss;
+	idx += bw * 2 + gi;
 
 #define STATS_OP_FMT(name) tx_stats->stats[ATH10K_STATS_TYPE_##name]
 
@@ -2709,12 +2711,16 @@ ath10k_accumulate_per_peer_tx_stats(struct ath10k *ar,
 			pstats->succ_bytes + pstats->retry_bytes;
 		STATS_OP_FMT(AMPDU).gi[0][gi] +=
 			pstats->succ_bytes + pstats->retry_bytes;
+		STATS_OP_FMT(AMPDU).rate_table[0][idx] +=
+			pstats->succ_bytes + pstats->retry_bytes;
 		STATS_OP_FMT(AMPDU).bw[1][bw] +=
 			pstats->succ_pkts + pstats->retry_pkts;
 		STATS_OP_FMT(AMPDU).nss[1][nss] +=
 			pstats->succ_pkts + pstats->retry_pkts;
 		STATS_OP_FMT(AMPDU).gi[1][gi] +=
 			pstats->succ_pkts + pstats->retry_pkts;
+		STATS_OP_FMT(AMPDU).rate_table[1][idx] +=
+			pstats->succ_pkts + pstats->retry_pkts;
 	} else {
 		tx_stats->ack_fails +=
 				ATH10K_HW_BA_FAIL(pstats->flags);
@@ -2743,6 +2749,15 @@ ath10k_accumulate_per_peer_tx_stats(struct ath10k *ar,
 	STATS_OP_FMT(RETRY).bw[1][bw] += pstats->retry_pkts;
 	STATS_OP_FMT(RETRY).nss[1][nss] += pstats->retry_pkts;
 	STATS_OP_FMT(RETRY).gi[1][gi] += pstats->retry_pkts;
+
+	if (txrate->flags >= RATE_INFO_FLAGS_MCS) {
+		STATS_OP_FMT(SUCC).rate_table[0][idx] += pstats->succ_bytes;
+		STATS_OP_FMT(SUCC).rate_table[1][idx] += pstats->succ_pkts;
+		STATS_OP_FMT(FAIL).rate_table[0][idx] += pstats->failed_bytes;
+		STATS_OP_FMT(FAIL).rate_table[1][idx] += pstats->failed_pkts;
+		STATS_OP_FMT(RETRY).rate_table[0][idx] += pstats->retry_bytes;
+		STATS_OP_FMT(RETRY).rate_table[1][idx] += pstats->retry_pkts;
+	}
 }
 
 static void
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index f7badd079051..4971d610f567 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -4991,6 +4991,7 @@ enum wmi_rate_preamble {
 #define ATH10K_LEGACY_NUM	12
 #define ATH10K_GI_NUM		2
 #define ATH10K_HT_MCS_NUM	32
+#define ATH10K_RATE_TABLE_NUM	320
 
 /* Value to disable fixed rate setting */
 #define WMI_FIXED_RATE_NONE    (0xff)
-- 
cgit v1.2.3


From bbcfb343fa7f40a42d11bdac753dd62fdbf0840b Mon Sep 17 00:00:00 2001
From: Anilkumar Kolli <akolli@codeaurora.org>
Date: Fri, 12 Oct 2018 11:36:36 +0530
Subject: ath10k: add memory dump support for QCA4019

This patch adds firmware crash memory dump support for QCA4019.

Tested on:

QCA4019 firmware 10.4-3.2.1.1-00017

Signed-off-by: Anilkumar Kolli <akolli@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/coredump.c | 103 ++++++++++++++++++++++++++++-
 1 file changed, 102 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/coredump.c b/drivers/net/wireless/ath/ath10k/coredump.c
index 4d28063052fe..1ccc73c6ef12 100644
--- a/drivers/net/wireless/ath/ath10k/coredump.c
+++ b/drivers/net/wireless/ath/ath10k/coredump.c
@@ -867,6 +867,101 @@ static const struct ath10k_mem_region qca9984_hw10_mem_regions[] = {
 	},
 };
 
+static const struct ath10k_mem_section ipq4019_soc_reg_range[] = {
+	{0x080000, 0x080004},
+	{0x080020, 0x080024},
+	{0x080028, 0x080050},
+	{0x0800d4, 0x0800ec},
+	{0x08010c, 0x080118},
+	{0x080284, 0x080290},
+	{0x0802a8, 0x0802b8},
+	{0x0802dc, 0x08030c},
+	{0x082000, 0x083fff}
+};
+
+static const struct ath10k_mem_region qca4019_hw10_mem_regions[] = {
+	{
+		.type = ATH10K_MEM_REGION_TYPE_DRAM,
+		.start = 0x400000,
+		.len = 0x68000,
+		.name = "DRAM",
+		.section_table = {
+			.sections = NULL,
+			.size = 0,
+		},
+	},
+	{
+		.type = ATH10K_MEM_REGION_TYPE_REG,
+		.start = 0xC0000,
+		.len = 0x40000,
+		.name = "SRAM",
+		.section_table = {
+			.sections = NULL,
+			.size = 0,
+		},
+	},
+	{
+		.type = ATH10K_MEM_REGION_TYPE_REG,
+		.start = 0x98000,
+		.len = 0x50000,
+		.name = "IRAM",
+		.section_table = {
+			.sections = NULL,
+			.size = 0,
+		},
+	},
+	{
+		.type = ATH10K_MEM_REGION_TYPE_IOREG,
+		.start = 0x30000,
+		.len = 0x7000,
+		.name = "APB REG 1",
+		.section_table = {
+			.sections = NULL,
+			.size = 0,
+		},
+	},
+	{
+		.type = ATH10K_MEM_REGION_TYPE_IOREG,
+		.start = 0x3f000,
+		.len = 0x3000,
+		.name = "APB REG 2",
+		.section_table = {
+			.sections = NULL,
+			.size = 0,
+		},
+	},
+	{
+		.type = ATH10K_MEM_REGION_TYPE_IOREG,
+		.start = 0x43000,
+		.len = 0x3000,
+		.name = "WIFI REG",
+		.section_table = {
+			.sections = NULL,
+			.size = 0,
+		},
+	},
+	{
+		.type = ATH10K_MEM_REGION_TYPE_IOREG,
+		.start = 0x4A000,
+		.len = 0x5000,
+		.name = "CE REG",
+		.section_table = {
+			.sections = NULL,
+			.size = 0,
+		},
+	},
+	{
+		.type = ATH10K_MEM_REGION_TYPE_REG,
+		.start = 0x080000,
+		.len = 0x083fff - 0x080000,
+		.name = "REG_TOTAL",
+		.section_table = {
+			.sections = ipq4019_soc_reg_range,
+			.size = ARRAY_SIZE(ipq4019_soc_reg_range),
+		},
+	},
+};
+
 static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	{
 		.hw_id = QCA6174_HW_1_0_VERSION,
@@ -945,7 +1040,13 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 			.size = ARRAY_SIZE(qca99x0_hw20_mem_regions),
 		},
 	},
-
+	{
+		.hw_id = QCA4019_HW_1_0_DEV_VERSION,
+		.region_table = {
+			.regions = qca4019_hw10_mem_regions,
+			.size = ARRAY_SIZE(qca4019_hw10_mem_regions),
+		},
+	},
 };
 
 static u32 ath10k_coredump_get_ramdump_size(struct ath10k *ar)
-- 
cgit v1.2.3


From 5f09037a0cc2b70d2afdb216d236b52e2bee0a2b Mon Sep 17 00:00:00 2001
From: Anilkumar Kolli <akolli@codeaurora.org>
Date: Fri, 12 Oct 2018 11:36:37 +0530
Subject: ath10k: assign proper firmware crash dump structure

ar->target_version is same for QCA99x0, QCA4019, QCA9888
and QCA9984, this ended up in assigning the wrong hw_mem_layouts.
This patch adds additional hw_rev check to assign correct
hw_mem_layouts.

Tested on:
QCA4019 firmware 10.4-3.2.1.1-00017
QCA9984 firmware 10.4-3.5.3-00057

Signed-off-by: Anilkumar Kolli <akolli@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/coredump.c | 15 ++++++++++++++-
 drivers/net/wireless/ath/ath10k/coredump.h |  1 +
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/coredump.c b/drivers/net/wireless/ath/ath10k/coredump.c
index 1ccc73c6ef12..eadae2f9206b 100644
--- a/drivers/net/wireless/ath/ath10k/coredump.c
+++ b/drivers/net/wireless/ath/ath10k/coredump.c
@@ -965,6 +965,7 @@ static const struct ath10k_mem_region qca4019_hw10_mem_regions[] = {
 static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	{
 		.hw_id = QCA6174_HW_1_0_VERSION,
+		.hw_rev = ATH10K_HW_QCA6174,
 		.region_table = {
 			.regions = qca6174_hw10_mem_regions,
 			.size = ARRAY_SIZE(qca6174_hw10_mem_regions),
@@ -972,6 +973,7 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	},
 	{
 		.hw_id = QCA6174_HW_1_1_VERSION,
+		.hw_rev = ATH10K_HW_QCA6174,
 		.region_table = {
 			.regions = qca6174_hw10_mem_regions,
 			.size = ARRAY_SIZE(qca6174_hw10_mem_regions),
@@ -979,6 +981,7 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	},
 	{
 		.hw_id = QCA6174_HW_1_3_VERSION,
+		.hw_rev = ATH10K_HW_QCA6174,
 		.region_table = {
 			.regions = qca6174_hw10_mem_regions,
 			.size = ARRAY_SIZE(qca6174_hw10_mem_regions),
@@ -986,6 +989,7 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	},
 	{
 		.hw_id = QCA6174_HW_2_1_VERSION,
+		.hw_rev = ATH10K_HW_QCA6174,
 		.region_table = {
 			.regions = qca6174_hw21_mem_regions,
 			.size = ARRAY_SIZE(qca6174_hw21_mem_regions),
@@ -993,6 +997,7 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	},
 	{
 		.hw_id = QCA6174_HW_3_0_VERSION,
+		.hw_rev = ATH10K_HW_QCA6174,
 		.region_table = {
 			.regions = qca6174_hw30_mem_regions,
 			.size = ARRAY_SIZE(qca6174_hw30_mem_regions),
@@ -1000,6 +1005,7 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	},
 	{
 		.hw_id = QCA6174_HW_3_2_VERSION,
+		.hw_rev = ATH10K_HW_QCA6174,
 		.region_table = {
 			.regions = qca6174_hw30_mem_regions,
 			.size = ARRAY_SIZE(qca6174_hw30_mem_regions),
@@ -1007,6 +1013,7 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	},
 	{
 		.hw_id = QCA9377_HW_1_1_DEV_VERSION,
+		.hw_rev = ATH10K_HW_QCA9377,
 		.region_table = {
 			.regions = qca6174_hw30_mem_regions,
 			.size = ARRAY_SIZE(qca6174_hw30_mem_regions),
@@ -1014,6 +1021,7 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	},
 	{
 		.hw_id = QCA988X_HW_2_0_VERSION,
+		.hw_rev = ATH10K_HW_QCA988X,
 		.region_table = {
 			.regions = qca988x_hw20_mem_regions,
 			.size = ARRAY_SIZE(qca988x_hw20_mem_regions),
@@ -1021,6 +1029,7 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	},
 	{
 		.hw_id = QCA9984_HW_1_0_DEV_VERSION,
+		.hw_rev = ATH10K_HW_QCA9984,
 		.region_table = {
 			.regions = qca9984_hw10_mem_regions,
 			.size = ARRAY_SIZE(qca9984_hw10_mem_regions),
@@ -1028,6 +1037,7 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	},
 	{
 		.hw_id = QCA9888_HW_2_0_DEV_VERSION,
+		.hw_rev = ATH10K_HW_QCA9888,
 		.region_table = {
 			.regions = qca9984_hw10_mem_regions,
 			.size = ARRAY_SIZE(qca9984_hw10_mem_regions),
@@ -1035,6 +1045,7 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	},
 	{
 		.hw_id = QCA99X0_HW_2_0_DEV_VERSION,
+		.hw_rev = ATH10K_HW_QCA99X0,
 		.region_table = {
 			.regions = qca99x0_hw20_mem_regions,
 			.size = ARRAY_SIZE(qca99x0_hw20_mem_regions),
@@ -1042,6 +1053,7 @@ static const struct ath10k_hw_mem_layout hw_mem_layouts[] = {
 	},
 	{
 		.hw_id = QCA4019_HW_1_0_DEV_VERSION,
+		.hw_rev = ATH10K_HW_QCA4019,
 		.region_table = {
 			.regions = qca4019_hw10_mem_regions,
 			.size = ARRAY_SIZE(qca4019_hw10_mem_regions),
@@ -1088,7 +1100,8 @@ const struct ath10k_hw_mem_layout *ath10k_coredump_get_mem_layout(struct ath10k
 		return NULL;
 
 	for (i = 0; i < ARRAY_SIZE(hw_mem_layouts); i++) {
-		if (ar->target_version == hw_mem_layouts[i].hw_id)
+		if (ar->target_version == hw_mem_layouts[i].hw_id &&
+		    ar->hw_rev == hw_mem_layouts[i].hw_rev)
 			return &hw_mem_layouts[i];
 	}
 
diff --git a/drivers/net/wireless/ath/ath10k/coredump.h b/drivers/net/wireless/ath/ath10k/coredump.h
index 3baaf9d2cbcd..5dac653e1649 100644
--- a/drivers/net/wireless/ath/ath10k/coredump.h
+++ b/drivers/net/wireless/ath/ath10k/coredump.h
@@ -165,6 +165,7 @@ struct ath10k_mem_region {
  */
 struct ath10k_hw_mem_layout {
 	u32 hw_id;
+	u32 hw_rev;
 
 	struct {
 		const struct ath10k_mem_region *regions;
-- 
cgit v1.2.3


From 4ab7fd955e471a71908d4970017c52b3ef6e47a2 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Tue, 16 Oct 2018 02:35:16 +0000
Subject: ath10k: fix copy-paste error in ath10k_qmi_setup_msa_resources()

The return value from devm_memremap() is not checked correctly.
The test is done against a wrong variable. This patch fix it.

Fixes: ba94c753ccb4 ("ath10k: add QMI message handshake for wcn3990 client")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/qmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/qmi.c b/drivers/net/wireless/ath/ath10k/qmi.c
index 56cb1831dcdf..c2cbb415971e 100644
--- a/drivers/net/wireless/ath/ath10k/qmi.c
+++ b/drivers/net/wireless/ath/ath10k/qmi.c
@@ -931,7 +931,7 @@ static int ath10k_qmi_setup_msa_resources(struct ath10k_qmi *qmi, u32 msa_size)
 		qmi->msa_mem_size = resource_size(&r);
 		qmi->msa_va = devm_memremap(dev, qmi->msa_pa, qmi->msa_mem_size,
 					    MEMREMAP_WT);
-		if (!qmi->msa_pa) {
+		if (!qmi->msa_va) {
 			dev_err(dev, "failed to map memory region: %pa\n", &r.start);
 			return -EBUSY;
 		}
-- 
cgit v1.2.3


From 13104929d2ec32aec0552007d55b9e15bc07176b Mon Sep 17 00:00:00 2001
From: Rakesh Pillai <pillair@codeaurora.org>
Date: Wed, 17 Oct 2018 16:50:03 +0530
Subject: ath10k: fill the channel survey results for WCN3990 correctly

The host driver currently expects the channel info event to be
received in pairs for all the channels, i.e. the first
chan_info event for a particular channel will not have the
COMPLETE flag set and the second chan_info event for the
same channel will have the COMPLETE flag set.

The HL2.0 firmware sends only one channel info event per channel
which is scanned without the COMPLETE flag set. After sending the
chan_info_event for all the channels, the HL2.0 firmware sends a
chan_info_event with COMPLETE flag set to indicate the completion
of the channel info event.

The firmware does not indicate this behavior with any service bitmap
and hence a new firmware feature flag is used to handle the modified
parsing of the channel info events, in the host driver, for the
firmware which sends single channel info event per scanned channel.

Tested HW: WCN3990
Tested FW: WLAN.HL.2.0-01188-QCAHLSWMTPLZ-1

Co-developed-by: Surabhi Vishnoi <svishnoi@codeaurora.org>
Signed-off-by: Surabhi Vishnoi <svishnoi@codeaurora.org>
Signed-off-by: Rakesh Pillai <pillair@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/core.c    |   1 +
 drivers/net/wireless/ath/ath10k/core.h    |   3 +
 drivers/net/wireless/ath/ath10k/wmi-tlv.c |   3 +
 drivers/net/wireless/ath/ath10k/wmi-tlv.h |  10 +++
 drivers/net/wireless/ath/ath10k/wmi.c     | 128 +++++++++++++++++++++---------
 drivers/net/wireless/ath/ath10k/wmi.h     |  12 +++
 6 files changed, 120 insertions(+), 37 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 0126e0ad45f4..9d0b3515989a 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -594,6 +594,7 @@ static const char *const ath10k_core_fw_feature_str[] = {
 	[ATH10K_FW_FEATURE_NO_PS] = "no-ps",
 	[ATH10K_FW_FEATURE_MGMT_TX_BY_REF] = "mgmt-tx-by-reference",
 	[ATH10K_FW_FEATURE_NON_BMI] = "non-bmi",
+	[ATH10K_FW_FEATURE_SINGLE_CHAN_INFO_PER_CHANNEL] = "single-chan-info-per-channel",
 };
 
 static unsigned int ath10k_core_get_fw_feature_str(char *buf,
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 7d8d4e004e31..d14a4f928218 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -761,6 +761,9 @@ enum ath10k_fw_features {
 	/* Firmware load is done externally, not by bmi */
 	ATH10K_FW_FEATURE_NON_BMI = 19,
 
+	/* Firmware sends only one chan_info event per channel */
+	ATH10K_FW_FEATURE_SINGLE_CHAN_INFO_PER_CHANNEL = 20,
+
 	/* keep last */
 	ATH10K_FW_FEATURE_COUNT,
 };
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index bab8b2527fb8..07c4a33d56b5 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -762,6 +762,9 @@ static int ath10k_wmi_tlv_op_pull_ch_info_ev(struct ath10k *ar,
 	arg->noise_floor = ev->noise_floor;
 	arg->rx_clear_count = ev->rx_clear_count;
 	arg->cycle_count = ev->cycle_count;
+	if (test_bit(ATH10K_FW_FEATURE_SINGLE_CHAN_INFO_PER_CHANNEL,
+		     ar->running_fw->fw_file.fw_features))
+		arg->mac_clk_mhz = ev->mac_clk_mhz;
 
 	kfree(tb);
 	return 0;
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.h b/drivers/net/wireless/ath/ath10k/wmi-tlv.h
index 92c25f51bf86..bf8a4320c39c 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.h
@@ -1579,6 +1579,16 @@ struct ath10k_mgmt_tx_pkt_addr {
 	dma_addr_t paddr;
 };
 
+struct chan_info_params {
+	u32 err_code;
+	u32 freq;
+	u32 cmd_flags;
+	u32 noise_floor;
+	u32 rx_clear_count;
+	u32 cycle_count;
+	u32 mac_clk_mhz;
+};
+
 struct wmi_tlv_mgmt_tx_compl_ev {
 	__le32 desc_id;
 	__le32 status;
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 25e8fa789e8d..659513bf4ddc 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -2554,60 +2554,69 @@ static int ath10k_wmi_10_4_op_pull_ch_info_ev(struct ath10k *ar,
 	return 0;
 }
 
-void ath10k_wmi_event_chan_info(struct ath10k *ar, struct sk_buff *skb)
+/*
+ * Handle the channel info event for firmware which only sends one
+ * chan_info event per scanned channel.
+ */
+static void ath10k_wmi_event_chan_info_unpaired(struct ath10k *ar,
+						struct chan_info_params *params)
 {
-	struct wmi_ch_info_ev_arg arg = {};
 	struct survey_info *survey;
-	u32 err_code, freq, cmd_flags, noise_floor, rx_clear_count, cycle_count;
-	int idx, ret;
+	int idx;
 
-	ret = ath10k_wmi_pull_ch_info(ar, skb, &arg);
-	if (ret) {
-		ath10k_warn(ar, "failed to parse chan info event: %d\n", ret);
+	if (params->cmd_flags & WMI_CHAN_INFO_FLAG_COMPLETE) {
+		ath10k_dbg(ar, ATH10K_DBG_WMI, "chan info report completed\n");
 		return;
 	}
 
-	err_code = __le32_to_cpu(arg.err_code);
-	freq = __le32_to_cpu(arg.freq);
-	cmd_flags = __le32_to_cpu(arg.cmd_flags);
-	noise_floor = __le32_to_cpu(arg.noise_floor);
-	rx_clear_count = __le32_to_cpu(arg.rx_clear_count);
-	cycle_count = __le32_to_cpu(arg.cycle_count);
+	idx = freq_to_idx(ar, params->freq);
+	if (idx >= ARRAY_SIZE(ar->survey)) {
+		ath10k_warn(ar, "chan info: invalid frequency %d (idx %d out of bounds)\n",
+			    params->freq, idx);
+		return;
+	}
 
-	ath10k_dbg(ar, ATH10K_DBG_WMI,
-		   "chan info err_code %d freq %d cmd_flags %d noise_floor %d rx_clear_count %d cycle_count %d\n",
-		   err_code, freq, cmd_flags, noise_floor, rx_clear_count,
-		   cycle_count);
+	survey = &ar->survey[idx];
 
-	spin_lock_bh(&ar->data_lock);
+	if (!params->mac_clk_mhz || !survey)
+		return;
 
-	switch (ar->scan.state) {
-	case ATH10K_SCAN_IDLE:
-	case ATH10K_SCAN_STARTING:
-		ath10k_warn(ar, "received chan info event without a scan request, ignoring\n");
-		goto exit;
-	case ATH10K_SCAN_RUNNING:
-	case ATH10K_SCAN_ABORTING:
-		break;
-	}
+	memset(survey, 0, sizeof(*survey));
 
-	idx = freq_to_idx(ar, freq);
+	survey->noise = params->noise_floor;
+	survey->time = (params->cycle_count / params->mac_clk_mhz) / 1000;
+	survey->time_busy = (params->rx_clear_count / params->mac_clk_mhz) / 1000;
+	survey->filled |= SURVEY_INFO_NOISE_DBM | SURVEY_INFO_TIME |
+			  SURVEY_INFO_TIME_BUSY;
+}
+
+/*
+ * Handle the channel info event for firmware which sends chan_info
+ * event in pairs(start and stop events) for every scanned channel.
+ */
+static void ath10k_wmi_event_chan_info_paired(struct ath10k *ar,
+					      struct chan_info_params *params)
+{
+	struct survey_info *survey;
+	int idx;
+
+	idx = freq_to_idx(ar, params->freq);
 	if (idx >= ARRAY_SIZE(ar->survey)) {
 		ath10k_warn(ar, "chan info: invalid frequency %d (idx %d out of bounds)\n",
-			    freq, idx);
-		goto exit;
+			    params->freq, idx);
+		return;
 	}
 
-	if (cmd_flags & WMI_CHAN_INFO_FLAG_COMPLETE) {
+	if (params->cmd_flags & WMI_CHAN_INFO_FLAG_COMPLETE) {
 		if (ar->ch_info_can_report_survey) {
 			survey = &ar->survey[idx];
-			survey->noise = noise_floor;
+			survey->noise = params->noise_floor;
 			survey->filled = SURVEY_INFO_NOISE_DBM;
 
 			ath10k_hw_fill_survey_time(ar,
 						   survey,
-						   cycle_count,
-						   rx_clear_count,
+						   params->cycle_count,
+						   params->rx_clear_count,
 						   ar->survey_last_cycle_count,
 						   ar->survey_last_rx_clear_count);
 		}
@@ -2617,11 +2626,56 @@ void ath10k_wmi_event_chan_info(struct ath10k *ar, struct sk_buff *skb)
 		ar->ch_info_can_report_survey = true;
 	}
 
-	if (!(cmd_flags & WMI_CHAN_INFO_FLAG_PRE_COMPLETE)) {
-		ar->survey_last_rx_clear_count = rx_clear_count;
-		ar->survey_last_cycle_count = cycle_count;
+	if (!(params->cmd_flags & WMI_CHAN_INFO_FLAG_PRE_COMPLETE)) {
+		ar->survey_last_rx_clear_count = params->rx_clear_count;
+		ar->survey_last_cycle_count = params->cycle_count;
+	}
+}
+
+void ath10k_wmi_event_chan_info(struct ath10k *ar, struct sk_buff *skb)
+{
+	struct chan_info_params ch_info_param;
+	struct wmi_ch_info_ev_arg arg = {};
+	int ret;
+
+	ret = ath10k_wmi_pull_ch_info(ar, skb, &arg);
+	if (ret) {
+		ath10k_warn(ar, "failed to parse chan info event: %d\n", ret);
+		return;
+	}
+
+	ch_info_param.err_code = __le32_to_cpu(arg.err_code);
+	ch_info_param.freq = __le32_to_cpu(arg.freq);
+	ch_info_param.cmd_flags = __le32_to_cpu(arg.cmd_flags);
+	ch_info_param.noise_floor = __le32_to_cpu(arg.noise_floor);
+	ch_info_param.rx_clear_count = __le32_to_cpu(arg.rx_clear_count);
+	ch_info_param.cycle_count = __le32_to_cpu(arg.cycle_count);
+	ch_info_param.mac_clk_mhz = __le32_to_cpu(arg.mac_clk_mhz);
+
+	ath10k_dbg(ar, ATH10K_DBG_WMI,
+		   "chan info err_code %d freq %d cmd_flags %d noise_floor %d rx_clear_count %d cycle_count %d\n",
+		   ch_info_param.err_code, ch_info_param.freq, ch_info_param.cmd_flags,
+		   ch_info_param.noise_floor, ch_info_param.rx_clear_count,
+		   ch_info_param.cycle_count);
+
+	spin_lock_bh(&ar->data_lock);
+
+	switch (ar->scan.state) {
+	case ATH10K_SCAN_IDLE:
+	case ATH10K_SCAN_STARTING:
+		ath10k_warn(ar, "received chan info event without a scan request, ignoring\n");
+		goto exit;
+	case ATH10K_SCAN_RUNNING:
+	case ATH10K_SCAN_ABORTING:
+		break;
 	}
 
+	if (test_bit(ATH10K_FW_FEATURE_SINGLE_CHAN_INFO_PER_CHANNEL,
+		     ar->running_fw->fw_file.fw_features))
+		ath10k_wmi_event_chan_info_unpaired(ar, &ch_info_param);
+	else
+		ath10k_wmi_event_chan_info_paired(ar, &ch_info_param);
+
 exit:
 	spin_unlock_bh(&ar->data_lock);
 }
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index 4971d610f567..58e33ab9e0e9 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -6442,6 +6442,14 @@ struct wmi_chan_info_event {
 	__le32 noise_floor;
 	__le32 rx_clear_count;
 	__le32 cycle_count;
+	__le32 chan_tx_pwr_range;
+	__le32 chan_tx_pwr_tp;
+	__le32 rx_frame_count;
+	__le32 my_bss_rx_cycle_count;
+	__le32 rx_11b_mode_data_duration;
+	__le32 tx_frame_cnt;
+	__le32 mac_clk_mhz;
+
 } __packed;
 
 struct wmi_10_4_chan_info_event {
@@ -6670,6 +6678,10 @@ struct wmi_ch_info_ev_arg {
 	__le32 chan_tx_pwr_range;
 	__le32 chan_tx_pwr_tp;
 	__le32 rx_frame_count;
+	__le32 my_bss_rx_cycle_count;
+	__le32 rx_11b_mode_data_duration;
+	__le32 tx_frame_cnt;
+	__le32 mac_clk_mhz;
 };
 
 /* From 10.4 firmware, not sure all have the same values. */
-- 
cgit v1.2.3


From 539b44e70c5b4ad82d2c0c97a4dfb37523d891f6 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 18 Oct 2018 10:36:19 +0300
Subject: ath10k: fixup extended per sta tx statistics

I had a couple concerns with this code.  First, we definitely need to
set the error code if the kzalloc() fails.  Secondly, I was worried that
if we didn't set "arsta->tx_stats" to NULL after freeing it, then it
looks to me like it might lead to a use after free.  I can't test that,
but it's harmless to set it to NULL so I did.

Fixes: a904417fc876 ("ath10k: add extended per sta tx statistics support")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index a1c2801ded10..2b8c8bf80b0d 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -6296,8 +6296,10 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 		if (ath10k_debug_is_extd_tx_stats_enabled(ar)) {
 			arsta->tx_stats = kzalloc(sizeof(*arsta->tx_stats),
 						  GFP_KERNEL);
-			if (!arsta->tx_stats)
+			if (!arsta->tx_stats) {
+				ret = -ENOMEM;
 				goto exit;
+			}
 		}
 
 		num_tdls_stations = ath10k_mac_tdls_vif_stations_count(hw, vif);
@@ -6385,8 +6387,10 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 			   "mac vdev %d peer delete %pM sta %pK (sta gone)\n",
 			   arvif->vdev_id, sta->addr, sta);
 
-		if (ath10k_debug_is_extd_tx_stats_enabled(ar))
+		if (ath10k_debug_is_extd_tx_stats_enabled(ar)) {
 			kfree(arsta->tx_stats);
+			arsta->tx_stats = NULL;
+		}
 
 		if (sta->tdls) {
 			ret = ath10k_mac_tdls_peer_update(ar, arvif->vdev_id,
-- 
cgit v1.2.3


From eb9bd8b963d61125b0e336f1f6c9487051a812c3 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 18 Oct 2018 22:51:04 +0100
Subject: ath10k: fix some spelling mistakes

Trivial fix to some spelling mistakes in ath10k_err and ath10k_dbg
messages:
"capablity" -> "capability"
"registed" -> "registered"

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/qmi.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/qmi.c b/drivers/net/wireless/ath/ath10k/qmi.c
index c2cbb415971e..f0429bee35c2 100644
--- a/drivers/net/wireless/ath/ath10k/qmi.c
+++ b/drivers/net/wireless/ath/ath10k/qmi.c
@@ -543,7 +543,7 @@ static int ath10k_qmi_cap_send_sync_msg(struct ath10k_qmi *qmi)
 		goto out;
 
 	if (resp->resp.result != QMI_RESULT_SUCCESS_V01) {
-		ath10k_err(ar, "capablity req rejected: %d\n", resp->resp.error);
+		ath10k_err(ar, "capability req rejected: %d\n", resp->resp.error);
 		ret = -EINVAL;
 		goto out;
 	}
@@ -623,7 +623,7 @@ static int ath10k_qmi_host_cap_send_sync(struct ath10k_qmi *qmi)
 		goto out;
 	}
 
-	ath10k_dbg(ar, ATH10K_DBG_QMI, "qmi host capablity request completed\n");
+	ath10k_dbg(ar, ATH10K_DBG_QMI, "qmi host capability request completed\n");
 	return 0;
 
 out:
@@ -657,7 +657,7 @@ ath10k_qmi_ind_register_send_sync_msg(struct ath10k_qmi *qmi)
 			       wlfw_ind_register_req_msg_v01_ei, &req);
 	if (ret < 0) {
 		qmi_txn_cancel(&txn);
-		ath10k_err(ar, "failed to send indication registed request: %d\n", ret);
+		ath10k_err(ar, "failed to send indication registered request: %d\n", ret);
 		goto out;
 	}
 
-- 
cgit v1.2.3


From 3468404f78e16208ca534cca9bb8e80425eb70ce Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 19 Oct 2018 12:20:26 +0000
Subject: ath10k: remove set but not used variable 'tlv_len'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/wireless/ath/ath10k/wmi-tlv.c: In function 'ath10k_wmi_tlv_op_gen_config_pno_start':
drivers/net/wireless/ath/ath10k/wmi-tlv.c:3455:6: warning:
 variable 'tlv_len' set but not used [-Wunused-but-set-variable]

It never used since inroduction in commit
ce834e280f2f ("ath10k: support NET_DETECT WoWLAN feature")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/wmi-tlv.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index 07c4a33d56b5..ad4114a88170 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -3455,7 +3455,6 @@ ath10k_wmi_tlv_op_gen_config_pno_start(struct ath10k *ar,
 	struct wmi_tlv *tlv;
 	struct sk_buff *skb;
 	__le32 *channel_list;
-	u16 tlv_len;
 	size_t len;
 	void *ptr;
 	u32 i;
@@ -3513,8 +3512,6 @@ ath10k_wmi_tlv_op_gen_config_pno_start(struct ath10k *ar,
 	/* nlo_configured_parameters(nlo_list) */
 	cmd->no_of_ssids = __cpu_to_le32(min_t(u8, pno->uc_networks_count,
 					       WMI_NLO_MAX_SSIDS));
-	tlv_len = __le32_to_cpu(cmd->no_of_ssids) *
-		sizeof(struct nlo_configured_parameters);
 
 	tlv = ptr;
 	tlv->tag = __cpu_to_le16(WMI_TLV_TAG_ARRAY_STRUCT);
-- 
cgit v1.2.3


From 604e986700721a4371546d0a356e00bc5ba46806 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:37:38 +0200
Subject: ath9k: ar5008_phy: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1056532 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/ar5008_phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/ar5008_phy.c b/drivers/net/wireless/ath/ath9k/ar5008_phy.c
index 11d6f975c87d..dae95402eb3a 100644
--- a/drivers/net/wireless/ath/ath9k/ar5008_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar5008_phy.c
@@ -586,7 +586,7 @@ static void ar5008_hw_init_chain_masks(struct ath_hw *ah)
 			REG_WRITE(ah, AR_PHY_CAL_CHAINMASK, 0x7);
 			break;
 		}
-		/* else: fall through */
+		/* fall through */
 	case 0x1:
 	case 0x2:
 	case 0x7:
-- 
cgit v1.2.3


From f2a881055094444da9f7c5a9609b261bba8634a9 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:38:11 +0200
Subject: ath9k: ar9002_phy: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1056532 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/ar9002_phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/ar9002_phy.c b/drivers/net/wireless/ath/ath9k/ar9002_phy.c
index 713291881208..6f32b8d2ec7f 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_phy.c
@@ -119,7 +119,7 @@ static int ar9002_hw_set_channel(struct ath_hw *ah, struct ath9k_channel *chan)
 				aModeRefSel = 2;
 			if (aModeRefSel)
 				break;
-			/* else: fall through */
+			/* fall through */
 		case 1:
 		default:
 			aModeRefSel = 0;
-- 
cgit v1.2.3


From bf74fd75137dd1fa9b95b82c49866e6608fb4990 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:39:15 +0200
Subject: ath9k: hw: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1056532 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/hw.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index bb319f22761f..8581d917635a 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -2279,6 +2279,7 @@ void ath9k_hw_beaconinit(struct ath_hw *ah, u32 next_beacon, u32 beacon_period)
 	case NL80211_IFTYPE_ADHOC:
 		REG_SET_BIT(ah, AR_TXCFG,
 			    AR_TXCFG_ADHOC_BEACON_ATIM_TX_POLICY);
+		/* fall through */
 	case NL80211_IFTYPE_MESH_POINT:
 	case NL80211_IFTYPE_AP:
 		REG_WRITE(ah, AR_NEXT_TBTT_TIMER, next_beacon);
-- 
cgit v1.2.3


From 53d76f1687ba7e4e4e1daa097d90ce6bf2f540d4 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Tue, 23 Oct 2018 11:27:14 +0800
Subject: ath9k: remove set but not used variable 'new_flags'

new_flags is not used after setting its value. It is safe to remove
the unused variable.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/ar9003_mci.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/ar9003_mci.c b/drivers/net/wireless/ath/ath9k/ar9003_mci.c
index 0fe9c8378249..9899661f9a60 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_mci.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_mci.c
@@ -1055,17 +1055,15 @@ void ar9003_mci_stop_bt(struct ath_hw *ah, bool save_fullsleep)
 static void ar9003_mci_send_2g5g_status(struct ath_hw *ah, bool wait_done)
 {
 	struct ath9k_hw_mci *mci = &ah->btcoex_hw.mci;
-	u32 new_flags, to_set, to_clear;
+	u32 to_set, to_clear;
 
 	if (!mci->update_2g5g || (mci->bt_state == MCI_BT_SLEEP))
 		return;
 
 	if (mci->is_2g) {
-		new_flags = MCI_2G_FLAGS;
 		to_clear = MCI_2G_FLAGS_CLEAR_MASK;
 		to_set = MCI_2G_FLAGS_SET_MASK;
 	} else {
-		new_flags = MCI_5G_FLAGS;
 		to_clear = MCI_5G_FLAGS_CLEAR_MASK;
 		to_set = MCI_5G_FLAGS_SET_MASK;
 	}
-- 
cgit v1.2.3


From 6d9e1ecd15373c4fff03e2066581e2374c0e1e61 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:37:31 +0200
Subject: ath6kl: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 201383 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Steve deRosier <derosier@cal-sierra.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath6kl/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath6kl/main.c b/drivers/net/wireless/ath/ath6kl/main.c
index cb59016c723b..5e7ea838a921 100644
--- a/drivers/net/wireless/ath/ath6kl/main.c
+++ b/drivers/net/wireless/ath/ath6kl/main.c
@@ -389,6 +389,7 @@ void ath6kl_connect_ap_mode_bss(struct ath6kl_vif *vif, u16 channel)
 		if (!ik->valid || ik->key_type != WAPI_CRYPT)
 			break;
 		/* for WAPI, we need to set the delayed group key, continue: */
+		/* fall through */
 	case WPA_PSK_AUTH:
 	case WPA2_PSK_AUTH:
 	case (WPA_PSK_AUTH | WPA2_PSK_AUTH):
-- 
cgit v1.2.3


From 003161445bc8ec38882e571916b0c2c495277297 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:39:59 +0200
Subject: carl9170: rx: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1056534 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/carl9170/rx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/carl9170/rx.c b/drivers/net/wireless/ath/carl9170/rx.c
index 705063259c8f..f7c2f19e81c1 100644
--- a/drivers/net/wireless/ath/carl9170/rx.c
+++ b/drivers/net/wireless/ath/carl9170/rx.c
@@ -766,6 +766,7 @@ static void carl9170_rx_untie_data(struct ar9170 *ar, u8 *buf, int len)
 
 			goto drop;
 		}
+		/* fall through */
 
 	case AR9170_RX_STATUS_MPDU_MIDDLE:
 		/*  These are just data + mac status */
-- 
cgit v1.2.3


From f458f9f4369086e86f0cdedf9aae86a525da0736 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:40:24 +0200
Subject: carl9170: tx: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/carl9170/tx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/ath/carl9170/tx.c b/drivers/net/wireless/ath/carl9170/tx.c
index 8c75651ede6c..2407931440ed 100644
--- a/drivers/net/wireless/ath/carl9170/tx.c
+++ b/drivers/net/wireless/ath/carl9170/tx.c
@@ -830,10 +830,12 @@ static bool carl9170_tx_rts_check(struct ar9170 *ar,
 	case CARL9170_ERP_AUTO:
 		if (ampdu)
 			break;
+		/* fall through */
 
 	case CARL9170_ERP_MAC80211:
 		if (!(rate->flags & IEEE80211_TX_RC_USE_RTS_CTS))
 			break;
+		/* fall through */
 
 	case CARL9170_ERP_RTS:
 		if (likely(!multi))
@@ -854,6 +856,7 @@ static bool carl9170_tx_cts_check(struct ar9170 *ar,
 	case CARL9170_ERP_MAC80211:
 		if (!(rate->flags & IEEE80211_TX_RC_USE_CTS_PROTECT))
 			break;
+		/* fall through */
 
 	case CARL9170_ERP_CTS:
 		return true;
-- 
cgit v1.2.3


From c8cb09644c6cc78aaccfca54ad76462e44486cd0 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Thu, 1 Nov 2018 11:29:32 -0400
Subject: ath10k: fix some typo

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/wow.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/wow.c b/drivers/net/wireless/ath/ath10k/wow.c
index 51b26b305885..36d4245c308e 100644
--- a/drivers/net/wireless/ath/ath10k/wow.c
+++ b/drivers/net/wireless/ath/ath10k/wow.c
@@ -135,7 +135,7 @@ static void ath10k_wow_convert_8023_to_80211
 	       &old_hdr_mask->h_proto,
 	       sizeof(old_hdr_mask->h_proto));
 
-	/* Caculate new pkt_offset */
+	/* Calculate new pkt_offset */
 	if (old->pkt_offset < ETH_ALEN)
 		new->pkt_offset = old->pkt_offset +
 			offsetof(struct ieee80211_hdr_3addr, addr1);
@@ -146,7 +146,7 @@ static void ath10k_wow_convert_8023_to_80211
 	else
 		new->pkt_offset = old->pkt_offset + hdr_len + rfc_len - ETH_HLEN;
 
-	/* Caculate new hdr end offset */
+	/* Calculate new hdr end offset */
 	if (total_len > ETH_HLEN)
 		hdr_80211_end_offset = hdr_len + rfc_len;
 	else if (total_len > offsetof(struct ethhdr, h_proto))
-- 
cgit v1.2.3


From a078c4cf0197c71a829ea927d1287e6b26a52c92 Mon Sep 17 00:00:00 2001
From: Hamad Kadmany <hkadmany@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:09 +0200
Subject: wil6210: remove fake support for RXHASH

Setting the same fake hash to all skbs prevents
distributing different flows to different CPU cores.

Signed-off-by: Hamad Kadmany <hkadmany@codeaurora.org>
Signed-off-by: Lior David <liord@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/netdev.c | 3 +--
 drivers/net/wireless/ath/wil6210/txrx.c   | 8 --------
 2 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/netdev.c b/drivers/net/wireless/ath/wil6210/netdev.c
index 7a78a06bd356..64fa1a295510 100644
--- a/drivers/net/wireless/ath/wil6210/netdev.c
+++ b/drivers/net/wireless/ath/wil6210/netdev.c
@@ -345,8 +345,7 @@ wil_vif_alloc(struct wil6210_priv *wil, const char *name,
 	ndev->ieee80211_ptr = wdev;
 	ndev->hw_features = NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
 			    NETIF_F_SG | NETIF_F_GRO |
-			    NETIF_F_TSO | NETIF_F_TSO6 |
-			    NETIF_F_RXHASH;
+			    NETIF_F_TSO | NETIF_F_TSO6;
 
 	ndev->features |= ndev->hw_features;
 	SET_NETDEV_DEV(ndev, wiphy_dev(wdev->wiphy));
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index cc5f263cc965..70eceec9945e 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -743,14 +743,6 @@ void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
 
 	stats = &wil->sta[cid].stats;
 
-	if (ndev->features & NETIF_F_RXHASH)
-		/* fake L4 to ensure it won't be re-calculated later
-		 * set hash to any non-zero value to activate rps
-		 * mechanism, core will be chosen according
-		 * to user-level rps configuration.
-		 */
-		skb_set_hash(skb, 1, PKT_HASH_TYPE_L4);
-
 	skb_orphan(skb);
 
 	if (security && (wil->txrx_ops.rx_crypto_check(wil, skb) != 0)) {
-- 
cgit v1.2.3


From d083b2e2b7db5cca1791643d036e6597af27f49b Mon Sep 17 00:00:00 2001
From: Alexei Avshalom Lazar <ailizaro@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:10 +0200
Subject: wil6210: fix reset flow for Talyn-mb

With current reset flow, Talyn sometimes get stuck causing PCIe
enumeration to fail. Fix this by removing some reset flow operations
that are not relevant for Talyn.
Setting bit 15 in RGF_HP_CTRL is WBE specific and is not in use for
all wil6210 devices.
For Sparrow, BIT_HPAL_PERST_FROM_PAD and BIT_CAR_PERST_RST were set
as a WA an HW issue.

Signed-off-by: Alexei Avshalom Lazar <ailizaro@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/main.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 398900a1c29e..c54b008996ee 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -998,10 +998,13 @@ static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
 
 	wil_dbg_misc(wil, "Resetting \"%s\"...\n", wil->hw_name);
 
-	/* Clear MAC link up */
-	wil_s(wil, RGF_HP_CTRL, BIT(15));
-	wil_s(wil, RGF_USER_CLKS_CTL_SW_RST_MASK_0, BIT_HPAL_PERST_FROM_PAD);
-	wil_s(wil, RGF_USER_CLKS_CTL_SW_RST_MASK_0, BIT_CAR_PERST_RST);
+	if (wil->hw_version < HW_VER_TALYN) {
+		/* Clear MAC link up */
+		wil_s(wil, RGF_HP_CTRL, BIT(15));
+		wil_s(wil, RGF_USER_CLKS_CTL_SW_RST_MASK_0,
+		      BIT_HPAL_PERST_FROM_PAD);
+		wil_s(wil, RGF_USER_CLKS_CTL_SW_RST_MASK_0, BIT_CAR_PERST_RST);
+	}
 
 	wil_halt_cpu(wil);
 
-- 
cgit v1.2.3


From cbebe277beb1169a157d5f486c87f5ceabf0bf82 Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:11 +0200
Subject: wil6210: increase RX rings and RX buff array size

In Talyn-MB, the 11ad throughput is higher and performance drops
may occur in the current RX configuration due to unavailability
of Rx buffers.
Increase the RX descriptor ring, RX status ring and number of RX
buffers to stabilize the performance in high throughput.

Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/main.c      | 7 ++++++-
 drivers/net/wireless/ath/wil6210/txrx_edma.c | 4 ++--
 drivers/net/wireless/ath/wil6210/txrx_edma.h | 4 ++--
 drivers/net/wireless/ath/wil6210/wil6210.h   | 1 +
 4 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index c54b008996ee..078ad5cf664c 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -80,7 +80,7 @@ static const struct kernel_param_ops mtu_max_ops = {
 module_param_cb(mtu_max, &mtu_max_ops, &mtu_max, 0444);
 MODULE_PARM_DESC(mtu_max, " Max MTU value.");
 
-static uint rx_ring_order = WIL_RX_RING_SIZE_ORDER_DEFAULT;
+static uint rx_ring_order;
 static uint tx_ring_order = WIL_TX_RING_SIZE_ORDER_DEFAULT;
 static uint bcast_ring_order = WIL_BCAST_RING_SIZE_ORDER_DEFAULT;
 
@@ -1684,6 +1684,11 @@ int __wil_up(struct wil6210_priv *wil)
 		return rc;
 
 	/* Rx RING. After MAC and beacon */
+	if (rx_ring_order == 0)
+		rx_ring_order = wil->hw_version < HW_VER_TALYN_MB ?
+			WIL_RX_RING_SIZE_ORDER_DEFAULT :
+			WIL_RX_RING_SIZE_ORDER_TALYN_DEFAULT;
+
 	rc = wil->txrx_ops.rx_init(wil, 1 << rx_ring_order);
 	if (rc)
 		return rc;
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index 2bbae75b9a84..ce713588a547 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -357,8 +357,8 @@ static int wil_init_rx_sring(struct wil6210_priv *wil,
 	struct wil_status_ring *sring = &wil->srings[ring_id];
 	int rc;
 
-	wil_dbg_misc(wil, "init RX sring: size=%u, ring_id=%u\n", sring->size,
-		     ring_id);
+	wil_dbg_misc(wil, "init RX sring: size=%u, ring_id=%u\n",
+		     status_ring_size, ring_id);
 
 	memset(&sring->rx_data, 0, sizeof(sring->rx_data));
 
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.h b/drivers/net/wireless/ath/wil6210/txrx_edma.h
index a7fe9292fda3..343516a03a1e 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.h
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.h
@@ -23,9 +23,9 @@
 #define WIL_SRING_SIZE_ORDER_MIN	(WIL_RING_SIZE_ORDER_MIN)
 #define WIL_SRING_SIZE_ORDER_MAX	(WIL_RING_SIZE_ORDER_MAX)
 /* RX sring order should be bigger than RX ring order */
-#define WIL_RX_SRING_SIZE_ORDER_DEFAULT	(11)
+#define WIL_RX_SRING_SIZE_ORDER_DEFAULT	(12)
 #define WIL_TX_SRING_SIZE_ORDER_DEFAULT	(12)
-#define WIL_RX_BUFF_ARR_SIZE_DEFAULT (1536)
+#define WIL_RX_BUFF_ARR_SIZE_DEFAULT (2600)
 
 #define WIL_DEFAULT_RX_STATUS_RING_ID 0
 #define WIL_RX_DESC_RING_ID 0
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index abb82018d3b4..414de541abd0 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -81,6 +81,7 @@ static inline u32 WIL_GET_BITS(u32 x, int b0, int b1)
 
 #define WIL_TX_Q_LEN_DEFAULT		(4000)
 #define WIL_RX_RING_SIZE_ORDER_DEFAULT	(10)
+#define WIL_RX_RING_SIZE_ORDER_TALYN_DEFAULT	(11)
 #define WIL_TX_RING_SIZE_ORDER_DEFAULT	(12)
 #define WIL_BCAST_RING_SIZE_ORDER_DEFAULT	(7)
 #define WIL_BCAST_MCS0_LIMIT		(1024) /* limit for MCS0 frame size */
-- 
cgit v1.2.3


From 61e5ec044748486f06dec760a19dce78247b3ad8 Mon Sep 17 00:00:00 2001
From: Dedy Lansky <dlansky@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:12 +0200
Subject: wil6210: make sure Rx ring sizes are correlated

When enlarging rx_ring_order module param, wil6210 fails to load
because there are not enough Rx buffers.
Fix this by enlarging number of Rx buffers at startup, if needed based
on rx_ring_order.

Signed-off-by: Dedy Lansky <dlansky@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/main.c      |  2 +-
 drivers/net/wireless/ath/wil6210/txrx.c      |  4 ++--
 drivers/net/wireless/ath/wil6210/txrx_edma.c | 11 ++++++++---
 drivers/net/wireless/ath/wil6210/wil6210.h   |  2 +-
 4 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 078ad5cf664c..55084770433c 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -1689,7 +1689,7 @@ int __wil_up(struct wil6210_priv *wil)
 			WIL_RX_RING_SIZE_ORDER_DEFAULT :
 			WIL_RX_RING_SIZE_ORDER_TALYN_DEFAULT;
 
-	rc = wil->txrx_ops.rx_init(wil, 1 << rx_ring_order);
+	rc = wil->txrx_ops.rx_init(wil, rx_ring_order);
 	if (rc)
 		return rc;
 
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index 70eceec9945e..c592c8e42abc 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -872,7 +872,7 @@ static void wil_rx_buf_len_init(struct wil6210_priv *wil)
 	}
 }
 
-static int wil_rx_init(struct wil6210_priv *wil, u16 size)
+static int wil_rx_init(struct wil6210_priv *wil, uint order)
 {
 	struct wil_ring *vring = &wil->ring_rx;
 	int rc;
@@ -886,7 +886,7 @@ static int wil_rx_init(struct wil6210_priv *wil, u16 size)
 
 	wil_rx_buf_len_init(wil);
 
-	vring->size = size;
+	vring->size = 1 << order;
 	vring->is_rx = true;
 	rc = wil_vring_alloc(wil, vring);
 	if (rc)
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index ce713588a547..fe758f24b448 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -606,9 +606,9 @@ static void wil_rx_buf_len_init_edma(struct wil6210_priv *wil)
 		WIL_MAX_ETH_MTU : WIL_EDMA_RX_BUF_LEN_DEFAULT;
 }
 
-static int wil_rx_init_edma(struct wil6210_priv *wil, u16 desc_ring_size)
+static int wil_rx_init_edma(struct wil6210_priv *wil, uint desc_ring_order)
 {
-	u16 status_ring_size;
+	u16 status_ring_size, desc_ring_size = 1 << desc_ring_order;
 	struct wil_ring *ring = &wil->ring_rx;
 	int rc;
 	size_t elem_size = wil->use_compressed_rx_status ?
@@ -623,7 +623,12 @@ static int wil_rx_init_edma(struct wil6210_priv *wil, u16 desc_ring_size)
 			"compressed RX status cannot be used with SW reorder\n");
 		return -EINVAL;
 	}
-
+	if (wil->rx_status_ring_order <= desc_ring_order)
+		/* make sure sring is larger than desc ring */
+		wil->rx_status_ring_order = desc_ring_order + 1;
+	if (wil->rx_buff_id_count <= desc_ring_size)
+		/* make sure we will not run out of buff_ids */
+		wil->rx_buff_id_count = desc_ring_size + 512;
 	if (wil->rx_status_ring_order < WIL_SRING_SIZE_ORDER_MIN ||
 	    wil->rx_status_ring_order > WIL_SRING_SIZE_ORDER_MAX)
 		wil->rx_status_ring_order = WIL_RX_SRING_SIZE_ORDER_DEFAULT;
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 414de541abd0..31753f941708 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -614,7 +614,7 @@ struct wil_txrx_ops {
 			      int cid, int tid);
 	irqreturn_t (*irq_tx)(int irq, void *cookie);
 	/* RX ops */
-	int (*rx_init)(struct wil6210_priv *wil, u16 ring_size);
+	int (*rx_init)(struct wil6210_priv *wil, uint ring_order);
 	void (*rx_fini)(struct wil6210_priv *wil);
 	int (*wmi_addba_rx_resp)(struct wil6210_priv *wil, u8 mid, u8 cid,
 				 u8 tid, u8 token, u16 status, bool amsdu,
-- 
cgit v1.2.3


From e41ab937d47b3c1180057f72968bf62b487fc80f Mon Sep 17 00:00:00 2001
From: Dedy Lansky <dlansky@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:13 +0200
Subject: wil6210: add recovery for FW error while in AP mode

AP configuration is stored by the driver. Upon FW error, disconnect
notification is sent to user space for any associated stations. AP is
then internally restarted with the stored configuration.

Signed-off-by: Dedy Lansky <dlansky@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/cfg80211.c | 102 ++++++++++++++++++++++++++--
 drivers/net/wireless/ath/wil6210/main.c     |  17 ++++-
 drivers/net/wireless/ath/wil6210/wil6210.h  |   9 +++
 3 files changed, 120 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index d18e81fae5f1..e9135d62756e 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -51,6 +51,19 @@ static struct ieee80211_channel wil_60ghz_channels[] = {
 	CHAN60G(4, 0),
 };
 
+static void
+wil_memdup_ie(u8 **pdst, size_t *pdst_len, const u8 *src, size_t src_len)
+{
+	kfree(*pdst);
+	*pdst = NULL;
+	*pdst_len = 0;
+	if (src_len > 0) {
+		*pdst = kmemdup(src, src_len, GFP_KERNEL);
+		if (*pdst)
+			*pdst_len = src_len;
+	}
+}
+
 static int wil_num_supported_channels(struct wil6210_priv *wil)
 {
 	int num_channels = ARRAY_SIZE(wil_60ghz_channels);
@@ -1441,11 +1454,19 @@ static int wil_cfg80211_add_key(struct wiphy *wiphy,
 
 	rc = wmi_add_cipher_key(vif, key_index, mac_addr, params->key_len,
 				params->key, key_usage);
-	if (!rc && !IS_ERR(cs))
+	if (!rc && !IS_ERR(cs)) {
+		/* update local storage used for AP recovery */
+		if (key_usage == WMI_KEY_USE_TX_GROUP && params->key &&
+		    params->key_len <= WMI_MAX_KEY_LEN) {
+			vif->gtk_index = key_index;
+			memcpy(vif->gtk, params->key, params->key_len);
+			vif->gtk_len = params->key_len;
+		}
 		/* in FT set crypto will take place upon receiving
 		 * WMI_RING_EN_EVENTID event
 		 */
 		wil_set_crypto_rx(key_index, key_usage, cs, params);
+	}
 
 	return rc;
 }
@@ -1634,6 +1655,14 @@ static int _wil_cfg80211_set_ies(struct wil6210_vif *vif,
 	u16 len = 0, proberesp_len = 0;
 	u8 *ies = NULL, *proberesp;
 
+	/* update local storage used for AP recovery */
+	wil_memdup_ie(&vif->proberesp, &vif->proberesp_len, bcon->probe_resp,
+		      bcon->probe_resp_len);
+	wil_memdup_ie(&vif->proberesp_ies, &vif->proberesp_ies_len,
+		      bcon->proberesp_ies, bcon->proberesp_ies_len);
+	wil_memdup_ie(&vif->assocresp_ies, &vif->assocresp_ies_len,
+		      bcon->assocresp_ies, bcon->assocresp_ies_len);
+
 	proberesp = _wil_cfg80211_get_proberesp_ies(bcon->probe_resp,
 						    bcon->probe_resp_len,
 						    &proberesp_len);
@@ -1735,6 +1764,9 @@ static int _wil_cfg80211_start_ap(struct wiphy *wiphy,
 	vif->channel = chan;
 	vif->hidden_ssid = hidden_ssid;
 	vif->pbss = pbss;
+	vif->bi = bi;
+	memcpy(vif->ssid, ssid, ssid_len);
+	vif->ssid_len = ssid_len;
 
 	netif_carrier_on(ndev);
 	if (!wil_has_other_active_ifaces(wil, ndev, false, true))
@@ -1761,11 +1793,64 @@ out:
 	return rc;
 }
 
+void wil_cfg80211_ap_recovery(struct wil6210_priv *wil)
+{
+	int rc, i;
+	struct wiphy *wiphy = wil_to_wiphy(wil);
+
+	for (i = 0; i < wil->max_vifs; i++) {
+		struct wil6210_vif *vif = wil->vifs[i];
+		struct net_device *ndev;
+		struct cfg80211_beacon_data bcon = {};
+		struct key_params key_params = {};
+
+		if (!vif || vif->ssid_len == 0)
+			continue;
+
+		ndev = vif_to_ndev(vif);
+		bcon.proberesp_ies = vif->proberesp_ies;
+		bcon.assocresp_ies = vif->assocresp_ies;
+		bcon.probe_resp = vif->proberesp;
+		bcon.proberesp_ies_len = vif->proberesp_ies_len;
+		bcon.assocresp_ies_len = vif->assocresp_ies_len;
+		bcon.probe_resp_len = vif->proberesp_len;
+
+		wil_info(wil,
+			 "AP (vif %d) recovery: privacy %d, bi %d, channel %d, hidden %d, pbss %d\n",
+			 i, vif->privacy, vif->bi, vif->channel,
+			 vif->hidden_ssid, vif->pbss);
+		wil_hex_dump_misc("SSID ", DUMP_PREFIX_OFFSET, 16, 1,
+				  vif->ssid, vif->ssid_len, true);
+		rc = _wil_cfg80211_start_ap(wiphy, ndev,
+					    vif->ssid, vif->ssid_len,
+					    vif->privacy, vif->bi,
+					    vif->channel, &bcon,
+					    vif->hidden_ssid, vif->pbss);
+		if (rc) {
+			wil_err(wil, "vif %d recovery failed (%d)\n", i, rc);
+			continue;
+		}
+
+		if (!vif->privacy || vif->gtk_len == 0)
+			continue;
+
+		key_params.key = vif->gtk;
+		key_params.key_len = vif->gtk_len;
+		key_params.seq_len = IEEE80211_GCMP_PN_LEN;
+		rc = wil_cfg80211_add_key(wiphy, ndev, vif->gtk_index, false,
+					  NULL, &key_params);
+		if (rc)
+			wil_err(wil, "vif %d recovery add key failed (%d)\n",
+				i, rc);
+	}
+}
+
 static int wil_cfg80211_change_beacon(struct wiphy *wiphy,
 				      struct net_device *ndev,
 				      struct cfg80211_beacon_data *bcon)
 {
 	struct wil6210_priv *wil = wiphy_to_wil(wiphy);
+	struct wireless_dev *wdev = ndev->ieee80211_ptr;
 	struct wil6210_vif *vif = ndev_to_vif(ndev);
 	int rc;
 	u32 privacy = 0;
@@ -1778,15 +1863,16 @@ static int wil_cfg80211_change_beacon(struct wiphy *wiphy,
 			     bcon->tail_len))
 		privacy = 1;
 
+	memcpy(vif->ssid, wdev->ssid, wdev->ssid_len);
+	vif->ssid_len = wdev->ssid_len;
+
 	/* in case privacy has changed, need to restart the AP */
 	if (vif->privacy != privacy) {
-		struct wireless_dev *wdev = ndev->ieee80211_ptr;
-
 		wil_dbg_misc(wil, "privacy changed %d=>%d. Restarting AP\n",
 			     vif->privacy, privacy);
 
-		rc = _wil_cfg80211_start_ap(wiphy, ndev, wdev->ssid,
-					    wdev->ssid_len, privacy,
+		rc = _wil_cfg80211_start_ap(wiphy, ndev, vif->ssid,
+					    vif->ssid_len, privacy,
 					    wdev->beacon_interval,
 					    vif->channel, bcon,
 					    vif->hidden_ssid,
@@ -1876,6 +1962,12 @@ static int wil_cfg80211_stop_ap(struct wiphy *wiphy,
 
 	wmi_pcp_stop(vif);
 	clear_bit(wil_vif_ft_roam, vif->status);
+	vif->ssid_len = 0;
+	wil_memdup_ie(&vif->proberesp, &vif->proberesp_len, NULL, 0);
+	wil_memdup_ie(&vif->proberesp_ies, &vif->proberesp_ies_len, NULL, 0);
+	wil_memdup_ie(&vif->assocresp_ies, &vif->assocresp_ies_len, NULL, 0);
+	memset(vif->gtk, 0, WMI_MAX_KEY_LEN);
+	vif->gtk_len = 0;
 
 	if (last)
 		__wil_down(wil);
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 55084770433c..2b328c197274 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -18,6 +18,7 @@
 #include <linux/moduleparam.h>
 #include <linux/if_arp.h>
 #include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
 
 #include "wil6210.h"
 #include "txrx.h"
@@ -485,10 +486,11 @@ static void wil_fw_error_worker(struct work_struct *work)
 	if (wil_wait_for_recovery(wil) != 0)
 		return;
 
+	rtnl_lock();
 	mutex_lock(&wil->mutex);
 	/* Needs adaptation for multiple VIFs
 	 * need to go over all VIFs and consider the appropriate
-	 * recovery.
+	 * recovery because each one can have different iftype.
 	 */
 	switch (wdev->iftype) {
 	case NL80211_IFTYPE_STATION:
@@ -500,15 +502,24 @@ static void wil_fw_error_worker(struct work_struct *work)
 		break;
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_P2P_GO:
-		wil_info(wil, "No recovery for AP-like interface\n");
-		/* recovery in these modes is done by upper layers */
+		if (no_fw_recovery) /* upper layers do recovery */
+			break;
+		/* silent recovery, upper layers will see disconnect */
+		__wil_down(wil);
+		__wil_up(wil);
+		mutex_unlock(&wil->mutex);
+		wil_cfg80211_ap_recovery(wil);
+		mutex_lock(&wil->mutex);
+		wil_info(wil, "... completed\n");
 		break;
 	default:
 		wil_err(wil, "No recovery - unknown interface type %d\n",
 			wdev->iftype);
 		break;
 	}
+
 	mutex_unlock(&wil->mutex);
+	rtnl_unlock();
 }
 
 static int wil_find_free_ring(struct wil6210_priv *wil)
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 31753f941708..8050c4bc5385 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -849,6 +849,14 @@ struct wil6210_vif {
 	u8 hidden_ssid; /* relevant in AP mode */
 	u32 ap_isolate; /* no intra-BSS communication */
 	bool pbss;
+	int bi;
+	u8 *proberesp, *proberesp_ies, *assocresp_ies;
+	size_t proberesp_len, proberesp_ies_len, assocresp_ies_len;
+	u8 ssid[IEEE80211_MAX_SSID_LEN];
+	size_t ssid_len;
+	u8 gtk_index;
+	u8 gtk[WMI_MAX_KEY_LEN];
+	size_t gtk_len;
 	int bcast_ring;
 	struct cfg80211_bss *bss; /* connected bss, relevant in STA mode */
 	int locally_generated_disc; /* relevant in STA mode */
@@ -1277,6 +1285,7 @@ int wmi_stop_discovery(struct wil6210_vif *vif);
 int wil_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 			 struct cfg80211_mgmt_tx_params *params,
 			 u64 *cookie);
+void wil_cfg80211_ap_recovery(struct wil6210_priv *wil);
 int wil_cfg80211_iface_combinations_from_fw(
 	struct wil6210_priv *wil,
 	const struct wil_fw_record_concurrency *conc);
-- 
cgit v1.2.3


From 664497400c89a4d40aee51bcf48bbd2e4dc71104 Mon Sep 17 00:00:00 2001
From: Lior David <liord@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:14 +0200
Subject: wil6210: fix memory leak in wil_find_tx_bcast_2

A successful call to wil_tx_ring takes skb reference so
it will only be freed in wil_tx_complete. Consume the skb
in wil_find_tx_bcast_2 to prevent memory leak.

Signed-off-by: Lior David <liord@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/txrx.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index c592c8e42abc..3e1c831ab2fb 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -1395,6 +1395,8 @@ found:
 			wil_dbg_txrx(wil, "BCAST DUP -> ring %d\n", i);
 			wil_set_da_for_vring(wil, skb2, i);
 			wil_tx_ring(wil, vif, v2, skb2);
+			/* successful call to wil_tx_ring takes skb2 ref */
+			dev_kfree_skb_any(skb2);
 		} else {
 			wil_err(wil, "skb_copy failed\n");
 		}
-- 
cgit v1.2.3


From e1b43407c034650c11bc597bef319f03b8262b6c Mon Sep 17 00:00:00 2001
From: Ahmad Masri <amasri@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:15 +0200
Subject: wil6210: refactor disconnect flow

Separate sending command to the fw from the event handling function to
simplify the disconnect flow and track the from_event flag correctly.

Signed-off-by: Ahmad Masri <amasri@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/cfg80211.c |   2 +-
 drivers/net/wireless/ath/wil6210/main.c     | 179 +++++++++++++++++++++-------
 drivers/net/wireless/ath/wil6210/netdev.c   |   2 +-
 drivers/net/wireless/ath/wil6210/wil6210.h  |   8 +-
 drivers/net/wireless/ath/wil6210/wmi.c      |  28 ++---
 5 files changed, 147 insertions(+), 72 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index e9135d62756e..9b2f9f543952 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -2015,7 +2015,7 @@ static int wil_cfg80211_del_station(struct wiphy *wiphy,
 		     params->mac, params->reason_code, vif->mid);
 
 	mutex_lock(&wil->mutex);
-	wil6210_disconnect(vif, params->mac, params->reason_code, false);
+	wil6210_disconnect(vif, params->mac, params->reason_code);
 	mutex_unlock(&wil->mutex);
 
 	return 0;
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 2b328c197274..68aca52a68e4 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -215,8 +215,21 @@ static void wil_ring_fini_tx(struct wil6210_priv *wil, int id)
 	wil->txrx_ops.ring_fini_tx(wil, ring);
 }
 
-static void wil_disconnect_cid(struct wil6210_vif *vif, int cid,
-			       u16 reason_code, bool from_event)
+static bool wil_vif_is_connected(struct wil6210_priv *wil, u8 mid)
+{
+	int i;
+
+	for (i = 0; i < WIL6210_MAX_CID; i++) {
+		if (wil->sta[i].mid == mid &&
+		    wil->sta[i].status == wil_sta_connected)
+			return true;
+	}
+
+	return false;
+}
+
+static void wil_disconnect_cid_complete(struct wil6210_vif *vif, int cid,
+					u16 reason_code)
 __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 {
 	uint i;
@@ -227,24 +240,14 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	int min_ring_id = wil_get_min_tx_ring_id(wil);
 
 	might_sleep();
-	wil_dbg_misc(wil, "disconnect_cid: CID %d, MID %d, status %d\n",
+	wil_dbg_misc(wil,
+		     "disconnect_cid_complete: CID %d, MID %d, status %d\n",
 		     cid, sta->mid, sta->status);
-	/* inform upper/lower layers */
+	/* inform upper layers */
 	if (sta->status != wil_sta_unused) {
 		if (vif->mid != sta->mid) {
 			wil_err(wil, "STA MID mismatch with VIF MID(%d)\n",
 				vif->mid);
-			/* let FW override sta->mid but be more strict with
-			 * user space requests
-			 */
-			if (!from_event)
-				return;
-		}
-		if (!from_event) {
-			bool del_sta = (wdev->iftype == NL80211_IFTYPE_AP) ?
-						disable_ap_sme : false;
-			wmi_disconnect_sta(vif, sta->addr, reason_code,
-					   true, del_sta);
 		}
 
 		switch (wdev->iftype) {
@@ -284,36 +287,20 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	sta->stats.tx_latency_min_us = U32_MAX;
 }
 
-static bool wil_vif_is_connected(struct wil6210_priv *wil, u8 mid)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(wil->sta); i++) {
-		if (wil->sta[i].mid == mid &&
-		    wil->sta[i].status == wil_sta_connected)
-			return true;
-	}
-
-	return false;
-}
-
-static void _wil6210_disconnect(struct wil6210_vif *vif, const u8 *bssid,
-				u16 reason_code, bool from_event)
+static void _wil6210_disconnect_complete(struct wil6210_vif *vif,
+					 const u8 *bssid, u16 reason_code)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	int cid = -ENOENT;
 	struct net_device *ndev;
 	struct wireless_dev *wdev;
 
-	if (unlikely(!vif))
-		return;
-
 	ndev = vif_to_ndev(vif);
 	wdev = vif_to_wdev(vif);
 
 	might_sleep();
-	wil_info(wil, "bssid=%pM, reason=%d, ev%s\n", bssid,
-		 reason_code, from_event ? "+" : "-");
+	wil_info(wil, "disconnect_complete: bssid=%pM, reason=%d\n",
+		 bssid, reason_code);
 
 	/* Cases are:
 	 * - disconnect single STA, still connected
@@ -328,14 +315,15 @@ static void _wil6210_disconnect(struct wil6210_vif *vif, const u8 *bssid,
 	if (bssid && !is_broadcast_ether_addr(bssid) &&
 	    !ether_addr_equal_unaligned(ndev->dev_addr, bssid)) {
 		cid = wil_find_cid(wil, vif->mid, bssid);
-		wil_dbg_misc(wil, "Disconnect %pM, CID=%d, reason=%d\n",
+		wil_dbg_misc(wil,
+			     "Disconnect complete %pM, CID=%d, reason=%d\n",
 			     bssid, cid, reason_code);
 		if (cid >= 0) /* disconnect 1 peer */
-			wil_disconnect_cid(vif, cid, reason_code, from_event);
+			wil_disconnect_cid_complete(vif, cid, reason_code);
 	} else { /* all */
-		wil_dbg_misc(wil, "Disconnect all\n");
+		wil_dbg_misc(wil, "Disconnect complete all\n");
 		for (cid = 0; cid < WIL6210_MAX_CID; cid++)
-			wil_disconnect_cid(vif, cid, reason_code, from_event);
+			wil_disconnect_cid_complete(vif, cid, reason_code);
 	}
 
 	/* link state */
@@ -381,6 +369,84 @@ static void _wil6210_disconnect(struct wil6210_vif *vif, const u8 *bssid,
 	}
 }
 
+static int wil_disconnect_cid(struct wil6210_vif *vif, int cid,
+			      u16 reason_code)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct wireless_dev *wdev = vif_to_wdev(vif);
+	struct wil_sta_info *sta = &wil->sta[cid];
+	bool del_sta = false;
+
+	might_sleep();
+	wil_dbg_misc(wil, "disconnect_cid: CID %d, MID %d, status %d\n",
+		     cid, sta->mid, sta->status);
+
+	if (sta->status == wil_sta_unused)
+		return 0;
+
+	if (vif->mid != sta->mid) {
+		wil_err(wil, "STA MID mismatch with VIF MID(%d)\n", vif->mid);
+		return -EINVAL;
+	}
+
+	/* inform lower layers */
+	if (wdev->iftype == NL80211_IFTYPE_AP && disable_ap_sme)
+		del_sta = true;
+
+	/* disconnect by sending command disconnect/del_sta and wait
+	 * synchronously for WMI_DISCONNECT_EVENTID event.
+	 */
+	return wmi_disconnect_sta(vif, sta->addr, reason_code, del_sta);
+}
+
+static void _wil6210_disconnect(struct wil6210_vif *vif, const u8 *bssid,
+				u16 reason_code)
+{
+	struct wil6210_priv *wil;
+	struct net_device *ndev;
+	struct wireless_dev *wdev;
+	int cid = -ENOENT;
+
+	if (unlikely(!vif))
+		return;
+
+	wil = vif_to_wil(vif);
+	ndev = vif_to_ndev(vif);
+	wdev = vif_to_wdev(vif);
+
+	might_sleep();
+	wil_info(wil, "disconnect bssid=%pM, reason=%d\n", bssid, reason_code);
+
+	/* Cases are:
+	 * - disconnect single STA, still connected
+	 * - disconnect single STA, already disconnected
+	 * - disconnect all
+	 *
+	 * For "disconnect all", there are 3 options:
+	 * - bssid == NULL
+	 * - bssid is broadcast address (ff:ff:ff:ff:ff:ff)
+	 * - bssid is our MAC address
+	 */
+	if (bssid && !is_broadcast_ether_addr(bssid) &&
+	    !ether_addr_equal_unaligned(ndev->dev_addr, bssid)) {
+		cid = wil_find_cid(wil, vif->mid, bssid);
+		wil_dbg_misc(wil, "Disconnect %pM, CID=%d, reason=%d\n",
+			     bssid, cid, reason_code);
+		if (cid >= 0) /* disconnect 1 peer */
+			wil_disconnect_cid(vif, cid, reason_code);
+	} else { /* all */
+		wil_dbg_misc(wil, "Disconnect all\n");
+		for (cid = 0; cid < WIL6210_MAX_CID; cid++)
+			wil_disconnect_cid(vif, cid, reason_code);
+	}
+
+	/* call event handler manually after processing wmi_call,
+	 * to avoid deadlock - disconnect event handler acquires
+	 * wil->mutex while it is already held here
+	 */
+	_wil6210_disconnect_complete(vif, bssid, reason_code);
+}
+
 void wil_disconnect_worker(struct work_struct *work)
 {
 	struct wil6210_vif *vif = container_of(work,
@@ -705,20 +771,41 @@ void wil6210_bus_request(struct wil6210_priv *wil, u32 kbps)
  * @vif: virtual interface context
  * @bssid: peer to disconnect, NULL to disconnect all
  * @reason_code: Reason code for the Disassociation frame
- * @from_event: whether is invoked from FW event handler
  *
- * Disconnect and release associated resources. If invoked not from the
- * FW event handler, issue WMI command(s) to trigger MAC disconnect.
+ * Disconnect and release associated resources. Issue WMI
+ * command(s) to trigger MAC disconnect. When command was issued
+ * successfully, call the wil6210_disconnect_complete function
+ * to handle the event synchronously
  */
 void wil6210_disconnect(struct wil6210_vif *vif, const u8 *bssid,
-			u16 reason_code, bool from_event)
+			u16 reason_code)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+
+	wil_dbg_misc(wil, "disconnecting\n");
+
+	del_timer_sync(&vif->connect_timer);
+	_wil6210_disconnect(vif, bssid, reason_code);
+}
+
+/**
+ * wil6210_disconnect_complete - handle disconnect event
+ * @vif: virtual interface context
+ * @bssid: peer to disconnect, NULL to disconnect all
+ * @reason_code: Reason code for the Disassociation frame
+ *
+ * Release associated resources and indicate upper layers the
+ * connection is terminated.
+ */
+void wil6210_disconnect_complete(struct wil6210_vif *vif, const u8 *bssid,
+				 u16 reason_code)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
 
-	wil_dbg_misc(wil, "disconnect\n");
+	wil_dbg_misc(wil, "got disconnect\n");
 
 	del_timer_sync(&vif->connect_timer);
-	_wil6210_disconnect(vif, bssid, reason_code, from_event);
+	_wil6210_disconnect_complete(vif, bssid, reason_code);
 }
 
 void wil_priv_deinit(struct wil6210_priv *wil)
@@ -1525,7 +1612,7 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 		if (vif) {
 			cancel_work_sync(&vif->disconnect_worker);
 			wil6210_disconnect(vif, NULL,
-					   WLAN_REASON_DEAUTH_LEAVING, false);
+					   WLAN_REASON_DEAUTH_LEAVING);
 		}
 	}
 	wil_bcast_fini_all(wil);
diff --git a/drivers/net/wireless/ath/wil6210/netdev.c b/drivers/net/wireless/ath/wil6210/netdev.c
index 64fa1a295510..b4e0eb1585b9 100644
--- a/drivers/net/wireless/ath/wil6210/netdev.c
+++ b/drivers/net/wireless/ath/wil6210/netdev.c
@@ -512,7 +512,7 @@ void wil_vif_remove(struct wil6210_priv *wil, u8 mid)
 	}
 
 	mutex_lock(&wil->mutex);
-	wil6210_disconnect(vif, NULL, WLAN_REASON_DEAUTH_LEAVING, false);
+	wil6210_disconnect(vif, NULL, WLAN_REASON_DEAUTH_LEAVING);
 	mutex_unlock(&wil->mutex);
 
 	ndev = vif_to_ndev(vif);
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 8050c4bc5385..ad7003f350a2 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -1229,8 +1229,8 @@ int wmi_rx_chain_add(struct wil6210_priv *wil, struct wil_ring *vring);
 int wmi_update_ft_ies(struct wil6210_vif *vif, u16 ie_len, const void *ie);
 int wmi_rxon(struct wil6210_priv *wil, bool on);
 int wmi_get_temperature(struct wil6210_priv *wil, u32 *t_m, u32 *t_r);
-int wmi_disconnect_sta(struct wil6210_vif *vif, const u8 *mac,
-		       u16 reason, bool full_disconnect, bool del_sta);
+int wmi_disconnect_sta(struct wil6210_vif *vif, const u8 *mac, u16 reason,
+		       bool del_sta);
 int wmi_addba(struct wil6210_priv *wil, u8 mid,
 	      u8 ringid, u8 size, u16 timeout);
 int wmi_delba_tx(struct wil6210_priv *wil, u8 mid, u8 ringid, u16 reason);
@@ -1316,7 +1316,9 @@ void wil_abort_scan(struct wil6210_vif *vif, bool sync);
 void wil_abort_scan_all_vifs(struct wil6210_priv *wil, bool sync);
 void wil6210_bus_request(struct wil6210_priv *wil, u32 kbps);
 void wil6210_disconnect(struct wil6210_vif *vif, const u8 *bssid,
-			u16 reason_code, bool from_event);
+			u16 reason_code);
+void wil6210_disconnect_complete(struct wil6210_vif *vif, const u8 *bssid,
+				 u16 reason_code);
 void wil_probe_client_flush(struct wil6210_vif *vif);
 void wil_probe_client_worker(struct work_struct *work);
 void wil_disconnect_worker(struct work_struct *work);
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 4859f0e43658..5ff1862460f0 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -1018,7 +1018,7 @@ static void wmi_evt_connect(struct wil6210_vif *vif, int id, void *d, int len)
 		wil_err(wil, "config tx vring failed for CID %d, rc (%d)\n",
 			evt->cid, rc);
 		wmi_disconnect_sta(vif, wil->sta[evt->cid].addr,
-				   WLAN_REASON_UNSPECIFIED, false, false);
+				   WLAN_REASON_UNSPECIFIED, false);
 	} else {
 		wil_info(wil, "successful connection to CID %d\n", evt->cid);
 	}
@@ -1112,7 +1112,7 @@ static void wmi_evt_disconnect(struct wil6210_vif *vif, int id,
 	}
 
 	mutex_lock(&wil->mutex);
-	wil6210_disconnect(vif, evt->bssid, reason_code, true);
+	wil6210_disconnect_complete(vif, evt->bssid, reason_code);
 	mutex_unlock(&wil->mutex);
 }
 
@@ -1637,7 +1637,7 @@ wmi_evt_auth_status(struct wil6210_vif *vif, int id, void *d, int len)
 	return;
 
 fail:
-	wil6210_disconnect(vif, NULL, WLAN_REASON_PREV_AUTH_NOT_VALID, false);
+	wil6210_disconnect(vif, NULL, WLAN_REASON_PREV_AUTH_NOT_VALID);
 }
 
 static void
@@ -1766,7 +1766,7 @@ wmi_evt_reassoc_status(struct wil6210_vif *vif, int id, void *d, int len)
 	return;
 
 fail:
-	wil6210_disconnect(vif, NULL, WLAN_REASON_PREV_AUTH_NOT_VALID, false);
+	wil6210_disconnect(vif, NULL, WLAN_REASON_PREV_AUTH_NOT_VALID);
 }
 
 /**
@@ -2560,12 +2560,11 @@ int wmi_get_temperature(struct wil6210_priv *wil, u32 *t_bb, u32 *t_rf)
 	return 0;
 }
 
-int wmi_disconnect_sta(struct wil6210_vif *vif, const u8 *mac,
-		       u16 reason, bool full_disconnect, bool del_sta)
+int wmi_disconnect_sta(struct wil6210_vif *vif, const u8 *mac, u16 reason,
+		       bool del_sta)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	int rc;
-	u16 reason_code;
 	struct wmi_disconnect_sta_cmd disc_sta_cmd = {
 		.disconnect_reason = cpu_to_le16(reason),
 	};
@@ -2598,21 +2597,8 @@ int wmi_disconnect_sta(struct wil6210_vif *vif, const u8 *mac,
 		wil_fw_error_recovery(wil);
 		return rc;
 	}
+	wil->sinfo_gen++;
 
-	if (full_disconnect) {
-		/* call event handler manually after processing wmi_call,
-		 * to avoid deadlock - disconnect event handler acquires
-		 * wil->mutex while it is already held here
-		 */
-		reason_code = le16_to_cpu(reply.evt.protocol_reason_status);
-
-		wil_dbg_wmi(wil, "Disconnect %pM reason [proto %d wmi %d]\n",
-			    reply.evt.bssid, reason_code,
-			    reply.evt.disconnect_reason);
-
-		wil->sinfo_gen++;
-		wil6210_disconnect(vif, reply.evt.bssid, reason_code, true);
-	}
 	return 0;
 }
 
-- 
cgit v1.2.3


From b571e71bcb98d6b629b486b9af027a73fc6da3c3 Mon Sep 17 00:00:00 2001
From: Ahmad Masri <amasri@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:16 +0200
Subject: wil6210: notify cqm packet loss on disable_ap_sme

wil6210 used to notify cfg80211_del_sta on every fw disconnect event.
In disable_ap_sme mode the userspace manages the protocol SME and
FW sends disconnect event only due to link loss.

In disable_ap_sme mode, indicate CQM packet loss to let the host
control the connection and disconnect the link if needed.

Signed-off-by: Ahmad Masri <amasri@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/wmi.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 5ff1862460f0..fa08a9637f44 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -1113,6 +1113,23 @@ static void wmi_evt_disconnect(struct wil6210_vif *vif, int id,
 
 	mutex_lock(&wil->mutex);
 	wil6210_disconnect_complete(vif, evt->bssid, reason_code);
+	if (disable_ap_sme) {
+		struct wireless_dev *wdev = vif_to_wdev(vif);
+		struct net_device *ndev = vif_to_ndev(vif);
+
+		/* disconnect event in disable_ap_sme mode means link loss */
+		switch (wdev->iftype) {
+		/* AP-like interface */
+		case NL80211_IFTYPE_AP:
+		case NL80211_IFTYPE_P2P_GO:
+			/* notify hostapd about link loss */
+			cfg80211_cqm_pktloss_notify(ndev, evt->bssid, 0,
+						    GFP_KERNEL);
+			break;
+		default:
+			break;
+		}
+	}
 	mutex_unlock(&wil->mutex);
 }
 
-- 
cgit v1.2.3


From ac0e541ab2f2951845acee784ef487be40fb4c77 Mon Sep 17 00:00:00 2001
From: Alexei Avshalom Lazar <ailizaro@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:17 +0200
Subject: wil6210: add general initialization/size checks

Initialize unset variable, and verify that mid is valid.

Signed-off-by: Alexei Avshalom Lazar <ailizaro@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/debugfs.c | 2 ++
 drivers/net/wireless/ath/wil6210/wmi.c     | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index aa50813a0595..099a04b91551 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -962,6 +962,8 @@ static ssize_t wil_write_file_txmgmt(struct file *file, const char __user *buf,
 	int rc;
 	void *frame;
 
+	memset(&params, 0, sizeof(params));
+
 	if (!len)
 		return -EINVAL;
 
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index fa08a9637f44..f46c703ca570 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -3148,7 +3148,7 @@ static void wmi_event_handle(struct wil6210_priv *wil,
 
 		if (mid == MID_BROADCAST)
 			mid = 0;
-		if (mid >= wil->max_vifs) {
+		if (mid >= ARRAY_SIZE(wil->vifs) || mid >= wil->max_vifs) {
 			wil_dbg_wmi(wil, "invalid mid %d, event skipped\n",
 				    mid);
 			return;
-- 
cgit v1.2.3


From 84ec040d0fb25197584d28a0dedc355503cd19b9 Mon Sep 17 00:00:00 2001
From: Ahmad Masri <amasri@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:18 +0200
Subject: wil6210: fix debugfs memory access alignment

All wil6210 device memory access should be 4 bytes aligned. In io
blob wil6210 did not force alignment for read function, this caused
alignment fault on some platforms.
Fixing that by accessing all 4 lower bytes and return to host the
requested data.

Signed-off-by: Ahmad Masri <amasri@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/debugfs.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 099a04b91551..20dd4d070911 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -664,10 +664,10 @@ static ssize_t wil_read_file_ioblob(struct file *file, char __user *user_buf,
 	enum { max_count = 4096 };
 	struct wil_blob_wrapper *wil_blob = file->private_data;
 	struct wil6210_priv *wil = wil_blob->wil;
-	loff_t pos = *ppos;
+	loff_t aligned_pos, pos = *ppos;
 	size_t available = wil_blob->blob.size;
 	void *buf;
-	size_t ret;
+	size_t unaligned_bytes, aligned_count, ret;
 	int rc;
 
 	if (test_bit(wil_status_suspending, wil_blob->wil->status) ||
@@ -685,7 +685,12 @@ static ssize_t wil_read_file_ioblob(struct file *file, char __user *user_buf,
 	if (count > max_count)
 		count = max_count;
 
-	buf = kmalloc(count, GFP_KERNEL);
+	/* set pos to 4 bytes aligned */
+	unaligned_bytes = pos % 4;
+	aligned_pos = pos - unaligned_bytes;
+	aligned_count = count + unaligned_bytes;
+
+	buf = kmalloc(aligned_count, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -696,9 +701,9 @@ static ssize_t wil_read_file_ioblob(struct file *file, char __user *user_buf,
 	}
 
 	wil_memcpy_fromio_32(buf, (const void __iomem *)
-			     wil_blob->blob.data + pos, count);
+			     wil_blob->blob.data + aligned_pos, aligned_count);
 
-	ret = copy_to_user(user_buf, buf, count);
+	ret = copy_to_user(user_buf, buf + unaligned_bytes, count);
 
 	wil_pm_runtime_put(wil);
 
-- 
cgit v1.2.3


From 04de15010aa42a92add66b159e3ae44b4287390f Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:19 +0200
Subject: wil6210: fix L2 RX status handling

L2 RX status errors should not be treated as a bitmap and the actual
error values should be checked.
Print L2 errors as wil_err_ratelimited for easier debugging
when such errors occurs.

Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/txrx_edma.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index fe758f24b448..c8490e727e6c 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -839,23 +839,24 @@ static int wil_rx_error_check_edma(struct wil6210_priv *wil,
 		wil_dbg_txrx(wil, "L2 RX error, l2_rx_status=0x%x\n",
 			     l2_rx_status);
 		/* Due to HW issue, KEY error will trigger a MIC error */
-		if (l2_rx_status & WIL_RX_EDMA_ERROR_MIC) {
-			wil_dbg_txrx(wil,
-				     "L2 MIC/KEY error, dropping packet\n");
+		if (l2_rx_status == WIL_RX_EDMA_ERROR_MIC) {
+			wil_err_ratelimited(wil,
+					    "L2 MIC/KEY error, dropping packet\n");
 			stats->rx_mic_error++;
 		}
-		if (l2_rx_status & WIL_RX_EDMA_ERROR_KEY) {
-			wil_dbg_txrx(wil, "L2 KEY error, dropping packet\n");
+		if (l2_rx_status == WIL_RX_EDMA_ERROR_KEY) {
+			wil_err_ratelimited(wil,
+					    "L2 KEY error, dropping packet\n");
 			stats->rx_key_error++;
 		}
-		if (l2_rx_status & WIL_RX_EDMA_ERROR_REPLAY) {
-			wil_dbg_txrx(wil,
-				     "L2 REPLAY error, dropping packet\n");
+		if (l2_rx_status == WIL_RX_EDMA_ERROR_REPLAY) {
+			wil_err_ratelimited(wil,
+					    "L2 REPLAY error, dropping packet\n");
 			stats->rx_replay++;
 		}
-		if (l2_rx_status & WIL_RX_EDMA_ERROR_AMSDU) {
-			wil_dbg_txrx(wil,
-				     "L2 AMSDU error, dropping packet\n");
+		if (l2_rx_status == WIL_RX_EDMA_ERROR_AMSDU) {
+			wil_err_ratelimited(wil,
+					    "L2 AMSDU error, dropping packet\n");
 			stats->rx_amsdu_error++;
 		}
 		return -EFAULT;
-- 
cgit v1.2.3


From 7c69709f8ed27197b16aa1c3f9b0744402b2fa02 Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:20 +0200
Subject: wil6210: fix RGF_CAF_ICR address for Talyn-MB

RGF_CAF_ICR register location has changed in Talyn-MB.
Add RGF_CAF_ICR_TALYN_MB to support the new address.

Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/main.c    | 11 +++++++++--
 drivers/net/wireless/ath/wil6210/wil6210.h |  1 +
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 68aca52a68e4..ba6a2eeedb65 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -1499,8 +1499,15 @@ static void wil_pre_fw_config(struct wil6210_priv *wil)
 	wil6210_clear_irq(wil);
 	/* CAF_ICR - clear and mask */
 	/* it is W1C, clear by writing back same value */
-	wil_s(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, ICR), 0);
-	wil_w(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, IMV), ~0);
+	if (wil->hw_version < HW_VER_TALYN_MB) {
+		wil_s(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, ICR), 0);
+		wil_w(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, IMV), ~0);
+	} else {
+		wil_s(wil,
+		      RGF_CAF_ICR_TALYN_MB + offsetof(struct RGF_ICR, ICR), 0);
+		wil_w(wil, RGF_CAF_ICR_TALYN_MB +
+		      offsetof(struct RGF_ICR, IMV), ~0);
+	}
 	/* clear PAL_UNIT_ICR (potential D0->D3 leftover)
 	 * In Talyn-MB host cannot access this register due to
 	 * access control, hence PAL_UNIT_ICR is cleared by the FW
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index ad7003f350a2..0f3be3ffc6a2 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -320,6 +320,7 @@ struct RGF_ICR {
 /* MAC timer, usec, for packet lifetime */
 #define RGF_MAC_MTRL_COUNTER_0		(0x886aa8)
 
+#define RGF_CAF_ICR_TALYN_MB		(0x8893d4) /* struct RGF_ICR */
 #define RGF_CAF_ICR			(0x88946c) /* struct RGF_ICR */
 #define RGF_CAF_OSC_CONTROL		(0x88afa4)
 	#define BIT_CAF_OSC_XTAL_EN		BIT(0)
-- 
cgit v1.2.3


From a834df7497b4e2bd609761b6e69fb9c8176ccf8e Mon Sep 17 00:00:00 2001
From: Ahmad Masri <amasri@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:22 +0200
Subject: wil6210: remove unnecessary alignment code from rx flow

Rx buffers in EDMA mode are initialized to 4 bytes aligned size.
Remove the unnecessary alignment code applied on rx buffer size.

Signed-off-by: Ahmad Masri <amasri@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/txrx_edma.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index c8490e727e6c..686ba3463970 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -160,7 +160,7 @@ static int wil_ring_alloc_skb_edma(struct wil6210_priv *wil,
 				   struct wil_ring *ring, u32 i)
 {
 	struct device *dev = wil_to_dev(wil);
-	unsigned int sz = ALIGN(wil->rx_buf_len, 4);
+	unsigned int sz = wil->rx_buf_len;
 	dma_addr_t pa;
 	u16 buff_id;
 	struct list_head *active = &wil->rx_buff_mgmt.active;
@@ -602,6 +602,7 @@ static bool wil_is_rx_idle_edma(struct wil6210_priv *wil)
 
 static void wil_rx_buf_len_init_edma(struct wil6210_priv *wil)
 {
+	/* RX buffer size must be aligned to 4 bytes */
 	wil->rx_buf_len = rx_large_buf ?
 		WIL_MAX_ETH_MTU : WIL_EDMA_RX_BUF_LEN_DEFAULT;
 }
@@ -615,7 +616,6 @@ static int wil_rx_init_edma(struct wil6210_priv *wil, uint desc_ring_order)
 		sizeof(struct wil_rx_status_compressed) :
 		sizeof(struct wil_rx_status_extended);
 	int i;
-	u16 max_rx_pl_per_desc;
 
 	/* In SW reorder one must use extended status messages */
 	if (wil->use_compressed_rx_status && !wil->use_rx_hw_reordering) {
@@ -641,8 +641,6 @@ static int wil_rx_init_edma(struct wil6210_priv *wil, uint desc_ring_order)
 
 	wil_rx_buf_len_init_edma(wil);
 
-	max_rx_pl_per_desc = ALIGN(wil->rx_buf_len, 4);
-
 	/* Use debugfs dbg_num_rx_srings if set, reserve one sring for TX */
 	if (wil->num_rx_status_rings > WIL6210_MAX_STATUS_RINGS - 1)
 		wil->num_rx_status_rings = WIL6210_MAX_STATUS_RINGS - 1;
@@ -650,7 +648,7 @@ static int wil_rx_init_edma(struct wil6210_priv *wil, uint desc_ring_order)
 	wil_dbg_misc(wil, "rx_init: allocate %d status rings\n",
 		     wil->num_rx_status_rings);
 
-	rc = wil_wmi_cfg_def_rx_offload(wil, max_rx_pl_per_desc);
+	rc = wil_wmi_cfg_def_rx_offload(wil, wil->rx_buf_len);
 	if (rc)
 		return rc;
 
@@ -887,7 +885,7 @@ static struct sk_buff *wil_sring_reap_rx_edma(struct wil6210_priv *wil,
 	struct sk_buff *skb;
 	dma_addr_t pa;
 	struct wil_ring_rx_data *rxdata = &sring->rx_data;
-	unsigned int sz = ALIGN(wil->rx_buf_len, 4);
+	unsigned int sz = wil->rx_buf_len;
 	struct wil_net_stats *stats = NULL;
 	u16 dmalen;
 	int cid;
-- 
cgit v1.2.3


From 6470f31927b46846d957628b719dcfda05446664 Mon Sep 17 00:00:00 2001
From: Ahmad Masri <amasri@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:23 +0200
Subject: wil6210: fix freeing of rx buffers in EDMA mode

After being associated with some EDMA rx traffic, upon "down" driver
doesn't free all skbs in the rx ring.
Modify wil_move_all_rx_buff_to_free_list to loop on active list of rx
buffers, unmap the physical memory and free the skb.

Signed-off-by: Ahmad Masri <amasri@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/txrx_edma.c | 44 +++++++++-------------------
 1 file changed, 14 insertions(+), 30 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index 686ba3463970..05a8348bd7b9 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -234,9 +234,10 @@ static int wil_rx_refill_edma(struct wil6210_priv *wil)
 	struct wil_ring *ring = &wil->ring_rx;
 	u32 next_head;
 	int rc = 0;
-	u32 swtail = *ring->edma_rx_swtail.va;
+	ring->swtail = *ring->edma_rx_swtail.va;
 
-	for (; next_head = wil_ring_next_head(ring), (next_head != swtail);
+	for (; next_head = wil_ring_next_head(ring),
+	     (next_head != ring->swtail);
 	     ring->swhead = next_head) {
 		rc = wil_ring_alloc_skb_edma(wil, ring, ring->swhead);
 		if (unlikely(rc)) {
@@ -264,43 +265,26 @@ static void wil_move_all_rx_buff_to_free_list(struct wil6210_priv *wil,
 					      struct wil_ring *ring)
 {
 	struct device *dev = wil_to_dev(wil);
-	u32 next_tail;
-	u32 swhead = (ring->swhead + 1) % ring->size;
+	struct list_head *active = &wil->rx_buff_mgmt.active;
 	dma_addr_t pa;
-	u16 dmalen;
 
-	for (; next_tail = wil_ring_next_tail(ring), (next_tail != swhead);
-	     ring->swtail = next_tail) {
-		struct wil_rx_enhanced_desc dd, *d = &dd;
-		struct wil_rx_enhanced_desc *_d =
-			(struct wil_rx_enhanced_desc *)
-			&ring->va[ring->swtail].rx.enhanced;
-		struct sk_buff *skb;
-		u16 buff_id;
+	while (!list_empty(active)) {
+		struct wil_rx_buff *rx_buff =
+			list_first_entry(active, struct wil_rx_buff, list);
+		struct sk_buff *skb = rx_buff->skb;
 
-		*d = *_d;
-
-		/* Extract the SKB from the rx_buff management array */
-		buff_id = __le16_to_cpu(d->mac.buff_id);
-		if (buff_id >= wil->rx_buff_mgmt.size) {
-			wil_err(wil, "invalid buff_id %d\n", buff_id);
-			continue;
-		}
-		skb = wil->rx_buff_mgmt.buff_arr[buff_id].skb;
-		wil->rx_buff_mgmt.buff_arr[buff_id].skb = NULL;
 		if (unlikely(!skb)) {
-			wil_err(wil, "No Rx skb at buff_id %d\n", buff_id);
+			wil_err(wil, "No Rx skb at buff_id %d\n", rx_buff->id);
 		} else {
-			pa = wil_rx_desc_get_addr_edma(&d->dma);
-			dmalen = le16_to_cpu(d->dma.length);
-			dma_unmap_single(dev, pa, dmalen, DMA_FROM_DEVICE);
-
+			rx_buff->skb = NULL;
+			memcpy(&pa, skb->cb, sizeof(pa));
+			dma_unmap_single(dev, pa, wil->rx_buf_len,
+					 DMA_FROM_DEVICE);
 			kfree_skb(skb);
 		}
 
 		/* Move the buffer from the active to the free list */
-		list_move(&wil->rx_buff_mgmt.buff_arr[buff_id].list,
-			  &wil->rx_buff_mgmt.free);
+		list_move(&rx_buff->list, &wil->rx_buff_mgmt.free);
 	}
 }
 
-- 
cgit v1.2.3


From dc57731dbd535880fe6ced31c229262c34df7d64 Mon Sep 17 00:00:00 2001
From: Lior David <liord@codeaurora.org>
Date: Wed, 31 Oct 2018 10:52:24 +0200
Subject: wil6210: fix locking in wmi_call

Switch from spin_lock to spin_lock_irqsave, because
wmi_ev_lock is used inside interrupt handler.

Signed-off-by: Lior David <liord@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/wmi.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index f46c703ca570..345f05969190 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -1966,16 +1966,17 @@ int wmi_call(struct wil6210_priv *wil, u16 cmdid, u8 mid, void *buf, u16 len,
 {
 	int rc;
 	unsigned long remain;
+	ulong flags;
 
 	mutex_lock(&wil->wmi_mutex);
 
-	spin_lock(&wil->wmi_ev_lock);
+	spin_lock_irqsave(&wil->wmi_ev_lock, flags);
 	wil->reply_id = reply_id;
 	wil->reply_mid = mid;
 	wil->reply_buf = reply;
 	wil->reply_size = reply_size;
 	reinit_completion(&wil->wmi_call);
-	spin_unlock(&wil->wmi_ev_lock);
+	spin_unlock_irqrestore(&wil->wmi_ev_lock, flags);
 
 	rc = __wmi_send(wil, cmdid, mid, buf, len);
 	if (rc)
@@ -1995,12 +1996,12 @@ int wmi_call(struct wil6210_priv *wil, u16 cmdid, u8 mid, void *buf, u16 len,
 	}
 
 out:
-	spin_lock(&wil->wmi_ev_lock);
+	spin_lock_irqsave(&wil->wmi_ev_lock, flags);
 	wil->reply_id = 0;
 	wil->reply_mid = U8_MAX;
 	wil->reply_buf = NULL;
 	wil->reply_size = 0;
-	spin_unlock(&wil->wmi_ev_lock);
+	spin_unlock_irqrestore(&wil->wmi_ev_lock, flags);
 
 	mutex_unlock(&wil->wmi_mutex);
 
-- 
cgit v1.2.3


From 887a3dcf589389756bad51b34b69d4e9e9b2aa86 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 5 Nov 2018 14:34:46 +0200
Subject: ath10k: snoc: remove 'wcn3990' from generic resource handling

ath10k_wcn3990_clk_info and ath10k_wcn3990_vreg_info are not
WCN3990-specific structures. They hold generic data. So don't name them
with wcn3990 specifics.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 34 +++++++++++++++++-----------------
 drivers/net/wireless/ath/ath10k/snoc.h |  8 ++++----
 2 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 98724d04baef..5ee0fb7beeee 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -46,14 +46,14 @@ static char *const ce_name[] = {
 	"WLAN_CE_11",
 };
 
-static struct ath10k_wcn3990_vreg_info vreg_cfg[] = {
+static struct ath10k_vreg_info vreg_cfg[] = {
 	{NULL, "vdd-0.8-cx-mx", 800000, 800000, 0, 0, false},
 	{NULL, "vdd-1.8-xo", 1800000, 1800000, 0, 0, false},
 	{NULL, "vdd-1.3-rfa", 1304000, 1304000, 0, 0, false},
 	{NULL, "vdd-3.3-ch0", 3312000, 3312000, 0, 0, false},
 };
 
-static struct ath10k_wcn3990_clk_info clk_cfg[] = {
+static struct ath10k_clk_info clk_cfg[] = {
 	{NULL, "cxo_ref_clk_pin", 0, false},
 };
 
@@ -1270,7 +1270,7 @@ static void ath10k_snoc_release_resource(struct ath10k *ar)
 }
 
 static int ath10k_get_vreg_info(struct ath10k *ar, struct device *dev,
-				struct ath10k_wcn3990_vreg_info *vreg_info)
+				struct ath10k_vreg_info *vreg_info)
 {
 	struct regulator *reg;
 	int ret = 0;
@@ -1308,7 +1308,7 @@ done:
 }
 
 static int ath10k_get_clk_info(struct ath10k *ar, struct device *dev,
-			       struct ath10k_wcn3990_clk_info *clk_info)
+			       struct ath10k_clk_info *clk_info)
 {
 	struct clk *handle;
 	int ret = 0;
@@ -1335,10 +1335,10 @@ static int ath10k_get_clk_info(struct ath10k *ar, struct device *dev,
 	return ret;
 }
 
-static int ath10k_wcn3990_vreg_on(struct ath10k *ar)
+static int ath10k_snoc_vreg_on(struct ath10k *ar)
 {
 	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
-	struct ath10k_wcn3990_vreg_info *vreg_info;
+	struct ath10k_vreg_info *vreg_info;
 	int ret = 0;
 	int i;
 
@@ -1400,10 +1400,10 @@ err_reg_config:
 	return ret;
 }
 
-static int ath10k_wcn3990_vreg_off(struct ath10k *ar)
+static int ath10k_snoc_vreg_off(struct ath10k *ar)
 {
 	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
-	struct ath10k_wcn3990_vreg_info *vreg_info;
+	struct ath10k_vreg_info *vreg_info;
 	int ret = 0;
 	int i;
 
@@ -1436,10 +1436,10 @@ static int ath10k_wcn3990_vreg_off(struct ath10k *ar)
 	return ret;
 }
 
-static int ath10k_wcn3990_clk_init(struct ath10k *ar)
+static int ath10k_snoc_clk_init(struct ath10k *ar)
 {
 	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
-	struct ath10k_wcn3990_clk_info *clk_info;
+	struct ath10k_clk_info *clk_info;
 	int ret = 0;
 	int i;
 
@@ -1485,10 +1485,10 @@ err_clock_config:
 	return ret;
 }
 
-static int ath10k_wcn3990_clk_deinit(struct ath10k *ar)
+static int ath10k_snoc_clk_deinit(struct ath10k *ar)
 {
 	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
-	struct ath10k_wcn3990_clk_info *clk_info;
+	struct ath10k_clk_info *clk_info;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(clk_cfg); i++) {
@@ -1512,18 +1512,18 @@ static int ath10k_hw_power_on(struct ath10k *ar)
 
 	ath10k_dbg(ar, ATH10K_DBG_SNOC, "soc power on\n");
 
-	ret = ath10k_wcn3990_vreg_on(ar);
+	ret = ath10k_snoc_vreg_on(ar);
 	if (ret)
 		return ret;
 
-	ret = ath10k_wcn3990_clk_init(ar);
+	ret = ath10k_snoc_clk_init(ar);
 	if (ret)
 		goto vreg_off;
 
 	return ret;
 
 vreg_off:
-	ath10k_wcn3990_vreg_off(ar);
+	ath10k_snoc_vreg_off(ar);
 	return ret;
 }
 
@@ -1533,9 +1533,9 @@ static int ath10k_hw_power_off(struct ath10k *ar)
 
 	ath10k_dbg(ar, ATH10K_DBG_SNOC, "soc power off\n");
 
-	ath10k_wcn3990_clk_deinit(ar);
+	ath10k_snoc_clk_deinit(ar);
 
-	ret = ath10k_wcn3990_vreg_off(ar);
+	ret = ath10k_snoc_vreg_off(ar);
 
 	return ret;
 }
diff --git a/drivers/net/wireless/ath/ath10k/snoc.h b/drivers/net/wireless/ath/ath10k/snoc.h
index 3a44e30696bc..d0fcf99a8eca 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.h
+++ b/drivers/net/wireless/ath/ath10k/snoc.h
@@ -53,7 +53,7 @@ struct ath10k_snoc_ce_irq {
 	u32 irq_line;
 };
 
-struct ath10k_wcn3990_vreg_info {
+struct ath10k_vreg_info {
 	struct regulator *reg;
 	const char *name;
 	u32 min_v;
@@ -63,7 +63,7 @@ struct ath10k_wcn3990_vreg_info {
 	bool required;
 };
 
-struct ath10k_wcn3990_clk_info {
+struct ath10k_clk_info {
 	struct clk *handle;
 	const char *name;
 	u32 freq;
@@ -87,8 +87,8 @@ struct ath10k_snoc {
 	struct ath10k_snoc_ce_irq ce_irqs[CE_COUNT_MAX];
 	struct ath10k_ce ce;
 	struct timer_list rx_post_retry;
-	struct ath10k_wcn3990_vreg_info *vreg;
-	struct ath10k_wcn3990_clk_info *clk;
+	struct ath10k_vreg_info *vreg;
+	struct ath10k_clk_info *clk;
 	struct ath10k_qmi *qmi;
 	unsigned long int flags;
 };
-- 
cgit v1.2.3


From 1a1a0d5ccefca6f3f7417b448793c753a610da0c Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 5 Nov 2018 14:34:57 +0200
Subject: ath10k: snoc: fix unabalanced regulator error handling

If a regulator fails to set its voltage, we end up with an unbalanced
call to regulator_disable(), because the error path starts with the
current regulator (which was never enabled).

Factor out the "on" function to perform (and unwind if failed) a single
regulator at a time, and then main loop (ath10k_snoc_vreg_on()) can just
worry about unwinding the regulators that were already enabled.

It also helps to factor out the "off" function, to avoid repeating some
code here.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 129 +++++++++++++++++++--------------
 1 file changed, 75 insertions(+), 54 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 5ee0fb7beeee..69bcf132a9bf 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -1335,6 +1335,76 @@ static int ath10k_get_clk_info(struct ath10k *ar, struct device *dev,
 	return ret;
 }
 
+static int __ath10k_snoc_vreg_on(struct ath10k *ar,
+				 struct ath10k_vreg_info *vreg_info)
+{
+	int ret;
+
+	ath10k_dbg(ar, ATH10K_DBG_SNOC, "snoc regulator %s being enabled\n",
+		   vreg_info->name);
+
+	ret = regulator_set_voltage(vreg_info->reg, vreg_info->min_v,
+				    vreg_info->max_v);
+	if (ret) {
+		ath10k_err(ar,
+			   "failed to set regulator %s voltage-min: %d voltage-max: %d\n",
+			   vreg_info->name, vreg_info->min_v, vreg_info->max_v);
+		return ret;
+	}
+
+	if (vreg_info->load_ua) {
+		ret = regulator_set_load(vreg_info->reg, vreg_info->load_ua);
+		if (ret < 0) {
+			ath10k_err(ar, "failed to set regulator %s load: %d\n",
+				   vreg_info->name, vreg_info->load_ua);
+			goto err_set_load;
+		}
+	}
+
+	ret = regulator_enable(vreg_info->reg);
+	if (ret) {
+		ath10k_err(ar, "failed to enable regulator %s\n",
+			   vreg_info->name);
+		goto err_enable;
+	}
+
+	if (vreg_info->settle_delay)
+		udelay(vreg_info->settle_delay);
+
+	return 0;
+
+err_enable:
+	regulator_set_load(vreg_info->reg, 0);
+err_set_load:
+	regulator_set_voltage(vreg_info->reg, 0, vreg_info->max_v);
+
+	return ret;
+}
+
+static int __ath10k_snoc_vreg_off(struct ath10k *ar,
+				  struct ath10k_vreg_info *vreg_info)
+{
+	int ret;
+
+	ath10k_dbg(ar, ATH10K_DBG_SNOC, "snoc regulator %s being disabled\n",
+		   vreg_info->name);
+
+	ret = regulator_disable(vreg_info->reg);
+	if (ret)
+		ath10k_err(ar, "failed to disable regulator %s\n",
+			   vreg_info->name);
+
+	ret = regulator_set_load(vreg_info->reg, 0);
+	if (ret < 0)
+		ath10k_err(ar, "failed to set load %s\n", vreg_info->name);
+
+	ret = regulator_set_voltage(vreg_info->reg, 0, vreg_info->max_v);
+	if (ret)
+		ath10k_err(ar, "failed to set voltage %s\n", vreg_info->name);
+
+	return ret;
+}
+
 static int ath10k_snoc_vreg_on(struct ath10k *ar)
 {
 	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
@@ -1348,53 +1418,21 @@ static int ath10k_snoc_vreg_on(struct ath10k *ar)
 		if (!vreg_info->reg)
 			continue;
 
-		ath10k_dbg(ar, ATH10K_DBG_SNOC, "snoc regulator %s being enabled\n",
-			   vreg_info->name);
-
-		ret = regulator_set_voltage(vreg_info->reg, vreg_info->min_v,
-					    vreg_info->max_v);
-		if (ret) {
-			ath10k_err(ar,
-				   "failed to set regulator %s voltage-min: %d voltage-max: %d\n",
-				   vreg_info->name, vreg_info->min_v, vreg_info->max_v);
-			goto err_reg_config;
-		}
-
-		if (vreg_info->load_ua) {
-			ret = regulator_set_load(vreg_info->reg,
-						 vreg_info->load_ua);
-			if (ret < 0) {
-				ath10k_err(ar,
-					   "failed to set regulator %s load: %d\n",
-					   vreg_info->name,
-					   vreg_info->load_ua);
-				goto err_reg_config;
-			}
-		}
-
-		ret = regulator_enable(vreg_info->reg);
-		if (ret) {
-			ath10k_err(ar, "failed to enable regulator %s\n",
-				   vreg_info->name);
+		ret = __ath10k_snoc_vreg_on(ar, vreg_info);
+		if (ret)
 			goto err_reg_config;
-		}
-
-		if (vreg_info->settle_delay)
-			udelay(vreg_info->settle_delay);
 	}
 
 	return 0;
 
 err_reg_config:
-	for (; i >= 0; i--) {
+	for (i = i - 1; i >= 0; i--) {
 		vreg_info = &ar_snoc->vreg[i];
 
 		if (!vreg_info->reg)
 			continue;
 
-		regulator_disable(vreg_info->reg);
-		regulator_set_load(vreg_info->reg, 0);
-		regulator_set_voltage(vreg_info->reg, 0, vreg_info->max_v);
+		__ath10k_snoc_vreg_off(ar, vreg_info);
 	}
 
 	return ret;
@@ -1413,24 +1451,7 @@ static int ath10k_snoc_vreg_off(struct ath10k *ar)
 		if (!vreg_info->reg)
 			continue;
 
-		ath10k_dbg(ar, ATH10K_DBG_SNOC, "snoc regulator %s being disabled\n",
-			   vreg_info->name);
-
-		ret = regulator_disable(vreg_info->reg);
-		if (ret)
-			ath10k_err(ar, "failed to disable regulator %s\n",
-				   vreg_info->name);
-
-		ret = regulator_set_load(vreg_info->reg, 0);
-		if (ret < 0)
-			ath10k_err(ar, "failed to set load %s\n",
-				   vreg_info->name);
-
-		ret = regulator_set_voltage(vreg_info->reg, 0,
-					    vreg_info->max_v);
-		if (ret)
-			ath10k_err(ar, "failed to set voltage %s\n",
-				   vreg_info->name);
+		ret = __ath10k_snoc_vreg_off(ar, vreg_info);
 	}
 
 	return ret;
-- 
cgit v1.2.3


From bfe57a6ac75aec73aec43ca24942d7704100fc2c Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 5 Nov 2018 14:35:09 +0200
Subject: ath10k: snoc: relax voltage requirements

I rarely see drivers specify precise voltage requirements like this, but
if we really have to...let's at least give a little wiggle room. Board
designs (and accompanying device trees) may not provide exactly the
voltage listed here, and we shouldn't fail to probe just because of
this.

Round these ranges down to the nearest volt, and provide a 0.05V margin.
The regulator should provide its own supported ranges, which will
helpfully intersect with these ranges.

I would just as well remove these ranges entirely, but if I understand
correctly, there's some reason that QCOM SoC's like to set zero /
non-zero voltages.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 69bcf132a9bf..48292ed7d494 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -47,10 +47,10 @@ static char *const ce_name[] = {
 };
 
 static struct ath10k_vreg_info vreg_cfg[] = {
-	{NULL, "vdd-0.8-cx-mx", 800000, 800000, 0, 0, false},
-	{NULL, "vdd-1.8-xo", 1800000, 1800000, 0, 0, false},
-	{NULL, "vdd-1.3-rfa", 1304000, 1304000, 0, 0, false},
-	{NULL, "vdd-3.3-ch0", 3312000, 3312000, 0, 0, false},
+	{NULL, "vdd-0.8-cx-mx", 800000, 850000, 0, 0, false},
+	{NULL, "vdd-1.8-xo", 1800000, 1850000, 0, 0, false},
+	{NULL, "vdd-1.3-rfa", 1300000, 1350000, 0, 0, false},
+	{NULL, "vdd-3.3-ch0", 3300000, 3350000, 0, 0, false},
 };
 
 static struct ath10k_clk_info clk_cfg[] = {
-- 
cgit v1.2.3


From 82e60d920e8ad70cd9a280ab156566755f1fe4aa Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 5 Nov 2018 14:35:22 +0200
Subject: ath10k: snoc: fix unbalanced clock error handling

Similar to regulator error handling, we should only start tearing down
the 'i - 1' clock when clock 'i' fails to enable. Otherwise, we might
end up with an unbalanced clock, where we never successfully enabled the
clock, but we try to disable it anyway.

Fixes: a6a793f98786 ("ath10k: vote for hardware resources for WCN3990")
Signed-off-by: Brian Norris <briannorris@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 48292ed7d494..81b86a787c34 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -1494,7 +1494,7 @@ static int ath10k_snoc_clk_init(struct ath10k *ar)
 	return 0;
 
 err_clock_config:
-	for (; i >= 0; i--) {
+	for (i = i - 1; i >= 0; i--) {
 		clk_info = &ar_snoc->clk[i];
 
 		if (!clk_info->handle)
-- 
cgit v1.2.3


From 97b9608be34f9fcad3d4aa79ea7b8720680b232d Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Fri, 2 Nov 2018 11:10:00 -0700
Subject: ath10k: ath10k_snoc_{read,write}32() should be static

They're provided as callbacks in ath10k_hif_ops and should be accessed
that way, if needed outside of snoc.c, and anyway, they're currently
unused outside snoc.c.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 4 ++--
 drivers/net/wireless/ath/ath10k/snoc.h | 2 --
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 81b86a787c34..85116986161c 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -474,14 +474,14 @@ static struct service_to_pipe target_service_to_ce_map_wlan[] = {
 	},
 };
 
-void ath10k_snoc_write32(struct ath10k *ar, u32 offset, u32 value)
+static void ath10k_snoc_write32(struct ath10k *ar, u32 offset, u32 value)
 {
 	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
 
 	iowrite32(value, ar_snoc->mem + offset);
 }
 
-u32 ath10k_snoc_read32(struct ath10k *ar, u32 offset)
+static u32 ath10k_snoc_read32(struct ath10k *ar, u32 offset)
 {
 	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
 	u32 val;
diff --git a/drivers/net/wireless/ath/ath10k/snoc.h b/drivers/net/wireless/ath/ath10k/snoc.h
index d0fcf99a8eca..2b2f23cf7c5d 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.h
+++ b/drivers/net/wireless/ath/ath10k/snoc.h
@@ -98,8 +98,6 @@ static inline struct ath10k_snoc *ath10k_snoc_priv(struct ath10k *ar)
 	return (struct ath10k_snoc *)ar->drv_priv;
 }
 
-void ath10k_snoc_write32(struct ath10k *ar, u32 offset, u32 value);
-u32 ath10k_snoc_read32(struct ath10k *ar, u32 offset);
 int ath10k_snoc_fw_indication(struct ath10k *ar, u64 type);
 
 #endif /* _SNOC_H_ */
-- 
cgit v1.2.3


From 2bd345cd2bfc0bd44528896313c0b45f087bdf67 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Fri, 2 Nov 2018 10:17:47 -0700
Subject: ath10k: assign 'n_cipher_suites' for WCN3990

Commit 2ea9f12cefe4 ("ath10k: add new cipher suite support") added a new
n_cipher_suites HW param with a fallback value and a warning log. Commit
03a72288c546 ("ath10k: wmi: add hw params entry for wcn3990") later
added WCN3990 HW entries, but it missed the n_cipher_suites.

Rather than seeing this warning every boot

  ath10k_snoc 18800000.wifi: invalid hw_params.n_cipher_suites 0

let's provide the appropriate value.

Cc: Rakesh Pillai <pillair@qti.qualcomm.com>
Cc: Govind Singh <govinds@qti.qualcomm.com>
Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 9d0b3515989a..22cbe9a2e646 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -561,6 +561,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &wcn3990_ops,
 		.decap_align_bytes = 1,
 		.num_peers = TARGET_HL_10_TLV_NUM_PEERS,
+		.n_cipher_suites = 8,
 		.ast_skid_limit = TARGET_HL_10_TLV_AST_SKID_LIMIT,
 		.num_wds_entries = TARGET_HL_10_TLV_NUM_WDS_ENTRIES,
 		.target_64bit = true,
-- 
cgit v1.2.3


From 79169f14865503fb3c1571ae3f9c456c3ca74865 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Fri, 2 Nov 2018 10:17:48 -0700
Subject: ath10k: don't assume this is a PCI dev in generic code

Not all devices using this driver are backed by a PCI device, so it's
not fair to assume 'to_pci_dev()' is valid. Fortunately, we only were
using this to convert straight back to a bare 'device', which means we
were only doing no-op pointer arithmetic, and not actually accessing
potentially out-of-bounds memory. But this is still bad practice.

Just use 'ar->dev' directly, since that's really all we're looking for.

Fixes: 209b2a68de76 ("ath10k: add platform regulatory domain support")
Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 2b8c8bf80b0d..c5130fa264eb 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -8317,7 +8317,6 @@ static u32 ath10k_mac_wrdd_get_mcc(struct ath10k *ar, union acpi_object *wrdd)
 
 static int ath10k_mac_get_wrdd_regulatory(struct ath10k *ar, u16 *rd)
 {
-	struct pci_dev __maybe_unused *pdev = to_pci_dev(ar->dev);
 	acpi_handle root_handle;
 	acpi_handle handle;
 	struct acpi_buffer wrdd = {ACPI_ALLOCATE_BUFFER, NULL};
@@ -8325,7 +8324,7 @@ static int ath10k_mac_get_wrdd_regulatory(struct ath10k *ar, u16 *rd)
 	u32 alpha2_code;
 	char alpha2[3];
 
-	root_handle = ACPI_HANDLE(&pdev->dev);
+	root_handle = ACPI_HANDLE(ar->dev);
 	if (!root_handle)
 		return -EOPNOTSUPP;
 
-- 
cgit v1.2.3


From cea04e3d8e3727185f9ebe736045655b30ff9079 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Fri, 2 Nov 2018 10:17:49 -0700
Subject: ath10k: fix struct init whitespace in SNOC driver

Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 85116986161c..dad7e1ce79c0 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -1695,12 +1695,12 @@ static int ath10k_snoc_remove(struct platform_device *pdev)
 }
 
 static struct platform_driver ath10k_snoc_driver = {
-		.probe  = ath10k_snoc_probe,
-		.remove = ath10k_snoc_remove,
-		.driver = {
-			.name   = "ath10k_snoc",
-			.of_match_table = ath10k_snoc_dt_match,
-		},
+	.probe  = ath10k_snoc_probe,
+	.remove = ath10k_snoc_remove,
+	.driver = {
+		.name   = "ath10k_snoc",
+		.of_match_table = ath10k_snoc_dt_match,
+	},
 };
 module_platform_driver(ath10k_snoc_driver);
 
-- 
cgit v1.2.3


From 3831a2a0010c72e3956020cbf1057a1701a2e469 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 2 Nov 2018 21:49:55 +0100
Subject: ath9k: dynack: use authentication messages for 'late' ack

In order to properly support dynack in ad-hoc mode running
wpa_supplicant, take into account authentication frames for
'late ack' detection. This patch has been tested on devices
mounted on offshore high-voltage stations connected through
~24Km link

Reported-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
Tested-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/dynack.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/dynack.c b/drivers/net/wireless/ath/ath9k/dynack.c
index 7334c9b09e82..cc0dc966c512 100644
--- a/drivers/net/wireless/ath/ath9k/dynack.c
+++ b/drivers/net/wireless/ath/ath9k/dynack.c
@@ -187,7 +187,8 @@ void ath_dynack_sample_tx_ts(struct ath_hw *ah, struct sk_buff *skb,
 	/* late ACK */
 	if (ts->ts_status & ATH9K_TXERR_XRETRY) {
 		if (ieee80211_is_assoc_req(hdr->frame_control) ||
-		    ieee80211_is_assoc_resp(hdr->frame_control)) {
+		    ieee80211_is_assoc_resp(hdr->frame_control) ||
+		    ieee80211_is_auth(hdr->frame_control)) {
 			ath_dbg(common, DYNACK, "late ack\n");
 			ath9k_hw_setslottime(ah, (LATEACK_TO - 3) / 2);
 			ath9k_hw_set_ack_timeout(ah, LATEACK_TO);
-- 
cgit v1.2.3


From 5e3d4718b1574c8634b45965307dee20a6c921a1 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 2 Nov 2018 21:49:56 +0100
Subject: ath9k: dynack: move debug log after buffer increments

Move debug log in ath_dynack_sample_tx_ts and ath_dynack_sample_ack_ts
after timestamp buffer head/tail increments in order to make debugging
more user friendly

Tested-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/dynack.c | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/dynack.c b/drivers/net/wireless/ath/ath9k/dynack.c
index cc0dc966c512..5c969d833825 100644
--- a/drivers/net/wireless/ath/ath9k/dynack.c
+++ b/drivers/net/wireless/ath/ath9k/dynack.c
@@ -171,11 +171,12 @@ static void ath_dynack_compute_to(struct ath_hw *ah)
 void ath_dynack_sample_tx_ts(struct ath_hw *ah, struct sk_buff *skb,
 			     struct ath_tx_status *ts)
 {
-	u8 ridx;
 	struct ieee80211_hdr *hdr;
 	struct ath_dynack *da = &ah->dynack;
 	struct ath_common *common = ath9k_hw_common(ah);
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	u32 dur = ts->duration;
+	u8 ridx;
 
 	if ((info->flags & IEEE80211_TX_CTL_NO_ACK) || !da->enabled)
 		return;
@@ -203,14 +204,13 @@ void ath_dynack_sample_tx_ts(struct ath_hw *ah, struct sk_buff *skb,
 	ridx = ts->ts_rateindex;
 
 	da->st_rbf.ts[da->st_rbf.t_rb].tstamp = ts->ts_tstamp;
-	da->st_rbf.ts[da->st_rbf.t_rb].dur = ts->duration;
 	ether_addr_copy(da->st_rbf.addr[da->st_rbf.t_rb].h_dest, hdr->addr1);
 	ether_addr_copy(da->st_rbf.addr[da->st_rbf.t_rb].h_src, hdr->addr2);
 
 	if (!(info->status.rates[ridx].flags & IEEE80211_TX_RC_MCS)) {
-		u32 phy, sifs;
 		const struct ieee80211_rate *rate;
 		struct ieee80211_tx_rate *rates = info->status.rates;
+		u32 phy;
 
 		rate = &common->sbands[info->band].bitrates[rates[ridx].idx];
 		if (info->band == NL80211_BAND_2GHZ &&
@@ -219,19 +219,18 @@ void ath_dynack_sample_tx_ts(struct ath_hw *ah, struct sk_buff *skb,
 		else
 			phy = WLAN_RC_PHY_OFDM;
 
-		sifs = ath_dynack_get_sifs(ah, phy);
-		da->st_rbf.ts[da->st_rbf.t_rb].dur -= sifs;
+		dur -= ath_dynack_get_sifs(ah, phy);
 	}
-
-	ath_dbg(common, DYNACK, "{%pM} tx sample %u [dur %u][h %u-t %u]\n",
-		hdr->addr1, da->st_rbf.ts[da->st_rbf.t_rb].tstamp,
-		da->st_rbf.ts[da->st_rbf.t_rb].dur, da->st_rbf.h_rb,
-		(da->st_rbf.t_rb + 1) % ATH_DYN_BUF);
+	da->st_rbf.ts[da->st_rbf.t_rb].dur = dur;
 
 	INCR(da->st_rbf.t_rb, ATH_DYN_BUF);
 	if (da->st_rbf.t_rb == da->st_rbf.h_rb)
 		INCR(da->st_rbf.h_rb, ATH_DYN_BUF);
 
+	ath_dbg(common, DYNACK, "{%pM} tx sample %u [dur %u][h %u-t %u]\n",
+		hdr->addr1, ts->ts_tstamp, dur, da->st_rbf.h_rb,
+		da->st_rbf.t_rb);
+
 	ath_dynack_compute_to(ah);
 
 	spin_unlock_bh(&da->qlock);
@@ -258,14 +257,13 @@ void ath_dynack_sample_ack_ts(struct ath_hw *ah, struct sk_buff *skb,
 	spin_lock_bh(&da->qlock);
 	da->ack_rbf.tstamp[da->ack_rbf.t_rb] = ts;
 
-	ath_dbg(common, DYNACK, "rx sample %u [h %u-t %u]\n",
-		da->ack_rbf.tstamp[da->ack_rbf.t_rb],
-		da->ack_rbf.h_rb, (da->ack_rbf.t_rb + 1) % ATH_DYN_BUF);
-
 	INCR(da->ack_rbf.t_rb, ATH_DYN_BUF);
 	if (da->ack_rbf.t_rb == da->ack_rbf.h_rb)
 		INCR(da->ack_rbf.h_rb, ATH_DYN_BUF);
 
+	ath_dbg(common, DYNACK, "rx sample %u [h %u-t %u]\n",
+		ts, da->ack_rbf.h_rb, da->ack_rbf.t_rb);
+
 	ath_dynack_compute_to(ah);
 
 	spin_unlock_bh(&da->qlock);
-- 
cgit v1.2.3


From 9d3d65a91f027b8a9af5e63752d9b78cb10eb92d Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 2 Nov 2018 21:49:57 +0100
Subject: ath9k: dynack: check da->enabled first in sampling routines

Check da->enabled flag first in ath_dynack_sample_tx_ts and
ath_dynack_sample_ack_ts routines in order to avoid useless
processing

Tested-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/dynack.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/dynack.c b/drivers/net/wireless/ath/ath9k/dynack.c
index 5c969d833825..5c3b32f4e61b 100644
--- a/drivers/net/wireless/ath/ath9k/dynack.c
+++ b/drivers/net/wireless/ath/ath9k/dynack.c
@@ -178,7 +178,7 @@ void ath_dynack_sample_tx_ts(struct ath_hw *ah, struct sk_buff *skb,
 	u32 dur = ts->duration;
 	u8 ridx;
 
-	if ((info->flags & IEEE80211_TX_CTL_NO_ACK) || !da->enabled)
+	if (!da->enabled || (info->flags & IEEE80211_TX_CTL_NO_ACK))
 		return;
 
 	spin_lock_bh(&da->qlock);
@@ -251,7 +251,7 @@ void ath_dynack_sample_ack_ts(struct ath_hw *ah, struct sk_buff *skb,
 	struct ath_common *common = ath9k_hw_common(ah);
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 
-	if (!ath_dynack_bssidmask(ah, hdr->addr1) || !da->enabled)
+	if (!da->enabled || !ath_dynack_bssidmask(ah, hdr->addr1))
 		return;
 
 	spin_lock_bh(&da->qlock);
-- 
cgit v1.2.3


From 0c60c490830a1a756c80f8de8d33d9c6359d4a36 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 2 Nov 2018 21:49:58 +0100
Subject: ath9k: dynack: make ewma estimation faster

In order to make propagation time estimation faster,
use current sample as ewma output value during 'late ack'
tracking

Tested-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/ath9k.h  |  2 +-
 drivers/net/wireless/ath/ath9k/dynack.c | 28 +++++++++++++++++++++-------
 drivers/net/wireless/ath/ath9k/dynack.h |  6 ++++--
 drivers/net/wireless/ath/ath9k/xmit.c   |  5 +++--
 4 files changed, 29 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index 21ba20981a80..0fca44e91a71 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -272,7 +272,7 @@ struct ath_node {
 #endif
 	u8 key_idx[4];
 
-	u32 ackto;
+	int ackto;
 	struct list_head list;
 };
 
diff --git a/drivers/net/wireless/ath/ath9k/dynack.c b/drivers/net/wireless/ath/ath9k/dynack.c
index 5c3b32f4e61b..f112fa5b2eac 100644
--- a/drivers/net/wireless/ath/ath9k/dynack.c
+++ b/drivers/net/wireless/ath/ath9k/dynack.c
@@ -29,9 +29,13 @@
  * ath_dynack_ewma - EWMA (Exponentially Weighted Moving Average) calculation
  *
  */
-static inline u32 ath_dynack_ewma(u32 old, u32 new)
+static inline int ath_dynack_ewma(int old, int new)
 {
-	return (new * (EWMA_DIV - EWMA_LEVEL) + old * EWMA_LEVEL) / EWMA_DIV;
+	if (old > 0)
+		return (new * (EWMA_DIV - EWMA_LEVEL) +
+			old * EWMA_LEVEL) / EWMA_DIV;
+	else
+		return new;
 }
 
 /**
@@ -82,10 +86,10 @@ static inline bool ath_dynack_bssidmask(struct ath_hw *ah, const u8 *mac)
  */
 static void ath_dynack_compute_ackto(struct ath_hw *ah)
 {
-	struct ath_node *an;
-	u32 to = 0;
-	struct ath_dynack *da = &ah->dynack;
 	struct ath_common *common = ath9k_hw_common(ah);
+	struct ath_dynack *da = &ah->dynack;
+	struct ath_node *an;
+	int to = 0;
 
 	list_for_each_entry(an, &da->nodes, list)
 		if (an->ackto > to)
@@ -144,7 +148,8 @@ static void ath_dynack_compute_to(struct ath_hw *ah)
 					an->ackto = ath_dynack_ewma(an->ackto,
 								    ackto);
 					ath_dbg(ath9k_hw_common(ah), DYNACK,
-						"%pM to %u\n", dst, an->ackto);
+						"%pM to %d [%u]\n", dst,
+						an->ackto, ackto);
 					if (time_is_before_jiffies(da->lto)) {
 						ath_dynack_compute_ackto(ah);
 						da->lto = jiffies + COMPUTE_TO;
@@ -166,10 +171,12 @@ static void ath_dynack_compute_to(struct ath_hw *ah)
  * @ah: ath hw
  * @skb: socket buffer
  * @ts: tx status info
+ * @sta: station pointer
  *
  */
 void ath_dynack_sample_tx_ts(struct ath_hw *ah, struct sk_buff *skb,
-			     struct ath_tx_status *ts)
+			     struct ath_tx_status *ts,
+			     struct ieee80211_sta *sta)
 {
 	struct ieee80211_hdr *hdr;
 	struct ath_dynack *da = &ah->dynack;
@@ -191,9 +198,16 @@ void ath_dynack_sample_tx_ts(struct ath_hw *ah, struct sk_buff *skb,
 		    ieee80211_is_assoc_resp(hdr->frame_control) ||
 		    ieee80211_is_auth(hdr->frame_control)) {
 			ath_dbg(common, DYNACK, "late ack\n");
+
 			ath9k_hw_setslottime(ah, (LATEACK_TO - 3) / 2);
 			ath9k_hw_set_ack_timeout(ah, LATEACK_TO);
 			ath9k_hw_set_cts_timeout(ah, LATEACK_TO);
+			if (sta) {
+				struct ath_node *an;
+
+				an = (struct ath_node *)sta->drv_priv;
+				an->ackto = -1;
+			}
 			da->lto = jiffies + LATEACK_DELAY;
 		}
 
diff --git a/drivers/net/wireless/ath/ath9k/dynack.h b/drivers/net/wireless/ath/ath9k/dynack.h
index 6d7bef976742..cf60224d40df 100644
--- a/drivers/net/wireless/ath/ath9k/dynack.h
+++ b/drivers/net/wireless/ath/ath9k/dynack.h
@@ -86,7 +86,8 @@ void ath_dynack_node_deinit(struct ath_hw *ah, struct ath_node *an);
 void ath_dynack_init(struct ath_hw *ah);
 void ath_dynack_sample_ack_ts(struct ath_hw *ah, struct sk_buff *skb, u32 ts);
 void ath_dynack_sample_tx_ts(struct ath_hw *ah, struct sk_buff *skb,
-			     struct ath_tx_status *ts);
+			     struct ath_tx_status *ts,
+			     struct ieee80211_sta *sta);
 #else
 static inline void ath_dynack_init(struct ath_hw *ah) {}
 static inline void ath_dynack_node_init(struct ath_hw *ah,
@@ -97,7 +98,8 @@ static inline void ath_dynack_sample_ack_ts(struct ath_hw *ah,
 					    struct sk_buff *skb, u32 ts) {}
 static inline void ath_dynack_sample_tx_ts(struct ath_hw *ah,
 					   struct sk_buff *skb,
-					   struct ath_tx_status *ts) {}
+					   struct ath_tx_status *ts,
+					   struct ieee80211_sta *sta) {}
 #endif
 
 #endif /* DYNACK_H */
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 25b3fc82d4ac..f448d5716639 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -629,7 +629,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq,
 				if (bf == bf->bf_lastbf)
 					ath_dynack_sample_tx_ts(sc->sc_ah,
 								bf->bf_mpdu,
-								ts);
+								ts, sta);
 			}
 
 			ath_tx_complete_buf(sc, bf, txq, &bf_head, sta, ts,
@@ -773,7 +773,8 @@ static void ath_tx_process_buffer(struct ath_softc *sc, struct ath_txq *txq,
 			memcpy(info->control.rates, bf->rates,
 			       sizeof(info->control.rates));
 			ath_tx_rc_status(sc, bf, ts, 1, txok ? 0 : 1, txok);
-			ath_dynack_sample_tx_ts(sc->sc_ah, bf->bf_mpdu, ts);
+			ath_dynack_sample_tx_ts(sc->sc_ah, bf->bf_mpdu, ts,
+						sta);
 		}
 		ath_tx_complete_buf(sc, bf, txq, bf_head, sta, ts, txok);
 	} else
-- 
cgit v1.2.3


From 55bb78d265c6bdebbe2fbfe2c7a30539f3b3412c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 2 Nov 2018 21:49:59 +0100
Subject: ath9k: dynack: remove 'experimental' tag

Remove experimental tag from dynack Kconfig entry since it has
been tested on outdoor 25Km links

Tested-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/Kconfig b/drivers/net/wireless/ath/ath9k/Kconfig
index 1f3523019509..ceca23a851d5 100644
--- a/drivers/net/wireless/ath/ath9k/Kconfig
+++ b/drivers/net/wireless/ath/ath9k/Kconfig
@@ -116,7 +116,7 @@ config ATH9K_DFS_CERTIFIED
 	  except increase code size.
 
 config ATH9K_DYNACK
-	bool "Atheros ath9k ACK timeout estimation algorithm (EXPERIMENTAL)"
+	bool "Atheros ath9k ACK timeout estimation algorithm"
 	depends on ATH9K
 	default n
 	---help---
-- 
cgit v1.2.3


From a1a3b762163868ad07a4499a73df324f40d5ab0b Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 10 Oct 2018 13:00:58 +0200
Subject: brcmfmac: Remove firmware-loading code duplication

brcmf_fw_request_next_item and brcmf_fw_request_done both have identical
code to complete the fw-request depending on the item-type.

This commit adds a new brcmf_fw_complete_request helper removing this code
duplication.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../broadcom/brcm80211/brcmfmac/firmware.c         | 62 +++++++++++-----------
 1 file changed, 31 insertions(+), 31 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
index 9095b830ae4d..784c84f0e9e7 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
@@ -504,6 +504,34 @@ fail:
 	return -ENOENT;
 }
 
+static int brcmf_fw_complete_request(const struct firmware *fw,
+				     struct brcmf_fw *fwctx)
+{
+	struct brcmf_fw_item *cur = &fwctx->req->items[fwctx->curpos];
+	int ret = 0;
+
+	brcmf_dbg(TRACE, "firmware %s %sfound\n", cur->path, fw ? "" : "not ");
+
+	switch (cur->type) {
+	case BRCMF_FW_TYPE_NVRAM:
+		ret = brcmf_fw_request_nvram_done(fw, fwctx);
+		break;
+	case BRCMF_FW_TYPE_BINARY:
+		if (fw)
+			cur->binary = fw;
+		else
+			ret = -ENOENT;
+		break;
+	default:
+		/* something fishy here so bail out early */
+		brcmf_err("unknown fw type: %d\n", cur->type);
+		release_firmware(fw);
+		ret = -EINVAL;
+	}
+
+	return (cur->flags & BRCMF_FW_REQF_OPTIONAL) ? 0 : ret;
+}
+
 static int brcmf_fw_request_next_item(struct brcmf_fw *fwctx, bool async)
 {
 	struct brcmf_fw_item *cur;
@@ -525,15 +553,7 @@ static int brcmf_fw_request_next_item(struct brcmf_fw *fwctx, bool async)
 	if (ret < 0) {
 		brcmf_fw_request_done(NULL, fwctx);
 	} else if (!async && fw) {
-		brcmf_dbg(TRACE, "firmware %s %sfound\n", cur->path,
-			  fw ? "" : "not ");
-		if (cur->type == BRCMF_FW_TYPE_BINARY)
-			cur->binary = fw;
-		else if (cur->type == BRCMF_FW_TYPE_NVRAM)
-			brcmf_fw_request_nvram_done(fw, fwctx);
-		else
-			release_firmware(fw);
-
+		brcmf_fw_complete_request(fw, fwctx);
 		return -EAGAIN;
 	}
 	return 0;
@@ -547,28 +567,8 @@ static void brcmf_fw_request_done(const struct firmware *fw, void *ctx)
 
 	cur = &fwctx->req->items[fwctx->curpos];
 
-	brcmf_dbg(TRACE, "enter: firmware %s %sfound\n", cur->path,
-		  fw ? "" : "not ");
-
-	if (!fw)
-		ret = -ENOENT;
-
-	switch (cur->type) {
-	case BRCMF_FW_TYPE_NVRAM:
-		ret = brcmf_fw_request_nvram_done(fw, fwctx);
-		break;
-	case BRCMF_FW_TYPE_BINARY:
-		cur->binary = fw;
-		break;
-	default:
-		/* something fishy here so bail out early */
-		brcmf_err("unknown fw type: %d\n", cur->type);
-		release_firmware(fw);
-		ret = -EINVAL;
-		goto fail;
-	}
-
-	if (ret < 0 && !(cur->flags & BRCMF_FW_REQF_OPTIONAL))
+	ret = brcmf_fw_complete_request(fw, fwctx);
+	if (ret < 0)
 		goto fail;
 
 	do {
-- 
cgit v1.2.3


From 5b587496dc63595b71265d986ce69728c2724370 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 10 Oct 2018 13:00:59 +0200
Subject: brcmfmac: Remove recursion from firmware load error handling

Before this commit brcmf_fw_request_done would call
brcmf_fw_request_next_item to load the next item, which on an error would
call brcmf_fw_request_done, which if the error is recoverable (*) will
then continue calling brcmf_fw_request_next_item for the next item again
which on an error will call brcmf_fw_request_done again...

This does not blow up because we only have a limited number of items so
we never recurse too deep. But the recursion is still quite ugly and
frankly is giving me a headache, so lets fix this.

This commit fixes this by removing brcmf_fw_request_next_item and by
making brcmf_fw_get_firmwares and brcmf_fw_request_done directly call
firmware_request_nowait resp. firmware_request themselves.

*) brcmf_fw_request_nvram_done fallback path succeeds or
   BRCMF_FW_REQF_OPTIONAL is set

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../broadcom/brcm80211/brcmfmac/firmware.c         | 65 +++++++---------------
 1 file changed, 19 insertions(+), 46 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
index 784c84f0e9e7..08aaf99fee34 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
@@ -532,33 +532,6 @@ static int brcmf_fw_complete_request(const struct firmware *fw,
 	return (cur->flags & BRCMF_FW_REQF_OPTIONAL) ? 0 : ret;
 }
 
-static int brcmf_fw_request_next_item(struct brcmf_fw *fwctx, bool async)
-{
-	struct brcmf_fw_item *cur;
-	const struct firmware *fw = NULL;
-	int ret;
-
-	cur = &fwctx->req->items[fwctx->curpos];
-
-	brcmf_dbg(TRACE, "%srequest for %s\n", async ? "async " : "",
-		  cur->path);
-
-	if (async)
-		ret = request_firmware_nowait(THIS_MODULE, true, cur->path,
-					      fwctx->dev, GFP_KERNEL, fwctx,
-					      brcmf_fw_request_done);
-	else
-		ret = request_firmware(&fw, cur->path, fwctx->dev);
-
-	if (ret < 0) {
-		brcmf_fw_request_done(NULL, fwctx);
-	} else if (!async && fw) {
-		brcmf_fw_complete_request(fw, fwctx);
-		return -EAGAIN;
-	}
-	return 0;
-}
-
 static void brcmf_fw_request_done(const struct firmware *fw, void *ctx)
 {
 	struct brcmf_fw *fwctx = ctx;
@@ -568,26 +541,19 @@ static void brcmf_fw_request_done(const struct firmware *fw, void *ctx)
 	cur = &fwctx->req->items[fwctx->curpos];
 
 	ret = brcmf_fw_complete_request(fw, fwctx);
-	if (ret < 0)
-		goto fail;
-
-	do {
-		if (++fwctx->curpos == fwctx->req->n_items) {
-			ret = 0;
-			goto done;
-		}
 
-		ret = brcmf_fw_request_next_item(fwctx, false);
-	} while (ret == -EAGAIN);
-
-	return;
+	while (ret == 0 && ++fwctx->curpos < fwctx->req->n_items) {
+		cur = &fwctx->req->items[fwctx->curpos];
+		request_firmware(&fw, cur->path, fwctx->dev);
+		ret = brcmf_fw_complete_request(fw, ctx);
+	}
 
-fail:
-	brcmf_dbg(TRACE, "failed err=%d: dev=%s, fw=%s\n", ret,
-		  dev_name(fwctx->dev), cur->path);
-	brcmf_fw_free_request(fwctx->req);
-	fwctx->req = NULL;
-done:
+	if (ret) {
+		brcmf_dbg(TRACE, "failed err=%d: dev=%s, fw=%s\n", ret,
+			  dev_name(fwctx->dev), cur->path);
+		brcmf_fw_free_request(fwctx->req);
+		fwctx->req = NULL;
+	}
 	fwctx->done(fwctx->dev, ret, fwctx->req);
 	kfree(fwctx);
 }
@@ -611,7 +577,9 @@ int brcmf_fw_get_firmwares(struct device *dev, struct brcmf_fw_request *req,
 			   void (*fw_cb)(struct device *dev, int err,
 					 struct brcmf_fw_request *req))
 {
+	struct brcmf_fw_item *first = &req->items[0];
 	struct brcmf_fw *fwctx;
+	int ret;
 
 	brcmf_dbg(TRACE, "enter: dev=%s\n", dev_name(dev));
 	if (!fw_cb)
@@ -628,7 +596,12 @@ int brcmf_fw_get_firmwares(struct device *dev, struct brcmf_fw_request *req,
 	fwctx->req = req;
 	fwctx->done = fw_cb;
 
-	brcmf_fw_request_next_item(fwctx, true);
+	ret = request_firmware_nowait(THIS_MODULE, true, first->path,
+				      fwctx->dev, GFP_KERNEL, fwctx,
+				      brcmf_fw_request_done);
+	if (ret < 0)
+		brcmf_fw_request_done(NULL, fwctx);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From eae8e50669e15002b195177212a6e25afbe7cf4d Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 10 Oct 2018 13:01:00 +0200
Subject: brcmfmac: Add support for first trying to get a board specific nvram
 file

The nvram files which some brcmfmac chips need are board-specific. To be
able to distribute these as part of linux-firmware, so that devices with
such a wifi chip will work OOTB, multiple (one per board) versions must
co-exist under /lib/firmware.

This commit adds support for callers of the brcmfmac/firmware.c code to
pass in a board_type parameter through the request structure.

If that parameter is set then the code will first try to load
chipmodel.board_type.txt before falling back to the old chipmodel.txt name.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../broadcom/brcm80211/brcmfmac/firmware.c         | 27 +++++++++++++++++++++-
 .../broadcom/brcm80211/brcmfmac/firmware.h         |  1 +
 2 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
index 08aaf99fee34..6755b2388fbc 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
@@ -532,6 +532,31 @@ static int brcmf_fw_complete_request(const struct firmware *fw,
 	return (cur->flags & BRCMF_FW_REQF_OPTIONAL) ? 0 : ret;
 }
 
+static int brcmf_fw_request_firmware(const struct firmware **fw,
+				     struct brcmf_fw *fwctx)
+{
+	struct brcmf_fw_item *cur = &fwctx->req->items[fwctx->curpos];
+	int ret;
+
+	/* nvram files are board-specific, first try a board-specific path */
+	if (cur->type == BRCMF_FW_TYPE_NVRAM && fwctx->req->board_type) {
+		char alt_path[BRCMF_FW_NAME_LEN];
+
+		strlcpy(alt_path, cur->path, BRCMF_FW_NAME_LEN);
+		/* strip .txt at the end */
+		alt_path[strlen(alt_path) - 4] = 0;
+		strlcat(alt_path, ".", BRCMF_FW_NAME_LEN);
+		strlcat(alt_path, fwctx->req->board_type, BRCMF_FW_NAME_LEN);
+		strlcat(alt_path, ".txt", BRCMF_FW_NAME_LEN);
+
+		ret = request_firmware(fw, alt_path, fwctx->dev);
+		if (ret == 0)
+			return ret;
+	}
+
+	return request_firmware(fw, cur->path, fwctx->dev);
+}
+
 static void brcmf_fw_request_done(const struct firmware *fw, void *ctx)
 {
 	struct brcmf_fw *fwctx = ctx;
@@ -544,7 +569,7 @@ static void brcmf_fw_request_done(const struct firmware *fw, void *ctx)
 
 	while (ret == 0 && ++fwctx->curpos < fwctx->req->n_items) {
 		cur = &fwctx->req->items[fwctx->curpos];
-		request_firmware(&fw, cur->path, fwctx->dev);
+		brcmf_fw_request_firmware(&fw, fwctx);
 		ret = brcmf_fw_complete_request(fw, ctx);
 	}
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h
index 2893e56910f0..a0834be8864e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h
@@ -70,6 +70,7 @@ struct brcmf_fw_request {
 	u16 domain_nr;
 	u16 bus_nr;
 	u32 n_items;
+	const char *board_type;
 	struct brcmf_fw_item items[0];
 };
 
-- 
cgit v1.2.3


From 0ad4b55b2f29784f93875e6231bf57cd233624a2 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 10 Oct 2018 13:01:01 +0200
Subject: brcmfmac: Set board_type used for nvram file selection to
 machine-compatible

For of/devicetree using machines, set the board_type used for nvram file
selection to the first string listed in the top-level's node compatible
string, aka the machine-compatible as used by of_machine_is_compatible().

The board_type setting is used to load the board-specific nvram file with
a board-specific name so that we can ship files for each supported board
in linux-firmware.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h |  1 +
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c     | 11 ++++++++++-
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c   |  1 +
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c   |  1 +
 4 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h
index a34642cb4d2f..e63a273642e9 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h
@@ -59,6 +59,7 @@ struct brcmf_mp_device {
 	bool		iapp;
 	bool		ignore_probe_fail;
 	struct brcmfmac_pd_cc *country_codes;
+	const char	*board_type;
 	union {
 		struct brcmfmac_sdio_pd sdio;
 	} bus;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
index aee6e5937c41..84e3373289eb 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
@@ -27,11 +27,20 @@ void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type,
 		    struct brcmf_mp_device *settings)
 {
 	struct brcmfmac_sdio_pd *sdio = &settings->bus.sdio;
-	struct device_node *np = dev->of_node;
+	struct device_node *root, *np = dev->of_node;
+	struct property *prop;
 	int irq;
 	u32 irqf;
 	u32 val;
 
+	/* Set board-type to the first string of the machine compatible prop */
+	root = of_find_node_by_path("/");
+	if (root) {
+		prop = of_find_property(root, "compatible", NULL);
+		settings->board_type = of_prop_next_string(prop, NULL);
+		of_node_put(root);
+	}
+
 	if (!np || bus_type != BRCMF_BUSTYPE_SDIO ||
 	    !of_device_is_compatible(np, "brcm,bcm4329-fmac"))
 		return;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index 5dea569d63ed..956a8b236836 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -1785,6 +1785,7 @@ brcmf_pcie_prepare_fw_request(struct brcmf_pciedev_info *devinfo)
 	fwreq->items[BRCMF_PCIE_FW_CODE].type = BRCMF_FW_TYPE_BINARY;
 	fwreq->items[BRCMF_PCIE_FW_NVRAM].type = BRCMF_FW_TYPE_NVRAM;
 	fwreq->items[BRCMF_PCIE_FW_NVRAM].flags = BRCMF_FW_REQF_OPTIONAL;
+	fwreq->board_type = devinfo->settings->board_type;
 	/* NVRAM reserves PCI domain 0 for Broadcom's SDK faked bus */
 	fwreq->domain_nr = pci_domain_nr(devinfo->pdev->bus) + 1;
 	fwreq->bus_nr = devinfo->pdev->bus->number;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index b2e1ab5adb64..22646a3b911e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4174,6 +4174,7 @@ brcmf_sdio_prepare_fw_request(struct brcmf_sdio *bus)
 
 	fwreq->items[BRCMF_SDIO_FW_CODE].type = BRCMF_FW_TYPE_BINARY;
 	fwreq->items[BRCMF_SDIO_FW_NVRAM].type = BRCMF_FW_TYPE_NVRAM;
+	fwreq->board_type = bus->sdiodev->settings->board_type;
 
 	return fwreq;
 }
-- 
cgit v1.2.3


From bd1e82bb420adf4ad7cd468d8a482cde622dd69d Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 10 Oct 2018 13:01:02 +0200
Subject: brcmfmac: Set board_type from DMI on x86 based machines

For x86 based machines, set the board_type used for nvram file selection
based on the DMI sys-vendor and product-name strings.

Since on some models these strings are too generic, this commit also adds
a quirk table overriding the strings for models listed in that table.

The board_type setting is used to load the board-specific nvram file with
a board-specific name so that we can ship files for each supported board
in linux-firmware.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../wireless/broadcom/brcm80211/brcmfmac/Makefile  |   2 +
 .../wireless/broadcom/brcm80211/brcmfmac/common.c  |   3 +-
 .../wireless/broadcom/brcm80211/brcmfmac/common.h  |   7 ++
 .../net/wireless/broadcom/brcm80211/brcmfmac/dmi.c | 116 +++++++++++++++++++++
 4 files changed, 127 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile
index 1f5a9b948abf..22fd95a736a8 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile
@@ -54,3 +54,5 @@ brcmfmac-$(CONFIG_BRCM_TRACING) += \
 		tracepoint.o
 brcmfmac-$(CONFIG_OF) += \
 		of.o
+brcmfmac-$(CONFIG_DMI) += \
+		dmi.o
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
index 94044a7a6021..d52774c6489b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
@@ -448,8 +448,9 @@ struct brcmf_mp_device *brcmf_get_module_param(struct device *dev,
 		}
 	}
 	if (!found) {
-		/* No platform data for this device, try OF (Open Firwmare) */
+		/* No platform data for this device, try OF and DMI data */
 		brcmf_of_probe(dev, bus_type, settings);
+		brcmf_dmi_probe(settings, chip, chiprev);
 	}
 	return settings;
 }
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h
index e63a273642e9..4ce56be90b74 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h
@@ -75,4 +75,11 @@ void brcmf_release_module_param(struct brcmf_mp_device *module_param);
 /* Sets dongle media info (drv_version, mac address). */
 int brcmf_c_preinit_dcmds(struct brcmf_if *ifp);
 
+#ifdef CONFIG_DMI
+void brcmf_dmi_probe(struct brcmf_mp_device *settings, u32 chip, u32 chiprev);
+#else
+static inline void
+brcmf_dmi_probe(struct brcmf_mp_device *settings, u32 chip, u32 chiprev) {}
+#endif
+
 #endif /* BRCMFMAC_COMMON_H */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c
new file mode 100644
index 000000000000..51d76ac45075
--- /dev/null
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright 2018 Hans de Goede <hdegoede@redhat.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
+ * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION
+ * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
+ * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/dmi.h>
+#include <linux/mod_devicetable.h>
+#include "core.h"
+#include "common.h"
+#include "brcm_hw_ids.h"
+
+/* The DMI data never changes so we can use a static buf for this */
+static char dmi_board_type[128];
+
+struct brcmf_dmi_data {
+	u32 chip;
+	u32 chiprev;
+	const char *board_type;
+};
+
+/* NOTE: Please keep all entries sorted alphabetically */
+
+static const struct brcmf_dmi_data gpd_win_pocket_data = {
+	BRCM_CC_4356_CHIP_ID, 2, "gpd-win-pocket"
+};
+
+static const struct brcmf_dmi_data jumper_ezpad_mini3_data = {
+	BRCM_CC_43430_CHIP_ID, 0, "jumper-ezpad-mini3"
+};
+
+static const struct brcmf_dmi_data meegopad_t08_data = {
+	BRCM_CC_43340_CHIP_ID, 2, "meegopad-t08"
+};
+
+static const struct dmi_system_id dmi_platform_data[] = {
+	{
+		/* Match for the GPDwin which unfortunately uses somewhat
+		 * generic dmi strings, which is why we test for 4 strings.
+		 * Comparing against 23 other byt/cht boards, board_vendor
+		 * and board_name are unique to the GPDwin, where as only one
+		 * other board has the same board_serial and 3 others have
+		 * the same default product_name. Also the GPDwin is the
+		 * only device to have both board_ and product_name not set.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
+			DMI_MATCH(DMI_BOARD_NAME, "Default string"),
+			DMI_MATCH(DMI_BOARD_SERIAL, "Default string"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
+		},
+		.driver_data = (void *)&gpd_win_pocket_data,
+	},
+	{
+		/* Jumper EZpad mini3 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "CherryTrail"),
+			/* jumperx.T87.KFBNEEA02 with the version-nr dropped */
+			DMI_MATCH(DMI_BIOS_VERSION, "jumperx.T87.KFBNEEA"),
+		},
+		.driver_data = (void *)&jumper_ezpad_mini3_data,
+	},
+	{
+		/* Meegopad T08 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Default string"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
+			DMI_MATCH(DMI_BOARD_NAME, "T3 MRD"),
+			DMI_MATCH(DMI_BOARD_VERSION, "V1.1"),
+		},
+		.driver_data = (void *)&meegopad_t08_data,
+	},
+	{}
+};
+
+void brcmf_dmi_probe(struct brcmf_mp_device *settings, u32 chip, u32 chiprev)
+{
+	const struct dmi_system_id *match;
+	const struct brcmf_dmi_data *data;
+	const char *sys_vendor;
+	const char *product_name;
+
+	/* Some models have DMI strings which are too generic, e.g.
+	 * "Default string", we use a quirk table for these.
+	 */
+	for (match = dmi_first_match(dmi_platform_data);
+	     match;
+	     match = dmi_first_match(match + 1)) {
+		data = match->driver_data;
+
+		if (data->chip == chip && data->chiprev == chiprev) {
+			settings->board_type = data->board_type;
+			return;
+		}
+	}
+
+	/* Not found in the quirk-table, use sys_vendor-product_name */
+	sys_vendor = dmi_get_system_info(DMI_SYS_VENDOR);
+	product_name = dmi_get_system_info(DMI_PRODUCT_NAME);
+	if (sys_vendor && product_name) {
+		snprintf(dmi_board_type, sizeof(dmi_board_type), "%s-%s",
+			 sys_vendor, product_name);
+		settings->board_type = dmi_board_type;
+	}
+}
-- 
cgit v1.2.3


From 55e491edbf14b2da5419c2a319ea3b1d6368d9a2 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 10 Oct 2018 13:01:03 +0200
Subject: brcmfmac: Cleanup brcmf_fw_request_done()

The "cur" variable is now only used for a debug print and we already
print the same info from brcmf_fw_complete_request(), so the debug print
does not provide any extra info and we can remove it.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
index 6755b2388fbc..b38c4b40b235 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
@@ -560,22 +560,16 @@ static int brcmf_fw_request_firmware(const struct firmware **fw,
 static void brcmf_fw_request_done(const struct firmware *fw, void *ctx)
 {
 	struct brcmf_fw *fwctx = ctx;
-	struct brcmf_fw_item *cur;
-	int ret = 0;
-
-	cur = &fwctx->req->items[fwctx->curpos];
+	int ret;
 
 	ret = brcmf_fw_complete_request(fw, fwctx);
 
 	while (ret == 0 && ++fwctx->curpos < fwctx->req->n_items) {
-		cur = &fwctx->req->items[fwctx->curpos];
 		brcmf_fw_request_firmware(&fw, fwctx);
 		ret = brcmf_fw_complete_request(fw, ctx);
 	}
 
 	if (ret) {
-		brcmf_dbg(TRACE, "failed err=%d: dev=%s, fw=%s\n", ret,
-			  dev_name(fwctx->dev), cur->path);
 		brcmf_fw_free_request(fwctx->req);
 		fwctx->req = NULL;
 	}
-- 
cgit v1.2.3


From ce2e6db554fad444fa0b3904fc3015336e0ef765 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 11 Oct 2018 11:51:06 +0200
Subject: brcmfmac: Add support for getting nvram contents from EFI variables

Various X86 laptops with a SDIO attached brcmfmac wifi chip, store the
nvram contents in a special EFI variable. This commit adds support for
getting nvram directly from this EFI variable, without the user needing
to manually copy it.

This makes Wifi / Bluetooth work out of the box on these devices instead of
requiring manual setup.

This has been tested on the following models: Acer Iconia Tab8 w1-810,
Acer One 10, Asus T100CHI, Asus T100HA, Asus T100TA, Asus T200TA and a
Lenovo Mixx 2 8.

Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../broadcom/brcm80211/brcmfmac/firmware.c         | 63 +++++++++++++++++++---
 1 file changed, 57 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
index b38c4b40b235..965ae5c24c2d 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
@@ -14,6 +14,7 @@
  * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
 
+#include <linux/efi.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/device.h>
@@ -445,6 +446,51 @@ struct brcmf_fw {
 
 static void brcmf_fw_request_done(const struct firmware *fw, void *ctx);
 
+#ifdef CONFIG_EFI
+static u8 *brcmf_fw_nvram_from_efi(size_t *data_len_ret)
+{
+	const u16 name[] = { 'n', 'v', 'r', 'a', 'm', 0 };
+	struct efivar_entry *nvram_efivar;
+	unsigned long data_len = 0;
+	u8 *data = NULL;
+	int err;
+
+	nvram_efivar = kzalloc(sizeof(*nvram_efivar), GFP_KERNEL);
+	if (!nvram_efivar)
+		return NULL;
+
+	memcpy(&nvram_efivar->var.VariableName, name, sizeof(name));
+	nvram_efivar->var.VendorGuid = EFI_GUID(0x74b00bd9, 0x805a, 0x4d61,
+						0xb5, 0x1f, 0x43, 0x26,
+						0x81, 0x23, 0xd1, 0x13);
+
+	err = efivar_entry_size(nvram_efivar, &data_len);
+	if (err)
+		goto fail;
+
+	data = kmalloc(data_len, GFP_KERNEL);
+	if (!data)
+		goto fail;
+
+	err = efivar_entry_get(nvram_efivar, NULL, &data_len, data);
+	if (err)
+		goto fail;
+
+	brcmf_info("Using nvram EFI variable\n");
+
+	kfree(nvram_efivar);
+	*data_len_ret = data_len;
+	return data;
+
+fail:
+	kfree(data);
+	kfree(nvram_efivar);
+	return NULL;
+}
+#else
+static u8 *brcmf_fw_nvram_from_efi(size_t *data_len) { return NULL; }
+#endif
+
 static void brcmf_fw_free_request(struct brcmf_fw_request *req)
 {
 	struct brcmf_fw_item *item;
@@ -463,11 +509,12 @@ static int brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
 {
 	struct brcmf_fw *fwctx = ctx;
 	struct brcmf_fw_item *cur;
+	bool free_bcm47xx_nvram = false;
+	bool kfree_nvram = false;
 	u32 nvram_length = 0;
 	void *nvram = NULL;
 	u8 *data = NULL;
 	size_t data_len;
-	bool raw_nvram;
 
 	brcmf_dbg(TRACE, "enter: dev=%s\n", dev_name(fwctx->dev));
 
@@ -476,12 +523,13 @@ static int brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
 	if (fw && fw->data) {
 		data = (u8 *)fw->data;
 		data_len = fw->size;
-		raw_nvram = false;
 	} else {
-		data = bcm47xx_nvram_get_contents(&data_len);
-		if (!data && !(cur->flags & BRCMF_FW_REQF_OPTIONAL))
+		if ((data = bcm47xx_nvram_get_contents(&data_len)))
+			free_bcm47xx_nvram = true;
+		else if ((data = brcmf_fw_nvram_from_efi(&data_len)))
+			kfree_nvram = true;
+		else if (!(cur->flags & BRCMF_FW_REQF_OPTIONAL))
 			goto fail;
-		raw_nvram = true;
 	}
 
 	if (data)
@@ -489,8 +537,11 @@ static int brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
 					     fwctx->req->domain_nr,
 					     fwctx->req->bus_nr);
 
-	if (raw_nvram)
+	if (free_bcm47xx_nvram)
 		bcm47xx_nvram_release_contents(data);
+	if (kfree_nvram)
+		kfree(data);
+
 	release_firmware(fw);
 	if (!nvram && !(cur->flags & BRCMF_FW_REQF_OPTIONAL))
 		goto fail;
-- 
cgit v1.2.3


From 29ec3394f0bd85c22674ab6693d92da5e2324610 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 11 Oct 2018 11:51:07 +0200
Subject: brcmfmac: Fix ccode from EFI nvram when necessary

In some cases the EFI-var stored nvram contains "ccode=ALL" or "ccode=XV"
to specify "worldwide" compatible settings, but these 2 ccode-s do not work
properly.

I've tested the different known "worldwide" ccode-s used in various nvram
sources with the latest firmwares from linux-firmware for various brcmfmac
models, here is a simplified (*) table with what each setting results in:

ALL: 12-14 disab, U-NII-1, U-NII-2 no-IR/radar, U-NII-3
XV:  12-14 no-IR, disables all 5G channels
XY:  12-13 enab, 14 disab, U-NII-1 enab, U-NII-2 no-IR/radar, U-NII-3 disab
X2:  12-13 no-IR, 14 dis, U-NII-1 no-IR, U-NII-2 no-IR/radar, U-NII-3 no-IR

Where 12,13,14 are 2.4G channels 12-14 and U-NII-1/2/3 are the 3 different
5G channel groups. no-IR is no-Initiate-Radiation, we will never send on
these channels without first having received valid wifi traffic there.

This immediately shows that both ALL and XV are not as worldwide as we want
them to be. ALL causes channels 12 and 13 to not be available and XV causes
all 5GHz channels to not be available. Also ALL unconditionally enables the
U-NII-1 and U-NII-3 5G groups, while we really should be using no-IR for
these.

This commit replace XV and ALL with X2, which allows usage of chan 12-13
and 5G channels, but only after receiving valid wifi traffic there first.

Note that this configure the firmware's channel limits, the kernels own
regulatory restrictions based on e.g. regulatory info received from the
access-point, will be applied on top of this.

This fixes channels 12+13 not working on the Asus T200TA and the Lenovo
Mixx 2 8 and 5G channels not working on the Asus T100HA.

This has been tested on the following models: Acer Iconia Tab8 w1-810,
Acer One 10, Asus T100CHI, Asus T100HA, Asus T100TA, Asus T200TA and a
Lenovo Mixx 2 8.

*) There are some exceptions to this table:
1) On really old firmware e.g. linux-firmware's 2011 brcmfmac4330-sdio.bin
   ALL really means all, unconditionally enabling everything
2) The exact meaning might be influenced by setting the regrev nvram var.
   Specifically using ccode=XV + regrev=1 on brcmfmac43241b4 leads to:
   12-14 no-ir, U-NII-1 no-ir, U-NII-2 no-ir/radar, U-NII-3 no-ir
   But only on the brcmfmac43241b4 and not on e.g. the brcmfmac43340

Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../broadcom/brcm80211/brcmfmac/firmware.c         | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
index 965ae5c24c2d..72d8c0c3c3a1 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
@@ -447,6 +447,29 @@ struct brcmf_fw {
 static void brcmf_fw_request_done(const struct firmware *fw, void *ctx);
 
 #ifdef CONFIG_EFI
+/* In some cases the EFI-var stored nvram contains "ccode=ALL" or "ccode=XV"
+ * to specify "worldwide" compatible settings, but these 2 ccode-s do not work
+ * properly. "ccode=ALL" causes channels 12 and 13 to not be available,
+ * "ccode=XV" causes all 5GHz channels to not be available. So we replace both
+ * with "ccode=X2" which allows channels 12+13 and 5Ghz channels in
+ * no-Initiate-Radiation mode. This means that we will never send on these
+ * channels without first having received valid wifi traffic on the channel.
+ */
+static void brcmf_fw_fix_efi_nvram_ccode(char *data, unsigned long data_len)
+{
+	char *ccode;
+
+	ccode = strnstr((char *)data, "ccode=ALL", data_len);
+	if (!ccode)
+		ccode = strnstr((char *)data, "ccode=XV\r", data_len);
+	if (!ccode)
+		return;
+
+	ccode[6] = 'X';
+	ccode[7] = '2';
+	ccode[8] = '\r';
+}
+
 static u8 *brcmf_fw_nvram_from_efi(size_t *data_len_ret)
 {
 	const u16 name[] = { 'n', 'v', 'r', 'a', 'm', 0 };
@@ -476,6 +499,7 @@ static u8 *brcmf_fw_nvram_from_efi(size_t *data_len_ret)
 	if (err)
 		goto fail;
 
+	brcmf_fw_fix_efi_nvram_ccode(data, data_len);
 	brcmf_info("Using nvram EFI variable\n");
 
 	kfree(nvram_efivar);
-- 
cgit v1.2.3


From 55930d2bf79bfed9c7a435e7920123b16620ee27 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 13 Oct 2018 16:37:30 +0100
Subject: rsi: fix spelling mistake "Initialzing" -> "Initializing"

Trivial fix to spelling mistake in rsi_dbg debug message

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_91x_sdio_ops.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
index 612c211e21a1..449f6d23c5e3 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
@@ -210,7 +210,7 @@ int rsi_init_sdio_slave_regs(struct rsi_hw *adapter)
 	}
 
 	/* This tells SDIO FIFO when to start read to host */
-	rsi_dbg(INIT_ZONE, "%s: Initialzing SDIO read start level\n", __func__);
+	rsi_dbg(INIT_ZONE, "%s: Initializing SDIO read start level\n", __func__);
 	byte = 0x24;
 
 	status = rsi_sdio_write_register(adapter,
@@ -223,7 +223,7 @@ int rsi_init_sdio_slave_regs(struct rsi_hw *adapter)
 		return -1;
 	}
 
-	rsi_dbg(INIT_ZONE, "%s: Initialzing FIFO ctrl registers\n", __func__);
+	rsi_dbg(INIT_ZONE, "%s: Initializing FIFO ctrl registers\n", __func__);
 	byte = (128 - 32);
 
 	status = rsi_sdio_write_register(adapter,
-- 
cgit v1.2.3


From 937a13091cbd36d2cf1c266522f962ef6fe84bb5 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 15 Oct 2018 02:16:35 +0000
Subject: libertas: remove set but not used variable 'int_type'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/wireless/marvell/libertas/if_spi.c: In function 'if_spi_h2c':
drivers/net/wireless/marvell/libertas/if_spi.c:799:6: warning:
 variable 'int_type' set but not used [-Wunused-but-set-variable]

It never used since introduction in
commit d2b21f191753 ("libertas: if_spi, driver for libertas GSPI devices")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Tested-by: Lubomir Rintel <lkundrak@v3.sk>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/libertas/if_spi.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/if_spi.c b/drivers/net/wireless/marvell/libertas/if_spi.c
index 504d6e096476..7c3224b83ef7 100644
--- a/drivers/net/wireless/marvell/libertas/if_spi.c
+++ b/drivers/net/wireless/marvell/libertas/if_spi.c
@@ -796,15 +796,13 @@ static void if_spi_h2c(struct if_spi_card *card,
 {
 	struct lbs_private *priv = card->priv;
 	int err = 0;
-	u16 int_type, port_reg;
+	u16 port_reg;
 
 	switch (type) {
 	case MVMS_DAT:
-		int_type = IF_SPI_CIC_TX_DOWNLOAD_OVER;
 		port_reg = IF_SPI_DATA_RDWRPORT_REG;
 		break;
 	case MVMS_CMD:
-		int_type = IF_SPI_CIC_CMD_DOWNLOAD_OVER;
 		port_reg = IF_SPI_CMD_RDWRPORT_REG;
 		break;
 	default:
-- 
cgit v1.2.3


From 3419348a97bcc256238101129d69b600ceb5cc70 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 16 Oct 2018 09:39:40 +0200
Subject: wlcore: Fix the return value in case of error in
 'wlcore_vendor_cmd_smart_config_start()'

We return 0 unconditionally at the end of
'wlcore_vendor_cmd_smart_config_start()'.
However, 'ret' is set to some error codes in several error handling paths
and we already return some error codes at the beginning of the function.

Return 'ret' instead to propagate the error code.

Fixes: 80ff8063e87c ("wlcore: handle smart config vendor commands")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wlcore/vendor_cmd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ti/wlcore/vendor_cmd.c b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
index dbe78d8491ef..7f34ec077ee5 100644
--- a/drivers/net/wireless/ti/wlcore/vendor_cmd.c
+++ b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
@@ -70,7 +70,7 @@ wlcore_vendor_cmd_smart_config_start(struct wiphy *wiphy,
 out:
 	mutex_unlock(&wl->mutex);
 
-	return 0;
+	return ret;
 }
 
 static int
-- 
cgit v1.2.3


From b7da53cd6cd13a782bb08e59b4a3358ec800f724 Mon Sep 17 00:00:00 2001
From: Igor Mitsyanko <igor.mitsyanko.os@quantenna.com>
Date: Tue, 16 Oct 2018 10:23:56 +0000
Subject: qtnfmac_pcie: use single PCIe driver for all platforms

Single PCIe driver can identify hardware type by reading CHIP ID at
probe time and invoking a correct initialization sequence.

Signed-off-by: Igor Mitsyanko <igor.mitsyanko.os@quantenna.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/quantenna/qtnfmac/Kconfig     |  10 +-
 drivers/net/wireless/quantenna/qtnfmac/Makefile    |   6 +-
 drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c | 279 ++++++++++++++-------
 .../wireless/quantenna/qtnfmac/pcie/pcie_priv.h    |  19 +-
 .../wireless/quantenna/qtnfmac/pcie/pearl_pcie.c   | 211 +++++-----------
 drivers/net/wireless/quantenna/qtnfmac/util.c      |  16 ++
 drivers/net/wireless/quantenna/qtnfmac/util.h      |   2 +
 7 files changed, 292 insertions(+), 251 deletions(-)

diff --git a/drivers/net/wireless/quantenna/qtnfmac/Kconfig b/drivers/net/wireless/quantenna/qtnfmac/Kconfig
index b8c12a5f16b4..696c50066b53 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/Kconfig
+++ b/drivers/net/wireless/quantenna/qtnfmac/Kconfig
@@ -1,10 +1,10 @@
 config QTNFMAC
 	tristate
-	depends on QTNFMAC_PEARL_PCIE
-	default m if QTNFMAC_PEARL_PCIE=m
-	default y if QTNFMAC_PEARL_PCIE=y
+	depends on QTNFMAC_PCIE
+	default m if QTNFMAC_PCIE=m
+	default y if QTNFMAC_PCIE=y
 
-config QTNFMAC_PEARL_PCIE
+config QTNFMAC_PCIE
 	tristate "Quantenna QSR10g PCIe support"
 	default n
 	depends on PCI && CFG80211
@@ -16,4 +16,4 @@ config QTNFMAC_PEARL_PCIE
 	  802.11ac QSR10g (aka Pearl) FullMAC chipset running over PCIe.
 
 	  If you choose to build it as a module, two modules will be built:
-	  qtnfmac.ko and qtnfmac_pearl_pcie.ko.
+	  qtnfmac.ko and qtnfmac_pcie.ko.
diff --git a/drivers/net/wireless/quantenna/qtnfmac/Makefile b/drivers/net/wireless/quantenna/qtnfmac/Makefile
index 17cd7adb4109..d7e8185fddab 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/Makefile
+++ b/drivers/net/wireless/quantenna/qtnfmac/Makefile
@@ -19,11 +19,11 @@ qtnfmac-objs += \
 
 #
 
-obj-$(CONFIG_QTNFMAC_PEARL_PCIE) += qtnfmac_pearl_pcie.o
+obj-$(CONFIG_QTNFMAC_PCIE) += qtnfmac_pcie.o
 
-qtnfmac_pearl_pcie-objs += \
+qtnfmac_pcie-objs += \
 	shm_ipc.o \
 	pcie/pcie.o \
 	pcie/pearl_pcie.o
 
-qtnfmac_pearl_pcie-$(CONFIG_DEBUG_FS) += debug.o
+qtnfmac_pcie-$(CONFIG_DEBUG_FS) += debug.o
diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c
index 16795dbe475b..70dd8da5b0dc 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0+
 /* Copyright (c) 2018 Quantenna Communications, Inc. All rights reserved. */
 
+#include <linux/module.h>
 #include <linux/printk.h>
 #include <linux/pci.h>
 #include <linux/spinlock.h>
@@ -15,14 +16,37 @@
 #include "shm_ipc.h"
 #include "core.h"
 #include "debug.h"
-
-#undef pr_fmt
-#define pr_fmt(fmt)	"qtnf_pcie: %s: " fmt, __func__
+#include "util.h"
+#include "qtn_hw_ids.h"
 
 #define QTN_SYSCTL_BAR	0
 #define QTN_SHMEM_BAR	2
 #define QTN_DMA_BAR	3
 
+#define QTN_PCIE_MAX_FW_BUFSZ		(1 * 1024 * 1024)
+
+static bool use_msi = true;
+module_param(use_msi, bool, 0644);
+MODULE_PARM_DESC(use_msi, "set 0 to use legacy interrupt");
+
+static unsigned int tx_bd_size_param;
+module_param(tx_bd_size_param, uint, 0644);
+MODULE_PARM_DESC(tx_bd_size_param, "Tx descriptors queue size");
+
+static unsigned int rx_bd_size_param = 256;
+module_param(rx_bd_size_param, uint, 0644);
+MODULE_PARM_DESC(rx_bd_size_param, "Rx descriptors queue size");
+
+static u8 flashboot = 1;
+module_param(flashboot, byte, 0644);
+MODULE_PARM_DESC(flashboot, "set to 0 to use FW binary file on FS");
+
+static unsigned int fw_blksize_param = QTN_PCIE_MAX_FW_BUFSZ;
+module_param(fw_blksize_param, uint, 0644);
+MODULE_PARM_DESC(fw_blksize_param, "firmware loading block size in bytes");
+
+#define DRV_NAME	"qtnfmac_pcie"
+
 int qtnf_pcie_control_tx(struct qtnf_bus *bus, struct sk_buff *skb)
 {
 	struct qtnf_pcie_bus_priv *priv = get_bus_priv(bus);
@@ -58,7 +82,7 @@ int qtnf_pcie_alloc_skb_array(struct qtnf_pcie_bus_priv *priv)
 	return 0;
 }
 
-void qtnf_pcie_bringup_fw_async(struct qtnf_bus *bus)
+static void qtnf_pcie_bringup_fw_async(struct qtnf_bus *bus)
 {
 	struct qtnf_pcie_bus_priv *priv = get_bus_priv(bus);
 	struct pci_dev *pdev = priv->pdev;
@@ -72,7 +96,7 @@ static int qtnf_dbg_mps_show(struct seq_file *s, void *data)
 	struct qtnf_bus *bus = dev_get_drvdata(s->private);
 	struct qtnf_pcie_bus_priv *priv = get_bus_priv(bus);
 
-	seq_printf(s, "%d\n", priv->mps);
+	seq_printf(s, "%d\n", pcie_get_mps(priv->pdev));
 
 	return 0;
 }
@@ -104,8 +128,7 @@ static int qtnf_dbg_shm_stats(struct seq_file *s, void *data)
 	return 0;
 }
 
-void qtnf_pcie_fw_boot_done(struct qtnf_bus *bus, bool boot_success,
-			    const char *drv_name)
+void qtnf_pcie_fw_boot_done(struct qtnf_bus *bus, bool boot_success)
 {
 	struct qtnf_pcie_bus_priv *priv = get_bus_priv(bus);
 	struct pci_dev *pdev = priv->pdev;
@@ -122,7 +145,7 @@ void qtnf_pcie_fw_boot_done(struct qtnf_bus *bus, bool boot_success,
 	}
 
 	if (boot_success) {
-		qtnf_debugfs_init(bus, drv_name);
+		qtnf_debugfs_init(bus, DRV_NAME);
 		qtnf_debugfs_add_entry(bus, "mps", qtnf_dbg_mps_show);
 		qtnf_debugfs_add_entry(bus, "msi_enabled", qtnf_dbg_msi_show);
 		qtnf_debugfs_add_entry(bus, "shm_stats", qtnf_dbg_shm_stats);
@@ -133,9 +156,8 @@ void qtnf_pcie_fw_boot_done(struct qtnf_bus *bus, bool boot_success,
 	put_device(&pdev->dev);
 }
 
-static void qtnf_tune_pcie_mps(struct qtnf_pcie_bus_priv *priv)
+static void qtnf_tune_pcie_mps(struct pci_dev *pdev)
 {
-	struct pci_dev *pdev = priv->pdev;
 	struct pci_dev *parent;
 	int mps_p, mps_o, mps_m, mps;
 	int ret;
@@ -163,12 +185,10 @@ static void qtnf_tune_pcie_mps(struct qtnf_pcie_bus_priv *priv)
 	if (ret) {
 		pr_err("failed to set mps to %d, keep using current %d\n",
 		       mps, mps_o);
-		priv->mps = mps_o;
 		return;
 	}
 
 	pr_debug("set mps to %d (was %d, max %d)\n", mps, mps_o, mps_m);
-	priv->mps = mps;
 }
 
 static void qtnf_pcie_init_irq(struct qtnf_pcie_bus_priv *priv, bool use_msi)
@@ -194,20 +214,20 @@ static void qtnf_pcie_init_irq(struct qtnf_pcie_bus_priv *priv, bool use_msi)
 	}
 }
 
-static void __iomem *qtnf_map_bar(struct qtnf_pcie_bus_priv *priv, u8 index)
+static void __iomem *qtnf_map_bar(struct pci_dev *pdev, u8 index)
 {
 	void __iomem *vaddr;
 	dma_addr_t busaddr;
 	size_t len;
 	int ret;
 
-	ret = pcim_iomap_regions(priv->pdev, 1 << index, "qtnfmac_pcie");
+	ret = pcim_iomap_regions(pdev, 1 << index, "qtnfmac_pcie");
 	if (ret)
 		return IOMEM_ERR_PTR(ret);
 
-	busaddr = pci_resource_start(priv->pdev, index);
-	len = pci_resource_len(priv->pdev, index);
-	vaddr = pcim_iomap_table(priv->pdev)[index];
+	busaddr = pci_resource_start(pdev, index);
+	len = pci_resource_len(pdev, index);
+	vaddr = pcim_iomap_table(pdev)[index];
 	if (!vaddr)
 		return IOMEM_ERR_PTR(-ENOMEM);
 
@@ -217,31 +237,6 @@ static void __iomem *qtnf_map_bar(struct qtnf_pcie_bus_priv *priv, u8 index)
 	return vaddr;
 }
 
-static int qtnf_pcie_init_memory(struct qtnf_pcie_bus_priv *priv)
-{
-	int ret = -ENOMEM;
-
-	priv->sysctl_bar = qtnf_map_bar(priv, QTN_SYSCTL_BAR);
-	if (IS_ERR(priv->sysctl_bar)) {
-		pr_err("failed to map BAR%u\n", QTN_SYSCTL_BAR);
-		return ret;
-	}
-
-	priv->dmareg_bar = qtnf_map_bar(priv, QTN_DMA_BAR);
-	if (IS_ERR(priv->dmareg_bar)) {
-		pr_err("failed to map BAR%u\n", QTN_DMA_BAR);
-		return ret;
-	}
-
-	priv->epmem_bar = qtnf_map_bar(priv, QTN_SHMEM_BAR);
-	if (IS_ERR(priv->epmem_bar)) {
-		pr_err("failed to map BAR%u\n", QTN_SHMEM_BAR);
-		return ret;
-	}
-
-	return 0;
-}
-
 static void qtnf_pcie_control_rx_callback(void *arg, const u8 __iomem *buf,
 					  size_t len)
 {
@@ -282,27 +277,80 @@ void qtnf_pcie_init_shm_ipc(struct qtnf_pcie_bus_priv *priv,
 			  ipc_int, &rx_callback);
 }
 
-int qtnf_pcie_probe(struct pci_dev *pdev, size_t priv_size,
-		    const struct qtnf_bus_ops *bus_ops, u64 dma_mask,
-		    bool use_msi)
+static int qtnf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct qtnf_pcie_bus_priv *pcie_priv;
 	struct qtnf_bus *bus;
+	void __iomem *sysctl_bar;
+	void __iomem *epmem_bar;
+	void __iomem *dmareg_bar;
+	unsigned int chipid;
 	int ret;
 
-	bus = devm_kzalloc(&pdev->dev,
-			   sizeof(*bus) + priv_size, GFP_KERNEL);
+	if (!pci_is_pcie(pdev)) {
+		pr_err("device %s is not PCI Express\n", pci_name(pdev));
+		return -EIO;
+	}
+
+	qtnf_tune_pcie_mps(pdev);
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		pr_err("failed to init PCI device %x\n", pdev->device);
+		return ret;
+	}
+
+	pci_set_master(pdev);
+
+	sysctl_bar = qtnf_map_bar(pdev, QTN_SYSCTL_BAR);
+	if (IS_ERR(sysctl_bar)) {
+		pr_err("failed to map BAR%u\n", QTN_SYSCTL_BAR);
+		return ret;
+	}
+
+	dmareg_bar = qtnf_map_bar(pdev, QTN_DMA_BAR);
+	if (IS_ERR(dmareg_bar)) {
+		pr_err("failed to map BAR%u\n", QTN_DMA_BAR);
+		return ret;
+	}
+
+	epmem_bar = qtnf_map_bar(pdev, QTN_SHMEM_BAR);
+	if (IS_ERR(epmem_bar)) {
+		pr_err("failed to map BAR%u\n", QTN_SHMEM_BAR);
+		return ret;
+	}
+
+	chipid = qtnf_chip_id_get(sysctl_bar);
+
+	pr_info("identified device: %s\n", qtnf_chipid_to_string(chipid));
+
+	switch (chipid) {
+	case QTN_CHIP_ID_PEARL:
+	case QTN_CHIP_ID_PEARL_B:
+	case QTN_CHIP_ID_PEARL_C:
+		bus = qtnf_pcie_pearl_alloc(pdev);
+		break;
+	default:
+		pr_err("unsupported chip ID 0x%x\n", chipid);
+		return -ENOTSUPP;
+	}
+
 	if (!bus)
 		return -ENOMEM;
 
 	pcie_priv = get_bus_priv(bus);
-
 	pci_set_drvdata(pdev, bus);
-	bus->bus_ops = bus_ops;
 	bus->dev = &pdev->dev;
 	bus->fw_state = QTNF_FW_STATE_RESET;
 	pcie_priv->pdev = pdev;
 	pcie_priv->tx_stopped = 0;
+	pcie_priv->rx_bd_num = rx_bd_size_param;
+	pcie_priv->flashboot = flashboot;
+
+	if (fw_blksize_param > QTN_PCIE_MAX_FW_BUFSZ)
+		pcie_priv->fw_blksize =  QTN_PCIE_MAX_FW_BUFSZ;
+	else
+		pcie_priv->fw_blksize = fw_blksize_param;
 
 	mutex_init(&bus->bus_lock);
 	spin_lock_init(&pcie_priv->tx_lock);
@@ -317,53 +365,35 @@ int qtnf_pcie_probe(struct pci_dev *pdev, size_t priv_size,
 	pcie_priv->workqueue = create_singlethread_workqueue("QTNF_PCIE");
 	if (!pcie_priv->workqueue) {
 		pr_err("failed to alloc bus workqueue\n");
-		ret = -ENODEV;
-		goto err_init;
-	}
-
-	init_dummy_netdev(&bus->mux_dev);
-
-	if (!pci_is_pcie(pdev)) {
-		pr_err("device %s is not PCI Express\n", pci_name(pdev));
-		ret = -EIO;
-		goto err_base;
+		return -ENODEV;
 	}
 
-	qtnf_tune_pcie_mps(pcie_priv);
-
-	ret = pcim_enable_device(pdev);
+	ret = dma_set_mask_and_coherent(&pdev->dev,
+					pcie_priv->dma_mask_get_cb());
 	if (ret) {
-		pr_err("failed to init PCI device %x\n", pdev->device);
-		goto err_base;
-	} else {
-		pr_debug("successful init of PCI device %x\n", pdev->device);
+		pr_err("PCIE DMA coherent mask init failed 0x%llx\n",
+		       pcie_priv->dma_mask_get_cb());
+		goto error;
 	}
 
-	ret = dma_set_mask_and_coherent(&pdev->dev, dma_mask);
-	if (ret) {
-		pr_err("PCIE DMA coherent mask init failed\n");
-		goto err_base;
-	}
-
-	pci_set_master(pdev);
+	init_dummy_netdev(&bus->mux_dev);
 	qtnf_pcie_init_irq(pcie_priv, use_msi);
-
-	ret = qtnf_pcie_init_memory(pcie_priv);
-	if (ret < 0) {
-		pr_err("PCIE memory init failed\n");
-		goto err_base;
-	}
-
+	pcie_priv->sysctl_bar = sysctl_bar;
+	pcie_priv->dmareg_bar = dmareg_bar;
+	pcie_priv->epmem_bar = epmem_bar;
 	pci_save_state(pdev);
 
+	ret = pcie_priv->probe_cb(bus, tx_bd_size_param);
+	if (ret)
+		goto error;
+
+	qtnf_pcie_bringup_fw_async(bus);
 	return 0;
 
-err_base:
+error:
 	flush_workqueue(pcie_priv->workqueue);
 	destroy_workqueue(pcie_priv->workqueue);
-err_init:
 	pci_set_drvdata(pdev, NULL);
-
 	return ret;
 }
 
@@ -373,8 +403,17 @@ static void qtnf_pcie_free_shm_ipc(struct qtnf_pcie_bus_priv *priv)
 	qtnf_shm_ipc_free(&priv->shm_ipc_ep_out);
 }
 
-void qtnf_pcie_remove(struct qtnf_bus *bus, struct qtnf_pcie_bus_priv *priv)
+static void qtnf_pcie_remove(struct pci_dev *dev)
 {
+	struct qtnf_pcie_bus_priv *priv;
+	struct qtnf_bus *bus;
+
+	bus = pci_get_drvdata(dev);
+	if (!bus)
+		return;
+
+	priv = get_bus_priv(bus);
+
 	cancel_work_sync(&bus->fw_work);
 
 	if (bus->fw_state == QTNF_FW_STATE_ACTIVE ||
@@ -388,5 +427,77 @@ void qtnf_pcie_remove(struct qtnf_bus *bus, struct qtnf_pcie_bus_priv *priv)
 
 	qtnf_pcie_free_shm_ipc(priv);
 	qtnf_debugfs_remove(bus);
+	priv->remove_cb(bus);
 	pci_set_drvdata(priv->pdev, NULL);
 }
+
+#ifdef CONFIG_PM_SLEEP
+static int qtnf_pcie_suspend(struct device *dev)
+{
+	struct qtnf_pcie_bus_priv *priv;
+	struct qtnf_bus *bus;
+
+	bus = pci_get_drvdata(to_pci_dev(dev));
+	if (!bus)
+		return -EFAULT;
+
+	priv = get_bus_priv(bus);
+	return priv->suspend_cb(bus);
+}
+
+static int qtnf_pcie_resume(struct device *dev)
+{
+	struct qtnf_pcie_bus_priv *priv;
+	struct qtnf_bus *bus;
+
+	bus = pci_get_drvdata(to_pci_dev(dev));
+	if (!bus)
+		return -EFAULT;
+
+	priv = get_bus_priv(bus);
+	return priv->resume_cb(bus);
+}
+
+/* Power Management Hooks */
+static SIMPLE_DEV_PM_OPS(qtnf_pcie_pm_ops, qtnf_pcie_suspend,
+			 qtnf_pcie_resume);
+#endif
+
+static const struct pci_device_id qtnf_pcie_devid_table[] = {
+	{
+		PCIE_VENDOR_ID_QUANTENNA, PCIE_DEVICE_ID_QTN_PEARL,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+	},
+	{ },
+};
+
+MODULE_DEVICE_TABLE(pci, qtnf_pcie_devid_table);
+
+static struct pci_driver qtnf_pcie_drv_data = {
+	.name = DRV_NAME,
+	.id_table = qtnf_pcie_devid_table,
+	.probe = qtnf_pcie_probe,
+	.remove = qtnf_pcie_remove,
+#ifdef CONFIG_PM_SLEEP
+	.driver = {
+		.pm = &qtnf_pcie_pm_ops,
+	},
+#endif
+};
+
+static int __init qtnf_pcie_register(void)
+{
+	return pci_register_driver(&qtnf_pcie_drv_data);
+}
+
+static void __exit qtnf_pcie_exit(void)
+{
+	pci_unregister_driver(&qtnf_pcie_drv_data);
+}
+
+module_init(qtnf_pcie_register);
+module_exit(qtnf_pcie_exit);
+
+MODULE_AUTHOR("Quantenna Communications");
+MODULE_DESCRIPTION("Quantenna PCIe bus driver for 802.11 wireless LAN.");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie_priv.h b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie_priv.h
index 5c70fb4c0f92..7c742c56efaf 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie_priv.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie_priv.h
@@ -23,9 +23,14 @@
 struct qtnf_pcie_bus_priv {
 	struct pci_dev *pdev;
 
+	int (*probe_cb)(struct qtnf_bus *bus, unsigned int tx_bd_size);
+	void (*remove_cb)(struct qtnf_bus *bus);
+	int (*suspend_cb)(struct qtnf_bus *bus);
+	int (*resume_cb)(struct qtnf_bus *bus);
+	u64 (*dma_mask_get_cb)(void);
+
 	spinlock_t tx_reclaim_lock;
 	spinlock_t tx_lock;
-	int mps;
 
 	struct workqueue_struct *workqueue;
 	struct tasklet_struct reclaim_tq;
@@ -43,6 +48,8 @@ struct qtnf_pcie_bus_priv {
 	struct sk_buff **tx_skb;
 	struct sk_buff **rx_skb;
 
+	unsigned int fw_blksize;
+
 	u32 rx_bd_w_index;
 	u32 rx_bd_r_index;
 
@@ -58,21 +65,17 @@ struct qtnf_pcie_bus_priv {
 
 	u8 msi_enabled;
 	u8 tx_stopped;
+	bool flashboot;
 };
 
 int qtnf_pcie_control_tx(struct qtnf_bus *bus, struct sk_buff *skb);
 int qtnf_pcie_alloc_skb_array(struct qtnf_pcie_bus_priv *priv);
-void qtnf_pcie_bringup_fw_async(struct qtnf_bus *bus);
-void qtnf_pcie_fw_boot_done(struct qtnf_bus *bus, bool boot_success,
-			    const char *drv_name);
+void qtnf_pcie_fw_boot_done(struct qtnf_bus *bus, bool boot_success);
 void qtnf_pcie_init_shm_ipc(struct qtnf_pcie_bus_priv *priv,
 			    struct qtnf_shm_ipc_region __iomem *ipc_tx_reg,
 			    struct qtnf_shm_ipc_region __iomem *ipc_rx_reg,
 			    const struct qtnf_shm_ipc_int *ipc_int);
-int qtnf_pcie_probe(struct pci_dev *pdev, size_t priv_size,
-		    const struct qtnf_bus_ops *bus_ops, u64 dma_mask,
-		    bool use_msi);
-void qtnf_pcie_remove(struct qtnf_bus *bus, struct qtnf_pcie_bus_priv *priv);
+struct qtnf_bus *qtnf_pcie_pearl_alloc(struct pci_dev *pdev);
 
 static inline void qtnf_non_posted_write(u32 val, void __iomem *basereg)
 {
diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/pearl_pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pcie/pearl_pcie.c
index 95c7b95c6f8a..1f5facbb8905 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/pcie/pearl_pcie.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/pearl_pcie.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2018 Quantenna Communications */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/pci.h>
 #include <linux/vmalloc.h>
@@ -24,23 +23,7 @@
 #include "shm_ipc.h"
 #include "debug.h"
 
-static bool use_msi = true;
-module_param(use_msi, bool, 0644);
-MODULE_PARM_DESC(use_msi, "set 0 to use legacy interrupt");
-
-static unsigned int tx_bd_size_param = 32;
-module_param(tx_bd_size_param, uint, 0644);
-MODULE_PARM_DESC(tx_bd_size_param, "Tx descriptors queue size, power of two");
-
-static unsigned int rx_bd_size_param = 256;
-module_param(rx_bd_size_param, uint, 0644);
-MODULE_PARM_DESC(rx_bd_size_param, "Rx descriptors queue size, power of two");
-
-static u8 flashboot = 1;
-module_param(flashboot, byte, 0644);
-MODULE_PARM_DESC(flashboot, "set to 0 to use FW binary file on FS");
-
-#define DRV_NAME	"qtnfmac_pearl_pcie"
+#define PEARL_TX_BD_SIZE_DEFAULT	32
 
 struct qtnf_pearl_bda {
 	__le16 bda_len;
@@ -415,30 +398,28 @@ static int pearl_hhbm_init(struct qtnf_pcie_pearl_state *ps)
 	return 0;
 }
 
-static int qtnf_pcie_pearl_init_xfer(struct qtnf_pcie_pearl_state *ps)
+static int qtnf_pcie_pearl_init_xfer(struct qtnf_pcie_pearl_state *ps,
+				     unsigned int tx_bd_size)
 {
 	struct qtnf_pcie_bus_priv *priv = &ps->base;
 	int ret;
 	u32 val;
 
-	priv->tx_bd_num = tx_bd_size_param;
-	priv->rx_bd_num = rx_bd_size_param;
-	priv->rx_bd_w_index = 0;
-	priv->rx_bd_r_index = 0;
+	if (tx_bd_size == 0)
+		tx_bd_size = PEARL_TX_BD_SIZE_DEFAULT;
 
-	if (!priv->tx_bd_num || !is_power_of_2(priv->tx_bd_num)) {
-		pr_err("tx_bd_size_param %u is not power of two\n",
-		       priv->tx_bd_num);
-		return -EINVAL;
-	}
+	val = tx_bd_size * sizeof(struct qtnf_pearl_tx_bd);
 
-	val = priv->tx_bd_num * sizeof(struct qtnf_pearl_tx_bd);
-	if (val > PCIE_HHBM_MAX_SIZE) {
-		pr_err("tx_bd_size_param %u is too large\n",
-		       priv->tx_bd_num);
-		return -EINVAL;
+	if (!is_power_of_2(tx_bd_size) || val > PCIE_HHBM_MAX_SIZE) {
+		pr_warn("bad tx_bd_size value %u\n", tx_bd_size);
+		priv->tx_bd_num = PEARL_TX_BD_SIZE_DEFAULT;
+	} else {
+		priv->tx_bd_num = tx_bd_size;
 	}
 
+	priv->rx_bd_w_index = 0;
+	priv->rx_bd_r_index = 0;
+
 	if (!priv->rx_bd_num || !is_power_of_2(priv->rx_bd_num)) {
 		pr_err("rx_bd_size_param %u is not power of two\n",
 		       priv->rx_bd_num);
@@ -1006,7 +987,7 @@ static void qtnf_pearl_fw_work_handler(struct work_struct *work)
 	const char *fwname = QTN_PCI_PEARL_FW_NAME;
 	bool fw_boot_success = false;
 
-	if (flashboot) {
+	if (ps->base.flashboot) {
 		state |= QTN_RC_FW_FLASHBOOT;
 	} else {
 		ret = request_firmware(&fw, fwname, &pdev->dev);
@@ -1022,7 +1003,7 @@ static void qtnf_pearl_fw_work_handler(struct work_struct *work)
 			    QTN_FW_DL_TIMEOUT_MS)) {
 		pr_err("card is not ready\n");
 
-		if (!flashboot)
+		if (!ps->base.flashboot)
 			release_firmware(fw);
 
 		goto fw_load_exit;
@@ -1030,7 +1011,7 @@ static void qtnf_pearl_fw_work_handler(struct work_struct *work)
 
 	qtnf_clear_state(&ps->bda->bda_ep_state, QTN_EP_FW_LOADRDY);
 
-	if (flashboot) {
+	if (ps->base.flashboot) {
 		pr_info("booting firmware from flash\n");
 
 	} else {
@@ -1061,7 +1042,7 @@ static void qtnf_pearl_fw_work_handler(struct work_struct *work)
 	fw_boot_success = true;
 
 fw_load_exit:
-	qtnf_pcie_fw_boot_done(bus, fw_boot_success, DRV_NAME);
+	qtnf_pcie_fw_boot_done(bus, fw_boot_success);
 
 	if (fw_boot_success) {
 		qtnf_debugfs_add_entry(bus, "hdp_stats", qtnf_dbg_hdp_stats);
@@ -1077,74 +1058,34 @@ static void qtnf_pearl_reclaim_tasklet_fn(unsigned long data)
 	qtnf_en_txdone_irq(ps);
 }
 
-static int qtnf_pearl_check_chip_id(struct qtnf_pcie_pearl_state *ps)
+static u64 qtnf_pearl_dma_mask_get(void)
 {
-	unsigned int chipid;
-
-	chipid = qtnf_chip_id_get(ps->base.sysctl_bar);
-
-	switch (chipid) {
-	case QTN_CHIP_ID_PEARL:
-	case QTN_CHIP_ID_PEARL_B:
-	case QTN_CHIP_ID_PEARL_C:
-		pr_info("chip ID is 0x%x\n", chipid);
-		break;
-	default:
-		pr_err("incorrect chip ID 0x%x\n", chipid);
-		return -ENODEV;
-	}
-
-	return 0;
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	return DMA_BIT_MASK(64);
+#else
+	return DMA_BIT_MASK(32);
+#endif
 }
 
-static int qtnf_pcie_pearl_probe(struct pci_dev *pdev,
-				 const struct pci_device_id *id)
+static int qtnf_pcie_pearl_probe(struct qtnf_bus *bus, unsigned int tx_bd_size)
 {
 	struct qtnf_shm_ipc_int ipc_int;
-	struct qtnf_pcie_pearl_state *ps;
-	struct qtnf_bus *bus;
+	struct qtnf_pcie_pearl_state *ps = get_bus_priv(bus);
+	struct pci_dev *pdev = ps->base.pdev;
 	int ret;
-	u64 dma_mask;
-
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	dma_mask = DMA_BIT_MASK(64);
-#else
-	dma_mask = DMA_BIT_MASK(32);
-#endif
-
-	ret = qtnf_pcie_probe(pdev, sizeof(*ps), &qtnf_pcie_pearl_bus_ops,
-			      dma_mask, use_msi);
-	if (ret)
-		return ret;
-
-	bus = pci_get_drvdata(pdev);
-	ps = get_bus_priv(bus);
 
+	bus->bus_ops = &qtnf_pcie_pearl_bus_ops;
 	spin_lock_init(&ps->irq_lock);
-
-	tasklet_init(&ps->base.reclaim_tq, qtnf_pearl_reclaim_tasklet_fn,
-		     (unsigned long)ps);
-	netif_napi_add(&bus->mux_dev, &bus->mux_napi,
-		       qtnf_pcie_pearl_rx_poll, 10);
 	INIT_WORK(&bus->fw_work, qtnf_pearl_fw_work_handler);
 
 	ps->pcie_reg_base = ps->base.dmareg_bar;
 	ps->bda = ps->base.epmem_bar;
 	writel(ps->base.msi_enabled, &ps->bda->bda_rc_msi_enabled);
 
-	ipc_int.fn = qtnf_pcie_pearl_ipc_gen_ep_int;
-	ipc_int.arg = ps;
-	qtnf_pcie_init_shm_ipc(&ps->base, &ps->bda->bda_shm_reg1,
-			       &ps->bda->bda_shm_reg2, &ipc_int);
-
-	ret = qtnf_pearl_check_chip_id(ps);
-	if (ret)
-		goto error;
-
-	ret = qtnf_pcie_pearl_init_xfer(ps);
+	ret = qtnf_pcie_pearl_init_xfer(ps, tx_bd_size);
 	if (ret) {
 		pr_err("PCIE xfer init failed\n");
-		goto error;
+		return ret;
 	}
 
 	/* init default irq settings */
@@ -1155,95 +1096,63 @@ static int qtnf_pcie_pearl_probe(struct pci_dev *pdev,
 
 	ret = devm_request_irq(&pdev->dev, pdev->irq,
 			       &qtnf_pcie_pearl_interrupt, 0,
-			       "qtnf_pcie_irq", (void *)bus);
+			       "qtnf_pearl_irq", (void *)bus);
 	if (ret) {
 		pr_err("failed to request pcie irq %d\n", pdev->irq);
-		goto err_xfer;
+		qtnf_pearl_free_xfer_buffers(ps);
+		return ret;
 	}
 
-	qtnf_pcie_bringup_fw_async(bus);
-
-	return 0;
+	tasklet_init(&ps->base.reclaim_tq, qtnf_pearl_reclaim_tasklet_fn,
+		     (unsigned long)ps);
+	netif_napi_add(&bus->mux_dev, &bus->mux_napi,
+		       qtnf_pcie_pearl_rx_poll, 10);
 
-err_xfer:
-	qtnf_pearl_free_xfer_buffers(ps);
-error:
-	qtnf_pcie_remove(bus, &ps->base);
+	ipc_int.fn = qtnf_pcie_pearl_ipc_gen_ep_int;
+	ipc_int.arg = ps;
+	qtnf_pcie_init_shm_ipc(&ps->base, &ps->bda->bda_shm_reg1,
+			       &ps->bda->bda_shm_reg2, &ipc_int);
 
-	return ret;
+	return 0;
 }
 
-static void qtnf_pcie_pearl_remove(struct pci_dev *pdev)
+static void qtnf_pcie_pearl_remove(struct qtnf_bus *bus)
 {
-	struct qtnf_pcie_pearl_state *ps;
-	struct qtnf_bus *bus;
-
-	bus = pci_get_drvdata(pdev);
-	if (!bus)
-		return;
-
-	ps = get_bus_priv(bus);
+	struct qtnf_pcie_pearl_state *ps = get_bus_priv(bus);
 
-	qtnf_pcie_remove(bus, &ps->base);
 	qtnf_pearl_reset_ep(ps);
 	qtnf_pearl_free_xfer_buffers(ps);
 }
 
 #ifdef CONFIG_PM_SLEEP
-static int qtnf_pcie_pearl_suspend(struct device *dev)
+static int qtnf_pcie_pearl_suspend(struct qtnf_bus *bus)
 {
 	return -EOPNOTSUPP;
 }
 
-static int qtnf_pcie_pearl_resume(struct device *dev)
+static int qtnf_pcie_pearl_resume(struct qtnf_bus *bus)
 {
 	return 0;
 }
-#endif /* CONFIG_PM_SLEEP */
-
-#ifdef CONFIG_PM_SLEEP
-/* Power Management Hooks */
-static SIMPLE_DEV_PM_OPS(qtnf_pcie_pearl_pm_ops, qtnf_pcie_pearl_suspend,
-			 qtnf_pcie_pearl_resume);
 #endif
 
-static const struct pci_device_id qtnf_pcie_devid_table[] = {
-	{
-		PCIE_VENDOR_ID_QUANTENNA, PCIE_DEVICE_ID_QTN_PEARL,
-		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-	},
-	{ },
-};
+struct qtnf_bus *qtnf_pcie_pearl_alloc(struct pci_dev *pdev)
+{
+	struct qtnf_bus *bus;
+	struct qtnf_pcie_pearl_state *ps;
 
-MODULE_DEVICE_TABLE(pci, qtnf_pcie_devid_table);
+	bus = devm_kzalloc(&pdev->dev, sizeof(*bus) + sizeof(*ps), GFP_KERNEL);
+	if (!bus)
+		return NULL;
 
-static struct pci_driver qtnf_pcie_pearl_drv_data = {
-	.name = DRV_NAME,
-	.id_table = qtnf_pcie_devid_table,
-	.probe = qtnf_pcie_pearl_probe,
-	.remove = qtnf_pcie_pearl_remove,
+	ps = get_bus_priv(bus);
+	ps->base.probe_cb = qtnf_pcie_pearl_probe;
+	ps->base.remove_cb = qtnf_pcie_pearl_remove;
+	ps->base.dma_mask_get_cb = qtnf_pearl_dma_mask_get;
 #ifdef CONFIG_PM_SLEEP
-	.driver = {
-		.pm = &qtnf_pcie_pearl_pm_ops,
-	},
+	ps->base.resume_cb = qtnf_pcie_pearl_resume;
+	ps->base.suspend_cb = qtnf_pcie_pearl_suspend;
 #endif
-};
-
-static int __init qtnf_pcie_pearl_register(void)
-{
-	pr_info("register Quantenna QSR10g FullMAC PCIE driver\n");
-	return pci_register_driver(&qtnf_pcie_pearl_drv_data);
-}
 
-static void __exit qtnf_pcie_pearl_exit(void)
-{
-	pr_info("unregister Quantenna QSR10g FullMAC PCIE driver\n");
-	pci_unregister_driver(&qtnf_pcie_pearl_drv_data);
+	return bus;
 }
-
-module_init(qtnf_pcie_pearl_register);
-module_exit(qtnf_pcie_pearl_exit);
-
-MODULE_AUTHOR("Quantenna Communications");
-MODULE_DESCRIPTION("Quantenna QSR10g PCIe bus driver for 802.11 wireless LAN.");
-MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/quantenna/qtnfmac/util.c b/drivers/net/wireless/quantenna/qtnfmac/util.c
index e745733ba417..dfe3fe8a42c1 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/util.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/util.c
@@ -15,6 +15,7 @@
  */
 
 #include "util.h"
+#include "qtn_hw_ids.h"
 
 void qtnf_sta_list_init(struct qtnf_sta_list *list)
 {
@@ -116,3 +117,18 @@ void qtnf_sta_list_free(struct qtnf_sta_list *list)
 
 	INIT_LIST_HEAD(&list->head);
 }
+
+const char *qtnf_chipid_to_string(unsigned long chip_id)
+{
+	switch (chip_id) {
+	case QTN_CHIP_ID_PEARL:
+		return "Pearl revA";
+	case QTN_CHIP_ID_PEARL_B:
+		return "Pearl revB";
+	case QTN_CHIP_ID_PEARL_C:
+		return "Pearl revC";
+	default:
+		return "unknown";
+	}
+}
+EXPORT_SYMBOL_GPL(qtnf_chipid_to_string);
diff --git a/drivers/net/wireless/quantenna/qtnfmac/util.h b/drivers/net/wireless/quantenna/qtnfmac/util.h
index 0d4d92b11540..b8744baac332 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/util.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/util.h
@@ -20,6 +20,8 @@
 #include <linux/kernel.h>
 #include "core.h"
 
+const char *qtnf_chipid_to_string(unsigned long chip_id);
+
 void qtnf_sta_list_init(struct qtnf_sta_list *list);
 
 struct qtnf_sta_node *qtnf_sta_list_lookup(struct qtnf_sta_list *list,
-- 
cgit v1.2.3


From e401fa25cfa23df8b17960a656ff11f49facae84 Mon Sep 17 00:00:00 2001
From: Sergey Matyukevich <sergey.matyukevich.os@quantenna.com>
Date: Tue, 16 Oct 2018 10:23:58 +0000
Subject: qtnfmac: add support for Topaz chipsets

This patch adds support for QSR1000/QSR2000 family of chipsets
to qtnfmac_pcie platform driver.

QSR1000/QSR2000 (aka Topaz) is a family of 80MHz, 11ac Wave2,
4x4/2x4/2x2 chips, including single and dual band devices.
Depending on specific chip model and firmware in use, either
STA or both STA and AP modes are supported.

Patch adds Topaz support to qtnfmac_pcie driver. Proper platform
bus will be selected on probing based on chip ID.

Signed-off-by: Igor Mitsyanko <igor.mitsyanko.os@quantenna.com>
Signed-off-by: Sergey Matyukevich <sergey.matyukevich.os@quantenna.com>
Signed-off-by: Andrey Shevchenko <ashevchenko@quantenna.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/quantenna/qtnfmac/Kconfig     |    5 +-
 drivers/net/wireless/quantenna/qtnfmac/Makefile    |    3 +-
 drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c |    5 +-
 .../wireless/quantenna/qtnfmac/pcie/pcie_priv.h    |    1 +
 .../wireless/quantenna/qtnfmac/pcie/topaz_pcie.c   | 1219 ++++++++++++++++++++
 .../quantenna/qtnfmac/pcie/topaz_pcie_ipc.h        |   94 ++
 .../quantenna/qtnfmac/pcie/topaz_pcie_regs.h       |   45 +
 .../net/wireless/quantenna/qtnfmac/qtn_hw_ids.h    |    4 +-
 drivers/net/wireless/quantenna/qtnfmac/util.c      |    2 +
 9 files changed, 1373 insertions(+), 5 deletions(-)
 create mode 100644 drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c
 create mode 100644 drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie_ipc.h
 create mode 100644 drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie_regs.h

diff --git a/drivers/net/wireless/quantenna/qtnfmac/Kconfig b/drivers/net/wireless/quantenna/qtnfmac/Kconfig
index 696c50066b53..6cf5202c3666 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/Kconfig
+++ b/drivers/net/wireless/quantenna/qtnfmac/Kconfig
@@ -5,7 +5,7 @@ config QTNFMAC
 	default y if QTNFMAC_PCIE=y
 
 config QTNFMAC_PCIE
-	tristate "Quantenna QSR10g PCIe support"
+	tristate "Quantenna QSR1000/QSR2000/QSR10g PCIe support"
 	default n
 	depends on PCI && CFG80211
 	select QTNFMAC
@@ -13,7 +13,8 @@ config QTNFMAC_PCIE
 	select CRC32
 	help
 	  This option adds support for wireless adapters based on Quantenna
-	  802.11ac QSR10g (aka Pearl) FullMAC chipset running over PCIe.
+	  802.11ac QSR10g (aka Pearl) and QSR1000/QSR2000 (aka Topaz)
+	  FullMAC chipsets running over PCIe.
 
 	  If you choose to build it as a module, two modules will be built:
 	  qtnfmac.ko and qtnfmac_pcie.ko.
diff --git a/drivers/net/wireless/quantenna/qtnfmac/Makefile b/drivers/net/wireless/quantenna/qtnfmac/Makefile
index d7e8185fddab..40dffbd2ea47 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/Makefile
+++ b/drivers/net/wireless/quantenna/qtnfmac/Makefile
@@ -24,6 +24,7 @@ obj-$(CONFIG_QTNFMAC_PCIE) += qtnfmac_pcie.o
 qtnfmac_pcie-objs += \
 	shm_ipc.o \
 	pcie/pcie.o \
-	pcie/pearl_pcie.o
+	pcie/pearl_pcie.o \
+	pcie/topaz_pcie.o
 
 qtnfmac_pcie-$(CONFIG_DEBUG_FS) += debug.o
diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c
index 70dd8da5b0dc..c3a32effa6f0 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c
@@ -330,6 +330,9 @@ static int qtnf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	case QTN_CHIP_ID_PEARL_C:
 		bus = qtnf_pcie_pearl_alloc(pdev);
 		break;
+	case QTN_CHIP_ID_TOPAZ:
+		bus = qtnf_pcie_topaz_alloc(pdev);
+		break;
 	default:
 		pr_err("unsupported chip ID 0x%x\n", chipid);
 		return -ENOTSUPP;
@@ -465,7 +468,7 @@ static SIMPLE_DEV_PM_OPS(qtnf_pcie_pm_ops, qtnf_pcie_suspend,
 
 static const struct pci_device_id qtnf_pcie_devid_table[] = {
 	{
-		PCIE_VENDOR_ID_QUANTENNA, PCIE_DEVICE_ID_QTN_PEARL,
+		PCIE_VENDOR_ID_QUANTENNA, PCIE_DEVICE_ID_QSR,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 	},
 	{ },
diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie_priv.h b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie_priv.h
index 7c742c56efaf..bbc074e1f34d 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie_priv.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie_priv.h
@@ -76,6 +76,7 @@ void qtnf_pcie_init_shm_ipc(struct qtnf_pcie_bus_priv *priv,
 			    struct qtnf_shm_ipc_region __iomem *ipc_rx_reg,
 			    const struct qtnf_shm_ipc_int *ipc_int);
 struct qtnf_bus *qtnf_pcie_pearl_alloc(struct pci_dev *pdev);
+struct qtnf_bus *qtnf_pcie_topaz_alloc(struct pci_dev *pdev);
 
 static inline void qtnf_non_posted_write(u32 val, void __iomem *basereg)
 {
diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c
new file mode 100644
index 000000000000..598edb814421
--- /dev/null
+++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c
@@ -0,0 +1,1219 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (c) 2018 Quantenna Communications */
+
+#include <linux/kernel.h>
+#include <linux/firmware.h>
+#include <linux/pci.h>
+#include <linux/vmalloc.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/crc32.h>
+#include <linux/completion.h>
+#include <linux/spinlock.h>
+#include <linux/circ_buf.h>
+
+#include "pcie_priv.h"
+#include "topaz_pcie_regs.h"
+#include "topaz_pcie_ipc.h"
+#include "qtn_hw_ids.h"
+#include "core.h"
+#include "bus.h"
+#include "shm_ipc.h"
+#include "debug.h"
+
+#define TOPAZ_TX_BD_SIZE_DEFAULT	128
+
+struct qtnf_topaz_tx_bd {
+	__le32 addr;
+	__le32 info;
+} __packed;
+
+struct qtnf_topaz_rx_bd {
+	__le32 addr;
+	__le32 info;
+} __packed;
+
+struct qtnf_extra_bd_params {
+	__le32 param1;
+	__le32 param2;
+	__le32 param3;
+	__le32 param4;
+} __packed;
+
+#define QTNF_BD_PARAM_OFFSET(n)	offsetof(struct qtnf_extra_bd_params, param##n)
+
+struct vmac_pkt_info {
+	__le32 addr;
+	__le32 info;
+};
+
+struct qtnf_topaz_bda {
+	__le16	bda_len;
+	__le16	bda_version;
+	__le32	bda_bootstate;
+	__le32	bda_dma_mask;
+	__le32	bda_dma_offset;
+	__le32	bda_flags;
+	__le32	bda_img;
+	__le32	bda_img_size;
+	__le32	bda_ep2h_irqstatus;
+	__le32	bda_h2ep_irqstatus;
+	__le32	bda_msi_addr;
+	u8	reserved1[56];
+	__le32	bda_flashsz;
+	u8	bda_boardname[PCIE_BDA_NAMELEN];
+	__le32	bda_pci_pre_status;
+	__le32	bda_pci_endian;
+	__le32	bda_pci_post_status;
+	__le32	bda_h2ep_txd_budget;
+	__le32	bda_ep2h_txd_budget;
+	__le32	bda_rc_rx_bd_base;
+	__le32	bda_rc_rx_bd_num;
+	__le32	bda_rc_tx_bd_base;
+	__le32	bda_rc_tx_bd_num;
+	u8	bda_ep_link_state;
+	u8	bda_rc_link_state;
+	u8	bda_rc_msi_enabled;
+	u8	reserved2;
+	__le32	bda_ep_next_pkt;
+	struct vmac_pkt_info request[QTN_PCIE_RC_TX_QUEUE_LEN];
+	struct qtnf_shm_ipc_region bda_shm_reg1 __aligned(4096);
+	struct qtnf_shm_ipc_region bda_shm_reg2 __aligned(4096);
+} __packed;
+
+struct qtnf_pcie_topaz_state {
+	struct qtnf_pcie_bus_priv base;
+	struct qtnf_topaz_bda __iomem *bda;
+
+	dma_addr_t dma_msi_dummy;
+	u32 dma_msi_imwr;
+
+	struct qtnf_topaz_tx_bd *tx_bd_vbase;
+	struct qtnf_topaz_rx_bd *rx_bd_vbase;
+
+	__le32 __iomem *ep_next_rx_pkt;
+	__le32 __iomem *txqueue_wake;
+	__le32 __iomem *ep_pmstate;
+
+	unsigned long rx_pkt_count;
+};
+
+static void qtnf_deassert_intx(struct qtnf_pcie_topaz_state *ts)
+{
+	void __iomem *reg = ts->base.sysctl_bar + TOPAZ_PCIE_CFG0_OFFSET;
+	u32 cfg;
+
+	cfg = readl(reg);
+	cfg &= ~TOPAZ_ASSERT_INTX;
+	qtnf_non_posted_write(cfg, reg);
+}
+
+static inline int qtnf_topaz_intx_asserted(struct qtnf_pcie_topaz_state *ts)
+{
+	void __iomem *reg = ts->base.sysctl_bar + TOPAZ_PCIE_CFG0_OFFSET;
+	u32 cfg = readl(reg);
+
+	return !!(cfg & TOPAZ_ASSERT_INTX);
+}
+
+static void qtnf_topaz_reset_ep(struct qtnf_pcie_topaz_state *ts)
+{
+	writel(TOPAZ_IPC_IRQ_WORD(TOPAZ_RC_RST_EP_IRQ),
+	       TOPAZ_LH_IPC4_INT(ts->base.sysctl_bar));
+	msleep(QTN_EP_RESET_WAIT_MS);
+	pci_restore_state(ts->base.pdev);
+}
+
+static void setup_rx_irqs(struct qtnf_pcie_topaz_state *ts)
+{
+	void __iomem *reg = PCIE_DMA_WR_DONE_IMWR_ADDR_LOW(ts->base.dmareg_bar);
+
+	ts->dma_msi_imwr = readl(reg);
+}
+
+static void enable_rx_irqs(struct qtnf_pcie_topaz_state *ts)
+{
+	void __iomem *reg = PCIE_DMA_WR_DONE_IMWR_ADDR_LOW(ts->base.dmareg_bar);
+
+	qtnf_non_posted_write(ts->dma_msi_imwr, reg);
+}
+
+static void disable_rx_irqs(struct qtnf_pcie_topaz_state *ts)
+{
+	void __iomem *reg = PCIE_DMA_WR_DONE_IMWR_ADDR_LOW(ts->base.dmareg_bar);
+
+	qtnf_non_posted_write(QTN_HOST_LO32(ts->dma_msi_dummy), reg);
+}
+
+static void qtnf_topaz_ipc_gen_ep_int(void *arg)
+{
+	struct qtnf_pcie_topaz_state *ts = arg;
+
+	writel(TOPAZ_IPC_IRQ_WORD(TOPAZ_RC_CTRL_IRQ),
+	       TOPAZ_CTL_M2L_INT(ts->base.sysctl_bar));
+}
+
+static int qtnf_is_state(__le32 __iomem *reg, u32 state)
+{
+	u32 s = readl(reg);
+
+	return (s == state);
+}
+
+static void qtnf_set_state(__le32 __iomem *reg, u32 state)
+{
+	qtnf_non_posted_write(state, reg);
+}
+
+static int qtnf_poll_state(__le32 __iomem *reg, u32 state, u32 delay_in_ms)
+{
+	u32 timeout = 0;
+
+	while ((qtnf_is_state(reg, state) == 0)) {
+		usleep_range(1000, 1200);
+		if (++timeout > delay_in_ms)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int topaz_alloc_bd_table(struct qtnf_pcie_topaz_state *ts,
+				struct qtnf_topaz_bda __iomem *bda)
+{
+	struct qtnf_extra_bd_params __iomem *extra_params;
+	struct qtnf_pcie_bus_priv *priv = &ts->base;
+	dma_addr_t paddr;
+	void *vaddr;
+	int len;
+	int i;
+
+	/* bd table */
+
+	len = priv->tx_bd_num * sizeof(struct qtnf_topaz_tx_bd) +
+		priv->rx_bd_num * sizeof(struct qtnf_topaz_rx_bd) +
+			sizeof(struct qtnf_extra_bd_params);
+
+	vaddr = dmam_alloc_coherent(&priv->pdev->dev, len, &paddr, GFP_KERNEL);
+	if (!vaddr)
+		return -ENOMEM;
+
+	memset(vaddr, 0, len);
+
+	/* tx bd */
+
+	ts->tx_bd_vbase = vaddr;
+	qtnf_non_posted_write(paddr, &bda->bda_rc_tx_bd_base);
+
+	for (i = 0; i < priv->tx_bd_num; i++)
+		ts->tx_bd_vbase[i].info |= cpu_to_le32(QTN_BD_EMPTY);
+
+	pr_debug("TX descriptor table: vaddr=0x%p paddr=%pad\n", vaddr, &paddr);
+
+	priv->tx_bd_r_index = 0;
+	priv->tx_bd_w_index = 0;
+
+	/* rx bd */
+
+	vaddr = ((struct qtnf_topaz_tx_bd *)vaddr) + priv->tx_bd_num;
+	paddr += priv->tx_bd_num * sizeof(struct qtnf_topaz_tx_bd);
+
+	ts->rx_bd_vbase = vaddr;
+	qtnf_non_posted_write(paddr, &bda->bda_rc_rx_bd_base);
+
+	pr_debug("RX descriptor table: vaddr=0x%p paddr=%pad\n", vaddr, &paddr);
+
+	/* extra shared params */
+
+	vaddr = ((struct qtnf_topaz_rx_bd *)vaddr) + priv->rx_bd_num;
+	paddr += priv->rx_bd_num * sizeof(struct qtnf_topaz_rx_bd);
+
+	extra_params = (struct qtnf_extra_bd_params __iomem *)vaddr;
+
+	ts->ep_next_rx_pkt = &extra_params->param1;
+	qtnf_non_posted_write(paddr + QTNF_BD_PARAM_OFFSET(1),
+			      &bda->bda_ep_next_pkt);
+	ts->txqueue_wake = &extra_params->param2;
+	ts->ep_pmstate = &extra_params->param3;
+	ts->dma_msi_dummy = paddr + QTNF_BD_PARAM_OFFSET(4);
+
+	return 0;
+}
+
+static int
+topaz_skb2rbd_attach(struct qtnf_pcie_topaz_state *ts, u16 index, u32 wrap)
+{
+	struct qtnf_topaz_rx_bd *rxbd = &ts->rx_bd_vbase[index];
+	struct sk_buff *skb;
+	dma_addr_t paddr;
+
+	skb = __netdev_alloc_skb_ip_align(NULL, SKB_BUF_SIZE, GFP_ATOMIC);
+	if (!skb) {
+		ts->base.rx_skb[index] = NULL;
+		return -ENOMEM;
+	}
+
+	ts->base.rx_skb[index] = skb;
+
+	paddr = pci_map_single(ts->base.pdev, skb->data,
+			       SKB_BUF_SIZE, PCI_DMA_FROMDEVICE);
+	if (pci_dma_mapping_error(ts->base.pdev, paddr)) {
+		pr_err("skb mapping error: %pad\n", &paddr);
+		return -ENOMEM;
+	}
+
+	rxbd->addr = cpu_to_le32(QTN_HOST_LO32(paddr));
+	rxbd->info = cpu_to_le32(QTN_BD_EMPTY | wrap);
+
+	ts->base.rx_bd_w_index = index;
+
+	return 0;
+}
+
+static int topaz_alloc_rx_buffers(struct qtnf_pcie_topaz_state *ts)
+{
+	u16 i;
+	int ret = 0;
+
+	memset(ts->rx_bd_vbase, 0x0,
+	       ts->base.rx_bd_num * sizeof(struct qtnf_topaz_rx_bd));
+
+	for (i = 0; i < ts->base.rx_bd_num; i++) {
+		ret = topaz_skb2rbd_attach(ts, i, 0);
+		if (ret)
+			break;
+	}
+
+	ts->rx_bd_vbase[ts->base.rx_bd_num - 1].info |=
+						cpu_to_le32(QTN_BD_WRAP);
+
+	return ret;
+}
+
+/* all rx/tx activity should have ceased before calling this function */
+static void qtnf_topaz_free_xfer_buffers(struct qtnf_pcie_topaz_state *ts)
+{
+	struct qtnf_pcie_bus_priv *priv = &ts->base;
+	struct qtnf_topaz_rx_bd *rxbd;
+	struct qtnf_topaz_tx_bd *txbd;
+	struct sk_buff *skb;
+	dma_addr_t paddr;
+	int i;
+
+	/* free rx buffers */
+	for (i = 0; i < priv->rx_bd_num; i++) {
+		if (priv->rx_skb && priv->rx_skb[i]) {
+			rxbd = &ts->rx_bd_vbase[i];
+			skb = priv->rx_skb[i];
+			paddr = QTN_HOST_ADDR(0x0, le32_to_cpu(rxbd->addr));
+			pci_unmap_single(priv->pdev, paddr, SKB_BUF_SIZE,
+					 PCI_DMA_FROMDEVICE);
+			dev_kfree_skb_any(skb);
+			priv->rx_skb[i] = NULL;
+			rxbd->addr = 0;
+			rxbd->info = 0;
+		}
+	}
+
+	/* free tx buffers */
+	for (i = 0; i < priv->tx_bd_num; i++) {
+		if (priv->tx_skb && priv->tx_skb[i]) {
+			txbd = &ts->tx_bd_vbase[i];
+			skb = priv->tx_skb[i];
+			paddr = QTN_HOST_ADDR(0x0, le32_to_cpu(txbd->addr));
+			pci_unmap_single(priv->pdev, paddr, SKB_BUF_SIZE,
+					 PCI_DMA_TODEVICE);
+			dev_kfree_skb_any(skb);
+			priv->tx_skb[i] = NULL;
+			txbd->addr = 0;
+			txbd->info = 0;
+		}
+	}
+}
+
+static int qtnf_pcie_topaz_init_xfer(struct qtnf_pcie_topaz_state *ts,
+				     unsigned int tx_bd_size)
+{
+	struct qtnf_topaz_bda __iomem *bda = ts->bda;
+	struct qtnf_pcie_bus_priv *priv = &ts->base;
+	int ret;
+
+	if (tx_bd_size == 0)
+		tx_bd_size = TOPAZ_TX_BD_SIZE_DEFAULT;
+
+	/* check TX BD queue max length according to struct qtnf_topaz_bda */
+	if (tx_bd_size > QTN_PCIE_RC_TX_QUEUE_LEN) {
+		pr_warn("TX BD queue cannot exceed %d\n",
+			QTN_PCIE_RC_TX_QUEUE_LEN);
+		tx_bd_size = QTN_PCIE_RC_TX_QUEUE_LEN;
+	}
+
+	priv->tx_bd_num = tx_bd_size;
+	qtnf_non_posted_write(priv->tx_bd_num, &bda->bda_rc_tx_bd_num);
+	qtnf_non_posted_write(priv->rx_bd_num, &bda->bda_rc_rx_bd_num);
+
+	priv->rx_bd_w_index = 0;
+	priv->rx_bd_r_index = 0;
+
+	ret = qtnf_pcie_alloc_skb_array(priv);
+	if (ret) {
+		pr_err("failed to allocate skb array\n");
+		return ret;
+	}
+
+	ret = topaz_alloc_bd_table(ts, bda);
+	if (ret) {
+		pr_err("failed to allocate bd table\n");
+		return ret;
+	}
+
+	ret = topaz_alloc_rx_buffers(ts);
+	if (ret) {
+		pr_err("failed to allocate rx buffers\n");
+		return ret;
+	}
+
+	return ret;
+}
+
+static void qtnf_topaz_data_tx_reclaim(struct qtnf_pcie_topaz_state *ts)
+{
+	struct qtnf_pcie_bus_priv *priv = &ts->base;
+	struct qtnf_topaz_tx_bd *txbd;
+	struct sk_buff *skb;
+	unsigned long flags;
+	dma_addr_t paddr;
+	u32 tx_done_index;
+	int count = 0;
+	int i;
+
+	spin_lock_irqsave(&priv->tx_reclaim_lock, flags);
+
+	tx_done_index = readl(ts->ep_next_rx_pkt);
+	i = priv->tx_bd_r_index;
+
+	if (CIRC_CNT(priv->tx_bd_w_index, tx_done_index, priv->tx_bd_num))
+		writel(TOPAZ_IPC_IRQ_WORD(TOPAZ_RC_TX_DONE_IRQ),
+		       TOPAZ_LH_IPC4_INT(priv->sysctl_bar));
+
+	while (CIRC_CNT(tx_done_index, i, priv->tx_bd_num)) {
+		skb = priv->tx_skb[i];
+
+		if (likely(skb)) {
+			txbd = &ts->tx_bd_vbase[i];
+			paddr = QTN_HOST_ADDR(0x0, le32_to_cpu(txbd->addr));
+			pci_unmap_single(priv->pdev, paddr, skb->len,
+					 PCI_DMA_TODEVICE);
+
+			if (skb->dev) {
+				qtnf_update_tx_stats(skb->dev, skb);
+				if (unlikely(priv->tx_stopped)) {
+					qtnf_wake_all_queues(skb->dev);
+					priv->tx_stopped = 0;
+				}
+			}
+
+			dev_kfree_skb_any(skb);
+		}
+
+		priv->tx_skb[i] = NULL;
+		count++;
+
+		if (++i >= priv->tx_bd_num)
+			i = 0;
+	}
+
+	priv->tx_reclaim_done += count;
+	priv->tx_reclaim_req++;
+	priv->tx_bd_r_index = i;
+
+	spin_unlock_irqrestore(&priv->tx_reclaim_lock, flags);
+}
+
+static void qtnf_try_stop_xmit(struct qtnf_bus *bus, struct net_device *ndev)
+{
+	struct qtnf_pcie_topaz_state *ts = (void *)get_bus_priv(bus);
+
+	if (ndev) {
+		netif_tx_stop_all_queues(ndev);
+		ts->base.tx_stopped = 1;
+	}
+
+	writel(0x0, ts->txqueue_wake);
+
+	/* sync up tx queue status before generating interrupt */
+	dma_wmb();
+
+	/* send irq to card: tx stopped */
+	writel(TOPAZ_IPC_IRQ_WORD(TOPAZ_RC_TX_STOP_IRQ),
+	       TOPAZ_LH_IPC4_INT(ts->base.sysctl_bar));
+
+	/* schedule reclaim attempt */
+	tasklet_hi_schedule(&ts->base.reclaim_tq);
+}
+
+static void qtnf_try_wake_xmit(struct qtnf_bus *bus, struct net_device *ndev)
+{
+	struct qtnf_pcie_topaz_state *ts = get_bus_priv(bus);
+	int ready;
+
+	ready = readl(ts->txqueue_wake);
+	if (ready) {
+		netif_wake_queue(ndev);
+	} else {
+		/* re-send irq to card: tx stopped */
+		writel(TOPAZ_IPC_IRQ_WORD(TOPAZ_RC_TX_STOP_IRQ),
+		       TOPAZ_LH_IPC4_INT(ts->base.sysctl_bar));
+	}
+}
+
+static int qtnf_tx_queue_ready(struct qtnf_pcie_topaz_state *ts)
+{
+	struct qtnf_pcie_bus_priv *priv = &ts->base;
+
+	if (!CIRC_SPACE(priv->tx_bd_w_index, priv->tx_bd_r_index,
+			priv->tx_bd_num)) {
+		qtnf_topaz_data_tx_reclaim(ts);
+
+		if (!CIRC_SPACE(priv->tx_bd_w_index, priv->tx_bd_r_index,
+				priv->tx_bd_num)) {
+			priv->tx_full_count++;
+			return 0;
+		}
+	}
+
+	return 1;
+}
+
+static int qtnf_pcie_data_tx(struct qtnf_bus *bus, struct sk_buff *skb)
+{
+	struct qtnf_pcie_topaz_state *ts = (void *)get_bus_priv(bus);
+	struct qtnf_pcie_bus_priv *priv = &ts->base;
+	struct qtnf_topaz_bda __iomem *bda = ts->bda;
+	struct qtnf_topaz_tx_bd *txbd;
+	dma_addr_t skb_paddr;
+	unsigned long flags;
+	int ret = 0;
+	int len;
+	int i;
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
+	if (!qtnf_tx_queue_ready(ts)) {
+		qtnf_try_stop_xmit(bus, skb->dev);
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
+		return NETDEV_TX_BUSY;
+	}
+
+	i = priv->tx_bd_w_index;
+	priv->tx_skb[i] = skb;
+	len = skb->len;
+
+	skb_paddr = pci_map_single(priv->pdev, skb->data,
+				   skb->len, PCI_DMA_TODEVICE);
+	if (pci_dma_mapping_error(priv->pdev, skb_paddr)) {
+		ret = -ENOMEM;
+		goto tx_done;
+	}
+
+	txbd = &ts->tx_bd_vbase[i];
+	txbd->addr = cpu_to_le32(QTN_HOST_LO32(skb_paddr));
+
+	writel(QTN_HOST_LO32(skb_paddr), &bda->request[i].addr);
+	writel(len | QTN_PCIE_TX_VALID_PKT, &bda->request[i].info);
+
+	/* sync up descriptor updates before generating interrupt */
+	dma_wmb();
+
+	/* generate irq to card: tx done */
+	writel(TOPAZ_IPC_IRQ_WORD(TOPAZ_RC_TX_DONE_IRQ),
+	       TOPAZ_LH_IPC4_INT(priv->sysctl_bar));
+
+	if (++i >= priv->tx_bd_num)
+		i = 0;
+
+	priv->tx_bd_w_index = i;
+
+tx_done:
+	if (ret) {
+		if (skb->dev)
+			skb->dev->stats.tx_dropped++;
+		dev_kfree_skb_any(skb);
+	}
+
+	priv->tx_done_count++;
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+	qtnf_topaz_data_tx_reclaim(ts);
+
+	return NETDEV_TX_OK;
+}
+
+static irqreturn_t qtnf_pcie_topaz_interrupt(int irq, void *data)
+{
+	struct qtnf_bus *bus = (struct qtnf_bus *)data;
+	struct qtnf_pcie_topaz_state *ts = (void *)get_bus_priv(bus);
+	struct qtnf_pcie_bus_priv *priv = &ts->base;
+
+	if (!priv->msi_enabled && !qtnf_topaz_intx_asserted(ts))
+		return IRQ_NONE;
+
+	priv->pcie_irq_count++;
+
+	qtnf_shm_ipc_irq_handler(&priv->shm_ipc_ep_in);
+	qtnf_shm_ipc_irq_handler(&priv->shm_ipc_ep_out);
+
+	if (napi_schedule_prep(&bus->mux_napi)) {
+		disable_rx_irqs(ts);
+		__napi_schedule(&bus->mux_napi);
+	}
+
+	tasklet_hi_schedule(&priv->reclaim_tq);
+
+	if (!priv->msi_enabled)
+		qtnf_deassert_intx(ts);
+
+	return IRQ_HANDLED;
+}
+
+static int qtnf_rx_data_ready(struct qtnf_pcie_topaz_state *ts)
+{
+	u16 index = ts->base.rx_bd_r_index;
+	struct qtnf_topaz_rx_bd *rxbd;
+	u32 descw;
+
+	rxbd = &ts->rx_bd_vbase[index];
+	descw = le32_to_cpu(rxbd->info);
+
+	if (descw & QTN_BD_EMPTY)
+		return 0;
+
+	return 1;
+}
+
+static int qtnf_topaz_rx_poll(struct napi_struct *napi, int budget)
+{
+	struct qtnf_bus *bus = container_of(napi, struct qtnf_bus, mux_napi);
+	struct qtnf_pcie_topaz_state *ts = (void *)get_bus_priv(bus);
+	struct qtnf_pcie_bus_priv *priv = &ts->base;
+	struct net_device *ndev = NULL;
+	struct sk_buff *skb = NULL;
+	int processed = 0;
+	struct qtnf_topaz_rx_bd *rxbd;
+	dma_addr_t skb_paddr;
+	int consume;
+	u32 descw;
+	u32 poffset;
+	u32 psize;
+	u16 r_idx;
+	u16 w_idx;
+	int ret;
+
+	while (processed < budget) {
+		if (!qtnf_rx_data_ready(ts))
+			goto rx_out;
+
+		r_idx = priv->rx_bd_r_index;
+		rxbd = &ts->rx_bd_vbase[r_idx];
+		descw = le32_to_cpu(rxbd->info);
+
+		skb = priv->rx_skb[r_idx];
+		poffset = QTN_GET_OFFSET(descw);
+		psize = QTN_GET_LEN(descw);
+		consume = 1;
+
+		if (descw & QTN_BD_EMPTY) {
+			pr_warn("skip invalid rxbd[%d]\n", r_idx);
+			consume = 0;
+		}
+
+		if (!skb) {
+			pr_warn("skip missing rx_skb[%d]\n", r_idx);
+			consume = 0;
+		}
+
+		if (skb && (skb_tailroom(skb) <  psize)) {
+			pr_err("skip packet with invalid length: %u > %u\n",
+			       psize, skb_tailroom(skb));
+			consume = 0;
+		}
+
+		if (skb) {
+			skb_paddr = QTN_HOST_ADDR(0x0, le32_to_cpu(rxbd->addr));
+			pci_unmap_single(priv->pdev, skb_paddr, SKB_BUF_SIZE,
+					 PCI_DMA_FROMDEVICE);
+		}
+
+		if (consume) {
+			skb_reserve(skb, poffset);
+			skb_put(skb, psize);
+			ndev = qtnf_classify_skb(bus, skb);
+			if (likely(ndev)) {
+				qtnf_update_rx_stats(ndev, skb);
+				skb->protocol = eth_type_trans(skb, ndev);
+				netif_receive_skb(skb);
+			} else {
+				pr_debug("drop untagged skb\n");
+				bus->mux_dev.stats.rx_dropped++;
+				dev_kfree_skb_any(skb);
+			}
+		} else {
+			if (skb) {
+				bus->mux_dev.stats.rx_dropped++;
+				dev_kfree_skb_any(skb);
+			}
+		}
+
+		/* notify card about recv packets once per several packets */
+		if (((++ts->rx_pkt_count) & RX_DONE_INTR_MSK) == 0)
+			writel(TOPAZ_IPC_IRQ_WORD(TOPAZ_RC_RX_DONE_IRQ),
+			       TOPAZ_LH_IPC4_INT(priv->sysctl_bar));
+
+		priv->rx_skb[r_idx] = NULL;
+		if (++r_idx >= priv->rx_bd_num)
+			r_idx = 0;
+
+		priv->rx_bd_r_index = r_idx;
+
+		/* repalce processed buffer by a new one */
+		w_idx = priv->rx_bd_w_index;
+		while (CIRC_SPACE(priv->rx_bd_w_index, priv->rx_bd_r_index,
+				  priv->rx_bd_num) > 0) {
+			if (++w_idx >= priv->rx_bd_num)
+				w_idx = 0;
+
+			ret = topaz_skb2rbd_attach(ts, w_idx,
+						   descw & QTN_BD_WRAP);
+			if (ret) {
+				pr_err("failed to allocate new rx_skb[%d]\n",
+				       w_idx);
+				break;
+			}
+		}
+
+		processed++;
+	}
+
+rx_out:
+	if (processed < budget) {
+		napi_complete(napi);
+		enable_rx_irqs(ts);
+	}
+
+	return processed;
+}
+
+static void
+qtnf_pcie_data_tx_timeout(struct qtnf_bus *bus, struct net_device *ndev)
+{
+	struct qtnf_pcie_topaz_state *ts = get_bus_priv(bus);
+
+	qtnf_try_wake_xmit(bus, ndev);
+	tasklet_hi_schedule(&ts->base.reclaim_tq);
+}
+
+static void qtnf_pcie_data_rx_start(struct qtnf_bus *bus)
+{
+	struct qtnf_pcie_topaz_state *ts = get_bus_priv(bus);
+
+	napi_enable(&bus->mux_napi);
+	enable_rx_irqs(ts);
+}
+
+static void qtnf_pcie_data_rx_stop(struct qtnf_bus *bus)
+{
+	struct qtnf_pcie_topaz_state *ts = get_bus_priv(bus);
+
+	disable_rx_irqs(ts);
+	napi_disable(&bus->mux_napi);
+}
+
+static const struct qtnf_bus_ops qtnf_pcie_topaz_bus_ops = {
+	/* control path methods */
+	.control_tx	= qtnf_pcie_control_tx,
+
+	/* data path methods */
+	.data_tx		= qtnf_pcie_data_tx,
+	.data_tx_timeout	= qtnf_pcie_data_tx_timeout,
+	.data_rx_start		= qtnf_pcie_data_rx_start,
+	.data_rx_stop		= qtnf_pcie_data_rx_stop,
+};
+
+static int qtnf_dbg_irq_stats(struct seq_file *s, void *data)
+{
+	struct qtnf_bus *bus = dev_get_drvdata(s->private);
+	struct qtnf_pcie_topaz_state *ts = get_bus_priv(bus);
+
+	seq_printf(s, "pcie_irq_count(%u)\n", ts->base.pcie_irq_count);
+
+	return 0;
+}
+
+static int qtnf_dbg_pkt_stats(struct seq_file *s, void *data)
+{
+	struct qtnf_bus *bus = dev_get_drvdata(s->private);
+	struct qtnf_pcie_topaz_state *ts = get_bus_priv(bus);
+	struct qtnf_pcie_bus_priv *priv = &ts->base;
+	u32 tx_done_index = readl(ts->ep_next_rx_pkt);
+
+	seq_printf(s, "tx_full_count(%u)\n", priv->tx_full_count);
+	seq_printf(s, "tx_done_count(%u)\n", priv->tx_done_count);
+	seq_printf(s, "tx_reclaim_done(%u)\n", priv->tx_reclaim_done);
+	seq_printf(s, "tx_reclaim_req(%u)\n", priv->tx_reclaim_req);
+
+	seq_printf(s, "tx_bd_r_index(%u)\n", priv->tx_bd_r_index);
+	seq_printf(s, "tx_done_index(%u)\n", tx_done_index);
+	seq_printf(s, "tx_bd_w_index(%u)\n", priv->tx_bd_w_index);
+
+	seq_printf(s, "tx host queue len(%u)\n",
+		   CIRC_CNT(priv->tx_bd_w_index, priv->tx_bd_r_index,
+			    priv->tx_bd_num));
+	seq_printf(s, "tx reclaim queue len(%u)\n",
+		   CIRC_CNT(tx_done_index, priv->tx_bd_r_index,
+			    priv->tx_bd_num));
+	seq_printf(s, "tx card queue len(%u)\n",
+		   CIRC_CNT(priv->tx_bd_w_index, tx_done_index,
+			    priv->tx_bd_num));
+
+	seq_printf(s, "rx_bd_r_index(%u)\n", priv->rx_bd_r_index);
+	seq_printf(s, "rx_bd_w_index(%u)\n", priv->rx_bd_w_index);
+	seq_printf(s, "rx alloc queue len(%u)\n",
+		   CIRC_SPACE(priv->rx_bd_w_index, priv->rx_bd_r_index,
+			      priv->rx_bd_num));
+
+	return 0;
+}
+
+static void qtnf_reset_dma_offset(struct qtnf_pcie_topaz_state *ts)
+{
+	struct qtnf_topaz_bda __iomem *bda = ts->bda;
+	u32 offset = readl(&bda->bda_dma_offset);
+
+	if ((offset & PCIE_DMA_OFFSET_ERROR_MASK) != PCIE_DMA_OFFSET_ERROR)
+		return;
+
+	writel(0x0, &bda->bda_dma_offset);
+}
+
+static int qtnf_pcie_endian_detect(struct qtnf_pcie_topaz_state *ts)
+{
+	struct qtnf_topaz_bda __iomem *bda = ts->bda;
+	u32 timeout = 0;
+	u32 endian;
+	int ret = 0;
+
+	writel(QTN_PCI_ENDIAN_DETECT_DATA, &bda->bda_pci_endian);
+
+	/* flush endian modifications before status update */
+	dma_wmb();
+
+	writel(QTN_PCI_ENDIAN_VALID_STATUS, &bda->bda_pci_pre_status);
+
+	while (readl(&bda->bda_pci_post_status) !=
+	       QTN_PCI_ENDIAN_VALID_STATUS) {
+		usleep_range(1000, 1200);
+		if (++timeout > QTN_FW_DL_TIMEOUT_MS) {
+			pr_err("card endianness detection timed out\n");
+			ret = -ETIMEDOUT;
+			goto endian_out;
+		}
+	}
+
+	/* do not read before status is updated */
+	dma_rmb();
+
+	endian = readl(&bda->bda_pci_endian);
+	WARN(endian != QTN_PCI_LITTLE_ENDIAN,
+	     "%s: unexpected card endianness", __func__);
+
+endian_out:
+	writel(0, &bda->bda_pci_pre_status);
+	writel(0, &bda->bda_pci_post_status);
+	writel(0, &bda->bda_pci_endian);
+
+	return ret;
+}
+
+static int qtnf_pre_init_ep(struct qtnf_bus *bus)
+{
+	struct qtnf_pcie_topaz_state *ts = (void *)get_bus_priv(bus);
+	struct qtnf_topaz_bda __iomem *bda = ts->bda;
+	u32 flags;
+	int ret;
+
+	ret = qtnf_pcie_endian_detect(ts);
+	if (ret < 0) {
+		pr_err("failed to detect card endianness\n");
+		return ret;
+	}
+
+	writeb(ts->base.msi_enabled, &ts->bda->bda_rc_msi_enabled);
+	qtnf_reset_dma_offset(ts);
+
+	/* notify card about driver type and boot mode */
+	flags = readl(&bda->bda_flags) | QTN_BDA_HOST_QLINK_DRV;
+
+	if (ts->base.flashboot)
+		flags |= QTN_BDA_FLASH_BOOT;
+	else
+		flags &= ~QTN_BDA_FLASH_BOOT;
+
+	writel(flags, &bda->bda_flags);
+
+	qtnf_set_state(&ts->bda->bda_bootstate, QTN_BDA_FW_HOST_RDY);
+	if (qtnf_poll_state(&ts->bda->bda_bootstate, QTN_BDA_FW_TARGET_RDY,
+			    QTN_FW_DL_TIMEOUT_MS)) {
+		pr_err("card is not ready to boot...\n");
+		return -ETIMEDOUT;
+	}
+
+	return ret;
+}
+
+static int qtnf_post_init_ep(struct qtnf_pcie_topaz_state *ts)
+{
+	struct pci_dev *pdev = ts->base.pdev;
+
+	setup_rx_irqs(ts);
+	disable_rx_irqs(ts);
+
+	if (qtnf_poll_state(&ts->bda->bda_bootstate, QTN_BDA_FW_QLINK_DONE,
+			    QTN_FW_QLINK_TIMEOUT_MS))
+		return -ETIMEDOUT;
+
+	enable_irq(pdev->irq);
+	return 0;
+}
+
+static int
+qtnf_ep_fw_load(struct qtnf_pcie_topaz_state *ts, const u8 *fw, u32 fw_size)
+{
+	struct qtnf_topaz_bda __iomem *bda = ts->bda;
+	struct pci_dev *pdev = ts->base.pdev;
+	u32 remaining = fw_size;
+	u8 *curr = (u8 *)fw;
+	u32 blksize;
+	u32 nblocks;
+	u32 offset;
+	u32 count;
+	u32 size;
+	dma_addr_t paddr;
+	void *data;
+	int ret = 0;
+
+	pr_debug("FW upload started: fw_addr = 0x%p, size=%d\n", fw, fw_size);
+
+	blksize = ts->base.fw_blksize;
+
+	if (blksize < PAGE_SIZE)
+		blksize = PAGE_SIZE;
+
+	while (blksize >= PAGE_SIZE) {
+		pr_debug("allocating %u bytes to upload FW\n", blksize);
+		data = dma_alloc_coherent(&pdev->dev, blksize,
+					  &paddr, GFP_KERNEL);
+		if (data)
+			break;
+		blksize /= 2;
+	}
+
+	if (!data) {
+		pr_err("failed to allocate DMA buffer for FW upload\n");
+		ret = -ENOMEM;
+		goto fw_load_out;
+	}
+
+	nblocks = NBLOCKS(fw_size, blksize);
+	offset = readl(&bda->bda_dma_offset);
+
+	qtnf_set_state(&ts->bda->bda_bootstate, QTN_BDA_FW_HOST_LOAD);
+	if (qtnf_poll_state(&ts->bda->bda_bootstate, QTN_BDA_FW_EP_RDY,
+			    QTN_FW_DL_TIMEOUT_MS)) {
+		pr_err("card is not ready to download FW\n");
+		ret = -ETIMEDOUT;
+		goto fw_load_map;
+	}
+
+	for (count = 0 ; count < nblocks; count++) {
+		size = (remaining > blksize) ? blksize : remaining;
+
+		memcpy(data, curr, size);
+		qtnf_non_posted_write(paddr + offset, &bda->bda_img);
+		qtnf_non_posted_write(size, &bda->bda_img_size);
+
+		pr_debug("chunk[%u] VA[0x%p] PA[%pad] sz[%u]\n",
+			 count, (void *)curr, &paddr, size);
+
+		qtnf_set_state(&ts->bda->bda_bootstate, QTN_BDA_FW_BLOCK_RDY);
+		if (qtnf_poll_state(&ts->bda->bda_bootstate,
+				    QTN_BDA_FW_BLOCK_DONE,
+				    QTN_FW_DL_TIMEOUT_MS)) {
+			pr_err("confirmation for block #%d timed out\n", count);
+			ret = -ETIMEDOUT;
+			goto fw_load_map;
+		}
+
+		remaining = (remaining < size) ? remaining : (remaining - size);
+		curr += size;
+	}
+
+	/* upload completion mark: zero-sized block */
+	qtnf_non_posted_write(0, &bda->bda_img);
+	qtnf_non_posted_write(0, &bda->bda_img_size);
+
+	qtnf_set_state(&ts->bda->bda_bootstate, QTN_BDA_FW_BLOCK_RDY);
+	if (qtnf_poll_state(&ts->bda->bda_bootstate, QTN_BDA_FW_BLOCK_DONE,
+			    QTN_FW_DL_TIMEOUT_MS)) {
+		pr_err("confirmation for the last block timed out\n");
+		ret = -ETIMEDOUT;
+		goto fw_load_map;
+	}
+
+	/* RC is done */
+	qtnf_set_state(&ts->bda->bda_bootstate, QTN_BDA_FW_BLOCK_END);
+	if (qtnf_poll_state(&ts->bda->bda_bootstate, QTN_BDA_FW_LOAD_DONE,
+			    QTN_FW_DL_TIMEOUT_MS)) {
+		pr_err("confirmation for FW upload completion timed out\n");
+		ret = -ETIMEDOUT;
+		goto fw_load_map;
+	}
+
+	pr_debug("FW upload completed: totally sent %d blocks\n", count);
+
+fw_load_map:
+	dma_free_coherent(&pdev->dev, blksize, data, paddr);
+
+fw_load_out:
+	return ret;
+}
+
+static int qtnf_topaz_fw_upload(struct qtnf_pcie_topaz_state *ts,
+				const char *fwname)
+{
+	const struct firmware *fw;
+	struct pci_dev *pdev = ts->base.pdev;
+	int ret;
+
+	if (qtnf_poll_state(&ts->bda->bda_bootstate,
+			    QTN_BDA_FW_LOAD_RDY,
+			    QTN_FW_DL_TIMEOUT_MS)) {
+		pr_err("%s: card is not ready\n", fwname);
+		return -1;
+	}
+
+	pr_info("starting firmware upload: %s\n", fwname);
+
+	ret = request_firmware(&fw, fwname, &pdev->dev);
+	if (ret < 0) {
+		pr_err("%s: request_firmware error %d\n", fwname, ret);
+		return -1;
+	}
+
+	ret = qtnf_ep_fw_load(ts, fw->data, fw->size);
+	release_firmware(fw);
+
+	if (ret)
+		pr_err("%s: FW upload error\n", fwname);
+
+	return ret;
+}
+
+static void qtnf_topaz_fw_work_handler(struct work_struct *work)
+{
+	struct qtnf_bus *bus = container_of(work, struct qtnf_bus, fw_work);
+	struct qtnf_pcie_topaz_state *ts = (void *)get_bus_priv(bus);
+	int ret;
+	int bootloader_needed = readl(&ts->bda->bda_flags) & QTN_BDA_XMIT_UBOOT;
+
+	qtnf_set_state(&ts->bda->bda_bootstate, QTN_BDA_FW_TARGET_BOOT);
+
+	if (bootloader_needed) {
+		ret = qtnf_topaz_fw_upload(ts, QTN_PCI_TOPAZ_BOOTLD_NAME);
+		if (ret)
+			goto fw_load_exit;
+
+		ret = qtnf_pre_init_ep(bus);
+		if (ret)
+			goto fw_load_exit;
+
+		qtnf_set_state(&ts->bda->bda_bootstate,
+			       QTN_BDA_FW_TARGET_BOOT);
+	}
+
+	if (ts->base.flashboot) {
+		pr_info("booting firmware from flash\n");
+
+		ret = qtnf_poll_state(&ts->bda->bda_bootstate,
+				      QTN_BDA_FW_FLASH_BOOT,
+				      QTN_FW_DL_TIMEOUT_MS);
+		if (ret)
+			goto fw_load_exit;
+	} else {
+		ret = qtnf_topaz_fw_upload(ts, QTN_PCI_TOPAZ_FW_NAME);
+		if (ret)
+			goto fw_load_exit;
+
+		qtnf_set_state(&ts->bda->bda_bootstate, QTN_BDA_FW_START);
+		ret = qtnf_poll_state(&ts->bda->bda_bootstate,
+				      QTN_BDA_FW_CONFIG,
+				      QTN_FW_QLINK_TIMEOUT_MS);
+		if (ret) {
+			pr_err("FW bringup timed out\n");
+			goto fw_load_exit;
+		}
+
+		qtnf_set_state(&ts->bda->bda_bootstate, QTN_BDA_FW_RUN);
+		ret = qtnf_poll_state(&ts->bda->bda_bootstate,
+				      QTN_BDA_FW_RUNNING,
+				      QTN_FW_QLINK_TIMEOUT_MS);
+		if (ret) {
+			pr_err("card bringup timed out\n");
+			goto fw_load_exit;
+		}
+	}
+
+	pr_info("firmware is up and running\n");
+
+	ret = qtnf_post_init_ep(ts);
+	if (ret)
+		pr_err("FW runtime failure\n");
+
+fw_load_exit:
+	qtnf_pcie_fw_boot_done(bus, ret ? false : true);
+
+	if (ret == 0) {
+		qtnf_debugfs_add_entry(bus, "pkt_stats", qtnf_dbg_pkt_stats);
+		qtnf_debugfs_add_entry(bus, "irq_stats", qtnf_dbg_irq_stats);
+	}
+}
+
+static void qtnf_reclaim_tasklet_fn(unsigned long data)
+{
+	struct qtnf_pcie_topaz_state *ts = (void *)data;
+
+	qtnf_topaz_data_tx_reclaim(ts);
+}
+
+static u64 qtnf_topaz_dma_mask_get(void)
+{
+	return DMA_BIT_MASK(32);
+}
+
+static int qtnf_pcie_topaz_probe(struct qtnf_bus *bus, unsigned int tx_bd_num)
+{
+	struct qtnf_pcie_topaz_state *ts = get_bus_priv(bus);
+	struct pci_dev *pdev = ts->base.pdev;
+	struct qtnf_shm_ipc_int ipc_int;
+	unsigned long irqflags;
+	int ret;
+
+	bus->bus_ops = &qtnf_pcie_topaz_bus_ops;
+	INIT_WORK(&bus->fw_work, qtnf_topaz_fw_work_handler);
+	ts->bda = ts->base.epmem_bar;
+
+	/* assign host msi irq before card init */
+	if (ts->base.msi_enabled)
+		irqflags = IRQF_NOBALANCING;
+	else
+		irqflags = IRQF_NOBALANCING | IRQF_SHARED;
+
+	ret = devm_request_irq(&pdev->dev, pdev->irq,
+			       &qtnf_pcie_topaz_interrupt,
+			       irqflags, "qtnf_topaz_irq", (void *)bus);
+	if (ret) {
+		pr_err("failed to request pcie irq %d\n", pdev->irq);
+		return ret;
+	}
+
+	disable_irq(pdev->irq);
+
+	ret = qtnf_pre_init_ep(bus);
+	if (ret) {
+		pr_err("failed to init card\n");
+		return ret;
+	}
+
+	ret = qtnf_pcie_topaz_init_xfer(ts, tx_bd_num);
+	if (ret) {
+		pr_err("PCIE xfer init failed\n");
+		return ret;
+	}
+
+	tasklet_init(&ts->base.reclaim_tq, qtnf_reclaim_tasklet_fn,
+		     (unsigned long)ts);
+	netif_napi_add(&bus->mux_dev, &bus->mux_napi,
+		       qtnf_topaz_rx_poll, 10);
+
+	ipc_int.fn = qtnf_topaz_ipc_gen_ep_int;
+	ipc_int.arg = ts;
+	qtnf_pcie_init_shm_ipc(&ts->base, &ts->bda->bda_shm_reg1,
+			       &ts->bda->bda_shm_reg2, &ipc_int);
+
+	return 0;
+}
+
+static void qtnf_pcie_topaz_remove(struct qtnf_bus *bus)
+{
+	struct qtnf_pcie_topaz_state *ts = get_bus_priv(bus);
+
+	qtnf_topaz_reset_ep(ts);
+	qtnf_topaz_free_xfer_buffers(ts);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int qtnf_pcie_topaz_suspend(struct qtnf_bus *bus)
+{
+	struct qtnf_pcie_topaz_state *ts = get_bus_priv(bus);
+	struct pci_dev *pdev = ts->base.pdev;
+
+	writel((u32 __force)PCI_D3hot, ts->ep_pmstate);
+	dma_wmb();
+	writel(TOPAZ_IPC_IRQ_WORD(TOPAZ_RC_PM_EP_IRQ),
+	       TOPAZ_LH_IPC4_INT(ts->base.sysctl_bar));
+
+	pci_save_state(pdev);
+	pci_enable_wake(pdev, PCI_D3hot, 1);
+	pci_set_power_state(pdev, PCI_D3hot);
+
+	return 0;
+}
+
+static int qtnf_pcie_topaz_resume(struct qtnf_bus *bus)
+{
+	struct qtnf_pcie_topaz_state *ts = get_bus_priv(bus);
+	struct pci_dev *pdev = ts->base.pdev;
+
+	pci_set_power_state(pdev, PCI_D0);
+	pci_restore_state(pdev);
+	pci_enable_wake(pdev, PCI_D0, 0);
+
+	writel((u32 __force)PCI_D0, ts->ep_pmstate);
+	dma_wmb();
+	writel(TOPAZ_IPC_IRQ_WORD(TOPAZ_RC_PM_EP_IRQ),
+	       TOPAZ_LH_IPC4_INT(ts->base.sysctl_bar));
+
+	return 0;
+}
+#endif
+
+struct qtnf_bus *qtnf_pcie_topaz_alloc(struct pci_dev *pdev)
+{
+	struct qtnf_bus *bus;
+	struct qtnf_pcie_topaz_state *ts;
+
+	bus = devm_kzalloc(&pdev->dev, sizeof(*bus) + sizeof(*ts), GFP_KERNEL);
+	if (!bus)
+		return NULL;
+
+	ts = get_bus_priv(bus);
+	ts->base.probe_cb = qtnf_pcie_topaz_probe;
+	ts->base.remove_cb = qtnf_pcie_topaz_remove;
+	ts->base.dma_mask_get_cb = qtnf_topaz_dma_mask_get;
+#ifdef CONFIG_PM_SLEEP
+	ts->base.resume_cb = qtnf_pcie_topaz_resume;
+	ts->base.suspend_cb = qtnf_pcie_topaz_suspend;
+#endif
+
+	return bus;
+}
diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie_ipc.h b/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie_ipc.h
new file mode 100644
index 000000000000..eb30e9d08de2
--- /dev/null
+++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie_ipc.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2018 Quantenna Communications */
+
+#ifndef _QTN_FMAC_PCIE_IPC_H_
+#define _QTN_FMAC_PCIE_IPC_H_
+
+#include <linux/types.h>
+
+#include "shm_ipc_defs.h"
+
+/* EP/RC status and flags */
+#define QTN_BDA_PCIE_INIT		0x01
+#define QTN_BDA_PCIE_RDY		0x02
+#define QTN_BDA_FW_LOAD_RDY		0x03
+#define QTN_BDA_FW_LOAD_DONE		0x04
+#define QTN_BDA_FW_START		0x05
+#define QTN_BDA_FW_RUN			0x06
+#define QTN_BDA_FW_HOST_RDY		0x07
+#define QTN_BDA_FW_TARGET_RDY		0x11
+#define QTN_BDA_FW_TARGET_BOOT		0x12
+#define QTN_BDA_FW_FLASH_BOOT		0x13
+#define QTN_BDA_FW_QLINK_DONE		0x14
+#define QTN_BDA_FW_HOST_LOAD		0x08
+#define QTN_BDA_FW_BLOCK_DONE		0x09
+#define QTN_BDA_FW_BLOCK_RDY		0x0A
+#define QTN_BDA_FW_EP_RDY		0x0B
+#define QTN_BDA_FW_BLOCK_END		0x0C
+#define QTN_BDA_FW_CONFIG		0x0D
+#define QTN_BDA_FW_RUNNING		0x0E
+#define QTN_BDA_PCIE_FAIL		0x82
+#define QTN_BDA_FW_LOAD_FAIL		0x85
+
+#define QTN_BDA_RCMODE			BIT(1)
+#define QTN_BDA_MSI			BIT(2)
+#define QTN_BDA_HOST_CALCMD		BIT(3)
+#define QTN_BDA_FLASH_PRESENT		BIT(4)
+#define QTN_BDA_FLASH_BOOT		BIT(5)
+#define QTN_BDA_XMIT_UBOOT		BIT(6)
+#define QTN_BDA_HOST_QLINK_DRV		BIT(7)
+#define QTN_BDA_TARGET_FBOOT_ERR	BIT(8)
+#define QTN_BDA_TARGET_FWLOAD_ERR	BIT(9)
+#define QTN_BDA_HOST_NOFW_ERR		BIT(12)
+#define QTN_BDA_HOST_MEMALLOC_ERR	BIT(13)
+#define QTN_BDA_HOST_MEMMAP_ERR		BIT(14)
+#define QTN_BDA_VER(x)			(((x) >> 4) & 0xFF)
+#define QTN_BDA_ERROR_MASK		0xFF00
+
+/* registers and shmem address macros */
+#if BITS_PER_LONG == 64
+#define QTN_HOST_HI32(a)	((u32)(((u64)a) >> 32))
+#define QTN_HOST_LO32(a)	((u32)(((u64)a) & 0xffffffffUL))
+#define QTN_HOST_ADDR(h, l)	((((u64)h) << 32) | ((u64)l))
+#elif BITS_PER_LONG == 32
+#define QTN_HOST_HI32(a)	0
+#define QTN_HOST_LO32(a)	((u32)(((u32)a) & 0xffffffffUL))
+#define QTN_HOST_ADDR(h, l)	((u32)l)
+#else
+#error Unexpected BITS_PER_LONG value
+#endif
+
+#define QTN_PCIE_BDA_VERSION		0x1001
+
+#define PCIE_BDA_NAMELEN		32
+
+#define QTN_PCIE_RC_TX_QUEUE_LEN	256
+#define QTN_PCIE_TX_VALID_PKT		0x80000000
+#define QTN_PCIE_PKT_LEN_MASK		0xffff
+
+#define QTN_BD_EMPTY		((uint32_t)0x00000001)
+#define QTN_BD_WRAP		((uint32_t)0x00000002)
+#define QTN_BD_MASK_LEN		((uint32_t)0xFFFF0000)
+#define QTN_BD_MASK_OFFSET	((uint32_t)0x0000FF00)
+
+#define QTN_GET_LEN(x)		(((x) >> 16) & 0xFFFF)
+#define QTN_GET_OFFSET(x)	(((x) >> 8) & 0xFF)
+#define QTN_SET_LEN(len)	(((len) & 0xFFFF) << 16)
+#define QTN_SET_OFFSET(of)	(((of) & 0xFF) << 8)
+
+#define RX_DONE_INTR_MSK	((0x1 << 6) - 1)
+
+#define PCIE_DMA_OFFSET_ERROR		0xFFFF
+#define PCIE_DMA_OFFSET_ERROR_MASK	0xFFFF
+
+#define QTN_PCI_ENDIAN_DETECT_DATA	0x12345678
+#define QTN_PCI_ENDIAN_REVERSE_DATA	0x78563412
+#define QTN_PCI_ENDIAN_VALID_STATUS	0x3c3c3c3c
+#define QTN_PCI_ENDIAN_INVALID_STATUS	0
+#define QTN_PCI_LITTLE_ENDIAN		0
+#define QTN_PCI_BIG_ENDIAN		0xffffffff
+
+#define NBLOCKS(size, blksize)		\
+	((size) / (blksize) + (((size) % (blksize) > 0) ? 1 : 0))
+
+#endif /* _QTN_FMAC_PCIE_IPC_H_ */
diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie_regs.h b/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie_regs.h
new file mode 100644
index 000000000000..4782e1ed3c2c
--- /dev/null
+++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie_regs.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2018 Quantenna Communications */
+
+#ifndef __TOPAZ_PCIE_H
+#define __TOPAZ_PCIE_H
+
+/* Topaz PCIe DMA registers */
+#define PCIE_DMA_WR_INTR_STATUS(base)		((base) + 0x9bc)
+#define PCIE_DMA_WR_INTR_MASK(base)		((base) + 0x9c4)
+#define PCIE_DMA_WR_INTR_CLR(base)		((base) + 0x9c8)
+#define PCIE_DMA_WR_ERR_STATUS(base)		((base) + 0x9cc)
+#define PCIE_DMA_WR_DONE_IMWR_ADDR_LOW(base)	((base) + 0x9D0)
+#define PCIE_DMA_WR_DONE_IMWR_ADDR_HIGH(base)	((base) + 0x9d4)
+
+#define PCIE_DMA_RD_INTR_STATUS(base)		((base) + 0x310)
+#define PCIE_DMA_RD_INTR_MASK(base)		((base) + 0x319)
+#define PCIE_DMA_RD_INTR_CLR(base)		((base) + 0x31c)
+#define PCIE_DMA_RD_ERR_STATUS_LOW(base)	((base) + 0x324)
+#define PCIE_DMA_RD_ERR_STATUS_HIGH(base)	((base) + 0x328)
+#define PCIE_DMA_RD_DONE_IMWR_ADDR_LOW(base)	((base) + 0x33c)
+#define PCIE_DMA_RD_DONE_IMWR_ADDR_HIGH(base)	((base) + 0x340)
+
+/* Topaz LHost IPC4 interrupt */
+#define TOPAZ_LH_IPC4_INT(base)			((base) + 0x13C)
+#define TOPAZ_LH_IPC4_INT_MASK(base)		((base) + 0x140)
+
+#define TOPAZ_RC_TX_DONE_IRQ			(0)
+#define TOPAZ_RC_RST_EP_IRQ			(1)
+#define TOPAZ_RC_TX_STOP_IRQ			(2)
+#define TOPAZ_RC_RX_DONE_IRQ			(3)
+#define TOPAZ_RC_PM_EP_IRQ			(4)
+
+/* Topaz LHost M2L interrupt */
+#define TOPAZ_CTL_M2L_INT(base)			((base) + 0x2C)
+#define TOPAZ_CTL_M2L_INT_MASK(base)		((base) + 0x30)
+
+#define TOPAZ_RC_CTRL_IRQ			(6)
+
+#define TOPAZ_IPC_IRQ_WORD(irq)			(BIT(irq) | BIT(irq + 16))
+
+/* PCIe legacy INTx */
+#define TOPAZ_PCIE_CFG0_OFFSET	(0x6C)
+#define TOPAZ_ASSERT_INTX	BIT(9)
+
+#endif /* __TOPAZ_PCIE_H */
diff --git a/drivers/net/wireless/quantenna/qtnfmac/qtn_hw_ids.h b/drivers/net/wireless/quantenna/qtnfmac/qtn_hw_ids.h
index 1fe798a9a667..40295a511224 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/qtn_hw_ids.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/qtn_hw_ids.h
@@ -23,7 +23,7 @@
 
 /* PCIE Device IDs */
 
-#define	PCIE_DEVICE_ID_QTN_PEARL	(0x0008)
+#define	PCIE_DEVICE_ID_QSR		(0x0008)
 
 #define QTN_REG_SYS_CTRL_CSR		0x14
 #define QTN_CHIP_ID_MASK		0xF0
@@ -35,6 +35,8 @@
 /* FW names */
 
 #define QTN_PCI_PEARL_FW_NAME		"qtn/fmac_qsr10g.img"
+#define QTN_PCI_TOPAZ_FW_NAME		"qtn/fmac_qsr1000.img"
+#define QTN_PCI_TOPAZ_BOOTLD_NAME	"qtn/uboot_qsr1000.img"
 
 static inline unsigned int qtnf_chip_id_get(const void __iomem *regs_base)
 {
diff --git a/drivers/net/wireless/quantenna/qtnfmac/util.c b/drivers/net/wireless/quantenna/qtnfmac/util.c
index dfe3fe8a42c1..3bc96b264769 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/util.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/util.c
@@ -121,6 +121,8 @@ void qtnf_sta_list_free(struct qtnf_sta_list *list)
 const char *qtnf_chipid_to_string(unsigned long chip_id)
 {
 	switch (chip_id) {
+	case QTN_CHIP_ID_TOPAZ:
+		return "Topaz";
 	case QTN_CHIP_ID_PEARL:
 		return "Pearl revA";
 	case QTN_CHIP_ID_PEARL_B:
-- 
cgit v1.2.3


From e966a79c2f761a696dec9cfb0e2d4aa977bf78cb Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 16 Oct 2018 18:43:42 +0100
Subject: brcmfmac: fix spelling mistake "Retreiving" -> "Retrieving"

Trivial fix to spelling mistake in brcmf_err error message.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
index d52774c6489b..e738112ed87c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
@@ -214,7 +214,7 @@ int brcmf_c_preinit_dcmds(struct brcmf_if *ifp)
 	err = brcmf_fil_iovar_data_get(ifp, "cur_etheraddr", ifp->mac_addr,
 				       sizeof(ifp->mac_addr));
 	if (err < 0) {
-		brcmf_err("Retreiving cur_etheraddr failed, %d\n", err);
+		brcmf_err("Retrieving cur_etheraddr failed, %d\n", err);
 		goto done;
 	}
 	memcpy(ifp->drvr->wiphy->perm_addr, ifp->drvr->mac, ETH_ALEN);
@@ -269,7 +269,7 @@ int brcmf_c_preinit_dcmds(struct brcmf_if *ifp)
 	strcpy(buf, "ver");
 	err = brcmf_fil_iovar_data_get(ifp, "ver", buf, sizeof(buf));
 	if (err < 0) {
-		brcmf_err("Retreiving version information failed, %d\n",
+		brcmf_err("Retrieving version information failed, %d\n",
 			  err);
 		goto done;
 	}
-- 
cgit v1.2.3


From 1066bd193d681bda0fbacda9df351241a5ee04d9 Mon Sep 17 00:00:00 2001
From: Sergey Matyukevich <sergey.matyukevich.os@quantenna.com>
Date: Wed, 17 Oct 2018 14:02:47 +0000
Subject: qtnfmac: fix error handling in control path

This patch fixes the following warnings:

- smatch
drivers/net/wireless/quantenna/qtnfmac/commands.c:132 qtnf_cmd_send_with_reply() warn: variable dereferenced before check 'resp' (see line 117)
drivers/net/wireless/quantenna/qtnfmac/commands.c:716  qtnf_cmd_get_sta_info() error: uninitialized symbol 'var_resp_len'.
drivers/net/wireless/quantenna/qtnfmac/commands.c:1668 qtnf_cmd_get_mac_info() error: uninitialized symbol 'var_data_len'.
drivers/net/wireless/quantenna/qtnfmac/commands.c:1697 qtnf_cmd_get_hw_info() error: uninitialized symbol 'info_len'.
drivers/net/wireless/quantenna/qtnfmac/commands.c:1753 qtnf_cmd_band_info_get() error: uninitialized symbol 'info_len'.
drivers/net/wireless/quantenna/qtnfmac/commands.c:1782 qtnf_cmd_send_get_phy_params() error: uninitialized symbol 'response_size'.
drivers/net/wireless/quantenna/qtnfmac/commands.c:2438 qtnf_cmd_get_chan_stats() error: uninitialized symbol 'var_data_len'.

- gcc-8.2.1
drivers/net/wireless/quantenna/qtnfmac/commands.c: In function 'qtnf_cmd_send_with_reply':
drivers/net/wireless/quantenna/qtnfmac/commands.c:133:54: error: 'resp' may be used uninitialized in this function [-Werror=maybe-uninitialized]

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Sergey Matyukevich <sergey.matyukevich.os@quantenna.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/quantenna/qtnfmac/commands.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c
index bfdc1ad30c13..659e7649fe22 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c
@@ -84,7 +84,7 @@ static int qtnf_cmd_send_with_reply(struct qtnf_bus *bus,
 				    size_t *var_resp_size)
 {
 	struct qlink_cmd *cmd;
-	const struct qlink_resp *resp;
+	struct qlink_resp *resp = NULL;
 	struct sk_buff *resp_skb = NULL;
 	u16 cmd_id;
 	u8 mac_id;
@@ -113,7 +113,12 @@ static int qtnf_cmd_send_with_reply(struct qtnf_bus *bus,
 	if (ret)
 		goto out;
 
-	resp = (const struct qlink_resp *)resp_skb->data;
+	if (WARN_ON(!resp_skb || !resp_skb->data)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	resp = (struct qlink_resp *)resp_skb->data;
 	ret = qtnf_cmd_check_reply_header(resp, cmd_id, mac_id, vif_id,
 					  const_resp_size);
 	if (ret)
@@ -686,7 +691,7 @@ int qtnf_cmd_get_sta_info(struct qtnf_vif *vif, const u8 *sta_mac,
 	struct sk_buff *cmd_skb, *resp_skb = NULL;
 	struct qlink_cmd_get_sta_info *cmd;
 	const struct qlink_resp_get_sta_info *resp;
-	size_t var_resp_len;
+	size_t var_resp_len = 0;
 	int ret = 0;
 
 	cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid,
@@ -1650,7 +1655,7 @@ int qtnf_cmd_get_mac_info(struct qtnf_wmac *mac)
 {
 	struct sk_buff *cmd_skb, *resp_skb = NULL;
 	const struct qlink_resp_get_mac_info *resp;
-	size_t var_data_len;
+	size_t var_data_len = 0;
 	int ret = 0;
 
 	cmd_skb = qtnf_cmd_alloc_new_cmdskb(mac->macid, QLINK_VIFID_RSVD,
@@ -1680,8 +1685,8 @@ int qtnf_cmd_get_hw_info(struct qtnf_bus *bus)
 {
 	struct sk_buff *cmd_skb, *resp_skb = NULL;
 	const struct qlink_resp_get_hw_info *resp;
+	size_t info_len = 0;
 	int ret = 0;
-	size_t info_len;
 
 	cmd_skb = qtnf_cmd_alloc_new_cmdskb(QLINK_MACID_RSVD, QLINK_VIFID_RSVD,
 					    QLINK_CMD_GET_HW_INFO,
@@ -1709,9 +1714,9 @@ int qtnf_cmd_band_info_get(struct qtnf_wmac *mac,
 			   struct ieee80211_supported_band *band)
 {
 	struct sk_buff *cmd_skb, *resp_skb = NULL;
-	size_t info_len;
 	struct qlink_cmd_band_info_get *cmd;
 	struct qlink_resp_band_info_get *resp;
+	size_t info_len = 0;
 	int ret = 0;
 	u8 qband;
 
@@ -1764,8 +1769,8 @@ out:
 int qtnf_cmd_send_get_phy_params(struct qtnf_wmac *mac)
 {
 	struct sk_buff *cmd_skb, *resp_skb = NULL;
-	size_t response_size;
 	struct qlink_resp_phy_params *resp;
+	size_t response_size = 0;
 	int ret = 0;
 
 	cmd_skb = qtnf_cmd_alloc_new_cmdskb(mac->macid, 0,
@@ -2431,7 +2436,7 @@ int qtnf_cmd_get_chan_stats(struct qtnf_wmac *mac, u16 channel,
 	struct sk_buff *cmd_skb, *resp_skb = NULL;
 	struct qlink_cmd_get_chan_stats *cmd;
 	struct qlink_resp_get_chan_stats *resp;
-	size_t var_data_len;
+	size_t var_data_len = 0;
 	int ret = 0;
 
 	cmd_skb = qtnf_cmd_alloc_new_cmdskb(mac->macid, QLINK_VIFID_RSVD,
-- 
cgit v1.2.3


From 9198f460ec9d0ba95b0e903537d4ef96d9e8d617 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 22 Oct 2018 07:51:15 +0000
Subject: rtlwifi: btcoex: remove set but not used variable 'ppsc'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c: In function 'halbtc_leave_lps':
drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c:295:21: warning:
 variable 'ppsc' set but not used [-Wunused-but-set-variable]

drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c: In function 'halbtc_enter_lps':
drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c:318:21: warning:
 variable 'ppsc' set but not used [-Wunused-but-set-variable]

It never used since introduction in
commit aa45a673b291 ("rtlwifi: btcoexist: Add new mini driver")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
index 6fbf8845a2ab..d748aab66aa2 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
@@ -292,11 +292,9 @@ bool halbtc_send_bt_mp_operation(struct btc_coexist *btcoexist, u8 op_code,
 static void halbtc_leave_lps(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv;
-	struct rtl_ps_ctl *ppsc;
 	bool ap_enable = false;
 
 	rtlpriv = btcoexist->adapter;
-	ppsc = rtl_psc(rtlpriv);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_AP_MODE_ENABLE,
 			   &ap_enable);
@@ -315,11 +313,9 @@ static void halbtc_leave_lps(struct btc_coexist *btcoexist)
 static void halbtc_enter_lps(struct btc_coexist *btcoexist)
 {
 	struct rtl_priv *rtlpriv;
-	struct rtl_ps_ctl *ppsc;
 	bool ap_enable = false;
 
 	rtlpriv = btcoexist->adapter;
-	ppsc = rtl_psc(rtlpriv);
 
 	btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_AP_MODE_ENABLE,
 			   &ap_enable);
-- 
cgit v1.2.3


From e20c50cdca19e1dfcba64b17e9ae8a0a7540c7a2 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 13:50:08 +0200
Subject: rtl8xxxu: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1357355 ("Missing break in switch")
Addresses-Coverity-ID: 1357378 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
index 56040b181cf5..c6b0686555b3 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
@@ -1153,6 +1153,7 @@ void rtl8xxxu_gen1_config_channel(struct ieee80211_hw *hw)
 	switch (hw->conf.chandef.width) {
 	case NL80211_CHAN_WIDTH_20_NOHT:
 		ht = false;
+		/* fall through */
 	case NL80211_CHAN_WIDTH_20:
 		opmode |= BW_OPMODE_20MHZ;
 		rtl8xxxu_write8(priv, REG_BW_OPMODE, opmode);
@@ -1280,6 +1281,7 @@ void rtl8xxxu_gen2_config_channel(struct ieee80211_hw *hw)
 	switch (hw->conf.chandef.width) {
 	case NL80211_CHAN_WIDTH_20_NOHT:
 		ht = false;
+		/* fall through */
 	case NL80211_CHAN_WIDTH_20:
 		rf_mode_bw |= WMAC_TRXPTCL_CTL_BW_20;
 		subchannel = 0;
@@ -1748,9 +1750,11 @@ static int rtl8xxxu_identify_chip(struct rtl8xxxu_priv *priv)
 		case 3:
 			priv->ep_tx_low_queue = 1;
 			priv->ep_tx_count++;
+			/* fall through */
 		case 2:
 			priv->ep_tx_normal_queue = 1;
 			priv->ep_tx_count++;
+			/* fall through */
 		case 1:
 			priv->ep_tx_high_queue = 1;
 			priv->ep_tx_count++;
-- 
cgit v1.2.3


From 307b00c5e695857ca92fc6a4b8ab6c48f988a1b1 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 13:51:03 +0200
Subject: rtl8xxxu: Fix missing break in switch

Add missing break statement in order to prevent the code from falling
through to the default case.

Fixes: 26f1fad29ad9 ("New driver: rtl8xxxu (mac80211)")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
index c6b0686555b3..2bd43057dda3 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
@@ -5692,6 +5692,7 @@ static int rtl8xxxu_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		break;
 	case WLAN_CIPHER_SUITE_TKIP:
 		key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIC;
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3


From e9904084dd1be8de5bc06eaca75276556ef53e79 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:40:53 +0200
Subject: iwlegacy: 4965-mac: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlegacy/4965-mac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index 280cd8ae1696..6b4488a178a7 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -559,7 +559,7 @@ il4965_translate_rx_status(struct il_priv *il, u32 decrypt_in)
 			decrypt_out |= RX_RES_STATUS_BAD_KEY_TTAK;
 			break;
 		}
-		/* fall through if TTAK OK */
+		/* fall through - if TTAK OK */
 	default:
 		if (!(decrypt_in & RX_MPDU_RES_STATUS_ICV_OK))
 			decrypt_out |= RX_RES_STATUS_BAD_ICV_MIC;
-- 
cgit v1.2.3


From af71f8fef45ce7ebc2d4cab611942dbe439905f1 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:41:23 +0200
Subject: iwlegacy: common: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 201384 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlegacy/common.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c
index 6514baf799fe..a2f86cbcc740 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.c
+++ b/drivers/net/wireless/intel/iwlegacy/common.c
@@ -2695,6 +2695,7 @@ il_set_decrypted_flag(struct il_priv *il, struct ieee80211_hdr *hdr,
 		if ((decrypt_res & RX_RES_STATUS_DECRYPT_TYPE_MSK) ==
 		    RX_RES_STATUS_BAD_KEY_TTAK)
 			break;
+		/* fall through */
 
 	case RX_RES_STATUS_SEC_TYPE_WEP:
 		if ((decrypt_res & RX_RES_STATUS_DECRYPT_TYPE_MSK) ==
@@ -2704,6 +2705,7 @@ il_set_decrypted_flag(struct il_priv *il, struct ieee80211_hdr *hdr,
 			D_RX("Packet destroyed\n");
 			return -1;
 		}
+		/* fall through */
 	case RX_RES_STATUS_SEC_TYPE_CCMP:
 		if ((decrypt_res & RX_RES_STATUS_DECRYPT_TYPE_MSK) ==
 		    RX_RES_STATUS_DECRYPT_OK) {
-- 
cgit v1.2.3


From d56b26801e1d7663f4d138fa8893174d91205586 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:42:04 +0200
Subject: orinoco_usb: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intersil/orinoco/orinoco_usb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
index 21bb68457cfe..40a8b941ad5c 100644
--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
@@ -908,6 +908,7 @@ static int ezusb_access_ltv(struct ezusb_priv *upriv,
 	case EZUSB_CTX_REQ_SUBMITTED:
 		if (!ctx->in_rid)
 			break;
+		/* fall through */
 	default:
 		err("%s: Unexpected context state %d", __func__,
 		    state);
-- 
cgit v1.2.3


From d22b8fadd08e95124e13860397d2071a6f6625bc Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:42:29 +0200
Subject: prism54: isl_38xx: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114944 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intersil/prism54/isl_38xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intersil/prism54/isl_38xx.c b/drivers/net/wireless/intersil/prism54/isl_38xx.c
index ce9d4db0d9ca..b0eb58a62c90 100644
--- a/drivers/net/wireless/intersil/prism54/isl_38xx.c
+++ b/drivers/net/wireless/intersil/prism54/isl_38xx.c
@@ -235,6 +235,7 @@ isl38xx_in_queue(isl38xx_control_block *cb, int queue)
 		/* send queues */
 	case ISL38XX_CB_TX_MGMTQ:
 		BUG_ON(delta > ISL38XX_CB_MGMT_QSIZE);
+		/* fall through */
 
 	case ISL38XX_CB_TX_DATA_LQ:
 	case ISL38XX_CB_TX_DATA_HQ:
-- 
cgit v1.2.3


From 3d238b9d5048886ca6c4dbbd1381c2ae81759a14 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:42:47 +0200
Subject: prism54: isl_ioctl: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intersil/prism54/isl_ioctl.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intersil/prism54/isl_ioctl.c b/drivers/net/wireless/intersil/prism54/isl_ioctl.c
index 334717b0a2be..3ccf2a4b548c 100644
--- a/drivers/net/wireless/intersil/prism54/isl_ioctl.c
+++ b/drivers/net/wireless/intersil/prism54/isl_ioctl.c
@@ -1691,6 +1691,7 @@ static int prism54_get_encodeext(struct net_device *ndev,
 	case DOT11_AUTH_BOTH:
 	case DOT11_AUTH_SK:
 		wrqu->encoding.flags |= IW_ENCODE_RESTRICTED;
+		/* fall through */
 	case DOT11_AUTH_OS:
 	default:
 		wrqu->encoding.flags |= IW_ENCODE_OPEN;
-- 
cgit v1.2.3


From 38a0792d08e98a9aac5bcf638d8533d3fa5ff253 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:43:05 +0200
Subject: prism54: islpci_dev: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114947 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intersil/prism54/islpci_dev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intersil/prism54/islpci_dev.c b/drivers/net/wireless/intersil/prism54/islpci_dev.c
index 325176d4d796..ad6d3a56ae06 100644
--- a/drivers/net/wireless/intersil/prism54/islpci_dev.c
+++ b/drivers/net/wireless/intersil/prism54/islpci_dev.c
@@ -932,6 +932,7 @@ islpci_set_state(islpci_private *priv, islpci_state_t new_state)
 	switch (new_state) {
 	case PRV_STATE_OFF:
 		priv->state_off++;
+		/* fall through */
 	default:
 		priv->state = new_state;
 		break;
-- 
cgit v1.2.3


From 63fdc952df36b26279ad394a84e454cc74decb89 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:43:55 +0200
Subject: mwifiex: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/mwifiex/ie.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/marvell/mwifiex/ie.c b/drivers/net/wireless/marvell/mwifiex/ie.c
index 75cbd609d606..6845eb57b39a 100644
--- a/drivers/net/wireless/marvell/mwifiex/ie.c
+++ b/drivers/net/wireless/marvell/mwifiex/ie.c
@@ -363,6 +363,7 @@ static int mwifiex_uap_parse_tail_ies(struct mwifiex_private *priv,
 						    (const u8 *)hdr,
 						    hdr->len + sizeof(struct ieee_types_header)))
 				break;
+			/* fall through */
 		default:
 			memcpy(gen_ie->ie_buffer + ie_len, hdr,
 			       hdr->len + sizeof(struct ieee_types_header));
-- 
cgit v1.2.3


From 6eba8fd2235237784dfd01da55c3210d493aebdb Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:44:34 +0200
Subject: rt2x00: rt2400pci: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ralink/rt2x00/rt2400pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c
index 0bc8b0249c57..49a732798395 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c
@@ -1302,7 +1302,7 @@ static void rt2400pci_txdone(struct rt2x00_dev *rt2x00dev,
 			break;
 		case 2: /* Failure, excessive retries */
 			__set_bit(TXDONE_EXCESSIVE_RETRY, &txdesc.flags);
-			/* Don't break, this is a failed frame! */
+			/* Fall through - this is a failed frame! */
 		default: /* Failure */
 			__set_bit(TXDONE_FAILURE, &txdesc.flags);
 		}
-- 
cgit v1.2.3


From 10bb92217747c3384a01ebec005faa2f5e72bbd8 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:45:19 +0200
Subject: rt2x00: rt2500pci: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ralink/rt2x00/rt2500pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c
index 1ff5434798ec..e8e7bfe1ba9b 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c
@@ -1430,7 +1430,7 @@ static void rt2500pci_txdone(struct rt2x00_dev *rt2x00dev,
 			break;
 		case 2: /* Failure, excessive retries */
 			__set_bit(TXDONE_EXCESSIVE_RETRY, &txdesc.flags);
-			/* Don't break, this is a failed frame! */
+			/* Fall through - this is a failed frame! */
 		default: /* Failure */
 			__set_bit(TXDONE_FAILURE, &txdesc.flags);
 		}
-- 
cgit v1.2.3


From 916e6bbcfcff6cc5d7d33bba8557a30f3af50326 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:46:03 +0200
Subject: rt2x00: rt2800lib: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 145198 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ralink/rt2x00/rt2800lib.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
index 9e7b8933d30c..0e95555aec62 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
@@ -2482,6 +2482,7 @@ static void rt2800_config_channel_rf3052(struct rt2x00_dev *rt2x00dev,
 		switch (rt2x00dev->default_ant.tx_chain_num) {
 		case 1:
 			rt2x00_set_field8(&rfcsr, RFCSR1_TX1_PD, 1);
+			/* fall through */
 		case 2:
 			rt2x00_set_field8(&rfcsr, RFCSR1_TX2_PD, 1);
 			break;
@@ -2490,6 +2491,7 @@ static void rt2800_config_channel_rf3052(struct rt2x00_dev *rt2x00dev,
 		switch (rt2x00dev->default_ant.rx_chain_num) {
 		case 1:
 			rt2x00_set_field8(&rfcsr, RFCSR1_RX1_PD, 1);
+			/* fall through */
 		case 2:
 			rt2x00_set_field8(&rfcsr, RFCSR1_RX2_PD, 1);
 			break;
@@ -9457,8 +9459,10 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev)
 	switch (rx_chains) {
 	case 3:
 		spec->ht.mcs.rx_mask[2] = 0xff;
+		/* fall through */
 	case 2:
 		spec->ht.mcs.rx_mask[1] = 0xff;
+		/* fall through */
 	case 1:
 		spec->ht.mcs.rx_mask[0] = 0xff;
 		spec->ht.mcs.rx_mask[4] = 0x1; /* MCS32 */
-- 
cgit v1.2.3


From 641dd8068ecb078e7d12efe465df202bc16ca5eb Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:46:47 +0200
Subject: rt2x00: rt61pci: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ralink/rt2x00/rt61pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt61pci.c b/drivers/net/wireless/ralink/rt2x00/rt61pci.c
index cb0e1196f2c2..4c5de8fc8f12 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt61pci.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt61pci.c
@@ -2226,7 +2226,7 @@ static void rt61pci_txdone(struct rt2x00_dev *rt2x00dev)
 			break;
 		case 6: /* Failure, excessive retries */
 			__set_bit(TXDONE_EXCESSIVE_RETRY, &txdesc.flags);
-			/* Don't break, this is a failed frame! */
+			/* Fall through - this is a failed frame! */
 		default: /* Failure */
 			__set_bit(TXDONE_FAILURE, &txdesc.flags);
 		}
-- 
cgit v1.2.3


From d22d2492a35d507ec8edc0797418341bb716d8ff Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:47:20 +0200
Subject: ray_cs: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114948 ("Missing break in switch")
Addresses-Coverity-ID: 114949 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ray_cs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index 08c607c031bc..33ad87528d9a 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -889,8 +889,10 @@ static int ray_hw_xmit(unsigned char *data, int len, struct net_device *dev,
 	switch (ccsindex = get_free_tx_ccs(local)) {
 	case ECCSBUSY:
 		pr_debug("ray_hw_xmit tx_ccs table busy\n");
+		/* fall through */
 	case ECCSFULL:
 		pr_debug("ray_hw_xmit No free tx ccs\n");
+		/* fall through */
 	case ECARDGONE:
 		netif_stop_queue(dev);
 		return XMIT_NO_CCS;
-- 
cgit v1.2.3


From 89e54fa4562e74f129a95855b0e81ef5863d618b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:47:59 +0200
Subject: rtlwifi: rtl8821ae: phy: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
index 176deb2b5386..a75451c246fd 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
@@ -394,6 +394,7 @@ static void _rtl8812ae_phy_set_rfe_reg_24g(struct ieee80211_hw *hw)
 			rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000);
 			break;
 		}
+		/* fall through */
 	case 0:
 	case 2:
 	default:
-- 
cgit v1.2.3


From 7cbbe1597e4497d14b4d4b22d444a168caae1ce4 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 22 Oct 2018 22:48:26 +0200
Subject: zd1201: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/zydas/zd1201.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/zydas/zd1201.c b/drivers/net/wireless/zydas/zd1201.c
index 253403899fe9..22c70f1f568c 100644
--- a/drivers/net/wireless/zydas/zd1201.c
+++ b/drivers/net/wireless/zydas/zd1201.c
@@ -969,6 +969,7 @@ static int zd1201_set_mode(struct net_device *dev,
 			 */
 			zd1201_join(zd, "\0-*#\0", 5);
 			/* Put port in pIBSS */
+			/* Fall through */
 		case 8: /* No pseudo-IBSS in wireless extensions (yet) */
 			porttype = ZD1201_PORTTYPE_PSEUDOIBSS;
 			break;
-- 
cgit v1.2.3


From 96fca788e5788b7ea3b0050eb35a343637e0a465 Mon Sep 17 00:00:00 2001
From: Ali MJ Al-Nasrawy <alimjalnasrawy@gmail.com>
Date: Tue, 23 Oct 2018 19:12:35 +0300
Subject: brcmsmac: never log "tid x is not agg'able" by default

This message greatly spams the log under heavy Tx of frames with BK access
class which is especially true when operating as AP. It is also not informative
as the "agg'ablity" of TIDs are set once and never change.
Fix this by logging only in debug mode.

Signed-off-by: Ali MJ Al-Nasrawy <alimjalnasrawy@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
index 81ff558046a8..6188275b17e5 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
@@ -846,8 +846,8 @@ brcms_ops_ampdu_action(struct ieee80211_hw *hw,
 		status = brcms_c_aggregatable(wl->wlc, tid);
 		spin_unlock_bh(&wl->lock);
 		if (!status) {
-			brcms_err(wl->wlc->hw->d11core,
-				  "START: tid %d is not agg\'able\n", tid);
+			brcms_dbg_ht(wl->wlc->hw->d11core,
+				     "START: tid %d is not agg\'able\n", tid);
 			return -EINVAL;
 		}
 		ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid);
-- 
cgit v1.2.3


From 90e3243d16ad1ffef78c2dc56f376cb7f6ca76f8 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Wed, 24 Oct 2018 13:52:09 +0800
Subject: rtlwifi: rtl8723ae: Remove set but not used variables and #defines

radiob_array_table' and 'radiob_arraylen' are not used after setting its value.
It is safe to remove the unused variable. Meanwhile, radio B array should be
removed as well. because it will no longer be referenced.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c   | 5 +----
 drivers/net/wireless/realtek/rtlwifi/rtl8723ae/table.c | 4 ----
 drivers/net/wireless/realtek/rtlwifi/rtl8723ae/table.h | 2 --
 3 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c
index 5cf29f5a4b54..3f3327878b51 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c
@@ -509,13 +509,10 @@ bool rtl8723e_phy_config_rf_with_headerfile(struct ieee80211_hw *hw,
 	int i;
 	bool rtstatus = true;
 	u32 *radioa_array_table;
-	u32 *radiob_array_table;
-	u16 radioa_arraylen, radiob_arraylen;
+	u16 radioa_arraylen;
 
 	radioa_arraylen = RTL8723ERADIOA_1TARRAYLENGTH;
 	radioa_array_table = RTL8723E_RADIOA_1TARRAY;
-	radiob_arraylen = RTL8723E_RADIOB_1TARRAYLENGTH;
-	radiob_array_table = RTL8723E_RADIOB_1TARRAY;
 
 	rtstatus = true;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/table.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/table.c
index 61e86045f15c..1bbee0bfac23 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/table.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/table.c
@@ -475,10 +475,6 @@ u32 RTL8723E_RADIOA_1TARRAY[RTL8723ERADIOA_1TARRAYLENGTH] = {
 	0x000, 0x00030159,
 };
 
-u32 RTL8723E_RADIOB_1TARRAY[RTL8723E_RADIOB_1TARRAYLENGTH] = {
-	0x0,
-};
-
 u32 RTL8723EMAC_ARRAY[RTL8723E_MACARRAYLENGTH] = {
 	0x420, 0x00000080,
 	0x423, 0x00000000,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/table.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/table.h
index 57a548ceba7d..a044f3c456fa 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/table.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/table.h
@@ -36,8 +36,6 @@ extern u32 RTL8723EPHY_REG_1TARRAY[RTL8723E_PHY_REG_1TARRAY_LENGTH];
 extern u32 RTL8723EPHY_REG_ARRAY_PG[RTL8723E_PHY_REG_ARRAY_PGLENGTH];
 #define RTL8723ERADIOA_1TARRAYLENGTH		282
 extern u32 RTL8723E_RADIOA_1TARRAY[RTL8723ERADIOA_1TARRAYLENGTH];
-#define RTL8723E_RADIOB_1TARRAYLENGTH		1
-extern u32 RTL8723E_RADIOB_1TARRAY[RTL8723E_RADIOB_1TARRAYLENGTH];
 #define RTL8723E_MACARRAYLENGTH			172
 extern u32 RTL8723EMAC_ARRAY[RTL8723E_MACARRAYLENGTH];
 #define RTL8723E_AGCTAB_1TARRAYLENGTH		320
-- 
cgit v1.2.3


From 963b307361bd415b6979910b1ef0c39bfee7f70c Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Wed, 24 Oct 2018 14:07:36 +0800
Subject: rtlwifi: Remove same duplicated includes

Just remove same duplicated includes.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c | 1 -
 drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
index 4c1f8b08fc10..14dcb0816bc0 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
@@ -29,7 +29,6 @@
 #include "../stats.h"
 #include "reg.h"
 #include "def.h"
-#include "phy.h"
 #include "trx.h"
 #include "led.h"
 #include "dm.h"
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
index d7960dd5bf1a..b01c3c5e21c7 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
@@ -29,7 +29,6 @@
 #include "../stats.h"
 #include "reg.h"
 #include "def.h"
-#include "phy.h"
 #include "trx.h"
 #include "led.h"
 #include "dm.h"
-- 
cgit v1.2.3


From 3d39e1bb1c88f32820c5f9271f2c8c2fb9a52bac Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 24 Oct 2018 11:33:34 +0300
Subject: wireless: airo: potential buffer overflow in sprintf()

It looks like we wanted to print a maximum of BSSList_rid.ssidLen bytes
of the ssid, but we accidentally use "%*s" (width) instead of "%.*s"
(precision) so if the ssid doesn't have a NUL terminator this could lead
to an overflow.

Static analysis.  Not tested.

Fixes: e174961ca1a0 ("net: convert print_mac to %pM")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/cisco/airo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index 04dd7a936593..5512c7f73fce 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -5462,7 +5462,7 @@ static int proc_BSSList_open( struct inode *inode, struct file *file ) {
            we have to add a spin lock... */
 	rc = readBSSListRid(ai, doLoseSync, &BSSList_rid);
 	while(rc == 0 && BSSList_rid.index != cpu_to_le16(0xffff)) {
-		ptr += sprintf(ptr, "%pM %*s rssi = %d",
+		ptr += sprintf(ptr, "%pM %.*s rssi = %d",
 			       BSSList_rid.bssid,
 				(int)BSSList_rid.ssidLen,
 				BSSList_rid.ssid,
-- 
cgit v1.2.3


From ae5848cb4511bbbfe0306fcdbe5d9a95cd9546a9 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Fri, 26 Oct 2018 13:22:32 +0200
Subject: brcmutil: print invalid chanspec when WARN-ing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On one of my devices I got WARNINGs when brcmfmac tried to decode
chanspec. I couldn't tell if it was some unsupported format or just a
malformed value passed by a firmware.

Print chanspec value so it's possible to debug a possible problem.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c b/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c
index e7584b842dce..40e94fe72f46 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c
@@ -128,7 +128,7 @@ static void brcmu_d11n_decchspec(struct brcmu_chan *ch)
 		}
 		break;
 	default:
-		WARN_ON_ONCE(1);
+		WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec);
 		break;
 	}
 
@@ -140,7 +140,7 @@ static void brcmu_d11n_decchspec(struct brcmu_chan *ch)
 		ch->band = BRCMU_CHAN_BAND_2G;
 		break;
 	default:
-		WARN_ON_ONCE(1);
+		WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec);
 		break;
 	}
 }
@@ -167,7 +167,7 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch)
 			ch->sb = BRCMU_CHAN_SB_U;
 			ch->control_ch_num += CH_10MHZ_APART;
 		} else {
-			WARN_ON_ONCE(1);
+			WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec);
 		}
 		break;
 	case BRCMU_CHSPEC_D11AC_BW_80:
@@ -188,7 +188,7 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch)
 			ch->control_ch_num += CH_30MHZ_APART;
 			break;
 		default:
-			WARN_ON_ONCE(1);
+			WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec);
 			break;
 		}
 		break;
@@ -219,13 +219,13 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch)
 			ch->control_ch_num += CH_70MHZ_APART;
 			break;
 		default:
-			WARN_ON_ONCE(1);
+			WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec);
 			break;
 		}
 		break;
 	case BRCMU_CHSPEC_D11AC_BW_8080:
 	default:
-		WARN_ON_ONCE(1);
+		WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec);
 		break;
 	}
 
@@ -237,7 +237,7 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch)
 		ch->band = BRCMU_CHAN_BAND_2G;
 		break;
 	default:
-		WARN_ON_ONCE(1);
+		WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec);
 		break;
 	}
 }
-- 
cgit v1.2.3


From f4bd758f3f20e3cbcc7bc66880118a2681981e7d Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Thu, 1 Nov 2018 11:33:19 -0400
Subject: cw1200: fix small typo

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/st/cw1200/sta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/st/cw1200/sta.c b/drivers/net/wireless/st/cw1200/sta.c
index 38678e9a0562..8dae92a79fe1 100644
--- a/drivers/net/wireless/st/cw1200/sta.c
+++ b/drivers/net/wireless/st/cw1200/sta.c
@@ -1123,7 +1123,7 @@ int cw1200_setup_mac(struct cw1200_common *priv)
 	 *
 	 * NOTE2: RSSI based reports have been switched to RCPI, since
 	 * FW has a bug and RSSI reported values are not stable,
-	 * what can leads to signal level oscilations in user-end applications
+	 * what can lead to signal level oscilations in user-end applications
 	 */
 	struct wsm_rcpi_rssi_threshold threshold = {
 		.rssiRcpiMode = WSM_RCPI_RSSI_THRESHOLD_ENABLE |
-- 
cgit v1.2.3


From ac9ccb8b991cfca7f5847734089115f992bef7ff Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Thu, 1 Nov 2018 11:40:23 -0400
Subject: iwlegacy: fix small typo

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlegacy/3945-rs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlegacy/3945-rs.c b/drivers/net/wireless/intel/iwlegacy/3945-rs.c
index e8983c6a2b7b..a697edd46e7f 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-rs.c
@@ -781,7 +781,7 @@ il3945_rs_get_rate(void *il_r, struct ieee80211_sta *sta, void *il_sta,
 
 	switch (scale_action) {
 	case -1:
-		/* Decrese rate */
+		/* Decrease rate */
 		if (low != RATE_INVALID)
 			idx = low;
 		break;
-- 
cgit v1.2.3


From 7d129adff3afbd3a449bc3593f2064ac546d58d3 Mon Sep 17 00:00:00 2001
From: Shaokun Zhang <zhangshaokun@hisilicon.com>
Date: Mon, 5 Nov 2018 19:25:30 +0800
Subject: rtlwifi: rtl8192de: Fix misleading REG_MCUFWDL information

RT_TRACE shows REG_MCUFWDL value as a decimal value with a '0x'
prefix, which is somewhat misleading.

Fix it to print hexadecimal, as was intended.

Cc: Ping-Ke Shih <pkshih@realtek.com>
Cc: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c
index 85cedd083d2b..75bfa9dfef4a 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c
@@ -173,7 +173,7 @@ static int _rtl92d_fw_init(struct ieee80211_hw *hw)
 			 rtl_read_byte(rtlpriv, FW_MAC1_READY));
 	}
 	RT_TRACE(rtlpriv, COMP_FW, DBG_DMESG,
-		 "Polling FW ready fail!! REG_MCUFWDL:0x%08ul\n",
+		 "Polling FW ready fail!! REG_MCUFWDL:0x%08x\n",
 		 rtl_read_dword(rtlpriv, REG_MCUFWDL));
 	return -1;
 }
-- 
cgit v1.2.3


From a8d6219536c16b6ab4d6e6f959032670c9368584 Mon Sep 17 00:00:00 2001
From: Olof Johansson <olof@lixom.net>
Date: Fri, 2 Nov 2018 15:00:26 -0700
Subject: ISDN: eicon: Remove driver

I started looking at the history of this driver, and last time the
maintainer was active on the mailing list was when discussing how to
remove it. This was in 2012:

https://lore.kernel.org/lkml/4F4DE175.30002@melware.de/

It looks to me like this has in practice been an orphan for quite a while.
It's throwing warnings about stack size in a function that is in dire
need of refactoring, and it's probably a case of "it's time to call it".

Cc: Armin Schindler <mac@melware.de>
Cc: Karsten Keil <isdn@linux-pingi.de>
Signed-off-by: Olof Johansson <olof@lixom.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                               |     7 -
 drivers/isdn/hardware/Kconfig             |     2 -
 drivers/isdn/hardware/Makefile            |     1 -
 drivers/isdn/hardware/eicon/Kconfig       |    51 -
 drivers/isdn/hardware/eicon/Makefile      |    24 -
 drivers/isdn/hardware/eicon/adapter.h     |    18 -
 drivers/isdn/hardware/eicon/capi20.h      |   699 --
 drivers/isdn/hardware/eicon/capidtmf.c    |   685 --
 drivers/isdn/hardware/eicon/capidtmf.h    |    79 -
 drivers/isdn/hardware/eicon/capifunc.c    |  1219 ---
 drivers/isdn/hardware/eicon/capifunc.h    |    40 -
 drivers/isdn/hardware/eicon/capimain.c    |   141 -
 drivers/isdn/hardware/eicon/cardtype.h    |  1098 --
 drivers/isdn/hardware/eicon/cp_vers.h     |    26 -
 drivers/isdn/hardware/eicon/dadapter.c    |   364 -
 drivers/isdn/hardware/eicon/dadapter.h    |    34 -
 drivers/isdn/hardware/eicon/debug.c       |  2128 ----
 drivers/isdn/hardware/eicon/debug_if.h    |    88 -
 drivers/isdn/hardware/eicon/debuglib.c    |   156 -
 drivers/isdn/hardware/eicon/debuglib.h    |   322 -
 drivers/isdn/hardware/eicon/dfifo.h       |    54 -
 drivers/isdn/hardware/eicon/di.c          |   835 --
 drivers/isdn/hardware/eicon/di.h          |   118 -
 drivers/isdn/hardware/eicon/di_dbg.h      |    37 -
 drivers/isdn/hardware/eicon/di_defs.h     |   181 -
 drivers/isdn/hardware/eicon/did_vers.h    |    26 -
 drivers/isdn/hardware/eicon/diddfunc.c    |   115 -
 drivers/isdn/hardware/eicon/diva.c        |   666 --
 drivers/isdn/hardware/eicon/diva.h        |    33 -
 drivers/isdn/hardware/eicon/diva_didd.c   |   139 -
 drivers/isdn/hardware/eicon/diva_dma.c    |    94 -
 drivers/isdn/hardware/eicon/diva_dma.h    |    48 -
 drivers/isdn/hardware/eicon/diva_pci.h    |    20 -
 drivers/isdn/hardware/eicon/divacapi.h    |  1350 ---
 drivers/isdn/hardware/eicon/divamnt.c     |   239 -
 drivers/isdn/hardware/eicon/divasfunc.c   |   237 -
 drivers/isdn/hardware/eicon/divasi.c      |   562 --
 drivers/isdn/hardware/eicon/divasmain.c   |   848 --
 drivers/isdn/hardware/eicon/divasproc.c   |   412 -
 drivers/isdn/hardware/eicon/divasync.h    |   489 -
 drivers/isdn/hardware/eicon/dqueue.c      |   110 -
 drivers/isdn/hardware/eicon/dqueue.h      |    32 -
 drivers/isdn/hardware/eicon/dsp_defs.h    |   301 -
 drivers/isdn/hardware/eicon/dsp_tst.h     |    48 -
 drivers/isdn/hardware/eicon/dspdids.h     |    75 -
 drivers/isdn/hardware/eicon/dsrv4bri.h    |    40 -
 drivers/isdn/hardware/eicon/dsrv_bri.h    |    37 -
 drivers/isdn/hardware/eicon/dsrv_pri.h    |    38 -
 drivers/isdn/hardware/eicon/entity.h      |    29 -
 drivers/isdn/hardware/eicon/helpers.h     |    51 -
 drivers/isdn/hardware/eicon/idifunc.c     |   268 -
 drivers/isdn/hardware/eicon/io.c          |   852 --
 drivers/isdn/hardware/eicon/io.h          |   308 -
 drivers/isdn/hardware/eicon/istream.c     |   226 -
 drivers/isdn/hardware/eicon/kst_ifc.h     |   335 -
 drivers/isdn/hardware/eicon/maintidi.c    |  2194 ----
 drivers/isdn/hardware/eicon/maintidi.h    |   171 -
 drivers/isdn/hardware/eicon/man_defs.h    |   133 -
 drivers/isdn/hardware/eicon/mdm_msg.h     |   346 -
 drivers/isdn/hardware/eicon/message.c     | 14954 ----------------------------
 drivers/isdn/hardware/eicon/mi_pc.h       |   204 -
 drivers/isdn/hardware/eicon/mntfunc.c     |   370 -
 drivers/isdn/hardware/eicon/os_4bri.c     |  1132 ---
 drivers/isdn/hardware/eicon/os_4bri.h     |     9 -
 drivers/isdn/hardware/eicon/os_bri.c      |   815 --
 drivers/isdn/hardware/eicon/os_bri.h      |     9 -
 drivers/isdn/hardware/eicon/os_capi.h     |    21 -
 drivers/isdn/hardware/eicon/os_pri.c      |  1053 --
 drivers/isdn/hardware/eicon/os_pri.h      |     9 -
 drivers/isdn/hardware/eicon/pc.h          |   738 --
 drivers/isdn/hardware/eicon/pc_init.h     |   267 -
 drivers/isdn/hardware/eicon/pc_maint.h    |   160 -
 drivers/isdn/hardware/eicon/pkmaint.h     |    43 -
 drivers/isdn/hardware/eicon/platform.h    |   369 -
 drivers/isdn/hardware/eicon/pr_pc.h       |    76 -
 drivers/isdn/hardware/eicon/s_4bri.c      |   510 -
 drivers/isdn/hardware/eicon/s_bri.c       |   191 -
 drivers/isdn/hardware/eicon/s_pri.c       |   205 -
 drivers/isdn/hardware/eicon/sdp_hdr.h     |   117 -
 drivers/isdn/hardware/eicon/um_idi.c      |   886 --
 drivers/isdn/hardware/eicon/um_idi.h      |    44 -
 drivers/isdn/hardware/eicon/um_xdi.h      |    69 -
 drivers/isdn/hardware/eicon/xdi_adapter.h |    71 -
 drivers/isdn/hardware/eicon/xdi_msg.h     |   128 -
 drivers/isdn/hardware/eicon/xdi_vers.h    |    26 -
 85 files changed, 41755 deletions(-)
 delete mode 100644 drivers/isdn/hardware/eicon/Kconfig
 delete mode 100644 drivers/isdn/hardware/eicon/Makefile
 delete mode 100644 drivers/isdn/hardware/eicon/adapter.h
 delete mode 100644 drivers/isdn/hardware/eicon/capi20.h
 delete mode 100644 drivers/isdn/hardware/eicon/capidtmf.c
 delete mode 100644 drivers/isdn/hardware/eicon/capidtmf.h
 delete mode 100644 drivers/isdn/hardware/eicon/capifunc.c
 delete mode 100644 drivers/isdn/hardware/eicon/capifunc.h
 delete mode 100644 drivers/isdn/hardware/eicon/capimain.c
 delete mode 100644 drivers/isdn/hardware/eicon/cardtype.h
 delete mode 100644 drivers/isdn/hardware/eicon/cp_vers.h
 delete mode 100644 drivers/isdn/hardware/eicon/dadapter.c
 delete mode 100644 drivers/isdn/hardware/eicon/dadapter.h
 delete mode 100644 drivers/isdn/hardware/eicon/debug.c
 delete mode 100644 drivers/isdn/hardware/eicon/debug_if.h
 delete mode 100644 drivers/isdn/hardware/eicon/debuglib.c
 delete mode 100644 drivers/isdn/hardware/eicon/debuglib.h
 delete mode 100644 drivers/isdn/hardware/eicon/dfifo.h
 delete mode 100644 drivers/isdn/hardware/eicon/di.c
 delete mode 100644 drivers/isdn/hardware/eicon/di.h
 delete mode 100644 drivers/isdn/hardware/eicon/di_dbg.h
 delete mode 100644 drivers/isdn/hardware/eicon/di_defs.h
 delete mode 100644 drivers/isdn/hardware/eicon/did_vers.h
 delete mode 100644 drivers/isdn/hardware/eicon/diddfunc.c
 delete mode 100644 drivers/isdn/hardware/eicon/diva.c
 delete mode 100644 drivers/isdn/hardware/eicon/diva.h
 delete mode 100644 drivers/isdn/hardware/eicon/diva_didd.c
 delete mode 100644 drivers/isdn/hardware/eicon/diva_dma.c
 delete mode 100644 drivers/isdn/hardware/eicon/diva_dma.h
 delete mode 100644 drivers/isdn/hardware/eicon/diva_pci.h
 delete mode 100644 drivers/isdn/hardware/eicon/divacapi.h
 delete mode 100644 drivers/isdn/hardware/eicon/divamnt.c
 delete mode 100644 drivers/isdn/hardware/eicon/divasfunc.c
 delete mode 100644 drivers/isdn/hardware/eicon/divasi.c
 delete mode 100644 drivers/isdn/hardware/eicon/divasmain.c
 delete mode 100644 drivers/isdn/hardware/eicon/divasproc.c
 delete mode 100644 drivers/isdn/hardware/eicon/divasync.h
 delete mode 100644 drivers/isdn/hardware/eicon/dqueue.c
 delete mode 100644 drivers/isdn/hardware/eicon/dqueue.h
 delete mode 100644 drivers/isdn/hardware/eicon/dsp_defs.h
 delete mode 100644 drivers/isdn/hardware/eicon/dsp_tst.h
 delete mode 100644 drivers/isdn/hardware/eicon/dspdids.h
 delete mode 100644 drivers/isdn/hardware/eicon/dsrv4bri.h
 delete mode 100644 drivers/isdn/hardware/eicon/dsrv_bri.h
 delete mode 100644 drivers/isdn/hardware/eicon/dsrv_pri.h
 delete mode 100644 drivers/isdn/hardware/eicon/entity.h
 delete mode 100644 drivers/isdn/hardware/eicon/helpers.h
 delete mode 100644 drivers/isdn/hardware/eicon/idifunc.c
 delete mode 100644 drivers/isdn/hardware/eicon/io.c
 delete mode 100644 drivers/isdn/hardware/eicon/io.h
 delete mode 100644 drivers/isdn/hardware/eicon/istream.c
 delete mode 100644 drivers/isdn/hardware/eicon/kst_ifc.h
 delete mode 100644 drivers/isdn/hardware/eicon/maintidi.c
 delete mode 100644 drivers/isdn/hardware/eicon/maintidi.h
 delete mode 100644 drivers/isdn/hardware/eicon/man_defs.h
 delete mode 100644 drivers/isdn/hardware/eicon/mdm_msg.h
 delete mode 100644 drivers/isdn/hardware/eicon/message.c
 delete mode 100644 drivers/isdn/hardware/eicon/mi_pc.h
 delete mode 100644 drivers/isdn/hardware/eicon/mntfunc.c
 delete mode 100644 drivers/isdn/hardware/eicon/os_4bri.c
 delete mode 100644 drivers/isdn/hardware/eicon/os_4bri.h
 delete mode 100644 drivers/isdn/hardware/eicon/os_bri.c
 delete mode 100644 drivers/isdn/hardware/eicon/os_bri.h
 delete mode 100644 drivers/isdn/hardware/eicon/os_capi.h
 delete mode 100644 drivers/isdn/hardware/eicon/os_pri.c
 delete mode 100644 drivers/isdn/hardware/eicon/os_pri.h
 delete mode 100644 drivers/isdn/hardware/eicon/pc.h
 delete mode 100644 drivers/isdn/hardware/eicon/pc_init.h
 delete mode 100644 drivers/isdn/hardware/eicon/pc_maint.h
 delete mode 100644 drivers/isdn/hardware/eicon/pkmaint.h
 delete mode 100644 drivers/isdn/hardware/eicon/platform.h
 delete mode 100644 drivers/isdn/hardware/eicon/pr_pc.h
 delete mode 100644 drivers/isdn/hardware/eicon/s_4bri.c
 delete mode 100644 drivers/isdn/hardware/eicon/s_bri.c
 delete mode 100644 drivers/isdn/hardware/eicon/s_pri.c
 delete mode 100644 drivers/isdn/hardware/eicon/sdp_hdr.h
 delete mode 100644 drivers/isdn/hardware/eicon/um_idi.c
 delete mode 100644 drivers/isdn/hardware/eicon/um_idi.h
 delete mode 100644 drivers/isdn/hardware/eicon/um_xdi.h
 delete mode 100644 drivers/isdn/hardware/eicon/xdi_adapter.h
 delete mode 100644 drivers/isdn/hardware/eicon/xdi_msg.h
 delete mode 100644 drivers/isdn/hardware/eicon/xdi_vers.h

diff --git a/MAINTAINERS b/MAINTAINERS
index f4855974f325..cfab497a97cc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7843,13 +7843,6 @@ F:	include/linux/isdn/
 F:	include/uapi/linux/isdn.h
 F:	include/uapi/linux/isdn/
 
-ISDN SUBSYSTEM (Eicon active card driver)
-M:	Armin Schindler <mac@melware.de>
-L:	isdn4linux@listserv.isdn4linux.de (subscribers-only)
-W:	http://www.melware.de
-S:	Maintained
-F:	drivers/isdn/hardware/eicon/
-
 IT87 HARDWARE MONITORING DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-hwmon@vger.kernel.org
diff --git a/drivers/isdn/hardware/Kconfig b/drivers/isdn/hardware/Kconfig
index 30d028d24955..95c403088cce 100644
--- a/drivers/isdn/hardware/Kconfig
+++ b/drivers/isdn/hardware/Kconfig
@@ -5,5 +5,3 @@ comment "CAPI hardware drivers"
 
 source "drivers/isdn/hardware/avm/Kconfig"
 
-source "drivers/isdn/hardware/eicon/Kconfig"
-
diff --git a/drivers/isdn/hardware/Makefile b/drivers/isdn/hardware/Makefile
index a5d8fce4c4c4..e503032b05a0 100644
--- a/drivers/isdn/hardware/Makefile
+++ b/drivers/isdn/hardware/Makefile
@@ -3,5 +3,4 @@
 # Object files in subdirectories
 
 obj-$(CONFIG_CAPI_AVM)		+= avm/
-obj-$(CONFIG_CAPI_EICON)	+= eicon/
 obj-$(CONFIG_MISDN)		+= mISDN/
diff --git a/drivers/isdn/hardware/eicon/Kconfig b/drivers/isdn/hardware/eicon/Kconfig
deleted file mode 100644
index 6082b6a5ced3..000000000000
--- a/drivers/isdn/hardware/eicon/Kconfig
+++ /dev/null
@@ -1,51 +0,0 @@
-#
-# ISDN DIVAS Eicon driver
-#
-
-menuconfig CAPI_EICON
-	bool "Active Eicon DIVA Server cards"
-	help
-	  Enable support for Eicon Networks active ISDN cards.
-
-if CAPI_EICON
-
-config ISDN_DIVAS
-	tristate "Support Eicon DIVA Server cards"
-	depends on PROC_FS && PCI
-	help
-	  Say Y here if you have an Eicon Networks DIVA Server PCI ISDN card.
-	  In order to use this card, additional firmware is necessary, which
-	  has to be downloaded into the card using the divactrl utility.
-
-if ISDN_DIVAS
-
-config ISDN_DIVAS_BRIPCI
-	bool "DIVA Server BRI/PCI support"
-	help
-	  Enable support for DIVA Server BRI-PCI.
-
-config ISDN_DIVAS_PRIPCI
-	bool "DIVA Server PRI/PCI support"
-	help
-	  Enable support for DIVA Server PRI-PCI.
-
-config ISDN_DIVAS_DIVACAPI
-	tristate "DIVA CAPI2.0 interface support"
-	help
-	  You need this to provide the CAPI interface
-	  for DIVA Server cards.
-
-config ISDN_DIVAS_USERIDI
-	tristate "DIVA User-IDI interface support"
-	help
-	  Enable support for user-mode IDI interface.
-
-config ISDN_DIVAS_MAINT
-	tristate "DIVA Maint driver support"
-	depends on m
-	help
-	  Enable Divas Maintenance driver.
-
-endif # ISDN_DIVAS
-
-endif # CAPI_EICON
diff --git a/drivers/isdn/hardware/eicon/Makefile b/drivers/isdn/hardware/eicon/Makefile
deleted file mode 100644
index a0ab2e2d7df0..000000000000
--- a/drivers/isdn/hardware/eicon/Makefile
+++ /dev/null
@@ -1,24 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-# Makefile for the Eicon DIVA ISDN drivers.
-
-# Each configuration option enables a list of files.
-
-obj-$(CONFIG_ISDN_DIVAS)		+= divadidd.o divas.o
-obj-$(CONFIG_ISDN_DIVAS_MAINT)		+= diva_mnt.o
-obj-$(CONFIG_ISDN_DIVAS_USERIDI)	+= diva_idi.o
-obj-$(CONFIG_ISDN_DIVAS_DIVACAPI)	+= divacapi.o
-
-# Multipart objects. 
-
-divas-y					:= divasmain.o divasfunc.o di.o io.o istream.o \
-					   diva.o divasproc.o diva_dma.o
-divas-$(CONFIG_ISDN_DIVAS_BRIPCI)	+= os_bri.o  s_bri.o os_4bri.o s_4bri.o
-divas-$(CONFIG_ISDN_DIVAS_PRIPCI)	+= os_pri.o  s_pri.o
-
-divacapi-y				:= capimain.o capifunc.o message.o capidtmf.o
-
-divadidd-y				:= diva_didd.o diddfunc.o dadapter.o
-
-diva_mnt-y				:= divamnt.o mntfunc.o debug.o maintidi.o
-
-diva_idi-y				:= divasi.o idifunc.o um_idi.o dqueue.o
diff --git a/drivers/isdn/hardware/eicon/adapter.h b/drivers/isdn/hardware/eicon/adapter.h
deleted file mode 100644
index f9b24eb8781d..000000000000
--- a/drivers/isdn/hardware/eicon/adapter.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: adapter.h,v 1.4 2004/03/21 17:26:01 armin Exp $ */
-
-#ifndef __DIVA_USER_MODE_IDI_ADAPTER_H__
-#define __DIVA_USER_MODE_IDI_ADAPTER_H__
-
-#define DIVA_UM_IDI_ADAPTER_REMOVED 0x00000001
-
-typedef struct _diva_um_idi_adapter {
-	struct list_head link;
-	DESCRIPTOR d;
-	int adapter_nr;
-	struct list_head entity_q;	/* entities linked to this adapter */
-	dword status;
-} diva_um_idi_adapter_t;
-
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/capi20.h b/drivers/isdn/hardware/eicon/capi20.h
deleted file mode 100644
index 391e4175b0b5..000000000000
--- a/drivers/isdn/hardware/eicon/capi20.h
+++ /dev/null
@@ -1,699 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef _INC_CAPI20
-#define _INC_CAPI20
-/* operations on message queues                             */
-/* the common device type for CAPI20 drivers */
-#define FILE_DEVICE_CAPI20 0x8001
-/* DEVICE_CONTROL codes for user and kernel mode applications */
-#define CAPI20_CTL_REGISTER             0x0801
-#define CAPI20_CTL_RELEASE              0x0802
-#define CAPI20_CTL_GET_MANUFACTURER     0x0805
-#define CAPI20_CTL_GET_VERSION          0x0806
-#define CAPI20_CTL_GET_SERIAL           0x0807
-#define CAPI20_CTL_GET_PROFILE          0x0808
-/* INTERNAL_DEVICE_CONTROL codes for kernel mode applicatios only */
-#define CAPI20_CTL_PUT_MESSAGE          0x0803
-#define CAPI20_CTL_GET_MESSAGE          0x0804
-/* the wrapped codes as required by the system */
-#define CAPI_CTL_CODE(f, m)             CTL_CODE(FILE_DEVICE_CAPI20, f, m, FILE_ANY_ACCESS)
-#define IOCTL_CAPI_REGISTER             CAPI_CTL_CODE(CAPI20_CTL_REGISTER, METHOD_BUFFERED)
-#define IOCTL_CAPI_RELEASE              CAPI_CTL_CODE(CAPI20_CTL_RELEASE, METHOD_BUFFERED)
-#define IOCTL_CAPI_GET_MANUFACTURER     CAPI_CTL_CODE(CAPI20_CTL_GET_MANUFACTURER, METHOD_BUFFERED)
-#define IOCTL_CAPI_GET_VERSION          CAPI_CTL_CODE(CAPI20_CTL_GET_VERSION, METHOD_BUFFERED)
-#define IOCTL_CAPI_GET_SERIAL           CAPI_CTL_CODE(CAPI20_CTL_GET_SERIAL, METHOD_BUFFERED)
-#define IOCTL_CAPI_GET_PROFILE          CAPI_CTL_CODE(CAPI20_CTL_GET_PROFILE, METHOD_BUFFERED)
-#define IOCTL_CAPI_PUT_MESSAGE          CAPI_CTL_CODE(CAPI20_CTL_PUT_MESSAGE, METHOD_BUFFERED)
-#define IOCTL_CAPI_GET_MESSAGE          CAPI_CTL_CODE(CAPI20_CTL_GET_MESSAGE, METHOD_BUFFERED)
-struct divas_capi_register_params  {
-	word MessageBufferSize;
-	word maxLogicalConnection;
-	word maxBDataBlocks;
-	word maxBDataLen;
-};
-struct divas_capi_version  {
-	word CapiMajor;
-	word CapiMinor;
-	word ManuMajor;
-	word ManuMinor;
-};
-typedef struct api_profile_s {
-	word          Number;
-	word          Channels;
-	dword         Global_Options;
-	dword         B1_Protocols;
-	dword         B2_Protocols;
-	dword         B3_Protocols;
-} API_PROFILE;
-/* ISDN Common API message types                            */
-#define _ALERT_R                        0x8001
-#define _CONNECT_R                      0x8002
-#define _CONNECT_I                      0x8202
-#define _CONNECT_ACTIVE_I               0x8203
-#define _DISCONNECT_R                   0x8004
-#define _DISCONNECT_I                   0x8204
-#define _LISTEN_R                       0x8005
-#define _INFO_R                         0x8008
-#define _INFO_I                         0x8208
-#define _SELECT_B_REQ                   0x8041
-#define _FACILITY_R                     0x8080
-#define _FACILITY_I                     0x8280
-#define _CONNECT_B3_R                   0x8082
-#define _CONNECT_B3_I                   0x8282
-#define _CONNECT_B3_ACTIVE_I            0x8283
-#define _DISCONNECT_B3_R                0x8084
-#define _DISCONNECT_B3_I                0x8284
-#define _DATA_B3_R                      0x8086
-#define _DATA_B3_I                      0x8286
-#define _RESET_B3_R                     0x8087
-#define _RESET_B3_I                     0x8287
-#define _CONNECT_B3_T90_ACTIVE_I        0x8288
-#define _MANUFACTURER_R                 0x80ff
-#define _MANUFACTURER_I                 0x82ff
-/* OR this to convert a REQUEST to a CONFIRM                */
-#define CONFIRM                 0x0100
-/* OR this to convert a INDICATION to a RESPONSE            */
-#define RESPONSE                0x0100
-/*------------------------------------------------------------------*/
-/* diehl isdn private MANUFACTURER codes                            */
-/*------------------------------------------------------------------*/
-#define _DI_MANU_ID             0x44444944
-#define _DI_ASSIGN_PLCI         0x0001
-#define _DI_ADV_CODEC           0x0002
-#define _DI_DSP_CTRL            0x0003
-#define _DI_SIG_CTRL            0x0004
-#define _DI_RXT_CTRL            0x0005
-#define _DI_IDI_CTRL            0x0006
-#define _DI_CFG_CTRL            0x0007
-#define _DI_REMOVE_CODEC        0x0008
-#define _DI_OPTIONS_REQUEST     0x0009
-#define _DI_SSEXT_CTRL          0x000a
-#define _DI_NEGOTIATE_B3        0x000b
-/*------------------------------------------------------------------*/
-/* parameter structures                                             */
-/*------------------------------------------------------------------*/
-/* ALERT-REQUEST                                            */
-typedef struct {
-	byte structs[0];      /* Additional Info */
-} _ALT_REQP;
-/* ALERT-CONFIRM                                            */
-typedef struct {
-	word Info;
-} _ALT_CONP;
-/* CONNECT-REQUEST                                          */
-typedef struct {
-	word CIP_Value;
-	byte structs[0];      /* Called party number,
-				 Called party subaddress,
-				 Calling party number,
-				 Calling party subaddress,
-				 B_protocol,
-				 BC,
-				 LLC,
-				 HLC,
-				 Additional Info */
-} _CON_REQP;
-/* CONNECT-CONFIRM                                          */
-typedef struct {
-	word Info;
-} _CON_CONP;
-/* CONNECT-INDICATION                                       */
-typedef struct {
-	word CIP_Value;
-	byte structs[0];      /* Called party number,
-				 Called party subaddress,
-				 Calling party number,
-				 Calling party subaddress,
-				 BC,
-				 LLC,
-				 HLC,
-				 Additional Info */
-} _CON_INDP;
-/* CONNECT-RESPONSE                                         */
-typedef struct {
-	word Accept;
-	byte structs[0];      /* B_protocol,
-				 Connected party number,
-				 Connected party subaddress,
-				 LLC */
-} _CON_RESP;
-/* CONNECT-ACTIVE-INDICATION                                */
-typedef struct {
-	byte structs[0];      /* Connected party number,
-				 Connected party subaddress,
-				 LLC */
-} _CON_A_INDP;
-/* CONNECT-ACTIVE-RESPONSE                                  */
-typedef struct {
-	byte structs[0];      /* empty */
-} _CON_A_RESP;
-/* DISCONNECT-REQUEST                                       */
-typedef struct {
-	byte structs[0];      /* Additional Info */
-} _DIS_REQP;
-/* DISCONNECT-CONFIRM                                       */
-typedef struct {
-	word Info;
-} _DIS_CONP;
-/* DISCONNECT-INDICATION                                    */
-typedef struct {
-	word Info;
-} _DIS_INDP;
-/* DISCONNECT-RESPONSE                                      */
-typedef struct {
-	byte structs[0];      /* empty */
-} _DIS_RESP;
-/* LISTEN-REQUEST                                           */
-typedef struct {
-	dword Info_Mask;
-	dword CIP_Mask;
-	byte structs[0];      /* Calling party number,
-				 Calling party subaddress */
-} _LIS_REQP;
-/* LISTEN-CONFIRM                                           */
-typedef struct {
-	word Info;
-} _LIS_CONP;
-/* INFO-REQUEST                                             */
-typedef struct {
-	byte structs[0];      /* Called party number,
-				 Additional Info */
-} _INF_REQP;
-/* INFO-CONFIRM                                             */
-typedef struct {
-	word Info;
-} _INF_CONP;
-/* INFO-INDICATION                                          */
-typedef struct {
-	word Number;
-	byte structs[0];      /* Info element */
-} _INF_INDP;
-/* INFO-RESPONSE                                            */
-typedef struct {
-	byte structs[0];      /* empty */
-} _INF_RESP;
-/* SELECT-B-REQUEST                                         */
-typedef struct {
-	byte structs[0];      /* B-protocol */
-} _SEL_B_REQP;
-/* SELECT-B-CONFIRM                                         */
-typedef struct {
-	word Info;
-} _SEL_B_CONP;
-/* FACILITY-REQUEST */
-typedef struct {
-	word Selector;
-	byte structs[0];      /* Facility parameters */
-} _FAC_REQP;
-/* FACILITY-CONFIRM STRUCT FOR SUPPLEMENT. SERVICES */
-typedef struct {
-	byte  struct_length;
-	word  function;
-	byte  length;
-	word  SupplementaryServiceInfo;
-	dword SupportedServices;
-} _FAC_CON_STRUCTS;
-/* FACILITY-CONFIRM */
-typedef struct {
-	word Info;
-	word Selector;
-	byte structs[0];      /* Facility parameters */
-} _FAC_CONP;
-/* FACILITY-INDICATION */
-typedef struct {
-	word Selector;
-	byte structs[0];      /* Facility parameters */
-} _FAC_INDP;
-/* FACILITY-RESPONSE */
-typedef struct {
-	word Selector;
-	byte structs[0];      /* Facility parameters */
-} _FAC_RESP;
-/* CONNECT-B3-REQUEST                                       */
-typedef struct {
-	byte structs[0];      /* NCPI */
-} _CON_B3_REQP;
-/* CONNECT-B3-CONFIRM                                       */
-typedef struct {
-	word Info;
-} _CON_B3_CONP;
-/* CONNECT-B3-INDICATION                                    */
-typedef struct {
-	byte structs[0];      /* NCPI */
-} _CON_B3_INDP;
-/* CONNECT-B3-RESPONSE                                      */
-typedef struct {
-	word Accept;
-	byte structs[0];      /* NCPI */
-} _CON_B3_RESP;
-/* CONNECT-B3-ACTIVE-INDICATION                             */
-typedef struct {
-	byte structs[0];      /* NCPI */
-} _CON_B3_A_INDP;
-/* CONNECT-B3-ACTIVE-RESPONSE                               */
-typedef struct {
-	byte structs[0];      /* empty */
-} _CON_B3_A_RESP;
-/* DISCONNECT-B3-REQUEST                                    */
-typedef struct {
-	byte structs[0];      /* NCPI */
-} _DIS_B3_REQP;
-/* DISCONNECT-B3-CONFIRM                                    */
-typedef struct {
-	word Info;
-} _DIS_B3_CONP;
-/* DISCONNECT-B3-INDICATION                                 */
-typedef struct {
-	word Info;
-	byte structs[0];      /* NCPI */
-} _DIS_B3_INDP;
-/* DISCONNECT-B3-RESPONSE                                   */
-typedef struct {
-	byte structs[0];      /* empty */
-} _DIS_B3_RESP;
-/* DATA-B3-REQUEST                                          */
-typedef struct {
-	dword         Data;
-	word          Data_Length;
-	word          Number;
-	word          Flags;
-} _DAT_B3_REQP;
-/* DATA-B3-REQUEST 64 BIT Systems                           */
-typedef struct {
-	dword         Data;
-	word          Data_Length;
-	word          Number;
-	word          Flags;
-	void          *pData;
-} _DAT_B3_REQ64P;
-/* DATA-B3-CONFIRM                                          */
-typedef struct {
-	word          Number;
-	word          Info;
-} _DAT_B3_CONP;
-/* DATA-B3-INDICATION                                       */
-typedef struct {
-	dword         Data;
-	word          Data_Length;
-	word          Number;
-	word          Flags;
-} _DAT_B3_INDP;
-/* DATA-B3-INDICATION  64 BIT Systems                       */
-typedef struct {
-	dword         Data;
-	word          Data_Length;
-	word          Number;
-	word          Flags;
-	void          *pData;
-} _DAT_B3_IND64P;
-/* DATA-B3-RESPONSE                                         */
-typedef struct {
-	word          Number;
-} _DAT_B3_RESP;
-/* RESET-B3-REQUEST                                         */
-typedef struct {
-	byte structs[0];      /* NCPI */
-} _RES_B3_REQP;
-/* RESET-B3-CONFIRM                                         */
-typedef struct {
-	word Info;
-} _RES_B3_CONP;
-/* RESET-B3-INDICATION                                      */
-typedef struct {
-	byte structs[0];      /* NCPI */
-} _RES_B3_INDP;
-/* RESET-B3-RESPONSE                                        */
-typedef struct {
-	byte structs[0];      /* empty */
-} _RES_B3_RESP;
-/* CONNECT-B3-T90-ACTIVE-INDICATION                         */
-typedef struct {
-	byte structs[0];      /* NCPI */
-} _CON_B3_T90_A_INDP;
-/* CONNECT-B3-T90-ACTIVE-RESPONSE                           */
-typedef struct {
-	word Reject;
-	byte structs[0];      /* NCPI */
-} _CON_B3_T90_A_RESP;
-/*------------------------------------------------------------------*/
-/* message structure                                                */
-/*------------------------------------------------------------------*/
-typedef struct _API_MSG CAPI_MSG;
-typedef struct _MSG_HEADER CAPI_MSG_HEADER;
-struct _API_MSG {
-	struct _MSG_HEADER {
-		word        length;
-		word        appl_id;
-		word        command;
-		word        number;
-		byte        controller;
-		byte        plci;
-		word        ncci;
-	} header;
-	union {
-		_ALT_REQP           alert_req;
-		_ALT_CONP           alert_con;
-		_CON_REQP           connect_req;
-		_CON_CONP           connect_con;
-		_CON_INDP           connect_ind;
-		_CON_RESP           connect_res;
-		_CON_A_INDP         connect_a_ind;
-		_CON_A_RESP         connect_a_res;
-		_DIS_REQP           disconnect_req;
-		_DIS_CONP           disconnect_con;
-		_DIS_INDP           disconnect_ind;
-		_DIS_RESP           disconnect_res;
-		_LIS_REQP           listen_req;
-		_LIS_CONP           listen_con;
-		_INF_REQP           info_req;
-		_INF_CONP           info_con;
-		_INF_INDP           info_ind;
-		_INF_RESP           info_res;
-		_SEL_B_REQP         select_b_req;
-		_SEL_B_CONP         select_b_con;
-		_FAC_REQP           facility_req;
-		_FAC_CONP           facility_con;
-		_FAC_INDP           facility_ind;
-		_FAC_RESP           facility_res;
-		_CON_B3_REQP        connect_b3_req;
-		_CON_B3_CONP        connect_b3_con;
-		_CON_B3_INDP        connect_b3_ind;
-		_CON_B3_RESP        connect_b3_res;
-		_CON_B3_A_INDP      connect_b3_a_ind;
-		_CON_B3_A_RESP      connect_b3_a_res;
-		_DIS_B3_REQP        disconnect_b3_req;
-		_DIS_B3_CONP        disconnect_b3_con;
-		_DIS_B3_INDP        disconnect_b3_ind;
-		_DIS_B3_RESP        disconnect_b3_res;
-		_DAT_B3_REQP        data_b3_req;
-		_DAT_B3_REQ64P      data_b3_req64;
-		_DAT_B3_CONP        data_b3_con;
-		_DAT_B3_INDP        data_b3_ind;
-		_DAT_B3_IND64P      data_b3_ind64;
-		_DAT_B3_RESP        data_b3_res;
-		_RES_B3_REQP        reset_b3_req;
-		_RES_B3_CONP        reset_b3_con;
-		_RES_B3_INDP        reset_b3_ind;
-		_RES_B3_RESP        reset_b3_res;
-		_CON_B3_T90_A_INDP  connect_b3_t90_a_ind;
-		_CON_B3_T90_A_RESP  connect_b3_t90_a_res;
-		byte                b[200];
-	} info;
-};
-/*------------------------------------------------------------------*/
-/* non-fatal errors                                                 */
-/*------------------------------------------------------------------*/
-#define _NCPI_IGNORED           0x0001
-#define _FLAGS_IGNORED          0x0002
-#define _ALERT_IGNORED          0x0003
-/*------------------------------------------------------------------*/
-/* API function error codes                                         */
-/*------------------------------------------------------------------*/
-#define GOOD                            0x0000
-#define _TOO_MANY_APPLICATIONS          0x1001
-#define _BLOCK_TOO_SMALL                0x1002
-#define _BUFFER_TOO_BIG                 0x1003
-#define _MSG_BUFFER_TOO_SMALL           0x1004
-#define _TOO_MANY_CONNECTIONS           0x1005
-#define _REG_CAPI_BUSY                  0x1007
-#define _REG_RESOURCE_ERROR             0x1008
-#define _REG_CAPI_NOT_INSTALLED         0x1009
-#define _WRONG_APPL_ID                  0x1101
-#define _BAD_MSG                        0x1102
-#define _QUEUE_FULL                     0x1103
-#define _GET_NO_MSG                     0x1104
-#define _MSG_LOST                       0x1105
-#define _WRONG_NOTIFY                   0x1106
-#define _CAPI_BUSY                      0x1107
-#define _RESOURCE_ERROR                 0x1108
-#define _CAPI_NOT_INSTALLED             0x1109
-#define _NO_EXTERNAL_EQUIPMENT          0x110a
-#define _ONLY_EXTERNAL_EQUIPMENT        0x110b
-/*------------------------------------------------------------------*/
-/* addressing/coding error codes                                    */
-/*------------------------------------------------------------------*/
-#define _WRONG_STATE                    0x2001
-#define _WRONG_IDENTIFIER               0x2002
-#define _OUT_OF_PLCI                    0x2003
-#define _OUT_OF_NCCI                    0x2004
-#define _OUT_OF_LISTEN                  0x2005
-#define _OUT_OF_FAX                     0x2006
-#define _WRONG_MESSAGE_FORMAT           0x2007
-#define _OUT_OF_INTERCONNECT_RESOURCES  0x2008
-/*------------------------------------------------------------------*/
-/* configuration error codes                                        */
-/*------------------------------------------------------------------*/
-#define _B1_NOT_SUPPORTED                    0x3001
-#define _B2_NOT_SUPPORTED                    0x3002
-#define _B3_NOT_SUPPORTED                    0x3003
-#define _B1_PARM_NOT_SUPPORTED               0x3004
-#define _B2_PARM_NOT_SUPPORTED               0x3005
-#define _B3_PARM_NOT_SUPPORTED               0x3006
-#define _B_STACK_NOT_SUPPORTED               0x3007
-#define _NCPI_NOT_SUPPORTED                  0x3008
-#define _CIP_NOT_SUPPORTED                   0x3009
-#define _FLAGS_NOT_SUPPORTED                 0x300a
-#define _FACILITY_NOT_SUPPORTED              0x300b
-#define _DATA_LEN_NOT_SUPPORTED              0x300c
-#define _RESET_NOT_SUPPORTED                 0x300d
-#define _SUPPLEMENTARY_SERVICE_NOT_SUPPORTED 0x300e
-#define _REQUEST_NOT_ALLOWED_IN_THIS_STATE   0x3010
-#define _FACILITY_SPECIFIC_FUNCTION_NOT_SUPP 0x3011
-/*------------------------------------------------------------------*/
-/* reason codes                                                     */
-/*------------------------------------------------------------------*/
-#define _L1_ERROR                       0x3301
-#define _L2_ERROR                       0x3302
-#define _L3_ERROR                       0x3303
-#define _OTHER_APPL_CONNECTED           0x3304
-#define _CAPI_GUARD_ERROR               0x3305
-#define _L3_CAUSE                       0x3400
-/*------------------------------------------------------------------*/
-/* b3 reason codes                                                  */
-/*------------------------------------------------------------------*/
-#define _B_CHANNEL_LOST                 0x3301
-#define _B2_ERROR                       0x3302
-#define _B3_ERROR                       0x3303
-/*------------------------------------------------------------------*/
-/* fax error codes                                                  */
-/*------------------------------------------------------------------*/
-#define _FAX_NO_CONNECTION              0x3311
-#define _FAX_TRAINING_ERROR             0x3312
-#define _FAX_REMOTE_REJECT              0x3313
-#define _FAX_REMOTE_ABORT               0x3314
-#define _FAX_PROTOCOL_ERROR             0x3315
-#define _FAX_TX_UNDERRUN                0x3316
-#define _FAX_RX_OVERFLOW                0x3317
-#define _FAX_LOCAL_ABORT                0x3318
-#define _FAX_PARAMETER_ERROR            0x3319
-/*------------------------------------------------------------------*/
-/* line interconnect error codes                                    */
-/*------------------------------------------------------------------*/
-#define _LI_USER_INITIATED               0x0000
-#define _LI_LINE_NO_LONGER_AVAILABLE     0x3805
-#define _LI_INTERCONNECT_NOT_ESTABLISHED 0x3806
-#define _LI_LINES_NOT_COMPATIBLE         0x3807
-#define _LI2_USER_INITIATED              0x0000
-#define _LI2_PLCI_HAS_NO_BCHANNEL        0x3800
-#define _LI2_LINES_NOT_COMPATIBLE        0x3801
-#define _LI2_NOT_IN_SAME_INTERCONNECTION 0x3802
-/*------------------------------------------------------------------*/
-/* global options                                                   */
-/*------------------------------------------------------------------*/
-#define GL_INTERNAL_CONTROLLER_SUPPORTED     0x00000001L
-#define GL_EXTERNAL_EQUIPMENT_SUPPORTED      0x00000002L
-#define GL_HANDSET_SUPPORTED                 0x00000004L
-#define GL_DTMF_SUPPORTED                    0x00000008L
-#define GL_SUPPLEMENTARY_SERVICES_SUPPORTED  0x00000010L
-#define GL_CHANNEL_ALLOCATION_SUPPORTED      0x00000020L
-#define GL_BCHANNEL_OPERATION_SUPPORTED      0x00000040L
-#define GL_LINE_INTERCONNECT_SUPPORTED       0x00000080L
-#define GL_ECHO_CANCELLER_SUPPORTED          0x00000100L
-/*------------------------------------------------------------------*/
-/* protocol selection                                               */
-/*------------------------------------------------------------------*/
-#define B1_HDLC                 0
-#define B1_TRANSPARENT          1
-#define B1_V110_ASYNC           2
-#define B1_V110_SYNC            3
-#define B1_T30                  4
-#define B1_HDLC_INVERTED        5
-#define B1_TRANSPARENT_R        6
-#define B1_MODEM_ALL_NEGOTIATE  7
-#define B1_MODEM_ASYNC          8
-#define B1_MODEM_SYNC_HDLC      9
-#define B2_X75                  0
-#define B2_TRANSPARENT          1
-#define B2_SDLC                 2
-#define B2_LAPD                 3
-#define B2_T30                  4
-#define B2_PPP                  5
-#define B2_TRANSPARENT_NO_CRC   6
-#define B2_MODEM_EC_COMPRESSION 7
-#define B2_X75_V42BIS           8
-#define B2_V120_ASYNC           9
-#define B2_V120_ASYNC_V42BIS    10
-#define B2_V120_BIT_TRANSPARENT 11
-#define B2_LAPD_FREE_SAPI_SEL   12
-#define B3_TRANSPARENT          0
-#define B3_T90NL                1
-#define B3_ISO8208              2
-#define B3_X25_DCE              3
-#define B3_T30                  4
-#define B3_T30_WITH_EXTENSIONS  5
-#define B3_RESERVED             6
-#define B3_MODEM                7
-/*------------------------------------------------------------------*/
-/*  facility definitions                                            */
-/*------------------------------------------------------------------*/
-#define SELECTOR_HANDSET            0
-#define SELECTOR_DTMF               1
-#define SELECTOR_V42BIS             2
-#define SELECTOR_SU_SERV            3
-#define SELECTOR_POWER_MANAGEMENT   4
-#define SELECTOR_LINE_INTERCONNECT  5
-#define SELECTOR_ECHO_CANCELLER     6
-/*------------------------------------------------------------------*/
-/*  supplementary services definitions                              */
-/*------------------------------------------------------------------*/
-#define S_GET_SUPPORTED_SERVICES  0x0000
-#define S_LISTEN                  0x0001
-#define S_HOLD                    0x0002
-#define S_RETRIEVE                0x0003
-#define S_SUSPEND                 0x0004
-#define S_RESUME                  0x0005
-#define S_ECT                     0x0006
-#define S_3PTY_BEGIN              0x0007
-#define S_3PTY_END                0x0008
-#define S_CALL_DEFLECTION         0x000d
-#define S_CALL_FORWARDING_START   0x0009
-#define S_CALL_FORWARDING_STOP    0x000a
-#define S_INTERROGATE_DIVERSION   0x000b /* or interrogate parameters */
-#define S_INTERROGATE_NUMBERS     0x000c
-#define S_CCBS_REQUEST            0x000f
-#define S_CCBS_DEACTIVATE         0x0010
-#define S_CCBS_INTERROGATE        0x0011
-#define S_CCBS_CALL               0x0012
-#define S_MWI_ACTIVATE            0x0013
-#define S_MWI_DEACTIVATE          0x0014
-#define S_CONF_BEGIN           0x0017
-#define S_CONF_ADD                0x0018
-#define S_CONF_SPLIT           0x0019
-#define S_CONF_DROP               0x001a
-#define S_CONF_ISOLATE           0x001b
-#define S_CONF_REATTACH           0x001c
-#define S_CCBS_ERASECALLLINKAGEID 0x800d
-#define S_CCBS_STOP_ALERTING      0x8012
-#define S_CCBS_INFO_RETAIN        0x8013
-#define S_MWI_INDICATE            0x8014
-#define S_CONF_PARTYDISC          0x8016
-#define S_CONF_NOTIFICATION       0x8017
-/* Service Masks */
-#define MASK_HOLD_RETRIEVE        0x00000001
-#define MASK_TERMINAL_PORTABILITY 0x00000002
-#define MASK_ECT                  0x00000004
-#define MASK_3PTY                 0x00000008
-#define MASK_CALL_FORWARDING      0x00000010
-#define MASK_CALL_DEFLECTION      0x00000020
-#define MASK_MWI                  0x00000100
-#define MASK_CCNR                 0x00000200
-#define MASK_CONF                 0x00000400
-/*------------------------------------------------------------------*/
-/*  dtmf definitions                                                */
-/*------------------------------------------------------------------*/
-#define DTMF_LISTEN_START     1
-#define DTMF_LISTEN_STOP      2
-#define DTMF_DIGITS_SEND      3
-#define DTMF_SUCCESS          0
-#define DTMF_INCORRECT_DIGIT  1
-#define DTMF_UNKNOWN_REQUEST  2
-/*------------------------------------------------------------------*/
-/*  line interconnect definitions                                   */
-/*------------------------------------------------------------------*/
-#define LI_GET_SUPPORTED_SERVICES       0
-#define LI_REQ_CONNECT                  1
-#define LI_REQ_DISCONNECT               2
-#define LI_IND_CONNECT_ACTIVE           1
-#define LI_IND_DISCONNECT               2
-#define LI_FLAG_CONFERENCE_A_B          ((dword) 0x00000001L)
-#define LI_FLAG_CONFERENCE_B_A          ((dword) 0x00000002L)
-#define LI_FLAG_MONITOR_A               ((dword) 0x00000004L)
-#define LI_FLAG_MONITOR_B               ((dword) 0x00000008L)
-#define LI_FLAG_ANNOUNCEMENT_A          ((dword) 0x00000010L)
-#define LI_FLAG_ANNOUNCEMENT_B          ((dword) 0x00000020L)
-#define LI_FLAG_MIX_A                   ((dword) 0x00000040L)
-#define LI_FLAG_MIX_B                   ((dword) 0x00000080L)
-#define LI_CONFERENCING_SUPPORTED       ((dword) 0x00000001L)
-#define LI_MONITORING_SUPPORTED         ((dword) 0x00000002L)
-#define LI_ANNOUNCEMENTS_SUPPORTED      ((dword) 0x00000004L)
-#define LI_MIXING_SUPPORTED             ((dword) 0x00000008L)
-#define LI_CROSS_CONTROLLER_SUPPORTED   ((dword) 0x00000010L)
-#define LI2_GET_SUPPORTED_SERVICES      0
-#define LI2_REQ_CONNECT                 1
-#define LI2_REQ_DISCONNECT              2
-#define LI2_IND_CONNECT_ACTIVE          1
-#define LI2_IND_DISCONNECT              2
-#define LI2_FLAG_INTERCONNECT_A_B       ((dword) 0x00000001L)
-#define LI2_FLAG_INTERCONNECT_B_A       ((dword) 0x00000002L)
-#define LI2_FLAG_MONITOR_B              ((dword) 0x00000004L)
-#define LI2_FLAG_MIX_B                  ((dword) 0x00000008L)
-#define LI2_FLAG_MONITOR_X              ((dword) 0x00000010L)
-#define LI2_FLAG_MIX_X                  ((dword) 0x00000020L)
-#define LI2_FLAG_LOOP_B                 ((dword) 0x00000040L)
-#define LI2_FLAG_LOOP_PC                ((dword) 0x00000080L)
-#define LI2_FLAG_LOOP_X                 ((dword) 0x00000100L)
-#define LI2_CROSS_CONTROLLER_SUPPORTED  ((dword) 0x00000001L)
-#define LI2_ASYMMETRIC_SUPPORTED        ((dword) 0x00000002L)
-#define LI2_MONITORING_SUPPORTED        ((dword) 0x00000004L)
-#define LI2_MIXING_SUPPORTED            ((dword) 0x00000008L)
-#define LI2_REMOTE_MONITORING_SUPPORTED ((dword) 0x00000010L)
-#define LI2_REMOTE_MIXING_SUPPORTED     ((dword) 0x00000020L)
-#define LI2_B_LOOPING_SUPPORTED         ((dword) 0x00000040L)
-#define LI2_PC_LOOPING_SUPPORTED        ((dword) 0x00000080L)
-#define LI2_X_LOOPING_SUPPORTED         ((dword) 0x00000100L)
-/*------------------------------------------------------------------*/
-/* echo canceller definitions                                       */
-/*------------------------------------------------------------------*/
-#define EC_GET_SUPPORTED_SERVICES            0
-#define EC_ENABLE_OPERATION                  1
-#define EC_DISABLE_OPERATION                 2
-#define EC_ENABLE_NON_LINEAR_PROCESSING      0x0001
-#define EC_DO_NOT_REQUIRE_REVERSALS          0x0002
-#define EC_DETECT_DISABLE_TONE               0x0004
-#define EC_ENABLE_ADAPTIVE_PREDELAY          0x0008
-#define EC_NON_LINEAR_PROCESSING_SUPPORTED   0x0001
-#define EC_BYPASS_ON_ANY_2100HZ_SUPPORTED    0x0002
-#define EC_BYPASS_ON_REV_2100HZ_SUPPORTED    0x0004
-#define EC_ADAPTIVE_PREDELAY_SUPPORTED       0x0008
-#define EC_BYPASS_INDICATION                 1
-#define EC_BYPASS_DUE_TO_CONTINUOUS_2100HZ   1
-#define EC_BYPASS_DUE_TO_REVERSED_2100HZ     2
-#define EC_BYPASS_RELEASED                   3
-/*------------------------------------------------------------------*/
-/* function prototypes                                              */
-/*------------------------------------------------------------------*/
-/*------------------------------------------------------------------*/
-#endif /* _INC_CAPI20 */
diff --git a/drivers/isdn/hardware/eicon/capidtmf.c b/drivers/isdn/hardware/eicon/capidtmf.c
deleted file mode 100644
index e3f778415199..000000000000
--- a/drivers/isdn/hardware/eicon/capidtmf.c
+++ /dev/null
@@ -1,685 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-
-#include "platform.h"
-
-
-
-
-
-
-
-
-
-#include "capidtmf.h"
-
-/* #define TRACE_ */
-
-#define FILE_ "CAPIDTMF.C"
-
-/*---------------------------------------------------------------------------*/
-
-
-#define trace(a)
-
-
-
-/*---------------------------------------------------------------------------*/
-
-static short capidtmf_expand_table_alaw[0x0100] =
-{
-	-5504,   5504,   -344,    344, -22016,  22016,  -1376,   1376,
-	-2752,   2752,    -88,     88, -11008,  11008,   -688,    688,
-	-7552,   7552,   -472,    472, -30208,  30208,  -1888,   1888,
-	-3776,   3776,   -216,    216, -15104,  15104,   -944,    944,
-	-4480,   4480,   -280,    280, -17920,  17920,  -1120,   1120,
-	-2240,   2240,    -24,     24,  -8960,   8960,   -560,    560,
-	-6528,   6528,   -408,    408, -26112,  26112,  -1632,   1632,
-	-3264,   3264,   -152,    152, -13056,  13056,   -816,    816,
-	-6016,   6016,   -376,    376, -24064,  24064,  -1504,   1504,
-	-3008,   3008,   -120,    120, -12032,  12032,   -752,    752,
-	-8064,   8064,   -504,    504, -32256,  32256,  -2016,   2016,
-	-4032,   4032,   -248,    248, -16128,  16128,  -1008,   1008,
-	-4992,   4992,   -312,    312, -19968,  19968,  -1248,   1248,
-	-2496,   2496,    -56,     56,  -9984,   9984,   -624,    624,
-	-7040,   7040,   -440,    440, -28160,  28160,  -1760,   1760,
-	-3520,   3520,   -184,    184, -14080,  14080,   -880,    880,
-	-5248,   5248,   -328,    328, -20992,  20992,  -1312,   1312,
-	-2624,   2624,    -72,     72, -10496,  10496,   -656,    656,
-	-7296,   7296,   -456,    456, -29184,  29184,  -1824,   1824,
-	-3648,   3648,   -200,    200, -14592,  14592,   -912,    912,
-	-4224,   4224,   -264,    264, -16896,  16896,  -1056,   1056,
-	-2112,   2112,     -8,      8,  -8448,   8448,   -528,    528,
-	-6272,   6272,   -392,    392, -25088,  25088,  -1568,   1568,
-	-3136,   3136,   -136,    136, -12544,  12544,   -784,    784,
-	-5760,   5760,   -360,    360, -23040,  23040,  -1440,   1440,
-	-2880,   2880,   -104,    104, -11520,  11520,   -720,    720,
-	-7808,   7808,   -488,    488, -31232,  31232,  -1952,   1952,
-	-3904,   3904,   -232,    232, -15616,  15616,   -976,    976,
-	-4736,   4736,   -296,    296, -18944,  18944,  -1184,   1184,
-	-2368,   2368,    -40,     40,  -9472,   9472,   -592,    592,
-	-6784,   6784,   -424,    424, -27136,  27136,  -1696,   1696,
-	-3392,   3392,   -168,    168, -13568,  13568,   -848,    848
-};
-
-static short capidtmf_expand_table_ulaw[0x0100] =
-{
-	-32124,  32124,  -1884,   1884,  -7932,   7932,   -372,    372,
-	-15996,  15996,   -876,    876,  -3900,   3900,   -120,    120,
-	-23932,  23932,  -1372,   1372,  -5884,   5884,   -244,    244,
-	-11900,  11900,   -620,    620,  -2876,   2876,    -56,     56,
-	-28028,  28028,  -1628,   1628,  -6908,   6908,   -308,    308,
-	-13948,  13948,   -748,    748,  -3388,   3388,    -88,     88,
-	-19836,  19836,  -1116,   1116,  -4860,   4860,   -180,    180,
-	-9852,   9852,   -492,    492,  -2364,   2364,    -24,     24,
-	-30076,  30076,  -1756,   1756,  -7420,   7420,   -340,    340,
-	-14972,  14972,   -812,    812,  -3644,   3644,   -104,    104,
-	-21884,  21884,  -1244,   1244,  -5372,   5372,   -212,    212,
-	-10876,  10876,   -556,    556,  -2620,   2620,    -40,     40,
-	-25980,  25980,  -1500,   1500,  -6396,   6396,   -276,    276,
-	-12924,  12924,   -684,    684,  -3132,   3132,    -72,     72,
-	-17788,  17788,   -988,    988,  -4348,   4348,   -148,    148,
-	-8828,   8828,   -428,    428,  -2108,   2108,     -8,      8,
-	-31100,  31100,  -1820,   1820,  -7676,   7676,   -356,    356,
-	-15484,  15484,   -844,    844,  -3772,   3772,   -112,    112,
-	-22908,  22908,  -1308,   1308,  -5628,   5628,   -228,    228,
-	-11388,  11388,   -588,    588,  -2748,   2748,    -48,     48,
-	-27004,  27004,  -1564,   1564,  -6652,   6652,   -292,    292,
-	-13436,  13436,   -716,    716,  -3260,   3260,    -80,     80,
-	-18812,  18812,  -1052,   1052,  -4604,   4604,   -164,    164,
-	-9340,   9340,   -460,    460,  -2236,   2236,    -16,     16,
-	-29052,  29052,  -1692,   1692,  -7164,   7164,   -324,    324,
-	-14460,  14460,   -780,    780,  -3516,   3516,    -96,     96,
-	-20860,  20860,  -1180,   1180,  -5116,   5116,   -196,    196,
-	-10364,  10364,   -524,    524,  -2492,   2492,    -32,     32,
-	-24956,  24956,  -1436,   1436,  -6140,   6140,   -260,    260,
-	-12412,  12412,   -652,    652,  -3004,   3004,    -64,     64,
-	-16764,  16764,   -924,    924,  -4092,   4092,   -132,    132,
-	-8316,   8316,   -396,    396,  -1980,   1980,      0,      0
-};
-
-
-/*---------------------------------------------------------------------------*/
-
-static short capidtmf_recv_window_function[CAPIDTMF_RECV_ACCUMULATE_CYCLES] =
-{
-	-500L,   -999L,  -1499L,  -1998L,  -2496L,  -2994L,  -3491L,  -3988L,
-	-4483L,  -4978L,  -5471L,  -5963L,  -6454L,  -6943L,  -7431L,  -7917L,
-	-8401L,  -8883L,  -9363L,  -9840L, -10316L, -10789L, -11259L, -11727L,
-	-12193L, -12655L, -13115L, -13571L, -14024L, -14474L, -14921L, -15364L,
-	-15804L, -16240L, -16672L, -17100L, -17524L, -17944L, -18360L, -18772L,
-	-19180L, -19583L, -19981L, -20375L, -20764L, -21148L, -21527L, -21901L,
-	-22270L, -22634L, -22993L, -23346L, -23694L, -24037L, -24374L, -24705L,
-	-25030L, -25350L, -25664L, -25971L, -26273L, -26568L, -26858L, -27141L,
-	-27418L, -27688L, -27952L, -28210L, -28461L, -28705L, -28943L, -29174L,
-	-29398L, -29615L, -29826L, -30029L, -30226L, -30415L, -30598L, -30773L,
-	-30941L, -31102L, -31256L, -31402L, -31541L, -31673L, -31797L, -31914L,
-	-32024L, -32126L, -32221L, -32308L, -32388L, -32460L, -32524L, -32581L,
-	-32631L, -32673L, -32707L, -32734L, -32753L, -32764L, -32768L, -32764L,
-	-32753L, -32734L, -32707L, -32673L, -32631L, -32581L, -32524L, -32460L,
-	-32388L, -32308L, -32221L, -32126L, -32024L, -31914L, -31797L, -31673L,
-	-31541L, -31402L, -31256L, -31102L, -30941L, -30773L, -30598L, -30415L,
-	-30226L, -30029L, -29826L, -29615L, -29398L, -29174L, -28943L, -28705L,
-	-28461L, -28210L, -27952L, -27688L, -27418L, -27141L, -26858L, -26568L,
-	-26273L, -25971L, -25664L, -25350L, -25030L, -24705L, -24374L, -24037L,
-	-23694L, -23346L, -22993L, -22634L, -22270L, -21901L, -21527L, -21148L,
-	-20764L, -20375L, -19981L, -19583L, -19180L, -18772L, -18360L, -17944L,
-	-17524L, -17100L, -16672L, -16240L, -15804L, -15364L, -14921L, -14474L,
-	-14024L, -13571L, -13115L, -12655L, -12193L, -11727L, -11259L, -10789L,
-	-10316L,  -9840L,  -9363L,  -8883L,  -8401L,  -7917L,  -7431L,  -6943L,
-	-6454L,  -5963L,  -5471L,  -4978L,  -4483L,  -3988L,  -3491L,  -2994L,
-	-2496L,  -1998L,  -1499L,   -999L,   -500L,
-};
-
-static byte capidtmf_leading_zeroes_table[0x100] =
-{
-	8, 7, 6, 6, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, 4, 4,
-	3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
-	2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
-	2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
-	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
-	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
-	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
-	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
-};
-
-#define capidtmf_byte_leading_zeroes(b)  (capidtmf_leading_zeroes_table[(BYTE)(b)])
-#define capidtmf_word_leading_zeroes(w)  (((w) & 0xff00) ? capidtmf_leading_zeroes_table[(w) >> 8] : 8 + capidtmf_leading_zeroes_table[(w)])
-#define capidtmf_dword_leading_zeroes(d)  (((d) & 0xffff0000L) ?    (((d) & 0xff000000L) ? capidtmf_leading_zeroes_table[(d) >> 24] : 8 + capidtmf_leading_zeroes_table[(d) >> 16]) :    (((d) & 0xff00) ? 16 + capidtmf_leading_zeroes_table[(d) >> 8] : 24 + capidtmf_leading_zeroes_table[(d)]))
-
-
-/*---------------------------------------------------------------------------*/
-
-
-static void capidtmf_goertzel_loop(long *buffer, long *coeffs, short *sample, long count)
-{
-	int i, j;
-	long c, d, q0, q1, q2;
-
-	for (i = 0; i < CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT - 1; i++)
-	{
-		q1 = buffer[i];
-		q2 = buffer[i + CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT];
-		d = coeffs[i] >> 1;
-		c = d << 1;
-		if (c >= 0)
-		{
-			for (j = 0; j < count; j++)
-			{
-				q0 = sample[j] - q2 + (c * (q1 >> 16)) + (((dword)(((dword) d) * ((dword)(q1 & 0xffff)))) >> 15);
-				q2 = q1;
-				q1 = q0;
-			}
-		}
-		else
-		{
-			c = -c;
-			d = -d;
-			for (j = 0; j < count; j++)
-			{
-				q0 = sample[j] - q2 - ((c * (q1 >> 16)) + (((dword)(((dword) d) * ((dword)(q1 & 0xffff)))) >> 15));
-				q2 = q1;
-				q1 = q0;
-			}
-		}
-		buffer[i] = q1;
-		buffer[i + CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT] = q2;
-	}
-	q1 = buffer[i];
-	q2 = buffer[i + CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT];
-	c = (coeffs[i] >> 1) << 1;
-	if (c >= 0)
-	{
-		for (j = 0; j < count; j++)
-		{
-			q0 = sample[j] - q2 + (c * (q1 >> 16)) + (((dword)(((dword)(c >> 1)) * ((dword)(q1 & 0xffff)))) >> 15);
-			q2 = q1;
-			q1 = q0;
-			c -= CAPIDTMF_RECV_FUNDAMENTAL_DECREMENT;
-		}
-	}
-	else
-	{
-		c = -c;
-		for (j = 0; j < count; j++)
-		{
-			q0 = sample[j] - q2 - ((c * (q1 >> 16)) + (((dword)(((dword)(c >> 1)) * ((dword)(q1 & 0xffff)))) >> 15));
-			q2 = q1;
-			q1 = q0;
-			c += CAPIDTMF_RECV_FUNDAMENTAL_DECREMENT;
-		}
-	}
-	coeffs[i] = c;
-	buffer[i] = q1;
-	buffer[i + CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT] = q2;
-}
-
-
-static void capidtmf_goertzel_result(long *buffer, long *coeffs)
-{
-	int i;
-	long d, e, q1, q2, lo, mid, hi;
-	dword k;
-
-	for (i = 0; i < CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT; i++)
-	{
-		q1 = buffer[i];
-		q2 = buffer[i + CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT];
-		d = coeffs[i] >> 1;
-		if (d >= 0)
-			d = ((d << 1) * (-q1 >> 16)) + (((dword)(((dword) d) * ((dword)(-q1 & 0xffff)))) >> 15);
-		else
-			d = ((-d << 1) * (-q1 >> 16)) + (((dword)(((dword) -d) * ((dword)(-q1 & 0xffff)))) >> 15);
-		e = (q2 >= 0) ? q2 : -q2;
-		if (d >= 0)
-		{
-			k = ((dword)(d & 0xffff)) * ((dword)(e & 0xffff));
-			lo = k & 0xffff;
-			mid = k >> 16;
-			k = ((dword)(d >> 16)) * ((dword)(e & 0xffff));
-			mid += k & 0xffff;
-			hi = k >> 16;
-			k = ((dword)(d & 0xffff)) * ((dword)(e >> 16));
-			mid += k & 0xffff;
-			hi += k >> 16;
-			hi += ((dword)(d >> 16)) * ((dword)(e >> 16));
-		}
-		else
-		{
-			d = -d;
-			k = ((dword)(d & 0xffff)) * ((dword)(e & 0xffff));
-			lo = -((long)(k & 0xffff));
-			mid = -((long)(k >> 16));
-			k = ((dword)(d >> 16)) * ((dword)(e & 0xffff));
-			mid -= k & 0xffff;
-			hi = -((long)(k >> 16));
-			k = ((dword)(d & 0xffff)) * ((dword)(e >> 16));
-			mid -= k & 0xffff;
-			hi -= k >> 16;
-			hi -= ((dword)(d >> 16)) * ((dword)(e >> 16));
-		}
-		if (q2 < 0)
-		{
-			lo = -lo;
-			mid = -mid;
-			hi = -hi;
-		}
-		d = (q1 >= 0) ? q1 : -q1;
-		k = ((dword)(d & 0xffff)) * ((dword)(d & 0xffff));
-		lo += k & 0xffff;
-		mid += k >> 16;
-		k = ((dword)(d >> 16)) * ((dword)(d & 0xffff));
-		mid += (k & 0xffff) << 1;
-		hi += (k >> 16) << 1;
-		hi += ((dword)(d >> 16)) * ((dword)(d >> 16));
-		d = (q2 >= 0) ? q2 : -q2;
-		k = ((dword)(d & 0xffff)) * ((dword)(d & 0xffff));
-		lo += k & 0xffff;
-		mid += k >> 16;
-		k = ((dword)(d >> 16)) * ((dword)(d & 0xffff));
-		mid += (k & 0xffff) << 1;
-		hi += (k >> 16) << 1;
-		hi += ((dword)(d >> 16)) * ((dword)(d >> 16));
-		mid += lo >> 16;
-		hi += mid >> 16;
-		buffer[i] = (lo & 0xffff) | (mid << 16);
-		buffer[i + CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT] = hi;
-	}
-}
-
-
-/*---------------------------------------------------------------------------*/
-
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_697     0
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_770     1
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_852     2
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_941     3
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_1209    4
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_1336    5
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_1477    6
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_1633    7
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_635     8
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_1010    9
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_1140    10
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_1272    11
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_1405    12
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_1555    13
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_1715    14
-#define CAPIDTMF_RECV_GUARD_SNR_INDEX_1875    15
-
-#define CAPIDTMF_RECV_GUARD_SNR_DONTCARE      0xc000
-#define CAPIDTMF_RECV_NO_DIGIT                0xff
-#define CAPIDTMF_RECV_TIME_GRANULARITY        (CAPIDTMF_RECV_ACCUMULATE_CYCLES + 1)
-
-#define CAPIDTMF_RECV_INDICATION_DIGIT        0x0001
-
-static long capidtmf_recv_goertzel_coef_table[CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT] =
-{
-	0xda97L * 2,  /* 697 Hz (Low group 697 Hz) */
-	0xd299L * 2,  /* 770 Hz (Low group 770 Hz) */
-	0xc8cbL * 2,  /* 852 Hz (Low group 852 Hz) */
-	0xbd36L * 2,  /* 941 Hz (Low group 941 Hz) */
-	0x9501L * 2,  /* 1209 Hz (High group 1209 Hz) */
-	0x7f89L * 2,  /* 1336 Hz (High group 1336 Hz) */
-	0x6639L * 2,  /* 1477 Hz (High group 1477 Hz) */
-	0x48c6L * 2,  /* 1633 Hz (High group 1633 Hz) */
-	0xe14cL * 2,  /* 630 Hz (Lower guard of low group 631 Hz) */
-	0xb2e0L * 2,  /* 1015 Hz (Upper guard of low group 1039 Hz) */
-	0xa1a0L * 2,  /* 1130 Hz (Lower guard of high group 1140 Hz) */
-	0x8a87L * 2,  /* 1272 Hz (Guard between 1209 Hz and 1336 Hz: 1271 Hz) */
-	0x7353L * 2,  /* 1405 Hz (2nd harmonics of 697 Hz and guard between 1336 Hz and 1477 Hz: 1405 Hz) */
-	0x583bL * 2,  /* 1552 Hz (2nd harmonics of 770 Hz and guard between 1477 Hz and 1633 Hz: 1553 Hz) */
-	0x37d8L * 2,  /* 1720 Hz (2nd harmonics of 852 Hz and upper guard of high group: 1715 Hz) */
-	0x0000L * 2   /* 100-630 Hz (fundamentals) */
-};
-
-
-static word capidtmf_recv_guard_snr_low_table[CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT] =
-{
-	14,                                    /* Low group peak versus 697 Hz */
-	14,                                    /* Low group peak versus 770 Hz */
-	16,                                    /* Low group peak versus 852 Hz */
-	16,                                    /* Low group peak versus 941 Hz */
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* Low group peak versus 1209 Hz */
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* Low group peak versus 1336 Hz */
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* Low group peak versus 1477 Hz */
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* Low group peak versus 1633 Hz */
-	14,                                    /* Low group peak versus 635 Hz */
-	16,                                    /* Low group peak versus 1010 Hz */
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* Low group peak versus 1140 Hz */
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* Low group peak versus 1272 Hz */
-	DSPDTMF_RX_HARMONICS_SEL_DEFAULT - 8,  /* Low group peak versus 1405 Hz */
-	DSPDTMF_RX_HARMONICS_SEL_DEFAULT - 4,  /* Low group peak versus 1555 Hz */
-	DSPDTMF_RX_HARMONICS_SEL_DEFAULT - 4,  /* Low group peak versus 1715 Hz */
-	12                                     /* Low group peak versus 100-630 Hz */
-};
-
-
-static word capidtmf_recv_guard_snr_high_table[CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT] =
-{
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* High group peak versus 697 Hz */
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* High group peak versus 770 Hz */
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* High group peak versus 852 Hz */
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* High group peak versus 941 Hz */
-	20,                                    /* High group peak versus 1209 Hz */
-	20,                                    /* High group peak versus 1336 Hz */
-	20,                                    /* High group peak versus 1477 Hz */
-	20,                                    /* High group peak versus 1633 Hz */
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* High group peak versus 635 Hz */
-	CAPIDTMF_RECV_GUARD_SNR_DONTCARE,      /* High group peak versus 1010 Hz */
-	16,                                    /* High group peak versus 1140 Hz */
-	4,                                     /* High group peak versus 1272 Hz */
-	6,                                     /* High group peak versus 1405 Hz */
-	8,                                     /* High group peak versus 1555 Hz */
-	16,                                    /* High group peak versus 1715 Hz */
-	12                                     /* High group peak versus 100-630 Hz */
-};
-
-
-/*---------------------------------------------------------------------------*/
-
-static void capidtmf_recv_init(t_capidtmf_state *p_state)
-{
-	p_state->recv.min_gap_duration = 1;
-	p_state->recv.min_digit_duration = 1;
-
-	p_state->recv.cycle_counter = 0;
-	p_state->recv.current_digit_on_time = 0;
-	p_state->recv.current_digit_off_time = 0;
-	p_state->recv.current_digit_value = CAPIDTMF_RECV_NO_DIGIT;
-
-	p_state->recv.digit_write_pos = 0;
-	p_state->recv.digit_read_pos = 0;
-	p_state->recv.indication_state = 0;
-	p_state->recv.indication_state_ack = 0;
-	p_state->recv.state = CAPIDTMF_RECV_STATE_IDLE;
-}
-
-
-void capidtmf_recv_enable(t_capidtmf_state *p_state, word min_digit_duration, word min_gap_duration)
-{
-	p_state->recv.indication_state_ack &= CAPIDTMF_RECV_INDICATION_DIGIT;
-	p_state->recv.min_digit_duration = (word)(((((dword) min_digit_duration) * 8) +
-						   ((dword)(CAPIDTMF_RECV_TIME_GRANULARITY / 2))) / ((dword) CAPIDTMF_RECV_TIME_GRANULARITY));
-	if (p_state->recv.min_digit_duration <= 1)
-		p_state->recv.min_digit_duration = 1;
-	else
-		(p_state->recv.min_digit_duration)--;
-	p_state->recv.min_gap_duration =
-		(word)((((dword) min_gap_duration) * 8) / ((dword) CAPIDTMF_RECV_TIME_GRANULARITY));
-	if (p_state->recv.min_gap_duration <= 1)
-		p_state->recv.min_gap_duration = 1;
-	else
-		(p_state->recv.min_gap_duration)--;
-	p_state->recv.state |= CAPIDTMF_RECV_STATE_DTMF_ACTIVE;
-}
-
-
-void capidtmf_recv_disable(t_capidtmf_state *p_state)
-{
-	p_state->recv.state &= ~CAPIDTMF_RECV_STATE_DTMF_ACTIVE;
-	if (p_state->recv.state == CAPIDTMF_RECV_STATE_IDLE)
-		capidtmf_recv_init(p_state);
-	else
-	{
-		p_state->recv.cycle_counter = 0;
-		p_state->recv.current_digit_on_time = 0;
-		p_state->recv.current_digit_off_time = 0;
-		p_state->recv.current_digit_value = CAPIDTMF_RECV_NO_DIGIT;
-	}
-}
-
-
-word capidtmf_recv_indication(t_capidtmf_state *p_state, byte *buffer)
-{
-	word i, j, k, flags;
-
-	flags = p_state->recv.indication_state ^ p_state->recv.indication_state_ack;
-	p_state->recv.indication_state_ack ^= flags & CAPIDTMF_RECV_INDICATION_DIGIT;
-	if (p_state->recv.digit_write_pos != p_state->recv.digit_read_pos)
-	{
-		i = 0;
-		k = p_state->recv.digit_write_pos;
-		j = p_state->recv.digit_read_pos;
-		do
-		{
-			buffer[i++] = p_state->recv.digit_buffer[j];
-			j = (j == CAPIDTMF_RECV_DIGIT_BUFFER_SIZE - 1) ? 0 : j + 1;
-		} while (j != k);
-		p_state->recv.digit_read_pos = k;
-		return (i);
-	}
-	p_state->recv.indication_state_ack ^= flags;
-	return (0);
-}
-
-
-#define CAPIDTMF_RECV_WINDOWED_SAMPLES  32
-
-void capidtmf_recv_block(t_capidtmf_state *p_state, byte *buffer, word length)
-{
-	byte result_digit;
-	word sample_number, cycle_counter, n, i;
-	word low_peak, high_peak;
-	dword lo, hi;
-	byte   *p;
-	short *q;
-	byte goertzel_result_buffer[CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT];
-	short windowed_sample_buffer[CAPIDTMF_RECV_WINDOWED_SAMPLES];
-
-
-	if (p_state->recv.state & CAPIDTMF_RECV_STATE_DTMF_ACTIVE)
-	{
-		cycle_counter = p_state->recv.cycle_counter;
-		sample_number = 0;
-		while (sample_number < length)
-		{
-			if (cycle_counter < CAPIDTMF_RECV_ACCUMULATE_CYCLES)
-			{
-				if (cycle_counter == 0)
-				{
-					for (i = 0; i < CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT; i++)
-					{
-						p_state->recv.goertzel_buffer[0][i] = 0;
-						p_state->recv.goertzel_buffer[1][i] = 0;
-					}
-				}
-				n = CAPIDTMF_RECV_ACCUMULATE_CYCLES - cycle_counter;
-				if (n > length - sample_number)
-					n = length - sample_number;
-				if (n > CAPIDTMF_RECV_WINDOWED_SAMPLES)
-					n = CAPIDTMF_RECV_WINDOWED_SAMPLES;
-				p = buffer + sample_number;
-				q = capidtmf_recv_window_function + cycle_counter;
-				if (p_state->ulaw)
-				{
-					for (i = 0; i < n; i++)
-					{
-						windowed_sample_buffer[i] =
-							(short)((capidtmf_expand_table_ulaw[p[i]] * ((long)(q[i]))) >> 15);
-					}
-				}
-				else
-				{
-					for (i = 0; i < n; i++)
-					{
-						windowed_sample_buffer[i] =
-							(short)((capidtmf_expand_table_alaw[p[i]] * ((long)(q[i]))) >> 15);
-					}
-				}
-				capidtmf_recv_goertzel_coef_table[CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT - 1] = CAPIDTMF_RECV_FUNDAMENTAL_OFFSET;
-				capidtmf_goertzel_loop(p_state->recv.goertzel_buffer[0],
-						       capidtmf_recv_goertzel_coef_table, windowed_sample_buffer, n);
-				cycle_counter += n;
-				sample_number += n;
-			}
-			else
-			{
-				capidtmf_goertzel_result(p_state->recv.goertzel_buffer[0],
-							 capidtmf_recv_goertzel_coef_table);
-				for (i = 0; i < CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT; i++)
-				{
-					lo = (dword)(p_state->recv.goertzel_buffer[0][i]);
-					hi = (dword)(p_state->recv.goertzel_buffer[1][i]);
-					if (hi != 0)
-					{
-						n = capidtmf_dword_leading_zeroes(hi);
-						hi = (hi << n) | (lo >> (32 - n));
-					}
-					else
-					{
-						n = capidtmf_dword_leading_zeroes(lo);
-						hi = lo << n;
-						n += 32;
-					}
-					n = 195 - 3 * n;
-					if (hi >= 0xcb300000L)
-						n += 2;
-					else if (hi >= 0xa1450000L)
-						n++;
-					goertzel_result_buffer[i] = (byte) n;
-				}
-				low_peak = DSPDTMF_RX_SENSITIVITY_LOW_DEFAULT;
-				result_digit = CAPIDTMF_RECV_NO_DIGIT;
-				for (i = 0; i < CAPIDTMF_LOW_GROUP_FREQUENCIES; i++)
-				{
-					if (goertzel_result_buffer[i] > low_peak)
-					{
-						low_peak = goertzel_result_buffer[i];
-						result_digit = (byte) i;
-					}
-				}
-				high_peak = DSPDTMF_RX_SENSITIVITY_HIGH_DEFAULT;
-				n = CAPIDTMF_RECV_NO_DIGIT;
-				for (i = CAPIDTMF_LOW_GROUP_FREQUENCIES; i < CAPIDTMF_RECV_BASE_FREQUENCY_COUNT; i++)
-				{
-					if (goertzel_result_buffer[i] > high_peak)
-					{
-						high_peak = goertzel_result_buffer[i];
-						n = (i - CAPIDTMF_LOW_GROUP_FREQUENCIES) << 2;
-					}
-				}
-				result_digit |= (byte) n;
-				if (low_peak + DSPDTMF_RX_HIGH_EXCEEDING_LOW_DEFAULT < high_peak)
-					result_digit = CAPIDTMF_RECV_NO_DIGIT;
-				if (high_peak + DSPDTMF_RX_LOW_EXCEEDING_HIGH_DEFAULT < low_peak)
-					result_digit = CAPIDTMF_RECV_NO_DIGIT;
-				n = 0;
-				for (i = 0; i < CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT; i++)
-				{
-					if ((((short)(low_peak - goertzel_result_buffer[i] - capidtmf_recv_guard_snr_low_table[i])) < 0)
-					    || (((short)(high_peak - goertzel_result_buffer[i] - capidtmf_recv_guard_snr_high_table[i])) < 0))
-					{
-						n++;
-					}
-				}
-				if (n != 2)
-					result_digit = CAPIDTMF_RECV_NO_DIGIT;
-
-				if (result_digit == CAPIDTMF_RECV_NO_DIGIT)
-				{
-					if (p_state->recv.current_digit_on_time != 0)
-					{
-						if (++(p_state->recv.current_digit_off_time) >= p_state->recv.min_gap_duration)
-						{
-							p_state->recv.current_digit_on_time = 0;
-							p_state->recv.current_digit_off_time = 0;
-						}
-					}
-					else
-					{
-						if (p_state->recv.current_digit_off_time != 0)
-							(p_state->recv.current_digit_off_time)--;
-					}
-				}
-				else
-				{
-					if ((p_state->recv.current_digit_on_time == 0)
-					    && (p_state->recv.current_digit_off_time != 0))
-					{
-						(p_state->recv.current_digit_off_time)--;
-					}
-					else
-					{
-						n = p_state->recv.current_digit_off_time;
-						if ((p_state->recv.current_digit_on_time != 0)
-						    && (result_digit != p_state->recv.current_digit_value))
-						{
-							p_state->recv.current_digit_on_time = 0;
-							n = 0;
-						}
-						p_state->recv.current_digit_value = result_digit;
-						p_state->recv.current_digit_off_time = 0;
-						if (p_state->recv.current_digit_on_time != 0xffff)
-						{
-							p_state->recv.current_digit_on_time += n + 1;
-							if (p_state->recv.current_digit_on_time >= p_state->recv.min_digit_duration)
-							{
-								p_state->recv.current_digit_on_time = 0xffff;
-								i = (p_state->recv.digit_write_pos == CAPIDTMF_RECV_DIGIT_BUFFER_SIZE - 1) ?
-									0 : p_state->recv.digit_write_pos + 1;
-								if (i == p_state->recv.digit_read_pos)
-								{
-									trace(dprintf("%s,%d: Receive digit overrun",
-										      (char *)(FILE_), __LINE__));
-								}
-								else
-								{
-									p_state->recv.digit_buffer[p_state->recv.digit_write_pos] = result_digit;
-									p_state->recv.digit_write_pos = i;
-									p_state->recv.indication_state =
-										(p_state->recv.indication_state & ~CAPIDTMF_RECV_INDICATION_DIGIT) |
-										(~p_state->recv.indication_state_ack & CAPIDTMF_RECV_INDICATION_DIGIT);
-								}
-							}
-						}
-					}
-				}
-				cycle_counter = 0;
-				sample_number++;
-			}
-		}
-		p_state->recv.cycle_counter = cycle_counter;
-	}
-}
-
-
-void capidtmf_init(t_capidtmf_state *p_state, byte ulaw)
-{
-	p_state->ulaw = ulaw;
-	capidtmf_recv_init(p_state);
-}
-
-
-/*---------------------------------------------------------------------------*/
diff --git a/drivers/isdn/hardware/eicon/capidtmf.h b/drivers/isdn/hardware/eicon/capidtmf.h
deleted file mode 100644
index 0a9cf59bb224..000000000000
--- a/drivers/isdn/hardware/eicon/capidtmf.h
+++ /dev/null
@@ -1,79 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef CAPIDTMF_H_
-#define CAPIDTMF_H_
-/*---------------------------------------------------------------------------*/
-/*---------------------------------------------------------------------------*/
-#define CAPIDTMF_TONE_GROUP_COUNT            2
-#define CAPIDTMF_LOW_GROUP_FREQUENCIES       4
-#define CAPIDTMF_HIGH_GROUP_FREQUENCIES      4
-#define DSPDTMF_RX_SENSITIVITY_LOW_DEFAULT	50	/* -52 dBm */
-#define DSPDTMF_RX_SENSITIVITY_HIGH_DEFAULT	50	/* -52 dBm */
-#define DSPDTMF_RX_HIGH_EXCEEDING_LOW_DEFAULT	10	/* dB */
-#define DSPDTMF_RX_LOW_EXCEEDING_HIGH_DEFAULT	10	/* dB */
-#define DSPDTMF_RX_HARMONICS_SEL_DEFAULT	12	/* dB */
-#define CAPIDTMF_RECV_BASE_FREQUENCY_COUNT   (CAPIDTMF_LOW_GROUP_FREQUENCIES + CAPIDTMF_HIGH_GROUP_FREQUENCIES)
-#define CAPIDTMF_RECV_GUARD_FREQUENCY_COUNT  8
-#define CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT  (CAPIDTMF_RECV_BASE_FREQUENCY_COUNT + CAPIDTMF_RECV_GUARD_FREQUENCY_COUNT)
-#define CAPIDTMF_RECV_POSITIVE_COEFF_COUNT   16
-#define CAPIDTMF_RECV_NEGATIVE_COEFF_COUNT   (CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT - CAPIDTMF_RECV_POSITIVE_COEFF_COUNT)
-#define CAPIDTMF_RECV_ACCUMULATE_CYCLES      205
-#define CAPIDTMF_RECV_FUNDAMENTAL_OFFSET     (0xff35L * 2)
-#define CAPIDTMF_RECV_FUNDAMENTAL_DECREMENT  (0x0028L * 2)
-#define CAPIDTMF_RECV_DIGIT_BUFFER_SIZE      32
-#define CAPIDTMF_RECV_STATE_IDLE             0x00
-#define CAPIDTMF_RECV_STATE_DTMF_ACTIVE      0x01
-typedef struct tag_capidtmf_recv_state
-{
-	byte digit_buffer[CAPIDTMF_RECV_DIGIT_BUFFER_SIZE];
-	word digit_write_pos;
-	word digit_read_pos;
-	word indication_state;
-	word indication_state_ack;
-	long goertzel_buffer[2][CAPIDTMF_RECV_TOTAL_FREQUENCY_COUNT];
-	word min_gap_duration;
-	word min_digit_duration;
-	word cycle_counter;
-	word current_digit_on_time;
-	word current_digit_off_time;
-	byte current_digit_value;
-	byte state;
-} t_capidtmf_recv_state;
-typedef struct tag_capidtmf_state
-{
-	byte ulaw;
-	t_capidtmf_recv_state recv;
-} t_capidtmf_state;
-word capidtmf_recv_indication(t_capidtmf_state *p_state, byte *buffer);
-void capidtmf_recv_block(t_capidtmf_state *p_state, byte *buffer, word length);
-void capidtmf_init(t_capidtmf_state *p_state, byte ulaw);
-void capidtmf_recv_enable(t_capidtmf_state *p_state, word min_digit_duration, word min_gap_duration);
-void capidtmf_recv_disable(t_capidtmf_state *p_state);
-#define capidtmf_indication(p_state, buffer)  (((p_state)->recv.indication_state != (p_state)->recv.indication_state_ack) ? capidtmf_recv_indication(p_state, buffer) : 0)
-#define capidtmf_recv_process_block(p_state, buffer, length)  { if ((p_state)->recv.state != CAPIDTMF_RECV_STATE_IDLE) capidtmf_recv_block(p_state, buffer, length); }
-/*---------------------------------------------------------------------------*/
-/*---------------------------------------------------------------------------*/
-#endif
diff --git a/drivers/isdn/hardware/eicon/capifunc.c b/drivers/isdn/hardware/eicon/capifunc.c
deleted file mode 100644
index 7a0bdbdd87ea..000000000000
--- a/drivers/isdn/hardware/eicon/capifunc.c
+++ /dev/null
@@ -1,1219 +0,0 @@
-/* $Id: capifunc.c,v 1.61.4.7 2005/02/11 19:40:25 armin Exp $
- *
- * ISDN interface module for Eicon active cards DIVA.
- * CAPI Interface common functions
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- *
- */
-
-#include "platform.h"
-#include "os_capi.h"
-#include "di_defs.h"
-#include "capi20.h"
-#include "divacapi.h"
-#include "divasync.h"
-#include "capifunc.h"
-
-#define DBG_MINIMUM  (DL_LOG + DL_FTL + DL_ERR)
-#define DBG_DEFAULT  (DBG_MINIMUM + DL_XLOG + DL_REG)
-
-DIVA_CAPI_ADAPTER *adapter = (DIVA_CAPI_ADAPTER *) NULL;
-APPL *application = (APPL *) NULL;
-byte max_appl = MAX_APPL;
-byte max_adapter = 0;
-static CAPI_MSG *mapped_msg = (CAPI_MSG *) NULL;
-
-byte UnMapController(byte);
-char DRIVERRELEASE_CAPI[32];
-
-extern void AutomaticLaw(DIVA_CAPI_ADAPTER *);
-extern void callback(ENTITY *);
-extern word api_remove_start(void);
-extern word CapiRelease(word);
-extern word CapiRegister(word);
-extern word api_put(APPL *, CAPI_MSG *);
-
-static diva_os_spin_lock_t api_lock;
-
-static LIST_HEAD(cards);
-
-static dword notify_handle;
-static void DIRequest(ENTITY *e);
-static DESCRIPTOR MAdapter;
-static DESCRIPTOR DAdapter;
-static byte ControllerMap[MAX_DESCRIPTORS + 1];
-
-
-static void diva_register_appl(struct capi_ctr *, __u16,
-			       capi_register_params *);
-static void diva_release_appl(struct capi_ctr *, __u16);
-static char *diva_procinfo(struct capi_ctr *);
-static u16 diva_send_message(struct capi_ctr *,
-			     diva_os_message_buffer_s *);
-extern void diva_os_set_controller_struct(struct capi_ctr *);
-
-extern void DIVA_DIDD_Read(DESCRIPTOR *, int);
-
-/*
- * debug
- */
-static void no_printf(unsigned char *, ...);
-#include "debuglib.c"
-static void xlog(char *x, ...)
-{
-#ifndef DIVA_NO_DEBUGLIB
-	va_list ap;
-	if (myDriverDebugHandle.dbgMask & DL_XLOG) {
-		va_start(ap, x);
-		if (myDriverDebugHandle.dbg_irq) {
-			myDriverDebugHandle.dbg_irq(myDriverDebugHandle.id,
-						    DLI_XLOG, x, ap);
-		} else if (myDriverDebugHandle.dbg_old) {
-			myDriverDebugHandle.dbg_old(myDriverDebugHandle.id,
-						    x, ap);
-		}
-		va_end(ap);
-	}
-#endif
-}
-
-/*
- * info for proc
- */
-static char *diva_procinfo(struct capi_ctr *ctrl)
-{
-	return (ctrl->serial);
-}
-
-/*
- * stop debugging
- */
-static void stop_dbg(void)
-{
-	DbgDeregister();
-	memset(&MAdapter, 0, sizeof(MAdapter));
-	dprintf = no_printf;
-}
-
-/*
- * dummy debug function
- */
-static void no_printf(unsigned char *x, ...)
-{
-}
-
-/*
- * Controller mapping
- */
-byte MapController(byte Controller)
-{
-	byte i;
-	byte MappedController = 0;
-	byte ctrl = Controller & 0x7f;	/* mask external controller bit off */
-
-	for (i = 1; i < max_adapter + 1; i++) {
-		if (ctrl == ControllerMap[i]) {
-			MappedController = (byte) i;
-			break;
-		}
-	}
-	if (i > max_adapter) {
-		ControllerMap[0] = ctrl;
-		MappedController = 0;
-	}
-	return (MappedController | (Controller & 0x80));	/* put back external controller bit */
-}
-
-/*
- * Controller unmapping
- */
-byte UnMapController(byte MappedController)
-{
-	byte Controller;
-	byte ctrl = MappedController & 0x7f;	/* mask external controller bit off */
-
-	if (ctrl <= max_adapter) {
-		Controller = ControllerMap[ctrl];
-	} else {
-		Controller = 0;
-	}
-
-	return (Controller | (MappedController & 0x80));	/* put back external controller bit */
-}
-
-/*
- * find a new free id
- */
-static int find_free_id(void)
-{
-	int num = 0;
-	DIVA_CAPI_ADAPTER *a;
-
-	while (num < MAX_DESCRIPTORS) {
-		a = &adapter[num];
-		if (!a->Id)
-			break;
-		num++;
-	}
-	return (num + 1);
-}
-
-/*
- * find a card structure by controller number
- */
-static diva_card *find_card_by_ctrl(word controller)
-{
-	struct list_head *tmp;
-	diva_card *card;
-
-	list_for_each(tmp, &cards) {
-		card = list_entry(tmp, diva_card, list);
-		if (ControllerMap[card->Id] == controller) {
-			if (card->remove_in_progress)
-				card = NULL;
-			return (card);
-		}
-	}
-	return (diva_card *) 0;
-}
-
-/*
- * Buffer RX/TX
- */
-void *TransmitBufferSet(APPL *appl, dword ref)
-{
-	appl->xbuffer_used[ref] = true;
-	DBG_PRV1(("%d:xbuf_used(%d)", appl->Id, ref + 1))
-		return (void *)(long)ref;
-}
-
-void *TransmitBufferGet(APPL *appl, void *p)
-{
-	if (appl->xbuffer_internal[(dword)(long)p])
-		return appl->xbuffer_internal[(dword)(long)p];
-
-	return appl->xbuffer_ptr[(dword)(long)p];
-}
-
-void TransmitBufferFree(APPL *appl, void *p)
-{
-	appl->xbuffer_used[(dword)(long)p] = false;
-	DBG_PRV1(("%d:xbuf_free(%d)", appl->Id, ((dword)(long)p) + 1))
-		}
-
-void *ReceiveBufferGet(APPL *appl, int Num)
-{
-	return &appl->ReceiveBuffer[Num * appl->MaxDataLength];
-}
-
-/*
- * api_remove_start/complete for cleanup
- */
-void api_remove_complete(void)
-{
-	DBG_PRV1(("api_remove_complete"))
-		}
-
-/*
- * main function called by message.c
- */
-void sendf(APPL *appl, word command, dword Id, word Number, byte *format, ...)
-{
-	word i, j;
-	word length = 12, dlength = 0;
-	byte *write;
-	CAPI_MSG msg;
-	byte *string = NULL;
-	va_list ap;
-	diva_os_message_buffer_s *dmb;
-	diva_card *card = NULL;
-	dword tmp;
-
-	if (!appl)
-		return;
-
-	DBG_PRV1(("sendf(a=%d,cmd=%x,format=%s)",
-		  appl->Id, command, (byte *) format))
-
-		PUT_WORD(&msg.header.appl_id, appl->Id);
-	PUT_WORD(&msg.header.command, command);
-	if ((byte) (command >> 8) == 0x82)
-		Number = appl->Number++;
-	PUT_WORD(&msg.header.number, Number);
-
-	PUT_DWORD(&msg.header.controller, Id);
-	write = (byte *)&msg;
-	write += 12;
-
-	va_start(ap, format);
-	for (i = 0; format[i]; i++) {
-		switch (format[i]) {
-		case 'b':
-			tmp = va_arg(ap, dword);
-			*(byte *) write = (byte) (tmp & 0xff);
-			write += 1;
-			length += 1;
-			break;
-		case 'w':
-			tmp = va_arg(ap, dword);
-			PUT_WORD(write, (tmp & 0xffff));
-			write += 2;
-			length += 2;
-			break;
-		case 'd':
-			tmp = va_arg(ap, dword);
-			PUT_DWORD(write, tmp);
-			write += 4;
-			length += 4;
-			break;
-		case 's':
-		case 'S':
-			string = va_arg(ap, byte *);
-			length += string[0] + 1;
-			for (j = 0; j <= string[0]; j++)
-				*write++ = string[j];
-			break;
-		}
-	}
-	va_end(ap);
-
-	PUT_WORD(&msg.header.length, length);
-	msg.header.controller = UnMapController(msg.header.controller);
-
-	if (command == _DATA_B3_I)
-		dlength = GET_WORD(
-			((byte *)&msg.info.data_b3_ind.Data_Length));
-
-	if (!(dmb = diva_os_alloc_message_buffer(length + dlength,
-						 (void **) &write))) {
-		DBG_ERR(("sendf: alloc_message_buffer failed, incoming msg dropped."))
-			return;
-	}
-
-	/* copy msg header to sk_buff */
-	memcpy(write, (byte *)&msg, length);
-
-	/* if DATA_B3_IND, copy data too */
-	if (command == _DATA_B3_I) {
-		dword data = GET_DWORD(&msg.info.data_b3_ind.Data);
-		memcpy(write + length, (void *)(long)data, dlength);
-	}
-
-#ifndef DIVA_NO_DEBUGLIB
-	if (myDriverDebugHandle.dbgMask & DL_XLOG) {
-		switch (command) {
-		default:
-			xlog("\x00\x02", &msg, 0x81, length);
-			break;
-		case _DATA_B3_R | CONFIRM:
-			if (myDriverDebugHandle.dbgMask & DL_BLK)
-				xlog("\x00\x02", &msg, 0x81, length);
-			break;
-		case _DATA_B3_I:
-			if (myDriverDebugHandle.dbgMask & DL_BLK) {
-				xlog("\x00\x02", &msg, 0x81, length);
-				for (i = 0; i < dlength; i += 256) {
-					DBG_BLK((((char *)(long)GET_DWORD(&msg.info.data_b3_ind.Data)) + i,
-						 ((dlength - i) < 256) ? (dlength - i) : 256))
-						if (!(myDriverDebugHandle.dbgMask & DL_PRV0))
-							break; /* not more if not explicitly requested */
-				}
-			}
-			break;
-		}
-	}
-#endif
-
-	/* find the card structure for this controller */
-	if (!(card = find_card_by_ctrl(write[8] & 0x7f))) {
-		DBG_ERR(("sendf - controller %d not found, incoming msg dropped",
-			 write[8] & 0x7f))
-			diva_os_free_message_buffer(dmb);
-		return;
-	}
-	/* send capi msg to capi layer */
-	capi_ctr_handle_message(&card->capi_ctrl, appl->Id, dmb);
-}
-
-/*
- * cleanup adapter
- */
-static void clean_adapter(int id, struct list_head *free_mem_q)
-{
-	DIVA_CAPI_ADAPTER *a;
-	int i, k;
-
-	a = &adapter[id];
-	k = li_total_channels - a->li_channels;
-	if (k == 0) {
-		if (li_config_table) {
-			list_add((struct list_head *)li_config_table, free_mem_q);
-			li_config_table = NULL;
-		}
-	} else {
-		if (a->li_base < k) {
-			memmove(&li_config_table[a->li_base],
-				&li_config_table[a->li_base + a->li_channels],
-				(k - a->li_base) * sizeof(LI_CONFIG));
-			for (i = 0; i < k; i++) {
-				memmove(&li_config_table[i].flag_table[a->li_base],
-					&li_config_table[i].flag_table[a->li_base + a->li_channels],
-					k - a->li_base);
-				memmove(&li_config_table[i].
-					coef_table[a->li_base],
-					&li_config_table[i].coef_table[a->li_base + a->li_channels],
-					k - a->li_base);
-			}
-		}
-	}
-	li_total_channels = k;
-	for (i = id; i < max_adapter; i++) {
-		if (adapter[i].request)
-			adapter[i].li_base -= a->li_channels;
-	}
-	if (a->plci)
-		list_add((struct list_head *)a->plci, free_mem_q);
-
-	memset(a, 0x00, sizeof(DIVA_CAPI_ADAPTER));
-	while ((max_adapter != 0) && !adapter[max_adapter - 1].request)
-		max_adapter--;
-}
-
-/*
- * remove a card, but ensures consistent state of LI tables
- * in the time adapter is removed
- */
-static void divacapi_remove_card(DESCRIPTOR *d)
-{
-	diva_card *card = NULL;
-	diva_os_spin_lock_magic_t old_irql;
-	LIST_HEAD(free_mem_q);
-	struct list_head *link;
-	struct list_head *tmp;
-
-	/*
-	 * Set "remove in progress flag".
-	 * Ensures that there is no call from sendf to CAPI in
-	 * the time CAPI controller is about to be removed.
-	 */
-	diva_os_enter_spin_lock(&api_lock, &old_irql, "remove card");
-	list_for_each(tmp, &cards) {
-		card = list_entry(tmp, diva_card, list);
-		if (card->d.request == d->request) {
-			card->remove_in_progress = 1;
-			list_del(tmp);
-			break;
-		}
-	}
-	diva_os_leave_spin_lock(&api_lock, &old_irql, "remove card");
-
-	if (card) {
-		/*
-		 * Detach CAPI. Sendf cannot call to CAPI any more.
-		 * After detach no call to send_message() is done too.
-		 */
-		detach_capi_ctr(&card->capi_ctrl);
-
-		/*
-		 * Now get API lock (to ensure stable state of LI tables)
-		 * and update the adapter map/LI table.
-		 */
-		diva_os_enter_spin_lock(&api_lock, &old_irql, "remove card");
-
-		clean_adapter(card->Id - 1, &free_mem_q);
-		DBG_TRC(("DelAdapterMap (%d) -> (%d)",
-			 ControllerMap[card->Id], card->Id))
-			ControllerMap[card->Id] = 0;
-		DBG_TRC(("adapter remove, max_adapter=%d",
-			 max_adapter));
-		diva_os_leave_spin_lock(&api_lock, &old_irql, "remove card");
-
-		/* After releasing the lock, we can free the memory */
-		diva_os_free(0, card);
-	}
-
-	/* free queued memory areas */
-	list_for_each_safe(link, tmp, &free_mem_q) {
-		list_del(link);
-		diva_os_free(0, link);
-	}
-}
-
-/*
- * remove cards
- */
-static void divacapi_remove_cards(void)
-{
-	DESCRIPTOR d;
-	struct list_head *tmp;
-	diva_card *card;
-	diva_os_spin_lock_magic_t old_irql;
-
-rescan:
-	diva_os_enter_spin_lock(&api_lock, &old_irql, "remove cards");
-	list_for_each(tmp, &cards) {
-		card = list_entry(tmp, diva_card, list);
-		diva_os_leave_spin_lock(&api_lock, &old_irql, "remove cards");
-		d.request = card->d.request;
-		divacapi_remove_card(&d);
-		goto rescan;
-	}
-	diva_os_leave_spin_lock(&api_lock, &old_irql, "remove cards");
-}
-
-/*
- * sync_callback
- */
-static void sync_callback(ENTITY *e)
-{
-	diva_os_spin_lock_magic_t old_irql;
-
-	DBG_TRC(("cb:Id=%x,Rc=%x,Ind=%x", e->Id, e->Rc, e->Ind))
-
-		diva_os_enter_spin_lock(&api_lock, &old_irql, "sync_callback");
-	callback(e);
-	diva_os_leave_spin_lock(&api_lock, &old_irql, "sync_callback");
-}
-
-/*
- * add a new card
- */
-static int diva_add_card(DESCRIPTOR *d)
-{
-	int k = 0, i = 0;
-	diva_os_spin_lock_magic_t old_irql;
-	diva_card *card = NULL;
-	struct capi_ctr *ctrl = NULL;
-	DIVA_CAPI_ADAPTER *a = NULL;
-	IDI_SYNC_REQ sync_req;
-	char serial[16];
-	void *mem_to_free;
-	LI_CONFIG *new_li_config_table;
-	int j;
-
-	if (!(card = (diva_card *) diva_os_malloc(0, sizeof(diva_card)))) {
-		DBG_ERR(("diva_add_card: failed to allocate card struct."))
-			return (0);
-	}
-	memset((char *) card, 0x00, sizeof(diva_card));
-	memcpy(&card->d, d, sizeof(DESCRIPTOR));
-	sync_req.GetName.Req = 0;
-	sync_req.GetName.Rc = IDI_SYNC_REQ_GET_NAME;
-	card->d.request((ENTITY *)&sync_req);
-	strlcpy(card->name, sync_req.GetName.name, sizeof(card->name));
-	ctrl = &card->capi_ctrl;
-	strcpy(ctrl->name, card->name);
-	ctrl->register_appl = diva_register_appl;
-	ctrl->release_appl = diva_release_appl;
-	ctrl->send_message = diva_send_message;
-	ctrl->procinfo = diva_procinfo;
-	ctrl->driverdata = card;
-	diva_os_set_controller_struct(ctrl);
-
-	if (attach_capi_ctr(ctrl)) {
-		DBG_ERR(("diva_add_card: failed to attach controller."))
-			diva_os_free(0, card);
-		return (0);
-	}
-
-	diva_os_enter_spin_lock(&api_lock, &old_irql, "find id");
-	card->Id = find_free_id();
-	diva_os_leave_spin_lock(&api_lock, &old_irql, "find id");
-
-	strlcpy(ctrl->manu, M_COMPANY, sizeof(ctrl->manu));
-	ctrl->version.majorversion = 2;
-	ctrl->version.minorversion = 0;
-	ctrl->version.majormanuversion = DRRELMAJOR;
-	ctrl->version.minormanuversion = DRRELMINOR;
-	sync_req.GetSerial.Req = 0;
-	sync_req.GetSerial.Rc = IDI_SYNC_REQ_GET_SERIAL;
-	sync_req.GetSerial.serial = 0;
-	card->d.request((ENTITY *)&sync_req);
-	if ((i = ((sync_req.GetSerial.serial & 0xff000000) >> 24))) {
-		sprintf(serial, "%ld-%d",
-			sync_req.GetSerial.serial & 0x00ffffff, i + 1);
-	} else {
-		sprintf(serial, "%ld", sync_req.GetSerial.serial);
-	}
-	serial[CAPI_SERIAL_LEN - 1] = 0;
-	strlcpy(ctrl->serial, serial, sizeof(ctrl->serial));
-
-	a = &adapter[card->Id - 1];
-	card->adapter = a;
-	a->os_card = card;
-	ControllerMap[card->Id] = (byte) (ctrl->cnr);
-
-	DBG_TRC(("AddAdapterMap (%d) -> (%d)", ctrl->cnr, card->Id))
-
-		sync_req.xdi_capi_prms.Req = 0;
-	sync_req.xdi_capi_prms.Rc = IDI_SYNC_REQ_XDI_GET_CAPI_PARAMS;
-	sync_req.xdi_capi_prms.info.structure_length =
-		sizeof(diva_xdi_get_capi_parameters_t);
-	card->d.request((ENTITY *)&sync_req);
-	a->flag_dynamic_l1_down =
-		sync_req.xdi_capi_prms.info.flag_dynamic_l1_down;
-	a->group_optimization_enabled =
-		sync_req.xdi_capi_prms.info.group_optimization_enabled;
-	a->request = DIRequest;	/* card->d.request; */
-	a->max_plci = card->d.channels + 30;
-	a->max_listen = (card->d.channels > 2) ? 8 : 2;
-	if (!
-	    (a->plci =
-	     (PLCI *) diva_os_malloc(0, sizeof(PLCI) * a->max_plci))) {
-		DBG_ERR(("diva_add_card: failed alloc plci struct."))
-			memset(a, 0, sizeof(DIVA_CAPI_ADAPTER));
-		return (0);
-	}
-	memset(a->plci, 0, sizeof(PLCI) * a->max_plci);
-
-	for (k = 0; k < a->max_plci; k++) {
-		a->Id = (byte) card->Id;
-		a->plci[k].Sig.callback = sync_callback;
-		a->plci[k].Sig.XNum = 1;
-		a->plci[k].Sig.X = a->plci[k].XData;
-		a->plci[k].Sig.user[0] = (word) (card->Id - 1);
-		a->plci[k].Sig.user[1] = (word) k;
-		a->plci[k].NL.callback = sync_callback;
-		a->plci[k].NL.XNum = 1;
-		a->plci[k].NL.X = a->plci[k].XData;
-		a->plci[k].NL.user[0] = (word) ((card->Id - 1) | 0x8000);
-		a->plci[k].NL.user[1] = (word) k;
-		a->plci[k].adapter = a;
-	}
-
-	a->profile.Number = card->Id;
-	a->profile.Channels = card->d.channels;
-	if (card->d.features & DI_FAX3) {
-		a->profile.Global_Options = 0x71;
-		if (card->d.features & DI_CODEC)
-			a->profile.Global_Options |= 0x6;
-#if IMPLEMENT_DTMF
-		a->profile.Global_Options |= 0x8;
-#endif				/* IMPLEMENT_DTMF */
-		a->profile.Global_Options |= 0x80; /* Line Interconnect */
-#if IMPLEMENT_ECHO_CANCELLER
-		a->profile.Global_Options |= 0x100;
-#endif				/* IMPLEMENT_ECHO_CANCELLER */
-		a->profile.B1_Protocols = 0xdf;
-		a->profile.B2_Protocols = 0x1fdb;
-		a->profile.B3_Protocols = 0xb7;
-		a->manufacturer_features = MANUFACTURER_FEATURE_HARDDTMF;
-	} else {
-		a->profile.Global_Options = 0x71;
-		if (card->d.features & DI_CODEC)
-			a->profile.Global_Options |= 0x2;
-		a->profile.B1_Protocols = 0x43;
-		a->profile.B2_Protocols = 0x1f0f;
-		a->profile.B3_Protocols = 0x07;
-		a->manufacturer_features = 0;
-	}
-
-	a->li_pri = (a->profile.Channels > 2);
-	a->li_channels = a->li_pri ? MIXER_CHANNELS_PRI : MIXER_CHANNELS_BRI;
-	a->li_base = 0;
-	for (i = 0; &adapter[i] != a; i++) {
-		if (adapter[i].request)
-			a->li_base = adapter[i].li_base + adapter[i].li_channels;
-	}
-	k = li_total_channels + a->li_channels;
-	new_li_config_table =
-		(LI_CONFIG *) diva_os_malloc(0, ((k * sizeof(LI_CONFIG) + 3) & ~3) + (2 * k) * ((k + 3) & ~3));
-	if (new_li_config_table == NULL) {
-		DBG_ERR(("diva_add_card: failed alloc li_config table."))
-			memset(a, 0, sizeof(DIVA_CAPI_ADAPTER));
-		return (0);
-	}
-
-	/* Prevent access to line interconnect table in process update */
-	diva_os_enter_spin_lock(&api_lock, &old_irql, "add card");
-
-	j = 0;
-	for (i = 0; i < k; i++) {
-		if ((i >= a->li_base) && (i < a->li_base + a->li_channels))
-			memset(&new_li_config_table[i], 0, sizeof(LI_CONFIG));
-		else
-			memcpy(&new_li_config_table[i], &li_config_table[j], sizeof(LI_CONFIG));
-		new_li_config_table[i].flag_table =
-			((byte *) new_li_config_table) + (((k * sizeof(LI_CONFIG) + 3) & ~3) + (2 * i) * ((k + 3) & ~3));
-		new_li_config_table[i].coef_table =
-			((byte *) new_li_config_table) + (((k * sizeof(LI_CONFIG) + 3) & ~3) + (2 * i + 1) * ((k + 3) & ~3));
-		if ((i >= a->li_base) && (i < a->li_base + a->li_channels)) {
-			new_li_config_table[i].adapter = a;
-			memset(&new_li_config_table[i].flag_table[0], 0, k);
-			memset(&new_li_config_table[i].coef_table[0], 0, k);
-		} else {
-			if (a->li_base != 0) {
-				memcpy(&new_li_config_table[i].flag_table[0],
-				       &li_config_table[j].flag_table[0],
-				       a->li_base);
-				memcpy(&new_li_config_table[i].coef_table[0],
-				       &li_config_table[j].coef_table[0],
-				       a->li_base);
-			}
-			memset(&new_li_config_table[i].flag_table[a->li_base], 0, a->li_channels);
-			memset(&new_li_config_table[i].coef_table[a->li_base], 0, a->li_channels);
-			if (a->li_base + a->li_channels < k) {
-				memcpy(&new_li_config_table[i].flag_table[a->li_base +
-									  a->li_channels],
-				       &li_config_table[j].flag_table[a->li_base],
-				       k - (a->li_base + a->li_channels));
-				memcpy(&new_li_config_table[i].coef_table[a->li_base +
-									  a->li_channels],
-				       &li_config_table[j].coef_table[a->li_base],
-				       k - (a->li_base + a->li_channels));
-			}
-			j++;
-		}
-	}
-	li_total_channels = k;
-
-	mem_to_free = li_config_table;
-
-	li_config_table = new_li_config_table;
-	for (i = card->Id; i < max_adapter; i++) {
-		if (adapter[i].request)
-			adapter[i].li_base += a->li_channels;
-	}
-
-	if (a == &adapter[max_adapter])
-		max_adapter++;
-
-	list_add(&(card->list), &cards);
-	AutomaticLaw(a);
-
-	diva_os_leave_spin_lock(&api_lock, &old_irql, "add card");
-
-	if (mem_to_free) {
-		diva_os_free(0, mem_to_free);
-	}
-
-	i = 0;
-	while (i++ < 30) {
-		if (a->automatic_law > 3)
-			break;
-		diva_os_sleep(10);
-	}
-
-	/* profile information */
-	PUT_WORD(&ctrl->profile.nbchannel, card->d.channels);
-	ctrl->profile.goptions = a->profile.Global_Options;
-	ctrl->profile.support1 = a->profile.B1_Protocols;
-	ctrl->profile.support2 = a->profile.B2_Protocols;
-	ctrl->profile.support3 = a->profile.B3_Protocols;
-	/* manufacturer profile information */
-	ctrl->profile.manu[0] = a->man_profile.private_options;
-	ctrl->profile.manu[1] = a->man_profile.rtp_primary_payloads;
-	ctrl->profile.manu[2] = a->man_profile.rtp_additional_payloads;
-	ctrl->profile.manu[3] = 0;
-	ctrl->profile.manu[4] = 0;
-
-	capi_ctr_ready(ctrl);
-
-	DBG_TRC(("adapter added, max_adapter=%d", max_adapter));
-	return (1);
-}
-
-/*
- *  register appl
- */
-static void diva_register_appl(struct capi_ctr *ctrl, __u16 appl,
-			       capi_register_params *rp)
-{
-	APPL *this;
-	word bnum, xnum;
-	int i = 0;
-	unsigned char *p;
-	void *DataNCCI, *DataFlags, *ReceiveBuffer, *xbuffer_used;
-	void **xbuffer_ptr, **xbuffer_internal;
-	diva_os_spin_lock_magic_t old_irql;
-	unsigned int mem_len;
-	int nconn = rp->level3cnt;
-
-
-	if (diva_os_in_irq()) {
-		DBG_ERR(("CAPI_REGISTER - in irq context !"))
-			return;
-	}
-
-	DBG_TRC(("application register Id=%d", appl))
-
-		if (appl > MAX_APPL) {
-			DBG_ERR(("CAPI_REGISTER - appl.Id exceeds MAX_APPL"))
-				return;
-		}
-
-	if (nconn <= 0)
-		nconn = ctrl->profile.nbchannel * -nconn;
-
-	if (nconn == 0)
-		nconn = ctrl->profile.nbchannel;
-
-	DBG_LOG(("CAPI_REGISTER - Id = %d", appl))
-		DBG_LOG(("  MaxLogicalConnections = %d(%d)", nconn, rp->level3cnt))
-		DBG_LOG(("  MaxBDataBuffers       = %d", rp->datablkcnt))
-		DBG_LOG(("  MaxBDataLength        = %d", rp->datablklen))
-
-		if (nconn < 1 ||
-		    nconn > 255 ||
-		    rp->datablklen < 80 ||
-		    rp->datablklen > 2150 || rp->datablkcnt > 255) {
-			DBG_ERR(("CAPI_REGISTER - invalid parameters"))
-				return;
-		}
-
-	if (application[appl - 1].Id == appl) {
-		DBG_LOG(("CAPI_REGISTER - appl already registered"))
-			return;	/* appl already registered */
-	}
-
-	/* alloc memory */
-
-	bnum = nconn * rp->datablkcnt;
-	xnum = nconn * MAX_DATA_B3;
-
-	mem_len  = bnum * sizeof(word);		/* DataNCCI */
-	mem_len += bnum * sizeof(word);		/* DataFlags */
-	mem_len += bnum * rp->datablklen;	/* ReceiveBuffer */
-	mem_len += xnum;			/* xbuffer_used */
-	mem_len += xnum * sizeof(void *);	/* xbuffer_ptr */
-	mem_len += xnum * sizeof(void *);	/* xbuffer_internal */
-	mem_len += xnum * rp->datablklen;	/* xbuffer_ptr[xnum] */
-
-	DBG_LOG(("  Allocated Memory      = %d", mem_len))
-		if (!(p = diva_os_malloc(0, mem_len))) {
-			DBG_ERR(("CAPI_REGISTER - memory allocation failed"))
-				return;
-		}
-	memset(p, 0, mem_len);
-
-	DataNCCI = (void *)p;
-	p += bnum * sizeof(word);
-	DataFlags = (void *)p;
-	p += bnum * sizeof(word);
-	ReceiveBuffer = (void *)p;
-	p += bnum * rp->datablklen;
-	xbuffer_used = (void *)p;
-	p += xnum;
-	xbuffer_ptr = (void **)p;
-	p += xnum * sizeof(void *);
-	xbuffer_internal = (void **)p;
-	p += xnum * sizeof(void *);
-	for (i = 0; i < xnum; i++) {
-		xbuffer_ptr[i] = (void *)p;
-		p += rp->datablklen;
-	}
-
-	/* initialize application data */
-	diva_os_enter_spin_lock(&api_lock, &old_irql, "register_appl");
-
-	this = &application[appl - 1];
-	memset(this, 0, sizeof(APPL));
-
-	this->Id = appl;
-
-	for (i = 0; i < max_adapter; i++) {
-		adapter[i].CIP_Mask[appl - 1] = 0;
-	}
-
-	this->queue_size = 1000;
-
-	this->MaxNCCI = (byte) nconn;
-	this->MaxNCCIData = (byte) rp->datablkcnt;
-	this->MaxBuffer = bnum;
-	this->MaxDataLength = rp->datablklen;
-
-	this->DataNCCI = DataNCCI;
-	this->DataFlags = DataFlags;
-	this->ReceiveBuffer = ReceiveBuffer;
-	this->xbuffer_used = xbuffer_used;
-	this->xbuffer_ptr = xbuffer_ptr;
-	this->xbuffer_internal = xbuffer_internal;
-	for (i = 0; i < xnum; i++) {
-		this->xbuffer_ptr[i] = xbuffer_ptr[i];
-	}
-
-	CapiRegister(this->Id);
-	diva_os_leave_spin_lock(&api_lock, &old_irql, "register_appl");
-
-}
-
-/*
- *  release appl
- */
-static void diva_release_appl(struct capi_ctr *ctrl, __u16 appl)
-{
-	diva_os_spin_lock_magic_t old_irql;
-	APPL *this = &application[appl - 1];
-	void *mem_to_free = NULL;
-
-	DBG_TRC(("application %d(%d) cleanup", this->Id, appl))
-
-		if (diva_os_in_irq()) {
-			DBG_ERR(("CAPI_RELEASE - in irq context !"))
-				return;
-		}
-
-	diva_os_enter_spin_lock(&api_lock, &old_irql, "release_appl");
-	if (this->Id) {
-		CapiRelease(this->Id);
-		mem_to_free = this->DataNCCI;
-		this->DataNCCI = NULL;
-		this->Id = 0;
-	}
-	diva_os_leave_spin_lock(&api_lock, &old_irql, "release_appl");
-
-	if (mem_to_free)
-		diva_os_free(0, mem_to_free);
-
-}
-
-/*
- *  send message
- */
-static u16 diva_send_message(struct capi_ctr *ctrl,
-			     diva_os_message_buffer_s *dmb)
-{
-	int i = 0;
-	word ret = 0;
-	diva_os_spin_lock_magic_t old_irql;
-	CAPI_MSG *msg = (CAPI_MSG *) DIVA_MESSAGE_BUFFER_DATA(dmb);
-	APPL *this = &application[GET_WORD(&msg->header.appl_id) - 1];
-	diva_card *card = ctrl->driverdata;
-	__u32 length = DIVA_MESSAGE_BUFFER_LEN(dmb);
-	word clength = GET_WORD(&msg->header.length);
-	word command = GET_WORD(&msg->header.command);
-	u16 retval = CAPI_NOERROR;
-
-	if (diva_os_in_irq()) {
-		DBG_ERR(("CAPI_SEND_MSG - in irq context !"))
-			return CAPI_REGOSRESOURCEERR;
-	}
-	DBG_PRV1(("Write - appl = %d, cmd = 0x%x", this->Id, command))
-
-		if (card->remove_in_progress) {
-			DBG_ERR(("CAPI_SEND_MSG - remove in progress!"))
-				return CAPI_REGOSRESOURCEERR;
-		}
-
-	diva_os_enter_spin_lock(&api_lock, &old_irql, "send message");
-
-	if (!this->Id) {
-		diva_os_leave_spin_lock(&api_lock, &old_irql, "send message");
-		return CAPI_ILLAPPNR;
-	}
-
-	/* patch controller number */
-	msg->header.controller = ControllerMap[card->Id]
-		| (msg->header.controller & 0x80);	/* preserve external controller bit */
-
-	switch (command) {
-	default:
-		xlog("\x00\x02", msg, 0x80, clength);
-		break;
-
-	case _DATA_B3_I | RESPONSE:
-#ifndef DIVA_NO_DEBUGLIB
-		if (myDriverDebugHandle.dbgMask & DL_BLK)
-			xlog("\x00\x02", msg, 0x80, clength);
-#endif
-		break;
-
-	case _DATA_B3_R:
-#ifndef DIVA_NO_DEBUGLIB
-		if (myDriverDebugHandle.dbgMask & DL_BLK)
-			xlog("\x00\x02", msg, 0x80, clength);
-#endif
-
-		if (clength == 24)
-			clength = 22;	/* workaround for PPcom bug */
-		/* header is always 22      */
-		if (GET_WORD(&msg->info.data_b3_req.Data_Length) >
-		    this->MaxDataLength
-		    || GET_WORD(&msg->info.data_b3_req.Data_Length) >
-		    (length - clength)) {
-			DBG_ERR(("Write - invalid message size"))
-				retval = CAPI_ILLCMDORSUBCMDORMSGTOSMALL;
-			goto write_end;
-		}
-
-		for (i = 0; i < (MAX_DATA_B3 * this->MaxNCCI)
-			     && this->xbuffer_used[i]; i++);
-		if (i == (MAX_DATA_B3 * this->MaxNCCI)) {
-			DBG_ERR(("Write - too many data pending"))
-				retval = CAPI_SENDQUEUEFULL;
-			goto write_end;
-		}
-		msg->info.data_b3_req.Data = i;
-
-		this->xbuffer_internal[i] = NULL;
-		memcpy(this->xbuffer_ptr[i], &((__u8 *) msg)[clength],
-		       GET_WORD(&msg->info.data_b3_req.Data_Length));
-
-#ifndef DIVA_NO_DEBUGLIB
-		if ((myDriverDebugHandle.dbgMask & DL_BLK)
-		    && (myDriverDebugHandle.dbgMask & DL_XLOG)) {
-			int j;
-			for (j = 0; j <
-				     GET_WORD(&msg->info.data_b3_req.Data_Length);
-			     j += 256) {
-				DBG_BLK((((char *) this->xbuffer_ptr[i]) + j,
-					 ((GET_WORD(&msg->info.data_b3_req.Data_Length) - j) <
-					  256) ? (GET_WORD(&msg->info.data_b3_req.Data_Length) - j) : 256))
-					if (!(myDriverDebugHandle.dbgMask & DL_PRV0))
-						break;	/* not more if not explicitly requested */
-			}
-		}
-#endif
-		break;
-	}
-
-	memcpy(mapped_msg, msg, (__u32) clength);
-	mapped_msg->header.controller = MapController(mapped_msg->header.controller);
-	mapped_msg->header.length = clength;
-	mapped_msg->header.command = command;
-	mapped_msg->header.number = GET_WORD(&msg->header.number);
-
-	ret = api_put(this, mapped_msg);
-	switch (ret) {
-	case 0:
-		break;
-	case _BAD_MSG:
-		DBG_ERR(("Write - bad message"))
-			retval = CAPI_ILLCMDORSUBCMDORMSGTOSMALL;
-		break;
-	case _QUEUE_FULL:
-		DBG_ERR(("Write - queue full"))
-			retval = CAPI_SENDQUEUEFULL;
-		break;
-	default:
-		DBG_ERR(("Write - api_put returned unknown error"))
-			retval = CAPI_UNKNOWNNOTPAR;
-		break;
-	}
-
-write_end:
-	diva_os_leave_spin_lock(&api_lock, &old_irql, "send message");
-	if (retval == CAPI_NOERROR)
-		diva_os_free_message_buffer(dmb);
-	return retval;
-}
-
-
-/*
- * cards request function
- */
-static void DIRequest(ENTITY *e)
-{
-	DIVA_CAPI_ADAPTER *a = &(adapter[(byte) e->user[0]]);
-	diva_card *os_card = (diva_card *) a->os_card;
-
-	if (e->Req && (a->FlowControlIdTable[e->ReqCh] == e->Id)) {
-		a->FlowControlSkipTable[e->ReqCh] = 1;
-	}
-
-	(*(os_card->d.request)) (e);
-}
-
-/*
- * callback function from didd
- */
-static void didd_callback(void *context, DESCRIPTOR *adapter, int removal)
-{
-	if (adapter->type == IDI_DADAPTER) {
-		DBG_ERR(("Notification about IDI_DADAPTER change ! Oops."));
-		return;
-	} else if (adapter->type == IDI_DIMAINT) {
-		if (removal) {
-			stop_dbg();
-		} else {
-			memcpy(&MAdapter, adapter, sizeof(MAdapter));
-			dprintf = (DIVA_DI_PRINTF) MAdapter.request;
-			DbgRegister("CAPI20", DRIVERRELEASE_CAPI, DBG_DEFAULT);
-		}
-	} else if ((adapter->type > 0) && (adapter->type < 16)) {	/* IDI Adapter */
-		if (removal) {
-			divacapi_remove_card(adapter);
-		} else {
-			diva_add_card(adapter);
-		}
-	}
-	return;
-}
-
-/*
- * connect to didd
- */
-static int divacapi_connect_didd(void)
-{
-	int x = 0;
-	int dadapter = 0;
-	IDI_SYNC_REQ req;
-	DESCRIPTOR DIDD_Table[MAX_DESCRIPTORS];
-
-	DIVA_DIDD_Read(DIDD_Table, sizeof(DIDD_Table));
-
-	for (x = 0; x < MAX_DESCRIPTORS; x++) {
-		if (DIDD_Table[x].type == IDI_DIMAINT) {	/* MAINT found */
-			memcpy(&MAdapter, &DIDD_Table[x], sizeof(DAdapter));
-			dprintf = (DIVA_DI_PRINTF) MAdapter.request;
-			DbgRegister("CAPI20", DRIVERRELEASE_CAPI, DBG_DEFAULT);
-			break;
-		}
-	}
-	for (x = 0; x < MAX_DESCRIPTORS; x++) {
-		if (DIDD_Table[x].type == IDI_DADAPTER) {	/* DADAPTER found */
-			dadapter = 1;
-			memcpy(&DAdapter, &DIDD_Table[x], sizeof(DAdapter));
-			req.didd_notify.e.Req = 0;
-			req.didd_notify.e.Rc =
-				IDI_SYNC_REQ_DIDD_REGISTER_ADAPTER_NOTIFY;
-			req.didd_notify.info.callback = (void *)didd_callback;
-			req.didd_notify.info.context = NULL;
-			DAdapter.request((ENTITY *)&req);
-			if (req.didd_notify.e.Rc != 0xff) {
-				stop_dbg();
-				return (0);
-			}
-			notify_handle = req.didd_notify.info.handle;
-		}
-		else if ((DIDD_Table[x].type > 0) && (DIDD_Table[x].type < 16)) {	/* IDI Adapter found */
-			diva_add_card(&DIDD_Table[x]);
-		}
-	}
-
-	if (!dadapter) {
-		stop_dbg();
-	}
-
-	return (dadapter);
-}
-
-/*
- * diconnect from didd
- */
-static void divacapi_disconnect_didd(void)
-{
-	IDI_SYNC_REQ req;
-
-	stop_dbg();
-
-	req.didd_notify.e.Req = 0;
-	req.didd_notify.e.Rc = IDI_SYNC_REQ_DIDD_REMOVE_ADAPTER_NOTIFY;
-	req.didd_notify.info.handle = notify_handle;
-	DAdapter.request((ENTITY *)&req);
-}
-
-/*
- * we do not provide date/time here,
- * the application should do this.
- */
-int fax_head_line_time(char *buffer)
-{
-	return (0);
-}
-
-/*
- * init (alloc) main structures
- */
-static int __init init_main_structs(void)
-{
-	if (!(mapped_msg = (CAPI_MSG *) diva_os_malloc(0, MAX_MSG_SIZE))) {
-		DBG_ERR(("init: failed alloc mapped_msg."))
-			return 0;
-	}
-
-	if (!(adapter = diva_os_malloc(0, sizeof(DIVA_CAPI_ADAPTER) * MAX_DESCRIPTORS))) {
-		DBG_ERR(("init: failed alloc adapter struct."))
-			diva_os_free(0, mapped_msg);
-		return 0;
-	}
-	memset(adapter, 0, sizeof(DIVA_CAPI_ADAPTER) * MAX_DESCRIPTORS);
-
-	if (!(application = diva_os_malloc(0, sizeof(APPL) * MAX_APPL))) {
-		DBG_ERR(("init: failed alloc application struct."))
-			diva_os_free(0, mapped_msg);
-		diva_os_free(0, adapter);
-		return 0;
-	}
-	memset(application, 0, sizeof(APPL) * MAX_APPL);
-
-	return (1);
-}
-
-/*
- * remove (free) main structures
- */
-static void remove_main_structs(void)
-{
-	if (application)
-		diva_os_free(0, application);
-	if (adapter)
-		diva_os_free(0, adapter);
-	if (mapped_msg)
-		diva_os_free(0, mapped_msg);
-}
-
-/*
- * api_remove_start
- */
-static void do_api_remove_start(void)
-{
-	diva_os_spin_lock_magic_t old_irql;
-	int ret = 1, count = 100;
-
-	do {
-		diva_os_enter_spin_lock(&api_lock, &old_irql, "api remove start");
-		ret = api_remove_start();
-		diva_os_leave_spin_lock(&api_lock, &old_irql, "api remove start");
-
-		diva_os_sleep(10);
-	} while (ret && count--);
-
-	if (ret)
-		DBG_ERR(("could not remove signaling ID's"))
-			}
-
-/*
- * init
- */
-int __init init_capifunc(void)
-{
-	diva_os_initialize_spin_lock(&api_lock, "capifunc");
-	memset(ControllerMap, 0, MAX_DESCRIPTORS + 1);
-	max_adapter = 0;
-
-
-	if (!init_main_structs()) {
-		DBG_ERR(("init: failed to init main structs."))
-			diva_os_destroy_spin_lock(&api_lock, "capifunc");
-		return (0);
-	}
-
-	if (!divacapi_connect_didd()) {
-		DBG_ERR(("init: failed to connect to DIDD."))
-			do_api_remove_start();
-		divacapi_remove_cards();
-		remove_main_structs();
-		diva_os_destroy_spin_lock(&api_lock, "capifunc");
-		return (0);
-	}
-
-	return (1);
-}
-
-/*
- * finit
- */
-void __exit finit_capifunc(void)
-{
-	do_api_remove_start();
-	divacapi_disconnect_didd();
-	divacapi_remove_cards();
-	remove_main_structs();
-	diva_os_destroy_spin_lock(&api_lock, "capifunc");
-}
diff --git a/drivers/isdn/hardware/eicon/capifunc.h b/drivers/isdn/hardware/eicon/capifunc.h
deleted file mode 100644
index e96c45bb5638..000000000000
--- a/drivers/isdn/hardware/eicon/capifunc.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/* $Id: capifunc.h,v 1.11.4.1 2004/08/28 20:03:53 armin Exp $
- *
- * ISDN interface module for Eicon active cards DIVA.
- * CAPI Interface common functions
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#ifndef __CAPIFUNC_H__
-#define __CAPIFUNC_H__
-
-#define DRRELMAJOR  2
-#define DRRELMINOR  0
-#define DRRELEXTRA  ""
-
-#define M_COMPANY "Eicon Networks"
-
-extern char DRIVERRELEASE_CAPI[];
-
-typedef struct _diva_card {
-	struct list_head list;
-	int remove_in_progress;
-	int Id;
-	struct capi_ctr capi_ctrl;
-	DIVA_CAPI_ADAPTER *adapter;
-	DESCRIPTOR d;
-	char name[32];
-} diva_card;
-
-/*
- * prototypes
- */
-int init_capifunc(void);
-void finit_capifunc(void);
-
-#endif /* __CAPIFUNC_H__ */
diff --git a/drivers/isdn/hardware/eicon/capimain.c b/drivers/isdn/hardware/eicon/capimain.c
deleted file mode 100644
index f9244dc1c3c9..000000000000
--- a/drivers/isdn/hardware/eicon/capimain.c
+++ /dev/null
@@ -1,141 +0,0 @@
-/* $Id: capimain.c,v 1.24 2003/09/09 06:51:05 schindler Exp $
- *
- * ISDN interface module for Eicon active cards DIVA.
- * CAPI Interface
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/uaccess.h>
-#include <linux/seq_file.h>
-#include <linux/skbuff.h>
-
-#include "os_capi.h"
-
-#include "platform.h"
-#include "di_defs.h"
-#include "capi20.h"
-#include "divacapi.h"
-#include "cp_vers.h"
-#include "capifunc.h"
-
-static char *main_revision = "$Revision: 1.24 $";
-static char *DRIVERNAME =
-	"Eicon DIVA - CAPI Interface driver (http://www.melware.net)";
-static char *DRIVERLNAME = "divacapi";
-
-MODULE_DESCRIPTION("CAPI driver for Eicon DIVA cards");
-MODULE_AUTHOR("Cytronics & Melware, Eicon Networks");
-MODULE_SUPPORTED_DEVICE("CAPI and DIVA card drivers");
-MODULE_LICENSE("GPL");
-
-/*
- * get revision number from revision string
- */
-static char *getrev(const char *revision)
-{
-	char *rev;
-	char *p;
-	if ((p = strchr(revision, ':'))) {
-		rev = p + 2;
-		p = strchr(rev, '$');
-		*--p = 0;
-	} else
-		rev = "1.0";
-	return rev;
-
-}
-
-/*
- * alloc a message buffer
- */
-diva_os_message_buffer_s *diva_os_alloc_message_buffer(unsigned long size,
-						       void **data_buf)
-{
-	diva_os_message_buffer_s *dmb = alloc_skb(size, GFP_ATOMIC);
-	if (dmb) {
-		*data_buf = skb_put(dmb, size);
-	}
-	return (dmb);
-}
-
-/*
- * free a message buffer
- */
-void diva_os_free_message_buffer(diva_os_message_buffer_s *dmb)
-{
-	kfree_skb(dmb);
-}
-
-/*
- * proc function for controller info
- */
-static int diva_ctl_proc_show(struct seq_file *m, void *v)
-{
-	struct capi_ctr *ctrl = m->private;
-	diva_card *card = (diva_card *) ctrl->driverdata;
-
-	seq_printf(m, "%s\n", ctrl->name);
-	seq_printf(m, "Serial No. : %s\n", ctrl->serial);
-	seq_printf(m, "Id         : %d\n", card->Id);
-	seq_printf(m, "Channels   : %d\n", card->d.channels);
-
-	return 0;
-}
-
-/*
- * set additional os settings in capi_ctr struct
- */
-void diva_os_set_controller_struct(struct capi_ctr *ctrl)
-{
-	ctrl->driver_name = DRIVERLNAME;
-	ctrl->load_firmware = NULL;
-	ctrl->reset_ctr = NULL;
-	ctrl->proc_show = diva_ctl_proc_show;
-	ctrl->owner = THIS_MODULE;
-}
-
-/*
- * module init
- */
-static int __init divacapi_init(void)
-{
-	char tmprev[32];
-	int ret = 0;
-
-	sprintf(DRIVERRELEASE_CAPI, "%d.%d%s", DRRELMAJOR, DRRELMINOR,
-		DRRELEXTRA);
-
-	printk(KERN_INFO "%s\n", DRIVERNAME);
-	printk(KERN_INFO "%s: Rel:%s  Rev:", DRIVERLNAME, DRIVERRELEASE_CAPI);
-	strcpy(tmprev, main_revision);
-	printk("%s  Build: %s(%s)\n", getrev(tmprev),
-	       diva_capi_common_code_build, DIVA_BUILD);
-
-	if (!(init_capifunc())) {
-		printk(KERN_ERR "%s: failed init capi_driver.\n",
-		       DRIVERLNAME);
-		ret = -EIO;
-	}
-
-	return ret;
-}
-
-/*
- * module exit
- */
-static void __exit divacapi_exit(void)
-{
-	finit_capifunc();
-	printk(KERN_INFO "%s: module unloaded.\n", DRIVERLNAME);
-}
-
-module_init(divacapi_init);
-module_exit(divacapi_exit);
diff --git a/drivers/isdn/hardware/eicon/cardtype.h b/drivers/isdn/hardware/eicon/cardtype.h
deleted file mode 100644
index 8b20e22cae1e..000000000000
--- a/drivers/isdn/hardware/eicon/cardtype.h
+++ /dev/null
@@ -1,1098 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef _CARDTYPE_H_
-#define _CARDTYPE_H_
-#ifndef CARDTYPE_H_WANT_DATA
-#define CARDTYPE_H_WANT_DATA   0
-#endif
-#ifndef CARDTYPE_H_WANT_IDI_DATA
-#define CARDTYPE_H_WANT_IDI_DATA  0
-#endif
-#ifndef CARDTYPE_H_WANT_RESOURCE_DATA
-#define CARDTYPE_H_WANT_RESOURCE_DATA 1
-#endif
-#ifndef CARDTYPE_H_WANT_FILE_DATA
-#define CARDTYPE_H_WANT_FILE_DATA  1
-#endif
-/*
- * D-channel protocol identifiers
- *
- * Attention: Unfortunately the identifiers defined here differ from
- *      the identifiers used in Protocol/1/Common/prot/q931.h .
- *     The only reason for this is that q931.h has not a global
- *     scope and we did not know about the definitions there.
- *     But the definitions here cannot be changed easily because
- *     they are used in setup scripts and programs.
- *     Thus the definitions here have to be mapped if they are
- *     used in the protocol code context !
- *
- * Now the identifiers are defined in the q931lib/constant.h file.
- * Unfortunately this file has also not a global scope.
- * But beginning with PROTTYPE_US any new identifier will get the same
- * value as the corresponding PROT_* definition in q931lib/constant.h !
- */
-#define PROTTYPE_MINVAL     0
-#define PROTTYPE_ETSI       0
-#define PROTTYPE_1TR6       1
-#define PROTTYPE_BELG       2
-#define PROTTYPE_FRANC      3
-#define PROTTYPE_ATEL       4
-#define PROTTYPE_NI         5  /* DMS 100, Nortel, National ISDN */
-#define PROTTYPE_5ESS       6  /* 5ESS   , AT&T,   5ESS Custom   */
-#define PROTTYPE_JAPAN      7
-#define PROTTYPE_SWED       8
-#define PROTTYPE_US         9  /* US autodetect */
-#define PROTTYPE_ITALY      10
-#define PROTTYPE_TWAN       11
-#define PROTTYPE_AUSTRAL    12
-#define PROTTYPE_4ESDN      13
-#define PROTTYPE_4ESDS      14
-#define PROTTYPE_4ELDS      15
-#define PROTTYPE_4EMGC      16
-#define PROTTYPE_4EMGI      17
-#define PROTTYPE_HONGKONG   18
-#define PROTTYPE_RBSCAS     19
-#define PROTTYPE_CORNETN    20
-#define PROTTYPE_QSIG       21
-#define PROTTYPE_NI_EWSD    22 /* EWSD, Siemens, National ISDN   */
-#define PROTTYPE_5ESS_NI    23 /* 5ESS, Lucent, National ISDN    */
-#define PROTTYPE_T1CORNETN  24
-#define PROTTYPE_CORNETNQ   25
-#define PROTTYPE_T1CORNETNQ 26
-#define PROTTYPE_T1QSIG     27
-#define PROTTYPE_E1UNCH     28
-#define PROTTYPE_T1UNCH     29
-#define PROTTYPE_E1CHAN     30
-#define PROTTYPE_T1CHAN     31
-#define PROTTYPE_R2CAS      32
-#define PROTTYPE_MAXVAL     32
-/*
- * Card type identifiers
- */
-#define CARD_UNKNOWN                      0
-#define CARD_NONE                         0
-/* DIVA cards */
-#define CARDTYPE_DIVA_MCA                 0
-#define CARDTYPE_DIVA_ISA                 1
-#define CARDTYPE_DIVA_PCM                 2
-#define CARDTYPE_DIVAPRO_ISA              3
-#define CARDTYPE_DIVAPRO_PCM              4
-#define CARDTYPE_DIVAPICO_ISA             5
-#define CARDTYPE_DIVAPICO_PCM             6
-/* DIVA 2.0 cards */
-#define CARDTYPE_DIVAPRO20_PCI            7
-#define CARDTYPE_DIVA20_PCI               8
-/* S cards */
-#define CARDTYPE_QUADRO_ISA               9
-#define CARDTYPE_S_ISA                    10
-#define CARDTYPE_S_MCA                    11
-#define CARDTYPE_SX_ISA                   12
-#define CARDTYPE_SX_MCA                   13
-#define CARDTYPE_SXN_ISA                  14
-#define CARDTYPE_SXN_MCA                  15
-#define CARDTYPE_SCOM_ISA                 16
-#define CARDTYPE_SCOM_MCA                 17
-#define CARDTYPE_PR_ISA                   18
-#define CARDTYPE_PR_MCA                   19
-/* Diva Server cards (formerly called Maestra, later Amadeo) */
-#define CARDTYPE_MAESTRA_ISA              20
-#define CARDTYPE_MAESTRA_PCI              21
-/* Diva Server cards to be developed (Quadro, Primary rate) */
-#define CARDTYPE_DIVASRV_Q_8M_PCI         22
-#define CARDTYPE_DIVASRV_P_30M_PCI        23
-#define CARDTYPE_DIVASRV_P_2M_PCI         24
-#define CARDTYPE_DIVASRV_P_9M_PCI         25
-/* DIVA 2.0 cards */
-#define CARDTYPE_DIVA20_ISA               26
-#define CARDTYPE_DIVA20U_ISA              27
-#define CARDTYPE_DIVA20U_PCI              28
-#define CARDTYPE_DIVAPRO20_ISA            29
-#define CARDTYPE_DIVAPRO20U_ISA           30
-#define CARDTYPE_DIVAPRO20U_PCI           31
-/* DIVA combi cards (piccola ISDN + rockwell V.34 modem) */
-#define CARDTYPE_DIVAMOBILE_PCM           32
-#define CARDTYPE_TDKGLOBALPRO_PCM         33
-/* DIVA Pro PC OEM card for 'New Media Corporation' */
-#define CARDTYPE_NMC_DIVAPRO_PCM          34
-/* DIVA Pro 2.0 OEM cards for 'British Telecom' */
-#define CARDTYPE_BT_EXLANE_PCI            35
-#define CARDTYPE_BT_EXLANE_ISA            36
-/* DIVA low cost cards, 1st name DIVA 3.0, 2nd DIVA 2.01, 3rd ??? */
-#define CARDTYPE_DIVALOW_ISA              37
-#define CARDTYPE_DIVALOWU_ISA             38
-#define CARDTYPE_DIVALOW_PCI              39
-#define CARDTYPE_DIVALOWU_PCI             40
-/* DIVA combi cards (piccola ISDN + rockwell V.90 modem) */
-#define CARDTYPE_DIVAMOBILE_V90_PCM       41
-#define CARDTYPE_TDKGLOBPRO_V90_PCM       42
-#define CARDTYPE_DIVASRV_P_23M_PCI        43
-#define CARDTYPE_DIVALOW_USB              44
-/* DIVA Audio (CT) family */
-#define CARDTYPE_DIVA_CT_ST               45
-#define CARDTYPE_DIVA_CT_U                46
-#define CARDTYPE_DIVA_CTLITE_ST           47
-#define CARDTYPE_DIVA_CTLITE_U            48
-/* DIVA ISDN plus V.90 series */
-#define CARDTYPE_DIVAISDN_V90_PCM         49
-#define CARDTYPE_DIVAISDN_V90_PCI         50
-#define CARDTYPE_DIVAISDN_TA              51
-/* DIVA Server Voice cards */
-#define CARDTYPE_DIVASRV_VOICE_Q_8M_PCI   52
-/* DIVA Server V2 cards */
-#define CARDTYPE_DIVASRV_Q_8M_V2_PCI      53
-#define CARDTYPE_DIVASRV_P_30M_V2_PCI     54
-/* DIVA Server Voice V2 cards */
-#define CARDTYPE_DIVASRV_VOICE_Q_8M_V2_PCI 55
-#define CARDTYPE_DIVASRV_VOICE_P_30M_V2_PCI 56
-/* Diva LAN */
-#define CARDTYPE_DIVAISDN_LAN             57
-#define CARDTYPE_DIVA_202_PCI_ST          58
-#define CARDTYPE_DIVA_202_PCI_U           59
-#define CARDTYPE_DIVASRV_B_2M_V2_PCI      60
-#define CARDTYPE_DIVASRV_B_2F_PCI         61
-#define CARDTYPE_DIVALOW_USBV2            62
-#define CARDTYPE_DIVASRV_VOICE_B_2M_V2_PCI 63
-#define CARDTYPE_DIVA_PRO_30_PCI_ST       64
-#define CARDTYPE_DIVA_CT_ST_V20           65
-/* Diva Mobile V.90 PC Card and Diva ISDN PC Card */
-#define CARDTYPE_DIVAMOBILE_V2_PCM        66
-#define CARDTYPE_DIVA_V2_PCM              67
-/* Re-badged Diva Pro PC Card */
-#define CARDTYPE_DIVA_PC_CARD             68
-/* next free card type identifier */
-#define CARDTYPE_MAX                      69
-/*
- * The card families
- */
-#define FAMILY_DIVA   1
-#define FAMILY_S   2
-#define FAMILY_MAESTRA  3
-#define FAMILY_MAX   4
-/*
- * The basic card types
- */
-#define CARD_DIVA           1  /* DSP based, old DSP */
-#define CARD_PRO            2  /* DSP based, new DSP */
-#define CARD_PICO           3  /* HSCX based   */
-#define CARD_S    4  /* IDI on board based */
-#define CARD_SX    5  /* IDI on board based */
-#define CARD_SXN   6  /* IDI on board based */
-#define CARD_SCOM   7  /* IDI on board based */
-#define CARD_QUAD   8  /* IDI on board based */
-#define CARD_PR    9  /* IDI on board based */
-#define CARD_MAE         10  /* IDI on board based */
-#define CARD_MAEQ        11  /* IDI on board based */
-#define CARD_MAEP        12  /* IDI on board based */
-#define CARD_DIVALOW  13  /* IPAC based   */
-#define CARD_CT    14  /* SCOUT based          */
-#define CARD_DIVATA   15  /* DIVA TA */
-#define CARD_DIVALAN  16  /* DIVA LAN */
-#define CARD_MAE2         17  /* IDI on board based */
-#define CARD_MAX   18
-/*
- * The internal card types of the S family
- */
-#define CARD_I_NONE   0
-#define CARD_I_S   0
-#define CARD_I_SX   1
-#define CARD_I_SCOM   2
-#define CARD_I_QUAD   3
-#define CARD_I_PR   4
-/*
- * The bus types we support
- */
-#define BUS_ISA             1
-#define BUS_PCM             2
-#define BUS_PCI             3
-#define BUS_MCA             4
-#define BUS_USB             5
-#define BUS_COM    6
-#define BUS_LAN    7
-/*
- * The chips we use for B-channel traffic
- */
-#define CHIP_NONE           0
-#define CHIP_DSP            1
-#define CHIP_HSCX           2
-#define CHIP_IPAC           3
-#define CHIP_SCOUT          4
-#define CHIP_EXTERN         5
-#define CHIP_IPACX          6
-/*
- * The structures where the card properties are aggregated by id
- */
-typedef struct CARD_PROPERTIES
-{   char     *Name;  /* official marketing name     */
-	unsigned short PnPId;  /* plug and play ID (for non PCMIA cards) */
-	unsigned short Version; /* major and minor version no of the card */
-	unsigned char DescType; /* card type to set in the IDI descriptor */
-	unsigned char  Family;  /* basic family of the card     */
-	unsigned short  Features; /* features bits to set in the IDI desc. */
-	unsigned char Card;  /* basic card type       */
-	unsigned char IType;  /* internal type of S cards (read from ram) */
-	unsigned char  Bus;  /* bus type this card is designed for  */
-	unsigned char  Chip;  /* chipset used on card      */
-	unsigned char Adapters; /* number of adapters on card    */
-	unsigned char Channels; /* # of channels per adapter    */
-	unsigned short E_info;  /* # of ram entity info structs per adapter */
-	unsigned short SizeIo;  /* size of IO window per adapter   */
-	unsigned short SizeMem; /* size of memory window per adapter  */
-} CARD_PROPERTIES;
-typedef struct CARD_RESOURCE
-{ unsigned char Int[10];
-	unsigned short IoFirst;
-	unsigned short IoStep;
-	unsigned short IoCnt;
-	unsigned long MemFirst;
-	unsigned long MemStep;
-	unsigned short MemCnt;
-} CARD_RESOURCE;
-/* test if the card of type 't' is a plug & play card */
-#define IS_PNP(t)						\
-	(							\
-		(						\
-			CardProperties[t].Bus != BUS_ISA	\
-			&&					\
-			CardProperties[t].Bus != BUS_MCA	\
-			)					\
-		||						\
-		(						\
-			CardProperties[t].Family != FAMILY_S	\
-			&&					\
-			CardProperties[t].Card != CARD_DIVA	\
-			)					\
-		)
-/* extract IDI Descriptor info for card type 't' (p == DescType/Features) */
-#define IDI_PROP(t, p) (CardProperties[t].p)
-#if CARDTYPE_H_WANT_DATA
-#if CARDTYPE_H_WANT_IDI_DATA
-/* include "di_defs.h" for IDI adapter type and feature flag definitions */
-#include "di_defs.h"
-#else /*!CARDTYPE_H_WANT_IDI_DATA*/
-/* define IDI adapter types and feature flags here to prevent inclusion  */
-#ifndef IDI_ADAPTER_S
-#define IDI_ADAPTER_S           1
-#define IDI_ADAPTER_PR          2
-#define IDI_ADAPTER_DIVA        3
-#define IDI_ADAPTER_MAESTRA     4
-#endif
-#ifndef DI_VOICE
-#define DI_VOICE          0x0 /* obsolete define */
-#define DI_FAX3           0x1
-#define DI_MODEM          0x2
-#define DI_POST           0x4
-#define DI_V110           0x8
-#define DI_V120           0x10
-#define DI_POTS           0x20
-#define DI_CODEC          0x40
-#define DI_MANAGE         0x80
-#define DI_V_42           0x0100
-#define DI_EXTD_FAX       0x0200 /* Extended FAX (ECM, 2D, T.6, Polling) */
-#define DI_AT_PARSER      0x0400 /* Build-in AT Parser in the L2 */
-#define DI_VOICE_OVER_IP  0x0800 /* Voice over IP support */
-#endif
-#endif /*CARDTYPE_H_WANT_IDI_DATA*/
-#define DI_V1x0         (DI_V110 | DI_V120)
-#define DI_NULL         0x0000
-#if defined(SOFT_DSP_SUPPORT)
-#define SOFT_DSP_ADD_FEATURES  (DI_MODEM | DI_FAX3 | DI_AT_PARSER)
-#else
-#define SOFT_DSP_ADD_FEATURES  0
-#endif
-#if defined(SOFT_V110_SUPPORT)
-#define DI_SOFT_V110  DI_V110
-#else
-#define DI_SOFT_V110  0
-#endif
-/*--- CardProperties [Index=CARDTYPE_....] ---------------------------------*/
-CARD_PROPERTIES CardProperties[] =
-{
-	{ /*  0  */
-		"Diva MCA",       0x6336,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3,
-		CARD_DIVA,   CARD_I_NONE, BUS_MCA, CHIP_DSP,
-		1, 2,  0,   8,      0
-	},
-	{ /*  1  */
-		"Diva ISA",       0x0000,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3,
-		CARD_DIVA,   CARD_I_NONE, BUS_ISA, CHIP_DSP,
-		1, 2,  0,   8,      0
-	},
-	{ /*  2  */
-		"Diva/PCM",       0x0000,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3,
-		CARD_DIVA,   CARD_I_NONE, BUS_PCM, CHIP_DSP,
-		1, 2,  0,   8,      0
-	},
-	{ /*  3  */
-		"Diva PRO ISA",      0x0031,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_CODEC,
-		CARD_PRO,   CARD_I_NONE, BUS_ISA, CHIP_DSP,
-		1, 2,  0,   8,      0
-	},
-	{ /*  4  */
-		"Diva PRO PC-Card",     0x0000,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_PRO,   CARD_I_NONE, BUS_PCM, CHIP_DSP,
-		1, 2,   0,   8,      0
-	},
-	{ /*  5  */
-		"Diva PICCOLA ISA",     0x0051,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_ISA, CHIP_HSCX,
-		1, 2,   0,   8,      0
-	},
-	{ /*  6  */
-		"Diva PICCOLA PCM",     0x0000,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_PCM, CHIP_HSCX,
-		1, 2,   0,   8,      0
-	},
-	{ /*  7  */
-		"Diva PRO 2.0 S/T PCI",    0xe001,  0x0200,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_POTS,
-		CARD_PRO,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 2,   0,   8,      0
-	},
-	{ /*  8  */
-		"Diva 2.0 S/T PCI",     0xe002,  0x0200,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | DI_POTS | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_PCI, CHIP_HSCX,
-		1, 2,   0,   8,      0
-	},
-	{ /*  9  */
-		"QUADRO ISA",      0x0000,  0x0100,
-		IDI_ADAPTER_S,  FAMILY_S,  DI_NULL,
-		CARD_QUAD,   CARD_I_QUAD, BUS_ISA, CHIP_NONE,
-		4, 2,   16,  0,  0x800
-	},
-	{ /* 10  */
-		"S ISA",       0x0000,  0x0100,
-		IDI_ADAPTER_S,  FAMILY_S,  DI_CODEC,
-		CARD_S,    CARD_I_S,  BUS_ISA, CHIP_NONE,
-		1, 1,   16,  0,  0x800
-	},
-	{ /* 11  */
-		"S MCA",       0x6a93,  0x0100,
-		IDI_ADAPTER_S,  FAMILY_S,  DI_CODEC,
-		CARD_S,    CARD_I_S,  BUS_MCA, CHIP_NONE,
-		1, 1,   16,  16,  0x400
-	},
-	{ /* 12 */
-		"SX ISA",       0x0000,  0x0100,
-		IDI_ADAPTER_S,  FAMILY_S,  DI_NULL,
-		CARD_SX,   CARD_I_SX,  BUS_ISA, CHIP_NONE,
-		1, 2,  16,  0,  0x800
-	},
-	{ /* 13 */
-		"SX MCA",       0x6a93,  0x0100,
-		IDI_ADAPTER_S,  FAMILY_S,  DI_NULL,
-		CARD_SX,   CARD_I_SX,  BUS_MCA, CHIP_NONE,
-		1, 2,  16,  16,  0x400
-	},
-	{ /* 14 */
-		"SXN ISA",       0x0000,  0x0100,
-		IDI_ADAPTER_S,  FAMILY_S,  DI_NULL,
-		CARD_SXN,   CARD_I_SCOM, BUS_ISA, CHIP_NONE,
-		1, 2,   16,  0,   0x800
-	},
-	{ /* 15 */
-		"SXN MCA",       0x6a93,  0x0100,
-		IDI_ADAPTER_S,  FAMILY_S,  DI_NULL,
-		CARD_SXN,   CARD_I_SCOM, BUS_MCA, CHIP_NONE,
-		1, 2,  16,  16,  0x400
-	},
-	{ /* 16 */
-		"SCOM ISA",       0x0000,  0x0100,
-		IDI_ADAPTER_S,  FAMILY_S,  DI_CODEC,
-		CARD_SCOM,   CARD_I_SCOM, BUS_ISA, CHIP_NONE,
-		1, 2,   16,  0,   0x800
-	},
-	{ /* 17 */
-		"SCOM MCA",       0x6a93,  0x0100,
-		IDI_ADAPTER_S,  FAMILY_S,  DI_CODEC,
-		CARD_SCOM,   CARD_I_SCOM, BUS_MCA, CHIP_NONE,
-		1, 2,  16,  16,  0x400
-	},
-	{ /* 18 */
-		"S2M ISA",       0x0000,  0x0100,
-		IDI_ADAPTER_PR,  FAMILY_S,  DI_NULL,
-		CARD_PR,   CARD_I_PR,  BUS_ISA, CHIP_NONE,
-		1, 30,  256, 0,   0x4000
-	},
-	{ /* 19 */
-		"S2M MCA",       0x6abb,  0x0100,
-		IDI_ADAPTER_PR,  FAMILY_S,  DI_NULL,
-		CARD_PR,   CARD_I_PR,  BUS_MCA, CHIP_NONE,
-		1, 30,  256, 16,  0x4000
-	},
-	{ /* 20 */
-		"Diva Server BRI-2M ISA",   0x0041,  0x0100,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_MAE,   CARD_I_NONE, BUS_ISA, CHIP_DSP,
-		1, 2,   16,  8,  0
-	},
-	{ /* 21 */
-		"Diva Server BRI-2M PCI",   0xE010,  0x0100,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_MAE,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 2,   16,  8,   0
-	},
-	{ /* 22 */
-		"Diva Server 4BRI-8M PCI",   0xE012,  0x0100,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_MAEQ,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		4, 2,   16,  8,   0
-	},
-	{ /* 23 */
-		"Diva Server PRI-30M PCI",   0xE014,  0x0100,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_MAEP,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 30,  256,  8,   0
-	},
-	{ /* 24 */
-		"Diva Server PRI-2M PCI",   0xe014,  0x0100,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_MAEP,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 30,  256,  8,   0
-	},
-	{ /* 25 */
-		"Diva Server PRI-9M PCI",   0x0000,  0x0100,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_MAEP,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 30,     256,  8,   0
-	},
-	{ /* 26 */
-		"Diva 2.0 S/T ISA",     0x0071,  0x0200,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | DI_POTS | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_ISA, CHIP_HSCX,
-		1, 2,  0,   8,   0
-	},
-	{ /* 27 */
-		"Diva 2.0 U ISA",     0x0091,  0x0200,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | DI_POTS | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_ISA, CHIP_HSCX,
-		1, 2,   0,   8,   0
-	},
-	{ /* 28 */
-		"Diva 2.0 U PCI",     0xe004,  0x0200,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | DI_POTS | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_PCI, CHIP_HSCX,
-		1, 2,   0,   8,   0
-	},
-	{ /* 29 */
-		"Diva PRO 2.0 S/T ISA",    0x0061,  0x0200,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_POTS,
-		CARD_PRO,   CARD_I_NONE, BUS_ISA, CHIP_DSP,
-		1, 2,  0,   8,   0
-	},
-	{ /* 30 */
-		"Diva PRO 2.0 U ISA",    0x0081,  0x0200,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_POTS,
-		CARD_PRO,   CARD_I_NONE, BUS_ISA, CHIP_DSP,
-		1, 2,  0,   8,   0
-	},
-	{ /* 31 */
-		"Diva PRO 2.0 U PCI",    0xe003,  0x0200,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_POTS,
-		CARD_PRO,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 2,   0,   8,   0
-	},
-	{ /* 32 */
-		"Diva MOBILE",      0x0000,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_PCM, CHIP_HSCX,
-		1, 2,  0,   8,   0
-	},
-	{ /* 33 */
-		"TDK DFI3600",      0x0000,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_PCM, CHIP_HSCX,
-		1, 2,  0,   8,   0
-	},
-	{ /* 34 (OEM version of 4 - "Diva PRO PC-Card") */
-		"New Media ISDN",     0x0000,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_PRO,   CARD_I_NONE, BUS_PCM, CHIP_DSP,
-		1, 2,   0,   8,   0
-	},
-	{ /* 35 (OEM version of 7 - "Diva PRO 2.0 S/T PCI") */
-		"BT ExLane PCI",     0xe101,  0x0200,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_POTS,
-		CARD_PRO,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 2,   0,   8,   0
-	},
-	{ /* 36 (OEM version of 29 - "Diva PRO 2.0 S/T ISA") */
-		"BT ExLane ISA",     0x1061,  0x0200,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_POTS,
-		CARD_PRO,   CARD_I_NONE, BUS_ISA, CHIP_DSP,
-		1, 2,   0,   8,   0
-	},
-	{ /* 37 */
-		"Diva 2.01 S/T ISA",    0x00A1,  0x0300,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_DIVALOW,  CARD_I_NONE, BUS_ISA, CHIP_IPAC,
-		1, 2,   0,   8,      0
-	},
-	{ /* 38 */
-		"Diva 2.01 U ISA",     0x00B1,  0x0300,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_DIVALOW,  CARD_I_NONE, BUS_ISA, CHIP_IPAC,
-		1, 2,   0,   8,      0
-	},
-	{ /* 39 */
-		"Diva 2.01 S/T PCI",    0xe005,  0x0300,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_DIVALOW,  CARD_I_NONE, BUS_PCI, CHIP_IPAC,
-		1, 2,   0,   8,   0
-	},
-	{ /* 40        no ID yet */
-		"Diva 2.01 U PCI",     0x0000,  0x0300,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_DIVALOW,  CARD_I_NONE, BUS_PCI, CHIP_IPAC,
-		1, 2,   0,   8,   0
-	},
-	{ /* 41 */
-		"Diva MOBILE V.90",     0x0000,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_PCM, CHIP_HSCX,
-		1, 2,  0,   8,   0
-	},
-	{ /* 42 */
-		"TDK DFI3600 V.90",     0x0000,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_PCM, CHIP_HSCX,
-		1, 2,  0,   8,   0
-	},
-	{ /* 43 */
-		"Diva Server PRI-23M PCI",   0xe014,  0x0100,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_MAEP,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 30,  256,  8,   0
-	},
-	{ /* 44 */
-		"Diva 2.01 S/T USB",    0x1000,     0x0300,
-		IDI_ADAPTER_DIVA   , FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_DIVALOW,  CARD_I_NONE, BUS_USB, CHIP_IPAC,
-		1,  2,  0,  8,   0
-	},
-	{ /* 45 */
-		"Diva CT S/T PCI",    0xe006,  0x0300,
-		IDI_ADAPTER_DIVA   , FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_CODEC,
-		CARD_CT,       CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1,  2,  0,  0,   0
-	},
-	{ /* 46 */
-		"Diva CT U PCI",     0xe007,  0x0300,
-		IDI_ADAPTER_DIVA   , FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_CODEC,
-		CARD_CT,       CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1,  2,  0,  0,   0
-	},
-	{ /* 47 */
-		"Diva CT Lite S/T PCI",   0xe008,  0x0300,
-		IDI_ADAPTER_DIVA   , FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_CODEC,
-		CARD_CT,       CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1,  2,  0,  0,   0
-	},
-	{ /* 48 */
-		"Diva CT Lite U PCI",   0xe009,  0x0300,
-		IDI_ADAPTER_DIVA   , FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_CODEC,
-		CARD_CT,       CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1,  2,  0,  0,   0
-	},
-	{ /* 49 */
-		"Diva ISDN+V.90 PC Card", 0x8D8C, 0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_CODEC,
-		CARD_DIVALOW, CARD_I_NONE, BUS_PCM, CHIP_IPAC,
-		1, 2,  0,   8,   0
-	},
-	{ /* 50 */
-		"Diva ISDN+V.90 PCI",    0xe00A,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120  | SOFT_DSP_ADD_FEATURES,
-		CARD_DIVALOW,  CARD_I_NONE, BUS_PCI, CHIP_IPAC,
-		1, 2,   0,   8,   0
-	},
-	{ /* 51 (DivaTA)      no ID */
-		"Diva TA",       0x0000,  0x0300,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V110 | DI_FAX3 | SOFT_DSP_ADD_FEATURES,
-		CARD_DIVATA,  CARD_I_NONE, BUS_COM, CHIP_EXTERN,
-		1, 1,   0,   8,   0
-	},
-	{ /* 52 (Diva Server 4BRI-8M PCI adapter enabled for Voice) */
-		"Diva Server Voice 4BRI-8M PCI", 0xE016,  0x0100,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_VOICE_OVER_IP,
-		CARD_MAEQ,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		4, 2,   16,  8,   0
-	},
-	{ /* 53 (Diva Server 4BRI 2.0 adapter) */
-		"Diva Server 4BRI-8M 2.0 PCI",  0xE013,  0x0200,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_MAEQ,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		4, 2,   16,  8,   0
-	},
-	{ /* 54 (Diva Server PRI 2.0 adapter) */
-		"Diva Server PRI 2.0 PCI",   0xE015,  0x0200,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_MAEP,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 30,  256,  8,   0
-	},
-	{ /* 55 (Diva Server 4BRI-8M 2.0 PCI adapter enabled for Voice) */
-		"Diva Server Voice 4BRI-8M 2.0 PCI", 0xE017,  0x0200,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_VOICE_OVER_IP,
-		CARD_MAEQ,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		4, 2,   16,  8,   0
-	},
-	{ /* 56 (Diva Server PRI 2.0 PCI adapter enabled for Voice) */
-		"Diva Server Voice PRI 2.0 PCI",  0xE019,  0x0200,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_VOICE_OVER_IP,
-		CARD_MAEP,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 30,  256,  8,   0
-	},
-	{
-		/* 57 (DivaLan )      no ID */
-		"Diva LAN",       0x0000,  0x0300,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V110 | DI_FAX3 | SOFT_DSP_ADD_FEATURES,
-		CARD_DIVALAN,  CARD_I_NONE, BUS_LAN, CHIP_EXTERN,
-		1, 1,   0,   8,   0
-	},
-	{ /* 58 */
-		"Diva 2.02 PCI S/T",    0xE00B,  0x0300,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES | DI_SOFT_V110,
-		CARD_DIVALOW,  CARD_I_NONE, BUS_PCI, CHIP_IPACX,
-		1, 2,   0,   8,   0
-	},
-	{ /* 59 */
-		"Diva 2.02 PCI U",     0xE00C,  0x0300,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_DIVALOW,  CARD_I_NONE, BUS_PCI, CHIP_IPACX,
-		1, 2,   0,   8,   0
-	},
-	{ /* 60 */
-		"Diva Server BRI-2M 2.0 PCI",     0xE018,  0x0200,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_MAE2,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 2,   16,  8,   0
-	},
-	{ /* 61  (the previous name was Diva Server BRI-2F 2.0 PCI) */
-		"Diva Server 2FX",                      0xE01A,     0x0200,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_SOFT_V110,
-		CARD_MAE2,          CARD_I_NONE,    BUS_PCI,    CHIP_IPACX,
-		1,  2,      16,     8,   0
-	},
-	{ /* 62 */
-		" Diva ISDN USB 2.0",    0x1003,     0x0300,
-		IDI_ADAPTER_DIVA   , FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_DIVALOW,  CARD_I_NONE, BUS_USB, CHIP_IPACX,
-		1, 2,  0,  8,   0
-	},
-	{ /* 63 (Diva Server BRI-2M 2.0 PCI adapter enabled for Voice) */
-		"Diva Server Voice BRI-2M 2.0 PCI", 0xE01B,  0x0200,
-		IDI_ADAPTER_MAESTRA, FAMILY_MAESTRA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_VOICE_OVER_IP,
-		CARD_MAE2,   CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1, 2,   16,  8,   0
-	},
-	{ /* 64 */
-		"Diva Pro 3.0 PCI",    0xe00d,  0x0300,
-		IDI_ADAPTER_DIVA   , FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM,
-		CARD_PRO,       CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1,  2,  0,  0,   0
-	},
-	{ /* 65 */
-		"Diva ISDN + CT 2.0",    0xE00E,  0x0300,
-		IDI_ADAPTER_DIVA   , FAMILY_DIVA, DI_V1x0 | DI_FAX3 | DI_MODEM | DI_CODEC,
-		CARD_CT,       CARD_I_NONE, BUS_PCI, CHIP_DSP,
-		1,  2,  0,  0,   0
-	},
-	{ /* 66 */
-		"Diva Mobile V.90 PC Card",  0x8331,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_PCM, CHIP_IPACX,
-		1, 2,  0,   8,   0
-	},
-	{ /* 67 */
-		"Diva ISDN PC Card",  0x8311,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_PICO,   CARD_I_NONE, BUS_PCM, CHIP_IPACX,
-		1, 2,  0,   8,   0
-	},
-	{ /* 68 */
-		"Diva ISDN PC Card",  0x0000,  0x0100,
-		IDI_ADAPTER_DIVA, FAMILY_DIVA, DI_V120 | SOFT_DSP_ADD_FEATURES,
-		CARD_PRO,   CARD_I_NONE, BUS_PCM, CHIP_DSP,
-		1, 2,   0,   8,      0
-	},
-};
-#if CARDTYPE_H_WANT_RESOURCE_DATA
-/*--- CardResource [Index=CARDTYPE_....]   ---------------------------(GEI)-*/
-CARD_RESOURCE CardResource[] = {
-/*   Interrupts     IO-Address   Mem-Address */
-	/* 0*/ {  3,4,9,0,0,0,0,0,0,0,   0x200,0x20,16,   0x0,0x0,0   }, // DIVA MCA
-	/* 1*/ {  3,4,9,10,11,12,0,0,0,0,  0x200,0x20,16,   0x0,0x0,0   }, // DIVA ISA
-	/* 2*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA PCMCIA
-	/* 3*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,   0x0,0x0,0   }, // DIVA PRO ISA
-	/* 4*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA PRO PCMCIA
-	/* 5*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,  0x0,0x0,0   }, // DIVA PICCOLA ISA
-	/* 6*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA PICCOLA PCMCIA
-	/* 7*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA PRO 2.0 PCI
-	/* 8*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA 2.0 PCI
-	/* 9*/ {  3,4,5,7,9,10,11,12,0,0,  0x0,0x0,0,   0x80000,0x2000,64 }, // QUADRO ISA
-	/*10*/ {  3,4,9,10,11,12,0,0,0,0,  0x0,0x0,0,   0xc0000,0x2000,16 }, // S ISA
-	/*11*/ {  3,4,9,0,0,0,0,0,0,0,  0xc00,0x10,16,  0xc0000,0x2000,16 }, // S MCA
-	/*12*/ {  3,4,9,10,11,12,0,0,0,0,  0x0,0x0,0,   0xc0000,0x2000,16 }, // SX ISA
-	/*13*/ {  3,4,9,0,0,0,0,0,0,0,  0xc00,0x10,16,  0xc0000,0x2000,16 }, // SX MCA
-	/*14*/ {  3,4,5,7,9,10,11,12,0,0,  0x0,0x0,0,   0x80000,0x0800,256 }, // SXN ISA
-	/*15*/ {  3,4,9,0,0,0,0,0,0,0,  0xc00,0x10,16,  0xc0000,0x2000,16 }, // SXN MCA
-	/*16*/ {  3,4,5,7,9,10,11,12,0,0,  0x0,0x0,0,   0x80000,0x0800,256 }, // SCOM ISA
-	/*17*/ {  3,4,9,0,0,0,0,0,0,0,  0xc00,0x10,16,  0xc0000,0x2000,16 }, // SCOM MCA
-	/*18*/ {  3,4,5,7,9,10,11,12,0,0,  0x0,0x0,0,   0xc0000,0x4000,16 }, // S2M ISA
-	/*19*/ {  3,4,9,0,0,0,0,0,0,0,  0xc00,0x10,16,  0xc0000,0x4000,16 }, // S2M MCA
-	/*20*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,  0x0,0x0,0   }, // MAESTRA ISA
-	/*21*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // MAESTRA PCI
-	/*22*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,  0x0,0x0,0   }, // MAESTRA QUADRO ISA
-	/*23*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x20,2048,  0x0,0x0,0   }, // MAESTRA QUADRO PCI
-	/*24*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,  0x0,0x0,0   }, // MAESTRA PRIMARY ISA
-	/*25*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // MAESTRA PRIMARY PCI
-	/*26*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,  0x0,0x0,0   }, // DIVA 2.0 ISA
-	/*27*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,  0x0,0x0,0   }, // DIVA 2.0 /U ISA
-	/*28*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA 2.0 /U PCI
-	/*29*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,   0x0,0x0,0   }, // DIVA PRO 2.0 ISA
-	/*30*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,   0x0,0x0,0   }, // DIVA PRO 2.0 /U ISA
-	/*31*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA PRO 2.0 /U PCI
-	/*32*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA MOBILE
-	/*33*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // TDK DFI3600 (same as DIVA MOBILE [32])
-	/*34*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // New Media ISDN (same as DIVA PRO PCMCIA [4])
-	/*35*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // BT ExLane PCI (same as DIVA PRO 2.0 PCI [7])
-	/*36*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,   0x0,0x0,0   }, // BT ExLane ISA (same as DIVA PRO 2.0 ISA [29])
-	/*37*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,  0x0,0x0,0   }, // DIVA 2.01 S/T ISA
-	/*38*/ {  3,5,7,9,10,11,12,14,15,0, 0x200,0x20,16,  0x0,0x0,0   }, // DIVA 2.01 U ISA
-	/*39*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA 2.01 S/T PCI
-	/*40*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA 2.01 U PCI
-	/*41*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA MOBILE V.90
-	/*42*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // TDK DFI3600 V.90 (same as DIVA MOBILE V.90 [39])
-	/*43*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x20,2048,  0x0,0x0,0   }, // DIVA Server PRI-23M PCI
-	/*44*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA 2.01 S/T USB
-	/*45*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA CT S/T PCI
-	/*46*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA CT U PCI
-	/*47*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA CT Lite S/T PCI
-	/*48*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA CT Lite U PCI
-	/*49*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA ISDN+V.90 PC Card
-	/*50*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA ISDN+V.90 PCI
-	/*51*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA TA
-	/*52*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x20,2048,  0x0,0x0,0   }, // MAESTRA VOICE QUADRO PCI
-	/*53*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x20,2048,  0x0,0x0,0   }, // MAESTRA VOICE QUADRO PCI
-	/*54*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // MAESTRA VOICE PRIMARY PCI
-	/*55*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x20,2048,  0x0,0x0,0   }, // MAESTRA VOICE QUADRO PCI
-	/*56*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // MAESTRA VOICE PRIMARY PCI
-	/*57*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA LAN
-	/*58*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA 2.02 S/T PCI
-	/*59*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA 2.02 U PCI
-	/*60*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // Diva Server BRI-2M 2.0 PCI
-	/*61*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // Diva Server BRI-2F PCI
-	/*62*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA 2.01 S/T USB
-	/*63*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // Diva Server Voice BRI-2M 2.0 PCI
-	/*64*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA 3.0 PCI
-	/*65*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA CT S/T PCI V2.0
-	/*66*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA Mobile V.90 PC Card
-	/*67*/ {  0,0,0,0,0,0,0,0,0,0,  0x0,0x0,0,   0x0,0x0,0   }, // DIVA ISDN PC Card
-	/*68*/ {  3,4,5,7,9,10,11,12,14,15, 0x0,0x8,8192,  0x0,0x0,0   }, // DIVA ISDN PC Card
-};
-#endif /*CARDTYPE_H_WANT_RESOURCE_DATA*/
-#else /*!CARDTYPE_H_WANT_DATA*/
-extern CARD_PROPERTIES  CardProperties[];
-extern CARD_RESOURCE  CardResource[];
-#endif /*CARDTYPE_H_WANT_DATA*/
-/*
- * all existing download files
- */
-#define CARD_DSP_CNT  5
-#define CARD_PROT_CNT  9
-#define CARD_FT_UNKNOWN     0
-#define CARD_FT_B   1
-#define CARD_FT_D   2
-#define CARD_FT_S   3
-#define CARD_FT_M   4
-#define CARD_FT_NEW_DSP_COMBIFILE 5  /* File format of new DSP code (the DSP code powered by Telindus) */
-#define CARD_FILE_NONE      0
-#define CARD_B_S   1
-#define CARD_B_P   2
-#define CARD_D_K1   3
-#define CARD_D_K2   4
-#define CARD_D_H   5
-#define CARD_D_V   6
-#define CARD_D_M   7
-#define CARD_D_F   8
-#define CARD_P_S_E   9
-#define CARD_P_S_1   10
-#define CARD_P_S_B   11
-#define CARD_P_S_F   12
-#define CARD_P_S_A   13
-#define CARD_P_S_N   14
-#define CARD_P_S_5   15
-#define CARD_P_S_J   16
-#define CARD_P_SX_E   17
-#define CARD_P_SX_1   18
-#define CARD_P_SX_B   19
-#define CARD_P_SX_F   20
-#define CARD_P_SX_A   21
-#define CARD_P_SX_N   22
-#define CARD_P_SX_5   23
-#define CARD_P_SX_J   24
-#define CARD_P_SY_E   25
-#define CARD_P_SY_1   26
-#define CARD_P_SY_B   27
-#define CARD_P_SY_F   28
-#define CARD_P_SY_A   29
-#define CARD_P_SY_N   30
-#define CARD_P_SY_5   31
-#define CARD_P_SY_J   32
-#define CARD_P_SQ_E   33
-#define CARD_P_SQ_1   34
-#define CARD_P_SQ_B   35
-#define CARD_P_SQ_F   36
-#define CARD_P_SQ_A   37
-#define CARD_P_SQ_N   38
-#define CARD_P_SQ_5   39
-#define CARD_P_SQ_J   40
-#define CARD_P_P_E   41
-#define CARD_P_P_1   42
-#define CARD_P_P_B   43
-#define CARD_P_P_F   44
-#define CARD_P_P_A   45
-#define CARD_P_P_N   46
-#define CARD_P_P_5   47
-#define CARD_P_P_J   48
-#define CARD_P_M_E   49
-#define CARD_P_M_1   50
-#define CARD_P_M_B   51
-#define CARD_P_M_F   52
-#define CARD_P_M_A   53
-#define CARD_P_M_N   54
-#define CARD_P_M_5   55
-#define CARD_P_M_J   56
-#define CARD_P_S_S   57
-#define CARD_P_SX_S   58
-#define CARD_P_SY_S   59
-#define CARD_P_SQ_S   60
-#define CARD_P_P_S   61
-#define CARD_P_M_S   62
-#define CARD_D_NEW_DSP_COMBIFILE 63
-typedef struct CARD_FILES_DATA
-{
-	char *Name;
-	unsigned char  Type;
-}
-	CARD_FILES_DATA;
-typedef struct CARD_FILES
-{
-	unsigned char  Boot;
-	unsigned char  Dsp[CARD_DSP_CNT];
-	unsigned char  DspTelindus;
-	unsigned char  Prot[CARD_PROT_CNT];
-}
-	CARD_FILES;
-#if CARDTYPE_H_WANT_DATA
-#if CARDTYPE_H_WANT_FILE_DATA
-CARD_FILES_DATA CardFData[] = {
-// Filename   Filetype
-	0,     CARD_FT_UNKNOWN,
-	"didnload.bin",  CARD_FT_B,
-	"diprload.bin",  CARD_FT_B,
-	"didiva.bin",  CARD_FT_D,
-	"didivapp.bin",  CARD_FT_D,
-	"dihscx.bin",  CARD_FT_D,
-	"div110.bin",  CARD_FT_D,
-	"dimodem.bin",  CARD_FT_D,
-	"difax.bin",  CARD_FT_D,
-	"di_etsi.bin",  CARD_FT_S,
-	"di_1tr6.bin",  CARD_FT_S,
-	"di_belg.bin",  CARD_FT_S,
-	"di_franc.bin",  CARD_FT_S,
-	"di_atel.bin",  CARD_FT_S,
-	"di_ni.bin",  CARD_FT_S,
-	"di_5ess.bin",  CARD_FT_S,
-	"di_japan.bin",  CARD_FT_S,
-	"di_etsi.sx",  CARD_FT_S,
-	"di_1tr6.sx",  CARD_FT_S,
-	"di_belg.sx",  CARD_FT_S,
-	"di_franc.sx",  CARD_FT_S,
-	"di_atel.sx",  CARD_FT_S,
-	"di_ni.sx",   CARD_FT_S,
-	"di_5ess.sx",  CARD_FT_S,
-	"di_japan.sx",  CARD_FT_S,
-	"di_etsi.sy",  CARD_FT_S,
-	"di_1tr6.sy",  CARD_FT_S,
-	"di_belg.sy",  CARD_FT_S,
-	"di_franc.sy",  CARD_FT_S,
-	"di_atel.sy",  CARD_FT_S,
-	"di_ni.sy",   CARD_FT_S,
-	"di_5ess.sy",  CARD_FT_S,
-	"di_japan.sy",  CARD_FT_S,
-	"di_etsi.sq",  CARD_FT_S,
-	"di_1tr6.sq",  CARD_FT_S,
-	"di_belg.sq",  CARD_FT_S,
-	"di_franc.sq",  CARD_FT_S,
-	"di_atel.sq",  CARD_FT_S,
-	"di_ni.sq",   CARD_FT_S,
-	"di_5ess.sq",  CARD_FT_S,
-	"di_japan.sq",  CARD_FT_S,
-	"di_etsi.p",  CARD_FT_S,
-	"di_1tr6.p",  CARD_FT_S,
-	"di_belg.p",  CARD_FT_S,
-	"di_franc.p",  CARD_FT_S,
-	"di_atel.p",  CARD_FT_S,
-	"di_ni.p",   CARD_FT_S,
-	"di_5ess.p",  CARD_FT_S,
-	"di_japan.p",  CARD_FT_S,
-	"di_etsi.sm",  CARD_FT_M,
-	"di_1tr6.sm",  CARD_FT_M,
-	"di_belg.sm",  CARD_FT_M,
-	"di_franc.sm",  CARD_FT_M,
-	"di_atel.sm",  CARD_FT_M,
-	"di_ni.sm",   CARD_FT_M,
-	"di_5ess.sm",  CARD_FT_M,
-	"di_japan.sm",  CARD_FT_M,
-	"di_swed.bin",  CARD_FT_S,
-	"di_swed.sx",  CARD_FT_S,
-	"di_swed.sy",  CARD_FT_S,
-	"di_swed.sq",  CARD_FT_S,
-	"di_swed.p",  CARD_FT_S,
-	"di_swed.sm",  CARD_FT_M,
-	"didspdld.bin",     CARD_FT_NEW_DSP_COMBIFILE
-};
-CARD_FILES CardFiles[] =
-{
-	{ /* CARD_UNKNOWN */
-		CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE
-	},
-	{ /* CARD_DIVA */
-		CARD_FILE_NONE,
-		CARD_D_K1, CARD_D_H, CARD_D_V, CARD_FILE_NONE, CARD_D_F,
-		CARD_D_NEW_DSP_COMBIFILE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE
-	},
-	{ /* CARD_PRO  */
-		CARD_FILE_NONE,
-		CARD_D_K2, CARD_D_H, CARD_D_V, CARD_D_M, CARD_D_F,
-		CARD_D_NEW_DSP_COMBIFILE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE
-	},
-	{ /* CARD_PICO */
-		CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE
-	},
-	{ /* CARD_S    */
-		CARD_B_S,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE,
-		CARD_P_S_E, CARD_P_S_1, CARD_P_S_B, CARD_P_S_F,
-		CARD_P_S_A, CARD_P_S_N, CARD_P_S_5, CARD_P_S_J,
-		CARD_P_S_S
-	},
-	{ /* CARD_SX   */
-		CARD_B_S,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE,
-		CARD_P_SX_E, CARD_P_SX_1, CARD_P_SX_B, CARD_P_SX_F,
-		CARD_P_SX_A, CARD_P_SX_N, CARD_P_SX_5, CARD_P_SX_J,
-		CARD_P_SX_S
-	},
-	{ /* CARD_SXN  */
-		CARD_B_S,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE,
-		CARD_P_SY_E, CARD_P_SY_1, CARD_P_SY_B, CARD_P_SY_F,
-		CARD_P_SY_A, CARD_P_SY_N, CARD_P_SY_5, CARD_P_SY_J,
-		CARD_P_SY_S
-	},
-	{ /* CARD_SCOM */
-		CARD_B_S,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE,
-		CARD_P_SY_E, CARD_P_SY_1, CARD_P_SY_B, CARD_P_SY_F,
-		CARD_P_SY_A, CARD_P_SY_N, CARD_P_SY_5, CARD_P_SY_J,
-		CARD_P_SY_S
-	},
-	{ /* CARD_QUAD */
-		CARD_B_S,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE,
-		CARD_P_SQ_E, CARD_P_SQ_1, CARD_P_SQ_B, CARD_P_SQ_F,
-		CARD_P_SQ_A, CARD_P_SQ_N, CARD_P_SQ_5, CARD_P_SQ_J,
-		CARD_P_SQ_S
-	},
-	{ /* CARD_PR   */
-		CARD_B_P,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE,
-		CARD_P_P_E, CARD_P_P_1, CARD_P_P_B, CARD_P_P_F,
-		CARD_P_P_A, CARD_P_P_N, CARD_P_P_5, CARD_P_P_J,
-		CARD_P_P_S
-	},
-	{ /* CARD_MAE  */
-		CARD_FILE_NONE,
-		CARD_D_K2, CARD_D_H, CARD_D_V, CARD_D_M, CARD_D_F,
-		CARD_D_NEW_DSP_COMBIFILE,
-		CARD_P_M_E, CARD_P_M_1, CARD_P_M_B, CARD_P_M_F,
-		CARD_P_M_A, CARD_P_M_N, CARD_P_M_5, CARD_P_M_J,
-		CARD_P_M_S
-	},
-	{ /* CARD_MAEQ */  /* currently not supported */
-		CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE
-	},
-	{ /* CARD_MAEP */  /* currently not supported */
-		CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE, CARD_FILE_NONE,
-		CARD_FILE_NONE
-	}
-};
-#endif /*CARDTYPE_H_WANT_FILE_DATA*/
-#else /*!CARDTYPE_H_WANT_DATA*/
-extern CARD_FILES_DATA  CardFData[];
-extern CARD_FILES   CardFiles[];
-#endif /*CARDTYPE_H_WANT_DATA*/
-#endif /* _CARDTYPE_H_ */
diff --git a/drivers/isdn/hardware/eicon/cp_vers.h b/drivers/isdn/hardware/eicon/cp_vers.h
deleted file mode 100644
index c97230c60e71..000000000000
--- a/drivers/isdn/hardware/eicon/cp_vers.h
+++ /dev/null
@@ -1,26 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-static char diva_capi_common_code_build[] = "102-28";
diff --git a/drivers/isdn/hardware/eicon/dadapter.c b/drivers/isdn/hardware/eicon/dadapter.c
deleted file mode 100644
index 51420999418d..000000000000
--- a/drivers/isdn/hardware/eicon/dadapter.c
+++ /dev/null
@@ -1,364 +0,0 @@
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#include "platform.h"
-#include "pc.h"
-#include "debuglib.h"
-#include "di_defs.h"
-#include "divasync.h"
-#include "dadapter.h"
-/* --------------------------------------------------------------------------
-   Adapter array change notification framework
-   -------------------------------------------------------------------------- */
-typedef struct _didd_adapter_change_notification {
-	didd_adapter_change_callback_t callback;
-	void IDI_CALL_ENTITY_T *context;
-} didd_adapter_change_notification_t,				\
-	* IDI_CALL_ENTITY_T pdidd_adapter_change_notification_t;
-#define DIVA_DIDD_MAX_NOTIFICATIONS 256
-static didd_adapter_change_notification_t	\
-NotificationTable[DIVA_DIDD_MAX_NOTIFICATIONS];
-/* --------------------------------------------------------------------------
-   Array to held adapter information
-   -------------------------------------------------------------------------- */
-static DESCRIPTOR  HandleTable[NEW_MAX_DESCRIPTORS];
-static dword Adapters = 0; /* Number of adapters */
-/* --------------------------------------------------------------------------
-   Shadow IDI_DIMAINT
-   and 'shadow' debug stuff
-   -------------------------------------------------------------------------- */
-static void no_printf(unsigned char *format, ...)
-{
-#ifdef EBUG
-	va_list ap;
-	va_start(ap, format);
-	debug((format, ap));
-	va_end(ap);
-#endif
-}
-
-/* -------------------------------------------------------------------------
-   Portable debug Library
-   ------------------------------------------------------------------------- */
-#include "debuglib.c"
-
-static DESCRIPTOR  MAdapter =  {IDI_DIMAINT, /* Adapter Type */
-				0x00,     /* Channels */
-				0x0000,    /* Features */
-				(IDI_CALL)no_printf};
-/* --------------------------------------------------------------------------
-   DAdapter. Only IDI clients with buffer, that is huge enough to
-   get all descriptors will receive information about DAdapter
-   { byte type, byte channels, word features, IDI_CALL request }
-   -------------------------------------------------------------------------- */
-static void IDI_CALL_LINK_T diva_dadapter_request(ENTITY IDI_CALL_ENTITY_T *);
-static DESCRIPTOR  DAdapter =  {IDI_DADAPTER, /* Adapter Type */
-				0x00,     /* Channels */
-				0x0000,    /* Features */
-				diva_dadapter_request };
-/* --------------------------------------------------------------------------
-   LOCALS
-   -------------------------------------------------------------------------- */
-static dword diva_register_adapter_callback(\
-	didd_adapter_change_callback_t callback,
-	void IDI_CALL_ENTITY_T *context);
-static void diva_remove_adapter_callback(dword handle);
-static void diva_notify_adapter_change(DESCRIPTOR *d, int removal);
-static diva_os_spin_lock_t didd_spin;
-/* --------------------------------------------------------------------------
-   Should be called as first step, after driver init
-   -------------------------------------------------------------------------- */
-void diva_didd_load_time_init(void) {
-	memset(&HandleTable[0], 0x00, sizeof(HandleTable));
-	memset(&NotificationTable[0], 0x00, sizeof(NotificationTable));
-	diva_os_initialize_spin_lock(&didd_spin, "didd");
-}
-/* --------------------------------------------------------------------------
-   Should be called as last step, if driver does unload
-   -------------------------------------------------------------------------- */
-void diva_didd_load_time_finit(void) {
-	diva_os_destroy_spin_lock(&didd_spin, "didd");
-}
-/* --------------------------------------------------------------------------
-   Called in order to register new adapter in adapter array
-   return adapter handle (> 0) on success
-   return -1 adapter array overflow
-   -------------------------------------------------------------------------- */
-static int diva_didd_add_descriptor(DESCRIPTOR *d) {
-	diva_os_spin_lock_magic_t      irql;
-	int i;
-	if (d->type == IDI_DIMAINT) {
-		if (d->request) {
-			MAdapter.request = d->request;
-			dprintf = (DIVA_DI_PRINTF)d->request;
-			diva_notify_adapter_change(&MAdapter, 0); /* Inserted */
-			DBG_TRC(("DIMAINT registered, dprintf=%08x", d->request))
-				} else {
-			DBG_TRC(("DIMAINT removed"))
-				diva_notify_adapter_change(&MAdapter, 1); /* About to remove */
-			MAdapter.request = (IDI_CALL)no_printf;
-			dprintf = no_printf;
-		}
-		return (NEW_MAX_DESCRIPTORS);
-	}
-	for (i = 0; i < NEW_MAX_DESCRIPTORS; i++) {
-		diva_os_enter_spin_lock(&didd_spin, &irql, "didd_add");
-		if (HandleTable[i].type == 0) {
-			memcpy(&HandleTable[i], d, sizeof(*d));
-			Adapters++;
-			diva_os_leave_spin_lock(&didd_spin, &irql, "didd_add");
-			diva_notify_adapter_change(d, 0); /* we have new adapter */
-			DBG_TRC(("Add adapter[%d], request=%08x", (i + 1), d->request))
-				return (i + 1);
-		}
-		diva_os_leave_spin_lock(&didd_spin, &irql, "didd_add");
-	}
-	DBG_ERR(("Can't add adapter, out of resources"))
-		return (-1);
-}
-/* --------------------------------------------------------------------------
-   Called in order to remove one registered adapter from array
-   return adapter handle (> 0) on success
-   return 0 on success
-   -------------------------------------------------------------------------- */
-static int diva_didd_remove_descriptor(IDI_CALL request) {
-	diva_os_spin_lock_magic_t      irql;
-	int i;
-	if (request == MAdapter.request) {
-		DBG_TRC(("DIMAINT removed"))
-			dprintf = no_printf;
-		diva_notify_adapter_change(&MAdapter, 1); /* About to remove */
-		MAdapter.request = (IDI_CALL)no_printf;
-		return (0);
-	}
-	for (i = 0; (Adapters && (i < NEW_MAX_DESCRIPTORS)); i++) {
-		if (HandleTable[i].request == request) {
-			diva_notify_adapter_change(&HandleTable[i], 1); /* About to remove */
-			diva_os_enter_spin_lock(&didd_spin, &irql, "didd_rm");
-			memset(&HandleTable[i], 0x00, sizeof(HandleTable[0]));
-			Adapters--;
-			diva_os_leave_spin_lock(&didd_spin, &irql, "didd_rm");
-			DBG_TRC(("Remove adapter[%d], request=%08x", (i + 1), request))
-				return (0);
-		}
-	}
-	DBG_ERR(("Invalid request=%08x, can't remove adapter", request))
-		return (-1);
-}
-/* --------------------------------------------------------------------------
-   Read adapter array
-   return 1 if not enough space to save all available adapters
-   -------------------------------------------------------------------------- */
-static int diva_didd_read_adapter_array(DESCRIPTOR *buffer, int length) {
-	diva_os_spin_lock_magic_t      irql;
-	int src, dst;
-	memset(buffer, 0x00, length);
-	length /= sizeof(DESCRIPTOR);
-	DBG_TRC(("DIDD_Read, space = %d, Adapters = %d", length, Adapters + 2))
-
-		diva_os_enter_spin_lock(&didd_spin, &irql, "didd_read");
-	for (src = 0, dst = 0;
-	     (Adapters && (src < NEW_MAX_DESCRIPTORS) && (dst < length));
-	     src++) {
-		if (HandleTable[src].type) {
-			memcpy(&buffer[dst], &HandleTable[src], sizeof(DESCRIPTOR));
-			dst++;
-		}
-	}
-	diva_os_leave_spin_lock(&didd_spin, &irql, "didd_read");
-	if (dst < length) {
-		memcpy(&buffer[dst], &MAdapter, sizeof(DESCRIPTOR));
-		dst++;
-	} else {
-		DBG_ERR(("Can't write DIMAINT. Array too small"))
-			}
-	if (dst < length) {
-		memcpy(&buffer[dst], &DAdapter, sizeof(DESCRIPTOR));
-		dst++;
-	} else {
-		DBG_ERR(("Can't write DADAPTER. Array too small"))
-			}
-	DBG_TRC(("Read %d adapters", dst))
-		return (dst == length);
-}
-/* --------------------------------------------------------------------------
-   DAdapter request function.
-   This function does process only synchronous requests, and is used
-   for reception/registration of new interfaces
-   -------------------------------------------------------------------------- */
-static void IDI_CALL_LINK_T diva_dadapter_request(	\
-	ENTITY IDI_CALL_ENTITY_T *e) {
-	IDI_SYNC_REQ *syncReq = (IDI_SYNC_REQ *)e;
-	if (e->Req) { /* We do not process it, also return error */
-		e->Rc = OUT_OF_RESOURCES;
-		DBG_ERR(("Can't process async request, Req=%02x", e->Req))
-			return;
-	}
-	/*
-	  So, we process sync request
-	*/
-	switch (e->Rc) {
-	case IDI_SYNC_REQ_DIDD_REGISTER_ADAPTER_NOTIFY: {
-		diva_didd_adapter_notify_t *pinfo = &syncReq->didd_notify.info;
-		pinfo->handle = diva_register_adapter_callback(		\
-			(didd_adapter_change_callback_t)pinfo->callback,
-			(void IDI_CALL_ENTITY_T *)pinfo->context);
-		e->Rc = 0xff;
-	} break;
-	case IDI_SYNC_REQ_DIDD_REMOVE_ADAPTER_NOTIFY: {
-		diva_didd_adapter_notify_t *pinfo = &syncReq->didd_notify.info;
-		diva_remove_adapter_callback(pinfo->handle);
-		e->Rc = 0xff;
-	} break;
-	case IDI_SYNC_REQ_DIDD_ADD_ADAPTER: {
-		diva_didd_add_adapter_t *pinfo = &syncReq->didd_add_adapter.info;
-		if (diva_didd_add_descriptor((DESCRIPTOR *)pinfo->descriptor) < 0) {
-			e->Rc = OUT_OF_RESOURCES;
-		} else {
-			e->Rc = 0xff;
-		}
-	} break;
-	case IDI_SYNC_REQ_DIDD_REMOVE_ADAPTER: {
-		diva_didd_remove_adapter_t *pinfo = &syncReq->didd_remove_adapter.info;
-		if (diva_didd_remove_descriptor((IDI_CALL)pinfo->p_request) < 0) {
-			e->Rc = OUT_OF_RESOURCES;
-		} else {
-			e->Rc = 0xff;
-		}
-	} break;
-	case IDI_SYNC_REQ_DIDD_READ_ADAPTER_ARRAY: {
-		diva_didd_read_adapter_array_t *pinfo =\
-			&syncReq->didd_read_adapter_array.info;
-		if (diva_didd_read_adapter_array((DESCRIPTOR *)pinfo->buffer,
-						  (int)pinfo->length)) {
-			e->Rc = OUT_OF_RESOURCES;
-		} else {
-			e->Rc = 0xff;
-		}
-	} break;
-	default:
-		DBG_ERR(("Can't process sync request, Req=%02x", e->Rc))
-			e->Rc = OUT_OF_RESOURCES;
-	}
-}
-/* --------------------------------------------------------------------------
-   IDI client does register his notification function
-   -------------------------------------------------------------------------- */
-static dword diva_register_adapter_callback(		\
-	didd_adapter_change_callback_t callback,
-	void IDI_CALL_ENTITY_T *context) {
-	diva_os_spin_lock_magic_t irql;
-	dword i;
-
-	for (i = 0; i < DIVA_DIDD_MAX_NOTIFICATIONS; i++) {
-		diva_os_enter_spin_lock(&didd_spin, &irql, "didd_nfy_add");
-		if (!NotificationTable[i].callback) {
-			NotificationTable[i].callback = callback;
-			NotificationTable[i].context = context;
-			diva_os_leave_spin_lock(&didd_spin, &irql, "didd_nfy_add");
-			DBG_TRC(("Register adapter notification[%d]=%08x", i + 1, callback))
-				return (i + 1);
-		}
-		diva_os_leave_spin_lock(&didd_spin, &irql, "didd_nfy_add");
-	}
-	DBG_ERR(("Can't register adapter notification, overflow"))
-		return (0);
-}
-/* --------------------------------------------------------------------------
-   IDI client does register his notification function
-   -------------------------------------------------------------------------- */
-static void diva_remove_adapter_callback(dword handle) {
-	diva_os_spin_lock_magic_t irql;
-	if (handle && ((--handle) < DIVA_DIDD_MAX_NOTIFICATIONS)) {
-		diva_os_enter_spin_lock(&didd_spin, &irql, "didd_nfy_rm");
-		NotificationTable[handle].callback = NULL;
-		NotificationTable[handle].context  = NULL;
-		diva_os_leave_spin_lock(&didd_spin, &irql, "didd_nfy_rm");
-		DBG_TRC(("Remove adapter notification[%d]", (int)(handle + 1)))
-			return;
-	}
-	DBG_ERR(("Can't remove adapter notification, handle=%d", handle))
-		}
-/* --------------------------------------------------------------------------
-   Notify all client about adapter array change
-   Does suppose following behavior in the client side:
-   Step 1: Redister Notification
-   Step 2: Read Adapter Array
-   -------------------------------------------------------------------------- */
-static void diva_notify_adapter_change(DESCRIPTOR *d, int removal) {
-	int i, do_notify;
-	didd_adapter_change_notification_t nfy;
-	diva_os_spin_lock_magic_t irql;
-	for (i = 0; i < DIVA_DIDD_MAX_NOTIFICATIONS; i++) {
-		do_notify = 0;
-		diva_os_enter_spin_lock(&didd_spin, &irql, "didd_nfy");
-		if (NotificationTable[i].callback) {
-			memcpy(&nfy, &NotificationTable[i], sizeof(nfy));
-			do_notify = 1;
-		}
-		diva_os_leave_spin_lock(&didd_spin, &irql, "didd_nfy");
-		if (do_notify) {
-			(*(nfy.callback))(nfy.context, d, removal);
-		}
-	}
-}
-/* --------------------------------------------------------------------------
-   For all systems, that are linked by Kernel Mode Linker this is ONLY one
-   function thet should be exported by this device driver
-   IDI clients should look for IDI_DADAPTER, and use request function
-   of this adapter (sync request) in order to receive appropriate services:
-   - add new adapter
-   - remove existing adapter
-   - add adapter array notification
-   - remove adapter array notification
-   (read adapter is redundant in this case)
-   INPUT:
-   buffer - pointer to buffer that will receive adapter array
-   length  - length (in bytes) of space in buffer
-   OUTPUT:
-   Adapter array will be written to memory described by 'buffer'
-   If the last adapter seen in the returned adapter array is
-   IDI_DADAPTER or if last adapter in array does have type '0', then
-   it was enougth space in buffer to accommodate all available
-   adapter descriptors
-   *NOTE 1 (debug interface):
-   The IDI adapter of type 'IDI_DIMAINT' does register as 'request'
-   famous 'dprintf' function (of type DI_PRINTF, please look
-   include/debuglib.c and include/debuglib.h) for details.
-   So dprintf is not exported from module debug module directly,
-   instead of this IDI_DIMAINT is registered.
-   Module load order will receive in this case:
-   1. DIDD (this file)
-   2. DIMAINT does load and register 'IDI_DIMAINT', at this step
-   DIDD should be able to get 'dprintf', save it, and
-   register with DIDD by means of 'dprintf' function.
-   3. any other driver is loaded and is able to access adapter array
-   and debug interface
-   This approach does allow to load/unload debug interface on demand,
-   and save memory, it it is necessary.
-   -------------------------------------------------------------------------- */
-void IDI_CALL_LINK_T DIVA_DIDD_Read(void IDI_CALL_ENTITY_T *buffer,
-				    int length) {
-	diva_didd_read_adapter_array(buffer, length);
-}
diff --git a/drivers/isdn/hardware/eicon/dadapter.h b/drivers/isdn/hardware/eicon/dadapter.h
deleted file mode 100644
index 5540f46a5be3..000000000000
--- a/drivers/isdn/hardware/eicon/dadapter.h
+++ /dev/null
@@ -1,34 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_DIDD_DADAPTER_INC__
-#define __DIVA_DIDD_DADAPTER_INC__
-
-void diva_didd_load_time_init(void);
-void diva_didd_load_time_finit(void);
-
-#define NEW_MAX_DESCRIPTORS     64
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/debug.c b/drivers/isdn/hardware/eicon/debug.c
deleted file mode 100644
index 301788115c4f..000000000000
--- a/drivers/isdn/hardware/eicon/debug.c
+++ /dev/null
@@ -1,2128 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "platform.h"
-#include "pc.h"
-#include "di_defs.h"
-#include "debug_if.h"
-#include "divasync.h"
-#include "kst_ifc.h"
-#include "maintidi.h"
-#include "man_defs.h"
-
-/*
-  LOCALS
-*/
-#define DBG_MAGIC (0x47114711L)
-
-static void DI_register(void *arg);
-static void DI_deregister(pDbgHandle hDbg);
-static void DI_format(int do_lock, word id, int type, char *format, va_list argument_list);
-static void DI_format_locked(word id, int type, char *format, va_list argument_list);
-static void DI_format_old(word id, char *format, va_list ap) { }
-static void DiProcessEventLog(unsigned short id, unsigned long msgID, va_list ap) { }
-static void single_p(byte *P, word *PLength, byte Id);
-static void diva_maint_xdi_cb(ENTITY *e);
-static word SuperTraceCreateReadReq(byte *P, const char *path);
-static int diva_mnt_cmp_nmbr(const char *nmbr);
-static void diva_free_dma_descriptor(IDI_CALL request, int nr);
-static int diva_get_dma_descriptor(IDI_CALL request, dword *dma_magic);
-void diva_mnt_internal_dprintf(dword drv_id, dword type, char *p, ...);
-
-static dword MaxDumpSize = 256;
-static dword MaxXlogSize = 2 + 128;
-static char  TraceFilter[DIVA_MAX_SELECTIVE_FILTER_LENGTH + 1];
-static int TraceFilterIdent   = -1;
-static int TraceFilterChannel = -1;
-
-typedef struct _diva_maint_client {
-	dword       sec;
-	dword       usec;
-	pDbgHandle  hDbg;
-	char        drvName[128];
-	dword       dbgMask;
-	dword       last_dbgMask;
-	IDI_CALL    request;
-	_DbgHandle_ Dbg;
-	int         logical;
-	int         channels;
-	diva_strace_library_interface_t *pIdiLib;
-	BUFFERS     XData;
-	char        xbuffer[2048 + 512];
-	byte        *pmem;
-	int         request_pending;
-	int         dma_handle;
-} diva_maint_client_t;
-static diva_maint_client_t clients[MAX_DESCRIPTORS];
-
-static void diva_change_management_debug_mask(diva_maint_client_t *pC, dword old_mask);
-
-static void diva_maint_error(void *user_context,
-			     diva_strace_library_interface_t *hLib,
-			     int Adapter,
-			     int error,
-			     const char *file,
-			     int line);
-static void diva_maint_state_change_notify(void *user_context,
-					   diva_strace_library_interface_t *hLib,
-					   int Adapter,
-					   diva_trace_line_state_t *channel,
-					   int notify_subject);
-static void diva_maint_trace_notify(void *user_context,
-				    diva_strace_library_interface_t *hLib,
-				    int Adapter,
-				    void *xlog_buffer,
-				    int length);
-
-
-
-typedef struct MSG_QUEUE {
-	dword	Size;		/* total size of queue (constant)	*/
-	byte	*Base;		/* lowest address (constant)		*/
-	byte	*High;		/* Base + Size (constant)		*/
-	byte	*Head;		/* first message in queue (if any)	*/
-	byte	*Tail;		/* first free position			*/
-	byte	*Wrap;		/* current wraparound position		*/
-	dword	Count;		/* current no of bytes in queue		*/
-} MSG_QUEUE;
-
-typedef struct MSG_HEAD {
-	volatile dword	Size;		/* size of data following MSG_HEAD	*/
-#define	MSG_INCOMPLETE	0x8000	/* ored to Size until queueCompleteMsg	*/
-} MSG_HEAD;
-
-#define queueCompleteMsg(p) do { ((MSG_HEAD *)p - 1)->Size &= ~MSG_INCOMPLETE; } while (0)
-#define queueCount(q)	((q)->Count)
-#define MSG_NEED(size)							\
-	((sizeof(MSG_HEAD) + size + sizeof(dword) - 1) & ~(sizeof(dword) - 1))
-
-static void queueInit(MSG_QUEUE *Q, byte *Buffer, dword sizeBuffer) {
-	Q->Size = sizeBuffer;
-	Q->Base = Q->Head = Q->Tail = Buffer;
-	Q->High = Buffer + sizeBuffer;
-	Q->Wrap = NULL;
-	Q->Count = 0;
-}
-
-static byte *queueAllocMsg(MSG_QUEUE *Q, word size) {
-	/* Allocate 'size' bytes at tail of queue which will be filled later
-	 * directly with callers own message header info and/or message.
-	 * An 'alloced' message is marked incomplete by oring the 'Size' field
-	 * with MSG_INCOMPLETE.
-	 * This must be reset via queueCompleteMsg() after the message is filled.
-	 * As long as a message is marked incomplete queuePeekMsg() will return
-	 * a 'queue empty' condition when it reaches such a message.  */
-
-	MSG_HEAD *Msg;
-	word need = MSG_NEED(size);
-
-	if (Q->Tail == Q->Head) {
-		if (Q->Wrap || need > Q->Size) {
-			return NULL; /* full */
-		}
-		goto alloc; /* empty */
-	}
-
-	if (Q->Tail > Q->Head) {
-		if (Q->Tail + need <= Q->High) goto alloc; /* append */
-		if (Q->Base + need > Q->Head) {
-			return NULL; /* too much */
-		}
-		/* wraparound the queue (but not the message) */
-		Q->Wrap = Q->Tail;
-		Q->Tail = Q->Base;
-		goto alloc;
-	}
-
-	if (Q->Tail + need > Q->Head) {
-		return NULL; /* too much */
-	}
-
-alloc:
-	Msg = (MSG_HEAD *)Q->Tail;
-
-	Msg->Size = size | MSG_INCOMPLETE;
-
-	Q->Tail	 += need;
-	Q->Count += size;
-
-
-
-	return ((byte *)(Msg + 1));
-}
-
-static void queueFreeMsg(MSG_QUEUE *Q) {
-/* Free the message at head of queue */
-
-	word size = ((MSG_HEAD *)Q->Head)->Size & ~MSG_INCOMPLETE;
-
-	Q->Head  += MSG_NEED(size);
-	Q->Count -= size;
-
-	if (Q->Wrap) {
-		if (Q->Head >= Q->Wrap) {
-			Q->Head = Q->Base;
-			Q->Wrap = NULL;
-		}
-	} else if (Q->Head >= Q->Tail) {
-		Q->Head = Q->Tail = Q->Base;
-	}
-}
-
-static byte *queuePeekMsg(MSG_QUEUE *Q, word *size) {
-	/* Show the first valid message in queue BUT DON'T free the message.
-	 * After looking on the message contents it can be freed queueFreeMsg()
-	 * or simply remain in message queue.  */
-
-	MSG_HEAD *Msg = (MSG_HEAD *)Q->Head;
-
-	if (((byte *)Msg == Q->Tail && !Q->Wrap) ||
-	    (Msg->Size & MSG_INCOMPLETE)) {
-		return NULL;
-	} else {
-		*size = Msg->Size;
-		return ((byte *)(Msg + 1));
-	}
-}
-
-/*
-  Message queue header
-*/
-static MSG_QUEUE *dbg_queue;
-static byte *dbg_base;
-static int                 external_dbg_queue;
-static diva_os_spin_lock_t dbg_q_lock;
-static diva_os_spin_lock_t dbg_adapter_lock;
-static int                 dbg_q_busy;
-static volatile dword      dbg_sequence;
-
-/*
-  INTERFACE:
-  Initialize run time queue structures.
-  base:    base of the message queue
-  length:  length of the message queue
-  do_init: perfor queue reset
-
-  return:  zero on success, -1 on error
-*/
-int diva_maint_init(byte *base, unsigned long length, int do_init) {
-	if (dbg_queue || (!base) || (length < (4096 * 4))) {
-		return (-1);
-	}
-
-	TraceFilter[0]     =  0;
-	TraceFilterIdent   = -1;
-	TraceFilterChannel = -1;
-
-	dbg_base = base;
-
-	*(dword *)base  = (dword)DBG_MAGIC; /* Store Magic */
-	base   += sizeof(dword);
-	length -= sizeof(dword);
-
-	*(dword *)base = 2048; /* Extension Field Length */
-	base   += sizeof(dword);
-	length -= sizeof(dword);
-
-	strcpy(base, "KERNEL MODE BUFFER\n");
-	base   += 2048;
-	length -= 2048;
-
-	*(dword *)base = 0; /* Terminate extension */
-	base   += sizeof(dword);
-	length -= sizeof(dword);
-
-	*(void **)base  =  (void *)(base + sizeof(void *)); /* Store Base  */
-	base   += sizeof(void *);
-	length -= sizeof(void *);
-
-	dbg_queue = (MSG_QUEUE *)base;
-	queueInit(dbg_queue, base + sizeof(MSG_QUEUE), length - sizeof(MSG_QUEUE) - 512);
-	external_dbg_queue = 0;
-
-	if (!do_init) {
-		external_dbg_queue = 1; /* memory was located on the external device */
-	}
-
-
-	if (diva_os_initialize_spin_lock(&dbg_q_lock, "dbg_init")) {
-		dbg_queue = NULL;
-		dbg_base = NULL;
-		external_dbg_queue = 0;
-		return (-1);
-	}
-
-	if (diva_os_initialize_spin_lock(&dbg_adapter_lock, "dbg_init")) {
-		diva_os_destroy_spin_lock(&dbg_q_lock, "dbg_init");
-		dbg_queue = NULL;
-		dbg_base = NULL;
-		external_dbg_queue = 0;
-		return (-1);
-	}
-
-	return (0);
-}
-
-/*
-  INTERFACE:
-  Finit at unload time
-  return address of internal queue or zero if queue
-  was external
-*/
-void *diva_maint_finit(void) {
-	void *ret = (void *)dbg_base;
-	int i;
-
-	dbg_queue = NULL;
-	dbg_base  = NULL;
-
-	if (ret) {
-		diva_os_destroy_spin_lock(&dbg_q_lock, "dbg_finit");
-		diva_os_destroy_spin_lock(&dbg_adapter_lock, "dbg_finit");
-	}
-
-	if (external_dbg_queue) {
-		ret = NULL;
-	}
-	external_dbg_queue = 0;
-
-	for (i = 1; i < ARRAY_SIZE(clients); i++) {
-		if (clients[i].pmem) {
-			diva_os_free(0, clients[i].pmem);
-		}
-	}
-
-	return (ret);
-}
-
-/*
-  INTERFACE:
-  Return amount of messages in debug queue
-*/
-dword diva_dbg_q_length(void) {
-	return (dbg_queue ? queueCount(dbg_queue)	: 0);
-}
-
-/*
-  INTERFACE:
-  Lock message queue and return the pointer to the first
-  entry.
-*/
-diva_dbg_entry_head_t *diva_maint_get_message(word *size,
-					      diva_os_spin_lock_magic_t *old_irql) {
-	diva_dbg_entry_head_t *pmsg = NULL;
-
-	diva_os_enter_spin_lock(&dbg_q_lock, old_irql, "read");
-	if (dbg_q_busy) {
-		diva_os_leave_spin_lock(&dbg_q_lock, old_irql, "read_busy");
-		return NULL;
-	}
-	dbg_q_busy = 1;
-
-	if (!(pmsg = (diva_dbg_entry_head_t *)queuePeekMsg(dbg_queue, size))) {
-		dbg_q_busy = 0;
-		diva_os_leave_spin_lock(&dbg_q_lock, old_irql, "read_empty");
-	}
-
-	return (pmsg);
-}
-
-/*
-  INTERFACE:
-  acknowledge last message and unlock queue
-*/
-void diva_maint_ack_message(int do_release,
-			    diva_os_spin_lock_magic_t *old_irql) {
-	if (!dbg_q_busy) {
-		return;
-	}
-	if (do_release) {
-		queueFreeMsg(dbg_queue);
-	}
-	dbg_q_busy = 0;
-	diva_os_leave_spin_lock(&dbg_q_lock, old_irql, "read_ack");
-}
-
-
-/*
-  INTERFACE:
-  PRT COMP function used to register
-  with MAINT adapter or log in compatibility
-  mode in case older driver version is connected too
-*/
-void diva_maint_prtComp(char *format, ...) {
-	void    *hDbg;
-	va_list ap;
-
-	if (!format)
-		return;
-
-	va_start(ap, format);
-
-	/*
-	  register to new log driver functions
-	*/
-	if ((format[0] == 0) && ((unsigned char)format[1] == 255)) {
-		hDbg = va_arg(ap, void *); /* ptr to DbgHandle */
-		DI_register(hDbg);
-	}
-
-	va_end(ap);
-}
-
-static void DI_register(void *arg) {
-	diva_os_spin_lock_magic_t old_irql;
-	dword sec, usec;
-	pDbgHandle	hDbg;
-	int id, free_id = -1, best_id = 0;
-
-	diva_os_get_time(&sec, &usec);
-
-	hDbg = (pDbgHandle)arg;
-	/*
-	  Check for bad args, specially for the old obsolete debug handle
-	*/
-	if ((hDbg == NULL) ||
-	    ((hDbg->id == 0) && (((_OldDbgHandle_ *)hDbg)->id == -1)) ||
-	    (hDbg->Registered != 0)) {
-		return;
-	}
-
-	diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "register");
-
-	for (id = 1; id < ARRAY_SIZE(clients); id++) {
-		if (clients[id].hDbg == hDbg) {
-			/*
-			  driver already registered
-			*/
-			diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "register");
-			return;
-		}
-		if (clients[id].hDbg) { /* slot is busy */
-			continue;
-		}
-		free_id = id;
-		if (!strcmp(clients[id].drvName, hDbg->drvName)) {
-			/*
-			  This driver was already registered with this name
-			  and slot is still free - reuse it
-			*/
-			best_id = 1;
-			break;
-		}
-		if (!clients[id].hDbg) { /* slot is busy */
-			break;
-		}
-	}
-
-	if (free_id != -1) {
-		diva_dbg_entry_head_t *pmsg = NULL;
-		int len;
-		char tmp[256];
-		word size;
-
-		/*
-		  Register new driver with id == free_id
-		*/
-		clients[free_id].hDbg = hDbg;
-		clients[free_id].sec  = sec;
-		clients[free_id].usec = usec;
-		strcpy(clients[free_id].drvName, hDbg->drvName);
-
-		clients[free_id].dbgMask = hDbg->dbgMask;
-		if (best_id) {
-			hDbg->dbgMask |= clients[free_id].last_dbgMask;
-		} else {
-			clients[free_id].last_dbgMask = 0;
-		}
-
-		hDbg->Registered = DBG_HANDLE_REG_NEW;
-		hDbg->id         = (byte)free_id;
-		hDbg->dbg_end    = DI_deregister;
-		hDbg->dbg_prt    = DI_format_locked;
-		hDbg->dbg_ev     = DiProcessEventLog;
-		hDbg->dbg_irq    = DI_format_locked;
-		if (hDbg->Version > 0) {
-			hDbg->dbg_old  = DI_format_old;
-		}
-		hDbg->next       = (pDbgHandle)DBG_MAGIC;
-
-		/*
-		  Log driver register, MAINT driver ID is '0'
-		*/
-		len = sprintf(tmp, "DIMAINT - drv # %d = '%s' registered",
-			      free_id, hDbg->drvName);
-
-		while (!(pmsg = (diva_dbg_entry_head_t *)queueAllocMsg(dbg_queue,
-								       (word)(len + 1 + sizeof(*pmsg))))) {
-			if ((pmsg = (diva_dbg_entry_head_t *)queuePeekMsg(dbg_queue, &size))) {
-				queueFreeMsg(dbg_queue);
-			} else {
-				break;
-			}
-		}
-
-		if (pmsg) {
-			pmsg->sequence    = dbg_sequence++;
-			pmsg->time_sec    = sec;
-			pmsg->time_usec   = usec;
-			pmsg->facility    = MSG_TYPE_STRING;
-			pmsg->dli         = DLI_REG;
-			pmsg->drv_id      = 0; /* id 0 - DIMAINT */
-			pmsg->di_cpu      = 0;
-			pmsg->data_length = len + 1;
-
-			memcpy(&pmsg[1], tmp, len + 1);
-			queueCompleteMsg(pmsg);
-			diva_maint_wakeup_read();
-		}
-	}
-
-	diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "register");
-}
-
-static void DI_deregister(pDbgHandle hDbg) {
-	diva_os_spin_lock_magic_t old_irql, old_irql1;
-	dword sec, usec;
-	int i;
-	word size;
-	byte *pmem = NULL;
-
-	diva_os_get_time(&sec, &usec);
-
-	diva_os_enter_spin_lock(&dbg_adapter_lock, &old_irql1, "read");
-	diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "read");
-
-	for (i = 1; i < ARRAY_SIZE(clients); i++) {
-		if (clients[i].hDbg == hDbg) {
-			diva_dbg_entry_head_t *pmsg;
-			char tmp[256];
-			int len;
-
-			clients[i].hDbg = NULL;
-
-			hDbg->id       = -1;
-			hDbg->dbgMask  = 0;
-			hDbg->dbg_end  = NULL;
-			hDbg->dbg_prt  = NULL;
-			hDbg->dbg_irq  = NULL;
-			if (hDbg->Version > 0)
-				hDbg->dbg_old = NULL;
-			hDbg->Registered = 0;
-			hDbg->next     = NULL;
-
-			if (clients[i].pIdiLib) {
-				(*(clients[i].pIdiLib->DivaSTraceLibraryFinit))(clients[i].pIdiLib->hLib);
-				clients[i].pIdiLib = NULL;
-
-				pmem = clients[i].pmem;
-				clients[i].pmem = NULL;
-			}
-
-			/*
-			  Log driver register, MAINT driver ID is '0'
-			*/
-			len = sprintf(tmp, "DIMAINT - drv # %d = '%s' de-registered",
-				      i, hDbg->drvName);
-
-			while (!(pmsg = (diva_dbg_entry_head_t *)queueAllocMsg(dbg_queue,
-									      (word)(len + 1 + sizeof(*pmsg))))) {
-				if ((pmsg = (diva_dbg_entry_head_t *)queuePeekMsg(dbg_queue, &size))) {
-					queueFreeMsg(dbg_queue);
-				} else {
-					break;
-				}
-			}
-
-			if (pmsg) {
-				pmsg->sequence    = dbg_sequence++;
-				pmsg->time_sec    = sec;
-				pmsg->time_usec   = usec;
-				pmsg->facility    = MSG_TYPE_STRING;
-				pmsg->dli         = DLI_REG;
-				pmsg->drv_id      = 0; /* id 0 - DIMAINT */
-				pmsg->di_cpu      = 0;
-				pmsg->data_length = len + 1;
-
-				memcpy(&pmsg[1], tmp, len + 1);
-				queueCompleteMsg(pmsg);
-				diva_maint_wakeup_read();
-			}
-
-			break;
-		}
-	}
-
-	diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "read_ack");
-	diva_os_leave_spin_lock(&dbg_adapter_lock, &old_irql1, "read_ack");
-
-	if (pmem) {
-		diva_os_free(0, pmem);
-	}
-}
-
-static void DI_format_locked(unsigned short id,
-			     int type,
-			     char *format,
-			     va_list argument_list) {
-	DI_format(1, id, type, format, argument_list);
-}
-
-static void DI_format(int do_lock,
-		      unsigned short id,
-		      int type,
-		      char *format,
-		      va_list ap) {
-	diva_os_spin_lock_magic_t old_irql;
-	dword sec, usec;
-	diva_dbg_entry_head_t *pmsg = NULL;
-	dword length;
-	word size;
-	static char fmtBuf[MSG_FRAME_MAX_SIZE + sizeof(*pmsg) + 1];
-	char          *data;
-	unsigned short code;
-
-	if (diva_os_in_irq()) {
-		dbg_sequence++;
-		return;
-	}
-
-	if ((!format) ||
-	    ((TraceFilter[0] != 0) && ((TraceFilterIdent < 0) || (TraceFilterChannel < 0)))) {
-		return;
-	}
-
-
-
-	diva_os_get_time(&sec, &usec);
-
-	if (do_lock) {
-		diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "format");
-	}
-
-	switch (type) {
-	case DLI_MXLOG:
-	case DLI_BLK:
-	case DLI_SEND:
-	case DLI_RECV:
-		if (!(length = va_arg(ap, unsigned long))) {
-			break;
-		}
-		if (length > MaxDumpSize) {
-			length = MaxDumpSize;
-		}
-		while (!(pmsg = (diva_dbg_entry_head_t *)queueAllocMsg(dbg_queue,
-								       (word)length + sizeof(*pmsg)))) {
-			if ((pmsg = (diva_dbg_entry_head_t *)queuePeekMsg(dbg_queue, &size))) {
-				queueFreeMsg(dbg_queue);
-			} else {
-				break;
-			}
-		}
-		if (pmsg) {
-			memcpy(&pmsg[1], format, length);
-			pmsg->sequence    = dbg_sequence++;
-			pmsg->time_sec    = sec;
-			pmsg->time_usec   = usec;
-			pmsg->facility    = MSG_TYPE_BINARY;
-			pmsg->dli         = type; /* DLI_XXX */
-			pmsg->drv_id      = id;   /* driver MAINT id */
-			pmsg->di_cpu      = 0;
-			pmsg->data_length = length;
-			queueCompleteMsg(pmsg);
-		}
-		break;
-
-	case DLI_XLOG: {
-		byte *p;
-		data    = va_arg(ap, char *);
-		code    = (unsigned short)va_arg(ap, unsigned int);
-		length	= (unsigned long)va_arg(ap, unsigned int);
-
-		if (length > MaxXlogSize)
-			length = MaxXlogSize;
-
-		while (!(pmsg = (diva_dbg_entry_head_t *)queueAllocMsg(dbg_queue,
-								      (word)length + sizeof(*pmsg) + 2))) {
-			if ((pmsg = (diva_dbg_entry_head_t *)queuePeekMsg(dbg_queue, &size))) {
-				queueFreeMsg(dbg_queue);
-			} else {
-				break;
-			}
-		}
-		if (pmsg) {
-			p = (byte *)&pmsg[1];
-			p[0] = (char)(code);
-			p[1] = (char)(code >> 8);
-			if (data && length) {
-				memcpy(&p[2], &data[0], length);
-			}
-			length += 2;
-
-			pmsg->sequence    = dbg_sequence++;
-			pmsg->time_sec    = sec;
-			pmsg->time_usec   = usec;
-			pmsg->facility    = MSG_TYPE_BINARY;
-			pmsg->dli         = type; /* DLI_XXX */
-			pmsg->drv_id      = id;   /* driver MAINT id */
-			pmsg->di_cpu      = 0;
-			pmsg->data_length = length;
-			queueCompleteMsg(pmsg);
-		}
-	} break;
-
-	case DLI_LOG:
-	case DLI_FTL:
-	case DLI_ERR:
-	case DLI_TRC:
-	case DLI_REG:
-	case DLI_MEM:
-	case DLI_SPL:
-	case DLI_IRP:
-	case DLI_TIM:
-	case DLI_TAPI:
-	case DLI_NDIS:
-	case DLI_CONN:
-	case DLI_STAT:
-	case DLI_PRV0:
-	case DLI_PRV1:
-	case DLI_PRV2:
-	case DLI_PRV3:
-		if ((length = (unsigned long)vsprintf(&fmtBuf[0], format, ap)) > 0) {
-			length += (sizeof(*pmsg) + 1);
-
-			while (!(pmsg = (diva_dbg_entry_head_t *)queueAllocMsg(dbg_queue,
-									       (word)length))) {
-				if ((pmsg = (diva_dbg_entry_head_t *)queuePeekMsg(dbg_queue, &size))) {
-					queueFreeMsg(dbg_queue);
-				} else {
-					break;
-				}
-			}
-
-			pmsg->sequence    = dbg_sequence++;
-			pmsg->time_sec    = sec;
-			pmsg->time_usec   = usec;
-			pmsg->facility    = MSG_TYPE_STRING;
-			pmsg->dli         = type; /* DLI_XXX */
-			pmsg->drv_id      = id;   /* driver MAINT id */
-			pmsg->di_cpu      = 0;
-			pmsg->data_length = length - sizeof(*pmsg);
-
-			memcpy(&pmsg[1], fmtBuf, pmsg->data_length);
-			queueCompleteMsg(pmsg);
-		}
-		break;
-
-	} /* switch type */
-
-
-	if (queueCount(dbg_queue)) {
-		diva_maint_wakeup_read();
-	}
-
-	if (do_lock) {
-		diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "format");
-	}
-}
-
-/*
-  Write driver ID and driver revision to callers buffer
-*/
-int diva_get_driver_info(dword id, byte *data, int data_length) {
-	diva_os_spin_lock_magic_t old_irql;
-	byte *p = data;
-	int to_copy;
-
-	if (!data || !id || (data_length < 17) ||
-	    (id >= ARRAY_SIZE(clients))) {
-		return (-1);
-	}
-
-	diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "driver info");
-
-	if (clients[id].hDbg) {
-		*p++ = 1;
-		*p++ = (byte)clients[id].sec; /* save seconds */
-		*p++ = (byte)(clients[id].sec >>  8);
-		*p++ = (byte)(clients[id].sec >> 16);
-		*p++ = (byte)(clients[id].sec >> 24);
-
-		*p++ = (byte)(clients[id].usec / 1000); /* save mseconds */
-		*p++ = (byte)((clients[id].usec / 1000) >>  8);
-		*p++ = (byte)((clients[id].usec / 1000) >> 16);
-		*p++ = (byte)((clients[id].usec / 1000) >> 24);
-
-		data_length -= 9;
-
-		if ((to_copy = min(strlen(clients[id].drvName), (size_t)(data_length - 1)))) {
-			memcpy(p, clients[id].drvName, to_copy);
-			p += to_copy;
-			data_length -= to_copy;
-			if ((data_length >= 4) && clients[id].hDbg->drvTag[0]) {
-				*p++ = '(';
-				data_length -= 1;
-				if ((to_copy = min(strlen(clients[id].hDbg->drvTag), (size_t)(data_length - 2)))) {
-					memcpy(p, clients[id].hDbg->drvTag, to_copy);
-					p += to_copy;
-					data_length -= to_copy;
-					if (data_length >= 2) {
-						*p++ = ')';
-						data_length--;
-					}
-				}
-			}
-		}
-	}
-	*p++ = 0;
-
-	diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "driver info");
-
-	return (p - data);
-}
-
-int diva_get_driver_dbg_mask(dword id, byte *data) {
-	diva_os_spin_lock_magic_t old_irql;
-	int ret = -1;
-
-	if (!data || !id || (id >= ARRAY_SIZE(clients))) {
-		return (-1);
-	}
-	diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "driver info");
-
-	if (clients[id].hDbg) {
-		ret = 4;
-		*data++ = (byte)(clients[id].hDbg->dbgMask);
-		*data++ = (byte)(clients[id].hDbg->dbgMask >>  8);
-		*data++ = (byte)(clients[id].hDbg->dbgMask >> 16);
-		*data++ = (byte)(clients[id].hDbg->dbgMask >> 24);
-	}
-
-	diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "driver info");
-
-	return (ret);
-}
-
-int diva_set_driver_dbg_mask(dword id, dword mask) {
-	diva_os_spin_lock_magic_t old_irql, old_irql1;
-	int ret = -1;
-
-
-	if (!id || (id >= ARRAY_SIZE(clients))) {
-		return (-1);
-	}
-
-	diva_os_enter_spin_lock(&dbg_adapter_lock, &old_irql1, "dbg mask");
-	diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "dbg mask");
-
-	if (clients[id].hDbg) {
-		dword old_mask = clients[id].hDbg->dbgMask;
-		mask &= 0x7fffffff;
-		clients[id].hDbg->dbgMask = mask;
-		clients[id].last_dbgMask = (clients[id].hDbg->dbgMask | clients[id].dbgMask);
-		ret = 4;
-		diva_change_management_debug_mask(&clients[id], old_mask);
-	}
-
-
-	diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "dbg mask");
-
-	if (clients[id].request_pending) {
-		clients[id].request_pending = 0;
-		(*(clients[id].request))((ENTITY *)(*(clients[id].pIdiLib->DivaSTraceGetHandle))(clients[id].pIdiLib->hLib));
-	}
-
-	diva_os_leave_spin_lock(&dbg_adapter_lock, &old_irql1, "dbg mask");
-
-	return (ret);
-}
-
-static int diva_get_idi_adapter_info(IDI_CALL request, dword *serial, dword *logical) {
-	IDI_SYNC_REQ sync_req;
-
-	sync_req.xdi_logical_adapter_number.Req = 0;
-	sync_req.xdi_logical_adapter_number.Rc = IDI_SYNC_REQ_XDI_GET_LOGICAL_ADAPTER_NUMBER;
-	(*request)((ENTITY *)&sync_req);
-	*logical = sync_req.xdi_logical_adapter_number.info.logical_adapter_number;
-
-	sync_req.GetSerial.Req = 0;
-	sync_req.GetSerial.Rc = IDI_SYNC_REQ_GET_SERIAL;
-	sync_req.GetSerial.serial = 0;
-	(*request)((ENTITY *)&sync_req);
-	*serial = sync_req.GetSerial.serial;
-
-	return (0);
-}
-
-/*
-  Register XDI adapter as MAINT compatible driver
-*/
-void diva_mnt_add_xdi_adapter(const DESCRIPTOR *d) {
-	diva_os_spin_lock_magic_t old_irql, old_irql1;
-	dword sec, usec, logical, serial, org_mask;
-	int id, free_id = -1;
-	char tmp[128];
-	diva_dbg_entry_head_t *pmsg = NULL;
-	int len;
-	word size;
-	byte *pmem;
-
-	diva_os_get_time(&sec, &usec);
-	diva_get_idi_adapter_info(d->request, &serial, &logical);
-	if (serial & 0xff000000) {
-		sprintf(tmp, "ADAPTER:%d SN:%u-%d",
-			(int)logical,
-			serial & 0x00ffffff,
-			(byte)(((serial & 0xff000000) >> 24) + 1));
-	} else {
-		sprintf(tmp, "ADAPTER:%d SN:%u", (int)logical, serial);
-	}
-
-	if (!(pmem = diva_os_malloc(0, DivaSTraceGetMemotyRequirement(d->channels)))) {
-		return;
-	}
-	memset(pmem, 0x00, DivaSTraceGetMemotyRequirement(d->channels));
-
-	diva_os_enter_spin_lock(&dbg_adapter_lock, &old_irql1, "register");
-	diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "register");
-
-	for (id = 1; id < ARRAY_SIZE(clients); id++) {
-		if (clients[id].hDbg && (clients[id].request == d->request)) {
-			diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "register");
-			diva_os_leave_spin_lock(&dbg_adapter_lock, &old_irql1, "register");
-			diva_os_free(0, pmem);
-			return;
-		}
-		if (clients[id].hDbg) { /* slot is busy */
-			continue;
-		}
-		if (free_id < 0) {
-			free_id = id;
-		}
-		if (!strcmp(clients[id].drvName, tmp)) {
-			/*
-			  This driver was already registered with this name
-			  and slot is still free - reuse it
-			*/
-			free_id = id;
-			break;
-		}
-	}
-
-	if (free_id < 0) {
-		diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "register");
-		diva_os_leave_spin_lock(&dbg_adapter_lock, &old_irql1, "register");
-		diva_os_free(0, pmem);
-		return;
-	}
-
-	id = free_id;
-	clients[id].request  = d->request;
-	clients[id].request_pending = 0;
-	clients[id].hDbg     = &clients[id].Dbg;
-	clients[id].sec      = sec;
-	clients[id].usec     = usec;
-	strcpy(clients[id].drvName,     tmp);
-	strcpy(clients[id].Dbg.drvName, tmp);
-	clients[id].Dbg.drvTag[0] = 0;
-	clients[id].logical  = (int)logical;
-	clients[id].channels = (int)d->channels;
-	clients[id].dma_handle = -1;
-
-	clients[id].Dbg.dbgMask    = 0;
-	clients[id].dbgMask        = clients[id].Dbg.dbgMask;
-	if (id) {
-		clients[id].Dbg.dbgMask |= clients[free_id].last_dbgMask;
-	} else {
-		clients[id].last_dbgMask = 0;
-	}
-	clients[id].Dbg.Registered = DBG_HANDLE_REG_NEW;
-	clients[id].Dbg.id         = (byte)id;
-	clients[id].Dbg.dbg_end    = DI_deregister;
-	clients[id].Dbg.dbg_prt    = DI_format_locked;
-	clients[id].Dbg.dbg_ev     = DiProcessEventLog;
-	clients[id].Dbg.dbg_irq    = DI_format_locked;
-	clients[id].Dbg.next       = (pDbgHandle)DBG_MAGIC;
-
-	{
-		diva_trace_library_user_interface_t diva_maint_user_ifc = { &clients[id],
-									    diva_maint_state_change_notify,
-									    diva_maint_trace_notify,
-									    diva_maint_error };
-
-		/*
-		  Attach to adapter management interface
-		*/
-		if ((clients[id].pIdiLib =
-		     DivaSTraceLibraryCreateInstance((int)logical, &diva_maint_user_ifc, pmem))) {
-			if (((*(clients[id].pIdiLib->DivaSTraceLibraryStart))(clients[id].pIdiLib->hLib))) {
-				diva_mnt_internal_dprintf(0, DLI_ERR, "Adapter(%d) Start failed", (int)logical);
-				(*(clients[id].pIdiLib->DivaSTraceLibraryFinit))(clients[id].pIdiLib->hLib);
-				clients[id].pIdiLib = NULL;
-			}
-		} else {
-			diva_mnt_internal_dprintf(0, DLI_ERR, "A(%d) management init failed", (int)logical);
-		}
-	}
-
-	if (!clients[id].pIdiLib) {
-		clients[id].request = NULL;
-		clients[id].request_pending = 0;
-		clients[id].hDbg    = NULL;
-		diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "register");
-		diva_os_leave_spin_lock(&dbg_adapter_lock, &old_irql1, "register");
-		diva_os_free(0, pmem);
-		return;
-	}
-
-	/*
-	  Log driver register, MAINT driver ID is '0'
-	*/
-	len = sprintf(tmp, "DIMAINT - drv # %d = '%s' registered",
-		      id, clients[id].Dbg.drvName);
-
-	while (!(pmsg = (diva_dbg_entry_head_t *)queueAllocMsg(dbg_queue,
-							       (word)(len + 1 + sizeof(*pmsg))))) {
-		if ((pmsg = (diva_dbg_entry_head_t *)queuePeekMsg(dbg_queue, &size))) {
-			queueFreeMsg(dbg_queue);
-		} else {
-			break;
-		}
-	}
-
-	if (pmsg) {
-		pmsg->sequence    = dbg_sequence++;
-		pmsg->time_sec    = sec;
-		pmsg->time_usec   = usec;
-		pmsg->facility    = MSG_TYPE_STRING;
-		pmsg->dli         = DLI_REG;
-		pmsg->drv_id      = 0; /* id 0 - DIMAINT */
-		pmsg->di_cpu      = 0;
-		pmsg->data_length = len + 1;
-
-		memcpy(&pmsg[1], tmp, len + 1);
-		queueCompleteMsg(pmsg);
-		diva_maint_wakeup_read();
-	}
-
-	org_mask = clients[id].Dbg.dbgMask;
-	clients[id].Dbg.dbgMask = 0;
-
-	diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "register");
-
-	if (clients[id].request_pending) {
-		clients[id].request_pending = 0;
-		(*(clients[id].request))((ENTITY *)(*(clients[id].pIdiLib->DivaSTraceGetHandle))(clients[id].pIdiLib->hLib));
-	}
-
-	diva_os_leave_spin_lock(&dbg_adapter_lock, &old_irql1, "register");
-
-	diva_set_driver_dbg_mask(id, org_mask);
-}
-
-/*
-  De-Register XDI adapter
-*/
-void diva_mnt_remove_xdi_adapter(const DESCRIPTOR *d) {
-	diva_os_spin_lock_magic_t old_irql, old_irql1;
-	dword sec, usec;
-	int i;
-	word size;
-	byte *pmem = NULL;
-
-	diva_os_get_time(&sec, &usec);
-
-	diva_os_enter_spin_lock(&dbg_adapter_lock, &old_irql1, "read");
-	diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "read");
-
-	for (i = 1; i < ARRAY_SIZE(clients); i++) {
-		if (clients[i].hDbg && (clients[i].request == d->request)) {
-			diva_dbg_entry_head_t *pmsg;
-			char tmp[256];
-			int len;
-
-			if (clients[i].pIdiLib) {
-				(*(clients[i].pIdiLib->DivaSTraceLibraryFinit))(clients[i].pIdiLib->hLib);
-				clients[i].pIdiLib = NULL;
-
-				pmem = clients[i].pmem;
-				clients[i].pmem = NULL;
-			}
-
-			clients[i].hDbg    = NULL;
-			clients[i].request_pending = 0;
-			if (clients[i].dma_handle >= 0) {
-				/*
-				  Free DMA handle
-				*/
-				diva_free_dma_descriptor(clients[i].request, clients[i].dma_handle);
-				clients[i].dma_handle = -1;
-			}
-			clients[i].request = NULL;
-
-			/*
-			  Log driver register, MAINT driver ID is '0'
-			*/
-			len = sprintf(tmp, "DIMAINT - drv # %d = '%s' de-registered",
-				      i, clients[i].Dbg.drvName);
-
-			memset(&clients[i].Dbg, 0x00, sizeof(clients[i].Dbg));
-
-			while (!(pmsg = (diva_dbg_entry_head_t *)queueAllocMsg(dbg_queue,
-									       (word)(len + 1 + sizeof(*pmsg))))) {
-				if ((pmsg = (diva_dbg_entry_head_t *)queuePeekMsg(dbg_queue, &size))) {
-					queueFreeMsg(dbg_queue);
-				} else {
-					break;
-				}
-			}
-
-			if (pmsg) {
-				pmsg->sequence    = dbg_sequence++;
-				pmsg->time_sec    = sec;
-				pmsg->time_usec   = usec;
-				pmsg->facility    = MSG_TYPE_STRING;
-				pmsg->dli         = DLI_REG;
-				pmsg->drv_id      = 0; /* id 0 - DIMAINT */
-				pmsg->di_cpu      = 0;
-				pmsg->data_length = len + 1;
-
-				memcpy(&pmsg[1], tmp, len + 1);
-				queueCompleteMsg(pmsg);
-				diva_maint_wakeup_read();
-			}
-
-			break;
-		}
-	}
-
-	diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "read_ack");
-	diva_os_leave_spin_lock(&dbg_adapter_lock, &old_irql1, "read_ack");
-
-	if (pmem) {
-		diva_os_free(0, pmem);
-	}
-}
-
-/* ----------------------------------------------------------------
-   Low level interface for management interface client
-   ---------------------------------------------------------------- */
-/*
-  Return handle to client structure
-*/
-void *SuperTraceOpenAdapter(int AdapterNumber) {
-	int i;
-
-	for (i = 1; i < ARRAY_SIZE(clients); i++) {
-		if (clients[i].hDbg && clients[i].request && (clients[i].logical == AdapterNumber)) {
-			return (&clients[i]);
-		}
-	}
-
-	return NULL;
-}
-
-int SuperTraceCloseAdapter(void *AdapterHandle) {
-	return (0);
-}
-
-int SuperTraceReadRequest(void *AdapterHandle, const char *name, byte *data) {
-	diva_maint_client_t *pC = (diva_maint_client_t *)AdapterHandle;
-
-	if (pC && pC->pIdiLib && pC->request) {
-		ENTITY *e = (ENTITY *)(*(pC->pIdiLib->DivaSTraceGetHandle))(pC->pIdiLib->hLib);
-		byte *xdata = (byte *)&pC->xbuffer[0];
-		char tmp = 0;
-		word length;
-
-		if (!strcmp(name, "\\")) { /* Read ROOT */
-			name = &tmp;
-		}
-		length = SuperTraceCreateReadReq(xdata, name);
-		single_p(xdata, &length, 0); /* End Of Message */
-
-		e->Req        = MAN_READ;
-		e->ReqCh      = 0;
-		e->X->PLength = length;
-		e->X->P	= (byte *)xdata;
-
-		pC->request_pending = 1;
-
-		return (0);
-	}
-
-	return (-1);
-}
-
-int SuperTraceGetNumberOfChannels(void *AdapterHandle) {
-	if (AdapterHandle) {
-		diva_maint_client_t *pC = (diva_maint_client_t *)AdapterHandle;
-
-		return (pC->channels);
-	}
-
-	return (0);
-}
-
-int SuperTraceASSIGN(void *AdapterHandle, byte *data) {
-	diva_maint_client_t *pC = (diva_maint_client_t *)AdapterHandle;
-
-	if (pC && pC->pIdiLib && pC->request) {
-		ENTITY *e = (ENTITY *)(*(pC->pIdiLib->DivaSTraceGetHandle))(pC->pIdiLib->hLib);
-		IDI_SYNC_REQ *preq;
-		char buffer[((sizeof(preq->xdi_extended_features) + 4) > sizeof(ENTITY)) ? (sizeof(preq->xdi_extended_features) + 4) : sizeof(ENTITY)];
-		char features[4];
-		word assign_data_length = 1;
-
-		features[0] = 0;
-		pC->xbuffer[0] = 0;
-		preq = (IDI_SYNC_REQ *)&buffer[0];
-		preq->xdi_extended_features.Req = 0;
-		preq->xdi_extended_features.Rc  = IDI_SYNC_REQ_XDI_GET_EXTENDED_FEATURES;
-		preq->xdi_extended_features.info.buffer_length_in_bytes = sizeof(features);
-		preq->xdi_extended_features.info.features = &features[0];
-
-		(*(pC->request))((ENTITY *)preq);
-
-		if ((features[0] & DIVA_XDI_EXTENDED_FEATURES_VALID) &&
-		    (features[0] & DIVA_XDI_EXTENDED_FEATURE_MANAGEMENT_DMA)) {
-			dword uninitialized_var(rx_dma_magic);
-			if ((pC->dma_handle = diva_get_dma_descriptor(pC->request, &rx_dma_magic)) >= 0) {
-				pC->xbuffer[0] = LLI;
-				pC->xbuffer[1] = 8;
-				pC->xbuffer[2] = 0x40;
-				pC->xbuffer[3] = (byte)pC->dma_handle;
-				pC->xbuffer[4] = (byte)rx_dma_magic;
-				pC->xbuffer[5] = (byte)(rx_dma_magic >>  8);
-				pC->xbuffer[6] = (byte)(rx_dma_magic >> 16);
-				pC->xbuffer[7] = (byte)(rx_dma_magic >> 24);
-				pC->xbuffer[8] = (byte)(DIVA_MAX_MANAGEMENT_TRANSFER_SIZE & 0xFF);
-				pC->xbuffer[9] = (byte)(DIVA_MAX_MANAGEMENT_TRANSFER_SIZE >> 8);
-				pC->xbuffer[10] = 0;
-
-				assign_data_length = 11;
-			}
-		} else {
-			pC->dma_handle = -1;
-		}
-
-		e->Id          = MAN_ID;
-		e->callback    = diva_maint_xdi_cb;
-		e->XNum        = 1;
-		e->X           = &pC->XData;
-		e->Req         = ASSIGN;
-		e->ReqCh       = 0;
-		e->X->PLength  = assign_data_length;
-		e->X->P        = (byte *)&pC->xbuffer[0];
-
-		pC->request_pending = 1;
-
-		return (0);
-	}
-
-	return (-1);
-}
-
-int SuperTraceREMOVE(void *AdapterHandle) {
-	diva_maint_client_t *pC = (diva_maint_client_t *)AdapterHandle;
-
-	if (pC && pC->pIdiLib && pC->request) {
-		ENTITY *e = (ENTITY *)(*(pC->pIdiLib->DivaSTraceGetHandle))(pC->pIdiLib->hLib);
-
-		e->XNum        = 1;
-		e->X           = &pC->XData;
-		e->Req         = REMOVE;
-		e->ReqCh       = 0;
-		e->X->PLength  = 1;
-		e->X->P        = (byte *)&pC->xbuffer[0];
-		pC->xbuffer[0] = 0;
-
-		pC->request_pending = 1;
-
-		return (0);
-	}
-
-	return (-1);
-}
-
-int SuperTraceTraceOnRequest(void *hAdapter, const char *name, byte *data) {
-	diva_maint_client_t *pC = (diva_maint_client_t *)hAdapter;
-
-	if (pC && pC->pIdiLib && pC->request) {
-		ENTITY *e = (ENTITY *)(*(pC->pIdiLib->DivaSTraceGetHandle))(pC->pIdiLib->hLib);
-		byte *xdata = (byte *)&pC->xbuffer[0];
-		char tmp = 0;
-		word length;
-
-		if (!strcmp(name, "\\")) { /* Read ROOT */
-			name = &tmp;
-		}
-		length = SuperTraceCreateReadReq(xdata, name);
-		single_p(xdata, &length, 0); /* End Of Message */
-		e->Req          = MAN_EVENT_ON;
-		e->ReqCh        = 0;
-		e->X->PLength   = length;
-		e->X->P = (byte *)xdata;
-
-		pC->request_pending = 1;
-
-		return (0);
-	}
-
-	return (-1);
-}
-
-int SuperTraceWriteVar(void *AdapterHandle,
-		       byte *data,
-		       const char *name,
-		       void *var,
-		       byte type,
-		       byte var_length) {
-	diva_maint_client_t *pC = (diva_maint_client_t *)AdapterHandle;
-
-	if (pC && pC->pIdiLib && pC->request) {
-		ENTITY *e = (ENTITY *)(*(pC->pIdiLib->DivaSTraceGetHandle))(pC->pIdiLib->hLib);
-		diva_man_var_header_t *pVar = (diva_man_var_header_t *)&pC->xbuffer[0];
-		word length = SuperTraceCreateReadReq((byte *)pVar, name);
-
-		memcpy(&pC->xbuffer[length], var, var_length);
-		length += var_length;
-		pVar->length += var_length;
-		pVar->value_length = var_length;
-		pVar->type = type;
-		single_p((byte *)pVar, &length, 0); /* End Of Message */
-
-		e->Req = MAN_WRITE;
-		e->ReqCh = 0;
-		e->X->PLength   = length;
-		e->X->P = (byte *)pVar;
-
-		pC->request_pending = 1;
-
-		return (0);
-	}
-
-	return (-1);
-}
-
-int SuperTraceExecuteRequest(void *AdapterHandle,
-			     const char *name,
-			     byte *data) {
-	diva_maint_client_t *pC = (diva_maint_client_t *)AdapterHandle;
-
-	if (pC && pC->pIdiLib && pC->request) {
-		ENTITY *e = (ENTITY *)(*(pC->pIdiLib->DivaSTraceGetHandle))(pC->pIdiLib->hLib);
-		byte *xdata = (byte *)&pC->xbuffer[0];
-		word length;
-
-		length = SuperTraceCreateReadReq(xdata, name);
-		single_p(xdata, &length, 0); /* End Of Message */
-
-		e->Req = MAN_EXECUTE;
-		e->ReqCh = 0;
-		e->X->PLength = length;
-		e->X->P = (byte *)xdata;
-
-		pC->request_pending = 1;
-
-		return (0);
-	}
-
-	return (-1);
-}
-
-static word SuperTraceCreateReadReq(byte *P, const char *path) {
-	byte var_length;
-	byte *plen;
-
-	var_length = (byte)strlen(path);
-
-	*P++ = ESC;
-	plen = P++;
-	*P++ = 0x80; /* MAN_IE */
-	*P++ = 0x00; /* Type */
-	*P++ = 0x00; /* Attribute */
-	*P++ = 0x00; /* Status */
-	*P++ = 0x00; /* Variable Length */
-	*P++ = var_length;
-	memcpy(P, path, var_length);
-	P += var_length;
-	*plen = var_length + 0x06;
-
-	return ((word)(var_length + 0x08));
-}
-
-static void single_p(byte *P, word *PLength, byte Id) {
-	P[(*PLength)++] = Id;
-}
-
-static void diva_maint_xdi_cb(ENTITY *e) {
-	diva_strace_context_t *pLib = DIVAS_CONTAINING_RECORD(e, diva_strace_context_t, e);
-	diva_maint_client_t *pC;
-	diva_os_spin_lock_magic_t old_irql, old_irql1;
-
-
-	diva_os_enter_spin_lock(&dbg_adapter_lock, &old_irql1, "xdi_cb");
-	diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "xdi_cb");
-
-	pC = (diva_maint_client_t *)pLib->hAdapter;
-
-	if ((e->complete == 255) || (pC->dma_handle < 0)) {
-		if ((*(pLib->instance.DivaSTraceMessageInput))(&pLib->instance)) {
-			diva_mnt_internal_dprintf(0, DLI_ERR, "Trace internal library error");
-		}
-	} else {
-		/*
-		  Process combined management interface indication
-		*/
-		if ((*(pLib->instance.DivaSTraceMessageInput))(&pLib->instance)) {
-			diva_mnt_internal_dprintf(0, DLI_ERR, "Trace internal library error (DMA mode)");
-		}
-	}
-
-	diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "xdi_cb");
-
-
-	if (pC->request_pending) {
-		pC->request_pending = 0;
-		(*(pC->request))(e);
-	}
-
-	diva_os_leave_spin_lock(&dbg_adapter_lock, &old_irql1, "xdi_cb");
-}
-
-
-static void diva_maint_error(void *user_context,
-			     diva_strace_library_interface_t *hLib,
-			     int Adapter,
-			     int error,
-			     const char *file,
-			     int line) {
-	diva_mnt_internal_dprintf(0, DLI_ERR,
-				  "Trace library error(%d) A(%d) %s %d", error, Adapter, file, line);
-}
-
-static void print_ie(diva_trace_ie_t *ie, char *buffer, int length) {
-	int i;
-
-	buffer[0] = 0;
-
-	if (length > 32) {
-		for (i = 0; ((i < ie->length) && (length > 3)); i++) {
-			sprintf(buffer, "%02x", ie->data[i]);
-			buffer += 2;
-			length -= 2;
-			if (i < (ie->length - 1)) {
-				strcpy(buffer, " ");
-				buffer++;
-				length--;
-			}
-		}
-	}
-}
-
-static void diva_maint_state_change_notify(void *user_context,
-					   diva_strace_library_interface_t *hLib,
-					   int Adapter,
-					   diva_trace_line_state_t *channel,
-					   int notify_subject) {
-	diva_maint_client_t *pC = (diva_maint_client_t *)user_context;
-	diva_trace_fax_state_t *fax = &channel->fax;
-	diva_trace_modem_state_t *modem = &channel->modem;
-	char tmp[256];
-
-	if (!pC->hDbg) {
-		return;
-	}
-
-	switch (notify_subject) {
-	case DIVA_SUPER_TRACE_NOTIFY_LINE_CHANGE: {
-		int view = (TraceFilter[0] == 0);
-		/*
-		  Process selective Trace
-		*/
-		if (channel->Line[0] == 'I' && channel->Line[1] == 'd' &&
-		    channel->Line[2] == 'l' && channel->Line[3] == 'e') {
-			if ((TraceFilterIdent == pC->hDbg->id) && (TraceFilterChannel == (int)channel->ChannelNumber)) {
-				(*(hLib->DivaSTraceSetBChannel))(hLib, (int)channel->ChannelNumber, 0);
-				(*(hLib->DivaSTraceSetAudioTap))(hLib, (int)channel->ChannelNumber, 0);
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG, "Selective Trace OFF for Ch=%d",
-							  (int)channel->ChannelNumber);
-				TraceFilterIdent   = -1;
-				TraceFilterChannel = -1;
-				view = 1;
-			}
-		} else if (TraceFilter[0] && (TraceFilterIdent < 0) && !(diva_mnt_cmp_nmbr(&channel->RemoteAddress[0]) &&
-									 diva_mnt_cmp_nmbr(&channel->LocalAddress[0]))) {
-
-			if ((pC->hDbg->dbgMask & DIVA_MGT_DBG_IFC_BCHANNEL) != 0) { /* Activate B-channel trace */
-				(*(hLib->DivaSTraceSetBChannel))(hLib, (int)channel->ChannelNumber, 1);
-			}
-			if ((pC->hDbg->dbgMask & DIVA_MGT_DBG_IFC_AUDIO) != 0) { /* Activate AudioTap Trace */
-				(*(hLib->DivaSTraceSetAudioTap))(hLib, (int)channel->ChannelNumber, 1);
-			}
-
-			TraceFilterIdent   = pC->hDbg->id;
-			TraceFilterChannel = (int)channel->ChannelNumber;
-
-			if (TraceFilterIdent >= 0) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG, "Selective Trace ON for Ch=%d",
-							  (int)channel->ChannelNumber);
-				view = 1;
-			}
-		}
-		if (view && (pC->hDbg->dbgMask & DIVA_MGT_DBG_LINE_EVENTS)) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L Ch     = %d",
-						  (int)channel->ChannelNumber);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L Status = <%s>", &channel->Line[0]);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L Layer1 = <%s>", &channel->Framing[0]);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L Layer2 = <%s>", &channel->Layer2[0]);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L Layer3 = <%s>", &channel->Layer3[0]);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L RAddr  = <%s>",
-						  &channel->RemoteAddress[0]);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L RSAddr = <%s>",
-						  &channel->RemoteSubAddress[0]);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L LAddr  = <%s>",
-						  &channel->LocalAddress[0]);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L LSAddr = <%s>",
-						  &channel->LocalSubAddress[0]);
-			print_ie(&channel->call_BC, tmp, sizeof(tmp));
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L BC     = <%s>", tmp);
-			print_ie(&channel->call_HLC, tmp, sizeof(tmp));
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L HLC    = <%s>", tmp);
-			print_ie(&channel->call_LLC, tmp, sizeof(tmp));
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L LLC    = <%s>", tmp);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L CR     = 0x%x", channel->CallReference);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L Disc   = 0x%x",
-						  channel->LastDisconnecCause);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "L Owner  = <%s>", &channel->UserID[0]);
-		}
-
-	} break;
-
-	case DIVA_SUPER_TRACE_NOTIFY_MODEM_CHANGE:
-		if (pC->hDbg->dbgMask & DIVA_MGT_DBG_MDM_PROGRESS) {
-			{
-				int ch = TraceFilterChannel;
-				int id = TraceFilterIdent;
-
-				if ((id >= 0) && (ch >= 0) && (id < ARRAY_SIZE(clients)) &&
-				    (clients[id].Dbg.id == (byte)id) && (clients[id].pIdiLib == hLib)) {
-					if (ch != (int)modem->ChannelNumber) {
-						break;
-					}
-				} else if (TraceFilter[0] != 0) {
-					break;
-				}
-			}
-
-
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM Ch    = %lu",
-						  (int)modem->ChannelNumber);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM Event = %lu", modem->Event);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM Norm  = %lu", modem->Norm);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM Opts. = 0x%08x", modem->Options);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM Tx    = %lu Bps", modem->TxSpeed);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM Rx    = %lu Bps", modem->RxSpeed);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM RT    = %lu mSec",
-						  modem->RoundtripMsec);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM Sr    = %lu", modem->SymbolRate);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM Rxl   = %d dBm", modem->RxLeveldBm);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM El    = %d dBm", modem->EchoLeveldBm);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM SNR   = %lu dB", modem->SNRdb);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM MAE   = %lu", modem->MAE);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM LRet  = %lu",
-						  modem->LocalRetrains);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM RRet  = %lu",
-						  modem->RemoteRetrains);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM LRes  = %lu", modem->LocalResyncs);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM RRes  = %lu",
-						  modem->RemoteResyncs);
-			if (modem->Event == 3) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "MDM Disc  =  %lu", modem->DiscReason);
-			}
-		}
-		if ((modem->Event == 3) && (pC->hDbg->dbgMask & DIVA_MGT_DBG_MDM_STATISTICS)) {
-			(*(pC->pIdiLib->DivaSTraceGetModemStatistics))(pC->pIdiLib);
-		}
-		break;
-
-	case DIVA_SUPER_TRACE_NOTIFY_FAX_CHANGE:
-		if (pC->hDbg->dbgMask & DIVA_MGT_DBG_FAX_PROGRESS) {
-			{
-				int ch = TraceFilterChannel;
-				int id = TraceFilterIdent;
-
-				if ((id >= 0) && (ch >= 0) && (id < ARRAY_SIZE(clients)) &&
-				    (clients[id].Dbg.id == (byte)id) && (clients[id].pIdiLib == hLib)) {
-					if (ch != (int)fax->ChannelNumber) {
-						break;
-					}
-				} else if (TraceFilter[0] != 0) {
-					break;
-				}
-			}
-
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX Ch    = %lu", (int)fax->ChannelNumber);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX Event = %lu",     fax->Event);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX Pages = %lu",     fax->Page_Counter);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX Feat. = 0x%08x",  fax->Features);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX ID    = <%s>",    &fax->Station_ID[0]);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX Saddr = <%s>",    &fax->Subaddress[0]);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX Pwd   = <%s>",    &fax->Password[0]);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX Speed = %lu",     fax->Speed);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX Res.  = 0x%08x",  fax->Resolution);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX Width = %lu",     fax->Paper_Width);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX Length= %lu",     fax->Paper_Length);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX SLT   = %lu",     fax->Scanline_Time);
-			if (fax->Event == 3) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT, "FAX Disc  = %lu",     fax->Disc_Reason);
-			}
-		}
-		if ((fax->Event == 3) && (pC->hDbg->dbgMask & DIVA_MGT_DBG_FAX_STATISTICS)) {
-			(*(pC->pIdiLib->DivaSTraceGetFaxStatistics))(pC->pIdiLib);
-		}
-		break;
-
-	case DIVA_SUPER_TRACE_INTERFACE_CHANGE:
-		if (pC->hDbg->dbgMask & DIVA_MGT_DBG_IFC_EVENTS) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT,
-						  "Layer 1 -> [%s]", channel->pInterface->Layer1);
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_STAT,
-						  "Layer 2 -> [%s]", channel->pInterface->Layer2);
-		}
-		break;
-
-	case DIVA_SUPER_TRACE_NOTIFY_STAT_CHANGE:
-		if (pC->hDbg->dbgMask & DIVA_MGT_DBG_IFC_STATISTICS) {
-			/*
-			  Incoming Statistics
-			*/
-			if (channel->pInterfaceStat->inc.Calls) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Inc Calls                     =%lu", channel->pInterfaceStat->inc.Calls);
-			}
-			if (channel->pInterfaceStat->inc.Connected) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Inc Connected                 =%lu", channel->pInterfaceStat->inc.Connected);
-			}
-			if (channel->pInterfaceStat->inc.User_Busy) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Inc Busy                      =%lu", channel->pInterfaceStat->inc.User_Busy);
-			}
-			if (channel->pInterfaceStat->inc.Call_Rejected) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Inc Rejected                  =%lu", channel->pInterfaceStat->inc.Call_Rejected);
-			}
-			if (channel->pInterfaceStat->inc.Wrong_Number) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Inc Wrong Nr                  =%lu", channel->pInterfaceStat->inc.Wrong_Number);
-			}
-			if (channel->pInterfaceStat->inc.Incompatible_Dst) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Inc Incomp. Dest              =%lu", channel->pInterfaceStat->inc.Incompatible_Dst);
-			}
-			if (channel->pInterfaceStat->inc.Out_of_Order) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Inc Out of Order              =%lu", channel->pInterfaceStat->inc.Out_of_Order);
-			}
-			if (channel->pInterfaceStat->inc.Ignored) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Inc Ignored                   =%lu", channel->pInterfaceStat->inc.Ignored);
-			}
-
-			/*
-			  Outgoing Statistics
-			*/
-			if (channel->pInterfaceStat->outg.Calls) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Outg Calls                    =%lu", channel->pInterfaceStat->outg.Calls);
-			}
-			if (channel->pInterfaceStat->outg.Connected) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Outg Connected                =%lu", channel->pInterfaceStat->outg.Connected);
-			}
-			if (channel->pInterfaceStat->outg.User_Busy) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Outg Busy                     =%lu", channel->pInterfaceStat->outg.User_Busy);
-			}
-			if (channel->pInterfaceStat->outg.No_Answer) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Outg No Answer                =%lu", channel->pInterfaceStat->outg.No_Answer);
-			}
-			if (channel->pInterfaceStat->outg.Wrong_Number) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Outg Wrong Nr                 =%lu", channel->pInterfaceStat->outg.Wrong_Number);
-			}
-			if (channel->pInterfaceStat->outg.Call_Rejected) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Outg Rejected                 =%lu", channel->pInterfaceStat->outg.Call_Rejected);
-			}
-			if (channel->pInterfaceStat->outg.Other_Failures) {
-				diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-							  "Outg Other Failures           =%lu", channel->pInterfaceStat->outg.Other_Failures);
-			}
-		}
-		break;
-
-	case DIVA_SUPER_TRACE_NOTIFY_MDM_STAT_CHANGE:
-		if (channel->pInterfaceStat->mdm.Disc_Normal) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "MDM Disc Normal        = %lu", channel->pInterfaceStat->mdm.Disc_Normal);
-		}
-		if (channel->pInterfaceStat->mdm.Disc_Unspecified) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "MDM Disc Unsp.         = %lu", channel->pInterfaceStat->mdm.Disc_Unspecified);
-		}
-		if (channel->pInterfaceStat->mdm.Disc_Busy_Tone) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "MDM Disc Busy Tone     = %lu", channel->pInterfaceStat->mdm.Disc_Busy_Tone);
-		}
-		if (channel->pInterfaceStat->mdm.Disc_Congestion) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "MDM Disc Congestion    = %lu", channel->pInterfaceStat->mdm.Disc_Congestion);
-		}
-		if (channel->pInterfaceStat->mdm.Disc_Carr_Wait) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "MDM Disc Carrier Wait  = %lu", channel->pInterfaceStat->mdm.Disc_Carr_Wait);
-		}
-		if (channel->pInterfaceStat->mdm.Disc_Trn_Timeout) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "MDM Disc Trn. T.o.     = %lu", channel->pInterfaceStat->mdm.Disc_Trn_Timeout);
-		}
-		if (channel->pInterfaceStat->mdm.Disc_Incompat) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "MDM Disc Incompatible  = %lu", channel->pInterfaceStat->mdm.Disc_Incompat);
-		}
-		if (channel->pInterfaceStat->mdm.Disc_Frame_Rej) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "MDM Disc Frame Reject  = %lu", channel->pInterfaceStat->mdm.Disc_Frame_Rej);
-		}
-		if (channel->pInterfaceStat->mdm.Disc_V42bis) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "MDM Disc V.42bis       = %lu", channel->pInterfaceStat->mdm.Disc_V42bis);
-		}
-		break;
-
-	case DIVA_SUPER_TRACE_NOTIFY_FAX_STAT_CHANGE:
-		if (channel->pInterfaceStat->fax.Disc_Normal) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Normal        = %lu", channel->pInterfaceStat->fax.Disc_Normal);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Not_Ident) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Not Ident.    = %lu", channel->pInterfaceStat->fax.Disc_Not_Ident);
-		}
-		if (channel->pInterfaceStat->fax.Disc_No_Response) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc No Response   = %lu", channel->pInterfaceStat->fax.Disc_No_Response);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Retries) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Max Retries   = %lu", channel->pInterfaceStat->fax.Disc_Retries);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Unexp_Msg) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Unexp. Msg.        = %lu", channel->pInterfaceStat->fax.Disc_Unexp_Msg);
-		}
-		if (channel->pInterfaceStat->fax.Disc_No_Polling) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc No Polling    = %lu", channel->pInterfaceStat->fax.Disc_No_Polling);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Training) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Training      = %lu", channel->pInterfaceStat->fax.Disc_Training);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Unexpected) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Unexpected    = %lu", channel->pInterfaceStat->fax.Disc_Unexpected);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Application) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Application   = %lu", channel->pInterfaceStat->fax.Disc_Application);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Incompat) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Incompatible  = %lu", channel->pInterfaceStat->fax.Disc_Incompat);
-		}
-		if (channel->pInterfaceStat->fax.Disc_No_Command) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc No Command    = %lu", channel->pInterfaceStat->fax.Disc_No_Command);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Long_Msg) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Long Msg.     = %lu", channel->pInterfaceStat->fax.Disc_Long_Msg);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Supervisor) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Supervisor    = %lu", channel->pInterfaceStat->fax.Disc_Supervisor);
-		}
-		if (channel->pInterfaceStat->fax.Disc_SUB_SEP_PWD) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc SUP SEP PWD   = %lu", channel->pInterfaceStat->fax.Disc_SUB_SEP_PWD);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Invalid_Msg) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Invalid Msg.  = %lu", channel->pInterfaceStat->fax.Disc_Invalid_Msg);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Page_Coding) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Page Coding   = %lu", channel->pInterfaceStat->fax.Disc_Page_Coding);
-		}
-		if (channel->pInterfaceStat->fax.Disc_App_Timeout) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Appl. T.o.    = %lu", channel->pInterfaceStat->fax.Disc_App_Timeout);
-		}
-		if (channel->pInterfaceStat->fax.Disc_Unspecified) {
-			diva_mnt_internal_dprintf(pC->hDbg->id, DLI_LOG,
-						  "FAX Disc Unspec.       = %lu", channel->pInterfaceStat->fax.Disc_Unspecified);
-		}
-		break;
-	}
-}
-
-/*
-  Receive trace information from the Management Interface and store it in the
-  internal trace buffer with MSG_TYPE_MLOG as is, without any filtering.
-  Event Filtering and formatting is done in  Management Interface self.
-*/
-static void diva_maint_trace_notify(void *user_context,
-				    diva_strace_library_interface_t *hLib,
-				    int Adapter,
-				    void *xlog_buffer,
-				    int length) {
-	diva_maint_client_t *pC = (diva_maint_client_t *)user_context;
-	diva_dbg_entry_head_t *pmsg;
-	word size;
-	dword sec, usec;
-	int ch = TraceFilterChannel;
-	int id = TraceFilterIdent;
-
-	/*
-	  Selective trace
-	*/
-	if ((id >= 0) && (ch >= 0) && (id < ARRAY_SIZE(clients)) &&
-	    (clients[id].Dbg.id == (byte)id) && (clients[id].pIdiLib == hLib)) {
-		const char *p = NULL;
-		int ch_value = -1;
-		MI_XLOG_HDR *TrcData = (MI_XLOG_HDR *)xlog_buffer;
-
-		if (Adapter != clients[id].logical) {
-			return; /* Ignore all trace messages from other adapters */
-		}
-
-		if (TrcData->code == 24) {
-			p = (char *)&TrcData->code;
-			p += 2;
-		}
-
-		/*
-		  All L1 messages start as [dsp,ch], so we can filter this information
-		  and filter out all messages that use different channel
-		*/
-		if (p && p[0] == '[') {
-			if (p[2] == ',') {
-				p += 3;
-				ch_value = *p - '0';
-			} else if (p[3] == ',') {
-				p += 4;
-				ch_value = *p - '0';
-			}
-			if (ch_value >= 0) {
-				if (p[2] == ']') {
-					ch_value = ch_value * 10 + p[1] - '0';
-				}
-				if (ch_value != ch) {
-					return; /* Ignore other channels */
-				}
-			}
-		}
-
-	} else if (TraceFilter[0] != 0) {
-		return; /* Ignore trace if trace filter is activated, but idle */
-	}
-
-	diva_os_get_time(&sec, &usec);
-
-	while (!(pmsg = (diva_dbg_entry_head_t *)queueAllocMsg(dbg_queue,
-							       (word)length + sizeof(*pmsg)))) {
-		if ((pmsg = (diva_dbg_entry_head_t *)queuePeekMsg(dbg_queue, &size))) {
-			queueFreeMsg(dbg_queue);
-		} else {
-			break;
-		}
-	}
-	if (pmsg) {
-		memcpy(&pmsg[1], xlog_buffer, length);
-		pmsg->sequence    = dbg_sequence++;
-		pmsg->time_sec    = sec;
-		pmsg->time_usec   = usec;
-		pmsg->facility    = MSG_TYPE_MLOG;
-		pmsg->dli         = pC->logical;
-		pmsg->drv_id      = pC->hDbg->id;
-		pmsg->di_cpu      = 0;
-		pmsg->data_length = length;
-		queueCompleteMsg(pmsg);
-		if (queueCount(dbg_queue)) {
-			diva_maint_wakeup_read();
-		}
-	}
-}
-
-
-/*
-  Convert MAINT trace mask to management interface trace mask/work/facility and
-  issue command to management interface
-*/
-static void diva_change_management_debug_mask(diva_maint_client_t *pC, dword old_mask) {
-	if (pC->request && pC->hDbg && pC->pIdiLib) {
-		dword changed = pC->hDbg->dbgMask ^ old_mask;
-
-		if (changed & DIVA_MGT_DBG_TRACE) {
-			(*(pC->pIdiLib->DivaSTraceSetInfo))(pC->pIdiLib,
-							    (pC->hDbg->dbgMask & DIVA_MGT_DBG_TRACE) != 0);
-		}
-		if (changed & DIVA_MGT_DBG_DCHAN) {
-			(*(pC->pIdiLib->DivaSTraceSetDChannel))(pC->pIdiLib,
-								(pC->hDbg->dbgMask & DIVA_MGT_DBG_DCHAN) != 0);
-		}
-		if (!TraceFilter[0]) {
-			if (changed & DIVA_MGT_DBG_IFC_BCHANNEL) {
-				int i, state = ((pC->hDbg->dbgMask & DIVA_MGT_DBG_IFC_BCHANNEL) != 0);
-
-				for (i = 0; i < pC->channels; i++) {
-					(*(pC->pIdiLib->DivaSTraceSetBChannel))(pC->pIdiLib, i + 1, state);
-				}
-			}
-			if (changed & DIVA_MGT_DBG_IFC_AUDIO) {
-				int i, state = ((pC->hDbg->dbgMask & DIVA_MGT_DBG_IFC_AUDIO) != 0);
-
-				for (i = 0; i < pC->channels; i++) {
-					(*(pC->pIdiLib->DivaSTraceSetAudioTap))(pC->pIdiLib, i + 1, state);
-				}
-			}
-		}
-	}
-}
-
-
-void diva_mnt_internal_dprintf(dword drv_id, dword type, char *fmt, ...) {
-	va_list ap;
-
-	va_start(ap, fmt);
-	DI_format(0, (word)drv_id, (int)type, fmt, ap);
-	va_end(ap);
-}
-
-/*
-  Shutdown all adapters before driver removal
-*/
-int diva_mnt_shutdown_xdi_adapters(void) {
-	diva_os_spin_lock_magic_t old_irql, old_irql1;
-	int i, fret = 0;
-	byte *pmem;
-
-
-	for (i = 1; i < ARRAY_SIZE(clients); i++) {
-		pmem = NULL;
-
-		diva_os_enter_spin_lock(&dbg_adapter_lock, &old_irql1, "unload");
-		diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "unload");
-
-		if (clients[i].hDbg && clients[i].pIdiLib && clients[i].request) {
-			if ((*(clients[i].pIdiLib->DivaSTraceLibraryStop))(clients[i].pIdiLib) == 1) {
-				/*
-				  Adapter removal complete
-				*/
-				if (clients[i].pIdiLib) {
-					(*(clients[i].pIdiLib->DivaSTraceLibraryFinit))(clients[i].pIdiLib->hLib);
-					clients[i].pIdiLib = NULL;
-
-					pmem = clients[i].pmem;
-					clients[i].pmem = NULL;
-				}
-				clients[i].hDbg    = NULL;
-				clients[i].request_pending = 0;
-
-				if (clients[i].dma_handle >= 0) {
-					/*
-					  Free DMA handle
-					*/
-					diva_free_dma_descriptor(clients[i].request, clients[i].dma_handle);
-					clients[i].dma_handle = -1;
-				}
-				clients[i].request = NULL;
-			} else {
-				fret = -1;
-			}
-		}
-
-		diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "unload");
-		if (clients[i].hDbg && clients[i].pIdiLib && clients[i].request && clients[i].request_pending) {
-			clients[i].request_pending = 0;
-			(*(clients[i].request))((ENTITY *)(*(clients[i].pIdiLib->DivaSTraceGetHandle))(clients[i].pIdiLib->hLib));
-			if (clients[i].dma_handle >= 0) {
-				diva_free_dma_descriptor(clients[i].request, clients[i].dma_handle);
-				clients[i].dma_handle = -1;
-			}
-		}
-		diva_os_leave_spin_lock(&dbg_adapter_lock, &old_irql1, "unload");
-
-		if (pmem) {
-			diva_os_free(0, pmem);
-		}
-	}
-
-	return (fret);
-}
-
-/*
-  Set/Read the trace filter used for selective tracing.
-  Affects B- and Audio Tap trace mask at run time
-*/
-int diva_set_trace_filter(int filter_length, const char *filter) {
-	diva_os_spin_lock_magic_t old_irql, old_irql1;
-	int i, ch, on, client_b_on, client_atap_on;
-
-	diva_os_enter_spin_lock(&dbg_adapter_lock, &old_irql1, "dbg mask");
-	diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "write_filter");
-
-	if (filter_length <= DIVA_MAX_SELECTIVE_FILTER_LENGTH) {
-		memcpy(&TraceFilter[0], filter, filter_length);
-		if (TraceFilter[filter_length]) {
-			TraceFilter[filter_length] = 0;
-		}
-		if (TraceFilter[0] == '*') {
-			TraceFilter[0] = 0;
-		}
-	} else {
-		filter_length = -1;
-	}
-
-	TraceFilterIdent   = -1;
-	TraceFilterChannel = -1;
-
-	on = (TraceFilter[0] == 0);
-
-	for (i = 1; i < ARRAY_SIZE(clients); i++) {
-		if (clients[i].hDbg && clients[i].pIdiLib && clients[i].request) {
-			client_b_on    = on && ((clients[i].hDbg->dbgMask & DIVA_MGT_DBG_IFC_BCHANNEL) != 0);
-			client_atap_on = on && ((clients[i].hDbg->dbgMask & DIVA_MGT_DBG_IFC_AUDIO)    != 0);
-			for (ch = 0; ch < clients[i].channels; ch++) {
-				(*(clients[i].pIdiLib->DivaSTraceSetBChannel))(clients[i].pIdiLib->hLib, ch + 1, client_b_on);
-				(*(clients[i].pIdiLib->DivaSTraceSetAudioTap))(clients[i].pIdiLib->hLib, ch + 1, client_atap_on);
-			}
-		}
-	}
-
-	for (i = 1; i < ARRAY_SIZE(clients); i++) {
-		if (clients[i].hDbg && clients[i].pIdiLib && clients[i].request && clients[i].request_pending) {
-			diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "write_filter");
-			clients[i].request_pending = 0;
-			(*(clients[i].request))((ENTITY *)(*(clients[i].pIdiLib->DivaSTraceGetHandle))(clients[i].pIdiLib->hLib));
-			diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "write_filter");
-		}
-	}
-
-	diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "write_filter");
-	diva_os_leave_spin_lock(&dbg_adapter_lock, &old_irql1, "dbg mask");
-
-	return (filter_length);
-}
-
-int diva_get_trace_filter(int max_length, char *filter) {
-	diva_os_spin_lock_magic_t old_irql;
-	int len;
-
-	diva_os_enter_spin_lock(&dbg_q_lock, &old_irql, "read_filter");
-	len = strlen(&TraceFilter[0]) + 1;
-	if (max_length >= len) {
-		memcpy(filter, &TraceFilter[0], len);
-	}
-	diva_os_leave_spin_lock(&dbg_q_lock, &old_irql, "read_filter");
-
-	return (len);
-}
-
-static int diva_dbg_cmp_key(const char *ref, const char *key) {
-	while (*key && (*ref++ == *key++));
-	return (!*key && !*ref);
-}
-
-/*
-  In case trace filter starts with "C" character then
-  all following characters are interpreted as command.
-  Following commands are available:
-  - single, trace single call at time, independent from CPN/CiPN
-*/
-static int diva_mnt_cmp_nmbr(const char *nmbr) {
-	const char *ref = &TraceFilter[0];
-	int ref_len = strlen(&TraceFilter[0]), nmbr_len = strlen(nmbr);
-
-	if (ref[0] == 'C') {
-		if (diva_dbg_cmp_key(&ref[1], "single")) {
-			return (0);
-		}
-		return (-1);
-	}
-
-	if (!ref_len || (ref_len > nmbr_len)) {
-		return (-1);
-	}
-
-	nmbr = nmbr + nmbr_len - 1;
-	ref  = ref  + ref_len  - 1;
-
-	while (ref_len--) {
-		if (*nmbr-- != *ref--) {
-			return (-1);
-		}
-	}
-
-	return (0);
-}
-
-static int diva_get_dma_descriptor(IDI_CALL request, dword *dma_magic) {
-	ENTITY e;
-	IDI_SYNC_REQ *pReq = (IDI_SYNC_REQ *)&e;
-
-	if (!request) {
-		return (-1);
-	}
-
-	pReq->xdi_dma_descriptor_operation.Req = 0;
-	pReq->xdi_dma_descriptor_operation.Rc = IDI_SYNC_REQ_DMA_DESCRIPTOR_OPERATION;
-
-	pReq->xdi_dma_descriptor_operation.info.operation =     IDI_SYNC_REQ_DMA_DESCRIPTOR_ALLOC;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_number  = -1;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_address = NULL;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_magic   = 0;
-
-	(*request)((ENTITY *)pReq);
-
-	if (!pReq->xdi_dma_descriptor_operation.info.operation &&
-	    (pReq->xdi_dma_descriptor_operation.info.descriptor_number >= 0) &&
-	    pReq->xdi_dma_descriptor_operation.info.descriptor_magic) {
-		*dma_magic = pReq->xdi_dma_descriptor_operation.info.descriptor_magic;
-		return (pReq->xdi_dma_descriptor_operation.info.descriptor_number);
-	} else {
-		return (-1);
-	}
-}
-
-static void diva_free_dma_descriptor(IDI_CALL request, int nr) {
-	ENTITY e;
-	IDI_SYNC_REQ *pReq = (IDI_SYNC_REQ *)&e;
-
-	if (!request || (nr < 0)) {
-		return;
-	}
-
-	pReq->xdi_dma_descriptor_operation.Req = 0;
-	pReq->xdi_dma_descriptor_operation.Rc = IDI_SYNC_REQ_DMA_DESCRIPTOR_OPERATION;
-
-	pReq->xdi_dma_descriptor_operation.info.operation = IDI_SYNC_REQ_DMA_DESCRIPTOR_FREE;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_number  = nr;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_address = NULL;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_magic   = 0;
-
-	(*request)((ENTITY *)pReq);
-}
diff --git a/drivers/isdn/hardware/eicon/debug_if.h b/drivers/isdn/hardware/eicon/debug_if.h
deleted file mode 100644
index fc5953a35ff6..000000000000
--- a/drivers/isdn/hardware/eicon/debug_if.h
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- *
- Copyright (c) Eicon Technology Corporation, 2000.
- *
- This source file is supplied for the use with Eicon
- Technology Corporation's range of DIVA Server Adapters.
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_DEBUG_IF_H__
-#define __DIVA_DEBUG_IF_H__
-#define MSG_TYPE_DRV_ID		0x0001
-#define MSG_TYPE_FLAGS		0x0002
-#define MSG_TYPE_STRING		0x0003
-#define MSG_TYPE_BINARY		0x0004
-#define MSG_TYPE_MLOG     0x0005
-
-#define MSG_FRAME_MAX_SIZE 2150
-
-typedef struct _diva_dbg_entry_head {
-	dword sequence;
-	dword time_sec;
-	dword time_usec;
-	dword facility;
-	dword dli;
-	dword drv_id;
-	dword di_cpu;
-	dword data_length;
-} diva_dbg_entry_head_t;
-
-int diva_maint_init(byte *base, unsigned long length, int do_init);
-void *diva_maint_finit(void);
-dword diva_dbg_q_length(void);
-diva_dbg_entry_head_t *diva_maint_get_message(word *size,
-					      diva_os_spin_lock_magic_t *old_irql);
-void diva_maint_ack_message(int do_release,
-			    diva_os_spin_lock_magic_t *old_irql);
-void diva_maint_prtComp(char *format, ...);
-void diva_maint_wakeup_read(void);
-int diva_get_driver_info(dword id, byte *data, int data_length);
-int diva_get_driver_dbg_mask(dword id, byte *data);
-int diva_set_driver_dbg_mask(dword id, dword mask);
-void diva_mnt_remove_xdi_adapter(const DESCRIPTOR *d);
-void diva_mnt_add_xdi_adapter(const DESCRIPTOR *d);
-int diva_mnt_shutdown_xdi_adapters(void);
-
-#define DIVA_MAX_SELECTIVE_FILTER_LENGTH 127
-int diva_set_trace_filter(int filter_length, const char *filter);
-int diva_get_trace_filter(int max_length, char *filter);
-
-
-#define DITRACE_CMD_GET_DRIVER_INFO   1
-#define DITRACE_READ_DRIVER_DBG_MASK  2
-#define DITRACE_WRITE_DRIVER_DBG_MASK 3
-#define DITRACE_READ_TRACE_ENTRY      4
-#define DITRACE_READ_TRACE_ENTRYS     5
-#define DITRACE_WRITE_SELECTIVE_TRACE_FILTER 6
-#define DITRACE_READ_SELECTIVE_TRACE_FILTER  7
-
-/*
-  Trace lavels for debug via management interface
-*/
-#define DIVA_MGT_DBG_TRACE          0x00000001 /* All trace messages from the card */
-#define DIVA_MGT_DBG_DCHAN          0x00000002 /* All D-channel relater trace messages */
-#define DIVA_MGT_DBG_MDM_PROGRESS   0x00000004 /* Modem progress events */
-#define DIVA_MGT_DBG_FAX_PROGRESS   0x00000008 /* Fax progress events */
-#define DIVA_MGT_DBG_IFC_STATISTICS 0x00000010 /* Interface call statistics */
-#define DIVA_MGT_DBG_MDM_STATISTICS 0x00000020 /* Global modem statistics   */
-#define DIVA_MGT_DBG_FAX_STATISTICS 0x00000040 /* Global call statistics    */
-#define DIVA_MGT_DBG_LINE_EVENTS    0x00000080 /* Line state events */
-#define DIVA_MGT_DBG_IFC_EVENTS     0x00000100 /* Interface/L1/L2 state events */
-#define DIVA_MGT_DBG_IFC_BCHANNEL   0x00000200 /* B-Channel trace for all channels */
-#define DIVA_MGT_DBG_IFC_AUDIO      0x00000400 /* Audio Tap trace for all channels */
-
-# endif /* DEBUG_IF___H */
diff --git a/drivers/isdn/hardware/eicon/debuglib.c b/drivers/isdn/hardware/eicon/debuglib.c
deleted file mode 100644
index d5b1092a54f0..000000000000
--- a/drivers/isdn/hardware/eicon/debuglib.c
+++ /dev/null
@@ -1,156 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-
-#include "debuglib.h"
-
-#ifdef DIVA_NO_DEBUGLIB
-static DIVA_DI_PRINTF dprintf;
-#else /* DIVA_NO_DEBUGLIB */
-
-_DbgHandle_ myDriverDebugHandle = { 0 /*!Registered*/, DBG_HANDLE_VERSION };
-DIVA_DI_PRINTF dprintf = no_printf;
-/*****************************************************************************/
-#define DBG_FUNC(name)							\
-	void								\
-	myDbgPrint_##name(char *format, ...)				\
-	{ va_list ap;							\
-		if (myDriverDebugHandle.dbg_prt)			\
-		{ va_start(ap, format);				\
-			(myDriverDebugHandle.dbg_prt)			\
-				(myDriverDebugHandle.id, DLI_##name, format, ap); \
-			va_end(ap);					\
-		} }
-DBG_FUNC(LOG)
-DBG_FUNC(FTL)
-DBG_FUNC(ERR)
-DBG_FUNC(TRC)
-DBG_FUNC(MXLOG)
-DBG_FUNC(FTL_MXLOG)
-void
-myDbgPrint_EVL(long msgID, ...)
-{ va_list ap;
-	if (myDriverDebugHandle.dbg_ev)
-	{ va_start(ap, msgID);
-		(myDriverDebugHandle.dbg_ev)
-			(myDriverDebugHandle.id, (unsigned long)msgID, ap);
-		va_end(ap);
-	} }
-DBG_FUNC(REG)
-DBG_FUNC(MEM)
-DBG_FUNC(SPL)
-DBG_FUNC(IRP)
-DBG_FUNC(TIM)
-DBG_FUNC(BLK)
-DBG_FUNC(TAPI)
-DBG_FUNC(NDIS)
-DBG_FUNC(CONN)
-DBG_FUNC(STAT)
-DBG_FUNC(SEND)
-DBG_FUNC(RECV)
-DBG_FUNC(PRV0)
-DBG_FUNC(PRV1)
-DBG_FUNC(PRV2)
-DBG_FUNC(PRV3)
-/*****************************************************************************/
-int
-DbgRegister(char *drvName, char *drvTag, unsigned long dbgMask)
-{
-	int len;
-/*
- * deregister (if already registered) and zero out myDriverDebugHandle
- */
-	DbgDeregister();
-/*
- * initialize the debug handle
- */
-	myDriverDebugHandle.Version = DBG_HANDLE_VERSION;
-	myDriverDebugHandle.id  = -1;
-	myDriverDebugHandle.dbgMask = dbgMask | (DL_EVL | DL_FTL | DL_LOG);
-	len = strlen(drvName);
-	memcpy(myDriverDebugHandle.drvName, drvName,
-	       (len < sizeof(myDriverDebugHandle.drvName)) ?
-	       len : sizeof(myDriverDebugHandle.drvName) - 1);
-	len = strlen(drvTag);
-	memcpy(myDriverDebugHandle.drvTag, drvTag,
-	       (len < sizeof(myDriverDebugHandle.drvTag)) ?
-	       len : sizeof(myDriverDebugHandle.drvTag) - 1);
-/*
- * Try to register debugging via old (and only) interface
- */
-	dprintf("\000\377", &myDriverDebugHandle);
-	if (myDriverDebugHandle.dbg_prt)
-	{
-		return (1);
-	}
-/*
- * Check if we registered with an old maint driver (see debuglib.h)
- */
-	if (myDriverDebugHandle.dbg_end != NULL
-	     /* location of 'dbg_prt' in _OldDbgHandle_ struct */
-	     && (myDriverDebugHandle.regTime.LowPart ||
-		 myDriverDebugHandle.regTime.HighPart))
-		/* same location as in _OldDbgHandle_ struct */
-	{
-		dprintf("%s: Cannot log to old maint driver !", drvName);
-		myDriverDebugHandle.dbg_end =
-			((_OldDbgHandle_ *)&myDriverDebugHandle)->dbg_end;
-		DbgDeregister();
-	}
-	return (0);
-}
-/*****************************************************************************/
-void
-DbgSetLevel(unsigned long dbgMask)
-{
-	myDriverDebugHandle.dbgMask = dbgMask | (DL_EVL | DL_FTL | DL_LOG);
-}
-/*****************************************************************************/
-void
-DbgDeregister(void)
-{
-	if (myDriverDebugHandle.dbg_end)
-	{
-		(myDriverDebugHandle.dbg_end)(&myDriverDebugHandle);
-	}
-	memset(&myDriverDebugHandle, 0, sizeof(myDriverDebugHandle));
-}
-void xdi_dbg_xlog(char *x, ...) {
-	va_list ap;
-	va_start(ap, x);
-	if (myDriverDebugHandle.dbg_end &&
-	    (myDriverDebugHandle.dbg_irq || myDriverDebugHandle.dbg_old) &&
-	    (myDriverDebugHandle.dbgMask & DL_STAT)) {
-		if (myDriverDebugHandle.dbg_irq) {
-			(*(myDriverDebugHandle.dbg_irq))(myDriverDebugHandle.id,
-							 (x[0] != 0) ? DLI_TRC : DLI_XLOG, x, ap);
-		} else {
-			(*(myDriverDebugHandle.dbg_old))(myDriverDebugHandle.id, x, ap);
-		}
-	}
-	va_end(ap);
-}
-/*****************************************************************************/
-#endif /* DIVA_NO_DEBUGLIB */
diff --git a/drivers/isdn/hardware/eicon/debuglib.h b/drivers/isdn/hardware/eicon/debuglib.h
deleted file mode 100644
index 6dcbf6afb8f9..000000000000
--- a/drivers/isdn/hardware/eicon/debuglib.h
+++ /dev/null
@@ -1,322 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#if !defined(__DEBUGLIB_H__)
-#define __DEBUGLIB_H__
-#include <stdarg.h>
-/*
- * define global debug priorities
- */
-#define DL_LOG  0x00000001 /* always worth mentioning */
-#define DL_FTL  0x00000002 /* always sampled error    */
-#define DL_ERR  0x00000004 /* any kind of error       */
-#define DL_TRC  0x00000008 /* verbose information     */
-#define DL_XLOG  0x00000010 /* old xlog info           */
-#define DL_MXLOG 0x00000020 /* maestra xlog info    */
-#define DL_FTL_MXLOG 0x00000021 /* fatal maestra xlog info */
-#define DL_EVL  0x00000080 /* special NT eventlog msg */
-#define DL_COMPAT (DL_MXLOG | DL_XLOG)
-#define DL_PRIOR_MASK (DL_EVL | DL_COMPAT | DL_TRC | DL_ERR | DL_FTL | DL_LOG)
-#define DLI_LOG  0x0100
-#define DLI_FTL  0x0200
-#define DLI_ERR  0x0300
-#define DLI_TRC  0x0400
-#define DLI_XLOG 0x0500
-#define DLI_MXLOG 0x0600
-#define DLI_FTL_MXLOG 0x0600
-#define DLI_EVL  0x0800
-/*
- * define OS (operating system interface) debuglevel
- */
-#define DL_REG  0x00000100 /* init/query registry     */
-#define DL_MEM  0x00000200 /* memory management       */
-#define DL_SPL  0x00000400 /* event/spinlock handling */
-#define DL_IRP  0x00000800 /* I/O request handling    */
-#define DL_TIM  0x00001000 /* timer/watchdog handling */
-#define DL_BLK  0x00002000 /* raw data block contents */
-#define DL_OS_MASK (DL_BLK | DL_TIM | DL_IRP | DL_SPL | DL_MEM | DL_REG)
-#define DLI_REG  0x0900
-#define DLI_MEM  0x0A00
-#define DLI_SPL  0x0B00
-#define DLI_IRP  0x0C00
-#define DLI_TIM  0x0D00
-#define DLI_BLK  0x0E00
-/*
- * define ISDN (connection interface) debuglevel
- */
-#define DL_TAPI  0x00010000 /* debug TAPI interface    */
-#define DL_NDIS  0x00020000 /* debug NDIS interface    */
-#define DL_CONN  0x00040000 /* connection handling     */
-#define DL_STAT  0x00080000 /* trace state machines    */
-#define DL_SEND  0x00100000 /* trace raw xmitted data  */
-#define DL_RECV  0x00200000 /* trace raw received data */
-#define DL_DATA  (DL_SEND | DL_RECV)
-#define DL_ISDN_MASK (DL_DATA | DL_STAT | DL_CONN | DL_NDIS | DL_TAPI)
-#define DLI_TAPI 0x1100
-#define DLI_NDIS 0x1200
-#define DLI_CONN 0x1300
-#define DLI_STAT 0x1400
-#define DLI_SEND 0x1500
-#define DLI_RECV 0x1600
-/*
- * define some private (unspecified) debuglevel
- */
-#define DL_PRV0  0x01000000
-#define DL_PRV1  0x02000000
-#define DL_PRV2  0x04000000
-#define DL_PRV3  0x08000000
-#define DL_PRIV_MASK (DL_PRV0 | DL_PRV1 | DL_PRV2 | DL_PRV3)
-#define DLI_PRV0 0x1900
-#define DLI_PRV1 0x1A00
-#define DLI_PRV2 0x1B00
-#define DLI_PRV3 0x1C00
-#define DT_INDEX(x)  ((x) & 0x000F)
-#define DL_INDEX(x)  ((((x) >> 8) & 0x00FF) - 1)
-#define DLI_NAME(x)  ((x) & 0xFF00)
-/*
- * Debug mask for kernel mode tracing, if set the output is also sent to
- * the system debug function. Requires that the project is compiled
- * with _KERNEL_DBG_PRINT_
- */
-#define DL_TO_KERNEL    0x40000000
-
-#ifdef DIVA_NO_DEBUGLIB
-#define myDbgPrint_LOG(x...) do { } while (0);
-#define myDbgPrint_FTL(x...) do { } while (0);
-#define myDbgPrint_ERR(x...) do { } while (0);
-#define myDbgPrint_TRC(x...) do { } while (0);
-#define myDbgPrint_MXLOG(x...) do { } while (0);
-#define myDbgPrint_EVL(x...) do { } while (0);
-#define myDbgPrint_REG(x...) do { } while (0);
-#define myDbgPrint_MEM(x...) do { } while (0);
-#define myDbgPrint_SPL(x...) do { } while (0);
-#define myDbgPrint_IRP(x...) do { } while (0);
-#define myDbgPrint_TIM(x...) do { } while (0);
-#define myDbgPrint_BLK(x...) do { } while (0);
-#define myDbgPrint_TAPI(x...) do { } while (0);
-#define myDbgPrint_NDIS(x...) do { } while (0);
-#define myDbgPrint_CONN(x...) do { } while (0);
-#define myDbgPrint_STAT(x...) do { } while (0);
-#define myDbgPrint_SEND(x...) do { } while (0);
-#define myDbgPrint_RECV(x...) do { } while (0);
-#define myDbgPrint_PRV0(x...) do { } while (0);
-#define myDbgPrint_PRV1(x...) do { } while (0);
-#define myDbgPrint_PRV2(x...) do { } while (0);
-#define myDbgPrint_PRV3(x...) do { } while (0);
-#define DBG_TEST(func, args) do { } while (0);
-#define DBG_EVL_ID(args) do { } while (0);
-
-#else /* DIVA_NO_DEBUGLIB */
-/*
- * define low level macros for formatted & raw debugging
- */
-#define DBG_DECL(func) extern void  myDbgPrint_##func(char *, ...);
-DBG_DECL(LOG)
-DBG_DECL(FTL)
-DBG_DECL(ERR)
-DBG_DECL(TRC)
-DBG_DECL(MXLOG)
-DBG_DECL(FTL_MXLOG)
-extern void  myDbgPrint_EVL(long, ...);
-DBG_DECL(REG)
-DBG_DECL(MEM)
-DBG_DECL(SPL)
-DBG_DECL(IRP)
-DBG_DECL(TIM)
-DBG_DECL(BLK)
-DBG_DECL(TAPI)
-DBG_DECL(NDIS)
-DBG_DECL(CONN)
-DBG_DECL(STAT)
-DBG_DECL(SEND)
-DBG_DECL(RECV)
-DBG_DECL(PRV0)
-DBG_DECL(PRV1)
-DBG_DECL(PRV2)
-DBG_DECL(PRV3)
-#ifdef _KERNEL_DBG_PRINT_
-/*
- * tracing to maint and kernel if selected in the trace mask.
- */
-#define DBG_TEST(func, args)						\
-	{ if ((myDriverDebugHandle.dbgMask) & (unsigned long)DL_##func) \
-		{							\
-			if ((myDriverDebugHandle.dbgMask) & DL_TO_KERNEL) \
-			{ DbgPrint args; DbgPrint("\r\n"); }		\
-			myDbgPrint_##func args;			\
-		} }
-#else
-/*
- * Standard tracing to maint driver.
- */
-#define DBG_TEST(func, args)						\
-	{ if ((myDriverDebugHandle.dbgMask) & (unsigned long)DL_##func) \
-		{ myDbgPrint_##func args;				\
-		} }
-#endif
-/*
- * For event level debug use a separate define, the parameter are
- * different and cause compiler errors on some systems.
- */
-#define DBG_EVL_ID(args)						\
-	{ if ((myDriverDebugHandle.dbgMask) & (unsigned long)DL_EVL)	\
-		{ myDbgPrint_EVL args;					\
-		} }
-
-#endif /* DIVA_NO_DEBUGLIB */
-
-#define DBG_LOG(args)  DBG_TEST(LOG, args)
-#define DBG_FTL(args)  DBG_TEST(FTL, args)
-#define DBG_ERR(args)  DBG_TEST(ERR, args)
-#define DBG_TRC(args)  DBG_TEST(TRC, args)
-#define DBG_MXLOG(args)  DBG_TEST(MXLOG, args)
-#define DBG_FTL_MXLOG(args) DBG_TEST(FTL_MXLOG, args)
-#define DBG_EVL(args)  DBG_EVL_ID(args)
-#define DBG_REG(args)  DBG_TEST(REG, args)
-#define DBG_MEM(args)  DBG_TEST(MEM, args)
-#define DBG_SPL(args)  DBG_TEST(SPL, args)
-#define DBG_IRP(args)  DBG_TEST(IRP, args)
-#define DBG_TIM(args)  DBG_TEST(TIM, args)
-#define DBG_BLK(args)  DBG_TEST(BLK, args)
-#define DBG_TAPI(args)  DBG_TEST(TAPI, args)
-#define DBG_NDIS(args)  DBG_TEST(NDIS, args)
-#define DBG_CONN(args)  DBG_TEST(CONN, args)
-#define DBG_STAT(args)  DBG_TEST(STAT, args)
-#define DBG_SEND(args)  DBG_TEST(SEND, args)
-#define DBG_RECV(args)  DBG_TEST(RECV, args)
-#define DBG_PRV0(args)  DBG_TEST(PRV0, args)
-#define DBG_PRV1(args)  DBG_TEST(PRV1, args)
-#define DBG_PRV2(args)  DBG_TEST(PRV2, args)
-#define DBG_PRV3(args)  DBG_TEST(PRV3, args)
-/*
- * prototypes for debug register/deregister functions in "debuglib.c"
- */
-#ifdef DIVA_NO_DEBUGLIB
-#define DbgRegister(name, tag, mask) do { } while (0)
-#define DbgDeregister() do { } while (0)
-#define DbgSetLevel(mask) do { } while (0)
-#else
-extern DIVA_DI_PRINTF dprintf;
-extern int  DbgRegister(char *drvName, char *drvTag, unsigned long dbgMask);
-extern void DbgDeregister(void);
-extern void DbgSetLevel(unsigned long dbgMask);
-#endif
-/*
- * driver internal structure for debug handling;
- * in client drivers this structure is maintained in "debuglib.c",
- * in the debug driver "debug.c" maintains a chain of such structs.
- */
-typedef struct _DbgHandle_ *pDbgHandle;
-typedef void (*DbgEnd)(pDbgHandle);
-typedef void (*DbgLog)(unsigned short, int, char *, va_list);
-typedef void (*DbgOld)(unsigned short, char *, va_list);
-typedef void (*DbgEv)(unsigned short, unsigned long, va_list);
-typedef void (*DbgIrq)(unsigned short, int, char *, va_list);
-typedef struct _DbgHandle_
-{ char    Registered; /* driver successfully registered */
-#define DBG_HANDLE_REG_NEW 0x01  /* this (new) structure    */
-#define DBG_HANDLE_REG_OLD 0x7f  /* old structure (see below)  */
-	char    Version;  /* version of this structure  */
-#define DBG_HANDLE_VERSION 1   /* contains dbg_old function now */
-#define DBG_HANDLE_VER_EXT  2           /* pReserved points to extended info*/
-	short               id;   /* internal id of registered driver */
-	struct _DbgHandle_ *next;   /* ptr to next registered driver    */
-	struct /*LARGE_INTEGER*/ {
-		unsigned long LowPart;
-		long          HighPart;
-	}     regTime;  /* timestamp for registration       */
-	void               *pIrp;   /* ptr to pending i/o request       */
-	unsigned long       dbgMask;  /* current debug mask               */
-	char                drvName[128]; /* ASCII name of registered driver  */
-	char                drvTag[64]; /* revision string     */
-	DbgEnd              dbg_end;  /* function for debug closing       */
-	DbgLog              dbg_prt;  /* function for debug appending     */
-	DbgOld              dbg_old;  /* function for old debug appending */
-	DbgEv       dbg_ev;  /* function for Windows NT Eventlog */
-	DbgIrq    dbg_irq;  /* function for irql checked debug  */
-	void      *pReserved3;
-} _DbgHandle_;
-extern _DbgHandle_ myDriverDebugHandle;
-typedef struct _OldDbgHandle_
-{ struct _OldDbgHandle_ *next;
-	void                *pIrp;
-	long    regTime[2];
-	unsigned long       dbgMask;
-	short               id;
-	char                drvName[78];
-	DbgEnd              dbg_end;
-	DbgLog              dbg_prt;
-} _OldDbgHandle_;
-/* the differences in DbgHandles
-   old:    tmp:     new:
-   0 long next  char Registered  char Registered
-   char filler   char Version
-   short id    short id
-   4 long pIrp  long    regTime.lo  long next
-   8 long    regTime.lo long    regTime.hi  long    regTime.lo
-   12 long    regTime.hi long next   long regTime.hi
-   16 long dbgMask  long pIrp   long pIrp
-   20 short id   long dbgMask   long dbgMask
-   22 char    drvName[78] ..
-   24 ..     char drvName[16]  char drvName[16]
-   40 ..     char drvTag[64]  char drvTag[64]
-   100 void *dbg_end ..      ..
-   104 void *dbg_prt void *dbg_end  void *dbg_end
-   108 ..     void *dbg_prt  void *dbg_prt
-   112 ..     ..      void *dbg_old
-   116 ..     ..      void *dbg_ev
-   120 ..     ..      void *dbg_irq
-   124 ..     ..      void *pReserved3
-   ( new->id == 0 && *((short *)&new->dbgMask) == -1 ) identifies "old",
-   new->Registered and new->Version overlay old->next,
-   new->next overlays old->pIrp, new->regTime matches old->regTime and
-   thus these fields can be maintained in new struct whithout trouble;
-   id, dbgMask, drvName, dbg_end and dbg_prt need special handling !
-*/
-#define DBG_EXT_TYPE_CARD_TRACE     0x00000001
-typedef struct
-{
-	unsigned long ExtendedType;
-	union
-	{
-		/* DBG_EXT_TYPE_CARD_TRACE */
-		struct
-		{
-			void (*MaskChangedNotify)(void *pContext);
-			unsigned long ModuleTxtMask;
-			unsigned long DebugLevel;
-			unsigned long B_ChannelMask;
-			unsigned long LogBufferSize;
-		} CardTrace;
-	} Data;
-} _DbgExtendedInfo_;
-#ifndef DIVA_NO_DEBUGLIB
-/* -------------------------------------------------------------
-   Function used for xlog-style debug
-   ------------------------------------------------------------- */
-#define XDI_USE_XLOG 1
-void xdi_dbg_xlog(char *x, ...);
-#endif /* DIVA_NO_DEBUGLIB */
-#endif /* __DEBUGLIB_H__ */
diff --git a/drivers/isdn/hardware/eicon/dfifo.h b/drivers/isdn/hardware/eicon/dfifo.h
deleted file mode 100644
index 6a1d3337f99e..000000000000
--- a/drivers/isdn/hardware/eicon/dfifo.h
+++ /dev/null
@@ -1,54 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_IDI_DFIFO_INC__
-#define __DIVA_IDI_DFIFO_INC__
-#define DIVA_DFIFO_CACHE_SZ   64 /* Used to isolate pipe from
-				    rest of the world
-				    should be divisible by 4
-				 */
-#define DIVA_DFIFO_RAW_SZ    (2512 * 8)
-#define DIVA_DFIFO_DATA_SZ   68
-#define DIVA_DFIFO_HDR_SZ    4
-#define DIVA_DFIFO_SEGMENT_SZ  (DIVA_DFIFO_DATA_SZ + DIVA_DFIFO_HDR_SZ)
-#define DIVA_DFIFO_SEGMENTS   ((DIVA_DFIFO_RAW_SZ) / (DIVA_DFIFO_SEGMENT_SZ) + 1)
-#define DIVA_DFIFO_MEM_SZ (						\
-		(DIVA_DFIFO_SEGMENT_SZ) * (DIVA_DFIFO_SEGMENTS) +	\
-		(DIVA_DFIFO_CACHE_SZ) * 2				\
-		)
-#define DIVA_DFIFO_STEP DIVA_DFIFO_SEGMENT_SZ
-/* -------------------------------------------------------------------------
-   Block header layout is:
-   byte[0] -> flags
-   byte[1] -> length of data in block
-   byte[2] -> reserved
-   byte[4] -> reserved
-   ------------------------------------------------------------------------- */
-#define DIVA_DFIFO_WRAP   0x80 /* This is the last block in fifo   */
-#define DIVA_DFIFO_READY  0x40 /* This block is ready for processing */
-#define DIVA_DFIFO_LAST   0x20 /* This block is last in message      */
-#define DIVA_DFIFO_AUTO   0x10 /* Don't look for 'ready', don't ack */
-int diva_dfifo_create(void *start, int length);
-#endif
diff --git a/drivers/isdn/hardware/eicon/di.c b/drivers/isdn/hardware/eicon/di.c
deleted file mode 100644
index cd3fba1add12..000000000000
--- a/drivers/isdn/hardware/eicon/di.c
+++ /dev/null
@@ -1,835 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#include "platform.h"
-#include "pc.h"
-#include "pr_pc.h"
-#include "di_defs.h"
-#include "di.h"
-#if !defined USE_EXTENDED_DEBUGS
-#include "dimaint.h"
-#else
-#define dprintf
-#endif
-#include "io.h"
-#include "dfifo.h"
-#define PR_RAM  ((struct pr_ram *)0)
-#define RAM ((struct dual *)0)
-/*------------------------------------------------------------------*/
-/* local function prototypes                                        */
-/*------------------------------------------------------------------*/
-void pr_out(ADAPTER *a);
-byte pr_dpc(ADAPTER *a);
-static byte pr_ready(ADAPTER *a);
-static byte isdn_rc(ADAPTER *, byte, byte, byte, word, dword, dword);
-static byte isdn_ind(ADAPTER *, byte, byte, byte, PBUFFER *, byte, word);
-/* -----------------------------------------------------------------
-   Functions used for the extended XDI Debug
-   macros
-   global convergence counter (used by all adapters)
-   Look by the implementation part of the functions
-   about the parameters.
-   If you change the dubugging parameters, then you should update
-   the aididbg.doc in the IDI doc's.
-   ----------------------------------------------------------------- */
-#if defined(XDI_USE_XLOG)
-#define XDI_A_NR(_x_) ((byte)(((ISDN_ADAPTER *)(_x_->io))->ANum))
-static void xdi_xlog(byte *msg, word code, int length);
-static byte xdi_xlog_sec = 0;
-#else
-#define XDI_A_NR(_x_) ((byte)0)
-#endif
-static void xdi_xlog_rc_event(byte Adapter,
-			      byte Id, byte Ch, byte Rc, byte cb, byte type);
-static void xdi_xlog_request(byte Adapter, byte Id,
-			     byte Ch, byte Req, byte type);
-static void xdi_xlog_ind(byte Adapter,
-			 byte Id,
-			 byte Ch,
-			 byte Ind,
-			 byte rnr_valid,
-			 byte rnr,
-			 byte type);
-/*------------------------------------------------------------------*/
-/* output function                                                  */
-/*------------------------------------------------------------------*/
-void pr_out(ADAPTER *a)
-{
-	byte e_no;
-	ENTITY *this = NULL;
-	BUFFERS *X;
-	word length;
-	word i;
-	word clength;
-	REQ *ReqOut;
-	byte more;
-	byte ReadyCount;
-	byte ReqCount;
-	byte Id;
-	dtrc(dprintf("pr_out"));
-	/* while a request is pending ...                           */
-	e_no = look_req(a);
-	if (!e_no)
-	{
-		dtrc(dprintf("no_req"));
-		return;
-	}
-	ReadyCount = pr_ready(a);
-	if (!ReadyCount)
-	{
-		dtrc(dprintf("not_ready"));
-		return;
-	}
-	ReqCount = 0;
-	while (e_no && ReadyCount) {
-		next_req(a);
-		this = entity_ptr(a, e_no);
-#ifdef USE_EXTENDED_DEBUGS
-		if (!this)
-		{
-			DBG_FTL(("XDI: [%02x] !A%d ==> NULL entity ptr - try to ignore",
-				 xdi_xlog_sec++, (int)((ISDN_ADAPTER *)a->io)->ANum))
-				e_no = look_req(a);
-			ReadyCount--;
-			continue;
-		}
-		{
-			DBG_TRC((">A%d Id=0x%x Req=0x%x", ((ISDN_ADAPTER *)a->io)->ANum, this->Id, this->Req))
-				}
-#else
-		dbug(dprintf("out:Req=%x,Id=%x,Ch=%x", this->Req, this->Id, this->ReqCh));
-#endif
-		/* get address of next available request buffer             */
-		ReqOut = (REQ *)&PR_RAM->B[a->ram_inw(a, &PR_RAM->NextReq)];
-#if defined(DIVA_ISTREAM)
-		if (!(a->tx_stream[this->Id]   &&
-		      this->Req == N_DATA)) {
-#endif
-			/* now copy the data from the current data buffer into the  */
-			/* adapters request buffer                                  */
-			length = 0;
-			i = this->XCurrent;
-			X = PTR_X(a, this);
-			while (i < this->XNum && length < 270) {
-				clength = min((word)(270 - length), (word)(X[i].PLength-this->XOffset));
-				a->ram_out_buffer(a,
-						  &ReqOut->XBuffer.P[length],
-						  PTR_P(a, this, &X[i].P[this->XOffset]),
-						  clength);
-				length += clength;
-				this->XOffset += clength;
-				if (this->XOffset == X[i].PLength) {
-					this->XCurrent = (byte)++i;
-					this->XOffset = 0;
-				}
-			}
-#if defined(DIVA_ISTREAM)
-		} else { /* Use CMA extension in order to transfer data to the card */
-			i = this->XCurrent;
-			X = PTR_X(a, this);
-			while (i < this->XNum) {
-				diva_istream_write(a,
-						   this->Id,
-						   PTR_P(a, this, &X[i].P[0]),
-						   X[i].PLength,
-						   ((i + 1) == this->XNum),
-						   0, 0);
-				this->XCurrent = (byte)++i;
-			}
-			length = 0;
-		}
-#endif
-		a->ram_outw(a, &ReqOut->XBuffer.length, length);
-		a->ram_out(a, &ReqOut->ReqId, this->Id);
-		a->ram_out(a, &ReqOut->ReqCh, this->ReqCh);
-		/* if it's a specific request (no ASSIGN) ...                */
-		if (this->Id & 0x1f) {
-			/* if buffers are left in the list of data buffers do       */
-			/* do chaining (LL_MDATA, N_MDATA)                          */
-			this->More++;
-			if (i < this->XNum && this->MInd) {
-				xdi_xlog_request(XDI_A_NR(a), this->Id, this->ReqCh, this->MInd,
-						 a->IdTypeTable[this->No]);
-				a->ram_out(a, &ReqOut->Req, this->MInd);
-				more = true;
-			}
-			else {
-				xdi_xlog_request(XDI_A_NR(a), this->Id, this->ReqCh, this->Req,
-						 a->IdTypeTable[this->No]);
-				this->More |= XMOREF;
-				a->ram_out(a, &ReqOut->Req, this->Req);
-				more = false;
-				if (a->FlowControlIdTable[this->ReqCh] == this->Id)
-					a->FlowControlSkipTable[this->ReqCh] = true;
-				/*
-				  Note that remove request was sent to the card
-				*/
-				if (this->Req == REMOVE) {
-					a->misc_flags_table[e_no] |= DIVA_MISC_FLAGS_REMOVE_PENDING;
-				}
-			}
-			/* if we did chaining, this entity is put back into the     */
-			/* request queue                                            */
-			if (more) {
-				req_queue(a, this->No);
-			}
-		}
-		/* else it's a ASSIGN                                       */
-		else {
-			/* save the request code used for buffer chaining           */
-			this->MInd = 0;
-			if (this->Id == BLLC_ID) this->MInd = LL_MDATA;
-			if (this->Id == NL_ID ||
-			    this->Id == TASK_ID ||
-			    this->Id == MAN_ID
-				) this->MInd = N_MDATA;
-			/* send the ASSIGN                                          */
-			a->IdTypeTable[this->No] = this->Id;
-			xdi_xlog_request(XDI_A_NR(a), this->Id, this->ReqCh, this->Req, this->Id);
-			this->More |= XMOREF;
-			a->ram_out(a, &ReqOut->Req, this->Req);
-			/* save the reference of the ASSIGN                         */
-			assign_queue(a, this->No, a->ram_inw(a, &ReqOut->Reference));
-		}
-		a->ram_outw(a, &PR_RAM->NextReq, a->ram_inw(a, &ReqOut->next));
-		ReadyCount--;
-		ReqCount++;
-		e_no = look_req(a);
-	}
-	/* send the filled request buffers to the ISDN adapter      */
-	a->ram_out(a, &PR_RAM->ReqInput,
-		   (byte)(a->ram_in(a, &PR_RAM->ReqInput) + ReqCount));
-	/* if it is a 'unreturncoded' UREMOVE request, remove the  */
-	/* Id from our table after sending the request             */
-	if (this && (this->Req == UREMOVE) && this->Id) {
-		Id = this->Id;
-		e_no = a->IdTable[Id];
-		free_entity(a, e_no);
-		for (i = 0; i < 256; i++)
-		{
-			if (a->FlowControlIdTable[i] == Id)
-				a->FlowControlIdTable[i] = 0;
-		}
-		a->IdTable[Id] = 0;
-		this->Id = 0;
-	}
-}
-static byte pr_ready(ADAPTER *a)
-{
-	byte ReadyCount;
-	ReadyCount = (byte)(a->ram_in(a, &PR_RAM->ReqOutput) -
-			    a->ram_in(a, &PR_RAM->ReqInput));
-	if (!ReadyCount) {
-		if (!a->ReadyInt) {
-			a->ram_inc(a, &PR_RAM->ReadyInt);
-			a->ReadyInt++;
-		}
-	}
-	return ReadyCount;
-}
-/*------------------------------------------------------------------*/
-/* isdn interrupt handler                                           */
-/*------------------------------------------------------------------*/
-byte pr_dpc(ADAPTER *a)
-{
-	byte Count;
-	RC *RcIn;
-	IND *IndIn;
-	byte c;
-	byte RNRId;
-	byte Rc;
-	byte Ind;
-	/* if return codes are available ...                        */
-	if ((Count = a->ram_in(a, &PR_RAM->RcOutput)) != 0) {
-		dtrc(dprintf("#Rc=%x", Count));
-		/* get the buffer address of the first return code          */
-		RcIn = (RC *)&PR_RAM->B[a->ram_inw(a, &PR_RAM->NextRc)];
-		/* for all return codes do ...                              */
-		while (Count--) {
-			if ((Rc = a->ram_in(a, &RcIn->Rc)) != 0) {
-				dword tmp[2];
-				/*
-				  Get extended information, associated with return code
-				*/
-				a->ram_in_buffer(a,
-						 &RcIn->Reserved2[0],
-						 (byte *)&tmp[0],
-						 8);
-				/* call return code handler, if it is not our return code   */
-				/* the handler returns 2                                    */
-				/* for all return codes we process, we clear the Rc field   */
-				isdn_rc(a,
-					Rc,
-					a->ram_in(a, &RcIn->RcId),
-					a->ram_in(a, &RcIn->RcCh),
-					a->ram_inw(a, &RcIn->Reference),
-					tmp[0],  /* type of extended information */
-					tmp[1]); /* extended information        */
-				a->ram_out(a, &RcIn->Rc, 0);
-			}
-			/* get buffer address of next return code                   */
-			RcIn = (RC *)&PR_RAM->B[a->ram_inw(a, &RcIn->next)];
-		}
-		/* clear all return codes (no chaining!)                    */
-		a->ram_out(a, &PR_RAM->RcOutput, 0);
-		/* call output function                                     */
-		pr_out(a);
-	}
-	/* clear RNR flag                                           */
-	RNRId = 0;
-	/* if indications are available ...                         */
-	if ((Count = a->ram_in(a, &PR_RAM->IndOutput)) != 0) {
-		dtrc(dprintf("#Ind=%x", Count));
-		/* get the buffer address of the first indication           */
-		IndIn = (IND *)&PR_RAM->B[a->ram_inw(a, &PR_RAM->NextInd)];
-		/* for all indications do ...                               */
-		while (Count--) {
-			/* if the application marks an indication as RNR, all       */
-			/* indications from the same Id delivered in this interrupt */
-			/* are marked RNR                                           */
-			if (RNRId && RNRId == a->ram_in(a, &IndIn->IndId)) {
-				a->ram_out(a, &IndIn->Ind, 0);
-				a->ram_out(a, &IndIn->RNR, true);
-			}
-			else {
-				Ind = a->ram_in(a, &IndIn->Ind);
-				if (Ind) {
-					RNRId = 0;
-					/* call indication handler, a return value of 2 means chain */
-					/* a return value of 1 means RNR                            */
-					/* for all indications we process, we clear the Ind field   */
-					c = isdn_ind(a,
-						     Ind,
-						     a->ram_in(a, &IndIn->IndId),
-						     a->ram_in(a, &IndIn->IndCh),
-						     &IndIn->RBuffer,
-						     a->ram_in(a, &IndIn->MInd),
-						     a->ram_inw(a, &IndIn->MLength));
-					if (c == 1) {
-						dtrc(dprintf("RNR"));
-						a->ram_out(a, &IndIn->Ind, 0);
-						RNRId = a->ram_in(a, &IndIn->IndId);
-						a->ram_out(a, &IndIn->RNR, true);
-					}
-				}
-			}
-			/* get buffer address of next indication                    */
-			IndIn = (IND *)&PR_RAM->B[a->ram_inw(a, &IndIn->next)];
-		}
-		a->ram_out(a, &PR_RAM->IndOutput, 0);
-	}
-	return false;
-}
-byte scom_test_int(ADAPTER *a)
-{
-	return a->ram_in(a, (void *)0x3fe);
-}
-void scom_clear_int(ADAPTER *a)
-{
-	a->ram_out(a, (void *)0x3fe, 0);
-}
-/*------------------------------------------------------------------*/
-/* return code handler                                              */
-/*------------------------------------------------------------------*/
-static byte isdn_rc(ADAPTER *a,
-		    byte Rc,
-		    byte Id,
-		    byte Ch,
-		    word Ref,
-		    dword extended_info_type,
-		    dword extended_info)
-{
-	ENTITY *this;
-	byte e_no;
-	word i;
-	int cancel_rc;
-#ifdef USE_EXTENDED_DEBUGS
-	{
-		DBG_TRC(("<A%d Id=0x%x Rc=0x%x", ((ISDN_ADAPTER *)a->io)->ANum, Id, Rc))
-			}
-#else
-	dbug(dprintf("isdn_rc(Rc=%x,Id=%x,Ch=%x)", Rc, Id, Ch));
-#endif
-	/* check for ready interrupt                                */
-	if (Rc == READY_INT) {
-		xdi_xlog_rc_event(XDI_A_NR(a), Id, Ch, Rc, 0, 0);
-		if (a->ReadyInt) {
-			a->ReadyInt--;
-			return 0;
-		}
-		return 2;
-	}
-	/* if we know this Id ...                                   */
-	e_no = a->IdTable[Id];
-	if (e_no) {
-		this = entity_ptr(a, e_no);
-		xdi_xlog_rc_event(XDI_A_NR(a), Id, Ch, Rc, 0, a->IdTypeTable[this->No]);
-		this->RcCh = Ch;
-		/* if it is a return code to a REMOVE request, remove the   */
-		/* Id from our table                                        */
-		if ((a->misc_flags_table[e_no] & DIVA_MISC_FLAGS_REMOVE_PENDING) &&
-		    (Rc == OK)) {
-			if (a->IdTypeTable[e_no] == NL_ID) {
-				if (a->RcExtensionSupported &&
-				    (extended_info_type != DIVA_RC_TYPE_REMOVE_COMPLETE)) {
-					dtrc(dprintf("XDI: N-REMOVE, A(%02x) Id:%02x, ignore RC=OK",
-						     XDI_A_NR(a), Id));
-					return (0);
-				}
-				if (extended_info_type == DIVA_RC_TYPE_REMOVE_COMPLETE)
-					a->RcExtensionSupported = true;
-			}
-			a->misc_flags_table[e_no] &= ~DIVA_MISC_FLAGS_REMOVE_PENDING;
-			a->misc_flags_table[e_no] &= ~DIVA_MISC_FLAGS_NO_RC_CANCELLING;
-			free_entity(a, e_no);
-			for (i = 0; i < 256; i++)
-			{
-				if (a->FlowControlIdTable[i] == Id)
-					a->FlowControlIdTable[i] = 0;
-			}
-			a->IdTable[Id] = 0;
-			this->Id = 0;
-			/* ---------------------------------------------------------------
-			   If we send N_DISC or N_DISK_ACK after we have received OK_FC
-			   then the card will respond with OK_FC and later with RC==OK.
-			   If we send N_REMOVE in this state we will receive only RC==OK
-			   This will create the state in that the XDI is waiting for the
-			   additional RC and does not delivery the RC to the client. This
-			   code corrects the counter of outstanding RC's in this case.
-			   --------------------------------------------------------------- */
-			if ((this->More & XMOREC) > 1) {
-				this->More &= ~XMOREC;
-				this->More |= 1;
-				dtrc(dprintf("XDI: correct MORE on REMOVE A(%02x) Id:%02x",
-					     XDI_A_NR(a), Id));
-			}
-		}
-		if (Rc == OK_FC) {
-			a->FlowControlIdTable[Ch] = Id;
-			a->FlowControlSkipTable[Ch] = false;
-			this->Rc = Rc;
-			this->More &= ~(XBUSY | XMOREC);
-			this->complete = 0xff;
-			xdi_xlog_rc_event(XDI_A_NR(a), Id, Ch, Rc, 1, a->IdTypeTable[this->No]);
-			CALLBACK(a, this);
-			return 0;
-		}
-		/*
-		  New protocol code sends return codes that comes from release
-		  of flow control condition marked with DIVA_RC_TYPE_OK_FC extended
-		  information element type.
-		  If like return code arrives then application is able to process
-		  all return codes self and XDI should not cances return codes.
-		  This return code does not decrement XMOREC partial return code
-		  counter due to fact that it was no request for this return code,
-		  also XMOREC was not incremented.
-		*/
-		if (extended_info_type == DIVA_RC_TYPE_OK_FC) {
-			a->misc_flags_table[e_no] |= DIVA_MISC_FLAGS_NO_RC_CANCELLING;
-			this->Rc = Rc;
-			this->complete = 0xff;
-			xdi_xlog_rc_event(XDI_A_NR(a), Id, Ch, Rc, 1, a->IdTypeTable[this->No]);
-			DBG_TRC(("XDI OK_FC A(%02x) Id:%02x Ch:%02x Rc:%02x",
-				 XDI_A_NR(a), Id, Ch, Rc))
-				CALLBACK(a, this);
-			return 0;
-		}
-		cancel_rc = !(a->misc_flags_table[e_no] & DIVA_MISC_FLAGS_NO_RC_CANCELLING);
-		if (cancel_rc && (a->FlowControlIdTable[Ch] == Id))
-		{
-			a->FlowControlIdTable[Ch] = 0;
-			if ((Rc != OK) || !a->FlowControlSkipTable[Ch])
-			{
-				this->Rc = Rc;
-				if (Ch == this->ReqCh)
-				{
-					this->More &= ~(XBUSY | XMOREC);
-					this->complete = 0xff;
-				}
-				xdi_xlog_rc_event(XDI_A_NR(a), Id, Ch, Rc, 1, a->IdTypeTable[this->No]);
-				CALLBACK(a, this);
-			}
-			return 0;
-		}
-		if (this->More & XMOREC)
-			this->More--;
-		/* call the application callback function                   */
-		if (((!cancel_rc) || (this->More & XMOREF)) && !(this->More & XMOREC)) {
-			this->Rc = Rc;
-			this->More &= ~XBUSY;
-			this->complete = 0xff;
-			xdi_xlog_rc_event(XDI_A_NR(a), Id, Ch, Rc, 1, a->IdTypeTable[this->No]);
-			CALLBACK(a, this);
-		}
-		return 0;
-	}
-	/* if it's an ASSIGN return code check if it's a return     */
-	/* code to an ASSIGN request from us                        */
-	if ((Rc & 0xf0) == ASSIGN_RC) {
-		e_no = get_assign(a, Ref);
-		if (e_no) {
-			this = entity_ptr(a, e_no);
-			this->Id = Id;
-			xdi_xlog_rc_event(XDI_A_NR(a), Id, Ch, Rc, 2, a->IdTypeTable[this->No]);
-			/* call the application callback function                   */
-			this->Rc = Rc;
-			this->More &= ~XBUSY;
-			this->complete = 0xff;
-#if defined(DIVA_ISTREAM) /* { */
-			if ((Rc == ASSIGN_OK) && a->ram_offset &&
-			    (a->IdTypeTable[this->No] == NL_ID) &&
-			    ((extended_info_type == DIVA_RC_TYPE_RX_DMA) ||
-			     (extended_info_type == DIVA_RC_TYPE_CMA_PTR)) &&
-			    extended_info) {
-				dword offset = (*(a->ram_offset)) (a);
-				dword tmp[2];
-				extended_info -= offset;
-#ifdef PLATFORM_GT_32BIT
-				a->ram_in_dw(a, (void *)ULongToPtr(extended_info), (dword *)&tmp[0], 2);
-#else
-				a->ram_in_dw(a, (void *)extended_info, (dword *)&tmp[0], 2);
-#endif
-				a->tx_stream[Id]  = tmp[0];
-				a->rx_stream[Id]  = tmp[1];
-				if (extended_info_type == DIVA_RC_TYPE_RX_DMA) {
-					DBG_TRC(("Id=0x%x RxDMA=%08x:%08x",
-						 Id, a->tx_stream[Id], a->rx_stream[Id]))
-						a->misc_flags_table[this->No] |= DIVA_MISC_FLAGS_RX_DMA;
-				} else {
-					DBG_TRC(("Id=0x%x CMA=%08x:%08x",
-						 Id, a->tx_stream[Id], a->rx_stream[Id]))
-						a->misc_flags_table[this->No] &= ~DIVA_MISC_FLAGS_RX_DMA;
-					a->rx_pos[Id]     = 0;
-					a->rx_stream[Id] -= offset;
-				}
-				a->tx_pos[Id]     = 0;
-				a->tx_stream[Id] -= offset;
-			} else {
-				a->tx_stream[Id] = 0;
-				a->rx_stream[Id] = 0;
-				a->misc_flags_table[this->No] &= ~DIVA_MISC_FLAGS_RX_DMA;
-			}
-#endif /* } */
-			CALLBACK(a, this);
-			if (Rc == ASSIGN_OK) {
-				a->IdTable[Id] = e_no;
-			}
-			else
-			{
-				free_entity(a, e_no);
-				for (i = 0; i < 256; i++)
-				{
-					if (a->FlowControlIdTable[i] == Id)
-						a->FlowControlIdTable[i] = 0;
-				}
-				a->IdTable[Id] = 0;
-				this->Id = 0;
-			}
-			return 1;
-		}
-	}
-	return 2;
-}
-/*------------------------------------------------------------------*/
-/* indication handler                                               */
-/*------------------------------------------------------------------*/
-static byte isdn_ind(ADAPTER *a,
-		     byte Ind,
-		     byte Id,
-		     byte Ch,
-		     PBUFFER *RBuffer,
-		     byte MInd,
-		     word MLength)
-{
-	ENTITY *this;
-	word clength;
-	word offset;
-	BUFFERS *R;
-	byte *cma = NULL;
-#ifdef USE_EXTENDED_DEBUGS
-	{
-		DBG_TRC(("<A%d Id=0x%x Ind=0x%x", ((ISDN_ADAPTER *)a->io)->ANum, Id, Ind))
-			}
-#else
-	dbug(dprintf("isdn_ind(Ind=%x,Id=%x,Ch=%x)", Ind, Id, Ch));
-#endif
-	if (a->IdTable[Id]) {
-		this = entity_ptr(a, a->IdTable[Id]);
-		this->IndCh = Ch;
-		xdi_xlog_ind(XDI_A_NR(a), Id, Ch, Ind,
-			     0/* rnr_valid */, 0 /* rnr */, a->IdTypeTable[this->No]);
-		/* if the Receive More flag is not yet set, this is the     */
-		/* first buffer of the packet                               */
-		if (this->RCurrent == 0xff) {
-			/* check for receive buffer chaining                        */
-			if (Ind == this->MInd) {
-				this->complete = 0;
-				this->Ind = MInd;
-			}
-			else {
-				this->complete = 1;
-				this->Ind = Ind;
-			}
-			/* call the application callback function for the receive   */
-			/* look ahead                                               */
-			this->RLength = MLength;
-#if defined(DIVA_ISTREAM)
-			if ((a->rx_stream[this->Id] ||
-			     (a->misc_flags_table[this->No] & DIVA_MISC_FLAGS_RX_DMA)) &&
-			    ((Ind == N_DATA) ||
-			     (a->protocol_capabilities & PROTCAP_CMA_ALLPR))) {
-				PISDN_ADAPTER IoAdapter = (PISDN_ADAPTER)a->io;
-				if (a->misc_flags_table[this->No] & DIVA_MISC_FLAGS_RX_DMA) {
-#if defined(DIVA_IDI_RX_DMA)
-					dword d;
-					diva_get_dma_map_entry(\
-						(struct _diva_dma_map_entry *)IoAdapter->dma_map,
-						(int)a->rx_stream[this->Id], (void **)&cma, &d);
-#else
-					cma = &a->stream_buffer[0];
-					cma[0] = cma[1] = cma[2] = cma[3] = 0;
-#endif
-					this->RLength = MLength = (word)*(dword *)cma;
-					cma += 4;
-				} else {
-					int final = 0;
-					cma = &a->stream_buffer[0];
-					this->RLength = MLength = (word)diva_istream_read(a,
-											  Id,
-											  cma,
-											  sizeof(a->stream_buffer),
-											  &final, NULL, NULL);
-				}
-				IoAdapter->RBuffer.length = min(MLength, (word)270);
-				if (IoAdapter->RBuffer.length != MLength) {
-					this->complete = 0;
-				} else {
-					this->complete = 1;
-				}
-				memcpy(IoAdapter->RBuffer.P, cma, IoAdapter->RBuffer.length);
-				this->RBuffer = (DBUFFER *)&IoAdapter->RBuffer;
-			}
-#endif
-			if (!cma) {
-				a->ram_look_ahead(a, RBuffer, this);
-			}
-			this->RNum = 0;
-			CALLBACK(a, this);
-			/* map entity ptr, selector could be re-mapped by call to   */
-			/* IDI from within callback                                 */
-			this = entity_ptr(a, a->IdTable[Id]);
-			xdi_xlog_ind(XDI_A_NR(a), Id, Ch, Ind,
-				     1/* rnr_valid */, this->RNR/* rnr */, a->IdTypeTable[this->No]);
-			/* check for RNR                                            */
-			if (this->RNR == 1) {
-				this->RNR = 0;
-				return 1;
-			}
-			/* if no buffers are provided by the application, the       */
-			/* application want to copy the data itself including       */
-			/* N_MDATA/LL_MDATA chaining                                */
-			if (!this->RNR && !this->RNum) {
-				xdi_xlog_ind(XDI_A_NR(a), Id, Ch, Ind,
-					     2/* rnr_valid */, 0/* rnr */, a->IdTypeTable[this->No]);
-				return 0;
-			}
-			/* if there is no RNR, set the More flag                    */
-			this->RCurrent = 0;
-			this->ROffset = 0;
-		}
-		if (this->RNR == 2) {
-			if (Ind != this->MInd) {
-				this->RCurrent = 0xff;
-				this->RNR = 0;
-			}
-			return 0;
-		}
-		/* if we have received buffers from the application, copy   */
-		/* the data into these buffers                              */
-		offset = 0;
-		R = PTR_R(a, this);
-		do {
-			if (this->ROffset == R[this->RCurrent].PLength) {
-				this->ROffset = 0;
-				this->RCurrent++;
-			}
-			if (cma) {
-				clength = min(MLength, (word)(R[this->RCurrent].PLength-this->ROffset));
-			} else {
-				clength = min(a->ram_inw(a, &RBuffer->length)-offset,
-					      R[this->RCurrent].PLength-this->ROffset);
-			}
-			if (R[this->RCurrent].P) {
-				if (cma) {
-					memcpy(PTR_P(a, this, &R[this->RCurrent].P[this->ROffset]),
-					       &cma[offset],
-					       clength);
-				} else {
-					a->ram_in_buffer(a,
-							 &RBuffer->P[offset],
-							 PTR_P(a, this, &R[this->RCurrent].P[this->ROffset]),
-							 clength);
-				}
-			}
-			offset += clength;
-			this->ROffset += clength;
-			if (cma) {
-				if (offset >= MLength) {
-					break;
-				}
-				continue;
-			}
-		} while (offset < (a->ram_inw(a, &RBuffer->length)));
-		/* if it's the last buffer of the packet, call the          */
-		/* application callback function for the receive complete   */
-		/* call                                                     */
-		if (Ind != this->MInd) {
-			R[this->RCurrent].PLength = this->ROffset;
-			if (this->ROffset) this->RCurrent++;
-			this->RNum = this->RCurrent;
-			this->RCurrent = 0xff;
-			this->Ind = Ind;
-			this->complete = 2;
-			xdi_xlog_ind(XDI_A_NR(a), Id, Ch, Ind,
-				     3/* rnr_valid */, 0/* rnr */, a->IdTypeTable[this->No]);
-			CALLBACK(a, this);
-		}
-		return 0;
-	}
-	return 2;
-}
-#if defined(XDI_USE_XLOG)
-/* -----------------------------------------------------------
-   This function works in the same way as xlog on the
-   active board
-   ----------------------------------------------------------- */
-static void xdi_xlog(byte *msg, word code, int length) {
-	xdi_dbg_xlog("\x00\x02", msg, code, length);
-}
-#endif
-/* -----------------------------------------------------------
-   This function writes the information about the Return Code
-   processing in the trace buffer. Trace ID is 221.
-   INPUT:
-   Adapter - system unicue adapter number (0 ... 255)
-   Id      - Id of the entity that had sent this return code
-   Ch      - Channel of the entity that had sent this return code
-   Rc      - return code value
-   cb:       (0...2)
-   switch (cb) {
-   case 0: printf ("DELIVERY"); break;
-   case 1: printf ("CALLBACK"); break;
-   case 2: printf ("ASSIGN"); break;
-   }
-   DELIVERY - have entered isdn_rc with this RC
-   CALLBACK - about to make callback to the application
-   for this RC
-   ASSIGN   - about to make callback for RC that is result
-   of ASSIGN request. It is no DELIVERY message
-   before of this message
-   type   - the Id that was sent by the ASSIGN of this entity.
-   This should be global Id like NL_ID, DSIG_ID, MAN_ID.
-   An unknown Id will cause "?-" in the front of the request.
-   In this case the log.c is to be extended.
-   ----------------------------------------------------------- */
-static void xdi_xlog_rc_event(byte Adapter,
-			      byte Id, byte Ch, byte Rc, byte cb, byte type) {
-#if defined(XDI_USE_XLOG)
-	word LogInfo[4];
-	PUT_WORD(&LogInfo[0], ((word)Adapter | (word)(xdi_xlog_sec++ << 8)));
-	PUT_WORD(&LogInfo[1], ((word)Id | (word)(Ch << 8)));
-	PUT_WORD(&LogInfo[2], ((word)Rc | (word)(type << 8)));
-	PUT_WORD(&LogInfo[3], cb);
-	xdi_xlog((byte *)&LogInfo[0], 221, sizeof(LogInfo));
-#endif
-}
-/* ------------------------------------------------------------------------
-   This function writes the information about the request processing
-   in the trace buffer. Trace ID is 220.
-   INPUT:
-   Adapter - system unicue adapter number (0 ... 255)
-   Id      - Id of the entity that had sent this request
-   Ch      - Channel of the entity that had sent this request
-   Req     - Code of the request
-   type    - the Id that was sent by the ASSIGN of this entity.
-   This should be global Id like NL_ID, DSIG_ID, MAN_ID.
-   An unknown Id will cause "?-" in the front of the request.
-   In this case the log.c is to be extended.
-   ------------------------------------------------------------------------ */
-static void xdi_xlog_request(byte Adapter, byte Id,
-			     byte Ch, byte Req, byte type) {
-#if defined(XDI_USE_XLOG)
-	word LogInfo[3];
-	PUT_WORD(&LogInfo[0], ((word)Adapter | (word)(xdi_xlog_sec++ << 8)));
-	PUT_WORD(&LogInfo[1], ((word)Id | (word)(Ch << 8)));
-	PUT_WORD(&LogInfo[2], ((word)Req | (word)(type << 8)));
-	xdi_xlog((byte *)&LogInfo[0], 220, sizeof(LogInfo));
-#endif
-}
-/* ------------------------------------------------------------------------
-   This function writes the information about the indication processing
-   in the trace buffer. Trace ID is 222.
-   INPUT:
-   Adapter - system unicue adapter number (0 ... 255)
-   Id      - Id of the entity that had sent this indication
-   Ch      - Channel of the entity that had sent this indication
-   Ind     - Code of the indication
-   rnr_valid: (0 .. 3) supported
-   switch (rnr_valid) {
-   case 0: printf ("DELIVERY"); break;
-   case 1: printf ("RNR=%d", rnr);
-   case 2: printf ("RNum=0");
-   case 3: printf ("COMPLETE");
-   }
-   DELIVERY - indication entered isdn_rc function
-   RNR=...  - application had returned RNR=... after the
-   look ahead callback
-   RNum=0   - application had not returned any buffer to copy
-   this indication and will copy it self
-   COMPLETE - XDI had copied the data to the buffers provided
-   bu the application and is about to issue the
-   final callback
-   rnr:  Look case 1 of the rnr_valid
-   type: the Id that was sent by the ASSIGN of this entity. This should
-   be global Id like NL_ID, DSIG_ID, MAN_ID. An unknown Id will
-   cause "?-" in the front of the request. In this case the
-   log.c is to be extended.
-   ------------------------------------------------------------------------ */
-static void xdi_xlog_ind(byte Adapter,
-			 byte Id,
-			 byte Ch,
-			 byte Ind,
-			 byte rnr_valid,
-			 byte rnr,
-			 byte type) {
-#if defined(XDI_USE_XLOG)
-	word LogInfo[4];
-	PUT_WORD(&LogInfo[0], ((word)Adapter | (word)(xdi_xlog_sec++ << 8)));
-	PUT_WORD(&LogInfo[1], ((word)Id | (word)(Ch << 8)));
-	PUT_WORD(&LogInfo[2], ((word)Ind | (word)(type << 8)));
-	PUT_WORD(&LogInfo[3], ((word)rnr | (word)(rnr_valid << 8)));
-	xdi_xlog((byte *)&LogInfo[0], 222, sizeof(LogInfo));
-#endif
-}
diff --git a/drivers/isdn/hardware/eicon/di.h b/drivers/isdn/hardware/eicon/di.h
deleted file mode 100644
index ff26c65631d6..000000000000
--- a/drivers/isdn/hardware/eicon/di.h
+++ /dev/null
@@ -1,118 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-/*
- *  some macros for detailed trace management
- */
-#include "di_dbg.h"
-/*****************************************************************************/
-#define XMOREC 0x1f
-#define XMOREF 0x20
-#define XBUSY  0x40
-#define RMORE  0x80
-#define DIVA_MISC_FLAGS_REMOVE_PENDING    0x01
-#define DIVA_MISC_FLAGS_NO_RC_CANCELLING  0x02
-#define DIVA_MISC_FLAGS_RX_DMA            0x04
-/* structure for all information we have to keep on a per   */
-/* adapater basis                                           */
-typedef struct adapter_s ADAPTER;
-struct adapter_s {
-	void *io;
-	byte IdTable[256];
-	byte IdTypeTable[256];
-	byte FlowControlIdTable[256];
-	byte FlowControlSkipTable[256];
-	byte ReadyInt;
-	byte RcExtensionSupported;
-	byte misc_flags_table[256];
-	dword protocol_capabilities;
-	byte (*ram_in)(ADAPTER *a, void *adr);
-	word (*ram_inw)(ADAPTER *a, void *adr);
-	void (*ram_in_buffer)(ADAPTER *a, void *adr, void *P, word length);
-	void (*ram_look_ahead)(ADAPTER *a, PBUFFER *RBuffer, ENTITY *e);
-	void (*ram_out)(ADAPTER *a, void *adr, byte data);
-	void (*ram_outw)(ADAPTER *a, void *adr, word data);
-	void (*ram_out_buffer)(ADAPTER *a, void *adr, void *P, word length);
-	void (*ram_inc)(ADAPTER *a, void *adr);
-#if defined(DIVA_ISTREAM)
-	dword rx_stream[256];
-	dword tx_stream[256];
-	word tx_pos[256];
-	word rx_pos[256];
-	byte stream_buffer[2512];
-	dword (*ram_offset)(ADAPTER *a);
-	void (*ram_out_dw)(ADAPTER *a,
-			   void *addr,
-			   const dword *data,
-			   int dwords);
-	void (*ram_in_dw)(ADAPTER *a,
-			  void *addr,
-			  dword *data,
-			  int dwords);
-	void (*istream_wakeup)(ADAPTER *a);
-#else
-	byte stream_buffer[4];
-#endif
-};
-/*------------------------------------------------------------------*/
-/* public functions of IDI common code                              */
-/*------------------------------------------------------------------*/
-void pr_out(ADAPTER *a);
-byte pr_dpc(ADAPTER *a);
-byte scom_test_int(ADAPTER *a);
-void scom_clear_int(ADAPTER *a);
-/*------------------------------------------------------------------*/
-/* OS specific functions used by IDI common code                    */
-/*------------------------------------------------------------------*/
-void free_entity(ADAPTER *a, byte e_no);
-void assign_queue(ADAPTER *a, byte e_no, word ref);
-byte get_assign(ADAPTER *a, word ref);
-void req_queue(ADAPTER *a, byte e_no);
-byte look_req(ADAPTER *a);
-void next_req(ADAPTER *a);
-ENTITY *entity_ptr(ADAPTER *a, byte e_no);
-#if defined(DIVA_ISTREAM)
-struct _diva_xdi_stream_interface;
-void diva_xdi_provide_istream_info(ADAPTER *a,
-				   struct _diva_xdi_stream_interface *pI);
-void pr_stream(ADAPTER *a);
-int diva_istream_write(void *context,
-		       int Id,
-		       void *data,
-		       int length,
-		       int final,
-		       byte usr1,
-		       byte usr2);
-int diva_istream_read(void *context,
-		      int Id,
-		      void *data,
-		      int max_length,
-		      int *final,
-		      byte *usr1,
-		      byte *usr2);
-#if defined(DIVA_IDI_RX_DMA)
-#include "diva_dma.h"
-#endif
-#endif
diff --git a/drivers/isdn/hardware/eicon/di_dbg.h b/drivers/isdn/hardware/eicon/di_dbg.h
deleted file mode 100644
index 1380b60e526e..000000000000
--- a/drivers/isdn/hardware/eicon/di_dbg.h
+++ /dev/null
@@ -1,37 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_DI_DBG_INC__
-#define __DIVA_DI_DBG_INC__
-#if !defined(dtrc)
-#define dtrc(a)
-#endif
-#if !defined(dbug)
-#define dbug(a)
-#endif
-#if !defined USE_EXTENDED_DEBUGS
-extern void (*dprintf)(char*, ...);
-#endif
-#endif
diff --git a/drivers/isdn/hardware/eicon/di_defs.h b/drivers/isdn/hardware/eicon/di_defs.h
deleted file mode 100644
index a5094d221086..000000000000
--- a/drivers/isdn/hardware/eicon/di_defs.h
+++ /dev/null
@@ -1,181 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef _DI_DEFS_
-#define _DI_DEFS_
-/* typedefs for our data structures                         */
-typedef struct get_name_s GET_NAME;
-/*  The entity_s structure is used to pass all
-    parameters between application and IDI   */
-typedef struct entity_s ENTITY;
-typedef struct buffers_s BUFFERS;
-typedef struct postcall_s POSTCALL;
-typedef struct get_para_s GET_PARA;
-#define BOARD_NAME_LENGTH 9
-#define IDI_CALL_LINK_T
-#define IDI_CALL_ENTITY_T
-/* typedef void ( * IDI_CALL)(ENTITY *); */
-/* --------------------------------------------------------
-   IDI_CALL
-   -------------------------------------------------------- */
-typedef void (IDI_CALL_LINK_T *IDI_CALL)(ENTITY IDI_CALL_ENTITY_T *);
-typedef struct {
-	word length;          /* length of data/parameter field           */
-	byte P[270];          /* data/parameter field                     */
-} DBUFFER;
-struct get_name_s {
-	word command;         /* command = 0x0100 */
-	byte name[BOARD_NAME_LENGTH];
-};
-struct postcall_s {
-	word      command;                           /* command = 0x0300 */
-	word      dummy;                             /* not used */
-	void      (*callback)(void *);      /* call back */
-	void      *context;                          /* context pointer */
-};
-#define REQ_PARA            0x0600   /* request command line parameters */
-#define REQ_PARA_LEN             1   /* number of data bytes */
-#define L1_STARTUP_DOWN_POS      0   /* '-y' command line parameter in......*/
-#define L1_STARTUP_DOWN_MSK   0x01   /* first byte position (index 0) with value 0x01 */
-struct get_para_s {
-	word  command;            /* command = 0x0600 */
-	byte  len;                /* max length of para field in bytes */
-	byte  para[REQ_PARA_LEN]; /* parameter field */
-};
-struct buffers_s {
-	word PLength;
-	byte *P;
-};
-struct entity_s {
-	byte                  Req;            /* pending request          */
-	byte                  Rc;             /* return code received     */
-	byte                  Ind;            /* indication received      */
-	byte                  ReqCh;          /* channel of current Req   */
-	byte                  RcCh;           /* channel of current Rc    */
-	byte                  IndCh;          /* channel of current Ind   */
-	byte                  Id;             /* ID used by this entity   */
-	byte                  GlobalId;       /* reserved field           */
-	byte                  XNum;           /* number of X-buffers      */
-	byte                  RNum;           /* number of R-buffers      */
-	BUFFERS               *X;             /* pointer to X-buffer list */
-	BUFFERS               *R;             /* pointer to R-buffer list */
-	word                  RLength;        /* length of current R-data */
-	DBUFFER               *RBuffer;       /* buffer of current R-data */
-	byte                  RNR;            /* receive not ready flag   */
-	byte                  complete;       /* receive complete status  */
-	IDI_CALL              callback;
-	word                  user[2];
-	/* fields used by the driver internally                     */
-	byte                  No;             /* entity number            */
-	byte                  reserved2;      /* reserved field           */
-	byte                  More;           /* R/X More flags           */
-	byte                  MInd;           /* MDATA coding for this ID */
-	byte                  XCurrent;       /* current transmit buffer  */
-	byte                  RCurrent;       /* current receive buffer   */
-	word                  XOffset;        /* offset in x-buffer       */
-	word                  ROffset;        /* offset in r-buffer       */
-};
-typedef struct {
-	byte                  type;
-	byte                  channels;
-	word                  features;
-	IDI_CALL              request;
-} DESCRIPTOR;
-/* descriptor type field coding */
-#define IDI_ADAPTER_S           1
-#define IDI_ADAPTER_PR          2
-#define IDI_ADAPTER_DIVA        3
-#define IDI_ADAPTER_MAESTRA     4
-#define IDI_VADAPTER            0x40
-#define IDI_DRIVER              0x80
-#define IDI_DADAPTER            0xfd
-#define IDI_DIDDPNP             0xfe
-#define IDI_DIMAINT             0xff
-/* Hardware IDs ISA PNP */
-#define HW_ID_DIVA_PRO     3    /* same as IDI_ADAPTER_DIVA    */
-#define HW_ID_MAESTRA      4    /* same as IDI_ADAPTER_MAESTRA */
-#define HW_ID_PICCOLA      5
-#define HW_ID_DIVA_PRO20   6
-#define HW_ID_DIVA20       7
-#define HW_ID_DIVA_PRO20_U 8
-#define HW_ID_DIVA20_U     9
-#define HW_ID_DIVA30       10
-#define HW_ID_DIVA30_U     11
-/* Hardware IDs PCI */
-#define HW_ID_EICON_PCI              0x1133
-#define HW_ID_SIEMENS_PCI            0x8001 /* unused SubVendor ID for Siemens Cornet-N cards */
-#define HW_ID_PROTTYPE_CORNETN       0x0014 /* SubDevice ID for Siemens Cornet-N cards */
-#define HW_ID_FUJITSU_SIEMENS_PCI    0x110A /* SubVendor ID for Fujitsu Siemens */
-#define HW_ID_GS03_PCI               0x0021 /* SubDevice ID for Fujitsu Siemens ISDN S0 card */
-#define HW_ID_DIVA_PRO20_PCI         0xe001
-#define HW_ID_DIVA20_PCI             0xe002
-#define HW_ID_DIVA_PRO20_PCI_U       0xe003
-#define HW_ID_DIVA20_PCI_U           0xe004
-#define HW_ID_DIVA201_PCI            0xe005
-#define HW_ID_DIVA_CT_ST             0xe006
-#define HW_ID_DIVA_CT_U              0xe007
-#define HW_ID_DIVA_CTL_ST            0xe008
-#define HW_ID_DIVA_CTL_U             0xe009
-#define HW_ID_DIVA_ISDN_V90_PCI      0xe00a
-#define HW_ID_DIVA202_PCI_ST         0xe00b
-#define HW_ID_DIVA202_PCI_U          0xe00c
-#define HW_ID_DIVA_PRO30_PCI         0xe00d
-#define HW_ID_MAESTRA_PCI            0xe010
-#define HW_ID_MAESTRAQ_PCI           0xe012
-#define HW_ID_DSRV_Q8M_V2_PCI        0xe013
-#define HW_ID_MAESTRAP_PCI           0xe014
-#define HW_ID_DSRV_P30M_V2_PCI       0xe015
-#define HW_ID_DSRV_VOICE_Q8M_PCI     0xe016
-#define HW_ID_DSRV_VOICE_Q8M_V2_PCI  0xe017
-#define HW_ID_DSRV_B2M_V2_PCI        0xe018
-#define HW_ID_DSRV_VOICE_P30M_V2_PCI 0xe019
-#define HW_ID_DSRV_B2F_PCI           0xe01a
-#define HW_ID_DSRV_VOICE_B2M_V2_PCI  0xe01b
-/* Hardware IDs USB */
-#define EICON_USB_VENDOR_ID          0x071D
-#define HW_ID_DIVA_USB_REV1          0x1000
-#define HW_ID_DIVA_USB_REV2          0x1003
-#define HW_ID_TELEDAT_SURF_USB_REV2  0x1004
-#define HW_ID_TELEDAT_SURF_USB_REV1  0x2000
-/* --------------------------------------------------------------------------
-   Adapter array change notification framework
-   -------------------------------------------------------------------------- */
-typedef void (IDI_CALL_LINK_T *didd_adapter_change_callback_t)(void IDI_CALL_ENTITY_T *context, DESCRIPTOR *adapter, int removal);
-/* -------------------------------------------------------------------------- */
-#define DI_VOICE          0x0 /* obsolete define */
-#define DI_FAX3           0x1
-#define DI_MODEM          0x2
-#define DI_POST           0x4
-#define DI_V110           0x8
-#define DI_V120           0x10
-#define DI_POTS           0x20
-#define DI_CODEC          0x40
-#define DI_MANAGE         0x80
-#define DI_V_42           0x0100
-#define DI_EXTD_FAX       0x0200 /* Extended FAX (ECM, 2D, T.6, Polling) */
-#define DI_AT_PARSER      0x0400 /* Build-in AT Parser in the L2 */
-#define DI_VOICE_OVER_IP  0x0800 /* Voice over IP support */
-typedef void (IDI_CALL_LINK_T *_IDI_CALL)(void *, ENTITY *);
-#endif
diff --git a/drivers/isdn/hardware/eicon/did_vers.h b/drivers/isdn/hardware/eicon/did_vers.h
deleted file mode 100644
index fa8db8249235..000000000000
--- a/drivers/isdn/hardware/eicon/did_vers.h
+++ /dev/null
@@ -1,26 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-static char diva_didd_common_code_build[] = "102-51";
diff --git a/drivers/isdn/hardware/eicon/diddfunc.c b/drivers/isdn/hardware/eicon/diddfunc.c
deleted file mode 100644
index b0b23ed8b374..000000000000
--- a/drivers/isdn/hardware/eicon/diddfunc.c
+++ /dev/null
@@ -1,115 +0,0 @@
-/* $Id: diddfunc.c,v 1.14.6.2 2004/08/28 20:03:53 armin Exp $
- *
- * DIDD Interface module for Eicon active cards.
- *
- * Functions are in dadapter.c
- *
- * Copyright 2002-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2002-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#include "platform.h"
-#include "di_defs.h"
-#include "dadapter.h"
-#include "divasync.h"
-
-#define DBG_MINIMUM  (DL_LOG + DL_FTL + DL_ERR)
-#define DBG_DEFAULT  (DBG_MINIMUM + DL_XLOG + DL_REG)
-
-
-extern void DIVA_DIDD_Read(void *, int);
-extern char *DRIVERRELEASE_DIDD;
-static dword notify_handle;
-static DESCRIPTOR _DAdapter;
-
-/*
- * didd callback function
- */
-static void *didd_callback(void *context, DESCRIPTOR *adapter,
-			   int removal)
-{
-	if (adapter->type == IDI_DADAPTER) {
-		DBG_ERR(("Notification about IDI_DADAPTER change ! Oops."))
-			return (NULL);
-	} else if (adapter->type == IDI_DIMAINT) {
-		if (removal) {
-			DbgDeregister();
-		} else {
-			DbgRegister("DIDD", DRIVERRELEASE_DIDD, DBG_DEFAULT);
-		}
-	}
-	return (NULL);
-}
-
-/*
- * connect to didd
- */
-static int __init connect_didd(void)
-{
-	int x = 0;
-	int dadapter = 0;
-	IDI_SYNC_REQ req;
-	DESCRIPTOR DIDD_Table[MAX_DESCRIPTORS];
-
-	DIVA_DIDD_Read(DIDD_Table, sizeof(DIDD_Table));
-
-	for (x = 0; x < MAX_DESCRIPTORS; x++) {
-		if (DIDD_Table[x].type == IDI_DADAPTER) {	/* DADAPTER found */
-			dadapter = 1;
-			memcpy(&_DAdapter, &DIDD_Table[x], sizeof(_DAdapter));
-			req.didd_notify.e.Req = 0;
-			req.didd_notify.e.Rc =
-				IDI_SYNC_REQ_DIDD_REGISTER_ADAPTER_NOTIFY;
-			req.didd_notify.info.callback = (void *)didd_callback;
-			req.didd_notify.info.context = NULL;
-			_DAdapter.request((ENTITY *)&req);
-			if (req.didd_notify.e.Rc != 0xff)
-				return (0);
-			notify_handle = req.didd_notify.info.handle;
-		} else if (DIDD_Table[x].type == IDI_DIMAINT) {	/* MAINT found */
-			DbgRegister("DIDD", DRIVERRELEASE_DIDD, DBG_DEFAULT);
-		}
-	}
-	return (dadapter);
-}
-
-/*
- * disconnect from didd
- */
-static void __exit disconnect_didd(void)
-{
-	IDI_SYNC_REQ req;
-
-	req.didd_notify.e.Req = 0;
-	req.didd_notify.e.Rc = IDI_SYNC_REQ_DIDD_REMOVE_ADAPTER_NOTIFY;
-	req.didd_notify.info.handle = notify_handle;
-	_DAdapter.request((ENTITY *)&req);
-}
-
-/*
- * init
- */
-int __init diddfunc_init(void)
-{
-	diva_didd_load_time_init();
-
-	if (!connect_didd()) {
-		DBG_ERR(("init: failed to connect to DIDD."))
-			diva_didd_load_time_finit();
-		return (0);
-	}
-	return (1);
-}
-
-/*
- * finit
- */
-void __exit diddfunc_finit(void)
-{
-	DbgDeregister();
-	disconnect_didd();
-	diva_didd_load_time_finit();
-}
diff --git a/drivers/isdn/hardware/eicon/diva.c b/drivers/isdn/hardware/eicon/diva.c
deleted file mode 100644
index 1b25d8bc153a..000000000000
--- a/drivers/isdn/hardware/eicon/diva.c
+++ /dev/null
@@ -1,666 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* $Id: diva.c,v 1.21.4.1 2004/05/08 14:33:43 armin Exp $ */
-
-#define CARDTYPE_H_WANT_DATA            1
-#define CARDTYPE_H_WANT_IDI_DATA        0
-#define CARDTYPE_H_WANT_RESOURCE_DATA   0
-#define CARDTYPE_H_WANT_FILE_DATA       0
-
-#include "platform.h"
-#include "debuglib.h"
-#include "cardtype.h"
-#include "pc.h"
-#include "di_defs.h"
-#include "di.h"
-#include "io.h"
-#include "pc_maint.h"
-#include "xdi_msg.h"
-#include "xdi_adapter.h"
-#include "diva_pci.h"
-#include "diva.h"
-
-#ifdef CONFIG_ISDN_DIVAS_PRIPCI
-#include "os_pri.h"
-#endif
-#ifdef CONFIG_ISDN_DIVAS_BRIPCI
-#include "os_bri.h"
-#include "os_4bri.h"
-#endif
-
-PISDN_ADAPTER IoAdapters[MAX_ADAPTER];
-extern IDI_CALL Requests[MAX_ADAPTER];
-extern int create_adapter_proc(diva_os_xdi_adapter_t *a);
-extern void remove_adapter_proc(diva_os_xdi_adapter_t *a);
-
-#define DivaIdiReqFunc(N)						\
-	static void DivaIdiRequest##N(ENTITY *e)			\
-	{ if (IoAdapters[N]) (*IoAdapters[N]->DIRequest)(IoAdapters[N], e); }
-
-/*
-**  Create own 32 Adapters
-*/
-DivaIdiReqFunc(0)
-DivaIdiReqFunc(1)
-DivaIdiReqFunc(2)
-DivaIdiReqFunc(3)
-DivaIdiReqFunc(4)
-DivaIdiReqFunc(5)
-DivaIdiReqFunc(6)
-DivaIdiReqFunc(7)
-DivaIdiReqFunc(8)
-DivaIdiReqFunc(9)
-DivaIdiReqFunc(10)
-DivaIdiReqFunc(11)
-DivaIdiReqFunc(12)
-DivaIdiReqFunc(13)
-DivaIdiReqFunc(14)
-DivaIdiReqFunc(15)
-DivaIdiReqFunc(16)
-DivaIdiReqFunc(17)
-DivaIdiReqFunc(18)
-DivaIdiReqFunc(19)
-DivaIdiReqFunc(20)
-DivaIdiReqFunc(21)
-DivaIdiReqFunc(22)
-DivaIdiReqFunc(23)
-DivaIdiReqFunc(24)
-DivaIdiReqFunc(25)
-DivaIdiReqFunc(26)
-DivaIdiReqFunc(27)
-DivaIdiReqFunc(28)
-DivaIdiReqFunc(29)
-DivaIdiReqFunc(30)
-DivaIdiReqFunc(31)
-
-/*
-**  LOCALS
-*/
-static LIST_HEAD(adapter_queue);
-
-typedef struct _diva_get_xlog {
-	word command;
-	byte req;
-	byte rc;
-	byte data[sizeof(struct mi_pc_maint)];
-} diva_get_xlog_t;
-
-typedef struct _diva_supported_cards_info {
-	int CardOrdinal;
-	diva_init_card_proc_t init_card;
-} diva_supported_cards_info_t;
-
-static diva_supported_cards_info_t divas_supported_cards[] = {
-#ifdef CONFIG_ISDN_DIVAS_PRIPCI
-	/*
-	  PRI Cards
-	*/
-	{CARDTYPE_DIVASRV_P_30M_PCI, diva_pri_init_card},
-	/*
-	  PRI Rev.2 Cards
-	*/
-	{CARDTYPE_DIVASRV_P_30M_V2_PCI, diva_pri_init_card},
-	/*
-	  PRI Rev.2 VoIP Cards
-	*/
-	{CARDTYPE_DIVASRV_VOICE_P_30M_V2_PCI, diva_pri_init_card},
-#endif
-#ifdef CONFIG_ISDN_DIVAS_BRIPCI
-	/*
-	  4BRI Rev 1 Cards
-	*/
-	{CARDTYPE_DIVASRV_Q_8M_PCI, diva_4bri_init_card},
-	{CARDTYPE_DIVASRV_VOICE_Q_8M_PCI, diva_4bri_init_card},
-	/*
-	  4BRI Rev 2 Cards
-	*/
-	{CARDTYPE_DIVASRV_Q_8M_V2_PCI, diva_4bri_init_card},
-	{CARDTYPE_DIVASRV_VOICE_Q_8M_V2_PCI, diva_4bri_init_card},
-	/*
-	  4BRI Based BRI Rev 2 Cards
-	*/
-	{CARDTYPE_DIVASRV_B_2M_V2_PCI, diva_4bri_init_card},
-	{CARDTYPE_DIVASRV_B_2F_PCI, diva_4bri_init_card},
-	{CARDTYPE_DIVASRV_VOICE_B_2M_V2_PCI, diva_4bri_init_card},
-	/*
-	  BRI
-	*/
-	{CARDTYPE_MAESTRA_PCI, diva_bri_init_card},
-#endif
-
-	/*
-	  EOL
-	*/
-	{-1}
-};
-
-static void diva_init_request_array(void);
-static void *divas_create_pci_card(int handle, void *pci_dev_handle);
-
-static diva_os_spin_lock_t adapter_lock;
-
-static int diva_find_free_adapters(int base, int nr)
-{
-	int i;
-
-	for (i = 0; i < nr; i++) {
-		if (IoAdapters[base + i]) {
-			return (-1);
-		}
-	}
-
-	return (0);
-}
-
-static diva_os_xdi_adapter_t *diva_q_get_next(struct list_head *what)
-{
-	diva_os_xdi_adapter_t *a = NULL;
-
-	if (what && (what->next != &adapter_queue))
-		a = list_entry(what->next, diva_os_xdi_adapter_t, link);
-
-	return (a);
-}
-
-/* --------------------------------------------------------------------------
-   Add card to the card list
-   -------------------------------------------------------------------------- */
-void *diva_driver_add_card(void *pdev, unsigned long CardOrdinal)
-{
-	diva_os_spin_lock_magic_t old_irql;
-	diva_os_xdi_adapter_t *pdiva, *pa;
-	int i, j, max, nr;
-
-	for (i = 0; divas_supported_cards[i].CardOrdinal != -1; i++) {
-		if (divas_supported_cards[i].CardOrdinal == CardOrdinal) {
-			if (!(pdiva = divas_create_pci_card(i, pdev))) {
-				return NULL;
-			}
-			switch (CardOrdinal) {
-			case CARDTYPE_DIVASRV_Q_8M_PCI:
-			case CARDTYPE_DIVASRV_VOICE_Q_8M_PCI:
-			case CARDTYPE_DIVASRV_Q_8M_V2_PCI:
-			case CARDTYPE_DIVASRV_VOICE_Q_8M_V2_PCI:
-				max = MAX_ADAPTER - 4;
-				nr = 4;
-				break;
-
-			default:
-				max = MAX_ADAPTER;
-				nr = 1;
-			}
-
-			diva_os_enter_spin_lock(&adapter_lock, &old_irql, "add card");
-
-			for (i = 0; i < max; i++) {
-				if (!diva_find_free_adapters(i, nr)) {
-					pdiva->controller = i + 1;
-					pdiva->xdi_adapter.ANum = pdiva->controller;
-					IoAdapters[i] = &pdiva->xdi_adapter;
-					diva_os_leave_spin_lock(&adapter_lock, &old_irql, "add card");
-					create_adapter_proc(pdiva);	/* add adapter to proc file system */
-
-					DBG_LOG(("add %s:%d",
-						 CardProperties
-						 [CardOrdinal].Name,
-						 pdiva->controller))
-
-						diva_os_enter_spin_lock(&adapter_lock, &old_irql, "add card");
-					pa = pdiva;
-					for (j = 1; j < nr; j++) {	/* slave adapters, if any */
-						pa = diva_q_get_next(&pa->link);
-						if (pa && !pa->interface.cleanup_adapter_proc) {
-							pa->controller = i + 1 + j;
-							pa->xdi_adapter.ANum = pa->controller;
-							IoAdapters[i + j] = &pa->xdi_adapter;
-							diva_os_leave_spin_lock(&adapter_lock, &old_irql, "add card");
-							DBG_LOG(("add slave adapter (%d)",
-								 pa->controller))
-								create_adapter_proc(pa);	/* add adapter to proc file system */
-							diva_os_enter_spin_lock(&adapter_lock, &old_irql, "add card");
-						} else {
-							DBG_ERR(("slave adapter problem"))
-								break;
-						}
-					}
-
-					diva_os_leave_spin_lock(&adapter_lock, &old_irql, "add card");
-					return (pdiva);
-				}
-			}
-
-			diva_os_leave_spin_lock(&adapter_lock, &old_irql, "add card");
-
-			/*
-			  Not able to add adapter - remove it and return error
-			*/
-			DBG_ERR(("can not alloc request array"))
-				diva_driver_remove_card(pdiva);
-
-			return NULL;
-		}
-	}
-
-	return NULL;
-}
-
-/* --------------------------------------------------------------------------
-   Called on driver load, MAIN, main, DriverEntry
-   -------------------------------------------------------------------------- */
-int divasa_xdi_driver_entry(void)
-{
-	diva_os_initialize_spin_lock(&adapter_lock, "adapter");
-	memset(&IoAdapters[0], 0x00, sizeof(IoAdapters));
-	diva_init_request_array();
-
-	return (0);
-}
-
-/* --------------------------------------------------------------------------
-   Remove adapter from list
-   -------------------------------------------------------------------------- */
-static diva_os_xdi_adapter_t *get_and_remove_from_queue(void)
-{
-	diva_os_spin_lock_magic_t old_irql;
-	diva_os_xdi_adapter_t *a = NULL;
-
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "driver_unload");
-
-	if (!list_empty(&adapter_queue)) {
-		a = list_entry(adapter_queue.next, diva_os_xdi_adapter_t, link);
-		list_del(adapter_queue.next);
-	}
-
-	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "driver_unload");
-	return (a);
-}
-
-/* --------------------------------------------------------------------------
-   Remove card from the card list
-   -------------------------------------------------------------------------- */
-void diva_driver_remove_card(void *pdiva)
-{
-	diva_os_spin_lock_magic_t old_irql;
-	diva_os_xdi_adapter_t *a[4];
-	diva_os_xdi_adapter_t *pa;
-	int i;
-
-	pa = a[0] = (diva_os_xdi_adapter_t *) pdiva;
-	a[1] = a[2] = a[3] = NULL;
-
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "remode adapter");
-
-	for (i = 1; i < 4; i++) {
-		if ((pa = diva_q_get_next(&pa->link))
-		    && !pa->interface.cleanup_adapter_proc) {
-			a[i] = pa;
-		} else {
-			break;
-		}
-	}
-
-	for (i = 0; ((i < 4) && a[i]); i++) {
-		list_del(&a[i]->link);
-	}
-
-	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "driver_unload");
-
-	(*(a[0]->interface.cleanup_adapter_proc)) (a[0]);
-
-	for (i = 0; i < 4; i++) {
-		if (a[i]) {
-			if (a[i]->controller) {
-				DBG_LOG(("remove adapter (%d)",
-					 a[i]->controller)) IoAdapters[a[i]->controller - 1] = NULL;
-				remove_adapter_proc(a[i]);
-			}
-			diva_os_free(0, a[i]);
-		}
-	}
-}
-
-/* --------------------------------------------------------------------------
-   Create diva PCI adapter and init internal adapter structures
-   -------------------------------------------------------------------------- */
-static void *divas_create_pci_card(int handle, void *pci_dev_handle)
-{
-	diva_supported_cards_info_t *pI = &divas_supported_cards[handle];
-	diva_os_spin_lock_magic_t old_irql;
-	diva_os_xdi_adapter_t *a;
-
-	DBG_LOG(("found %d-%s", pI->CardOrdinal, CardProperties[pI->CardOrdinal].Name))
-
-		if (!(a = (diva_os_xdi_adapter_t *) diva_os_malloc(0, sizeof(*a)))) {
-			DBG_ERR(("A: can't alloc adapter"));
-			return NULL;
-		}
-
-	memset(a, 0x00, sizeof(*a));
-
-	a->CardIndex = handle;
-	a->CardOrdinal = pI->CardOrdinal;
-	a->Bus = DIVAS_XDI_ADAPTER_BUS_PCI;
-	a->xdi_adapter.cardType = a->CardOrdinal;
-	a->resources.pci.bus = diva_os_get_pci_bus(pci_dev_handle);
-	a->resources.pci.func = diva_os_get_pci_func(pci_dev_handle);
-	a->resources.pci.hdev = pci_dev_handle;
-
-	/*
-	  Add master adapter first, so slave adapters will receive higher
-	  numbers as master adapter
-	*/
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "found_pci_card");
-	list_add_tail(&a->link, &adapter_queue);
-	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "found_pci_card");
-
-	if ((*(pI->init_card)) (a)) {
-		diva_os_enter_spin_lock(&adapter_lock, &old_irql, "found_pci_card");
-		list_del(&a->link);
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "found_pci_card");
-		diva_os_free(0, a);
-		DBG_ERR(("A: can't get adapter resources"));
-		return NULL;
-	}
-
-	return (a);
-}
-
-/* --------------------------------------------------------------------------
-   Called on driver unload FINIT, finit, Unload
-   -------------------------------------------------------------------------- */
-void divasa_xdi_driver_unload(void)
-{
-	diva_os_xdi_adapter_t *a;
-
-	while ((a = get_and_remove_from_queue())) {
-		if (a->interface.cleanup_adapter_proc) {
-			(*(a->interface.cleanup_adapter_proc)) (a);
-		}
-		if (a->controller) {
-			IoAdapters[a->controller - 1] = NULL;
-			remove_adapter_proc(a);
-		}
-		diva_os_free(0, a);
-	}
-	diva_os_destroy_spin_lock(&adapter_lock, "adapter");
-}
-
-/*
-**  Receive and process command from user mode utility
-*/
-void *diva_xdi_open_adapter(void *os_handle, const void __user *src,
-			    int length, void *mptr,
-			    divas_xdi_copy_from_user_fn_t cp_fn)
-{
-	diva_xdi_um_cfg_cmd_t *msg = (diva_xdi_um_cfg_cmd_t *)mptr;
-	diva_os_xdi_adapter_t *a = NULL;
-	diva_os_spin_lock_magic_t old_irql;
-	struct list_head *tmp;
-
-	if (length < sizeof(diva_xdi_um_cfg_cmd_t)) {
-		DBG_ERR(("A: A(?) open, msg too small (%d < %d)",
-			 length, sizeof(diva_xdi_um_cfg_cmd_t)))
-			return NULL;
-	}
-	if ((*cp_fn) (os_handle, msg, src, sizeof(*msg)) <= 0) {
-		DBG_ERR(("A: A(?) open, write error"))
-			return NULL;
-	}
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "open_adapter");
-	list_for_each(tmp, &adapter_queue) {
-		a = list_entry(tmp, diva_os_xdi_adapter_t, link);
-		if (a->controller == (int)msg->adapter)
-			break;
-		a = NULL;
-	}
-	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "open_adapter");
-
-	if (!a) {
-		DBG_ERR(("A: A(%d) open, adapter not found", msg->adapter))
-			}
-
-	return (a);
-}
-
-/*
-**  Easy cleanup mailbox status
-*/
-void diva_xdi_close_adapter(void *adapter, void *os_handle)
-{
-	diva_os_xdi_adapter_t *a = (diva_os_xdi_adapter_t *) adapter;
-
-	a->xdi_mbox.status &= ~DIVA_XDI_MBOX_BUSY;
-	if (a->xdi_mbox.data) {
-		diva_os_free(0, a->xdi_mbox.data);
-		a->xdi_mbox.data = NULL;
-	}
-}
-
-int
-diva_xdi_write(void *adapter, void *os_handle, const void __user *src,
-	       int length, void *mptr,
-	       divas_xdi_copy_from_user_fn_t cp_fn)
-{
-	diva_xdi_um_cfg_cmd_t *msg = (diva_xdi_um_cfg_cmd_t *)mptr;
-	diva_os_xdi_adapter_t *a = (diva_os_xdi_adapter_t *) adapter;
-	void *data;
-
-	if (a->xdi_mbox.status & DIVA_XDI_MBOX_BUSY) {
-		DBG_ERR(("A: A(%d) write, mbox busy", a->controller))
-			return (-1);
-	}
-
-	if (length < sizeof(diva_xdi_um_cfg_cmd_t)) {
-		DBG_ERR(("A: A(%d) write, message too small (%d < %d)",
-			 a->controller, length,
-			 sizeof(diva_xdi_um_cfg_cmd_t)))
-			return (-3);
-	}
-
-	if (!(data = diva_os_malloc(0, length))) {
-		DBG_ERR(("A: A(%d) write, ENOMEM", a->controller))
-			return (-2);
-	}
-
-	if (msg) {
-		*(diva_xdi_um_cfg_cmd_t *)data = *msg;
-		length = (*cp_fn) (os_handle, (char *)data + sizeof(*msg),
-				   src + sizeof(*msg), length - sizeof(*msg));
-	} else {
-		length = (*cp_fn) (os_handle, data, src, length);
-	}
-	if (length > 0) {
-		if ((*(a->interface.cmd_proc))
-		    (a, (diva_xdi_um_cfg_cmd_t *) data, length)) {
-			length = -3;
-		}
-	} else {
-		DBG_ERR(("A: A(%d) write error (%d)", a->controller,
-			 length))
-			}
-
-	diva_os_free(0, data);
-
-	return (length);
-}
-
-/*
-**  Write answers to user mode utility, if any
-*/
-int
-diva_xdi_read(void *adapter, void *os_handle, void __user *dst,
-	      int max_length, divas_xdi_copy_to_user_fn_t cp_fn)
-{
-	diva_os_xdi_adapter_t *a = (diva_os_xdi_adapter_t *) adapter;
-	int ret;
-
-	if (!(a->xdi_mbox.status & DIVA_XDI_MBOX_BUSY)) {
-		DBG_ERR(("A: A(%d) rx mbox empty", a->controller))
-			return (-1);
-	}
-	if (!a->xdi_mbox.data) {
-		a->xdi_mbox.status &= ~DIVA_XDI_MBOX_BUSY;
-		DBG_ERR(("A: A(%d) rx ENOMEM", a->controller))
-			return (-2);
-	}
-
-	if (max_length < a->xdi_mbox.data_length) {
-		DBG_ERR(("A: A(%d) rx buffer too short(%d < %d)",
-			 a->controller, max_length,
-			 a->xdi_mbox.data_length))
-			return (-3);
-	}
-
-	ret = (*cp_fn) (os_handle, dst, a->xdi_mbox.data,
-			a->xdi_mbox.data_length);
-	if (ret > 0) {
-		diva_os_free(0, a->xdi_mbox.data);
-		a->xdi_mbox.data = NULL;
-		a->xdi_mbox.status &= ~DIVA_XDI_MBOX_BUSY;
-	}
-
-	return (ret);
-}
-
-
-irqreturn_t diva_os_irq_wrapper(int irq, void *context)
-{
-	diva_os_xdi_adapter_t *a = context;
-	diva_xdi_clear_interrupts_proc_t clear_int_proc;
-
-	if (!a || !a->xdi_adapter.diva_isr_handler)
-		return IRQ_NONE;
-
-	if ((clear_int_proc = a->clear_interrupts_proc)) {
-		(*clear_int_proc) (a);
-		a->clear_interrupts_proc = NULL;
-		return IRQ_HANDLED;
-	}
-
-	(*(a->xdi_adapter.diva_isr_handler)) (&a->xdi_adapter);
-	return IRQ_HANDLED;
-}
-
-static void diva_init_request_array(void)
-{
-	Requests[0] = DivaIdiRequest0;
-	Requests[1] = DivaIdiRequest1;
-	Requests[2] = DivaIdiRequest2;
-	Requests[3] = DivaIdiRequest3;
-	Requests[4] = DivaIdiRequest4;
-	Requests[5] = DivaIdiRequest5;
-	Requests[6] = DivaIdiRequest6;
-	Requests[7] = DivaIdiRequest7;
-	Requests[8] = DivaIdiRequest8;
-	Requests[9] = DivaIdiRequest9;
-	Requests[10] = DivaIdiRequest10;
-	Requests[11] = DivaIdiRequest11;
-	Requests[12] = DivaIdiRequest12;
-	Requests[13] = DivaIdiRequest13;
-	Requests[14] = DivaIdiRequest14;
-	Requests[15] = DivaIdiRequest15;
-	Requests[16] = DivaIdiRequest16;
-	Requests[17] = DivaIdiRequest17;
-	Requests[18] = DivaIdiRequest18;
-	Requests[19] = DivaIdiRequest19;
-	Requests[20] = DivaIdiRequest20;
-	Requests[21] = DivaIdiRequest21;
-	Requests[22] = DivaIdiRequest22;
-	Requests[23] = DivaIdiRequest23;
-	Requests[24] = DivaIdiRequest24;
-	Requests[25] = DivaIdiRequest25;
-	Requests[26] = DivaIdiRequest26;
-	Requests[27] = DivaIdiRequest27;
-	Requests[28] = DivaIdiRequest28;
-	Requests[29] = DivaIdiRequest29;
-	Requests[30] = DivaIdiRequest30;
-	Requests[31] = DivaIdiRequest31;
-}
-
-void diva_xdi_display_adapter_features(int card)
-{
-	dword features;
-	if (!card || ((card - 1) >= MAX_ADAPTER) || !IoAdapters[card - 1]) {
-		return;
-	}
-	card--;
-	features = IoAdapters[card]->Properties.Features;
-
-	DBG_LOG(("FEATURES FOR ADAPTER: %d", card + 1))
-		DBG_LOG((" DI_FAX3          :  %s",
-			 (features & DI_FAX3) ? "Y" : "N"))
-		DBG_LOG((" DI_MODEM         :  %s",
-			 (features & DI_MODEM) ? "Y" : "N"))
-		DBG_LOG((" DI_POST          :  %s",
-			 (features & DI_POST) ? "Y" : "N"))
-		DBG_LOG((" DI_V110          :  %s",
-			 (features & DI_V110) ? "Y" : "N"))
-		DBG_LOG((" DI_V120          :  %s",
-			 (features & DI_V120) ? "Y" : "N"))
-		DBG_LOG((" DI_POTS          :  %s",
-			 (features & DI_POTS) ? "Y" : "N"))
-		DBG_LOG((" DI_CODEC         :  %s",
-			 (features & DI_CODEC) ? "Y" : "N"))
-		DBG_LOG((" DI_MANAGE        :  %s",
-			 (features & DI_MANAGE) ? "Y" : "N"))
-		DBG_LOG((" DI_V_42          :  %s",
-			 (features & DI_V_42) ? "Y" : "N"))
-		DBG_LOG((" DI_EXTD_FAX      :  %s",
-			 (features & DI_EXTD_FAX) ? "Y" : "N"))
-		DBG_LOG((" DI_AT_PARSER     :  %s",
-			 (features & DI_AT_PARSER) ? "Y" : "N"))
-		DBG_LOG((" DI_VOICE_OVER_IP :  %s",
-			 (features & DI_VOICE_OVER_IP) ? "Y" : "N"))
-		}
-
-void diva_add_slave_adapter(diva_os_xdi_adapter_t *a)
-{
-	diva_os_spin_lock_magic_t old_irql;
-
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "add_slave");
-	list_add_tail(&a->link, &adapter_queue);
-	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "add_slave");
-}
-
-int diva_card_read_xlog(diva_os_xdi_adapter_t *a)
-{
-	diva_get_xlog_t *req;
-	byte *data;
-
-	if (!a->xdi_adapter.Initialized || !a->xdi_adapter.DIRequest) {
-		return (-1);
-	}
-	if (!(data = diva_os_malloc(0, sizeof(struct mi_pc_maint)))) {
-		return (-1);
-	}
-	memset(data, 0x00, sizeof(struct mi_pc_maint));
-
-	if (!(req = diva_os_malloc(0, sizeof(*req)))) {
-		diva_os_free(0, data);
-		return (-1);
-	}
-	req->command = 0x0400;
-	req->req = LOG;
-	req->rc = 0x00;
-
-	(*(a->xdi_adapter.DIRequest)) (&a->xdi_adapter, (ENTITY *) req);
-
-	if (!req->rc || req->req) {
-		diva_os_free(0, data);
-		diva_os_free(0, req);
-		return (-1);
-	}
-
-	memcpy(data, &req->req, sizeof(struct mi_pc_maint));
-
-	diva_os_free(0, req);
-
-	a->xdi_mbox.data_length = sizeof(struct mi_pc_maint);
-	a->xdi_mbox.data = data;
-	a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-
-	return (0);
-}
-
-void xdiFreeFile(void *handle)
-{
-}
diff --git a/drivers/isdn/hardware/eicon/diva.h b/drivers/isdn/hardware/eicon/diva.h
deleted file mode 100644
index 1ad76650fbf9..000000000000
--- a/drivers/isdn/hardware/eicon/diva.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: diva.h,v 1.1.2.2 2001/02/08 12:25:43 armin Exp $ */
-
-#ifndef __DIVA_XDI_OS_PART_H__
-#define __DIVA_XDI_OS_PART_H__
-
-
-int divasa_xdi_driver_entry(void);
-void divasa_xdi_driver_unload(void);
-void *diva_driver_add_card(void *pdev, unsigned long CardOrdinal);
-void diva_driver_remove_card(void *pdiva);
-
-typedef int (*divas_xdi_copy_to_user_fn_t) (void *os_handle, void __user *dst,
-					    const void *src, int length);
-
-typedef int (*divas_xdi_copy_from_user_fn_t) (void *os_handle, void *dst,
-					      const void __user *src, int length);
-
-int diva_xdi_read(void *adapter, void *os_handle, void __user *dst,
-		  int max_length, divas_xdi_copy_to_user_fn_t cp_fn);
-
-int diva_xdi_write(void *adapter, void *os_handle, const void __user *src,
-		   int length, void *msg,
-		   divas_xdi_copy_from_user_fn_t cp_fn);
-
-void *diva_xdi_open_adapter(void *os_handle, const void __user *src,
-			    int length, void *msg,
-			    divas_xdi_copy_from_user_fn_t cp_fn);
-
-void diva_xdi_close_adapter(void *adapter, void *os_handle);
-
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/diva_didd.c b/drivers/isdn/hardware/eicon/diva_didd.c
deleted file mode 100644
index 60e79257dd5f..000000000000
--- a/drivers/isdn/hardware/eicon/diva_didd.c
+++ /dev/null
@@ -1,139 +0,0 @@
-/* $Id: diva_didd.c,v 1.13.6.4 2005/02/11 19:40:25 armin Exp $
- *
- * DIDD Interface module for Eicon active cards.
- *
- * Functions are in dadapter.c
- *
- * Copyright 2002-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2002-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <net/net_namespace.h>
-
-#include "platform.h"
-#include "di_defs.h"
-#include "dadapter.h"
-#include "divasync.h"
-#include "did_vers.h"
-
-static char *main_revision = "$Revision: 1.13.6.4 $";
-
-static char *DRIVERNAME =
-	"Eicon DIVA - DIDD table (http://www.melware.net)";
-static char *DRIVERLNAME = "divadidd";
-char *DRIVERRELEASE_DIDD = "2.0";
-
-MODULE_DESCRIPTION("DIDD table driver for diva drivers");
-MODULE_AUTHOR("Cytronics & Melware, Eicon Networks");
-MODULE_SUPPORTED_DEVICE("Eicon diva drivers");
-MODULE_LICENSE("GPL");
-
-#define DBG_MINIMUM  (DL_LOG + DL_FTL + DL_ERR)
-#define DBG_DEFAULT  (DBG_MINIMUM + DL_XLOG + DL_REG)
-
-extern int diddfunc_init(void);
-extern void diddfunc_finit(void);
-
-extern void DIVA_DIDD_Read(void *, int);
-
-static struct proc_dir_entry *proc_didd;
-struct proc_dir_entry *proc_net_eicon = NULL;
-
-EXPORT_SYMBOL(DIVA_DIDD_Read);
-EXPORT_SYMBOL(proc_net_eicon);
-
-static char *getrev(const char *revision)
-{
-	char *rev;
-	char *p;
-	if ((p = strchr(revision, ':'))) {
-		rev = p + 2;
-		p = strchr(rev, '$');
-		*--p = 0;
-	} else
-		rev = "1.0";
-	return rev;
-}
-
-static int divadidd_proc_show(struct seq_file *m, void *v)
-{
-	char tmprev[32];
-
-	strcpy(tmprev, main_revision);
-	seq_printf(m, "%s\n", DRIVERNAME);
-	seq_printf(m, "name     : %s\n", DRIVERLNAME);
-	seq_printf(m, "release  : %s\n", DRIVERRELEASE_DIDD);
-	seq_printf(m, "build    : %s(%s)\n",
-		   diva_didd_common_code_build, DIVA_BUILD);
-	seq_printf(m, "revision : %s\n", getrev(tmprev));
-
-	return 0;
-}
-
-static int __init create_proc(void)
-{
-	proc_net_eicon = proc_mkdir("eicon", init_net.proc_net);
-
-	if (proc_net_eicon) {
-		proc_didd = proc_create_single(DRIVERLNAME, S_IRUGO,
-				proc_net_eicon, divadidd_proc_show);
-		return (1);
-	}
-	return (0);
-}
-
-static void remove_proc(void)
-{
-	remove_proc_entry(DRIVERLNAME, proc_net_eicon);
-	remove_proc_entry("eicon", init_net.proc_net);
-}
-
-static int __init divadidd_init(void)
-{
-	char tmprev[32];
-	int ret = 0;
-
-	printk(KERN_INFO "%s\n", DRIVERNAME);
-	printk(KERN_INFO "%s: Rel:%s  Rev:", DRIVERLNAME, DRIVERRELEASE_DIDD);
-	strcpy(tmprev, main_revision);
-	printk("%s  Build:%s(%s)\n", getrev(tmprev),
-	       diva_didd_common_code_build, DIVA_BUILD);
-
-	if (!create_proc()) {
-		printk(KERN_ERR "%s: could not create proc entry\n",
-		       DRIVERLNAME);
-		ret = -EIO;
-		goto out;
-	}
-
-	if (!diddfunc_init()) {
-		printk(KERN_ERR "%s: failed to connect to DIDD.\n",
-		       DRIVERLNAME);
-#ifdef MODULE
-		remove_proc();
-#endif
-		ret = -EIO;
-		goto out;
-	}
-
-out:
-	return (ret);
-}
-
-static void __exit divadidd_exit(void)
-{
-	diddfunc_finit();
-	remove_proc();
-	printk(KERN_INFO "%s: module unloaded.\n", DRIVERLNAME);
-}
-
-module_init(divadidd_init);
-module_exit(divadidd_exit);
diff --git a/drivers/isdn/hardware/eicon/diva_dma.c b/drivers/isdn/hardware/eicon/diva_dma.c
deleted file mode 100644
index 217b6aa9f612..000000000000
--- a/drivers/isdn/hardware/eicon/diva_dma.c
+++ /dev/null
@@ -1,94 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#include "platform.h"
-#include "diva_dma.h"
-/*
-  Every entry has length of PAGE_SIZE
-  and represents one single physical page
-*/
-struct _diva_dma_map_entry {
-	int busy;
-	dword phys_bus_addr;  /* 32bit address as seen by the card */
-	void *local_ram_addr; /* local address as seen by the host */
-	void *addr_handle;    /* handle uset to free allocated memory */
-};
-/*
-  Create local mapping structure and init it to default state
-*/
-struct _diva_dma_map_entry *diva_alloc_dma_map(void *os_context, int nentries) {
-	diva_dma_map_entry_t *pmap = diva_os_malloc(0, sizeof(*pmap) * (nentries + 1));
-	if (pmap)
-		memset(pmap, 0, sizeof(*pmap) * (nentries + 1));
-	return pmap;
-}
-/*
-  Free local map (context should be freed before) if any
-*/
-void diva_free_dma_mapping(struct _diva_dma_map_entry *pmap) {
-	if (pmap) {
-		diva_os_free(0, pmap);
-	}
-}
-/*
-  Set information saved on the map entry
-*/
-void diva_init_dma_map_entry(struct _diva_dma_map_entry *pmap,
-			     int nr, void *virt, dword phys,
-			     void *addr_handle) {
-	pmap[nr].phys_bus_addr  = phys;
-	pmap[nr].local_ram_addr = virt;
-	pmap[nr].addr_handle    = addr_handle;
-}
-/*
-  Allocate one single entry in the map
-*/
-int diva_alloc_dma_map_entry(struct _diva_dma_map_entry *pmap) {
-	int i;
-	for (i = 0; (pmap && pmap[i].local_ram_addr); i++) {
-		if (!pmap[i].busy) {
-			pmap[i].busy = 1;
-			return (i);
-		}
-	}
-	return (-1);
-}
-/*
-  Free one single entry in the map
-*/
-void diva_free_dma_map_entry(struct _diva_dma_map_entry *pmap, int nr) {
-	pmap[nr].busy = 0;
-}
-/*
-  Get information saved on the map entry
-*/
-void diva_get_dma_map_entry(struct _diva_dma_map_entry *pmap, int nr,
-			    void **pvirt, dword *pphys) {
-	*pphys = pmap[nr].phys_bus_addr;
-	*pvirt = pmap[nr].local_ram_addr;
-}
-void *diva_get_entry_handle(struct _diva_dma_map_entry *pmap, int nr) {
-	return (pmap[nr].addr_handle);
-}
diff --git a/drivers/isdn/hardware/eicon/diva_dma.h b/drivers/isdn/hardware/eicon/diva_dma.h
deleted file mode 100644
index d32c91be562b..000000000000
--- a/drivers/isdn/hardware/eicon/diva_dma.h
+++ /dev/null
@@ -1,48 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_DMA_MAPPING_IFC_H__
-#define __DIVA_DMA_MAPPING_IFC_H__
-typedef struct _diva_dma_map_entry  diva_dma_map_entry_t;
-struct _diva_dma_map_entry *diva_alloc_dma_map(void *os_context, int nentries);
-void diva_init_dma_map_entry(struct _diva_dma_map_entry *pmap,
-			     int nr, void *virt, dword phys,
-			     void *addr_handle);
-int diva_alloc_dma_map_entry(struct _diva_dma_map_entry *pmap);
-void diva_free_dma_map_entry(struct _diva_dma_map_entry *pmap, int entry);
-void diva_get_dma_map_entry(struct _diva_dma_map_entry *pmap, int nr,
-			    void **pvirt, dword *pphys);
-void diva_free_dma_mapping(struct _diva_dma_map_entry *pmap);
-/*
-  Functionality to be implemented by OS wrapper
-  and running in process context
-*/
-void diva_init_dma_map(void *hdev,
-		       struct _diva_dma_map_entry **ppmap,
-		       int nentries);
-void diva_free_dma_map(void *hdev,
-		       struct _diva_dma_map_entry *pmap);
-void *diva_get_entry_handle(struct _diva_dma_map_entry *pmap, int nr);
-#endif
diff --git a/drivers/isdn/hardware/eicon/diva_pci.h b/drivers/isdn/hardware/eicon/diva_pci.h
deleted file mode 100644
index 7ef5db98ad3c..000000000000
--- a/drivers/isdn/hardware/eicon/diva_pci.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: diva_pci.h,v 1.6 2003/01/04 15:29:45 schindler Exp $ */
-
-#ifndef __DIVA_PCI_INTERFACE_H__
-#define __DIVA_PCI_INTERFACE_H__
-
-void __iomem *divasa_remap_pci_bar(diva_os_xdi_adapter_t *a,
-				   int id,
-				   unsigned long bar,
-				   unsigned long area_length);
-void divasa_unmap_pci_bar(void __iomem *bar);
-unsigned long divasa_get_pci_irq(unsigned char bus,
-				 unsigned char func, void *pci_dev_handle);
-unsigned long divasa_get_pci_bar(unsigned char bus,
-				 unsigned char func,
-				 int bar, void *pci_dev_handle);
-byte diva_os_get_pci_bus(void *pci_dev_handle);
-byte diva_os_get_pci_func(void *pci_dev_handle);
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/divacapi.h b/drivers/isdn/hardware/eicon/divacapi.h
deleted file mode 100644
index c4868a0d82f4..000000000000
--- a/drivers/isdn/hardware/eicon/divacapi.h
+++ /dev/null
@@ -1,1350 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-
-/*#define DEBUG */
-
-#include <linux/types.h>
-
-#define IMPLEMENT_DTMF 1
-#define IMPLEMENT_LINE_INTERCONNECT2 1
-#define IMPLEMENT_ECHO_CANCELLER 1
-#define IMPLEMENT_RTP 1
-#define IMPLEMENT_T38 1
-#define IMPLEMENT_FAX_SUB_SEP_PWD 1
-#define IMPLEMENT_V18 1
-#define IMPLEMENT_DTMF_TONE 1
-#define IMPLEMENT_PIAFS 1
-#define IMPLEMENT_FAX_PAPER_FORMATS 1
-#define IMPLEMENT_VOWN 1
-#define IMPLEMENT_CAPIDTMF 1
-#define IMPLEMENT_FAX_NONSTANDARD 1
-#define VSWITCH_SUPPORT 1
-
-
-#define IMPLEMENT_LINE_INTERCONNECT 0
-#define IMPLEMENT_MARKED_OK_AFTER_FC 1
-
-#include "capidtmf.h"
-
-/*------------------------------------------------------------------*/
-/* Common API internal definitions                                  */
-/*------------------------------------------------------------------*/
-
-#define MAX_APPL 240
-#define MAX_NCCI           127
-
-#define MSG_IN_QUEUE_SIZE  ((4096 + 3) & 0xfffc)  /* must be multiple of 4 */
-
-
-#define MSG_IN_OVERHEAD    sizeof(APPL   *)
-
-#define MAX_NL_CHANNEL     255
-#define MAX_DATA_B3        8
-#define MAX_DATA_ACK       MAX_DATA_B3
-#define MAX_MULTI_IE       6
-#define MAX_MSG_SIZE       256
-#define MAX_MSG_PARMS      10
-#define MAX_CPN_MASK_SIZE  16
-#define MAX_MSN_CONFIG     10
-#define EXT_CONTROLLER     0x80
-#define CODEC              0x01
-#define CODEC_PERMANENT    0x02
-#define ADV_VOICE          0x03
-#define MAX_CIP_TYPES      5  /* kind of CIP types for group optimization */
-
-#define FAX_CONNECT_INFO_BUFFER_SIZE  256
-#define NCPI_BUFFER_SIZE              256
-
-#define MAX_CHANNELS_PER_PLCI         8
-#define MAX_INTERNAL_COMMAND_LEVELS   4
-#define INTERNAL_REQ_BUFFER_SIZE      272
-
-#define INTERNAL_IND_BUFFER_SIZE      768
-
-#define DTMF_PARAMETER_BUFFER_SIZE    12
-#define ADV_VOICE_COEF_BUFFER_SIZE    50
-
-#define LI_PLCI_B_QUEUE_ENTRIES       256
-
-
-
-typedef struct _APPL APPL;
-typedef struct _PLCI PLCI;
-typedef struct _NCCI NCCI;
-typedef struct _DIVA_CAPI_ADAPTER DIVA_CAPI_ADAPTER;
-typedef struct _DATA_B3_DESC DATA_B3_DESC;
-typedef struct _DATA_ACK_DESC DATA_ACK_DESC;
-typedef struct manufacturer_profile_s MANUFACTURER_PROFILE;
-typedef struct fax_ncpi_s FAX_NCPI;
-typedef struct api_parse_s API_PARSE;
-typedef struct api_save_s API_SAVE;
-typedef struct msn_config_s MSN_CONFIG;
-typedef struct msn_config_max_s MSN_CONFIG_MAX;
-typedef struct msn_ld_s MSN_LD;
-
-struct manufacturer_profile_s {
-	dword private_options;
-	dword rtp_primary_payloads;
-	dword rtp_additional_payloads;
-};
-
-struct fax_ncpi_s {
-	word options;
-	word format;
-};
-
-struct msn_config_s {
-	byte msn[MAX_CPN_MASK_SIZE];
-};
-
-struct msn_config_max_s {
-	MSN_CONFIG    msn_conf[MAX_MSN_CONFIG];
-};
-
-struct msn_ld_s {
-	dword low;
-	dword high;
-};
-
-struct api_parse_s {
-	word          length;
-	byte *info;
-};
-
-struct api_save_s {
-	API_PARSE     parms[MAX_MSG_PARMS + 1];
-	byte          info[MAX_MSG_SIZE];
-};
-
-struct _DATA_B3_DESC {
-	word          Handle;
-	word          Number;
-	word          Flags;
-	word          Length;
-	void *P;
-};
-
-struct _DATA_ACK_DESC {
-	word          Handle;
-	word          Number;
-};
-
-typedef void (*t_std_internal_command)(dword Id, PLCI *plci, byte Rc);
-
-/************************************************************************/
-/* Don't forget to adapt dos.asm after changing the _APPL structure!!!! */
-struct _APPL {
-	word          Id;
-	word          NullCREnable;
-	word          CDEnable;
-	dword         S_Handle;
-
-
-
-
-
-
-	LIST_ENTRY    s_function;
-	dword         s_context;
-	word          s_count;
-	APPL *s_next;
-	byte *xbuffer_used;
-	void **xbuffer_internal;
-	void **xbuffer_ptr;
-
-
-
-
-
-
-	byte *queue;
-	word          queue_size;
-	word          queue_free;
-	word          queue_read;
-	word          queue_write;
-	word          queue_signal;
-	byte          msg_lost;
-	byte          appl_flags;
-	word          Number;
-
-	word          MaxBuffer;
-	byte          MaxNCCI;
-	byte          MaxNCCIData;
-	word          MaxDataLength;
-	word          NCCIDataFlowCtrlTimer;
-	byte *ReceiveBuffer;
-	word *DataNCCI;
-	word *DataFlags;
-};
-
-
-struct _PLCI {
-	ENTITY        Sig;
-	ENTITY        NL;
-	word          RNum;
-	word          RFlags;
-	BUFFERS       RData[2];
-	BUFFERS       XData[1];
-	BUFFERS       NData[2];
-
-	DIVA_CAPI_ADAPTER   *adapter;
-	APPL      *appl;
-	PLCI      *relatedPTYPLCI;
-	byte          Id;
-	byte          State;
-	byte          sig_req;
-	byte          nl_req;
-	byte          SuppState;
-	byte          channels;
-	byte          tel;
-	byte          B1_resource;
-	byte          B2_prot;
-	byte          B3_prot;
-
-	word          command;
-	word          m_command;
-	word          internal_command;
-	word          number;
-	word          req_in_start;
-	word          req_in;
-	word          req_out;
-	word          msg_in_write_pos;
-	word          msg_in_read_pos;
-	word          msg_in_wrap_pos;
-
-	void *data_sent_ptr;
-	byte          data_sent;
-	byte          send_disc;
-	byte          sig_global_req;
-	byte          sig_remove_id;
-	byte          nl_global_req;
-	byte          nl_remove_id;
-	byte          b_channel;
-	byte          adv_nl;
-	byte          manufacturer;
-	byte          call_dir;
-	byte          hook_state;
-	byte          spoofed_msg;
-	byte          ptyState;
-	byte          cr_enquiry;
-	word          hangup_flow_ctrl_timer;
-
-	word          ncci_ring_list;
-	byte          inc_dis_ncci_table[MAX_CHANNELS_PER_PLCI];
-	t_std_internal_command internal_command_queue[MAX_INTERNAL_COMMAND_LEVELS];
-	DECLARE_BITMAP(c_ind_mask_table, MAX_APPL);
-	DECLARE_BITMAP(group_optimization_mask_table, MAX_APPL);
-	byte          RBuffer[200];
-	dword         msg_in_queue[MSG_IN_QUEUE_SIZE/sizeof(dword)];
-	API_SAVE      saved_msg;
-	API_SAVE      B_protocol;
-	byte          fax_connect_info_length;
-	byte          fax_connect_info_buffer[FAX_CONNECT_INFO_BUFFER_SIZE];
-	byte          fax_edata_ack_length;
-	word          nsf_control_bits;
-	byte          ncpi_state;
-	byte          ncpi_buffer[NCPI_BUFFER_SIZE];
-
-	byte          internal_req_buffer[INTERNAL_REQ_BUFFER_SIZE];
-	byte          internal_ind_buffer[INTERNAL_IND_BUFFER_SIZE + 3];
-	dword         requested_options_conn;
-	dword         requested_options;
-	word          B1_facilities;
-	API_SAVE   *adjust_b_parms_msg;
-	word          adjust_b_facilities;
-	word          adjust_b_command;
-	word          adjust_b_ncci;
-	word          adjust_b_mode;
-	word          adjust_b_state;
-	byte          adjust_b_restore;
-
-	byte          dtmf_rec_active;
-	word          dtmf_rec_pulse_ms;
-	word          dtmf_rec_pause_ms;
-	byte          dtmf_send_requests;
-	word          dtmf_send_pulse_ms;
-	word          dtmf_send_pause_ms;
-	word          dtmf_cmd;
-	word          dtmf_msg_number_queue[8];
-	byte          dtmf_parameter_length;
-	byte          dtmf_parameter_buffer[DTMF_PARAMETER_BUFFER_SIZE];
-
-
-	t_capidtmf_state capidtmf_state;
-
-
-	byte          li_bchannel_id;    /* BRI: 1..2, PRI: 1..32 */
-	byte          li_channel_bits;
-	byte          li_notify_update;
-	word          li_cmd;
-	word          li_write_command;
-	word          li_write_channel;
-	word          li_plci_b_write_pos;
-	word          li_plci_b_read_pos;
-	word          li_plci_b_req_pos;
-	dword         li_plci_b_queue[LI_PLCI_B_QUEUE_ENTRIES];
-
-
-	word          ec_cmd;
-	word          ec_idi_options;
-	word          ec_tail_length;
-
-
-	byte          tone_last_indication_code;
-
-	byte          vswitchstate;
-	byte          vsprot;
-	byte          vsprotdialect;
-	byte          notifiedcall; /* Flag if it is a spoofed call */
-
-	int           rx_dma_descriptor;
-	dword         rx_dma_magic;
-};
-
-
-struct _NCCI {
-	byte          data_out;
-	byte          data_pending;
-	byte          data_ack_out;
-	byte          data_ack_pending;
-	DATA_B3_DESC  DBuffer[MAX_DATA_B3];
-	DATA_ACK_DESC DataAck[MAX_DATA_ACK];
-};
-
-
-struct _DIVA_CAPI_ADAPTER {
-	IDI_CALL      request;
-	byte          Id;
-	byte          max_plci;
-	byte          max_listen;
-	byte          listen_active;
-	PLCI      *plci;
-	byte          ch_ncci[MAX_NL_CHANNEL + 1];
-	byte          ncci_ch[MAX_NCCI + 1];
-	byte          ncci_plci[MAX_NCCI + 1];
-	byte          ncci_state[MAX_NCCI + 1];
-	byte          ncci_next[MAX_NCCI + 1];
-	NCCI          ncci[MAX_NCCI + 1];
-
-	byte          ch_flow_control[MAX_NL_CHANNEL + 1];  /* Used by XON protocol */
-	byte          ch_flow_control_pending;
-	byte          ch_flow_plci[MAX_NL_CHANNEL + 1];
-	int           last_flow_control_ch;
-
-	dword         Info_Mask[MAX_APPL];
-	dword         CIP_Mask[MAX_APPL];
-
-	dword         Notification_Mask[MAX_APPL];
-	PLCI      *codec_listen[MAX_APPL];
-	dword         requested_options_table[MAX_APPL];
-	API_PROFILE   profile;
-	MANUFACTURER_PROFILE man_profile;
-	dword         manufacturer_features;
-
-	byte          AdvCodecFLAG;
-	PLCI      *AdvCodecPLCI;
-	PLCI      *AdvSignalPLCI;
-	APPL      *AdvSignalAppl;
-	byte          TelOAD[23];
-	byte          TelOSA[23];
-	byte          scom_appl_disable;
-	PLCI      *automatic_lawPLCI;
-	byte          automatic_law;
-	byte          u_law;
-
-	byte          adv_voice_coef_length;
-	byte          adv_voice_coef_buffer[ADV_VOICE_COEF_BUFFER_SIZE];
-
-	byte          li_pri;
-	byte          li_channels;
-	word          li_base;
-
-	byte adapter_disabled;
-	byte group_optimization_enabled; /* use application groups if enabled */
-	dword sdram_bar;
-	byte flag_dynamic_l1_down; /* for hunt groups:down layer 1 if no appl present*/
-	byte FlowControlIdTable[256];
-	byte FlowControlSkipTable[256];
-	void *os_card; /* pointer to associated OS dependent adapter structure */
-};
-
-
-/*------------------------------------------------------------------*/
-/* Application flags                                                */
-/*------------------------------------------------------------------*/
-
-#define APPL_FLAG_OLD_LI_SPEC           0x01
-#define APPL_FLAG_PRIV_EC_SPEC          0x02
-
-
-/*------------------------------------------------------------------*/
-/* API parameter definitions                                        */
-/*------------------------------------------------------------------*/
-
-#define X75_TTX         1       /* x.75 for ttx                     */
-#define TRF             2       /* transparent with hdlc framing    */
-#define TRF_IN          3       /* transparent with hdlc fr. inc.   */
-#define SDLC            4       /* sdlc, sna layer-2                */
-#define X75_BTX         5       /* x.75 for btx                     */
-#define LAPD            6       /* lapd (Q.921)                     */
-#define X25_L2          7       /* x.25 layer-2                     */
-#define V120_L2         8       /* V.120 layer-2 protocol           */
-#define V42_IN          9       /* V.42 layer-2 protocol, incoming */
-#define V42            10       /* V.42 layer-2 protocol            */
-#define MDM_ATP        11       /* AT Parser built in the L2        */
-#define X75_V42BIS     12       /* ISO7776 (X.75 SLP) modified to support V.42 bis compression */
-#define RTPL2_IN       13       /* RTP layer-2 protocol, incoming  */
-#define RTPL2          14       /* RTP layer-2 protocol             */
-#define V120_V42BIS    15       /* V.120 layer-2 protocol supporting V.42 bis compression */
-
-#define T70NL           1
-#define X25PLP          2
-#define T70NLX          3
-#define TRANSPARENT_NL  4
-#define ISO8208         5
-#define T30             6
-
-
-/*------------------------------------------------------------------*/
-/* FAX interface to IDI                                             */
-/*------------------------------------------------------------------*/
-
-#define CAPI_MAX_HEAD_LINE_SPACE        89
-#define CAPI_MAX_DATE_TIME_LENGTH       18
-
-#define T30_MAX_STATION_ID_LENGTH       20
-#define T30_MAX_SUBADDRESS_LENGTH       20
-#define T30_MAX_PASSWORD_LENGTH         20
-
-typedef struct t30_info_s T30_INFO;
-struct t30_info_s {
-	byte          code;
-	byte          rate_div_2400;
-	byte          resolution;
-	byte          data_format;
-	byte          pages_low;
-	byte          pages_high;
-	byte          operating_mode;
-	byte          control_bits_low;
-	byte          control_bits_high;
-	byte          feature_bits_low;
-	byte          feature_bits_high;
-	byte          recording_properties;
-	byte          universal_6;
-	byte          universal_7;
-	byte          station_id_len;
-	byte          head_line_len;
-	byte          station_id[T30_MAX_STATION_ID_LENGTH];
-/* byte          head_line[];      */
-/* byte          sub_sep_length;   */
-/* byte          sub_sep_field[];  */
-/* byte          pwd_length;       */
-/* byte          pwd_field[];      */
-/* byte          nsf_info_length;   */
-/* byte          nsf_info_field[];  */
-};
-
-
-#define T30_RESOLUTION_R8_0385          0x00
-#define T30_RESOLUTION_R8_0770_OR_200   0x01
-#define T30_RESOLUTION_R8_1540          0x02
-#define T30_RESOLUTION_R16_1540_OR_400  0x04
-#define T30_RESOLUTION_R4_0385_OR_100   0x08
-#define T30_RESOLUTION_300_300          0x10
-#define T30_RESOLUTION_INCH_BASED       0x40
-#define T30_RESOLUTION_METRIC_BASED     0x80
-
-#define T30_RECORDING_WIDTH_ISO_A4      0
-#define T30_RECORDING_WIDTH_ISO_B4      1
-#define T30_RECORDING_WIDTH_ISO_A3      2
-#define T30_RECORDING_WIDTH_COUNT       3
-
-#define T30_RECORDING_LENGTH_ISO_A4     0
-#define T30_RECORDING_LENGTH_ISO_B4     1
-#define T30_RECORDING_LENGTH_UNLIMITED  2
-#define T30_RECORDING_LENGTH_COUNT      3
-
-#define T30_MIN_SCANLINE_TIME_00_00_00  0
-#define T30_MIN_SCANLINE_TIME_05_05_05  1
-#define T30_MIN_SCANLINE_TIME_10_05_05  2
-#define T30_MIN_SCANLINE_TIME_10_10_10  3
-#define T30_MIN_SCANLINE_TIME_20_10_10  4
-#define T30_MIN_SCANLINE_TIME_20_20_20  5
-#define T30_MIN_SCANLINE_TIME_40_20_20  6
-#define T30_MIN_SCANLINE_TIME_40_40_40  7
-#define T30_MIN_SCANLINE_TIME_RES_8     8
-#define T30_MIN_SCANLINE_TIME_RES_9     9
-#define T30_MIN_SCANLINE_TIME_RES_10    10
-#define T30_MIN_SCANLINE_TIME_10_10_05  11
-#define T30_MIN_SCANLINE_TIME_20_10_05  12
-#define T30_MIN_SCANLINE_TIME_20_20_10  13
-#define T30_MIN_SCANLINE_TIME_40_20_10  14
-#define T30_MIN_SCANLINE_TIME_40_40_20  15
-#define T30_MIN_SCANLINE_TIME_COUNT     16
-
-#define T30_DATA_FORMAT_SFF             0
-#define T30_DATA_FORMAT_ASCII           1
-#define T30_DATA_FORMAT_NATIVE          2
-#define T30_DATA_FORMAT_COUNT           3
-
-
-#define T30_OPERATING_MODE_STANDARD     0
-#define T30_OPERATING_MODE_CLASS2       1
-#define T30_OPERATING_MODE_CLASS1       2
-#define T30_OPERATING_MODE_CAPI         3
-#define T30_OPERATING_MODE_CAPI_NEG     4
-#define T30_OPERATING_MODE_COUNT        5
-
-/* EDATA transmit messages */
-#define EDATA_T30_DIS         0x01
-#define EDATA_T30_FTT         0x02
-#define EDATA_T30_MCF         0x03
-#define EDATA_T30_PARAMETERS  0x04
-
-/* EDATA receive messages */
-#define EDATA_T30_DCS         0x81
-#define EDATA_T30_TRAIN_OK    0x82
-#define EDATA_T30_EOP         0x83
-#define EDATA_T30_MPS         0x84
-#define EDATA_T30_EOM         0x85
-#define EDATA_T30_DTC         0x86
-#define EDATA_T30_PAGE_END    0x87   /* Indicates end of page data. Reserved, but not implemented ! */
-#define EDATA_T30_EOP_CAPI    0x88
-
-
-#define T30_SUCCESS                        0
-#define T30_ERR_NO_DIS_RECEIVED            1
-#define T30_ERR_TIMEOUT_NO_RESPONSE        2
-#define T30_ERR_RETRY_NO_RESPONSE          3
-#define T30_ERR_TOO_MANY_REPEATS           4
-#define T30_ERR_UNEXPECTED_MESSAGE         5
-#define T30_ERR_UNEXPECTED_DCN             6
-#define T30_ERR_DTC_UNSUPPORTED            7
-#define T30_ERR_ALL_RATES_FAILED           8
-#define T30_ERR_TOO_MANY_TRAINS            9
-#define T30_ERR_RECEIVE_CORRUPTED          10
-#define T30_ERR_UNEXPECTED_DISC            11
-#define T30_ERR_APPLICATION_DISC           12
-#define T30_ERR_INCOMPATIBLE_DIS           13
-#define T30_ERR_INCOMPATIBLE_DCS           14
-#define T30_ERR_TIMEOUT_NO_COMMAND         15
-#define T30_ERR_RETRY_NO_COMMAND           16
-#define T30_ERR_TIMEOUT_COMMAND_TOO_LONG   17
-#define T30_ERR_TIMEOUT_RESPONSE_TOO_LONG  18
-#define T30_ERR_NOT_IDENTIFIED             19
-#define T30_ERR_SUPERVISORY_TIMEOUT        20
-#define T30_ERR_TOO_LONG_SCAN_LINE         21
-/* #define T30_ERR_RETRY_NO_PAGE_AFTER_MPS    22 */
-#define T30_ERR_RETRY_NO_PAGE_RECEIVED     23
-#define T30_ERR_RETRY_NO_DCS_AFTER_FTT     24
-#define T30_ERR_RETRY_NO_DCS_AFTER_EOM     25
-#define T30_ERR_RETRY_NO_DCS_AFTER_MPS     26
-#define T30_ERR_RETRY_NO_DCN_AFTER_MCF     27
-#define T30_ERR_RETRY_NO_DCN_AFTER_RTN     28
-#define T30_ERR_RETRY_NO_CFR               29
-#define T30_ERR_RETRY_NO_MCF_AFTER_EOP     30
-#define T30_ERR_RETRY_NO_MCF_AFTER_EOM     31
-#define T30_ERR_RETRY_NO_MCF_AFTER_MPS     32
-#define T30_ERR_SUB_SEP_UNSUPPORTED        33
-#define T30_ERR_PWD_UNSUPPORTED            34
-#define T30_ERR_SUB_SEP_PWD_UNSUPPORTED    35
-#define T30_ERR_INVALID_COMMAND_FRAME      36
-#define T30_ERR_UNSUPPORTED_PAGE_CODING    37
-#define T30_ERR_INVALID_PAGE_CODING        38
-#define T30_ERR_INCOMPATIBLE_PAGE_CONFIG   39
-#define T30_ERR_TIMEOUT_FROM_APPLICATION   40
-#define T30_ERR_V34FAX_NO_REACTION_ON_MARK 41
-#define T30_ERR_V34FAX_TRAINING_TIMEOUT    42
-#define T30_ERR_V34FAX_UNEXPECTED_V21      43
-#define T30_ERR_V34FAX_PRIMARY_CTS_ON      44
-#define T30_ERR_V34FAX_TURNAROUND_POLLING  45
-#define T30_ERR_V34FAX_V8_INCOMPATIBILITY  46
-
-
-#define T30_CONTROL_BIT_DISABLE_FINE       0x0001
-#define T30_CONTROL_BIT_ENABLE_ECM         0x0002
-#define T30_CONTROL_BIT_ECM_64_BYTES       0x0004
-#define T30_CONTROL_BIT_ENABLE_2D_CODING   0x0008
-#define T30_CONTROL_BIT_ENABLE_T6_CODING   0x0010
-#define T30_CONTROL_BIT_ENABLE_UNCOMPR     0x0020
-#define T30_CONTROL_BIT_ACCEPT_POLLING     0x0040
-#define T30_CONTROL_BIT_REQUEST_POLLING    0x0080
-#define T30_CONTROL_BIT_MORE_DOCUMENTS     0x0100
-#define T30_CONTROL_BIT_ACCEPT_SUBADDRESS  0x0200
-#define T30_CONTROL_BIT_ACCEPT_SEL_POLLING 0x0400
-#define T30_CONTROL_BIT_ACCEPT_PASSWORD    0x0800
-#define T30_CONTROL_BIT_ENABLE_V34FAX      0x1000
-#define T30_CONTROL_BIT_EARLY_CONNECT      0x2000
-
-#define T30_CONTROL_BIT_ALL_FEATURES  (T30_CONTROL_BIT_ENABLE_ECM | T30_CONTROL_BIT_ENABLE_2D_CODING |   T30_CONTROL_BIT_ENABLE_T6_CODING | T30_CONTROL_BIT_ENABLE_UNCOMPR |   T30_CONTROL_BIT_ENABLE_V34FAX)
-
-#define T30_FEATURE_BIT_FINE               0x0001
-#define T30_FEATURE_BIT_ECM                0x0002
-#define T30_FEATURE_BIT_ECM_64_BYTES       0x0004
-#define T30_FEATURE_BIT_2D_CODING          0x0008
-#define T30_FEATURE_BIT_T6_CODING          0x0010
-#define T30_FEATURE_BIT_UNCOMPR_ENABLED    0x0020
-#define T30_FEATURE_BIT_POLLING            0x0040
-#define T30_FEATURE_BIT_MORE_DOCUMENTS     0x0100
-#define T30_FEATURE_BIT_V34FAX             0x1000
-
-
-#define T30_NSF_CONTROL_BIT_ENABLE_NSF     0x0001
-#define T30_NSF_CONTROL_BIT_RAW_INFO       0x0002
-#define T30_NSF_CONTROL_BIT_NEGOTIATE_IND  0x0004
-#define T30_NSF_CONTROL_BIT_NEGOTIATE_RESP 0x0008
-
-#define T30_NSF_ELEMENT_NSF_FIF            0x00
-#define T30_NSF_ELEMENT_NSC_FIF            0x01
-#define T30_NSF_ELEMENT_NSS_FIF            0x02
-#define T30_NSF_ELEMENT_COMPANY_NAME       0x03
-
-
-/*------------------------------------------------------------------*/
-/* Analog modem definitions                                         */
-/*------------------------------------------------------------------*/
-
-typedef struct async_s ASYNC_FORMAT;
-struct async_s {
-	unsigned pe:1;
-	unsigned parity:2;
-	unsigned spare:2;
-	unsigned stp:1;
-	unsigned ch_len:2;   /* 3th octett in CAI */
-};
-
-
-/*------------------------------------------------------------------*/
-/* PLCI/NCCI states                                                 */
-/*------------------------------------------------------------------*/
-
-#define IDLE                    0
-#define OUTG_CON_PENDING        1
-#define INC_CON_PENDING         2
-#define INC_CON_ALERT           3
-#define INC_CON_ACCEPT          4
-#define INC_ACT_PENDING         5
-#define LISTENING               6
-#define CONNECTED               7
-#define OUTG_DIS_PENDING        8
-#define INC_DIS_PENDING         9
-#define LOCAL_CONNECT           10
-#define INC_RES_PENDING         11
-#define OUTG_RES_PENDING        12
-#define SUSPENDING              13
-#define ADVANCED_VOICE_SIG      14
-#define ADVANCED_VOICE_NOSIG    15
-#define RESUMING                16
-#define INC_CON_CONNECTED_ALERT 17
-#define OUTG_REJ_PENDING        18
-
-
-/*------------------------------------------------------------------*/
-/* auxiliary states for supplementary services                     */
-/*------------------------------------------------------------------*/
-
-#define IDLE                0
-#define HOLD_REQUEST        1
-#define HOLD_INDICATE       2
-#define CALL_HELD           3
-#define RETRIEVE_REQUEST    4
-#define RETRIEVE_INDICATION 5
-
-/*------------------------------------------------------------------*/
-/* Capi IE + Msg types                                              */
-/*------------------------------------------------------------------*/
-#define ESC_CAUSE        0x800 | CAU        /* Escape cause element */
-#define ESC_MSGTYPE      0x800 | MSGTYPEIE  /* Escape message type  */
-#define ESC_CHI          0x800 | CHI        /* Escape channel id    */
-#define ESC_LAW          0x800 | BC         /* Escape law info      */
-#define ESC_CR           0x800 | CRIE       /* Escape CallReference */
-#define ESC_PROFILE      0x800 | PROFILEIE  /* Escape profile       */
-#define ESC_SSEXT        0x800 | SSEXTIE    /* Escape Supplem. Serv.*/
-#define ESC_VSWITCH      0x800 | VSWITCHIE  /* Escape VSwitch       */
-#define CST              0x14               /* Call State i.e.      */
-#define PI               0x1E               /* Progress Indicator   */
-#define NI               0x27               /* Notification Ind     */
-#define CONN_NR          0x4C               /* Connected Number     */
-#define CONG_RNR         0xBF               /* Congestion RNR       */
-#define CONG_RR          0xB0               /* Congestion RR        */
-#define RESERVED         0xFF               /* Res. for future use  */
-#define ON_BOARD_CODEC   0x02               /* external controller  */
-#define HANDSET          0x04               /* Codec+Handset(Pro11) */
-#define HOOK_SUPPORT     0x01               /* activate Hook signal */
-#define SCR              0x7a               /* unscreened number    */
-
-#define HOOK_OFF_REQ     0x9001             /* internal conn req    */
-#define HOOK_ON_REQ      0x9002             /* internal disc req    */
-#define SUSPEND_REQ      0x9003             /* internal susp req    */
-#define RESUME_REQ       0x9004             /* internal resume req  */
-#define USELAW_REQ       0x9005             /* internal law    req  */
-#define LISTEN_SIG_ASSIGN_PEND  0x9006
-#define PERM_LIST_REQ    0x900a             /* permanent conn DCE   */
-#define C_HOLD_REQ       0x9011
-#define C_RETRIEVE_REQ   0x9012
-#define C_NCR_FAC_REQ    0x9013
-#define PERM_COD_ASSIGN  0x9014
-#define PERM_COD_CALL    0x9015
-#define PERM_COD_HOOK    0x9016
-#define PERM_COD_CONN_PEND 0x9017           /* wait for connect_con */
-#define PTY_REQ_PEND     0x9018
-#define CD_REQ_PEND      0x9019
-#define CF_START_PEND    0x901a
-#define CF_STOP_PEND     0x901b
-#define ECT_REQ_PEND     0x901c
-#define GETSERV_REQ_PEND 0x901d
-#define BLOCK_PLCI       0x901e
-#define INTERR_NUMBERS_REQ_PEND         0x901f
-#define INTERR_DIVERSION_REQ_PEND       0x9020
-#define MWI_ACTIVATE_REQ_PEND           0x9021
-#define MWI_DEACTIVATE_REQ_PEND         0x9022
-#define SSEXT_REQ_COMMAND               0x9023
-#define SSEXT_NC_REQ_COMMAND            0x9024
-#define START_L1_SIG_ASSIGN_PEND        0x9025
-#define REM_L1_SIG_ASSIGN_PEND          0x9026
-#define CONF_BEGIN_REQ_PEND             0x9027
-#define CONF_ADD_REQ_PEND               0x9028
-#define CONF_SPLIT_REQ_PEND             0x9029
-#define CONF_DROP_REQ_PEND              0x902a
-#define CONF_ISOLATE_REQ_PEND           0x902b
-#define CONF_REATTACH_REQ_PEND          0x902c
-#define VSWITCH_REQ_PEND                0x902d
-#define GET_MWI_STATE                   0x902e
-#define CCBS_REQUEST_REQ_PEND           0x902f
-#define CCBS_DEACTIVATE_REQ_PEND        0x9030
-#define CCBS_INTERROGATE_REQ_PEND       0x9031
-
-#define NO_INTERNAL_COMMAND             0
-#define DTMF_COMMAND_1                  1
-#define DTMF_COMMAND_2                  2
-#define DTMF_COMMAND_3                  3
-#define MIXER_COMMAND_1                 4
-#define MIXER_COMMAND_2                 5
-#define MIXER_COMMAND_3                 6
-#define ADV_VOICE_COMMAND_CONNECT_1     7
-#define ADV_VOICE_COMMAND_CONNECT_2     8
-#define ADV_VOICE_COMMAND_CONNECT_3     9
-#define ADV_VOICE_COMMAND_DISCONNECT_1  10
-#define ADV_VOICE_COMMAND_DISCONNECT_2  11
-#define ADV_VOICE_COMMAND_DISCONNECT_3  12
-#define ADJUST_B_RESTORE_1              13
-#define ADJUST_B_RESTORE_2              14
-#define RESET_B3_COMMAND_1              15
-#define SELECT_B_COMMAND_1              16
-#define FAX_CONNECT_INFO_COMMAND_1      17
-#define FAX_CONNECT_INFO_COMMAND_2      18
-#define FAX_ADJUST_B23_COMMAND_1        19
-#define FAX_ADJUST_B23_COMMAND_2        20
-#define EC_COMMAND_1                    21
-#define EC_COMMAND_2                    22
-#define EC_COMMAND_3                    23
-#define RTP_CONNECT_B3_REQ_COMMAND_1    24
-#define RTP_CONNECT_B3_REQ_COMMAND_2    25
-#define RTP_CONNECT_B3_REQ_COMMAND_3    26
-#define RTP_CONNECT_B3_RES_COMMAND_1    27
-#define RTP_CONNECT_B3_RES_COMMAND_2    28
-#define RTP_CONNECT_B3_RES_COMMAND_3    29
-#define HOLD_SAVE_COMMAND_1             30
-#define RETRIEVE_RESTORE_COMMAND_1      31
-#define FAX_DISCONNECT_COMMAND_1        32
-#define FAX_DISCONNECT_COMMAND_2        33
-#define FAX_DISCONNECT_COMMAND_3        34
-#define FAX_EDATA_ACK_COMMAND_1         35
-#define FAX_EDATA_ACK_COMMAND_2         36
-#define FAX_CONNECT_ACK_COMMAND_1       37
-#define FAX_CONNECT_ACK_COMMAND_2       38
-#define STD_INTERNAL_COMMAND_COUNT      39
-
-#define UID              0x2d               /* User Id for Mgmt      */
-
-#define CALL_DIR_OUT             0x01       /* call direction of initial call */
-#define CALL_DIR_IN              0x02
-#define CALL_DIR_ORIGINATE       0x04       /* DTE/DCE direction according to */
-#define CALL_DIR_ANSWER          0x08       /*   state of B-Channel Operation */
-#define CALL_DIR_FORCE_OUTG_NL   0x10       /* for RESET_B3 reconnect, after DISC_B3... */
-
-#define AWAITING_MANUF_CON 0x80             /* command spoofing flags */
-#define SPOOFING_REQUIRED  0xff
-#define AWAITING_SELECT_B  0xef
-
-/*------------------------------------------------------------------*/
-/* B_CTRL / DSP_CTRL                                                */
-/*------------------------------------------------------------------*/
-
-#define DSP_CTRL_OLD_SET_MIXER_COEFFICIENTS     0x01
-#define DSP_CTRL_SET_BCHANNEL_PASSIVATION_BRI   0x02
-#define DSP_CTRL_SET_DTMF_PARAMETERS            0x03
-
-#define MANUFACTURER_FEATURE_SLAVE_CODEC          0x00000001L
-#define MANUFACTURER_FEATURE_FAX_MORE_DOCUMENTS   0x00000002L
-#define MANUFACTURER_FEATURE_HARDDTMF             0x00000004L
-#define MANUFACTURER_FEATURE_SOFTDTMF_SEND        0x00000008L
-#define MANUFACTURER_FEATURE_DTMF_PARAMETERS      0x00000010L
-#define MANUFACTURER_FEATURE_SOFTDTMF_RECEIVE     0x00000020L
-#define MANUFACTURER_FEATURE_FAX_SUB_SEP_PWD      0x00000040L
-#define MANUFACTURER_FEATURE_V18                  0x00000080L
-#define MANUFACTURER_FEATURE_MIXER_CH_CH          0x00000100L
-#define MANUFACTURER_FEATURE_MIXER_CH_PC          0x00000200L
-#define MANUFACTURER_FEATURE_MIXER_PC_CH          0x00000400L
-#define MANUFACTURER_FEATURE_MIXER_PC_PC          0x00000800L
-#define MANUFACTURER_FEATURE_ECHO_CANCELLER       0x00001000L
-#define MANUFACTURER_FEATURE_RTP                  0x00002000L
-#define MANUFACTURER_FEATURE_T38                  0x00004000L
-#define MANUFACTURER_FEATURE_TRANSP_DELIVERY_CONF 0x00008000L
-#define MANUFACTURER_FEATURE_XONOFF_FLOW_CONTROL  0x00010000L
-#define MANUFACTURER_FEATURE_OOB_CHANNEL          0x00020000L
-#define MANUFACTURER_FEATURE_IN_BAND_CHANNEL      0x00040000L
-#define MANUFACTURER_FEATURE_IN_BAND_FEATURE      0x00080000L
-#define MANUFACTURER_FEATURE_PIAFS                0x00100000L
-#define MANUFACTURER_FEATURE_DTMF_TONE            0x00200000L
-#define MANUFACTURER_FEATURE_FAX_PAPER_FORMATS    0x00400000L
-#define MANUFACTURER_FEATURE_OK_FC_LABEL          0x00800000L
-#define MANUFACTURER_FEATURE_VOWN                 0x01000000L
-#define MANUFACTURER_FEATURE_XCONNECT             0x02000000L
-#define MANUFACTURER_FEATURE_DMACONNECT           0x04000000L
-#define MANUFACTURER_FEATURE_AUDIO_TAP            0x08000000L
-#define MANUFACTURER_FEATURE_FAX_NONSTANDARD      0x10000000L
-
-/*------------------------------------------------------------------*/
-/* DTMF interface to IDI                                            */
-/*------------------------------------------------------------------*/
-
-
-#define DTMF_DIGIT_TONE_LOW_GROUP_697_HZ        0x00
-#define DTMF_DIGIT_TONE_LOW_GROUP_770_HZ        0x01
-#define DTMF_DIGIT_TONE_LOW_GROUP_852_HZ        0x02
-#define DTMF_DIGIT_TONE_LOW_GROUP_941_HZ        0x03
-#define DTMF_DIGIT_TONE_LOW_GROUP_MASK          0x03
-#define DTMF_DIGIT_TONE_HIGH_GROUP_1209_HZ      0x00
-#define DTMF_DIGIT_TONE_HIGH_GROUP_1336_HZ      0x04
-#define DTMF_DIGIT_TONE_HIGH_GROUP_1477_HZ      0x08
-#define DTMF_DIGIT_TONE_HIGH_GROUP_1633_HZ      0x0c
-#define DTMF_DIGIT_TONE_HIGH_GROUP_MASK         0x0c
-#define DTMF_DIGIT_TONE_CODE_0                  0x07
-#define DTMF_DIGIT_TONE_CODE_1                  0x00
-#define DTMF_DIGIT_TONE_CODE_2                  0x04
-#define DTMF_DIGIT_TONE_CODE_3                  0x08
-#define DTMF_DIGIT_TONE_CODE_4                  0x01
-#define DTMF_DIGIT_TONE_CODE_5                  0x05
-#define DTMF_DIGIT_TONE_CODE_6                  0x09
-#define DTMF_DIGIT_TONE_CODE_7                  0x02
-#define DTMF_DIGIT_TONE_CODE_8                  0x06
-#define DTMF_DIGIT_TONE_CODE_9                  0x0a
-#define DTMF_DIGIT_TONE_CODE_STAR               0x03
-#define DTMF_DIGIT_TONE_CODE_HASHMARK           0x0b
-#define DTMF_DIGIT_TONE_CODE_A                  0x0c
-#define DTMF_DIGIT_TONE_CODE_B                  0x0d
-#define DTMF_DIGIT_TONE_CODE_C                  0x0e
-#define DTMF_DIGIT_TONE_CODE_D                  0x0f
-
-#define DTMF_UDATA_REQUEST_SEND_DIGITS            16
-#define DTMF_UDATA_REQUEST_ENABLE_RECEIVER        17
-#define DTMF_UDATA_REQUEST_DISABLE_RECEIVER       18
-#define DTMF_UDATA_INDICATION_DIGITS_SENT         16
-#define DTMF_UDATA_INDICATION_DIGITS_RECEIVED     17
-#define DTMF_UDATA_INDICATION_MODEM_CALLING_TONE  18
-#define DTMF_UDATA_INDICATION_FAX_CALLING_TONE    19
-#define DTMF_UDATA_INDICATION_ANSWER_TONE         20
-
-#define UDATA_REQUEST_MIXER_TAP_DATA        27
-#define UDATA_INDICATION_MIXER_TAP_DATA     27
-
-#define DTMF_LISTEN_ACTIVE_FLAG        0x01
-#define DTMF_SEND_DIGIT_FLAG           0x01
-
-
-/*------------------------------------------------------------------*/
-/* Mixer interface to IDI                                           */
-/*------------------------------------------------------------------*/
-
-
-#define LI2_FLAG_PCCONNECT_A_B 0x40000000
-#define LI2_FLAG_PCCONNECT_B_A 0x80000000
-
-#define MIXER_BCHANNELS_BRI    2
-#define MIXER_IC_CHANNELS_BRI  MIXER_BCHANNELS_BRI
-#define MIXER_IC_CHANNEL_BASE  MIXER_BCHANNELS_BRI
-#define MIXER_CHANNELS_BRI     (MIXER_BCHANNELS_BRI + MIXER_IC_CHANNELS_BRI)
-#define MIXER_CHANNELS_PRI     32
-
-typedef struct li_config_s LI_CONFIG;
-
-struct xconnect_card_address_s {
-	dword low;
-	dword high;
-};
-
-struct xconnect_transfer_address_s {
-	struct xconnect_card_address_s card_address;
-	dword offset;
-};
-
-struct li_config_s {
-	DIVA_CAPI_ADAPTER   *adapter;
-	PLCI   *plci;
-	struct xconnect_transfer_address_s send_b;
-	struct xconnect_transfer_address_s send_pc;
-	byte   *flag_table;  /* dword aligned and sized */
-	byte   *coef_table;  /* dword aligned and sized */
-	byte channel;
-	byte curchnl;
-	byte chflags;
-};
-
-extern LI_CONFIG   *li_config_table;
-extern word li_total_channels;
-
-#define LI_CHANNEL_INVOLVED        0x01
-#define LI_CHANNEL_ACTIVE          0x02
-#define LI_CHANNEL_TX_DATA         0x04
-#define LI_CHANNEL_RX_DATA         0x08
-#define LI_CHANNEL_CONFERENCE      0x10
-#define LI_CHANNEL_ADDRESSES_SET   0x80
-
-#define LI_CHFLAG_MONITOR          0x01
-#define LI_CHFLAG_MIX              0x02
-#define LI_CHFLAG_LOOP             0x04
-
-#define LI_FLAG_INTERCONNECT       0x01
-#define LI_FLAG_MONITOR            0x02
-#define LI_FLAG_MIX                0x04
-#define LI_FLAG_PCCONNECT          0x08
-#define LI_FLAG_CONFERENCE         0x10
-#define LI_FLAG_ANNOUNCEMENT       0x20
-
-#define LI_COEF_CH_CH              0x01
-#define LI_COEF_CH_PC              0x02
-#define LI_COEF_PC_CH              0x04
-#define LI_COEF_PC_PC              0x08
-#define LI_COEF_CH_CH_SET          0x10
-#define LI_COEF_CH_PC_SET          0x20
-#define LI_COEF_PC_CH_SET          0x40
-#define LI_COEF_PC_PC_SET          0x80
-
-#define LI_REQ_SILENT_UPDATE       0xffff
-
-#define LI_PLCI_B_LAST_FLAG        ((dword) 0x80000000L)
-#define LI_PLCI_B_DISC_FLAG        ((dword) 0x40000000L)
-#define LI_PLCI_B_SKIP_FLAG        ((dword) 0x20000000L)
-#define LI_PLCI_B_FLAG_MASK        ((dword) 0xe0000000L)
-
-#define UDATA_REQUEST_SET_MIXER_COEFS_BRI       24
-#define UDATA_REQUEST_SET_MIXER_COEFS_PRI_SYNC  25
-#define UDATA_REQUEST_SET_MIXER_COEFS_PRI_ASYN  26
-#define UDATA_INDICATION_MIXER_COEFS_SET        24
-
-#define MIXER_FEATURE_ENABLE_TX_DATA        0x0001
-#define MIXER_FEATURE_ENABLE_RX_DATA        0x0002
-
-#define MIXER_COEF_LINE_CHANNEL_MASK        0x1f
-#define MIXER_COEF_LINE_FROM_PC_FLAG        0x20
-#define MIXER_COEF_LINE_TO_PC_FLAG          0x40
-#define MIXER_COEF_LINE_ROW_FLAG            0x80
-
-#define UDATA_REQUEST_XCONNECT_FROM         28
-#define UDATA_INDICATION_XCONNECT_FROM      28
-#define UDATA_REQUEST_XCONNECT_TO           29
-#define UDATA_INDICATION_XCONNECT_TO        29
-
-#define XCONNECT_CHANNEL_PORT_B             0x0000
-#define XCONNECT_CHANNEL_PORT_PC            0x8000
-#define XCONNECT_CHANNEL_PORT_MASK          0x8000
-#define XCONNECT_CHANNEL_NUMBER_MASK        0x7fff
-#define XCONNECT_CHANNEL_PORT_COUNT         2
-
-#define XCONNECT_SUCCESS           0x0000
-#define XCONNECT_ERROR             0x0001
-
-
-/*------------------------------------------------------------------*/
-/* Echo canceller interface to IDI                                  */
-/*------------------------------------------------------------------*/
-
-
-#define PRIVATE_ECHO_CANCELLER         0
-
-#define PRIV_SELECTOR_ECHO_CANCELLER   255
-
-#define EC_ENABLE_OPERATION            1
-#define EC_DISABLE_OPERATION           2
-#define EC_FREEZE_COEFFICIENTS         3
-#define EC_RESUME_COEFFICIENT_UPDATE   4
-#define EC_RESET_COEFFICIENTS          5
-
-#define EC_DISABLE_NON_LINEAR_PROCESSING     0x0001
-#define EC_DO_NOT_REQUIRE_REVERSALS          0x0002
-#define EC_DETECT_DISABLE_TONE               0x0004
-
-#define EC_SUCCESS                           0
-#define EC_UNSUPPORTED_OPERATION             1
-
-#define EC_BYPASS_DUE_TO_CONTINUOUS_2100HZ   1
-#define EC_BYPASS_DUE_TO_REVERSED_2100HZ     2
-#define EC_BYPASS_RELEASED                   3
-
-#define DSP_CTRL_SET_LEC_PARAMETERS          0x05
-
-#define LEC_ENABLE_ECHO_CANCELLER            0x0001
-#define LEC_ENABLE_2100HZ_DETECTOR           0x0002
-#define LEC_REQUIRE_2100HZ_REVERSALS         0x0004
-#define LEC_MANUAL_DISABLE                   0x0008
-#define LEC_ENABLE_NONLINEAR_PROCESSING      0x0010
-#define LEC_FREEZE_COEFFICIENTS              0x0020
-#define LEC_RESET_COEFFICIENTS               0x8000
-
-#define LEC_MAX_SUPPORTED_TAIL_LENGTH        32
-
-#define LEC_UDATA_INDICATION_DISABLE_DETECT  9
-
-#define LEC_DISABLE_TYPE_CONTIGNUOUS_2100HZ  0x00
-#define LEC_DISABLE_TYPE_REVERSED_2100HZ     0x01
-#define LEC_DISABLE_RELEASED                 0x02
-
-
-/*------------------------------------------------------------------*/
-/* RTP interface to IDI                                             */
-/*------------------------------------------------------------------*/
-
-
-#define B1_RTP                  31
-#define B2_RTP                  31
-#define B3_RTP                  31
-
-#define PRIVATE_RTP                    1
-
-#define RTP_PRIM_PAYLOAD_PCMU_8000     0
-#define RTP_PRIM_PAYLOAD_1016_8000     1
-#define RTP_PRIM_PAYLOAD_G726_32_8000  2
-#define RTP_PRIM_PAYLOAD_GSM_8000      3
-#define RTP_PRIM_PAYLOAD_G723_8000     4
-#define RTP_PRIM_PAYLOAD_DVI4_8000     5
-#define RTP_PRIM_PAYLOAD_DVI4_16000    6
-#define RTP_PRIM_PAYLOAD_LPC_8000      7
-#define RTP_PRIM_PAYLOAD_PCMA_8000     8
-#define RTP_PRIM_PAYLOAD_G722_16000    9
-#define RTP_PRIM_PAYLOAD_QCELP_8000    12
-#define RTP_PRIM_PAYLOAD_G728_8000     14
-#define RTP_PRIM_PAYLOAD_G729_8000     18
-#define RTP_PRIM_PAYLOAD_GSM_HR_8000   30
-#define RTP_PRIM_PAYLOAD_GSM_EFR_8000  31
-
-#define RTP_ADD_PAYLOAD_BASE           32
-#define RTP_ADD_PAYLOAD_RED            32
-#define RTP_ADD_PAYLOAD_CN_8000        33
-#define RTP_ADD_PAYLOAD_DTMF           34
-
-#define RTP_SUCCESS                         0
-#define RTP_ERR_SSRC_OR_PAYLOAD_CHANGE      1
-
-#define UDATA_REQUEST_RTP_RECONFIGURE       64
-#define UDATA_INDICATION_RTP_CHANGE         65
-#define BUDATA_REQUEST_QUERY_RTCP_REPORT    1
-#define BUDATA_INDICATION_RTCP_REPORT       1
-
-#define RTP_CONNECT_OPTION_DISC_ON_SSRC_CHANGE    0x00000001L
-#define RTP_CONNECT_OPTION_DISC_ON_PT_CHANGE      0x00000002L
-#define RTP_CONNECT_OPTION_DISC_ON_UNKNOWN_PT     0x00000004L
-#define RTP_CONNECT_OPTION_NO_SILENCE_TRANSMIT    0x00010000L
-
-#define RTP_PAYLOAD_OPTION_VOICE_ACTIVITY_DETECT  0x0001
-#define RTP_PAYLOAD_OPTION_DISABLE_POST_FILTER    0x0002
-#define RTP_PAYLOAD_OPTION_G723_LOW_CODING_RATE   0x0100
-
-#define RTP_PACKET_FILTER_IGNORE_UNKNOWN_SSRC     0x00000001L
-
-#define RTP_CHANGE_FLAG_SSRC_CHANGE               0x00000001L
-#define RTP_CHANGE_FLAG_PAYLOAD_TYPE_CHANGE       0x00000002L
-#define RTP_CHANGE_FLAG_UNKNOWN_PAYLOAD_TYPE      0x00000004L
-
-
-/*------------------------------------------------------------------*/
-/* T.38 interface to IDI                                            */
-/*------------------------------------------------------------------*/
-
-
-#define B1_T38                  30
-#define B2_T38                  30
-#define B3_T38                  30
-
-#define PRIVATE_T38                    2
-
-
-/*------------------------------------------------------------------*/
-/* PIAFS interface to IDI                                            */
-/*------------------------------------------------------------------*/
-
-
-#define B1_PIAFS                29
-#define B2_PIAFS                29
-
-#define PRIVATE_PIAFS           29
-
-/*
-  B2 configuration for PIAFS:
-  +---------------------+------+-----------------------------------------+
-  | PIAFS Protocol      | byte | Bit 1 - Protocol Speed                  |
-  | Speed configuration |      |         0 - 32K                         |
-  |                     |      |         1 - 64K (default)               |
-  |                     |      | Bit 2 - Variable Protocol Speed         |
-  |                     |      |         0 - Speed is fix                |
-  |                     |      |         1 - Speed is variable (default) |
-  +---------------------+------+-----------------------------------------+
-  | Direction           | word | Enable compression/decompression for    |
-  |                     |      | 0: All direction                        |
-  |                     |      | 1: disable outgoing data                |
-  |                     |      | 2: disable incoming data               |
-  |                     |      | 3: disable both direction (default)     |
-  +---------------------+------+-----------------------------------------+
-  | Number of code      | word | Parameter P1 of V.42bis in accordance   |
-  | words               |      | with V.42bis                            |
-  +---------------------+------+-----------------------------------------+
-  | Maximum String      | word | Parameter P2 of V.42bis in accordance   |
-  | Length              |      | with V.42bis                            |
-  +---------------------+------+-----------------------------------------+
-  | control (UDATA)     | byte | enable PIAFS control communication      |
-  | abilities           |      |                                         |
-  +---------------------+------+-----------------------------------------+
-*/
-#define PIAFS_UDATA_ABILITIES  0x80
-
-/*------------------------------------------------------------------*/
-/* FAX SUB/SEP/PWD extension                                        */
-/*------------------------------------------------------------------*/
-
-
-#define PRIVATE_FAX_SUB_SEP_PWD        3
-
-
-
-/*------------------------------------------------------------------*/
-/* V.18 extension                                                   */
-/*------------------------------------------------------------------*/
-
-
-#define PRIVATE_V18                    4
-
-
-
-/*------------------------------------------------------------------*/
-/* DTMF TONE extension                                              */
-/*------------------------------------------------------------------*/
-
-
-#define DTMF_GET_SUPPORTED_DETECT_CODES  0xf8
-#define DTMF_GET_SUPPORTED_SEND_CODES    0xf9
-#define DTMF_LISTEN_TONE_START           0xfa
-#define DTMF_LISTEN_TONE_STOP            0xfb
-#define DTMF_SEND_TONE                   0xfc
-#define DTMF_LISTEN_MF_START             0xfd
-#define DTMF_LISTEN_MF_STOP              0xfe
-#define DTMF_SEND_MF                     0xff
-
-#define DTMF_MF_DIGIT_TONE_CODE_1               0x10
-#define DTMF_MF_DIGIT_TONE_CODE_2               0x11
-#define DTMF_MF_DIGIT_TONE_CODE_3               0x12
-#define DTMF_MF_DIGIT_TONE_CODE_4               0x13
-#define DTMF_MF_DIGIT_TONE_CODE_5               0x14
-#define DTMF_MF_DIGIT_TONE_CODE_6               0x15
-#define DTMF_MF_DIGIT_TONE_CODE_7               0x16
-#define DTMF_MF_DIGIT_TONE_CODE_8               0x17
-#define DTMF_MF_DIGIT_TONE_CODE_9               0x18
-#define DTMF_MF_DIGIT_TONE_CODE_0               0x19
-#define DTMF_MF_DIGIT_TONE_CODE_K1              0x1a
-#define DTMF_MF_DIGIT_TONE_CODE_K2              0x1b
-#define DTMF_MF_DIGIT_TONE_CODE_KP              0x1c
-#define DTMF_MF_DIGIT_TONE_CODE_S1              0x1d
-#define DTMF_MF_DIGIT_TONE_CODE_ST              0x1e
-
-#define DTMF_DIGIT_CODE_COUNT                   16
-#define DTMF_MF_DIGIT_CODE_BASE                 DSP_DTMF_DIGIT_CODE_COUNT
-#define DTMF_MF_DIGIT_CODE_COUNT                15
-#define DTMF_TOTAL_DIGIT_CODE_COUNT             (DSP_MF_DIGIT_CODE_BASE + DSP_MF_DIGIT_CODE_COUNT)
-
-#define DTMF_TONE_DIGIT_BASE                    0x80
-
-#define DTMF_SIGNAL_NO_TONE                     (DTMF_TONE_DIGIT_BASE + 0)
-#define DTMF_SIGNAL_UNIDENTIFIED_TONE           (DTMF_TONE_DIGIT_BASE + 1)
-
-#define DTMF_SIGNAL_DIAL_TONE                   (DTMF_TONE_DIGIT_BASE + 2)
-#define DTMF_SIGNAL_PABX_INTERNAL_DIAL_TONE     (DTMF_TONE_DIGIT_BASE + 3)
-#define DTMF_SIGNAL_SPECIAL_DIAL_TONE           (DTMF_TONE_DIGIT_BASE + 4)   /* stutter dial tone */
-#define DTMF_SIGNAL_SECOND_DIAL_TONE            (DTMF_TONE_DIGIT_BASE + 5)
-#define DTMF_SIGNAL_RINGING_TONE                (DTMF_TONE_DIGIT_BASE + 6)
-#define DTMF_SIGNAL_SPECIAL_RINGING_TONE        (DTMF_TONE_DIGIT_BASE + 7)
-#define DTMF_SIGNAL_BUSY_TONE                   (DTMF_TONE_DIGIT_BASE + 8)
-#define DTMF_SIGNAL_CONGESTION_TONE             (DTMF_TONE_DIGIT_BASE + 9)   /* reorder tone */
-#define DTMF_SIGNAL_SPECIAL_INFORMATION_TONE    (DTMF_TONE_DIGIT_BASE + 10)
-#define DTMF_SIGNAL_COMFORT_TONE                (DTMF_TONE_DIGIT_BASE + 11)
-#define DTMF_SIGNAL_HOLD_TONE                   (DTMF_TONE_DIGIT_BASE + 12)
-#define DTMF_SIGNAL_RECORD_TONE                 (DTMF_TONE_DIGIT_BASE + 13)
-#define DTMF_SIGNAL_CALLER_WAITING_TONE         (DTMF_TONE_DIGIT_BASE + 14)
-#define DTMF_SIGNAL_CALL_WAITING_TONE           (DTMF_TONE_DIGIT_BASE + 15)
-#define DTMF_SIGNAL_PAY_TONE                    (DTMF_TONE_DIGIT_BASE + 16)
-#define DTMF_SIGNAL_POSITIVE_INDICATION_TONE    (DTMF_TONE_DIGIT_BASE + 17)
-#define DTMF_SIGNAL_NEGATIVE_INDICATION_TONE    (DTMF_TONE_DIGIT_BASE + 18)
-#define DTMF_SIGNAL_WARNING_TONE                (DTMF_TONE_DIGIT_BASE + 19)
-#define DTMF_SIGNAL_INTRUSION_TONE              (DTMF_TONE_DIGIT_BASE + 20)
-#define DTMF_SIGNAL_CALLING_CARD_SERVICE_TONE   (DTMF_TONE_DIGIT_BASE + 21)
-#define DTMF_SIGNAL_PAYPHONE_RECOGNITION_TONE   (DTMF_TONE_DIGIT_BASE + 22)
-#define DTMF_SIGNAL_CPE_ALERTING_SIGNAL         (DTMF_TONE_DIGIT_BASE + 23)
-#define DTMF_SIGNAL_OFF_HOOK_WARNING_TONE       (DTMF_TONE_DIGIT_BASE + 24)
-
-#define DTMF_SIGNAL_INTERCEPT_TONE              (DTMF_TONE_DIGIT_BASE + 63)
-
-#define DTMF_SIGNAL_MODEM_CALLING_TONE          (DTMF_TONE_DIGIT_BASE + 64)
-#define DTMF_SIGNAL_FAX_CALLING_TONE            (DTMF_TONE_DIGIT_BASE + 65)
-#define DTMF_SIGNAL_ANSWER_TONE                 (DTMF_TONE_DIGIT_BASE + 66)
-#define DTMF_SIGNAL_REVERSED_ANSWER_TONE        (DTMF_TONE_DIGIT_BASE + 67)
-#define DTMF_SIGNAL_ANSAM_TONE                  (DTMF_TONE_DIGIT_BASE + 68)
-#define DTMF_SIGNAL_REVERSED_ANSAM_TONE         (DTMF_TONE_DIGIT_BASE + 69)
-#define DTMF_SIGNAL_BELL103_ANSWER_TONE         (DTMF_TONE_DIGIT_BASE + 70)
-#define DTMF_SIGNAL_FAX_FLAGS                   (DTMF_TONE_DIGIT_BASE + 71)
-#define DTMF_SIGNAL_G2_FAX_GROUP_ID             (DTMF_TONE_DIGIT_BASE + 72)
-#define DTMF_SIGNAL_HUMAN_SPEECH                (DTMF_TONE_DIGIT_BASE + 73)
-#define DTMF_SIGNAL_ANSWERING_MACHINE_390       (DTMF_TONE_DIGIT_BASE + 74)
-
-#define DTMF_MF_LISTEN_ACTIVE_FLAG     0x02
-#define DTMF_SEND_MF_FLAG              0x02
-#define DTMF_TONE_LISTEN_ACTIVE_FLAG   0x04
-#define DTMF_SEND_TONE_FLAG            0x04
-
-#define PRIVATE_DTMF_TONE              5
-
-
-/*------------------------------------------------------------------*/
-/* FAX paper format extension                                       */
-/*------------------------------------------------------------------*/
-
-
-#define PRIVATE_FAX_PAPER_FORMATS      6
-
-
-
-/*------------------------------------------------------------------*/
-/* V.OWN extension                                                  */
-/*------------------------------------------------------------------*/
-
-
-#define PRIVATE_VOWN                   7
-
-
-
-/*------------------------------------------------------------------*/
-/* FAX non-standard facilities extension                            */
-/*------------------------------------------------------------------*/
-
-
-#define PRIVATE_FAX_NONSTANDARD        8
-
-
-
-/*------------------------------------------------------------------*/
-/* Advanced voice                                                   */
-/*------------------------------------------------------------------*/
-
-#define ADV_VOICE_WRITE_ACTIVATION    0
-#define ADV_VOICE_WRITE_DEACTIVATION  1
-#define ADV_VOICE_WRITE_UPDATE        2
-
-#define ADV_VOICE_OLD_COEF_COUNT    6
-#define ADV_VOICE_NEW_COEF_BASE     (ADV_VOICE_OLD_COEF_COUNT * sizeof(word))
-
-/*------------------------------------------------------------------*/
-/* B1 resource switching                                            */
-/*------------------------------------------------------------------*/
-
-#define B1_FACILITY_LOCAL  0x01
-#define B1_FACILITY_MIXER  0x02
-#define B1_FACILITY_DTMFX  0x04
-#define B1_FACILITY_DTMFR  0x08
-#define B1_FACILITY_VOICE  0x10
-#define B1_FACILITY_EC     0x20
-
-#define ADJUST_B_MODE_SAVE          0x0001
-#define ADJUST_B_MODE_REMOVE_L23    0x0002
-#define ADJUST_B_MODE_SWITCH_L1     0x0004
-#define ADJUST_B_MODE_NO_RESOURCE   0x0008
-#define ADJUST_B_MODE_ASSIGN_L23    0x0010
-#define ADJUST_B_MODE_USER_CONNECT  0x0020
-#define ADJUST_B_MODE_CONNECT       0x0040
-#define ADJUST_B_MODE_RESTORE       0x0080
-
-#define ADJUST_B_START                     0
-#define ADJUST_B_SAVE_MIXER_1              1
-#define ADJUST_B_SAVE_DTMF_1               2
-#define ADJUST_B_REMOVE_L23_1              3
-#define ADJUST_B_REMOVE_L23_2              4
-#define ADJUST_B_SAVE_EC_1                 5
-#define ADJUST_B_SAVE_DTMF_PARAMETER_1     6
-#define ADJUST_B_SAVE_VOICE_1              7
-#define ADJUST_B_SWITCH_L1_1               8
-#define ADJUST_B_SWITCH_L1_2               9
-#define ADJUST_B_RESTORE_VOICE_1           10
-#define ADJUST_B_RESTORE_VOICE_2           11
-#define ADJUST_B_RESTORE_DTMF_PARAMETER_1  12
-#define ADJUST_B_RESTORE_DTMF_PARAMETER_2  13
-#define ADJUST_B_RESTORE_EC_1              14
-#define ADJUST_B_RESTORE_EC_2              15
-#define ADJUST_B_ASSIGN_L23_1              16
-#define ADJUST_B_ASSIGN_L23_2              17
-#define ADJUST_B_CONNECT_1                 18
-#define ADJUST_B_CONNECT_2                 19
-#define ADJUST_B_CONNECT_3                 20
-#define ADJUST_B_CONNECT_4                 21
-#define ADJUST_B_RESTORE_DTMF_1            22
-#define ADJUST_B_RESTORE_DTMF_2            23
-#define ADJUST_B_RESTORE_MIXER_1           24
-#define ADJUST_B_RESTORE_MIXER_2           25
-#define ADJUST_B_RESTORE_MIXER_3           26
-#define ADJUST_B_RESTORE_MIXER_4           27
-#define ADJUST_B_RESTORE_MIXER_5           28
-#define ADJUST_B_RESTORE_MIXER_6           29
-#define ADJUST_B_RESTORE_MIXER_7           30
-#define ADJUST_B_END                       31
-
-/*------------------------------------------------------------------*/
-/* XON Protocol def's                                               */
-/*------------------------------------------------------------------*/
-#define N_CH_XOFF               0x01
-#define N_XON_SENT              0x02
-#define N_XON_REQ               0x04
-#define N_XON_CONNECT_IND       0x08
-#define N_RX_FLOW_CONTROL_MASK  0x3f
-#define N_OK_FC_PENDING         0x80
-#define N_TX_FLOW_CONTROL_MASK  0xc0
-
-/*------------------------------------------------------------------*/
-/* NCPI state                                                       */
-/*------------------------------------------------------------------*/
-#define NCPI_VALID_CONNECT_B3_IND  0x01
-#define NCPI_VALID_CONNECT_B3_ACT  0x02
-#define NCPI_VALID_DISC_B3_IND     0x04
-#define NCPI_CONNECT_B3_ACT_SENT   0x08
-#define NCPI_NEGOTIATE_B3_SENT     0x10
-#define NCPI_MDM_CTS_ON_RECEIVED   0x40
-#define NCPI_MDM_DCD_ON_RECEIVED   0x80
-
-/*------------------------------------------------------------------*/
diff --git a/drivers/isdn/hardware/eicon/divamnt.c b/drivers/isdn/hardware/eicon/divamnt.c
deleted file mode 100644
index 5a95587b3117..000000000000
--- a/drivers/isdn/hardware/eicon/divamnt.c
+++ /dev/null
@@ -1,239 +0,0 @@
-/* $Id: divamnt.c,v 1.32.6.10 2005/02/11 19:40:25 armin Exp $
- *
- * Driver for Eicon DIVA Server ISDN cards.
- * Maint module
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/poll.h>
-#include <linux/mutex.h>
-#include <linux/uaccess.h>
-
-#include "platform.h"
-#include "di_defs.h"
-#include "divasync.h"
-#include "debug_if.h"
-
-static DEFINE_MUTEX(maint_mutex);
-static char *main_revision = "$Revision: 1.32.6.10 $";
-
-static int major;
-
-MODULE_DESCRIPTION("Maint driver for Eicon DIVA Server cards");
-MODULE_AUTHOR("Cytronics & Melware, Eicon Networks");
-MODULE_SUPPORTED_DEVICE("DIVA card driver");
-MODULE_LICENSE("GPL");
-
-static int buffer_length = 128;
-module_param(buffer_length, int, 0);
-static unsigned long diva_dbg_mem = 0;
-module_param(diva_dbg_mem, ulong, 0);
-
-static char *DRIVERNAME =
-	"Eicon DIVA - MAINT module (http://www.melware.net)";
-static char *DRIVERLNAME = "diva_mnt";
-static char *DEVNAME = "DivasMAINT";
-char *DRIVERRELEASE_MNT = "2.0";
-
-static wait_queue_head_t msgwaitq;
-static unsigned long opened;
-
-extern int mntfunc_init(int *, void **, unsigned long);
-extern void mntfunc_finit(void);
-extern int maint_read_write(void __user *buf, int count);
-
-/*
- *  helper functions
- */
-static char *getrev(const char *revision)
-{
-	char *rev;
-	char *p;
-
-	if ((p = strchr(revision, ':'))) {
-		rev = p + 2;
-		p = strchr(rev, '$');
-		*--p = 0;
-	} else
-		rev = "1.0";
-
-	return rev;
-}
-
-/*
- * kernel/user space copy functions
- */
-int diva_os_copy_to_user(void *os_handle, void __user *dst, const void *src,
-			 int length)
-{
-	return (copy_to_user(dst, src, length));
-}
-int diva_os_copy_from_user(void *os_handle, void *dst, const void __user *src,
-			   int length)
-{
-	return (copy_from_user(dst, src, length));
-}
-
-/*
- * get time
- */
-void diva_os_get_time(dword *sec, dword *usec)
-{
-	struct timespec64 time;
-
-	ktime_get_ts64(&time);
-
-	*sec = (dword) time.tv_sec;
-	*usec = (dword) (time.tv_nsec / NSEC_PER_USEC);
-}
-
-/*
- * device node operations
- */
-static __poll_t maint_poll(struct file *file, poll_table *wait)
-{
-	__poll_t mask = 0;
-
-	poll_wait(file, &msgwaitq, wait);
-	mask = EPOLLOUT | EPOLLWRNORM;
-	if (file->private_data || diva_dbg_q_length()) {
-		mask |= EPOLLIN | EPOLLRDNORM;
-	}
-	return (mask);
-}
-
-static int maint_open(struct inode *ino, struct file *filep)
-{
-	int ret;
-
-	mutex_lock(&maint_mutex);
-	/* only one open is allowed, so we test
-	   it atomically */
-	if (test_and_set_bit(0, &opened))
-		ret = -EBUSY;
-	else {
-		filep->private_data = NULL;
-		ret = nonseekable_open(ino, filep);
-	}
-	mutex_unlock(&maint_mutex);
-	return ret;
-}
-
-static int maint_close(struct inode *ino, struct file *filep)
-{
-	if (filep->private_data) {
-		diva_os_free(0, filep->private_data);
-		filep->private_data = NULL;
-	}
-
-	/* clear 'used' flag */
-	clear_bit(0, &opened);
-
-	return (0);
-}
-
-static ssize_t divas_maint_write(struct file *file, const char __user *buf,
-				 size_t count, loff_t *ppos)
-{
-	return (maint_read_write((char __user *) buf, (int) count));
-}
-
-static ssize_t divas_maint_read(struct file *file, char __user *buf,
-				size_t count, loff_t *ppos)
-{
-	return (maint_read_write(buf, (int) count));
-}
-
-static const struct file_operations divas_maint_fops = {
-	.owner   = THIS_MODULE,
-	.llseek  = no_llseek,
-	.read    = divas_maint_read,
-	.write   = divas_maint_write,
-	.poll    = maint_poll,
-	.open    = maint_open,
-	.release = maint_close
-};
-
-static void divas_maint_unregister_chrdev(void)
-{
-	unregister_chrdev(major, DEVNAME);
-}
-
-static int __init divas_maint_register_chrdev(void)
-{
-	if ((major = register_chrdev(0, DEVNAME, &divas_maint_fops)) < 0)
-	{
-		printk(KERN_ERR "%s: failed to create /dev entry.\n",
-		       DRIVERLNAME);
-		return (0);
-	}
-
-	return (1);
-}
-
-/*
- * wake up reader
- */
-void diva_maint_wakeup_read(void)
-{
-	wake_up_interruptible(&msgwaitq);
-}
-
-/*
- *  Driver Load
- */
-static int __init maint_init(void)
-{
-	char tmprev[50];
-	int ret = 0;
-	void *buffer = NULL;
-
-	init_waitqueue_head(&msgwaitq);
-
-	printk(KERN_INFO "%s\n", DRIVERNAME);
-	printk(KERN_INFO "%s: Rel:%s  Rev:", DRIVERLNAME, DRIVERRELEASE_MNT);
-	strcpy(tmprev, main_revision);
-	printk("%s  Build: %s \n", getrev(tmprev), DIVA_BUILD);
-
-	if (!divas_maint_register_chrdev()) {
-		ret = -EIO;
-		goto out;
-	}
-
-	if (!(mntfunc_init(&buffer_length, &buffer, diva_dbg_mem))) {
-		printk(KERN_ERR "%s: failed to connect to DIDD.\n",
-		       DRIVERLNAME);
-		divas_maint_unregister_chrdev();
-		ret = -EIO;
-		goto out;
-	}
-
-	printk(KERN_INFO "%s: trace buffer = %p - %d kBytes, %s (Major: %d)\n",
-	       DRIVERLNAME, buffer, (buffer_length / 1024),
-	       (diva_dbg_mem == 0) ? "internal" : "external", major);
-
-out:
-	return (ret);
-}
-
-/*
-**  Driver Unload
-*/
-static void __exit maint_exit(void)
-{
-	divas_maint_unregister_chrdev();
-	mntfunc_finit();
-
-	printk(KERN_INFO "%s: module unloaded.\n", DRIVERLNAME);
-}
-
-module_init(maint_init);
-module_exit(maint_exit);
diff --git a/drivers/isdn/hardware/eicon/divasfunc.c b/drivers/isdn/hardware/eicon/divasfunc.c
deleted file mode 100644
index 4be5f8814777..000000000000
--- a/drivers/isdn/hardware/eicon/divasfunc.c
+++ /dev/null
@@ -1,237 +0,0 @@
-/* $Id: divasfunc.c,v 1.23.4.2 2004/08/28 20:03:53 armin Exp $
- *
- * Low level driver for Eicon DIVA Server ISDN cards.
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#include "platform.h"
-#include "di_defs.h"
-#include "pc.h"
-#include "di.h"
-#include "io.h"
-#include "divasync.h"
-#include "diva.h"
-#include "xdi_vers.h"
-
-#define DBG_MINIMUM  (DL_LOG + DL_FTL + DL_ERR)
-#define DBG_DEFAULT  (DBG_MINIMUM + DL_XLOG + DL_REG)
-
-static int debugmask;
-
-extern void DIVA_DIDD_Read(void *, int);
-
-extern PISDN_ADAPTER IoAdapters[MAX_ADAPTER];
-
-extern char *DRIVERRELEASE_DIVAS;
-
-static dword notify_handle;
-static DESCRIPTOR DAdapter;
-static DESCRIPTOR MAdapter;
-
-/* --------------------------------------------------------------------------
-   MAINT driver connector section
-   -------------------------------------------------------------------------- */
-static void no_printf(unsigned char *x, ...)
-{
-	/* dummy debug function */
-}
-
-#include "debuglib.c"
-
-/*
- * get the adapters serial number
- */
-void diva_get_vserial_number(PISDN_ADAPTER IoAdapter, char *buf)
-{
-	int contr = 0;
-
-	if ((contr = ((IoAdapter->serialNo & 0xff000000) >> 24))) {
-		sprintf(buf, "%d-%d",
-			IoAdapter->serialNo & 0x00ffffff, contr + 1);
-	} else {
-		sprintf(buf, "%d", IoAdapter->serialNo);
-	}
-}
-
-/*
- * register a new adapter
- */
-void diva_xdi_didd_register_adapter(int card)
-{
-	DESCRIPTOR d;
-	IDI_SYNC_REQ req;
-
-	if (card && ((card - 1) < MAX_ADAPTER) &&
-	    IoAdapters[card - 1] && Requests[card - 1]) {
-		d.type = IoAdapters[card - 1]->Properties.DescType;
-		d.request = Requests[card - 1];
-		d.channels = IoAdapters[card - 1]->Properties.Channels;
-		d.features = IoAdapters[card - 1]->Properties.Features;
-		DBG_TRC(("DIDD register A(%d) channels=%d", card,
-			 d.channels))
-			/* workaround for different Name in structure */
-			strlcpy(IoAdapters[card - 1]->Name,
-				IoAdapters[card - 1]->Properties.Name,
-				sizeof(IoAdapters[card - 1]->Name));
-		req.didd_remove_adapter.e.Req = 0;
-		req.didd_add_adapter.e.Rc = IDI_SYNC_REQ_DIDD_ADD_ADAPTER;
-		req.didd_add_adapter.info.descriptor = (void *) &d;
-		DAdapter.request((ENTITY *)&req);
-		if (req.didd_add_adapter.e.Rc != 0xff) {
-			DBG_ERR(("DIDD register A(%d) failed !", card))
-				}
-		IoAdapters[card - 1]->os_trap_nfy_Fnc = NULL;
-	}
-}
-
-/*
- * remove an adapter
- */
-void diva_xdi_didd_remove_adapter(int card)
-{
-	IDI_SYNC_REQ req;
-	ADAPTER *a = &IoAdapters[card - 1]->a;
-
-	IoAdapters[card - 1]->os_trap_nfy_Fnc = NULL;
-	DBG_TRC(("DIDD de-register A(%d)", card))
-		req.didd_remove_adapter.e.Req = 0;
-	req.didd_remove_adapter.e.Rc = IDI_SYNC_REQ_DIDD_REMOVE_ADAPTER;
-	req.didd_remove_adapter.info.p_request =
-		(IDI_CALL) Requests[card - 1];
-	DAdapter.request((ENTITY *)&req);
-	memset(&(a->IdTable), 0x00, 256);
-}
-
-/*
- * start debug
- */
-static void start_dbg(void)
-{
-	DbgRegister("DIVAS", DRIVERRELEASE_DIVAS, (debugmask) ? debugmask : DBG_DEFAULT);
-	DBG_LOG(("DIVA ISDNXDI BUILD (%s[%s])",
-		 DIVA_BUILD, diva_xdi_common_code_build))
-		}
-
-/*
- * stop debug
- */
-static void stop_dbg(void)
-{
-	DbgDeregister();
-	memset(&MAdapter, 0, sizeof(MAdapter));
-	dprintf = no_printf;
-}
-
-/*
- * didd callback function
- */
-static void *didd_callback(void *context, DESCRIPTOR *adapter,
-			   int removal)
-{
-	if (adapter->type == IDI_DADAPTER) {
-		DBG_ERR(("Notification about IDI_DADAPTER change ! Oops."));
-		return (NULL);
-	}
-
-	if (adapter->type == IDI_DIMAINT) {
-		if (removal) {
-			stop_dbg();
-		} else {
-			memcpy(&MAdapter, adapter, sizeof(MAdapter));
-			dprintf = (DIVA_DI_PRINTF) MAdapter.request;
-			start_dbg();
-		}
-	}
-	return (NULL);
-}
-
-/*
- * connect to didd
- */
-static int __init connect_didd(void)
-{
-	int x = 0;
-	int dadapter = 0;
-	IDI_SYNC_REQ req;
-	DESCRIPTOR DIDD_Table[MAX_DESCRIPTORS];
-
-	DIVA_DIDD_Read(DIDD_Table, sizeof(DIDD_Table));
-
-	for (x = 0; x < MAX_DESCRIPTORS; x++) {
-		if (DIDD_Table[x].type == IDI_DADAPTER) {	/* DADAPTER found */
-			dadapter = 1;
-			memcpy(&DAdapter, &DIDD_Table[x], sizeof(DAdapter));
-			req.didd_notify.e.Req = 0;
-			req.didd_notify.e.Rc =
-				IDI_SYNC_REQ_DIDD_REGISTER_ADAPTER_NOTIFY;
-			req.didd_notify.info.callback = (void *)didd_callback;
-			req.didd_notify.info.context = NULL;
-			DAdapter.request((ENTITY *)&req);
-			if (req.didd_notify.e.Rc != 0xff) {
-				stop_dbg();
-				return (0);
-			}
-			notify_handle = req.didd_notify.info.handle;
-		} else if (DIDD_Table[x].type == IDI_DIMAINT) {	/* MAINT found */
-			memcpy(&MAdapter, &DIDD_Table[x], sizeof(DAdapter));
-			dprintf = (DIVA_DI_PRINTF) MAdapter.request;
-			start_dbg();
-		}
-	}
-
-	if (!dadapter) {
-		stop_dbg();
-	}
-
-	return (dadapter);
-}
-
-/*
- * disconnect from didd
- */
-static void disconnect_didd(void)
-{
-	IDI_SYNC_REQ req;
-
-	stop_dbg();
-
-	req.didd_notify.e.Req = 0;
-	req.didd_notify.e.Rc = IDI_SYNC_REQ_DIDD_REMOVE_ADAPTER_NOTIFY;
-	req.didd_notify.info.handle = notify_handle;
-	DAdapter.request((ENTITY *)&req);
-}
-
-/*
- * init
- */
-int __init divasfunc_init(int dbgmask)
-{
-	char *version;
-
-	debugmask = dbgmask;
-
-	if (!connect_didd()) {
-		DBG_ERR(("divasfunc: failed to connect to DIDD."))
-			return (0);
-	}
-
-	version = diva_xdi_common_code_build;
-
-	divasa_xdi_driver_entry();
-
-	return (1);
-}
-
-/*
- * exit
- */
-void divasfunc_exit(void)
-{
-	divasa_xdi_driver_unload();
-	disconnect_didd();
-}
diff --git a/drivers/isdn/hardware/eicon/divasi.c b/drivers/isdn/hardware/eicon/divasi.c
deleted file mode 100644
index e7081e0c0e35..000000000000
--- a/drivers/isdn/hardware/eicon/divasi.c
+++ /dev/null
@@ -1,562 +0,0 @@
-/* $Id: divasi.c,v 1.25.6.2 2005/01/31 12:22:20 armin Exp $
- *
- * Driver for Eicon DIVA Server ISDN cards.
- * User Mode IDI Interface
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/poll.h>
-#include <linux/proc_fs.h>
-#include <linux/skbuff.h>
-#include <linux/seq_file.h>
-#include <linux/uaccess.h>
-
-#include "platform.h"
-#include "di_defs.h"
-#include "divasync.h"
-#include "um_xdi.h"
-#include "um_idi.h"
-
-static char *main_revision = "$Revision: 1.25.6.2 $";
-
-static int major;
-
-MODULE_DESCRIPTION("User IDI Interface for Eicon ISDN cards");
-MODULE_AUTHOR("Cytronics & Melware, Eicon Networks");
-MODULE_SUPPORTED_DEVICE("DIVA card driver");
-MODULE_LICENSE("GPL");
-
-typedef struct _diva_um_idi_os_context {
-	wait_queue_head_t read_wait;
-	wait_queue_head_t close_wait;
-	struct timer_list diva_timer_id;
-	int aborted;
-	int adapter_nr;
-} diva_um_idi_os_context_t;
-
-static char *DRIVERNAME = "Eicon DIVA - User IDI (http://www.melware.net)";
-static char *DRIVERLNAME = "diva_idi";
-static char *DEVNAME = "DivasIDI";
-char *DRIVERRELEASE_IDI = "2.0";
-
-extern int idifunc_init(void);
-extern void idifunc_finit(void);
-
-/*
- *  helper functions
- */
-static char *getrev(const char *revision)
-{
-	char *rev;
-	char *p;
-	if ((p = strchr(revision, ':'))) {
-		rev = p + 2;
-		p = strchr(rev, '$');
-		*--p = 0;
-	} else
-		rev = "1.0";
-	return rev;
-}
-
-/*
- *  LOCALS
- */
-static ssize_t um_idi_read(struct file *file, char __user *buf, size_t count,
-			   loff_t *offset);
-static ssize_t um_idi_write(struct file *file, const char __user *buf,
-			    size_t count, loff_t *offset);
-static __poll_t um_idi_poll(struct file *file, poll_table *wait);
-static int um_idi_open(struct inode *inode, struct file *file);
-static int um_idi_release(struct inode *inode, struct file *file);
-static int remove_entity(void *entity);
-static void diva_um_timer_function(struct timer_list *t);
-
-/*
- * proc entry
- */
-extern struct proc_dir_entry *proc_net_eicon;
-static struct proc_dir_entry *um_idi_proc_entry = NULL;
-
-static int um_idi_proc_show(struct seq_file *m, void *v)
-{
-	char tmprev[32];
-
-	seq_printf(m, "%s\n", DRIVERNAME);
-	seq_printf(m, "name     : %s\n", DRIVERLNAME);
-	seq_printf(m, "release  : %s\n", DRIVERRELEASE_IDI);
-	strcpy(tmprev, main_revision);
-	seq_printf(m, "revision : %s\n", getrev(tmprev));
-	seq_printf(m, "build    : %s\n", DIVA_BUILD);
-	seq_printf(m, "major    : %d\n", major);
-
-	return 0;
-}
-
-static int __init create_um_idi_proc(void)
-{
-	um_idi_proc_entry = proc_create_single(DRIVERLNAME, S_IRUGO,
-			proc_net_eicon, um_idi_proc_show);
-	if (!um_idi_proc_entry)
-		return (0);
-	return (1);
-}
-
-static void remove_um_idi_proc(void)
-{
-	if (um_idi_proc_entry) {
-		remove_proc_entry(DRIVERLNAME, proc_net_eicon);
-		um_idi_proc_entry = NULL;
-	}
-}
-
-static const struct file_operations divas_idi_fops = {
-	.owner   = THIS_MODULE,
-	.llseek  = no_llseek,
-	.read    = um_idi_read,
-	.write   = um_idi_write,
-	.poll    = um_idi_poll,
-	.open    = um_idi_open,
-	.release = um_idi_release
-};
-
-static void divas_idi_unregister_chrdev(void)
-{
-	unregister_chrdev(major, DEVNAME);
-}
-
-static int __init divas_idi_register_chrdev(void)
-{
-	if ((major = register_chrdev(0, DEVNAME, &divas_idi_fops)) < 0)
-	{
-		printk(KERN_ERR "%s: failed to create /dev entry.\n",
-		       DRIVERLNAME);
-		return (0);
-	}
-
-	return (1);
-}
-
-/*
-** Driver Load
-*/
-static int __init divasi_init(void)
-{
-	char tmprev[50];
-	int ret = 0;
-
-	printk(KERN_INFO "%s\n", DRIVERNAME);
-	printk(KERN_INFO "%s: Rel:%s  Rev:", DRIVERLNAME, DRIVERRELEASE_IDI);
-	strcpy(tmprev, main_revision);
-	printk("%s  Build: %s\n", getrev(tmprev), DIVA_BUILD);
-
-	if (!divas_idi_register_chrdev()) {
-		ret = -EIO;
-		goto out;
-	}
-
-	if (!create_um_idi_proc()) {
-		divas_idi_unregister_chrdev();
-		printk(KERN_ERR "%s: failed to create proc entry.\n",
-		       DRIVERLNAME);
-		ret = -EIO;
-		goto out;
-	}
-
-	if (!(idifunc_init())) {
-		remove_um_idi_proc();
-		divas_idi_unregister_chrdev();
-		printk(KERN_ERR "%s: failed to connect to DIDD.\n",
-		       DRIVERLNAME);
-		ret = -EIO;
-		goto out;
-	}
-	printk(KERN_INFO "%s: started with major %d\n", DRIVERLNAME, major);
-
-out:
-	return (ret);
-}
-
-
-/*
-** Driver Unload
-*/
-static void __exit divasi_exit(void)
-{
-	idifunc_finit();
-	remove_um_idi_proc();
-	divas_idi_unregister_chrdev();
-
-	printk(KERN_INFO "%s: module unloaded.\n", DRIVERLNAME);
-}
-
-module_init(divasi_init);
-module_exit(divasi_exit);
-
-
-/*
- *  FILE OPERATIONS
- */
-
-static int
-divas_um_idi_copy_to_user(void *os_handle, void *dst, const void *src,
-			  int length)
-{
-	memcpy(dst, src, length);
-	return (length);
-}
-
-static ssize_t
-um_idi_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
-{
-	diva_um_idi_os_context_t *p_os;
-	int ret = -EINVAL;
-	void *data;
-
-	if (!file->private_data) {
-		return (-ENODEV);
-	}
-
-	if (!
-	    (p_os =
-	     (diva_um_idi_os_context_t *) diva_um_id_get_os_context(file->
-								    private_data)))
-	{
-		return (-ENODEV);
-	}
-	if (p_os->aborted) {
-		return (-ENODEV);
-	}
-
-	if (!(data = diva_os_malloc(0, count))) {
-		return (-ENOMEM);
-	}
-
-	ret = diva_um_idi_read(file->private_data,
-			       file, data, count,
-			       divas_um_idi_copy_to_user);
-	switch (ret) {
-	case 0:		/* no message available */
-		ret = (-EAGAIN);
-		break;
-	case (-1):		/* adapter was removed */
-		ret = (-ENODEV);
-		break;
-	case (-2):		/* message_length > length of user buffer */
-		ret = (-EFAULT);
-		break;
-	}
-
-	if (ret > 0) {
-		if (copy_to_user(buf, data, ret)) {
-			ret = (-EFAULT);
-		}
-	}
-
-	diva_os_free(0, data);
-	DBG_TRC(("read: ret %d", ret));
-	return (ret);
-}
-
-
-static int
-divas_um_idi_copy_from_user(void *os_handle, void *dst, const void *src,
-			    int length)
-{
-	memcpy(dst, src, length);
-	return (length);
-}
-
-static int um_idi_open_adapter(struct file *file, int adapter_nr)
-{
-	diva_um_idi_os_context_t *p_os;
-	void *e =
-		divas_um_idi_create_entity((dword) adapter_nr, (void *) file);
-
-	if (!(file->private_data = e)) {
-		return (0);
-	}
-	p_os = (diva_um_idi_os_context_t *) diva_um_id_get_os_context(e);
-	init_waitqueue_head(&p_os->read_wait);
-	init_waitqueue_head(&p_os->close_wait);
-	timer_setup(&p_os->diva_timer_id, diva_um_timer_function, 0);
-	p_os->aborted = 0;
-	p_os->adapter_nr = adapter_nr;
-	return (1);
-}
-
-static ssize_t
-um_idi_write(struct file *file, const char __user *buf, size_t count,
-	     loff_t *offset)
-{
-	diva_um_idi_os_context_t *p_os;
-	int ret = -EINVAL;
-	void *data;
-	int adapter_nr = 0;
-
-	if (!file->private_data) {
-		/* the first write() selects the adapter_nr */
-		if (count == sizeof(int)) {
-			if (copy_from_user
-			    ((void *) &adapter_nr, buf,
-			     count)) return (-EFAULT);
-			if (!(um_idi_open_adapter(file, adapter_nr)))
-				return (-ENODEV);
-			return (count);
-		} else
-			return (-ENODEV);
-	}
-
-	if (!(p_os =
-	      (diva_um_idi_os_context_t *) diva_um_id_get_os_context(file->
-								     private_data)))
-	{
-		return (-ENODEV);
-	}
-	if (p_os->aborted) {
-		return (-ENODEV);
-	}
-
-	if (!(data = diva_os_malloc(0, count))) {
-		return (-ENOMEM);
-	}
-
-	if (copy_from_user(data, buf, count)) {
-		ret = -EFAULT;
-	} else {
-		ret = diva_um_idi_write(file->private_data,
-					file, data, count,
-					divas_um_idi_copy_from_user);
-		switch (ret) {
-		case 0:	/* no space available */
-			ret = (-EAGAIN);
-			break;
-		case (-1):	/* adapter was removed */
-			ret = (-ENODEV);
-			break;
-		case (-2):	/* length of user buffer > max message_length */
-			ret = (-EFAULT);
-			break;
-		}
-	}
-	diva_os_free(0, data);
-	DBG_TRC(("write: ret %d", ret));
-	return (ret);
-}
-
-static __poll_t um_idi_poll(struct file *file, poll_table *wait)
-{
-	diva_um_idi_os_context_t *p_os;
-
-	if (!file->private_data) {
-		return (EPOLLERR);
-	}
-
-	if ((!(p_os =
-	       (diva_um_idi_os_context_t *)
-	       diva_um_id_get_os_context(file->private_data)))
-	    || p_os->aborted) {
-		return (EPOLLERR);
-	}
-
-	poll_wait(file, &p_os->read_wait, wait);
-
-	if (p_os->aborted) {
-		return (EPOLLERR);
-	}
-
-	switch (diva_user_mode_idi_ind_ready(file->private_data, file)) {
-	case (-1):
-		return (EPOLLERR);
-
-	case 0:
-		return (0);
-	}
-
-	return (EPOLLIN | EPOLLRDNORM);
-}
-
-static int um_idi_open(struct inode *inode, struct file *file)
-{
-	return (0);
-}
-
-
-static int um_idi_release(struct inode *inode, struct file *file)
-{
-	diva_um_idi_os_context_t *p_os;
-	unsigned int adapter_nr;
-	int ret = 0;
-
-	if (!(file->private_data)) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	if (!(p_os =
-	      (diva_um_idi_os_context_t *) diva_um_id_get_os_context(file->private_data))) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	adapter_nr = p_os->adapter_nr;
-
-	if ((ret = remove_entity(file->private_data))) {
-		goto out;
-	}
-
-	if (divas_um_idi_delete_entity
-	    ((int) adapter_nr, file->private_data)) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-out:
-	return (ret);
-}
-
-int diva_os_get_context_size(void)
-{
-	return (sizeof(diva_um_idi_os_context_t));
-}
-
-void diva_os_wakeup_read(void *os_context)
-{
-	diva_um_idi_os_context_t *p_os =
-		(diva_um_idi_os_context_t *) os_context;
-	wake_up_interruptible(&p_os->read_wait);
-}
-
-void diva_os_wakeup_close(void *os_context)
-{
-	diva_um_idi_os_context_t *p_os =
-		(diva_um_idi_os_context_t *) os_context;
-	wake_up_interruptible(&p_os->close_wait);
-}
-
-static
-void diva_um_timer_function(struct timer_list *t)
-{
-	diva_um_idi_os_context_t *p_os = from_timer(p_os, t, diva_timer_id);
-
-	p_os->aborted = 1;
-	wake_up_interruptible(&p_os->read_wait);
-	wake_up_interruptible(&p_os->close_wait);
-	DBG_ERR(("entity removal watchdog"))
-		}
-
-/*
-**  If application exits without entity removal this function will remove
-**  entity and block until removal is complete
-*/
-static int remove_entity(void *entity)
-{
-	struct task_struct *curtask = current;
-	diva_um_idi_os_context_t *p_os;
-
-	diva_um_idi_stop_wdog(entity);
-
-	if (!entity) {
-		DBG_FTL(("Zero entity on remove"))
-			return (0);
-	}
-
-	if (!(p_os =
-	      (diva_um_idi_os_context_t *)
-	      diva_um_id_get_os_context(entity))) {
-		DBG_FTL(("Zero entity os context on remove"))
-			return (0);
-	}
-
-	if (!divas_um_idi_entity_assigned(entity) || p_os->aborted) {
-		/*
-		  Entity is not assigned, also can be removed
-		*/
-		return (0);
-	}
-
-	DBG_TRC(("E(%08x) check remove", entity))
-
-		/*
-		  If adapter not answers on remove request inside of
-		  10 Sec, then adapter is dead
-		*/
-		diva_um_idi_start_wdog(entity);
-
-	{
-		DECLARE_WAITQUEUE(wait, curtask);
-
-		add_wait_queue(&p_os->close_wait, &wait);
-		for (;;) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			if (!divas_um_idi_entity_start_remove(entity)
-			    || p_os->aborted) {
-				break;
-			}
-			schedule();
-		}
-		set_current_state(TASK_RUNNING);
-		remove_wait_queue(&p_os->close_wait, &wait);
-	}
-
-	DBG_TRC(("E(%08x) start remove", entity))
-	{
-		DECLARE_WAITQUEUE(wait, curtask);
-
-		add_wait_queue(&p_os->close_wait, &wait);
-		for (;;) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			if (!divas_um_idi_entity_assigned(entity)
-			    || p_os->aborted) {
-				break;
-			}
-			schedule();
-		}
-		set_current_state(TASK_RUNNING);
-		remove_wait_queue(&p_os->close_wait, &wait);
-	}
-
-	DBG_TRC(("E(%08x) remove complete, aborted:%d", entity,
-		 p_os->aborted))
-
-		diva_um_idi_stop_wdog(entity);
-
-	p_os->aborted = 0;
-
-	return (0);
-}
-
-/*
- * timer watchdog
- */
-void diva_um_idi_start_wdog(void *entity)
-{
-	diva_um_idi_os_context_t *p_os;
-
-	if (entity &&
-	    ((p_os =
-	      (diva_um_idi_os_context_t *)
-	      diva_um_id_get_os_context(entity)))) {
-		mod_timer(&p_os->diva_timer_id, jiffies + 10 * HZ);
-	}
-}
-
-void diva_um_idi_stop_wdog(void *entity)
-{
-	diva_um_idi_os_context_t *p_os;
-
-	if (entity &&
-	    ((p_os =
-	      (diva_um_idi_os_context_t *)
-	      diva_um_id_get_os_context(entity)))) {
-		del_timer(&p_os->diva_timer_id);
-	}
-}
diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c
deleted file mode 100644
index b6a3950b2564..000000000000
--- a/drivers/isdn/hardware/eicon/divasmain.c
+++ /dev/null
@@ -1,848 +0,0 @@
-/* $Id: divasmain.c,v 1.55.4.6 2005/02/09 19:28:20 armin Exp $
- *
- * Low level driver for Eicon DIVA Server ISDN cards.
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/uaccess.h>
-#include <asm/io.h>
-#include <linux/ioport.h>
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include <linux/list.h>
-#include <linux/poll.h>
-#include <linux/kmod.h>
-
-#include "platform.h"
-#undef ID_MASK
-#undef N_DATA
-#include "pc.h"
-#include "di_defs.h"
-#include "divasync.h"
-#include "diva.h"
-#include "di.h"
-#include "io.h"
-#include "xdi_msg.h"
-#include "xdi_adapter.h"
-#include "xdi_vers.h"
-#include "diva_dma.h"
-#include "diva_pci.h"
-
-static char *main_revision = "$Revision: 1.55.4.6 $";
-
-static int major;
-
-static int dbgmask;
-
-MODULE_DESCRIPTION("Kernel driver for Eicon DIVA Server cards");
-MODULE_AUTHOR("Cytronics & Melware, Eicon Networks");
-MODULE_LICENSE("GPL");
-
-module_param(dbgmask, int, 0);
-MODULE_PARM_DESC(dbgmask, "initial debug mask");
-
-static char *DRIVERNAME =
-	"Eicon DIVA Server driver (http://www.melware.net)";
-static char *DRIVERLNAME = "divas";
-static char *DEVNAME = "Divas";
-char *DRIVERRELEASE_DIVAS = "2.0";
-
-extern irqreturn_t diva_os_irq_wrapper(int irq, void *context);
-extern int create_divas_proc(void);
-extern void remove_divas_proc(void);
-extern void diva_get_vserial_number(PISDN_ADAPTER IoAdapter, char *buf);
-extern int divasfunc_init(int dbgmask);
-extern void divasfunc_exit(void);
-
-typedef struct _diva_os_thread_dpc {
-	struct tasklet_struct divas_task;
-	diva_os_soft_isr_t *psoft_isr;
-} diva_os_thread_dpc_t;
-
-/* --------------------------------------------------------------------------
-   PCI driver interface section
-   -------------------------------------------------------------------------- */
-/*
-  vendor, device	Vendor and device ID to match (or PCI_ANY_ID)
-  subvendor,	Subsystem vendor and device ID to match (or PCI_ANY_ID)
-  subdevice
-  class,		Device class to match. The class_mask tells which bits
-  class_mask	of the class are honored during the comparison.
-  driver_data	Data private to the driver.
-*/
-
-#if !defined(PCI_DEVICE_ID_EICON_MAESTRAP_2)
-#define PCI_DEVICE_ID_EICON_MAESTRAP_2       0xE015
-#endif
-
-#if !defined(PCI_DEVICE_ID_EICON_4BRI_VOIP)
-#define PCI_DEVICE_ID_EICON_4BRI_VOIP        0xE016
-#endif
-
-#if !defined(PCI_DEVICE_ID_EICON_4BRI_2_VOIP)
-#define PCI_DEVICE_ID_EICON_4BRI_2_VOIP      0xE017
-#endif
-
-#if !defined(PCI_DEVICE_ID_EICON_BRI2M_2)
-#define PCI_DEVICE_ID_EICON_BRI2M_2          0xE018
-#endif
-
-#if !defined(PCI_DEVICE_ID_EICON_MAESTRAP_2_VOIP)
-#define PCI_DEVICE_ID_EICON_MAESTRAP_2_VOIP  0xE019
-#endif
-
-#if !defined(PCI_DEVICE_ID_EICON_2F)
-#define PCI_DEVICE_ID_EICON_2F               0xE01A
-#endif
-
-#if !defined(PCI_DEVICE_ID_EICON_BRI2M_2_VOIP)
-#define PCI_DEVICE_ID_EICON_BRI2M_2_VOIP     0xE01B
-#endif
-
-/*
-  This table should be sorted by PCI device ID
-*/
-static const struct pci_device_id divas_pci_tbl[] = {
-	/* Diva Server BRI-2M PCI 0xE010 */
-	{ PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_MAESTRA),
-	  CARDTYPE_MAESTRA_PCI },
-	/* Diva Server 4BRI-8M PCI 0xE012 */
-	{ PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_MAESTRAQ),
-	  CARDTYPE_DIVASRV_Q_8M_PCI },
-	/* Diva Server 4BRI-8M 2.0 PCI 0xE013 */
-	{ PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_MAESTRAQ_U),
-	  CARDTYPE_DIVASRV_Q_8M_V2_PCI },
-	/* Diva Server PRI-30M PCI 0xE014 */
-	{ PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_MAESTRAP),
-	  CARDTYPE_DIVASRV_P_30M_PCI },
-	/* Diva Server PRI 2.0 adapter 0xE015 */
-	{ PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_MAESTRAP_2),
-	  CARDTYPE_DIVASRV_P_30M_V2_PCI },
-	/* Diva Server Voice 4BRI-8M PCI 0xE016 */
-	{ PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_4BRI_VOIP),
-	  CARDTYPE_DIVASRV_VOICE_Q_8M_PCI },
-	/* Diva Server Voice 4BRI-8M 2.0 PCI 0xE017 */
-	{ PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_4BRI_2_VOIP),
-	  CARDTYPE_DIVASRV_VOICE_Q_8M_V2_PCI },
-	/* Diva Server BRI-2M 2.0 PCI 0xE018 */
-	{ PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_BRI2M_2),
-	  CARDTYPE_DIVASRV_B_2M_V2_PCI },
-	/* Diva Server Voice PRI 2.0 PCI 0xE019 */
-	{ PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_MAESTRAP_2_VOIP),
-	  CARDTYPE_DIVASRV_VOICE_P_30M_V2_PCI },
-	/* Diva Server 2FX 0xE01A */
-	{ PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_2F),
-	  CARDTYPE_DIVASRV_B_2F_PCI },
-	/* Diva Server Voice BRI-2M 2.0 PCI 0xE01B */
-	{ PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_BRI2M_2_VOIP),
-	  CARDTYPE_DIVASRV_VOICE_B_2M_V2_PCI },
-	{ 0, }			/* 0 terminated list. */
-};
-MODULE_DEVICE_TABLE(pci, divas_pci_tbl);
-
-static int divas_init_one(struct pci_dev *pdev,
-			  const struct pci_device_id *ent);
-static void divas_remove_one(struct pci_dev *pdev);
-
-static struct pci_driver diva_pci_driver = {
-	.name     = "divas",
-	.probe    = divas_init_one,
-	.remove   = divas_remove_one,
-	.id_table = divas_pci_tbl,
-};
-
-/*********************************************************
- ** little helper functions
- *********************************************************/
-static char *getrev(const char *revision)
-{
-	char *rev;
-	char *p;
-	if ((p = strchr(revision, ':'))) {
-		rev = p + 2;
-		p = strchr(rev, '$');
-		*--p = 0;
-	} else
-		rev = "1.0";
-	return rev;
-}
-
-void diva_log_info(unsigned char *format, ...)
-{
-	va_list args;
-	unsigned char line[160];
-
-	va_start(args, format);
-	vsnprintf(line, sizeof(line), format, args);
-	va_end(args);
-
-	printk(KERN_INFO "%s: %s\n", DRIVERLNAME, line);
-}
-
-void divas_get_version(char *p)
-{
-	char tmprev[32];
-
-	strcpy(tmprev, main_revision);
-	sprintf(p, "%s: %s(%s) %s(%s) major=%d\n", DRIVERLNAME, DRIVERRELEASE_DIVAS,
-		getrev(tmprev), diva_xdi_common_code_build, DIVA_BUILD, major);
-}
-
-/* --------------------------------------------------------------------------
-   PCI Bus services
-   -------------------------------------------------------------------------- */
-byte diva_os_get_pci_bus(void *pci_dev_handle)
-{
-	struct pci_dev *pdev = (struct pci_dev *) pci_dev_handle;
-	return ((byte) pdev->bus->number);
-}
-
-byte diva_os_get_pci_func(void *pci_dev_handle)
-{
-	struct pci_dev *pdev = (struct pci_dev *) pci_dev_handle;
-	return ((byte) pdev->devfn);
-}
-
-unsigned long divasa_get_pci_irq(unsigned char bus, unsigned char func,
-				 void *pci_dev_handle)
-{
-	unsigned char irq = 0;
-	struct pci_dev *dev = (struct pci_dev *) pci_dev_handle;
-
-	irq = dev->irq;
-
-	return ((unsigned long) irq);
-}
-
-unsigned long divasa_get_pci_bar(unsigned char bus, unsigned char func,
-				 int bar, void *pci_dev_handle)
-{
-	unsigned long ret = 0;
-	struct pci_dev *dev = (struct pci_dev *) pci_dev_handle;
-
-	if (bar < 6) {
-		ret = dev->resource[bar].start;
-	}
-
-	DBG_TRC(("GOT BAR[%d]=%08x", bar, ret));
-
-	{
-		unsigned long type = (ret & 0x00000001);
-		if (type & PCI_BASE_ADDRESS_SPACE_IO) {
-			DBG_TRC(("  I/O"));
-			ret &= PCI_BASE_ADDRESS_IO_MASK;
-		} else {
-			DBG_TRC(("  memory"));
-			ret &= PCI_BASE_ADDRESS_MEM_MASK;
-		}
-		DBG_TRC(("  final=%08x", ret));
-	}
-
-	return (ret);
-}
-
-void PCIwrite(byte bus, byte func, int offset, void *data, int length,
-	      void *pci_dev_handle)
-{
-	struct pci_dev *dev = (struct pci_dev *) pci_dev_handle;
-
-	switch (length) {
-	case 1:		/* byte */
-		pci_write_config_byte(dev, offset,
-				      *(unsigned char *) data);
-		break;
-	case 2:		/* word */
-		pci_write_config_word(dev, offset,
-				      *(unsigned short *) data);
-		break;
-	case 4:		/* dword */
-		pci_write_config_dword(dev, offset,
-				       *(unsigned int *) data);
-		break;
-
-	default:		/* buffer */
-		if (!(length % 4) && !(length & 0x03)) {	/* Copy as dword */
-			dword *p = (dword *) data;
-			length /= 4;
-
-			while (length--) {
-				pci_write_config_dword(dev, offset,
-						       *(unsigned int *)
-						       p++);
-			}
-		} else {	/* copy as byte stream */
-			byte *p = (byte *) data;
-
-			while (length--) {
-				pci_write_config_byte(dev, offset,
-						      *(unsigned char *)
-						      p++);
-			}
-		}
-	}
-}
-
-void PCIread(byte bus, byte func, int offset, void *data, int length,
-	     void *pci_dev_handle)
-{
-	struct pci_dev *dev = (struct pci_dev *) pci_dev_handle;
-
-	switch (length) {
-	case 1:		/* byte */
-		pci_read_config_byte(dev, offset, (unsigned char *) data);
-		break;
-	case 2:		/* word */
-		pci_read_config_word(dev, offset, (unsigned short *) data);
-		break;
-	case 4:		/* dword */
-		pci_read_config_dword(dev, offset, (unsigned int *) data);
-		break;
-
-	default:		/* buffer */
-		if (!(length % 4) && !(length & 0x03)) {	/* Copy as dword */
-			dword *p = (dword *) data;
-			length /= 4;
-
-			while (length--) {
-				pci_read_config_dword(dev, offset,
-						      (unsigned int *)
-						      p++);
-			}
-		} else {	/* copy as byte stream */
-			byte *p = (byte *) data;
-
-			while (length--) {
-				pci_read_config_byte(dev, offset,
-						     (unsigned char *)
-						     p++);
-			}
-		}
-	}
-}
-
-/*
-  Init map with DMA pages. It is not problem if some allocations fail -
-  the channels that will not get one DMA page will use standard PIO
-  interface
-*/
-static void *diva_pci_alloc_consistent(struct pci_dev *hwdev,
-				       size_t size,
-				       dma_addr_t *dma_handle,
-				       void **addr_handle)
-{
-	void *addr = pci_alloc_consistent(hwdev, size, dma_handle);
-
-	*addr_handle = addr;
-
-	return (addr);
-}
-
-void diva_init_dma_map(void *hdev,
-		       struct _diva_dma_map_entry **ppmap, int nentries)
-{
-	struct pci_dev *pdev = (struct pci_dev *) hdev;
-	struct _diva_dma_map_entry *pmap =
-		diva_alloc_dma_map(hdev, nentries);
-
-	if (pmap) {
-		int i;
-		dma_addr_t dma_handle;
-		void *cpu_addr;
-		void *addr_handle;
-
-		for (i = 0; i < nentries; i++) {
-			if (!(cpu_addr = diva_pci_alloc_consistent(pdev,
-								   PAGE_SIZE,
-								   &dma_handle,
-								   &addr_handle)))
-			{
-				break;
-			}
-			diva_init_dma_map_entry(pmap, i, cpu_addr,
-						(dword) dma_handle,
-						addr_handle);
-			DBG_TRC(("dma map alloc [%d]=(%08lx:%08x:%08lx)",
-				 i, (unsigned long) cpu_addr,
-				 (dword) dma_handle,
-				 (unsigned long) addr_handle))}
-	}
-
-	*ppmap = pmap;
-}
-
-/*
-  Free all contained in the map entries and memory used by the map
-  Should be always called after adapter removal from DIDD array
-*/
-void diva_free_dma_map(void *hdev, struct _diva_dma_map_entry *pmap)
-{
-	struct pci_dev *pdev = (struct pci_dev *) hdev;
-	int i;
-	dword phys_addr;
-	void *cpu_addr;
-	dma_addr_t dma_handle;
-	void *addr_handle;
-
-	for (i = 0; (pmap != NULL); i++) {
-		diva_get_dma_map_entry(pmap, i, &cpu_addr, &phys_addr);
-		if (!cpu_addr) {
-			break;
-		}
-		addr_handle = diva_get_entry_handle(pmap, i);
-		dma_handle = (dma_addr_t) phys_addr;
-		pci_free_consistent(pdev, PAGE_SIZE, addr_handle,
-				    dma_handle);
-		DBG_TRC(("dma map free [%d]=(%08lx:%08x:%08lx)", i,
-			 (unsigned long) cpu_addr, (dword) dma_handle,
-			 (unsigned long) addr_handle))
-			}
-
-	diva_free_dma_mapping(pmap);
-}
-
-
-/*********************************************************
- ** I/O port utilities
- *********************************************************/
-
-int
-diva_os_register_io_port(void *adapter, int on, unsigned long port,
-			 unsigned long length, const char *name, int id)
-{
-	if (on) {
-		if (!request_region(port, length, name)) {
-			DBG_ERR(("A: I/O: can't register port=%08x", port))
-				return (-1);
-		}
-	} else {
-		release_region(port, length);
-	}
-	return (0);
-}
-
-void __iomem *divasa_remap_pci_bar(diva_os_xdi_adapter_t *a, int id, unsigned long bar, unsigned long area_length)
-{
-	void __iomem *ret = ioremap(bar, area_length);
-	DBG_TRC(("remap(%08x)->%p", bar, ret));
-	return (ret);
-}
-
-void divasa_unmap_pci_bar(void __iomem *bar)
-{
-	if (bar) {
-		iounmap(bar);
-	}
-}
-
-/*********************************************************
- ** I/O port access
- *********************************************************/
-inline byte inpp(void __iomem *addr)
-{
-	return (inb((unsigned long) addr));
-}
-
-inline word inppw(void __iomem *addr)
-{
-	return (inw((unsigned long) addr));
-}
-
-inline void inppw_buffer(void __iomem *addr, void *P, int length)
-{
-	insw((unsigned long) addr, (word *) P, length >> 1);
-}
-
-inline void outppw_buffer(void __iomem *addr, void *P, int length)
-{
-	outsw((unsigned long) addr, (word *) P, length >> 1);
-}
-
-inline void outppw(void __iomem *addr, word w)
-{
-	outw(w, (unsigned long) addr);
-}
-
-inline void outpp(void __iomem *addr, word p)
-{
-	outb(p, (unsigned long) addr);
-}
-
-/* --------------------------------------------------------------------------
-   IRQ request / remove
-   -------------------------------------------------------------------------- */
-int diva_os_register_irq(void *context, byte irq, const char *name)
-{
-	int result = request_irq(irq, diva_os_irq_wrapper,
-				 IRQF_SHARED, name, context);
-	return (result);
-}
-
-void diva_os_remove_irq(void *context, byte irq)
-{
-	free_irq(irq, context);
-}
-
-/* --------------------------------------------------------------------------
-   DPC framework implementation
-   -------------------------------------------------------------------------- */
-static void diva_os_dpc_proc(unsigned long context)
-{
-	diva_os_thread_dpc_t *psoft_isr = (diva_os_thread_dpc_t *) context;
-	diva_os_soft_isr_t *pisr = psoft_isr->psoft_isr;
-
-	(*(pisr->callback)) (pisr, pisr->callback_context);
-}
-
-int diva_os_initialize_soft_isr(diva_os_soft_isr_t *psoft_isr,
-				diva_os_soft_isr_callback_t callback,
-				void *callback_context)
-{
-	diva_os_thread_dpc_t *pdpc;
-
-	pdpc = (diva_os_thread_dpc_t *) diva_os_malloc(0, sizeof(*pdpc));
-	if (!(psoft_isr->object = pdpc)) {
-		return (-1);
-	}
-	memset(pdpc, 0x00, sizeof(*pdpc));
-	psoft_isr->callback = callback;
-	psoft_isr->callback_context = callback_context;
-	pdpc->psoft_isr = psoft_isr;
-	tasklet_init(&pdpc->divas_task, diva_os_dpc_proc, (unsigned long)pdpc);
-
-	return (0);
-}
-
-int diva_os_schedule_soft_isr(diva_os_soft_isr_t *psoft_isr)
-{
-	if (psoft_isr && psoft_isr->object) {
-		diva_os_thread_dpc_t *pdpc =
-			(diva_os_thread_dpc_t *) psoft_isr->object;
-
-		tasklet_schedule(&pdpc->divas_task);
-	}
-
-	return (1);
-}
-
-int diva_os_cancel_soft_isr(diva_os_soft_isr_t *psoft_isr)
-{
-	return (0);
-}
-
-void diva_os_remove_soft_isr(diva_os_soft_isr_t *psoft_isr)
-{
-	if (psoft_isr && psoft_isr->object) {
-		diva_os_thread_dpc_t *pdpc =
-			(diva_os_thread_dpc_t *) psoft_isr->object;
-		void *mem;
-
-		tasklet_kill(&pdpc->divas_task);
-		mem = psoft_isr->object;
-		psoft_isr->object = NULL;
-		diva_os_free(0, mem);
-	}
-}
-
-/*
- * kernel/user space copy functions
- */
-static int
-xdi_copy_to_user(void *os_handle, void __user *dst, const void *src, int length)
-{
-	if (copy_to_user(dst, src, length)) {
-		return (-EFAULT);
-	}
-	return (length);
-}
-
-static int
-xdi_copy_from_user(void *os_handle, void *dst, const void __user *src, int length)
-{
-	if (copy_from_user(dst, src, length)) {
-		return (-EFAULT);
-	}
-	return (length);
-}
-
-/*
- * device node operations
- */
-static int divas_open(struct inode *inode, struct file *file)
-{
-	return (0);
-}
-
-static int divas_release(struct inode *inode, struct file *file)
-{
-	if (file->private_data) {
-		diva_xdi_close_adapter(file->private_data, file);
-	}
-	return (0);
-}
-
-static ssize_t divas_write(struct file *file, const char __user *buf,
-			   size_t count, loff_t *ppos)
-{
-	diva_xdi_um_cfg_cmd_t msg;
-	int ret = -EINVAL;
-
-	if (!file->private_data) {
-		file->private_data = diva_xdi_open_adapter(file, buf,
-							   count, &msg,
-							   xdi_copy_from_user);
-		if (!file->private_data)
-			return (-ENODEV);
-		ret = diva_xdi_write(file->private_data, file,
-				     buf, count, &msg, xdi_copy_from_user);
-	} else {
-		ret = diva_xdi_write(file->private_data, file,
-				     buf, count, NULL, xdi_copy_from_user);
-	}
-
-	switch (ret) {
-	case -1:		/* Message should be removed from rx mailbox first */
-		ret = -EBUSY;
-		break;
-	case -2:		/* invalid adapter was specified in this call */
-		ret = -ENOMEM;
-		break;
-	case -3:
-		ret = -ENXIO;
-		break;
-	}
-	DBG_TRC(("write: ret %d", ret));
-	return (ret);
-}
-
-static ssize_t divas_read(struct file *file, char __user *buf,
-			  size_t count, loff_t *ppos)
-{
-	diva_xdi_um_cfg_cmd_t msg;
-	int ret = -EINVAL;
-
-	if (!file->private_data) {
-		file->private_data = diva_xdi_open_adapter(file, buf,
-							   count, &msg,
-							   xdi_copy_from_user);
-	}
-	if (!file->private_data) {
-		return (-ENODEV);
-	}
-
-	ret = diva_xdi_read(file->private_data, file,
-			    buf, count, xdi_copy_to_user);
-	switch (ret) {
-	case -1:		/* RX mailbox is empty */
-		ret = -EAGAIN;
-		break;
-	case -2:		/* no memory, mailbox was cleared, last command is failed */
-		ret = -ENOMEM;
-		break;
-	case -3:		/* can't copy to user, retry */
-		ret = -EFAULT;
-		break;
-	}
-	DBG_TRC(("read: ret %d", ret));
-	return (ret);
-}
-
-static __poll_t divas_poll(struct file *file, poll_table *wait)
-{
-	if (!file->private_data) {
-		return (EPOLLERR);
-	}
-	return (EPOLLIN | EPOLLRDNORM);
-}
-
-static const struct file_operations divas_fops = {
-	.owner   = THIS_MODULE,
-	.llseek  = no_llseek,
-	.read    = divas_read,
-	.write   = divas_write,
-	.poll    = divas_poll,
-	.open    = divas_open,
-	.release = divas_release
-};
-
-static void divas_unregister_chrdev(void)
-{
-	unregister_chrdev(major, DEVNAME);
-}
-
-static int __init divas_register_chrdev(void)
-{
-	if ((major = register_chrdev(0, DEVNAME, &divas_fops)) < 0)
-	{
-		printk(KERN_ERR "%s: failed to create /dev entry.\n",
-		       DRIVERLNAME);
-		return (0);
-	}
-
-	return (1);
-}
-
-/* --------------------------------------------------------------------------
-   PCI driver section
-   -------------------------------------------------------------------------- */
-static int divas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
-{
-	void *pdiva = NULL;
-	u8 pci_latency;
-	u8 new_latency = 32;
-
-	DBG_TRC(("%s bus: %08x fn: %08x insertion.\n",
-		 CardProperties[ent->driver_data].Name,
-		 pdev->bus->number, pdev->devfn))
-		printk(KERN_INFO "%s: %s bus: %08x fn: %08x insertion.\n",
-		       DRIVERLNAME, CardProperties[ent->driver_data].Name,
-		       pdev->bus->number, pdev->devfn);
-
-	if (pci_enable_device(pdev)) {
-		DBG_TRC(("%s: %s bus: %08x fn: %08x device init failed.\n",
-			 DRIVERLNAME,
-			 CardProperties[ent->driver_data].Name,
-			 pdev->bus->number,
-			 pdev->devfn))
-			printk(KERN_ERR
-			       "%s: %s bus: %08x fn: %08x device init failed.\n",
-			       DRIVERLNAME,
-			       CardProperties[ent->driver_data].
-			       Name, pdev->bus->number,
-			       pdev->devfn);
-		return (-EIO);
-	}
-
-	pci_set_master(pdev);
-
-	pci_read_config_byte(pdev, PCI_LATENCY_TIMER, &pci_latency);
-	if (!pci_latency) {
-		DBG_TRC(("%s: bus: %08x fn: %08x fix latency.\n",
-			 DRIVERLNAME, pdev->bus->number, pdev->devfn))
-			printk(KERN_INFO
-			       "%s: bus: %08x fn: %08x fix latency.\n",
-			       DRIVERLNAME, pdev->bus->number, pdev->devfn);
-		pci_write_config_byte(pdev, PCI_LATENCY_TIMER, new_latency);
-	}
-
-	if (!(pdiva = diva_driver_add_card(pdev, ent->driver_data))) {
-		DBG_TRC(("%s: %s bus: %08x fn: %08x card init failed.\n",
-			 DRIVERLNAME,
-			 CardProperties[ent->driver_data].Name,
-			 pdev->bus->number,
-			 pdev->devfn))
-			printk(KERN_ERR
-			       "%s: %s bus: %08x fn: %08x card init failed.\n",
-			       DRIVERLNAME,
-			       CardProperties[ent->driver_data].
-			       Name, pdev->bus->number,
-			       pdev->devfn);
-		return (-EIO);
-	}
-
-	pci_set_drvdata(pdev, pdiva);
-
-	return (0);
-}
-
-static void divas_remove_one(struct pci_dev *pdev)
-{
-	void *pdiva = pci_get_drvdata(pdev);
-
-	DBG_TRC(("bus: %08x fn: %08x removal.\n",
-		 pdev->bus->number, pdev->devfn))
-		printk(KERN_INFO "%s: bus: %08x fn: %08x removal.\n",
-		       DRIVERLNAME, pdev->bus->number, pdev->devfn);
-
-	if (pdiva) {
-		diva_driver_remove_card(pdiva);
-	}
-
-}
-
-/* --------------------------------------------------------------------------
-   Driver Load / Startup
-   -------------------------------------------------------------------------- */
-static int __init divas_init(void)
-{
-	char tmprev[50];
-	int ret = 0;
-
-	printk(KERN_INFO "%s\n", DRIVERNAME);
-	printk(KERN_INFO "%s: Rel:%s  Rev:", DRIVERLNAME, DRIVERRELEASE_DIVAS);
-	strcpy(tmprev, main_revision);
-	printk("%s  Build: %s(%s)\n", getrev(tmprev),
-	       diva_xdi_common_code_build, DIVA_BUILD);
-	printk(KERN_INFO "%s: support for: ", DRIVERLNAME);
-#ifdef CONFIG_ISDN_DIVAS_BRIPCI
-	printk("BRI/PCI ");
-#endif
-#ifdef CONFIG_ISDN_DIVAS_PRIPCI
-	printk("PRI/PCI ");
-#endif
-	printk("adapters\n");
-
-	if (!divasfunc_init(dbgmask)) {
-		printk(KERN_ERR "%s: failed to connect to DIDD.\n",
-		       DRIVERLNAME);
-		ret = -EIO;
-		goto out;
-	}
-
-	if (!divas_register_chrdev()) {
-#ifdef MODULE
-		divasfunc_exit();
-#endif
-		ret = -EIO;
-		goto out;
-	}
-
-	if (!create_divas_proc()) {
-#ifdef MODULE
-		divas_unregister_chrdev();
-		divasfunc_exit();
-#endif
-		printk(KERN_ERR "%s: failed to create proc entry.\n",
-		       DRIVERLNAME);
-		ret = -EIO;
-		goto out;
-	}
-
-	if ((ret = pci_register_driver(&diva_pci_driver))) {
-#ifdef MODULE
-		remove_divas_proc();
-		divas_unregister_chrdev();
-		divasfunc_exit();
-#endif
-		printk(KERN_ERR "%s: failed to init pci driver.\n",
-		       DRIVERLNAME);
-		goto out;
-	}
-	printk(KERN_INFO "%s: started with major %d\n", DRIVERLNAME, major);
-
-out:
-	return (ret);
-}
-
-/* --------------------------------------------------------------------------
-   Driver Unload
-   -------------------------------------------------------------------------- */
-static void __exit divas_exit(void)
-{
-	pci_unregister_driver(&diva_pci_driver);
-	remove_divas_proc();
-	divas_unregister_chrdev();
-	divasfunc_exit();
-
-	printk(KERN_INFO "%s: module unloaded.\n", DRIVERLNAME);
-}
-
-module_init(divas_init);
-module_exit(divas_exit);
diff --git a/drivers/isdn/hardware/eicon/divasproc.c b/drivers/isdn/hardware/eicon/divasproc.c
deleted file mode 100644
index f52f4622b10b..000000000000
--- a/drivers/isdn/hardware/eicon/divasproc.c
+++ /dev/null
@@ -1,412 +0,0 @@
-/* $Id: divasproc.c,v 1.19.4.3 2005/01/31 12:22:20 armin Exp $
- *
- * Low level driver for Eicon DIVA Server ISDN cards.
- * /proc functions
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/poll.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/list.h>
-#include <linux/uaccess.h>
-
-#include "platform.h"
-#include "debuglib.h"
-#undef ID_MASK
-#undef N_DATA
-#include "pc.h"
-#include "di_defs.h"
-#include "divasync.h"
-#include "di.h"
-#include "io.h"
-#include "xdi_msg.h"
-#include "xdi_adapter.h"
-#include "diva.h"
-#include "diva_pci.h"
-
-
-extern PISDN_ADAPTER IoAdapters[MAX_ADAPTER];
-extern void divas_get_version(char *);
-extern void diva_get_vserial_number(PISDN_ADAPTER IoAdapter, char *buf);
-
-/*********************************************************
- ** Functions for /proc interface / File operations
- *********************************************************/
-
-static char *divas_proc_name = "divas";
-static char *adapter_dir_name = "adapter";
-static char *info_proc_name = "info";
-static char *grp_opt_proc_name = "group_optimization";
-static char *d_l1_down_proc_name = "dynamic_l1_down";
-
-/*
-** "divas" entry
-*/
-
-extern struct proc_dir_entry *proc_net_eicon;
-static struct proc_dir_entry *divas_proc_entry = NULL;
-
-static ssize_t
-divas_read(struct file *file, char __user *buf, size_t count, loff_t *off)
-{
-	int len = 0;
-	int cadapter;
-	char tmpbuf[80];
-	char tmpser[16];
-
-	if (*off)
-		return 0;
-
-	divas_get_version(tmpbuf);
-	if (copy_to_user(buf + len, &tmpbuf, strlen(tmpbuf)))
-		return -EFAULT;
-	len += strlen(tmpbuf);
-
-	for (cadapter = 0; cadapter < MAX_ADAPTER; cadapter++) {
-		if (IoAdapters[cadapter]) {
-			diva_get_vserial_number(IoAdapters[cadapter],
-						tmpser);
-			sprintf(tmpbuf,
-				"%2d: %-30s Serial:%-10s IRQ:%2d\n",
-				cadapter + 1,
-				IoAdapters[cadapter]->Properties.Name,
-				tmpser,
-				IoAdapters[cadapter]->irq_info.irq_nr);
-			if ((strlen(tmpbuf) + len) > count)
-				break;
-			if (copy_to_user
-			    (buf + len, &tmpbuf,
-			     strlen(tmpbuf))) return -EFAULT;
-			len += strlen(tmpbuf);
-		}
-	}
-
-	*off += len;
-	return (len);
-}
-
-static ssize_t
-divas_write(struct file *file, const char __user *buf, size_t count, loff_t *off)
-{
-	return (-ENODEV);
-}
-
-static __poll_t divas_poll(struct file *file, poll_table *wait)
-{
-	return (EPOLLERR);
-}
-
-static int divas_open(struct inode *inode, struct file *file)
-{
-	return nonseekable_open(inode, file);
-}
-
-static int divas_close(struct inode *inode, struct file *file)
-{
-	return (0);
-}
-
-static const struct file_operations divas_fops = {
-	.owner   = THIS_MODULE,
-	.llseek  = no_llseek,
-	.read    = divas_read,
-	.write   = divas_write,
-	.poll    = divas_poll,
-	.open    = divas_open,
-	.release = divas_close
-};
-
-int create_divas_proc(void)
-{
-	divas_proc_entry = proc_create(divas_proc_name, S_IFREG | S_IRUGO,
-				       proc_net_eicon, &divas_fops);
-	if (!divas_proc_entry)
-		return (0);
-
-	return (1);
-}
-
-void remove_divas_proc(void)
-{
-	if (divas_proc_entry) {
-		remove_proc_entry(divas_proc_name, proc_net_eicon);
-		divas_proc_entry = NULL;
-	}
-}
-
-static ssize_t grp_opt_proc_write(struct file *file, const char __user *buffer,
-				  size_t count, loff_t *pos)
-{
-	diva_os_xdi_adapter_t *a = PDE_DATA(file_inode(file));
-	PISDN_ADAPTER IoAdapter = IoAdapters[a->controller - 1];
-
-	if ((count == 1) || (count == 2)) {
-		char c;
-		if (get_user(c, buffer))
-			return -EFAULT;
-		switch (c) {
-		case '0':
-			IoAdapter->capi_cfg.cfg_1 &=
-				~DIVA_XDI_CAPI_CFG_1_GROUP_POPTIMIZATION_ON;
-			break;
-		case '1':
-			IoAdapter->capi_cfg.cfg_1 |=
-				DIVA_XDI_CAPI_CFG_1_GROUP_POPTIMIZATION_ON;
-			break;
-		default:
-			return (-EINVAL);
-		}
-		return (count);
-	}
-	return (-EINVAL);
-}
-
-static ssize_t d_l1_down_proc_write(struct file *file, const char __user *buffer,
-				    size_t count, loff_t *pos)
-{
-	diva_os_xdi_adapter_t *a = PDE_DATA(file_inode(file));
-	PISDN_ADAPTER IoAdapter = IoAdapters[a->controller - 1];
-
-	if ((count == 1) || (count == 2)) {
-		char c;
-		if (get_user(c, buffer))
-			return -EFAULT;
-		switch (c) {
-		case '0':
-			IoAdapter->capi_cfg.cfg_1 &=
-				~DIVA_XDI_CAPI_CFG_1_DYNAMIC_L1_ON;
-			break;
-		case '1':
-			IoAdapter->capi_cfg.cfg_1 |=
-				DIVA_XDI_CAPI_CFG_1_DYNAMIC_L1_ON;
-			break;
-		default:
-			return (-EINVAL);
-		}
-		return (count);
-	}
-	return (-EINVAL);
-}
-
-static int d_l1_down_proc_show(struct seq_file *m, void *v)
-{
-	diva_os_xdi_adapter_t *a = m->private;
-	PISDN_ADAPTER IoAdapter = IoAdapters[a->controller - 1];
-
-	seq_printf(m, "%s\n",
-		   (IoAdapter->capi_cfg.
-		    cfg_1 & DIVA_XDI_CAPI_CFG_1_DYNAMIC_L1_ON) ? "1" :
-		   "0");
-	return 0;
-}
-
-static int d_l1_down_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, d_l1_down_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations d_l1_down_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= d_l1_down_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= d_l1_down_proc_write,
-};
-
-static int grp_opt_proc_show(struct seq_file *m, void *v)
-{
-	diva_os_xdi_adapter_t *a = m->private;
-	PISDN_ADAPTER IoAdapter = IoAdapters[a->controller - 1];
-
-	seq_printf(m, "%s\n",
-		   (IoAdapter->capi_cfg.
-		    cfg_1 & DIVA_XDI_CAPI_CFG_1_GROUP_POPTIMIZATION_ON)
-		   ? "1" : "0");
-	return 0;
-}
-
-static int grp_opt_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, grp_opt_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations grp_opt_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= grp_opt_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= grp_opt_proc_write,
-};
-
-static ssize_t info_proc_write(struct file *file, const char __user *buffer,
-			       size_t count, loff_t *pos)
-{
-	diva_os_xdi_adapter_t *a = PDE_DATA(file_inode(file));
-	PISDN_ADAPTER IoAdapter = IoAdapters[a->controller - 1];
-	char c[4];
-
-	if (count <= 4)
-		return -EINVAL;
-
-	if (copy_from_user(c, buffer, 4))
-		return -EFAULT;
-
-	/* this is for test purposes only */
-	if (!memcmp(c, "trap", 4)) {
-		(*(IoAdapter->os_trap_nfy_Fnc)) (IoAdapter, IoAdapter->ANum);
-		return (count);
-	}
-	return (-EINVAL);
-}
-
-static int info_proc_show(struct seq_file *m, void *v)
-{
-	int i = 0;
-	char *p;
-	char tmpser[16];
-	diva_os_xdi_adapter_t *a = m->private;
-	PISDN_ADAPTER IoAdapter = IoAdapters[a->controller - 1];
-
-	seq_printf(m, "Name        : %s\n", IoAdapter->Properties.Name);
-	seq_printf(m, "DSP state   : %08x\n", a->dsp_mask);
-	seq_printf(m, "Channels    : %02d\n", IoAdapter->Properties.Channels);
-	seq_printf(m, "E. max/used : %03d/%03d\n",
-		   IoAdapter->e_max, IoAdapter->e_count);
-	diva_get_vserial_number(IoAdapter, tmpser);
-	seq_printf(m, "Serial      : %s\n", tmpser);
-	seq_printf(m, "IRQ         : %d\n", IoAdapter->irq_info.irq_nr);
-	seq_printf(m, "CardIndex   : %d\n", a->CardIndex);
-	seq_printf(m, "CardOrdinal : %d\n", a->CardOrdinal);
-	seq_printf(m, "Controller  : %d\n", a->controller);
-	seq_printf(m, "Bus-Type    : %s\n",
-		   (a->Bus ==
-		    DIVAS_XDI_ADAPTER_BUS_ISA) ? "ISA" : "PCI");
-	seq_printf(m, "Port-Name   : %s\n", a->port_name);
-	if (a->Bus == DIVAS_XDI_ADAPTER_BUS_PCI) {
-		seq_printf(m, "PCI-bus     : %d\n", a->resources.pci.bus);
-		seq_printf(m, "PCI-func    : %d\n", a->resources.pci.func);
-		for (i = 0; i < 8; i++) {
-			if (a->resources.pci.bar[i]) {
-				seq_printf(m,
-					   "Mem / I/O %d : 0x%x / mapped : 0x%lx",
-					   i, a->resources.pci.bar[i],
-					   (unsigned long) a->resources.
-					   pci.addr[i]);
-				if (a->resources.pci.length[i]) {
-					seq_printf(m,
-						   " / length : %d",
-						   a->resources.pci.
-						   length[i]);
-				}
-				seq_putc(m, '\n');
-			}
-		}
-	}
-	if ((!a->xdi_adapter.port) &&
-	    ((!a->xdi_adapter.ram) ||
-	     (!a->xdi_adapter.reset)
-	     || (!a->xdi_adapter.cfg))) {
-		if (!IoAdapter->irq_info.irq_nr) {
-			p = "slave";
-		} else {
-			p = "out of service";
-		}
-	} else if (a->xdi_adapter.trapped) {
-		p = "trapped";
-	} else if (a->xdi_adapter.Initialized) {
-		p = "active";
-	} else {
-		p = "ready";
-	}
-	seq_printf(m, "State       : %s\n", p);
-
-	return 0;
-}
-
-static int info_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, info_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations info_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= info_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= info_proc_write,
-};
-
-/*
-** adapter proc init/de-init
-*/
-
-/* --------------------------------------------------------------------------
-   Create adapter directory and files in proc file system
-   -------------------------------------------------------------------------- */
-int create_adapter_proc(diva_os_xdi_adapter_t *a)
-{
-	struct proc_dir_entry *de, *pe;
-	char tmp[16];
-
-	sprintf(tmp, "%s%d", adapter_dir_name, a->controller);
-	if (!(de = proc_mkdir(tmp, proc_net_eicon)))
-		return (0);
-	a->proc_adapter_dir = (void *) de;
-
-	pe = proc_create_data(info_proc_name, S_IRUGO | S_IWUSR, de,
-			      &info_proc_fops, a);
-	if (!pe)
-		return (0);
-	a->proc_info = (void *) pe;
-
-	pe = proc_create_data(grp_opt_proc_name, S_IRUGO | S_IWUSR, de,
-			      &grp_opt_proc_fops, a);
-	if (pe)
-		a->proc_grp_opt = (void *) pe;
-	pe = proc_create_data(d_l1_down_proc_name, S_IRUGO | S_IWUSR, de,
-			      &d_l1_down_proc_fops, a);
-	if (pe)
-		a->proc_d_l1_down = (void *) pe;
-
-	DBG_TRC(("proc entry %s created", tmp));
-
-	return (1);
-}
-
-/* --------------------------------------------------------------------------
-   Remove adapter directory and files in proc file system
-   -------------------------------------------------------------------------- */
-void remove_adapter_proc(diva_os_xdi_adapter_t *a)
-{
-	char tmp[16];
-
-	if (a->proc_adapter_dir) {
-		if (a->proc_d_l1_down) {
-			remove_proc_entry(d_l1_down_proc_name,
-					  (struct proc_dir_entry *) a->proc_adapter_dir);
-		}
-		if (a->proc_grp_opt) {
-			remove_proc_entry(grp_opt_proc_name,
-					  (struct proc_dir_entry *) a->proc_adapter_dir);
-		}
-		if (a->proc_info) {
-			remove_proc_entry(info_proc_name,
-					  (struct proc_dir_entry *) a->proc_adapter_dir);
-		}
-		sprintf(tmp, "%s%d", adapter_dir_name, a->controller);
-		remove_proc_entry(tmp, proc_net_eicon);
-		DBG_TRC(("proc entry %s%d removed", adapter_dir_name,
-			 a->controller));
-	}
-}
diff --git a/drivers/isdn/hardware/eicon/divasync.h b/drivers/isdn/hardware/eicon/divasync.h
deleted file mode 100644
index dd6b53a2c2c8..000000000000
--- a/drivers/isdn/hardware/eicon/divasync.h
+++ /dev/null
@@ -1,489 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_SYNC__H
-#define __DIVA_SYNC__H
-#define IDI_SYNC_REQ_REMOVE             0x00
-#define IDI_SYNC_REQ_GET_NAME           0x01
-#define IDI_SYNC_REQ_GET_SERIAL         0x02
-#define IDI_SYNC_REQ_SET_POSTCALL       0x03
-#define IDI_SYNC_REQ_GET_XLOG           0x04
-#define IDI_SYNC_REQ_GET_FEATURES       0x05
-#define IDI_SYNC_REQ_USB_REGISTER       0x06
-#define IDI_SYNC_REQ_USB_RELEASE        0x07
-#define IDI_SYNC_REQ_USB_ADD_DEVICE     0x08
-#define IDI_SYNC_REQ_USB_START_DEVICE   0x09
-#define IDI_SYNC_REQ_USB_STOP_DEVICE    0x0A
-#define IDI_SYNC_REQ_USB_REMOVE_DEVICE  0x0B
-#define IDI_SYNC_REQ_GET_CARDTYPE       0x0C
-#define IDI_SYNC_REQ_GET_DBG_XLOG       0x0D
-#define DIVA_USB
-#define DIVA_USB_REQ                    0xAC
-#define DIVA_USB_TEST                   0xAB
-#define DIVA_USB_ADD_ADAPTER            0xAC
-#define DIVA_USB_REMOVE_ADAPTER         0xAD
-#define IDI_SYNC_REQ_SERIAL_HOOK        0x80
-#define IDI_SYNC_REQ_XCHANGE_STATUS     0x81
-#define IDI_SYNC_REQ_USB_HOOK           0x82
-#define IDI_SYNC_REQ_PORTDRV_HOOK       0x83
-#define IDI_SYNC_REQ_SLI                0x84   /*  SLI request from 3signal modem drivers */
-#define IDI_SYNC_REQ_RECONFIGURE        0x85
-#define IDI_SYNC_REQ_RESET              0x86
-#define IDI_SYNC_REQ_GET_85X_DEVICE_DATA     0x87
-#define IDI_SYNC_REQ_LOCK_85X                   0x88
-#define IDI_SYNC_REQ_DIVA_85X_USB_DATA_EXCHANGE 0x99
-#define IDI_SYNC_REQ_DIPORT_EXCHANGE_REQ   0x98
-#define IDI_SYNC_REQ_GET_85X_EXT_PORT_TYPE      0xA0
-/******************************************************************************/
-#define IDI_SYNC_REQ_XDI_GET_EXTENDED_FEATURES  0x92
-/*
-  To receive XDI features:
-  1. set 'buffer_length_in_bytes' to length of you buffer
-  2. set 'features' to pointer to your buffer
-  3. issue synchronous request to XDI
-  4. Check that feature 'DIVA_XDI_EXTENDED_FEATURES_VALID' is present
-  after call. This feature does indicate that your request
-  was processed and XDI does support this synchronous request
-  5. if on return bit 31 (0x80000000) in 'buffer_length_in_bytes' is
-  set then provided buffer was too small, and bits 30-0 does
-  contain necessary length of buffer.
-  in this case only features that do find place in the buffer
-  are indicated to caller
-*/
-typedef struct _diva_xdi_get_extended_xdi_features {
-	dword buffer_length_in_bytes;
-	byte  *features;
-} diva_xdi_get_extended_xdi_features_t;
-/*
-  features[0]
-*/
-#define DIVA_XDI_EXTENDED_FEATURES_VALID          0x01
-#define DIVA_XDI_EXTENDED_FEATURE_CMA             0x02
-#define DIVA_XDI_EXTENDED_FEATURE_SDRAM_BAR       0x04
-#define DIVA_XDI_EXTENDED_FEATURE_CAPI_PRMS       0x08
-#define DIVA_XDI_EXTENDED_FEATURE_NO_CANCEL_RC    0x10
-#define DIVA_XDI_EXTENDED_FEATURE_RX_DMA          0x20
-#define DIVA_XDI_EXTENDED_FEATURE_MANAGEMENT_DMA  0x40
-#define DIVA_XDI_EXTENDED_FEATURE_WIDE_ID         0x80
-#define DIVA_XDI_EXTENDED_FEATURES_MAX_SZ    1
-/******************************************************************************/
-#define IDI_SYNC_REQ_XDI_GET_ADAPTER_SDRAM_BAR   0x93
-typedef struct _diva_xdi_get_adapter_sdram_bar {
-	dword bar;
-} diva_xdi_get_adapter_sdram_bar_t;
-/******************************************************************************/
-#define IDI_SYNC_REQ_XDI_GET_CAPI_PARAMS   0x94
-/*
-  CAPI Parameters will be written in the caller's buffer
-*/
-typedef struct _diva_xdi_get_capi_parameters {
-	dword structure_length;
-	byte flag_dynamic_l1_down;
-	byte group_optimization_enabled;
-} diva_xdi_get_capi_parameters_t;
-/******************************************************************************/
-#define IDI_SYNC_REQ_XDI_GET_LOGICAL_ADAPTER_NUMBER   0x95
-/*
-  Get logical adapter number, as assigned by XDI
-  'controller' is starting with zero 'sub' controller number
-  in case of one adapter that supports multiple interfaces
-  'controller' is zero for Master adapter (and adapter that supports
-  only one interface)
-*/
-typedef struct _diva_xdi_get_logical_adapter_number {
-	dword logical_adapter_number;
-	dword controller;
-	dword total_controllers;
-} diva_xdi_get_logical_adapter_number_s_t;
-/******************************************************************************/
-#define IDI_SYNC_REQ_UP1DM_OPERATION   0x96
-/******************************************************************************/
-#define IDI_SYNC_REQ_DMA_DESCRIPTOR_OPERATION 0x97
-#define IDI_SYNC_REQ_DMA_DESCRIPTOR_ALLOC     0x01
-#define IDI_SYNC_REQ_DMA_DESCRIPTOR_FREE      0x02
-typedef struct _diva_xdi_dma_descriptor_operation {
-	int operation;
-	int descriptor_number;
-	void *descriptor_address;
-	dword descriptor_magic;
-} diva_xdi_dma_descriptor_operation_t;
-/******************************************************************************/
-#define IDI_SYNC_REQ_DIDD_REGISTER_ADAPTER_NOTIFY   0x01
-#define IDI_SYNC_REQ_DIDD_REMOVE_ADAPTER_NOTIFY     0x02
-#define IDI_SYNC_REQ_DIDD_ADD_ADAPTER               0x03
-#define IDI_SYNC_REQ_DIDD_REMOVE_ADAPTER            0x04
-#define IDI_SYNC_REQ_DIDD_READ_ADAPTER_ARRAY        0x05
-#define IDI_SYNC_REQ_DIDD_GET_CFG_LIB_IFC           0x10
-typedef struct _diva_didd_adapter_notify {
-	dword handle; /* Notification handle */
-	void *callback;
-	void *context;
-} diva_didd_adapter_notify_t;
-typedef struct _diva_didd_add_adapter {
-	void *descriptor;
-} diva_didd_add_adapter_t;
-typedef struct _diva_didd_remove_adapter {
-	IDI_CALL p_request;
-} diva_didd_remove_adapter_t;
-typedef struct _diva_didd_read_adapter_array {
-	void *buffer;
-	dword length;
-} diva_didd_read_adapter_array_t;
-typedef struct _diva_didd_get_cfg_lib_ifc {
-	void *ifc;
-} diva_didd_get_cfg_lib_ifc_t;
-/******************************************************************************/
-#define IDI_SYNC_REQ_XDI_GET_STREAM    0x91
-#define DIVA_XDI_SYNCHRONOUS_SERVICE   0x01
-#define DIVA_XDI_DMA_SERVICE           0x02
-#define DIVA_XDI_AUTO_SERVICE          0x03
-#define DIVA_ISTREAM_COMPLETE_NOTIFY   0
-#define DIVA_ISTREAM_COMPLETE_READ     1
-#define DIVA_ISTREAM_COMPLETE_WRITE    2
-typedef struct _diva_xdi_stream_interface {
-	unsigned char  Id;                 /* filled by XDI client */
-	unsigned char provided_service;    /* filled by XDI        */
-	unsigned char requested_service;   /* filled by XDI Client */
-	void *xdi_context;    /* filled by XDI */
-	void *client_context;   /* filled by XDI client */
-	int (*write)(void *context,
-		     int Id,
-		     void *data,
-		     int length,
-		     int final,
-		     byte usr1,
-		     byte usr2);
-	int (*read)(void *context,
-		    int Id,
-		    void *data,
-		    int max_length,
-		    int *final,
-		    byte *usr1,
-		    byte *usr2);
-	int (*complete)(void *client_context,
-			int Id,
-			int what,
-			void *data,
-			int length,
-			int *final);
-} diva_xdi_stream_interface_t;
-/******************************************************************************/
-/*
- * IDI_SYNC_REQ_SERIAL_HOOK - special interface for the DIVA Mobile card
- */
-typedef struct
-{ unsigned char LineState;         /* Modem line state (STATUS_R) */
-#define SERIAL_GSM_CELL 0x01   /* GSM or CELL cable attached  */
-	unsigned char CardState;          /* PCMCIA card state (0 = down) */
-	unsigned char IsdnState;          /* ISDN layer 1 state (0 = down)*/
-	unsigned char HookState;          /* current logical hook state */
-#define SERIAL_ON_HOOK 0x02   /* set in DIVA CTRL_R register */
-} SERIAL_STATE;
-typedef int (*SERIAL_INT_CB)(void *Context);
-typedef int (*SERIAL_DPC_CB)(void *Context);
-typedef unsigned char (*SERIAL_I_SYNC)(void *Context);
-typedef struct
-{ /* 'Req' and 'Rc' must be at the same place as in the ENTITY struct */
-	unsigned char Req;             /* request (must be always 0) */
-	unsigned char Rc;              /* return code (is the request) */
-	unsigned char Function;           /* private function code  */
-#define SERIAL_HOOK_ATTACH 0x81
-#define SERIAL_HOOK_STATUS 0x82
-#define SERIAL_HOOK_I_SYNC 0x83
-#define SERIAL_HOOK_NOECHO 0x84
-#define SERIAL_HOOK_RING 0x85
-#define SERIAL_HOOK_DETACH 0x8f
-	unsigned char Flags;           /* function refinements   */
-	/* parameters passed by the ATTACH request      */
-	SERIAL_INT_CB InterruptHandler; /* called on each interrupt  */
-	SERIAL_DPC_CB DeferredHandler; /* called on hook state changes */
-	void   *HandlerContext; /* context for both handlers */
-	/* return values for both the ATTACH and the STATUS request   */
-	unsigned long IoBase;    /* IO port assigned to UART  */
-	SERIAL_STATE State;
-	/* parameters and return values for the I_SYNC function    */
-	SERIAL_I_SYNC SyncFunction;  /* to be called synchronized */
-	void   *SyncContext;  /* context for this function */
-	unsigned char SyncResult;   /* return value of function  */
-} SERIAL_HOOK;
-/*
- * IDI_SYNC_REQ_XCHANGE_STATUS - exchange the status between IDI and WMP
- * IDI_SYNC_REQ_RECONFIGURE - reconfiguration of IDI from WMP
- */
-typedef struct
-{ /* 'Req' and 'Rc' must be at the same place as in the ENTITY struct */
-	unsigned char Req;             /* request (must be always 0) */
-	unsigned char Rc;              /* return code (is the request) */
-#define DRIVER_STATUS_BOOT  0xA1
-#define DRIVER_STATUS_INIT_DEV 0xA2
-#define DRIVER_STATUS_RUNNING 0xA3
-#define DRIVER_STATUS_SHUTDOWN 0xAF
-#define DRIVER_STATUS_TRAPPED 0xAE
-	unsigned char wmpStatus;          /* exported by WMP              */
-	unsigned char idiStatus;   /* exported by IDI              */
-	unsigned long wizProto;   /* from WMP registry to IDI     */
-	/* the cardtype value is defined by cardtype.h */
-	unsigned long cardType;   /* from IDI registry to WMP     */
-	unsigned long nt2;    /* from IDI registry to WMP     */
-	unsigned long permanent;   /* from IDI registry to WMP     */
-	unsigned long stableL2;   /* from IDI registry to WMP     */
-	unsigned long tei;    /* from IDI registry to WMP     */
-#define CRC4_MASK   0x00000003
-#define L1_TRISTATE_MASK 0x00000004
-#define WATCHDOG_MASK  0x00000008
-#define NO_ORDER_CHECK_MASK 0x00000010
-#define LOW_CHANNEL_MASK 0x00000020
-#define NO_HSCX30_MASK  0x00000040
-#define SET_BOARD   0x00001000
-#define SET_CRC4   0x00030000
-#define SET_L1_TRISTATE  0x00040000
-#define SET_WATCHDOG  0x00080000
-#define SET_NO_ORDER_CHECK 0x00100000
-#define SET_LOW_CHANNEL  0x00200000
-#define SET_NO_HSCX30  0x00400000
-#define SET_MODE   0x00800000
-#define SET_PROTO   0x02000000
-#define SET_CARDTYPE  0x04000000
-#define SET_NT2    0x08000000
-#define SET_PERMANENT  0x10000000
-#define SET_STABLEL2  0x20000000
-#define SET_TEI    0x40000000
-#define SET_NUMBERLEN  0x80000000
-	unsigned long Flag;  /* |31-Type-16|15-Mask-0| */
-	unsigned long NumberLen; /* reconfiguration: union is empty */
-	union {
-		struct {    /* possible reconfiguration, but ... ; SET_BOARD */
-			unsigned long SerialNumber;
-			char     *pCardname; /* di_defs.h: BOARD_NAME_LENGTH */
-		} board;
-		struct {      /* reset: need resources */
-			void *pRawResources;
-			void *pXlatResources;
-		} res;
-		struct { /* reconfiguration: wizProto == PROTTYPE_RBSCAS */
-#define GLARE_RESOLVE_MASK 0x00000001
-#define DID_MASK   0x00000002
-#define BEARER_CAP_MASK  0x0000000c
-#define SET_GLARE_RESOLVE 0x00010000
-#define SET_DID    0x00020000
-#define SET_BEARER_CAP  0x000c0000
-			unsigned long Flag;  /* |31-Type-16|15-VALUE-0| */
-			unsigned short DigitTimeout;
-			unsigned short AnswerDelay;
-		} rbs;
-		struct { /* reconfiguration: wizProto == PROTTYPE_QSIG */
-#define CALL_REF_LENGTH1_MASK 0x00000001
-#define BRI_CHANNEL_ID_MASK  0x00000002
-#define SET_CALL_REF_LENGTH  0x00010000
-#define SET_BRI_CHANNEL_ID  0x00020000
-			unsigned long Flag;  /* |31-Type-16|15-VALUE-0| */
-		} qsig;
-		struct { /* reconfiguration: NumberLen != 0 */
-#define SET_SPID1   0x00010000
-#define SET_NUMBER1   0x00020000
-#define SET_SUBADDRESS1  0x00040000
-#define SET_SPID2   0x00100000
-#define SET_NUMBER2   0x00200000
-#define SET_SUBADDRESS2  0x00400000
-#define MASK_SET   0xffff0000
-			unsigned long Flag;   /* |31-Type-16|15-Channel-0| */
-			unsigned char *pBuffer; /* number value */
-		} isdnNo;
-	}
-		parms
-		;
-} isdnProps;
-/*
- * IDI_SYNC_REQ_PORTDRV_HOOK - signal plug/unplug (Award Cardware only)
- */
-typedef void (*PORTDRV_HOOK_CB)(void *Context, int Plug);
-typedef struct
-{ /* 'Req' and 'Rc' must be at the same place as in the ENTITY struct */
-	unsigned char Req;             /* request (must be always 0) */
-	unsigned char Rc;              /* return code (is the request) */
-	unsigned char Function;           /* private function code  */
-	unsigned char Flags;           /* function refinements   */
-	PORTDRV_HOOK_CB Callback;   /* to be called on plug/unplug */
-	void   *Context;   /* context for callback   */
-	unsigned long Info;    /* more info if needed   */
-} PORTDRV_HOOK;
-/*  Codes for the 'Rc' element in structure below. */
-#define SLI_INSTALL     (0xA1)
-#define SLI_UNINSTALL   (0xA2)
-typedef int (*SLIENTRYPOINT)(void *p3SignalAPI, void *pContext);
-typedef struct
-{   /* 'Req' and 'Rc' must be at the same place as in the ENTITY struct */
-	unsigned char   Req;                /* request (must be always 0)   */
-	unsigned char   Rc;                 /* return code (is the request) */
-	unsigned char   Function;           /* private function code        */
-	unsigned char   Flags;              /* function refinements         */
-	SLIENTRYPOINT   Callback;           /* to be called on plug/unplug  */
-	void            *Context;           /* context for callback         */
-	unsigned long   Info;               /* more info if needed          */
-} SLIENTRYPOINT_REQ;
-/******************************************************************************/
-/*
- *  Definitions for DIVA USB
- */
-typedef int (*USB_SEND_REQ)(unsigned char PipeIndex, unsigned char Type, void *Data, int sizeData);
-typedef int (*USB_START_DEV)(void *Adapter, void *Ipac);
-/* called from WDM */
-typedef void (*USB_RECV_NOTIFY)(void *Ipac, void *msg);
-typedef void (*USB_XMIT_NOTIFY)(void *Ipac, unsigned char PipeIndex);
-/******************************************************************************/
-/*
- * Parameter description for synchronous requests.
- *
- * Sorry, must repeat some parts of di_defs.h here because
- * they are not defined for all operating environments
- */
-typedef union
-{ ENTITY Entity;
-	struct
-	{ /* 'Req' and 'Rc' are at the same place as in the ENTITY struct */
-		unsigned char   Req; /* request (must be always 0) */
-		unsigned char   Rc;  /* return code (is the request) */
-	}   Request;
-	struct
-	{ unsigned char   Req; /* request (must be always 0) */
-		unsigned char   Rc;  /* return code (0x01)   */
-		unsigned char   name[BOARD_NAME_LENGTH];
-	}   GetName;
-	struct
-	{ unsigned char   Req; /* request (must be always 0) */
-		unsigned char   Rc;  /* return code (0x02)   */
-		unsigned long   serial; /* serial number    */
-	}   GetSerial;
-	struct
-	{ unsigned char   Req; /* request (must be always 0) */
-		unsigned char   Rc;  /* return code (0x02)   */
-		unsigned long   lineIdx;/* line, 0 if card has only one */
-	}   GetLineIdx;
-	struct
-	{ unsigned char  Req;     /* request (must be always 0) */
-		unsigned char  Rc;      /* return code (0x02)   */
-		unsigned long  cardtype;/* card type        */
-	}   GetCardType;
-	struct
-	{ unsigned short command;/* command = 0x0300 */
-		unsigned short dummy; /* not used */
-		IDI_CALL       callback;/* routine to call back */
-		ENTITY      *contxt; /* ptr to entity to use */
-	}   PostCall;
-	struct
-	{ unsigned char  Req;  /* request (must be always 0) */
-		unsigned char  Rc;   /* return code (0x04)   */
-		unsigned char  pcm[1]; /* buffer (a pc_maint struct) */
-	}   GetXlog;
-	struct
-	{ unsigned char  Req;  /* request (must be always 0) */
-		unsigned char  Rc;   /* return code (0x05)   */
-		unsigned short features;/* feature defines see below */
-	}   GetFeatures;
-	SERIAL_HOOK  SerialHook;
-/* Added for DIVA USB */
-	struct
-	{ unsigned char   Req;
-		unsigned char   Rc;
-		USB_SEND_REQ    UsbSendRequest; /* function in Diva Usb WDM driver in usb_os.c, */
-		/* called from usb_drv.c to send a message to our device */
-		/* eg UsbSendRequest (USB_PIPE_SIGNAL, USB_IPAC_START, 0, 0); */
-		USB_RECV_NOTIFY usb_recv;       /* called from usb_os.c to pass a received message and ptr to IPAC */
-		/* on to usb_drv.c by a call to usb_recv(). */
-		USB_XMIT_NOTIFY usb_xmit;       /* called from usb_os.c in DivaUSB.sys WDM to indicate a completed transmit */
-		/* to usb_drv.c by a call to usb_xmit(). */
-		USB_START_DEV   UsbStartDevice; /* Start the USB Device, in usb_os.c */
-		IDI_CALL        callback;       /* routine to call back */
-		ENTITY          *contxt;     /* ptr to entity to use */
-		void **ipac_ptr;    /* pointer to struct IPAC in VxD */
-	} Usb_Msg_old;
-/* message used by WDM and VXD to pass pointers of function and IPAC* */
-	struct
-	{ unsigned char Req;
-		unsigned char Rc;
-		USB_SEND_REQ    pUsbSendRequest;/* function in Diva Usb WDM driver in usb_os.c, */
-		/* called from usb_drv.c to send a message to our device */
-		/* eg UsbSendRequest (USB_PIPE_SIGNAL, USB_IPAC_START, 0, 0); */
-		USB_RECV_NOTIFY p_usb_recv;     /* called from usb_os.c to pass a received message and ptr to IPAC */
-		/* on to usb_drv.c by a call to usb_recv(). */
-		USB_XMIT_NOTIFY p_usb_xmit;     /* called from usb_os.c in DivaUSB.sys WDM to indicate a completed transmit */
-		/* to usb_drv.c by a call to usb_xmit().*/
-		void            *ipac_ptr;      /* &Diva.ipac pointer to struct IPAC in VxD */
-	} Usb_Msg;
-	PORTDRV_HOOK PortdrvHook;
-	SLIENTRYPOINT_REQ   sliEntryPointReq;
-	struct {
-		unsigned char Req;
-		unsigned char Rc;
-		diva_xdi_stream_interface_t info;
-	} xdi_stream_info;
-	struct {
-		unsigned char Req;
-		unsigned char Rc;
-		diva_xdi_get_extended_xdi_features_t info;
-	} xdi_extended_features;
-	struct {
-		unsigned char Req;
-		unsigned char Rc;
-		diva_xdi_get_adapter_sdram_bar_t info;
-	} xdi_sdram_bar;
-	struct {
-		unsigned char Req;
-		unsigned char Rc;
-		diva_xdi_get_capi_parameters_t info;
-	} xdi_capi_prms;
-	struct {
-		ENTITY           e;
-		diva_didd_adapter_notify_t info;
-	} didd_notify;
-	struct {
-		ENTITY           e;
-		diva_didd_add_adapter_t   info;
-	} didd_add_adapter;
-	struct {
-		ENTITY           e;
-		diva_didd_remove_adapter_t info;
-	} didd_remove_adapter;
-	struct {
-		ENTITY             e;
-		diva_didd_read_adapter_array_t info;
-	} didd_read_adapter_array;
-	struct {
-		ENTITY             e;
-		diva_didd_get_cfg_lib_ifc_t     info;
-	} didd_get_cfg_lib_ifc;
-	struct {
-		unsigned char Req;
-		unsigned char Rc;
-		diva_xdi_get_logical_adapter_number_s_t info;
-	} xdi_logical_adapter_number;
-	struct {
-		unsigned char Req;
-		unsigned char Rc;
-		diva_xdi_dma_descriptor_operation_t info;
-	} xdi_dma_descriptor_operation;
-} IDI_SYNC_REQ;
-/******************************************************************************/
-#endif /* __DIVA_SYNC__H */
diff --git a/drivers/isdn/hardware/eicon/dqueue.c b/drivers/isdn/hardware/eicon/dqueue.c
deleted file mode 100644
index 7958a2536a10..000000000000
--- a/drivers/isdn/hardware/eicon/dqueue.c
+++ /dev/null
@@ -1,110 +0,0 @@
-/* $Id: dqueue.c,v 1.5 2003/04/12 21:40:49 schindler Exp $
- *
- * Driver for Eicon DIVA Server ISDN cards.
- * User Mode IDI Interface
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#include "platform.h"
-#include "dqueue.h"
-
-int
-diva_data_q_init(diva_um_idi_data_queue_t *q,
-		 int max_length, int max_segments)
-{
-	int i;
-
-	q->max_length = max_length;
-	q->segments = max_segments;
-
-	for (i = 0; i < q->segments; i++) {
-		q->data[i] = NULL;
-		q->length[i] = 0;
-	}
-	q->read = q->write = q->count = q->segment_pending = 0;
-
-	for (i = 0; i < q->segments; i++) {
-		if (!(q->data[i] = diva_os_malloc(0, q->max_length))) {
-			diva_data_q_finit(q);
-			return (-1);
-		}
-	}
-
-	return (0);
-}
-
-int diva_data_q_finit(diva_um_idi_data_queue_t *q)
-{
-	int i;
-
-	for (i = 0; i < q->segments; i++) {
-		if (q->data[i]) {
-			diva_os_free(0, q->data[i]);
-		}
-		q->data[i] = NULL;
-		q->length[i] = 0;
-	}
-	q->read = q->write = q->count = q->segment_pending = 0;
-
-	return (0);
-}
-
-int diva_data_q_get_max_length(const diva_um_idi_data_queue_t *q)
-{
-	return (q->max_length);
-}
-
-void *diva_data_q_get_segment4write(diva_um_idi_data_queue_t *q)
-{
-	if ((!q->segment_pending) && (q->count < q->segments)) {
-		q->segment_pending = 1;
-		return (q->data[q->write]);
-	}
-
-	return NULL;
-}
-
-void
-diva_data_q_ack_segment4write(diva_um_idi_data_queue_t *q, int length)
-{
-	if (q->segment_pending) {
-		q->length[q->write] = length;
-		q->count++;
-		q->write++;
-		if (q->write >= q->segments) {
-			q->write = 0;
-		}
-		q->segment_pending = 0;
-	}
-}
-
-const void *diva_data_q_get_segment4read(const diva_um_idi_data_queue_t *
-					 q)
-{
-	if (q->count) {
-		return (q->data[q->read]);
-	}
-	return NULL;
-}
-
-int diva_data_q_get_segment_length(const diva_um_idi_data_queue_t *q)
-{
-	return (q->length[q->read]);
-}
-
-void diva_data_q_ack_segment4read(diva_um_idi_data_queue_t *q)
-{
-	if (q->count) {
-		q->length[q->read] = 0;
-		q->count--;
-		q->read++;
-		if (q->read >= q->segments) {
-			q->read = 0;
-		}
-	}
-}
diff --git a/drivers/isdn/hardware/eicon/dqueue.h b/drivers/isdn/hardware/eicon/dqueue.h
deleted file mode 100644
index 2da9799686ab..000000000000
--- a/drivers/isdn/hardware/eicon/dqueue.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: dqueue.h,v 1.1.2.2 2001/02/08 12:25:43 armin Exp $ */
-
-#ifndef _DIVA_USER_MODE_IDI_DATA_QUEUE_H__
-#define _DIVA_USER_MODE_IDI_DATA_QUEUE_H__
-
-#define DIVA_UM_IDI_MAX_MSGS 64
-
-typedef struct _diva_um_idi_data_queue {
-	int segments;
-	int max_length;
-	int read;
-	int write;
-	int count;
-	int segment_pending;
-	void *data[DIVA_UM_IDI_MAX_MSGS];
-	int length[DIVA_UM_IDI_MAX_MSGS];
-} diva_um_idi_data_queue_t;
-
-int diva_data_q_init(diva_um_idi_data_queue_t *q,
-		     int max_length, int max_segments);
-int diva_data_q_finit(diva_um_idi_data_queue_t *q);
-int diva_data_q_get_max_length(const diva_um_idi_data_queue_t *q);
-void *diva_data_q_get_segment4write(diva_um_idi_data_queue_t *q);
-void diva_data_q_ack_segment4write(diva_um_idi_data_queue_t *q,
-				   int length);
-const void *diva_data_q_get_segment4read(const diva_um_idi_data_queue_t *
-					 q);
-int diva_data_q_get_segment_length(const diva_um_idi_data_queue_t *q);
-void diva_data_q_ack_segment4read(diva_um_idi_data_queue_t *q);
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/dsp_defs.h b/drivers/isdn/hardware/eicon/dsp_defs.h
deleted file mode 100644
index 94828c87e2a4..000000000000
--- a/drivers/isdn/hardware/eicon/dsp_defs.h
+++ /dev/null
@@ -1,301 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef DSP_DEFS_H_
-#define DSP_DEFS_H_
-#include "dspdids.h"
-/*---------------------------------------------------------------------------*/
-#define dsp_download_reserve_space(fp, length)
-/*****************************************************************************/
-/*
- * OS file access abstraction layer
- *
- * I/O functions returns -1 on error, 0 on EOF
- */
-struct _OsFileHandle_;
-typedef long (*OsFileIo)(struct _OsFileHandle_ *handle,
-			 void *buffer,
-			 long size);
-typedef long (*OsFileSeek)(struct _OsFileHandle_ *handle,
-			   long position,
-			   int mode);
-typedef long (*OsCardLoad)(struct _OsFileHandle_    *handle,
-			   long length,
-			   void **addr);
-typedef struct _OsFileHandle_
-{ void       *sysFileDesc;
-	unsigned long sysFileSize;
-	OsFileIo      sysFileRead;
-	OsFileSeek    sysFileSeek;
-	void       *sysLoadDesc;
-	OsCardLoad    sysCardLoad;
-} OsFileHandle;
-extern OsFileHandle *OsOpenFile(char *path_name);
-extern void          OsCloseFile(OsFileHandle *fp);
-/*****************************************************************************/
-#define DSP_TELINDUS_FILE "dspdload.bin"
-/* special DSP file for BRI cards for Qsig and CornetN because of missing memory */
-#define DSP_QSIG_TELINDUS_FILE "dspdqsig.bin"
-#define DSP_MDM_TELINDUS_FILE "dspdvmdm.bin"
-#define DSP_FAX_TELINDUS_FILE "dspdvfax.bin"
-#define DSP_DIRECTORY_ENTRIES 64
-#define DSP_MEMORY_TYPE_EXTERNAL_DM         0
-#define DSP_MEMORY_TYPE_EXTERNAL_PM         1
-#define DSP_MEMORY_TYPE_INTERNAL_DM         2
-#define DSP_MEMORY_TYPE_INTERNAL_PM         3
-#define DSP_DOWNLOAD_FLAG_BOOTABLE          0x0001
-#define DSP_DOWNLOAD_FLAG_2181              0x0002
-#define DSP_DOWNLOAD_FLAG_TIMECRITICAL      0x0004
-#define DSP_DOWNLOAD_FLAG_COMPAND           0x0008
-#define DSP_MEMORY_BLOCK_COUNT              16
-#define DSP_SEGMENT_PM_FLAG                 0x0001
-#define DSP_SEGMENT_SHARED_FLAG             0x0002
-#define DSP_SEGMENT_EXTERNAL_DM             DSP_MEMORY_TYPE_EXTERNAL_DM
-#define DSP_SEGMENT_EXTERNAL_PM             DSP_MEMORY_TYPE_EXTERNAL_PM
-#define DSP_SEGMENT_INTERNAL_DM             DSP_MEMORY_TYPE_INTERNAL_DM
-#define DSP_SEGMENT_INTERNAL_PM             DSP_MEMORY_TYPE_INTERNAL_PM
-#define DSP_SEGMENT_FIRST_RELOCATABLE       4
-#define DSP_DATA_BLOCK_PM_FLAG              0x0001
-#define DSP_DATA_BLOCK_DWORD_FLAG           0x0002
-#define DSP_DATA_BLOCK_RESOLVE_FLAG         0x0004
-#define DSP_RELOC_NONE                      0x00
-#define DSP_RELOC_SEGMENT_MASK              0x3f
-#define DSP_RELOC_TYPE_MASK                 0xc0
-#define DSP_RELOC_TYPE_0                    0x00  /* relocation of address in DM word / high part of PM word */
-#define DSP_RELOC_TYPE_1                    0x40  /* relocation of address in low part of PM data word */
-#define DSP_RELOC_TYPE_2                    0x80  /* relocation of address in standard command */
-#define DSP_RELOC_TYPE_3                    0xc0  /* relocation of address in call/jump on flag in */
-#define DSP_COMBIFILE_FORMAT_IDENTIFICATION_SIZE 48
-#define DSP_COMBIFILE_FORMAT_VERSION_BCD    0x0100
-#define DSP_FILE_FORMAT_IDENTIFICATION_SIZE 48
-#define DSP_FILE_FORMAT_VERSION_BCD         0x0100
-typedef struct tag_dsp_combifile_header
-{
-	char                  format_identification[DSP_COMBIFILE_FORMAT_IDENTIFICATION_SIZE];
-	word                  format_version_bcd;
-	word                  header_size;
-	word                  combifile_description_size;
-	word                  directory_entries;
-	word                  directory_size;
-	word                  download_count;
-	word                  usage_mask_size;
-} t_dsp_combifile_header;
-typedef struct tag_dsp_combifile_directory_entry
-{
-	word                  card_type_number;
-	word                  file_set_number;
-} t_dsp_combifile_directory_entry;
-typedef struct tag_dsp_file_header
-{
-	char                  format_identification[DSP_FILE_FORMAT_IDENTIFICATION_SIZE];
-	word                  format_version_bcd;
-	word                  download_id;
-	word                  download_flags;
-	word                  required_processing_power;
-	word                  interface_channel_count;
-	word                  header_size;
-	word                  download_description_size;
-	word                  memory_block_table_size;
-	word                  memory_block_count;
-	word                  segment_table_size;
-	word                  segment_count;
-	word                  symbol_table_size;
-	word                  symbol_count;
-	word                  total_data_size_dm;
-	word                  data_block_count_dm;
-	word                  total_data_size_pm;
-	word                  data_block_count_pm;
-} t_dsp_file_header;
-typedef struct tag_dsp_memory_block_desc
-{
-	word                  alias_memory_block;
-	word                  memory_type;
-	word                  address;
-	word                  size;             /* DSP words */
-} t_dsp_memory_block_desc;
-typedef struct tag_dsp_segment_desc
-{
-	word                  memory_block;
-	word                  attributes;
-	word                  base;
-	word                  size;
-	word                  alignment;        /* ==0 -> no other legal start address than base */
-} t_dsp_segment_desc;
-typedef struct tag_dsp_symbol_desc
-{
-	word                  symbol_id;
-	word                  segment;
-	word                  offset;
-	word                  size;             /* DSP words */
-} t_dsp_symbol_desc;
-typedef struct tag_dsp_data_block_header
-{
-	word                  attributes;
-	word                  segment;
-	word                  offset;
-	word                  size;             /* DSP words */
-} t_dsp_data_block_header;
-typedef struct tag_dsp_download_desc
-{
-	word                  download_id;
-	word                  download_flags;
-	word                  required_processing_power;
-	word                  interface_channel_count;
-	word                  excess_header_size;
-	word                  memory_block_count;
-	word                  segment_count;
-	word                  symbol_count;
-	word                  data_block_count_dm;
-	word                  data_block_count_pm;
-	byte *p_excess_header_data;
-	char *p_download_description;
-	t_dsp_memory_block_desc *p_memory_block_table;
-	t_dsp_segment_desc *p_segment_table;
-	t_dsp_symbol_desc *p_symbol_table;
-	word *p_data_blocks_dm;
-	word *p_data_blocks_pm;
-} t_dsp_desc;
-typedef struct tag_dsp_portable_download_desc /* be sure to keep native alignment for MAESTRA's */
-{
-	word                  download_id;
-	word                  download_flags;
-	word                  required_processing_power;
-	word                  interface_channel_count;
-	word                  excess_header_size;
-	word                  memory_block_count;
-	word                  segment_count;
-	word                  symbol_count;
-	word                  data_block_count_dm;
-	word                  data_block_count_pm;
-	dword                 p_excess_header_data;
-	dword                 p_download_description;
-	dword                 p_memory_block_table;
-	dword                 p_segment_table;
-	dword                 p_symbol_table;
-	dword                 p_data_blocks_dm;
-	dword                 p_data_blocks_pm;
-} t_dsp_portable_desc;
-#define DSP_DOWNLOAD_INDEX_KERNEL               0
-#define DSP30TX_DOWNLOAD_INDEX_KERNEL           1
-#define DSP30RX_DOWNLOAD_INDEX_KERNEL           2
-#define DSP_MAX_DOWNLOAD_COUNT                  64
-#define DSP_DOWNLOAD_MAX_SEGMENTS         16
-#define DSP_UDATA_REQUEST_RECONFIGURE     0
-/*
-  parameters:
-  <word> reconfigure delay (in 8kHz samples)
-  <word> reconfigure code
-  <byte> reconfigure hdlc preamble flags
-*/
-#define DSP_RECONFIGURE_TX_FLAG           0x8000
-#define DSP_RECONFIGURE_SHORT_TRAIN_FLAG  0x4000
-#define DSP_RECONFIGURE_ECHO_PROTECT_FLAG 0x2000
-#define DSP_RECONFIGURE_HDLC_FLAG         0x1000
-#define DSP_RECONFIGURE_SYNC_FLAG         0x0800
-#define DSP_RECONFIGURE_PROTOCOL_MASK     0x00ff
-#define DSP_RECONFIGURE_IDLE              0
-#define DSP_RECONFIGURE_V25               1
-#define DSP_RECONFIGURE_V21_CH2           2
-#define DSP_RECONFIGURE_V27_2400          3
-#define DSP_RECONFIGURE_V27_4800          4
-#define DSP_RECONFIGURE_V29_7200          5
-#define DSP_RECONFIGURE_V29_9600          6
-#define DSP_RECONFIGURE_V33_12000         7
-#define DSP_RECONFIGURE_V33_14400         8
-#define DSP_RECONFIGURE_V17_7200          9
-#define DSP_RECONFIGURE_V17_9600          10
-#define DSP_RECONFIGURE_V17_12000         11
-#define DSP_RECONFIGURE_V17_14400         12
-/*
-  data indications if transparent framer
-  <byte> data 0
-  <byte> data 1
-  ...
-  data indications if HDLC framer
-  <byte> data 0
-  <byte> data 1
-  ...
-  <byte> CRC 0
-  <byte> CRC 1
-  <byte> preamble flags
-*/
-#define DSP_UDATA_INDICATION_SYNC         0
-/*
-  returns:
-  <word> time of sync (sampled from counter at 8kHz)
-*/
-#define DSP_UDATA_INDICATION_DCD_OFF      1
-/*
-  returns:
-  <word> time of DCD off (sampled from counter at 8kHz)
-*/
-#define DSP_UDATA_INDICATION_DCD_ON       2
-/*
-  returns:
-  <word> time of DCD on (sampled from counter at 8kHz)
-  <byte> connected norm
-  <word> connected options
-  <dword> connected speed (bit/s)
-*/
-#define DSP_UDATA_INDICATION_CTS_OFF      3
-/*
-  returns:
-  <word> time of CTS off (sampled from counter at 8kHz)
-*/
-#define DSP_UDATA_INDICATION_CTS_ON       4
-/*
-  returns:
-  <word> time of CTS on (sampled from counter at 8kHz)
-  <byte> connected norm
-  <word> connected options
-  <dword> connected speed (bit/s)
-*/
-#define DSP_CONNECTED_NORM_UNSPECIFIED      0
-#define DSP_CONNECTED_NORM_V21              1
-#define DSP_CONNECTED_NORM_V23              2
-#define DSP_CONNECTED_NORM_V22              3
-#define DSP_CONNECTED_NORM_V22_BIS          4
-#define DSP_CONNECTED_NORM_V32_BIS          5
-#define DSP_CONNECTED_NORM_V34              6
-#define DSP_CONNECTED_NORM_V8               7
-#define DSP_CONNECTED_NORM_BELL_212A        8
-#define DSP_CONNECTED_NORM_BELL_103         9
-#define DSP_CONNECTED_NORM_V29_LEASED_LINE  10
-#define DSP_CONNECTED_NORM_V33_LEASED_LINE  11
-#define DSP_CONNECTED_NORM_TFAST            12
-#define DSP_CONNECTED_NORM_V21_CH2          13
-#define DSP_CONNECTED_NORM_V27_TER          14
-#define DSP_CONNECTED_NORM_V29              15
-#define DSP_CONNECTED_NORM_V33              16
-#define DSP_CONNECTED_NORM_V17              17
-#define DSP_CONNECTED_OPTION_TRELLIS        0x0001
-/*---------------------------------------------------------------------------*/
-extern char *dsp_read_file(OsFileHandle *fp,
-			   word card_type_number,
-			   word *p_dsp_download_count,
-			   t_dsp_desc *p_dsp_download_table,
-			   t_dsp_portable_desc *p_dsp_portable_download_table);
-/*---------------------------------------------------------------------------*/
-#endif /* DSP_DEFS_H_ */
diff --git a/drivers/isdn/hardware/eicon/dsp_tst.h b/drivers/isdn/hardware/eicon/dsp_tst.h
deleted file mode 100644
index 85edd3ea50f7..000000000000
--- a/drivers/isdn/hardware/eicon/dsp_tst.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: dsp_tst.h,v 1.1.2.2 2001/02/08 12:25:43 armin Exp $ */
-
-#ifndef __DIVA_PRI_HOST_TEST_DSPS_H__
-#define __DIVA_PRI_HOST_TEST_DSPS_H__
-
-/*
-  DSP registers on maestra pri
-*/
-#define DSP1_PORT       (0x00)
-#define DSP2_PORT       (0x8)
-#define DSP3_PORT       (0x800)
-#define DSP4_PORT       (0x808)
-#define DSP5_PORT       (0x810)
-#define DSP6_PORT       (0x818)
-#define DSP7_PORT       (0x820)
-#define DSP8_PORT       (0x828)
-#define DSP9_PORT       (0x830)
-#define DSP10_PORT      (0x840)
-#define DSP11_PORT      (0x848)
-#define DSP12_PORT      (0x850)
-#define DSP13_PORT      (0x858)
-#define DSP14_PORT      (0x860)
-#define DSP15_PORT      (0x868)
-#define DSP16_PORT      (0x870)
-#define DSP17_PORT      (0x1000)
-#define DSP18_PORT      (0x1008)
-#define DSP19_PORT      (0x1010)
-#define DSP20_PORT      (0x1018)
-#define DSP21_PORT      (0x1020)
-#define DSP22_PORT      (0x1028)
-#define DSP23_PORT      (0x1030)
-#define DSP24_PORT      (0x1040)
-#define DSP25_PORT      (0x1048)
-#define DSP26_PORT      (0x1050)
-#define DSP27_PORT      (0x1058)
-#define DSP28_PORT      (0x1060)
-#define DSP29_PORT      (0x1068)
-#define DSP30_PORT      (0x1070)
-#define DSP_ADR_OFFS    0x80
-
-/*------------------------------------------------------------------
-  Dsp related definitions
-  ------------------------------------------------------------------ */
-#define DSP_SIGNATURE_PROBE_WORD 0x5a5a
-#define dsp_make_address_ex(pm, address) ((word)((pm) ? (address) : (address) + 0x4000))
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/dspdids.h b/drivers/isdn/hardware/eicon/dspdids.h
deleted file mode 100644
index 957b33cc0022..000000000000
--- a/drivers/isdn/hardware/eicon/dspdids.h
+++ /dev/null
@@ -1,75 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef DSPDIDS_H_
-#define DSPDIDS_H_
-/*---------------------------------------------------------------------------*/
-#define DSP_DID_INVALID   0
-#define DSP_DID_DIVA   1
-#define DSP_DID_DIVA_PRO  2
-#define DSP_DID_DIVA_PRO_20  3
-#define DSP_DID_DIVA_PRO_PCCARD  4
-#define DSP_DID_DIVA_SERVER_BRI_1M 5
-#define DSP_DID_DIVA_SERVER_BRI_2M 6
-#define DSP_DID_DIVA_SERVER_PRI_2M_TX 7
-#define DSP_DID_DIVA_SERVER_PRI_2M_RX 8
-#define DSP_DID_DIVA_SERVER_PRI_30M 9
-#define DSP_DID_TASK_HSCX  100
-#define DSP_DID_TASK_HSCX_PRI_2M_TX 101
-#define DSP_DID_TASK_HSCX_PRI_2M_RX 102
-#define DSP_DID_TASK_V110KRNL  200
-#define DSP_DID_OVERLAY_V1100  201
-#define DSP_DID_OVERLAY_V1101  202
-#define DSP_DID_OVERLAY_V1102  203
-#define DSP_DID_OVERLAY_V1103  204
-#define DSP_DID_OVERLAY_V1104  205
-#define DSP_DID_OVERLAY_V1105  206
-#define DSP_DID_OVERLAY_V1106  207
-#define DSP_DID_OVERLAY_V1107  208
-#define DSP_DID_OVERLAY_V1108  209
-#define DSP_DID_OVERLAY_V1109  210
-#define DSP_DID_TASK_V110_PRI_2M_TX 220
-#define DSP_DID_TASK_V110_PRI_2M_RX 221
-#define DSP_DID_TASK_MODEM  300
-#define DSP_DID_TASK_FAX05  400
-#define DSP_DID_TASK_VOICE  500
-#define DSP_DID_TASK_TIKRNL81  600
-#define DSP_DID_OVERLAY_DIAL  601
-#define DSP_DID_OVERLAY_V22  602
-#define DSP_DID_OVERLAY_V32  603
-#define DSP_DID_OVERLAY_FSK  604
-#define DSP_DID_OVERLAY_FAX  605
-#define DSP_DID_OVERLAY_VXX  606
-#define DSP_DID_OVERLAY_V8  607
-#define DSP_DID_OVERLAY_INFO  608
-#define DSP_DID_OVERLAY_V34  609
-#define DSP_DID_OVERLAY_DFX  610
-#define DSP_DID_PARTIAL_OVERLAY_DIAL 611
-#define DSP_DID_PARTIAL_OVERLAY_FSK 612
-#define DSP_DID_PARTIAL_OVERLAY_FAX 613
-#define DSP_DID_TASK_TIKRNL05  700
-/*---------------------------------------------------------------------------*/
-#endif
-/*---------------------------------------------------------------------------*/
diff --git a/drivers/isdn/hardware/eicon/dsrv4bri.h b/drivers/isdn/hardware/eicon/dsrv4bri.h
deleted file mode 100644
index f353fb6b8933..000000000000
--- a/drivers/isdn/hardware/eicon/dsrv4bri.h
+++ /dev/null
@@ -1,40 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_XDI_DSRV_4_BRI_INC__
-#define __DIVA_XDI_DSRV_4_BRI_INC__
-/*
- * Some special registers in the PLX 9054
- */
-#define PLX9054_P2LDBELL    0x60
-#define PLX9054_L2PDBELL    0x64
-#define PLX9054_INTCSR      0x69
-#define PLX9054_INT_ENABLE  0x09
-#define PLX9054_SOFT_RESET 0x4000
-#define PLX9054_RELOAD_EEPROM 0x2000
-#define DIVA_4BRI_REVISION(__x__) (((__x__)->cardType == CARDTYPE_DIVASRV_Q_8M_V2_PCI) || ((__x__)->cardType == CARDTYPE_DIVASRV_VOICE_Q_8M_V2_PCI) || ((__x__)->cardType == CARDTYPE_DIVASRV_B_2M_V2_PCI) || ((__x__)->cardType == CARDTYPE_DIVASRV_B_2F_PCI) || ((__x__)->cardType == CARDTYPE_DIVASRV_VOICE_B_2M_V2_PCI))
-void diva_os_set_qBri_functions(PISDN_ADAPTER IoAdapter);
-void diva_os_set_qBri2_functions(PISDN_ADAPTER IoAdapter);
-#endif
diff --git a/drivers/isdn/hardware/eicon/dsrv_bri.h b/drivers/isdn/hardware/eicon/dsrv_bri.h
deleted file mode 100644
index 8a67dbc65be4..000000000000
--- a/drivers/isdn/hardware/eicon/dsrv_bri.h
+++ /dev/null
@@ -1,37 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_XDI_DSRV_BRI_INC__
-#define __DIVA_XDI_DSRV_BRI_INC__
-/*
-  Functions exported from os dependent part of
-  BRI card configuration and used in
-  OS independed part
-*/
-/*
-  Prepare OS dependent part of BRI functions
-*/
-void diva_os_prepare_maestra_functions(PISDN_ADAPTER IoAdapter);
-#endif
diff --git a/drivers/isdn/hardware/eicon/dsrv_pri.h b/drivers/isdn/hardware/eicon/dsrv_pri.h
deleted file mode 100644
index fd1a9ff9f195..000000000000
--- a/drivers/isdn/hardware/eicon/dsrv_pri.h
+++ /dev/null
@@ -1,38 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_XDI_DSRV_PRI_INC__
-#define __DIVA_XDI_DSRV_PRI_INC__
-/*
-  Functions exported from os dependent part of
-  PRI card configuration and used in
-  OS independed part
-*/
-/*
-  Prepare OS dependent part of PRI/PRI Rev.2 functions
-*/
-void diva_os_prepare_pri_functions(PISDN_ADAPTER IoAdapter);
-void diva_os_prepare_pri2_functions(PISDN_ADAPTER IoAdapter);
-#endif
diff --git a/drivers/isdn/hardware/eicon/entity.h b/drivers/isdn/hardware/eicon/entity.h
deleted file mode 100644
index f9767d321db9..000000000000
--- a/drivers/isdn/hardware/eicon/entity.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: entity.h,v 1.4 2004/03/21 17:26:01 armin Exp $ */
-
-#ifndef __DIVAS_USER_MODE_IDI_ENTITY__
-#define __DIVAS_USER_MODE_IDI_ENTITY__
-
-#define DIVA_UM_IDI_RC_PENDING      0x00000001
-#define DIVA_UM_IDI_REMOVE_PENDING  0x00000002
-#define DIVA_UM_IDI_TX_FLOW_CONTROL 0x00000004
-#define DIVA_UM_IDI_REMOVED         0x00000008
-#define DIVA_UM_IDI_ASSIGN_PENDING  0x00000010
-
-typedef struct _divas_um_idi_entity {
-	struct list_head          link;
-	diva_um_idi_adapter_t *adapter; /* Back to adapter */
-	ENTITY e;
-	void *os_ref;
-	dword status;
-	void *os_context;
-	int rc_count;
-	diva_um_idi_data_queue_t  data; /* definad by user 1 ... MAX */
-	diva_um_idi_data_queue_t  rc;   /* two entries */
-	BUFFERS                   XData;
-	BUFFERS                   RData;
-	byte                      buffer[2048 + 512];
-} divas_um_idi_entity_t;
-
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/helpers.h b/drivers/isdn/hardware/eicon/helpers.h
deleted file mode 100644
index c9156b0acaba..000000000000
--- a/drivers/isdn/hardware/eicon/helpers.h
+++ /dev/null
@@ -1,51 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_XDI_CARD_CONFIG_HELPERS_INC__
-#define __DIVA_XDI_CARD_CONFIG_HELPERS_INC__
-dword diva_get_protocol_file_features(byte *File,
-				      int offset,
-				      char *IdStringBuffer,
-				      dword IdBufferSize);
-void diva_configure_protocol(PISDN_ADAPTER IoAdapter);
-/*
-  Low level file access system abstraction
-*/
-/* -------------------------------------------------------------------------
-   Access to single file
-   Return pointer to the image of the requested file,
-   write image length to 'FileLength'
-   ------------------------------------------------------------------------- */
-void *xdiLoadFile(char *FileName, dword *FileLength, unsigned long MaxLoadSize);
-/* -------------------------------------------------------------------------
-   Dependent on the protocol settings does read return pointer
-   to the image of appropriate protocol file
-   ------------------------------------------------------------------------- */
-void *xdiLoadArchive(PISDN_ADAPTER IoAdapter, dword *FileLength, unsigned long MaxLoadSize);
-/* --------------------------------------------------------------------------
-   Free all system resources accessed by xdiLoadFile and xdiLoadArchive
-   -------------------------------------------------------------------------- */
-void xdiFreeFile(void *handle);
-#endif
diff --git a/drivers/isdn/hardware/eicon/idifunc.c b/drivers/isdn/hardware/eicon/idifunc.c
deleted file mode 100644
index fef6586fe5ac..000000000000
--- a/drivers/isdn/hardware/eicon/idifunc.c
+++ /dev/null
@@ -1,268 +0,0 @@
-/* $Id: idifunc.c,v 1.14.4.4 2004/08/28 20:03:53 armin Exp $
- *
- * Driver for Eicon DIVA Server ISDN cards.
- * User Mode IDI Interface
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#include "platform.h"
-#include "di_defs.h"
-#include "divasync.h"
-#include "um_xdi.h"
-#include "um_idi.h"
-
-#define DBG_MINIMUM  (DL_LOG + DL_FTL + DL_ERR)
-#define DBG_DEFAULT  (DBG_MINIMUM + DL_XLOG + DL_REG)
-
-extern char *DRIVERRELEASE_IDI;
-
-extern void DIVA_DIDD_Read(void *, int);
-extern int diva_user_mode_idi_create_adapter(const DESCRIPTOR *, int);
-extern void diva_user_mode_idi_remove_adapter(int);
-
-static dword notify_handle;
-static DESCRIPTOR DAdapter;
-static DESCRIPTOR MAdapter;
-
-static void no_printf(unsigned char *x, ...)
-{
-	/* dummy debug function */
-}
-
-#include "debuglib.c"
-
-/*
- * stop debug
- */
-static void stop_dbg(void)
-{
-	DbgDeregister();
-	memset(&MAdapter, 0, sizeof(MAdapter));
-	dprintf = no_printf;
-}
-
-typedef struct _udiva_card {
-	struct list_head list;
-	int Id;
-	DESCRIPTOR d;
-} udiva_card;
-
-static LIST_HEAD(cards);
-static diva_os_spin_lock_t ll_lock;
-
-/*
- * find card in list
- */
-static udiva_card *find_card_in_list(DESCRIPTOR *d)
-{
-	udiva_card *card;
-	struct list_head *tmp;
-	diva_os_spin_lock_magic_t old_irql;
-
-	diva_os_enter_spin_lock(&ll_lock, &old_irql, "find card");
-	list_for_each(tmp, &cards) {
-		card = list_entry(tmp, udiva_card, list);
-		if (card->d.request == d->request) {
-			diva_os_leave_spin_lock(&ll_lock, &old_irql,
-						"find card");
-			return (card);
-		}
-	}
-	diva_os_leave_spin_lock(&ll_lock, &old_irql, "find card");
-	return ((udiva_card *) NULL);
-}
-
-/*
- * new card
- */
-static void um_new_card(DESCRIPTOR *d)
-{
-	int adapter_nr = 0;
-	udiva_card *card = NULL;
-	IDI_SYNC_REQ sync_req;
-	diva_os_spin_lock_magic_t old_irql;
-
-	if (!(card = diva_os_malloc(0, sizeof(udiva_card)))) {
-		DBG_ERR(("cannot get buffer for card"));
-		return;
-	}
-	memcpy(&card->d, d, sizeof(DESCRIPTOR));
-	sync_req.xdi_logical_adapter_number.Req = 0;
-	sync_req.xdi_logical_adapter_number.Rc =
-		IDI_SYNC_REQ_XDI_GET_LOGICAL_ADAPTER_NUMBER;
-	card->d.request((ENTITY *)&sync_req);
-	adapter_nr =
-		sync_req.xdi_logical_adapter_number.info.logical_adapter_number;
-	card->Id = adapter_nr;
-	if (!(diva_user_mode_idi_create_adapter(d, adapter_nr))) {
-		diva_os_enter_spin_lock(&ll_lock, &old_irql, "add card");
-		list_add_tail(&card->list, &cards);
-		diva_os_leave_spin_lock(&ll_lock, &old_irql, "add card");
-	} else {
-		DBG_ERR(("could not create user mode idi card %d",
-			 adapter_nr));
-		diva_os_free(0, card);
-	}
-}
-
-/*
- * remove card
- */
-static void um_remove_card(DESCRIPTOR *d)
-{
-	diva_os_spin_lock_magic_t old_irql;
-	udiva_card *card = NULL;
-
-	if (!(card = find_card_in_list(d))) {
-		DBG_ERR(("cannot find card to remove"));
-		return;
-	}
-	diva_user_mode_idi_remove_adapter(card->Id);
-	diva_os_enter_spin_lock(&ll_lock, &old_irql, "remove card");
-	list_del(&card->list);
-	diva_os_leave_spin_lock(&ll_lock, &old_irql, "remove card");
-	DBG_LOG(("idi proc entry removed for card %d", card->Id));
-	diva_os_free(0, card);
-}
-
-/*
- * remove all adapter
- */
-static void __exit remove_all_idi_proc(void)
-{
-	udiva_card *card;
-	diva_os_spin_lock_magic_t old_irql;
-
-rescan:
-	diva_os_enter_spin_lock(&ll_lock, &old_irql, "remove all");
-	if (!list_empty(&cards)) {
-		card = list_entry(cards.next, udiva_card, list);
-		list_del(&card->list);
-		diva_os_leave_spin_lock(&ll_lock, &old_irql, "remove all");
-		diva_user_mode_idi_remove_adapter(card->Id);
-		diva_os_free(0, card);
-		goto rescan;
-	}
-	diva_os_leave_spin_lock(&ll_lock, &old_irql, "remove all");
-}
-
-/*
- * DIDD notify callback
- */
-static void *didd_callback(void *context, DESCRIPTOR *adapter,
-			   int removal)
-{
-	if (adapter->type == IDI_DADAPTER) {
-		DBG_ERR(("Notification about IDI_DADAPTER change ! Oops."));
-		return (NULL);
-	} else if (adapter->type == IDI_DIMAINT) {
-		if (removal) {
-			stop_dbg();
-		} else {
-			memcpy(&MAdapter, adapter, sizeof(MAdapter));
-			dprintf = (DIVA_DI_PRINTF) MAdapter.request;
-			DbgRegister("User IDI", DRIVERRELEASE_IDI, DBG_DEFAULT);
-		}
-	} else if ((adapter->type > 0) && (adapter->type < 16)) {	/* IDI Adapter */
-		if (removal) {
-			um_remove_card(adapter);
-		} else {
-			um_new_card(adapter);
-		}
-	}
-	return (NULL);
-}
-
-/*
- * connect DIDD
- */
-static int __init connect_didd(void)
-{
-	int x = 0;
-	int dadapter = 0;
-	IDI_SYNC_REQ req;
-	DESCRIPTOR DIDD_Table[MAX_DESCRIPTORS];
-
-	DIVA_DIDD_Read(DIDD_Table, sizeof(DIDD_Table));
-
-	for (x = 0; x < MAX_DESCRIPTORS; x++) {
-		if (DIDD_Table[x].type == IDI_DADAPTER) {	/* DADAPTER found */
-			dadapter = 1;
-			memcpy(&DAdapter, &DIDD_Table[x], sizeof(DAdapter));
-			req.didd_notify.e.Req = 0;
-			req.didd_notify.e.Rc =
-				IDI_SYNC_REQ_DIDD_REGISTER_ADAPTER_NOTIFY;
-			req.didd_notify.info.callback = (void *)didd_callback;
-			req.didd_notify.info.context = NULL;
-			DAdapter.request((ENTITY *)&req);
-			if (req.didd_notify.e.Rc != 0xff) {
-				stop_dbg();
-				return (0);
-			}
-			notify_handle = req.didd_notify.info.handle;
-		} else if (DIDD_Table[x].type == IDI_DIMAINT) {	/* MAINT found */
-			memcpy(&MAdapter, &DIDD_Table[x], sizeof(DAdapter));
-			dprintf = (DIVA_DI_PRINTF) MAdapter.request;
-			DbgRegister("User IDI", DRIVERRELEASE_IDI, DBG_DEFAULT);
-		} else if ((DIDD_Table[x].type > 0)
-			   && (DIDD_Table[x].type < 16)) {	/* IDI Adapter found */
-			um_new_card(&DIDD_Table[x]);
-		}
-	}
-
-	if (!dadapter) {
-		stop_dbg();
-	}
-
-	return (dadapter);
-}
-
-/*
- *  Disconnect from DIDD
- */
-static void __exit disconnect_didd(void)
-{
-	IDI_SYNC_REQ req;
-
-	stop_dbg();
-
-	req.didd_notify.e.Req = 0;
-	req.didd_notify.e.Rc = IDI_SYNC_REQ_DIDD_REMOVE_ADAPTER_NOTIFY;
-	req.didd_notify.info.handle = notify_handle;
-	DAdapter.request((ENTITY *)&req);
-}
-
-/*
- * init
- */
-int __init idifunc_init(void)
-{
-	diva_os_initialize_spin_lock(&ll_lock, "idifunc");
-
-	if (diva_user_mode_idi_init()) {
-		DBG_ERR(("init: init failed."));
-		return (0);
-	}
-
-	if (!connect_didd()) {
-		diva_user_mode_idi_finit();
-		DBG_ERR(("init: failed to connect to DIDD."));
-		return (0);
-	}
-	return (1);
-}
-
-/*
- * finit
- */
-void __exit idifunc_finit(void)
-{
-	diva_user_mode_idi_finit();
-	disconnect_didd();
-	remove_all_idi_proc();
-}
diff --git a/drivers/isdn/hardware/eicon/io.c b/drivers/isdn/hardware/eicon/io.c
deleted file mode 100644
index 8851ce580c23..000000000000
--- a/drivers/isdn/hardware/eicon/io.c
+++ /dev/null
@@ -1,852 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#include "platform.h"
-#include "di_defs.h"
-#include "pc.h"
-#include "pr_pc.h"
-#include "divasync.h"
-#define MIPS_SCOM
-#include "pkmaint.h" /* pc_main.h, packed in os-dependent fashion */
-#include "di.h"
-#include "mi_pc.h"
-#include "io.h"
-extern ADAPTER *adapter[MAX_ADAPTER];
-extern PISDN_ADAPTER IoAdapters[MAX_ADAPTER];
-void request(PISDN_ADAPTER, ENTITY *);
-static void pcm_req(PISDN_ADAPTER, ENTITY *);
-/* --------------------------------------------------------------------------
-   local functions
-   -------------------------------------------------------------------------- */
-#define ReqFunc(N)							\
-	static void Request##N(ENTITY *e)				\
-	{ if (IoAdapters[N]) (*IoAdapters[N]->DIRequest)(IoAdapters[N], e); }
-ReqFunc(0)
-ReqFunc(1)
-ReqFunc(2)
-ReqFunc(3)
-ReqFunc(4)
-ReqFunc(5)
-ReqFunc(6)
-ReqFunc(7)
-ReqFunc(8)
-ReqFunc(9)
-ReqFunc(10)
-ReqFunc(11)
-ReqFunc(12)
-ReqFunc(13)
-ReqFunc(14)
-ReqFunc(15)
-IDI_CALL Requests[MAX_ADAPTER] =
-{ &Request0, &Request1, &Request2, &Request3,
-  &Request4, &Request5, &Request6, &Request7,
-  &Request8, &Request9, &Request10, &Request11,
-  &Request12, &Request13, &Request14, &Request15
-};
-/*****************************************************************************/
-/*
-  This array should indicate all new services, that this version of XDI
-  is able to provide to his clients
-*/
-static byte extended_xdi_features[DIVA_XDI_EXTENDED_FEATURES_MAX_SZ + 1] = {
-	(DIVA_XDI_EXTENDED_FEATURES_VALID       |
-	 DIVA_XDI_EXTENDED_FEATURE_SDRAM_BAR    |
-	 DIVA_XDI_EXTENDED_FEATURE_CAPI_PRMS    |
-#if defined(DIVA_IDI_RX_DMA)
-	 DIVA_XDI_EXTENDED_FEATURE_CMA          |
-	 DIVA_XDI_EXTENDED_FEATURE_RX_DMA       |
-	 DIVA_XDI_EXTENDED_FEATURE_MANAGEMENT_DMA |
-#endif
-	 DIVA_XDI_EXTENDED_FEATURE_NO_CANCEL_RC),
-	0
-};
-/*****************************************************************************/
-void
-dump_xlog_buffer(PISDN_ADAPTER IoAdapter, Xdesc *xlogDesc)
-{
-	dword   logLen;
-	word *Xlog   = xlogDesc->buf;
-	word  logCnt = xlogDesc->cnt;
-	word  logOut = xlogDesc->out / sizeof(*Xlog);
-	DBG_FTL(("%s: ************* XLOG recovery (%d) *************",
-		 &IoAdapter->Name[0], (int)logCnt))
-		DBG_FTL(("Microcode: %s", &IoAdapter->ProtocolIdString[0]))
-		for (; logCnt > 0; --logCnt)
-		{
-			if (!GET_WORD(&Xlog[logOut]))
-			{
-				if (--logCnt == 0)
-					break;
-				logOut = 0;
-			}
-			if (GET_WORD(&Xlog[logOut]) <= (logOut * sizeof(*Xlog)))
-			{
-				if (logCnt > 2)
-				{
-					DBG_FTL(("Possibly corrupted XLOG: %d entries left",
-						 (int)logCnt))
-						}
-				break;
-			}
-			logLen = (dword)(GET_WORD(&Xlog[logOut]) - (logOut * sizeof(*Xlog)));
-			DBG_FTL_MXLOG(((char *)&Xlog[logOut + 1], (dword)(logLen - 2)))
-				logOut = (GET_WORD(&Xlog[logOut]) + 1) / sizeof(*Xlog);
-		}
-	DBG_FTL(("%s: ***************** end of XLOG *****************",
-		 &IoAdapter->Name[0]))
-		}
-/*****************************************************************************/
-#if defined(XDI_USE_XLOG)
-static char *(ExceptionCauseTable[]) =
-{
-	"Interrupt",
-	"TLB mod /IBOUND",
-	"TLB load /DBOUND",
-	"TLB store",
-	"Address error load",
-	"Address error store",
-	"Instruction load bus error",
-	"Data load/store bus error",
-	"Syscall",
-	"Breakpoint",
-	"Reverd instruction",
-	"Coprocessor unusable",
-	"Overflow",
-	"TRAP",
-	"VCEI",
-	"Floating Point Exception",
-	"CP2",
-	"Reserved 17",
-	"Reserved 18",
-	"Reserved 19",
-	"Reserved 20",
-	"Reserved 21",
-	"Reserved 22",
-	"WATCH",
-	"Reserved 24",
-	"Reserved 25",
-	"Reserved 26",
-	"Reserved 27",
-	"Reserved 28",
-	"Reserved 29",
-	"Reserved 30",
-	"VCED"
-};
-#endif
-void
-dump_trap_frame(PISDN_ADAPTER IoAdapter, byte __iomem *exceptionFrame)
-{
-	MP_XCPTC __iomem *xcept = (MP_XCPTC __iomem *)exceptionFrame;
-	dword    __iomem *regs;
-	regs  = &xcept->regs[0];
-	DBG_FTL(("%s: ***************** CPU TRAPPED *****************",
-		 &IoAdapter->Name[0]))
-		DBG_FTL(("Microcode: %s", &IoAdapter->ProtocolIdString[0]))
-		DBG_FTL(("Cause: %s",
-			 ExceptionCauseTable[(READ_DWORD(&xcept->cr) & 0x0000007c) >> 2]))
-		DBG_FTL(("sr    0x%08x cr    0x%08x epc   0x%08x vaddr 0x%08x",
-			 READ_DWORD(&xcept->sr), READ_DWORD(&xcept->cr),
-			 READ_DWORD(&xcept->epc), READ_DWORD(&xcept->vaddr)))
-		DBG_FTL(("zero  0x%08x at    0x%08x v0    0x%08x v1    0x%08x",
-			 READ_DWORD(&regs[0]), READ_DWORD(&regs[1]),
-			 READ_DWORD(&regs[2]), READ_DWORD(&regs[3])))
-		DBG_FTL(("a0    0x%08x a1    0x%08x a2    0x%08x a3    0x%08x",
-			 READ_DWORD(&regs[4]), READ_DWORD(&regs[5]),
-			 READ_DWORD(&regs[6]), READ_DWORD(&regs[7])))
-		DBG_FTL(("t0    0x%08x t1    0x%08x t2    0x%08x t3    0x%08x",
-			 READ_DWORD(&regs[8]), READ_DWORD(&regs[9]),
-			 READ_DWORD(&regs[10]), READ_DWORD(&regs[11])))
-		DBG_FTL(("t4    0x%08x t5    0x%08x t6    0x%08x t7    0x%08x",
-			 READ_DWORD(&regs[12]), READ_DWORD(&regs[13]),
-			 READ_DWORD(&regs[14]), READ_DWORD(&regs[15])))
-		DBG_FTL(("s0    0x%08x s1    0x%08x s2    0x%08x s3    0x%08x",
-			 READ_DWORD(&regs[16]), READ_DWORD(&regs[17]),
-			 READ_DWORD(&regs[18]), READ_DWORD(&regs[19])))
-		DBG_FTL(("s4    0x%08x s5    0x%08x s6    0x%08x s7    0x%08x",
-			 READ_DWORD(&regs[20]), READ_DWORD(&regs[21]),
-			 READ_DWORD(&regs[22]), READ_DWORD(&regs[23])))
-		DBG_FTL(("t8    0x%08x t9    0x%08x k0    0x%08x k1    0x%08x",
-			 READ_DWORD(&regs[24]), READ_DWORD(&regs[25]),
-			 READ_DWORD(&regs[26]), READ_DWORD(&regs[27])))
-		DBG_FTL(("gp    0x%08x sp    0x%08x s8    0x%08x ra    0x%08x",
-			 READ_DWORD(&regs[28]), READ_DWORD(&regs[29]),
-			 READ_DWORD(&regs[30]), READ_DWORD(&regs[31])))
-		DBG_FTL(("md    0x%08x|%08x         resvd 0x%08x class 0x%08x",
-			 READ_DWORD(&xcept->mdhi), READ_DWORD(&xcept->mdlo),
-			 READ_DWORD(&xcept->reseverd), READ_DWORD(&xcept->xclass)))
-		}
-/* --------------------------------------------------------------------------
-   Real XDI Request function
-   -------------------------------------------------------------------------- */
-void request(PISDN_ADAPTER IoAdapter, ENTITY *e)
-{
-	byte i;
-	diva_os_spin_lock_magic_t irql;
-/*
- * if the Req field in the entity structure is 0,
- * we treat this request as a special function call
- */
-	if (!e->Req)
-	{
-		IDI_SYNC_REQ *syncReq = (IDI_SYNC_REQ *)e;
-		switch (e->Rc)
-		{
-#if defined(DIVA_IDI_RX_DMA)
-		case IDI_SYNC_REQ_DMA_DESCRIPTOR_OPERATION: {
-			diva_xdi_dma_descriptor_operation_t *pI = \
-				&syncReq->xdi_dma_descriptor_operation.info;
-			if (!IoAdapter->dma_map) {
-				pI->operation         = -1;
-				pI->descriptor_number = -1;
-				return;
-			}
-			diva_os_enter_spin_lock(&IoAdapter->data_spin_lock, &irql, "dma_op");
-			if (pI->operation == IDI_SYNC_REQ_DMA_DESCRIPTOR_ALLOC) {
-				pI->descriptor_number = diva_alloc_dma_map_entry(\
-					(struct _diva_dma_map_entry *)IoAdapter->dma_map);
-				if (pI->descriptor_number >= 0) {
-					dword dma_magic;
-					void *local_addr;
-					diva_get_dma_map_entry(\
-						(struct _diva_dma_map_entry *)IoAdapter->dma_map,
-						pI->descriptor_number,
-						&local_addr, &dma_magic);
-					pI->descriptor_address  = local_addr;
-					pI->descriptor_magic    = dma_magic;
-					pI->operation           = 0;
-				} else {
-					pI->operation           = -1;
-				}
-			} else if ((pI->operation == IDI_SYNC_REQ_DMA_DESCRIPTOR_FREE) &&
-				   (pI->descriptor_number >= 0)) {
-				diva_free_dma_map_entry((struct _diva_dma_map_entry *)IoAdapter->dma_map,
-							pI->descriptor_number);
-				pI->descriptor_number = -1;
-				pI->operation         = 0;
-			} else {
-				pI->descriptor_number = -1;
-				pI->operation         = -1;
-			}
-			diva_os_leave_spin_lock(&IoAdapter->data_spin_lock, &irql, "dma_op");
-		} return;
-#endif
-		case IDI_SYNC_REQ_XDI_GET_LOGICAL_ADAPTER_NUMBER: {
-			diva_xdi_get_logical_adapter_number_s_t *pI = \
-				&syncReq->xdi_logical_adapter_number.info;
-			pI->logical_adapter_number = IoAdapter->ANum;
-			pI->controller = IoAdapter->ControllerNumber;
-			pI->total_controllers = IoAdapter->Properties.Adapters;
-		} return;
-		case IDI_SYNC_REQ_XDI_GET_CAPI_PARAMS: {
-			diva_xdi_get_capi_parameters_t prms, *pI = &syncReq->xdi_capi_prms.info;
-			memset(&prms, 0x00, sizeof(prms));
-			prms.structure_length = min_t(size_t, sizeof(prms), pI->structure_length);
-			memset(pI, 0x00, pI->structure_length);
-			prms.flag_dynamic_l1_down    = (IoAdapter->capi_cfg.cfg_1 & \
-							DIVA_XDI_CAPI_CFG_1_DYNAMIC_L1_ON) ? 1 : 0;
-			prms.group_optimization_enabled = (IoAdapter->capi_cfg.cfg_1 & \
-							   DIVA_XDI_CAPI_CFG_1_GROUP_POPTIMIZATION_ON) ? 1 : 0;
-			memcpy(pI, &prms, prms.structure_length);
-		} return;
-		case IDI_SYNC_REQ_XDI_GET_ADAPTER_SDRAM_BAR:
-			syncReq->xdi_sdram_bar.info.bar = IoAdapter->sdram_bar;
-			return;
-		case IDI_SYNC_REQ_XDI_GET_EXTENDED_FEATURES: {
-			dword i;
-			diva_xdi_get_extended_xdi_features_t *pI =\
-				&syncReq->xdi_extended_features.info;
-			pI->buffer_length_in_bytes &= ~0x80000000;
-			if (pI->buffer_length_in_bytes && pI->features) {
-				memset(pI->features, 0x00, pI->buffer_length_in_bytes);
-			}
-			for (i = 0; ((pI->features) && (i < pI->buffer_length_in_bytes) &&
-				     (i < DIVA_XDI_EXTENDED_FEATURES_MAX_SZ)); i++) {
-				pI->features[i] = extended_xdi_features[i];
-			}
-			if ((pI->buffer_length_in_bytes < DIVA_XDI_EXTENDED_FEATURES_MAX_SZ) ||
-			    (!pI->features)) {
-				pI->buffer_length_in_bytes =\
-					(0x80000000 | DIVA_XDI_EXTENDED_FEATURES_MAX_SZ);
-			}
-		} return;
-		case IDI_SYNC_REQ_XDI_GET_STREAM:
-			if (IoAdapter) {
-				diva_xdi_provide_istream_info(&IoAdapter->a,
-							      &syncReq->xdi_stream_info.info);
-			} else {
-				syncReq->xdi_stream_info.info.provided_service = 0;
-			}
-			return;
-		case IDI_SYNC_REQ_GET_NAME:
-			if (IoAdapter)
-			{
-				strcpy(&syncReq->GetName.name[0], IoAdapter->Name);
-				DBG_TRC(("xdi: Adapter %d / Name '%s'",
-					 IoAdapter->ANum, IoAdapter->Name))
-					return;
-			}
-			syncReq->GetName.name[0] = '\0';
-			break;
-		case IDI_SYNC_REQ_GET_SERIAL:
-			if (IoAdapter)
-			{
-				syncReq->GetSerial.serial = IoAdapter->serialNo;
-				DBG_TRC(("xdi: Adapter %d / SerialNo %ld",
-					 IoAdapter->ANum, IoAdapter->serialNo))
-					return;
-			}
-			syncReq->GetSerial.serial = 0;
-			break;
-		case IDI_SYNC_REQ_GET_CARDTYPE:
-			if (IoAdapter)
-			{
-				syncReq->GetCardType.cardtype = IoAdapter->cardType;
-				DBG_TRC(("xdi: Adapter %d / CardType %ld",
-					 IoAdapter->ANum, IoAdapter->cardType))
-					return;
-			}
-			syncReq->GetCardType.cardtype = 0;
-			break;
-		case IDI_SYNC_REQ_GET_XLOG:
-			if (IoAdapter)
-			{
-				pcm_req(IoAdapter, e);
-				return;
-			}
-			e->Ind = 0;
-			break;
-		case IDI_SYNC_REQ_GET_DBG_XLOG:
-			if (IoAdapter)
-			{
-				pcm_req(IoAdapter, e);
-				return;
-			}
-			e->Ind = 0;
-			break;
-		case IDI_SYNC_REQ_GET_FEATURES:
-			if (IoAdapter)
-			{
-				syncReq->GetFeatures.features =
-					(unsigned short)IoAdapter->features;
-				return;
-			}
-			syncReq->GetFeatures.features = 0;
-			break;
-		case IDI_SYNC_REQ_PORTDRV_HOOK:
-			if (IoAdapter)
-			{
-				DBG_TRC(("Xdi:IDI_SYNC_REQ_PORTDRV_HOOK - ignored"))
-					return;
-			}
-			break;
-		}
-		if (IoAdapter)
-		{
-			return;
-		}
-	}
-	DBG_TRC(("xdi: Id 0x%x / Req 0x%x / Rc 0x%x", e->Id, e->Req, e->Rc))
-		if (!IoAdapter)
-		{
-			DBG_FTL(("xdi: uninitialized Adapter used - ignore request"))
-				return;
-		}
-	diva_os_enter_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_req");
-/*
- * assign an entity
- */
-	if (!(e->Id & 0x1f))
-	{
-		if (IoAdapter->e_count >= IoAdapter->e_max)
-		{
-			DBG_FTL(("xdi: all Ids in use (max=%d) --> Req ignored",
-				 IoAdapter->e_max))
-				diva_os_leave_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_req");
-			return;
-		}
-/*
- * find a new free id
- */
-		for (i = 1; IoAdapter->e_tbl[i].e; ++i);
-		IoAdapter->e_tbl[i].e = e;
-		IoAdapter->e_count++;
-		e->No = (byte)i;
-		e->More = 0;
-		e->RCurrent = 0xff;
-	}
-	else
-	{
-		i = e->No;
-	}
-/*
- * if the entity is still busy, ignore the request call
- */
-	if (e->More & XBUSY)
-	{
-		DBG_FTL(("xdi: Id 0x%x busy --> Req 0x%x ignored", e->Id, e->Req))
-			if (!IoAdapter->trapped && IoAdapter->trapFnc)
-			{
-				IoAdapter->trapFnc(IoAdapter);
-				/*
-				  Firs trap, also notify user if supported
-				*/
-				if (IoAdapter->trapped && IoAdapter->os_trap_nfy_Fnc) {
-					(*(IoAdapter->os_trap_nfy_Fnc))(IoAdapter, IoAdapter->ANum);
-				}
-			}
-		diva_os_leave_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_req");
-		return;
-	}
-/*
- * initialize transmit status variables
- */
-	e->More |= XBUSY;
-	e->More &= ~XMOREF;
-	e->XCurrent = 0;
-	e->XOffset = 0;
-/*
- * queue this entity in the adapter request queue
- */
-	IoAdapter->e_tbl[i].next = 0;
-	if (IoAdapter->head)
-	{
-		IoAdapter->e_tbl[IoAdapter->tail].next = i;
-		IoAdapter->tail = i;
-	}
-	else
-	{
-		IoAdapter->head = i;
-		IoAdapter->tail = i;
-	}
-/*
- * queue the DPC to process the request
- */
-	diva_os_schedule_soft_isr(&IoAdapter->req_soft_isr);
-	diva_os_leave_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_req");
-}
-/* ---------------------------------------------------------------------
-   Main DPC routine
-   --------------------------------------------------------------------- */
-void DIDpcRoutine(struct _diva_os_soft_isr *psoft_isr, void *Context) {
-	PISDN_ADAPTER IoAdapter = (PISDN_ADAPTER)Context;
-	ADAPTER *a = &IoAdapter->a;
-	diva_os_atomic_t *pin_dpc = &IoAdapter->in_dpc;
-	if (diva_os_atomic_increment(pin_dpc) == 1) {
-		do {
-			if (IoAdapter->tst_irq(a))
-			{
-				if (!IoAdapter->Unavailable)
-					IoAdapter->dpc(a);
-				IoAdapter->clr_irq(a);
-			}
-			IoAdapter->out(a);
-		} while (diva_os_atomic_decrement(pin_dpc) > 0);
-		/* ----------------------------------------------------------------
-		   Look for XLOG request (cards with indirect addressing)
-		   ---------------------------------------------------------------- */
-		if (IoAdapter->pcm_pending) {
-			struct pc_maint *pcm;
-			diva_os_spin_lock_magic_t OldIrql;
-			diva_os_enter_spin_lock(&IoAdapter->data_spin_lock,
-						&OldIrql,
-						"data_dpc");
-			pcm = (struct pc_maint *)IoAdapter->pcm_data;
-			switch (IoAdapter->pcm_pending) {
-			case 1: /* ask card for XLOG */
-				a->ram_out(a, &IoAdapter->pcm->rc, 0);
-				a->ram_out(a, &IoAdapter->pcm->req, pcm->req);
-				IoAdapter->pcm_pending = 2;
-				break;
-			case 2: /* Try to get XLOG from the card */
-				if ((int)(a->ram_in(a, &IoAdapter->pcm->rc))) {
-					a->ram_in_buffer(a, IoAdapter->pcm, pcm, sizeof(*pcm));
-					IoAdapter->pcm_pending = 3;
-				}
-				break;
-			case 3: /* let XDI recovery XLOG */
-				break;
-			}
-			diva_os_leave_spin_lock(&IoAdapter->data_spin_lock,
-						&OldIrql,
-						"data_dpc");
-		}
-		/* ---------------------------------------------------------------- */
-	}
-}
-/* --------------------------------------------------------------------------
-   XLOG interface
-   -------------------------------------------------------------------------- */
-static void
-pcm_req(PISDN_ADAPTER IoAdapter, ENTITY *e)
-{
-	diva_os_spin_lock_magic_t OldIrql;
-	int              i, rc;
-	ADAPTER         *a = &IoAdapter->a;
-	struct pc_maint *pcm = (struct pc_maint *)&e->Ind;
-/*
- * special handling of I/O based card interface
- * the memory access isn't an atomic operation !
- */
-	if (IoAdapter->Properties.Card == CARD_MAE)
-	{
-		diva_os_enter_spin_lock(&IoAdapter->data_spin_lock,
-					&OldIrql,
-					"data_pcm_1");
-		IoAdapter->pcm_data = (void *)pcm;
-		IoAdapter->pcm_pending = 1;
-		diva_os_schedule_soft_isr(&IoAdapter->req_soft_isr);
-		diva_os_leave_spin_lock(&IoAdapter->data_spin_lock,
-					&OldIrql,
-					"data_pcm_1");
-		for (rc = 0, i = (IoAdapter->trapped ? 3000 : 250); !rc && (i > 0); --i)
-		{
-			diva_os_sleep(1);
-			if (IoAdapter->pcm_pending == 3) {
-				diva_os_enter_spin_lock(&IoAdapter->data_spin_lock,
-							&OldIrql,
-							"data_pcm_3");
-				IoAdapter->pcm_pending = 0;
-				IoAdapter->pcm_data    = NULL;
-				diva_os_leave_spin_lock(&IoAdapter->data_spin_lock,
-							&OldIrql,
-							"data_pcm_3");
-				return;
-			}
-			diva_os_enter_spin_lock(&IoAdapter->data_spin_lock,
-						&OldIrql,
-						"data_pcm_2");
-			diva_os_schedule_soft_isr(&IoAdapter->req_soft_isr);
-			diva_os_leave_spin_lock(&IoAdapter->data_spin_lock,
-						&OldIrql,
-						"data_pcm_2");
-		}
-		diva_os_enter_spin_lock(&IoAdapter->data_spin_lock,
-					&OldIrql,
-					"data_pcm_4");
-		IoAdapter->pcm_pending = 0;
-		IoAdapter->pcm_data    = NULL;
-		diva_os_leave_spin_lock(&IoAdapter->data_spin_lock,
-					&OldIrql,
-					"data_pcm_4");
-		goto Trapped;
-	}
-/*
- * memory based shared ram is accessible from different
- * processors without disturbing concurrent processes.
- */
-	a->ram_out(a, &IoAdapter->pcm->rc, 0);
-	a->ram_out(a, &IoAdapter->pcm->req, pcm->req);
-	for (i = (IoAdapter->trapped ? 3000 : 250); --i > 0;)
-	{
-		diva_os_sleep(1);
-		rc = (int)(a->ram_in(a, &IoAdapter->pcm->rc));
-		if (rc)
-		{
-			a->ram_in_buffer(a, IoAdapter->pcm, pcm, sizeof(*pcm));
-			return;
-		}
-	}
-Trapped:
-	if (IoAdapter->trapFnc)
-	{
-		int trapped = IoAdapter->trapped;
-		IoAdapter->trapFnc(IoAdapter);
-		/*
-		  Firs trap, also notify user if supported
-		*/
-		if (!trapped && IoAdapter->trapped && IoAdapter->os_trap_nfy_Fnc) {
-			(*(IoAdapter->os_trap_nfy_Fnc))(IoAdapter, IoAdapter->ANum);
-		}
-	}
-}
-/*------------------------------------------------------------------*/
-/* ram access functions for memory mapped cards                     */
-/*------------------------------------------------------------------*/
-byte mem_in(ADAPTER *a, void *addr)
-{
-	byte val;
-	volatile byte __iomem *Base = DIVA_OS_MEM_ATTACH_RAM((PISDN_ADAPTER)a->io);
-	val = READ_BYTE(Base + (unsigned long)addr);
-	DIVA_OS_MEM_DETACH_RAM((PISDN_ADAPTER)a->io, Base);
-	return (val);
-}
-word mem_inw(ADAPTER *a, void *addr)
-{
-	word val;
-	volatile byte __iomem *Base = DIVA_OS_MEM_ATTACH_RAM((PISDN_ADAPTER)a->io);
-	val = READ_WORD((Base + (unsigned long)addr));
-	DIVA_OS_MEM_DETACH_RAM((PISDN_ADAPTER)a->io, Base);
-	return (val);
-}
-void mem_in_dw(ADAPTER *a, void *addr, dword *data, int dwords)
-{
-	volatile byte __iomem *Base = DIVA_OS_MEM_ATTACH_RAM((PISDN_ADAPTER)a->io);
-	while (dwords--) {
-		*data++ = READ_DWORD((Base + (unsigned long)addr));
-		addr += 4;
-	}
-	DIVA_OS_MEM_DETACH_RAM((PISDN_ADAPTER)a->io, Base);
-}
-void mem_in_buffer(ADAPTER *a, void *addr, void *buffer, word length)
-{
-	volatile byte __iomem *Base = DIVA_OS_MEM_ATTACH_RAM((PISDN_ADAPTER)a->io);
-	memcpy_fromio(buffer, (Base + (unsigned long)addr), length);
-	DIVA_OS_MEM_DETACH_RAM((PISDN_ADAPTER)a->io, Base);
-}
-void mem_look_ahead(ADAPTER *a, PBUFFER *RBuffer, ENTITY *e)
-{
-	PISDN_ADAPTER IoAdapter = (PISDN_ADAPTER)a->io;
-	IoAdapter->RBuffer.length = mem_inw(a, &RBuffer->length);
-	mem_in_buffer(a, RBuffer->P, IoAdapter->RBuffer.P,
-		      IoAdapter->RBuffer.length);
-	e->RBuffer = (DBUFFER *)&IoAdapter->RBuffer;
-}
-void mem_out(ADAPTER *a, void *addr, byte data)
-{
-	volatile byte __iomem *Base = DIVA_OS_MEM_ATTACH_RAM((PISDN_ADAPTER)a->io);
-	WRITE_BYTE(Base + (unsigned long)addr, data);
-	DIVA_OS_MEM_DETACH_RAM((PISDN_ADAPTER)a->io, Base);
-}
-void mem_outw(ADAPTER *a, void *addr, word data)
-{
-	volatile byte __iomem *Base = DIVA_OS_MEM_ATTACH_RAM((PISDN_ADAPTER)a->io);
-	WRITE_WORD((Base + (unsigned long)addr), data);
-	DIVA_OS_MEM_DETACH_RAM((PISDN_ADAPTER)a->io, Base);
-}
-void mem_out_dw(ADAPTER *a, void *addr, const dword *data, int dwords)
-{
-	volatile byte __iomem *Base = DIVA_OS_MEM_ATTACH_RAM((PISDN_ADAPTER)a->io);
-	while (dwords--) {
-		WRITE_DWORD((Base + (unsigned long)addr), *data);
-		addr += 4;
-		data++;
-	}
-	DIVA_OS_MEM_DETACH_RAM((PISDN_ADAPTER)a->io, Base);
-}
-void mem_out_buffer(ADAPTER *a, void *addr, void *buffer, word length)
-{
-	volatile byte __iomem *Base = DIVA_OS_MEM_ATTACH_RAM((PISDN_ADAPTER)a->io);
-	memcpy_toio((Base + (unsigned long)addr), buffer, length);
-	DIVA_OS_MEM_DETACH_RAM((PISDN_ADAPTER)a->io, Base);
-}
-void mem_inc(ADAPTER *a, void *addr)
-{
-	volatile byte __iomem *Base = DIVA_OS_MEM_ATTACH_RAM((PISDN_ADAPTER)a->io);
-	byte  x = READ_BYTE(Base + (unsigned long)addr);
-	WRITE_BYTE(Base + (unsigned long)addr, x + 1);
-	DIVA_OS_MEM_DETACH_RAM((PISDN_ADAPTER)a->io, Base);
-}
-/*------------------------------------------------------------------*/
-/* ram access functions for io-mapped cards                         */
-/*------------------------------------------------------------------*/
-byte io_in(ADAPTER *a, void *adr)
-{
-	byte val;
-	byte __iomem *Port = DIVA_OS_MEM_ATTACH_PORT((PISDN_ADAPTER)a->io);
-	outppw(Port + 4, (word)(unsigned long)adr);
-	val = inpp(Port);
-	DIVA_OS_MEM_DETACH_PORT((PISDN_ADAPTER)a->io, Port);
-	return (val);
-}
-word io_inw(ADAPTER *a, void *adr)
-{
-	word val;
-	byte __iomem *Port = DIVA_OS_MEM_ATTACH_PORT((PISDN_ADAPTER)a->io);
-	outppw(Port + 4, (word)(unsigned long)adr);
-	val = inppw(Port);
-	DIVA_OS_MEM_DETACH_PORT((PISDN_ADAPTER)a->io, Port);
-	return (val);
-}
-void io_in_buffer(ADAPTER *a, void *adr, void *buffer, word len)
-{
-	byte __iomem *Port = DIVA_OS_MEM_ATTACH_PORT((PISDN_ADAPTER)a->io);
-	byte *P = (byte *)buffer;
-	if ((long)adr & 1) {
-		outppw(Port + 4, (word)(unsigned long)adr);
-		*P = inpp(Port);
-		P++;
-		adr = ((byte *) adr) + 1;
-		len--;
-		if (!len) {
-			DIVA_OS_MEM_DETACH_PORT((PISDN_ADAPTER)a->io, Port);
-			return;
-		}
-	}
-	outppw(Port + 4, (word)(unsigned long)adr);
-	inppw_buffer(Port, P, len + 1);
-	DIVA_OS_MEM_DETACH_PORT((PISDN_ADAPTER)a->io, Port);
-}
-void io_look_ahead(ADAPTER *a, PBUFFER *RBuffer, ENTITY *e)
-{
-	byte __iomem *Port = DIVA_OS_MEM_ATTACH_PORT((PISDN_ADAPTER)a->io);
-	outppw(Port + 4, (word)(unsigned long)RBuffer);
-	((PISDN_ADAPTER)a->io)->RBuffer.length = inppw(Port);
-	inppw_buffer(Port, ((PISDN_ADAPTER)a->io)->RBuffer.P, ((PISDN_ADAPTER)a->io)->RBuffer.length + 1);
-	e->RBuffer = (DBUFFER *) &(((PISDN_ADAPTER)a->io)->RBuffer);
-	DIVA_OS_MEM_DETACH_PORT((PISDN_ADAPTER)a->io, Port);
-}
-void io_out(ADAPTER *a, void *adr, byte data)
-{
-	byte __iomem *Port = DIVA_OS_MEM_ATTACH_PORT((PISDN_ADAPTER)a->io);
-	outppw(Port + 4, (word)(unsigned long)adr);
-	outpp(Port, data);
-	DIVA_OS_MEM_DETACH_PORT((PISDN_ADAPTER)a->io, Port);
-}
-void io_outw(ADAPTER *a, void *adr, word data)
-{
-	byte __iomem *Port = DIVA_OS_MEM_ATTACH_PORT((PISDN_ADAPTER)a->io);
-	outppw(Port + 4, (word)(unsigned long)adr);
-	outppw(Port, data);
-	DIVA_OS_MEM_DETACH_PORT((PISDN_ADAPTER)a->io, Port);
-}
-void io_out_buffer(ADAPTER *a, void *adr, void *buffer, word len)
-{
-	byte __iomem *Port = DIVA_OS_MEM_ATTACH_PORT((PISDN_ADAPTER)a->io);
-	byte *P = (byte *)buffer;
-	if ((long)adr & 1) {
-		outppw(Port + 4, (word)(unsigned long)adr);
-		outpp(Port, *P);
-		P++;
-		adr = ((byte *) adr) + 1;
-		len--;
-		if (!len) {
-			DIVA_OS_MEM_DETACH_PORT((PISDN_ADAPTER)a->io, Port);
-			return;
-		}
-	}
-	outppw(Port + 4, (word)(unsigned long)adr);
-	outppw_buffer(Port, P, len + 1);
-	DIVA_OS_MEM_DETACH_PORT((PISDN_ADAPTER)a->io, Port);
-}
-void io_inc(ADAPTER *a, void *adr)
-{
-	byte x;
-	byte __iomem *Port = DIVA_OS_MEM_ATTACH_PORT((PISDN_ADAPTER)a->io);
-	outppw(Port + 4, (word)(unsigned long)adr);
-	x = inpp(Port);
-	outppw(Port + 4, (word)(unsigned long)adr);
-	outpp(Port, x + 1);
-	DIVA_OS_MEM_DETACH_PORT((PISDN_ADAPTER)a->io, Port);
-}
-/*------------------------------------------------------------------*/
-/* OS specific functions related to queuing of entities             */
-/*------------------------------------------------------------------*/
-void free_entity(ADAPTER *a, byte e_no)
-{
-	PISDN_ADAPTER IoAdapter;
-	diva_os_spin_lock_magic_t irql;
-	IoAdapter = (PISDN_ADAPTER) a->io;
-	diva_os_enter_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_free");
-	IoAdapter->e_tbl[e_no].e = NULL;
-	IoAdapter->e_count--;
-	diva_os_leave_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_free");
-}
-void assign_queue(ADAPTER *a, byte e_no, word ref)
-{
-	PISDN_ADAPTER IoAdapter;
-	diva_os_spin_lock_magic_t irql;
-	IoAdapter = (PISDN_ADAPTER) a->io;
-	diva_os_enter_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_assign");
-	IoAdapter->e_tbl[e_no].assign_ref = ref;
-	IoAdapter->e_tbl[e_no].next = (byte)IoAdapter->assign;
-	IoAdapter->assign = e_no;
-	diva_os_leave_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_assign");
-}
-byte get_assign(ADAPTER *a, word ref)
-{
-	PISDN_ADAPTER IoAdapter;
-	diva_os_spin_lock_magic_t irql;
-	byte e_no;
-	IoAdapter = (PISDN_ADAPTER) a->io;
-	diva_os_enter_spin_lock(&IoAdapter->data_spin_lock,
-				&irql,
-				"data_assign_get");
-	for (e_no = (byte)IoAdapter->assign;
-	    e_no && IoAdapter->e_tbl[e_no].assign_ref != ref;
-	    e_no = IoAdapter->e_tbl[e_no].next);
-	diva_os_leave_spin_lock(&IoAdapter->data_spin_lock,
-				&irql,
-				"data_assign_get");
-	return e_no;
-}
-void req_queue(ADAPTER *a, byte e_no)
-{
-	PISDN_ADAPTER IoAdapter;
-	diva_os_spin_lock_magic_t irql;
-	IoAdapter = (PISDN_ADAPTER) a->io;
-	diva_os_enter_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_req_q");
-	IoAdapter->e_tbl[e_no].next = 0;
-	if (IoAdapter->head) {
-		IoAdapter->e_tbl[IoAdapter->tail].next = e_no;
-		IoAdapter->tail = e_no;
-	}
-	else {
-		IoAdapter->head = e_no;
-		IoAdapter->tail = e_no;
-	}
-	diva_os_leave_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_req_q");
-}
-byte look_req(ADAPTER *a)
-{
-	PISDN_ADAPTER IoAdapter;
-	IoAdapter = (PISDN_ADAPTER) a->io;
-	return ((byte)IoAdapter->head);
-}
-void next_req(ADAPTER *a)
-{
-	PISDN_ADAPTER IoAdapter;
-	diva_os_spin_lock_magic_t irql;
-	IoAdapter = (PISDN_ADAPTER) a->io;
-	diva_os_enter_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_req_next");
-	IoAdapter->head = IoAdapter->e_tbl[IoAdapter->head].next;
-	if (!IoAdapter->head) IoAdapter->tail = 0;
-	diva_os_leave_spin_lock(&IoAdapter->data_spin_lock, &irql, "data_req_next");
-}
-/*------------------------------------------------------------------*/
-/* memory map functions                                             */
-/*------------------------------------------------------------------*/
-ENTITY *entity_ptr(ADAPTER *a, byte e_no)
-{
-	PISDN_ADAPTER IoAdapter;
-	IoAdapter = (PISDN_ADAPTER)a->io;
-	return (IoAdapter->e_tbl[e_no].e);
-}
-void *PTR_X(ADAPTER *a, ENTITY *e)
-{
-	return ((void *) e->X);
-}
-void *PTR_R(ADAPTER *a, ENTITY *e)
-{
-	return ((void *) e->R);
-}
-void *PTR_P(ADAPTER *a, ENTITY *e, void *P)
-{
-	return P;
-}
-void CALLBACK(ADAPTER *a, ENTITY *e)
-{
-	if (e && e->callback)
-		e->callback(e);
-}
diff --git a/drivers/isdn/hardware/eicon/io.h b/drivers/isdn/hardware/eicon/io.h
deleted file mode 100644
index 01deced18ab8..000000000000
--- a/drivers/isdn/hardware/eicon/io.h
+++ /dev/null
@@ -1,308 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_XDI_COMMON_IO_H_INC__ /* { */
-#define __DIVA_XDI_COMMON_IO_H_INC__
-/*
-  maximum = 16 adapters
-*/
-#define DI_MAX_LINKS    MAX_ADAPTER
-#define ISDN_MAX_NUM_LEN 60
-/* --------------------------------------------------------------------------
-   structure for quadro card management (obsolete for
-   systems that do provide per card load event)
-   -------------------------------------------------------------------------- */
-typedef struct {
-	dword         Num;
-	DEVICE_NAME   DeviceName[4];
-	PISDN_ADAPTER QuadroAdapter[4];
-} ADAPTER_LIST_ENTRY, *PADAPTER_LIST_ENTRY;
-/* --------------------------------------------------------------------------
-   Special OS memory support structures
-   -------------------------------------------------------------------------- */
-#define MAX_MAPPED_ENTRIES 8
-typedef struct {
-	void *Address;
-	dword    Length;
-} ADAPTER_MEMORY;
-/* --------------------------------------------------------------------------
-   Configuration of XDI clients carried by XDI
-   -------------------------------------------------------------------------- */
-#define DIVA_XDI_CAPI_CFG_1_DYNAMIC_L1_ON      0x01
-#define DIVA_XDI_CAPI_CFG_1_GROUP_POPTIMIZATION_ON 0x02
-typedef struct _diva_xdi_capi_cfg {
-	byte cfg_1;
-} diva_xdi_capi_cfg_t;
-/* --------------------------------------------------------------------------
-   Main data structure kept per adapter
-   -------------------------------------------------------------------------- */
-struct _ISDN_ADAPTER {
-	void (*DIRequest)(PISDN_ADAPTER, ENTITY *);
-	int State; /* from NT4 1.srv, a good idea, but  a poor achievement */
-	int Initialized;
-	int RegisteredWithDidd;
-	int Unavailable;  /* callback function possible? */
-	int ResourcesClaimed;
-	int PnpBiosConfigUsed;
-	dword Logging;
-	dword features;
-	char ProtocolIdString[80];
-	/*
-	  remember mapped memory areas
-	*/
-	ADAPTER_MEMORY MappedMemory[MAX_MAPPED_ENTRIES];
-	CARD_PROPERTIES Properties;
-	dword cardType;
-	dword protocol_id;       /* configured protocol identifier */
-	char protocol_name[8];  /* readable name of protocol */
-	dword BusType;
-	dword BusNumber;
-	dword slotNumber;
-	dword slotId;
-	dword ControllerNumber;  /* for QUADRO cards only */
-	PISDN_ADAPTER MultiMaster;       /* for 4-BRI card only - use MultiMaster or QuadroList */
-	PADAPTER_LIST_ENTRY QuadroList;        /* for QUADRO card  only */
-	PDEVICE_OBJECT DeviceObject;
-	dword DeviceId;
-	diva_os_adapter_irq_info_t irq_info;
-	dword volatile IrqCount;
-	int trapped;
-	dword DspCodeBaseAddr;
-	dword MaxDspCodeSize;
-	dword downloadAddr;
-	dword DspCodeBaseAddrTable[4]; /* add. for MultiMaster */
-	dword MaxDspCodeSizeTable[4]; /* add. for MultiMaster */
-	dword downloadAddrTable[4]; /* add. for MultiMaster */
-	dword MemoryBase;
-	dword MemorySize;
-	byte __iomem *Address;
-	byte __iomem *Config;
-	byte __iomem *Control;
-	byte __iomem *reset;
-	byte __iomem *port;
-	byte __iomem *ram;
-	byte __iomem *cfg;
-	byte __iomem *prom;
-	byte __iomem *ctlReg;
-	struct pc_maint  *pcm;
-	diva_os_dependent_devica_name_t os_name;
-	byte Name[32];
-	dword serialNo;
-	dword ANum;
-	dword ArchiveType; /* ARCHIVE_TYPE_NONE ..._SINGLE ..._USGEN ..._MULTI */
-	char *ProtocolSuffix; /* internal protocolfile table */
-	char Archive[32];
-	char Protocol[32];
-	char AddDownload[32]; /* Dsp- or other additional download files */
-	char Oad1[ISDN_MAX_NUM_LEN];
-	char Osa1[ISDN_MAX_NUM_LEN];
-	char Oad2[ISDN_MAX_NUM_LEN];
-	char Osa2[ISDN_MAX_NUM_LEN];
-	char Spid1[ISDN_MAX_NUM_LEN];
-	char Spid2[ISDN_MAX_NUM_LEN];
-	byte nosig;
-	byte BriLayer2LinkCount; /* amount of TEI's that adapter will support in P2MP mode */
-	dword Channels;
-	dword tei;
-	dword nt2;
-	dword TerminalCount;
-	dword WatchDog;
-	dword Permanent;
-	dword BChMask; /* B channel mask for unchannelized modes */
-	dword StableL2;
-	dword DidLen;
-	dword NoOrderCheck;
-	dword ForceLaw; /* VoiceCoding - default:0, a-law: 1, my-law: 2 */
-	dword SigFlags;
-	dword LowChannel;
-	dword NoHscx30;
-	dword ProtVersion;
-	dword crc4;
-	dword L1TristateOrQsig; /* enable Layer 1 Tristate (bit 2)Or Qsig params (bit 0,1)*/
-	dword InitialDspInfo;
-	dword ModemGuardTone;
-	dword ModemMinSpeed;
-	dword ModemMaxSpeed;
-	dword ModemOptions;
-	dword ModemOptions2;
-	dword ModemNegotiationMode;
-	dword ModemModulationsMask;
-	dword ModemTransmitLevel;
-	dword FaxOptions;
-	dword FaxMaxSpeed;
-	dword Part68LevelLimiter;
-	dword UsEktsNumCallApp;
-	byte UsEktsFeatAddConf;
-	byte UsEktsFeatRemoveConf;
-	byte UsEktsFeatCallTransfer;
-	byte UsEktsFeatMsgWaiting;
-	byte QsigDialect;
-	byte ForceVoiceMailAlert;
-	byte DisableAutoSpid;
-	byte ModemCarrierWaitTimeSec;
-	byte ModemCarrierLossWaitTimeTenthSec;
-	byte PiafsLinkTurnaroundInFrames;
-	byte DiscAfterProgress;
-	byte AniDniLimiter[3];
-	byte TxAttenuation;  /* PRI/E1 only: attenuate TX signal */
-	word QsigFeatures;
-	dword GenerateRingtone;
-	dword SupplementaryServicesFeatures;
-	dword R2Dialect;
-	dword R2CasOptions;
-	dword FaxV34Options;
-	dword DisabledDspMask;
-	dword AdapterTestMask;
-	dword DspImageLength;
-	word AlertToIn20mSecTicks;
-	word ModemEyeSetup;
-	byte R2CtryLength;
-	byte CCBSRelTimer;
-	byte *PcCfgBufferFile;/* flexible parameter via file */
-	byte *PcCfgBuffer; /* flexible parameter via multistring */
-	diva_os_dump_file_t dump_file; /* dump memory to file at lowest irq level */
-	diva_os_board_trace_t board_trace; /* traces from the board */
-	diva_os_spin_lock_t isr_spin_lock;
-	diva_os_spin_lock_t data_spin_lock;
-	diva_os_soft_isr_t req_soft_isr;
-	diva_os_soft_isr_t isr_soft_isr;
-	diva_os_atomic_t  in_dpc;
-	PBUFFER RBuffer;        /* Copy of receive lookahead buffer */
-	word e_max;
-	word e_count;
-	E_INFO *e_tbl;
-	word assign;         /* list of pending ASSIGNs  */
-	word head;           /* head of request queue    */
-	word tail;           /* tail of request queue    */
-	ADAPTER a;             /* not a separate structure */
-	void (*out)(ADAPTER *a);
-	byte (*dpc)(ADAPTER *a);
-	byte (*tst_irq)(ADAPTER *a);
-	void (*clr_irq)(ADAPTER *a);
-	int (*load)(PISDN_ADAPTER);
-	int (*mapmem)(PISDN_ADAPTER);
-	int (*chkIrq)(PISDN_ADAPTER);
-	void (*disIrq)(PISDN_ADAPTER);
-	void (*start)(PISDN_ADAPTER);
-	void (*stop)(PISDN_ADAPTER);
-	void (*rstFnc)(PISDN_ADAPTER);
-	void (*trapFnc)(PISDN_ADAPTER);
-	dword (*DetectDsps)(PISDN_ADAPTER);
-	void (*os_trap_nfy_Fnc)(PISDN_ADAPTER, dword);
-	diva_os_isr_callback_t diva_isr_handler;
-	dword sdram_bar;  /* must be 32 bit */
-	dword fpga_features;
-	volatile int pcm_pending;
-	volatile void *pcm_data;
-	diva_xdi_capi_cfg_t capi_cfg;
-	dword tasks;
-	void *dma_map;
-	int (*DivaAdapterTestProc)(PISDN_ADAPTER);
-	void *AdapterTestMemoryStart;
-	dword AdapterTestMemoryLength;
-	const byte *cfg_lib_memory_init;
-	dword cfg_lib_memory_init_length;
-};
-/* ---------------------------------------------------------------------
-   Entity table
-   --------------------------------------------------------------------- */
-struct e_info_s {
-	ENTITY *e;
-	byte          next;                   /* chaining index           */
-	word          assign_ref;             /* assign reference         */
-};
-/* ---------------------------------------------------------------------
-   S-cards shared ram structure for loading
-   --------------------------------------------------------------------- */
-struct s_load {
-	byte ctrl;
-	byte card;
-	byte msize;
-	byte fill0;
-	word ebit;
-	word elocl;
-	word eloch;
-	byte reserved[20];
-	word signature;
-	byte fill[224];
-	byte b[256];
-};
-#define PR_RAM  ((struct pr_ram *)0)
-#define RAM ((struct dual *)0)
-/* ---------------------------------------------------------------------
-   platform specific conversions
-   --------------------------------------------------------------------- */
-extern void *PTR_P(ADAPTER *a, ENTITY *e, void *P);
-extern void *PTR_X(ADAPTER *a, ENTITY *e);
-extern void *PTR_R(ADAPTER *a, ENTITY *e);
-extern void CALLBACK(ADAPTER *a, ENTITY *e);
-extern void set_ram(void **adr_ptr);
-/* ---------------------------------------------------------------------
-   ram access functions for io mapped cards
-   --------------------------------------------------------------------- */
-byte io_in(ADAPTER *a, void *adr);
-word io_inw(ADAPTER *a, void *adr);
-void io_in_buffer(ADAPTER *a, void *adr, void *P, word length);
-void io_look_ahead(ADAPTER *a, PBUFFER *RBuffer, ENTITY *e);
-void io_out(ADAPTER *a, void *adr, byte data);
-void io_outw(ADAPTER *a, void *adr, word data);
-void io_out_buffer(ADAPTER *a, void *adr, void *P, word length);
-void io_inc(ADAPTER *a, void *adr);
-void bri_in_buffer(PISDN_ADAPTER IoAdapter, dword Pos,
-		   void *Buf, dword Len);
-int bri_out_buffer(PISDN_ADAPTER IoAdapter, dword Pos,
-		   void *Buf, dword Len, int Verify);
-/* ---------------------------------------------------------------------
-   ram access functions for memory mapped cards
-   --------------------------------------------------------------------- */
-byte mem_in(ADAPTER *a, void *adr);
-word mem_inw(ADAPTER *a, void *adr);
-void mem_in_buffer(ADAPTER *a, void *adr, void *P, word length);
-void mem_look_ahead(ADAPTER *a, PBUFFER *RBuffer, ENTITY *e);
-void mem_out(ADAPTER *a, void *adr, byte data);
-void mem_outw(ADAPTER *a, void *adr, word data);
-void mem_out_buffer(ADAPTER *a, void *adr, void *P, word length);
-void mem_inc(ADAPTER *a, void *adr);
-void mem_in_dw(ADAPTER *a, void *addr, dword *data, int dwords);
-void mem_out_dw(ADAPTER *a, void *addr, const dword *data, int dwords);
-/* ---------------------------------------------------------------------
-   functions exported by io.c
-   --------------------------------------------------------------------- */
-extern IDI_CALL Requests[MAX_ADAPTER];
-extern void     DIDpcRoutine(struct _diva_os_soft_isr *psoft_isr,
-			     void *context);
-extern void     request(PISDN_ADAPTER, ENTITY *);
-/* ---------------------------------------------------------------------
-   trapFn helpers, used to recover debug trace from dead card
-   --------------------------------------------------------------------- */
-typedef struct {
-	word *buf;
-	word  cnt;
-	word  out;
-} Xdesc;
-extern void dump_trap_frame(PISDN_ADAPTER IoAdapter, byte __iomem *exception);
-extern void dump_xlog_buffer(PISDN_ADAPTER IoAdapter, Xdesc *xlogDesc);
-/* --------------------------------------------------------------------- */
-#endif  /* } __DIVA_XDI_COMMON_IO_H_INC__ */
diff --git a/drivers/isdn/hardware/eicon/istream.c b/drivers/isdn/hardware/eicon/istream.c
deleted file mode 100644
index 045bda5c839f..000000000000
--- a/drivers/isdn/hardware/eicon/istream.c
+++ /dev/null
@@ -1,226 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#include "platform.h"
-#if defined(DIVA_ISTREAM) /* { */
-#include "pc.h"
-#include "pr_pc.h"
-#include "di_defs.h"
-#include "divasync.h"
-#include "di.h"
-#if !defined USE_EXTENDED_DEBUGS
-#include "dimaint.h"
-#else
-#define dprintf
-#endif
-#include "dfifo.h"
-int diva_istream_write(void *context,
-		       int   Id,
-		       void *data,
-		       int length,
-		       int final,
-		       byte usr1,
-		       byte usr2);
-int diva_istream_read(void *context,
-		      int Id,
-		      void *data,
-		      int max_length,
-		      int *final,
-		      byte *usr1,
-		      byte *usr2);
-/* -------------------------------------------------------------------
-   Does provide iStream interface to the client
-   ------------------------------------------------------------------- */
-void diva_xdi_provide_istream_info(ADAPTER *a,
-				   diva_xdi_stream_interface_t *pi) {
-	pi->provided_service = 0;
-}
-/* ------------------------------------------------------------------
-   Does write the data from caller's buffer to the card's
-   stream interface.
-   If synchronous service was requested, then function
-   does return amount of data written to stream.
-   'final' does indicate that piece of data to be written is
-   final part of frame (necessary only by structured datatransfer)
-   return  0 if zero lengh packet was written
-   return -1 if stream is full
-   ------------------------------------------------------------------ */
-int diva_istream_write(void *context,
-		       int Id,
-		       void *data,
-		       int length,
-		       int final,
-		       byte usr1,
-		       byte usr2) {
-	ADAPTER *a = (ADAPTER *)context;
-	int written = 0, to_write = -1;
-	char tmp[4];
-	byte *data_ptr = (byte *)data;
-	for (;;) {
-		a->ram_in_dw(a,
-#ifdef PLATFORM_GT_32BIT
-			      ULongToPtr(a->tx_stream[Id] + a->tx_pos[Id]),
-#else
-			      (void *)(a->tx_stream[Id] + a->tx_pos[Id]),
-#endif
-			      (dword *)&tmp[0],
-			      1);
-		if (tmp[0] & DIVA_DFIFO_READY) { /* No free blocks more */
-			if (to_write < 0)
-				return (-1); /* was not able to write       */
-			break;     /* only part of message was written */
-		}
-		to_write = min(length, DIVA_DFIFO_DATA_SZ);
-		if (to_write) {
-			a->ram_out_buffer(a,
-#ifdef PLATFORM_GT_32BIT
-					   ULongToPtr(a->tx_stream[Id] + a->tx_pos[Id] + 4),
-#else
-					   (void *)(a->tx_stream[Id] + a->tx_pos[Id] + 4),
-#endif
-					   data_ptr,
-					   (word)to_write);
-			length  -= to_write;
-			written  += to_write;
-			data_ptr += to_write;
-		}
-		tmp[1] = (char)to_write;
-		tmp[0] = (tmp[0] & DIVA_DFIFO_WRAP) |
-			DIVA_DFIFO_READY |
-			((!length && final) ? DIVA_DFIFO_LAST : 0);
-		if (tmp[0] & DIVA_DFIFO_LAST) {
-			tmp[2] = usr1;
-			tmp[3] = usr2;
-		}
-		a->ram_out_dw(a,
-#ifdef PLATFORM_GT_32BIT
-			       ULongToPtr(a->tx_stream[Id] + a->tx_pos[Id]),
-#else
-			       (void *)(a->tx_stream[Id] + a->tx_pos[Id]),
-#endif
-			       (dword *)&tmp[0],
-			       1);
-		if (tmp[0] & DIVA_DFIFO_WRAP) {
-			a->tx_pos[Id]  = 0;
-		} else {
-			a->tx_pos[Id] += DIVA_DFIFO_STEP;
-		}
-		if (!length) {
-			break;
-		}
-	}
-	return (written);
-}
-/* -------------------------------------------------------------------
-   In case of SYNCRONOUS service:
-   Does write data from stream in caller's buffer.
-   Does return amount of data written to buffer
-   Final flag is set on return if last part of structured frame
-   was received
-   return 0  if zero packet was received
-   return -1 if stream is empty
-   return -2 if read buffer does not profide sufficient space
-   to accommodate entire segment
-   max_length should be at least 68 bytes
-   ------------------------------------------------------------------- */
-int diva_istream_read(void *context,
-		      int Id,
-		      void *data,
-		      int max_length,
-		      int *final,
-		      byte *usr1,
-		      byte *usr2) {
-	ADAPTER *a = (ADAPTER *)context;
-	int read = 0, to_read = -1;
-	char tmp[4];
-	byte *data_ptr = (byte *)data;
-	*final = 0;
-	for (;;) {
-		a->ram_in_dw(a,
-#ifdef PLATFORM_GT_32BIT
-			      ULongToPtr(a->rx_stream[Id] + a->rx_pos[Id]),
-#else
-			      (void *)(a->rx_stream[Id] + a->rx_pos[Id]),
-#endif
-			      (dword *)&tmp[0],
-			      1);
-		if (tmp[1] > max_length) {
-			if (to_read < 0)
-				return (-2); /* was not able to read */
-			break;
-		}
-		if (!(tmp[0] & DIVA_DFIFO_READY)) {
-			if (to_read < 0)
-				return (-1); /* was not able to read */
-			break;
-		}
-		to_read = min(max_length, (int)tmp[1]);
-		if (to_read) {
-			a->ram_in_buffer(a,
-#ifdef PLATFORM_GT_32BIT
-					 ULongToPtr(a->rx_stream[Id] + a->rx_pos[Id] + 4),
-#else
-					 (void *)(a->rx_stream[Id] + a->rx_pos[Id] + 4),
-#endif
-					 data_ptr,
-					 (word)to_read);
-			max_length -= to_read;
-			read     += to_read;
-			data_ptr  += to_read;
-		}
-		if (tmp[0] & DIVA_DFIFO_LAST) {
-			*final = 1;
-		}
-		tmp[0] &= DIVA_DFIFO_WRAP;
-		a->ram_out_dw(a,
-#ifdef PLATFORM_GT_32BIT
-			      ULongToPtr(a->rx_stream[Id] + a->rx_pos[Id]),
-#else
-			      (void *)(a->rx_stream[Id] + a->rx_pos[Id]),
-#endif
-			      (dword *)&tmp[0],
-			      1);
-		if (tmp[0] & DIVA_DFIFO_WRAP) {
-			a->rx_pos[Id]  = 0;
-		} else {
-			a->rx_pos[Id] += DIVA_DFIFO_STEP;
-		}
-		if (*final) {
-			if (usr1)
-				*usr1 = tmp[2];
-			if (usr2)
-				*usr2 = tmp[3];
-			break;
-		}
-	}
-	return (read);
-}
-/* ---------------------------------------------------------------------
-   Does check if one of streams had caused interrupt and does
-   wake up corresponding application
-   --------------------------------------------------------------------- */
-void pr_stream(ADAPTER *a) {
-}
-#endif /* } */
diff --git a/drivers/isdn/hardware/eicon/kst_ifc.h b/drivers/isdn/hardware/eicon/kst_ifc.h
deleted file mode 100644
index 894fdfda1090..000000000000
--- a/drivers/isdn/hardware/eicon/kst_ifc.h
+++ /dev/null
@@ -1,335 +0,0 @@
-/*
- *
- Copyright (c) Eicon Networks, 2000.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    1.9
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_EICON_TRACE_API__
-#define __DIVA_EICON_TRACE_API__
-
-#define DIVA_TRACE_LINE_TYPE_LEN 64
-#define DIVA_TRACE_IE_LEN        64
-#define DIVA_TRACE_FAX_PRMS_LEN  128
-
-typedef struct _diva_trace_ie {
-	byte length;
-	byte data[DIVA_TRACE_IE_LEN];
-} diva_trace_ie_t;
-
-/*
-  Structure used to represent "State\\BX\\Modem" directory
-  to user.
-*/
-typedef struct _diva_trace_modem_state {
-	dword	ChannelNumber;
-
-	dword	Event;
-
-	dword	Norm;
-
-	dword Options; /* Options received from Application */
-
-	dword	TxSpeed;
-	dword	RxSpeed;
-
-	dword RoundtripMsec;
-
-	dword SymbolRate;
-
-	int		RxLeveldBm;
-	int		EchoLeveldBm;
-
-	dword	SNRdb;
-	dword MAE;
-
-	dword LocalRetrains;
-	dword RemoteRetrains;
-	dword LocalResyncs;
-	dword RemoteResyncs;
-
-	dword DiscReason;
-
-} diva_trace_modem_state_t;
-
-/*
-  Representation of "State\\BX\\FAX" directory
-*/
-typedef struct _diva_trace_fax_state {
-	dword	ChannelNumber;
-	dword Event;
-	dword Page_Counter;
-	dword Features;
-	char Station_ID[DIVA_TRACE_FAX_PRMS_LEN];
-	char Subaddress[DIVA_TRACE_FAX_PRMS_LEN];
-	char Password[DIVA_TRACE_FAX_PRMS_LEN];
-	dword Speed;
-	dword Resolution;
-	dword Paper_Width;
-	dword Paper_Length;
-	dword Scanline_Time;
-	dword Disc_Reason;
-	dword	dummy;
-} diva_trace_fax_state_t;
-
-/*
-  Structure used to represent Interface State in the abstract
-  and interface/D-channel protocol independent form.
-*/
-typedef struct _diva_trace_interface_state {
-	char Layer1[DIVA_TRACE_LINE_TYPE_LEN];
-	char Layer2[DIVA_TRACE_LINE_TYPE_LEN];
-} diva_trace_interface_state_t;
-
-typedef struct _diva_incoming_call_statistics {
-	dword Calls;
-	dword Connected;
-	dword User_Busy;
-	dword Call_Rejected;
-	dword Wrong_Number;
-	dword Incompatible_Dst;
-	dword Out_of_Order;
-	dword Ignored;
-} diva_incoming_call_statistics_t;
-
-typedef struct _diva_outgoing_call_statistics {
-	dword Calls;
-	dword Connected;
-	dword User_Busy;
-	dword No_Answer;
-	dword Wrong_Number;
-	dword Call_Rejected;
-	dword Other_Failures;
-} diva_outgoing_call_statistics_t;
-
-typedef struct _diva_modem_call_statistics {
-	dword Disc_Normal;
-	dword Disc_Unspecified;
-	dword Disc_Busy_Tone;
-	dword Disc_Congestion;
-	dword Disc_Carr_Wait;
-	dword Disc_Trn_Timeout;
-	dword Disc_Incompat;
-	dword Disc_Frame_Rej;
-	dword Disc_V42bis;
-} diva_modem_call_statistics_t;
-
-typedef struct _diva_fax_call_statistics {
-	dword Disc_Normal;
-	dword Disc_Not_Ident;
-	dword Disc_No_Response;
-	dword Disc_Retries;
-	dword Disc_Unexp_Msg;
-	dword Disc_No_Polling;
-	dword Disc_Training;
-	dword Disc_Unexpected;
-	dword Disc_Application;
-	dword Disc_Incompat;
-	dword Disc_No_Command;
-	dword Disc_Long_Msg;
-	dword Disc_Supervisor;
-	dword Disc_SUB_SEP_PWD;
-	dword Disc_Invalid_Msg;
-	dword Disc_Page_Coding;
-	dword Disc_App_Timeout;
-	dword Disc_Unspecified;
-} diva_fax_call_statistics_t;
-
-typedef struct _diva_prot_statistics {
-	dword X_Frames;
-	dword X_Bytes;
-	dword X_Errors;
-	dword R_Frames;
-	dword R_Bytes;
-	dword R_Errors;
-} diva_prot_statistics_t;
-
-typedef struct _diva_ifc_statistics {
-	diva_incoming_call_statistics_t	inc;
-	diva_outgoing_call_statistics_t outg;
-	diva_modem_call_statistics_t mdm;
-	diva_fax_call_statistics_t fax;
-	diva_prot_statistics_t b1;
-	diva_prot_statistics_t b2;
-	diva_prot_statistics_t d1;
-	diva_prot_statistics_t d2;
-} diva_ifc_statistics_t;
-
-/*
-  Structure used to represent "State\\BX" directory
-  to user.
-*/
-typedef struct _diva_trace_line_state {
-	dword	ChannelNumber;
-
-	char Line[DIVA_TRACE_LINE_TYPE_LEN];
-
-	char Framing[DIVA_TRACE_LINE_TYPE_LEN];
-
-	char Layer2[DIVA_TRACE_LINE_TYPE_LEN];
-	char Layer3[DIVA_TRACE_LINE_TYPE_LEN];
-
-	char RemoteAddress[DIVA_TRACE_LINE_TYPE_LEN];
-	char RemoteSubAddress[DIVA_TRACE_LINE_TYPE_LEN];
-
-	char LocalAddress[DIVA_TRACE_LINE_TYPE_LEN];
-	char LocalSubAddress[DIVA_TRACE_LINE_TYPE_LEN];
-
-	diva_trace_ie_t call_BC;
-	diva_trace_ie_t call_HLC;
-	diva_trace_ie_t call_LLC;
-
-	dword Charges;
-
-	dword CallReference;
-
-	dword LastDisconnecCause;
-
-	char UserID[DIVA_TRACE_LINE_TYPE_LEN];
-
-	diva_trace_modem_state_t modem;
-	diva_trace_fax_state_t fax;
-
-	diva_trace_interface_state_t *pInterface;
-
-	diva_ifc_statistics_t *pInterfaceStat;
-
-} diva_trace_line_state_t;
-
-#define DIVA_SUPER_TRACE_NOTIFY_LINE_CHANGE             ('l')
-#define DIVA_SUPER_TRACE_NOTIFY_MODEM_CHANGE            ('m')
-#define DIVA_SUPER_TRACE_NOTIFY_FAX_CHANGE              ('f')
-#define DIVA_SUPER_TRACE_INTERFACE_CHANGE               ('i')
-#define DIVA_SUPER_TRACE_NOTIFY_STAT_CHANGE             ('s')
-#define DIVA_SUPER_TRACE_NOTIFY_MDM_STAT_CHANGE         ('M')
-#define DIVA_SUPER_TRACE_NOTIFY_FAX_STAT_CHANGE         ('F')
-
-struct _diva_strace_library_interface;
-typedef void (*diva_trace_channel_state_change_proc_t)(void *user_context,
-						       struct _diva_strace_library_interface *hLib,
-						       int Adapter,
-						       diva_trace_line_state_t *channel, int notify_subject);
-typedef void (*diva_trace_channel_trace_proc_t)(void *user_context,
-						struct _diva_strace_library_interface *hLib,
-						int Adapter, void *xlog_buffer, int length);
-typedef void (*diva_trace_error_proc_t)(void *user_context,
-					struct _diva_strace_library_interface *hLib,
-					int Adapter,
-					int error, const char *file, int line);
-
-/*
-  This structure creates interface from user to library
-*/
-typedef struct _diva_trace_library_user_interface {
-	void *user_context;
-	diva_trace_channel_state_change_proc_t notify_proc;
-	diva_trace_channel_trace_proc_t trace_proc;
-	diva_trace_error_proc_t error_notify_proc;
-} diva_trace_library_user_interface_t;
-
-/*
-  Interface from Library to User
-*/
-typedef int (*DivaSTraceLibraryStart_proc_t)(void *hLib);
-typedef int (*DivaSTraceLibraryFinit_proc_t)(void *hLib);
-typedef int (*DivaSTraceMessageInput_proc_t)(void *hLib);
-typedef void* (*DivaSTraceGetHandle_proc_t)(void *hLib);
-
-/*
-  Turn Audio Tap trace on/off
-  Channel should be in the range 1 ... Number of Channels
-*/
-typedef int (*DivaSTraceSetAudioTap_proc_t)(void *hLib, int Channel, int on);
-
-/*
-  Turn B-channel trace on/off
-  Channel should be in the range 1 ... Number of Channels
-*/
-typedef int (*DivaSTraceSetBChannel_proc_t)(void *hLib, int Channel, int on);
-
-/*
-  Turn	D-channel (Layer1/Layer2/Layer3) trace on/off
-  Layer1 - All D-channel frames received/sent over the interface
-  inclusive Layer 2 headers, Layer 2 frames and TEI management frames
-  Layer2 - Events from LAPD protocol instance with SAPI of signalling protocol
-  Layer3 - All D-channel frames addressed to assigned to the card TEI and
-  SAPI of signalling protocol, and signalling protocol events.
-*/
-typedef int (*DivaSTraceSetDChannel_proc_t)(void *hLib, int on);
-
-/*
-  Get overall card statistics
-*/
-typedef int (*DivaSTraceGetOutgoingCallStatistics_proc_t)(void *hLib);
-typedef int (*DivaSTraceGetIncomingCallStatistics_proc_t)(void *hLib);
-typedef int (*DivaSTraceGetModemStatistics_proc_t)(void *hLib);
-typedef int (*DivaSTraceGetFaxStatistics_proc_t)(void *hLib);
-typedef int (*DivaSTraceGetBLayer1Statistics_proc_t)(void *hLib);
-typedef int (*DivaSTraceGetBLayer2Statistics_proc_t)(void *hLib);
-typedef int (*DivaSTraceGetDLayer1Statistics_proc_t)(void *hLib);
-typedef int (*DivaSTraceGetDLayer2Statistics_proc_t)(void *hLib);
-
-/*
-  Call control
-*/
-typedef int (*DivaSTraceClearCall_proc_t)(void *hLib, int Channel);
-
-typedef struct _diva_strace_library_interface {
-	void *hLib;
-	DivaSTraceLibraryStart_proc_t DivaSTraceLibraryStart;
-	DivaSTraceLibraryStart_proc_t DivaSTraceLibraryStop;
-	DivaSTraceLibraryFinit_proc_t DivaSTraceLibraryFinit;
-	DivaSTraceMessageInput_proc_t DivaSTraceMessageInput;
-	DivaSTraceGetHandle_proc_t DivaSTraceGetHandle;
-	DivaSTraceSetAudioTap_proc_t DivaSTraceSetAudioTap;
-	DivaSTraceSetBChannel_proc_t DivaSTraceSetBChannel;
-	DivaSTraceSetDChannel_proc_t DivaSTraceSetDChannel;
-	DivaSTraceSetDChannel_proc_t DivaSTraceSetInfo;
-	DivaSTraceGetOutgoingCallStatistics_proc_t \
-	DivaSTraceGetOutgoingCallStatistics;
-	DivaSTraceGetIncomingCallStatistics_proc_t \
-	DivaSTraceGetIncomingCallStatistics;
-	DivaSTraceGetModemStatistics_proc_t \
-	DivaSTraceGetModemStatistics;
-	DivaSTraceGetFaxStatistics_proc_t \
-	DivaSTraceGetFaxStatistics;
-	DivaSTraceGetBLayer1Statistics_proc_t \
-	DivaSTraceGetBLayer1Statistics;
-	DivaSTraceGetBLayer2Statistics_proc_t \
-	DivaSTraceGetBLayer2Statistics;
-	DivaSTraceGetDLayer1Statistics_proc_t \
-	DivaSTraceGetDLayer1Statistics;
-	DivaSTraceGetDLayer2Statistics_proc_t \
-	DivaSTraceGetDLayer2Statistics;
-	DivaSTraceClearCall_proc_t DivaSTraceClearCall;
-} diva_strace_library_interface_t;
-
-/*
-  Create and return Library interface
-*/
-diva_strace_library_interface_t *DivaSTraceLibraryCreateInstance(int Adapter,
-								 const diva_trace_library_user_interface_t *user_proc,
-								 byte *pmem);
-dword DivaSTraceGetMemotyRequirement(int channels);
-
-#define DIVA_MAX_ADAPTERS  64
-#define DIVA_MAX_LINES     32
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/maintidi.c b/drivers/isdn/hardware/eicon/maintidi.c
deleted file mode 100644
index 2ee789f95867..000000000000
--- a/drivers/isdn/hardware/eicon/maintidi.c
+++ /dev/null
@@ -1,2194 +0,0 @@
-/*
- *
- Copyright (c) Eicon Networks, 2000.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    1.9
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#include "platform.h"
-#include "kst_ifc.h"
-#include "di_defs.h"
-#include "maintidi.h"
-#include "pc.h"
-#include "man_defs.h"
-
-
-extern void diva_mnt_internal_dprintf(dword drv_id, dword type, char *p, ...);
-
-#define MODEM_PARSE_ENTRIES  16 /* amount of variables of interest */
-#define FAX_PARSE_ENTRIES    12 /* amount of variables of interest */
-#define LINE_PARSE_ENTRIES   15 /* amount of variables of interest */
-#define STAT_PARSE_ENTRIES   70 /* amount of variables of interest */
-
-/*
-  LOCAL FUNCTIONS
-*/
-static int DivaSTraceLibraryStart(void *hLib);
-static int DivaSTraceLibraryStop(void *hLib);
-static int SuperTraceLibraryFinit(void *hLib);
-static void *SuperTraceGetHandle(void *hLib);
-static int SuperTraceMessageInput(void *hLib);
-static int SuperTraceSetAudioTap(void *hLib, int Channel, int on);
-static int SuperTraceSetBChannel(void *hLib, int Channel, int on);
-static int SuperTraceSetDChannel(void *hLib, int on);
-static int SuperTraceSetInfo(void *hLib, int on);
-static int SuperTraceClearCall(void *hLib, int Channel);
-static int SuperTraceGetOutgoingCallStatistics(void *hLib);
-static int SuperTraceGetIncomingCallStatistics(void *hLib);
-static int SuperTraceGetModemStatistics(void *hLib);
-static int SuperTraceGetFaxStatistics(void *hLib);
-static int SuperTraceGetBLayer1Statistics(void *hLib);
-static int SuperTraceGetBLayer2Statistics(void *hLib);
-static int SuperTraceGetDLayer1Statistics(void *hLib);
-static int SuperTraceGetDLayer2Statistics(void *hLib);
-
-/*
-  LOCAL FUNCTIONS
-*/
-static int ScheduleNextTraceRequest(diva_strace_context_t *pLib);
-static int process_idi_event(diva_strace_context_t *pLib,
-			     diva_man_var_header_t *pVar);
-static int process_idi_info(diva_strace_context_t *pLib,
-			    diva_man_var_header_t *pVar);
-static int diva_modem_event(diva_strace_context_t *pLib, int Channel);
-static int diva_fax_event(diva_strace_context_t *pLib, int Channel);
-static int diva_line_event(diva_strace_context_t *pLib, int Channel);
-static int diva_modem_info(diva_strace_context_t *pLib,
-			   int Channel,
-			   diva_man_var_header_t *pVar);
-static int diva_fax_info(diva_strace_context_t *pLib,
-			 int Channel,
-			 diva_man_var_header_t *pVar);
-static int diva_line_info(diva_strace_context_t *pLib,
-			  int Channel,
-			  diva_man_var_header_t *pVar);
-static int diva_ifc_statistics(diva_strace_context_t *pLib,
-			       diva_man_var_header_t *pVar);
-static diva_man_var_header_t *get_next_var(diva_man_var_header_t *pVar);
-static diva_man_var_header_t *find_var(diva_man_var_header_t *pVar,
-				       const char *name);
-static int diva_strace_read_int(diva_man_var_header_t *pVar, int *var);
-static int diva_strace_read_uint(diva_man_var_header_t *pVar, dword *var);
-static int diva_strace_read_asz(diva_man_var_header_t *pVar, char *var);
-static int diva_strace_read_asc(diva_man_var_header_t *pVar, char *var);
-static int diva_strace_read_ie(diva_man_var_header_t *pVar,
-			       diva_trace_ie_t *var);
-static void diva_create_parse_table(diva_strace_context_t *pLib);
-static void diva_trace_error(diva_strace_context_t *pLib,
-			     int error, const char *file, int line);
-static void diva_trace_notify_user(diva_strace_context_t *pLib,
-				   int Channel,
-				   int notify_subject);
-static int diva_trace_read_variable(diva_man_var_header_t *pVar,
-				    void *variable);
-
-/*
-  Initialize the library and return context
-  of the created trace object that will represent
-  the IDI adapter.
-  Return 0 on error.
-*/
-diva_strace_library_interface_t *DivaSTraceLibraryCreateInstance(int Adapter,
-								 const diva_trace_library_user_interface_t *user_proc,
-								 byte *pmem) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)pmem;
-	int i;
-
-	if (!pLib) {
-		return NULL;
-	}
-
-	pmem += sizeof(*pLib);
-	memset(pLib, 0x00, sizeof(*pLib));
-
-	pLib->Adapter  = Adapter;
-
-	/*
-	  Set up Library Interface
-	*/
-	pLib->instance.hLib                                = pLib;
-	pLib->instance.DivaSTraceLibraryStart              = DivaSTraceLibraryStart;
-	pLib->instance.DivaSTraceLibraryStop               = DivaSTraceLibraryStop;
-	pLib->instance.DivaSTraceLibraryFinit              = SuperTraceLibraryFinit;
-	pLib->instance.DivaSTraceMessageInput              = SuperTraceMessageInput;
-	pLib->instance.DivaSTraceGetHandle                 = SuperTraceGetHandle;
-	pLib->instance.DivaSTraceSetAudioTap               = SuperTraceSetAudioTap;
-	pLib->instance.DivaSTraceSetBChannel               = SuperTraceSetBChannel;
-	pLib->instance.DivaSTraceSetDChannel               = SuperTraceSetDChannel;
-	pLib->instance.DivaSTraceSetInfo                   = SuperTraceSetInfo;
-	pLib->instance.DivaSTraceGetOutgoingCallStatistics = \
-		SuperTraceGetOutgoingCallStatistics;
-	pLib->instance.DivaSTraceGetIncomingCallStatistics = \
-		SuperTraceGetIncomingCallStatistics;
-	pLib->instance.DivaSTraceGetModemStatistics        = \
-		SuperTraceGetModemStatistics;
-	pLib->instance.DivaSTraceGetFaxStatistics          = \
-		SuperTraceGetFaxStatistics;
-	pLib->instance.DivaSTraceGetBLayer1Statistics      = \
-		SuperTraceGetBLayer1Statistics;
-	pLib->instance.DivaSTraceGetBLayer2Statistics      = \
-		SuperTraceGetBLayer2Statistics;
-	pLib->instance.DivaSTraceGetDLayer1Statistics      = \
-		SuperTraceGetDLayer1Statistics;
-	pLib->instance.DivaSTraceGetDLayer2Statistics      = \
-		SuperTraceGetDLayer2Statistics;
-	pLib->instance.DivaSTraceClearCall                 = SuperTraceClearCall;
-
-
-	if (user_proc) {
-		pLib->user_proc_table.user_context      = user_proc->user_context;
-		pLib->user_proc_table.notify_proc       = user_proc->notify_proc;
-		pLib->user_proc_table.trace_proc        = user_proc->trace_proc;
-		pLib->user_proc_table.error_notify_proc = user_proc->error_notify_proc;
-	}
-
-	if (!(pLib->hAdapter = SuperTraceOpenAdapter(Adapter))) {
-		diva_mnt_internal_dprintf(0, DLI_ERR, "Can not open XDI adapter");
-		return NULL;
-	}
-	pLib->Channels = SuperTraceGetNumberOfChannels(pLib->hAdapter);
-
-	/*
-	  Calculate amount of parte table entites necessary to translate
-	  information from all events of onterest
-	*/
-	pLib->parse_entries = (MODEM_PARSE_ENTRIES + FAX_PARSE_ENTRIES + \
-			       STAT_PARSE_ENTRIES + \
-			       LINE_PARSE_ENTRIES + 1) * pLib->Channels;
-	pLib->parse_table = (diva_strace_path2action_t *)pmem;
-
-	for (i = 0; i < 30; i++) {
-		pLib->lines[i].pInterface     = &pLib->Interface;
-		pLib->lines[i].pInterfaceStat = &pLib->InterfaceStat;
-	}
-
-	pLib->e.R = &pLib->RData;
-
-	pLib->req_busy = 1;
-	pLib->rc_ok    = ASSIGN_OK;
-
-	diva_create_parse_table(pLib);
-
-	return ((diva_strace_library_interface_t *)pLib);
-}
-
-static int DivaSTraceLibraryStart(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-
-	return (SuperTraceASSIGN(pLib->hAdapter, pLib->buffer));
-}
-
-/*
-  Return (-1) on error
-  Return (0) if was initiated or pending
-  Return (1) if removal is complete
-*/
-static int DivaSTraceLibraryStop(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-
-	if (!pLib->e.Id) { /* Was never started/assigned */
-		return (1);
-	}
-
-	switch (pLib->removal_state) {
-	case 0:
-		pLib->removal_state = 1;
-		ScheduleNextTraceRequest(pLib);
-		break;
-
-	case 3:
-		return (1);
-	}
-
-	return (0);
-}
-
-static int SuperTraceLibraryFinit(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-	if (pLib) {
-		if (pLib->hAdapter) {
-			SuperTraceCloseAdapter(pLib->hAdapter);
-		}
-		return (0);
-	}
-	return (-1);
-}
-
-static void *SuperTraceGetHandle(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-
-	return (&pLib->e);
-}
-
-/*
-  After library handle object is gone in signaled state
-  this function should be called and will pick up incoming
-  IDI messages (return codes and indications).
-*/
-static int SuperTraceMessageInput(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-	int ret = 0;
-	byte Rc, Ind;
-
-	if (pLib->e.complete == 255) {
-		/*
-		  Process return code
-		*/
-		pLib->req_busy = 0;
-		Rc             = pLib->e.Rc;
-		pLib->e.Rc     = 0;
-
-		if (pLib->removal_state == 2) {
-			pLib->removal_state = 3;
-			return (0);
-		}
-
-		if (Rc != pLib->rc_ok) {
-			int ignore = 0;
-			/*
-			  Auto-detect amount of events/channels and features
-			*/
-			if (pLib->general_b_ch_event == 1) {
-				pLib->general_b_ch_event = 2;
-				ignore = 1;
-			} else if (pLib->general_fax_event == 1) {
-				pLib->general_fax_event = 2;
-				ignore = 1;
-			} else if (pLib->general_mdm_event == 1) {
-				pLib->general_mdm_event = 2;
-				ignore = 1;
-			} else if ((pLib->ChannelsTraceActive < pLib->Channels) && pLib->ChannelsTraceActive) {
-				pLib->ChannelsTraceActive = pLib->Channels;
-				ignore = 1;
-			} else if (pLib->ModemTraceActive < pLib->Channels) {
-				pLib->ModemTraceActive = pLib->Channels;
-				ignore = 1;
-			} else if (pLib->FaxTraceActive < pLib->Channels) {
-				pLib->FaxTraceActive = pLib->Channels;
-				ignore = 1;
-			} else if (pLib->audio_trace_init == 2) {
-				ignore = 1;
-				pLib->audio_trace_init = 1;
-			} else if (pLib->eye_pattern_pending) {
-				pLib->eye_pattern_pending =  0;
-				ignore = 1;
-			} else if (pLib->audio_tap_pending) {
-				pLib->audio_tap_pending = 0;
-				ignore = 1;
-			}
-
-			if (!ignore) {
-				return (-1); /* request failed */
-			}
-		} else {
-			if (pLib->general_b_ch_event == 1) {
-				pLib->ChannelsTraceActive = pLib->Channels;
-				pLib->general_b_ch_event = 2;
-			} else if (pLib->general_fax_event == 1) {
-				pLib->general_fax_event = 2;
-				pLib->FaxTraceActive = pLib->Channels;
-			} else if (pLib->general_mdm_event == 1) {
-				pLib->general_mdm_event = 2;
-				pLib->ModemTraceActive = pLib->Channels;
-			}
-		}
-		if (pLib->audio_trace_init == 2) {
-			pLib->audio_trace_init = 1;
-		}
-		pLib->rc_ok = 0xff; /* default OK after assign was done */
-		if ((ret = ScheduleNextTraceRequest(pLib))) {
-			return (-1);
-		}
-	} else {
-		/*
-		  Process indication
-		  Always 'RNR' indication if return code is pending
-		*/
-		Ind         = pLib->e.Ind;
-		pLib->e.Ind = 0;
-		if (pLib->removal_state) {
-			pLib->e.RNum	= 0;
-			pLib->e.RNR	= 2;
-		} else if (pLib->req_busy) {
-			pLib->e.RNum	= 0;
-			pLib->e.RNR	= 1;
-		} else {
-			if (pLib->e.complete != 0x02) {
-				/*
-				  Look-ahead call, set up buffers
-				*/
-				pLib->e.RNum       = 1;
-				pLib->e.R->P       = (byte *)&pLib->buffer[0];
-				pLib->e.R->PLength = (word)(sizeof(pLib->buffer) - 1);
-
-			} else {
-				/*
-				  Indication reception complete, process it now
-				*/
-				byte *p = (byte *)&pLib->buffer[0];
-				pLib->buffer[pLib->e.R->PLength] = 0; /* terminate I.E. with zero */
-
-				switch (Ind) {
-				case MAN_COMBI_IND: {
-					int total_length    = pLib->e.R->PLength;
-					word  this_ind_length;
-
-					while (total_length > 3 && *p) {
-						Ind = *p++;
-						this_ind_length = (word)p[0] | ((word)p[1] << 8);
-						p += 2;
-
-						switch (Ind) {
-						case MAN_INFO_IND:
-							if (process_idi_info(pLib, (diva_man_var_header_t *)p)) {
-								return (-1);
-							}
-							break;
-						case MAN_EVENT_IND:
-							if (process_idi_event(pLib, (diva_man_var_header_t *)p)) {
-								return (-1);
-							}
-							break;
-						case MAN_TRACE_IND:
-							if (pLib->trace_on == 1) {
-								/*
-								  Ignore first trace event that is result of
-								  EVENT_ON operation
-								*/
-								pLib->trace_on++;
-							} else {
-								/*
-								  Delivery XLOG buffer to application
-								*/
-								if (pLib->user_proc_table.trace_proc) {
-									(*(pLib->user_proc_table.trace_proc))(pLib->user_proc_table.user_context,
-													      &pLib->instance, pLib->Adapter,
-													      p, this_ind_length);
-								}
-							}
-							break;
-						default:
-							diva_mnt_internal_dprintf(0, DLI_ERR, "Unknown IDI Ind (DMA mode): %02x", Ind);
-						}
-						p += (this_ind_length + 1);
-						total_length -= (4 + this_ind_length);
-					}
-				} break;
-				case MAN_INFO_IND:
-					if (process_idi_info(pLib, (diva_man_var_header_t *)p)) {
-						return (-1);
-					}
-					break;
-				case MAN_EVENT_IND:
-					if (process_idi_event(pLib, (diva_man_var_header_t *)p)) {
-						return (-1);
-					}
-					break;
-				case MAN_TRACE_IND:
-					if (pLib->trace_on == 1) {
-						/*
-						  Ignore first trace event that is result of
-						  EVENT_ON operation
-						*/
-						pLib->trace_on++;
-					} else {
-						/*
-						  Delivery XLOG buffer to application
-						*/
-						if (pLib->user_proc_table.trace_proc) {
-							(*(pLib->user_proc_table.trace_proc))(pLib->user_proc_table.user_context,
-											      &pLib->instance, pLib->Adapter,
-											      p, pLib->e.R->PLength);
-						}
-					}
-					break;
-				default:
-					diva_mnt_internal_dprintf(0, DLI_ERR, "Unknown IDI Ind: %02x", Ind);
-				}
-			}
-		}
-	}
-
-	if ((ret = ScheduleNextTraceRequest(pLib))) {
-		return (-1);
-	}
-
-	return (ret);
-}
-
-/*
-  Internal state machine responsible for scheduling of requests
-*/
-static int ScheduleNextTraceRequest(diva_strace_context_t *pLib) {
-	char name[64];
-	int ret = 0;
-	int i;
-
-	if (pLib->req_busy) {
-		return (0);
-	}
-
-	if (pLib->removal_state == 1) {
-		if (SuperTraceREMOVE(pLib->hAdapter)) {
-			pLib->removal_state = 3;
-		} else {
-			pLib->req_busy = 1;
-			pLib->removal_state = 2;
-		}
-		return (0);
-	}
-
-	if (pLib->removal_state) {
-		return (0);
-	}
-
-	if (!pLib->general_b_ch_event) {
-		if ((ret = SuperTraceTraceOnRequest(pLib->hAdapter, "State\\B Event", pLib->buffer))) {
-			return (-1);
-		}
-		pLib->general_b_ch_event = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (!pLib->general_fax_event) {
-		if ((ret = SuperTraceTraceOnRequest(pLib->hAdapter, "State\\FAX Event", pLib->buffer))) {
-			return (-1);
-		}
-		pLib->general_fax_event = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (!pLib->general_mdm_event) {
-		if ((ret = SuperTraceTraceOnRequest(pLib->hAdapter, "State\\Modem Event", pLib->buffer))) {
-			return (-1);
-		}
-		pLib->general_mdm_event = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->ChannelsTraceActive < pLib->Channels) {
-		pLib->ChannelsTraceActive++;
-		sprintf(name, "State\\B%d\\Line", pLib->ChannelsTraceActive);
-		if ((ret = SuperTraceTraceOnRequest(pLib->hAdapter, name, pLib->buffer))) {
-			pLib->ChannelsTraceActive--;
-			return (-1);
-		}
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->ModemTraceActive < pLib->Channels) {
-		pLib->ModemTraceActive++;
-		sprintf(name, "State\\B%d\\Modem\\Event", pLib->ModemTraceActive);
-		if ((ret = SuperTraceTraceOnRequest(pLib->hAdapter, name, pLib->buffer))) {
-			pLib->ModemTraceActive--;
-			return (-1);
-		}
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->FaxTraceActive < pLib->Channels) {
-		pLib->FaxTraceActive++;
-		sprintf(name, "State\\B%d\\FAX\\Event", pLib->FaxTraceActive);
-		if ((ret = SuperTraceTraceOnRequest(pLib->hAdapter, name, pLib->buffer))) {
-			pLib->FaxTraceActive--;
-			return (-1);
-		}
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (!pLib->trace_mask_init) {
-		word tmp = 0x0000;
-		if (SuperTraceWriteVar(pLib->hAdapter,
-				       pLib->buffer,
-				       "Trace\\Event Enable",
-				       &tmp,
-				       0x87, /* MI_BITFLD */
-					sizeof(tmp))) {
-			return (-1);
-		}
-		pLib->trace_mask_init = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (!pLib->audio_trace_init) {
-		dword tmp = 0x00000000;
-		if (SuperTraceWriteVar(pLib->hAdapter,
-				       pLib->buffer,
-				       "Trace\\AudioCh# Enable",
-				       &tmp,
-				       0x87, /* MI_BITFLD */
-					sizeof(tmp))) {
-			return (-1);
-		}
-		pLib->audio_trace_init = 2;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (!pLib->bchannel_init) {
-		dword tmp = 0x00000000;
-		if (SuperTraceWriteVar(pLib->hAdapter,
-				       pLib->buffer,
-				       "Trace\\B-Ch# Enable",
-				       &tmp,
-				       0x87, /* MI_BITFLD */
-					sizeof(tmp))) {
-			return (-1);
-		}
-		pLib->bchannel_init = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (!pLib->trace_length_init) {
-		word tmp = 30;
-		if (SuperTraceWriteVar(pLib->hAdapter,
-				       pLib->buffer,
-				       "Trace\\Max Log Length",
-				       &tmp,
-				       0x82, /* MI_UINT */
-					sizeof(tmp))) {
-			return (-1);
-		}
-		pLib->trace_length_init = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (!pLib->trace_on) {
-		if (SuperTraceTraceOnRequest(pLib->hAdapter,
-					     "Trace\\Log Buffer",
-					     pLib->buffer)) {
-			return (-1);
-		}
-		pLib->trace_on = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->trace_event_mask != pLib->current_trace_event_mask) {
-		if (SuperTraceWriteVar(pLib->hAdapter,
-				       pLib->buffer,
-				       "Trace\\Event Enable",
-				       &pLib->trace_event_mask,
-				       0x87, /* MI_BITFLD */
-					sizeof(pLib->trace_event_mask))) {
-			return (-1);
-		}
-		pLib->current_trace_event_mask = pLib->trace_event_mask;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if ((pLib->audio_tap_pending >= 0) && (pLib->audio_tap_mask != pLib->current_audio_tap_mask)) {
-		if (SuperTraceWriteVar(pLib->hAdapter,
-				       pLib->buffer,
-				       "Trace\\AudioCh# Enable",
-				       &pLib->audio_tap_mask,
-				       0x87, /* MI_BITFLD */
-					sizeof(pLib->audio_tap_mask))) {
-			return (-1);
-		}
-		pLib->current_audio_tap_mask = pLib->audio_tap_mask;
-		pLib->audio_tap_pending = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if ((pLib->eye_pattern_pending >= 0) && (pLib->audio_tap_mask != pLib->current_eye_pattern_mask)) {
-		if (SuperTraceWriteVar(pLib->hAdapter,
-				       pLib->buffer,
-				       "Trace\\EyeCh# Enable",
-				       &pLib->audio_tap_mask,
-				       0x87, /* MI_BITFLD */
-					sizeof(pLib->audio_tap_mask))) {
-			return (-1);
-		}
-		pLib->current_eye_pattern_mask = pLib->audio_tap_mask;
-		pLib->eye_pattern_pending = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->bchannel_trace_mask != pLib->current_bchannel_trace_mask) {
-		if (SuperTraceWriteVar(pLib->hAdapter,
-				       pLib->buffer,
-				       "Trace\\B-Ch# Enable",
-				       &pLib->bchannel_trace_mask,
-				       0x87, /* MI_BITFLD */
-					sizeof(pLib->bchannel_trace_mask))) {
-			return (-1);
-		}
-		pLib->current_bchannel_trace_mask = pLib->bchannel_trace_mask;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (!pLib->trace_events_down) {
-		if (SuperTraceTraceOnRequest(pLib->hAdapter,
-					     "Events Down",
-					     pLib->buffer)) {
-			return (-1);
-		}
-		pLib->trace_events_down = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (!pLib->l1_trace) {
-		if (SuperTraceTraceOnRequest(pLib->hAdapter,
-					     "State\\Layer1",
-					     pLib->buffer)) {
-			return (-1);
-		}
-		pLib->l1_trace = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (!pLib->l2_trace) {
-		if (SuperTraceTraceOnRequest(pLib->hAdapter,
-					     "State\\Layer2 No1",
-					     pLib->buffer)) {
-			return (-1);
-		}
-		pLib->l2_trace = 1;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	for (i = 0; i < 30; i++) {
-		if (pLib->pending_line_status & (1L << i)) {
-			sprintf(name, "State\\B%d", i + 1);
-			if (SuperTraceReadRequest(pLib->hAdapter, name, pLib->buffer)) {
-				return (-1);
-			}
-			pLib->pending_line_status &= ~(1L << i);
-			pLib->req_busy = 1;
-			return (0);
-		}
-		if (pLib->pending_modem_status & (1L << i)) {
-			sprintf(name, "State\\B%d\\Modem", i + 1);
-			if (SuperTraceReadRequest(pLib->hAdapter, name, pLib->buffer)) {
-				return (-1);
-			}
-			pLib->pending_modem_status &= ~(1L << i);
-			pLib->req_busy = 1;
-			return (0);
-		}
-		if (pLib->pending_fax_status & (1L << i)) {
-			sprintf(name, "State\\B%d\\FAX", i + 1);
-			if (SuperTraceReadRequest(pLib->hAdapter, name, pLib->buffer)) {
-				return (-1);
-			}
-			pLib->pending_fax_status &= ~(1L << i);
-			pLib->req_busy = 1;
-			return (0);
-		}
-		if (pLib->clear_call_command & (1L << i)) {
-			sprintf(name, "State\\B%d\\Clear Call", i + 1);
-			if (SuperTraceExecuteRequest(pLib->hAdapter, name, pLib->buffer)) {
-				return (-1);
-			}
-			pLib->clear_call_command &= ~(1L << i);
-			pLib->req_busy = 1;
-			return (0);
-		}
-	}
-
-	if (pLib->outgoing_ifc_stats) {
-		if (SuperTraceReadRequest(pLib->hAdapter,
-					  "Statistics\\Outgoing Calls",
-					  pLib->buffer)) {
-			return (-1);
-		}
-		pLib->outgoing_ifc_stats = 0;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->incoming_ifc_stats) {
-		if (SuperTraceReadRequest(pLib->hAdapter,
-					  "Statistics\\Incoming Calls",
-					  pLib->buffer)) {
-			return (-1);
-		}
-		pLib->incoming_ifc_stats = 0;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->modem_ifc_stats) {
-		if (SuperTraceReadRequest(pLib->hAdapter,
-					  "Statistics\\Modem",
-					  pLib->buffer)) {
-			return (-1);
-		}
-		pLib->modem_ifc_stats = 0;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->fax_ifc_stats) {
-		if (SuperTraceReadRequest(pLib->hAdapter,
-					  "Statistics\\FAX",
-					  pLib->buffer)) {
-			return (-1);
-		}
-		pLib->fax_ifc_stats = 0;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->b1_ifc_stats) {
-		if (SuperTraceReadRequest(pLib->hAdapter,
-					  "Statistics\\B-Layer1",
-					  pLib->buffer)) {
-			return (-1);
-		}
-		pLib->b1_ifc_stats = 0;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->b2_ifc_stats) {
-		if (SuperTraceReadRequest(pLib->hAdapter,
-					  "Statistics\\B-Layer2",
-					  pLib->buffer)) {
-			return (-1);
-		}
-		pLib->b2_ifc_stats = 0;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->d1_ifc_stats) {
-		if (SuperTraceReadRequest(pLib->hAdapter,
-					  "Statistics\\D-Layer1",
-					  pLib->buffer)) {
-			return (-1);
-		}
-		pLib->d1_ifc_stats = 0;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (pLib->d2_ifc_stats) {
-		if (SuperTraceReadRequest(pLib->hAdapter,
-					  "Statistics\\D-Layer2",
-					  pLib->buffer)) {
-			return (-1);
-		}
-		pLib->d2_ifc_stats = 0;
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	if (!pLib->IncomingCallsCallsActive) {
-		pLib->IncomingCallsCallsActive = 1;
-		sprintf(name, "%s", "Statistics\\Incoming Calls\\Calls");
-		if ((ret = SuperTraceTraceOnRequest(pLib->hAdapter, name, pLib->buffer))) {
-			pLib->IncomingCallsCallsActive = 0;
-			return (-1);
-		}
-		pLib->req_busy = 1;
-		return (0);
-	}
-	if (!pLib->IncomingCallsConnectedActive) {
-		pLib->IncomingCallsConnectedActive = 1;
-		sprintf(name, "%s", "Statistics\\Incoming Calls\\Connected");
-		if ((ret = SuperTraceTraceOnRequest(pLib->hAdapter, name, pLib->buffer))) {
-			pLib->IncomingCallsConnectedActive = 0;
-			return (-1);
-		}
-		pLib->req_busy = 1;
-		return (0);
-	}
-	if (!pLib->OutgoingCallsCallsActive) {
-		pLib->OutgoingCallsCallsActive = 1;
-		sprintf(name, "%s", "Statistics\\Outgoing Calls\\Calls");
-		if ((ret = SuperTraceTraceOnRequest(pLib->hAdapter, name, pLib->buffer))) {
-			pLib->OutgoingCallsCallsActive = 0;
-			return (-1);
-		}
-		pLib->req_busy = 1;
-		return (0);
-	}
-	if (!pLib->OutgoingCallsConnectedActive) {
-		pLib->OutgoingCallsConnectedActive = 1;
-		sprintf(name, "%s", "Statistics\\Outgoing Calls\\Connected");
-		if ((ret = SuperTraceTraceOnRequest(pLib->hAdapter, name, pLib->buffer))) {
-			pLib->OutgoingCallsConnectedActive = 0;
-			return (-1);
-		}
-		pLib->req_busy = 1;
-		return (0);
-	}
-
-	return (0);
-}
-
-static int process_idi_event(diva_strace_context_t *pLib,
-			     diva_man_var_header_t *pVar) {
-	const char *path = (char *)&pVar->path_length + 1;
-	char name[64];
-	int i;
-
-	if (!strncmp("State\\B Event", path, pVar->path_length)) {
-		dword ch_id;
-		if (!diva_trace_read_variable(pVar, &ch_id)) {
-			if (!pLib->line_init_event && !pLib->pending_line_status) {
-				for (i = 1; i <= pLib->Channels; i++) {
-					diva_line_event(pLib, i);
-				}
-				return (0);
-			} else if (ch_id && ch_id <= pLib->Channels) {
-				return (diva_line_event(pLib, (int)ch_id));
-			}
-			return (0);
-		}
-		return (-1);
-	}
-
-	if (!strncmp("State\\FAX Event", path, pVar->path_length)) {
-		dword ch_id;
-		if (!diva_trace_read_variable(pVar, &ch_id)) {
-			if (!pLib->pending_fax_status && !pLib->fax_init_event) {
-				for (i = 1; i <= pLib->Channels; i++) {
-					diva_fax_event(pLib, i);
-				}
-				return (0);
-			} else if (ch_id && ch_id <= pLib->Channels) {
-				return (diva_fax_event(pLib, (int)ch_id));
-			}
-			return (0);
-		}
-		return (-1);
-	}
-
-	if (!strncmp("State\\Modem Event", path, pVar->path_length)) {
-		dword ch_id;
-		if (!diva_trace_read_variable(pVar, &ch_id)) {
-			if (!pLib->pending_modem_status && !pLib->modem_init_event) {
-				for (i = 1; i <= pLib->Channels; i++) {
-					diva_modem_event(pLib, i);
-				}
-				return (0);
-			} else if (ch_id && ch_id <= pLib->Channels) {
-				return (diva_modem_event(pLib, (int)ch_id));
-			}
-			return (0);
-		}
-		return (-1);
-	}
-
-	/*
-	  First look for Line Event
-	*/
-	for (i = 1; i <= pLib->Channels; i++) {
-		sprintf(name, "State\\B%d\\Line", i);
-		if (find_var(pVar, name)) {
-			return (diva_line_event(pLib, i));
-		}
-	}
-
-	/*
-	  Look for Moden Progress Event
-	*/
-	for (i = 1; i <= pLib->Channels; i++) {
-		sprintf(name, "State\\B%d\\Modem\\Event", i);
-		if (find_var(pVar, name)) {
-			return (diva_modem_event(pLib, i));
-		}
-	}
-
-	/*
-	  Look for Fax Event
-	*/
-	for (i = 1; i <= pLib->Channels; i++) {
-		sprintf(name, "State\\B%d\\FAX\\Event", i);
-		if (find_var(pVar, name)) {
-			return (diva_fax_event(pLib, i));
-		}
-	}
-
-	/*
-	  Notification about loss of events
-	*/
-	if (!strncmp("Events Down", path, pVar->path_length)) {
-		if (pLib->trace_events_down == 1) {
-			pLib->trace_events_down = 2;
-		} else {
-			diva_trace_error(pLib, 1, "Events Down", 0);
-		}
-		return (0);
-	}
-
-	if (!strncmp("State\\Layer1", path, pVar->path_length)) {
-		diva_strace_read_asz(pVar, &pLib->lines[0].pInterface->Layer1[0]);
-		if (pLib->l1_trace == 1) {
-			pLib->l1_trace = 2;
-		} else {
-			diva_trace_notify_user(pLib, 0, DIVA_SUPER_TRACE_INTERFACE_CHANGE);
-		}
-		return (0);
-	}
-	if (!strncmp("State\\Layer2 No1", path, pVar->path_length)) {
-		char *tmp = &pLib->lines[0].pInterface->Layer2[0];
-		dword l2_state;
-		if (diva_strace_read_uint(pVar, &l2_state))
-			return -1;
-
-		switch (l2_state) {
-		case 0:
-			strcpy(tmp, "Idle");
-			break;
-		case 1:
-			strcpy(tmp, "Layer2 UP");
-			break;
-		case 2:
-			strcpy(tmp, "Layer2 Disconnecting");
-			break;
-		case 3:
-			strcpy(tmp, "Layer2 Connecting");
-			break;
-		case 4:
-			strcpy(tmp, "SPID Initializing");
-			break;
-		case 5:
-			strcpy(tmp, "SPID Initialised");
-			break;
-		case 6:
-			strcpy(tmp, "Layer2 Connecting");
-			break;
-
-		case  7:
-			strcpy(tmp, "Auto SPID Stopped");
-			break;
-
-		case  8:
-			strcpy(tmp, "Auto SPID Idle");
-			break;
-
-		case  9:
-			strcpy(tmp, "Auto SPID Requested");
-			break;
-
-		case  10:
-			strcpy(tmp, "Auto SPID Delivery");
-			break;
-
-		case 11:
-			strcpy(tmp, "Auto SPID Complete");
-			break;
-
-		default:
-			sprintf(tmp, "U:%d", (int)l2_state);
-		}
-		if (pLib->l2_trace == 1) {
-			pLib->l2_trace = 2;
-		} else {
-			diva_trace_notify_user(pLib, 0, DIVA_SUPER_TRACE_INTERFACE_CHANGE);
-		}
-		return (0);
-	}
-
-	if (!strncmp("Statistics\\Incoming Calls\\Calls", path, pVar->path_length) ||
-	    !strncmp("Statistics\\Incoming Calls\\Connected", path, pVar->path_length)) {
-		return (SuperTraceGetIncomingCallStatistics(pLib));
-	}
-
-	if (!strncmp("Statistics\\Outgoing Calls\\Calls", path, pVar->path_length) ||
-	    !strncmp("Statistics\\Outgoing Calls\\Connected", path, pVar->path_length)) {
-		return (SuperTraceGetOutgoingCallStatistics(pLib));
-	}
-
-	return (-1);
-}
-
-static int diva_line_event(diva_strace_context_t *pLib, int Channel) {
-	pLib->pending_line_status |= (1L << (Channel - 1));
-	return (0);
-}
-
-static int diva_modem_event(diva_strace_context_t *pLib, int Channel) {
-	pLib->pending_modem_status |= (1L << (Channel - 1));
-	return (0);
-}
-
-static int diva_fax_event(diva_strace_context_t *pLib, int Channel) {
-	pLib->pending_fax_status |= (1L << (Channel - 1));
-	return (0);
-}
-
-/*
-  Process INFO indications that arrive from the card
-  Uses path of first I.E. to detect the source of the
-  infication
-*/
-static int process_idi_info(diva_strace_context_t *pLib,
-			    diva_man_var_header_t *pVar) {
-	const char *path = (char *)&pVar->path_length + 1;
-	char name[64];
-	int i, len;
-
-	/*
-	  First look for Modem Status Info
-	*/
-	for (i = pLib->Channels; i > 0; i--) {
-		len = sprintf(name, "State\\B%d\\Modem", i);
-		if (!strncmp(name, path, len)) {
-			return (diva_modem_info(pLib, i, pVar));
-		}
-	}
-
-	/*
-	  Look for Fax Status Info
-	*/
-	for (i = pLib->Channels; i > 0; i--) {
-		len = sprintf(name, "State\\B%d\\FAX", i);
-		if (!strncmp(name, path, len)) {
-			return (diva_fax_info(pLib, i, pVar));
-		}
-	}
-
-	/*
-	  Look for Line Status Info
-	*/
-	for (i = pLib->Channels; i > 0; i--) {
-		len = sprintf(name, "State\\B%d", i);
-		if (!strncmp(name, path, len)) {
-			return (diva_line_info(pLib, i, pVar));
-		}
-	}
-
-	if (!diva_ifc_statistics(pLib, pVar)) {
-		return (0);
-	}
-
-	return (-1);
-}
-
-/*
-  MODEM INSTANCE STATE UPDATE
-
-  Update Modem Status Information and issue notification to user,
-  that will inform about change in the state of modem instance, that is
-  associuated with this channel
-*/
-static int diva_modem_info(diva_strace_context_t *pLib,
-			   int Channel,
-			   diva_man_var_header_t *pVar) {
-	diva_man_var_header_t *cur;
-	int i, nr = Channel - 1;
-
-	for (i  = pLib->modem_parse_entry_first[nr];
-	     i <= pLib->modem_parse_entry_last[nr]; i++) {
-		if ((cur = find_var(pVar, pLib->parse_table[i].path))) {
-			if (diva_trace_read_variable(cur, pLib->parse_table[i].variable)) {
-				diva_trace_error(pLib, -3, __FILE__, __LINE__);
-				return (-1);
-			}
-		} else {
-			diva_trace_error(pLib, -2, __FILE__, __LINE__);
-			return (-1);
-		}
-	}
-
-	/*
-	  We do not use first event to notify user - this is the event that is
-	  generated as result of EVENT ON operation and is used only to initialize
-	  internal variables of application
-	*/
-	if (pLib->modem_init_event & (1L << nr)) {
-		diva_trace_notify_user(pLib, nr, DIVA_SUPER_TRACE_NOTIFY_MODEM_CHANGE);
-	} else {
-		pLib->modem_init_event |= (1L << nr);
-	}
-
-	return (0);
-}
-
-static int diva_fax_info(diva_strace_context_t *pLib,
-			 int Channel,
-			 diva_man_var_header_t *pVar) {
-	diva_man_var_header_t *cur;
-	int i, nr = Channel - 1;
-
-	for (i  = pLib->fax_parse_entry_first[nr];
-	     i <= pLib->fax_parse_entry_last[nr]; i++) {
-		if ((cur = find_var(pVar, pLib->parse_table[i].path))) {
-			if (diva_trace_read_variable(cur, pLib->parse_table[i].variable)) {
-				diva_trace_error(pLib, -3, __FILE__, __LINE__);
-				return (-1);
-			}
-		} else {
-			diva_trace_error(pLib, -2, __FILE__, __LINE__);
-			return (-1);
-		}
-	}
-
-	/*
-	  We do not use first event to notify user - this is the event that is
-	  generated as result of EVENT ON operation and is used only to initialize
-	  internal variables of application
-	*/
-	if (pLib->fax_init_event & (1L << nr)) {
-		diva_trace_notify_user(pLib, nr, DIVA_SUPER_TRACE_NOTIFY_FAX_CHANGE);
-	} else {
-		pLib->fax_init_event |= (1L << nr);
-	}
-
-	return (0);
-}
-
-/*
-  LINE STATE UPDATE
-  Update Line Status Information and issue notification to user,
-  that will inform about change in the line state.
-*/
-static int diva_line_info(diva_strace_context_t *pLib,
-			  int Channel,
-			  diva_man_var_header_t *pVar) {
-	diva_man_var_header_t *cur;
-	int i, nr = Channel - 1;
-
-	for (i = pLib->line_parse_entry_first[nr];
-	     i <= pLib->line_parse_entry_last[nr]; i++) {
-		if ((cur = find_var(pVar, pLib->parse_table[i].path))) {
-			if (diva_trace_read_variable(cur, pLib->parse_table[i].variable)) {
-				diva_trace_error(pLib, -3, __FILE__, __LINE__);
-				return (-1);
-			}
-		} else {
-			diva_trace_error(pLib, -2 , __FILE__, __LINE__);
-			return (-1);
-		}
-	}
-
-	/*
-	  We do not use first event to notify user - this is the event that is
-	  generated as result of EVENT ON operation and is used only to initialize
-	  internal variables of application
-
-	  Exception is is if the line is "online". In this case we have to notify
-	  user about this confition.
-	*/
-	if (pLib->line_init_event & (1L << nr)) {
-		diva_trace_notify_user(pLib, nr, DIVA_SUPER_TRACE_NOTIFY_LINE_CHANGE);
-	} else {
-		pLib->line_init_event |= (1L << nr);
-		if (strcmp(&pLib->lines[nr].Line[0], "Idle")) {
-			diva_trace_notify_user(pLib, nr, DIVA_SUPER_TRACE_NOTIFY_LINE_CHANGE);
-		}
-	}
-
-	return (0);
-}
-
-/*
-  Move position to next vatianle in the chain
-*/
-static diva_man_var_header_t *get_next_var(diva_man_var_header_t *pVar) {
-	byte *msg = (byte *)pVar;
-	byte *start;
-	int msg_length;
-
-	if (*msg != ESC) return NULL;
-
-	start = msg + 2;
-	msg_length = *(msg + 1);
-	msg = (start + msg_length);
-
-	if (*msg != ESC) return NULL;
-
-	return ((diva_man_var_header_t *)msg);
-}
-
-/*
-  Move position to variable with given name
-*/
-static diva_man_var_header_t *find_var(diva_man_var_header_t *pVar,
-				       const char *name) {
-	const char *path;
-
-	do {
-		path = (char *)&pVar->path_length + 1;
-
-		if (!strncmp(name, path, pVar->path_length)) {
-			break;
-		}
-	} while ((pVar = get_next_var(pVar)));
-
-	return (pVar);
-}
-
-static void diva_create_line_parse_table(diva_strace_context_t *pLib,
-					 int Channel) {
-	diva_trace_line_state_t *pLine = &pLib->lines[Channel];
-	int nr = Channel + 1;
-
-	if ((pLib->cur_parse_entry + LINE_PARSE_ENTRIES) >= pLib->parse_entries) {
-		diva_trace_error(pLib, -1, __FILE__, __LINE__);
-		return;
-	}
-
-	pLine->ChannelNumber = nr;
-
-	pLib->line_parse_entry_first[Channel] = pLib->cur_parse_entry;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Framing", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pLine->Framing[0];
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Line", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pLine->Line[0];
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Layer2", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pLine->Layer2[0];
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Layer3", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pLine->Layer3[0];
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Remote Address", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLine->RemoteAddress[0];
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Remote SubAddr", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLine->RemoteSubAddress[0];
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Local Address", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLine->LocalAddress[0];
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Local SubAddr", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLine->LocalSubAddress[0];
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\BC", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pLine->call_BC;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\HLC", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pLine->call_HLC;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\LLC", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pLine->call_LLC;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Charges", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pLine->Charges;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Call Reference", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pLine->CallReference;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Last Disc Cause", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLine->LastDisconnecCause;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\User ID", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pLine->UserID[0];
-
-	pLib->line_parse_entry_last[Channel] = pLib->cur_parse_entry - 1;
-}
-
-static void diva_create_fax_parse_table(diva_strace_context_t *pLib,
-					int Channel) {
-	diva_trace_fax_state_t *pFax = &pLib->lines[Channel].fax;
-	int nr = Channel + 1;
-
-	if ((pLib->cur_parse_entry + FAX_PARSE_ENTRIES) >= pLib->parse_entries) {
-		diva_trace_error(pLib, -1, __FILE__, __LINE__);
-		return;
-	}
-	pFax->ChannelNumber = nr;
-
-	pLib->fax_parse_entry_first[Channel] = pLib->cur_parse_entry;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Event", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Event;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Page Counter", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Page_Counter;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Features", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Features;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Station ID", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Station_ID[0];
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Subaddress", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Subaddress[0];
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Password", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Password[0];
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Speed", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Speed;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Resolution", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Resolution;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Paper Width", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Paper_Width;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Paper Length", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Paper_Length;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Scanline Time", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Scanline_Time;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\FAX\\Disc Reason", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pFax->Disc_Reason;
-
-	pLib->fax_parse_entry_last[Channel] = pLib->cur_parse_entry - 1;
-}
-
-static void diva_create_modem_parse_table(diva_strace_context_t *pLib,
-					  int Channel) {
-	diva_trace_modem_state_t *pModem = &pLib->lines[Channel].modem;
-	int nr = Channel + 1;
-
-	if ((pLib->cur_parse_entry + MODEM_PARSE_ENTRIES) >= pLib->parse_entries) {
-		diva_trace_error(pLib, -1, __FILE__, __LINE__);
-		return;
-	}
-	pModem->ChannelNumber = nr;
-
-	pLib->modem_parse_entry_first[Channel] = pLib->cur_parse_entry;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\Event", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->Event;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\Norm", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->Norm;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\Options", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->Options;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\TX Speed", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->TxSpeed;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\RX Speed", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->RxSpeed;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\Roundtrip ms", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->RoundtripMsec;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\Symbol Rate", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->SymbolRate;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\RX Level dBm", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->RxLeveldBm;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\Echo Level dBm", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->EchoLeveldBm;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\SNR dB", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->SNRdb;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\MAE", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->MAE;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\Local Retrains", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->LocalRetrains;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\Remote Retrains", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->RemoteRetrains;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\Local Resyncs", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->LocalResyncs;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\Remote Resyncs", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->RemoteResyncs;
-
-	sprintf(pLib->parse_table[pLib->cur_parse_entry].path,
-		"State\\B%d\\Modem\\Disc Reason", nr);
-	pLib->parse_table[pLib->cur_parse_entry++].variable = &pModem->DiscReason;
-
-	pLib->modem_parse_entry_last[Channel] = pLib->cur_parse_entry - 1;
-}
-
-static void diva_create_parse_table(diva_strace_context_t *pLib) {
-	int i;
-
-	for (i = 0; i < pLib->Channels; i++) {
-		diva_create_line_parse_table(pLib, i);
-		diva_create_modem_parse_table(pLib, i);
-		diva_create_fax_parse_table(pLib, i);
-	}
-
-	pLib->statistic_parse_first = pLib->cur_parse_entry;
-
-	/*
-	  Outgoing Calls
-	*/
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Outgoing Calls\\Calls");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.outg.Calls;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Outgoing Calls\\Connected");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.outg.Connected;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Outgoing Calls\\User Busy");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.outg.User_Busy;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Outgoing Calls\\No Answer");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.outg.No_Answer;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Outgoing Calls\\Wrong Number");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.outg.Wrong_Number;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Outgoing Calls\\Call Rejected");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.outg.Call_Rejected;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Outgoing Calls\\Other Failures");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.outg.Other_Failures;
-
-	/*
-	  Incoming Calls
-	*/
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Incoming Calls\\Calls");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.inc.Calls;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Incoming Calls\\Connected");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.inc.Connected;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Incoming Calls\\User Busy");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.inc.User_Busy;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Incoming Calls\\Call Rejected");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.inc.Call_Rejected;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Incoming Calls\\Wrong Number");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.inc.Wrong_Number;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Incoming Calls\\Incompatible Dst");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.inc.Incompatible_Dst;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Incoming Calls\\Out of Order");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.inc.Out_of_Order;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Incoming Calls\\Ignored");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.inc.Ignored;
-
-	/*
-	  Modem Statistics
-	*/
-	pLib->mdm_statistic_parse_first = pLib->cur_parse_entry;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Modem\\Disc Normal");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.mdm.Disc_Normal;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Modem\\Disc Unspecified");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.mdm.Disc_Unspecified;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Modem\\Disc Busy Tone");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.mdm.Disc_Busy_Tone;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Modem\\Disc Congestion");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.mdm.Disc_Congestion;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Modem\\Disc Carr. Wait");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.mdm.Disc_Carr_Wait;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Modem\\Disc Trn Timeout");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.mdm.Disc_Trn_Timeout;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Modem\\Disc Incompat.");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.mdm.Disc_Incompat;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Modem\\Disc Frame Rej.");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.mdm.Disc_Frame_Rej;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\Modem\\Disc V42bis");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.mdm.Disc_V42bis;
-
-	pLib->mdm_statistic_parse_last  = pLib->cur_parse_entry - 1;
-
-	/*
-	  Fax Statistics
-	*/
-	pLib->fax_statistic_parse_first = pLib->cur_parse_entry;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Normal");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Normal;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Not Ident.");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Not_Ident;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc No Response");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_No_Response;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Retries");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Retries;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Unexp. Msg.");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Unexp_Msg;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc No Polling.");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_No_Polling;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Training");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Training;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Unexpected");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Unexpected;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Application");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Application;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Incompat.");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Incompat;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc No Command");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_No_Command;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Long Msg");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Long_Msg;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Supervisor");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Supervisor;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc SUB SEP PWD");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_SUB_SEP_PWD;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Invalid Msg");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Invalid_Msg;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Page Coding");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Page_Coding;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc App Timeout");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_App_Timeout;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\FAX\\Disc Unspecified");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.fax.Disc_Unspecified;
-
-	pLib->fax_statistic_parse_last  = pLib->cur_parse_entry - 1;
-
-	/*
-	  B-Layer1"
-	*/
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer1\\X-Frames");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b1.X_Frames;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer1\\X-Bytes");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b1.X_Bytes;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer1\\X-Errors");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b1.X_Errors;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer1\\R-Frames");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b1.R_Frames;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer1\\R-Bytes");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b1.R_Bytes;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer1\\R-Errors");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b1.R_Errors;
-
-	/*
-	  B-Layer2
-	*/
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer2\\X-Frames");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b2.X_Frames;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer2\\X-Bytes");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b2.X_Bytes;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer2\\X-Errors");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b2.X_Errors;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer2\\R-Frames");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b2.R_Frames;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer2\\R-Bytes");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b2.R_Bytes;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\B-Layer2\\R-Errors");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.b2.R_Errors;
-
-	/*
-	  D-Layer1
-	*/
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer1\\X-Frames");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d1.X_Frames;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer1\\X-Bytes");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d1.X_Bytes;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer1\\X-Errors");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d1.X_Errors;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer1\\R-Frames");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d1.R_Frames;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer1\\R-Bytes");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d1.R_Bytes;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer1\\R-Errors");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d1.R_Errors;
-
-	/*
-	  D-Layer2
-	*/
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer2\\X-Frames");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d2.X_Frames;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer2\\X-Bytes");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d2.X_Bytes;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer2\\X-Errors");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d2.X_Errors;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer2\\R-Frames");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d2.R_Frames;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer2\\R-Bytes");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d2.R_Bytes;
-
-	strcpy(pLib->parse_table[pLib->cur_parse_entry].path,
-	       "Statistics\\D-Layer2\\R-Errors");
-	pLib->parse_table[pLib->cur_parse_entry++].variable = \
-		&pLib->InterfaceStat.d2.R_Errors;
-
-
-	pLib->statistic_parse_last  = pLib->cur_parse_entry - 1;
-}
-
-static void diva_trace_error(diva_strace_context_t *pLib,
-			     int error, const char *file, int line) {
-	if (pLib->user_proc_table.error_notify_proc) {
-		(*(pLib->user_proc_table.error_notify_proc))(\
-			pLib->user_proc_table.user_context,
-			&pLib->instance, pLib->Adapter,
-			error, file, line);
-	}
-}
-
-/*
-  Delivery notification to user
-*/
-static void diva_trace_notify_user(diva_strace_context_t *pLib,
-				   int Channel,
-				   int notify_subject) {
-	if (pLib->user_proc_table.notify_proc) {
-		(*(pLib->user_proc_table.notify_proc))(pLib->user_proc_table.user_context,
-						       &pLib->instance,
-						       pLib->Adapter,
-						       &pLib->lines[Channel],
-						       notify_subject);
-	}
-}
-
-/*
-  Read variable value to they destination based on the variable type
-*/
-static int diva_trace_read_variable(diva_man_var_header_t *pVar,
-				    void *variable) {
-	switch (pVar->type) {
-	case 0x03: /* MI_ASCIIZ - syting                               */
-		return (diva_strace_read_asz(pVar, (char *)variable));
-	case 0x04: /* MI_ASCII  - string                               */
-		return (diva_strace_read_asc(pVar, (char *)variable));
-	case 0x05: /* MI_NUMBER - counted sequence of bytes            */
-		return (diva_strace_read_ie(pVar, (diva_trace_ie_t *)variable));
-	case 0x81: /* MI_INT    - signed integer                       */
-		return (diva_strace_read_int(pVar, (int *)variable));
-	case 0x82: /* MI_UINT   - unsigned integer                     */
-		return (diva_strace_read_uint(pVar, (dword *)variable));
-	case 0x83: /* MI_HINT   - unsigned integer, hex representetion */
-		return (diva_strace_read_uint(pVar, (dword *)variable));
-	case 0x87: /* MI_BITFLD - unsigned integer, bit representation */
-		return (diva_strace_read_uint(pVar, (dword *)variable));
-	}
-
-	/*
-	  This type of variable is not handled, indicate error
-	  Or one problem in management interface, or in application recodeing
-	  table, or this application should handle it.
-	*/
-	return (-1);
-}
-
-/*
-  Read signed integer to destination
-*/
-static int diva_strace_read_int(diva_man_var_header_t *pVar, int *var) {
-	byte *ptr = (char *)&pVar->path_length;
-	int value;
-
-	ptr += (pVar->path_length + 1);
-
-	switch (pVar->value_length) {
-	case 1:
-		value = *(char *)ptr;
-		break;
-
-	case 2:
-		value = (short)GET_WORD(ptr);
-		break;
-
-	case 4:
-		value = (int)GET_DWORD(ptr);
-		break;
-
-	default:
-		return (-1);
-	}
-
-	*var = value;
-
-	return (0);
-}
-
-static int diva_strace_read_uint(diva_man_var_header_t *pVar, dword *var) {
-	byte *ptr = (char *)&pVar->path_length;
-	dword value;
-
-	ptr += (pVar->path_length + 1);
-
-	switch (pVar->value_length) {
-	case 1:
-		value = (byte)(*ptr);
-		break;
-
-	case 2:
-		value = (word)GET_WORD(ptr);
-		break;
-
-	case 3:
-		value  = (dword)GET_DWORD(ptr);
-		value &= 0x00ffffff;
-		break;
-
-	case 4:
-		value = (dword)GET_DWORD(ptr);
-		break;
-
-	default:
-		return (-1);
-	}
-
-	*var = value;
-
-	return (0);
-}
-
-/*
-  Read zero terminated ASCII string
-*/
-static int diva_strace_read_asz(diva_man_var_header_t *pVar, char *var) {
-	char *ptr = (char *)&pVar->path_length;
-	int length;
-
-	ptr += (pVar->path_length + 1);
-
-	if (!(length = pVar->value_length)) {
-		length = strlen(ptr);
-	}
-	memcpy(var, ptr, length);
-	var[length] = 0;
-
-	return (0);
-}
-
-/*
-  Read counted (with leading length byte) ASCII string
-*/
-static int diva_strace_read_asc(diva_man_var_header_t *pVar, char *var) {
-	char *ptr = (char *)&pVar->path_length;
-
-	ptr += (pVar->path_length + 1);
-	memcpy(var, ptr + 1, *ptr);
-	var[(int)*ptr] = 0;
-
-	return (0);
-}
-
-/*
-  Read one information element - i.e. one string of byte values with
-  one length byte in front
-*/
-static int diva_strace_read_ie(diva_man_var_header_t *pVar,
-			       diva_trace_ie_t *var) {
-	char *ptr = (char *)&pVar->path_length;
-
-	ptr += (pVar->path_length + 1);
-
-	var->length = *ptr;
-	memcpy(&var->data[0], ptr + 1, *ptr);
-
-	return (0);
-}
-
-static int SuperTraceSetAudioTap(void *hLib, int Channel, int on) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-
-	if ((Channel < 1) || (Channel > pLib->Channels)) {
-		return (-1);
-	}
-	Channel--;
-
-	if (on) {
-		pLib->audio_tap_mask |=  (1L << Channel);
-	} else {
-		pLib->audio_tap_mask &= ~(1L << Channel);
-	}
-
-	/*
-	  EYE patterns have TM_M_DATA set as additional
-	  condition
-	*/
-	if (pLib->audio_tap_mask) {
-		pLib->trace_event_mask |= TM_M_DATA;
-	} else {
-		pLib->trace_event_mask &= ~TM_M_DATA;
-	}
-
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-static int SuperTraceSetBChannel(void *hLib, int Channel, int on) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-
-	if ((Channel < 1) || (Channel > pLib->Channels)) {
-		return (-1);
-	}
-	Channel--;
-
-	if (on) {
-		pLib->bchannel_trace_mask |=  (1L << Channel);
-	} else {
-		pLib->bchannel_trace_mask &= ~(1L << Channel);
-	}
-
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-static int SuperTraceSetDChannel(void *hLib, int on) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-
-	if (on) {
-		pLib->trace_event_mask |= (TM_D_CHAN | TM_C_COMM | TM_DL_ERR | TM_LAYER1);
-	} else {
-		pLib->trace_event_mask &= ~(TM_D_CHAN | TM_C_COMM | TM_DL_ERR | TM_LAYER1);
-	}
-
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-static int SuperTraceSetInfo(void *hLib, int on) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-
-	if (on) {
-		pLib->trace_event_mask |= TM_STRING;
-	} else {
-		pLib->trace_event_mask &= ~TM_STRING;
-	}
-
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-static int SuperTraceClearCall(void *hLib, int Channel) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-
-	if ((Channel < 1) || (Channel > pLib->Channels)) {
-		return (-1);
-	}
-	Channel--;
-
-	pLib->clear_call_command |= (1L << Channel);
-
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-/*
-  Parse and update cumulative statistice
-*/
-static int diva_ifc_statistics(diva_strace_context_t *pLib,
-			       diva_man_var_header_t *pVar) {
-	diva_man_var_header_t *cur;
-	int i, one_updated = 0, mdm_updated = 0, fax_updated = 0;
-
-	for (i  = pLib->statistic_parse_first; i <= pLib->statistic_parse_last; i++) {
-		if ((cur = find_var(pVar, pLib->parse_table[i].path))) {
-			if (diva_trace_read_variable(cur, pLib->parse_table[i].variable)) {
-				diva_trace_error(pLib, -3 , __FILE__, __LINE__);
-				return (-1);
-			}
-			one_updated = 1;
-			if ((i >= pLib->mdm_statistic_parse_first) && (i <= pLib->mdm_statistic_parse_last)) {
-				mdm_updated = 1;
-			}
-			if ((i >= pLib->fax_statistic_parse_first) && (i <= pLib->fax_statistic_parse_last)) {
-				fax_updated = 1;
-			}
-		}
-	}
-
-	/*
-	  We do not use first event to notify user - this is the event that is
-	  generated as result of EVENT ON operation and is used only to initialize
-	  internal variables of application
-	*/
-	if (mdm_updated) {
-		diva_trace_notify_user(pLib, 0, DIVA_SUPER_TRACE_NOTIFY_MDM_STAT_CHANGE);
-	} else if (fax_updated) {
-		diva_trace_notify_user(pLib, 0, DIVA_SUPER_TRACE_NOTIFY_FAX_STAT_CHANGE);
-	} else if (one_updated) {
-		diva_trace_notify_user(pLib, 0, DIVA_SUPER_TRACE_NOTIFY_STAT_CHANGE);
-	}
-
-	return (one_updated ? 0 : -1);
-}
-
-static int SuperTraceGetOutgoingCallStatistics(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-	pLib->outgoing_ifc_stats = 1;
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-static int SuperTraceGetIncomingCallStatistics(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-	pLib->incoming_ifc_stats = 1;
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-static int SuperTraceGetModemStatistics(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-	pLib->modem_ifc_stats = 1;
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-static int SuperTraceGetFaxStatistics(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-	pLib->fax_ifc_stats = 1;
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-static int SuperTraceGetBLayer1Statistics(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-	pLib->b1_ifc_stats = 1;
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-static int SuperTraceGetBLayer2Statistics(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-	pLib->b2_ifc_stats = 1;
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-static int SuperTraceGetDLayer1Statistics(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-	pLib->d1_ifc_stats = 1;
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-static int SuperTraceGetDLayer2Statistics(void *hLib) {
-	diva_strace_context_t *pLib = (diva_strace_context_t *)hLib;
-	pLib->d2_ifc_stats = 1;
-	return (ScheduleNextTraceRequest(pLib));
-}
-
-dword DivaSTraceGetMemotyRequirement(int channels) {
-	dword parse_entries = (MODEM_PARSE_ENTRIES + FAX_PARSE_ENTRIES + \
-			       STAT_PARSE_ENTRIES + \
-			       LINE_PARSE_ENTRIES + 1) * channels;
-	return (sizeof(diva_strace_context_t) + \
-		(parse_entries * sizeof(diva_strace_path2action_t)));
-}
diff --git a/drivers/isdn/hardware/eicon/maintidi.h b/drivers/isdn/hardware/eicon/maintidi.h
deleted file mode 100644
index 2b46147c5532..000000000000
--- a/drivers/isdn/hardware/eicon/maintidi.h
+++ /dev/null
@@ -1,171 +0,0 @@
-/*
- *
- Copyright (c) Eicon Networks, 2000.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    1.9
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_EICON_TRACE_IDI_IFC_H__
-#define __DIVA_EICON_TRACE_IDI_IFC_H__
-
-void *SuperTraceOpenAdapter(int AdapterNumber);
-int SuperTraceCloseAdapter(void *AdapterHandle);
-int SuperTraceWrite(void *AdapterHandle,
-		    const void *data, int length);
-int SuperTraceReadRequest(void *AdapterHandle, const char *name, byte *data);
-int SuperTraceGetNumberOfChannels(void *AdapterHandle);
-int SuperTraceASSIGN(void *AdapterHandle, byte *data);
-int SuperTraceREMOVE(void *AdapterHandle);
-int SuperTraceTraceOnRequest(void *hAdapter, const char *name, byte *data);
-int SuperTraceWriteVar(void *AdapterHandle,
-		       byte *data,
-		       const char *name,
-		       void *var,
-		       byte type,
-		       byte var_length);
-int SuperTraceExecuteRequest(void *AdapterHandle,
-			     const char *name,
-			     byte *data);
-
-typedef struct _diva_strace_path2action {
-	char path[64]; /* Full path to variable            */
-	void *variable; /* Variable that will receive value */
-} diva_strace_path2action_t;
-
-#define DIVA_MAX_MANAGEMENT_TRANSFER_SIZE 4096
-
-typedef struct _diva_strace_context {
-	diva_strace_library_interface_t	instance;
-
-	int Adapter;
-	void *hAdapter;
-
-	int Channels;
-	int req_busy;
-
-	ENTITY e;
-	IDI_CALL request;
-	BUFFERS XData;
-	BUFFERS RData;
-	byte buffer[DIVA_MAX_MANAGEMENT_TRANSFER_SIZE + 1];
-	int removal_state;
-	int general_b_ch_event;
-	int general_fax_event;
-	int general_mdm_event;
-
-	byte rc_ok;
-
-	/*
-	  Initialization request state machine
-	*/
-	int ChannelsTraceActive;
-	int ModemTraceActive;
-	int FaxTraceActive;
-	int IncomingCallsCallsActive;
-	int IncomingCallsConnectedActive;
-	int OutgoingCallsCallsActive;
-	int OutgoingCallsConnectedActive;
-
-	int trace_mask_init;
-	int audio_trace_init;
-	int bchannel_init;
-	int trace_length_init;
-	int	trace_on;
-	int trace_events_down;
-	int l1_trace;
-	int l2_trace;
-
-	/*
-	  Trace\Event Enable
-	*/
-	word trace_event_mask;
-	word current_trace_event_mask;
-
-	dword audio_tap_mask;
-	dword current_audio_tap_mask;
-	dword current_eye_pattern_mask;
-	int   audio_tap_pending;
-	int   eye_pattern_pending;
-
-	dword bchannel_trace_mask;
-	dword current_bchannel_trace_mask;
-
-
-	diva_trace_line_state_t lines[30];
-
-	int	parse_entries;
-	int	cur_parse_entry;
-	diva_strace_path2action_t *parse_table;
-
-	diva_trace_library_user_interface_t user_proc_table;
-
-	int line_parse_entry_first[30];
-	int line_parse_entry_last[30];
-
-	int modem_parse_entry_first[30];
-	int modem_parse_entry_last[30];
-
-	int fax_parse_entry_first[30];
-	int fax_parse_entry_last[30];
-
-	int statistic_parse_first;
-	int statistic_parse_last;
-
-	int mdm_statistic_parse_first;
-	int mdm_statistic_parse_last;
-
-	int fax_statistic_parse_first;
-	int fax_statistic_parse_last;
-
-	dword	line_init_event;
-	dword	modem_init_event;
-	dword	fax_init_event;
-
-	dword	pending_line_status;
-	dword	pending_modem_status;
-	dword	pending_fax_status;
-
-	dword clear_call_command;
-
-	int outgoing_ifc_stats;
-	int incoming_ifc_stats;
-	int modem_ifc_stats;
-	int fax_ifc_stats;
-	int b1_ifc_stats;
-	int b2_ifc_stats;
-	int d1_ifc_stats;
-	int d2_ifc_stats;
-
-	diva_trace_interface_state_t Interface;
-	diva_ifc_statistics_t				 InterfaceStat;
-} diva_strace_context_t;
-
-typedef struct _diva_man_var_header {
-	byte   escape;
-	byte   length;
-	byte   management_id;
-	byte   type;
-	byte   attribute;
-	byte   status;
-	byte   value_length;
-	byte	 path_length;
-} diva_man_var_header_t;
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/man_defs.h b/drivers/isdn/hardware/eicon/man_defs.h
deleted file mode 100644
index 249c471700e7..000000000000
--- a/drivers/isdn/hardware/eicon/man_defs.h
+++ /dev/null
@@ -1,133 +0,0 @@
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    1.9
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-/* Definitions for use with the Management Information Element      */
-
-/*------------------------------------------------------------------*/
-/* Management information element                                   */
-/* ----------------------------------------------------------       */
-/* Byte     Coding            Comment                               */
-/* ----------------------------------------------------------       */
-/*    0 | 0 1 1 1 1 1 1 1 | ESC                                     */
-/*    1 | 0 x x x x x x x | Length of information element (m-1)     */
-/*    2 | 1 0 0 0 0 0 0 0 | Management Information Id               */
-/*    3 | x x x x x x x x | Type                                    */
-/*    4 | x x x x x x x x | Attribute                               */
-/*    5 | x x x x x x x x | Status                                  */
-/*    6 | x x x x x x x x | Variable Value Length (m-n)             */
-/*    7 | x x x x x x x x | Path / Variable Name String Length (n-8)*/
-/* 8..n | x x x x x x x x | Path/Node Name String separated by '\'  */
-/* n..m | x x x x x x x x | Variable content                        */
-/*------------------------------------------------------------------*/
-
-/*------------------------------------------------------------------*/
-/* Type Field                                                       */
-/*                                                                  */
-/* MAN_READ:      not used                                          */
-/* MAN_WRITE:     not used                                          */
-/* MAN_EVENT_ON:  not used                                          */
-/* MAN_EVENT_OFF: not used                                          */
-/* MAN_INFO_IND:  type of variable                                  */
-/* MAN_EVENT_IND: type of variable                                  */
-/* MAN_TRACE_IND  not used                                          */
-/*------------------------------------------------------------------*/
-#define MI_DIR          0x01  /* Directory string (zero terminated) */
-#define MI_EXECUTE      0x02  /* Executable function (has no value) */
-#define MI_ASCIIZ       0x03  /* Zero terminated string             */
-#define MI_ASCII        0x04  /* String, first byte is length       */
-#define MI_NUMBER       0x05  /* Number string, first byte is length*/
-#define MI_TRACE        0x06  /* Trace information, format see below*/
-
-#define MI_FIXED_LENGTH 0x80  /* get length from MAN_INFO max_len   */
-#define MI_INT          0x81  /* number to display as signed int    */
-#define MI_UINT         0x82  /* number to display as unsigned int  */
-#define MI_HINT         0x83  /* number to display in hex format    */
-#define MI_HSTR         0x84  /* number to display as a hex string  */
-#define MI_BOOLEAN      0x85  /* number to display as boolean       */
-#define MI_IP_ADDRESS   0x86  /* number to display as IP address    */
-#define MI_BITFLD       0x87  /* number to display as bit field     */
-#define MI_SPID_STATE   0x88  /* state# of SPID initialisation      */
-
-/*------------------------------------------------------------------*/
-/* Attribute Field                                                  */
-/*                                                                  */
-/* MAN_READ:      not used                                          */
-/* MAN_WRITE:     not used                                          */
-/* MAN_EVENT_ON:  not used                                          */
-/* MAN_EVENT_OFF: not used                                          */
-/* MAN_INFO_IND:  set according to capabilities of that variable    */
-/* MAN_EVENT_IND: not used                                          */
-/* MAN_TRACE_IND  not used                                          */
-/*------------------------------------------------------------------*/
-#define MI_WRITE        0x01  /* Variable is writeable              */
-#define MI_EVENT        0x02  /* Variable can indicate changes      */
-
-/*------------------------------------------------------------------*/
-/* Status Field                                                     */
-/*                                                                  */
-/* MAN_READ:      not used                                          */
-/* MAN_WRITE:     not used                                          */
-/* MAN_EVENT_ON:  not used                                          */
-/* MAN_EVENT_OFF: not used                                          */
-/* MAN_INFO_IND:  set according to the actual status                */
-/* MAN_EVENT_IND: set according to the actual statu                 */
-/* MAN_TRACE_IND  not used                                          */
-/*------------------------------------------------------------------*/
-#define MI_LOCKED       0x01  /* write protected by another instance*/
-#define MI_EVENT_ON     0x02  /* Event logging switched on          */
-#define MI_PROTECTED    0x04  /* write protected by this instance   */
-
-/*------------------------------------------------------------------*/
-/* Data Format used for MAN_TRACE_IND (no MI-element used)          */
-/*------------------------------------------------------------------*/
-typedef struct mi_xlog_hdr_s MI_XLOG_HDR;
-struct mi_xlog_hdr_s
-{
-	unsigned long  time;   /* Timestamp in msec units                 */
-	unsigned short size;   /* Size of data that follows               */
-	unsigned short code;   /* code of trace event                     */
-};                       /* unspecified data follows this header    */
-
-/*------------------------------------------------------------------*/
-/* Trace mask definitions for trace events except B channel and     */
-/* debug trace events                                               */
-/*------------------------------------------------------------------*/
-#define TM_D_CHAN   0x0001  /* D-Channel        (D-.) Code 3,4      */
-#define TM_L_LAYER  0x0002  /* Low Layer        (LL)  Code 6,7      */
-#define TM_N_LAYER  0x0004  /* Network Layer    (N)   Code 14,15    */
-#define TM_DL_ERR   0x0008  /* Data Link Error  (MDL) Code 9        */
-#define TM_LAYER1   0x0010  /* Layer 1                Code 20       */
-#define TM_C_COMM   0x0020  /* Call Comment     (SIG) Code 5,21,22  */
-#define TM_M_DATA   0x0040  /* Modulation Data  (EYE) Code 23       */
-#define TM_STRING   0x0080  /* Sting data             Code 24       */
-#define TM_N_USED2  0x0100  /* not used                             */
-#define TM_N_USED3  0x0200  /* not used                             */
-#define TM_N_USED4  0x0400  /* not used                             */
-#define TM_N_USED5  0x0800  /* not used                             */
-#define TM_N_USED6  0x1000  /* not used                             */
-#define TM_N_USED7  0x2000  /* not used                             */
-#define TM_N_USED8  0x4000  /* not used                             */
-#define TM_REST     0x8000  /* Codes 10,11,12,13,16,18,19,128,129   */
-
-/*------ End of file -----------------------------------------------*/
diff --git a/drivers/isdn/hardware/eicon/mdm_msg.h b/drivers/isdn/hardware/eicon/mdm_msg.h
deleted file mode 100644
index 0e6b2e009a74..000000000000
--- a/drivers/isdn/hardware/eicon/mdm_msg.h
+++ /dev/null
@@ -1,346 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __EICON_MDM_MSG_H__
-#define __EICON_MDM_MSG_H__
-#define DSP_UDATA_INDICATION_DCD_OFF  0x01
-#define DSP_UDATA_INDICATION_DCD_ON  0x02
-#define DSP_UDATA_INDICATION_CTS_OFF  0x03
-#define DSP_UDATA_INDICATION_CTS_ON  0x04
-/* =====================================================================
-   DCD_OFF Message:
-   <word> time of DCD off (sampled from counter at 8kHz)
-   DCD_ON Message:
-   <word> time of DCD on (sampled from counter at 8kHz)
-   <byte> connected norm
-   <word> connected options
-   <dword> connected speed (bit/s, max of tx and rx speed)
-   <word> roundtrip delay (ms)
-   <dword> connected speed tx (bit/s)
-   <dword> connected speed rx (bit/s)
-   Size of this message == 19 bytes, but we will receive only 11
-   ===================================================================== */
-#define DSP_CONNECTED_NORM_UNSPECIFIED      0
-#define DSP_CONNECTED_NORM_V21              1
-#define DSP_CONNECTED_NORM_V23              2
-#define DSP_CONNECTED_NORM_V22              3
-#define DSP_CONNECTED_NORM_V22_BIS          4
-#define DSP_CONNECTED_NORM_V32_BIS          5
-#define DSP_CONNECTED_NORM_V34              6
-#define DSP_CONNECTED_NORM_V8               7
-#define DSP_CONNECTED_NORM_BELL_212A        8
-#define DSP_CONNECTED_NORM_BELL_103         9
-#define DSP_CONNECTED_NORM_V29_LEASED_LINE  10
-#define DSP_CONNECTED_NORM_V33_LEASED_LINE  11
-#define DSP_CONNECTED_NORM_V90              12
-#define DSP_CONNECTED_NORM_V21_CH2          13
-#define DSP_CONNECTED_NORM_V27_TER          14
-#define DSP_CONNECTED_NORM_V29              15
-#define DSP_CONNECTED_NORM_V33              16
-#define DSP_CONNECTED_NORM_V17              17
-#define DSP_CONNECTED_NORM_V32              18
-#define DSP_CONNECTED_NORM_K56_FLEX         19
-#define DSP_CONNECTED_NORM_X2               20
-#define DSP_CONNECTED_NORM_V18              21
-#define DSP_CONNECTED_NORM_V18_LOW_HIGH     22
-#define DSP_CONNECTED_NORM_V18_HIGH_LOW     23
-#define DSP_CONNECTED_NORM_V21_LOW_HIGH     24
-#define DSP_CONNECTED_NORM_V21_HIGH_LOW     25
-#define DSP_CONNECTED_NORM_BELL103_LOW_HIGH 26
-#define DSP_CONNECTED_NORM_BELL103_HIGH_LOW 27
-#define DSP_CONNECTED_NORM_V23_75_1200      28
-#define DSP_CONNECTED_NORM_V23_1200_75      29
-#define DSP_CONNECTED_NORM_EDT_110          30
-#define DSP_CONNECTED_NORM_BAUDOT_45        31
-#define DSP_CONNECTED_NORM_BAUDOT_47        32
-#define DSP_CONNECTED_NORM_BAUDOT_50        33
-#define DSP_CONNECTED_NORM_DTMF             34
-#define DSP_CONNECTED_NORM_V18_RESERVED_13  35
-#define DSP_CONNECTED_NORM_V18_RESERVED_14  36
-#define DSP_CONNECTED_NORM_V18_RESERVED_15  37
-#define DSP_CONNECTED_NORM_VOWN             38
-#define DSP_CONNECTED_NORM_V23_OFF_HOOK     39
-#define DSP_CONNECTED_NORM_V23_ON_HOOK      40
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_3  41
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_4  42
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_5  43
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_6  44
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_7  45
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_8  46
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_9  47
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_10 48
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_11 49
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_12 50
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_13 51
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_14 52
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_15 53
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_16 54
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_17 55
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_18 56
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_19 57
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_20 58
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_21 59
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_22 60
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_23 61
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_24 62
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_25 63
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_26 64
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_27 65
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_28 66
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_29 67
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_30 68
-#define DSP_CONNECTED_NORM_VOWN_RESERVED_31 69
-#define DSP_CONNECTED_OPTION_TRELLIS             0x0001
-#define DSP_CONNECTED_OPTION_V42_TRANS           0x0002
-#define DSP_CONNECTED_OPTION_V42_LAPM            0x0004
-#define DSP_CONNECTED_OPTION_SHORT_TRAIN         0x0008
-#define DSP_CONNECTED_OPTION_TALKER_ECHO_PROTECT 0x0010
-#define DSP_CONNECTED_OPTION_V42BIS              0x0020
-#define DSP_CONNECTED_OPTION_MNP2                0x0040
-#define DSP_CONNECTED_OPTION_MNP3                0x0080
-#define DSP_CONNECTED_OPTION_MNP4                0x00c0
-#define DSP_CONNECTED_OPTION_MNP5                0x0100
-#define DSP_CONNECTED_OPTION_MNP10               0x0200
-#define DSP_CONNECTED_OPTION_MASK_V42            0x0024
-#define DSP_CONNECTED_OPTION_MASK_MNP            0x03c0
-#define DSP_CONNECTED_OPTION_MASK_ERROR_CORRECT  0x03e4
-#define DSP_CONNECTED_OPTION_MASK_COMPRESSION    0x0320
-#define DSP_UDATA_INDICATION_DISCONNECT         5
-/*
-  returns:
-  <byte> cause
-*/
-/* ==========================================================
-   DLC: B2 modem configuration
-   ========================================================== */
-/*
-  Fields in assign DLC information element for modem protocol V.42/MNP:
-  <byte> length of information element
-  <word> information field length
-  <byte> address A       (not used, default 3)
-  <byte> address B       (not used, default 1)
-  <byte> modulo mode     (not used, default 7)
-  <byte> window size     (not used, default 7)
-  <word> XID length      (not used, default 0)
-  ...    XID information (not used, default empty)
-  <byte> modem protocol negotiation options
-  <byte> modem protocol options
-  <byte> modem protocol break configuration
-  <byte> modem protocol application options
-*/
-#define DLC_MODEMPROT_DISABLE_V42_V42BIS     0x01
-#define DLC_MODEMPROT_DISABLE_MNP_MNP5       0x02
-#define DLC_MODEMPROT_REQUIRE_PROTOCOL       0x04
-#define DLC_MODEMPROT_DISABLE_V42_DETECT     0x08
-#define DLC_MODEMPROT_DISABLE_COMPRESSION    0x10
-#define DLC_MODEMPROT_REQUIRE_PROTOCOL_V34UP 0x20
-#define DLC_MODEMPROT_NO_PROTOCOL_IF_1200    0x01
-#define DLC_MODEMPROT_BUFFER_IN_V42_DETECT   0x02
-#define DLC_MODEMPROT_DISABLE_V42_SREJ       0x04
-#define DLC_MODEMPROT_DISABLE_MNP3           0x08
-#define DLC_MODEMPROT_DISABLE_MNP4           0x10
-#define DLC_MODEMPROT_DISABLE_MNP10          0x20
-#define DLC_MODEMPROT_NO_PROTOCOL_IF_V22BIS  0x40
-#define DLC_MODEMPROT_NO_PROTOCOL_IF_V32BIS  0x80
-#define DLC_MODEMPROT_BREAK_DISABLED         0x00
-#define DLC_MODEMPROT_BREAK_NORMAL           0x01
-#define DLC_MODEMPROT_BREAK_EXPEDITED        0x02
-#define DLC_MODEMPROT_BREAK_DESTRUCTIVE      0x03
-#define DLC_MODEMPROT_BREAK_CONFIG_MASK      0x03
-#define DLC_MODEMPROT_APPL_EARLY_CONNECT     0x01
-#define DLC_MODEMPROT_APPL_PASS_INDICATIONS  0x02
-/* ==========================================================
-   CAI parameters used for the modem L1 configuration
-   ========================================================== */
-/*
-  Fields in assign CAI information element:
-  <byte> length of information element
-  <byte> info field and B-channel hardware
-  <byte> rate adaptation bit rate
-  <byte> async framing parameters
-  <byte> reserved
-  <word> packet length
-  <byte> modem line taking options
-  <byte> modem modulation negotiation parameters
-  <byte> modem modulation options
-  <byte> modem disabled modulations mask low
-  <byte> modem disabled modulations mask high
-  <byte> modem enabled modulations mask
-  <word> modem min TX speed
-  <word> modem max TX speed
-  <word> modem min RX speed
-  <word> modem max RX speed
-  <byte> modem disabled symbol rates mask
-  <byte> modem info options mask
-  <byte> modem transmit level adjust
-  <byte> modem speaker parameters
-  <word> modem private debug config
-  <struct> modem reserved
-  <struct> v18 config parameters
-  <struct> v18 probing sequence
-  <struct> v18 probing message
-*/
-#define DSP_CAI_HARDWARE_HDLC_64K          0x05
-#define DSP_CAI_HARDWARE_HDLC_56K          0x08
-#define DSP_CAI_HARDWARE_TRANSP            0x09
-#define DSP_CAI_HARDWARE_V110_SYNC         0x0c
-#define DSP_CAI_HARDWARE_V110_ASYNC        0x0d
-#define DSP_CAI_HARDWARE_HDLC_128K         0x0f
-#define DSP_CAI_HARDWARE_FAX               0x10
-#define DSP_CAI_HARDWARE_MODEM_ASYNC       0x11
-#define DSP_CAI_HARDWARE_MODEM_SYNC        0x12
-#define DSP_CAI_HARDWARE_V110_HDLCA        0x13
-#define DSP_CAI_HARDWARE_ADVANCED_VOICE    0x14
-#define DSP_CAI_HARDWARE_TRANSP_DTMF       0x16
-#define DSP_CAI_HARDWARE_DTMF_VOICE_ISDN   0x17
-#define DSP_CAI_HARDWARE_DTMF_VOICE_LOCAL  0x18
-#define DSP_CAI_HARDWARE_MASK              0x3f
-#define DSP_CAI_ENABLE_INFO_INDICATIONS    0x80
-#define DSP_CAI_RATE_ADAPTATION_300        0x00
-#define DSP_CAI_RATE_ADAPTATION_600        0x01
-#define DSP_CAI_RATE_ADAPTATION_1200       0x02
-#define DSP_CAI_RATE_ADAPTATION_2400       0x03
-#define DSP_CAI_RATE_ADAPTATION_4800       0x04
-#define DSP_CAI_RATE_ADAPTATION_9600       0x05
-#define DSP_CAI_RATE_ADAPTATION_19200      0x06
-#define DSP_CAI_RATE_ADAPTATION_38400      0x07
-#define DSP_CAI_RATE_ADAPTATION_48000      0x08
-#define DSP_CAI_RATE_ADAPTATION_56000      0x09
-#define DSP_CAI_RATE_ADAPTATION_7200       0x0a
-#define DSP_CAI_RATE_ADAPTATION_14400      0x0b
-#define DSP_CAI_RATE_ADAPTATION_28800      0x0c
-#define DSP_CAI_RATE_ADAPTATION_12000      0x0d
-#define DSP_CAI_RATE_ADAPTATION_1200_75    0x0e
-#define DSP_CAI_RATE_ADAPTATION_75_1200    0x0f
-#define DSP_CAI_RATE_ADAPTATION_MASK       0x0f
-#define DSP_CAI_ASYNC_PARITY_ENABLE        0x01
-#define DSP_CAI_ASYNC_PARITY_SPACE         0x00
-#define DSP_CAI_ASYNC_PARITY_ODD           0x02
-#define DSP_CAI_ASYNC_PARITY_EVEN          0x04
-#define DSP_CAI_ASYNC_PARITY_MARK          0x06
-#define DSP_CAI_ASYNC_PARITY_MASK          0x06
-#define DSP_CAI_ASYNC_ONE_STOP_BIT         0x00
-#define DSP_CAI_ASYNC_TWO_STOP_BITS        0x20
-#define DSP_CAI_ASYNC_CHAR_LENGTH_8        0x00
-#define DSP_CAI_ASYNC_CHAR_LENGTH_7        0x40
-#define DSP_CAI_ASYNC_CHAR_LENGTH_6        0x80
-#define DSP_CAI_ASYNC_CHAR_LENGTH_5        0xc0
-#define DSP_CAI_ASYNC_CHAR_LENGTH_MASK     0xc0
-#define DSP_CAI_MODEM_LEASED_LINE_MODE     0x01
-#define DSP_CAI_MODEM_4_WIRE_OPERATION     0x02
-#define DSP_CAI_MODEM_DISABLE_BUSY_DETECT  0x04
-#define DSP_CAI_MODEM_DISABLE_CALLING_TONE 0x08
-#define DSP_CAI_MODEM_DISABLE_ANSWER_TONE  0x10
-#define DSP_CAI_MODEM_ENABLE_DIAL_TONE_DET 0x20
-#define DSP_CAI_MODEM_USE_POTS_INTERFACE   0x40
-#define DSP_CAI_MODEM_FORCE_RAY_TAYLOR_FAX 0x80
-#define DSP_CAI_MODEM_NEGOTIATE_HIGHEST    0x00
-#define DSP_CAI_MODEM_NEGOTIATE_DISABLED   0x01
-#define DSP_CAI_MODEM_NEGOTIATE_IN_CLASS   0x02
-#define DSP_CAI_MODEM_NEGOTIATE_V100       0x03
-#define DSP_CAI_MODEM_NEGOTIATE_V8         0x04
-#define DSP_CAI_MODEM_NEGOTIATE_V8BIS      0x05
-#define DSP_CAI_MODEM_NEGOTIATE_MASK       0x07
-#define DSP_CAI_MODEM_GUARD_TONE_NONE      0x00
-#define DSP_CAI_MODEM_GUARD_TONE_550HZ     0x40
-#define DSP_CAI_MODEM_GUARD_TONE_1800HZ    0x80
-#define DSP_CAI_MODEM_GUARD_TONE_MASK      0xc0
-#define DSP_CAI_MODEM_DISABLE_RETRAIN      0x01
-#define DSP_CAI_MODEM_DISABLE_STEPUPDOWN   0x02
-#define DSP_CAI_MODEM_DISABLE_SPLIT_SPEED  0x04
-#define DSP_CAI_MODEM_DISABLE_TRELLIS      0x08
-#define DSP_CAI_MODEM_ALLOW_RDL_TEST_LOOP  0x10
-#define DSP_CAI_MODEM_DISABLE_FLUSH_TIMER  0x40
-#define DSP_CAI_MODEM_REVERSE_DIRECTION    0x80
-#define DSP_CAI_MODEM_DISABLE_V21          0x01
-#define DSP_CAI_MODEM_DISABLE_V23          0x02
-#define DSP_CAI_MODEM_DISABLE_V22          0x04
-#define DSP_CAI_MODEM_DISABLE_V22BIS       0x08
-#define DSP_CAI_MODEM_DISABLE_V32          0x10
-#define DSP_CAI_MODEM_DISABLE_V32BIS       0x20
-#define DSP_CAI_MODEM_DISABLE_V34          0x40
-#define DSP_CAI_MODEM_DISABLE_V90          0x80
-#define DSP_CAI_MODEM_DISABLE_BELL103      0x01
-#define DSP_CAI_MODEM_DISABLE_BELL212A     0x02
-#define DSP_CAI_MODEM_DISABLE_VFC          0x04
-#define DSP_CAI_MODEM_DISABLE_K56FLEX      0x08
-#define DSP_CAI_MODEM_DISABLE_X2           0x10
-#define DSP_CAI_MODEM_ENABLE_V29FDX        0x01
-#define DSP_CAI_MODEM_ENABLE_V33           0x02
-#define DSP_CAI_MODEM_DISABLE_2400_SYMBOLS 0x01
-#define DSP_CAI_MODEM_DISABLE_2743_SYMBOLS 0x02
-#define DSP_CAI_MODEM_DISABLE_2800_SYMBOLS 0x04
-#define DSP_CAI_MODEM_DISABLE_3000_SYMBOLS 0x08
-#define DSP_CAI_MODEM_DISABLE_3200_SYMBOLS 0x10
-#define DSP_CAI_MODEM_DISABLE_3429_SYMBOLS 0x20
-#define DSP_CAI_MODEM_DISABLE_TX_REDUCTION 0x01
-#define DSP_CAI_MODEM_DISABLE_PRECODING    0x02
-#define DSP_CAI_MODEM_DISABLE_PREEMPHASIS  0x04
-#define DSP_CAI_MODEM_DISABLE_SHAPING      0x08
-#define DSP_CAI_MODEM_DISABLE_NONLINEAR_EN 0x10
-#define DSP_CAI_MODEM_SPEAKER_OFF          0x00
-#define DSP_CAI_MODEM_SPEAKER_DURING_TRAIN 0x01
-#define DSP_CAI_MODEM_SPEAKER_TIL_CONNECT  0x02
-#define DSP_CAI_MODEM_SPEAKER_ALWAYS_ON    0x03
-#define DSP_CAI_MODEM_SPEAKER_CONTROL_MASK 0x03
-#define DSP_CAI_MODEM_SPEAKER_VOLUME_MIN   0x00
-#define DSP_CAI_MODEM_SPEAKER_VOLUME_LOW   0x04
-#define DSP_CAI_MODEM_SPEAKER_VOLUME_HIGH  0x08
-#define DSP_CAI_MODEM_SPEAKER_VOLUME_MAX   0x0c
-#define DSP_CAI_MODEM_SPEAKER_VOLUME_MASK  0x0c
-/* ==========================================================
-   DCD/CTS State
-   ========================================================== */
-#define MDM_WANT_CONNECT_B3_ACTIVE_I  0x01
-#define MDM_NCPI_VALID                0x02
-#define MDM_NCPI_CTS_ON_RECEIVED      0x04
-#define MDM_NCPI_DCD_ON_RECEIVED      0x08
-/* ==========================================================
-   CAPI NCPI Constants
-   ========================================================== */
-#define MDM_NCPI_ECM_V42              0x0001
-#define MDM_NCPI_ECM_MNP              0x0002
-#define MDM_NCPI_TRANSPARENT          0x0004
-#define MDM_NCPI_COMPRESSED           0x0010
-/* ==========================================================
-   CAPI B2 Config Constants
-   ========================================================== */
-#define MDM_B2_DISABLE_V42bis         0x0001
-#define MDM_B2_DISABLE_MNP            0x0002
-#define MDM_B2_DISABLE_TRANS          0x0004
-#define MDM_B2_DISABLE_V42            0x0008
-#define MDM_B2_DISABLE_COMP           0x0010
-/* ==========================================================
-   CAPI B1 Config Constants
-   ========================================================== */
-#define MDM_CAPI_DISABLE_RETRAIN      0x0001
-#define MDM_CAPI_DISABLE_RING_TONE    0x0002
-#define MDM_CAPI_GUARD_1800           0x0004
-#define MDM_CAPI_GUARD_550            0x0008
-#define MDM_CAPI_NEG_V8               0x0003
-#define MDM_CAPI_NEG_V100             0x0002
-#define MDM_CAPI_NEG_MOD_CLASS        0x0001
-#define MDM_CAPI_NEG_DISABLED         0x0000
-#endif
diff --git a/drivers/isdn/hardware/eicon/message.c b/drivers/isdn/hardware/eicon/message.c
deleted file mode 100644
index def7992a38e6..000000000000
--- a/drivers/isdn/hardware/eicon/message.c
+++ /dev/null
@@ -1,14954 +0,0 @@
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-
-#include <linux/bitmap.h>
-
-#include "platform.h"
-#include "di_defs.h"
-#include "pc.h"
-#include "capi20.h"
-#include "divacapi.h"
-#include "mdm_msg.h"
-#include "divasync.h"
-
-#define FILE_ "MESSAGE.C"
-#define dprintf
-
-/*------------------------------------------------------------------*/
-/* This is options supported for all adapters that are server by    */
-/* XDI driver. Allo it is not necessary to ask it from every adapter*/
-/* and it is not necessary to save it separate for every adapter    */
-/* Macrose defined here have only local meaning                     */
-/*------------------------------------------------------------------*/
-static dword diva_xdi_extended_features = 0;
-
-#define DIVA_CAPI_USE_CMA                 0x00000001
-#define DIVA_CAPI_XDI_PROVIDES_SDRAM_BAR  0x00000002
-#define DIVA_CAPI_XDI_PROVIDES_NO_CANCEL  0x00000004
-#define DIVA_CAPI_XDI_PROVIDES_RX_DMA     0x00000008
-
-/*
-  CAPI can request to process all return codes self only if:
-  protocol code supports this && xdi supports this
-*/
-#define DIVA_CAPI_SUPPORTS_NO_CANCEL(__a__)   (((__a__)->manufacturer_features & MANUFACTURER_FEATURE_XONOFF_FLOW_CONTROL) && ((__a__)->manufacturer_features & MANUFACTURER_FEATURE_OK_FC_LABEL) && (diva_xdi_extended_features & DIVA_CAPI_XDI_PROVIDES_NO_CANCEL))
-
-/*------------------------------------------------------------------*/
-/* local function prototypes                                        */
-/*------------------------------------------------------------------*/
-
-static void group_optimization(DIVA_CAPI_ADAPTER *a, PLCI *plci);
-void AutomaticLaw(DIVA_CAPI_ADAPTER *);
-word CapiRelease(word);
-word CapiRegister(word);
-word api_put(APPL *, CAPI_MSG *);
-static word api_parse(byte *, word, byte *, API_PARSE *);
-static void api_save_msg(API_PARSE *in, byte *format, API_SAVE *out);
-static void api_load_msg(API_SAVE *in, API_PARSE *out);
-
-word api_remove_start(void);
-void api_remove_complete(void);
-
-static void plci_remove(PLCI *);
-static void diva_get_extended_adapter_features(DIVA_CAPI_ADAPTER *a);
-static void diva_ask_for_xdi_sdram_bar(DIVA_CAPI_ADAPTER *, IDI_SYNC_REQ *);
-
-void callback(ENTITY *);
-
-static void control_rc(PLCI *, byte, byte, byte, byte, byte);
-static void data_rc(PLCI *, byte);
-static void data_ack(PLCI *, byte);
-static void sig_ind(PLCI *);
-static void SendInfo(PLCI *, dword, byte **, byte);
-static void SendSetupInfo(APPL *, PLCI *, dword, byte **, byte);
-static void SendSSExtInd(APPL *, PLCI *plci, dword Id, byte **parms);
-
-static void VSwitchReqInd(PLCI *plci, dword Id, byte **parms);
-
-static void nl_ind(PLCI *);
-
-static byte connect_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte connect_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte connect_a_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte disconnect_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte disconnect_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte listen_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte info_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte info_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte alert_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte facility_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte facility_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte connect_b3_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte connect_b3_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte connect_b3_a_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte disconnect_b3_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte disconnect_b3_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte data_b3_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte data_b3_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte reset_b3_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte reset_b3_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte connect_b3_t90_a_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte select_b_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte manufacturer_req(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-static byte manufacturer_res(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-
-static word get_plci(DIVA_CAPI_ADAPTER *);
-static void add_p(PLCI *, byte, byte *);
-static void add_s(PLCI *plci, byte code, API_PARSE *p);
-static void add_ss(PLCI *plci, byte code, API_PARSE *p);
-static void add_ie(PLCI *plci, byte code, byte *p, word p_length);
-static void add_d(PLCI *, word, byte *);
-static void add_ai(PLCI *, API_PARSE *);
-static word add_b1(PLCI *, API_PARSE *, word, word);
-static word add_b23(PLCI *, API_PARSE *);
-static word add_modem_b23(PLCI *plci, API_PARSE *bp_parms);
-static void sig_req(PLCI *, byte, byte);
-static void nl_req_ncci(PLCI *, byte, byte);
-static void send_req(PLCI *);
-static void send_data(PLCI *);
-static word plci_remove_check(PLCI *);
-static void listen_check(DIVA_CAPI_ADAPTER *);
-static byte AddInfo(byte **, byte **, byte *, byte *);
-static byte getChannel(API_PARSE *);
-static void IndParse(PLCI *, const word *, byte **, byte);
-static byte ie_compare(byte *, byte *);
-static word find_cip(DIVA_CAPI_ADAPTER *, byte *, byte *);
-static word CPN_filter_ok(byte *cpn, DIVA_CAPI_ADAPTER *, word);
-
-/*
-  XON protocol helpers
-*/
-static void channel_flow_control_remove(PLCI *plci);
-static void channel_x_off(PLCI *plci, byte ch, byte flag);
-static void channel_x_on(PLCI *plci, byte ch);
-static void channel_request_xon(PLCI *plci, byte ch);
-static void channel_xmit_xon(PLCI *plci);
-static int channel_can_xon(PLCI *plci, byte ch);
-static void channel_xmit_extended_xon(PLCI *plci);
-
-static byte SendMultiIE(PLCI *plci, dword Id, byte **parms, byte ie_type, dword info_mask, byte setupParse);
-static word AdvCodecSupport(DIVA_CAPI_ADAPTER *, PLCI *, APPL *, byte);
-static void CodecIdCheck(DIVA_CAPI_ADAPTER *, PLCI *);
-static void SetVoiceChannel(PLCI *, byte *, DIVA_CAPI_ADAPTER *);
-static void VoiceChannelOff(PLCI *plci);
-static void adv_voice_write_coefs(PLCI *plci, word write_command);
-static void adv_voice_clear_config(PLCI *plci);
-
-static word get_b1_facilities(PLCI *plci, byte b1_resource);
-static byte add_b1_facilities(PLCI *plci, byte b1_resource, word b1_facilities);
-static void adjust_b1_facilities(PLCI *plci, byte new_b1_resource, word new_b1_facilities);
-static word adjust_b_process(dword Id, PLCI *plci, byte Rc);
-static void adjust_b1_resource(dword Id, PLCI *plci, API_SAVE *bp_msg, word b1_facilities, word internal_command);
-static void adjust_b_restore(dword Id, PLCI *plci, byte Rc);
-static void reset_b3_command(dword Id, PLCI *plci, byte Rc);
-static void select_b_command(dword Id, PLCI *plci, byte Rc);
-static void fax_connect_ack_command(dword Id, PLCI *plci, byte Rc);
-static void fax_edata_ack_command(dword Id, PLCI *plci, byte Rc);
-static void fax_connect_info_command(dword Id, PLCI *plci, byte Rc);
-static void fax_adjust_b23_command(dword Id, PLCI *plci, byte Rc);
-static void fax_disconnect_command(dword Id, PLCI *plci, byte Rc);
-static void hold_save_command(dword Id, PLCI *plci, byte Rc);
-static void retrieve_restore_command(dword Id, PLCI *plci, byte Rc);
-static void init_b1_config(PLCI *plci);
-static void clear_b1_config(PLCI *plci);
-
-static void dtmf_command(dword Id, PLCI *plci, byte Rc);
-static byte dtmf_request(dword Id, word Number, DIVA_CAPI_ADAPTER *a, PLCI *plci, APPL *appl, API_PARSE *msg);
-static void dtmf_confirmation(dword Id, PLCI *plci);
-static void dtmf_indication(dword Id, PLCI *plci, byte *msg, word length);
-static void dtmf_parameter_write(PLCI *plci);
-
-
-static void mixer_set_bchannel_id_esc(PLCI *plci, byte bchannel_id);
-static void mixer_set_bchannel_id(PLCI *plci, byte *chi);
-static void mixer_clear_config(PLCI *plci);
-static void mixer_notify_update(PLCI *plci, byte others);
-static void mixer_command(dword Id, PLCI *plci, byte Rc);
-static byte mixer_request(dword Id, word Number, DIVA_CAPI_ADAPTER *a, PLCI *plci, APPL *appl, API_PARSE *msg);
-static void mixer_indication_coefs_set(dword Id, PLCI *plci);
-static void mixer_indication_xconnect_from(dword Id, PLCI *plci, byte *msg, word length);
-static void mixer_indication_xconnect_to(dword Id, PLCI *plci, byte *msg, word length);
-static void mixer_remove(PLCI *plci);
-
-
-static void ec_command(dword Id, PLCI *plci, byte Rc);
-static byte ec_request(dword Id, word Number, DIVA_CAPI_ADAPTER *a, PLCI *plci, APPL *appl, API_PARSE *msg);
-static void ec_indication(dword Id, PLCI *plci, byte *msg, word length);
-
-
-static void rtp_connect_b3_req_command(dword Id, PLCI *plci, byte Rc);
-static void rtp_connect_b3_res_command(dword Id, PLCI *plci, byte Rc);
-
-
-static int diva_get_dma_descriptor(PLCI *plci, dword *dma_magic);
-static void diva_free_dma_descriptor(PLCI *plci, int nr);
-
-/*------------------------------------------------------------------*/
-/* external function prototypes                                     */
-/*------------------------------------------------------------------*/
-
-extern byte MapController(byte);
-extern byte UnMapController(byte);
-#define MapId(Id)(((Id) & 0xffffff00L) | MapController((byte)(Id)))
-#define UnMapId(Id)(((Id) & 0xffffff00L) | UnMapController((byte)(Id)))
-
-void sendf(APPL *, word, dword, word, byte *, ...);
-void *TransmitBufferSet(APPL *appl, dword ref);
-void *TransmitBufferGet(APPL *appl, void *p);
-void TransmitBufferFree(APPL *appl, void *p);
-void *ReceiveBufferGet(APPL *appl, int Num);
-
-int fax_head_line_time(char *buffer);
-
-
-/*------------------------------------------------------------------*/
-/* Global data definitions                                          */
-/*------------------------------------------------------------------*/
-extern byte max_adapter;
-extern byte max_appl;
-extern DIVA_CAPI_ADAPTER *adapter;
-extern APPL *application;
-
-
-
-
-
-
-
-static byte remove_started = false;
-static PLCI dummy_plci;
-
-
-static struct _ftable {
-	word command;
-	byte *format;
-	byte (*function)(dword, word, DIVA_CAPI_ADAPTER *, PLCI *, APPL *, API_PARSE *);
-} ftable[] = {
-	{_DATA_B3_R,                          "dwww",         data_b3_req},
-	{_DATA_B3_I | RESPONSE,               "w",            data_b3_res},
-	{_INFO_R,                             "ss",           info_req},
-	{_INFO_I | RESPONSE,                  "",             info_res},
-	{_CONNECT_R,                          "wsssssssss",   connect_req},
-	{_CONNECT_I | RESPONSE,               "wsssss",       connect_res},
-	{_CONNECT_ACTIVE_I | RESPONSE,        "",             connect_a_res},
-	{_DISCONNECT_R,                       "s",            disconnect_req},
-	{_DISCONNECT_I | RESPONSE,            "",             disconnect_res},
-	{_LISTEN_R,                           "dddss",        listen_req},
-	{_ALERT_R,                            "s",            alert_req},
-	{_FACILITY_R,                         "ws",           facility_req},
-	{_FACILITY_I | RESPONSE,              "ws",           facility_res},
-	{_CONNECT_B3_R,                       "s",            connect_b3_req},
-	{_CONNECT_B3_I | RESPONSE,            "ws",           connect_b3_res},
-	{_CONNECT_B3_ACTIVE_I | RESPONSE,     "",             connect_b3_a_res},
-	{_DISCONNECT_B3_R,                    "s",            disconnect_b3_req},
-	{_DISCONNECT_B3_I | RESPONSE,         "",             disconnect_b3_res},
-	{_RESET_B3_R,                         "s",            reset_b3_req},
-	{_RESET_B3_I | RESPONSE,              "",             reset_b3_res},
-	{_CONNECT_B3_T90_ACTIVE_I | RESPONSE, "ws",           connect_b3_t90_a_res},
-	{_CONNECT_B3_T90_ACTIVE_I | RESPONSE, "",             connect_b3_t90_a_res},
-	{_SELECT_B_REQ,                       "s",            select_b_req},
-	{_MANUFACTURER_R,                     "dws",          manufacturer_req},
-	{_MANUFACTURER_I | RESPONSE,          "dws",          manufacturer_res},
-	{_MANUFACTURER_I | RESPONSE,          "",             manufacturer_res}
-};
-
-static byte *cip_bc[29][2] = {
-	{ "",                     ""                     }, /* 0 */
-	{ "\x03\x80\x90\xa3",     "\x03\x80\x90\xa2"     }, /* 1 */
-	{ "\x02\x88\x90",         "\x02\x88\x90"         }, /* 2 */
-	{ "\x02\x89\x90",         "\x02\x89\x90"         }, /* 3 */
-	{ "\x03\x90\x90\xa3",     "\x03\x90\x90\xa2"     }, /* 4 */
-	{ "\x03\x91\x90\xa5",     "\x03\x91\x90\xa5"     }, /* 5 */
-	{ "\x02\x98\x90",         "\x02\x98\x90"         }, /* 6 */
-	{ "\x04\x88\xc0\xc6\xe6", "\x04\x88\xc0\xc6\xe6" }, /* 7 */
-	{ "\x04\x88\x90\x21\x8f", "\x04\x88\x90\x21\x8f" }, /* 8 */
-	{ "\x03\x91\x90\xa5",     "\x03\x91\x90\xa5"     }, /* 9 */
-	{ "",                     ""                     }, /* 10 */
-	{ "",                     ""                     }, /* 11 */
-	{ "",                     ""                     }, /* 12 */
-	{ "",                     ""                     }, /* 13 */
-	{ "",                     ""                     }, /* 14 */
-	{ "",                     ""                     }, /* 15 */
-
-	{ "\x03\x80\x90\xa3",     "\x03\x80\x90\xa2"     }, /* 16 */
-	{ "\x03\x90\x90\xa3",     "\x03\x90\x90\xa2"     }, /* 17 */
-	{ "\x02\x88\x90",         "\x02\x88\x90"         }, /* 18 */
-	{ "\x02\x88\x90",         "\x02\x88\x90"         }, /* 19 */
-	{ "\x02\x88\x90",         "\x02\x88\x90"         }, /* 20 */
-	{ "\x02\x88\x90",         "\x02\x88\x90"         }, /* 21 */
-	{ "\x02\x88\x90",         "\x02\x88\x90"         }, /* 22 */
-	{ "\x02\x88\x90",         "\x02\x88\x90"         }, /* 23 */
-	{ "\x02\x88\x90",         "\x02\x88\x90"         }, /* 24 */
-	{ "\x02\x88\x90",         "\x02\x88\x90"         }, /* 25 */
-	{ "\x03\x91\x90\xa5",     "\x03\x91\x90\xa5"     }, /* 26 */
-	{ "\x03\x91\x90\xa5",     "\x03\x91\x90\xa5"     }, /* 27 */
-	{ "\x02\x88\x90",         "\x02\x88\x90"         }  /* 28 */
-};
-
-static byte *cip_hlc[29] = {
-	"",                           /* 0 */
-	"",                           /* 1 */
-	"",                           /* 2 */
-	"",                           /* 3 */
-	"",                           /* 4 */
-	"",                           /* 5 */
-	"",                           /* 6 */
-	"",                           /* 7 */
-	"",                           /* 8 */
-	"",                           /* 9 */
-	"",                           /* 10 */
-	"",                           /* 11 */
-	"",                           /* 12 */
-	"",                           /* 13 */
-	"",                           /* 14 */
-	"",                           /* 15 */
-
-	"\x02\x91\x81",               /* 16 */
-	"\x02\x91\x84",               /* 17 */
-	"\x02\x91\xa1",               /* 18 */
-	"\x02\x91\xa4",               /* 19 */
-	"\x02\x91\xa8",               /* 20 */
-	"\x02\x91\xb1",               /* 21 */
-	"\x02\x91\xb2",               /* 22 */
-	"\x02\x91\xb5",               /* 23 */
-	"\x02\x91\xb8",               /* 24 */
-	"\x02\x91\xc1",               /* 25 */
-	"\x02\x91\x81",               /* 26 */
-	"\x03\x91\xe0\x01",           /* 27 */
-	"\x03\x91\xe0\x02"            /* 28 */
-};
-
-/*------------------------------------------------------------------*/
-
-#define V120_HEADER_LENGTH 1
-#define V120_HEADER_EXTEND_BIT  0x80
-#define V120_HEADER_BREAK_BIT   0x40
-#define V120_HEADER_C1_BIT      0x04
-#define V120_HEADER_C2_BIT      0x08
-#define V120_HEADER_FLUSH_COND  (V120_HEADER_BREAK_BIT | V120_HEADER_C1_BIT | V120_HEADER_C2_BIT)
-
-static byte v120_default_header[] =
-{
-
-	0x83                          /*  Ext, BR , res, res, C2 , C1 , B  , F   */
-
-};
-
-static byte v120_break_header[] =
-{
-
-	0xc3 | V120_HEADER_BREAK_BIT  /*  Ext, BR , res, res, C2 , C1 , B  , F   */
-
-};
-
-
-/*------------------------------------------------------------------*/
-/* API_PUT function                                                 */
-/*------------------------------------------------------------------*/
-
-word api_put(APPL *appl, CAPI_MSG *msg)
-{
-	word i, j, k, l, n;
-	word ret;
-	byte c;
-	byte controller;
-	DIVA_CAPI_ADAPTER *a;
-	PLCI *plci;
-	NCCI *ncci_ptr;
-	word ncci;
-	CAPI_MSG *m;
-	API_PARSE msg_parms[MAX_MSG_PARMS + 1];
-
-	if (msg->header.length < sizeof(msg->header) ||
-	    msg->header.length > MAX_MSG_SIZE) {
-		dbug(1, dprintf("bad len"));
-		return _BAD_MSG;
-	}
-
-	controller = (byte)((msg->header.controller & 0x7f) - 1);
-
-	/* controller starts with 0 up to (max_adapter - 1) */
-	if (controller >= max_adapter)
-	{
-		dbug(1, dprintf("invalid ctrl"));
-		return _BAD_MSG;
-	}
-
-	a = &adapter[controller];
-	plci = NULL;
-	if ((msg->header.plci != 0) && (msg->header.plci <= a->max_plci) && !a->adapter_disabled)
-	{
-		dbug(1, dprintf("plci=%x", msg->header.plci));
-		plci = &a->plci[msg->header.plci - 1];
-		ncci = GET_WORD(&msg->header.ncci);
-		if (plci->Id
-		    && (plci->appl
-			|| (plci->State == INC_CON_PENDING)
-			|| (plci->State == INC_CON_ALERT)
-			|| (msg->header.command == (_DISCONNECT_I | RESPONSE)))
-		    && ((ncci == 0)
-			|| (msg->header.command == (_DISCONNECT_B3_I | RESPONSE))
-			|| ((ncci < MAX_NCCI + 1) && (a->ncci_plci[ncci] == plci->Id))))
-		{
-			i = plci->msg_in_read_pos;
-			j = plci->msg_in_write_pos;
-			if (j >= i)
-			{
-				if (j + msg->header.length + MSG_IN_OVERHEAD <= MSG_IN_QUEUE_SIZE)
-					i += MSG_IN_QUEUE_SIZE - j;
-				else
-					j = 0;
-			}
-			else
-			{
-
-				n = (((CAPI_MSG *)(plci->msg_in_queue))->header.length + MSG_IN_OVERHEAD + 3) & 0xfffc;
-
-				if (i > MSG_IN_QUEUE_SIZE - n)
-					i = MSG_IN_QUEUE_SIZE - n + 1;
-				i -= j;
-			}
-
-			if (i <= ((msg->header.length + MSG_IN_OVERHEAD + 3) & 0xfffc))
-
-			{
-				dbug(0, dprintf("Q-FULL1(msg) - len=%d write=%d read=%d wrap=%d free=%d",
-						msg->header.length, plci->msg_in_write_pos,
-						plci->msg_in_read_pos, plci->msg_in_wrap_pos, i));
-
-				return _QUEUE_FULL;
-			}
-			c = false;
-			if ((((byte *) msg) < ((byte *)(plci->msg_in_queue)))
-			    || (((byte *) msg) >= ((byte *)(plci->msg_in_queue)) + sizeof(plci->msg_in_queue)))
-			{
-				if (plci->msg_in_write_pos != plci->msg_in_read_pos)
-					c = true;
-			}
-			if (msg->header.command == _DATA_B3_R)
-			{
-				if (msg->header.length < 20)
-				{
-					dbug(1, dprintf("DATA_B3 REQ wrong length %d", msg->header.length));
-					return _BAD_MSG;
-				}
-				ncci_ptr = &(a->ncci[ncci]);
-				n = ncci_ptr->data_pending;
-				l = ncci_ptr->data_ack_pending;
-				k = plci->msg_in_read_pos;
-				while (k != plci->msg_in_write_pos)
-				{
-					if (k == plci->msg_in_wrap_pos)
-						k = 0;
-					if ((((CAPI_MSG *)(&((byte *)(plci->msg_in_queue))[k]))->header.command == _DATA_B3_R)
-					    && (((CAPI_MSG *)(&((byte *)(plci->msg_in_queue))[k]))->header.ncci == ncci))
-					{
-						n++;
-						if (((CAPI_MSG *)(&((byte *)(plci->msg_in_queue))[k]))->info.data_b3_req.Flags & 0x0004)
-							l++;
-					}
-
-					k += (((CAPI_MSG *)(&((byte *)(plci->msg_in_queue))[k]))->header.length +
-					      MSG_IN_OVERHEAD + 3) & 0xfffc;
-
-				}
-				if ((n >= MAX_DATA_B3) || (l >= MAX_DATA_ACK))
-				{
-					dbug(0, dprintf("Q-FULL2(data) - pending=%d/%d ack_pending=%d/%d",
-							ncci_ptr->data_pending, n, ncci_ptr->data_ack_pending, l));
-
-					return _QUEUE_FULL;
-				}
-				if (plci->req_in || plci->internal_command)
-				{
-					if ((((byte *) msg) >= ((byte *)(plci->msg_in_queue)))
-					    && (((byte *) msg) < ((byte *)(plci->msg_in_queue)) + sizeof(plci->msg_in_queue)))
-					{
-						dbug(0, dprintf("Q-FULL3(requeue)"));
-
-						return _QUEUE_FULL;
-					}
-					c = true;
-				}
-			}
-			else
-			{
-				if (plci->req_in || plci->internal_command)
-					c = true;
-				else
-				{
-					plci->command = msg->header.command;
-					plci->number = msg->header.number;
-				}
-			}
-			if (c)
-			{
-				dbug(1, dprintf("enqueue msg(0x%04x,0x%x,0x%x) - len=%d write=%d read=%d wrap=%d free=%d",
-						msg->header.command, plci->req_in, plci->internal_command,
-						msg->header.length, plci->msg_in_write_pos,
-						plci->msg_in_read_pos, plci->msg_in_wrap_pos, i));
-				if (j == 0)
-					plci->msg_in_wrap_pos = plci->msg_in_write_pos;
-				m = (CAPI_MSG *)(&((byte *)(plci->msg_in_queue))[j]);
-				for (i = 0; i < msg->header.length; i++)
-					((byte *)(plci->msg_in_queue))[j++] = ((byte *) msg)[i];
-				if (m->header.command == _DATA_B3_R)
-				{
-
-					m->info.data_b3_req.Data = (dword)(long)(TransmitBufferSet(appl, m->info.data_b3_req.Data));
-
-				}
-
-				j = (j + 3) & 0xfffc;
-
-				*((APPL **)(&((byte *)(plci->msg_in_queue))[j])) = appl;
-				plci->msg_in_write_pos = j + MSG_IN_OVERHEAD;
-				return 0;
-			}
-		}
-		else
-		{
-			plci = NULL;
-		}
-	}
-	dbug(1, dprintf("com=%x", msg->header.command));
-
-	for (j = 0; j < MAX_MSG_PARMS + 1; j++) msg_parms[j].length = 0;
-	for (i = 0, ret = _BAD_MSG; i < ARRAY_SIZE(ftable); i++) {
-
-		if (ftable[i].command == msg->header.command) {
-			/* break loop if the message is correct, otherwise continue scan  */
-			/* (for example: CONNECT_B3_T90_ACT_RES has two specifications)   */
-			if (!api_parse(msg->info.b, (word)(msg->header.length - 12), ftable[i].format, msg_parms)) {
-				ret = 0;
-				break;
-			}
-			for (j = 0; j < MAX_MSG_PARMS + 1; j++) msg_parms[j].length = 0;
-		}
-	}
-	if (ret) {
-		dbug(1, dprintf("BAD_MSG"));
-		if (plci) plci->command = 0;
-		return ret;
-	}
-
-
-	c = ftable[i].function(GET_DWORD(&msg->header.controller),
-			       msg->header.number,
-			       a,
-			       plci,
-			       appl,
-			       msg_parms);
-
-	channel_xmit_extended_xon(plci);
-
-	if (c == 1) send_req(plci);
-	if (c == 2 && plci) plci->req_in = plci->req_in_start = plci->req_out = 0;
-	if (plci && !plci->req_in) plci->command = 0;
-	return 0;
-}
-
-
-/*------------------------------------------------------------------*/
-/* api_parse function, check the format of api messages             */
-/*------------------------------------------------------------------*/
-
-static word api_parse(byte *msg, word length, byte *format, API_PARSE *parms)
-{
-	word i;
-	word p;
-
-	for (i = 0, p = 0; format[i]; i++) {
-		if (parms)
-		{
-			parms[i].info = &msg[p];
-		}
-		switch (format[i]) {
-		case 'b':
-			p += 1;
-			break;
-		case 'w':
-			p += 2;
-			break;
-		case 'd':
-			p += 4;
-			break;
-		case 's':
-			if (msg[p] == 0xff) {
-				parms[i].info += 2;
-				parms[i].length = msg[p + 1] + (msg[p + 2] << 8);
-				p += (parms[i].length + 3);
-			}
-			else {
-				parms[i].length = msg[p];
-				p += (parms[i].length + 1);
-			}
-			break;
-		}
-
-		if (p > length) return true;
-	}
-	if (parms) parms[i].info = NULL;
-	return false;
-}
-
-static void api_save_msg(API_PARSE *in, byte *format, API_SAVE *out)
-{
-	word i, j, n = 0;
-	byte *p;
-
-	p = out->info;
-	for (i = 0; format[i] != '\0'; i++)
-	{
-		out->parms[i].info = p;
-		out->parms[i].length = in[i].length;
-		switch (format[i])
-		{
-		case 'b':
-			n = 1;
-			break;
-		case 'w':
-			n = 2;
-			break;
-		case 'd':
-			n = 4;
-			break;
-		case 's':
-			n = in[i].length + 1;
-			break;
-		}
-		for (j = 0; j < n; j++)
-			*(p++) = in[i].info[j];
-	}
-	out->parms[i].info = NULL;
-	out->parms[i].length = 0;
-}
-
-static void api_load_msg(API_SAVE *in, API_PARSE *out)
-{
-	word i;
-
-	i = 0;
-	do
-	{
-		out[i].info = in->parms[i].info;
-		out[i].length = in->parms[i].length;
-	} while (in->parms[i++].info);
-}
-
-
-/*------------------------------------------------------------------*/
-/* CAPI remove function                                             */
-/*------------------------------------------------------------------*/
-
-word api_remove_start(void)
-{
-	word i;
-	word j;
-
-	if (!remove_started) {
-		remove_started = true;
-		for (i = 0; i < max_adapter; i++) {
-			if (adapter[i].request) {
-				for (j = 0; j < adapter[i].max_plci; j++) {
-					if (adapter[i].plci[j].Sig.Id) plci_remove(&adapter[i].plci[j]);
-				}
-			}
-		}
-		return 1;
-	}
-	else {
-		for (i = 0; i < max_adapter; i++) {
-			if (adapter[i].request) {
-				for (j = 0; j < adapter[i].max_plci; j++) {
-					if (adapter[i].plci[j].Sig.Id) return 1;
-				}
-			}
-		}
-	}
-	api_remove_complete();
-	return 0;
-}
-
-
-/*------------------------------------------------------------------*/
-/* internal command queue                                           */
-/*------------------------------------------------------------------*/
-
-static void init_internal_command_queue(PLCI *plci)
-{
-	word i;
-
-	dbug(1, dprintf("%s,%d: init_internal_command_queue",
-			(char *)(FILE_), __LINE__));
-
-	plci->internal_command = 0;
-	for (i = 0; i < MAX_INTERNAL_COMMAND_LEVELS; i++)
-		plci->internal_command_queue[i] = NULL;
-}
-
-
-static void start_internal_command(dword Id, PLCI *plci, t_std_internal_command command_function)
-{
-	word i;
-
-	dbug(1, dprintf("[%06lx] %s,%d: start_internal_command",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-	if (plci->internal_command == 0)
-	{
-		plci->internal_command_queue[0] = command_function;
-		(*command_function)(Id, plci, OK);
-	}
-	else
-	{
-		i = 1;
-		while (plci->internal_command_queue[i] != NULL)
-			i++;
-		plci->internal_command_queue[i] = command_function;
-	}
-}
-
-
-static void next_internal_command(dword Id, PLCI *plci)
-{
-	word i;
-
-	dbug(1, dprintf("[%06lx] %s,%d: next_internal_command",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-	plci->internal_command = 0;
-	plci->internal_command_queue[0] = NULL;
-	while (plci->internal_command_queue[1] != NULL)
-	{
-		for (i = 0; i < MAX_INTERNAL_COMMAND_LEVELS - 1; i++)
-			plci->internal_command_queue[i] = plci->internal_command_queue[i + 1];
-		plci->internal_command_queue[MAX_INTERNAL_COMMAND_LEVELS - 1] = NULL;
-		(*(plci->internal_command_queue[0]))(Id, plci, OK);
-		if (plci->internal_command != 0)
-			return;
-		plci->internal_command_queue[0] = NULL;
-	}
-}
-
-
-/*------------------------------------------------------------------*/
-/* NCCI allocate/remove function                                    */
-/*------------------------------------------------------------------*/
-
-static dword ncci_mapping_bug = 0;
-
-static word get_ncci(PLCI *plci, byte ch, word force_ncci)
-{
-	DIVA_CAPI_ADAPTER *a;
-	word ncci, i, j, k;
-
-	a = plci->adapter;
-	if (!ch || a->ch_ncci[ch])
-	{
-		ncci_mapping_bug++;
-		dbug(1, dprintf("NCCI mapping exists %ld %02x %02x %02x-%02x",
-				ncci_mapping_bug, ch, force_ncci, a->ncci_ch[a->ch_ncci[ch]], a->ch_ncci[ch]));
-		ncci = ch;
-	}
-	else
-	{
-		if (force_ncci)
-			ncci = force_ncci;
-		else
-		{
-			if ((ch < MAX_NCCI + 1) && !a->ncci_ch[ch])
-				ncci = ch;
-			else
-			{
-				ncci = 1;
-				while ((ncci < MAX_NCCI + 1) && a->ncci_ch[ncci])
-					ncci++;
-				if (ncci == MAX_NCCI + 1)
-				{
-					ncci_mapping_bug++;
-					i = 1;
-					do
-					{
-						j = 1;
-						while ((j < MAX_NCCI + 1) && (a->ncci_ch[j] != i))
-							j++;
-						k = j;
-						if (j < MAX_NCCI + 1)
-						{
-							do
-							{
-								j++;
-							} while ((j < MAX_NCCI + 1) && (a->ncci_ch[j] != i));
-						}
-					} while ((i < MAX_NL_CHANNEL + 1) && (j < MAX_NCCI + 1));
-					if (i < MAX_NL_CHANNEL + 1)
-					{
-						dbug(1, dprintf("NCCI mapping overflow %ld %02x %02x %02x-%02x-%02x",
-								ncci_mapping_bug, ch, force_ncci, i, k, j));
-					}
-					else
-					{
-						dbug(1, dprintf("NCCI mapping overflow %ld %02x %02x",
-								ncci_mapping_bug, ch, force_ncci));
-					}
-					ncci = ch;
-				}
-			}
-			a->ncci_plci[ncci] = plci->Id;
-			a->ncci_state[ncci] = IDLE;
-			if (!plci->ncci_ring_list)
-				plci->ncci_ring_list = ncci;
-			else
-				a->ncci_next[ncci] = a->ncci_next[plci->ncci_ring_list];
-			a->ncci_next[plci->ncci_ring_list] = (byte) ncci;
-		}
-		a->ncci_ch[ncci] = ch;
-		a->ch_ncci[ch] = (byte) ncci;
-		dbug(1, dprintf("NCCI mapping established %ld %02x %02x %02x-%02x",
-				ncci_mapping_bug, ch, force_ncci, ch, ncci));
-	}
-	return (ncci);
-}
-
-
-static void ncci_free_receive_buffers(PLCI *plci, word ncci)
-{
-	DIVA_CAPI_ADAPTER *a;
-	APPL *appl;
-	word i, ncci_code;
-	dword Id;
-
-	a = plci->adapter;
-	Id = (((dword) ncci) << 16) | (((word)(plci->Id)) << 8) | a->Id;
-	if (ncci)
-	{
-		if (a->ncci_plci[ncci] == plci->Id)
-		{
-			if (!plci->appl)
-			{
-				ncci_mapping_bug++;
-				dbug(1, dprintf("NCCI mapping appl expected %ld %08lx",
-						ncci_mapping_bug, Id));
-			}
-			else
-			{
-				appl = plci->appl;
-				ncci_code = ncci | (((word) a->Id) << 8);
-				for (i = 0; i < appl->MaxBuffer; i++)
-				{
-					if ((appl->DataNCCI[i] == ncci_code)
-					    && (((byte)(appl->DataFlags[i] >> 8)) == plci->Id))
-					{
-						appl->DataNCCI[i] = 0;
-					}
-				}
-			}
-		}
-	}
-	else
-	{
-		for (ncci = 1; ncci < MAX_NCCI + 1; ncci++)
-		{
-			if (a->ncci_plci[ncci] == plci->Id)
-			{
-				if (!plci->appl)
-				{
-					ncci_mapping_bug++;
-					dbug(1, dprintf("NCCI mapping no appl %ld %08lx",
-							ncci_mapping_bug, Id));
-				}
-				else
-				{
-					appl = plci->appl;
-					ncci_code = ncci | (((word) a->Id) << 8);
-					for (i = 0; i < appl->MaxBuffer; i++)
-					{
-						if ((appl->DataNCCI[i] == ncci_code)
-						    && (((byte)(appl->DataFlags[i] >> 8)) == plci->Id))
-						{
-							appl->DataNCCI[i] = 0;
-						}
-					}
-				}
-			}
-		}
-	}
-}
-
-
-static void cleanup_ncci_data(PLCI *plci, word ncci)
-{
-	NCCI *ncci_ptr;
-
-	if (ncci && (plci->adapter->ncci_plci[ncci] == plci->Id))
-	{
-		ncci_ptr = &(plci->adapter->ncci[ncci]);
-		if (plci->appl)
-		{
-			while (ncci_ptr->data_pending != 0)
-			{
-				if (!plci->data_sent || (ncci_ptr->DBuffer[ncci_ptr->data_out].P != plci->data_sent_ptr))
-					TransmitBufferFree(plci->appl, ncci_ptr->DBuffer[ncci_ptr->data_out].P);
-				(ncci_ptr->data_out)++;
-				if (ncci_ptr->data_out == MAX_DATA_B3)
-					ncci_ptr->data_out = 0;
-				(ncci_ptr->data_pending)--;
-			}
-		}
-		ncci_ptr->data_out = 0;
-		ncci_ptr->data_pending = 0;
-		ncci_ptr->data_ack_out = 0;
-		ncci_ptr->data_ack_pending = 0;
-	}
-}
-
-
-static void ncci_remove(PLCI *plci, word ncci, byte preserve_ncci)
-{
-	DIVA_CAPI_ADAPTER *a;
-	dword Id;
-	word i;
-
-	a = plci->adapter;
-	Id = (((dword) ncci) << 16) | (((word)(plci->Id)) << 8) | a->Id;
-	if (!preserve_ncci)
-		ncci_free_receive_buffers(plci, ncci);
-	if (ncci)
-	{
-		if (a->ncci_plci[ncci] != plci->Id)
-		{
-			ncci_mapping_bug++;
-			dbug(1, dprintf("NCCI mapping doesn't exist %ld %08lx %02x",
-					ncci_mapping_bug, Id, preserve_ncci));
-		}
-		else
-		{
-			cleanup_ncci_data(plci, ncci);
-			dbug(1, dprintf("NCCI mapping released %ld %08lx %02x %02x-%02x",
-					ncci_mapping_bug, Id, preserve_ncci, a->ncci_ch[ncci], ncci));
-			a->ch_ncci[a->ncci_ch[ncci]] = 0;
-			if (!preserve_ncci)
-			{
-				a->ncci_ch[ncci] = 0;
-				a->ncci_plci[ncci] = 0;
-				a->ncci_state[ncci] = IDLE;
-				i = plci->ncci_ring_list;
-				while ((i != 0) && (a->ncci_next[i] != plci->ncci_ring_list) && (a->ncci_next[i] != ncci))
-					i = a->ncci_next[i];
-				if ((i != 0) && (a->ncci_next[i] == ncci))
-				{
-					if (i == ncci)
-						plci->ncci_ring_list = 0;
-					else if (plci->ncci_ring_list == ncci)
-						plci->ncci_ring_list = i;
-					a->ncci_next[i] = a->ncci_next[ncci];
-				}
-				a->ncci_next[ncci] = 0;
-			}
-		}
-	}
-	else
-	{
-		for (ncci = 1; ncci < MAX_NCCI + 1; ncci++)
-		{
-			if (a->ncci_plci[ncci] == plci->Id)
-			{
-				cleanup_ncci_data(plci, ncci);
-				dbug(1, dprintf("NCCI mapping released %ld %08lx %02x %02x-%02x",
-						ncci_mapping_bug, Id, preserve_ncci, a->ncci_ch[ncci], ncci));
-				a->ch_ncci[a->ncci_ch[ncci]] = 0;
-				if (!preserve_ncci)
-				{
-					a->ncci_ch[ncci] = 0;
-					a->ncci_plci[ncci] = 0;
-					a->ncci_state[ncci] = IDLE;
-					a->ncci_next[ncci] = 0;
-				}
-			}
-		}
-		if (!preserve_ncci)
-			plci->ncci_ring_list = 0;
-	}
-}
-
-
-/*------------------------------------------------------------------*/
-/* PLCI remove function                                             */
-/*------------------------------------------------------------------*/
-
-static void plci_free_msg_in_queue(PLCI *plci)
-{
-	word i;
-
-	if (plci->appl)
-	{
-		i = plci->msg_in_read_pos;
-		while (i != plci->msg_in_write_pos)
-		{
-			if (i == plci->msg_in_wrap_pos)
-				i = 0;
-			if (((CAPI_MSG *)(&((byte *)(plci->msg_in_queue))[i]))->header.command == _DATA_B3_R)
-			{
-
-				TransmitBufferFree(plci->appl,
-						   (byte *)(long)(((CAPI_MSG *)(&((byte *)(plci->msg_in_queue))[i]))->info.data_b3_req.Data));
-
-			}
-
-			i += (((CAPI_MSG *)(&((byte *)(plci->msg_in_queue))[i]))->header.length +
-			      MSG_IN_OVERHEAD + 3) & 0xfffc;
-
-		}
-	}
-	plci->msg_in_write_pos = MSG_IN_QUEUE_SIZE;
-	plci->msg_in_read_pos = MSG_IN_QUEUE_SIZE;
-	plci->msg_in_wrap_pos = MSG_IN_QUEUE_SIZE;
-}
-
-
-static void plci_remove(PLCI *plci)
-{
-
-	if (!plci) {
-		dbug(1, dprintf("plci_remove(no plci)"));
-		return;
-	}
-	init_internal_command_queue(plci);
-	dbug(1, dprintf("plci_remove(%x,tel=%x)", plci->Id, plci->tel));
-	if (plci_remove_check(plci))
-	{
-		return;
-	}
-	if (plci->Sig.Id == 0xff)
-	{
-		dbug(1, dprintf("D-channel X.25 plci->NL.Id:%0x", plci->NL.Id));
-		if (plci->NL.Id && !plci->nl_remove_id)
-		{
-			nl_req_ncci(plci, REMOVE, 0);
-			send_req(plci);
-		}
-	}
-	else
-	{
-		if (!plci->sig_remove_id
-		    && (plci->Sig.Id
-			|| (plci->req_in != plci->req_out)
-			|| (plci->nl_req || plci->sig_req)))
-		{
-			sig_req(plci, HANGUP, 0);
-			send_req(plci);
-		}
-	}
-	ncci_remove(plci, 0, false);
-	plci_free_msg_in_queue(plci);
-
-	plci->channels = 0;
-	plci->appl = NULL;
-	if ((plci->State == INC_CON_PENDING) || (plci->State == INC_CON_ALERT))
-		plci->State = OUTG_DIS_PENDING;
-}
-
-/*------------------------------------------------------------------*/
-/* translation function for each message                            */
-/*------------------------------------------------------------------*/
-
-static byte connect_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word ch;
-	word i;
-	word Info;
-	byte LinkLayer;
-	API_PARSE *ai;
-	API_PARSE *bp;
-	API_PARSE ai_parms[5];
-	word channel = 0;
-	dword ch_mask;
-	byte m;
-	static byte esc_chi[35] = {0x02, 0x18, 0x01};
-	static byte lli[2] = {0x01, 0x00};
-	byte noCh = 0;
-	word dir = 0;
-	byte *p_chi = "";
-
-	for (i = 0; i < 5; i++) ai_parms[i].length = 0;
-
-	dbug(1, dprintf("connect_req(%d)", parms->length));
-	Info = _WRONG_IDENTIFIER;
-	if (a)
-	{
-		if (a->adapter_disabled)
-		{
-			dbug(1, dprintf("adapter disabled"));
-			Id = ((word)1 << 8) | a->Id;
-			sendf(appl, _CONNECT_R | CONFIRM, Id, Number, "w", 0);
-			sendf(appl, _DISCONNECT_I, Id, 0, "w", _L1_ERROR);
-			return false;
-		}
-		Info = _OUT_OF_PLCI;
-		if ((i = get_plci(a)))
-		{
-			Info = 0;
-			plci = &a->plci[i - 1];
-			plci->appl = appl;
-			plci->call_dir = CALL_DIR_OUT | CALL_DIR_ORIGINATE;
-			/* check 'external controller' bit for codec support */
-			if (Id & EXT_CONTROLLER)
-			{
-				if (AdvCodecSupport(a, plci, appl, 0))
-				{
-					plci->Id = 0;
-					sendf(appl, _CONNECT_R | CONFIRM, Id, Number, "w", _WRONG_IDENTIFIER);
-					return 2;
-				}
-			}
-			ai = &parms[9];
-			bp = &parms[5];
-			ch = 0;
-			if (bp->length)LinkLayer = bp->info[3];
-			else LinkLayer = 0;
-			if (ai->length)
-			{
-				ch = 0xffff;
-				if (!api_parse(&ai->info[1], (word)ai->length, "ssss", ai_parms))
-				{
-					ch = 0;
-					if (ai_parms[0].length)
-					{
-						ch = GET_WORD(ai_parms[0].info + 1);
-						if (ch > 4) ch = 0; /* safety -> ignore ChannelID */
-						if (ch == 4) /* explizit CHI in message */
-						{
-							/* check length of B-CH struct */
-							if ((ai_parms[0].info)[3] >= 1)
-							{
-								if ((ai_parms[0].info)[4] == CHI)
-								{
-									p_chi = &((ai_parms[0].info)[5]);
-								}
-								else
-								{
-									p_chi = &((ai_parms[0].info)[3]);
-								}
-								if (p_chi[0] > 35) /* check length of channel ID */
-								{
-									Info = _WRONG_MESSAGE_FORMAT;
-								}
-							}
-							else Info = _WRONG_MESSAGE_FORMAT;
-						}
-
-						if (ch == 3 && ai_parms[0].length >= 7 && ai_parms[0].length <= 36)
-						{
-							dir = GET_WORD(ai_parms[0].info + 3);
-							ch_mask = 0;
-							m = 0x3f;
-							for (i = 0; i + 5 <= ai_parms[0].length; i++)
-							{
-								if (ai_parms[0].info[i + 5] != 0)
-								{
-									if ((ai_parms[0].info[i + 5] | m) != 0xff)
-										Info = _WRONG_MESSAGE_FORMAT;
-									else
-									{
-										if (ch_mask == 0)
-											channel = i;
-										ch_mask |= 1L << i;
-									}
-								}
-								m = 0;
-							}
-							if (ch_mask == 0)
-								Info = _WRONG_MESSAGE_FORMAT;
-							if (!Info)
-							{
-								if ((ai_parms[0].length == 36) || (ch_mask != ((dword)(1L << channel))))
-								{
-									esc_chi[0] = (byte)(ai_parms[0].length - 2);
-									for (i = 0; i + 5 <= ai_parms[0].length; i++)
-										esc_chi[i + 3] = ai_parms[0].info[i + 5];
-								}
-								else
-									esc_chi[0] = 2;
-								esc_chi[2] = (byte)channel;
-								plci->b_channel = (byte)channel; /* not correct for ETSI ch 17..31 */
-								add_p(plci, LLI, lli);
-								add_p(plci, ESC, esc_chi);
-								plci->State = LOCAL_CONNECT;
-								if (!dir) plci->call_dir |= CALL_DIR_FORCE_OUTG_NL;     /* dir 0=DTE, 1=DCE */
-							}
-						}
-					}
-				}
-				else  Info = _WRONG_MESSAGE_FORMAT;
-			}
-
-			dbug(1, dprintf("ch=%x,dir=%x,p_ch=%d", ch, dir, channel));
-			plci->command = _CONNECT_R;
-			plci->number = Number;
-			/* x.31 or D-ch free SAPI in LinkLayer? */
-			if (ch == 1 && LinkLayer != 3 && LinkLayer != 12) noCh = true;
-			if ((ch == 0 || ch == 2 || noCh || ch == 3 || ch == 4) && !Info)
-			{
-				/* B-channel used for B3 connections (ch==0), or no B channel    */
-				/* is used (ch==2) or perm. connection (3) is used  do a CALL    */
-				if (noCh) Info = add_b1(plci, &parms[5], 2, 0);    /* no resource    */
-				else     Info = add_b1(plci, &parms[5], ch, 0);
-				add_s(plci, OAD, &parms[2]);
-				add_s(plci, OSA, &parms[4]);
-				add_s(plci, BC, &parms[6]);
-				add_s(plci, LLC, &parms[7]);
-				add_s(plci, HLC, &parms[8]);
-				if (a->Info_Mask[appl->Id - 1] & 0x200)
-				{
-					/* early B3 connect (CIP mask bit 9) no release after a disc */
-					add_p(plci, LLI, "\x01\x01");
-				}
-				if (GET_WORD(parms[0].info) < 29) {
-					add_p(plci, BC, cip_bc[GET_WORD(parms[0].info)][a->u_law]);
-					add_p(plci, HLC, cip_hlc[GET_WORD(parms[0].info)]);
-				}
-				add_p(plci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-				sig_req(plci, ASSIGN, DSIG_ID);
-			}
-			else if (ch == 1) {
-
-				/* D-Channel used for B3 connections */
-				plci->Sig.Id = 0xff;
-				Info = 0;
-			}
-
-			if (!Info && ch != 2 && !noCh) {
-				Info = add_b23(plci, &parms[5]);
-				if (!Info) {
-					if (!(plci->tel && !plci->adv_nl))nl_req_ncci(plci, ASSIGN, 0);
-				}
-			}
-
-			if (!Info)
-			{
-				if (ch == 0 || ch == 2 || ch == 3 || noCh || ch == 4)
-				{
-					if (plci->spoofed_msg == SPOOFING_REQUIRED)
-					{
-						api_save_msg(parms, "wsssssssss", &plci->saved_msg);
-						plci->spoofed_msg = CALL_REQ;
-						plci->internal_command = BLOCK_PLCI;
-						plci->command = 0;
-						dbug(1, dprintf("Spoof"));
-						send_req(plci);
-						return false;
-					}
-					if (ch == 4)add_p(plci, CHI, p_chi);
-					add_s(plci, CPN, &parms[1]);
-					add_s(plci, DSA, &parms[3]);
-					if (noCh) add_p(plci, ESC, "\x02\x18\xfd");  /* D-channel, no B-L3 */
-					add_ai(plci, &parms[9]);
-					if (!dir)sig_req(plci, CALL_REQ, 0);
-					else
-					{
-						plci->command = PERM_LIST_REQ;
-						plci->appl = appl;
-						sig_req(plci, LISTEN_REQ, 0);
-						send_req(plci);
-						return false;
-					}
-				}
-				send_req(plci);
-				return false;
-			}
-			plci->Id = 0;
-		}
-	}
-	sendf(appl,
-	      _CONNECT_R | CONFIRM,
-	      Id,
-	      Number,
-	      "w", Info);
-	return 2;
-}
-
-static byte connect_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word i, Info;
-	word Reject;
-	static byte cau_t[] = {0, 0, 0x90, 0x91, 0xac, 0x9d, 0x86, 0xd8, 0x9b};
-	static byte esc_t[] = {0x03, 0x08, 0x00, 0x00};
-	API_PARSE *ai;
-	API_PARSE ai_parms[5];
-	word ch = 0;
-
-	if (!plci) {
-		dbug(1, dprintf("connect_res(no plci)"));
-		return 0;  /* no plci, no send */
-	}
-
-	dbug(1, dprintf("connect_res(State=0x%x)", plci->State));
-	for (i = 0; i < 5; i++) ai_parms[i].length = 0;
-	ai = &parms[5];
-	dbug(1, dprintf("ai->length=%d", ai->length));
-
-	if (ai->length)
-	{
-		if (!api_parse(&ai->info[1], (word)ai->length, "ssss", ai_parms))
-		{
-			dbug(1, dprintf("ai_parms[0].length=%d/0x%x", ai_parms[0].length, GET_WORD(ai_parms[0].info + 1)));
-			ch = 0;
-			if (ai_parms[0].length)
-			{
-				ch = GET_WORD(ai_parms[0].info + 1);
-				dbug(1, dprintf("BCH-I=0x%x", ch));
-			}
-		}
-	}
-
-	if (plci->State == INC_CON_CONNECTED_ALERT)
-	{
-		dbug(1, dprintf("Connected Alert Call_Res"));
-		if (a->Info_Mask[appl->Id - 1] & 0x200)
-		{
-			/* early B3 connect (CIP mask bit 9) no release after a disc */
-			add_p(plci, LLI, "\x01\x01");
-		}
-		add_s(plci, CONN_NR, &parms[2]);
-		add_s(plci, LLC, &parms[4]);
-		add_ai(plci, &parms[5]);
-		plci->State = INC_CON_ACCEPT;
-		sig_req(plci, CALL_RES, 0);
-		return 1;
-	}
-	else if (plci->State == INC_CON_PENDING || plci->State == INC_CON_ALERT) {
-		__clear_bit(appl->Id - 1, plci->c_ind_mask_table);
-		dbug(1, dprintf("c_ind_mask =%*pb", MAX_APPL, plci->c_ind_mask_table));
-		Reject = GET_WORD(parms[0].info);
-		dbug(1, dprintf("Reject=0x%x", Reject));
-		if (Reject)
-		{
-			if (bitmap_empty(plci->c_ind_mask_table, MAX_APPL))
-			{
-				if ((Reject & 0xff00) == 0x3400)
-				{
-					esc_t[2] = ((byte)(Reject & 0x00ff)) | 0x80;
-					add_p(plci, ESC, esc_t);
-					add_ai(plci, &parms[5]);
-					sig_req(plci, REJECT, 0);
-				}
-				else if (Reject == 1 || Reject >= 9)
-				{
-					add_ai(plci, &parms[5]);
-					sig_req(plci, HANGUP, 0);
-				}
-				else
-				{
-					esc_t[2] = cau_t[(Reject&0x000f)];
-					add_p(plci, ESC, esc_t);
-					add_ai(plci, &parms[5]);
-					sig_req(plci, REJECT, 0);
-				}
-				plci->appl = appl;
-			}
-			else
-			{
-				sendf(appl, _DISCONNECT_I, Id, 0, "w", _OTHER_APPL_CONNECTED);
-			}
-		}
-		else {
-			plci->appl = appl;
-			if (Id & EXT_CONTROLLER) {
-				if (AdvCodecSupport(a, plci, appl, 0)) {
-					dbug(1, dprintf("connect_res(error from AdvCodecSupport)"));
-					sig_req(plci, HANGUP, 0);
-					return 1;
-				}
-				if (plci->tel == ADV_VOICE && a->AdvCodecPLCI)
-				{
-					Info = add_b23(plci, &parms[1]);
-					if (Info)
-					{
-						dbug(1, dprintf("connect_res(error from add_b23)"));
-						sig_req(plci, HANGUP, 0);
-						return 1;
-					}
-					if (plci->adv_nl)
-					{
-						nl_req_ncci(plci, ASSIGN, 0);
-					}
-				}
-			}
-			else
-			{
-				plci->tel = 0;
-				if (ch != 2)
-				{
-					Info = add_b23(plci, &parms[1]);
-					if (Info)
-					{
-						dbug(1, dprintf("connect_res(error from add_b23 2)"));
-						sig_req(plci, HANGUP, 0);
-						return 1;
-					}
-				}
-				nl_req_ncci(plci, ASSIGN, 0);
-			}
-
-			if (plci->spoofed_msg == SPOOFING_REQUIRED)
-			{
-				api_save_msg(parms, "wsssss", &plci->saved_msg);
-				plci->spoofed_msg = CALL_RES;
-				plci->internal_command = BLOCK_PLCI;
-				plci->command = 0;
-				dbug(1, dprintf("Spoof"));
-			}
-			else
-			{
-				add_b1(plci, &parms[1], ch, plci->B1_facilities);
-				if (a->Info_Mask[appl->Id - 1] & 0x200)
-				{
-					/* early B3 connect (CIP mask bit 9) no release after a disc */
-					add_p(plci, LLI, "\x01\x01");
-				}
-				add_s(plci, CONN_NR, &parms[2]);
-				add_s(plci, LLC, &parms[4]);
-				add_ai(plci, &parms[5]);
-				plci->State = INC_CON_ACCEPT;
-				sig_req(plci, CALL_RES, 0);
-			}
-
-			for_each_set_bit(i, plci->c_ind_mask_table, max_appl)
-				sendf(&application[i], _DISCONNECT_I, Id, 0, "w", _OTHER_APPL_CONNECTED);
-		}
-	}
-	return 1;
-}
-
-static byte connect_a_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			  PLCI *plci, APPL *appl, API_PARSE *msg)
-{
-	dbug(1, dprintf("connect_a_res"));
-	return false;
-}
-
-static byte disconnect_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			   PLCI *plci, APPL *appl, API_PARSE *msg)
-{
-	word Info;
-	word i;
-
-	dbug(1, dprintf("disconnect_req"));
-
-	Info = _WRONG_IDENTIFIER;
-
-	if (plci)
-	{
-		if (plci->State == INC_CON_PENDING || plci->State == INC_CON_ALERT)
-		{
-			__clear_bit(appl->Id - 1, plci->c_ind_mask_table);
-			plci->appl = appl;
-			for_each_set_bit(i, plci->c_ind_mask_table, max_appl)
-				sendf(&application[i], _DISCONNECT_I, Id, 0, "w", 0);
-			plci->State = OUTG_DIS_PENDING;
-		}
-		if (plci->Sig.Id && plci->appl)
-		{
-			Info = 0;
-			if (plci->Sig.Id != 0xff)
-			{
-				if (plci->State != INC_DIS_PENDING)
-				{
-					add_ai(plci, &msg[0]);
-					sig_req(plci, HANGUP, 0);
-					plci->State = OUTG_DIS_PENDING;
-					return 1;
-				}
-			}
-			else
-			{
-				if (plci->NL.Id && !plci->nl_remove_id)
-				{
-					mixer_remove(plci);
-					nl_req_ncci(plci, REMOVE, 0);
-					sendf(appl, _DISCONNECT_R | CONFIRM, Id, Number, "w", 0);
-					sendf(appl, _DISCONNECT_I, Id, 0, "w", 0);
-					plci->State = INC_DIS_PENDING;
-				}
-				return 1;
-			}
-		}
-	}
-
-	if (!appl)  return false;
-	sendf(appl, _DISCONNECT_R | CONFIRM, Id, Number, "w", Info);
-	return false;
-}
-
-static byte disconnect_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			   PLCI *plci, APPL *appl, API_PARSE *msg)
-{
-	dbug(1, dprintf("disconnect_res"));
-	if (plci)
-	{
-		/* clear ind mask bit, just in case of collsion of          */
-		/* DISCONNECT_IND and CONNECT_RES                           */
-		__clear_bit(appl->Id - 1, plci->c_ind_mask_table);
-		ncci_free_receive_buffers(plci, 0);
-		if (plci_remove_check(plci))
-		{
-			return 0;
-		}
-		if (plci->State == INC_DIS_PENDING
-		    || plci->State == SUSPENDING) {
-			if (bitmap_empty(plci->c_ind_mask_table, MAX_APPL)) {
-				if (plci->State != SUSPENDING) plci->State = IDLE;
-				dbug(1, dprintf("chs=%d", plci->channels));
-				if (!plci->channels) {
-					plci_remove(plci);
-				}
-			}
-		}
-	}
-	return 0;
-}
-
-static byte listen_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-		       PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word Info;
-	byte i;
-
-	dbug(1, dprintf("listen_req(Appl=0x%x)", appl->Id));
-
-	Info = _WRONG_IDENTIFIER;
-	if (a) {
-		Info = 0;
-		a->Info_Mask[appl->Id - 1] = GET_DWORD(parms[0].info);
-		a->CIP_Mask[appl->Id - 1] = GET_DWORD(parms[1].info);
-		dbug(1, dprintf("CIP_MASK=0x%lx", GET_DWORD(parms[1].info)));
-		if (a->Info_Mask[appl->Id - 1] & 0x200) { /* early B3 connect provides */
-			a->Info_Mask[appl->Id - 1] |=  0x10;   /* call progression infos    */
-		}
-
-		/* check if external controller listen and switch listen on or off*/
-		if (Id&EXT_CONTROLLER && GET_DWORD(parms[1].info)) {
-			if (a->profile.Global_Options & ON_BOARD_CODEC) {
-				dummy_plci.State = IDLE;
-				a->codec_listen[appl->Id - 1] = &dummy_plci;
-				a->TelOAD[0] = (byte)(parms[3].length);
-				for (i = 1; parms[3].length >= i && i < 22; i++) {
-					a->TelOAD[i] = parms[3].info[i];
-				}
-				a->TelOAD[i] = 0;
-				a->TelOSA[0] = (byte)(parms[4].length);
-				for (i = 1; parms[4].length >= i && i < 22; i++) {
-					a->TelOSA[i] = parms[4].info[i];
-				}
-				a->TelOSA[i] = 0;
-			}
-			else Info = 0x2002; /* wrong controller, codec not supported */
-		}
-		else{               /* clear listen */
-			a->codec_listen[appl->Id - 1] = (PLCI *)0;
-		}
-	}
-	sendf(appl,
-	      _LISTEN_R | CONFIRM,
-	      Id,
-	      Number,
-	      "w", Info);
-
-	if (a) listen_check(a);
-	return false;
-}
-
-static byte info_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-		     PLCI *plci, APPL *appl, API_PARSE *msg)
-{
-	word i;
-	API_PARSE *ai;
-	PLCI *rc_plci = NULL;
-	API_PARSE ai_parms[5];
-	word Info = 0;
-
-	dbug(1, dprintf("info_req"));
-	for (i = 0; i < 5; i++) ai_parms[i].length = 0;
-
-	ai = &msg[1];
-
-	if (ai->length)
-	{
-		if (api_parse(&ai->info[1], (word)ai->length, "ssss", ai_parms))
-		{
-			dbug(1, dprintf("AddInfo wrong"));
-			Info = _WRONG_MESSAGE_FORMAT;
-		}
-	}
-	if (!a) Info = _WRONG_STATE;
-
-	if (!Info && plci)
-	{                /* no fac, with CPN, or KEY */
-		rc_plci = plci;
-		if (!ai_parms[3].length && plci->State && (msg[0].length || ai_parms[1].length))
-		{
-			/* overlap sending option */
-			dbug(1, dprintf("OvlSnd"));
-			add_s(plci, CPN, &msg[0]);
-			add_s(plci, KEY, &ai_parms[1]);
-			sig_req(plci, INFO_REQ, 0);
-			send_req(plci);
-			return false;
-		}
-
-		if (plci->State && ai_parms[2].length)
-		{
-			/* User_Info option */
-			dbug(1, dprintf("UUI"));
-			add_s(plci, UUI, &ai_parms[2]);
-			sig_req(plci, USER_DATA, 0);
-		}
-		else if (plci->State && ai_parms[3].length)
-		{
-			/* Facility option */
-			dbug(1, dprintf("FAC"));
-			add_s(plci, CPN, &msg[0]);
-			add_ai(plci, &msg[1]);
-			sig_req(plci, FACILITY_REQ, 0);
-		}
-		else
-		{
-			Info = _WRONG_STATE;
-		}
-	}
-	else if ((ai_parms[1].length || ai_parms[2].length || ai_parms[3].length) && !Info)
-	{
-		/* NCR_Facility option -> send UUI and Keypad too */
-		dbug(1, dprintf("NCR_FAC"));
-		if ((i = get_plci(a)))
-		{
-			rc_plci = &a->plci[i - 1];
-			appl->NullCREnable = true;
-			rc_plci->internal_command = C_NCR_FAC_REQ;
-			rc_plci->appl = appl;
-			add_p(rc_plci, CAI, "\x01\x80");
-			add_p(rc_plci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-			sig_req(rc_plci, ASSIGN, DSIG_ID);
-			send_req(rc_plci);
-		}
-		else
-		{
-			Info = _OUT_OF_PLCI;
-		}
-
-		if (!Info)
-		{
-			add_s(rc_plci, CPN, &msg[0]);
-			add_ai(rc_plci, &msg[1]);
-			sig_req(rc_plci, NCR_FACILITY, 0);
-			send_req(rc_plci);
-			return false;
-			/* for application controlled supplementary services    */
-		}
-	}
-
-	if (!rc_plci)
-	{
-		Info = _WRONG_MESSAGE_FORMAT;
-	}
-
-	if (!Info)
-	{
-		send_req(rc_plci);
-	}
-	else
-	{  /* appl is not assigned to a PLCI or error condition */
-		dbug(1, dprintf("localInfoCon"));
-		sendf(appl,
-		      _INFO_R | CONFIRM,
-		      Id,
-		      Number,
-		      "w", Info);
-	}
-	return false;
-}
-
-static byte info_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-		     PLCI *plci, APPL *appl, API_PARSE *msg)
-{
-	dbug(1, dprintf("info_res"));
-	return false;
-}
-
-static byte alert_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-		      PLCI *plci, APPL *appl, API_PARSE *msg)
-{
-	word Info;
-	byte ret;
-
-	dbug(1, dprintf("alert_req"));
-
-	Info = _WRONG_IDENTIFIER;
-	ret = false;
-	if (plci) {
-		Info = _ALERT_IGNORED;
-		if (plci->State != INC_CON_ALERT) {
-			Info = _WRONG_STATE;
-			if (plci->State == INC_CON_PENDING) {
-				Info = 0;
-				plci->State = INC_CON_ALERT;
-				add_ai(plci, &msg[0]);
-				sig_req(plci, CALL_ALERT, 0);
-				ret = 1;
-			}
-		}
-	}
-	sendf(appl,
-	      _ALERT_R | CONFIRM,
-	      Id,
-	      Number,
-	      "w", Info);
-	return ret;
-}
-
-static byte facility_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			 PLCI *plci, APPL *appl, API_PARSE *msg)
-{
-	word Info = 0;
-	word i    = 0;
-
-	word selector;
-	word SSreq;
-	long relatedPLCIvalue;
-	DIVA_CAPI_ADAPTER *relatedadapter;
-	byte *SSparms  = "";
-	byte RCparms[]  = "\x05\x00\x00\x02\x00\x00";
-	byte SSstruct[] = "\x09\x00\x00\x06\x00\x00\x00\x00\x00\x00";
-	API_PARSE *parms;
-	API_PARSE ss_parms[11];
-	PLCI *rplci;
-	byte cai[15];
-	dword d;
-	API_PARSE dummy;
-
-	dbug(1, dprintf("facility_req"));
-	for (i = 0; i < 9; i++) ss_parms[i].length = 0;
-
-	parms = &msg[1];
-
-	if (!a)
-	{
-		dbug(1, dprintf("wrong Ctrl"));
-		Info = _WRONG_IDENTIFIER;
-	}
-
-	selector = GET_WORD(msg[0].info);
-
-	if (!Info)
-	{
-		switch (selector)
-		{
-		case SELECTOR_HANDSET:
-			Info = AdvCodecSupport(a, plci, appl, HOOK_SUPPORT);
-			break;
-
-		case SELECTOR_SU_SERV:
-			if (!msg[1].length)
-			{
-				Info = _WRONG_MESSAGE_FORMAT;
-				break;
-			}
-			SSreq = GET_WORD(&(msg[1].info[1]));
-			PUT_WORD(&RCparms[1], SSreq);
-			SSparms = RCparms;
-			switch (SSreq)
-			{
-			case S_GET_SUPPORTED_SERVICES:
-				if ((i = get_plci(a)))
-				{
-					rplci = &a->plci[i - 1];
-					rplci->appl = appl;
-					add_p(rplci, CAI, "\x01\x80");
-					add_p(rplci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-					sig_req(rplci, ASSIGN, DSIG_ID);
-					send_req(rplci);
-				}
-				else
-				{
-					PUT_DWORD(&SSstruct[6], MASK_TERMINAL_PORTABILITY);
-					SSparms = (byte *)SSstruct;
-					break;
-				}
-				rplci->internal_command = GETSERV_REQ_PEND;
-				rplci->number = Number;
-				rplci->appl = appl;
-				sig_req(rplci, S_SUPPORTED, 0);
-				send_req(rplci);
-				return false;
-				break;
-
-			case S_LISTEN:
-				if (parms->length == 7)
-				{
-					if (api_parse(&parms->info[1], (word)parms->length, "wbd", ss_parms))
-					{
-						dbug(1, dprintf("format wrong"));
-						Info = _WRONG_MESSAGE_FORMAT;
-						break;
-					}
-				}
-				else
-				{
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				a->Notification_Mask[appl->Id - 1] = GET_DWORD(ss_parms[2].info);
-				if (a->Notification_Mask[appl->Id - 1] & SMASK_MWI) /* MWI active? */
-				{
-					if ((i = get_plci(a)))
-					{
-						rplci = &a->plci[i - 1];
-						rplci->appl = appl;
-						add_p(rplci, CAI, "\x01\x80");
-						add_p(rplci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-						sig_req(rplci, ASSIGN, DSIG_ID);
-						send_req(rplci);
-					}
-					else
-					{
-						break;
-					}
-					rplci->internal_command = GET_MWI_STATE;
-					rplci->number = Number;
-					sig_req(rplci, MWI_POLL, 0);
-					send_req(rplci);
-				}
-				break;
-
-			case S_HOLD:
-				api_parse(&parms->info[1], (word)parms->length, "ws", ss_parms);
-				if (plci && plci->State && plci->SuppState == IDLE)
-				{
-					plci->SuppState = HOLD_REQUEST;
-					plci->command = C_HOLD_REQ;
-					add_s(plci, CAI, &ss_parms[1]);
-					sig_req(plci, CALL_HOLD, 0);
-					send_req(plci);
-					return false;
-				}
-				else Info = 0x3010;                    /* wrong state           */
-				break;
-			case S_RETRIEVE:
-				if (plci && plci->State && plci->SuppState == CALL_HELD)
-				{
-					if (Id & EXT_CONTROLLER)
-					{
-						if (AdvCodecSupport(a, plci, appl, 0))
-						{
-							Info = 0x3010;                    /* wrong state           */
-							break;
-						}
-					}
-					else plci->tel = 0;
-
-					plci->SuppState = RETRIEVE_REQUEST;
-					plci->command = C_RETRIEVE_REQ;
-					if (plci->spoofed_msg == SPOOFING_REQUIRED)
-					{
-						plci->spoofed_msg = CALL_RETRIEVE;
-						plci->internal_command = BLOCK_PLCI;
-						plci->command = 0;
-						dbug(1, dprintf("Spoof"));
-						return false;
-					}
-					else
-					{
-						sig_req(plci, CALL_RETRIEVE, 0);
-						send_req(plci);
-						return false;
-					}
-				}
-				else Info = 0x3010;                    /* wrong state           */
-				break;
-			case S_SUSPEND:
-				if (parms->length)
-				{
-					if (api_parse(&parms->info[1], (word)parms->length, "wbs", ss_parms))
-					{
-						dbug(1, dprintf("format wrong"));
-						Info = _WRONG_MESSAGE_FORMAT;
-						break;
-					}
-				}
-				if (plci && plci->State)
-				{
-					add_s(plci, CAI, &ss_parms[2]);
-					plci->command = SUSPEND_REQ;
-					sig_req(plci, SUSPEND, 0);
-					plci->State = SUSPENDING;
-					send_req(plci);
-				}
-				else Info = 0x3010;                    /* wrong state           */
-				break;
-
-			case S_RESUME:
-				if (!(i = get_plci(a)))
-				{
-					Info = _OUT_OF_PLCI;
-					break;
-				}
-				rplci = &a->plci[i - 1];
-				rplci->appl = appl;
-				rplci->number = Number;
-				rplci->tel = 0;
-				rplci->call_dir = CALL_DIR_OUT | CALL_DIR_ORIGINATE;
-				/* check 'external controller' bit for codec support */
-				if (Id & EXT_CONTROLLER)
-				{
-					if (AdvCodecSupport(a, rplci, appl, 0))
-					{
-						rplci->Id = 0;
-						Info = 0x300A;
-						break;
-					}
-				}
-				if (parms->length)
-				{
-					if (api_parse(&parms->info[1], (word)parms->length, "wbs", ss_parms))
-					{
-						dbug(1, dprintf("format wrong"));
-						rplci->Id = 0;
-						Info = _WRONG_MESSAGE_FORMAT;
-						break;
-					}
-				}
-				dummy.length = 0;
-				dummy.info = "\x00";
-				add_b1(rplci, &dummy, 0, 0);
-				if (a->Info_Mask[appl->Id - 1] & 0x200)
-				{
-					/* early B3 connect (CIP mask bit 9) no release after a disc */
-					add_p(rplci, LLI, "\x01\x01");
-				}
-				add_p(rplci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-				sig_req(rplci, ASSIGN, DSIG_ID);
-				send_req(rplci);
-				add_s(rplci, CAI, &ss_parms[2]);
-				rplci->command = RESUME_REQ;
-				sig_req(rplci, RESUME, 0);
-				rplci->State = RESUMING;
-				send_req(rplci);
-				break;
-
-			case S_CONF_BEGIN: /* Request */
-			case S_CONF_DROP:
-			case S_CONF_ISOLATE:
-			case S_CONF_REATTACH:
-				if (api_parse(&parms->info[1], (word)parms->length, "wbd", ss_parms))
-				{
-					dbug(1, dprintf("format wrong"));
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				if (plci && plci->State && ((plci->SuppState == IDLE) || (plci->SuppState == CALL_HELD)))
-				{
-					d = GET_DWORD(ss_parms[2].info);
-					if (d >= 0x80)
-					{
-						dbug(1, dprintf("format wrong"));
-						Info = _WRONG_MESSAGE_FORMAT;
-						break;
-					}
-					plci->ptyState = (byte)SSreq;
-					plci->command = 0;
-					cai[0] = 2;
-					switch (SSreq)
-					{
-					case S_CONF_BEGIN:
-						cai[1] = CONF_BEGIN;
-						plci->internal_command = CONF_BEGIN_REQ_PEND;
-						break;
-					case S_CONF_DROP:
-						cai[1] = CONF_DROP;
-						plci->internal_command = CONF_DROP_REQ_PEND;
-						break;
-					case S_CONF_ISOLATE:
-						cai[1] = CONF_ISOLATE;
-						plci->internal_command = CONF_ISOLATE_REQ_PEND;
-						break;
-					case S_CONF_REATTACH:
-						cai[1] = CONF_REATTACH;
-						plci->internal_command = CONF_REATTACH_REQ_PEND;
-						break;
-					}
-					cai[2] = (byte)d; /* Conference Size resp. PartyId */
-					add_p(plci, CAI, cai);
-					sig_req(plci, S_SERVICE, 0);
-					send_req(plci);
-					return false;
-				}
-				else Info = 0x3010;                    /* wrong state           */
-				break;
-
-			case S_ECT:
-			case S_3PTY_BEGIN:
-			case S_3PTY_END:
-			case S_CONF_ADD:
-				if (parms->length == 7)
-				{
-					if (api_parse(&parms->info[1], (word)parms->length, "wbd", ss_parms))
-					{
-						dbug(1, dprintf("format wrong"));
-						Info = _WRONG_MESSAGE_FORMAT;
-						break;
-					}
-				}
-				else if (parms->length == 8) /* workaround for the T-View-S */
-				{
-					if (api_parse(&parms->info[1], (word)parms->length, "wbdb", ss_parms))
-					{
-						dbug(1, dprintf("format wrong"));
-						Info = _WRONG_MESSAGE_FORMAT;
-						break;
-					}
-				}
-				else
-				{
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				if (!msg[1].length)
-				{
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				if (!plci)
-				{
-					Info = _WRONG_IDENTIFIER;
-					break;
-				}
-				relatedPLCIvalue = GET_DWORD(ss_parms[2].info);
-				relatedPLCIvalue &= 0x0000FFFF;
-				dbug(1, dprintf("PTY/ECT/addCONF,relPLCI=%lx", relatedPLCIvalue));
-				/* controller starts with 0 up to (max_adapter - 1) */
-				if (((relatedPLCIvalue & 0x7f) == 0)
-				    || (MapController((byte)(relatedPLCIvalue & 0x7f)) == 0)
-				    || (MapController((byte)(relatedPLCIvalue & 0x7f)) > max_adapter))
-				{
-					if (SSreq == S_3PTY_END)
-					{
-						dbug(1, dprintf("wrong Controller use 2nd PLCI=PLCI"));
-						rplci = plci;
-					}
-					else
-					{
-						Info = 0x3010;                    /* wrong state           */
-						break;
-					}
-				}
-				else
-				{
-					relatedadapter = &adapter[MapController((byte)(relatedPLCIvalue & 0x7f)) - 1];
-					relatedPLCIvalue >>= 8;
-					/* find PLCI PTR*/
-					for (i = 0, rplci = NULL; i < relatedadapter->max_plci; i++)
-					{
-						if (relatedadapter->plci[i].Id == (byte)relatedPLCIvalue)
-						{
-							rplci = &relatedadapter->plci[i];
-						}
-					}
-					if (!rplci || !relatedPLCIvalue)
-					{
-						if (SSreq == S_3PTY_END)
-						{
-							dbug(1, dprintf("use 2nd PLCI=PLCI"));
-							rplci = plci;
-						}
-						else
-						{
-							Info = 0x3010;                    /* wrong state           */
-							break;
-						}
-					}
-				}
-/*
-  dbug(1, dprintf("rplci:%x", rplci));
-  dbug(1, dprintf("plci:%x", plci));
-  dbug(1, dprintf("rplci->ptyState:%x", rplci->ptyState));
-  dbug(1, dprintf("plci->ptyState:%x", plci->ptyState));
-  dbug(1, dprintf("SSreq:%x", SSreq));
-  dbug(1, dprintf("rplci->internal_command:%x", rplci->internal_command));
-  dbug(1, dprintf("rplci->appl:%x", rplci->appl));
-  dbug(1, dprintf("rplci->Id:%x", rplci->Id));
-*/
-				/* send PTY/ECT req, cannot check all states because of US stuff */
-				if (!rplci->internal_command && rplci->appl)
-				{
-					plci->command = 0;
-					rplci->relatedPTYPLCI = plci;
-					plci->relatedPTYPLCI = rplci;
-					rplci->ptyState = (byte)SSreq;
-					if (SSreq == S_ECT)
-					{
-						rplci->internal_command = ECT_REQ_PEND;
-						cai[1] = ECT_EXECUTE;
-
-						rplci->vswitchstate = 0;
-						rplci->vsprot = 0;
-						rplci->vsprotdialect = 0;
-						plci->vswitchstate = 0;
-						plci->vsprot = 0;
-						plci->vsprotdialect = 0;
-
-					}
-					else if (SSreq == S_CONF_ADD)
-					{
-						rplci->internal_command = CONF_ADD_REQ_PEND;
-						cai[1] = CONF_ADD;
-					}
-					else
-					{
-						rplci->internal_command = PTY_REQ_PEND;
-						cai[1] = (byte)(SSreq - 3);
-					}
-					rplci->number = Number;
-					if (plci != rplci) /* explicit invocation */
-					{
-						cai[0] = 2;
-						cai[2] = plci->Sig.Id;
-						dbug(1, dprintf("explicit invocation"));
-					}
-					else
-					{
-						dbug(1, dprintf("implicit invocation"));
-						cai[0] = 1;
-					}
-					add_p(rplci, CAI, cai);
-					sig_req(rplci, S_SERVICE, 0);
-					send_req(rplci);
-					return false;
-				}
-				else
-				{
-					dbug(0, dprintf("Wrong line"));
-					Info = 0x3010;                    /* wrong state           */
-					break;
-				}
-				break;
-
-			case S_CALL_DEFLECTION:
-				if (api_parse(&parms->info[1], (word)parms->length, "wbwss", ss_parms))
-				{
-					dbug(1, dprintf("format wrong"));
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				if (!plci)
-				{
-					Info = _WRONG_IDENTIFIER;
-					break;
-				}
-				/* reuse unused screening indicator */
-				ss_parms[3].info[3] = (byte)GET_WORD(&(ss_parms[2].info[0]));
-				plci->command = 0;
-				plci->internal_command = CD_REQ_PEND;
-				appl->CDEnable = true;
-				cai[0] = 1;
-				cai[1] = CALL_DEFLECTION;
-				add_p(plci, CAI, cai);
-				add_p(plci, CPN, ss_parms[3].info);
-				sig_req(plci, S_SERVICE, 0);
-				send_req(plci);
-				return false;
-				break;
-
-			case S_CALL_FORWARDING_START:
-				if (api_parse(&parms->info[1], (word)parms->length, "wbdwwsss", ss_parms))
-				{
-					dbug(1, dprintf("format wrong"));
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-
-				if ((i = get_plci(a)))
-				{
-					rplci = &a->plci[i - 1];
-					rplci->appl = appl;
-					add_p(rplci, CAI, "\x01\x80");
-					add_p(rplci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-					sig_req(rplci, ASSIGN, DSIG_ID);
-					send_req(rplci);
-				}
-				else
-				{
-					Info = _OUT_OF_PLCI;
-					break;
-				}
-
-				/* reuse unused screening indicator */
-				rplci->internal_command = CF_START_PEND;
-				rplci->appl = appl;
-				rplci->number = Number;
-				appl->S_Handle = GET_DWORD(&(ss_parms[2].info[0]));
-				cai[0] = 2;
-				cai[1] = 0x70 | (byte)GET_WORD(&(ss_parms[3].info[0])); /* Function */
-				cai[2] = (byte)GET_WORD(&(ss_parms[4].info[0])); /* Basic Service */
-				add_p(rplci, CAI, cai);
-				add_p(rplci, OAD, ss_parms[5].info);
-				add_p(rplci, CPN, ss_parms[6].info);
-				sig_req(rplci, S_SERVICE, 0);
-				send_req(rplci);
-				return false;
-				break;
-
-			case S_INTERROGATE_DIVERSION:
-			case S_INTERROGATE_NUMBERS:
-			case S_CALL_FORWARDING_STOP:
-			case S_CCBS_REQUEST:
-			case S_CCBS_DEACTIVATE:
-			case S_CCBS_INTERROGATE:
-				switch (SSreq)
-				{
-				case S_INTERROGATE_NUMBERS:
-					if (api_parse(&parms->info[1], (word)parms->length, "wbd", ss_parms))
-					{
-						dbug(0, dprintf("format wrong"));
-						Info = _WRONG_MESSAGE_FORMAT;
-					}
-					break;
-				case S_CCBS_REQUEST:
-				case S_CCBS_DEACTIVATE:
-					if (api_parse(&parms->info[1], (word)parms->length, "wbdw", ss_parms))
-					{
-						dbug(0, dprintf("format wrong"));
-						Info = _WRONG_MESSAGE_FORMAT;
-					}
-					break;
-				case S_CCBS_INTERROGATE:
-					if (api_parse(&parms->info[1], (word)parms->length, "wbdws", ss_parms))
-					{
-						dbug(0, dprintf("format wrong"));
-						Info = _WRONG_MESSAGE_FORMAT;
-					}
-					break;
-				default:
-					if (api_parse(&parms->info[1], (word)parms->length, "wbdwws", ss_parms))
-					{
-						dbug(0, dprintf("format wrong"));
-						Info = _WRONG_MESSAGE_FORMAT;
-						break;
-					}
-					break;
-				}
-
-				if (Info) break;
-				if ((i = get_plci(a)))
-				{
-					rplci = &a->plci[i - 1];
-					switch (SSreq)
-					{
-					case S_INTERROGATE_DIVERSION: /* use cai with S_SERVICE below */
-						cai[1] = 0x60 | (byte)GET_WORD(&(ss_parms[3].info[0])); /* Function */
-						rplci->internal_command = INTERR_DIVERSION_REQ_PEND; /* move to rplci if assigned */
-						break;
-					case S_INTERROGATE_NUMBERS: /* use cai with S_SERVICE below */
-						cai[1] = DIVERSION_INTERROGATE_NUM; /* Function */
-						rplci->internal_command = INTERR_NUMBERS_REQ_PEND; /* move to rplci if assigned */
-						break;
-					case S_CALL_FORWARDING_STOP:
-						rplci->internal_command = CF_STOP_PEND;
-						cai[1] = 0x80 | (byte)GET_WORD(&(ss_parms[3].info[0])); /* Function */
-						break;
-					case S_CCBS_REQUEST:
-						cai[1] = CCBS_REQUEST;
-						rplci->internal_command = CCBS_REQUEST_REQ_PEND;
-						break;
-					case S_CCBS_DEACTIVATE:
-						cai[1] = CCBS_DEACTIVATE;
-						rplci->internal_command = CCBS_DEACTIVATE_REQ_PEND;
-						break;
-					case S_CCBS_INTERROGATE:
-						cai[1] = CCBS_INTERROGATE;
-						rplci->internal_command = CCBS_INTERROGATE_REQ_PEND;
-						break;
-					default:
-						cai[1] = 0;
-						break;
-					}
-					rplci->appl = appl;
-					rplci->number = Number;
-					add_p(rplci, CAI, "\x01\x80");
-					add_p(rplci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-					sig_req(rplci, ASSIGN, DSIG_ID);
-					send_req(rplci);
-				}
-				else
-				{
-					Info = _OUT_OF_PLCI;
-					break;
-				}
-
-				appl->S_Handle = GET_DWORD(&(ss_parms[2].info[0]));
-				switch (SSreq)
-				{
-				case S_INTERROGATE_NUMBERS:
-					cai[0] = 1;
-					add_p(rplci, CAI, cai);
-					break;
-				case S_CCBS_REQUEST:
-				case S_CCBS_DEACTIVATE:
-					cai[0] = 3;
-					PUT_WORD(&cai[2], GET_WORD(&(ss_parms[3].info[0])));
-					add_p(rplci, CAI, cai);
-					break;
-				case S_CCBS_INTERROGATE:
-					cai[0] = 3;
-					PUT_WORD(&cai[2], GET_WORD(&(ss_parms[3].info[0])));
-					add_p(rplci, CAI, cai);
-					add_p(rplci, OAD, ss_parms[4].info);
-					break;
-				default:
-					cai[0] = 2;
-					cai[2] = (byte)GET_WORD(&(ss_parms[4].info[0])); /* Basic Service */
-					add_p(rplci, CAI, cai);
-					add_p(rplci, OAD, ss_parms[5].info);
-					break;
-				}
-
-				sig_req(rplci, S_SERVICE, 0);
-				send_req(rplci);
-				return false;
-				break;
-
-			case S_MWI_ACTIVATE:
-				if (api_parse(&parms->info[1], (word)parms->length, "wbwdwwwssss", ss_parms))
-				{
-					dbug(1, dprintf("format wrong"));
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				if (!plci)
-				{
-					if ((i = get_plci(a)))
-					{
-						rplci = &a->plci[i - 1];
-						rplci->appl = appl;
-						rplci->cr_enquiry = true;
-						add_p(rplci, CAI, "\x01\x80");
-						add_p(rplci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-						sig_req(rplci, ASSIGN, DSIG_ID);
-						send_req(rplci);
-					}
-					else
-					{
-						Info = _OUT_OF_PLCI;
-						break;
-					}
-				}
-				else
-				{
-					rplci = plci;
-					rplci->cr_enquiry = false;
-				}
-
-				rplci->command = 0;
-				rplci->internal_command = MWI_ACTIVATE_REQ_PEND;
-				rplci->appl = appl;
-				rplci->number = Number;
-
-				cai[0] = 13;
-				cai[1] = ACTIVATION_MWI; /* Function */
-				PUT_WORD(&cai[2], GET_WORD(&(ss_parms[2].info[0]))); /* Basic Service */
-				PUT_DWORD(&cai[4], GET_DWORD(&(ss_parms[3].info[0]))); /* Number of Messages */
-				PUT_WORD(&cai[8], GET_WORD(&(ss_parms[4].info[0]))); /* Message Status */
-				PUT_WORD(&cai[10], GET_WORD(&(ss_parms[5].info[0]))); /* Message Reference */
-				PUT_WORD(&cai[12], GET_WORD(&(ss_parms[6].info[0]))); /* Invocation Mode */
-				add_p(rplci, CAI, cai);
-				add_p(rplci, CPN, ss_parms[7].info); /* Receiving User Number */
-				add_p(rplci, OAD, ss_parms[8].info); /* Controlling User Number */
-				add_p(rplci, OSA, ss_parms[9].info); /* Controlling User Provided Number */
-				add_p(rplci, UID, ss_parms[10].info); /* Time */
-				sig_req(rplci, S_SERVICE, 0);
-				send_req(rplci);
-				return false;
-
-			case S_MWI_DEACTIVATE:
-				if (api_parse(&parms->info[1], (word)parms->length, "wbwwss", ss_parms))
-				{
-					dbug(1, dprintf("format wrong"));
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				if (!plci)
-				{
-					if ((i = get_plci(a)))
-					{
-						rplci = &a->plci[i - 1];
-						rplci->appl = appl;
-						rplci->cr_enquiry = true;
-						add_p(rplci, CAI, "\x01\x80");
-						add_p(rplci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-						sig_req(rplci, ASSIGN, DSIG_ID);
-						send_req(rplci);
-					}
-					else
-					{
-						Info = _OUT_OF_PLCI;
-						break;
-					}
-				}
-				else
-				{
-					rplci = plci;
-					rplci->cr_enquiry = false;
-				}
-
-				rplci->command = 0;
-				rplci->internal_command = MWI_DEACTIVATE_REQ_PEND;
-				rplci->appl = appl;
-				rplci->number = Number;
-
-				cai[0] = 5;
-				cai[1] = DEACTIVATION_MWI; /* Function */
-				PUT_WORD(&cai[2], GET_WORD(&(ss_parms[2].info[0]))); /* Basic Service */
-				PUT_WORD(&cai[4], GET_WORD(&(ss_parms[3].info[0]))); /* Invocation Mode */
-				add_p(rplci, CAI, cai);
-				add_p(rplci, CPN, ss_parms[4].info); /* Receiving User Number */
-				add_p(rplci, OAD, ss_parms[5].info); /* Controlling User Number */
-				sig_req(rplci, S_SERVICE, 0);
-				send_req(rplci);
-				return false;
-
-			default:
-				Info = 0x300E;  /* not supported */
-				break;
-			}
-			break; /* case SELECTOR_SU_SERV: end */
-
-
-		case SELECTOR_DTMF:
-			return (dtmf_request(Id, Number, a, plci, appl, msg));
-
-
-
-		case SELECTOR_LINE_INTERCONNECT:
-			return (mixer_request(Id, Number, a, plci, appl, msg));
-
-
-
-		case PRIV_SELECTOR_ECHO_CANCELLER:
-			appl->appl_flags |= APPL_FLAG_PRIV_EC_SPEC;
-			return (ec_request(Id, Number, a, plci, appl, msg));
-
-		case SELECTOR_ECHO_CANCELLER:
-			appl->appl_flags &= ~APPL_FLAG_PRIV_EC_SPEC;
-			return (ec_request(Id, Number, a, plci, appl, msg));
-
-
-		case SELECTOR_V42BIS:
-		default:
-			Info = _FACILITY_NOT_SUPPORTED;
-			break;
-		} /* end of switch (selector) */
-	}
-
-	dbug(1, dprintf("SendFacRc"));
-	sendf(appl,
-	      _FACILITY_R | CONFIRM,
-	      Id,
-	      Number,
-	      "wws", Info, selector, SSparms);
-	return false;
-}
-
-static byte facility_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			 PLCI *plci, APPL *appl, API_PARSE *msg)
-{
-	dbug(1, dprintf("facility_res"));
-	return false;
-}
-
-static byte connect_b3_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			   PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word Info = 0;
-	byte req;
-	byte len;
-	word w;
-	word fax_control_bits, fax_feature_bits, fax_info_change;
-	API_PARSE *ncpi;
-	byte pvc[2];
-
-	API_PARSE fax_parms[9];
-	word i;
-
-
-	dbug(1, dprintf("connect_b3_req"));
-	if (plci)
-	{
-		if ((plci->State == IDLE) || (plci->State == OUTG_DIS_PENDING)
-		    || (plci->State == INC_DIS_PENDING) || (plci->SuppState != IDLE))
-		{
-			Info = _WRONG_STATE;
-		}
-		else
-		{
-			/* local reply if assign unsuccessful
-			   or B3 protocol allows only one layer 3 connection
-			   and already connected
-			   or B2 protocol not any LAPD
-			   and connect_b3_req contradicts originate/answer direction */
-			if (!plci->NL.Id
-			    || (((plci->B3_prot != B3_T90NL) && (plci->B3_prot != B3_ISO8208) && (plci->B3_prot != B3_X25_DCE))
-				&& ((plci->channels != 0)
-				    || (((plci->B2_prot != B2_SDLC) && (plci->B2_prot != B2_LAPD) && (plci->B2_prot != B2_LAPD_FREE_SAPI_SEL))
-					&& ((plci->call_dir & CALL_DIR_ANSWER) && !(plci->call_dir & CALL_DIR_FORCE_OUTG_NL))))))
-			{
-				dbug(1, dprintf("B3 already connected=%d or no NL.Id=0x%x, dir=%d sstate=0x%x",
-						plci->channels, plci->NL.Id, plci->call_dir, plci->SuppState));
-				Info = _WRONG_STATE;
-				sendf(appl,
-				      _CONNECT_B3_R | CONFIRM,
-				      Id,
-				      Number,
-				      "w", Info);
-				return false;
-			}
-			plci->requested_options_conn = 0;
-
-			req = N_CONNECT;
-			ncpi = &parms[0];
-			if (plci->B3_prot == 2 || plci->B3_prot == 3)
-			{
-				if (ncpi->length > 2)
-				{
-					/* check for PVC */
-					if (ncpi->info[2] || ncpi->info[3])
-					{
-						pvc[0] = ncpi->info[3];
-						pvc[1] = ncpi->info[2];
-						add_d(plci, 2, pvc);
-						req = N_RESET;
-					}
-					else
-					{
-						if (ncpi->info[1] & 1) req = N_CONNECT | N_D_BIT;
-						add_d(plci, (word)(ncpi->length - 3), &ncpi->info[4]);
-					}
-				}
-			}
-			else if (plci->B3_prot == 5)
-			{
-				if (plci->NL.Id && !plci->nl_remove_id)
-				{
-					fax_control_bits = GET_WORD(&((T30_INFO *)plci->fax_connect_info_buffer)->control_bits_low);
-					fax_feature_bits = GET_WORD(&((T30_INFO *)plci->fax_connect_info_buffer)->feature_bits_low);
-					if (!(fax_control_bits & T30_CONTROL_BIT_MORE_DOCUMENTS)
-					    || (fax_feature_bits & T30_FEATURE_BIT_MORE_DOCUMENTS))
-					{
-						len = offsetof(T30_INFO, universal_6);
-						fax_info_change = false;
-						if (ncpi->length >= 4)
-						{
-							w = GET_WORD(&ncpi->info[3]);
-							if ((w & 0x0001) != ((word)(((T30_INFO *)(plci->fax_connect_info_buffer))->resolution & 0x0001)))
-							{
-								((T30_INFO *)(plci->fax_connect_info_buffer))->resolution =
-									(byte)((((T30_INFO *)(plci->fax_connect_info_buffer))->resolution & ~T30_RESOLUTION_R8_0770_OR_200) |
-									       ((w & 0x0001) ? T30_RESOLUTION_R8_0770_OR_200 : 0));
-								fax_info_change = true;
-							}
-							fax_control_bits &= ~(T30_CONTROL_BIT_REQUEST_POLLING | T30_CONTROL_BIT_MORE_DOCUMENTS);
-							if (w & 0x0002)  /* Fax-polling request */
-								fax_control_bits |= T30_CONTROL_BIT_REQUEST_POLLING;
-							if ((w & 0x0004) /* Request to send / poll another document */
-							    && (a->manufacturer_features & MANUFACTURER_FEATURE_FAX_MORE_DOCUMENTS))
-							{
-								fax_control_bits |= T30_CONTROL_BIT_MORE_DOCUMENTS;
-							}
-							if (ncpi->length >= 6)
-							{
-								w = GET_WORD(&ncpi->info[5]);
-								if (((byte) w) != ((T30_INFO *)(plci->fax_connect_info_buffer))->data_format)
-								{
-									((T30_INFO *)(plci->fax_connect_info_buffer))->data_format = (byte) w;
-									fax_info_change = true;
-								}
-
-								if ((a->man_profile.private_options & (1L << PRIVATE_FAX_SUB_SEP_PWD))
-								    && (GET_WORD(&ncpi->info[5]) & 0x8000)) /* Private SEP/SUB/PWD enable */
-								{
-									plci->requested_options_conn |= (1L << PRIVATE_FAX_SUB_SEP_PWD);
-								}
-								if ((a->man_profile.private_options & (1L << PRIVATE_FAX_NONSTANDARD))
-								    && (GET_WORD(&ncpi->info[5]) & 0x4000)) /* Private non-standard facilities enable */
-								{
-									plci->requested_options_conn |= (1L << PRIVATE_FAX_NONSTANDARD);
-								}
-								fax_control_bits &= ~(T30_CONTROL_BIT_ACCEPT_SUBADDRESS | T30_CONTROL_BIT_ACCEPT_SEL_POLLING |
-										      T30_CONTROL_BIT_ACCEPT_PASSWORD);
-								if ((plci->requested_options_conn | plci->requested_options | a->requested_options_table[appl->Id - 1])
-								    & ((1L << PRIVATE_FAX_SUB_SEP_PWD) | (1L << PRIVATE_FAX_NONSTANDARD)))
-								{
-									if (api_parse(&ncpi->info[1], ncpi->length, "wwwwsss", fax_parms))
-										Info = _WRONG_MESSAGE_FORMAT;
-									else
-									{
-										if ((plci->requested_options_conn | plci->requested_options | a->requested_options_table[appl->Id - 1])
-										    & (1L << PRIVATE_FAX_SUB_SEP_PWD))
-										{
-											fax_control_bits |= T30_CONTROL_BIT_ACCEPT_SUBADDRESS | T30_CONTROL_BIT_ACCEPT_PASSWORD;
-											if (fax_control_bits & T30_CONTROL_BIT_ACCEPT_POLLING)
-												fax_control_bits |= T30_CONTROL_BIT_ACCEPT_SEL_POLLING;
-										}
-										w = fax_parms[4].length;
-										if (w > 20)
-											w = 20;
-										((T30_INFO *)(plci->fax_connect_info_buffer))->station_id_len = (byte) w;
-										for (i = 0; i < w; i++)
-											((T30_INFO *)(plci->fax_connect_info_buffer))->station_id[i] = fax_parms[4].info[1 + i];
-										((T30_INFO *)(plci->fax_connect_info_buffer))->head_line_len = 0;
-										len = offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH;
-										w = fax_parms[5].length;
-										if (w > 20)
-											w = 20;
-										plci->fax_connect_info_buffer[len++] = (byte) w;
-										for (i = 0; i < w; i++)
-											plci->fax_connect_info_buffer[len++] = fax_parms[5].info[1 + i];
-										w = fax_parms[6].length;
-										if (w > 20)
-											w = 20;
-										plci->fax_connect_info_buffer[len++] = (byte) w;
-										for (i = 0; i < w; i++)
-											plci->fax_connect_info_buffer[len++] = fax_parms[6].info[1 + i];
-										if ((plci->requested_options_conn | plci->requested_options | a->requested_options_table[appl->Id - 1])
-										    & (1L << PRIVATE_FAX_NONSTANDARD))
-										{
-											if (api_parse(&ncpi->info[1], ncpi->length, "wwwwssss", fax_parms))
-											{
-												dbug(1, dprintf("non-standard facilities info missing or wrong format"));
-												plci->fax_connect_info_buffer[len++] = 0;
-											}
-											else
-											{
-												if ((fax_parms[7].length >= 3) && (fax_parms[7].info[1] >= 2))
-													plci->nsf_control_bits = GET_WORD(&fax_parms[7].info[2]);
-												plci->fax_connect_info_buffer[len++] = (byte)(fax_parms[7].length);
-												for (i = 0; i < fax_parms[7].length; i++)
-													plci->fax_connect_info_buffer[len++] = fax_parms[7].info[1 + i];
-											}
-										}
-									}
-								}
-								else
-								{
-									len = offsetof(T30_INFO, universal_6);
-								}
-								fax_info_change = true;
-
-							}
-							if (fax_control_bits != GET_WORD(&((T30_INFO *)plci->fax_connect_info_buffer)->control_bits_low))
-							{
-								PUT_WORD(&((T30_INFO *)plci->fax_connect_info_buffer)->control_bits_low, fax_control_bits);
-								fax_info_change = true;
-							}
-						}
-						if (Info == GOOD)
-						{
-							plci->fax_connect_info_length = len;
-							if (fax_info_change)
-							{
-								if (fax_feature_bits & T30_FEATURE_BIT_MORE_DOCUMENTS)
-								{
-									start_internal_command(Id, plci, fax_connect_info_command);
-									return false;
-								}
-								else
-								{
-									start_internal_command(Id, plci, fax_adjust_b23_command);
-									return false;
-								}
-							}
-						}
-					}
-					else  Info = _WRONG_STATE;
-				}
-				else  Info = _WRONG_STATE;
-			}
-
-			else if (plci->B3_prot == B3_RTP)
-			{
-				plci->internal_req_buffer[0] = ncpi->length + 1;
-				plci->internal_req_buffer[1] = UDATA_REQUEST_RTP_RECONFIGURE;
-				for (w = 0; w < ncpi->length; w++)
-					plci->internal_req_buffer[2 + w] = ncpi->info[1 + w];
-				start_internal_command(Id, plci, rtp_connect_b3_req_command);
-				return false;
-			}
-
-			if (!Info)
-			{
-				nl_req_ncci(plci, req, 0);
-				return 1;
-			}
-		}
-	}
-	else Info = _WRONG_IDENTIFIER;
-
-	sendf(appl,
-	      _CONNECT_B3_R | CONFIRM,
-	      Id,
-	      Number,
-	      "w", Info);
-	return false;
-}
-
-static byte connect_b3_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			   PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word ncci;
-	API_PARSE *ncpi;
-	byte req;
-
-	word w;
-
-
-	API_PARSE fax_parms[9];
-	word i;
-	byte len;
-
-
-	dbug(1, dprintf("connect_b3_res"));
-
-	ncci = (word)(Id >> 16);
-	if (plci && ncci) {
-		if (a->ncci_state[ncci] == INC_CON_PENDING) {
-			if (GET_WORD(&parms[0].info[0]) != 0)
-			{
-				a->ncci_state[ncci] = OUTG_REJ_PENDING;
-				channel_request_xon(plci, a->ncci_ch[ncci]);
-				channel_xmit_xon(plci);
-				cleanup_ncci_data(plci, ncci);
-				nl_req_ncci(plci, N_DISC, (byte)ncci);
-				return 1;
-			}
-			a->ncci_state[ncci] = INC_ACT_PENDING;
-
-			req = N_CONNECT_ACK;
-			ncpi = &parms[1];
-			if ((plci->B3_prot == 4) || (plci->B3_prot == 5) || (plci->B3_prot == 7))
-			{
-
-				if ((plci->requested_options_conn | plci->requested_options | a->requested_options_table[plci->appl->Id - 1])
-				    & (1L << PRIVATE_FAX_NONSTANDARD))
-				{
-					if (((plci->B3_prot == 4) || (plci->B3_prot == 5))
-					    && (plci->nsf_control_bits & T30_NSF_CONTROL_BIT_ENABLE_NSF)
-					    && (plci->nsf_control_bits & T30_NSF_CONTROL_BIT_NEGOTIATE_RESP))
-					{
-						len = offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH;
-						if (plci->fax_connect_info_length < len)
-						{
-							((T30_INFO *)(plci->fax_connect_info_buffer))->station_id_len = 0;
-							((T30_INFO *)(plci->fax_connect_info_buffer))->head_line_len = 0;
-						}
-						if (api_parse(&ncpi->info[1], ncpi->length, "wwwwssss", fax_parms))
-						{
-							dbug(1, dprintf("non-standard facilities info missing or wrong format"));
-						}
-						else
-						{
-							if (plci->fax_connect_info_length <= len)
-								plci->fax_connect_info_buffer[len] = 0;
-							len += 1 + plci->fax_connect_info_buffer[len];
-							if (plci->fax_connect_info_length <= len)
-								plci->fax_connect_info_buffer[len] = 0;
-							len += 1 + plci->fax_connect_info_buffer[len];
-							if ((fax_parms[7].length >= 3) && (fax_parms[7].info[1] >= 2))
-								plci->nsf_control_bits = GET_WORD(&fax_parms[7].info[2]);
-							plci->fax_connect_info_buffer[len++] = (byte)(fax_parms[7].length);
-							for (i = 0; i < fax_parms[7].length; i++)
-								plci->fax_connect_info_buffer[len++] = fax_parms[7].info[1 + i];
-						}
-						plci->fax_connect_info_length = len;
-						((T30_INFO *)(plci->fax_connect_info_buffer))->code = 0;
-						start_internal_command(Id, plci, fax_connect_ack_command);
-						return false;
-					}
-				}
-
-				nl_req_ncci(plci, req, (byte)ncci);
-				if ((plci->ncpi_state & NCPI_VALID_CONNECT_B3_ACT)
-				    && !(plci->ncpi_state & NCPI_CONNECT_B3_ACT_SENT))
-				{
-					if (plci->B3_prot == 4)
-						sendf(appl, _CONNECT_B3_ACTIVE_I, Id, 0, "s", "");
-					else
-						sendf(appl, _CONNECT_B3_ACTIVE_I, Id, 0, "S", plci->ncpi_buffer);
-					plci->ncpi_state |= NCPI_CONNECT_B3_ACT_SENT;
-				}
-			}
-
-			else if (plci->B3_prot == B3_RTP)
-			{
-				plci->internal_req_buffer[0] = ncpi->length + 1;
-				plci->internal_req_buffer[1] = UDATA_REQUEST_RTP_RECONFIGURE;
-				for (w = 0; w < ncpi->length; w++)
-					plci->internal_req_buffer[2 + w] = ncpi->info[1+w];
-				start_internal_command(Id, plci, rtp_connect_b3_res_command);
-				return false;
-			}
-
-			else
-			{
-				if (ncpi->length > 2) {
-					if (ncpi->info[1] & 1) req = N_CONNECT_ACK | N_D_BIT;
-					add_d(plci, (word)(ncpi->length - 3), &ncpi->info[4]);
-				}
-				nl_req_ncci(plci, req, (byte)ncci);
-				sendf(appl, _CONNECT_B3_ACTIVE_I, Id, 0, "s", "");
-				if (plci->adjust_b_restore)
-				{
-					plci->adjust_b_restore = false;
-					start_internal_command(Id, plci, adjust_b_restore);
-				}
-			}
-			return 1;
-		}
-	}
-	return false;
-}
-
-static byte connect_b3_a_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			     PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word ncci;
-
-	ncci = (word)(Id >> 16);
-	dbug(1, dprintf("connect_b3_a_res(ncci=0x%x)", ncci));
-
-	if (plci && ncci && (plci->State != IDLE) && (plci->State != INC_DIS_PENDING)
-	    && (plci->State != OUTG_DIS_PENDING))
-	{
-		if (a->ncci_state[ncci] == INC_ACT_PENDING) {
-			a->ncci_state[ncci] = CONNECTED;
-			if (plci->State != INC_CON_CONNECTED_ALERT) plci->State = CONNECTED;
-			channel_request_xon(plci, a->ncci_ch[ncci]);
-			channel_xmit_xon(plci);
-		}
-	}
-	return false;
-}
-
-static byte disconnect_b3_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			      PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word Info;
-	word ncci;
-	API_PARSE *ncpi;
-
-	dbug(1, dprintf("disconnect_b3_req"));
-
-	Info = _WRONG_IDENTIFIER;
-	ncci = (word)(Id >> 16);
-	if (plci && ncci)
-	{
-		Info = _WRONG_STATE;
-		if ((a->ncci_state[ncci] == CONNECTED)
-		    || (a->ncci_state[ncci] == OUTG_CON_PENDING)
-		    || (a->ncci_state[ncci] == INC_CON_PENDING)
-		    || (a->ncci_state[ncci] == INC_ACT_PENDING))
-		{
-			a->ncci_state[ncci] = OUTG_DIS_PENDING;
-			channel_request_xon(plci, a->ncci_ch[ncci]);
-			channel_xmit_xon(plci);
-
-			if (a->ncci[ncci].data_pending
-			    && ((plci->B3_prot == B3_TRANSPARENT)
-				|| (plci->B3_prot == B3_T30)
-				|| (plci->B3_prot == B3_T30_WITH_EXTENSIONS)))
-			{
-				plci->send_disc = (byte)ncci;
-				plci->command = 0;
-				return false;
-			}
-			else
-			{
-				cleanup_ncci_data(plci, ncci);
-
-				if (plci->B3_prot == 2 || plci->B3_prot == 3)
-				{
-					ncpi = &parms[0];
-					if (ncpi->length > 3)
-					{
-						add_d(plci, (word)(ncpi->length - 3), (byte *)&(ncpi->info[4]));
-					}
-				}
-				nl_req_ncci(plci, N_DISC, (byte)ncci);
-			}
-			return 1;
-		}
-	}
-	sendf(appl,
-	      _DISCONNECT_B3_R | CONFIRM,
-	      Id,
-	      Number,
-	      "w", Info);
-	return false;
-}
-
-static byte disconnect_b3_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			      PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word ncci;
-	word i;
-
-	ncci = (word)(Id >> 16);
-	dbug(1, dprintf("disconnect_b3_res(ncci=0x%x", ncci));
-	if (plci && ncci) {
-		plci->requested_options_conn = 0;
-		plci->fax_connect_info_length = 0;
-		plci->ncpi_state = 0x00;
-		if (((plci->B3_prot != B3_T90NL) && (plci->B3_prot != B3_ISO8208) && (plci->B3_prot != B3_X25_DCE))
-		    && ((plci->B2_prot != B2_LAPD) && (plci->B2_prot != B2_LAPD_FREE_SAPI_SEL)))
-		{
-			plci->call_dir |= CALL_DIR_FORCE_OUTG_NL;
-		}
-		for (i = 0; i < MAX_CHANNELS_PER_PLCI && plci->inc_dis_ncci_table[i] != (byte)ncci; i++);
-		if (i < MAX_CHANNELS_PER_PLCI) {
-			if (plci->channels)plci->channels--;
-			for (; i < MAX_CHANNELS_PER_PLCI - 1; i++) plci->inc_dis_ncci_table[i] = plci->inc_dis_ncci_table[i + 1];
-			plci->inc_dis_ncci_table[MAX_CHANNELS_PER_PLCI - 1] = 0;
-
-			ncci_free_receive_buffers(plci, ncci);
-
-			if ((plci->State == IDLE || plci->State == SUSPENDING) && !plci->channels) {
-				if (plci->State == SUSPENDING) {
-					sendf(plci->appl,
-					      _FACILITY_I,
-					      Id & 0xffffL,
-					      0,
-					      "ws", (word)3, "\x03\x04\x00\x00");
-					sendf(plci->appl, _DISCONNECT_I, Id & 0xffffL, 0, "w", 0);
-				}
-				plci_remove(plci);
-				plci->State = IDLE;
-			}
-		}
-		else
-		{
-			if ((a->manufacturer_features & MANUFACTURER_FEATURE_FAX_PAPER_FORMATS)
-			    && ((plci->B3_prot == 4) || (plci->B3_prot == 5))
-			    && (a->ncci_state[ncci] == INC_DIS_PENDING))
-			{
-				ncci_free_receive_buffers(plci, ncci);
-
-				nl_req_ncci(plci, N_EDATA, (byte)ncci);
-
-				plci->adapter->ncci_state[ncci] = IDLE;
-				start_internal_command(Id, plci, fax_disconnect_command);
-				return 1;
-			}
-		}
-	}
-	return false;
-}
-
-static byte data_b3_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	NCCI *ncci_ptr;
-	DATA_B3_DESC *data;
-	word Info;
-	word ncci;
-	word i;
-
-	dbug(1, dprintf("data_b3_req"));
-
-	Info = _WRONG_IDENTIFIER;
-	ncci = (word)(Id >> 16);
-	dbug(1, dprintf("ncci=0x%x, plci=0x%x", ncci, plci));
-
-	if (plci && ncci)
-	{
-		Info = _WRONG_STATE;
-		if ((a->ncci_state[ncci] == CONNECTED)
-		    || (a->ncci_state[ncci] == INC_ACT_PENDING))
-		{
-			/* queue data */
-			ncci_ptr = &(a->ncci[ncci]);
-			i = ncci_ptr->data_out + ncci_ptr->data_pending;
-			if (i >= MAX_DATA_B3)
-				i -= MAX_DATA_B3;
-			data = &(ncci_ptr->DBuffer[i]);
-			data->Number = Number;
-			if ((((byte *)(parms[0].info)) >= ((byte *)(plci->msg_in_queue)))
-			    && (((byte *)(parms[0].info)) < ((byte *)(plci->msg_in_queue)) + sizeof(plci->msg_in_queue)))
-			{
-
-				data->P = (byte *)(long)(*((dword *)(parms[0].info)));
-
-			}
-			else
-				data->P = TransmitBufferSet(appl, *(dword *)parms[0].info);
-			data->Length = GET_WORD(parms[1].info);
-			data->Handle = GET_WORD(parms[2].info);
-			data->Flags = GET_WORD(parms[3].info);
-			(ncci_ptr->data_pending)++;
-
-			/* check for delivery confirmation */
-			if (data->Flags & 0x0004)
-			{
-				i = ncci_ptr->data_ack_out + ncci_ptr->data_ack_pending;
-				if (i >= MAX_DATA_ACK)
-					i -= MAX_DATA_ACK;
-				ncci_ptr->DataAck[i].Number = data->Number;
-				ncci_ptr->DataAck[i].Handle = data->Handle;
-				(ncci_ptr->data_ack_pending)++;
-			}
-
-			send_data(plci);
-			return false;
-		}
-	}
-	if (appl)
-	{
-		if (plci)
-		{
-			if ((((byte *)(parms[0].info)) >= ((byte *)(plci->msg_in_queue)))
-			    && (((byte *)(parms[0].info)) < ((byte *)(plci->msg_in_queue)) + sizeof(plci->msg_in_queue)))
-			{
-
-				TransmitBufferFree(appl, (byte *)(long)(*((dword *)(parms[0].info))));
-
-			}
-		}
-		sendf(appl,
-		      _DATA_B3_R | CONFIRM,
-		      Id,
-		      Number,
-		      "ww", GET_WORD(parms[2].info), Info);
-	}
-	return false;
-}
-
-static byte data_b3_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word n;
-	word ncci;
-	word NCCIcode;
-
-	dbug(1, dprintf("data_b3_res"));
-
-	ncci = (word)(Id >> 16);
-	if (plci && ncci) {
-		n = GET_WORD(parms[0].info);
-		dbug(1, dprintf("free(%d)", n));
-		NCCIcode = ncci | (((word) a->Id) << 8);
-		if (n < appl->MaxBuffer &&
-		    appl->DataNCCI[n] == NCCIcode &&
-		    (byte)(appl->DataFlags[n] >> 8) == plci->Id) {
-			dbug(1, dprintf("found"));
-			appl->DataNCCI[n] = 0;
-
-			if (channel_can_xon(plci, a->ncci_ch[ncci])) {
-				channel_request_xon(plci, a->ncci_ch[ncci]);
-			}
-			channel_xmit_xon(plci);
-
-			if (appl->DataFlags[n] & 4) {
-				nl_req_ncci(plci, N_DATA_ACK, (byte)ncci);
-				return 1;
-			}
-		}
-	}
-	return false;
-}
-
-static byte reset_b3_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			 PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word Info;
-	word ncci;
-
-	dbug(1, dprintf("reset_b3_req"));
-
-	Info = _WRONG_IDENTIFIER;
-	ncci = (word)(Id >> 16);
-	if (plci && ncci)
-	{
-		Info = _WRONG_STATE;
-		switch (plci->B3_prot)
-		{
-		case B3_ISO8208:
-		case B3_X25_DCE:
-			if (a->ncci_state[ncci] == CONNECTED)
-			{
-				nl_req_ncci(plci, N_RESET, (byte)ncci);
-				send_req(plci);
-				Info = GOOD;
-			}
-			break;
-		case B3_TRANSPARENT:
-			if (a->ncci_state[ncci] == CONNECTED)
-			{
-				start_internal_command(Id, plci, reset_b3_command);
-				Info = GOOD;
-			}
-			break;
-		}
-	}
-	/* reset_b3 must result in a reset_b3_con & reset_b3_Ind */
-	sendf(appl,
-	      _RESET_B3_R | CONFIRM,
-	      Id,
-	      Number,
-	      "w", Info);
-	return false;
-}
-
-static byte reset_b3_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			 PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word ncci;
-
-	dbug(1, dprintf("reset_b3_res"));
-
-	ncci = (word)(Id >> 16);
-	if (plci && ncci) {
-		switch (plci->B3_prot)
-		{
-		case B3_ISO8208:
-		case B3_X25_DCE:
-			if (a->ncci_state[ncci] == INC_RES_PENDING)
-			{
-				a->ncci_state[ncci] = CONNECTED;
-				nl_req_ncci(plci, N_RESET_ACK, (byte)ncci);
-				return true;
-			}
-			break;
-		}
-	}
-	return false;
-}
-
-static byte connect_b3_t90_a_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-				 PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word ncci;
-	API_PARSE *ncpi;
-	byte req;
-
-	dbug(1, dprintf("connect_b3_t90_a_res"));
-
-	ncci = (word)(Id >> 16);
-	if (plci && ncci) {
-		if (a->ncci_state[ncci] == INC_ACT_PENDING) {
-			a->ncci_state[ncci] = CONNECTED;
-		}
-		else if (a->ncci_state[ncci] == INC_CON_PENDING) {
-			a->ncci_state[ncci] = CONNECTED;
-
-			req = N_CONNECT_ACK;
-
-			/* parms[0]==0 for CAPI original message definition! */
-			if (parms[0].info) {
-				ncpi = &parms[1];
-				if (ncpi->length > 2) {
-					if (ncpi->info[1] & 1) req = N_CONNECT_ACK | N_D_BIT;
-					add_d(plci, (word)(ncpi->length - 3), &ncpi->info[4]);
-				}
-			}
-			nl_req_ncci(plci, req, (byte)ncci);
-			return 1;
-		}
-	}
-	return false;
-}
-
-
-static byte select_b_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			 PLCI *plci, APPL *appl, API_PARSE *msg)
-{
-	word Info = 0;
-	word i;
-	byte tel;
-	API_PARSE bp_parms[7];
-
-	if (!plci || !msg)
-	{
-		Info = _WRONG_IDENTIFIER;
-	}
-	else
-	{
-		dbug(1, dprintf("select_b_req[%d],PLCI=0x%x,Tel=0x%x,NL=0x%x,appl=0x%x,sstate=0x%x",
-				msg->length, plci->Id, plci->tel, plci->NL.Id, plci->appl, plci->SuppState));
-		dbug(1, dprintf("PlciState=0x%x", plci->State));
-		for (i = 0; i < 7; i++) bp_parms[i].length = 0;
-
-		/* check if no channel is open, no B3 connected only */
-		if ((plci->State == IDLE) || (plci->State == OUTG_DIS_PENDING) || (plci->State == INC_DIS_PENDING)
-		    || (plci->SuppState != IDLE) || plci->channels || plci->nl_remove_id)
-		{
-			Info = _WRONG_STATE;
-		}
-		/* check message format and fill bp_parms pointer */
-		else if (msg->length && api_parse(&msg->info[1], (word)msg->length, "wwwsss", bp_parms))
-		{
-			Info = _WRONG_MESSAGE_FORMAT;
-		}
-		else
-		{
-			if ((plci->State == INC_CON_PENDING) || (plci->State == INC_CON_ALERT)) /* send alert tone inband to the network, */
-			{                                                                  /* e.g. Qsig or RBS or Cornet-N or xess PRI */
-				if (Id & EXT_CONTROLLER)
-				{
-					sendf(appl, _SELECT_B_REQ | CONFIRM, Id, Number, "w", 0x2002); /* wrong controller */
-					return 0;
-				}
-				plci->State = INC_CON_CONNECTED_ALERT;
-				plci->appl = appl;
-				__clear_bit(appl->Id - 1, plci->c_ind_mask_table);
-				dbug(1, dprintf("c_ind_mask =%*pb", MAX_APPL, plci->c_ind_mask_table));
-				/* disconnect the other appls its quasi a connect */
-				for_each_set_bit(i, plci->c_ind_mask_table, max_appl)
-					sendf(&application[i], _DISCONNECT_I, Id, 0, "w", _OTHER_APPL_CONNECTED);
-			}
-
-			api_save_msg(msg, "s", &plci->saved_msg);
-			tel = plci->tel;
-			if (Id & EXT_CONTROLLER)
-			{
-				if (tel) /* external controller in use by this PLCI */
-				{
-					if (a->AdvSignalAppl && a->AdvSignalAppl != appl)
-					{
-						dbug(1, dprintf("Ext_Ctrl in use 1"));
-						Info = _WRONG_STATE;
-					}
-				}
-				else  /* external controller NOT in use by this PLCI ? */
-				{
-					if (a->AdvSignalPLCI)
-					{
-						dbug(1, dprintf("Ext_Ctrl in use 2"));
-						Info = _WRONG_STATE;
-					}
-					else /* activate the codec */
-					{
-						dbug(1, dprintf("Ext_Ctrl start"));
-						if (AdvCodecSupport(a, plci, appl, 0))
-						{
-							dbug(1, dprintf("Error in codec procedures"));
-							Info = _WRONG_STATE;
-						}
-						else if (plci->spoofed_msg == SPOOFING_REQUIRED) /* wait until codec is active */
-						{
-							plci->spoofed_msg = AWAITING_SELECT_B;
-							plci->internal_command = BLOCK_PLCI; /* lock other commands */
-							plci->command = 0;
-							dbug(1, dprintf("continue if codec loaded"));
-							return false;
-						}
-					}
-				}
-			}
-			else /* external controller bit is OFF */
-			{
-				if (tel) /* external controller in use, need to switch off */
-				{
-					if (a->AdvSignalAppl == appl)
-					{
-						CodecIdCheck(a, plci);
-						plci->tel = 0;
-						plci->adv_nl = 0;
-						dbug(1, dprintf("Ext_Ctrl disable"));
-					}
-					else
-					{
-						dbug(1, dprintf("Ext_Ctrl not requested"));
-					}
-				}
-			}
-			if (!Info)
-			{
-				if (plci->call_dir & CALL_DIR_OUT)
-					plci->call_dir = CALL_DIR_OUT | CALL_DIR_ORIGINATE;
-				else if (plci->call_dir & CALL_DIR_IN)
-					plci->call_dir = CALL_DIR_IN | CALL_DIR_ANSWER;
-				start_internal_command(Id, plci, select_b_command);
-				return false;
-			}
-		}
-	}
-	sendf(appl, _SELECT_B_REQ | CONFIRM, Id, Number, "w", Info);
-	return false;
-}
-
-static byte manufacturer_req(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			     PLCI *plci, APPL *appl, API_PARSE *parms)
-{
-	word command;
-	word i;
-	word ncci;
-	API_PARSE *m;
-	API_PARSE m_parms[5];
-	word codec;
-	byte req;
-	byte ch;
-	byte dir;
-	static byte chi[2] = {0x01, 0x00};
-	static byte lli[2] = {0x01, 0x00};
-	static byte codec_cai[2] = {0x01, 0x01};
-	static byte null_msg = {0};
-	static API_PARSE null_parms = { 0, &null_msg };
-	PLCI *v_plci;
-	word Info = 0;
-
-	dbug(1, dprintf("manufacturer_req"));
-	for (i = 0; i < 5; i++) m_parms[i].length = 0;
-
-	if (GET_DWORD(parms[0].info) != _DI_MANU_ID) {
-		Info = _WRONG_MESSAGE_FORMAT;
-	}
-	command = GET_WORD(parms[1].info);
-	m = &parms[2];
-	if (!Info)
-	{
-		switch (command) {
-		case _DI_ASSIGN_PLCI:
-			if (api_parse(&m->info[1], (word)m->length, "wbbs", m_parms)) {
-				Info = _WRONG_MESSAGE_FORMAT;
-				break;
-			}
-			codec = GET_WORD(m_parms[0].info);
-			ch = m_parms[1].info[0];
-			dir = m_parms[2].info[0];
-			if ((i = get_plci(a))) {
-				plci = &a->plci[i - 1];
-				plci->appl = appl;
-				plci->command = _MANUFACTURER_R;
-				plci->m_command = command;
-				plci->number = Number;
-				plci->State = LOCAL_CONNECT;
-				Id = (((word)plci->Id << 8) | plci->adapter->Id | 0x80);
-				dbug(1, dprintf("ManCMD,plci=0x%x", Id));
-
-				if ((ch == 1 || ch == 2) && (dir <= 2)) {
-					chi[1] = (byte)(0x80 | ch);
-					lli[1] = 0;
-					plci->call_dir = CALL_DIR_OUT | CALL_DIR_ORIGINATE;
-					switch (codec)
-					{
-					case 0:
-						Info = add_b1(plci, &m_parms[3], 0, 0);
-						break;
-					case 1:
-						add_p(plci, CAI, codec_cai);
-						break;
-						/* manual 'swich on' to the codec support without signalling */
-						/* first 'assign plci' with this function, then use */
-					case 2:
-						if (AdvCodecSupport(a, plci, appl, 0)) {
-							Info = _RESOURCE_ERROR;
-						}
-						else {
-							Info = add_b1(plci, &null_parms, 0, B1_FACILITY_LOCAL);
-							lli[1] = 0x10; /* local call codec stream */
-						}
-						break;
-					}
-
-					plci->State = LOCAL_CONNECT;
-					plci->manufacturer = true;
-					plci->command = _MANUFACTURER_R;
-					plci->m_command = command;
-					plci->number = Number;
-
-					if (!Info)
-					{
-						add_p(plci, LLI, lli);
-						add_p(plci, CHI, chi);
-						add_p(plci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-						sig_req(plci, ASSIGN, DSIG_ID);
-
-						if (!codec)
-						{
-							Info = add_b23(plci, &m_parms[3]);
-							if (!Info)
-							{
-								nl_req_ncci(plci, ASSIGN, 0);
-								send_req(plci);
-							}
-						}
-						if (!Info)
-						{
-							dbug(1, dprintf("dir=0x%x,spoof=0x%x", dir, plci->spoofed_msg));
-							if (plci->spoofed_msg == SPOOFING_REQUIRED)
-							{
-								api_save_msg(m_parms, "wbbs", &plci->saved_msg);
-								plci->spoofed_msg = AWAITING_MANUF_CON;
-								plci->internal_command = BLOCK_PLCI; /* reject other req meanwhile */
-								plci->command = 0;
-								send_req(plci);
-								return false;
-							}
-							if (dir == 1) {
-								sig_req(plci, CALL_REQ, 0);
-							}
-							else if (!dir) {
-								sig_req(plci, LISTEN_REQ, 0);
-							}
-							send_req(plci);
-						}
-						else
-						{
-							sendf(appl,
-							      _MANUFACTURER_R | CONFIRM,
-							      Id,
-							      Number,
-							      "dww", _DI_MANU_ID, command, Info);
-							return 2;
-						}
-					}
-				}
-			}
-			else  Info = _OUT_OF_PLCI;
-			break;
-
-		case _DI_IDI_CTRL:
-			if (!plci)
-			{
-				Info = _WRONG_IDENTIFIER;
-				break;
-			}
-			if (api_parse(&m->info[1], (word)m->length, "bs", m_parms)) {
-				Info = _WRONG_MESSAGE_FORMAT;
-				break;
-			}
-			req = m_parms[0].info[0];
-			plci->command = _MANUFACTURER_R;
-			plci->m_command = command;
-			plci->number = Number;
-			if (req == CALL_REQ)
-			{
-				plci->b_channel = getChannel(&m_parms[1]);
-				mixer_set_bchannel_id_esc(plci, plci->b_channel);
-				if (plci->spoofed_msg == SPOOFING_REQUIRED)
-				{
-					plci->spoofed_msg = CALL_REQ | AWAITING_MANUF_CON;
-					plci->internal_command = BLOCK_PLCI; /* reject other req meanwhile */
-					plci->command = 0;
-					break;
-				}
-			}
-			else if (req == LAW_REQ)
-			{
-				plci->cr_enquiry = true;
-			}
-			add_ss(plci, FTY, &m_parms[1]);
-			sig_req(plci, req, 0);
-			send_req(plci);
-			if (req == HANGUP)
-			{
-				if (plci->NL.Id && !plci->nl_remove_id)
-				{
-					if (plci->channels)
-					{
-						for (ncci = 1; ncci < MAX_NCCI + 1; ncci++)
-						{
-							if ((a->ncci_plci[ncci] == plci->Id) && (a->ncci_state[ncci] == CONNECTED))
-							{
-								a->ncci_state[ncci] = OUTG_DIS_PENDING;
-								cleanup_ncci_data(plci, ncci);
-								nl_req_ncci(plci, N_DISC, (byte)ncci);
-							}
-						}
-					}
-					mixer_remove(plci);
-					nl_req_ncci(plci, REMOVE, 0);
-					send_req(plci);
-				}
-			}
-			break;
-
-		case _DI_SIG_CTRL:
-			/* signalling control for loop activation B-channel */
-			if (!plci)
-			{
-				Info = _WRONG_IDENTIFIER;
-				break;
-			}
-			if (m->length) {
-				plci->command = _MANUFACTURER_R;
-				plci->number = Number;
-				add_ss(plci, FTY, m);
-				sig_req(plci, SIG_CTRL, 0);
-				send_req(plci);
-			}
-			else Info = _WRONG_MESSAGE_FORMAT;
-			break;
-
-		case _DI_RXT_CTRL:
-			/* activation control for receiver/transmitter B-channel */
-			if (!plci)
-			{
-				Info = _WRONG_IDENTIFIER;
-				break;
-			}
-			if (m->length) {
-				plci->command = _MANUFACTURER_R;
-				plci->number = Number;
-				add_ss(plci, FTY, m);
-				sig_req(plci, DSP_CTRL, 0);
-				send_req(plci);
-			}
-			else Info = _WRONG_MESSAGE_FORMAT;
-			break;
-
-		case _DI_ADV_CODEC:
-		case _DI_DSP_CTRL:
-			/* TEL_CTRL commands to support non standard adjustments: */
-			/* Ring on/off, Handset micro volume, external micro vol. */
-			/* handset+external speaker volume, receiver+transm. gain,*/
-			/* handsfree on (hookinfo off), set mixer command         */
-
-			if (command == _DI_ADV_CODEC)
-			{
-				if (!a->AdvCodecPLCI) {
-					Info = _WRONG_STATE;
-					break;
-				}
-				v_plci = a->AdvCodecPLCI;
-			}
-			else
-			{
-				if (plci
-				    && (m->length >= 3)
-				    && (m->info[1] == 0x1c)
-				    && (m->info[2] >= 1))
-				{
-					if (m->info[3] == DSP_CTRL_OLD_SET_MIXER_COEFFICIENTS)
-					{
-						if ((plci->tel != ADV_VOICE) || (plci != a->AdvSignalPLCI))
-						{
-							Info = _WRONG_STATE;
-							break;
-						}
-						a->adv_voice_coef_length = m->info[2] - 1;
-						if (a->adv_voice_coef_length > m->length - 3)
-							a->adv_voice_coef_length = (byte)(m->length - 3);
-						if (a->adv_voice_coef_length > ADV_VOICE_COEF_BUFFER_SIZE)
-							a->adv_voice_coef_length = ADV_VOICE_COEF_BUFFER_SIZE;
-						for (i = 0; i < a->adv_voice_coef_length; i++)
-							a->adv_voice_coef_buffer[i] = m->info[4 + i];
-						if (plci->B1_facilities & B1_FACILITY_VOICE)
-							adv_voice_write_coefs(plci, ADV_VOICE_WRITE_UPDATE);
-						break;
-					}
-					else if (m->info[3] == DSP_CTRL_SET_DTMF_PARAMETERS)
-					{
-						if (!(a->manufacturer_features & MANUFACTURER_FEATURE_DTMF_PARAMETERS))
-						{
-							Info = _FACILITY_NOT_SUPPORTED;
-							break;
-						}
-
-						plci->dtmf_parameter_length = m->info[2] - 1;
-						if (plci->dtmf_parameter_length > m->length - 3)
-							plci->dtmf_parameter_length = (byte)(m->length - 3);
-						if (plci->dtmf_parameter_length > DTMF_PARAMETER_BUFFER_SIZE)
-							plci->dtmf_parameter_length = DTMF_PARAMETER_BUFFER_SIZE;
-						for (i = 0; i < plci->dtmf_parameter_length; i++)
-							plci->dtmf_parameter_buffer[i] = m->info[4 + i];
-						if (plci->B1_facilities & B1_FACILITY_DTMFR)
-							dtmf_parameter_write(plci);
-						break;
-
-					}
-				}
-				v_plci = plci;
-			}
-
-			if (!v_plci)
-			{
-				Info = _WRONG_IDENTIFIER;
-				break;
-			}
-			if (m->length) {
-				add_ss(v_plci, FTY, m);
-				sig_req(v_plci, TEL_CTRL, 0);
-				send_req(v_plci);
-			}
-			else Info = _WRONG_MESSAGE_FORMAT;
-
-			break;
-
-		case _DI_OPTIONS_REQUEST:
-			if (api_parse(&m->info[1], (word)m->length, "d", m_parms)) {
-				Info = _WRONG_MESSAGE_FORMAT;
-				break;
-			}
-			if (GET_DWORD(m_parms[0].info) & ~a->man_profile.private_options)
-			{
-				Info = _FACILITY_NOT_SUPPORTED;
-				break;
-			}
-			a->requested_options_table[appl->Id - 1] = GET_DWORD(m_parms[0].info);
-			break;
-
-
-
-		default:
-			Info = _WRONG_MESSAGE_FORMAT;
-			break;
-		}
-	}
-
-	sendf(appl,
-	      _MANUFACTURER_R | CONFIRM,
-	      Id,
-	      Number,
-	      "dww", _DI_MANU_ID, command, Info);
-	return false;
-}
-
-
-static byte manufacturer_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a,
-			     PLCI *plci, APPL *appl, API_PARSE *msg)
-{
-	word indication;
-
-	API_PARSE m_parms[3];
-	API_PARSE *ncpi;
-	API_PARSE fax_parms[9];
-	word i;
-	byte len;
-
-
-	dbug(1, dprintf("manufacturer_res"));
-
-	if ((msg[0].length == 0)
-	    || (msg[1].length == 0)
-	    || (GET_DWORD(msg[0].info) != _DI_MANU_ID))
-	{
-		return false;
-	}
-	indication = GET_WORD(msg[1].info);
-	switch (indication)
-	{
-
-	case _DI_NEGOTIATE_B3:
-		if (!plci)
-			break;
-		if (((plci->B3_prot != 4) && (plci->B3_prot != 5))
-		    || !(plci->ncpi_state & NCPI_NEGOTIATE_B3_SENT))
-		{
-			dbug(1, dprintf("wrong state for NEGOTIATE_B3 parameters"));
-			break;
-		}
-		if (api_parse(&msg[2].info[1], msg[2].length, "ws", m_parms))
-		{
-			dbug(1, dprintf("wrong format in NEGOTIATE_B3 parameters"));
-			break;
-		}
-		ncpi = &m_parms[1];
-		len = offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH;
-		if (plci->fax_connect_info_length < len)
-		{
-			((T30_INFO *)(plci->fax_connect_info_buffer))->station_id_len = 0;
-			((T30_INFO *)(plci->fax_connect_info_buffer))->head_line_len = 0;
-		}
-		if (api_parse(&ncpi->info[1], ncpi->length, "wwwwssss", fax_parms))
-		{
-			dbug(1, dprintf("non-standard facilities info missing or wrong format"));
-		}
-		else
-		{
-			if (plci->fax_connect_info_length <= len)
-				plci->fax_connect_info_buffer[len] = 0;
-			len += 1 + plci->fax_connect_info_buffer[len];
-			if (plci->fax_connect_info_length <= len)
-				plci->fax_connect_info_buffer[len] = 0;
-			len += 1 + plci->fax_connect_info_buffer[len];
-			if ((fax_parms[7].length >= 3) && (fax_parms[7].info[1] >= 2))
-				plci->nsf_control_bits = GET_WORD(&fax_parms[7].info[2]);
-			plci->fax_connect_info_buffer[len++] = (byte)(fax_parms[7].length);
-			for (i = 0; i < fax_parms[7].length; i++)
-				plci->fax_connect_info_buffer[len++] = fax_parms[7].info[1 + i];
-		}
-		plci->fax_connect_info_length = len;
-		plci->fax_edata_ack_length = plci->fax_connect_info_length;
-		start_internal_command(Id, plci, fax_edata_ack_command);
-		break;
-
-	}
-	return false;
-}
-
-/*------------------------------------------------------------------*/
-/* IDI callback function                                            */
-/*------------------------------------------------------------------*/
-
-void callback(ENTITY *e)
-{
-	DIVA_CAPI_ADAPTER *a;
-	APPL *appl;
-	PLCI *plci;
-	CAPI_MSG *m;
-	word i, j;
-	byte rc;
-	byte ch;
-	byte req;
-	byte global_req;
-	int no_cancel_rc;
-
-	dbug(1, dprintf("%x:CB(%x:Req=%x,Rc=%x,Ind=%x)",
-			(e->user[0] + 1) & 0x7fff, e->Id, e->Req, e->Rc, e->Ind));
-
-	a = &(adapter[(byte)e->user[0]]);
-	plci = &(a->plci[e->user[1]]);
-	no_cancel_rc = DIVA_CAPI_SUPPORTS_NO_CANCEL(a);
-
-	/*
-	  If new protocol code and new XDI is used then CAPI should work
-	  fully in accordance with IDI cpec an look on callback field instead
-	  of Rc field for return codes.
-	*/
-	if (((e->complete == 0xff) && no_cancel_rc) ||
-	    (e->Rc && !no_cancel_rc)) {
-		rc = e->Rc;
-		ch = e->RcCh;
-		req = e->Req;
-		e->Rc = 0;
-
-		if (e->user[0] & 0x8000)
-		{
-			/*
-			  If REMOVE request was sent then we have to wait until
-			  return code with Id set to zero arrives.
-			  All other return codes should be ignored.
-			*/
-			if (req == REMOVE)
-			{
-				if (e->Id)
-				{
-					dbug(1, dprintf("cancel RC in REMOVE state"));
-					return;
-				}
-				channel_flow_control_remove(plci);
-				for (i = 0; i < 256; i++)
-				{
-					if (a->FlowControlIdTable[i] == plci->nl_remove_id)
-						a->FlowControlIdTable[i] = 0;
-				}
-				plci->nl_remove_id = 0;
-				if (plci->rx_dma_descriptor > 0) {
-					diva_free_dma_descriptor(plci, plci->rx_dma_descriptor - 1);
-					plci->rx_dma_descriptor = 0;
-				}
-			}
-			if (rc == OK_FC)
-			{
-				a->FlowControlIdTable[ch] = e->Id;
-				a->FlowControlSkipTable[ch] = 0;
-
-				a->ch_flow_control[ch] |= N_OK_FC_PENDING;
-				a->ch_flow_plci[ch] = plci->Id;
-				plci->nl_req = 0;
-			}
-			else
-			{
-				/*
-				  Cancel return codes self, if feature was requested
-				*/
-				if (no_cancel_rc && (a->FlowControlIdTable[ch] == e->Id) && e->Id) {
-					a->FlowControlIdTable[ch] = 0;
-					if ((rc == OK) && a->FlowControlSkipTable[ch]) {
-						dbug(3, dprintf("XDI CAPI: RC cancelled Id:0x02, Ch:%02x", e->Id, ch));
-						return;
-					}
-				}
-
-				if (a->ch_flow_control[ch] & N_OK_FC_PENDING)
-				{
-					a->ch_flow_control[ch] &= ~N_OK_FC_PENDING;
-					if (ch == e->ReqCh)
-						plci->nl_req = 0;
-				}
-				else
-					plci->nl_req = 0;
-			}
-			if (plci->nl_req)
-				control_rc(plci, 0, rc, ch, 0, true);
-			else
-			{
-				if (req == N_XON)
-				{
-					channel_x_on(plci, ch);
-					if (plci->internal_command)
-						control_rc(plci, req, rc, ch, 0, true);
-				}
-				else
-				{
-					if (plci->nl_global_req)
-					{
-						global_req = plci->nl_global_req;
-						plci->nl_global_req = 0;
-						if (rc != ASSIGN_OK) {
-							e->Id = 0;
-							if (plci->rx_dma_descriptor > 0) {
-								diva_free_dma_descriptor(plci, plci->rx_dma_descriptor - 1);
-								plci->rx_dma_descriptor = 0;
-							}
-						}
-						channel_xmit_xon(plci);
-						control_rc(plci, 0, rc, ch, global_req, true);
-					}
-					else if (plci->data_sent)
-					{
-						channel_xmit_xon(plci);
-						plci->data_sent = false;
-						plci->NL.XNum = 1;
-						data_rc(plci, ch);
-						if (plci->internal_command)
-							control_rc(plci, req, rc, ch, 0, true);
-					}
-					else
-					{
-						channel_xmit_xon(plci);
-						control_rc(plci, req, rc, ch, 0, true);
-					}
-				}
-			}
-		}
-		else
-		{
-			/*
-			  If REMOVE request was sent then we have to wait until
-			  return code with Id set to zero arrives.
-			  All other return codes should be ignored.
-			*/
-			if (req == REMOVE)
-			{
-				if (e->Id)
-				{
-					dbug(1, dprintf("cancel RC in REMOVE state"));
-					return;
-				}
-				plci->sig_remove_id = 0;
-			}
-			plci->sig_req = 0;
-			if (plci->sig_global_req)
-			{
-				global_req = plci->sig_global_req;
-				plci->sig_global_req = 0;
-				if (rc != ASSIGN_OK)
-					e->Id = 0;
-				channel_xmit_xon(plci);
-				control_rc(plci, 0, rc, ch, global_req, false);
-			}
-			else
-			{
-				channel_xmit_xon(plci);
-				control_rc(plci, req, rc, ch, 0, false);
-			}
-		}
-		/*
-		  Again: in accordance with IDI spec Rc and Ind can't be delivered in the
-		  same callback. Also if new XDI and protocol code used then jump
-		  direct to finish.
-		*/
-		if (no_cancel_rc) {
-			channel_xmit_xon(plci);
-			goto capi_callback_suffix;
-		}
-	}
-
-	channel_xmit_xon(plci);
-
-	if (e->Ind) {
-		if (e->user[0] & 0x8000) {
-			byte Ind = e->Ind & 0x0f;
-			byte Ch = e->IndCh;
-			if (((Ind == N_DISC) || (Ind == N_DISC_ACK)) &&
-			    (a->ch_flow_plci[Ch] == plci->Id)) {
-				if (a->ch_flow_control[Ch] & N_RX_FLOW_CONTROL_MASK) {
-					dbug(3, dprintf("XDI CAPI: I: pending N-XON Ch:%02x", Ch));
-				}
-				a->ch_flow_control[Ch] &= ~N_RX_FLOW_CONTROL_MASK;
-			}
-			nl_ind(plci);
-			if ((e->RNR != 1) &&
-			    (a->ch_flow_plci[Ch] == plci->Id) &&
-			    (a->ch_flow_control[Ch] & N_RX_FLOW_CONTROL_MASK)) {
-				a->ch_flow_control[Ch] &= ~N_RX_FLOW_CONTROL_MASK;
-				dbug(3, dprintf("XDI CAPI: I: remove faked N-XON Ch:%02x", Ch));
-			}
-		} else {
-			sig_ind(plci);
-		}
-		e->Ind = 0;
-	}
-
-capi_callback_suffix:
-
-	while (!plci->req_in
-	       && !plci->internal_command
-	       && (plci->msg_in_write_pos != plci->msg_in_read_pos))
-	{
-		j = (plci->msg_in_read_pos == plci->msg_in_wrap_pos) ? 0 : plci->msg_in_read_pos;
-
-		i = (((CAPI_MSG *)(&((byte *)(plci->msg_in_queue))[j]))->header.length + 3) & 0xfffc;
-
-		m = (CAPI_MSG *)(&((byte *)(plci->msg_in_queue))[j]);
-		appl = *((APPL **)(&((byte *)(plci->msg_in_queue))[j + i]));
-		dbug(1, dprintf("dequeue msg(0x%04x) - write=%d read=%d wrap=%d",
-				m->header.command, plci->msg_in_write_pos, plci->msg_in_read_pos, plci->msg_in_wrap_pos));
-		if (plci->msg_in_read_pos == plci->msg_in_wrap_pos)
-		{
-			plci->msg_in_wrap_pos = MSG_IN_QUEUE_SIZE;
-			plci->msg_in_read_pos = i + MSG_IN_OVERHEAD;
-		}
-		else
-		{
-			plci->msg_in_read_pos = j + i + MSG_IN_OVERHEAD;
-		}
-		if (plci->msg_in_read_pos == plci->msg_in_write_pos)
-		{
-			plci->msg_in_write_pos = MSG_IN_QUEUE_SIZE;
-			plci->msg_in_read_pos = MSG_IN_QUEUE_SIZE;
-		}
-		else if (plci->msg_in_read_pos == plci->msg_in_wrap_pos)
-		{
-			plci->msg_in_read_pos = MSG_IN_QUEUE_SIZE;
-			plci->msg_in_wrap_pos = MSG_IN_QUEUE_SIZE;
-		}
-		i = api_put(appl, m);
-		if (i != 0)
-		{
-			if (m->header.command == _DATA_B3_R)
-
-				TransmitBufferFree(appl, (byte *)(long)(m->info.data_b3_req.Data));
-
-			dbug(1, dprintf("Error 0x%04x from msg(0x%04x)", i, m->header.command));
-			break;
-		}
-
-		if (plci->li_notify_update)
-		{
-			plci->li_notify_update = false;
-			mixer_notify_update(plci, false);
-		}
-
-	}
-	send_data(plci);
-	send_req(plci);
-}
-
-
-static void control_rc(PLCI *plci, byte req, byte rc, byte ch, byte global_req,
-		       byte nl_rc)
-{
-	dword Id;
-	dword rId;
-	word Number;
-	word Info = 0;
-	word i;
-	word ncci;
-	DIVA_CAPI_ADAPTER *a;
-	APPL *appl;
-	PLCI *rplci;
-	byte SSparms[] = "\x05\x00\x00\x02\x00\x00";
-	byte SSstruct[] = "\x09\x00\x00\x06\x00\x00\x00\x00\x00\x00";
-
-	if (!plci) {
-		dbug(0, dprintf("A: control_rc, no plci %02x:%02x:%02x:%02x:%02x", req, rc, ch, global_req, nl_rc));
-		return;
-	}
-	dbug(1, dprintf("req0_in/out=%d/%d", plci->req_in, plci->req_out));
-	if (plci->req_in != plci->req_out)
-	{
-		if (nl_rc || (global_req != ASSIGN) || (rc == ASSIGN_OK))
-		{
-			dbug(1, dprintf("req_1return"));
-			return;
-		}
-		/* cancel outstanding request on the PLCI after SIG ASSIGN failure */
-	}
-	plci->req_in = plci->req_in_start = plci->req_out = 0;
-	dbug(1, dprintf("control_rc"));
-
-	appl = plci->appl;
-	a = plci->adapter;
-	ncci = a->ch_ncci[ch];
-	if (appl)
-	{
-		Id = (((dword)(ncci ? ncci : ch)) << 16) | ((word)plci->Id << 8) | a->Id;
-		if (plci->tel && plci->SuppState != CALL_HELD) Id |= EXT_CONTROLLER;
-		Number = plci->number;
-		dbug(1, dprintf("Contr_RC-Id=%08lx,plci=%x,tel=%x, entity=0x%x, command=0x%x, int_command=0x%x", Id, plci->Id, plci->tel, plci->Sig.Id, plci->command, plci->internal_command));
-		dbug(1, dprintf("channels=0x%x", plci->channels));
-		if (plci_remove_check(plci))
-			return;
-		if (req == REMOVE && rc == ASSIGN_OK)
-		{
-			sig_req(plci, HANGUP, 0);
-			sig_req(plci, REMOVE, 0);
-			send_req(plci);
-		}
-		if (plci->command)
-		{
-			switch (plci->command)
-			{
-			case C_HOLD_REQ:
-				dbug(1, dprintf("HoldRC=0x%x", rc));
-				SSparms[1] = (byte)S_HOLD;
-				if (rc != OK)
-				{
-					plci->SuppState = IDLE;
-					Info = 0x2001;
-				}
-				sendf(appl, _FACILITY_R | CONFIRM, Id, Number, "wws", Info, 3, SSparms);
-				break;
-
-			case C_RETRIEVE_REQ:
-				dbug(1, dprintf("RetrieveRC=0x%x", rc));
-				SSparms[1] = (byte)S_RETRIEVE;
-				if (rc != OK)
-				{
-					plci->SuppState = CALL_HELD;
-					Info = 0x2001;
-				}
-				sendf(appl, _FACILITY_R | CONFIRM, Id, Number, "wws", Info, 3, SSparms);
-				break;
-
-			case _INFO_R:
-				dbug(1, dprintf("InfoRC=0x%x", rc));
-				if (rc != OK) Info = _WRONG_STATE;
-				sendf(appl, _INFO_R | CONFIRM, Id, Number, "w", Info);
-				break;
-
-			case _CONNECT_R:
-				dbug(1, dprintf("Connect_R=0x%x/0x%x/0x%x/0x%x", req, rc, global_req, nl_rc));
-				if (plci->State == INC_DIS_PENDING)
-					break;
-				if (plci->Sig.Id != 0xff)
-				{
-					if (((global_req == ASSIGN) && (rc != ASSIGN_OK))
-					    || (!nl_rc && (req == CALL_REQ) && (rc != OK)))
-					{
-						dbug(1, dprintf("No more IDs/Call_Req failed"));
-						sendf(appl, _CONNECT_R | CONFIRM, Id & 0xffL, Number, "w", _OUT_OF_PLCI);
-						plci_remove(plci);
-						plci->State = IDLE;
-						break;
-					}
-					if (plci->State != LOCAL_CONNECT) plci->State = OUTG_CON_PENDING;
-					sendf(appl, _CONNECT_R | CONFIRM, Id, Number, "w", 0);
-				}
-				else /* D-ch activation */
-				{
-					if (rc != ASSIGN_OK)
-					{
-						dbug(1, dprintf("No more IDs/X.25 Call_Req failed"));
-						sendf(appl, _CONNECT_R | CONFIRM, Id & 0xffL, Number, "w", _OUT_OF_PLCI);
-						plci_remove(plci);
-						plci->State = IDLE;
-						break;
-					}
-					sendf(appl, _CONNECT_R | CONFIRM, Id, Number, "w", 0);
-					sendf(plci->appl, _CONNECT_ACTIVE_I, Id, 0, "sss", "", "", "");
-					plci->State = INC_ACT_PENDING;
-				}
-				break;
-
-			case _CONNECT_I | RESPONSE:
-				if (plci->State != INC_DIS_PENDING)
-					plci->State = INC_CON_ACCEPT;
-				break;
-
-			case _DISCONNECT_R:
-				if (plci->State == INC_DIS_PENDING)
-					break;
-				if (plci->Sig.Id != 0xff)
-				{
-					plci->State = OUTG_DIS_PENDING;
-					sendf(appl, _DISCONNECT_R | CONFIRM, Id, Number, "w", 0);
-				}
-				break;
-
-			case SUSPEND_REQ:
-				break;
-
-			case RESUME_REQ:
-				break;
-
-			case _CONNECT_B3_R:
-				if (rc != OK)
-				{
-					sendf(appl, _CONNECT_B3_R | CONFIRM, Id, Number, "w", _WRONG_IDENTIFIER);
-					break;
-				}
-				ncci = get_ncci(plci, ch, 0);
-				Id = (Id & 0xffff) | (((dword) ncci) << 16);
-				plci->channels++;
-				if (req == N_RESET)
-				{
-					a->ncci_state[ncci] = INC_ACT_PENDING;
-					sendf(appl, _CONNECT_B3_R | CONFIRM, Id, Number, "w", 0);
-					sendf(appl, _CONNECT_B3_ACTIVE_I, Id, 0, "s", "");
-				}
-				else
-				{
-					a->ncci_state[ncci] = OUTG_CON_PENDING;
-					sendf(appl, _CONNECT_B3_R | CONFIRM, Id, Number, "w", 0);
-				}
-				break;
-
-			case _CONNECT_B3_I | RESPONSE:
-				break;
-
-			case _RESET_B3_R:
-/*        sendf(appl, _RESET_B3_R | CONFIRM, Id, Number, "w", 0);*/
-				break;
-
-			case _DISCONNECT_B3_R:
-				sendf(appl, _DISCONNECT_B3_R | CONFIRM, Id, Number, "w", 0);
-				break;
-
-			case _MANUFACTURER_R:
-				break;
-
-			case PERM_LIST_REQ:
-				if (rc != OK)
-				{
-					Info = _WRONG_IDENTIFIER;
-					sendf(plci->appl, _CONNECT_R | CONFIRM, Id, Number, "w", Info);
-					plci_remove(plci);
-				}
-				else
-					sendf(plci->appl, _CONNECT_R | CONFIRM, Id, Number, "w", Info);
-				break;
-
-			default:
-				break;
-			}
-			plci->command = 0;
-		}
-		else if (plci->internal_command)
-		{
-			switch (plci->internal_command)
-			{
-			case BLOCK_PLCI:
-				return;
-
-			case GET_MWI_STATE:
-				if (rc == OK) /* command supported, wait for indication */
-				{
-					return;
-				}
-				plci_remove(plci);
-				break;
-
-				/* Get Supported Services */
-			case GETSERV_REQ_PEND:
-				if (rc == OK) /* command supported, wait for indication */
-				{
-					break;
-				}
-				PUT_DWORD(&SSstruct[6], MASK_TERMINAL_PORTABILITY);
-				sendf(appl, _FACILITY_R | CONFIRM, Id, Number, "wws", 0, 3, SSstruct);
-				plci_remove(plci);
-				break;
-
-			case INTERR_DIVERSION_REQ_PEND:      /* Interrogate Parameters        */
-			case INTERR_NUMBERS_REQ_PEND:
-			case CF_START_PEND:                  /* Call Forwarding Start pending */
-			case CF_STOP_PEND:                   /* Call Forwarding Stop pending  */
-			case CCBS_REQUEST_REQ_PEND:
-			case CCBS_DEACTIVATE_REQ_PEND:
-			case CCBS_INTERROGATE_REQ_PEND:
-				switch (plci->internal_command)
-				{
-				case INTERR_DIVERSION_REQ_PEND:
-					SSparms[1] = S_INTERROGATE_DIVERSION;
-					break;
-				case INTERR_NUMBERS_REQ_PEND:
-					SSparms[1] = S_INTERROGATE_NUMBERS;
-					break;
-				case CF_START_PEND:
-					SSparms[1] = S_CALL_FORWARDING_START;
-					break;
-				case CF_STOP_PEND:
-					SSparms[1] = S_CALL_FORWARDING_STOP;
-					break;
-				case CCBS_REQUEST_REQ_PEND:
-					SSparms[1] = S_CCBS_REQUEST;
-					break;
-				case CCBS_DEACTIVATE_REQ_PEND:
-					SSparms[1] = S_CCBS_DEACTIVATE;
-					break;
-				case CCBS_INTERROGATE_REQ_PEND:
-					SSparms[1] = S_CCBS_INTERROGATE;
-					break;
-				}
-				if (global_req == ASSIGN)
-				{
-					dbug(1, dprintf("AssignDiversion_RC=0x%x/0x%x", req, rc));
-					return;
-				}
-				if (!plci->appl) break;
-				if (rc == ISDN_GUARD_REJ)
-				{
-					Info = _CAPI_GUARD_ERROR;
-				}
-				else if (rc != OK)
-				{
-					Info = _SUPPLEMENTARY_SERVICE_NOT_SUPPORTED;
-				}
-				sendf(plci->appl, _FACILITY_R | CONFIRM, Id & 0x7,
-				      plci->number, "wws", Info, (word)3, SSparms);
-				if (Info) plci_remove(plci);
-				break;
-
-				/* 3pty conference pending */
-			case PTY_REQ_PEND:
-				if (!plci->relatedPTYPLCI) break;
-				rplci = plci->relatedPTYPLCI;
-				SSparms[1] = plci->ptyState;
-				rId = ((word)rplci->Id << 8) | rplci->adapter->Id;
-				if (rplci->tel) rId |= EXT_CONTROLLER;
-				if (rc != OK)
-				{
-					Info = 0x300E; /* not supported */
-					plci->relatedPTYPLCI = NULL;
-					plci->ptyState = 0;
-				}
-				sendf(rplci->appl,
-				      _FACILITY_R | CONFIRM,
-				      rId,
-				      plci->number,
-				      "wws", Info, (word)3, SSparms);
-				break;
-
-				/* Explicit Call Transfer pending */
-			case ECT_REQ_PEND:
-				dbug(1, dprintf("ECT_RC=0x%x/0x%x", req, rc));
-				if (!plci->relatedPTYPLCI) break;
-				rplci = plci->relatedPTYPLCI;
-				SSparms[1] = S_ECT;
-				rId = ((word)rplci->Id << 8) | rplci->adapter->Id;
-				if (rplci->tel) rId |= EXT_CONTROLLER;
-				if (rc != OK)
-				{
-					Info = 0x300E; /* not supported */
-					plci->relatedPTYPLCI = NULL;
-					plci->ptyState = 0;
-				}
-				sendf(rplci->appl,
-				      _FACILITY_R | CONFIRM,
-				      rId,
-				      plci->number,
-				      "wws", Info, (word)3, SSparms);
-				break;
-
-			case _MANUFACTURER_R:
-				dbug(1, dprintf("_Manufacturer_R=0x%x/0x%x", req, rc));
-				if ((global_req == ASSIGN) && (rc != ASSIGN_OK))
-				{
-					dbug(1, dprintf("No more IDs"));
-					sendf(appl, _MANUFACTURER_R | CONFIRM, Id, Number, "dww", _DI_MANU_ID, _MANUFACTURER_R, _OUT_OF_PLCI);
-					plci_remove(plci);  /* after codec init, internal codec commands pending */
-				}
-				break;
-
-			case _CONNECT_R:
-				dbug(1, dprintf("_Connect_R=0x%x/0x%x", req, rc));
-				if ((global_req == ASSIGN) && (rc != ASSIGN_OK))
-				{
-					dbug(1, dprintf("No more IDs"));
-					sendf(appl, _CONNECT_R | CONFIRM, Id & 0xffL, Number, "w", _OUT_OF_PLCI);
-					plci_remove(plci);  /* after codec init, internal codec commands pending */
-				}
-				break;
-
-			case PERM_COD_HOOK:                     /* finished with Hook_Ind */
-				return;
-
-			case PERM_COD_CALL:
-				dbug(1, dprintf("***Codec Connect_Pending A, Rc = 0x%x", rc));
-				plci->internal_command = PERM_COD_CONN_PEND;
-				return;
-
-			case PERM_COD_ASSIGN:
-				dbug(1, dprintf("***Codec Assign A, Rc = 0x%x", rc));
-				if (rc != ASSIGN_OK) break;
-				sig_req(plci, CALL_REQ, 0);
-				send_req(plci);
-				plci->internal_command = PERM_COD_CALL;
-				return;
-
-				/* Null Call Reference Request pending */
-			case C_NCR_FAC_REQ:
-				dbug(1, dprintf("NCR_FAC=0x%x/0x%x", req, rc));
-				if (global_req == ASSIGN)
-				{
-					if (rc == ASSIGN_OK)
-					{
-						return;
-					}
-					else
-					{
-						sendf(appl, _INFO_R | CONFIRM, Id & 0xf, Number, "w", _WRONG_STATE);
-						appl->NullCREnable = false;
-						plci_remove(plci);
-					}
-				}
-				else if (req == NCR_FACILITY)
-				{
-					if (rc == OK)
-					{
-						sendf(appl, _INFO_R | CONFIRM, Id & 0xf, Number, "w", 0);
-					}
-					else
-					{
-						sendf(appl, _INFO_R | CONFIRM, Id & 0xf, Number, "w", _WRONG_STATE);
-						appl->NullCREnable = false;
-					}
-					plci_remove(plci);
-				}
-				break;
-
-			case HOOK_ON_REQ:
-				if (plci->channels)
-				{
-					if (a->ncci_state[ncci] == CONNECTED)
-					{
-						a->ncci_state[ncci] = OUTG_DIS_PENDING;
-						cleanup_ncci_data(plci, ncci);
-						nl_req_ncci(plci, N_DISC, (byte)ncci);
-					}
-					break;
-				}
-				break;
-
-			case HOOK_OFF_REQ:
-				if (plci->State == INC_DIS_PENDING)
-					break;
-				sig_req(plci, CALL_REQ, 0);
-				send_req(plci);
-				plci->State = OUTG_CON_PENDING;
-				break;
-
-
-			case MWI_ACTIVATE_REQ_PEND:
-			case MWI_DEACTIVATE_REQ_PEND:
-				if (global_req == ASSIGN && rc == ASSIGN_OK)
-				{
-					dbug(1, dprintf("MWI_REQ assigned"));
-					return;
-				}
-				else if (rc != OK)
-				{
-					if (rc == WRONG_IE)
-					{
-						Info = 0x2007; /* Illegal message parameter coding */
-						dbug(1, dprintf("MWI_REQ invalid parameter"));
-					}
-					else
-					{
-						Info = 0x300B; /* not supported */
-						dbug(1, dprintf("MWI_REQ not supported"));
-					}
-					/* 0x3010: Request not allowed in this state */
-					PUT_WORD(&SSparms[4], 0x300E); /* SS not supported */
-
-				}
-				if (plci->internal_command == MWI_ACTIVATE_REQ_PEND)
-				{
-					PUT_WORD(&SSparms[1], S_MWI_ACTIVATE);
-				}
-				else PUT_WORD(&SSparms[1], S_MWI_DEACTIVATE);
-
-				if (plci->cr_enquiry)
-				{
-					sendf(plci->appl,
-					      _FACILITY_R | CONFIRM,
-					      Id & 0xf,
-					      plci->number,
-					      "wws", Info, (word)3, SSparms);
-					if (rc != OK) plci_remove(plci);
-				}
-				else
-				{
-					sendf(plci->appl,
-					      _FACILITY_R | CONFIRM,
-					      Id,
-					      plci->number,
-					      "wws", Info, (word)3, SSparms);
-				}
-				break;
-
-			case CONF_BEGIN_REQ_PEND:
-			case CONF_ADD_REQ_PEND:
-			case CONF_SPLIT_REQ_PEND:
-			case CONF_DROP_REQ_PEND:
-			case CONF_ISOLATE_REQ_PEND:
-			case CONF_REATTACH_REQ_PEND:
-				dbug(1, dprintf("CONF_RC=0x%x/0x%x", req, rc));
-				if ((plci->internal_command == CONF_ADD_REQ_PEND) && (!plci->relatedPTYPLCI)) break;
-				rplci = plci;
-				rId = Id;
-				switch (plci->internal_command)
-				{
-				case CONF_BEGIN_REQ_PEND:
-					SSparms[1] = S_CONF_BEGIN;
-					break;
-				case CONF_ADD_REQ_PEND:
-					SSparms[1] = S_CONF_ADD;
-					rplci = plci->relatedPTYPLCI;
-					rId = ((word)rplci->Id << 8) | rplci->adapter->Id;
-					break;
-				case CONF_SPLIT_REQ_PEND:
-					SSparms[1] = S_CONF_SPLIT;
-					break;
-				case CONF_DROP_REQ_PEND:
-					SSparms[1] = S_CONF_DROP;
-					break;
-				case CONF_ISOLATE_REQ_PEND:
-					SSparms[1] = S_CONF_ISOLATE;
-					break;
-				case CONF_REATTACH_REQ_PEND:
-					SSparms[1] = S_CONF_REATTACH;
-					break;
-				}
-
-				if (rc != OK)
-				{
-					Info = 0x300E; /* not supported */
-					plci->relatedPTYPLCI = NULL;
-					plci->ptyState = 0;
-				}
-				sendf(rplci->appl,
-				      _FACILITY_R | CONFIRM,
-				      rId,
-				      plci->number,
-				      "wws", Info, (word)3, SSparms);
-				break;
-
-			case VSWITCH_REQ_PEND:
-				if (rc != OK)
-				{
-					if (plci->relatedPTYPLCI)
-					{
-						plci->relatedPTYPLCI->vswitchstate = 0;
-						plci->relatedPTYPLCI->vsprot = 0;
-						plci->relatedPTYPLCI->vsprotdialect = 0;
-					}
-					plci->vswitchstate = 0;
-					plci->vsprot = 0;
-					plci->vsprotdialect = 0;
-				}
-				else
-				{
-					if (plci->relatedPTYPLCI &&
-					    plci->vswitchstate == 1 &&
-					    plci->relatedPTYPLCI->vswitchstate == 3) /* join complete */
-						plci->vswitchstate = 3;
-				}
-				break;
-
-				/* Call Deflection Request pending (SSCT) */
-			case CD_REQ_PEND:
-				SSparms[1] = S_CALL_DEFLECTION;
-				if (rc != OK)
-				{
-					Info = 0x300E; /* not supported */
-					plci->appl->CDEnable = 0;
-				}
-				sendf(plci->appl, _FACILITY_R | CONFIRM, Id,
-				      plci->number, "wws", Info, (word)3, SSparms);
-				break;
-
-			case RTP_CONNECT_B3_REQ_COMMAND_2:
-				if (rc == OK)
-				{
-					ncci = get_ncci(plci, ch, 0);
-					Id = (Id & 0xffff) | (((dword) ncci) << 16);
-					plci->channels++;
-					a->ncci_state[ncci] = OUTG_CON_PENDING;
-				}
-				/* fall through */
-
-			default:
-				if (plci->internal_command_queue[0])
-				{
-					(*(plci->internal_command_queue[0]))(Id, plci, rc);
-					if (plci->internal_command)
-						return;
-				}
-				break;
-			}
-			next_internal_command(Id, plci);
-		}
-	}
-	else /* appl==0 */
-	{
-		Id = ((word)plci->Id << 8) | plci->adapter->Id;
-		if (plci->tel) Id |= EXT_CONTROLLER;
-
-		switch (plci->internal_command)
-		{
-		case BLOCK_PLCI:
-			return;
-
-		case START_L1_SIG_ASSIGN_PEND:
-		case REM_L1_SIG_ASSIGN_PEND:
-			if (global_req == ASSIGN)
-			{
-				break;
-			}
-			else
-			{
-				dbug(1, dprintf("***L1 Req rem PLCI"));
-				plci->internal_command = 0;
-				sig_req(plci, REMOVE, 0);
-				send_req(plci);
-			}
-			break;
-
-			/* Call Deflection Request pending, just no appl ptr assigned */
-		case CD_REQ_PEND:
-			SSparms[1] = S_CALL_DEFLECTION;
-			if (rc != OK)
-			{
-				Info = 0x300E; /* not supported */
-			}
-			for (i = 0; i < max_appl; i++)
-			{
-				if (application[i].CDEnable)
-				{
-					if (!application[i].Id) application[i].CDEnable = 0;
-					else
-					{
-						sendf(&application[i], _FACILITY_R | CONFIRM, Id,
-						      plci->number, "wws", Info, (word)3, SSparms);
-						if (Info) application[i].CDEnable = 0;
-					}
-				}
-			}
-			plci->internal_command = 0;
-			break;
-
-		case PERM_COD_HOOK:                   /* finished with Hook_Ind */
-			return;
-
-		case PERM_COD_CALL:
-			plci->internal_command = PERM_COD_CONN_PEND;
-			dbug(1, dprintf("***Codec Connect_Pending, Rc = 0x%x", rc));
-			return;
-
-		case PERM_COD_ASSIGN:
-			dbug(1, dprintf("***Codec Assign, Rc = 0x%x", rc));
-			plci->internal_command = 0;
-			if (rc != ASSIGN_OK) break;
-			plci->internal_command = PERM_COD_CALL;
-			sig_req(plci, CALL_REQ, 0);
-			send_req(plci);
-			return;
-
-		case LISTEN_SIG_ASSIGN_PEND:
-			if (rc == ASSIGN_OK)
-			{
-				plci->internal_command = 0;
-				dbug(1, dprintf("ListenCheck, new SIG_ID = 0x%x", plci->Sig.Id));
-				add_p(plci, ESC, "\x02\x18\x00");             /* support call waiting */
-				sig_req(plci, INDICATE_REQ, 0);
-				send_req(plci);
-			}
-			else
-			{
-				dbug(1, dprintf("ListenCheck failed (assignRc=0x%x)", rc));
-				a->listen_active--;
-				plci_remove(plci);
-				plci->State = IDLE;
-			}
-			break;
-
-		case USELAW_REQ:
-			if (global_req == ASSIGN)
-			{
-				if (rc == ASSIGN_OK)
-				{
-					sig_req(plci, LAW_REQ, 0);
-					send_req(plci);
-					dbug(1, dprintf("Auto-Law assigned"));
-				}
-				else
-				{
-					dbug(1, dprintf("Auto-Law assign failed"));
-					a->automatic_law = 3;
-					plci->internal_command = 0;
-					a->automatic_lawPLCI = NULL;
-				}
-				break;
-			}
-			else if (req == LAW_REQ && rc == OK)
-			{
-				dbug(1, dprintf("Auto-Law initiated"));
-				a->automatic_law = 2;
-				plci->internal_command = 0;
-			}
-			else
-			{
-				dbug(1, dprintf("Auto-Law not supported"));
-				a->automatic_law = 3;
-				plci->internal_command = 0;
-				sig_req(plci, REMOVE, 0);
-				send_req(plci);
-				a->automatic_lawPLCI = NULL;
-			}
-			break;
-		}
-		plci_remove_check(plci);
-	}
-}
-
-static void data_rc(PLCI *plci, byte ch)
-{
-	dword Id;
-	DIVA_CAPI_ADAPTER *a;
-	NCCI *ncci_ptr;
-	DATA_B3_DESC *data;
-	word ncci;
-
-	if (plci->appl)
-	{
-		TransmitBufferFree(plci->appl, plci->data_sent_ptr);
-		a = plci->adapter;
-		ncci = a->ch_ncci[ch];
-		if (ncci && (a->ncci_plci[ncci] == plci->Id))
-		{
-			ncci_ptr = &(a->ncci[ncci]);
-			dbug(1, dprintf("data_out=%d, data_pending=%d", ncci_ptr->data_out, ncci_ptr->data_pending));
-			if (ncci_ptr->data_pending)
-			{
-				data = &(ncci_ptr->DBuffer[ncci_ptr->data_out]);
-				if (!(data->Flags & 4) && a->ncci_state[ncci])
-				{
-					Id = (((dword)ncci) << 16) | ((word)plci->Id << 8) | a->Id;
-					if (plci->tel) Id |= EXT_CONTROLLER;
-					sendf(plci->appl, _DATA_B3_R | CONFIRM, Id, data->Number,
-					      "ww", data->Handle, 0);
-				}
-				(ncci_ptr->data_out)++;
-				if (ncci_ptr->data_out == MAX_DATA_B3)
-					ncci_ptr->data_out = 0;
-				(ncci_ptr->data_pending)--;
-			}
-		}
-	}
-}
-
-static void data_ack(PLCI *plci, byte ch)
-{
-	dword Id;
-	DIVA_CAPI_ADAPTER *a;
-	NCCI *ncci_ptr;
-	word ncci;
-
-	a = plci->adapter;
-	ncci = a->ch_ncci[ch];
-	ncci_ptr = &(a->ncci[ncci]);
-	if (ncci_ptr->data_ack_pending)
-	{
-		if (a->ncci_state[ncci] && (a->ncci_plci[ncci] == plci->Id))
-		{
-			Id = (((dword)ncci) << 16) | ((word)plci->Id << 8) | a->Id;
-			if (plci->tel) Id |= EXT_CONTROLLER;
-			sendf(plci->appl, _DATA_B3_R | CONFIRM, Id, ncci_ptr->DataAck[ncci_ptr->data_ack_out].Number,
-			      "ww", ncci_ptr->DataAck[ncci_ptr->data_ack_out].Handle, 0);
-		}
-		(ncci_ptr->data_ack_out)++;
-		if (ncci_ptr->data_ack_out == MAX_DATA_ACK)
-			ncci_ptr->data_ack_out = 0;
-		(ncci_ptr->data_ack_pending)--;
-	}
-}
-
-static void sig_ind(PLCI *plci)
-{
-	dword x_Id;
-	dword Id;
-	dword rId;
-	word i;
-	word cip;
-	dword cip_mask;
-	byte *ie;
-	DIVA_CAPI_ADAPTER *a;
-	API_PARSE saved_parms[MAX_MSG_PARMS + 1];
-#define MAXPARMSIDS 31
-	byte *parms[MAXPARMSIDS];
-	byte *add_i[4];
-	byte *multi_fac_parms[MAX_MULTI_IE];
-	byte *multi_pi_parms[MAX_MULTI_IE];
-	byte *multi_ssext_parms[MAX_MULTI_IE];
-	byte *multi_CiPN_parms[MAX_MULTI_IE];
-
-	byte *multi_vswitch_parms[MAX_MULTI_IE];
-
-	byte ai_len;
-	byte *esc_chi = "";
-	byte *esc_law = "";
-	byte *pty_cai = "";
-	byte *esc_cr  = "";
-	byte *esc_profile = "";
-
-	byte facility[256];
-	PLCI *tplci = NULL;
-	byte chi[] = "\x02\x18\x01";
-	byte voice_cai[]  = "\x06\x14\x00\x00\x00\x00\x08";
-	byte resume_cau[] = "\x05\x05\x00\x02\x00\x00";
-	/* ESC_MSGTYPE must be the last but one message, a new IE has to be */
-	/* included before the ESC_MSGTYPE and MAXPARMSIDS has to be incremented */
-	/* SMSG is situated at the end because its 0 (for compatibility reasons */
-	/* (see Info_Mask Bit 4, first IE. then the message type)           */
-	static const word parms_id[] =
-		{MAXPARMSIDS, CPN, 0xff, DSA, OSA, BC, LLC, HLC, ESC_CAUSE, DSP, DT, CHA,
-		 UUI, CONG_RR, CONG_RNR, ESC_CHI, KEY, CHI, CAU, ESC_LAW,
-		 RDN, RDX, CONN_NR, RIN, NI, CAI, ESC_CR,
-		 CST, ESC_PROFILE, 0xff, ESC_MSGTYPE, SMSG};
-	/* 14 FTY repl by ESC_CHI */
-	/* 18 PI  repl by ESC_LAW */
-	/* removed OAD changed to 0xff for future use, OAD is multiIE now */
-	static const word multi_fac_id[] = {1, FTY};
-	static const word multi_pi_id[]  = {1, PI};
-	static const word multi_CiPN_id[]  = {1, OAD};
-	static const word multi_ssext_id[]  = {1, ESC_SSEXT};
-
-	static const word multi_vswitch_id[]  = {1, ESC_VSWITCH};
-
-	byte *cau;
-	word ncci;
-	byte SS_Ind[] = "\x05\x02\x00\x02\x00\x00"; /* Hold_Ind struct*/
-	byte CF_Ind[] = "\x09\x02\x00\x06\x00\x00\x00\x00\x00\x00";
-	byte Interr_Err_Ind[] = "\x0a\x02\x00\x07\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00";
-	byte CONF_Ind[] = "\x09\x16\x00\x06\x00\x00\x00\x00\x00\x00";
-	byte force_mt_info = false;
-	byte dir;
-	dword d;
-	word w;
-
-	a = plci->adapter;
-	Id = ((word)plci->Id << 8) | a->Id;
-	PUT_WORD(&SS_Ind[4], 0x0000);
-
-	if (plci->sig_remove_id)
-	{
-		plci->Sig.RNR = 2; /* discard */
-		dbug(1, dprintf("SIG discard while remove pending"));
-		return;
-	}
-	if (plci->tel && plci->SuppState != CALL_HELD) Id |= EXT_CONTROLLER;
-	dbug(1, dprintf("SigInd-Id=%08lx,plci=%x,tel=%x,state=0x%x,channels=%d,Discflowcl=%d",
-			Id, plci->Id, plci->tel, plci->State, plci->channels, plci->hangup_flow_ctrl_timer));
-	if (plci->Sig.Ind == CALL_HOLD_ACK && plci->channels)
-	{
-		plci->Sig.RNR = 1;
-		return;
-	}
-	if (plci->Sig.Ind == HANGUP && plci->channels)
-	{
-		plci->Sig.RNR = 1;
-		plci->hangup_flow_ctrl_timer++;
-		/* recover the network layer after timeout */
-		if (plci->hangup_flow_ctrl_timer == 100)
-		{
-			dbug(1, dprintf("Exceptional disc"));
-			plci->Sig.RNR = 0;
-			plci->hangup_flow_ctrl_timer = 0;
-			for (ncci = 1; ncci < MAX_NCCI + 1; ncci++)
-			{
-				if (a->ncci_plci[ncci] == plci->Id)
-				{
-					cleanup_ncci_data(plci, ncci);
-					if (plci->channels)plci->channels--;
-					if (plci->appl)
-						sendf(plci->appl, _DISCONNECT_B3_I, (((dword) ncci) << 16) | Id, 0, "ws", 0, "");
-				}
-			}
-			if (plci->appl)
-				sendf(plci->appl, _DISCONNECT_I, Id, 0, "w", 0);
-			plci_remove(plci);
-			plci->State = IDLE;
-		}
-		return;
-	}
-
-	/* do first parse the info with no OAD in, because OAD will be converted */
-	/* first the multiple facility IE, then mult. progress ind.              */
-	/* then the parameters for the info_ind + conn_ind                       */
-	IndParse(plci, multi_fac_id, multi_fac_parms, MAX_MULTI_IE);
-	IndParse(plci, multi_pi_id, multi_pi_parms, MAX_MULTI_IE);
-	IndParse(plci, multi_ssext_id, multi_ssext_parms, MAX_MULTI_IE);
-
-	IndParse(plci, multi_vswitch_id, multi_vswitch_parms, MAX_MULTI_IE);
-
-	IndParse(plci, parms_id, parms, 0);
-	IndParse(plci, multi_CiPN_id, multi_CiPN_parms, MAX_MULTI_IE);
-	esc_chi  = parms[14];
-	esc_law  = parms[18];
-	pty_cai  = parms[24];
-	esc_cr   = parms[25];
-	esc_profile = parms[27];
-	if (esc_cr[0] && plci)
-	{
-		if (plci->cr_enquiry && plci->appl)
-		{
-			plci->cr_enquiry = false;
-			/* d = MANU_ID            */
-			/* w = m_command          */
-			/* b = total length       */
-			/* b = indication type    */
-			/* b = length of all IEs  */
-			/* b = IE1                */
-			/* S = IE1 length + cont. */
-			/* b = IE2                */
-			/* S = IE2 length + cont. */
-			sendf(plci->appl,
-			      _MANUFACTURER_I,
-			      Id,
-			      0,
-			      "dwbbbbSbS", _DI_MANU_ID, plci->m_command,
-			      2 + 1 + 1 + esc_cr[0] + 1 + 1 + esc_law[0], plci->Sig.Ind, 1 + 1 + esc_cr[0] + 1 + 1 + esc_law[0], ESC, esc_cr, ESC, esc_law);
-		}
-	}
-	/* create the additional info structure                                  */
-	add_i[1] = parms[15]; /* KEY of additional info */
-	add_i[2] = parms[11]; /* UUI of additional info */
-	ai_len = AddInfo(add_i, multi_fac_parms, esc_chi, facility);
-
-	/* the ESC_LAW indicates if u-Law or a-Law is actually used by the card  */
-	/* indication returns by the card if requested by the function           */
-	/* AutomaticLaw() after driver init                                      */
-	if (a->automatic_law < 4)
-	{
-		if (esc_law[0]) {
-			if (esc_law[2]) {
-				dbug(0, dprintf("u-Law selected"));
-				a->u_law = 1;
-			}
-			else {
-				dbug(0, dprintf("a-Law selected"));
-				a->u_law = 0;
-			}
-			a->automatic_law = 4;
-			if (plci == a->automatic_lawPLCI) {
-				plci->internal_command = 0;
-				sig_req(plci, REMOVE, 0);
-				send_req(plci);
-				a->automatic_lawPLCI = NULL;
-			}
-		}
-		if (esc_profile[0])
-		{
-			dbug(1, dprintf("[%06x] CardProfile: %lx %lx %lx %lx %lx",
-					UnMapController(a->Id), GET_DWORD(&esc_profile[6]),
-					GET_DWORD(&esc_profile[10]), GET_DWORD(&esc_profile[14]),
-					GET_DWORD(&esc_profile[18]), GET_DWORD(&esc_profile[46])));
-
-			a->profile.Global_Options &= 0x000000ffL;
-			a->profile.B1_Protocols &= 0x000003ffL;
-			a->profile.B2_Protocols &= 0x00001fdfL;
-			a->profile.B3_Protocols &= 0x000000b7L;
-
-			a->profile.Global_Options &= GET_DWORD(&esc_profile[6]) |
-				GL_BCHANNEL_OPERATION_SUPPORTED;
-			a->profile.B1_Protocols &= GET_DWORD(&esc_profile[10]);
-			a->profile.B2_Protocols &= GET_DWORD(&esc_profile[14]);
-			a->profile.B3_Protocols &= GET_DWORD(&esc_profile[18]);
-			a->manufacturer_features = GET_DWORD(&esc_profile[46]);
-			a->man_profile.private_options = 0;
-
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_ECHO_CANCELLER)
-			{
-				a->man_profile.private_options |= 1L << PRIVATE_ECHO_CANCELLER;
-				a->profile.Global_Options |= GL_ECHO_CANCELLER_SUPPORTED;
-			}
-
-
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_RTP)
-				a->man_profile.private_options |= 1L << PRIVATE_RTP;
-			a->man_profile.rtp_primary_payloads = GET_DWORD(&esc_profile[50]);
-			a->man_profile.rtp_additional_payloads = GET_DWORD(&esc_profile[54]);
-
-
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_T38)
-				a->man_profile.private_options |= 1L << PRIVATE_T38;
-
-
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_FAX_SUB_SEP_PWD)
-				a->man_profile.private_options |= 1L << PRIVATE_FAX_SUB_SEP_PWD;
-
-
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_V18)
-				a->man_profile.private_options |= 1L << PRIVATE_V18;
-
-
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_DTMF_TONE)
-				a->man_profile.private_options |= 1L << PRIVATE_DTMF_TONE;
-
-
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_PIAFS)
-				a->man_profile.private_options |= 1L << PRIVATE_PIAFS;
-
-
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_FAX_PAPER_FORMATS)
-				a->man_profile.private_options |= 1L << PRIVATE_FAX_PAPER_FORMATS;
-
-
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_VOWN)
-				a->man_profile.private_options |= 1L << PRIVATE_VOWN;
-
-
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_FAX_NONSTANDARD)
-				a->man_profile.private_options |= 1L << PRIVATE_FAX_NONSTANDARD;
-
-		}
-		else
-		{
-			a->profile.Global_Options &= 0x0000007fL;
-			a->profile.B1_Protocols &= 0x000003dfL;
-			a->profile.B2_Protocols &= 0x00001adfL;
-			a->profile.B3_Protocols &= 0x000000b7L;
-			a->manufacturer_features &= MANUFACTURER_FEATURE_HARDDTMF;
-		}
-		if (a->manufacturer_features & (MANUFACTURER_FEATURE_HARDDTMF |
-						MANUFACTURER_FEATURE_SOFTDTMF_SEND | MANUFACTURER_FEATURE_SOFTDTMF_RECEIVE))
-		{
-			a->profile.Global_Options |= GL_DTMF_SUPPORTED;
-		}
-		a->manufacturer_features &= ~MANUFACTURER_FEATURE_OOB_CHANNEL;
-		dbug(1, dprintf("[%06x] Profile: %lx %lx %lx %lx %lx",
-				UnMapController(a->Id), a->profile.Global_Options,
-				a->profile.B1_Protocols, a->profile.B2_Protocols,
-				a->profile.B3_Protocols, a->manufacturer_features));
-	}
-	/* codec plci for the handset/hook state support is just an internal id  */
-	if (plci != a->AdvCodecPLCI)
-	{
-		force_mt_info = SendMultiIE(plci, Id, multi_fac_parms, FTY, 0x20, 0);
-		force_mt_info |= SendMultiIE(plci, Id, multi_pi_parms, PI, 0x210, 0);
-		SendSSExtInd(NULL, plci, Id, multi_ssext_parms);
-		SendInfo(plci, Id, parms, force_mt_info);
-
-		VSwitchReqInd(plci, Id, multi_vswitch_parms);
-
-	}
-
-	/* switch the codec to the b-channel                                     */
-	if (esc_chi[0] && plci && !plci->SuppState) {
-		plci->b_channel = esc_chi[esc_chi[0]]&0x1f;
-		mixer_set_bchannel_id_esc(plci, plci->b_channel);
-		dbug(1, dprintf("storeChannel=0x%x", plci->b_channel));
-		if (plci->tel == ADV_VOICE && plci->appl) {
-			SetVoiceChannel(a->AdvCodecPLCI, esc_chi, a);
-		}
-	}
-
-	if (plci->appl) plci->appl->Number++;
-
-	switch (plci->Sig.Ind) {
-		/* Response to Get_Supported_Services request */
-	case S_SUPPORTED:
-		dbug(1, dprintf("S_Supported"));
-		if (!plci->appl) break;
-		if (pty_cai[0] == 4)
-		{
-			PUT_DWORD(&CF_Ind[6], GET_DWORD(&pty_cai[1]));
-		}
-		else
-		{
-			PUT_DWORD(&CF_Ind[6], MASK_TERMINAL_PORTABILITY | MASK_HOLD_RETRIEVE);
-		}
-		PUT_WORD(&CF_Ind[1], 0);
-		PUT_WORD(&CF_Ind[4], 0);
-		sendf(plci->appl, _FACILITY_R | CONFIRM, Id & 0x7, plci->number, "wws", 0, 3, CF_Ind);
-		plci_remove(plci);
-		break;
-
-		/* Supplementary Service rejected */
-	case S_SERVICE_REJ:
-		dbug(1, dprintf("S_Reject=0x%x", pty_cai[5]));
-		if (!pty_cai[0]) break;
-		switch (pty_cai[5])
-		{
-		case ECT_EXECUTE:
-		case THREE_PTY_END:
-		case THREE_PTY_BEGIN:
-			if (!plci->relatedPTYPLCI) break;
-			tplci = plci->relatedPTYPLCI;
-			rId = ((word)tplci->Id << 8) | tplci->adapter->Id;
-			if (tplci->tel) rId |= EXT_CONTROLLER;
-			if (pty_cai[5] == ECT_EXECUTE)
-			{
-				PUT_WORD(&SS_Ind[1], S_ECT);
-
-				plci->vswitchstate = 0;
-				plci->relatedPTYPLCI->vswitchstate = 0;
-
-			}
-			else
-			{
-				PUT_WORD(&SS_Ind[1], pty_cai[5] + 3);
-			}
-			if (pty_cai[2] != 0xff)
-			{
-				PUT_WORD(&SS_Ind[4], 0x3600 | (word)pty_cai[2]);
-			}
-			else
-			{
-				PUT_WORD(&SS_Ind[4], 0x300E);
-			}
-			plci->relatedPTYPLCI = NULL;
-			plci->ptyState = 0;
-			sendf(tplci->appl, _FACILITY_I, rId, 0, "ws", 3, SS_Ind);
-			break;
-
-		case CALL_DEFLECTION:
-			if (pty_cai[2] != 0xff)
-			{
-				PUT_WORD(&SS_Ind[4], 0x3600 | (word)pty_cai[2]);
-			}
-			else
-			{
-				PUT_WORD(&SS_Ind[4], 0x300E);
-			}
-			PUT_WORD(&SS_Ind[1], pty_cai[5]);
-			for (i = 0; i < max_appl; i++)
-			{
-				if (application[i].CDEnable)
-				{
-					if (application[i].Id) sendf(&application[i], _FACILITY_I, Id, 0, "ws", 3, SS_Ind);
-					application[i].CDEnable = false;
-				}
-			}
-			break;
-
-		case DEACTIVATION_DIVERSION:
-		case ACTIVATION_DIVERSION:
-		case DIVERSION_INTERROGATE_CFU:
-		case DIVERSION_INTERROGATE_CFB:
-		case DIVERSION_INTERROGATE_CFNR:
-		case DIVERSION_INTERROGATE_NUM:
-		case CCBS_REQUEST:
-		case CCBS_DEACTIVATE:
-		case CCBS_INTERROGATE:
-			if (!plci->appl) break;
-			if (pty_cai[2] != 0xff)
-			{
-				PUT_WORD(&Interr_Err_Ind[4], 0x3600 | (word)pty_cai[2]);
-			}
-			else
-			{
-				PUT_WORD(&Interr_Err_Ind[4], 0x300E);
-			}
-			switch (pty_cai[5])
-			{
-			case DEACTIVATION_DIVERSION:
-				dbug(1, dprintf("Deact_Div"));
-				Interr_Err_Ind[0] = 0x9;
-				Interr_Err_Ind[3] = 0x6;
-				PUT_WORD(&Interr_Err_Ind[1], S_CALL_FORWARDING_STOP);
-				break;
-			case ACTIVATION_DIVERSION:
-				dbug(1, dprintf("Act_Div"));
-				Interr_Err_Ind[0] = 0x9;
-				Interr_Err_Ind[3] = 0x6;
-				PUT_WORD(&Interr_Err_Ind[1], S_CALL_FORWARDING_START);
-				break;
-			case DIVERSION_INTERROGATE_CFU:
-			case DIVERSION_INTERROGATE_CFB:
-			case DIVERSION_INTERROGATE_CFNR:
-				dbug(1, dprintf("Interr_Div"));
-				Interr_Err_Ind[0] = 0xa;
-				Interr_Err_Ind[3] = 0x7;
-				PUT_WORD(&Interr_Err_Ind[1], S_INTERROGATE_DIVERSION);
-				break;
-			case DIVERSION_INTERROGATE_NUM:
-				dbug(1, dprintf("Interr_Num"));
-				Interr_Err_Ind[0] = 0xa;
-				Interr_Err_Ind[3] = 0x7;
-				PUT_WORD(&Interr_Err_Ind[1], S_INTERROGATE_NUMBERS);
-				break;
-			case CCBS_REQUEST:
-				dbug(1, dprintf("CCBS Request"));
-				Interr_Err_Ind[0] = 0xd;
-				Interr_Err_Ind[3] = 0xa;
-				PUT_WORD(&Interr_Err_Ind[1], S_CCBS_REQUEST);
-				break;
-			case CCBS_DEACTIVATE:
-				dbug(1, dprintf("CCBS Deactivate"));
-				Interr_Err_Ind[0] = 0x9;
-				Interr_Err_Ind[3] = 0x6;
-				PUT_WORD(&Interr_Err_Ind[1], S_CCBS_DEACTIVATE);
-				break;
-			case CCBS_INTERROGATE:
-				dbug(1, dprintf("CCBS Interrogate"));
-				Interr_Err_Ind[0] = 0xb;
-				Interr_Err_Ind[3] = 0x8;
-				PUT_WORD(&Interr_Err_Ind[1], S_CCBS_INTERROGATE);
-				break;
-			}
-			PUT_DWORD(&Interr_Err_Ind[6], plci->appl->S_Handle);
-			sendf(plci->appl, _FACILITY_I, Id & 0x7, 0, "ws", 3, Interr_Err_Ind);
-			plci_remove(plci);
-			break;
-		case ACTIVATION_MWI:
-		case DEACTIVATION_MWI:
-			if (pty_cai[5] == ACTIVATION_MWI)
-			{
-				PUT_WORD(&SS_Ind[1], S_MWI_ACTIVATE);
-			}
-			else PUT_WORD(&SS_Ind[1], S_MWI_DEACTIVATE);
-
-			if (pty_cai[2] != 0xff)
-			{
-				PUT_WORD(&SS_Ind[4], 0x3600 | (word)pty_cai[2]);
-			}
-			else
-			{
-				PUT_WORD(&SS_Ind[4], 0x300E);
-			}
-
-			if (plci->cr_enquiry)
-			{
-				sendf(plci->appl, _FACILITY_I, Id & 0xf, 0, "ws", 3, SS_Ind);
-				plci_remove(plci);
-			}
-			else
-			{
-				sendf(plci->appl, _FACILITY_I, Id, 0, "ws", 3, SS_Ind);
-			}
-			break;
-		case CONF_ADD: /* ERROR */
-		case CONF_BEGIN:
-		case CONF_DROP:
-		case CONF_ISOLATE:
-		case CONF_REATTACH:
-			CONF_Ind[0] = 9;
-			CONF_Ind[3] = 6;
-			switch (pty_cai[5])
-			{
-			case CONF_BEGIN:
-				PUT_WORD(&CONF_Ind[1], S_CONF_BEGIN);
-				plci->ptyState = 0;
-				break;
-			case CONF_DROP:
-				CONF_Ind[0] = 5;
-				CONF_Ind[3] = 2;
-				PUT_WORD(&CONF_Ind[1], S_CONF_DROP);
-				plci->ptyState = CONNECTED;
-				break;
-			case CONF_ISOLATE:
-				CONF_Ind[0] = 5;
-				CONF_Ind[3] = 2;
-				PUT_WORD(&CONF_Ind[1], S_CONF_ISOLATE);
-				plci->ptyState = CONNECTED;
-				break;
-			case CONF_REATTACH:
-				CONF_Ind[0] = 5;
-				CONF_Ind[3] = 2;
-				PUT_WORD(&CONF_Ind[1], S_CONF_REATTACH);
-				plci->ptyState = CONNECTED;
-				break;
-			case CONF_ADD:
-				PUT_WORD(&CONF_Ind[1], S_CONF_ADD);
-				plci->relatedPTYPLCI = NULL;
-				tplci = plci->relatedPTYPLCI;
-				if (tplci) tplci->ptyState = CONNECTED;
-				plci->ptyState = CONNECTED;
-				break;
-			}
-
-			if (pty_cai[2] != 0xff)
-			{
-				PUT_WORD(&CONF_Ind[4], 0x3600 | (word)pty_cai[2]);
-			}
-			else
-			{
-				PUT_WORD(&CONF_Ind[4], 0x3303); /* Time-out: network did not respond
-								  within the required time */
-			}
-
-			PUT_DWORD(&CONF_Ind[6], 0x0);
-			sendf(plci->appl, _FACILITY_I, Id, 0, "ws", 3, CONF_Ind);
-			break;
-		}
-		break;
-
-		/* Supplementary Service indicates success */
-	case S_SERVICE:
-		dbug(1, dprintf("Service_Ind"));
-		PUT_WORD(&CF_Ind[4], 0);
-		switch (pty_cai[5])
-		{
-		case THREE_PTY_END:
-		case THREE_PTY_BEGIN:
-		case ECT_EXECUTE:
-			if (!plci->relatedPTYPLCI) break;
-			tplci = plci->relatedPTYPLCI;
-			rId = ((word)tplci->Id << 8) | tplci->adapter->Id;
-			if (tplci->tel) rId |= EXT_CONTROLLER;
-			if (pty_cai[5] == ECT_EXECUTE)
-			{
-				PUT_WORD(&SS_Ind[1], S_ECT);
-
-				if (plci->vswitchstate != 3)
-				{
-
-					plci->ptyState = IDLE;
-					plci->relatedPTYPLCI = NULL;
-					plci->ptyState = 0;
-
-				}
-
-				dbug(1, dprintf("ECT OK"));
-				sendf(tplci->appl, _FACILITY_I, rId, 0, "ws", 3, SS_Ind);
-
-
-
-			}
-			else
-			{
-				switch (plci->ptyState)
-				{
-				case S_3PTY_BEGIN:
-					plci->ptyState = CONNECTED;
-					dbug(1, dprintf("3PTY ON"));
-					break;
-
-				case S_3PTY_END:
-					plci->ptyState = IDLE;
-					plci->relatedPTYPLCI = NULL;
-					plci->ptyState = 0;
-					dbug(1, dprintf("3PTY OFF"));
-					break;
-				}
-				PUT_WORD(&SS_Ind[1], pty_cai[5] + 3);
-				sendf(tplci->appl, _FACILITY_I, rId, 0, "ws", 3, SS_Ind);
-			}
-			break;
-
-		case CALL_DEFLECTION:
-			PUT_WORD(&SS_Ind[1], pty_cai[5]);
-			for (i = 0; i < max_appl; i++)
-			{
-				if (application[i].CDEnable)
-				{
-					if (application[i].Id) sendf(&application[i], _FACILITY_I, Id, 0, "ws", 3, SS_Ind);
-					application[i].CDEnable = false;
-				}
-			}
-			break;
-
-		case DEACTIVATION_DIVERSION:
-		case ACTIVATION_DIVERSION:
-			if (!plci->appl) break;
-			PUT_WORD(&CF_Ind[1], pty_cai[5] + 2);
-			PUT_DWORD(&CF_Ind[6], plci->appl->S_Handle);
-			sendf(plci->appl, _FACILITY_I, Id & 0x7, 0, "ws", 3, CF_Ind);
-			plci_remove(plci);
-			break;
-
-		case DIVERSION_INTERROGATE_CFU:
-		case DIVERSION_INTERROGATE_CFB:
-		case DIVERSION_INTERROGATE_CFNR:
-		case DIVERSION_INTERROGATE_NUM:
-		case CCBS_REQUEST:
-		case CCBS_DEACTIVATE:
-		case CCBS_INTERROGATE:
-			if (!plci->appl) break;
-			switch (pty_cai[5])
-			{
-			case DIVERSION_INTERROGATE_CFU:
-			case DIVERSION_INTERROGATE_CFB:
-			case DIVERSION_INTERROGATE_CFNR:
-				dbug(1, dprintf("Interr_Div"));
-				PUT_WORD(&pty_cai[1], S_INTERROGATE_DIVERSION);
-				pty_cai[3] = pty_cai[0] - 3; /* Supplementary Service-specific parameter len */
-				break;
-			case DIVERSION_INTERROGATE_NUM:
-				dbug(1, dprintf("Interr_Num"));
-				PUT_WORD(&pty_cai[1], S_INTERROGATE_NUMBERS);
-				pty_cai[3] = pty_cai[0] - 3; /* Supplementary Service-specific parameter len */
-				break;
-			case CCBS_REQUEST:
-				dbug(1, dprintf("CCBS Request"));
-				PUT_WORD(&pty_cai[1], S_CCBS_REQUEST);
-				pty_cai[3] = pty_cai[0] - 3; /* Supplementary Service-specific parameter len */
-				break;
-			case CCBS_DEACTIVATE:
-				dbug(1, dprintf("CCBS Deactivate"));
-				PUT_WORD(&pty_cai[1], S_CCBS_DEACTIVATE);
-				pty_cai[3] = pty_cai[0] - 3; /* Supplementary Service-specific parameter len */
-				break;
-			case CCBS_INTERROGATE:
-				dbug(1, dprintf("CCBS Interrogate"));
-				PUT_WORD(&pty_cai[1], S_CCBS_INTERROGATE);
-				pty_cai[3] = pty_cai[0] - 3; /* Supplementary Service-specific parameter len */
-				break;
-			}
-			PUT_WORD(&pty_cai[4], 0); /* Supplementary Service Reason */
-			PUT_DWORD(&pty_cai[6], plci->appl->S_Handle);
-			sendf(plci->appl, _FACILITY_I, Id & 0x7, 0, "wS", 3, pty_cai);
-			plci_remove(plci);
-			break;
-
-		case ACTIVATION_MWI:
-		case DEACTIVATION_MWI:
-			if (pty_cai[5] == ACTIVATION_MWI)
-			{
-				PUT_WORD(&SS_Ind[1], S_MWI_ACTIVATE);
-			}
-			else PUT_WORD(&SS_Ind[1], S_MWI_DEACTIVATE);
-			if (plci->cr_enquiry)
-			{
-				sendf(plci->appl, _FACILITY_I, Id & 0xf, 0, "ws", 3, SS_Ind);
-				plci_remove(plci);
-			}
-			else
-			{
-				sendf(plci->appl, _FACILITY_I, Id, 0, "ws", 3, SS_Ind);
-			}
-			break;
-		case MWI_INDICATION:
-			if (pty_cai[0] >= 0x12)
-			{
-				PUT_WORD(&pty_cai[3], S_MWI_INDICATE);
-				pty_cai[2] = pty_cai[0] - 2; /* len Parameter */
-				pty_cai[5] = pty_cai[0] - 5; /* Supplementary Service-specific parameter len */
-				if (plci->appl && (a->Notification_Mask[plci->appl->Id - 1] & SMASK_MWI))
-				{
-					if (plci->internal_command == GET_MWI_STATE) /* result on Message Waiting Listen */
-					{
-						sendf(plci->appl, _FACILITY_I, Id & 0xf, 0, "wS", 3, &pty_cai[2]);
-						plci_remove(plci);
-						return;
-					}
-					else sendf(plci->appl, _FACILITY_I, Id, 0, "wS", 3, &pty_cai[2]);
-					pty_cai[0] = 0;
-				}
-				else
-				{
-					for (i = 0; i < max_appl; i++)
-					{
-						if (a->Notification_Mask[i]&SMASK_MWI)
-						{
-							sendf(&application[i], _FACILITY_I, Id & 0x7, 0, "wS", 3, &pty_cai[2]);
-							pty_cai[0] = 0;
-						}
-					}
-				}
-
-				if (!pty_cai[0])
-				{ /* acknowledge */
-					facility[2] = 0; /* returncode */
-				}
-				else facility[2] = 0xff;
-			}
-			else
-			{
-				/* reject */
-				facility[2] = 0xff; /* returncode */
-			}
-			facility[0] = 2;
-			facility[1] = MWI_RESPONSE; /* Function */
-			add_p(plci, CAI, facility);
-			add_p(plci, ESC, multi_ssext_parms[0]); /* remembered parameter -> only one possible */
-			sig_req(plci, S_SERVICE, 0);
-			send_req(plci);
-			plci->command = 0;
-			next_internal_command(Id, plci);
-			break;
-		case CONF_ADD: /* OK */
-		case CONF_BEGIN:
-		case CONF_DROP:
-		case CONF_ISOLATE:
-		case CONF_REATTACH:
-		case CONF_PARTYDISC:
-			CONF_Ind[0] = 9;
-			CONF_Ind[3] = 6;
-			switch (pty_cai[5])
-			{
-			case CONF_BEGIN:
-				PUT_WORD(&CONF_Ind[1], S_CONF_BEGIN);
-				if (pty_cai[0] == 6)
-				{
-					d = pty_cai[6];
-					PUT_DWORD(&CONF_Ind[6], d); /* PartyID */
-				}
-				else
-				{
-					PUT_DWORD(&CONF_Ind[6], 0x0);
-				}
-				break;
-			case CONF_ISOLATE:
-				PUT_WORD(&CONF_Ind[1], S_CONF_ISOLATE);
-				CONF_Ind[0] = 5;
-				CONF_Ind[3] = 2;
-				break;
-			case CONF_REATTACH:
-				PUT_WORD(&CONF_Ind[1], S_CONF_REATTACH);
-				CONF_Ind[0] = 5;
-				CONF_Ind[3] = 2;
-				break;
-			case CONF_DROP:
-				PUT_WORD(&CONF_Ind[1], S_CONF_DROP);
-				CONF_Ind[0] = 5;
-				CONF_Ind[3] = 2;
-				break;
-			case CONF_ADD:
-				PUT_WORD(&CONF_Ind[1], S_CONF_ADD);
-				d = pty_cai[6];
-				PUT_DWORD(&CONF_Ind[6], d); /* PartyID */
-				tplci = plci->relatedPTYPLCI;
-				if (tplci) tplci->ptyState = CONNECTED;
-				break;
-			case CONF_PARTYDISC:
-				CONF_Ind[0] = 7;
-				CONF_Ind[3] = 4;
-				PUT_WORD(&CONF_Ind[1], S_CONF_PARTYDISC);
-				d = pty_cai[6];
-				PUT_DWORD(&CONF_Ind[4], d); /* PartyID */
-				break;
-			}
-			plci->ptyState = CONNECTED;
-			sendf(plci->appl, _FACILITY_I, Id, 0, "ws", 3, CONF_Ind);
-			break;
-		case CCBS_INFO_RETAIN:
-		case CCBS_ERASECALLLINKAGEID:
-		case CCBS_STOP_ALERTING:
-			CONF_Ind[0] = 5;
-			CONF_Ind[3] = 2;
-			switch (pty_cai[5])
-			{
-			case CCBS_INFO_RETAIN:
-				PUT_WORD(&CONF_Ind[1], S_CCBS_INFO_RETAIN);
-				break;
-			case CCBS_STOP_ALERTING:
-				PUT_WORD(&CONF_Ind[1], S_CCBS_STOP_ALERTING);
-				break;
-			case CCBS_ERASECALLLINKAGEID:
-				PUT_WORD(&CONF_Ind[1], S_CCBS_ERASECALLLINKAGEID);
-				CONF_Ind[0] = 7;
-				CONF_Ind[3] = 4;
-				CONF_Ind[6] = 0;
-				CONF_Ind[7] = 0;
-				break;
-			}
-			w = pty_cai[6];
-			PUT_WORD(&CONF_Ind[4], w); /* PartyID */
-
-			if (plci->appl && (a->Notification_Mask[plci->appl->Id - 1] & SMASK_CCBS))
-			{
-				sendf(plci->appl, _FACILITY_I, Id, 0, "ws", 3, CONF_Ind);
-			}
-			else
-			{
-				for (i = 0; i < max_appl; i++)
-					if (a->Notification_Mask[i] & SMASK_CCBS)
-						sendf(&application[i], _FACILITY_I, Id & 0x7, 0, "ws", 3, CONF_Ind);
-			}
-			break;
-		}
-		break;
-	case CALL_HOLD_REJ:
-		cau = parms[7];
-		if (cau)
-		{
-			i = _L3_CAUSE | cau[2];
-			if (cau[2] == 0) i = 0x3603;
-		}
-		else
-		{
-			i = 0x3603;
-		}
-		PUT_WORD(&SS_Ind[1], S_HOLD);
-		PUT_WORD(&SS_Ind[4], i);
-		if (plci->SuppState == HOLD_REQUEST)
-		{
-			plci->SuppState = IDLE;
-			sendf(plci->appl, _FACILITY_I, Id, 0, "ws", 3, SS_Ind);
-		}
-		break;
-
-	case CALL_HOLD_ACK:
-		if (plci->SuppState == HOLD_REQUEST)
-		{
-			plci->SuppState = CALL_HELD;
-			CodecIdCheck(a, plci);
-			start_internal_command(Id, plci, hold_save_command);
-		}
-		break;
-
-	case CALL_RETRIEVE_REJ:
-		cau = parms[7];
-		if (cau)
-		{
-			i = _L3_CAUSE | cau[2];
-			if (cau[2] == 0) i = 0x3603;
-		}
-		else
-		{
-			i = 0x3603;
-		}
-		PUT_WORD(&SS_Ind[1], S_RETRIEVE);
-		PUT_WORD(&SS_Ind[4], i);
-		if (plci->SuppState == RETRIEVE_REQUEST)
-		{
-			plci->SuppState = CALL_HELD;
-			CodecIdCheck(a, plci);
-			sendf(plci->appl, _FACILITY_I, Id, 0, "ws", 3, SS_Ind);
-		}
-		break;
-
-	case CALL_RETRIEVE_ACK:
-		PUT_WORD(&SS_Ind[1], S_RETRIEVE);
-		if (plci->SuppState == RETRIEVE_REQUEST)
-		{
-			plci->SuppState = IDLE;
-			plci->call_dir |= CALL_DIR_FORCE_OUTG_NL;
-			plci->b_channel = esc_chi[esc_chi[0]]&0x1f;
-			if (plci->tel)
-			{
-				mixer_set_bchannel_id_esc(plci, plci->b_channel);
-				dbug(1, dprintf("RetrChannel=0x%x", plci->b_channel));
-				SetVoiceChannel(a->AdvCodecPLCI, esc_chi, a);
-				if (plci->B2_prot == B2_TRANSPARENT && plci->B3_prot == B3_TRANSPARENT)
-				{
-					dbug(1, dprintf("Get B-ch"));
-					start_internal_command(Id, plci, retrieve_restore_command);
-				}
-				else
-					sendf(plci->appl, _FACILITY_I, Id, 0, "ws", 3, SS_Ind);
-			}
-			else
-				start_internal_command(Id, plci, retrieve_restore_command);
-		}
-		break;
-
-	case INDICATE_IND:
-		if (plci->State != LISTENING) {
-			sig_req(plci, HANGUP, 0);
-			send_req(plci);
-			break;
-		}
-		cip = find_cip(a, parms[4], parms[6]);
-		cip_mask = 1L << cip;
-		dbug(1, dprintf("cip=%d,cip_mask=%lx", cip, cip_mask));
-		bitmap_zero(plci->c_ind_mask_table, MAX_APPL);
-		if (!remove_started && !a->adapter_disabled)
-		{
-			group_optimization(a, plci);
-			for_each_set_bit(i, plci->group_optimization_mask_table, max_appl) {
-				if (application[i].Id
-				    && (a->CIP_Mask[i] & 1 || a->CIP_Mask[i] & cip_mask)
-				    && CPN_filter_ok(parms[0], a, i)) {
-					dbug(1, dprintf("storedcip_mask[%d]=0x%lx", i, a->CIP_Mask[i]));
-					__set_bit(i, plci->c_ind_mask_table);
-					dbug(1, dprintf("c_ind_mask =%*pb", MAX_APPL, plci->c_ind_mask_table));
-					plci->State = INC_CON_PENDING;
-					plci->call_dir = (plci->call_dir & ~(CALL_DIR_OUT | CALL_DIR_ORIGINATE)) |
-						CALL_DIR_IN | CALL_DIR_ANSWER;
-					if (esc_chi[0]) {
-						plci->b_channel = esc_chi[esc_chi[0]] & 0x1f;
-						mixer_set_bchannel_id_esc(plci, plci->b_channel);
-					}
-					/* if a listen on the ext controller is done, check if hook states */
-					/* are supported or if just a on board codec must be activated     */
-					if (a->codec_listen[i] && !a->AdvSignalPLCI) {
-						if (a->profile.Global_Options & HANDSET)
-							plci->tel = ADV_VOICE;
-						else if (a->profile.Global_Options & ON_BOARD_CODEC)
-							plci->tel = CODEC;
-						if (plci->tel) Id |= EXT_CONTROLLER;
-						a->codec_listen[i] = plci;
-					}
-
-					sendf(&application[i], _CONNECT_I, Id, 0,
-					      "wSSSSSSSbSSSSS", cip,    /* CIP                 */
-					      parms[0],    /* CalledPartyNumber   */
-					      multi_CiPN_parms[0],    /* CallingPartyNumber  */
-					      parms[2],    /* CalledPartySubad    */
-					      parms[3],    /* CallingPartySubad   */
-					      parms[4],    /* BearerCapability    */
-					      parms[5],    /* LowLC               */
-					      parms[6],    /* HighLC              */
-					      ai_len,      /* nested struct add_i */
-					      add_i[0],    /* B channel info    */
-					      add_i[1],    /* keypad facility   */
-					      add_i[2],    /* user user data    */
-					      add_i[3],    /* nested facility   */
-					      multi_CiPN_parms[1]    /* second CiPN(SCR)   */
-						);
-					SendSSExtInd(&application[i],
-						     plci,
-						     Id,
-						     multi_ssext_parms);
-					SendSetupInfo(&application[i],
-						      plci,
-						      Id,
-						      parms,
-						      SendMultiIE(plci, Id, multi_pi_parms, PI, 0x210, true));
-				}
-			}
-			dbug(1, dprintf("c_ind_mask =%*pb", MAX_APPL, plci->c_ind_mask_table));
-		}
-		if (bitmap_empty(plci->c_ind_mask_table, MAX_APPL)) {
-			sig_req(plci, HANGUP, 0);
-			send_req(plci);
-			plci->State = IDLE;
-		}
-		plci->notifiedcall = 0;
-		a->listen_active--;
-		listen_check(a);
-		break;
-
-	case CALL_PEND_NOTIFY:
-		plci->notifiedcall = 1;
-		listen_check(a);
-		break;
-
-	case CALL_IND:
-	case CALL_CON:
-		if (plci->State == ADVANCED_VOICE_SIG || plci->State == ADVANCED_VOICE_NOSIG)
-		{
-			if (plci->internal_command == PERM_COD_CONN_PEND)
-			{
-				if (plci->State == ADVANCED_VOICE_NOSIG)
-				{
-					dbug(1, dprintf("***Codec OK"));
-					if (a->AdvSignalPLCI)
-					{
-						tplci = a->AdvSignalPLCI;
-						if (tplci->spoofed_msg)
-						{
-							dbug(1, dprintf("***Spoofed Msg(0x%x)", tplci->spoofed_msg));
-							tplci->command = 0;
-							tplci->internal_command = 0;
-							x_Id = ((word)tplci->Id << 8) | tplci->adapter->Id | 0x80;
-							switch (tplci->spoofed_msg)
-							{
-							case CALL_RES:
-								tplci->command = _CONNECT_I | RESPONSE;
-								api_load_msg(&tplci->saved_msg, saved_parms);
-								add_b1(tplci, &saved_parms[1], 0, tplci->B1_facilities);
-								if (tplci->adapter->Info_Mask[tplci->appl->Id - 1] & 0x200)
-								{
-									/* early B3 connect (CIP mask bit 9) no release after a disc */
-									add_p(tplci, LLI, "\x01\x01");
-								}
-								add_s(tplci, CONN_NR, &saved_parms[2]);
-								add_s(tplci, LLC, &saved_parms[4]);
-								add_ai(tplci, &saved_parms[5]);
-								tplci->State = INC_CON_ACCEPT;
-								sig_req(tplci, CALL_RES, 0);
-								send_req(tplci);
-								break;
-
-							case AWAITING_SELECT_B:
-								dbug(1, dprintf("Select_B continue"));
-								start_internal_command(x_Id, tplci, select_b_command);
-								break;
-
-							case AWAITING_MANUF_CON: /* Get_Plci per Manufacturer_Req to ext controller */
-								if (!tplci->Sig.Id)
-								{
-									dbug(1, dprintf("No SigID!"));
-									sendf(tplci->appl, _MANUFACTURER_R | CONFIRM, x_Id, tplci->number, "dww", _DI_MANU_ID, _MANUFACTURER_R, _OUT_OF_PLCI);
-									plci_remove(tplci);
-									break;
-								}
-								tplci->command = _MANUFACTURER_R;
-								api_load_msg(&tplci->saved_msg, saved_parms);
-								dir = saved_parms[2].info[0];
-								if (dir == 1) {
-									sig_req(tplci, CALL_REQ, 0);
-								}
-								else if (!dir) {
-									sig_req(tplci, LISTEN_REQ, 0);
-								}
-								send_req(tplci);
-								sendf(tplci->appl, _MANUFACTURER_R | CONFIRM, x_Id, tplci->number, "dww", _DI_MANU_ID, _MANUFACTURER_R, 0);
-								break;
-
-							case (CALL_REQ | AWAITING_MANUF_CON):
-								sig_req(tplci, CALL_REQ, 0);
-								send_req(tplci);
-								break;
-
-							case CALL_REQ:
-								if (!tplci->Sig.Id)
-								{
-									dbug(1, dprintf("No SigID!"));
-									sendf(tplci->appl, _CONNECT_R | CONFIRM, tplci->adapter->Id, 0, "w", _OUT_OF_PLCI);
-									plci_remove(tplci);
-									break;
-								}
-								tplci->command = _CONNECT_R;
-								api_load_msg(&tplci->saved_msg, saved_parms);
-								add_s(tplci, CPN, &saved_parms[1]);
-								add_s(tplci, DSA, &saved_parms[3]);
-								add_ai(tplci, &saved_parms[9]);
-								sig_req(tplci, CALL_REQ, 0);
-								send_req(tplci);
-								break;
-
-							case CALL_RETRIEVE:
-								tplci->command = C_RETRIEVE_REQ;
-								sig_req(tplci, CALL_RETRIEVE, 0);
-								send_req(tplci);
-								break;
-							}
-							tplci->spoofed_msg = 0;
-							if (tplci->internal_command == 0)
-								next_internal_command(x_Id, tplci);
-						}
-					}
-					next_internal_command(Id, plci);
-					break;
-				}
-				dbug(1, dprintf("***Codec Hook Init Req"));
-				plci->internal_command = PERM_COD_HOOK;
-				add_p(plci, FTY, "\x01\x09");             /* Get Hook State*/
-				sig_req(plci, TEL_CTRL, 0);
-				send_req(plci);
-			}
-		}
-		else if (plci->command != _MANUFACTURER_R  /* old style permanent connect */
-			 && plci->State != INC_ACT_PENDING)
-		{
-			mixer_set_bchannel_id_esc(plci, plci->b_channel);
-			if (plci->tel == ADV_VOICE && plci->SuppState == IDLE) /* with permanent codec switch on immediately */
-			{
-				chi[2] = plci->b_channel;
-				SetVoiceChannel(a->AdvCodecPLCI, chi, a);
-			}
-			sendf(plci->appl, _CONNECT_ACTIVE_I, Id, 0, "Sss", parms[21], "", "");
-			plci->State = INC_ACT_PENDING;
-		}
-		break;
-
-	case TEL_CTRL:
-		ie = multi_fac_parms[0]; /* inspect the facility hook indications */
-		if (plci->State == ADVANCED_VOICE_SIG && ie[0]) {
-			switch (ie[1] & 0x91) {
-			case 0x80:   /* hook off */
-			case 0x81:
-				if (plci->internal_command == PERM_COD_HOOK)
-				{
-					dbug(1, dprintf("init:hook_off"));
-					plci->hook_state = ie[1];
-					next_internal_command(Id, plci);
-					break;
-				}
-				else /* ignore doubled hook indications */
-				{
-					if (((plci->hook_state) & 0xf0) == 0x80)
-					{
-						dbug(1, dprintf("ignore hook"));
-						break;
-					}
-					plci->hook_state = ie[1]&0x91;
-				}
-				/* check for incoming call pending */
-				/* and signal '+'.Appl must decide */
-				/* with connect_res if call must   */
-				/* accepted or not                 */
-				for (i = 0, tplci = NULL; i < max_appl; i++) {
-					if (a->codec_listen[i]
-					    && (a->codec_listen[i]->State == INC_CON_PENDING
-						|| a->codec_listen[i]->State == INC_CON_ALERT)) {
-						tplci = a->codec_listen[i];
-						tplci->appl = &application[i];
-					}
-				}
-				/* no incoming call, do outgoing call */
-				/* and signal '+' if outg. setup   */
-				if (!a->AdvSignalPLCI && !tplci) {
-					if ((i = get_plci(a))) {
-						a->AdvSignalPLCI = &a->plci[i - 1];
-						tplci = a->AdvSignalPLCI;
-						tplci->tel  = ADV_VOICE;
-						PUT_WORD(&voice_cai[5], a->AdvSignalAppl->MaxDataLength);
-						if (a->Info_Mask[a->AdvSignalAppl->Id - 1] & 0x200) {
-							/* early B3 connect (CIP mask bit 9) no release after a disc */
-							add_p(tplci, LLI, "\x01\x01");
-						}
-						add_p(tplci, CAI, voice_cai);
-						add_p(tplci, OAD, a->TelOAD);
-						add_p(tplci, OSA, a->TelOSA);
-						add_p(tplci, SHIFT | 6, NULL);
-						add_p(tplci, SIN, "\x02\x01\x00");
-						add_p(tplci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-						sig_req(tplci, ASSIGN, DSIG_ID);
-						a->AdvSignalPLCI->internal_command = HOOK_OFF_REQ;
-						a->AdvSignalPLCI->command = 0;
-						tplci->appl = a->AdvSignalAppl;
-						tplci->call_dir = CALL_DIR_OUT | CALL_DIR_ORIGINATE;
-						send_req(tplci);
-					}
-
-				}
-
-				if (!tplci) break;
-				Id = ((word)tplci->Id << 8) | a->Id;
-				Id |= EXT_CONTROLLER;
-				sendf(tplci->appl,
-				      _FACILITY_I,
-				      Id,
-				      0,
-				      "ws", (word)0, "\x01+");
-				break;
-
-			case 0x90:   /* hook on  */
-			case 0x91:
-				if (plci->internal_command == PERM_COD_HOOK)
-				{
-					dbug(1, dprintf("init:hook_on"));
-					plci->hook_state = ie[1] & 0x91;
-					next_internal_command(Id, plci);
-					break;
-				}
-				else /* ignore doubled hook indications */
-				{
-					if (((plci->hook_state) & 0xf0) == 0x90) break;
-					plci->hook_state = ie[1] & 0x91;
-				}
-				/* hangup the adv. voice call and signal '-' to the appl */
-				if (a->AdvSignalPLCI) {
-					Id = ((word)a->AdvSignalPLCI->Id << 8) | a->Id;
-					if (plci->tel) Id |= EXT_CONTROLLER;
-					sendf(a->AdvSignalAppl,
-					      _FACILITY_I,
-					      Id,
-					      0,
-					      "ws", (word)0, "\x01-");
-					a->AdvSignalPLCI->internal_command = HOOK_ON_REQ;
-					a->AdvSignalPLCI->command = 0;
-					sig_req(a->AdvSignalPLCI, HANGUP, 0);
-					send_req(a->AdvSignalPLCI);
-				}
-				break;
-			}
-		}
-		break;
-
-	case RESUME:
-		__clear_bit(plci->appl->Id - 1, plci->c_ind_mask_table);
-		PUT_WORD(&resume_cau[4], GOOD);
-		sendf(plci->appl, _FACILITY_I, Id, 0, "ws", (word)3, resume_cau);
-		break;
-
-	case SUSPEND:
-		bitmap_zero(plci->c_ind_mask_table, MAX_APPL);
-
-		if (plci->NL.Id && !plci->nl_remove_id) {
-			mixer_remove(plci);
-			nl_req_ncci(plci, REMOVE, 0);
-		}
-		if (!plci->sig_remove_id) {
-			plci->internal_command = 0;
-			sig_req(plci, REMOVE, 0);
-		}
-		send_req(plci);
-		if (!plci->channels) {
-			sendf(plci->appl, _FACILITY_I, Id, 0, "ws", (word)3, "\x05\x04\x00\x02\x00\x00");
-			sendf(plci->appl, _DISCONNECT_I, Id, 0, "w", 0);
-		}
-		break;
-
-	case SUSPEND_REJ:
-		break;
-
-	case HANGUP:
-		plci->hangup_flow_ctrl_timer = 0;
-		if (plci->manufacturer && plci->State == LOCAL_CONNECT) break;
-		cau = parms[7];
-		if (cau) {
-			i = _L3_CAUSE | cau[2];
-			if (cau[2] == 0) i = 0;
-			else if (cau[2] == 8) i = _L1_ERROR;
-			else if (cau[2] == 9 || cau[2] == 10) i = _L2_ERROR;
-			else if (cau[2] == 5) i = _CAPI_GUARD_ERROR;
-		}
-		else {
-			i = _L3_ERROR;
-		}
-
-		if (plci->State == INC_CON_PENDING || plci->State == INC_CON_ALERT)
-		{
-			for_each_set_bit(i, plci->c_ind_mask_table, max_appl)
-				sendf(&application[i], _DISCONNECT_I, Id, 0, "w", 0);
-		}
-		else
-		{
-			bitmap_zero(plci->c_ind_mask_table, MAX_APPL);
-		}
-		if (!plci->appl)
-		{
-			if (plci->State == LISTENING)
-			{
-				plci->notifiedcall = 0;
-				a->listen_active--;
-			}
-			plci->State = INC_DIS_PENDING;
-			if (bitmap_empty(plci->c_ind_mask_table, MAX_APPL))
-			{
-				plci->State = IDLE;
-				if (plci->NL.Id && !plci->nl_remove_id)
-				{
-					mixer_remove(plci);
-					nl_req_ncci(plci, REMOVE, 0);
-				}
-				if (!plci->sig_remove_id)
-				{
-					plci->internal_command = 0;
-					sig_req(plci, REMOVE, 0);
-				}
-				send_req(plci);
-			}
-		}
-		else
-		{
-			/* collision of DISCONNECT or CONNECT_RES with HANGUP can   */
-			/* result in a second HANGUP! Don't generate another        */
-			/* DISCONNECT                                               */
-			if (plci->State != IDLE && plci->State != INC_DIS_PENDING)
-			{
-				if (plci->State == RESUMING)
-				{
-					PUT_WORD(&resume_cau[4], i);
-					sendf(plci->appl, _FACILITY_I, Id, 0, "ws", (word)3, resume_cau);
-				}
-				plci->State = INC_DIS_PENDING;
-				sendf(plci->appl, _DISCONNECT_I, Id, 0, "w", i);
-			}
-		}
-		break;
-
-	case SSEXT_IND:
-		SendSSExtInd(NULL, plci, Id, multi_ssext_parms);
-		break;
-
-	case VSWITCH_REQ:
-		VSwitchReqInd(plci, Id, multi_vswitch_parms);
-		break;
-	case VSWITCH_IND:
-		if (plci->relatedPTYPLCI &&
-		    plci->vswitchstate == 3 &&
-		    plci->relatedPTYPLCI->vswitchstate == 3 &&
-		    parms[MAXPARMSIDS - 1][0])
-		{
-			add_p(plci->relatedPTYPLCI, SMSG, parms[MAXPARMSIDS - 1]);
-			sig_req(plci->relatedPTYPLCI, VSWITCH_REQ, 0);
-			send_req(plci->relatedPTYPLCI);
-		}
-		else VSwitchReqInd(plci, Id, multi_vswitch_parms);
-		break;
-
-	}
-}
-
-
-static void SendSetupInfo(APPL *appl, PLCI *plci, dword Id, byte **parms, byte Info_Sent_Flag)
-{
-	word i;
-	byte *ie;
-	word Info_Number;
-	byte *Info_Element;
-	word Info_Mask = 0;
-
-	dbug(1, dprintf("SetupInfo"));
-
-	for (i = 0; i < MAXPARMSIDS; i++) {
-		ie = parms[i];
-		Info_Number = 0;
-		Info_Element = ie;
-		if (ie[0]) {
-			switch (i) {
-			case 0:
-				dbug(1, dprintf("CPN "));
-				Info_Number = 0x0070;
-				Info_Mask = 0x80;
-				Info_Sent_Flag = true;
-				break;
-			case 8:  /* display      */
-				dbug(1, dprintf("display(%d)", i));
-				Info_Number = 0x0028;
-				Info_Mask = 0x04;
-				Info_Sent_Flag = true;
-				break;
-			case 16: /* Channel Id */
-				dbug(1, dprintf("CHI"));
-				Info_Number = 0x0018;
-				Info_Mask = 0x100;
-				Info_Sent_Flag = true;
-				mixer_set_bchannel_id(plci, Info_Element);
-				break;
-			case 19: /* Redirected Number */
-				dbug(1, dprintf("RDN"));
-				Info_Number = 0x0074;
-				Info_Mask = 0x400;
-				Info_Sent_Flag = true;
-				break;
-			case 20: /* Redirected Number extended */
-				dbug(1, dprintf("RDX"));
-				Info_Number = 0x0073;
-				Info_Mask = 0x400;
-				Info_Sent_Flag = true;
-				break;
-			case 22: /* Redirecing Number  */
-				dbug(1, dprintf("RIN"));
-				Info_Number = 0x0076;
-				Info_Mask = 0x400;
-				Info_Sent_Flag = true;
-				break;
-			default:
-				Info_Number = 0;
-				break;
-			}
-		}
-
-		if (i == MAXPARMSIDS - 2) { /* to indicate the message type "Setup" */
-			Info_Number = 0x8000 | 5;
-			Info_Mask = 0x10;
-			Info_Element = "";
-		}
-
-		if (Info_Sent_Flag && Info_Number) {
-			if (plci->adapter->Info_Mask[appl->Id - 1] & Info_Mask) {
-				sendf(appl, _INFO_I, Id, 0, "wS", Info_Number, Info_Element);
-			}
-		}
-	}
-}
-
-
-static void SendInfo(PLCI *plci, dword Id, byte **parms, byte iesent)
-{
-	word i;
-	word j;
-	word k;
-	byte *ie;
-	word Info_Number;
-	byte *Info_Element;
-	word Info_Mask = 0;
-	static byte charges[5] = {4, 0, 0, 0, 0};
-	static byte cause[] = {0x02, 0x80, 0x00};
-	APPL *appl;
-
-	dbug(1, dprintf("InfoParse "));
-
-	if (
-		!plci->appl
-		&& !plci->State
-		&& plci->Sig.Ind != NCR_FACILITY
-		)
-	{
-		dbug(1, dprintf("NoParse "));
-		return;
-	}
-	cause[2] = 0;
-	for (i = 0; i < MAXPARMSIDS; i++) {
-		ie = parms[i];
-		Info_Number = 0;
-		Info_Element = ie;
-		if (ie[0]) {
-			switch (i) {
-			case 0:
-				dbug(1, dprintf("CPN "));
-				Info_Number = 0x0070;
-				Info_Mask   = 0x80;
-				break;
-			case 7: /* ESC_CAU */
-				dbug(1, dprintf("cau(0x%x)", ie[2]));
-				Info_Number = 0x0008;
-				Info_Mask = 0x00;
-				cause[2] = ie[2];
-				Info_Element = NULL;
-				break;
-			case 8:  /* display      */
-				dbug(1, dprintf("display(%d)", i));
-				Info_Number = 0x0028;
-				Info_Mask = 0x04;
-				break;
-			case 9:  /* Date display */
-				dbug(1, dprintf("date(%d)", i));
-				Info_Number = 0x0029;
-				Info_Mask = 0x02;
-				break;
-			case 10: /* charges */
-				for (j = 0; j < 4; j++) charges[1 + j] = 0;
-				for (j = 0; j < ie[0] && !(ie[1 + j] & 0x80); j++);
-				for (k = 1, j++; j < ie[0] && k <= 4; j++, k++) charges[k] = ie[1 + j];
-				Info_Number = 0x4000;
-				Info_Mask = 0x40;
-				Info_Element = charges;
-				break;
-			case 11: /* user user info */
-				dbug(1, dprintf("uui"));
-				Info_Number = 0x007E;
-				Info_Mask = 0x08;
-				break;
-			case 12: /* congestion receiver ready */
-				dbug(1, dprintf("clRDY"));
-				Info_Number = 0x00B0;
-				Info_Mask = 0x08;
-				Info_Element = "";
-				break;
-			case 13: /* congestion receiver not ready */
-				dbug(1, dprintf("clNRDY"));
-				Info_Number = 0x00BF;
-				Info_Mask = 0x08;
-				Info_Element = "";
-				break;
-			case 15: /* Keypad Facility */
-				dbug(1, dprintf("KEY"));
-				Info_Number = 0x002C;
-				Info_Mask = 0x20;
-				break;
-			case 16: /* Channel Id */
-				dbug(1, dprintf("CHI"));
-				Info_Number = 0x0018;
-				Info_Mask = 0x100;
-				mixer_set_bchannel_id(plci, Info_Element);
-				break;
-			case 17: /* if no 1tr6 cause, send full cause, else esc_cause */
-				dbug(1, dprintf("q9cau(0x%x)", ie[2]));
-				if (!cause[2] || cause[2] < 0x80) break;  /* eg. layer 1 error */
-				Info_Number = 0x0008;
-				Info_Mask = 0x01;
-				if (cause[2] != ie[2]) Info_Element = cause;
-				break;
-			case 19: /* Redirected Number */
-				dbug(1, dprintf("RDN"));
-				Info_Number = 0x0074;
-				Info_Mask = 0x400;
-				break;
-			case 22: /* Redirecing Number  */
-				dbug(1, dprintf("RIN"));
-				Info_Number = 0x0076;
-				Info_Mask = 0x400;
-				break;
-			case 23: /* Notification Indicator  */
-				dbug(1, dprintf("NI"));
-				Info_Number = (word)NI;
-				Info_Mask = 0x210;
-				break;
-			case 26: /* Call State  */
-				dbug(1, dprintf("CST"));
-				Info_Number = (word)CST;
-				Info_Mask = 0x01; /* do with cause i.e. for now */
-				break;
-			case MAXPARMSIDS - 2:  /* Escape Message Type, must be the last indication */
-				dbug(1, dprintf("ESC/MT[0x%x]", ie[3]));
-				Info_Number = 0x8000 | ie[3];
-				if (iesent) Info_Mask = 0xffff;
-				else  Info_Mask = 0x10;
-				Info_Element = "";
-				break;
-			default:
-				Info_Number  = 0;
-				Info_Mask    = 0;
-				Info_Element = "";
-				break;
-			}
-		}
-
-		if (plci->Sig.Ind == NCR_FACILITY)           /* check controller broadcast */
-		{
-			for (j = 0; j < max_appl; j++)
-			{
-				appl = &application[j];
-				if (Info_Number
-				    && appl->Id
-				    && plci->adapter->Info_Mask[appl->Id - 1] & Info_Mask)
-				{
-					dbug(1, dprintf("NCR_Ind"));
-					iesent = true;
-					sendf(&application[j], _INFO_I, Id & 0x0f, 0, "wS", Info_Number, Info_Element);
-				}
-			}
-		}
-		else if (!plci->appl)
-		{ /* overlap receiving broadcast */
-			if (Info_Number == CPN
-			    || Info_Number == KEY
-			    || Info_Number == NI
-			    || Info_Number == DSP
-			    || Info_Number == UUI)
-			{
-				for_each_set_bit(j, plci->c_ind_mask_table, max_appl) {
-					dbug(1, dprintf("Ovl_Ind"));
-					iesent = true;
-					sendf(&application[j], _INFO_I, Id, 0, "wS", Info_Number, Info_Element);
-				}
-			}
-		}               /* all other signalling states */
-		else if (Info_Number
-			 && plci->adapter->Info_Mask[plci->appl->Id - 1] & Info_Mask)
-		{
-			dbug(1, dprintf("Std_Ind"));
-			iesent = true;
-			sendf(plci->appl, _INFO_I, Id, 0, "wS", Info_Number, Info_Element);
-		}
-	}
-}
-
-
-static byte SendMultiIE(PLCI *plci, dword Id, byte **parms, byte ie_type,
-			dword info_mask, byte setupParse)
-{
-	word i;
-	word j;
-	byte *ie;
-	word Info_Number;
-	byte *Info_Element;
-	APPL *appl;
-	word Info_Mask = 0;
-	byte iesent = 0;
-
-	if (
-		!plci->appl
-		&& !plci->State
-		&& plci->Sig.Ind != NCR_FACILITY
-		&& !setupParse
-		)
-	{
-		dbug(1, dprintf("NoM-IEParse "));
-		return 0;
-	}
-	dbug(1, dprintf("M-IEParse "));
-
-	for (i = 0; i < MAX_MULTI_IE; i++)
-	{
-		ie = parms[i];
-		Info_Number = 0;
-		Info_Element = ie;
-		if (ie[0])
-		{
-			dbug(1, dprintf("[Ind0x%x]:IE=0x%x", plci->Sig.Ind, ie_type));
-			Info_Number = (word)ie_type;
-			Info_Mask = (word)info_mask;
-		}
-
-		if (plci->Sig.Ind == NCR_FACILITY)           /* check controller broadcast */
-		{
-			for (j = 0; j < max_appl; j++)
-			{
-				appl = &application[j];
-				if (Info_Number
-				    && appl->Id
-				    && plci->adapter->Info_Mask[appl->Id - 1] & Info_Mask)
-				{
-					iesent = true;
-					dbug(1, dprintf("Mlt_NCR_Ind"));
-					sendf(&application[j], _INFO_I, Id & 0x0f, 0, "wS", Info_Number, Info_Element);
-				}
-			}
-		}
-		else if (!plci->appl && Info_Number)
-		{                                        /* overlap receiving broadcast */
-			for_each_set_bit(j, plci->c_ind_mask_table, max_appl) {
-				iesent = true;
-				dbug(1, dprintf("Mlt_Ovl_Ind"));
-				sendf(&application[j] , _INFO_I, Id, 0, "wS", Info_Number, Info_Element);
-			}
-		}                                        /* all other signalling states */
-		else if (Info_Number
-			 && plci->adapter->Info_Mask[plci->appl->Id - 1] & Info_Mask)
-		{
-			iesent = true;
-			dbug(1, dprintf("Mlt_Std_Ind"));
-			sendf(plci->appl, _INFO_I, Id, 0, "wS", Info_Number, Info_Element);
-		}
-	}
-	return iesent;
-}
-
-static void SendSSExtInd(APPL *appl, PLCI *plci, dword Id, byte **parms)
-{
-	word i;
-	/* Format of multi_ssext_parms[i][]:
-	   0 byte length
-	   1 byte SSEXTIE
-	   2 byte SSEXT_REQ/SSEXT_IND
-	   3 byte length
-	   4 word SSExtCommand
-	   6... Params
-	*/
-	if (
-		plci
-		&& plci->State
-		&& plci->Sig.Ind != NCR_FACILITY
-		)
-		for (i = 0; i < MAX_MULTI_IE; i++)
-		{
-			if (parms[i][0] < 6) continue;
-			if (parms[i][2] == SSEXT_REQ) continue;
-
-			if (appl)
-			{
-				parms[i][0] = 0; /* kill it */
-				sendf(appl, _MANUFACTURER_I,
-				      Id,
-				      0,
-				      "dwS",
-				      _DI_MANU_ID,
-				      _DI_SSEXT_CTRL,
-				      &parms[i][3]);
-			}
-			else if (plci->appl)
-			{
-				parms[i][0] = 0; /* kill it */
-				sendf(plci->appl, _MANUFACTURER_I,
-				      Id,
-				      0,
-				      "dwS",
-				      _DI_MANU_ID,
-				      _DI_SSEXT_CTRL,
-				      &parms[i][3]);
-			}
-		}
-};
-
-static void nl_ind(PLCI *plci)
-{
-	byte ch;
-	word ncci;
-	dword Id;
-	DIVA_CAPI_ADAPTER *a;
-	word NCCIcode;
-	APPL *APPLptr;
-	word count;
-	word Num;
-	word i, ncpi_state;
-	byte len, ncci_state;
-	word msg;
-	word info = 0;
-	word fax_feature_bits;
-	byte fax_send_edata_ack;
-	static byte v120_header_buffer[2 + 3];
-	static word fax_info[] = {
-		0,                     /* T30_SUCCESS                        */
-		_FAX_NO_CONNECTION,    /* T30_ERR_NO_DIS_RECEIVED            */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_TIMEOUT_NO_RESPONSE        */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_RESPONSE          */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_TOO_MANY_REPEATS           */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_UNEXPECTED_MESSAGE         */
-		_FAX_REMOTE_ABORT,     /* T30_ERR_UNEXPECTED_DCN             */
-		_FAX_LOCAL_ABORT,      /* T30_ERR_DTC_UNSUPPORTED            */
-		_FAX_TRAINING_ERROR,   /* T30_ERR_ALL_RATES_FAILED           */
-		_FAX_TRAINING_ERROR,   /* T30_ERR_TOO_MANY_TRAINS            */
-		_FAX_PARAMETER_ERROR,  /* T30_ERR_RECEIVE_CORRUPTED          */
-		_FAX_REMOTE_ABORT,     /* T30_ERR_UNEXPECTED_DISC            */
-		_FAX_LOCAL_ABORT,      /* T30_ERR_APPLICATION_DISC           */
-		_FAX_REMOTE_REJECT,    /* T30_ERR_INCOMPATIBLE_DIS           */
-		_FAX_LOCAL_ABORT,      /* T30_ERR_INCOMPATIBLE_DCS           */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_TIMEOUT_NO_COMMAND         */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_COMMAND           */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_TIMEOUT_COMMAND_TOO_LONG   */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_TIMEOUT_RESPONSE_TOO_LONG  */
-		_FAX_NO_CONNECTION,    /* T30_ERR_NOT_IDENTIFIED             */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_SUPERVISORY_TIMEOUT        */
-		_FAX_PARAMETER_ERROR,  /* T30_ERR_TOO_LONG_SCAN_LINE         */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_PAGE_AFTER_MPS    */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_PAGE_AFTER_CFR    */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_DCS_AFTER_FTT     */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_DCS_AFTER_EOM     */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_DCS_AFTER_MPS     */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_DCN_AFTER_MCF     */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_DCN_AFTER_RTN     */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_CFR               */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_MCF_AFTER_EOP     */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_MCF_AFTER_EOM     */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_RETRY_NO_MCF_AFTER_MPS     */
-		0x331d,                /* T30_ERR_SUB_SEP_UNSUPPORTED        */
-		0x331e,                /* T30_ERR_PWD_UNSUPPORTED            */
-		0x331f,                /* T30_ERR_SUB_SEP_PWD_UNSUPPORTED    */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_INVALID_COMMAND_FRAME      */
-		_FAX_PARAMETER_ERROR,  /* T30_ERR_UNSUPPORTED_PAGE_CODING    */
-		_FAX_PARAMETER_ERROR,  /* T30_ERR_INVALID_PAGE_CODING        */
-		_FAX_REMOTE_REJECT,    /* T30_ERR_INCOMPATIBLE_PAGE_CONFIG   */
-		_FAX_LOCAL_ABORT,      /* T30_ERR_TIMEOUT_FROM_APPLICATION   */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_V34FAX_NO_REACTION_ON_MARK */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_V34FAX_TRAINING_TIMEOUT    */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_V34FAX_UNEXPECTED_V21      */
-		_FAX_PROTOCOL_ERROR,   /* T30_ERR_V34FAX_PRIMARY_CTS_ON      */
-		_FAX_LOCAL_ABORT,      /* T30_ERR_V34FAX_TURNAROUND_POLLING  */
-		_FAX_LOCAL_ABORT       /* T30_ERR_V34FAX_V8_INCOMPATIBILITY  */
-	};
-
-	byte dtmf_code_buffer[CAPIDTMF_RECV_DIGIT_BUFFER_SIZE + 1];
-
-
-	static word rtp_info[] = {
-		GOOD,                  /* RTP_SUCCESS                       */
-		0x3600                 /* RTP_ERR_SSRC_OR_PAYLOAD_CHANGE    */
-	};
-
-	static dword udata_forwarding_table[0x100 / sizeof(dword)] =
-		{
-			0x0020301e, 0x00000000, 0x00000000, 0x00000000,
-			0x00000000, 0x00000000, 0x00000000, 0x00000000
-		};
-
-	ch = plci->NL.IndCh;
-	a = plci->adapter;
-	ncci = a->ch_ncci[ch];
-	Id = (((dword)(ncci ? ncci : ch)) << 16) | (((word) plci->Id) << 8) | a->Id;
-	if (plci->tel) Id |= EXT_CONTROLLER;
-	APPLptr = plci->appl;
-	dbug(1, dprintf("NL_IND-Id(NL:0x%x)=0x%08lx,plci=%x,tel=%x,state=0x%x,ch=0x%x,chs=%d,Ind=%x",
-			plci->NL.Id, Id, plci->Id, plci->tel, plci->State, ch, plci->channels, plci->NL.Ind & 0x0f));
-
-	/* in the case if no connect_active_Ind was sent to the appl we wait for */
-
-	if (plci->nl_remove_id)
-	{
-		plci->NL.RNR = 2; /* discard */
-		dbug(1, dprintf("NL discard while remove pending"));
-		return;
-	}
-	if ((plci->NL.Ind & 0x0f) == N_CONNECT)
-	{
-		if (plci->State == INC_DIS_PENDING
-		    || plci->State == OUTG_DIS_PENDING
-		    || plci->State == IDLE)
-		{
-			plci->NL.RNR = 2; /* discard */
-			dbug(1, dprintf("discard n_connect"));
-			return;
-		}
-		if (plci->State < INC_ACT_PENDING)
-		{
-			plci->NL.RNR = 1; /* flow control */
-			channel_x_off(plci, ch, N_XON_CONNECT_IND);
-			return;
-		}
-	}
-
-	if (!APPLptr)                         /* no application or invalid data */
-	{                                    /* while reloading the DSP        */
-		dbug(1, dprintf("discard1"));
-		plci->NL.RNR = 2;
-		return;
-	}
-
-	if (((plci->NL.Ind & 0x0f) == N_UDATA)
-	    && (((plci->B2_prot != B2_SDLC) && ((plci->B1_resource == 17) || (plci->B1_resource == 18)))
-		|| (plci->B2_prot == 7)
-		|| (plci->B3_prot == 7)))
-	{
-		plci->ncpi_buffer[0] = 0;
-
-		ncpi_state = plci->ncpi_state;
-		if (plci->NL.complete == 1)
-		{
-			byte *data = &plci->NL.RBuffer->P[0];
-
-			if ((plci->NL.RBuffer->length >= 12)
-			    && ((*data == DSP_UDATA_INDICATION_DCD_ON)
-				|| (*data == DSP_UDATA_INDICATION_CTS_ON)))
-			{
-				word conn_opt, ncpi_opt = 0x00;
-/*      HexDump ("MDM N_UDATA:", plci->NL.RBuffer->length, data); */
-
-				if (*data == DSP_UDATA_INDICATION_DCD_ON)
-					plci->ncpi_state |= NCPI_MDM_DCD_ON_RECEIVED;
-				if (*data == DSP_UDATA_INDICATION_CTS_ON)
-					plci->ncpi_state |= NCPI_MDM_CTS_ON_RECEIVED;
-
-				data++;    /* indication code */
-				data += 2; /* timestamp */
-				if ((*data == DSP_CONNECTED_NORM_V18) || (*data == DSP_CONNECTED_NORM_VOWN))
-					ncpi_state &= ~(NCPI_MDM_DCD_ON_RECEIVED | NCPI_MDM_CTS_ON_RECEIVED);
-				data++;    /* connected norm */
-				conn_opt = GET_WORD(data);
-				data += 2; /* connected options */
-
-				PUT_WORD(&(plci->ncpi_buffer[1]), (word)(GET_DWORD(data) & 0x0000FFFF));
-
-				if (conn_opt & DSP_CONNECTED_OPTION_MASK_V42)
-				{
-					ncpi_opt |= MDM_NCPI_ECM_V42;
-				}
-				else if (conn_opt & DSP_CONNECTED_OPTION_MASK_MNP)
-				{
-					ncpi_opt |= MDM_NCPI_ECM_MNP;
-				}
-				else
-				{
-					ncpi_opt |= MDM_NCPI_TRANSPARENT;
-				}
-				if (conn_opt & DSP_CONNECTED_OPTION_MASK_COMPRESSION)
-				{
-					ncpi_opt |= MDM_NCPI_COMPRESSED;
-				}
-				PUT_WORD(&(plci->ncpi_buffer[3]), ncpi_opt);
-				plci->ncpi_buffer[0] = 4;
-
-				plci->ncpi_state |= NCPI_VALID_CONNECT_B3_IND | NCPI_VALID_CONNECT_B3_ACT | NCPI_VALID_DISC_B3_IND;
-			}
-		}
-		if (plci->B3_prot == 7)
-		{
-			if (((a->ncci_state[ncci] == INC_ACT_PENDING) || (a->ncci_state[ncci] == OUTG_CON_PENDING))
-			    && (plci->ncpi_state & NCPI_VALID_CONNECT_B3_ACT)
-			    && !(plci->ncpi_state & NCPI_CONNECT_B3_ACT_SENT))
-			{
-				a->ncci_state[ncci] = INC_ACT_PENDING;
-				sendf(plci->appl, _CONNECT_B3_ACTIVE_I, Id, 0, "S", plci->ncpi_buffer);
-				plci->ncpi_state |= NCPI_CONNECT_B3_ACT_SENT;
-			}
-		}
-
-		if (!((plci->requested_options_conn | plci->requested_options | plci->adapter->requested_options_table[plci->appl->Id - 1])
-		      & ((1L << PRIVATE_V18) | (1L << PRIVATE_VOWN)))
-		    || !(ncpi_state & NCPI_MDM_DCD_ON_RECEIVED)
-		    || !(ncpi_state & NCPI_MDM_CTS_ON_RECEIVED))
-
-		{
-			plci->NL.RNR = 2;
-			return;
-		}
-	}
-
-	if (plci->NL.complete == 2)
-	{
-		if (((plci->NL.Ind & 0x0f) == N_UDATA)
-		    && !(udata_forwarding_table[plci->RData[0].P[0] >> 5] & (1L << (plci->RData[0].P[0] & 0x1f))))
-		{
-			switch (plci->RData[0].P[0])
-			{
-
-			case DTMF_UDATA_INDICATION_FAX_CALLING_TONE:
-				if (plci->dtmf_rec_active & DTMF_LISTEN_ACTIVE_FLAG)
-					sendf(plci->appl, _FACILITY_I, Id & 0xffffL, 0, "ws", SELECTOR_DTMF, "\x01X");
-				break;
-			case DTMF_UDATA_INDICATION_ANSWER_TONE:
-				if (plci->dtmf_rec_active & DTMF_LISTEN_ACTIVE_FLAG)
-					sendf(plci->appl, _FACILITY_I, Id & 0xffffL, 0, "ws", SELECTOR_DTMF, "\x01Y");
-				break;
-			case DTMF_UDATA_INDICATION_DIGITS_RECEIVED:
-				dtmf_indication(Id, plci, plci->RData[0].P, plci->RData[0].PLength);
-				break;
-			case DTMF_UDATA_INDICATION_DIGITS_SENT:
-				dtmf_confirmation(Id, plci);
-				break;
-
-
-			case UDATA_INDICATION_MIXER_TAP_DATA:
-				capidtmf_recv_process_block(&(plci->capidtmf_state), plci->RData[0].P + 1, (word)(plci->RData[0].PLength - 1));
-				i = capidtmf_indication(&(plci->capidtmf_state), dtmf_code_buffer + 1);
-				if (i != 0)
-				{
-					dtmf_code_buffer[0] = DTMF_UDATA_INDICATION_DIGITS_RECEIVED;
-					dtmf_indication(Id, plci, dtmf_code_buffer, (word)(i + 1));
-				}
-				break;
-
-
-			case UDATA_INDICATION_MIXER_COEFS_SET:
-				mixer_indication_coefs_set(Id, plci);
-				break;
-			case UDATA_INDICATION_XCONNECT_FROM:
-				mixer_indication_xconnect_from(Id, plci, plci->RData[0].P, plci->RData[0].PLength);
-				break;
-			case UDATA_INDICATION_XCONNECT_TO:
-				mixer_indication_xconnect_to(Id, plci, plci->RData[0].P, plci->RData[0].PLength);
-				break;
-
-
-			case LEC_UDATA_INDICATION_DISABLE_DETECT:
-				ec_indication(Id, plci, plci->RData[0].P, plci->RData[0].PLength);
-				break;
-
-
-
-			default:
-				break;
-			}
-		}
-		else
-		{
-			if ((plci->RData[0].PLength != 0)
-			    && ((plci->B2_prot == B2_V120_ASYNC)
-				|| (plci->B2_prot == B2_V120_ASYNC_V42BIS)
-				|| (plci->B2_prot == B2_V120_BIT_TRANSPARENT)))
-			{
-
-				sendf(plci->appl, _DATA_B3_I, Id, 0,
-				      "dwww",
-				      plci->RData[1].P,
-				      (plci->NL.RNum < 2) ? 0 : plci->RData[1].PLength,
-				      plci->RNum,
-				      plci->RFlags);
-
-			}
-			else
-			{
-
-				sendf(plci->appl, _DATA_B3_I, Id, 0,
-				      "dwww",
-				      plci->RData[0].P,
-				      plci->RData[0].PLength,
-				      plci->RNum,
-				      plci->RFlags);
-
-			}
-		}
-		return;
-	}
-
-	fax_feature_bits = 0;
-	if ((plci->NL.Ind & 0x0f) == N_CONNECT ||
-	    (plci->NL.Ind & 0x0f) == N_CONNECT_ACK ||
-	    (plci->NL.Ind & 0x0f) == N_DISC ||
-	    (plci->NL.Ind & 0x0f) == N_EDATA ||
-	    (plci->NL.Ind & 0x0f) == N_DISC_ACK)
-	{
-		info = 0;
-		plci->ncpi_buffer[0] = 0;
-		switch (plci->B3_prot) {
-		case  0: /*XPARENT*/
-		case  1: /*T.90 NL*/
-			break;    /* no network control protocol info - jfr */
-		case  2: /*ISO8202*/
-		case  3: /*X25 DCE*/
-			for (i = 0; i < plci->NL.RLength; i++) plci->ncpi_buffer[4 + i] = plci->NL.RBuffer->P[i];
-			plci->ncpi_buffer[0] = (byte)(i + 3);
-			plci->ncpi_buffer[1] = (byte)(plci->NL.Ind & N_D_BIT ? 1 : 0);
-			plci->ncpi_buffer[2] = 0;
-			plci->ncpi_buffer[3] = 0;
-			break;
-		case  4: /*T.30 - FAX*/
-		case  5: /*T.30 - FAX*/
-			if (plci->NL.RLength >= sizeof(T30_INFO))
-			{
-				dbug(1, dprintf("FaxStatus %04x", ((T30_INFO *)plci->NL.RBuffer->P)->code));
-				len = 9;
-				PUT_WORD(&(plci->ncpi_buffer[1]), ((T30_INFO *)plci->NL.RBuffer->P)->rate_div_2400 * 2400);
-				fax_feature_bits = GET_WORD(&((T30_INFO *)plci->NL.RBuffer->P)->feature_bits_low);
-				i = (((T30_INFO *)plci->NL.RBuffer->P)->resolution & T30_RESOLUTION_R8_0770_OR_200) ? 0x0001 : 0x0000;
-				if (plci->B3_prot == 5)
-				{
-					if (!(fax_feature_bits & T30_FEATURE_BIT_ECM))
-						i |= 0x8000; /* This is not an ECM connection */
-					if (fax_feature_bits & T30_FEATURE_BIT_T6_CODING)
-						i |= 0x4000; /* This is a connection with MMR compression */
-					if (fax_feature_bits & T30_FEATURE_BIT_2D_CODING)
-						i |= 0x2000; /* This is a connection with MR compression */
-					if (fax_feature_bits & T30_FEATURE_BIT_MORE_DOCUMENTS)
-						i |= 0x0004; /* More documents */
-					if (fax_feature_bits & T30_FEATURE_BIT_POLLING)
-						i |= 0x0002; /* Fax-polling indication */
-				}
-				dbug(1, dprintf("FAX Options %04x %04x", fax_feature_bits, i));
-				PUT_WORD(&(plci->ncpi_buffer[3]), i);
-				PUT_WORD(&(plci->ncpi_buffer[5]), ((T30_INFO *)plci->NL.RBuffer->P)->data_format);
-				plci->ncpi_buffer[7] = ((T30_INFO *)plci->NL.RBuffer->P)->pages_low;
-				plci->ncpi_buffer[8] = ((T30_INFO *)plci->NL.RBuffer->P)->pages_high;
-				plci->ncpi_buffer[len] = 0;
-				if (((T30_INFO *)plci->NL.RBuffer->P)->station_id_len)
-				{
-					plci->ncpi_buffer[len] = 20;
-					for (i = 0; i < T30_MAX_STATION_ID_LENGTH; i++)
-						plci->ncpi_buffer[++len] = ((T30_INFO *)plci->NL.RBuffer->P)->station_id[i];
-				}
-				if (((plci->NL.Ind & 0x0f) == N_DISC) || ((plci->NL.Ind & 0x0f) == N_DISC_ACK))
-				{
-					if (((T30_INFO *)plci->NL.RBuffer->P)->code < ARRAY_SIZE(fax_info))
-						info = fax_info[((T30_INFO *)plci->NL.RBuffer->P)->code];
-					else
-						info = _FAX_PROTOCOL_ERROR;
-				}
-
-				if ((plci->requested_options_conn | plci->requested_options | a->requested_options_table[plci->appl->Id - 1])
-				    & ((1L << PRIVATE_FAX_SUB_SEP_PWD) | (1L << PRIVATE_FAX_NONSTANDARD)))
-				{
-					i = offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH + ((T30_INFO *)plci->NL.RBuffer->P)->head_line_len;
-					while (i < plci->NL.RBuffer->length)
-						plci->ncpi_buffer[++len] = plci->NL.RBuffer->P[i++];
-				}
-
-				plci->ncpi_buffer[0] = len;
-				fax_feature_bits = GET_WORD(&((T30_INFO *)plci->NL.RBuffer->P)->feature_bits_low);
-				PUT_WORD(&((T30_INFO *)plci->fax_connect_info_buffer)->feature_bits_low, fax_feature_bits);
-
-				plci->ncpi_state |= NCPI_VALID_CONNECT_B3_IND;
-				if (((plci->NL.Ind & 0x0f) == N_CONNECT_ACK)
-				    || (((plci->NL.Ind & 0x0f) == N_CONNECT)
-					&& (fax_feature_bits & T30_FEATURE_BIT_POLLING))
-				    || (((plci->NL.Ind & 0x0f) == N_EDATA)
-					&& ((((T30_INFO *)plci->NL.RBuffer->P)->code == EDATA_T30_TRAIN_OK)
-					    || (((T30_INFO *)plci->NL.RBuffer->P)->code == EDATA_T30_DIS)
-					    || (((T30_INFO *)plci->NL.RBuffer->P)->code == EDATA_T30_DTC))))
-				{
-					plci->ncpi_state |= NCPI_VALID_CONNECT_B3_ACT;
-				}
-				if (((plci->NL.Ind & 0x0f) == N_DISC)
-				    || ((plci->NL.Ind & 0x0f) == N_DISC_ACK)
-				    || (((plci->NL.Ind & 0x0f) == N_EDATA)
-					&& (((T30_INFO *)plci->NL.RBuffer->P)->code == EDATA_T30_EOP_CAPI)))
-				{
-					plci->ncpi_state |= NCPI_VALID_CONNECT_B3_ACT | NCPI_VALID_DISC_B3_IND;
-				}
-			}
-			break;
-
-		case B3_RTP:
-			if (((plci->NL.Ind & 0x0f) == N_DISC) || ((plci->NL.Ind & 0x0f) == N_DISC_ACK))
-			{
-				if (plci->NL.RLength != 0)
-				{
-					info = rtp_info[plci->NL.RBuffer->P[0]];
-					plci->ncpi_buffer[0] = plci->NL.RLength - 1;
-					for (i = 1; i < plci->NL.RLength; i++)
-						plci->ncpi_buffer[i] = plci->NL.RBuffer->P[i];
-				}
-			}
-			break;
-
-		}
-		plci->NL.RNR = 2;
-	}
-	switch (plci->NL.Ind & 0x0f) {
-	case N_EDATA:
-		if ((plci->B3_prot == 4) || (plci->B3_prot == 5))
-		{
-			dbug(1, dprintf("EDATA ncci=0x%x state=%d code=%02x", ncci, a->ncci_state[ncci],
-					((T30_INFO *)plci->NL.RBuffer->P)->code));
-			fax_send_edata_ack = (((T30_INFO *)(plci->fax_connect_info_buffer))->operating_mode == T30_OPERATING_MODE_CAPI_NEG);
-
-			if ((plci->nsf_control_bits & T30_NSF_CONTROL_BIT_ENABLE_NSF)
-			    && (plci->nsf_control_bits & (T30_NSF_CONTROL_BIT_NEGOTIATE_IND | T30_NSF_CONTROL_BIT_NEGOTIATE_RESP))
-			    && (((T30_INFO *)plci->NL.RBuffer->P)->code == EDATA_T30_DIS)
-			    && (a->ncci_state[ncci] == OUTG_CON_PENDING)
-			    && (plci->ncpi_state & NCPI_VALID_CONNECT_B3_ACT)
-			    && !(plci->ncpi_state & NCPI_NEGOTIATE_B3_SENT))
-			{
-				((T30_INFO *)(plci->fax_connect_info_buffer))->code = ((T30_INFO *)plci->NL.RBuffer->P)->code;
-				sendf(plci->appl, _MANUFACTURER_I, Id, 0, "dwbS", _DI_MANU_ID, _DI_NEGOTIATE_B3,
-				      (byte)(plci->ncpi_buffer[0] + 1), plci->ncpi_buffer);
-				plci->ncpi_state |= NCPI_NEGOTIATE_B3_SENT;
-				if (plci->nsf_control_bits & T30_NSF_CONTROL_BIT_NEGOTIATE_RESP)
-					fax_send_edata_ack = false;
-			}
-
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_FAX_PAPER_FORMATS)
-			{
-				switch (((T30_INFO *)plci->NL.RBuffer->P)->code)
-				{
-				case EDATA_T30_DIS:
-					if ((a->ncci_state[ncci] == OUTG_CON_PENDING)
-					    && !(GET_WORD(&((T30_INFO *)plci->fax_connect_info_buffer)->control_bits_low) & T30_CONTROL_BIT_REQUEST_POLLING)
-					    && (plci->ncpi_state & NCPI_VALID_CONNECT_B3_ACT)
-					    && !(plci->ncpi_state & NCPI_CONNECT_B3_ACT_SENT))
-					{
-						a->ncci_state[ncci] = INC_ACT_PENDING;
-						if (plci->B3_prot == 4)
-							sendf(plci->appl, _CONNECT_B3_ACTIVE_I, Id, 0, "s", "");
-						else
-							sendf(plci->appl, _CONNECT_B3_ACTIVE_I, Id, 0, "S", plci->ncpi_buffer);
-						plci->ncpi_state |= NCPI_CONNECT_B3_ACT_SENT;
-					}
-					break;
-
-				case EDATA_T30_TRAIN_OK:
-					if ((a->ncci_state[ncci] == INC_ACT_PENDING)
-					    && (plci->ncpi_state & NCPI_VALID_CONNECT_B3_ACT)
-					    && !(plci->ncpi_state & NCPI_CONNECT_B3_ACT_SENT))
-					{
-						if (plci->B3_prot == 4)
-							sendf(plci->appl, _CONNECT_B3_ACTIVE_I, Id, 0, "s", "");
-						else
-							sendf(plci->appl, _CONNECT_B3_ACTIVE_I, Id, 0, "S", plci->ncpi_buffer);
-						plci->ncpi_state |= NCPI_CONNECT_B3_ACT_SENT;
-					}
-					break;
-
-				case EDATA_T30_EOP_CAPI:
-					if (a->ncci_state[ncci] == CONNECTED)
-					{
-						sendf(plci->appl, _DISCONNECT_B3_I, Id, 0, "wS", GOOD, plci->ncpi_buffer);
-						a->ncci_state[ncci] = INC_DIS_PENDING;
-						plci->ncpi_state = 0;
-						fax_send_edata_ack = false;
-					}
-					break;
-				}
-			}
-			else
-			{
-				switch (((T30_INFO *)plci->NL.RBuffer->P)->code)
-				{
-				case EDATA_T30_TRAIN_OK:
-					if ((a->ncci_state[ncci] == INC_ACT_PENDING)
-					    && (plci->ncpi_state & NCPI_VALID_CONNECT_B3_ACT)
-					    && !(plci->ncpi_state & NCPI_CONNECT_B3_ACT_SENT))
-					{
-						if (plci->B3_prot == 4)
-							sendf(plci->appl, _CONNECT_B3_ACTIVE_I, Id, 0, "s", "");
-						else
-							sendf(plci->appl, _CONNECT_B3_ACTIVE_I, Id, 0, "S", plci->ncpi_buffer);
-						plci->ncpi_state |= NCPI_CONNECT_B3_ACT_SENT;
-					}
-					break;
-				}
-			}
-			if (fax_send_edata_ack)
-			{
-				((T30_INFO *)(plci->fax_connect_info_buffer))->code = ((T30_INFO *)plci->NL.RBuffer->P)->code;
-				plci->fax_edata_ack_length = 1;
-				start_internal_command(Id, plci, fax_edata_ack_command);
-			}
-		}
-		else
-		{
-			dbug(1, dprintf("EDATA ncci=0x%x state=%d", ncci, a->ncci_state[ncci]));
-		}
-		break;
-	case N_CONNECT:
-		if (!a->ch_ncci[ch])
-		{
-			ncci = get_ncci(plci, ch, 0);
-			Id = (Id & 0xffff) | (((dword) ncci) << 16);
-		}
-		dbug(1, dprintf("N_CONNECT: ch=%d state=%d plci=%lx plci_Id=%lx plci_State=%d",
-				ch, a->ncci_state[ncci], a->ncci_plci[ncci], plci->Id, plci->State));
-
-		msg = _CONNECT_B3_I;
-		if (a->ncci_state[ncci] == IDLE)
-			plci->channels++;
-		else if (plci->B3_prot == 1)
-			msg = _CONNECT_B3_T90_ACTIVE_I;
-
-		a->ncci_state[ncci] = INC_CON_PENDING;
-		if (plci->B3_prot == 4)
-			sendf(plci->appl, msg, Id, 0, "s", "");
-		else
-			sendf(plci->appl, msg, Id, 0, "S", plci->ncpi_buffer);
-		break;
-	case N_CONNECT_ACK:
-		dbug(1, dprintf("N_connect_Ack"));
-		if (plci->internal_command_queue[0]
-		    && ((plci->adjust_b_state == ADJUST_B_CONNECT_2)
-			|| (plci->adjust_b_state == ADJUST_B_CONNECT_3)
-			|| (plci->adjust_b_state == ADJUST_B_CONNECT_4)))
-		{
-			(*(plci->internal_command_queue[0]))(Id, plci, 0);
-			if (!plci->internal_command)
-				next_internal_command(Id, plci);
-			break;
-		}
-		msg = _CONNECT_B3_ACTIVE_I;
-		if (plci->B3_prot == 1)
-		{
-			if (a->ncci_state[ncci] != OUTG_CON_PENDING)
-				msg = _CONNECT_B3_T90_ACTIVE_I;
-			a->ncci_state[ncci] = INC_ACT_PENDING;
-			sendf(plci->appl, msg, Id, 0, "S", plci->ncpi_buffer);
-		}
-		else if ((plci->B3_prot == 4) || (plci->B3_prot == 5) || (plci->B3_prot == 7))
-		{
-			if ((a->ncci_state[ncci] == OUTG_CON_PENDING)
-			    && (plci->ncpi_state & NCPI_VALID_CONNECT_B3_ACT)
-			    && !(plci->ncpi_state & NCPI_CONNECT_B3_ACT_SENT))
-			{
-				a->ncci_state[ncci] = INC_ACT_PENDING;
-				if (plci->B3_prot == 4)
-					sendf(plci->appl, msg, Id, 0, "s", "");
-				else
-					sendf(plci->appl, msg, Id, 0, "S", plci->ncpi_buffer);
-				plci->ncpi_state |= NCPI_CONNECT_B3_ACT_SENT;
-			}
-		}
-		else
-		{
-			a->ncci_state[ncci] = INC_ACT_PENDING;
-			sendf(plci->appl, msg, Id, 0, "S", plci->ncpi_buffer);
-		}
-		if (plci->adjust_b_restore)
-		{
-			plci->adjust_b_restore = false;
-			start_internal_command(Id, plci, adjust_b_restore);
-		}
-		break;
-	case N_DISC:
-	case N_DISC_ACK:
-		if (plci->internal_command_queue[0]
-		    && ((plci->internal_command == FAX_DISCONNECT_COMMAND_1)
-			|| (plci->internal_command == FAX_DISCONNECT_COMMAND_2)
-			|| (plci->internal_command == FAX_DISCONNECT_COMMAND_3)))
-		{
-			(*(plci->internal_command_queue[0]))(Id, plci, 0);
-			if (!plci->internal_command)
-				next_internal_command(Id, plci);
-		}
-		ncci_state = a->ncci_state[ncci];
-		ncci_remove(plci, ncci, false);
-
-		/* with N_DISC or N_DISC_ACK the IDI frees the respective   */
-		/* channel, so we cannot store the state in ncci_state! The */
-		/* information which channel we received a N_DISC is thus   */
-		/* stored in the inc_dis_ncci_table buffer.                 */
-		for (i = 0; plci->inc_dis_ncci_table[i]; i++);
-		plci->inc_dis_ncci_table[i] = (byte) ncci;
-
-		/* need a connect_b3_ind before a disconnect_b3_ind with FAX */
-		if (!plci->channels
-		    && (plci->B1_resource == 16)
-		    && (plci->State <= CONNECTED))
-		{
-			len = 9;
-			i = ((T30_INFO *)plci->fax_connect_info_buffer)->rate_div_2400 * 2400;
-			PUT_WORD(&plci->ncpi_buffer[1], i);
-			PUT_WORD(&plci->ncpi_buffer[3], 0);
-			i = ((T30_INFO *)plci->fax_connect_info_buffer)->data_format;
-			PUT_WORD(&plci->ncpi_buffer[5], i);
-			PUT_WORD(&plci->ncpi_buffer[7], 0);
-			plci->ncpi_buffer[len] = 0;
-			plci->ncpi_buffer[0] = len;
-			if (plci->B3_prot == 4)
-				sendf(plci->appl, _CONNECT_B3_I, Id, 0, "s", "");
-			else
-			{
-
-				if ((plci->requested_options_conn | plci->requested_options | a->requested_options_table[plci->appl->Id - 1])
-				    & ((1L << PRIVATE_FAX_SUB_SEP_PWD) | (1L << PRIVATE_FAX_NONSTANDARD)))
-				{
-					plci->ncpi_buffer[++len] = 0;
-					plci->ncpi_buffer[++len] = 0;
-					plci->ncpi_buffer[++len] = 0;
-					plci->ncpi_buffer[0] = len;
-				}
-
-				sendf(plci->appl, _CONNECT_B3_I, Id, 0, "S", plci->ncpi_buffer);
-			}
-			sendf(plci->appl, _DISCONNECT_B3_I, Id, 0, "wS", info, plci->ncpi_buffer);
-			plci->ncpi_state = 0;
-			sig_req(plci, HANGUP, 0);
-			send_req(plci);
-			plci->State = OUTG_DIS_PENDING;
-			/* disc here */
-		}
-		else if ((a->manufacturer_features & MANUFACTURER_FEATURE_FAX_PAPER_FORMATS)
-			 && ((plci->B3_prot == 4) || (plci->B3_prot == 5))
-			 && ((ncci_state == INC_DIS_PENDING) || (ncci_state == IDLE)))
-		{
-			if (ncci_state == IDLE)
-			{
-				if (plci->channels)
-					plci->channels--;
-				if ((plci->State == IDLE || plci->State == SUSPENDING) && !plci->channels) {
-					if (plci->State == SUSPENDING) {
-						sendf(plci->appl,
-						      _FACILITY_I,
-						      Id & 0xffffL,
-						      0,
-						      "ws", (word)3, "\x03\x04\x00\x00");
-						sendf(plci->appl, _DISCONNECT_I, Id & 0xffffL, 0, "w", 0);
-					}
-					plci_remove(plci);
-					plci->State = IDLE;
-				}
-			}
-		}
-		else if (plci->channels)
-		{
-			sendf(plci->appl, _DISCONNECT_B3_I, Id, 0, "wS", info, plci->ncpi_buffer);
-			plci->ncpi_state = 0;
-			if ((ncci_state == OUTG_REJ_PENDING)
-			    && ((plci->B3_prot != B3_T90NL) && (plci->B3_prot != B3_ISO8208) && (plci->B3_prot != B3_X25_DCE)))
-			{
-				sig_req(plci, HANGUP, 0);
-				send_req(plci);
-				plci->State = OUTG_DIS_PENDING;
-			}
-		}
-		break;
-	case N_RESET:
-		a->ncci_state[ncci] = INC_RES_PENDING;
-		sendf(plci->appl, _RESET_B3_I, Id, 0, "S", plci->ncpi_buffer);
-		break;
-	case N_RESET_ACK:
-		a->ncci_state[ncci] = CONNECTED;
-		sendf(plci->appl, _RESET_B3_I, Id, 0, "S", plci->ncpi_buffer);
-		break;
-
-	case N_UDATA:
-		if (!(udata_forwarding_table[plci->NL.RBuffer->P[0] >> 5] & (1L << (plci->NL.RBuffer->P[0] & 0x1f))))
-		{
-			plci->RData[0].P = plci->internal_ind_buffer + (-((int)(long)(plci->internal_ind_buffer)) & 3);
-			plci->RData[0].PLength = INTERNAL_IND_BUFFER_SIZE;
-			plci->NL.R = plci->RData;
-			plci->NL.RNum = 1;
-			return;
-		}
-		/* fall through */
-	case N_BDATA:
-	case N_DATA:
-		if (((a->ncci_state[ncci] != CONNECTED) && (plci->B2_prot == 1)) /* transparent */
-		    || (a->ncci_state[ncci] == IDLE)
-		    || (a->ncci_state[ncci] == INC_DIS_PENDING))
-		{
-			plci->NL.RNR = 2;
-			break;
-		}
-		if ((a->ncci_state[ncci] != CONNECTED)
-		    && (a->ncci_state[ncci] != OUTG_DIS_PENDING)
-		    && (a->ncci_state[ncci] != OUTG_REJ_PENDING))
-		{
-			dbug(1, dprintf("flow control"));
-			plci->NL.RNR = 1; /* flow control  */
-			channel_x_off(plci, ch, 0);
-			break;
-		}
-
-		NCCIcode = ncci | (((word)a->Id) << 8);
-
-		/* count all buffers within the Application pool    */
-		/* belonging to the same NCCI. If this is below the */
-		/* number of buffers available per NCCI we accept   */
-		/* this packet, otherwise we reject it              */
-		count = 0;
-		Num = 0xffff;
-		for (i = 0; i < APPLptr->MaxBuffer; i++) {
-			if (NCCIcode == APPLptr->DataNCCI[i]) count++;
-			if (!APPLptr->DataNCCI[i] && Num == 0xffff) Num = i;
-		}
-
-		if (count >= APPLptr->MaxNCCIData || Num == 0xffff)
-		{
-			dbug(3, dprintf("Flow-Control"));
-			plci->NL.RNR = 1;
-			if (++(APPLptr->NCCIDataFlowCtrlTimer) >=
-			    (word)((a->manufacturer_features & MANUFACTURER_FEATURE_OOB_CHANNEL) ? 40 : 2000))
-			{
-				plci->NL.RNR = 2;
-				dbug(3, dprintf("DiscardData"));
-			} else {
-				channel_x_off(plci, ch, 0);
-			}
-			break;
-		}
-		else
-		{
-			APPLptr->NCCIDataFlowCtrlTimer = 0;
-		}
-
-		plci->RData[0].P = ReceiveBufferGet(APPLptr, Num);
-		if (!plci->RData[0].P) {
-			plci->NL.RNR = 1;
-			channel_x_off(plci, ch, 0);
-			break;
-		}
-
-		APPLptr->DataNCCI[Num] = NCCIcode;
-		APPLptr->DataFlags[Num] = (plci->Id << 8) | (plci->NL.Ind >> 4);
-		dbug(3, dprintf("Buffer(%d), Max = %d", Num, APPLptr->MaxBuffer));
-
-		plci->RNum = Num;
-		plci->RFlags = plci->NL.Ind >> 4;
-		plci->RData[0].PLength = APPLptr->MaxDataLength;
-		plci->NL.R = plci->RData;
-		if ((plci->NL.RLength != 0)
-		    && ((plci->B2_prot == B2_V120_ASYNC)
-			|| (plci->B2_prot == B2_V120_ASYNC_V42BIS)
-			|| (plci->B2_prot == B2_V120_BIT_TRANSPARENT)))
-		{
-			plci->RData[1].P = plci->RData[0].P;
-			plci->RData[1].PLength = plci->RData[0].PLength;
-			plci->RData[0].P = v120_header_buffer + (-((unsigned long)v120_header_buffer) & 3);
-			if ((plci->NL.RBuffer->P[0] & V120_HEADER_EXTEND_BIT) || (plci->NL.RLength == 1))
-				plci->RData[0].PLength = 1;
-			else
-				plci->RData[0].PLength = 2;
-			if (plci->NL.RBuffer->P[0] & V120_HEADER_BREAK_BIT)
-				plci->RFlags |= 0x0010;
-			if (plci->NL.RBuffer->P[0] & (V120_HEADER_C1_BIT | V120_HEADER_C2_BIT))
-				plci->RFlags |= 0x8000;
-			plci->NL.RNum = 2;
-		}
-		else
-		{
-			if ((plci->NL.Ind & 0x0f) == N_UDATA)
-				plci->RFlags |= 0x0010;
-
-			else if ((plci->B3_prot == B3_RTP) && ((plci->NL.Ind & 0x0f) == N_BDATA))
-				plci->RFlags |= 0x0001;
-
-			plci->NL.RNum = 1;
-		}
-		break;
-	case N_DATA_ACK:
-		data_ack(plci, ch);
-		break;
-	default:
-		plci->NL.RNR = 2;
-		break;
-	}
-}
-
-/*------------------------------------------------------------------*/
-/* find a free PLCI */
-/*------------------------------------------------------------------*/
-
-static word get_plci(DIVA_CAPI_ADAPTER *a)
-{
-	word i, j;
-	PLCI *plci;
-
-	for (i = 0; i < a->max_plci && a->plci[i].Id; i++);
-	if (i == a->max_plci) {
-		dbug(1, dprintf("get_plci: out of PLCIs"));
-		return 0;
-	}
-	plci = &a->plci[i];
-	plci->Id = (byte)(i + 1);
-
-	plci->Sig.Id = 0;
-	plci->NL.Id = 0;
-	plci->sig_req = 0;
-	plci->nl_req = 0;
-
-	plci->appl = NULL;
-	plci->relatedPTYPLCI = NULL;
-	plci->State = IDLE;
-	plci->SuppState = IDLE;
-	plci->channels = 0;
-	plci->tel = 0;
-	plci->B1_resource = 0;
-	plci->B2_prot = 0;
-	plci->B3_prot = 0;
-
-	plci->command = 0;
-	plci->m_command = 0;
-	init_internal_command_queue(plci);
-	plci->number = 0;
-	plci->req_in_start = 0;
-	plci->req_in = 0;
-	plci->req_out = 0;
-	plci->msg_in_write_pos = MSG_IN_QUEUE_SIZE;
-	plci->msg_in_read_pos = MSG_IN_QUEUE_SIZE;
-	plci->msg_in_wrap_pos = MSG_IN_QUEUE_SIZE;
-
-	plci->data_sent = false;
-	plci->send_disc = 0;
-	plci->sig_global_req = 0;
-	plci->sig_remove_id = 0;
-	plci->nl_global_req = 0;
-	plci->nl_remove_id = 0;
-	plci->adv_nl = 0;
-	plci->manufacturer = false;
-	plci->call_dir = CALL_DIR_OUT | CALL_DIR_ORIGINATE;
-	plci->spoofed_msg = 0;
-	plci->ptyState = 0;
-	plci->cr_enquiry = false;
-	plci->hangup_flow_ctrl_timer = 0;
-
-	plci->ncci_ring_list = 0;
-	for (j = 0; j < MAX_CHANNELS_PER_PLCI; j++) plci->inc_dis_ncci_table[j] = 0;
-	bitmap_zero(plci->c_ind_mask_table, MAX_APPL);
-	bitmap_fill(plci->group_optimization_mask_table, MAX_APPL);
-	plci->fax_connect_info_length = 0;
-	plci->nsf_control_bits = 0;
-	plci->ncpi_state = 0x00;
-	plci->ncpi_buffer[0] = 0;
-
-	plci->requested_options_conn = 0;
-	plci->requested_options = 0;
-	plci->notifiedcall = 0;
-	plci->vswitchstate = 0;
-	plci->vsprot = 0;
-	plci->vsprotdialect = 0;
-	init_b1_config(plci);
-	dbug(1, dprintf("get_plci(%x)", plci->Id));
-	return i + 1;
-}
-
-/*------------------------------------------------------------------*/
-/* put a parameter in the parameter buffer                          */
-/*------------------------------------------------------------------*/
-
-static void add_p(PLCI *plci, byte code, byte *p)
-{
-	word p_length;
-
-	p_length = 0;
-	if (p) p_length = p[0];
-	add_ie(plci, code, p, p_length);
-}
-
-/*------------------------------------------------------------------*/
-/* put a structure in the parameter buffer                          */
-/*------------------------------------------------------------------*/
-static void add_s(PLCI *plci, byte code, API_PARSE *p)
-{
-	if (p) add_ie(plci, code, p->info, (word)p->length);
-}
-
-/*------------------------------------------------------------------*/
-/* put multiple structures in the parameter buffer                  */
-/*------------------------------------------------------------------*/
-static void add_ss(PLCI *plci, byte code, API_PARSE *p)
-{
-	byte i;
-
-	if (p) {
-		dbug(1, dprintf("add_ss(%x,len=%d)", code, p->length));
-		for (i = 2; i < (byte)p->length; i += p->info[i] + 2) {
-			dbug(1, dprintf("add_ss_ie(%x,len=%d)", p->info[i - 1], p->info[i]));
-			add_ie(plci, p->info[i - 1], (byte *)&(p->info[i]), (word)p->info[i]);
-		}
-	}
-}
-
-/*------------------------------------------------------------------*/
-/* return the channel number sent by the application in a esc_chi   */
-/*------------------------------------------------------------------*/
-static byte getChannel(API_PARSE *p)
-{
-	byte i;
-
-	if (p) {
-		for (i = 2; i < (byte)p->length; i += p->info[i] + 2) {
-			if (p->info[i] == 2) {
-				if (p->info[i - 1] == ESC && p->info[i + 1] == CHI) return (p->info[i + 2]);
-			}
-		}
-	}
-	return 0;
-}
-
-
-/*------------------------------------------------------------------*/
-/* put an information element in the parameter buffer               */
-/*------------------------------------------------------------------*/
-
-static void add_ie(PLCI *plci, byte code, byte *p, word p_length)
-{
-	word i;
-
-	if (!(code & 0x80) && !p_length) return;
-
-	if (plci->req_in == plci->req_in_start) {
-		plci->req_in += 2;
-	}
-	else {
-		plci->req_in--;
-	}
-	plci->RBuffer[plci->req_in++] = code;
-
-	if (p) {
-		plci->RBuffer[plci->req_in++] = (byte)p_length;
-		for (i = 0; i < p_length; i++) plci->RBuffer[plci->req_in++] = p[1 + i];
-	}
-
-	plci->RBuffer[plci->req_in++] = 0;
-}
-
-/*------------------------------------------------------------------*/
-/* put a unstructured data into the buffer                          */
-/*------------------------------------------------------------------*/
-
-static void add_d(PLCI *plci, word length, byte *p)
-{
-	word i;
-
-	if (plci->req_in == plci->req_in_start) {
-		plci->req_in += 2;
-	}
-	else {
-		plci->req_in--;
-	}
-	for (i = 0; i < length; i++) plci->RBuffer[plci->req_in++] = p[i];
-}
-
-/*------------------------------------------------------------------*/
-/* put parameters from the Additional Info parameter in the         */
-/* parameter buffer                                                 */
-/*------------------------------------------------------------------*/
-
-static void add_ai(PLCI *plci, API_PARSE *ai)
-{
-	word i;
-	API_PARSE ai_parms[5];
-
-	for (i = 0; i < 5; i++) ai_parms[i].length = 0;
-
-	if (!ai->length)
-		return;
-	if (api_parse(&ai->info[1], (word)ai->length, "ssss", ai_parms))
-		return;
-
-	add_s(plci, KEY, &ai_parms[1]);
-	add_s(plci, UUI, &ai_parms[2]);
-	add_ss(plci, FTY, &ai_parms[3]);
-}
-
-/*------------------------------------------------------------------*/
-/* put parameter for b1 protocol in the parameter buffer            */
-/*------------------------------------------------------------------*/
-
-static word add_b1(PLCI *plci, API_PARSE *bp, word b_channel_info,
-		   word b1_facilities)
-{
-	API_PARSE bp_parms[8];
-	API_PARSE mdm_cfg[9];
-	API_PARSE global_config[2];
-	byte cai[256];
-	byte resource[] = {5, 9, 13, 12, 16, 39, 9, 17, 17, 18};
-	byte voice_cai[] = "\x06\x14\x00\x00\x00\x00\x08";
-	word i;
-
-	API_PARSE mdm_cfg_v18[4];
-	word j, n, w;
-	dword d;
-
-
-	for (i = 0; i < 8; i++) bp_parms[i].length = 0;
-	for (i = 0; i < 2; i++) global_config[i].length = 0;
-
-	dbug(1, dprintf("add_b1"));
-	api_save_msg(bp, "s", &plci->B_protocol);
-
-	if (b_channel_info == 2) {
-		plci->B1_resource = 0;
-		adjust_b1_facilities(plci, plci->B1_resource, b1_facilities);
-		add_p(plci, CAI, "\x01\x00");
-		dbug(1, dprintf("Cai=1,0 (no resource)"));
-		return 0;
-	}
-
-	if (plci->tel == CODEC_PERMANENT) return 0;
-	else if (plci->tel == CODEC) {
-		plci->B1_resource = 1;
-		adjust_b1_facilities(plci, plci->B1_resource, b1_facilities);
-		add_p(plci, CAI, "\x01\x01");
-		dbug(1, dprintf("Cai=1,1 (Codec)"));
-		return 0;
-	}
-	else if (plci->tel == ADV_VOICE) {
-		plci->B1_resource = add_b1_facilities(plci, 9, (word)(b1_facilities | B1_FACILITY_VOICE));
-		adjust_b1_facilities(plci, plci->B1_resource, (word)(b1_facilities | B1_FACILITY_VOICE));
-		voice_cai[1] = plci->B1_resource;
-		PUT_WORD(&voice_cai[5], plci->appl->MaxDataLength);
-		add_p(plci, CAI, voice_cai);
-		dbug(1, dprintf("Cai=1,0x%x (AdvVoice)", voice_cai[1]));
-		return 0;
-	}
-	plci->call_dir &= ~(CALL_DIR_ORIGINATE | CALL_DIR_ANSWER);
-	if (plci->call_dir & CALL_DIR_OUT)
-		plci->call_dir |= CALL_DIR_ORIGINATE;
-	else if (plci->call_dir & CALL_DIR_IN)
-		plci->call_dir |= CALL_DIR_ANSWER;
-
-	if (!bp->length) {
-		plci->B1_resource = 0x5;
-		adjust_b1_facilities(plci, plci->B1_resource, b1_facilities);
-		add_p(plci, CAI, "\x01\x05");
-		return 0;
-	}
-
-	dbug(1, dprintf("b_prot_len=%d", (word)bp->length));
-	if (bp->length > 256) return _WRONG_MESSAGE_FORMAT;
-	if (api_parse(&bp->info[1], (word)bp->length, "wwwsssb", bp_parms))
-	{
-		bp_parms[6].length = 0;
-		if (api_parse(&bp->info[1], (word)bp->length, "wwwsss", bp_parms))
-		{
-			dbug(1, dprintf("b-form.!"));
-			return _WRONG_MESSAGE_FORMAT;
-		}
-	}
-	else if (api_parse(&bp->info[1], (word)bp->length, "wwwssss", bp_parms))
-	{
-		dbug(1, dprintf("b-form.!"));
-		return _WRONG_MESSAGE_FORMAT;
-	}
-
-	if (bp_parms[6].length)
-	{
-		if (api_parse(&bp_parms[6].info[1], (word)bp_parms[6].length, "w", global_config))
-		{
-			return _WRONG_MESSAGE_FORMAT;
-		}
-		switch (GET_WORD(global_config[0].info))
-		{
-		case 1:
-			plci->call_dir = (plci->call_dir & ~CALL_DIR_ANSWER) | CALL_DIR_ORIGINATE;
-			break;
-		case 2:
-			plci->call_dir = (plci->call_dir & ~CALL_DIR_ORIGINATE) | CALL_DIR_ANSWER;
-			break;
-		}
-	}
-	dbug(1, dprintf("call_dir=%04x", plci->call_dir));
-
-
-	if ((GET_WORD(bp_parms[0].info) == B1_RTP)
-	    && (plci->adapter->man_profile.private_options & (1L << PRIVATE_RTP)))
-	{
-		plci->B1_resource = add_b1_facilities(plci, 31, (word)(b1_facilities & ~B1_FACILITY_VOICE));
-		adjust_b1_facilities(plci, plci->B1_resource, (word)(b1_facilities & ~B1_FACILITY_VOICE));
-		cai[1] = plci->B1_resource;
-		cai[2] = 0;
-		cai[3] = 0;
-		cai[4] = 0;
-		PUT_WORD(&cai[5], plci->appl->MaxDataLength);
-		for (i = 0; i < bp_parms[3].length; i++)
-			cai[7 + i] = bp_parms[3].info[1 + i];
-		cai[0] = 6 + bp_parms[3].length;
-		add_p(plci, CAI, cai);
-		return 0;
-	}
-
-
-	if ((GET_WORD(bp_parms[0].info) == B1_PIAFS)
-	    && (plci->adapter->man_profile.private_options & (1L << PRIVATE_PIAFS)))
-	{
-		plci->B1_resource = add_b1_facilities(plci, 35/* PIAFS HARDWARE FACILITY */, (word)(b1_facilities & ~B1_FACILITY_VOICE));
-		adjust_b1_facilities(plci, plci->B1_resource, (word)(b1_facilities & ~B1_FACILITY_VOICE));
-		cai[1] = plci->B1_resource;
-		cai[2] = 0;
-		cai[3] = 0;
-		cai[4] = 0;
-		PUT_WORD(&cai[5], plci->appl->MaxDataLength);
-		cai[0] = 6;
-		add_p(plci, CAI, cai);
-		return 0;
-	}
-
-
-	if ((GET_WORD(bp_parms[0].info) >= 32)
-	    || (!((1L << GET_WORD(bp_parms[0].info)) & plci->adapter->profile.B1_Protocols)
-		&& ((GET_WORD(bp_parms[0].info) != 3)
-		    || !((1L << B1_HDLC) & plci->adapter->profile.B1_Protocols)
-		    || ((bp_parms[3].length != 0) && (GET_WORD(&bp_parms[3].info[1]) != 0) && (GET_WORD(&bp_parms[3].info[1]) != 56000)))))
-	{
-		return _B1_NOT_SUPPORTED;
-	}
-	plci->B1_resource = add_b1_facilities(plci, resource[GET_WORD(bp_parms[0].info)],
-					      (word)(b1_facilities & ~B1_FACILITY_VOICE));
-	adjust_b1_facilities(plci, plci->B1_resource, (word)(b1_facilities & ~B1_FACILITY_VOICE));
-	cai[0] = 6;
-	cai[1] = plci->B1_resource;
-	for (i = 2; i < sizeof(cai); i++) cai[i] = 0;
-
-	if ((GET_WORD(bp_parms[0].info) == B1_MODEM_ALL_NEGOTIATE)
-	    || (GET_WORD(bp_parms[0].info) == B1_MODEM_ASYNC)
-	    || (GET_WORD(bp_parms[0].info) == B1_MODEM_SYNC_HDLC))
-	{ /* B1 - modem */
-		for (i = 0; i < 7; i++) mdm_cfg[i].length = 0;
-
-		if (bp_parms[3].length)
-		{
-			if (api_parse(&bp_parms[3].info[1], (word)bp_parms[3].length, "wwwwww", mdm_cfg))
-			{
-				return (_WRONG_MESSAGE_FORMAT);
-			}
-
-			cai[2] = 0; /* Bit rate for adaptation */
-
-			dbug(1, dprintf("MDM Max Bit Rate:<%d>", GET_WORD(mdm_cfg[0].info)));
-
-			PUT_WORD(&cai[13], 0);                          /* Min Tx speed */
-			PUT_WORD(&cai[15], GET_WORD(mdm_cfg[0].info)); /* Max Tx speed */
-			PUT_WORD(&cai[17], 0);                          /* Min Rx speed */
-			PUT_WORD(&cai[19], GET_WORD(mdm_cfg[0].info)); /* Max Rx speed */
-
-			cai[3] = 0; /* Async framing parameters */
-			switch (GET_WORD(mdm_cfg[2].info))
-			{       /* Parity     */
-			case 1: /* odd parity */
-				cai[3] |= (DSP_CAI_ASYNC_PARITY_ENABLE | DSP_CAI_ASYNC_PARITY_ODD);
-				dbug(1, dprintf("MDM: odd parity"));
-				break;
-
-			case 2: /* even parity */
-				cai[3] |= (DSP_CAI_ASYNC_PARITY_ENABLE | DSP_CAI_ASYNC_PARITY_EVEN);
-				dbug(1, dprintf("MDM: even parity"));
-				break;
-
-			default:
-				dbug(1, dprintf("MDM: no parity"));
-				break;
-			}
-
-			switch (GET_WORD(mdm_cfg[3].info))
-			{       /* stop bits   */
-			case 1: /* 2 stop bits */
-				cai[3] |= DSP_CAI_ASYNC_TWO_STOP_BITS;
-				dbug(1, dprintf("MDM: 2 stop bits"));
-				break;
-
-			default:
-				dbug(1, dprintf("MDM: 1 stop bit"));
-				break;
-			}
-
-			switch (GET_WORD(mdm_cfg[1].info))
-			{     /* char length */
-			case 5:
-				cai[3] |= DSP_CAI_ASYNC_CHAR_LENGTH_5;
-				dbug(1, dprintf("MDM: 5 bits"));
-				break;
-
-			case 6:
-				cai[3] |= DSP_CAI_ASYNC_CHAR_LENGTH_6;
-				dbug(1, dprintf("MDM: 6 bits"));
-				break;
-
-			case 7:
-				cai[3] |= DSP_CAI_ASYNC_CHAR_LENGTH_7;
-				dbug(1, dprintf("MDM: 7 bits"));
-				break;
-
-			default:
-				dbug(1, dprintf("MDM: 8 bits"));
-				break;
-			}
-
-			cai[7] = 0; /* Line taking options */
-			cai[8] = 0; /* Modulation negotiation options */
-			cai[9] = 0; /* Modulation options */
-
-			if (((plci->call_dir & CALL_DIR_ORIGINATE) != 0) ^ ((plci->call_dir & CALL_DIR_OUT) != 0))
-			{
-				cai[9] |= DSP_CAI_MODEM_REVERSE_DIRECTION;
-				dbug(1, dprintf("MDM: Reverse direction"));
-			}
-
-			if (GET_WORD(mdm_cfg[4].info) & MDM_CAPI_DISABLE_RETRAIN)
-			{
-				cai[9] |= DSP_CAI_MODEM_DISABLE_RETRAIN;
-				dbug(1, dprintf("MDM: Disable retrain"));
-			}
-
-			if (GET_WORD(mdm_cfg[4].info) & MDM_CAPI_DISABLE_RING_TONE)
-			{
-				cai[7] |= DSP_CAI_MODEM_DISABLE_CALLING_TONE | DSP_CAI_MODEM_DISABLE_ANSWER_TONE;
-				dbug(1, dprintf("MDM: Disable ring tone"));
-			}
-
-			if (GET_WORD(mdm_cfg[4].info) & MDM_CAPI_GUARD_1800)
-			{
-				cai[8] |= DSP_CAI_MODEM_GUARD_TONE_1800HZ;
-				dbug(1, dprintf("MDM: 1800 guard tone"));
-			}
-			else if (GET_WORD(mdm_cfg[4].info) & MDM_CAPI_GUARD_550)
-			{
-				cai[8] |= DSP_CAI_MODEM_GUARD_TONE_550HZ;
-				dbug(1, dprintf("MDM: 550 guard tone"));
-			}
-
-			if ((GET_WORD(mdm_cfg[5].info) & 0x00ff) == MDM_CAPI_NEG_V100)
-			{
-				cai[8] |= DSP_CAI_MODEM_NEGOTIATE_V100;
-				dbug(1, dprintf("MDM: V100"));
-			}
-			else if ((GET_WORD(mdm_cfg[5].info) & 0x00ff) == MDM_CAPI_NEG_MOD_CLASS)
-			{
-				cai[8] |= DSP_CAI_MODEM_NEGOTIATE_IN_CLASS;
-				dbug(1, dprintf("MDM: IN CLASS"));
-			}
-			else if ((GET_WORD(mdm_cfg[5].info) & 0x00ff) == MDM_CAPI_NEG_DISABLED)
-			{
-				cai[8] |= DSP_CAI_MODEM_NEGOTIATE_DISABLED;
-				dbug(1, dprintf("MDM: DISABLED"));
-			}
-			cai[0] = 20;
-
-			if ((plci->adapter->man_profile.private_options & (1L << PRIVATE_V18))
-			    && (GET_WORD(mdm_cfg[5].info) & 0x8000)) /* Private V.18 enable */
-			{
-				plci->requested_options |= 1L << PRIVATE_V18;
-			}
-			if (GET_WORD(mdm_cfg[5].info) & 0x4000) /* Private VOWN enable */
-				plci->requested_options |= 1L << PRIVATE_VOWN;
-
-			if ((plci->requested_options_conn | plci->requested_options | plci->adapter->requested_options_table[plci->appl->Id - 1])
-			    & ((1L << PRIVATE_V18) | (1L << PRIVATE_VOWN)))
-			{
-				if (!api_parse(&bp_parms[3].info[1], (word)bp_parms[3].length, "wwwwwws", mdm_cfg))
-				{
-					i = 27;
-					if (mdm_cfg[6].length >= 4)
-					{
-						d = GET_DWORD(&mdm_cfg[6].info[1]);
-						cai[7] |= (byte) d;          /* line taking options */
-						cai[9] |= (byte)(d >> 8);    /* modulation options */
-						cai[++i] = (byte)(d >> 16);  /* vown modulation options */
-						cai[++i] = (byte)(d >> 24);
-						if (mdm_cfg[6].length >= 8)
-						{
-							d = GET_DWORD(&mdm_cfg[6].info[5]);
-							cai[10] |= (byte) d;        /* disabled modulations mask */
-							cai[11] |= (byte)(d >> 8);
-							if (mdm_cfg[6].length >= 12)
-							{
-								d = GET_DWORD(&mdm_cfg[6].info[9]);
-								cai[12] = (byte) d;          /* enabled modulations mask */
-								cai[++i] = (byte)(d >> 8);   /* vown enabled modulations */
-								cai[++i] = (byte)(d >> 16);
-								cai[++i] = (byte)(d >> 24);
-								cai[++i] = 0;
-								if (mdm_cfg[6].length >= 14)
-								{
-									w = GET_WORD(&mdm_cfg[6].info[13]);
-									if (w != 0)
-										PUT_WORD(&cai[13], w);  /* min tx speed */
-									if (mdm_cfg[6].length >= 16)
-									{
-										w = GET_WORD(&mdm_cfg[6].info[15]);
-										if (w != 0)
-											PUT_WORD(&cai[15], w);  /* max tx speed */
-										if (mdm_cfg[6].length >= 18)
-										{
-											w = GET_WORD(&mdm_cfg[6].info[17]);
-											if (w != 0)
-												PUT_WORD(&cai[17], w);  /* min rx speed */
-											if (mdm_cfg[6].length >= 20)
-											{
-												w = GET_WORD(&mdm_cfg[6].info[19]);
-												if (w != 0)
-													PUT_WORD(&cai[19], w);  /* max rx speed */
-												if (mdm_cfg[6].length >= 22)
-												{
-													w = GET_WORD(&mdm_cfg[6].info[21]);
-													cai[23] = (byte)(-((short) w));  /* transmit level */
-													if (mdm_cfg[6].length >= 24)
-													{
-														w = GET_WORD(&mdm_cfg[6].info[23]);
-														cai[22] |= (byte) w;        /* info options mask */
-														cai[21] |= (byte)(w >> 8);  /* disabled symbol rates */
-													}
-												}
-											}
-										}
-									}
-								}
-							}
-						}
-					}
-					cai[27] = i - 27;
-					i++;
-					if (!api_parse(&bp_parms[3].info[1], (word)bp_parms[3].length, "wwwwwwss", mdm_cfg))
-					{
-						if (!api_parse(&mdm_cfg[7].info[1], (word)mdm_cfg[7].length, "sss", mdm_cfg_v18))
-						{
-							for (n = 0; n < 3; n++)
-							{
-								cai[i] = (byte)(mdm_cfg_v18[n].length);
-								for (j = 1; j < ((word)(cai[i] + 1)); j++)
-									cai[i + j] = mdm_cfg_v18[n].info[j];
-								i += cai[i] + 1;
-							}
-						}
-					}
-					cai[0] = (byte)(i - 1);
-				}
-			}
-
-		}
-	}
-	if (GET_WORD(bp_parms[0].info) == 2 ||                         /* V.110 async */
-	    GET_WORD(bp_parms[0].info) == 3)                           /* V.110 sync */
-	{
-		if (bp_parms[3].length) {
-			dbug(1, dprintf("V.110,%d", GET_WORD(&bp_parms[3].info[1])));
-			switch (GET_WORD(&bp_parms[3].info[1])) {                 /* Rate */
-			case 0:
-			case 56000:
-				if (GET_WORD(bp_parms[0].info) == 3) {                  /* V.110 sync 56k */
-					dbug(1, dprintf("56k sync HSCX"));
-					cai[1] = 8;
-					cai[2] = 0;
-					cai[3] = 0;
-				}
-				else if (GET_WORD(bp_parms[0].info) == 2) {
-					dbug(1, dprintf("56k async DSP"));
-					cai[2] = 9;
-				}
-				break;
-			case 50:     cai[2] = 1;  break;
-			case 75:     cai[2] = 1;  break;
-			case 110:    cai[2] = 1;  break;
-			case 150:    cai[2] = 1;  break;
-			case 200:    cai[2] = 1;  break;
-			case 300:    cai[2] = 1;  break;
-			case 600:    cai[2] = 1;  break;
-			case 1200:   cai[2] = 2;  break;
-			case 2400:   cai[2] = 3;  break;
-			case 4800:   cai[2] = 4;  break;
-			case 7200:   cai[2] = 10; break;
-			case 9600:   cai[2] = 5;  break;
-			case 12000:  cai[2] = 13; break;
-			case 24000:  cai[2] = 0;  break;
-			case 14400:  cai[2] = 11; break;
-			case 19200:  cai[2] = 6;  break;
-			case 28800:  cai[2] = 12; break;
-			case 38400:  cai[2] = 7;  break;
-			case 48000:  cai[2] = 8;  break;
-			case 76:     cai[2] = 15; break;  /* 75/1200     */
-			case 1201:   cai[2] = 14; break;  /* 1200/75     */
-			case 56001:  cai[2] = 9;  break;  /* V.110 56000 */
-
-			default:
-				return _B1_PARM_NOT_SUPPORTED;
-			}
-			cai[3] = 0;
-			if (cai[1] == 13)                                        /* v.110 async */
-			{
-				if (bp_parms[3].length >= 8)
-				{
-					switch (GET_WORD(&bp_parms[3].info[3]))
-					{       /* char length */
-					case 5:
-						cai[3] |= DSP_CAI_ASYNC_CHAR_LENGTH_5;
-						break;
-					case 6:
-						cai[3] |= DSP_CAI_ASYNC_CHAR_LENGTH_6;
-						break;
-					case 7:
-						cai[3] |= DSP_CAI_ASYNC_CHAR_LENGTH_7;
-						break;
-					}
-					switch (GET_WORD(&bp_parms[3].info[5]))
-					{       /* Parity     */
-					case 1: /* odd parity */
-						cai[3] |= (DSP_CAI_ASYNC_PARITY_ENABLE | DSP_CAI_ASYNC_PARITY_ODD);
-						break;
-					case 2: /* even parity */
-						cai[3] |= (DSP_CAI_ASYNC_PARITY_ENABLE | DSP_CAI_ASYNC_PARITY_EVEN);
-						break;
-					}
-					switch (GET_WORD(&bp_parms[3].info[7]))
-					{       /* stop bits   */
-					case 1: /* 2 stop bits */
-						cai[3] |= DSP_CAI_ASYNC_TWO_STOP_BITS;
-						break;
-					}
-				}
-			}
-		}
-		else if (cai[1] == 8 || GET_WORD(bp_parms[0].info) == 3) {
-			dbug(1, dprintf("V.110 default 56k sync"));
-			cai[1] = 8;
-			cai[2] = 0;
-			cai[3] = 0;
-		}
-		else {
-			dbug(1, dprintf("V.110 default 9600 async"));
-			cai[2] = 5;
-		}
-	}
-	PUT_WORD(&cai[5], plci->appl->MaxDataLength);
-	dbug(1, dprintf("CAI[%d]=%x,%x,%x,%x,%x,%x", cai[0], cai[1], cai[2], cai[3], cai[4], cai[5], cai[6]));
-/* HexDump ("CAI", sizeof(cai), &cai[0]); */
-
-	add_p(plci, CAI, cai);
-	return 0;
-}
-
-/*------------------------------------------------------------------*/
-/* put parameter for b2 and B3  protocol in the parameter buffer    */
-/*------------------------------------------------------------------*/
-
-static word add_b23(PLCI *plci, API_PARSE *bp)
-{
-	word i, fax_control_bits;
-	byte pos, len;
-	byte SAPI = 0x40;  /* default SAPI 16 for x.31 */
-	API_PARSE bp_parms[8];
-	API_PARSE *b1_config;
-	API_PARSE *b2_config;
-	API_PARSE b2_config_parms[8];
-	API_PARSE *b3_config;
-	API_PARSE b3_config_parms[6];
-	API_PARSE global_config[2];
-
-	static byte llc[3] = {2,0,0};
-	static byte dlc[20] = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0};
-	static byte nlc[256];
-	static byte lli[12] = {1,1};
-
-	const byte llc2_out[] = {1,2,4,6,2,0,0,0, X75_V42BIS,V120_L2,V120_V42BIS,V120_L2,6};
-	const byte llc2_in[]  = {1,3,4,6,3,0,0,0, X75_V42BIS,V120_L2,V120_V42BIS,V120_L2,6};
-
-	const byte llc3[] = {4,3,2,2,6,6,0};
-	const byte header[] = {0,2,3,3,0,0,0};
-
-	for (i = 0; i < 8; i++) bp_parms[i].length = 0;
-	for (i = 0; i < 6; i++) b2_config_parms[i].length = 0;
-	for (i = 0; i < 5; i++) b3_config_parms[i].length = 0;
-
-	lli[0] = 1;
-	lli[1] = 1;
-	if (plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_XONOFF_FLOW_CONTROL)
-		lli[1] |= 2;
-	if (plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_OOB_CHANNEL)
-		lli[1] |= 4;
-
-	if ((lli[1] & 0x02) && (diva_xdi_extended_features & DIVA_CAPI_USE_CMA)) {
-		lli[1] |= 0x10;
-		if (plci->rx_dma_descriptor <= 0) {
-			plci->rx_dma_descriptor = diva_get_dma_descriptor(plci, &plci->rx_dma_magic);
-			if (plci->rx_dma_descriptor >= 0)
-				plci->rx_dma_descriptor++;
-		}
-		if (plci->rx_dma_descriptor > 0) {
-			lli[0] = 6;
-			lli[1] |= 0x40;
-			lli[2] = (byte)(plci->rx_dma_descriptor - 1);
-			lli[3] = (byte)plci->rx_dma_magic;
-			lli[4] = (byte)(plci->rx_dma_magic >>  8);
-			lli[5] = (byte)(plci->rx_dma_magic >> 16);
-			lli[6] = (byte)(plci->rx_dma_magic >> 24);
-		}
-	}
-
-	if (DIVA_CAPI_SUPPORTS_NO_CANCEL(plci->adapter)) {
-		lli[1] |= 0x20;
-	}
-
-	dbug(1, dprintf("add_b23"));
-	api_save_msg(bp, "s", &plci->B_protocol);
-
-	if (!bp->length && plci->tel)
-	{
-		plci->adv_nl = true;
-		dbug(1, dprintf("Default adv.Nl"));
-		add_p(plci, LLI, lli);
-		plci->B2_prot = 1 /*XPARENT*/;
-		plci->B3_prot = 0 /*XPARENT*/;
-		llc[1] = 2;
-		llc[2] = 4;
-		add_p(plci, LLC, llc);
-		dlc[0] = 2;
-		PUT_WORD(&dlc[1], plci->appl->MaxDataLength);
-		add_p(plci, DLC, dlc);
-		return 0;
-	}
-
-	if (!bp->length) /*default*/
-	{
-		dbug(1, dprintf("ret default"));
-		add_p(plci, LLI, lli);
-		plci->B2_prot = 0 /*X.75   */;
-		plci->B3_prot = 0 /*XPARENT*/;
-		llc[1] = 1;
-		llc[2] = 4;
-		add_p(plci, LLC, llc);
-		dlc[0] = 2;
-		PUT_WORD(&dlc[1], plci->appl->MaxDataLength);
-		add_p(plci, DLC, dlc);
-		return 0;
-	}
-	dbug(1, dprintf("b_prot_len=%d", (word)bp->length));
-	if ((word)bp->length > 256)    return _WRONG_MESSAGE_FORMAT;
-
-	if (api_parse(&bp->info[1], (word)bp->length, "wwwsssb", bp_parms))
-	{
-		bp_parms[6].length = 0;
-		if (api_parse(&bp->info[1], (word)bp->length, "wwwsss", bp_parms))
-		{
-			dbug(1, dprintf("b-form.!"));
-			return _WRONG_MESSAGE_FORMAT;
-		}
-	}
-	else if (api_parse(&bp->info[1], (word)bp->length, "wwwssss", bp_parms))
-	{
-		dbug(1, dprintf("b-form.!"));
-		return _WRONG_MESSAGE_FORMAT;
-	}
-
-	if (plci->tel == ADV_VOICE) /* transparent B on advanced voice */
-	{
-		if (GET_WORD(bp_parms[1].info) != 1
-		    || GET_WORD(bp_parms[2].info) != 0) return _B2_NOT_SUPPORTED;
-		plci->adv_nl = true;
-	}
-	else if (plci->tel) return _B2_NOT_SUPPORTED;
-
-
-	if ((GET_WORD(bp_parms[1].info) == B2_RTP)
-	    && (GET_WORD(bp_parms[2].info) == B3_RTP)
-	    && (plci->adapter->man_profile.private_options & (1L << PRIVATE_RTP)))
-	{
-		add_p(plci, LLI, lli);
-		plci->B2_prot = (byte) GET_WORD(bp_parms[1].info);
-		plci->B3_prot = (byte) GET_WORD(bp_parms[2].info);
-		llc[1] = (plci->call_dir & (CALL_DIR_ORIGINATE | CALL_DIR_FORCE_OUTG_NL)) ? 14 : 13;
-		llc[2] = 4;
-		add_p(plci, LLC, llc);
-		dlc[0] = 2;
-		PUT_WORD(&dlc[1], plci->appl->MaxDataLength);
-		dlc[3] = 3; /* Addr A */
-		dlc[4] = 1; /* Addr B */
-		dlc[5] = 7; /* modulo mode */
-		dlc[6] = 7; /* window size */
-		dlc[7] = 0; /* XID len Lo  */
-		dlc[8] = 0; /* XID len Hi  */
-		for (i = 0; i < bp_parms[4].length; i++)
-			dlc[9 + i] = bp_parms[4].info[1 + i];
-		dlc[0] = (byte)(8 + bp_parms[4].length);
-		add_p(plci, DLC, dlc);
-		for (i = 0; i < bp_parms[5].length; i++)
-			nlc[1 + i] = bp_parms[5].info[1 + i];
-		nlc[0] = (byte)(bp_parms[5].length);
-		add_p(plci, NLC, nlc);
-		return 0;
-	}
-
-
-
-	if ((GET_WORD(bp_parms[1].info) >= 32)
-	    || (!((1L << GET_WORD(bp_parms[1].info)) & plci->adapter->profile.B2_Protocols)
-		&& ((GET_WORD(bp_parms[1].info) != B2_PIAFS)
-		    || !(plci->adapter->man_profile.private_options & (1L << PRIVATE_PIAFS)))))
-
-	{
-		return _B2_NOT_SUPPORTED;
-	}
-	if ((GET_WORD(bp_parms[2].info) >= 32)
-	    || !((1L << GET_WORD(bp_parms[2].info)) & plci->adapter->profile.B3_Protocols))
-	{
-		return _B3_NOT_SUPPORTED;
-	}
-	if ((GET_WORD(bp_parms[1].info) != B2_SDLC)
-	    && ((GET_WORD(bp_parms[0].info) == B1_MODEM_ALL_NEGOTIATE)
-		|| (GET_WORD(bp_parms[0].info) == B1_MODEM_ASYNC)
-		|| (GET_WORD(bp_parms[0].info) == B1_MODEM_SYNC_HDLC)))
-	{
-		return (add_modem_b23(plci, bp_parms));
-	}
-
-	add_p(plci, LLI, lli);
-
-	plci->B2_prot = (byte)GET_WORD(bp_parms[1].info);
-	plci->B3_prot = (byte)GET_WORD(bp_parms[2].info);
-	if (plci->B2_prot == 12) SAPI = 0; /* default SAPI D-channel */
-
-	if (bp_parms[6].length)
-	{
-		if (api_parse(&bp_parms[6].info[1], (word)bp_parms[6].length, "w", global_config))
-		{
-			return _WRONG_MESSAGE_FORMAT;
-		}
-		switch (GET_WORD(global_config[0].info))
-		{
-		case 1:
-			plci->call_dir = (plci->call_dir & ~CALL_DIR_ANSWER) | CALL_DIR_ORIGINATE;
-			break;
-		case 2:
-			plci->call_dir = (plci->call_dir & ~CALL_DIR_ORIGINATE) | CALL_DIR_ANSWER;
-			break;
-		}
-	}
-	dbug(1, dprintf("call_dir=%04x", plci->call_dir));
-
-
-	if (plci->B2_prot == B2_PIAFS)
-		llc[1] = PIAFS_CRC;
-	else
-/* IMPLEMENT_PIAFS */
-	{
-		llc[1] = (plci->call_dir & (CALL_DIR_ORIGINATE | CALL_DIR_FORCE_OUTG_NL)) ?
-			llc2_out[GET_WORD(bp_parms[1].info)] : llc2_in[GET_WORD(bp_parms[1].info)];
-	}
-	llc[2] = llc3[GET_WORD(bp_parms[2].info)];
-
-	add_p(plci, LLC, llc);
-
-	dlc[0] = 2;
-	PUT_WORD(&dlc[1], plci->appl->MaxDataLength +
-		 header[GET_WORD(bp_parms[2].info)]);
-
-	b1_config = &bp_parms[3];
-	nlc[0] = 0;
-	if (plci->B3_prot == 4
-	    || plci->B3_prot == 5)
-	{
-		for (i = 0; i < sizeof(T30_INFO); i++) nlc[i] = 0;
-		nlc[0] = sizeof(T30_INFO);
-		if (plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_FAX_PAPER_FORMATS)
-			((T30_INFO *)&nlc[1])->operating_mode = T30_OPERATING_MODE_CAPI;
-		((T30_INFO *)&nlc[1])->rate_div_2400 = 0xff;
-		if (b1_config->length >= 2)
-		{
-			((T30_INFO *)&nlc[1])->rate_div_2400 = (byte)(GET_WORD(&b1_config->info[1]) / 2400);
-		}
-	}
-	b2_config = &bp_parms[4];
-
-
-	if (llc[1] == PIAFS_CRC)
-	{
-		if (plci->B3_prot != B3_TRANSPARENT)
-		{
-			return _B_STACK_NOT_SUPPORTED;
-		}
-		if (b2_config->length && api_parse(&b2_config->info[1], (word)b2_config->length, "bwww", b2_config_parms)) {
-			return _WRONG_MESSAGE_FORMAT;
-		}
-		PUT_WORD(&dlc[1], plci->appl->MaxDataLength);
-		dlc[3] = 0; /* Addr A */
-		dlc[4] = 0; /* Addr B */
-		dlc[5] = 0; /* modulo mode */
-		dlc[6] = 0; /* window size */
-		if (b2_config->length >= 7) {
-			dlc[7] = 7;
-			dlc[8] = 0;
-			dlc[9] = b2_config_parms[0].info[0]; /* PIAFS protocol Speed configuration */
-			dlc[10] = b2_config_parms[1].info[0]; /* V.42bis P0 */
-			dlc[11] = b2_config_parms[1].info[1]; /* V.42bis P0 */
-			dlc[12] = b2_config_parms[2].info[0]; /* V.42bis P1 */
-			dlc[13] = b2_config_parms[2].info[1]; /* V.42bis P1 */
-			dlc[14] = b2_config_parms[3].info[0]; /* V.42bis P2 */
-			dlc[15] = b2_config_parms[3].info[1]; /* V.42bis P2 */
-			dlc[0] = 15;
-			if (b2_config->length >= 8) { /* PIAFS control abilities */
-				dlc[7] = 10;
-				dlc[16] = 2; /* Length of PIAFS extension */
-				dlc[17] = PIAFS_UDATA_ABILITIES; /* control (UDATA) ability */
-				dlc[18] = b2_config_parms[4].info[0]; /* value */
-				dlc[0] = 18;
-			}
-		}
-		else /* default values, 64K, variable, no compression */
-		{
-			dlc[7] = 7;
-			dlc[8] = 0;
-			dlc[9] = 0x03; /* PIAFS protocol Speed configuration */
-			dlc[10] = 0x03; /* V.42bis P0 */
-			dlc[11] = 0;    /* V.42bis P0 */
-			dlc[12] = 0;    /* V.42bis P1 */
-			dlc[13] = 0;    /* V.42bis P1 */
-			dlc[14] = 0;    /* V.42bis P2 */
-			dlc[15] = 0;    /* V.42bis P2 */
-			dlc[0] = 15;
-		}
-		add_p(plci, DLC, dlc);
-	}
-	else
-
-		if ((llc[1] == V120_L2) || (llc[1] == V120_V42BIS))
-		{
-			if (plci->B3_prot != B3_TRANSPARENT)
-				return _B_STACK_NOT_SUPPORTED;
-
-			dlc[0] = 6;
-			PUT_WORD(&dlc[1], GET_WORD(&dlc[1]) + 2);
-			dlc[3] = 0x08;
-			dlc[4] = 0x01;
-			dlc[5] = 127;
-			dlc[6] = 7;
-			if (b2_config->length != 0)
-			{
-				if ((llc[1] == V120_V42BIS) && api_parse(&b2_config->info[1], (word)b2_config->length, "bbbbwww", b2_config_parms)) {
-					return _WRONG_MESSAGE_FORMAT;
-				}
-				dlc[3] = (byte)((b2_config->info[2] << 3) | ((b2_config->info[1] >> 5) & 0x04));
-				dlc[4] = (byte)((b2_config->info[1] << 1) | 0x01);
-				if (b2_config->info[3] != 128)
-				{
-					dbug(1, dprintf("1D-dlc= %x %x %x %x %x", dlc[0], dlc[1], dlc[2], dlc[3], dlc[4]));
-					return _B2_PARM_NOT_SUPPORTED;
-				}
-				dlc[5] = (byte)(b2_config->info[3] - 1);
-				dlc[6] = b2_config->info[4];
-				if (llc[1] == V120_V42BIS) {
-					if (b2_config->length >= 10) {
-						dlc[7] = 6;
-						dlc[8] = 0;
-						dlc[9] = b2_config_parms[4].info[0];
-						dlc[10] = b2_config_parms[4].info[1];
-						dlc[11] = b2_config_parms[5].info[0];
-						dlc[12] = b2_config_parms[5].info[1];
-						dlc[13] = b2_config_parms[6].info[0];
-						dlc[14] = b2_config_parms[6].info[1];
-						dlc[0] = 14;
-						dbug(1, dprintf("b2_config_parms[4].info[0] [1]:  %x %x", b2_config_parms[4].info[0], b2_config_parms[4].info[1]));
-						dbug(1, dprintf("b2_config_parms[5].info[0] [1]:  %x %x", b2_config_parms[5].info[0], b2_config_parms[5].info[1]));
-						dbug(1, dprintf("b2_config_parms[6].info[0] [1]:  %x %x", b2_config_parms[6].info[0], b2_config_parms[6].info[1]));
-					}
-					else {
-						dlc[6] = 14;
-					}
-				}
-			}
-		}
-		else
-		{
-			if (b2_config->length)
-			{
-				dbug(1, dprintf("B2-Config"));
-				if (llc[1] == X75_V42BIS) {
-					if (api_parse(&b2_config->info[1], (word)b2_config->length, "bbbbwww", b2_config_parms))
-					{
-						return _WRONG_MESSAGE_FORMAT;
-					}
-				}
-				else {
-					if (api_parse(&b2_config->info[1], (word)b2_config->length, "bbbbs", b2_config_parms))
-					{
-						return _WRONG_MESSAGE_FORMAT;
-					}
-				}
-				/* if B2 Protocol is LAPD, b2_config structure is different */
-				if (llc[1] == 6)
-				{
-					dlc[0] = 4;
-					if (b2_config->length >= 1) dlc[2] = b2_config->info[1];      /* TEI */
-					else dlc[2] = 0x01;
-					if ((b2_config->length >= 2) && (plci->B2_prot == 12))
-					{
-						SAPI = b2_config->info[2];    /* SAPI */
-					}
-					dlc[1] = SAPI;
-					if ((b2_config->length >= 3) && (b2_config->info[3] == 128))
-					{
-						dlc[3] = 127;      /* Mode */
-					}
-					else
-					{
-						dlc[3] = 7;        /* Mode */
-					}
-
-					if (b2_config->length >= 4) dlc[4] = b2_config->info[4];      /* Window */
-					else dlc[4] = 1;
-					dbug(1, dprintf("D-dlc[%d]=%x,%x,%x,%x", dlc[0], dlc[1], dlc[2], dlc[3], dlc[4]));
-					if (b2_config->length > 5) return _B2_PARM_NOT_SUPPORTED;
-				}
-				else
-				{
-					dlc[0] = (byte)(b2_config_parms[4].length + 6);
-					dlc[3] = b2_config->info[1];
-					dlc[4] = b2_config->info[2];
-					if (b2_config->info[3] != 8 && b2_config->info[3] != 128) {
-						dbug(1, dprintf("1D-dlc= %x %x %x %x %x", dlc[0], dlc[1], dlc[2], dlc[3], dlc[4]));
-						return _B2_PARM_NOT_SUPPORTED;
-					}
-
-					dlc[5] = (byte)(b2_config->info[3] - 1);
-					dlc[6] = b2_config->info[4];
-					if (dlc[6] > dlc[5]) {
-						dbug(1, dprintf("2D-dlc= %x %x %x %x %x %x %x", dlc[0], dlc[1], dlc[2], dlc[3], dlc[4], dlc[5], dlc[6]));
-						return _B2_PARM_NOT_SUPPORTED;
-					}
-
-					if (llc[1] == X75_V42BIS) {
-						if (b2_config->length >= 10) {
-							dlc[7] = 6;
-							dlc[8] = 0;
-							dlc[9] = b2_config_parms[4].info[0];
-							dlc[10] = b2_config_parms[4].info[1];
-							dlc[11] = b2_config_parms[5].info[0];
-							dlc[12] = b2_config_parms[5].info[1];
-							dlc[13] = b2_config_parms[6].info[0];
-							dlc[14] = b2_config_parms[6].info[1];
-							dlc[0] = 14;
-							dbug(1, dprintf("b2_config_parms[4].info[0] [1]:  %x %x", b2_config_parms[4].info[0], b2_config_parms[4].info[1]));
-							dbug(1, dprintf("b2_config_parms[5].info[0] [1]:  %x %x", b2_config_parms[5].info[0], b2_config_parms[5].info[1]));
-							dbug(1, dprintf("b2_config_parms[6].info[0] [1]:  %x %x", b2_config_parms[6].info[0], b2_config_parms[6].info[1]));
-						}
-						else {
-							dlc[6] = 14;
-						}
-
-					}
-					else {
-						PUT_WORD(&dlc[7], (word)b2_config_parms[4].length);
-						for (i = 0; i < b2_config_parms[4].length; i++)
-							dlc[11 + i] = b2_config_parms[4].info[1 + i];
-					}
-				}
-			}
-		}
-	add_p(plci, DLC, dlc);
-
-	b3_config = &bp_parms[5];
-	if (b3_config->length)
-	{
-		if (plci->B3_prot == 4
-		    || plci->B3_prot == 5)
-		{
-			if (api_parse(&b3_config->info[1], (word)b3_config->length, "wwss", b3_config_parms))
-			{
-				return _WRONG_MESSAGE_FORMAT;
-			}
-			i = GET_WORD((byte *)(b3_config_parms[0].info));
-			((T30_INFO *)&nlc[1])->resolution = (byte)(((i & 0x0001) ||
-								    ((plci->B3_prot == 4) && (((byte)(GET_WORD((byte *)b3_config_parms[1].info))) != 5))) ? T30_RESOLUTION_R8_0770_OR_200 : 0);
-			((T30_INFO *)&nlc[1])->data_format = (byte)(GET_WORD((byte *)b3_config_parms[1].info));
-			fax_control_bits = T30_CONTROL_BIT_ALL_FEATURES;
-			if ((((T30_INFO *)&nlc[1])->rate_div_2400 != 0) && (((T30_INFO *)&nlc[1])->rate_div_2400 <= 6))
-				fax_control_bits &= ~T30_CONTROL_BIT_ENABLE_V34FAX;
-			if (plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_FAX_PAPER_FORMATS)
-			{
-
-				if ((plci->requested_options_conn | plci->requested_options | plci->adapter->requested_options_table[plci->appl->Id - 1])
-				    & (1L << PRIVATE_FAX_PAPER_FORMATS))
-				{
-					((T30_INFO *)&nlc[1])->resolution |= T30_RESOLUTION_R8_1540 |
-						T30_RESOLUTION_R16_1540_OR_400 | T30_RESOLUTION_300_300 |
-						T30_RESOLUTION_INCH_BASED | T30_RESOLUTION_METRIC_BASED;
-				}
-
-				((T30_INFO *)&nlc[1])->recording_properties =
-					T30_RECORDING_WIDTH_ISO_A3 |
-					(T30_RECORDING_LENGTH_UNLIMITED << 2) |
-					(T30_MIN_SCANLINE_TIME_00_00_00 << 4);
-			}
-			if (plci->B3_prot == 5)
-			{
-				if (i & 0x0002) /* Accept incoming fax-polling requests */
-					fax_control_bits |= T30_CONTROL_BIT_ACCEPT_POLLING;
-				if (i & 0x2000) /* Do not use MR compression */
-					fax_control_bits &= ~T30_CONTROL_BIT_ENABLE_2D_CODING;
-				if (i & 0x4000) /* Do not use MMR compression */
-					fax_control_bits &= ~T30_CONTROL_BIT_ENABLE_T6_CODING;
-				if (i & 0x8000) /* Do not use ECM */
-					fax_control_bits &= ~T30_CONTROL_BIT_ENABLE_ECM;
-				if (plci->fax_connect_info_length != 0)
-				{
-					((T30_INFO *)&nlc[1])->resolution = ((T30_INFO *)plci->fax_connect_info_buffer)->resolution;
-					((T30_INFO *)&nlc[1])->data_format = ((T30_INFO *)plci->fax_connect_info_buffer)->data_format;
-					((T30_INFO *)&nlc[1])->recording_properties = ((T30_INFO *)plci->fax_connect_info_buffer)->recording_properties;
-					fax_control_bits |= GET_WORD(&((T30_INFO *)plci->fax_connect_info_buffer)->control_bits_low) &
-						(T30_CONTROL_BIT_REQUEST_POLLING | T30_CONTROL_BIT_MORE_DOCUMENTS);
-				}
-			}
-			/* copy station id to NLC */
-			for (i = 0; i < T30_MAX_STATION_ID_LENGTH; i++)
-			{
-				if (i < b3_config_parms[2].length)
-				{
-					((T30_INFO *)&nlc[1])->station_id[i] = ((byte *)b3_config_parms[2].info)[1 + i];
-				}
-				else
-				{
-					((T30_INFO *)&nlc[1])->station_id[i] = ' ';
-				}
-			}
-			((T30_INFO *)&nlc[1])->station_id_len = T30_MAX_STATION_ID_LENGTH;
-			/* copy head line to NLC */
-			if (b3_config_parms[3].length)
-			{
-
-				pos = (byte)(fax_head_line_time(&(((T30_INFO *)&nlc[1])->station_id[T30_MAX_STATION_ID_LENGTH])));
-				if (pos != 0)
-				{
-					if (CAPI_MAX_DATE_TIME_LENGTH + 2 + b3_config_parms[3].length > CAPI_MAX_HEAD_LINE_SPACE)
-						pos = 0;
-					else
-					{
-						nlc[1 + offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH + pos++] = ' ';
-						nlc[1 + offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH + pos++] = ' ';
-						len = (byte)b3_config_parms[2].length;
-						if (len > 20)
-							len = 20;
-						if (CAPI_MAX_DATE_TIME_LENGTH + 2 + len + 2 + b3_config_parms[3].length <= CAPI_MAX_HEAD_LINE_SPACE)
-						{
-							for (i = 0; i < len; i++)
-								nlc[1 + offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH + pos++] = ((byte *)b3_config_parms[2].info)[1 + i];
-							nlc[1 + offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH + pos++] = ' ';
-							nlc[1 + offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH + pos++] = ' ';
-						}
-					}
-				}
-
-				len = (byte)b3_config_parms[3].length;
-				if (len > CAPI_MAX_HEAD_LINE_SPACE - pos)
-					len = (byte)(CAPI_MAX_HEAD_LINE_SPACE - pos);
-				((T30_INFO *)&nlc[1])->head_line_len = (byte)(pos + len);
-				nlc[0] += (byte)(pos + len);
-				for (i = 0; i < len; i++)
-					nlc[1 + offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH + pos++] =  ((byte *)b3_config_parms[3].info)[1 + i];
-			} else
-				((T30_INFO *)&nlc[1])->head_line_len = 0;
-
-			plci->nsf_control_bits = 0;
-			if (plci->B3_prot == 5)
-			{
-				if ((plci->adapter->man_profile.private_options & (1L << PRIVATE_FAX_SUB_SEP_PWD))
-				    && (GET_WORD((byte *)b3_config_parms[1].info) & 0x8000)) /* Private SUB/SEP/PWD enable */
-				{
-					plci->requested_options |= 1L << PRIVATE_FAX_SUB_SEP_PWD;
-				}
-				if ((plci->adapter->man_profile.private_options & (1L << PRIVATE_FAX_NONSTANDARD))
-				    && (GET_WORD((byte *)b3_config_parms[1].info) & 0x4000)) /* Private non-standard facilities enable */
-				{
-					plci->requested_options |= 1L << PRIVATE_FAX_NONSTANDARD;
-				}
-				if ((plci->requested_options_conn | plci->requested_options | plci->adapter->requested_options_table[plci->appl->Id - 1])
-				    & ((1L << PRIVATE_FAX_SUB_SEP_PWD) | (1L << PRIVATE_FAX_NONSTANDARD)))
-				{
-					if ((plci->requested_options_conn | plci->requested_options | plci->adapter->requested_options_table[plci->appl->Id - 1])
-					    & (1L << PRIVATE_FAX_SUB_SEP_PWD))
-					{
-						fax_control_bits |= T30_CONTROL_BIT_ACCEPT_SUBADDRESS | T30_CONTROL_BIT_ACCEPT_PASSWORD;
-						if (fax_control_bits & T30_CONTROL_BIT_ACCEPT_POLLING)
-							fax_control_bits |= T30_CONTROL_BIT_ACCEPT_SEL_POLLING;
-					}
-					len = nlc[0];
-					pos = offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH;
-					if (pos < plci->fax_connect_info_length)
-					{
-						for (i = 1 + plci->fax_connect_info_buffer[pos]; i != 0; i--)
-							nlc[++len] = plci->fax_connect_info_buffer[pos++];
-					}
-					else
-						nlc[++len] = 0;
-					if (pos < plci->fax_connect_info_length)
-					{
-						for (i = 1 + plci->fax_connect_info_buffer[pos]; i != 0; i--)
-							nlc[++len] = plci->fax_connect_info_buffer[pos++];
-					}
-					else
-						nlc[++len] = 0;
-					if ((plci->requested_options_conn | plci->requested_options | plci->adapter->requested_options_table[plci->appl->Id - 1])
-					    & (1L << PRIVATE_FAX_NONSTANDARD))
-					{
-						if ((pos < plci->fax_connect_info_length) && (plci->fax_connect_info_buffer[pos] != 0))
-						{
-							if ((plci->fax_connect_info_buffer[pos] >= 3) && (plci->fax_connect_info_buffer[pos + 1] >= 2))
-								plci->nsf_control_bits = GET_WORD(&plci->fax_connect_info_buffer[pos + 2]);
-							for (i = 1 + plci->fax_connect_info_buffer[pos]; i != 0; i--)
-								nlc[++len] = plci->fax_connect_info_buffer[pos++];
-						}
-						else
-						{
-							if (api_parse(&b3_config->info[1], (word)b3_config->length, "wwsss", b3_config_parms))
-							{
-								dbug(1, dprintf("non-standard facilities info missing or wrong format"));
-								nlc[++len] = 0;
-							}
-							else
-							{
-								if ((b3_config_parms[4].length >= 3) && (b3_config_parms[4].info[1] >= 2))
-									plci->nsf_control_bits = GET_WORD(&b3_config_parms[4].info[2]);
-								nlc[++len] = (byte)(b3_config_parms[4].length);
-								for (i = 0; i < b3_config_parms[4].length; i++)
-									nlc[++len] = b3_config_parms[4].info[1 + i];
-							}
-						}
-					}
-					nlc[0] = len;
-					if ((plci->nsf_control_bits & T30_NSF_CONTROL_BIT_ENABLE_NSF)
-					    && (plci->nsf_control_bits & T30_NSF_CONTROL_BIT_NEGOTIATE_RESP))
-					{
-						((T30_INFO *)&nlc[1])->operating_mode = T30_OPERATING_MODE_CAPI_NEG;
-					}
-				}
-			}
-
-			PUT_WORD(&(((T30_INFO *)&nlc[1])->control_bits_low), fax_control_bits);
-			len = offsetof(T30_INFO, station_id) + T30_MAX_STATION_ID_LENGTH;
-			for (i = 0; i < len; i++)
-				plci->fax_connect_info_buffer[i] = nlc[1 + i];
-			((T30_INFO *) plci->fax_connect_info_buffer)->head_line_len = 0;
-			i += ((T30_INFO *)&nlc[1])->head_line_len;
-			while (i < nlc[0])
-				plci->fax_connect_info_buffer[len++] = nlc[++i];
-			plci->fax_connect_info_length = len;
-		}
-		else
-		{
-			nlc[0] = 14;
-			if (b3_config->length != 16)
-				return _B3_PARM_NOT_SUPPORTED;
-			for (i = 0; i < 12; i++) nlc[1 + i] = b3_config->info[1 + i];
-			if (GET_WORD(&b3_config->info[13]) != 8 && GET_WORD(&b3_config->info[13]) != 128)
-				return _B3_PARM_NOT_SUPPORTED;
-			nlc[13] = b3_config->info[13];
-			if (GET_WORD(&b3_config->info[15]) >= nlc[13])
-				return _B3_PARM_NOT_SUPPORTED;
-			nlc[14] = b3_config->info[15];
-		}
-	}
-	else
-	{
-		if (plci->B3_prot == 4
-		    || plci->B3_prot == 5 /*T.30 - FAX*/) return _B3_PARM_NOT_SUPPORTED;
-	}
-	add_p(plci, NLC, nlc);
-	return 0;
-}
-
-/*----------------------------------------------------------------*/
-/*      make the same as add_b23, but only for the modem related  */
-/*      L2 and L3 B-Chan protocol.                                */
-/*                                                                */
-/*      Enabled L2 and L3 Configurations:                         */
-/*        If L1 == Modem all negotiation                          */
-/*          only L2 == Modem with full negotiation is allowed     */
-/*        If L1 == Modem async or sync                            */
-/*          only L2 == Transparent is allowed                     */
-/*        L3 == Modem or L3 == Transparent are allowed            */
-/*      B2 Configuration for modem:                               */
-/*          word : enable/disable compression, bitoptions         */
-/*      B3 Configuration for modem:                               */
-/*          empty                                                 */
-/*----------------------------------------------------------------*/
-static word add_modem_b23(PLCI *plci, API_PARSE *bp_parms)
-{
-	static byte lli[12] = {1,1};
-	static byte llc[3] = {2,0,0};
-	static byte dlc[16] = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0};
-	API_PARSE mdm_config[2];
-	word i;
-	word b2_config = 0;
-
-	for (i = 0; i < 2; i++) mdm_config[i].length = 0;
-	for (i = 0; i < sizeof(dlc); i++) dlc[i] = 0;
-
-	if (((GET_WORD(bp_parms[0].info) == B1_MODEM_ALL_NEGOTIATE)
-	     && (GET_WORD(bp_parms[1].info) != B2_MODEM_EC_COMPRESSION))
-	    || ((GET_WORD(bp_parms[0].info) != B1_MODEM_ALL_NEGOTIATE)
-		&& (GET_WORD(bp_parms[1].info) != B2_TRANSPARENT)))
-	{
-		return (_B_STACK_NOT_SUPPORTED);
-	}
-	if ((GET_WORD(bp_parms[2].info) != B3_MODEM)
-	    && (GET_WORD(bp_parms[2].info) != B3_TRANSPARENT))
-	{
-		return (_B_STACK_NOT_SUPPORTED);
-	}
-
-	plci->B2_prot = (byte) GET_WORD(bp_parms[1].info);
-	plci->B3_prot = (byte) GET_WORD(bp_parms[2].info);
-
-	if ((GET_WORD(bp_parms[1].info) == B2_MODEM_EC_COMPRESSION) && bp_parms[4].length)
-	{
-		if (api_parse(&bp_parms[4].info[1],
-			      (word)bp_parms[4].length, "w",
-			      mdm_config))
-		{
-			return (_WRONG_MESSAGE_FORMAT);
-		}
-		b2_config = GET_WORD(mdm_config[0].info);
-	}
-
-	/* OK, L2 is modem */
-
-	lli[0] = 1;
-	lli[1] = 1;
-	if (plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_XONOFF_FLOW_CONTROL)
-		lli[1] |= 2;
-	if (plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_OOB_CHANNEL)
-		lli[1] |= 4;
-
-	if ((lli[1] & 0x02) && (diva_xdi_extended_features & DIVA_CAPI_USE_CMA)) {
-		lli[1] |= 0x10;
-		if (plci->rx_dma_descriptor <= 0) {
-			plci->rx_dma_descriptor = diva_get_dma_descriptor(plci, &plci->rx_dma_magic);
-			if (plci->rx_dma_descriptor >= 0)
-				plci->rx_dma_descriptor++;
-		}
-		if (plci->rx_dma_descriptor > 0) {
-			lli[1] |= 0x40;
-			lli[0] = 6;
-			lli[2] = (byte)(plci->rx_dma_descriptor - 1);
-			lli[3] = (byte)plci->rx_dma_magic;
-			lli[4] = (byte)(plci->rx_dma_magic >>  8);
-			lli[5] = (byte)(plci->rx_dma_magic >> 16);
-			lli[6] = (byte)(plci->rx_dma_magic >> 24);
-		}
-	}
-
-	if (DIVA_CAPI_SUPPORTS_NO_CANCEL(plci->adapter)) {
-		lli[1] |= 0x20;
-	}
-
-	llc[1] = (plci->call_dir & (CALL_DIR_ORIGINATE | CALL_DIR_FORCE_OUTG_NL)) ?
-		/*V42*/ 10 : /*V42_IN*/ 9;
-	llc[2] = 4;                      /* pass L3 always transparent */
-	add_p(plci, LLI, lli);
-	add_p(plci, LLC, llc);
-	i =  1;
-	PUT_WORD(&dlc[i], plci->appl->MaxDataLength);
-	i += 2;
-	if (GET_WORD(bp_parms[1].info) == B2_MODEM_EC_COMPRESSION)
-	{
-		if (bp_parms[4].length)
-		{
-			dbug(1, dprintf("MDM b2_config=%02x", b2_config));
-			dlc[i++] = 3; /* Addr A */
-			dlc[i++] = 1; /* Addr B */
-			dlc[i++] = 7; /* modulo mode */
-			dlc[i++] = 7; /* window size */
-			dlc[i++] = 0; /* XID len Lo  */
-			dlc[i++] = 0; /* XID len Hi  */
-
-			if (b2_config & MDM_B2_DISABLE_V42bis)
-			{
-				dlc[i] |= DLC_MODEMPROT_DISABLE_V42_V42BIS;
-			}
-			if (b2_config & MDM_B2_DISABLE_MNP)
-			{
-				dlc[i] |= DLC_MODEMPROT_DISABLE_MNP_MNP5;
-			}
-			if (b2_config & MDM_B2_DISABLE_TRANS)
-			{
-				dlc[i] |= DLC_MODEMPROT_REQUIRE_PROTOCOL;
-			}
-			if (b2_config & MDM_B2_DISABLE_V42)
-			{
-				dlc[i] |= DLC_MODEMPROT_DISABLE_V42_DETECT;
-			}
-			if (b2_config & MDM_B2_DISABLE_COMP)
-			{
-				dlc[i] |= DLC_MODEMPROT_DISABLE_COMPRESSION;
-			}
-			i++;
-		}
-	}
-	else
-	{
-		dlc[i++] = 3; /* Addr A */
-		dlc[i++] = 1; /* Addr B */
-		dlc[i++] = 7; /* modulo mode */
-		dlc[i++] = 7; /* window size */
-		dlc[i++] = 0; /* XID len Lo  */
-		dlc[i++] = 0; /* XID len Hi  */
-		dlc[i++] = DLC_MODEMPROT_DISABLE_V42_V42BIS |
-			DLC_MODEMPROT_DISABLE_MNP_MNP5 |
-			DLC_MODEMPROT_DISABLE_V42_DETECT |
-			DLC_MODEMPROT_DISABLE_COMPRESSION;
-	}
-	dlc[0] = (byte)(i - 1);
-/* HexDump ("DLC", sizeof(dlc), &dlc[0]); */
-	add_p(plci, DLC, dlc);
-	return (0);
-}
-
-
-/*------------------------------------------------------------------*/
-/* send a request for the signaling entity                          */
-/*------------------------------------------------------------------*/
-
-static void sig_req(PLCI *plci, byte req, byte Id)
-{
-	if (!plci) return;
-	if (plci->adapter->adapter_disabled) return;
-	dbug(1, dprintf("sig_req(%x)", req));
-	if (req == REMOVE)
-		plci->sig_remove_id = plci->Sig.Id;
-	if (plci->req_in == plci->req_in_start) {
-		plci->req_in += 2;
-		plci->RBuffer[plci->req_in++] = 0;
-	}
-	PUT_WORD(&plci->RBuffer[plci->req_in_start], plci->req_in-plci->req_in_start - 2);
-	plci->RBuffer[plci->req_in++] = Id;   /* sig/nl flag */
-	plci->RBuffer[plci->req_in++] = req;  /* request */
-	plci->RBuffer[plci->req_in++] = 0;    /* channel */
-	plci->req_in_start = plci->req_in;
-}
-
-/*------------------------------------------------------------------*/
-/* send a request for the network layer entity                      */
-/*------------------------------------------------------------------*/
-
-static void nl_req_ncci(PLCI *plci, byte req, byte ncci)
-{
-	if (!plci) return;
-	if (plci->adapter->adapter_disabled) return;
-	dbug(1, dprintf("nl_req %02x %02x %02x", plci->Id, req, ncci));
-	if (req == REMOVE)
-	{
-		plci->nl_remove_id = plci->NL.Id;
-		ncci_remove(plci, 0, (byte)(ncci != 0));
-		ncci = 0;
-	}
-	if (plci->req_in == plci->req_in_start) {
-		plci->req_in += 2;
-		plci->RBuffer[plci->req_in++] = 0;
-	}
-	PUT_WORD(&plci->RBuffer[plci->req_in_start], plci->req_in-plci->req_in_start - 2);
-	plci->RBuffer[plci->req_in++] = 1;    /* sig/nl flag */
-	plci->RBuffer[plci->req_in++] = req;  /* request */
-	plci->RBuffer[plci->req_in++] = plci->adapter->ncci_ch[ncci];   /* channel */
-	plci->req_in_start = plci->req_in;
-}
-
-static void send_req(PLCI *plci)
-{
-	ENTITY *e;
-	word l;
-/*  word i; */
-
-	if (!plci) return;
-	if (plci->adapter->adapter_disabled) return;
-	channel_xmit_xon(plci);
-
-	/* if nothing to do, return */
-	if (plci->req_in == plci->req_out) return;
-	dbug(1, dprintf("send_req(in=%d,out=%d)", plci->req_in, plci->req_out));
-
-	if (plci->nl_req || plci->sig_req) return;
-
-	l = GET_WORD(&plci->RBuffer[plci->req_out]);
-	plci->req_out += 2;
-	plci->XData[0].P = &plci->RBuffer[plci->req_out];
-	plci->req_out += l;
-	if (plci->RBuffer[plci->req_out] == 1)
-	{
-		e = &plci->NL;
-		plci->req_out++;
-		e->Req = plci->nl_req = plci->RBuffer[plci->req_out++];
-		e->ReqCh = plci->RBuffer[plci->req_out++];
-		if (!(e->Id & 0x1f))
-		{
-			e->Id = NL_ID;
-			plci->RBuffer[plci->req_out - 4] = CAI;
-			plci->RBuffer[plci->req_out - 3] = 1;
-			plci->RBuffer[plci->req_out - 2] = (plci->Sig.Id == 0xff) ? 0 : plci->Sig.Id;
-			plci->RBuffer[plci->req_out - 1] = 0;
-			l += 3;
-			plci->nl_global_req = plci->nl_req;
-		}
-		dbug(1, dprintf("%x:NLREQ(%x:%x:%x)", plci->adapter->Id, e->Id, e->Req, e->ReqCh));
-	}
-	else
-	{
-		e = &plci->Sig;
-		if (plci->RBuffer[plci->req_out])
-			e->Id = plci->RBuffer[plci->req_out];
-		plci->req_out++;
-		e->Req = plci->sig_req = plci->RBuffer[plci->req_out++];
-		e->ReqCh = plci->RBuffer[plci->req_out++];
-		if (!(e->Id & 0x1f))
-			plci->sig_global_req = plci->sig_req;
-		dbug(1, dprintf("%x:SIGREQ(%x:%x:%x)", plci->adapter->Id, e->Id, e->Req, e->ReqCh));
-	}
-	plci->XData[0].PLength = l;
-	e->X = plci->XData;
-	plci->adapter->request(e);
-	dbug(1, dprintf("send_ok"));
-}
-
-static void send_data(PLCI *plci)
-{
-	DIVA_CAPI_ADAPTER *a;
-	DATA_B3_DESC *data;
-	NCCI   *ncci_ptr;
-	word ncci;
-
-	if (!plci->nl_req && plci->ncci_ring_list)
-	{
-		a = plci->adapter;
-		ncci = plci->ncci_ring_list;
-		do
-		{
-			ncci = a->ncci_next[ncci];
-			ncci_ptr = &(a->ncci[ncci]);
-			if (!(a->ncci_ch[ncci]
-			      && (a->ch_flow_control[a->ncci_ch[ncci]] & N_OK_FC_PENDING)))
-			{
-				if (ncci_ptr->data_pending)
-				{
-					if ((a->ncci_state[ncci] == CONNECTED)
-					    || (a->ncci_state[ncci] == INC_ACT_PENDING)
-					    || (plci->send_disc == ncci))
-					{
-						data = &(ncci_ptr->DBuffer[ncci_ptr->data_out]);
-						if ((plci->B2_prot == B2_V120_ASYNC)
-						    || (plci->B2_prot == B2_V120_ASYNC_V42BIS)
-						    || (plci->B2_prot == B2_V120_BIT_TRANSPARENT))
-						{
-							plci->NData[1].P = TransmitBufferGet(plci->appl, data->P);
-							plci->NData[1].PLength = data->Length;
-							if (data->Flags & 0x10)
-								plci->NData[0].P = v120_break_header;
-							else
-								plci->NData[0].P = v120_default_header;
-							plci->NData[0].PLength = 1;
-							plci->NL.XNum = 2;
-							plci->NL.Req = plci->nl_req = (byte)((data->Flags & 0x07) << 4 | N_DATA);
-						}
-						else
-						{
-							plci->NData[0].P = TransmitBufferGet(plci->appl, data->P);
-							plci->NData[0].PLength = data->Length;
-							if (data->Flags & 0x10)
-								plci->NL.Req = plci->nl_req = (byte)N_UDATA;
-
-							else if ((plci->B3_prot == B3_RTP) && (data->Flags & 0x01))
-								plci->NL.Req = plci->nl_req = (byte)N_BDATA;
-
-							else
-								plci->NL.Req = plci->nl_req = (byte)((data->Flags & 0x07) << 4 | N_DATA);
-						}
-						plci->NL.X = plci->NData;
-						plci->NL.ReqCh = a->ncci_ch[ncci];
-						dbug(1, dprintf("%x:DREQ(%x:%x)", a->Id, plci->NL.Id, plci->NL.Req));
-						plci->data_sent = true;
-						plci->data_sent_ptr = data->P;
-						a->request(&plci->NL);
-					}
-					else {
-						cleanup_ncci_data(plci, ncci);
-					}
-				}
-				else if (plci->send_disc == ncci)
-				{
-					/* dprintf("N_DISC"); */
-					plci->NData[0].PLength = 0;
-					plci->NL.ReqCh = a->ncci_ch[ncci];
-					plci->NL.Req = plci->nl_req = N_DISC;
-					a->request(&plci->NL);
-					plci->command = _DISCONNECT_B3_R;
-					plci->send_disc = 0;
-				}
-			}
-		} while (!plci->nl_req && (ncci != plci->ncci_ring_list));
-		plci->ncci_ring_list = ncci;
-	}
-}
-
-static void listen_check(DIVA_CAPI_ADAPTER *a)
-{
-	word i, j;
-	PLCI *plci;
-	byte activnotifiedcalls = 0;
-
-	dbug(1, dprintf("listen_check(%d,%d)", a->listen_active, a->max_listen));
-	if (!remove_started && !a->adapter_disabled)
-	{
-		for (i = 0; i < a->max_plci; i++)
-		{
-			plci = &(a->plci[i]);
-			if (plci->notifiedcall) activnotifiedcalls++;
-		}
-		dbug(1, dprintf("listen_check(%d)", activnotifiedcalls));
-
-		for (i = a->listen_active; i < ((word)(a->max_listen + activnotifiedcalls)); i++) {
-			if ((j = get_plci(a))) {
-				a->listen_active++;
-				plci = &a->plci[j - 1];
-				plci->State = LISTENING;
-
-				add_p(plci, OAD, "\x01\xfd");
-
-				add_p(plci, KEY, "\x04\x43\x41\x32\x30");
-
-				add_p(plci, CAI, "\x01\xc0");
-				add_p(plci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-				add_p(plci, LLI, "\x01\xc4");                  /* support Dummy CR FAC + MWI + SpoofNotify */
-				add_p(plci, SHIFT | 6, NULL);
-				add_p(plci, SIN, "\x02\x00\x00");
-				plci->internal_command = LISTEN_SIG_ASSIGN_PEND;     /* do indicate_req if OK  */
-				sig_req(plci, ASSIGN, DSIG_ID);
-				send_req(plci);
-			}
-		}
-	}
-}
-
-/*------------------------------------------------------------------*/
-/* functions for all parameters sent in INDs                        */
-/*------------------------------------------------------------------*/
-
-static void IndParse(PLCI *plci, const word *parms_id, byte **parms, byte multiIEsize)
-{
-	word ploc;            /* points to current location within packet */
-	byte w;
-	byte wlen;
-	byte codeset, lock;
-	byte *in;
-	word i;
-	word code;
-	word mIEindex = 0;
-	ploc = 0;
-	codeset = 0;
-	lock = 0;
-
-	in = plci->Sig.RBuffer->P;
-	for (i = 0; i < parms_id[0]; i++)   /* multiIE parms_id contains just the 1st */
-	{                            /* element but parms array is larger      */
-		parms[i] = (byte *)"";
-	}
-	for (i = 0; i < multiIEsize; i++)
-	{
-		parms[i] = (byte *)"";
-	}
-
-	while (ploc < plci->Sig.RBuffer->length - 1) {
-
-		/* read information element id and length                   */
-		w = in[ploc];
-
-		if (w & 0x80) {
-/*    w &=0xf0; removed, cannot detect congestion levels */
-/*    upper 4 bit masked with w==SHIFT now               */
-			wlen = 0;
-		}
-		else {
-			wlen = (byte)(in[ploc + 1] + 1);
-		}
-		/* check if length valid (not exceeding end of packet)      */
-		if ((ploc + wlen) > 270) return;
-		if (lock & 0x80) lock &= 0x7f;
-		else codeset = lock;
-
-		if ((w & 0xf0) == SHIFT) {
-			codeset = in[ploc];
-			if (!(codeset & 0x08)) lock = (byte)(codeset & 7);
-			codeset &= 7;
-			lock |= 0x80;
-		}
-		else {
-			if (w == ESC && wlen >= 3) code = in[ploc + 2] | 0x800;
-			else code = w;
-			code |= (codeset << 8);
-
-			for (i = 1; i < parms_id[0] + 1 && parms_id[i] != code; i++);
-
-			if (i < parms_id[0] + 1) {
-				if (!multiIEsize) { /* with multiIEs use next field index,          */
-					mIEindex = i - 1;    /* with normal IEs use same index like parms_id */
-				}
-
-				parms[mIEindex] = &in[ploc + 1];
-				dbug(1, dprintf("mIE[%d]=0x%x", *parms[mIEindex], in[ploc]));
-				if (parms_id[i] == OAD
-				    || parms_id[i] == CONN_NR
-				    || parms_id[i] == CAD) {
-					if (in[ploc + 2] & 0x80) {
-						in[ploc + 0] = (byte)(in[ploc + 1] + 1);
-						in[ploc + 1] = (byte)(in[ploc + 2] & 0x7f);
-						in[ploc + 2] = 0x80;
-						parms[mIEindex] = &in[ploc];
-					}
-				}
-				mIEindex++;       /* effects multiIEs only */
-			}
-		}
-
-		ploc += (wlen + 1);
-	}
-	return;
-}
-
-/*------------------------------------------------------------------*/
-/* try to match a cip from received BC and HLC                      */
-/*------------------------------------------------------------------*/
-
-static byte ie_compare(byte *ie1, byte *ie2)
-{
-	word i;
-	if (!ie1 || !ie2) return false;
-	if (!ie1[0]) return false;
-	for (i = 0; i < (word)(ie1[0] + 1); i++) if (ie1[i] != ie2[i]) return false;
-	return true;
-}
-
-static word find_cip(DIVA_CAPI_ADAPTER *a, byte *bc, byte *hlc)
-{
-	word i;
-	word j;
-
-	for (i = 9; i && !ie_compare(bc, cip_bc[i][a->u_law]); i--);
-
-	for (j = 16; j < 29 &&
-		     (!ie_compare(bc, cip_bc[j][a->u_law]) || !ie_compare(hlc, cip_hlc[j])); j++);
-	if (j == 29) return i;
-	return j;
-}
-
-
-static byte AddInfo(byte **add_i,
-		    byte **fty_i,
-		    byte *esc_chi,
-		    byte *facility)
-{
-	byte i;
-	byte j;
-	byte k;
-	byte flen;
-	byte len = 0;
-	/* facility is a nested structure */
-	/* FTY can be more than once      */
-
-	if (esc_chi[0] && !(esc_chi[esc_chi[0]] & 0x7f))
-	{
-		add_i[0] = (byte *)"\x02\x02\x00"; /* use neither b nor d channel */
-	}
-
-	else
-	{
-		add_i[0] = (byte *)"";
-	}
-	if (!fty_i[0][0])
-	{
-		add_i[3] = (byte *)"";
-	}
-	else
-	{    /* facility array found  */
-		for (i = 0, j = 1; i < MAX_MULTI_IE && fty_i[i][0]; i++)
-		{
-			dbug(1, dprintf("AddIFac[%d]", fty_i[i][0]));
-			len += fty_i[i][0];
-			len += 2;
-			flen = fty_i[i][0];
-			facility[j++] = 0x1c; /* copy fac IE */
-			for (k = 0; k <= flen; k++, j++)
-			{
-				facility[j] = fty_i[i][k];
-/*      dbug(1, dprintf("%x ",facility[j])); */
-			}
-		}
-		facility[0] = len;
-		add_i[3] = facility;
-	}
-/*  dbug(1, dprintf("FacArrLen=%d ",len)); */
-	len = add_i[0][0] + add_i[1][0] + add_i[2][0] + add_i[3][0];
-	len += 4;                          /* calculate length of all */
-	return (len);
-}
-
-/*------------------------------------------------------------------*/
-/* voice and codec features                                         */
-/*------------------------------------------------------------------*/
-
-static void SetVoiceChannel(PLCI *plci, byte *chi, DIVA_CAPI_ADAPTER *a)
-{
-	byte voice_chi[] = "\x02\x18\x01";
-	byte channel;
-
-	channel = chi[chi[0]] & 0x3;
-	dbug(1, dprintf("ExtDevON(Ch=0x%x)", channel));
-	voice_chi[2] = (channel) ? channel : 1;
-	add_p(plci, FTY, "\x02\x01\x07");             /* B On, default on 1 */
-	add_p(plci, ESC, voice_chi);                  /* Channel */
-	sig_req(plci, TEL_CTRL, 0);
-	send_req(plci);
-	if (a->AdvSignalPLCI)
-	{
-		adv_voice_write_coefs(a->AdvSignalPLCI, ADV_VOICE_WRITE_ACTIVATION);
-	}
-}
-
-static void VoiceChannelOff(PLCI *plci)
-{
-	dbug(1, dprintf("ExtDevOFF"));
-	add_p(plci, FTY, "\x02\x01\x08");             /* B Off */
-	sig_req(plci, TEL_CTRL, 0);
-	send_req(plci);
-	if (plci->adapter->AdvSignalPLCI)
-	{
-		adv_voice_clear_config(plci->adapter->AdvSignalPLCI);
-	}
-}
-
-
-static word AdvCodecSupport(DIVA_CAPI_ADAPTER *a, PLCI *plci, APPL *appl,
-			    byte hook_listen)
-{
-	word j;
-	PLCI *splci;
-
-	/* check if hardware supports handset with hook states (adv.codec) */
-	/* or if just a on board codec is supported                        */
-	/* the advanced codec plci is just for internal use                */
-
-	/* diva Pro with on-board codec:                                   */
-	if (a->profile.Global_Options & HANDSET)
-	{
-		/* new call, but hook states are already signalled */
-		if (a->AdvCodecFLAG)
-		{
-			if (a->AdvSignalAppl != appl || a->AdvSignalPLCI)
-			{
-				dbug(1, dprintf("AdvSigPlci=0x%x", a->AdvSignalPLCI));
-				return 0x2001; /* codec in use by another application */
-			}
-			if (plci != NULL)
-			{
-				a->AdvSignalPLCI = plci;
-				plci->tel = ADV_VOICE;
-			}
-			return 0;                      /* adv codec still used */
-		}
-		if ((j = get_plci(a)))
-		{
-			splci = &a->plci[j - 1];
-			splci->tel = CODEC_PERMANENT;
-			/* hook_listen indicates if a facility_req with handset/hook support */
-			/* was sent. Otherwise if just a call on an external device was made */
-			/* the codec will be used but the hook info will be discarded (just  */
-			/* the external controller is in use                                 */
-			if (hook_listen) splci->State = ADVANCED_VOICE_SIG;
-			else
-			{
-				splci->State = ADVANCED_VOICE_NOSIG;
-				if (plci)
-				{
-					plci->spoofed_msg = SPOOFING_REQUIRED;
-				}
-				/* indicate D-ch connect if  */
-			}                                        /* codec is connected OK     */
-			if (plci != NULL)
-			{
-				a->AdvSignalPLCI = plci;
-				plci->tel = ADV_VOICE;
-			}
-			a->AdvSignalAppl = appl;
-			a->AdvCodecFLAG = true;
-			a->AdvCodecPLCI = splci;
-			add_p(splci, CAI, "\x01\x15");
-			add_p(splci, LLI, "\x01\x00");
-			add_p(splci, ESC, "\x02\x18\x00");
-			add_p(splci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-			splci->internal_command = PERM_COD_ASSIGN;
-			dbug(1, dprintf("Codec Assign"));
-			sig_req(splci, ASSIGN, DSIG_ID);
-			send_req(splci);
-		}
-		else
-		{
-			return 0x2001; /* wrong state, no more plcis */
-		}
-	}
-	else if (a->profile.Global_Options & ON_BOARD_CODEC)
-	{
-		if (hook_listen) return 0x300B;               /* Facility not supported */
-		/* no hook with SCOM      */
-		if (plci != NULL) plci->tel = CODEC;
-		dbug(1, dprintf("S/SCOM codec"));
-		/* first time we use the scom-s codec we must shut down the internal   */
-		/* handset application of the card. This can be done by an assign with */
-		/* a cai with the 0x80 bit set. Assign return code is 'out of resource'*/
-		if (!a->scom_appl_disable) {
-			if ((j = get_plci(a))) {
-				splci = &a->plci[j - 1];
-				add_p(splci, CAI, "\x01\x80");
-				add_p(splci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-				sig_req(splci, ASSIGN, 0xC0);  /* 0xc0 is the TEL_ID */
-				send_req(splci);
-				a->scom_appl_disable = true;
-			}
-			else{
-				return 0x2001; /* wrong state, no more plcis */
-			}
-		}
-	}
-	else return 0x300B;               /* Facility not supported */
-
-	return 0;
-}
-
-
-static void CodecIdCheck(DIVA_CAPI_ADAPTER *a, PLCI *plci)
-{
-
-	dbug(1, dprintf("CodecIdCheck"));
-
-	if (a->AdvSignalPLCI == plci)
-	{
-		dbug(1, dprintf("PLCI owns codec"));
-		VoiceChannelOff(a->AdvCodecPLCI);
-		if (a->AdvCodecPLCI->State == ADVANCED_VOICE_NOSIG)
-		{
-			dbug(1, dprintf("remove temp codec PLCI"));
-			plci_remove(a->AdvCodecPLCI);
-			a->AdvCodecFLAG  = 0;
-			a->AdvCodecPLCI  = NULL;
-			a->AdvSignalAppl = NULL;
-		}
-		a->AdvSignalPLCI = NULL;
-	}
-}
-
-/* -------------------------------------------------------------------
-   Ask for physical address of card on PCI bus
-   ------------------------------------------------------------------- */
-static void diva_ask_for_xdi_sdram_bar(DIVA_CAPI_ADAPTER *a,
-				       IDI_SYNC_REQ *preq) {
-	a->sdram_bar = 0;
-	if (diva_xdi_extended_features & DIVA_CAPI_XDI_PROVIDES_SDRAM_BAR) {
-		ENTITY *e = (ENTITY *)preq;
-
-		e->user[0] = a->Id - 1;
-		preq->xdi_sdram_bar.info.bar    = 0;
-		preq->xdi_sdram_bar.Req         = 0;
-		preq->xdi_sdram_bar.Rc           = IDI_SYNC_REQ_XDI_GET_ADAPTER_SDRAM_BAR;
-
-		(*(a->request))(e);
-
-		a->sdram_bar = preq->xdi_sdram_bar.info.bar;
-		dbug(3, dprintf("A(%d) SDRAM BAR = %08x", a->Id, a->sdram_bar));
-	}
-}
-
-/* -------------------------------------------------------------------
-   Ask XDI about extended features
-   ------------------------------------------------------------------- */
-static void diva_get_extended_adapter_features(DIVA_CAPI_ADAPTER *a) {
-	IDI_SYNC_REQ *preq;
-	char buffer[((sizeof(preq->xdi_extended_features) + 4) > sizeof(ENTITY)) ? (sizeof(preq->xdi_extended_features) + 4) : sizeof(ENTITY)];
-
-	char features[4];
-	preq = (IDI_SYNC_REQ *)&buffer[0];
-
-	if (!diva_xdi_extended_features) {
-		ENTITY *e = (ENTITY *)preq;
-		diva_xdi_extended_features |= 0x80000000;
-
-		e->user[0] = a->Id - 1;
-		preq->xdi_extended_features.Req = 0;
-		preq->xdi_extended_features.Rc  = IDI_SYNC_REQ_XDI_GET_EXTENDED_FEATURES;
-		preq->xdi_extended_features.info.buffer_length_in_bytes = sizeof(features);
-		preq->xdi_extended_features.info.features = &features[0];
-
-		(*(a->request))(e);
-
-		if (features[0] & DIVA_XDI_EXTENDED_FEATURES_VALID) {
-			/*
-			  Check features located in the byte '0'
-			*/
-			if (features[0] & DIVA_XDI_EXTENDED_FEATURE_CMA) {
-				diva_xdi_extended_features |= DIVA_CAPI_USE_CMA;
-			}
-			if (features[0] & DIVA_XDI_EXTENDED_FEATURE_RX_DMA) {
-				diva_xdi_extended_features |= DIVA_CAPI_XDI_PROVIDES_RX_DMA;
-				dbug(1, dprintf("XDI provides RxDMA"));
-			}
-			if (features[0] & DIVA_XDI_EXTENDED_FEATURE_SDRAM_BAR) {
-				diva_xdi_extended_features |= DIVA_CAPI_XDI_PROVIDES_SDRAM_BAR;
-			}
-			if (features[0] & DIVA_XDI_EXTENDED_FEATURE_NO_CANCEL_RC) {
-				diva_xdi_extended_features |= DIVA_CAPI_XDI_PROVIDES_NO_CANCEL;
-				dbug(3, dprintf("XDI provides NO_CANCEL_RC feature"));
-			}
-
-		}
-	}
-
-	diva_ask_for_xdi_sdram_bar(a, preq);
-}
-
-/*------------------------------------------------------------------*/
-/* automatic law                                                    */
-/*------------------------------------------------------------------*/
-/* called from OS specific part after init time to get the Law              */
-/* a-law (Euro) and u-law (us,japan) use different BCs in the Setup message */
-void AutomaticLaw(DIVA_CAPI_ADAPTER *a)
-{
-	word j;
-	PLCI *splci;
-
-	if (a->automatic_law) {
-		return;
-	}
-	if ((j = get_plci(a))) {
-		diva_get_extended_adapter_features(a);
-		splci = &a->plci[j - 1];
-		a->automatic_lawPLCI = splci;
-		a->automatic_law = 1;
-		add_p(splci, CAI, "\x01\x80");
-		add_p(splci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-		splci->internal_command = USELAW_REQ;
-		splci->command = 0;
-		splci->number = 0;
-		sig_req(splci, ASSIGN, DSIG_ID);
-		send_req(splci);
-	}
-}
-
-/* called from OS specific part if an application sends an Capi20Release */
-word CapiRelease(word Id)
-{
-	word i, j, appls_found;
-	PLCI *plci;
-	APPL   *this;
-	DIVA_CAPI_ADAPTER *a;
-
-	if (!Id)
-	{
-		dbug(0, dprintf("A: CapiRelease(Id==0)"));
-		return (_WRONG_APPL_ID);
-	}
-
-	this = &application[Id - 1];               /* get application pointer */
-
-	for (i = 0, appls_found = 0; i < max_appl; i++)
-	{
-		if (application[i].Id)       /* an application has been found        */
-		{
-			appls_found++;
-		}
-	}
-
-	for (i = 0; i < max_adapter; i++)             /* scan all adapters...    */
-	{
-		a = &adapter[i];
-		if (a->request)
-		{
-			a->Info_Mask[Id - 1] = 0;
-			a->CIP_Mask[Id - 1] = 0;
-			a->Notification_Mask[Id - 1] = 0;
-			a->codec_listen[Id - 1] = NULL;
-			a->requested_options_table[Id - 1] = 0;
-			for (j = 0; j < a->max_plci; j++)           /* and all PLCIs connected */
-			{                                      /* with this application   */
-				plci = &a->plci[j];
-				if (plci->Id)                         /* if plci owns no application */
-				{                                    /* it may be not jet connected */
-					if (plci->State == INC_CON_PENDING
-					    || plci->State == INC_CON_ALERT)
-					{
-						if (test_bit(Id - 1, plci->c_ind_mask_table))
-						{
-							__clear_bit(Id - 1, plci->c_ind_mask_table);
-							if (bitmap_empty(plci->c_ind_mask_table, MAX_APPL))
-							{
-								sig_req(plci, HANGUP, 0);
-								send_req(plci);
-								plci->State = OUTG_DIS_PENDING;
-							}
-						}
-					}
-					if (test_bit(Id - 1, plci->c_ind_mask_table))
-					{
-						__clear_bit(Id - 1, plci->c_ind_mask_table);
-						if (bitmap_empty(plci->c_ind_mask_table, MAX_APPL))
-						{
-							if (!plci->appl)
-							{
-								plci_remove(plci);
-								plci->State = IDLE;
-							}
-						}
-					}
-					if (plci->appl == this)
-					{
-						plci->appl = NULL;
-						plci_remove(plci);
-						plci->State = IDLE;
-					}
-				}
-			}
-			listen_check(a);
-
-			if (a->flag_dynamic_l1_down)
-			{
-				if (appls_found == 1)            /* last application does a capi release */
-				{
-					if ((j = get_plci(a)))
-					{
-						plci = &a->plci[j - 1];
-						plci->command = 0;
-						add_p(plci, OAD, "\x01\xfd");
-						add_p(plci, CAI, "\x01\x80");
-						add_p(plci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-						add_p(plci, SHIFT | 6, NULL);
-						add_p(plci, SIN, "\x02\x00\x00");
-						plci->internal_command = REM_L1_SIG_ASSIGN_PEND;
-						sig_req(plci, ASSIGN, DSIG_ID);
-						add_p(plci, FTY, "\x02\xff\x06"); /* l1 down */
-						sig_req(plci, SIG_CTRL, 0);
-						send_req(plci);
-					}
-				}
-			}
-			if (a->AdvSignalAppl == this)
-			{
-				this->NullCREnable = false;
-				if (a->AdvCodecPLCI)
-				{
-					plci_remove(a->AdvCodecPLCI);
-					a->AdvCodecPLCI->tel = 0;
-					a->AdvCodecPLCI->adv_nl = 0;
-				}
-				a->AdvSignalAppl = NULL;
-				a->AdvSignalPLCI = NULL;
-				a->AdvCodecFLAG = 0;
-				a->AdvCodecPLCI = NULL;
-			}
-		}
-	}
-
-	this->Id = 0;
-
-	return GOOD;
-}
-
-static word plci_remove_check(PLCI *plci)
-{
-	if (!plci) return true;
-	if (!plci->NL.Id && bitmap_empty(plci->c_ind_mask_table, MAX_APPL))
-	{
-		if (plci->Sig.Id == 0xff)
-			plci->Sig.Id = 0;
-		if (!plci->Sig.Id)
-		{
-			dbug(1, dprintf("plci_remove_complete(%x)", plci->Id));
-			dbug(1, dprintf("tel=0x%x,Sig=0x%x", plci->tel, plci->Sig.Id));
-			if (plci->Id)
-			{
-				CodecIdCheck(plci->adapter, plci);
-				clear_b1_config(plci);
-				ncci_remove(plci, 0, false);
-				plci_free_msg_in_queue(plci);
-				channel_flow_control_remove(plci);
-				plci->Id = 0;
-				plci->State = IDLE;
-				plci->channels = 0;
-				plci->appl = NULL;
-				plci->notifiedcall = 0;
-			}
-			listen_check(plci->adapter);
-			return true;
-		}
-	}
-	return false;
-}
-
-
-/*------------------------------------------------------------------*/
-
-static byte plci_nl_busy(PLCI *plci)
-{
-	/* only applicable for non-multiplexed protocols */
-	return (plci->nl_req
-		|| (plci->ncci_ring_list
-		    && plci->adapter->ncci_ch[plci->ncci_ring_list]
-		    && (plci->adapter->ch_flow_control[plci->adapter->ncci_ch[plci->ncci_ring_list]] & N_OK_FC_PENDING)));
-}
-
-
-/*------------------------------------------------------------------*/
-/* DTMF facilities                                                  */
-/*------------------------------------------------------------------*/
-
-
-static struct
-{
-	byte send_mask;
-	byte listen_mask;
-	byte character;
-	byte code;
-} dtmf_digit_map[] =
-{
-	{ 0x01, 0x01, 0x23, DTMF_DIGIT_TONE_CODE_HASHMARK },
-	{ 0x01, 0x01, 0x2a, DTMF_DIGIT_TONE_CODE_STAR },
-	{ 0x01, 0x01, 0x30, DTMF_DIGIT_TONE_CODE_0 },
-	{ 0x01, 0x01, 0x31, DTMF_DIGIT_TONE_CODE_1 },
-	{ 0x01, 0x01, 0x32, DTMF_DIGIT_TONE_CODE_2 },
-	{ 0x01, 0x01, 0x33, DTMF_DIGIT_TONE_CODE_3 },
-	{ 0x01, 0x01, 0x34, DTMF_DIGIT_TONE_CODE_4 },
-	{ 0x01, 0x01, 0x35, DTMF_DIGIT_TONE_CODE_5 },
-	{ 0x01, 0x01, 0x36, DTMF_DIGIT_TONE_CODE_6 },
-	{ 0x01, 0x01, 0x37, DTMF_DIGIT_TONE_CODE_7 },
-	{ 0x01, 0x01, 0x38, DTMF_DIGIT_TONE_CODE_8 },
-	{ 0x01, 0x01, 0x39, DTMF_DIGIT_TONE_CODE_9 },
-	{ 0x01, 0x01, 0x41, DTMF_DIGIT_TONE_CODE_A },
-	{ 0x01, 0x01, 0x42, DTMF_DIGIT_TONE_CODE_B },
-	{ 0x01, 0x01, 0x43, DTMF_DIGIT_TONE_CODE_C },
-	{ 0x01, 0x01, 0x44, DTMF_DIGIT_TONE_CODE_D },
-	{ 0x01, 0x00, 0x61, DTMF_DIGIT_TONE_CODE_A },
-	{ 0x01, 0x00, 0x62, DTMF_DIGIT_TONE_CODE_B },
-	{ 0x01, 0x00, 0x63, DTMF_DIGIT_TONE_CODE_C },
-	{ 0x01, 0x00, 0x64, DTMF_DIGIT_TONE_CODE_D },
-
-	{ 0x04, 0x04, 0x80, DTMF_SIGNAL_NO_TONE },
-	{ 0x00, 0x04, 0x81, DTMF_SIGNAL_UNIDENTIFIED_TONE },
-	{ 0x04, 0x04, 0x82, DTMF_SIGNAL_DIAL_TONE },
-	{ 0x04, 0x04, 0x83, DTMF_SIGNAL_PABX_INTERNAL_DIAL_TONE },
-	{ 0x04, 0x04, 0x84, DTMF_SIGNAL_SPECIAL_DIAL_TONE },
-	{ 0x04, 0x04, 0x85, DTMF_SIGNAL_SECOND_DIAL_TONE },
-	{ 0x04, 0x04, 0x86, DTMF_SIGNAL_RINGING_TONE },
-	{ 0x04, 0x04, 0x87, DTMF_SIGNAL_SPECIAL_RINGING_TONE },
-	{ 0x04, 0x04, 0x88, DTMF_SIGNAL_BUSY_TONE },
-	{ 0x04, 0x04, 0x89, DTMF_SIGNAL_CONGESTION_TONE },
-	{ 0x04, 0x04, 0x8a, DTMF_SIGNAL_SPECIAL_INFORMATION_TONE },
-	{ 0x04, 0x04, 0x8b, DTMF_SIGNAL_COMFORT_TONE },
-	{ 0x04, 0x04, 0x8c, DTMF_SIGNAL_HOLD_TONE },
-	{ 0x04, 0x04, 0x8d, DTMF_SIGNAL_RECORD_TONE },
-	{ 0x04, 0x04, 0x8e, DTMF_SIGNAL_CALLER_WAITING_TONE },
-	{ 0x04, 0x04, 0x8f, DTMF_SIGNAL_CALL_WAITING_TONE },
-	{ 0x04, 0x04, 0x90, DTMF_SIGNAL_PAY_TONE },
-	{ 0x04, 0x04, 0x91, DTMF_SIGNAL_POSITIVE_INDICATION_TONE },
-	{ 0x04, 0x04, 0x92, DTMF_SIGNAL_NEGATIVE_INDICATION_TONE },
-	{ 0x04, 0x04, 0x93, DTMF_SIGNAL_WARNING_TONE },
-	{ 0x04, 0x04, 0x94, DTMF_SIGNAL_INTRUSION_TONE },
-	{ 0x04, 0x04, 0x95, DTMF_SIGNAL_CALLING_CARD_SERVICE_TONE },
-	{ 0x04, 0x04, 0x96, DTMF_SIGNAL_PAYPHONE_RECOGNITION_TONE },
-	{ 0x04, 0x04, 0x97, DTMF_SIGNAL_CPE_ALERTING_SIGNAL },
-	{ 0x04, 0x04, 0x98, DTMF_SIGNAL_OFF_HOOK_WARNING_TONE },
-	{ 0x04, 0x04, 0xbf, DTMF_SIGNAL_INTERCEPT_TONE },
-	{ 0x04, 0x04, 0xc0, DTMF_SIGNAL_MODEM_CALLING_TONE },
-	{ 0x04, 0x04, 0xc1, DTMF_SIGNAL_FAX_CALLING_TONE },
-	{ 0x04, 0x04, 0xc2, DTMF_SIGNAL_ANSWER_TONE },
-	{ 0x04, 0x04, 0xc3, DTMF_SIGNAL_REVERSED_ANSWER_TONE },
-	{ 0x04, 0x04, 0xc4, DTMF_SIGNAL_ANSAM_TONE },
-	{ 0x04, 0x04, 0xc5, DTMF_SIGNAL_REVERSED_ANSAM_TONE },
-	{ 0x04, 0x04, 0xc6, DTMF_SIGNAL_BELL103_ANSWER_TONE },
-	{ 0x04, 0x04, 0xc7, DTMF_SIGNAL_FAX_FLAGS },
-	{ 0x04, 0x04, 0xc8, DTMF_SIGNAL_G2_FAX_GROUP_ID },
-	{ 0x00, 0x04, 0xc9, DTMF_SIGNAL_HUMAN_SPEECH },
-	{ 0x04, 0x04, 0xca, DTMF_SIGNAL_ANSWERING_MACHINE_390 },
-	{ 0x02, 0x02, 0xf1, DTMF_MF_DIGIT_TONE_CODE_1 },
-	{ 0x02, 0x02, 0xf2, DTMF_MF_DIGIT_TONE_CODE_2 },
-	{ 0x02, 0x02, 0xf3, DTMF_MF_DIGIT_TONE_CODE_3 },
-	{ 0x02, 0x02, 0xf4, DTMF_MF_DIGIT_TONE_CODE_4 },
-	{ 0x02, 0x02, 0xf5, DTMF_MF_DIGIT_TONE_CODE_5 },
-	{ 0x02, 0x02, 0xf6, DTMF_MF_DIGIT_TONE_CODE_6 },
-	{ 0x02, 0x02, 0xf7, DTMF_MF_DIGIT_TONE_CODE_7 },
-	{ 0x02, 0x02, 0xf8, DTMF_MF_DIGIT_TONE_CODE_8 },
-	{ 0x02, 0x02, 0xf9, DTMF_MF_DIGIT_TONE_CODE_9 },
-	{ 0x02, 0x02, 0xfa, DTMF_MF_DIGIT_TONE_CODE_0 },
-	{ 0x02, 0x02, 0xfb, DTMF_MF_DIGIT_TONE_CODE_K1 },
-	{ 0x02, 0x02, 0xfc, DTMF_MF_DIGIT_TONE_CODE_K2 },
-	{ 0x02, 0x02, 0xfd, DTMF_MF_DIGIT_TONE_CODE_KP },
-	{ 0x02, 0x02, 0xfe, DTMF_MF_DIGIT_TONE_CODE_S1 },
-	{ 0x02, 0x02, 0xff, DTMF_MF_DIGIT_TONE_CODE_ST },
-
-};
-
-#define DTMF_DIGIT_MAP_ENTRIES ARRAY_SIZE(dtmf_digit_map)
-
-
-static void dtmf_enable_receiver(PLCI *plci, byte enable_mask)
-{
-	word min_digit_duration, min_gap_duration;
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_enable_receiver %02x",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__, enable_mask));
-
-	if (enable_mask != 0)
-	{
-		min_digit_duration = (plci->dtmf_rec_pulse_ms == 0) ? 40 : plci->dtmf_rec_pulse_ms;
-		min_gap_duration = (plci->dtmf_rec_pause_ms == 0) ? 40 : plci->dtmf_rec_pause_ms;
-		plci->internal_req_buffer[0] = DTMF_UDATA_REQUEST_ENABLE_RECEIVER;
-		PUT_WORD(&plci->internal_req_buffer[1], min_digit_duration);
-		PUT_WORD(&plci->internal_req_buffer[3], min_gap_duration);
-		plci->NData[0].PLength = 5;
-
-		PUT_WORD(&plci->internal_req_buffer[5], INTERNAL_IND_BUFFER_SIZE);
-		plci->NData[0].PLength += 2;
-		capidtmf_recv_enable(&(plci->capidtmf_state), min_digit_duration, min_gap_duration);
-
-	}
-	else
-	{
-		plci->internal_req_buffer[0] = DTMF_UDATA_REQUEST_DISABLE_RECEIVER;
-		plci->NData[0].PLength = 1;
-
-		capidtmf_recv_disable(&(plci->capidtmf_state));
-
-	}
-	plci->NData[0].P = plci->internal_req_buffer;
-	plci->NL.X = plci->NData;
-	plci->NL.ReqCh = 0;
-	plci->NL.Req = plci->nl_req = (byte) N_UDATA;
-	plci->adapter->request(&plci->NL);
-}
-
-
-static void dtmf_send_digits(PLCI *plci, byte *digit_buffer, word digit_count)
-{
-	word w, i;
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_send_digits %d",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__, digit_count));
-
-	plci->internal_req_buffer[0] = DTMF_UDATA_REQUEST_SEND_DIGITS;
-	w = (plci->dtmf_send_pulse_ms == 0) ? 40 : plci->dtmf_send_pulse_ms;
-	PUT_WORD(&plci->internal_req_buffer[1], w);
-	w = (plci->dtmf_send_pause_ms == 0) ? 40 : plci->dtmf_send_pause_ms;
-	PUT_WORD(&plci->internal_req_buffer[3], w);
-	for (i = 0; i < digit_count; i++)
-	{
-		w = 0;
-		while ((w < DTMF_DIGIT_MAP_ENTRIES)
-		       && (digit_buffer[i] != dtmf_digit_map[w].character))
-		{
-			w++;
-		}
-		plci->internal_req_buffer[5 + i] = (w < DTMF_DIGIT_MAP_ENTRIES) ?
-			dtmf_digit_map[w].code : DTMF_DIGIT_TONE_CODE_STAR;
-	}
-	plci->NData[0].PLength = 5 + digit_count;
-	plci->NData[0].P = plci->internal_req_buffer;
-	plci->NL.X = plci->NData;
-	plci->NL.ReqCh = 0;
-	plci->NL.Req = plci->nl_req = (byte) N_UDATA;
-	plci->adapter->request(&plci->NL);
-}
-
-
-static void dtmf_rec_clear_config(PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_rec_clear_config",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	plci->dtmf_rec_active = 0;
-	plci->dtmf_rec_pulse_ms = 0;
-	plci->dtmf_rec_pause_ms = 0;
-
-	capidtmf_init(&(plci->capidtmf_state), plci->adapter->u_law);
-
-}
-
-
-static void dtmf_send_clear_config(PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_send_clear_config",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	plci->dtmf_send_requests = 0;
-	plci->dtmf_send_pulse_ms = 0;
-	plci->dtmf_send_pause_ms = 0;
-}
-
-
-static void dtmf_prepare_switch(dword Id, PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_prepare_switch",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-	while (plci->dtmf_send_requests != 0)
-		dtmf_confirmation(Id, plci);
-}
-
-
-static word dtmf_save_config(dword Id, PLCI *plci, byte Rc)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_save_config %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->adjust_b_state));
-
-	return (GOOD);
-}
-
-
-static word dtmf_restore_config(dword Id, PLCI *plci, byte Rc)
-{
-	word Info;
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_restore_config %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->adjust_b_state));
-
-	Info = GOOD;
-	if (plci->B1_facilities & B1_FACILITY_DTMFR)
-	{
-		switch (plci->adjust_b_state)
-		{
-		case ADJUST_B_RESTORE_DTMF_1:
-			plci->internal_command = plci->adjust_b_command;
-			if (plci_nl_busy(plci))
-			{
-				plci->adjust_b_state = ADJUST_B_RESTORE_DTMF_1;
-				break;
-			}
-			dtmf_enable_receiver(plci, plci->dtmf_rec_active);
-			plci->adjust_b_state = ADJUST_B_RESTORE_DTMF_2;
-			break;
-		case ADJUST_B_RESTORE_DTMF_2:
-			if ((Rc != OK) && (Rc != OK_FC))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Reenable DTMF receiver failed %02x",
-						UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-				Info = _WRONG_STATE;
-				break;
-			}
-			break;
-		}
-	}
-	return (Info);
-}
-
-
-static void dtmf_command(dword Id, PLCI *plci, byte Rc)
-{
-	word internal_command, Info;
-	byte mask;
-	byte result[4];
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_command %02x %04x %04x %d %d %d %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command,
-			plci->dtmf_cmd, plci->dtmf_rec_pulse_ms, plci->dtmf_rec_pause_ms,
-			plci->dtmf_send_pulse_ms, plci->dtmf_send_pause_ms));
-
-	Info = GOOD;
-	result[0] = 2;
-	PUT_WORD(&result[1], DTMF_SUCCESS);
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	mask = 0x01;
-	switch (plci->dtmf_cmd)
-	{
-
-	case DTMF_LISTEN_TONE_START:
-		mask <<= 1; /* fall through */
-	case DTMF_LISTEN_MF_START:
-		mask <<= 1; /* fall through */
-
-	case DTMF_LISTEN_START:
-		switch (internal_command)
-		{
-		default:
-			adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities |
-								  B1_FACILITY_DTMFR), DTMF_COMMAND_1);
-			/* fall through */
-		case DTMF_COMMAND_1:
-			if (adjust_b_process(Id, plci, Rc) != GOOD)
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Load DTMF failed",
-						UnMapId(Id), (char *)(FILE_), __LINE__));
-				Info = _FACILITY_NOT_SUPPORTED;
-				break;
-			}
-			if (plci->internal_command)
-				return;
-			/* fall through */
-		case DTMF_COMMAND_2:
-			if (plci_nl_busy(plci))
-			{
-				plci->internal_command = DTMF_COMMAND_2;
-				return;
-			}
-			plci->internal_command = DTMF_COMMAND_3;
-			dtmf_enable_receiver(plci, (byte)(plci->dtmf_rec_active | mask));
-			return;
-		case DTMF_COMMAND_3:
-			if ((Rc != OK) && (Rc != OK_FC))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Enable DTMF receiver failed %02x",
-						UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-				Info = _FACILITY_NOT_SUPPORTED;
-				break;
-			}
-
-			plci->tone_last_indication_code = DTMF_SIGNAL_NO_TONE;
-
-			plci->dtmf_rec_active |= mask;
-			break;
-		}
-		break;
-
-
-	case DTMF_LISTEN_TONE_STOP:
-		mask <<= 1; /* fall through */
-	case DTMF_LISTEN_MF_STOP:
-		mask <<= 1; /* fall through */
-
-	case DTMF_LISTEN_STOP:
-		switch (internal_command)
-		{
-		default:
-			plci->dtmf_rec_active &= ~mask;
-			if (plci->dtmf_rec_active)
-				break;
-/*
-  case DTMF_COMMAND_1:
-  if (plci->dtmf_rec_active)
-  {
-  if (plci_nl_busy (plci))
-  {
-  plci->internal_command = DTMF_COMMAND_1;
-  return;
-  }
-  plci->dtmf_rec_active &= ~mask;
-  plci->internal_command = DTMF_COMMAND_2;
-  dtmf_enable_receiver (plci, false);
-  return;
-  }
-  Rc = OK;
-  case DTMF_COMMAND_2:
-  if ((Rc != OK) && (Rc != OK_FC))
-  {
-  dbug (1, dprintf("[%06lx] %s,%d: Disable DTMF receiver failed %02x",
-  UnMapId (Id), (char far *)(FILE_), __LINE__, Rc));
-  Info = _FACILITY_NOT_SUPPORTED;
-  break;
-  }
-*/
-			adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities &
-								  ~(B1_FACILITY_DTMFX | B1_FACILITY_DTMFR)), DTMF_COMMAND_3);
-			/* fall through */
-		case DTMF_COMMAND_3:
-			if (adjust_b_process(Id, plci, Rc) != GOOD)
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Unload DTMF failed",
-						UnMapId(Id), (char *)(FILE_), __LINE__));
-				Info = _FACILITY_NOT_SUPPORTED;
-				break;
-			}
-			if (plci->internal_command)
-				return;
-			break;
-		}
-		break;
-
-
-	case DTMF_SEND_TONE:
-		mask <<= 1; /* fall through */
-	case DTMF_SEND_MF:
-		mask <<= 1; /* fall through */
-
-	case DTMF_DIGITS_SEND:
-		switch (internal_command)
-		{
-		default:
-			adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities |
-								  ((plci->dtmf_parameter_length != 0) ? B1_FACILITY_DTMFX | B1_FACILITY_DTMFR : B1_FACILITY_DTMFX)),
-					   DTMF_COMMAND_1);
-			/* fall through */
-		case DTMF_COMMAND_1:
-			if (adjust_b_process(Id, plci, Rc) != GOOD)
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Load DTMF failed",
-						UnMapId(Id), (char *)(FILE_), __LINE__));
-				Info = _FACILITY_NOT_SUPPORTED;
-				break;
-			}
-			if (plci->internal_command)
-				return;
-			/* fall through */
-		case DTMF_COMMAND_2:
-			if (plci_nl_busy(plci))
-			{
-				plci->internal_command = DTMF_COMMAND_2;
-				return;
-			}
-			plci->dtmf_msg_number_queue[(plci->dtmf_send_requests)++] = plci->number;
-			plci->internal_command = DTMF_COMMAND_3;
-			dtmf_send_digits(plci, &plci->saved_msg.parms[3].info[1], plci->saved_msg.parms[3].length);
-			return;
-		case DTMF_COMMAND_3:
-			if ((Rc != OK) && (Rc != OK_FC))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Send DTMF digits failed %02x",
-						UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-				if (plci->dtmf_send_requests != 0)
-					(plci->dtmf_send_requests)--;
-				Info = _FACILITY_NOT_SUPPORTED;
-				break;
-			}
-			return;
-		}
-		break;
-	}
-	sendf(plci->appl, _FACILITY_R | CONFIRM, Id & 0xffffL, plci->number,
-	      "wws", Info, SELECTOR_DTMF, result);
-}
-
-
-static byte dtmf_request(dword Id, word Number, DIVA_CAPI_ADAPTER *a, PLCI *plci, APPL   *appl, API_PARSE *msg)
-{
-	word Info;
-	word i, j;
-	byte mask;
-	API_PARSE dtmf_parms[5];
-	byte result[40];
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_request",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-	Info = GOOD;
-	result[0] = 2;
-	PUT_WORD(&result[1], DTMF_SUCCESS);
-	if (!(a->profile.Global_Options & GL_DTMF_SUPPORTED))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: Facility not supported",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		Info = _FACILITY_NOT_SUPPORTED;
-	}
-	else if (api_parse(&msg[1].info[1], msg[1].length, "w", dtmf_parms))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		Info = _WRONG_MESSAGE_FORMAT;
-	}
-
-	else if ((GET_WORD(dtmf_parms[0].info) == DTMF_GET_SUPPORTED_DETECT_CODES)
-		 || (GET_WORD(dtmf_parms[0].info) == DTMF_GET_SUPPORTED_SEND_CODES))
-	{
-		if (!((a->requested_options_table[appl->Id - 1])
-		      & (1L << PRIVATE_DTMF_TONE)))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: DTMF unknown request %04x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, GET_WORD(dtmf_parms[0].info)));
-			PUT_WORD(&result[1], DTMF_UNKNOWN_REQUEST);
-		}
-		else
-		{
-			for (i = 0; i < 32; i++)
-				result[4 + i] = 0;
-			if (GET_WORD(dtmf_parms[0].info) == DTMF_GET_SUPPORTED_DETECT_CODES)
-			{
-				for (i = 0; i < DTMF_DIGIT_MAP_ENTRIES; i++)
-				{
-					if (dtmf_digit_map[i].listen_mask != 0)
-						result[4 + (dtmf_digit_map[i].character >> 3)] |= (1 << (dtmf_digit_map[i].character & 0x7));
-				}
-			}
-			else
-			{
-				for (i = 0; i < DTMF_DIGIT_MAP_ENTRIES; i++)
-				{
-					if (dtmf_digit_map[i].send_mask != 0)
-						result[4 + (dtmf_digit_map[i].character >> 3)] |= (1 << (dtmf_digit_map[i].character & 0x7));
-				}
-			}
-			result[0] = 3 + 32;
-			result[3] = 32;
-		}
-	}
-
-	else if (plci == NULL)
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: Wrong PLCI",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		Info = _WRONG_IDENTIFIER;
-	}
-	else
-	{
-		if (!plci->State
-		    || !plci->NL.Id || plci->nl_remove_id)
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: Wrong state",
-					UnMapId(Id), (char *)(FILE_), __LINE__));
-			Info = _WRONG_STATE;
-		}
-		else
-		{
-			plci->command = 0;
-			plci->dtmf_cmd = GET_WORD(dtmf_parms[0].info);
-			mask = 0x01;
-			switch (plci->dtmf_cmd)
-			{
-
-			case DTMF_LISTEN_TONE_START:
-			case DTMF_LISTEN_TONE_STOP:
-				mask <<= 1; /* fall through */
-			case DTMF_LISTEN_MF_START:
-			case DTMF_LISTEN_MF_STOP:
-				mask <<= 1;
-				if (!((plci->requested_options_conn | plci->requested_options | plci->adapter->requested_options_table[appl->Id - 1])
-				      & (1L << PRIVATE_DTMF_TONE)))
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: DTMF unknown request %04x",
-							UnMapId(Id), (char *)(FILE_), __LINE__, GET_WORD(dtmf_parms[0].info)));
-					PUT_WORD(&result[1], DTMF_UNKNOWN_REQUEST);
-					break;
-				}
-				/* fall through */
-
-			case DTMF_LISTEN_START:
-			case DTMF_LISTEN_STOP:
-				if (!(a->manufacturer_features & MANUFACTURER_FEATURE_HARDDTMF)
-				    && !(a->manufacturer_features & MANUFACTURER_FEATURE_SOFTDTMF_RECEIVE))
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Facility not supported",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					Info = _FACILITY_NOT_SUPPORTED;
-					break;
-				}
-				if (mask & DTMF_LISTEN_ACTIVE_FLAG)
-				{
-					if (api_parse(&msg[1].info[1], msg[1].length, "wwws", dtmf_parms))
-					{
-						plci->dtmf_rec_pulse_ms = 0;
-						plci->dtmf_rec_pause_ms = 0;
-					}
-					else
-					{
-						plci->dtmf_rec_pulse_ms = GET_WORD(dtmf_parms[1].info);
-						plci->dtmf_rec_pause_ms = GET_WORD(dtmf_parms[2].info);
-					}
-				}
-				start_internal_command(Id, plci, dtmf_command);
-				return (false);
-
-
-			case DTMF_SEND_TONE:
-				mask <<= 1; /* fall through */
-			case DTMF_SEND_MF:
-				mask <<= 1;
-				if (!((plci->requested_options_conn | plci->requested_options | plci->adapter->requested_options_table[appl->Id - 1])
-				      & (1L << PRIVATE_DTMF_TONE)))
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: DTMF unknown request %04x",
-							UnMapId(Id), (char *)(FILE_), __LINE__, GET_WORD(dtmf_parms[0].info)));
-					PUT_WORD(&result[1], DTMF_UNKNOWN_REQUEST);
-					break;
-				}
-				/* fall through */
-
-			case DTMF_DIGITS_SEND:
-				if (api_parse(&msg[1].info[1], msg[1].length, "wwws", dtmf_parms))
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				if (mask & DTMF_LISTEN_ACTIVE_FLAG)
-				{
-					plci->dtmf_send_pulse_ms = GET_WORD(dtmf_parms[1].info);
-					plci->dtmf_send_pause_ms = GET_WORD(dtmf_parms[2].info);
-				}
-				i = 0;
-				j = 0;
-				while ((i < dtmf_parms[3].length) && (j < DTMF_DIGIT_MAP_ENTRIES))
-				{
-					j = 0;
-					while ((j < DTMF_DIGIT_MAP_ENTRIES)
-					       && ((dtmf_parms[3].info[i + 1] != dtmf_digit_map[j].character)
-						   || ((dtmf_digit_map[j].send_mask & mask) == 0)))
-					{
-						j++;
-					}
-					i++;
-				}
-				if (j == DTMF_DIGIT_MAP_ENTRIES)
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Incorrect DTMF digit %02x",
-							UnMapId(Id), (char *)(FILE_), __LINE__, dtmf_parms[3].info[i]));
-					PUT_WORD(&result[1], DTMF_INCORRECT_DIGIT);
-					break;
-				}
-				if (plci->dtmf_send_requests >= ARRAY_SIZE(plci->dtmf_msg_number_queue))
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: DTMF request overrun",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					Info = _WRONG_STATE;
-					break;
-				}
-				api_save_msg(dtmf_parms, "wwws", &plci->saved_msg);
-				start_internal_command(Id, plci, dtmf_command);
-				return (false);
-
-			default:
-				dbug(1, dprintf("[%06lx] %s,%d: DTMF unknown request %04x",
-						UnMapId(Id), (char *)(FILE_), __LINE__, plci->dtmf_cmd));
-				PUT_WORD(&result[1], DTMF_UNKNOWN_REQUEST);
-			}
-		}
-	}
-	sendf(appl, _FACILITY_R | CONFIRM, Id & 0xffffL, Number,
-	      "wws", Info, SELECTOR_DTMF, result);
-	return (false);
-}
-
-
-static void dtmf_confirmation(dword Id, PLCI *plci)
-{
-	word i;
-	byte result[4];
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_confirmation",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-	result[0] = 2;
-	PUT_WORD(&result[1], DTMF_SUCCESS);
-	if (plci->dtmf_send_requests != 0)
-	{
-		sendf(plci->appl, _FACILITY_R | CONFIRM, Id & 0xffffL, plci->dtmf_msg_number_queue[0],
-		      "wws", GOOD, SELECTOR_DTMF, result);
-		(plci->dtmf_send_requests)--;
-		for (i = 0; i < plci->dtmf_send_requests; i++)
-			plci->dtmf_msg_number_queue[i] = plci->dtmf_msg_number_queue[i + 1];
-	}
-}
-
-
-static void dtmf_indication(dword Id, PLCI *plci, byte *msg, word length)
-{
-	word i, j, n;
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_indication",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-	n = 0;
-	for (i = 1; i < length; i++)
-	{
-		j = 0;
-		while ((j < DTMF_DIGIT_MAP_ENTRIES)
-		       && ((msg[i] != dtmf_digit_map[j].code)
-			   || ((dtmf_digit_map[j].listen_mask & plci->dtmf_rec_active) == 0)))
-		{
-			j++;
-		}
-		if (j < DTMF_DIGIT_MAP_ENTRIES)
-		{
-
-			if ((dtmf_digit_map[j].listen_mask & DTMF_TONE_LISTEN_ACTIVE_FLAG)
-			    && (plci->tone_last_indication_code == DTMF_SIGNAL_NO_TONE)
-			    && (dtmf_digit_map[j].character != DTMF_SIGNAL_UNIDENTIFIED_TONE))
-			{
-				if (n + 1 == i)
-				{
-					for (i = length; i > n + 1; i--)
-						msg[i] = msg[i - 1];
-					length++;
-					i++;
-				}
-				msg[++n] = DTMF_SIGNAL_UNIDENTIFIED_TONE;
-			}
-			plci->tone_last_indication_code = dtmf_digit_map[j].character;
-
-			msg[++n] = dtmf_digit_map[j].character;
-		}
-	}
-	if (n != 0)
-	{
-		msg[0] = (byte) n;
-		sendf(plci->appl, _FACILITY_I, Id & 0xffffL, 0, "wS", SELECTOR_DTMF, msg);
-	}
-}
-
-
-/*------------------------------------------------------------------*/
-/* DTMF parameters                                                  */
-/*------------------------------------------------------------------*/
-
-static void dtmf_parameter_write(PLCI *plci)
-{
-	word i;
-	byte parameter_buffer[DTMF_PARAMETER_BUFFER_SIZE + 2];
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_parameter_write",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	parameter_buffer[0] = plci->dtmf_parameter_length + 1;
-	parameter_buffer[1] = DSP_CTRL_SET_DTMF_PARAMETERS;
-	for (i = 0; i < plci->dtmf_parameter_length; i++)
-		parameter_buffer[2 + i] = plci->dtmf_parameter_buffer[i];
-	add_p(plci, FTY, parameter_buffer);
-	sig_req(plci, TEL_CTRL, 0);
-	send_req(plci);
-}
-
-
-static void dtmf_parameter_clear_config(PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_parameter_clear_config",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	plci->dtmf_parameter_length = 0;
-}
-
-
-static void dtmf_parameter_prepare_switch(dword Id, PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_parameter_prepare_switch",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-}
-
-
-static word dtmf_parameter_save_config(dword Id, PLCI *plci, byte Rc)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_parameter_save_config %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->adjust_b_state));
-
-	return (GOOD);
-}
-
-
-static word dtmf_parameter_restore_config(dword Id, PLCI *plci, byte Rc)
-{
-	word Info;
-
-	dbug(1, dprintf("[%06lx] %s,%d: dtmf_parameter_restore_config %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->adjust_b_state));
-
-	Info = GOOD;
-	if ((plci->B1_facilities & B1_FACILITY_DTMFR)
-	    && (plci->dtmf_parameter_length != 0))
-	{
-		switch (plci->adjust_b_state)
-		{
-		case ADJUST_B_RESTORE_DTMF_PARAMETER_1:
-			plci->internal_command = plci->adjust_b_command;
-			if (plci->sig_req)
-			{
-				plci->adjust_b_state = ADJUST_B_RESTORE_DTMF_PARAMETER_1;
-				break;
-			}
-			dtmf_parameter_write(plci);
-			plci->adjust_b_state = ADJUST_B_RESTORE_DTMF_PARAMETER_2;
-			break;
-		case ADJUST_B_RESTORE_DTMF_PARAMETER_2:
-			if ((Rc != OK) && (Rc != OK_FC))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Restore DTMF parameters failed %02x",
-						UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-				Info = _WRONG_STATE;
-				break;
-			}
-			break;
-		}
-	}
-	return (Info);
-}
-
-
-/*------------------------------------------------------------------*/
-/* Line interconnect facilities                                     */
-/*------------------------------------------------------------------*/
-
-
-LI_CONFIG   *li_config_table;
-word li_total_channels;
-
-
-/*------------------------------------------------------------------*/
-/* translate a CHI information element to a channel number          */
-/* returns 0xff - any channel                                       */
-/*         0xfe - chi wrong coding                                  */
-/*         0xfd - D-channel                                         */
-/*         0x00 - no channel                                        */
-/*         else channel number / PRI: timeslot                      */
-/* if channels is provided we accept more than one channel.         */
-/*------------------------------------------------------------------*/
-
-static byte chi_to_channel(byte *chi, dword *pchannelmap)
-{
-	int p;
-	int i;
-	dword map;
-	byte excl;
-	byte ofs;
-	byte ch;
-
-	if (pchannelmap) *pchannelmap = 0;
-	if (!chi[0]) return 0xff;
-	excl = 0;
-
-	if (chi[1] & 0x20) {
-		if (chi[0] == 1 && chi[1] == 0xac) return 0xfd; /* exclusive d-channel */
-		for (i = 1; i < chi[0] && !(chi[i] & 0x80); i++);
-		if (i == chi[0] || !(chi[i] & 0x80)) return 0xfe;
-		if ((chi[1] | 0xc8) != 0xe9) return 0xfe;
-		if (chi[1] & 0x08) excl = 0x40;
-
-		/* int. id present */
-		if (chi[1] & 0x40) {
-			p = i + 1;
-			for (i = p; i < chi[0] && !(chi[i] & 0x80); i++);
-			if (i == chi[0] || !(chi[i] & 0x80)) return 0xfe;
-		}
-
-		/* coding standard, Number/Map, Channel Type */
-		p = i + 1;
-		for (i = p; i < chi[0] && !(chi[i] & 0x80); i++);
-		if (i == chi[0] || !(chi[i] & 0x80)) return 0xfe;
-		if ((chi[p] | 0xd0) != 0xd3) return 0xfe;
-
-		/* Number/Map */
-		if (chi[p] & 0x10) {
-
-			/* map */
-			if ((chi[0] - p) == 4) ofs = 0;
-			else if ((chi[0] - p) == 3) ofs = 1;
-			else return 0xfe;
-			ch = 0;
-			map = 0;
-			for (i = 0; i < 4 && p < chi[0]; i++) {
-				p++;
-				ch += 8;
-				map <<= 8;
-				if (chi[p]) {
-					for (ch = 0; !(chi[p] & (1 << ch)); ch++);
-					map |= chi[p];
-				}
-			}
-			ch += ofs;
-			map <<= ofs;
-		}
-		else {
-
-			/* number */
-			p = i + 1;
-			ch = chi[p] & 0x3f;
-			if (pchannelmap) {
-				if ((byte)(chi[0] - p) > 30) return 0xfe;
-				map = 0;
-				for (i = p; i <= chi[0]; i++) {
-					if ((chi[i] & 0x7f) > 31) return 0xfe;
-					map |= (1L << (chi[i] & 0x7f));
-				}
-			}
-			else {
-				if (p != chi[0]) return 0xfe;
-				if (ch > 31) return 0xfe;
-				map = (1L << ch);
-			}
-			if (chi[p] & 0x40) return 0xfe;
-		}
-		if (pchannelmap) *pchannelmap = map;
-		else if (map != ((dword)(1L << ch))) return 0xfe;
-		return (byte)(excl | ch);
-	}
-	else {  /* not PRI */
-		for (i = 1; i < chi[0] && !(chi[i] & 0x80); i++);
-		if (i != chi[0] || !(chi[i] & 0x80)) return 0xfe;
-		if (chi[1] & 0x08) excl = 0x40;
-
-		switch (chi[1] | 0x98) {
-		case 0x98: return 0;
-		case 0x99:
-			if (pchannelmap) *pchannelmap = 2;
-			return excl | 1;
-		case 0x9a:
-			if (pchannelmap) *pchannelmap = 4;
-			return excl | 2;
-		case 0x9b: return 0xff;
-		case 0x9c: return 0xfd; /* d-ch */
-		default: return 0xfe;
-		}
-	}
-}
-
-
-static void mixer_set_bchannel_id_esc(PLCI *plci, byte bchannel_id)
-{
-	DIVA_CAPI_ADAPTER *a;
-	PLCI *splci;
-	byte old_id;
-
-	a = plci->adapter;
-	old_id = plci->li_bchannel_id;
-	if (a->li_pri)
-	{
-		if ((old_id != 0) && (li_config_table[a->li_base + (old_id - 1)].plci == plci))
-			li_config_table[a->li_base + (old_id - 1)].plci = NULL;
-		plci->li_bchannel_id = (bchannel_id & 0x1f) + 1;
-		if (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == NULL)
-			li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci = plci;
-	}
-	else
-	{
-		if (((bchannel_id & 0x03) == 1) || ((bchannel_id & 0x03) == 2))
-		{
-			if ((old_id != 0) && (li_config_table[a->li_base + (old_id - 1)].plci == plci))
-				li_config_table[a->li_base + (old_id - 1)].plci = NULL;
-			plci->li_bchannel_id = bchannel_id & 0x03;
-			if ((a->AdvSignalPLCI != NULL) && (a->AdvSignalPLCI != plci) && (a->AdvSignalPLCI->tel == ADV_VOICE))
-			{
-				splci = a->AdvSignalPLCI;
-				if (li_config_table[a->li_base + (2 - plci->li_bchannel_id)].plci == NULL)
-				{
-					if ((splci->li_bchannel_id != 0)
-					    && (li_config_table[a->li_base + (splci->li_bchannel_id - 1)].plci == splci))
-					{
-						li_config_table[a->li_base + (splci->li_bchannel_id - 1)].plci = NULL;
-					}
-					splci->li_bchannel_id = 3 - plci->li_bchannel_id;
-					li_config_table[a->li_base + (2 - plci->li_bchannel_id)].plci = splci;
-					dbug(1, dprintf("[%06lx] %s,%d: adv_voice_set_bchannel_id_esc %d",
-							(dword)((splci->Id << 8) | UnMapController(splci->adapter->Id)),
-							(char *)(FILE_), __LINE__, splci->li_bchannel_id));
-				}
-			}
-			if (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == NULL)
-				li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci = plci;
-		}
-	}
-	if ((old_id == 0) && (plci->li_bchannel_id != 0)
-	    && (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == plci))
-	{
-		mixer_clear_config(plci);
-	}
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_set_bchannel_id_esc %d %d",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__, bchannel_id, plci->li_bchannel_id));
-}
-
-
-static void mixer_set_bchannel_id(PLCI *plci, byte *chi)
-{
-	DIVA_CAPI_ADAPTER *a;
-	PLCI *splci;
-	byte ch, old_id;
-
-	a = plci->adapter;
-	old_id = plci->li_bchannel_id;
-	ch = chi_to_channel(chi, NULL);
-	if (!(ch & 0x80))
-	{
-		if (a->li_pri)
-		{
-			if ((old_id != 0) && (li_config_table[a->li_base + (old_id - 1)].plci == plci))
-				li_config_table[a->li_base + (old_id - 1)].plci = NULL;
-			plci->li_bchannel_id = (ch & 0x1f) + 1;
-			if (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == NULL)
-				li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci = plci;
-		}
-		else
-		{
-			if (((ch & 0x1f) == 1) || ((ch & 0x1f) == 2))
-			{
-				if ((old_id != 0) && (li_config_table[a->li_base + (old_id - 1)].plci == plci))
-					li_config_table[a->li_base + (old_id - 1)].plci = NULL;
-				plci->li_bchannel_id = ch & 0x1f;
-				if ((a->AdvSignalPLCI != NULL) && (a->AdvSignalPLCI != plci) && (a->AdvSignalPLCI->tel == ADV_VOICE))
-				{
-					splci = a->AdvSignalPLCI;
-					if (li_config_table[a->li_base + (2 - plci->li_bchannel_id)].plci == NULL)
-					{
-						if ((splci->li_bchannel_id != 0)
-						    && (li_config_table[a->li_base + (splci->li_bchannel_id - 1)].plci == splci))
-						{
-							li_config_table[a->li_base + (splci->li_bchannel_id - 1)].plci = NULL;
-						}
-						splci->li_bchannel_id = 3 - plci->li_bchannel_id;
-						li_config_table[a->li_base + (2 - plci->li_bchannel_id)].plci = splci;
-						dbug(1, dprintf("[%06lx] %s,%d: adv_voice_set_bchannel_id %d",
-								(dword)((splci->Id << 8) | UnMapController(splci->adapter->Id)),
-								(char *)(FILE_), __LINE__, splci->li_bchannel_id));
-					}
-				}
-				if (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == NULL)
-					li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci = plci;
-			}
-		}
-	}
-	if ((old_id == 0) && (plci->li_bchannel_id != 0)
-	    && (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == plci))
-	{
-		mixer_clear_config(plci);
-	}
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_set_bchannel_id %02x %d",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__, ch, plci->li_bchannel_id));
-}
-
-
-#define MIXER_MAX_DUMP_CHANNELS 34
-
-static void mixer_calculate_coefs(DIVA_CAPI_ADAPTER *a)
-{
-	word n, i, j;
-	char *p;
-	char hex_line[2 * MIXER_MAX_DUMP_CHANNELS + MIXER_MAX_DUMP_CHANNELS / 8 + 4];
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_calculate_coefs",
-			(dword)(UnMapController(a->Id)), (char *)(FILE_), __LINE__));
-
-	for (i = 0; i < li_total_channels; i++)
-	{
-		li_config_table[i].channel &= LI_CHANNEL_ADDRESSES_SET;
-		if (li_config_table[i].chflags != 0)
-			li_config_table[i].channel |= LI_CHANNEL_INVOLVED;
-		else
-		{
-			for (j = 0; j < li_total_channels; j++)
-			{
-				if (((li_config_table[i].flag_table[j]) != 0)
-				    || ((li_config_table[j].flag_table[i]) != 0))
-				{
-					li_config_table[i].channel |= LI_CHANNEL_INVOLVED;
-				}
-				if (((li_config_table[i].flag_table[j] & LI_FLAG_CONFERENCE) != 0)
-				    || ((li_config_table[j].flag_table[i] & LI_FLAG_CONFERENCE) != 0))
-				{
-					li_config_table[i].channel |= LI_CHANNEL_CONFERENCE;
-				}
-			}
-		}
-	}
-	for (i = 0; i < li_total_channels; i++)
-	{
-		for (j = 0; j < li_total_channels; j++)
-		{
-			li_config_table[i].coef_table[j] &= ~(LI_COEF_CH_CH | LI_COEF_CH_PC | LI_COEF_PC_CH | LI_COEF_PC_PC);
-			if (li_config_table[i].flag_table[j] & LI_FLAG_CONFERENCE)
-				li_config_table[i].coef_table[j] |= LI_COEF_CH_CH;
-		}
-	}
-	for (n = 0; n < li_total_channels; n++)
-	{
-		if (li_config_table[n].channel & LI_CHANNEL_CONFERENCE)
-		{
-			for (i = 0; i < li_total_channels; i++)
-			{
-				if (li_config_table[i].channel & LI_CHANNEL_CONFERENCE)
-				{
-					for (j = 0; j < li_total_channels; j++)
-					{
-						li_config_table[i].coef_table[j] |=
-							li_config_table[i].coef_table[n] & li_config_table[n].coef_table[j];
-					}
-				}
-			}
-		}
-	}
-	for (i = 0; i < li_total_channels; i++)
-	{
-		if (li_config_table[i].channel & LI_CHANNEL_INVOLVED)
-		{
-			li_config_table[i].coef_table[i] &= ~LI_COEF_CH_CH;
-			for (j = 0; j < li_total_channels; j++)
-			{
-				if (li_config_table[i].coef_table[j] & LI_COEF_CH_CH)
-					li_config_table[i].flag_table[j] |= LI_FLAG_CONFERENCE;
-			}
-			if (li_config_table[i].flag_table[i] & LI_FLAG_CONFERENCE)
-				li_config_table[i].coef_table[i] |= LI_COEF_CH_CH;
-		}
-	}
-	for (i = 0; i < li_total_channels; i++)
-	{
-		if (li_config_table[i].channel & LI_CHANNEL_INVOLVED)
-		{
-			for (j = 0; j < li_total_channels; j++)
-			{
-				if (li_config_table[i].flag_table[j] & LI_FLAG_INTERCONNECT)
-					li_config_table[i].coef_table[j] |= LI_COEF_CH_CH;
-				if (li_config_table[i].flag_table[j] & LI_FLAG_MONITOR)
-					li_config_table[i].coef_table[j] |= LI_COEF_CH_PC;
-				if (li_config_table[i].flag_table[j] & LI_FLAG_MIX)
-					li_config_table[i].coef_table[j] |= LI_COEF_PC_CH;
-				if (li_config_table[i].flag_table[j] & LI_FLAG_PCCONNECT)
-					li_config_table[i].coef_table[j] |= LI_COEF_PC_PC;
-			}
-			if (li_config_table[i].chflags & LI_CHFLAG_MONITOR)
-			{
-				for (j = 0; j < li_total_channels; j++)
-				{
-					if (li_config_table[i].flag_table[j] & LI_FLAG_INTERCONNECT)
-					{
-						li_config_table[i].coef_table[j] |= LI_COEF_CH_PC;
-						if (li_config_table[j].chflags & LI_CHFLAG_MIX)
-							li_config_table[i].coef_table[j] |= LI_COEF_PC_CH | LI_COEF_PC_PC;
-					}
-				}
-			}
-			if (li_config_table[i].chflags & LI_CHFLAG_MIX)
-			{
-				for (j = 0; j < li_total_channels; j++)
-				{
-					if (li_config_table[j].flag_table[i] & LI_FLAG_INTERCONNECT)
-						li_config_table[j].coef_table[i] |= LI_COEF_PC_CH;
-				}
-			}
-			if (li_config_table[i].chflags & LI_CHFLAG_LOOP)
-			{
-				for (j = 0; j < li_total_channels; j++)
-				{
-					if (li_config_table[i].flag_table[j] & LI_FLAG_INTERCONNECT)
-					{
-						for (n = 0; n < li_total_channels; n++)
-						{
-							if (li_config_table[n].flag_table[i] & LI_FLAG_INTERCONNECT)
-							{
-								li_config_table[n].coef_table[j] |= LI_COEF_CH_CH;
-								if (li_config_table[j].chflags & LI_CHFLAG_MIX)
-								{
-									li_config_table[n].coef_table[j] |= LI_COEF_PC_CH;
-									if (li_config_table[n].chflags & LI_CHFLAG_MONITOR)
-										li_config_table[n].coef_table[j] |= LI_COEF_CH_PC | LI_COEF_PC_PC;
-								}
-								else if (li_config_table[n].chflags & LI_CHFLAG_MONITOR)
-									li_config_table[n].coef_table[j] |= LI_COEF_CH_PC;
-							}
-						}
-					}
-				}
-			}
-		}
-	}
-	for (i = 0; i < li_total_channels; i++)
-	{
-		if (li_config_table[i].channel & LI_CHANNEL_INVOLVED)
-		{
-			if (li_config_table[i].chflags & (LI_CHFLAG_MONITOR | LI_CHFLAG_MIX | LI_CHFLAG_LOOP))
-				li_config_table[i].channel |= LI_CHANNEL_ACTIVE;
-			if (li_config_table[i].chflags & LI_CHFLAG_MONITOR)
-				li_config_table[i].channel |= LI_CHANNEL_RX_DATA;
-			if (li_config_table[i].chflags & LI_CHFLAG_MIX)
-				li_config_table[i].channel |= LI_CHANNEL_TX_DATA;
-			for (j = 0; j < li_total_channels; j++)
-			{
-				if ((li_config_table[i].flag_table[j] &
-				     (LI_FLAG_INTERCONNECT | LI_FLAG_PCCONNECT | LI_FLAG_CONFERENCE | LI_FLAG_MONITOR))
-				    || (li_config_table[j].flag_table[i] &
-					(LI_FLAG_INTERCONNECT | LI_FLAG_PCCONNECT | LI_FLAG_CONFERENCE | LI_FLAG_ANNOUNCEMENT | LI_FLAG_MIX)))
-				{
-					li_config_table[i].channel |= LI_CHANNEL_ACTIVE;
-				}
-				if (li_config_table[i].flag_table[j] & (LI_FLAG_PCCONNECT | LI_FLAG_MONITOR))
-					li_config_table[i].channel |= LI_CHANNEL_RX_DATA;
-				if (li_config_table[j].flag_table[i] & (LI_FLAG_PCCONNECT | LI_FLAG_ANNOUNCEMENT | LI_FLAG_MIX))
-					li_config_table[i].channel |= LI_CHANNEL_TX_DATA;
-			}
-			if (!(li_config_table[i].channel & LI_CHANNEL_ACTIVE))
-			{
-				li_config_table[i].coef_table[i] |= LI_COEF_PC_CH | LI_COEF_CH_PC;
-				li_config_table[i].channel |= LI_CHANNEL_TX_DATA | LI_CHANNEL_RX_DATA;
-			}
-		}
-	}
-	for (i = 0; i < li_total_channels; i++)
-	{
-		if (li_config_table[i].channel & LI_CHANNEL_INVOLVED)
-		{
-			j = 0;
-			while ((j < li_total_channels) && !(li_config_table[i].flag_table[j] & LI_FLAG_ANNOUNCEMENT))
-				j++;
-			if (j < li_total_channels)
-			{
-				for (j = 0; j < li_total_channels; j++)
-				{
-					li_config_table[i].coef_table[j] &= ~(LI_COEF_CH_CH | LI_COEF_PC_CH);
-					if (li_config_table[i].flag_table[j] & LI_FLAG_ANNOUNCEMENT)
-						li_config_table[i].coef_table[j] |= LI_COEF_PC_CH;
-				}
-			}
-		}
-	}
-	n = li_total_channels;
-	if (n > MIXER_MAX_DUMP_CHANNELS)
-		n = MIXER_MAX_DUMP_CHANNELS;
-
-	p = hex_line;
-	for (j = 0; j < n; j++)
-	{
-		if ((j & 0x7) == 0)
-			*(p++) = ' ';
-		p = hex_byte_pack(p, li_config_table[j].curchnl);
-	}
-	*p = '\0';
-	dbug(1, dprintf("[%06lx] CURRENT %s",
-			(dword)(UnMapController(a->Id)), (char *)hex_line));
-	p = hex_line;
-	for (j = 0; j < n; j++)
-	{
-		if ((j & 0x7) == 0)
-			*(p++) = ' ';
-		p = hex_byte_pack(p, li_config_table[j].channel);
-	}
-	*p = '\0';
-	dbug(1, dprintf("[%06lx] CHANNEL %s",
-			(dword)(UnMapController(a->Id)), (char *)hex_line));
-	p = hex_line;
-	for (j = 0; j < n; j++)
-	{
-		if ((j & 0x7) == 0)
-			*(p++) = ' ';
-		p = hex_byte_pack(p, li_config_table[j].chflags);
-	}
-	*p = '\0';
-	dbug(1, dprintf("[%06lx] CHFLAG  %s",
-			(dword)(UnMapController(a->Id)), (char *)hex_line));
-	for (i = 0; i < n; i++)
-	{
-		p = hex_line;
-		for (j = 0; j < n; j++)
-		{
-			if ((j & 0x7) == 0)
-				*(p++) = ' ';
-			p = hex_byte_pack(p, li_config_table[i].flag_table[j]);
-		}
-		*p = '\0';
-		dbug(1, dprintf("[%06lx] FLAG[%02x]%s",
-				(dword)(UnMapController(a->Id)), i, (char *)hex_line));
-	}
-	for (i = 0; i < n; i++)
-	{
-		p = hex_line;
-		for (j = 0; j < n; j++)
-		{
-			if ((j & 0x7) == 0)
-				*(p++) = ' ';
-			p = hex_byte_pack(p, li_config_table[i].coef_table[j]);
-		}
-		*p = '\0';
-		dbug(1, dprintf("[%06lx] COEF[%02x]%s",
-				(dword)(UnMapController(a->Id)), i, (char *)hex_line));
-	}
-}
-
-
-static struct
-{
-	byte mask;
-	byte line_flags;
-} mixer_write_prog_pri[] =
-{
-	{ LI_COEF_CH_CH, 0 },
-	{ LI_COEF_CH_PC, MIXER_COEF_LINE_TO_PC_FLAG },
-	{ LI_COEF_PC_CH, MIXER_COEF_LINE_FROM_PC_FLAG },
-	{ LI_COEF_PC_PC, MIXER_COEF_LINE_TO_PC_FLAG | MIXER_COEF_LINE_FROM_PC_FLAG }
-};
-
-static struct
-{
-	byte from_ch;
-	byte to_ch;
-	byte mask;
-	byte xconnect_override;
-} mixer_write_prog_bri[] =
-{
-	{ 0, 0, LI_COEF_CH_CH, 0x01 },  /* B      to B      */
-	{ 1, 0, LI_COEF_CH_CH, 0x01 },  /* Alt B  to B      */
-	{ 0, 0, LI_COEF_PC_CH, 0x80 },  /* PC     to B      */
-	{ 1, 0, LI_COEF_PC_CH, 0x01 },  /* Alt PC to B      */
-	{ 2, 0, LI_COEF_CH_CH, 0x00 },  /* IC     to B      */
-	{ 3, 0, LI_COEF_CH_CH, 0x00 },  /* Alt IC to B      */
-	{ 0, 0, LI_COEF_CH_PC, 0x80 },  /* B      to PC     */
-	{ 1, 0, LI_COEF_CH_PC, 0x01 },  /* Alt B  to PC     */
-	{ 0, 0, LI_COEF_PC_PC, 0x01 },  /* PC     to PC     */
-	{ 1, 0, LI_COEF_PC_PC, 0x01 },  /* Alt PC to PC     */
-	{ 2, 0, LI_COEF_CH_PC, 0x00 },  /* IC     to PC     */
-	{ 3, 0, LI_COEF_CH_PC, 0x00 },  /* Alt IC to PC     */
-	{ 0, 2, LI_COEF_CH_CH, 0x00 },  /* B      to IC     */
-	{ 1, 2, LI_COEF_CH_CH, 0x00 },  /* Alt B  to IC     */
-	{ 0, 2, LI_COEF_PC_CH, 0x00 },  /* PC     to IC     */
-	{ 1, 2, LI_COEF_PC_CH, 0x00 },  /* Alt PC to IC     */
-	{ 2, 2, LI_COEF_CH_CH, 0x00 },  /* IC     to IC     */
-	{ 3, 2, LI_COEF_CH_CH, 0x00 },  /* Alt IC to IC     */
-	{ 1, 1, LI_COEF_CH_CH, 0x01 },  /* Alt B  to Alt B  */
-	{ 0, 1, LI_COEF_CH_CH, 0x01 },  /* B      to Alt B  */
-	{ 1, 1, LI_COEF_PC_CH, 0x80 },  /* Alt PC to Alt B  */
-	{ 0, 1, LI_COEF_PC_CH, 0x01 },  /* PC     to Alt B  */
-	{ 3, 1, LI_COEF_CH_CH, 0x00 },  /* Alt IC to Alt B  */
-	{ 2, 1, LI_COEF_CH_CH, 0x00 },  /* IC     to Alt B  */
-	{ 1, 1, LI_COEF_CH_PC, 0x80 },  /* Alt B  to Alt PC */
-	{ 0, 1, LI_COEF_CH_PC, 0x01 },  /* B      to Alt PC */
-	{ 1, 1, LI_COEF_PC_PC, 0x01 },  /* Alt PC to Alt PC */
-	{ 0, 1, LI_COEF_PC_PC, 0x01 },  /* PC     to Alt PC */
-	{ 3, 1, LI_COEF_CH_PC, 0x00 },  /* Alt IC to Alt PC */
-	{ 2, 1, LI_COEF_CH_PC, 0x00 },  /* IC     to Alt PC */
-	{ 1, 3, LI_COEF_CH_CH, 0x00 },  /* Alt B  to Alt IC */
-	{ 0, 3, LI_COEF_CH_CH, 0x00 },  /* B      to Alt IC */
-	{ 1, 3, LI_COEF_PC_CH, 0x00 },  /* Alt PC to Alt IC */
-	{ 0, 3, LI_COEF_PC_CH, 0x00 },  /* PC     to Alt IC */
-	{ 3, 3, LI_COEF_CH_CH, 0x00 },  /* Alt IC to Alt IC */
-	{ 2, 3, LI_COEF_CH_CH, 0x00 }   /* IC     to Alt IC */
-};
-
-static byte mixer_swapped_index_bri[] =
-{
-	18,  /* B      to B      */
-	19,  /* Alt B  to B      */
-	20,  /* PC     to B      */
-	21,  /* Alt PC to B      */
-	22,  /* IC     to B      */
-	23,  /* Alt IC to B      */
-	24,  /* B      to PC     */
-	25,  /* Alt B  to PC     */
-	26,  /* PC     to PC     */
-	27,  /* Alt PC to PC     */
-	28,  /* IC     to PC     */
-	29,  /* Alt IC to PC     */
-	30,  /* B      to IC     */
-	31,  /* Alt B  to IC     */
-	32,  /* PC     to IC     */
-	33,  /* Alt PC to IC     */
-	34,  /* IC     to IC     */
-	35,  /* Alt IC to IC     */
-	0,   /* Alt B  to Alt B  */
-	1,   /* B      to Alt B  */
-	2,   /* Alt PC to Alt B  */
-	3,   /* PC     to Alt B  */
-	4,   /* Alt IC to Alt B  */
-	5,   /* IC     to Alt B  */
-	6,   /* Alt B  to Alt PC */
-	7,   /* B      to Alt PC */
-	8,   /* Alt PC to Alt PC */
-	9,   /* PC     to Alt PC */
-	10,  /* Alt IC to Alt PC */
-	11,  /* IC     to Alt PC */
-	12,  /* Alt B  to Alt IC */
-	13,  /* B      to Alt IC */
-	14,  /* Alt PC to Alt IC */
-	15,  /* PC     to Alt IC */
-	16,  /* Alt IC to Alt IC */
-	17   /* IC     to Alt IC */
-};
-
-static struct
-{
-	byte mask;
-	byte from_pc;
-	byte to_pc;
-} xconnect_write_prog[] =
-{
-	{ LI_COEF_CH_CH, false, false },
-	{ LI_COEF_CH_PC, false, true },
-	{ LI_COEF_PC_CH, true, false },
-	{ LI_COEF_PC_PC, true, true }
-};
-
-
-static void xconnect_query_addresses(PLCI *plci)
-{
-	DIVA_CAPI_ADAPTER *a;
-	word w, ch;
-	byte *p;
-
-	dbug(1, dprintf("[%06lx] %s,%d: xconnect_query_addresses",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	a = plci->adapter;
-	if (a->li_pri && ((plci->li_bchannel_id == 0)
-			  || (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci != plci)))
-	{
-		dbug(1, dprintf("[%06x] %s,%d: Channel id wiped out",
-				(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-				(char *)(FILE_), __LINE__));
-		return;
-	}
-	p = plci->internal_req_buffer;
-	ch = (a->li_pri) ? plci->li_bchannel_id - 1 : 0;
-	*(p++) = UDATA_REQUEST_XCONNECT_FROM;
-	w = ch;
-	*(p++) = (byte) w;
-	*(p++) = (byte)(w >> 8);
-	w = ch | XCONNECT_CHANNEL_PORT_PC;
-	*(p++) = (byte) w;
-	*(p++) = (byte)(w >> 8);
-	plci->NData[0].P = plci->internal_req_buffer;
-	plci->NData[0].PLength = p - plci->internal_req_buffer;
-	plci->NL.X = plci->NData;
-	plci->NL.ReqCh = 0;
-	plci->NL.Req = plci->nl_req = (byte) N_UDATA;
-	plci->adapter->request(&plci->NL);
-}
-
-
-static void xconnect_write_coefs(PLCI *plci, word internal_command)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: xconnect_write_coefs %04x",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__, internal_command));
-
-	plci->li_write_command = internal_command;
-	plci->li_write_channel = 0;
-}
-
-
-static byte xconnect_write_coefs_process(dword Id, PLCI *plci, byte Rc)
-{
-	DIVA_CAPI_ADAPTER *a;
-	word w, n, i, j, r, s, to_ch;
-	dword d;
-	byte *p;
-	struct xconnect_transfer_address_s   *transfer_address;
-	byte ch_map[MIXER_CHANNELS_BRI];
-
-	dbug(1, dprintf("[%06x] %s,%d: xconnect_write_coefs_process %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->li_write_channel));
-
-	a = plci->adapter;
-	if ((plci->li_bchannel_id == 0)
-	    || (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci != plci))
-	{
-		dbug(1, dprintf("[%06x] %s,%d: Channel id wiped out",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		return (true);
-	}
-	i = a->li_base + (plci->li_bchannel_id - 1);
-	j = plci->li_write_channel;
-	p = plci->internal_req_buffer;
-	if (j != 0)
-	{
-		if ((Rc != OK) && (Rc != OK_FC))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: LI write coefs failed %02x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-			return (false);
-		}
-	}
-	if (li_config_table[i].adapter->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)
-	{
-		r = 0;
-		s = 0;
-		if (j < li_total_channels)
-		{
-			if (li_config_table[i].channel & LI_CHANNEL_ADDRESSES_SET)
-			{
-				s = ((li_config_table[i].send_b.card_address.low | li_config_table[i].send_b.card_address.high) ?
-				     (LI_COEF_CH_CH | LI_COEF_CH_PC | LI_COEF_PC_CH | LI_COEF_PC_PC) : (LI_COEF_CH_PC | LI_COEF_PC_PC)) &
-					((li_config_table[i].send_pc.card_address.low | li_config_table[i].send_pc.card_address.high) ?
-					 (LI_COEF_CH_CH | LI_COEF_CH_PC | LI_COEF_PC_CH | LI_COEF_PC_PC) : (LI_COEF_CH_CH | LI_COEF_PC_CH));
-			}
-			r = ((li_config_table[i].coef_table[j] & 0xf) ^ (li_config_table[i].coef_table[j] >> 4));
-			while ((j < li_total_channels)
-			       && ((r == 0)
-				   || (!(li_config_table[j].channel & LI_CHANNEL_ADDRESSES_SET))
-				   || (!li_config_table[j].adapter->li_pri
-				       && (j >= li_config_table[j].adapter->li_base + MIXER_BCHANNELS_BRI))
-				   || (((li_config_table[j].send_b.card_address.low != li_config_table[i].send_b.card_address.low)
-					|| (li_config_table[j].send_b.card_address.high != li_config_table[i].send_b.card_address.high))
-				       && (!(a->manufacturer_features & MANUFACTURER_FEATURE_DMACONNECT)
-					   || !(li_config_table[j].adapter->manufacturer_features & MANUFACTURER_FEATURE_DMACONNECT)))
-				   || ((li_config_table[j].adapter->li_base != a->li_base)
-				       && !(r & s &
-					    ((li_config_table[j].send_b.card_address.low | li_config_table[j].send_b.card_address.high) ?
-					     (LI_COEF_CH_CH | LI_COEF_CH_PC | LI_COEF_PC_CH | LI_COEF_PC_PC) : (LI_COEF_PC_CH | LI_COEF_PC_PC)) &
-					    ((li_config_table[j].send_pc.card_address.low | li_config_table[j].send_pc.card_address.high) ?
-					     (LI_COEF_CH_CH | LI_COEF_CH_PC | LI_COEF_PC_CH | LI_COEF_PC_PC) : (LI_COEF_CH_CH | LI_COEF_CH_PC))))))
-			{
-				j++;
-				if (j < li_total_channels)
-					r = ((li_config_table[i].coef_table[j] & 0xf) ^ (li_config_table[i].coef_table[j] >> 4));
-			}
-		}
-		if (j < li_total_channels)
-		{
-			plci->internal_command = plci->li_write_command;
-			if (plci_nl_busy(plci))
-				return (true);
-			to_ch = (a->li_pri) ? plci->li_bchannel_id - 1 : 0;
-			*(p++) = UDATA_REQUEST_XCONNECT_TO;
-			do
-			{
-				if (li_config_table[j].adapter->li_base != a->li_base)
-				{
-					r &= s &
-						((li_config_table[j].send_b.card_address.low | li_config_table[j].send_b.card_address.high) ?
-						 (LI_COEF_CH_CH | LI_COEF_CH_PC | LI_COEF_PC_CH | LI_COEF_PC_PC) : (LI_COEF_PC_CH | LI_COEF_PC_PC)) &
-						((li_config_table[j].send_pc.card_address.low | li_config_table[j].send_pc.card_address.high) ?
-						 (LI_COEF_CH_CH | LI_COEF_CH_PC | LI_COEF_PC_CH | LI_COEF_PC_PC) : (LI_COEF_CH_CH | LI_COEF_CH_PC));
-				}
-				n = 0;
-				do
-				{
-					if (r & xconnect_write_prog[n].mask)
-					{
-						if (xconnect_write_prog[n].from_pc)
-							transfer_address = &(li_config_table[j].send_pc);
-						else
-							transfer_address = &(li_config_table[j].send_b);
-						d = transfer_address->card_address.low;
-						*(p++) = (byte) d;
-						*(p++) = (byte)(d >> 8);
-						*(p++) = (byte)(d >> 16);
-						*(p++) = (byte)(d >> 24);
-						d = transfer_address->card_address.high;
-						*(p++) = (byte) d;
-						*(p++) = (byte)(d >> 8);
-						*(p++) = (byte)(d >> 16);
-						*(p++) = (byte)(d >> 24);
-						d = transfer_address->offset;
-						*(p++) = (byte) d;
-						*(p++) = (byte)(d >> 8);
-						*(p++) = (byte)(d >> 16);
-						*(p++) = (byte)(d >> 24);
-						w = xconnect_write_prog[n].to_pc ? to_ch | XCONNECT_CHANNEL_PORT_PC : to_ch;
-						*(p++) = (byte) w;
-						*(p++) = (byte)(w >> 8);
-						w = ((li_config_table[i].coef_table[j] & xconnect_write_prog[n].mask) == 0) ? 0x01 :
-							(li_config_table[i].adapter->u_law ?
-							 (li_config_table[j].adapter->u_law ? 0x80 : 0x86) :
-							 (li_config_table[j].adapter->u_law ? 0x7a : 0x80));
-						*(p++) = (byte) w;
-						*(p++) = (byte) 0;
-						li_config_table[i].coef_table[j] ^= xconnect_write_prog[n].mask << 4;
-					}
-					n++;
-				} while ((n < ARRAY_SIZE(xconnect_write_prog))
-					 && ((p - plci->internal_req_buffer) + 16 < INTERNAL_REQ_BUFFER_SIZE));
-				if (n == ARRAY_SIZE(xconnect_write_prog))
-				{
-					do
-					{
-						j++;
-						if (j < li_total_channels)
-							r = ((li_config_table[i].coef_table[j] & 0xf) ^ (li_config_table[i].coef_table[j] >> 4));
-					} while ((j < li_total_channels)
-						 && ((r == 0)
-						     || (!(li_config_table[j].channel & LI_CHANNEL_ADDRESSES_SET))
-						     || (!li_config_table[j].adapter->li_pri
-							 && (j >= li_config_table[j].adapter->li_base + MIXER_BCHANNELS_BRI))
-						     || (((li_config_table[j].send_b.card_address.low != li_config_table[i].send_b.card_address.low)
-							  || (li_config_table[j].send_b.card_address.high != li_config_table[i].send_b.card_address.high))
-							 && (!(a->manufacturer_features & MANUFACTURER_FEATURE_DMACONNECT)
-							     || !(li_config_table[j].adapter->manufacturer_features & MANUFACTURER_FEATURE_DMACONNECT)))
-						     || ((li_config_table[j].adapter->li_base != a->li_base)
-							 && !(r & s &
-							      ((li_config_table[j].send_b.card_address.low | li_config_table[j].send_b.card_address.high) ?
-							       (LI_COEF_CH_CH | LI_COEF_CH_PC | LI_COEF_PC_CH | LI_COEF_PC_PC) : (LI_COEF_PC_CH | LI_COEF_PC_PC)) &
-							      ((li_config_table[j].send_pc.card_address.low | li_config_table[j].send_pc.card_address.high) ?
-							       (LI_COEF_CH_CH | LI_COEF_CH_PC | LI_COEF_PC_CH | LI_COEF_PC_PC) : (LI_COEF_CH_CH | LI_COEF_CH_PC))))));
-				}
-			} while ((j < li_total_channels)
-				 && ((p - plci->internal_req_buffer) + 16 < INTERNAL_REQ_BUFFER_SIZE));
-		}
-		else if (j == li_total_channels)
-		{
-			plci->internal_command = plci->li_write_command;
-			if (plci_nl_busy(plci))
-				return (true);
-			if (a->li_pri)
-			{
-				*(p++) = UDATA_REQUEST_SET_MIXER_COEFS_PRI_SYNC;
-				w = 0;
-				if (li_config_table[i].channel & LI_CHANNEL_TX_DATA)
-					w |= MIXER_FEATURE_ENABLE_TX_DATA;
-				if (li_config_table[i].channel & LI_CHANNEL_RX_DATA)
-					w |= MIXER_FEATURE_ENABLE_RX_DATA;
-				*(p++) = (byte) w;
-				*(p++) = (byte)(w >> 8);
-			}
-			else
-			{
-				*(p++) = UDATA_REQUEST_SET_MIXER_COEFS_BRI;
-				w = 0;
-				if ((plci->tel == ADV_VOICE) && (plci == a->AdvSignalPLCI)
-				    && (ADV_VOICE_NEW_COEF_BASE + sizeof(word) <= a->adv_voice_coef_length))
-				{
-					w = GET_WORD(a->adv_voice_coef_buffer + ADV_VOICE_NEW_COEF_BASE);
-				}
-				if (li_config_table[i].channel & LI_CHANNEL_TX_DATA)
-					w |= MIXER_FEATURE_ENABLE_TX_DATA;
-				if (li_config_table[i].channel & LI_CHANNEL_RX_DATA)
-					w |= MIXER_FEATURE_ENABLE_RX_DATA;
-				*(p++) = (byte) w;
-				*(p++) = (byte)(w >> 8);
-				for (j = 0; j < sizeof(ch_map); j += 2)
-				{
-					if (plci->li_bchannel_id == 2)
-					{
-						ch_map[j] = (byte)(j + 1);
-						ch_map[j + 1] = (byte) j;
-					}
-					else
-					{
-						ch_map[j] = (byte) j;
-						ch_map[j + 1] = (byte)(j + 1);
-					}
-				}
-				for (n = 0; n < ARRAY_SIZE(mixer_write_prog_bri); n++)
-				{
-					i = a->li_base + ch_map[mixer_write_prog_bri[n].to_ch];
-					j = a->li_base + ch_map[mixer_write_prog_bri[n].from_ch];
-					if (li_config_table[i].channel & li_config_table[j].channel & LI_CHANNEL_INVOLVED)
-					{
-						*p = (mixer_write_prog_bri[n].xconnect_override != 0) ?
-							mixer_write_prog_bri[n].xconnect_override :
-							((li_config_table[i].coef_table[j] & mixer_write_prog_bri[n].mask) ? 0x80 : 0x01);
-						if ((i >= a->li_base + MIXER_BCHANNELS_BRI) || (j >= a->li_base + MIXER_BCHANNELS_BRI))
-						{
-							w = ((li_config_table[i].coef_table[j] & 0xf) ^ (li_config_table[i].coef_table[j] >> 4));
-							li_config_table[i].coef_table[j] ^= (w & mixer_write_prog_bri[n].mask) << 4;
-						}
-					}
-					else
-					{
-						*p = 0x00;
-						if ((a->AdvSignalPLCI != NULL) && (a->AdvSignalPLCI->tel == ADV_VOICE))
-						{
-							w = (plci == a->AdvSignalPLCI) ? n : mixer_swapped_index_bri[n];
-							if (ADV_VOICE_NEW_COEF_BASE + sizeof(word) + w < a->adv_voice_coef_length)
-								*p = a->adv_voice_coef_buffer[ADV_VOICE_NEW_COEF_BASE + sizeof(word) + w];
-						}
-					}
-					p++;
-				}
-			}
-			j = li_total_channels + 1;
-		}
-	}
-	else
-	{
-		if (j <= li_total_channels)
-		{
-			plci->internal_command = plci->li_write_command;
-			if (plci_nl_busy(plci))
-				return (true);
-			if (j < a->li_base)
-				j = a->li_base;
-			if (a->li_pri)
-			{
-				*(p++) = UDATA_REQUEST_SET_MIXER_COEFS_PRI_SYNC;
-				w = 0;
-				if (li_config_table[i].channel & LI_CHANNEL_TX_DATA)
-					w |= MIXER_FEATURE_ENABLE_TX_DATA;
-				if (li_config_table[i].channel & LI_CHANNEL_RX_DATA)
-					w |= MIXER_FEATURE_ENABLE_RX_DATA;
-				*(p++) = (byte) w;
-				*(p++) = (byte)(w >> 8);
-				for (n = 0; n < ARRAY_SIZE(mixer_write_prog_pri); n++)
-				{
-					*(p++) = (byte)((plci->li_bchannel_id - 1) | mixer_write_prog_pri[n].line_flags);
-					for (j = a->li_base; j < a->li_base + MIXER_CHANNELS_PRI; j++)
-					{
-						w = ((li_config_table[i].coef_table[j] & 0xf) ^ (li_config_table[i].coef_table[j] >> 4));
-						if (w & mixer_write_prog_pri[n].mask)
-						{
-							*(p++) = (li_config_table[i].coef_table[j] & mixer_write_prog_pri[n].mask) ? 0x80 : 0x01;
-							li_config_table[i].coef_table[j] ^= mixer_write_prog_pri[n].mask << 4;
-						}
-						else
-							*(p++) = 0x00;
-					}
-					*(p++) = (byte)((plci->li_bchannel_id - 1) | MIXER_COEF_LINE_ROW_FLAG | mixer_write_prog_pri[n].line_flags);
-					for (j = a->li_base; j < a->li_base + MIXER_CHANNELS_PRI; j++)
-					{
-						w = ((li_config_table[j].coef_table[i] & 0xf) ^ (li_config_table[j].coef_table[i] >> 4));
-						if (w & mixer_write_prog_pri[n].mask)
-						{
-							*(p++) = (li_config_table[j].coef_table[i] & mixer_write_prog_pri[n].mask) ? 0x80 : 0x01;
-							li_config_table[j].coef_table[i] ^= mixer_write_prog_pri[n].mask << 4;
-						}
-						else
-							*(p++) = 0x00;
-					}
-				}
-			}
-			else
-			{
-				*(p++) = UDATA_REQUEST_SET_MIXER_COEFS_BRI;
-				w = 0;
-				if ((plci->tel == ADV_VOICE) && (plci == a->AdvSignalPLCI)
-				    && (ADV_VOICE_NEW_COEF_BASE + sizeof(word) <= a->adv_voice_coef_length))
-				{
-					w = GET_WORD(a->adv_voice_coef_buffer + ADV_VOICE_NEW_COEF_BASE);
-				}
-				if (li_config_table[i].channel & LI_CHANNEL_TX_DATA)
-					w |= MIXER_FEATURE_ENABLE_TX_DATA;
-				if (li_config_table[i].channel & LI_CHANNEL_RX_DATA)
-					w |= MIXER_FEATURE_ENABLE_RX_DATA;
-				*(p++) = (byte) w;
-				*(p++) = (byte)(w >> 8);
-				for (j = 0; j < sizeof(ch_map); j += 2)
-				{
-					if (plci->li_bchannel_id == 2)
-					{
-						ch_map[j] = (byte)(j + 1);
-						ch_map[j + 1] = (byte) j;
-					}
-					else
-					{
-						ch_map[j] = (byte) j;
-						ch_map[j + 1] = (byte)(j + 1);
-					}
-				}
-				for (n = 0; n < ARRAY_SIZE(mixer_write_prog_bri); n++)
-				{
-					i = a->li_base + ch_map[mixer_write_prog_bri[n].to_ch];
-					j = a->li_base + ch_map[mixer_write_prog_bri[n].from_ch];
-					if (li_config_table[i].channel & li_config_table[j].channel & LI_CHANNEL_INVOLVED)
-					{
-						*p = ((li_config_table[i].coef_table[j] & mixer_write_prog_bri[n].mask) ? 0x80 : 0x01);
-						w = ((li_config_table[i].coef_table[j] & 0xf) ^ (li_config_table[i].coef_table[j] >> 4));
-						li_config_table[i].coef_table[j] ^= (w & mixer_write_prog_bri[n].mask) << 4;
-					}
-					else
-					{
-						*p = 0x00;
-						if ((a->AdvSignalPLCI != NULL) && (a->AdvSignalPLCI->tel == ADV_VOICE))
-						{
-							w = (plci == a->AdvSignalPLCI) ? n : mixer_swapped_index_bri[n];
-							if (ADV_VOICE_NEW_COEF_BASE + sizeof(word) + w < a->adv_voice_coef_length)
-								*p = a->adv_voice_coef_buffer[ADV_VOICE_NEW_COEF_BASE + sizeof(word) + w];
-						}
-					}
-					p++;
-				}
-			}
-			j = li_total_channels + 1;
-		}
-	}
-	plci->li_write_channel = j;
-	if (p != plci->internal_req_buffer)
-	{
-		plci->NData[0].P = plci->internal_req_buffer;
-		plci->NData[0].PLength = p - plci->internal_req_buffer;
-		plci->NL.X = plci->NData;
-		plci->NL.ReqCh = 0;
-		plci->NL.Req = plci->nl_req = (byte) N_UDATA;
-		plci->adapter->request(&plci->NL);
-	}
-	return (true);
-}
-
-
-static void mixer_notify_update(PLCI *plci, byte others)
-{
-	DIVA_CAPI_ADAPTER *a;
-	word i, w;
-	PLCI *notify_plci;
-	byte msg[sizeof(CAPI_MSG_HEADER) + 6];
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_notify_update %d",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__, others));
-
-	a = plci->adapter;
-	if (a->profile.Global_Options & GL_LINE_INTERCONNECT_SUPPORTED)
-	{
-		if (others)
-			plci->li_notify_update = true;
-		i = 0;
-		do
-		{
-			notify_plci = NULL;
-			if (others)
-			{
-				while ((i < li_total_channels) && (li_config_table[i].plci == NULL))
-					i++;
-				if (i < li_total_channels)
-					notify_plci = li_config_table[i++].plci;
-			}
-			else
-			{
-				if ((plci->li_bchannel_id != 0)
-				    && (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == plci))
-				{
-					notify_plci = plci;
-				}
-			}
-			if ((notify_plci != NULL)
-			    && !notify_plci->li_notify_update
-			    && (notify_plci->appl != NULL)
-			    && (notify_plci->State)
-			    && notify_plci->NL.Id && !notify_plci->nl_remove_id)
-			{
-				notify_plci->li_notify_update = true;
-				((CAPI_MSG *) msg)->header.length = 18;
-				((CAPI_MSG *) msg)->header.appl_id = notify_plci->appl->Id;
-				((CAPI_MSG *) msg)->header.command = _FACILITY_R;
-				((CAPI_MSG *) msg)->header.number = 0;
-				((CAPI_MSG *) msg)->header.controller = notify_plci->adapter->Id;
-				((CAPI_MSG *) msg)->header.plci = notify_plci->Id;
-				((CAPI_MSG *) msg)->header.ncci = 0;
-				((CAPI_MSG *) msg)->info.facility_req.Selector = SELECTOR_LINE_INTERCONNECT;
-				((CAPI_MSG *) msg)->info.facility_req.structs[0] = 3;
-				((CAPI_MSG *) msg)->info.facility_req.structs[1] = LI_REQ_SILENT_UPDATE & 0xff;
-				((CAPI_MSG *) msg)->info.facility_req.structs[2] = LI_REQ_SILENT_UPDATE >> 8;
-				((CAPI_MSG *) msg)->info.facility_req.structs[3] = 0;
-				w = api_put(notify_plci->appl, (CAPI_MSG *) msg);
-				if (w != _QUEUE_FULL)
-				{
-					if (w != 0)
-					{
-						dbug(1, dprintf("[%06lx] %s,%d: Interconnect notify failed %06x %d",
-								(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-								(char *)(FILE_), __LINE__,
-								(dword)((notify_plci->Id << 8) | UnMapController(notify_plci->adapter->Id)), w));
-					}
-					notify_plci->li_notify_update = false;
-				}
-			}
-		} while (others && (notify_plci != NULL));
-		if (others)
-			plci->li_notify_update = false;
-	}
-}
-
-
-static void mixer_clear_config(PLCI *plci)
-{
-	DIVA_CAPI_ADAPTER *a;
-	word i, j;
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_clear_config",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	plci->li_notify_update = false;
-	plci->li_plci_b_write_pos = 0;
-	plci->li_plci_b_read_pos = 0;
-	plci->li_plci_b_req_pos = 0;
-	a = plci->adapter;
-	if ((plci->li_bchannel_id != 0)
-	    && (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == plci))
-	{
-		i = a->li_base + (plci->li_bchannel_id - 1);
-		li_config_table[i].curchnl = 0;
-		li_config_table[i].channel = 0;
-		li_config_table[i].chflags = 0;
-		for (j = 0; j < li_total_channels; j++)
-		{
-			li_config_table[j].flag_table[i] = 0;
-			li_config_table[i].flag_table[j] = 0;
-			li_config_table[i].coef_table[j] = 0;
-			li_config_table[j].coef_table[i] = 0;
-		}
-		if (!a->li_pri)
-		{
-			li_config_table[i].coef_table[i] |= LI_COEF_CH_PC_SET | LI_COEF_PC_CH_SET;
-			if ((plci->tel == ADV_VOICE) && (plci == a->AdvSignalPLCI))
-			{
-				i = a->li_base + MIXER_IC_CHANNEL_BASE + (plci->li_bchannel_id - 1);
-				li_config_table[i].curchnl = 0;
-				li_config_table[i].channel = 0;
-				li_config_table[i].chflags = 0;
-				for (j = 0; j < li_total_channels; j++)
-				{
-					li_config_table[i].flag_table[j] = 0;
-					li_config_table[j].flag_table[i] = 0;
-					li_config_table[i].coef_table[j] = 0;
-					li_config_table[j].coef_table[i] = 0;
-				}
-				if (a->manufacturer_features & MANUFACTURER_FEATURE_SLAVE_CODEC)
-				{
-					i = a->li_base + MIXER_IC_CHANNEL_BASE + (2 - plci->li_bchannel_id);
-					li_config_table[i].curchnl = 0;
-					li_config_table[i].channel = 0;
-					li_config_table[i].chflags = 0;
-					for (j = 0; j < li_total_channels; j++)
-					{
-						li_config_table[i].flag_table[j] = 0;
-						li_config_table[j].flag_table[i] = 0;
-						li_config_table[i].coef_table[j] = 0;
-						li_config_table[j].coef_table[i] = 0;
-					}
-				}
-			}
-		}
-	}
-}
-
-
-static void mixer_prepare_switch(dword Id, PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_prepare_switch",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-	do
-	{
-		mixer_indication_coefs_set(Id, plci);
-	} while (plci->li_plci_b_read_pos != plci->li_plci_b_req_pos);
-}
-
-
-static word mixer_save_config(dword Id, PLCI *plci, byte Rc)
-{
-	DIVA_CAPI_ADAPTER *a;
-	word i, j;
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_save_config %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->adjust_b_state));
-
-	a = plci->adapter;
-	if ((plci->li_bchannel_id != 0)
-	    && (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == plci))
-	{
-		i = a->li_base + (plci->li_bchannel_id - 1);
-		for (j = 0; j < li_total_channels; j++)
-		{
-			li_config_table[i].coef_table[j] &= 0xf;
-			li_config_table[j].coef_table[i] &= 0xf;
-		}
-		if (!a->li_pri)
-			li_config_table[i].coef_table[i] |= LI_COEF_CH_PC_SET | LI_COEF_PC_CH_SET;
-	}
-	return (GOOD);
-}
-
-
-static word mixer_restore_config(dword Id, PLCI *plci, byte Rc)
-{
-	DIVA_CAPI_ADAPTER *a;
-	word Info;
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_restore_config %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->adjust_b_state));
-
-	Info = GOOD;
-	a = plci->adapter;
-	if ((plci->B1_facilities & B1_FACILITY_MIXER)
-	    && (plci->li_bchannel_id != 0)
-	    && (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == plci))
-	{
-		switch (plci->adjust_b_state)
-		{
-		case ADJUST_B_RESTORE_MIXER_1:
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)
-			{
-				plci->internal_command = plci->adjust_b_command;
-				if (plci_nl_busy(plci))
-				{
-					plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_1;
-					break;
-				}
-				xconnect_query_addresses(plci);
-				plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_2;
-				break;
-			}
-			plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_5;
-			Rc = OK;
-			/* fall through */
-		case ADJUST_B_RESTORE_MIXER_2:
-		case ADJUST_B_RESTORE_MIXER_3:
-		case ADJUST_B_RESTORE_MIXER_4:
-			if ((Rc != OK) && (Rc != OK_FC) && (Rc != 0))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Adjust B query addresses failed %02x",
-						UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-				Info = _WRONG_STATE;
-				break;
-			}
-			if (Rc == OK)
-			{
-				if (plci->adjust_b_state == ADJUST_B_RESTORE_MIXER_2)
-					plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_3;
-				else if (plci->adjust_b_state == ADJUST_B_RESTORE_MIXER_4)
-					plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_5;
-			}
-			else if (Rc == 0)
-			{
-				if (plci->adjust_b_state == ADJUST_B_RESTORE_MIXER_2)
-					plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_4;
-				else if (plci->adjust_b_state == ADJUST_B_RESTORE_MIXER_3)
-					plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_5;
-			}
-			if (plci->adjust_b_state != ADJUST_B_RESTORE_MIXER_5)
-			{
-				plci->internal_command = plci->adjust_b_command;
-				break;
-			}
-			/* fall through */
-		case ADJUST_B_RESTORE_MIXER_5:
-			xconnect_write_coefs(plci, plci->adjust_b_command);
-			plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_6;
-			Rc = OK;
-			/* fall through */
-		case ADJUST_B_RESTORE_MIXER_6:
-			if (!xconnect_write_coefs_process(Id, plci, Rc))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Write mixer coefs failed",
-						UnMapId(Id), (char *)(FILE_), __LINE__));
-				Info = _FACILITY_NOT_SUPPORTED;
-				break;
-			}
-			if (plci->internal_command)
-				break;
-			plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_7;
-		case ADJUST_B_RESTORE_MIXER_7:
-			break;
-		}
-	}
-	return (Info);
-}
-
-
-static void mixer_command(dword Id, PLCI *plci, byte Rc)
-{
-	DIVA_CAPI_ADAPTER *a;
-	word i, internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_command %02x %04x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command,
-			plci->li_cmd));
-
-	a = plci->adapter;
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (plci->li_cmd)
-	{
-	case LI_REQ_CONNECT:
-	case LI_REQ_DISCONNECT:
-	case LI_REQ_SILENT_UPDATE:
-		switch (internal_command)
-		{
-		default:
-			if (plci->li_channel_bits & LI_CHANNEL_INVOLVED)
-			{
-				adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities |
-									  B1_FACILITY_MIXER), MIXER_COMMAND_1);
-			}
-			/* fall through */
-		case MIXER_COMMAND_1:
-			if (plci->li_channel_bits & LI_CHANNEL_INVOLVED)
-			{
-				if (adjust_b_process(Id, plci, Rc) != GOOD)
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Load mixer failed",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					break;
-				}
-				if (plci->internal_command)
-					return;
-			}
-			plci->li_plci_b_req_pos = plci->li_plci_b_write_pos;
-			if ((plci->li_channel_bits & LI_CHANNEL_INVOLVED)
-			    || ((get_b1_facilities(plci, plci->B1_resource) & B1_FACILITY_MIXER)
-				&& (add_b1_facilities(plci, plci->B1_resource, (word)(plci->B1_facilities &
-										      ~B1_FACILITY_MIXER)) == plci->B1_resource)))
-			{
-				xconnect_write_coefs(plci, MIXER_COMMAND_2);
-			}
-			else
-			{
-				do
-				{
-					mixer_indication_coefs_set(Id, plci);
-				} while (plci->li_plci_b_read_pos != plci->li_plci_b_req_pos);
-			}
-			/* fall through */
-		case MIXER_COMMAND_2:
-			if ((plci->li_channel_bits & LI_CHANNEL_INVOLVED)
-			    || ((get_b1_facilities(plci, plci->B1_resource) & B1_FACILITY_MIXER)
-				&& (add_b1_facilities(plci, plci->B1_resource, (word)(plci->B1_facilities &
-										      ~B1_FACILITY_MIXER)) == plci->B1_resource)))
-			{
-				if (!xconnect_write_coefs_process(Id, plci, Rc))
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Write mixer coefs failed",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					if (plci->li_plci_b_write_pos != plci->li_plci_b_req_pos)
-					{
-						do
-						{
-							plci->li_plci_b_write_pos = (plci->li_plci_b_write_pos == 0) ?
-								LI_PLCI_B_QUEUE_ENTRIES - 1 : plci->li_plci_b_write_pos - 1;
-							i = (plci->li_plci_b_write_pos == 0) ?
-								LI_PLCI_B_QUEUE_ENTRIES - 1 : plci->li_plci_b_write_pos - 1;
-						} while ((plci->li_plci_b_write_pos != plci->li_plci_b_req_pos)
-							 && !(plci->li_plci_b_queue[i] & LI_PLCI_B_LAST_FLAG));
-					}
-					break;
-				}
-				if (plci->internal_command)
-					return;
-			}
-			if (!(plci->li_channel_bits & LI_CHANNEL_INVOLVED))
-			{
-				adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities &
-									  ~B1_FACILITY_MIXER), MIXER_COMMAND_3);
-			}
-			/* fall through */
-		case MIXER_COMMAND_3:
-			if (!(plci->li_channel_bits & LI_CHANNEL_INVOLVED))
-			{
-				if (adjust_b_process(Id, plci, Rc) != GOOD)
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Unload mixer failed",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					break;
-				}
-				if (plci->internal_command)
-					return;
-			}
-			break;
-		}
-		break;
-	}
-	if ((plci->li_bchannel_id == 0)
-	    || (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci != plci))
-	{
-		dbug(1, dprintf("[%06x] %s,%d: Channel id wiped out %d",
-				UnMapId(Id), (char *)(FILE_), __LINE__, (int)(plci->li_bchannel_id)));
-	}
-	else
-	{
-		i = a->li_base + (plci->li_bchannel_id - 1);
-		li_config_table[i].curchnl = plci->li_channel_bits;
-		if (!a->li_pri && (plci->tel == ADV_VOICE) && (plci == a->AdvSignalPLCI))
-		{
-			i = a->li_base + MIXER_IC_CHANNEL_BASE + (plci->li_bchannel_id - 1);
-			li_config_table[i].curchnl = plci->li_channel_bits;
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_SLAVE_CODEC)
-			{
-				i = a->li_base + MIXER_IC_CHANNEL_BASE + (2 - plci->li_bchannel_id);
-				li_config_table[i].curchnl = plci->li_channel_bits;
-			}
-		}
-	}
-}
-
-
-static void li_update_connect(dword Id, DIVA_CAPI_ADAPTER *a, PLCI *plci,
-			      dword plci_b_id, byte connect, dword li_flags)
-{
-	word i, ch_a, ch_a_v, ch_a_s, ch_b, ch_b_v, ch_b_s;
-	PLCI *plci_b;
-	DIVA_CAPI_ADAPTER *a_b;
-
-	a_b = &(adapter[MapController((byte)(plci_b_id & 0x7f)) - 1]);
-	plci_b = &(a_b->plci[((plci_b_id >> 8) & 0xff) - 1]);
-	ch_a = a->li_base + (plci->li_bchannel_id - 1);
-	if (!a->li_pri && (plci->tel == ADV_VOICE)
-	    && (plci == a->AdvSignalPLCI) && (Id & EXT_CONTROLLER))
-	{
-		ch_a_v = ch_a + MIXER_IC_CHANNEL_BASE;
-		ch_a_s = (a->manufacturer_features & MANUFACTURER_FEATURE_SLAVE_CODEC) ?
-			a->li_base + MIXER_IC_CHANNEL_BASE + (2 - plci->li_bchannel_id) : ch_a_v;
-	}
-	else
-	{
-		ch_a_v = ch_a;
-		ch_a_s = ch_a;
-	}
-	ch_b = a_b->li_base + (plci_b->li_bchannel_id - 1);
-	if (!a_b->li_pri && (plci_b->tel == ADV_VOICE)
-	    && (plci_b == a_b->AdvSignalPLCI) && (plci_b_id & EXT_CONTROLLER))
-	{
-		ch_b_v = ch_b + MIXER_IC_CHANNEL_BASE;
-		ch_b_s = (a_b->manufacturer_features & MANUFACTURER_FEATURE_SLAVE_CODEC) ?
-			a_b->li_base + MIXER_IC_CHANNEL_BASE + (2 - plci_b->li_bchannel_id) : ch_b_v;
-	}
-	else
-	{
-		ch_b_v = ch_b;
-		ch_b_s = ch_b;
-	}
-	if (connect)
-	{
-		li_config_table[ch_a].flag_table[ch_a_v] &= ~LI_FLAG_MONITOR;
-		li_config_table[ch_a].flag_table[ch_a_s] &= ~LI_FLAG_MONITOR;
-		li_config_table[ch_a_v].flag_table[ch_a] &= ~(LI_FLAG_ANNOUNCEMENT | LI_FLAG_MIX);
-		li_config_table[ch_a_s].flag_table[ch_a] &= ~(LI_FLAG_ANNOUNCEMENT | LI_FLAG_MIX);
-	}
-	li_config_table[ch_a].flag_table[ch_b_v] &= ~LI_FLAG_MONITOR;
-	li_config_table[ch_a].flag_table[ch_b_s] &= ~LI_FLAG_MONITOR;
-	li_config_table[ch_b_v].flag_table[ch_a] &= ~(LI_FLAG_ANNOUNCEMENT | LI_FLAG_MIX);
-	li_config_table[ch_b_s].flag_table[ch_a] &= ~(LI_FLAG_ANNOUNCEMENT | LI_FLAG_MIX);
-	if (ch_a_v == ch_b_v)
-	{
-		li_config_table[ch_a_v].flag_table[ch_b_v] &= ~LI_FLAG_CONFERENCE;
-		li_config_table[ch_a_s].flag_table[ch_b_s] &= ~LI_FLAG_CONFERENCE;
-	}
-	else
-	{
-		if (li_config_table[ch_a_v].flag_table[ch_b_v] & LI_FLAG_CONFERENCE)
-		{
-			for (i = 0; i < li_total_channels; i++)
-			{
-				if (i != ch_a_v)
-					li_config_table[ch_a_v].flag_table[i] &= ~LI_FLAG_CONFERENCE;
-			}
-		}
-		if (li_config_table[ch_a_s].flag_table[ch_b_v] & LI_FLAG_CONFERENCE)
-		{
-			for (i = 0; i < li_total_channels; i++)
-			{
-				if (i != ch_a_s)
-					li_config_table[ch_a_s].flag_table[i] &= ~LI_FLAG_CONFERENCE;
-			}
-		}
-		if (li_config_table[ch_b_v].flag_table[ch_a_v] & LI_FLAG_CONFERENCE)
-		{
-			for (i = 0; i < li_total_channels; i++)
-			{
-				if (i != ch_a_v)
-					li_config_table[i].flag_table[ch_a_v] &= ~LI_FLAG_CONFERENCE;
-			}
-		}
-		if (li_config_table[ch_b_v].flag_table[ch_a_s] & LI_FLAG_CONFERENCE)
-		{
-			for (i = 0; i < li_total_channels; i++)
-			{
-				if (i != ch_a_s)
-					li_config_table[i].flag_table[ch_a_s] &= ~LI_FLAG_CONFERENCE;
-			}
-		}
-	}
-	if (li_flags & LI_FLAG_CONFERENCE_A_B)
-	{
-		li_config_table[ch_b_v].flag_table[ch_a_v] |= LI_FLAG_CONFERENCE;
-		li_config_table[ch_b_s].flag_table[ch_a_v] |= LI_FLAG_CONFERENCE;
-		li_config_table[ch_b_v].flag_table[ch_a_s] |= LI_FLAG_CONFERENCE;
-		li_config_table[ch_b_s].flag_table[ch_a_s] |= LI_FLAG_CONFERENCE;
-	}
-	if (li_flags & LI_FLAG_CONFERENCE_B_A)
-	{
-		li_config_table[ch_a_v].flag_table[ch_b_v] |= LI_FLAG_CONFERENCE;
-		li_config_table[ch_a_v].flag_table[ch_b_s] |= LI_FLAG_CONFERENCE;
-		li_config_table[ch_a_s].flag_table[ch_b_v] |= LI_FLAG_CONFERENCE;
-		li_config_table[ch_a_s].flag_table[ch_b_s] |= LI_FLAG_CONFERENCE;
-	}
-	if (li_flags & LI_FLAG_MONITOR_A)
-	{
-		li_config_table[ch_a].flag_table[ch_a_v] |= LI_FLAG_MONITOR;
-		li_config_table[ch_a].flag_table[ch_a_s] |= LI_FLAG_MONITOR;
-	}
-	if (li_flags & LI_FLAG_MONITOR_B)
-	{
-		li_config_table[ch_a].flag_table[ch_b_v] |= LI_FLAG_MONITOR;
-		li_config_table[ch_a].flag_table[ch_b_s] |= LI_FLAG_MONITOR;
-	}
-	if (li_flags & LI_FLAG_ANNOUNCEMENT_A)
-	{
-		li_config_table[ch_a_v].flag_table[ch_a] |= LI_FLAG_ANNOUNCEMENT;
-		li_config_table[ch_a_s].flag_table[ch_a] |= LI_FLAG_ANNOUNCEMENT;
-	}
-	if (li_flags & LI_FLAG_ANNOUNCEMENT_B)
-	{
-		li_config_table[ch_b_v].flag_table[ch_a] |= LI_FLAG_ANNOUNCEMENT;
-		li_config_table[ch_b_s].flag_table[ch_a] |= LI_FLAG_ANNOUNCEMENT;
-	}
-	if (li_flags & LI_FLAG_MIX_A)
-	{
-		li_config_table[ch_a_v].flag_table[ch_a] |= LI_FLAG_MIX;
-		li_config_table[ch_a_s].flag_table[ch_a] |= LI_FLAG_MIX;
-	}
-	if (li_flags & LI_FLAG_MIX_B)
-	{
-		li_config_table[ch_b_v].flag_table[ch_a] |= LI_FLAG_MIX;
-		li_config_table[ch_b_s].flag_table[ch_a] |= LI_FLAG_MIX;
-	}
-	if (ch_a_v != ch_a_s)
-	{
-		li_config_table[ch_a_v].flag_table[ch_a_s] |= LI_FLAG_CONFERENCE;
-		li_config_table[ch_a_s].flag_table[ch_a_v] |= LI_FLAG_CONFERENCE;
-	}
-	if (ch_b_v != ch_b_s)
-	{
-		li_config_table[ch_b_v].flag_table[ch_b_s] |= LI_FLAG_CONFERENCE;
-		li_config_table[ch_b_s].flag_table[ch_b_v] |= LI_FLAG_CONFERENCE;
-	}
-}
-
-
-static void li2_update_connect(dword Id, DIVA_CAPI_ADAPTER *a, PLCI *plci,
-			       dword plci_b_id, byte connect, dword li_flags)
-{
-	word ch_a, ch_a_v, ch_a_s, ch_b, ch_b_v, ch_b_s;
-	PLCI *plci_b;
-	DIVA_CAPI_ADAPTER *a_b;
-
-	a_b = &(adapter[MapController((byte)(plci_b_id & 0x7f)) - 1]);
-	plci_b = &(a_b->plci[((plci_b_id >> 8) & 0xff) - 1]);
-	ch_a = a->li_base + (plci->li_bchannel_id - 1);
-	if (!a->li_pri && (plci->tel == ADV_VOICE)
-	    && (plci == a->AdvSignalPLCI) && (Id & EXT_CONTROLLER))
-	{
-		ch_a_v = ch_a + MIXER_IC_CHANNEL_BASE;
-		ch_a_s = (a->manufacturer_features & MANUFACTURER_FEATURE_SLAVE_CODEC) ?
-			a->li_base + MIXER_IC_CHANNEL_BASE + (2 - plci->li_bchannel_id) : ch_a_v;
-	}
-	else
-	{
-		ch_a_v = ch_a;
-		ch_a_s = ch_a;
-	}
-	ch_b = a_b->li_base + (plci_b->li_bchannel_id - 1);
-	if (!a_b->li_pri && (plci_b->tel == ADV_VOICE)
-	    && (plci_b == a_b->AdvSignalPLCI) && (plci_b_id & EXT_CONTROLLER))
-	{
-		ch_b_v = ch_b + MIXER_IC_CHANNEL_BASE;
-		ch_b_s = (a_b->manufacturer_features & MANUFACTURER_FEATURE_SLAVE_CODEC) ?
-			a_b->li_base + MIXER_IC_CHANNEL_BASE + (2 - plci_b->li_bchannel_id) : ch_b_v;
-	}
-	else
-	{
-		ch_b_v = ch_b;
-		ch_b_s = ch_b;
-	}
-	if (connect)
-	{
-		li_config_table[ch_b].flag_table[ch_b_v] &= ~LI_FLAG_MONITOR;
-		li_config_table[ch_b].flag_table[ch_b_s] &= ~LI_FLAG_MONITOR;
-		li_config_table[ch_b_v].flag_table[ch_b] &= ~LI_FLAG_MIX;
-		li_config_table[ch_b_s].flag_table[ch_b] &= ~LI_FLAG_MIX;
-		li_config_table[ch_b].flag_table[ch_b] &= ~LI_FLAG_PCCONNECT;
-		li_config_table[ch_b].chflags &= ~(LI_CHFLAG_MONITOR | LI_CHFLAG_MIX | LI_CHFLAG_LOOP);
-	}
-	li_config_table[ch_b_v].flag_table[ch_a_v] &= ~(LI_FLAG_INTERCONNECT | LI_FLAG_CONFERENCE);
-	li_config_table[ch_b_s].flag_table[ch_a_v] &= ~(LI_FLAG_INTERCONNECT | LI_FLAG_CONFERENCE);
-	li_config_table[ch_b_v].flag_table[ch_a_s] &= ~(LI_FLAG_INTERCONNECT | LI_FLAG_CONFERENCE);
-	li_config_table[ch_b_s].flag_table[ch_a_s] &= ~(LI_FLAG_INTERCONNECT | LI_FLAG_CONFERENCE);
-	li_config_table[ch_a_v].flag_table[ch_b_v] &= ~(LI_FLAG_INTERCONNECT | LI_FLAG_CONFERENCE);
-	li_config_table[ch_a_v].flag_table[ch_b_s] &= ~(LI_FLAG_INTERCONNECT | LI_FLAG_CONFERENCE);
-	li_config_table[ch_a_s].flag_table[ch_b_v] &= ~(LI_FLAG_INTERCONNECT | LI_FLAG_CONFERENCE);
-	li_config_table[ch_a_s].flag_table[ch_b_s] &= ~(LI_FLAG_INTERCONNECT | LI_FLAG_CONFERENCE);
-	if (li_flags & LI2_FLAG_INTERCONNECT_A_B)
-	{
-		li_config_table[ch_b_v].flag_table[ch_a_v] |= LI_FLAG_INTERCONNECT;
-		li_config_table[ch_b_s].flag_table[ch_a_v] |= LI_FLAG_INTERCONNECT;
-		li_config_table[ch_b_v].flag_table[ch_a_s] |= LI_FLAG_INTERCONNECT;
-		li_config_table[ch_b_s].flag_table[ch_a_s] |= LI_FLAG_INTERCONNECT;
-	}
-	if (li_flags & LI2_FLAG_INTERCONNECT_B_A)
-	{
-		li_config_table[ch_a_v].flag_table[ch_b_v] |= LI_FLAG_INTERCONNECT;
-		li_config_table[ch_a_v].flag_table[ch_b_s] |= LI_FLAG_INTERCONNECT;
-		li_config_table[ch_a_s].flag_table[ch_b_v] |= LI_FLAG_INTERCONNECT;
-		li_config_table[ch_a_s].flag_table[ch_b_s] |= LI_FLAG_INTERCONNECT;
-	}
-	if (li_flags & LI2_FLAG_MONITOR_B)
-	{
-		li_config_table[ch_b].flag_table[ch_b_v] |= LI_FLAG_MONITOR;
-		li_config_table[ch_b].flag_table[ch_b_s] |= LI_FLAG_MONITOR;
-	}
-	if (li_flags & LI2_FLAG_MIX_B)
-	{
-		li_config_table[ch_b_v].flag_table[ch_b] |= LI_FLAG_MIX;
-		li_config_table[ch_b_s].flag_table[ch_b] |= LI_FLAG_MIX;
-	}
-	if (li_flags & LI2_FLAG_MONITOR_X)
-		li_config_table[ch_b].chflags |= LI_CHFLAG_MONITOR;
-	if (li_flags & LI2_FLAG_MIX_X)
-		li_config_table[ch_b].chflags |= LI_CHFLAG_MIX;
-	if (li_flags & LI2_FLAG_LOOP_B)
-	{
-		li_config_table[ch_b_v].flag_table[ch_b_v] |= LI_FLAG_INTERCONNECT;
-		li_config_table[ch_b_s].flag_table[ch_b_v] |= LI_FLAG_INTERCONNECT;
-		li_config_table[ch_b_v].flag_table[ch_b_s] |= LI_FLAG_INTERCONNECT;
-		li_config_table[ch_b_s].flag_table[ch_b_s] |= LI_FLAG_INTERCONNECT;
-	}
-	if (li_flags & LI2_FLAG_LOOP_PC)
-		li_config_table[ch_b].flag_table[ch_b] |= LI_FLAG_PCCONNECT;
-	if (li_flags & LI2_FLAG_LOOP_X)
-		li_config_table[ch_b].chflags |= LI_CHFLAG_LOOP;
-	if (li_flags & LI2_FLAG_PCCONNECT_A_B)
-		li_config_table[ch_b_s].flag_table[ch_a_s] |= LI_FLAG_PCCONNECT;
-	if (li_flags & LI2_FLAG_PCCONNECT_B_A)
-		li_config_table[ch_a_s].flag_table[ch_b_s] |= LI_FLAG_PCCONNECT;
-	if (ch_a_v != ch_a_s)
-	{
-		li_config_table[ch_a_v].flag_table[ch_a_s] |= LI_FLAG_CONFERENCE;
-		li_config_table[ch_a_s].flag_table[ch_a_v] |= LI_FLAG_CONFERENCE;
-	}
-	if (ch_b_v != ch_b_s)
-	{
-		li_config_table[ch_b_v].flag_table[ch_b_s] |= LI_FLAG_CONFERENCE;
-		li_config_table[ch_b_s].flag_table[ch_b_v] |= LI_FLAG_CONFERENCE;
-	}
-}
-
-
-static word li_check_main_plci(dword Id, PLCI *plci)
-{
-	if (plci == NULL)
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: Wrong PLCI",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		return (_WRONG_IDENTIFIER);
-	}
-	if (!plci->State
-	    || !plci->NL.Id || plci->nl_remove_id
-	    || (plci->li_bchannel_id == 0))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: Wrong state",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		return (_WRONG_STATE);
-	}
-	li_config_table[plci->adapter->li_base + (plci->li_bchannel_id - 1)].plci = plci;
-	return (GOOD);
-}
-
-
-static PLCI *li_check_plci_b(dword Id, PLCI *plci,
-			     dword plci_b_id, word plci_b_write_pos, byte *p_result)
-{
-	byte ctlr_b;
-	PLCI *plci_b;
-
-	if (((plci->li_plci_b_read_pos > plci_b_write_pos) ? plci->li_plci_b_read_pos :
-	     LI_PLCI_B_QUEUE_ENTRIES + plci->li_plci_b_read_pos) - plci_b_write_pos - 1 < 2)
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: LI request overrun",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		PUT_WORD(p_result, _REQUEST_NOT_ALLOWED_IN_THIS_STATE);
-		return (NULL);
-	}
-	ctlr_b = 0;
-	if ((plci_b_id & 0x7f) != 0)
-	{
-		ctlr_b = MapController((byte)(plci_b_id & 0x7f));
-		if ((ctlr_b > max_adapter) || ((ctlr_b != 0) && (adapter[ctlr_b - 1].request == NULL)))
-			ctlr_b = 0;
-	}
-	if ((ctlr_b == 0)
-	    || (((plci_b_id >> 8) & 0xff) == 0)
-	    || (((plci_b_id >> 8) & 0xff) > adapter[ctlr_b - 1].max_plci))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: LI invalid second PLCI %08lx",
-				UnMapId(Id), (char *)(FILE_), __LINE__, plci_b_id));
-		PUT_WORD(p_result, _WRONG_IDENTIFIER);
-		return (NULL);
-	}
-	plci_b = &(adapter[ctlr_b - 1].plci[((plci_b_id >> 8) & 0xff) - 1]);
-	if (!plci_b->State
-	    || !plci_b->NL.Id || plci_b->nl_remove_id
-	    || (plci_b->li_bchannel_id == 0))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: LI peer in wrong state %08lx",
-				UnMapId(Id), (char *)(FILE_), __LINE__, plci_b_id));
-		PUT_WORD(p_result, _REQUEST_NOT_ALLOWED_IN_THIS_STATE);
-		return (NULL);
-	}
-	li_config_table[plci_b->adapter->li_base + (plci_b->li_bchannel_id - 1)].plci = plci_b;
-	if (((byte)(plci_b_id & ~EXT_CONTROLLER)) !=
-	    ((byte)(UnMapController(plci->adapter->Id) & ~EXT_CONTROLLER))
-	    && (!(plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)
-		|| !(plci_b->adapter->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: LI not on same ctrl %08lx",
-				UnMapId(Id), (char *)(FILE_), __LINE__, plci_b_id));
-		PUT_WORD(p_result, _WRONG_IDENTIFIER);
-		return (NULL);
-	}
-	if (!(get_b1_facilities(plci_b, add_b1_facilities(plci_b, plci_b->B1_resource,
-							  (word)(plci_b->B1_facilities | B1_FACILITY_MIXER))) & B1_FACILITY_MIXER))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: Interconnect peer cannot mix %d",
-				UnMapId(Id), (char *)(FILE_), __LINE__, plci_b->B1_resource));
-		PUT_WORD(p_result, _REQUEST_NOT_ALLOWED_IN_THIS_STATE);
-		return (NULL);
-	}
-	return (plci_b);
-}
-
-
-static PLCI *li2_check_plci_b(dword Id, PLCI *plci,
-			      dword plci_b_id, word plci_b_write_pos, byte *p_result)
-{
-	byte ctlr_b;
-	PLCI *plci_b;
-
-	if (((plci->li_plci_b_read_pos > plci_b_write_pos) ? plci->li_plci_b_read_pos :
-	     LI_PLCI_B_QUEUE_ENTRIES + plci->li_plci_b_read_pos) - plci_b_write_pos - 1 < 2)
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: LI request overrun",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		PUT_WORD(p_result, _WRONG_STATE);
-		return (NULL);
-	}
-	ctlr_b = 0;
-	if ((plci_b_id & 0x7f) != 0)
-	{
-		ctlr_b = MapController((byte)(plci_b_id & 0x7f));
-		if ((ctlr_b > max_adapter) || ((ctlr_b != 0) && (adapter[ctlr_b - 1].request == NULL)))
-			ctlr_b = 0;
-	}
-	if ((ctlr_b == 0)
-	    || (((plci_b_id >> 8) & 0xff) == 0)
-	    || (((plci_b_id >> 8) & 0xff) > adapter[ctlr_b - 1].max_plci))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: LI invalid second PLCI %08lx",
-				UnMapId(Id), (char *)(FILE_), __LINE__, plci_b_id));
-		PUT_WORD(p_result, _WRONG_IDENTIFIER);
-		return (NULL);
-	}
-	plci_b = &(adapter[ctlr_b - 1].plci[((plci_b_id >> 8) & 0xff) - 1]);
-	if (!plci_b->State
-	    || !plci_b->NL.Id || plci_b->nl_remove_id
-	    || (plci_b->li_bchannel_id == 0)
-	    || (li_config_table[plci_b->adapter->li_base + (plci_b->li_bchannel_id - 1)].plci != plci_b))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: LI peer in wrong state %08lx",
-				UnMapId(Id), (char *)(FILE_), __LINE__, plci_b_id));
-		PUT_WORD(p_result, _WRONG_STATE);
-		return (NULL);
-	}
-	if (((byte)(plci_b_id & ~EXT_CONTROLLER)) !=
-	    ((byte)(UnMapController(plci->adapter->Id) & ~EXT_CONTROLLER))
-	    && (!(plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)
-		|| !(plci_b->adapter->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: LI not on same ctrl %08lx",
-				UnMapId(Id), (char *)(FILE_), __LINE__, plci_b_id));
-		PUT_WORD(p_result, _WRONG_IDENTIFIER);
-		return (NULL);
-	}
-	if (!(get_b1_facilities(plci_b, add_b1_facilities(plci_b, plci_b->B1_resource,
-							  (word)(plci_b->B1_facilities | B1_FACILITY_MIXER))) & B1_FACILITY_MIXER))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: Interconnect peer cannot mix %d",
-				UnMapId(Id), (char *)(FILE_), __LINE__, plci_b->B1_resource));
-		PUT_WORD(p_result, _WRONG_STATE);
-		return (NULL);
-	}
-	return (plci_b);
-}
-
-
-static byte mixer_request(dword Id, word Number, DIVA_CAPI_ADAPTER *a, PLCI *plci, APPL   *appl, API_PARSE *msg)
-{
-	word Info;
-	word i;
-	dword d, li_flags, plci_b_id;
-	PLCI *plci_b;
-	API_PARSE li_parms[3];
-	API_PARSE li_req_parms[3];
-	API_PARSE li_participant_struct[2];
-	API_PARSE li_participant_parms[3];
-	word participant_parms_pos;
-	byte result_buffer[32];
-	byte *result;
-	word result_pos;
-	word plci_b_write_pos;
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_request",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-	Info = GOOD;
-	result = result_buffer;
-	result_buffer[0] = 0;
-	if (!(a->profile.Global_Options & GL_LINE_INTERCONNECT_SUPPORTED))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: Facility not supported",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		Info = _FACILITY_NOT_SUPPORTED;
-	}
-	else if (api_parse(&msg[1].info[1], msg[1].length, "ws", li_parms))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		Info = _WRONG_MESSAGE_FORMAT;
-	}
-	else
-	{
-		result_buffer[0] = 3;
-		PUT_WORD(&result_buffer[1], GET_WORD(li_parms[0].info));
-		result_buffer[3] = 0;
-		switch (GET_WORD(li_parms[0].info))
-		{
-		case LI_GET_SUPPORTED_SERVICES:
-			if (appl->appl_flags & APPL_FLAG_OLD_LI_SPEC)
-			{
-				result_buffer[0] = 17;
-				result_buffer[3] = 14;
-				PUT_WORD(&result_buffer[4], GOOD);
-				d = 0;
-				if (a->manufacturer_features & MANUFACTURER_FEATURE_MIXER_CH_CH)
-					d |= LI_CONFERENCING_SUPPORTED;
-				if (a->manufacturer_features & MANUFACTURER_FEATURE_MIXER_CH_PC)
-					d |= LI_MONITORING_SUPPORTED;
-				if (a->manufacturer_features & MANUFACTURER_FEATURE_MIXER_PC_CH)
-					d |= LI_ANNOUNCEMENTS_SUPPORTED | LI_MIXING_SUPPORTED;
-				if (a->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)
-					d |= LI_CROSS_CONTROLLER_SUPPORTED;
-				PUT_DWORD(&result_buffer[6], d);
-				if (a->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)
-				{
-					d = 0;
-					for (i = 0; i < li_total_channels; i++)
-					{
-						if ((li_config_table[i].adapter->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)
-						    && (li_config_table[i].adapter->li_pri
-							|| (i < li_config_table[i].adapter->li_base + MIXER_BCHANNELS_BRI)))
-						{
-							d++;
-						}
-					}
-				}
-				else
-				{
-					d = a->li_pri ? a->li_channels : MIXER_BCHANNELS_BRI;
-				}
-				PUT_DWORD(&result_buffer[10], d / 2);
-				PUT_DWORD(&result_buffer[14], d);
-			}
-			else
-			{
-				result_buffer[0] = 25;
-				result_buffer[3] = 22;
-				PUT_WORD(&result_buffer[4], GOOD);
-				d = LI2_ASYMMETRIC_SUPPORTED | LI2_B_LOOPING_SUPPORTED | LI2_X_LOOPING_SUPPORTED;
-				if (a->manufacturer_features & MANUFACTURER_FEATURE_MIXER_CH_PC)
-					d |= LI2_MONITORING_SUPPORTED | LI2_REMOTE_MONITORING_SUPPORTED;
-				if (a->manufacturer_features & MANUFACTURER_FEATURE_MIXER_PC_CH)
-					d |= LI2_MIXING_SUPPORTED | LI2_REMOTE_MIXING_SUPPORTED;
-				if (a->manufacturer_features & MANUFACTURER_FEATURE_MIXER_PC_PC)
-					d |= LI2_PC_LOOPING_SUPPORTED;
-				if (a->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)
-					d |= LI2_CROSS_CONTROLLER_SUPPORTED;
-				PUT_DWORD(&result_buffer[6], d);
-				d = a->li_pri ? a->li_channels : MIXER_BCHANNELS_BRI;
-				PUT_DWORD(&result_buffer[10], d / 2);
-				PUT_DWORD(&result_buffer[14], d - 1);
-				if (a->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)
-				{
-					d = 0;
-					for (i = 0; i < li_total_channels; i++)
-					{
-						if ((li_config_table[i].adapter->manufacturer_features & MANUFACTURER_FEATURE_XCONNECT)
-						    && (li_config_table[i].adapter->li_pri
-							|| (i < li_config_table[i].adapter->li_base + MIXER_BCHANNELS_BRI)))
-						{
-							d++;
-						}
-					}
-				}
-				PUT_DWORD(&result_buffer[18], d / 2);
-				PUT_DWORD(&result_buffer[22], d - 1);
-			}
-			break;
-
-		case LI_REQ_CONNECT:
-			if (li_parms[1].length == 8)
-			{
-				appl->appl_flags |= APPL_FLAG_OLD_LI_SPEC;
-				if (api_parse(&li_parms[1].info[1], li_parms[1].length, "dd", li_req_parms))
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				plci_b_id = GET_DWORD(li_req_parms[0].info) & 0xffff;
-				li_flags = GET_DWORD(li_req_parms[1].info);
-				Info = li_check_main_plci(Id, plci);
-				result_buffer[0] = 9;
-				result_buffer[3] = 6;
-				PUT_DWORD(&result_buffer[4], plci_b_id);
-				PUT_WORD(&result_buffer[8], GOOD);
-				if (Info != GOOD)
-					break;
-				result = plci->saved_msg.info;
-				for (i = 0; i <= result_buffer[0]; i++)
-					result[i] = result_buffer[i];
-				plci_b_write_pos = plci->li_plci_b_write_pos;
-				plci_b = li_check_plci_b(Id, plci, plci_b_id, plci_b_write_pos, &result[8]);
-				if (plci_b == NULL)
-					break;
-				li_update_connect(Id, a, plci, plci_b_id, true, li_flags);
-				plci->li_plci_b_queue[plci_b_write_pos] = plci_b_id | LI_PLCI_B_LAST_FLAG;
-				plci_b_write_pos = (plci_b_write_pos == LI_PLCI_B_QUEUE_ENTRIES - 1) ? 0 : plci_b_write_pos + 1;
-				plci->li_plci_b_write_pos = plci_b_write_pos;
-			}
-			else
-			{
-				appl->appl_flags &= ~APPL_FLAG_OLD_LI_SPEC;
-				if (api_parse(&li_parms[1].info[1], li_parms[1].length, "ds", li_req_parms))
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				li_flags = GET_DWORD(li_req_parms[0].info) & ~(LI2_FLAG_INTERCONNECT_A_B | LI2_FLAG_INTERCONNECT_B_A);
-				Info = li_check_main_plci(Id, plci);
-				result_buffer[0] = 7;
-				result_buffer[3] = 4;
-				PUT_WORD(&result_buffer[4], Info);
-				result_buffer[6] = 0;
-				if (Info != GOOD)
-					break;
-				result = plci->saved_msg.info;
-				for (i = 0; i <= result_buffer[0]; i++)
-					result[i] = result_buffer[i];
-				plci_b_write_pos = plci->li_plci_b_write_pos;
-				participant_parms_pos = 0;
-				result_pos = 7;
-				li2_update_connect(Id, a, plci, UnMapId(Id), true, li_flags);
-				while (participant_parms_pos < li_req_parms[1].length)
-				{
-					result[result_pos] = 6;
-					result_pos += 7;
-					PUT_DWORD(&result[result_pos - 6], 0);
-					PUT_WORD(&result[result_pos - 2], GOOD);
-					if (api_parse(&li_req_parms[1].info[1 + participant_parms_pos],
-						      (word)(li_parms[1].length - participant_parms_pos), "s", li_participant_struct))
-					{
-						dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-								UnMapId(Id), (char *)(FILE_), __LINE__));
-						PUT_WORD(&result[result_pos - 2], _WRONG_MESSAGE_FORMAT);
-						break;
-					}
-					if (api_parse(&li_participant_struct[0].info[1],
-						      li_participant_struct[0].length, "dd", li_participant_parms))
-					{
-						dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-								UnMapId(Id), (char *)(FILE_), __LINE__));
-						PUT_WORD(&result[result_pos - 2], _WRONG_MESSAGE_FORMAT);
-						break;
-					}
-					plci_b_id = GET_DWORD(li_participant_parms[0].info) & 0xffff;
-					li_flags = GET_DWORD(li_participant_parms[1].info);
-					PUT_DWORD(&result[result_pos - 6], plci_b_id);
-					if (sizeof(result) - result_pos < 7)
-					{
-						dbug(1, dprintf("[%06lx] %s,%d: LI result overrun",
-								UnMapId(Id), (char *)(FILE_), __LINE__));
-						PUT_WORD(&result[result_pos - 2], _WRONG_STATE);
-						break;
-					}
-					plci_b = li2_check_plci_b(Id, plci, plci_b_id, plci_b_write_pos, &result[result_pos - 2]);
-					if (plci_b != NULL)
-					{
-						li2_update_connect(Id, a, plci, plci_b_id, true, li_flags);
-						plci->li_plci_b_queue[plci_b_write_pos] = plci_b_id |
-							((li_flags & (LI2_FLAG_INTERCONNECT_A_B | LI2_FLAG_INTERCONNECT_B_A |
-								      LI2_FLAG_PCCONNECT_A_B | LI2_FLAG_PCCONNECT_B_A)) ? 0 : LI_PLCI_B_DISC_FLAG);
-						plci_b_write_pos = (plci_b_write_pos == LI_PLCI_B_QUEUE_ENTRIES - 1) ? 0 : plci_b_write_pos + 1;
-					}
-					participant_parms_pos = (word)((&li_participant_struct[0].info[1 + li_participant_struct[0].length]) -
-								       (&li_req_parms[1].info[1]));
-				}
-				result[0] = (byte)(result_pos - 1);
-				result[3] = (byte)(result_pos - 4);
-				result[6] = (byte)(result_pos - 7);
-				i = (plci_b_write_pos == 0) ? LI_PLCI_B_QUEUE_ENTRIES - 1 : plci_b_write_pos - 1;
-				if ((plci_b_write_pos == plci->li_plci_b_read_pos)
-				    || (plci->li_plci_b_queue[i] & LI_PLCI_B_LAST_FLAG))
-				{
-					plci->li_plci_b_queue[plci_b_write_pos] = LI_PLCI_B_SKIP_FLAG | LI_PLCI_B_LAST_FLAG;
-					plci_b_write_pos = (plci_b_write_pos == LI_PLCI_B_QUEUE_ENTRIES - 1) ? 0 : plci_b_write_pos + 1;
-				}
-				else
-					plci->li_plci_b_queue[i] |= LI_PLCI_B_LAST_FLAG;
-				plci->li_plci_b_write_pos = plci_b_write_pos;
-			}
-			mixer_calculate_coefs(a);
-			plci->li_channel_bits = li_config_table[a->li_base + (plci->li_bchannel_id - 1)].channel;
-			mixer_notify_update(plci, true);
-			sendf(appl, _FACILITY_R | CONFIRM, Id & 0xffffL, Number,
-			      "wwS", Info, SELECTOR_LINE_INTERCONNECT, result);
-			plci->command = 0;
-			plci->li_cmd = GET_WORD(li_parms[0].info);
-			start_internal_command(Id, plci, mixer_command);
-			return (false);
-
-		case LI_REQ_DISCONNECT:
-			if (li_parms[1].length == 4)
-			{
-				appl->appl_flags |= APPL_FLAG_OLD_LI_SPEC;
-				if (api_parse(&li_parms[1].info[1], li_parms[1].length, "d", li_req_parms))
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				plci_b_id = GET_DWORD(li_req_parms[0].info) & 0xffff;
-				Info = li_check_main_plci(Id, plci);
-				result_buffer[0] = 9;
-				result_buffer[3] = 6;
-				PUT_DWORD(&result_buffer[4], GET_DWORD(li_req_parms[0].info));
-				PUT_WORD(&result_buffer[8], GOOD);
-				if (Info != GOOD)
-					break;
-				result = plci->saved_msg.info;
-				for (i = 0; i <= result_buffer[0]; i++)
-					result[i] = result_buffer[i];
-				plci_b_write_pos = plci->li_plci_b_write_pos;
-				plci_b = li_check_plci_b(Id, plci, plci_b_id, plci_b_write_pos, &result[8]);
-				if (plci_b == NULL)
-					break;
-				li_update_connect(Id, a, plci, plci_b_id, false, 0);
-				plci->li_plci_b_queue[plci_b_write_pos] = plci_b_id | LI_PLCI_B_DISC_FLAG | LI_PLCI_B_LAST_FLAG;
-				plci_b_write_pos = (plci_b_write_pos == LI_PLCI_B_QUEUE_ENTRIES - 1) ? 0 : plci_b_write_pos + 1;
-				plci->li_plci_b_write_pos = plci_b_write_pos;
-			}
-			else
-			{
-				appl->appl_flags &= ~APPL_FLAG_OLD_LI_SPEC;
-				if (api_parse(&li_parms[1].info[1], li_parms[1].length, "s", li_req_parms))
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					Info = _WRONG_MESSAGE_FORMAT;
-					break;
-				}
-				Info = li_check_main_plci(Id, plci);
-				result_buffer[0] = 7;
-				result_buffer[3] = 4;
-				PUT_WORD(&result_buffer[4], Info);
-				result_buffer[6] = 0;
-				if (Info != GOOD)
-					break;
-				result = plci->saved_msg.info;
-				for (i = 0; i <= result_buffer[0]; i++)
-					result[i] = result_buffer[i];
-				plci_b_write_pos = plci->li_plci_b_write_pos;
-				participant_parms_pos = 0;
-				result_pos = 7;
-				while (participant_parms_pos < li_req_parms[0].length)
-				{
-					result[result_pos] = 6;
-					result_pos += 7;
-					PUT_DWORD(&result[result_pos - 6], 0);
-					PUT_WORD(&result[result_pos - 2], GOOD);
-					if (api_parse(&li_req_parms[0].info[1 + participant_parms_pos],
-						      (word)(li_parms[1].length - participant_parms_pos), "s", li_participant_struct))
-					{
-						dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-								UnMapId(Id), (char *)(FILE_), __LINE__));
-						PUT_WORD(&result[result_pos - 2], _WRONG_MESSAGE_FORMAT);
-						break;
-					}
-					if (api_parse(&li_participant_struct[0].info[1],
-						      li_participant_struct[0].length, "d", li_participant_parms))
-					{
-						dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-								UnMapId(Id), (char *)(FILE_), __LINE__));
-						PUT_WORD(&result[result_pos - 2], _WRONG_MESSAGE_FORMAT);
-						break;
-					}
-					plci_b_id = GET_DWORD(li_participant_parms[0].info) & 0xffff;
-					PUT_DWORD(&result[result_pos - 6], plci_b_id);
-					if (sizeof(result) - result_pos < 7)
-					{
-						dbug(1, dprintf("[%06lx] %s,%d: LI result overrun",
-								UnMapId(Id), (char *)(FILE_), __LINE__));
-						PUT_WORD(&result[result_pos - 2], _WRONG_STATE);
-						break;
-					}
-					plci_b = li2_check_plci_b(Id, plci, plci_b_id, plci_b_write_pos, &result[result_pos - 2]);
-					if (plci_b != NULL)
-					{
-						li2_update_connect(Id, a, plci, plci_b_id, false, 0);
-						plci->li_plci_b_queue[plci_b_write_pos] = plci_b_id | LI_PLCI_B_DISC_FLAG;
-						plci_b_write_pos = (plci_b_write_pos == LI_PLCI_B_QUEUE_ENTRIES - 1) ? 0 : plci_b_write_pos + 1;
-					}
-					participant_parms_pos = (word)((&li_participant_struct[0].info[1 + li_participant_struct[0].length]) -
-								       (&li_req_parms[0].info[1]));
-				}
-				result[0] = (byte)(result_pos - 1);
-				result[3] = (byte)(result_pos - 4);
-				result[6] = (byte)(result_pos - 7);
-				i = (plci_b_write_pos == 0) ? LI_PLCI_B_QUEUE_ENTRIES - 1 : plci_b_write_pos - 1;
-				if ((plci_b_write_pos == plci->li_plci_b_read_pos)
-				    || (plci->li_plci_b_queue[i] & LI_PLCI_B_LAST_FLAG))
-				{
-					plci->li_plci_b_queue[plci_b_write_pos] = LI_PLCI_B_SKIP_FLAG | LI_PLCI_B_LAST_FLAG;
-					plci_b_write_pos = (plci_b_write_pos == LI_PLCI_B_QUEUE_ENTRIES - 1) ? 0 : plci_b_write_pos + 1;
-				}
-				else
-					plci->li_plci_b_queue[i] |= LI_PLCI_B_LAST_FLAG;
-				plci->li_plci_b_write_pos = plci_b_write_pos;
-			}
-			mixer_calculate_coefs(a);
-			plci->li_channel_bits = li_config_table[a->li_base + (plci->li_bchannel_id - 1)].channel;
-			mixer_notify_update(plci, true);
-			sendf(appl, _FACILITY_R | CONFIRM, Id & 0xffffL, Number,
-			      "wwS", Info, SELECTOR_LINE_INTERCONNECT, result);
-			plci->command = 0;
-			plci->li_cmd = GET_WORD(li_parms[0].info);
-			start_internal_command(Id, plci, mixer_command);
-			return (false);
-
-		case LI_REQ_SILENT_UPDATE:
-			if (!plci || !plci->State
-			    || !plci->NL.Id || plci->nl_remove_id
-			    || (plci->li_bchannel_id == 0)
-			    || (li_config_table[plci->adapter->li_base + (plci->li_bchannel_id - 1)].plci != plci))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Wrong state",
-						UnMapId(Id), (char *)(FILE_), __LINE__));
-				return (false);
-			}
-			plci_b_write_pos = plci->li_plci_b_write_pos;
-			if (((plci->li_plci_b_read_pos > plci_b_write_pos) ? plci->li_plci_b_read_pos :
-			     LI_PLCI_B_QUEUE_ENTRIES + plci->li_plci_b_read_pos) - plci_b_write_pos - 1 < 2)
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: LI request overrun",
-						UnMapId(Id), (char *)(FILE_), __LINE__));
-				return (false);
-			}
-			i = (plci_b_write_pos == 0) ? LI_PLCI_B_QUEUE_ENTRIES - 1 : plci_b_write_pos - 1;
-			if ((plci_b_write_pos == plci->li_plci_b_read_pos)
-			    || (plci->li_plci_b_queue[i] & LI_PLCI_B_LAST_FLAG))
-			{
-				plci->li_plci_b_queue[plci_b_write_pos] = LI_PLCI_B_SKIP_FLAG | LI_PLCI_B_LAST_FLAG;
-				plci_b_write_pos = (plci_b_write_pos == LI_PLCI_B_QUEUE_ENTRIES - 1) ? 0 : plci_b_write_pos + 1;
-			}
-			else
-				plci->li_plci_b_queue[i] |= LI_PLCI_B_LAST_FLAG;
-			plci->li_plci_b_write_pos = plci_b_write_pos;
-			plci->li_channel_bits = li_config_table[a->li_base + (plci->li_bchannel_id - 1)].channel;
-			plci->command = 0;
-			plci->li_cmd = GET_WORD(li_parms[0].info);
-			start_internal_command(Id, plci, mixer_command);
-			return (false);
-
-		default:
-			dbug(1, dprintf("[%06lx] %s,%d: LI unknown request %04x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, GET_WORD(li_parms[0].info)));
-			Info = _FACILITY_NOT_SUPPORTED;
-		}
-	}
-	sendf(appl, _FACILITY_R | CONFIRM, Id & 0xffffL, Number,
-	      "wwS", Info, SELECTOR_LINE_INTERCONNECT, result);
-	return (false);
-}
-
-
-static void mixer_indication_coefs_set(dword Id, PLCI *plci)
-{
-	dword d;
-	byte result[12];
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_indication_coefs_set",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-	if (plci->li_plci_b_read_pos != plci->li_plci_b_req_pos)
-	{
-		do
-		{
-			d = plci->li_plci_b_queue[plci->li_plci_b_read_pos];
-			if (!(d & LI_PLCI_B_SKIP_FLAG))
-			{
-				if (plci->appl->appl_flags & APPL_FLAG_OLD_LI_SPEC)
-				{
-					if (d & LI_PLCI_B_DISC_FLAG)
-					{
-						result[0] = 5;
-						PUT_WORD(&result[1], LI_IND_DISCONNECT);
-						result[3] = 2;
-						PUT_WORD(&result[4], _LI_USER_INITIATED);
-					}
-					else
-					{
-						result[0] = 7;
-						PUT_WORD(&result[1], LI_IND_CONNECT_ACTIVE);
-						result[3] = 4;
-						PUT_DWORD(&result[4], d & ~LI_PLCI_B_FLAG_MASK);
-					}
-				}
-				else
-				{
-					if (d & LI_PLCI_B_DISC_FLAG)
-					{
-						result[0] = 9;
-						PUT_WORD(&result[1], LI_IND_DISCONNECT);
-						result[3] = 6;
-						PUT_DWORD(&result[4], d & ~LI_PLCI_B_FLAG_MASK);
-						PUT_WORD(&result[8], _LI_USER_INITIATED);
-					}
-					else
-					{
-						result[0] = 7;
-						PUT_WORD(&result[1], LI_IND_CONNECT_ACTIVE);
-						result[3] = 4;
-						PUT_DWORD(&result[4], d & ~LI_PLCI_B_FLAG_MASK);
-					}
-				}
-				sendf(plci->appl, _FACILITY_I, Id & 0xffffL, 0,
-				      "ws", SELECTOR_LINE_INTERCONNECT, result);
-			}
-			plci->li_plci_b_read_pos = (plci->li_plci_b_read_pos == LI_PLCI_B_QUEUE_ENTRIES - 1) ?
-				0 : plci->li_plci_b_read_pos + 1;
-		} while (!(d & LI_PLCI_B_LAST_FLAG) && (plci->li_plci_b_read_pos != plci->li_plci_b_req_pos));
-	}
-}
-
-
-static void mixer_indication_xconnect_from(dword Id, PLCI *plci, byte *msg, word length)
-{
-	word i, j, ch;
-	struct xconnect_transfer_address_s s,   *p;
-	DIVA_CAPI_ADAPTER *a;
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_indication_xconnect_from %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, (int)length));
-
-	a = plci->adapter;
-	i = 1;
-	for (i = 1; i < length; i += 16)
-	{
-		s.card_address.low = msg[i] | (msg[i + 1] << 8) | (((dword)(msg[i + 2])) << 16) | (((dword)(msg[i + 3])) << 24);
-		s.card_address.high = msg[i + 4] | (msg[i + 5] << 8) | (((dword)(msg[i + 6])) << 16) | (((dword)(msg[i + 7])) << 24);
-		s.offset = msg[i + 8] | (msg[i + 9] << 8) | (((dword)(msg[i + 10])) << 16) | (((dword)(msg[i + 11])) << 24);
-		ch = msg[i + 12] | (msg[i + 13] << 8);
-		j = ch & XCONNECT_CHANNEL_NUMBER_MASK;
-		if (!a->li_pri && (plci->li_bchannel_id == 2))
-			j = 1 - j;
-		j += a->li_base;
-		if (ch & XCONNECT_CHANNEL_PORT_PC)
-			p = &(li_config_table[j].send_pc);
-		else
-			p = &(li_config_table[j].send_b);
-		p->card_address.low = s.card_address.low;
-		p->card_address.high = s.card_address.high;
-		p->offset = s.offset;
-		li_config_table[j].channel |= LI_CHANNEL_ADDRESSES_SET;
-	}
-	if (plci->internal_command_queue[0]
-	    && ((plci->adjust_b_state == ADJUST_B_RESTORE_MIXER_2)
-		|| (plci->adjust_b_state == ADJUST_B_RESTORE_MIXER_3)
-		|| (plci->adjust_b_state == ADJUST_B_RESTORE_MIXER_4)))
-	{
-		(*(plci->internal_command_queue[0]))(Id, plci, 0);
-		if (!plci->internal_command)
-			next_internal_command(Id, plci);
-	}
-	mixer_notify_update(plci, true);
-}
-
-
-static void mixer_indication_xconnect_to(dword Id, PLCI *plci, byte *msg, word length)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_indication_xconnect_to %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, (int) length));
-
-}
-
-
-static byte mixer_notify_source_removed(PLCI *plci, dword plci_b_id)
-{
-	word plci_b_write_pos;
-
-	plci_b_write_pos = plci->li_plci_b_write_pos;
-	if (((plci->li_plci_b_read_pos > plci_b_write_pos) ? plci->li_plci_b_read_pos :
-	     LI_PLCI_B_QUEUE_ENTRIES + plci->li_plci_b_read_pos) - plci_b_write_pos - 1 < 1)
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: LI request overrun",
-				(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-				(char *)(FILE_), __LINE__));
-		return (false);
-	}
-	plci->li_plci_b_queue[plci_b_write_pos] = plci_b_id | LI_PLCI_B_DISC_FLAG;
-	plci_b_write_pos = (plci_b_write_pos == LI_PLCI_B_QUEUE_ENTRIES - 1) ? 0 : plci_b_write_pos + 1;
-	plci->li_plci_b_write_pos = plci_b_write_pos;
-	return (true);
-}
-
-
-static void mixer_remove(PLCI *plci)
-{
-	DIVA_CAPI_ADAPTER *a;
-	PLCI *notify_plci;
-	dword plci_b_id;
-	word i, j;
-
-	dbug(1, dprintf("[%06lx] %s,%d: mixer_remove",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	a = plci->adapter;
-	plci_b_id = (plci->Id << 8) | UnMapController(plci->adapter->Id);
-	if (a->profile.Global_Options & GL_LINE_INTERCONNECT_SUPPORTED)
-	{
-		if ((plci->li_bchannel_id != 0)
-		    && (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == plci))
-		{
-			i = a->li_base + (plci->li_bchannel_id - 1);
-			if ((li_config_table[i].curchnl | li_config_table[i].channel) & LI_CHANNEL_INVOLVED)
-			{
-				for (j = 0; j < li_total_channels; j++)
-				{
-					if ((li_config_table[i].flag_table[j] & LI_FLAG_INTERCONNECT)
-					    || (li_config_table[j].flag_table[i] & LI_FLAG_INTERCONNECT))
-					{
-						notify_plci = li_config_table[j].plci;
-						if ((notify_plci != NULL)
-						    && (notify_plci != plci)
-						    && (notify_plci->appl != NULL)
-						    && !(notify_plci->appl->appl_flags & APPL_FLAG_OLD_LI_SPEC)
-						    && (notify_plci->State)
-						    && notify_plci->NL.Id && !notify_plci->nl_remove_id)
-						{
-							mixer_notify_source_removed(notify_plci, plci_b_id);
-						}
-					}
-				}
-				mixer_clear_config(plci);
-				mixer_calculate_coefs(a);
-				mixer_notify_update(plci, true);
-			}
-			li_config_table[i].plci = NULL;
-			plci->li_bchannel_id = 0;
-		}
-	}
-}
-
-
-/*------------------------------------------------------------------*/
-/* Echo canceller facilities                                        */
-/*------------------------------------------------------------------*/
-
-
-static void ec_write_parameters(PLCI *plci)
-{
-	word w;
-	byte parameter_buffer[6];
-
-	dbug(1, dprintf("[%06lx] %s,%d: ec_write_parameters",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	parameter_buffer[0] = 5;
-	parameter_buffer[1] = DSP_CTRL_SET_LEC_PARAMETERS;
-	PUT_WORD(&parameter_buffer[2], plci->ec_idi_options);
-	plci->ec_idi_options &= ~LEC_RESET_COEFFICIENTS;
-	w = (plci->ec_tail_length == 0) ? 128 : plci->ec_tail_length;
-	PUT_WORD(&parameter_buffer[4], w);
-	add_p(plci, FTY, parameter_buffer);
-	sig_req(plci, TEL_CTRL, 0);
-	send_req(plci);
-}
-
-
-static void ec_clear_config(PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: ec_clear_config",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	plci->ec_idi_options = LEC_ENABLE_ECHO_CANCELLER |
-		LEC_MANUAL_DISABLE | LEC_ENABLE_NONLINEAR_PROCESSING;
-	plci->ec_tail_length = 0;
-}
-
-
-static void ec_prepare_switch(dword Id, PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: ec_prepare_switch",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-}
-
-
-static word ec_save_config(dword Id, PLCI *plci, byte Rc)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: ec_save_config %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->adjust_b_state));
-
-	return (GOOD);
-}
-
-
-static word ec_restore_config(dword Id, PLCI *plci, byte Rc)
-{
-	word Info;
-
-	dbug(1, dprintf("[%06lx] %s,%d: ec_restore_config %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->adjust_b_state));
-
-	Info = GOOD;
-	if (plci->B1_facilities & B1_FACILITY_EC)
-	{
-		switch (plci->adjust_b_state)
-		{
-		case ADJUST_B_RESTORE_EC_1:
-			plci->internal_command = plci->adjust_b_command;
-			if (plci->sig_req)
-			{
-				plci->adjust_b_state = ADJUST_B_RESTORE_EC_1;
-				break;
-			}
-			ec_write_parameters(plci);
-			plci->adjust_b_state = ADJUST_B_RESTORE_EC_2;
-			break;
-		case ADJUST_B_RESTORE_EC_2:
-			if ((Rc != OK) && (Rc != OK_FC))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Restore EC failed %02x",
-						UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-				Info = _WRONG_STATE;
-				break;
-			}
-			break;
-		}
-	}
-	return (Info);
-}
-
-
-static void ec_command(dword Id, PLCI *plci, byte Rc)
-{
-	word internal_command, Info;
-	byte result[8];
-
-	dbug(1, dprintf("[%06lx] %s,%d: ec_command %02x %04x %04x %04x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command,
-			plci->ec_cmd, plci->ec_idi_options, plci->ec_tail_length));
-
-	Info = GOOD;
-	if (plci->appl->appl_flags & APPL_FLAG_PRIV_EC_SPEC)
-	{
-		result[0] = 2;
-		PUT_WORD(&result[1], EC_SUCCESS);
-	}
-	else
-	{
-		result[0] = 5;
-		PUT_WORD(&result[1], plci->ec_cmd);
-		result[3] = 2;
-		PUT_WORD(&result[4], GOOD);
-	}
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (plci->ec_cmd)
-	{
-	case EC_ENABLE_OPERATION:
-	case EC_FREEZE_COEFFICIENTS:
-	case EC_RESUME_COEFFICIENT_UPDATE:
-	case EC_RESET_COEFFICIENTS:
-		switch (internal_command)
-		{
-		default:
-			adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities |
-								  B1_FACILITY_EC), EC_COMMAND_1);
-			/* fall through */
-		case EC_COMMAND_1:
-			if (adjust_b_process(Id, plci, Rc) != GOOD)
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Load EC failed",
-						UnMapId(Id), (char *)(FILE_), __LINE__));
-				Info = _FACILITY_NOT_SUPPORTED;
-				break;
-			}
-			if (plci->internal_command)
-				return;
-			/* fall through */
-		case EC_COMMAND_2:
-			if (plci->sig_req)
-			{
-				plci->internal_command = EC_COMMAND_2;
-				return;
-			}
-			plci->internal_command = EC_COMMAND_3;
-			ec_write_parameters(plci);
-			return;
-		case EC_COMMAND_3:
-			if ((Rc != OK) && (Rc != OK_FC))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Enable EC failed %02x",
-						UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-				Info = _FACILITY_NOT_SUPPORTED;
-				break;
-			}
-			break;
-		}
-		break;
-
-	case EC_DISABLE_OPERATION:
-		switch (internal_command)
-		{
-		default:
-		case EC_COMMAND_1:
-			if (plci->B1_facilities & B1_FACILITY_EC)
-			{
-				if (plci->sig_req)
-				{
-					plci->internal_command = EC_COMMAND_1;
-					return;
-				}
-				plci->internal_command = EC_COMMAND_2;
-				ec_write_parameters(plci);
-				return;
-			}
-			Rc = OK;
-			/* fall through */
-		case EC_COMMAND_2:
-			if ((Rc != OK) && (Rc != OK_FC))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Disable EC failed %02x",
-						UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-				Info = _FACILITY_NOT_SUPPORTED;
-				break;
-			}
-			adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities &
-								  ~B1_FACILITY_EC), EC_COMMAND_3);
-			/* fall through */
-		case EC_COMMAND_3:
-			if (adjust_b_process(Id, plci, Rc) != GOOD)
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Unload EC failed",
-						UnMapId(Id), (char *)(FILE_), __LINE__));
-				Info = _FACILITY_NOT_SUPPORTED;
-				break;
-			}
-			if (plci->internal_command)
-				return;
-			break;
-		}
-		break;
-	}
-	sendf(plci->appl, _FACILITY_R | CONFIRM, Id & 0xffffL, plci->number,
-	      "wws", Info, (plci->appl->appl_flags & APPL_FLAG_PRIV_EC_SPEC) ?
-	      PRIV_SELECTOR_ECHO_CANCELLER : SELECTOR_ECHO_CANCELLER, result);
-}
-
-
-static byte ec_request(dword Id, word Number, DIVA_CAPI_ADAPTER *a, PLCI *plci, APPL   *appl, API_PARSE *msg)
-{
-	word Info;
-	word opt;
-	API_PARSE ec_parms[3];
-	byte result[16];
-
-	dbug(1, dprintf("[%06lx] %s,%d: ec_request",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-	Info = GOOD;
-	result[0] = 0;
-	if (!(a->man_profile.private_options & (1L << PRIVATE_ECHO_CANCELLER)))
-	{
-		dbug(1, dprintf("[%06lx] %s,%d: Facility not supported",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		Info = _FACILITY_NOT_SUPPORTED;
-	}
-	else
-	{
-		if (appl->appl_flags & APPL_FLAG_PRIV_EC_SPEC)
-		{
-			if (api_parse(&msg[1].info[1], msg[1].length, "w", ec_parms))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-						UnMapId(Id), (char *)(FILE_), __LINE__));
-				Info = _WRONG_MESSAGE_FORMAT;
-			}
-			else
-			{
-				if (plci == NULL)
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Wrong PLCI",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					Info = _WRONG_IDENTIFIER;
-				}
-				else if (!plci->State || !plci->NL.Id || plci->nl_remove_id)
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Wrong state",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					Info = _WRONG_STATE;
-				}
-				else
-				{
-					plci->command = 0;
-					plci->ec_cmd = GET_WORD(ec_parms[0].info);
-					plci->ec_idi_options &= ~(LEC_MANUAL_DISABLE | LEC_RESET_COEFFICIENTS);
-					result[0] = 2;
-					PUT_WORD(&result[1], EC_SUCCESS);
-					if (msg[1].length >= 4)
-					{
-						opt = GET_WORD(&ec_parms[0].info[2]);
-						plci->ec_idi_options &= ~(LEC_ENABLE_NONLINEAR_PROCESSING |
-									  LEC_ENABLE_2100HZ_DETECTOR | LEC_REQUIRE_2100HZ_REVERSALS);
-						if (!(opt & EC_DISABLE_NON_LINEAR_PROCESSING))
-							plci->ec_idi_options |= LEC_ENABLE_NONLINEAR_PROCESSING;
-						if (opt & EC_DETECT_DISABLE_TONE)
-							plci->ec_idi_options |= LEC_ENABLE_2100HZ_DETECTOR;
-						if (!(opt & EC_DO_NOT_REQUIRE_REVERSALS))
-							plci->ec_idi_options |= LEC_REQUIRE_2100HZ_REVERSALS;
-						if (msg[1].length >= 6)
-						{
-							plci->ec_tail_length = GET_WORD(&ec_parms[0].info[4]);
-						}
-					}
-					switch (plci->ec_cmd)
-					{
-					case EC_ENABLE_OPERATION:
-						plci->ec_idi_options &= ~LEC_FREEZE_COEFFICIENTS;
-						start_internal_command(Id, plci, ec_command);
-						return (false);
-
-					case EC_DISABLE_OPERATION:
-						plci->ec_idi_options = LEC_ENABLE_ECHO_CANCELLER |
-							LEC_MANUAL_DISABLE | LEC_ENABLE_NONLINEAR_PROCESSING |
-							LEC_RESET_COEFFICIENTS;
-						start_internal_command(Id, plci, ec_command);
-						return (false);
-
-					case EC_FREEZE_COEFFICIENTS:
-						plci->ec_idi_options |= LEC_FREEZE_COEFFICIENTS;
-						start_internal_command(Id, plci, ec_command);
-						return (false);
-
-					case EC_RESUME_COEFFICIENT_UPDATE:
-						plci->ec_idi_options &= ~LEC_FREEZE_COEFFICIENTS;
-						start_internal_command(Id, plci, ec_command);
-						return (false);
-
-					case EC_RESET_COEFFICIENTS:
-						plci->ec_idi_options |= LEC_RESET_COEFFICIENTS;
-						start_internal_command(Id, plci, ec_command);
-						return (false);
-
-					default:
-						dbug(1, dprintf("[%06lx] %s,%d: EC unknown request %04x",
-								UnMapId(Id), (char *)(FILE_), __LINE__, plci->ec_cmd));
-						PUT_WORD(&result[1], EC_UNSUPPORTED_OPERATION);
-					}
-				}
-			}
-		}
-		else
-		{
-			if (api_parse(&msg[1].info[1], msg[1].length, "ws", ec_parms))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Wrong message format",
-						UnMapId(Id), (char *)(FILE_), __LINE__));
-				Info = _WRONG_MESSAGE_FORMAT;
-			}
-			else
-			{
-				if (GET_WORD(ec_parms[0].info) == EC_GET_SUPPORTED_SERVICES)
-				{
-					result[0] = 11;
-					PUT_WORD(&result[1], EC_GET_SUPPORTED_SERVICES);
-					result[3] = 8;
-					PUT_WORD(&result[4], GOOD);
-					PUT_WORD(&result[6], 0x0007);
-					PUT_WORD(&result[8], LEC_MAX_SUPPORTED_TAIL_LENGTH);
-					PUT_WORD(&result[10], 0);
-				}
-				else if (plci == NULL)
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Wrong PLCI",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					Info = _WRONG_IDENTIFIER;
-				}
-				else if (!plci->State || !plci->NL.Id || plci->nl_remove_id)
-				{
-					dbug(1, dprintf("[%06lx] %s,%d: Wrong state",
-							UnMapId(Id), (char *)(FILE_), __LINE__));
-					Info = _WRONG_STATE;
-				}
-				else
-				{
-					plci->command = 0;
-					plci->ec_cmd = GET_WORD(ec_parms[0].info);
-					plci->ec_idi_options &= ~(LEC_MANUAL_DISABLE | LEC_RESET_COEFFICIENTS);
-					result[0] = 5;
-					PUT_WORD(&result[1], plci->ec_cmd);
-					result[3] = 2;
-					PUT_WORD(&result[4], GOOD);
-					plci->ec_idi_options &= ~(LEC_ENABLE_NONLINEAR_PROCESSING |
-								  LEC_ENABLE_2100HZ_DETECTOR | LEC_REQUIRE_2100HZ_REVERSALS);
-					plci->ec_tail_length = 0;
-					if (ec_parms[1].length >= 2)
-					{
-						opt = GET_WORD(&ec_parms[1].info[1]);
-						if (opt & EC_ENABLE_NON_LINEAR_PROCESSING)
-							plci->ec_idi_options |= LEC_ENABLE_NONLINEAR_PROCESSING;
-						if (opt & EC_DETECT_DISABLE_TONE)
-							plci->ec_idi_options |= LEC_ENABLE_2100HZ_DETECTOR;
-						if (!(opt & EC_DO_NOT_REQUIRE_REVERSALS))
-							plci->ec_idi_options |= LEC_REQUIRE_2100HZ_REVERSALS;
-						if (ec_parms[1].length >= 4)
-						{
-							plci->ec_tail_length = GET_WORD(&ec_parms[1].info[3]);
-						}
-					}
-					switch (plci->ec_cmd)
-					{
-					case EC_ENABLE_OPERATION:
-						plci->ec_idi_options &= ~LEC_FREEZE_COEFFICIENTS;
-						start_internal_command(Id, plci, ec_command);
-						return (false);
-
-					case EC_DISABLE_OPERATION:
-						plci->ec_idi_options = LEC_ENABLE_ECHO_CANCELLER |
-							LEC_MANUAL_DISABLE | LEC_ENABLE_NONLINEAR_PROCESSING |
-							LEC_RESET_COEFFICIENTS;
-						start_internal_command(Id, plci, ec_command);
-						return (false);
-
-					default:
-						dbug(1, dprintf("[%06lx] %s,%d: EC unknown request %04x",
-								UnMapId(Id), (char *)(FILE_), __LINE__, plci->ec_cmd));
-						PUT_WORD(&result[4], _FACILITY_SPECIFIC_FUNCTION_NOT_SUPP);
-					}
-				}
-			}
-		}
-	}
-	sendf(appl, _FACILITY_R | CONFIRM, Id & 0xffffL, Number,
-	      "wws", Info, (appl->appl_flags & APPL_FLAG_PRIV_EC_SPEC) ?
-	      PRIV_SELECTOR_ECHO_CANCELLER : SELECTOR_ECHO_CANCELLER, result);
-	return (false);
-}
-
-
-static void ec_indication(dword Id, PLCI *plci, byte *msg, word length)
-{
-	byte result[8];
-
-	dbug(1, dprintf("[%06lx] %s,%d: ec_indication",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-	if (!(plci->ec_idi_options & LEC_MANUAL_DISABLE))
-	{
-		if (plci->appl->appl_flags & APPL_FLAG_PRIV_EC_SPEC)
-		{
-			result[0] = 2;
-			PUT_WORD(&result[1], 0);
-			switch (msg[1])
-			{
-			case LEC_DISABLE_TYPE_CONTIGNUOUS_2100HZ:
-				PUT_WORD(&result[1], EC_BYPASS_DUE_TO_CONTINUOUS_2100HZ);
-				break;
-			case LEC_DISABLE_TYPE_REVERSED_2100HZ:
-				PUT_WORD(&result[1], EC_BYPASS_DUE_TO_REVERSED_2100HZ);
-				break;
-			case LEC_DISABLE_RELEASED:
-				PUT_WORD(&result[1], EC_BYPASS_RELEASED);
-				break;
-			}
-		}
-		else
-		{
-			result[0] = 5;
-			PUT_WORD(&result[1], EC_BYPASS_INDICATION);
-			result[3] = 2;
-			PUT_WORD(&result[4], 0);
-			switch (msg[1])
-			{
-			case LEC_DISABLE_TYPE_CONTIGNUOUS_2100HZ:
-				PUT_WORD(&result[4], EC_BYPASS_DUE_TO_CONTINUOUS_2100HZ);
-				break;
-			case LEC_DISABLE_TYPE_REVERSED_2100HZ:
-				PUT_WORD(&result[4], EC_BYPASS_DUE_TO_REVERSED_2100HZ);
-				break;
-			case LEC_DISABLE_RELEASED:
-				PUT_WORD(&result[4], EC_BYPASS_RELEASED);
-				break;
-			}
-		}
-		sendf(plci->appl, _FACILITY_I, Id & 0xffffL, 0, "ws", (plci->appl->appl_flags & APPL_FLAG_PRIV_EC_SPEC) ?
-		      PRIV_SELECTOR_ECHO_CANCELLER : SELECTOR_ECHO_CANCELLER, result);
-	}
-}
-
-
-
-/*------------------------------------------------------------------*/
-/* Advanced voice                                                   */
-/*------------------------------------------------------------------*/
-
-static void adv_voice_write_coefs(PLCI *plci, word write_command)
-{
-	DIVA_CAPI_ADAPTER *a;
-	word i;
-	byte *p;
-
-	word w, n, j, k;
-	byte ch_map[MIXER_CHANNELS_BRI];
-
-	byte coef_buffer[ADV_VOICE_COEF_BUFFER_SIZE + 2];
-
-	dbug(1, dprintf("[%06lx] %s,%d: adv_voice_write_coefs %d",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__, write_command));
-
-	a = plci->adapter;
-	p = coef_buffer + 1;
-	*(p++) = DSP_CTRL_OLD_SET_MIXER_COEFFICIENTS;
-	i = 0;
-	while (i + sizeof(word) <= a->adv_voice_coef_length)
-	{
-		PUT_WORD(p, GET_WORD(a->adv_voice_coef_buffer + i));
-		p += 2;
-		i += 2;
-	}
-	while (i < ADV_VOICE_OLD_COEF_COUNT * sizeof(word))
-	{
-		PUT_WORD(p, 0x8000);
-		p += 2;
-		i += 2;
-	}
-
-	if (!a->li_pri && (plci->li_bchannel_id == 0))
-	{
-		if ((li_config_table[a->li_base].plci == NULL) && (li_config_table[a->li_base + 1].plci != NULL))
-		{
-			plci->li_bchannel_id = 1;
-			li_config_table[a->li_base].plci = plci;
-			dbug(1, dprintf("[%06lx] %s,%d: adv_voice_set_bchannel_id %d",
-					(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-					(char *)(FILE_), __LINE__, plci->li_bchannel_id));
-		}
-		else if ((li_config_table[a->li_base].plci != NULL) && (li_config_table[a->li_base + 1].plci == NULL))
-		{
-			plci->li_bchannel_id = 2;
-			li_config_table[a->li_base + 1].plci = plci;
-			dbug(1, dprintf("[%06lx] %s,%d: adv_voice_set_bchannel_id %d",
-					(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-					(char *)(FILE_), __LINE__, plci->li_bchannel_id));
-		}
-	}
-	if (!a->li_pri && (plci->li_bchannel_id != 0)
-	    && (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == plci))
-	{
-		i = a->li_base + (plci->li_bchannel_id - 1);
-		switch (write_command)
-		{
-		case ADV_VOICE_WRITE_ACTIVATION:
-			j = a->li_base + MIXER_IC_CHANNEL_BASE + (plci->li_bchannel_id - 1);
-			k = a->li_base + MIXER_IC_CHANNEL_BASE + (2 - plci->li_bchannel_id);
-			if (!(plci->B1_facilities & B1_FACILITY_MIXER))
-			{
-				li_config_table[j].flag_table[i] |= LI_FLAG_CONFERENCE | LI_FLAG_MIX;
-				li_config_table[i].flag_table[j] |= LI_FLAG_CONFERENCE | LI_FLAG_MONITOR;
-			}
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_SLAVE_CODEC)
-			{
-				li_config_table[k].flag_table[i] |= LI_FLAG_CONFERENCE | LI_FLAG_MIX;
-				li_config_table[i].flag_table[k] |= LI_FLAG_CONFERENCE | LI_FLAG_MONITOR;
-				li_config_table[k].flag_table[j] |= LI_FLAG_CONFERENCE;
-				li_config_table[j].flag_table[k] |= LI_FLAG_CONFERENCE;
-			}
-			mixer_calculate_coefs(a);
-			li_config_table[i].curchnl = li_config_table[i].channel;
-			li_config_table[j].curchnl = li_config_table[j].channel;
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_SLAVE_CODEC)
-				li_config_table[k].curchnl = li_config_table[k].channel;
-			break;
-
-		case ADV_VOICE_WRITE_DEACTIVATION:
-			for (j = 0; j < li_total_channels; j++)
-			{
-				li_config_table[i].flag_table[j] = 0;
-				li_config_table[j].flag_table[i] = 0;
-			}
-			k = a->li_base + MIXER_IC_CHANNEL_BASE + (plci->li_bchannel_id - 1);
-			for (j = 0; j < li_total_channels; j++)
-			{
-				li_config_table[k].flag_table[j] = 0;
-				li_config_table[j].flag_table[k] = 0;
-			}
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_SLAVE_CODEC)
-			{
-				k = a->li_base + MIXER_IC_CHANNEL_BASE + (2 - plci->li_bchannel_id);
-				for (j = 0; j < li_total_channels; j++)
-				{
-					li_config_table[k].flag_table[j] = 0;
-					li_config_table[j].flag_table[k] = 0;
-				}
-			}
-			mixer_calculate_coefs(a);
-			break;
-		}
-		if (plci->B1_facilities & B1_FACILITY_MIXER)
-		{
-			w = 0;
-			if (ADV_VOICE_NEW_COEF_BASE + sizeof(word) <= a->adv_voice_coef_length)
-				w = GET_WORD(a->adv_voice_coef_buffer + ADV_VOICE_NEW_COEF_BASE);
-			if (li_config_table[i].channel & LI_CHANNEL_TX_DATA)
-				w |= MIXER_FEATURE_ENABLE_TX_DATA;
-			if (li_config_table[i].channel & LI_CHANNEL_RX_DATA)
-				w |= MIXER_FEATURE_ENABLE_RX_DATA;
-			*(p++) = (byte) w;
-			*(p++) = (byte)(w >> 8);
-			for (j = 0; j < sizeof(ch_map); j += 2)
-			{
-				ch_map[j] = (byte)(j + (plci->li_bchannel_id - 1));
-				ch_map[j + 1] = (byte)(j + (2 - plci->li_bchannel_id));
-			}
-			for (n = 0; n < ARRAY_SIZE(mixer_write_prog_bri); n++)
-			{
-				i = a->li_base + ch_map[mixer_write_prog_bri[n].to_ch];
-				j = a->li_base + ch_map[mixer_write_prog_bri[n].from_ch];
-				if (li_config_table[i].channel & li_config_table[j].channel & LI_CHANNEL_INVOLVED)
-				{
-					*(p++) = ((li_config_table[i].coef_table[j] & mixer_write_prog_bri[n].mask) ? 0x80 : 0x01);
-					w = ((li_config_table[i].coef_table[j] & 0xf) ^ (li_config_table[i].coef_table[j] >> 4));
-					li_config_table[i].coef_table[j] ^= (w & mixer_write_prog_bri[n].mask) << 4;
-				}
-				else
-				{
-					*(p++) = (ADV_VOICE_NEW_COEF_BASE + sizeof(word) + n < a->adv_voice_coef_length) ?
-						a->adv_voice_coef_buffer[ADV_VOICE_NEW_COEF_BASE + sizeof(word) + n] : 0x00;
-				}
-			}
-		}
-		else
-		{
-			for (i = ADV_VOICE_NEW_COEF_BASE; i < a->adv_voice_coef_length; i++)
-				*(p++) = a->adv_voice_coef_buffer[i];
-		}
-	}
-	else
-
-	{
-		for (i = ADV_VOICE_NEW_COEF_BASE; i < a->adv_voice_coef_length; i++)
-			*(p++) = a->adv_voice_coef_buffer[i];
-	}
-	coef_buffer[0] = (p - coef_buffer) - 1;
-	add_p(plci, FTY, coef_buffer);
-	sig_req(plci, TEL_CTRL, 0);
-	send_req(plci);
-}
-
-
-static void adv_voice_clear_config(PLCI *plci)
-{
-	DIVA_CAPI_ADAPTER *a;
-
-	word i, j;
-
-
-	dbug(1, dprintf("[%06lx] %s,%d: adv_voice_clear_config",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	a = plci->adapter;
-	if ((plci->tel == ADV_VOICE) && (plci == a->AdvSignalPLCI))
-	{
-		a->adv_voice_coef_length = 0;
-
-		if (!a->li_pri && (plci->li_bchannel_id != 0)
-		    && (li_config_table[a->li_base + (plci->li_bchannel_id - 1)].plci == plci))
-		{
-			i = a->li_base + (plci->li_bchannel_id - 1);
-			li_config_table[i].curchnl = 0;
-			li_config_table[i].channel = 0;
-			li_config_table[i].chflags = 0;
-			for (j = 0; j < li_total_channels; j++)
-			{
-				li_config_table[i].flag_table[j] = 0;
-				li_config_table[j].flag_table[i] = 0;
-				li_config_table[i].coef_table[j] = 0;
-				li_config_table[j].coef_table[i] = 0;
-			}
-			li_config_table[i].coef_table[i] |= LI_COEF_CH_PC_SET | LI_COEF_PC_CH_SET;
-			i = a->li_base + MIXER_IC_CHANNEL_BASE + (plci->li_bchannel_id - 1);
-			li_config_table[i].curchnl = 0;
-			li_config_table[i].channel = 0;
-			li_config_table[i].chflags = 0;
-			for (j = 0; j < li_total_channels; j++)
-			{
-				li_config_table[i].flag_table[j] = 0;
-				li_config_table[j].flag_table[i] = 0;
-				li_config_table[i].coef_table[j] = 0;
-				li_config_table[j].coef_table[i] = 0;
-			}
-			if (a->manufacturer_features & MANUFACTURER_FEATURE_SLAVE_CODEC)
-			{
-				i = a->li_base + MIXER_IC_CHANNEL_BASE + (2 - plci->li_bchannel_id);
-				li_config_table[i].curchnl = 0;
-				li_config_table[i].channel = 0;
-				li_config_table[i].chflags = 0;
-				for (j = 0; j < li_total_channels; j++)
-				{
-					li_config_table[i].flag_table[j] = 0;
-					li_config_table[j].flag_table[i] = 0;
-					li_config_table[i].coef_table[j] = 0;
-					li_config_table[j].coef_table[i] = 0;
-				}
-			}
-		}
-
-	}
-}
-
-
-static void adv_voice_prepare_switch(dword Id, PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: adv_voice_prepare_switch",
-			UnMapId(Id), (char *)(FILE_), __LINE__));
-
-}
-
-
-static word adv_voice_save_config(dword Id, PLCI *plci, byte Rc)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: adv_voice_save_config %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->adjust_b_state));
-
-	return (GOOD);
-}
-
-
-static word adv_voice_restore_config(dword Id, PLCI *plci, byte Rc)
-{
-	DIVA_CAPI_ADAPTER *a;
-	word Info;
-
-	dbug(1, dprintf("[%06lx] %s,%d: adv_voice_restore_config %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->adjust_b_state));
-
-	Info = GOOD;
-	a = plci->adapter;
-	if ((plci->B1_facilities & B1_FACILITY_VOICE)
-	    && (plci->tel == ADV_VOICE) && (plci == a->AdvSignalPLCI))
-	{
-		switch (plci->adjust_b_state)
-		{
-		case ADJUST_B_RESTORE_VOICE_1:
-			plci->internal_command = plci->adjust_b_command;
-			if (plci->sig_req)
-			{
-				plci->adjust_b_state = ADJUST_B_RESTORE_VOICE_1;
-				break;
-			}
-			adv_voice_write_coefs(plci, ADV_VOICE_WRITE_UPDATE);
-			plci->adjust_b_state = ADJUST_B_RESTORE_VOICE_2;
-			break;
-		case ADJUST_B_RESTORE_VOICE_2:
-			if ((Rc != OK) && (Rc != OK_FC))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Restore voice config failed %02x",
-						UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-				Info = _WRONG_STATE;
-				break;
-			}
-			break;
-		}
-	}
-	return (Info);
-}
-
-
-
-
-/*------------------------------------------------------------------*/
-/* B1 resource switching                                            */
-/*------------------------------------------------------------------*/
-
-static byte b1_facilities_table[] =
-{
-	0x00,  /* 0  No bchannel resources      */
-	0x00,  /* 1  Codec (automatic law)      */
-	0x00,  /* 2  Codec (A-law)              */
-	0x00,  /* 3  Codec (y-law)              */
-	0x00,  /* 4  HDLC for X.21              */
-	0x00,  /* 5  HDLC                       */
-	0x00,  /* 6  External Device 0          */
-	0x00,  /* 7  External Device 1          */
-	0x00,  /* 8  HDLC 56k                   */
-	0x00,  /* 9  Transparent                */
-	0x00,  /* 10 Loopback to network        */
-	0x00,  /* 11 Test pattern to net        */
-	0x00,  /* 12 Rate adaptation sync       */
-	0x00,  /* 13 Rate adaptation async      */
-	0x00,  /* 14 R-Interface                */
-	0x00,  /* 15 HDLC 128k leased line      */
-	0x00,  /* 16 FAX                        */
-	0x00,  /* 17 Modem async                */
-	0x00,  /* 18 Modem sync HDLC            */
-	0x00,  /* 19 V.110 async HDLC           */
-	0x12,  /* 20 Adv voice (Trans,mixer)    */
-	0x00,  /* 21 Codec connected to IC      */
-	0x0c,  /* 22 Trans,DTMF                 */
-	0x1e,  /* 23 Trans,DTMF+mixer           */
-	0x1f,  /* 24 Trans,DTMF+mixer+local     */
-	0x13,  /* 25 Trans,mixer+local          */
-	0x12,  /* 26 HDLC,mixer                 */
-	0x12,  /* 27 HDLC 56k,mixer             */
-	0x2c,  /* 28 Trans,LEC+DTMF             */
-	0x3e,  /* 29 Trans,LEC+DTMF+mixer       */
-	0x3f,  /* 30 Trans,LEC+DTMF+mixer+local */
-	0x2c,  /* 31 RTP,LEC+DTMF               */
-	0x3e,  /* 32 RTP,LEC+DTMF+mixer         */
-	0x3f,  /* 33 RTP,LEC+DTMF+mixer+local   */
-	0x00,  /* 34 Signaling task             */
-	0x00,  /* 35 PIAFS                      */
-	0x0c,  /* 36 Trans,DTMF+TONE            */
-	0x1e,  /* 37 Trans,DTMF+TONE+mixer      */
-	0x1f   /* 38 Trans,DTMF+TONE+mixer+local*/
-};
-
-
-static word get_b1_facilities(PLCI *plci, byte b1_resource)
-{
-	word b1_facilities;
-
-	b1_facilities = b1_facilities_table[b1_resource];
-	if ((b1_resource == 9) || (b1_resource == 20) || (b1_resource == 25))
-	{
-
-		if (!(((plci->requested_options_conn | plci->requested_options) & (1L << PRIVATE_DTMF_TONE))
-		      || (plci->appl && (plci->adapter->requested_options_table[plci->appl->Id - 1] & (1L << PRIVATE_DTMF_TONE)))))
-
-		{
-			if (plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_SOFTDTMF_SEND)
-				b1_facilities |= B1_FACILITY_DTMFX;
-			if (plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_SOFTDTMF_RECEIVE)
-				b1_facilities |= B1_FACILITY_DTMFR;
-		}
-	}
-	if ((b1_resource == 17) || (b1_resource == 18))
-	{
-		if (plci->adapter->manufacturer_features & (MANUFACTURER_FEATURE_V18 | MANUFACTURER_FEATURE_VOWN))
-			b1_facilities |= B1_FACILITY_DTMFX | B1_FACILITY_DTMFR;
-	}
-/*
-  dbug (1, dprintf("[%06lx] %s,%d: get_b1_facilities %d %04x",
-  (dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-  (char far *)(FILE_), __LINE__, b1_resource, b1_facilites));
-*/
-	return (b1_facilities);
-}
-
-
-static byte add_b1_facilities(PLCI *plci, byte b1_resource, word b1_facilities)
-{
-	byte b;
-
-	switch (b1_resource)
-	{
-	case 5:
-	case 26:
-		if (b1_facilities & (B1_FACILITY_MIXER | B1_FACILITY_VOICE))
-			b = 26;
-		else
-			b = 5;
-		break;
-
-	case 8:
-	case 27:
-		if (b1_facilities & (B1_FACILITY_MIXER | B1_FACILITY_VOICE))
-			b = 27;
-		else
-			b = 8;
-		break;
-
-	case 9:
-	case 20:
-	case 22:
-	case 23:
-	case 24:
-	case 25:
-	case 28:
-	case 29:
-	case 30:
-	case 36:
-	case 37:
-	case 38:
-		if (b1_facilities & B1_FACILITY_EC)
-		{
-			if (b1_facilities & B1_FACILITY_LOCAL)
-				b = 30;
-			else if (b1_facilities & (B1_FACILITY_MIXER | B1_FACILITY_VOICE))
-				b = 29;
-			else
-				b = 28;
-		}
-
-		else if ((b1_facilities & (B1_FACILITY_DTMFX | B1_FACILITY_DTMFR | B1_FACILITY_MIXER))
-			 && (((plci->requested_options_conn | plci->requested_options) & (1L << PRIVATE_DTMF_TONE))
-			     || (plci->appl && (plci->adapter->requested_options_table[plci->appl->Id - 1] & (1L << PRIVATE_DTMF_TONE)))))
-		{
-			if (b1_facilities & B1_FACILITY_LOCAL)
-				b = 38;
-			else if (b1_facilities & (B1_FACILITY_MIXER | B1_FACILITY_VOICE))
-				b = 37;
-			else
-				b = 36;
-		}
-
-		else if (((plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_HARDDTMF)
-			  && !(plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_SOFTDTMF_RECEIVE))
-			 || ((b1_facilities & B1_FACILITY_DTMFR)
-			     && ((b1_facilities & B1_FACILITY_MIXER)
-				 || !(plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_SOFTDTMF_RECEIVE)))
-			 || ((b1_facilities & B1_FACILITY_DTMFX)
-			     && ((b1_facilities & B1_FACILITY_MIXER)
-				 || !(plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_SOFTDTMF_SEND))))
-		{
-			if (b1_facilities & B1_FACILITY_LOCAL)
-				b = 24;
-			else if (b1_facilities & (B1_FACILITY_MIXER | B1_FACILITY_VOICE))
-				b = 23;
-			else
-				b = 22;
-		}
-		else
-		{
-			if (b1_facilities & B1_FACILITY_LOCAL)
-				b = 25;
-			else if (b1_facilities & (B1_FACILITY_MIXER | B1_FACILITY_VOICE))
-				b = 20;
-			else
-				b = 9;
-		}
-		break;
-
-	case 31:
-	case 32:
-	case 33:
-		if (b1_facilities & B1_FACILITY_LOCAL)
-			b = 33;
-		else if (b1_facilities & (B1_FACILITY_MIXER | B1_FACILITY_VOICE))
-			b = 32;
-		else
-			b = 31;
-		break;
-
-	default:
-		b = b1_resource;
-	}
-	dbug(1, dprintf("[%06lx] %s,%d: add_b1_facilities %d %04x %d %04x",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__,
-			b1_resource, b1_facilities, b, get_b1_facilities(plci, b)));
-	return (b);
-}
-
-
-static void adjust_b1_facilities(PLCI *plci, byte new_b1_resource, word new_b1_facilities)
-{
-	word removed_facilities;
-
-	dbug(1, dprintf("[%06lx] %s,%d: adjust_b1_facilities %d %04x %04x",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__, new_b1_resource, new_b1_facilities,
-			new_b1_facilities & get_b1_facilities(plci, new_b1_resource)));
-
-	new_b1_facilities &= get_b1_facilities(plci, new_b1_resource);
-	removed_facilities = plci->B1_facilities & ~new_b1_facilities;
-
-	if (removed_facilities & B1_FACILITY_EC)
-		ec_clear_config(plci);
-
-
-	if (removed_facilities & B1_FACILITY_DTMFR)
-	{
-		dtmf_rec_clear_config(plci);
-		dtmf_parameter_clear_config(plci);
-	}
-	if (removed_facilities & B1_FACILITY_DTMFX)
-		dtmf_send_clear_config(plci);
-
-
-	if (removed_facilities & B1_FACILITY_MIXER)
-		mixer_clear_config(plci);
-
-	if (removed_facilities & B1_FACILITY_VOICE)
-		adv_voice_clear_config(plci);
-	plci->B1_facilities = new_b1_facilities;
-}
-
-
-static void adjust_b_clear(PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: adjust_b_clear",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	plci->adjust_b_restore = false;
-}
-
-
-static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
-{
-	word Info;
-	byte b1_resource;
-	NCCI *ncci_ptr;
-	API_PARSE bp[2];
-
-	dbug(1, dprintf("[%06lx] %s,%d: adjust_b_process %02x %d",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->adjust_b_state));
-
-	Info = GOOD;
-	switch (plci->adjust_b_state)
-	{
-	case ADJUST_B_START:
-		if ((plci->adjust_b_parms_msg == NULL)
-		    && (plci->adjust_b_mode & ADJUST_B_MODE_SWITCH_L1)
-		    && ((plci->adjust_b_mode & ~(ADJUST_B_MODE_SAVE | ADJUST_B_MODE_SWITCH_L1 |
-						 ADJUST_B_MODE_NO_RESOURCE | ADJUST_B_MODE_RESTORE)) == 0))
-		{
-			b1_resource = (plci->adjust_b_mode == ADJUST_B_MODE_NO_RESOURCE) ?
-				0 : add_b1_facilities(plci, plci->B1_resource, plci->adjust_b_facilities);
-			if (b1_resource == plci->B1_resource)
-			{
-				adjust_b1_facilities(plci, b1_resource, plci->adjust_b_facilities);
-				break;
-			}
-			if (plci->adjust_b_facilities & ~get_b1_facilities(plci, b1_resource))
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Adjust B nonsupported facilities %d %d %04x",
-						UnMapId(Id), (char *)(FILE_), __LINE__,
-						plci->B1_resource, b1_resource, plci->adjust_b_facilities));
-				Info = _WRONG_STATE;
-				break;
-			}
-		}
-		if (plci->adjust_b_mode & ADJUST_B_MODE_SAVE)
-		{
-
-			mixer_prepare_switch(Id, plci);
-
-
-			dtmf_prepare_switch(Id, plci);
-			dtmf_parameter_prepare_switch(Id, plci);
-
-
-			ec_prepare_switch(Id, plci);
-
-			adv_voice_prepare_switch(Id, plci);
-		}
-		plci->adjust_b_state = ADJUST_B_SAVE_MIXER_1;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_SAVE_MIXER_1:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_SAVE)
-		{
-
-			Info = mixer_save_config(Id, plci, Rc);
-			if ((Info != GOOD) || plci->internal_command)
-				break;
-
-		}
-		plci->adjust_b_state = ADJUST_B_SAVE_DTMF_1;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_SAVE_DTMF_1:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_SAVE)
-		{
-
-			Info = dtmf_save_config(Id, plci, Rc);
-			if ((Info != GOOD) || plci->internal_command)
-				break;
-
-		}
-		plci->adjust_b_state = ADJUST_B_REMOVE_L23_1;
-		/* fall through */
-	case ADJUST_B_REMOVE_L23_1:
-		if ((plci->adjust_b_mode & ADJUST_B_MODE_REMOVE_L23)
-		    && plci->NL.Id && !plci->nl_remove_id)
-		{
-			plci->internal_command = plci->adjust_b_command;
-			if (plci->adjust_b_ncci != 0)
-			{
-				ncci_ptr = &(plci->adapter->ncci[plci->adjust_b_ncci]);
-				while (ncci_ptr->data_pending)
-				{
-					plci->data_sent_ptr = ncci_ptr->DBuffer[ncci_ptr->data_out].P;
-					data_rc(plci, plci->adapter->ncci_ch[plci->adjust_b_ncci]);
-				}
-				while (ncci_ptr->data_ack_pending)
-					data_ack(plci, plci->adapter->ncci_ch[plci->adjust_b_ncci]);
-			}
-			nl_req_ncci(plci, REMOVE,
-				    (byte)((plci->adjust_b_mode & ADJUST_B_MODE_CONNECT) ? plci->adjust_b_ncci : 0));
-			send_req(plci);
-			plci->adjust_b_state = ADJUST_B_REMOVE_L23_2;
-			break;
-		}
-		plci->adjust_b_state = ADJUST_B_REMOVE_L23_2;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_REMOVE_L23_2:
-		if ((Rc != OK) && (Rc != OK_FC))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: Adjust B remove failed %02x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-			Info = _WRONG_STATE;
-			break;
-		}
-		if (plci->adjust_b_mode & ADJUST_B_MODE_REMOVE_L23)
-		{
-			if (plci_nl_busy(plci))
-			{
-				plci->internal_command = plci->adjust_b_command;
-				break;
-			}
-		}
-		plci->adjust_b_state = ADJUST_B_SAVE_EC_1;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_SAVE_EC_1:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_SAVE)
-		{
-
-			Info = ec_save_config(Id, plci, Rc);
-			if ((Info != GOOD) || plci->internal_command)
-				break;
-
-		}
-		plci->adjust_b_state = ADJUST_B_SAVE_DTMF_PARAMETER_1;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_SAVE_DTMF_PARAMETER_1:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_SAVE)
-		{
-
-			Info = dtmf_parameter_save_config(Id, plci, Rc);
-			if ((Info != GOOD) || plci->internal_command)
-				break;
-
-		}
-		plci->adjust_b_state = ADJUST_B_SAVE_VOICE_1;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_SAVE_VOICE_1:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_SAVE)
-		{
-			Info = adv_voice_save_config(Id, plci, Rc);
-			if ((Info != GOOD) || plci->internal_command)
-				break;
-		}
-		plci->adjust_b_state = ADJUST_B_SWITCH_L1_1;
-		/* fall through */
-	case ADJUST_B_SWITCH_L1_1:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_SWITCH_L1)
-		{
-			if (plci->sig_req)
-			{
-				plci->internal_command = plci->adjust_b_command;
-				break;
-			}
-			if (plci->adjust_b_parms_msg != NULL)
-				api_load_msg(plci->adjust_b_parms_msg, bp);
-			else
-				api_load_msg(&plci->B_protocol, bp);
-			Info = add_b1(plci, bp,
-				      (word)((plci->adjust_b_mode & ADJUST_B_MODE_NO_RESOURCE) ? 2 : 0),
-				      plci->adjust_b_facilities);
-			if (Info != GOOD)
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Adjust B invalid L1 parameters %d %04x",
-						UnMapId(Id), (char *)(FILE_), __LINE__,
-						plci->B1_resource, plci->adjust_b_facilities));
-				break;
-			}
-			plci->internal_command = plci->adjust_b_command;
-			sig_req(plci, RESOURCES, 0);
-			send_req(plci);
-			plci->adjust_b_state = ADJUST_B_SWITCH_L1_2;
-			break;
-		}
-		plci->adjust_b_state = ADJUST_B_SWITCH_L1_2;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_SWITCH_L1_2:
-		if ((Rc != OK) && (Rc != OK_FC))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: Adjust B switch failed %02x %d %04x",
-					UnMapId(Id), (char *)(FILE_), __LINE__,
-					Rc, plci->B1_resource, plci->adjust_b_facilities));
-			Info = _WRONG_STATE;
-			break;
-		}
-		plci->adjust_b_state = ADJUST_B_RESTORE_VOICE_1;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_RESTORE_VOICE_1:
-	case ADJUST_B_RESTORE_VOICE_2:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_RESTORE)
-		{
-			Info = adv_voice_restore_config(Id, plci, Rc);
-			if ((Info != GOOD) || plci->internal_command)
-				break;
-		}
-		plci->adjust_b_state = ADJUST_B_RESTORE_DTMF_PARAMETER_1;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_RESTORE_DTMF_PARAMETER_1:
-	case ADJUST_B_RESTORE_DTMF_PARAMETER_2:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_RESTORE)
-		{
-
-			Info = dtmf_parameter_restore_config(Id, plci, Rc);
-			if ((Info != GOOD) || plci->internal_command)
-				break;
-
-		}
-		plci->adjust_b_state = ADJUST_B_RESTORE_EC_1;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_RESTORE_EC_1:
-	case ADJUST_B_RESTORE_EC_2:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_RESTORE)
-		{
-
-			Info = ec_restore_config(Id, plci, Rc);
-			if ((Info != GOOD) || plci->internal_command)
-				break;
-
-		}
-		plci->adjust_b_state = ADJUST_B_ASSIGN_L23_1;
-		/* fall through */
-	case ADJUST_B_ASSIGN_L23_1:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_ASSIGN_L23)
-		{
-			if (plci_nl_busy(plci))
-			{
-				plci->internal_command = plci->adjust_b_command;
-				break;
-			}
-			if (plci->adjust_b_mode & ADJUST_B_MODE_CONNECT)
-				plci->call_dir |= CALL_DIR_FORCE_OUTG_NL;
-			if (plci->adjust_b_parms_msg != NULL)
-				api_load_msg(plci->adjust_b_parms_msg, bp);
-			else
-				api_load_msg(&plci->B_protocol, bp);
-			Info = add_b23(plci, bp);
-			if (Info != GOOD)
-			{
-				dbug(1, dprintf("[%06lx] %s,%d: Adjust B invalid L23 parameters %04x",
-						UnMapId(Id), (char *)(FILE_), __LINE__, Info));
-				break;
-			}
-			plci->internal_command = plci->adjust_b_command;
-			nl_req_ncci(plci, ASSIGN, 0);
-			send_req(plci);
-			plci->adjust_b_state = ADJUST_B_ASSIGN_L23_2;
-			break;
-		}
-		plci->adjust_b_state = ADJUST_B_ASSIGN_L23_2;
-		Rc = ASSIGN_OK;
-		/* fall through */
-	case ADJUST_B_ASSIGN_L23_2:
-		if ((Rc != OK) && (Rc != OK_FC) && (Rc != ASSIGN_OK))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: Adjust B assign failed %02x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-			Info = _WRONG_STATE;
-			break;
-		}
-		if (plci->adjust_b_mode & ADJUST_B_MODE_ASSIGN_L23)
-		{
-			if (Rc != ASSIGN_OK)
-			{
-				plci->internal_command = plci->adjust_b_command;
-				break;
-			}
-		}
-		if (plci->adjust_b_mode & ADJUST_B_MODE_USER_CONNECT)
-		{
-			plci->adjust_b_restore = true;
-			break;
-		}
-		plci->adjust_b_state = ADJUST_B_CONNECT_1;
-		/* fall through */
-	case ADJUST_B_CONNECT_1:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_CONNECT)
-		{
-			plci->internal_command = plci->adjust_b_command;
-			if (plci_nl_busy(plci))
-				break;
-			nl_req_ncci(plci, N_CONNECT, 0);
-			send_req(plci);
-			plci->adjust_b_state = ADJUST_B_CONNECT_2;
-			break;
-		}
-		plci->adjust_b_state = ADJUST_B_RESTORE_DTMF_1;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_CONNECT_2:
-	case ADJUST_B_CONNECT_3:
-	case ADJUST_B_CONNECT_4:
-		if ((Rc != OK) && (Rc != OK_FC) && (Rc != 0))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: Adjust B connect failed %02x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-			Info = _WRONG_STATE;
-			break;
-		}
-		if (Rc == OK)
-		{
-			if (plci->adjust_b_mode & ADJUST_B_MODE_CONNECT)
-			{
-				get_ncci(plci, (byte)(Id >> 16), plci->adjust_b_ncci);
-				Id = (Id & 0xffff) | (((dword)(plci->adjust_b_ncci)) << 16);
-			}
-			if (plci->adjust_b_state == ADJUST_B_CONNECT_2)
-				plci->adjust_b_state = ADJUST_B_CONNECT_3;
-			else if (plci->adjust_b_state == ADJUST_B_CONNECT_4)
-				plci->adjust_b_state = ADJUST_B_RESTORE_DTMF_1;
-		}
-		else if (Rc == 0)
-		{
-			if (plci->adjust_b_state == ADJUST_B_CONNECT_2)
-				plci->adjust_b_state = ADJUST_B_CONNECT_4;
-			else if (plci->adjust_b_state == ADJUST_B_CONNECT_3)
-				plci->adjust_b_state = ADJUST_B_RESTORE_DTMF_1;
-		}
-		if (plci->adjust_b_state != ADJUST_B_RESTORE_DTMF_1)
-		{
-			plci->internal_command = plci->adjust_b_command;
-			break;
-		}
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_RESTORE_DTMF_1:
-	case ADJUST_B_RESTORE_DTMF_2:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_RESTORE)
-		{
-
-			Info = dtmf_restore_config(Id, plci, Rc);
-			if ((Info != GOOD) || plci->internal_command)
-				break;
-
-		}
-		plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_1;
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_RESTORE_MIXER_1:
-	case ADJUST_B_RESTORE_MIXER_2:
-	case ADJUST_B_RESTORE_MIXER_3:
-	case ADJUST_B_RESTORE_MIXER_4:
-	case ADJUST_B_RESTORE_MIXER_5:
-	case ADJUST_B_RESTORE_MIXER_6:
-	case ADJUST_B_RESTORE_MIXER_7:
-		if (plci->adjust_b_mode & ADJUST_B_MODE_RESTORE)
-		{
-
-			Info = mixer_restore_config(Id, plci, Rc);
-			if ((Info != GOOD) || plci->internal_command)
-				break;
-
-		}
-		plci->adjust_b_state = ADJUST_B_END;
-	case ADJUST_B_END:
-		break;
-	}
-	return (Info);
-}
-
-
-static void adjust_b1_resource(dword Id, PLCI *plci, API_SAVE   *bp_msg, word b1_facilities, word internal_command)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: adjust_b1_resource %d %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__,
-			plci->B1_resource, b1_facilities));
-
-	plci->adjust_b_parms_msg = bp_msg;
-	plci->adjust_b_facilities = b1_facilities;
-	plci->adjust_b_command = internal_command;
-	plci->adjust_b_ncci = (word)(Id >> 16);
-	if ((bp_msg == NULL) && (plci->B1_resource == 0))
-		plci->adjust_b_mode = ADJUST_B_MODE_SAVE | ADJUST_B_MODE_NO_RESOURCE | ADJUST_B_MODE_SWITCH_L1;
-	else
-		plci->adjust_b_mode = ADJUST_B_MODE_SAVE | ADJUST_B_MODE_SWITCH_L1 | ADJUST_B_MODE_RESTORE;
-	plci->adjust_b_state = ADJUST_B_START;
-	dbug(1, dprintf("[%06lx] %s,%d: Adjust B1 resource %d %04x...",
-			UnMapId(Id), (char *)(FILE_), __LINE__,
-			plci->B1_resource, b1_facilities));
-}
-
-
-static void adjust_b_restore(dword Id, PLCI *plci, byte Rc)
-{
-	word internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: adjust_b_restore %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		plci->command = 0;
-		if (plci->req_in != 0)
-		{
-			plci->internal_command = ADJUST_B_RESTORE_1;
-			break;
-		}
-		Rc = OK;
-		/* fall through */
-	case ADJUST_B_RESTORE_1:
-		if ((Rc != OK) && (Rc != OK_FC))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: Adjust B enqueued failed %02x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-		}
-		plci->adjust_b_parms_msg = NULL;
-		plci->adjust_b_facilities = plci->B1_facilities;
-		plci->adjust_b_command = ADJUST_B_RESTORE_2;
-		plci->adjust_b_ncci = (word)(Id >> 16);
-		plci->adjust_b_mode = ADJUST_B_MODE_RESTORE;
-		plci->adjust_b_state = ADJUST_B_START;
-		dbug(1, dprintf("[%06lx] %s,%d: Adjust B restore...",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		/* fall through */
-	case ADJUST_B_RESTORE_2:
-		if (adjust_b_process(Id, plci, Rc) != GOOD)
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: Adjust B restore failed",
-					UnMapId(Id), (char *)(FILE_), __LINE__));
-		}
-		if (plci->internal_command)
-			break;
-		break;
-	}
-}
-
-
-static void reset_b3_command(dword Id, PLCI *plci, byte Rc)
-{
-	word Info;
-	word internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: reset_b3_command %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	Info = GOOD;
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		plci->command = 0;
-		plci->adjust_b_parms_msg = NULL;
-		plci->adjust_b_facilities = plci->B1_facilities;
-		plci->adjust_b_command = RESET_B3_COMMAND_1;
-		plci->adjust_b_ncci = (word)(Id >> 16);
-		plci->adjust_b_mode = ADJUST_B_MODE_REMOVE_L23 | ADJUST_B_MODE_ASSIGN_L23 | ADJUST_B_MODE_CONNECT;
-		plci->adjust_b_state = ADJUST_B_START;
-		dbug(1, dprintf("[%06lx] %s,%d: Reset B3...",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		/* fall through */
-	case RESET_B3_COMMAND_1:
-		Info = adjust_b_process(Id, plci, Rc);
-		if (Info != GOOD)
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: Reset failed",
-					UnMapId(Id), (char *)(FILE_), __LINE__));
-			break;
-		}
-		if (plci->internal_command)
-			return;
-		break;
-	}
-/*  sendf (plci->appl, _RESET_B3_R | CONFIRM, Id, plci->number, "w", Info);*/
-	sendf(plci->appl, _RESET_B3_I, Id, 0, "s", "");
-}
-
-
-static void select_b_command(dword Id, PLCI *plci, byte Rc)
-{
-	word Info;
-	word internal_command;
-	byte esc_chi[3];
-
-	dbug(1, dprintf("[%06lx] %s,%d: select_b_command %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	Info = GOOD;
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		plci->command = 0;
-		plci->adjust_b_parms_msg = &plci->saved_msg;
-		if ((plci->tel == ADV_VOICE) && (plci == plci->adapter->AdvSignalPLCI))
-			plci->adjust_b_facilities = plci->B1_facilities | B1_FACILITY_VOICE;
-		else
-			plci->adjust_b_facilities = plci->B1_facilities & ~B1_FACILITY_VOICE;
-		plci->adjust_b_command = SELECT_B_COMMAND_1;
-		plci->adjust_b_ncci = (word)(Id >> 16);
-		if (plci->saved_msg.parms[0].length == 0)
-		{
-			plci->adjust_b_mode = ADJUST_B_MODE_SAVE | ADJUST_B_MODE_REMOVE_L23 | ADJUST_B_MODE_SWITCH_L1 |
-				ADJUST_B_MODE_NO_RESOURCE;
-		}
-		else
-		{
-			plci->adjust_b_mode = ADJUST_B_MODE_SAVE | ADJUST_B_MODE_REMOVE_L23 | ADJUST_B_MODE_SWITCH_L1 |
-				ADJUST_B_MODE_ASSIGN_L23 | ADJUST_B_MODE_USER_CONNECT | ADJUST_B_MODE_RESTORE;
-		}
-		plci->adjust_b_state = ADJUST_B_START;
-		dbug(1, dprintf("[%06lx] %s,%d: Select B protocol...",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		/* fall through */
-	case SELECT_B_COMMAND_1:
-		Info = adjust_b_process(Id, plci, Rc);
-		if (Info != GOOD)
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: Select B protocol failed",
-					UnMapId(Id), (char *)(FILE_), __LINE__));
-			break;
-		}
-		if (plci->internal_command)
-			return;
-		if (plci->tel == ADV_VOICE)
-		{
-			esc_chi[0] = 0x02;
-			esc_chi[1] = 0x18;
-			esc_chi[2] = plci->b_channel;
-			SetVoiceChannel(plci->adapter->AdvCodecPLCI, esc_chi, plci->adapter);
-		}
-		break;
-	}
-	sendf(plci->appl, _SELECT_B_REQ | CONFIRM, Id, plci->number, "w", Info);
-}
-
-
-static void fax_connect_ack_command(dword Id, PLCI *plci, byte Rc)
-{
-	word internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: fax_connect_ack_command %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		plci->command = 0; /* fall through */
-	case FAX_CONNECT_ACK_COMMAND_1:
-		if (plci_nl_busy(plci))
-		{
-			plci->internal_command = FAX_CONNECT_ACK_COMMAND_1;
-			return;
-		}
-		plci->internal_command = FAX_CONNECT_ACK_COMMAND_2;
-		plci->NData[0].P = plci->fax_connect_info_buffer;
-		plci->NData[0].PLength = plci->fax_connect_info_length;
-		plci->NL.X = plci->NData;
-		plci->NL.ReqCh = 0;
-		plci->NL.Req = plci->nl_req = (byte) N_CONNECT_ACK;
-		plci->adapter->request(&plci->NL);
-		return;
-	case FAX_CONNECT_ACK_COMMAND_2:
-		if ((Rc != OK) && (Rc != OK_FC))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: FAX issue CONNECT ACK failed %02x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-			break;
-		}
-	}
-	if ((plci->ncpi_state & NCPI_VALID_CONNECT_B3_ACT)
-	    && !(plci->ncpi_state & NCPI_CONNECT_B3_ACT_SENT))
-	{
-		if (plci->B3_prot == 4)
-			sendf(plci->appl, _CONNECT_B3_ACTIVE_I, Id, 0, "s", "");
-		else
-			sendf(plci->appl, _CONNECT_B3_ACTIVE_I, Id, 0, "S", plci->ncpi_buffer);
-		plci->ncpi_state |= NCPI_CONNECT_B3_ACT_SENT;
-	}
-}
-
-
-static void fax_edata_ack_command(dword Id, PLCI *plci, byte Rc)
-{
-	word internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: fax_edata_ack_command %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		plci->command = 0;
-		/* fall through */
-	case FAX_EDATA_ACK_COMMAND_1:
-		if (plci_nl_busy(plci))
-		{
-			plci->internal_command = FAX_EDATA_ACK_COMMAND_1;
-			return;
-		}
-		plci->internal_command = FAX_EDATA_ACK_COMMAND_2;
-		plci->NData[0].P = plci->fax_connect_info_buffer;
-		plci->NData[0].PLength = plci->fax_edata_ack_length;
-		plci->NL.X = plci->NData;
-		plci->NL.ReqCh = 0;
-		plci->NL.Req = plci->nl_req = (byte) N_EDATA;
-		plci->adapter->request(&plci->NL);
-		return;
-	case FAX_EDATA_ACK_COMMAND_2:
-		if ((Rc != OK) && (Rc != OK_FC))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: FAX issue EDATA ACK failed %02x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-			break;
-		}
-	}
-}
-
-
-static void fax_connect_info_command(dword Id, PLCI *plci, byte Rc)
-{
-	word Info;
-	word internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: fax_connect_info_command %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	Info = GOOD;
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		plci->command = 0; /* fall through */
-	case FAX_CONNECT_INFO_COMMAND_1:
-		if (plci_nl_busy(plci))
-		{
-			plci->internal_command = FAX_CONNECT_INFO_COMMAND_1;
-			return;
-		}
-		plci->internal_command = FAX_CONNECT_INFO_COMMAND_2;
-		plci->NData[0].P = plci->fax_connect_info_buffer;
-		plci->NData[0].PLength = plci->fax_connect_info_length;
-		plci->NL.X = plci->NData;
-		plci->NL.ReqCh = 0;
-		plci->NL.Req = plci->nl_req = (byte) N_EDATA;
-		plci->adapter->request(&plci->NL);
-		return;
-	case FAX_CONNECT_INFO_COMMAND_2:
-		if ((Rc != OK) && (Rc != OK_FC))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: FAX setting connect info failed %02x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-			Info = _WRONG_STATE;
-			break;
-		}
-		if (plci_nl_busy(plci))
-		{
-			plci->internal_command = FAX_CONNECT_INFO_COMMAND_2;
-			return;
-		}
-		plci->command = _CONNECT_B3_R;
-		nl_req_ncci(plci, N_CONNECT, 0);
-		send_req(plci);
-		return;
-	}
-	sendf(plci->appl, _CONNECT_B3_R | CONFIRM, Id, plci->number, "w", Info);
-}
-
-
-static void fax_adjust_b23_command(dword Id, PLCI *plci, byte Rc)
-{
-	word Info;
-	word internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: fax_adjust_b23_command %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	Info = GOOD;
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		plci->command = 0;
-		plci->adjust_b_parms_msg = NULL;
-		plci->adjust_b_facilities = plci->B1_facilities;
-		plci->adjust_b_command = FAX_ADJUST_B23_COMMAND_1;
-		plci->adjust_b_ncci = (word)(Id >> 16);
-		plci->adjust_b_mode = ADJUST_B_MODE_REMOVE_L23 | ADJUST_B_MODE_ASSIGN_L23;
-		plci->adjust_b_state = ADJUST_B_START;
-		dbug(1, dprintf("[%06lx] %s,%d: FAX adjust B23...",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		/* fall through */
-	case FAX_ADJUST_B23_COMMAND_1:
-		Info = adjust_b_process(Id, plci, Rc);
-		if (Info != GOOD)
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: FAX adjust failed",
-					UnMapId(Id), (char *)(FILE_), __LINE__));
-			break;
-		}
-		if (plci->internal_command)
-			return;
-		/* fall through */
-	case FAX_ADJUST_B23_COMMAND_2:
-		if (plci_nl_busy(plci))
-		{
-			plci->internal_command = FAX_ADJUST_B23_COMMAND_2;
-			return;
-		}
-		plci->command = _CONNECT_B3_R;
-		nl_req_ncci(plci, N_CONNECT, 0);
-		send_req(plci);
-		return;
-	}
-	sendf(plci->appl, _CONNECT_B3_R | CONFIRM, Id, plci->number, "w", Info);
-}
-
-
-static void fax_disconnect_command(dword Id, PLCI *plci, byte Rc)
-{
-	word internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: fax_disconnect_command %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		plci->command = 0;
-		plci->internal_command = FAX_DISCONNECT_COMMAND_1;
-		return;
-	case FAX_DISCONNECT_COMMAND_1:
-	case FAX_DISCONNECT_COMMAND_2:
-	case FAX_DISCONNECT_COMMAND_3:
-		if ((Rc != OK) && (Rc != OK_FC) && (Rc != 0))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: FAX disconnect EDATA failed %02x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-			break;
-		}
-		if (Rc == OK)
-		{
-			if ((internal_command == FAX_DISCONNECT_COMMAND_1)
-			    || (internal_command == FAX_DISCONNECT_COMMAND_2))
-			{
-				plci->internal_command = FAX_DISCONNECT_COMMAND_2;
-			}
-		}
-		else if (Rc == 0)
-		{
-			if (internal_command == FAX_DISCONNECT_COMMAND_1)
-				plci->internal_command = FAX_DISCONNECT_COMMAND_3;
-		}
-		return;
-	}
-}
-
-
-
-static void rtp_connect_b3_req_command(dword Id, PLCI *plci, byte Rc)
-{
-	word Info;
-	word internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: rtp_connect_b3_req_command %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	Info = GOOD;
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		plci->command = 0; /* fall through */
-	case RTP_CONNECT_B3_REQ_COMMAND_1:
-		if (plci_nl_busy(plci))
-		{
-			plci->internal_command = RTP_CONNECT_B3_REQ_COMMAND_1;
-			return;
-		}
-		plci->internal_command = RTP_CONNECT_B3_REQ_COMMAND_2;
-		nl_req_ncci(plci, N_CONNECT, 0);
-		send_req(plci);
-		return;
-	case RTP_CONNECT_B3_REQ_COMMAND_2:
-		if ((Rc != OK) && (Rc != OK_FC))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: RTP setting connect info failed %02x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-			Info = _WRONG_STATE;
-			break;
-		}
-		if (plci_nl_busy(plci))
-		{
-			plci->internal_command = RTP_CONNECT_B3_REQ_COMMAND_2;
-			return;
-		}
-		plci->internal_command = RTP_CONNECT_B3_REQ_COMMAND_3;
-		plci->NData[0].PLength = plci->internal_req_buffer[0];
-		plci->NData[0].P = plci->internal_req_buffer + 1;
-		plci->NL.X = plci->NData;
-		plci->NL.ReqCh = 0;
-		plci->NL.Req = plci->nl_req = (byte) N_UDATA;
-		plci->adapter->request(&plci->NL);
-		break;
-	case RTP_CONNECT_B3_REQ_COMMAND_3:
-		return;
-	}
-	sendf(plci->appl, _CONNECT_B3_R | CONFIRM, Id, plci->number, "w", Info);
-}
-
-
-static void rtp_connect_b3_res_command(dword Id, PLCI *plci, byte Rc)
-{
-	word internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: rtp_connect_b3_res_command %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		plci->command = 0; /* fall through */
-	case RTP_CONNECT_B3_RES_COMMAND_1:
-		if (plci_nl_busy(plci))
-		{
-			plci->internal_command = RTP_CONNECT_B3_RES_COMMAND_1;
-			return;
-		}
-		plci->internal_command = RTP_CONNECT_B3_RES_COMMAND_2;
-		nl_req_ncci(plci, N_CONNECT_ACK, (byte)(Id >> 16));
-		send_req(plci);
-		return;
-	case RTP_CONNECT_B3_RES_COMMAND_2:
-		if ((Rc != OK) && (Rc != OK_FC))
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: RTP setting connect resp info failed %02x",
-					UnMapId(Id), (char *)(FILE_), __LINE__, Rc));
-			break;
-		}
-		if (plci_nl_busy(plci))
-		{
-			plci->internal_command = RTP_CONNECT_B3_RES_COMMAND_2;
-			return;
-		}
-		sendf(plci->appl, _CONNECT_B3_ACTIVE_I, Id, 0, "s", "");
-		plci->internal_command = RTP_CONNECT_B3_RES_COMMAND_3;
-		plci->NData[0].PLength = plci->internal_req_buffer[0];
-		plci->NData[0].P = plci->internal_req_buffer + 1;
-		plci->NL.X = plci->NData;
-		plci->NL.ReqCh = 0;
-		plci->NL.Req = plci->nl_req = (byte) N_UDATA;
-		plci->adapter->request(&plci->NL);
-		return;
-	case RTP_CONNECT_B3_RES_COMMAND_3:
-		return;
-	}
-}
-
-
-
-static void hold_save_command(dword Id, PLCI *plci, byte Rc)
-{
-	byte SS_Ind[] = "\x05\x02\x00\x02\x00\x00"; /* Hold_Ind struct*/
-	word Info;
-	word internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: hold_save_command %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	Info = GOOD;
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		if (!plci->NL.Id)
-			break;
-		plci->command = 0;
-		plci->adjust_b_parms_msg = NULL;
-		plci->adjust_b_facilities = plci->B1_facilities;
-		plci->adjust_b_command = HOLD_SAVE_COMMAND_1;
-		plci->adjust_b_ncci = (word)(Id >> 16);
-		plci->adjust_b_mode = ADJUST_B_MODE_SAVE | ADJUST_B_MODE_REMOVE_L23;
-		plci->adjust_b_state = ADJUST_B_START;
-		dbug(1, dprintf("[%06lx] %s,%d: HOLD save...",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		/* fall through */
-	case HOLD_SAVE_COMMAND_1:
-		Info = adjust_b_process(Id, plci, Rc);
-		if (Info != GOOD)
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: HOLD save failed",
-					UnMapId(Id), (char *)(FILE_), __LINE__));
-			break;
-		}
-		if (plci->internal_command)
-			return;
-	}
-	sendf(plci->appl, _FACILITY_I, Id & 0xffffL, 0, "ws", 3, SS_Ind);
-}
-
-
-static void retrieve_restore_command(dword Id, PLCI *plci, byte Rc)
-{
-	byte SS_Ind[] = "\x05\x03\x00\x02\x00\x00"; /* Retrieve_Ind struct*/
-	word Info;
-	word internal_command;
-
-	dbug(1, dprintf("[%06lx] %s,%d: retrieve_restore_command %02x %04x",
-			UnMapId(Id), (char *)(FILE_), __LINE__, Rc, plci->internal_command));
-
-	Info = GOOD;
-	internal_command = plci->internal_command;
-	plci->internal_command = 0;
-	switch (internal_command)
-	{
-	default:
-		plci->command = 0;
-		plci->adjust_b_parms_msg = NULL;
-		plci->adjust_b_facilities = plci->B1_facilities;
-		plci->adjust_b_command = RETRIEVE_RESTORE_COMMAND_1;
-		plci->adjust_b_ncci = (word)(Id >> 16);
-		plci->adjust_b_mode = ADJUST_B_MODE_ASSIGN_L23 | ADJUST_B_MODE_USER_CONNECT | ADJUST_B_MODE_RESTORE;
-		plci->adjust_b_state = ADJUST_B_START;
-		dbug(1, dprintf("[%06lx] %s,%d: RETRIEVE restore...",
-				UnMapId(Id), (char *)(FILE_), __LINE__));
-		/* fall through */
-	case RETRIEVE_RESTORE_COMMAND_1:
-		Info = adjust_b_process(Id, plci, Rc);
-		if (Info != GOOD)
-		{
-			dbug(1, dprintf("[%06lx] %s,%d: RETRIEVE restore failed",
-					UnMapId(Id), (char *)(FILE_), __LINE__));
-			break;
-		}
-		if (plci->internal_command)
-			return;
-	}
-	sendf(plci->appl, _FACILITY_I, Id & 0xffffL, 0, "ws", 3, SS_Ind);
-}
-
-
-static void init_b1_config(PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: init_b1_config",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	plci->B1_resource = 0;
-	plci->B1_facilities = 0;
-
-	plci->li_bchannel_id = 0;
-	mixer_clear_config(plci);
-
-
-	ec_clear_config(plci);
-
-
-	dtmf_rec_clear_config(plci);
-	dtmf_send_clear_config(plci);
-	dtmf_parameter_clear_config(plci);
-
-	adv_voice_clear_config(plci);
-	adjust_b_clear(plci);
-}
-
-
-static void clear_b1_config(PLCI *plci)
-{
-
-	dbug(1, dprintf("[%06lx] %s,%d: clear_b1_config",
-			(dword)((plci->Id << 8) | UnMapController(plci->adapter->Id)),
-			(char *)(FILE_), __LINE__));
-
-	adv_voice_clear_config(plci);
-	adjust_b_clear(plci);
-
-	ec_clear_config(plci);
-
-
-	dtmf_rec_clear_config(plci);
-	dtmf_send_clear_config(plci);
-	dtmf_parameter_clear_config(plci);
-
-
-	if ((plci->li_bchannel_id != 0)
-	    && (li_config_table[plci->adapter->li_base + (plci->li_bchannel_id - 1)].plci == plci))
-	{
-		mixer_clear_config(plci);
-		li_config_table[plci->adapter->li_base + (plci->li_bchannel_id - 1)].plci = NULL;
-		plci->li_bchannel_id = 0;
-	}
-
-	plci->B1_resource = 0;
-	plci->B1_facilities = 0;
-}
-
-
-/* -----------------------------------------------------------------
-   XON protocol local helpers
-   ----------------------------------------------------------------- */
-static void channel_flow_control_remove(PLCI *plci) {
-	DIVA_CAPI_ADAPTER *a = plci->adapter;
-	word i;
-	for (i = 1; i < MAX_NL_CHANNEL + 1; i++) {
-		if (a->ch_flow_plci[i] == plci->Id) {
-			a->ch_flow_plci[i] = 0;
-			a->ch_flow_control[i] = 0;
-		}
-	}
-}
-
-static void channel_x_on(PLCI *plci, byte ch) {
-	DIVA_CAPI_ADAPTER *a = plci->adapter;
-	if (a->ch_flow_control[ch] & N_XON_SENT) {
-		a->ch_flow_control[ch] &= ~N_XON_SENT;
-	}
-}
-
-static void channel_x_off(PLCI *plci, byte ch, byte flag) {
-	DIVA_CAPI_ADAPTER *a = plci->adapter;
-	if ((a->ch_flow_control[ch] & N_RX_FLOW_CONTROL_MASK) == 0) {
-		a->ch_flow_control[ch] |= (N_CH_XOFF | flag);
-		a->ch_flow_plci[ch] = plci->Id;
-		a->ch_flow_control_pending++;
-	}
-}
-
-static void channel_request_xon(PLCI *plci, byte ch) {
-	DIVA_CAPI_ADAPTER *a = plci->adapter;
-
-	if (a->ch_flow_control[ch] & N_CH_XOFF) {
-		a->ch_flow_control[ch] |= N_XON_REQ;
-		a->ch_flow_control[ch] &= ~N_CH_XOFF;
-		a->ch_flow_control[ch] &= ~N_XON_CONNECT_IND;
-	}
-}
-
-static void channel_xmit_extended_xon(PLCI *plci) {
-	DIVA_CAPI_ADAPTER *a;
-	int max_ch = ARRAY_SIZE(a->ch_flow_control);
-	int i, one_requested = 0;
-
-	if ((!plci) || (!plci->Id) || ((a = plci->adapter) == NULL)) {
-		return;
-	}
-
-	for (i = 0; i < max_ch; i++) {
-		if ((a->ch_flow_control[i] & N_CH_XOFF) &&
-		    (a->ch_flow_control[i] & N_XON_CONNECT_IND) &&
-		    (plci->Id == a->ch_flow_plci[i])) {
-			channel_request_xon(plci, (byte)i);
-			one_requested = 1;
-		}
-	}
-
-	if (one_requested) {
-		channel_xmit_xon(plci);
-	}
-}
-
-/*
-  Try to xmit next X_ON
-*/
-static int find_channel_with_pending_x_on(DIVA_CAPI_ADAPTER *a, PLCI *plci) {
-	int max_ch = ARRAY_SIZE(a->ch_flow_control);
-	int i;
-
-	if (!(plci->adapter->manufacturer_features & MANUFACTURER_FEATURE_XONOFF_FLOW_CONTROL)) {
-		return (0);
-	}
-
-	if (a->last_flow_control_ch >= max_ch) {
-		a->last_flow_control_ch = 1;
-	}
-	for (i = a->last_flow_control_ch; i < max_ch; i++) {
-		if ((a->ch_flow_control[i] & N_XON_REQ) &&
-		    (plci->Id == a->ch_flow_plci[i])) {
-			a->last_flow_control_ch = i + 1;
-			return (i);
-		}
-	}
-
-	for (i = 1; i < a->last_flow_control_ch; i++) {
-		if ((a->ch_flow_control[i] & N_XON_REQ) &&
-		    (plci->Id == a->ch_flow_plci[i])) {
-			a->last_flow_control_ch = i + 1;
-			return (i);
-		}
-	}
-
-	return (0);
-}
-
-static void channel_xmit_xon(PLCI *plci) {
-	DIVA_CAPI_ADAPTER *a = plci->adapter;
-	byte ch;
-
-	if (plci->nl_req || !plci->NL.Id || plci->nl_remove_id) {
-		return;
-	}
-	if ((ch = (byte)find_channel_with_pending_x_on(a, plci)) == 0) {
-		return;
-	}
-	a->ch_flow_control[ch] &= ~N_XON_REQ;
-	a->ch_flow_control[ch] |= N_XON_SENT;
-
-	plci->NL.Req = plci->nl_req = (byte)N_XON;
-	plci->NL.ReqCh         = ch;
-	plci->NL.X             = plci->NData;
-	plci->NL.XNum          = 1;
-	plci->NData[0].P       = &plci->RBuffer[0];
-	plci->NData[0].PLength = 0;
-
-	plci->adapter->request(&plci->NL);
-}
-
-static int channel_can_xon(PLCI *plci, byte ch) {
-	APPL *APPLptr;
-	DIVA_CAPI_ADAPTER *a;
-	word NCCIcode;
-	dword count;
-	word Num;
-	word i;
-
-	APPLptr = plci->appl;
-	a = plci->adapter;
-
-	if (!APPLptr)
-		return (0);
-
-	NCCIcode = a->ch_ncci[ch] | (((word) a->Id) << 8);
-
-	/* count all buffers within the Application pool    */
-	/* belonging to the same NCCI. XON if a first is    */
-	/* used.                                            */
-	count = 0;
-	Num = 0xffff;
-	for (i = 0; i < APPLptr->MaxBuffer; i++) {
-		if (NCCIcode == APPLptr->DataNCCI[i]) count++;
-		if (!APPLptr->DataNCCI[i] && Num == 0xffff) Num = i;
-	}
-	if ((count > 2) || (Num == 0xffff)) {
-		return (0);
-	}
-	return (1);
-}
-
-
-/*------------------------------------------------------------------*/
-
-static word CPN_filter_ok(byte *cpn, DIVA_CAPI_ADAPTER *a, word offset)
-{
-	return 1;
-}
-
-
-
-/**********************************************************************************/
-/* function groups the listening applications according to the CIP mask and the   */
-/* Info_Mask. Each group gets just one Connect_Ind. Some application manufacturer */
-/* are not multi-instance capable, so they start e.g. 30 applications what causes */
-/* big problems on application level (one call, 30 Connect_Ind, ect). The         */
-/* function must be enabled by setting "a->group_optimization_enabled" from the   */
-/* OS specific part (per adapter).                                                */
-/**********************************************************************************/
-static void group_optimization(DIVA_CAPI_ADAPTER *a, PLCI *plci)
-{
-	word i, j, k, busy, group_found;
-	dword info_mask_group[MAX_CIP_TYPES];
-	dword cip_mask_group[MAX_CIP_TYPES];
-	word appl_number_group_type[MAX_APPL];
-	PLCI *auxplci;
-
-	/* all APPLs within this inc. call are allowed to dial in */
-	bitmap_fill(plci->group_optimization_mask_table, MAX_APPL);
-
-	if (!a->group_optimization_enabled)
-	{
-		dbug(1, dprintf("No group optimization"));
-		return;
-	}
-
-	dbug(1, dprintf("Group optimization = 0x%x...", a->group_optimization_enabled));
-
-	for (i = 0; i < MAX_CIP_TYPES; i++)
-	{
-		info_mask_group[i] = 0;
-		cip_mask_group[i] = 0;
-	}
-	for (i = 0; i < MAX_APPL; i++)
-	{
-		appl_number_group_type[i] = 0;
-	}
-	for (i = 0; i < max_appl; i++) /* check if any multi instance capable application is present */
-	{  /* group_optimization set to 1 means not to optimize multi-instance capable applications (default) */
-		if (application[i].Id && (application[i].MaxNCCI) > 1 && (a->CIP_Mask[i]) && (a->group_optimization_enabled == 1))
-		{
-			dbug(1, dprintf("Multi-Instance capable, no optimization required"));
-			return; /* allow good application unfiltered access */
-		}
-	}
-	for (i = 0; i < max_appl; i++) /* Build CIP Groups */
-	{
-		if (application[i].Id && a->CIP_Mask[i])
-		{
-			for (k = 0, busy = false; k < a->max_plci; k++)
-			{
-				if (a->plci[k].Id)
-				{
-					auxplci = &a->plci[k];
-					if (auxplci->appl == &application[i]) {
-						/* application has a busy PLCI */
-						busy = true;
-						dbug(1, dprintf("Appl 0x%x is busy", i + 1));
-					} else if (test_bit(i, plci->c_ind_mask_table)) {
-						/* application has an incoming call pending */
-						busy = true;
-						dbug(1, dprintf("Appl 0x%x has inc. call pending", i + 1));
-					}
-				}
-			}
-
-			for (j = 0, group_found = 0; j <= (MAX_CIP_TYPES) && !busy && !group_found; j++)     /* build groups with free applications only */
-			{
-				if (j == MAX_CIP_TYPES)       /* all groups are in use but group still not found */
-				{                           /* the MAX_CIP_TYPES group enables all calls because of field overflow */
-					appl_number_group_type[i] = MAX_CIP_TYPES;
-					group_found = true;
-					dbug(1, dprintf("Field overflow appl 0x%x", i + 1));
-				}
-				else if ((info_mask_group[j] == a->CIP_Mask[i]) && (cip_mask_group[j] == a->Info_Mask[i]))
-				{                                      /* is group already present ?                  */
-					appl_number_group_type[i] = j | 0x80;  /* store the group number for each application */
-					group_found = true;
-					dbug(1, dprintf("Group 0x%x found with appl 0x%x, CIP=0x%lx", appl_number_group_type[i], i + 1, info_mask_group[j]));
-				}
-				else if (!info_mask_group[j])
-				{                                      /* establish a new group                       */
-					appl_number_group_type[i] = j | 0x80;  /* store the group number for each application */
-					info_mask_group[j] = a->CIP_Mask[i]; /* store the new CIP mask for the new group    */
-					cip_mask_group[j] = a->Info_Mask[i]; /* store the new Info_Mask for this new group  */
-					group_found = true;
-					dbug(1, dprintf("New Group 0x%x established with appl 0x%x, CIP=0x%lx", appl_number_group_type[i], i + 1, info_mask_group[j]));
-				}
-			}
-		}
-	}
-
-	for (i = 0; i < max_appl; i++) /* Build group_optimization_mask_table */
-	{
-		if (appl_number_group_type[i]) /* application is free, has listens and is member of a group */
-		{
-			if (appl_number_group_type[i] == MAX_CIP_TYPES)
-			{
-				dbug(1, dprintf("OverflowGroup 0x%x, valid appl = 0x%x, call enabled", appl_number_group_type[i], i + 1));
-			}
-			else
-			{
-				dbug(1, dprintf("Group 0x%x, valid appl = 0x%x", appl_number_group_type[i], i + 1));
-				for (j = i + 1; j < max_appl; j++)   /* search other group members and mark them as busy        */
-				{
-					if (appl_number_group_type[i] == appl_number_group_type[j])
-					{
-						dbug(1, dprintf("Appl 0x%x is member of group 0x%x, no call", j + 1, appl_number_group_type[j]));
-						/* disable call on other group members */
-						__clear_bit(j, plci->group_optimization_mask_table);
-						appl_number_group_type[j] = 0;       /* remove disabled group member from group list */
-					}
-				}
-			}
-		}
-		else                                                 /* application should not get a call */
-		{
-			__clear_bit(i, plci->group_optimization_mask_table);
-		}
-	}
-
-}
-
-
-
-/* OS notifies the driver about a application Capi_Register */
-word CapiRegister(word id)
-{
-	word i, j, appls_found;
-
-	PLCI *plci;
-	DIVA_CAPI_ADAPTER *a;
-
-	for (i = 0, appls_found = 0; i < max_appl; i++)
-	{
-		if (application[i].Id && (application[i].Id != id))
-		{
-			appls_found++;                       /* an application has been found */
-		}
-	}
-
-	if (appls_found) return true;
-	for (i = 0; i < max_adapter; i++)                   /* scan all adapters...    */
-	{
-		a = &adapter[i];
-		if (a->request)
-		{
-			if (a->flag_dynamic_l1_down)  /* remove adapter from L1 tristate (Huntgroup) */
-			{
-				if (!appls_found)           /* first application does a capi register   */
-				{
-					if ((j = get_plci(a)))                    /* activate L1 of all adapters */
-					{
-						plci = &a->plci[j - 1];
-						plci->command = 0;
-						add_p(plci, OAD, "\x01\xfd");
-						add_p(plci, CAI, "\x01\x80");
-						add_p(plci, UID, "\x06\x43\x61\x70\x69\x32\x30");
-						add_p(plci, SHIFT | 6, NULL);
-						add_p(plci, SIN, "\x02\x00\x00");
-						plci->internal_command = START_L1_SIG_ASSIGN_PEND;
-						sig_req(plci, ASSIGN, DSIG_ID);
-						add_p(plci, FTY, "\x02\xff\x07"); /* l1 start */
-						sig_req(plci, SIG_CTRL, 0);
-						send_req(plci);
-					}
-				}
-			}
-		}
-	}
-	return false;
-}
-
-/*------------------------------------------------------------------*/
-
-/* Functions for virtual Switching e.g. Transfer by join, Conference */
-
-static void VSwitchReqInd(PLCI *plci, dword Id, byte **parms)
-{
-	word i;
-	/* Format of vswitch_t:
-	   0 byte length
-	   1 byte VSWITCHIE
-	   2 byte VSWITCH_REQ/VSWITCH_IND
-	   3 byte reserved
-	   4 word VSwitchcommand
-	   6 word returnerror
-	   8... Params
-	*/
-	if (!plci ||
-	    !plci->appl ||
-	    !plci->State ||
-	    plci->Sig.Ind == NCR_FACILITY
-		)
-		return;
-
-	for (i = 0; i < MAX_MULTI_IE; i++)
-	{
-		if (!parms[i][0]) continue;
-		if (parms[i][0] < 7)
-		{
-			parms[i][0] = 0; /* kill it */
-			continue;
-		}
-		dbug(1, dprintf("VSwitchReqInd(%d)", parms[i][4]));
-		switch (parms[i][4])
-		{
-		case VSJOIN:
-			if (!plci->relatedPTYPLCI ||
-			    (plci->ptyState != S_ECT && plci->relatedPTYPLCI->ptyState != S_ECT))
-			{ /* Error */
-				break;
-			}
-			/* remember all necessary informations */
-			if (parms[i][0] != 11 || parms[i][8] != 3) /* Length Test */
-			{
-				break;
-			}
-			if (parms[i][2] == VSWITCH_IND && parms[i][9] == 1)
-			{   /* first indication after ECT-Request on Consultation Call */
-				plci->vswitchstate = parms[i][9];
-				parms[i][9] = 2; /* State */
-				/* now ask first Call to join */
-			}
-			else if (parms[i][2] == VSWITCH_REQ && parms[i][9] == 3)
-			{ /* Answer of VSWITCH_REQ from first Call */
-				plci->vswitchstate = parms[i][9];
-				/* tell consultation call to join
-				   and the protocol capabilities of the first call */
-			}
-			else
-			{ /* Error */
-				break;
-			}
-			plci->vsprot = parms[i][10]; /* protocol */
-			plci->vsprotdialect = parms[i][11]; /* protocoldialect */
-			/* send join request to related PLCI */
-			parms[i][1] = VSWITCHIE;
-			parms[i][2] = VSWITCH_REQ;
-
-			plci->relatedPTYPLCI->command = 0;
-			plci->relatedPTYPLCI->internal_command = VSWITCH_REQ_PEND;
-			add_p(plci->relatedPTYPLCI, ESC, &parms[i][0]);
-			sig_req(plci->relatedPTYPLCI, VSWITCH_REQ, 0);
-			send_req(plci->relatedPTYPLCI);
-			break;
-		case VSTRANSPORT:
-		default:
-			if (plci->relatedPTYPLCI &&
-			    plci->vswitchstate == 3 &&
-			    plci->relatedPTYPLCI->vswitchstate == 3)
-			{
-				add_p(plci->relatedPTYPLCI, ESC, &parms[i][0]);
-				sig_req(plci->relatedPTYPLCI, VSWITCH_REQ, 0);
-				send_req(plci->relatedPTYPLCI);
-			}
-			break;
-		}
-		parms[i][0] = 0; /* kill it */
-	}
-}
-
-
-/*------------------------------------------------------------------*/
-
-static int diva_get_dma_descriptor(PLCI *plci, dword   *dma_magic) {
-	ENTITY e;
-	IDI_SYNC_REQ *pReq = (IDI_SYNC_REQ *)&e;
-
-	if (!(diva_xdi_extended_features & DIVA_CAPI_XDI_PROVIDES_RX_DMA)) {
-		return (-1);
-	}
-
-	pReq->xdi_dma_descriptor_operation.Req = 0;
-	pReq->xdi_dma_descriptor_operation.Rc = IDI_SYNC_REQ_DMA_DESCRIPTOR_OPERATION;
-
-	pReq->xdi_dma_descriptor_operation.info.operation = IDI_SYNC_REQ_DMA_DESCRIPTOR_ALLOC;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_number  = -1;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_address = NULL;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_magic   = 0;
-
-	e.user[0] = plci->adapter->Id - 1;
-	plci->adapter->request((ENTITY *)pReq);
-
-	if (!pReq->xdi_dma_descriptor_operation.info.operation &&
-	    (pReq->xdi_dma_descriptor_operation.info.descriptor_number >= 0) &&
-	    pReq->xdi_dma_descriptor_operation.info.descriptor_magic) {
-		*dma_magic = pReq->xdi_dma_descriptor_operation.info.descriptor_magic;
-		dbug(3, dprintf("dma_alloc, a:%d (%d-%08x)",
-				plci->adapter->Id,
-				pReq->xdi_dma_descriptor_operation.info.descriptor_number,
-				*dma_magic));
-		return (pReq->xdi_dma_descriptor_operation.info.descriptor_number);
-	} else {
-		dbug(1, dprintf("dma_alloc failed"));
-		return (-1);
-	}
-}
-
-static void diva_free_dma_descriptor(PLCI *plci, int nr) {
-	ENTITY e;
-	IDI_SYNC_REQ *pReq = (IDI_SYNC_REQ *)&e;
-
-	if (nr < 0) {
-		return;
-	}
-
-	pReq->xdi_dma_descriptor_operation.Req = 0;
-	pReq->xdi_dma_descriptor_operation.Rc = IDI_SYNC_REQ_DMA_DESCRIPTOR_OPERATION;
-
-	pReq->xdi_dma_descriptor_operation.info.operation = IDI_SYNC_REQ_DMA_DESCRIPTOR_FREE;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_number  = nr;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_address = NULL;
-	pReq->xdi_dma_descriptor_operation.info.descriptor_magic   = 0;
-
-	e.user[0] = plci->adapter->Id - 1;
-	plci->adapter->request((ENTITY *)pReq);
-
-	if (!pReq->xdi_dma_descriptor_operation.info.operation) {
-		dbug(1, dprintf("dma_free(%d)", nr));
-	} else {
-		dbug(1, dprintf("dma_free failed (%d)", nr));
-	}
-}
-
-/*------------------------------------------------------------------*/
diff --git a/drivers/isdn/hardware/eicon/mi_pc.h b/drivers/isdn/hardware/eicon/mi_pc.h
deleted file mode 100644
index 83e9ed8c1bf3..000000000000
--- a/drivers/isdn/hardware/eicon/mi_pc.h
+++ /dev/null
@@ -1,204 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-/*----------------------------------------------------------------------------
-// MAESTRA ISA PnP */
-#define BRI_MEMORY_BASE                 0x1f700000
-#define BRI_MEMORY_SIZE                 0x00100000  /* 1MB on the BRI                         */
-#define BRI_SHARED_RAM_SIZE             0x00010000  /* 64k shared RAM                         */
-#define BRI_RAY_TAYLOR_DSP_CODE_SIZE    0x00020000  /* max 128k DSP-Code (Ray Taylor's code)  */
-#define BRI_ORG_MAX_DSP_CODE_SIZE       0x00050000  /* max 320k DSP-Code (Telindus)           */
-#define BRI_V90D_MAX_DSP_CODE_SIZE      0x00060000  /* max 384k DSP-Code if V.90D included    */
-#define BRI_CACHED_ADDR(x)              (((x) & 0x1fffffffL) | 0x80000000L)
-#define BRI_UNCACHED_ADDR(x)            (((x) & 0x1fffffffL) | 0xa0000000L)
-#define ADDR  4
-#define ADDRH 6
-#define DATA  0
-#define RESET 7
-#define DEFAULT_ADDRESS 0x240
-#define DEFAULT_IRQ     3
-#define M_PCI_ADDR   0x04  /* MAESTRA BRI PCI */
-#define M_PCI_ADDRH  0x0c  /* MAESTRA BRI PCI */
-#define M_PCI_DATA   0x00  /* MAESTRA BRI PCI */
-#define M_PCI_RESET  0x10  /* MAESTRA BRI PCI */
-/*----------------------------------------------------------------------------
-// MAESTRA PRI PCI */
-#define MP_IRQ_RESET                    0xc18       /* offset of isr in the CONFIG memory bar */
-#define MP_IRQ_RESET_VAL                0xfe        /* value to clear an interrupt            */
-#define MP_MEMORY_SIZE                  0x00400000  /* 4MB on standard PRI                    */
-#define MP2_MEMORY_SIZE                 0x00800000  /* 8MB on PRI Rev. 2                      */
-#define MP_SHARED_RAM_OFFSET            0x00001000  /* offset of shared RAM base in the DRAM memory bar */
-#define MP_SHARED_RAM_SIZE              0x00010000  /* 64k shared RAM                         */
-#define MP_PROTOCOL_OFFSET              (MP_SHARED_RAM_OFFSET + MP_SHARED_RAM_SIZE)
-#define MP_RAY_TAYLOR_DSP_CODE_SIZE     0x00040000  /* max 256k DSP-Code (Ray Taylor's code)  */
-#define MP_ORG_MAX_DSP_CODE_SIZE        0x00060000  /* max 384k DSP-Code (Telindus)           */
-#define MP_V90D_MAX_DSP_CODE_SIZE       0x00070000  /* max 448k DSP-Code if V.90D included)   */
-#define MP_VOIP_MAX_DSP_CODE_SIZE       0x00090000  /* max 576k DSP-Code if voice over IP included */
-#define MP_CACHED_ADDR(x)               (((x) & 0x1fffffffL) | 0x80000000L)
-#define MP_UNCACHED_ADDR(x)             (((x) & 0x1fffffffL) | 0xa0000000L)
-#define MP_RESET         0x20        /* offset of RESET register in the DEVICES memory bar */
-/* RESET register bits */
-#define _MP_S2M_RESET    0x10        /* active lo   */
-#define _MP_LED2         0x08        /* 1 = on      */
-#define _MP_LED1         0x04        /* 1 = on      */
-#define _MP_DSP_RESET    0x02        /* active lo   */
-#define _MP_RISC_RESET   0x81        /* active hi, bit 7 for compatibility with old boards */
-/* CPU exception context structure in MP shared ram after trap */
-typedef struct mp_xcptcontext_s MP_XCPTC;
-struct mp_xcptcontext_s {
-	dword       sr;
-	dword       cr;
-	dword       epc;
-	dword       vaddr;
-	dword       regs[32];
-	dword       mdlo;
-	dword       mdhi;
-	dword       reseverd;
-	dword       xclass;
-};
-/* boot interface structure for PRI */
-struct mp_load {
-	dword     volatile cmd;
-	dword     volatile addr;
-	dword     volatile len;
-	dword     volatile err;
-	dword     volatile live;
-	dword     volatile res1[0x1b];
-	dword     volatile TrapId;    /* has value 0x999999XX on a CPU trap */
-	dword     volatile res2[0x03];
-	MP_XCPTC  volatile xcpt;      /* contains register dump */
-	dword     volatile rest[((0x1020 >> 2) - 6) - 0x1b - 1 - 0x03 - (sizeof(MP_XCPTC) >> 2)];
-	dword     volatile signature;
-	dword data[60000]; /* real interface description */
-};
-/*----------------------------------------------------------------------------*/
-/* SERVER 4BRI (Quattro PCI)                                                  */
-#define MQ_BOARD_REG_OFFSET             0x800000    /* PC relative On board registers offset  */
-#define MQ_BREG_RISC                    0x1200      /* RISC Reset ect                         */
-#define MQ_RISC_COLD_RESET_MASK         0x0001      /* RISC Cold reset                        */
-#define MQ_RISC_WARM_RESET_MASK         0x0002      /* RISC Warm reset                        */
-#define MQ_BREG_IRQ_TEST                0x0608      /* Interrupt request, no CPU interaction  */
-#define MQ_IRQ_REQ_ON                   0x1
-#define MQ_IRQ_REQ_OFF                  0x0
-#define MQ_BOARD_DSP_OFFSET             0xa00000    /* PC relative On board DSP regs offset   */
-#define MQ_DSP1_ADDR_OFFSET             0x0008      /* Addr register offset DSP 1 subboard 1  */
-#define MQ_DSP2_ADDR_OFFSET             0x0208      /* Addr register offset DSP 2 subboard 1  */
-#define MQ_DSP1_DATA_OFFSET             0x0000      /* Data register offset DSP 1 subboard 1  */
-#define MQ_DSP2_DATA_OFFSET             0x0200      /* Data register offset DSP 2 subboard 1  */
-#define MQ_DSP_JUNK_OFFSET              0x0400      /* DSP Data/Addr regs subboard offset     */
-#define MQ_ISAC_DSP_RESET               0x0028      /* ISAC and DSP reset address offset      */
-#define MQ_BOARD_ISAC_DSP_RESET         0x800028    /* ISAC and DSP reset address offset      */
-#define MQ_INSTANCE_COUNT               4           /* 4BRI consists of four instances        */
-#define MQ_MEMORY_SIZE                  0x00400000  /* 4MB on standard 4BRI                   */
-#define MQ_CTRL_SIZE                    0x00002000  /* 8K memory mapped registers             */
-#define MQ_SHARED_RAM_SIZE              0x00010000  /* 64k shared RAM                         */
-#define MQ_ORG_MAX_DSP_CODE_SIZE        0x00050000  /* max 320k DSP-Code (Telindus) */
-#define MQ_V90D_MAX_DSP_CODE_SIZE       0x00060000  /* max 384K DSP-Code if V.90D included */
-#define MQ_VOIP_MAX_DSP_CODE_SIZE       0x00028000  /* max 4*160k = 640K DSP-Code if voice over IP included */
-#define MQ_CACHED_ADDR(x)               (((x) & 0x1fffffffL) | 0x80000000L)
-#define MQ_UNCACHED_ADDR(x)             (((x) & 0x1fffffffL) | 0xa0000000L)
-/*--------------------------------------------------------------------------------------------*/
-/* Additional definitions reflecting the different address map of the  SERVER 4BRI V2          */
-#define MQ2_BREG_RISC                   0x0200      /* RISC Reset ect                         */
-#define MQ2_BREG_IRQ_TEST               0x0400      /* Interrupt request, no CPU interaction  */
-#define MQ2_BOARD_DSP_OFFSET            0x800000    /* PC relative On board DSP regs offset   */
-#define MQ2_DSP1_DATA_OFFSET            0x1800      /* Data register offset DSP 1 subboard 1  */
-#define MQ2_DSP1_ADDR_OFFSET            0x1808      /* Addr register offset DSP 1 subboard 1  */
-#define MQ2_DSP2_DATA_OFFSET            0x1810      /* Data register offset DSP 2 subboard 1  */
-#define MQ2_DSP2_ADDR_OFFSET            0x1818      /* Addr register offset DSP 2 subboard 1  */
-#define MQ2_DSP_JUNK_OFFSET             0x1000      /* DSP Data/Addr regs subboard offset     */
-#define MQ2_ISAC_DSP_RESET              0x0000      /* ISAC and DSP reset address offset      */
-#define MQ2_BOARD_ISAC_DSP_RESET        0x800000    /* ISAC and DSP reset address offset      */
-#define MQ2_IPACX_CONFIG                0x0300      /* IPACX Configuration TE(0)/NT(1)        */
-#define MQ2_BOARD_IPACX_CONFIG          0x800300    /*     ""                                 */
-#define MQ2_MEMORY_SIZE                 0x01000000  /* 16MB code/data memory                  */
-#define MQ2_CTRL_SIZE                   0x00008000  /* 32K memory mapped registers            */
-/*----------------------------------------------------------------------------*/
-/* SERVER BRI 2M/2F as derived from 4BRI V2                                   */
-#define BRI2_MEMORY_SIZE                0x00800000  /* 8MB code/data memory                   */
-#define BRI2_PROTOCOL_MEMORY_SIZE       (MQ2_MEMORY_SIZE >> 2) /*  same as one 4BRI Rev.2 task */
-#define BRI2_CTRL_SIZE                  0x00008000  /* 32K memory mapped registers            */
-#define M_INSTANCE_COUNT                1           /*  BRI consists of one instance          */
-/*
- * Some useful constants for proper initialization of the GT6401x
- */
-#define ID_REG        0x0000      /*Pci reg-contain the Dev&Ven ID of the card*/
-#define RAS0_BASEREG  0x0010      /*Ras0 register - contain the base addr Ras0*/
-#define RAS2_BASEREG  0x0014
-#define CS_BASEREG    0x0018
-#define BOOT_BASEREG  0x001c
-#define GTREGS_BASEREG 0x0024   /*GTRegsBase reg-contain the base addr where*/
-				/*the GT64010 internal regs where mapped    */
-/*
- *  GT64010 internal registers
- */
-/* DRAM device coding  */
-#define LOW_RAS0_DREG 0x0400    /*Ras0 low decode address*/
-#define HI_RAS0_DREG  0x0404    /*Ras0 high decode address*/
-#define LOW_RAS1_DREG 0x0408    /*Ras1 low decode address*/
-#define HI_RAS1_DREG  0x040c    /*Ras1 high decode address*/
-#define LOW_RAS2_DREG 0x0410    /*Ras2 low decode address*/
-#define HI_RAS2_DREG  0x0414    /*Ras2 high decode address*/
-#define LOW_RAS3_DREG 0x0418    /*Ras3 low decode address*/
-#define HI_RAS3_DREG  0x041c    /*Ras3 high decode address*/
-/* I/O CS device coding  */
-#define LOW_CS0_DREG  0x0420 /* CS0* low decode register */
-#define HI_CS0_DREG   0x0424 /* CS0* high decode register */
-#define LOW_CS1_DREG  0x0428 /* CS1* low decode register */
-#define HI_CS1_DREG   0x042c /* CS1* high decode register */
-#define LOW_CS2_DREG  0x0430 /* CS2* low decode register */
-#define HI_CS2_DREG   0x0434 /* CS2* high decode register */
-#define LOW_CS3_DREG  0x0438 /* CS3* low decode register */
-#define HI_CS3_DREG   0x043c /* CS3* high decode register */
-/* Boot PROM device coding */
-#define LOW_BOOTCS_DREG 0x0440 /* Boot CS low decode register */
-#define HI_BOOTCS_DREG 0x0444 /* Boot CS High decode register */
-/* DRAM group coding (for CPU)  */
-#define LO_RAS10_GREG 0x0008    /*Ras1..0 group low decode address*/
-#define HI_RAS10_GREG 0x0010    /*Ras1..0 group high decode address*/
-#define LO_RAS32_GREG 0x0018    /*Ras3..2 group low decode address  */
-#define HI_RAS32_GREG 0x0020    /*Ras3..2 group high decode address  */
-/* I/O CS group coding for (CPU)  */
-#define LO_CS20_GREG  0x0028 /* CS2..0 group low decode register */
-#define HI_CS20_GREG  0x0030 /* CS2..0 group high decode register */
-#define LO_CS3B_GREG  0x0038 /* CS3 & PROM group low decode register */
-#define HI_CS3B_GREG  0x0040 /* CS3 & PROM group high decode register */
-/* Galileo specific PCI config. */
-#define PCI_TIMEOUT_RET 0x0c04 /* Time Out and retry register */
-#define RAS10_BANKSIZE 0x0c08 /* RAS 1..0 group PCI bank size */
-#define RAS32_BANKSIZE 0x0c0c /* RAS 3..2 group PCI bank size */
-#define CS20_BANKSIZE 0x0c10 /* CS 2..0 group PCI bank size */
-#define CS3B_BANKSIZE 0x0c14 /* CS 3 & Boot group PCI bank size */
-#define DRAM_SIZE     0x0001      /*Dram size in mega bytes*/
-#define PROM_SIZE     0x08000     /*Prom size in bytes*/
-/*--------------------------------------------------------------------------*/
-#define OFFS_DIVA_INIT_TASK_COUNT 0x68
-#define OFFS_DSP_CODE_BASE_ADDR   0x6c
-#define OFFS_XLOG_BUF_ADDR        0x70
-#define OFFS_XLOG_COUNT_ADDR      0x74
-#define OFFS_XLOG_OUT_ADDR        0x78
-#define OFFS_PROTOCOL_END_ADDR    0x7c
-#define OFFS_PROTOCOL_ID_STRING   0x80
-/*--------------------------------------------------------------------------*/
diff --git a/drivers/isdn/hardware/eicon/mntfunc.c b/drivers/isdn/hardware/eicon/mntfunc.c
deleted file mode 100644
index 1cd9affb6058..000000000000
--- a/drivers/isdn/hardware/eicon/mntfunc.c
+++ /dev/null
@@ -1,370 +0,0 @@
-/* $Id: mntfunc.c,v 1.19.6.4 2005/01/31 12:22:20 armin Exp $
- *
- * Driver for Eicon DIVA Server ISDN cards.
- * Maint module
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-
-#include "platform.h"
-#include "di_defs.h"
-#include "divasync.h"
-#include "debug_if.h"
-
-extern char *DRIVERRELEASE_MNT;
-
-#define DBG_MINIMUM  (DL_LOG + DL_FTL + DL_ERR)
-#define DBG_DEFAULT  (DBG_MINIMUM + DL_XLOG + DL_REG)
-
-extern void DIVA_DIDD_Read(void *, int);
-
-static dword notify_handle;
-static DESCRIPTOR DAdapter;
-static DESCRIPTOR MAdapter;
-static DESCRIPTOR MaintDescriptor =
-{ IDI_DIMAINT, 0, 0, (IDI_CALL) diva_maint_prtComp };
-
-extern int diva_os_copy_to_user(void *os_handle, void __user *dst,
-				const void *src, int length);
-extern int diva_os_copy_from_user(void *os_handle, void *dst,
-				  const void __user *src, int length);
-
-static void no_printf(unsigned char *x, ...)
-{
-	/* dummy debug function */
-}
-
-#include "debuglib.c"
-
-/*
- *  DIDD callback function
- */
-static void *didd_callback(void *context, DESCRIPTOR *adapter,
-			   int removal)
-{
-	if (adapter->type == IDI_DADAPTER) {
-		DBG_ERR(("cb: Change in DAdapter ? Oops ?."));
-	} else if (adapter->type == IDI_DIMAINT) {
-		if (removal) {
-			DbgDeregister();
-			memset(&MAdapter, 0, sizeof(MAdapter));
-			dprintf = no_printf;
-		} else {
-			memcpy(&MAdapter, adapter, sizeof(MAdapter));
-			dprintf = (DIVA_DI_PRINTF) MAdapter.request;
-			DbgRegister("MAINT", DRIVERRELEASE_MNT, DBG_DEFAULT);
-		}
-	} else if ((adapter->type > 0) && (adapter->type < 16)) {
-		if (removal) {
-			diva_mnt_remove_xdi_adapter(adapter);
-		} else {
-			diva_mnt_add_xdi_adapter(adapter);
-		}
-	}
-	return (NULL);
-}
-
-/*
- * connect to didd
- */
-static int __init connect_didd(void)
-{
-	int x = 0;
-	int dadapter = 0;
-	IDI_SYNC_REQ req;
-	DESCRIPTOR DIDD_Table[MAX_DESCRIPTORS];
-
-	DIVA_DIDD_Read(DIDD_Table, sizeof(DIDD_Table));
-
-	for (x = 0; x < MAX_DESCRIPTORS; x++) {
-		if (DIDD_Table[x].type == IDI_DADAPTER) {	/* DADAPTER found */
-			dadapter = 1;
-			memcpy(&DAdapter, &DIDD_Table[x], sizeof(DAdapter));
-			req.didd_notify.e.Req = 0;
-			req.didd_notify.e.Rc =
-				IDI_SYNC_REQ_DIDD_REGISTER_ADAPTER_NOTIFY;
-			req.didd_notify.info.callback = (void *)didd_callback;
-			req.didd_notify.info.context = NULL;
-			DAdapter.request((ENTITY *)&req);
-			if (req.didd_notify.e.Rc != 0xff)
-				return (0);
-			notify_handle = req.didd_notify.info.handle;
-			/* Register MAINT (me) */
-			req.didd_add_adapter.e.Req = 0;
-			req.didd_add_adapter.e.Rc =
-				IDI_SYNC_REQ_DIDD_ADD_ADAPTER;
-			req.didd_add_adapter.info.descriptor =
-				(void *) &MaintDescriptor;
-			DAdapter.request((ENTITY *)&req);
-			if (req.didd_add_adapter.e.Rc != 0xff)
-				return (0);
-		} else if ((DIDD_Table[x].type > 0)
-			   && (DIDD_Table[x].type < 16)) {
-			diva_mnt_add_xdi_adapter(&DIDD_Table[x]);
-		}
-	}
-	return (dadapter);
-}
-
-/*
- * disconnect from didd
- */
-static void __exit disconnect_didd(void)
-{
-	IDI_SYNC_REQ req;
-
-	req.didd_notify.e.Req = 0;
-	req.didd_notify.e.Rc = IDI_SYNC_REQ_DIDD_REMOVE_ADAPTER_NOTIFY;
-	req.didd_notify.info.handle = notify_handle;
-	DAdapter.request((ENTITY *)&req);
-
-	req.didd_remove_adapter.e.Req = 0;
-	req.didd_remove_adapter.e.Rc = IDI_SYNC_REQ_DIDD_REMOVE_ADAPTER;
-	req.didd_remove_adapter.info.p_request =
-		(IDI_CALL) MaintDescriptor.request;
-	DAdapter.request((ENTITY *)&req);
-}
-
-/*
- * read/write maint
- */
-int maint_read_write(void __user *buf, int count)
-{
-	byte data[128];
-	dword cmd, id, mask;
-	int ret = 0;
-
-	if (count < (3 * sizeof(dword)))
-		return (-EFAULT);
-
-	if (diva_os_copy_from_user(NULL, (void *) &data[0],
-				   buf, 3 * sizeof(dword))) {
-		return (-EFAULT);
-	}
-
-	cmd = *(dword *)&data[0];	/* command */
-	id = *(dword *)&data[4];	/* driver id */
-	mask = *(dword *)&data[8];	/* mask or size */
-
-	switch (cmd) {
-	case DITRACE_CMD_GET_DRIVER_INFO:
-		if ((ret = diva_get_driver_info(id, data, sizeof(data))) > 0) {
-			if ((count < ret) || diva_os_copy_to_user
-			    (NULL, buf, (void *) &data[0], ret))
-				ret = -EFAULT;
-		} else {
-			ret = -EINVAL;
-		}
-		break;
-
-	case DITRACE_READ_DRIVER_DBG_MASK:
-		if ((ret = diva_get_driver_dbg_mask(id, (byte *) data)) > 0) {
-			if ((count < ret) || diva_os_copy_to_user
-			    (NULL, buf, (void *) &data[0], ret))
-				ret = -EFAULT;
-		} else {
-			ret = -ENODEV;
-		}
-		break;
-
-	case DITRACE_WRITE_DRIVER_DBG_MASK:
-		if ((ret = diva_set_driver_dbg_mask(id, mask)) <= 0) {
-			ret = -ENODEV;
-		}
-		break;
-
-		/*
-		  Filter commands will ignore the ID due to fact that filtering affects
-		  the B- channel and Audio Tap trace levels only. Also MAINT driver will
-		  select the right trace ID by itself
-		*/
-	case DITRACE_WRITE_SELECTIVE_TRACE_FILTER:
-		if (!mask) {
-			ret = diva_set_trace_filter(1, "*");
-		} else if (mask < sizeof(data)) {
-			if (diva_os_copy_from_user(NULL, data, (char __user *)buf + 12, mask)) {
-				ret = -EFAULT;
-			} else {
-				ret = diva_set_trace_filter((int)mask, data);
-			}
-		} else {
-			ret = -EINVAL;
-		}
-		break;
-
-	case DITRACE_READ_SELECTIVE_TRACE_FILTER:
-		if ((ret = diva_get_trace_filter(sizeof(data), data)) > 0) {
-			if (diva_os_copy_to_user(NULL, buf, data, ret))
-				ret = -EFAULT;
-		} else {
-			ret = -ENODEV;
-		}
-		break;
-
-	case DITRACE_READ_TRACE_ENTRY:{
-		diva_os_spin_lock_magic_t old_irql;
-		word size;
-		diva_dbg_entry_head_t *pmsg;
-		byte *pbuf;
-
-		if (!(pbuf = diva_os_malloc(0, mask))) {
-			return (-ENOMEM);
-		}
-
-		for (;;) {
-			if (!(pmsg =
-			      diva_maint_get_message(&size, &old_irql))) {
-				break;
-			}
-			if (size > mask) {
-				diva_maint_ack_message(0, &old_irql);
-				ret = -EINVAL;
-				break;
-			}
-			ret = size;
-			memcpy(pbuf, pmsg, size);
-			diva_maint_ack_message(1, &old_irql);
-			if ((count < size) ||
-			    diva_os_copy_to_user(NULL, buf, (void *) pbuf, size))
-				ret = -EFAULT;
-			break;
-		}
-		diva_os_free(0, pbuf);
-	}
-		break;
-
-	case DITRACE_READ_TRACE_ENTRYS:{
-		diva_os_spin_lock_magic_t old_irql;
-		word size;
-		diva_dbg_entry_head_t *pmsg;
-		byte *pbuf = NULL;
-		int written = 0;
-
-		if (mask < 4096) {
-			ret = -EINVAL;
-			break;
-		}
-		if (!(pbuf = diva_os_malloc(0, mask))) {
-			return (-ENOMEM);
-		}
-
-		for (;;) {
-			if (!(pmsg =
-			      diva_maint_get_message(&size, &old_irql))) {
-				break;
-			}
-			if ((size + 8) > mask) {
-				diva_maint_ack_message(0, &old_irql);
-				break;
-			}
-			/*
-			  Write entry length
-			*/
-			pbuf[written++] = (byte) size;
-			pbuf[written++] = (byte) (size >> 8);
-			pbuf[written++] = 0;
-			pbuf[written++] = 0;
-			/*
-			  Write message
-			*/
-			memcpy(&pbuf[written], pmsg, size);
-			diva_maint_ack_message(1, &old_irql);
-			written += size;
-			mask -= (size + 4);
-		}
-		pbuf[written++] = 0;
-		pbuf[written++] = 0;
-		pbuf[written++] = 0;
-		pbuf[written++] = 0;
-
-		if ((count < written) || diva_os_copy_to_user(NULL, buf, (void *) pbuf, written)) {
-			ret = -EFAULT;
-		} else {
-			ret = written;
-		}
-		diva_os_free(0, pbuf);
-	}
-		break;
-
-	default:
-		ret = -EINVAL;
-	}
-	return (ret);
-}
-
-/*
- *  init
- */
-int __init mntfunc_init(int *buffer_length, void **buffer,
-				    unsigned long diva_dbg_mem)
-{
-	if (*buffer_length < 64) {
-		*buffer_length = 64;
-	}
-	if (*buffer_length > 512) {
-		*buffer_length = 512;
-	}
-	*buffer_length *= 1024;
-
-	if (diva_dbg_mem) {
-		*buffer = (void *) diva_dbg_mem;
-	} else {
-		while ((*buffer_length >= (64 * 1024))
-		       &&
-		       (!(*buffer = diva_os_malloc(0, *buffer_length)))) {
-			*buffer_length -= 1024;
-		}
-
-		if (!*buffer) {
-			DBG_ERR(("init: Can not alloc trace buffer"));
-			return (0);
-		}
-	}
-
-	if (diva_maint_init(*buffer, *buffer_length, (diva_dbg_mem == 0))) {
-		if (!diva_dbg_mem) {
-			diva_os_free(0, *buffer);
-		}
-		DBG_ERR(("init: maint init failed"));
-		return (0);
-	}
-
-	if (!connect_didd()) {
-		DBG_ERR(("init: failed to connect to DIDD."));
-		diva_maint_finit();
-		if (!diva_dbg_mem) {
-			diva_os_free(0, *buffer);
-		}
-		return (0);
-	}
-	return (1);
-}
-
-/*
- *  exit
- */
-void __exit mntfunc_finit(void)
-{
-	void *buffer;
-	int i = 100;
-
-	DbgDeregister();
-
-	while (diva_mnt_shutdown_xdi_adapters() && i--) {
-		diva_os_sleep(10);
-	}
-
-	disconnect_didd();
-
-	if ((buffer = diva_maint_finit())) {
-		diva_os_free(0, buffer);
-	}
-
-	memset(&MAdapter, 0, sizeof(MAdapter));
-	dprintf = no_printf;
-}
diff --git a/drivers/isdn/hardware/eicon/os_4bri.c b/drivers/isdn/hardware/eicon/os_4bri.c
deleted file mode 100644
index 87db5f4df27d..000000000000
--- a/drivers/isdn/hardware/eicon/os_4bri.c
+++ /dev/null
@@ -1,1132 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* $Id: os_4bri.c,v 1.28.4.4 2005/02/11 19:40:25 armin Exp $ */
-
-#include "platform.h"
-#include "debuglib.h"
-#include "cardtype.h"
-#include "pc.h"
-#include "pr_pc.h"
-#include "di_defs.h"
-#include "dsp_defs.h"
-#include "di.h"
-#include "io.h"
-
-#include "xdi_msg.h"
-#include "xdi_adapter.h"
-#include "os_4bri.h"
-#include "diva_pci.h"
-#include "mi_pc.h"
-#include "dsrv4bri.h"
-#include "helpers.h"
-
-static void *diva_xdiLoadFileFile = NULL;
-static dword diva_xdiLoadFileLength = 0;
-
-/*
-**  IMPORTS
-*/
-extern void prepare_qBri_functions(PISDN_ADAPTER IoAdapter);
-extern void prepare_qBri2_functions(PISDN_ADAPTER IoAdapter);
-extern void diva_xdi_display_adapter_features(int card);
-extern void diva_add_slave_adapter(diva_os_xdi_adapter_t *a);
-
-extern int qBri_FPGA_download(PISDN_ADAPTER IoAdapter);
-extern void start_qBri_hardware(PISDN_ADAPTER IoAdapter);
-
-extern int diva_card_read_xlog(diva_os_xdi_adapter_t *a);
-
-/*
-**  LOCALS
-*/
-static unsigned long _4bri_bar_length[4] = {
-	0x100,
-	0x100,			/* I/O */
-	MQ_MEMORY_SIZE,
-	0x2000
-};
-static unsigned long _4bri_v2_bar_length[4] = {
-	0x100,
-	0x100,			/* I/O */
-	MQ2_MEMORY_SIZE,
-	0x10000
-};
-static unsigned long _4bri_v2_bri_bar_length[4] = {
-	0x100,
-	0x100,			/* I/O */
-	BRI2_MEMORY_SIZE,
-	0x10000
-};
-
-
-static int diva_4bri_cleanup_adapter(diva_os_xdi_adapter_t *a);
-static int _4bri_get_serial_number(diva_os_xdi_adapter_t *a);
-static int diva_4bri_cmd_card_proc(struct _diva_os_xdi_adapter *a,
-				   diva_xdi_um_cfg_cmd_t *cmd,
-				   int length);
-static int diva_4bri_cleanup_slave_adapters(diva_os_xdi_adapter_t *a);
-static int diva_4bri_write_fpga_image(diva_os_xdi_adapter_t *a,
-				      byte *data, dword length);
-static int diva_4bri_reset_adapter(PISDN_ADAPTER IoAdapter);
-static int diva_4bri_write_sdram_block(PISDN_ADAPTER IoAdapter,
-				       dword address,
-				       const byte *data,
-				       dword length, dword limit);
-static int diva_4bri_start_adapter(PISDN_ADAPTER IoAdapter,
-				   dword start_address, dword features);
-static int check_qBri_interrupt(PISDN_ADAPTER IoAdapter);
-static int diva_4bri_stop_adapter(diva_os_xdi_adapter_t *a);
-
-static int _4bri_is_rev_2_card(int card_ordinal)
-{
-	switch (card_ordinal) {
-	case CARDTYPE_DIVASRV_Q_8M_V2_PCI:
-	case CARDTYPE_DIVASRV_VOICE_Q_8M_V2_PCI:
-	case CARDTYPE_DIVASRV_B_2M_V2_PCI:
-	case CARDTYPE_DIVASRV_B_2F_PCI:
-	case CARDTYPE_DIVASRV_VOICE_B_2M_V2_PCI:
-		return (1);
-	}
-	return (0);
-}
-
-static int _4bri_is_rev_2_bri_card(int card_ordinal)
-{
-	switch (card_ordinal) {
-	case CARDTYPE_DIVASRV_B_2M_V2_PCI:
-	case CARDTYPE_DIVASRV_B_2F_PCI:
-	case CARDTYPE_DIVASRV_VOICE_B_2M_V2_PCI:
-		return (1);
-	}
-	return (0);
-}
-
-static void diva_4bri_set_addresses(diva_os_xdi_adapter_t *a)
-{
-	dword offset = a->resources.pci.qoffset;
-	dword c_offset = offset * a->xdi_adapter.ControllerNumber;
-
-	a->resources.pci.mem_type_id[MEM_TYPE_RAM] = 2;
-	a->resources.pci.mem_type_id[MEM_TYPE_ADDRESS] = 2;
-	a->resources.pci.mem_type_id[MEM_TYPE_CONTROL] = 2;
-	a->resources.pci.mem_type_id[MEM_TYPE_RESET] = 0;
-	a->resources.pci.mem_type_id[MEM_TYPE_CTLREG] = 3;
-	a->resources.pci.mem_type_id[MEM_TYPE_PROM] = 0;
-
-	/*
-	  Set up hardware related pointers
-	*/
-	a->xdi_adapter.Address = a->resources.pci.addr[2];	/* BAR2 SDRAM  */
-	a->xdi_adapter.Address += c_offset;
-
-	a->xdi_adapter.Control = a->resources.pci.addr[2];	/* BAR2 SDRAM  */
-
-	a->xdi_adapter.ram = a->resources.pci.addr[2];	/* BAR2 SDRAM  */
-	a->xdi_adapter.ram += c_offset + (offset - MQ_SHARED_RAM_SIZE);
-
-	a->xdi_adapter.reset = a->resources.pci.addr[0];	/* BAR0 CONFIG */
-	/*
-	  ctlReg contains the register address for the MIPS CPU reset control
-	*/
-	a->xdi_adapter.ctlReg = a->resources.pci.addr[3];	/* BAR3 CNTRL  */
-	/*
-	  prom contains the register address for FPGA and EEPROM programming
-	*/
-	a->xdi_adapter.prom = &a->xdi_adapter.reset[0x6E];
-}
-
-/*
-**  BAR0 - MEM - 0x100    - CONFIG MEM
-**  BAR1 - I/O - 0x100    - UNUSED
-**  BAR2 - MEM - MQ_MEMORY_SIZE (MQ2_MEMORY_SIZE on Rev.2) - SDRAM
-**  BAR3 - MEM - 0x2000 (0x10000 on Rev.2)   - CNTRL
-**
-**  Called by master adapter, that will initialize and add slave adapters
-*/
-int diva_4bri_init_card(diva_os_xdi_adapter_t *a)
-{
-	int bar, i;
-	byte __iomem *p;
-	PADAPTER_LIST_ENTRY quadro_list;
-	diva_os_xdi_adapter_t *diva_current;
-	diva_os_xdi_adapter_t *adapter_list[4];
-	PISDN_ADAPTER Slave;
-	unsigned long bar_length[ARRAY_SIZE(_4bri_bar_length)];
-	int v2 = _4bri_is_rev_2_card(a->CardOrdinal);
-	int tasks = _4bri_is_rev_2_bri_card(a->CardOrdinal) ? 1 : MQ_INSTANCE_COUNT;
-	int factor = (tasks == 1) ? 1 : 2;
-
-	if (v2) {
-		if (_4bri_is_rev_2_bri_card(a->CardOrdinal)) {
-			memcpy(bar_length, _4bri_v2_bri_bar_length,
-			       sizeof(bar_length));
-		} else {
-			memcpy(bar_length, _4bri_v2_bar_length,
-			       sizeof(bar_length));
-		}
-	} else {
-		memcpy(bar_length, _4bri_bar_length, sizeof(bar_length));
-	}
-	DBG_TRC(("SDRAM_LENGTH=%08x, tasks=%d, factor=%d",
-		 bar_length[2], tasks, factor))
-
-		/*
-		  Get Serial Number
-		  The serial number of 4BRI is accessible in accordance with PCI spec
-		  via command register located in configuration space, also we do not
-		  have to map any BAR before we can access it
-		*/
-		if (!_4bri_get_serial_number(a)) {
-			DBG_ERR(("A: 4BRI can't get Serial Number"))
-				diva_4bri_cleanup_adapter(a);
-			return (-1);
-		}
-
-	/*
-	  Set properties
-	*/
-	a->xdi_adapter.Properties = CardProperties[a->CardOrdinal];
-	DBG_LOG(("Load %s, SN:%ld, bus:%02x, func:%02x",
-		 a->xdi_adapter.Properties.Name,
-		 a->xdi_adapter.serialNo,
-		 a->resources.pci.bus, a->resources.pci.func))
-
-		/*
-		  First initialization step: get and check hardware resoures.
-		  Do not map resources and do not access card at this step
-		*/
-		for (bar = 0; bar < 4; bar++) {
-			a->resources.pci.bar[bar] =
-				divasa_get_pci_bar(a->resources.pci.bus,
-						   a->resources.pci.func, bar,
-						   a->resources.pci.hdev);
-			if (!a->resources.pci.bar[bar]
-			    || (a->resources.pci.bar[bar] == 0xFFFFFFF0)) {
-				DBG_ERR(
-					("A: invalid bar[%d]=%08x", bar,
-					 a->resources.pci.bar[bar]))
-					return (-1);
-			}
-		}
-	a->resources.pci.irq =
-		(byte) divasa_get_pci_irq(a->resources.pci.bus,
-					  a->resources.pci.func,
-					  a->resources.pci.hdev);
-	if (!a->resources.pci.irq) {
-		DBG_ERR(("A: invalid irq"));
-		return (-1);
-	}
-
-	a->xdi_adapter.sdram_bar = a->resources.pci.bar[2];
-
-	/*
-	  Map all MEMORY BAR's
-	*/
-	for (bar = 0; bar < 4; bar++) {
-		if (bar != 1) {	/* ignore I/O */
-			a->resources.pci.addr[bar] =
-				divasa_remap_pci_bar(a, bar, a->resources.pci.bar[bar],
-						     bar_length[bar]);
-			if (!a->resources.pci.addr[bar]) {
-				DBG_ERR(("A: 4BRI: can't map bar[%d]", bar))
-					diva_4bri_cleanup_adapter(a);
-				return (-1);
-			}
-		}
-	}
-
-	/*
-	  Register I/O port
-	*/
-	sprintf(&a->port_name[0], "DIVA 4BRI %ld", (long) a->xdi_adapter.serialNo);
-
-	if (diva_os_register_io_port(a, 1, a->resources.pci.bar[1],
-				     bar_length[1], &a->port_name[0], 1)) {
-		DBG_ERR(("A: 4BRI: can't register bar[1]"))
-			diva_4bri_cleanup_adapter(a);
-		return (-1);
-	}
-
-	a->resources.pci.addr[1] =
-		(void *) (unsigned long) a->resources.pci.bar[1];
-
-	/*
-	  Set cleanup pointer for base adapter only, so slave adapter
-	  will be unable to get cleanup
-	*/
-	a->interface.cleanup_adapter_proc = diva_4bri_cleanup_adapter;
-
-	/*
-	  Create slave adapters
-	*/
-	if (tasks > 1) {
-		if (!(a->slave_adapters[0] =
-		      (diva_os_xdi_adapter_t *) diva_os_malloc(0, sizeof(*a))))
-		{
-			diva_4bri_cleanup_adapter(a);
-			return (-1);
-		}
-		if (!(a->slave_adapters[1] =
-		      (diva_os_xdi_adapter_t *) diva_os_malloc(0, sizeof(*a))))
-		{
-			diva_os_free(0, a->slave_adapters[0]);
-			a->slave_adapters[0] = NULL;
-			diva_4bri_cleanup_adapter(a);
-			return (-1);
-		}
-		if (!(a->slave_adapters[2] =
-		      (diva_os_xdi_adapter_t *) diva_os_malloc(0, sizeof(*a))))
-		{
-			diva_os_free(0, a->slave_adapters[0]);
-			diva_os_free(0, a->slave_adapters[1]);
-			a->slave_adapters[0] = NULL;
-			a->slave_adapters[1] = NULL;
-			diva_4bri_cleanup_adapter(a);
-			return (-1);
-		}
-		memset(a->slave_adapters[0], 0x00, sizeof(*a));
-		memset(a->slave_adapters[1], 0x00, sizeof(*a));
-		memset(a->slave_adapters[2], 0x00, sizeof(*a));
-	}
-
-	adapter_list[0] = a;
-	adapter_list[1] = a->slave_adapters[0];
-	adapter_list[2] = a->slave_adapters[1];
-	adapter_list[3] = a->slave_adapters[2];
-
-	/*
-	  Allocate slave list
-	*/
-	quadro_list =
-		(PADAPTER_LIST_ENTRY) diva_os_malloc(0, sizeof(*quadro_list));
-	if (!(a->slave_list = quadro_list)) {
-		for (i = 0; i < (tasks - 1); i++) {
-			diva_os_free(0, a->slave_adapters[i]);
-			a->slave_adapters[i] = NULL;
-		}
-		diva_4bri_cleanup_adapter(a);
-		return (-1);
-	}
-	memset(quadro_list, 0x00, sizeof(*quadro_list));
-
-	/*
-	  Set interfaces
-	*/
-	a->xdi_adapter.QuadroList = quadro_list;
-	for (i = 0; i < tasks; i++) {
-		adapter_list[i]->xdi_adapter.ControllerNumber = i;
-		adapter_list[i]->xdi_adapter.tasks = tasks;
-		quadro_list->QuadroAdapter[i] =
-			&adapter_list[i]->xdi_adapter;
-	}
-
-	for (i = 0; i < tasks; i++) {
-		diva_current = adapter_list[i];
-
-		diva_current->dsp_mask = 0x00000003;
-
-		diva_current->xdi_adapter.a.io =
-			&diva_current->xdi_adapter;
-		diva_current->xdi_adapter.DIRequest = request;
-		diva_current->interface.cmd_proc = diva_4bri_cmd_card_proc;
-		diva_current->xdi_adapter.Properties =
-			CardProperties[a->CardOrdinal];
-		diva_current->CardOrdinal = a->CardOrdinal;
-
-		diva_current->xdi_adapter.Channels =
-			CardProperties[a->CardOrdinal].Channels;
-		diva_current->xdi_adapter.e_max =
-			CardProperties[a->CardOrdinal].E_info;
-		diva_current->xdi_adapter.e_tbl =
-			diva_os_malloc(0,
-				       diva_current->xdi_adapter.e_max *
-				       sizeof(E_INFO));
-
-		if (!diva_current->xdi_adapter.e_tbl) {
-			diva_4bri_cleanup_slave_adapters(a);
-			diva_4bri_cleanup_adapter(a);
-			for (i = 1; i < (tasks - 1); i++) {
-				diva_os_free(0, adapter_list[i]);
-			}
-			return (-1);
-		}
-		memset(diva_current->xdi_adapter.e_tbl, 0x00,
-		       diva_current->xdi_adapter.e_max * sizeof(E_INFO));
-
-		if (diva_os_initialize_spin_lock(&diva_current->xdi_adapter.isr_spin_lock, "isr")) {
-			diva_4bri_cleanup_slave_adapters(a);
-			diva_4bri_cleanup_adapter(a);
-			for (i = 1; i < (tasks - 1); i++) {
-				diva_os_free(0, adapter_list[i]);
-			}
-			return (-1);
-		}
-		if (diva_os_initialize_spin_lock(&diva_current->xdi_adapter.data_spin_lock, "data")) {
-			diva_4bri_cleanup_slave_adapters(a);
-			diva_4bri_cleanup_adapter(a);
-			for (i = 1; i < (tasks - 1); i++) {
-				diva_os_free(0, adapter_list[i]);
-			}
-			return (-1);
-		}
-
-		strcpy(diva_current->xdi_adapter.req_soft_isr. dpc_thread_name, "kdivas4brid");
-
-		if (diva_os_initialize_soft_isr(&diva_current->xdi_adapter.req_soft_isr, DIDpcRoutine,
-						&diva_current->xdi_adapter)) {
-			diva_4bri_cleanup_slave_adapters(a);
-			diva_4bri_cleanup_adapter(a);
-			for (i = 1; i < (tasks - 1); i++) {
-				diva_os_free(0, adapter_list[i]);
-			}
-			return (-1);
-		}
-
-		/*
-		  Do not initialize second DPC - only one thread will be created
-		*/
-		diva_current->xdi_adapter.isr_soft_isr.object =
-			diva_current->xdi_adapter.req_soft_isr.object;
-	}
-
-	if (v2) {
-		prepare_qBri2_functions(&a->xdi_adapter);
-	} else {
-		prepare_qBri_functions(&a->xdi_adapter);
-	}
-
-	for (i = 0; i < tasks; i++) {
-		diva_current = adapter_list[i];
-		if (i)
-			memcpy(&diva_current->resources, &a->resources, sizeof(divas_card_resources_t));
-		diva_current->resources.pci.qoffset = (a->xdi_adapter.MemorySize >> factor);
-	}
-
-	/*
-	  Set up hardware related pointers
-	*/
-	a->xdi_adapter.cfg = (void *) (unsigned long) a->resources.pci.bar[0];	/* BAR0 CONFIG */
-	a->xdi_adapter.port = (void *) (unsigned long) a->resources.pci.bar[1];	/* BAR1        */
-	a->xdi_adapter.ctlReg = (void *) (unsigned long) a->resources.pci.bar[3];	/* BAR3 CNTRL  */
-
-	for (i = 0; i < tasks; i++) {
-		diva_current = adapter_list[i];
-		diva_4bri_set_addresses(diva_current);
-		Slave = a->xdi_adapter.QuadroList->QuadroAdapter[i];
-		Slave->MultiMaster = &a->xdi_adapter;
-		Slave->sdram_bar = a->xdi_adapter.sdram_bar;
-		if (i) {
-			Slave->serialNo = ((dword) (Slave->ControllerNumber << 24)) |
-				a->xdi_adapter.serialNo;
-			Slave->cardType = a->xdi_adapter.cardType;
-		}
-	}
-
-	/*
-	  reset contains the base address for the PLX 9054 register set
-	*/
-	p = DIVA_OS_MEM_ATTACH_RESET(&a->xdi_adapter);
-	WRITE_BYTE(&p[PLX9054_INTCSR], 0x00);	/* disable PCI interrupts */
-	DIVA_OS_MEM_DETACH_RESET(&a->xdi_adapter, p);
-
-	/*
-	  Set IRQ handler
-	*/
-	a->xdi_adapter.irq_info.irq_nr = a->resources.pci.irq;
-	sprintf(a->xdi_adapter.irq_info.irq_name, "DIVA 4BRI %ld",
-		(long) a->xdi_adapter.serialNo);
-
-	if (diva_os_register_irq(a, a->xdi_adapter.irq_info.irq_nr,
-				 a->xdi_adapter.irq_info.irq_name)) {
-		diva_4bri_cleanup_slave_adapters(a);
-		diva_4bri_cleanup_adapter(a);
-		for (i = 1; i < (tasks - 1); i++) {
-			diva_os_free(0, adapter_list[i]);
-		}
-		return (-1);
-	}
-
-	a->xdi_adapter.irq_info.registered = 1;
-
-	/*
-	  Add three slave adapters
-	*/
-	if (tasks > 1) {
-		diva_add_slave_adapter(adapter_list[1]);
-		diva_add_slave_adapter(adapter_list[2]);
-		diva_add_slave_adapter(adapter_list[3]);
-	}
-
-	diva_log_info("%s IRQ:%d SerNo:%d", a->xdi_adapter.Properties.Name,
-		      a->resources.pci.irq, a->xdi_adapter.serialNo);
-
-	return (0);
-}
-
-/*
-**  Cleanup function will be called for master adapter only
-**  this is guaranteed by design: cleanup callback is set
-**  by master adapter only
-*/
-static int diva_4bri_cleanup_adapter(diva_os_xdi_adapter_t *a)
-{
-	int bar;
-
-	/*
-	  Stop adapter if running
-	*/
-	if (a->xdi_adapter.Initialized) {
-		diva_4bri_stop_adapter(a);
-	}
-
-	/*
-	  Remove IRQ handler
-	*/
-	if (a->xdi_adapter.irq_info.registered) {
-		diva_os_remove_irq(a, a->xdi_adapter.irq_info.irq_nr);
-	}
-	a->xdi_adapter.irq_info.registered = 0;
-
-	/*
-	  Free DPC's and spin locks on all adapters
-	*/
-	diva_4bri_cleanup_slave_adapters(a);
-
-	/*
-	  Unmap all BARS
-	*/
-	for (bar = 0; bar < 4; bar++) {
-		if (bar != 1) {
-			if (a->resources.pci.bar[bar]
-			    && a->resources.pci.addr[bar]) {
-				divasa_unmap_pci_bar(a->resources.pci.addr[bar]);
-				a->resources.pci.bar[bar] = 0;
-				a->resources.pci.addr[bar] = NULL;
-			}
-		}
-	}
-
-	/*
-	  Unregister I/O
-	*/
-	if (a->resources.pci.bar[1] && a->resources.pci.addr[1]) {
-		diva_os_register_io_port(a, 0, a->resources.pci.bar[1],
-					 _4bri_is_rev_2_card(a->
-							     CardOrdinal) ?
-					 _4bri_v2_bar_length[1] :
-					 _4bri_bar_length[1],
-					 &a->port_name[0], 1);
-		a->resources.pci.bar[1] = 0;
-		a->resources.pci.addr[1] = NULL;
-	}
-
-	if (a->slave_list) {
-		diva_os_free(0, a->slave_list);
-		a->slave_list = NULL;
-	}
-
-	return (0);
-}
-
-static int _4bri_get_serial_number(diva_os_xdi_adapter_t *a)
-{
-	dword data[64];
-	dword serNo;
-	word addr, status, i, j;
-	byte Bus, Slot;
-	void *hdev;
-
-	Bus = a->resources.pci.bus;
-	Slot = a->resources.pci.func;
-	hdev = a->resources.pci.hdev;
-
-	for (i = 0; i < 64; ++i) {
-		addr = i * 4;
-		for (j = 0; j < 5; ++j) {
-			PCIwrite(Bus, Slot, 0x4E, &addr, sizeof(addr),
-				 hdev);
-			diva_os_wait(1);
-			PCIread(Bus, Slot, 0x4E, &status, sizeof(status),
-				hdev);
-			if (status & 0x8000)
-				break;
-		}
-		if (j >= 5) {
-			DBG_ERR(("EEPROM[%d] read failed (0x%x)", i * 4, addr))
-				return (0);
-		}
-		PCIread(Bus, Slot, 0x50, &data[i], sizeof(data[i]), hdev);
-	}
-	DBG_BLK(((char *) &data[0], sizeof(data)))
-
-		serNo = data[32];
-	if (serNo == 0 || serNo == 0xffffffff)
-		serNo = data[63];
-
-	if (!serNo) {
-		DBG_LOG(("W: Serial Number == 0, create one serial number"));
-		serNo = a->resources.pci.bar[1] & 0xffff0000;
-		serNo |= a->resources.pci.bus << 8;
-		serNo |= a->resources.pci.func;
-	}
-
-	a->xdi_adapter.serialNo = serNo;
-
-	DBG_REG(("Serial No.          : %ld", a->xdi_adapter.serialNo))
-
-		return (serNo);
-}
-
-/*
-**  Release resources of slave adapters
-*/
-static int diva_4bri_cleanup_slave_adapters(diva_os_xdi_adapter_t *a)
-{
-	diva_os_xdi_adapter_t *adapter_list[4];
-	diva_os_xdi_adapter_t *diva_current;
-	int i;
-
-	adapter_list[0] = a;
-	adapter_list[1] = a->slave_adapters[0];
-	adapter_list[2] = a->slave_adapters[1];
-	adapter_list[3] = a->slave_adapters[2];
-
-	for (i = 0; i < a->xdi_adapter.tasks; i++) {
-		diva_current = adapter_list[i];
-		if (diva_current) {
-			diva_os_destroy_spin_lock(&diva_current->
-						  xdi_adapter.
-						  isr_spin_lock, "unload");
-			diva_os_destroy_spin_lock(&diva_current->
-						  xdi_adapter.
-						  data_spin_lock,
-						  "unload");
-
-			diva_os_cancel_soft_isr(&diva_current->xdi_adapter.
-						req_soft_isr);
-			diva_os_cancel_soft_isr(&diva_current->xdi_adapter.
-						isr_soft_isr);
-
-			diva_os_remove_soft_isr(&diva_current->xdi_adapter.
-						req_soft_isr);
-			diva_current->xdi_adapter.isr_soft_isr.object = NULL;
-
-			if (diva_current->xdi_adapter.e_tbl) {
-				diva_os_free(0,
-					     diva_current->xdi_adapter.
-					     e_tbl);
-			}
-			diva_current->xdi_adapter.e_tbl = NULL;
-			diva_current->xdi_adapter.e_max = 0;
-			diva_current->xdi_adapter.e_count = 0;
-		}
-	}
-
-	return (0);
-}
-
-static int
-diva_4bri_cmd_card_proc(struct _diva_os_xdi_adapter *a,
-			diva_xdi_um_cfg_cmd_t *cmd, int length)
-{
-	int ret = -1;
-
-	if (cmd->adapter != a->controller) {
-		DBG_ERR(("A: 4bri_cmd, invalid controller=%d != %d",
-			 cmd->adapter, a->controller))
-			return (-1);
-	}
-
-	switch (cmd->command) {
-	case DIVA_XDI_UM_CMD_GET_CARD_ORDINAL:
-		a->xdi_mbox.data_length = sizeof(dword);
-		a->xdi_mbox.data =
-			diva_os_malloc(0, a->xdi_mbox.data_length);
-		if (a->xdi_mbox.data) {
-			*(dword *) a->xdi_mbox.data =
-				(dword) a->CardOrdinal;
-			a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-			ret = 0;
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_GET_SERIAL_NR:
-		a->xdi_mbox.data_length = sizeof(dword);
-		a->xdi_mbox.data =
-			diva_os_malloc(0, a->xdi_mbox.data_length);
-		if (a->xdi_mbox.data) {
-			*(dword *) a->xdi_mbox.data =
-				(dword) a->xdi_adapter.serialNo;
-			a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-			ret = 0;
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_GET_PCI_HW_CONFIG:
-		if (!a->xdi_adapter.ControllerNumber) {
-			/*
-			  Only master adapter can access hardware config
-			*/
-			a->xdi_mbox.data_length = sizeof(dword) * 9;
-			a->xdi_mbox.data =
-				diva_os_malloc(0, a->xdi_mbox.data_length);
-			if (a->xdi_mbox.data) {
-				int i;
-				dword *data = (dword *) a->xdi_mbox.data;
-
-				for (i = 0; i < 8; i++) {
-					*data++ = a->resources.pci.bar[i];
-				}
-				*data++ = (dword) a->resources.pci.irq;
-				a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-				ret = 0;
-			}
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_GET_CARD_STATE:
-		if (!a->xdi_adapter.ControllerNumber) {
-			a->xdi_mbox.data_length = sizeof(dword);
-			a->xdi_mbox.data =
-				diva_os_malloc(0, a->xdi_mbox.data_length);
-			if (a->xdi_mbox.data) {
-				dword *data = (dword *) a->xdi_mbox.data;
-				if (!a->xdi_adapter.ram
-				    || !a->xdi_adapter.reset
-				    || !a->xdi_adapter.cfg) {
-					*data = 3;
-				} else if (a->xdi_adapter.trapped) {
-					*data = 2;
-				} else if (a->xdi_adapter.Initialized) {
-					*data = 1;
-				} else {
-					*data = 0;
-				}
-				a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-				ret = 0;
-			}
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_WRITE_FPGA:
-		if (!a->xdi_adapter.ControllerNumber) {
-			ret =
-				diva_4bri_write_fpga_image(a,
-							   (byte *)&cmd[1],
-							   cmd->command_data.
-							   write_fpga.
-							   image_length);
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_RESET_ADAPTER:
-		if (!a->xdi_adapter.ControllerNumber) {
-			ret = diva_4bri_reset_adapter(&a->xdi_adapter);
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_WRITE_SDRAM_BLOCK:
-		if (!a->xdi_adapter.ControllerNumber) {
-			ret = diva_4bri_write_sdram_block(&a->xdi_adapter,
-							  cmd->
-							  command_data.
-							  write_sdram.
-							  offset,
-							  (byte *) &
-							  cmd[1],
-							  cmd->
-							  command_data.
-							  write_sdram.
-							  length,
-							  a->xdi_adapter.
-							  MemorySize);
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_START_ADAPTER:
-		if (!a->xdi_adapter.ControllerNumber) {
-			ret = diva_4bri_start_adapter(&a->xdi_adapter,
-						      cmd->command_data.
-						      start.offset,
-						      cmd->command_data.
-						      start.features);
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_SET_PROTOCOL_FEATURES:
-		if (!a->xdi_adapter.ControllerNumber) {
-			a->xdi_adapter.features =
-				cmd->command_data.features.features;
-			a->xdi_adapter.a.protocol_capabilities =
-				a->xdi_adapter.features;
-			DBG_TRC(("Set raw protocol features (%08x)",
-				 a->xdi_adapter.features))
-				ret = 0;
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_STOP_ADAPTER:
-		if (!a->xdi_adapter.ControllerNumber) {
-			ret = diva_4bri_stop_adapter(a);
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_READ_XLOG_ENTRY:
-		ret = diva_card_read_xlog(a);
-		break;
-
-	case DIVA_XDI_UM_CMD_READ_SDRAM:
-		if (!a->xdi_adapter.ControllerNumber
-		    && a->xdi_adapter.Address) {
-			if (
-				(a->xdi_mbox.data_length =
-				 cmd->command_data.read_sdram.length)) {
-				if (
-					(a->xdi_mbox.data_length +
-					 cmd->command_data.read_sdram.offset) <
-					a->xdi_adapter.MemorySize) {
-					a->xdi_mbox.data =
-						diva_os_malloc(0,
-							       a->xdi_mbox.
-							       data_length);
-					if (a->xdi_mbox.data) {
-						byte __iomem *p = DIVA_OS_MEM_ATTACH_ADDRESS(&a->xdi_adapter);
-						byte __iomem *src = p;
-						byte *dst = a->xdi_mbox.data;
-						dword len = a->xdi_mbox.data_length;
-
-						src += cmd->command_data.read_sdram.offset;
-
-						while (len--) {
-							*dst++ = READ_BYTE(src++);
-						}
-						DIVA_OS_MEM_DETACH_ADDRESS(&a->xdi_adapter, p);
-						a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-						ret = 0;
-					}
-				}
-			}
-		}
-		break;
-
-	default:
-		DBG_ERR(("A: A(%d) invalid cmd=%d", a->controller,
-			 cmd->command))
-			}
-
-	return (ret);
-}
-
-void *xdiLoadFile(char *FileName, dword *FileLength,
-		  unsigned long lim)
-{
-	void *ret = diva_xdiLoadFileFile;
-
-	if (FileLength) {
-		*FileLength = diva_xdiLoadFileLength;
-	}
-	diva_xdiLoadFileFile = NULL;
-	diva_xdiLoadFileLength = 0;
-
-	return (ret);
-}
-
-void diva_os_set_qBri_functions(PISDN_ADAPTER IoAdapter)
-{
-}
-
-void diva_os_set_qBri2_functions(PISDN_ADAPTER IoAdapter)
-{
-}
-
-static int
-diva_4bri_write_fpga_image(diva_os_xdi_adapter_t *a, byte *data,
-			   dword length)
-{
-	int ret;
-
-	diva_xdiLoadFileFile = data;
-	diva_xdiLoadFileLength = length;
-
-	ret = qBri_FPGA_download(&a->xdi_adapter);
-
-	diva_xdiLoadFileFile = NULL;
-	diva_xdiLoadFileLength = 0;
-
-	return (ret ? 0 : -1);
-}
-
-static int diva_4bri_reset_adapter(PISDN_ADAPTER IoAdapter)
-{
-	PISDN_ADAPTER Slave;
-	int i;
-
-	if (!IoAdapter->Address || !IoAdapter->reset) {
-		return (-1);
-	}
-	if (IoAdapter->Initialized) {
-		DBG_ERR(("A: A(%d) can't reset 4BRI adapter - please stop first",
-			 IoAdapter->ANum))
-			return (-1);
-	}
-
-	/*
-	  Forget all entities on all adapters
-	*/
-	for (i = 0; ((i < IoAdapter->tasks) && IoAdapter->QuadroList); i++) {
-		Slave = IoAdapter->QuadroList->QuadroAdapter[i];
-		Slave->e_count = 0;
-		if (Slave->e_tbl) {
-			memset(Slave->e_tbl, 0x00,
-			       Slave->e_max * sizeof(E_INFO));
-		}
-		Slave->head = 0;
-		Slave->tail = 0;
-		Slave->assign = 0;
-		Slave->trapped = 0;
-
-		memset(&Slave->a.IdTable[0], 0x00,
-		       sizeof(Slave->a.IdTable));
-		memset(&Slave->a.IdTypeTable[0], 0x00,
-		       sizeof(Slave->a.IdTypeTable));
-		memset(&Slave->a.FlowControlIdTable[0], 0x00,
-		       sizeof(Slave->a.FlowControlIdTable));
-		memset(&Slave->a.FlowControlSkipTable[0], 0x00,
-		       sizeof(Slave->a.FlowControlSkipTable));
-		memset(&Slave->a.misc_flags_table[0], 0x00,
-		       sizeof(Slave->a.misc_flags_table));
-		memset(&Slave->a.rx_stream[0], 0x00,
-		       sizeof(Slave->a.rx_stream));
-		memset(&Slave->a.tx_stream[0], 0x00,
-		       sizeof(Slave->a.tx_stream));
-		memset(&Slave->a.tx_pos[0], 0x00, sizeof(Slave->a.tx_pos));
-		memset(&Slave->a.rx_pos[0], 0x00, sizeof(Slave->a.rx_pos));
-	}
-
-	return (0);
-}
-
-
-static int
-diva_4bri_write_sdram_block(PISDN_ADAPTER IoAdapter,
-			    dword address,
-			    const byte *data, dword length, dword limit)
-{
-	byte __iomem *p = DIVA_OS_MEM_ATTACH_ADDRESS(IoAdapter);
-	byte __iomem *mem = p;
-
-	if (((address + length) >= limit) || !mem) {
-		DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, p);
-		DBG_ERR(("A: A(%d) write 4BRI address=0x%08lx",
-			 IoAdapter->ANum, address + length))
-			return (-1);
-	}
-	mem += address;
-
-	while (length--) {
-		WRITE_BYTE(mem++, *data++);
-	}
-
-	DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, p);
-	return (0);
-}
-
-static int
-diva_4bri_start_adapter(PISDN_ADAPTER IoAdapter,
-			dword start_address, dword features)
-{
-	volatile word __iomem *signature;
-	int started = 0;
-	int i;
-	byte __iomem *p;
-
-	/*
-	  start adapter
-	*/
-	start_qBri_hardware(IoAdapter);
-
-	p = DIVA_OS_MEM_ATTACH_RAM(IoAdapter);
-	/*
-	  wait for signature in shared memory (max. 3 seconds)
-	*/
-	signature = (volatile word __iomem *) (&p[0x1E]);
-
-	for (i = 0; i < 300; ++i) {
-		diva_os_wait(10);
-		if (READ_WORD(&signature[0]) == 0x4447) {
-			DBG_TRC(("Protocol startup time %d.%02d seconds",
-				 (i / 100), (i % 100)))
-				started = 1;
-			break;
-		}
-	}
-
-	for (i = 1; i < IoAdapter->tasks; i++) {
-		IoAdapter->QuadroList->QuadroAdapter[i]->features =
-			IoAdapter->features;
-		IoAdapter->QuadroList->QuadroAdapter[i]->a.
-			protocol_capabilities = IoAdapter->features;
-	}
-
-	if (!started) {
-		DBG_FTL(("%s: Adapter selftest failed, signature=%04x",
-			 IoAdapter->Properties.Name,
-			 READ_WORD(&signature[0])))
-			DIVA_OS_MEM_DETACH_RAM(IoAdapter, p);
-		(*(IoAdapter->trapFnc)) (IoAdapter);
-		IoAdapter->stop(IoAdapter);
-		return (-1);
-	}
-	DIVA_OS_MEM_DETACH_RAM(IoAdapter, p);
-
-	for (i = 0; i < IoAdapter->tasks; i++) {
-		IoAdapter->QuadroList->QuadroAdapter[i]->Initialized = 1;
-		IoAdapter->QuadroList->QuadroAdapter[i]->IrqCount = 0;
-	}
-
-	if (check_qBri_interrupt(IoAdapter)) {
-		DBG_ERR(("A: A(%d) interrupt test failed",
-			 IoAdapter->ANum))
-			for (i = 0; i < IoAdapter->tasks; i++) {
-				IoAdapter->QuadroList->QuadroAdapter[i]->Initialized = 0;
-			}
-		IoAdapter->stop(IoAdapter);
-		return (-1);
-	}
-
-	IoAdapter->Properties.Features = (word) features;
-	diva_xdi_display_adapter_features(IoAdapter->ANum);
-
-	for (i = 0; i < IoAdapter->tasks; i++) {
-		DBG_LOG(("A(%d) %s adapter successfully started",
-			 IoAdapter->QuadroList->QuadroAdapter[i]->ANum,
-			 (IoAdapter->tasks == 1) ? "BRI 2.0" : "4BRI"))
-			diva_xdi_didd_register_adapter(IoAdapter->QuadroList->QuadroAdapter[i]->ANum);
-		IoAdapter->QuadroList->QuadroAdapter[i]->Properties.Features = (word) features;
-	}
-
-	return (0);
-}
-
-static int check_qBri_interrupt(PISDN_ADAPTER IoAdapter)
-{
-#ifdef	SUPPORT_INTERRUPT_TEST_ON_4BRI
-	int i;
-	ADAPTER *a = &IoAdapter->a;
-	byte __iomem *p;
-
-	IoAdapter->IrqCount = 0;
-
-	if (IoAdapter->ControllerNumber > 0)
-		return (-1);
-
-	p = DIVA_OS_MEM_ATTACH_RESET(IoAdapter);
-	WRITE_BYTE(&p[PLX9054_INTCSR], PLX9054_INT_ENABLE);
-	DIVA_OS_MEM_DETACH_RESET(IoAdapter, p);
-	/*
-	  interrupt test
-	*/
-	a->ReadyInt = 1;
-	a->ram_out(a, &PR_RAM->ReadyInt, 1);
-
-	for (i = 100; !IoAdapter->IrqCount && (i-- > 0); diva_os_wait(10));
-
-	return ((IoAdapter->IrqCount > 0) ? 0 : -1);
-#else
-	dword volatile __iomem *qBriIrq;
-	byte __iomem *p;
-	/*
-	  Reset on-board interrupt register
-	*/
-	IoAdapter->IrqCount = 0;
-	p = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	qBriIrq = (dword volatile __iomem *) (&p[_4bri_is_rev_2_card
-						 (IoAdapter->
-						  cardType) ? (MQ2_BREG_IRQ_TEST)
-						 : (MQ_BREG_IRQ_TEST)]);
-
-	WRITE_DWORD(qBriIrq, MQ_IRQ_REQ_OFF);
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, p);
-
-	p = DIVA_OS_MEM_ATTACH_RESET(IoAdapter);
-	WRITE_BYTE(&p[PLX9054_INTCSR], PLX9054_INT_ENABLE);
-	DIVA_OS_MEM_DETACH_RESET(IoAdapter, p);
-
-	diva_os_wait(100);
-
-	return (0);
-#endif				/* SUPPORT_INTERRUPT_TEST_ON_4BRI */
-}
-
-static void diva_4bri_clear_interrupts(diva_os_xdi_adapter_t *a)
-{
-	PISDN_ADAPTER IoAdapter = &a->xdi_adapter;
-
-	/*
-	  clear any pending interrupt
-	*/
-	IoAdapter->disIrq(IoAdapter);
-
-	IoAdapter->tst_irq(&IoAdapter->a);
-	IoAdapter->clr_irq(&IoAdapter->a);
-	IoAdapter->tst_irq(&IoAdapter->a);
-
-	/*
-	  kill pending dpcs
-	*/
-	diva_os_cancel_soft_isr(&IoAdapter->req_soft_isr);
-	diva_os_cancel_soft_isr(&IoAdapter->isr_soft_isr);
-}
-
-static int diva_4bri_stop_adapter(diva_os_xdi_adapter_t *a)
-{
-	PISDN_ADAPTER IoAdapter = &a->xdi_adapter;
-	int i;
-
-	if (!IoAdapter->ram) {
-		return (-1);
-	}
-
-	if (!IoAdapter->Initialized) {
-		DBG_ERR(("A: A(%d) can't stop PRI adapter - not running",
-			 IoAdapter->ANum))
-			return (-1);	/* nothing to stop */
-	}
-
-	for (i = 0; i < IoAdapter->tasks; i++) {
-		IoAdapter->QuadroList->QuadroAdapter[i]->Initialized = 0;
-	}
-
-	/*
-	  Disconnect Adapters from DIDD
-	*/
-	for (i = 0; i < IoAdapter->tasks; i++) {
-		diva_xdi_didd_remove_adapter(IoAdapter->QuadroList->QuadroAdapter[i]->ANum);
-	}
-
-	i = 100;
-
-	/*
-	  Stop interrupts
-	*/
-	a->clear_interrupts_proc = diva_4bri_clear_interrupts;
-	IoAdapter->a.ReadyInt = 1;
-	IoAdapter->a.ram_inc(&IoAdapter->a, &PR_RAM->ReadyInt);
-	do {
-		diva_os_sleep(10);
-	} while (i-- && a->clear_interrupts_proc);
-
-	if (a->clear_interrupts_proc) {
-		diva_4bri_clear_interrupts(a);
-		a->clear_interrupts_proc = NULL;
-		DBG_ERR(("A: A(%d) no final interrupt from 4BRI adapter",
-			 IoAdapter->ANum))
-			}
-	IoAdapter->a.ReadyInt = 0;
-
-	/*
-	  Stop and reset adapter
-	*/
-	IoAdapter->stop(IoAdapter);
-
-	return (0);
-}
diff --git a/drivers/isdn/hardware/eicon/os_4bri.h b/drivers/isdn/hardware/eicon/os_4bri.h
deleted file mode 100644
index 94b2709537d8..000000000000
--- a/drivers/isdn/hardware/eicon/os_4bri.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: os_4bri.h,v 1.1.2.2 2001/02/08 12:25:44 armin Exp $ */
-
-#ifndef __DIVA_OS_4_BRI_H__
-#define __DIVA_OS_4_BRI_H__
-
-int diva_4bri_init_card(diva_os_xdi_adapter_t *a);
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/os_bri.c b/drivers/isdn/hardware/eicon/os_bri.c
deleted file mode 100644
index de93090bcacb..000000000000
--- a/drivers/isdn/hardware/eicon/os_bri.c
+++ /dev/null
@@ -1,815 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* $Id: os_bri.c,v 1.21 2004/03/21 17:26:01 armin Exp $ */
-
-#include "platform.h"
-#include "debuglib.h"
-#include "cardtype.h"
-#include "pc.h"
-#include "pr_pc.h"
-#include "di_defs.h"
-#include "dsp_defs.h"
-#include "di.h"
-#include "io.h"
-
-#include "xdi_msg.h"
-#include "xdi_adapter.h"
-#include "os_bri.h"
-#include "diva_pci.h"
-#include "mi_pc.h"
-#include "pc_maint.h"
-#include "dsrv_bri.h"
-
-/*
-**  IMPORTS
-*/
-extern void prepare_maestra_functions(PISDN_ADAPTER IoAdapter);
-extern void diva_xdi_display_adapter_features(int card);
-extern int diva_card_read_xlog(diva_os_xdi_adapter_t *a);
-
-/*
-**  LOCALS
-*/
-static int bri_bar_length[3] = {
-	0x80,
-	0x80,
-	0x20
-};
-static int diva_bri_cleanup_adapter(diva_os_xdi_adapter_t *a);
-static dword diva_bri_get_serial_number(diva_os_xdi_adapter_t *a);
-static int diva_bri_cmd_card_proc(struct _diva_os_xdi_adapter *a,
-				  diva_xdi_um_cfg_cmd_t *cmd, int length);
-static int diva_bri_reregister_io(diva_os_xdi_adapter_t *a);
-static int diva_bri_reset_adapter(PISDN_ADAPTER IoAdapter);
-static int diva_bri_write_sdram_block(PISDN_ADAPTER IoAdapter,
-				      dword address,
-				      const byte *data, dword length);
-static int diva_bri_start_adapter(PISDN_ADAPTER IoAdapter,
-				  dword start_address, dword features);
-static int diva_bri_stop_adapter(diva_os_xdi_adapter_t *a);
-
-static void diva_bri_set_addresses(diva_os_xdi_adapter_t *a)
-{
-	a->resources.pci.mem_type_id[MEM_TYPE_RAM] = 0;
-	a->resources.pci.mem_type_id[MEM_TYPE_CFG] = 1;
-	a->resources.pci.mem_type_id[MEM_TYPE_ADDRESS] = 2;
-	a->resources.pci.mem_type_id[MEM_TYPE_RESET] = 1;
-	a->resources.pci.mem_type_id[MEM_TYPE_PORT] = 2;
-	a->resources.pci.mem_type_id[MEM_TYPE_CTLREG] = 2;
-
-	a->xdi_adapter.ram = a->resources.pci.addr[0];
-	a->xdi_adapter.cfg = a->resources.pci.addr[1];
-	a->xdi_adapter.Address = a->resources.pci.addr[2];
-
-	a->xdi_adapter.reset = a->xdi_adapter.cfg;
-	a->xdi_adapter.port = a->xdi_adapter.Address;
-
-	a->xdi_adapter.ctlReg = a->xdi_adapter.port + M_PCI_RESET;
-
-	a->xdi_adapter.reset += 0x4C;	/* PLX 9050 !! */
-}
-
-/*
-**  BAR0 - MEM Addr  - 0x80  - NOT USED
-**  BAR1 - I/O Addr  - 0x80
-**  BAR2 - I/O Addr  - 0x20
-*/
-int diva_bri_init_card(diva_os_xdi_adapter_t *a)
-{
-	int bar;
-	dword bar2 = 0, bar2_length = 0xffffffff;
-	word cmd = 0, cmd_org;
-	byte Bus, Slot;
-	void *hdev;
-	byte __iomem *p;
-
-	/*
-	  Set properties
-	*/
-	a->xdi_adapter.Properties = CardProperties[a->CardOrdinal];
-	DBG_LOG(("Load %s", a->xdi_adapter.Properties.Name))
-
-		/*
-		  Get resources
-		*/
-		for (bar = 0; bar < 3; bar++) {
-			a->resources.pci.bar[bar] =
-				divasa_get_pci_bar(a->resources.pci.bus,
-						   a->resources.pci.func, bar,
-						   a->resources.pci.hdev);
-			if (!a->resources.pci.bar[bar]) {
-				DBG_ERR(("A: can't get BAR[%d]", bar))
-					return (-1);
-			}
-		}
-
-	a->resources.pci.irq =
-		(byte) divasa_get_pci_irq(a->resources.pci.bus,
-					  a->resources.pci.func,
-					  a->resources.pci.hdev);
-	if (!a->resources.pci.irq) {
-		DBG_ERR(("A: invalid irq"));
-		return (-1);
-	}
-
-	/*
-	  Get length of I/O bar 2 - it is different by older
-	  EEPROM version
-	*/
-	Bus = a->resources.pci.bus;
-	Slot = a->resources.pci.func;
-	hdev = a->resources.pci.hdev;
-
-	/*
-	  Get plain original values of the BAR2 CDM registers
-	*/
-	PCIread(Bus, Slot, 0x18, &bar2, sizeof(bar2), hdev);
-	PCIread(Bus, Slot, 0x04, &cmd_org, sizeof(cmd_org), hdev);
-	/*
-	  Disable device and get BAR2 length
-	*/
-	PCIwrite(Bus, Slot, 0x04, &cmd, sizeof(cmd), hdev);
-	PCIwrite(Bus, Slot, 0x18, &bar2_length, sizeof(bar2_length), hdev);
-	PCIread(Bus, Slot, 0x18, &bar2_length, sizeof(bar2_length), hdev);
-	/*
-	  Restore BAR2 and CMD registers
-	*/
-	PCIwrite(Bus, Slot, 0x18, &bar2, sizeof(bar2), hdev);
-	PCIwrite(Bus, Slot, 0x04, &cmd_org, sizeof(cmd_org), hdev);
-
-	/*
-	  Calculate BAR2 length
-	*/
-	bar2_length = (~(bar2_length & ~7)) + 1;
-	DBG_LOG(("BAR[2] length=%lx", bar2_length))
-
-		/*
-		  Map and register resources
-		*/
-		if (!(a->resources.pci.addr[0] =
-		      divasa_remap_pci_bar(a, 0, a->resources.pci.bar[0],
-					   bri_bar_length[0]))) {
-			DBG_ERR(("A: BRI, can't map BAR[0]"))
-				diva_bri_cleanup_adapter(a);
-			return (-1);
-		}
-
-	sprintf(&a->port_name[0], "BRI %02x:%02x",
-		a->resources.pci.bus, a->resources.pci.func);
-
-	if (diva_os_register_io_port(a, 1, a->resources.pci.bar[1],
-				     bri_bar_length[1], &a->port_name[0], 1)) {
-		DBG_ERR(("A: BRI, can't register BAR[1]"))
-			diva_bri_cleanup_adapter(a);
-		return (-1);
-	}
-	a->resources.pci.addr[1] = (void *) (unsigned long) a->resources.pci.bar[1];
-	a->resources.pci.length[1] = bri_bar_length[1];
-
-	if (diva_os_register_io_port(a, 1, a->resources.pci.bar[2],
-				     bar2_length, &a->port_name[0], 2)) {
-		DBG_ERR(("A: BRI, can't register BAR[2]"))
-			diva_bri_cleanup_adapter(a);
-		return (-1);
-	}
-	a->resources.pci.addr[2] = (void *) (unsigned long) a->resources.pci.bar[2];
-	a->resources.pci.length[2] = bar2_length;
-
-	/*
-	  Set all memory areas
-	*/
-	diva_bri_set_addresses(a);
-
-	/*
-	  Get Serial Number
-	*/
-	a->xdi_adapter.serialNo = diva_bri_get_serial_number(a);
-
-	/*
-	  Register I/O ports with correct name now
-	*/
-	if (diva_bri_reregister_io(a)) {
-		diva_bri_cleanup_adapter(a);
-		return (-1);
-	}
-
-	/*
-	  Initialize OS dependent objects
-	*/
-	if (diva_os_initialize_spin_lock
-	    (&a->xdi_adapter.isr_spin_lock, "isr")) {
-		diva_bri_cleanup_adapter(a);
-		return (-1);
-	}
-	if (diva_os_initialize_spin_lock
-	    (&a->xdi_adapter.data_spin_lock, "data")) {
-		diva_bri_cleanup_adapter(a);
-		return (-1);
-	}
-
-	strcpy(a->xdi_adapter.req_soft_isr.dpc_thread_name, "kdivasbrid");
-
-	if (diva_os_initialize_soft_isr(&a->xdi_adapter.req_soft_isr,
-					DIDpcRoutine, &a->xdi_adapter)) {
-		diva_bri_cleanup_adapter(a);
-		return (-1);
-	}
-	/*
-	  Do not initialize second DPC - only one thread will be created
-	*/
-	a->xdi_adapter.isr_soft_isr.object = a->xdi_adapter.req_soft_isr.object;
-
-	/*
-	  Create entity table
-	*/
-	a->xdi_adapter.Channels = CardProperties[a->CardOrdinal].Channels;
-	a->xdi_adapter.e_max = CardProperties[a->CardOrdinal].E_info;
-	a->xdi_adapter.e_tbl = diva_os_malloc(0, a->xdi_adapter.e_max * sizeof(E_INFO));
-	if (!a->xdi_adapter.e_tbl) {
-		diva_bri_cleanup_adapter(a);
-		return (-1);
-	}
-	memset(a->xdi_adapter.e_tbl, 0x00, a->xdi_adapter.e_max * sizeof(E_INFO));
-
-	/*
-	  Set up interface
-	*/
-	a->xdi_adapter.a.io = &a->xdi_adapter;
-	a->xdi_adapter.DIRequest = request;
-	a->interface.cleanup_adapter_proc = diva_bri_cleanup_adapter;
-	a->interface.cmd_proc = diva_bri_cmd_card_proc;
-
-	p = DIVA_OS_MEM_ATTACH_RESET(&a->xdi_adapter);
-	outpp(p, 0x41);
-	DIVA_OS_MEM_DETACH_RESET(&a->xdi_adapter, p);
-
-	prepare_maestra_functions(&a->xdi_adapter);
-
-	a->dsp_mask = 0x00000003;
-
-	/*
-	  Set IRQ handler
-	*/
-	a->xdi_adapter.irq_info.irq_nr = a->resources.pci.irq;
-	sprintf(a->xdi_adapter.irq_info.irq_name, "DIVA BRI %ld",
-		(long) a->xdi_adapter.serialNo);
-	if (diva_os_register_irq(a, a->xdi_adapter.irq_info.irq_nr,
-				 a->xdi_adapter.irq_info.irq_name)) {
-		diva_bri_cleanup_adapter(a);
-		return (-1);
-	}
-	a->xdi_adapter.irq_info.registered = 1;
-
-	diva_log_info("%s IRQ:%d SerNo:%d", a->xdi_adapter.Properties.Name,
-		      a->resources.pci.irq, a->xdi_adapter.serialNo);
-
-	return (0);
-}
-
-
-static int diva_bri_cleanup_adapter(diva_os_xdi_adapter_t *a)
-{
-	int i;
-
-	if (a->xdi_adapter.Initialized) {
-		diva_bri_stop_adapter(a);
-	}
-
-	/*
-	  Remove ISR Handler
-	*/
-	if (a->xdi_adapter.irq_info.registered) {
-		diva_os_remove_irq(a, a->xdi_adapter.irq_info.irq_nr);
-	}
-	a->xdi_adapter.irq_info.registered = 0;
-
-	if (a->resources.pci.addr[0] && a->resources.pci.bar[0]) {
-		divasa_unmap_pci_bar(a->resources.pci.addr[0]);
-		a->resources.pci.addr[0] = NULL;
-		a->resources.pci.bar[0] = 0;
-	}
-
-	for (i = 1; i < 3; i++) {
-		if (a->resources.pci.addr[i] && a->resources.pci.bar[i]) {
-			diva_os_register_io_port(a, 0,
-						 a->resources.pci.bar[i],
-						 a->resources.pci.
-						 length[i],
-						 &a->port_name[0], i);
-			a->resources.pci.addr[i] = NULL;
-			a->resources.pci.bar[i] = 0;
-		}
-	}
-
-	/*
-	  Free OS objects
-	*/
-	diva_os_cancel_soft_isr(&a->xdi_adapter.req_soft_isr);
-	diva_os_cancel_soft_isr(&a->xdi_adapter.isr_soft_isr);
-
-	diva_os_remove_soft_isr(&a->xdi_adapter.req_soft_isr);
-	a->xdi_adapter.isr_soft_isr.object = NULL;
-
-	diva_os_destroy_spin_lock(&a->xdi_adapter.isr_spin_lock, "rm");
-	diva_os_destroy_spin_lock(&a->xdi_adapter.data_spin_lock, "rm");
-
-	/*
-	  Free memory
-	*/
-	if (a->xdi_adapter.e_tbl) {
-		diva_os_free(0, a->xdi_adapter.e_tbl);
-		a->xdi_adapter.e_tbl = NULL;
-	}
-
-	return (0);
-}
-
-void diva_os_prepare_maestra_functions(PISDN_ADAPTER IoAdapter)
-{
-}
-
-/*
-**  Get serial number
-*/
-static dword diva_bri_get_serial_number(diva_os_xdi_adapter_t *a)
-{
-	dword serNo = 0;
-	byte __iomem *confIO;
-	word serHi, serLo;
-	word __iomem *confMem;
-
-	confIO = DIVA_OS_MEM_ATTACH_CFG(&a->xdi_adapter);
-	serHi = (word) (inppw(&confIO[0x22]) & 0x0FFF);
-	serLo = (word) (inppw(&confIO[0x26]) & 0x0FFF);
-	serNo = ((dword) serHi << 16) | (dword) serLo;
-	DIVA_OS_MEM_DETACH_CFG(&a->xdi_adapter, confIO);
-
-	if ((serNo == 0) || (serNo == 0xFFFFFFFF)) {
-		DBG_FTL(("W: BRI use BAR[0] to get card serial number"))
-
-			confMem = (word __iomem *)DIVA_OS_MEM_ATTACH_RAM(&a->xdi_adapter);
-		serHi = (word) (READ_WORD(&confMem[0x11]) & 0x0FFF);
-		serLo = (word) (READ_WORD(&confMem[0x13]) & 0x0FFF);
-		serNo = (((dword) serHi) << 16) | ((dword) serLo);
-		DIVA_OS_MEM_DETACH_RAM(&a->xdi_adapter, confMem);
-	}
-
-	DBG_LOG(("Serial Number=%ld", serNo))
-
-		return (serNo);
-}
-
-/*
-**  Unregister I/O and register it with new name,
-**  based on Serial Number
-*/
-static int diva_bri_reregister_io(diva_os_xdi_adapter_t *a)
-{
-	int i;
-
-	for (i = 1; i < 3; i++) {
-		diva_os_register_io_port(a, 0, a->resources.pci.bar[i],
-					 a->resources.pci.length[i],
-					 &a->port_name[0], i);
-		a->resources.pci.addr[i] = NULL;
-	}
-
-	sprintf(a->port_name, "DIVA BRI %ld",
-		(long) a->xdi_adapter.serialNo);
-
-	for (i = 1; i < 3; i++) {
-		if (diva_os_register_io_port(a, 1, a->resources.pci.bar[i],
-					     a->resources.pci.length[i],
-					     &a->port_name[0], i)) {
-			DBG_ERR(("A: failed to reregister BAR[%d]", i))
-				return (-1);
-		}
-		a->resources.pci.addr[i] =
-			(void *) (unsigned long) a->resources.pci.bar[i];
-	}
-
-	return (0);
-}
-
-/*
-**  Process command from user mode
-*/
-static int
-diva_bri_cmd_card_proc(struct _diva_os_xdi_adapter *a,
-		       diva_xdi_um_cfg_cmd_t *cmd, int length)
-{
-	int ret = -1;
-
-	if (cmd->adapter != a->controller) {
-		DBG_ERR(("A: pri_cmd, invalid controller=%d != %d",
-			 cmd->adapter, a->controller))
-			return (-1);
-	}
-
-	switch (cmd->command) {
-	case DIVA_XDI_UM_CMD_GET_CARD_ORDINAL:
-		a->xdi_mbox.data_length = sizeof(dword);
-		a->xdi_mbox.data =
-			diva_os_malloc(0, a->xdi_mbox.data_length);
-		if (a->xdi_mbox.data) {
-			*(dword *) a->xdi_mbox.data =
-				(dword) a->CardOrdinal;
-			a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-			ret = 0;
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_GET_SERIAL_NR:
-		a->xdi_mbox.data_length = sizeof(dword);
-		a->xdi_mbox.data =
-			diva_os_malloc(0, a->xdi_mbox.data_length);
-		if (a->xdi_mbox.data) {
-			*(dword *) a->xdi_mbox.data =
-				(dword) a->xdi_adapter.serialNo;
-			a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-			ret = 0;
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_GET_PCI_HW_CONFIG:
-		a->xdi_mbox.data_length = sizeof(dword) * 9;
-		a->xdi_mbox.data =
-			diva_os_malloc(0, a->xdi_mbox.data_length);
-		if (a->xdi_mbox.data) {
-			int i;
-			dword *data = (dword *) a->xdi_mbox.data;
-
-			for (i = 0; i < 8; i++) {
-				*data++ = a->resources.pci.bar[i];
-			}
-			*data++ = (dword) a->resources.pci.irq;
-			a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-			ret = 0;
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_GET_CARD_STATE:
-		a->xdi_mbox.data_length = sizeof(dword);
-		a->xdi_mbox.data =
-			diva_os_malloc(0, a->xdi_mbox.data_length);
-		if (a->xdi_mbox.data) {
-			dword *data = (dword *) a->xdi_mbox.data;
-			if (!a->xdi_adapter.port) {
-				*data = 3;
-			} else if (a->xdi_adapter.trapped) {
-				*data = 2;
-			} else if (a->xdi_adapter.Initialized) {
-				*data = 1;
-			} else {
-				*data = 0;
-			}
-			a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-			ret = 0;
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_RESET_ADAPTER:
-		ret = diva_bri_reset_adapter(&a->xdi_adapter);
-		break;
-
-	case DIVA_XDI_UM_CMD_WRITE_SDRAM_BLOCK:
-		ret = diva_bri_write_sdram_block(&a->xdi_adapter,
-						 cmd->command_data.
-						 write_sdram.offset,
-						 (byte *)&cmd[1],
-						 cmd->command_data.
-						 write_sdram.length);
-		break;
-
-	case DIVA_XDI_UM_CMD_START_ADAPTER:
-		ret = diva_bri_start_adapter(&a->xdi_adapter,
-					     cmd->command_data.start.
-					     offset,
-					     cmd->command_data.start.
-					     features);
-		break;
-
-	case DIVA_XDI_UM_CMD_SET_PROTOCOL_FEATURES:
-		a->xdi_adapter.features =
-			cmd->command_data.features.features;
-		a->xdi_adapter.a.protocol_capabilities =
-			a->xdi_adapter.features;
-		DBG_TRC(
-			("Set raw protocol features (%08x)",
-			 a->xdi_adapter.features)) ret = 0;
-		break;
-
-	case DIVA_XDI_UM_CMD_STOP_ADAPTER:
-		ret = diva_bri_stop_adapter(a);
-		break;
-
-	case DIVA_XDI_UM_CMD_READ_XLOG_ENTRY:
-		ret = diva_card_read_xlog(a);
-		break;
-
-	default:
-		DBG_ERR(
-			("A: A(%d) invalid cmd=%d", a->controller,
-			 cmd->command))}
-
-	return (ret);
-}
-
-static int diva_bri_reset_adapter(PISDN_ADAPTER IoAdapter)
-{
-	byte __iomem *addrHi, *addrLo, *ioaddr;
-	dword i;
-	byte __iomem *Port;
-
-	if (!IoAdapter->port) {
-		return (-1);
-	}
-	if (IoAdapter->Initialized) {
-		DBG_ERR(("A: A(%d) can't reset BRI adapter - please stop first",
-			 IoAdapter->ANum)) return (-1);
-	}
-	(*(IoAdapter->rstFnc)) (IoAdapter);
-	diva_os_wait(100);
-	Port = DIVA_OS_MEM_ATTACH_PORT(IoAdapter);
-	addrHi = Port +
-		((IoAdapter->Properties.Bus == BUS_PCI) ? M_PCI_ADDRH : ADDRH);
-	addrLo = Port + ADDR;
-	ioaddr = Port + DATA;
-	/*
-	  recover
-	*/
-	outpp(addrHi, (byte) 0);
-	outppw(addrLo, (word) 0);
-	outppw(ioaddr, (word) 0);
-	/*
-	  clear shared memory
-	*/
-	outpp(addrHi,
-	      (byte) (
-		      (IoAdapter->MemoryBase + IoAdapter->MemorySize -
-		       BRI_SHARED_RAM_SIZE) >> 16));
-	outppw(addrLo, 0);
-	for (i = 0; i < 0x8000; outppw(ioaddr, 0), ++i);
-	diva_os_wait(100);
-
-	/*
-	  clear signature
-	*/
-	outpp(addrHi,
-	      (byte) (
-		      (IoAdapter->MemoryBase + IoAdapter->MemorySize -
-		       BRI_SHARED_RAM_SIZE) >> 16));
-	outppw(addrLo, 0x1e);
-	outpp(ioaddr, 0);
-	outpp(ioaddr, 0);
-
-	outpp(addrHi, (byte) 0);
-	outppw(addrLo, (word) 0);
-	outppw(ioaddr, (word) 0);
-
-	DIVA_OS_MEM_DETACH_PORT(IoAdapter, Port);
-
-	/*
-	  Forget all outstanding entities
-	*/
-	IoAdapter->e_count = 0;
-	if (IoAdapter->e_tbl) {
-		memset(IoAdapter->e_tbl, 0x00,
-		       IoAdapter->e_max * sizeof(E_INFO));
-	}
-	IoAdapter->head = 0;
-	IoAdapter->tail = 0;
-	IoAdapter->assign = 0;
-	IoAdapter->trapped = 0;
-
-	memset(&IoAdapter->a.IdTable[0], 0x00,
-	       sizeof(IoAdapter->a.IdTable));
-	memset(&IoAdapter->a.IdTypeTable[0], 0x00,
-	       sizeof(IoAdapter->a.IdTypeTable));
-	memset(&IoAdapter->a.FlowControlIdTable[0], 0x00,
-	       sizeof(IoAdapter->a.FlowControlIdTable));
-	memset(&IoAdapter->a.FlowControlSkipTable[0], 0x00,
-	       sizeof(IoAdapter->a.FlowControlSkipTable));
-	memset(&IoAdapter->a.misc_flags_table[0], 0x00,
-	       sizeof(IoAdapter->a.misc_flags_table));
-	memset(&IoAdapter->a.rx_stream[0], 0x00,
-	       sizeof(IoAdapter->a.rx_stream));
-	memset(&IoAdapter->a.tx_stream[0], 0x00,
-	       sizeof(IoAdapter->a.tx_stream));
-	memset(&IoAdapter->a.tx_pos[0], 0x00, sizeof(IoAdapter->a.tx_pos));
-	memset(&IoAdapter->a.rx_pos[0], 0x00, sizeof(IoAdapter->a.rx_pos));
-
-	return (0);
-}
-
-static int
-diva_bri_write_sdram_block(PISDN_ADAPTER IoAdapter,
-			   dword address, const byte *data, dword length)
-{
-	byte __iomem *addrHi, *addrLo, *ioaddr;
-	byte __iomem *Port;
-
-	if (!IoAdapter->port) {
-		return (-1);
-	}
-
-	Port = DIVA_OS_MEM_ATTACH_PORT(IoAdapter);
-	addrHi = Port +
-		((IoAdapter->Properties.Bus == BUS_PCI) ? M_PCI_ADDRH : ADDRH);
-	addrLo = Port + ADDR;
-	ioaddr = Port + DATA;
-
-	while (length--) {
-		outpp(addrHi, (word) (address >> 16));
-		outppw(addrLo, (word) (address & 0x0000ffff));
-		outpp(ioaddr, *data++);
-		address++;
-	}
-
-	DIVA_OS_MEM_DETACH_PORT(IoAdapter, Port);
-	return (0);
-}
-
-static int
-diva_bri_start_adapter(PISDN_ADAPTER IoAdapter,
-		       dword start_address, dword features)
-{
-	byte __iomem *Port;
-	dword i, test;
-	byte __iomem *addrHi, *addrLo, *ioaddr;
-	int started = 0;
-	ADAPTER *a = &IoAdapter->a;
-
-	if (IoAdapter->Initialized) {
-		DBG_ERR(
-			("A: A(%d) bri_start_adapter, adapter already running",
-			 IoAdapter->ANum)) return (-1);
-	}
-	if (!IoAdapter->port) {
-		DBG_ERR(("A: A(%d) bri_start_adapter, adapter not mapped",
-			 IoAdapter->ANum)) return (-1);
-	}
-
-	sprintf(IoAdapter->Name, "A(%d)", (int) IoAdapter->ANum);
-	DBG_LOG(("A(%d) start BRI", IoAdapter->ANum))
-
-		Port = DIVA_OS_MEM_ATTACH_PORT(IoAdapter);
-	addrHi = Port +
-		((IoAdapter->Properties.Bus == BUS_PCI) ? M_PCI_ADDRH : ADDRH);
-	addrLo = Port + ADDR;
-	ioaddr = Port + DATA;
-
-	outpp(addrHi,
-	      (byte) (
-		      (IoAdapter->MemoryBase + IoAdapter->MemorySize -
-		       BRI_SHARED_RAM_SIZE) >> 16));
-	outppw(addrLo, 0x1e);
-	outppw(ioaddr, 0x00);
-	DIVA_OS_MEM_DETACH_PORT(IoAdapter, Port);
-
-	/*
-	  start the protocol code
-	*/
-	Port = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	outpp(Port, 0x08);
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, Port);
-
-	Port = DIVA_OS_MEM_ATTACH_PORT(IoAdapter);
-	addrHi = Port +
-		((IoAdapter->Properties.Bus == BUS_PCI) ? M_PCI_ADDRH : ADDRH);
-	addrLo = Port + ADDR;
-	ioaddr = Port + DATA;
-	/*
-	  wait for signature (max. 3 seconds)
-	*/
-	for (i = 0; i < 300; ++i) {
-		diva_os_wait(10);
-		outpp(addrHi,
-		      (byte) (
-			      (IoAdapter->MemoryBase +
-			       IoAdapter->MemorySize -
-			       BRI_SHARED_RAM_SIZE) >> 16));
-		outppw(addrLo, 0x1e);
-		test = (dword) inppw(ioaddr);
-		if (test == 0x4447) {
-			DBG_LOG(
-				("Protocol startup time %d.%02d seconds",
-				 (i / 100), (i % 100)))
-				started = 1;
-			break;
-		}
-	}
-	DIVA_OS_MEM_DETACH_PORT(IoAdapter, Port);
-
-	if (!started) {
-		DBG_FTL(("A: A(%d) %s: Adapter selftest failed 0x%04X",
-			 IoAdapter->ANum, IoAdapter->Properties.Name,
-			 test))
-			(*(IoAdapter->trapFnc)) (IoAdapter);
-		return (-1);
-	}
-
-	IoAdapter->Initialized = 1;
-
-	/*
-	  Check Interrupt
-	*/
-	IoAdapter->IrqCount = 0;
-	a->ReadyInt = 1;
-
-	if (IoAdapter->reset) {
-		Port = DIVA_OS_MEM_ATTACH_RESET(IoAdapter);
-		outpp(Port, 0x41);
-		DIVA_OS_MEM_DETACH_RESET(IoAdapter, Port);
-	}
-
-	a->ram_out(a, &PR_RAM->ReadyInt, 1);
-	for (i = 0; ((!IoAdapter->IrqCount) && (i < 100)); i++) {
-		diva_os_wait(10);
-	}
-	if (!IoAdapter->IrqCount) {
-		DBG_ERR(
-			("A: A(%d) interrupt test failed",
-			 IoAdapter->ANum))
-			IoAdapter->Initialized = 0;
-		IoAdapter->stop(IoAdapter);
-		return (-1);
-	}
-
-	IoAdapter->Properties.Features = (word) features;
-	diva_xdi_display_adapter_features(IoAdapter->ANum);
-	DBG_LOG(("A(%d) BRI adapter successfully started", IoAdapter->ANum))
-		/*
-		  Register with DIDD
-		*/
-		diva_xdi_didd_register_adapter(IoAdapter->ANum);
-
-	return (0);
-}
-
-static void diva_bri_clear_interrupts(diva_os_xdi_adapter_t *a)
-{
-	PISDN_ADAPTER IoAdapter = &a->xdi_adapter;
-
-	/*
-	  clear any pending interrupt
-	*/
-	IoAdapter->disIrq(IoAdapter);
-
-	IoAdapter->tst_irq(&IoAdapter->a);
-	IoAdapter->clr_irq(&IoAdapter->a);
-	IoAdapter->tst_irq(&IoAdapter->a);
-
-	/*
-	  kill pending dpcs
-	*/
-	diva_os_cancel_soft_isr(&IoAdapter->req_soft_isr);
-	diva_os_cancel_soft_isr(&IoAdapter->isr_soft_isr);
-}
-
-/*
-**  Stop card
-*/
-static int diva_bri_stop_adapter(diva_os_xdi_adapter_t *a)
-{
-	PISDN_ADAPTER IoAdapter = &a->xdi_adapter;
-	int i = 100;
-
-	if (!IoAdapter->port) {
-		return (-1);
-	}
-	if (!IoAdapter->Initialized) {
-		DBG_ERR(("A: A(%d) can't stop BRI adapter - not running",
-			 IoAdapter->ANum))
-			return (-1);	/* nothing to stop */
-	}
-	IoAdapter->Initialized = 0;
-
-	/*
-	  Disconnect Adapter from DIDD
-	*/
-	diva_xdi_didd_remove_adapter(IoAdapter->ANum);
-
-	/*
-	  Stop interrupts
-	*/
-	a->clear_interrupts_proc = diva_bri_clear_interrupts;
-	IoAdapter->a.ReadyInt = 1;
-	IoAdapter->a.ram_inc(&IoAdapter->a, &PR_RAM->ReadyInt);
-	do {
-		diva_os_sleep(10);
-	} while (i-- && a->clear_interrupts_proc);
-	if (a->clear_interrupts_proc) {
-		diva_bri_clear_interrupts(a);
-		a->clear_interrupts_proc = NULL;
-		DBG_ERR(("A: A(%d) no final interrupt from BRI adapter",
-			 IoAdapter->ANum))
-			}
-	IoAdapter->a.ReadyInt = 0;
-
-	/*
-	  Stop and reset adapter
-	*/
-	IoAdapter->stop(IoAdapter);
-
-	return (0);
-}
diff --git a/drivers/isdn/hardware/eicon/os_bri.h b/drivers/isdn/hardware/eicon/os_bri.h
deleted file mode 100644
index 37c92cc53ded..000000000000
--- a/drivers/isdn/hardware/eicon/os_bri.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: os_bri.h,v 1.1.2.2 2001/02/08 12:25:44 armin Exp $ */
-
-#ifndef __DIVA_OS_BRI_REV_1_H__
-#define __DIVA_OS_BRI_REV_1_H__
-
-int diva_bri_init_card(diva_os_xdi_adapter_t *a);
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/os_capi.h b/drivers/isdn/hardware/eicon/os_capi.h
deleted file mode 100644
index e72394b95d50..000000000000
--- a/drivers/isdn/hardware/eicon/os_capi.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* $Id: os_capi.h,v 1.7 2003/04/12 21:40:49 schindler Exp $
- *
- * ISDN interface module for Eicon active cards DIVA.
- * CAPI Interface OS include files
- *
- * Copyright 2000-2003 by Armin Schindler (mac@melware.de)
- * Copyright 2000-2003 Cytronics & Melware (info@melware.de)
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#ifndef __OS_CAPI_H__
-#define __OS_CAPI_H__
-
-#include <linux/capi.h>
-#include <linux/kernelcapi.h>
-#include <linux/isdn/capiutil.h>
-#include <linux/isdn/capilli.h>
-
-#endif /* __OS_CAPI_H__ */
diff --git a/drivers/isdn/hardware/eicon/os_pri.c b/drivers/isdn/hardware/eicon/os_pri.c
deleted file mode 100644
index b20f1fb89d14..000000000000
--- a/drivers/isdn/hardware/eicon/os_pri.c
+++ /dev/null
@@ -1,1053 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* $Id: os_pri.c,v 1.32 2004/03/21 17:26:01 armin Exp $ */
-
-#include "platform.h"
-#include "debuglib.h"
-#include "cardtype.h"
-#include "pc.h"
-#include "pr_pc.h"
-#include "di_defs.h"
-#include "dsp_defs.h"
-#include "di.h"
-#include "io.h"
-
-#include "xdi_msg.h"
-#include "xdi_adapter.h"
-#include "os_pri.h"
-#include "diva_pci.h"
-#include "mi_pc.h"
-#include "pc_maint.h"
-#include "dsp_tst.h"
-#include "diva_dma.h"
-#include "dsrv_pri.h"
-
-/* --------------------------------------------------------------------------
-   OS Dependent part of XDI driver for DIVA PRI Adapter
-
-   DSP detection/validation by Anthony Booth (Eicon Networks, www.eicon.com)
-   -------------------------------------------------------------------------- */
-
-#define DIVA_PRI_NO_PCI_BIOS_WORKAROUND 1
-
-extern int diva_card_read_xlog(diva_os_xdi_adapter_t *a);
-
-/*
-**  IMPORTS
-*/
-extern void prepare_pri_functions(PISDN_ADAPTER IoAdapter);
-extern void prepare_pri2_functions(PISDN_ADAPTER IoAdapter);
-extern void diva_xdi_display_adapter_features(int card);
-
-static int diva_pri_cleanup_adapter(diva_os_xdi_adapter_t *a);
-static int diva_pri_cmd_card_proc(struct _diva_os_xdi_adapter *a,
-				  diva_xdi_um_cfg_cmd_t *cmd, int length);
-static int pri_get_serial_number(diva_os_xdi_adapter_t *a);
-static int diva_pri_stop_adapter(diva_os_xdi_adapter_t *a);
-static dword diva_pri_detect_dsps(diva_os_xdi_adapter_t *a);
-
-/*
-**  Check card revision
-*/
-static int pri_is_rev_2_card(int card_ordinal)
-{
-	switch (card_ordinal) {
-	case CARDTYPE_DIVASRV_P_30M_V2_PCI:
-	case CARDTYPE_DIVASRV_VOICE_P_30M_V2_PCI:
-		return (1);
-	}
-	return (0);
-}
-
-static void diva_pri_set_addresses(diva_os_xdi_adapter_t *a)
-{
-	a->resources.pci.mem_type_id[MEM_TYPE_ADDRESS] = 0;
-	a->resources.pci.mem_type_id[MEM_TYPE_CONTROL] = 2;
-	a->resources.pci.mem_type_id[MEM_TYPE_CONFIG] = 4;
-	a->resources.pci.mem_type_id[MEM_TYPE_RAM] = 0;
-	a->resources.pci.mem_type_id[MEM_TYPE_RESET] = 2;
-	a->resources.pci.mem_type_id[MEM_TYPE_CFG] = 4;
-	a->resources.pci.mem_type_id[MEM_TYPE_PROM] = 3;
-
-	a->xdi_adapter.Address = a->resources.pci.addr[0];
-	a->xdi_adapter.Control = a->resources.pci.addr[2];
-	a->xdi_adapter.Config = a->resources.pci.addr[4];
-
-	a->xdi_adapter.ram = a->resources.pci.addr[0];
-	a->xdi_adapter.ram += MP_SHARED_RAM_OFFSET;
-
-	a->xdi_adapter.reset = a->resources.pci.addr[2];
-	a->xdi_adapter.reset += MP_RESET;
-
-	a->xdi_adapter.cfg = a->resources.pci.addr[4];
-	a->xdi_adapter.cfg += MP_IRQ_RESET;
-
-	a->xdi_adapter.sdram_bar = a->resources.pci.bar[0];
-
-	a->xdi_adapter.prom = a->resources.pci.addr[3];
-}
-
-/*
-**  BAR0 - SDRAM, MP_MEMORY_SIZE, MP2_MEMORY_SIZE by Rev.2
-**  BAR1 - DEVICES,				0x1000
-**  BAR2 - CONTROL (REG), 0x2000
-**  BAR3 - FLASH (REG),		0x8000
-**  BAR4 - CONFIG (CFG),	0x1000
-*/
-int diva_pri_init_card(diva_os_xdi_adapter_t *a)
-{
-	int bar = 0;
-	int pri_rev_2;
-	unsigned long bar_length[5] = {
-		MP_MEMORY_SIZE,
-		0x1000,
-		0x2000,
-		0x8000,
-		0x1000
-	};
-
-	pri_rev_2 = pri_is_rev_2_card(a->CardOrdinal);
-
-	if (pri_rev_2) {
-		bar_length[0] = MP2_MEMORY_SIZE;
-	}
-	/*
-	  Set properties
-	*/
-	a->xdi_adapter.Properties = CardProperties[a->CardOrdinal];
-	DBG_LOG(("Load %s", a->xdi_adapter.Properties.Name))
-
-		/*
-		  First initialization step: get and check hardware resoures.
-		  Do not map resources and do not acecess card at this step
-		*/
-		for (bar = 0; bar < 5; bar++) {
-			a->resources.pci.bar[bar] =
-				divasa_get_pci_bar(a->resources.pci.bus,
-						   a->resources.pci.func, bar,
-						   a->resources.pci.hdev);
-			if (!a->resources.pci.bar[bar]
-			    || (a->resources.pci.bar[bar] == 0xFFFFFFF0)) {
-				DBG_ERR(("A: invalid bar[%d]=%08x", bar,
-					 a->resources.pci.bar[bar]))
-					return (-1);
-			}
-		}
-	a->resources.pci.irq =
-		(byte) divasa_get_pci_irq(a->resources.pci.bus,
-					  a->resources.pci.func,
-					  a->resources.pci.hdev);
-	if (!a->resources.pci.irq) {
-		DBG_ERR(("A: invalid irq"));
-		return (-1);
-	}
-
-	/*
-	  Map all BAR's
-	*/
-	for (bar = 0; bar < 5; bar++) {
-		a->resources.pci.addr[bar] =
-			divasa_remap_pci_bar(a, bar, a->resources.pci.bar[bar],
-					     bar_length[bar]);
-		if (!a->resources.pci.addr[bar]) {
-			DBG_ERR(("A: A(%d), can't map bar[%d]",
-				 a->controller, bar))
-				diva_pri_cleanup_adapter(a);
-			return (-1);
-		}
-	}
-
-	/*
-	  Set all memory areas
-	*/
-	diva_pri_set_addresses(a);
-
-	/*
-	  Get Serial Number of this adapter
-	*/
-	if (pri_get_serial_number(a)) {
-		dword serNo;
-		serNo = a->resources.pci.bar[1] & 0xffff0000;
-		serNo |= ((dword) a->resources.pci.bus) << 8;
-		serNo += (a->resources.pci.func + a->controller + 1);
-		a->xdi_adapter.serialNo = serNo & ~0xFF000000;
-		DBG_ERR(("A: A(%d) can't get Serial Number, generated serNo=%ld",
-			 a->controller, a->xdi_adapter.serialNo))
-			}
-
-
-	/*
-	  Initialize os objects
-	*/
-	if (diva_os_initialize_spin_lock(&a->xdi_adapter.isr_spin_lock, "isr")) {
-		diva_pri_cleanup_adapter(a);
-		return (-1);
-	}
-	if (diva_os_initialize_spin_lock
-	    (&a->xdi_adapter.data_spin_lock, "data")) {
-		diva_pri_cleanup_adapter(a);
-		return (-1);
-	}
-
-	strcpy(a->xdi_adapter.req_soft_isr.dpc_thread_name, "kdivasprid");
-
-	if (diva_os_initialize_soft_isr(&a->xdi_adapter.req_soft_isr,
-					DIDpcRoutine, &a->xdi_adapter)) {
-		diva_pri_cleanup_adapter(a);
-		return (-1);
-	}
-
-	/*
-	  Do not initialize second DPC - only one thread will be created
-	*/
-	a->xdi_adapter.isr_soft_isr.object =
-		a->xdi_adapter.req_soft_isr.object;
-
-	/*
-	  Next step of card initialization:
-	  set up all interface pointers
-	*/
-	a->xdi_adapter.Channels = CardProperties[a->CardOrdinal].Channels;
-	a->xdi_adapter.e_max = CardProperties[a->CardOrdinal].E_info;
-
-	a->xdi_adapter.e_tbl =
-		diva_os_malloc(0, a->xdi_adapter.e_max * sizeof(E_INFO));
-	if (!a->xdi_adapter.e_tbl) {
-		diva_pri_cleanup_adapter(a);
-		return (-1);
-	}
-	memset(a->xdi_adapter.e_tbl, 0x00, a->xdi_adapter.e_max * sizeof(E_INFO));
-
-	a->xdi_adapter.a.io = &a->xdi_adapter;
-	a->xdi_adapter.DIRequest = request;
-	a->interface.cleanup_adapter_proc = diva_pri_cleanup_adapter;
-	a->interface.cmd_proc = diva_pri_cmd_card_proc;
-
-	if (pri_rev_2) {
-		prepare_pri2_functions(&a->xdi_adapter);
-	} else {
-		prepare_pri_functions(&a->xdi_adapter);
-	}
-
-	a->dsp_mask = diva_pri_detect_dsps(a);
-
-	/*
-	  Allocate DMA map
-	*/
-	if (pri_rev_2) {
-		diva_init_dma_map(a->resources.pci.hdev,
-				  (struct _diva_dma_map_entry **) &a->xdi_adapter.dma_map, 32);
-	}
-
-	/*
-	  Set IRQ handler
-	*/
-	a->xdi_adapter.irq_info.irq_nr = a->resources.pci.irq;
-	sprintf(a->xdi_adapter.irq_info.irq_name,
-		"DIVA PRI %ld", (long) a->xdi_adapter.serialNo);
-
-	if (diva_os_register_irq(a, a->xdi_adapter.irq_info.irq_nr,
-				 a->xdi_adapter.irq_info.irq_name)) {
-		diva_pri_cleanup_adapter(a);
-		return (-1);
-	}
-	a->xdi_adapter.irq_info.registered = 1;
-
-	diva_log_info("%s IRQ:%d SerNo:%d", a->xdi_adapter.Properties.Name,
-		      a->resources.pci.irq, a->xdi_adapter.serialNo);
-
-	return (0);
-}
-
-static int diva_pri_cleanup_adapter(diva_os_xdi_adapter_t *a)
-{
-	int bar = 0;
-
-	/*
-	  Stop Adapter if adapter is running
-	*/
-	if (a->xdi_adapter.Initialized) {
-		diva_pri_stop_adapter(a);
-	}
-
-	/*
-	  Remove ISR Handler
-	*/
-	if (a->xdi_adapter.irq_info.registered) {
-		diva_os_remove_irq(a, a->xdi_adapter.irq_info.irq_nr);
-	}
-	a->xdi_adapter.irq_info.registered = 0;
-
-	/*
-	  Step 1: unmap all BAR's, if any was mapped
-	*/
-	for (bar = 0; bar < 5; bar++) {
-		if (a->resources.pci.bar[bar]
-		    && a->resources.pci.addr[bar]) {
-			divasa_unmap_pci_bar(a->resources.pci.addr[bar]);
-			a->resources.pci.bar[bar] = 0;
-			a->resources.pci.addr[bar] = NULL;
-		}
-	}
-
-	/*
-	  Free OS objects
-	*/
-	diva_os_cancel_soft_isr(&a->xdi_adapter.isr_soft_isr);
-	diva_os_cancel_soft_isr(&a->xdi_adapter.req_soft_isr);
-
-	diva_os_remove_soft_isr(&a->xdi_adapter.req_soft_isr);
-	a->xdi_adapter.isr_soft_isr.object = NULL;
-
-	diva_os_destroy_spin_lock(&a->xdi_adapter.isr_spin_lock, "rm");
-	diva_os_destroy_spin_lock(&a->xdi_adapter.data_spin_lock, "rm");
-
-	/*
-	  Free memory accupied by XDI adapter
-	*/
-	if (a->xdi_adapter.e_tbl) {
-		diva_os_free(0, a->xdi_adapter.e_tbl);
-		a->xdi_adapter.e_tbl = NULL;
-	}
-	a->xdi_adapter.Channels = 0;
-	a->xdi_adapter.e_max = 0;
-
-
-	/*
-	  Free adapter DMA map
-	*/
-	diva_free_dma_map(a->resources.pci.hdev,
-			  (struct _diva_dma_map_entry *) a->xdi_adapter.
-			  dma_map);
-	a->xdi_adapter.dma_map = NULL;
-
-
-	/*
-	  Detach this adapter from debug driver
-	*/
-
-	return (0);
-}
-
-/*
-**  Activate On Board Boot Loader
-*/
-static int diva_pri_reset_adapter(PISDN_ADAPTER IoAdapter)
-{
-	dword i;
-	struct mp_load __iomem *boot;
-
-	if (!IoAdapter->Address || !IoAdapter->reset) {
-		return (-1);
-	}
-	if (IoAdapter->Initialized) {
-		DBG_ERR(("A: A(%d) can't reset PRI adapter - please stop first",
-			 IoAdapter->ANum))
-			return (-1);
-	}
-
-	boot = (struct mp_load __iomem *) DIVA_OS_MEM_ATTACH_ADDRESS(IoAdapter);
-	WRITE_DWORD(&boot->err, 0);
-	DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, boot);
-
-	IoAdapter->rstFnc(IoAdapter);
-
-	diva_os_wait(10);
-
-	boot = (struct mp_load __iomem *) DIVA_OS_MEM_ATTACH_ADDRESS(IoAdapter);
-	i = READ_DWORD(&boot->live);
-
-	diva_os_wait(10);
-	if (i == READ_DWORD(&boot->live)) {
-		DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, boot);
-		DBG_ERR(("A: A(%d) CPU on PRI %ld is not alive!",
-			 IoAdapter->ANum, IoAdapter->serialNo))
-			return (-1);
-	}
-	if (READ_DWORD(&boot->err)) {
-		DBG_ERR(("A: A(%d) PRI %ld Board Selftest failed, error=%08lx",
-			 IoAdapter->ANum, IoAdapter->serialNo,
-			 READ_DWORD(&boot->err)))
-			DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, boot);
-		return (-1);
-	}
-	DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, boot);
-
-	/*
-	  Forget all outstanding entities
-	*/
-	IoAdapter->e_count = 0;
-	if (IoAdapter->e_tbl) {
-		memset(IoAdapter->e_tbl, 0x00,
-		       IoAdapter->e_max * sizeof(E_INFO));
-	}
-	IoAdapter->head = 0;
-	IoAdapter->tail = 0;
-	IoAdapter->assign = 0;
-	IoAdapter->trapped = 0;
-
-	memset(&IoAdapter->a.IdTable[0], 0x00,
-	       sizeof(IoAdapter->a.IdTable));
-	memset(&IoAdapter->a.IdTypeTable[0], 0x00,
-	       sizeof(IoAdapter->a.IdTypeTable));
-	memset(&IoAdapter->a.FlowControlIdTable[0], 0x00,
-	       sizeof(IoAdapter->a.FlowControlIdTable));
-	memset(&IoAdapter->a.FlowControlSkipTable[0], 0x00,
-	       sizeof(IoAdapter->a.FlowControlSkipTable));
-	memset(&IoAdapter->a.misc_flags_table[0], 0x00,
-	       sizeof(IoAdapter->a.misc_flags_table));
-	memset(&IoAdapter->a.rx_stream[0], 0x00,
-	       sizeof(IoAdapter->a.rx_stream));
-	memset(&IoAdapter->a.tx_stream[0], 0x00,
-	       sizeof(IoAdapter->a.tx_stream));
-	memset(&IoAdapter->a.tx_pos[0], 0x00, sizeof(IoAdapter->a.tx_pos));
-	memset(&IoAdapter->a.rx_pos[0], 0x00, sizeof(IoAdapter->a.rx_pos));
-
-	return (0);
-}
-
-static int
-diva_pri_write_sdram_block(PISDN_ADAPTER IoAdapter,
-			   dword address,
-			   const byte *data, dword length, dword limit)
-{
-	byte __iomem *p = DIVA_OS_MEM_ATTACH_ADDRESS(IoAdapter);
-	byte __iomem *mem = p;
-
-	if (((address + length) >= limit) || !mem) {
-		DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, p);
-		DBG_ERR(("A: A(%d) write PRI address=0x%08lx",
-			 IoAdapter->ANum, address + length))
-			return (-1);
-	}
-	mem += address;
-
-	/* memcpy_toio(), maybe? */
-	while (length--) {
-		WRITE_BYTE(mem++, *data++);
-	}
-
-	DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, p);
-	return (0);
-}
-
-static int
-diva_pri_start_adapter(PISDN_ADAPTER IoAdapter,
-		       dword start_address, dword features)
-{
-	dword i;
-	int started = 0;
-	byte __iomem *p;
-	struct mp_load __iomem *boot = (struct mp_load __iomem *) DIVA_OS_MEM_ATTACH_ADDRESS(IoAdapter);
-	ADAPTER *a = &IoAdapter->a;
-
-	if (IoAdapter->Initialized) {
-		DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, boot);
-		DBG_ERR(("A: A(%d) pri_start_adapter, adapter already running",
-			 IoAdapter->ANum))
-			return (-1);
-	}
-	if (!boot) {
-		DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, boot);
-		DBG_ERR(("A: PRI %ld can't start, adapter not mapped",
-			 IoAdapter->serialNo))
-			return (-1);
-	}
-
-	sprintf(IoAdapter->Name, "A(%d)", (int) IoAdapter->ANum);
-	DBG_LOG(("A(%d) start PRI at 0x%08lx", IoAdapter->ANum,
-		 start_address))
-
-		WRITE_DWORD(&boot->addr, start_address);
-	WRITE_DWORD(&boot->cmd, 3);
-
-	for (i = 0; i < 300; ++i) {
-		diva_os_wait(10);
-		if ((READ_DWORD(&boot->signature) >> 16) == 0x4447) {
-			DBG_LOG(("A(%d) Protocol startup time %d.%02d seconds",
-				 IoAdapter->ANum, (i / 100), (i % 100)))
-				started = 1;
-			break;
-		}
-	}
-
-	if (!started) {
-		byte __iomem *p = (byte __iomem *)boot;
-		dword TrapId;
-		dword debug;
-		TrapId = READ_DWORD(&p[0x80]);
-		debug = READ_DWORD(&p[0x1c]);
-		DBG_ERR(("A(%d) Adapter start failed 0x%08lx, TrapId=%08lx, debug=%08lx",
-			 IoAdapter->ANum, READ_DWORD(&boot->signature),
-			 TrapId, debug))
-			DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, boot);
-		if (IoAdapter->trapFnc) {
-			(*(IoAdapter->trapFnc)) (IoAdapter);
-		}
-		IoAdapter->stop(IoAdapter);
-		return (-1);
-	}
-	DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, boot);
-
-	IoAdapter->Initialized = true;
-
-	/*
-	  Check Interrupt
-	*/
-	IoAdapter->IrqCount = 0;
-	p = DIVA_OS_MEM_ATTACH_CFG(IoAdapter);
-	WRITE_DWORD(p, (dword)~0x03E00000);
-	DIVA_OS_MEM_DETACH_CFG(IoAdapter, p);
-	a->ReadyInt = 1;
-	a->ram_out(a, &PR_RAM->ReadyInt, 1);
-
-	for (i = 100; !IoAdapter->IrqCount && (i-- > 0); diva_os_wait(10));
-
-	if (!IoAdapter->IrqCount) {
-		DBG_ERR(("A: A(%d) interrupt test failed",
-			 IoAdapter->ANum))
-			IoAdapter->Initialized = false;
-		IoAdapter->stop(IoAdapter);
-		return (-1);
-	}
-
-	IoAdapter->Properties.Features = (word) features;
-
-	diva_xdi_display_adapter_features(IoAdapter->ANum);
-
-	DBG_LOG(("A(%d) PRI adapter successfully started", IoAdapter->ANum))
-		/*
-		  Register with DIDD
-		*/
-		diva_xdi_didd_register_adapter(IoAdapter->ANum);
-
-	return (0);
-}
-
-static void diva_pri_clear_interrupts(diva_os_xdi_adapter_t *a)
-{
-	PISDN_ADAPTER IoAdapter = &a->xdi_adapter;
-
-	/*
-	  clear any pending interrupt
-	*/
-	IoAdapter->disIrq(IoAdapter);
-
-	IoAdapter->tst_irq(&IoAdapter->a);
-	IoAdapter->clr_irq(&IoAdapter->a);
-	IoAdapter->tst_irq(&IoAdapter->a);
-
-	/*
-	  kill pending dpcs
-	*/
-	diva_os_cancel_soft_isr(&IoAdapter->req_soft_isr);
-	diva_os_cancel_soft_isr(&IoAdapter->isr_soft_isr);
-}
-
-/*
-**  Stop Adapter, but do not unmap/unregister - adapter
-**  will be restarted later
-*/
-static int diva_pri_stop_adapter(diva_os_xdi_adapter_t *a)
-{
-	PISDN_ADAPTER IoAdapter = &a->xdi_adapter;
-	int i = 100;
-
-	if (!IoAdapter->ram) {
-		return (-1);
-	}
-	if (!IoAdapter->Initialized) {
-		DBG_ERR(("A: A(%d) can't stop PRI adapter - not running",
-			 IoAdapter->ANum))
-			return (-1);	/* nothing to stop */
-	}
-	IoAdapter->Initialized = 0;
-
-	/*
-	  Disconnect Adapter from DIDD
-	*/
-	diva_xdi_didd_remove_adapter(IoAdapter->ANum);
-
-	/*
-	  Stop interrupts
-	*/
-	a->clear_interrupts_proc = diva_pri_clear_interrupts;
-	IoAdapter->a.ReadyInt = 1;
-	IoAdapter->a.ram_inc(&IoAdapter->a, &PR_RAM->ReadyInt);
-	do {
-		diva_os_sleep(10);
-	} while (i-- && a->clear_interrupts_proc);
-
-	if (a->clear_interrupts_proc) {
-		diva_pri_clear_interrupts(a);
-		a->clear_interrupts_proc = NULL;
-		DBG_ERR(("A: A(%d) no final interrupt from PRI adapter",
-			 IoAdapter->ANum))
-			}
-	IoAdapter->a.ReadyInt = 0;
-
-	/*
-	  Stop and reset adapter
-	*/
-	IoAdapter->stop(IoAdapter);
-
-	return (0);
-}
-
-/*
-**  Process commands form configuration/download framework and from
-**  user mode
-**
-**  return 0 on success
-*/
-static int
-diva_pri_cmd_card_proc(struct _diva_os_xdi_adapter *a,
-		       diva_xdi_um_cfg_cmd_t *cmd, int length)
-{
-	int ret = -1;
-
-	if (cmd->adapter != a->controller) {
-		DBG_ERR(("A: pri_cmd, invalid controller=%d != %d",
-			 cmd->adapter, a->controller))
-			return (-1);
-	}
-
-	switch (cmd->command) {
-	case DIVA_XDI_UM_CMD_GET_CARD_ORDINAL:
-		a->xdi_mbox.data_length = sizeof(dword);
-		a->xdi_mbox.data =
-			diva_os_malloc(0, a->xdi_mbox.data_length);
-		if (a->xdi_mbox.data) {
-			*(dword *) a->xdi_mbox.data =
-				(dword) a->CardOrdinal;
-			a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-			ret = 0;
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_GET_SERIAL_NR:
-		a->xdi_mbox.data_length = sizeof(dword);
-		a->xdi_mbox.data =
-			diva_os_malloc(0, a->xdi_mbox.data_length);
-		if (a->xdi_mbox.data) {
-			*(dword *) a->xdi_mbox.data =
-				(dword) a->xdi_adapter.serialNo;
-			a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-			ret = 0;
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_GET_PCI_HW_CONFIG:
-		a->xdi_mbox.data_length = sizeof(dword) * 9;
-		a->xdi_mbox.data =
-			diva_os_malloc(0, a->xdi_mbox.data_length);
-		if (a->xdi_mbox.data) {
-			int i;
-			dword *data = (dword *) a->xdi_mbox.data;
-
-			for (i = 0; i < 8; i++) {
-				*data++ = a->resources.pci.bar[i];
-			}
-			*data++ = (dword) a->resources.pci.irq;
-			a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-			ret = 0;
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_RESET_ADAPTER:
-		ret = diva_pri_reset_adapter(&a->xdi_adapter);
-		break;
-
-	case DIVA_XDI_UM_CMD_WRITE_SDRAM_BLOCK:
-		ret = diva_pri_write_sdram_block(&a->xdi_adapter,
-						 cmd->command_data.
-						 write_sdram.offset,
-						 (byte *)&cmd[1],
-						 cmd->command_data.
-						 write_sdram.length,
-						 pri_is_rev_2_card(a->
-								   CardOrdinal)
-						 ? MP2_MEMORY_SIZE :
-						 MP_MEMORY_SIZE);
-		break;
-
-	case DIVA_XDI_UM_CMD_STOP_ADAPTER:
-		ret = diva_pri_stop_adapter(a);
-		break;
-
-	case DIVA_XDI_UM_CMD_START_ADAPTER:
-		ret = diva_pri_start_adapter(&a->xdi_adapter,
-					     cmd->command_data.start.
-					     offset,
-					     cmd->command_data.start.
-					     features);
-		break;
-
-	case DIVA_XDI_UM_CMD_SET_PROTOCOL_FEATURES:
-		a->xdi_adapter.features =
-			cmd->command_data.features.features;
-		a->xdi_adapter.a.protocol_capabilities =
-			a->xdi_adapter.features;
-		DBG_TRC(("Set raw protocol features (%08x)",
-			 a->xdi_adapter.features))
-			ret = 0;
-		break;
-
-	case DIVA_XDI_UM_CMD_GET_CARD_STATE:
-		a->xdi_mbox.data_length = sizeof(dword);
-		a->xdi_mbox.data =
-			diva_os_malloc(0, a->xdi_mbox.data_length);
-		if (a->xdi_mbox.data) {
-			dword *data = (dword *) a->xdi_mbox.data;
-			if (!a->xdi_adapter.ram ||
-			    !a->xdi_adapter.reset ||
-			    !a->xdi_adapter.cfg) {
-				*data = 3;
-			} else if (a->xdi_adapter.trapped) {
-				*data = 2;
-			} else if (a->xdi_adapter.Initialized) {
-				*data = 1;
-			} else {
-				*data = 0;
-			}
-			a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-			ret = 0;
-		}
-		break;
-
-	case DIVA_XDI_UM_CMD_READ_XLOG_ENTRY:
-		ret = diva_card_read_xlog(a);
-		break;
-
-	case DIVA_XDI_UM_CMD_READ_SDRAM:
-		if (a->xdi_adapter.Address) {
-			if (
-				(a->xdi_mbox.data_length =
-				 cmd->command_data.read_sdram.length)) {
-				if (
-					(a->xdi_mbox.data_length +
-					 cmd->command_data.read_sdram.offset) <
-					a->xdi_adapter.MemorySize) {
-					a->xdi_mbox.data =
-						diva_os_malloc(0,
-							       a->xdi_mbox.
-							       data_length);
-					if (a->xdi_mbox.data) {
-						byte __iomem *p = DIVA_OS_MEM_ATTACH_ADDRESS(&a->xdi_adapter);
-						byte __iomem *src = p;
-						byte *dst = a->xdi_mbox.data;
-						dword len = a->xdi_mbox.data_length;
-
-						src += cmd->command_data.read_sdram.offset;
-
-						while (len--) {
-							*dst++ = READ_BYTE(src++);
-						}
-						a->xdi_mbox.status = DIVA_XDI_MBOX_BUSY;
-						DIVA_OS_MEM_DETACH_ADDRESS(&a->xdi_adapter, p);
-						ret = 0;
-					}
-				}
-			}
-		}
-		break;
-
-	default:
-		DBG_ERR(("A: A(%d) invalid cmd=%d", a->controller,
-			 cmd->command))
-			}
-
-	return (ret);
-}
-
-/*
-**  Get Serial Number
-*/
-static int pri_get_serial_number(diva_os_xdi_adapter_t *a)
-{
-	byte data[64];
-	int i;
-	dword len = sizeof(data);
-	volatile byte __iomem *config;
-	volatile byte __iomem *flash;
-	byte c;
-
-/*
- *  First set some GT6401x config registers before accessing the BOOT-ROM
- */
-	config = DIVA_OS_MEM_ATTACH_CONFIG(&a->xdi_adapter);
-	c = READ_BYTE(&config[0xc3c]);
-	if (!(c & 0x08)) {
-		WRITE_BYTE(&config[0xc3c], c);	/* Base Address enable register */
-	}
-	WRITE_BYTE(&config[LOW_BOOTCS_DREG], 0x00);
-	WRITE_BYTE(&config[HI_BOOTCS_DREG], 0xFF);
-	DIVA_OS_MEM_DETACH_CONFIG(&a->xdi_adapter, config);
-/*
- *  Read only the last 64 bytes of manufacturing data
- */
-	memset(data, '\0', len);
-	flash = DIVA_OS_MEM_ATTACH_PROM(&a->xdi_adapter);
-	for (i = 0; i < len; i++) {
-		data[i] = READ_BYTE(&flash[0x8000 - len + i]);
-	}
-	DIVA_OS_MEM_DETACH_PROM(&a->xdi_adapter, flash);
-
-	config = DIVA_OS_MEM_ATTACH_CONFIG(&a->xdi_adapter);
-	WRITE_BYTE(&config[LOW_BOOTCS_DREG], 0xFC);	/* Disable FLASH EPROM access */
-	WRITE_BYTE(&config[HI_BOOTCS_DREG], 0xFF);
-	DIVA_OS_MEM_DETACH_CONFIG(&a->xdi_adapter, config);
-
-	if (memcmp(&data[48], "DIVAserverPR", 12)) {
-#if !defined(DIVA_PRI_NO_PCI_BIOS_WORKAROUND)	/* { */
-		word cmd = 0, cmd_org;
-		void *addr;
-		dword addr1, addr3, addr4;
-		byte Bus, Slot;
-		void *hdev;
-		addr4 = a->resources.pci.bar[4];
-		addr3 = a->resources.pci.bar[3];	/* flash  */
-		addr1 = a->resources.pci.bar[1];	/* unused */
-
-		DBG_ERR(("A: apply Compaq BIOS workaround"))
-			DBG_LOG(("%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x",
-				 data[0], data[1], data[2], data[3],
-				 data[4], data[5], data[6], data[7]))
-
-			Bus = a->resources.pci.bus;
-		Slot = a->resources.pci.func;
-		hdev = a->resources.pci.hdev;
-		PCIread(Bus, Slot, 0x04, &cmd_org, sizeof(cmd_org), hdev);
-		PCIwrite(Bus, Slot, 0x04, &cmd, sizeof(cmd), hdev);
-
-		PCIwrite(Bus, Slot, 0x14, &addr4, sizeof(addr4), hdev);
-		PCIwrite(Bus, Slot, 0x20, &addr1, sizeof(addr1), hdev);
-
-		PCIwrite(Bus, Slot, 0x04, &cmd_org, sizeof(cmd_org), hdev);
-
-		addr = a->resources.pci.addr[1];
-		a->resources.pci.addr[1] = a->resources.pci.addr[4];
-		a->resources.pci.addr[4] = addr;
-
-		addr1 = a->resources.pci.bar[1];
-		a->resources.pci.bar[1] = a->resources.pci.bar[4];
-		a->resources.pci.bar[4] = addr1;
-
-		/*
-		  Try to read Flash again
-		*/
-		len = sizeof(data);
-
-		config = DIVA_OS_MEM_ATTACH_CONFIG(&a->xdi_adapter);
-		if (!(config[0xc3c] & 0x08)) {
-			config[0xc3c] |= 0x08;	/* Base Address enable register */
-		}
-		config[LOW_BOOTCS_DREG] = 0x00;
-		config[HI_BOOTCS_DREG] = 0xFF;
-		DIVA_OS_MEM_DETACH_CONFIG(&a->xdi_adapter, config);
-
-		memset(data, '\0', len);
-		flash = DIVA_OS_MEM_ATTACH_PROM(&a->xdi_adapter);
-		for (i = 0; i < len; i++) {
-			data[i] = flash[0x8000 - len + i];
-		}
-		DIVA_OS_MEM_ATTACH_PROM(&a->xdi_adapter, flash);
-		config = DIVA_OS_MEM_ATTACH_CONFIG(&a->xdi_adapter);
-		config[LOW_BOOTCS_DREG] = 0xFC;
-		config[HI_BOOTCS_DREG] = 0xFF;
-		DIVA_OS_MEM_DETACH_CONFIG(&a->xdi_adapter, config);
-
-		if (memcmp(&data[48], "DIVAserverPR", 12)) {
-			DBG_ERR(("A: failed to read serial number"))
-				DBG_LOG(("%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x",
-					 data[0], data[1], data[2], data[3],
-					 data[4], data[5], data[6], data[7]))
-				return (-1);
-		}
-#else				/* } { */
-		DBG_ERR(("A: failed to read DIVA signature word"))
-			DBG_LOG(("%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x",
-				 data[0], data[1], data[2], data[3],
-				 data[4], data[5], data[6], data[7]))
-			DBG_LOG(("%02x:%02x:%02x:%02x", data[47], data[46],
-				 data[45], data[44]))
-#endif				/* } */
-			}
-
-	a->xdi_adapter.serialNo =
-		(data[47] << 24) | (data[46] << 16) | (data[45] << 8) |
-		data[44];
-	if (!a->xdi_adapter.serialNo
-	    || (a->xdi_adapter.serialNo == 0xffffffff)) {
-		a->xdi_adapter.serialNo = 0;
-		DBG_ERR(("A: failed to read serial number"))
-			return (-1);
-	}
-
-	DBG_LOG(("Serial No.          : %ld", a->xdi_adapter.serialNo))
-		DBG_TRC(("Board Revision      : %d.%02d", (int) data[41],
-			 (int) data[40]))
-		DBG_TRC(("PLD revision        : %d.%02d", (int) data[33],
-			 (int) data[32]))
-		DBG_TRC(("Boot loader version : %d.%02d", (int) data[37],
-			 (int) data[36]))
-
-		DBG_TRC(("Manufacturing Date  : %d/%02d/%02d  (yyyy/mm/dd)",
-			 (int) ((data[28] > 90) ? 1900 : 2000) +
-			 (int) data[28], (int) data[29], (int) data[30]))
-
-		return (0);
-}
-
-void diva_os_prepare_pri2_functions(PISDN_ADAPTER IoAdapter)
-{
-}
-
-void diva_os_prepare_pri_functions(PISDN_ADAPTER IoAdapter)
-{
-}
-
-/*
-**  Checks presence of DSP on board
-*/
-static int
-dsp_check_presence(volatile byte __iomem *addr, volatile byte __iomem *data, int dsp)
-{
-	word pattern;
-
-	WRITE_WORD(addr, 0x4000);
-	WRITE_WORD(data, DSP_SIGNATURE_PROBE_WORD);
-
-	WRITE_WORD(addr, 0x4000);
-	pattern = READ_WORD(data);
-
-	if (pattern != DSP_SIGNATURE_PROBE_WORD) {
-		DBG_TRC(("W: DSP[%d] %04x(is) != %04x(should)",
-			 dsp, pattern, DSP_SIGNATURE_PROBE_WORD))
-			return (-1);
-	}
-
-	WRITE_WORD(addr, 0x4000);
-	WRITE_WORD(data, ~DSP_SIGNATURE_PROBE_WORD);
-
-	WRITE_WORD(addr, 0x4000);
-	pattern = READ_WORD(data);
-
-	if (pattern != (word)~DSP_SIGNATURE_PROBE_WORD) {
-		DBG_ERR(("A: DSP[%d] %04x(is) != %04x(should)",
-			 dsp, pattern, (word)~DSP_SIGNATURE_PROBE_WORD))
-			return (-2);
-	}
-
-	DBG_TRC(("DSP[%d] present", dsp))
-
-		return (0);
-}
-
-
-/*
-**  Check if DSP's are present and operating
-**  Information about detected DSP's is returned as bit mask
-**  Bit 0  - DSP1
-**  ...
-**  ...
-**  ...
-**  Bit 29 - DSP30
-*/
-static dword diva_pri_detect_dsps(diva_os_xdi_adapter_t *a)
-{
-	byte __iomem *base;
-	byte __iomem *p;
-	dword ret = 0;
-	dword row_offset[7] = {
-		0x00000000,
-		0x00000800,	/* 1 - ROW 1 */
-		0x00000840,	/* 2 - ROW 2 */
-		0x00001000,	/* 3 - ROW 3 */
-		0x00001040,	/* 4 - ROW 4 */
-		0x00000000	/* 5 - ROW 0 */
-	};
-
-	byte __iomem *dsp_addr_port;
-	byte __iomem *dsp_data_port;
-	byte row_state;
-	int dsp_row = 0, dsp_index, dsp_num;
-
-	if (!a->xdi_adapter.Control || !a->xdi_adapter.reset) {
-		return (0);
-	}
-
-	p = DIVA_OS_MEM_ATTACH_RESET(&a->xdi_adapter);
-	WRITE_BYTE(p, _MP_RISC_RESET | _MP_DSP_RESET);
-	DIVA_OS_MEM_DETACH_RESET(&a->xdi_adapter, p);
-	diva_os_wait(5);
-
-	base = DIVA_OS_MEM_ATTACH_CONTROL(&a->xdi_adapter);
-
-	for (dsp_num = 0; dsp_num < 30; dsp_num++) {
-		dsp_row = dsp_num / 7 + 1;
-		dsp_index = dsp_num % 7;
-
-		dsp_data_port = base;
-		dsp_addr_port = base;
-
-		dsp_data_port += row_offset[dsp_row];
-		dsp_addr_port += row_offset[dsp_row];
-
-		dsp_data_port += (dsp_index * 8);
-		dsp_addr_port += (dsp_index * 8) + 0x80;
-
-		if (!dsp_check_presence
-		    (dsp_addr_port, dsp_data_port, dsp_num + 1)) {
-			ret |= (1 << dsp_num);
-		}
-	}
-	DIVA_OS_MEM_DETACH_CONTROL(&a->xdi_adapter, base);
-
-	p = DIVA_OS_MEM_ATTACH_RESET(&a->xdi_adapter);
-	WRITE_BYTE(p, _MP_RISC_RESET | _MP_LED1 | _MP_LED2);
-	DIVA_OS_MEM_DETACH_RESET(&a->xdi_adapter, p);
-	diva_os_wait(5);
-
-	/*
-	  Verify modules
-	*/
-	for (dsp_row = 0; dsp_row < 4; dsp_row++) {
-		row_state = ((ret >> (dsp_row * 7)) & 0x7F);
-		if (row_state && (row_state != 0x7F)) {
-			for (dsp_index = 0; dsp_index < 7; dsp_index++) {
-				if (!(row_state & (1 << dsp_index))) {
-					DBG_ERR(("A: MODULE[%d]-DSP[%d] failed",
-						 dsp_row + 1,
-						 dsp_index + 1))
-						}
-			}
-		}
-	}
-
-	if (!(ret & 0x10000000)) {
-		DBG_ERR(("A: ON BOARD-DSP[1] failed"))
-			}
-	if (!(ret & 0x20000000)) {
-		DBG_ERR(("A: ON BOARD-DSP[2] failed"))
-			}
-
-	/*
-	  Print module population now
-	*/
-	DBG_LOG(("+-----------------------+"))
-		DBG_LOG(("| DSP MODULE POPULATION |"))
-		DBG_LOG(("+-----------------------+"))
-		DBG_LOG(("|  1  |  2  |  3  |  4  |"))
-		DBG_LOG(("+-----------------------+"))
-		DBG_LOG(("|  %s  |  %s  |  %s  |  %s  |",
-			 ((ret >> (0 * 7)) & 0x7F) ? "Y" : "N",
-			 ((ret >> (1 * 7)) & 0x7F) ? "Y" : "N",
-			 ((ret >> (2 * 7)) & 0x7F) ? "Y" : "N",
-			 ((ret >> (3 * 7)) & 0x7F) ? "Y" : "N"))
-		DBG_LOG(("+-----------------------+"))
-
-		DBG_LOG(("DSP's(present-absent):%08x-%08x", ret,
-			 ~ret & 0x3fffffff))
-
-		return (ret);
-}
diff --git a/drivers/isdn/hardware/eicon/os_pri.h b/drivers/isdn/hardware/eicon/os_pri.h
deleted file mode 100644
index 0e91855b171a..000000000000
--- a/drivers/isdn/hardware/eicon/os_pri.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: os_pri.h,v 1.1.2.2 2001/02/08 12:25:44 armin Exp $ */
-
-#ifndef __DIVA_OS_PRI_REV_1_H__
-#define __DIVA_OS_PRI_REV_1_H__
-
-int diva_pri_init_card(diva_os_xdi_adapter_t *a);
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/pc.h b/drivers/isdn/hardware/eicon/pc.h
deleted file mode 100644
index 329c0c26abfb..000000000000
--- a/drivers/isdn/hardware/eicon/pc.h
+++ /dev/null
@@ -1,738 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef PC_H_INCLUDED  /* { */
-#define PC_H_INCLUDED
-/*------------------------------------------------------------------*/
-/* buffer definition                                                */
-/*------------------------------------------------------------------*/
-typedef struct {
-	word length;          /* length of data/parameter field           */
-	byte P[270];          /* data/parameter field                     */
-} PBUFFER;
-/*------------------------------------------------------------------*/
-/* dual port ram structure                                          */
-/*------------------------------------------------------------------*/
-struct dual
-{
-	byte Req;             /* request register                         */
-	byte ReqId;           /* request task/entity identification       */
-	byte Rc;              /* return code register                     */
-	byte RcId;            /* return code task/entity identification   */
-	byte Ind;             /* Indication register                      */
-	byte IndId;           /* Indication task/entity identification    */
-	byte IMask;           /* Interrupt Mask Flag                      */
-	byte RNR;             /* Receiver Not Ready (set by PC)           */
-	byte XLock;           /* XBuffer locked Flag                      */
-	byte Int;             /* ISDN-S interrupt                         */
-	byte ReqCh;           /* Channel field for layer-3 Requests       */
-	byte RcCh;            /* Channel field for layer-3 Returncodes    */
-	byte IndCh;           /* Channel field for layer-3 Indications    */
-	byte MInd;            /* more data indication field               */
-	word MLength;         /* more data total packet length            */
-	byte ReadyInt;        /* request field for ready interrupt        */
-	byte SWReg;           /* Software register for special purposes   */
-	byte Reserved[11];    /* reserved space                           */
-	byte InterfaceType;   /* interface type 1=16K interface           */
-	word Signature;       /* ISDN-S adapter Signature (GD)            */
-	PBUFFER XBuffer;      /* Transmit Buffer                          */
-	PBUFFER RBuffer;      /* Receive Buffer                           */
-};
-/*------------------------------------------------------------------*/
-/* SWReg Values (0 means no command)                                */
-/*------------------------------------------------------------------*/
-#define SWREG_DIE_WITH_LEDON  0x01
-#define SWREG_HALT_CPU        0x02 /* Push CPU into a while (1) loop */
-/*------------------------------------------------------------------*/
-/* Id Fields Coding                                                 */
-/*------------------------------------------------------------------*/
-#define ID_MASK 0xe0    /* Mask for the ID field                    */
-#define GL_ERR_ID 0x1f  /* ID for error reporting on global requests*/
-#define DSIG_ID  0x00   /* ID for D-channel signaling               */
-#define NL_ID    0x20   /* ID for network-layer access (B or D)     */
-#define BLLC_ID  0x60   /* ID for B-channel link level access       */
-#define TASK_ID  0x80   /* ID for dynamic user tasks                */
-#define TIMER_ID 0xa0   /* ID for timer task                        */
-#define TEL_ID   0xc0   /* ID for telephone support                 */
-#define MAN_ID   0xe0   /* ID for management                        */
-/*------------------------------------------------------------------*/
-/* ASSIGN and REMOVE requests are the same for all entities         */
-/*------------------------------------------------------------------*/
-#define ASSIGN  0x01
-#define UREMOVE 0xfe /* without return code */
-#define REMOVE  0xff
-/*------------------------------------------------------------------*/
-/* Timer Interrupt Task Interface                                   */
-/*------------------------------------------------------------------*/
-#define ASSIGN_TIM 0x01
-#define REMOVE_TIM 0xff
-/*------------------------------------------------------------------*/
-/* dynamic user task interface                                      */
-/*------------------------------------------------------------------*/
-#define ASSIGN_TSK 0x01
-#define REMOVE_TSK 0xff
-#define LOAD 0xf0
-#define RELOCATE 0xf1
-#define START 0xf2
-#define LOAD2 0xf3
-#define RELOCATE2 0xf4
-/*------------------------------------------------------------------*/
-/* dynamic user task messages                                       */
-/*------------------------------------------------------------------*/
-#define TSK_B2          0x0000
-#define TSK_WAKEUP      0x2000
-#define TSK_TIMER       0x4000
-#define TSK_TSK         0x6000
-#define TSK_PC          0xe000
-/*------------------------------------------------------------------*/
-/* LL management primitives                                         */
-/*------------------------------------------------------------------*/
-#define ASSIGN_LL 1     /* assign logical link                      */
-#define REMOVE_LL 0xff  /* remove logical link                      */
-/*------------------------------------------------------------------*/
-/* LL service primitives                                            */
-/*------------------------------------------------------------------*/
-#define LL_UDATA 1      /* link unit data request/indication        */
-#define LL_ESTABLISH 2  /* link establish request/indication        */
-#define LL_RELEASE 3    /* link release request/indication          */
-#define LL_DATA 4       /* data request/indication                  */
-#define LL_LOCAL 5      /* switch to local operation (COM only)     */
-#define LL_DATA_PEND 5  /* data pending indication (SDLC SHM only)  */
-#define LL_REMOTE 6     /* switch to remote operation (COM only)    */
-#define LL_TEST 8       /* link test request                        */
-#define LL_MDATA 9      /* more data request/indication             */
-#define LL_BUDATA 10    /* broadcast unit data request/indication   */
-#define LL_XID 12       /* XID command request/indication           */
-#define LL_XID_R 13     /* XID response request/indication          */
-/*------------------------------------------------------------------*/
-/* NL service primitives                                            */
-/*------------------------------------------------------------------*/
-#define N_MDATA         1       /* more data to come REQ/IND        */
-#define N_CONNECT       2       /* OSI N-CONNECT REQ/IND            */
-#define N_CONNECT_ACK   3       /* OSI N-CONNECT CON/RES            */
-#define N_DISC          4       /* OSI N-DISC REQ/IND               */
-#define N_DISC_ACK      5       /* OSI N-DISC CON/RES               */
-#define N_RESET         6       /* OSI N-RESET REQ/IND              */
-#define N_RESET_ACK     7       /* OSI N-RESET CON/RES              */
-#define N_DATA          8       /* OSI N-DATA REQ/IND               */
-#define N_EDATA         9       /* OSI N-EXPEDITED DATA REQ/IND     */
-#define N_UDATA         10      /* OSI D-UNIT-DATA REQ/IND          */
-#define N_BDATA         11      /* BROADCAST-DATA REQ/IND           */
-#define N_DATA_ACK      12      /* data ack ind for D-bit procedure */
-#define N_EDATA_ACK     13      /* data ack ind for INTERRUPT       */
-#define N_XON           15      /* clear RNR state */
-#define N_COMBI_IND     N_XON   /* combined indication              */
-#define N_Q_BIT         0x10    /* Q-bit for req/ind                */
-#define N_M_BIT         0x20    /* M-bit for req/ind                */
-#define N_D_BIT         0x40    /* D-bit for req/ind                */
-/*------------------------------------------------------------------*/
-/* Signaling management primitives                                  */
-/*------------------------------------------------------------------*/
-#define ASSIGN_SIG  1    /* assign signaling task                    */
-#define UREMOVE_SIG 0xfe /* remove signaling task without return code*/
-#define REMOVE_SIG  0xff /* remove signaling task                    */
-/*------------------------------------------------------------------*/
-/* Signaling service primitives                                     */
-/*------------------------------------------------------------------*/
-#define CALL_REQ 1      /* call request                             */
-#define CALL_CON 1      /* call confirmation                        */
-#define CALL_IND 2      /* incoming call connected                  */
-#define LISTEN_REQ 2    /* listen request                           */
-#define HANGUP 3        /* hangup request/indication                */
-#define SUSPEND 4       /* call suspend request/confirm             */
-#define RESUME 5        /* call resume request/confirm              */
-#define SUSPEND_REJ 6   /* suspend rejected indication              */
-#define USER_DATA 8     /* user data for user to user signaling     */
-#define CONGESTION 9    /* network congestion indication            */
-#define INDICATE_REQ 10 /* request to indicate an incoming call     */
-#define INDICATE_IND 10 /* indicates that there is an incoming call */
-#define CALL_RES 11     /* accept an incoming call                  */
-#define CALL_ALERT 12   /* send ALERT for incoming call             */
-#define INFO_REQ 13     /* INFO request                             */
-#define INFO_IND 13     /* INFO indication                          */
-#define REJECT 14       /* reject an incoming call                  */
-#define RESOURCES 15    /* reserve B-Channel hardware resources     */
-#define HW_CTRL 16      /* B-Channel hardware IOCTL req/ind         */
-#define TEL_CTRL 16     /* Telephone control request/indication     */
-#define STATUS_REQ 17   /* Request D-State (returned in INFO_IND)   */
-#define FAC_REG_REQ 18  /* 1TR6 connection independent fac reg      */
-#define FAC_REG_ACK 19  /* 1TR6 fac registration acknowledge        */
-#define FAC_REG_REJ 20  /* 1TR6 fac registration reject             */
-#define CALL_COMPLETE 21/* send a CALL_PROC for incoming call       */
-#define SW_CTRL 22      /* extended software features               */
-#define REGISTER_REQ 23 /* Q.931 connection independent reg req     */
-#define REGISTER_IND 24 /* Q.931 connection independent reg ind     */
-#define FACILITY_REQ 25 /* Q.931 connection independent fac req     */
-#define FACILITY_IND 26 /* Q.931 connection independent fac ind     */
-#define NCR_INFO_REQ 27 /* INFO_REQ with NULL CR                    */
-#define GCR_MIM_REQ 28  /* MANAGEMENT_INFO_REQ with global CR       */
-#define SIG_CTRL    29  /* Control for Signalling Hardware          */
-#define DSP_CTRL    30  /* Control for DSPs                         */
-#define LAW_REQ      31 /* Law config request for (returns info_i)  */
-#define SPID_CTRL    32 /* Request/indication SPID related          */
-#define NCR_FACILITY 33 /* Request/indication with NULL/DUMMY CR    */
-#define CALL_HOLD    34 /* Request/indication to hold a CALL        */
-#define CALL_RETRIEVE 35 /* Request/indication to retrieve a CALL   */
-#define CALL_HOLD_ACK 36 /* OK of                hold a CALL        */
-#define CALL_RETRIEVE_ACK 37 /* OK of             retrieve a CALL   */
-#define CALL_HOLD_REJ 38 /* Reject of            hold a CALL        */
-#define CALL_RETRIEVE_REJ 39 /* Reject of         retrieve a call   */
-#define GCR_RESTART   40 /* Send/Receive Restart message            */
-#define S_SERVICE     41 /* Send/Receive Supplementary Service      */
-#define S_SERVICE_REJ 42 /* Reject Supplementary Service indication */
-#define S_SUPPORTED   43 /* Req/Ind to get Supported Services       */
-#define STATUS_ENQ    44 /* Req to send the D-ch request if !state0 */
-#define CALL_GUARD    45 /* Req/Ind to use the FLAGS_CALL_OUTCHECK  */
-#define CALL_GUARD_HP 46 /* Call Guard function to reject a call    */
-#define CALL_GUARD_IF 47 /* Call Guard function, inform the appl    */
-#define SSEXT_REQ     48 /* Supplem.Serv./QSIG specific request     */
-#define SSEXT_IND     49 /* Supplem.Serv./QSIG specific indication  */
-/* reserved commands for the US protocols */
-#define INT_3PTY_NIND 50 /* US       specific indication            */
-#define INT_CF_NIND   51 /* US       specific indication            */
-#define INT_3PTY_DROP 52 /* US       specific indication            */
-#define INT_MOVE_CONF 53 /* US       specific indication            */
-#define INT_MOVE_RC   54 /* US       specific indication            */
-#define INT_MOVE_FLIPPED_CONF 55 /* US specific indication          */
-#define INT_X5NI_OK   56 /* internal transfer OK indication         */
-#define INT_XDMS_START 57 /* internal transfer OK indication        */
-#define INT_XDMS_STOP 58 /* internal transfer finish indication     */
-#define INT_XDMS_STOP2 59 /* internal transfer send FA              */
-#define INT_CUSTCONF_REJ 60 /* internal conference reject           */
-#define INT_CUSTXFER 61 /* internal transfer request                */
-#define INT_CUSTX_NIND 62 /* internal transfer ack                  */
-#define INT_CUSTXREJ_NIND 63 /* internal transfer rej               */
-#define INT_X5NI_CF_XFER  64 /* internal transfer OK indication     */
-#define VSWITCH_REQ 65        /* communication between protocol and */
-#define VSWITCH_IND 66        /* capifunctions for D-CH-switching   */
-#define MWI_POLL 67     /* Message Waiting Status Request fkt */
-#define CALL_PEND_NOTIFY 68 /* notify capi to set new listen        */
-#define DO_NOTHING 69       /* dont do somethin if you get this     */
-#define INT_CT_REJ 70       /* ECT rejected internal command        */
-#define CALL_HOLD_COMPLETE 71 /* In NT Mode indicate hold complete  */
-#define CALL_RETRIEVE_COMPLETE 72 /* In NT Mode indicate retrieve complete  */
-/*------------------------------------------------------------------*/
-/* management service primitives                                    */
-/*------------------------------------------------------------------*/
-#define MAN_READ        2
-#define MAN_WRITE       3
-#define MAN_EXECUTE     4
-#define MAN_EVENT_ON    5
-#define MAN_EVENT_OFF   6
-#define MAN_LOCK        7
-#define MAN_UNLOCK      8
-#define MAN_INFO_IND    2
-#define MAN_EVENT_IND   3
-#define MAN_TRACE_IND   4
-#define MAN_COMBI_IND   9
-#define MAN_ESC         0x80
-/*------------------------------------------------------------------*/
-/* return code coding                                               */
-/*------------------------------------------------------------------*/
-#define UNKNOWN_COMMAND         0x01    /* unknown command          */
-#define WRONG_COMMAND           0x02    /* wrong command            */
-#define WRONG_ID                0x03    /* unknown task/entity id   */
-#define WRONG_CH                0x04    /* wrong task/entity id     */
-#define UNKNOWN_IE              0x05    /* unknown information el.  */
-#define WRONG_IE                0x06    /* wrong information el.    */
-#define OUT_OF_RESOURCES        0x07    /* ISDN-S card out of res.  */
-#define ISDN_GUARD_REJ          0x09    /* ISDN-Guard SuppServ rej  */
-#define N_FLOW_CONTROL          0x10    /* Flow-Control, retry      */
-#define ASSIGN_RC               0xe0    /* ASSIGN acknowledgement   */
-#define ASSIGN_OK               0xef    /* ASSIGN OK                */
-#define OK_FC                   0xfc    /* Flow-Control RC          */
-#define READY_INT               0xfd    /* Ready interrupt          */
-#define TIMER_INT               0xfe    /* timer interrupt          */
-#define OK                      0xff    /* command accepted         */
-/*------------------------------------------------------------------*/
-/* information elements                                             */
-/*------------------------------------------------------------------*/
-#define SHIFT 0x90              /* codeset shift                    */
-#define MORE 0xa0               /* more data                        */
-#define SDNCMPL 0xa1            /* sending complete                 */
-#define CL 0xb0                 /* congestion level                 */
-/* codeset 0                                                */
-#define SMSG 0x00               /* segmented message                */
-#define BC  0x04                /* Bearer Capability                */
-#define CAU 0x08                /* cause                            */
-#define CAD 0x0c                /* Connected address                */
-#define CAI 0x10                /* call identity                    */
-#define CHI 0x18                /* channel identification           */
-#define LLI 0x19                /* logical link id                  */
-#define CHA 0x1a                /* charge advice                    */
-#define FTY 0x1c                /* Facility                         */
-#define DT  0x29                /* ETSI date/time                   */
-#define KEY 0x2c                /* keypad information element       */
-#define UID 0x2d                /* User id information element      */
-#define DSP 0x28                /* display                          */
-#define SIG 0x34                /* signalling hardware control      */
-#define OAD 0x6c                /* origination address              */
-#define OSA 0x6d                /* origination sub-address          */
-#define CPN 0x70                /* called party number              */
-#define DSA 0x71                /* destination sub-address          */
-#define RDX 0x73                /* redirecting number extended      */
-#define RDN 0x74                /* redirecting number               */
-#define RIN 0x76                /* redirection number               */
-#define IUP 0x76                /* VN6 rerouter->PCS (codeset 6)    */
-#define IPU 0x77                /* VN6 PCS->rerouter (codeset 6)    */
-#define RI  0x79                /* restart indicator                */
-#define MIE 0x7a                /* management info element          */
-#define LLC 0x7c                /* low layer compatibility          */
-#define HLC 0x7d                /* high layer compatibility         */
-#define UUI 0x7e                /* user user information            */
-#define ESC 0x7f                /* escape extension                 */
-#define DLC 0x20                /* data link layer configuration    */
-#define NLC 0x21                /* network layer configuration      */
-#define REDIRECT_IE     0x22    /* redirection request/indication data */
-#define REDIRECT_NET_IE 0x23    /* redirection network override data   */
-/* codeset 6                                                */
-#define SIN 0x01                /* service indicator                */
-#define CIF 0x02                /* charging information             */
-#define DATE 0x03               /* date                             */
-#define CPS 0x07                /* called party status              */
-/*------------------------------------------------------------------*/
-/* ESC information elements                                         */
-/*------------------------------------------------------------------*/
-#define MSGTYPEIE        0x7a   /* Messagetype info element         */
-#define CRIE             0x7b   /* INFO info element                */
-#define CODESET6IE       0xec   /* Tunnel for Codeset 6 IEs         */
-#define VSWITCHIE        0xed   /* VSwitch info element             */
-#define SSEXTIE          0xee   /* Supplem. Service info element    */
-#define PROFILEIE        0xef   /* Profile info element             */
-/*------------------------------------------------------------------*/
-/* TEL_CTRL contents                                                */
-/*------------------------------------------------------------------*/
-#define RING_ON         0x01
-#define RING_OFF        0x02
-#define HANDS_FREE_ON   0x03
-#define HANDS_FREE_OFF  0x04
-#define ON_HOOK         0x80
-#define OFF_HOOK        0x90
-/* operation values used by ETSI supplementary services */
-#define THREE_PTY_BEGIN           0x04
-#define THREE_PTY_END             0x05
-#define ECT_EXECUTE               0x06
-#define ACTIVATION_DIVERSION      0x07
-#define DEACTIVATION_DIVERSION    0x08
-#define CALL_DEFLECTION           0x0D
-#define INTERROGATION_DIVERSION   0x0B
-#define INTERROGATION_SERV_USR_NR 0x11
-#define ACTIVATION_MWI            0x20
-#define DEACTIVATION_MWI          0x21
-#define MWI_INDICATION            0x22
-#define MWI_RESPONSE              0x23
-#define CONF_BEGIN                0x28
-#define CONF_ADD                  0x29
-#define CONF_SPLIT                0x2a
-#define CONF_DROP                 0x2b
-#define CONF_ISOLATE              0x2c
-#define CONF_REATTACH             0x2d
-#define CONF_PARTYDISC            0x2e
-#define CCBS_INFO_RETAIN          0x2f
-#define CCBS_ERASECALLLINKAGEID   0x30
-#define CCBS_STOP_ALERTING        0x31
-#define CCBS_REQUEST              0x32
-#define CCBS_DEACTIVATE           0x33
-#define CCBS_INTERROGATE          0x34
-#define CCBS_STATUS               0x35
-#define CCBS_ERASE                0x36
-#define CCBS_B_FREE               0x37
-#define CCNR_INFO_RETAIN          0x38
-#define CCBS_REMOTE_USER_FREE     0x39
-#define CCNR_REQUEST              0x3a
-#define CCNR_INTERROGATE          0x3b
-#define GET_SUPPORTED_SERVICES    0xff
-#define DIVERSION_PROCEDURE_CFU     0x70
-#define DIVERSION_PROCEDURE_CFB     0x71
-#define DIVERSION_PROCEDURE_CFNR    0x72
-#define DIVERSION_DEACTIVATION_CFU  0x80
-#define DIVERSION_DEACTIVATION_CFB  0x81
-#define DIVERSION_DEACTIVATION_CFNR 0x82
-#define DIVERSION_INTERROGATE_NUM   0x11
-#define DIVERSION_INTERROGATE_CFU   0x60
-#define DIVERSION_INTERROGATE_CFB   0x61
-#define DIVERSION_INTERROGATE_CFNR  0x62
-/* Service Masks */
-#define SMASK_HOLD_RETRIEVE        0x00000001
-#define SMASK_TERMINAL_PORTABILITY 0x00000002
-#define SMASK_ECT                  0x00000004
-#define SMASK_3PTY                 0x00000008
-#define SMASK_CALL_FORWARDING      0x00000010
-#define SMASK_CALL_DEFLECTION      0x00000020
-#define SMASK_MCID                 0x00000040
-#define SMASK_CCBS                 0x00000080
-#define SMASK_MWI                  0x00000100
-#define SMASK_CCNR                 0x00000200
-#define SMASK_CONF                 0x00000400
-/* ----------------------------------------------
-   Types of transfers used to transfer the
-   information in the 'struct RC->Reserved2[8]'
-   The information is transferred as 2 dwords
-   (2 4Byte unsigned values)
-   First of them is the transfer type.
-   2^32-1 possible messages are possible in this way.
-   The context of the second one had no meaning
-   ---------------------------------------------- */
-#define DIVA_RC_TYPE_NONE              0x00000000
-#define DIVA_RC_TYPE_REMOVE_COMPLETE   0x00000008
-#define DIVA_RC_TYPE_STREAM_PTR        0x00000009
-#define DIVA_RC_TYPE_CMA_PTR           0x0000000a
-#define DIVA_RC_TYPE_OK_FC             0x0000000b
-#define DIVA_RC_TYPE_RX_DMA            0x0000000c
-/* ------------------------------------------------------
-   IO Control codes for IN BAND SIGNALING
-   ------------------------------------------------------ */
-#define CTRL_L1_SET_SIG_ID        5
-#define CTRL_L1_SET_DAD           6
-#define CTRL_L1_RESOURCES         7
-/* ------------------------------------------------------ */
-/* ------------------------------------------------------
-   Layer 2 types
-   ------------------------------------------------------ */
-#define X75T            1       /* x.75 for ttx                     */
-#define TRF             2       /* transparent with hdlc framing    */
-#define TRF_IN          3       /* transparent with hdlc fr. inc.   */
-#define SDLC            4       /* sdlc, sna layer-2                */
-#define X75             5       /* x.75 for btx                     */
-#define LAPD            6       /* lapd (Q.921)                     */
-#define X25_L2          7       /* x.25 layer-2                     */
-#define V120_L2         8       /* V.120 layer-2 protocol           */
-#define V42_IN          9       /* V.42 layer-2 protocol, incoming */
-#define V42            10       /* V.42 layer-2 protocol            */
-#define MDM_ATP        11       /* AT Parser built in the L2        */
-#define X75_V42BIS     12       /* x.75 with V.42bis                */
-#define RTPL2_IN       13       /* RTP layer-2 protocol, incoming  */
-#define RTPL2          14       /* RTP layer-2 protocol             */
-#define V120_V42BIS    15       /* V.120 asynchronous mode supporting V.42bis compression */
-#define LISTENER       27       /* Layer 2 to listen line */
-#define MTP2           28       /* MTP2 Layer 2 */
-#define PIAFS_CRC      29       /* PIAFS Layer 2 with CRC calculation at L2 */
-/* ------------------------------------------------------
-   PIAFS DLC DEFINITIONS
-   ------------------------------------------------------ */
-#define PIAFS_64K            0x01
-#define PIAFS_VARIABLE_SPEED 0x02
-#define PIAFS_CHINESE_SPEED    0x04
-#define PIAFS_UDATA_ABILITY_ID    0x80
-#define PIAFS_UDATA_ABILITY_DCDON 0x01
-#define PIAFS_UDATA_ABILITY_DDI   0x80
-/*
-  DLC of PIAFS :
-  Byte | 8 7 6 5 4 3 2 1
-  -----+--------------------------------------------------------
-  0 | 0 0 1 0 0 0 0 0  Data Link Configuration
-  1 | X X X X X X X X  Length of IE (at least 15 Bytes)
-  2 | 0 0 0 0 0 0 0 0  max. information field, LOW  byte (not used, fix 73 Bytes)
-  3 | 0 0 0 0 0 0 0 0  max. information field, HIGH byte (not used, fix 73 Bytes)
-  4 | 0 0 0 0 0 0 0 0  address A (not used)
-  5 | 0 0 0 0 0 0 0 0  address B (not used)
-  6 | 0 0 0 0 0 0 0 0  Mode (not used, fix 128)
-  7 | 0 0 0 0 0 0 0 0  Window Size (not used, fix 127)
-  8 | X X X X X X X X  XID Length, Low Byte (at least 7 Bytes)
-  9 | X X X X X X X X  XID Length, High Byte
-  10 | 0 0 0 0 0 C V S  PIAFS Protocol Speed configuration -> Note(1)
-  |                  S = 0 -> Protocol Speed is 32K
-  |                  S = 1 -> Protocol Speed is 64K
-  |                  V = 0 -> Protocol Speed is fixed
-  |                  V = 1 -> Protocol Speed is variable
-  |                  C = 0 -> speed setting according to standard
-  |                  C = 1 -> speed setting for chinese implementation
-  11 | 0 0 0 0 0 0 R T  P0 - V42bis Compression enable/disable, Low Byte
-  |                  T = 0 -> Transmit Direction enable
-  |                  T = 1 -> Transmit Direction disable
-  |                  R = 0 -> Receive  Direction enable
-  |                  R = 1 -> Receive  Direction disable
-  13 | 0 0 0 0 0 0 0 0  P0 - V42bis Compression enable/disable, High Byte
-  14 | X X X X X X X X  P1 - V42bis Dictionary Size, Low Byte
-  15 | X X X X X X X X  P1 - V42bis Dictionary Size, High Byte
-  16 | X X X X X X X X  P2 - V42bis String Length, Low Byte
-  17 | X X X X X X X X  P2 - V42bis String Length, High Byte
-  18 | X X X X X X X X  PIAFS extension length
-  19 | 1 0 0 0 0 0 0 0  PIAFS extension Id (0x80) - UDATA abilities
-  20 | U 0 0 0 0 0 0 D  UDATA abilities -> Note (2)
-  |                  up to now the following Bits are defined:
-  |                  D - signal DCD ON
-  |                  U - use extensive UDATA control communication
-  |                      for DDI test application
-  + Note (1): ----------+------+-----------------------------------------+
-  | PIAFS Protocol      | Bit  |                                         |
-  | Speed configuration |    S | Bit 1 - Protocol Speed                  |
-  |                     |      |         0 - 32K                         |
-  |                     |      |         1 - 64K (default)               |
-  |                     |    V | Bit 2 - Variable Protocol Speed         |
-  |                     |      |         0 - Speed is fix                |
-  |                     |      |         1 - Speed is variable (default) |
-  |                     |      |             OVERWRITES 32k Bit 1        |
-  |                     |    C | Bit 3   0 - Speed Settings according to |
-  |                     |      |             PIAFS specification         |
-  |                     |      |         1 - Speed setting for chinese   |
-  |                     |      |             PIAFS implementation        |
-  |                     |      | Explanation for chinese speed settings: |
-  |                     |      |         if Bit 3 is set the following   |
-  |                     |      |         rules apply:                    |
-  |                     |      |         Bit1=0 Bit2=0: 32k fix          |
-  |                     |      |         Bit1=1 Bit2=0: 64k fix          |
-  |                     |      |         Bit1=0 Bit2=1: PIAFS is trying  |
-  |                     |      |             to negotiate 32k is that is |
-  |                     |      |             not possible it tries to    |
-  |                     |      |             negotiate 64k               |
-  |                     |      |         Bit1=1 Bit2=1: PIAFS is trying  |
-  |                     |      |             to negotiate 64k is that is |
-  |                     |      |             not possible it tries to    |
-  |                     |      |             negotiate 32k               |
-  + Note (2): ----------+------+-----------------------------------------+
-  | PIAFS               | Bit  | this byte defines the usage of UDATA    |
-  | Implementation      |      | control communication                   |
-  | UDATA usage         |    D | Bit 1 - DCD-ON signalling               |
-  |                     |      |         0 - no DCD-ON is signalled      |
-  |                     |      |             (default)                   |
-  |                     |      |         1 - DCD-ON will be signalled    |
-  |                     |    U | Bit 8 - DDI test application UDATA      |
-  |                     |      |         control communication           |
-  |                     |      |         0 - no UDATA control            |
-  |                     |      |             communication (default)     |
-  |                     |      |             sets as well the DCD-ON     |
-  |                     |      |             signalling                  |
-  |                     |      |         1 - UDATA control communication |
-  |                     |      |             ATTENTION: Do not use these |
-  |                     |      |                        setting if you   |
-  |                     |      |                        are not really   |
-  |                     |      |                        that you need it |
-  |                     |      |                        and you know     |
-  |                     |      |                        exactly what you |
-  |                     |      |                        are doing.       |
-  |                     |      |                        You can easily   |
-  |                     |      |                        disable any      |
-  |                     |      |                        data transfer.   |
-  +---------------------+------+-----------------------------------------+
-*/
-/* ------------------------------------------------------
-   LISTENER DLC DEFINITIONS
-   ------------------------------------------------------ */
-#define LISTENER_FEATURE_MASK_CUMMULATIVE            0x0001
-/* ------------------------------------------------------
-   LISTENER META-FRAME CODE/PRIMITIVE DEFINITIONS
-   ------------------------------------------------------ */
-#define META_CODE_LL_UDATA_RX 0x01
-#define META_CODE_LL_UDATA_TX 0x02
-#define META_CODE_LL_DATA_RX  0x03
-#define META_CODE_LL_DATA_TX  0x04
-#define META_CODE_LL_MDATA_RX 0x05
-#define META_CODE_LL_MDATA_TX 0x06
-#define META_CODE_EMPTY       0x10
-#define META_CODE_LOST_FRAMES 0x11
-#define META_FLAG_TRUNCATED   0x0001
-/*------------------------------------------------------------------*/
-/* CAPI-like profile to indicate features on LAW_REQ                */
-/*------------------------------------------------------------------*/
-#define GL_INTERNAL_CONTROLLER_SUPPORTED     0x00000001L
-#define GL_EXTERNAL_EQUIPMENT_SUPPORTED      0x00000002L
-#define GL_HANDSET_SUPPORTED                 0x00000004L
-#define GL_DTMF_SUPPORTED                    0x00000008L
-#define GL_SUPPLEMENTARY_SERVICES_SUPPORTED  0x00000010L
-#define GL_CHANNEL_ALLOCATION_SUPPORTED      0x00000020L
-#define GL_BCHANNEL_OPERATION_SUPPORTED      0x00000040L
-#define GL_LINE_INTERCONNECT_SUPPORTED       0x00000080L
-#define B1_HDLC_SUPPORTED                    0x00000001L
-#define B1_TRANSPARENT_SUPPORTED             0x00000002L
-#define B1_V110_ASYNC_SUPPORTED              0x00000004L
-#define B1_V110_SYNC_SUPPORTED               0x00000008L
-#define B1_T30_SUPPORTED                     0x00000010L
-#define B1_HDLC_INVERTED_SUPPORTED           0x00000020L
-#define B1_TRANSPARENT_R_SUPPORTED           0x00000040L
-#define B1_MODEM_ALL_NEGOTIATE_SUPPORTED     0x00000080L
-#define B1_MODEM_ASYNC_SUPPORTED             0x00000100L
-#define B1_MODEM_SYNC_HDLC_SUPPORTED         0x00000200L
-#define B2_X75_SUPPORTED                     0x00000001L
-#define B2_TRANSPARENT_SUPPORTED             0x00000002L
-#define B2_SDLC_SUPPORTED                    0x00000004L
-#define B2_LAPD_SUPPORTED                    0x00000008L
-#define B2_T30_SUPPORTED                     0x00000010L
-#define B2_PPP_SUPPORTED                     0x00000020L
-#define B2_TRANSPARENT_NO_CRC_SUPPORTED      0x00000040L
-#define B2_MODEM_EC_COMPRESSION_SUPPORTED    0x00000080L
-#define B2_X75_V42BIS_SUPPORTED              0x00000100L
-#define B2_V120_ASYNC_SUPPORTED              0x00000200L
-#define B2_V120_ASYNC_V42BIS_SUPPORTED       0x00000400L
-#define B2_V120_BIT_TRANSPARENT_SUPPORTED    0x00000800L
-#define B2_LAPD_FREE_SAPI_SEL_SUPPORTED      0x00001000L
-#define B3_TRANSPARENT_SUPPORTED             0x00000001L
-#define B3_T90NL_SUPPORTED                   0x00000002L
-#define B3_ISO8208_SUPPORTED                 0x00000004L
-#define B3_X25_DCE_SUPPORTED                 0x00000008L
-#define B3_T30_SUPPORTED                     0x00000010L
-#define B3_T30_WITH_EXTENSIONS_SUPPORTED     0x00000020L
-#define B3_RESERVED_SUPPORTED                0x00000040L
-#define B3_MODEM_SUPPORTED                   0x00000080L
-#define MANUFACTURER_FEATURE_SLAVE_CODEC          0x00000001L
-#define MANUFACTURER_FEATURE_FAX_MORE_DOCUMENTS   0x00000002L
-#define MANUFACTURER_FEATURE_HARDDTMF             0x00000004L
-#define MANUFACTURER_FEATURE_SOFTDTMF_SEND        0x00000008L
-#define MANUFACTURER_FEATURE_DTMF_PARAMETERS      0x00000010L
-#define MANUFACTURER_FEATURE_SOFTDTMF_RECEIVE     0x00000020L
-#define MANUFACTURER_FEATURE_FAX_SUB_SEP_PWD      0x00000040L
-#define MANUFACTURER_FEATURE_V18                  0x00000080L
-#define MANUFACTURER_FEATURE_MIXER_CH_CH          0x00000100L
-#define MANUFACTURER_FEATURE_MIXER_CH_PC          0x00000200L
-#define MANUFACTURER_FEATURE_MIXER_PC_CH          0x00000400L
-#define MANUFACTURER_FEATURE_MIXER_PC_PC          0x00000800L
-#define MANUFACTURER_FEATURE_ECHO_CANCELLER       0x00001000L
-#define MANUFACTURER_FEATURE_RTP                  0x00002000L
-#define MANUFACTURER_FEATURE_T38                  0x00004000L
-#define MANUFACTURER_FEATURE_TRANSP_DELIVERY_CONF 0x00008000L
-#define MANUFACTURER_FEATURE_XONOFF_FLOW_CONTROL  0x00010000L
-#define MANUFACTURER_FEATURE_OOB_CHANNEL          0x00020000L
-#define MANUFACTURER_FEATURE_IN_BAND_CHANNEL      0x00040000L
-#define MANUFACTURER_FEATURE_IN_BAND_FEATURE      0x00080000L
-#define MANUFACTURER_FEATURE_PIAFS                0x00100000L
-#define MANUFACTURER_FEATURE_DTMF_TONE            0x00200000L
-#define MANUFACTURER_FEATURE_FAX_PAPER_FORMATS    0x00400000L
-#define MANUFACTURER_FEATURE_OK_FC_LABEL          0x00800000L
-#define MANUFACTURER_FEATURE_VOWN                 0x01000000L
-#define MANUFACTURER_FEATURE_XCONNECT             0x02000000L
-#define MANUFACTURER_FEATURE_DMACONNECT           0x04000000L
-#define MANUFACTURER_FEATURE_AUDIO_TAP            0x08000000L
-#define MANUFACTURER_FEATURE_FAX_NONSTANDARD      0x10000000L
-#define MANUFACTURER_FEATURE_SS7                  0x20000000L
-#define MANUFACTURER_FEATURE_MADAPTER             0x40000000L
-#define MANUFACTURER_FEATURE_MEASURE              0x80000000L
-#define MANUFACTURER_FEATURE2_LISTENING           0x00000001L
-#define MANUFACTURER_FEATURE2_SS_DIFFCONTPOSSIBLE 0x00000002L
-#define MANUFACTURER_FEATURE2_GENERIC_TONE        0x00000004L
-#define MANUFACTURER_FEATURE2_COLOR_FAX           0x00000008L
-#define MANUFACTURER_FEATURE2_SS_ECT_DIFFCONTPOSSIBLE 0x00000010L
-#define RTP_PRIM_PAYLOAD_PCMU_8000     0
-#define RTP_PRIM_PAYLOAD_1016_8000     1
-#define RTP_PRIM_PAYLOAD_G726_32_8000  2
-#define RTP_PRIM_PAYLOAD_GSM_8000      3
-#define RTP_PRIM_PAYLOAD_G723_8000     4
-#define RTP_PRIM_PAYLOAD_DVI4_8000     5
-#define RTP_PRIM_PAYLOAD_DVI4_16000    6
-#define RTP_PRIM_PAYLOAD_LPC_8000      7
-#define RTP_PRIM_PAYLOAD_PCMA_8000     8
-#define RTP_PRIM_PAYLOAD_G722_16000    9
-#define RTP_PRIM_PAYLOAD_QCELP_8000    12
-#define RTP_PRIM_PAYLOAD_G728_8000     14
-#define RTP_PRIM_PAYLOAD_G729_8000     18
-#define RTP_PRIM_PAYLOAD_GSM_HR_8000   30
-#define RTP_PRIM_PAYLOAD_GSM_EFR_8000  31
-#define RTP_ADD_PAYLOAD_BASE           32
-#define RTP_ADD_PAYLOAD_RED            32
-#define RTP_ADD_PAYLOAD_CN_8000        33
-#define RTP_ADD_PAYLOAD_DTMF           34
-#define RTP_PRIM_PAYLOAD_PCMU_8000_SUPPORTED     (1L << RTP_PRIM_PAYLOAD_PCMU_8000)
-#define RTP_PRIM_PAYLOAD_1016_8000_SUPPORTED     (1L << RTP_PRIM_PAYLOAD_1016_8000)
-#define RTP_PRIM_PAYLOAD_G726_32_8000_SUPPORTED  (1L << RTP_PRIM_PAYLOAD_G726_32_8000)
-#define RTP_PRIM_PAYLOAD_GSM_8000_SUPPORTED      (1L << RTP_PRIM_PAYLOAD_GSM_8000)
-#define RTP_PRIM_PAYLOAD_G723_8000_SUPPORTED     (1L << RTP_PRIM_PAYLOAD_G723_8000)
-#define RTP_PRIM_PAYLOAD_DVI4_8000_SUPPORTED     (1L << RTP_PRIM_PAYLOAD_DVI4_8000)
-#define RTP_PRIM_PAYLOAD_DVI4_16000_SUPPORTED    (1L << RTP_PRIM_PAYLOAD_DVI4_16000)
-#define RTP_PRIM_PAYLOAD_LPC_8000_SUPPORTED      (1L << RTP_PRIM_PAYLOAD_LPC_8000)
-#define RTP_PRIM_PAYLOAD_PCMA_8000_SUPPORTED     (1L << RTP_PRIM_PAYLOAD_PCMA_8000)
-#define RTP_PRIM_PAYLOAD_G722_16000_SUPPORTED    (1L << RTP_PRIM_PAYLOAD_G722_16000)
-#define RTP_PRIM_PAYLOAD_QCELP_8000_SUPPORTED    (1L << RTP_PRIM_PAYLOAD_QCELP_8000)
-#define RTP_PRIM_PAYLOAD_G728_8000_SUPPORTED     (1L << RTP_PRIM_PAYLOAD_G728_8000)
-#define RTP_PRIM_PAYLOAD_G729_8000_SUPPORTED     (1L << RTP_PRIM_PAYLOAD_G729_8000)
-#define RTP_PRIM_PAYLOAD_GSM_HR_8000_SUPPORTED   (1L << RTP_PRIM_PAYLOAD_GSM_HR_8000)
-#define RTP_PRIM_PAYLOAD_GSM_EFR_8000_SUPPORTED  (1L << RTP_PRIM_PAYLOAD_GSM_EFR_8000)
-#define RTP_ADD_PAYLOAD_RED_SUPPORTED            (1L << (RTP_ADD_PAYLOAD_RED - RTP_ADD_PAYLOAD_BASE))
-#define RTP_ADD_PAYLOAD_CN_8000_SUPPORTED        (1L << (RTP_ADD_PAYLOAD_CN_8000 - RTP_ADD_PAYLOAD_BASE))
-#define RTP_ADD_PAYLOAD_DTMF_SUPPORTED           (1L << (RTP_ADD_PAYLOAD_DTMF - RTP_ADD_PAYLOAD_BASE))
-/* virtual switching definitions */
-#define VSJOIN         1
-#define VSTRANSPORT    2
-#define VSGETPARAMS    3
-#define VSCAD          1
-#define VSRXCPNAME     2
-#define VSCALLSTAT     3
-#define VSINVOKEID    4
-#define VSCLMRKS       5
-#define VSTBCTIDENT    6
-#define VSETSILINKID   7
-#define VSSAMECONTROLLER 8
-/* Errorcodes for VSETSILINKID begin */
-#define VSETSILINKIDRRWC      1
-#define VSETSILINKIDREJECT    2
-#define VSETSILINKIDTIMEOUT   3
-#define VSETSILINKIDFAILCOUNT 4
-#define VSETSILINKIDERROR     5
-/* Errorcodes for VSETSILINKID end */
-/* -----------------------------------------------------------**
-** The PROTOCOL_FEATURE_STRING in feature.h (included         **
-** in prstart.sx and astart.sx) defines capabilities and      **
-** features of the actual protocol code. It's used as a bit   **
-** mask.                                                      **
-** The following Bits are defined:                            **
-** -----------------------------------------------------------*/
-#define PROTCAP_TELINDUS  0x0001  /* Telindus Variant of protocol code   */
-#define PROTCAP_MAN_IF    0x0002  /* Management interface implemented    */
-#define PROTCAP_V_42      0x0004  /* V42 implemented                     */
-#define PROTCAP_V90D      0x0008  /* V.90D (implies up to 384k DSP code) */
-#define PROTCAP_EXTD_FAX  0x0010  /* Extended FAX (ECM, 2D, T6, Polling) */
-#define PROTCAP_EXTD_RXFC 0x0020  /* RxFC (Extd Flow Control), OOB Chnl  */
-#define PROTCAP_VOIP      0x0040  /* VoIP (implies up to 512k DSP code)  */
-#define PROTCAP_CMA_ALLPR 0x0080  /* CMA support for all NL primitives   */
-#define PROTCAP_FREE8     0x0100  /* not used                            */
-#define PROTCAP_FREE9     0x0200  /* not used                            */
-#define PROTCAP_FREE10    0x0400  /* not used                            */
-#define PROTCAP_FREE11    0x0800  /* not used                            */
-#define PROTCAP_FREE12    0x1000  /* not used                            */
-#define PROTCAP_FREE13    0x2000  /* not used                            */
-#define PROTCAP_FREE14    0x4000  /* not used                            */
-#define PROTCAP_EXTENSION 0x8000  /* used for future extensions          */
-/* -----------------------------------------------------------* */
-/* Onhook data transmission ETS30065901 */
-/* Message Type */
-/*#define RESERVED4                 0x4*/
-#define CALL_SETUP                0x80
-#define MESSAGE_WAITING_INDICATOR 0x82
-/*#define RESERVED84                0x84*/
-/*#define RESERVED85                0x85*/
-#define ADVICE_OF_CHARGE          0x86
-/*1111 0001
-  to
-  1111 1111
-  F1H - Reserved for network operator use
-  to
-  FFH*/
-/* Parameter Types */
-#define DATE_AND_TIME                                           1
-#define CLI_PARAMETER_TYPE                                      2
-#define CALLED_DIRECTORY_NUMBER_PARAMETER_TYPE                  3
-#define REASON_FOR_ABSENCE_OF_CLI_PARAMETER_TYPE                4
-#define NAME_PARAMETER_TYPE                                     7
-#define REASON_FOR_ABSENCE_OF_CALLING_PARTY_NAME_PARAMETER_TYPE 8
-#define VISUAL_INDICATOR_PARAMETER_TYPE                         0xb
-#define COMPLEMENTARY_CLI_PARAMETER_TYPE                        0x10
-#define CALL_TYPE_PARAMETER_TYPE                                0x11
-#define FIRST_CALLED_LINE_DIRECTORY_NUMBER_PARAMETER_TYPE       0x12
-#define NETWORK_MESSAGE_SYSTEM_STATUS_PARAMETER_TYPE            0x13
-#define FORWARDED_CALL_TYPE_PARAMETER_TYPE                      0x15
-#define TYPE_OF_CALLING_USER_PARAMETER_TYPE                     0x16
-#define REDIRECTING_NUMBER_PARAMETER_TYPE                       0x1a
-#define EXTENSION_FOR_NETWORK_OPERATOR_USE_PARAMETER_TYPE       0xe0
-/* -----------------------------------------------------------* */
-#else
-#endif /* PC_H_INCLUDED  } */
diff --git a/drivers/isdn/hardware/eicon/pc_init.h b/drivers/isdn/hardware/eicon/pc_init.h
deleted file mode 100644
index d1d00866e8d4..000000000000
--- a/drivers/isdn/hardware/eicon/pc_init.h
+++ /dev/null
@@ -1,267 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef PC_INIT_H_
-#define PC_INIT_H_
-/*------------------------------------------------------------------*/
-/*
-  Initialisation parameters for the card
-  0x0008 <byte> TEI
-  0x0009 <byte> NT2 flag
-  0x000a <byte> Default DID length
-  0x000b <byte> Disable watchdog flag
-  0x000c <byte> Permanent connection flag
-  0x000d <byte> Bit 3-8: L1 Hunt Group/Tristate
-  0x000d <byte> Bit 1: QSig small CR length if set to 1
-  0x000d <byte> Bit 2: QSig small CHI length if set to 1
-  0x000e <byte> Bit 1-3: Stable L2, 0=OnDemand,1=NoDisc,2=permanent
-  0x000e <byte> Bit 4: NT mode
-  0x000e <byte> Bit 5: QSig Channel ID format
-  0x000e <byte> Bit 6: QSig Call Forwarding Allowed Flag
-  0x000e <byte> Bit 7: Disable AutoSPID Flag
-  0x000f <byte> No order check flag
-  0x0010 <byte> Force companding type:0=default,1=a-law,2=u-law
-  0x0012 <byte> Low channel flag
-  0x0013 <byte> Protocol version
-  0x0014 <byte> CRC4 option:0=default,1=double_frm,2=multi_frm,3=auto
-  0x0015 <byte> Bit 0: NoHscx30, Bit 1: Loopback flag, Bit 2: ForceHscx30
-  0x0016 <byte> DSP info
-  0x0017-0x0019 Serial number
-  0x001a <byte> Card type
-  0x0020 <string> OAD 0
-  0x0040 <string> OSA 0
-  0x0060 <string> SPID 0 (if not T.1)
-  0x0060 <struct> if T.1: Robbed Bit Configuration
-  0x0060          length (8)
-  0x0061          RBS Answer Delay
-  0x0062          RBS Config Bit 3, 4:
-  0  0 -> Wink Start
-  1  0 -> Loop Start
-  0  1 -> Ground Start
-  1  1 -> reserved
-  Bit 5, 6:
-  0  0 -> Pulse Dial -> Rotary
-  1  0 -> DTMF
-  0  1 -> MF
-  1  1 -> reserved
-  0x0063          RBS RX Digit Timeout
-  0x0064          RBS Bearer Capability
-  0x0065-0x0069   RBS Debug Mask
-  0x0080 <string> OAD 1
-  0x00a0 <string> OSA 1
-  0x00c0 <string> SPID 1
-  0x00e0 <w-element list> Additional configuration
-*/
-#define PCINIT_END_OF_LIST                0x00
-#define PCINIT_MODEM_GUARD_TONE           0x01
-#define PCINIT_MODEM_MIN_SPEED            0x02
-#define PCINIT_MODEM_MAX_SPEED            0x03
-#define PCINIT_MODEM_PROTOCOL_OPTIONS     0x04
-#define PCINIT_FAX_OPTIONS                0x05
-#define PCINIT_FAX_MAX_SPEED              0x06
-#define PCINIT_MODEM_OPTIONS              0x07
-#define PCINIT_MODEM_NEGOTIATION_MODE     0x08
-#define PCINIT_MODEM_MODULATIONS_MASK     0x09
-#define PCINIT_MODEM_TRANSMIT_LEVEL       0x0a
-#define PCINIT_FAX_DISABLED_RESOLUTIONS   0x0b
-#define PCINIT_FAX_MAX_RECORDING_WIDTH    0x0c
-#define PCINIT_FAX_MAX_RECORDING_LENGTH   0x0d
-#define PCINIT_FAX_MIN_SCANLINE_TIME      0x0e
-#define PCINIT_US_EKTS_CACH_HANDLES       0x0f
-#define PCINIT_US_EKTS_BEGIN_CONF         0x10
-#define PCINIT_US_EKTS_DROP_CONF          0x11
-#define PCINIT_US_EKTS_CALL_TRANSFER      0x12
-#define PCINIT_RINGERTONE_OPTION          0x13
-#define PCINIT_CARD_ADDRESS               0x14
-#define PCINIT_FPGA_FEATURES              0x15
-#define PCINIT_US_EKTS_MWI                0x16
-#define PCINIT_MODEM_SPEAKER_CONTROL      0x17
-#define PCINIT_MODEM_SPEAKER_VOLUME       0x18
-#define PCINIT_MODEM_CARRIER_WAIT_TIME    0x19
-#define PCINIT_MODEM_CARRIER_LOSS_TIME    0x1a
-#define PCINIT_UNCHAN_B_MASK              0x1b
-#define PCINIT_PART68_LIMITER             0x1c
-#define PCINIT_XDI_FEATURES               0x1d
-#define PCINIT_QSIG_DIALECT               0x1e
-#define PCINIT_DISABLE_AUTOSPID_FLAG      0x1f
-#define PCINIT_FORCE_VOICE_MAIL_ALERT     0x20
-#define PCINIT_PIAFS_TURNAROUND_FRAMES    0x21
-#define PCINIT_L2_COUNT                   0x22
-#define PCINIT_QSIG_FEATURES              0x23
-#define PCINIT_NO_SIGNALLING              0x24
-#define PCINIT_CARD_SN                    0x25
-#define PCINIT_CARD_PORT                  0x26
-#define PCINIT_ALERTTO                    0x27
-#define PCINIT_MODEM_EYE_SETUP            0x28
-#define PCINIT_FAX_V34_OPTIONS            0x29
-/*------------------------------------------------------------------*/
-#define PCINIT_MODEM_GUARD_TONE_NONE            0x00
-#define PCINIT_MODEM_GUARD_TONE_550HZ           0x01
-#define PCINIT_MODEM_GUARD_TONE_1800HZ          0x02
-#define PCINIT_MODEM_GUARD_TONE_CHOICES         0x03
-#define PCINIT_MODEMPROT_DISABLE_V42_V42BIS     0x0001
-#define PCINIT_MODEMPROT_DISABLE_MNP_MNP5       0x0002
-#define PCINIT_MODEMPROT_REQUIRE_PROTOCOL       0x0004
-#define PCINIT_MODEMPROT_DISABLE_V42_DETECT     0x0008
-#define PCINIT_MODEMPROT_DISABLE_COMPRESSION    0x0010
-#define PCINIT_MODEMPROT_REQUIRE_PROTOCOL_V34UP 0x0020
-#define PCINIT_MODEMPROT_NO_PROTOCOL_IF_1200    0x0100
-#define PCINIT_MODEMPROT_BUFFER_IN_V42_DETECT   0x0200
-#define PCINIT_MODEMPROT_DISABLE_V42_SREJ       0x0400
-#define PCINIT_MODEMPROT_DISABLE_MNP3           0x0800
-#define PCINIT_MODEMPROT_DISABLE_MNP4           0x1000
-#define PCINIT_MODEMPROT_DISABLE_MNP10          0x2000
-#define PCINIT_MODEMPROT_NO_PROTOCOL_IF_V22BIS  0x4000
-#define PCINIT_MODEMPROT_NO_PROTOCOL_IF_V32BIS  0x8000
-#define PCINIT_MODEMCONFIG_LEASED_LINE_MODE     0x00000001L
-#define PCINIT_MODEMCONFIG_4_WIRE_OPERATION     0x00000002L
-#define PCINIT_MODEMCONFIG_DISABLE_BUSY_DETECT  0x00000004L
-#define PCINIT_MODEMCONFIG_DISABLE_CALLING_TONE 0x00000008L
-#define PCINIT_MODEMCONFIG_DISABLE_ANSWER_TONE  0x00000010L
-#define PCINIT_MODEMCONFIG_ENABLE_DIAL_TONE_DET 0x00000020L
-#define PCINIT_MODEMCONFIG_USE_POTS_INTERFACE   0x00000040L
-#define PCINIT_MODEMCONFIG_FORCE_RAY_TAYLOR_FAX 0x00000080L
-#define PCINIT_MODEMCONFIG_DISABLE_RETRAIN      0x00000100L
-#define PCINIT_MODEMCONFIG_DISABLE_STEPDOWN     0x00000200L
-#define PCINIT_MODEMCONFIG_DISABLE_SPLIT_SPEED  0x00000400L
-#define PCINIT_MODEMCONFIG_DISABLE_TRELLIS      0x00000800L
-#define PCINIT_MODEMCONFIG_ALLOW_RDL_TEST_LOOP  0x00001000L
-#define PCINIT_MODEMCONFIG_DISABLE_STEPUP       0x00002000L
-#define PCINIT_MODEMCONFIG_DISABLE_FLUSH_TIMER  0x00004000L
-#define PCINIT_MODEMCONFIG_REVERSE_DIRECTION    0x00008000L
-#define PCINIT_MODEMCONFIG_DISABLE_TX_REDUCTION 0x00010000L
-#define PCINIT_MODEMCONFIG_DISABLE_PRECODING    0x00020000L
-#define PCINIT_MODEMCONFIG_DISABLE_PREEMPHASIS  0x00040000L
-#define PCINIT_MODEMCONFIG_DISABLE_SHAPING      0x00080000L
-#define PCINIT_MODEMCONFIG_DISABLE_NONLINEAR_EN 0x00100000L
-#define PCINIT_MODEMCONFIG_DISABLE_MANUALREDUCT 0x00200000L
-#define PCINIT_MODEMCONFIG_DISABLE_16_POINT_TRN 0x00400000L
-#define PCINIT_MODEMCONFIG_DISABLE_2400_SYMBOLS 0x01000000L
-#define PCINIT_MODEMCONFIG_DISABLE_2743_SYMBOLS 0x02000000L
-#define PCINIT_MODEMCONFIG_DISABLE_2800_SYMBOLS 0x04000000L
-#define PCINIT_MODEMCONFIG_DISABLE_3000_SYMBOLS 0x08000000L
-#define PCINIT_MODEMCONFIG_DISABLE_3200_SYMBOLS 0x10000000L
-#define PCINIT_MODEMCONFIG_DISABLE_3429_SYMBOLS 0x20000000L
-#define PCINIT_MODEM_NEGOTIATE_HIGHEST          0x00
-#define PCINIT_MODEM_NEGOTIATE_DISABLED         0x01
-#define PCINIT_MODEM_NEGOTIATE_IN_CLASS         0x02
-#define PCINIT_MODEM_NEGOTIATE_V100             0x03
-#define PCINIT_MODEM_NEGOTIATE_V8               0x04
-#define PCINIT_MODEM_NEGOTIATE_V8BIS            0x05
-#define PCINIT_MODEM_NEGOTIATE_CHOICES          0x06
-#define PCINIT_MODEMMODULATION_DISABLE_V21      0x00000001L
-#define PCINIT_MODEMMODULATION_DISABLE_V23      0x00000002L
-#define PCINIT_MODEMMODULATION_DISABLE_V22      0x00000004L
-#define PCINIT_MODEMMODULATION_DISABLE_V22BIS   0x00000008L
-#define PCINIT_MODEMMODULATION_DISABLE_V32      0x00000010L
-#define PCINIT_MODEMMODULATION_DISABLE_V32BIS   0x00000020L
-#define PCINIT_MODEMMODULATION_DISABLE_V34      0x00000040L
-#define PCINIT_MODEMMODULATION_DISABLE_V90      0x00000080L
-#define PCINIT_MODEMMODULATION_DISABLE_BELL103  0x00000100L
-#define PCINIT_MODEMMODULATION_DISABLE_BELL212A 0x00000200L
-#define PCINIT_MODEMMODULATION_DISABLE_VFC      0x00000400L
-#define PCINIT_MODEMMODULATION_DISABLE_K56FLEX  0x00000800L
-#define PCINIT_MODEMMODULATION_DISABLE_X2       0x00001000L
-#define PCINIT_MODEMMODULATION_ENABLE_V29FDX    0x00010000L
-#define PCINIT_MODEMMODULATION_ENABLE_V33       0x00020000L
-#define PCINIT_MODEMMODULATION_ENABLE_V90A      0x00040000L
-#define PCINIT_MODEM_TRANSMIT_LEVEL_CHOICES     0x10
-#define PCINIT_MODEM_SPEAKER_OFF                0x00
-#define PCINIT_MODEM_SPEAKER_DURING_TRAIN       0x01
-#define PCINIT_MODEM_SPEAKER_TIL_CONNECT        0x02
-#define PCINIT_MODEM_SPEAKER_ALWAYS_ON          0x03
-#define PCINIT_MODEM_SPEAKER_CHOICES            0x04
-#define PCINIT_MODEM_SPEAKER_VOLUME_MIN         0x00
-#define PCINIT_MODEM_SPEAKER_VOLUME_LOW         0x01
-#define PCINIT_MODEM_SPEAKER_VOLUME_HIGH        0x02
-#define PCINIT_MODEM_SPEAKER_VOLUME_MAX         0x03
-#define PCINIT_MODEM_SPEAKER_VOLUME_CHOICES     0x04
-/*------------------------------------------------------------------*/
-#define PCINIT_FAXCONFIG_DISABLE_FINE           0x0001
-#define PCINIT_FAXCONFIG_DISABLE_ECM            0x0002
-#define PCINIT_FAXCONFIG_ECM_64_BYTES           0x0004
-#define PCINIT_FAXCONFIG_DISABLE_2D_CODING      0x0008
-#define PCINIT_FAXCONFIG_DISABLE_T6_CODING      0x0010
-#define PCINIT_FAXCONFIG_DISABLE_UNCOMPR        0x0020
-#define PCINIT_FAXCONFIG_REFUSE_POLLING         0x0040
-#define PCINIT_FAXCONFIG_HIDE_TOTAL_PAGES       0x0080
-#define PCINIT_FAXCONFIG_HIDE_ALL_HEADLINE      0x0100
-#define PCINIT_FAXCONFIG_HIDE_PAGE_INFO         0x0180
-#define PCINIT_FAXCONFIG_HEADLINE_OPTIONS_MASK  0x0180
-#define PCINIT_FAXCONFIG_DISABLE_FEATURE_FALLBACK 0x0200
-#define PCINIT_FAXCONFIG_V34FAX_CONTROL_RATE_1200 0x0800
-#define PCINIT_FAXCONFIG_DISABLE_V34FAX         0x1000
-#define PCINIT_FAXCONFIG_DISABLE_R8_0770_OR_200 0x01
-#define PCINIT_FAXCONFIG_DISABLE_R8_1540        0x02
-#define PCINIT_FAXCONFIG_DISABLE_R16_1540_OR_400 0x04
-#define PCINIT_FAXCONFIG_DISABLE_R4_0385_OR_100 0x08
-#define PCINIT_FAXCONFIG_DISABLE_300_300        0x10
-#define PCINIT_FAXCONFIG_DISABLE_INCH_BASED     0x40
-#define PCINIT_FAXCONFIG_DISABLE_METRIC_BASED   0x80
-#define PCINIT_FAXCONFIG_REC_WIDTH_ISO_A3       0
-#define PCINIT_FAXCONFIG_REC_WIDTH_ISO_B4       1
-#define PCINIT_FAXCONFIG_REC_WIDTH_ISO_A4       2
-#define PCINIT_FAXCONFIG_REC_WIDTH_COUNT        3
-#define PCINIT_FAXCONFIG_REC_LENGTH_UNLIMITED   0
-#define PCINIT_FAXCONFIG_REC_LENGTH_ISO_B4      1
-#define PCINIT_FAXCONFIG_REC_LENGTH_ISO_A4      2
-#define PCINIT_FAXCONFIG_REC_LENGTH_COUNT       3
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_00_00_00 0
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_05_05_05 1
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_10_05_05 2
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_10_10_10 3
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_20_10_10 4
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_20_20_20 5
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_40_20_20 6
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_40_40_40 7
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_RES_8    8
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_RES_9    9
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_RES_10   10
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_10_10_05 11
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_20_10_05 12
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_20_20_10 13
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_40_20_10 14
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_40_40_20 15
-#define PCINIT_FAXCONFIG_SCANLINE_TIME_COUNT    16
-#define PCINIT_FAXCONFIG_DISABLE_TX_REDUCTION   0x00010000L
-#define PCINIT_FAXCONFIG_DISABLE_PRECODING      0x00020000L
-#define PCINIT_FAXCONFIG_DISABLE_PREEMPHASIS    0x00040000L
-#define PCINIT_FAXCONFIG_DISABLE_SHAPING        0x00080000L
-#define PCINIT_FAXCONFIG_DISABLE_NONLINEAR_EN   0x00100000L
-#define PCINIT_FAXCONFIG_DISABLE_MANUALREDUCT   0x00200000L
-#define PCINIT_FAXCONFIG_DISABLE_16_POINT_TRN   0x00400000L
-#define PCINIT_FAXCONFIG_DISABLE_2400_SYMBOLS   0x01000000L
-#define PCINIT_FAXCONFIG_DISABLE_2743_SYMBOLS   0x02000000L
-#define PCINIT_FAXCONFIG_DISABLE_2800_SYMBOLS   0x04000000L
-#define PCINIT_FAXCONFIG_DISABLE_3000_SYMBOLS   0x08000000L
-#define PCINIT_FAXCONFIG_DISABLE_3200_SYMBOLS   0x10000000L
-#define PCINIT_FAXCONFIG_DISABLE_3429_SYMBOLS   0x20000000L
-/*--------------------------------------------------------------------------*/
-#define PCINIT_XDI_CMA_FOR_ALL_NL_PRIMITIVES    0x01
-/*--------------------------------------------------------------------------*/
-#define PCINIT_FPGA_PLX_ACCESS_SUPPORTED        0x01
-/*--------------------------------------------------------------------------*/
-#endif
-/*--------------------------------------------------------------------------*/
diff --git a/drivers/isdn/hardware/eicon/pc_maint.h b/drivers/isdn/hardware/eicon/pc_maint.h
deleted file mode 100644
index 496f018fb5a2..000000000000
--- a/drivers/isdn/hardware/eicon/pc_maint.h
+++ /dev/null
@@ -1,160 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifdef PLATFORM_GT_32BIT
-/* #define POINTER_32BIT byte * __ptr32 */
-#define POINTER_32BIT dword
-#else
-#define POINTER_32BIT byte *
-#endif
-#if !defined(MIPS_SCOM)
-#define BUFFER_SZ  48
-#define MAINT_OFFS 0x380
-#else
-#define BUFFER_SZ  128
-#if defined(PRI)
-#define MAINT_OFFS 0xef00
-#else
-#define MAINT_OFFS 0xff00
-#endif
-#endif
-#define MIPS_BUFFER_SZ  128
-#if defined(PRI)
-#define MIPS_MAINT_OFFS 0xef00
-#else
-#define MIPS_MAINT_OFFS 0xff00
-#endif
-#define LOG                     1
-#define MEMR                    2
-#define MEMW                    3
-#define IOR                     4
-#define IOW                     5
-#define B1TEST                  6
-#define B2TEST                  7
-#define BTESTOFF                8
-#define DSIG_STATS              9
-#define B_CH_STATS              10
-#define D_CH_STATS              11
-#define BL1_STATS               12
-#define BL1_STATS_C             13
-#define GET_VERSION             14
-#define OS_STATS                15
-#define XLOG_SET_MASK           16
-#define XLOG_GET_MASK           17
-#define DSP_READ                20
-#define DSP_WRITE               21
-#define OK 0xff
-#define MORE_EVENTS 0xfe
-#define NO_EVENT 1
-struct DSigStruc
-{
-	byte Id;
-	byte u;
-	byte listen;
-	byte active;
-	byte sin[3];
-	byte bc[6];
-	byte llc[6];
-	byte hlc[6];
-	byte oad[20];
-};
-struct BL1Struc {
-	dword cx_b1;
-	dword cx_b2;
-	dword cr_b1;
-	dword cr_b2;
-	dword px_b1;
-	dword px_b2;
-	dword pr_b1;
-	dword pr_b2;
-	word er_b1;
-	word er_b2;
-};
-struct L2Struc {
-	dword XTotal;
-	dword RTotal;
-	word XError;
-	word RError;
-};
-struct OSStruc {
-	dword free_n;
-};
-typedef union
-{
-	struct DSigStruc DSigStats;
-	struct BL1Struc BL1Stats;
-	struct L2Struc L2Stats;
-	struct OSStruc OSStats;
-	byte   b[BUFFER_SZ];
-	word   w[BUFFER_SZ >> 1];
-	word   l[BUFFER_SZ >> 2]; /* word is wrong, do not use! Use 'd' instead. */
-	dword  d[BUFFER_SZ >> 2];
-} BUFFER;
-typedef union
-{
-	struct DSigStruc DSigStats;
-	struct BL1Struc BL1Stats;
-	struct L2Struc L2Stats;
-	struct OSStruc OSStats;
-	byte   b[MIPS_BUFFER_SZ];
-	word   w[MIPS_BUFFER_SZ >> 1];
-	word   l[BUFFER_SZ >> 2]; /* word is wrong, do not use! Use 'd' instead. */
-	dword  d[MIPS_BUFFER_SZ >> 2];
-} MIPS_BUFFER;
-#if !defined(MIPS_SCOM)
-struct pc_maint
-{
-	byte req;
-	byte rc;
-	POINTER_32BIT mem;
-	short length;
-	word port;
-	byte fill[6];
-	BUFFER data;
-};
-#else
-struct pc_maint
-{
-	byte req;
-	byte rc;
-	byte reserved[2];     /* R3000 alignment ... */
-	POINTER_32BIT mem;
-	short length;
-	word port;
-	byte fill[4];         /* data at offset 16   */
-	BUFFER data;
-};
-#endif
-struct mi_pc_maint
-{
-	byte req;
-	byte rc;
-	byte reserved[2];     /* R3000 alignment ... */
-	POINTER_32BIT mem;
-	short length;
-	word port;
-	byte fill[4];         /* data at offset 16   */
-	MIPS_BUFFER data;
-};
diff --git a/drivers/isdn/hardware/eicon/pkmaint.h b/drivers/isdn/hardware/eicon/pkmaint.h
deleted file mode 100644
index cf3fb14a8e6f..000000000000
--- a/drivers/isdn/hardware/eicon/pkmaint.h
+++ /dev/null
@@ -1,43 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_XDI_OS_DEPENDENT_PACK_MAIN_ON_BYTE_INC__
-#define __DIVA_XDI_OS_DEPENDENT_PACK_MAIN_ON_BYTE_INC__
-
-
-/*
-  Only one purpose of this compiler dependent file to pack
-  structures, described in pc_maint.h so that no padding
-  will be included.
-
-  With microsoft compile it is done by "pshpack1.h" and
-  after is restored by "poppack.h"
-*/
-
-
-#include "pc_maint.h"
-
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/platform.h b/drivers/isdn/hardware/eicon/platform.h
deleted file mode 100644
index 62e2073c3690..000000000000
--- a/drivers/isdn/hardware/eicon/platform.h
+++ /dev/null
@@ -1,369 +0,0 @@
-/* $Id: platform.h,v 1.37.4.6 2005/01/31 12:22:20 armin Exp $
- *
- * platform.h
- *
- *
- * Copyright 2000-2003  by Armin Schindler (mac@melware.de)
- * Copyright 2000  Eicon Networks
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-
-#ifndef	__PLATFORM_H__
-#define	__PLATFORM_H__
-
-#if !defined(DIVA_BUILD)
-#define DIVA_BUILD "local"
-#endif
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/skbuff.h>
-#include <linux/vmalloc.h>
-#include <linux/proc_fs.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/list.h>
-#include <asm/types.h>
-#include <asm/io.h>
-
-#include "cardtype.h"
-
-/* activate debuglib for modules only */
-#ifndef MODULE
-#define DIVA_NO_DEBUGLIB
-#endif
-
-#define DIVA_USER_MODE_CARD_CONFIG 1
-#define	USE_EXTENDED_DEBUGS 1
-
-#define MAX_ADAPTER     32
-
-#define DIVA_ISTREAM 1
-
-#define MEMORY_SPACE_TYPE  0
-#define PORT_SPACE_TYPE    1
-
-
-#include <linux/string.h>
-
-#ifndef	byte
-#define	byte   u8
-#endif
-
-#ifndef	word
-#define	word   u16
-#endif
-
-#ifndef	dword
-#define	dword  u32
-#endif
-
-#ifndef	qword
-#define	qword  u64
-#endif
-
-#ifndef	NULL
-#define	NULL	((void *) 0)
-#endif
-
-#ifndef	far
-#define far
-#endif
-
-#ifndef	_pascal
-#define _pascal
-#endif
-
-#ifndef	_loadds
-#define _loadds
-#endif
-
-#ifndef	_cdecl
-#define _cdecl
-#endif
-
-#define MEM_TYPE_RAM		0
-#define MEM_TYPE_PORT		1
-#define MEM_TYPE_PROM		2
-#define MEM_TYPE_CTLREG		3
-#define MEM_TYPE_RESET		4
-#define MEM_TYPE_CFG		5
-#define MEM_TYPE_ADDRESS	6
-#define MEM_TYPE_CONFIG		7
-#define MEM_TYPE_CONTROL	8
-
-#define MAX_MEM_TYPE		10
-
-#define DIVA_OS_MEM_ATTACH_RAM(a)	((a)->ram)
-#define DIVA_OS_MEM_ATTACH_PORT(a)	((a)->port)
-#define DIVA_OS_MEM_ATTACH_PROM(a)	((a)->prom)
-#define DIVA_OS_MEM_ATTACH_CTLREG(a)	((a)->ctlReg)
-#define DIVA_OS_MEM_ATTACH_RESET(a)	((a)->reset)
-#define DIVA_OS_MEM_ATTACH_CFG(a)	((a)->cfg)
-#define DIVA_OS_MEM_ATTACH_ADDRESS(a)	((a)->Address)
-#define DIVA_OS_MEM_ATTACH_CONFIG(a)	((a)->Config)
-#define DIVA_OS_MEM_ATTACH_CONTROL(a)	((a)->Control)
-
-#define DIVA_OS_MEM_DETACH_RAM(a, x)	do { } while (0)
-#define DIVA_OS_MEM_DETACH_PORT(a, x)	do { } while (0)
-#define DIVA_OS_MEM_DETACH_PROM(a, x)	do { } while (0)
-#define DIVA_OS_MEM_DETACH_CTLREG(a, x)	do { } while (0)
-#define DIVA_OS_MEM_DETACH_RESET(a, x)	do { } while (0)
-#define DIVA_OS_MEM_DETACH_CFG(a, x)	do { } while (0)
-#define DIVA_OS_MEM_DETACH_ADDRESS(a, x)	do { } while (0)
-#define DIVA_OS_MEM_DETACH_CONFIG(a, x)	do { } while (0)
-#define DIVA_OS_MEM_DETACH_CONTROL(a, x)	do { } while (0)
-
-#define DIVA_INVALID_FILE_HANDLE  ((dword)(-1))
-
-#define DIVAS_CONTAINING_RECORD(address, type, field)			\
-	((type *)((char *)(address) - (char *)(&((type *)0)->field)))
-
-extern int sprintf(char *, const char *, ...);
-
-typedef void *LIST_ENTRY;
-
-typedef char DEVICE_NAME[64];
-typedef struct _ISDN_ADAPTER ISDN_ADAPTER;
-typedef struct _ISDN_ADAPTER *PISDN_ADAPTER;
-
-typedef void (*DIVA_DI_PRINTF)(unsigned char *, ...);
-#include "debuglib.h"
-
-#define dtrc(p) DBG_PRV0(p)
-#define dbug(a, p) DBG_PRV1(p)
-
-
-typedef struct e_info_s E_INFO;
-
-typedef char diva_os_dependent_devica_name_t[64];
-typedef void *PDEVICE_OBJECT;
-
-struct _diva_os_soft_isr;
-struct _diva_os_timer;
-struct _ISDN_ADAPTER;
-
-void diva_log_info(unsigned char *, ...);
-
-/*
-**  XDI DIDD Interface
-*/
-void diva_xdi_didd_register_adapter(int card);
-void diva_xdi_didd_remove_adapter(int card);
-
-/*
-** memory allocation
-*/
-static __inline__ void *diva_os_malloc(unsigned long flags, unsigned long size)
-{
-	void *ret = NULL;
-
-	if (size) {
-		ret = (void *) vmalloc((unsigned int) size);
-	}
-	return (ret);
-}
-static __inline__ void diva_os_free(unsigned long flags, void *ptr)
-{
-	vfree(ptr);
-}
-
-/*
-** use skbuffs for message buffer
-*/
-typedef struct sk_buff diva_os_message_buffer_s;
-diva_os_message_buffer_s *diva_os_alloc_message_buffer(unsigned long size, void **data_buf);
-void diva_os_free_message_buffer(diva_os_message_buffer_s *dmb);
-#define DIVA_MESSAGE_BUFFER_LEN(x) x->len
-#define DIVA_MESSAGE_BUFFER_DATA(x) x->data
-
-/*
-** mSeconds waiting
-*/
-static __inline__ void diva_os_sleep(dword mSec)
-{
-	msleep(mSec);
-}
-static __inline__ void diva_os_wait(dword mSec)
-{
-	mdelay(mSec);
-}
-
-/*
-**  PCI Configuration space access
-*/
-void PCIwrite(byte bus, byte func, int offset, void *data, int length, void *pci_dev_handle);
-void PCIread(byte bus, byte func, int offset, void *data, int length, void *pci_dev_handle);
-
-/*
-**  I/O Port utilities
-*/
-int diva_os_register_io_port(void *adapter, int reg, unsigned long port,
-			     unsigned long length, const char *name, int id);
-/*
-**  I/O port access abstraction
-*/
-byte inpp(void __iomem *);
-word inppw(void __iomem *);
-void inppw_buffer(void __iomem *, void *, int);
-void outppw(void __iomem *, word);
-void outppw_buffer(void __iomem * , void*, int);
-void outpp(void __iomem *, word);
-
-/*
-**  IRQ
-*/
-typedef struct _diva_os_adapter_irq_info {
-	byte irq_nr;
-	int  registered;
-	char irq_name[24];
-} diva_os_adapter_irq_info_t;
-int diva_os_register_irq(void *context, byte irq, const char *name);
-void diva_os_remove_irq(void *context, byte irq);
-
-#define diva_os_in_irq() in_irq()
-
-/*
-**  Spin Lock framework
-*/
-typedef long diva_os_spin_lock_magic_t;
-typedef spinlock_t diva_os_spin_lock_t;
-static __inline__ int diva_os_initialize_spin_lock(spinlock_t *lock, void *unused) { \
-	spin_lock_init(lock); return (0); }
-static __inline__ void diva_os_enter_spin_lock(diva_os_spin_lock_t *a, \
-					       diva_os_spin_lock_magic_t *old_irql, \
-					       void *dbg) { spin_lock_bh(a); }
-static __inline__ void diva_os_leave_spin_lock(diva_os_spin_lock_t *a, \
-					       diva_os_spin_lock_magic_t *old_irql, \
-					       void *dbg) { spin_unlock_bh(a); }
-
-#define diva_os_destroy_spin_lock(a, b) do { } while (0)
-
-/*
-**  Deffered processing framework
-*/
-typedef int (*diva_os_isr_callback_t)(struct _ISDN_ADAPTER *);
-typedef void (*diva_os_soft_isr_callback_t)(struct _diva_os_soft_isr *psoft_isr, void *context);
-
-typedef struct _diva_os_soft_isr {
-	void *object;
-	diva_os_soft_isr_callback_t callback;
-	void *callback_context;
-	char dpc_thread_name[24];
-} diva_os_soft_isr_t;
-
-int diva_os_initialize_soft_isr(diva_os_soft_isr_t *psoft_isr, diva_os_soft_isr_callback_t callback, void *callback_context);
-int diva_os_schedule_soft_isr(diva_os_soft_isr_t *psoft_isr);
-int diva_os_cancel_soft_isr(diva_os_soft_isr_t *psoft_isr);
-void diva_os_remove_soft_isr(diva_os_soft_isr_t *psoft_isr);
-
-/*
-  Get time service
-*/
-void diva_os_get_time(dword *sec, dword *usec);
-
-/*
-**  atomic operation, fake because we use threads
-*/
-typedef int diva_os_atomic_t;
-static inline diva_os_atomic_t
-diva_os_atomic_increment(diva_os_atomic_t *pv)
-{
-	*pv += 1;
-	return (*pv);
-}
-static inline diva_os_atomic_t
-diva_os_atomic_decrement(diva_os_atomic_t *pv)
-{
-	*pv -= 1;
-	return (*pv);
-}
-
-/*
-**  CAPI SECTION
-*/
-#define NO_CORNETN
-#define IMPLEMENT_DTMF 1
-#define IMPLEMENT_ECHO_CANCELLER 1
-#define IMPLEMENT_RTP 1
-#define IMPLEMENT_T38 1
-#define IMPLEMENT_FAX_SUB_SEP_PWD 1
-#define IMPLEMENT_V18 1
-#define IMPLEMENT_DTMF_TONE 1
-#define IMPLEMENT_PIAFS 1
-#define IMPLEMENT_FAX_PAPER_FORMATS 1
-#define IMPLEMENT_VOWN 1
-#define IMPLEMENT_CAPIDTMF 1
-#define IMPLEMENT_FAX_NONSTANDARD 1
-#define VSWITCH_SUPPORT 1
-
-#define IMPLEMENT_MARKED_OK_AFTER_FC 1
-
-#define DIVA_IDI_RX_DMA 1
-
-/*
-** endian macros
-**
-** If only...  In some cases we did use them for endianness conversion;
-** unfortunately, other uses were real iomem accesses.
-*/
-#define READ_BYTE(addr)   readb(addr)
-#define READ_WORD(addr)   readw(addr)
-#define READ_DWORD(addr)  readl(addr)
-
-#define WRITE_BYTE(addr, v)  writeb(v, addr)
-#define WRITE_WORD(addr, v)  writew(v, addr)
-#define WRITE_DWORD(addr, v) writel(v, addr)
-
-static inline __u16 GET_WORD(void *addr)
-{
-	return le16_to_cpu(*(__le16 *)addr);
-}
-static inline __u32 GET_DWORD(void *addr)
-{
-	return le32_to_cpu(*(__le32 *)addr);
-}
-static inline void PUT_WORD(void *addr, __u16 v)
-{
-	*(__le16 *)addr = cpu_to_le16(v);
-}
-static inline void PUT_DWORD(void *addr, __u32 v)
-{
-	*(__le32 *)addr = cpu_to_le32(v);
-}
-
-/*
-** 32/64 bit macors
-*/
-#ifdef BITS_PER_LONG
-#if BITS_PER_LONG > 32
-#define PLATFORM_GT_32BIT
-#define ULongToPtr(x) (void *)(unsigned long)(x)
-#endif
-#endif
-
-/*
-** undef os definitions of macros we use
-*/
-#undef ID_MASK
-#undef N_DATA
-#undef ADDR
-
-/*
-** dump file
-*/
-#define diva_os_dump_file_t char
-#define diva_os_board_trace_t char
-#define diva_os_dump_file(__x__) do { } while (0)
-
-/*
-** size of internal arrays
-*/
-#define MAX_DESCRIPTORS 64
-
-#endif	/* __PLATFORM_H__ */
diff --git a/drivers/isdn/hardware/eicon/pr_pc.h b/drivers/isdn/hardware/eicon/pr_pc.h
deleted file mode 100644
index a08d6d57a486..000000000000
--- a/drivers/isdn/hardware/eicon/pr_pc.h
+++ /dev/null
@@ -1,76 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-struct pr_ram {
-	word NextReq;         /* pointer to next Req Buffer               */
-	word NextRc;          /* pointer to next Rc Buffer                */
-	word NextInd;         /* pointer to next Ind Buffer               */
-	byte ReqInput;        /* number of Req Buffers sent               */
-	byte ReqOutput;       /* number of Req Buffers returned           */
-	byte ReqReserved;     /* number of Req Buffers reserved           */
-	byte Int;             /* ISDN-P interrupt                         */
-	byte XLock;           /* Lock field for arbitration               */
-	byte RcOutput;        /* number of Rc buffers received            */
-	byte IndOutput;       /* number of Ind buffers received           */
-	byte IMask;           /* Interrupt Mask Flag                      */
-	byte Reserved1[2];    /* reserved field, do not use               */
-	byte ReadyInt;        /* request field for ready interrupt        */
-	byte Reserved2[12];   /* reserved field, do not use               */
-	byte InterfaceType;   /* interface type 1=16K interface           */
-	word Signature;       /* ISDN-P initialized indication            */
-	byte B[1];            /* buffer space for Req,Ind and Rc          */
-};
-typedef struct {
-	word next;
-	byte Req;
-	byte ReqId;
-	byte ReqCh;
-	byte Reserved1;
-	word Reference;
-	byte Reserved[8];
-	PBUFFER XBuffer;
-} REQ;
-typedef struct {
-	word next;
-	byte Rc;
-	byte RcId;
-	byte RcCh;
-	byte Reserved1;
-	word Reference;
-	byte Reserved2[8];
-} RC;
-typedef struct {
-	word next;
-	byte Ind;
-	byte IndId;
-	byte IndCh;
-	byte MInd;
-	word MLength;
-	word Reference;
-	byte RNR;
-	byte Reserved;
-	dword Ack;
-	PBUFFER RBuffer;
-} IND;
diff --git a/drivers/isdn/hardware/eicon/s_4bri.c b/drivers/isdn/hardware/eicon/s_4bri.c
deleted file mode 100644
index ec12165fbf62..000000000000
--- a/drivers/isdn/hardware/eicon/s_4bri.c
+++ /dev/null
@@ -1,510 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#include "platform.h"
-#include "di_defs.h"
-#include "pc.h"
-#include "pr_pc.h"
-#include "di.h"
-#include "mi_pc.h"
-#include "pc_maint.h"
-#include "divasync.h"
-#include "pc_init.h"
-#include "io.h"
-#include "helpers.h"
-#include "dsrv4bri.h"
-#include "dsp_defs.h"
-#include "sdp_hdr.h"
-
-/*****************************************************************************/
-#define	MAX_XLOG_SIZE	(64 * 1024)
-
-/* --------------------------------------------------------------------------
-   Recovery XLOG from QBRI Card
-   -------------------------------------------------------------------------- */
-static void qBri_cpu_trapped(PISDN_ADAPTER IoAdapter) {
-	byte  __iomem *base;
-	word *Xlog;
-	dword   regs[4], TrapID, offset, size;
-	Xdesc   xlogDesc;
-	int factor = (IoAdapter->tasks == 1) ? 1 : 2;
-
-/*
- *	check for trapped MIPS 46xx CPU, dump exception frame
- */
-
-	base = DIVA_OS_MEM_ATTACH_CONTROL(IoAdapter);
-	offset = IoAdapter->ControllerNumber * (IoAdapter->MemorySize >> factor);
-
-	TrapID = READ_DWORD(&base[0x80]);
-
-	if ((TrapID == 0x99999999) || (TrapID == 0x99999901))
-	{
-		dump_trap_frame(IoAdapter, &base[0x90]);
-		IoAdapter->trapped = 1;
-	}
-
-	regs[0] = READ_DWORD((base + offset) + 0x70);
-	regs[1] = READ_DWORD((base + offset) + 0x74);
-	regs[2] = READ_DWORD((base + offset) + 0x78);
-	regs[3] = READ_DWORD((base + offset) + 0x7c);
-	regs[0] &= IoAdapter->MemorySize - 1;
-
-	if ((regs[0] >= offset)
-	    && (regs[0] < offset + (IoAdapter->MemorySize >> factor) - 1))
-	{
-		if (!(Xlog = (word *)diva_os_malloc(0, MAX_XLOG_SIZE))) {
-			DIVA_OS_MEM_DETACH_CONTROL(IoAdapter, base);
-			return;
-		}
-
-		size = offset + (IoAdapter->MemorySize >> factor) - regs[0];
-		if (size > MAX_XLOG_SIZE)
-			size = MAX_XLOG_SIZE;
-		memcpy_fromio(Xlog, &base[regs[0]], size);
-		xlogDesc.buf = Xlog;
-		xlogDesc.cnt = READ_WORD(&base[regs[1] & (IoAdapter->MemorySize - 1)]);
-		xlogDesc.out = READ_WORD(&base[regs[2] & (IoAdapter->MemorySize - 1)]);
-		dump_xlog_buffer(IoAdapter, &xlogDesc);
-		diva_os_free(0, Xlog);
-		IoAdapter->trapped = 2;
-	}
-	DIVA_OS_MEM_DETACH_CONTROL(IoAdapter, base);
-}
-
-/* --------------------------------------------------------------------------
-   Reset QBRI Hardware
-   -------------------------------------------------------------------------- */
-static void reset_qBri_hardware(PISDN_ADAPTER IoAdapter) {
-	word volatile __iomem *qBriReset;
-	byte  volatile __iomem *qBriCntrl;
-	byte  volatile __iomem *p;
-
-	qBriReset = (word volatile __iomem *)DIVA_OS_MEM_ATTACH_PROM(IoAdapter);
-	WRITE_WORD(qBriReset, READ_WORD(qBriReset) | PLX9054_SOFT_RESET);
-	diva_os_wait(1);
-	WRITE_WORD(qBriReset, READ_WORD(qBriReset) & ~PLX9054_SOFT_RESET);
-	diva_os_wait(1);
-	WRITE_WORD(qBriReset, READ_WORD(qBriReset) | PLX9054_RELOAD_EEPROM);
-	diva_os_wait(1);
-	WRITE_WORD(qBriReset, READ_WORD(qBriReset) & ~PLX9054_RELOAD_EEPROM);
-	diva_os_wait(1);
-	DIVA_OS_MEM_DETACH_PROM(IoAdapter, qBriReset);
-
-	qBriCntrl = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	p = &qBriCntrl[DIVA_4BRI_REVISION(IoAdapter) ? (MQ2_BREG_RISC) : (MQ_BREG_RISC)];
-	WRITE_DWORD(p, 0);
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, qBriCntrl);
-
-	DBG_TRC(("resetted board @ reset addr 0x%08lx", qBriReset))
-		DBG_TRC(("resetted board @ cntrl addr 0x%08lx", p))
-		}
-
-/* --------------------------------------------------------------------------
-   Start Card CPU
-   -------------------------------------------------------------------------- */
-void start_qBri_hardware(PISDN_ADAPTER IoAdapter) {
-	byte volatile __iomem *qBriReset;
-	byte volatile __iomem *p;
-
-	p = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	qBriReset = &p[(DIVA_4BRI_REVISION(IoAdapter)) ? (MQ2_BREG_RISC) : (MQ_BREG_RISC)];
-	WRITE_DWORD(qBriReset, MQ_RISC_COLD_RESET_MASK);
-	diva_os_wait(2);
-	WRITE_DWORD(qBriReset, MQ_RISC_WARM_RESET_MASK | MQ_RISC_COLD_RESET_MASK);
-	diva_os_wait(10);
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, p);
-
-	DBG_TRC(("started processor @ addr 0x%08lx", qBriReset))
-		}
-
-/* --------------------------------------------------------------------------
-   Stop Card CPU
-   -------------------------------------------------------------------------- */
-static void stop_qBri_hardware(PISDN_ADAPTER IoAdapter) {
-	byte volatile __iomem *p;
-	dword volatile __iomem *qBriReset;
-	dword volatile __iomem *qBriIrq;
-	dword volatile __iomem *qBriIsacDspReset;
-	int rev2 = DIVA_4BRI_REVISION(IoAdapter);
-	int reset_offset = rev2 ? (MQ2_BREG_RISC)      : (MQ_BREG_RISC);
-	int irq_offset   = rev2 ? (MQ2_BREG_IRQ_TEST)  : (MQ_BREG_IRQ_TEST);
-	int hw_offset    = rev2 ? (MQ2_ISAC_DSP_RESET) : (MQ_ISAC_DSP_RESET);
-
-	if (IoAdapter->ControllerNumber > 0)
-		return;
-	p = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	qBriReset = (dword volatile __iomem *)&p[reset_offset];
-	qBriIsacDspReset = (dword volatile __iomem *)&p[hw_offset];
-/*
- *	clear interrupt line (reset Local Interrupt Test Register)
- */
-	WRITE_DWORD(qBriReset, 0);
-	WRITE_DWORD(qBriIsacDspReset, 0);
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, p);
-
-	p = DIVA_OS_MEM_ATTACH_RESET(IoAdapter);
-	WRITE_BYTE(&p[PLX9054_INTCSR], 0x00);	/* disable PCI interrupts */
-	DIVA_OS_MEM_DETACH_RESET(IoAdapter, p);
-
-	p = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	qBriIrq   = (dword volatile __iomem *)&p[irq_offset];
-	WRITE_DWORD(qBriIrq, MQ_IRQ_REQ_OFF);
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, p);
-
-	DBG_TRC(("stopped processor @ addr 0x%08lx", qBriReset))
-
-		}
-
-/* --------------------------------------------------------------------------
-   FPGA download
-   -------------------------------------------------------------------------- */
-#define FPGA_NAME_OFFSET         0x10
-
-static byte *qBri_check_FPGAsrc(PISDN_ADAPTER IoAdapter, char *FileName,
-				dword *Length, dword *code) {
-	byte *File;
-	char *fpgaFile, *fpgaType, *fpgaDate, *fpgaTime;
-	dword fpgaFlen, fpgaTlen, fpgaDlen, cnt, year, i;
-
-	if (!(File = (byte *)xdiLoadFile(FileName, Length, 0))) {
-		return (NULL);
-	}
-/*
- *	 scan file until FF and put id string into buffer
- */
-	for (i = 0; File[i] != 0xff;)
-	{
-		if (++i >= *Length)
-		{
-			DBG_FTL(("FPGA download: start of data header not found"))
-				xdiFreeFile(File);
-			return (NULL);
-		}
-	}
-	*code = i++;
-
-	if ((File[i] & 0xF0) != 0x20)
-	{
-		DBG_FTL(("FPGA download: data header corrupted"))
-			xdiFreeFile(File);
-		return (NULL);
-	}
-	fpgaFlen = (dword)File[FPGA_NAME_OFFSET - 1];
-	if (fpgaFlen == 0)
-		fpgaFlen = 12;
-	fpgaFile = (char *)&File[FPGA_NAME_OFFSET];
-	fpgaTlen = (dword)fpgaFile[fpgaFlen + 2];
-	if (fpgaTlen == 0)
-		fpgaTlen = 10;
-	fpgaType = (char *)&fpgaFile[fpgaFlen + 3];
-	fpgaDlen = (dword)  fpgaType[fpgaTlen + 2];
-	if (fpgaDlen == 0)
-		fpgaDlen = 11;
-	fpgaDate = (char *)&fpgaType[fpgaTlen + 3];
-	fpgaTime = (char *)&fpgaDate[fpgaDlen + 3];
-	cnt = (dword)(((File[i] & 0x0F) << 20) + (File[i + 1] << 12)
-		      + (File[i + 2] << 4) + (File[i + 3] >> 4));
-
-	if ((dword)(i + (cnt / 8)) > *Length)
-	{
-		DBG_FTL(("FPGA download: '%s' file too small (%ld < %ld)",
-			 FileName, *Length, code + ((cnt + 7) / 8)))
-			xdiFreeFile(File);
-		return (NULL);
-	}
-	i = 0;
-	do
-	{
-		while ((fpgaDate[i] != '\0')
-		       && ((fpgaDate[i] < '0') || (fpgaDate[i] > '9')))
-		{
-			i++;
-		}
-		year = 0;
-		while ((fpgaDate[i] >= '0') && (fpgaDate[i] <= '9'))
-			year = year * 10 + (fpgaDate[i++] - '0');
-	} while ((year < 2000) && (fpgaDate[i] != '\0'));
-
-	switch (IoAdapter->cardType) {
-	case CARDTYPE_DIVASRV_B_2F_PCI:
-		break;
-
-	default:
-		if (year >= 2001) {
-			IoAdapter->fpga_features |= PCINIT_FPGA_PLX_ACCESS_SUPPORTED;
-		}
-	}
-
-	DBG_LOG(("FPGA[%s] file %s (%s %s) len %d",
-		 fpgaType, fpgaFile, fpgaDate, fpgaTime, cnt))
-		return (File);
-}
-
-/******************************************************************************/
-
-#define FPGA_PROG   0x0001		/* PROG enable low */
-#define FPGA_BUSY   0x0002		/* BUSY high, DONE low */
-#define	FPGA_CS     0x000C		/* Enable I/O pins */
-#define FPGA_CCLK   0x0100
-#define FPGA_DOUT   0x0400
-#define FPGA_DIN    FPGA_DOUT   /* bidirectional I/O */
-
-int qBri_FPGA_download(PISDN_ADAPTER IoAdapter) {
-	int            bit;
-	byte           *File;
-	dword          code, FileLength;
-	word volatile __iomem *addr = (word volatile __iomem *)DIVA_OS_MEM_ATTACH_PROM(IoAdapter);
-	word           val, baseval = FPGA_CS | FPGA_PROG;
-
-
-
-	if (DIVA_4BRI_REVISION(IoAdapter))
-	{
-		char *name;
-
-		switch (IoAdapter->cardType) {
-		case CARDTYPE_DIVASRV_B_2F_PCI:
-			name = "dsbri2f.bit";
-			break;
-
-		case CARDTYPE_DIVASRV_B_2M_V2_PCI:
-		case CARDTYPE_DIVASRV_VOICE_B_2M_V2_PCI:
-			name = "dsbri2m.bit";
-			break;
-
-		default:
-			name = "ds4bri2.bit";
-		}
-
-		File = qBri_check_FPGAsrc(IoAdapter, name,
-					  &FileLength, &code);
-	}
-	else
-	{
-		File = qBri_check_FPGAsrc(IoAdapter, "ds4bri.bit",
-					  &FileLength, &code);
-	}
-	if (!File) {
-		DIVA_OS_MEM_DETACH_PROM(IoAdapter, addr);
-		return (0);
-	}
-/*
- *	prepare download, pulse PROGRAM pin down.
- */
-	WRITE_WORD(addr, baseval & ~FPGA_PROG); /* PROGRAM low pulse */
-	WRITE_WORD(addr, baseval);              /* release */
-	diva_os_wait(50);  /* wait until FPGA finished internal memory clear */
-/*
- *	check done pin, must be low
- */
-	if (READ_WORD(addr) & FPGA_BUSY)
-	{
-		DBG_FTL(("FPGA download: acknowledge for FPGA memory clear missing"))
-			xdiFreeFile(File);
-		DIVA_OS_MEM_DETACH_PROM(IoAdapter, addr);
-		return (0);
-	}
-/*
- *	put data onto the FPGA
- */
-	while (code < FileLength)
-	{
-		val = ((word)File[code++]) << 3;
-
-		for (bit = 8; bit-- > 0; val <<= 1) /* put byte onto FPGA */
-		{
-			baseval &= ~FPGA_DOUT;             /* clr  data bit */
-			baseval |= (val & FPGA_DOUT);      /* copy data bit */
-			WRITE_WORD(addr, baseval);
-			WRITE_WORD(addr, baseval | FPGA_CCLK);     /* set CCLK hi */
-			WRITE_WORD(addr, baseval | FPGA_CCLK);     /* set CCLK hi */
-			WRITE_WORD(addr, baseval);                 /* set CCLK lo */
-		}
-	}
-	xdiFreeFile(File);
-	diva_os_wait(100);
-	val = READ_WORD(addr);
-
-	DIVA_OS_MEM_DETACH_PROM(IoAdapter, addr);
-
-	if (!(val & FPGA_BUSY))
-	{
-		DBG_FTL(("FPGA download: chip remains in busy state (0x%04x)", val))
-			return (0);
-	}
-
-	return (1);
-}
-
-static int load_qBri_hardware(PISDN_ADAPTER IoAdapter) {
-	return (0);
-}
-
-/* --------------------------------------------------------------------------
-   Card ISR
-   -------------------------------------------------------------------------- */
-static int qBri_ISR(struct _ISDN_ADAPTER *IoAdapter) {
-	dword volatile     __iomem *qBriIrq;
-
-	PADAPTER_LIST_ENTRY QuadroList = IoAdapter->QuadroList;
-
-	word			i;
-	int			serviced = 0;
-	byte __iomem *p;
-
-	p = DIVA_OS_MEM_ATTACH_RESET(IoAdapter);
-
-	if (!(READ_BYTE(&p[PLX9054_INTCSR]) & 0x80)) {
-		DIVA_OS_MEM_DETACH_RESET(IoAdapter, p);
-		return (0);
-	}
-	DIVA_OS_MEM_DETACH_RESET(IoAdapter, p);
-
-/*
- *	clear interrupt line (reset Local Interrupt Test Register)
- */
-	p = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	qBriIrq = (dword volatile __iomem *)(&p[DIVA_4BRI_REVISION(IoAdapter) ? (MQ2_BREG_IRQ_TEST)  : (MQ_BREG_IRQ_TEST)]);
-	WRITE_DWORD(qBriIrq, MQ_IRQ_REQ_OFF);
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, p);
-
-	for (i = 0; i < IoAdapter->tasks; ++i)
-	{
-		IoAdapter = QuadroList->QuadroAdapter[i];
-
-		if (IoAdapter && IoAdapter->Initialized
-		    && IoAdapter->tst_irq(&IoAdapter->a))
-		{
-			IoAdapter->IrqCount++;
-			serviced = 1;
-			diva_os_schedule_soft_isr(&IoAdapter->isr_soft_isr);
-		}
-	}
-
-	return (serviced);
-}
-
-/* --------------------------------------------------------------------------
-   Does disable the interrupt on the card
-   -------------------------------------------------------------------------- */
-static void disable_qBri_interrupt(PISDN_ADAPTER IoAdapter) {
-	dword volatile __iomem *qBriIrq;
-	byte __iomem *p;
-
-	if (IoAdapter->ControllerNumber > 0)
-		return;
-/*
- *	clear interrupt line (reset Local Interrupt Test Register)
- */
-	p = DIVA_OS_MEM_ATTACH_RESET(IoAdapter);
-	WRITE_BYTE(&p[PLX9054_INTCSR], 0x00);	/* disable PCI interrupts */
-	DIVA_OS_MEM_DETACH_RESET(IoAdapter, p);
-
-	p = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	qBriIrq = (dword volatile __iomem *)(&p[DIVA_4BRI_REVISION(IoAdapter) ? (MQ2_BREG_IRQ_TEST)  : (MQ_BREG_IRQ_TEST)]);
-	WRITE_DWORD(qBriIrq, MQ_IRQ_REQ_OFF);
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, p);
-}
-
-/* --------------------------------------------------------------------------
-   Install Adapter Entry Points
-   -------------------------------------------------------------------------- */
-static void set_common_qBri_functions(PISDN_ADAPTER IoAdapter) {
-	ADAPTER *a;
-
-	a = &IoAdapter->a;
-
-	a->ram_in           = mem_in;
-	a->ram_inw          = mem_inw;
-	a->ram_in_buffer    = mem_in_buffer;
-	a->ram_look_ahead   = mem_look_ahead;
-	a->ram_out          = mem_out;
-	a->ram_outw         = mem_outw;
-	a->ram_out_buffer   = mem_out_buffer;
-	a->ram_inc          = mem_inc;
-
-	IoAdapter->out = pr_out;
-	IoAdapter->dpc = pr_dpc;
-	IoAdapter->tst_irq = scom_test_int;
-	IoAdapter->clr_irq  = scom_clear_int;
-	IoAdapter->pcm  = (struct pc_maint *)MIPS_MAINT_OFFS;
-
-	IoAdapter->load = load_qBri_hardware;
-
-	IoAdapter->disIrq = disable_qBri_interrupt;
-	IoAdapter->rstFnc = reset_qBri_hardware;
-	IoAdapter->stop = stop_qBri_hardware;
-	IoAdapter->trapFnc = qBri_cpu_trapped;
-
-	IoAdapter->diva_isr_handler = qBri_ISR;
-
-	IoAdapter->a.io = (void *)IoAdapter;
-}
-
-static void set_qBri_functions(PISDN_ADAPTER IoAdapter) {
-	if (!IoAdapter->tasks) {
-		IoAdapter->tasks = MQ_INSTANCE_COUNT;
-	}
-	IoAdapter->MemorySize = MQ_MEMORY_SIZE;
-	set_common_qBri_functions(IoAdapter);
-	diva_os_set_qBri_functions(IoAdapter);
-}
-
-static void set_qBri2_functions(PISDN_ADAPTER IoAdapter) {
-	if (!IoAdapter->tasks) {
-		IoAdapter->tasks = MQ_INSTANCE_COUNT;
-	}
-	IoAdapter->MemorySize = (IoAdapter->tasks == 1) ? BRI2_MEMORY_SIZE : MQ2_MEMORY_SIZE;
-	set_common_qBri_functions(IoAdapter);
-	diva_os_set_qBri2_functions(IoAdapter);
-}
-
-/******************************************************************************/
-
-void prepare_qBri_functions(PISDN_ADAPTER IoAdapter) {
-
-	set_qBri_functions(IoAdapter->QuadroList->QuadroAdapter[0]);
-	set_qBri_functions(IoAdapter->QuadroList->QuadroAdapter[1]);
-	set_qBri_functions(IoAdapter->QuadroList->QuadroAdapter[2]);
-	set_qBri_functions(IoAdapter->QuadroList->QuadroAdapter[3]);
-
-}
-
-void prepare_qBri2_functions(PISDN_ADAPTER IoAdapter) {
-	if (!IoAdapter->tasks) {
-		IoAdapter->tasks = MQ_INSTANCE_COUNT;
-	}
-
-	set_qBri2_functions(IoAdapter->QuadroList->QuadroAdapter[0]);
-	if (IoAdapter->tasks > 1) {
-		set_qBri2_functions(IoAdapter->QuadroList->QuadroAdapter[1]);
-		set_qBri2_functions(IoAdapter->QuadroList->QuadroAdapter[2]);
-		set_qBri2_functions(IoAdapter->QuadroList->QuadroAdapter[3]);
-	}
-
-}
-
-/* -------------------------------------------------------------------------- */
diff --git a/drivers/isdn/hardware/eicon/s_bri.c b/drivers/isdn/hardware/eicon/s_bri.c
deleted file mode 100644
index 6a5bb7462339..000000000000
--- a/drivers/isdn/hardware/eicon/s_bri.c
+++ /dev/null
@@ -1,191 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#include "platform.h"
-#include "di_defs.h"
-#include "pc.h"
-#include "pr_pc.h"
-#include "di.h"
-#include "mi_pc.h"
-#include "pc_maint.h"
-#include "divasync.h"
-#include "io.h"
-#include "helpers.h"
-#include "dsrv_bri.h"
-#include "dsp_defs.h"
-/*****************************************************************************/
-#define MAX_XLOG_SIZE (64 * 1024)
-/* --------------------------------------------------------------------------
-   Investigate card state, recovery trace buffer
-   -------------------------------------------------------------------------- */
-static void bri_cpu_trapped(PISDN_ADAPTER IoAdapter) {
-	byte  __iomem *addrHi, *addrLo, *ioaddr;
-	word *Xlog;
-	dword   regs[4], i, size;
-	Xdesc   xlogDesc;
-	byte __iomem *Port;
-/*
- * first read pointers and trap frame
- */
-	if (!(Xlog = (word *)diva_os_malloc(0, MAX_XLOG_SIZE)))
-		return;
-	Port = DIVA_OS_MEM_ATTACH_PORT(IoAdapter);
-	addrHi = Port + ((IoAdapter->Properties.Bus == BUS_PCI) ? M_PCI_ADDRH : ADDRH);
-	addrLo = Port + ADDR;
-	ioaddr = Port + DATA;
-	outpp(addrHi,  0);
-	outppw(addrLo, 0);
-	for (i = 0; i < 0x100; Xlog[i++] = inppw(ioaddr));
-/*
- * check for trapped MIPS 3xxx CPU, dump only exception frame
- */
-	if (GET_DWORD(&Xlog[0x80 / sizeof(Xlog[0])]) == 0x99999999)
-	{
-		dump_trap_frame(IoAdapter, &((byte *)Xlog)[0x90]);
-		IoAdapter->trapped = 1;
-	}
-	regs[0] = GET_DWORD(&((byte *)Xlog)[0x70]);
-	regs[1] = GET_DWORD(&((byte *)Xlog)[0x74]);
-	regs[2] = GET_DWORD(&((byte *)Xlog)[0x78]);
-	regs[3] = GET_DWORD(&((byte *)Xlog)[0x7c]);
-	outpp(addrHi, (regs[1] >> 16) & 0x7F);
-	outppw(addrLo, regs[1] & 0xFFFF);
-	xlogDesc.cnt = inppw(ioaddr);
-	outpp(addrHi, (regs[2] >> 16) & 0x7F);
-	outppw(addrLo, regs[2] & 0xFFFF);
-	xlogDesc.out = inppw(ioaddr);
-	xlogDesc.buf = Xlog;
-	regs[0] &= IoAdapter->MemorySize - 1;
-	if ((regs[0] < IoAdapter->MemorySize - 1))
-	{
-		size = IoAdapter->MemorySize - regs[0];
-		if (size > MAX_XLOG_SIZE)
-			size = MAX_XLOG_SIZE;
-		for (i = 0; i < (size / sizeof(*Xlog)); regs[0] += 2)
-		{
-			outpp(addrHi, (regs[0] >> 16) & 0x7F);
-			outppw(addrLo, regs[0] & 0xFFFF);
-			Xlog[i++] = inppw(ioaddr);
-		}
-		dump_xlog_buffer(IoAdapter, &xlogDesc);
-		diva_os_free(0, Xlog);
-		IoAdapter->trapped = 2;
-	}
-	outpp(addrHi, (byte)((BRI_UNCACHED_ADDR(IoAdapter->MemoryBase + IoAdapter->MemorySize -
-						BRI_SHARED_RAM_SIZE)) >> 16));
-	outppw(addrLo, 0x00);
-	DIVA_OS_MEM_DETACH_PORT(IoAdapter, Port);
-}
-/* ---------------------------------------------------------------------
-   Reset hardware
-   --------------------------------------------------------------------- */
-static void reset_bri_hardware(PISDN_ADAPTER IoAdapter) {
-	byte __iomem *p = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	outpp(p, 0x00);
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, p);
-}
-/* ---------------------------------------------------------------------
-   Halt system
-   --------------------------------------------------------------------- */
-static void stop_bri_hardware(PISDN_ADAPTER IoAdapter) {
-	byte __iomem *p = DIVA_OS_MEM_ATTACH_RESET(IoAdapter);
-	if (p) {
-		outpp(p, 0x00); /* disable interrupts ! */
-	}
-	DIVA_OS_MEM_DETACH_RESET(IoAdapter, p);
-	p = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	outpp(p, 0x00);    /* clear int, halt cpu */
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, p);
-}
-static int load_bri_hardware(PISDN_ADAPTER IoAdapter) {
-	return (0);
-}
-/******************************************************************************/
-static int bri_ISR(struct _ISDN_ADAPTER *IoAdapter) {
-	byte __iomem *p;
-
-	p = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	if (!(inpp(p) & 0x01)) {
-		DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, p);
-		return (0);
-	}
-	/*
-	  clear interrupt line
-	*/
-	outpp(p, 0x08);
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, p);
-	IoAdapter->IrqCount++;
-	if (IoAdapter->Initialized) {
-		diva_os_schedule_soft_isr(&IoAdapter->isr_soft_isr);
-	}
-	return (1);
-}
-/* --------------------------------------------------------------------------
-   Disable IRQ in the card hardware
-   -------------------------------------------------------------------------- */
-static void disable_bri_interrupt(PISDN_ADAPTER IoAdapter) {
-	byte __iomem *p;
-	p = DIVA_OS_MEM_ATTACH_RESET(IoAdapter);
-	if (p)
-	{
-		outpp(p, 0x00); /* disable interrupts ! */
-	}
-	DIVA_OS_MEM_DETACH_RESET(IoAdapter, p);
-	p = DIVA_OS_MEM_ATTACH_CTLREG(IoAdapter);
-	outpp(p, 0x00); /* clear int, halt cpu */
-	DIVA_OS_MEM_DETACH_CTLREG(IoAdapter, p);
-}
-/* -------------------------------------------------------------------------
-   Fill card entry points
-   ------------------------------------------------------------------------- */
-void prepare_maestra_functions(PISDN_ADAPTER IoAdapter) {
-	ADAPTER *a = &IoAdapter->a;
-	a->ram_in             = io_in;
-	a->ram_inw            = io_inw;
-	a->ram_in_buffer      = io_in_buffer;
-	a->ram_look_ahead     = io_look_ahead;
-	a->ram_out            = io_out;
-	a->ram_outw           = io_outw;
-	a->ram_out_buffer     = io_out_buffer;
-	a->ram_inc            = io_inc;
-	IoAdapter->MemoryBase = BRI_MEMORY_BASE;
-	IoAdapter->MemorySize = BRI_MEMORY_SIZE;
-	IoAdapter->out        = pr_out;
-	IoAdapter->dpc        = pr_dpc;
-	IoAdapter->tst_irq    = scom_test_int;
-	IoAdapter->clr_irq    = scom_clear_int;
-	IoAdapter->pcm        = (struct pc_maint *)MIPS_MAINT_OFFS;
-	IoAdapter->load       = load_bri_hardware;
-	IoAdapter->disIrq     = disable_bri_interrupt;
-	IoAdapter->rstFnc     = reset_bri_hardware;
-	IoAdapter->stop       = stop_bri_hardware;
-	IoAdapter->trapFnc    = bri_cpu_trapped;
-	IoAdapter->diva_isr_handler = bri_ISR;
-	/*
-	  Prepare OS dependent functions
-	*/
-	diva_os_prepare_maestra_functions(IoAdapter);
-}
-/* -------------------------------------------------------------------------- */
diff --git a/drivers/isdn/hardware/eicon/s_pri.c b/drivers/isdn/hardware/eicon/s_pri.c
deleted file mode 100644
index ddd0e0ef8ed7..000000000000
--- a/drivers/isdn/hardware/eicon/s_pri.c
+++ /dev/null
@@ -1,205 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#include "platform.h"
-#include "di_defs.h"
-#include "pc.h"
-#include "pr_pc.h"
-#include "di.h"
-#include "mi_pc.h"
-#include "pc_maint.h"
-#include "divasync.h"
-#include "io.h"
-#include "helpers.h"
-#include "dsrv_pri.h"
-#include "dsp_defs.h"
-/*****************************************************************************/
-#define MAX_XLOG_SIZE  (64 * 1024)
-/* -------------------------------------------------------------------------
-   Does return offset between ADAPTER->ram and real begin of memory
-   ------------------------------------------------------------------------- */
-static dword pri_ram_offset(ADAPTER *a) {
-	return ((dword)MP_SHARED_RAM_OFFSET);
-}
-/* -------------------------------------------------------------------------
-   Recovery XLOG buffer from the card
-   ------------------------------------------------------------------------- */
-static void pri_cpu_trapped(PISDN_ADAPTER IoAdapter) {
-	byte  __iomem *base;
-	word *Xlog;
-	dword   regs[4], TrapID, size;
-	Xdesc   xlogDesc;
-/*
- * check for trapped MIPS 46xx CPU, dump exception frame
- */
-	base   = DIVA_OS_MEM_ATTACH_ADDRESS(IoAdapter);
-	TrapID = READ_DWORD(&base[0x80]);
-	if ((TrapID == 0x99999999) || (TrapID == 0x99999901))
-	{
-		dump_trap_frame(IoAdapter, &base[0x90]);
-		IoAdapter->trapped = 1;
-	}
-	regs[0] = READ_DWORD(&base[MP_PROTOCOL_OFFSET + 0x70]);
-	regs[1] = READ_DWORD(&base[MP_PROTOCOL_OFFSET + 0x74]);
-	regs[2] = READ_DWORD(&base[MP_PROTOCOL_OFFSET + 0x78]);
-	regs[3] = READ_DWORD(&base[MP_PROTOCOL_OFFSET + 0x7c]);
-	regs[0] &= IoAdapter->MemorySize - 1;
-	if ((regs[0] < IoAdapter->MemorySize - 1))
-	{
-		if (!(Xlog = (word *)diva_os_malloc(0, MAX_XLOG_SIZE))) {
-			DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, base);
-			return;
-		}
-		size = IoAdapter->MemorySize - regs[0];
-		if (size > MAX_XLOG_SIZE)
-			size = MAX_XLOG_SIZE;
-		memcpy_fromio(Xlog, &base[regs[0]], size);
-		xlogDesc.buf = Xlog;
-		xlogDesc.cnt = READ_WORD(&base[regs[1] & (IoAdapter->MemorySize - 1)]);
-		xlogDesc.out = READ_WORD(&base[regs[2] & (IoAdapter->MemorySize - 1)]);
-		dump_xlog_buffer(IoAdapter, &xlogDesc);
-		diva_os_free(0, Xlog);
-		IoAdapter->trapped = 2;
-	}
-	DIVA_OS_MEM_DETACH_ADDRESS(IoAdapter, base);
-}
-/* -------------------------------------------------------------------------
-   Hardware reset of PRI card
-   ------------------------------------------------------------------------- */
-static void reset_pri_hardware(PISDN_ADAPTER IoAdapter) {
-	byte __iomem *p = DIVA_OS_MEM_ATTACH_RESET(IoAdapter);
-	WRITE_BYTE(p, _MP_RISC_RESET | _MP_LED1 | _MP_LED2);
-	diva_os_wait(50);
-	WRITE_BYTE(p, 0x00);
-	diva_os_wait(50);
-	DIVA_OS_MEM_DETACH_RESET(IoAdapter, p);
-}
-/* -------------------------------------------------------------------------
-   Stop Card Hardware
-   ------------------------------------------------------------------------- */
-static void stop_pri_hardware(PISDN_ADAPTER IoAdapter) {
-	dword i;
-	byte __iomem *p;
-	dword volatile __iomem *cfgReg = (void __iomem *)DIVA_OS_MEM_ATTACH_CFG(IoAdapter);
-	WRITE_DWORD(&cfgReg[3], 0);
-	WRITE_DWORD(&cfgReg[1], 0);
-	DIVA_OS_MEM_DETACH_CFG(IoAdapter, cfgReg);
-	IoAdapter->a.ram_out(&IoAdapter->a, &RAM->SWReg, SWREG_HALT_CPU);
-	i = 0;
-	while ((i < 100) && (IoAdapter->a.ram_in(&IoAdapter->a, &RAM->SWReg) != 0))
-	{
-		diva_os_wait(1);
-		i++;
-	}
-	DBG_TRC(("%s: PRI stopped (%d)", IoAdapter->Name, i))
-		cfgReg = (void __iomem *)DIVA_OS_MEM_ATTACH_CFG(IoAdapter);
-	WRITE_DWORD(&cfgReg[0], ((dword)(~0x03E00000)));
-	DIVA_OS_MEM_DETACH_CFG(IoAdapter, cfgReg);
-	diva_os_wait(1);
-	p = DIVA_OS_MEM_ATTACH_RESET(IoAdapter);
-	WRITE_BYTE(p, _MP_RISC_RESET | _MP_LED1 | _MP_LED2);
-	DIVA_OS_MEM_DETACH_RESET(IoAdapter, p);
-}
-static int load_pri_hardware(PISDN_ADAPTER IoAdapter) {
-	return (0);
-}
-/* --------------------------------------------------------------------------
-   PRI Adapter interrupt Service Routine
-   -------------------------------------------------------------------------- */
-static int pri_ISR(struct _ISDN_ADAPTER *IoAdapter) {
-	byte __iomem *cfg = DIVA_OS_MEM_ATTACH_CFG(IoAdapter);
-	if (!(READ_DWORD(cfg) & 0x80000000)) {
-		DIVA_OS_MEM_DETACH_CFG(IoAdapter, cfg);
-		return (0);
-	}
-	/*
-	  clear interrupt line
-	*/
-	WRITE_DWORD(cfg, (dword)~0x03E00000);
-	DIVA_OS_MEM_DETACH_CFG(IoAdapter, cfg);
-	IoAdapter->IrqCount++;
-	if (IoAdapter->Initialized)
-	{
-		diva_os_schedule_soft_isr(&IoAdapter->isr_soft_isr);
-	}
-	return (1);
-}
-/* -------------------------------------------------------------------------
-   Disable interrupt in the card hardware
-   ------------------------------------------------------------------------- */
-static void disable_pri_interrupt(PISDN_ADAPTER IoAdapter) {
-	dword volatile __iomem *cfgReg = (dword volatile __iomem *)DIVA_OS_MEM_ATTACH_CFG(IoAdapter);
-	WRITE_DWORD(&cfgReg[3], 0);
-	WRITE_DWORD(&cfgReg[1], 0);
-	WRITE_DWORD(&cfgReg[0], (dword)(~0x03E00000));
-	DIVA_OS_MEM_DETACH_CFG(IoAdapter, cfgReg);
-}
-/* -------------------------------------------------------------------------
-   Install entry points for PRI Adapter
-   ------------------------------------------------------------------------- */
-static void prepare_common_pri_functions(PISDN_ADAPTER IoAdapter) {
-	ADAPTER *a = &IoAdapter->a;
-	a->ram_in           = mem_in;
-	a->ram_inw          = mem_inw;
-	a->ram_in_buffer    = mem_in_buffer;
-	a->ram_look_ahead   = mem_look_ahead;
-	a->ram_out          = mem_out;
-	a->ram_outw         = mem_outw;
-	a->ram_out_buffer   = mem_out_buffer;
-	a->ram_inc          = mem_inc;
-	a->ram_offset       = pri_ram_offset;
-	a->ram_out_dw    = mem_out_dw;
-	a->ram_in_dw    = mem_in_dw;
-	a->istream_wakeup   = pr_stream;
-	IoAdapter->out      = pr_out;
-	IoAdapter->dpc      = pr_dpc;
-	IoAdapter->tst_irq  = scom_test_int;
-	IoAdapter->clr_irq  = scom_clear_int;
-	IoAdapter->pcm      = (struct pc_maint *)(MIPS_MAINT_OFFS
-						  - MP_SHARED_RAM_OFFSET);
-	IoAdapter->load     = load_pri_hardware;
-	IoAdapter->disIrq   = disable_pri_interrupt;
-	IoAdapter->rstFnc   = reset_pri_hardware;
-	IoAdapter->stop     = stop_pri_hardware;
-	IoAdapter->trapFnc  = pri_cpu_trapped;
-	IoAdapter->diva_isr_handler = pri_ISR;
-}
-/* -------------------------------------------------------------------------
-   Install entry points for PRI Adapter
-   ------------------------------------------------------------------------- */
-void prepare_pri_functions(PISDN_ADAPTER IoAdapter) {
-	IoAdapter->MemorySize = MP_MEMORY_SIZE;
-	prepare_common_pri_functions(IoAdapter);
-	diva_os_prepare_pri_functions(IoAdapter);
-}
-/* -------------------------------------------------------------------------
-   Install entry points for PRI Rev.2 Adapter
-   ------------------------------------------------------------------------- */
-void prepare_pri2_functions(PISDN_ADAPTER IoAdapter) {
-	IoAdapter->MemorySize = MP2_MEMORY_SIZE;
-	prepare_common_pri_functions(IoAdapter);
-	diva_os_prepare_pri2_functions(IoAdapter);
-}
-/* ------------------------------------------------------------------------- */
diff --git a/drivers/isdn/hardware/eicon/sdp_hdr.h b/drivers/isdn/hardware/eicon/sdp_hdr.h
deleted file mode 100644
index 5e20f8d68673..000000000000
--- a/drivers/isdn/hardware/eicon/sdp_hdr.h
+++ /dev/null
@@ -1,117 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-#ifndef __DIVA_SOFT_DSP_TASK_ENTRY_H__
-#define __DIVA_SOFT_DSP_TASK_ENTRY_H__
-/*
-  The soft DSP image is described by binary header contained on begin of this
-  image:
-  OFFSET FROM IMAGE START |  VARIABLE
-  ------------------------------------------------------------------------
-  DIVA_MIPS_TASK_IMAGE_LINK_OFFS   |  link to the next image
-  ----------------------------------------------------------------------
-  DIVA_MIPS_TASK_IMAGE_GP_OFFS    |  image gp register value, void*
-  ----------------------------------------------------------------------
-  DIVA_MIPS_TASK_IMAGE_ENTRY_OFFS   |  diva_mips_sdp_task_entry_t*
-  ----------------------------------------------------------------------
-  DIVA_MIPS_TASK_IMAGE_LOAD_ADDR_OFFS |  image image start address (void*)
-  ----------------------------------------------------------------------
-  DIVA_MIPS_TASK_IMAGE_END_ADDR_OFFS |  image image end address   (void*)
-  ----------------------------------------------------------------------
-  DIVA_MIPS_TASK_IMAGE_ID_STRING_OFFS |  image id string char[...];
-  ----------------------------------------------------------------------
-*/
-#define DIVA_MIPS_TASK_IMAGE_LINK_OFFS   0x6C
-#define DIVA_MIPS_TASK_IMAGE_GP_OFFS    0x70
-#define DIVA_MIPS_TASK_IMAGE_ENTRY_OFFS   0x74
-#define DIVA_MIPS_TASK_IMAGE_LOAD_ADDR_OFFS 0x78
-#define DIVA_MIPS_TASK_IMAGE_END_ADDR_OFFS 0x7c
-#define DIVA_MIPS_TASK_IMAGE_ID_STRING_OFFS 0x80
-/*
-  This function is called in order to set GP register of this task
-  This function should be always called before any function of the
-  task is called
-*/
-typedef void (*diva_task_set_prog_gp_proc_t)(void *new_gp);
-/*
-  This function is called to clear .bss at task initialization step
-*/
-typedef void (*diva_task_sys_reset_proc_t)(void);
-/*
-  This function is called in order to provide GP of master call to
-  task, that will be used by calls from the task to the master
-*/
-typedef void (*diva_task_set_main_gp_proc_t)(void *main_gp);
-/*
-  This function is called to provide address of 'dprintf' function
-  to the task
-*/
-typedef word (*diva_prt_proc_t)(char *, ...);
-typedef void (*diva_task_set_prt_proc_t)(diva_prt_proc_t fn);
-/*
-  This function is called to set task PID
-*/
-typedef void (*diva_task_set_pid_proc_t)(dword id);
-/*
-  This function is called for run-time task init
-*/
-typedef int (*diva_task_run_time_init_proc_t)(void*, dword);
-/*
-  This function is called from system scheduler or from timer
-*/
-typedef void (*diva_task_callback_proc_t)(void);
-/*
-  This callback is used by task to get current time im mS
-*/
-typedef dword (*diva_task_get_tick_count_proc_t)(void);
-typedef void (*diva_task_set_get_time_proc_t)(\
-	diva_task_get_tick_count_proc_t fn);
-typedef struct _diva_mips_sdp_task_entry {
-	diva_task_set_prog_gp_proc_t  set_gp_proc;
-	diva_task_sys_reset_proc_t   sys_reset_proc;
-	diva_task_set_main_gp_proc_t  set_main_gp_proc;
-	diva_task_set_prt_proc_t    set_dprintf_proc;
-	diva_task_set_pid_proc_t    set_pid_proc;
-	diva_task_run_time_init_proc_t run_time_init_proc;
-	diva_task_callback_proc_t    task_callback_proc;
-	diva_task_callback_proc_t    timer_callback_proc;
-	diva_task_set_get_time_proc_t  set_get_time_proc;
-	void *last_entry_proc;
-} diva_mips_sdp_task_entry_t;
-/*
-  'last_entry_proc' should be set to zero and is used for future extensuios
-*/
-typedef struct _diva_mips_sw_task {
-	diva_mips_sdp_task_entry_t  sdp_entry;
-	void *sdp_gp_reg;
-	void *own_gp_reg;
-} diva_mips_sw_task_t;
-#if !defined(DIVA_BRI2F_SDP_1_NAME)
-#define DIVA_BRI2F_SDP_1_NAME "sdp0.2q0"
-#endif
-#if !defined(DIVA_BRI2F_SDP_2_NAME)
-#define DIVA_BRI2F_SDP_2_NAME "sdp1.2q0"
-#endif
-#endif
diff --git a/drivers/isdn/hardware/eicon/um_idi.c b/drivers/isdn/hardware/eicon/um_idi.c
deleted file mode 100644
index db4dd4ff3642..000000000000
--- a/drivers/isdn/hardware/eicon/um_idi.c
+++ /dev/null
@@ -1,886 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* $Id: um_idi.c,v 1.14 2004/03/21 17:54:37 armin Exp $ */
-
-#include "platform.h"
-#include "di_defs.h"
-#include "pc.h"
-#include "dqueue.h"
-#include "adapter.h"
-#include "entity.h"
-#include "um_xdi.h"
-#include "um_idi.h"
-#include "debuglib.h"
-#include "divasync.h"
-
-#define DIVAS_MAX_XDI_ADAPTERS	64
-
-/* --------------------------------------------------------------------------
-   IMPORTS
-   -------------------------------------------------------------------------- */
-extern void diva_os_wakeup_read(void *os_context);
-extern void diva_os_wakeup_close(void *os_context);
-/* --------------------------------------------------------------------------
-   LOCALS
-   -------------------------------------------------------------------------- */
-static LIST_HEAD(adapter_q);
-static diva_os_spin_lock_t adapter_lock;
-
-static diva_um_idi_adapter_t *diva_um_idi_find_adapter(dword nr);
-static void cleanup_adapter(diva_um_idi_adapter_t *a);
-static void cleanup_entity(divas_um_idi_entity_t *e);
-static int diva_user_mode_idi_adapter_features(diva_um_idi_adapter_t *a,
-					       diva_um_idi_adapter_features_t
-					       *features);
-static int process_idi_request(divas_um_idi_entity_t *e,
-			       const diva_um_idi_req_hdr_t *req);
-static int process_idi_rc(divas_um_idi_entity_t *e, byte rc);
-static int process_idi_ind(divas_um_idi_entity_t *e, byte ind);
-static int write_return_code(divas_um_idi_entity_t *e, byte rc);
-
-/* --------------------------------------------------------------------------
-   MAIN
-   -------------------------------------------------------------------------- */
-int diva_user_mode_idi_init(void)
-{
-	diva_os_initialize_spin_lock(&adapter_lock, "adapter");
-	return (0);
-}
-
-/* --------------------------------------------------------------------------
-   Copy adapter features to user supplied buffer
-   -------------------------------------------------------------------------- */
-static int
-diva_user_mode_idi_adapter_features(diva_um_idi_adapter_t *a,
-				    diva_um_idi_adapter_features_t *
-				    features)
-{
-	IDI_SYNC_REQ sync_req;
-
-	if ((a) && (a->d.request)) {
-		features->type = a->d.type;
-		features->features = a->d.features;
-		features->channels = a->d.channels;
-		memset(features->name, 0, sizeof(features->name));
-
-		sync_req.GetName.Req = 0;
-		sync_req.GetName.Rc = IDI_SYNC_REQ_GET_NAME;
-		(*(a->d.request)) ((ENTITY *)&sync_req);
-		strlcpy(features->name, sync_req.GetName.name,
-			sizeof(features->name));
-
-		sync_req.GetSerial.Req = 0;
-		sync_req.GetSerial.Rc = IDI_SYNC_REQ_GET_SERIAL;
-		sync_req.GetSerial.serial = 0;
-		(*(a->d.request))((ENTITY *)&sync_req);
-		features->serial_number = sync_req.GetSerial.serial;
-	}
-
-	return ((a) ? 0 : -1);
-}
-
-/* --------------------------------------------------------------------------
-   REMOVE ADAPTER
-   -------------------------------------------------------------------------- */
-void diva_user_mode_idi_remove_adapter(int adapter_nr)
-{
-	struct list_head *tmp;
-	diva_um_idi_adapter_t *a;
-
-	list_for_each(tmp, &adapter_q) {
-		a = list_entry(tmp, diva_um_idi_adapter_t, link);
-		if (a->adapter_nr == adapter_nr) {
-			list_del(tmp);
-			cleanup_adapter(a);
-			DBG_LOG(("DIDD: del adapter(%d)", a->adapter_nr));
-			diva_os_free(0, a);
-			break;
-		}
-	}
-}
-
-/* --------------------------------------------------------------------------
-   CALLED ON DRIVER EXIT (UNLOAD)
-   -------------------------------------------------------------------------- */
-void diva_user_mode_idi_finit(void)
-{
-	struct list_head *tmp, *safe;
-	diva_um_idi_adapter_t *a;
-
-	list_for_each_safe(tmp, safe, &adapter_q) {
-		a = list_entry(tmp, diva_um_idi_adapter_t, link);
-		list_del(tmp);
-		cleanup_adapter(a);
-		DBG_LOG(("DIDD: del adapter(%d)", a->adapter_nr));
-		diva_os_free(0, a);
-	}
-	diva_os_destroy_spin_lock(&adapter_lock, "adapter");
-}
-
-/* -------------------------------------------------------------------------
-   CREATE AND INIT IDI ADAPTER
-   ------------------------------------------------------------------------- */
-int diva_user_mode_idi_create_adapter(const DESCRIPTOR *d, int adapter_nr)
-{
-	diva_os_spin_lock_magic_t old_irql;
-	diva_um_idi_adapter_t *a =
-		(diva_um_idi_adapter_t *) diva_os_malloc(0,
-							 sizeof
-							 (diva_um_idi_adapter_t));
-
-	if (!a) {
-		return (-1);
-	}
-	memset(a, 0x00, sizeof(*a));
-	INIT_LIST_HEAD(&a->entity_q);
-
-	a->d = *d;
-	a->adapter_nr = adapter_nr;
-
-	DBG_LOG(("DIDD_ADD A(%d), type:%02x, features:%04x, channels:%d",
-		 adapter_nr, a->d.type, a->d.features, a->d.channels));
-
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "create_adapter");
-	list_add_tail(&a->link, &adapter_q);
-	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "create_adapter");
-	return (0);
-}
-
-/* ------------------------------------------------------------------------
-   Find adapter by Adapter number
-   ------------------------------------------------------------------------ */
-static diva_um_idi_adapter_t *diva_um_idi_find_adapter(dword nr)
-{
-	diva_um_idi_adapter_t *a = NULL;
-	struct list_head *tmp;
-
-	list_for_each(tmp, &adapter_q) {
-		a = list_entry(tmp, diva_um_idi_adapter_t, link);
-		DBG_TRC(("find_adapter: (%d)-(%d)", nr, a->adapter_nr));
-		if (a->adapter_nr == (int)nr)
-			break;
-		a = NULL;
-	}
-	return (a);
-}
-
-/* ------------------------------------------------------------------------
-   Cleanup this adapter and cleanup/delete all entities assigned
-   to this adapter
-   ------------------------------------------------------------------------ */
-static void cleanup_adapter(diva_um_idi_adapter_t *a)
-{
-	struct list_head *tmp, *safe;
-	divas_um_idi_entity_t *e;
-
-	list_for_each_safe(tmp, safe, &a->entity_q) {
-		e = list_entry(tmp, divas_um_idi_entity_t, link);
-		list_del(tmp);
-		cleanup_entity(e);
-		if (e->os_context) {
-			diva_os_wakeup_read(e->os_context);
-			diva_os_wakeup_close(e->os_context);
-		}
-	}
-	memset(&a->d, 0x00, sizeof(DESCRIPTOR));
-}
-
-/* ------------------------------------------------------------------------
-   Cleanup, but NOT delete this entity
-   ------------------------------------------------------------------------ */
-static void cleanup_entity(divas_um_idi_entity_t *e)
-{
-	e->os_ref = NULL;
-	e->status = 0;
-	e->adapter = NULL;
-	e->e.Id = 0;
-	e->rc_count = 0;
-
-	e->status |= DIVA_UM_IDI_REMOVED;
-	e->status |= DIVA_UM_IDI_REMOVE_PENDING;
-
-	diva_data_q_finit(&e->data);
-	diva_data_q_finit(&e->rc);
-}
-
-
-/* ------------------------------------------------------------------------
-   Create ENTITY, link it to the adapter and remove pointer to entity
-   ------------------------------------------------------------------------ */
-void *divas_um_idi_create_entity(dword adapter_nr, void *file)
-{
-	divas_um_idi_entity_t *e;
-	diva_um_idi_adapter_t *a;
-	diva_os_spin_lock_magic_t old_irql;
-
-	if ((e = (divas_um_idi_entity_t *) diva_os_malloc(0, sizeof(*e)))) {
-		memset(e, 0x00, sizeof(*e));
-		if (!
-		    (e->os_context =
-		     diva_os_malloc(0, diva_os_get_context_size()))) {
-			DBG_LOG(("E(%08x) no memory for os context", e));
-			diva_os_free(0, e);
-			return NULL;
-		}
-		memset(e->os_context, 0x00, diva_os_get_context_size());
-
-		if ((diva_data_q_init(&e->data, 2048 + 512, 16))) {
-			diva_os_free(0, e->os_context);
-			diva_os_free(0, e);
-			return NULL;
-		}
-		if ((diva_data_q_init(&e->rc, sizeof(diva_um_idi_ind_hdr_t), 2))) {
-			diva_data_q_finit(&e->data);
-			diva_os_free(0, e->os_context);
-			diva_os_free(0, e);
-			return NULL;
-		}
-
-		diva_os_enter_spin_lock(&adapter_lock, &old_irql, "create_entity");
-		/*
-		  Look for Adapter requested
-		*/
-		if (!(a = diva_um_idi_find_adapter(adapter_nr))) {
-			/*
-			  No adapter was found, or this adapter was removed
-			*/
-			diva_os_leave_spin_lock(&adapter_lock, &old_irql, "create_entity");
-
-			DBG_LOG(("A: no adapter(%ld)", adapter_nr));
-
-			cleanup_entity(e);
-			diva_os_free(0, e->os_context);
-			diva_os_free(0, e);
-
-			return NULL;
-		}
-
-		e->os_ref = file;	/* link to os handle */
-		e->adapter = a;	/* link to adapter   */
-
-		list_add_tail(&e->link, &a->entity_q);	/* link from adapter */
-
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "create_entity");
-
-		DBG_LOG(("A(%ld), create E(%08x)", adapter_nr, e));
-	}
-
-	return (e);
-}
-
-/* ------------------------------------------------------------------------
-   Unlink entity and free memory
-   ------------------------------------------------------------------------ */
-int divas_um_idi_delete_entity(int adapter_nr, void *entity)
-{
-	divas_um_idi_entity_t *e;
-	diva_um_idi_adapter_t *a;
-	diva_os_spin_lock_magic_t old_irql;
-
-	if (!(e = (divas_um_idi_entity_t *) entity))
-		return (-1);
-
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "delete_entity");
-	if ((a = e->adapter)) {
-		list_del(&e->link);
-	}
-	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "delete_entity");
-
-	diva_um_idi_stop_wdog(entity);
-	cleanup_entity(e);
-	diva_os_free(0, e->os_context);
-	memset(e, 0x00, sizeof(*e));
-
-	DBG_LOG(("A(%d) remove E:%08x", adapter_nr, e));
-	diva_os_free(0, e);
-
-	return (0);
-}
-
-/* --------------------------------------------------------------------------
-   Called by application to read data from IDI
-   -------------------------------------------------------------------------- */
-int diva_um_idi_read(void *entity,
-		     void *os_handle,
-		     void *dst,
-		     int max_length, divas_um_idi_copy_to_user_fn_t cp_fn)
-{
-	divas_um_idi_entity_t *e;
-	diva_um_idi_adapter_t *a;
-	const void *data;
-	int length, ret = 0;
-	diva_um_idi_data_queue_t *q;
-	diva_os_spin_lock_magic_t old_irql;
-
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "read");
-
-	e = (divas_um_idi_entity_t *) entity;
-	if (!e || (!(a = e->adapter)) ||
-	    (e->status & DIVA_UM_IDI_REMOVE_PENDING) ||
-	    (e->status & DIVA_UM_IDI_REMOVED) ||
-	    (a->status & DIVA_UM_IDI_ADAPTER_REMOVED)) {
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "read");
-		DBG_ERR(("E(%08x) read failed - adapter removed", e))
-			return (-1);
-	}
-
-	DBG_TRC(("A(%d) E(%08x) read(%d)", a->adapter_nr, e, max_length));
-
-	/*
-	  Try to read return code first
-	*/
-	data = diva_data_q_get_segment4read(&e->rc);
-	q = &e->rc;
-
-	/*
-	  No return codes available, read indications now
-	*/
-	if (!data) {
-		if (!(e->status & DIVA_UM_IDI_RC_PENDING)) {
-			DBG_TRC(("A(%d) E(%08x) read data", a->adapter_nr, e));
-			data = diva_data_q_get_segment4read(&e->data);
-			q = &e->data;
-		}
-	} else {
-		e->status &= ~DIVA_UM_IDI_RC_PENDING;
-		DBG_TRC(("A(%d) E(%08x) read rc", a->adapter_nr, e));
-	}
-
-	if (data) {
-		if ((length = diva_data_q_get_segment_length(q)) >
-		    max_length) {
-			/*
-			  Not enough space to read message
-			*/
-			DBG_ERR(("A: A(%d) E(%08x) read small buffer",
-				 a->adapter_nr, e, ret));
-			diva_os_leave_spin_lock(&adapter_lock, &old_irql,
-						"read");
-			return (-2);
-		}
-		/*
-		  Copy it to user, this function does access ONLY locked an verified
-		  memory, also we can access it witch spin lock held
-		*/
-
-		if ((ret = (*cp_fn) (os_handle, dst, data, length)) >= 0) {
-			/*
-			  Acknowledge only if read was successful
-			*/
-			diva_data_q_ack_segment4read(q);
-		}
-	}
-
-
-	DBG_TRC(("A(%d) E(%08x) read=%d", a->adapter_nr, e, ret));
-
-	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "read");
-
-	return (ret);
-}
-
-
-int diva_um_idi_write(void *entity,
-		      void *os_handle,
-		      const void *src,
-		      int length, divas_um_idi_copy_from_user_fn_t cp_fn)
-{
-	divas_um_idi_entity_t *e;
-	diva_um_idi_adapter_t *a;
-	diva_um_idi_req_hdr_t *req;
-	void *data;
-	int ret = 0;
-	diva_os_spin_lock_magic_t old_irql;
-
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "write");
-
-	e = (divas_um_idi_entity_t *) entity;
-	if (!e || (!(a = e->adapter)) ||
-	    (e->status & DIVA_UM_IDI_REMOVE_PENDING) ||
-	    (e->status & DIVA_UM_IDI_REMOVED) ||
-	    (a->status & DIVA_UM_IDI_ADAPTER_REMOVED)) {
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "write");
-		DBG_ERR(("E(%08x) write failed - adapter removed", e))
-			return (-1);
-	}
-
-	DBG_TRC(("A(%d) E(%08x) write(%d)", a->adapter_nr, e, length));
-
-	if ((length < sizeof(*req)) || (length > sizeof(e->buffer))) {
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "write");
-		return (-2);
-	}
-
-	if (e->status & DIVA_UM_IDI_RC_PENDING) {
-		DBG_ERR(("A: A(%d) E(%08x) rc pending", a->adapter_nr, e));
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "write");
-		return (-1);	/* should wait for RC code first */
-	}
-
-	/*
-	  Copy function does access only locked verified memory,
-	  also it can be called with spin lock held
-	*/
-	if ((ret = (*cp_fn) (os_handle, e->buffer, src, length)) < 0) {
-		DBG_TRC(("A: A(%d) E(%08x) write error=%d", a->adapter_nr,
-			 e, ret));
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "write");
-		return (ret);
-	}
-
-	req = (diva_um_idi_req_hdr_t *)&e->buffer[0];
-
-	switch (req->type) {
-	case DIVA_UM_IDI_GET_FEATURES:{
-		DBG_LOG(("A(%d) get_features", a->adapter_nr));
-		if (!(data =
-		      diva_data_q_get_segment4write(&e->data))) {
-			DBG_ERR(("A(%d) get_features, no free buffer",
-				 a->adapter_nr));
-			diva_os_leave_spin_lock(&adapter_lock,
-						&old_irql,
-						"write");
-			return (0);
-		}
-		diva_user_mode_idi_adapter_features(a, &(((diva_um_idi_ind_hdr_t
-							   *) data)->hdr.features));
-		((diva_um_idi_ind_hdr_t *) data)->type =
-			DIVA_UM_IDI_IND_FEATURES;
-		((diva_um_idi_ind_hdr_t *) data)->data_length = 0;
-		diva_data_q_ack_segment4write(&e->data,
-					      sizeof(diva_um_idi_ind_hdr_t));
-
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "write");
-
-		diva_os_wakeup_read(e->os_context);
-	}
-		break;
-
-	case DIVA_UM_IDI_REQ:
-	case DIVA_UM_IDI_REQ_MAN:
-	case DIVA_UM_IDI_REQ_SIG:
-	case DIVA_UM_IDI_REQ_NET:
-		DBG_TRC(("A(%d) REQ(%02d)-(%02d)-(%08x)", a->adapter_nr,
-			 req->Req, req->ReqCh,
-			 req->type & DIVA_UM_IDI_REQ_TYPE_MASK));
-		switch (process_idi_request(e, req)) {
-		case -1:
-			diva_os_leave_spin_lock(&adapter_lock, &old_irql, "write");
-			return (-1);
-		case -2:
-			diva_os_leave_spin_lock(&adapter_lock, &old_irql, "write");
-			diva_os_wakeup_read(e->os_context);
-			break;
-		default:
-			diva_os_leave_spin_lock(&adapter_lock, &old_irql, "write");
-			break;
-		}
-		break;
-
-	default:
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "write");
-		return (-1);
-	}
-
-	DBG_TRC(("A(%d) E(%08x) write=%d", a->adapter_nr, e, ret));
-
-	return (ret);
-}
-
-/* --------------------------------------------------------------------------
-   CALLBACK FROM XDI
-   -------------------------------------------------------------------------- */
-static void diva_um_idi_xdi_callback(ENTITY *entity)
-{
-	divas_um_idi_entity_t *e = DIVAS_CONTAINING_RECORD(entity,
-							   divas_um_idi_entity_t,
-							   e);
-	diva_os_spin_lock_magic_t old_irql;
-	int call_wakeup = 0;
-
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "xdi_callback");
-
-	if (e->e.complete == 255) {
-		if (!(e->status & DIVA_UM_IDI_REMOVE_PENDING)) {
-			diva_um_idi_stop_wdog(e);
-		}
-		if ((call_wakeup = process_idi_rc(e, e->e.Rc))) {
-			if (e->rc_count) {
-				e->rc_count--;
-			}
-		}
-		e->e.Rc = 0;
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "xdi_callback");
-
-		if (call_wakeup) {
-			diva_os_wakeup_read(e->os_context);
-			diva_os_wakeup_close(e->os_context);
-		}
-	} else {
-		if (e->status & DIVA_UM_IDI_REMOVE_PENDING) {
-			e->e.RNum = 0;
-			e->e.RNR = 2;
-		} else {
-			call_wakeup = process_idi_ind(e, e->e.Ind);
-		}
-		e->e.Ind = 0;
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "xdi_callback");
-		if (call_wakeup) {
-			diva_os_wakeup_read(e->os_context);
-		}
-	}
-}
-
-static int process_idi_request(divas_um_idi_entity_t *e,
-			       const diva_um_idi_req_hdr_t *req)
-{
-	int assign = 0;
-	byte Req = (byte) req->Req;
-	dword type = req->type & DIVA_UM_IDI_REQ_TYPE_MASK;
-
-	if (!e->e.Id || !e->e.callback) {	/* not assigned */
-		if (Req != ASSIGN) {
-			DBG_ERR(("A: A(%d) E(%08x) not assigned",
-				 e->adapter->adapter_nr, e));
-			return (-1);	/* NOT ASSIGNED */
-		} else {
-			switch (type) {
-			case DIVA_UM_IDI_REQ_TYPE_MAN:
-				e->e.Id = MAN_ID;
-				DBG_TRC(("A(%d) E(%08x) assign MAN",
-					 e->adapter->adapter_nr, e));
-				break;
-
-			case DIVA_UM_IDI_REQ_TYPE_SIG:
-				e->e.Id = DSIG_ID;
-				DBG_TRC(("A(%d) E(%08x) assign SIG",
-					 e->adapter->adapter_nr, e));
-				break;
-
-			case DIVA_UM_IDI_REQ_TYPE_NET:
-				e->e.Id = NL_ID;
-				DBG_TRC(("A(%d) E(%08x) assign NET",
-					 e->adapter->adapter_nr, e));
-				break;
-
-			default:
-				DBG_ERR(("A: A(%d) E(%08x) unknown type=%08x",
-					 e->adapter->adapter_nr, e,
-					 type));
-				return (-1);
-			}
-		}
-		e->e.XNum = 1;
-		e->e.RNum = 1;
-		e->e.callback = diva_um_idi_xdi_callback;
-		e->e.X = &e->XData;
-		e->e.R = &e->RData;
-		assign = 1;
-	}
-	e->status |= DIVA_UM_IDI_RC_PENDING;
-	e->e.Req = Req;
-	e->e.ReqCh = (byte) req->ReqCh;
-	e->e.X->PLength = (word) req->data_length;
-	e->e.X->P = (byte *)&req[1];	/* Our buffer is safe */
-
-	DBG_TRC(("A(%d) E(%08x) request(%02x-%02x-%02x (%d))",
-		 e->adapter->adapter_nr, e, e->e.Id, e->e.Req,
-		 e->e.ReqCh, e->e.X->PLength));
-
-	e->rc_count++;
-
-	if (e->adapter && e->adapter->d.request) {
-		diva_um_idi_start_wdog(e);
-		(*(e->adapter->d.request)) (&e->e);
-	}
-
-	if (assign) {
-		if (e->e.Rc == OUT_OF_RESOURCES) {
-			/*
-			  XDI has no entities more, call was not forwarded to the card,
-			  no callback will be scheduled
-			*/
-			DBG_ERR(("A: A(%d) E(%08x) XDI out of entities",
-				 e->adapter->adapter_nr, e));
-
-			e->e.Id = 0;
-			e->e.ReqCh = 0;
-			e->e.RcCh = 0;
-			e->e.Ind = 0;
-			e->e.IndCh = 0;
-			e->e.XNum = 0;
-			e->e.RNum = 0;
-			e->e.callback = NULL;
-			e->e.X = NULL;
-			e->e.R = NULL;
-			write_return_code(e, ASSIGN_RC | OUT_OF_RESOURCES);
-			return (-2);
-		} else {
-			e->status |= DIVA_UM_IDI_ASSIGN_PENDING;
-		}
-	}
-
-	return (0);
-}
-
-static int process_idi_rc(divas_um_idi_entity_t *e, byte rc)
-{
-	DBG_TRC(("A(%d) E(%08x) rc(%02x-%02x-%02x)",
-		 e->adapter->adapter_nr, e, e->e.Id, rc, e->e.RcCh));
-
-	if (e->status & DIVA_UM_IDI_ASSIGN_PENDING) {
-		e->status &= ~DIVA_UM_IDI_ASSIGN_PENDING;
-		if (rc != ASSIGN_OK) {
-			DBG_ERR(("A: A(%d) E(%08x) ASSIGN failed",
-				 e->adapter->adapter_nr, e));
-			e->e.callback = NULL;
-			e->e.Id = 0;
-			e->e.Req = 0;
-			e->e.ReqCh = 0;
-			e->e.Rc = 0;
-			e->e.RcCh = 0;
-			e->e.Ind = 0;
-			e->e.IndCh = 0;
-			e->e.X = NULL;
-			e->e.R = NULL;
-			e->e.XNum = 0;
-			e->e.RNum = 0;
-		}
-	}
-	if ((e->e.Req == REMOVE) && e->e.Id && (rc == 0xff)) {
-		DBG_ERR(("A: A(%d) E(%08x)  discard OK in REMOVE",
-			 e->adapter->adapter_nr, e));
-		return (0);	/* let us do it in the driver */
-	}
-	if ((e->e.Req == REMOVE) && (!e->e.Id)) {	/* REMOVE COMPLETE */
-		e->e.callback = NULL;
-		e->e.Id = 0;
-		e->e.Req = 0;
-		e->e.ReqCh = 0;
-		e->e.Rc = 0;
-		e->e.RcCh = 0;
-		e->e.Ind = 0;
-		e->e.IndCh = 0;
-		e->e.X = NULL;
-		e->e.R = NULL;
-		e->e.XNum = 0;
-		e->e.RNum = 0;
-		e->rc_count = 0;
-	}
-	if ((e->e.Req == REMOVE) && (rc != 0xff)) {	/* REMOVE FAILED */
-		DBG_ERR(("A: A(%d) E(%08x)  REMOVE FAILED",
-			 e->adapter->adapter_nr, e));
-	}
-	write_return_code(e, rc);
-
-	return (1);
-}
-
-static int process_idi_ind(divas_um_idi_entity_t *e, byte ind)
-{
-	int do_wakeup = 0;
-
-	if (e->e.complete != 0x02) {
-		diva_um_idi_ind_hdr_t *pind =
-			(diva_um_idi_ind_hdr_t *)
-			diva_data_q_get_segment4write(&e->data);
-		if (pind) {
-			e->e.RNum = 1;
-			e->e.R->P = (byte *)&pind[1];
-			e->e.R->PLength =
-				(word) (diva_data_q_get_max_length(&e->data) -
-					sizeof(*pind));
-			DBG_TRC(("A(%d) E(%08x) ind_1(%02x-%02x-%02x)-[%d-%d]",
-				 e->adapter->adapter_nr, e, e->e.Id, ind,
-				 e->e.IndCh, e->e.RLength,
-				 e->e.R->PLength));
-
-		} else {
-			DBG_TRC(("A(%d) E(%08x) ind(%02x-%02x-%02x)-RNR",
-				 e->adapter->adapter_nr, e, e->e.Id, ind,
-				 e->e.IndCh));
-			e->e.RNum = 0;
-			e->e.RNR = 1;
-			do_wakeup = 1;
-		}
-	} else {
-		diva_um_idi_ind_hdr_t *pind =
-			(diva_um_idi_ind_hdr_t *) (e->e.R->P);
-
-		DBG_TRC(("A(%d) E(%08x) ind(%02x-%02x-%02x)-[%d]",
-			 e->adapter->adapter_nr, e, e->e.Id, ind,
-			 e->e.IndCh, e->e.R->PLength));
-
-		pind--;
-		pind->type = DIVA_UM_IDI_IND;
-		pind->hdr.ind.Ind = ind;
-		pind->hdr.ind.IndCh = e->e.IndCh;
-		pind->data_length = e->e.R->PLength;
-		diva_data_q_ack_segment4write(&e->data,
-					      (int) (sizeof(*pind) +
-						     e->e.R->PLength));
-		do_wakeup = 1;
-	}
-
-	if ((e->status & DIVA_UM_IDI_RC_PENDING) && !e->rc.count) {
-		do_wakeup = 0;
-	}
-
-	return (do_wakeup);
-}
-
-/* --------------------------------------------------------------------------
-   Write return code to the return code queue of entity
-   -------------------------------------------------------------------------- */
-static int write_return_code(divas_um_idi_entity_t *e, byte rc)
-{
-	diva_um_idi_ind_hdr_t *prc;
-
-	if (!(prc =
-	      (diva_um_idi_ind_hdr_t *) diva_data_q_get_segment4write(&e->rc)))
-	{
-		DBG_ERR(("A: A(%d) E(%08x) rc(%02x) lost",
-			 e->adapter->adapter_nr, e, rc));
-		e->status &= ~DIVA_UM_IDI_RC_PENDING;
-		return (-1);
-	}
-
-	prc->type = DIVA_UM_IDI_IND_RC;
-	prc->hdr.rc.Rc = rc;
-	prc->hdr.rc.RcCh = e->e.RcCh;
-	prc->data_length = 0;
-	diva_data_q_ack_segment4write(&e->rc, sizeof(*prc));
-
-	return (0);
-}
-
-/* --------------------------------------------------------------------------
-   Return amount of entries that can be bead from this entity or
-   -1 if adapter was removed
-   -------------------------------------------------------------------------- */
-int diva_user_mode_idi_ind_ready(void *entity, void *os_handle)
-{
-	divas_um_idi_entity_t *e;
-	diva_um_idi_adapter_t *a;
-	diva_os_spin_lock_magic_t old_irql;
-	int ret;
-
-	if (!entity)
-		return (-1);
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "ind_ready");
-	e = (divas_um_idi_entity_t *) entity;
-	a = e->adapter;
-
-	if ((!a) || (a->status & DIVA_UM_IDI_ADAPTER_REMOVED)) {
-		/*
-		  Adapter was unloaded
-		*/
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "ind_ready");
-		return (-1);	/* adapter was removed */
-	}
-	if (e->status & DIVA_UM_IDI_REMOVED) {
-		/*
-		  entity was removed as result of adapter removal
-		  user should assign this entity again
-		*/
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "ind_ready");
-		return (-1);
-	}
-
-	ret = e->rc.count + e->data.count;
-
-	if ((e->status & DIVA_UM_IDI_RC_PENDING) && !e->rc.count) {
-		ret = 0;
-	}
-
-	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "ind_ready");
-
-	return (ret);
-}
-
-void *diva_um_id_get_os_context(void *entity)
-{
-	return (((divas_um_idi_entity_t *) entity)->os_context);
-}
-
-int divas_um_idi_entity_assigned(void *entity)
-{
-	divas_um_idi_entity_t *e;
-	diva_um_idi_adapter_t *a;
-	int ret;
-	diva_os_spin_lock_magic_t old_irql;
-
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "assigned?");
-
-
-	e = (divas_um_idi_entity_t *) entity;
-	if (!e || (!(a = e->adapter)) ||
-	    (e->status & DIVA_UM_IDI_REMOVED) ||
-	    (a->status & DIVA_UM_IDI_ADAPTER_REMOVED)) {
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "assigned?");
-		return (0);
-	}
-
-	e->status |= DIVA_UM_IDI_REMOVE_PENDING;
-
-	ret = (e->e.Id || e->rc_count
-	       || (e->status & DIVA_UM_IDI_ASSIGN_PENDING));
-
-	DBG_TRC(("Id:%02x, rc_count:%d, status:%08x", e->e.Id, e->rc_count,
-		 e->status))
-
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "assigned?");
-
-	return (ret);
-}
-
-int divas_um_idi_entity_start_remove(void *entity)
-{
-	divas_um_idi_entity_t *e;
-	diva_um_idi_adapter_t *a;
-	diva_os_spin_lock_magic_t old_irql;
-
-	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "start_remove");
-
-	e = (divas_um_idi_entity_t *) entity;
-	if (!e || (!(a = e->adapter)) ||
-	    (e->status & DIVA_UM_IDI_REMOVED) ||
-	    (a->status & DIVA_UM_IDI_ADAPTER_REMOVED)) {
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "start_remove");
-		return (0);
-	}
-
-	if (e->rc_count) {
-		/*
-		  Entity BUSY
-		*/
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "start_remove");
-		return (1);
-	}
-
-	if (!e->e.Id) {
-		/*
-		  Remove request was already pending, and arrived now
-		*/
-		diva_os_leave_spin_lock(&adapter_lock, &old_irql, "start_remove");
-		return (0);	/* REMOVE was pending */
-	}
-
-	/*
-	  Now send remove request
-	*/
-	e->e.Req = REMOVE;
-	e->e.ReqCh = 0;
-
-	e->rc_count++;
-
-	DBG_TRC(("A(%d) E(%08x) request(%02x-%02x-%02x (%d))",
-		 e->adapter->adapter_nr, e, e->e.Id, e->e.Req,
-		 e->e.ReqCh, e->e.X->PLength));
-
-	if (a->d.request)
-		(*(a->d.request)) (&e->e);
-
-	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "start_remove");
-
-	return (0);
-}
diff --git a/drivers/isdn/hardware/eicon/um_idi.h b/drivers/isdn/hardware/eicon/um_idi.h
deleted file mode 100644
index 9aedd9e351a3..000000000000
--- a/drivers/isdn/hardware/eicon/um_idi.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: um_idi.h,v 1.6 2004/03/21 17:26:01 armin Exp $ */
-
-#ifndef __DIVA_USER_MODE_IDI_CORE_H__
-#define __DIVA_USER_MODE_IDI_CORE_H__
-
-
-/*
-  interface between UM IDI core and OS dependent part
-*/
-int diva_user_mode_idi_init(void);
-void diva_user_mode_idi_finit(void);
-void *divas_um_idi_create_entity(dword adapter_nr, void *file);
-int divas_um_idi_delete_entity(int adapter_nr, void *entity);
-
-typedef int (*divas_um_idi_copy_to_user_fn_t) (void *os_handle,
-					       void *dst,
-					       const void *src,
-					       int length);
-typedef int (*divas_um_idi_copy_from_user_fn_t) (void *os_handle,
-						 void *dst,
-						 const void *src,
-						 int length);
-
-int diva_um_idi_read(void *entity,
-		     void *os_handle,
-		     void *dst,
-		     int max_length, divas_um_idi_copy_to_user_fn_t cp_fn);
-
-int diva_um_idi_write(void *entity,
-		      void *os_handle,
-		      const void *src,
-		      int length, divas_um_idi_copy_from_user_fn_t cp_fn);
-
-int diva_user_mode_idi_ind_ready(void *entity, void *os_handle);
-void *diva_um_id_get_os_context(void *entity);
-int diva_os_get_context_size(void);
-int divas_um_idi_entity_assigned(void *entity);
-int divas_um_idi_entity_start_remove(void *entity);
-
-void diva_um_idi_start_wdog(void *entity);
-void diva_um_idi_stop_wdog(void *entity);
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/um_xdi.h b/drivers/isdn/hardware/eicon/um_xdi.h
deleted file mode 100644
index 1f37aa4efd18..000000000000
--- a/drivers/isdn/hardware/eicon/um_xdi.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: um_xdi.h,v 1.1.2.2 2002/10/02 14:38:38 armin Exp $ */
-
-#ifndef __DIVA_USER_MODE_XDI_H__
-#define __DIVA_USER_MODE_XDI_H__
-
-/*
-  Contains declaratiom of structures shared between application
-  and user mode idi driver
-*/
-
-typedef struct _diva_um_idi_adapter_features {
-	dword type;
-	dword features;
-	dword channels;
-	dword serial_number;
-	char name[128];
-} diva_um_idi_adapter_features_t;
-
-#define DIVA_UM_IDI_REQ_MASK			0x0000FFFF
-#define DIVA_UM_IDI_REQ_TYPE_MASK		(~(DIVA_UM_IDI_REQ_MASK))
-#define DIVA_UM_IDI_GET_FEATURES		1	/* trigger features indication */
-#define DIVA_UM_IDI_REQ				2
-#define DIVA_UM_IDI_REQ_TYPE_MAN		0x10000000
-#define DIVA_UM_IDI_REQ_TYPE_SIG		0x20000000
-#define DIVA_UM_IDI_REQ_TYPE_NET		0x30000000
-#define DIVA_UM_IDI_REQ_MAN			(DIVA_UM_IDI_REQ | DIVA_UM_IDI_REQ_TYPE_MAN)
-#define DIVA_UM_IDI_REQ_SIG			(DIVA_UM_IDI_REQ | DIVA_UM_IDI_REQ_TYPE_SIG)
-#define DIVA_UM_IDI_REQ_NET			(DIVA_UM_IDI_REQ | DIVA_UM_IDI_REQ_TYPE_NET)
-/*
-  data_length  bytes will follow this structure
-*/
-typedef struct _diva_um_idi_req_hdr {
-	dword type;
-	dword Req;
-	dword ReqCh;
-	dword data_length;
-} diva_um_idi_req_hdr_t;
-
-typedef struct _diva_um_idi_ind_parameters {
-	dword Ind;
-	dword IndCh;
-} diva_um_idi_ind_parameters_t;
-
-typedef struct _diva_um_idi_rc_parameters {
-	dword Rc;
-	dword RcCh;
-} diva_um_idi_rc_parameters_t;
-
-typedef union _diva_um_idi_ind {
-	diva_um_idi_adapter_features_t features;
-	diva_um_idi_ind_parameters_t ind;
-	diva_um_idi_rc_parameters_t rc;
-} diva_um_idi_ind_t;
-
-#define DIVA_UM_IDI_IND_FEATURES  1	/* features indication */
-#define DIVA_UM_IDI_IND           2
-#define DIVA_UM_IDI_IND_RC        3
-/*
-  data_length bytes of data follow
-  this structure
-*/
-typedef struct _diva_um_idi_ind_hdr {
-	dword type;
-	diva_um_idi_ind_t hdr;
-	dword data_length;
-} diva_um_idi_ind_hdr_t;
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/xdi_adapter.h b/drivers/isdn/hardware/eicon/xdi_adapter.h
deleted file mode 100644
index b036e217c659..000000000000
--- a/drivers/isdn/hardware/eicon/xdi_adapter.h
+++ /dev/null
@@ -1,71 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: xdi_adapter.h,v 1.7 2004/03/21 17:26:01 armin Exp $ */
-
-#ifndef __DIVA_OS_XDI_ADAPTER_H__
-#define __DIVA_OS_XDI_ADAPTER_H__
-
-#define DIVAS_XDI_ADAPTER_BUS_PCI  0
-#define DIVAS_XDI_ADAPTER_BUS_ISA  1
-
-typedef struct _divas_pci_card_resources {
-	byte bus;
-	byte func;
-	void *hdev;
-
-	dword bar[8];		/* contains context of appropriate BAR Register */
-	void __iomem *addr[8];		/* same bar, but mapped into memory */
-	dword length[8];	/* bar length */
-	int mem_type_id[MAX_MEM_TYPE];
-	unsigned int qoffset;
-	byte irq;
-} divas_pci_card_resources_t;
-
-typedef union _divas_card_resources {
-	divas_pci_card_resources_t pci;
-} divas_card_resources_t;
-
-struct _diva_os_xdi_adapter;
-typedef int (*diva_init_card_proc_t)(struct _diva_os_xdi_adapter *a);
-typedef int (*diva_cmd_card_proc_t)(struct _diva_os_xdi_adapter *a,
-				    diva_xdi_um_cfg_cmd_t *data,
-				    int length);
-typedef void (*diva_xdi_clear_interrupts_proc_t)(struct
-						 _diva_os_xdi_adapter *);
-
-#define DIVA_XDI_MBOX_BUSY			1
-#define DIVA_XDI_MBOX_WAIT_XLOG	2
-
-typedef struct _xdi_mbox_t {
-	dword status;
-	diva_xdi_um_cfg_cmd_data_t cmd_data;
-	dword data_length;
-	void *data;
-} xdi_mbox_t;
-
-typedef struct _diva_os_idi_adapter_interface {
-	diva_init_card_proc_t cleanup_adapter_proc;
-	diva_cmd_card_proc_t cmd_proc;
-} diva_os_idi_adapter_interface_t;
-
-typedef struct _diva_os_xdi_adapter {
-	struct list_head link;
-	int CardIndex;
-	int CardOrdinal;
-	int controller;		/* number of this controller */
-	int Bus;		/* PCI, ISA, ... */
-	divas_card_resources_t resources;
-	char port_name[24];
-	ISDN_ADAPTER xdi_adapter;
-	xdi_mbox_t xdi_mbox;
-	diva_os_idi_adapter_interface_t interface;
-	struct _diva_os_xdi_adapter *slave_adapters[3];
-	void *slave_list;
-	void *proc_adapter_dir;	/* adapterX proc entry */
-	void *proc_info;	/* info proc entry     */
-	void *proc_grp_opt;	/* group_optimization  */
-	void *proc_d_l1_down;	/* dynamic_l1_down     */
-	volatile diva_xdi_clear_interrupts_proc_t clear_interrupts_proc;
-	dword dsp_mask;
-} diva_os_xdi_adapter_t;
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/xdi_msg.h b/drivers/isdn/hardware/eicon/xdi_msg.h
deleted file mode 100644
index 0646079bf466..000000000000
--- a/drivers/isdn/hardware/eicon/xdi_msg.h
+++ /dev/null
@@ -1,128 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* $Id: xdi_msg.h,v 1.1.2.2 2001/02/16 08:40:36 armin Exp $ */
-
-#ifndef __DIVA_XDI_UM_CFG_MESSAGE_H__
-#define __DIVA_XDI_UM_CFG_MESSAGE_H__
-
-/*
-  Definition of messages used to communicate between
-  XDI device driver and user mode configuration utility
-*/
-
-/*
-  As acknowledge one DWORD - card ordinal will be read from the card
-*/
-#define DIVA_XDI_UM_CMD_GET_CARD_ORDINAL	0
-
-/*
-  no acknowledge will be generated, memory block will be written in the
-  memory at given offset
-*/
-#define DIVA_XDI_UM_CMD_WRITE_SDRAM_BLOCK	1
-
-/*
-  no acknowledge will be genatated, FPGA will be programmed
-*/
-#define DIVA_XDI_UM_CMD_WRITE_FPGA				2
-
-/*
-  As acknowledge block of SDRAM will be read in the user buffer
-*/
-#define DIVA_XDI_UM_CMD_READ_SDRAM				3
-
-/*
-  As acknowledge dword with serial number will be read in the user buffer
-*/
-#define DIVA_XDI_UM_CMD_GET_SERIAL_NR			4
-
-/*
-  As acknowledge struct consisting from 9 dwords with PCI info.
-  dword[0...7] = 8 PCI BARS
-  dword[9]		 = IRQ
-*/
-#define DIVA_XDI_UM_CMD_GET_PCI_HW_CONFIG	5
-
-/*
-  Reset of the board + activation of primary
-  boot loader
-*/
-#define DIVA_XDI_UM_CMD_RESET_ADAPTER			6
-
-/*
-  Called after code download to start adapter
-  at specified address
-  Start does set new set of features due to fact that we not know
-  if protocol features have changed
-*/
-#define DIVA_XDI_UM_CMD_START_ADAPTER			7
-
-/*
-  Stop adapter, called if user
-  wishes to stop adapter without unload
-  of the driver, to reload adapter with
-  different protocol
-*/
-#define DIVA_XDI_UM_CMD_STOP_ADAPTER			8
-
-/*
-  Get state of current adapter
-  Acknowledge is one dword with following values:
-  0 - adapter ready for download
-  1 - adapter running
-  2 - adapter dead
-  3 - out of service, driver should be restarted or hardware problem
-*/
-#define DIVA_XDI_UM_CMD_GET_CARD_STATE		9
-
-/*
-  Reads XLOG entry from the card
-*/
-#define DIVA_XDI_UM_CMD_READ_XLOG_ENTRY		10
-
-/*
-  Set untranslated protocol code features
-*/
-#define DIVA_XDI_UM_CMD_SET_PROTOCOL_FEATURES	11
-
-typedef struct _diva_xdi_um_cfg_cmd_data_set_features {
-	dword features;
-} diva_xdi_um_cfg_cmd_data_set_features_t;
-
-typedef struct _diva_xdi_um_cfg_cmd_data_start {
-	dword offset;
-	dword features;
-} diva_xdi_um_cfg_cmd_data_start_t;
-
-typedef struct _diva_xdi_um_cfg_cmd_data_write_sdram {
-	dword ram_number;
-	dword offset;
-	dword length;
-} diva_xdi_um_cfg_cmd_data_write_sdram_t;
-
-typedef struct _diva_xdi_um_cfg_cmd_data_write_fpga {
-	dword fpga_number;
-	dword image_length;
-} diva_xdi_um_cfg_cmd_data_write_fpga_t;
-
-typedef struct _diva_xdi_um_cfg_cmd_data_read_sdram {
-	dword ram_number;
-	dword offset;
-	dword length;
-} diva_xdi_um_cfg_cmd_data_read_sdram_t;
-
-typedef union _diva_xdi_um_cfg_cmd_data {
-	diva_xdi_um_cfg_cmd_data_write_sdram_t write_sdram;
-	diva_xdi_um_cfg_cmd_data_write_fpga_t write_fpga;
-	diva_xdi_um_cfg_cmd_data_read_sdram_t read_sdram;
-	diva_xdi_um_cfg_cmd_data_start_t start;
-	diva_xdi_um_cfg_cmd_data_set_features_t features;
-} diva_xdi_um_cfg_cmd_data_t;
-
-typedef struct _diva_xdi_um_cfg_cmd {
-	dword adapter;		/* Adapter number 1...N */
-	dword command;
-	diva_xdi_um_cfg_cmd_data_t command_data;
-	dword data_length;	/* Plain binary data will follow */
-} diva_xdi_um_cfg_cmd_t;
-
-#endif
diff --git a/drivers/isdn/hardware/eicon/xdi_vers.h b/drivers/isdn/hardware/eicon/xdi_vers.h
deleted file mode 100644
index b3479e59c7c5..000000000000
--- a/drivers/isdn/hardware/eicon/xdi_vers.h
+++ /dev/null
@@ -1,26 +0,0 @@
-
-/*
- *
- Copyright (c) Eicon Networks, 2002.
- *
- This source file is supplied for the use with
- Eicon Networks range of DIVA Server Adapters.
- *
- Eicon File Revision :    2.1
- *
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
- *
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY OF ANY KIND WHATSOEVER INCLUDING ANY
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- *
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-static char diva_xdi_common_code_build[] = "102-52";
-- 
cgit v1.2.3


From 5e1abdc3fe56939d9ac34209706b1a527b77b61b Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Tue, 6 Nov 2018 10:45:36 -0500
Subject: net: skbuff.h: remove unnecessary unlikely()

WARN_ON() already contains an unlikely(), so it's not necessary to use
unlikely.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0ba687454267..7dcfb5591dc3 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2508,10 +2508,8 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len);
 
 static inline void __skb_set_length(struct sk_buff *skb, unsigned int len)
 {
-	if (unlikely(skb_is_nonlinear(skb))) {
-		WARN_ON(1);
+	if (WARN_ON(skb_is_nonlinear(skb)))
 		return;
-	}
 	skb->len = len;
 	skb_set_tail_pointer(skb, len);
 }
-- 
cgit v1.2.3


From 0b215b9798640a542c526e3ae69dee83861a4aee Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 6 Nov 2018 14:25:52 -0800
Subject: ipv6: gro: do not use slow memcmp() in ipv6_gro_receive()

ipv6_gro_receive() compares 34 bytes using slow memcmp(),
while handcoding with a couple of ipv6_addr_equal() is much faster.

Before this patch, "perf top -e cycles:pp -C <cpu>" would
see memcmp() using ~10% of cpu cycles on a 40Gbit NIC
receiving IPv6 TCP traffic.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_offload.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index c7e495f12011..70f525c33cb6 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -229,14 +229,21 @@ static struct sk_buff *ipv6_gro_receive(struct list_head *head,
 		 * XXX skbs on the gro_list have all been parsed and pulled
 		 * already so we don't need to compare nlen
 		 * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops)))
-		 * memcmp() alone below is suffcient, right?
+		 * memcmp() alone below is sufficient, right?
 		 */
 		 if ((first_word & htonl(0xF00FFFFF)) ||
-		    memcmp(&iph->nexthdr, &iph2->nexthdr,
-			   nlen - offsetof(struct ipv6hdr, nexthdr))) {
+		    !ipv6_addr_equal(&iph->saddr, &iph2->saddr) ||
+		    !ipv6_addr_equal(&iph->daddr, &iph2->daddr) ||
+		    *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) {
+not_same_flow:
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
 		}
+		if (unlikely(nlen > sizeof(struct ipv6hdr))) {
+			if (memcmp(iph + 1, iph2 + 1,
+				   nlen - sizeof(struct ipv6hdr)))
+				goto not_same_flow;
+		}
 		/* flush if Traffic Class fields are different */
 		NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000));
 		NAPI_GRO_CB(p)->flush |= flush;
-- 
cgit v1.2.3


From d0522f1cd25edb796548f91e04766fa3cbc3b6df Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 6 Nov 2018 12:51:14 -0800
Subject: net: Add extack argument to rtnl_create_link

Add extack arg to rtnl_create_link and add messages for invalid
number of Tx or Rx queues.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/can/vxcan.c |  2 +-
 drivers/net/geneve.c    |  2 +-
 drivers/net/veth.c      |  2 +-
 drivers/net/vxlan.c     |  2 +-
 include/net/rtnetlink.h |  3 ++-
 net/core/rtnetlink.c    | 18 ++++++++++++------
 net/ipv4/ip_gre.c       |  2 +-
 7 files changed, 19 insertions(+), 12 deletions(-)

diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c
index ed6828821fbd..80af658e530d 100644
--- a/drivers/net/can/vxcan.c
+++ b/drivers/net/can/vxcan.c
@@ -207,7 +207,7 @@ static int vxcan_newlink(struct net *net, struct net_device *dev,
 		return PTR_ERR(peer_net);
 
 	peer = rtnl_create_link(peer_net, ifname, name_assign_type,
-				&vxcan_link_ops, tbp);
+				&vxcan_link_ops, tbp, extack);
 	if (IS_ERR(peer)) {
 		put_net(peer_net);
 		return PTR_ERR(peer);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index a0cd1c41cf5f..fbfc13d81f66 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1666,7 +1666,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 
 	memset(tb, 0, sizeof(tb));
 	dev = rtnl_create_link(net, name, name_assign_type,
-			       &geneve_link_ops, tb);
+			       &geneve_link_ops, tb, NULL);
 	if (IS_ERR(dev))
 		return dev;
 
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 890fa5b905e2..f412ea1cef18 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1253,7 +1253,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 		return PTR_ERR(net);
 
 	peer = rtnl_create_link(net, ifname, name_assign_type,
-				&veth_link_ops, tbp);
+				&veth_link_ops, tbp, extack);
 	if (IS_ERR(peer)) {
 		put_net(net);
 		return PTR_ERR(peer);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 297cdeaef479..ae969f806d56 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3749,7 +3749,7 @@ struct net_device *vxlan_dev_create(struct net *net, const char *name,
 	memset(&tb, 0, sizeof(tb));
 
 	dev = rtnl_create_link(net, name, name_assign_type,
-			       &vxlan_link_ops, tb);
+			       &vxlan_link_ops, tb, NULL);
 	if (IS_ERR(dev))
 		return dev;
 
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index cf26e5aacac4..e2091bb2b3a8 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -159,7 +159,8 @@ struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]);
 struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 				    unsigned char name_assign_type,
 				    const struct rtnl_link_ops *ops,
-				    struct nlattr *tb[]);
+				    struct nlattr *tb[],
+				    struct netlink_ext_ack *extack);
 int rtnl_delete_link(struct net_device *dev);
 int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 33d9227a8b80..f787b7640d49 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2885,9 +2885,11 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 }
 EXPORT_SYMBOL(rtnl_configure_link);
 
-struct net_device *rtnl_create_link(struct net *net,
-	const char *ifname, unsigned char name_assign_type,
-	const struct rtnl_link_ops *ops, struct nlattr *tb[])
+struct net_device *rtnl_create_link(struct net *net, const char *ifname,
+				    unsigned char name_assign_type,
+				    const struct rtnl_link_ops *ops,
+				    struct nlattr *tb[],
+				    struct netlink_ext_ack *extack)
 {
 	struct net_device *dev;
 	unsigned int num_tx_queues = 1;
@@ -2903,11 +2905,15 @@ struct net_device *rtnl_create_link(struct net *net,
 	else if (ops->get_num_rx_queues)
 		num_rx_queues = ops->get_num_rx_queues();
 
-	if (num_tx_queues < 1 || num_tx_queues > 4096)
+	if (num_tx_queues < 1 || num_tx_queues > 4096) {
+		NL_SET_ERR_MSG(extack, "Invalid number of transmit queues");
 		return ERR_PTR(-EINVAL);
+	}
 
-	if (num_rx_queues < 1 || num_rx_queues > 4096)
+	if (num_rx_queues < 1 || num_rx_queues > 4096) {
+		NL_SET_ERR_MSG(extack, "Invalid number of receive queues");
 		return ERR_PTR(-EINVAL);
+	}
 
 	dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type,
 			       ops->setup, num_tx_queues, num_rx_queues);
@@ -3163,7 +3169,7 @@ replay:
 		}
 
 		dev = rtnl_create_link(link_net ? : dest_net, ifname,
-				       name_assign_type, ops, tb);
+				       name_assign_type, ops, tb, extack);
 		if (IS_ERR(dev)) {
 			err = PTR_ERR(dev);
 			goto out;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 38befe829caf..2c67af644e64 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1601,7 +1601,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	memset(&tb, 0, sizeof(tb));
 
 	dev = rtnl_create_link(net, name, name_assign_type,
-			       &ipgre_tap_ops, tb);
+			       &ipgre_tap_ops, tb, NULL);
 	if (IS_ERR(dev))
 		return dev;
 
-- 
cgit v1.2.3


From d7e774f356765d49b63490d611caa496713b7abb Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 6 Nov 2018 12:51:15 -0800
Subject: net: Add extack argument to ip_fib_metrics_init

Add extack argument to ip_fib_metrics_init and add messages for invalid
metrics.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h         |  3 ++-
 net/ipv4/fib_semantics.c |  2 +-
 net/ipv4/metrics.c       | 26 +++++++++++++++++++-------
 net/ipv6/route.c         |  5 +++--
 4 files changed, 25 insertions(+), 11 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 72593e171d14..462182f78236 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -421,7 +421,8 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
 }
 
 struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
-					int fc_mx_len);
+					int fc_mx_len,
+					struct netlink_ext_ack *extack);
 static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics)
 {
 	if (fib_metrics != &dst_default_metrics &&
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b5c3937ca6ec..5022bc63863a 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1076,7 +1076,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	if (!fi)
 		goto failure;
 	fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx,
-					      cfg->fc_mx_len);
+					      cfg->fc_mx_len, extack);
 	if (unlikely(IS_ERR(fi->fib_metrics))) {
 		err = PTR_ERR(fi->fib_metrics);
 		kfree(fi);
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
index 6d218f5a2e71..ca9a5fefdefa 100644
--- a/net/ipv4/metrics.c
+++ b/net/ipv4/metrics.c
@@ -6,7 +6,8 @@
 #include <net/tcp.h>
 
 static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
-			      int fc_mx_len, u32 *metrics)
+			      int fc_mx_len, u32 *metrics,
+			      struct netlink_ext_ack *extack)
 {
 	bool ecn_ca = false;
 	struct nlattr *nla;
@@ -21,19 +22,26 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
 
 		if (!type)
 			continue;
-		if (type > RTAX_MAX)
+		if (type > RTAX_MAX) {
+			NL_SET_ERR_MSG(extack, "Invalid metric type");
 			return -EINVAL;
+		}
 
 		if (type == RTAX_CC_ALGO) {
 			char tmp[TCP_CA_NAME_MAX];
 
 			nla_strlcpy(tmp, nla, sizeof(tmp));
 			val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
-			if (val == TCP_CA_UNSPEC)
+			if (val == TCP_CA_UNSPEC) {
+				NL_SET_ERR_MSG(extack, "Unknown tcp congestion algorithm");
 				return -EINVAL;
+			}
 		} else {
-			if (nla_len(nla) != sizeof(u32))
+			if (nla_len(nla) != sizeof(u32)) {
+				NL_SET_ERR_MSG_ATTR(extack, nla,
+						    "Invalid attribute in metrics");
 				return -EINVAL;
+			}
 			val = nla_get_u32(nla);
 		}
 		if (type == RTAX_ADVMSS && val > 65535 - 40)
@@ -42,8 +50,10 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
 			val = 65535 - 15;
 		if (type == RTAX_HOPLIMIT && val > 255)
 			val = 255;
-		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
+		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) {
+			NL_SET_ERR_MSG(extack, "Unknown flag set in feature mask in metrics attribute");
 			return -EINVAL;
+		}
 		metrics[type - 1] = val;
 	}
 
@@ -54,7 +64,8 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
 }
 
 struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
-					int fc_mx_len)
+					int fc_mx_len,
+					struct netlink_ext_ack *extack)
 {
 	struct dst_metrics *fib_metrics;
 	int err;
@@ -66,7 +77,8 @@ struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
 	if (unlikely(!fib_metrics))
 		return ERR_PTR(-ENOMEM);
 
-	err = ip_metrics_convert(net, fc_mx, fc_mx_len, fib_metrics->metrics);
+	err = ip_metrics_convert(net, fc_mx, fc_mx_len, fib_metrics->metrics,
+				 extack);
 	if (!err) {
 		refcount_set(&fib_metrics->refcnt, 1);
 	} else {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2a7423c39456..b2447b7c7303 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2975,7 +2975,8 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	if (!rt)
 		goto out;
 
-	rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len);
+	rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len,
+					       extack);
 	if (IS_ERR(rt->fib6_metrics)) {
 		err = PTR_ERR(rt->fib6_metrics);
 		/* Do not leave garbage there. */
@@ -3708,7 +3709,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 	if (!f6i)
 		return ERR_PTR(-ENOMEM);
 
-	f6i->fib6_metrics = ip_fib_metrics_init(net, NULL, 0);
+	f6i->fib6_metrics = ip_fib_metrics_init(net, NULL, 0, NULL);
 	f6i->dst_nocount = true;
 	f6i->dst_host = true;
 	f6i->fib6_protocol = RTPROT_KERNEL;
-- 
cgit v1.2.3


From 68d57f3b1d1a87b4022a0a7463126d7ea172bda1 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 6 Nov 2018 12:51:16 -0800
Subject: rtnetlink: Add more extack messages to rtnl_newlink

Add extack arg to the nla_parse_nested calls in rtnl_newlink, and
add messages for unknown device type and link network namespace id.
In particular, it improves the failure message when the wrong link
type is used. From
    $ ip li add bond1 type bonding
    RTNETLINK answers: Operation not supported
to
    $ ip li add bond1 type bonding
    Error: Unknown device type.

(The module name is bonding but the link type is bond.)

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f787b7640d49..86f2d9cbdae3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3054,7 +3054,7 @@ replay:
 			if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
 				err = nla_parse_nested(attr, ops->maxtype,
 						       linkinfo[IFLA_INFO_DATA],
-						       ops->policy, NULL);
+						       ops->policy, extack);
 				if (err < 0)
 					return err;
 				data = attr;
@@ -3076,7 +3076,7 @@ replay:
 						       m_ops->slave_maxtype,
 						       linkinfo[IFLA_INFO_SLAVE_DATA],
 						       m_ops->slave_policy,
-						       NULL);
+						       extack);
 				if (err < 0)
 					return err;
 				slave_data = slave_attr;
@@ -3140,6 +3140,7 @@ replay:
 					goto replay;
 			}
 #endif
+			NL_SET_ERR_MSG(extack, "Unknown device type");
 			return -EOPNOTSUPP;
 		}
 
@@ -3160,6 +3161,7 @@ replay:
 
 			link_net = get_net_ns_by_id(dest_net, id);
 			if (!link_net) {
+				NL_SET_ERR_MSG(extack, "Unknown network namespace id");
 				err =  -EINVAL;
 				goto out;
 			}
-- 
cgit v1.2.3


From ae7a5aff783c79d5ca87867df84b08c43447159b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 6 Nov 2018 12:58:37 -0800
Subject: net: dsa: bcm_sf2: Keep copy of inserted rules

We tried hard to use the hardware as a storage area, which made things
needlessly complex in that we had to both marshall and unmarshall the
ethtool_rx_flow_spec into what the CFP hardware understands but it did
not require any driver level allocations, so that was nice.

Keep a copy of the ethtool_rx_flow_spec rule we want to insert, and also
make sure we don't have a duplicate rule already. This greatly speeds up
the deletion time since we only need to clear the slice's valid bit and
not perform a full read.

This is a preparatory step for being able to restore rules upon system
resumption where the hardware loses its context partially or entirely.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c     |   2 +
 drivers/net/dsa/bcm_sf2.h     |   2 +
 drivers/net/dsa/bcm_sf2_cfp.c | 144 ++++++++++++++++++++++++++++++++++++++----
 3 files changed, 137 insertions(+), 11 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 2eb68769562c..89722dbfafb8 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1061,6 +1061,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	spin_lock_init(&priv->indir_lock);
 	mutex_init(&priv->stats_mutex);
 	mutex_init(&priv->cfp.lock);
+	INIT_LIST_HEAD(&priv->cfp.rules_list);
 
 	/* CFP rule #0 cannot be used for specific classifications, flag it as
 	 * permanently used
@@ -1166,6 +1167,7 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev)
 
 	priv->wol_ports_mask = 0;
 	dsa_unregister_switch(priv->dev->ds);
+	bcm_sf2_cfp_exit(priv->dev->ds);
 	/* Disable all ports and interrupts */
 	bcm_sf2_sw_suspend(priv->dev->ds);
 	bcm_sf2_mdio_unregister(priv);
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index cc31e986e6e3..03444982c25e 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -56,6 +56,7 @@ struct bcm_sf2_cfp_priv {
 	DECLARE_BITMAP(used, CFP_NUM_RULES);
 	DECLARE_BITMAP(unique, CFP_NUM_RULES);
 	unsigned int rules_cnt;
+	struct list_head rules_list;
 };
 
 struct bcm_sf2_priv {
@@ -213,5 +214,6 @@ int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port,
 int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port,
 		      struct ethtool_rxnfc *nfc);
 int bcm_sf2_cfp_rst(struct bcm_sf2_priv *priv);
+void bcm_sf2_cfp_exit(struct dsa_switch *ds);
 
 #endif /* __BCM_SF2_H */
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 47c5f272a084..29b6b4204662 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -20,6 +20,12 @@
 #include "bcm_sf2.h"
 #include "bcm_sf2_regs.h"
 
+struct cfp_rule {
+	int port;
+	struct ethtool_rx_flow_spec fs;
+	struct list_head next;
+};
+
 struct cfp_udf_slice_layout {
 	u8 slices[UDFS_PER_SLICE];
 	u32 mask_value;
@@ -515,6 +521,61 @@ static void bcm_sf2_cfp_slice_ipv6(struct bcm_sf2_priv *priv,
 	core_writel(priv, reg, offset);
 }
 
+static struct cfp_rule *bcm_sf2_cfp_rule_find(struct bcm_sf2_priv *priv,
+					      int port, u32 location)
+{
+	struct cfp_rule *rule = NULL;
+
+	list_for_each_entry(rule, &priv->cfp.rules_list, next) {
+		if (rule->port == port && rule->fs.location == location)
+			break;
+	};
+
+	return rule;
+}
+
+static int bcm_sf2_cfp_rule_cmp(struct bcm_sf2_priv *priv, int port,
+				struct ethtool_rx_flow_spec *fs)
+{
+	struct cfp_rule *rule = NULL;
+	size_t fs_size = 0;
+	int ret = 1;
+
+	if (list_empty(&priv->cfp.rules_list))
+		return ret;
+
+	list_for_each_entry(rule, &priv->cfp.rules_list, next) {
+		ret = 1;
+		if (rule->port != port)
+			continue;
+
+		if (rule->fs.flow_type != fs->flow_type ||
+		    rule->fs.ring_cookie != fs->ring_cookie ||
+		    rule->fs.m_ext.data[0] != fs->m_ext.data[0])
+			continue;
+
+		switch (fs->flow_type & ~FLOW_EXT) {
+		case TCP_V6_FLOW:
+		case UDP_V6_FLOW:
+			fs_size = sizeof(struct ethtool_tcpip6_spec);
+			break;
+		case TCP_V4_FLOW:
+		case UDP_V4_FLOW:
+			fs_size = sizeof(struct ethtool_tcpip4_spec);
+			break;
+		default:
+			continue;
+		}
+
+		ret = memcmp(&rule->fs.h_u, &fs->h_u, fs_size);
+		ret |= memcmp(&rule->fs.m_u, &fs->m_u, fs_size);
+		if (ret == 0)
+			break;
+	}
+
+	return ret;
+}
+
 static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
 				     unsigned int port_num,
 				     unsigned int queue_num,
@@ -735,6 +796,7 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	s8 cpu_port = ds->ports[port].cpu_dp->index;
 	__u64 ring_cookie = fs->ring_cookie;
 	unsigned int queue_num, port_num;
+	struct cfp_rule *rule = NULL;
 	int ret = -EINVAL;
 
 	/* Check for unsupported extensions */
@@ -750,6 +812,10 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	    fs->location > bcm_sf2_cfp_rule_size(priv))
 		return -EINVAL;
 
+	ret = bcm_sf2_cfp_rule_cmp(priv, port, fs);
+	if (ret == 0)
+		return -EEXIST;
+
 	/* This rule is a Wake-on-LAN filter and we must specifically
 	 * target the CPU port in order for it to be working.
 	 */
@@ -775,6 +841,10 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	if (port_num >= 7)
 		port_num -= 1;
 
+	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+	if (!rule)
+		return -ENOMEM;
+
 	switch (fs->flow_type & ~FLOW_EXT) {
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
@@ -787,9 +857,19 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 						queue_num, fs);
 		break;
 	default:
+		ret = -EINVAL;
 		break;
 	}
 
+	if (ret) {
+		kfree(rule);
+		return ret;
+	}
+
+	rule->port = port;
+	memcpy(&rule->fs, fs, sizeof(*fs));
+	list_add_tail(&rule->next, &priv->cfp.rules_list);
+
 	return ret;
 }
 
@@ -833,6 +913,7 @@ static int bcm_sf2_cfp_rule_del_one(struct bcm_sf2_priv *priv, int port,
 static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 				u32 loc)
 {
+	struct cfp_rule *rule;
 	u32 next_loc = 0;
 	int ret;
 
@@ -843,6 +924,10 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 	if (!test_bit(loc, priv->cfp.unique) || loc == 0)
 		return -EINVAL;
 
+	rule = bcm_sf2_cfp_rule_find(priv, port, loc);
+	if (!rule)
+		return -EINVAL;
+
 	ret = bcm_sf2_cfp_rule_del_one(priv, port, loc, &next_loc);
 	if (ret)
 		return ret;
@@ -851,6 +936,9 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 	if (next_loc)
 		ret = bcm_sf2_cfp_rule_del_one(priv, port, next_loc, NULL);
 
+	list_del(&rule->next);
+	kfree(rule);
+
 	return ret;
 }
 
@@ -867,9 +955,9 @@ static void bcm_sf2_invert_masks(struct ethtool_rx_flow_spec *flow)
 	flow->m_ext.data[1] ^= cpu_to_be32(~0);
 }
 
-static int bcm_sf2_cfp_unslice_ipv4(struct bcm_sf2_priv *priv,
-				    struct ethtool_tcpip4_spec *v4_spec,
-				    bool mask)
+static int __maybe_unused bcm_sf2_cfp_unslice_ipv4(struct bcm_sf2_priv *priv,
+						   struct ethtool_tcpip4_spec *v4_spec,
+						   bool mask)
 {
 	u32 reg, offset, ipv4;
 	u16 src_dst_port;
@@ -969,9 +1057,10 @@ static int bcm_sf2_cfp_ipv4_rule_get(struct bcm_sf2_priv *priv, int port,
 	return bcm_sf2_cfp_unslice_ipv4(priv, v4_m_spec, true);
 }
 
-static int bcm_sf2_cfp_unslice_ipv6(struct bcm_sf2_priv *priv,
-				     __be32 *ip6_addr, __be16 *port,
-				     bool mask)
+static int __maybe_unused bcm_sf2_cfp_unslice_ipv6(struct bcm_sf2_priv *priv,
+						   __be32 *ip6_addr,
+						   __be16 *port,
+						   bool mask)
 {
 	u32 reg, tmp, offset;
 
@@ -1050,9 +1139,10 @@ static int bcm_sf2_cfp_unslice_ipv6(struct bcm_sf2_priv *priv,
 	return 0;
 }
 
-static int bcm_sf2_cfp_ipv6_rule_get(struct bcm_sf2_priv *priv, int port,
-				     struct ethtool_rx_flow_spec *fs,
-				     u32 next_loc)
+static int __maybe_unused bcm_sf2_cfp_ipv6_rule_get(struct bcm_sf2_priv *priv,
+						    int port,
+						    struct ethtool_rx_flow_spec *fs,
+						    u32 next_loc)
 {
 	struct ethtool_tcpip6_spec *v6_spec = NULL, *v6_m_spec = NULL;
 	u32 reg;
@@ -1111,8 +1201,9 @@ static int bcm_sf2_cfp_ipv6_rule_get(struct bcm_sf2_priv *priv, int port,
 					&v6_m_spec->psrc, true);
 }
 
-static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
-				struct ethtool_rxnfc *nfc)
+static int __maybe_unused bcm_sf2_cfp_rule_get_hw(struct bcm_sf2_priv *priv,
+						  int port,
+						  struct ethtool_rxnfc *nfc)
 {
 	u32 reg, ipv4_or_chain_id;
 	unsigned int queue_num;
@@ -1174,6 +1265,25 @@ static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
 	return 0;
 }
 
+static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
+				struct ethtool_rxnfc *nfc)
+{
+	struct cfp_rule *rule;
+
+	rule = bcm_sf2_cfp_rule_find(priv, port, nfc->fs.location);
+	if (!rule)
+		return -EINVAL;
+
+	memcpy(&nfc->fs, &rule->fs, sizeof(rule->fs));
+
+	bcm_sf2_invert_masks(&nfc->fs);
+
+	/* Put the TCAM size here */
+	nfc->data = bcm_sf2_cfp_rule_size(priv);
+
+	return 0;
+}
+
 /* We implement the search doing a TCAM search operation */
 static int bcm_sf2_cfp_rule_get_all(struct bcm_sf2_priv *priv,
 				    int port, struct ethtool_rxnfc *nfc,
@@ -1302,3 +1412,15 @@ int bcm_sf2_cfp_rst(struct bcm_sf2_priv *priv)
 
 	return 0;
 }
+
+void bcm_sf2_cfp_exit(struct dsa_switch *ds)
+{
+	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	struct cfp_rule *rule, *n;
+
+	if (list_empty(&priv->cfp.rules_list))
+		return;
+
+	list_for_each_entry_safe_reverse(rule, n, &priv->cfp.rules_list, next)
+		bcm_sf2_cfp_rule_del(priv, rule->port, rule->fs.location);
+}
-- 
cgit v1.2.3


From ce24b08a2e6f7c70dd7a13bd8c2082950f3dd9f3 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 6 Nov 2018 12:58:38 -0800
Subject: net: dsa: bcm_sf2: Split rule handling from HW operation

In preparation for restoring CFP rules during system wide system
suspend/resume where the hardware loses its context, split the rule
validation from its actual insertion as well as the rule removal from
its actual hardware deletion operation.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2_cfp.c | 89 ++++++++++++++++++++++++++-----------------
 1 file changed, 54 insertions(+), 35 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 29b6b4204662..396bfa43c2e1 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -789,32 +789,14 @@ out_err:
 	return ret;
 }
 
-static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
-				struct ethtool_rx_flow_spec *fs)
+static int bcm_sf2_cfp_rule_insert(struct dsa_switch *ds, int port,
+				   struct ethtool_rx_flow_spec *fs)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
 	s8 cpu_port = ds->ports[port].cpu_dp->index;
 	__u64 ring_cookie = fs->ring_cookie;
 	unsigned int queue_num, port_num;
-	struct cfp_rule *rule = NULL;
-	int ret = -EINVAL;
-
-	/* Check for unsupported extensions */
-	if ((fs->flow_type & FLOW_EXT) && (fs->m_ext.vlan_etype ||
-	     fs->m_ext.data[1]))
-		return -EINVAL;
-
-	if (fs->location != RX_CLS_LOC_ANY &&
-	    test_bit(fs->location, priv->cfp.used))
-		return -EBUSY;
-
-	if (fs->location != RX_CLS_LOC_ANY &&
-	    fs->location > bcm_sf2_cfp_rule_size(priv))
-		return -EINVAL;
-
-	ret = bcm_sf2_cfp_rule_cmp(priv, port, fs);
-	if (ret == 0)
-		return -EEXIST;
+	int ret;
 
 	/* This rule is a Wake-on-LAN filter and we must specifically
 	 * target the CPU port in order for it to be working.
@@ -841,10 +823,6 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	if (port_num >= 7)
 		port_num -= 1;
 
-	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
-	if (!rule)
-		return -ENOMEM;
-
 	switch (fs->flow_type & ~FLOW_EXT) {
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
@@ -861,6 +839,38 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 		break;
 	}
 
+	return ret;
+}
+
+static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
+				struct ethtool_rx_flow_spec *fs)
+{
+	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	struct cfp_rule *rule = NULL;
+	int ret = -EINVAL;
+
+	/* Check for unsupported extensions */
+	if ((fs->flow_type & FLOW_EXT) && (fs->m_ext.vlan_etype ||
+	     fs->m_ext.data[1]))
+		return -EINVAL;
+
+	if (fs->location != RX_CLS_LOC_ANY &&
+	    test_bit(fs->location, priv->cfp.used))
+		return -EBUSY;
+
+	if (fs->location != RX_CLS_LOC_ANY &&
+	    fs->location > bcm_sf2_cfp_rule_size(priv))
+		return -EINVAL;
+
+	ret = bcm_sf2_cfp_rule_cmp(priv, port, fs);
+	if (ret == 0)
+		return -EEXIST;
+
+	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+	if (!rule)
+		return -ENOMEM;
+
+	ret = bcm_sf2_cfp_rule_insert(ds, port, fs);
 	if (ret) {
 		kfree(rule);
 		return ret;
@@ -910,13 +920,28 @@ static int bcm_sf2_cfp_rule_del_one(struct bcm_sf2_priv *priv, int port,
 	return 0;
 }
 
-static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
-				u32 loc)
+static int bcm_sf2_cfp_rule_remove(struct bcm_sf2_priv *priv, int port,
+				   u32 loc)
 {
-	struct cfp_rule *rule;
 	u32 next_loc = 0;
 	int ret;
 
+	ret = bcm_sf2_cfp_rule_del_one(priv, port, loc, &next_loc);
+	if (ret)
+		return ret;
+
+	/* If this was an IPv6 rule, delete is companion rule too */
+	if (next_loc)
+		ret = bcm_sf2_cfp_rule_del_one(priv, port, next_loc, NULL);
+
+	return ret;
+}
+
+static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port, u32 loc)
+{
+	struct cfp_rule *rule;
+	int ret;
+
 	/* Refuse deleting unused rules, and those that are not unique since
 	 * that could leave IPv6 rules with one of the chained rule in the
 	 * table.
@@ -928,13 +953,7 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 	if (!rule)
 		return -EINVAL;
 
-	ret = bcm_sf2_cfp_rule_del_one(priv, port, loc, &next_loc);
-	if (ret)
-		return ret;
-
-	/* If this was an IPv6 rule, delete is companion rule too */
-	if (next_loc)
-		ret = bcm_sf2_cfp_rule_del_one(priv, port, next_loc, NULL);
+	ret = bcm_sf2_cfp_rule_remove(priv, port, loc);
 
 	list_del(&rule->next);
 	kfree(rule);
-- 
cgit v1.2.3


From 1c0130f0b5756b38b636e3cb7b3abc2b48bb9edc Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 6 Nov 2018 12:58:39 -0800
Subject: net: dsa: bcm_sf2: Restore CFP rules during system resume

The hardware can lose its context during system suspend, and depending
on the switch generation (7445 vs. 7278), while the rules are still
there, they will have their valid bit cleared (because that's the
fastest way for the HW to reset things). Just make sure we re-apply them
coming back from resume. The 7445 switch is an older version of the core
that has some quirky RAM technology requiring a delete then re-inser to
guarantee the RAM entries are properly latched.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c     |  4 ++++
 drivers/net/dsa/bcm_sf2.h     |  1 +
 drivers/net/dsa/bcm_sf2_cfp.c | 36 ++++++++++++++++++++++++++++++++++++
 3 files changed, 41 insertions(+)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 89722dbfafb8..d8b93043b789 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -710,6 +710,10 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds)
 		return ret;
 	}
 
+	ret = bcm_sf2_cfp_resume(ds);
+	if (ret)
+		return ret;
+
 	if (priv->hw_params.num_gphy == 1)
 		bcm_sf2_gphy_enable_set(ds, true);
 
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 03444982c25e..faaef320ec48 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -215,5 +215,6 @@ int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port,
 		      struct ethtool_rxnfc *nfc);
 int bcm_sf2_cfp_rst(struct bcm_sf2_priv *priv);
 void bcm_sf2_cfp_exit(struct dsa_switch *ds);
+int bcm_sf2_cfp_resume(struct dsa_switch *ds);
 
 #endif /* __BCM_SF2_H */
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 396bfa43c2e1..5034e4f56fd5 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -1443,3 +1443,39 @@ void bcm_sf2_cfp_exit(struct dsa_switch *ds)
 	list_for_each_entry_safe_reverse(rule, n, &priv->cfp.rules_list, next)
 		bcm_sf2_cfp_rule_del(priv, rule->port, rule->fs.location);
 }
+
+int bcm_sf2_cfp_resume(struct dsa_switch *ds)
+{
+	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	struct cfp_rule *rule;
+	int ret = 0;
+	u32 reg;
+
+	if (list_empty(&priv->cfp.rules_list))
+		return ret;
+
+	reg = core_readl(priv, CORE_CFP_CTL_REG);
+	reg &= ~CFP_EN_MAP_MASK;
+	core_writel(priv, reg, CORE_CFP_CTL_REG);
+
+	ret = bcm_sf2_cfp_rst(priv);
+	if (ret)
+		return ret;
+
+	list_for_each_entry(rule, &priv->cfp.rules_list, next) {
+		ret = bcm_sf2_cfp_rule_remove(priv, rule->port,
+					      rule->fs.location);
+		if (ret) {
+			dev_err(ds->dev, "failed to remove rule\n");
+			return ret;
+		}
+
+		ret = bcm_sf2_cfp_rule_insert(ds, rule->port, &rule->fs);
+		if (ret) {
+			dev_err(ds->dev, "failed to restore rule\n");
+			return ret;
+		}
+	};
+
+	return ret;
+}
-- 
cgit v1.2.3


From 1c60c7f9001140e4a3bfae4b1cdcead6b075aecf Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 6 Nov 2018 12:58:40 -0800
Subject: net: dsa: bcm_sf2: Get rid of unmarshalling functions

Now that we have migrated the CFP rule handling to a list with a
software copy, the delete/get operation just returns what is on the
list, no need to read from the hardware which is both slow and more
error prone.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2_cfp.c | 310 ------------------------------------------
 1 file changed, 310 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 5034e4f56fd5..8f734abde7b3 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -974,316 +974,6 @@ static void bcm_sf2_invert_masks(struct ethtool_rx_flow_spec *flow)
 	flow->m_ext.data[1] ^= cpu_to_be32(~0);
 }
 
-static int __maybe_unused bcm_sf2_cfp_unslice_ipv4(struct bcm_sf2_priv *priv,
-						   struct ethtool_tcpip4_spec *v4_spec,
-						   bool mask)
-{
-	u32 reg, offset, ipv4;
-	u16 src_dst_port;
-
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(3);
-	else
-		offset = CORE_CFP_DATA_PORT(3);
-
-	reg = core_readl(priv, offset);
-	/* src port [15:8] */
-	src_dst_port = reg << 8;
-
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(2);
-	else
-		offset = CORE_CFP_DATA_PORT(2);
-
-	reg = core_readl(priv, offset);
-	/* src port [7:0] */
-	src_dst_port |= (reg >> 24);
-
-	v4_spec->pdst = cpu_to_be16(src_dst_port);
-	v4_spec->psrc = cpu_to_be16((u16)(reg >> 8));
-
-	/* IPv4 dst [15:8] */
-	ipv4 = (reg & 0xff) << 8;
-
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(1);
-	else
-		offset = CORE_CFP_DATA_PORT(1);
-
-	reg = core_readl(priv, offset);
-	/* IPv4 dst [31:16] */
-	ipv4 |= ((reg >> 8) & 0xffff) << 16;
-	/* IPv4 dst [7:0] */
-	ipv4 |= (reg >> 24) & 0xff;
-	v4_spec->ip4dst = cpu_to_be32(ipv4);
-
-	/* IPv4 src [15:8] */
-	ipv4 = (reg & 0xff) << 8;
-
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(0);
-	else
-		offset = CORE_CFP_DATA_PORT(0);
-	reg = core_readl(priv, offset);
-
-	/* Once the TCAM is programmed, the mask reflects the slice number
-	 * being matched, don't bother checking it when reading back the
-	 * mask spec
-	 */
-	if (!mask && !(reg & SLICE_VALID))
-		return -EINVAL;
-
-	/* IPv4 src [7:0] */
-	ipv4 |= (reg >> 24) & 0xff;
-	/* IPv4 src [31:16] */
-	ipv4 |= ((reg >> 8) & 0xffff) << 16;
-	v4_spec->ip4src = cpu_to_be32(ipv4);
-
-	return 0;
-}
-
-static int bcm_sf2_cfp_ipv4_rule_get(struct bcm_sf2_priv *priv, int port,
-				     struct ethtool_rx_flow_spec *fs)
-{
-	struct ethtool_tcpip4_spec *v4_spec = NULL, *v4_m_spec = NULL;
-	u32 reg;
-	int ret;
-
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
-
-	switch ((reg & IPPROTO_MASK) >> IPPROTO_SHIFT) {
-	case IPPROTO_TCP:
-		fs->flow_type = TCP_V4_FLOW;
-		v4_spec = &fs->h_u.tcp_ip4_spec;
-		v4_m_spec = &fs->m_u.tcp_ip4_spec;
-		break;
-	case IPPROTO_UDP:
-		fs->flow_type = UDP_V4_FLOW;
-		v4_spec = &fs->h_u.udp_ip4_spec;
-		v4_m_spec = &fs->m_u.udp_ip4_spec;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	fs->m_ext.data[0] = cpu_to_be32((reg >> IP_FRAG_SHIFT) & 1);
-	v4_spec->tos = (reg >> IPTOS_SHIFT) & IPTOS_MASK;
-
-	ret = bcm_sf2_cfp_unslice_ipv4(priv, v4_spec, false);
-	if (ret)
-		return ret;
-
-	return bcm_sf2_cfp_unslice_ipv4(priv, v4_m_spec, true);
-}
-
-static int __maybe_unused bcm_sf2_cfp_unslice_ipv6(struct bcm_sf2_priv *priv,
-						   __be32 *ip6_addr,
-						   __be16 *port,
-						   bool mask)
-{
-	u32 reg, tmp, offset;
-
-	/* C-Tag		[31:24]
-	 * UDF_n_B8		[23:8] (port)
-	 * UDF_n_B7 (upper)	[7:0] (addr[15:8])
-	 */
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(4);
-	else
-		offset = CORE_CFP_DATA_PORT(4);
-	reg = core_readl(priv, offset);
-	*port = cpu_to_be32(reg) >> 8;
-	tmp = (u32)(reg & 0xff) << 8;
-
-	/* UDF_n_B7 (lower)	[31:24] (addr[7:0])
-	 * UDF_n_B6		[23:8] (addr[31:16])
-	 * UDF_n_B5 (upper)	[7:0] (addr[47:40])
-	 */
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(3);
-	else
-		offset = CORE_CFP_DATA_PORT(3);
-	reg = core_readl(priv, offset);
-	tmp |= (reg >> 24) & 0xff;
-	tmp |= (u32)((reg >> 8) << 16);
-	ip6_addr[3] = cpu_to_be32(tmp);
-	tmp = (u32)(reg & 0xff) << 8;
-
-	/* UDF_n_B5 (lower)	[31:24] (addr[39:32])
-	 * UDF_n_B4		[23:8] (addr[63:48])
-	 * UDF_n_B3 (upper)	[7:0] (addr[79:72])
-	 */
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(2);
-	else
-		offset = CORE_CFP_DATA_PORT(2);
-	reg = core_readl(priv, offset);
-	tmp |= (reg >> 24) & 0xff;
-	tmp |= (u32)((reg >> 8) << 16);
-	ip6_addr[2] = cpu_to_be32(tmp);
-	tmp = (u32)(reg & 0xff) << 8;
-
-	/* UDF_n_B3 (lower)	[31:24] (addr[71:64])
-	 * UDF_n_B2		[23:8] (addr[95:80])
-	 * UDF_n_B1 (upper)	[7:0] (addr[111:104])
-	 */
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(1);
-	else
-		offset = CORE_CFP_DATA_PORT(1);
-	reg = core_readl(priv, offset);
-	tmp |= (reg >> 24) & 0xff;
-	tmp |= (u32)((reg >> 8) << 16);
-	ip6_addr[1] = cpu_to_be32(tmp);
-	tmp = (u32)(reg & 0xff) << 8;
-
-	/* UDF_n_B1 (lower)	[31:24] (addr[103:96])
-	 * UDF_n_B0		[23:8] (addr[127:112])
-	 * Reserved		[7:4]
-	 * Slice ID		[3:2]
-	 * Slice valid		[1:0]
-	 */
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(0);
-	else
-		offset = CORE_CFP_DATA_PORT(0);
-	reg = core_readl(priv, offset);
-	tmp |= (reg >> 24) & 0xff;
-	tmp |= (u32)((reg >> 8) << 16);
-	ip6_addr[0] = cpu_to_be32(tmp);
-
-	if (!mask && !(reg & SLICE_VALID))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int __maybe_unused bcm_sf2_cfp_ipv6_rule_get(struct bcm_sf2_priv *priv,
-						    int port,
-						    struct ethtool_rx_flow_spec *fs,
-						    u32 next_loc)
-{
-	struct ethtool_tcpip6_spec *v6_spec = NULL, *v6_m_spec = NULL;
-	u32 reg;
-	int ret;
-
-	/* UDPv6 and TCPv6 both use ethtool_tcpip6_spec so we are fine
-	 * assuming tcp_ip6_spec here being an union.
-	 */
-	v6_spec = &fs->h_u.tcp_ip6_spec;
-	v6_m_spec = &fs->m_u.tcp_ip6_spec;
-
-	/* Read the second half first */
-	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_spec->ip6dst, &v6_spec->pdst,
-				       false);
-	if (ret)
-		return ret;
-
-	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_m_spec->ip6dst,
-				       &v6_m_spec->pdst, true);
-	if (ret)
-		return ret;
-
-	/* Read last to avoid next entry clobbering the results during search
-	 * operations. We would not have the port enabled for this rule, so
-	 * don't bother checking it.
-	 */
-	(void)core_readl(priv, CORE_CFP_DATA_PORT(7));
-
-	/* The slice number is valid, so read the rule we are chained from now
-	 * which is our first half.
-	 */
-	bcm_sf2_cfp_rule_addr_set(priv, next_loc);
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | TCAM_SEL);
-	if (ret)
-		return ret;
-
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
-
-	switch ((reg & IPPROTO_MASK) >> IPPROTO_SHIFT) {
-	case IPPROTO_TCP:
-		fs->flow_type = TCP_V6_FLOW;
-		break;
-	case IPPROTO_UDP:
-		fs->flow_type = UDP_V6_FLOW;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_spec->ip6src, &v6_spec->psrc,
-				       false);
-	if (ret)
-		return ret;
-
-	return bcm_sf2_cfp_unslice_ipv6(priv, v6_m_spec->ip6src,
-					&v6_m_spec->psrc, true);
-}
-
-static int __maybe_unused bcm_sf2_cfp_rule_get_hw(struct bcm_sf2_priv *priv,
-						  int port,
-						  struct ethtool_rxnfc *nfc)
-{
-	u32 reg, ipv4_or_chain_id;
-	unsigned int queue_num;
-	int ret;
-
-	bcm_sf2_cfp_rule_addr_set(priv, nfc->fs.location);
-
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | ACT_POL_RAM);
-	if (ret)
-		return ret;
-
-	reg = core_readl(priv, CORE_ACT_POL_DATA0);
-
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | TCAM_SEL);
-	if (ret)
-		return ret;
-
-	/* Extract the destination port */
-	nfc->fs.ring_cookie = fls((reg >> DST_MAP_IB_SHIFT) &
-				  DST_MAP_IB_MASK) - 1;
-
-	/* There is no Port 6, so we compensate for that here */
-	if (nfc->fs.ring_cookie >= 6)
-		nfc->fs.ring_cookie++;
-	nfc->fs.ring_cookie *= SF2_NUM_EGRESS_QUEUES;
-
-	/* Extract the destination queue */
-	queue_num = (reg >> NEW_TC_SHIFT) & NEW_TC_MASK;
-	nfc->fs.ring_cookie += queue_num;
-
-	/* Extract the L3_FRAMING or CHAIN_ID */
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
-
-	/* With IPv6 rules this would contain a non-zero chain ID since
-	 * we reserve entry 0 and it cannot be used. So if we read 0 here
-	 * this means an IPv4 rule.
-	 */
-	ipv4_or_chain_id = (reg >> L3_FRAMING_SHIFT) & 0xff;
-	if (ipv4_or_chain_id == 0)
-		ret = bcm_sf2_cfp_ipv4_rule_get(priv, port, &nfc->fs);
-	else
-		ret = bcm_sf2_cfp_ipv6_rule_get(priv, port, &nfc->fs,
-						ipv4_or_chain_id);
-	if (ret)
-		return ret;
-
-	/* Read last to avoid next entry clobbering the results during search
-	 * operations
-	 */
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(7));
-	if (!(reg & 1 << port))
-		return -EINVAL;
-
-	bcm_sf2_invert_masks(&nfc->fs);
-
-	/* Put the TCAM size here */
-	nfc->data = bcm_sf2_cfp_rule_size(priv);
-
-	return 0;
-}
-
 static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
 				struct ethtool_rxnfc *nfc)
 {
-- 
cgit v1.2.3


From 80f8dea8767ef8fe357f1529fae0e6d8452b5fd2 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 6 Nov 2018 12:58:41 -0800
Subject: net: systemport: Restore Broadcom tag match filters upon resume

Some of the system suspend states that we support wipe out entirely the
HW contents. If we had a Wake-on-LAN filter programmed prior to going
into suspend, but we did not actually wake-up from Wake-on-LAN and
instead used a deeper suspend state, make sure we restore the CID number
that we need to match against.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 12 ++++++++++++
 drivers/net/ethernet/broadcom/bcmsysport.h |  1 +
 2 files changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 0e2d99c737e3..2e60dda32adc 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1068,6 +1068,7 @@ static void mpd_enable_set(struct bcm_sysport_priv *priv, bool enable)
 
 static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
 {
+	unsigned int index;
 	u32 reg;
 
 	/* Disable RXCHK, active filters and Broadcom tag matching */
@@ -1076,6 +1077,15 @@ static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
 		 RXCHK_BRCM_TAG_MATCH_SHIFT | RXCHK_EN | RXCHK_BRCM_TAG_EN);
 	rxchk_writel(priv, reg, RXCHK_CONTROL);
 
+	/* Make sure we restore correct CID index in case HW lost
+	 * its context during deep idle state
+	 */
+	for_each_set_bit(index, priv->filters, RXCHK_BRCM_TAG_MAX) {
+		rxchk_writel(priv, priv->filters_loc[index] <<
+			     RXCHK_BRCM_TAG_CID_SHIFT, RXCHK_BRCM_TAG(index));
+		rxchk_writel(priv, 0xff00ffff, RXCHK_BRCM_TAG_MASK(index));
+	}
+
 	/* Clear the MagicPacket detection logic */
 	mpd_enable_set(priv, false);
 
@@ -2189,6 +2199,7 @@ static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv,
 	rxchk_writel(priv, reg, RXCHK_BRCM_TAG(index));
 	rxchk_writel(priv, 0xff00ffff, RXCHK_BRCM_TAG_MASK(index));
 
+	priv->filters_loc[index] = nfc->fs.location;
 	set_bit(index, priv->filters);
 
 	return 0;
@@ -2208,6 +2219,7 @@ static int bcm_sysport_rule_del(struct bcm_sysport_priv *priv,
 	 * be taken care of during suspend time by bcm_sysport_suspend_to_wol
 	 */
 	clear_bit(index, priv->filters);
+	priv->filters_loc[index] = 0;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index a7a230884a87..7a0b7bfedd19 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -786,6 +786,7 @@ struct bcm_sysport_priv {
 	/* Ethtool */
 	u32			msg_enable;
 	DECLARE_BITMAP(filters, RXCHK_BRCM_TAG_MAX);
+	u32			filters_loc[RXCHK_BRCM_TAG_MAX];
 
 	struct bcm_sysport_stats64	stats64;
 
-- 
cgit v1.2.3


From c04a17d2a9ccf1eaba1c5a56f83e997540a70556 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 6 Nov 2018 15:15:16 -0800
Subject: net: dsa: bcm_sf2: Turn on PHY to allow successful registration

We are binding to the PHY using the SF2 slave MDIO bus that we create,
binding involves reading the PHY's MII_PHYSID1/2 which won't be possible
if the PHY is turned off. Temporarily turn it on/off for the bus probing
to succeeed. This fixes unbind/bind problems where the port connecting
to that PHY would be in error since it could not connect to it.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index d8b93043b789..aa4a1f5206f1 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1095,12 +1095,16 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	bcm_sf2_gphy_enable_set(priv->dev->ds, true);
+
 	ret = bcm_sf2_mdio_register(ds);
 	if (ret) {
 		pr_err("failed to register MDIO bus\n");
 		return ret;
 	}
 
+	bcm_sf2_gphy_enable_set(priv->dev->ds, false);
+
 	ret = bcm_sf2_cfp_rst(priv);
 	if (ret) {
 		pr_err("failed to reset CFP\n");
-- 
cgit v1.2.3


From 25c440704661c1e842516f9364c9cb022a44c5b9 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 6 Nov 2018 15:15:17 -0800
Subject: net: systemport: Simplify queue mapping logic

The use of a bitmap speeds up the finding of the first available queue
to which we could start establishing the mapping for, but we still have
to loop over all slave network devices to set them up. Simplify the
logic to have a single loop, and use the fact that a correctly
configured ring has inspect set to true. This will make things simpler
to unwind during device unregistration.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 17 +++++++++--------
 drivers/net/ethernet/broadcom/bcmsysport.h |  1 -
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 2e60dda32adc..a161d3282321 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2324,7 +2324,7 @@ static int bcm_sysport_map_queues(struct notifier_block *nb,
 	struct bcm_sysport_priv *priv;
 	struct net_device *slave_dev;
 	unsigned int num_tx_queues;
-	unsigned int q, start, port;
+	unsigned int q, qp, port;
 	struct net_device *dev;
 
 	priv = container_of(nb, struct bcm_sysport_priv, dsa_notifier);
@@ -2363,20 +2363,21 @@ static int bcm_sysport_map_queues(struct notifier_block *nb,
 
 	priv->per_port_num_tx_queues = num_tx_queues;
 
-	start = find_first_zero_bit(&priv->queue_bitmap, dev->num_tx_queues);
-	for (q = 0; q < num_tx_queues; q++) {
-		ring = &priv->tx_rings[q + start];
+	for (q = 0, qp = 0; q < dev->num_tx_queues && qp < num_tx_queues;
+	     q++) {
+		ring = &priv->tx_rings[q];
+
+		if (ring->inspect)
+			continue;
 
 		/* Just remember the mapping actual programming done
 		 * during bcm_sysport_init_tx_ring
 		 */
-		ring->switch_queue = q;
+		ring->switch_queue = qp;
 		ring->switch_port = port;
 		ring->inspect = true;
 		priv->ring_map[q + port * num_tx_queues] = ring;
-
-		/* Set all queues as being used now */
-		set_bit(q + start, &priv->queue_bitmap);
+		qp++;
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 7a0b7bfedd19..0887e6356649 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -796,7 +796,6 @@ struct bcm_sysport_priv {
 	/* map information between switch port queues and local queues */
 	struct notifier_block	dsa_notifier;
 	unsigned int		per_port_num_tx_queues;
-	unsigned long		queue_bitmap;
 	struct bcm_sysport_tx_ring *ring_map[DSA_MAX_PORTS * 8];
 
 };
-- 
cgit v1.2.3


From da106a140f9c6955bb98dfc5a08c0dac72656d5c Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 6 Nov 2018 15:15:18 -0800
Subject: net: systemport: Unmap queues upon DSA unregister event

Binding and unbinding the switch driver which creates the DSA slave
network devices for which we set-up inspection would lead to
undesireable effects since we were not clearing the port/queue mapping
to the SYSTEMPORT TX queue.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 56 ++++++++++++++++++++++++++----
 1 file changed, 50 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index a161d3282321..4574275ef445 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2383,17 +2383,61 @@ static int bcm_sysport_map_queues(struct notifier_block *nb,
 	return 0;
 }
 
+static int bcm_sysport_unmap_queues(struct notifier_block *nb,
+				    struct dsa_notifier_register_info *info)
+{
+	struct bcm_sysport_tx_ring *ring;
+	struct bcm_sysport_priv *priv;
+	struct net_device *slave_dev;
+	unsigned int num_tx_queues;
+	struct net_device *dev;
+	unsigned int q, port;
+
+	priv = container_of(nb, struct bcm_sysport_priv, dsa_notifier);
+	if (priv->netdev != info->master)
+		return 0;
+
+	dev = info->master;
+
+	if (dev->netdev_ops != &bcm_sysport_netdev_ops)
+		return 0;
+
+	port = info->port_number;
+	slave_dev = info->info.dev;
+
+	num_tx_queues = slave_dev->real_num_tx_queues;
+
+	for (q = 0; q < dev->num_tx_queues; q++) {
+		ring = &priv->tx_rings[q];
+
+		if (ring->switch_port != port)
+			continue;
+
+		if (!ring->inspect)
+			continue;
+
+		ring->inspect = false;
+		priv->ring_map[q + port * num_tx_queues] = NULL;
+	}
+
+	return 0;
+}
+
 static int bcm_sysport_dsa_notifier(struct notifier_block *nb,
 				    unsigned long event, void *ptr)
 {
-	struct dsa_notifier_register_info *info;
+	int ret = NOTIFY_DONE;
 
-	if (event != DSA_PORT_REGISTER)
-		return NOTIFY_DONE;
-
-	info = ptr;
+	switch (event) {
+	case DSA_PORT_REGISTER:
+		ret = bcm_sysport_map_queues(nb, ptr);
+		break;
+	case DSA_PORT_UNREGISTER:
+		ret = bcm_sysport_unmap_queues(nb, ptr);
+		break;
+	}
 
-	return notifier_from_errno(bcm_sysport_map_queues(nb, info));
+	return notifier_from_errno(ret);
 }
 
 #define REV_FMT	"v%2x.%02x"
-- 
cgit v1.2.3


From b86077207d0c08e181c7715bc75f50a3ad2fdf74 Mon Sep 17 00:00:00 2001
From: Lance Roy <ldr709@gmail.com>
Date: Tue, 2 Oct 2018 22:38:51 -0700
Subject: igbvf: Replace spin_is_locked() with lockdep

lockdep_assert_held() is better suited to checking locking requirements,
since it won't get confused when someone else holds the lock. This is
also a step towards possibly removing spin_is_locked().

Signed-off-by: Lance Roy <ldr709@gmail.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igbvf/mbx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igbvf/mbx.c b/drivers/net/ethernet/intel/igbvf/mbx.c
index 163e5838f7c2..a3cd7ac48d4b 100644
--- a/drivers/net/ethernet/intel/igbvf/mbx.c
+++ b/drivers/net/ethernet/intel/igbvf/mbx.c
@@ -241,7 +241,7 @@ static s32 e1000_write_mbx_vf(struct e1000_hw *hw, u32 *msg, u16 size)
 	s32 err;
 	u16 i;
 
-	WARN_ON_ONCE(!spin_is_locked(&hw->mbx_lock));
+	lockdep_assert_held(&hw->mbx_lock);
 
 	/* lock the mailbox to prevent pf/vf race condition */
 	err = e1000_obtain_mbx_lock_vf(hw);
@@ -279,7 +279,7 @@ static s32 e1000_read_mbx_vf(struct e1000_hw *hw, u32 *msg, u16 size)
 	s32 err;
 	u16 i;
 
-	WARN_ON_ONCE(!spin_is_locked(&hw->mbx_lock));
+	lockdep_assert_held(&hw->mbx_lock);
 
 	/* lock the mailbox to prevent pf/vf race condition */
 	err = e1000_obtain_mbx_lock_vf(hw);
-- 
cgit v1.2.3


From 0db4a47c05e6b5f7dda2a5d8b213ade5373afa49 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 4 Oct 2018 18:57:32 +0100
Subject: ixgbe: don't clear_bit on xdp_ring->state if xdp_ring is null

There is an earlier check to see if xdp_ring is null when configuring
the tx ring, so assuming that it can still be null, the clearing of
the xdp_ring->state currently could end up with a null pointer
dereference.  Fix this by only clearing the bit if xdp_ring is not null.

Detected by CoverityScan, CID#1473795 ("Dereference after null check")

Fixes: 024aa5800f32 ("ixgbe: added Rx/Tx ring disable/enable functions")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 113b38e0defb..aeda1834e66a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10517,7 +10517,8 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring)
 	ixgbe_configure_rx_ring(adapter, rx_ring);
 
 	clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state);
-	clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state);
+	if (xdp_ring)
+		clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state);
 }
 
 /**
-- 
cgit v1.2.3


From 7fa57ca443cffe81ce8416b57966bfb0370678a1 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Thu, 4 Oct 2018 16:28:52 -0700
Subject: ixgbe: allow IPsec Tx offload in VEPA mode

When it's possible that the PF might end up trying to send a
packet to one of its own VFs, we have to forbid IPsec offload
because the device drops the packets into a black hole.
See commit 47b6f50077e6 ("ixgbe: disallow IPsec Tx offload
when in SR-IOV mode") for more info.

This really is only necessary when the device is in the default
VEB mode.  If instead the device is running in VEPA mode,
the packets will go through the encryption engine and out the
MAC/PHY as normal, and get "hairpinned" as needed by the switch.

So let's not block IPsec offload when in VEPA mode.  To get
there with the ixgbe device, use the handy 'bridge' command:
	bridge link set dev eth1 hwmode vepa

Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index fd1b0546fd67..4d77f42e035c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -4,6 +4,7 @@
 #include "ixgbe.h"
 #include <net/xfrm.h>
 #include <crypto/aead.h>
+#include <linux/if_bridge.h>
 
 #define IXGBE_IPSEC_KEY_BITS  160
 static const char aes_gcm_name[] = "rfc4106(gcm(aes))";
@@ -693,7 +694,8 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs)
 	} else {
 		struct tx_sa tsa;
 
-		if (adapter->num_vfs)
+		if (adapter->num_vfs &&
+		    adapter->bridge_mode != BRIDGE_MODE_VEPA)
 			return -EOPNOTSUPP;
 
 		/* find the first unused index */
-- 
cgit v1.2.3


From 9fc145fcb5fbf2e10ad5e4b31a011b5cecb77b10 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 5 Oct 2018 09:33:55 -0700
Subject: ixgbevf: add support for software timestamps

Add a call to skb_tx_timestamp in the ixgbevf_tx_map function. This
enables software timestamping for packets sent over this device driver.
The call is placed just prior to when we notify hardware of the new
packet, in order to software timestamp as close as possible to when the
hardware will transmit.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 5e47ede7e832..196b890467b2 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4016,6 +4016,8 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring,
 	/* set the timestamp */
 	first->time_stamp = jiffies;
 
+	skb_tx_timestamp(skb);
+
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.  (Only applicable for weak-ordered
 	 * memory model archs, such as IA-64).
-- 
cgit v1.2.3


From a9e510589d7017ee4e82800d0a1d78a694772787 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 5 Oct 2018 09:33:56 -0700
Subject: intel-ethernet: software timestamp skbs as late as possible

Many of the Intel Ethernet drivers call skb_tx_timestamp() earlier than
necessary. Move the calls to this function to the latest point possible,
just prior to notifying hardware of the new Tx packet when we bump the
tail register.

This affects i40e, iavf, igb, igc, and ixgbe.

The e100, e1000, e1000e, fm10k, and ice drivers already call the
skb_tx_timestamp() function just prior to indicating the Tx packet to
hardware, so they do not need to be changed.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 4 ++--
 drivers/net/ethernet/intel/iavf/iavf_txrx.c   | 4 ++--
 drivers/net/ethernet/intel/igb/igb_main.c     | 4 ++--
 drivers/net/ethernet/intel/igc/igc_main.c     | 4 ++--
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++--
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index aef3c89ee79c..1384a5a006a4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3473,6 +3473,8 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	tx_desc->cmd_type_offset_bsz =
 			build_ctob(td_cmd, td_offset, size, td_tag);
 
+	skb_tx_timestamp(skb);
+
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.
 	 *
@@ -3652,8 +3654,6 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	if (tsyn)
 		tx_flags |= I40E_TX_FLAGS_TSYN;
 
-	skb_tx_timestamp(skb);
-
 	/* always enable CRC insertion offload */
 	td_cmd |= I40E_TX_DESC_CMD_ICRC;
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index fb9bfad96daf..3b1dc77ae368 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -2343,6 +2343,8 @@ static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb,
 	tx_desc->cmd_type_offset_bsz =
 			build_ctob(td_cmd, td_offset, size, td_tag);
 
+	skb_tx_timestamp(skb);
+
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.
 	 *
@@ -2461,8 +2463,6 @@ static netdev_tx_t iavf_xmit_frame_ring(struct sk_buff *skb,
 	if (tso < 0)
 		goto out_drop;
 
-	skb_tx_timestamp(skb);
-
 	/* always enable CRC insertion offload */
 	td_cmd |= IAVF_TX_DESC_CMD_ICRC;
 
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 5df88ad8ac81..4584ebc9e8fe 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6019,6 +6019,8 @@ static int igb_tx_map(struct igb_ring *tx_ring,
 	/* set the timestamp */
 	first->time_stamp = jiffies;
 
+	skb_tx_timestamp(skb);
+
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.  (Only applicable for weak-ordered
 	 * memory model archs, such as IA-64).
@@ -6147,8 +6149,6 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	else if (!tso)
 		igb_tx_csum(tx_ring, first);
 
-	skb_tx_timestamp(skb);
-
 	if (igb_tx_map(tx_ring, first, hdr_len))
 		goto cleanup_tx_tstamp;
 
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 9d85707e8a81..615a5fcd5a00 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -865,6 +865,8 @@ static int igc_tx_map(struct igc_ring *tx_ring,
 	/* set the timestamp */
 	first->time_stamp = jiffies;
 
+	skb_tx_timestamp(skb);
+
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.  (Only applicable for weak-ordered
 	 * memory model archs, such as IA-64).
@@ -959,8 +961,6 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 	first->bytecount = skb->len;
 	first->gso_segs = 1;
 
-	skb_tx_timestamp(skb);
-
 	/* record initial flags and protocol */
 	first->tx_flags = tx_flags;
 	first->protocol = protocol;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index aeda1834e66a..cfb83687c3d8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8269,6 +8269,8 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 	/* set the timestamp */
 	first->time_stamp = jiffies;
 
+	skb_tx_timestamp(skb);
+
 	/*
 	 * Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.  (Only applicable for weak-ordered
@@ -8646,8 +8648,6 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 		}
 	}
 
-	skb_tx_timestamp(skb);
-
 #ifdef CONFIG_PCI_IOV
 	/*
 	 * Use the l2switch_enable flag - would be false if the DMA
-- 
cgit v1.2.3


From 540a152da762a2360e0dac18e2eafff2775c4670 Mon Sep 17 00:00:00 2001
From: Todd Fujinaka <todd.fujinaka@intel.com>
Date: Wed, 10 Oct 2018 11:10:10 -0700
Subject: i40e/ixgbe/igb: fail on new WoL flag setting WAKE_MAGICSECURE

There's a new flag for setting WoL filters that is only
enabled on one manufacturer's NICs, and it's not ours. Fail
with EOPNOTSUPP.

Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c   | 3 ++-
 drivers/net/ethernet/intel/igb/igb_ethtool.c     | 2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 3 ++-
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 9f8464f80783..9c1211ad2c6b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -2377,7 +2377,8 @@ static int i40e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 		return -EOPNOTSUPP;
 
 	/* only magic packet is supported */
-	if (wol->wolopts && (wol->wolopts != WAKE_MAGIC))
+	if (wol->wolopts && (wol->wolopts != WAKE_MAGIC)
+			  | (wol->wolopts != WAKE_FILTER))
 		return -EOPNOTSUPP;
 
 	/* is this a new value? */
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 5acf3b743876..c57671068245 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -2113,7 +2113,7 @@ static int igb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 
-	if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE))
+	if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE | WAKE_FILTER))
 		return -EOPNOTSUPP;
 
 	if (!(adapter->flags & IGB_FLAG_WOL_SUPPORTED))
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 732b1e6ecc43..acba067cc15a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -2206,7 +2206,8 @@ static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
-	if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE))
+	if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE |
+			    WAKE_FILTER))
 		return -EOPNOTSUPP;
 
 	if (ixgbe_wol_exclusion(adapter, wol))
-- 
cgit v1.2.3


From dda458d28567d0bb99ad67180a72aaff2e0adc3b Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 19 Oct 2018 12:40:30 +0000
Subject: igc: Remove set but not used variables 'ctrl_ext, link_mode'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/intel/igc/igc_base.c: In function 'igc_init_phy_params_base':
drivers/net/ethernet/intel/igc/igc_base.c:240:6: warning:
 variable 'ctrl_ext' set but not used [-Wunused-but-set-variable]
  u32 ctrl_ext;

drivers/net/ethernet/intel/igc/igc_base.c: In function 'igc_get_invariants_base':
drivers/net/ethernet/intel/igc/igc_base.c:290:6: warning:
 variable 'link_mode' set but not used [-Wunused-but-set-variable]
  u32 link_mode = 0;

It never used since introduction in
commit c0071c7aa5fe ("igc: Add HW initialization code")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_base.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index 832da609d9a7..df40af759542 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -237,7 +237,6 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw)
 {
 	struct igc_phy_info *phy = &hw->phy;
 	s32 ret_val = 0;
-	u32 ctrl_ext;
 
 	if (hw->phy.media_type != igc_media_type_copper) {
 		phy->type = igc_phy_none;
@@ -247,8 +246,6 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw)
 	phy->autoneg_mask	= AUTONEG_ADVERTISE_SPEED_DEFAULT_2500;
 	phy->reset_delay_us	= 100;
 
-	ctrl_ext = rd32(IGC_CTRL_EXT);
-
 	/* set lan id */
 	hw->bus.func = (rd32(IGC_STATUS) & IGC_STATUS_FUNC_MASK) >>
 			IGC_STATUS_FUNC_SHIFT;
@@ -287,8 +284,6 @@ out:
 static s32 igc_get_invariants_base(struct igc_hw *hw)
 {
 	struct igc_mac_info *mac = &hw->mac;
-	u32 link_mode = 0;
-	u32 ctrl_ext = 0;
 	s32 ret_val = 0;
 
 	switch (hw->device_id) {
@@ -302,9 +297,6 @@ static s32 igc_get_invariants_base(struct igc_hw *hw)
 
 	hw->phy.media_type = igc_media_type_copper;
 
-	ctrl_ext = rd32(IGC_CTRL_EXT);
-	link_mode = ctrl_ext & IGC_CTRL_EXT_LINK_MODE_MASK;
-
 	/* mac initialization and operations */
 	ret_val = igc_init_mac_params_base(hw);
 	if (ret_val)
-- 
cgit v1.2.3


From 84cfa53740e137a7ead9aab26e1ad0704fe21caa Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 19 Oct 2018 12:48:11 +0000
Subject: igc: Remove set but not used variable 'pci_using_dac'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/intel/igc/igc_main.c: In function 'igc_probe':
drivers/net/ethernet/intel/igc/igc_main.c:3535:11: warning:
 variable 'pci_using_dac' set but not used [-Wunused-but-set-variable]

It never used since introduction in commit
d89f88419f99 ("igc: Add skeletal frame for Intel(R) 2.5G Ethernet Controller support")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 615a5fcd5a00..529c3e952621 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3532,19 +3532,16 @@ static int igc_probe(struct pci_dev *pdev,
 	struct net_device *netdev;
 	struct igc_hw *hw;
 	const struct igc_info *ei = igc_info_tbl[ent->driver_data];
-	int err, pci_using_dac;
+	int err;
 
 	err = pci_enable_device_mem(pdev);
 	if (err)
 		return err;
 
-	pci_using_dac = 0;
 	err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
 	if (!err) {
 		err = dma_set_coherent_mask(&pdev->dev,
 					    DMA_BIT_MASK(64));
-		if (!err)
-			pci_using_dac = 1;
 	} else {
 		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
-- 
cgit v1.2.3


From 14b21cec85858001b2134c0ac251fb8673d7ad67 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 19 Oct 2018 19:16:15 +0100
Subject: igc: fix error return handling from call to
 netif_set_real_num_tx_queues

The call to netif_set_real_num_tx_queues is not assigning the error
return to variable err even though the next line checks err for an
error.  Fix this by adding the missing err assignment.

Detected by CoverityScan, CID#1474551 ("Logically dead code")

Fixes: 3df25e4c1e66 ("igc: Add interrupt support")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 529c3e952621..f176540f5ed7 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3358,7 +3358,7 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 		goto err_req_irq;
 
 	/* Notify the stack of the actual queue counts. */
-	netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues);
+	err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues);
 	if (err)
 		goto err_set_queues;
 
-- 
cgit v1.2.3


From bb9089b668d65ac94f771e5ef6b2431c70697830 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 19 Oct 2018 22:57:47 +0300
Subject: igc: Tidy up some white space

I just cleaned up a couple small white space issues.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index f176540f5ed7..827eda044d97 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1108,7 +1108,7 @@ static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring,
 
 	/* update pointers within the skb to store the data */
 	skb_reserve(skb, IGC_SKB_PAD);
-	 __skb_put(skb, size);
+	__skb_put(skb, size);
 
 	/* update buffer offset */
 #if (PAGE_SIZE < 8192)
@@ -1160,9 +1160,9 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,
 				(va + headlen) - page_address(rx_buffer->page),
 				size, truesize);
 #if (PAGE_SIZE < 8192)
-	rx_buffer->page_offset ^= truesize;
+		rx_buffer->page_offset ^= truesize;
 #else
-	rx_buffer->page_offset += truesize;
+		rx_buffer->page_offset += truesize;
 #endif
 	} else {
 		rx_buffer->pagecnt_bias++;
@@ -1668,8 +1668,8 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 				tx_buffer->next_to_watch,
 				jiffies,
 				tx_buffer->next_to_watch->wb.status);
-				netif_stop_subqueue(tx_ring->netdev,
-						    tx_ring->queue_index);
+			netif_stop_subqueue(tx_ring->netdev,
+					    tx_ring->queue_index);
 
 			/* we are about to reset, no point in enabling stuff */
 			return true;
-- 
cgit v1.2.3


From e1f65b0d70e9e5c80e15105cd96fa00174d7c436 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Tue, 23 Oct 2018 14:37:39 +0200
Subject: e1000e: allow non-monotonic SYSTIM readings

It seems with some NICs supported by the e1000e driver a SYSTIM reading
may occasionally be few microseconds before the previous reading and if
enabled also pass e1000e_sanitize_systim() without reaching the maximum
number of rereads, even if the function is modified to check three
consecutive readings (i.e. it doesn't look like a double read error).
This causes an underflow in the timecounter and the PHC time jumps hours
ahead.

This was observed on 82574, I217 and I219. The fastest way to reproduce
it is to run a program that continuously calls the PTP_SYS_OFFSET ioctl
on the PHC.

Modify e1000e_phc_gettime() to use timecounter_cyc2time() instead of
timecounter_read() in order to allow non-monotonic SYSTIM readings and
prevent the PHC from jumping.

Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Acked-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e1000e/ptp.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 37c76945ad9b..e1f821edbc21 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -173,10 +173,14 @@ static int e1000e_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
 	struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter,
 						     ptp_clock_info);
 	unsigned long flags;
-	u64 ns;
+	u64 cycles, ns;
 
 	spin_lock_irqsave(&adapter->systim_lock, flags);
-	ns = timecounter_read(&adapter->tc);
+
+	/* Use timecounter_cyc2time() to allow non-monotonic SYSTIM readings */
+	cycles = adapter->cc.read(&adapter->cc);
+	ns = timecounter_cyc2time(&adapter->tc, cycles);
+
 	spin_unlock_irqrestore(&adapter->systim_lock, flags);
 
 	*ts = ns_to_timespec64(ns);
@@ -232,9 +236,12 @@ static void e1000e_systim_overflow_work(struct work_struct *work)
 						     systim_overflow_work.work);
 	struct e1000_hw *hw = &adapter->hw;
 	struct timespec64 ts;
+	u64 ns;
 
-	adapter->ptp_clock_info.gettime64(&adapter->ptp_clock_info, &ts);
+	/* Update the timecounter */
+	ns = timecounter_read(&adapter->tc);
 
+	ts = ns_to_timespec64(ns);
 	e_dbg("SYSTIM overflow check at %lld.%09lu\n",
 	      (long long) ts.tv_sec, ts.tv_nsec);
 
-- 
cgit v1.2.3


From 920664a8f79084df50033f0ff26238d7d32dcede Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Thu, 25 Oct 2018 10:06:18 +0300
Subject: igc: Clean up code

Address few community comments.
Remove unused code, will be added per demand.
Remove blank lines and unneeded includes.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h      |  9 ---------
 drivers/net/ethernet/intel/igc/igc_main.c | 15 ---------------
 2 files changed, 24 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index cdf18a5d9e08..3b00b109b34a 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -5,23 +5,14 @@
 #define _IGC_H_
 
 #include <linux/kobject.h>
-
 #include <linux/pci.h>
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
-
 #include <linux/ethtool.h>
-
 #include <linux/sctp.h>
 
 #define IGC_ERR(args...) pr_err("igc: " args)
 
-#define PFX "igc: "
-
-#include <linux/timecounter.h>
-#include <linux/net_tstamp.h>
-#include <linux/ptp_clock_kernel.h>
-
 #include "igc_hw.h"
 
 /* main */
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 827eda044d97..d002055c0623 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1699,20 +1699,6 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 	return !!budget;
 }
 
-/**
- * igc_ioctl - I/O control method
- * @netdev: network interface device structure
- * @ifreq: frequency
- * @cmd: command
- */
-static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
-	switch (cmd) {
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 /**
  * igc_up - Open the interface and prepare it to handle traffic
  * @adapter: board private structure
@@ -3445,7 +3431,6 @@ static const struct net_device_ops igc_netdev_ops = {
 	.ndo_set_mac_address	= igc_set_mac,
 	.ndo_change_mtu		= igc_change_mtu,
 	.ndo_get_stats		= igc_get_stats,
-	.ndo_do_ioctl		= igc_ioctl,
 };
 
 /* PCIe configuration access */
-- 
cgit v1.2.3


From 814da63c557726e60b06a206ec8c1123f176d392 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:07 +0800
Subject: net: hns3: use HNS3_NIC_STATE_INITED to indicate the initialization
 state of enet

Besides of module_init and module_exit, the process of reset will
also uninitialize and initialize the enet client. When reset process
fails with enet client uninitialized, the module_exit does not need
to uninitialize the enet client, otherwise it may cause double
uninitialization problem.

So we need the HNS3_NIC_STATE_INITED flag to indicate whether
the enet client is initialized.

Also HNS3_NIC_STATE_REINITING is previously unused, so change it to
HNS3_NIC_STATE_INITED.

Fixes: bb6b94a896d4 ("net: hns3: Add reset interface implementation in client")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 17 +++++++++++++++++
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h |  2 +-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 3f96aa30068e..d51469c6f759 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3397,6 +3397,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	/* MTU range: (ETH_MIN_MTU(kernel default) - 9706) */
 	netdev->max_mtu = HNS3_MAX_MTU - (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
 
+	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
+
 	return ret;
 
 out_reg_netdev_fail:
@@ -3423,6 +3425,11 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 	if (netdev->reg_state != NETREG_UNINITIALIZED)
 		unregister_netdev(netdev);
 
+	if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
+		netdev_warn(netdev, "already uninitialized\n");
+		goto out_netdev_free;
+	}
+
 	hns3_del_all_fd_rules(netdev, true);
 
 	hns3_force_clear_all_rx_ring(handle);
@@ -3443,6 +3450,7 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 
 	priv->ring_data = NULL;
 
+out_netdev_free:
 	free_netdev(netdev);
 }
 
@@ -3782,6 +3790,8 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 		priv->ring_data = NULL;
 	}
 
+	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
+
 	return ret;
 }
 
@@ -3792,6 +3802,11 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	int ret;
 
+	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
+		netdev_warn(netdev, "already uninitialized\n");
+		return 0;
+	}
+
 	hns3_force_clear_all_rx_ring(handle);
 
 	ret = hns3_nic_uninit_vector_data(priv);
@@ -3815,6 +3830,8 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 		hns3_del_all_fd_rules(netdev, false);
 	}
 
+	clear_bit(HNS3_NIC_STATE_INITED, &priv->state);
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index d3636d088aa3..7b759e424d54 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -15,7 +15,7 @@ extern const char hns3_driver_version[];
 enum hns3_nic_state {
 	HNS3_NIC_STATE_TESTING,
 	HNS3_NIC_STATE_RESETTING,
-	HNS3_NIC_STATE_REINITING,
+	HNS3_NIC_STATE_INITED,
 	HNS3_NIC_STATE_DOWN,
 	HNS3_NIC_STATE_DISABLED,
 	HNS3_NIC_STATE_REMOVING,
-- 
cgit v1.2.3


From 720bd5837e3721f553a896a00da4a99ea12f0551 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:08 +0800
Subject: net: hns3: add set_default_reset_request in the hnae3_ae_ops

Currently, when reset_event is called because of tx timeout, it will
upgrade the reset level (For PF, HNAE3_FUNC_RESET -> HNAE3_CORE_RESET
-> HNAE3_GLOBAL_RESET) if the time between the new reset and last reset
is within 20 secs, or restore the reset level to HNAE3_FUNC_RESET if
the time between the new reset and last reset is over 20 secs.

There is requirement that the caller needs to decide the reset level
when triggering a reset, for example, RAS recovery. So this patch
adds the set_default_reset_request to meet this requirement.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  2 ++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 13 ++++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  1 +
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 29 +++++++++++++++++++++-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  1 +
 5 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 055b40606dbc..7deab9270d16 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -403,6 +403,8 @@ struct hnae3_ae_ops {
 				  u16 vlan, u8 qos, __be16 proto);
 	int (*enable_hw_strip_rxvtag)(struct hnae3_handle *handle, bool enable);
 	void (*reset_event)(struct pci_dev *pdev, struct hnae3_handle *handle);
+	void (*set_default_reset_request)(struct hnae3_ae_dev *ae_dev,
+					  enum hnae3_reset_type rst_type);
 	void (*get_channels)(struct hnae3_handle *handle,
 			     struct ethtool_channels *ch);
 	void (*get_tqps_and_rss_info)(struct hnae3_handle *h,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index ffdd96020860..5e6006b6ed1a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2517,6 +2517,10 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
 
 	if (time_before(jiffies, (handle->last_reset_time + 3 * HZ)))
 		return;
+	else if (hdev->default_reset_request)
+		handle->reset_level =
+			hclge_get_reset_level(hdev,
+					      &hdev->default_reset_request);
 	else if (time_after(jiffies, (handle->last_reset_time + 4 * 5 * HZ)))
 		handle->reset_level = HNAE3_FUNC_RESET;
 
@@ -2531,6 +2535,14 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
 		handle->reset_level++;
 }
 
+static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
+					enum hnae3_reset_type rst_type)
+{
+	struct hclge_dev *hdev = ae_dev->priv;
+
+	set_bit(rst_type, &hdev->default_reset_request);
+}
+
 static void hclge_reset_subtask(struct hclge_dev *hdev)
 {
 	/* check if there is any ongoing reset in the hardware. This status can
@@ -7321,6 +7333,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_vf_vlan_filter = hclge_set_vf_vlan_filter,
 	.enable_hw_strip_rxvtag = hclge_en_hw_strip_rxvtag,
 	.reset_event = hclge_reset_event,
+	.set_default_reset_request = hclge_set_def_reset_request,
 	.get_tqps_and_rss_info = hclge_get_tqps_and_rss_info,
 	.set_channels = hclge_set_channels,
 	.get_channels = hclge_get_channels,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 0d9215404269..7cfb61ebb92e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -595,6 +595,7 @@ struct hclge_dev {
 	unsigned long state;
 
 	enum hnae3_reset_type reset_type;
+	unsigned long default_reset_request;
 	unsigned long reset_request;	/* reset has been requested */
 	unsigned long reset_pending;	/* client rst is pending to be served */
 	u32 fw_version;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 085edb945389..42982fc2b5d7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1219,6 +1219,19 @@ static int hclgevf_do_reset(struct hclgevf_dev *hdev)
 	return status;
 }
 
+static enum hnae3_reset_type hclgevf_get_reset_level(struct hclgevf_dev *hdev,
+						     unsigned long *addr)
+{
+	enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
+
+	if (test_bit(HNAE3_VF_RESET, addr)) {
+		rst_level = HNAE3_VF_RESET;
+		clear_bit(HNAE3_VF_RESET, addr);
+	}
+
+	return rst_level;
+}
+
 static void hclgevf_reset_event(struct pci_dev *pdev,
 				struct hnae3_handle *handle)
 {
@@ -1226,7 +1239,12 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
 
 	dev_info(&hdev->pdev->dev, "received reset request from VF enet\n");
 
-	handle->reset_level = HNAE3_VF_RESET;
+	if (!hdev->default_reset_request)
+		handle->reset_level =
+			hclgevf_get_reset_level(hdev,
+						&hdev->default_reset_request);
+	else
+		handle->reset_level = HNAE3_VF_RESET;
 
 	/* reset of this VF requested */
 	set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state);
@@ -1235,6 +1253,14 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
 	handle->last_reset_time = jiffies;
 }
 
+static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
+					  enum hnae3_reset_type rst_type)
+{
+	struct hclgevf_dev *hdev = ae_dev->priv;
+
+	set_bit(rst_type, &hdev->default_reset_request);
+}
+
 static u32 hclgevf_get_fw_version(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
@@ -2193,6 +2219,7 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.set_vlan_filter = hclgevf_set_vlan_filter,
 	.enable_hw_strip_rxvtag = hclgevf_en_hw_strip_rxvtag,
 	.reset_event = hclgevf_reset_event,
+	.set_default_reset_request = hclgevf_set_def_reset_request,
 	.get_channels = hclgevf_get_channels,
 	.get_tqps_and_rss_info = hclgevf_get_tqps_and_rss_info,
 	.get_status = hclgevf_get_status,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index aed241e8ffab..6b2fd5a0326f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -145,6 +145,7 @@ struct hclgevf_dev {
 	struct hclgevf_misc_vector misc_vector;
 	struct hclgevf_rss_cfg rss_cfg;
 	unsigned long state;
+	unsigned long default_reset_request;
 
 #define HCLGEVF_RESET_REQUESTED		0
 #define HCLGEVF_RESET_PENDING		1
-- 
cgit v1.2.3


From 4d60291b6b53afd246a57817fdae0c61a4655182 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:09 +0800
Subject: net: hns3: provide some interface & information for the client

The client needs to know if the hardware is resetting when
loading or unloading itself, because client may abort the loading
process or wait for the reset process to finish when unloading
if hardware is resetting.

So this patch provides these interfaces to do it.
1. get_hw_reset_stat, the reset status of hardware.
2. ae_dev_resetting, whether reset task is scheduling.
3. ae_dev_reset_cnt, how many reset has been done.

Also, the RoCE client needs some field in the hnae3_roce_private_info
to save its state, and process_hw_error interface in the
hnae3_client_ops to process hardware errors.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        | 12 +++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 29 ++++++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  1 +
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 25 +++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  1 +
 5 files changed, 68 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 7deab9270d16..f57034d1654c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -162,6 +162,7 @@ struct hnae3_client_ops {
 	int (*setup_tc)(struct hnae3_handle *handle, u8 tc);
 	int (*reset_notify)(struct hnae3_handle *handle,
 			    enum hnae3_reset_notify_type type);
+	enum hnae3_reset_type (*process_hw_error)(struct hnae3_handle *handle);
 };
 
 #define HNAE3_CLIENT_NAME_LENGTH 16
@@ -432,6 +433,9 @@ struct hnae3_ae_ops {
 	int (*restore_fd_rules)(struct hnae3_handle *handle);
 	void (*enable_fd)(struct hnae3_handle *handle, bool enable);
 	pci_ers_result_t (*process_hw_error)(struct hnae3_ae_dev *ae_dev);
+	bool (*get_hw_reset_stat)(struct hnae3_handle *handle);
+	bool (*ae_dev_resetting)(struct hnae3_handle *handle);
+	unsigned long (*ae_dev_reset_cnt)(struct hnae3_handle *handle);
 };
 
 struct hnae3_dcb_ops {
@@ -490,6 +494,14 @@ struct hnae3_roce_private_info {
 	void __iomem *roce_io_base;
 	int base_vector;
 	int num_vectors;
+
+	/* The below attributes defined for RoCE client, hnae3 gives
+	 * initial values to them, and RoCE client can modify and use
+	 * them.
+	 */
+	unsigned long reset_state;
+	unsigned long instance_state;
+	unsigned long state;
 };
 
 struct hnae3_unic_private_info {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 5e6006b6ed1a..b6695424805b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2466,6 +2466,7 @@ static void hclge_reset(struct hclge_dev *hdev)
 	 * know if device is undergoing reset
 	 */
 	ae_dev->reset_type = hdev->reset_type;
+	hdev->reset_count++;
 	/* perform reset of the stack & ae device for a client */
 	handle = &hdev->vport[0].nic;
 	rtnl_lock();
@@ -4604,6 +4605,31 @@ static int hclge_get_all_rules(struct hnae3_handle *handle,
 	return 0;
 }
 
+static bool hclge_get_hw_reset_stat(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	return hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG) ||
+	       hclge_read_dev(&hdev->hw, HCLGE_FUN_RST_ING);
+}
+
+static bool hclge_ae_dev_resetting(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	return test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
+}
+
+static unsigned long hclge_ae_dev_reset_cnt(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	return hdev->reset_count;
+}
+
 static void hclge_enable_fd(struct hnae3_handle *handle, bool enable)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
@@ -7350,6 +7376,9 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.restore_fd_rules = hclge_restore_fd_entries,
 	.enable_fd = hclge_enable_fd,
 	.process_hw_error = hclge_process_ras_hw_error,
+	.get_hw_reset_stat = hclge_get_hw_reset_stat,
+	.ae_dev_resetting = hclge_ae_dev_resetting,
+	.ae_dev_reset_cnt = hclge_ae_dev_reset_cnt,
 };
 
 static struct hnae3_ae_algo ae_algo = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 7cfb61ebb92e..b6a17f56c8d8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -598,6 +598,7 @@ struct hclge_dev {
 	unsigned long default_reset_request;
 	unsigned long reset_request;	/* reset has been requested */
 	unsigned long reset_pending;	/* client rst is pending to be served */
+	unsigned long reset_count;	/* the number of reset has been done */
 	u32 fw_version;
 	u16 num_vmdq_vport;		/* Num vmdq vport this PF has set up */
 	u16 num_tqps;			/* Num task queue pairs of this PF */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 42982fc2b5d7..517204bbf0b7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1165,6 +1165,7 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
 {
 	int ret;
 
+	hdev->reset_count++;
 	rtnl_lock();
 
 	/* bring down the nic to stop any ongoing TX/RX */
@@ -2185,6 +2186,27 @@ static void hclgevf_get_media_type(struct hnae3_handle *handle,
 		*media_type = hdev->hw.mac.media_type;
 }
 
+static bool hclgevf_get_hw_reset_stat(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return !!hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
+}
+
+static bool hclgevf_ae_dev_resetting(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
+}
+
+static unsigned long hclgevf_ae_dev_reset_cnt(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return hdev->reset_count;
+}
+
 static const struct hnae3_ae_ops hclgevf_ops = {
 	.init_ae_dev = hclgevf_init_ae_dev,
 	.uninit_ae_dev = hclgevf_uninit_ae_dev,
@@ -2225,6 +2247,9 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.get_status = hclgevf_get_status,
 	.get_ksettings_an_result = hclgevf_get_ksettings_an_result,
 	.get_media_type = hclgevf_get_media_type,
+	.get_hw_reset_stat = hclgevf_get_hw_reset_stat,
+	.ae_dev_resetting = hclgevf_ae_dev_resetting,
+	.ae_dev_reset_cnt = hclgevf_ae_dev_reset_cnt,
 };
 
 static struct hnae3_ae_algo ae_algovf = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 6b2fd5a0326f..ffb8c7768b88 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -150,6 +150,7 @@ struct hclgevf_dev {
 #define HCLGEVF_RESET_REQUESTED		0
 #define HCLGEVF_RESET_PENDING		1
 	unsigned long reset_state;	/* requested, pending */
+	unsigned long reset_count;	/* the number of reset has been done */
 	u32 reset_attempts;
 
 	u32 fw_version;
-- 
cgit v1.2.3


From 7edff5339a4a7515b5c4b72338c679c5eb402923 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:10 +0800
Subject: net: hns3: adjust the location of clearing the table when doing reset

When doing a function reset, the hardware table should be cleared
before the hardware reset. In current code, this clearing is done
in hns3_reset_notify_uninit_enet, but it is too late, because
the hardware reset is already done, hns3_reset_notify_down_enet
is more suitable to do that.

Fixes: bb6b94a896d4 ("net: hns3: Add reset interface implementation in client")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index d51469c6f759..75e3e79fa695 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3716,9 +3716,19 @@ static void hns3_restore_coal(struct hns3_nic_priv *priv)
 
 static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct net_device *ndev = kinfo->netdev;
 
+	/* it is cumbersome for hardware to pick-and-choose entries for deletion
+	 * from table space. Hence, for function reset software intervention is
+	 * required to delete the entries
+	 */
+	if (hns3_dev_ongoing_func_reset(ae_dev)) {
+		hns3_remove_hw_addr(ndev);
+		hns3_del_all_fd_rules(ndev, false);
+	}
+
 	if (!netif_running(ndev))
 		return 0;
 
@@ -3797,7 +3807,6 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 
 static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	struct net_device *netdev = handle->kinfo.netdev;
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	int ret;
@@ -3821,15 +3830,6 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 	if (ret)
 		netdev_err(netdev, "uninit ring error\n");
 
-	/* it is cumbersome for hardware to pick-and-choose entries for deletion
-	 * from table space. Hence, for function reset software intervention is
-	 * required to delete the entries
-	 */
-	if (hns3_dev_ongoing_func_reset(ae_dev)) {
-		hns3_remove_hw_addr(netdev);
-		hns3_del_all_fd_rules(netdev, false);
-	}
-
 	clear_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
 	return ret;
-- 
cgit v1.2.3


From 8df0fa91682c86403173f0813a615efb46e8be42 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:11 +0800
Subject: net: hns3: enable/disable ring in the enet while doing UP/DOWN

While hardware gets into reset status, the firmware will not respond to
driver's command request, which may cause ring not disabled problem
during reset process.

So this patch uses register instead of command to enable/disable the ring
in the enet while doing UP/DOWN operation.

Also, HNS3_RING_RX_VM_REG is previously unused, so change it to the
correct meaning, and add a wrapper function for readl().

Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 30 +++++++++++++++++++
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    | 12 +++++++-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    |  8 -----
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 35 ----------------------
 4 files changed, 41 insertions(+), 44 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 75e3e79fa695..e4cf3247c0ac 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -312,6 +312,24 @@ static u16 hns3_get_max_available_channels(struct hnae3_handle *h)
 	return min_t(u16, rss_size, max_rss_size);
 }
 
+static void hns3_tqp_enable(struct hnae3_queue *tqp)
+{
+	u32 rcb_reg;
+
+	rcb_reg = hns3_read_dev(tqp, HNS3_RING_EN_REG);
+	rcb_reg |= BIT(HNS3_RING_EN_B);
+	hns3_write_dev(tqp, HNS3_RING_EN_REG, rcb_reg);
+}
+
+static void hns3_tqp_disable(struct hnae3_queue *tqp)
+{
+	u32 rcb_reg;
+
+	rcb_reg = hns3_read_dev(tqp, HNS3_RING_EN_REG);
+	rcb_reg &= ~BIT(HNS3_RING_EN_B);
+	hns3_write_dev(tqp, HNS3_RING_EN_REG, rcb_reg);
+}
+
 static int hns3_nic_net_up(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -334,6 +352,10 @@ static int hns3_nic_net_up(struct net_device *netdev)
 	for (i = 0; i < priv->vector_num; i++)
 		hns3_vector_enable(&priv->tqp_vector[i]);
 
+	/* enable rcb */
+	for (j = 0; j < h->kinfo.num_tqps; j++)
+		hns3_tqp_enable(h->kinfo.tqp[j]);
+
 	/* start the ae_dev */
 	ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0;
 	if (ret)
@@ -344,6 +366,9 @@ static int hns3_nic_net_up(struct net_device *netdev)
 	return 0;
 
 out_start_err:
+	while (j--)
+		hns3_tqp_disable(h->kinfo.tqp[j]);
+
 	for (j = i - 1; j >= 0; j--)
 		hns3_vector_disable(&priv->tqp_vector[j]);
 
@@ -385,6 +410,7 @@ static int hns3_nic_net_open(struct net_device *netdev)
 static void hns3_nic_net_down(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	const struct hnae3_ae_ops *ops;
 	int i;
 
@@ -395,6 +421,10 @@ static void hns3_nic_net_down(struct net_device *netdev)
 	for (i = 0; i < priv->vector_num; i++)
 		hns3_vector_disable(&priv->tqp_vector[i]);
 
+	/* disable rcb */
+	for (i = 0; i < h->kinfo.num_tqps; i++)
+		hns3_tqp_disable(h->kinfo.tqp[i]);
+
 	/* stop ae_dev */
 	ops = priv->ae_handle->ae_algo->ops;
 	if (ops->stop)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 7b759e424d54..3e9db7356cf2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -47,7 +47,7 @@ enum hns3_nic_state {
 #define HNS3_RING_PREFETCH_EN_REG		0x0007C
 #define HNS3_RING_CFG_VF_NUM_REG		0x00080
 #define HNS3_RING_ASID_REG			0x0008C
-#define HNS3_RING_RX_VM_REG			0x00090
+#define HNS3_RING_EN_REG			0x00090
 #define HNS3_RING_T0_BE_RST			0x00094
 #define HNS3_RING_COULD_BE_RST			0x00098
 #define HNS3_RING_WRR_WEIGHT_REG		0x0009c
@@ -194,6 +194,8 @@ enum hns3_nic_state {
 #define HNS3_VECTOR_RL_OFFSET			0x900
 #define HNS3_VECTOR_RL_EN_B			6
 
+#define HNS3_RING_EN_B				0
+
 enum hns3_pkt_l3t_type {
 	HNS3_L3T_NONE,
 	HNS3_L3T_IPV6,
@@ -577,6 +579,11 @@ static inline int is_ring_empty(struct hns3_enet_ring *ring)
 	return ring->next_to_use == ring->next_to_clean;
 }
 
+static inline u32 hns3_read_reg(void __iomem *base, u32 reg)
+{
+	return readl(base + reg);
+}
+
 static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 {
 	u8 __iomem *reg_addr = READ_ONCE(base);
@@ -589,6 +596,9 @@ static inline bool hns3_dev_ongoing_func_reset(struct hnae3_ae_dev *ae_dev)
 	return (ae_dev && (ae_dev->reset_type == HNAE3_FUNC_RESET));
 }
 
+#define hns3_read_dev(a, reg) \
+	hns3_read_reg((a)->io_base, (reg))
+
 #define hns3_write_dev(a, reg, value) \
 	hns3_write_reg((a)->io_base, (reg), (value))
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b6695424805b..b784db067290 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -4843,10 +4843,6 @@ static int hclge_ae_start(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	int i;
-
-	for (i = 0; i < vport->alloc_tqps; i++)
-		hclge_tqp_enable(hdev, i, 0, true);
 
 	/* mac enable */
 	hclge_cfg_mac_mode(hdev, true);
@@ -4866,7 +4862,6 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	int i;
 
 	set_bit(HCLGE_STATE_DOWN, &hdev->state);
 
@@ -4879,9 +4874,6 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 		return;
 	}
 
-	for (i = 0; i < vport->alloc_tqps; i++)
-		hclge_tqp_enable(hdev, i, 0, false);
-
 	/* Mac disable */
 	hclge_cfg_mac_mode(hdev, false);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 517204bbf0b7..7531bdde02a7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -956,13 +956,6 @@ static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, int tqp_id,
 	return status;
 }
 
-static int hclgevf_get_queue_id(struct hnae3_queue *queue)
-{
-	struct hclgevf_tqp *tqp = container_of(queue, struct hclgevf_tqp, q);
-
-	return tqp->index;
-}
-
 static void hclgevf_reset_tqp_stats(struct hnae3_handle *handle)
 {
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
@@ -1593,21 +1586,7 @@ static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
 
 static int hclgevf_ae_start(struct hnae3_handle *handle)
 {
-	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	int i, queue_id;
-
-	for (i = 0; i < kinfo->num_tqps; i++) {
-		/* ring enable */
-		queue_id = hclgevf_get_queue_id(kinfo->tqp[i]);
-		if (queue_id < 0) {
-			dev_warn(&hdev->pdev->dev,
-				 "Get invalid queue id, ignore it\n");
-			continue;
-		}
-
-		hclgevf_tqp_enable(hdev, queue_id, 0, true);
-	}
 
 	/* reset tqp stats */
 	hclgevf_reset_tqp_stats(handle);
@@ -1622,24 +1601,10 @@ static int hclgevf_ae_start(struct hnae3_handle *handle)
 
 static void hclgevf_ae_stop(struct hnae3_handle *handle)
 {
-	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	int i, queue_id;
 
 	set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
 
-	for (i = 0; i < kinfo->num_tqps; i++) {
-		/* Ring disable */
-		queue_id = hclgevf_get_queue_id(kinfo->tqp[i]);
-		if (queue_id < 0) {
-			dev_warn(&hdev->pdev->dev,
-				 "Get invalid queue id, ignore it\n");
-			continue;
-		}
-
-		hclgevf_tqp_enable(hdev, queue_id, 0, false);
-	}
-
 	/* reset tqp stats */
 	hclgevf_reset_tqp_stats(handle);
 	del_timer_sync(&hdev->service_timer);
-- 
cgit v1.2.3


From 257e4f29946ab8e257ee9bfbc35e680726298571 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:12 +0800
Subject: net: hns3: use HNS3_NIC_STATE_RESETTING to indicate resetting

While hclge is going to reset, it will notify its client with
HNAE3_DOWN_CLIENT, so this client should get into a resetting
status from this moment, other operations from the stack need to
be blocked as well. And when the reset is finished, the client
will be notified with HNAE3_UP_CLIENT, so this is the end of
the resetting status.

This patch uses HNS3_NIC_STATE_RESETTING flag to implement that,
and adds hns3_nic_resetting() to indicate which operation is not
allowed.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c   | 12 ++++++++++++
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 10 ++++++++++
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    |  7 +++++++
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 19 +++++++++++++++++++
 4 files changed, 48 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
index ea5f8a84070d..b6fabbbdfd5b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
@@ -9,6 +9,9 @@ int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
+	if (hns3_nic_resetting(ndev))
+		return -EBUSY;
+
 	if (h->kinfo.dcb_ops->ieee_getets)
 		return h->kinfo.dcb_ops->ieee_getets(h, ets);
 
@@ -20,6 +23,9 @@ int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
+	if (hns3_nic_resetting(ndev))
+		return -EBUSY;
+
 	if (h->kinfo.dcb_ops->ieee_setets)
 		return h->kinfo.dcb_ops->ieee_setets(h, ets);
 
@@ -31,6 +37,9 @@ int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
+	if (hns3_nic_resetting(ndev))
+		return -EBUSY;
+
 	if (h->kinfo.dcb_ops->ieee_getpfc)
 		return h->kinfo.dcb_ops->ieee_getpfc(h, pfc);
 
@@ -42,6 +51,9 @@ int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
+	if (hns3_nic_resetting(ndev))
+		return -EBUSY;
+
 	if (h->kinfo.dcb_ops->ieee_setpfc)
 		return h->kinfo.dcb_ops->ieee_setpfc(h, pfc);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index e4cf3247c0ac..d573f5fc9575 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -384,6 +384,9 @@ static int hns3_nic_net_open(struct net_device *netdev)
 	struct hnae3_knic_private_info *kinfo;
 	int i, ret;
 
+	if (hns3_nic_resetting(netdev))
+		return -EBUSY;
+
 	netif_carrier_off(netdev);
 
 	ret = hns3_nic_set_real_num_queue(netdev);
@@ -3749,6 +3752,10 @@ static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct net_device *ndev = kinfo->netdev;
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+
+	if (test_and_set_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
+		return 0;
 
 	/* it is cumbersome for hardware to pick-and-choose entries for deletion
 	 * from table space. Hence, for function reset software intervention is
@@ -3768,6 +3775,7 @@ static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
 static int hns3_reset_notify_up_enet(struct hnae3_handle *handle)
 {
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+	struct hns3_nic_priv *priv = netdev_priv(kinfo->netdev);
 	int ret = 0;
 
 	if (netif_running(kinfo->netdev)) {
@@ -3780,6 +3788,8 @@ static int hns3_reset_notify_up_enet(struct hnae3_handle *handle)
 		handle->last_reset_time = jiffies;
 	}
 
+	clear_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 3e9db7356cf2..cfd6a7109691 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -599,6 +599,13 @@ static inline bool hns3_dev_ongoing_func_reset(struct hnae3_ae_dev *ae_dev)
 #define hns3_read_dev(a, reg) \
 	hns3_read_reg((a)->io_base, (reg))
 
+static inline bool hns3_nic_resetting(struct net_device *netdev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+	return test_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
+}
+
 #define hns3_write_dev(a, reg, value) \
 	hns3_write_reg((a)->io_base, (reg), (value))
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index a4762c2b8ba1..4563638367ac 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -291,6 +291,11 @@ static void hns3_self_test(struct net_device *ndev,
 	int test_index = 0;
 	u32 i;
 
+	if (hns3_nic_resetting(ndev)) {
+		netdev_err(ndev, "dev resetting!");
+		return;
+	}
+
 	/* Only do offline selftest, or pass by default */
 	if (eth_test->flags != ETH_TEST_FL_OFFLINE)
 		return;
@@ -530,6 +535,11 @@ static void hns3_get_ringparam(struct net_device *netdev,
 	struct hnae3_handle *h = priv->ae_handle;
 	int queue_num = h->kinfo.num_tqps;
 
+	if (hns3_nic_resetting(netdev)) {
+		netdev_err(netdev, "dev resetting!");
+		return;
+	}
+
 	param->tx_max_pending = HNS3_RING_MAX_PENDING;
 	param->rx_max_pending = HNS3_RING_MAX_PENDING;
 
@@ -760,6 +770,9 @@ static int hns3_set_ringparam(struct net_device *ndev,
 	u32 old_desc_num, new_desc_num;
 	int ret;
 
+	if (hns3_nic_resetting(ndev))
+		return -EBUSY;
+
 	if (param->rx_mini_pending || param->rx_jumbo_pending)
 		return -EINVAL;
 
@@ -872,6 +885,9 @@ static int hns3_get_coalesce_per_queue(struct net_device *netdev, u32 queue,
 	struct hnae3_handle *h = priv->ae_handle;
 	u16 queue_num = h->kinfo.num_tqps;
 
+	if (hns3_nic_resetting(netdev))
+		return -EBUSY;
+
 	if (queue >= queue_num) {
 		netdev_err(netdev,
 			   "Invalid queue value %d! Queue max id=%d\n",
@@ -1033,6 +1049,9 @@ static int hns3_set_coalesce(struct net_device *netdev,
 	int ret;
 	int i;
 
+	if (hns3_nic_resetting(netdev))
+		return -EBUSY;
+
 	ret = hns3_check_coalesce_para(netdev, cmd);
 	if (ret)
 		return ret;
-- 
cgit v1.2.3


From 7cea834d942c2d47ebb81fba0e44d2ce6172c0ae Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:13 +0800
Subject: net: hns3: ignore new coming low-level reset while doing high-level
 reset

When processing a higher level reset, the pending lower level reset
does not have to be processed anymore, because the higher level
reset is the superset of the lower level reset.

Therefore, when processing an higher level reset, the request of
lower level reset needs to be cleared.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 27 +++++++++++++---------
 1 file changed, 16 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b784db067290..62022d552f5d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2414,20 +2414,25 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hclge_dev *hdev,
 	enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
 
 	/* return the highest priority reset level amongst all */
-	if (test_bit(HNAE3_GLOBAL_RESET, addr))
+	if (test_bit(HNAE3_IMP_RESET, addr)) {
+		rst_level = HNAE3_IMP_RESET;
+		clear_bit(HNAE3_IMP_RESET, addr);
+		clear_bit(HNAE3_GLOBAL_RESET, addr);
+		clear_bit(HNAE3_CORE_RESET, addr);
+		clear_bit(HNAE3_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_GLOBAL_RESET, addr)) {
 		rst_level = HNAE3_GLOBAL_RESET;
-	else if (test_bit(HNAE3_CORE_RESET, addr))
+		clear_bit(HNAE3_GLOBAL_RESET, addr);
+		clear_bit(HNAE3_CORE_RESET, addr);
+		clear_bit(HNAE3_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_CORE_RESET, addr)) {
 		rst_level = HNAE3_CORE_RESET;
-	else if (test_bit(HNAE3_IMP_RESET, addr))
-		rst_level = HNAE3_IMP_RESET;
-	else if (test_bit(HNAE3_FUNC_RESET, addr))
+		clear_bit(HNAE3_CORE_RESET, addr);
+		clear_bit(HNAE3_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_FUNC_RESET, addr)) {
 		rst_level = HNAE3_FUNC_RESET;
-
-	/* now, clear all other resets */
-	clear_bit(HNAE3_GLOBAL_RESET, addr);
-	clear_bit(HNAE3_CORE_RESET, addr);
-	clear_bit(HNAE3_IMP_RESET, addr);
-	clear_bit(HNAE3_FUNC_RESET, addr);
+		clear_bit(HNAE3_FUNC_RESET, addr);
+	}
 
 	return rst_level;
 }
-- 
cgit v1.2.3


From 0742ed7c240ceadc4472ab5a80bcb2a5f05e7ff8 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:14 +0800
Subject: net: hns3: move some reset information from hnae3_handle into
 hclge_dev/hclgevf_dev

Saving reset related information in the hclge_dev/hclgevf_dev
structure is more suitable than the hnae3_handle, since hardware
related information is kept in these two structure.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  3 ---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 16 +++------------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 23 +++++++++++-----------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  2 ++
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 10 ++++++----
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  6 ++++--
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c   |  2 +-
 7 files changed, 28 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index f57034d1654c..5b3b10479cd4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -534,9 +534,6 @@ struct hnae3_handle {
 	struct hnae3_ae_algo *ae_algo;  /* the class who provides this handle */
 	u64 flags; /* Indicate the capabilities for this handle*/
 
-	unsigned long last_reset_time;
-	enum hnae3_reset_type reset_level;
-
 	union {
 		struct net_device *netdev; /* first member */
 		struct hnae3_knic_private_info kinfo;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index d573f5fc9575..183fd8344b80 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -379,7 +379,6 @@ out_start_err:
 
 static int hns3_nic_net_open(struct net_device *netdev)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct hnae3_knic_private_info *kinfo;
 	int i, ret;
@@ -406,7 +405,6 @@ static int hns3_nic_net_open(struct net_device *netdev)
 				       kinfo->prio_tc[i]);
 	}
 
-	priv->ae_handle->last_reset_time = jiffies;
 	return 0;
 }
 
@@ -1648,10 +1646,9 @@ static void hns3_nic_net_timeout(struct net_device *ndev)
 
 	priv->tx_timeout_count++;
 
-	if (time_before(jiffies, (h->last_reset_time + ndev->watchdog_timeo)))
-		return;
-
-	/* request the reset */
+	/* request the reset, and let the hclge to determine
+	 * which reset level should be done
+	 */
 	if (h->ae_algo->ops->reset_event)
 		h->ae_algo->ops->reset_event(h->pdev, h);
 }
@@ -3370,7 +3367,6 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	priv->dev = &pdev->dev;
 	priv->netdev = netdev;
 	priv->ae_handle = handle;
-	priv->ae_handle->last_reset_time = jiffies;
 	priv->tx_timeout_count = 0;
 
 	handle->kinfo.netdev = netdev;
@@ -3390,11 +3386,6 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	/* Carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(netdev);
 
-	if (handle->flags & HNAE3_SUPPORT_VF)
-		handle->reset_level = HNAE3_VF_RESET;
-	else
-		handle->reset_level = HNAE3_FUNC_RESET;
-
 	ret = hns3_get_ring_config(priv);
 	if (ret) {
 		ret = -ENOMEM;
@@ -3785,7 +3776,6 @@ static int hns3_reset_notify_up_enet(struct hnae3_handle *handle)
 				   "hns net up fail, ret=%d!\n", ret);
 			return ret;
 		}
-		handle->last_reset_time = jiffies;
 	}
 
 	clear_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 62022d552f5d..a90c19e6f2ca 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2465,15 +2465,14 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
 static void hclge_reset(struct hclge_dev *hdev)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
-	struct hnae3_handle *handle;
 
 	/* Initialize ae_dev reset status as well, in case enet layer wants to
 	 * know if device is undergoing reset
 	 */
 	ae_dev->reset_type = hdev->reset_type;
 	hdev->reset_count++;
+	hdev->last_reset_time = jiffies;
 	/* perform reset of the stack & ae device for a client */
-	handle = &hdev->vport[0].nic;
 	rtnl_lock();
 	hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
 	rtnl_unlock();
@@ -2493,7 +2492,6 @@ static void hclge_reset(struct hclge_dev *hdev)
 	}
 
 	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
-	handle->last_reset_time = jiffies;
 	rtnl_unlock();
 	ae_dev->reset_type = HNAE3_NONE_RESET;
 }
@@ -2521,24 +2519,24 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
 	if (!handle)
 		handle = &hdev->vport[0].nic;
 
-	if (time_before(jiffies, (handle->last_reset_time + 3 * HZ)))
+	if (time_before(jiffies, (hdev->last_reset_time + 3 * HZ)))
 		return;
 	else if (hdev->default_reset_request)
-		handle->reset_level =
+		hdev->reset_level =
 			hclge_get_reset_level(hdev,
 					      &hdev->default_reset_request);
-	else if (time_after(jiffies, (handle->last_reset_time + 4 * 5 * HZ)))
-		handle->reset_level = HNAE3_FUNC_RESET;
+	else if (time_after(jiffies, (hdev->last_reset_time + 4 * 5 * HZ)))
+		hdev->reset_level = HNAE3_FUNC_RESET;
 
 	dev_info(&hdev->pdev->dev, "received reset event , reset type is %d",
-		 handle->reset_level);
+		 hdev->reset_level);
 
 	/* request reset & schedule reset task */
-	set_bit(handle->reset_level, &hdev->reset_request);
+	set_bit(hdev->reset_level, &hdev->reset_request);
 	hclge_reset_task_schedule(hdev);
 
-	if (handle->reset_level < HNAE3_GLOBAL_RESET)
-		handle->reset_level++;
+	if (hdev->reset_level < HNAE3_GLOBAL_RESET)
+		hdev->reset_level++;
 }
 
 static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
@@ -2560,6 +2558,7 @@ static void hclge_reset_subtask(struct hclge_dev *hdev)
 	 *    b. else, we can come back later to check this status so re-sched
 	 *       now.
 	 */
+	hdev->last_reset_time = jiffies;
 	hdev->reset_type = hclge_get_reset_level(hdev, &hdev->reset_pending);
 	if (hdev->reset_type != HNAE3_NONE_RESET)
 		hclge_reset(hdev);
@@ -6670,6 +6669,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hdev->pdev = pdev;
 	hdev->ae_dev = ae_dev;
 	hdev->reset_type = HNAE3_NONE_RESET;
+	hdev->reset_level = HNAE3_FUNC_RESET;
 	ae_dev->priv = hdev;
 
 	ret = hclge_pci_init(hdev);
@@ -6814,6 +6814,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_enable_vector(&hdev->misc_vector, true);
 
 	hclge_state_init(hdev);
+	hdev->last_reset_time = jiffies;
 
 	pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME);
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index b6a17f56c8d8..69bdb7f646ee 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -593,8 +593,10 @@ struct hclge_dev {
 	struct hclge_misc_vector misc_vector;
 	struct hclge_hw_stats hw_stats;
 	unsigned long state;
+	unsigned long last_reset_time;
 
 	enum hnae3_reset_type reset_type;
+	enum hnae3_reset_type reset_level;
 	unsigned long default_reset_request;
 	unsigned long reset_request;	/* reset has been requested */
 	unsigned long reset_pending;	/* client rst is pending to be served */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 7531bdde02a7..4a2148bde35a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1234,17 +1234,17 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
 	dev_info(&hdev->pdev->dev, "received reset request from VF enet\n");
 
 	if (!hdev->default_reset_request)
-		handle->reset_level =
+		hdev->reset_level =
 			hclgevf_get_reset_level(hdev,
 						&hdev->default_reset_request);
 	else
-		handle->reset_level = HNAE3_VF_RESET;
+		hdev->reset_level = HNAE3_VF_RESET;
 
 	/* reset of this VF requested */
 	set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state);
 	hclgevf_reset_task_schedule(hdev);
 
-	handle->last_reset_time = jiffies;
+	hdev->last_reset_time = jiffies;
 }
 
 static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
@@ -1372,7 +1372,7 @@ static void hclgevf_reset_service_task(struct work_struct *work)
 		 */
 		if (hdev->reset_attempts > 3) {
 			/* prepare for full reset of stack + pcie interface */
-			hdev->nic.reset_level = HNAE3_VF_FULL_RESET;
+			hdev->reset_level = HNAE3_VF_FULL_RESET;
 
 			/* "defer" schedule the reset task again */
 			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
@@ -1985,6 +1985,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 	}
 
 	hclgevf_state_init(hdev);
+	hdev->reset_level = HNAE3_VF_RESET;
 
 	ret = hclgevf_misc_irq_init(hdev);
 	if (ret) {
@@ -2026,6 +2027,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_config;
 	}
 
+	hdev->last_reset_time = jiffies;
 	pr_info("finished initializing %s driver\n", HCLGEVF_DRIVER_NAME);
 
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index ffb8c7768b88..0ea4c9b3ae0a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -146,6 +146,8 @@ struct hclgevf_dev {
 	struct hclgevf_rss_cfg rss_cfg;
 	unsigned long state;
 	unsigned long default_reset_request;
+	unsigned long last_reset_time;
+	enum hnae3_reset_type reset_level;
 
 #define HCLGEVF_RESET_REQUESTED		0
 #define HCLGEVF_RESET_PENDING		1
@@ -198,14 +200,14 @@ static inline bool hclgevf_dev_ongoing_reset(struct hclgevf_dev *hdev)
 {
 	return (hdev &&
 		(test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) &&
-		(hdev->nic.reset_level == HNAE3_VF_RESET));
+		(hdev->reset_level == HNAE3_VF_RESET));
 }
 
 static inline bool hclgevf_dev_ongoing_full_reset(struct hclgevf_dev *hdev)
 {
 	return (hdev &&
 		(test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) &&
-		(hdev->nic.reset_level == HNAE3_VF_FULL_RESET));
+		(hdev->reset_level == HNAE3_VF_FULL_RESET));
 }
 
 int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, u16 code, u16 subcode,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index e9d5a4f96304..558e3b838676 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -267,7 +267,7 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 			 * has been completely reset. After this stack should
 			 * eventually be re-initialized.
 			 */
-			hdev->nic.reset_level = HNAE3_VF_RESET;
+			hdev->reset_level = HNAE3_VF_RESET;
 			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 			hclgevf_reset_task_schedule(hdev);
 
-- 
cgit v1.2.3


From 35d93a30040c3884d8752c35a3fc1200d8f96b1b Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:15 +0800
Subject: net: hns3: adjust the process of PF reset

When doing PF reset, the driver needs to do some preparatory work
before asserting PF reset. Since when hardware is resetting, it
is necessary to stop tx/rx queue, clear hardware table, etc,
otherwise hardware may run into unrecoverable state if there is
still IO running when the hardware is resetting.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 38 ++++++++++++++++++++--
 1 file changed, 36 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index a90c19e6f2ca..3c327f8cb865 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2396,7 +2396,6 @@ static void hclge_do_reset(struct hclge_dev *hdev)
 		break;
 	case HNAE3_FUNC_RESET:
 		dev_info(&pdev->dev, "PF Reset requested\n");
-		hclge_func_reset_cmd(hdev, 0);
 		/* schedule again to check later */
 		set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending);
 		hclge_reset_task_schedule(hdev);
@@ -2462,6 +2461,35 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
 	hclge_enable_vector(&hdev->misc_vector, true);
 }
 
+static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
+{
+	int ret = 0;
+
+	switch (hdev->reset_type) {
+	case HNAE3_FUNC_RESET:
+		ret = hclge_func_reset_cmd(hdev, 0);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"assertting function reset fail %d!\n", ret);
+			return ret;
+		}
+
+		/* After performaning pf reset, it is not necessary to do the
+		 * mailbox handling or send any command to firmware, because
+		 * any mailbox handling or command to firmware is only valid
+		 * after hclge_cmd_init is called.
+		 */
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+		break;
+	default:
+		break;
+	}
+
+	dev_info(&hdev->pdev->dev, "prepare wait ok\n");
+
+	return ret;
+}
+
 static void hclge_reset(struct hclge_dev *hdev)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
@@ -2477,6 +2505,8 @@ static void hclge_reset(struct hclge_dev *hdev)
 	hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
 	rtnl_unlock();
 
+	hclge_reset_prepare_wait(hdev);
+
 	if (!hclge_reset_wait(hdev)) {
 		rtnl_lock();
 		hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
@@ -4873,7 +4903,11 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 	cancel_work_sync(&hdev->service_task);
 	clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state);
 
-	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) {
+	/* If it is not PF reset, the firmware will disable the MAC,
+	 * so it only need to stop phy here.
+	 */
+	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) &&
+	    hdev->reset_type != HNAE3_FUNC_RESET) {
 		hclge_mac_stop_phy(hdev);
 		return;
 	}
-- 
cgit v1.2.3


From f403a84fb25ea5a49cf9d6d27f522e8f752ef36f Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:16 +0800
Subject: net: hns3: call roce's reset notify callback when resetting

While doing resetting, roce should do its uninitailization part
before nic's, and do its initialization part after nic's.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 33 ++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 3c327f8cb865..0c0327b733a2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2315,6 +2315,34 @@ static int hclge_notify_client(struct hclge_dev *hdev,
 	return 0;
 }
 
+static int hclge_notify_roce_client(struct hclge_dev *hdev,
+				    enum hnae3_reset_notify_type type)
+{
+	struct hnae3_client *client = hdev->roce_client;
+	int ret = 0;
+	u16 i;
+
+	if (!client)
+		return 0;
+
+	if (!client->ops->reset_notify)
+		return -EOPNOTSUPP;
+
+	for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
+		struct hnae3_handle *handle = &hdev->vport[i].roce;
+
+		ret = client->ops->reset_notify(handle, type);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"notify roce client failed %d(%d)",
+				type, ret);
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
 static int hclge_reset_wait(struct hclge_dev *hdev)
 {
 #define HCLGE_RESET_WATI_MS	100
@@ -2501,6 +2529,7 @@ static void hclge_reset(struct hclge_dev *hdev)
 	hdev->reset_count++;
 	hdev->last_reset_time = jiffies;
 	/* perform reset of the stack & ae device for a client */
+	hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
 	rtnl_lock();
 	hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
 	rtnl_unlock();
@@ -2508,6 +2537,7 @@ static void hclge_reset(struct hclge_dev *hdev)
 	hclge_reset_prepare_wait(hdev);
 
 	if (!hclge_reset_wait(hdev)) {
+		hclge_notify_roce_client(hdev, HNAE3_UNINIT_CLIENT);
 		rtnl_lock();
 		hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
 		hclge_reset_ae_dev(hdev->ae_dev);
@@ -2524,6 +2554,9 @@ static void hclge_reset(struct hclge_dev *hdev)
 	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
 	rtnl_unlock();
 	ae_dev->reset_type = HNAE3_NONE_RESET;
+
+	hclge_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
+	hclge_notify_roce_client(hdev, HNAE3_UP_CLIENT);
 }
 
 static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
-- 
cgit v1.2.3


From 65e41e7e683862136a817f29a1a457ecdf37ba8a Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:17 +0800
Subject: net: hns3: add error handler for hclge_reset()

When hclge_reset() is called, it may fail for several reasons.
For example, an higher-level reset event occurs, memory allocation
failure, hardware reset timeout, etc. Therefore, it is necessary
to add corresponding error handling for these situations.
1. A high-level reset is required due to a high-level reset failure.
2. For memory allocation failure, a high-level reset is initiated by
the timer to recover. The reason for using the timer is to prevent this
new high-level reset to interrupt the reset process of other pf/vf;
3. For the case of hardware reset timeout, reschedule the reset task
to wait for the hardware to complete the reset.
For memory allocation failure and reset timeouts, in order to prevent
an infinite number of scheduled reset tasks, the number of error
recovery needs to be limited.

This patch also add some reset related debug log printing.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 139 +++++++++++++++++----
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |   3 +
 2 files changed, 120 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 0c0327b733a2..579945bdcc76 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2145,6 +2145,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 
 	/* check for vector0 reset event sources */
 	if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & rst_src_reg) {
+		dev_info(&hdev->pdev->dev, "global reset interrupt\n");
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
 		*clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
@@ -2152,6 +2153,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	}
 
 	if (BIT(HCLGE_VECTOR0_CORERESET_INT_B) & rst_src_reg) {
+		dev_info(&hdev->pdev->dev, "core reset interrupt\n");
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_CORE_RESET, &hdev->reset_pending);
 		*clearval = BIT(HCLGE_VECTOR0_CORERESET_INT_B);
@@ -2159,6 +2161,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	}
 
 	if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & rst_src_reg) {
+		dev_info(&hdev->pdev->dev, "IMP reset interrupt\n");
 		set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
 		*clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B);
 		return HCLGE_VECTOR0_EVENT_RST;
@@ -2308,8 +2311,11 @@ static int hclge_notify_client(struct hclge_dev *hdev,
 		int ret;
 
 		ret = client->ops->reset_notify(handle, type);
-		if (ret)
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"notify nic client failed %d(%d)\n", type, ret);
 			return ret;
+		}
 	}
 
 	return 0;
@@ -2518,9 +2524,49 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 	return ret;
 }
 
+static bool hclge_reset_err_handle(struct hclge_dev *hdev, bool is_timeout)
+{
+#define MAX_RESET_FAIL_CNT 5
+#define RESET_UPGRADE_DELAY_SEC 10
+
+	if (hdev->reset_pending) {
+		dev_info(&hdev->pdev->dev, "Reset pending %lu\n",
+			 hdev->reset_pending);
+		return true;
+	} else if ((hdev->reset_type != HNAE3_IMP_RESET) &&
+		   (hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG) &
+		    BIT(HCLGE_IMP_RESET_BIT))) {
+		dev_info(&hdev->pdev->dev,
+			 "reset failed because IMP Reset is pending\n");
+		hclge_clear_reset_cause(hdev);
+		return false;
+	} else if (hdev->reset_fail_cnt < MAX_RESET_FAIL_CNT) {
+		hdev->reset_fail_cnt++;
+		if (is_timeout) {
+			set_bit(hdev->reset_type, &hdev->reset_pending);
+			dev_info(&hdev->pdev->dev,
+				 "re-schedule to wait for hw reset done\n");
+			return true;
+		}
+
+		dev_info(&hdev->pdev->dev, "Upgrade reset level\n");
+		hclge_clear_reset_cause(hdev);
+		mod_timer(&hdev->reset_timer,
+			  jiffies + RESET_UPGRADE_DELAY_SEC * HZ);
+
+		return false;
+	}
+
+	hclge_clear_reset_cause(hdev);
+	dev_err(&hdev->pdev->dev, "Reset fail!\n");
+	return false;
+}
+
 static void hclge_reset(struct hclge_dev *hdev)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+	bool is_timeout = false;
+	int ret;
 
 	/* Initialize ae_dev reset status as well, in case enet layer wants to
 	 * know if device is undergoing reset
@@ -2529,34 +2575,66 @@ static void hclge_reset(struct hclge_dev *hdev)
 	hdev->reset_count++;
 	hdev->last_reset_time = jiffies;
 	/* perform reset of the stack & ae device for a client */
-	hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
+	ret = hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
+	if (ret)
+		goto err_reset;
+
 	rtnl_lock();
-	hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
-	rtnl_unlock();
+	ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+	if (ret)
+		goto err_reset_lock;
 
-	hclge_reset_prepare_wait(hdev);
+	rtnl_unlock();
 
-	if (!hclge_reset_wait(hdev)) {
-		hclge_notify_roce_client(hdev, HNAE3_UNINIT_CLIENT);
-		rtnl_lock();
-		hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
-		hclge_reset_ae_dev(hdev->ae_dev);
-		hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+	ret = hclge_reset_prepare_wait(hdev);
+	if (ret)
+		goto err_reset;
 
-		hclge_clear_reset_cause(hdev);
-	} else {
-		rtnl_lock();
-		/* schedule again to check pending resets later */
-		set_bit(hdev->reset_type, &hdev->reset_pending);
-		hclge_reset_task_schedule(hdev);
+	if (hclge_reset_wait(hdev)) {
+		is_timeout = true;
+		goto err_reset;
 	}
 
-	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+	ret = hclge_notify_roce_client(hdev, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		goto err_reset;
+
+	rtnl_lock();
+	ret = hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		goto err_reset_lock;
+
+	ret = hclge_reset_ae_dev(hdev->ae_dev);
+	if (ret)
+		goto err_reset_lock;
+
+	ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+	if (ret)
+		goto err_reset_lock;
+
+	hclge_clear_reset_cause(hdev);
+
+	ret = hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+	if (ret)
+		goto err_reset_lock;
+
 	rtnl_unlock();
-	ae_dev->reset_type = HNAE3_NONE_RESET;
 
-	hclge_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
-	hclge_notify_roce_client(hdev, HNAE3_UP_CLIENT);
+	ret = hclge_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
+	if (ret)
+		goto err_reset;
+
+	ret = hclge_notify_roce_client(hdev, HNAE3_UP_CLIENT);
+	if (ret)
+		goto err_reset;
+
+	return;
+
+err_reset_lock:
+	rtnl_unlock();
+err_reset:
+	if (hclge_reset_err_handle(hdev, is_timeout))
+		hclge_reset_task_schedule(hdev);
 }
 
 static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
@@ -2610,6 +2688,16 @@ static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
 	set_bit(rst_type, &hdev->default_reset_request);
 }
 
+static void hclge_reset_timer(struct timer_list *t)
+{
+	struct hclge_dev *hdev = from_timer(hdev, t, reset_timer);
+
+	dev_info(&hdev->pdev->dev,
+		 "triggering global reset in reset timer\n");
+	set_bit(HNAE3_GLOBAL_RESET, &hdev->default_reset_request);
+	hclge_reset_event(hdev->pdev, NULL);
+}
+
 static void hclge_reset_subtask(struct hclge_dev *hdev)
 {
 	/* check if there is any ongoing reset in the hardware. This status can
@@ -4416,8 +4504,12 @@ static int hclge_restore_fd_entries(struct hnae3_handle *handle)
 	struct hlist_node *node;
 	int ret;
 
+	/* Return ok here, because reset error handling will check this
+	 * return value. If error is returned here, the reset process will
+	 * fail.
+	 */
 	if (!hnae3_dev_fd_supported(hdev))
-		return -EOPNOTSUPP;
+		return 0;
 
 	hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list, rule_node) {
 		ret = hclge_config_action(hdev, HCLGE_FD_STAGE_1, rule);
@@ -6713,6 +6805,8 @@ static void hclge_state_uninit(struct hclge_dev *hdev)
 
 	if (hdev->service_timer.function)
 		del_timer_sync(&hdev->service_timer);
+	if (hdev->reset_timer.function)
+		del_timer_sync(&hdev->reset_timer);
 	if (hdev->service_task.func)
 		cancel_work_sync(&hdev->service_task);
 	if (hdev->rst_service_task.func)
@@ -6871,6 +6965,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_dcb_ops_set(hdev);
 
 	timer_setup(&hdev->service_timer, hclge_service_timer, 0);
+	timer_setup(&hdev->reset_timer, hclge_reset_timer, 0);
 	INIT_WORK(&hdev->service_task, hclge_service_task);
 	INIT_WORK(&hdev->rst_service_task, hclge_reset_service_task);
 	INIT_WORK(&hdev->mbx_service_task, hclge_mailbox_service_task);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 69bdb7f646ee..36f341368683 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -102,6 +102,7 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_GLOBAL_RESET_REG		0x20A00
 #define HCLGE_GLOBAL_RESET_BIT		0
 #define HCLGE_CORE_RESET_BIT		1
+#define HCLGE_IMP_RESET_BIT		2
 #define HCLGE_FUN_RST_ING		0x20C00
 #define HCLGE_FUN_RST_ING_B		0
 
@@ -601,6 +602,7 @@ struct hclge_dev {
 	unsigned long reset_request;	/* reset has been requested */
 	unsigned long reset_pending;	/* client rst is pending to be served */
 	unsigned long reset_count;	/* the number of reset has been done */
+	u32 reset_fail_cnt;
 	u32 fw_version;
 	u16 num_vmdq_vport;		/* Num vmdq vport this PF has set up */
 	u16 num_tqps;			/* Num task queue pairs of this PF */
@@ -648,6 +650,7 @@ struct hclge_dev {
 	unsigned long service_timer_period;
 	unsigned long service_timer_previous;
 	struct timer_list service_timer;
+	struct timer_list reset_timer;
 	struct work_struct service_task;
 	struct work_struct rst_service_task;
 	struct work_struct mbx_service_task;
-- 
cgit v1.2.3


From 8b0195a30585fefd4c181881077b4181670ca85d Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 7 Nov 2018 12:06:18 +0800
Subject: net: hns3: fix for cmd queue memory not freed problem during reset

It is not necessary to reallocate the descriptor and remap the
descriptor memory in reset process, otherwise it may cause memory
not freed problem.

Also, this patch initializes the cmd queue's spinlocks in
hclgevf_alloc_cmd_queue, and take the spinlocks when reinitializing
cmd queue' registers.

Fixes: fedd0c15d288 ("net: hns3: Add HNS3 VF IMP(Integrated Management Proc) cmd interface")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c   | 141 ++++++++++++---------
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h   |   1 +
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  |  14 +-
 3 files changed, 91 insertions(+), 65 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index 0d3b445f6799..b917acf71ee6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -72,6 +72,45 @@ static bool hclgevf_is_special_opcode(u16 opcode)
 	return false;
 }
 
+static void hclgevf_cmd_config_regs(struct hclgevf_cmq_ring *ring)
+{
+	struct hclgevf_dev *hdev = ring->dev;
+	struct hclgevf_hw *hw = &hdev->hw;
+	u32 reg_val;
+
+	if (ring->flag == HCLGEVF_TYPE_CSQ) {
+		reg_val = (u32)ring->desc_dma_addr;
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_L_REG, reg_val);
+		reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, reg_val);
+
+		reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
+		reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, reg_val);
+
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0);
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0);
+	} else {
+		reg_val = (u32)ring->desc_dma_addr;
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_L_REG, reg_val);
+		reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_H_REG, reg_val);
+
+		reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
+		reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_DEPTH_REG, reg_val);
+
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0);
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0);
+	}
+}
+
+static void hclgevf_cmd_init_regs(struct hclgevf_hw *hw)
+{
+	hclgevf_cmd_config_regs(&hw->cmq.csq);
+	hclgevf_cmd_config_regs(&hw->cmq.crq);
+}
+
 static int hclgevf_alloc_cmd_desc(struct hclgevf_cmq_ring *ring)
 {
 	int size = ring->desc_num * sizeof(struct hclgevf_desc);
@@ -96,61 +135,23 @@ static void hclgevf_free_cmd_desc(struct hclgevf_cmq_ring *ring)
 	}
 }
 
-static int hclgevf_init_cmd_queue(struct hclgevf_dev *hdev,
-				  struct hclgevf_cmq_ring *ring)
+static int hclgevf_alloc_cmd_queue(struct hclgevf_dev *hdev, int ring_type)
 {
 	struct hclgevf_hw *hw = &hdev->hw;
-	int ring_type = ring->flag;
-	u32 reg_val;
+	struct hclgevf_cmq_ring *ring =
+		(ring_type == HCLGEVF_TYPE_CSQ) ? &hw->cmq.csq : &hw->cmq.crq;
 	int ret;
 
-	ring->desc_num = HCLGEVF_NIC_CMQ_DESC_NUM;
-	spin_lock_init(&ring->lock);
-	ring->next_to_clean = 0;
-	ring->next_to_use = 0;
 	ring->dev = hdev;
+	ring->flag = ring_type;
 
 	/* allocate CSQ/CRQ descriptor */
 	ret = hclgevf_alloc_cmd_desc(ring);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev, "failed(%d) to alloc %s desc\n", ret,
 			(ring_type == HCLGEVF_TYPE_CSQ) ? "CSQ" : "CRQ");
-		return ret;
-	}
-
-	/* initialize the hardware registers with csq/crq dma-address,
-	 * descriptor number, head & tail pointers
-	 */
-	switch (ring_type) {
-	case HCLGEVF_TYPE_CSQ:
-		reg_val = (u32)ring->desc_dma_addr;
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_L_REG, reg_val);
-		reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, reg_val);
 
-		reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
-		reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, reg_val);
-
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0);
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0);
-		return 0;
-	case HCLGEVF_TYPE_CRQ:
-		reg_val = (u32)ring->desc_dma_addr;
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_L_REG, reg_val);
-		reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_H_REG, reg_val);
-
-		reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
-		reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_DEPTH_REG, reg_val);
-
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0);
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0);
-		return 0;
-	default:
-		return -EINVAL;
-	}
+	return ret;
 }
 
 void hclgevf_cmd_setup_basic_desc(struct hclgevf_desc *desc,
@@ -282,55 +283,73 @@ static int  hclgevf_cmd_query_firmware_version(struct hclgevf_hw *hw,
 	return status;
 }
 
-int hclgevf_cmd_init(struct hclgevf_dev *hdev)
+int hclgevf_cmd_queue_init(struct hclgevf_dev *hdev)
 {
-	u32 version;
 	int ret;
 
-	/* setup Tx write back timeout */
+	/* Setup the lock for command queue */
+	spin_lock_init(&hdev->hw.cmq.csq.lock);
+	spin_lock_init(&hdev->hw.cmq.crq.lock);
+
 	hdev->hw.cmq.tx_timeout = HCLGEVF_CMDQ_TX_TIMEOUT;
+	hdev->hw.cmq.csq.desc_num = HCLGEVF_NIC_CMQ_DESC_NUM;
+	hdev->hw.cmq.crq.desc_num = HCLGEVF_NIC_CMQ_DESC_NUM;
 
-	/* setup queue CSQ/CRQ rings */
-	hdev->hw.cmq.csq.flag = HCLGEVF_TYPE_CSQ;
-	ret = hclgevf_init_cmd_queue(hdev, &hdev->hw.cmq.csq);
+	ret = hclgevf_alloc_cmd_queue(hdev, HCLGEVF_TYPE_CSQ);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"failed(%d) to initialize CSQ ring\n", ret);
+			"CSQ ring setup error %d\n", ret);
 		return ret;
 	}
 
-	hdev->hw.cmq.crq.flag = HCLGEVF_TYPE_CRQ;
-	ret = hclgevf_init_cmd_queue(hdev, &hdev->hw.cmq.crq);
+	ret = hclgevf_alloc_cmd_queue(hdev, HCLGEVF_TYPE_CRQ);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"failed(%d) to initialize CRQ ring\n", ret);
+			"CRQ ring setup error %d\n", ret);
 		goto err_csq;
 	}
 
+	return 0;
+err_csq:
+	hclgevf_free_cmd_desc(&hdev->hw.cmq.csq);
+	return ret;
+}
+
+int hclgevf_cmd_init(struct hclgevf_dev *hdev)
+{
+	u32 version;
+	int ret;
+
+	spin_lock_bh(&hdev->hw.cmq.csq.lock);
+	spin_lock_bh(&hdev->hw.cmq.crq.lock);
+
 	/* initialize the pointers of async rx queue of mailbox */
 	hdev->arq.hdev = hdev;
 	hdev->arq.head = 0;
 	hdev->arq.tail = 0;
 	hdev->arq.count = 0;
+	hdev->hw.cmq.csq.next_to_clean = 0;
+	hdev->hw.cmq.csq.next_to_use = 0;
+	hdev->hw.cmq.crq.next_to_clean = 0;
+	hdev->hw.cmq.crq.next_to_use = 0;
+
+	hclgevf_cmd_init_regs(&hdev->hw);
+
+	spin_unlock_bh(&hdev->hw.cmq.crq.lock);
+	spin_unlock_bh(&hdev->hw.cmq.csq.lock);
 
 	/* get firmware version */
 	ret = hclgevf_cmd_query_firmware_version(&hdev->hw, &version);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed(%d) to query firmware version\n", ret);
-		goto err_crq;
+		return ret;
 	}
 	hdev->fw_version = version;
 
 	dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version);
 
 	return 0;
-err_crq:
-	hclgevf_free_cmd_desc(&hdev->hw.cmq.crq);
-err_csq:
-	hclgevf_free_cmd_desc(&hdev->hw.cmq.csq);
-
-	return ret;
 }
 
 void hclgevf_cmd_uninit(struct hclgevf_dev *hdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index bc294b0c8b62..090541de0c7d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -256,6 +256,7 @@ static inline u32 hclgevf_read_reg(u8 __iomem *base, u32 reg)
 
 int hclgevf_cmd_init(struct hclgevf_dev *hdev);
 void hclgevf_cmd_uninit(struct hclgevf_dev *hdev);
+int hclgevf_cmd_queue_init(struct hclgevf_dev *hdev);
 
 int hclgevf_cmd_send(struct hclgevf_hw *hw, struct hclgevf_desc *desc, int num);
 void hclgevf_cmd_setup_basic_desc(struct hclgevf_desc *desc,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 4a2148bde35a..29da4806c100 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1966,6 +1966,12 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		return ret;
 	}
 
+	ret = hclgevf_cmd_queue_init(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Cmd queue init failed: %d\n", ret);
+		goto err_cmd_queue_init;
+	}
+
 	ret = hclgevf_cmd_init(hdev);
 	if (ret)
 		goto err_cmd_init;
@@ -1975,13 +1981,13 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Query vf status error, ret = %d.\n", ret);
-		goto err_query_vf;
+		goto err_cmd_init;
 	}
 
 	ret = hclgevf_init_msi(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed(%d) to init MSI/MSI-X\n", ret);
-		goto err_query_vf;
+		goto err_cmd_init;
 	}
 
 	hclgevf_state_init(hdev);
@@ -2037,9 +2043,9 @@ err_config:
 err_misc_irq_init:
 	hclgevf_state_uninit(hdev);
 	hclgevf_uninit_msi(hdev);
-err_query_vf:
-	hclgevf_cmd_uninit(hdev);
 err_cmd_init:
+	hclgevf_cmd_uninit(hdev);
+err_cmd_queue_init:
 	hclgevf_pci_uninit(hdev);
 	return ret;
 }
-- 
cgit v1.2.3


From a3c6b063fee70a7ceae385741210f39b1ec2ab94 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Tue, 6 Nov 2018 17:07:28 -0800
Subject: nfp: flower: add ipv4 set ttl and tos offload

Add ipv4 set ttl and tos action offload. Since pedit sets headers per 4
byte word, we need to ensure that setting either version, ihl, protocol,
total length or checksum does not get offloaded.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 69 ++++++++++++++++++++--
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h   | 10 ++++
 2 files changed, 73 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 244dc261006e..b79b924ef56d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -384,10 +384,21 @@ nfp_fl_set_eth(const struct tc_action *action, int idx, u32 off,
 	return 0;
 }
 
+struct ipv4_ttl_word {
+	__u8	ttl;
+	__u8	protocol;
+	__sum16	check;
+};
+
 static int
 nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off,
-	       struct nfp_fl_set_ip4_addrs *set_ip_addr)
+	       struct nfp_fl_set_ip4_addrs *set_ip_addr,
+	       struct nfp_fl_set_ip4_ttl_tos *set_ip_ttl_tos)
 {
+	struct ipv4_ttl_word *ttl_word_mask;
+	struct ipv4_ttl_word *ttl_word;
+	struct iphdr *tos_word_mask;
+	struct iphdr *tos_word;
 	__be32 exact, mask;
 
 	/* We are expecting tcf_pedit to return a big endian value */
@@ -402,20 +413,53 @@ nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off,
 		set_ip_addr->ipv4_dst_mask |= mask;
 		set_ip_addr->ipv4_dst &= ~mask;
 		set_ip_addr->ipv4_dst |= exact & mask;
+		set_ip_addr->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS;
+		set_ip_addr->head.len_lw = sizeof(*set_ip_addr) >>
+					   NFP_FL_LW_SIZ;
 		break;
 	case offsetof(struct iphdr, saddr):
 		set_ip_addr->ipv4_src_mask |= mask;
 		set_ip_addr->ipv4_src &= ~mask;
 		set_ip_addr->ipv4_src |= exact & mask;
+		set_ip_addr->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS;
+		set_ip_addr->head.len_lw = sizeof(*set_ip_addr) >>
+					   NFP_FL_LW_SIZ;
+		break;
+	case offsetof(struct iphdr, ttl):
+		ttl_word_mask = (struct ipv4_ttl_word *)&mask;
+		ttl_word = (struct ipv4_ttl_word *)&exact;
+
+		if (ttl_word_mask->protocol || ttl_word_mask->check)
+			return -EOPNOTSUPP;
+
+		set_ip_ttl_tos->ipv4_ttl_mask |= ttl_word_mask->ttl;
+		set_ip_ttl_tos->ipv4_ttl &= ~ttl_word_mask->ttl;
+		set_ip_ttl_tos->ipv4_ttl |= ttl_word->ttl & ttl_word_mask->ttl;
+		set_ip_ttl_tos->head.jump_id =
+			NFP_FL_ACTION_OPCODE_SET_IPV4_TTL_TOS;
+		set_ip_ttl_tos->head.len_lw = sizeof(*set_ip_ttl_tos) >>
+					      NFP_FL_LW_SIZ;
+		break;
+	case round_down(offsetof(struct iphdr, tos), 4):
+		tos_word_mask = (struct iphdr *)&mask;
+		tos_word = (struct iphdr *)&exact;
+
+		if (tos_word_mask->version || tos_word_mask->ihl ||
+		    tos_word_mask->tot_len)
+			return -EOPNOTSUPP;
+
+		set_ip_ttl_tos->ipv4_tos_mask |= tos_word_mask->tos;
+		set_ip_ttl_tos->ipv4_tos &= ~tos_word_mask->tos;
+		set_ip_ttl_tos->ipv4_tos |= tos_word->tos & tos_word_mask->tos;
+		set_ip_ttl_tos->head.jump_id =
+			NFP_FL_ACTION_OPCODE_SET_IPV4_TTL_TOS;
+		set_ip_ttl_tos->head.len_lw = sizeof(*set_ip_ttl_tos) >>
+					      NFP_FL_LW_SIZ;
 		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
-	set_ip_addr->reserved = cpu_to_be16(0);
-	set_ip_addr->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS;
-	set_ip_addr->head.len_lw = sizeof(*set_ip_addr) >> NFP_FL_LW_SIZ;
-
 	return 0;
 }
 
@@ -513,6 +557,7 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 	     char *nfp_action, int *a_len, u32 *csum_updated)
 {
 	struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src;
+	struct nfp_fl_set_ip4_ttl_tos set_ip_ttl_tos;
 	struct nfp_fl_set_ip4_addrs set_ip_addr;
 	struct nfp_fl_set_tport set_tport;
 	struct nfp_fl_set_eth set_eth;
@@ -522,6 +567,7 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 	u32 offset, cmd;
 	u8 ip_proto = 0;
 
+	memset(&set_ip_ttl_tos, 0, sizeof(set_ip_ttl_tos));
 	memset(&set_ip6_dst, 0, sizeof(set_ip6_dst));
 	memset(&set_ip6_src, 0, sizeof(set_ip6_src));
 	memset(&set_ip_addr, 0, sizeof(set_ip_addr));
@@ -542,7 +588,8 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 			err = nfp_fl_set_eth(action, idx, offset, &set_eth);
 			break;
 		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
-			err = nfp_fl_set_ip4(action, idx, offset, &set_ip_addr);
+			err = nfp_fl_set_ip4(action, idx, offset, &set_ip_addr,
+					     &set_ip_ttl_tos);
 			break;
 		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
 			err = nfp_fl_set_ip6(action, idx, offset, &set_ip6_dst,
@@ -577,6 +624,16 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 		memcpy(nfp_action, &set_eth, act_size);
 		*a_len += act_size;
 	}
+	if (set_ip_ttl_tos.head.len_lw) {
+		nfp_action += act_size;
+		act_size = sizeof(set_ip_ttl_tos);
+		memcpy(nfp_action, &set_ip_ttl_tos, act_size);
+		*a_len += act_size;
+
+		/* Hardware will automatically fix IPv4 and TCP/UDP checksum. */
+		*csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR |
+				nfp_fl_csum_l4_to_flag(ip_proto);
+	}
 	if (set_ip_addr.head.len_lw) {
 		nfp_action += act_size;
 		act_size = sizeof(set_ip_addr);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 29d673aa5277..a00f45b5e16c 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -65,6 +65,7 @@
 #define NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL	6
 #define NFP_FL_ACTION_OPCODE_SET_ETHERNET	7
 #define NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS	9
+#define NFP_FL_ACTION_OPCODE_SET_IPV4_TTL_TOS	10
 #define NFP_FL_ACTION_OPCODE_SET_IPV6_SRC	11
 #define NFP_FL_ACTION_OPCODE_SET_IPV6_DST	12
 #define NFP_FL_ACTION_OPCODE_SET_UDP		14
@@ -125,6 +126,15 @@ struct nfp_fl_set_ip4_addrs {
 	__be32 ipv4_dst;
 };
 
+struct nfp_fl_set_ip4_ttl_tos {
+	struct nfp_fl_act_head head;
+	u8 ipv4_ttl_mask;
+	u8 ipv4_tos_mask;
+	u8 ipv4_ttl;
+	u8 ipv4_tos;
+	__be16 reserved;
+};
+
 struct nfp_fl_set_ipv6_addr {
 	struct nfp_fl_act_head head;
 	__be16 reserved;
-- 
cgit v1.2.3


From 4234d62c27a633a089506f0b05040d7c6ff5fd6c Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Tue, 6 Nov 2018 17:07:29 -0800
Subject: nfp: flower: add ipv6 set flow label and hop limit offload

Add ipv6 set flow label and hop limit action offload. Since pedit sets
headers per 4 byte word, we need to ensure that setting either version,
priority, payload_len or nexthdr does not get offloaded.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 65 ++++++++++++++++++++--
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h   | 14 +++++
 2 files changed, 75 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index b79b924ef56d..cfea8f790f95 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -476,12 +476,57 @@ nfp_fl_set_ip6_helper(int opcode_tag, u8 word, __be32 exact, __be32 mask,
 	ip6->head.len_lw = sizeof(*ip6) >> NFP_FL_LW_SIZ;
 }
 
+struct ipv6_hop_limit_word {
+	__be16 payload_len;
+	u8 nexthdr;
+	u8 hop_limit;
+};
+
+static int
+nfp_fl_set_ip6_hop_limit_flow_label(u32 off, __be32 exact, __be32 mask,
+				    struct nfp_fl_set_ipv6_tc_hl_fl *ip_hl_fl)
+{
+	struct ipv6_hop_limit_word *fl_hl_mask;
+	struct ipv6_hop_limit_word *fl_hl;
+
+	switch (off) {
+	case offsetof(struct ipv6hdr, payload_len):
+		fl_hl_mask = (struct ipv6_hop_limit_word *)&mask;
+		fl_hl = (struct ipv6_hop_limit_word *)&exact;
+
+		if (fl_hl_mask->nexthdr || fl_hl_mask->payload_len)
+			return -EOPNOTSUPP;
+
+		ip_hl_fl->ipv6_hop_limit_mask |= fl_hl_mask->hop_limit;
+		ip_hl_fl->ipv6_hop_limit &= ~fl_hl_mask->hop_limit;
+		ip_hl_fl->ipv6_hop_limit |= fl_hl->hop_limit &
+					    fl_hl_mask->hop_limit;
+		break;
+	case round_down(offsetof(struct ipv6hdr, flow_lbl), 4):
+		if (mask & ~IPV6_FLOW_LABEL_MASK ||
+		    exact & ~IPV6_FLOW_LABEL_MASK)
+			return -EOPNOTSUPP;
+
+		ip_hl_fl->ipv6_label_mask |= mask;
+		ip_hl_fl->ipv6_label &= ~mask;
+		ip_hl_fl->ipv6_label |= exact & mask;
+		break;
+	}
+
+	ip_hl_fl->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV6_TC_HL_FL;
+	ip_hl_fl->head.len_lw = sizeof(*ip_hl_fl) >> NFP_FL_LW_SIZ;
+
+	return 0;
+}
+
 static int
 nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off,
 	       struct nfp_fl_set_ipv6_addr *ip_dst,
-	       struct nfp_fl_set_ipv6_addr *ip_src)
+	       struct nfp_fl_set_ipv6_addr *ip_src,
+	       struct nfp_fl_set_ipv6_tc_hl_fl *ip_hl_fl)
 {
 	__be32 exact, mask;
+	int err = 0;
 	u8 word;
 
 	/* We are expecting tcf_pedit to return a big endian value */
@@ -492,7 +537,8 @@ nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off,
 		return -EOPNOTSUPP;
 
 	if (off < offsetof(struct ipv6hdr, saddr)) {
-		return -EOPNOTSUPP;
+		err = nfp_fl_set_ip6_hop_limit_flow_label(off, exact, mask,
+							  ip_hl_fl);
 	} else if (off < offsetof(struct ipv6hdr, daddr)) {
 		word = (off - offsetof(struct ipv6hdr, saddr)) / sizeof(exact);
 		nfp_fl_set_ip6_helper(NFP_FL_ACTION_OPCODE_SET_IPV6_SRC, word,
@@ -506,7 +552,7 @@ nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off,
 		return -EOPNOTSUPP;
 	}
 
-	return 0;
+	return err;
 }
 
 static int
@@ -557,6 +603,7 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 	     char *nfp_action, int *a_len, u32 *csum_updated)
 {
 	struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src;
+	struct nfp_fl_set_ipv6_tc_hl_fl set_ip6_tc_hl_fl;
 	struct nfp_fl_set_ip4_ttl_tos set_ip_ttl_tos;
 	struct nfp_fl_set_ip4_addrs set_ip_addr;
 	struct nfp_fl_set_tport set_tport;
@@ -567,6 +614,7 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 	u32 offset, cmd;
 	u8 ip_proto = 0;
 
+	memset(&set_ip6_tc_hl_fl, 0, sizeof(set_ip6_tc_hl_fl));
 	memset(&set_ip_ttl_tos, 0, sizeof(set_ip_ttl_tos));
 	memset(&set_ip6_dst, 0, sizeof(set_ip6_dst));
 	memset(&set_ip6_src, 0, sizeof(set_ip6_src));
@@ -593,7 +641,7 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 			break;
 		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
 			err = nfp_fl_set_ip6(action, idx, offset, &set_ip6_dst,
-					     &set_ip6_src);
+					     &set_ip6_src, &set_ip6_tc_hl_fl);
 			break;
 		case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
 			err = nfp_fl_set_tport(action, idx, offset, &set_tport,
@@ -644,6 +692,15 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 		*csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR |
 				nfp_fl_csum_l4_to_flag(ip_proto);
 	}
+	if (set_ip6_tc_hl_fl.head.len_lw) {
+		nfp_action += act_size;
+		act_size = sizeof(set_ip6_tc_hl_fl);
+		memcpy(nfp_action, &set_ip6_tc_hl_fl, act_size);
+		*a_len += act_size;
+
+		/* Hardware will automatically fix TCP/UDP checksum. */
+		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
+	}
 	if (set_ip6_dst.head.len_lw && set_ip6_src.head.len_lw) {
 		/* TC compiles set src and dst IPv6 address as a single action,
 		 * the hardware requires this to be 2 separate actions.
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index a00f45b5e16c..3e391555e191 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -68,6 +68,7 @@
 #define NFP_FL_ACTION_OPCODE_SET_IPV4_TTL_TOS	10
 #define NFP_FL_ACTION_OPCODE_SET_IPV6_SRC	11
 #define NFP_FL_ACTION_OPCODE_SET_IPV6_DST	12
+#define NFP_FL_ACTION_OPCODE_SET_IPV6_TC_HL_FL	13
 #define NFP_FL_ACTION_OPCODE_SET_UDP		14
 #define NFP_FL_ACTION_OPCODE_SET_TCP		15
 #define NFP_FL_ACTION_OPCODE_PRE_LAG		16
@@ -83,6 +84,8 @@
 #define NFP_FL_PUSH_VLAN_CFI		BIT(12)
 #define NFP_FL_PUSH_VLAN_VID		GENMASK(11, 0)
 
+#define IPV6_FLOW_LABEL_MASK		cpu_to_be32(0x000fffff)
+
 /* LAG ports */
 #define NFP_FL_LAG_OUT			0xC0DE0000
 
@@ -135,6 +138,17 @@ struct nfp_fl_set_ip4_ttl_tos {
 	__be16 reserved;
 };
 
+struct nfp_fl_set_ipv6_tc_hl_fl {
+	struct nfp_fl_act_head head;
+	u8 ipv6_tc_mask;
+	u8 ipv6_hop_limit_mask;
+	__be16 reserved;
+	u8 ipv6_tc;
+	u8 ipv6_hop_limit;
+	__be32 ipv6_label_mask;
+	__be32 ipv6_label;
+};
+
 struct nfp_fl_set_ipv6_addr {
 	struct nfp_fl_act_head head;
 	__be16 reserved;
-- 
cgit v1.2.3


From e50bfdf74d5f81c81f7a00498aa7fd1cba53b65b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 6 Nov 2018 17:07:30 -0800
Subject: nfp: flower: remove unnecessary iteration over devices

For flower tunnel offloads FW has to be informed about MAC addresses
of tunnel devices.  We use a netdev notifier to keep track of these
addresses.

Remove unnecessary loop over netdevices after notifier is registered.
The intention of the loop was to catch devices which already existed
on the system before nfp driver got loaded, but netdev notifier will
replay NETDEV_REGISTER events.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 8e5bec04d1f9..a3a44f1187d3 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -686,7 +686,6 @@ static int nfp_tun_mac_event_handler(struct notifier_block *nb,
 int nfp_tunnel_config_start(struct nfp_app *app)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	struct net_device *netdev;
 	int err;
 
 	/* Initialise priv data for MAC offloading. */
@@ -715,12 +714,6 @@ int nfp_tunnel_config_start(struct nfp_app *app)
 	if (err)
 		goto err_unreg_mac_nb;
 
-	/* Parse netdevs already registered for MACs that need offloaded. */
-	rtnl_lock();
-	for_each_netdev(&init_net, netdev)
-		nfp_tun_add_to_mac_offload_list(netdev, app);
-	rtnl_unlock();
-
 	return 0;
 
 err_unreg_mac_nb:
-- 
cgit v1.2.3


From a558c982a8ab43ec4262e7fd5e8d462e5fdabe45 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 6 Nov 2018 17:07:31 -0800
Subject: nfp: flower: don't try to nack device unregister events

Returning an error from a notifier means we want to veto the change.
We shouldn't veto NETDEV_UNREGISTER just because we couldn't find
the tracking info for given master.

I can't seem to find a way to trigger this unless we have some
other bug, so it's probably not fix-worthy.

While at it move the checking if the netdev really is of interest
into the handling functions, like we do for other events.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/netronome/nfp/flower/lag_conf.c    | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
index 81dcf5b318ba..dc060748b33b 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
@@ -472,17 +472,25 @@ nfp_fl_lag_schedule_group_remove(struct nfp_fl_lag *lag,
 	schedule_delayed_work(&lag->work, NFP_FL_LAG_DELAY);
 }
 
-static int
+static void
 nfp_fl_lag_schedule_group_delete(struct nfp_fl_lag *lag,
 				 struct net_device *master)
 {
 	struct nfp_fl_lag_group *group;
+	struct nfp_flower_priv *priv;
+
+	priv = container_of(lag, struct nfp_flower_priv, nfp_lag);
+
+	if (!netif_is_bond_master(master))
+		return;
 
 	mutex_lock(&lag->lock);
 	group = nfp_fl_lag_find_group_for_master_with_lag(lag, master);
 	if (!group) {
 		mutex_unlock(&lag->lock);
-		return -ENOENT;
+		nfp_warn(priv->app->cpp, "untracked bond got unregistered %s\n",
+			 netdev_name(master));
+		return;
 	}
 
 	group->to_remove = true;
@@ -490,7 +498,6 @@ nfp_fl_lag_schedule_group_delete(struct nfp_fl_lag *lag,
 	mutex_unlock(&lag->lock);
 
 	schedule_delayed_work(&lag->work, NFP_FL_LAG_DELAY);
-	return 0;
 }
 
 static int
@@ -643,12 +650,8 @@ nfp_fl_lag_netdev_event(struct notifier_block *nb, unsigned long event,
 			return NOTIFY_BAD;
 		return NOTIFY_OK;
 	case NETDEV_UNREGISTER:
-		if (netif_is_bond_master(netdev)) {
-			err = nfp_fl_lag_schedule_group_delete(lag, netdev);
-			if (err)
-				return NOTIFY_BAD;
-			return NOTIFY_OK;
-		}
+		nfp_fl_lag_schedule_group_delete(lag, netdev);
+		return NOTIFY_OK;
 	}
 
 	return NOTIFY_DONE;
-- 
cgit v1.2.3


From 659bb404eb00536cec57315b460c6296e8ebe6ab Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 6 Nov 2018 17:07:32 -0800
Subject: nfp: flower: make nfp_fl_lag_changels_event() void

nfp_fl_lag_changels_event() never fails, and therefore we would
never return NOTIFY_BAD for NETDEV_CHANGELOWERSTATE.  Make this
clearer by changing nfp_fl_lag_changels_event()'s return type
to void.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/lag_conf.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
index dc060748b33b..22b75a519269 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
@@ -582,7 +582,7 @@ nfp_fl_lag_changeupper_event(struct nfp_fl_lag *lag,
 	return 0;
 }
 
-static int
+static void
 nfp_fl_lag_changels_event(struct nfp_fl_lag *lag, struct net_device *netdev,
 			  struct netdev_notifier_changelowerstate_info *info)
 {
@@ -593,18 +593,18 @@ nfp_fl_lag_changels_event(struct nfp_fl_lag *lag, struct net_device *netdev,
 	unsigned long *flags;
 
 	if (!netif_is_lag_port(netdev) || !nfp_netdev_is_nfp_repr(netdev))
-		return 0;
+		return;
 
 	lag_lower_info = info->lower_state_info;
 	if (!lag_lower_info)
-		return 0;
+		return;
 
 	priv = container_of(lag, struct nfp_flower_priv, nfp_lag);
 	repr = netdev_priv(netdev);
 
 	/* Verify that the repr is associated with this app. */
 	if (repr->app != priv->app)
-		return 0;
+		return;
 
 	repr_priv = repr->app_priv;
 	flags = &repr_priv->lag_port_flags;
@@ -624,7 +624,6 @@ nfp_fl_lag_changels_event(struct nfp_fl_lag *lag, struct net_device *netdev,
 	mutex_unlock(&lag->lock);
 
 	schedule_delayed_work(&lag->work, NFP_FL_LAG_DELAY);
-	return 0;
 }
 
 static int
@@ -645,9 +644,7 @@ nfp_fl_lag_netdev_event(struct notifier_block *nb, unsigned long event,
 			return NOTIFY_BAD;
 		return NOTIFY_OK;
 	case NETDEV_CHANGELOWERSTATE:
-		err = nfp_fl_lag_changels_event(lag, netdev, ptr);
-		if (err)
-			return NOTIFY_BAD;
+		nfp_fl_lag_changels_event(lag, netdev, ptr);
 		return NOTIFY_OK;
 	case NETDEV_UNREGISTER:
 		nfp_fl_lag_schedule_group_delete(lag, netdev);
-- 
cgit v1.2.3


From 3e333590400b7bc97449d3db4ac68cf88d9bdafc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 6 Nov 2018 17:07:33 -0800
Subject: nfp: register a notifier handler in a central location for the device

Code interested in networking events registers its own notifier
handlers.  Create one device-wide notifier instance.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_app.c | 47 ++++++++++++++++++++++++++++
 drivers/net/ethernet/netronome/nfp/nfp_app.h | 25 ++++++---------
 2 files changed, 57 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c
index 68a0991aac22..4a1b8f79e731 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c
@@ -136,6 +136,53 @@ nfp_app_reprs_set(struct nfp_app *app, enum nfp_repr_type type,
 	return old;
 }
 
+static int
+nfp_app_netdev_event(struct notifier_block *nb, unsigned long event, void *ptr)
+{
+	struct net_device *netdev;
+	struct nfp_app *app;
+
+	netdev = netdev_notifier_info_to_dev(ptr);
+	app = container_of(nb, struct nfp_app, netdev_nb);
+
+	if (app->type->netdev_event)
+		return app->type->netdev_event(app, netdev, event, ptr);
+	return NOTIFY_DONE;
+}
+
+int nfp_app_start(struct nfp_app *app, struct nfp_net *ctrl)
+{
+	int err;
+
+	app->ctrl = ctrl;
+
+	if (app->type->start) {
+		err = app->type->start(app);
+		if (err)
+			return err;
+	}
+
+	app->netdev_nb.notifier_call = nfp_app_netdev_event;
+	err = register_netdevice_notifier(&app->netdev_nb);
+	if (err)
+		goto err_app_stop;
+
+	return 0;
+
+err_app_stop:
+	if (app->type->stop)
+		app->type->stop(app);
+	return err;
+}
+
+void nfp_app_stop(struct nfp_app *app)
+{
+	unregister_netdevice_notifier(&app->netdev_nb);
+
+	if (app->type->stop)
+		app->type->stop(app);
+}
+
 struct nfp_app *nfp_app_alloc(struct nfp_pf *pf, enum nfp_app_id id)
 {
 	struct nfp_app *app;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h
index 4d6ecf99b1cc..d578d856a009 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h
@@ -69,6 +69,7 @@ extern const struct nfp_app_type app_abm;
  * @port_get_stats_strings:	get strings for extra statistics
  * @start:	start application logic
  * @stop:	stop application logic
+ * @netdev_event:	Netdevice notifier event
  * @ctrl_msg_rx:    control message handler
  * @ctrl_msg_rx_raw:	handler for control messages from data queues
  * @setup_tc:	setup TC ndo
@@ -122,6 +123,9 @@ struct nfp_app_type {
 	int (*start)(struct nfp_app *app);
 	void (*stop)(struct nfp_app *app);
 
+	int (*netdev_event)(struct nfp_app *app, struct net_device *netdev,
+			    unsigned long event, void *ptr);
+
 	void (*ctrl_msg_rx)(struct nfp_app *app, struct sk_buff *skb);
 	void (*ctrl_msg_rx_raw)(struct nfp_app *app, const void *data,
 				unsigned int len);
@@ -151,6 +155,7 @@ struct nfp_app_type {
  * @reprs:	array of pointers to representors
  * @type:	pointer to const application ops and info
  * @ctrl_mtu:	MTU to set on the control vNIC (set in .init())
+ * @netdev_nb:	Netdevice notifier block
  * @priv:	app-specific priv data
  */
 struct nfp_app {
@@ -163,6 +168,9 @@ struct nfp_app {
 
 	const struct nfp_app_type *type;
 	unsigned int ctrl_mtu;
+
+	struct notifier_block netdev_nb;
+
 	void *priv;
 };
 
@@ -264,21 +272,6 @@ nfp_app_repr_change_mtu(struct nfp_app *app, struct net_device *netdev,
 	return app->type->repr_change_mtu(app, netdev, new_mtu);
 }
 
-static inline int nfp_app_start(struct nfp_app *app, struct nfp_net *ctrl)
-{
-	app->ctrl = ctrl;
-	if (!app->type->start)
-		return 0;
-	return app->type->start(app);
-}
-
-static inline void nfp_app_stop(struct nfp_app *app)
-{
-	if (!app->type->stop)
-		return;
-	app->type->stop(app);
-}
-
 static inline const char *nfp_app_name(struct nfp_app *app)
 {
 	if (!app)
@@ -430,6 +423,8 @@ nfp_app_ctrl_msg_alloc(struct nfp_app *app, unsigned int size, gfp_t priority);
 
 struct nfp_app *nfp_app_alloc(struct nfp_pf *pf, enum nfp_app_id id);
 void nfp_app_free(struct nfp_app *app);
+int nfp_app_start(struct nfp_app *app, struct nfp_net *ctrl);
+void nfp_app_stop(struct nfp_app *app);
 
 /* Callbacks shared between apps */
 
-- 
cgit v1.2.3


From 0c665e2bf440a59a2f5c5fe7657f13aef3fe92f2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 6 Nov 2018 17:07:34 -0800
Subject: nfp: flower: use the common netdev notifier

Use driver's common notifier for LAG and tunnel configuration.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/netronome/nfp/flower/lag_conf.c   | 14 +++-----
 drivers/net/ethernet/netronome/nfp/flower/main.c   | 23 +++++++++----
 drivers/net/ethernet/netronome/nfp/flower/main.h   | 10 +++---
 .../ethernet/netronome/nfp/flower/tunnel_conf.c    | 38 +++-------------------
 4 files changed, 30 insertions(+), 55 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
index 22b75a519269..5db838f45694 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
@@ -626,17 +626,13 @@ nfp_fl_lag_changels_event(struct nfp_fl_lag *lag, struct net_device *netdev,
 	schedule_delayed_work(&lag->work, NFP_FL_LAG_DELAY);
 }
 
-static int
-nfp_fl_lag_netdev_event(struct notifier_block *nb, unsigned long event,
-			void *ptr)
+int nfp_flower_lag_netdev_event(struct nfp_flower_priv *priv,
+				struct net_device *netdev,
+				unsigned long event, void *ptr)
 {
-	struct net_device *netdev;
-	struct nfp_fl_lag *lag;
+	struct nfp_fl_lag *lag = &priv->nfp_lag;
 	int err;
 
-	netdev = netdev_notifier_info_to_dev(ptr);
-	lag = container_of(nb, struct nfp_fl_lag, lag_nb);
-
 	switch (event) {
 	case NETDEV_CHANGEUPPER:
 		err = nfp_fl_lag_changeupper_event(lag, ptr);
@@ -673,8 +669,6 @@ void nfp_flower_lag_init(struct nfp_fl_lag *lag)
 
 	/* 0 is a reserved batch version so increment to first valid value. */
 	nfp_fl_increment_version(lag);
-
-	lag->lag_nb.notifier_call = nfp_fl_lag_netdev_event;
 }
 
 void nfp_flower_lag_cleanup(struct nfp_fl_lag *lag)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 3a54728d2ea6..2ad00773750f 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -661,23 +661,30 @@ static int nfp_flower_start(struct nfp_app *app)
 		err = nfp_flower_lag_reset(&app_priv->nfp_lag);
 		if (err)
 			return err;
-
-		err = register_netdevice_notifier(&app_priv->nfp_lag.lag_nb);
-		if (err)
-			return err;
 	}
 
 	return nfp_tunnel_config_start(app);
 }
 
 static void nfp_flower_stop(struct nfp_app *app)
+{
+	nfp_tunnel_config_stop(app);
+}
+
+static int
+nfp_flower_netdev_event(struct nfp_app *app, struct net_device *netdev,
+			unsigned long event, void *ptr)
 {
 	struct nfp_flower_priv *app_priv = app->priv;
+	int ret;
 
-	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG)
-		unregister_netdevice_notifier(&app_priv->nfp_lag.lag_nb);
+	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG) {
+		ret = nfp_flower_lag_netdev_event(app_priv, netdev, event, ptr);
+		if (ret & NOTIFY_STOP_MASK)
+			return ret;
+	}
 
-	nfp_tunnel_config_stop(app);
+	return nfp_tunnel_mac_event_handler(app, netdev, event, ptr);
 }
 
 const struct nfp_app_type app_flower = {
@@ -708,6 +715,8 @@ const struct nfp_app_type app_flower = {
 	.start		= nfp_flower_start,
 	.stop		= nfp_flower_stop,
 
+	.netdev_event	= nfp_flower_netdev_event,
+
 	.ctrl_msg_rx	= nfp_flower_cmsg_rx,
 
 	.sriov_enable	= nfp_flower_sriov_enable,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 90045bab95bf..0f6f1675f6f1 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -72,7 +72,6 @@ struct nfp_mtu_conf {
 
 /**
  * struct nfp_fl_lag - Flower APP priv data for link aggregation
- * @lag_nb:		Notifier to track master/slave events
  * @work:		Work queue for writing configs to the HW
  * @lock:		Lock to protect lag_group_list
  * @group_list:		List of all master/slave groups offloaded
@@ -85,7 +84,6 @@ struct nfp_mtu_conf {
  *			retransmission
  */
 struct nfp_fl_lag {
-	struct notifier_block lag_nb;
 	struct delayed_work work;
 	struct mutex lock;
 	struct list_head group_list;
@@ -126,7 +124,6 @@ struct nfp_fl_lag {
  * @nfp_neigh_off_lock:	Lock for the neighbour address list
  * @nfp_mac_off_ids:	IDA to manage id assignment for offloaded macs
  * @nfp_mac_off_count:	Number of MACs in address list
- * @nfp_tun_mac_nb:	Notifier to monitor link state
  * @nfp_tun_neigh_nb:	Notifier to monitor neighbour state
  * @reify_replies:	atomically stores the number of replies received
  *			from firmware for repr reify
@@ -160,7 +157,6 @@ struct nfp_flower_priv {
 	spinlock_t nfp_neigh_off_lock;
 	struct ida nfp_mac_off_ids;
 	int nfp_mac_off_count;
-	struct notifier_block nfp_tun_mac_nb;
 	struct notifier_block nfp_tun_neigh_nb;
 	atomic_t reify_replies;
 	wait_queue_head_t reify_wait_queue;
@@ -252,6 +248,9 @@ void nfp_flower_rx_flow_stats(struct nfp_app *app, struct sk_buff *skb);
 
 int nfp_tunnel_config_start(struct nfp_app *app);
 void nfp_tunnel_config_stop(struct nfp_app *app);
+int nfp_tunnel_mac_event_handler(struct nfp_app *app,
+				 struct net_device *netdev,
+				 unsigned long event, void *ptr);
 void nfp_tunnel_write_macs(struct nfp_app *app);
 void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4);
 void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4);
@@ -262,6 +261,9 @@ int nfp_flower_setup_tc_egress_cb(enum tc_setup_type type, void *type_data,
 void nfp_flower_lag_init(struct nfp_fl_lag *lag);
 void nfp_flower_lag_cleanup(struct nfp_fl_lag *lag);
 int nfp_flower_lag_reset(struct nfp_fl_lag *lag);
+int nfp_flower_lag_netdev_event(struct nfp_flower_priv *priv,
+				struct net_device *netdev,
+				unsigned long event, void *ptr);
 bool nfp_flower_lag_unprocessed_msg(struct nfp_app *app, struct sk_buff *skb);
 int nfp_flower_lag_populate_pre_action(struct nfp_app *app,
 				       struct net_device *master,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index a3a44f1187d3..fb6442d820b5 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -652,29 +652,16 @@ static void nfp_tun_add_to_mac_offload_list(struct net_device *netdev,
 	mutex_unlock(&priv->nfp_mac_off_lock);
 }
 
-static int nfp_tun_mac_event_handler(struct notifier_block *nb,
-				     unsigned long event, void *ptr)
+int nfp_tunnel_mac_event_handler(struct nfp_app *app,
+				 struct net_device *netdev,
+				 unsigned long event, void *ptr)
 {
-	struct nfp_flower_priv *app_priv;
-	struct net_device *netdev;
-	struct nfp_app *app;
-
 	if (event == NETDEV_DOWN || event == NETDEV_UNREGISTER) {
-		app_priv = container_of(nb, struct nfp_flower_priv,
-					nfp_tun_mac_nb);
-		app = app_priv->app;
-		netdev = netdev_notifier_info_to_dev(ptr);
-
 		/* If non-nfp netdev then free its offload index. */
 		if (nfp_tun_is_netdev_to_offload(netdev))
 			nfp_tun_del_mac_idx(app, netdev->ifindex);
 	} else if (event == NETDEV_UP || event == NETDEV_CHANGEADDR ||
 		   event == NETDEV_REGISTER) {
-		app_priv = container_of(nb, struct nfp_flower_priv,
-					nfp_tun_mac_nb);
-		app = app_priv->app;
-		netdev = netdev_notifier_info_to_dev(ptr);
-
 		nfp_tun_add_to_mac_offload_list(netdev, app);
 
 		/* Force a list write to keep NFP up to date. */
@@ -686,13 +673,11 @@ static int nfp_tun_mac_event_handler(struct notifier_block *nb,
 int nfp_tunnel_config_start(struct nfp_app *app)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	int err;
 
 	/* Initialise priv data for MAC offloading. */
 	priv->nfp_mac_off_count = 0;
 	mutex_init(&priv->nfp_mac_off_lock);
 	INIT_LIST_HEAD(&priv->nfp_mac_off_list);
-	priv->nfp_tun_mac_nb.notifier_call = nfp_tun_mac_event_handler;
 	mutex_init(&priv->nfp_mac_index_lock);
 	INIT_LIST_HEAD(&priv->nfp_mac_index_list);
 	ida_init(&priv->nfp_mac_off_ids);
@@ -706,21 +691,7 @@ int nfp_tunnel_config_start(struct nfp_app *app)
 	INIT_LIST_HEAD(&priv->nfp_neigh_off_list);
 	priv->nfp_tun_neigh_nb.notifier_call = nfp_tun_neigh_event_handler;
 
-	err = register_netdevice_notifier(&priv->nfp_tun_mac_nb);
-	if (err)
-		goto err_free_mac_ida;
-
-	err = register_netevent_notifier(&priv->nfp_tun_neigh_nb);
-	if (err)
-		goto err_unreg_mac_nb;
-
-	return 0;
-
-err_unreg_mac_nb:
-	unregister_netdevice_notifier(&priv->nfp_tun_mac_nb);
-err_free_mac_ida:
-	ida_destroy(&priv->nfp_mac_off_ids);
-	return err;
+	return register_netevent_notifier(&priv->nfp_tun_neigh_nb);
 }
 
 void nfp_tunnel_config_stop(struct nfp_app *app)
@@ -732,7 +703,6 @@ void nfp_tunnel_config_stop(struct nfp_app *app)
 	struct nfp_ipv4_addr_entry *ip_entry;
 	struct list_head *ptr, *storage;
 
-	unregister_netdevice_notifier(&priv->nfp_tun_mac_nb);
 	unregister_netevent_notifier(&priv->nfp_tun_neigh_nb);
 
 	/* Free any memory that may be occupied by MAC list. */
-- 
cgit v1.2.3


From f601a85bd7883708f48911d8c88e69fe5bde2b4d Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 7 Nov 2018 02:33:53 +0000
Subject: net: hns3: Remove set but not used variable 'reset_level'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c: In function 'hclge_log_and_clear_ppp_error':
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c:821:24: warning:
 variable 'reset_level' set but not used [-Wunused-but-set-variable]
  enum hnae3_reset_type reset_level = HNAE3_NONE_RESET;

It never used since introduction in commit
01865a50d78f ("net: hns3: Add enable and process hw errors of TM scheduler")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 123c37e653f3..6da9e22d82d0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -818,7 +818,6 @@ static void hclge_process_igu_egu_error(struct hclge_dev *hdev,
 static int hclge_log_and_clear_ppp_error(struct hclge_dev *hdev, u32 cmd,
 					 enum hclge_err_int_type int_type)
 {
-	enum hnae3_reset_type reset_level = HNAE3_NONE_RESET;
 	struct device *dev = &hdev->pdev->dev;
 	const struct hclge_hw_error *hw_err_lst1, *hw_err_lst2, *hw_err_lst3;
 	struct hclge_desc desc[2];
@@ -848,23 +847,17 @@ static int hclge_log_and_clear_ppp_error(struct hclge_dev *hdev, u32 cmd,
 	}
 
 	err_sts = le32_to_cpu(desc[0].data[2]);
-	if (err_sts) {
+	if (err_sts)
 		hclge_log_error(dev, hw_err_lst1, err_sts);
-		reset_level = HNAE3_FUNC_RESET;
-	}
 
 	err_sts = le32_to_cpu(desc[0].data[3]);
-	if (err_sts) {
+	if (err_sts)
 		hclge_log_error(dev, hw_err_lst2, err_sts);
-		reset_level = HNAE3_FUNC_RESET;
-	}
 
 	if (cmd == HCLGE_PPP_CMD0_INT_CMD) {
 		err_sts = (le32_to_cpu(desc[0].data[4]) >> 8) & 0x3;
-		if (err_sts) {
+		if (err_sts)
 			hclge_log_error(dev, hw_err_lst3, err_sts);
-			reset_level = HNAE3_FUNC_RESET;
-		}
 	}
 
 	/* clear PPP INT */
-- 
cgit v1.2.3


From f96afa767baffba7645f5e10998f5178948bb9aa Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Wed, 7 Nov 2018 12:28:45 +0000
Subject: selftests/bpf: enable (uncomment) all tests in test_libbpf.sh

libbpf is now able to load successfully test_l4lb_noinline.o and
samples/bpf/tracex3_kern.o.

For the test_l4lb_noinline, uncomment related tests from test_libbpf.c
and remove the associated "TODO".

For tracex3_kern.o, instead of loading a program from samples/bpf/ that
might not have been compiled at this stage, try loading a program from
BPF selftests. Since this test case is about loading a program compiled
without the "-target bpf" flag, change the Makefile to compile one
program accordingly (instead of passing the flag for compiling all
programs).

Regarding test_xdp_noinline.o: in its current shape the program fails to
load because it provides no version section, but the loader needs one.
The test was added to make sure that libbpf could load XDP programs even
if they do not provide a version number in a dedicated section. But
libbpf is already capable of doing that: in our case loading fails
because the loader does not know that this is an XDP program (it does
not need to, since it does not attach the program). So trying to load
test_xdp_noinline.o does not bring much here: just delete this subtest.

For the record, the error message obtained with tracex3_kern.o was
fixed by commit e3d91b0ca523 ("tools/libbpf: handle issues with bpf ELF
objects containing .eh_frames")

I have not been abled to reproduce the "libbpf: incorrect bpf_call
opcode" error for test_l4lb_noinline.o, even with the version of libbpf
present at the time when test_libbpf.sh and test_libbpf_open.c were
created.

RFC -> v1:
- Compile test_xdp without the "-target bpf" flag, and try to load it
  instead of ../../samples/bpf/tracex3_kern.o.
- Delete test_xdp_noinline.o subtest.

Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile       | 10 ++++++++++
 tools/testing/selftests/bpf/test_libbpf.sh | 14 ++++----------
 2 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e39dfb4e7970..ecd79b7fb107 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -135,6 +135,16 @@ endif
 endif
 endif
 
+# Have one program compiled without "-target bpf" to test whether libbpf loads
+# it successfully
+$(OUTPUT)/test_xdp.o: test_xdp.c
+	$(CLANG) $(CLANG_FLAGS) \
+		-O2 -emit-llvm -c $< -o - | \
+	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
+ifeq ($(DWARF2BTF),y)
+	$(BTF_PAHOLE) -J $@
+endif
+
 $(OUTPUT)/%.o: %.c
 	$(CLANG) $(CLANG_FLAGS) \
 		 -O2 -target bpf -emit-llvm -c $< -o - |      \
diff --git a/tools/testing/selftests/bpf/test_libbpf.sh b/tools/testing/selftests/bpf/test_libbpf.sh
index 156d89f1edcc..2989b2e2d856 100755
--- a/tools/testing/selftests/bpf/test_libbpf.sh
+++ b/tools/testing/selftests/bpf/test_libbpf.sh
@@ -33,17 +33,11 @@ trap exit_handler 0 2 3 6 9
 
 libbpf_open_file test_l4lb.o
 
-# TODO: fix libbpf to load noinline functions
-# [warning] libbpf: incorrect bpf_call opcode
-#libbpf_open_file test_l4lb_noinline.o
+# Load a program with BPF-to-BPF calls
+libbpf_open_file test_l4lb_noinline.o
 
-# TODO: fix test_xdp_meta.c to load with libbpf
-# [warning] libbpf: test_xdp_meta.o doesn't provide kernel version
-#libbpf_open_file test_xdp_meta.o
-
-# TODO: fix libbpf to handle .eh_frame
-# [warning] libbpf: relocation failed: no section(10)
-#libbpf_open_file ../../../../samples/bpf/tracex3_kern.o
+# Load a program compiled without the "-target bpf" flag
+libbpf_open_file test_xdp.o
 
 # Success
 exit 0
-- 
cgit v1.2.3


From 8302b9bd31d29f29dd24dd6b1e1e5682c302c11c Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Wed, 7 Nov 2018 12:29:30 +0000
Subject: tools: bpftool: adjust rlimit RLIMIT_MEMLOCK when loading programs,
 maps

The limit for memory locked in the kernel by a process is usually set to
64 kbytes by default. This can be an issue when creating large BPF maps
and/or loading many programs. A workaround is to raise this limit for
the current process before trying to create a new BPF map. Changing the
hard limit requires the CAP_SYS_RESOURCE and can usually only be done by
root user (for non-root users, a call to setrlimit fails (and sets
errno) and the program simply goes on with its rlimit unchanged).

There is no API to get the current amount of memory locked for a user,
therefore we cannot raise the limit only when required. One solution,
used by bcc, is to try to create the map, and on getting a EPERM error,
raising the limit to infinity before giving another try. Another
approach, used in iproute2, is to raise the limit in all cases, before
trying to create the map.

Here we do the same as in iproute2: the rlimit is raised to infinity
before trying to load programs or to create maps with bpftool.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/common.c | 8 ++++++++
 tools/bpf/bpftool/main.h   | 2 ++
 tools/bpf/bpftool/map.c    | 2 ++
 tools/bpf/bpftool/prog.c   | 2 ++
 4 files changed, 14 insertions(+)

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 25af85304ebe..1149565be4b1 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -46,6 +46,7 @@
 #include <linux/magic.h>
 #include <net/if.h>
 #include <sys/mount.h>
+#include <sys/resource.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
@@ -99,6 +100,13 @@ static bool is_bpffs(char *path)
 	return (unsigned long)st_fs.f_type == BPF_FS_MAGIC;
 }
 
+void set_max_rlimit(void)
+{
+	struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
+
+	setrlimit(RLIMIT_MEMLOCK, &rinf);
+}
+
 static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
 {
 	bool bind_done = false;
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 28322ace2856..14857c273bf6 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -100,6 +100,8 @@ bool is_prefix(const char *pfx, const char *str);
 void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep);
 void usage(void) __noreturn;
 
+void set_max_rlimit(void);
+
 struct pinned_obj_table {
 	DECLARE_HASHTABLE(table, 16);
 };
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 7bf38f0e152e..101b8a881225 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -1140,6 +1140,8 @@ static int do_create(int argc, char **argv)
 		return -1;
 	}
 
+	set_max_rlimit();
+
 	fd = bpf_create_map_xattr(&attr);
 	if (fd < 0) {
 		p_err("map create failed: %s", strerror(errno));
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 5302ee282409..b9b84553bec4 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -995,6 +995,8 @@ static int do_load(int argc, char **argv)
 		goto err_close_obj;
 	}
 
+	set_max_rlimit();
+
 	err = bpf_object__load(obj);
 	if (err) {
 		p_err("failed to load object file");
-- 
cgit v1.2.3


From bce6a14996f991e570d973179b5ff57544efaa9a Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Mon, 29 Oct 2018 14:14:41 -0700
Subject: bpf_load: add map name to load_maps error message

To help when debugging bpf/xdp load issues, have the load_map()
error message include the number and name of the map that
failed.

Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/bpf_load.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index e6d7e0fe155b..5c052b9ea63f 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -284,8 +284,8 @@ static int load_maps(struct bpf_map_data *maps, int nr_maps,
 							numa_node);
 		}
 		if (map_fd[i] < 0) {
-			printf("failed to create a map: %d %s\n",
-			       errno, strerror(errno));
+			printf("failed to create map %d (%s): %d %s\n",
+			       i, maps[i].name, errno, strerror(errno));
 			return 1;
 		}
 		maps[i].fd = map_fd[i];
-- 
cgit v1.2.3


From 3c82a21f4320c8d54cf6456b27c8d49e5ffb722e Mon Sep 17 00:00:00 2001
From: Robert Shearman <rshearma@vyatta.att-mail.com>
Date: Wed, 7 Nov 2018 15:36:02 +0000
Subject: net: allow binding socket in a VRF when there's an unbound socket

Change the inet socket lookup to avoid packets arriving on a device
enslaved to an l3mdev from matching unbound sockets by removing the
wildcard for non sk_bound_dev_if and instead relying on check against
the secondary device index, which will be 0 when the input device is
not enslaved to an l3mdev and so match against an unbound socket and
not match when the input device is enslaved.

Change the socket binding to take the l3mdev into account to allow an
unbound socket to not conflict sockets bound to an l3mdev given the
datapath isolation now guaranteed.

Signed-off-by: Robert Shearman <rshearma@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/vrf.txt |  9 +++++----
 include/net/inet6_hashtables.h   |  5 ++---
 include/net/inet_hashtables.h    | 13 ++++++-------
 include/net/inet_sock.h          | 13 +++++++++++++
 net/ipv4/inet_connection_sock.c  | 13 ++++++++++---
 net/ipv4/inet_hashtables.c       | 20 +++++++++++++++-----
 6 files changed, 51 insertions(+), 22 deletions(-)

diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt
index 8ff7b4c8f91b..d4b129402d57 100644
--- a/Documentation/networking/vrf.txt
+++ b/Documentation/networking/vrf.txt
@@ -103,6 +103,11 @@ VRF device:
 
 or to specify the output device using cmsg and IP_PKTINFO.
 
+By default the scope of the port bindings for unbound sockets is
+limited to the default VRF. That is, it will not be matched by packets
+arriving on interfaces enslaved to an l3mdev and processes may bind to
+the same port if they bind to an l3mdev.
+
 TCP & UDP services running in the default VRF context (ie., not bound
 to any VRF device) can work across all VRF domains by enabling the
 tcp_l3mdev_accept and udp_l3mdev_accept sysctl options:
@@ -112,10 +117,6 @@ tcp_l3mdev_accept and udp_l3mdev_accept sysctl options:
 netfilter rules on the VRF device can be used to limit access to services
 running in the default VRF context as well.
 
-The default VRF does not have limited scope with respect to port bindings.
-That is, if a process does a wildcard bind to a port in the default VRF it
-owns the port across all VRF domains within the network namespace.
-
 ################################################################################
 
 Using iproute2 for VRFs
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 6e91e38a31da..9db98af46985 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -115,9 +115,8 @@ int inet6_hash(struct sock *sk);
 	 ((__sk)->sk_family == AF_INET6)			&&	\
 	 ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr))		&&	\
 	 ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr))	&&	\
-	 (!(__sk)->sk_bound_dev_if	||				\
-	   ((__sk)->sk_bound_dev_if == (__dif))	||			\
-	   ((__sk)->sk_bound_dev_if == (__sdif)))		&&	\
+	 (((__sk)->sk_bound_dev_if == (__dif))	||			\
+	  ((__sk)->sk_bound_dev_if == (__sdif)))		&&	\
 	 net_eq(sock_net(__sk), (__net)))
 
 #endif /* _INET6_HASHTABLES_H */
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 9141e95529e7..4ae060b4bac2 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -79,6 +79,7 @@ struct inet_ehash_bucket {
 
 struct inet_bind_bucket {
 	possible_net_t		ib_net;
+	int			l3mdev;
 	unsigned short		port;
 	signed char		fastreuse;
 	signed char		fastreuseport;
@@ -191,7 +192,7 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 struct inet_bind_bucket *
 inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
 			struct inet_bind_hashbucket *head,
-			const unsigned short snum);
+			const unsigned short snum, int l3mdev);
 void inet_bind_bucket_destroy(struct kmem_cache *cachep,
 			      struct inet_bind_bucket *tb);
 
@@ -282,9 +283,8 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 #define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
 	(((__sk)->sk_portpair == (__ports))			&&	\
 	 ((__sk)->sk_addrpair == (__cookie))			&&	\
-	 (!(__sk)->sk_bound_dev_if	||				\
-	   ((__sk)->sk_bound_dev_if == (__dif))			||	\
-	   ((__sk)->sk_bound_dev_if == (__sdif)))		&&	\
+	 (((__sk)->sk_bound_dev_if == (__dif))			||	\
+	  ((__sk)->sk_bound_dev_if == (__sdif)))		&&	\
 	 net_eq(sock_net(__sk), (__net)))
 #else /* 32-bit arch */
 #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
@@ -294,9 +294,8 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 	(((__sk)->sk_portpair == (__ports))		&&		\
 	 ((__sk)->sk_daddr	== (__saddr))		&&		\
 	 ((__sk)->sk_rcv_saddr	== (__daddr))		&&		\
-	 (!(__sk)->sk_bound_dev_if	||				\
-	   ((__sk)->sk_bound_dev_if == (__dif))		||		\
-	   ((__sk)->sk_bound_dev_if == (__sdif)))	&&		\
+	 (((__sk)->sk_bound_dev_if == (__dif))		||		\
+	  ((__sk)->sk_bound_dev_if == (__sdif)))	&&		\
 	 net_eq(sock_net(__sk), (__net)))
 #endif /* 64-bit arch */
 
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index a80fd0ac4563..ed3f723af00b 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -130,6 +130,19 @@ static inline int inet_request_bound_dev_if(const struct sock *sk,
 	return sk->sk_bound_dev_if;
 }
 
+static inline int inet_sk_bound_l3mdev(const struct sock *sk)
+{
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	struct net *net = sock_net(sk);
+
+	if (!net->ipv4.sysctl_tcp_l3mdev_accept)
+		return l3mdev_master_ifindex_by_index(net,
+						      sk->sk_bound_dev_if);
+#endif
+
+	return 0;
+}
+
 struct inet_cork {
 	unsigned int		flags;
 	__be32			addr;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 15e7f7915a21..5c63449130d9 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -183,7 +183,9 @@ inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *
 	int i, low, high, attempt_half;
 	struct inet_bind_bucket *tb;
 	u32 remaining, offset;
+	int l3mdev;
 
+	l3mdev = inet_sk_bound_l3mdev(sk);
 	attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
 other_half_scan:
 	inet_get_local_port_range(net, &low, &high);
@@ -219,7 +221,8 @@ other_parity_scan:
 						  hinfo->bhash_size)];
 		spin_lock_bh(&head->lock);
 		inet_bind_bucket_for_each(tb, &head->chain)
-			if (net_eq(ib_net(tb), net) && tb->port == port) {
+			if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+			    tb->port == port) {
 				if (!inet_csk_bind_conflict(sk, tb, false, false))
 					goto success;
 				goto next_port;
@@ -293,6 +296,9 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 	struct net *net = sock_net(sk);
 	struct inet_bind_bucket *tb = NULL;
 	kuid_t uid = sock_i_uid(sk);
+	int l3mdev;
+
+	l3mdev = inet_sk_bound_l3mdev(sk);
 
 	if (!port) {
 		head = inet_csk_find_open_port(sk, &tb, &port);
@@ -306,11 +312,12 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 					  hinfo->bhash_size)];
 	spin_lock_bh(&head->lock);
 	inet_bind_bucket_for_each(tb, &head->chain)
-		if (net_eq(ib_net(tb), net) && tb->port == port)
+		if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+		    tb->port == port)
 			goto tb_found;
 tb_not_found:
 	tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
-				     net, head, port);
+				     net, head, port, l3mdev);
 	if (!tb)
 		goto fail_unlock;
 tb_found:
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 411dd7a90046..40d722ab1738 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -65,12 +65,14 @@ static u32 sk_ehashfn(const struct sock *sk)
 struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
 						 struct net *net,
 						 struct inet_bind_hashbucket *head,
-						 const unsigned short snum)
+						 const unsigned short snum,
+						 int l3mdev)
 {
 	struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
 
 	if (tb) {
 		write_pnet(&tb->ib_net, net);
+		tb->l3mdev    = l3mdev;
 		tb->port      = snum;
 		tb->fastreuse = 0;
 		tb->fastreuseport = 0;
@@ -135,6 +137,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
 			table->bhash_size);
 	struct inet_bind_hashbucket *head = &table->bhash[bhash];
 	struct inet_bind_bucket *tb;
+	int l3mdev;
 
 	spin_lock(&head->lock);
 	tb = inet_csk(sk)->icsk_bind_hash;
@@ -143,6 +146,8 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
 		return -ENOENT;
 	}
 	if (tb->port != port) {
+		l3mdev = inet_sk_bound_l3mdev(sk);
+
 		/* NOTE: using tproxy and redirecting skbs to a proxy
 		 * on a different listener port breaks the assumption
 		 * that the listener socket's icsk_bind_hash is the same
@@ -150,12 +155,13 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
 		 * create a new bind bucket for the child here. */
 		inet_bind_bucket_for_each(tb, &head->chain) {
 			if (net_eq(ib_net(tb), sock_net(sk)) &&
-			    tb->port == port)
+			    tb->l3mdev == l3mdev && tb->port == port)
 				break;
 		}
 		if (!tb) {
 			tb = inet_bind_bucket_create(table->bind_bucket_cachep,
-						     sock_net(sk), head, port);
+						     sock_net(sk), head, port,
+						     l3mdev);
 			if (!tb) {
 				spin_unlock(&head->lock);
 				return -ENOMEM;
@@ -675,6 +681,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	u32 remaining, offset;
 	int ret, i, low, high;
 	static u32 hint;
+	int l3mdev;
 
 	if (port) {
 		head = &hinfo->bhash[inet_bhashfn(net, port,
@@ -693,6 +700,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		return ret;
 	}
 
+	l3mdev = inet_sk_bound_l3mdev(sk);
+
 	inet_get_local_port_range(net, &low, &high);
 	high++; /* [32768, 60999] -> [32768, 61000[ */
 	remaining = high - low;
@@ -719,7 +728,8 @@ other_parity_scan:
 		 * the established check is already unique enough.
 		 */
 		inet_bind_bucket_for_each(tb, &head->chain) {
-			if (net_eq(ib_net(tb), net) && tb->port == port) {
+			if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+			    tb->port == port) {
 				if (tb->fastreuse >= 0 ||
 				    tb->fastreuseport >= 0)
 					goto next_port;
@@ -732,7 +742,7 @@ other_parity_scan:
 		}
 
 		tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
-					     net, head, port);
+					     net, head, port, l3mdev);
 		if (!tb) {
 			spin_unlock_bh(&head->lock);
 			return -ENOMEM;
-- 
cgit v1.2.3


From e78190581aff7c96fbd6324aa633170934650b65 Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@vyatta.att-mail.com>
Date: Wed, 7 Nov 2018 15:36:03 +0000
Subject: net: ensure unbound stream socket to be chosen when not in a VRF

The commit a04a480d4392 ("net: Require exact match for TCP socket
lookups if dif is l3mdev") only ensures that the correct socket is
selected for packets in a VRF. However, there is no guarantee that
the unbound socket will be selected for packets when not in a VRF.
By checking for a device match in compute_score() also for the case
when there is no bound device and attaching a score to this, the
unbound socket is selected. And if a failure is returned when there
is no device match, this ensures that bound sockets are never selected,
even if there is no unbound socket.

Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h | 11 +++++++++++
 include/net/inet_sock.h       |  8 ++++++++
 net/ipv4/inet_hashtables.c    | 14 ++++++--------
 net/ipv6/inet6_hashtables.c   | 14 ++++++--------
 4 files changed, 31 insertions(+), 16 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 4ae060b4bac2..0ce460e93dc4 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -189,6 +189,17 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 	hashinfo->ehash_locks = NULL;
 }
 
+static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+					int dif, int sdif)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	return inet_bound_dev_eq(!!net->ipv4.sysctl_tcp_l3mdev_accept,
+				 bound_dev_if, dif, sdif);
+#else
+	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
+#endif
+}
+
 struct inet_bind_bucket *
 inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
 			struct inet_bind_hashbucket *head,
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index ed3f723af00b..e8eef85006aa 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -143,6 +143,14 @@ static inline int inet_sk_bound_l3mdev(const struct sock *sk)
 	return 0;
 }
 
+static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if,
+				     int dif, int sdif)
+{
+	if (!bound_dev_if)
+		return !sdif || l3mdev_accept;
+	return bound_dev_if == dif || bound_dev_if == sdif;
+}
+
 struct inet_cork {
 	unsigned int		flags;
 	__be32			addr;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 40d722ab1738..13890d5bfc34 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -235,6 +235,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
 {
 	int score = -1;
 	struct inet_sock *inet = inet_sk(sk);
+	bool dev_match;
 
 	if (net_eq(sock_net(sk), net) && inet->inet_num == hnum &&
 			!ipv6_only_sock(sk)) {
@@ -245,15 +246,12 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				return -1;
 			score += 4;
 		}
-		if (sk->sk_bound_dev_if || exact_dif) {
-			bool dev_match = (sk->sk_bound_dev_if == dif ||
-					  sk->sk_bound_dev_if == sdif);
+		dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+						 dif, sdif);
+		if (!dev_match)
+			return -1;
+		score += 4;
 
-			if (!dev_match)
-				return -1;
-			if (sk->sk_bound_dev_if)
-				score += 4;
-		}
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())
 			score++;
 	}
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 3d7c7460a0c5..5eeeba7181a1 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -99,6 +99,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				const int dif, const int sdif, bool exact_dif)
 {
 	int score = -1;
+	bool dev_match;
 
 	if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
 	    sk->sk_family == PF_INET6) {
@@ -109,15 +110,12 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				return -1;
 			score++;
 		}
-		if (sk->sk_bound_dev_if || exact_dif) {
-			bool dev_match = (sk->sk_bound_dev_if == dif ||
-					  sk->sk_bound_dev_if == sdif);
+		dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+						 dif, sdif);
+		if (!dev_match)
+			return -1;
+		score++;
 
-			if (!dev_match)
-				return -1;
-			if (sk->sk_bound_dev_if)
-				score++;
-		}
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())
 			score++;
 	}
-- 
cgit v1.2.3


From 6da5b0f027a825df2aebc1927a27bda185dc03d4 Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@vyatta.att-mail.com>
Date: Wed, 7 Nov 2018 15:36:04 +0000
Subject: net: ensure unbound datagram socket to be chosen when not in a VRF

Ensure an unbound datagram skt is chosen when not in a VRF. The check
for a device match in compute_score() for UDP must be performed when
there is no device match. For this, a failure is returned when there is
no device match. This ensures that bound sockets are never selected,
even if there is no unbound socket.

Allow IPv6 packets to be sent over a datagram skt bound to a VRF. These
packets are currently blocked, as flowi6_oif was set to that of the
master vrf device, and the ipi6_ifindex is that of the slave device.
Allow these packets to be sent by checking the device with ipi6_ifindex
has the same L3 scope as that of the bound device of the skt, which is
the master vrf device. Note that this check always succeeds if the skt
is unbound.

Even though the right datagram skt is now selected by compute_score(),
a different skt is being returned that is bound to the wrong vrf. The
difference between these and stream sockets is the handling of the skt
option for SO_REUSEPORT. While the handling when adding a skt for reuse
correctly checks that the bound device of the skt is a match, the skts
in the hashslot are already incorrect. So for the same hash, a skt for
the wrong vrf may be selected for the required port. The root cause is
that the skt is immediately placed into a slot when it is created,
but when the skt is then bound using SO_BINDTODEVICE, it remains in the
same slot. The solution is to move the skt to the correct slot by
forcing a rehash.

Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h   | 11 +++++++++++
 net/core/sock.c     |  2 ++
 net/ipv4/udp.c      | 15 ++++++---------
 net/ipv6/datagram.c | 10 +++++++---
 net/ipv6/udp.c      | 14 +++++---------
 5 files changed, 31 insertions(+), 21 deletions(-)

diff --git a/include/net/udp.h b/include/net/udp.h
index 9e82cb391dea..a496e441645e 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -252,6 +252,17 @@ static inline int udp_rqueue_get(struct sock *sk)
 	return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit);
 }
 
+static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+				       int dif, int sdif)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	return inet_bound_dev_eq(!!net->ipv4.sysctl_udp_l3mdev_accept,
+				 bound_dev_if, dif, sdif);
+#else
+	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
+#endif
+}
+
 /* net/ipv4/udp.c */
 void udp_destruct_sock(struct sock *sk);
 void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
diff --git a/net/core/sock.c b/net/core/sock.c
index 080a880a1761..7b304e454a38 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -567,6 +567,8 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval,
 
 	lock_sock(sk);
 	sk->sk_bound_dev_if = index;
+	if (sk->sk_prot->rehash)
+		sk->sk_prot->rehash(sk);
 	sk_dst_reset(sk);
 	release_sock(sk);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1976fddb9e00..cf73c9194bb6 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -371,6 +371,7 @@ static int compute_score(struct sock *sk, struct net *net,
 {
 	int score;
 	struct inet_sock *inet;
+	bool dev_match;
 
 	if (!net_eq(sock_net(sk), net) ||
 	    udp_sk(sk)->udp_port_hash != hnum ||
@@ -398,15 +399,11 @@ static int compute_score(struct sock *sk, struct net *net,
 		score += 4;
 	}
 
-	if (sk->sk_bound_dev_if || exact_dif) {
-		bool dev_match = (sk->sk_bound_dev_if == dif ||
-				  sk->sk_bound_dev_if == sdif);
-
-		if (!dev_match)
-			return -1;
-		if (sk->sk_bound_dev_if)
-			score += 4;
-	}
+	dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+					dif, sdif);
+	if (!dev_match)
+		return -1;
+	score += 4;
 
 	if (sk->sk_incoming_cpu == raw_smp_processor_id())
 		score++;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 1ede7a16a0be..bde08aa549f3 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -772,6 +772,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 		case IPV6_2292PKTINFO:
 		    {
 			struct net_device *dev = NULL;
+			int src_idx;
 
 			if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) {
 				err = -EINVAL;
@@ -779,12 +780,15 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 			}
 
 			src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
+			src_idx = src_info->ipi6_ifindex;
 
-			if (src_info->ipi6_ifindex) {
+			if (src_idx) {
 				if (fl6->flowi6_oif &&
-				    src_info->ipi6_ifindex != fl6->flowi6_oif)
+				    src_idx != fl6->flowi6_oif &&
+				    (sk->sk_bound_dev_if != fl6->flowi6_oif ||
+				     !sk_dev_equal_l3scope(sk, src_idx)))
 					return -EINVAL;
-				fl6->flowi6_oif = src_info->ipi6_ifindex;
+				fl6->flowi6_oif = src_idx;
 			}
 
 			addr_type = __ipv6_addr_type(&src_info->ipi6_addr);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d2d97d07ef27..0559adc2f357 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -117,6 +117,7 @@ static int compute_score(struct sock *sk, struct net *net,
 {
 	int score;
 	struct inet_sock *inet;
+	bool dev_match;
 
 	if (!net_eq(sock_net(sk), net) ||
 	    udp_sk(sk)->udp_port_hash != hnum ||
@@ -144,15 +145,10 @@ static int compute_score(struct sock *sk, struct net *net,
 		score++;
 	}
 
-	if (sk->sk_bound_dev_if || exact_dif) {
-		bool dev_match = (sk->sk_bound_dev_if == dif ||
-				  sk->sk_bound_dev_if == sdif);
-
-		if (!dev_match)
-			return -1;
-		if (sk->sk_bound_dev_if)
-			score++;
-	}
+	dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif);
+	if (!dev_match)
+		return -1;
+	score++;
 
 	if (sk->sk_incoming_cpu == raw_smp_processor_id())
 		score++;
-- 
cgit v1.2.3


From 6897445fb194c8ad046df4a13e1ee9f080a5a21e Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@vyatta.att-mail.com>
Date: Wed, 7 Nov 2018 15:36:05 +0000
Subject: net: provide a sysctl raw_l3mdev_accept for raw socket lookup with
 VRFs

Add a sysctl raw_l3mdev_accept to control raw socket lookup in a manner
similar to use of tcp_l3mdev_accept for stream and of udp_l3mdev_accept
for datagram sockets. Have this default to enabled for reasons of
backwards compatibility. This is so as to specify the output device
with cmsg and IP_PKTINFO, but using a socket not bound to the
corresponding VRF. This allows e.g. older ping implementations to be
run with specifying the device but without executing it in the VRF.
If the option is disabled, packets received in a VRF context are only
handled by a raw socket bound to the VRF, and correspondingly packets
in the default VRF are only handled by a socket not bound to any VRF.

Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 12 ++++++++++++
 Documentation/networking/vrf.txt       | 13 +++++++++++++
 include/net/netns/ipv4.h               |  3 +++
 include/net/raw.h                      |  1 +
 net/ipv4/af_inet.c                     |  2 ++
 net/ipv4/raw.c                         | 28 ++++++++++++++++++++++++++--
 net/ipv4/sysctl_net_ipv4.c             | 11 +++++++++++
 7 files changed, 68 insertions(+), 2 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 32b21571adfe..aa9e6a331679 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -370,6 +370,7 @@ tcp_l3mdev_accept - BOOLEAN
 	derived from the listen socket to be bound to the L3 domain in
 	which the packets originated. Only valid when the kernel was
 	compiled with CONFIG_NET_L3_MASTER_DEV.
+        Default: 0 (disabled)
 
 tcp_low_latency - BOOLEAN
 	This is a legacy option, it has no effect anymore.
@@ -773,6 +774,7 @@ udp_l3mdev_accept - BOOLEAN
 	being received regardless of the L3 domain in which they
 	originated. Only valid when the kernel was compiled with
 	CONFIG_NET_L3_MASTER_DEV.
+        Default: 0 (disabled)
 
 udp_mem - vector of 3 INTEGERs: min, pressure, max
 	Number of pages allowed for queueing by all UDP sockets.
@@ -799,6 +801,16 @@ udp_wmem_min - INTEGER
 	total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
 	Default: 4K
 
+RAW variables:
+
+raw_l3mdev_accept - BOOLEAN
+	Enabling this option allows a "global" bound socket to work
+	across L3 master domains (e.g., VRFs) with packets capable of
+	being received regardless of the L3 domain in which they
+	originated. Only valid when the kernel was compiled with
+	CONFIG_NET_L3_MASTER_DEV.
+	Default: 1 (enabled)
+
 CIPSOv4 Variables:
 
 cipso_cache_enable - BOOLEAN
diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt
index d4b129402d57..a5f103b083a0 100644
--- a/Documentation/networking/vrf.txt
+++ b/Documentation/networking/vrf.txt
@@ -111,9 +111,22 @@ the same port if they bind to an l3mdev.
 TCP & UDP services running in the default VRF context (ie., not bound
 to any VRF device) can work across all VRF domains by enabling the
 tcp_l3mdev_accept and udp_l3mdev_accept sysctl options:
+
     sysctl -w net.ipv4.tcp_l3mdev_accept=1
     sysctl -w net.ipv4.udp_l3mdev_accept=1
 
+These options are disabled by default so that a socket in a VRF is only
+selected for packets in that VRF. There is a similar option for RAW
+sockets, which is enabled by default for reasons of backwards compatibility.
+This is so as to specify the output device with cmsg and IP_PKTINFO, but
+using a socket not bound to the corresponding VRF. This allows e.g. older ping
+implementations to be run with specifying the device but without executing it
+in the VRF. This option can be disabled so that packets received in a VRF
+context are only handled by a raw socket bound to the VRF, and packets in the
+default VRF are only handled by a socket not bound to any VRF:
+
+    sysctl -w net.ipv4.raw_l3mdev_accept=0
+
 netfilter rules on the VRF device can be used to limit access to services
 running in the default VRF context as well.
 
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index e47503b4e4d1..104a6669e344 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -103,6 +103,9 @@ struct netns_ipv4 {
 	/* Shall we try to damage output packets if routing dev changes? */
 	int sysctl_ip_dynaddr;
 	int sysctl_ip_early_demux;
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	int sysctl_raw_l3mdev_accept;
+#endif
 	int sysctl_tcp_early_demux;
 	int sysctl_udp_early_demux;
 
diff --git a/include/net/raw.h b/include/net/raw.h
index 9c9fa98a91a4..20ebf0b3dfa8 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -61,6 +61,7 @@ void raw_seq_stop(struct seq_file *seq, void *v);
 
 int raw_hash_sk(struct sock *sk);
 void raw_unhash_sk(struct sock *sk);
+void raw_init(void);
 
 struct raw_sock {
 	/* inet_sock has to be the first member */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 1fbe2f815474..07749c5b0a50 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1964,6 +1964,8 @@ static int __init inet_init(void)
 	/* Add UDP-Lite (RFC 3828) */
 	udplite4_register();
 
+	raw_init();
+
 	ping_init();
 
 	/*
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8ca3eb06ba04..1ebd29abe79c 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -805,7 +805,7 @@ out:
 	return copied;
 }
 
-static int raw_init(struct sock *sk)
+static int raw_sk_init(struct sock *sk)
 {
 	struct raw_sock *rp = raw_sk(sk);
 
@@ -970,7 +970,7 @@ struct proto raw_prot = {
 	.connect	   = ip4_datagram_connect,
 	.disconnect	   = __udp_disconnect,
 	.ioctl		   = raw_ioctl,
-	.init		   = raw_init,
+	.init		   = raw_sk_init,
 	.setsockopt	   = raw_setsockopt,
 	.getsockopt	   = raw_getsockopt,
 	.sendmsg	   = raw_sendmsg,
@@ -1133,4 +1133,28 @@ void __init raw_proc_exit(void)
 {
 	unregister_pernet_subsys(&raw_net_ops);
 }
+
+static void raw_sysctl_init_net(struct net *net)
+{
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	net->ipv4.sysctl_raw_l3mdev_accept = 1;
+#endif
+}
+
+static int __net_init raw_sysctl_init(struct net *net)
+{
+	raw_sysctl_init_net(net);
+	return 0;
+}
+
+static struct pernet_operations __net_initdata raw_sysctl_ops = {
+	.init	= raw_sysctl_init,
+};
+
+void __init raw_init(void)
+{
+	raw_sysctl_init_net(&init_net);
+	if (register_pernet_subsys(&raw_sysctl_ops))
+		panic("RAW: failed to init sysctl parameters.\n");
+}
 #endif /* CONFIG_PROC_FS */
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 891ed2f91467..ba0fc4b18465 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -602,6 +602,17 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= ipv4_ping_group_range,
 	},
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	{
+		.procname	= "raw_l3mdev_accept",
+		.data		= &init_net.ipv4.sysctl_raw_l3mdev_accept,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif
 	{
 		.procname	= "tcp_ecn",
 		.data		= &init_net.ipv4.sysctl_tcp_ecn,
-- 
cgit v1.2.3


From 7055420fb6a1cb754a64be99ddcabd45bd902d99 Mon Sep 17 00:00:00 2001
From: Duncan Eastoe <deastoe@vyatta.att-mail.com>
Date: Wed, 7 Nov 2018 15:36:06 +0000
Subject: net: fix raw socket lookup device bind matching with VRFs

When there exist a pair of raw sockets one unbound and one bound
to a VRF but equal in all other respects, when a packet is received
in the VRF context, __raw_v4_lookup() matches on both sockets.

This results in the packet being delivered over both sockets,
instead of only the raw socket bound to the VRF. The bound device
checks in __raw_v4_lookup() are replaced with a call to
raw_sk_bound_dev_eq() which correctly handles whether the packet
should be delivered over the unbound socket in such cases.

In __raw_v6_lookup() the match on the device binding of the socket is
similarly updated to use raw_sk_bound_dev_eq() which matches the
handling in __raw_v4_lookup().

Importantly raw_sk_bound_dev_eq() takes the raw_l3mdev_accept sysctl
into account.

Signed-off-by: Duncan Eastoe <deastoe@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/raw.h | 13 ++++++++++++-
 net/ipv4/raw.c    |  3 +--
 net/ipv6/raw.c    |  5 ++---
 3 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/include/net/raw.h b/include/net/raw.h
index 20ebf0b3dfa8..821ff4887f77 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -17,7 +17,7 @@
 #ifndef _RAW_H
 #define _RAW_H
 
-
+#include <net/inet_sock.h>
 #include <net/protocol.h>
 #include <linux/icmp.h>
 
@@ -75,4 +75,15 @@ static inline struct raw_sock *raw_sk(const struct sock *sk)
 	return (struct raw_sock *)sk;
 }
 
+static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+				       int dif, int sdif)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	return inet_bound_dev_eq(!!net->ipv4.sysctl_raw_l3mdev_accept,
+				 bound_dev_if, dif, sdif);
+#else
+	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
+#endif
+}
+
 #endif	/* _RAW_H */
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 1ebd29abe79c..fb1f02015a15 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -131,8 +131,7 @@ struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
 		if (net_eq(sock_net(sk), net) && inet->inet_num == num	&&
 		    !(inet->inet_daddr && inet->inet_daddr != raddr) 	&&
 		    !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
-		    !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
-		      sk->sk_bound_dev_if != sdif))
+		    raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
 			goto found; /* gotcha */
 	}
 	sk = NULL;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 5e0efd3954e9..aed7eb5c2123 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -86,9 +86,8 @@ struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
 			    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
 				continue;
 
-			if (sk->sk_bound_dev_if &&
-			    sk->sk_bound_dev_if != dif &&
-			    sk->sk_bound_dev_if != sdif)
+			if (!raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+						 dif, sdif))
 				continue;
 
 			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
-- 
cgit v1.2.3


From 6f12fa775530195a501fb090d092c637f32d0cc5 Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@vyatta.att-mail.com>
Date: Wed, 7 Nov 2018 15:36:07 +0000
Subject: vrf: mark skb for multicast or link-local as enslaved to VRF

The skb for packets that are multicast or to a link-local address are
not marked as being enslaved to a VRF, if they are received on a socket
bound to the VRF. This is needed for ND and it is preferable for the
kernel not to have to deal with the additional use-cases if ll or mcast
packets are handled as enslaved. However, this does not allow service
instances listening on unbound and bound to VRF sockets to distinguish
the VRF used, if packets are sent as multicast or to a link-local
address. The fix is for the VRF driver to also mark these skb as being
enslaved to the VRF.

Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 69b7227c637e..21ad4b1d7f03 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -981,24 +981,23 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 				   struct sk_buff *skb)
 {
 	int orig_iif = skb->skb_iif;
-	bool need_strict;
+	bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr);
+	bool is_ndisc = ipv6_ndisc_frame(skb);
 
-	/* loopback traffic; do not push through packet taps again.
-	 * Reset pkt_type for upper layers to process skb
+	/* loopback, multicast & non-ND link-local traffic; do not push through
+	 * packet taps again. Reset pkt_type for upper layers to process skb
 	 */
-	if (skb->pkt_type == PACKET_LOOPBACK) {
+	if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) {
 		skb->dev = vrf_dev;
 		skb->skb_iif = vrf_dev->ifindex;
 		IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
-		skb->pkt_type = PACKET_HOST;
+		if (skb->pkt_type == PACKET_LOOPBACK)
+			skb->pkt_type = PACKET_HOST;
 		goto out;
 	}
 
-	/* if packet is NDISC or addressed to multicast or link-local
-	 * then keep the ingress interface
-	 */
-	need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr);
-	if (!ipv6_ndisc_frame(skb) && !need_strict) {
+	/* if packet is NDISC then keep the ingress interface */
+	if (!is_ndisc) {
 		vrf_rx_stats(vrf_dev, skb->len);
 		skb->dev = vrf_dev;
 		skb->skb_iif = vrf_dev->ifindex;
-- 
cgit v1.2.3


From d839a0ebeb4e81a4f2923f581c28b41e1238bdfe Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@vyatta.att-mail.com>
Date: Wed, 7 Nov 2018 15:36:08 +0000
Subject: ipv6: allow ping to link-local address in VRF

If link-local packets are marked as enslaved to a VRF, then to allow
ping to the link-local from a vrf, the error handling for IPV6_PKTINFO
needs to be relaxed to also allow the pkt ipi6_ifindex to be that of a
slave device to the vrf.

Note that the real device also needs to be retrieved in icmp6_iif()
to set the ipv6 flow oif to this for icmp echo reply handling. The
recent commit 24b711edfc34 ("net/ipv6: Fix linklocal to global address
with VRF") takes care of this, so the sdif does not need checking here.

This fix makes ping to link-local consistent with that to global
addresses, in that this can now be done from within the same VRF that
the address is in.

Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ipv6_sockglue.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 381ce38940ae..973e215c3114 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -486,7 +486,7 @@ sticky_done:
 				retv = -EFAULT;
 				break;
 		}
-		if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if)
+		if (!sk_dev_equal_l3scope(sk, pkt.ipi6_ifindex))
 			goto e_inval;
 
 		np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
-- 
cgit v1.2.3


From 5226b6a920ba78d9fbcbb843388d2a844a1fa1c8 Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@vyatta.att-mail.com>
Date: Wed, 7 Nov 2018 15:36:09 +0000
Subject: ipv6: handling of multicast packets received in VRF

If the skb for multicast packets marked as enslaved to a VRF are
received, then the secondary device index should be used to obtain
the real device. And verify the multicast address against the
enslaved rather than the l3mdev device.

Signed-off-by: Dewi Morgan <morgand@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_input.c | 35 ++++++++++++++++++++++++++++++++---
 1 file changed, 32 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 96577e742afd..df58e1100226 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -359,6 +359,8 @@ resubmit_final:
 			}
 		} else if (ipprot->flags & INET6_PROTO_FINAL) {
 			const struct ipv6hdr *hdr;
+			int sdif = inet6_sdif(skb);
+			struct net_device *dev;
 
 			/* Only do this once for first final protocol */
 			have_final = true;
@@ -371,9 +373,19 @@ resubmit_final:
 			skb_postpull_rcsum(skb, skb_network_header(skb),
 					   skb_network_header_len(skb));
 			hdr = ipv6_hdr(skb);
+
+			/* skb->dev passed may be master dev for vrfs. */
+			if (sdif) {
+				dev = dev_get_by_index_rcu(net, sdif);
+				if (!dev)
+					goto discard;
+			} else {
+				dev = skb->dev;
+			}
+
 			if (ipv6_addr_is_multicast(&hdr->daddr) &&
-			    !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
-			    &hdr->saddr) &&
+			    !ipv6_chk_mcast_addr(dev, &hdr->daddr,
+						 &hdr->saddr) &&
 			    !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
 				goto discard;
 		}
@@ -432,15 +444,32 @@ EXPORT_SYMBOL_GPL(ip6_input);
 
 int ip6_mc_input(struct sk_buff *skb)
 {
+	int sdif = inet6_sdif(skb);
 	const struct ipv6hdr *hdr;
+	struct net_device *dev;
 	bool deliver;
 
 	__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
 			 __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
 			 skb->len);
 
+	/* skb->dev passed may be master dev for vrfs. */
+	if (sdif) {
+		rcu_read_lock();
+		dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
+		if (!dev) {
+			rcu_read_unlock();
+			kfree_skb(skb);
+			return -ENODEV;
+		}
+	} else {
+		dev = skb->dev;
+	}
+
 	hdr = ipv6_hdr(skb);
-	deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL);
+	deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
+	if (sdif)
+		rcu_read_unlock();
 
 #ifdef CONFIG_IPV6_MROUTE
 	/*
-- 
cgit v1.2.3


From 7bd2db404efa3daff700e8c88561b435611d07a5 Mon Sep 17 00:00:00 2001
From: Dewi Morgan <morgand@vyatta.att-mail.com>
Date: Wed, 7 Nov 2018 15:36:10 +0000
Subject: ipv6: do not drop vrf udp multicast packets

For bound udp sockets in a vrf, also check the sdif to get the index
for ingress devices enslaved to an l3mdev.

Signed-off-by: Dewi Morgan <morgand@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 0559adc2f357..a25571c12a8a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -637,7 +637,7 @@ drop:
 static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
 				   __be16 loc_port, const struct in6_addr *loc_addr,
 				   __be16 rmt_port, const struct in6_addr *rmt_addr,
-				   int dif, unsigned short hnum)
+				   int dif, int sdif, unsigned short hnum)
 {
 	struct inet_sock *inet = inet_sk(sk);
 
@@ -649,7 +649,7 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
 	    (inet->inet_dport && inet->inet_dport != rmt_port) ||
 	    (!ipv6_addr_any(&sk->sk_v6_daddr) &&
 		    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
-	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) ||
+	    !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif) ||
 	    (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
 		    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
 		return false;
@@ -683,6 +683,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	unsigned int offset = offsetof(typeof(*sk), sk_node);
 	unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
 	int dif = inet6_iif(skb);
+	int sdif = inet6_sdif(skb);
 	struct hlist_node *node;
 	struct sk_buff *nskb;
 
@@ -697,7 +698,8 @@ start_lookup:
 
 	sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
 		if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr,
-					    uh->source, saddr, dif, hnum))
+					    uh->source, saddr, dif, sdif,
+					    hnum))
 			continue;
 		/* If zero checksum and no_check is not on for
 		 * the socket then skip it.
-- 
cgit v1.2.3


From 60fb9567bf30937e6bedfa939d7c8fd4ee6a1b1c Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:28 +0100
Subject: udp: implement complete book-keeping for encap_needed

The *encap_needed static keys are enabled by UDP tunnels
and several UDP encapsulations type, but they are never
turned off. This can cause unneeded overall performance
degradation for systems where such features are used
transiently.

This patch introduces complete book-keeping for such keys,
decreasing the usage at socket destruction time, if needed,
and avoiding that the same socket could increase the key
usage multiple times.

rfc v3 -> v1:
 - add socket lock around udp_tunnel_encap_enable()

rfc v2 -> rfc v3:
 - use udp_tunnel_encap_enable() in setsockopt()

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h      |  7 ++++++-
 include/net/udp_tunnel.h |  6 ++++++
 net/ipv4/udp.c           | 19 +++++++++++++------
 net/ipv6/udp.c           | 14 +++++++++-----
 4 files changed, 34 insertions(+), 12 deletions(-)

diff --git a/include/linux/udp.h b/include/linux/udp.h
index 320d49d85484..a4dafff407fb 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -49,7 +49,12 @@ struct udp_sock {
 	unsigned int	 corkflag;	/* Cork is required */
 	__u8		 encap_type;	/* Is this an Encapsulation socket? */
 	unsigned char	 no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
-			 no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */
+			 no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
+			 encap_enabled:1; /* This socket enabled encap
+					   * processing; UDP tunnels and
+					   * different encapsulation layer set
+					   * this
+					   */
 	/*
 	 * Following member retains the information to create a UDP header
 	 * when the socket is uncorked.
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index fe680ab6b15a..3fbe56430e3b 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -165,6 +165,12 @@ static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum)
 
 static inline void udp_tunnel_encap_enable(struct socket *sock)
 {
+	struct udp_sock *up = udp_sk(sock->sk);
+
+	if (up->encap_enabled)
+		return;
+
+	up->encap_enabled = 1;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sock->sk->sk_family == PF_INET6)
 		ipv6_stub->udpv6_encap_enable();
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index cf73c9194bb6..f81409921e27 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -115,6 +115,7 @@
 #include "udp_impl.h"
 #include <net/sock_reuseport.h>
 #include <net/addrconf.h>
+#include <net/udp_tunnel.h>
 
 struct udp_table udp_table __read_mostly;
 EXPORT_SYMBOL(udp_table);
@@ -2395,11 +2396,15 @@ void udp_destroy_sock(struct sock *sk)
 	bool slow = lock_sock_fast(sk);
 	udp_flush_pending_frames(sk);
 	unlock_sock_fast(sk, slow);
-	if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) {
-		void (*encap_destroy)(struct sock *sk);
-		encap_destroy = READ_ONCE(up->encap_destroy);
-		if (encap_destroy)
-			encap_destroy(sk);
+	if (static_branch_unlikely(&udp_encap_needed_key)) {
+		if (up->encap_type) {
+			void (*encap_destroy)(struct sock *sk);
+			encap_destroy = READ_ONCE(up->encap_destroy);
+			if (encap_destroy)
+				encap_destroy(sk);
+		}
+		if (up->encap_enabled)
+			static_branch_disable(&udp_encap_needed_key);
 	}
 }
 
@@ -2444,7 +2449,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 			/* FALLTHROUGH */
 		case UDP_ENCAP_L2TPINUDP:
 			up->encap_type = val;
-			udp_encap_enable();
+			lock_sock(sk);
+			udp_tunnel_encap_enable(sk->sk_socket);
+			release_sock(sk);
 			break;
 		default:
 			err = -ENOPROTOOPT;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index a25571c12a8a..bdf7e071a63b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1456,11 +1456,15 @@ void udpv6_destroy_sock(struct sock *sk)
 	udp_v6_flush_pending_frames(sk);
 	release_sock(sk);
 
-	if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) {
-		void (*encap_destroy)(struct sock *sk);
-		encap_destroy = READ_ONCE(up->encap_destroy);
-		if (encap_destroy)
-			encap_destroy(sk);
+	if (static_branch_unlikely(&udpv6_encap_needed_key)) {
+		if (up->encap_type) {
+			void (*encap_destroy)(struct sock *sk);
+			encap_destroy = READ_ONCE(up->encap_destroy);
+			if (encap_destroy)
+				encap_destroy(sk);
+		}
+		if (up->encap_enabled)
+			static_branch_disable(&udpv6_encap_needed_key);
 	}
 
 	inet6_destroy_sock(sk);
-- 
cgit v1.2.3


From e20cf8d3f1f763ad28a9cb3b41305b8a8a42653e Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:29 +0100
Subject: udp: implement GRO for plain UDP sockets.

This is the RX counterpart of commit bec1f6f69736 ("udp: generate gso
with UDP_SEGMENT"). When UDP_GRO is enabled, such socket is also
eligible for GRO in the rx path: UDP segments directed to such socket
are assembled into a larger GSO_UDP_L4 packet.

The core UDP GRO support is enabled with setsockopt(UDP_GRO).

Initial benchmark numbers:

Before:
udp rx:   1079 MB/s   769065 calls/s

After:
udp rx:   1466 MB/s    24877 calls/s

This change introduces a side effect in respect to UDP tunnels:
after a UDP tunnel creation, now the kernel performs a lookup per ingress
UDP packet, while before such lookup happened only if the ingress packet
carried a valid internal header csum.

rfc v2 -> rfc v3:
 - fixed typos in macro name and comments
 - really enforce UDP_GRO_CNT_MAX, instead of UDP_GRO_CNT_MAX + 1
 - acquire socket lock in UDP_GRO setsockopt

rfc v1 -> rfc v2:
 - use a new option to enable UDP GRO
 - use static keys to protect the UDP GRO socket lookup

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h      |   3 +-
 include/uapi/linux/udp.h |   1 +
 net/ipv4/udp.c           |   8 ++++
 net/ipv4/udp_offload.c   | 109 +++++++++++++++++++++++++++++++++++++----------
 net/ipv6/udp_offload.c   |   6 +--
 5 files changed, 99 insertions(+), 28 deletions(-)

diff --git a/include/linux/udp.h b/include/linux/udp.h
index a4dafff407fb..f613b329852e 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -50,11 +50,12 @@ struct udp_sock {
 	__u8		 encap_type;	/* Is this an Encapsulation socket? */
 	unsigned char	 no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
 			 no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
-			 encap_enabled:1; /* This socket enabled encap
+			 encap_enabled:1, /* This socket enabled encap
 					   * processing; UDP tunnels and
 					   * different encapsulation layer set
 					   * this
 					   */
+			 gro_enabled:1;	/* Can accept GRO packets */
 	/*
 	 * Following member retains the information to create a UDP header
 	 * when the socket is uncorked.
diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
index 09502de447f5..30baccb6c9c4 100644
--- a/include/uapi/linux/udp.h
+++ b/include/uapi/linux/udp.h
@@ -33,6 +33,7 @@ struct udphdr {
 #define UDP_NO_CHECK6_TX 101	/* Disable sending checksum for UDP6X */
 #define UDP_NO_CHECK6_RX 102	/* Disable accpeting checksum for UDP6 */
 #define UDP_SEGMENT	103	/* Set GSO segmentation size */
+#define UDP_GRO		104	/* This socket can receive UDP GRO packets */
 
 /* UDP encapsulation types */
 #define UDP_ENCAP_ESPINUDP_NON_IKE	1 /* draft-ietf-ipsec-nat-t-ike-00/01 */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f81409921e27..9fc08b098ced 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2473,6 +2473,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		up->gso_size = val;
 		break;
 
+	case UDP_GRO:
+		lock_sock(sk);
+		if (valbool)
+			udp_tunnel_encap_enable(sk->sk_socket);
+		up->gro_enabled = valbool;
+		release_sock(sk);
+		break;
+
 	/*
 	 * 	UDP-Lite's partial checksum coverage (RFC 3828).
 	 */
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 802f2bc00d69..0646d61f4fa8 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -343,6 +343,54 @@ out:
 	return segs;
 }
 
+#define UDP_GRO_CNT_MAX 64
+static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
+					       struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_hdr(skb);
+	struct sk_buff *pp = NULL;
+	struct udphdr *uh2;
+	struct sk_buff *p;
+
+	/* requires non zero csum, for symmetry with GSO */
+	if (!uh->check) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	/* pull encapsulating udp header */
+	skb_gro_pull(skb, sizeof(struct udphdr));
+	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
+
+	list_for_each_entry(p, head, list) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		uh2 = udp_hdr(p);
+
+		/* Match ports only, as csum is always non zero */
+		if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+
+		/* Terminate the flow on len mismatch or if it grow "too much".
+		 * Under small packet flood GRO count could elsewhere grow a lot
+		 * leading to execessive truesize values
+		 */
+		if (!skb_gro_receive(p, skb) &&
+		    NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
+			pp = p;
+		else if (uh->len != uh2->len)
+			pp = p;
+
+		return pp;
+	}
+
+	/* mismatch, but we never need to flush */
+	return NULL;
+}
+
 struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 				struct udphdr *uh, udp_lookup_t lookup)
 {
@@ -353,23 +401,27 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 	int flush = 1;
 	struct sock *sk;
 
+	rcu_read_lock();
+	sk = (*lookup)(skb, uh->source, uh->dest);
+	if (!sk)
+		goto out_unlock;
+
+	if (udp_sk(sk)->gro_enabled) {
+		pp = call_gro_receive(udp_gro_receive_segment, head, skb);
+		rcu_read_unlock();
+		return pp;
+	}
+
 	if (NAPI_GRO_CB(skb)->encap_mark ||
 	    (skb->ip_summed != CHECKSUM_PARTIAL &&
 	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
-	     !NAPI_GRO_CB(skb)->csum_valid))
-		goto out;
+	     !NAPI_GRO_CB(skb)->csum_valid) ||
+	    !udp_sk(sk)->gro_receive)
+		goto out_unlock;
 
 	/* mark that this skb passed once through the tunnel gro layer */
 	NAPI_GRO_CB(skb)->encap_mark = 1;
 
-	rcu_read_lock();
-	sk = (*lookup)(skb, uh->source, uh->dest);
-
-	if (sk && udp_sk(sk)->gro_receive)
-		goto unflush;
-	goto out_unlock;
-
-unflush:
 	flush = 0;
 
 	list_for_each_entry(p, head, list) {
@@ -394,7 +446,6 @@ unflush:
 
 out_unlock:
 	rcu_read_unlock();
-out:
 	skb_gro_flush_final(skb, pp, flush);
 	return pp;
 }
@@ -427,6 +478,19 @@ flush:
 	return NULL;
 }
 
+static int udp_gro_complete_segment(struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_hdr(skb);
+
+	skb->csum_start = (unsigned char *)uh - skb->head;
+	skb->csum_offset = offsetof(struct udphdr, check);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+
+	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4;
+	return 0;
+}
+
 int udp_gro_complete(struct sk_buff *skb, int nhoff,
 		     udp_lookup_t lookup)
 {
@@ -437,16 +501,21 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
 
 	uh->len = newlen;
 
-	/* Set encapsulation before calling into inner gro_complete() functions
-	 * to make them set up the inner offsets.
-	 */
-	skb->encapsulation = 1;
-
 	rcu_read_lock();
 	sk = (*lookup)(skb, uh->source, uh->dest);
-	if (sk && udp_sk(sk)->gro_complete)
+	if (sk && udp_sk(sk)->gro_enabled) {
+		err = udp_gro_complete_segment(skb);
+	} else if (sk && udp_sk(sk)->gro_complete) {
+		skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM
+					: SKB_GSO_UDP_TUNNEL;
+
+		/* Set encapsulation before calling into inner gro_complete()
+		 * functions to make them set up the inner offsets.
+		 */
+		skb->encapsulation = 1;
 		err = udp_sk(sk)->gro_complete(sk, skb,
 				nhoff + sizeof(struct udphdr));
+	}
 	rcu_read_unlock();
 
 	if (skb->remcsum_offload)
@@ -461,13 +530,9 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
-	if (uh->check) {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+	if (uh->check)
 		uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
 					  iph->daddr, 0);
-	} else {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
-	}
 
 	return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb);
 }
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 1b8e161ac527..828b2457f97b 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -147,13 +147,9 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
-	if (uh->check) {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+	if (uh->check)
 		uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr,
 					  &ipv6h->daddr, 0);
-	} else {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
-	}
 
 	return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb);
 }
-- 
cgit v1.2.3


From bcd1665e3569b0a6f569514f023a41fc7df0b4a3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:30 +0100
Subject: udp: add support for UDP_GRO cmsg

When UDP GRO is enabled, the UDP_GRO cmsg will carry the ingress
datagram size. User-space can use such info to compute the original
packets layout.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h | 11 +++++++++++
 net/ipv4/udp.c      |  4 ++++
 net/ipv6/udp.c      |  3 +++
 3 files changed, 18 insertions(+)

diff --git a/include/linux/udp.h b/include/linux/udp.h
index f613b329852e..e23d5024f42f 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -121,6 +121,17 @@ static inline bool udp_get_no_check6_rx(struct sock *sk)
 	return udp_sk(sk)->no_check6_rx;
 }
 
+static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk,
+				 struct sk_buff *skb)
+{
+	int gso_size;
+
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
+		gso_size = skb_shinfo(skb)->gso_size;
+		put_cmsg(msg, SOL_UDP, UDP_GRO, sizeof(gso_size), &gso_size);
+	}
+}
+
 #define udp_portaddr_for_each_entry(__sk, list) \
 	hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node)
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9fc08b098ced..dddc6fe90f51 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1711,6 +1711,10 @@ try_again:
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
 		*addr_len = sizeof(*sin);
 	}
+
+	if (udp_sk(sk)->gro_enabled)
+		udp_cmsg_recv(msg, sk, skb);
+
 	if (inet->cmsg_flags)
 		ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index bdf7e071a63b..4c79dc5329bc 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -417,6 +417,9 @@ try_again:
 		*addr_len = sizeof(*sin6);
 	}
 
+	if (udp_sk(sk)->gro_enabled)
+		udp_cmsg_recv(msg, sk, skb);
+
 	if (np->rxopt.all)
 		ip6_datagram_recv_common_ctl(sk, msg, skb);
 
-- 
cgit v1.2.3


From 68cb7d531e6a87250a51b8a4ee1c79b3445aeff3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:31 +0100
Subject: ip: factor out protocol delivery helper

So that we can re-use it at the UDP level in a later patch

rfc v3 -> v1
 - add the helper declaration into the ip header

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h    |  1 +
 net/ipv4/ip_input.c | 73 ++++++++++++++++++++++++++---------------------------
 2 files changed, 37 insertions(+), 37 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 462182f78236..8866bfce6121 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -155,6 +155,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 void ip_list_rcv(struct list_head *head, struct packet_type *pt,
 		 struct net_device *orig_dev);
 int ip_local_deliver(struct sk_buff *skb);
+void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto);
 int ip_mr_input(struct sk_buff *skb);
 int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 35a786c0aaa0..72250b4e466d 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -188,51 +188,50 @@ bool ip_call_ra_chain(struct sk_buff *skb)
 	return false;
 }
 
-static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
 {
-	__skb_pull(skb, skb_network_header_len(skb));
-
-	rcu_read_lock();
-	{
-		int protocol = ip_hdr(skb)->protocol;
-		const struct net_protocol *ipprot;
-		int raw;
+	const struct net_protocol *ipprot;
+	int raw, ret;
 
-	resubmit:
-		raw = raw_local_deliver(skb, protocol);
+resubmit:
+	raw = raw_local_deliver(skb, protocol);
 
-		ipprot = rcu_dereference(inet_protos[protocol]);
-		if (ipprot) {
-			int ret;
-
-			if (!ipprot->no_policy) {
-				if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
-					kfree_skb(skb);
-					goto out;
-				}
-				nf_reset(skb);
+	ipprot = rcu_dereference(inet_protos[protocol]);
+	if (ipprot) {
+		if (!ipprot->no_policy) {
+			if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+				kfree_skb(skb);
+				return;
 			}
-			ret = ipprot->handler(skb);
-			if (ret < 0) {
-				protocol = -ret;
-				goto resubmit;
+			nf_reset(skb);
+		}
+		ret = ipprot->handler(skb);
+		if (ret < 0) {
+			protocol = -ret;
+			goto resubmit;
+		}
+		__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
+	} else {
+		if (!raw) {
+			if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+				__IP_INC_STATS(net, IPSTATS_MIB_INUNKNOWNPROTOS);
+				icmp_send(skb, ICMP_DEST_UNREACH,
+					  ICMP_PROT_UNREACH, 0);
 			}
-			__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
+			kfree_skb(skb);
 		} else {
-			if (!raw) {
-				if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
-					__IP_INC_STATS(net, IPSTATS_MIB_INUNKNOWNPROTOS);
-					icmp_send(skb, ICMP_DEST_UNREACH,
-						  ICMP_PROT_UNREACH, 0);
-				}
-				kfree_skb(skb);
-			} else {
-				__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
-				consume_skb(skb);
-			}
+			__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
+			consume_skb(skb);
 		}
 	}
- out:
+}
+
+static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	__skb_pull(skb, skb_network_header_len(skb));
+
+	rcu_read_lock();
+	ip_protocol_deliver_rcu(net, skb, ip_hdr(skb)->protocol);
 	rcu_read_unlock();
 
 	return 0;
-- 
cgit v1.2.3


From 80bde363f9a43d942e404821b966e362131cd0ca Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:32 +0100
Subject: ipv6: factor out protocol delivery helper

So that we can re-use it at the UDP level in the next patch

rfc v3 -> v1:
 - add the helper declaration into the ipv6 header

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h   |  2 ++
 net/ipv6/ip6_input.c | 28 ++++++++++++++++------------
 2 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 829650540780..daf80863d3a5 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -975,6 +975,8 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip6_forward(struct sk_buff *skb);
 int ip6_input(struct sk_buff *skb);
 int ip6_mc_input(struct sk_buff *skb);
+void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
+			      bool have_final);
 
 int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index df58e1100226..3c06cc9e9b79 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -319,28 +319,26 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
 /*
  *	Deliver the packet to the host
  */
-
-
-static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
+			      bool have_final)
 {
 	const struct inet6_protocol *ipprot;
 	struct inet6_dev *idev;
 	unsigned int nhoff;
-	int nexthdr;
 	bool raw;
-	bool have_final = false;
 
 	/*
 	 *	Parse extension headers
 	 */
 
-	rcu_read_lock();
 resubmit:
 	idev = ip6_dst_idev(skb_dst(skb));
-	if (!pskb_pull(skb, skb_transport_offset(skb)))
-		goto discard;
 	nhoff = IP6CB(skb)->nhoff;
-	nexthdr = skb_network_header(skb)[nhoff];
+	if (!have_final) {
+		if (!pskb_pull(skb, skb_transport_offset(skb)))
+			goto discard;
+		nexthdr = skb_network_header(skb)[nhoff];
+	}
 
 resubmit_final:
 	raw = raw6_local_deliver(skb, nexthdr);
@@ -423,13 +421,19 @@ resubmit_final:
 			consume_skb(skb);
 		}
 	}
-	rcu_read_unlock();
-	return 0;
+	return;
 
 discard:
 	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
-	rcu_read_unlock();
 	kfree_skb(skb);
+}
+
+static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	rcu_read_lock();
+	ip6_protocol_deliver_rcu(net, skb, 0, false);
+	rcu_read_unlock();
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From cf329aa42b6659204fee865bbce0ea20462552eb Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:33 +0100
Subject: udp: cope with UDP GRO packet misdirection

In some scenarios, the GRO engine can assemble an UDP GRO packet
that ultimately lands on a non GRO-enabled socket.
This patch tries to address the issue explicitly checking for the UDP
socket features before enqueuing the packet, and eventually segmenting
the unexpected GRO packet, as needed.

We must also cope with re-insertion requests: after segmentation the
UDP code calls the helper introduced by the previous patches, as needed.

Segmentation is performed by a common helper, which takes care of
updating socket and protocol stats is case of failure.

rfc v3 -> v1
 - fix compile issues with rxrpc
 - when gso_segment returns NULL, treat is as an error
 - added 'ipv4' argument to udp_rcv_segment()

rfc v2 -> rfc v3
 - moved udp_rcv_segment() into net/udp.h, account errors to socket
   and ns, always return NULL or segs list

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h |  6 ++++++
 include/net/udp.h   | 45 +++++++++++++++++++++++++++++++++++++--------
 net/ipv4/udp.c      | 23 ++++++++++++++++++++++-
 net/ipv6/udp.c      | 24 +++++++++++++++++++++++-
 4 files changed, 88 insertions(+), 10 deletions(-)

diff --git a/include/linux/udp.h b/include/linux/udp.h
index e23d5024f42f..0a9c54e76305 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -132,6 +132,12 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk,
 	}
 }
 
+static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb)
+{
+	return !udp_sk(sk)->gro_enabled && skb_is_gso(skb) &&
+	       skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4;
+}
+
 #define udp_portaddr_for_each_entry(__sk, list) \
 	hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node)
 
diff --git a/include/net/udp.h b/include/net/udp.h
index a496e441645e..eccca2325ee6 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -417,17 +417,24 @@ static inline int copy_linear_skb(struct sk_buff *skb, int len, int off,
 } while(0)
 
 #if IS_ENABLED(CONFIG_IPV6)
-#define __UDPX_INC_STATS(sk, field)					\
-do {									\
-	if ((sk)->sk_family == AF_INET)					\
-		__UDP_INC_STATS(sock_net(sk), field, 0);		\
-	else								\
-		__UDP6_INC_STATS(sock_net(sk), field, 0);		\
-} while (0)
+#define __UDPX_MIB(sk, ipv4)						\
+({									\
+	ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics :	\
+				 sock_net(sk)->mib.udp_statistics) :	\
+		(IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 :	\
+				 sock_net(sk)->mib.udp_stats_in6);	\
+})
 #else
-#define __UDPX_INC_STATS(sk, field) __UDP_INC_STATS(sock_net(sk), field, 0)
+#define __UDPX_MIB(sk, ipv4)						\
+({									\
+	IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics :		\
+			 sock_net(sk)->mib.udp_statistics;		\
+})
 #endif
 
+#define __UDPX_INC_STATS(sk, field) \
+	__SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field)
+
 #ifdef CONFIG_PROC_FS
 struct udp_seq_afinfo {
 	sa_family_t			family;
@@ -461,4 +468,26 @@ DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
 void udpv6_encap_enable(void);
 #endif
 
+static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
+					      struct sk_buff *skb, bool ipv4)
+{
+	struct sk_buff *segs;
+
+	/* the GSO CB lays after the UDP one, no need to save and restore any
+	 * CB fragment
+	 */
+	segs = __skb_gso_segment(skb, NETIF_F_SG, false);
+	if (unlikely(IS_ERR_OR_NULL(segs))) {
+		int segs_nr = skb_shinfo(skb)->gso_segs;
+
+		atomic_add(segs_nr, &sk->sk_drops);
+		SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr);
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	consume_skb(skb);
+	return segs;
+}
+
 #endif	/* _UDP_H */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index dddc6fe90f51..3488650b90ac 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1906,7 +1906,7 @@ EXPORT_SYMBOL(udp_encap_enable);
  * Note that in the success and error cases, the skb is assumed to
  * have either been requeued or freed.
  */
-static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_sock *up = udp_sk(sk);
 	int is_udplite = IS_UDPLITE(sk);
@@ -2009,6 +2009,27 @@ drop:
 	return -1;
 }
 
+static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct sk_buff *next, *segs;
+	int ret;
+
+	if (likely(!udp_unexpected_gso(sk, skb)))
+		return udp_queue_rcv_one_skb(sk, skb);
+
+	BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_SGO_CB_OFFSET);
+	__skb_push(skb, -skb_mac_offset(skb));
+	segs = udp_rcv_segment(sk, skb, true);
+	for (skb = segs; skb; skb = next) {
+		next = skb->next;
+		__skb_pull(skb, skb_transport_offset(skb));
+		ret = udp_queue_rcv_one_skb(sk, skb);
+		if (ret > 0)
+			ip_protocol_deliver_rcu(dev_net(skb->dev), skb, -ret);
+	}
+	return 0;
+}
+
 /* For TCP sockets, sk_rx_dst is protected by socket lock
  * For UDP, we use xchg() to guard against concurrent changes.
  */
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4c79dc5329bc..c55698d19d68 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -554,7 +554,7 @@ void udpv6_encap_enable(void)
 }
 EXPORT_SYMBOL(udpv6_encap_enable);
 
-static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_sock *up = udp_sk(sk);
 	int is_udplite = IS_UDPLITE(sk);
@@ -637,6 +637,28 @@ drop:
 	return -1;
 }
 
+static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct sk_buff *next, *segs;
+	int ret;
+
+	if (likely(!udp_unexpected_gso(sk, skb)))
+		return udpv6_queue_rcv_one_skb(sk, skb);
+
+	__skb_push(skb, -skb_mac_offset(skb));
+	segs = udp_rcv_segment(sk, skb, false);
+	for (skb = segs; skb; skb = next) {
+		next = skb->next;
+		__skb_pull(skb, skb_transport_offset(skb));
+
+		ret = udpv6_queue_rcv_one_skb(sk, skb);
+		if (ret > 0)
+			ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret,
+						 true);
+	}
+	return 0;
+}
+
 static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
 				   __be16 loc_port, const struct in6_addr *loc_addr,
 				   __be16 rmt_port, const struct in6_addr *rmt_addr,
-- 
cgit v1.2.3


From 0a9ac2e95409169ed42ea66dd4270bc16b868e21 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:34 +0100
Subject: selftests: add GRO support to udp bench rx program

And fix a couple of buglets (port option processing,
clean termination on SIGINT). This is preparatory work
for GRO tests.

rfc v2 -> rfc v3:
 - use ETH_MAX_MTU

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/udpgso_bench_rx.c | 37 ++++++++++++++++++++++-----
 1 file changed, 30 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index 727cf67a3f75..8f48d7fb32cf 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -31,9 +31,15 @@
 #include <sys/wait.h>
 #include <unistd.h>
 
+#ifndef UDP_GRO
+#define UDP_GRO		104
+#endif
+
 static int  cfg_port		= 8000;
 static bool cfg_tcp;
 static bool cfg_verify;
+static bool cfg_read_all;
+static bool cfg_gro_segment;
 
 static bool interrupted;
 static unsigned long packets, bytes;
@@ -63,6 +69,8 @@ static void do_poll(int fd)
 
 	do {
 		ret = poll(&pfd, 1, 10);
+		if (interrupted)
+			break;
 		if (ret == -1)
 			error(1, errno, "poll");
 		if (ret == 0)
@@ -70,7 +78,7 @@ static void do_poll(int fd)
 		if (pfd.revents != POLLIN)
 			error(1, errno, "poll: 0x%x expected 0x%x\n",
 					pfd.revents, POLLIN);
-	} while (!ret && !interrupted);
+	} while (!ret);
 }
 
 static int do_socket(bool do_tcp)
@@ -102,6 +110,8 @@ static int do_socket(bool do_tcp)
 			error(1, errno, "listen");
 
 		do_poll(accept_fd);
+		if (interrupted)
+			exit(0);
 
 		fd = accept(accept_fd, NULL, NULL);
 		if (fd == -1)
@@ -167,10 +177,10 @@ static void do_verify_udp(const char *data, int len)
 /* Flush all outstanding datagrams. Verify first few bytes of each. */
 static void do_flush_udp(int fd)
 {
-	static char rbuf[ETH_DATA_LEN];
+	static char rbuf[ETH_MAX_MTU];
 	int ret, len, budget = 256;
 
-	len = cfg_verify ? sizeof(rbuf) : 0;
+	len = cfg_read_all ? sizeof(rbuf) : 0;
 	while (budget--) {
 		/* MSG_TRUNC will make return value full datagram length */
 		ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
@@ -178,7 +188,7 @@ static void do_flush_udp(int fd)
 			return;
 		if (ret == -1)
 			error(1, errno, "recv");
-		if (len) {
+		if (len && cfg_verify) {
 			if (ret == 0)
 				error(1, errno, "recv: 0 byte datagram\n");
 
@@ -192,23 +202,30 @@ static void do_flush_udp(int fd)
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-tv] [-p port]", filepath);
+	error(1, 0, "Usage: %s [-Grtv] [-p port]", filepath);
 }
 
 static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "ptv")) != -1) {
+	while ((c = getopt(argc, argv, "Gp:rtv")) != -1) {
 		switch (c) {
+		case 'G':
+			cfg_gro_segment = true;
+			break;
 		case 'p':
-			cfg_port = htons(strtoul(optarg, NULL, 0));
+			cfg_port = strtoul(optarg, NULL, 0);
+			break;
+		case 'r':
+			cfg_read_all = true;
 			break;
 		case 't':
 			cfg_tcp = true;
 			break;
 		case 'v':
 			cfg_verify = true;
+			cfg_read_all = true;
 			break;
 		}
 	}
@@ -227,6 +244,12 @@ static void do_recv(void)
 
 	fd = do_socket(cfg_tcp);
 
+	if (cfg_gro_segment && !cfg_tcp) {
+		int val = 1;
+		if (setsockopt(fd, IPPROTO_UDP, UDP_GRO, &val, sizeof(val)))
+			error(1, errno, "setsockopt UDP_GRO");
+	}
+
 	treport = gettimeofday_ms() + 1000;
 	do {
 		do_poll(fd);
-- 
cgit v1.2.3


From bd8e1afe6436558de3a7b25eaef34b69d98e5719 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:35 +0100
Subject: selftests: add dummy xdp test helper

This trivial XDP program does nothing, but will be used by the
next patch to test the GRO path in a net namespace, leveraging
the veth XDP implementation.

It's added here, despite its 'net' usage, to avoid the duplication
of the llc-related makefile boilerplate.

rfc v3 -> v1:
 - move the helper implementation into the bpf directory, don't
   touch udpgso_bench_rx

rfc v2 -> rfc v3:
 - move 'x' option handling here

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/Makefile    |  3 ++-
 tools/testing/selftests/bpf/xdp_dummy.c | 13 +++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/xdp_dummy.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e39dfb4e7970..4a54236475ae 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -37,7 +37,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
 	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \
-	test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o
+	test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o \
+	xdp_dummy.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
diff --git a/tools/testing/selftests/bpf/xdp_dummy.c b/tools/testing/selftests/bpf/xdp_dummy.c
new file mode 100644
index 000000000000..43b0ef1001ed
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_dummy.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+SEC("xdp_dummy")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From e87f53b4fab72f95952c17f672088e082e8e79ab Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:36 +0100
Subject: selftests: add some benchmark for UDP GRO

Run on top of veth pair, using a dummy XDP program to enable the GRO.

 rfc v3 -> v1:
  - use ip route to attach the xdp helper to the veth

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile        |  1 +
 tools/testing/selftests/net/udpgro_bench.sh | 93 +++++++++++++++++++++++++++++
 2 files changed, 94 insertions(+)
 create mode 100755 tools/testing/selftests/net/udpgro_bench.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 256d82d5fa87..b1bba2f60467 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -7,6 +7,7 @@ CFLAGS += -I../../../../usr/include/
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
+TEST_PROGS += udpgro_bench.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
new file mode 100755
index 000000000000..9ef4b1ee0f76
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -0,0 +1,93 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgro benchmarks
+
+readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+
+cleanup() {
+	local -r jobs="$(jobs -p)"
+	local -r ns="$(ip netns list|grep $PEER_NS)"
+
+	[ -n "${jobs}" ] && kill -INT ${jobs} 2>/dev/null
+	[ -n "$ns" ] && ip netns del $ns 2>/dev/null
+}
+trap cleanup EXIT
+
+run_one() {
+	# use 'rx' as separator between sender args and receiver args
+	local -r all="$@"
+	local -r tx_args=${all%rx*}
+	local -r rx_args=${all#*rx}
+
+	ip netns add "${PEER_NS}"
+	ip -netns "${PEER_NS}" link set lo up
+	ip link add type veth
+	ip link set dev veth0 up
+	ip addr add dev veth0 192.168.1.2/24
+	ip addr add dev veth0 2001:db8::2/64 nodad
+
+	ip link set dev veth1 netns "${PEER_NS}"
+	ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
+	ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
+	ip -netns "${PEER_NS}" link set dev veth1 up
+
+	ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r &
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r &
+
+	# Hack: let bg programs complete the startup
+	sleep 0.1
+	./udpgso_bench_tx ${tx_args}
+}
+
+run_in_netns() {
+	local -r args=$@
+
+	./in_netns.sh $0 __subprocess ${args}
+}
+
+run_udp() {
+	local -r args=$@
+
+	echo "udp gso - over veth touching data"
+	run_in_netns ${args} -S rx
+
+	echo "udp gso and gro - over veth touching data"
+	run_in_netns ${args} -S rx -G
+}
+
+run_tcp() {
+	local -r args=$@
+
+	echo "tcp - over veth touching data"
+	run_in_netns ${args} -t rx
+}
+
+run_all() {
+	local -r core_args="-l 4"
+	local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
+	local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+
+	echo "ipv4"
+	run_tcp "${ipv4_args}"
+	run_udp "${ipv4_args}"
+
+	echo "ipv6"
+	run_tcp "${ipv4_args}"
+	run_udp "${ipv6_args}"
+}
+
+if [ ! -f ../bpf/xdp_dummy.o ]; then
+	echo "Missing xdp_dummy helper. Build bpf selftest first"
+	exit -1
+fi
+
+if [[ $# -eq 0 ]]; then
+	run_all
+elif [[ $1 == "__subprocess" ]]; then
+	shift
+	run_one $@
+else
+	run_in_netns $@
+fi
-- 
cgit v1.2.3


From 3327a9c46352f111697d93d6134e7bf37c6bffca Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:37 +0100
Subject: selftests: add functionals test for UDP GRO

Extends the existing udp programs to allow checking for proper
GRO aggregation/GSO size, and run the tests via a shell script, using
a veth pair with XDP program attached to trigger the GRO code path.

rfc v3 -> v1:
 - use ip route to attach the xdp helper to the veth

rfc v2 -> rfc v3:
 - add missing test program options documentation
 - fix sporatic test failures (receiver faster than sender)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile          |   2 +-
 tools/testing/selftests/net/udpgro.sh         | 148 ++++++++++++++++++++++++++
 tools/testing/selftests/net/udpgro_bench.sh   |   8 +-
 tools/testing/selftests/net/udpgso_bench.sh   |   2 +-
 tools/testing/selftests/net/udpgso_bench_rx.c | 123 ++++++++++++++++++---
 tools/testing/selftests/net/udpgso_bench_tx.c |  22 ++--
 6 files changed, 282 insertions(+), 23 deletions(-)
 create mode 100755 tools/testing/selftests/net/udpgro.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index b1bba2f60467..eec359895feb 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -7,7 +7,7 @@ CFLAGS += -I../../../../usr/include/
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
-TEST_PROGS += udpgro_bench.sh
+TEST_PROGS += udpgro_bench.sh udpgro.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
new file mode 100755
index 000000000000..e94ef8067173
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -0,0 +1,148 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgro functional tests.
+
+readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+
+cleanup() {
+	local -r jobs="$(jobs -p)"
+	local -r ns="$(ip netns list|grep $PEER_NS)"
+
+	[ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
+	[ -n "$ns" ] && ip netns del $ns 2>/dev/null
+}
+trap cleanup EXIT
+
+cfg_veth() {
+	ip netns add "${PEER_NS}"
+	ip -netns "${PEER_NS}" link set lo up
+	ip link add type veth
+	ip link set dev veth0 up
+	ip addr add dev veth0 192.168.1.2/24
+	ip addr add dev veth0 2001:db8::2/64 nodad
+
+	ip link set dev veth1 netns "${PEER_NS}"
+	ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
+	ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
+	ip -netns "${PEER_NS}" link set dev veth1 up
+	ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+}
+
+run_one() {
+	# use 'rx' as separator between sender args and receiver args
+	local -r all="$@"
+	local -r tx_args=${all%rx*}
+	local -r rx_args=${all#*rx}
+
+	cfg_veth
+
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \
+		echo "ok" || \
+		echo "failed" &
+
+	# Hack: let bg programs complete the startup
+	sleep 0.1
+	./udpgso_bench_tx ${tx_args}
+	wait $(jobs -p)
+}
+
+run_test() {
+	local -r args=$@
+
+	printf " %-40s" "$1"
+	./in_netns.sh $0 __subprocess $2 rx -G -r $3
+}
+
+run_one_nat() {
+	# use 'rx' as separator between sender args and receiver args
+	local addr1 addr2 pid family="" ipt_cmd=ip6tables
+	local -r all="$@"
+	local -r tx_args=${all%rx*}
+	local -r rx_args=${all#*rx}
+
+	if [[ ${tx_args} = *-4* ]]; then
+		ipt_cmd=iptables
+		family=-4
+		addr1=192.168.1.1
+		addr2=192.168.1.3/24
+	else
+		addr1=2001:db8::1
+		addr2="2001:db8::3/64 nodad"
+	fi
+
+	cfg_veth
+	ip -netns "${PEER_NS}" addr add dev veth1 ${addr2}
+
+	# fool the GRO engine changing the destination address ...
+	ip netns exec "${PEER_NS}" $ipt_cmd -t nat -I PREROUTING -d ${addr1} -j DNAT --to-destination ${addr2%/*}
+
+	# ... so that GRO will match the UDP_GRO enabled socket, but packets
+	# will land on the 'plain' one
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 &
+	pid=$!
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${family} -b ${addr2%/*} ${rx_args} && \
+		echo "ok" || \
+		echo "failed"&
+
+	sleep 0.1
+	./udpgso_bench_tx ${tx_args}
+	kill -INT $pid
+	wait $(jobs -p)
+}
+
+run_nat_test() {
+	local -r args=$@
+
+	printf " %-40s" "$1"
+	./in_netns.sh $0 __subprocess_nat $2 rx -r $3
+}
+
+run_all() {
+	local -r core_args="-l 4"
+	local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
+	local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+
+	echo "ipv4"
+	run_test "no GRO" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400"
+
+	# explicitly check we are not receiving UDP_SEGMENT cmsg (-S -1)
+	# when GRO does not take place
+	run_test "no GRO chk cmsg" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400 -S -1"
+
+	# the GSO packets are aggregated because:
+	# * veth schedule napi after each xmit
+	# * segmentation happens in BH context, veth napi poll is delayed after
+	#   the transmission of the last segment
+	run_test "GRO" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720"
+	run_test "GRO chk cmsg" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+	run_test "GRO with custom segment size" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720"
+	run_test "GRO with custom segment size cmsg" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720 -S 500"
+
+	run_nat_test "bad GRO lookup" "${ipv4_args} -M 1 -s 14720 -S 0" "-n 10 -l 1472"
+
+	echo "ipv6"
+	run_test "no GRO" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400"
+	run_test "no GRO chk cmsg" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400 -S -1"
+	run_test "GRO" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520"
+	run_test "GRO chk cmsg" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520 -S 1452"
+	run_test "GRO with custom segment size" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520"
+	run_test "GRO with custom segment size cmsg" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520 -S 500"
+
+	run_nat_test "bad GRO lookup" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 10 -l 1452"
+}
+
+if [ ! -f ../bpf/xdp_dummy.o ]; then
+	echo "Missing xdp_dummy helper. Build bpf selftest first"
+	exit -1
+fi
+
+if [[ $# -eq 0 ]]; then
+	run_all
+elif [[ $1 == "__subprocess" ]]; then
+	shift
+	run_one $@
+elif [[ $1 == "__subprocess_nat" ]]; then
+	shift
+	run_one_nat $@
+fi
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index 9ef4b1ee0f76..820bc50f6b68 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -18,7 +18,9 @@ run_one() {
 	# use 'rx' as separator between sender args and receiver args
 	local -r all="$@"
 	local -r tx_args=${all%rx*}
-	local -r rx_args=${all#*rx}
+	local rx_args=${all#*rx}
+
+	[[ "${tx_args}" == *"-4"* ]] && rx_args="${rx_args} -4"
 
 	ip netns add "${PEER_NS}"
 	ip -netns "${PEER_NS}" link set lo up
@@ -51,10 +53,10 @@ run_udp() {
 	local -r args=$@
 
 	echo "udp gso - over veth touching data"
-	run_in_netns ${args} -S rx
+	run_in_netns ${args} -S 0 rx
 
 	echo "udp gso and gro - over veth touching data"
-	run_in_netns ${args} -S rx -G
+	run_in_netns ${args} -S 0 rx -G
 }
 
 run_tcp() {
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 99e537ab5ad9..0f0628613f81 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -34,7 +34,7 @@ run_udp() {
 	run_in_netns ${args}
 
 	echo "udp gso"
-	run_in_netns ${args} -S
+	run_in_netns ${args} -S 0
 }
 
 run_tcp() {
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index 8f48d7fb32cf..0c960f673324 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -40,6 +40,12 @@ static bool cfg_tcp;
 static bool cfg_verify;
 static bool cfg_read_all;
 static bool cfg_gro_segment;
+static int  cfg_family		= PF_INET6;
+static int  cfg_alen 		= sizeof(struct sockaddr_in6);
+static int  cfg_expected_pkt_nr;
+static int  cfg_expected_pkt_len;
+static int  cfg_expected_gso_size;
+static struct sockaddr_storage cfg_bind_addr;
 
 static bool interrupted;
 static unsigned long packets, bytes;
@@ -50,6 +56,29 @@ static void sigint_handler(int signum)
 		interrupted = true;
 }
 
+static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr)
+{
+	struct sockaddr_in6 *addr6 = (void *) sockaddr;
+	struct sockaddr_in *addr4 = (void *) sockaddr;
+
+	switch (domain) {
+	case PF_INET:
+		addr4->sin_family = AF_INET;
+		addr4->sin_port = htons(cfg_port);
+		if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+			error(1, 0, "ipv4 parse error: %s", str_addr);
+		break;
+	case PF_INET6:
+		addr6->sin6_family = AF_INET6;
+		addr6->sin6_port = htons(cfg_port);
+		if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+			error(1, 0, "ipv6 parse error: %s", str_addr);
+		break;
+	default:
+		error(1, 0, "illegal domain");
+	}
+}
+
 static unsigned long gettimeofday_ms(void)
 {
 	struct timeval tv;
@@ -83,10 +112,9 @@ static void do_poll(int fd)
 
 static int do_socket(bool do_tcp)
 {
-	struct sockaddr_in6 addr = {0};
 	int fd, val;
 
-	fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+	fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
 	if (fd == -1)
 		error(1, errno, "socket");
 
@@ -97,10 +125,7 @@ static int do_socket(bool do_tcp)
 	if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val)))
 		error(1, errno, "setsockopt reuseport");
 
-	addr.sin6_family =	PF_INET6;
-	addr.sin6_port =	htons(cfg_port);
-	addr.sin6_addr =	in6addr_any;
-	if (bind(fd, (void *) &addr, sizeof(addr)))
+	if (bind(fd, (void *)&cfg_bind_addr, cfg_alen))
 		error(1, errno, "bind");
 
 	if (do_tcp) {
@@ -174,52 +199,117 @@ static void do_verify_udp(const char *data, int len)
 	}
 }
 
+static int recv_msg(int fd, char *buf, int len, int *gso_size)
+{
+	char control[CMSG_SPACE(sizeof(uint16_t))] = {0};
+	struct msghdr msg = {0};
+	struct iovec iov = {0};
+	struct cmsghdr *cmsg;
+	uint16_t *gsosizeptr;
+	int ret;
+
+	iov.iov_base = buf;
+	iov.iov_len = len;
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+
+	msg.msg_control = control;
+	msg.msg_controllen = sizeof(control);
+
+	*gso_size = -1;
+	ret = recvmsg(fd, &msg, MSG_TRUNC | MSG_DONTWAIT);
+	if (ret != -1) {
+		for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL;
+		     cmsg = CMSG_NXTHDR(&msg, cmsg)) {
+			if (cmsg->cmsg_level == SOL_UDP
+			    && cmsg->cmsg_type == UDP_GRO) {
+				gsosizeptr = (uint16_t *) CMSG_DATA(cmsg);
+				*gso_size = *gsosizeptr;
+				break;
+			}
+		}
+	}
+	return ret;
+}
+
 /* Flush all outstanding datagrams. Verify first few bytes of each. */
 static void do_flush_udp(int fd)
 {
 	static char rbuf[ETH_MAX_MTU];
-	int ret, len, budget = 256;
+	int ret, len, gso_size, budget = 256;
 
 	len = cfg_read_all ? sizeof(rbuf) : 0;
 	while (budget--) {
 		/* MSG_TRUNC will make return value full datagram length */
-		ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+		if (!cfg_expected_gso_size)
+			ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+		else
+			ret = recv_msg(fd, rbuf, len, &gso_size);
 		if (ret == -1 && errno == EAGAIN)
-			return;
+			break;
 		if (ret == -1)
 			error(1, errno, "recv");
+		if (cfg_expected_pkt_len && ret != cfg_expected_pkt_len)
+			error(1, 0, "recv: bad packet len, got %d,"
+			      " expected %d\n", ret, cfg_expected_pkt_len);
 		if (len && cfg_verify) {
 			if (ret == 0)
 				error(1, errno, "recv: 0 byte datagram\n");
 
 			do_verify_udp(rbuf, ret);
 		}
+		if (cfg_expected_gso_size && cfg_expected_gso_size != gso_size)
+			error(1, 0, "recv: bad gso size, got %d, expected %d "
+			      "(-1 == no gso cmsg))\n", gso_size,
+			      cfg_expected_gso_size);
 
 		packets++;
 		bytes += ret;
+		if (cfg_expected_pkt_nr && packets >= cfg_expected_pkt_nr)
+			break;
 	}
 }
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-Grtv] [-p port]", filepath);
+	error(1, 0, "Usage: %s [-Grtv] [-b addr] [-p port] [-l pktlen] [-n packetnr] [-S gsosize]", filepath);
 }
 
 static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "Gp:rtv")) != -1) {
+	/* bind to any by default */
+	setup_sockaddr(PF_INET6, "::", &cfg_bind_addr);
+	while ((c = getopt(argc, argv, "4b:Gl:n:p:rS:tv")) != -1) {
 		switch (c) {
+		case '4':
+			cfg_family = PF_INET;
+			cfg_alen = sizeof(struct sockaddr_in);
+			setup_sockaddr(PF_INET, "0.0.0.0", &cfg_bind_addr);
+			break;
+		case 'b':
+			setup_sockaddr(cfg_family, optarg, &cfg_bind_addr);
+			break;
 		case 'G':
 			cfg_gro_segment = true;
 			break;
+		case 'l':
+			cfg_expected_pkt_len = strtoul(optarg, NULL, 0);
+			break;
+		case 'n':
+			cfg_expected_pkt_nr = strtoul(optarg, NULL, 0);
+			break;
 		case 'p':
 			cfg_port = strtoul(optarg, NULL, 0);
 			break;
 		case 'r':
 			cfg_read_all = true;
 			break;
+		case 'S':
+			cfg_expected_gso_size = strtol(optarg, NULL, 0);
+			break;
 		case 't':
 			cfg_tcp = true;
 			break;
@@ -240,7 +330,7 @@ static void parse_opts(int argc, char **argv)
 static void do_recv(void)
 {
 	unsigned long tnow, treport;
-	int fd;
+	int fd, loop = 0;
 
 	fd = do_socket(cfg_tcp);
 
@@ -252,6 +342,11 @@ static void do_recv(void)
 
 	treport = gettimeofday_ms() + 1000;
 	do {
+		/* force termination after the second poll(); this cope both
+		 * with sender slower than receiver and missing packet errors
+		 */
+		if (cfg_expected_pkt_nr && loop++)
+			interrupted = true;
 		do_poll(fd);
 
 		if (cfg_tcp)
@@ -272,6 +367,10 @@ static void do_recv(void)
 
 	} while (!interrupted);
 
+	if (cfg_expected_pkt_nr && (packets != cfg_expected_pkt_nr))
+		error(1, 0, "wrong packet number! got %ld, expected %d\n",
+		      packets, cfg_expected_pkt_nr);
+
 	if (close(fd))
 		error(1, errno, "close");
 }
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
index e821564053cf..4074538b5df5 100644
--- a/tools/testing/selftests/net/udpgso_bench_tx.c
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -52,6 +52,8 @@ static bool	cfg_segment;
 static bool	cfg_sendmmsg;
 static bool	cfg_tcp;
 static bool	cfg_zerocopy;
+static int	cfg_msg_nr;
+static uint16_t	cfg_gso_size;
 
 static socklen_t cfg_alen;
 static struct sockaddr_storage cfg_dst_addr;
@@ -205,14 +207,14 @@ static void send_udp_segment_cmsg(struct cmsghdr *cm)
 
 	cm->cmsg_level = SOL_UDP;
 	cm->cmsg_type = UDP_SEGMENT;
-	cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss));
+	cm->cmsg_len = CMSG_LEN(sizeof(cfg_gso_size));
 	valp = (void *)CMSG_DATA(cm);
-	*valp = cfg_mss;
+	*valp = cfg_gso_size;
 }
 
 static int send_udp_segment(int fd, char *data)
 {
-	char control[CMSG_SPACE(sizeof(cfg_mss))] = {0};
+	char control[CMSG_SPACE(sizeof(cfg_gso_size))] = {0};
 	struct msghdr msg = {0};
 	struct iovec iov = {0};
 	int ret;
@@ -241,7 +243,7 @@ static int send_udp_segment(int fd, char *data)
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]",
+	error(1, 0, "Usage: %s [-46cmtuz] [-C cpu] [-D dst ip] [-l secs] [-m messagenr] [-p port] [-s sendsize] [-S gsosize]",
 		    filepath);
 }
 
@@ -250,7 +252,7 @@ static void parse_opts(int argc, char **argv)
 	int max_len, hdrlen;
 	int c;
 
-	while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) {
+	while ((c = getopt(argc, argv, "46cC:D:l:mM:p:s:S:tuz")) != -1) {
 		switch (c) {
 		case '4':
 			if (cfg_family != PF_UNSPEC)
@@ -279,6 +281,9 @@ static void parse_opts(int argc, char **argv)
 		case 'm':
 			cfg_sendmmsg = true;
 			break;
+		case 'M':
+			cfg_msg_nr = strtoul(optarg, NULL, 10);
+			break;
 		case 'p':
 			cfg_port = strtoul(optarg, NULL, 0);
 			break;
@@ -286,6 +291,7 @@ static void parse_opts(int argc, char **argv)
 			cfg_payload_len = strtoul(optarg, NULL, 0);
 			break;
 		case 'S':
+			cfg_gso_size = strtoul(optarg, NULL, 0);
 			cfg_segment = true;
 			break;
 		case 't':
@@ -317,6 +323,8 @@ static void parse_opts(int argc, char **argv)
 
 	cfg_mss = ETH_DATA_LEN - hdrlen;
 	max_len = ETH_MAX_MTU - hdrlen;
+	if (!cfg_gso_size)
+		cfg_gso_size = cfg_mss;
 
 	if (cfg_payload_len > max_len)
 		error(1, 0, "payload length %u exceeds max %u",
@@ -392,10 +400,12 @@ int main(int argc, char **argv)
 		else
 			num_sends += send_udp(fd, buf[i]);
 		num_msgs++;
-
 		if (cfg_zerocopy && ((num_msgs & 0xF) == 0))
 			flush_zerocopy(fd);
 
+		if (cfg_msg_nr && num_msgs >= cfg_msg_nr)
+			break;
+
 		tnow = gettimeofday_ms();
 		if (tnow > treport) {
 			fprintf(stderr,
-- 
cgit v1.2.3


From 8572a1b4dbc0e03d7082d8e8f7a282c0f55c3ca5 Mon Sep 17 00:00:00 2001
From: Justin Chen <justinpopo6@gmail.com>
Date: Tue, 6 Nov 2018 16:37:44 -0800
Subject: net: phy: bcm7xxx: Add entry for BCM7255

Add support for BCM7255 EPHY.

Signed-off-by: Justin Chen <justinpopo6@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm7xxx.c | 2 ++
 include/linux/brcmphy.h   | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index b2b6307d64a4..712224cc442d 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -650,6 +650,7 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev)
 
 static struct phy_driver bcm7xxx_driver[] = {
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"),
+	BCM7XXX_28NM_EPHY(PHY_ID_BCM7255, "Broadcom BCM7255"),
 	BCM7XXX_28NM_EPHY(PHY_ID_BCM7260, "Broadcom BCM7260"),
 	BCM7XXX_28NM_EPHY(PHY_ID_BCM7268, "Broadcom BCM7268"),
 	BCM7XXX_28NM_EPHY(PHY_ID_BCM7271, "Broadcom BCM7271"),
@@ -670,6 +671,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 
 static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
 	{ PHY_ID_BCM7250, 0xfffffff0, },
+	{ PHY_ID_BCM7255, 0xfffffff0, },
 	{ PHY_ID_BCM7260, 0xfffffff0, },
 	{ PHY_ID_BCM7268, 0xfffffff0, },
 	{ PHY_ID_BCM7271, 0xfffffff0, },
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 949e9af8d9d6..9cd00a37b8d3 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -28,6 +28,7 @@
 #define PHY_ID_BCM89610			0x03625cd0
 
 #define PHY_ID_BCM7250			0xae025280
+#define PHY_ID_BCM7255			0xae025120
 #define PHY_ID_BCM7260			0xae025190
 #define PHY_ID_BCM7268			0xae025090
 #define PHY_ID_BCM7271			0xae0253b0
-- 
cgit v1.2.3


From f908620019324872ce0776b37b27a31dfd8c05a0 Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Wed, 7 Nov 2018 08:50:34 +0800
Subject: net: dsa: bcm_sf2: fix semicolon.cocci warnings

drivers/net/dsa/bcm_sf2_cfp.c:1168:2-3: Unneeded semicolon
drivers/net/dsa/bcm_sf2_cfp.c:532:2-3: Unneeded semicolon

 Remove unneeded semicolon.

Generated by: scripts/coccinelle/misc/semicolon.cocci

Fixes: ae7a5aff783c ("net: dsa: bcm_sf2: Keep copy of inserted rules")
CC: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2_cfp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 8f734abde7b3..e14663ab6dbc 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -529,7 +529,7 @@ static struct cfp_rule *bcm_sf2_cfp_rule_find(struct bcm_sf2_priv *priv,
 	list_for_each_entry(rule, &priv->cfp.rules_list, next) {
 		if (rule->port == port && rule->fs.location == location)
 			break;
-	};
+	}
 
 	return rule;
 }
@@ -1165,7 +1165,7 @@ int bcm_sf2_cfp_resume(struct dsa_switch *ds)
 			dev_err(ds->dev, "failed to restore rule\n");
 			return ret;
 		}
-	};
+	}
 
 	return ret;
 }
-- 
cgit v1.2.3


From a3320bcf28e07163354b0acfad874bf46209df63 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 7 Nov 2018 08:15:58 +0100
Subject: net: phy: make phy_trigger_machine static

phy_trigger_machine() is used in phy.c only, so we can make it static.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 33 ++++++++++++---------------------
 include/linux/phy.h   |  1 -
 2 files changed, 12 insertions(+), 22 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 1d73ac3309ce..476578746d91 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -467,6 +467,18 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL(phy_mii_ioctl);
 
+static void phy_queue_state_machine(struct phy_device *phydev,
+				    unsigned int secs)
+{
+	mod_delayed_work(system_power_efficient_wq, &phydev->state_queue,
+			 secs * HZ);
+}
+
+static void phy_trigger_machine(struct phy_device *phydev)
+{
+	phy_queue_state_machine(phydev, 0);
+}
+
 static int phy_config_aneg(struct phy_device *phydev)
 {
 	if (phydev->drv->config_aneg)
@@ -620,13 +632,6 @@ int phy_speed_up(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(phy_speed_up);
 
-static void phy_queue_state_machine(struct phy_device *phydev,
-				    unsigned int secs)
-{
-	mod_delayed_work(system_power_efficient_wq, &phydev->state_queue,
-			 secs * HZ);
-}
-
 /**
  * phy_start_machine - start PHY state machine tracking
  * @phydev: the phy_device struct
@@ -643,20 +648,6 @@ void phy_start_machine(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(phy_start_machine);
 
-/**
- * phy_trigger_machine - trigger the state machine to run
- *
- * @phydev: the phy_device struct
- *
- * Description: There has been a change in state which requires that the
- *   state machine runs.
- */
-
-void phy_trigger_machine(struct phy_device *phydev)
-{
-	phy_queue_state_machine(phydev, 0);
-}
-
 /**
  * phy_stop_machine - stop the PHY state machine tracking
  * @phydev: target phy_device struct
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3ea87f774a76..9e4d49ef4bca 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1054,7 +1054,6 @@ void phy_change_work(struct work_struct *work);
 void phy_mac_interrupt(struct phy_device *phydev);
 void phy_start_machine(struct phy_device *phydev);
 void phy_stop_machine(struct phy_device *phydev);
-void phy_trigger_machine(struct phy_device *phydev);
 int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd);
 void phy_ethtool_ksettings_get(struct phy_device *phydev,
 			       struct ethtool_link_ksettings *cmd);
-- 
cgit v1.2.3


From 3b73e842c7265a645f373a2de956ad36292f819d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 7 Nov 2018 08:52:46 +0100
Subject: net: phy: realtek: load driver for all PHYs with a Realtek OUI

Instead of listing every single PHYID, load the driver for every PHYID
with a Realtek OUI, independent of model number and revision.

This patch also improves two further aspects:
- constify realtek_tbl[]
- the mask should have been 0xffffffff instead of 0x001fffff so far,
  by masking out some bits a PHY from another vendor could have been
  matched

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/realtek.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 271e8adc39f1..7b1c89b3833c 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -305,15 +305,8 @@ static struct phy_driver realtek_drvs[] = {
 
 module_phy_driver(realtek_drvs);
 
-static struct mdio_device_id __maybe_unused realtek_tbl[] = {
-	{ 0x001cc816, 0x001fffff },
-	{ 0x001cc910, 0x001fffff },
-	{ 0x001cc912, 0x001fffff },
-	{ 0x001cc913, 0x001fffff },
-	{ 0x001cc914, 0x001fffff },
-	{ 0x001cc915, 0x001fffff },
-	{ 0x001cc916, 0x001fffff },
-	{ 0x001cc961, 0x001fffff },
+static const struct mdio_device_id __maybe_unused realtek_tbl[] = {
+	{ 0x001cc800, GENMASK(31, 10) },
 	{ }
 };
 
-- 
cgit v1.2.3


From 2e7ad56aa54778de863998579fc6b5ff52838571 Mon Sep 17 00:00:00 2001
From: Mathias Thore <mathias.thore@infinera.com>
Date: Wed, 7 Nov 2018 09:09:45 +0100
Subject: net/wan/fsl_ucc_hdlc: add BQL support

Add byte queue limits support in the fsl_ucc_hdlc driver.

Signed-off-by: Mathias Thore <mathias.thore@infinera.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/fsl_ucc_hdlc.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index 4d6409605207..7a42336c8af8 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -391,6 +391,7 @@ static netdev_tx_t ucc_hdlc_tx(struct sk_buff *skb, struct net_device *dev)
 		dev_kfree_skb(skb);
 		return -ENOMEM;
 	}
+	netdev_sent_queue(dev, skb->len);
 	spin_lock_irqsave(&priv->lock, flags);
 
 	/* Start from the next BD that should be filled */
@@ -447,6 +448,8 @@ static int hdlc_tx_done(struct ucc_hdlc_private *priv)
 {
 	/* Start from the next BD that should be filled */
 	struct net_device *dev = priv->ndev;
+	unsigned int bytes_sent = 0;
+	int howmany = 0;
 	struct qe_bd *bd;		/* BD pointer */
 	u16 bd_status;
 	int tx_restart = 0;
@@ -474,6 +477,8 @@ static int hdlc_tx_done(struct ucc_hdlc_private *priv)
 		skb = priv->tx_skbuff[priv->skb_dirtytx];
 		if (!skb)
 			break;
+		howmany++;
+		bytes_sent += skb->len;
 		dev->stats.tx_packets++;
 		memset(priv->tx_buffer +
 		       (be32_to_cpu(bd->buf) - priv->dma_tx_addr),
@@ -501,6 +506,7 @@ static int hdlc_tx_done(struct ucc_hdlc_private *priv)
 	if (tx_restart)
 		hdlc_tx_restart(priv);
 
+	netdev_completed_queue(dev, howmany, bytes_sent);
 	return 0;
 }
 
@@ -721,6 +727,7 @@ static int uhdlc_open(struct net_device *dev)
 		priv->hdlc_busy = 1;
 		netif_device_attach(priv->ndev);
 		napi_enable(&priv->napi);
+		netdev_reset_queue(dev);
 		netif_start_queue(dev);
 		hdlc_open(dev);
 	}
@@ -812,6 +819,7 @@ static int uhdlc_close(struct net_device *dev)
 
 	free_irq(priv->ut_info->uf_info.irq, priv);
 	netif_stop_queue(dev);
+	netdev_reset_queue(dev);
 	priv->hdlc_busy = 0;
 
 	return 0;
-- 
cgit v1.2.3


From f29eb2a96c56ebff6b4d9b530d5ccd61b9f538d7 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 10:34:36 +0100
Subject: tun: compute the RFS hash only if needed.

The tun XDP sendmsg code path, unconditionally computes the symmetric
hash of each packet for RFS's sake, even when we could skip it. e.g.
when the device has a single queue.

This change adds the check already in-place for the skb sendmsg path
to avoid unneeded hashing.

The above gives small, but measurable, performance gain for VM xmit
path when zerocopy is not enabled.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 060135ceaf0e..a65779c6d72f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2448,7 +2448,8 @@ build:
 			goto out;
 	}
 
-	if (!rcu_dereference(tun->steering_prog))
+	if (!rcu_dereference(tun->steering_prog) && tun->numqueues > 1 &&
+	    !tfile->detached)
 		rxhash = __skb_get_hash_symmetric(skb);
 
 	netif_receive_skb(skb);
-- 
cgit v1.2.3


From 7dad9937e064a6411cc3427f3f5870fa72132ad8 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 7 Nov 2018 11:28:18 +0100
Subject: net: vlan: add support for tunnel offload

GSO tunneled packets are always segmented in software before they are
transmitted by a VLAN, even when the lower device can offload tunnel
encapsulation and VLAN together (i.e., some bits in NETIF_F_GSO_ENCAP_ALL
mask are set in the lower device 'vlan_features'). If we let VLANs have
the same tunnel offload capabilities as their lower device, throughput
can improve significantly when CPU is limited on the transmitter side.

 - set NETIF_F_GSO_ENCAP_ALL bits in the VLAN 'hw_features', to ensure
 that 'features' will have those bits zeroed only when the lower device
 has no hardware support for tunnel encapsulation.
 - for the same reason, copy GSO-related bits of 'hw_enc_features' from
 lower device to VLAN, and ensure to update that value when the lower
 device changes its features.
 - set NETIF_F_HW_CSUM bit in the VLAN 'hw_enc_features' if 'real_dev'
 is able to compute checksums at least for a kind of packets, like done
 with commit 8403debeead8 ("vlan: Keep NETIF_F_HW_CSUM similar to other
 software devices"). This avoids software segmentation due to mismatching
 checksum capabilities between VLAN's 'features' and 'hw_enc_features'.

Reported-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan.c     |  1 +
 net/8021q/vlan.h     | 12 ++++++++++++
 net/8021q/vlan_dev.c |  2 ++
 3 files changed, 15 insertions(+)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 5e9950453955..1b7a375c6616 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -330,6 +330,7 @@ static void vlan_transfer_features(struct net_device *dev,
 
 	vlandev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 	vlandev->priv_flags |= (vlan->real_dev->priv_flags & IFF_XMIT_DST_RELEASE);
+	vlandev->hw_enc_features = vlan_tnl_features(vlan->real_dev);
 
 	netdev_update_features(vlandev);
 }
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 44df1c3df02d..c46daf09a501 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -92,6 +92,18 @@ static inline struct net_device *vlan_find_dev(struct net_device *real_dev,
 	return NULL;
 }
 
+static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev)
+{
+	netdev_features_t ret;
+
+	ret = real_dev->hw_enc_features &
+	      (NETIF_F_CSUM_MASK | NETIF_F_ALL_TSO | NETIF_F_GSO_ENCAP_ALL);
+
+	if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK))
+		return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM;
+	return 0;
+}
+
 #define vlan_group_for_each_dev(grp, i, dev) \
 	for ((i) = 0; i < VLAN_PROTO_NUM * VLAN_N_VID; i++) \
 		if (((dev) = __vlan_group_get_device((grp), (i) / VLAN_N_VID, \
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index ff720f1ebf73..b2d9c8f27cd7 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -562,6 +562,7 @@ static int vlan_dev_init(struct net_device *dev)
 
 	dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG |
 			   NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE |
+			   NETIF_F_GSO_ENCAP_ALL |
 			   NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC |
 			   NETIF_F_ALL_FCOE;
 
@@ -572,6 +573,7 @@ static int vlan_dev_init(struct net_device *dev)
 		netdev_warn(real_dev, "VLAN features are set incorrectly.  Q-in-Q configurations may not work correctly.\n");
 
 	dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE;
+	dev->hw_enc_features = vlan_tnl_features(real_dev);
 
 	/* ipv6 shared card related stuff */
 	dev->dev_id = real_dev->dev_id;
-- 
cgit v1.2.3


From 1295e2cf3065a55f35d112e4dfeb2c7322823249 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Wed, 7 Nov 2018 19:20:16 +0800
Subject: inet: minor optimization for backlog setting in listen(2)

Set the backlog earlier in inet_dccp_listen() and inet_listen(),
then we can avoid the redundant setting.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c                | 2 +-
 net/ipv4/af_inet.c              | 2 +-
 net/ipv4/inet_connection_sock.c | 1 -
 3 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 43733accf58e..658cd32bb7b3 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -948,6 +948,7 @@ int inet_dccp_listen(struct socket *sock, int backlog)
 	if (!((1 << old_state) & (DCCPF_CLOSED | DCCPF_LISTEN)))
 		goto out;
 
+	sk->sk_max_ack_backlog = backlog;
 	/* Really, if the socket is already in listen state
 	 * we can only allow the backlog to be adjusted.
 	 */
@@ -960,7 +961,6 @@ int inet_dccp_listen(struct socket *sock, int backlog)
 		if (err)
 			goto out;
 	}
-	sk->sk_max_ack_backlog = backlog;
 	err = 0;
 
 out:
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 07749c5b0a50..326c422c22f8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -208,6 +208,7 @@ int inet_listen(struct socket *sock, int backlog)
 	if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		goto out;
 
+	sk->sk_max_ack_backlog = backlog;
 	/* Really, if the socket is already in listen state
 	 * we can only allow the backlog to be adjusted.
 	 */
@@ -231,7 +232,6 @@ int inet_listen(struct socket *sock, int backlog)
 			goto out;
 		tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL);
 	}
-	sk->sk_max_ack_backlog = backlog;
 	err = 0;
 
 out:
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5c63449130d9..6ea523d71947 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -881,7 +881,6 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
 
 	reqsk_queue_alloc(&icsk->icsk_accept_queue);
 
-	sk->sk_max_ack_backlog = backlog;
 	sk->sk_ack_backlog = 0;
 	inet_csk_delack_init(sk);
 
-- 
cgit v1.2.3


From c8accd5a0a6abfc0405a331afa5bfc06ee92623a Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Wed, 7 Nov 2018 18:07:02 +0100
Subject: net/vlan: introduce __vlan_hwaccel_clear_tag() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 83ea4df6ab81..c438fa0a1c6a 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -461,6 +461,17 @@ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb,
 	return skb;
 }
 
+/**
+ * __vlan_hwaccel_clear_tag - clear hardware accelerated VLAN info
+ * @skb: skbuff to clear
+ *
+ * Clears the VLAN information from @skb
+ */
+static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb)
+{
+	skb->vlan_tci = 0;
+}
+
 /*
  * __vlan_hwaccel_push_inside - pushes vlan tag to the payload
  * @skb: skbuff to tag
@@ -475,7 +486,7 @@ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb)
 	skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
 					skb_vlan_tag_get(skb));
 	if (likely(skb))
-		skb->vlan_tci = 0;
+		__vlan_hwaccel_clear_tag(skb);
 	return skb;
 }
 
-- 
cgit v1.2.3


From e0a6b8097351255a2dbbb45274a8b9c52850cbb6 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Wed, 7 Nov 2018 18:07:02 +0100
Subject: net/vlan: introduce __vlan_hwaccel_copy_tag() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index c438fa0a1c6a..941da4bf3929 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -472,6 +472,19 @@ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb)
 	skb->vlan_tci = 0;
 }
 
+/**
+ * __vlan_hwaccel_copy_tag - copy hardware accelerated VLAN info from another skb
+ * @dst: skbuff to copy to
+ * @src: skbuff to copy from
+ *
+ * Copies VLAN information from @src to @dst (for branchless code)
+ */
+static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src)
+{
+	dst->vlan_proto = src->vlan_proto;
+	dst->vlan_tci = src->vlan_tci;
+}
+
 /*
  * __vlan_hwaccel_push_inside - pushes vlan tag to the payload
  * @skb: skbuff to tag
-- 
cgit v1.2.3


From 9b319148cb34ecccacff09eca87765c87d5e19ff Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Wed, 7 Nov 2018 18:07:03 +0100
Subject: net/vlan: include the shift in skb_vlan_tag_get_prio()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h   | 2 +-
 net/core/flow_dissector.c | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 941da4bf3929..b14bf87999aa 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -81,7 +81,7 @@ static inline bool is_vlan_dev(const struct net_device *dev)
 #define skb_vlan_tag_present(__skb)	((__skb)->vlan_tci & VLAN_TAG_PRESENT)
 #define skb_vlan_tag_get(__skb)		((__skb)->vlan_tci & ~VLAN_TAG_PRESENT)
 #define skb_vlan_tag_get_id(__skb)	((__skb)->vlan_tci & VLAN_VID_MASK)
-#define skb_vlan_tag_get_prio(__skb)	((__skb)->vlan_tci & VLAN_PRIO_MASK)
+#define skb_vlan_tag_get_prio(__skb)	(((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT)
 
 static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev)
 {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 676f3ad629f9..56d1e9b73142 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -952,8 +952,7 @@ proto_again:
 
 			if (!vlan) {
 				key_vlan->vlan_id = skb_vlan_tag_get_id(skb);
-				key_vlan->vlan_priority =
-					(skb_vlan_tag_get_prio(skb) >> VLAN_PRIO_SHIFT);
+				key_vlan->vlan_priority = skb_vlan_tag_get_prio(skb);
 			} else {
 				key_vlan->vlan_id = ntohs(vlan->h_vlan_TCI) &
 					VLAN_VID_MASK;
-- 
cgit v1.2.3


From 295d072a42fe1a654e765fffcaadb2f08a692dd0 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Wed, 7 Nov 2018 18:07:03 +0100
Subject: net/vlan: remove unused #define HAVE_VLAN_GET_TAG
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index b14bf87999aa..03b08ffded07 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -555,8 +555,6 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb,
 	}
 }
 
-#define HAVE_VLAN_GET_TAG
-
 /**
  * vlan_get_tag - get the VLAN ID from the skb
  * @skb: skbuff to query
-- 
cgit v1.2.3


From cea0604d3f94ef41878d6e484ffeb67a8129ab5a Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Wed, 7 Nov 2018 18:12:42 +0000
Subject: sfc: add missing NVRAM partition types for EF10

Expose the MUM/SUC Firmware, UEFI Expansion ROM and MC Status partitions
 of the NIC's NVRAM as MTDs if found on the NIC.  The first two are needed
 in order to properly update them when performing firmware updates; the MC
 Status partition is used to determine whether a signed firmware image was
 accepted or rejected by a Secure NIC.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 7eeac3d6cfe8..b6a50058bb8d 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -6041,6 +6041,10 @@ static const struct efx_ef10_nvram_type_info efx_ef10_nvram_types[] = {
 	{ NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT3, 0,   3, "sfc_exp_rom_cfg" },
 	{ NVRAM_PARTITION_TYPE_LICENSE,		   0,    0, "sfc_license" },
 	{ NVRAM_PARTITION_TYPE_PHY_MIN,		   0xff, 0, "sfc_phy_fw" },
+	/* MUM and SUC firmware share the same partition type */
+	{ NVRAM_PARTITION_TYPE_MUM_FIRMWARE,	   0,    0, "sfc_mumfw" },
+	{ NVRAM_PARTITION_TYPE_EXPANSION_UEFI,	   0,    0, "sfc_uefi" },
+	{ NVRAM_PARTITION_TYPE_STATUS,		   0,    0, "sfc_status" }
 };
 
 static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
@@ -6091,6 +6095,9 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 	part->common.mtd.flags = MTD_CAP_NORFLASH;
 	part->common.mtd.size = size;
 	part->common.mtd.erasesize = erase_size;
+	/* sfc_status is read-only */
+	if (!erase_size)
+		part->common.mtd.flags |= MTD_NO_ERASE;
 
 	return 0;
 }
-- 
cgit v1.2.3


From 1d10bd167667655362a7e2b407a96aad5979bfca Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Wed, 7 Nov 2018 18:32:48 +0000
Subject: net: add netif_is_geneve()

Add a helper function to determine if the type of a netdev is geneve based
on its rtnl_link_ops. This allows drivers that may wish to offload tunnels
to check the underlying type of the device.

A recent patch added a similar helper to vxlan.h

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/geneve.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/net/geneve.h b/include/net/geneve.h
index a7600ed55ea3..fc6a7e0a874a 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -60,6 +60,12 @@ struct genevehdr {
 	struct geneve_opt options[];
 };
 
+static inline bool netif_is_geneve(const struct net_device *dev)
+{
+	return dev->rtnl_link_ops &&
+	       !strcmp(dev->rtnl_link_ops->kind, "geneve");
+}
+
 #ifdef CONFIG_INET
 struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 					u8 name_assign_type, u16 dst_port);
-- 
cgit v1.2.3


From 83f27d027da3a1d4fff95fd66df0c0100b66ae4c Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Wed, 7 Nov 2018 18:32:49 +0000
Subject: nfp: flower: use geneve and vxlan helpers

Make use of the recently added VXLAN and geneve helper functions to
determine the type of the netdev from its rtnl_link_ops.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index cfea8f790f95..fbc052d5bb47 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -11,6 +11,7 @@
 #include <net/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_vlan.h>
 #include <net/tc_act/tc_tunnel_key.h>
+#include <net/vxlan.h>
 
 #include "cmsg.h"
 #include "main.h"
@@ -94,13 +95,10 @@ nfp_fl_pre_lag(struct nfp_app *app, const struct tc_action *action,
 static bool nfp_fl_netdev_is_tunnel_type(struct net_device *out_dev,
 					 enum nfp_flower_tun_type tun_type)
 {
-	if (!out_dev->rtnl_link_ops)
-		return false;
-
-	if (!strcmp(out_dev->rtnl_link_ops->kind, "vxlan"))
+	if (netif_is_vxlan(out_dev))
 		return tun_type == NFP_FL_TUNNEL_VXLAN;
 
-	if (!strcmp(out_dev->rtnl_link_ops->kind, "geneve"))
+	if (netif_is_geneve(out_dev))
 		return tun_type == NFP_FL_TUNNEL_GENEVE;
 
 	return false;
-- 
cgit v1.2.3


From e963e1097ad3c9f2062e10356af8c89de245c6b2 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Wed, 7 Nov 2018 18:32:50 +0000
Subject: nfp: flower: include geneve as supported offload tunnel type

Offload of geneve decap rules is supported in NFP. Include geneve in the
check for supported types.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index fb6442d820b5..5d641d7dabff 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -190,6 +190,8 @@ static bool nfp_tun_is_netdev_to_offload(struct net_device *netdev)
 		return true;
 	if (netif_is_vxlan(netdev))
 		return true;
+	if (netif_is_geneve(netdev))
+		return true;
 
 	return false;
 }
-- 
cgit v1.2.3


From 3b01ea72f34cf8e18d16d993bb20f3cd241e4e52 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 7 Nov 2018 20:43:20 +0100
Subject: net: phy: remove useless check in state machine case PHY_NOLINK

If aneg is enabled and the PHY reports the link as up then definitely
aneg finished successfully. Therefore this check is useless and
can be removed.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 476578746d91..87c6d304cbc8 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -970,17 +970,6 @@ void phy_state_machine(struct work_struct *work)
 			break;
 
 		if (phydev->link) {
-			if (AUTONEG_ENABLE == phydev->autoneg) {
-				err = phy_aneg_done(phydev);
-				if (err < 0)
-					break;
-
-				if (!err) {
-					phydev->state = PHY_AN;
-					phydev->link_timeout = PHY_AN_TIMEOUT;
-					break;
-				}
-			}
 			phydev->state = PHY_RUNNING;
 			phy_link_up(phydev);
 		}
-- 
cgit v1.2.3


From c96469f830568d8859cd65d723da3b79ec0219e0 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 7 Nov 2018 20:44:56 +0100
Subject: net: phy: remove useless check in state machine case PHY_RESUMING

If aneg isn't finished yet then the PHY reports the link as down.
There's no benefit in setting the state to PHY_AN because the next
state machine run would set the status to PHY_NOLINK anyway (except
in the meantime aneg has been finished and link is up). Therefore
we can set the state to PHY_RUNNING or PHY_NOLINK directly.

In addition change the do_carrier parameter in phy_link_down() to true.
If carrier was marked as up before (what should never be the case because
PHY was in state PHY_HALTED before) then we should mark it as down now.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 87c6d304cbc8..14dffa0da1b8 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1022,17 +1022,6 @@ void phy_state_machine(struct work_struct *work)
 		}
 		break;
 	case PHY_RESUMING:
-		if (AUTONEG_ENABLE == phydev->autoneg) {
-			err = phy_aneg_done(phydev);
-			if (err < 0) {
-				break;
-			} else if (!err) {
-				phydev->state = PHY_AN;
-				phydev->link_timeout = PHY_AN_TIMEOUT;
-				break;
-			}
-		}
-
 		err = phy_read_status(phydev);
 		if (err)
 			break;
@@ -1042,7 +1031,7 @@ void phy_state_machine(struct work_struct *work)
 			phy_link_up(phydev);
 		} else	{
 			phydev->state = PHY_NOLINK;
-			phy_link_down(phydev, false);
+			phy_link_down(phydev, true);
 		}
 		break;
 	}
-- 
cgit v1.2.3


From 74a992b3598ad22784ce238f59875b782e1ca537 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 7 Nov 2018 20:45:58 +0100
Subject: net: phy: add phy_check_link_status

In few places in the state machine the state is set to PHY_RUNNING or
PHY_NOLINK after doing a phy_read_status(). So factor this out to
phy_check_link_status().

First use it in phy_start_aneg(): By setting the state to PHY_RUNNING
or PHY_NOLINK directly we can remove the code to handle the case that
we're using interrupts and aneg was finished already.

Definition of phy_link_up and phy_link_down needs to be moved because
they are called in the new function.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 70 +++++++++++++++++++++++++++++----------------------
 1 file changed, 40 insertions(+), 30 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 14dffa0da1b8..87ed000307b7 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -62,6 +62,17 @@ static const char *phy_state_to_str(enum phy_state st)
 	return NULL;
 }
 
+static void phy_link_up(struct phy_device *phydev)
+{
+	phydev->phy_link_change(phydev, true, true);
+	phy_led_trigger_change_speed(phydev);
+}
+
+static void phy_link_down(struct phy_device *phydev, bool do_carrier)
+{
+	phydev->phy_link_change(phydev, false, do_carrier);
+	phy_led_trigger_change_speed(phydev);
+}
 
 /**
  * phy_print_status - Convenience function to print out the current phy status
@@ -493,6 +504,34 @@ static int phy_config_aneg(struct phy_device *phydev)
 	return genphy_config_aneg(phydev);
 }
 
+/**
+ * phy_check_link_status - check link status and set state accordingly
+ * @phydev: the phy_device struct
+ *
+ * Description: Check for link and whether autoneg was triggered / is running
+ * and set state accordingly
+ */
+static int phy_check_link_status(struct phy_device *phydev)
+{
+	int err;
+
+	WARN_ON(!mutex_is_locked(&phydev->lock));
+
+	err = phy_read_status(phydev);
+	if (err)
+		return err;
+
+	if (phydev->link && phydev->state != PHY_RUNNING) {
+		phydev->state = PHY_RUNNING;
+		phy_link_up(phydev);
+	} else if (!phydev->link && phydev->state != PHY_NOLINK) {
+		phydev->state = PHY_NOLINK;
+		phy_link_down(phydev, true);
+	}
+
+	return 0;
+}
+
 /**
  * phy_start_aneg - start auto-negotiation for this PHY device
  * @phydev: the phy_device struct
@@ -504,7 +543,6 @@ static int phy_config_aneg(struct phy_device *phydev)
  */
 int phy_start_aneg(struct phy_device *phydev)
 {
-	bool trigger = 0;
 	int err;
 
 	if (!phydev->drv)
@@ -524,32 +562,16 @@ int phy_start_aneg(struct phy_device *phydev)
 
 	if (phydev->state != PHY_HALTED) {
 		if (AUTONEG_ENABLE == phydev->autoneg) {
-			phydev->state = PHY_AN;
-			phydev->link_timeout = PHY_AN_TIMEOUT;
+			err = phy_check_link_status(phydev);
 		} else {
 			phydev->state = PHY_FORCING;
 			phydev->link_timeout = PHY_FORCE_TIMEOUT;
 		}
 	}
 
-	/* Re-schedule a PHY state machine to check PHY status because
-	 * negotiation may already be done and aneg interrupt may not be
-	 * generated.
-	 */
-	if (!phy_polling_mode(phydev) && phydev->state == PHY_AN) {
-		err = phy_aneg_done(phydev);
-		if (err > 0) {
-			trigger = true;
-			err = 0;
-		}
-	}
-
 out_unlock:
 	mutex_unlock(&phydev->lock);
 
-	if (trigger)
-		phy_trigger_machine(phydev);
-
 	return err;
 }
 EXPORT_SYMBOL(phy_start_aneg);
@@ -893,18 +915,6 @@ void phy_start(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_start);
 
-static void phy_link_up(struct phy_device *phydev)
-{
-	phydev->phy_link_change(phydev, true, true);
-	phy_led_trigger_change_speed(phydev);
-}
-
-static void phy_link_down(struct phy_device *phydev, bool do_carrier)
-{
-	phydev->phy_link_change(phydev, false, do_carrier);
-	phy_led_trigger_change_speed(phydev);
-}
-
 /**
  * phy_state_machine - Handle the state machine
  * @work: work_struct that describes the work to be done
-- 
cgit v1.2.3


From 85a1f31d6392fb2c6726fcc4e072de008e3f0656 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 7 Nov 2018 20:46:51 +0100
Subject: net: phy: remove state PHY_AN

After the recent changes in the state machine state PHY_AN isn't used
any longer and can be removed.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 27 ---------------------------
 include/linux/phy.h   | 19 +------------------
 2 files changed, 1 insertion(+), 45 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 87ed000307b7..226824804208 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -50,7 +50,6 @@ static const char *phy_state_to_str(enum phy_state st)
 	PHY_STATE_STR(READY)
 	PHY_STATE_STR(PENDING)
 	PHY_STATE_STR(UP)
-	PHY_STATE_STR(AN)
 	PHY_STATE_STR(RUNNING)
 	PHY_STATE_STR(NOLINK)
 	PHY_STATE_STR(FORCING)
@@ -944,32 +943,6 @@ void phy_state_machine(struct work_struct *work)
 	case PHY_UP:
 		needs_aneg = true;
 
-		phydev->link_timeout = PHY_AN_TIMEOUT;
-
-		break;
-	case PHY_AN:
-		err = phy_read_status(phydev);
-		if (err < 0)
-			break;
-
-		/* If the link is down, give up on negotiation for now */
-		if (!phydev->link) {
-			phydev->state = PHY_NOLINK;
-			phy_link_down(phydev, true);
-			break;
-		}
-
-		/* Check if negotiation is done.  Break if there's an error */
-		err = phy_aneg_done(phydev);
-		if (err < 0)
-			break;
-
-		/* If AN is done, we're running */
-		if (err > 0) {
-			phydev->state = PHY_RUNNING;
-			phy_link_up(phydev);
-		} else if (0 == phydev->link_timeout--)
-			needs_aneg = true;
 		break;
 	case PHY_NOLINK:
 		if (!phy_polling_mode(phydev))
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 9e4d49ef4bca..2090277eac4f 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -178,7 +178,6 @@ static inline const char *phy_modes(phy_interface_t interface)
 #define PHY_INIT_TIMEOUT	100000
 #define PHY_STATE_TIME		1
 #define PHY_FORCE_TIMEOUT	10
-#define PHY_AN_TIMEOUT		10
 
 #define PHY_MAX_ADDR	32
 
@@ -297,24 +296,10 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
  *
  * UP: The PHY and attached device are ready to do work.
  * Interrupts should be started here.
- * - timer moves to AN
- *
- * AN: The PHY is currently negotiating the link state.  Link is
- * therefore down for now.  phy_timer will set this state when it
- * detects the state is UP.  config_aneg will set this state
- * whenever called with phydev->autoneg set to AUTONEG_ENABLE.
- * - If autonegotiation finishes, but there's no link, it sets
- *   the state to NOLINK.
- * - If aneg finishes with link, it sets the state to RUNNING,
- *   and calls adjust_link
- * - If autonegotiation did not finish after an arbitrary amount
- *   of time, autonegotiation should be tried again if the PHY
- *   supports "magic" autonegotiation (back to AN)
- * - If it didn't finish, and no magic_aneg, move to FORCING.
+ * - timer moves to NOLINK or RUNNING
  *
  * NOLINK: PHY is up, but not currently plugged in.
  * - If the timer notes that the link comes back, we move to RUNNING
- * - config_aneg moves to AN
  * - phy_stop moves to HALTED
  *
  * FORCING: PHY is being configured with forced settings
@@ -329,7 +314,6 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
  *   link state is polled every other cycle of this state machine,
  *   which makes it every other second)
  * - irq will set CHANGELINK
- * - config_aneg will set AN
  * - phy_stop moves to HALTED
  *
  * CHANGELINK: PHY experienced a change in link state
@@ -353,7 +337,6 @@ enum phy_state {
 	PHY_READY,
 	PHY_PENDING,
 	PHY_UP,
-	PHY_AN,
 	PHY_RUNNING,
 	PHY_NOLINK,
 	PHY_FORCING,
-- 
cgit v1.2.3


From c8e977bab363006e5f5291ebf34ee5293cfb8515 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 7 Nov 2018 20:47:53 +0100
Subject: net: phy: use phy_check_link_status in more places in the state
 machine

Use phy_check_link_status in more places in the state machine.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 53 +++++----------------------------------------------
 1 file changed, 5 insertions(+), 48 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 226824804208..dd5bff955128 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -945,17 +945,13 @@ void phy_state_machine(struct work_struct *work)
 
 		break;
 	case PHY_NOLINK:
+	case PHY_RUNNING:
 		if (!phy_polling_mode(phydev))
 			break;
-
-		err = phy_read_status(phydev);
-		if (err)
-			break;
-
-		if (phydev->link) {
-			phydev->state = PHY_RUNNING;
-			phy_link_up(phydev);
-		}
+		/* fall through */
+	case PHY_CHANGELINK:
+	case PHY_RESUMING:
+		err = phy_check_link_status(phydev);
 		break;
 	case PHY_FORCING:
 		err = genphy_update_link(phydev);
@@ -971,32 +967,6 @@ void phy_state_machine(struct work_struct *work)
 			phy_link_down(phydev, false);
 		}
 		break;
-	case PHY_RUNNING:
-		if (!phy_polling_mode(phydev))
-			break;
-
-		err = phy_read_status(phydev);
-		if (err)
-			break;
-
-		if (!phydev->link) {
-			phydev->state = PHY_NOLINK;
-			phy_link_down(phydev, true);
-		}
-		break;
-	case PHY_CHANGELINK:
-		err = phy_read_status(phydev);
-		if (err)
-			break;
-
-		if (phydev->link) {
-			phydev->state = PHY_RUNNING;
-			phy_link_up(phydev);
-		} else {
-			phydev->state = PHY_NOLINK;
-			phy_link_down(phydev, true);
-		}
-		break;
 	case PHY_HALTED:
 		if (phydev->link) {
 			phydev->link = 0;
@@ -1004,19 +974,6 @@ void phy_state_machine(struct work_struct *work)
 			do_suspend = true;
 		}
 		break;
-	case PHY_RESUMING:
-		err = phy_read_status(phydev);
-		if (err)
-			break;
-
-		if (phydev->link) {
-			phydev->state = PHY_RUNNING;
-			phy_link_up(phydev);
-		} else	{
-			phydev->state = PHY_NOLINK;
-			phy_link_down(phydev, true);
-		}
-		break;
 	}
 
 	mutex_unlock(&phydev->lock);
-- 
cgit v1.2.3


From b592843c6723a850be70bf9618578082f3b73851 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 7 Nov 2018 17:33:34 -0800
Subject: net: sched: add an offload dump helper

Qdisc dump operation of offload-capable qdiscs performs a few
extra steps which are identical among all the qdiscs.  Add
a helper to share this code.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 12 ++++++++++++
 net/sched/sch_api.c       | 21 +++++++++++++++++++++
 net/sched/sch_prio.c      | 16 +---------------
 net/sched/sch_red.c       | 17 +----------------
 4 files changed, 35 insertions(+), 31 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 4d736427a4cb..af55c1c4edb1 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -579,6 +579,18 @@ void qdisc_put(struct Qdisc *qdisc);
 void qdisc_put_unlocked(struct Qdisc *qdisc);
 void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
 			       unsigned int len);
+#ifdef CONFIG_NET_SCHED
+int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type,
+			      void *type_data);
+#else
+static inline int
+qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type,
+			  void *type_data)
+{
+	q->flags &= ~TCQ_F_OFFLOADED;
+	return 0;
+}
+#endif
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops,
 			  struct netlink_ext_ack *extack);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index ca3b0f46de53..e534825d3d3a 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -810,6 +810,27 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n,
 }
 EXPORT_SYMBOL(qdisc_tree_reduce_backlog);
 
+int qdisc_offload_dump_helper(struct Qdisc *sch, enum tc_setup_type type,
+			      void *type_data)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	int err;
+
+	sch->flags &= ~TCQ_F_OFFLOADED;
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return 0;
+
+	err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data);
+	if (err == -EOPNOTSUPP)
+		return 0;
+
+	if (!err)
+		sch->flags |= TCQ_F_OFFLOADED;
+
+	return err;
+}
+EXPORT_SYMBOL(qdisc_offload_dump_helper);
+
 static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 			 u32 portid, u32 seq, u16 flags, int event)
 {
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index f8af98621179..4bdd04c30ead 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -251,7 +251,6 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt,
 
 static int prio_dump_offload(struct Qdisc *sch)
 {
-	struct net_device *dev = qdisc_dev(sch);
 	struct tc_prio_qopt_offload hw_stats = {
 		.command = TC_PRIO_STATS,
 		.handle = sch->handle,
@@ -263,21 +262,8 @@ static int prio_dump_offload(struct Qdisc *sch)
 			},
 		},
 	};
-	int err;
-
-	sch->flags &= ~TCQ_F_OFFLOADED;
-	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
-		return 0;
-
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_PRIO,
-					    &hw_stats);
-	if (err == -EOPNOTSUPP)
-		return 0;
-
-	if (!err)
-		sch->flags |= TCQ_F_OFFLOADED;
 
-	return err;
+	return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_PRIO, &hw_stats);
 }
 
 static int prio_dump(struct Qdisc *sch, struct sk_buff *skb)
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 3ce6c0a2c493..d5e441194397 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -281,7 +281,6 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt,
 
 static int red_dump_offload_stats(struct Qdisc *sch, struct tc_red_qopt *opt)
 {
-	struct net_device *dev = qdisc_dev(sch);
 	struct tc_red_qopt_offload hw_stats = {
 		.command = TC_RED_STATS,
 		.handle = sch->handle,
@@ -291,22 +290,8 @@ static int red_dump_offload_stats(struct Qdisc *sch, struct tc_red_qopt *opt)
 			.stats.qstats = &sch->qstats,
 		},
 	};
-	int err;
-
-	sch->flags &= ~TCQ_F_OFFLOADED;
-
-	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
-		return 0;
-
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED,
-					    &hw_stats);
-	if (err == -EOPNOTSUPP)
-		return 0;
-
-	if (!err)
-		sch->flags |= TCQ_F_OFFLOADED;
 
-	return err;
+	return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_RED, &hw_stats);
 }
 
 static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
-- 
cgit v1.2.3


From dad54c0fab31c2ed813cb54bb024c65d6467d0b9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 7 Nov 2018 17:33:35 -0800
Subject: net: sched: red: remove unnecessary red_dump_offload_stats parameter

Offload dump helper does not use opt parameter, remove it.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_red.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index d5e441194397..2bf1d2fabc48 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -279,7 +279,7 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt,
 	return red_change(sch, opt, extack);
 }
 
-static int red_dump_offload_stats(struct Qdisc *sch, struct tc_red_qopt *opt)
+static int red_dump_offload_stats(struct Qdisc *sch)
 {
 	struct tc_red_qopt_offload hw_stats = {
 		.command = TC_RED_STATS,
@@ -309,7 +309,7 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
 	};
 	int err;
 
-	err = red_dump_offload_stats(sch, &opt);
+	err = red_dump_offload_stats(sch);
 	if (err)
 		goto nla_put_failure;
 
-- 
cgit v1.2.3


From 58f8927399eac8f2ac3c7289a2856b8b5516ba30 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 7 Nov 2018 17:33:36 -0800
Subject: net: sched: set TCQ_F_OFFLOADED flag for MQ

PRIO and RED mark the qdisc with TCQ_F_OFFLOADED upon successful offload,
make MQ do the same.  The consistency will help with consistent
graft callback behaviour.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_mq.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index f20f3a0f8424..1db5c1bf6ddd 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -38,9 +38,8 @@ static int mq_offload(struct Qdisc *sch, enum tc_mq_command cmd)
 	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt);
 }
 
-static void mq_offload_stats(struct Qdisc *sch)
+static int mq_offload_stats(struct Qdisc *sch)
 {
-	struct net_device *dev = qdisc_dev(sch);
 	struct tc_mq_qopt_offload opt = {
 		.command = TC_MQ_STATS,
 		.handle = sch->handle,
@@ -50,8 +49,7 @@ static void mq_offload_stats(struct Qdisc *sch)
 		},
 	};
 
-	if (tc_can_offload(dev) && dev->netdev_ops->ndo_setup_tc)
-		dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt);
+	return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_MQ, &opt);
 }
 
 static void mq_destroy(struct Qdisc *sch)
@@ -171,9 +169,8 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
 
 		spin_unlock_bh(qdisc_lock(qdisc));
 	}
-	mq_offload_stats(sch);
 
-	return 0;
+	return mq_offload_stats(sch);
 }
 
 static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl)
-- 
cgit v1.2.3


From bfaee9113f30abfa1f77ecb5e4a6f53a9d4c690c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 7 Nov 2018 17:33:37 -0800
Subject: net: sched: add an offload graft helper

Qdisc graft operation of offload-capable qdiscs performs a few
extra steps which are identical among all the qdiscs.  Add
a helper to share this code.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 12 ++++++++++++
 net/sched/sch_api.c       | 29 +++++++++++++++++++++++++++++
 net/sched/sch_prio.c      | 27 +++------------------------
 3 files changed, 44 insertions(+), 24 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index af55c1c4edb1..a8dd1fc141b6 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -582,6 +582,10 @@ void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
 #ifdef CONFIG_NET_SCHED
 int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type,
 			      void *type_data);
+void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch,
+				struct Qdisc *new, struct Qdisc *old,
+				enum tc_setup_type type, void *type_data,
+				struct netlink_ext_ack *extack);
 #else
 static inline int
 qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type,
@@ -590,6 +594,14 @@ qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type,
 	q->flags &= ~TCQ_F_OFFLOADED;
 	return 0;
 }
+
+static inline void
+qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch,
+			   struct Qdisc *new, struct Qdisc *old,
+			   enum tc_setup_type type, void *type_data,
+			   struct netlink_ext_ack *extack)
+{
+}
 #endif
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops,
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index e534825d3d3a..4b3af41cc1d7 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -831,6 +831,35 @@ int qdisc_offload_dump_helper(struct Qdisc *sch, enum tc_setup_type type,
 }
 EXPORT_SYMBOL(qdisc_offload_dump_helper);
 
+void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch,
+				struct Qdisc *new, struct Qdisc *old,
+				enum tc_setup_type type, void *type_data,
+				struct netlink_ext_ack *extack)
+{
+	bool any_qdisc_is_offloaded;
+	int err;
+
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return;
+
+	err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data);
+
+	/* Don't report error if the graft is part of destroy operation. */
+	if (!err || !new || new == &noop_qdisc)
+		return;
+
+	/* Don't report error if the parent, the old child and the new
+	 * one are not offloaded.
+	 */
+	any_qdisc_is_offloaded = new->flags & TCQ_F_OFFLOADED;
+	any_qdisc_is_offloaded |= sch && sch->flags & TCQ_F_OFFLOADED;
+	any_qdisc_is_offloaded |= old && old->flags & TCQ_F_OFFLOADED;
+
+	if (any_qdisc_is_offloaded)
+		NL_SET_ERR_MSG(extack, "Offloading graft operation failed.");
+}
+EXPORT_SYMBOL(qdisc_offload_graft_helper);
+
 static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 			 u32 portid, u32 seq, u16 flags, int event)
 {
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 4bdd04c30ead..63a90c5055ee 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -295,43 +295,22 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
 	struct tc_prio_qopt_offload graft_offload;
-	struct net_device *dev = qdisc_dev(sch);
 	unsigned long band = arg - 1;
-	bool any_qdisc_is_offloaded;
-	int err;
 
 	if (new == NULL)
 		new = &noop_qdisc;
 
 	*old = qdisc_replace(sch, new, &q->queues[band]);
 
-	if (!tc_can_offload(dev))
-		return 0;
-
 	graft_offload.handle = sch->handle;
 	graft_offload.parent = sch->parent;
 	graft_offload.graft_params.band = band;
 	graft_offload.graft_params.child_handle = new->handle;
 	graft_offload.command = TC_PRIO_GRAFT;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_PRIO,
-					    &graft_offload);
-
-	/* Don't report error if the graft is part of destroy operation. */
-	if (err && new != &noop_qdisc) {
-		/* Don't report error if the parent, the old child and the new
-		 * one are not offloaded.
-		 */
-		any_qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED;
-		any_qdisc_is_offloaded |= new->flags & TCQ_F_OFFLOADED;
-		if (*old)
-			any_qdisc_is_offloaded |= (*old)->flags &
-						   TCQ_F_OFFLOADED;
-
-		if (any_qdisc_is_offloaded)
-			NL_SET_ERR_MSG(extack, "Offloading graft operation failed.");
-	}
-
+	qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old,
+				   TC_SETUP_QDISC_PRIO, &graft_offload,
+				   extack);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 9da93ece59f4a3e1544dfa2aa53e91f9e724abc6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 7 Nov 2018 17:33:38 -0800
Subject: net: sched: refactor grafting Qdiscs with a parent

The code for grafting Qdiscs when there is a parent has two needless
indentation levels, and breaks the "keep the success path unindented"
guideline.  Refactor.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 4b3af41cc1d7..f55bc50cd0a9 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1007,7 +1007,6 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 {
 	struct Qdisc *q = old;
 	struct net *net = dev_net(dev);
-	int err = 0;
 
 	if (parent == NULL) {
 		unsigned int i, num_q, ingress;
@@ -1062,28 +1061,29 @@ skip:
 			dev_activate(dev);
 	} else {
 		const struct Qdisc_class_ops *cops = parent->ops->cl_ops;
+		unsigned long cl;
+		int err;
 
 		/* Only support running class lockless if parent is lockless */
 		if (new && (new->flags & TCQ_F_NOLOCK) &&
 		    parent && !(parent->flags & TCQ_F_NOLOCK))
 			new->flags &= ~TCQ_F_NOLOCK;
 
-		err = -EOPNOTSUPP;
-		if (cops && cops->graft) {
-			unsigned long cl = cops->find(parent, classid);
+		if (!cops || !cops->graft)
+			return -EOPNOTSUPP;
 
-			if (cl) {
-				err = cops->graft(parent, cl, new, &old,
-						  extack);
-			} else {
-				NL_SET_ERR_MSG(extack, "Specified class not found");
-				err = -ENOENT;
-			}
+		cl = cops->find(parent, classid);
+		if (!cl) {
+			NL_SET_ERR_MSG(extack, "Specified class not found");
+			return -ENOENT;
 		}
-		if (!err)
-			notify_and_destroy(net, skb, n, classid, old, new);
+
+		err = cops->graft(parent, cl, new, &old, extack);
+		if (err)
+			return err;
+		notify_and_destroy(net, skb, n, classid, old, new);
 	}
-	return err;
+	return 0;
 }
 
 static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca,
-- 
cgit v1.2.3


From 0c8d13ac96070000da33f394f45e9c19638483c5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 7 Nov 2018 17:33:39 -0800
Subject: net: sched: red: delay destroying child qdisc on replace

Move destroying of the old child qdisc outside of the sch_tree_lock()
section.  This should improve the software qdisc replace but is even
more important for offloads.  Firstly calling offloads under a spin
lock is best avoided.  Secondly the destroy event of existing child
would have been sent to the offload device before the replace, causing
confusion.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_red.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 2bf1d2fabc48..7682f7a618a1 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -193,10 +193,10 @@ static const struct nla_policy red_policy[TCA_RED_MAX + 1] = {
 static int red_change(struct Qdisc *sch, struct nlattr *opt,
 		      struct netlink_ext_ack *extack)
 {
+	struct Qdisc *old_child = NULL, *child = NULL;
 	struct red_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_RED_MAX + 1];
 	struct tc_red_qopt *ctl;
-	struct Qdisc *child = NULL;
 	int err;
 	u32 max_P;
 
@@ -233,7 +233,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
 	if (child) {
 		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
 					  q->qdisc->qstats.backlog);
-		qdisc_put(q->qdisc);
+		old_child = q->qdisc;
 		q->qdisc = child;
 	}
 
@@ -252,7 +252,11 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
 		red_start_of_idle_period(&q->vars);
 
 	sch_tree_unlock(sch);
+
 	red_offload(sch, true);
+
+	if (old_child)
+		qdisc_put(old_child);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 7b8e0b6e659983154c8d7e756cdb833d89a3d4d7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 7 Nov 2018 17:33:40 -0800
Subject: net: sched: prio: delay destroying child qdiscs on change

Move destroying of the old child qdiscs outside of the sch_tree_lock()
section.  This should improve the software qdisc replace but is even
more important for offloads.  Calling offloads under a spin lock is
best avoided, and child's destroy would be called under sch_tree_lock().

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_prio.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 63a90c5055ee..cdf68706e40f 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -220,7 +220,6 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
 
 		qdisc_tree_reduce_backlog(child, child->q.qlen,
 					  child->qstats.backlog);
-		qdisc_put(child);
 	}
 
 	for (i = oldbands; i < q->bands; i++) {
@@ -230,6 +229,9 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
 	}
 
 	sch_tree_unlock(sch);
+
+	for (i = q->bands; i < oldbands; i++)
+		qdisc_put(q->queues[i]);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 0db55093b56618088b9a1d445eb6e43b311bea33 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 8 Nov 2018 02:08:43 +0000
Subject: net: bcmgenet: return correct value 'ret' from bcmgenet_power_down

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/broadcom/genet/bcmgenet.c: In function 'bcmgenet_power_down':
drivers/net/ethernet/broadcom/genet/bcmgenet.c:1136:6: warning:
 variable 'ret' set but not used [-Wunused-but-set-variable]

bcmgenet_power_down should return 'ret' instead of 0.

Fixes: ca8cf341903f ("net: bcmgenet: propagate errors from bcmgenet_power_down")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 2d6f090bf644..bf88749505a9 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1169,7 +1169,7 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 		break;
 	}
 
-	return 0;
+	return ret;
 }
 
 static void bcmgenet_power_up(struct bcmgenet_priv *priv,
-- 
cgit v1.2.3


From 1c51dc9ad68acf4d2cb89ba847fb48fd6e2de723 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Thu, 8 Nov 2018 14:58:07 +0800
Subject: net/ipv6: compute anycast address hash only if dev is null

avoid to compute the hash value if dev is not null, since
hash value is not used

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/anycast.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 94999058e110..cca3b3603c42 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -433,7 +433,6 @@ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *ad
 bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
 			 const struct in6_addr *addr)
 {
-	unsigned int hash = inet6_acaddr_hash(net, addr);
 	struct net_device *nh_dev;
 	struct ifacaddr6 *aca;
 	bool found = false;
@@ -441,7 +440,9 @@ bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
 	rcu_read_lock();
 	if (dev)
 		found = ipv6_chk_acast_dev(dev, addr);
-	else
+	else {
+		unsigned int hash = inet6_acaddr_hash(net, addr);
+
 		hlist_for_each_entry_rcu(aca, &inet6_acaddr_lst[hash],
 					 aca_addr_lst) {
 			nh_dev = fib6_info_nh_dev(aca->aca_rt);
@@ -452,6 +453,7 @@ bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
 				break;
 			}
 		}
+	}
 	rcu_read_unlock();
 	return found;
 }
-- 
cgit v1.2.3


From 6d444c4efcdeca8b36f6059aa5a1a93f6ca3be6a Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Thu, 8 Nov 2018 14:21:07 +0530
Subject: cxgb4: Add new T6 PCI device ids 0x608a

Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index 60df66f4d21c..bf7325f6d553 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -217,6 +217,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x6087), /* Custom T6225-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x6088), /* Custom T62100-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x6089), /* Custom T62100-KR */
+	CH_PCI_ID_TABLE_FENTRY(0x608a), /* Custom T62100-CR */
 CH_PCI_DEVICE_ID_TABLE_DEFINE_END;
 
 #endif /* __T4_PCI_ID_TBL_H__ */
-- 
cgit v1.2.3


From 141b95d5519eafebfa3d8d3130a4f1cbb1eef622 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 8 Nov 2018 10:32:02 +0000
Subject: net: hns3: fix spelling mistake, "assertting" -> "asserting"

Trivial fix to spelling mistake in dev_err error message

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 579945bdcc76..77980e54ad09 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2504,7 +2504,7 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 		ret = hclge_func_reset_cmd(hdev, 0);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
-				"assertting function reset fail %d!\n", ret);
+				"asserting function reset fail %d!\n", ret);
 			return ret;
 		}
 
-- 
cgit v1.2.3


From a36e185e8c85523413c1ae3e03a0bdde5501f403 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 8 Nov 2018 12:19:14 +0100
Subject: udp: Handle ICMP errors for tunnels with same destination port on
 both endpoints

For both IPv4 and IPv6, if we can't match errors to a socket, try
tunnels before ignoring them. Look up a socket with the original source
and destination ports as found in the UDP packet inside the ICMP payload,
this will work for tunnels that force the same destination port for both
endpoints, i.e. VXLAN and GENEVE.

Actually, lwtunnels could break this assumption if they are configured by
an external control plane to have different destination ports on the
endpoints: in this case, we won't be able to trace ICMP messages back to
them.

For IPv6 redirect messages, call ip6_redirect() directly with the output
interface argument set to the interface we received the packet from (as
it's the very interface we should build the exception on), otherwise the
new nexthop will be rejected. There's no such need for IPv4.

Tunnels can now export an encap_err_lookup() operation that indicates a
match. Pass the packet to the lookup function, and if the tunnel driver
reports a matching association, continue with regular ICMP error handling.

v2:
- Added newline between network and transport header sets in
  __udp{4,6}_lib_err_encap() (David Miller)
- Removed redundant skb_reset_network_header(skb); in
  __udp4_lib_err_encap()
- Removed redundant reassignment of iph in __udp4_lib_err_encap()
  (Sabrina Dubroca)
- Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this
  won't work with lwtunnels configured to use asymmetric ports. By the way,
  it's VXLAN, not VxLAN (Jiri Benc)

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h      |  1 +
 include/net/udp_tunnel.h |  3 ++
 net/ipv4/udp.c           | 79 +++++++++++++++++++++++++++++++++++++-----
 net/ipv4/udp_tunnel.c    |  1 +
 net/ipv6/udp.c           | 89 ++++++++++++++++++++++++++++++++++++++++++------
 5 files changed, 153 insertions(+), 20 deletions(-)

diff --git a/include/linux/udp.h b/include/linux/udp.h
index 0a9c54e76305..2725c83395bf 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -77,6 +77,7 @@ struct udp_sock {
 	 * For encapsulation sockets.
 	 */
 	int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
+	int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb);
 	void (*encap_destroy)(struct sock *sk);
 
 	/* GRO functions for UDP socket */
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 3fbe56430e3b..dc8d804af3b4 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -64,6 +64,8 @@ static inline int udp_sock_create(struct net *net,
 }
 
 typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
+typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk,
+					     struct sk_buff *skb);
 typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
 typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
 						    struct list_head *head,
@@ -76,6 +78,7 @@ struct udp_tunnel_sock_cfg {
 	/* Used for setting up udp_sock fields, see udp.h for details */
 	__u8  encap_type;
 	udp_tunnel_encap_rcv_t encap_rcv;
+	udp_tunnel_encap_err_lookup_t encap_err_lookup;
 	udp_tunnel_encap_destroy_t encap_destroy;
 	udp_tunnel_gro_receive_t gro_receive;
 	udp_tunnel_gro_complete_t gro_complete;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3488650b90ac..ce759b61f6cd 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -583,6 +583,62 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
 	return true;
 }
 
+DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
+void udp_encap_enable(void)
+{
+	static_branch_enable(&udp_encap_needed_key);
+}
+EXPORT_SYMBOL(udp_encap_enable);
+
+/* Try to match ICMP errors to UDP tunnels by looking up a socket without
+ * reversing source and destination port: this will match tunnels that force the
+ * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
+ * lwtunnels might actually break this assumption by being configured with
+ * different destination ports on endpoints, in this case we won't be able to
+ * trace ICMP messages back to them.
+ *
+ * Then ask the tunnel implementation to match the error against a valid
+ * association.
+ *
+ * Return the socket if we have a match.
+ */
+static struct sock *__udp4_lib_err_encap(struct net *net,
+					 const struct iphdr *iph,
+					 struct udphdr *uh,
+					 struct udp_table *udptable,
+					 struct sk_buff *skb)
+{
+	int (*lookup)(struct sock *sk, struct sk_buff *skb);
+	int network_offset, transport_offset;
+	struct udp_sock *up;
+	struct sock *sk;
+
+	sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
+			       iph->saddr, uh->dest, skb->dev->ifindex, 0,
+			       udptable, NULL);
+	if (!sk)
+		return NULL;
+
+	network_offset = skb_network_offset(skb);
+	transport_offset = skb_transport_offset(skb);
+
+	/* Network header needs to point to the outer IPv4 header inside ICMP */
+	skb_reset_network_header(skb);
+
+	/* Transport header needs to point to the UDP header */
+	skb_set_transport_header(skb, iph->ihl << 2);
+
+	up = udp_sk(sk);
+	lookup = READ_ONCE(up->encap_err_lookup);
+	if (!lookup || lookup(sk, skb))
+		sk = NULL;
+
+	skb_set_transport_header(skb, transport_offset);
+	skb_set_network_header(skb, network_offset);
+
+	return sk;
+}
+
 /*
  * This routine is called by the ICMP module when it gets some
  * sort of error condition.  If err < 0 then the socket should
@@ -601,6 +657,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2));
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	bool tunnel = false;
 	struct sock *sk;
 	int harderr;
 	int err;
@@ -610,8 +667,15 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 			       iph->saddr, uh->source, skb->dev->ifindex,
 			       inet_sdif(skb), udptable, NULL);
 	if (!sk) {
-		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-		return;	/* No socket for error */
+		/* No socket for error: try tunnels before discarding */
+		if (static_branch_unlikely(&udp_encap_needed_key))
+			sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb);
+
+		if (!sk) {
+			__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
+			return;
+		}
+		tunnel = true;
 	}
 
 	err = 0;
@@ -654,6 +718,10 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	 *      RFC1122: OK.  Passes ICMP errors back to application, as per
 	 *	4.1.3.3.
 	 */
+	if (tunnel) {
+		/* ...not for tunnels though: we don't have a sending socket */
+		goto out;
+	}
 	if (!inet->recverr) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
 			goto out;
@@ -1891,13 +1959,6 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	return 0;
 }
 
-DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
-void udp_encap_enable(void)
-{
-	static_branch_enable(&udp_encap_needed_key);
-}
-EXPORT_SYMBOL(udp_encap_enable);
-
 /* returns:
  *  -1: error
  *   0: success
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 6539ff15e9a3..d0c412fc56ad 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -68,6 +68,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 
 	udp_sk(sk)->encap_type = cfg->encap_type;
 	udp_sk(sk)->encap_rcv = cfg->encap_rcv;
+	udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup;
 	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
 	udp_sk(sk)->gro_receive = cfg->gro_receive;
 	udp_sk(sk)->gro_complete = cfg->gro_complete;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index c55698d19d68..1216c920f945 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -462,6 +462,61 @@ csum_copy_err:
 	goto try_again;
 }
 
+DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
+void udpv6_encap_enable(void)
+{
+	static_branch_enable(&udpv6_encap_needed_key);
+}
+EXPORT_SYMBOL(udpv6_encap_enable);
+
+/* Try to match ICMP errors to UDP tunnels by looking up a socket without
+ * reversing source and destination port: this will match tunnels that force the
+ * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
+ * lwtunnels might actually break this assumption by being configured with
+ * different destination ports on endpoints, in this case we won't be able to
+ * trace ICMP messages back to them.
+ *
+ * Then ask the tunnel implementation to match the error against a valid
+ * association.
+ *
+ * Return the socket if we have a match.
+ */
+static struct sock *__udp6_lib_err_encap(struct net *net,
+					 const struct ipv6hdr *hdr, int offset,
+					 struct udphdr *uh,
+					 struct udp_table *udptable,
+					 struct sk_buff *skb)
+{
+	int (*lookup)(struct sock *sk, struct sk_buff *skb);
+	int network_offset, transport_offset;
+	struct udp_sock *up;
+	struct sock *sk;
+
+	sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
+			       &hdr->saddr, uh->dest,
+			       inet6_iif(skb), 0, udptable, skb);
+	if (!sk)
+		return NULL;
+
+	network_offset = skb_network_offset(skb);
+	transport_offset = skb_transport_offset(skb);
+
+	/* Network header needs to point to the outer IPv6 header inside ICMP */
+	skb_reset_network_header(skb);
+
+	/* Transport header needs to point to the UDP header */
+	skb_set_transport_header(skb, offset);
+
+	up = udp_sk(sk);
+	lookup = READ_ONCE(up->encap_err_lookup);
+	if (!lookup || lookup(sk, skb))
+		sk = NULL;
+
+	skb_set_transport_header(skb, transport_offset);
+	skb_set_network_header(skb, network_offset);
+	return sk;
+}
+
 void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		    u8 type, u8 code, int offset, __be32 info,
 		    struct udp_table *udptable)
@@ -471,6 +526,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	const struct in6_addr *saddr = &hdr->saddr;
 	const struct in6_addr *daddr = &hdr->daddr;
 	struct udphdr *uh = (struct udphdr *)(skb->data+offset);
+	bool tunnel = false;
 	struct sock *sk;
 	int harderr;
 	int err;
@@ -479,9 +535,18 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
 			       inet6_iif(skb), inet6_sdif(skb), udptable, skb);
 	if (!sk) {
-		__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
-				  ICMP6_MIB_INERRORS);
-		return;
+		/* No socket for error: try tunnels before discarding */
+		if (static_branch_unlikely(&udpv6_encap_needed_key)) {
+			sk = __udp6_lib_err_encap(net, hdr, offset, uh,
+						  udptable, skb);
+		}
+
+		if (!sk) {
+			__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
+					  ICMP6_MIB_INERRORS);
+			return;
+		}
+		tunnel = true;
 	}
 
 	harderr = icmpv6_err_convert(type, code, &err);
@@ -495,10 +560,19 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			harderr = 1;
 	}
 	if (type == NDISC_REDIRECT) {
-		ip6_sk_redirect(skb, sk);
+		if (tunnel) {
+			ip6_redirect(skb, sock_net(sk), inet6_iif(skb),
+				     sk->sk_mark, sk->sk_uid);
+		} else {
+			ip6_sk_redirect(skb, sk);
+		}
 		goto out;
 	}
 
+	/* Tunnels don't have an application socket: don't pass errors back */
+	if (tunnel)
+		goto out;
+
 	if (!np->recverr) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
 			goto out;
@@ -547,13 +621,6 @@ static __inline__ void udpv6_err(struct sk_buff *skb,
 	__udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
 }
 
-DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
-void udpv6_encap_enable(void)
-{
-	static_branch_enable(&udpv6_encap_needed_key);
-}
-EXPORT_SYMBOL(udpv6_encap_enable);
-
 static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_sock *up = udp_sk(sk);
-- 
cgit v1.2.3


From c3a43b9fec8a1d0cd6c5b404d2c378ac873facad Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 8 Nov 2018 12:19:15 +0100
Subject: vxlan: ICMP error lookup handler

Export an encap_err_lookup() operation to match an ICMP error against a
valid VNI.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index ae969f806d56..0851af6733f3 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1552,6 +1552,34 @@ drop:
 	return 0;
 }
 
+/* Callback from net/ipv{4,6}/udp.c to check that we have a VNI for errors */
+static int vxlan_err_lookup(struct sock *sk, struct sk_buff *skb)
+{
+	struct vxlan_dev *vxlan;
+	struct vxlan_sock *vs;
+	struct vxlanhdr *hdr;
+	__be32 vni;
+
+	if (skb->len < VXLAN_HLEN)
+		return -EINVAL;
+
+	hdr = vxlan_hdr(skb);
+
+	if (!(hdr->vx_flags & VXLAN_HF_VNI))
+		return -EINVAL;
+
+	vs = rcu_dereference_sk_user_data(sk);
+	if (!vs)
+		return -ENOENT;
+
+	vni = vxlan_vni(hdr->vx_vni);
+	vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni);
+	if (!vxlan)
+		return -ENOENT;
+
+	return 0;
+}
+
 static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
@@ -2948,6 +2976,7 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
 	tunnel_cfg.sk_user_data = vs;
 	tunnel_cfg.encap_type = 1;
 	tunnel_cfg.encap_rcv = vxlan_rcv;
+	tunnel_cfg.encap_err_lookup = vxlan_err_lookup;
 	tunnel_cfg.encap_destroy = NULL;
 	tunnel_cfg.gro_receive = vxlan_gro_receive;
 	tunnel_cfg.gro_complete = vxlan_gro_complete;
-- 
cgit v1.2.3


From b4d3069783bccf0c965468da7db141d359d796fc Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 8 Nov 2018 12:19:16 +0100
Subject: vxlan: Allow configuration of DF behaviour

Allow users to set the IPv4 DF bit in outgoing packets, or to inherit its
value from the IPv4 inner header. If the encapsulated protocol is IPv6 and
DF is configured to be inherited, always set it.

For IPv4, inheriting DF from the inner header was probably intended from
the very beginning judging by the comment to vxlan_xmit(), but it wasn't
actually implemented -- also because it would have done more harm than
good, without handling for ICMP Fragmentation Needed messages.

According to RFC 7348, "Path MTU discovery MAY be used". An expired RFC
draft, draft-saum-nvo3-pmtud-over-vxlan-05, whose purpose was to describe
PMTUD implementation, says that "is a MUST that Vxlan gateways [...]
SHOULD set the DF-bit [...]", whatever that means.

Given this background, the only sane option is probably to let the user
decide, and keep the current behaviour as default.

This only applies to non-lwt tunnels: if an external control plane is
used, tunnel key will still control the DF flag.

v2:
- DF behaviour configuration only applies for non-lwt tunnels, move DF
  setting to if (!info) block in vxlan_xmit_one() (Stephen Hemminger)

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c          | 29 ++++++++++++++++++++++++++++-
 include/net/vxlan.h          |  1 +
 include/uapi/linux/if_link.h |  9 +++++++++
 3 files changed, 38 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0851af6733f3..c3e65e78f015 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2278,13 +2278,24 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 		}
 
-		/* Bypass encapsulation if the destination is local */
 		if (!info) {
+			/* Bypass encapsulation if the destination is local */
 			err = encap_bypass_if_local(skb, dev, vxlan, dst,
 						    dst_port, ifindex, vni,
 						    &rt->dst, rt->rt_flags);
 			if (err)
 				goto out_unlock;
+
+			if (vxlan->cfg.df == VXLAN_DF_SET) {
+				df = htons(IP_DF);
+			} else if (vxlan->cfg.df == VXLAN_DF_INHERIT) {
+				struct ethhdr *eth = eth_hdr(skb);
+
+				if (ntohs(eth->h_proto) == ETH_P_IPV6 ||
+				    (ntohs(eth->h_proto) == ETH_P_IP &&
+				     old_iph->frag_off & htons(IP_DF)))
+					df = htons(IP_DF);
+			}
 		} else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) {
 			df = htons(IP_DF);
 		}
@@ -2837,6 +2848,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_GPE]	= { .type = NLA_FLAG, },
 	[IFLA_VXLAN_REMCSUM_NOPARTIAL]	= { .type = NLA_FLAG },
 	[IFLA_VXLAN_TTL_INHERIT]	= { .type = NLA_FLAG },
+	[IFLA_VXLAN_DF]		= { .type = NLA_U8 },
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -2893,6 +2905,16 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		}
 	}
 
+	if (data[IFLA_VXLAN_DF]) {
+		enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]);
+
+		if (df < 0 || df > VXLAN_DF_MAX) {
+			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_DF],
+					    "Invalid DF attribute");
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 
@@ -3538,6 +3560,9 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 		conf->mtu = nla_get_u32(tb[IFLA_MTU]);
 	}
 
+	if (data[IFLA_VXLAN_DF])
+		conf->df = nla_get_u8(data[IFLA_VXLAN_DF]);
+
 	return 0;
 }
 
@@ -3630,6 +3655,7 @@ static size_t vxlan_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TTL */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TTL_INHERIT */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TOS */
+		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_DF */
 		nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_LEARNING */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_PROXY */
@@ -3696,6 +3722,7 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT,
 		       !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) ||
 	    nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) ||
+	    nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) ||
 	    nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) ||
 	    nla_put_u8(skb, IFLA_VXLAN_LEARNING,
 			!!(vxlan->cfg.flags & VXLAN_F_LEARN)) ||
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 03431c148e16..ec999c49df1f 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -216,6 +216,7 @@ struct vxlan_config {
 	unsigned long		age_interval;
 	unsigned int		addrmax;
 	bool			no_share;
+	enum ifla_vxlan_df	df;
 };
 
 struct vxlan_dev_node {
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 1debfa42cba1..efc588949431 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -533,6 +533,7 @@ enum {
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
 	IFLA_VXLAN_TTL_INHERIT,
+	IFLA_VXLAN_DF,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -542,6 +543,14 @@ struct ifla_vxlan_port_range {
 	__be16	high;
 };
 
+enum ifla_vxlan_df {
+	VXLAN_DF_UNSET = 0,
+	VXLAN_DF_SET,
+	VXLAN_DF_INHERIT,
+	__VXLAN_DF_END,
+	VXLAN_DF_MAX = __VXLAN_DF_END - 1,
+};
+
 /* GENEVE section */
 enum {
 	IFLA_GENEVE_UNSPEC,
-- 
cgit v1.2.3


From 582888792f7bc2d543d85cb610160e2162d5f132 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 8 Nov 2018 12:19:17 +0100
Subject: selftests: pmtu: Introduce tests for IPv4/IPv6 over VXLAN over
 IPv4/IPv6

Use a router between endpoints, implemented via namespaces, set a low MTU
between router and destination endpoint, exceed it and check PMTU value in
route exceptions.

v2:
- Change all occurrences of VxLAN to VXLAN (Jiri Benc)
- Introduce IPv4 tests right away, if iproute2 doesn't support the 'df'
  link option they will be skipped (David Ahern)

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 143 +++++++++++++++++++++++++++++++-----
 1 file changed, 125 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index a369d616b390..33cba295ad45 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -26,6 +26,23 @@
 # - pmtu_ipv6
 #	Same as pmtu_ipv4, except for locked PMTU tests, using IPv6
 #
+# - pmtu_ipv4_vxlan4_exception
+#	Set up the same network topology as pmtu_ipv4, create a VXLAN tunnel
+#	over IPv4 between A and B, routed via R1. On the link between R1 and B,
+#	set a MTU lower than the VXLAN MTU and the MTU on the link between A and
+#	R1. Send IPv4 packets, exceeding the MTU between R1 and B, over VXLAN
+#	from A to B and check that the PMTU exception is created with the right
+#	value on A
+#
+# - pmtu_ipv6_vxlan4_exception
+#	Same as pmtu_ipv4_vxlan4_exception, but send IPv6 packets from A to B
+#
+# - pmtu_ipv4_vxlan6_exception
+#	Same as pmtu_ipv4_vxlan4_exception, but use IPv6 transport from A to B
+#
+# - pmtu_ipv6_vxlan6_exception
+#	Same as pmtu_ipv4_vxlan6_exception, but send IPv6 packets from A to B
+#
 # - pmtu_vti4_exception
 #	Set up vti tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is not
@@ -72,6 +89,10 @@ which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
 tests="
 	pmtu_ipv4_exception		ipv4: PMTU exceptions
 	pmtu_ipv6_exception		ipv6: PMTU exceptions
+	pmtu_ipv4_vxlan4_exception	IPv4 over vxlan4: PMTU exceptions
+	pmtu_ipv6_vxlan4_exception	IPv6 over vxlan4: PMTU exceptions
+	pmtu_ipv4_vxlan6_exception	IPv4 over vxlan6: PMTU exceptions
+	pmtu_ipv6_vxlan6_exception	IPv6 over vxlan6: PMTU exceptions
 	pmtu_vti6_exception		vti6: PMTU exceptions
 	pmtu_vti4_exception		vti4: PMTU exceptions
 	pmtu_vti4_default_mtu		vti4: default MTU assignment
@@ -95,8 +116,8 @@ ns_r2="ip netns exec ${NS_R2}"
 # Addresses are:
 # - IPv4: PREFIX4.SEGMENT.ID (/24)
 # - IPv6: PREFIX6:SEGMENT::ID (/64)
-prefix4="192.168"
-prefix6="fd00"
+prefix4="10.0"
+prefix6="fc00"
 a_r1=1
 a_r2=2
 b_r1=3
@@ -129,12 +150,12 @@ veth6_a_addr="fd00:1::a"
 veth6_b_addr="fd00:1::b"
 veth6_mask="64"
 
-vti4_a_addr="192.168.2.1"
-vti4_b_addr="192.168.2.2"
-vti4_mask="24"
-vti6_a_addr="fd00:2::a"
-vti6_b_addr="fd00:2::b"
-vti6_mask="64"
+tunnel4_a_addr="192.168.2.1"
+tunnel4_b_addr="192.168.2.2"
+tunnel4_mask="24"
+tunnel6_a_addr="fd00:2::a"
+tunnel6_b_addr="fd00:2::b"
+tunnel6_mask="64"
 
 dummy6_0_addr="fc00:1000::0"
 dummy6_1_addr="fc00:1001::0"
@@ -202,11 +223,39 @@ setup_vti() {
 }
 
 setup_vti4() {
-	setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${vti4_a_addr} ${vti4_b_addr} ${vti4_mask}
+	setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask}
 }
 
 setup_vti6() {
-	setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${vti6_a_addr} ${vti6_b_addr} ${vti6_mask}
+	setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
+}
+
+setup_vxlan() {
+	a_addr="${1}"
+	b_addr="${2}"
+	opts="${3}"
+
+	${ns_a} ip link add vxlan_a type vxlan id 1 local ${a_addr} remote ${b_addr} ttl 64 dstport 4789 ${opts} || return 1
+	${ns_b} ip link add vxlan_b type vxlan id 1 local ${b_addr} remote ${a_addr} ttl 64 dstport 4789 ${opts}
+
+	${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask}   dev vxlan_a
+	${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask}   dev vxlan_b
+
+	${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask}   dev vxlan_a
+	${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask}   dev vxlan_b
+
+	${ns_a} ip link set vxlan_a up
+	${ns_b} ip link set vxlan_b up
+
+	sleep 1
+}
+
+setup_vxlan4() {
+	setup_vxlan ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set"
+}
+
+setup_vxlan6() {
+	setup_vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ""
 }
 
 setup_xfrm() {
@@ -465,6 +514,64 @@ test_pmtu_ipv6_exception() {
 	test_pmtu_ipvX 6
 }
 
+test_pmtu_ipvX_over_vxlanY_exception() {
+	family=${1}
+	outer_family=${2}
+	ll_mtu=4000
+
+	if [ ${outer_family} -eq 4 ]; then
+		setup namespaces routing vxlan4 || return 2
+		#                      IPv4 header   UDP header   VXLAN header   Ethernet header
+		exp_mtu=$((${ll_mtu} - 20          - 8          - 8            - 14))
+	else
+		setup namespaces routing vxlan6 || return 2
+		#                      IPv6 header   UDP header   VXLAN header   Ethernet header
+		exp_mtu=$((${ll_mtu} - 40          - 8          - 8            - 14))
+	fi
+
+	trace "${ns_a}" vxlan_a      "${ns_b}"  vxlan_b \
+	      "${ns_a}" veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_b}" veth_B-R1    "${ns_r1}" veth_R1-B
+
+	if [ ${family} -eq 4 ]; then
+		ping=ping
+		dst=${tunnel4_b_addr}
+	else
+		ping=${ping6}
+		dst=${tunnel6_b_addr}
+	fi
+
+	# Create route exception by exceeding link layer MTU
+	mtu "${ns_a}"  veth_A-R1 $((${ll_mtu} + 1000))
+	mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
+	mtu "${ns_b}"  veth_B-R1 ${ll_mtu}
+	mtu "${ns_r1}" veth_R1-B ${ll_mtu}
+
+	mtu "${ns_a}" vxlan_a $((${ll_mtu} + 1000))
+	mtu "${ns_b}" vxlan_b $((${ll_mtu} + 1000))
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+
+	# Check that exception was created
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
+	check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on VXLAN interface"
+}
+
+test_pmtu_ipv4_vxlan4_exception() {
+	test_pmtu_ipvX_over_vxlanY_exception 4 4
+}
+
+test_pmtu_ipv6_vxlan4_exception() {
+	test_pmtu_ipvX_over_vxlanY_exception 6 4
+}
+
+test_pmtu_ipv4_vxlan6_exception() {
+	test_pmtu_ipvX_over_vxlanY_exception 4 6
+}
+
+test_pmtu_ipv6_vxlan6_exception() {
+	test_pmtu_ipvX_over_vxlanY_exception 6 6
+}
+
 test_pmtu_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
 	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
@@ -484,14 +591,14 @@ test_pmtu_vti4_exception() {
 
 	# Send DF packet without exceeding link layer MTU, check that no
 	# exception is created
-	${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${vti4_b_addr} > /dev/null
-	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
+	${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${tunnel4_b_addr} > /dev/null
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
 	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
 
 	# Now exceed link layer MTU by one byte, check that exception is created
 	# with the right PMTU value
-	${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${vti4_b_addr} > /dev/null
-	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
+	${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${tunnel4_b_addr} > /dev/null
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
 	check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
 }
 
@@ -506,20 +613,20 @@ test_pmtu_vti6_exception() {
 	mtu "${ns_b}" veth_b 4000
 	mtu "${ns_a}" vti6_a 5000
 	mtu "${ns_b}" vti6_b 5000
-	${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null
+	${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${tunnel6_b_addr} > /dev/null
 
 	# Check that exception was created
-	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
 	check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
 
 	# Decrease tunnel MTU, check for PMTU decrease in route exception
 	mtu "${ns_a}" vti6_a 3000
-	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
 	check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
 
 	# Increase tunnel MTU, check for PMTU increase in route exception
 	mtu "${ns_a}" vti6_a 9000
-	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
 	check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
 
 	return ${fail}
-- 
cgit v1.2.3


From a07966447f39fe43e37d05c9bfc92b1493267a59 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 8 Nov 2018 12:19:18 +0100
Subject: geneve: ICMP error lookup handler

Export an encap_err_lookup() operation to match an ICMP error against a
valid VNI.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index fbfc13d81f66..4dc457489770 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -387,6 +387,57 @@ drop:
 	return 0;
 }
 
+/* Callback from net/ipv{4,6}/udp.c to check that we have a tunnel for errors */
+static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb)
+{
+	struct genevehdr *geneveh;
+	struct geneve_sock *gs;
+	u8 zero_vni[3] = { 0 };
+	u8 *vni = zero_vni;
+
+	if (skb->len < GENEVE_BASE_HLEN)
+		return -EINVAL;
+
+	geneveh = geneve_hdr(skb);
+	if (geneveh->ver != GENEVE_VER)
+		return -EINVAL;
+
+	if (geneveh->proto_type != htons(ETH_P_TEB))
+		return -EINVAL;
+
+	gs = rcu_dereference_sk_user_data(sk);
+	if (!gs)
+		return -ENOENT;
+
+	if (geneve_get_sk_family(gs) == AF_INET) {
+		struct iphdr *iph = ip_hdr(skb);
+		__be32 addr4 = 0;
+
+		if (!gs->collect_md) {
+			vni = geneve_hdr(skb)->vni;
+			addr4 = iph->daddr;
+		}
+
+		return geneve_lookup(gs, addr4, vni) ? 0 : -ENOENT;
+	}
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (geneve_get_sk_family(gs) == AF_INET6) {
+		struct ipv6hdr *ip6h = ipv6_hdr(skb);
+		struct in6_addr addr6 = { 0 };
+
+		if (!gs->collect_md) {
+			vni = geneve_hdr(skb)->vni;
+			addr6 = ip6h->daddr;
+		}
+
+		return geneve6_lookup(gs, addr6, vni) ? 0 : -ENOENT;
+	}
+#endif
+
+	return -EPFNOSUPPORT;
+}
+
 static struct socket *geneve_create_sock(struct net *net, bool ipv6,
 					 __be16 port, bool ipv6_rx_csum)
 {
@@ -544,6 +595,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	tunnel_cfg.gro_receive = geneve_gro_receive;
 	tunnel_cfg.gro_complete = geneve_gro_complete;
 	tunnel_cfg.encap_rcv = geneve_udp_encap_recv;
+	tunnel_cfg.encap_err_lookup = geneve_udp_encap_err_lookup;
 	tunnel_cfg.encap_destroy = NULL;
 	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
 	list_add(&gs->list, &gn->sock_list);
-- 
cgit v1.2.3


From a025fb5f49ad38cf749753b16fcd031d0d678f2b Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 8 Nov 2018 12:19:19 +0100
Subject: geneve: Allow configuration of DF behaviour

draft-ietf-nvo3-geneve-08 says:

   It is strongly RECOMMENDED that Path MTU Discovery ([RFC1191],
   [RFC1981]) be used by setting the DF bit in the IP header when Geneve
   packets are transmitted over IPv4 (this is the default with IPv6).

Now that ICMP error handling is working for GENEVE, we can comply with
this recommendation.

Make this configurable, though, to avoid breaking existing setups. By
default, DF won't be set. It can be set or inherited from inner IPv4
packets. If it's configured to be inherited and we are encapsulating IPv6,
it will be set.

This only applies to non-lwt tunnels: if an external control plane is
used, tunnel key will still control the DF flag.

v2:
- DF behaviour configuration only applies for non-lwt tunnels, apply DF
  setting only if (!geneve->collect_md) in geneve_xmit_skb()
  (Stephen Hemminger)

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c         | 55 +++++++++++++++++++++++++++++++++++++-------
 include/uapi/linux/if_link.h |  9 ++++++++
 2 files changed, 56 insertions(+), 8 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 4dc457489770..7c53e06b31c3 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -70,6 +70,7 @@ struct geneve_dev {
 	bool		   collect_md;
 	bool		   use_udp6_rx_checksums;
 	bool		   ttl_inherit;
+	enum ifla_geneve_df df;
 };
 
 struct geneve_sock {
@@ -875,8 +876,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	struct rtable *rt;
 	struct flowi4 fl4;
 	__u8 tos, ttl;
+	__be16 df = 0;
 	__be16 sport;
-	__be16 df;
 	int err;
 
 	rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
@@ -890,6 +891,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	if (geneve->collect_md) {
 		tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
+
+		df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
 	} else {
 		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb);
 		if (geneve->ttl_inherit)
@@ -897,8 +900,22 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		else
 			ttl = key->ttl;
 		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
+
+		if (geneve->df == GENEVE_DF_SET) {
+			df = htons(IP_DF);
+		} else if (geneve->df == GENEVE_DF_INHERIT) {
+			struct ethhdr *eth = eth_hdr(skb);
+
+			if (ntohs(eth->h_proto) == ETH_P_IPV6) {
+				df = htons(IP_DF);
+			} else if (ntohs(eth->h_proto) == ETH_P_IP) {
+				struct iphdr *iph = ip_hdr(skb);
+
+				if (iph->frag_off & htons(IP_DF))
+					df = htons(IP_DF);
+			}
+		}
 	}
-	df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
 
 	err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr));
 	if (unlikely(err))
@@ -1145,6 +1162,7 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
 	[IFLA_GENEVE_UDP_ZERO_CSUM6_TX]	= { .type = NLA_U8 },
 	[IFLA_GENEVE_UDP_ZERO_CSUM6_RX]	= { .type = NLA_U8 },
 	[IFLA_GENEVE_TTL_INHERIT]	= { .type = NLA_U8 },
+	[IFLA_GENEVE_DF]		= { .type = NLA_U8 },
 };
 
 static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -1180,6 +1198,16 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
 		}
 	}
 
+	if (data[IFLA_GENEVE_DF]) {
+		enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]);
+
+		if (df < 0 || df > GENEVE_DF_MAX) {
+			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_GENEVE_DF],
+					    "Invalid DF attribute");
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 
@@ -1225,7 +1253,7 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 			    struct netlink_ext_ack *extack,
 			    const struct ip_tunnel_info *info,
 			    bool metadata, bool ipv6_rx_csum,
-			    bool ttl_inherit)
+			    bool ttl_inherit, enum ifla_geneve_df df)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_dev *t, *geneve = netdev_priv(dev);
@@ -1275,6 +1303,7 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 	geneve->collect_md = metadata;
 	geneve->use_udp6_rx_checksums = ipv6_rx_csum;
 	geneve->ttl_inherit = ttl_inherit;
+	geneve->df = df;
 
 	err = register_netdevice(dev);
 	if (err)
@@ -1294,7 +1323,7 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[],
 			  struct netlink_ext_ack *extack,
 			  struct ip_tunnel_info *info, bool *metadata,
 			  bool *use_udp6_rx_checksums, bool *ttl_inherit,
-			  bool changelink)
+			  enum ifla_geneve_df *df, bool changelink)
 {
 	int attrtype;
 
@@ -1382,6 +1411,9 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[],
 	if (data[IFLA_GENEVE_TOS])
 		info->key.tos = nla_get_u8(data[IFLA_GENEVE_TOS]);
 
+	if (data[IFLA_GENEVE_DF])
+		*df = nla_get_u8(data[IFLA_GENEVE_DF]);
+
 	if (data[IFLA_GENEVE_LABEL]) {
 		info->key.label = nla_get_be32(data[IFLA_GENEVE_LABEL]) &
 				  IPV6_FLOWLABEL_MASK;
@@ -1500,6 +1532,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 			  struct nlattr *tb[], struct nlattr *data[],
 			  struct netlink_ext_ack *extack)
 {
+	enum ifla_geneve_df df = GENEVE_DF_UNSET;
 	bool use_udp6_rx_checksums = false;
 	struct ip_tunnel_info info;
 	bool ttl_inherit = false;
@@ -1508,12 +1541,12 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 
 	init_tnl_info(&info, GENEVE_UDP_PORT);
 	err = geneve_nl2info(tb, data, extack, &info, &metadata,
-			     &use_udp6_rx_checksums, &ttl_inherit, false);
+			     &use_udp6_rx_checksums, &ttl_inherit, &df, false);
 	if (err)
 		return err;
 
 	err = geneve_configure(net, dev, extack, &info, metadata,
-			       use_udp6_rx_checksums, ttl_inherit);
+			       use_udp6_rx_checksums, ttl_inherit, df);
 	if (err)
 		return err;
 
@@ -1576,6 +1609,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct ip_tunnel_info info;
 	bool metadata;
 	bool use_udp6_rx_checksums;
+	enum ifla_geneve_df df;
 	bool ttl_inherit;
 	int err;
 
@@ -1591,7 +1625,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 	use_udp6_rx_checksums = geneve->use_udp6_rx_checksums;
 	ttl_inherit = geneve->ttl_inherit;
 	err = geneve_nl2info(tb, data, extack, &info, &metadata,
-			     &use_udp6_rx_checksums, &ttl_inherit, true);
+			     &use_udp6_rx_checksums, &ttl_inherit, &df, true);
 	if (err)
 		return err;
 
@@ -1624,6 +1658,7 @@ static size_t geneve_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */
 		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TTL */
 		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TOS */
+		nla_total_size(sizeof(__u8)) +	/* IFLA_GENEVE_DF */
 		nla_total_size(sizeof(__be32)) +  /* IFLA_GENEVE_LABEL */
 		nla_total_size(sizeof(__be16)) +  /* IFLA_GENEVE_PORT */
 		nla_total_size(0) +	 /* IFLA_GENEVE_COLLECT_METADATA */
@@ -1672,6 +1707,9 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_be32(skb, IFLA_GENEVE_LABEL, info->key.label))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_GENEVE_DF, geneve->df))
+		goto nla_put_failure;
+
 	if (nla_put_be16(skb, IFLA_GENEVE_PORT, info->key.tp_dst))
 		goto nla_put_failure;
 
@@ -1723,7 +1761,8 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 		return dev;
 
 	init_tnl_info(&info, dst_port);
-	err = geneve_configure(net, dev, NULL, &info, true, true, false);
+	err = geneve_configure(net, dev, NULL, &info,
+			       true, true, false, GENEVE_DF_UNSET);
 	if (err) {
 		free_netdev(dev);
 		return ERR_PTR(err);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index efc588949431..f42c069d81db 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -566,10 +566,19 @@ enum {
 	IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
 	IFLA_GENEVE_LABEL,
 	IFLA_GENEVE_TTL_INHERIT,
+	IFLA_GENEVE_DF,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
 
+enum ifla_geneve_df {
+	GENEVE_DF_UNSET = 0,
+	GENEVE_DF_SET,
+	GENEVE_DF_INHERIT,
+	__GENEVE_DF_END,
+	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
+};
+
 /* PPP section */
 enum {
 	IFLA_PPP_UNSPEC,
-- 
cgit v1.2.3


From ce7336610ca950cda131293def57a0178d860121 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 8 Nov 2018 12:19:20 +0100
Subject: selftests: pmtu: Introduce tests for IPv4/IPv6 over GENEVE over
 IPv4/IPv6

Use a router between endpoints, implemented via namespaces, set a low MTU
between router and destination endpoint, exceed it and check PMTU value in
route exceptions.

v2:
- Introduce IPv4 tests right away, if iproute2 doesn't support the 'df'
  link option they will be skipped (David Ahern)

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 117 ++++++++++++++++++++++++++----------
 1 file changed, 86 insertions(+), 31 deletions(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 33cba295ad45..14d20782ccb7 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -43,6 +43,22 @@
 # - pmtu_ipv6_vxlan6_exception
 #	Same as pmtu_ipv4_vxlan6_exception, but send IPv6 packets from A to B
 #
+# - pmtu_ipv4_geneve4_exception
+#	Same as pmtu_ipv4_vxlan4_exception, but using a GENEVE tunnel instead of
+#	VXLAN
+#
+# - pmtu_ipv6_geneve4_exception
+#	Same as pmtu_ipv6_vxlan4_exception, but using a GENEVE tunnel instead of
+#	VXLAN
+#
+# - pmtu_ipv4_geneve6_exception
+#	Same as pmtu_ipv4_vxlan6_exception, but using a GENEVE tunnel instead of
+#	VXLAN
+#
+# - pmtu_ipv6_geneve6_exception
+#	Same as pmtu_ipv6_vxlan6_exception, but using a GENEVE tunnel instead of
+#	VXLAN
+#
 # - pmtu_vti4_exception
 #	Set up vti tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is not
@@ -93,6 +109,10 @@ tests="
 	pmtu_ipv6_vxlan4_exception	IPv6 over vxlan4: PMTU exceptions
 	pmtu_ipv4_vxlan6_exception	IPv4 over vxlan6: PMTU exceptions
 	pmtu_ipv6_vxlan6_exception	IPv6 over vxlan6: PMTU exceptions
+	pmtu_ipv4_geneve4_exception	IPv4 over geneve4: PMTU exceptions
+	pmtu_ipv6_geneve4_exception	IPv6 over geneve4: PMTU exceptions
+	pmtu_ipv4_geneve6_exception	IPv4 over geneve6: PMTU exceptions
+	pmtu_ipv6_geneve6_exception	IPv6 over geneve6: PMTU exceptions
 	pmtu_vti6_exception		vti6: PMTU exceptions
 	pmtu_vti4_exception		vti4: PMTU exceptions
 	pmtu_vti4_default_mtu		vti4: default MTU assignment
@@ -230,32 +250,50 @@ setup_vti6() {
 	setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
 }
 
-setup_vxlan() {
-	a_addr="${1}"
-	b_addr="${2}"
-	opts="${3}"
+setup_vxlan_or_geneve() {
+	type="${1}"
+	a_addr="${2}"
+	b_addr="${3}"
+	opts="${4}"
+
+	if [ "${type}" = "vxlan" ]; then
+		opts="${opts} ttl 64 dstport 4789"
+		opts_a="local ${a_addr}"
+		opts_b="local ${b_addr}"
+	else
+		opts_a=""
+		opts_b=""
+	fi
 
-	${ns_a} ip link add vxlan_a type vxlan id 1 local ${a_addr} remote ${b_addr} ttl 64 dstport 4789 ${opts} || return 1
-	${ns_b} ip link add vxlan_b type vxlan id 1 local ${b_addr} remote ${a_addr} ttl 64 dstport 4789 ${opts}
+	${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1
+	${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts}
 
-	${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask}   dev vxlan_a
-	${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask}   dev vxlan_b
+	${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a
+	${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b
 
-	${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask}   dev vxlan_a
-	${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask}   dev vxlan_b
+	${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a
+	${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b
 
-	${ns_a} ip link set vxlan_a up
-	${ns_b} ip link set vxlan_b up
+	${ns_a} ip link set ${type}_a up
+	${ns_b} ip link set ${type}_b up
 
 	sleep 1
 }
 
+setup_geneve4() {
+	setup_vxlan_or_geneve geneve ${prefix4}.${a_r1}.1  ${prefix4}.${b_r1}.1  "df set"
+}
+
 setup_vxlan4() {
-	setup_vxlan ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set"
+	setup_vxlan_or_geneve vxlan  ${prefix4}.${a_r1}.1  ${prefix4}.${b_r1}.1  "df set"
+}
+
+setup_geneve6() {
+	setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
 }
 
 setup_vxlan6() {
-	setup_vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ""
+	setup_vxlan_or_geneve vxlan  ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
 }
 
 setup_xfrm() {
@@ -514,22 +552,23 @@ test_pmtu_ipv6_exception() {
 	test_pmtu_ipvX 6
 }
 
-test_pmtu_ipvX_over_vxlanY_exception() {
-	family=${1}
-	outer_family=${2}
+test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() {
+	type=${1}
+	family=${2}
+	outer_family=${3}
 	ll_mtu=4000
 
 	if [ ${outer_family} -eq 4 ]; then
-		setup namespaces routing vxlan4 || return 2
-		#                      IPv4 header   UDP header   VXLAN header   Ethernet header
-		exp_mtu=$((${ll_mtu} - 20          - 8          - 8            - 14))
+		setup namespaces routing ${type}4 || return 2
+		#                      IPv4 header   UDP header   VXLAN/GENEVE header   Ethernet header
+		exp_mtu=$((${ll_mtu} - 20          - 8          - 8                   - 14))
 	else
-		setup namespaces routing vxlan6 || return 2
-		#                      IPv6 header   UDP header   VXLAN header   Ethernet header
-		exp_mtu=$((${ll_mtu} - 40          - 8          - 8            - 14))
+		setup namespaces routing ${type}6 || return 2
+		#                      IPv6 header   UDP header   VXLAN/GENEVE header   Ethernet header
+		exp_mtu=$((${ll_mtu} - 40          - 8          - 8                   - 14))
 	fi
 
-	trace "${ns_a}" vxlan_a      "${ns_b}"  vxlan_b \
+	trace "${ns_a}" ${type}_a    "${ns_b}"  ${type}_b \
 	      "${ns_a}" veth_A-R1    "${ns_r1}" veth_R1-A \
 	      "${ns_b}" veth_B-R1    "${ns_r1}" veth_R1-B
 
@@ -547,29 +586,45 @@ test_pmtu_ipvX_over_vxlanY_exception() {
 	mtu "${ns_b}"  veth_B-R1 ${ll_mtu}
 	mtu "${ns_r1}" veth_R1-B ${ll_mtu}
 
-	mtu "${ns_a}" vxlan_a $((${ll_mtu} + 1000))
-	mtu "${ns_b}" vxlan_b $((${ll_mtu} + 1000))
+	mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000))
+	mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000))
 	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
 
 	# Check that exception was created
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
-	check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on VXLAN interface"
+	check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ${type} interface"
 }
 
 test_pmtu_ipv4_vxlan4_exception() {
-	test_pmtu_ipvX_over_vxlanY_exception 4 4
+	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan  4 4
 }
 
 test_pmtu_ipv6_vxlan4_exception() {
-	test_pmtu_ipvX_over_vxlanY_exception 6 4
+	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan  6 4
+}
+
+test_pmtu_ipv4_geneve4_exception() {
+	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 4 4
+}
+
+test_pmtu_ipv6_geneve4_exception() {
+	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 4
 }
 
 test_pmtu_ipv4_vxlan6_exception() {
-	test_pmtu_ipvX_over_vxlanY_exception 4 6
+	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan  4 6
 }
 
 test_pmtu_ipv6_vxlan6_exception() {
-	test_pmtu_ipvX_over_vxlanY_exception 6 6
+	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan  6 6
+}
+
+test_pmtu_ipv4_geneve6_exception() {
+	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 4 6
+}
+
+test_pmtu_ipv6_geneve6_exception() {
+	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 6
 }
 
 test_pmtu_vti4_exception() {
-- 
cgit v1.2.3


From 32bbd8793f24b0d5beb1cdb33c45c75ad1140e4b Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 8 Nov 2018 12:19:21 +0100
Subject: net: Convert protocol error handlers from void to int

We'll need this to handle ICMP errors for tunnels without a sending socket
(i.e. FoU and GUE). There, we might have to look up different types of IP
tunnels, registered as network protocols, before we get a match, so we
want this for the error handlers of IPPROTO_IPIP and IPPROTO_IPV6 in both
inet_protos and inet6_protos. These error codes will be used in the next
patch.

For consistency, return sensible error codes in protocol error handlers
whenever handlers can't handle errors because, even if valid, they don't
match a protocol or any of its states.

This has no effect on existing error handling paths.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/icmp.h        |  2 +-
 include/net/protocol.h    |  9 +++++++--
 include/net/sctp/sctp.h   |  2 +-
 include/net/tcp.h         |  2 +-
 include/net/udp.h         |  2 +-
 net/dccp/ipv4.c           | 13 ++++++++-----
 net/dccp/ipv6.c           | 13 ++++++++-----
 net/ipv4/gre_demux.c      |  9 +++++++--
 net/ipv4/icmp.c           |  6 ++++--
 net/ipv4/ip_gre.c         | 48 ++++++++++++++++++++++++-----------------------
 net/ipv4/ipip.c           | 14 +++++++-------
 net/ipv4/tcp_ipv4.c       | 22 ++++++++++++----------
 net/ipv4/tunnel4.c        | 18 ++++++++++++------
 net/ipv4/udp.c            | 10 +++++-----
 net/ipv4/udp_impl.h       |  2 +-
 net/ipv4/udplite.c        |  4 ++--
 net/ipv4/xfrm4_protocol.c | 18 ++++++++++++------
 net/ipv6/icmp.c           |  4 +++-
 net/ipv6/ip6_gre.c        | 18 ++++++++++--------
 net/ipv6/tcp_ipv6.c       | 13 ++++++++-----
 net/ipv6/tunnel6.c        | 12 ++++++++----
 net/ipv6/udp.c            | 18 +++++++++---------
 net/ipv6/udp_impl.h       |  4 ++--
 net/ipv6/udplite.c        |  5 +++--
 net/ipv6/xfrm6_protocol.c | 18 ++++++++++++------
 net/sctp/input.c          |  5 +++--
 net/sctp/ipv6.c           |  7 +++++--
 27 files changed, 177 insertions(+), 121 deletions(-)

diff --git a/include/net/icmp.h b/include/net/icmp.h
index 3ef2743a8eec..6ac3a5bd0117 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -41,7 +41,7 @@ struct net;
 
 void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info);
 int icmp_rcv(struct sk_buff *skb);
-void icmp_err(struct sk_buff *skb, u32 info);
+int icmp_err(struct sk_buff *skb, u32 info);
 int icmp_init(void);
 void icmp_out_count(struct net *net, unsigned char type);
 
diff --git a/include/net/protocol.h b/include/net/protocol.h
index 4fc75f7ae23b..92b3eaad6088 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -42,7 +42,10 @@ struct net_protocol {
 	int			(*early_demux)(struct sk_buff *skb);
 	int			(*early_demux_handler)(struct sk_buff *skb);
 	int			(*handler)(struct sk_buff *skb);
-	void			(*err_handler)(struct sk_buff *skb, u32 info);
+
+	/* This returns an error if we weren't able to handle the error. */
+	int			(*err_handler)(struct sk_buff *skb, u32 info);
+
 	unsigned int		no_policy:1,
 				netns_ok:1,
 				/* does the protocol do more stringent
@@ -58,10 +61,12 @@ struct inet6_protocol {
 	void    (*early_demux_handler)(struct sk_buff *skb);
 	int	(*handler)(struct sk_buff *skb);
 
-	void	(*err_handler)(struct sk_buff *skb,
+	/* This returns an error if we weren't able to handle the error. */
+	int	(*err_handler)(struct sk_buff *skb,
 			       struct inet6_skb_parm *opt,
 			       u8 type, u8 code, int offset,
 			       __be32 info);
+
 	unsigned int	flags;	/* INET6_PROTO_xxx */
 };
 
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 8c2caa370e0f..9a3b48a35e90 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -151,7 +151,7 @@ int sctp_primitive_RECONF(struct net *net, struct sctp_association *asoc,
  * sctp/input.c
  */
 int sctp_rcv(struct sk_buff *skb);
-void sctp_v4_err(struct sk_buff *skb, u32 info);
+int sctp_v4_err(struct sk_buff *skb, u32 info);
 void sctp_hash_endpoint(struct sctp_endpoint *);
 void sctp_unhash_endpoint(struct sctp_endpoint *);
 struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index a18914d20486..4743836bed2e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -313,7 +313,7 @@ extern struct proto tcp_prot;
 
 void tcp_tasklet_init(void);
 
-void tcp_v4_err(struct sk_buff *skb, u32);
+int tcp_v4_err(struct sk_buff *skb, u32);
 
 void tcp_shutdown(struct sock *sk, int how);
 
diff --git a/include/net/udp.h b/include/net/udp.h
index eccca2325ee6..fd6d948755c8 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -283,7 +283,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
 int udp_get_port(struct sock *sk, unsigned short snum,
 		 int (*saddr_cmp)(const struct sock *,
 				  const struct sock *));
-void udp_err(struct sk_buff *, u32);
+int udp_err(struct sk_buff *, u32);
 int udp_abort(struct sock *sk, int err);
 int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
 int udp_push_pending_frames(struct sock *sk);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 8e08cea6f178..26a21d97b6b0 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -231,7 +231,7 @@ EXPORT_SYMBOL(dccp_req_err);
  * check at all. A more general error queue to queue errors for later handling
  * is probably better.
  */
-static void dccp_v4_err(struct sk_buff *skb, u32 info)
+static int dccp_v4_err(struct sk_buff *skb, u32 info)
 {
 	const struct iphdr *iph = (struct iphdr *)skb->data;
 	const u8 offset = iph->ihl << 2;
@@ -259,16 +259,18 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 				       inet_iif(skb), 0);
 	if (!sk) {
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-		return;
+		return -ENOENT;
 	}
 
 	if (sk->sk_state == DCCP_TIME_WAIT) {
 		inet_twsk_put(inet_twsk(sk));
-		return;
+		return 0;
 	}
 	seq = dccp_hdr_seq(dh);
-	if (sk->sk_state == DCCP_NEW_SYN_RECV)
-		return dccp_req_err(sk, seq);
+	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
+		dccp_req_err(sk, seq);
+		return 0;
+	}
 
 	bh_lock_sock(sk);
 	/* If too many ICMPs get dropped on busy
@@ -357,6 +359,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
+	return 0;
 }
 
 static inline __sum16 dccp_v4_csum_finish(struct sk_buff *skb,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6344f1b18a6a..d5740bad5b18 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -68,7 +68,7 @@ static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb)
 
 }
 
-static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			u8 type, u8 code, int offset, __be32 info)
 {
 	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
@@ -96,16 +96,18 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (!sk) {
 		__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
 				  ICMP6_MIB_INERRORS);
-		return;
+		return -ENOENT;
 	}
 
 	if (sk->sk_state == DCCP_TIME_WAIT) {
 		inet_twsk_put(inet_twsk(sk));
-		return;
+		return 0;
 	}
 	seq = dccp_hdr_seq(dh);
-	if (sk->sk_state == DCCP_NEW_SYN_RECV)
-		return dccp_req_err(sk, seq);
+	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
+		dccp_req_err(sk, seq);
+		return 0;
+	}
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk))
@@ -183,6 +185,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
+	return 0;
 }
 
 
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 7efe740c06eb..a4bf22ee3aed 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -151,20 +151,25 @@ drop:
 	return NET_RX_DROP;
 }
 
-static void gre_err(struct sk_buff *skb, u32 info)
+static int gre_err(struct sk_buff *skb, u32 info)
 {
 	const struct gre_protocol *proto;
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	u8 ver = skb->data[(iph->ihl<<2) + 1]&0x7f;
+	int err = 0;
 
 	if (ver >= GREPROTO_MAX)
-		return;
+		return -EINVAL;
 
 	rcu_read_lock();
 	proto = rcu_dereference(gre_proto[ver]);
 	if (proto && proto->err_handler)
 		proto->err_handler(skb, info);
+	else
+		err = -EPROTONOSUPPORT;
 	rcu_read_unlock();
+
+	return err;
 }
 
 static const struct net_protocol net_gre_protocol = {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index d832beed6e3a..065997f414e6 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1079,7 +1079,7 @@ error:
 	goto drop;
 }
 
-void icmp_err(struct sk_buff *skb, u32 info)
+int icmp_err(struct sk_buff *skb, u32 info)
 {
 	struct iphdr *iph = (struct iphdr *)skb->data;
 	int offset = iph->ihl<<2;
@@ -1094,13 +1094,15 @@ void icmp_err(struct sk_buff *skb, u32 info)
 	 */
 	if (icmph->type != ICMP_ECHOREPLY) {
 		ping_err(skb, offset, info);
-		return;
+		return 0;
 	}
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
 		ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ICMP);
 	else if (type == ICMP_REDIRECT)
 		ipv4_redirect(skb, net, 0, IPPROTO_ICMP);
+
+	return 0;
 }
 
 /*
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2c67af644e64..76a9a5f7a40e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -121,8 +121,8 @@ static unsigned int ipgre_net_id __read_mostly;
 static unsigned int gre_tap_net_id __read_mostly;
 static unsigned int erspan_net_id __read_mostly;
 
-static void ipgre_err(struct sk_buff *skb, u32 info,
-		      const struct tnl_ptk_info *tpi)
+static int ipgre_err(struct sk_buff *skb, u32 info,
+		     const struct tnl_ptk_info *tpi)
 {
 
 	/* All the routers (except for Linux) return only
@@ -146,17 +146,32 @@ static void ipgre_err(struct sk_buff *skb, u32 info,
 	unsigned int data_len = 0;
 	struct ip_tunnel *t;
 
+	if (tpi->proto == htons(ETH_P_TEB))
+		itn = net_generic(net, gre_tap_net_id);
+	else if (tpi->proto == htons(ETH_P_ERSPAN) ||
+		 tpi->proto == htons(ETH_P_ERSPAN2))
+		itn = net_generic(net, erspan_net_id);
+	else
+		itn = net_generic(net, ipgre_net_id);
+
+	iph = (const struct iphdr *)(icmp_hdr(skb) + 1);
+	t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags,
+			     iph->daddr, iph->saddr, tpi->key);
+
+	if (!t)
+		return -ENOENT;
+
 	switch (type) {
 	default:
 	case ICMP_PARAMETERPROB:
-		return;
+		return 0;
 
 	case ICMP_DEST_UNREACH:
 		switch (code) {
 		case ICMP_SR_FAILED:
 		case ICMP_PORT_UNREACH:
 			/* Impossible event. */
-			return;
+			return 0;
 		default:
 			/* All others are translated to HOST_UNREACH.
 			   rfc2003 contains "deep thoughts" about NET_UNREACH,
@@ -168,7 +183,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info,
 
 	case ICMP_TIME_EXCEEDED:
 		if (code != ICMP_EXC_TTL)
-			return;
+			return 0;
 		data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
 		break;
 
@@ -176,40 +191,27 @@ static void ipgre_err(struct sk_buff *skb, u32 info,
 		break;
 	}
 
-	if (tpi->proto == htons(ETH_P_TEB))
-		itn = net_generic(net, gre_tap_net_id);
-	else if (tpi->proto == htons(ETH_P_ERSPAN) ||
-		 tpi->proto == htons(ETH_P_ERSPAN2))
-		itn = net_generic(net, erspan_net_id);
-	else
-		itn = net_generic(net, ipgre_net_id);
-
-	iph = (const struct iphdr *)(icmp_hdr(skb) + 1);
-	t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags,
-			     iph->daddr, iph->saddr, tpi->key);
-
-	if (!t)
-		return;
-
 #if IS_ENABLED(CONFIG_IPV6)
        if (tpi->proto == htons(ETH_P_IPV6) &&
            !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
 				       type, data_len))
-               return;
+               return 0;
 #endif
 
 	if (t->parms.iph.daddr == 0 ||
 	    ipv4_is_multicast(t->parms.iph.daddr))
-		return;
+		return 0;
 
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
-		return;
+		return 0;
 
 	if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
 		t->err_count++;
 	else
 		t->err_count = 1;
 	t->err_time = jiffies;
+
+	return 0;
 }
 
 static void gre_err(struct sk_buff *skb, u32 info)
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index e65287c27e3d..57c5dd283a2c 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -140,6 +140,13 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 	struct ip_tunnel *t;
 	int err = 0;
 
+	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+			     iph->daddr, iph->saddr, 0);
+	if (!t) {
+		err = -ENOENT;
+		goto out;
+	}
+
 	switch (type) {
 	case ICMP_DEST_UNREACH:
 		switch (code) {
@@ -167,13 +174,6 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 		goto out;
 	}
 
-	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
-			     iph->daddr, iph->saddr, 0);
-	if (!t) {
-		err = -ENOENT;
-		goto out;
-	}
-
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, net, info, t->parms.link, iph->protocol);
 		goto out;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index de47038afdf0..a336787d75e5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -423,7 +423,7 @@ EXPORT_SYMBOL(tcp_req_err);
  *
  */
 
-void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
+int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 {
 	const struct iphdr *iph = (const struct iphdr *)icmp_skb->data;
 	struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2));
@@ -446,20 +446,21 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 				       inet_iif(icmp_skb), 0);
 	if (!sk) {
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-		return;
+		return -ENOENT;
 	}
 	if (sk->sk_state == TCP_TIME_WAIT) {
 		inet_twsk_put(inet_twsk(sk));
-		return;
+		return 0;
 	}
 	seq = ntohl(th->seq);
-	if (sk->sk_state == TCP_NEW_SYN_RECV)
-		return tcp_req_err(sk, seq,
-				  type == ICMP_PARAMETERPROB ||
-				  type == ICMP_TIME_EXCEEDED ||
-				  (type == ICMP_DEST_UNREACH &&
-				   (code == ICMP_NET_UNREACH ||
-				    code == ICMP_HOST_UNREACH)));
+	if (sk->sk_state == TCP_NEW_SYN_RECV) {
+		tcp_req_err(sk, seq, type == ICMP_PARAMETERPROB ||
+				     type == ICMP_TIME_EXCEEDED ||
+				     (type == ICMP_DEST_UNREACH &&
+				      (code == ICMP_NET_UNREACH ||
+				       code == ICMP_HOST_UNREACH)));
+		return 0;
+	}
 
 	bh_lock_sock(sk);
 	/* If too many ICMPs get dropped on busy
@@ -613,6 +614,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
+	return 0;
 }
 
 void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr)
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index c0630013c1ae..33bf8e9c8663 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -149,34 +149,40 @@ drop:
 }
 #endif
 
-static void tunnel4_err(struct sk_buff *skb, u32 info)
+static int tunnel4_err(struct sk_buff *skb, u32 info)
 {
 	struct xfrm_tunnel *handler;
 
 	for_each_tunnel_rcu(tunnel4_handlers, handler)
 		if (!handler->err_handler(skb, info))
-			break;
+			return 0;
+
+	return -ENOENT;
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static void tunnel64_err(struct sk_buff *skb, u32 info)
+static int tunnel64_err(struct sk_buff *skb, u32 info)
 {
 	struct xfrm_tunnel *handler;
 
 	for_each_tunnel_rcu(tunnel64_handlers, handler)
 		if (!handler->err_handler(skb, info))
-			break;
+			return 0;
+
+	return -ENOENT;
 }
 #endif
 
 #if IS_ENABLED(CONFIG_MPLS)
-static void tunnelmpls4_err(struct sk_buff *skb, u32 info)
+static int tunnelmpls4_err(struct sk_buff *skb, u32 info)
 {
 	struct xfrm_tunnel *handler;
 
 	for_each_tunnel_rcu(tunnelmpls4_handlers, handler)
 		if (!handler->err_handler(skb, info))
-			break;
+			return 0;
+
+	return -ENOENT;
 }
 #endif
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ce759b61f6cd..a505ee5eb92c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -650,7 +650,7 @@ static struct sock *__udp4_lib_err_encap(struct net *net,
  * to find the appropriate port.
  */
 
-void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
+int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 {
 	struct inet_sock *inet;
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
@@ -673,7 +673,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 
 		if (!sk) {
 			__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-			return;
+			return -ENOENT;
 		}
 		tunnel = true;
 	}
@@ -731,12 +731,12 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	sk->sk_err = err;
 	sk->sk_error_report(sk);
 out:
-	return;
+	return 0;
 }
 
-void udp_err(struct sk_buff *skb, u32 info)
+int udp_err(struct sk_buff *skb, u32 info)
 {
-	__udp4_lib_err(skb, info, &udp_table);
+	return __udp4_lib_err(skb, info, &udp_table);
 }
 
 /*
diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h
index e7d18b140287..322672655419 100644
--- a/net/ipv4/udp_impl.h
+++ b/net/ipv4/udp_impl.h
@@ -7,7 +7,7 @@
 #include <net/inet_common.h>
 
 int __udp4_lib_rcv(struct sk_buff *, struct udp_table *, int);
-void __udp4_lib_err(struct sk_buff *, u32, struct udp_table *);
+int __udp4_lib_err(struct sk_buff *, u32, struct udp_table *);
 
 int udp_v4_get_port(struct sock *sk, unsigned short snum);
 
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 8545457752fb..39c7f17d916f 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -25,9 +25,9 @@ static int udplite_rcv(struct sk_buff *skb)
 	return __udp4_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE);
 }
 
-static void udplite_err(struct sk_buff *skb, u32 info)
+static int udplite_err(struct sk_buff *skb, u32 info)
 {
-	__udp4_lib_err(skb, info, &udplite_table);
+	return __udp4_lib_err(skb, info, &udplite_table);
 }
 
 static const struct net_protocol udplite_protocol = {
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
index 8dd0e6ab8606..35c54865dc42 100644
--- a/net/ipv4/xfrm4_protocol.c
+++ b/net/ipv4/xfrm4_protocol.c
@@ -106,13 +106,15 @@ static int xfrm4_esp_rcv(struct sk_buff *skb)
 	return 0;
 }
 
-static void xfrm4_esp_err(struct sk_buff *skb, u32 info)
+static int xfrm4_esp_err(struct sk_buff *skb, u32 info)
 {
 	struct xfrm4_protocol *handler;
 
 	for_each_protocol_rcu(esp4_handlers, handler)
 		if (!handler->err_handler(skb, info))
-			break;
+			return 0;
+
+	return -ENOENT;
 }
 
 static int xfrm4_ah_rcv(struct sk_buff *skb)
@@ -132,13 +134,15 @@ static int xfrm4_ah_rcv(struct sk_buff *skb)
 	return 0;
 }
 
-static void xfrm4_ah_err(struct sk_buff *skb, u32 info)
+static int xfrm4_ah_err(struct sk_buff *skb, u32 info)
 {
 	struct xfrm4_protocol *handler;
 
 	for_each_protocol_rcu(ah4_handlers, handler)
 		if (!handler->err_handler(skb, info))
-			break;
+			return 0;
+
+	return -ENOENT;
 }
 
 static int xfrm4_ipcomp_rcv(struct sk_buff *skb)
@@ -158,13 +162,15 @@ static int xfrm4_ipcomp_rcv(struct sk_buff *skb)
 	return 0;
 }
 
-static void xfrm4_ipcomp_err(struct sk_buff *skb, u32 info)
+static int xfrm4_ipcomp_err(struct sk_buff *skb, u32 info)
 {
 	struct xfrm4_protocol *handler;
 
 	for_each_protocol_rcu(ipcomp4_handlers, handler)
 		if (!handler->err_handler(skb, info))
-			break;
+			return 0;
+
+	return -ENOENT;
 }
 
 static const struct net_protocol esp4_protocol = {
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index c9c53ade55c3..5d7aa2c2770c 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -84,7 +84,7 @@ static inline struct sock *icmpv6_sk(struct net *net)
 	return net->ipv6.icmp_sk[smp_processor_id()];
 }
 
-static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		       u8 type, u8 code, int offset, __be32 info)
 {
 	/* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */
@@ -100,6 +100,8 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (!(type & ICMPV6_INFOMSG_MASK))
 		if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
 			ping_err(skb, offset, ntohl(info));
+
+	return 0;
 }
 
 static int icmpv6_rcv(struct sk_buff *skb);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 515adbdba1d2..81b69bcee714 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -423,7 +423,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 }
 
 
-static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		       u8 type, u8 code, int offset, __be32 info)
 {
 	struct net *net = dev_net(skb->dev);
@@ -433,13 +433,13 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IPV6),
 			     offset) < 0)
-		return;
+		return -EINVAL;
 
 	ipv6h = (const struct ipv6hdr *)skb->data;
 	t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr,
 				 tpi.key, tpi.proto);
 	if (!t)
-		return;
+		return -ENOENT;
 
 	switch (type) {
 		struct ipv6_tlv_tnl_enc_lim *tel;
@@ -449,14 +449,14 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 				    t->parms.name);
 		if (code != ICMPV6_PORT_UNREACH)
 			break;
-		return;
+		return 0;
 	case ICMPV6_TIME_EXCEED:
 		if (code == ICMPV6_EXC_HOPLIMIT) {
 			net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
 					    t->parms.name);
 			break;
 		}
-		return;
+		return 0;
 	case ICMPV6_PARAMPROB:
 		teli = 0;
 		if (code == ICMPV6_HDR_FIELD)
@@ -472,14 +472,14 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
 					    t->parms.name);
 		}
-		return;
+		return 0;
 	case ICMPV6_PKT_TOOBIG:
 		ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
-		return;
+		return 0;
 	case NDISC_REDIRECT:
 		ip6_redirect(skb, net, skb->dev->ifindex, 0,
 			     sock_net_uid(net, NULL));
-		return;
+		return 0;
 	}
 
 	if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO))
@@ -487,6 +487,8 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	else
 		t->err_count = 1;
 	t->err_time = jiffies;
+
+	return 0;
 }
 
 static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 03e6b7a2bc53..a3f559162521 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -349,7 +349,7 @@ static void tcp_v6_mtu_reduced(struct sock *sk)
 	}
 }
 
-static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		u8 type, u8 code, int offset, __be32 info)
 {
 	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
@@ -371,17 +371,19 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (!sk) {
 		__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
 				  ICMP6_MIB_INERRORS);
-		return;
+		return -ENOENT;
 	}
 
 	if (sk->sk_state == TCP_TIME_WAIT) {
 		inet_twsk_put(inet_twsk(sk));
-		return;
+		return 0;
 	}
 	seq = ntohl(th->seq);
 	fatal = icmpv6_err_convert(type, code, &err);
-	if (sk->sk_state == TCP_NEW_SYN_RECV)
-		return tcp_req_err(sk, seq, fatal);
+	if (sk->sk_state == TCP_NEW_SYN_RECV) {
+		tcp_req_err(sk, seq, fatal);
+		return 0;
+	}
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
@@ -467,6 +469,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
+	return 0;
 }
 
 
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index dae25cad05cd..1991dede7367 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -134,24 +134,28 @@ drop:
 	return 0;
 }
 
-static void tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			u8 type, u8 code, int offset, __be32 info)
 {
 	struct xfrm6_tunnel *handler;
 
 	for_each_tunnel_rcu(tunnel6_handlers, handler)
 		if (!handler->err_handler(skb, opt, type, code, offset, info))
-			break;
+			return 0;
+
+	return -ENOENT;
 }
 
-static void tunnel46_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int tunnel46_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			 u8 type, u8 code, int offset, __be32 info)
 {
 	struct xfrm6_tunnel *handler;
 
 	for_each_tunnel_rcu(tunnel46_handlers, handler)
 		if (!handler->err_handler(skb, opt, type, code, offset, info))
-			break;
+			return 0;
+
+	return -ENOENT;
 }
 
 static const struct inet6_protocol tunnel6_protocol = {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1216c920f945..61316ec48b51 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -517,9 +517,9 @@ static struct sock *__udp6_lib_err_encap(struct net *net,
 	return sk;
 }
 
-void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
-		    u8 type, u8 code, int offset, __be32 info,
-		    struct udp_table *udptable)
+int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+		   u8 type, u8 code, int offset, __be32 info,
+		   struct udp_table *udptable)
 {
 	struct ipv6_pinfo *np;
 	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
@@ -544,7 +544,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (!sk) {
 			__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
 					  ICMP6_MIB_INERRORS);
-			return;
+			return -ENOENT;
 		}
 		tunnel = true;
 	}
@@ -583,7 +583,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	sk->sk_err = err;
 	sk->sk_error_report(sk);
 out:
-	return;
+	return 0;
 }
 
 static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
@@ -614,11 +614,11 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	return 0;
 }
 
-static __inline__ void udpv6_err(struct sk_buff *skb,
-				 struct inet6_skb_parm *opt, u8 type,
-				 u8 code, int offset, __be32 info)
+static __inline__ int udpv6_err(struct sk_buff *skb,
+				struct inet6_skb_parm *opt, u8 type,
+				u8 code, int offset, __be32 info)
 {
-	__udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
+	return __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
 }
 
 static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h
index 7903e21c178b..5730e6503cb4 100644
--- a/net/ipv6/udp_impl.h
+++ b/net/ipv6/udp_impl.h
@@ -9,8 +9,8 @@
 #include <net/transp_v6.h>
 
 int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int);
-void __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int,
-		    __be32, struct udp_table *);
+int __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int,
+		   __be32, struct udp_table *);
 
 int udp_v6_get_port(struct sock *sk, unsigned short snum);
 
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 5000ad6878e6..a125aebc29e5 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -20,11 +20,12 @@ static int udplitev6_rcv(struct sk_buff *skb)
 	return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE);
 }
 
-static void udplitev6_err(struct sk_buff *skb,
+static int udplitev6_err(struct sk_buff *skb,
 			  struct inet6_skb_parm *opt,
 			  u8 type, u8 code, int offset, __be32 info)
 {
-	__udp6_lib_err(skb, opt, type, code, offset, info, &udplite_table);
+	return __udp6_lib_err(skb, opt, type, code, offset, info,
+			      &udplite_table);
 }
 
 static const struct inet6_protocol udplitev6_protocol = {
diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c
index b2dc8ce49378..cc979b702c89 100644
--- a/net/ipv6/xfrm6_protocol.c
+++ b/net/ipv6/xfrm6_protocol.c
@@ -80,14 +80,16 @@ static int xfrm6_esp_rcv(struct sk_buff *skb)
 	return 0;
 }
 
-static void xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			  u8 type, u8 code, int offset, __be32 info)
 {
 	struct xfrm6_protocol *handler;
 
 	for_each_protocol_rcu(esp6_handlers, handler)
 		if (!handler->err_handler(skb, opt, type, code, offset, info))
-			break;
+			return 0;
+
+	return -ENOENT;
 }
 
 static int xfrm6_ah_rcv(struct sk_buff *skb)
@@ -107,14 +109,16 @@ static int xfrm6_ah_rcv(struct sk_buff *skb)
 	return 0;
 }
 
-static void xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			 u8 type, u8 code, int offset, __be32 info)
 {
 	struct xfrm6_protocol *handler;
 
 	for_each_protocol_rcu(ah6_handlers, handler)
 		if (!handler->err_handler(skb, opt, type, code, offset, info))
-			break;
+			return 0;
+
+	return -ENOENT;
 }
 
 static int xfrm6_ipcomp_rcv(struct sk_buff *skb)
@@ -134,14 +138,16 @@ static int xfrm6_ipcomp_rcv(struct sk_buff *skb)
 	return 0;
 }
 
-static void xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			     u8 type, u8 code, int offset, __be32 info)
 {
 	struct xfrm6_protocol *handler;
 
 	for_each_protocol_rcu(ipcomp6_handlers, handler)
 		if (!handler->err_handler(skb, opt, type, code, offset, info))
-			break;
+			return 0;
+
+	return -ENOENT;
 }
 
 static const struct inet6_protocol esp6_protocol = {
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 5c36a99882ed..7ab08a5b36dc 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -574,7 +574,7 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t)
  * is probably better.
  *
  */
-void sctp_v4_err(struct sk_buff *skb, __u32 info)
+int sctp_v4_err(struct sk_buff *skb, __u32 info)
 {
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	const int ihlen = iph->ihl * 4;
@@ -599,7 +599,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info)
 	skb->transport_header = savesctp;
 	if (!sk) {
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-		return;
+		return -ENOENT;
 	}
 	/* Warning:  The sock lock is held.  Remember to call
 	 * sctp_err_finish!
@@ -653,6 +653,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info)
 
 out_unlock:
 	sctp_err_finish(sk, transport);
+	return 0;
 }
 
 /*
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index fc6c5e4bffa5..6e27c62646e9 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -138,7 +138,7 @@ static struct notifier_block sctp_inet6addr_notifier = {
 };
 
 /* ICMP error handler. */
-static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			u8 type, u8 code, int offset, __be32 info)
 {
 	struct inet6_dev *idev;
@@ -147,7 +147,7 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	struct sctp_transport *transport;
 	struct ipv6_pinfo *np;
 	__u16 saveip, savesctp;
-	int err;
+	int err, ret = 0;
 	struct net *net = dev_net(skb->dev);
 
 	idev = in6_dev_get(skb->dev);
@@ -163,6 +163,7 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	skb->transport_header = savesctp;
 	if (!sk) {
 		__ICMP6_INC_STATS(net, idev, ICMP6_MIB_INERRORS);
+		ret = -ENOENT;
 		goto out;
 	}
 
@@ -202,6 +203,8 @@ out_unlock:
 out:
 	if (likely(idev != NULL))
 		in6_dev_put(idev);
+
+	return ret;
 }
 
 static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
-- 
cgit v1.2.3


From e7cc082455cb49ea937a3ec4ab3d001b0b5f137b Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 8 Nov 2018 12:19:22 +0100
Subject: udp: Support for error handlers of tunnels with arbitrary destination
 port

ICMP error handling is currently not possible for UDP tunnels not
employing a receiving socket with local destination port matching the
remote one, because we have no way to look them up.

Add an err_handler tunnel encapsulation operation that can be exported by
tunnels in order to pass the error to the protocol implementing the
encapsulation. We can't easily use a lookup function as we did for VXLAN
and GENEVE, as protocol error handlers, which would be in turn called by
implementations of this new operation, handle the errors themselves,
together with the tunnel lookup.

Without a socket, we can't be sure which encapsulation error handler is
the appropriate one: encapsulation handlers (the ones for FoU and GUE
introduced in the next patch, e.g.) will need to check the new error codes
returned by protocol handlers to figure out if errors match the given
encapsulation, and, in turn, report this error back, so that we can try
all of them in __udp{4,6}_lib_err_encap_no_sk() until we have a match.

v2:
- Name all arguments in err_handler prototypes (David Miller)

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_tunnel.h |  2 ++
 include/net/ip_tunnels.h |  1 +
 net/ipv4/udp.c           | 70 ++++++++++++++++++++++++++++++++------------
 net/ipv6/udp.c           | 75 +++++++++++++++++++++++++++++++++++++-----------
 4 files changed, 113 insertions(+), 35 deletions(-)

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 236e40ba06bf..69b4bcf880c9 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -69,6 +69,8 @@ struct ip6_tnl_encap_ops {
 	size_t (*encap_hlen)(struct ip_tunnel_encap *e);
 	int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
 			    u8 *protocol, struct flowi6 *fl6);
+	int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
+			   u8 type, u8 code, int offset, __be32 info);
 };
 
 #ifdef CONFIG_INET
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index b0d022ff6ea1..db6b2218a2ad 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -311,6 +311,7 @@ struct ip_tunnel_encap_ops {
 	size_t (*encap_hlen)(struct ip_tunnel_encap *e);
 	int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
 			    u8 *protocol, struct flowi4 *fl4);
+	int (*err_handler)(struct sk_buff *skb, u32 info);
 };
 
 #define MAX_IPTUN_ENCAP_OPS 8
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index a505ee5eb92c..6f8890c5bc7e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -105,6 +105,7 @@
 #include <net/net_namespace.h>
 #include <net/icmp.h>
 #include <net/inet_hashtables.h>
+#include <net/ip_tunnels.h>
 #include <net/route.h>
 #include <net/checksum.h>
 #include <net/xfrm.h>
@@ -590,6 +591,26 @@ void udp_encap_enable(void)
 }
 EXPORT_SYMBOL(udp_encap_enable);
 
+/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
+ * through error handlers in encapsulations looking for a match.
+ */
+static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info)
+{
+	int i;
+
+	for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
+		int (*handler)(struct sk_buff *skb, u32 info);
+
+		if (!iptun_encaps[i])
+			continue;
+		handler = rcu_dereference(iptun_encaps[i]->err_handler);
+		if (handler && !handler(skb, info))
+			return 0;
+	}
+
+	return -ENOENT;
+}
+
 /* Try to match ICMP errors to UDP tunnels by looking up a socket without
  * reversing source and destination port: this will match tunnels that force the
  * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
@@ -597,28 +618,25 @@ EXPORT_SYMBOL(udp_encap_enable);
  * different destination ports on endpoints, in this case we won't be able to
  * trace ICMP messages back to them.
  *
+ * If this doesn't match any socket, probe tunnels with arbitrary destination
+ * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port
+ * we've sent packets to won't necessarily match the local destination port.
+ *
  * Then ask the tunnel implementation to match the error against a valid
  * association.
  *
- * Return the socket if we have a match.
+ * Return an error if we can't find a match, the socket if we need further
+ * processing, zero otherwise.
  */
 static struct sock *__udp4_lib_err_encap(struct net *net,
 					 const struct iphdr *iph,
 					 struct udphdr *uh,
 					 struct udp_table *udptable,
-					 struct sk_buff *skb)
+					 struct sk_buff *skb, u32 info)
 {
-	int (*lookup)(struct sock *sk, struct sk_buff *skb);
 	int network_offset, transport_offset;
-	struct udp_sock *up;
 	struct sock *sk;
 
-	sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
-			       iph->saddr, uh->dest, skb->dev->ifindex, 0,
-			       udptable, NULL);
-	if (!sk)
-		return NULL;
-
 	network_offset = skb_network_offset(skb);
 	transport_offset = skb_transport_offset(skb);
 
@@ -628,10 +646,20 @@ static struct sock *__udp4_lib_err_encap(struct net *net,
 	/* Transport header needs to point to the UDP header */
 	skb_set_transport_header(skb, iph->ihl << 2);
 
-	up = udp_sk(sk);
-	lookup = READ_ONCE(up->encap_err_lookup);
-	if (!lookup || lookup(sk, skb))
-		sk = NULL;
+	sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
+			       iph->saddr, uh->dest, skb->dev->ifindex, 0,
+			       udptable, NULL);
+	if (sk) {
+		int (*lookup)(struct sock *sk, struct sk_buff *skb);
+		struct udp_sock *up = udp_sk(sk);
+
+		lookup = READ_ONCE(up->encap_err_lookup);
+		if (!lookup || lookup(sk, skb))
+			sk = NULL;
+	}
+
+	if (!sk)
+		sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info));
 
 	skb_set_transport_header(skb, transport_offset);
 	skb_set_network_header(skb, network_offset);
@@ -668,13 +696,19 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 			       inet_sdif(skb), udptable, NULL);
 	if (!sk) {
 		/* No socket for error: try tunnels before discarding */
-		if (static_branch_unlikely(&udp_encap_needed_key))
-			sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb);
+		sk = ERR_PTR(-ENOENT);
+		if (static_branch_unlikely(&udp_encap_needed_key)) {
+			sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb,
+						  info);
+			if (!sk)
+				return 0;
+		}
 
-		if (!sk) {
+		if (IS_ERR(sk)) {
 			__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-			return -ENOENT;
+			return PTR_ERR(sk);
 		}
+
 		tunnel = true;
 	}
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 61316ec48b51..0c0cb1611aef 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -45,6 +45,7 @@
 #include <net/raw.h>
 #include <net/tcp_states.h>
 #include <net/ip6_checksum.h>
+#include <net/ip6_tunnel.h>
 #include <net/xfrm.h>
 #include <net/inet_hashtables.h>
 #include <net/inet6_hashtables.h>
@@ -469,6 +470,29 @@ void udpv6_encap_enable(void)
 }
 EXPORT_SYMBOL(udpv6_encap_enable);
 
+/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
+ * through error handlers in encapsulations looking for a match.
+ */
+static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb,
+				      struct inet6_skb_parm *opt,
+				      u8 type, u8 code, int offset, u32 info)
+{
+	int i;
+
+	for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
+		int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
+			       u8 type, u8 code, int offset, u32 info);
+
+		if (!ip6tun_encaps[i])
+			continue;
+		handler = rcu_dereference(ip6tun_encaps[i]->err_handler);
+		if (handler && !handler(skb, opt, type, code, offset, info))
+			return 0;
+	}
+
+	return -ENOENT;
+}
+
 /* Try to match ICMP errors to UDP tunnels by looking up a socket without
  * reversing source and destination port: this will match tunnels that force the
  * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
@@ -476,28 +500,27 @@ EXPORT_SYMBOL(udpv6_encap_enable);
  * different destination ports on endpoints, in this case we won't be able to
  * trace ICMP messages back to them.
  *
+ * If this doesn't match any socket, probe tunnels with arbitrary destination
+ * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port
+ * we've sent packets to won't necessarily match the local destination port.
+ *
  * Then ask the tunnel implementation to match the error against a valid
  * association.
  *
- * Return the socket if we have a match.
+ * Return an error if we can't find a match, the socket if we need further
+ * processing, zero otherwise.
  */
 static struct sock *__udp6_lib_err_encap(struct net *net,
 					 const struct ipv6hdr *hdr, int offset,
 					 struct udphdr *uh,
 					 struct udp_table *udptable,
-					 struct sk_buff *skb)
+					 struct sk_buff *skb,
+					 struct inet6_skb_parm *opt,
+					 u8 type, u8 code, __be32 info)
 {
-	int (*lookup)(struct sock *sk, struct sk_buff *skb);
 	int network_offset, transport_offset;
-	struct udp_sock *up;
 	struct sock *sk;
 
-	sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
-			       &hdr->saddr, uh->dest,
-			       inet6_iif(skb), 0, udptable, skb);
-	if (!sk)
-		return NULL;
-
 	network_offset = skb_network_offset(skb);
 	transport_offset = skb_transport_offset(skb);
 
@@ -507,13 +530,26 @@ static struct sock *__udp6_lib_err_encap(struct net *net,
 	/* Transport header needs to point to the UDP header */
 	skb_set_transport_header(skb, offset);
 
-	up = udp_sk(sk);
-	lookup = READ_ONCE(up->encap_err_lookup);
-	if (!lookup || lookup(sk, skb))
-		sk = NULL;
+	sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
+			       &hdr->saddr, uh->dest,
+			       inet6_iif(skb), 0, udptable, skb);
+	if (sk) {
+		int (*lookup)(struct sock *sk, struct sk_buff *skb);
+		struct udp_sock *up = udp_sk(sk);
+
+		lookup = READ_ONCE(up->encap_err_lookup);
+		if (!lookup || lookup(sk, skb))
+			sk = NULL;
+	}
+
+	if (!sk) {
+		sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code,
+							offset, info));
+	}
 
 	skb_set_transport_header(skb, transport_offset);
 	skb_set_network_header(skb, network_offset);
+
 	return sk;
 }
 
@@ -536,16 +572,21 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			       inet6_iif(skb), inet6_sdif(skb), udptable, skb);
 	if (!sk) {
 		/* No socket for error: try tunnels before discarding */
+		sk = ERR_PTR(-ENOENT);
 		if (static_branch_unlikely(&udpv6_encap_needed_key)) {
 			sk = __udp6_lib_err_encap(net, hdr, offset, uh,
-						  udptable, skb);
+						  udptable, skb,
+						  opt, type, code, info);
+			if (!sk)
+				return 0;
 		}
 
-		if (!sk) {
+		if (IS_ERR(sk)) {
 			__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
 					  ICMP6_MIB_INERRORS);
-			return -ENOENT;
+			return PTR_ERR(sk);
 		}
+
 		tunnel = true;
 	}
 
-- 
cgit v1.2.3


From b8a51b38e4d4dec3e379d52c0fe1a66827f7cf1e Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 8 Nov 2018 12:19:23 +0100
Subject: fou, fou6: ICMP error handlers for FoU and GUE

As the destination port in FoU and GUE receiving sockets doesn't
necessarily match the remote destination port, we can't associate errors
to the encapsulating tunnels with a socket lookup -- we need to blindly
try them instead. This means we don't even know if we are handling errors
for FoU or GUE without digging into the packets.

Hence, implement a single handler for both, one for IPv4 and one for IPv6,
that will check whether the packet that generated the ICMP error used a
direct IP encapsulation or if it had a GUE header, and send the error to
the matching protocol handler, if any.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fou.c      | 68 ++++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/protocol.c |  1 +
 net/ipv6/fou6.c     | 74 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 143 insertions(+)

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 500a59906b87..0d0ad19ecb87 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -3,6 +3,7 @@
 #include <linux/socket.h>
 #include <linux/skbuff.h>
 #include <linux/ip.h>
+#include <linux/icmp.h>
 #include <linux/udp.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -1003,15 +1004,82 @@ static int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 	return 0;
 }
 
+static int gue_err_proto_handler(int proto, struct sk_buff *skb, u32 info)
+{
+	const struct net_protocol *ipprot = rcu_dereference(inet_protos[proto]);
+
+	if (ipprot && ipprot->err_handler) {
+		if (!ipprot->err_handler(skb, info))
+			return 0;
+	}
+
+	return -ENOENT;
+}
+
+static int gue_err(struct sk_buff *skb, u32 info)
+{
+	int transport_offset = skb_transport_offset(skb);
+	struct guehdr *guehdr;
+	size_t optlen;
+	int ret;
+
+	if (skb->len < sizeof(struct udphdr) + sizeof(struct guehdr))
+		return -EINVAL;
+
+	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
+
+	switch (guehdr->version) {
+	case 0: /* Full GUE header present */
+		break;
+	case 1: {
+		/* Direct encasulation of IPv4 or IPv6 */
+		skb_set_transport_header(skb, -(int)sizeof(struct icmphdr));
+
+		switch (((struct iphdr *)guehdr)->version) {
+		case 4:
+			ret = gue_err_proto_handler(IPPROTO_IPIP, skb, info);
+			goto out;
+#if IS_ENABLED(CONFIG_IPV6)
+		case 6:
+			ret = gue_err_proto_handler(IPPROTO_IPV6, skb, info);
+			goto out;
+#endif
+		default:
+			ret = -EOPNOTSUPP;
+			goto out;
+		}
+	}
+	default: /* Undefined version */
+		return -EOPNOTSUPP;
+	}
+
+	if (guehdr->control)
+		return -ENOENT;
+
+	optlen = guehdr->hlen << 2;
+
+	if (validate_gue_flags(guehdr, optlen))
+		return -EINVAL;
+
+	skb_set_transport_header(skb, -(int)sizeof(struct icmphdr));
+	ret = gue_err_proto_handler(guehdr->proto_ctype, skb, info);
+
+out:
+	skb_set_transport_header(skb, transport_offset);
+	return ret;
+}
+
 
 static const struct ip_tunnel_encap_ops fou_iptun_ops = {
 	.encap_hlen = fou_encap_hlen,
 	.build_header = fou_build_header,
+	.err_handler = gue_err,
 };
 
 static const struct ip_tunnel_encap_ops gue_iptun_ops = {
 	.encap_hlen = gue_encap_hlen,
 	.build_header = gue_build_header,
+	.err_handler = gue_err,
 };
 
 static int ip_tunnel_encap_add_fou_ops(void)
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 32a691b7ce2c..92d249e053be 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -29,6 +29,7 @@
 #include <net/protocol.h>
 
 struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
+EXPORT_SYMBOL(inet_protos);
 const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
 EXPORT_SYMBOL(inet_offloads);
 
diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c
index 6de3c04b0f30..bd675c61deb1 100644
--- a/net/ipv6/fou6.c
+++ b/net/ipv6/fou6.c
@@ -4,6 +4,7 @@
 #include <linux/skbuff.h>
 #include <linux/ip.h>
 #include <linux/udp.h>
+#include <linux/icmpv6.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <net/fou.h>
@@ -69,14 +70,87 @@ static int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 	return 0;
 }
 
+static int gue6_err_proto_handler(int proto, struct sk_buff *skb,
+				  struct inet6_skb_parm *opt,
+				  u8 type, u8 code, int offset, u32 info)
+{
+	const struct inet6_protocol *ipprot;
+
+	ipprot = rcu_dereference(inet6_protos[proto]);
+	if (ipprot && ipprot->err_handler) {
+		if (!ipprot->err_handler(skb, opt, type, code, offset, info))
+			return 0;
+	}
+
+	return -ENOENT;
+}
+
+static int gue6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+		    u8 type, u8 code, int offset, __be32 info)
+{
+	int transport_offset = skb_transport_offset(skb);
+	struct guehdr *guehdr;
+	size_t optlen;
+	int ret;
+
+	if (skb->len < sizeof(struct udphdr) + sizeof(struct guehdr))
+		return -EINVAL;
+
+	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
+
+	switch (guehdr->version) {
+	case 0: /* Full GUE header present */
+		break;
+	case 1: {
+		/* Direct encasulation of IPv4 or IPv6 */
+		skb_set_transport_header(skb, -(int)sizeof(struct icmp6hdr));
+
+		switch (((struct iphdr *)guehdr)->version) {
+		case 4:
+			ret = gue6_err_proto_handler(IPPROTO_IPIP, skb, opt,
+						     type, code, offset, info);
+			goto out;
+		case 6:
+			ret = gue6_err_proto_handler(IPPROTO_IPV6, skb, opt,
+						     type, code, offset, info);
+			goto out;
+		default:
+			ret = -EOPNOTSUPP;
+			goto out;
+		}
+	}
+	default: /* Undefined version */
+		return -EOPNOTSUPP;
+	}
+
+	if (guehdr->control)
+		return -ENOENT;
+
+	optlen = guehdr->hlen << 2;
+
+	if (validate_gue_flags(guehdr, optlen))
+		return -EINVAL;
+
+	skb_set_transport_header(skb, -(int)sizeof(struct icmp6hdr));
+	ret = gue6_err_proto_handler(guehdr->proto_ctype, skb,
+				     opt, type, code, offset, info);
+
+out:
+	skb_set_transport_header(skb, transport_offset);
+	return ret;
+}
+
+
 static const struct ip6_tnl_encap_ops fou_ip6tun_ops = {
 	.encap_hlen = fou_encap_hlen,
 	.build_header = fou6_build_header,
+	.err_handler = gue6_err,
 };
 
 static const struct ip6_tnl_encap_ops gue_ip6tun_ops = {
 	.encap_hlen = gue_encap_hlen,
 	.build_header = gue6_build_header,
+	.err_handler = gue6_err,
 };
 
 static int ip6_tnl_encap_add_fou_ops(void)
-- 
cgit v1.2.3


From 56fd865f46b894681dd7e7f83761243add7a71a3 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 8 Nov 2018 12:19:24 +0100
Subject: selftests: pmtu: Introduce FoU and GUE PMTU exceptions tests

Introduce eight tests, for FoU and GUE, with IPv4 and IPv6 payload,
on IPv4 and IPv6 transport, that check that PMTU exceptions are created
with the right value when exceeding the MTU on a link of the path.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 179 ++++++++++++++++++++++++++++++++++++
 1 file changed, 179 insertions(+)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 14d20782ccb7..e2c94e47707c 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -59,6 +59,14 @@
 #	Same as pmtu_ipv6_vxlan6_exception, but using a GENEVE tunnel instead of
 #	VXLAN
 #
+# - pmtu_ipv{4,6}_fou{4,6}_exception
+#	Same as pmtu_ipv4_vxlan4, but using a direct IPv4/IPv6 encapsulation
+#	(FoU) over IPv4/IPv6, instead of VXLAN
+#
+# - pmtu_ipv{4,6}_fou{4,6}_exception
+#	Same as pmtu_ipv4_vxlan4, but using a generic UDP IPv4/IPv6
+#	encapsulation (GUE) over IPv4/IPv6, instead of VXLAN
+#
 # - pmtu_vti4_exception
 #	Set up vti tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is not
@@ -113,6 +121,14 @@ tests="
 	pmtu_ipv6_geneve4_exception	IPv6 over geneve4: PMTU exceptions
 	pmtu_ipv4_geneve6_exception	IPv4 over geneve6: PMTU exceptions
 	pmtu_ipv6_geneve6_exception	IPv6 over geneve6: PMTU exceptions
+	pmtu_ipv4_fou4_exception	IPv4 over fou4: PMTU exceptions
+	pmtu_ipv6_fou4_exception	IPv6 over fou4: PMTU exceptions
+	pmtu_ipv4_fou6_exception	IPv4 over fou6: PMTU exceptions
+	pmtu_ipv6_fou6_exception	IPv6 over fou6: PMTU exceptions
+	pmtu_ipv4_gue4_exception	IPv4 over gue4: PMTU exceptions
+	pmtu_ipv6_gue4_exception	IPv6 over gue4: PMTU exceptions
+	pmtu_ipv4_gue6_exception	IPv4 over gue6: PMTU exceptions
+	pmtu_ipv6_gue6_exception	IPv6 over gue6: PMTU exceptions
 	pmtu_vti6_exception		vti6: PMTU exceptions
 	pmtu_vti4_exception		vti4: PMTU exceptions
 	pmtu_vti4_default_mtu		vti4: default MTU assignment
@@ -200,6 +216,89 @@ nsname() {
 	eval echo \$NS_$1
 }
 
+setup_fou_or_gue() {
+	outer="${1}"
+	inner="${2}"
+	encap="${3}"
+
+	if [ "${outer}" = "4" ]; then
+		modprobe fou || return 2
+		a_addr="${prefix4}.${a_r1}.1"
+		b_addr="${prefix4}.${b_r1}.1"
+		if [ "${inner}" = "4" ]; then
+			type="ipip"
+			ipproto="4"
+		else
+			type="sit"
+			ipproto="41"
+		fi
+	else
+		modprobe fou6 || return 2
+		a_addr="${prefix6}:${a_r1}::1"
+		b_addr="${prefix6}:${b_r1}::1"
+		if [ "${inner}" = "4" ]; then
+			type="ip6tnl"
+			mode="mode ipip6"
+			ipproto="4 -6"
+		else
+			type="ip6tnl"
+			mode="mode ip6ip6"
+			ipproto="41 -6"
+		fi
+	fi
+
+	${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2
+	${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return 2
+
+	${ns_b} ip fou add port 5556 ipproto ${ipproto}
+	${ns_b} ip link add ${encap}_b type ${type} ${mode} local ${b_addr} remote ${a_addr} encap ${encap} encap-sport auto encap-dport 5555
+
+	if [ "${inner}" = "4" ]; then
+		${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${encap}_a
+		${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${encap}_b
+	else
+		${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${encap}_a
+		${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${encap}_b
+	fi
+
+	${ns_a} ip link set ${encap}_a up
+	${ns_b} ip link set ${encap}_b up
+
+	sleep 1
+}
+
+setup_fou44() {
+	setup_fou_or_gue 4 4 fou
+}
+
+setup_fou46() {
+	setup_fou_or_gue 4 6 fou
+}
+
+setup_fou64() {
+	setup_fou_or_gue 6 4 fou
+}
+
+setup_fou66() {
+	setup_fou_or_gue 6 6 fou
+}
+
+setup_gue44() {
+	setup_fou_or_gue 4 4 gue
+}
+
+setup_gue46() {
+	setup_fou_or_gue 4 6 gue
+}
+
+setup_gue64() {
+	setup_fou_or_gue 6 4 gue
+}
+
+setup_gue66() {
+	setup_fou_or_gue 6 6 gue
+}
+
 setup_namespaces() {
 	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
 		ip netns add ${n} || return 1
@@ -627,6 +726,86 @@ test_pmtu_ipv6_geneve6_exception() {
 	test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 6
 }
 
+test_pmtu_ipvX_over_fouY_or_gueY() {
+	inner_family=${1}
+	outer_family=${2}
+	encap=${3}
+	ll_mtu=4000
+
+	setup namespaces routing ${encap}${outer_family}${inner_family} || return 2
+	trace "${ns_a}" ${encap}_a   "${ns_b}"  ${encap}_b \
+	      "${ns_a}" veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_b}" veth_B-R1    "${ns_r1}" veth_R1-B
+
+	if [ ${inner_family} -eq 4 ]; then
+		ping=ping
+		dst=${tunnel4_b_addr}
+	else
+		ping=${ping6}
+		dst=${tunnel6_b_addr}
+	fi
+
+	if [ "${encap}" = "gue" ]; then
+		encap_overhead=4
+	else
+		encap_overhead=0
+	fi
+
+	if [ ${outer_family} -eq 4 ]; then
+		#                      IPv4 header   UDP header
+		exp_mtu=$((${ll_mtu} - 20          - 8         - ${encap_overhead}))
+	else
+		#                      IPv6 header   Option 4   UDP header
+		exp_mtu=$((${ll_mtu} - 40          - 8        - 8       - ${encap_overhead}))
+	fi
+
+	# Create route exception by exceeding link layer MTU
+	mtu "${ns_a}"  veth_A-R1 $((${ll_mtu} + 1000))
+	mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
+	mtu "${ns_b}"  veth_B-R1 ${ll_mtu}
+	mtu "${ns_r1}" veth_R1-B ${ll_mtu}
+
+	mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000))
+	mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000))
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+
+	# Check that exception was created
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
+	check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ${encap} interface"
+}
+
+test_pmtu_ipv4_fou4_exception() {
+	test_pmtu_ipvX_over_fouY_or_gueY 4 4 fou
+}
+
+test_pmtu_ipv6_fou4_exception() {
+	test_pmtu_ipvX_over_fouY_or_gueY 6 4 fou
+}
+
+test_pmtu_ipv4_fou6_exception() {
+	test_pmtu_ipvX_over_fouY_or_gueY 4 6 fou
+}
+
+test_pmtu_ipv6_fou6_exception() {
+	test_pmtu_ipvX_over_fouY_or_gueY 6 6 fou
+}
+
+test_pmtu_ipv4_gue4_exception() {
+	test_pmtu_ipvX_over_fouY_or_gueY 4 4 gue
+}
+
+test_pmtu_ipv6_gue4_exception() {
+	test_pmtu_ipvX_over_fouY_or_gueY 6 4 gue
+}
+
+test_pmtu_ipv4_gue6_exception() {
+	test_pmtu_ipvX_over_fouY_or_gueY 4 6 gue
+}
+
+test_pmtu_ipv6_gue6_exception() {
+	test_pmtu_ipvX_over_fouY_or_gueY 6 6 gue
+}
+
 test_pmtu_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
 	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
-- 
cgit v1.2.3


From 04087d9a89bef97998c71c21e3ecfca0cc7c52f3 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Thu, 8 Nov 2018 20:40:20 +0800
Subject: openvswitch: remove BUG_ON from get_dpdev

if local is NULL pointer, and the following access of local's
dev will trigger panic, which is same as BUG_ON

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/vport-netdev.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index 2e5e7a41d8ef..9bec22e3e9e8 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -84,7 +84,6 @@ static struct net_device *get_dpdev(const struct datapath *dp)
 	struct vport *local;
 
 	local = ovs_vport_ovsl(dp, OVSP_LOCAL);
-	BUG_ON(!local);
 	return local->dev;
 }
 
-- 
cgit v1.2.3


From b144b99fff69a5bc0d34c8e168bedb88c68ca23d Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 8 Nov 2018 15:06:15 +0100
Subject: s390/qeth: utilize virtual MAC for Layer2 OSD devices

By default, READ MAC on a Layer2 OSD device returns the adapter's
burnt-in MAC address. Given the default scenario of many virtual devices
on the same adapter, qeth can't make any use of this address and
therefore skips the READ MAC call for this device type.

But in some configurations, the READ MAC command for a Layer2 OSD device
actually returns a pre-provisioned, virtual MAC address. So enable the
READ MAC code to detect this situation, and let the L2 subdriver
call READ MAC for OSD devices.

This also removes the QETH_LAYER2_MAC_READ flag, which protects L2
devices against calling READ MAC multiple times. Instead protect the
whole call to qeth_l2_request_initial_mac().

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  1 -
 drivers/s390/net/qeth_core_main.c | 12 +++++++-----
 drivers/s390/net/qeth_core_mpc.h  | 25 +++++++++++++++----------
 drivers/s390/net/qeth_l2_main.c   | 10 ++++------
 4 files changed, 26 insertions(+), 22 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 04e294d1d16d..99af1a0a3314 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -665,7 +665,6 @@ struct qeth_card_blkt {
 
 #define QETH_BROADCAST_WITH_ECHO    0x01
 #define QETH_BROADCAST_WITHOUT_ECHO 0x02
-#define QETH_LAYER2_MAC_READ	    0x01
 #define QETH_LAYER2_MAC_REGISTERED  0x02
 struct qeth_card_info {
 	unsigned short unit_addr2;
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 4bce5ae65a55..abeecffb6d2e 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -4235,16 +4235,18 @@ static int qeth_setadpparms_change_macaddr_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
 {
 	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
+	struct qeth_ipacmd_setadpparms *adp_cmd;
 
 	QETH_CARD_TEXT(card, 4, "chgmaccb");
 	if (qeth_setadpparms_inspect_rc(cmd))
 		return 0;
 
-	if (IS_LAYER3(card) || !(card->info.mac_bits & QETH_LAYER2_MAC_READ)) {
-		ether_addr_copy(card->dev->dev_addr,
-				cmd->data.setadapterparms.data.change_addr.addr);
-		card->info.mac_bits |= QETH_LAYER2_MAC_READ;
-	}
+	adp_cmd = &cmd->data.setadapterparms;
+	if (IS_LAYER2(card) && IS_OSD(card) && !IS_VM_NIC(card) &&
+	    !(adp_cmd->hdr.flags & QETH_SETADP_FLAGS_VIRTUAL_MAC))
+		return 0;
+
+	ether_addr_copy(card->dev->dev_addr, adp_cmd->data.change_addr.addr);
 	return 0;
 }
 
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index 3e54be201b27..10cc487c16d6 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -80,7 +80,9 @@ enum qeth_card_types {
 };
 
 #define IS_IQD(card)	((card)->info.type == QETH_CARD_TYPE_IQD)
+#define IS_OSD(card)	((card)->info.type == QETH_CARD_TYPE_OSD)
 #define IS_OSN(card)	((card)->info.type == QETH_CARD_TYPE_OSN)
+#define IS_VM_NIC(card)	((card)->info.guestlan)
 
 #define QETH_MPC_DIFINFO_LEN_INDICATES_LINK_TYPE 0x18
 /* only the first two bytes are looked at in qeth_get_cardname_short */
@@ -529,17 +531,20 @@ struct qeth_query_switch_attributes {
 	__u8  reserved3[8];
 };
 
+#define QETH_SETADP_FLAGS_VIRTUAL_MAC	0x80	/* for CHANGE_ADDR_READ_MAC */
+
 struct qeth_ipacmd_setadpparms_hdr {
-	__u32 supp_hw_cmds;
-	__u32 reserved1;
-	__u16 cmdlength;
-	__u16 reserved2;
-	__u32 command_code;
-	__u16 return_code;
-	__u8  used_total;
-	__u8  seq_no;
-	__u32 reserved3;
-} __attribute__ ((packed));
+	u32 supp_hw_cmds;
+	u32 reserved1;
+	u16 cmdlength;
+	u16 reserved2;
+	u32 command_code;
+	u16 return_code;
+	u8 used_total;
+	u8 seq_no;
+	u8 flags;
+	u8 reserved3[3];
+};
 
 struct qeth_ipacmd_setadpparms {
 	struct qeth_ipacmd_setadpparms_hdr hdr;
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 2914a1a69f83..8d3601891c62 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -461,12 +461,9 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card)
 		/* fall back to alternative mechanism: */
 	}
 
-	if (card->info.type == QETH_CARD_TYPE_IQD ||
-	    card->info.type == QETH_CARD_TYPE_OSM ||
-	    card->info.type == QETH_CARD_TYPE_OSX ||
-	    card->info.guestlan) {
+	if (!IS_OSN(card)) {
 		rc = qeth_setadpparms_change_macaddr(card);
-		if (!rc)
+		if (!rc && is_valid_ether_addr(card->dev->dev_addr))
 			goto out;
 		QETH_DBF_MESSAGE(2, "READ_MAC Assist failed on device %x: %#x\n",
 				 CARD_DEVID(card), rc);
@@ -917,7 +914,8 @@ static int qeth_l2_setup_netdev(struct qeth_card *card, bool carrier_ok)
 				       PAGE_SIZE * (QDIO_MAX_ELEMENTS_PER_BUFFER - 1));
 	}
 
-	qeth_l2_request_initial_mac(card);
+	if (!is_valid_ether_addr(card->dev->dev_addr))
+		qeth_l2_request_initial_mac(card);
 	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
 	rc = register_netdev(card->dev);
 	if (!rc && carrier_ok)
-- 
cgit v1.2.3


From 5a541f6d00c6d8aace789dfaa468443bd0edf564 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 8 Nov 2018 15:06:16 +0100
Subject: s390/qeth: handle af_iucv skbs in qeth_l3_fill_header()

Filling the HW header from one single function will make it easier to
rip out all the duplicated transmit code in qeth_l3_xmit(). On top, this
saves one conditional branch in the TSO path.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h    |  2 +-
 drivers/s390/net/qeth_l3_main.c | 45 +++++++++++++++--------------------------
 2 files changed, 17 insertions(+), 30 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 99af1a0a3314..d50d91219cf3 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -314,7 +314,7 @@ struct qeth_hdr_layer3 {
 	__u16 frame_offset;
 	union {
 		/* TX: */
-		u8 ipv6_addr[16];
+		struct in6_addr ipv6_addr;
 		struct ipv4 {
 			u8 res[12];
 			u32 addr;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index f08b745c2007..004085344e85 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1929,22 +1929,6 @@ static int qeth_l3_get_cast_type(struct sk_buff *skb)
 	}
 }
 
-static void qeth_l3_fill_af_iucv_hdr(struct qeth_hdr *hdr, struct sk_buff *skb,
-				     unsigned int data_len)
-{
-	char daddr[16];
-
-	hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3;
-	hdr->hdr.l3.length = data_len;
-	hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST;
-
-	memset(daddr, 0, sizeof(daddr));
-	daddr[0] = 0xfe;
-	daddr[1] = 0x80;
-	memcpy(&daddr[8], iucv_trans_hdr(skb)->destUserID, 8);
-	memcpy(hdr->hdr.l3.next_hop.ipv6_addr, daddr, 16);
-}
-
 static u8 qeth_l3_cast_type_to_flag(int cast_type)
 {
 	if (cast_type == RTN_MULTICAST)
@@ -1960,6 +1944,7 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
 				struct sk_buff *skb, int ipv, int cast_type,
 				unsigned int data_len)
 {
+	struct qeth_hdr_layer3 *l3_hdr = &hdr->hdr.l3;
 	struct vlan_ethhdr *veth = vlan_eth_hdr(skb);
 
 	hdr->hdr.l3.length = data_len;
@@ -1968,6 +1953,15 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
 		hdr->hdr.l3.id = QETH_HEADER_TYPE_L3_TSO;
 	} else {
 		hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3;
+
+		if (skb->protocol == htons(ETH_P_AF_IUCV)) {
+			l3_hdr->flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST;
+			l3_hdr->next_hop.ipv6_addr.s6_addr16[0] = htons(0xfe80);
+			memcpy(&l3_hdr->next_hop.ipv6_addr.s6_addr32[2],
+			       iucv_trans_hdr(skb)->destUserID, 8);
+			return;
+		}
+
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			qeth_tx_csum(skb, &hdr->hdr.l3.ext_flags, ipv);
 			/* some HW requires combined L3+L4 csum offload: */
@@ -2012,13 +2006,11 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
 	} else {
 		/* IPv6 */
 		const struct rt6_info *rt = skb_rt6_info(skb);
-		const struct in6_addr *next_hop;
 
 		if (rt && !ipv6_addr_any(&rt->rt6i_gateway))
-			next_hop = &rt->rt6i_gateway;
+			l3_hdr->next_hop.ipv6_addr = rt->rt6i_gateway;
 		else
-			next_hop = &ipv6_hdr(skb)->daddr;
-		memcpy(hdr->hdr.l3.next_hop.ipv6_addr, next_hop, 16);
+			l3_hdr->next_hop.ipv6_addr = ipv6_hdr(skb)->daddr;
 
 		hdr->hdr.l3.flags |= QETH_HDR_IPV6;
 		if (card->info.type != QETH_CARD_TYPE_IQD)
@@ -2082,15 +2074,10 @@ static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
 	}
 	memset(hdr, 0, hw_hdr_len);
 
-	if (skb->protocol == htons(ETH_P_AF_IUCV)) {
-		qeth_l3_fill_af_iucv_hdr(hdr, skb, frame_len);
-	} else {
-		qeth_l3_fill_header(card, hdr, skb, ipv, cast_type, frame_len);
-		if (is_tso)
-			qeth_fill_tso_ext((struct qeth_hdr_tso *) hdr,
-					  frame_len - proto_len, skb,
-					  proto_len);
-	}
+	qeth_l3_fill_header(card, hdr, skb, ipv, cast_type, frame_len);
+	if (is_tso)
+		qeth_fill_tso_ext((struct qeth_hdr_tso *) hdr,
+				  frame_len - proto_len, skb, proto_len);
 
 	is_sg = skb_is_nonlinear(skb);
 	if (IS_IQD(card)) {
-- 
cgit v1.2.3


From 81ec54393944fc0303127e1357dbbd615a6abb63 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 8 Nov 2018 15:06:17 +0100
Subject: s390/qeth: unify transmit code

Since commit 82bf5c0867f6 ("s390/qeth: add support for IPv6 TSO"),
qeth_xmit() also knows how to build TSO packets and is practically
identical to qeth_l3_xmit().
Convert qeth_l3_xmit() into a thin wrapper that merely strips the
L2 header off a packet, and calls qeth_xmit() for the actual
TX processing.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  8 -----
 drivers/s390/net/qeth_core_main.c | 22 ++++++------
 drivers/s390/net/qeth_l3_main.c   | 72 +++++----------------------------------
 3 files changed, 19 insertions(+), 83 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index d50d91219cf3..afe3662a4ad5 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -1024,9 +1024,6 @@ int qeth_send_control_data(struct qeth_card *, int, struct qeth_cmd_buffer *,
 	int (*reply_cb)(struct qeth_card *, struct qeth_reply*, unsigned long),
 	void *reply_param);
 unsigned int qeth_count_elements(struct sk_buff *skb, unsigned int data_offset);
-int qeth_do_send_packet_fast(struct qeth_qdio_out_q *queue, struct sk_buff *skb,
-			     struct qeth_hdr *hdr, unsigned int offset,
-			     unsigned int hd_len);
 int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue,
 			struct sk_buff *skb, struct qeth_hdr *hdr,
 			unsigned int offset, unsigned int hd_len,
@@ -1057,11 +1054,6 @@ netdev_features_t qeth_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
 				      netdev_features_t features);
 int qeth_vm_request_mac(struct qeth_card *card);
-int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb,
-		       struct qeth_hdr **hdr, unsigned int hdr_len,
-		       unsigned int proto_len, unsigned int *elements);
-void qeth_fill_tso_ext(struct qeth_hdr_tso *hdr, unsigned int payload_len,
-		       struct sk_buff *skb, unsigned int proto_len);
 int qeth_xmit(struct qeth_card *card, struct sk_buff *skb,
 	      struct qeth_qdio_out_q *queue, int ipv, int cast_type,
 	      void (*fill_header)(struct qeth_card *card, struct qeth_hdr *hdr,
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index abeecffb6d2e..2568ddc1bbc3 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3777,9 +3777,9 @@ EXPORT_SYMBOL_GPL(qeth_count_elements);
  * The number of needed buffer elements is returned in @elements.
  * Error to create the hdr is indicated by returning with < 0.
  */
-int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb,
-		       struct qeth_hdr **hdr, unsigned int hdr_len,
-		       unsigned int proto_len, unsigned int *elements)
+static int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb,
+			      struct qeth_hdr **hdr, unsigned int hdr_len,
+			      unsigned int proto_len, unsigned int *elements)
 {
 	const unsigned int max_elements = QETH_MAX_BUFFER_ELEMENTS(card);
 	const unsigned int contiguous = proto_len ? proto_len : 1;
@@ -3849,7 +3849,6 @@ check_layout:
 	skb_copy_from_linear_data(skb, ((char *)*hdr) + hdr_len, proto_len);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(qeth_add_hw_header);
 
 static void __qeth_fill_buffer(struct sk_buff *skb,
 			       struct qeth_qdio_out_buffer *buf,
@@ -3972,9 +3971,9 @@ static int qeth_fill_buffer(struct qeth_qdio_out_q *queue,
 	return flush_cnt;
 }
 
-int qeth_do_send_packet_fast(struct qeth_qdio_out_q *queue, struct sk_buff *skb,
-			     struct qeth_hdr *hdr, unsigned int offset,
-			     unsigned int hd_len)
+static int qeth_do_send_packet_fast(struct qeth_qdio_out_q *queue,
+				    struct sk_buff *skb, struct qeth_hdr *hdr,
+				    unsigned int offset, unsigned int hd_len)
 {
 	int index = queue->next_buf_to_fill;
 	struct qeth_qdio_out_buffer *buffer = queue->bufs[index];
@@ -3990,7 +3989,6 @@ int qeth_do_send_packet_fast(struct qeth_qdio_out_q *queue, struct sk_buff *skb,
 	qeth_flush_buffers(queue, index, 1);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(qeth_do_send_packet_fast);
 
 int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue,
 			struct sk_buff *skb, struct qeth_hdr *hdr,
@@ -4082,8 +4080,9 @@ out:
 }
 EXPORT_SYMBOL_GPL(qeth_do_send_packet);
 
-void qeth_fill_tso_ext(struct qeth_hdr_tso *hdr, unsigned int payload_len,
-		       struct sk_buff *skb, unsigned int proto_len)
+static void qeth_fill_tso_ext(struct qeth_hdr_tso *hdr,
+			      unsigned int payload_len, struct sk_buff *skb,
+			      unsigned int proto_len)
 {
 	struct qeth_hdr_ext_tso *ext = &hdr->ext;
 
@@ -4096,7 +4095,6 @@ void qeth_fill_tso_ext(struct qeth_hdr_tso *hdr, unsigned int payload_len,
 	ext->mss = skb_shinfo(skb)->gso_size;
 	ext->dg_hdr_len = proto_len;
 }
-EXPORT_SYMBOL_GPL(qeth_fill_tso_ext);
 
 int qeth_xmit(struct qeth_card *card, struct sk_buff *skb,
 	      struct qeth_qdio_out_q *queue, int ipv, int cast_type,
@@ -4119,7 +4117,7 @@ int qeth_xmit(struct qeth_card *card, struct sk_buff *skb,
 		proto_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
 	} else {
 		hw_hdr_len = sizeof(struct qeth_hdr);
-		proto_len = IS_IQD(card) ? ETH_HLEN : 0;
+		proto_len = (IS_IQD(card) && IS_LAYER2(card)) ? ETH_HLEN : 0;
 	}
 
 	rc = skb_cow_head(skb, hw_hdr_len);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 004085344e85..61d847d41cab 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2036,79 +2036,25 @@ static void qeth_l3_fixup_headers(struct sk_buff *skb)
 static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
 			struct qeth_qdio_out_q *queue, int ipv, int cast_type)
 {
-	unsigned int hw_hdr_len, proto_len, frame_len, elements;
 	unsigned char eth_hdr[ETH_HLEN];
-	bool is_tso = skb_is_gso(skb);
-	unsigned int data_offset = 0;
-	struct qeth_hdr *hdr = NULL;
-	unsigned int hd_len = 0;
-	int push_len, rc;
-	bool is_sg;
-
-	if (is_tso) {
-		hw_hdr_len = sizeof(struct qeth_hdr_tso);
-		proto_len = skb_transport_offset(skb) + tcp_hdrlen(skb) -
-			    ETH_HLEN;
-	} else {
-		hw_hdr_len = sizeof(struct qeth_hdr);
-		proto_len = 0;
-	}
+	unsigned int hw_hdr_len;
+	int rc;
 
 	/* re-use the L2 header area for the HW header: */
+	hw_hdr_len = skb_is_gso(skb) ? sizeof(struct qeth_hdr_tso) :
+				       sizeof(struct qeth_hdr);
 	rc = skb_cow_head(skb, hw_hdr_len - ETH_HLEN);
 	if (rc)
 		return rc;
 	skb_copy_from_linear_data(skb, eth_hdr, ETH_HLEN);
 	skb_pull(skb, ETH_HLEN);
-	frame_len = skb->len;
 
 	qeth_l3_fixup_headers(skb);
-	push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, proto_len,
-				      &elements);
-	if (push_len < 0)
-		return push_len;
-	if (is_tso || !push_len) {
-		/* HW header needs its own buffer element. */
-		hd_len = hw_hdr_len + proto_len;
-		data_offset = push_len + proto_len;
-	}
-	memset(hdr, 0, hw_hdr_len);
-
-	qeth_l3_fill_header(card, hdr, skb, ipv, cast_type, frame_len);
-	if (is_tso)
-		qeth_fill_tso_ext((struct qeth_hdr_tso *) hdr,
-				  frame_len - proto_len, skb, proto_len);
-
-	is_sg = skb_is_nonlinear(skb);
-	if (IS_IQD(card)) {
-		rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset,
-					      hd_len);
-	} else {
-		/* TODO: drop skb_orphan() once TX completion is fast enough */
-		skb_orphan(skb);
-		rc = qeth_do_send_packet(card, queue, skb, hdr, data_offset,
-					 hd_len, elements);
-	}
-
-	if (!rc) {
-		if (card->options.performance_stats) {
-			card->perf_stats.buf_elements_sent += elements;
-			if (is_sg)
-				card->perf_stats.sg_skbs_sent++;
-			if (is_tso) {
-				card->perf_stats.large_send_bytes += frame_len;
-				card->perf_stats.large_send_cnt++;
-			}
-		}
-	} else {
-		if (!push_len)
-			kmem_cache_free(qeth_core_header_cache, hdr);
-		if (rc == -EBUSY) {
-			/* roll back to ETH header */
-			skb_pull(skb, push_len);
-			skb_push(skb, ETH_HLEN);
-			skb_copy_to_linear_data(skb, eth_hdr, ETH_HLEN);
-		}
+	rc = qeth_xmit(card, skb, queue, ipv, cast_type, qeth_l3_fill_header);
+	if (rc == -EBUSY) {
+		/* roll back to ETH header */
+		skb_push(skb, ETH_HLEN);
+		skb_copy_to_linear_data(skb, eth_hdr, ETH_HLEN);
 	}
 	return rc;
 }
-- 
cgit v1.2.3


From d7d18da1f7033439f5359f4a95303a496cd16feb Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 8 Nov 2018 15:06:18 +0100
Subject: s390/qeth: remove card list

Re-implement the card-by-RDEV lookup by using device model concepts, and
remove the now redundant list of all qeth card instances in the system.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  8 +-------
 drivers/s390/net/qeth_core_main.c | 25 +++++++++++++++----------
 drivers/s390/net/qeth_l2_main.c   | 35 ++++++++---------------------------
 3 files changed, 24 insertions(+), 44 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index afe3662a4ad5..0ee026947f20 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -774,7 +774,6 @@ struct qeth_switch_info {
 #define QETH_NAPI_WEIGHT NAPI_POLL_WEIGHT
 
 struct qeth_card {
-	struct list_head list;
 	enum qeth_card_states state;
 	spinlock_t lock;
 	struct ccwgroup_device *gdev;
@@ -826,11 +825,6 @@ struct qeth_card {
 	struct work_struct close_dev_work;
 };
 
-struct qeth_card_list_struct {
-	struct list_head list;
-	rwlock_t rwlock;
-};
-
 struct qeth_trap_id {
 	__u16 lparnr;
 	char vmname[8];
@@ -977,11 +971,11 @@ int qeth_core_load_discipline(struct qeth_card *, enum qeth_discipline_id);
 void qeth_core_free_discipline(struct qeth_card *);
 
 /* exports for qeth discipline device drivers */
-extern struct qeth_card_list_struct qeth_core_card_list;
 extern struct kmem_cache *qeth_core_header_cache;
 extern struct qeth_dbf_info qeth_dbf[QETH_DBF_INFOS];
 
 struct net_device *qeth_clone_netdev(struct net_device *orig);
+struct qeth_card *qeth_get_card_by_busid(char *bus_id);
 void qeth_set_recovery_task(struct qeth_card *);
 void qeth_clear_recovery_task(struct qeth_card *);
 void qeth_set_allowed_threads(struct qeth_card *, unsigned long , int);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 2568ddc1bbc3..508bad2dbd0b 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -54,8 +54,6 @@ struct qeth_dbf_info qeth_dbf[QETH_DBF_INFOS] = {
 };
 EXPORT_SYMBOL_GPL(qeth_dbf);
 
-struct qeth_card_list_struct qeth_core_card_list;
-EXPORT_SYMBOL_GPL(qeth_core_card_list);
 struct kmem_cache *qeth_core_header_cache;
 EXPORT_SYMBOL_GPL(qeth_core_header_cache);
 static struct kmem_cache *qeth_qdio_outbuf_cache;
@@ -5806,9 +5804,6 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 		break;
 	}
 
-	write_lock_irq(&qeth_core_card_list.rwlock);
-	list_add_tail(&card->list, &qeth_core_card_list.list);
-	write_unlock_irq(&qeth_core_card_list.rwlock);
 	return 0;
 
 err_disc:
@@ -5833,9 +5828,6 @@ static void qeth_core_remove_device(struct ccwgroup_device *gdev)
 		qeth_core_free_discipline(card);
 	}
 
-	write_lock_irq(&qeth_core_card_list.rwlock);
-	list_del(&card->list);
-	write_unlock_irq(&qeth_core_card_list.rwlock);
 	free_netdev(card->dev);
 	qeth_core_free_card(card);
 	put_device(&gdev->dev);
@@ -5950,6 +5942,21 @@ static struct ccwgroup_driver qeth_core_ccwgroup_driver = {
 	.restore = qeth_core_restore,
 };
 
+struct qeth_card *qeth_get_card_by_busid(char *bus_id)
+{
+	struct ccwgroup_device *gdev;
+	struct qeth_card *card;
+
+	gdev = get_ccwgroupdev_by_busid(&qeth_core_ccwgroup_driver, bus_id);
+	if (!gdev)
+		return NULL;
+
+	card = dev_get_drvdata(&gdev->dev);
+	put_device(&gdev->dev);
+	return card;
+}
+EXPORT_SYMBOL_GPL(qeth_get_card_by_busid);
+
 int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct qeth_card *card = dev->ml_priv;
@@ -6688,8 +6695,6 @@ static int __init qeth_core_init(void)
 	int rc;
 
 	pr_info("loading core functions\n");
-	INIT_LIST_HEAD(&qeth_core_card_list.list);
-	rwlock_init(&qeth_core_card_list.rwlock);
 
 	qeth_wq = create_singlethread_workqueue("qeth_wq");
 	if (!qeth_wq) {
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 8d3601891c62..2836231c1c5d 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -36,28 +36,6 @@ static void qeth_l2_vnicc_init(struct qeth_card *card);
 static bool qeth_l2_vnicc_recover_timeout(struct qeth_card *card, u32 vnicc,
 					  u32 *timeout);
 
-static struct net_device *qeth_l2_netdev_by_devno(unsigned char *read_dev_no)
-{
-	struct qeth_card *card;
-	struct net_device *ndev;
-	__u16 temp_dev_no;
-	unsigned long flags;
-	struct ccw_dev_id read_devid;
-
-	ndev = NULL;
-	memcpy(&temp_dev_no, read_dev_no, 2);
-	read_lock_irqsave(&qeth_core_card_list.rwlock, flags);
-	list_for_each_entry(card, &qeth_core_card_list.list, list) {
-		ccw_device_get_id(CARD_RDEV(card), &read_devid);
-		if (read_devid.devno == temp_dev_no) {
-			ndev = card->dev;
-			break;
-		}
-	}
-	read_unlock_irqrestore(&qeth_core_card_list.rwlock, flags);
-	return ndev;
-}
-
 static int qeth_setdelmac_makerc(struct qeth_card *card, int retcode)
 {
 	int rc;
@@ -1286,13 +1264,16 @@ int qeth_osn_register(unsigned char *read_dev_no, struct net_device **dev,
 		  int (*data_cb)(struct sk_buff *))
 {
 	struct qeth_card *card;
+	char bus_id[16];
+	u16 devno;
 
-	*dev = qeth_l2_netdev_by_devno(read_dev_no);
-	if (*dev == NULL)
-		return -ENODEV;
-	card = (*dev)->ml_priv;
-	if (!card)
+	memcpy(&devno, read_dev_no, 2);
+	sprintf(bus_id, "0.0.%04x", devno);
+	card = qeth_get_card_by_busid(bus_id);
+	if (!card || !IS_OSN(card))
 		return -ENODEV;
+	*dev = card->dev;
+
 	QETH_CARD_TEXT(card, 2, "osnreg");
 	if ((assist_cb == NULL) || (data_cb == NULL))
 		return -EINVAL;
-- 
cgit v1.2.3


From 605c9d5f58cc8a58882cf39375c39fcab8066dd4 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 8 Nov 2018 15:06:19 +0100
Subject: s390/qeth: replace open-coded cmd setup

Call qeth_prepare_ipa_cmd() during setup of a new IPA cmd buffer, so
that it is used for all commands. Thus ARP and SNMP requests don't have
to do their own initialization.

This will now also set the proper MPC protocol version for SNMP requests
on L2 devices.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 27 ++++++++++++---------------
 drivers/s390/net/qeth_core_mpc.c  |  1 -
 drivers/s390/net/qeth_l3_main.c   |  3 ---
 3 files changed, 12 insertions(+), 19 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 508bad2dbd0b..c1315ac63041 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2835,6 +2835,17 @@ static void qeth_fill_ipacmd_header(struct qeth_card *card,
 	cmd->hdr.prot_version = prot;
 }
 
+void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob)
+{
+	u8 prot_type = qeth_mpc_select_prot_type(card);
+
+	memcpy(iob->data, IPA_PDU_HEADER, IPA_PDU_HEADER_SIZE);
+	memcpy(QETH_IPA_CMD_PROT_TYPE(iob->data), &prot_type, 1);
+	memcpy(QETH_IPA_CMD_DEST_ADDR(iob->data),
+	       &card->token.ulp_connection_r, QETH_MPC_TOKEN_LENGTH);
+}
+EXPORT_SYMBOL_GPL(qeth_prepare_ipa_cmd);
+
 struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card,
 		enum qeth_ipa_cmds ipacmd, enum qeth_prot_versions prot)
 {
@@ -2842,6 +2853,7 @@ struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card,
 
 	iob = qeth_get_buffer(&card->write);
 	if (iob) {
+		qeth_prepare_ipa_cmd(card, iob);
 		qeth_fill_ipacmd_header(card, __ipa_cmd(iob), ipacmd, prot);
 	} else {
 		dev_warn(&card->gdev->dev,
@@ -2854,17 +2866,6 @@ struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card,
 }
 EXPORT_SYMBOL_GPL(qeth_get_ipacmd_buffer);
 
-void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob)
-{
-	u8 prot_type = qeth_mpc_select_prot_type(card);
-
-	memcpy(iob->data, IPA_PDU_HEADER, IPA_PDU_HEADER_SIZE);
-	memcpy(QETH_IPA_CMD_PROT_TYPE(iob->data), &prot_type, 1);
-	memcpy(QETH_IPA_CMD_DEST_ADDR(iob->data),
-	       &card->token.ulp_connection_r, QETH_MPC_TOKEN_LENGTH);
-}
-EXPORT_SYMBOL_GPL(qeth_prepare_ipa_cmd);
-
 /**
  * qeth_send_ipa_cmd() - send an IPA command
  *
@@ -2879,7 +2880,6 @@ int qeth_send_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob,
 	int rc;
 
 	QETH_CARD_TEXT(card, 4, "sendipa");
-	qeth_prepare_ipa_cmd(card, iob);
 	rc = qeth_send_control_data(card, IPA_CMD_LENGTH,
 						iob, reply_cb, reply_param);
 	if (rc == -ETIME) {
@@ -4497,9 +4497,6 @@ static int qeth_send_ipa_snmp_cmd(struct qeth_card *card,
 
 	QETH_CARD_TEXT(card, 4, "sendsnmp");
 
-	memcpy(iob->data, IPA_PDU_HEADER, IPA_PDU_HEADER_SIZE);
-	memcpy(QETH_IPA_CMD_DEST_ADDR(iob->data),
-	       &card->token.ulp_connection_r, QETH_MPC_TOKEN_LENGTH);
 	/* adjust PDU length fields in IPA_PDU_HEADER */
 	s1 = (u32) IPA_PDU_HEADER_SIZE + len;
 	s2 = (u32) len;
diff --git a/drivers/s390/net/qeth_core_mpc.c b/drivers/s390/net/qeth_core_mpc.c
index e891c0b52f4c..16fc51ad0514 100644
--- a/drivers/s390/net/qeth_core_mpc.c
+++ b/drivers/s390/net/qeth_core_mpc.c
@@ -144,7 +144,6 @@ unsigned char IPA_PDU_HEADER[] = {
 		sizeof(struct qeth_ipa_cmd) % 256,
 	0x00, 0x00, 0x00, 0x40,
 };
-EXPORT_SYMBOL_GPL(IPA_PDU_HEADER);
 
 struct ipa_rc_msg {
 	enum qeth_ipa_return_codes rc;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 61d847d41cab..ce5ef6aca891 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1693,9 +1693,6 @@ static int qeth_l3_send_ipa_arp_cmd(struct qeth_card *card,
 {
 	QETH_CARD_TEXT(card, 4, "sendarp");
 
-	memcpy(iob->data, IPA_PDU_HEADER, IPA_PDU_HEADER_SIZE);
-	memcpy(QETH_IPA_CMD_DEST_ADDR(iob->data),
-	       &card->token.ulp_connection_r, QETH_MPC_TOKEN_LENGTH);
 	return qeth_send_control_data(card, IPA_PDU_HEADER_SIZE + len, iob,
 				      reply_cb, reply_param);
 }
-- 
cgit v1.2.3


From 4fa55fa94f55f5bc31472e8b96b9846bc191eaf8 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 8 Nov 2018 15:06:20 +0100
Subject: s390/qeth: remove two IPA command helpers

qeth_l3_send_ipa_arp_cmd() is merely a wrapper around
qeth_send_control_data() now. So push the length adjustment into
QETH_SETASS_BASE_LEN, and remove the wrapper. While at it, also remove
some redundant 0-initializations.

qeth_send_setassparms() requires that callers prepare their command
parameters, so that they can be copied into the parameter area in one
go. Skip the indirection, and just let callers set up the command
themselves.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 51 ++++++++++-----------------------------
 drivers/s390/net/qeth_core_mpc.h  |  7 +++---
 drivers/s390/net/qeth_l3_main.c   | 20 +++------------
 3 files changed, 19 insertions(+), 59 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index c1315ac63041..ae972461860e 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5475,34 +5475,11 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card,
 }
 EXPORT_SYMBOL_GPL(qeth_get_setassparms_cmd);
 
-static int qeth_send_setassparms(struct qeth_card *card,
-				 struct qeth_cmd_buffer *iob, u16 len,
-				 long data, int (*reply_cb)(struct qeth_card *,
-							    struct qeth_reply *,
-							    unsigned long),
-				 void *reply_param)
-{
-	int rc;
-	struct qeth_ipa_cmd *cmd;
-
-	QETH_CARD_TEXT(card, 4, "sendassp");
-
-	cmd = __ipa_cmd(iob);
-	if (len <= sizeof(__u32))
-		cmd->data.setassparms.data.flags_32bit = (__u32) data;
-	else   /* (len > sizeof(__u32)) */
-		memcpy(&cmd->data.setassparms.data, (void *) data, len);
-
-	rc = qeth_send_ipa_cmd(card, iob, reply_cb, reply_param);
-	return rc;
-}
-
 int qeth_send_simple_setassparms_prot(struct qeth_card *card,
 				      enum qeth_ipa_funcs ipa_func,
 				      u16 cmd_code, long data,
 				      enum qeth_prot_versions prot)
 {
-	int rc;
 	int length = 0;
 	struct qeth_cmd_buffer *iob;
 
@@ -5512,9 +5489,9 @@ int qeth_send_simple_setassparms_prot(struct qeth_card *card,
 	iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code, length, prot);
 	if (!iob)
 		return -ENOMEM;
-	rc = qeth_send_setassparms(card, iob, length, data,
-				   qeth_setassparms_cb, NULL);
-	return rc;
+
+	__ipa_cmd(iob)->data.setassparms.data.flags_32bit = (__u32) data;
+	return qeth_send_ipa_cmd(card, iob, qeth_setassparms_cb, NULL);
 }
 EXPORT_SYMBOL_GPL(qeth_send_simple_setassparms_prot);
 
@@ -6385,16 +6362,16 @@ static int qeth_ipa_checksum_run_cmd(struct qeth_card *card,
 				     enum qeth_prot_versions prot)
 {
 	struct qeth_cmd_buffer *iob;
-	int rc = -ENOMEM;
 
 	QETH_CARD_TEXT(card, 4, "chkdocmd");
 	iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code,
 				       sizeof(__u32), prot);
-	if (iob)
-		rc = qeth_send_setassparms(card, iob, sizeof(__u32), data,
-					   qeth_ipa_checksum_run_cmd_cb,
-					   chksum_cb);
-	return rc;
+	if (!iob)
+		return -ENOMEM;
+
+	__ipa_cmd(iob)->data.setassparms.data.flags_32bit = (__u32) data;
+	return qeth_send_ipa_cmd(card, iob, qeth_ipa_checksum_run_cmd_cb,
+				 chksum_cb);
 }
 
 static int qeth_send_checksum_on(struct qeth_card *card, int cstype,
@@ -6492,8 +6469,7 @@ static int qeth_set_tso_on(struct qeth_card *card,
 	if (!iob)
 		return -ENOMEM;
 
-	rc = qeth_send_setassparms(card, iob, 0, 0 /* unused */,
-				   qeth_start_tso_cb, &tso_data);
+	rc = qeth_send_ipa_cmd(card, iob, qeth_start_tso_cb, &tso_data);
 	if (rc)
 		return rc;
 
@@ -6510,10 +6486,9 @@ static int qeth_set_tso_on(struct qeth_card *card,
 	}
 
 	/* enable TSO capability */
-	caps.supported = 0;
-	caps.enabled = QETH_IPA_LARGE_SEND_TCP;
-	rc = qeth_send_setassparms(card, iob, sizeof(caps), (long) &caps,
-				   qeth_setassparms_get_caps_cb, &caps);
+	__ipa_cmd(iob)->data.setassparms.data.caps.enabled =
+		QETH_IPA_LARGE_SEND_TCP;
+	rc = qeth_send_ipa_cmd(card, iob, qeth_setassparms_get_caps_cb, &caps);
 	if (rc) {
 		qeth_set_tso_off(card, prot);
 		return rc;
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index 10cc487c16d6..1ab321926f64 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -833,10 +833,9 @@ enum qeth_ipa_arp_return_codes {
 extern const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc);
 extern const char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd);
 
-#define QETH_SETASS_BASE_LEN (sizeof(struct qeth_ipacmd_hdr) + \
-			       sizeof(struct qeth_ipacmd_setassparms_hdr))
-#define QETH_IPA_ARP_DATA_POS(buffer) (buffer + IPA_PDU_HEADER_SIZE + \
-				       QETH_SETASS_BASE_LEN)
+#define QETH_SETASS_BASE_LEN (IPA_PDU_HEADER_SIZE + \
+			      sizeof(struct qeth_ipacmd_hdr) + \
+			      sizeof(struct qeth_ipacmd_setassparms_hdr))
 #define QETH_SETADP_BASE_LEN (sizeof(struct qeth_ipacmd_hdr) + \
 			      sizeof(struct qeth_ipacmd_setadpparms_hdr))
 #define QETH_SNMP_SETADP_CMDLENGTH 16
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index ce5ef6aca891..89d5e6fb21ac 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1685,18 +1685,6 @@ out_error:
 	return 0;
 }
 
-static int qeth_l3_send_ipa_arp_cmd(struct qeth_card *card,
-		struct qeth_cmd_buffer *iob, int len,
-		int (*reply_cb)(struct qeth_card *, struct qeth_reply *,
-			unsigned long),
-		void *reply_param)
-{
-	QETH_CARD_TEXT(card, 4, "sendarp");
-
-	return qeth_send_control_data(card, IPA_PDU_HEADER_SIZE + len, iob,
-				      reply_cb, reply_param);
-}
-
 static int qeth_l3_query_arp_cache_info(struct qeth_card *card,
 	enum qeth_prot_versions prot,
 	struct qeth_arp_query_info *qinfo)
@@ -1716,11 +1704,9 @@ static int qeth_l3_query_arp_cache_info(struct qeth_card *card,
 		return -ENOMEM;
 	cmd = __ipa_cmd(iob);
 	cmd->data.setassparms.data.query_arp.request_bits = 0x000F;
-	cmd->data.setassparms.data.query_arp.reply_bits = 0;
-	cmd->data.setassparms.data.query_arp.no_entries = 0;
-	rc = qeth_l3_send_ipa_arp_cmd(card, iob,
-			   QETH_SETASS_BASE_LEN+QETH_ARP_CMD_LEN,
-			   qeth_l3_arp_query_cb, (void *)qinfo);
+	rc = qeth_send_control_data(card,
+				    QETH_SETASS_BASE_LEN + QETH_ARP_CMD_LEN,
+				    iob, qeth_l3_arp_query_cb, qinfo);
 	if (rc)
 		QETH_DBF_MESSAGE(2, "Error while querying ARP cache on device %x: %#x\n",
 				 CARD_DEVID(card), rc);
-- 
cgit v1.2.3


From 9168f5ae3837dd98cb201d16f813c6f1d96670ca Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 8 Nov 2018 15:06:21 +0100
Subject: s390/qeth: remove unused fallback in Layer3's MAC code

If the CREATE ADDR sent by qeth_l3_iqd_read_initial_mac() fails, its
callback sets a random MAC address on the net_device. The error then
propagates back, and qeth_l3_setup_netdev() bails out without
registering the net_device.

Any subsequent call to qeth_l3_setup_netdev() will then attempt a fresh
CREATE ADDR which either 1) also fails, or 2) sets a proper MAC address
on the net_device. Consequently, the net_device will never be registered
with a random MAC and we can drop the fallback code.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 89d5e6fb21ac..674ff3344ff3 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -949,9 +949,6 @@ static int qeth_l3_iqd_read_initial_mac_cb(struct qeth_card *card,
 	if (cmd->hdr.return_code == 0)
 		ether_addr_copy(card->dev->dev_addr,
 				cmd->data.create_destroy_addr.unique_id);
-	else
-		eth_random_addr(card->dev->dev_addr);
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From ded9da1fc2d9509c1fd18ecdaae5f6185fb81dbc Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 8 Nov 2018 15:06:22 +0100
Subject: s390/qeth: don't process hsuid in qeth_l3_setup_netdev()

qeth_l3_setup_netdev() checks if the hsuid attribute is set on the qeth
device, and propagates it to the net_device. In the past this was needed
to pick up any hsuid that was set before allocation of the net_device.

With commit d3d1b205e89f ("s390/qeth: allocate netdevice early") this
is no longer necessary, qeth_l3_dev_hsuid_store() always stores the
hsuid straight into dev->perm_addr.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 674ff3344ff3..eca68da39d05 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2279,9 +2279,6 @@ static int qeth_l3_setup_netdev(struct qeth_card *card, bool carrier_ok)
 		rc = qeth_l3_iqd_read_initial_mac(card);
 		if (rc)
 			goto out;
-
-		if (card->options.hsuid[0])
-			memcpy(card->dev->perm_addr, card->options.hsuid, 9);
 	} else
 		return -ENODEV;
 
-- 
cgit v1.2.3


From 50254256f382c56bde87d970f3d0d02fdb76ec70 Mon Sep 17 00:00:00 2001
From: David Barmann <david.barmann@stackpath.com>
Date: Thu, 8 Nov 2018 08:13:35 -0600
Subject: sock: Reset dst when changing sk_mark via setsockopt

When setting the SO_MARK socket option, if the mark changes, the dst
needs to be reset so that a new route lookup is performed.

This fixes the case where an application wants to change routing by
setting a new sk_mark.  If this is done after some packets have already
been sent, the dst is cached and has no effect.

Signed-off-by: David Barmann <david.barmann@stackpath.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 7b304e454a38..6d7e189e3cd9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -952,10 +952,12 @@ set_rcvbuf:
 			clear_bit(SOCK_PASSSEC, &sock->flags);
 		break;
 	case SO_MARK:
-		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
-		else
+		} else if (val != sk->sk_mark) {
 			sk->sk_mark = val;
+			sk_dst_reset(sk);
+		}
 		break;
 
 	case SO_RXQ_OVFL:
-- 
cgit v1.2.3


From 026b907d58c48b2ff2a4c04a67bb5f71ebda1f2d Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Thu, 8 Nov 2018 14:38:21 +0100
Subject: net: qca_spi: Add available buffer space verification

Interferences on the SPI line could distort the response of
available buffer space. So at least we should check that the
response doesn't exceed the maximum available buffer space.
In error case increase a new error counter and retry it later.
This behavior avoids buffer errors in the QCA7000, which
results in an unnecessary chip reset including packet loss.

Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_debug.c |  1 +
 drivers/net/ethernet/qualcomm/qca_spi.c   | 16 +++++++++++++++-
 drivers/net/ethernet/qualcomm/qca_spi.h   |  1 +
 3 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c
index a9f1bc013364..1450f386bc65 100644
--- a/drivers/net/ethernet/qualcomm/qca_debug.c
+++ b/drivers/net/ethernet/qualcomm/qca_debug.c
@@ -61,6 +61,7 @@ static const char qcaspi_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"Transmit ring full",
 	"SPI errors",
 	"Write verify errors",
+	"Buffer available errors",
 };
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index d5310504f436..97f92953bdb9 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -289,6 +289,14 @@ qcaspi_transmit(struct qcaspi *qca)
 
 	qcaspi_read_register(qca, SPI_REG_WRBUF_SPC_AVA, &available);
 
+	if (available > QCASPI_HW_BUF_LEN) {
+		/* This could only happen by interferences on the SPI line.
+		 * So retry later ...
+		 */
+		qca->stats.buf_avail_err++;
+		return -1;
+	}
+
 	while (qca->txr.skb[qca->txr.head]) {
 		pkt_len = qca->txr.skb[qca->txr.head]->len + QCASPI_HW_PKT_LEN;
 
@@ -355,7 +363,13 @@ qcaspi_receive(struct qcaspi *qca)
 	netdev_dbg(net_dev, "qcaspi_receive: SPI_REG_RDBUF_BYTE_AVA: Value: %08x\n",
 		   available);
 
-	if (available == 0) {
+	if (available > QCASPI_HW_BUF_LEN) {
+		/* This could only happen by interferences on the SPI line.
+		 * So retry later ...
+		 */
+		qca->stats.buf_avail_err++;
+		return -1;
+	} else if (available == 0) {
 		netdev_dbg(net_dev, "qcaspi_receive called without any data being available!\n");
 		return -1;
 	}
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h
index 2d2c49726492..eb9af45fcc5e 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.h
+++ b/drivers/net/ethernet/qualcomm/qca_spi.h
@@ -74,6 +74,7 @@ struct qcaspi_stats {
 	u64 ring_full;
 	u64 spi_err;
 	u64 write_verify_failed;
+	u64 buf_avail_err;
 };
 
 struct qcaspi {
-- 
cgit v1.2.3


From 4acb20b46214bc866945340b4d9e1de77700d6a3 Mon Sep 17 00:00:00 2001
From: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Date: Thu, 8 Nov 2018 17:19:54 +0200
Subject: net: socionext: different approach on DMA

Current driver dynamically allocates an skb and maps it as DMA Rx
buffer. In order to prepare for upcoming XDP changes, let's introduce a
different allocation scheme.
Buffers are allocated dynamically and mapped into hardware.
During the Rx operation the driver uses build_skb() to produce the
necessary buffers for the network stack.
This change increases performance ~15% on 64b packets with smmu disabled
and ~5% with smmu enabled

Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 227 ++++++++++++++++++--------------
 1 file changed, 128 insertions(+), 99 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index d9d0d03e4ce7..9d24f299798a 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -234,6 +234,9 @@
 
 #define DESC_NUM	256
 
+#define NETSEC_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
+#define NETSEC_RX_BUF_SZ 1536
+
 #define DESC_SZ	sizeof(struct netsec_de)
 
 #define NETSEC_F_NETSEC_VER_MAJOR_NUM(x)	((x) & 0xffff0000)
@@ -571,34 +574,10 @@ static const struct ethtool_ops netsec_ethtool_ops = {
 
 /************* NETDEV_OPS FOLLOW *************/
 
-static struct sk_buff *netsec_alloc_skb(struct netsec_priv *priv,
-					struct netsec_desc *desc)
-{
-	struct sk_buff *skb;
-
-	if (device_get_dma_attr(priv->dev) == DEV_DMA_COHERENT) {
-		skb = netdev_alloc_skb_ip_align(priv->ndev, desc->len);
-	} else {
-		desc->len = L1_CACHE_ALIGN(desc->len);
-		skb = netdev_alloc_skb(priv->ndev, desc->len);
-	}
-	if (!skb)
-		return NULL;
-
-	desc->addr = skb->data;
-	desc->dma_addr = dma_map_single(priv->dev, desc->addr, desc->len,
-					DMA_FROM_DEVICE);
-	if (dma_mapping_error(priv->dev, desc->dma_addr)) {
-		dev_kfree_skb_any(skb);
-		return NULL;
-	}
-	return skb;
-}
 
 static void netsec_set_rx_de(struct netsec_priv *priv,
 			     struct netsec_desc_ring *dring, u16 idx,
-			     const struct netsec_desc *desc,
-			     struct sk_buff *skb)
+			     const struct netsec_desc *desc)
 {
 	struct netsec_de *de = dring->vaddr + DESC_SZ * idx;
 	u32 attr = (1 << NETSEC_RX_PKT_OWN_FIELD) |
@@ -617,59 +596,6 @@ static void netsec_set_rx_de(struct netsec_priv *priv,
 	dring->desc[idx].dma_addr = desc->dma_addr;
 	dring->desc[idx].addr = desc->addr;
 	dring->desc[idx].len = desc->len;
-	dring->desc[idx].skb = skb;
-}
-
-static struct sk_buff *netsec_get_rx_de(struct netsec_priv *priv,
-					struct netsec_desc_ring *dring,
-					u16 idx,
-					struct netsec_rx_pkt_info *rxpi,
-					struct netsec_desc *desc, u16 *len)
-{
-	struct netsec_de de = {};
-
-	memcpy(&de, dring->vaddr + DESC_SZ * idx, DESC_SZ);
-
-	*len = de.buf_len_info >> 16;
-
-	rxpi->err_flag = (de.attr >> NETSEC_RX_PKT_ER_FIELD) & 1;
-	rxpi->rx_cksum_result = (de.attr >> NETSEC_RX_PKT_CO_FIELD) & 3;
-	rxpi->err_code = (de.attr >> NETSEC_RX_PKT_ERR_FIELD) &
-							NETSEC_RX_PKT_ERR_MASK;
-	*desc = dring->desc[idx];
-	return desc->skb;
-}
-
-static struct sk_buff *netsec_get_rx_pkt_data(struct netsec_priv *priv,
-					      struct netsec_rx_pkt_info *rxpi,
-					      struct netsec_desc *desc,
-					      u16 *len)
-{
-	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
-	struct sk_buff *tmp_skb, *skb = NULL;
-	struct netsec_desc td;
-	int tail;
-
-	*rxpi = (struct netsec_rx_pkt_info){};
-
-	td.len = priv->ndev->mtu + 22;
-
-	tmp_skb = netsec_alloc_skb(priv, &td);
-
-	tail = dring->tail;
-
-	if (!tmp_skb) {
-		netsec_set_rx_de(priv, dring, tail, &dring->desc[tail],
-				 dring->desc[tail].skb);
-	} else {
-		skb = netsec_get_rx_de(priv, dring, tail, rxpi, desc, len);
-		netsec_set_rx_de(priv, dring, tail, &td, tmp_skb);
-	}
-
-	/* move tail ahead */
-	dring->tail = (dring->tail + 1) % DESC_NUM;
-
-	return skb;
 }
 
 static int netsec_clean_tx_dring(struct netsec_priv *priv, int budget)
@@ -736,19 +662,65 @@ static int netsec_process_tx(struct netsec_priv *priv, int budget)
 	return done;
 }
 
+static void *netsec_alloc_rx_data(struct netsec_priv *priv,
+				  dma_addr_t *dma_handle, u16 *desc_len)
+{
+	size_t total_len = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	size_t payload_len = NETSEC_RX_BUF_SZ;
+	dma_addr_t mapping;
+	void *buf;
+
+	total_len += SKB_DATA_ALIGN(payload_len + NETSEC_SKB_PAD);
+
+	buf = napi_alloc_frag(total_len);
+	if (!buf)
+		return NULL;
+
+	mapping = dma_map_single(priv->dev, buf + NETSEC_SKB_PAD, payload_len,
+				 DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(priv->dev, mapping)))
+		goto err_out;
+
+	*dma_handle = mapping;
+	*desc_len = payload_len;
+
+	return buf;
+
+err_out:
+	skb_free_frag(buf);
+	return NULL;
+}
+
+static void netsec_rx_fill(struct netsec_priv *priv, u16 from, u16 num)
+{
+	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
+	u16 idx = from;
+
+	while (num) {
+		netsec_set_rx_de(priv, dring, idx, &dring->desc[idx]);
+		idx++;
+		if (idx >= DESC_NUM)
+			idx = 0;
+		num--;
+	}
+}
+
 static int netsec_process_rx(struct netsec_priv *priv, int budget)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
 	struct net_device *ndev = priv->ndev;
 	struct netsec_rx_pkt_info rx_info;
-	int done = 0;
-	struct netsec_desc desc;
 	struct sk_buff *skb;
-	u16 len;
+	int done = 0;
 
 	while (done < budget) {
 		u16 idx = dring->tail;
 		struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
+		struct netsec_desc *desc = &dring->desc[idx];
+		u16 pkt_len, desc_len;
+		dma_addr_t dma_handle;
+		void *buf_addr;
+		u32 truesize;
 
 		if (de->attr & (1U << NETSEC_RX_PKT_OWN_FIELD)) {
 			/* reading the register clears the irq */
@@ -762,18 +734,59 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		 */
 		dma_rmb();
 		done++;
-		skb = netsec_get_rx_pkt_data(priv, &rx_info, &desc, &len);
-		if (unlikely(!skb) || rx_info.err_flag) {
+
+		pkt_len = de->buf_len_info >> 16;
+		rx_info.err_code = (de->attr >> NETSEC_RX_PKT_ERR_FIELD) &
+			NETSEC_RX_PKT_ERR_MASK;
+		rx_info.err_flag = (de->attr >> NETSEC_RX_PKT_ER_FIELD) & 1;
+		if (rx_info.err_flag) {
 			netif_err(priv, drv, priv->ndev,
-				  "%s: rx fail err(%d)\n",
-				  __func__, rx_info.err_code);
+				  "%s: rx fail err(%d)\n", __func__,
+				  rx_info.err_code);
 			ndev->stats.rx_dropped++;
+			dring->tail = (dring->tail + 1) % DESC_NUM;
+			/* reuse buffer page frag */
+			netsec_rx_fill(priv, idx, 1);
 			continue;
 		}
+		rx_info.rx_cksum_result =
+			(de->attr >> NETSEC_RX_PKT_CO_FIELD) & 3;
 
-		dma_unmap_single(priv->dev, desc.dma_addr, desc.len,
-				 DMA_FROM_DEVICE);
-		skb_put(skb, len);
+		/* allocate a fresh buffer and map it to the hardware.
+		 * This will eventually replace the old buffer in the hardware
+		 */
+		buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len);
+		if (unlikely(!buf_addr))
+			break;
+
+		dma_sync_single_for_cpu(priv->dev, desc->dma_addr, pkt_len,
+					DMA_FROM_DEVICE);
+		prefetch(desc->addr);
+
+		truesize = SKB_DATA_ALIGN(desc->len + NETSEC_SKB_PAD) +
+			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+		skb = build_skb(desc->addr, truesize);
+		if (unlikely(!skb)) {
+			/* free the newly allocated buffer, we are not going to
+			 * use it
+			 */
+			dma_unmap_single(priv->dev, dma_handle, desc_len,
+					 DMA_FROM_DEVICE);
+			skb_free_frag(buf_addr);
+			netif_err(priv, drv, priv->ndev,
+				  "rx failed to build skb\n");
+			break;
+		}
+		dma_unmap_single_attrs(priv->dev, desc->dma_addr, desc->len,
+				       DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+
+		/* Update the descriptor with the new buffer we allocated */
+		desc->len = desc_len;
+		desc->dma_addr = dma_handle;
+		desc->addr = buf_addr;
+
+		skb_reserve(skb, NETSEC_SKB_PAD);
+		skb_put(skb, pkt_len);
 		skb->protocol = eth_type_trans(skb, priv->ndev);
 
 		if (priv->rx_cksum_offload_flag &&
@@ -782,8 +795,11 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 
 		if (napi_gro_receive(&priv->napi, skb) != GRO_DROP) {
 			ndev->stats.rx_packets++;
-			ndev->stats.rx_bytes += len;
+			ndev->stats.rx_bytes += pkt_len;
 		}
+
+		netsec_rx_fill(priv, idx, 1);
+		dring->tail = (dring->tail + 1) % DESC_NUM;
 	}
 
 	return done;
@@ -946,7 +962,10 @@ static void netsec_uninit_pkt_dring(struct netsec_priv *priv, int id)
 		dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
 				 id == NETSEC_RING_RX ? DMA_FROM_DEVICE :
 							      DMA_TO_DEVICE);
-		dev_kfree_skb(desc->skb);
+		if (id == NETSEC_RING_RX)
+			skb_free_frag(desc->addr);
+		else if (id == NETSEC_RING_TX)
+			dev_kfree_skb(desc->skb);
 	}
 
 	memset(dring->desc, 0, sizeof(struct netsec_desc) * DESC_NUM);
@@ -1002,22 +1021,30 @@ err:
 static int netsec_setup_rx_dring(struct netsec_priv *priv)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
-	struct netsec_desc desc;
-	struct sk_buff *skb;
-	int n;
+	int i;
 
-	desc.len = priv->ndev->mtu + 22;
+	for (i = 0; i < DESC_NUM; i++) {
+		struct netsec_desc *desc = &dring->desc[i];
+		dma_addr_t dma_handle;
+		void *buf;
+		u16 len;
 
-	for (n = 0; n < DESC_NUM; n++) {
-		skb = netsec_alloc_skb(priv, &desc);
-		if (!skb) {
+		buf = netsec_alloc_rx_data(priv, &dma_handle, &len);
+		if (!buf) {
 			netsec_uninit_pkt_dring(priv, NETSEC_RING_RX);
-			return -ENOMEM;
+			goto err_out;
 		}
-		netsec_set_rx_de(priv, dring, n, &desc, skb);
+		desc->dma_addr = dma_handle;
+		desc->addr = buf;
+		desc->len = len;
 	}
 
+	netsec_rx_fill(priv, 0, DESC_NUM);
+
 	return 0;
+
+err_out:
+	return -ENOMEM;
 }
 
 static int netsec_netdev_load_ucode_region(struct netsec_priv *priv, u32 reg,
@@ -1377,6 +1404,8 @@ static int netsec_netdev_init(struct net_device *ndev)
 	int ret;
 	u16 data;
 
+	BUILD_BUG_ON_NOT_POWER_OF_2(DESC_NUM);
+
 	ret = netsec_alloc_dring(priv, NETSEC_RING_TX);
 	if (ret)
 		return ret;
-- 
cgit v1.2.3


From 0d404a61286f2ffcde2157e8c5427f93f409d8ab Mon Sep 17 00:00:00 2001
From: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Date: Thu, 8 Nov 2018 17:19:55 +0200
Subject: net: socionext: refactor netsec_alloc_dring()

return -ENOMEM directly instead of assigning it in a variable

Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 9d24f299798a..bba9733b5119 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -996,26 +996,21 @@ static void netsec_free_dring(struct netsec_priv *priv, int id)
 static int netsec_alloc_dring(struct netsec_priv *priv, enum ring_id id)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[id];
-	int ret = 0;
 
 	dring->vaddr = dma_zalloc_coherent(priv->dev, DESC_SZ * DESC_NUM,
 					   &dring->desc_dma, GFP_KERNEL);
-	if (!dring->vaddr) {
-		ret = -ENOMEM;
+	if (!dring->vaddr)
 		goto err;
-	}
 
 	dring->desc = kcalloc(DESC_NUM, sizeof(*dring->desc), GFP_KERNEL);
-	if (!dring->desc) {
-		ret = -ENOMEM;
+	if (!dring->desc)
 		goto err;
-	}
 
 	return 0;
 err:
 	netsec_free_dring(priv, id);
 
-	return ret;
+	return -ENOMEM;
 }
 
 static int netsec_setup_rx_dring(struct netsec_priv *priv)
-- 
cgit v1.2.3


From 1ef212afa40ede497a141ee3a8bd050cacfd9e55 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Thu, 8 Nov 2018 18:44:49 +0100
Subject: i40iw: remove use of VLAN_TAG_PRESENT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/i40iw/i40iw_cm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index 771eb6bd0785..4b3999d88c9e 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -404,7 +404,7 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node,
 	if (pdata)
 		pd_len = pdata->size;
 
-	if (cm_node->vlan_id < VLAN_TAG_PRESENT)
+	if (cm_node->vlan_id <= VLAN_VID_MASK)
 		eth_hlen += 4;
 
 	if (cm_node->ipv4)
@@ -433,7 +433,7 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node,
 
 		ether_addr_copy(ethh->h_dest, cm_node->rem_mac);
 		ether_addr_copy(ethh->h_source, cm_node->loc_mac);
-		if (cm_node->vlan_id < VLAN_TAG_PRESENT) {
+		if (cm_node->vlan_id <= VLAN_VID_MASK) {
 			((struct vlan_ethhdr *)ethh)->h_vlan_proto = htons(ETH_P_8021Q);
 			vtag = (cm_node->user_pri << VLAN_PRIO_SHIFT) | cm_node->vlan_id;
 			((struct vlan_ethhdr *)ethh)->h_vlan_TCI = htons(vtag);
@@ -463,7 +463,7 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node,
 
 		ether_addr_copy(ethh->h_dest, cm_node->rem_mac);
 		ether_addr_copy(ethh->h_source, cm_node->loc_mac);
-		if (cm_node->vlan_id < VLAN_TAG_PRESENT) {
+		if (cm_node->vlan_id <= VLAN_VID_MASK) {
 			((struct vlan_ethhdr *)ethh)->h_vlan_proto = htons(ETH_P_8021Q);
 			vtag = (cm_node->user_pri << VLAN_PRIO_SHIFT) | cm_node->vlan_id;
 			((struct vlan_ethhdr *)ethh)->h_vlan_TCI = htons(vtag);
@@ -3323,7 +3323,7 @@ static void i40iw_init_tcp_ctx(struct i40iw_cm_node *cm_node,
 
 	tcp_info->flow_label = 0;
 	tcp_info->snd_mss = cpu_to_le32(((u32)cm_node->tcp_cntxt.mss));
-	if (cm_node->vlan_id < VLAN_TAG_PRESENT) {
+	if (cm_node->vlan_id <= VLAN_VID_MASK) {
 		tcp_info->insert_vlan_tag = true;
 		tcp_info->vlan_tag = cpu_to_le16(((u16)cm_node->user_pri << I40IW_VLAN_PRIO_SHIFT) |
 						  cm_node->vlan_id);
-- 
cgit v1.2.3


From f723a1a293deefa7f25b3833266fa7eb18d877f7 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Thu, 8 Nov 2018 18:44:50 +0100
Subject: cnic: remove use of VLAN_TAG_PRESENT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This just removes VLAN_TAG_PRESENT use.  VLAN TCI=0 special meaning is
deeply embedded in the driver code and so is left as is.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/cnic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index d83233ae4a15..510dfc1c236b 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -5731,7 +5731,7 @@ static int cnic_netdev_event(struct notifier_block *this, unsigned long event,
 		if (realdev) {
 			dev = cnic_from_netdev(realdev);
 			if (dev) {
-				vid |= VLAN_TAG_PRESENT;
+				vid |= VLAN_CFI_MASK;	/* make non-zero */
 				cnic_rcv_netevent(dev->cnic_priv, event, vid);
 				cnic_put(dev);
 			}
-- 
cgit v1.2.3


From 9df46aefafa6dee81a27c2a9d8ba360abd8c5fe3 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Thu, 8 Nov 2018 18:44:50 +0100
Subject: OVS: remove use of VLAN_TAG_PRESENT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is a minimal change to allow removing of VLAN_TAG_PRESENT.
It leaves OVS unable to use CFI bit, as fixing this would need
a deeper surgery involving userspace interface.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c      | 13 +++++++++----
 net/openvswitch/flow.c         |  4 ++--
 net/openvswitch/flow.h         |  2 +-
 net/openvswitch/flow_netlink.c | 22 +++++++++++-----------
 4 files changed, 23 insertions(+), 18 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 85ae53d8fd09..e47ebbbe71b8 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -301,7 +301,7 @@ static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
 		key->eth.vlan.tpid = vlan->vlan_tpid;
 	}
 	return skb_vlan_push(skb, vlan->vlan_tpid,
-			     ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
+			     ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK);
 }
 
 /* 'src' is already properly masked. */
@@ -822,8 +822,10 @@ static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *sk
 	__skb_dst_copy(skb, data->dst);
 	*OVS_CB(skb) = data->cb;
 	skb->inner_protocol = data->inner_protocol;
-	skb->vlan_tci = data->vlan_tci;
-	skb->vlan_proto = data->vlan_proto;
+	if (data->vlan_tci & VLAN_CFI_MASK)
+		__vlan_hwaccel_put_tag(skb, data->vlan_proto, data->vlan_tci & ~VLAN_CFI_MASK);
+	else
+		__vlan_hwaccel_clear_tag(skb);
 
 	/* Reconstruct the MAC header.  */
 	skb_push(skb, data->l2_len);
@@ -867,7 +869,10 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb,
 	data->cb = *OVS_CB(skb);
 	data->inner_protocol = skb->inner_protocol;
 	data->network_offset = orig_network_offset;
-	data->vlan_tci = skb->vlan_tci;
+	if (skb_vlan_tag_present(skb))
+		data->vlan_tci = skb_vlan_tag_get(skb) | VLAN_CFI_MASK;
+	else
+		data->vlan_tci = 0;
 	data->vlan_proto = skb->vlan_proto;
 	data->mac_proto = mac_proto;
 	data->l2_len = hlen;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 35966da84769..fa393815991e 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -325,7 +325,7 @@ static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh,
 		return -ENOMEM;
 
 	vh = (struct vlan_head *)skb->data;
-	key_vh->tci = vh->tci | htons(VLAN_TAG_PRESENT);
+	key_vh->tci = vh->tci | htons(VLAN_CFI_MASK);
 	key_vh->tpid = vh->tpid;
 
 	if (unlikely(untag_vlan)) {
@@ -358,7 +358,7 @@ static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 	int res;
 
 	if (skb_vlan_tag_present(skb)) {
-		key->eth.vlan.tci = htons(skb->vlan_tci);
+		key->eth.vlan.tci = htons(skb->vlan_tci) | htons(VLAN_CFI_MASK);
 		key->eth.vlan.tpid = skb->vlan_proto;
 	} else {
 		/* Parse outer vlan tag in the non-accelerated case. */
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index c670dd24b8b7..ba01fc4270bd 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -60,7 +60,7 @@ struct ovs_tunnel_info {
 
 struct vlan_head {
 	__be16 tpid; /* Vlan type. Generally 802.1q or 802.1ad.*/
-	__be16 tci;  /* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */
+	__be16 tci;  /* 0 if no VLAN, VLAN_CFI_MASK set otherwise. */
 };
 
 #define OVS_SW_FLOW_KEY_METADATA_SIZE			\
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 865ecef68196..435a4bdf8f89 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -990,9 +990,9 @@ static int validate_vlan_from_nlattrs(const struct sw_flow_match *match,
 	if (a[OVS_KEY_ATTR_VLAN])
 		tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
 
-	if (!(tci & htons(VLAN_TAG_PRESENT))) {
+	if (!(tci & htons(VLAN_CFI_MASK))) {
 		if (tci) {
-			OVS_NLERR(log, "%s TCI does not have VLAN_TAG_PRESENT bit set.",
+			OVS_NLERR(log, "%s TCI does not have VLAN_CFI_MASK bit set.",
 				  (inner) ? "C-VLAN" : "VLAN");
 			return -EINVAL;
 		} else if (nla_len(a[OVS_KEY_ATTR_ENCAP])) {
@@ -1013,9 +1013,9 @@ static int validate_vlan_mask_from_nlattrs(const struct sw_flow_match *match,
 	__be16 tci = 0;
 	__be16 tpid = 0;
 	bool encap_valid = !!(match->key->eth.vlan.tci &
-			      htons(VLAN_TAG_PRESENT));
+			      htons(VLAN_CFI_MASK));
 	bool i_encap_valid = !!(match->key->eth.cvlan.tci &
-				htons(VLAN_TAG_PRESENT));
+				htons(VLAN_CFI_MASK));
 
 	if (!(key_attrs & (1 << OVS_KEY_ATTR_ENCAP))) {
 		/* Not a VLAN. */
@@ -1039,8 +1039,8 @@ static int validate_vlan_mask_from_nlattrs(const struct sw_flow_match *match,
 			  (inner) ? "C-VLAN" : "VLAN", ntohs(tpid));
 		return -EINVAL;
 	}
-	if (!(tci & htons(VLAN_TAG_PRESENT))) {
-		OVS_NLERR(log, "%s TCI mask does not have exact match for VLAN_TAG_PRESENT bit.",
+	if (!(tci & htons(VLAN_CFI_MASK))) {
+		OVS_NLERR(log, "%s TCI mask does not have exact match for VLAN_CFI_MASK bit.",
 			  (inner) ? "C-VLAN" : "VLAN");
 		return -EINVAL;
 	}
@@ -1095,7 +1095,7 @@ static int parse_vlan_from_nlattrs(struct sw_flow_match *match,
 	if (err)
 		return err;
 
-	encap_valid = !!(match->key->eth.vlan.tci & htons(VLAN_TAG_PRESENT));
+	encap_valid = !!(match->key->eth.vlan.tci & htons(VLAN_CFI_MASK));
 	if (encap_valid) {
 		err = __parse_vlan_from_nlattrs(match, key_attrs, true, a,
 						is_mask, log);
@@ -2943,7 +2943,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			vlan = nla_data(a);
 			if (!eth_type_vlan(vlan->vlan_tpid))
 				return -EINVAL;
-			if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
+			if (!(vlan->vlan_tci & htons(VLAN_CFI_MASK)))
 				return -EINVAL;
 			vlan_tci = vlan->vlan_tci;
 			break;
@@ -2959,7 +2959,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			/* Prohibit push MPLS other than to a white list
 			 * for packets that have a known tag order.
 			 */
-			if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
+			if (vlan_tci & htons(VLAN_CFI_MASK) ||
 			    (eth_type != htons(ETH_P_IP) &&
 			     eth_type != htons(ETH_P_IPV6) &&
 			     eth_type != htons(ETH_P_ARP) &&
@@ -2971,7 +2971,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 		}
 
 		case OVS_ACTION_ATTR_POP_MPLS:
-			if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
+			if (vlan_tci & htons(VLAN_CFI_MASK) ||
 			    !eth_p_mpls(eth_type))
 				return -EINVAL;
 
@@ -3036,7 +3036,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 		case OVS_ACTION_ATTR_POP_ETH:
 			if (mac_proto != MAC_PROTO_ETHERNET)
 				return -EINVAL;
-			if (vlan_tci & htons(VLAN_TAG_PRESENT))
+			if (vlan_tci & htons(VLAN_CFI_MASK))
 				return -EINVAL;
 			mac_proto = MAC_PROTO_NONE;
 			break;
-- 
cgit v1.2.3


From f4f9a5e6cc7341c6c74060ee5a594d395c364c6f Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Thu, 8 Nov 2018 18:44:50 +0100
Subject: gianfar: remove use of VLAN_TAG_PRESENT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/gianfar_ethtool.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 0d76e15cd6dd..241325c35cb4 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -1134,11 +1134,9 @@ static int gfar_convert_to_filer(struct ethtool_rx_flow_spec *rule,
 		prio = vlan_tci_prio(rule);
 		prio_mask = vlan_tci_priom(rule);
 
-		if (cfi == VLAN_TAG_PRESENT && cfi_mask == VLAN_TAG_PRESENT) {
-			vlan |= RQFPR_CFI;
-			vlan_mask |= RQFPR_CFI;
-		} else if (cfi != VLAN_TAG_PRESENT &&
-			   cfi_mask == VLAN_TAG_PRESENT) {
+		if (cfi_mask) {
+			if (cfi)
+				vlan |= RQFPR_CFI;
 			vlan_mask |= RQFPR_CFI;
 		}
 	}
-- 
cgit v1.2.3


From 29e12207174a58ac8cab4914d0a7ce5e6c872646 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Thu, 8 Nov 2018 19:47:19 +0000
Subject: sfc: use the new __netdev_tx_sent_queue BQL optimisation

As added in 3e59020abf0f ("net: bql: add __netdev_tx_sent_queue()"), which
 see for performance rationale.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/tx.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index c3ad564ac4c0..22eb059086f7 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -553,13 +553,10 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	if (!data_mapped && (efx_tx_map_data(tx_queue, skb, segments)))
 		goto err;
 
-	/* Update BQL */
-	netdev_tx_sent_queue(tx_queue->core_txq, skb_len);
-
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+	if (__netdev_tx_sent_queue(tx_queue->core_txq, skb_len, xmit_more)) {
 		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
 
 		/* There could be packets left on the partner queue if those
-- 
cgit v1.2.3


From c74d90c11c05bdfd78f8e29ee96b8a6f23daea99 Mon Sep 17 00:00:00 2001
From: Gal Pressman <pressmangal@gmail.com>
Date: Wed, 7 Nov 2018 20:31:37 +0200
Subject: net/mlx5: Fix offsets of ifc reserved fields

Fix wrong offsets of reserved fields in ifc file.
Issues found using pahole.

Signed-off-by: Gal Pressman <pressmangal@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 34e17e6f8942..6f64e814cc10 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -349,7 +349,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8	   reformat_l3_tunnel_to_l2[0x1];
 	u8	   reformat_l2_to_l3_tunnel[0x1];
 	u8	   reformat_and_modify_action[0x1];
-	u8         reserved_at_14[0xb];
+	u8         reserved_at_15[0xb];
 	u8         reserved_at_20[0x2];
 	u8         log_max_ft_size[0x6];
 	u8         log_max_modify_header_context[0x8];
@@ -586,7 +586,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 	u8      fdb_multi_path_to_table[0x1];
 	u8      reserved_at_1d[0x1];
 	u8      multi_fdb_encap[0x1];
-	u8      reserved_at_1e[0x1e1];
+	u8      reserved_at_1f[0x1e1];
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb;
 
@@ -829,7 +829,7 @@ struct mlx5_ifc_vector_calc_cap_bits {
 	struct mlx5_ifc_calc_op calc2;
 	struct mlx5_ifc_calc_op calc3;
 
-	u8         reserved_at_e0[0x720];
+	u8         reserved_at_c0[0x720];
 };
 
 enum {
@@ -5567,7 +5567,7 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits {
 struct mlx5_ifc_modify_nic_vport_field_select_bits {
 	u8         reserved_at_0[0x12];
 	u8	   affiliation[0x1];
-	u8	   reserved_at_e[0x1];
+	u8	   reserved_at_13[0x1];
 	u8         disable_uc_local_lb[0x1];
 	u8         disable_mc_local_lb[0x1];
 	u8         node_guid[0x1];
@@ -9028,7 +9028,7 @@ struct mlx5_ifc_dcbx_param_bits {
 	u8         dcbx_cee_cap[0x1];
 	u8         dcbx_ieee_cap[0x1];
 	u8         dcbx_standby_cap[0x1];
-	u8         reserved_at_0[0x5];
+	u8         reserved_at_3[0x5];
 	u8         port_number[0x8];
 	u8         reserved_at_10[0xa];
 	u8         max_application_table_size[6];
-- 
cgit v1.2.3


From e7946760de5852f32c4e52ce47f37e85346981b9 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Thu, 8 Nov 2018 22:27:54 +0200
Subject: net: core: dev_addr_lists: add auxiliary func to handle reference
 address updates

In order to avoid all table update, and only remove or add new
address, the auxiliary function exists, named __hw_addr_sync_dev().
It allows end driver do nothing when nothing changed and add/rm when
concrete address is firstly added or lastly removed. But it doesn't
include cases when an address of real device or vlan was reused by
other vlans or vlan/macval devices.

For handaling events when address was reused/unreused the patch adds
new auxiliary routine - __hw_addr_ref_sync_dev(). It allows to do
nothing when nothing was changed and do updates only for an address
being added/reused/deleted/unreused. Thus, clone address changes for
vlans can be mirrored in the table. The function is exclusive with
__hw_addr_sync_dev(). It's responsibility of the end driver to
identify address vlan device, if it needs so.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 10 +++++
 net/core/dev_addr_lists.c | 97 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 107 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 857f8abf7b91..487fa5e0e165 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4068,6 +4068,16 @@ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
 		       int (*sync)(struct net_device *, const unsigned char *),
 		       int (*unsync)(struct net_device *,
 				     const unsigned char *));
+int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list,
+			   struct net_device *dev,
+			   int (*sync)(struct net_device *,
+				       const unsigned char *, int),
+			   int (*unsync)(struct net_device *,
+					 const unsigned char *, int));
+void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list,
+			      struct net_device *dev,
+			      int (*unsync)(struct net_device *,
+					    const unsigned char *, int));
 void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list,
 			  struct net_device *dev,
 			  int (*unsync)(struct net_device *,
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index d884d8f5f0e5..81a8cd4ea3bd 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -277,6 +277,103 @@ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
 }
 EXPORT_SYMBOL(__hw_addr_sync_dev);
 
+/**
+ *  __hw_addr_ref_sync_dev - Synchronize device's multicast address list taking
+ *  into account references
+ *  @list: address list to synchronize
+ *  @dev:  device to sync
+ *  @sync: function to call if address or reference on it should be added
+ *  @unsync: function to call if address or some reference on it should removed
+ *
+ *  This function is intended to be called from the ndo_set_rx_mode
+ *  function of devices that require explicit address or references on it
+ *  add/remove notifications. The unsync function may be NULL in which case
+ *  the addresses or references on it requiring removal will simply be
+ *  removed without any notification to the device. That is responsibility of
+ *  the driver to identify and distribute address or references on it between
+ *  internal address tables.
+ **/
+int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list,
+			   struct net_device *dev,
+			   int (*sync)(struct net_device *,
+				       const unsigned char *, int),
+			   int (*unsync)(struct net_device *,
+					 const unsigned char *, int))
+{
+	struct netdev_hw_addr *ha, *tmp;
+	int err, ref_cnt;
+
+	/* first go through and flush out any unsynced/stale entries */
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		/* sync if address is not used */
+		if ((ha->sync_cnt << 1) <= ha->refcount)
+			continue;
+
+		/* if fails defer unsyncing address */
+		ref_cnt = ha->refcount - ha->sync_cnt;
+		if (unsync && unsync(dev, ha->addr, ref_cnt))
+			continue;
+
+		ha->refcount = (ref_cnt << 1) + 1;
+		ha->sync_cnt = ref_cnt;
+		__hw_addr_del_entry(list, ha, false, false);
+	}
+
+	/* go through and sync updated/new entries to the list */
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		/* sync if address added or reused */
+		if ((ha->sync_cnt << 1) >= ha->refcount)
+			continue;
+
+		ref_cnt = ha->refcount - ha->sync_cnt;
+		err = sync(dev, ha->addr, ref_cnt);
+		if (err)
+			return err;
+
+		ha->refcount = ref_cnt << 1;
+		ha->sync_cnt = ref_cnt;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(__hw_addr_ref_sync_dev);
+
+/**
+ *  __hw_addr_ref_unsync_dev - Remove synchronized addresses and references on
+ *  it from device
+ *  @list: address list to remove synchronized addresses (references on it) from
+ *  @dev:  device to sync
+ *  @unsync: function to call if address and references on it should be removed
+ *
+ *  Remove all addresses that were added to the device by
+ *  __hw_addr_ref_sync_dev(). This function is intended to be called from the
+ *  ndo_stop or ndo_open functions on devices that require explicit address (or
+ *  references on it) add/remove notifications. If the unsync function pointer
+ *  is NULL then this function can be used to just reset the sync_cnt for the
+ *  addresses in the list.
+ **/
+void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list,
+			      struct net_device *dev,
+			      int (*unsync)(struct net_device *,
+					    const unsigned char *, int))
+{
+	struct netdev_hw_addr *ha, *tmp;
+
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		if (!ha->sync_cnt)
+			continue;
+
+		/* if fails defer unsyncing address */
+		if (unsync && unsync(dev, ha->addr, ha->sync_cnt))
+			continue;
+
+		ha->refcount -= ha->sync_cnt - 1;
+		ha->sync_cnt = 0;
+		__hw_addr_del_entry(list, ha, false, false);
+	}
+}
+EXPORT_SYMBOL(__hw_addr_ref_unsync_dev);
+
 /**
  *  __hw_addr_unsync_dev - Remove synchronized addresses from device
  *  @list: address list to remove synchronized addresses from
-- 
cgit v1.2.3


From 960abf68d2023f0d0b08c6f5d05971630496cfb0 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Thu, 8 Nov 2018 22:27:55 +0200
Subject: net: 8021q: vlan_core: allow use list of vlans for real device

It's redundancy for the drivers to hold the list of vlans when
absolutely the same list exists in vlan core. In most cases it's
needed only to traverse the vlan devices, their vids and sync some
settings with h/w, so add API to simplify this.

At least some of these drivers also can benefit:
grep "for_each.*vid" -r drivers/net/ethernet/

drivers/net/ethernet/hisilicon/hns3/hns3_enet.c:
drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c:
drivers/net/ethernet/qlogic/qlge/qlge_main.c:
drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c:
drivers/net/ethernet/via/via-rhine.c:
drivers/net/ethernet/via/via-velocity.c:
drivers/net/ethernet/intel/igb/igb_main.c:
drivers/net/ethernet/intel/ice/ice_main.c:
drivers/net/ethernet/intel/e1000/e1000_main.c:
drivers/net/ethernet/intel/i40e/i40e_main.c:
drivers/net/ethernet/intel/e1000e/netdev.c:
drivers/net/ethernet/intel/igbvf/netdev.c:
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c:
drivers/net/ethernet/intel/ixgb/ixgb_main.c:
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c:
drivers/net/ethernet/amd/xgbe/xgbe-dev.c:
drivers/net/ethernet/emulex/benet/be_main.c:
drivers/net/ethernet/neterion/vxge/vxge-main.c:
drivers/net/ethernet/adaptec/starfire.c:
drivers/net/ethernet/brocade/bna/bnad.c:

Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 11 +++++++++++
 net/8021q/vlan_core.c   | 27 +++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 03b08ffded07..1be5230921b5 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -133,6 +133,9 @@ struct vlan_pcpu_stats {
 
 extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev,
 					       __be16 vlan_proto, u16 vlan_id);
+extern int vlan_for_each(struct net_device *dev,
+			 int (*action)(struct net_device *dev, int vid,
+				       void *arg), void *arg);
 extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
 extern u16 vlan_dev_vlan_id(const struct net_device *dev);
 extern __be16 vlan_dev_vlan_proto(const struct net_device *dev);
@@ -236,6 +239,14 @@ __vlan_find_dev_deep_rcu(struct net_device *real_dev,
 	return NULL;
 }
 
+static inline int
+vlan_for_each(struct net_device *dev,
+	      int (*action)(struct net_device *dev, int vid, void *arg),
+	      void *arg)
+{
+	return 0;
+}
+
 static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev)
 {
 	BUG();
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 4f60e86f4b8d..6308b5427a66 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -223,6 +223,33 @@ static int vlan_kill_rx_filter_info(struct net_device *dev, __be16 proto, u16 vi
 		return -ENODEV;
 }
 
+int vlan_for_each(struct net_device *dev,
+		  int (*action)(struct net_device *dev, int vid, void *arg),
+		  void *arg)
+{
+	struct vlan_vid_info *vid_info;
+	struct vlan_info *vlan_info;
+	struct net_device *vdev;
+	int ret;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info)
+		return 0;
+
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		vdev = vlan_group_get_device(&vlan_info->grp, vid_info->proto,
+					     vid_info->vid);
+		ret = action(vdev, vid_info->vid, arg);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(vlan_for_each);
+
 int vlan_filter_push_vids(struct vlan_info *vlan_info, __be16 proto)
 {
 	struct net_device *real_dev = vlan_info->real_dev;
-- 
cgit v1.2.3


From 15180eca569bfe1d4d3edbe02da76d5345e773b5 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Thu, 8 Nov 2018 22:27:56 +0200
Subject: net: ethernet: ti: cpsw: fix vlan mcast

At this moment, mcast addresses are added for real device only
(reserved vlans for dual-emac mode), even if a mcast address was added
for some vlan only, thus ALE doesn't have corresponding vlan mcast
entries after vlan socket joined multicast group. So ALE drops vlan
frames with mcast addresses intended for vlans and potentially can
receive mcast frames for base ndev. That's not correct. So, fix it by
creating only vlan/mcast entries as requested. Patch doesn't use any
additional lists and is based on device mc address list and cpsw ALE
table entries.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 169 +++++++++++++++++++++++++++++++++--------
 1 file changed, 138 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 500f7ed8c58c..0b18634d336c 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -570,21 +570,6 @@ static inline int cpsw_get_slave_port(u32 slave_num)
 	return slave_num + 1;
 }
 
-static void cpsw_add_mcast(struct cpsw_priv *priv, const u8 *addr)
-{
-	struct cpsw_common *cpsw = priv->cpsw;
-
-	if (cpsw->data.dual_emac) {
-		struct cpsw_slave *slave = cpsw->slaves + priv->emac_port;
-
-		cpsw_ale_add_mcast(cpsw->ale, addr, ALE_PORT_HOST,
-				   ALE_VLAN, slave->port_vlan, 0);
-		return;
-	}
-
-	cpsw_ale_add_mcast(cpsw->ale, addr, ALE_ALL_PORTS, 0, 0, 0);
-}
-
 static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 {
 	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
@@ -640,7 +625,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 
 			/* Clear all mcast from ALE */
 			cpsw_ale_flush_multicast(ale, ALE_ALL_PORTS, -1);
-			__dev_mc_unsync(ndev, NULL);
+			__hw_addr_ref_unsync_dev(&ndev->mc, ndev, NULL);
 
 			/* Flood All Unicast Packets to Host port */
 			cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 1);
@@ -661,29 +646,148 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 	}
 }
 
-static int cpsw_add_mc_addr(struct net_device *ndev, const u8 *addr)
+struct addr_sync_ctx {
+	struct net_device *ndev;
+	const u8 *addr;		/* address to be synched */
+	int consumed;		/* number of address instances */
+	int flush;		/* flush flag */
+};
+
+/**
+ * cpsw_set_mc - adds multicast entry to the table if it's not added or deletes
+ * if it's not deleted
+ * @ndev: device to sync
+ * @addr: address to be added or deleted
+ * @vid: vlan id, if vid < 0 set/unset address for real device
+ * @add: add address if the flag is set or remove otherwise
+ */
+static int cpsw_set_mc(struct net_device *ndev, const u8 *addr,
+		       int vid, int add)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int mask, flags, ret;
+
+	if (vid < 0) {
+		if (cpsw->data.dual_emac)
+			vid = cpsw->slaves[priv->emac_port].port_vlan;
+		else
+			vid = 0;
+	}
+
+	mask = cpsw->data.dual_emac ? ALE_PORT_HOST : ALE_ALL_PORTS;
+	flags = vid ? ALE_VLAN : 0;
+
+	if (add)
+		ret = cpsw_ale_add_mcast(cpsw->ale, addr, mask, flags, vid, 0);
+	else
+		ret = cpsw_ale_del_mcast(cpsw->ale, addr, 0, flags, vid);
+
+	return ret;
+}
+
+static int cpsw_update_vlan_mc(struct net_device *vdev, int vid, void *ctx)
+{
+	struct addr_sync_ctx *sync_ctx = ctx;
+	struct netdev_hw_addr *ha;
+	int found = 0, ret = 0;
+
+	if (!vdev || !(vdev->flags & IFF_UP))
+		return 0;
+
+	/* vlan address is relevant if its sync_cnt != 0 */
+	netdev_for_each_mc_addr(ha, vdev) {
+		if (ether_addr_equal(ha->addr, sync_ctx->addr)) {
+			found = ha->sync_cnt;
+			break;
+		}
+	}
+
+	if (found)
+		sync_ctx->consumed++;
+
+	if (sync_ctx->flush) {
+		if (!found)
+			cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 0);
+		return 0;
+	}
+
+	if (found)
+		ret = cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 1);
+
+	return ret;
+}
+
+static int cpsw_add_mc_addr(struct net_device *ndev, const u8 *addr, int num)
+{
+	struct addr_sync_ctx sync_ctx;
+	int ret;
+
+	sync_ctx.consumed = 0;
+	sync_ctx.addr = addr;
+	sync_ctx.ndev = ndev;
+	sync_ctx.flush = 0;
+
+	ret = vlan_for_each(ndev, cpsw_update_vlan_mc, &sync_ctx);
+	if (sync_ctx.consumed < num && !ret)
+		ret = cpsw_set_mc(ndev, addr, -1, 1);
+
+	return ret;
+}
+
+static int cpsw_del_mc_addr(struct net_device *ndev, const u8 *addr, int num)
+{
+	struct addr_sync_ctx sync_ctx;
+
+	sync_ctx.consumed = 0;
+	sync_ctx.addr = addr;
+	sync_ctx.ndev = ndev;
+	sync_ctx.flush = 1;
+
+	vlan_for_each(ndev, cpsw_update_vlan_mc, &sync_ctx);
+	if (sync_ctx.consumed == num)
+		cpsw_set_mc(ndev, addr, -1, 0);
 
-	cpsw_add_mcast(priv, addr);
 	return 0;
 }
 
-static int cpsw_del_mc_addr(struct net_device *ndev, const u8 *addr)
+static int cpsw_purge_vlan_mc(struct net_device *vdev, int vid, void *ctx)
 {
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int vid, flags;
+	struct addr_sync_ctx *sync_ctx = ctx;
+	struct netdev_hw_addr *ha;
+	int found = 0;
 
-	if (cpsw->data.dual_emac) {
-		vid = cpsw->slaves[priv->emac_port].port_vlan;
-		flags = ALE_VLAN;
-	} else {
-		vid = 0;
-		flags = 0;
+	if (!vdev || !(vdev->flags & IFF_UP))
+		return 0;
+
+	/* vlan address is relevant if its sync_cnt != 0 */
+	netdev_for_each_mc_addr(ha, vdev) {
+		if (ether_addr_equal(ha->addr, sync_ctx->addr)) {
+			found = ha->sync_cnt;
+			break;
+		}
 	}
 
-	cpsw_ale_del_mcast(cpsw->ale, addr, 0, flags, vid);
+	if (!found)
+		return 0;
+
+	sync_ctx->consumed++;
+	cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 0);
+	return 0;
+}
+
+static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num)
+{
+	struct addr_sync_ctx sync_ctx;
+
+	sync_ctx.addr = addr;
+	sync_ctx.ndev = ndev;
+	sync_ctx.consumed = 0;
+
+	vlan_for_each(ndev, cpsw_purge_vlan_mc, &sync_ctx);
+	if (sync_ctx.consumed < num)
+		cpsw_set_mc(ndev, addr, -1, 0);
+
 	return 0;
 }
 
@@ -704,7 +808,9 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 	/* Restore allmulti on vlans if necessary */
 	cpsw_ale_set_allmulti(cpsw->ale, ndev->flags & IFF_ALLMULTI);
 
-	__dev_mc_sync(ndev, cpsw_add_mc_addr, cpsw_del_mc_addr);
+	/* add/remove mcast address either for real netdev or for vlan */
+	__hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr,
+			       cpsw_del_mc_addr);
 }
 
 static void cpsw_intr_enable(struct cpsw_common *cpsw)
@@ -1964,7 +2070,7 @@ static int cpsw_ndo_stop(struct net_device *ndev)
 	struct cpsw_common *cpsw = priv->cpsw;
 
 	cpsw_info(priv, ifdown, "shutting down cpsw device\n");
-	__dev_mc_unsync(priv->ndev, cpsw_del_mc_addr);
+	__hw_addr_ref_unsync_dev(&ndev->mc, ndev, cpsw_purge_all_mc);
 	netif_tx_stop_all_queues(priv->ndev);
 	netif_carrier_off(priv->ndev);
 
@@ -2415,6 +2521,7 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev,
 				  HOST_PORT_NUM, ALE_VLAN, vid);
 	ret |= cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
 				  0, ALE_VLAN, vid);
+	ret |= cpsw_ale_flush_multicast(cpsw->ale, 0, vid);
 err:
 	pm_runtime_put(cpsw->dev);
 	return ret;
-- 
cgit v1.2.3


From 00fe47120502076e8a377ba259c10a30ba21d777 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Thu, 8 Nov 2018 22:27:57 +0200
Subject: net: ethernet: ti: cpsw: fix vlan configuration while down/up

The vlan configuration is not restored after interface donw/up sequence
(if dual-emac - both interfaces). Tested on am572x EVM.

Steps to check:
~# ip link add link eth1 name eth1.100 type vlan id 100
~# ifconfig eth0 down
~# ifconfig eth1 down

Try to remove vid and observe warning:
~# ip link del eth1.100
[  739.526757] net eth1: removing vlanid 100 from vlan filter
[  739.533322] failed to kill vid 0081/100 for device eth1

This patch fixes it, restoring only vlan ALE entries and all other
unicast/multicast entries are restored by system calling rx_mode ndo.

Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 0b18634d336c..9434fd5a5477 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -565,6 +565,9 @@ static const struct cpsw_stats cpsw_gstrings_ch_stats[] = {
 				(func)(slave++, ##arg);			\
 	} while (0)
 
+static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
+				    __be16 proto, u16 vid);
+
 static inline int cpsw_get_slave_port(u32 slave_num)
 {
 	return slave_num + 1;
@@ -1951,9 +1954,23 @@ static void cpsw_mqprio_resume(struct cpsw_slave *slave, struct cpsw_priv *priv)
 	slave_write(slave, tx_prio_map, tx_prio_rg);
 }
 
+static int cpsw_restore_vlans(struct net_device *vdev, int vid, void *arg)
+{
+	struct cpsw_priv *priv = arg;
+
+	if (!vdev)
+		return 0;
+
+	cpsw_ndo_vlan_rx_add_vid(priv->ndev, 0, vid);
+	return 0;
+}
+
 /* restore resources after port reset */
 static void cpsw_restore(struct cpsw_priv *priv)
 {
+	/* restore vlan configurations */
+	vlan_for_each(priv->ndev, cpsw_restore_vlans, priv);
+
 	/* restore MQPRIO offload */
 	for_each_slave(priv, cpsw_mqprio_resume, priv);
 
-- 
cgit v1.2.3


From 49f8e8329c3c05e78a75112ce006c41d24eaad0d Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 8 Nov 2018 14:05:42 -0800
Subject: net: move __skb_checksum_complete*() to skbuff.c

__skb_checksum_complete_head() and __skb_checksum_complete()
are both declared in skbuff.h, they fit better in skbuff.c
than datagram.c.

Cc: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 43 -------------------------------------------
 net/core/skbuff.c   | 43 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+), 43 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 57f3a6fcfc1e..07983b90d2bd 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -728,49 +728,6 @@ fault:
 	return -EFAULT;
 }
 
-__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
-{
-	__sum16 sum;
-
-	sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
-	if (likely(!sum)) {
-		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
-		    !skb->csum_complete_sw)
-			netdev_rx_csum_fault(skb->dev);
-	}
-	if (!skb_shared(skb))
-		skb->csum_valid = !sum;
-	return sum;
-}
-EXPORT_SYMBOL(__skb_checksum_complete_head);
-
-__sum16 __skb_checksum_complete(struct sk_buff *skb)
-{
-	__wsum csum;
-	__sum16 sum;
-
-	csum = skb_checksum(skb, 0, skb->len, 0);
-
-	/* skb->csum holds pseudo checksum */
-	sum = csum_fold(csum_add(skb->csum, csum));
-	if (likely(!sum)) {
-		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
-		    !skb->csum_complete_sw)
-			netdev_rx_csum_fault(skb->dev);
-	}
-
-	if (!skb_shared(skb)) {
-		/* Save full packet checksum */
-		skb->csum = csum;
-		skb->ip_summed = CHECKSUM_COMPLETE;
-		skb->csum_complete_sw = 1;
-		skb->csum_valid = !sum;
-	}
-
-	return sum;
-}
-EXPORT_SYMBOL(__skb_checksum_complete);
-
 /**
  *	skb_copy_and_csum_datagram_msg - Copy and checksum skb to user iovec.
  *	@skb: skbuff
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b4ee5c8b928f..5cb4b3440153 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2645,6 +2645,49 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
 }
 EXPORT_SYMBOL(skb_copy_and_csum_bits);
 
+__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
+{
+	__sum16 sum;
+
+	sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+	if (!skb_shared(skb))
+		skb->csum_valid = !sum;
+	return sum;
+}
+EXPORT_SYMBOL(__skb_checksum_complete_head);
+
+__sum16 __skb_checksum_complete(struct sk_buff *skb)
+{
+	__wsum csum;
+	__sum16 sum;
+
+	csum = skb_checksum(skb, 0, skb->len, 0);
+
+	/* skb->csum holds pseudo checksum */
+	sum = csum_fold(csum_add(skb->csum, csum));
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+
+	if (!skb_shared(skb)) {
+		/* Save full packet checksum */
+		skb->csum = csum;
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum_complete_sw = 1;
+		skb->csum_valid = !sum;
+	}
+
+	return sum;
+}
+EXPORT_SYMBOL(__skb_checksum_complete);
+
 static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum)
 {
 	net_warn_ratelimited(
-- 
cgit v1.2.3


From 35c4a95d95287ffae90c111b861d755f1565dbc1 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 9 Nov 2018 00:18:01 +0100
Subject: cxgb4: use __vlan_hwaccel helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use __vlan_hwaccel_put_tag() to set vlan tag and proto fields.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/cxgb4/cm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 615413bd3e8d..8ed01e07c463 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -3944,7 +3944,7 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb)
 	} else {
 		vlan_eh = (struct vlan_ethhdr *)(req + 1);
 		iph = (struct iphdr *)(vlan_eh + 1);
-		skb->vlan_tci = ntohs(cpl->vlan);
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(cpl->vlan));
 	}
 
 	if (iph->version != 0x4)
-- 
cgit v1.2.3


From b1817524c028a5a5284f21358185c74790001e0e Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 9 Nov 2018 00:18:02 +0100
Subject: net/core: use __vlan_hwaccel helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This removes assumptions about VLAN_TAG_PRESENT bit.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c       | 8 +++++---
 net/core/skbuff.c    | 2 +-
 net/sched/act_vlan.c | 2 +-
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 0ffcbdd55fa9..bf7e0a471186 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4889,7 +4889,7 @@ skip_classify:
 		 * and set skb->priority like in vlan_do_receive()
 		 * For the time being, just ignore Priority Code Point
 		 */
-		skb->vlan_tci = 0;
+		__vlan_hwaccel_clear_tag(skb);
 	}
 
 	type = skb->protocol;
@@ -5386,7 +5386,9 @@ static struct list_head *gro_list_prepare(struct napi_struct *napi,
 		}
 
 		diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
-		diffs |= p->vlan_tci ^ skb->vlan_tci;
+		diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb);
+		if (skb_vlan_tag_present(p))
+			diffs |= p->vlan_tci ^ skb->vlan_tci;
 		diffs |= skb_metadata_dst_cmp(p, skb);
 		diffs |= skb_metadata_differs(p, skb);
 		if (maclen == ETH_HLEN)
@@ -5652,7 +5654,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	__skb_pull(skb, skb_headlen(skb));
 	/* restore the reserve we had after netdev_alloc_skb_ip_align() */
 	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb));
-	skb->vlan_tci = 0;
+	__vlan_hwaccel_clear_tag(skb);
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
 	skb->encapsulation = 0;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5cb4b3440153..396fcb3baad0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5166,7 +5166,7 @@ int skb_vlan_pop(struct sk_buff *skb)
 	int err;
 
 	if (likely(skb_vlan_tag_present(skb))) {
-		skb->vlan_tci = 0;
+		__vlan_hwaccel_clear_tag(skb);
 	} else {
 		if (unlikely(!eth_type_vlan(skb->protocol)))
 			return 0;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index ba677d54a7af..93fdaf707313 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -63,7 +63,7 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a,
 		/* extract existing tag (and guarantee no hw-accel tag) */
 		if (skb_vlan_tag_present(skb)) {
 			tci = skb_vlan_tag_get(skb);
-			skb->vlan_tci = 0;
+			__vlan_hwaccel_clear_tag(skb);
 		} else {
 			/* in-payload vlan tag, pop it */
 			err = __skb_vlan_pop(skb, &tci);
-- 
cgit v1.2.3


From 82eea4cfe41dfc1f50a7e3af1ab3d76a89d193fc Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 9 Nov 2018 00:18:02 +0100
Subject: nfnetlink/queue: use __vlan_hwaccel helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netfilter/nfnetlink_queue.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 43041f087eb3..1ce30efe6854 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1148,8 +1148,9 @@ static int nfqa_parse_bridge(struct nf_queue_entry *entry,
 		if (!tb[NFQA_VLAN_TCI] || !tb[NFQA_VLAN_PROTO])
 			return -EINVAL;
 
-		entry->skb->vlan_tci = ntohs(nla_get_be16(tb[NFQA_VLAN_TCI]));
-		entry->skb->vlan_proto = nla_get_be16(tb[NFQA_VLAN_PROTO]);
+		__vlan_hwaccel_put_tag(entry->skb,
+			nla_get_be16(tb[NFQA_VLAN_PROTO]),
+			ntohs(nla_get_be16(tb[NFQA_VLAN_TCI])));
 	}
 
 	if (nfqa[NFQA_L2HDR]) {
-- 
cgit v1.2.3


From 418a976d6c68d0835ffebf755cdbd53e9b9c6e7f Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 9 Nov 2018 00:18:03 +0100
Subject: 8021q: use __vlan_hwaccel helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 6308b5427a66..57425049faf2 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -57,7 +57,7 @@ bool vlan_do_receive(struct sk_buff **skbp)
 	}
 
 	skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci);
-	skb->vlan_tci = 0;
+	__vlan_hwaccel_clear_tag(skb);
 
 	rx_stats = this_cpu_ptr(vlan_dev_priv(vlan_dev)->vlan_pcpu_stats);
 
-- 
cgit v1.2.3


From 5978f8a9fb492a74765822a545f16eb879fab937 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 9 Nov 2018 00:18:03 +0100
Subject: bridge: use __vlan_hwaccel helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This removes assumption than vlan_tci != 0 when tag is present.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netfilter_hooks.c | 15 +++++++++------
 net/bridge/br_private.h         |  2 +-
 net/bridge/br_vlan.c            |  6 +++---
 3 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index b1b5e8516724..c9383c470a83 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -671,10 +671,8 @@ static int br_nf_push_frag_xmit(struct net *net, struct sock *sk, struct sk_buff
 		return 0;
 	}
 
-	if (data->vlan_tci) {
-		skb->vlan_tci = data->vlan_tci;
-		skb->vlan_proto = data->vlan_proto;
-	}
+	if (data->vlan_proto)
+		__vlan_hwaccel_put_tag(skb, data->vlan_proto, data->vlan_tci);
 
 	skb_copy_to_linear_data_offset(skb, -data->size, data->mac, data->size);
 	__skb_push(skb, data->encap_size);
@@ -740,8 +738,13 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff
 
 		data = this_cpu_ptr(&brnf_frag_data_storage);
 
-		data->vlan_tci = skb->vlan_tci;
-		data->vlan_proto = skb->vlan_proto;
+		if (skb_vlan_tag_present(skb)) {
+			data->vlan_tci = skb->vlan_tci;
+			data->vlan_proto = skb->vlan_proto;
+		} else {
+			data->vlan_proto = 0;
+		}
+
 		data->encap_size = nf_bridge_encap_header_len(skb);
 		data->size = ETH_HLEN + data->encap_size;
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 2920e06a5403..67105c66584a 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -905,7 +905,7 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid)
 	int err = 0;
 
 	if (skb_vlan_tag_present(skb)) {
-		*vid = skb_vlan_tag_get(skb) & VLAN_VID_MASK;
+		*vid = skb_vlan_tag_get_id(skb);
 	} else {
 		*vid = 0;
 		err = -EINVAL;
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 8c9297a01947..a7e869da21bf 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -420,7 +420,7 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
 	}
 
 	if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)
-		skb->vlan_tci = 0;
+		__vlan_hwaccel_clear_tag(skb);
 
 	if (p && (p->flags & BR_VLAN_TUNNEL) &&
 	    br_handle_egress_vlan_tunnel(skb, v)) {
@@ -493,8 +493,8 @@ static bool __allowed_ingress(const struct net_bridge *br,
 			__vlan_hwaccel_put_tag(skb, br->vlan_proto, pvid);
 		else
 			/* Priority-tagged Frame.
-			 * At this point, We know that skb->vlan_tci had
-			 * VLAN_TAG_PRESENT bit and its VID field was 0x000.
+			 * At this point, we know that skb->vlan_tci VID
+			 * field was 0.
 			 * We update only VID field and preserve PCP field.
 			 */
 			skb->vlan_tci |= pvid;
-- 
cgit v1.2.3


From 3e2ed0c2575091254760f1dc9b0ddeb999aca716 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 9 Nov 2018 00:18:04 +0100
Subject: ipv4/tunnel: use __vlan_hwaccel helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index dde671e97829..f45b96d715f0 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -120,7 +120,7 @@ int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len,
 	}
 
 	skb_clear_hash_if_not_l4(skb);
-	skb->vlan_tci = 0;
+	__vlan_hwaccel_clear_tag(skb);
 	skb_set_queue_mapping(skb, 0);
 	skb_scrub_packet(skb, xnet);
 
-- 
cgit v1.2.3


From c4062f89c5eb1af2b88ba6512a8452c630f7a6cc Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 9 Nov 2018 00:18:04 +0100
Subject: benet: use __vlan_hwaccel helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_main.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index c5ad7a4f4d83..80b2bd3747ce 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1049,30 +1049,35 @@ static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter,
 					     struct be_wrb_params
 					     *wrb_params)
 {
+	bool insert_vlan = false;
 	u16 vlan_tag = 0;
 
 	skb = skb_share_check(skb, GFP_ATOMIC);
 	if (unlikely(!skb))
 		return skb;
 
-	if (skb_vlan_tag_present(skb))
+	if (skb_vlan_tag_present(skb)) {
 		vlan_tag = be_get_tx_vlan_tag(adapter, skb);
+		insert_vlan = true;
+	}
 
 	if (qnq_async_evt_rcvd(adapter) && adapter->pvid) {
-		if (!vlan_tag)
+		if (!insert_vlan) {
 			vlan_tag = adapter->pvid;
+			insert_vlan = true;
+		}
 		/* f/w workaround to set skip_hw_vlan = 1, informs the F/W to
 		 * skip VLAN insertion
 		 */
 		BE_WRB_F_SET(wrb_params->features, VLAN_SKIP_HW, 1);
 	}
 
-	if (vlan_tag) {
+	if (insert_vlan) {
 		skb = vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q),
 						vlan_tag);
 		if (unlikely(!skb))
 			return skb;
-		skb->vlan_tci = 0;
+		__vlan_hwaccel_clear_tag(skb);
 	}
 
 	/* Insert the outer VLAN, if any */
-- 
cgit v1.2.3


From 4b17f9fe48c001d8fbcb7995df33a502dac25ae6 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 9 Nov 2018 00:18:05 +0100
Subject: mlx4: use __vlan_hwaccel helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index db00bf1c23f5..fd09ba98c0a6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -875,7 +875,7 @@ csum_none:
 			skb->data_len = length;
 			napi_gro_frags(&cq->napi);
 		} else {
-			skb->vlan_tci = 0;
+			__vlan_hwaccel_clear_tag(skb);
 			skb_clear_hash(skb);
 		}
 next:
-- 
cgit v1.2.3


From 3149a2711bac22a673bc4b9e99d0ace2d23e11da Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Fri, 9 Nov 2018 00:18:06 +0100
Subject: sky2: use __vlan_hwaccel helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 697d9b374f5e..c7cd0081058e 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -2485,13 +2485,11 @@ static struct sk_buff *receive_copy(struct sky2_port *sky2,
 		skb->ip_summed = re->skb->ip_summed;
 		skb->csum = re->skb->csum;
 		skb_copy_hash(skb, re->skb);
-		skb->vlan_proto = re->skb->vlan_proto;
-		skb->vlan_tci = re->skb->vlan_tci;
+		__vlan_hwaccel_copy_tag(skb, re->skb);
 
 		pci_dma_sync_single_for_device(sky2->hw->pdev, re->data_addr,
 					       length, PCI_DMA_FROMDEVICE);
-		re->skb->vlan_proto = 0;
-		re->skb->vlan_tci = 0;
+		__vlan_hwaccel_clear_tag(re->skb);
 		skb_clear_hash(re->skb);
 		re->skb->ip_summed = CHECKSUM_NONE;
 		skb_put(skb, length);
-- 
cgit v1.2.3


From 1106a5ade15fa2effdbfb3b3a1ba560a536dbcfe Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Thu, 8 Nov 2018 21:54:00 -0500
Subject: tcp_bbr: update comments to reflect pacing_margin_percent

Recently, in commit ab408b6dc744 ("tcp: switch tcp and sch_fq to new
earliest departure time model"), the TCP BBR code switched to a new
approach of using an explicit bbr_pacing_margin_percent for shaving a
pacing rate "haircut", rather than the previous implict
approach. Update an old comment to reflect the new approach.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 9277abdd822a..0f497fc49c3f 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -128,7 +128,12 @@ static const u32 bbr_probe_rtt_mode_ms = 200;
 /* Skip TSO below the following bandwidth (bits/sec): */
 static const int bbr_min_tso_rate = 1200000;
 
-/* Pace at ~1% below estimated bw, on average, to reduce queue at bottleneck. */
+/* Pace at ~1% below estimated bw, on average, to reduce queue at bottleneck.
+ * In order to help drive the network toward lower queues and low latency while
+ * maintaining high utilization, the average pacing rate aims to be slightly
+ * lower than the estimated bandwidth. This is an important aspect of the
+ * design.
+ */
 static const int bbr_pacing_margin_percent = 1;
 
 /* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain
@@ -247,13 +252,7 @@ static void bbr_init_pacing_rate_from_rtt(struct sock *sk)
 	sk->sk_pacing_rate = bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain);
 }
 
-/* Pace using current bw estimate and a gain factor. In order to help drive the
- * network toward lower queues while maintaining high utilization and low
- * latency, the average pacing rate aims to be slightly (~1%) lower than the
- * estimated bandwidth. This is an important aspect of the design. In this
- * implementation this slightly lower pacing rate is achieved implicitly by not
- * including link-layer headers in the packet size used for the pacing rate.
- */
+/* Pace using current bw estimate and a gain factor. */
 static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-- 
cgit v1.2.3


From 47330f9bdf240f5a582f756cf93354281b36453a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 8 Nov 2018 19:50:33 -0800
Subject: nfp: abm: split qdisc offload code into a separate file

The Qdisc offload code is logically separate, and we will soon
do significant surgery on it to support more Qdiscs, so move
it to a separate file.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/Makefile    |   1 +
 drivers/net/ethernet/netronome/nfp/abm/main.c  | 266 ------------------------
 drivers/net/ethernet/netronome/nfp/abm/main.h  |   6 +
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 272 +++++++++++++++++++++++++
 4 files changed, 279 insertions(+), 266 deletions(-)
 create mode 100644 drivers/net/ethernet/netronome/nfp/abm/qdisc.c

diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile
index 4afb10375397..190e8b56a41f 100644
--- a/drivers/net/ethernet/netronome/nfp/Makefile
+++ b/drivers/net/ethernet/netronome/nfp/Makefile
@@ -57,6 +57,7 @@ endif
 ifeq ($(CONFIG_NFP_APP_ABM_NIC),y)
 nfp-objs += \
 	    abm/ctrl.o \
+	    abm/qdisc.o \
 	    abm/main.o
 endif
 
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index c0830c0c2c3f..3d15de0ae271 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -7,9 +7,6 @@
 #include <linux/netdevice.h>
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
-#include <net/pkt_cls.h>
-#include <net/pkt_sched.h>
-#include <net/red.h>
 
 #include "../nfpcore/nfp.h"
 #include "../nfpcore/nfp_cpp.h"
@@ -27,269 +24,6 @@ static u32 nfp_abm_portid(enum nfp_repr_type rtype, unsigned int id)
 	       FIELD_PREP(NFP_ABM_PORTID_ID, id);
 }
 
-static int
-__nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
-		     u32 handle, unsigned int qs, u32 init_val)
-{
-	struct nfp_port *port = nfp_port_from_netdev(netdev);
-	int ret;
-
-	ret = nfp_abm_ctrl_set_all_q_lvls(alink, init_val);
-	memset(alink->qdiscs, 0, sizeof(*alink->qdiscs) * alink->num_qdiscs);
-
-	alink->parent = handle;
-	alink->num_qdiscs = qs;
-	port->tc_offload_cnt = qs;
-
-	return ret;
-}
-
-static void
-nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
-		   u32 handle, unsigned int qs)
-{
-	__nfp_abm_reset_root(netdev, alink, handle, qs, ~0);
-}
-
-static int
-nfp_abm_red_find(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
-{
-	unsigned int i = TC_H_MIN(opt->parent) - 1;
-
-	if (opt->parent == TC_H_ROOT)
-		i = 0;
-	else if (TC_H_MAJ(alink->parent) == TC_H_MAJ(opt->parent))
-		i = TC_H_MIN(opt->parent) - 1;
-	else
-		return -EOPNOTSUPP;
-
-	if (i >= alink->num_qdiscs || opt->handle != alink->qdiscs[i].handle)
-		return -EOPNOTSUPP;
-
-	return i;
-}
-
-static void
-nfp_abm_red_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
-		    u32 handle)
-{
-	unsigned int i;
-
-	for (i = 0; i < alink->num_qdiscs; i++)
-		if (handle == alink->qdiscs[i].handle)
-			break;
-	if (i == alink->num_qdiscs)
-		return;
-
-	if (alink->parent == TC_H_ROOT) {
-		nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
-	} else {
-		nfp_abm_ctrl_set_q_lvl(alink, i, ~0);
-		memset(&alink->qdiscs[i], 0, sizeof(*alink->qdiscs));
-	}
-}
-
-static int
-nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
-		    struct tc_red_qopt_offload *opt)
-{
-	bool existing;
-	int i, err;
-
-	i = nfp_abm_red_find(alink, opt);
-	existing = i >= 0;
-
-	if (opt->set.min != opt->set.max || !opt->set.is_ecn) {
-		nfp_warn(alink->abm->app->cpp,
-			 "RED offload failed - unsupported parameters\n");
-		err = -EINVAL;
-		goto err_destroy;
-	}
-
-	if (existing) {
-		if (alink->parent == TC_H_ROOT)
-			err = nfp_abm_ctrl_set_all_q_lvls(alink, opt->set.min);
-		else
-			err = nfp_abm_ctrl_set_q_lvl(alink, i, opt->set.min);
-		if (err)
-			goto err_destroy;
-		return 0;
-	}
-
-	if (opt->parent == TC_H_ROOT) {
-		i = 0;
-		err = __nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 1,
-					   opt->set.min);
-	} else if (TC_H_MAJ(alink->parent) == TC_H_MAJ(opt->parent)) {
-		i = TC_H_MIN(opt->parent) - 1;
-		err = nfp_abm_ctrl_set_q_lvl(alink, i, opt->set.min);
-	} else {
-		return -EINVAL;
-	}
-	/* Set the handle to try full clean up, in case IO failed */
-	alink->qdiscs[i].handle = opt->handle;
-	if (err)
-		goto err_destroy;
-
-	if (opt->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_stats(alink, &alink->qdiscs[i].stats);
-	else
-		err = nfp_abm_ctrl_read_q_stats(alink, i,
-						&alink->qdiscs[i].stats);
-	if (err)
-		goto err_destroy;
-
-	if (opt->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_xstats(alink,
-					       &alink->qdiscs[i].xstats);
-	else
-		err = nfp_abm_ctrl_read_q_xstats(alink, i,
-						 &alink->qdiscs[i].xstats);
-	if (err)
-		goto err_destroy;
-
-	alink->qdiscs[i].stats.backlog_pkts = 0;
-	alink->qdiscs[i].stats.backlog_bytes = 0;
-
-	return 0;
-err_destroy:
-	/* If the qdisc keeps on living, but we can't offload undo changes */
-	if (existing) {
-		opt->set.qstats->qlen -= alink->qdiscs[i].stats.backlog_pkts;
-		opt->set.qstats->backlog -=
-			alink->qdiscs[i].stats.backlog_bytes;
-	}
-	nfp_abm_red_destroy(netdev, alink, opt->handle);
-
-	return err;
-}
-
-static void
-nfp_abm_update_stats(struct nfp_alink_stats *new, struct nfp_alink_stats *old,
-		     struct tc_qopt_offload_stats *stats)
-{
-	_bstats_update(stats->bstats, new->tx_bytes - old->tx_bytes,
-		       new->tx_pkts - old->tx_pkts);
-	stats->qstats->qlen += new->backlog_pkts - old->backlog_pkts;
-	stats->qstats->backlog += new->backlog_bytes - old->backlog_bytes;
-	stats->qstats->overlimits += new->overlimits - old->overlimits;
-	stats->qstats->drops += new->drops - old->drops;
-}
-
-static int
-nfp_abm_red_stats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
-{
-	struct nfp_alink_stats *prev_stats;
-	struct nfp_alink_stats stats;
-	int i, err;
-
-	i = nfp_abm_red_find(alink, opt);
-	if (i < 0)
-		return i;
-	prev_stats = &alink->qdiscs[i].stats;
-
-	if (alink->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_stats(alink, &stats);
-	else
-		err = nfp_abm_ctrl_read_q_stats(alink, i, &stats);
-	if (err)
-		return err;
-
-	nfp_abm_update_stats(&stats, prev_stats, &opt->stats);
-
-	*prev_stats = stats;
-
-	return 0;
-}
-
-static int
-nfp_abm_red_xstats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
-{
-	struct nfp_alink_xstats *prev_xstats;
-	struct nfp_alink_xstats xstats;
-	int i, err;
-
-	i = nfp_abm_red_find(alink, opt);
-	if (i < 0)
-		return i;
-	prev_xstats = &alink->qdiscs[i].xstats;
-
-	if (alink->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_xstats(alink, &xstats);
-	else
-		err = nfp_abm_ctrl_read_q_xstats(alink, i, &xstats);
-	if (err)
-		return err;
-
-	opt->xstats->forced_mark += xstats.ecn_marked - prev_xstats->ecn_marked;
-	opt->xstats->pdrop += xstats.pdrop - prev_xstats->pdrop;
-
-	*prev_xstats = xstats;
-
-	return 0;
-}
-
-static int
-nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
-		     struct tc_red_qopt_offload *opt)
-{
-	switch (opt->command) {
-	case TC_RED_REPLACE:
-		return nfp_abm_red_replace(netdev, alink, opt);
-	case TC_RED_DESTROY:
-		nfp_abm_red_destroy(netdev, alink, opt->handle);
-		return 0;
-	case TC_RED_STATS:
-		return nfp_abm_red_stats(alink, opt);
-	case TC_RED_XSTATS:
-		return nfp_abm_red_xstats(alink, opt);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int
-nfp_abm_mq_stats(struct nfp_abm_link *alink, struct tc_mq_qopt_offload *opt)
-{
-	struct nfp_alink_stats stats;
-	unsigned int i;
-	int err;
-
-	for (i = 0; i < alink->num_qdiscs; i++) {
-		if (alink->qdiscs[i].handle == TC_H_UNSPEC)
-			continue;
-
-		err = nfp_abm_ctrl_read_q_stats(alink, i, &stats);
-		if (err)
-			return err;
-
-		nfp_abm_update_stats(&stats, &alink->qdiscs[i].stats,
-				     &opt->stats);
-	}
-
-	return 0;
-}
-
-static int
-nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
-		    struct tc_mq_qopt_offload *opt)
-{
-	switch (opt->command) {
-	case TC_MQ_CREATE:
-		nfp_abm_reset_root(netdev, alink, opt->handle,
-				   alink->total_queues);
-		return 0;
-	case TC_MQ_DESTROY:
-		if (opt->handle == alink->parent)
-			nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
-		return 0;
-	case TC_MQ_STATS:
-		return nfp_abm_mq_stats(alink, opt);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static int
 nfp_abm_setup_tc(struct nfp_app *app, struct net_device *netdev,
 		 enum tc_setup_type type, void *type_data)
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index f907b7d98917..c617d213e406 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -5,6 +5,7 @@
 #define __NFP_ABM_H__ 1
 
 #include <net/devlink.h>
+#include <net/pkt_cls.h>
 
 struct nfp_app;
 struct nfp_net;
@@ -91,6 +92,11 @@ struct nfp_abm_link {
 	struct nfp_red_qdisc *qdiscs;
 };
 
+int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
+			 struct tc_red_qopt_offload *opt);
+int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
+			struct tc_mq_qopt_offload *opt);
+
 void nfp_abm_ctrl_read_params(struct nfp_abm_link *alink);
 int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm);
 int nfp_abm_ctrl_set_all_q_lvls(struct nfp_abm_link *alink, u32 val);
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
new file mode 100644
index 000000000000..f36da95827ee
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2018 Netronome Systems, Inc. */
+
+#include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
+#include <net/red.h>
+
+#include "../nfpcore/nfp_cpp.h"
+#include "../nfp_app.h"
+#include "../nfp_port.h"
+#include "main.h"
+
+static int
+__nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
+		     u32 handle, unsigned int qs, u32 init_val)
+{
+	struct nfp_port *port = nfp_port_from_netdev(netdev);
+	int ret;
+
+	ret = nfp_abm_ctrl_set_all_q_lvls(alink, init_val);
+	memset(alink->qdiscs, 0, sizeof(*alink->qdiscs) * alink->num_qdiscs);
+
+	alink->parent = handle;
+	alink->num_qdiscs = qs;
+	port->tc_offload_cnt = qs;
+
+	return ret;
+}
+
+static void
+nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
+		   u32 handle, unsigned int qs)
+{
+	__nfp_abm_reset_root(netdev, alink, handle, qs, ~0);
+}
+
+static int
+nfp_abm_red_find(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
+{
+	unsigned int i = TC_H_MIN(opt->parent) - 1;
+
+	if (opt->parent == TC_H_ROOT)
+		i = 0;
+	else if (TC_H_MAJ(alink->parent) == TC_H_MAJ(opt->parent))
+		i = TC_H_MIN(opt->parent) - 1;
+	else
+		return -EOPNOTSUPP;
+
+	if (i >= alink->num_qdiscs || opt->handle != alink->qdiscs[i].handle)
+		return -EOPNOTSUPP;
+
+	return i;
+}
+
+static void
+nfp_abm_red_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
+		    u32 handle)
+{
+	unsigned int i;
+
+	for (i = 0; i < alink->num_qdiscs; i++)
+		if (handle == alink->qdiscs[i].handle)
+			break;
+	if (i == alink->num_qdiscs)
+		return;
+
+	if (alink->parent == TC_H_ROOT) {
+		nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
+	} else {
+		nfp_abm_ctrl_set_q_lvl(alink, i, ~0);
+		memset(&alink->qdiscs[i], 0, sizeof(*alink->qdiscs));
+	}
+}
+
+static int
+nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
+		    struct tc_red_qopt_offload *opt)
+{
+	bool existing;
+	int i, err;
+
+	i = nfp_abm_red_find(alink, opt);
+	existing = i >= 0;
+
+	if (opt->set.min != opt->set.max || !opt->set.is_ecn) {
+		nfp_warn(alink->abm->app->cpp,
+			 "RED offload failed - unsupported parameters\n");
+		err = -EINVAL;
+		goto err_destroy;
+	}
+
+	if (existing) {
+		if (alink->parent == TC_H_ROOT)
+			err = nfp_abm_ctrl_set_all_q_lvls(alink, opt->set.min);
+		else
+			err = nfp_abm_ctrl_set_q_lvl(alink, i, opt->set.min);
+		if (err)
+			goto err_destroy;
+		return 0;
+	}
+
+	if (opt->parent == TC_H_ROOT) {
+		i = 0;
+		err = __nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 1,
+					   opt->set.min);
+	} else if (TC_H_MAJ(alink->parent) == TC_H_MAJ(opt->parent)) {
+		i = TC_H_MIN(opt->parent) - 1;
+		err = nfp_abm_ctrl_set_q_lvl(alink, i, opt->set.min);
+	} else {
+		return -EINVAL;
+	}
+	/* Set the handle to try full clean up, in case IO failed */
+	alink->qdiscs[i].handle = opt->handle;
+	if (err)
+		goto err_destroy;
+
+	if (opt->parent == TC_H_ROOT)
+		err = nfp_abm_ctrl_read_stats(alink, &alink->qdiscs[i].stats);
+	else
+		err = nfp_abm_ctrl_read_q_stats(alink, i,
+						&alink->qdiscs[i].stats);
+	if (err)
+		goto err_destroy;
+
+	if (opt->parent == TC_H_ROOT)
+		err = nfp_abm_ctrl_read_xstats(alink,
+					       &alink->qdiscs[i].xstats);
+	else
+		err = nfp_abm_ctrl_read_q_xstats(alink, i,
+						 &alink->qdiscs[i].xstats);
+	if (err)
+		goto err_destroy;
+
+	alink->qdiscs[i].stats.backlog_pkts = 0;
+	alink->qdiscs[i].stats.backlog_bytes = 0;
+
+	return 0;
+err_destroy:
+	/* If the qdisc keeps on living, but we can't offload undo changes */
+	if (existing) {
+		opt->set.qstats->qlen -= alink->qdiscs[i].stats.backlog_pkts;
+		opt->set.qstats->backlog -=
+			alink->qdiscs[i].stats.backlog_bytes;
+	}
+	nfp_abm_red_destroy(netdev, alink, opt->handle);
+
+	return err;
+}
+
+static void
+nfp_abm_update_stats(struct nfp_alink_stats *new, struct nfp_alink_stats *old,
+		     struct tc_qopt_offload_stats *stats)
+{
+	_bstats_update(stats->bstats, new->tx_bytes - old->tx_bytes,
+		       new->tx_pkts - old->tx_pkts);
+	stats->qstats->qlen += new->backlog_pkts - old->backlog_pkts;
+	stats->qstats->backlog += new->backlog_bytes - old->backlog_bytes;
+	stats->qstats->overlimits += new->overlimits - old->overlimits;
+	stats->qstats->drops += new->drops - old->drops;
+}
+
+static int
+nfp_abm_red_stats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
+{
+	struct nfp_alink_stats *prev_stats;
+	struct nfp_alink_stats stats;
+	int i, err;
+
+	i = nfp_abm_red_find(alink, opt);
+	if (i < 0)
+		return i;
+	prev_stats = &alink->qdiscs[i].stats;
+
+	if (alink->parent == TC_H_ROOT)
+		err = nfp_abm_ctrl_read_stats(alink, &stats);
+	else
+		err = nfp_abm_ctrl_read_q_stats(alink, i, &stats);
+	if (err)
+		return err;
+
+	nfp_abm_update_stats(&stats, prev_stats, &opt->stats);
+
+	*prev_stats = stats;
+
+	return 0;
+}
+
+static int
+nfp_abm_red_xstats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
+{
+	struct nfp_alink_xstats *prev_xstats;
+	struct nfp_alink_xstats xstats;
+	int i, err;
+
+	i = nfp_abm_red_find(alink, opt);
+	if (i < 0)
+		return i;
+	prev_xstats = &alink->qdiscs[i].xstats;
+
+	if (alink->parent == TC_H_ROOT)
+		err = nfp_abm_ctrl_read_xstats(alink, &xstats);
+	else
+		err = nfp_abm_ctrl_read_q_xstats(alink, i, &xstats);
+	if (err)
+		return err;
+
+	opt->xstats->forced_mark += xstats.ecn_marked - prev_xstats->ecn_marked;
+	opt->xstats->pdrop += xstats.pdrop - prev_xstats->pdrop;
+
+	*prev_xstats = xstats;
+
+	return 0;
+}
+
+int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
+			 struct tc_red_qopt_offload *opt)
+{
+	switch (opt->command) {
+	case TC_RED_REPLACE:
+		return nfp_abm_red_replace(netdev, alink, opt);
+	case TC_RED_DESTROY:
+		nfp_abm_red_destroy(netdev, alink, opt->handle);
+		return 0;
+	case TC_RED_STATS:
+		return nfp_abm_red_stats(alink, opt);
+	case TC_RED_XSTATS:
+		return nfp_abm_red_xstats(alink, opt);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+nfp_abm_mq_stats(struct nfp_abm_link *alink, struct tc_mq_qopt_offload *opt)
+{
+	struct nfp_alink_stats stats;
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < alink->num_qdiscs; i++) {
+		if (alink->qdiscs[i].handle == TC_H_UNSPEC)
+			continue;
+
+		err = nfp_abm_ctrl_read_q_stats(alink, i, &stats);
+		if (err)
+			return err;
+
+		nfp_abm_update_stats(&stats, &alink->qdiscs[i].stats,
+				     &opt->stats);
+	}
+
+	return 0;
+}
+
+int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
+			struct tc_mq_qopt_offload *opt)
+{
+	switch (opt->command) {
+	case TC_MQ_CREATE:
+		nfp_abm_reset_root(netdev, alink, opt->handle,
+				   alink->total_queues);
+		return 0;
+	case TC_MQ_DESTROY:
+		if (opt->handle == alink->parent)
+			nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
+		return 0;
+	case TC_MQ_STATS:
+		return nfp_abm_mq_stats(alink, opt);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
-- 
cgit v1.2.3


From e38f5d11b98fa65a23301c28567bd786e4a97e75 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 8 Nov 2018 19:50:34 -0800
Subject: nfp: pass ctrl_bar pointer to nfp_net_alloc

Move setting ctrl_bar pointer to the nfp_net_alloc function,
to make sure we can parse capabilities early in the following
patch.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net.h        | 2 +-
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 8 +++++---
 drivers/net/ethernet/netronome/nfp/nfp_net_main.c   | 4 ++--
 drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c | 3 +--
 4 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 6f0c37d09256..dda02fefc806 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -851,7 +851,7 @@ void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver,
 			    void __iomem *ctrl_bar);
 
 struct nfp_net *
-nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
+nfp_net_alloc(struct pci_dev *pdev, void __iomem *ctrl_bar, bool needs_netdev,
 	      unsigned int max_tx_rings, unsigned int max_rx_rings);
 void nfp_net_free(struct nfp_net *nn);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 6bddfcfdec34..54ce8353715f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3560,6 +3560,7 @@ void nfp_net_info(struct nfp_net *nn)
 /**
  * nfp_net_alloc() - Allocate netdev and related structure
  * @pdev:         PCI device
+ * @ctrl_bar:     PCI IOMEM with vNIC config memory
  * @needs_netdev: Whether to allocate a netdev for this vNIC
  * @max_tx_rings: Maximum number of TX rings supported by device
  * @max_rx_rings: Maximum number of RX rings supported by device
@@ -3570,9 +3571,9 @@ void nfp_net_info(struct nfp_net *nn)
  *
  * Return: NFP Net device structure, or ERR_PTR on error.
  */
-struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
-			      unsigned int max_tx_rings,
-			      unsigned int max_rx_rings)
+struct nfp_net *
+nfp_net_alloc(struct pci_dev *pdev, void __iomem *ctrl_bar, bool needs_netdev,
+	      unsigned int max_tx_rings, unsigned int max_rx_rings)
 {
 	struct nfp_net *nn;
 
@@ -3594,6 +3595,7 @@ struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
 	}
 
 	nn->dp.dev = &pdev->dev;
+	nn->dp.ctrl_bar = ctrl_bar;
 	nn->pdev = pdev;
 
 	nn->max_tx_rings = max_tx_rings;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
index 1e7d20468a34..08f5fdbd8e41 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
@@ -116,13 +116,13 @@ nfp_net_pf_alloc_vnic(struct nfp_pf *pf, bool needs_netdev,
 	n_rx_rings = readl(ctrl_bar + NFP_NET_CFG_MAX_RXRINGS);
 
 	/* Allocate and initialise the vNIC */
-	nn = nfp_net_alloc(pf->pdev, needs_netdev, n_tx_rings, n_rx_rings);
+	nn = nfp_net_alloc(pf->pdev, ctrl_bar, needs_netdev,
+			   n_tx_rings, n_rx_rings);
 	if (IS_ERR(nn))
 		return nn;
 
 	nn->app = pf->app;
 	nfp_net_get_fw_version(&nn->fw_ver, ctrl_bar);
-	nn->dp.ctrl_bar = ctrl_bar;
 	nn->tx_bar = qc_bar + tx_base * NFP_QCP_QUEUE_ADDR_SZ;
 	nn->rx_bar = qc_bar + rx_base * NFP_QCP_QUEUE_ADDR_SZ;
 	nn->dp.is_vf = 0;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
index d2c1e9ea5668..1145849ca7ba 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
@@ -172,7 +172,7 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	rx_bar_off = NFP_PCIE_QUEUE(startq);
 
 	/* Allocate and initialise the netdev */
-	nn = nfp_net_alloc(pdev, true, max_tx_rings, max_rx_rings);
+	nn = nfp_net_alloc(pdev, ctrl_bar, true, max_tx_rings, max_rx_rings);
 	if (IS_ERR(nn)) {
 		err = PTR_ERR(nn);
 		goto err_ctrl_unmap;
@@ -180,7 +180,6 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	vf->nn = nn;
 
 	nn->fw_ver = fw_ver;
-	nn->dp.ctrl_bar = ctrl_bar;
 	nn->dp.is_vf = 1;
 	nn->stride_tx = stride;
 	nn->stride_rx = stride;
-- 
cgit v1.2.3


From 83ec8857a00ff11cb3abc4d7c003de8ea103b715 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 8 Nov 2018 19:50:35 -0800
Subject: nfp: parse vNIC TLV capabilities at alloc time

In certain cases initialization logic which follows allocation of
the vNIC structure may want to validate the capabilities of that vNIC.
This is easy before vNIC is initialized for normal capabilities which
are at fixed offsets in control memory, easy to locate and read, but
poses a challenge if the capabilities are in form of TLVs.  Parse
the TLVs early on so other code can just access parsed info, instead
of having to do the parsing by itself.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 54ce8353715f..e00d5a2a41ee 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3576,6 +3576,7 @@ nfp_net_alloc(struct pci_dev *pdev, void __iomem *ctrl_bar, bool needs_netdev,
 	      unsigned int max_tx_rings, unsigned int max_rx_rings)
 {
 	struct nfp_net *nn;
+	int err;
 
 	if (needs_netdev) {
 		struct net_device *netdev;
@@ -3618,7 +3619,19 @@ nfp_net_alloc(struct pci_dev *pdev, void __iomem *ctrl_bar, bool needs_netdev,
 
 	timer_setup(&nn->reconfig_timer, nfp_net_reconfig_timer, 0);
 
+	err = nfp_net_tlv_caps_parse(&nn->pdev->dev, nn->dp.ctrl_bar,
+				     &nn->tlv_caps);
+	if (err)
+		goto err_free_nn;
+
 	return nn;
+
+err_free_nn:
+	if (nn->dp.netdev)
+		free_netdev(nn->dp.netdev);
+	else
+		vfree(nn);
+	return ERR_PTR(err);
 }
 
 /**
@@ -3891,11 +3904,6 @@ int nfp_net_init(struct nfp_net *nn)
 		nn->dp.ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
 	}
 
-	err = nfp_net_tlv_caps_parse(&nn->pdev->dev, nn->dp.ctrl_bar,
-				     &nn->tlv_caps);
-	if (err)
-		return err;
-
 	if (nn->dp.netdev)
 		nfp_net_netdev_init(nn);
 
-- 
cgit v1.2.3


From 032748acf616c250aa195c92715ba89e136c61fe Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 8 Nov 2018 19:50:36 -0800
Subject: nfp: abm: provide more precise info about offload parameter
 validation

Improve log messages printed when RED can't be offloaded because
of Qdisc parameters.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index f36da95827ee..04b91cc12434 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -72,6 +72,26 @@ nfp_abm_red_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
 	}
 }
 
+static bool
+nfp_abm_red_check_params(struct nfp_abm_link *alink,
+			 struct tc_red_qopt_offload *opt)
+{
+	struct nfp_cpp *cpp = alink->abm->app->cpp;
+
+	if (!opt->set.is_ecn) {
+		nfp_warn(cpp, "RED offload failed - drop is not supported (ECN option required) (p:%08x h:%08x)\n",
+			 opt->parent, opt->handle);
+		return false;
+	}
+	if (opt->set.min != opt->set.max) {
+		nfp_warn(cpp, "RED offload failed - unsupported min/max parameters (p:%08x h:%08x)\n",
+			 opt->parent, opt->handle);
+		return false;
+	}
+
+	return true;
+}
+
 static int
 nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 		    struct tc_red_qopt_offload *opt)
@@ -82,9 +102,7 @@ nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 	i = nfp_abm_red_find(alink, opt);
 	existing = i >= 0;
 
-	if (opt->set.min != opt->set.max || !opt->set.is_ecn) {
-		nfp_warn(alink->abm->app->cpp,
-			 "RED offload failed - unsupported parameters\n");
+	if (!nfp_abm_red_check_params(alink, opt)) {
 		err = -EINVAL;
 		goto err_destroy;
 	}
-- 
cgit v1.2.3


From cae5f48e3234dda5bab6f7f361b5eff6d4cc77b2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 8 Nov 2018 19:50:37 -0800
Subject: nfp: abm: don't set negative threshold

Turns out the threshold value is used in signed compares in the FW,
so we should avoid setting the top bit.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.h  |  3 +++
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 10 ++++++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index c617d213e406..3774c063e419 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -4,9 +4,12 @@
 #ifndef __NFP_ABM_H__
 #define __NFP_ABM_H__ 1
 
+#include <linux/bits.h>
 #include <net/devlink.h>
 #include <net/pkt_cls.h>
 
+#define NFP_ABM_LVL_INFINITY		S32_MAX
+
 struct nfp_app;
 struct nfp_net;
 
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index 04b91cc12434..979afb3ea855 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -31,7 +31,7 @@ static void
 nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
 		   u32 handle, unsigned int qs)
 {
-	__nfp_abm_reset_root(netdev, alink, handle, qs, ~0);
+	__nfp_abm_reset_root(netdev, alink, handle, qs, NFP_ABM_LVL_INFINITY);
 }
 
 static int
@@ -67,7 +67,7 @@ nfp_abm_red_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
 	if (alink->parent == TC_H_ROOT) {
 		nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
 	} else {
-		nfp_abm_ctrl_set_q_lvl(alink, i, ~0);
+		nfp_abm_ctrl_set_q_lvl(alink, i, NFP_ABM_LVL_INFINITY);
 		memset(&alink->qdiscs[i], 0, sizeof(*alink->qdiscs));
 	}
 }
@@ -88,6 +88,12 @@ nfp_abm_red_check_params(struct nfp_abm_link *alink,
 			 opt->parent, opt->handle);
 		return false;
 	}
+	if (opt->set.min > NFP_ABM_LVL_INFINITY) {
+		nfp_warn(cpp, "RED offload failed - threshold too large %d > %d (p:%08x h:%08x)\n",
+			 opt->set.min, NFP_ABM_LVL_INFINITY, opt->parent,
+			 opt->handle);
+		return false;
+	}
 
 	return true;
 }
-- 
cgit v1.2.3


From 190852a55edbe138503259ea1bb40c08be221d75 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 8 Nov 2018 19:50:38 -0800
Subject: net: sched: red: inform offloads about harddrop setting

To mirror software behaviour on offload more precisely inform
the drivers about the state of the harddrop flag.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h | 1 +
 net/sched/sch_red.c   | 1 +
 2 files changed, 2 insertions(+)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 72ffb3120ced..00f71644fbcd 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -807,6 +807,7 @@ struct tc_red_qopt_offload_params {
 	u32 max;
 	u32 probability;
 	bool is_ecn;
+	bool is_harddrop;
 	struct gnet_stats_queue *qstats;
 };
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 7682f7a618a1..a1d08bdd9357 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -167,6 +167,7 @@ static int red_offload(struct Qdisc *sch, bool enable)
 		opt.set.max = q->parms.qth_max >> q->parms.Wlog;
 		opt.set.probability = q->parms.max_P;
 		opt.set.is_ecn = red_use_ecn(q);
+		opt.set.is_harddrop = red_use_harddrop(q);
 		opt.set.qstats = &sch->qstats;
 	} else {
 		opt.command = TC_RED_DESTROY;
-- 
cgit v1.2.3


From 6e5a716f424b1020fc8cf52b0ab4a1551e952733 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 8 Nov 2018 19:50:39 -0800
Subject: nfp: abm: refuse RED offload with harddrop set

RED Qdisc will now inform the drivers about the state of the harddrop
flag.  Refuse to offload in case harddrop is set.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index 979afb3ea855..bb05f9ee0401 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -83,6 +83,11 @@ nfp_abm_red_check_params(struct nfp_abm_link *alink,
 			 opt->parent, opt->handle);
 		return false;
 	}
+	if (opt->set.is_harddrop) {
+		nfp_warn(cpp, "RED offload failed - harddrop is not supported (p:%08x h:%08x)\n",
+			 opt->parent, opt->handle);
+		return false;
+	}
 	if (opt->set.min != opt->set.max) {
 		nfp_warn(cpp, "RED offload failed - unsupported min/max parameters (p:%08x h:%08x)\n",
 			 opt->parent, opt->handle);
-- 
cgit v1.2.3


From e647815a4d3b3be9d85b5750ed0f2947fd78fac7 Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Thu, 8 Nov 2018 04:08:42 -0500
Subject: bpf: let verifier to calculate and record max_pkt_offset

In check_packet_access, update max_pkt_offset after the offset has passed
__check_packet_access.

It should be safe to use u32 for max_pkt_offset as explained in code
comment.

Also, when there is tail call, the max_pkt_offset of the called program is
unknown, so conservatively set max_pkt_offset to MAX_PACKET_OFF for such
case.

Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h   |  1 +
 kernel/bpf/verifier.c | 12 ++++++++++++
 2 files changed, 13 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 33014ae73103..b6a296e01f6a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -293,6 +293,7 @@ struct bpf_prog_aux {
 	atomic_t refcnt;
 	u32 used_map_cnt;
 	u32 max_ctx_offset;
+	u32 max_pkt_offset;
 	u32 stack_depth;
 	u32 id;
 	u32 func_cnt;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1971ca325fb4..75dab40b19a3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1455,6 +1455,17 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
 		verbose(env, "R%d offset is outside of the packet\n", regno);
 		return err;
 	}
+
+	/* __check_packet_access has made sure "off + size - 1" is within u16.
+	 * reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff,
+	 * otherwise find_good_pkt_pointers would have refused to set range info
+	 * that __check_packet_access would have rejected this pkt access.
+	 * Therefore, "off + reg->umax_value + size - 1" won't overflow u32.
+	 */
+	env->prog->aux->max_pkt_offset =
+		max_t(u32, env->prog->aux->max_pkt_offset,
+		      off + reg->umax_value + size - 1);
+
 	return err;
 }
 
@@ -6138,6 +6149,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			 */
 			prog->cb_access = 1;
 			env->prog->aux->stack_depth = MAX_BPF_STACK;
+			env->prog->aux->max_pkt_offset = MAX_PACKET_OFF;
 
 			/* mark bpf_tail_call as different opcode to avoid
 			 * conditional branch in the interpeter for every normal
-- 
cgit v1.2.3


From cf599f50311dd4a5d3b5fc427beb9303dfa6be4b Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Thu, 8 Nov 2018 04:08:43 -0500
Subject: nfp: bpf: relax prog rejection through max_pkt_offset

NFP is refusing to offload programs whenever the MTU is set to a value
larger than the max packet bytes that fits in NFP Cluster Target Memory
(CTM). However, a eBPF program doesn't always need to access the whole
packet data.

Verifier has always calculated maximum direct packet access (DPA) offset,
and kept it in max_pkt_offset inside prog auxiliar information. This patch
relax prog rejection based on max_pkt_offset.

Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index ba8ceedcf6a2..07bdc1f61996 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -489,14 +489,15 @@ nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog,
 		 struct netlink_ext_ack *extack)
 {
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
-	unsigned int max_mtu, max_stack, max_prog_len;
+	unsigned int fw_mtu, pkt_off, max_stack, max_prog_len;
 	dma_addr_t dma_addr;
 	void *img;
 	int err;
 
-	max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
-	if (max_mtu < nn->dp.netdev->mtu) {
-		NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with MTU larger than HW packet split boundary");
+	fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
+	pkt_off = min(prog->aux->max_pkt_offset, nn->dp.netdev->mtu);
+	if (fw_mtu < pkt_off) {
+		NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with potential packet access beyond HW packet split boundary");
 		return -EOPNOTSUPP;
 	}
 
-- 
cgit v1.2.3


From a5a3a828cd00788a78da686c57c6d1f66191d8af Mon Sep 17 00:00:00 2001
From: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Date: Wed, 7 Nov 2018 16:12:01 -0800
Subject: bpf: add perf event notificaton support for sock_ops

This patch allows eBPF programs that use sock_ops to send perf
based event notifications using bpf_perf_event_output(). Our main
use case for this is the following:

  We would like to monitor some subset of TCP sockets in user-space,
  (the monitoring application would define 4-tuples it wants to monitor)
  using TCP_INFO stats to analyze reported problems. The idea is to
  use those stats to see where the bottlenecks are likely to be ("is
  it application-limited?" or "is there evidence of BufferBloat in
  the path?" etc).

  Today we can do this by periodically polling for tcp_info, but this
  could be made more efficient if the kernel would asynchronously
  notify the application via tcp_info when some "interesting"
  thresholds (e.g., "RTT variance > X", or "total_retrans > Y" etc)
  are reached. And to make this effective, it is better if
  we could apply the threshold check *before* constructing the
  tcp_info netlink notification, so that we don't waste resources
  constructing notifications that will be discarded by the filter.

This work solves the problem by adding perf event based notification
support for sock_ops. The eBPF program can thus be designed to apply
any desired filters to the bpf_sock_ops and trigger a perf event
notification based on the evaluation from the filter. The user space
component can use these perf event notifications to either read any
state managed by the eBPF program, or issue a TCP_INFO netlink call
if desired.

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/core/filter.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index e521c5ebc7d1..ba97a6bee6f9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3908,6 +3908,26 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_5(bpf_sockopt_event_output, struct bpf_sock_ops_kern *, bpf_sock,
+	   struct bpf_map *, map, u64, flags, void *, data, u64, size)
+{
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+		return -EINVAL;
+
+	return bpf_event_output(map, flags, data, size, NULL, 0, NULL);
+}
+
+static const struct bpf_func_proto bpf_sockopt_event_output_proto =  {
+	.func		= bpf_sockopt_event_output,
+	.gpl_only       = true,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
+	.arg3_type      = ARG_ANYTHING,
+	.arg4_type      = ARG_PTR_TO_MEM,
+	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
+};
+
 BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
@@ -5240,6 +5260,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_socket_cookie_sock_ops_proto;
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_sockopt_event_output_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
-- 
cgit v1.2.3


From 435f90a338ae42c0d7c0109a1742d1b16bc99bf6 Mon Sep 17 00:00:00 2001
From: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Date: Wed, 7 Nov 2018 16:12:02 -0800
Subject: selftests/bpf: add a test case for sock_ops perf-event notification

This patch provides a tcp_bpf based eBPF sample. The test

- ncat(1) as the TCP client program to connect() to a port
  with the intention of triggerring SYN retransmissions: we
  first install an iptables DROP rule to make sure ncat SYNs are
  resent (instead of aborting instantly after a TCP RST)

- has a bpf kernel module that sends a perf-event notification for
  each TCP retransmit, and also tracks the number of such notifications
  sent in the global_map

The test passes when the number of event notifications intercepted
in user-space matches the value in the global_map.

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile              |   4 +-
 tools/testing/selftests/bpf/test_tcpnotify.h      |  19 +++
 tools/testing/selftests/bpf/test_tcpnotify_kern.c |  95 +++++++++++
 tools/testing/selftests/bpf/test_tcpnotify_user.c | 186 ++++++++++++++++++++++
 4 files changed, 303 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/test_tcpnotify.h
 create mode 100644 tools/testing/selftests/bpf/test_tcpnotify_kern.c
 create mode 100644 tools/testing/selftests/bpf/test_tcpnotify_user.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index ecd79b7fb107..57b4712a6276 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -24,12 +24,13 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
 	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \
-	test_netcnt
+	test_netcnt test_tcpnotify_user
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
 	sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
 	test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
+	test_tcpnotify_kern.o \
 	sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
 	sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
 	test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
@@ -74,6 +75,7 @@ $(OUTPUT)/test_sock_addr: cgroup_helpers.c
 $(OUTPUT)/test_socket_cookie: cgroup_helpers.c
 $(OUTPUT)/test_sockmap: cgroup_helpers.c
 $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
+$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
diff --git a/tools/testing/selftests/bpf/test_tcpnotify.h b/tools/testing/selftests/bpf/test_tcpnotify.h
new file mode 100644
index 000000000000..8b6cea030bfc
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify.h
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _TEST_TCPBPF_H
+#define _TEST_TCPBPF_H
+
+struct tcpnotify_globals {
+	__u32 total_retrans;
+	__u32 ncalls;
+};
+
+struct tcp_notifier {
+	__u8    type;
+	__u8    subtype;
+	__u8    source;
+	__u8    hash;
+};
+
+#define	TESTPORT	12877
+#endif
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/test_tcpnotify_kern.c
new file mode 100644
index 000000000000..edbca203ce2d
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify_kern.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/tcp.h>
+#include <netinet/in.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+#include "test_tcpnotify.h"
+
+struct bpf_map_def SEC("maps") global_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct tcpnotify_globals),
+	.max_entries = 4,
+};
+
+struct bpf_map_def SEC("maps") perf_event_map = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(__u32),
+	.max_entries = 2,
+};
+
+int _version SEC("version") = 1;
+
+SEC("sockops")
+int bpf_testcb(struct bpf_sock_ops *skops)
+{
+	int rv = -1;
+	int op;
+
+	op = (int) skops->op;
+
+	if (bpf_ntohl(skops->remote_port) != TESTPORT) {
+		skops->reply = -1;
+		return 0;
+	}
+
+	switch (op) {
+	case BPF_SOCK_OPS_TIMEOUT_INIT:
+	case BPF_SOCK_OPS_RWND_INIT:
+	case BPF_SOCK_OPS_NEEDS_ECN:
+	case BPF_SOCK_OPS_BASE_RTT:
+	case BPF_SOCK_OPS_RTO_CB:
+		rv = 1;
+		break;
+
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+	case BPF_SOCK_OPS_TCP_LISTEN_CB:
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		bpf_sock_ops_cb_flags_set(skops, (BPF_SOCK_OPS_RETRANS_CB_FLAG|
+					  BPF_SOCK_OPS_RTO_CB_FLAG));
+		rv = 1;
+		break;
+	case BPF_SOCK_OPS_RETRANS_CB: {
+			__u32 key = 0;
+			struct tcpnotify_globals g, *gp;
+			struct tcp_notifier msg = {
+				.type = 0xde,
+				.subtype = 0xad,
+				.source = 0xbe,
+				.hash = 0xef,
+			};
+
+			rv = 1;
+
+			/* Update results */
+			gp = bpf_map_lookup_elem(&global_map, &key);
+			if (!gp)
+				break;
+			g = *gp;
+			g.total_retrans = skops->total_retrans;
+			g.ncalls++;
+			bpf_map_update_elem(&global_map, &key, &g,
+					    BPF_ANY);
+			bpf_perf_event_output(skops, &perf_event_map,
+					      BPF_F_CURRENT_CPU,
+					      &msg, sizeof(msg));
+		}
+		break;
+	default:
+		rv = -1;
+	}
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c
new file mode 100644
index 000000000000..ff3c4522aed6
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <asm/types.h>
+#include <sys/syscall.h>
+#include <errno.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <sys/socket.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <sys/ioctl.h>
+#include <linux/rtnetlink.h>
+#include <signal.h>
+#include <linux/perf_event.h>
+
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
+#include "test_tcpnotify.h"
+#include "trace_helpers.h"
+
+#define SOCKET_BUFFER_SIZE (getpagesize() < 8192L ? getpagesize() : 8192L)
+
+pthread_t tid;
+int rx_callbacks;
+
+static int dummyfn(void *data, int size)
+{
+	struct tcp_notifier *t = data;
+
+	if (t->type != 0xde || t->subtype != 0xad ||
+	    t->source != 0xbe || t->hash != 0xef)
+		return 1;
+	rx_callbacks++;
+	return 0;
+}
+
+void tcp_notifier_poller(int fd)
+{
+	while (1)
+		perf_event_poller(fd, dummyfn);
+}
+
+static void *poller_thread(void *arg)
+{
+	int fd = *(int *)arg;
+
+	tcp_notifier_poller(fd);
+	return arg;
+}
+
+int verify_result(const struct tcpnotify_globals *result)
+{
+	return (result->ncalls > 0 && result->ncalls == rx_callbacks ? 0 : 1);
+}
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+			const char *name)
+{
+	struct bpf_map *map;
+
+	map = bpf_object__find_map_by_name(obj, name);
+	if (!map) {
+		printf("%s:FAIL:map '%s' not found\n", test, name);
+		return -1;
+	}
+	return bpf_map__fd(map);
+}
+
+static int setup_bpf_perf_event(int mapfd)
+{
+	struct perf_event_attr attr = {
+		.sample_type = PERF_SAMPLE_RAW,
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_BPF_OUTPUT,
+	};
+	int key = 0;
+	int pmu_fd;
+
+	pmu_fd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, 0);
+	if (pmu_fd < 0)
+		return pmu_fd;
+	bpf_map_update_elem(mapfd, &key, &pmu_fd, BPF_ANY);
+
+	ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+	return pmu_fd;
+}
+
+int main(int argc, char **argv)
+{
+	const char *file = "test_tcpnotify_kern.o";
+	int prog_fd, map_fd, perf_event_fd;
+	struct tcpnotify_globals g = {0};
+	const char *cg_path = "/foo";
+	int error = EXIT_FAILURE;
+	struct bpf_object *obj;
+	int cg_fd = -1;
+	__u32 key = 0;
+	int rv;
+	char test_script[80];
+	int pmu_fd;
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset);
+
+	if (setup_cgroup_environment())
+		goto err;
+
+	cg_fd = create_and_get_cgroup(cg_path);
+	if (!cg_fd)
+		goto err;
+
+	if (join_cgroup(cg_path))
+		goto err;
+
+	if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
+		printf("FAILED: load_bpf_file failed for: %s\n", file);
+		goto err;
+	}
+
+	rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+	if (rv) {
+		printf("FAILED: bpf_prog_attach: %d (%s)\n",
+		       error, strerror(errno));
+		goto err;
+	}
+
+	perf_event_fd = bpf_find_map(__func__, obj, "perf_event_map");
+	if (perf_event_fd < 0)
+		goto err;
+
+	map_fd = bpf_find_map(__func__, obj, "global_map");
+	if (map_fd < 0)
+		goto err;
+
+	pmu_fd = setup_bpf_perf_event(perf_event_fd);
+	if (pmu_fd < 0 || perf_event_mmap(pmu_fd) < 0)
+		goto err;
+
+	pthread_create(&tid, NULL, poller_thread, (void *)&pmu_fd);
+
+	sprintf(test_script,
+		"/usr/sbin/iptables -A INPUT -p tcp --dport %d -j DROP",
+		TESTPORT);
+	system(test_script);
+
+	sprintf(test_script,
+		"/usr/bin/nc 127.0.0.1 %d < /etc/passwd > /dev/null 2>&1 ",
+		TESTPORT);
+	system(test_script);
+
+	sprintf(test_script,
+		"/usr/sbin/iptables -D INPUT -p tcp --dport %d -j DROP",
+		TESTPORT);
+	system(test_script);
+
+	rv = bpf_map_lookup_elem(map_fd, &key, &g);
+	if (rv != 0) {
+		printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
+		goto err;
+	}
+
+	sleep(10);
+
+	if (verify_result(&g)) {
+		printf("FAILED: Wrong stats Expected %d calls, got %d\n",
+			g.ncalls, rx_callbacks);
+		goto err;
+	}
+
+	printf("PASSED!\n");
+	error = 0;
+err:
+	bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+	close(cg_fd);
+	cleanup_cgroup_environment();
+	return error;
+}
-- 
cgit v1.2.3


From bf598a8f0f771302d4ecb0ef0003c54732221597 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 8 Nov 2018 13:00:07 -0800
Subject: bpftool: Improve handling of ENOENT on map dumps

bpftool output is not user friendly when dumping a map with only a few
populated entries:

    $ bpftool map
    1: devmap  name tx_devmap  flags 0x0
            key 4B  value 4B  max_entries 64  memlock 4096B
    2: array  name tx_idxmap  flags 0x0
            key 4B  value 4B  max_entries 64  memlock 4096B

    $ bpftool map dump id 1
    key:
    00 00 00 00
    value:
    No such file or directory
    key:
    01 00 00 00
    value:
    No such file or directory
    key:
    02 00 00 00
    value:
    No such file or directory
    key: 03 00 00 00  value: 03 00 00 00

Handle ENOENT by keeping the line format sane and dumping
"<no entry>" for the value

    $ bpftool map dump id 1
    key: 00 00 00 00  value: <no entry>
    key: 01 00 00 00  value: <no entry>
    key: 02 00 00 00  value: <no entry>
    key: 03 00 00 00  value: 03 00 00 00
    ...

Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/map.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 101b8a881225..dc9a8967ab8c 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -383,7 +383,10 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 		printf(single_line ? "  " : "\n");
 
 		printf("value:%c", break_names ? '\n' : ' ');
-		fprint_hex(stdout, value, info->value_size, " ");
+		if (value)
+			fprint_hex(stdout, value, info->value_size, " ");
+		else
+			printf("<no entry>");
 
 		printf("\n");
 	} else {
@@ -398,8 +401,11 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 		for (i = 0; i < n; i++) {
 			printf("value (CPU %02d):%c",
 			       i, info->value_size > 16 ? '\n' : ' ');
-			fprint_hex(stdout, value + i * step,
-				   info->value_size, " ");
+			if (value)
+				fprint_hex(stdout, value + i * step,
+					   info->value_size, " ");
+			else
+				printf("<no entry>");
 			printf("\n");
 		}
 	}
@@ -731,7 +737,11 @@ static int dump_map_elem(int fd, void *key, void *value,
 		jsonw_string_field(json_wtr, "error", strerror(lookup_errno));
 		jsonw_end_object(json_wtr);
 	} else {
-		print_entry_error(map_info, key, strerror(lookup_errno));
+		if (errno == ENOENT)
+			print_entry_plain(map_info, key, NULL);
+		else
+			print_entry_error(map_info, key,
+					  strerror(lookup_errno));
 	}
 
 	return 0;
-- 
cgit v1.2.3


From c8123ead13a5c92dc5fd15c0fdfe88eef41e6ac1 Mon Sep 17 00:00:00 2001
From: Nitin Hande <nitin.hande@gmail.com>
Date: Sun, 28 Oct 2018 21:02:45 -0700
Subject: bpf: Extend the sk_lookup() helper to XDP hookpoint.

This patch proposes to extend the sk_lookup() BPF API to the
XDP hookpoint. The sk_lookup() helper supports a lookup
on incoming packet to find the corresponding socket that will
receive this packet. Current support for this BPF API is
at the tc hookpoint. This patch will extend this API at XDP
hookpoint. A XDP program can map the incoming packet to the
5-tuple parameter and invoke the API to find the corresponding
socket structure.

Signed-off-by: Nitin Hande <Nitin.Hande@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h |   4 ++
 net/core/filter.c        | 105 ++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 90 insertions(+), 19 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 852dc17ab47a..47d606d744cc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2201,6 +2201,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, *struct bpf_sock*
+ *		return is from reuse->socks[] using hash of the packet.
  *
  * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
  *	Description
@@ -2233,6 +2235,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, *struct bpf_sock*
+ *		return is from reuse->socks[] using hash of the packet.
  *
  * int bpf_sk_release(struct bpf_sock *sk)
  *	Description
diff --git a/net/core/filter.c b/net/core/filter.c
index ba97a6bee6f9..53d50fb75ea1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4845,38 +4845,32 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
 
 #ifdef CONFIG_INET
 static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
-			      struct sk_buff *skb, u8 family, u8 proto)
+			      int dif, int sdif, u8 family, u8 proto)
 {
 	bool refcounted = false;
 	struct sock *sk = NULL;
-	int dif = 0;
-
-	if (skb->dev)
-		dif = skb->dev->ifindex;
 
 	if (family == AF_INET) {
 		__be32 src4 = tuple->ipv4.saddr;
 		__be32 dst4 = tuple->ipv4.daddr;
-		int sdif = inet_sdif(skb);
 
 		if (proto == IPPROTO_TCP)
-			sk = __inet_lookup(net, &tcp_hashinfo, skb, 0,
+			sk = __inet_lookup(net, &tcp_hashinfo, NULL, 0,
 					   src4, tuple->ipv4.sport,
 					   dst4, tuple->ipv4.dport,
 					   dif, sdif, &refcounted);
 		else
 			sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport,
 					       dst4, tuple->ipv4.dport,
-					       dif, sdif, &udp_table, skb);
+					       dif, sdif, &udp_table, NULL);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
 		struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
 		struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
 		u16 hnum = ntohs(tuple->ipv6.dport);
-		int sdif = inet6_sdif(skb);
 
 		if (proto == IPPROTO_TCP)
-			sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
+			sk = __inet6_lookup(net, &tcp_hashinfo, NULL, 0,
 					    src6, tuple->ipv6.sport,
 					    dst6, hnum,
 					    dif, sdif, &refcounted);
@@ -4885,7 +4879,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 							    src6, tuple->ipv6.sport,
 							    dst6, hnum,
 							    dif, sdif,
-							    &udp_table, skb);
+							    &udp_table, NULL);
 #endif
 	}
 
@@ -4902,31 +4896,33 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
  * callers to satisfy BPF_CALL declarations.
  */
 static unsigned long
-bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
-	      u8 proto, u64 netns_id, u64 flags)
+__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+		struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
+		u64 flags)
 {
-	struct net *caller_net;
 	struct sock *sk = NULL;
 	u8 family = AF_UNSPEC;
 	struct net *net;
+	int sdif;
 
 	family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6;
 	if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags))
 		goto out;
 
-	if (skb->dev)
-		caller_net = dev_net(skb->dev);
+	if (family == AF_INET)
+		sdif = inet_sdif(skb);
 	else
-		caller_net = sock_net(skb->sk);
+		sdif = inet6_sdif(skb);
+
 	if (netns_id) {
 		net = get_net_ns_by_id(caller_net, netns_id);
 		if (unlikely(!net))
 			goto out;
-		sk = sk_lookup(net, tuple, skb, family, proto);
+		sk = sk_lookup(net, tuple, ifindex, sdif, family, proto);
 		put_net(net);
 	} else {
 		net = caller_net;
-		sk = sk_lookup(net, tuple, skb, family, proto);
+		sk = sk_lookup(net, tuple, ifindex, sdif, family, proto);
 	}
 
 	if (sk)
@@ -4935,6 +4931,25 @@ out:
 	return (unsigned long) sk;
 }
 
+static unsigned long
+bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+	      u8 proto, u64 netns_id, u64 flags)
+{
+	struct net *caller_net;
+	int ifindex;
+
+	if (skb->dev) {
+		caller_net = dev_net(skb->dev);
+		ifindex = skb->dev->ifindex;
+	} else {
+		caller_net = sock_net(skb->sk);
+		ifindex = 0;
+	}
+
+	return __bpf_sk_lookup(skb, tuple, len, caller_net, ifindex,
+			      proto, netns_id, flags);
+}
+
 BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
@@ -4984,6 +4999,50 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_SOCKET,
 };
+
+BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
+	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
+{
+	struct net *caller_net = dev_net(ctx->rxq->dev);
+	int ifindex = ctx->rxq->dev->ifindex;
+
+	return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
+			      IPPROTO_UDP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
+	.func           = bpf_xdp_sk_lookup_udp,
+	.gpl_only       = false,
+	.pkt_access     = true,
+	.ret_type       = RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_PTR_TO_MEM,
+	.arg3_type      = ARG_CONST_SIZE,
+	.arg4_type      = ARG_ANYTHING,
+	.arg5_type      = ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx,
+	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
+{
+	struct net *caller_net = dev_net(ctx->rxq->dev);
+	int ifindex = ctx->rxq->dev->ifindex;
+
+	return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
+			      IPPROTO_TCP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
+	.func           = bpf_xdp_sk_lookup_tcp,
+	.gpl_only       = false,
+	.pkt_access     = true,
+	.ret_type       = RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_PTR_TO_MEM,
+	.arg3_type      = ARG_CONST_SIZE,
+	.arg4_type      = ARG_ANYTHING,
+	.arg5_type      = ARG_ANYTHING,
+};
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -5234,6 +5293,14 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_adjust_tail_proto;
 	case BPF_FUNC_fib_lookup:
 		return &bpf_xdp_fib_lookup_proto;
+#ifdef CONFIG_INET
+	case BPF_FUNC_sk_lookup_udp:
+		return &bpf_xdp_sk_lookup_udp_proto;
+	case BPF_FUNC_sk_lookup_tcp:
+		return &bpf_xdp_sk_lookup_tcp_proto;
+	case BPF_FUNC_sk_release:
+		return &bpf_sk_release_proto;
+#endif
 	default:
 		return bpf_base_func_proto(func_id);
 	}
-- 
cgit v1.2.3


From aaaa10e01d30e7d4cd3ddc0ff4cb82ed73632d9b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 9 Nov 2018 11:10:47 +0100
Subject: cfg80211: tracing: avoid 'idx' variable

This variable shadows something that gets generated inside
the tracing macros, which causes sparse to warn. Avoid it
so sparse output is more readable, even if it doesn't seem
to cause any trouble.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/trace.h | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index c6a9446b4e6b..f7909867d8fb 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -770,9 +770,9 @@ DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_set_wds_peer,
 );
 
 TRACE_EVENT(rdev_dump_station,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int idx,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int _idx,
 		 u8 *mac),
-	TP_ARGS(wiphy, netdev, idx, mac),
+	TP_ARGS(wiphy, netdev, _idx, mac),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		NETDEV_ENTRY
@@ -783,7 +783,7 @@ TRACE_EVENT(rdev_dump_station,
 		WIPHY_ASSIGN;
 		NETDEV_ASSIGN;
 		MAC_ASSIGN(sta_mac, mac);
-		__entry->idx = idx;
+		__entry->idx = _idx;
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: " MAC_PR_FMT ", idx: %d",
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac),
@@ -847,9 +847,9 @@ DEFINE_EVENT(mpath_evt, rdev_get_mpath,
 );
 
 TRACE_EVENT(rdev_dump_mpath,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int idx,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int _idx,
 		 u8 *dst, u8 *next_hop),
-	TP_ARGS(wiphy, netdev, idx, dst, next_hop),
+	TP_ARGS(wiphy, netdev, _idx, dst, next_hop),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		NETDEV_ENTRY
@@ -862,7 +862,7 @@ TRACE_EVENT(rdev_dump_mpath,
 		NETDEV_ASSIGN;
 		MAC_ASSIGN(dst, dst);
 		MAC_ASSIGN(next_hop, next_hop);
-		__entry->idx = idx;
+		__entry->idx = _idx;
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", index: %d, destination: "
 		  MAC_PR_FMT ", next hop: " MAC_PR_FMT,
@@ -892,9 +892,9 @@ TRACE_EVENT(rdev_get_mpp,
 );
 
 TRACE_EVENT(rdev_dump_mpp,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int idx,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int _idx,
 		 u8 *dst, u8 *mpp),
-	TP_ARGS(wiphy, netdev, idx, mpp, dst),
+	TP_ARGS(wiphy, netdev, _idx, mpp, dst),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		NETDEV_ENTRY
@@ -907,7 +907,7 @@ TRACE_EVENT(rdev_dump_mpp,
 		NETDEV_ASSIGN;
 		MAC_ASSIGN(dst, dst);
 		MAC_ASSIGN(mpp, mpp);
-		__entry->idx = idx;
+		__entry->idx = _idx;
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", index: %d, destination: "
 		  MAC_PR_FMT ", mpp: " MAC_PR_FMT,
@@ -1673,8 +1673,8 @@ TRACE_EVENT(rdev_tdls_mgmt,
 );
 
 TRACE_EVENT(rdev_dump_survey,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int idx),
-	TP_ARGS(wiphy, netdev, idx),
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int _idx),
+	TP_ARGS(wiphy, netdev, _idx),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		NETDEV_ENTRY
@@ -1683,7 +1683,7 @@ TRACE_EVENT(rdev_dump_survey,
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		NETDEV_ASSIGN;
-		__entry->idx = idx;
+		__entry->idx = _idx;
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", index: %d",
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->idx)
-- 
cgit v1.2.3


From 140d905b256165ae22c12837c046665a8d0aa599 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 9 Nov 2018 11:10:47 +0100
Subject: mac80211: tracing: avoid 'idx' variable

This variable shadows something that gets generated inside
the tracing macros, which causes sparse to warn. Avoid it
so sparse output is more readable, even if it doesn't seem
to cause any trouble.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/trace.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 588c51a67c89..a152263478dc 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -1052,10 +1052,10 @@ TRACE_EVENT(drv_ampdu_action,
 );
 
 TRACE_EVENT(drv_get_survey,
-	TP_PROTO(struct ieee80211_local *local, int idx,
+	TP_PROTO(struct ieee80211_local *local, int _idx,
 		 struct survey_info *survey),
 
-	TP_ARGS(local, idx, survey),
+	TP_ARGS(local, _idx, survey),
 
 	TP_STRUCT__entry(
 		LOCAL_ENTRY
@@ -1064,7 +1064,7 @@ TRACE_EVENT(drv_get_survey,
 
 	TP_fast_assign(
 		LOCAL_ASSIGN;
-		__entry->idx = idx;
+		__entry->idx = _idx;
 	),
 
 	TP_printk(
-- 
cgit v1.2.3


From 6af8354f1db95a01a1ca0638868367d7fa7b6324 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 9 Nov 2018 11:13:15 +0100
Subject: mac80211: sta_info: avoid tidstats variable shadowing

We have a pointer called 'tidstats' that shadows a bool function
argument with the same name, but we actually only use it once so
just remove the pointer.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/sta_info.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index fb8c2252ac0e..11b7ae691db0 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -2253,11 +2253,8 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 	}
 
 	if (tidstats && !cfg80211_sinfo_alloc_tid_stats(sinfo, GFP_KERNEL)) {
-		for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) {
-			struct cfg80211_tid_stats *tidstats = &sinfo->pertid[i];
-
-			sta_set_tidstats(sta, tidstats, i);
-		}
+		for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++)
+			sta_set_tidstats(sta, &sinfo->pertid[i], i);
 	}
 
 	if (ieee80211_vif_is_mesh(&sdata->vif)) {
-- 
cgit v1.2.3


From 63c713e1e810a5470d96e2a74ab288d14e45aa14 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 9 Nov 2018 11:14:51 +0100
Subject: mac80211: debugfs: avoid variable shadowing

We have a macro here that uses an inner variable 'i' that
also exists in the outer scope - use '_i' in the macro.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/debugfs_sta.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index af5185a836e5..b753194710ad 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -795,22 +795,22 @@ static ssize_t sta_he_capa_read(struct file *file, char __user *userbuf,
 
 #define PRINT_NSS_SUPP(f, n)						\
 	do {								\
-		int i;							\
+		int _i;							\
 		u16 v = le16_to_cpu(nss->f);				\
 		p += scnprintf(p, buf_sz + buf - p, n ": %#.4x\n", v);	\
-		for (i = 0; i < 8; i += 2) {				\
-			switch ((v >> i) & 0x3) {			\
+		for (_i = 0; _i < 8; _i += 2) {				\
+			switch ((v >> _i) & 0x3) {			\
 			case 0:						\
-				PRINT(n "-%d-SUPPORT-0-7", i / 2);	\
+				PRINT(n "-%d-SUPPORT-0-7", _i / 2);	\
 				break;					\
 			case 1:						\
-				PRINT(n "-%d-SUPPORT-0-9", i / 2);	\
+				PRINT(n "-%d-SUPPORT-0-9", _i / 2);	\
 				break;					\
 			case 2:						\
-				PRINT(n "-%d-SUPPORT-0-11", i / 2);	\
+				PRINT(n "-%d-SUPPORT-0-11", _i / 2);	\
 				break;					\
 			case 3:						\
-				PRINT(n "-%d-NOT-SUPPORTED", i / 2);	\
+				PRINT(n "-%d-NOT-SUPPORTED", _i / 2);	\
 				break;					\
 			}						\
 		}							\
-- 
cgit v1.2.3


From e0ba7095433a717a62d163dafe0fc2b0eba70d4b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 9 Nov 2018 11:16:46 +0100
Subject: mac80211: tx: avoid variable shadowing

We have a bool and an __le16 called qos, rename the inner __le16
to 'qoshdr' to make it more obvious and to avoid sparse warnings.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/tx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index e0ccee23fbcd..582b3d49f891 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -4579,7 +4579,7 @@ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw,
 					      IEEE80211_STYPE_NULLFUNC |
 					      IEEE80211_FCTL_TODS);
 	if (qos) {
-		__le16 qos = cpu_to_le16(7);
+		__le16 qoshdr = cpu_to_le16(7);
 
 		BUILD_BUG_ON((IEEE80211_STYPE_QOS_NULLFUNC |
 			      IEEE80211_STYPE_NULLFUNC) !=
@@ -4588,7 +4588,7 @@ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw,
 			cpu_to_le16(IEEE80211_STYPE_QOS_NULLFUNC);
 		skb->priority = 7;
 		skb_set_queue_mapping(skb, IEEE80211_AC_VO);
-		skb_put_data(skb, &qos, sizeof(qos));
+		skb_put_data(skb, &qoshdr, sizeof(qoshdr));
 	}
 
 	memcpy(nullfunc->addr1, ifmgd->bssid, ETH_ALEN);
-- 
cgit v1.2.3


From 801f87469ee8d97af5997ef52188bb0e1908b110 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 23 Aug 2018 10:48:13 +0200
Subject: netlink: add nl_set_extack_cookie_u64()

Add a helper function nl_set_extack_cookie_u64() to use a u64 as
the netlink extended ACK cookie, to avoid having to open-code it
in any users of the cookie.

A u64 should be sufficient for most subsystems though we allow
for up to 20 bytes right now. This also matches the cookies in
nl80211 where I intend to use this.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/netlink.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 4da90a6ab536..0b83dbae0a57 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -110,6 +110,15 @@ struct netlink_ext_ack {
 	}						\
 } while (0)
 
+static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack,
+					    u64 cookie)
+{
+	u64 __cookie = cookie;
+
+	memcpy(extack->cookie, &__cookie, sizeof(__cookie));
+	extack->cookie_len = sizeof(__cookie);
+}
+
 extern void netlink_kernel_release(struct sock *sk);
 extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups);
 extern int netlink_change_ngroups(struct sock *sk, unsigned int groups);
-- 
cgit v1.2.3


From 9bb7e0f24e7e7d00daa1219b14539e2e602649b2 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 10 Sep 2018 13:29:12 +0200
Subject: cfg80211: add peer measurement with FTM initiator API

Add a new "peer measurement" API, that can be used to measure
certain things related to a peer. Right now, only implement
FTM (flight time measurement) over it, but the idea is that
it'll be extensible to also support measuring the necessary
things to calculate e.g. angle-of-arrival for WiGig.

The API is structured to have a generic list of peers and
channels to measure with/on, and then for each of those a
set of measurements (again, only FTM right now) to perform.

Results are sent to the requesting socket, including a final
complete message.

Closing the controlling netlink socket will abort a running
measurement.

v3:
 - add a bit to report "final" for partial results
 - remove list keeping etc. and just unicast out the results
   to the requester (big code reduction ...)
 - also send complete message unicast, and as a result
   remove the multicast group
 - separate out struct cfg80211_pmsr_ftm_request_peer
   from struct cfg80211_pmsr_request_peer
 - document timeout == 0 if no timeout
 - disallow setting timeout nl80211 attribute to 0,
   must not include attribute for no timeout
 - make MAC address randomization optional
 - change num bursts exponent default to 0 (1 burst, rather
   rather than the old default of 15==don't care)

v4:
 - clarify NL80211_ATTR_TIMEOUT documentation

v5:
 - remove unnecessary nl80211 multicast/family changes
 - remove partial results bit/flag, final is sufficient
 - add max_bursts_exponent, max_ftms_per_burst to capability
 - rename "frames per burst" -> "FTMs per burst"

v6:
 - rename cfg80211_pmsr_free_wdev() to cfg80211_pmsr_wdev_down()
   and call it in leave, so the device can't go down with any
   pending measurements

v7:
 - wording fixes (Lior)
 - fix ftm.max_bursts_exponent to allow having the limit of 0 (Lior)

v8:
 - copyright statements
 - minor coding style fixes
 - fix error path leak

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 263 +++++++++++++++++++
 include/uapi/linux/nl80211.h | 418 ++++++++++++++++++++++++++++++
 net/wireless/Makefile        |   1 +
 net/wireless/core.c          |  34 +++
 net/wireless/core.h          |   5 +
 net/wireless/nl80211.c       | 192 ++++++++++++--
 net/wireless/nl80211.h       |  32 +++
 net/wireless/pmsr.c          | 590 +++++++++++++++++++++++++++++++++++++++++++
 net/wireless/rdev-ops.h      |  25 ++
 net/wireless/trace.h         |  68 +++++
 10 files changed, 1609 insertions(+), 19 deletions(-)
 create mode 100644 net/wireless/pmsr.c

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 1fa41b7a1be3..c21c5c70a2fd 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2848,6 +2848,190 @@ struct cfg80211_ftm_responder_stats {
 	u32 out_of_window_triggers_num;
 };
 
+/**
+ * struct cfg80211_pmsr_ftm_result - FTM result
+ * @failure_reason: if this measurement failed (PMSR status is
+ *	%NL80211_PMSR_STATUS_FAILURE), this gives a more precise
+ *	reason than just "failure"
+ * @burst_index: if reporting partial results, this is the index
+ *	in [0 .. num_bursts-1] of the burst that's being reported
+ * @num_ftmr_attempts: number of FTM request frames transmitted
+ * @num_ftmr_successes: number of FTM request frames acked
+ * @busy_retry_time: if failure_reason is %NL80211_PMSR_FTM_FAILURE_PEER_BUSY,
+ *	fill this to indicate in how many seconds a retry is deemed possible
+ *	by the responder
+ * @num_bursts_exp: actual number of bursts exponent negotiated
+ * @burst_duration: actual burst duration negotiated
+ * @ftms_per_burst: actual FTMs per burst negotiated
+ * @lci_len: length of LCI information (if present)
+ * @civicloc_len: length of civic location information (if present)
+ * @lci: LCI data (may be %NULL)
+ * @civicloc: civic location data (may be %NULL)
+ * @rssi_avg: average RSSI over FTM action frames reported
+ * @rssi_spread: spread of the RSSI over FTM action frames reported
+ * @tx_rate: bitrate for transmitted FTM action frame response
+ * @rx_rate: bitrate of received FTM action frame
+ * @rtt_avg: average of RTTs measured (must have either this or @dist_avg)
+ * @rtt_variance: variance of RTTs measured (note that standard deviation is
+ *	the square root of the variance)
+ * @rtt_spread: spread of the RTTs measured
+ * @dist_avg: average of distances (mm) measured
+ *	(must have either this or @rtt_avg)
+ * @dist_variance: variance of distances measured (see also @rtt_variance)
+ * @dist_spread: spread of distances measured (see also @rtt_spread)
+ * @num_ftmr_attempts_valid: @num_ftmr_attempts is valid
+ * @num_ftmr_successes_valid: @num_ftmr_successes is valid
+ * @rssi_avg_valid: @rssi_avg is valid
+ * @rssi_spread_valid: @rssi_spread is valid
+ * @tx_rate_valid: @tx_rate is valid
+ * @rx_rate_valid: @rx_rate is valid
+ * @rtt_avg_valid: @rtt_avg is valid
+ * @rtt_variance_valid: @rtt_variance is valid
+ * @rtt_spread_valid: @rtt_spread is valid
+ * @dist_avg_valid: @dist_avg is valid
+ * @dist_variance_valid: @dist_variance is valid
+ * @dist_spread_valid: @dist_spread is valid
+ */
+struct cfg80211_pmsr_ftm_result {
+	const u8 *lci;
+	const u8 *civicloc;
+	unsigned int lci_len;
+	unsigned int civicloc_len;
+	enum nl80211_peer_measurement_ftm_failure_reasons failure_reason;
+	u32 num_ftmr_attempts, num_ftmr_successes;
+	s16 burst_index;
+	u8 busy_retry_time;
+	u8 num_bursts_exp;
+	u8 burst_duration;
+	u8 ftms_per_burst;
+	s32 rssi_avg;
+	s32 rssi_spread;
+	struct rate_info tx_rate, rx_rate;
+	s64 rtt_avg;
+	s64 rtt_variance;
+	s64 rtt_spread;
+	s64 dist_avg;
+	s64 dist_variance;
+	s64 dist_spread;
+
+	u16 num_ftmr_attempts_valid:1,
+	    num_ftmr_successes_valid:1,
+	    rssi_avg_valid:1,
+	    rssi_spread_valid:1,
+	    tx_rate_valid:1,
+	    rx_rate_valid:1,
+	    rtt_avg_valid:1,
+	    rtt_variance_valid:1,
+	    rtt_spread_valid:1,
+	    dist_avg_valid:1,
+	    dist_variance_valid:1,
+	    dist_spread_valid:1;
+};
+
+/**
+ * struct cfg80211_pmsr_result - peer measurement result
+ * @addr: address of the peer
+ * @host_time: host time (use ktime_get_boottime() adjust to the time when the
+ *	measurement was made)
+ * @ap_tsf: AP's TSF at measurement time
+ * @status: status of the measurement
+ * @final: if reporting partial results, mark this as the last one; if not
+ *	reporting partial results always set this flag
+ * @ap_tsf_valid: indicates the @ap_tsf value is valid
+ * @type: type of the measurement reported, note that we only support reporting
+ *	one type at a time, but you can report multiple results separately and
+ *	they're all aggregated for userspace.
+ */
+struct cfg80211_pmsr_result {
+	u64 host_time, ap_tsf;
+	enum nl80211_peer_measurement_status status;
+
+	u8 addr[ETH_ALEN];
+
+	u8 final:1,
+	   ap_tsf_valid:1;
+
+	enum nl80211_peer_measurement_type type;
+
+	union {
+		struct cfg80211_pmsr_ftm_result ftm;
+	};
+};
+
+/**
+ * struct cfg80211_pmsr_ftm_request_peer - FTM request data
+ * @requested: indicates FTM is requested
+ * @preamble: frame preamble to use
+ * @burst_period: burst period to use
+ * @asap: indicates to use ASAP mode
+ * @num_bursts_exp: number of bursts exponent
+ * @burst_duration: burst duration
+ * @ftms_per_burst: number of FTMs per burst
+ * @ftmr_retries: number of retries for FTM request
+ * @request_lci: request LCI information
+ * @request_civicloc: request civic location information
+ *
+ * See also nl80211 for the respective attribute documentation.
+ */
+struct cfg80211_pmsr_ftm_request_peer {
+	enum nl80211_preamble preamble;
+	u16 burst_period;
+	u8 requested:1,
+	   asap:1,
+	   request_lci:1,
+	   request_civicloc:1;
+	u8 num_bursts_exp;
+	u8 burst_duration;
+	u8 ftms_per_burst;
+	u8 ftmr_retries;
+};
+
+/**
+ * struct cfg80211_pmsr_request_peer - peer data for a peer measurement request
+ * @addr: MAC address
+ * @chandef: channel to use
+ * @report_ap_tsf: report the associated AP's TSF
+ * @ftm: FTM data, see &struct cfg80211_pmsr_ftm_request_peer
+ */
+struct cfg80211_pmsr_request_peer {
+	u8 addr[ETH_ALEN];
+	struct cfg80211_chan_def chandef;
+	u8 report_ap_tsf:1;
+	struct cfg80211_pmsr_ftm_request_peer ftm;
+};
+
+/**
+ * struct cfg80211_pmsr_request - peer measurement request
+ * @cookie: cookie, set by cfg80211
+ * @nl_portid: netlink portid - used by cfg80211
+ * @drv_data: driver data for this request, if required for aborting,
+ *	not otherwise freed or anything by cfg80211
+ * @mac_addr: MAC address used for (randomised) request
+ * @mac_addr_mask: MAC address mask used for randomisation, bits that
+ *	are 0 in the mask should be randomised, bits that are 1 should
+ *	be taken from the @mac_addr
+ * @list: used by cfg80211 to hold on to the request
+ * @timeout: timeout (in milliseconds) for the whole operation, if
+ *	zero it means there's no timeout
+ * @n_peers: number of peers to do measurements with
+ * @peers: per-peer measurement request data
+ */
+struct cfg80211_pmsr_request {
+	u64 cookie;
+	void *drv_data;
+	u32 n_peers;
+	u32 nl_portid;
+
+	u32 timeout;
+
+	u8 mac_addr[ETH_ALEN] __aligned(2);
+	u8 mac_addr_mask[ETH_ALEN] __aligned(2);
+
+	struct list_head list;
+
+	struct cfg80211_pmsr_request_peer peers[];
+};
+
 /**
  * struct cfg80211_ops - backend description for wireless configuration
  *
@@ -3183,6 +3367,8 @@ struct cfg80211_ftm_responder_stats {
  *
  * @get_ftm_responder_stats: Retrieve FTM responder statistics, if available.
  *	Statistics should be cumulative, currently no way to reset is provided.
+ * @start_pmsr: start peer measurement (e.g. FTM)
+ * @abort_pmsr: abort peer measurement
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -3492,6 +3678,11 @@ struct cfg80211_ops {
 	int	(*get_ftm_responder_stats)(struct wiphy *wiphy,
 				struct net_device *dev,
 				struct cfg80211_ftm_responder_stats *ftm_stats);
+
+	int	(*start_pmsr)(struct wiphy *wiphy, struct wireless_dev *wdev,
+			      struct cfg80211_pmsr_request *request);
+	void	(*abort_pmsr)(struct wiphy *wiphy, struct wireless_dev *wdev,
+			      struct cfg80211_pmsr_request *request);
 };
 
 /*
@@ -3863,6 +4054,42 @@ struct wiphy_iftype_ext_capab {
 	u8 extended_capabilities_len;
 };
 
+/**
+ * struct cfg80211_pmsr_capabilities - cfg80211 peer measurement capabilities
+ * @max_peers: maximum number of peers in a single measurement
+ * @report_ap_tsf: can report assoc AP's TSF for radio resource measurement
+ * @randomize_mac_addr: can randomize MAC address for measurement
+ * @ftm.supported: FTM measurement is supported
+ * @ftm.asap: ASAP-mode is supported
+ * @ftm.non_asap: non-ASAP-mode is supported
+ * @ftm.request_lci: can request LCI data
+ * @ftm.request_civicloc: can request civic location data
+ * @ftm.preambles: bitmap of preambles supported (&enum nl80211_preamble)
+ * @ftm.bandwidths: bitmap of bandwidths supported (&enum nl80211_chan_width)
+ * @ftm.max_bursts_exponent: maximum burst exponent supported
+ *	(set to -1 if not limited; note that setting this will necessarily
+ *	forbid using the value 15 to let the responder pick)
+ * @ftm.max_ftms_per_burst: maximum FTMs per burst supported (set to 0 if
+ *	not limited)
+ */
+struct cfg80211_pmsr_capabilities {
+	unsigned int max_peers;
+	u8 report_ap_tsf:1,
+	   randomize_mac_addr:1;
+
+	struct {
+		u32 preambles;
+		u32 bandwidths;
+		s8 max_bursts_exponent;
+		u8 max_ftms_per_burst;
+		u8 supported:1,
+		   asap:1,
+		   non_asap:1,
+		   request_lci:1,
+		   request_civicloc:1;
+	} ftm;
+};
+
 /**
  * struct wiphy - wireless hardware description
  * @reg_notifier: the driver's regulatory notification callback,
@@ -4027,6 +4254,8 @@ struct wiphy_iftype_ext_capab {
  * @txq_limit: configuration of internal TX queue frame limit
  * @txq_memory_limit: configuration internal TX queue memory limit
  * @txq_quantum: configuration of internal TX queue scheduler quantum
+ *
+ * @pmsr_capa: peer measurement capabilities
  */
 struct wiphy {
 	/* assign these fields before you register the wiphy */
@@ -4163,6 +4392,8 @@ struct wiphy {
 	u32 txq_memory_limit;
 	u32 txq_quantum;
 
+	const struct cfg80211_pmsr_capabilities *pmsr_capa;
+
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
 
@@ -4365,6 +4596,9 @@ struct cfg80211_cqm_config;
  * @owner_nlportid: (private) owner socket port ID
  * @nl_owner_dead: (private) owner socket went away
  * @cqm_config: (private) nl80211 RSSI monitor state
+ * @pmsr_list: (private) peer measurement requests
+ * @pmsr_lock: (private) peer measurements requests/results lock
+ * @pmsr_free_wk: (private) peer measurements cleanup work
  */
 struct wireless_dev {
 	struct wiphy *wiphy;
@@ -4436,6 +4670,10 @@ struct wireless_dev {
 #endif
 
 	struct cfg80211_cqm_config *cqm_config;
+
+	struct list_head pmsr_list;
+	spinlock_t pmsr_lock;
+	struct work_struct pmsr_free_wk;
 };
 
 static inline u8 *wdev_address(struct wireless_dev *wdev)
@@ -6630,6 +6868,31 @@ int cfg80211_external_auth_request(struct net_device *netdev,
 				   struct cfg80211_external_auth_params *params,
 				   gfp_t gfp);
 
+/**
+ * cfg80211_pmsr_report - report peer measurement result data
+ * @wdev: the wireless device reporting the measurement
+ * @req: the original measurement request
+ * @result: the result data
+ * @gfp: allocation flags
+ */
+void cfg80211_pmsr_report(struct wireless_dev *wdev,
+			  struct cfg80211_pmsr_request *req,
+			  struct cfg80211_pmsr_result *result,
+			  gfp_t gfp);
+
+/**
+ * cfg80211_pmsr_complete - report peer measurement completed
+ * @wdev: the wireless device reporting the measurement
+ * @req: the original measurement request
+ * @gfp: allocation flags
+ *
+ * Report that the entire measurement completed, after this
+ * the request pointer will no longer be valid.
+ */
+void cfg80211_pmsr_complete(struct wireless_dev *wdev,
+			    struct cfg80211_pmsr_request *req,
+			    gfp_t gfp);
+
 /* Logging, debugging and troubleshooting/diagnostic helpers. */
 
 /* wiphy_printk helpers, similar to dev_printk */
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 6d610bae30a9..e45b88925783 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1036,6 +1036,30 @@
  * @NL80211_CMD_GET_FTM_RESPONDER_STATS: Retrieve FTM responder statistics, in
  *	the %NL80211_ATTR_FTM_RESPONDER_STATS attribute.
  *
+ * @NL80211_CMD_PEER_MEASUREMENT_START: start a (set of) peer measurement(s)
+ *	with the given parameters, which are encapsulated in the nested
+ *	%NL80211_ATTR_PEER_MEASUREMENTS attribute. Optionally, MAC address
+ *	randomization may be enabled and configured by specifying the
+ *	%NL80211_ATTR_MAC and %NL80211_ATTR_MAC_MASK attributes.
+ *	If a timeout is requested, use the %NL80211_ATTR_TIMEOUT attribute.
+ *	A u64 cookie for further %NL80211_ATTR_COOKIE use is is returned in
+ *	the netlink extended ack message.
+ *
+ *	To cancel a measurement, close the socket that requested it.
+ *
+ *	Measurement results are reported to the socket that requested the
+ *	measurement using @NL80211_CMD_PEER_MEASUREMENT_RESULT when they
+ *	become available, so applications must ensure a large enough socket
+ *	buffer size.
+ *
+ *	Depending on driver support it may or may not be possible to start
+ *	multiple concurrent measurements.
+ * @NL80211_CMD_PEER_MEASUREMENT_RESULT: This command number is used for the
+ *	result notification from the driver to the requesting socket.
+ * @NL80211_CMD_PEER_MEASUREMENT_COMPLETE: Notification only, indicating that
+ *	the measurement completed, using the measurement cookie
+ *	(%NL80211_ATTR_COOKIE).
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -1250,6 +1274,10 @@ enum nl80211_commands {
 
 	NL80211_CMD_GET_FTM_RESPONDER_STATS,
 
+	NL80211_CMD_PEER_MEASUREMENT_START,
+	NL80211_CMD_PEER_MEASUREMENT_RESULT,
+	NL80211_CMD_PEER_MEASUREMENT_COMPLETE,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
@@ -2254,6 +2282,16 @@ enum nl80211_commands {
  * @NL80211_ATTR_FTM_RESPONDER_STATS: Nested attribute with FTM responder
  *	statistics, see &enum nl80211_ftm_responder_stats.
  *
+ * @NL80211_ATTR_TIMEOUT: Timeout for the given operation in milliseconds (u32),
+ *	if the attribute is not given no timeout is requested. Note that 0 is an
+ *	invalid value.
+ *
+ * @NL80211_ATTR_PEER_MEASUREMENTS: peer measurements request (and result)
+ *	data, uses nested attributes specified in
+ *	&enum nl80211_peer_measurement_attrs.
+ *	This is also used for capability advertisement in the wiphy information,
+ *	with the appropriate sub-attributes.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2699,6 +2737,10 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_FTM_RESPONDER_STATS,
 
+	NL80211_ATTR_TIMEOUT,
+
+	NL80211_ATTR_PEER_MEASUREMENTS,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -5906,4 +5948,380 @@ enum nl80211_ftm_responder_stats {
 	NL80211_FTM_STATS_MAX = __NL80211_FTM_STATS_AFTER_LAST - 1
 };
 
+/**
+ * enum nl80211_preamble - frame preamble types
+ * @NL80211_PREAMBLE_LEGACY: legacy (HR/DSSS, OFDM, ERP PHY) preamble
+ * @NL80211_PREAMBLE_HT: HT preamble
+ * @NL80211_PREAMBLE_VHT: VHT preamble
+ * @NL80211_PREAMBLE_DMG: DMG preamble
+ */
+enum nl80211_preamble {
+	NL80211_PREAMBLE_LEGACY,
+	NL80211_PREAMBLE_HT,
+	NL80211_PREAMBLE_VHT,
+	NL80211_PREAMBLE_DMG,
+};
+
+/**
+ * enum nl80211_peer_measurement_type - peer measurement types
+ * @NL80211_PMSR_TYPE_INVALID: invalid/unused, needed as we use
+ *	these numbers also for attributes
+ *
+ * @NL80211_PMSR_TYPE_FTM: flight time measurement
+ *
+ * @NUM_NL80211_PMSR_TYPES: internal
+ * @NL80211_PMSR_TYPE_MAX: highest type number
+ */
+enum nl80211_peer_measurement_type {
+	NL80211_PMSR_TYPE_INVALID,
+
+	NL80211_PMSR_TYPE_FTM,
+
+	NUM_NL80211_PMSR_TYPES,
+	NL80211_PMSR_TYPE_MAX = NUM_NL80211_PMSR_TYPES - 1
+};
+
+/**
+ * enum nl80211_peer_measurement_status - peer measurement status
+ * @NL80211_PMSR_STATUS_SUCCESS: measurement completed successfully
+ * @NL80211_PMSR_STATUS_REFUSED: measurement was locally refused
+ * @NL80211_PMSR_STATUS_TIMEOUT: measurement timed out
+ * @NL80211_PMSR_STATUS_FAILURE: measurement failed, a type-dependent
+ *	reason may be available in the response data
+ */
+enum nl80211_peer_measurement_status {
+	NL80211_PMSR_STATUS_SUCCESS,
+	NL80211_PMSR_STATUS_REFUSED,
+	NL80211_PMSR_STATUS_TIMEOUT,
+	NL80211_PMSR_STATUS_FAILURE,
+};
+
+/**
+ * enum nl80211_peer_measurement_req - peer measurement request attributes
+ * @__NL80211_PMSR_REQ_ATTR_INVALID: invalid
+ *
+ * @NL80211_PMSR_REQ_ATTR_DATA: This is a nested attribute with measurement
+ *	type-specific request data inside. The attributes used are from the
+ *	enums named nl80211_peer_measurement_<type>_req.
+ * @NL80211_PMSR_REQ_ATTR_GET_AP_TSF: include AP TSF timestamp, if supported
+ *	(flag attribute)
+ *
+ * @NUM_NL80211_PMSR_REQ_ATTRS: internal
+ * @NL80211_PMSR_REQ_ATTR_MAX: highest attribute number
+ */
+enum nl80211_peer_measurement_req {
+	__NL80211_PMSR_REQ_ATTR_INVALID,
+
+	NL80211_PMSR_REQ_ATTR_DATA,
+	NL80211_PMSR_REQ_ATTR_GET_AP_TSF,
+
+	/* keep last */
+	NUM_NL80211_PMSR_REQ_ATTRS,
+	NL80211_PMSR_REQ_ATTR_MAX = NUM_NL80211_PMSR_REQ_ATTRS - 1
+};
+
+/**
+ * enum nl80211_peer_measurement_resp - peer measurement response attributes
+ * @__NL80211_PMSR_RESP_ATTR_INVALID: invalid
+ *
+ * @NL80211_PMSR_RESP_ATTR_DATA: This is a nested attribute with measurement
+ *	type-specific results inside. The attributes used are from the enums
+ *	named nl80211_peer_measurement_<type>_resp.
+ * @NL80211_PMSR_RESP_ATTR_STATUS: u32 value with the measurement status
+ *	(using values from &enum nl80211_peer_measurement_status.)
+ * @NL80211_PMSR_RESP_ATTR_HOST_TIME: host time (%CLOCK_BOOTTIME) when the
+ *	result was measured; this value is not expected to be accurate to
+ *	more than 20ms. (u64, nanoseconds)
+ * @NL80211_PMSR_RESP_ATTR_AP_TSF: TSF of the AP that the interface
+ *	doing the measurement is connected to when the result was measured.
+ *	This shall be accurately reported if supported and requested
+ *	(u64, usec)
+ * @NL80211_PMSR_RESP_ATTR_FINAL: If results are sent to the host partially
+ *	(*e.g. with FTM per-burst data) this flag will be cleared on all but
+ *	the last result; if all results are combined it's set on the single
+ *	result.
+ * @NL80211_PMSR_RESP_ATTR_PAD: padding for 64-bit attributes, ignore
+ *
+ * @NUM_NL80211_PMSR_RESP_ATTRS: internal
+ * @NL80211_PMSR_RESP_ATTR_MAX: highest attribute number
+ */
+enum nl80211_peer_measurement_resp {
+	__NL80211_PMSR_RESP_ATTR_INVALID,
+
+	NL80211_PMSR_RESP_ATTR_DATA,
+	NL80211_PMSR_RESP_ATTR_STATUS,
+	NL80211_PMSR_RESP_ATTR_HOST_TIME,
+	NL80211_PMSR_RESP_ATTR_AP_TSF,
+	NL80211_PMSR_RESP_ATTR_FINAL,
+	NL80211_PMSR_RESP_ATTR_PAD,
+
+	/* keep last */
+	NUM_NL80211_PMSR_RESP_ATTRS,
+	NL80211_PMSR_RESP_ATTR_MAX = NUM_NL80211_PMSR_RESP_ATTRS - 1
+};
+
+/**
+ * enum nl80211_peer_measurement_peer_attrs - peer attributes for measurement
+ * @__NL80211_PMSR_PEER_ATTR_INVALID: invalid
+ *
+ * @NL80211_PMSR_PEER_ATTR_ADDR: peer's MAC address
+ * @NL80211_PMSR_PEER_ATTR_CHAN: channel definition, nested, using top-level
+ *	attributes like %NL80211_ATTR_WIPHY_FREQ etc.
+ * @NL80211_PMSR_PEER_ATTR_REQ: This is a nested attribute indexed by
+ *	measurement type, with attributes from the
+ *	&enum nl80211_peer_measurement_req inside.
+ * @NL80211_PMSR_PEER_ATTR_RESP: This is a nested attribute indexed by
+ *	measurement type, with attributes from the
+ *	&enum nl80211_peer_measurement_resp inside.
+ *
+ * @NUM_NL80211_PMSR_PEER_ATTRS: internal
+ * @NL80211_PMSR_PEER_ATTR_MAX: highest attribute number
+ */
+enum nl80211_peer_measurement_peer_attrs {
+	__NL80211_PMSR_PEER_ATTR_INVALID,
+
+	NL80211_PMSR_PEER_ATTR_ADDR,
+	NL80211_PMSR_PEER_ATTR_CHAN,
+	NL80211_PMSR_PEER_ATTR_REQ,
+	NL80211_PMSR_PEER_ATTR_RESP,
+
+	/* keep last */
+	NUM_NL80211_PMSR_PEER_ATTRS,
+	NL80211_PMSR_PEER_ATTR_MAX = NUM_NL80211_PMSR_PEER_ATTRS - 1,
+};
+
+/**
+ * enum nl80211_peer_measurement_attrs - peer measurement attributes
+ * @__NL80211_PMSR_ATTR_INVALID: invalid
+ *
+ * @NL80211_PMSR_ATTR_MAX_PEERS: u32 attribute used for capability
+ *	advertisement only, indicates the maximum number of peers
+ *	measurements can be done with in a single request
+ * @NL80211_PMSR_ATTR_REPORT_AP_TSF: flag attribute in capability
+ *	indicating that the connected AP's TSF can be reported in
+ *	measurement results
+ * @NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR: flag attribute in capability
+ *	indicating that MAC address randomization is supported.
+ * @NL80211_PMSR_ATTR_TYPE_CAPA: capabilities reported by the device,
+ *	this contains a nesting indexed by measurement type, and
+ *	type-specific capabilities inside, which are from the enums
+ *	named nl80211_peer_measurement_<type>_capa.
+ * @NL80211_PMSR_ATTR_PEERS: nested attribute, the nesting index is
+ *	meaningless, just a list of peers to measure with, with the
+ *	sub-attributes taken from
+ *	&enum nl80211_peer_measurement_peer_attrs.
+ *
+ * @NUM_NL80211_PMSR_ATTR: internal
+ * @NL80211_PMSR_ATTR_MAX: highest attribute number
+ */
+enum nl80211_peer_measurement_attrs {
+	__NL80211_PMSR_ATTR_INVALID,
+
+	NL80211_PMSR_ATTR_MAX_PEERS,
+	NL80211_PMSR_ATTR_REPORT_AP_TSF,
+	NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR,
+	NL80211_PMSR_ATTR_TYPE_CAPA,
+	NL80211_PMSR_ATTR_PEERS,
+
+	/* keep last */
+	NUM_NL80211_PMSR_ATTR,
+	NL80211_PMSR_ATTR_MAX = NUM_NL80211_PMSR_ATTR - 1
+};
+
+/**
+ * enum nl80211_peer_measurement_ftm_capa - FTM capabilities
+ * @__NL80211_PMSR_FTM_CAPA_ATTR_INVALID: invalid
+ *
+ * @NL80211_PMSR_FTM_CAPA_ATTR_ASAP: flag attribute indicating ASAP mode
+ *	is supported
+ * @NL80211_PMSR_FTM_CAPA_ATTR_NON_ASAP: flag attribute indicating non-ASAP
+ *	mode is supported
+ * @NL80211_PMSR_FTM_CAPA_ATTR_REQ_LCI: flag attribute indicating if LCI
+ *	data can be requested during the measurement
+ * @NL80211_PMSR_FTM_CAPA_ATTR_REQ_CIVICLOC: flag attribute indicating if civic
+ *	location data can be requested during the measurement
+ * @NL80211_PMSR_FTM_CAPA_ATTR_PREAMBLES: u32 bitmap attribute of bits
+ *	from &enum nl80211_preamble.
+ * @NL80211_PMSR_FTM_CAPA_ATTR_BANDWIDTHS: bitmap of values from
+ *	&enum nl80211_chan_width indicating the supported channel
+ *	bandwidths for FTM. Note that a higher channel bandwidth may be
+ *	configured to allow for other measurements types with different
+ *	bandwidth requirement in the same measurement.
+ * @NL80211_PMSR_FTM_CAPA_ATTR_MAX_BURSTS_EXPONENT: u32 attribute indicating
+ *	the maximum bursts exponent that can be used (if not present anything
+ *	is valid)
+ * @NL80211_PMSR_FTM_CAPA_ATTR_MAX_FTMS_PER_BURST: u32 attribute indicating
+ *	the maximum FTMs per burst (if not present anything is valid)
+ *
+ * @NUM_NL80211_PMSR_FTM_CAPA_ATTR: internal
+ * @NL80211_PMSR_FTM_CAPA_ATTR_MAX: highest attribute number
+ */
+enum nl80211_peer_measurement_ftm_capa {
+	__NL80211_PMSR_FTM_CAPA_ATTR_INVALID,
+
+	NL80211_PMSR_FTM_CAPA_ATTR_ASAP,
+	NL80211_PMSR_FTM_CAPA_ATTR_NON_ASAP,
+	NL80211_PMSR_FTM_CAPA_ATTR_REQ_LCI,
+	NL80211_PMSR_FTM_CAPA_ATTR_REQ_CIVICLOC,
+	NL80211_PMSR_FTM_CAPA_ATTR_PREAMBLES,
+	NL80211_PMSR_FTM_CAPA_ATTR_BANDWIDTHS,
+	NL80211_PMSR_FTM_CAPA_ATTR_MAX_BURSTS_EXPONENT,
+	NL80211_PMSR_FTM_CAPA_ATTR_MAX_FTMS_PER_BURST,
+
+	/* keep last */
+	NUM_NL80211_PMSR_FTM_CAPA_ATTR,
+	NL80211_PMSR_FTM_CAPA_ATTR_MAX = NUM_NL80211_PMSR_FTM_CAPA_ATTR - 1
+};
+
+/**
+ * enum nl80211_peer_measurement_ftm_req - FTM request attributes
+ * @__NL80211_PMSR_FTM_REQ_ATTR_INVALID: invalid
+ *
+ * @NL80211_PMSR_FTM_REQ_ATTR_ASAP: ASAP mode requested (flag)
+ * @NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE: preamble type (see
+ *	&enum nl80211_preamble), optional for DMG (u32)
+ * @NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP: number of bursts exponent as in
+ *	802.11-2016 9.4.2.168 "Fine Timing Measurement Parameters element"
+ *	(u8, 0-15, optional with default 15 i.e. "no preference")
+ * @NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD: interval between bursts in units
+ *	of 100ms (u16, optional with default 0)
+ * @NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION: burst duration, as in 802.11-2016
+ *	Table 9-257 "Burst Duration field encoding" (u8, 0-15, optional with
+ *	default 15 i.e. "no preference")
+ * @NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST: number of successful FTM frames
+ *	requested per burst
+ *	(u8, 0-31, optional with default 0 i.e. "no preference")
+ * @NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES: number of FTMR frame retries
+ *	(u8, default 3)
+ * @NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI: request LCI data (flag)
+ * @NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC: request civic location data
+ *	(flag)
+ *
+ * @NUM_NL80211_PMSR_FTM_REQ_ATTR: internal
+ * @NL80211_PMSR_FTM_REQ_ATTR_MAX: highest attribute number
+ */
+enum nl80211_peer_measurement_ftm_req {
+	__NL80211_PMSR_FTM_REQ_ATTR_INVALID,
+
+	NL80211_PMSR_FTM_REQ_ATTR_ASAP,
+	NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE,
+	NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP,
+	NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD,
+	NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION,
+	NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST,
+	NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES,
+	NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI,
+	NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC,
+
+	/* keep last */
+	NUM_NL80211_PMSR_FTM_REQ_ATTR,
+	NL80211_PMSR_FTM_REQ_ATTR_MAX = NUM_NL80211_PMSR_FTM_REQ_ATTR - 1
+};
+
+/**
+ * enum nl80211_peer_measurement_ftm_failure_reasons - FTM failure reasons
+ * @NL80211_PMSR_FTM_FAILURE_UNSPECIFIED: unspecified failure, not used
+ * @NL80211_PMSR_FTM_FAILURE_NO_RESPONSE: no response from the FTM responder
+ * @NL80211_PMSR_FTM_FAILURE_REJECTED: FTM responder rejected measurement
+ * @NL80211_PMSR_FTM_FAILURE_WRONG_CHANNEL: we already know the peer is
+ *	on a different channel, so can't measure (if we didn't know, we'd
+ *	try and get no response)
+ * @NL80211_PMSR_FTM_FAILURE_PEER_NOT_CAPABLE: peer can't actually do FTM
+ * @NL80211_PMSR_FTM_FAILURE_INVALID_TIMESTAMP: invalid T1/T4 timestamps
+ *	received
+ * @NL80211_PMSR_FTM_FAILURE_PEER_BUSY: peer reports busy, you may retry
+ *	later (see %NL80211_PMSR_FTM_RESP_ATTR_BUSY_RETRY_TIME)
+ * @NL80211_PMSR_FTM_FAILURE_BAD_CHANGED_PARAMS: parameters were changed
+ *	by the peer and are no longer supported
+ */
+enum nl80211_peer_measurement_ftm_failure_reasons {
+	NL80211_PMSR_FTM_FAILURE_UNSPECIFIED,
+	NL80211_PMSR_FTM_FAILURE_NO_RESPONSE,
+	NL80211_PMSR_FTM_FAILURE_REJECTED,
+	NL80211_PMSR_FTM_FAILURE_WRONG_CHANNEL,
+	NL80211_PMSR_FTM_FAILURE_PEER_NOT_CAPABLE,
+	NL80211_PMSR_FTM_FAILURE_INVALID_TIMESTAMP,
+	NL80211_PMSR_FTM_FAILURE_PEER_BUSY,
+	NL80211_PMSR_FTM_FAILURE_BAD_CHANGED_PARAMS,
+};
+
+/**
+ * enum nl80211_peer_measurement_ftm_resp - FTM response attributes
+ * @__NL80211_PMSR_FTM_RESP_ATTR_INVALID: invalid
+ *
+ * @NL80211_PMSR_FTM_RESP_ATTR_FAIL_REASON: FTM-specific failure reason
+ *	(u32, optional)
+ * @NL80211_PMSR_FTM_RESP_ATTR_BURST_INDEX: optional, if bursts are reported
+ *	as separate results then it will be the burst index 0...(N-1) and
+ *	the top level will indicate partial results (u32)
+ * @NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_ATTEMPTS: number of FTM Request frames
+ *	transmitted (u32, optional)
+ * @NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_SUCCESSES: number of FTM Request frames
+ *	that were acknowleged (u32, optional)
+ * @NL80211_PMSR_FTM_RESP_ATTR_BUSY_RETRY_TIME: retry time received from the
+ *	busy peer (u32, seconds)
+ * @NL80211_PMSR_FTM_RESP_ATTR_NUM_BURSTS_EXP: actual number of bursts exponent
+ *	used by the responder (similar to request, u8)
+ * @NL80211_PMSR_FTM_RESP_ATTR_BURST_DURATION: actual burst duration used by
+ *	the responder (similar to request, u8)
+ * @NL80211_PMSR_FTM_RESP_ATTR_FTMS_PER_BURST: actual FTMs per burst used
+ *	by the responder (similar to request, u8)
+ * @NL80211_PMSR_FTM_RESP_ATTR_RSSI_AVG: average RSSI across all FTM action
+ *	frames (optional, s32, 1/2 dBm)
+ * @NL80211_PMSR_FTM_RESP_ATTR_RSSI_SPREAD: RSSI spread across all FTM action
+ *	frames (optional, s32, 1/2 dBm)
+ * @NL80211_PMSR_FTM_RESP_ATTR_TX_RATE: bitrate we used for the response to the
+ *	FTM action frame (optional, nested, using &enum nl80211_rate_info
+ *	attributes)
+ * @NL80211_PMSR_FTM_RESP_ATTR_RX_RATE: bitrate the responder used for the FTM
+ *	action frame (optional, nested, using &enum nl80211_rate_info attrs)
+ * @NL80211_PMSR_FTM_RESP_ATTR_RTT_AVG: average RTT (s64, picoseconds, optional
+ *	but one of RTT/DIST must be present)
+ * @NL80211_PMSR_FTM_RESP_ATTR_RTT_VARIANCE: RTT variance (u64, ps^2, note that
+ *	standard deviation is the square root of variance, optional)
+ * @NL80211_PMSR_FTM_RESP_ATTR_RTT_SPREAD: RTT spread (u64, picoseconds,
+ *	optional)
+ * @NL80211_PMSR_FTM_RESP_ATTR_DIST_AVG: average distance (s64, mm, optional
+ *	but one of RTT/DIST must be present)
+ * @NL80211_PMSR_FTM_RESP_ATTR_DIST_VARIANCE: distance variance (u64, mm^2, note
+ *	that standard deviation is the square root of variance, optional)
+ * @NL80211_PMSR_FTM_RESP_ATTR_DIST_SPREAD: distance spread (u64, mm, optional)
+ * @NL80211_PMSR_FTM_RESP_ATTR_LCI: LCI data from peer (binary, optional)
+ * @NL80211_PMSR_FTM_RESP_ATTR_CIVICLOC: civic location data from peer
+ *	(binary, optional)
+ * @NL80211_PMSR_FTM_RESP_ATTR_PAD: ignore, for u64/s64 padding only
+ *
+ * @NUM_NL80211_PMSR_FTM_RESP_ATTR: internal
+ * @NL80211_PMSR_FTM_RESP_ATTR_MAX: highest attribute number
+ */
+enum nl80211_peer_measurement_ftm_resp {
+	__NL80211_PMSR_FTM_RESP_ATTR_INVALID,
+
+	NL80211_PMSR_FTM_RESP_ATTR_FAIL_REASON,
+	NL80211_PMSR_FTM_RESP_ATTR_BURST_INDEX,
+	NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_ATTEMPTS,
+	NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_SUCCESSES,
+	NL80211_PMSR_FTM_RESP_ATTR_BUSY_RETRY_TIME,
+	NL80211_PMSR_FTM_RESP_ATTR_NUM_BURSTS_EXP,
+	NL80211_PMSR_FTM_RESP_ATTR_BURST_DURATION,
+	NL80211_PMSR_FTM_RESP_ATTR_FTMS_PER_BURST,
+	NL80211_PMSR_FTM_RESP_ATTR_RSSI_AVG,
+	NL80211_PMSR_FTM_RESP_ATTR_RSSI_SPREAD,
+	NL80211_PMSR_FTM_RESP_ATTR_TX_RATE,
+	NL80211_PMSR_FTM_RESP_ATTR_RX_RATE,
+	NL80211_PMSR_FTM_RESP_ATTR_RTT_AVG,
+	NL80211_PMSR_FTM_RESP_ATTR_RTT_VARIANCE,
+	NL80211_PMSR_FTM_RESP_ATTR_RTT_SPREAD,
+	NL80211_PMSR_FTM_RESP_ATTR_DIST_AVG,
+	NL80211_PMSR_FTM_RESP_ATTR_DIST_VARIANCE,
+	NL80211_PMSR_FTM_RESP_ATTR_DIST_SPREAD,
+	NL80211_PMSR_FTM_RESP_ATTR_LCI,
+	NL80211_PMSR_FTM_RESP_ATTR_CIVICLOC,
+	NL80211_PMSR_FTM_RESP_ATTR_PAD,
+
+	/* keep last */
+	NUM_NL80211_PMSR_FTM_RESP_ATTR,
+	NL80211_PMSR_FTM_RESP_ATTR_MAX = NUM_NL80211_PMSR_FTM_RESP_ATTR - 1
+};
+
 #endif /* __LINUX_NL80211_H */
diff --git a/net/wireless/Makefile b/net/wireless/Makefile
index 1d84f91bbfb0..72a224ce8e0a 100644
--- a/net/wireless/Makefile
+++ b/net/wireless/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_WEXT_PRIV) += wext-priv.o
 
 cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o
 cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o trace.o ocb.o
+cfg80211-y += pmsr.o
 cfg80211-$(CONFIG_OF) += of.o
 cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o
 cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 5bd01058b9e6..0a3092c56b3e 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -4,6 +4,7 @@
  * Copyright 2006-2010		Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2015-2017	Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -664,6 +665,34 @@ int wiphy_register(struct wiphy *wiphy)
 		return -EINVAL;
 #endif
 
+	if (WARN_ON(wiphy->pmsr_capa && !wiphy->pmsr_capa->ftm.supported))
+		return -EINVAL;
+
+	if (wiphy->pmsr_capa && wiphy->pmsr_capa->ftm.supported) {
+		if (WARN_ON(!wiphy->pmsr_capa->ftm.asap &&
+			    !wiphy->pmsr_capa->ftm.non_asap))
+			return -EINVAL;
+		if (WARN_ON(!wiphy->pmsr_capa->ftm.preambles ||
+			    !wiphy->pmsr_capa->ftm.bandwidths))
+			return -EINVAL;
+		if (WARN_ON(wiphy->pmsr_capa->ftm.preambles &
+				~(BIT(NL80211_PREAMBLE_LEGACY) |
+				  BIT(NL80211_PREAMBLE_HT) |
+				  BIT(NL80211_PREAMBLE_VHT) |
+				  BIT(NL80211_PREAMBLE_DMG))))
+			return -EINVAL;
+		if (WARN_ON(wiphy->pmsr_capa->ftm.bandwidths &
+				~(BIT(NL80211_CHAN_WIDTH_20_NOHT) |
+				  BIT(NL80211_CHAN_WIDTH_20) |
+				  BIT(NL80211_CHAN_WIDTH_40) |
+				  BIT(NL80211_CHAN_WIDTH_80) |
+				  BIT(NL80211_CHAN_WIDTH_80P80) |
+				  BIT(NL80211_CHAN_WIDTH_160) |
+				  BIT(NL80211_CHAN_WIDTH_5) |
+				  BIT(NL80211_CHAN_WIDTH_10))))
+			return -EINVAL;
+	}
+
 	/*
 	 * if a wiphy has unsupported modes for regulatory channel enforcement,
 	 * opt-out of enforcement checking
@@ -1087,6 +1116,8 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
 	ASSERT_RTNL();
 	ASSERT_WDEV_LOCK(wdev);
 
+	cfg80211_pmsr_wdev_down(wdev);
+
 	switch (wdev->iftype) {
 	case NL80211_IFTYPE_ADHOC:
 		__cfg80211_leave_ibss(rdev, dev, true);
@@ -1174,6 +1205,9 @@ void cfg80211_init_wdev(struct cfg80211_registered_device *rdev,
 	spin_lock_init(&wdev->event_lock);
 	INIT_LIST_HEAD(&wdev->mgmt_registrations);
 	spin_lock_init(&wdev->mgmt_registrations_lock);
+	INIT_LIST_HEAD(&wdev->pmsr_list);
+	spin_lock_init(&wdev->pmsr_lock);
+	INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk);
 
 	/*
 	 * We get here also when the interface changes network namespaces,
diff --git a/net/wireless/core.h b/net/wireless/core.h
index c61dbba8bf47..c5d6f3418601 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -3,6 +3,7 @@
  * Wireless configuration interface internals.
  *
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright (C) 2018 Intel Corporation
  */
 #ifndef __NET_WIRELESS_CORE_H
 #define __NET_WIRELESS_CORE_H
@@ -530,4 +531,8 @@ void cfg80211_stop_nan(struct cfg80211_registered_device *rdev,
 
 void cfg80211_cqm_config_free(struct wireless_dev *wdev);
 
+void cfg80211_release_pmsr(struct wireless_dev *wdev, u32 portid);
+void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev);
+void cfg80211_pmsr_free_wk(struct work_struct *work);
+
 #endif /* __NET_WIRELESS_CORE_H */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 744b5851bbf9..6fd93eb0df6d 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -240,7 +240,63 @@ nl80211_ftm_responder_policy[NL80211_FTM_RESP_ATTR_MAX + 1] = {
 					     .len = U8_MAX },
 };
 
-static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
+static const struct nla_policy
+nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = {
+	[NL80211_PMSR_FTM_REQ_ATTR_ASAP] = { .type = NLA_FLAG },
+	[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE] = { .type = NLA_U32 },
+	[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP] =
+		NLA_POLICY_MAX(NLA_U8, 15),
+	[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD] = { .type = NLA_U16 },
+	[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION] =
+		NLA_POLICY_MAX(NLA_U8, 15),
+	[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST] =
+		NLA_POLICY_MAX(NLA_U8, 15),
+	[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES] = { .type = NLA_U8 },
+	[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI] = { .type = NLA_FLAG },
+	[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC] = { .type = NLA_FLAG },
+};
+
+static const struct nla_policy
+nl80211_pmsr_req_data_policy[NL80211_PMSR_TYPE_MAX + 1] = {
+	[NL80211_PMSR_TYPE_FTM] =
+		NLA_POLICY_NESTED(NL80211_PMSR_FTM_REQ_ATTR_MAX,
+				  nl80211_pmsr_ftm_req_attr_policy),
+};
+
+static const struct nla_policy
+nl80211_pmsr_req_attr_policy[NL80211_PMSR_REQ_ATTR_MAX + 1] = {
+	[NL80211_PMSR_REQ_ATTR_DATA] =
+		NLA_POLICY_NESTED(NL80211_PMSR_TYPE_MAX,
+				  nl80211_pmsr_req_data_policy),
+	[NL80211_PMSR_REQ_ATTR_GET_AP_TSF] = { .type = NLA_FLAG },
+};
+
+static const struct nla_policy
+nl80211_psmr_peer_attr_policy[NL80211_PMSR_PEER_ATTR_MAX + 1] = {
+	[NL80211_PMSR_PEER_ATTR_ADDR] = NLA_POLICY_ETH_ADDR,
+	/*
+	 * we could specify this again to be the top-level policy,
+	 * but that would open us up to recursion problems ...
+	 */
+	[NL80211_PMSR_PEER_ATTR_CHAN] = { .type = NLA_NESTED },
+	[NL80211_PMSR_PEER_ATTR_REQ] =
+		NLA_POLICY_NESTED(NL80211_PMSR_REQ_ATTR_MAX,
+				  nl80211_pmsr_req_attr_policy),
+	[NL80211_PMSR_PEER_ATTR_RESP] = { .type = NLA_REJECT },
+};
+
+static const struct nla_policy
+nl80211_pmsr_attr_policy[NL80211_PMSR_ATTR_MAX + 1] = {
+	[NL80211_PMSR_ATTR_MAX_PEERS] = { .type = NLA_REJECT },
+	[NL80211_PMSR_ATTR_REPORT_AP_TSF] = { .type = NLA_REJECT },
+	[NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR] = { .type = NLA_REJECT },
+	[NL80211_PMSR_ATTR_TYPE_CAPA] = { .type = NLA_REJECT },
+	[NL80211_PMSR_ATTR_PEERS] =
+		NLA_POLICY_NESTED_ARRAY(NL80211_PMSR_PEER_ATTR_MAX,
+					nl80211_psmr_peer_attr_policy),
+};
+
+const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_WIPHY] = { .type = NLA_U32 },
 	[NL80211_ATTR_WIPHY_NAME] = { .type = NLA_NUL_STRING,
 				      .len = 20-1 },
@@ -497,6 +553,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 		.type = NLA_NESTED,
 		.validation_data = nl80211_ftm_responder_policy,
 	},
+	[NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1),
+	[NL80211_ATTR_PEER_MEASUREMENTS] =
+		NLA_POLICY_NESTED(NL80211_PMSR_FTM_REQ_ATTR_MAX,
+				  nl80211_pmsr_attr_policy),
 };
 
 /* policy for the key attributes */
@@ -637,9 +697,9 @@ nl80211_packet_pattern_policy[MAX_NL80211_PKTPAT + 1] = {
 	[NL80211_PKTPAT_OFFSET] = { .type = NLA_U32 },
 };
 
-static int nl80211_prepare_wdev_dump(struct netlink_callback *cb,
-				     struct cfg80211_registered_device **rdev,
-				     struct wireless_dev **wdev)
+int nl80211_prepare_wdev_dump(struct netlink_callback *cb,
+			      struct cfg80211_registered_device **rdev,
+			      struct wireless_dev **wdev)
 {
 	int err;
 
@@ -684,8 +744,8 @@ static int nl80211_prepare_wdev_dump(struct netlink_callback *cb,
 }
 
 /* message building helper */
-static inline void *nl80211hdr_put(struct sk_buff *skb, u32 portid, u32 seq,
-				   int flags, u8 cmd)
+void *nl80211hdr_put(struct sk_buff *skb, u32 portid, u32 seq,
+		     int flags, u8 cmd)
 {
 	/* since there is no private header just add the generic one */
 	return genlmsg_put(skb, portid, seq, &nl80211_fam, flags, cmd);
@@ -1615,6 +1675,91 @@ static int nl80211_add_commands_unsplit(struct cfg80211_registered_device *rdev,
 	return -ENOBUFS;
 }
 
+static int
+nl80211_send_pmsr_ftm_capa(const struct cfg80211_pmsr_capabilities *cap,
+			   struct sk_buff *msg)
+{
+	struct nlattr *ftm;
+
+	if (!cap->ftm.supported)
+		return 0;
+
+	ftm = nla_nest_start(msg, NL80211_PMSR_TYPE_FTM);
+	if (!ftm)
+		return -ENOBUFS;
+
+	if (cap->ftm.asap && nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_ASAP))
+		return -ENOBUFS;
+	if (cap->ftm.non_asap &&
+	    nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_NON_ASAP))
+		return -ENOBUFS;
+	if (cap->ftm.request_lci &&
+	    nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_REQ_LCI))
+		return -ENOBUFS;
+	if (cap->ftm.request_civicloc &&
+	    nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_REQ_CIVICLOC))
+		return -ENOBUFS;
+	if (nla_put_u32(msg, NL80211_PMSR_FTM_CAPA_ATTR_PREAMBLES,
+			cap->ftm.preambles))
+		return -ENOBUFS;
+	if (nla_put_u32(msg, NL80211_PMSR_FTM_CAPA_ATTR_BANDWIDTHS,
+			cap->ftm.bandwidths))
+		return -ENOBUFS;
+	if (cap->ftm.max_bursts_exponent >= 0 &&
+	    nla_put_u32(msg, NL80211_PMSR_FTM_CAPA_ATTR_MAX_BURSTS_EXPONENT,
+			cap->ftm.max_bursts_exponent))
+		return -ENOBUFS;
+	if (cap->ftm.max_ftms_per_burst &&
+	    nla_put_u32(msg, NL80211_PMSR_FTM_CAPA_ATTR_MAX_FTMS_PER_BURST,
+			cap->ftm.max_ftms_per_burst))
+		return -ENOBUFS;
+
+	nla_nest_end(msg, ftm);
+	return 0;
+}
+
+static int nl80211_send_pmsr_capa(struct cfg80211_registered_device *rdev,
+				  struct sk_buff *msg)
+{
+	const struct cfg80211_pmsr_capabilities *cap = rdev->wiphy.pmsr_capa;
+	struct nlattr *pmsr, *caps;
+
+	if (!cap)
+		return 0;
+
+	/*
+	 * we don't need to clean up anything here since the caller
+	 * will genlmsg_cancel() if we fail
+	 */
+
+	pmsr = nla_nest_start(msg, NL80211_ATTR_PEER_MEASUREMENTS);
+	if (!pmsr)
+		return -ENOBUFS;
+
+	if (nla_put_u32(msg, NL80211_PMSR_ATTR_MAX_PEERS, cap->max_peers))
+		return -ENOBUFS;
+
+	if (cap->report_ap_tsf &&
+	    nla_put_flag(msg, NL80211_PMSR_ATTR_REPORT_AP_TSF))
+		return -ENOBUFS;
+
+	if (cap->randomize_mac_addr &&
+	    nla_put_flag(msg, NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR))
+		return -ENOBUFS;
+
+	caps = nla_nest_start(msg, NL80211_PMSR_ATTR_TYPE_CAPA);
+	if (!caps)
+		return -ENOBUFS;
+
+	if (nl80211_send_pmsr_ftm_capa(cap, msg))
+		return -ENOBUFS;
+
+	nla_nest_end(msg, caps);
+	nla_nest_end(msg, pmsr);
+
+	return 0;
+}
+
 struct nl80211_dump_wiphy_state {
 	s64 filter_wiphy;
 	long start;
@@ -2118,6 +2263,12 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 				goto nla_put_failure;
 		}
 
+		state->split_start++;
+		break;
+	case 14:
+		if (nl80211_send_pmsr_capa(rdev, msg))
+			goto nla_put_failure;
+
 		/* done */
 		state->split_start = 0;
 		break;
@@ -2318,9 +2469,9 @@ static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev)
 		wdev->iftype == NL80211_IFTYPE_P2P_GO;
 }
 
-static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
-				 struct genl_info *info,
-				 struct cfg80211_chan_def *chandef)
+int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
+			  struct genl_info *info,
+			  struct cfg80211_chan_def *chandef)
 {
 	struct netlink_ext_ack *extack = info->extack;
 	struct nlattr **attrs = info->attrs;
@@ -2794,12 +2945,6 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
-static inline u64 wdev_id(struct wireless_dev *wdev)
-{
-	return (u64)wdev->identifier |
-	       ((u64)wiphy_to_rdev(wdev->wiphy)->wiphy_idx << 32);
-}
-
 static int nl80211_send_chandef(struct sk_buff *msg,
 				const struct cfg80211_chan_def *chandef)
 {
@@ -4521,8 +4666,7 @@ static int parse_station_flags(struct genl_info *info,
 	return 0;
 }
 
-static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
-				 int attr)
+bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr)
 {
 	struct nlattr *rate;
 	u32 bitrate;
@@ -6855,8 +6999,8 @@ static int parse_bss_select(struct nlattr *nla, struct wiphy *wiphy,
 	return 0;
 }
 
-static int nl80211_parse_random_mac(struct nlattr **attrs,
-				    u8 *mac_addr, u8 *mac_addr_mask)
+int nl80211_parse_random_mac(struct nlattr **attrs,
+			     u8 *mac_addr, u8 *mac_addr_mask)
 {
 	int i;
 
@@ -13898,6 +14042,14 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_PEER_MEASUREMENT_START,
+		.doit = nl80211_pmsr_start,
+		.policy = nl80211_policy,
+		.flags = GENL_UNS_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 static struct genl_family nl80211_fam __ro_after_init = {
@@ -15881,6 +16033,8 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 			} else if (wdev->conn_owner_nlportid == notify->portid) {
 				schedule_work(&wdev->disconnect_wk);
 			}
+
+			cfg80211_release_pmsr(wdev, notify->portid);
 		}
 
 		spin_lock_bh(&rdev->beacon_registrations_lock);
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index 79e47fe60c35..531c82dcba6b 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -1,4 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Portions of this file
+ * Copyright (C) 2018 Intel Corporation
+ */
 #ifndef __NET_WIRELESS_NL80211_H
 #define __NET_WIRELESS_NL80211_H
 
@@ -6,6 +10,30 @@
 
 int nl80211_init(void);
 void nl80211_exit(void);
+
+extern const struct nla_policy nl80211_policy[NUM_NL80211_ATTR];
+
+void *nl80211hdr_put(struct sk_buff *skb, u32 portid, u32 seq,
+		     int flags, u8 cmd);
+bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
+			  int attr);
+
+static inline u64 wdev_id(struct wireless_dev *wdev)
+{
+	return (u64)wdev->identifier |
+	       ((u64)wiphy_to_rdev(wdev->wiphy)->wiphy_idx << 32);
+}
+
+int nl80211_prepare_wdev_dump(struct netlink_callback *cb,
+			      struct cfg80211_registered_device **rdev,
+			      struct wireless_dev **wdev);
+
+int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
+			  struct genl_info *info,
+			  struct cfg80211_chan_def *chandef);
+int nl80211_parse_random_mac(struct nlattr **attrs,
+			     u8 *mac_addr, u8 *mac_addr_mask);
+
 void nl80211_notify_wiphy(struct cfg80211_registered_device *rdev,
 			  enum nl80211_commands cmd);
 void nl80211_notify_iface(struct cfg80211_registered_device *rdev,
@@ -95,4 +123,8 @@ void nl80211_send_ap_stopped(struct wireless_dev *wdev);
 
 void cfg80211_rdev_free_coalesce(struct cfg80211_registered_device *rdev);
 
+/* peer measurement */
+int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info);
+int nl80211_pmsr_dump_results(struct sk_buff *skb, struct netlink_callback *cb);
+
 #endif /* __NET_WIRELESS_NL80211_H */
diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c
new file mode 100644
index 000000000000..de9286703280
--- /dev/null
+++ b/net/wireless/pmsr.c
@@ -0,0 +1,590 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Intel Corporation
+ */
+#ifndef __PMSR_H
+#define __PMSR_H
+#include <net/cfg80211.h>
+#include "core.h"
+#include "nl80211.h"
+#include "rdev-ops.h"
+
+static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev,
+			  struct nlattr *ftmreq,
+			  struct cfg80211_pmsr_request_peer *out,
+			  struct genl_info *info)
+{
+	const struct cfg80211_pmsr_capabilities *capa = rdev->wiphy.pmsr_capa;
+	struct nlattr *tb[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1];
+	u32 preamble = NL80211_PREAMBLE_DMG; /* only optional in DMG */
+
+	/* validate existing data */
+	if (!(rdev->wiphy.pmsr_capa->ftm.bandwidths & BIT(out->chandef.width))) {
+		NL_SET_ERR_MSG(info->extack, "FTM: unsupported bandwidth");
+		return -EINVAL;
+	}
+
+	/* no validation needed - was already done via nested policy */
+	nla_parse_nested(tb, NL80211_PMSR_FTM_REQ_ATTR_MAX, ftmreq, NULL, NULL);
+
+	if (tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE])
+		preamble = nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE]);
+
+	/* set up values - struct is 0-initialized */
+	out->ftm.requested = true;
+
+	switch (out->chandef.chan->band) {
+	case NL80211_BAND_60GHZ:
+		/* optional */
+		break;
+	default:
+		if (!tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE]) {
+			NL_SET_ERR_MSG(info->extack,
+				       "FTM: must specify preamble");
+			return -EINVAL;
+		}
+	}
+
+	if (!(capa->ftm.preambles & BIT(preamble))) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE],
+				    "FTM: invalid preamble");
+		return -EINVAL;
+	}
+
+	out->ftm.preamble = preamble;
+
+	out->ftm.burst_period = 0;
+	if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD])
+		out->ftm.burst_period =
+			nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD]);
+
+	out->ftm.asap = !!tb[NL80211_PMSR_FTM_REQ_ATTR_ASAP];
+	if (out->ftm.asap && !capa->ftm.asap) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[NL80211_PMSR_FTM_REQ_ATTR_ASAP],
+				    "FTM: ASAP mode not supported");
+		return -EINVAL;
+	}
+
+	if (!out->ftm.asap && !capa->ftm.non_asap) {
+		NL_SET_ERR_MSG(info->extack,
+			       "FTM: non-ASAP mode not supported");
+		return -EINVAL;
+	}
+
+	out->ftm.num_bursts_exp = 0;
+	if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP])
+		out->ftm.num_bursts_exp =
+			nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP]);
+
+	if (capa->ftm.max_bursts_exponent >= 0 &&
+	    out->ftm.num_bursts_exp > capa->ftm.max_bursts_exponent) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP],
+				    "FTM: max NUM_BURSTS_EXP must be set lower than the device limit");
+		return -EINVAL;
+	}
+
+	out->ftm.burst_duration = 15;
+	if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION])
+		out->ftm.burst_duration =
+			nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION]);
+
+	out->ftm.ftms_per_burst = 0;
+	if (tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST])
+		out->ftm.ftms_per_burst =
+			nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST]);
+
+	if (capa->ftm.max_ftms_per_burst &&
+	    (out->ftm.ftms_per_burst > capa->ftm.max_ftms_per_burst ||
+	     out->ftm.ftms_per_burst == 0)) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST],
+				    "FTM: FTMs per burst must be set lower than the device limit but non-zero");
+		return -EINVAL;
+	}
+
+	out->ftm.ftmr_retries = 3;
+	if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES])
+		out->ftm.ftmr_retries =
+			nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES]);
+
+	out->ftm.request_lci = !!tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI];
+	if (out->ftm.request_lci && !capa->ftm.request_lci) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI],
+				    "FTM: LCI request not supported");
+	}
+
+	out->ftm.request_civicloc =
+		!!tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC];
+	if (out->ftm.request_civicloc && !capa->ftm.request_civicloc) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC],
+			    "FTM: civic location request not supported");
+	}
+
+	return 0;
+}
+
+static int pmsr_parse_peer(struct cfg80211_registered_device *rdev,
+			   struct nlattr *peer,
+			   struct cfg80211_pmsr_request_peer *out,
+			   struct genl_info *info)
+{
+	struct nlattr *tb[NL80211_PMSR_PEER_ATTR_MAX + 1];
+	struct nlattr *req[NL80211_PMSR_REQ_ATTR_MAX + 1];
+	struct nlattr *treq;
+	int err, rem;
+
+	/* no validation needed - was already done via nested policy */
+	nla_parse_nested(tb, NL80211_PMSR_PEER_ATTR_MAX, peer, NULL, NULL);
+
+	if (!tb[NL80211_PMSR_PEER_ATTR_ADDR] ||
+	    !tb[NL80211_PMSR_PEER_ATTR_CHAN] ||
+	    !tb[NL80211_PMSR_PEER_ATTR_REQ]) {
+		NL_SET_ERR_MSG_ATTR(info->extack, peer,
+				    "insufficient peer data");
+		return -EINVAL;
+	}
+
+	memcpy(out->addr, nla_data(tb[NL80211_PMSR_PEER_ATTR_ADDR]), ETH_ALEN);
+
+	/* reuse info->attrs */
+	memset(info->attrs, 0, sizeof(*info->attrs) * (NL80211_ATTR_MAX + 1));
+	/* need to validate here, we don't want to have validation recursion */
+	err = nla_parse_nested(info->attrs, NL80211_ATTR_MAX,
+			       tb[NL80211_PMSR_PEER_ATTR_CHAN],
+			       nl80211_policy, info->extack);
+	if (err)
+		return err;
+
+	err = nl80211_parse_chandef(rdev, info, &out->chandef);
+	if (err)
+		return err;
+
+	/* no validation needed - was already done via nested policy */
+	nla_parse_nested(req, NL80211_PMSR_REQ_ATTR_MAX,
+			 tb[NL80211_PMSR_PEER_ATTR_REQ],
+			 NULL, NULL);
+
+	if (!req[NL80211_PMSR_REQ_ATTR_DATA]) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[NL80211_PMSR_PEER_ATTR_REQ],
+				    "missing request type/data");
+		return -EINVAL;
+	}
+
+	if (req[NL80211_PMSR_REQ_ATTR_GET_AP_TSF])
+		out->report_ap_tsf = true;
+
+	if (out->report_ap_tsf && !rdev->wiphy.pmsr_capa->report_ap_tsf) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    req[NL80211_PMSR_REQ_ATTR_GET_AP_TSF],
+				    "reporting AP TSF is not supported");
+		return -EINVAL;
+	}
+
+	nla_for_each_nested(treq, req[NL80211_PMSR_REQ_ATTR_DATA], rem) {
+		switch (nla_type(treq)) {
+		case NL80211_PMSR_TYPE_FTM:
+			err = pmsr_parse_ftm(rdev, treq, out, info);
+			break;
+		default:
+			NL_SET_ERR_MSG_ATTR(info->extack, treq,
+					    "unsupported measurement type");
+			err = -EINVAL;
+		}
+	}
+
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr *reqattr = info->attrs[NL80211_ATTR_PEER_MEASUREMENTS];
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct wireless_dev *wdev = info->user_ptr[1];
+	struct cfg80211_pmsr_request *req;
+	struct nlattr *peers, *peer;
+	int count, rem, err, idx;
+
+	if (!rdev->wiphy.pmsr_capa)
+		return -EOPNOTSUPP;
+
+	if (!reqattr)
+		return -EINVAL;
+
+	peers = nla_find(nla_data(reqattr), nla_len(reqattr),
+			 NL80211_PMSR_ATTR_PEERS);
+	if (!peers)
+		return -EINVAL;
+
+	count = 0;
+	nla_for_each_nested(peer, peers, rem) {
+		count++;
+
+		if (count > rdev->wiphy.pmsr_capa->max_peers) {
+			NL_SET_ERR_MSG_ATTR(info->extack, peer,
+					    "Too many peers used");
+			return -EINVAL;
+		}
+	}
+
+	req = kzalloc(struct_size(req, peers, count), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	if (info->attrs[NL80211_ATTR_TIMEOUT])
+		req->timeout = nla_get_u32(info->attrs[NL80211_ATTR_TIMEOUT]);
+
+	if (info->attrs[NL80211_ATTR_MAC]) {
+		if (!rdev->wiphy.pmsr_capa->randomize_mac_addr) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    info->attrs[NL80211_ATTR_MAC],
+					    "device cannot randomize MAC address");
+			err = -EINVAL;
+			goto out_err;
+		}
+
+		err = nl80211_parse_random_mac(info->attrs, req->mac_addr,
+					       req->mac_addr_mask);
+		if (err)
+			goto out_err;
+	} else {
+		memcpy(req->mac_addr, nla_data(info->attrs[NL80211_ATTR_MAC]),
+		       ETH_ALEN);
+		memset(req->mac_addr_mask, 0xff, ETH_ALEN);
+	}
+
+	idx = 0;
+	nla_for_each_nested(peer, peers, rem) {
+		/* NB: this reuses info->attrs, but we no longer need it */
+		err = pmsr_parse_peer(rdev, peer, &req->peers[idx], info);
+		if (err)
+			goto out_err;
+		idx++;
+	}
+
+	req->n_peers = count;
+	req->cookie = cfg80211_assign_cookie(rdev);
+
+	err = rdev_start_pmsr(rdev, wdev, req);
+	if (err)
+		goto out_err;
+
+	list_add_tail(&req->list, &wdev->pmsr_list);
+
+	nl_set_extack_cookie_u64(info->extack, req->cookie);
+	return 0;
+out_err:
+	kfree(req);
+	return err;
+}
+
+void cfg80211_pmsr_complete(struct wireless_dev *wdev,
+			    struct cfg80211_pmsr_request *req,
+			    gfp_t gfp)
+{
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+	struct sk_buff *msg;
+	void *hdr;
+
+	trace_cfg80211_pmsr_complete(wdev->wiphy, wdev, req->cookie);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
+	if (!msg)
+		goto free_request;
+
+	hdr = nl80211hdr_put(msg, 0, 0, 0,
+			     NL80211_CMD_PEER_MEASUREMENT_COMPLETE);
+	if (!hdr)
+		goto free_msg;
+
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
+	    nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev),
+			      NL80211_ATTR_PAD))
+		goto free_msg;
+
+	if (nla_put_u64_64bit(msg, NL80211_ATTR_COOKIE, req->cookie,
+			      NL80211_ATTR_PAD))
+		goto free_msg;
+
+	genlmsg_end(msg, hdr);
+	genlmsg_unicast(wiphy_net(wdev->wiphy), msg, req->nl_portid);
+	goto free_request;
+free_msg:
+	nlmsg_free(msg);
+free_request:
+	spin_lock_bh(&wdev->pmsr_lock);
+	list_del(&req->list);
+	spin_unlock_bh(&wdev->pmsr_lock);
+	kfree(req);
+}
+EXPORT_SYMBOL_GPL(cfg80211_pmsr_complete);
+
+static int nl80211_pmsr_send_ftm_res(struct sk_buff *msg,
+				     struct cfg80211_pmsr_result *res)
+{
+	if (res->status == NL80211_PMSR_STATUS_FAILURE) {
+		if (nla_put_u32(msg, NL80211_PMSR_FTM_RESP_ATTR_FAIL_REASON,
+				res->ftm.failure_reason))
+			goto error;
+
+		if (res->ftm.failure_reason ==
+			NL80211_PMSR_FTM_FAILURE_PEER_BUSY &&
+		    res->ftm.busy_retry_time &&
+		    nla_put_u32(msg, NL80211_PMSR_FTM_RESP_ATTR_BUSY_RETRY_TIME,
+				res->ftm.busy_retry_time))
+			goto error;
+
+		return 0;
+	}
+
+#define PUT(tp, attr, val)						\
+	do {								\
+		if (nla_put_##tp(msg,					\
+				 NL80211_PMSR_FTM_RESP_ATTR_##attr,	\
+				 res->ftm.val))				\
+			goto error;					\
+	} while (0)
+
+#define PUTOPT(tp, attr, val)						\
+	do {								\
+		if (res->ftm.val##_valid)				\
+			PUT(tp, attr, val);				\
+	} while (0)
+
+#define PUT_U64(attr, val)						\
+	do {								\
+		if (nla_put_u64_64bit(msg,				\
+				      NL80211_PMSR_FTM_RESP_ATTR_##attr,\
+				      res->ftm.val,			\
+				      NL80211_PMSR_FTM_RESP_ATTR_PAD))	\
+			goto error;					\
+	} while (0)
+
+#define PUTOPT_U64(attr, val)						\
+	do {								\
+		if (res->ftm.val##_valid)				\
+			PUT_U64(attr, val);				\
+	} while (0)
+
+	if (res->ftm.burst_index >= 0)
+		PUT(u32, BURST_INDEX, burst_index);
+	PUTOPT(u32, NUM_FTMR_ATTEMPTS, num_ftmr_attempts);
+	PUTOPT(u32, NUM_FTMR_SUCCESSES, num_ftmr_successes);
+	PUT(u8, NUM_BURSTS_EXP, num_bursts_exp);
+	PUT(u8, BURST_DURATION, burst_duration);
+	PUT(u8, FTMS_PER_BURST, ftms_per_burst);
+	PUTOPT(s32, RSSI_AVG, rssi_avg);
+	PUTOPT(s32, RSSI_SPREAD, rssi_spread);
+	if (res->ftm.tx_rate_valid &&
+	    !nl80211_put_sta_rate(msg, &res->ftm.tx_rate,
+				  NL80211_PMSR_FTM_RESP_ATTR_TX_RATE))
+		goto error;
+	if (res->ftm.rx_rate_valid &&
+	    !nl80211_put_sta_rate(msg, &res->ftm.rx_rate,
+				  NL80211_PMSR_FTM_RESP_ATTR_RX_RATE))
+		goto error;
+	PUTOPT_U64(RTT_AVG, rtt_avg);
+	PUTOPT_U64(RTT_VARIANCE, rtt_variance);
+	PUTOPT_U64(RTT_SPREAD, rtt_spread);
+	PUTOPT_U64(DIST_AVG, dist_avg);
+	PUTOPT_U64(DIST_VARIANCE, dist_variance);
+	PUTOPT_U64(DIST_SPREAD, dist_spread);
+	if (res->ftm.lci && res->ftm.lci_len &&
+	    nla_put(msg, NL80211_PMSR_FTM_RESP_ATTR_LCI,
+		    res->ftm.lci_len, res->ftm.lci))
+		goto error;
+	if (res->ftm.civicloc && res->ftm.civicloc_len &&
+	    nla_put(msg, NL80211_PMSR_FTM_RESP_ATTR_CIVICLOC,
+		    res->ftm.civicloc_len, res->ftm.civicloc))
+		goto error;
+#undef PUT
+#undef PUTOPT
+#undef PUT_U64
+#undef PUTOPT_U64
+
+	return 0;
+error:
+	return -ENOSPC;
+}
+
+static int nl80211_pmsr_send_result(struct sk_buff *msg,
+				    struct cfg80211_pmsr_result *res)
+{
+	struct nlattr *pmsr, *peers, *peer, *resp, *data, *typedata;
+
+	pmsr = nla_nest_start(msg, NL80211_ATTR_PEER_MEASUREMENTS);
+	if (!pmsr)
+		goto error;
+
+	peers = nla_nest_start(msg, NL80211_PMSR_ATTR_PEERS);
+	if (!peers)
+		goto error;
+
+	peer = nla_nest_start(msg, 1);
+	if (!peer)
+		goto error;
+
+	if (nla_put(msg, NL80211_PMSR_PEER_ATTR_ADDR, ETH_ALEN, res->addr))
+		goto error;
+
+	resp = nla_nest_start(msg, NL80211_PMSR_PEER_ATTR_RESP);
+	if (!resp)
+		goto error;
+
+	if (nla_put_u32(msg, NL80211_PMSR_RESP_ATTR_STATUS, res->status) ||
+	    nla_put_u64_64bit(msg, NL80211_PMSR_RESP_ATTR_HOST_TIME,
+			      res->host_time, NL80211_PMSR_RESP_ATTR_PAD))
+		goto error;
+
+	if (res->ap_tsf_valid &&
+	    nla_put_u64_64bit(msg, NL80211_PMSR_RESP_ATTR_AP_TSF,
+			      res->host_time, NL80211_PMSR_RESP_ATTR_PAD))
+		goto error;
+
+	if (res->final && nla_put_flag(msg, NL80211_PMSR_RESP_ATTR_FINAL))
+		goto error;
+
+	data = nla_nest_start(msg, NL80211_PMSR_RESP_ATTR_DATA);
+	if (!data)
+		goto error;
+
+	typedata = nla_nest_start(msg, res->type);
+	if (!typedata)
+		goto error;
+
+	switch (res->type) {
+	case NL80211_PMSR_TYPE_FTM:
+		if (nl80211_pmsr_send_ftm_res(msg, res))
+			goto error;
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	nla_nest_end(msg, typedata);
+	nla_nest_end(msg, data);
+	nla_nest_end(msg, resp);
+	nla_nest_end(msg, peer);
+	nla_nest_end(msg, peers);
+	nla_nest_end(msg, pmsr);
+
+	return 0;
+error:
+	return -ENOSPC;
+}
+
+void cfg80211_pmsr_report(struct wireless_dev *wdev,
+			  struct cfg80211_pmsr_request *req,
+			  struct cfg80211_pmsr_result *result,
+			  gfp_t gfp)
+{
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+	struct sk_buff *msg;
+	void *hdr;
+	int err;
+
+	trace_cfg80211_pmsr_report(wdev->wiphy, wdev, req->cookie,
+				   result->addr);
+
+	/*
+	 * Currently, only variable items are LCI and civic location,
+	 * both of which are reasonably short so we don't need to
+	 * worry about them here for the allocation.
+	 */
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
+	if (!msg)
+		return;
+
+	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_PEER_MEASUREMENT_RESULT);
+	if (!hdr)
+		goto free;
+
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
+	    nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev),
+			      NL80211_ATTR_PAD))
+		goto free;
+
+	if (nla_put_u64_64bit(msg, NL80211_ATTR_COOKIE, req->cookie,
+			      NL80211_ATTR_PAD))
+		goto free;
+
+	err = nl80211_pmsr_send_result(msg, result);
+	if (err) {
+		pr_err_ratelimited("peer measurement result: message didn't fit!");
+		goto free;
+	}
+
+	genlmsg_end(msg, hdr);
+	genlmsg_unicast(wiphy_net(wdev->wiphy), msg, req->nl_portid);
+	return;
+free:
+	nlmsg_free(msg);
+}
+EXPORT_SYMBOL_GPL(cfg80211_pmsr_report);
+
+void cfg80211_pmsr_free_wk(struct work_struct *work)
+{
+	struct wireless_dev *wdev = container_of(work, struct wireless_dev,
+						 pmsr_free_wk);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+	struct cfg80211_pmsr_request *req, *tmp;
+	LIST_HEAD(free_list);
+
+	spin_lock_bh(&wdev->pmsr_lock);
+	list_for_each_entry_safe(req, tmp, &wdev->pmsr_list, list) {
+		if (req->nl_portid)
+			continue;
+		list_move_tail(&req->list, &free_list);
+	}
+	spin_unlock_bh(&wdev->pmsr_lock);
+
+	list_for_each_entry_safe(req, tmp, &free_list, list) {
+		wdev_lock(wdev);
+		rdev_abort_pmsr(rdev, wdev, req);
+		wdev_unlock(wdev);
+
+		kfree(req);
+	}
+}
+
+void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev)
+{
+	struct cfg80211_pmsr_request *req;
+	bool found = false;
+
+	spin_lock_bh(&wdev->pmsr_lock);
+	list_for_each_entry(req, &wdev->pmsr_list, list) {
+		found = true;
+		req->nl_portid = 0;
+	}
+	spin_unlock_bh(&wdev->pmsr_lock);
+
+	if (found)
+		schedule_work(&wdev->pmsr_free_wk);
+	flush_work(&wdev->pmsr_free_wk);
+	WARN_ON(!list_empty(&wdev->pmsr_list));
+}
+
+void cfg80211_release_pmsr(struct wireless_dev *wdev, u32 portid)
+{
+	struct cfg80211_pmsr_request *req;
+
+	spin_lock_bh(&wdev->pmsr_lock);
+	list_for_each_entry(req, &wdev->pmsr_list, list) {
+		if (req->nl_portid == portid) {
+			req->nl_portid = 0;
+			schedule_work(&wdev->pmsr_free_wk);
+		}
+	}
+	spin_unlock_bh(&wdev->pmsr_lock);
+}
+
+#endif /* __PMSR_H */
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 51380b5c32f2..5cb48d135fab 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -1247,4 +1247,29 @@ rdev_get_ftm_responder_stats(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int
+rdev_start_pmsr(struct cfg80211_registered_device *rdev,
+		struct wireless_dev *wdev,
+		struct cfg80211_pmsr_request *request)
+{
+	int ret = -EOPNOTSUPP;
+
+	trace_rdev_start_pmsr(&rdev->wiphy, wdev, request->cookie);
+	if (rdev->ops->start_pmsr)
+		ret = rdev->ops->start_pmsr(&rdev->wiphy, wdev, request);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+	return ret;
+}
+
+static inline void
+rdev_abort_pmsr(struct cfg80211_registered_device *rdev,
+		struct wireless_dev *wdev,
+		struct cfg80211_pmsr_request *request)
+{
+	trace_rdev_abort_pmsr(&rdev->wiphy, wdev, request->cookie);
+	if (rdev->ops->abort_pmsr)
+		rdev->ops->abort_pmsr(&rdev->wiphy, wdev, request);
+	trace_rdev_return_void(&rdev->wiphy);
+}
+
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index f7909867d8fb..44b2ce1bb13a 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -361,6 +361,24 @@ DECLARE_EVENT_CLASS(wiphy_wdev_evt,
 	TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT, WIPHY_PR_ARG, WDEV_PR_ARG)
 );
 
+DECLARE_EVENT_CLASS(wiphy_wdev_cookie_evt,
+	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie),
+	TP_ARGS(wiphy, wdev, cookie),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		WDEV_ENTRY
+		__field(u64, cookie)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		WDEV_ASSIGN;
+		__entry->cookie = cookie;
+	),
+	TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", cookie: %lld",
+		  WIPHY_PR_ARG, WDEV_PR_ARG,
+		  (unsigned long long)__entry->cookie)
+);
+
 DEFINE_EVENT(wiphy_wdev_evt, rdev_return_wdev,
 	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev),
 	TP_ARGS(wiphy, wdev)
@@ -2502,6 +2520,16 @@ TRACE_EVENT(rdev_get_ftm_responder_stats,
 		__entry->out_of_window)
 );
 
+DEFINE_EVENT(wiphy_wdev_cookie_evt, rdev_start_pmsr,
+	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie),
+	TP_ARGS(wiphy, wdev, cookie)
+);
+
+DEFINE_EVENT(wiphy_wdev_cookie_evt, rdev_abort_pmsr,
+	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie),
+	TP_ARGS(wiphy, wdev, cookie)
+);
+
 /*************************************************************
  *	     cfg80211 exported functions traces		     *
  *************************************************************/
@@ -3294,6 +3322,46 @@ TRACE_EVENT(cfg80211_stop_iface,
 	TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT,
 		  WIPHY_PR_ARG, WDEV_PR_ARG)
 );
+
+TRACE_EVENT(cfg80211_pmsr_report,
+	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev,
+		 u64 cookie, const u8 *addr),
+	TP_ARGS(wiphy, wdev, cookie, addr),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		WDEV_ENTRY
+		__field(u64, cookie)
+		MAC_ENTRY(addr)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		WDEV_ASSIGN;
+		__entry->cookie = cookie;
+		MAC_ASSIGN(addr, addr);
+	),
+	TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", cookie:%lld, " MAC_PR_FMT,
+		  WIPHY_PR_ARG, WDEV_PR_ARG,
+		  (unsigned long long)__entry->cookie,
+		  MAC_PR_ARG(addr))
+);
+
+TRACE_EVENT(cfg80211_pmsr_complete,
+	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie),
+	TP_ARGS(wiphy, wdev, cookie),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		WDEV_ENTRY
+		__field(u64, cookie)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		WDEV_ASSIGN;
+		__entry->cookie = cookie;
+	),
+	TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", cookie:%lld",
+		  WIPHY_PR_ARG, WDEV_PR_ARG,
+		  (unsigned long long)__entry->cookie)
+);
 #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
-- 
cgit v1.2.3


From cee7013be9b71082c7ea63c46850157aaa1bf4b1 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 16 Oct 2018 11:24:47 +0200
Subject: mac80211: allow drivers to use peer measurement API

There's nothing much for mac80211 to do, so only pass through
the requests with minimal checks and tracing. The driver must
call cfg80211's results APIs.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    |  7 +++++++
 net/mac80211/cfg.c        | 22 ++++++++++++++++++++++
 net/mac80211/driver-ops.h | 34 ++++++++++++++++++++++++++++++++++
 net/mac80211/trace.h      | 12 ++++++++++++
 4 files changed, 75 insertions(+)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 71985e95d2d9..e3d57e7a55cc 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3623,6 +3623,9 @@ enum ieee80211_reconfig_type {
  *	skb is always a real frame, head may or may not be an A-MSDU.
  * @get_ftm_responder_stats: Retrieve FTM responder statistics, if available.
  *	Statistics should be cumulative, currently no way to reset is provided.
+ *
+ * @start_pmsr: start peer measurement (e.g. FTM) (this call can sleep)
+ * @abort_pmsr: abort peer measurement (this call can sleep)
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -3911,6 +3914,10 @@ struct ieee80211_ops {
 	int (*get_ftm_responder_stats)(struct ieee80211_hw *hw,
 				       struct ieee80211_vif *vif,
 				       struct cfg80211_ftm_responder_stats *ftm_stats);
+	int (*start_pmsr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			  struct cfg80211_pmsr_request *request);
+	void (*abort_pmsr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			   struct cfg80211_pmsr_request *request);
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 51622333d460..2fccccfbbf4d 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3849,6 +3849,26 @@ ieee80211_get_ftm_responder_stats(struct wiphy *wiphy,
 	return drv_get_ftm_responder_stats(local, sdata, ftm_stats);
 }
 
+static int
+ieee80211_start_pmsr(struct wiphy *wiphy, struct wireless_dev *dev,
+		     struct cfg80211_pmsr_request *request)
+{
+	struct ieee80211_local *local = wiphy_priv(wiphy);
+	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(dev);
+
+	return drv_start_pmsr(local, sdata, request);
+}
+
+static void
+ieee80211_abort_pmsr(struct wiphy *wiphy, struct wireless_dev *dev,
+		     struct cfg80211_pmsr_request *request)
+{
+	struct ieee80211_local *local = wiphy_priv(wiphy);
+	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(dev);
+
+	return drv_abort_pmsr(local, sdata, request);
+}
+
 const struct cfg80211_ops mac80211_config_ops = {
 	.add_virtual_intf = ieee80211_add_iface,
 	.del_virtual_intf = ieee80211_del_iface,
@@ -3944,4 +3964,6 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.tx_control_port = ieee80211_tx_control_port,
 	.get_txq_stats = ieee80211_get_txq_stats,
 	.get_ftm_responder_stats = ieee80211_get_ftm_responder_stats,
+	.start_pmsr = ieee80211_start_pmsr,
+	.abort_pmsr = ieee80211_abort_pmsr,
 };
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 0b1747a2313d..3e0d5922a440 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1199,6 +1199,40 @@ drv_get_ftm_responder_stats(struct ieee80211_local *local,
 	return ret;
 }
 
+static inline int drv_start_pmsr(struct ieee80211_local *local,
+				 struct ieee80211_sub_if_data *sdata,
+				 struct cfg80211_pmsr_request *request)
+{
+	int ret = -EOPNOTSUPP;
+
+	might_sleep();
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
+
+	trace_drv_start_pmsr(local, sdata);
+
+	if (local->ops->start_pmsr)
+		ret = local->ops->start_pmsr(&local->hw, &sdata->vif, request);
+	trace_drv_return_int(local, ret);
+
+	return ret;
+}
+
+static inline void drv_abort_pmsr(struct ieee80211_local *local,
+				  struct ieee80211_sub_if_data *sdata,
+				  struct cfg80211_pmsr_request *request)
+{
+	trace_drv_abort_pmsr(local, sdata);
+
+	might_sleep();
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	if (local->ops->abort_pmsr)
+		local->ops->abort_pmsr(&local->hw, &sdata->vif, request);
+	trace_drv_return_void(local);
+}
+
 static inline int drv_start_nan(struct ieee80211_local *local,
 				struct ieee80211_sub_if_data *sdata,
 				struct cfg80211_nan_conf *conf)
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index a152263478dc..35ea0dcb55e6 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -1882,6 +1882,18 @@ TRACE_EVENT(drv_del_nan_func,
 	)
 );
 
+DEFINE_EVENT(local_sdata_evt, drv_start_pmsr,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata),
+	TP_ARGS(local, sdata)
+);
+
+DEFINE_EVENT(local_sdata_evt, drv_abort_pmsr,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata),
+	TP_ARGS(local, sdata)
+);
+
 /*
  * Tracing for API calls that drivers call.
  */
-- 
cgit v1.2.3


From c90b670b5c610266e255848f7fc774b57189a9a4 Mon Sep 17 00:00:00 2001
From: Martin Willi <martin@strongswan.org>
Date: Sat, 27 Oct 2018 09:31:24 +0200
Subject: nl80211: announce radios/interfaces when switching namespaces

When a wiphy changes its namespace, all interfaces are moved to the
new namespace as well. The network interfaces are properly announced
as leaving on the old and as appearing on the new namespace through
RTM_NEWLINK/RTM_DELLINK. On nl80211, however, these events are missing
for radios and their interfaces.

Add netlink announcements through nl80211 when switching namespaces,
so userspace can rely on these events to discover radios properly.

Signed-off-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/net/wireless/core.c b/net/wireless/core.c
index 0a3092c56b3e..623dfe5e211c 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -191,11 +191,25 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
 		return err;
 	}
 
+	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
+		if (!wdev->netdev)
+			continue;
+		nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE);
+	}
+	nl80211_notify_wiphy(rdev, NL80211_CMD_DEL_WIPHY);
+
 	wiphy_net_set(&rdev->wiphy, net);
 
 	err = device_rename(&rdev->wiphy.dev, dev_name(&rdev->wiphy.dev));
 	WARN_ON(err);
 
+	nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY);
+	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
+		if (!wdev->netdev)
+			continue;
+		nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE);
+	}
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 3d1a5bbfafbc655c05bfe87cfec2816f0a981565 Mon Sep 17 00:00:00 2001
From: Andrew Zaborowski <andrew.zaborowski@intel.com>
Date: Fri, 19 Oct 2018 23:19:06 +0200
Subject: nl80211: Emit a SET_INTERFACE on iftype change

Let userspace learn about iftype changes by sending a notification
when handling the NL80211_CMD_SET_INTERFACE command.  There seems
to be no other place where the iftype can change: nl80211_set_interface
is the only caller of cfg80211_change_iface which is the only caller of
ops->change_virtual_intf.

Signed-off-by: Andrew Zaborowski <andrew.zaborowski@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 6fd93eb0df6d..5e7178954d61 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2977,14 +2977,15 @@ static int nl80211_send_chandef(struct sk_buff *msg,
 
 static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags,
 			      struct cfg80211_registered_device *rdev,
-			      struct wireless_dev *wdev, bool removal)
+			      struct wireless_dev *wdev,
+			      enum nl80211_commands cmd)
 {
 	struct net_device *dev = wdev->netdev;
-	u8 cmd = NL80211_CMD_NEW_INTERFACE;
 	void *hdr;
 
-	if (removal)
-		cmd = NL80211_CMD_DEL_INTERFACE;
+	WARN_ON(cmd != NL80211_CMD_NEW_INTERFACE &&
+		cmd != NL80211_CMD_DEL_INTERFACE &&
+		cmd != NL80211_CMD_SET_INTERFACE);
 
 	hdr = nl80211hdr_put(msg, portid, seq, flags, cmd);
 	if (!hdr)
@@ -3132,7 +3133,8 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 			}
 			if (nl80211_send_iface(skb, NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					       rdev, wdev, false) < 0) {
+					       rdev, wdev,
+					       NL80211_CMD_NEW_INTERFACE) < 0) {
 				goto out;
 			}
 			if_idx++;
@@ -3162,7 +3164,7 @@ static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 
 	if (nl80211_send_iface(msg, info->snd_portid, info->snd_seq, 0,
-			       rdev, wdev, false) < 0) {
+			       rdev, wdev, NL80211_CMD_NEW_INTERFACE) < 0) {
 		nlmsg_free(msg);
 		return -ENOBUFS;
 	}
@@ -3352,6 +3354,12 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info)
 	if (!err && params.use_4addr != -1)
 		dev->ieee80211_ptr->use_4addr = params.use_4addr;
 
+	if (change && !err) {
+		struct wireless_dev *wdev = dev->ieee80211_ptr;
+
+		nl80211_notify_iface(rdev, wdev, NL80211_CMD_SET_INTERFACE);
+	}
+
 	return err;
 }
 
@@ -3443,7 +3451,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (nl80211_send_iface(msg, info->snd_portid, info->snd_seq, 0,
-			       rdev, wdev, false) < 0) {
+			       rdev, wdev, NL80211_CMD_NEW_INTERFACE) < 0) {
 		nlmsg_free(msg);
 		return -ENOBUFS;
 	}
@@ -14097,15 +14105,11 @@ void nl80211_notify_iface(struct cfg80211_registered_device *rdev,
 {
 	struct sk_buff *msg;
 
-	WARN_ON(cmd != NL80211_CMD_NEW_INTERFACE &&
-		cmd != NL80211_CMD_DEL_INTERFACE);
-
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return;
 
-	if (nl80211_send_iface(msg, 0, 0, 0, rdev, wdev,
-			       cmd == NL80211_CMD_DEL_INTERFACE) < 0) {
+	if (nl80211_send_iface(msg, 0, 0, 0, rdev, wdev, cmd) < 0) {
 		nlmsg_free(msg);
 		return;
 	}
-- 
cgit v1.2.3


From 2f98abb17dd57b9c3ebdf6741ae2726ed360d902 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 9 Nov 2018 11:32:39 +0100
Subject: mac80211_hwsim: move HWSIM_ATTR_RADIO_NAME parsing last

Avoid the need to kfree() the name in many places by moving
the name parsing last.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index aa8058264d5b..05408345b03d 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -3321,15 +3321,6 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 	if (info->attrs[HWSIM_ATTR_NO_VIF])
 		param.no_vif = true;
 
-	if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
-		hwname = kasprintf(GFP_KERNEL, "%.*s",
-				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
-				   (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]));
-		if (!hwname)
-			return -ENOMEM;
-		param.hwname = hwname;
-	}
-
 	if (info->attrs[HWSIM_ATTR_USE_CHANCTX])
 		param.use_chanctx = true;
 	else
@@ -3342,10 +3333,8 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 	if (info->attrs[HWSIM_ATTR_REG_CUSTOM_REG]) {
 		u32 idx = nla_get_u32(info->attrs[HWSIM_ATTR_REG_CUSTOM_REG]);
 
-		if (idx >= ARRAY_SIZE(hwsim_world_regdom_custom)) {
-			kfree(hwname);
+		if (idx >= ARRAY_SIZE(hwsim_world_regdom_custom))
 			return -EINVAL;
-		}
 
 		idx = array_index_nospec(idx,
 					 ARRAY_SIZE(hwsim_world_regdom_custom));
@@ -3358,7 +3347,6 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 			GENL_SET_ERR_MSG(info,"MAC is no valid source addr");
 			NL_SET_BAD_ATTR(info->extack,
 					info->attrs[HWSIM_ATTR_PERM_ADDR]);
-			kfree(hwname);
 			return -EINVAL;
 		}
 
@@ -3366,6 +3354,15 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 		param.perm_addr = nla_data(info->attrs[HWSIM_ATTR_PERM_ADDR]);
 	}
 
+	if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
+		hwname = kasprintf(GFP_KERNEL, "%.*s",
+				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				   (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]));
+		if (!hwname)
+			return -ENOMEM;
+		param.hwname = hwname;
+	}
+
 	ret = mac80211_hwsim_new_radio(info, &param);
 	kfree(hwname);
 	return ret;
-- 
cgit v1.2.3


From 99e3a44bac37ff033af711ec2ee8e48b6fabcad3 Mon Sep 17 00:00:00 2001
From: James Prestwood <james.prestwood@linux.intel.com>
Date: Wed, 17 Oct 2018 12:33:06 -0700
Subject: mac80211_hwsim: allow setting iftype support

The mac80211_hwsim driver hard codes its supported interface types. For
testing purposes it would be valuable to allow changing these supported
types in order to simulate actual drivers than support a limited set of
iftypes. A new attribute was added to allow this:

- HWSIM_ATTR_IFTYPE_SUPPORT
	A u32 bit field of supported NL80211_IFTYPE_* bits

This will only enable/disable iftypes that mac80211_hwsim already
supports.

In order to accomplish this, the ieee80211_iface_limit structure needed
to be built dynamically to only include limit rules for iftypes that
the user requested to enable.

Signed-off-by: James Prestwood <james.prestwood@linux.intel.com>
[fix some indentation, add netlink error string]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c | 155 +++++++++++++++++++---------------
 drivers/net/wireless/mac80211_hwsim.h |   2 +
 2 files changed, 91 insertions(+), 66 deletions(-)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 05408345b03d..2fbea02e289a 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -451,48 +451,6 @@ static const struct nl80211_vendor_cmd_info mac80211_hwsim_vendor_events[] = {
 	{ .vendor_id = OUI_QCA, .subcmd = 1 },
 };
 
-static const struct ieee80211_iface_limit hwsim_if_limits[] = {
-	{ .max = 1, .types = BIT(NL80211_IFTYPE_ADHOC) },
-	{ .max = 2048,  .types = BIT(NL80211_IFTYPE_STATION) |
-				 BIT(NL80211_IFTYPE_P2P_CLIENT) |
-#ifdef CONFIG_MAC80211_MESH
-				 BIT(NL80211_IFTYPE_MESH_POINT) |
-#endif
-				 BIT(NL80211_IFTYPE_AP) |
-				 BIT(NL80211_IFTYPE_P2P_GO) },
-	/* must be last, see hwsim_if_comb */
-	{ .max = 1, .types = BIT(NL80211_IFTYPE_P2P_DEVICE) }
-};
-
-static const struct ieee80211_iface_combination hwsim_if_comb[] = {
-	{
-		.limits = hwsim_if_limits,
-		/* remove the last entry which is P2P_DEVICE */
-		.n_limits = ARRAY_SIZE(hwsim_if_limits) - 1,
-		.max_interfaces = 2048,
-		.num_different_channels = 1,
-		.radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) |
-				       BIT(NL80211_CHAN_WIDTH_20) |
-				       BIT(NL80211_CHAN_WIDTH_40) |
-				       BIT(NL80211_CHAN_WIDTH_80) |
-				       BIT(NL80211_CHAN_WIDTH_160),
-	},
-};
-
-static const struct ieee80211_iface_combination hwsim_if_comb_p2p_dev[] = {
-	{
-		.limits = hwsim_if_limits,
-		.n_limits = ARRAY_SIZE(hwsim_if_limits),
-		.max_interfaces = 2048,
-		.num_different_channels = 1,
-		.radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) |
-				       BIT(NL80211_CHAN_WIDTH_20) |
-				       BIT(NL80211_CHAN_WIDTH_40) |
-				       BIT(NL80211_CHAN_WIDTH_80) |
-				       BIT(NL80211_CHAN_WIDTH_160),
-	},
-};
-
 static spinlock_t hwsim_radio_lock;
 static LIST_HEAD(hwsim_radios);
 static struct rhashtable hwsim_radios_rht;
@@ -515,6 +473,8 @@ struct mac80211_hwsim_data {
 	struct ieee80211_channel channels_5ghz[ARRAY_SIZE(hwsim_channels_5ghz)];
 	struct ieee80211_rate rates[ARRAY_SIZE(hwsim_rates)];
 	struct ieee80211_iface_combination if_combination;
+	struct ieee80211_iface_limit if_limits[3];
+	int n_if_limits;
 
 	struct mac_address addresses[2];
 	int channels, idx;
@@ -642,6 +602,7 @@ static const struct nla_policy hwsim_genl_policy[HWSIM_ATTR_MAX + 1] = {
 	[HWSIM_ATTR_NO_VIF] = { .type = NLA_FLAG },
 	[HWSIM_ATTR_FREQ] = { .type = NLA_U32 },
 	[HWSIM_ATTR_PERM_ADDR] = { .type = NLA_UNSPEC, .len = ETH_ALEN },
+	[HWSIM_ATTR_IFTYPE_SUPPORT] = { .type = NLA_U32 },
 };
 
 static void mac80211_hwsim_tx_frame(struct ieee80211_hw *hw,
@@ -2414,6 +2375,7 @@ struct hwsim_new_radio_params {
 	const char *hwname;
 	bool no_vif;
 	const u8 *perm_addr;
+	u32 iftypes;
 };
 
 static void hwsim_mcast_config_msg(struct sk_buff *mcast_skb,
@@ -2630,6 +2592,27 @@ static void mac80211_hswim_he_capab(struct ieee80211_supported_band *sband)
 	sband->n_iftype_data = 1;
 }
 
+#ifdef CONFIG_MAC80211_MESH
+#define HWSIM_MESH_BIT BIT(NL80211_IFTYPE_MESH_POINT)
+#else
+#define HWSIM_MESH_BIT 0
+#endif
+
+#define HWSIM_DEFAULT_IF_LIMIT \
+	(BIT(NL80211_IFTYPE_STATION) | \
+	 BIT(NL80211_IFTYPE_P2P_CLIENT) | \
+	 BIT(NL80211_IFTYPE_AP) | \
+	 BIT(NL80211_IFTYPE_P2P_GO) | \
+	 HWSIM_MESH_BIT)
+
+#define HWSIM_IFTYPE_SUPPORT_MASK \
+	(BIT(NL80211_IFTYPE_STATION) | \
+	 BIT(NL80211_IFTYPE_AP) | \
+	 BIT(NL80211_IFTYPE_P2P_CLIENT) | \
+	 BIT(NL80211_IFTYPE_P2P_GO) | \
+	 BIT(NL80211_IFTYPE_ADHOC) | \
+	 BIT(NL80211_IFTYPE_MESH_POINT))
+
 static int mac80211_hwsim_new_radio(struct genl_info *info,
 				    struct hwsim_new_radio_params *param)
 {
@@ -2641,6 +2624,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 	const struct ieee80211_ops *ops = &mac80211_hwsim_ops;
 	struct net *net;
 	int idx;
+	int n_limits = 0;
 
 	if (WARN_ON(param->channels > 1 && !param->use_chanctx))
 		return -EINVAL;
@@ -2716,43 +2700,60 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 	if (info)
 		data->portid = info->snd_portid;
 
+	/* setup interface limits, only on interface types we support */
+	if (param->iftypes & BIT(NL80211_IFTYPE_ADHOC)) {
+		data->if_limits[n_limits].max = 1;
+		data->if_limits[n_limits].types = BIT(NL80211_IFTYPE_ADHOC);
+		n_limits++;
+	}
+
+	if (param->iftypes & HWSIM_DEFAULT_IF_LIMIT) {
+		data->if_limits[n_limits].max = 2048;
+		/*
+		 * For this case, we may only support a subset of
+		 * HWSIM_DEFAULT_IF_LIMIT, therefore we only want to add the
+		 * bits that both param->iftype & HWSIM_DEFAULT_IF_LIMIT have.
+		 */
+		data->if_limits[n_limits].types =
+					HWSIM_DEFAULT_IF_LIMIT & param->iftypes;
+		n_limits++;
+	}
+
+	if (param->iftypes & BIT(NL80211_IFTYPE_P2P_DEVICE)) {
+		data->if_limits[n_limits].max = 1;
+		data->if_limits[n_limits].types =
+						BIT(NL80211_IFTYPE_P2P_DEVICE);
+		n_limits++;
+	}
+
 	if (data->use_chanctx) {
 		hw->wiphy->max_scan_ssids = 255;
 		hw->wiphy->max_scan_ie_len = IEEE80211_MAX_DATA_LEN;
 		hw->wiphy->max_remain_on_channel_duration = 1000;
-		hw->wiphy->iface_combinations = &data->if_combination;
-		if (param->p2p_device)
-			data->if_combination = hwsim_if_comb_p2p_dev[0];
-		else
-			data->if_combination = hwsim_if_comb[0];
-		hw->wiphy->n_iface_combinations = 1;
-		/* For channels > 1 DFS is not allowed */
 		data->if_combination.radar_detect_widths = 0;
 		data->if_combination.num_different_channels = data->channels;
-	} else if (param->p2p_device) {
-		hw->wiphy->iface_combinations = hwsim_if_comb_p2p_dev;
-		hw->wiphy->n_iface_combinations =
-			ARRAY_SIZE(hwsim_if_comb_p2p_dev);
-	} else {
-		hw->wiphy->iface_combinations = hwsim_if_comb;
-		hw->wiphy->n_iface_combinations = ARRAY_SIZE(hwsim_if_comb);
 	}
 
+	data->if_combination.n_limits = n_limits;
+	data->if_combination.max_interfaces = 2048;
+	data->if_combination.num_different_channels = 1;
+	data->if_combination.radar_detect_widths =
+					BIT(NL80211_CHAN_WIDTH_20_NOHT) |
+					BIT(NL80211_CHAN_WIDTH_20) |
+					BIT(NL80211_CHAN_WIDTH_40) |
+					BIT(NL80211_CHAN_WIDTH_80) |
+					BIT(NL80211_CHAN_WIDTH_160);
+	data->if_combination.limits = data->if_limits;
+
+	hw->wiphy->iface_combinations = &data->if_combination;
+	hw->wiphy->n_iface_combinations = 1;
+
 	INIT_DELAYED_WORK(&data->roc_start, hw_roc_start);
 	INIT_DELAYED_WORK(&data->roc_done, hw_roc_done);
 	INIT_DELAYED_WORK(&data->hw_scan, hw_scan_work);
 
 	hw->queues = 5;
 	hw->offchannel_tx_hw_queue = 4;
-	hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) |
-				     BIT(NL80211_IFTYPE_AP) |
-				     BIT(NL80211_IFTYPE_P2P_CLIENT) |
-				     BIT(NL80211_IFTYPE_P2P_GO) |
-				     BIT(NL80211_IFTYPE_ADHOC) |
-				     BIT(NL80211_IFTYPE_MESH_POINT);
-
-	if (param->p2p_device)
-		hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_P2P_DEVICE);
 
 	ieee80211_hw_set(hw, SUPPORT_FAST_XMIT);
 	ieee80211_hw_set(hw, CHANCTX_STA_CSA);
@@ -2778,6 +2779,8 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 			       NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR;
 	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 
+	hw->wiphy->interface_modes = param->iftypes;
+
 	/* ask mac80211 to reserve space for magic */
 	hw->vif_data_size = sizeof(struct hwsim_vif_priv);
 	hw->sta_data_size = sizeof(struct hwsim_sta_priv);
@@ -3350,10 +3353,30 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 			return -EINVAL;
 		}
 
-
 		param.perm_addr = nla_data(info->attrs[HWSIM_ATTR_PERM_ADDR]);
 	}
 
+	if (info->attrs[HWSIM_ATTR_IFTYPE_SUPPORT]) {
+		param.iftypes =
+			nla_get_u32(info->attrs[HWSIM_ATTR_IFTYPE_SUPPORT]);
+
+		if (param.iftypes & ~HWSIM_IFTYPE_SUPPORT_MASK) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    info->attrs[HWSIM_ATTR_IFTYPE_SUPPORT],
+					    "cannot support more iftypes than kernel");
+			return -EINVAL;
+		}
+	} else {
+		param.iftypes = HWSIM_IFTYPE_SUPPORT_MASK;
+	}
+
+	/* ensure both flag and iftype support is honored */
+	if (param.p2p_device ||
+	    param.iftypes & BIT(NL80211_IFTYPE_P2P_DEVICE)) {
+		param.iftypes |= BIT(NL80211_IFTYPE_P2P_DEVICE);
+		param.p2p_device = true;
+	}
+
 	if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
 		hwname = kasprintf(GFP_KERNEL, "%.*s",
 				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
diff --git a/drivers/net/wireless/mac80211_hwsim.h b/drivers/net/wireless/mac80211_hwsim.h
index 0fe3199f8c72..3f6b670116d0 100644
--- a/drivers/net/wireless/mac80211_hwsim.h
+++ b/drivers/net/wireless/mac80211_hwsim.h
@@ -132,6 +132,7 @@ enum {
  * @HWSIM_ATTR_TX_INFO_FLAGS: additional flags for corresponding
  *	rates of %HWSIM_ATTR_TX_INFO
  * @HWSIM_ATTR_PERM_ADDR: permanent mac address of new radio
+ * @HWSIM_ATTR_IFTYPE_SUPPORT: u32 attribute of supported interface types bits
  * @__HWSIM_ATTR_MAX: enum limit
  */
 
@@ -160,6 +161,7 @@ enum {
 	HWSIM_ATTR_PAD,
 	HWSIM_ATTR_TX_INFO_FLAGS,
 	HWSIM_ATTR_PERM_ADDR,
+	HWSIM_ATTR_IFTYPE_SUPPORT,
 	__HWSIM_ATTR_MAX,
 };
 #define HWSIM_ATTR_MAX (__HWSIM_ATTR_MAX - 1)
-- 
cgit v1.2.3


From c0a0189d827de189b15d07d0d9776b3965d59d8c Mon Sep 17 00:00:00 2001
From: James Prestwood <james.prestwood@linux.intel.com>
Date: Wed, 17 Oct 2018 14:16:24 -0700
Subject: mac80211_hwsim: allow configurable cipher types

The mac80211_hwsim driver does not specify supported cipher types, which
in turn enables all ciphers to be supported in software. (see
net/mac80211/main.c:ieee80211_init_cipher_suites). Allowing ciphers
to be configurable is valuable for simulating older drivers that may
not support all ciphers.

This patch adds a new attribute:

 - HWSIM_ATTR_CIPHER_SUPPORT
	A u32 array/list of supported cipher types

This only allows enabling/disabling cipher types listed in the (new)
"hwsim_ciphers" array in mac80211_hwsim.c. Any unknown cipher type
will result in -EINVAL.

Signed-off-by: James Prestwood <james.prestwood@linux.intel.com>
[fix some indentation, change to hwsim_known_ciphers(),
 add error messages, validate length better]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c | 79 +++++++++++++++++++++++++++++++++++
 drivers/net/wireless/mac80211_hwsim.h |  2 +
 2 files changed, 81 insertions(+)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 2fbea02e289a..4033a800b209 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -374,6 +374,20 @@ static const struct ieee80211_rate hwsim_rates[] = {
 	{ .bitrate = 540 }
 };
 
+static const u32 hwsim_ciphers[] = {
+	WLAN_CIPHER_SUITE_WEP40,
+	WLAN_CIPHER_SUITE_WEP104,
+	WLAN_CIPHER_SUITE_TKIP,
+	WLAN_CIPHER_SUITE_CCMP,
+	WLAN_CIPHER_SUITE_CCMP_256,
+	WLAN_CIPHER_SUITE_GCMP,
+	WLAN_CIPHER_SUITE_GCMP_256,
+	WLAN_CIPHER_SUITE_AES_CMAC,
+	WLAN_CIPHER_SUITE_BIP_CMAC_256,
+	WLAN_CIPHER_SUITE_BIP_GMAC_128,
+	WLAN_CIPHER_SUITE_BIP_GMAC_256,
+};
+
 #define OUI_QCA 0x001374
 #define QCA_NL80211_SUBCMD_TEST 1
 enum qca_nl80211_vendor_subcmds {
@@ -476,6 +490,8 @@ struct mac80211_hwsim_data {
 	struct ieee80211_iface_limit if_limits[3];
 	int n_if_limits;
 
+	u32 ciphers[ARRAY_SIZE(hwsim_ciphers)];
+
 	struct mac_address addresses[2];
 	int channels, idx;
 	bool use_chanctx;
@@ -603,6 +619,7 @@ static const struct nla_policy hwsim_genl_policy[HWSIM_ATTR_MAX + 1] = {
 	[HWSIM_ATTR_FREQ] = { .type = NLA_U32 },
 	[HWSIM_ATTR_PERM_ADDR] = { .type = NLA_UNSPEC, .len = ETH_ALEN },
 	[HWSIM_ATTR_IFTYPE_SUPPORT] = { .type = NLA_U32 },
+	[HWSIM_ATTR_CIPHER_SUPPORT] = { .type = NLA_BINARY },
 };
 
 static void mac80211_hwsim_tx_frame(struct ieee80211_hw *hw,
@@ -2376,6 +2393,8 @@ struct hwsim_new_radio_params {
 	bool no_vif;
 	const u8 *perm_addr;
 	u32 iftypes;
+	u32 *ciphers;
+	u8 n_ciphers;
 };
 
 static void hwsim_mcast_config_msg(struct sk_buff *mcast_skb,
@@ -2748,6 +2767,13 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 	hw->wiphy->iface_combinations = &data->if_combination;
 	hw->wiphy->n_iface_combinations = 1;
 
+	if (param->ciphers) {
+		memcpy(data->ciphers, param->ciphers,
+		       param->n_ciphers * sizeof(u32));
+		hw->wiphy->cipher_suites = data->ciphers;
+		hw->wiphy->n_cipher_suites = param->n_ciphers;
+	}
+
 	INIT_DELAYED_WORK(&data->roc_start, hw_roc_start);
 	INIT_DELAYED_WORK(&data->roc_done, hw_roc_done);
 	INIT_DELAYED_WORK(&data->hw_scan, hw_scan_work);
@@ -3296,6 +3322,29 @@ static int hwsim_register_received_nl(struct sk_buff *skb_2,
 	return 0;
 }
 
+/* ensures ciphers only include ciphers listed in 'hwsim_ciphers' array */
+static bool hwsim_known_ciphers(const u32 *ciphers, int n_ciphers)
+{
+	int i;
+
+	for (i = 0; i < n_ciphers; i++) {
+		int j;
+		int found = 0;
+
+		for (j = 0; j < ARRAY_SIZE(hwsim_ciphers); j++) {
+			if (ciphers[i] == hwsim_ciphers[j]) {
+				found = 1;
+				break;
+			}
+		}
+
+		if (!found)
+			return false;
+	}
+
+	return true;
+}
+
 static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 {
 	struct hwsim_new_radio_params param = { 0 };
@@ -3377,6 +3426,36 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 		param.p2p_device = true;
 	}
 
+	if (info->attrs[HWSIM_ATTR_CIPHER_SUPPORT]) {
+		u32 len = nla_len(info->attrs[HWSIM_ATTR_CIPHER_SUPPORT]);
+
+		param.ciphers =
+			nla_data(info->attrs[HWSIM_ATTR_CIPHER_SUPPORT]);
+
+		if (len % sizeof(u32)) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    info->attrs[HWSIM_ATTR_CIPHER_SUPPORT],
+					    "bad cipher list length");
+			return -EINVAL;
+		}
+
+		param.n_ciphers = len / sizeof(u32);
+
+		if (param.n_ciphers > ARRAY_SIZE(hwsim_ciphers)) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    info->attrs[HWSIM_ATTR_CIPHER_SUPPORT],
+					    "too many ciphers specified");
+			return -EINVAL;
+		}
+
+		if (!hwsim_known_ciphers(param.ciphers, param.n_ciphers)) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    info->attrs[HWSIM_ATTR_CIPHER_SUPPORT],
+					    "unsupported ciphers specified");
+			return -EINVAL;
+		}
+	}
+
 	if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
 		hwname = kasprintf(GFP_KERNEL, "%.*s",
 				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
diff --git a/drivers/net/wireless/mac80211_hwsim.h b/drivers/net/wireless/mac80211_hwsim.h
index 3f6b670116d0..a1ef8457fad4 100644
--- a/drivers/net/wireless/mac80211_hwsim.h
+++ b/drivers/net/wireless/mac80211_hwsim.h
@@ -133,6 +133,7 @@ enum {
  *	rates of %HWSIM_ATTR_TX_INFO
  * @HWSIM_ATTR_PERM_ADDR: permanent mac address of new radio
  * @HWSIM_ATTR_IFTYPE_SUPPORT: u32 attribute of supported interface types bits
+ * @HWSIM_ATTR_CIPHER_SUPPORT: u32 array of supported cipher types
  * @__HWSIM_ATTR_MAX: enum limit
  */
 
@@ -162,6 +163,7 @@ enum {
 	HWSIM_ATTR_TX_INFO_FLAGS,
 	HWSIM_ATTR_PERM_ADDR,
 	HWSIM_ATTR_IFTYPE_SUPPORT,
+	HWSIM_ATTR_CIPHER_SUPPORT,
 	__HWSIM_ATTR_MAX,
 };
 #define HWSIM_ATTR_MAX (__HWSIM_ATTR_MAX - 1)
-- 
cgit v1.2.3


From e9da68ddea6030b214dfe420564d48bb579f58fc Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 18 Oct 2018 10:35:47 +0200
Subject: mac80211: allow hardware scan to fall back to software

In some cases, like in the rsi driver hardware scan offload, there
may be scenarios in which hardware scan might not be available or
desirable.

Allow drivers to cope with this by letting them fall back to software
scan by returning the special value 1 from the hardware scan method.

Requested-by: Sushant Kumar Mishra <sushant2k1513@gmail.com>
Requested-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  5 +++++
 net/mac80211/scan.c    | 22 ++++++++++++++++++----
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index e3d57e7a55cc..9386cf9fe714 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3239,6 +3239,11 @@ enum ieee80211_reconfig_type {
  *	When the scan finishes, ieee80211_scan_completed() must be called;
  *	note that it also must be called when the scan cannot finish due to
  *	any error unless this callback returned a negative error code.
+ *	This callback is also allowed to return the special return value 1,
+ *	this indicates that hardware scan isn't desirable right now and a
+ *	software scan should be done instead. A driver wishing to use this
+ *	capability must ensure its (hardware) scan capabilities aren't
+ *	advertised as more capable than mac80211's software scan is.
  *	The callback can sleep.
  *
  * @cancel_hw_scan: Ask the low-level tp cancel the active hw scan.
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 5d2a11777718..95413413f98c 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -356,7 +356,7 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local)
 static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
-	bool hw_scan = local->ops->hw_scan;
+	bool hw_scan = test_bit(SCAN_HW_SCANNING, &local->scanning);
 	bool was_scanning = local->scanning;
 	struct cfg80211_scan_request *scan_req;
 	struct ieee80211_sub_if_data *scan_sdata;
@@ -606,6 +606,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 				  struct cfg80211_scan_request *req)
 {
 	struct ieee80211_local *local = sdata->local;
+	bool hw_scan = local->ops->hw_scan;
 	int rc;
 
 	lockdep_assert_held(&local->mtx);
@@ -620,7 +621,8 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 		return 0;
 	}
 
-	if (local->ops->hw_scan) {
+ again:
+	if (hw_scan) {
 		u8 *ies;
 
 		local->hw_scan_ies_bufsize = local->scan_ies_len + req->ie_len;
@@ -679,7 +681,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 	else
 		memcpy(local->scan_addr, sdata->vif.addr, ETH_ALEN);
 
-	if (local->ops->hw_scan) {
+	if (hw_scan) {
 		__set_bit(SCAN_HW_SCANNING, &local->scanning);
 	} else if ((req->n_channels == 1) &&
 		   (req->channels[0] == local->_oper_chandef.chan)) {
@@ -722,7 +724,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 
 	ieee80211_recalc_idle(local);
 
-	if (local->ops->hw_scan) {
+	if (hw_scan) {
 		WARN_ON(!ieee80211_prep_hw_scan(local));
 		rc = drv_hw_scan(local, sdata, local->hw_scan_req);
 	} else {
@@ -740,6 +742,18 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 		RCU_INIT_POINTER(local->scan_sdata, NULL);
 	}
 
+	if (hw_scan && rc == 1) {
+		/*
+		 * we can't fall back to software for P2P-GO
+		 * as it must update NoA etc.
+		 */
+		if (ieee80211_vif_type_p2p(&sdata->vif) ==
+				NL80211_IFTYPE_P2P_GO)
+			return -EOPNOTSUPP;
+		hw_scan = false;
+		goto again;
+	}
+
 	return rc;
 }
 
-- 
cgit v1.2.3


From 4a6ecd35f95b0e29b3470ca16772a1cc89607c97 Mon Sep 17 00:00:00 2001
From: Bob Copeland <me@bobcopeland.com>
Date: Thu, 25 Oct 2018 15:48:52 -0400
Subject: mac80211: mesh: advertise gates in mesh formation

The Connected to Mesh Gate subfield (802.11-2016 9.4.2.98.7) in the Mesh
Formation Info field is currently unset.  This field may be useful in
determining which MBSSes to join or which mesh STAs to peer with.

If this mesh STA is a gate, by having turned on mesh gate announcements,
or if we have a path to one (e.g. by having received RANNs) then set this
bit to 1.

Signed-off-by: Bob Copeland <bobcopeland@fb.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mesh.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 8bad414c52ad..19205c821dee 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -254,6 +254,8 @@ int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
 	u8 *pos, neighbors;
 	u8 meshconf_len = sizeof(struct ieee80211_meshconf_ie);
+	bool is_connected_to_gate = ifmsh->num_gates > 0 ||
+		ifmsh->mshcfg.dot11MeshGateAnnouncementProtocol;
 
 	if (skb_tailroom(skb) < 2 + meshconf_len)
 		return -ENOMEM;
@@ -278,7 +280,7 @@ int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata,
 	/* Mesh Formation Info - number of neighbors */
 	neighbors = atomic_read(&ifmsh->estab_plinks);
 	neighbors = min_t(int, neighbors, IEEE80211_MAX_MESH_PEERINGS);
-	*pos++ = neighbors << 1;
+	*pos++ = (neighbors << 1) | is_connected_to_gate;
 	/* Mesh capability */
 	*pos = 0x00;
 	*pos |= ifmsh->mshcfg.dot11MeshForwarding ?
-- 
cgit v1.2.3


From dbdaee7aa6e61f56aac61b71a7807e76f92cc895 Mon Sep 17 00:00:00 2001
From: Bob Copeland <me@bobcopeland.com>
Date: Thu, 25 Oct 2018 15:48:53 -0400
Subject: {nl,mac}80211: report gate connectivity in station info

Capture the current state of gate connectivity from the mesh
formation field in mesh config whenever we receive a beacon,
and report that via GET_STATION.  This allows applications
doing mesh peering in userspace to make peering decisions
based on peers' current upstream connectivity.

Signed-off-by: Bob Copeland <bobcopeland@fb.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h    | 2 ++
 include/net/cfg80211.h       | 3 +++
 include/uapi/linux/nl80211.h | 3 +++
 net/mac80211/mesh_plink.c    | 3 +++
 net/mac80211/sta_info.c      | 4 +++-
 net/mac80211/sta_info.h      | 2 ++
 net/wireless/nl80211.c       | 1 +
 7 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 0ef67f837ae1..407d6fd66fa9 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -812,6 +812,8 @@ enum mesh_config_capab_flags {
 	IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL	= 0x40,
 };
 
+#define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1
+
 /**
  * mesh channel switch parameters element's flag indicator
  *
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index c21c5c70a2fd..24d2db8e082d 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1296,6 +1296,7 @@ struct cfg80211_tid_stats {
  * @rx_beacon: number of beacons received from this peer
  * @rx_beacon_signal_avg: signal strength average (in dBm) for beacons received
  *	from this peer
+ * @connected_to_gate: true if mesh STA has a path to mesh gate
  * @rx_duration: aggregate PPDU duration(usecs) for all the frames from a peer
  * @pertid: per-TID statistics, see &struct cfg80211_tid_stats, using the last
  *	(IEEE80211_NUM_TIDS) index for MSDUs not encapsulated in QoS-MPDUs.
@@ -1350,6 +1351,8 @@ struct station_info {
 	u64 rx_beacon;
 	u64 rx_duration;
 	u8 rx_beacon_signal_avg;
+	u8 connected_to_gate;
+
 	struct cfg80211_tid_stats *pertid;
 	s8 ack_signal;
 	s8 avg_ack_signal;
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index e45b88925783..ff6005edf32f 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3116,6 +3116,8 @@ enum nl80211_sta_bss_param {
  *	with an FCS error (u32, from this station). This count may not include
  *	some packets with an FCS error due to TA corruption. Hence this counter
  *	might not be fully accurate.
+ * @NL80211_STA_INFO_CONNECTED_TO_GATE: set to true if STA has a path to a
+ *	mesh gate
  * @__NL80211_STA_INFO_AFTER_LAST: internal
  * @NL80211_STA_INFO_MAX: highest possible station info attribute
  */
@@ -3158,6 +3160,7 @@ enum nl80211_sta_info {
 	NL80211_STA_INFO_ACK_SIGNAL_AVG,
 	NL80211_STA_INFO_RX_MPDUS,
 	NL80211_STA_INFO_FCS_ERROR_COUNT,
+	NL80211_STA_INFO_CONNECTED_TO_GATE,
 
 	/* keep last */
 	__NL80211_STA_INFO_AFTER_LAST,
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 5b5b0f95ffd1..5f45a2b273df 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -590,6 +590,9 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata,
 	if (!sta)
 		goto out;
 
+	sta->mesh->connected_to_gate = elems->mesh_config->meshconf_form &
+		IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE;
+
 	if (mesh_peer_accepts_plinks(elems) &&
 	    sta->mesh->plink_state == NL80211_PLINK_LISTEN &&
 	    sdata->u.mesh.accepting_plinks &&
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 11b7ae691db0..c4a8f115ed33 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -2264,7 +2264,8 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 				 BIT_ULL(NL80211_STA_INFO_PLINK_STATE) |
 				 BIT_ULL(NL80211_STA_INFO_LOCAL_PM) |
 				 BIT_ULL(NL80211_STA_INFO_PEER_PM) |
-				 BIT_ULL(NL80211_STA_INFO_NONPEER_PM);
+				 BIT_ULL(NL80211_STA_INFO_NONPEER_PM) |
+				 BIT_ULL(NL80211_STA_INFO_CONNECTED_TO_GATE);
 
 		sinfo->llid = sta->mesh->llid;
 		sinfo->plid = sta->mesh->plid;
@@ -2276,6 +2277,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 		sinfo->local_pm = sta->mesh->local_pm;
 		sinfo->peer_pm = sta->mesh->peer_pm;
 		sinfo->nonpeer_pm = sta->mesh->nonpeer_pm;
+		sinfo->connected_to_gate = sta->mesh->connected_to_gate;
 #endif
 	}
 
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 9a04327d71d1..8eb29041be54 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -364,6 +364,7 @@ DECLARE_EWMA(mesh_fail_avg, 20, 8)
  * @nonpeer_pm: STA power save mode towards non-peer neighbors
  * @processed_beacon: set to true after peer rates and capabilities are
  *	processed
+ * @connected_to_gate: true if mesh STA has a path to a mesh gate
  * @fail_avg: moving percentage of failed MSDUs
  */
 struct mesh_sta {
@@ -381,6 +382,7 @@ struct mesh_sta {
 	u8 plink_retries;
 
 	bool processed_beacon;
+	bool connected_to_gate;
 
 	enum nl80211_plink_state plink_state;
 	u32 plink_timeout;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5e7178954d61..f231059242cc 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4883,6 +4883,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 	PUT_SINFO(LOCAL_PM, local_pm, u32);
 	PUT_SINFO(PEER_PM, peer_pm, u32);
 	PUT_SINFO(NONPEER_PM, nonpeer_pm, u32);
+	PUT_SINFO(CONNECTED_TO_GATE, connected_to_gate, u8);
 
 	if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_BSS_PARAM)) {
 		bss_param = nla_nest_start(msg, NL80211_STA_INFO_BSS_PARAM);
-- 
cgit v1.2.3


From 01d66fbd5b18ac9f01a6a2ae1278189d19208ad5 Mon Sep 17 00:00:00 2001
From: Bob Copeland <me@bobcopeland.com>
Date: Thu, 25 Oct 2018 17:36:34 -0400
Subject: {nl,mac}80211: add dot11MeshConnectedToMeshGate to meshconf

When userspace is controlling mesh routing, it may have better
knowledge about whether a mesh STA is connected to a mesh
gate than the kernel mpath table.  Add dot11MeshConnectedToMeshGate
to the mesh config so that such applications can explicitly
signal that a mesh STA is connected to a gate, which will then
be advertised in the beacon.

Signed-off-by: Bob Copeland <bobcopeland@fb.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h        | 5 +++++
 include/uapi/linux/nl80211.h  | 8 +++++++-
 net/mac80211/cfg.c            | 3 +++
 net/mac80211/debugfs_netdev.c | 3 +++
 net/mac80211/mesh.c           | 3 ++-
 net/wireless/nl80211.c        | 8 +++++++-
 6 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 24d2db8e082d..16d595b93ba3 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1562,6 +1562,10 @@ struct bss_parameters {
  * @plink_timeout: If no tx activity is seen from a STA we've established
  *	peering with for longer than this time (in seconds), then remove it
  *	from the STA's list of peers.  Default is 30 minutes.
+ * @dot11MeshConnectedToMeshGate: if set to true, advertise that this STA is
+ *      connected to a mesh gate in mesh formation info.  If false, the
+ *      value in mesh formation is determined by the presence of root paths
+ *      in the mesh path table
  */
 struct mesh_config {
 	u16 dot11MeshRetryTimeout;
@@ -1581,6 +1585,7 @@ struct mesh_config {
 	u16 dot11MeshHWMPperrMinInterval;
 	u16 dot11MeshHWMPnetDiameterTraversalTime;
 	u8 dot11MeshHWMPRootMode;
+	bool dot11MeshConnectedToMeshGate;
 	u16 dot11MeshHWMPRannInterval;
 	bool dot11MeshGateAnnouncementProtocol;
 	bool dot11MeshForwarding;
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index ff6005edf32f..51bd85b7d839 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3117,7 +3117,7 @@ enum nl80211_sta_bss_param {
  *	some packets with an FCS error due to TA corruption. Hence this counter
  *	might not be fully accurate.
  * @NL80211_STA_INFO_CONNECTED_TO_GATE: set to true if STA has a path to a
- *	mesh gate
+ *	mesh gate (u8, 0 or 1)
  * @__NL80211_STA_INFO_AFTER_LAST: internal
  * @NL80211_STA_INFO_MAX: highest possible station info attribute
  */
@@ -3940,6 +3940,11 @@ enum nl80211_mesh_power_mode {
  *	remove it from the STA's list of peers. You may set this to 0 to disable
  *	the removal of the STA. Default is 30 minutes.
  *
+ * @NL80211_MESHCONF_CONNECTED_TO_GATE: If set to true then this mesh STA
+ *	will advertise that it is connected to a gate in the mesh formation
+ *	field.  If left unset then the mesh formation field will only
+ *	advertise such if there is an active root mesh path.
+ *
  * @__NL80211_MESHCONF_ATTR_AFTER_LAST: internal use
  */
 enum nl80211_meshconf_params {
@@ -3972,6 +3977,7 @@ enum nl80211_meshconf_params {
 	NL80211_MESHCONF_POWER_MODE,
 	NL80211_MESHCONF_AWAKE_WINDOW,
 	NL80211_MESHCONF_PLINK_TIMEOUT,
+	NL80211_MESHCONF_CONNECTED_TO_GATE,
 
 	/* keep last */
 	__NL80211_MESHCONF_ATTR_AFTER_LAST,
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 2fccccfbbf4d..cf8f946ae724 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2028,6 +2028,9 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy,
 			nconf->dot11MeshAwakeWindowDuration;
 	if (_chg_mesh_attr(NL80211_MESHCONF_PLINK_TIMEOUT, mask))
 		conf->plink_timeout = nconf->plink_timeout;
+	if (_chg_mesh_attr(NL80211_MESHCONF_CONNECTED_TO_GATE, mask))
+		conf->dot11MeshConnectedToMeshGate =
+			nconf->dot11MeshConnectedToMeshGate;
 	ieee80211_mbss_info_change_notify(sdata, BSS_CHANGED_BEACON);
 	return 0;
 }
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index c813207bb123..cff0fb3578c9 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -641,6 +641,8 @@ IEEE80211_IF_FILE(dot11MeshHWMPconfirmationInterval,
 IEEE80211_IF_FILE(power_mode, u.mesh.mshcfg.power_mode, DEC);
 IEEE80211_IF_FILE(dot11MeshAwakeWindowDuration,
 		  u.mesh.mshcfg.dot11MeshAwakeWindowDuration, DEC);
+IEEE80211_IF_FILE(dot11MeshConnectedToMeshGate,
+		  u.mesh.mshcfg.dot11MeshConnectedToMeshGate, DEC);
 #endif
 
 #define DEBUGFS_ADD_MODE(name, mode) \
@@ -762,6 +764,7 @@ static void add_mesh_config(struct ieee80211_sub_if_data *sdata)
 	MESHPARAMS_ADD(dot11MeshHWMPconfirmationInterval);
 	MESHPARAMS_ADD(power_mode);
 	MESHPARAMS_ADD(dot11MeshAwakeWindowDuration);
+	MESHPARAMS_ADD(dot11MeshConnectedToMeshGate);
 #undef MESHPARAMS_ADD
 }
 #endif
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 19205c821dee..4869280a6413 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -255,7 +255,8 @@ int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata,
 	u8 *pos, neighbors;
 	u8 meshconf_len = sizeof(struct ieee80211_meshconf_ie);
 	bool is_connected_to_gate = ifmsh->num_gates > 0 ||
-		ifmsh->mshcfg.dot11MeshGateAnnouncementProtocol;
+		ifmsh->mshcfg.dot11MeshGateAnnouncementProtocol ||
+		ifmsh->mshcfg.dot11MeshConnectedToMeshGate;
 
 	if (skb_tailroom(skb) < 2 + meshconf_len)
 		return -ENOMEM;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index f231059242cc..d5f0ffd076b2 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6275,7 +6275,9 @@ static int nl80211_get_mesh_config(struct sk_buff *skb,
 	    nla_put_u16(msg, NL80211_MESHCONF_AWAKE_WINDOW,
 			cur_params.dot11MeshAwakeWindowDuration) ||
 	    nla_put_u32(msg, NL80211_MESHCONF_PLINK_TIMEOUT,
-			cur_params.plink_timeout))
+			cur_params.plink_timeout) ||
+	    nla_put_u8(msg, NL80211_MESHCONF_CONNECTED_TO_GATE,
+		       cur_params.dot11MeshConnectedToMeshGate))
 		goto nla_put_failure;
 	nla_nest_end(msg, pinfoattr);
 	genlmsg_end(msg, hdr);
@@ -6332,6 +6334,7 @@ nl80211_meshconf_params_policy[NL80211_MESHCONF_ATTR_MAX+1] = {
 				 NL80211_MESH_POWER_MAX),
 	[NL80211_MESHCONF_AWAKE_WINDOW] = { .type = NLA_U16 },
 	[NL80211_MESHCONF_PLINK_TIMEOUT] = { .type = NLA_U32 },
+	[NL80211_MESHCONF_CONNECTED_TO_GATE] = NLA_POLICY_RANGE(NLA_U8, 0, 1),
 };
 
 static const struct nla_policy
@@ -6443,6 +6446,9 @@ do {									\
 	FILL_IN_MESH_PARAM_IF_SET(tb, cfg, rssi_threshold, mask,
 				  NL80211_MESHCONF_RSSI_THRESHOLD,
 				  nla_get_s32);
+	FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshConnectedToMeshGate, mask,
+				  NL80211_MESHCONF_CONNECTED_TO_GATE,
+				  nla_get_u8);
 	/*
 	 * Check HT operation mode based on
 	 * IEEE 802.11-2016 9.4.2.57 HT Operation element.
-- 
cgit v1.2.3


From ecbc12ad6b682680ae26a429225d7c295f7f0e77 Mon Sep 17 00:00:00 2001
From: Bob Copeland <me@bobcopeland.com>
Date: Fri, 26 Oct 2018 10:03:50 -0400
Subject: {nl,mac}80211: add rssi to mesh candidates

When peering is in userspace, some implementations may want to control
which peers are accepted based on RSSI in addition to the information
elements being sent today.  Add signal level so that info is available
to clients.

Signed-off-by: Bob Copeland <bobcopeland@fb.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h    |  3 ++-
 net/mac80211/mesh.c       |  3 ++-
 net/mac80211/mesh.h       |  3 ++-
 net/mac80211/mesh_plink.c | 32 ++++++++++++++++++++++----------
 net/wireless/nl80211.c    |  7 +++++--
 5 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 16d595b93ba3..ede7fcd68348 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5574,7 +5574,8 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid,
  * cfg80211 then sends a notification to userspace.
  */
 void cfg80211_notify_new_peer_candidate(struct net_device *dev,
-		const u8 *macaddr, const u8 *ie, u8 ie_len, gfp_t gfp);
+		const u8 *macaddr, const u8 *ie, u8 ie_len,
+		int sig_dbm, gfp_t gfp);
 
 /**
  * DOC: RFkill integration
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 4869280a6413..c90452aa0c42 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -1194,7 +1194,8 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata,
 		if (!sdata->u.mesh.user_mpm ||
 		    sdata->u.mesh.mshcfg.rssi_threshold == 0 ||
 		    sdata->u.mesh.mshcfg.rssi_threshold < rx_status->signal)
-			mesh_neighbour_update(sdata, mgmt->sa, &elems);
+			mesh_neighbour_update(sdata, mgmt->sa, &elems,
+					      rx_status);
 	}
 
 	if (ifmsh->sync_ops)
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index 21526630bf65..cad6592c52a1 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -273,7 +273,8 @@ int mesh_gate_num(struct ieee80211_sub_if_data *sdata);
 
 /* Mesh plinks */
 void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata,
-			   u8 *hw_addr, struct ieee802_11_elems *ie);
+			   u8 *hw_addr, struct ieee802_11_elems *ie,
+			   struct ieee80211_rx_status *rx_status);
 bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie);
 u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata);
 void mesh_plink_timer(struct timer_list *t);
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 5f45a2b273df..33055c8ed37e 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -513,7 +513,8 @@ __mesh_sta_info_alloc(struct ieee80211_sub_if_data *sdata, u8 *hw_addr)
 
 static struct sta_info *
 mesh_sta_info_alloc(struct ieee80211_sub_if_data *sdata, u8 *addr,
-		    struct ieee802_11_elems *elems)
+		    struct ieee802_11_elems *elems,
+		    struct ieee80211_rx_status *rx_status)
 {
 	struct sta_info *sta = NULL;
 
@@ -521,11 +522,17 @@ mesh_sta_info_alloc(struct ieee80211_sub_if_data *sdata, u8 *addr,
 	if (sdata->u.mesh.user_mpm ||
 	    sdata->u.mesh.security & IEEE80211_MESH_SEC_AUTHED) {
 		if (mesh_peer_accepts_plinks(elems) &&
-		    mesh_plink_availables(sdata))
+		    mesh_plink_availables(sdata)) {
+			int sig = 0;
+
+			if (ieee80211_hw_check(&sdata->local->hw, SIGNAL_DBM))
+				sig = rx_status->signal;
+
 			cfg80211_notify_new_peer_candidate(sdata->dev, addr,
 							   elems->ie_start,
 							   elems->total_len,
-							   GFP_KERNEL);
+							   sig, GFP_KERNEL);
+		}
 	} else
 		sta = __mesh_sta_info_alloc(sdata, addr);
 
@@ -538,13 +545,15 @@ mesh_sta_info_alloc(struct ieee80211_sub_if_data *sdata, u8 *addr,
  * @sdata: local meshif
  * @addr: peer's address
  * @elems: IEs from beacon or mesh peering frame.
+ * @rx_status: rx status for the frame for signal reporting
  *
  * Return existing or newly allocated sta_info under RCU read lock.
  * (re)initialize with given IEs.
  */
 static struct sta_info *
 mesh_sta_info_get(struct ieee80211_sub_if_data *sdata,
-		  u8 *addr, struct ieee802_11_elems *elems) __acquires(RCU)
+		  u8 *addr, struct ieee802_11_elems *elems,
+		  struct ieee80211_rx_status *rx_status) __acquires(RCU)
 {
 	struct sta_info *sta = NULL;
 
@@ -555,7 +564,7 @@ mesh_sta_info_get(struct ieee80211_sub_if_data *sdata,
 	} else {
 		rcu_read_unlock();
 		/* can't run atomic */
-		sta = mesh_sta_info_alloc(sdata, addr, elems);
+		sta = mesh_sta_info_alloc(sdata, addr, elems, rx_status);
 		if (!sta) {
 			rcu_read_lock();
 			return NULL;
@@ -576,17 +585,19 @@ mesh_sta_info_get(struct ieee80211_sub_if_data *sdata,
  * @sdata: local meshif
  * @addr: peer's address
  * @elems: IEs from beacon or mesh peering frame
+ * @rx_status: rx status for the frame for signal reporting
  *
  * Initiates peering if appropriate.
  */
 void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata,
 			   u8 *hw_addr,
-			   struct ieee802_11_elems *elems)
+			   struct ieee802_11_elems *elems,
+			   struct ieee80211_rx_status *rx_status)
 {
 	struct sta_info *sta;
 	u32 changed = 0;
 
-	sta = mesh_sta_info_get(sdata, hw_addr, elems);
+	sta = mesh_sta_info_get(sdata, hw_addr, elems, rx_status);
 	if (!sta)
 		goto out;
 
@@ -1072,7 +1083,8 @@ out:
 static void
 mesh_process_plink_frame(struct ieee80211_sub_if_data *sdata,
 			 struct ieee80211_mgmt *mgmt,
-			 struct ieee802_11_elems *elems)
+			 struct ieee802_11_elems *elems,
+			 struct ieee80211_rx_status *rx_status)
 {
 
 	struct sta_info *sta;
@@ -1137,7 +1149,7 @@ mesh_process_plink_frame(struct ieee80211_sub_if_data *sdata,
 	if (event == OPN_ACPT) {
 		rcu_read_unlock();
 		/* allocate sta entry if necessary and update info */
-		sta = mesh_sta_info_get(sdata, mgmt->sa, elems);
+		sta = mesh_sta_info_get(sdata, mgmt->sa, elems, rx_status);
 		if (!sta) {
 			mpl_dbg(sdata, "Mesh plink: failed to init peer!\n");
 			goto unlock_rcu;
@@ -1203,5 +1215,5 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata,
 			return;
 	}
 	ieee802_11_parse_elems(baseaddr, len - baselen, true, &elems);
-	mesh_process_plink_frame(sdata, mgmt, &elems);
+	mesh_process_plink_frame(sdata, mgmt, &elems, rx_status);
 }
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d5f0ffd076b2..e20329b34840 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -14735,7 +14735,8 @@ void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev,
 }
 
 void cfg80211_notify_new_peer_candidate(struct net_device *dev, const u8 *addr,
-					const u8* ie, u8 ie_len, gfp_t gfp)
+					const u8 *ie, u8 ie_len,
+					int sig_dbm, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
@@ -14761,7 +14762,9 @@ void cfg80211_notify_new_peer_candidate(struct net_device *dev, const u8 *addr,
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
 	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) ||
 	    (ie_len && ie &&
-	     nla_put(msg, NL80211_ATTR_IE, ie_len , ie)))
+	     nla_put(msg, NL80211_ATTR_IE, ie_len, ie)) ||
+	    (sig_dbm &&
+	     nla_put_u32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm)))
 		goto nla_put_failure;
 
 	genlmsg_end(msg, hdr);
-- 
cgit v1.2.3


From b69d540da7db84e836cea77fbd56a518aafa1f2f Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Nov 2018 23:00:31 +0100
Subject: selftests: add xfrm policy test script

add a script that adds a ipsec tunnel between two network
namespaces plus following policies:

.0/24 -> ipsec tunnel
.240/28 -> bypass
.253/32 -> ipsec tunnel

Then check that .254 bypasses tunnel (match /28 exception),
and .2 (match /24) and .253 (match direct policy) pass through the
tunnel.

Abuses iptables to check if ping did resolve an ipsec policy or not.

Also adds a bunch of 'block' rules that are not supposed to match.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 tools/testing/selftests/net/Makefile       |   3 +-
 tools/testing/selftests/net/xfrm_policy.sh | 276 +++++++++++++++++++++++++++++
 2 files changed, 278 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/xfrm_policy.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index eec359895feb..2ab3e3437a92 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -4,7 +4,8 @@
 CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g
 CFLAGS += -I../../../../usr/include/
 
-TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
+TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \
+	      rtnetlink.sh xfrm_policy.sh
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
 TEST_PROGS += udpgro_bench.sh udpgro.sh
diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh
new file mode 100755
index 000000000000..6ca63a6e50e9
--- /dev/null
+++ b/tools/testing/selftests/net/xfrm_policy.sh
@@ -0,0 +1,276 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Check xfrm policy resolution.  Topology:
+#
+# 1.2   1.1   3.1  3.10    2.1   2.2
+# eth1  eth1 veth0 veth0 eth1   eth1
+# ns1 ---- ns3 ----- ns4 ---- ns2
+#
+# ns3 and ns4 are connected via ipsec tunnel.
+# pings from ns1 to ns2 (and vice versa) are supposed to work like this:
+# ns1: ping 10.0.2.2: passes via ipsec tunnel.
+# ns2: ping 10.0.1.2: passes via ipsec tunnel.
+
+# ns1: ping 10.0.1.253: passes via ipsec tunnel (direct policy)
+# ns2: ping 10.0.2.253: passes via ipsec tunnel (direct policy)
+#
+# ns1: ping 10.0.2.254: does NOT pass via ipsec tunnel (exception)
+# ns2: ping 10.0.1.254: does NOT pass via ipsec tunnel (exception)
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+KEY_SHA=0xdeadbeef1234567890abcdefabcdefabcdefabcd
+KEY_AES=0x0123456789abcdef0123456789012345
+SPI1=0x1
+SPI2=0x2
+
+do_esp() {
+    local ns=$1
+    local me=$2
+    local remote=$3
+    local lnet=$4
+    local rnet=$5
+    local spi_out=$6
+    local spi_in=$7
+
+    ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in  enc aes $KEY_AES  auth sha1 $KEY_SHA  mode tunnel sel src $rnet dst $lnet
+    ip -net $ns xfrm state add src $me  dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet
+
+    # to encrypt packets as they go out (includes forwarded packets that need encapsulation)
+    ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow
+    # to fwd decrypted packets after esp processing:
+    ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow
+}
+
+do_exception() {
+    local ns=$1
+    local me=$2
+    local remote=$3
+    local encryptip=$4
+    local plain=$5
+
+    # network $plain passes without tunnel
+    ip -net $ns xfrm policy add dst $plain dir out priority 10 action allow
+
+    # direct policy for $encryptip, use tunnel, higher prio takes precedence
+    ip -net $ns xfrm policy add dst $encryptip dir out tmpl src $me dst $remote proto esp mode tunnel priority 1 action allow
+}
+
+# policies that are not supposed to match any packets generated in this test.
+do_dummies4() {
+    local ns=$1
+
+    for i in $(seq 10 16);do
+      # dummy policy with wildcard src/dst.
+      echo netns exec $ns ip xfrm policy add src 0.0.0.0/0 dst 10.$i.99.0/30 dir out action block
+      echo netns exec $ns ip xfrm policy add src 10.$i.99.0/30 dst 0.0.0.0/0 dir out action block
+      for j in $(seq 32 64);do
+        echo netns exec $ns ip xfrm policy add src 10.$i.1.0/30 dst 10.$i.$j.0/30 dir out action block
+        # silly, as it encompasses the one above too, but its allowed:
+        echo netns exec $ns ip xfrm policy add src 10.$i.1.0/29 dst 10.$i.$j.0/29 dir out action block
+        # and yet again, even more broad one.
+        echo netns exec $ns ip xfrm policy add src 10.$i.1.0/24 dst 10.$i.$j.0/24 dir out action block
+        echo netns exec $ns ip xfrm policy add src 10.$i.$j.0/24 dst 10.$i.1.0/24 dir fwd action block
+      done
+    done | ip -batch /dev/stdin
+}
+
+do_dummies6() {
+    local ns=$1
+
+    for i in $(seq 10 16);do
+      for j in $(seq 32 64);do
+       echo netns exec $ns ip xfrm policy add src dead:$i::/64 dst dead:$i:$j::/64 dir out action block
+       echo netns exec $ns ip xfrm policy add src dead:$i:$j::/64 dst dead:$i::/24 dir fwd action block
+      done
+    done | ip -batch /dev/stdin
+}
+
+check_ipt_policy_count()
+{
+	ns=$1
+
+	ip netns exec $ns iptables-save -c |grep policy | ( read c rest
+		ip netns exec $ns iptables -Z
+		if [ x"$c" = x'[0:0]' ]; then
+			exit 0
+		elif [ x"$c" = x ]; then
+			echo "ERROR: No counters"
+			ret=1
+			exit 111
+		else
+			exit 1
+		fi
+	)
+}
+
+check_xfrm() {
+	# 0: iptables -m policy rule count == 0
+	# 1: iptables -m policy rule count != 0
+	rval=$1
+	ip=$2
+	ret=0
+
+	ip netns exec ns1 ping -q -c 1 10.0.2.$ip > /dev/null
+
+	check_ipt_policy_count ns3
+	if [ $? -ne $rval ] ; then
+		ret=1
+	fi
+	check_ipt_policy_count ns4
+	if [ $? -ne $rval ] ; then
+		ret=1
+	fi
+
+	ip netns exec ns2 ping -q -c 1 10.0.1.$ip > /dev/null
+
+	check_ipt_policy_count ns3
+	if [ $? -ne $rval ] ; then
+		ret=1
+	fi
+	check_ipt_policy_count ns4
+	if [ $? -ne $rval ] ; then
+		ret=1
+	fi
+
+	return $ret
+}
+
+#check for needed privileges
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit $ksft_skip
+fi
+
+ip -Version 2>/dev/null >/dev/null
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without the ip tool"
+	exit $ksft_skip
+fi
+
+# needed to check if policy lookup got valid ipsec result
+iptables --version 2>/dev/null >/dev/null
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without iptables tool"
+	exit $ksft_skip
+fi
+
+for i in 1 2 3 4; do
+    ip netns add ns$i
+    ip -net ns$i link set lo up
+done
+
+DEV=veth0
+ip link add $DEV netns ns1 type veth peer name eth1 netns ns3
+ip link add $DEV netns ns2 type veth peer name eth1 netns ns4
+
+ip link add $DEV netns ns3 type veth peer name veth0 netns ns4
+
+DEV=veth0
+for i in 1 2; do
+    ip -net ns$i link set $DEV up
+    ip -net ns$i addr add 10.0.$i.2/24 dev $DEV
+    ip -net ns$i addr add dead:$i::2/64 dev $DEV
+
+    ip -net ns$i addr add 10.0.$i.253 dev $DEV
+    ip -net ns$i addr add 10.0.$i.254 dev $DEV
+    ip -net ns$i addr add dead:$i::fd dev $DEV
+    ip -net ns$i addr add dead:$i::fe dev $DEV
+done
+
+for i in 3 4; do
+ip -net ns$i link set eth1 up
+ip -net ns$i link set veth0 up
+done
+
+ip -net ns1 route add default via 10.0.1.1
+ip -net ns2 route add default via 10.0.2.1
+
+ip -net ns3 addr add 10.0.1.1/24 dev eth1
+ip -net ns3 addr add 10.0.3.1/24 dev veth0
+ip -net ns3 addr add 2001:1::1/64 dev eth1
+ip -net ns3 addr add 2001:3::1/64 dev veth0
+
+ip -net ns3 route add default via 10.0.3.10
+
+ip -net ns4 addr add 10.0.2.1/24 dev eth1
+ip -net ns4 addr add 10.0.3.10/24 dev veth0
+ip -net ns4 addr add 2001:2::1/64 dev eth1
+ip -net ns4 addr add 2001:3::10/64 dev veth0
+ip -net ns4 route add default via 10.0.3.1
+
+for j in 4 6; do
+	for i in 3 4;do
+		ip netns exec ns$i sysctl net.ipv$j.conf.eth1.forwarding=1 > /dev/null
+		ip netns exec ns$i sysctl net.ipv$j.conf.veth0.forwarding=1 > /dev/null
+	done
+done
+
+# abuse iptables rule counter to check if ping matches a policy
+ip netns exec ns3 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec
+ip netns exec ns4 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not insert iptables rule"
+	for i in 1 2 3 4;do ip netns del ns$i;done
+	exit $ksft_skip
+fi
+
+#          localip  remoteip  localnet    remotenet
+do_esp ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
+do_esp ns3 dead:3::1 dead:3::10 dead:1::/64 dead:2::/64 $SPI1 $SPI2
+do_esp ns4 10.0.3.10 10.0.3.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
+do_esp ns4 dead:3::10 dead:3::1 dead:2::/64 dead:1::/64 $SPI2 $SPI1
+
+do_dummies4 ns3
+do_dummies6 ns4
+
+# ping to .254 should use ipsec, exception is not installed.
+check_xfrm 1 254
+if [ $? -ne 0 ]; then
+	echo "FAIL: expected ping to .254 to use ipsec tunnel"
+	ret=1
+else
+	echo "PASS: policy before exception matches"
+fi
+
+# installs exceptions
+#                localip  remoteip   encryptdst  plaindst
+do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28
+do_exception ns4 10.0.3.10 10.0.3.1 10.0.1.253 10.0.1.240/28
+
+do_exception ns3 dead:3::1 dead:3::10 dead:2::fd  dead:2:f0::/96
+do_exception ns4 dead:3::10 dead:3::1 dead:1::fd  dead:1:f0::/96
+
+# ping to .254 should now be excluded from the tunnel
+check_xfrm 0 254
+if [ $? -ne 0 ]; then
+	echo "FAIL: expected ping to .254 to fail"
+	ret=1
+else
+	echo "PASS: ping to .254 bypassed ipsec tunnel"
+fi
+
+# ping to .253 should use use ipsec due to direct policy exception.
+check_xfrm 1 253
+if [ $? -ne 0 ]; then
+	echo "FAIL: expected ping to .253 to use ipsec tunnel"
+	ret=1
+else
+	echo "PASS: direct policy matches"
+fi
+
+# ping to .2 should use ipsec.
+check_xfrm 1 2
+if [ $? -ne 0 ]; then
+	echo "FAIL: expected ping to .2 to use ipsec tunnel"
+	ret=1
+else
+	echo "PASS: policy matches"
+fi
+
+for i in 1 2 3 4;do ip netns del ns$i;done
+
+exit $ret
-- 
cgit v1.2.3


From ceb159e30ad22efa0981d544e6166003515aa896 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Nov 2018 23:00:32 +0100
Subject: xfrm: security: iterate all, not inexact lists

currently all non-socket policies are either hashed in the dst table,
or placed on the 'inexact list'.  When flushing, we first walk the
table, then the (per-direction) inexact lists.

When we try and get rid of the inexact lists to having "n" inexact
lists (e.g. per-af inexact lists, or sorted into a tree), this walk
would become more complicated.

Simplify this: walk the 'all' list and skip socket policies during
traversal so we don't need to handle exact and inexact policies
separately anymore.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 93 ++++++++++++++------------------------------------
 1 file changed, 26 insertions(+), 67 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 119a427d9b2b..39d0db2a50d9 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -892,36 +892,19 @@ EXPORT_SYMBOL(xfrm_policy_byid);
 static inline int
 xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
 {
-	int dir, err = 0;
+	struct xfrm_policy *pol;
+	int err = 0;
 
-	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
-		struct xfrm_policy *pol;
-		int i;
+	list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+		if (pol->walk.dead ||
+		    xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX ||
+		    pol->type != type)
+			continue;
 
-		hlist_for_each_entry(pol,
-				     &net->xfrm.policy_inexact[dir], bydst) {
-			if (pol->type != type)
-				continue;
-			err = security_xfrm_policy_delete(pol->security);
-			if (err) {
-				xfrm_audit_policy_delete(pol, 0, task_valid);
-				return err;
-			}
-		}
-		for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) {
-			hlist_for_each_entry(pol,
-					     net->xfrm.policy_bydst[dir].table + i,
-					     bydst) {
-				if (pol->type != type)
-					continue;
-				err = security_xfrm_policy_delete(
-								pol->security);
-				if (err) {
-					xfrm_audit_policy_delete(pol, 0,
-								 task_valid);
-					return err;
-				}
-			}
+		err = security_xfrm_policy_delete(pol->security);
+		if (err) {
+			xfrm_audit_policy_delete(pol, 0, task_valid);
+			return err;
 		}
 	}
 	return err;
@@ -937,6 +920,7 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
 int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
 {
 	int dir, err = 0, cnt = 0;
+	struct xfrm_policy *pol;
 
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 
@@ -944,46 +928,21 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
 	if (err)
 		goto out;
 
-	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
-		struct xfrm_policy *pol;
-		int i;
-
-	again1:
-		hlist_for_each_entry(pol,
-				     &net->xfrm.policy_inexact[dir], bydst) {
-			if (pol->type != type)
-				continue;
-			__xfrm_policy_unlink(pol, dir);
-			spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-			cnt++;
-
-			xfrm_audit_policy_delete(pol, 1, task_valid);
-
-			xfrm_policy_kill(pol);
-
-			spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-			goto again1;
-		}
-
-		for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) {
-	again2:
-			hlist_for_each_entry(pol,
-					     net->xfrm.policy_bydst[dir].table + i,
-					     bydst) {
-				if (pol->type != type)
-					continue;
-				__xfrm_policy_unlink(pol, dir);
-				spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-				cnt++;
-
-				xfrm_audit_policy_delete(pol, 1, task_valid);
-				xfrm_policy_kill(pol);
-
-				spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-				goto again2;
-			}
-		}
+again:
+	list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+		dir = xfrm_policy_id2dir(pol->index);
+		if (pol->walk.dead ||
+		    dir >= XFRM_POLICY_MAX ||
+		    pol->type != type)
+			continue;
 
+		__xfrm_policy_unlink(pol, dir);
+		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		cnt++;
+		xfrm_audit_policy_delete(pol, 1, task_valid);
+		xfrm_policy_kill(pol);
+		spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+		goto again;
 	}
 	if (!cnt)
 		err = -ESRCH;
-- 
cgit v1.2.3


From a927d6af53eec08661628e3992d74736e848a743 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Nov 2018 23:00:33 +0100
Subject: xfrm: policy: split list insertion into a helper

... so we can reuse this later without code duplication when we add
policy to a second inexact list.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 43 +++++++++++++++++++++++++++----------------
 1 file changed, 27 insertions(+), 16 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 39d0db2a50d9..20d6815be0d7 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -740,18 +740,12 @@ static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
 	return false;
 }
 
-int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
+static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
+						   struct xfrm_policy *policy,
+						   bool excl)
 {
-	struct net *net = xp_net(policy);
-	struct xfrm_policy *pol;
-	struct xfrm_policy *delpol;
-	struct hlist_head *chain;
-	struct hlist_node *newpos;
+	struct xfrm_policy *pol, *newpos = NULL, *delpol = NULL;
 
-	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
-	delpol = NULL;
-	newpos = NULL;
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (pol->type == policy->type &&
 		    pol->if_id == policy->if_id &&
@@ -759,24 +753,41 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 		    xfrm_policy_mark_match(policy, pol) &&
 		    xfrm_sec_ctx_match(pol->security, policy->security) &&
 		    !WARN_ON(delpol)) {
-			if (excl) {
-				spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-				return -EEXIST;
-			}
+			if (excl)
+				return ERR_PTR(-EEXIST);
 			delpol = pol;
 			if (policy->priority > pol->priority)
 				continue;
 		} else if (policy->priority >= pol->priority) {
-			newpos = &pol->bydst;
+			newpos = pol;
 			continue;
 		}
 		if (delpol)
 			break;
 	}
 	if (newpos)
-		hlist_add_behind_rcu(&policy->bydst, newpos);
+		hlist_add_behind_rcu(&policy->bydst, &newpos->bydst);
 	else
 		hlist_add_head_rcu(&policy->bydst, chain);
+
+	return delpol;
+}
+
+int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
+{
+	struct net *net = xp_net(policy);
+	struct xfrm_policy *delpol;
+	struct hlist_head *chain;
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
+	delpol = xfrm_policy_insert_list(chain, policy, excl);
+
+	if (IS_ERR(delpol)) {
+		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		return PTR_ERR(delpol);
+	}
+
 	__xfrm_policy_link(policy, dir);
 
 	/* After previous checking, family can either be AF_INET or AF_INET6 */
-- 
cgit v1.2.3


From cc1bb845adc9b3a005cbb67fd18c69af1c3aec94 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Nov 2018 23:00:34 +0100
Subject: xfrm: policy: return NULL when inexact search needed

currently policy_hash_bysel() returns the hash bucket list
(for exact policies), or the inexact list (when policy uses a prefix).

Searching this inexact list is slow, so it might be better to pre-sort
inexact lists into a tree or another data structure for faster
searching.

However, due to 'any' policies, that need to be searched in any case,
doing so will require that 'inexact' policies need to be handled
specially to decide the best search strategy.  So change hash_bysel()
and return NULL if the policy can't be handled via the policy hash
table.

Right now, we simply use the inexact list when this happens, but
future patch can then implement a different strategy.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 20d6815be0d7..b00c265f6be3 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -365,7 +365,7 @@ static struct hlist_head *policy_hash_bysel(struct net *net,
 	hash = __sel_hash(sel, family, hmask, dbits, sbits);
 
 	if (hash == hmask + 1)
-		return &net->xfrm.policy_inexact[dir];
+		return NULL;
 
 	return rcu_dereference_check(net->xfrm.policy_bydst[dir].table,
 		     lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash;
@@ -625,6 +625,8 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 		chain = policy_hash_bysel(net, &policy->selector,
 					  policy->family,
 					  xfrm_policy_id2dir(policy->index));
+		if (!chain)
+			chain = &net->xfrm.policy_inexact[dir];
 		hlist_for_each_entry(pol, chain, bydst) {
 			if (policy->priority >= pol->priority)
 				newpos = &pol->bydst;
@@ -781,7 +783,12 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
-	delpol = xfrm_policy_insert_list(chain, policy, excl);
+	if (chain) {
+		delpol = xfrm_policy_insert_list(chain, policy, excl);
+	} else {
+		chain = &net->xfrm.policy_inexact[dir];
+		delpol = xfrm_policy_insert_list(chain, policy, excl);
+	}
 
 	if (IS_ERR(delpol)) {
 		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
@@ -829,6 +836,8 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 	*err = 0;
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, sel, sel->family, dir);
+	if (!chain)
+		chain = &net->xfrm.policy_inexact[dir];
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (pol->type == type &&
-- 
cgit v1.2.3


From 24969facd704a5f0dd8e08da86bf32a9ce972bee Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Nov 2018 23:00:35 +0100
Subject: xfrm: policy: store inexact policies in an rhashtable

Switch packet-path lookups for inexact policies to rhashtable.

In this initial version, we now no longer need to search policies with
non-matching address family and type.

Next patch will add the if_id as well so lookups from the xfrm interface
driver only need to search inexact policies for that device.

Future patches will augment the hlist in each rhash bucket with a tree
and pre-sort policies according to daddr/prefix.

A single rhashtable is used.  In order to avoid a full rhashtable walk on
netns exit, the bins get placed on a pernet list, i.e. we add almost no
cost for network namespaces that had no xfrm policies.

The inexact lists are kept in place, and policies are added to both the
per-rhash-inexact list and a pernet one.

The latter is needed for the control plane to handle migrate -- these
requests do not consider the if_id, so if we'd remove the inexact_list
now we would have to search all hash buckets and then figure
out which matching policy candidate is the most recent one -- this appears
a bit harder than just keeping the 'old' inexact list for this purpose.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/netns/xfrm.h |   2 +
 include/net/xfrm.h       |   1 +
 net/xfrm/xfrm_policy.c   | 350 ++++++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 335 insertions(+), 18 deletions(-)

diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 9991e5ef52cc..59f45b1e9dac 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -5,6 +5,7 @@
 #include <linux/list.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <linux/rhashtable-types.h>
 #include <linux/xfrm.h>
 #include <net/dst_ops.h>
 
@@ -53,6 +54,7 @@ struct netns_xfrm {
 	unsigned int		policy_count[XFRM_POLICY_MAX * 2];
 	struct work_struct	policy_hash_work;
 	struct xfrm_policy_hthresh policy_hthresh;
+	struct list_head	inexact_bins;
 
 
 	struct sock		*nlsk;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 0eb390c205af..870fa9b27f7e 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -596,6 +596,7 @@ struct xfrm_policy {
 	u16			family;
 	struct xfrm_sec_ctx	*security;
 	struct xfrm_tmpl       	xfrm_vec[XFRM_MAX_DEPTH];
+	struct hlist_node	bydst_inexact_list;
 	struct rcu_head		rcu;
 };
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index b00c265f6be3..5c7e7399323f 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -26,6 +26,7 @@
 #include <linux/cache.h>
 #include <linux/cpu.h>
 #include <linux/audit.h>
+#include <linux/rhashtable.h>
 #include <net/dst.h>
 #include <net/flow.h>
 #include <net/xfrm.h>
@@ -45,6 +46,22 @@ struct xfrm_flo {
 	u8 flags;
 };
 
+struct xfrm_pol_inexact_key {
+	possible_net_t net;
+	u16 family;
+	u8 dir, type;
+};
+
+struct xfrm_pol_inexact_bin {
+	struct xfrm_pol_inexact_key k;
+	struct rhash_head head;
+	struct hlist_head hhead;
+
+	/* slow path below */
+	struct list_head inexact_bins;
+	struct rcu_head rcu;
+};
+
 static DEFINE_SPINLOCK(xfrm_if_cb_lock);
 static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
 
@@ -55,6 +72,9 @@ static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1]
 static struct kmem_cache *xfrm_dst_cache __ro_after_init;
 static __read_mostly seqcount_t xfrm_policy_hash_generation;
 
+static struct rhashtable xfrm_policy_inexact_table;
+static const struct rhashtable_params xfrm_pol_inexact_params;
+
 static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr);
 static int stale_bundle(struct dst_entry *dst);
 static int xfrm_bundle_ok(struct xfrm_dst *xdst);
@@ -64,6 +84,18 @@ static void __xfrm_policy_link(struct xfrm_policy *pol, int dir);
 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 						int dir);
 
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir);
+
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup_rcu(struct net *net,
+			       u8 type, u16 family, u8 dir);
+static struct xfrm_policy *
+xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy,
+			bool excl);
+static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
+					    struct xfrm_policy *policy);
+
 static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy)
 {
 	return refcount_inc_not_zero(&policy->refcnt);
@@ -269,6 +301,7 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
 	if (policy) {
 		write_pnet(&policy->xp_net, net);
 		INIT_LIST_HEAD(&policy->walk.all);
+		INIT_HLIST_NODE(&policy->bydst_inexact_list);
 		INIT_HLIST_NODE(&policy->bydst);
 		INIT_HLIST_NODE(&policy->byidx);
 		rwlock_init(&policy->lock);
@@ -563,6 +596,107 @@ static void xfrm_hash_resize(struct work_struct *work)
 	mutex_unlock(&hash_resize_mutex);
 }
 
+static void xfrm_hash_reset_inexact_table(struct net *net)
+{
+	struct xfrm_pol_inexact_bin *b;
+
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	list_for_each_entry(b, &net->xfrm.inexact_bins, inexact_bins)
+		INIT_HLIST_HEAD(&b->hhead);
+}
+
+/* Make sure *pol can be inserted into fastbin.
+ * Useful to check that later insert requests will be sucessful
+ * (provided xfrm_policy_lock is held throughout).
+ */
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
+{
+	struct xfrm_pol_inexact_bin *bin, *prev;
+	struct xfrm_pol_inexact_key k = {
+		.family = pol->family,
+		.type = pol->type,
+		.dir = dir,
+	};
+	struct net *net = xp_net(pol);
+
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	write_pnet(&k.net, net);
+	bin = rhashtable_lookup_fast(&xfrm_policy_inexact_table, &k,
+				     xfrm_pol_inexact_params);
+	if (bin)
+		return bin;
+
+	bin = kzalloc(sizeof(*bin), GFP_ATOMIC);
+	if (!bin)
+		return NULL;
+
+	bin->k = k;
+	INIT_HLIST_HEAD(&bin->hhead);
+
+	prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
+						&bin->k, &bin->head,
+						xfrm_pol_inexact_params);
+	if (!prev) {
+		list_add(&bin->inexact_bins, &net->xfrm.inexact_bins);
+		return bin;
+	}
+
+	kfree(bin);
+
+	return IS_ERR(prev) ? NULL : prev;
+}
+
+static void xfrm_policy_inexact_delete_bin(struct net *net,
+					   struct xfrm_pol_inexact_bin *b)
+{
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	if (!hlist_empty(&b->hhead))
+		return;
+
+	if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head,
+				   xfrm_pol_inexact_params) == 0) {
+		list_del(&b->inexact_bins);
+		kfree_rcu(b, rcu);
+	}
+}
+
+static void __xfrm_policy_inexact_flush(struct net *net)
+{
+	struct xfrm_pol_inexact_bin *bin;
+
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	list_for_each_entry(bin, &net->xfrm.inexact_bins, inexact_bins)
+		xfrm_policy_inexact_delete_bin(net, bin);
+}
+
+static struct xfrm_policy *
+xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
+{
+	struct xfrm_pol_inexact_bin *bin;
+	struct xfrm_policy *delpol;
+	struct hlist_head *chain;
+	struct net *net;
+
+	bin = xfrm_policy_inexact_alloc_bin(policy, dir);
+	if (!bin)
+		return ERR_PTR(-ENOMEM);
+
+	delpol = xfrm_policy_insert_list(&bin->hhead, policy, excl);
+	if (delpol && excl)
+		return ERR_PTR(-EEXIST);
+
+	net = xp_net(policy);
+	chain = &net->xfrm.policy_inexact[dir];
+	xfrm_policy_insert_inexact_list(chain, policy);
+
+	return delpol;
+}
+
 static void xfrm_hash_rebuild(struct work_struct *work)
 {
 	struct net *net = container_of(work, struct net,
@@ -592,7 +726,45 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 
+	/* make sure that we can insert the indirect policies again before
+	 * we start with destructive action.
+	 */
+	list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) {
+		u8 dbits, sbits;
+
+		dir = xfrm_policy_id2dir(policy->index);
+		if (policy->walk.dead || dir >= XFRM_POLICY_MAX)
+			continue;
+
+		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
+			if (policy->family == AF_INET) {
+				dbits = rbits4;
+				sbits = lbits4;
+			} else {
+				dbits = rbits6;
+				sbits = lbits6;
+			}
+		} else {
+			if (policy->family == AF_INET) {
+				dbits = lbits4;
+				sbits = rbits4;
+			} else {
+				dbits = lbits6;
+				sbits = rbits6;
+			}
+		}
+
+		if (policy->selector.prefixlen_d < dbits ||
+		    policy->selector.prefixlen_s < sbits)
+			continue;
+
+		if (!xfrm_policy_inexact_alloc_bin(policy, dir))
+			goto out_unlock;
+	}
+
 	/* reset the bydst and inexact table in all directions */
+	xfrm_hash_reset_inexact_table(net);
+
 	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
 		hmask = net->xfrm.policy_bydst[dir].hmask;
@@ -625,8 +797,13 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 		chain = policy_hash_bysel(net, &policy->selector,
 					  policy->family,
 					  xfrm_policy_id2dir(policy->index));
-		if (!chain)
-			chain = &net->xfrm.policy_inexact[dir];
+		if (!chain) {
+			void *p = xfrm_policy_inexact_insert(policy, dir, 0);
+
+			WARN_ONCE(IS_ERR(p), "reinsert: %ld\n", PTR_ERR(p));
+			continue;
+		}
+
 		hlist_for_each_entry(pol, chain, bydst) {
 			if (policy->priority >= pol->priority)
 				newpos = &pol->bydst;
@@ -639,6 +816,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 			hlist_add_head_rcu(&policy->bydst, chain);
 	}
 
+out_unlock:
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	mutex_unlock(&hash_resize_mutex);
@@ -742,6 +920,84 @@ static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
 	return false;
 }
 
+static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed)
+{
+	const struct xfrm_pol_inexact_key *k = data;
+	u32 a = k->type << 24 | k->dir << 16 | k->family;
+
+	return jhash_2words(a, net_hash_mix(read_pnet(&k->net)), seed);
+}
+
+static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed)
+{
+	const struct xfrm_pol_inexact_bin *b = data;
+
+	return xfrm_pol_bin_key(&b->k, 0, seed);
+}
+
+static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg,
+			    const void *ptr)
+{
+	const struct xfrm_pol_inexact_key *key = arg->key;
+	const struct xfrm_pol_inexact_bin *b = ptr;
+	int ret;
+
+	if (!net_eq(read_pnet(&b->k.net), read_pnet(&key->net)))
+		return -1;
+
+	ret = b->k.dir ^ key->dir;
+	if (ret)
+		return ret;
+
+	ret = b->k.type ^ key->type;
+	if (ret)
+		return ret;
+
+	ret = b->k.family ^ key->family;
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct rhashtable_params xfrm_pol_inexact_params = {
+	.head_offset		= offsetof(struct xfrm_pol_inexact_bin, head),
+	.hashfn			= xfrm_pol_bin_key,
+	.obj_hashfn		= xfrm_pol_bin_obj,
+	.obj_cmpfn		= xfrm_pol_bin_cmp,
+	.automatic_shrinking	= true,
+};
+
+static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
+					    struct xfrm_policy *policy)
+{
+	struct xfrm_policy *pol, *delpol = NULL;
+	struct hlist_node *newpos = NULL;
+
+	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
+		if (pol->type == policy->type &&
+		    pol->if_id == policy->if_id &&
+		    !selector_cmp(&pol->selector, &policy->selector) &&
+		    xfrm_policy_mark_match(policy, pol) &&
+		    xfrm_sec_ctx_match(pol->security, policy->security) &&
+		    !WARN_ON(delpol)) {
+			delpol = pol;
+			if (policy->priority > pol->priority)
+				continue;
+		} else if (policy->priority >= pol->priority) {
+			newpos = &pol->bydst_inexact_list;
+			continue;
+		}
+		if (delpol)
+			break;
+	}
+
+	if (newpos)
+		hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos);
+	else
+		hlist_add_head_rcu(&policy->bydst_inexact_list, chain);
+}
+
 static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
 						   struct xfrm_policy *policy,
 						   bool excl)
@@ -767,6 +1023,7 @@ static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
 		if (delpol)
 			break;
 	}
+
 	if (newpos)
 		hlist_add_behind_rcu(&policy->bydst, &newpos->bydst);
 	else
@@ -783,12 +1040,10 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
-	if (chain) {
+	if (chain)
 		delpol = xfrm_policy_insert_list(chain, policy, excl);
-	} else {
-		chain = &net->xfrm.policy_inexact[dir];
-		delpol = xfrm_policy_insert_list(chain, policy, excl);
-	}
+	else
+		delpol = xfrm_policy_inexact_insert(policy, dir, excl);
 
 	if (IS_ERR(delpol)) {
 		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
@@ -830,14 +1085,24 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 					  struct xfrm_sec_ctx *ctx, int delete,
 					  int *err)
 {
-	struct xfrm_policy *pol, *ret;
+	struct xfrm_pol_inexact_bin *bin = NULL;
+	struct xfrm_policy *pol, *ret = NULL;
 	struct hlist_head *chain;
 
 	*err = 0;
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, sel, sel->family, dir);
-	if (!chain)
-		chain = &net->xfrm.policy_inexact[dir];
+	if (!chain) {
+		bin = xfrm_policy_inexact_lookup(net, type,
+						 sel->family, dir);
+		if (!bin) {
+			spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+			return NULL;
+		}
+
+		chain = &bin->hhead;
+	}
+
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (pol->type == type &&
@@ -854,6 +1119,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 					return pol;
 				}
 				__xfrm_policy_unlink(pol, dir);
+				xfrm_policy_inexact_delete_bin(net, bin);
 			}
 			ret = pol;
 			break;
@@ -964,7 +1230,9 @@ again:
 		spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 		goto again;
 	}
-	if (!cnt)
+	if (cnt)
+		__xfrm_policy_inexact_flush(net);
+	else
 		err = -ESRCH;
 out:
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
@@ -1063,21 +1331,50 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
 	if (match)
 		ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid,
 						  dir);
-
 	return ret;
 }
 
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir)
+{
+	struct xfrm_pol_inexact_key k = {
+		.family = family,
+		.type = type,
+		.dir = dir,
+	};
+
+	write_pnet(&k.net, net);
+
+	return rhashtable_lookup(&xfrm_policy_inexact_table, &k,
+				 xfrm_pol_inexact_params);
+}
+
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir)
+{
+	struct xfrm_pol_inexact_bin *bin;
+
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	rcu_read_lock();
+	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir);
+	rcu_read_unlock();
+
+	return bin;
+}
+
 static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 						     const struct flowi *fl,
 						     u16 family, u8 dir,
 						     u32 if_id)
 {
-	int err;
-	struct xfrm_policy *pol, *ret;
 	const xfrm_address_t *daddr, *saddr;
+	struct xfrm_pol_inexact_bin *bin;
+	struct xfrm_policy *pol, *ret;
 	struct hlist_head *chain;
 	unsigned int sequence;
 	u32 priority;
+	int err;
 
 	daddr = xfrm_flowi_daddr(fl, family);
 	saddr = xfrm_flowi_saddr(fl, family);
@@ -1108,7 +1405,10 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 			break;
 		}
 	}
-	chain = &net->xfrm.policy_inexact[dir];
+	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir);
+	if (!bin)
+		goto skip_inexact;
+	chain = &bin->hhead;
 	hlist_for_each_entry_rcu(pol, chain, bydst) {
 		if ((pol->priority >= priority) && ret)
 			break;
@@ -1127,6 +1427,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 		}
 	}
 
+skip_inexact:
 	if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence))
 		goto retry;
 
@@ -1218,6 +1519,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 	/* Socket policies are not hashed. */
 	if (!hlist_unhashed(&pol->bydst)) {
 		hlist_del_rcu(&pol->bydst);
+		hlist_del_init(&pol->bydst_inexact_list);
 		hlist_del(&pol->byidx);
 	}
 
@@ -2795,13 +3097,17 @@ static void xfrm_statistics_fini(struct net *net)
 static int __net_init xfrm_policy_init(struct net *net)
 {
 	unsigned int hmask, sz;
-	int dir;
+	int dir, err;
 
-	if (net_eq(net, &init_net))
+	if (net_eq(net, &init_net)) {
 		xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache",
 					   sizeof(struct xfrm_dst),
 					   0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 					   NULL);
+		err = rhashtable_init(&xfrm_policy_inexact_table,
+				      &xfrm_pol_inexact_params);
+		BUG_ON(err);
+	}
 
 	hmask = 8 - 1;
 	sz = (hmask+1) * sizeof(struct hlist_head);
@@ -2836,6 +3142,7 @@ static int __net_init xfrm_policy_init(struct net *net)
 	seqlock_init(&net->xfrm.policy_hthresh.lock);
 
 	INIT_LIST_HEAD(&net->xfrm.policy_all);
+	INIT_LIST_HEAD(&net->xfrm.inexact_bins);
 	INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
 	INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
 	return 0;
@@ -2854,6 +3161,7 @@ out_byidx:
 
 static void xfrm_policy_fini(struct net *net)
 {
+	struct xfrm_pol_inexact_bin *bin, *tmp;
 	unsigned int sz;
 	int dir;
 
@@ -2879,6 +3187,12 @@ static void xfrm_policy_fini(struct net *net)
 	sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head);
 	WARN_ON(!hlist_empty(net->xfrm.policy_byidx));
 	xfrm_hash_free(net->xfrm.policy_byidx, sz);
+
+	list_for_each_entry_safe(bin, tmp, &net->xfrm.inexact_bins,
+				 inexact_bins) {
+		WARN_ON(!hlist_empty(&bin->hhead));
+		xfrm_policy_inexact_delete_bin(net, bin);
+	}
 }
 
 static int __net_init xfrm_net_init(struct net *net)
@@ -3044,7 +3358,7 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *
 		}
 	}
 	chain = &net->xfrm.policy_inexact[dir];
-	hlist_for_each_entry(pol, chain, bydst) {
+	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
 		if ((pol->priority >= priority) && ret)
 			break;
 
-- 
cgit v1.2.3


From b5fe22e2337d47cd68bb7d8e4103a628808c4d5e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Nov 2018 23:00:36 +0100
Subject: xfrm: policy: consider if_id when hashing inexact policy

This avoids searches of polices that cannot match in the first
place due to different interface id by placing them in different bins.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 5c7e7399323f..dda27fd7b8a4 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -48,6 +48,7 @@ struct xfrm_flo {
 
 struct xfrm_pol_inexact_key {
 	possible_net_t net;
+	u32 if_id;
 	u16 family;
 	u8 dir, type;
 };
@@ -85,11 +86,12 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 						int dir);
 
 static struct xfrm_pol_inexact_bin *
-xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir);
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir,
+			   u32 if_id);
 
 static struct xfrm_pol_inexact_bin *
 xfrm_policy_inexact_lookup_rcu(struct net *net,
-			       u8 type, u16 family, u8 dir);
+			       u8 type, u16 family, u8 dir, u32 if_id);
 static struct xfrm_policy *
 xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy,
 			bool excl);
@@ -618,6 +620,7 @@ xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
 		.family = pol->family,
 		.type = pol->type,
 		.dir = dir,
+		.if_id = pol->if_id,
 	};
 	struct net *net = xp_net(pol);
 
@@ -925,7 +928,8 @@ static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed)
 	const struct xfrm_pol_inexact_key *k = data;
 	u32 a = k->type << 24 | k->dir << 16 | k->family;
 
-	return jhash_2words(a, net_hash_mix(read_pnet(&k->net)), seed);
+	return jhash_3words(a, k->if_id, net_hash_mix(read_pnet(&k->net)),
+			    seed);
 }
 
 static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed)
@@ -957,7 +961,7 @@ static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg,
 	if (ret)
 		return ret;
 
-	return 0;
+	return b->k.if_id ^ key->if_id;
 }
 
 static const struct rhashtable_params xfrm_pol_inexact_params = {
@@ -1094,7 +1098,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 	chain = policy_hash_bysel(net, sel, sel->family, dir);
 	if (!chain) {
 		bin = xfrm_policy_inexact_lookup(net, type,
-						 sel->family, dir);
+						 sel->family, dir, if_id);
 		if (!bin) {
 			spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 			return NULL;
@@ -1335,12 +1339,14 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
 }
 
 static struct xfrm_pol_inexact_bin *
-xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir)
+xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family,
+			       u8 dir, u32 if_id)
 {
 	struct xfrm_pol_inexact_key k = {
 		.family = family,
 		.type = type,
 		.dir = dir,
+		.if_id = if_id,
 	};
 
 	write_pnet(&k.net, net);
@@ -1350,14 +1356,15 @@ xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir)
 }
 
 static struct xfrm_pol_inexact_bin *
-xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir)
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family,
+			   u8 dir, u32 if_id)
 {
 	struct xfrm_pol_inexact_bin *bin;
 
 	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
 
 	rcu_read_lock();
-	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir);
+	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
 	rcu_read_unlock();
 
 	return bin;
@@ -1405,7 +1412,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 			break;
 		}
 	}
-	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir);
+	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
 	if (!bin)
 		goto skip_inexact;
 	chain = &bin->hhead;
-- 
cgit v1.2.3


From 6be3b0db6db82cf056a72cc18042048edd27f8ee Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Nov 2018 23:00:37 +0100
Subject: xfrm: policy: add inexact policy search tree infrastructure

At this time inexact policies are all searched in-order until the first
match is found.  After removal of the flow cache, this resolution has
to be performed for every packetm resulting in major slowdown when
number of inexact policies is high.

This adds infrastructure to later sort inexact policies into a tree.
This only introduces a single class: any:any.

Next patch will add a search tree to pre-sort policies that
have a fixed daddr/prefixlen, so in this patch the any:any class
will still be used for all policies.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h     |   1 +
 net/xfrm/xfrm_policy.c | 301 ++++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 248 insertions(+), 54 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 870fa9b27f7e..9df6dca17155 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -577,6 +577,7 @@ struct xfrm_policy {
 	/* This lock only affects elements except for entry. */
 	rwlock_t		lock;
 	refcount_t		refcnt;
+	u32			pos;
 	struct timer_list	timer;
 
 	atomic_t		genid;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index dda27fd7b8a4..4eb12e9b40c2 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -46,6 +46,9 @@ struct xfrm_flo {
 	u8 flags;
 };
 
+/* prefixes smaller than this are stored in lists, not trees. */
+#define INEXACT_PREFIXLEN_IPV4	16
+#define INEXACT_PREFIXLEN_IPV6	48
 struct xfrm_pol_inexact_key {
 	possible_net_t net;
 	u32 if_id;
@@ -56,6 +59,7 @@ struct xfrm_pol_inexact_key {
 struct xfrm_pol_inexact_bin {
 	struct xfrm_pol_inexact_key k;
 	struct rhash_head head;
+	/* list containing '*:*' policies */
 	struct hlist_head hhead;
 
 	/* slow path below */
@@ -63,6 +67,16 @@ struct xfrm_pol_inexact_bin {
 	struct rcu_head rcu;
 };
 
+enum xfrm_pol_inexact_candidate_type {
+	XFRM_POL_CAND_ANY,
+
+	XFRM_POL_CAND_MAX,
+};
+
+struct xfrm_pol_inexact_candidates {
+	struct hlist_head *res[XFRM_POL_CAND_MAX];
+};
+
 static DEFINE_SPINLOCK(xfrm_if_cb_lock);
 static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
 
@@ -98,6 +112,12 @@ xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy,
 static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
 					    struct xfrm_policy *policy);
 
+static bool
+xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
+				    struct xfrm_pol_inexact_bin *b,
+				    const xfrm_address_t *saddr,
+				    const xfrm_address_t *daddr);
+
 static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy)
 {
 	return refcount_inc_not_zero(&policy->refcnt);
@@ -652,13 +672,48 @@ xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
 	return IS_ERR(prev) ? NULL : prev;
 }
 
-static void xfrm_policy_inexact_delete_bin(struct net *net,
-					   struct xfrm_pol_inexact_bin *b)
+static bool xfrm_pol_inexact_addr_use_any_list(const xfrm_address_t *addr,
+					       int family, u8 prefixlen)
 {
-	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+	if (xfrm_addr_any(addr, family))
+		return true;
+
+	if (family == AF_INET6 && prefixlen < INEXACT_PREFIXLEN_IPV6)
+		return true;
+
+	if (family == AF_INET && prefixlen < INEXACT_PREFIXLEN_IPV4)
+		return true;
+
+	return false;
+}
+
+static bool
+xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy)
+{
+	const xfrm_address_t *addr;
+	bool saddr_any, daddr_any;
+	u8 prefixlen;
+
+	addr = &policy->selector.saddr;
+	prefixlen = policy->selector.prefixlen_s;
 
-	if (!hlist_empty(&b->hhead))
+	saddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
+						       policy->family,
+						       prefixlen);
+	addr = &policy->selector.daddr;
+	prefixlen = policy->selector.prefixlen_d;
+	daddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
+						       policy->family,
+						       prefixlen);
+	return saddr_any && daddr_any;
+}
+
+static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit)
+{
+	if (!hlist_empty(&b->hhead)) {
+		WARN_ON_ONCE(net_exit);
 		return;
+	}
 
 	if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head,
 				   xfrm_pol_inexact_params) == 0) {
@@ -667,14 +722,23 @@ static void xfrm_policy_inexact_delete_bin(struct net *net,
 	}
 }
 
+static void xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b)
+{
+	struct net *net = read_pnet(&b->k.net);
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	__xfrm_policy_inexact_prune_bin(b, false);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+}
+
 static void __xfrm_policy_inexact_flush(struct net *net)
 {
-	struct xfrm_pol_inexact_bin *bin;
+	struct xfrm_pol_inexact_bin *bin, *t;
 
 	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
 
-	list_for_each_entry(bin, &net->xfrm.inexact_bins, inexact_bins)
-		xfrm_policy_inexact_delete_bin(net, bin);
+	list_for_each_entry_safe(bin, t, &net->xfrm.inexact_bins, inexact_bins)
+		__xfrm_policy_inexact_prune_bin(bin, false);
 }
 
 static struct xfrm_policy *
@@ -689,14 +753,28 @@ xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
 	if (!bin)
 		return ERR_PTR(-ENOMEM);
 
-	delpol = xfrm_policy_insert_list(&bin->hhead, policy, excl);
-	if (delpol && excl)
+	net = xp_net(policy);
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	if (xfrm_policy_inexact_insert_use_any_list(policy)) {
+		chain = &bin->hhead;
+		goto insert_to_list;
+	}
+
+	chain = &bin->hhead;
+insert_to_list:
+	delpol = xfrm_policy_insert_list(chain, policy, excl);
+	if (delpol && excl) {
+		__xfrm_policy_inexact_prune_bin(bin, false);
 		return ERR_PTR(-EEXIST);
+	}
 
-	net = xp_net(policy);
 	chain = &net->xfrm.policy_inexact[dir];
 	xfrm_policy_insert_inexact_list(chain, policy);
 
+	if (delpol)
+		__xfrm_policy_inexact_prune_bin(bin, false);
+
 	return delpol;
 }
 
@@ -733,6 +811,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 	 * we start with destructive action.
 	 */
 	list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) {
+		struct xfrm_pol_inexact_bin *bin;
 		u8 dbits, sbits;
 
 		dir = xfrm_policy_id2dir(policy->index);
@@ -761,7 +840,8 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 		    policy->selector.prefixlen_s < sbits)
 			continue;
 
-		if (!xfrm_policy_inexact_alloc_bin(policy, dir))
+		bin = xfrm_policy_inexact_alloc_bin(policy, dir);
+		if (!bin)
 			goto out_unlock;
 	}
 
@@ -820,6 +900,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 	}
 
 out_unlock:
+	__xfrm_policy_inexact_flush(net);
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	mutex_unlock(&hash_resize_mutex);
@@ -977,6 +1058,7 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
 {
 	struct xfrm_policy *pol, *delpol = NULL;
 	struct hlist_node *newpos = NULL;
+	int i = 0;
 
 	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
 		if (pol->type == policy->type &&
@@ -1000,6 +1082,11 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
 		hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos);
 	else
 		hlist_add_head_rcu(&policy->bydst_inexact_list, chain);
+
+	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
+		pol->pos = i;
+		i++;
+	}
 }
 
 static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
@@ -1083,6 +1170,29 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 }
 EXPORT_SYMBOL(xfrm_policy_insert);
 
+static struct xfrm_policy *
+__xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id,
+			u8 type, int dir,
+			struct xfrm_selector *sel,
+			struct xfrm_sec_ctx *ctx)
+{
+	struct xfrm_policy *pol;
+
+	if (!chain)
+		return NULL;
+
+	hlist_for_each_entry(pol, chain, bydst) {
+		if (pol->type == type &&
+		    pol->if_id == if_id &&
+		    (mark & pol->mark.m) == pol->mark.v &&
+		    !selector_cmp(sel, &pol->selector) &&
+		    xfrm_sec_ctx_match(ctx, pol->security))
+			return pol;
+	}
+
+	return NULL;
+}
+
 struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 					  u8 type, int dir,
 					  struct xfrm_selector *sel,
@@ -1097,6 +1207,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, sel, sel->family, dir);
 	if (!chain) {
+		struct xfrm_pol_inexact_candidates cand;
+		int i;
+
 		bin = xfrm_policy_inexact_lookup(net, type,
 						 sel->family, dir, if_id);
 		if (!bin) {
@@ -1104,35 +1217,46 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 			return NULL;
 		}
 
-		chain = &bin->hhead;
+		if (!xfrm_policy_find_inexact_candidates(&cand, bin,
+							 &sel->saddr,
+							 &sel->daddr)) {
+			spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+			return NULL;
+		}
+
+		pol = NULL;
+		for (i = 0; i < ARRAY_SIZE(cand.res); i++) {
+			struct xfrm_policy *tmp;
+
+			tmp = __xfrm_policy_bysel_ctx(cand.res[i], mark,
+						      if_id, type, dir,
+						      sel, ctx);
+			if (tmp && pol && tmp->pos < pol->pos)
+				pol = tmp;
+		}
+	} else {
+		pol = __xfrm_policy_bysel_ctx(chain, mark, if_id, type, dir,
+					      sel, ctx);
 	}
 
-	ret = NULL;
-	hlist_for_each_entry(pol, chain, bydst) {
-		if (pol->type == type &&
-		    pol->if_id == if_id &&
-		    (mark & pol->mark.m) == pol->mark.v &&
-		    !selector_cmp(sel, &pol->selector) &&
-		    xfrm_sec_ctx_match(ctx, pol->security)) {
-			xfrm_pol_hold(pol);
-			if (delete) {
-				*err = security_xfrm_policy_delete(
-								pol->security);
-				if (*err) {
-					spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-					return pol;
-				}
-				__xfrm_policy_unlink(pol, dir);
-				xfrm_policy_inexact_delete_bin(net, bin);
+	if (pol) {
+		xfrm_pol_hold(pol);
+		if (delete) {
+			*err = security_xfrm_policy_delete(pol->security);
+			if (*err) {
+				spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+				return pol;
 			}
-			ret = pol;
-			break;
+			__xfrm_policy_unlink(pol, dir);
 		}
+		ret = pol;
 	}
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (ret && delete)
 		xfrm_policy_kill(ret);
+	if (bin && delete)
+		xfrm_policy_inexact_prune_bin(bin);
 	return ret;
 }
 EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
@@ -1338,6 +1462,20 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
 	return ret;
 }
 
+static bool
+xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
+				    struct xfrm_pol_inexact_bin *b,
+				    const xfrm_address_t *saddr,
+				    const xfrm_address_t *daddr)
+{
+	if (!b)
+		return false;
+
+	memset(cand, 0, sizeof(*cand));
+	cand->res[XFRM_POL_CAND_ANY] = &b->hhead;
+	return true;
+}
+
 static struct xfrm_pol_inexact_bin *
 xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family,
 			       u8 dir, u32 if_id)
@@ -1370,11 +1508,76 @@ xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family,
 	return bin;
 }
 
+static struct xfrm_policy *
+__xfrm_policy_eval_candidates(struct hlist_head *chain,
+			      struct xfrm_policy *prefer,
+			      const struct flowi *fl,
+			      u8 type, u16 family, int dir, u32 if_id)
+{
+	u32 priority = prefer ? prefer->priority : ~0u;
+	struct xfrm_policy *pol;
+
+	if (!chain)
+		return NULL;
+
+	hlist_for_each_entry_rcu(pol, chain, bydst) {
+		int err;
+
+		if (pol->priority > priority)
+			break;
+
+		err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
+		if (err) {
+			if (err != -ESRCH)
+				return ERR_PTR(err);
+
+			continue;
+		}
+
+		if (prefer) {
+			/* matches.  Is it older than *prefer? */
+			if (pol->priority == priority &&
+			    prefer->pos < pol->pos)
+				return prefer;
+		}
+
+		return pol;
+	}
+
+	return NULL;
+}
+
+static struct xfrm_policy *
+xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates *cand,
+			    struct xfrm_policy *prefer,
+			    const struct flowi *fl,
+			    u8 type, u16 family, int dir, u32 if_id)
+{
+	struct xfrm_policy *tmp;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cand->res); i++) {
+		tmp = __xfrm_policy_eval_candidates(cand->res[i],
+						    prefer,
+						    fl, type, family, dir,
+						    if_id);
+		if (!tmp)
+			continue;
+
+		if (IS_ERR(tmp))
+			return tmp;
+		prefer = tmp;
+	}
+
+	return prefer;
+}
+
 static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 						     const struct flowi *fl,
 						     u16 family, u8 dir,
 						     u32 if_id)
 {
+	struct xfrm_pol_inexact_candidates cand;
 	const xfrm_address_t *daddr, *saddr;
 	struct xfrm_pol_inexact_bin *bin;
 	struct xfrm_policy *pol, *ret;
@@ -1413,25 +1616,16 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 		}
 	}
 	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
-	if (!bin)
+	if (!bin || !xfrm_policy_find_inexact_candidates(&cand, bin, saddr,
+							 daddr))
 		goto skip_inexact;
-	chain = &bin->hhead;
-	hlist_for_each_entry_rcu(pol, chain, bydst) {
-		if ((pol->priority >= priority) && ret)
-			break;
 
-		err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
-		if (err) {
-			if (err == -ESRCH)
-				continue;
-			else {
-				ret = ERR_PTR(err);
-				goto fail;
-			}
-		} else {
-			ret = pol;
-			break;
-		}
+	pol = xfrm_policy_eval_candidates(&cand, ret, fl, type,
+					  family, dir, if_id);
+	if (pol) {
+		ret = pol;
+		if (IS_ERR(pol))
+			goto fail;
 	}
 
 skip_inexact:
@@ -3168,7 +3362,7 @@ out_byidx:
 
 static void xfrm_policy_fini(struct net *net)
 {
-	struct xfrm_pol_inexact_bin *bin, *tmp;
+	struct xfrm_pol_inexact_bin *b, *t;
 	unsigned int sz;
 	int dir;
 
@@ -3195,11 +3389,10 @@ static void xfrm_policy_fini(struct net *net)
 	WARN_ON(!hlist_empty(net->xfrm.policy_byidx));
 	xfrm_hash_free(net->xfrm.policy_byidx, sz);
 
-	list_for_each_entry_safe(bin, tmp, &net->xfrm.inexact_bins,
-				 inexact_bins) {
-		WARN_ON(!hlist_empty(&bin->hhead));
-		xfrm_policy_inexact_delete_bin(net, bin);
-	}
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	list_for_each_entry_safe(b, t, &net->xfrm.inexact_bins, inexact_bins)
+		__xfrm_policy_inexact_prune_bin(b, true);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 }
 
 static int __net_init xfrm_net_init(struct net *net)
-- 
cgit v1.2.3


From 9cf545ebd591da673bb6b6c88150212ad83567a9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Nov 2018 23:00:38 +0100
Subject: xfrm: policy: store inexact policies in a tree ordered by destination
 address

This adds inexact lists per destination network, stored in a search tree.

Inexact lookups now return two 'candidate lists', the 'any' policies
('any' destionations), and a list of policies that share same
daddr/prefix.

Next patch will add a second search tree for 'saddr:any' policies
so we can avoid placing those on the 'any:any' list too.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h     |   1 +
 net/xfrm/xfrm_policy.c | 333 ++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 328 insertions(+), 6 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 9df6dca17155..fa4b3c877fcf 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -590,6 +590,7 @@ struct xfrm_policy {
 	struct xfrm_lifetime_cur curlft;
 	struct xfrm_policy_walk_entry walk;
 	struct xfrm_policy_queue polq;
+	bool                    bydst_reinsert;
 	u8			type;
 	u8			action;
 	u8			flags;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 4eb12e9b40c2..81447d5d02e6 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -49,6 +49,38 @@ struct xfrm_flo {
 /* prefixes smaller than this are stored in lists, not trees. */
 #define INEXACT_PREFIXLEN_IPV4	16
 #define INEXACT_PREFIXLEN_IPV6	48
+
+struct xfrm_pol_inexact_node {
+	struct rb_node node;
+	union {
+		xfrm_address_t addr;
+		struct rcu_head rcu;
+	};
+	u8 prefixlen;
+
+	/* the policies matching this node, can be empty list */
+	struct hlist_head hhead;
+};
+
+/* xfrm inexact policy search tree:
+ * xfrm_pol_inexact_bin = hash(dir,type,family,if_id);
+ *  |
+ * +---- root_d: sorted by daddr:prefix
+ * |                 |
+ * |        xfrm_pol_inexact_node
+ * |                 |
+ * |                 +- coarse policies and all any:daddr policies
+ * |
+ * +---- coarse policies and all any:any policies
+ *
+ * Lookups return two candidate lists:
+ * 1. any:any list from top-level xfrm_pol_inexact_bin
+ * 2. any:daddr list from daddr tree
+ *
+ * This result set then needs to be searched for the policy with
+ * the lowest priority.  If two results have same prio, youngest one wins.
+ */
+
 struct xfrm_pol_inexact_key {
 	possible_net_t net;
 	u32 if_id;
@@ -62,12 +94,17 @@ struct xfrm_pol_inexact_bin {
 	/* list containing '*:*' policies */
 	struct hlist_head hhead;
 
+	seqcount_t count;
+	/* tree sorted by daddr/prefix */
+	struct rb_root root_d;
+
 	/* slow path below */
 	struct list_head inexact_bins;
 	struct rcu_head rcu;
 };
 
 enum xfrm_pol_inexact_candidate_type {
+	XFRM_POL_CAND_DADDR,
 	XFRM_POL_CAND_ANY,
 
 	XFRM_POL_CAND_MAX,
@@ -658,6 +695,8 @@ xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
 
 	bin->k = k;
 	INIT_HLIST_HEAD(&bin->hhead);
+	bin->root_d = RB_ROOT;
+	seqcount_init(&bin->count);
 
 	prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
 						&bin->k, &bin->head,
@@ -708,9 +747,211 @@ xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy)
 	return saddr_any && daddr_any;
 }
 
+static void xfrm_pol_inexact_node_init(struct xfrm_pol_inexact_node *node,
+				       const xfrm_address_t *addr, u8 prefixlen)
+{
+	node->addr = *addr;
+	node->prefixlen = prefixlen;
+}
+
+static struct xfrm_pol_inexact_node *
+xfrm_pol_inexact_node_alloc(const xfrm_address_t *addr, u8 prefixlen)
+{
+	struct xfrm_pol_inexact_node *node;
+
+	node = kzalloc(sizeof(*node), GFP_ATOMIC);
+	if (node)
+		xfrm_pol_inexact_node_init(node, addr, prefixlen);
+
+	return node;
+}
+
+static int xfrm_policy_addr_delta(const xfrm_address_t *a,
+				  const xfrm_address_t *b,
+				  u8 prefixlen, u16 family)
+{
+	unsigned int pdw, pbi;
+	int delta = 0;
+
+	switch (family) {
+	case AF_INET:
+		if (sizeof(long) == 4 && prefixlen == 0)
+			return ntohl(a->a4) - ntohl(b->a4);
+		return (ntohl(a->a4) & ((~0UL << (32 - prefixlen)))) -
+		       (ntohl(b->a4) & ((~0UL << (32 - prefixlen))));
+	case AF_INET6:
+		pdw = prefixlen >> 5;
+		pbi = prefixlen & 0x1f;
+
+		if (pdw) {
+			delta = memcmp(a->a6, b->a6, pdw << 2);
+			if (delta)
+				return delta;
+		}
+		if (pbi) {
+			u32 mask = ~0u << (32 - pbi);
+
+			delta = (ntohl(a->a6[pdw]) & mask) -
+				(ntohl(b->a6[pdw]) & mask);
+		}
+		break;
+	default:
+		break;
+	}
+
+	return delta;
+}
+
+static void xfrm_policy_inexact_list_reinsert(struct net *net,
+					      struct xfrm_pol_inexact_node *n,
+					      u16 family)
+{
+	struct hlist_node *newpos = NULL;
+	struct xfrm_policy *policy, *p;
+
+	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+		if (!policy->bydst_reinsert)
+			continue;
+
+		WARN_ON_ONCE(policy->family != family);
+
+		policy->bydst_reinsert = false;
+		hlist_for_each_entry(p, &n->hhead, bydst) {
+			if (policy->priority >= p->priority)
+				newpos = &p->bydst;
+			else
+				break;
+		}
+
+		if (newpos)
+			hlist_add_behind(&policy->bydst, newpos);
+		else
+			hlist_add_head(&policy->bydst, &n->hhead);
+	}
+}
+
+/* merge nodes v and n */
+static void xfrm_policy_inexact_node_merge(struct net *net,
+					   struct xfrm_pol_inexact_node *v,
+					   struct xfrm_pol_inexact_node *n,
+					   u16 family)
+{
+	struct xfrm_policy *tmp;
+
+	hlist_for_each_entry(tmp, &v->hhead, bydst)
+		tmp->bydst_reinsert = true;
+	hlist_for_each_entry(tmp, &n->hhead, bydst)
+		tmp->bydst_reinsert = true;
+
+	INIT_HLIST_HEAD(&n->hhead);
+	xfrm_policy_inexact_list_reinsert(net, n, family);
+}
+
+static struct xfrm_pol_inexact_node *
+xfrm_policy_inexact_insert_node(struct net *net,
+				struct rb_root *root,
+				xfrm_address_t *addr,
+				u16 family, u8 prefixlen, u8 dir)
+{
+	struct xfrm_pol_inexact_node *cached = NULL;
+	struct rb_node **p, *parent = NULL;
+	struct xfrm_pol_inexact_node *node;
+
+	p = &root->rb_node;
+	while (*p) {
+		int delta;
+
+		parent = *p;
+		node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
+
+		delta = xfrm_policy_addr_delta(addr, &node->addr,
+					       node->prefixlen,
+					       family);
+		if (delta == 0 && prefixlen >= node->prefixlen) {
+			WARN_ON_ONCE(cached); /* ipsec policies got lost */
+			return node;
+		}
+
+		if (delta < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+
+		if (prefixlen < node->prefixlen) {
+			delta = xfrm_policy_addr_delta(addr, &node->addr,
+						       prefixlen,
+						       family);
+			if (delta)
+				continue;
+
+			/* This node is a subnet of the new prefix. It needs
+			 * to be removed and re-inserted with the smaller
+			 * prefix and all nodes that are now also covered
+			 * by the reduced prefixlen.
+			 */
+			rb_erase(&node->node, root);
+
+			if (!cached) {
+				xfrm_pol_inexact_node_init(node, addr,
+							   prefixlen);
+				cached = node;
+			} else {
+				/* This node also falls within the new
+				 * prefixlen. Merge the to-be-reinserted
+				 * node and this one.
+				 */
+				xfrm_policy_inexact_node_merge(net, node,
+							       cached, family);
+				kfree_rcu(node, rcu);
+			}
+
+			/* restart */
+			p = &root->rb_node;
+			parent = NULL;
+		}
+	}
+
+	node = cached;
+	if (!node) {
+		node = xfrm_pol_inexact_node_alloc(addr, prefixlen);
+		if (!node)
+			return NULL;
+	}
+
+	rb_link_node_rcu(&node->node, parent, p);
+	rb_insert_color(&node->node, root);
+
+	return node;
+}
+
+static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm)
+{
+	struct xfrm_pol_inexact_node *node;
+	struct rb_node *rn = rb_first(r);
+
+	while (rn) {
+		node = rb_entry(rn, struct xfrm_pol_inexact_node, node);
+
+		rn = rb_next(rn);
+
+		if (!hlist_empty(&node->hhead)) {
+			WARN_ON_ONCE(rm);
+			continue;
+		}
+
+		rb_erase(&node->node, r);
+		kfree_rcu(node, rcu);
+	}
+}
+
 static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit)
 {
-	if (!hlist_empty(&b->hhead)) {
+	write_seqcount_begin(&b->count);
+	xfrm_policy_inexact_gc_tree(&b->root_d, net_exit);
+	write_seqcount_end(&b->count);
+
+	if (!RB_EMPTY_ROOT(&b->root_d) ||
+	    !hlist_empty(&b->hhead)) {
 		WARN_ON_ONCE(net_exit);
 		return;
 	}
@@ -741,6 +982,37 @@ static void __xfrm_policy_inexact_flush(struct net *net)
 		__xfrm_policy_inexact_prune_bin(bin, false);
 }
 
+static struct hlist_head *
+xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
+				struct xfrm_policy *policy, u8 dir)
+{
+	struct xfrm_pol_inexact_node *n;
+	struct net *net;
+
+	net = xp_net(policy);
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	if (xfrm_policy_inexact_insert_use_any_list(policy))
+		return &bin->hhead;
+
+	if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
+					       policy->family,
+					       policy->selector.prefixlen_d))
+		return &bin->hhead;
+
+	/* daddr is fixed */
+	write_seqcount_begin(&bin->count);
+	n = xfrm_policy_inexact_insert_node(net,
+					    &bin->root_d,
+					    &policy->selector.daddr,
+					    policy->family,
+					    policy->selector.prefixlen_d, dir);
+	write_seqcount_end(&bin->count);
+	if (!n)
+		return NULL;
+	return &n->hhead;
+}
+
 static struct xfrm_policy *
 xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
 {
@@ -756,13 +1028,12 @@ xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
 	net = xp_net(policy);
 	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
 
-	if (xfrm_policy_inexact_insert_use_any_list(policy)) {
-		chain = &bin->hhead;
-		goto insert_to_list;
+	chain = xfrm_policy_inexact_alloc_chain(bin, policy, dir);
+	if (!chain) {
+		__xfrm_policy_inexact_prune_bin(bin, false);
+		return ERR_PTR(-ENOMEM);
 	}
 
-	chain = &bin->hhead;
-insert_to_list:
 	delpol = xfrm_policy_insert_list(chain, policy, excl);
 	if (delpol && excl) {
 		__xfrm_policy_inexact_prune_bin(bin, false);
@@ -843,6 +1114,9 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 		bin = xfrm_policy_inexact_alloc_bin(policy, dir);
 		if (!bin)
 			goto out_unlock;
+
+		if (!xfrm_policy_inexact_alloc_chain(bin, policy, dir))
+			goto out_unlock;
 	}
 
 	/* reset the bydst and inexact table in all directions */
@@ -1462,17 +1736,64 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
 	return ret;
 }
 
+static struct xfrm_pol_inexact_node *
+xfrm_policy_lookup_inexact_addr(const struct rb_root *r,
+				seqcount_t *count,
+				const xfrm_address_t *addr, u16 family)
+{
+	const struct rb_node *parent;
+	int seq;
+
+again:
+	seq = read_seqcount_begin(count);
+
+	parent = rcu_dereference_raw(r->rb_node);
+	while (parent) {
+		struct xfrm_pol_inexact_node *node;
+		int delta;
+
+		node = rb_entry(parent, struct xfrm_pol_inexact_node, node);
+
+		delta = xfrm_policy_addr_delta(addr, &node->addr,
+					       node->prefixlen, family);
+		if (delta < 0) {
+			parent = rcu_dereference_raw(parent->rb_left);
+			continue;
+		} else if (delta > 0) {
+			parent = rcu_dereference_raw(parent->rb_right);
+			continue;
+		}
+
+		return node;
+	}
+
+	if (read_seqcount_retry(count, seq))
+		goto again;
+
+	return NULL;
+}
+
 static bool
 xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
 				    struct xfrm_pol_inexact_bin *b,
 				    const xfrm_address_t *saddr,
 				    const xfrm_address_t *daddr)
 {
+	struct xfrm_pol_inexact_node *n;
+	u16 family;
+
 	if (!b)
 		return false;
 
+	family = b->k.family;
 	memset(cand, 0, sizeof(*cand));
 	cand->res[XFRM_POL_CAND_ANY] = &b->hhead;
+
+	n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr,
+					    family);
+	if (n)
+		cand->res[XFRM_POL_CAND_DADDR] = &n->hhead;
+
 	return true;
 }
 
-- 
cgit v1.2.3


From e901cbc29316fb06423de5dfbc5afb78d4efda53 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Nov 2018 23:00:39 +0100
Subject: xfrm: policy: check reinserted policies match their node

validate the re-inserted policies match the lookup node.
Policies that fail this test won't be returned in the candidate set.

This is enabled by default for now, it should not cause noticeable
reinsert slow down.

Such reinserts are needed when we have to merge an existing node
(e.g. for 10.0.0.0/28 because a overlapping subnet was added (e.g.
10.0.0.0/24), so whenever this happens existing policies have to
be placed on the list of the new node.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 81447d5d02e6..57e28dcd7c53 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -806,10 +806,16 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net,
 					      struct xfrm_pol_inexact_node *n,
 					      u16 family)
 {
+	unsigned int matched_s, matched_d;
 	struct hlist_node *newpos = NULL;
 	struct xfrm_policy *policy, *p;
 
+	matched_s = 0;
+	matched_d = 0;
+
 	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+		bool matches_s, matches_d;
+
 		if (!policy->bydst_reinsert)
 			continue;
 
@@ -827,6 +833,32 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net,
 			hlist_add_behind(&policy->bydst, newpos);
 		else
 			hlist_add_head(&policy->bydst, &n->hhead);
+
+		/* paranoia checks follow.
+		 * Check that the reinserted policy matches at least
+		 * saddr or daddr for current node prefix.
+		 *
+		 * Matching both is fine, matching saddr in one policy
+		 * (but not daddr) and then matching only daddr in another
+		 * is a bug.
+		 */
+		matches_s = xfrm_policy_addr_delta(&policy->selector.saddr,
+						   &n->addr,
+						   n->prefixlen,
+						   family) == 0;
+		matches_d = xfrm_policy_addr_delta(&policy->selector.daddr,
+						   &n->addr,
+						   n->prefixlen,
+						   family) == 0;
+		if (matches_s && matches_d)
+			continue;
+
+		WARN_ON_ONCE(!matches_s && !matches_d);
+		if (matches_s)
+			matched_s++;
+		if (matches_d)
+			matched_d++;
+		WARN_ON_ONCE(matched_s && matched_d);
 	}
 }
 
-- 
cgit v1.2.3


From 64a09a7bfedee6ab97273d653dfac28e82635b61 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Nov 2018 23:00:40 +0100
Subject: xfrm: policy: store inexact policies in a tree ordered by source
 address

This adds the 'saddr:any' search class.  It contains all policies that have
a fixed saddr/prefixlen, but 'any' destination.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 46 ++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 42 insertions(+), 4 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 57e28dcd7c53..38e33326c856 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -71,11 +71,20 @@ struct xfrm_pol_inexact_node {
  * |                 |
  * |                 +- coarse policies and all any:daddr policies
  * |
+ * +---- root_s: sorted by saddr:prefix
+ * |                 |
+ * |        xfrm_pol_inexact_node
+ * |                 |
+ * |                 + root: unused
+ * |                 |
+ * |                 + hhead: saddr:any policies
+ * |
  * +---- coarse policies and all any:any policies
  *
- * Lookups return two candidate lists:
+ * Lookups return three candidate lists:
  * 1. any:any list from top-level xfrm_pol_inexact_bin
  * 2. any:daddr list from daddr tree
+ * 2. saddr:any list from saddr tree
  *
  * This result set then needs to be searched for the policy with
  * the lowest priority.  If two results have same prio, youngest one wins.
@@ -98,12 +107,16 @@ struct xfrm_pol_inexact_bin {
 	/* tree sorted by daddr/prefix */
 	struct rb_root root_d;
 
+	/* tree sorted by saddr/prefix */
+	struct rb_root root_s;
+
 	/* slow path below */
 	struct list_head inexact_bins;
 	struct rcu_head rcu;
 };
 
 enum xfrm_pol_inexact_candidate_type {
+	XFRM_POL_CAND_SADDR,
 	XFRM_POL_CAND_DADDR,
 	XFRM_POL_CAND_ANY,
 
@@ -696,6 +709,7 @@ xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
 	bin->k = k;
 	INIT_HLIST_HEAD(&bin->hhead);
 	bin->root_d = RB_ROOT;
+	bin->root_s = RB_ROOT;
 	seqcount_init(&bin->count);
 
 	prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
@@ -980,9 +994,10 @@ static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool
 {
 	write_seqcount_begin(&b->count);
 	xfrm_policy_inexact_gc_tree(&b->root_d, net_exit);
+	xfrm_policy_inexact_gc_tree(&b->root_s, net_exit);
 	write_seqcount_end(&b->count);
 
-	if (!RB_EMPTY_ROOT(&b->root_d) ||
+	if (!RB_EMPTY_ROOT(&b->root_d) || !RB_EMPTY_ROOT(&b->root_s) ||
 	    !hlist_empty(&b->hhead)) {
 		WARN_ON_ONCE(net_exit);
 		return;
@@ -1027,11 +1042,29 @@ xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
 	if (xfrm_policy_inexact_insert_use_any_list(policy))
 		return &bin->hhead;
 
-	if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
+	/* saddr is wildcard */
+	if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr,
 					       policy->family,
-					       policy->selector.prefixlen_d))
+					       policy->selector.prefixlen_s))
 		return &bin->hhead;
 
+	if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
+					       policy->family,
+					       policy->selector.prefixlen_d)) {
+		write_seqcount_begin(&bin->count);
+		n = xfrm_policy_inexact_insert_node(net,
+						    &bin->root_s,
+						    &policy->selector.saddr,
+						    policy->family,
+						    policy->selector.prefixlen_s,
+						    dir);
+		write_seqcount_end(&bin->count);
+		if (!n)
+			return NULL;
+
+		return &n->hhead;
+	}
+
 	/* daddr is fixed */
 	write_seqcount_begin(&bin->count);
 	n = xfrm_policy_inexact_insert_node(net,
@@ -1826,6 +1859,11 @@ xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
 	if (n)
 		cand->res[XFRM_POL_CAND_DADDR] = &n->hhead;
 
+	n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr,
+					    family);
+	if (n)
+		cand->res[XFRM_POL_CAND_SADDR] = &n->hhead;
+
 	return true;
 }
 
-- 
cgit v1.2.3


From 6ac098b2a9d3088781f1c2b7138cf38e817a3da7 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Nov 2018 23:00:41 +0100
Subject: xfrm: policy: add 2nd-level saddr trees for inexact policies

This adds the fourth and final search class, containing policies
where both saddr and daddr have prefix lengths (i.e., not wildcards).

Inexact policies now end up in one of the following four search classes:

1. "Any:Any" list, containing policies where both saddr and daddr are
   wildcards or have very coarse prefixes, e.g. 10.0.0.0/8 and the like.
2. "saddr:any" list, containing policies with a fixed saddr/prefixlen,
   but without destination restrictions.
   These lists are stored in rbtree nodes; each node contains those
   policies matching saddr/prefixlen.
3. "Any:daddr" list. Similar to 2), except for policies where only the
   destinations are specified.
4. "saddr:daddr" lists, containing only those policies that
   match the given source/destination network.
   The root of the saddr/daddr nodes gets stored in the nodes of the
   'daddr' tree.

This diagram illustrates the list classes, and their
placement in the lookup hierarchy:

    xfrm_pol_inexact_bin = hash(dir,type,family,if_id);
      |
      +---- root_d: sorted by daddr:prefix
      |                 |
      |        xfrm_pol_inexact_node
      |                 |
      |                 +- root: sorted by saddr/prefix
      |                 |              |
      |                 |         xfrm_pol_inexact_node
      |                 |              |
      |                 |              + root: unused
      |                 |              |
      |                 |              + hhead: saddr:daddr policies
      |                 |
      |                 +- coarse policies and all any:daddr policies
      |
      +---- root_s: sorted by saddr:prefix
      |                 |
      |        xfrm_pol_inexact_node
      |                 |
      |                 + root: unused
      |                 |
      |                 + hhead: saddr:any policies
      |
      +---- coarse policies and all any:any policies

lookup for an inexact policy returns pointers to the four relevant list
classes, after which each of the lists needs to be searched for the policy
with the higher priority.

This will only speed up lookups in case we have many policies and a
sizeable portion of these have disjunct saddr/daddr addresses.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 118 ++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 108 insertions(+), 10 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 38e33326c856..bd80b8a4322f 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -58,6 +58,8 @@ struct xfrm_pol_inexact_node {
 	};
 	u8 prefixlen;
 
+	struct rb_root root;
+
 	/* the policies matching this node, can be empty list */
 	struct hlist_head hhead;
 };
@@ -69,6 +71,14 @@ struct xfrm_pol_inexact_node {
  * |                 |
  * |        xfrm_pol_inexact_node
  * |                 |
+ * |                 +- root: sorted by saddr/prefix
+ * |                 |              |
+ * |                 |         xfrm_pol_inexact_node
+ * |                 |              |
+ * |                 |              + root: unused
+ * |                 |              |
+ * |                 |              + hhead: saddr:daddr policies
+ * |                 |
  * |                 +- coarse policies and all any:daddr policies
  * |
  * +---- root_s: sorted by saddr:prefix
@@ -81,10 +91,11 @@ struct xfrm_pol_inexact_node {
  * |
  * +---- coarse policies and all any:any policies
  *
- * Lookups return three candidate lists:
+ * Lookups return four candidate lists:
  * 1. any:any list from top-level xfrm_pol_inexact_bin
  * 2. any:daddr list from daddr tree
- * 2. saddr:any list from saddr tree
+ * 3. saddr:daddr list from 2nd level daddr tree
+ * 4. saddr:any list from saddr tree
  *
  * This result set then needs to be searched for the policy with
  * the lowest priority.  If two results have same prio, youngest one wins.
@@ -116,6 +127,7 @@ struct xfrm_pol_inexact_bin {
 };
 
 enum xfrm_pol_inexact_candidate_type {
+	XFRM_POL_CAND_BOTH,
 	XFRM_POL_CAND_SADDR,
 	XFRM_POL_CAND_DADDR,
 	XFRM_POL_CAND_ANY,
@@ -876,13 +888,82 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net,
 	}
 }
 
+static void xfrm_policy_inexact_node_reinsert(struct net *net,
+					      struct xfrm_pol_inexact_node *n,
+					      struct rb_root *new,
+					      u16 family)
+{
+	struct rb_node **p, *parent = NULL;
+	struct xfrm_pol_inexact_node *node;
+
+	/* we should not have another subtree here */
+	WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root));
+
+	p = &new->rb_node;
+	while (*p) {
+		u8 prefixlen;
+		int delta;
+
+		parent = *p;
+		node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
+
+		prefixlen = min(node->prefixlen, n->prefixlen);
+
+		delta = xfrm_policy_addr_delta(&n->addr, &node->addr,
+					       prefixlen, family);
+		if (delta < 0) {
+			p = &parent->rb_left;
+		} else if (delta > 0) {
+			p = &parent->rb_right;
+		} else {
+			struct xfrm_policy *tmp;
+
+			hlist_for_each_entry(tmp, &node->hhead, bydst)
+				tmp->bydst_reinsert = true;
+			hlist_for_each_entry(tmp, &n->hhead, bydst)
+				tmp->bydst_reinsert = true;
+
+			INIT_HLIST_HEAD(&node->hhead);
+			xfrm_policy_inexact_list_reinsert(net, node, family);
+
+			if (node->prefixlen == n->prefixlen) {
+				kfree_rcu(n, rcu);
+				return;
+			}
+
+			rb_erase(*p, new);
+			kfree_rcu(n, rcu);
+			n = node;
+			n->prefixlen = prefixlen;
+			*p = new->rb_node;
+			parent = NULL;
+		}
+	}
+
+	rb_link_node_rcu(&n->node, parent, p);
+	rb_insert_color(&n->node, new);
+}
+
 /* merge nodes v and n */
 static void xfrm_policy_inexact_node_merge(struct net *net,
 					   struct xfrm_pol_inexact_node *v,
 					   struct xfrm_pol_inexact_node *n,
 					   u16 family)
 {
+	struct xfrm_pol_inexact_node *node;
 	struct xfrm_policy *tmp;
+	struct rb_node *rnode;
+
+	/* To-be-merged node v has a subtree.
+	 *
+	 * Dismantle it and insert its nodes to n->root.
+	 */
+	while ((rnode = rb_first(&v->root)) != NULL) {
+		node = rb_entry(rnode, struct xfrm_pol_inexact_node, node);
+		rb_erase(&node->node, &v->root);
+		xfrm_policy_inexact_node_reinsert(net, node, &n->root,
+						  family);
+	}
 
 	hlist_for_each_entry(tmp, &v->hhead, bydst)
 		tmp->bydst_reinsert = true;
@@ -978,9 +1059,10 @@ static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm)
 	while (rn) {
 		node = rb_entry(rn, struct xfrm_pol_inexact_node, node);
 
+		xfrm_policy_inexact_gc_tree(&node->root, rm);
 		rn = rb_next(rn);
 
-		if (!hlist_empty(&node->hhead)) {
+		if (!hlist_empty(&node->hhead) || !RB_EMPTY_ROOT(&node->root)) {
 			WARN_ON_ONCE(rm);
 			continue;
 		}
@@ -1042,12 +1124,6 @@ xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
 	if (xfrm_policy_inexact_insert_use_any_list(policy))
 		return &bin->hhead;
 
-	/* saddr is wildcard */
-	if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr,
-					       policy->family,
-					       policy->selector.prefixlen_s))
-		return &bin->hhead;
-
 	if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
 					       policy->family,
 					       policy->selector.prefixlen_d)) {
@@ -1075,6 +1151,23 @@ xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
 	write_seqcount_end(&bin->count);
 	if (!n)
 		return NULL;
+
+	/* saddr is wildcard */
+	if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr,
+					       policy->family,
+					       policy->selector.prefixlen_s))
+		return &n->hhead;
+
+	write_seqcount_begin(&bin->count);
+	n = xfrm_policy_inexact_insert_node(net,
+					    &n->root,
+					    &policy->selector.saddr,
+					    policy->family,
+					    policy->selector.prefixlen_s, dir);
+	write_seqcount_end(&bin->count);
+	if (!n)
+		return NULL;
+
 	return &n->hhead;
 }
 
@@ -1856,8 +1949,13 @@ xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
 
 	n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr,
 					    family);
-	if (n)
+	if (n) {
 		cand->res[XFRM_POL_CAND_DADDR] = &n->hhead;
+		n = xfrm_policy_lookup_inexact_addr(&n->root, &b->count, saddr,
+						    family);
+		if (n)
+			cand->res[XFRM_POL_CAND_BOTH] = &n->hhead;
+	}
 
 	n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr,
 					    family);
-- 
cgit v1.2.3


From 307f39b021995db67b2f39da7af006e2376fb452 Mon Sep 17 00:00:00 2001
From: Jacob Wen <jian.w.wen@oracle.com>
Date: Fri, 9 Nov 2018 14:53:59 +0800
Subject: xen/netfront: remove unnecessary wmb

RING_PUSH_REQUESTS_AND_CHECK_NOTIFY is already able to make sure backend sees
requests before req_prod is updated.

Signed-off-by: Jacob Wen <jian.w.wen@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index f17f602e6171..a8303afa15f1 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -337,8 +337,6 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
 		return;
 	}
 
-	wmb();		/* barrier so backend seens requests */
-
 	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->rx, notify);
 	if (notify)
 		notify_remote_via_irq(queue->rx_irq);
-- 
cgit v1.2.3


From e6e8869aed897a021fafa6f412e9e4b7e2ea6cd3 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Fri, 9 Nov 2018 17:04:51 +0800
Subject: net: tcp: remove BUG_ON from tcp_v4_err

if skb is NULL pointer, and the following access of skb's
skb_mstamp_ns will trigger panic, which is same as BUG_ON

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a336787d75e5..5424a4077c27 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -542,7 +542,6 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
 
 		skb = tcp_rtx_queue_head(sk);
-		BUG_ON(!skb);
 
 		tcp_mstamp_refresh(tp);
 		delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb));
-- 
cgit v1.2.3


From 2a8d84bf513823ba398f4b2dec41b8decf4041af Mon Sep 17 00:00:00 2001
From: Arjun Vynipadath <arjun@chelsio.com>
Date: Fri, 9 Nov 2018 14:50:25 +0530
Subject: cxgb4: free mac_hlist properly

The locally maintained list for tracking hash mac table was
not freed during driver remove.

Signed-off-by: Arjun Vynipadath <arjun@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 05a46926016a..956e708c777d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2295,6 +2295,8 @@ static int cxgb_up(struct adapter *adap)
 
 static void cxgb_down(struct adapter *adapter)
 {
+	struct hash_mac_addr *entry, *tmp;
+
 	cancel_work_sync(&adapter->tid_release_task);
 	cancel_work_sync(&adapter->db_full_task);
 	cancel_work_sync(&adapter->db_drop_task);
@@ -2303,6 +2305,12 @@ static void cxgb_down(struct adapter *adapter)
 
 	t4_sge_stop(adapter);
 	t4_free_sge_resources(adapter);
+
+	list_for_each_entry_safe(entry, tmp, &adapter->mac_hlist, list) {
+		list_del(&entry->list);
+		kfree(entry);
+	}
+
 	adapter->flags &= ~FULL_INIT_DONE;
 }
 
-- 
cgit v1.2.3


From 24357e06ba511ad874d664d39475dbb01c1ca450 Mon Sep 17 00:00:00 2001
From: Arjun Vynipadath <arjun@chelsio.com>
Date: Fri, 9 Nov 2018 14:52:01 +0530
Subject: cxgb4vf: fix memleak in mac_hlist initialization

mac_hlist was initialized during adapter_up, which will be called
every time a vf device is first brought up, or every time when device
is brought up again after bringing all devices down. This means our
state of previous list is lost, causing a memleak if entries are
present in the list. To fix that, move list init to the condition
that performs initial one time adapter setup.

Signed-off-by: Arjun Vynipadath <arjun@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index ff84791a0ff8..972dc7bd721d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -722,6 +722,10 @@ static int adapter_up(struct adapter *adapter)
 
 		if (adapter->flags & USING_MSIX)
 			name_msix_vecs(adapter);
+
+		/* Initialize hash mac addr list*/
+		INIT_LIST_HEAD(&adapter->mac_hlist);
+
 		adapter->flags |= FULL_INIT_DONE;
 	}
 
@@ -747,8 +751,6 @@ static int adapter_up(struct adapter *adapter)
 	enable_rx(adapter);
 	t4vf_sge_start(adapter);
 
-	/* Initialize hash mac addr list*/
-	INIT_LIST_HEAD(&adapter->mac_hlist);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 40c4b1e9b6ca39c9b0b40b69cf3fb71e01c5d490 Mon Sep 17 00:00:00 2001
From: Arjun Vynipadath <arjun@chelsio.com>
Date: Fri, 9 Nov 2018 14:52:53 +0530
Subject: cxgb4vf: free mac_hlist properly

The locally maintained list for tracking hash mac table was
not freed during driver remove.

Signed-off-by: Arjun Vynipadath <arjun@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 972dc7bd721d..8ec503c88c06 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -3289,6 +3289,7 @@ err_disable_device:
 static void cxgb4vf_pci_remove(struct pci_dev *pdev)
 {
 	struct adapter *adapter = pci_get_drvdata(pdev);
+	struct hash_mac_addr *entry, *tmp;
 
 	/*
 	 * Tear down driver state associated with device.
@@ -3339,6 +3340,11 @@ static void cxgb4vf_pci_remove(struct pci_dev *pdev)
 		if (!is_t4(adapter->params.chip))
 			iounmap(adapter->bar2);
 		kfree(adapter->mbox_log);
+		list_for_each_entry_safe(entry, tmp, &adapter->mac_hlist,
+					 list) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
 		kfree(adapter);
 	}
 
-- 
cgit v1.2.3


From 9c6f70857785902a089e4aa06041c52eb67d2b29 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Nov 2018 22:07:46 +0800
Subject: net: hns3: add reset_hdev to reinit the hdev in VF's reset process

When doing reset, the reset handling function only need to
reinitialize hardware, it makes sense to add a function to
do that job. Also the error handling of hclgevf_init_hdev is
different when it is used in reset process.

This patch adds reset_hdev to reinitialize hardware when resetting.
Also, this patch removes the hclgevf_dev_ongoing_full_reset because
it is unused now.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 71 ++++++++++------------
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  | 14 -----
 2 files changed, 31 insertions(+), 54 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 29da4806c100..cdeb231088b8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -10,8 +10,7 @@
 
 #define HCLGEVF_NAME	"hclgevf"
 
-static int hclgevf_init_hdev(struct hclgevf_dev *hdev);
-static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev);
+static int hclgevf_reset_hdev(struct hclgevf_dev *hdev);
 static struct hnae3_ae_algo ae_algovf;
 
 static const struct pci_device_id ae_algovf_pci_tbl[] = {
@@ -209,12 +208,6 @@ static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev)
 	struct hclgevf_tqp *tqp;
 	int i;
 
-	/* if this is on going reset then we need to re-allocate the TPQs
-	 * since we cannot assume we would get same number of TPQs back from PF
-	 */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		devm_kfree(&hdev->pdev->dev, hdev->htqp);
-
 	hdev->htqp = devm_kcalloc(&hdev->pdev->dev, hdev->num_tqps,
 				  sizeof(struct hclgevf_tqp), GFP_KERNEL);
 	if (!hdev->htqp)
@@ -258,12 +251,6 @@ static int hclgevf_knic_setup(struct hclgevf_dev *hdev)
 	new_tqps = kinfo->rss_size * kinfo->num_tc;
 	kinfo->num_tqps = min(new_tqps, hdev->num_tqps);
 
-	/* if this is on going reset then we need to re-allocate the hnae queues
-	 * as well since number of TPQs from PF might have changed.
-	 */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		devm_kfree(&hdev->pdev->dev, kinfo->tqp);
-
 	kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, kinfo->num_tqps,
 				  sizeof(struct hnae3_queue *), GFP_KERNEL);
 	if (!kinfo->tqp)
@@ -1141,7 +1128,7 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev)
 	hclgevf_notify_client(hdev, HNAE3_UNINIT_CLIENT);
 
 	/* re-initialize the hclge device */
-	ret = hclgevf_init_hdev(hdev);
+	ret = hclgevf_reset_hdev(hdev);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"hclge device re-init failed, VF is disabled!\n");
@@ -1615,10 +1602,6 @@ static void hclgevf_ae_stop(struct hnae3_handle *handle)
 
 static void hclgevf_state_init(struct hclgevf_dev *hdev)
 {
-	/* if this is on going reset then skip this initialization */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		return;
-
 	/* setup tasks for the MBX */
 	INIT_WORK(&hdev->mbx_service_task, hclgevf_mailbox_service_task);
 	clear_bit(HCLGEVF_STATE_MBX_SERVICE_SCHED, &hdev->state);
@@ -1660,10 +1643,6 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 	int vectors;
 	int i;
 
-	/* if this is on going reset then skip this initialization */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		return 0;
-
 	if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B))
 		vectors = pci_alloc_irq_vectors(pdev,
 						hdev->roce_base_msix_offset + 1,
@@ -1720,10 +1699,6 @@ static int hclgevf_misc_irq_init(struct hclgevf_dev *hdev)
 {
 	int ret = 0;
 
-	/* if this is on going reset then skip this initialization */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		return 0;
-
 	hclgevf_get_misc_vector(hdev);
 
 	ret = request_irq(hdev->misc_vector.vector_irq, hclgevf_misc_irq_handle,
@@ -1853,14 +1828,6 @@ static int hclgevf_pci_init(struct hclgevf_dev *hdev)
 	struct hclgevf_hw *hw;
 	int ret;
 
-	/* check if we need to skip initialization of pci. This will happen if
-	 * device is undergoing VF reset. Otherwise, we would need to
-	 * re-initialize pci interface again i.e. when device is not going
-	 * through *any* reset or actually undergoing full reset.
-	 */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		return 0;
-
 	ret = pci_enable_device(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to enable PCI device\n");
@@ -1949,17 +1916,41 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
 	return 0;
 }
 
-static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
+static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
 	int ret;
 
-	/* check if device is on-going full reset(i.e. pcie as well) */
-	if (hclgevf_dev_ongoing_full_reset(hdev)) {
-		dev_warn(&pdev->dev, "device is going full reset\n");
-		hclgevf_uninit_hdev(hdev);
+	ret = hclgevf_cmd_init(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "cmd failed %d\n", ret);
+		return ret;
+	}
+
+	ret = hclgevf_rss_init_hw(hdev);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed(%d) to initialize RSS\n", ret);
+		return ret;
+	}
+
+	ret = hclgevf_init_vlan_config(hdev);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed(%d) to initialize VLAN config\n", ret);
+		return ret;
 	}
 
+	dev_info(&hdev->pdev->dev, "Reset done\n");
+
+	return 0;
+}
+
+static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	int ret;
+
 	ret = hclgevf_pci_init(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "PCI initialization failed\n");
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 0ea4c9b3ae0a..29ae4b6281c6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -196,20 +196,6 @@ struct hclgevf_dev {
 	u32 flag;
 };
 
-static inline bool hclgevf_dev_ongoing_reset(struct hclgevf_dev *hdev)
-{
-	return (hdev &&
-		(test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) &&
-		(hdev->reset_level == HNAE3_VF_RESET));
-}
-
-static inline bool hclgevf_dev_ongoing_full_reset(struct hclgevf_dev *hdev)
-{
-	return (hdev &&
-		(test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) &&
-		(hdev->reset_level == HNAE3_VF_FULL_RESET));
-}
-
 int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, u16 code, u16 subcode,
 			 const u8 *msg_data, u8 msg_len, bool need_resp,
 			 u8 *resp_data, u16 resp_len);
-- 
cgit v1.2.3


From dea846e85aaf77a681e6f0f90df7aaaa467e61a5 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Nov 2018 22:07:47 +0800
Subject: net: hns3: adjust VF's reset process

Currently when VF need to reset itself, it will send a cmd to PF,
after receiving the VF reset requset, PF sends a cmd to inform
VF to enter the reset process and send a cmd to firmware to do the
actual reset for the VF, it is possible that firmware has resetted
the VF, but VF has not entered the reset process, which may cause
IO not stopped problem when firmware is resetting VF.

This patch fixes it by adjusting the VF reset process, when VF
need to reset itself, it will enter the reset process first, and
it will tell the PF to send cmd to firmware to reset itself.

Add member reset_pending to struct hclgevf_dev, which indicates that
there is reset event need to be processed by the VF's reset task, and
the VF's reset task chooses the highest-level one and clears other
low-level one when it processes reset_pending.

hclge_inform_reset_assert_to_vf function is unused now, but it will
be used to support the PF reset with VF working, so declare it in
the header file.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  1 +
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    |  3 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  1 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 22 ++----
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 80 ++++++++++++++--------
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  2 +
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c   |  2 +-
 7 files changed, 63 insertions(+), 48 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 5b3b10479cd4..510dd083e43f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -124,6 +124,7 @@ enum hnae3_reset_notify_type {
 
 enum hnae3_reset_type {
 	HNAE3_VF_RESET,
+	HNAE3_VF_FUNC_RESET,
 	HNAE3_VF_FULL_RESET,
 	HNAE3_FUNC_RESET,
 	HNAE3_CORE_RESET,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index cfd6a7109691..5a38226c4c1f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -593,7 +593,8 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 
 static inline bool hns3_dev_ongoing_func_reset(struct hnae3_ae_dev *ae_dev)
 {
-	return (ae_dev && (ae_dev->reset_type == HNAE3_FUNC_RESET));
+	return (ae_dev && (ae_dev->reset_type == HNAE3_FUNC_RESET ||
+			   ae_dev->reset_type == HNAE3_VF_FUNC_RESET));
 }
 
 #define hns3_read_dev(a, reg) \
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 36f341368683..6df4cfe6af35 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -775,6 +775,7 @@ static inline int hclge_get_queue_id(struct hnae3_queue *queue)
 	return tqp->index;
 }
 
+int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport);
 int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex);
 int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
 			  u16 vlan_id, bool is_kill);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index f890022938d9..013bc7a8c798 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -79,7 +79,7 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len,
 	return status;
 }
 
-static int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
+int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
 {
 	u8 msg_data[2];
 	u8 dest_vfid;
@@ -363,24 +363,10 @@ static void hclge_reset_vf(struct hclge_vport *vport,
 	int ret;
 
 	dev_warn(&hdev->pdev->dev, "PF received VF reset request from VF %d!",
-		 mbx_req->mbx_src_vfid);
-
-	/* Acknowledge VF that PF is now about to assert the reset for the VF.
-	 * On receiving this message VF will get into pending state and will
-	 * start polling for the hardware reset completion status.
-	 */
-	ret = hclge_inform_reset_assert_to_vf(vport);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"PF fail(%d) to inform VF(%d)of reset, reset failed!\n",
-			ret, vport->vport_id);
-		return;
-	}
+		 vport->vport_id);
 
-	dev_warn(&hdev->pdev->dev, "PF is now resetting VF %d.\n",
-		 mbx_req->mbx_src_vfid);
-	/* reset this virtual function */
-	hclge_func_reset_cmd(hdev, mbx_req->mbx_src_vfid);
+	ret = hclge_func_reset_cmd(hdev, vport->vport_id);
+	hclge_gen_resp_to_vf(vport, mbx_req, ret, NULL, 0);
 }
 
 static bool hclge_cmd_crq_empty(struct hclge_hw *hw)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index cdeb231088b8..7a1462a41e81 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -855,6 +855,9 @@ static int hclgevf_unmap_ring_from_vector(
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	int ret, vector_id;
 
+	if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state))
+		return 0;
+
 	vector_id = hclgevf_get_vector_index(hdev, vector);
 	if (vector_id < 0) {
 		dev_err(&handle->pdev->dev,
@@ -1141,10 +1144,34 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev)
 	return 0;
 }
 
+static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev)
+{
+	int ret = 0;
+
+	switch (hdev->reset_type) {
+	case HNAE3_VF_FUNC_RESET:
+		ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_RESET, 0, NULL,
+					   0, true, NULL, sizeof(u8));
+		break;
+	default:
+		break;
+	}
+
+	dev_info(&hdev->pdev->dev, "prepare reset(%d) wait done, ret:%d\n",
+		 hdev->reset_type, ret);
+
+	return ret;
+}
+
 static int hclgevf_reset(struct hclgevf_dev *hdev)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
 	int ret;
 
+	/* Initialize ae_dev reset status as well, in case enet layer wants to
+	 * know if device is undergoing reset
+	 */
+	ae_dev->reset_type = hdev->reset_type;
 	hdev->reset_count++;
 	rtnl_lock();
 
@@ -1153,6 +1180,8 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
 
 	rtnl_unlock();
 
+	hclgevf_reset_prepare_wait(hdev);
+
 	/* check if VF could successfully fetch the hardware reset completion
 	 * status from the hardware
 	 */
@@ -1186,28 +1215,19 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
 	return ret;
 }
 
-static int hclgevf_do_reset(struct hclgevf_dev *hdev)
-{
-	int status;
-	u8 respmsg;
-
-	status = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_RESET, 0, NULL,
-				      0, false, &respmsg, sizeof(u8));
-	if (status)
-		dev_err(&hdev->pdev->dev,
-			"VF reset request to PF failed(=%d)\n", status);
-
-	return status;
-}
-
 static enum hnae3_reset_type hclgevf_get_reset_level(struct hclgevf_dev *hdev,
 						     unsigned long *addr)
 {
 	enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
 
-	if (test_bit(HNAE3_VF_RESET, addr)) {
-		rst_level = HNAE3_VF_RESET;
-		clear_bit(HNAE3_VF_RESET, addr);
+	/* return the highest priority reset level amongst all */
+	if (test_bit(HNAE3_VF_FULL_RESET, addr)) {
+		rst_level = HNAE3_VF_FULL_RESET;
+		clear_bit(HNAE3_VF_FULL_RESET, addr);
+		clear_bit(HNAE3_VF_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_VF_FUNC_RESET, addr)) {
+		rst_level = HNAE3_VF_FUNC_RESET;
+		clear_bit(HNAE3_VF_FUNC_RESET, addr);
 	}
 
 	return rst_level;
@@ -1225,7 +1245,7 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
 			hclgevf_get_reset_level(hdev,
 						&hdev->default_reset_request);
 	else
-		hdev->reset_level = HNAE3_VF_RESET;
+		hdev->reset_level = HNAE3_VF_FUNC_RESET;
 
 	/* reset of this VF requested */
 	set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state);
@@ -1328,9 +1348,15 @@ static void hclgevf_reset_service_task(struct work_struct *work)
 		 */
 		hdev->reset_attempts = 0;
 
-		ret = hclgevf_reset(hdev);
-		if (ret)
-			dev_err(&hdev->pdev->dev, "VF stack reset failed.\n");
+		hdev->last_reset_time = jiffies;
+		while ((hdev->reset_type =
+			hclgevf_get_reset_level(hdev, &hdev->reset_pending))
+		       != HNAE3_NONE_RESET) {
+			ret = hclgevf_reset(hdev);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"VF stack reset failed %d.\n", ret);
+		}
 	} else if (test_and_clear_bit(HCLGEVF_RESET_REQUESTED,
 				      &hdev->reset_state)) {
 		/* we could be here when either of below happens:
@@ -1359,19 +1385,17 @@ static void hclgevf_reset_service_task(struct work_struct *work)
 		 */
 		if (hdev->reset_attempts > 3) {
 			/* prepare for full reset of stack + pcie interface */
-			hdev->reset_level = HNAE3_VF_FULL_RESET;
+			set_bit(HNAE3_VF_FULL_RESET, &hdev->reset_pending);
 
 			/* "defer" schedule the reset task again */
 			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		} else {
 			hdev->reset_attempts++;
 
-			/* request PF for resetting this VF via mailbox */
-			ret = hclgevf_do_reset(hdev);
-			if (ret)
-				dev_warn(&hdev->pdev->dev,
-					 "VF rst fail, stack will call\n");
+			set_bit(hdev->reset_level, &hdev->reset_pending);
+			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		}
+		hclgevf_reset_task_schedule(hdev);
 	}
 
 	clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
@@ -1982,7 +2006,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 	}
 
 	hclgevf_state_init(hdev);
-	hdev->reset_level = HNAE3_VF_RESET;
+	hdev->reset_level = HNAE3_VF_FUNC_RESET;
 
 	ret = hclgevf_misc_irq_init(hdev);
 	if (ret) {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 29ae4b6281c6..e6abc4e19e6f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -148,6 +148,8 @@ struct hclgevf_dev {
 	unsigned long default_reset_request;
 	unsigned long last_reset_time;
 	enum hnae3_reset_type reset_level;
+	unsigned long reset_pending;
+	enum hnae3_reset_type reset_type;
 
 #define HCLGEVF_RESET_REQUESTED		0
 #define HCLGEVF_RESET_PENDING		1
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index 558e3b838676..d3519f7e9b07 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -267,7 +267,7 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 			 * has been completely reset. After this stack should
 			 * eventually be re-initialized.
 			 */
-			hdev->reset_level = HNAE3_VF_RESET;
+			set_bit(HNAE3_VF_FULL_RESET, &hdev->reset_pending);
 			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 			hclgevf_reset_task_schedule(hdev);
 
-- 
cgit v1.2.3


From aa5c4f175be66696f73eb9f4e18028c6aa2ce652 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Nov 2018 22:07:48 +0800
Subject: net: hns3: add reset handling for VF when doing PF reset

When PF performs a function reset, the hardware will reset both PF
and all the VF belong to this PF. Hence, both PF's driver and VF's
driver need to perform corresponding reset operations.

Before PF driver asserting function reset to hardware, it firstly
set up VF's hardware reset status, and inform the VF driver with
HNAE3_VF_PF_FUNC_RESET, then VF driver sets this reset type to
reset_pending and shechule reset task to stop IO and waits for the
hardware reset status to clear. When PF driver has reinitialized the
hardware and is ready to process mailbox from VF, PF driver clears
VF's hardware reset status for VF to continue its reset process.

Also, this patch uses readl_poll_timeout to simplify the hardware reset
status waitting.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h    |  6 ++
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  1 +
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    |  3 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 91 ++++++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  1 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 11 ++-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 39 ++++++----
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  | 10 ++-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c   |  4 +-
 9 files changed, 146 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index 038326cfda93..3bb313cdbc9f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -85,6 +85,12 @@ struct hclge_mbx_pf_to_vf_cmd {
 	u16 msg[8];
 };
 
+struct hclge_vf_rst_cmd {
+	u8 dest_vfid;
+	u8 vf_rst;
+	u8 rsv[22];
+};
+
 /* used by VF to store the received Async responses from PF */
 struct hclgevf_mbx_arq_ring {
 #define HCLGE_MBX_MAX_ARQ_MSG_SIZE	8
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 510dd083e43f..f15f5958decf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -125,6 +125,7 @@ enum hnae3_reset_notify_type {
 enum hnae3_reset_type {
 	HNAE3_VF_RESET,
 	HNAE3_VF_FUNC_RESET,
+	HNAE3_VF_PF_FUNC_RESET,
 	HNAE3_VF_FULL_RESET,
 	HNAE3_FUNC_RESET,
 	HNAE3_CORE_RESET,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 5a38226c4c1f..bd6ee5c8516b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -594,7 +594,8 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 static inline bool hns3_dev_ongoing_func_reset(struct hnae3_ae_dev *ae_dev)
 {
 	return (ae_dev && (ae_dev->reset_type == HNAE3_FUNC_RESET ||
-			   ae_dev->reset_type == HNAE3_VF_FUNC_RESET));
+			   ae_dev->reset_type == HNAE3_VF_FUNC_RESET ||
+			   ae_dev->reset_type == HNAE3_VF_PF_FUNC_RESET));
 }
 
 #define hns3_read_dev(a, reg) \
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 77980e54ad09..ba6ea6b804fb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2392,6 +2392,55 @@ static int hclge_reset_wait(struct hclge_dev *hdev)
 	return 0;
 }
 
+static int hclge_set_vf_rst(struct hclge_dev *hdev, int func_id, bool reset)
+{
+	struct hclge_vf_rst_cmd *req;
+	struct hclge_desc desc;
+
+	req = (struct hclge_vf_rst_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_GBL_RST_STATUS, false);
+	req->dest_vfid = func_id;
+
+	if (reset)
+		req->vf_rst = 0x1;
+
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
+int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset)
+{
+	int i;
+
+	for (i = hdev->num_vmdq_vport + 1; i < hdev->num_alloc_vport; i++) {
+		struct hclge_vport *vport = &hdev->vport[i];
+		int ret;
+
+		/* Send cmd to set/clear VF's FUNC_RST_ING */
+		ret = hclge_set_vf_rst(hdev, vport->vport_id, reset);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"set vf(%d) rst failded %d!\n",
+				vport->vport_id, ret);
+			return ret;
+		}
+
+		if (!reset)
+			continue;
+
+		/* Inform VF to process the reset.
+		 * hclge_inform_reset_assert_to_vf may fail if VF
+		 * driver is not loaded.
+		 */
+		ret = hclge_inform_reset_assert_to_vf(vport);
+		if (ret)
+			dev_warn(&hdev->pdev->dev,
+				 "inform reset to vf(%d) failded %d!\n",
+				 vport->vport_id, ret);
+	}
+
+	return 0;
+}
+
 int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id)
 {
 	struct hclge_desc desc;
@@ -2495,12 +2544,31 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
 	hclge_enable_vector(&hdev->misc_vector, true);
 }
 
+static int hclge_reset_prepare_down(struct hclge_dev *hdev)
+{
+	int ret = 0;
+
+	switch (hdev->reset_type) {
+	case HNAE3_FUNC_RESET:
+		ret = hclge_set_all_vf_rst(hdev, true);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 {
 	int ret = 0;
 
 	switch (hdev->reset_type) {
 	case HNAE3_FUNC_RESET:
+		/* There is no mechanism for PF to know if VF has stopped IO
+		 * for now, just wait 100 ms for VF to stop IO
+		 */
+		msleep(100);
 		ret = hclge_func_reset_cmd(hdev, 0);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
@@ -2562,6 +2630,21 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev, bool is_timeout)
 	return false;
 }
 
+static int hclge_reset_prepare_up(struct hclge_dev *hdev)
+{
+	int ret = 0;
+
+	switch (hdev->reset_type) {
+	case HNAE3_FUNC_RESET:
+		ret = hclge_set_all_vf_rst(hdev, false);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 static void hclge_reset(struct hclge_dev *hdev)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
@@ -2579,6 +2662,10 @@ static void hclge_reset(struct hclge_dev *hdev)
 	if (ret)
 		goto err_reset;
 
+	ret = hclge_reset_prepare_down(hdev);
+	if (ret)
+		goto err_reset;
+
 	rtnl_lock();
 	ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
 	if (ret)
@@ -2614,6 +2701,10 @@ static void hclge_reset(struct hclge_dev *hdev)
 
 	hclge_clear_reset_cause(hdev);
 
+	ret = hclge_reset_prepare_up(hdev);
+	if (ret)
+		goto err_reset_lock;
+
 	ret = hclge_notify_client(hdev, HNAE3_UP_CLIENT);
 	if (ret)
 		goto err_reset_lock;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 6df4cfe6af35..8ab974c4fc4b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -785,6 +785,7 @@ int hclge_buffer_alloc(struct hclge_dev *hdev);
 int hclge_rss_init_hw(struct hclge_dev *hdev);
 void hclge_rss_indir_init_cfg(struct hclge_dev *hdev);
 
+int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport);
 void hclge_mbx_handler(struct hclge_dev *hdev);
 int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id);
 void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 013bc7a8c798..f15b807b977e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -81,13 +81,22 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len,
 
 int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
 {
+	struct hclge_dev *hdev = vport->back;
+	enum hnae3_reset_type reset_type;
 	u8 msg_data[2];
 	u8 dest_vfid;
 
 	dest_vfid = (u8)vport->vport_id;
 
+	if (hdev->reset_type == HNAE3_FUNC_RESET)
+		reset_type = HNAE3_VF_PF_FUNC_RESET;
+	else
+		return -EINVAL;
+
+	memcpy(&msg_data[0], &reset_type, sizeof(u16));
+
 	/* send this requested info to VF */
-	return hclge_send_mbx_msg(vport, msg_data, sizeof(u8),
+	return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data),
 				  HCLGE_MBX_ASSERTING_RESET, dest_vfid);
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 7a1462a41e81..940551746bea 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2,6 +2,7 @@
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/etherdevice.h>
+#include <linux/iopoll.h>
 #include <net/rtnetlink.h>
 #include "hclgevf_cmd.h"
 #include "hclgevf_main.h"
@@ -1094,24 +1095,28 @@ static int hclgevf_notify_client(struct hclgevf_dev *hdev,
 
 static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
 {
-#define HCLGEVF_RESET_WAIT_MS	500
-#define HCLGEVF_RESET_WAIT_CNT	20
-	u32 val, cnt = 0;
+#define HCLGEVF_RESET_WAIT_US	20000
+#define HCLGEVF_RESET_WAIT_CNT	2000
+#define HCLGEVF_RESET_WAIT_TIMEOUT_US	\
+	(HCLGEVF_RESET_WAIT_US * HCLGEVF_RESET_WAIT_CNT)
+
+	u32 val;
+	int ret;
 
 	/* wait to check the hardware reset completion status */
-	val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
-	while (hnae3_get_bit(val, HCLGEVF_FUN_RST_ING_B) &&
-	       (cnt < HCLGEVF_RESET_WAIT_CNT)) {
-		msleep(HCLGEVF_RESET_WAIT_MS);
-		val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
-		cnt++;
-	}
+	val = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
+	dev_info(&hdev->pdev->dev, "checking vf resetting status: %x\n", val);
+
+	ret = readl_poll_timeout(hdev->hw.io_base + HCLGEVF_RST_ING, val,
+				 !(val & HCLGEVF_RST_ING_BITS),
+				 HCLGEVF_RESET_WAIT_US,
+				 HCLGEVF_RESET_WAIT_TIMEOUT_US);
 
 	/* hardware completion status should be available by this time */
-	if (cnt >= HCLGEVF_RESET_WAIT_CNT) {
-		dev_warn(&hdev->pdev->dev,
-			 "could'nt get reset done status from h/w, timeout!\n");
-		return -EBUSY;
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"could'nt get reset done status from h/w, timeout!\n");
+		return ret;
 	}
 
 	/* we will wait a bit more to let reset of the stack to complete. This
@@ -1225,6 +1230,10 @@ static enum hnae3_reset_type hclgevf_get_reset_level(struct hclgevf_dev *hdev,
 		rst_level = HNAE3_VF_FULL_RESET;
 		clear_bit(HNAE3_VF_FULL_RESET, addr);
 		clear_bit(HNAE3_VF_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_VF_PF_FUNC_RESET, addr)) {
+		rst_level = HNAE3_VF_PF_FUNC_RESET;
+		clear_bit(HNAE3_VF_PF_FUNC_RESET, addr);
+		clear_bit(HNAE3_VF_FUNC_RESET, addr);
 	} else if (test_bit(HNAE3_VF_FUNC_RESET, addr)) {
 		rst_level = HNAE3_VF_FUNC_RESET;
 		clear_bit(HNAE3_VF_FUNC_RESET, addr);
@@ -2178,7 +2187,7 @@ static bool hclgevf_get_hw_reset_stat(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 
-	return !!hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
+	return !!hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
 }
 
 static bool hclgevf_ae_dev_resetting(struct hnae3_handle *handle)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index e6abc4e19e6f..2735414cc9ce 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -34,8 +34,14 @@
 
 #define HCLGEVF_TQP_RESET_TRY_TIMES	10
 /* Reset related Registers */
-#define HCLGEVF_FUN_RST_ING		0x20C00
-#define HCLGEVF_FUN_RST_ING_B		0
+#define HCLGEVF_RST_ING			0x20C00
+#define HCLGEVF_FUN_RST_ING_BIT		BIT(0)
+#define HCLGEVF_GLOBAL_RST_ING_BIT	BIT(5)
+#define HCLGEVF_CORE_RST_ING_BIT	BIT(6)
+#define HCLGEVF_IMP_RST_ING_BIT		BIT(7)
+#define HCLGEVF_RST_ING_BITS \
+	(HCLGEVF_FUN_RST_ING_BIT | HCLGEVF_GLOBAL_RST_ING_BIT | \
+	 HCLGEVF_CORE_RST_ING_BIT | HCLGEVF_IMP_RST_ING_BIT)
 
 #define HCLGEVF_RSS_IND_TBL_SIZE		512
 #define HCLGEVF_RSS_SET_BITMAP_MSK	0xffff
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index d3519f7e9b07..01a028aa71f7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -233,6 +233,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 
 void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 {
+	enum hnae3_reset_type reset_type;
 	u16 link_status;
 	u16 *msg_q;
 	u8 duplex;
@@ -267,7 +268,8 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 			 * has been completely reset. After this stack should
 			 * eventually be re-initialized.
 			 */
-			set_bit(HNAE3_VF_FULL_RESET, &hdev->reset_pending);
+			reset_type = le16_to_cpu(msg_q[1]);
+			set_bit(reset_type, &hdev->reset_pending);
 			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 			hclgevf_reset_task_schedule(hdev);
 
-- 
cgit v1.2.3


From b90fcc5bd904fe1ec1b4b0a5ba8299cd2625a16c Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Nov 2018 22:07:49 +0800
Subject: net: hns3: add reset handling for VF when doing Core/Global/IMP reset

When a Core/Global/IMP reset occurs, the hardware sets the reset status
register of all PF/VF and reports a reset interrupt to all PF/VF and
firmware.

When receiving the reset interrupt:
1. The firmware will wait for 100 ms before resetting the hardware and
   clear the reset status register of all PF when hardware reset is done.
2. The PF/VF driver needs to down the netdev within 100 ms and then wait
   for hardware reset to finish.
3. After firmware clearing the reset status register of all PF, the PF
   driver reinitializes the hardware and clear the reset status register
   of it's VF.
4. After PF driver clearing the reset status register of VF, the VF driver
   reinitializes the hardware.

This patch mainly add handling for the step 4.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 50 ++++++++++++++++------
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  8 ++++
 2 files changed, 46 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 940551746bea..fe97cc7f621b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1226,7 +1226,12 @@ static enum hnae3_reset_type hclgevf_get_reset_level(struct hclgevf_dev *hdev,
 	enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
 
 	/* return the highest priority reset level amongst all */
-	if (test_bit(HNAE3_VF_FULL_RESET, addr)) {
+	if (test_bit(HNAE3_VF_RESET, addr)) {
+		rst_level = HNAE3_VF_RESET;
+		clear_bit(HNAE3_VF_RESET, addr);
+		clear_bit(HNAE3_VF_PF_FUNC_RESET, addr);
+		clear_bit(HNAE3_VF_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_VF_FULL_RESET, addr)) {
 		rst_level = HNAE3_VF_FULL_RESET;
 		clear_bit(HNAE3_VF_FULL_RESET, addr);
 		clear_bit(HNAE3_VF_FUNC_RESET, addr);
@@ -1447,24 +1452,36 @@ static void hclgevf_clear_event_cause(struct hclgevf_dev *hdev, u32 regclr)
 	hclgevf_write_dev(&hdev->hw, HCLGEVF_VECTOR0_CMDQ_SRC_REG, regclr);
 }
 
-static bool hclgevf_check_event_cause(struct hclgevf_dev *hdev, u32 *clearval)
+static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
+						      u32 *clearval)
 {
-	u32 cmdq_src_reg;
+	u32 cmdq_src_reg, rst_ing_reg;
 
 	/* fetch the events from their corresponding regs */
 	cmdq_src_reg = hclgevf_read_dev(&hdev->hw,
 					HCLGEVF_VECTOR0_CMDQ_SRC_REG);
 
+	if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_src_reg) {
+		rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
+		dev_info(&hdev->pdev->dev,
+			 "receive reset interrupt 0x%x!\n", rst_ing_reg);
+		set_bit(HNAE3_VF_RESET, &hdev->reset_pending);
+		set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
+		cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RST_INT_B);
+		*clearval = cmdq_src_reg;
+		return HCLGEVF_VECTOR0_EVENT_RST;
+	}
+
 	/* check for vector0 mailbox(=CMDQ RX) event source */
 	if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) {
 		cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B);
 		*clearval = cmdq_src_reg;
-		return true;
+		return HCLGEVF_VECTOR0_EVENT_MBX;
 	}
 
 	dev_dbg(&hdev->pdev->dev, "vector 0 interrupt from unknown source\n");
 
-	return false;
+	return HCLGEVF_VECTOR0_EVENT_OTHER;
 }
 
 static void hclgevf_enable_vector(struct hclgevf_misc_vector *vector, bool en)
@@ -1474,19 +1491,28 @@ static void hclgevf_enable_vector(struct hclgevf_misc_vector *vector, bool en)
 
 static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data)
 {
+	enum hclgevf_evt_cause event_cause;
 	struct hclgevf_dev *hdev = data;
 	u32 clearval;
 
 	hclgevf_enable_vector(&hdev->misc_vector, false);
-	if (!hclgevf_check_event_cause(hdev, &clearval))
-		goto skip_sched;
-
-	hclgevf_mbx_handler(hdev);
+	event_cause = hclgevf_check_evt_cause(hdev, &clearval);
 
-	hclgevf_clear_event_cause(hdev, clearval);
+	switch (event_cause) {
+	case HCLGEVF_VECTOR0_EVENT_RST:
+		hclgevf_reset_task_schedule(hdev);
+		break;
+	case HCLGEVF_VECTOR0_EVENT_MBX:
+		hclgevf_mbx_handler(hdev);
+		break;
+	default:
+		break;
+	}
 
-skip_sched:
-	hclgevf_enable_vector(&hdev->misc_vector, true);
+	if (event_cause != HCLGEVF_VECTOR0_EVENT_OTHER) {
+		hclgevf_clear_event_cause(hdev, clearval);
+		hclgevf_enable_vector(&hdev->misc_vector, true);
+	}
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 2735414cc9ce..e37897df6afc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -31,6 +31,8 @@
 #define HCLGEVF_VECTOR0_CMDQ_SRC_REG	0x27100
 /* CMDQ register bits for RX event(=MBX event) */
 #define HCLGEVF_VECTOR0_RX_CMDQ_INT_B	1
+/* RST register bits for RESET event */
+#define HCLGEVF_VECTOR0_RST_INT_B	2
 
 #define HCLGEVF_TQP_RESET_TRY_TIMES	10
 /* Reset related Registers */
@@ -60,6 +62,12 @@
 #define HCLGEVF_S_IP_BIT		BIT(3)
 #define HCLGEVF_V_TAG_BIT		BIT(4)
 
+enum hclgevf_evt_cause {
+	HCLGEVF_VECTOR0_EVENT_RST,
+	HCLGEVF_VECTOR0_EVENT_MBX,
+	HCLGEVF_VECTOR0_EVENT_OTHER,
+};
+
 /* states of hclgevf device & tasks */
 enum hclgevf_states {
 	/* device states */
-- 
cgit v1.2.3


From ef5f8e507ec9c226ef961c21ede99bab9fd313d4 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Nov 2018 22:07:50 +0800
Subject: net: hns3: stop handling command queue while resetting VF

According to hardware's description, after the reset occurs, the driver
needs to re-initialize the command queue before sending and receiving
any commands. Therefore, the VF's driver needs to identify the command
queue needs to re-initialize with HCLGEVF_STATE_CMD_DISABLE, and does
not allow sending or receiving commands before the re-initialization.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c  | 13 ++++++++++++-
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c |  3 +++
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h |  6 ++++++
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c  | 14 ++++++++++++++
 4 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index b917acf71ee6..d5765c8cf3a3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -189,7 +189,8 @@ int hclgevf_cmd_send(struct hclgevf_hw *hw, struct hclgevf_desc *desc, int num)
 
 	spin_lock_bh(&hw->cmq.csq.lock);
 
-	if (num > hclgevf_ring_space(&hw->cmq.csq)) {
+	if (num > hclgevf_ring_space(&hw->cmq.csq) ||
+	    test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state)) {
 		spin_unlock_bh(&hw->cmq.csq.lock);
 		return -EBUSY;
 	}
@@ -338,6 +339,16 @@ int hclgevf_cmd_init(struct hclgevf_dev *hdev)
 	spin_unlock_bh(&hdev->hw.cmq.crq.lock);
 	spin_unlock_bh(&hdev->hw.cmq.csq.lock);
 
+	clear_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+
+	/* Check if there is new reset pending, because the higher level
+	 * reset may happen when lower level reset is being processed.
+	 */
+	if (hclgevf_is_reset_pending(hdev)) {
+		set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+		return -EBUSY;
+	}
+
 	/* get firmware version */
 	ret = hclgevf_cmd_query_firmware_version(&hdev->hw, &version);
 	if (ret) {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index fe97cc7f621b..5da9053ebf4b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1162,6 +1162,8 @@ static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev)
 		break;
 	}
 
+	set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+
 	dev_info(&hdev->pdev->dev, "prepare reset(%d) wait done, ret:%d\n",
 		 hdev->reset_type, ret);
 
@@ -1467,6 +1469,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 			 "receive reset interrupt 0x%x!\n", rst_ing_reg);
 		set_bit(HNAE3_VF_RESET, &hdev->reset_pending);
 		set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
+		set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
 		cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RST_INT_B);
 		*clearval = cmdq_src_reg;
 		return HCLGEVF_VECTOR0_EVENT_RST;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index e37897df6afc..ffe3d495376c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -79,6 +79,7 @@ enum hclgevf_states {
 	HCLGEVF_STATE_RST_HANDLING,
 	HCLGEVF_STATE_MBX_SERVICE_SCHED,
 	HCLGEVF_STATE_MBX_HANDLING,
+	HCLGEVF_STATE_CMD_DISABLE,
 };
 
 #define HCLGEVF_MPF_ENBALE 1
@@ -212,6 +213,11 @@ struct hclgevf_dev {
 	u32 flag;
 };
 
+static inline bool hclgevf_is_reset_pending(struct hclgevf_dev *hdev)
+{
+	return !!hdev->reset_pending;
+}
+
 int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, u16 code, u16 subcode,
 			 const u8 *msg_data, u8 msg_len, bool need_resp,
 			 u8 *resp_data, u16 resp_len);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index 01a028aa71f7..ef9c8e6eca28 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -40,6 +40,9 @@ static int hclgevf_get_mbx_resp(struct hclgevf_dev *hdev, u16 code0, u16 code1,
 	}
 
 	while ((!hdev->mbx_resp.received_resp) && (i < HCLGEVF_MAX_TRY_TIMES)) {
+		if (test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state))
+			return -EIO;
+
 		udelay(HCLGEVF_SLEEP_USCOEND);
 		i++;
 	}
@@ -148,6 +151,11 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 	crq = &hdev->hw.cmq.crq;
 
 	while (!hclgevf_cmd_crq_empty(&hdev->hw)) {
+		if (test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state)) {
+			dev_info(&hdev->pdev->dev, "vf crq need init\n");
+			return;
+		}
+
 		desc = &crq->desc[crq->next_to_use];
 		req = (struct hclge_mbx_pf_to_vf_cmd *)desc->data;
 
@@ -249,6 +257,12 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 
 	/* process all the async queue messages */
 	while (tail != hdev->arq.head) {
+		if (test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state)) {
+			dev_info(&hdev->pdev->dev,
+				 "vf crq need init in async\n");
+			return;
+		}
+
 		msg_q = hdev->arq.msg_q[hdev->arq.head];
 
 		switch (msg_q[0]) {
-- 
cgit v1.2.3


From 6a5f6fa382f3f4d5f519a9a52ed63afb4841fc0c Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Nov 2018 22:07:51 +0800
Subject: net: hns3: add error handler for hclgevf_reset()

Since hclgevf_reset() may fail for some reasons, so it needs an error
handler to deal with it. When VF reset failed, VF can only be restored
by a higher level reset asserted by PF. So, it needs to reinitialize
its command queue, then it can respond to higher level reset.

Also, this patch adds error logging in the hclgevf_notify_client().

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 51 ++++++++++++++++------
 1 file changed, 37 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 5da9053ebf4b..4dfac6c0cece 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1086,11 +1086,17 @@ static int hclgevf_notify_client(struct hclgevf_dev *hdev,
 {
 	struct hnae3_client *client = hdev->nic_client;
 	struct hnae3_handle *handle = &hdev->nic;
+	int ret;
 
 	if (!client->ops->reset_notify)
 		return -EOPNOTSUPP;
 
-	return client->ops->reset_notify(handle, type);
+	ret = client->ops->reset_notify(handle, type);
+	if (ret)
+		dev_err(&hdev->pdev->dev, "notify nic client failed %d(%d)\n",
+			type, ret);
+
+	return ret;
 }
 
 static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
@@ -1133,7 +1139,9 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev)
 	int ret;
 
 	/* uninitialize the nic client */
-	hclgevf_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+	ret = hclgevf_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		return ret;
 
 	/* re-initialize the hclge device */
 	ret = hclgevf_reset_hdev(hdev);
@@ -1144,7 +1152,9 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev)
 	}
 
 	/* bring up the nic client again */
-	hclgevf_notify_client(hdev, HNAE3_INIT_CLIENT);
+	ret = hclgevf_notify_client(hdev, HNAE3_INIT_CLIENT);
+	if (ret)
+		return ret;
 
 	return 0;
 }
@@ -1183,11 +1193,15 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
 	rtnl_lock();
 
 	/* bring down the nic to stop any ongoing TX/RX */
-	hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT);
+	ret = hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT);
+	if (ret)
+		goto err_reset_lock;
 
 	rtnl_unlock();
 
-	hclgevf_reset_prepare_wait(hdev);
+	ret = hclgevf_reset_prepare_wait(hdev);
+	if (ret)
+		goto err_reset;
 
 	/* check if VF could successfully fetch the hardware reset completion
 	 * status from the hardware
@@ -1198,27 +1212,36 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
 		dev_err(&hdev->pdev->dev,
 			"VF failed(=%d) to fetch H/W reset completion status\n",
 			ret);
-
-		dev_warn(&hdev->pdev->dev, "VF reset failed, disabling VF!\n");
-		rtnl_lock();
-		hclgevf_notify_client(hdev, HNAE3_UNINIT_CLIENT);
-
-		rtnl_unlock();
-		return ret;
+		goto err_reset;
 	}
 
 	rtnl_lock();
 
 	/* now, re-initialize the nic client and ae device*/
 	ret = hclgevf_reset_stack(hdev);
-	if (ret)
+	if (ret) {
 		dev_err(&hdev->pdev->dev, "failed to reset VF stack\n");
+		goto err_reset_lock;
+	}
 
 	/* bring up the nic to enable TX/RX again */
-	hclgevf_notify_client(hdev, HNAE3_UP_CLIENT);
+	ret = hclgevf_notify_client(hdev, HNAE3_UP_CLIENT);
+	if (ret)
+		goto err_reset_lock;
 
 	rtnl_unlock();
 
+	return ret;
+err_reset_lock:
+	rtnl_unlock();
+err_reset:
+	/* When VF reset failed, only the higher level reset asserted by PF
+	 * can restore it, so re-initialize the command queue to receive
+	 * this higher reset event.
+	 */
+	hclgevf_cmd_init(hdev);
+	dev_err(&hdev->pdev->dev, "failed to reset VF\n");
+
 	return ret;
 }
 
-- 
cgit v1.2.3


From ff0699e04b977b61c5505cdfa5a386b9bceb3e6d Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Nov 2018 22:07:52 +0800
Subject: net: hns3: stop napi polling when HNS3_NIC_STATE_DOWN is set

When calling napi_disable during reset down process, if NAPIF_STATE_MISSED
is set, napi_complete will call __napi_schedule to do the polling again.
So this patch uses HNS3_NIC_STATE_DOWN to ensure the polling is not
scheduled again.

Also, when napi_complete returns true, it means polling is scheduled
again, it is not neccssary to enable the interrupt.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 183fd8344b80..499032bba705 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -415,9 +415,6 @@ static void hns3_nic_net_down(struct net_device *netdev)
 	const struct hnae3_ae_ops *ops;
 	int i;
 
-	if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state))
-		return;
-
 	/* disable vectors */
 	for (i = 0; i < priv->vector_num; i++)
 		hns3_vector_disable(&priv->tqp_vector[i]);
@@ -439,6 +436,11 @@ static void hns3_nic_net_down(struct net_device *netdev)
 
 static int hns3_nic_net_stop(struct net_device *netdev)
 {
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+	if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state))
+		return 0;
+
 	netif_tx_stop_all_queues(netdev);
 	netif_carrier_off(netdev);
 
@@ -2699,6 +2701,7 @@ static void hns3_update_new_int_gl(struct hns3_enet_tqp_vector *tqp_vector)
 
 static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 {
+	struct hns3_nic_priv *priv = netdev_priv(napi->dev);
 	struct hns3_enet_ring *ring;
 	int rx_pkt_total = 0;
 
@@ -2707,6 +2710,11 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 	bool clean_complete = true;
 	int rx_budget;
 
+	if (unlikely(test_bit(HNS3_NIC_STATE_DOWN, &priv->state))) {
+		napi_complete(napi);
+		return 0;
+	}
+
 	/* Since the actual Tx work is minimal, we can give the Tx a larger
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
@@ -2731,9 +2739,11 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 
-	napi_complete(napi);
-	hns3_update_new_int_gl(tqp_vector);
-	hns3_mask_vector_irq(tqp_vector, 1);
+	if (likely(!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) &&
+	    napi_complete(napi)) {
+		hns3_update_new_int_gl(tqp_vector);
+		hns3_mask_vector_irq(tqp_vector, 1);
+	}
 
 	return rx_pkt_total;
 }
-- 
cgit v1.2.3


From 6dd22bbc77f76208294f573c2de41f1d2dde72b9 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Nov 2018 22:07:53 +0800
Subject: net: hns3: implement the IMP reset processing for PF

The current code only print the prompt message after receiving
the IMP reset interrupt and does not perform the corresponding driver
reset operation. This patch implements the missing IMP reset handling
in the driver.
1. The driver sets the HCLGE_STATE_CMD_DISABLE to stop sending command
   after receiving the IMP reset interrupt.
2. The driver needs to notify the hardware to reload the IMP firmware.
3. The IMP firmware reloading makes the reset time of hardware longer,
   so it is necessary to extend the driver's waiting time to wait for
   the hardware reset to complete.
4. In hclge_check_event_cause, IMP reset event should have higher
   priority than other events.

Also, after clearing HCLGE_STATE_CMD_DISABLE in the hclge_cmd_init(),
it needs to check whether there is a pending reset, if so, just set
the HCLGE_STATE_CMD_DISABLE back and return.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 11 ++++++++-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 27 +++++++++++++++-------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  8 +++++++
 3 files changed, 37 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 690f62ed87dc..8af0cef5609b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -350,11 +350,20 @@ int hclge_cmd_init(struct hclge_dev *hdev)
 	hdev->hw.cmq.crq.next_to_use = 0;
 
 	hclge_cmd_init_regs(&hdev->hw);
-	clear_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 
 	spin_unlock_bh(&hdev->hw.cmq.crq.lock);
 	spin_unlock_bh(&hdev->hw.cmq.csq.lock);
 
+	clear_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+
+	/* Check if there is new reset pending, because the higher level
+	 * reset may happen when lower level reset is being processed.
+	 */
+	if ((hclge_is_reset_pending(hdev))) {
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+		return -EBUSY;
+	}
+
 	ret = hclge_cmd_query_firmware_version(&hdev->hw, &version);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index ba6ea6b804fb..7dbab29da212 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2144,6 +2144,14 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	 */
 
 	/* check for vector0 reset event sources */
+	if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & rst_src_reg) {
+		dev_info(&hdev->pdev->dev, "IMP reset interrupt\n");
+		set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+		*clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B);
+		return HCLGE_VECTOR0_EVENT_RST;
+	}
+
 	if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & rst_src_reg) {
 		dev_info(&hdev->pdev->dev, "global reset interrupt\n");
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
@@ -2160,13 +2168,6 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 		return HCLGE_VECTOR0_EVENT_RST;
 	}
 
-	if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & rst_src_reg) {
-		dev_info(&hdev->pdev->dev, "IMP reset interrupt\n");
-		set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
-		*clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B);
-		return HCLGE_VECTOR0_EVENT_RST;
-	}
-
 	/* check for vector0 mailbox(=CMDQ RX) event source */
 	if (BIT(HCLGE_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) {
 		cmdq_src_reg &= ~BIT(HCLGE_VECTOR0_RX_CMDQ_INT_B);
@@ -2352,11 +2353,15 @@ static int hclge_notify_roce_client(struct hclge_dev *hdev,
 static int hclge_reset_wait(struct hclge_dev *hdev)
 {
 #define HCLGE_RESET_WATI_MS	100
-#define HCLGE_RESET_WAIT_CNT	5
+#define HCLGE_RESET_WAIT_CNT	200
 	u32 val, reg, reg_bit;
 	u32 cnt = 0;
 
 	switch (hdev->reset_type) {
+	case HNAE3_IMP_RESET:
+		reg = HCLGE_GLOBAL_RESET_REG;
+		reg_bit = HCLGE_IMP_RESET_BIT;
+		break;
 	case HNAE3_GLOBAL_RESET:
 		reg = HCLGE_GLOBAL_RESET_REG;
 		reg_bit = HCLGE_GLOBAL_RESET_BIT;
@@ -2561,6 +2566,7 @@ static int hclge_reset_prepare_down(struct hclge_dev *hdev)
 
 static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 {
+	u32 reg_val;
 	int ret = 0;
 
 	switch (hdev->reset_type) {
@@ -2583,6 +2589,11 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 		 */
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		break;
+	case HNAE3_IMP_RESET:
+		reg_val = hclge_read_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG);
+		hclge_write_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG,
+				BIT(HCLGE_VECTOR0_IMP_RESET_INT_B) | reg_val);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 8ab974c4fc4b..b0e683e05a49 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -97,6 +97,7 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_NETWORK_PORT_ID_M		GENMASK(3, 0)
 
 /* Reset related Registers */
+#define HCLGE_PF_OTHER_INT_REG		0x20600
 #define HCLGE_MISC_RESET_STS_REG	0x20700
 #define HCLGE_MISC_VECTOR_INT_STS	0x20800
 #define HCLGE_GLOBAL_RESET_REG		0x20A00
@@ -116,6 +117,8 @@ enum HLCGE_PORT_TYPE {
 /* CMDQ register bits for RX event(=MBX event) */
 #define HCLGE_VECTOR0_RX_CMDQ_INT_B	1
 
+#define HCLGE_VECTOR0_IMP_RESET_INT_B	1
+
 #define HCLGE_MAC_DEFAULT_FRAME \
 	(ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN + ETH_DATA_LEN)
 #define HCLGE_MAC_MIN_FRAME		64
@@ -775,6 +778,11 @@ static inline int hclge_get_queue_id(struct hnae3_queue *queue)
 	return tqp->index;
 }
 
+static inline bool hclge_is_reset_pending(struct hclge_dev *hdev)
+{
+	return !!hdev->reset_pending;
+}
+
 int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport);
 int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex);
 int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
-- 
cgit v1.2.3


From 6b9a97ee43b211faec91c277fa73965dccce8f6a Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Nov 2018 22:07:54 +0800
Subject: net: hns3: add PCIe FLR support for PF

This patch implements the .reset_prepare and .reset_done
ops from pci framework to support the PF FLR.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  9 ++-
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 20 +++++++
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    |  2 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 67 ++++++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  1 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c |  2 +
 6 files changed, 100 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index f15f5958decf..f69d39f17bdd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -127,6 +127,7 @@ enum hnae3_reset_type {
 	HNAE3_VF_FUNC_RESET,
 	HNAE3_VF_PF_FUNC_RESET,
 	HNAE3_VF_FULL_RESET,
+	HNAE3_FLR_RESET,
 	HNAE3_FUNC_RESET,
 	HNAE3_CORE_RESET,
 	HNAE3_GLOBAL_RESET,
@@ -134,6 +135,11 @@ enum hnae3_reset_type {
 	HNAE3_NONE_RESET,
 };
 
+enum hnae3_flr_state {
+	HNAE3_FLR_DOWN,
+	HNAE3_FLR_DONE,
+};
+
 struct hnae3_vector_info {
 	u8 __iomem *io_addr;
 	int vector;
@@ -299,7 +305,8 @@ struct hnae3_ae_dev {
 struct hnae3_ae_ops {
 	int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev);
 	void (*uninit_ae_dev)(struct hnae3_ae_dev *ae_dev);
-
+	void (*flr_prepare)(struct hnae3_ae_dev *ae_dev);
+	void (*flr_done)(struct hnae3_ae_dev *ae_dev);
 	int (*init_client_instance)(struct hnae3_client *client,
 				    struct hnae3_ae_dev *ae_dev);
 	void (*uninit_client_instance)(struct hnae3_client *client,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 499032bba705..52ebba77f15e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1851,9 +1851,29 @@ static pci_ers_result_t hns3_slot_reset(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_DISCONNECT;
 }
 
+static void hns3_reset_prepare(struct pci_dev *pdev)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
+
+	dev_info(&pdev->dev, "hns3 flr prepare\n");
+	if (ae_dev && ae_dev->ops && ae_dev->ops->flr_prepare)
+		ae_dev->ops->flr_prepare(ae_dev);
+}
+
+static void hns3_reset_done(struct pci_dev *pdev)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
+
+	dev_info(&pdev->dev, "hns3 flr done\n");
+	if (ae_dev && ae_dev->ops && ae_dev->ops->flr_done)
+		ae_dev->ops->flr_done(ae_dev);
+}
+
 static const struct pci_error_handlers hns3_err_handler = {
 	.error_detected = hns3_error_detected,
 	.slot_reset     = hns3_slot_reset,
+	.reset_prepare	= hns3_reset_prepare,
+	.reset_done	= hns3_reset_done,
 };
 
 static struct pci_driver hns3_driver = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index bd6ee5c8516b..10ff18af3cc7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -594,7 +594,9 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 static inline bool hns3_dev_ongoing_func_reset(struct hnae3_ae_dev *ae_dev)
 {
 	return (ae_dev && (ae_dev->reset_type == HNAE3_FUNC_RESET ||
+			   ae_dev->reset_type == HNAE3_FLR_RESET ||
 			   ae_dev->reset_type == HNAE3_VF_FUNC_RESET ||
+			   ae_dev->reset_type == HNAE3_VF_FULL_RESET ||
 			   ae_dev->reset_type == HNAE3_VF_PF_FUNC_RESET));
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 7dbab29da212..ab90108db1c9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2374,6 +2374,8 @@ static int hclge_reset_wait(struct hclge_dev *hdev)
 		reg = HCLGE_FUN_RST_ING;
 		reg_bit = HCLGE_FUN_RST_ING_B;
 		break;
+	case HNAE3_FLR_RESET:
+		break;
 	default:
 		dev_err(&hdev->pdev->dev,
 			"Wait for unsupported reset type: %d\n",
@@ -2381,6 +2383,20 @@ static int hclge_reset_wait(struct hclge_dev *hdev)
 		return -EINVAL;
 	}
 
+	if (hdev->reset_type == HNAE3_FLR_RESET) {
+		while (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state) &&
+		       cnt++ < HCLGE_RESET_WAIT_CNT)
+			msleep(HCLGE_RESET_WATI_MS);
+
+		if (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state)) {
+			dev_err(&hdev->pdev->dev,
+				"flr wait timeout: %d\n", cnt);
+			return -EBUSY;
+		}
+
+		return 0;
+	}
+
 	val = hclge_read_dev(&hdev->hw, reg);
 	while (hnae3_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) {
 		msleep(HCLGE_RESET_WATI_MS);
@@ -2488,6 +2504,12 @@ static void hclge_do_reset(struct hclge_dev *hdev)
 		set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending);
 		hclge_reset_task_schedule(hdev);
 		break;
+	case HNAE3_FLR_RESET:
+		dev_info(&pdev->dev, "FLR requested\n");
+		/* schedule again to check later */
+		set_bit(HNAE3_FLR_RESET, &hdev->reset_pending);
+		hclge_reset_task_schedule(hdev);
+		break;
 	default:
 		dev_warn(&pdev->dev,
 			 "Unsupported reset type: %d\n", hdev->reset_type);
@@ -2519,6 +2541,9 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hclge_dev *hdev,
 	} else if (test_bit(HNAE3_FUNC_RESET, addr)) {
 		rst_level = HNAE3_FUNC_RESET;
 		clear_bit(HNAE3_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_FLR_RESET, addr)) {
+		rst_level = HNAE3_FLR_RESET;
+		clear_bit(HNAE3_FLR_RESET, addr);
 	}
 
 	return rst_level;
@@ -2555,6 +2580,8 @@ static int hclge_reset_prepare_down(struct hclge_dev *hdev)
 
 	switch (hdev->reset_type) {
 	case HNAE3_FUNC_RESET:
+		/* fall through */
+	case HNAE3_FLR_RESET:
 		ret = hclge_set_all_vf_rst(hdev, true);
 		break;
 	default:
@@ -2589,6 +2616,14 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 		 */
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		break;
+	case HNAE3_FLR_RESET:
+		/* There is no mechanism for PF to know if VF has stopped IO
+		 * for now, just wait 100 ms for VF to stop IO
+		 */
+		msleep(100);
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+		set_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
+		break;
 	case HNAE3_IMP_RESET:
 		reg_val = hclge_read_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG);
 		hclge_write_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG,
@@ -2647,6 +2682,8 @@ static int hclge_reset_prepare_up(struct hclge_dev *hdev)
 
 	switch (hdev->reset_type) {
 	case HNAE3_FUNC_RESET:
+		/* fall through */
+	case HNAE3_FLR_RESET:
 		ret = hclge_set_all_vf_rst(hdev, false);
 		break;
 	default:
@@ -6917,6 +6954,34 @@ static void hclge_state_uninit(struct hclge_dev *hdev)
 		cancel_work_sync(&hdev->mbx_service_task);
 }
 
+static void hclge_flr_prepare(struct hnae3_ae_dev *ae_dev)
+{
+#define HCLGE_FLR_WAIT_MS	100
+#define HCLGE_FLR_WAIT_CNT	50
+	struct hclge_dev *hdev = ae_dev->priv;
+	int cnt = 0;
+
+	clear_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
+	clear_bit(HNAE3_FLR_DONE, &hdev->flr_state);
+	set_bit(HNAE3_FLR_RESET, &hdev->default_reset_request);
+	hclge_reset_event(hdev->pdev, NULL);
+
+	while (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state) &&
+	       cnt++ < HCLGE_FLR_WAIT_CNT)
+		msleep(HCLGE_FLR_WAIT_MS);
+
+	if (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state))
+		dev_err(&hdev->pdev->dev,
+			"flr wait down timeout: %d\n", cnt);
+}
+
+static void hclge_flr_done(struct hnae3_ae_dev *ae_dev)
+{
+	struct hclge_dev *hdev = ae_dev->priv;
+
+	set_bit(HNAE3_FLR_DONE, &hdev->flr_state);
+}
+
 static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct pci_dev *pdev = ae_dev->pdev;
@@ -7575,6 +7640,8 @@ static void hclge_get_link_mode(struct hnae3_handle *handle,
 static const struct hnae3_ae_ops hclge_ops = {
 	.init_ae_dev = hclge_init_ae_dev,
 	.uninit_ae_dev = hclge_uninit_ae_dev,
+	.flr_prepare = hclge_flr_prepare,
+	.flr_done = hclge_flr_done,
 	.init_client_instance = hclge_init_client_instance,
 	.uninit_client_instance = hclge_uninit_client_instance,
 	.map_ring_to_vector = hclge_map_ring_to_vector,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index b0e683e05a49..ca90b662e33b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -597,6 +597,7 @@ struct hclge_dev {
 	struct hclge_misc_vector misc_vector;
 	struct hclge_hw_stats hw_stats;
 	unsigned long state;
+	unsigned long flr_state;
 	unsigned long last_reset_time;
 
 	enum hnae3_reset_type reset_type;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index f15b807b977e..4c7e7bd3c847 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -90,6 +90,8 @@ int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
 
 	if (hdev->reset_type == HNAE3_FUNC_RESET)
 		reset_type = HNAE3_VF_PF_FUNC_RESET;
+	else if (hdev->reset_type == HNAE3_FLR_RESET)
+		reset_type = HNAE3_VF_FULL_RESET;
 	else
 		return -EINVAL;
 
-- 
cgit v1.2.3


From 862d969a3a4dcd80e92fdb09d6eab2c3149eb582 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Nov 2018 22:07:55 +0800
Subject: net: hns3: do VF's pci re-initialization while PF doing FLR

While doing PF FLR, VF's PCIe configuration space will be cleared, so
the pci and vector of VF should be re-initialized in the VF's reset
process while PF doing FLR.

Also, this patch fixes some memory not freed problem when pci
re-initialization is done during reset process.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 24 +++++++--
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 57 ++++++++++++++++++++--
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  1 +
 3 files changed, 74 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 52ebba77f15e..b23a6e12d607 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3848,20 +3848,30 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 	/* Carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(netdev);
 
+	ret = hns3_nic_alloc_vector_data(priv);
+	if (ret)
+		return ret;
+
 	hns3_restore_coal(priv);
 
 	ret = hns3_nic_init_vector_data(priv);
 	if (ret)
-		return ret;
+		goto err_dealloc_vector;
 
 	ret = hns3_init_all_ring(priv);
-	if (ret) {
-		hns3_nic_uninit_vector_data(priv);
-		priv->ring_data = NULL;
-	}
+	if (ret)
+		goto err_uninit_vector;
 
 	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
+	return ret;
+
+err_uninit_vector:
+	hns3_nic_uninit_vector_data(priv);
+	priv->ring_data = NULL;
+err_dealloc_vector:
+	hns3_nic_dealloc_vector_data(priv);
+
 	return ret;
 }
 
@@ -3886,6 +3896,10 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 
 	hns3_store_coal(priv);
 
+	ret = hns3_nic_dealloc_vector_data(priv);
+	if (ret)
+		netdev_err(netdev, "dealloc vector error\n");
+
 	ret = hns3_uninit_all_ring(priv);
 	if (ret)
 		netdev_err(netdev, "uninit ring error\n");
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 4dfac6c0cece..8f1c681d96ef 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1766,6 +1766,7 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 	hdev->vector_irq = devm_kcalloc(&pdev->dev, hdev->num_msi,
 					sizeof(int), GFP_KERNEL);
 	if (!hdev->vector_irq) {
+		devm_kfree(&pdev->dev, hdev->vector_status);
 		pci_free_irq_vectors(pdev);
 		return -ENOMEM;
 	}
@@ -1777,6 +1778,8 @@ static void hclgevf_uninit_msi(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
 
+	devm_kfree(&pdev->dev, hdev->vector_status);
+	devm_kfree(&pdev->dev, hdev->vector_irq);
 	pci_free_irq_vectors(pdev);
 }
 
@@ -2001,11 +2004,52 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
 	return 0;
 }
 
+static int hclgevf_pci_reset(struct hclgevf_dev *hdev)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	int ret = 0;
+
+	if (hdev->reset_type == HNAE3_VF_FULL_RESET &&
+	    test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) {
+		hclgevf_misc_irq_uninit(hdev);
+		hclgevf_uninit_msi(hdev);
+		clear_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state);
+	}
+
+	if (!test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) {
+		pci_set_master(pdev);
+		ret = hclgevf_init_msi(hdev);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"failed(%d) to init MSI/MSI-X\n", ret);
+			return ret;
+		}
+
+		ret = hclgevf_misc_irq_init(hdev);
+		if (ret) {
+			hclgevf_uninit_msi(hdev);
+			dev_err(&pdev->dev, "failed(%d) to init Misc IRQ(vector0)\n",
+				ret);
+			return ret;
+		}
+
+		set_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state);
+	}
+
+	return ret;
+}
+
 static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
 	int ret;
 
+	ret = hclgevf_pci_reset(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "pci reset failed %d\n", ret);
+		return ret;
+	}
+
 	ret = hclgevf_cmd_init(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "cmd failed %d\n", ret);
@@ -2076,6 +2120,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_misc_irq_init;
 	}
 
+	set_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state);
+
 	ret = hclgevf_configure(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed(%d) to fetch configuration\n", ret);
@@ -2123,16 +2169,21 @@ err_cmd_init:
 	hclgevf_cmd_uninit(hdev);
 err_cmd_queue_init:
 	hclgevf_pci_uninit(hdev);
+	clear_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state);
 	return ret;
 }
 
 static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev)
 {
 	hclgevf_state_uninit(hdev);
-	hclgevf_misc_irq_uninit(hdev);
+
+	if (test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) {
+		hclgevf_misc_irq_uninit(hdev);
+		hclgevf_uninit_msi(hdev);
+		hclgevf_pci_uninit(hdev);
+	}
+
 	hclgevf_cmd_uninit(hdev);
-	hclgevf_uninit_msi(hdev);
-	hclgevf_pci_uninit(hdev);
 }
 
 static int hclgevf_init_ae_dev(struct hnae3_ae_dev *ae_dev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index ffe3d495376c..028c52ecb6b9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -73,6 +73,7 @@ enum hclgevf_states {
 	/* device states */
 	HCLGEVF_STATE_DOWN,
 	HCLGEVF_STATE_DISABLED,
+	HCLGEVF_STATE_IRQ_INITED,
 	/* task states */
 	HCLGEVF_STATE_SERVICE_SCHED,
 	HCLGEVF_STATE_RST_SERVICE_SCHED,
-- 
cgit v1.2.3


From 6ff3cf0783e9343297ef7af2d03c42cbb664ed9b Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Nov 2018 22:07:56 +0800
Subject: net: hns3: add PCIe FLR support for VF

This patch implements the .reset_prepare and .reset_done
ops from pci framework to support the VF FLR.

This patch uses hclgevf_set_def_reset_request() and
hclgevf_reset_event() to handle FLR, so when
hdev->default_reset_request is non zero, it means there is
some reset requseted by hclgevf_set_def_reset_request() need
to be processed. Also get the hdev from the ae_dev because
hclgevf_reset_event is called with handle being NULL.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 65 +++++++++++++++++++++-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  1 +
 2 files changed, 64 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 8f1c681d96ef..6b4d1477055f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1099,6 +1099,32 @@ static int hclgevf_notify_client(struct hclgevf_dev *hdev,
 	return ret;
 }
 
+static void hclgevf_flr_done(struct hnae3_ae_dev *ae_dev)
+{
+	struct hclgevf_dev *hdev = ae_dev->priv;
+
+	set_bit(HNAE3_FLR_DONE, &hdev->flr_state);
+}
+
+static int hclgevf_flr_poll_timeout(struct hclgevf_dev *hdev,
+				    unsigned long delay_us,
+				    unsigned long wait_cnt)
+{
+	unsigned long cnt = 0;
+
+	while (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state) &&
+	       cnt++ < wait_cnt)
+		usleep_range(delay_us, delay_us * 2);
+
+	if (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state)) {
+		dev_err(&hdev->pdev->dev,
+			"flr wait timeout\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
 static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
 {
 #define HCLGEVF_RESET_WAIT_US	20000
@@ -1113,6 +1139,11 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
 	val = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
 	dev_info(&hdev->pdev->dev, "checking vf resetting status: %x\n", val);
 
+	if (hdev->reset_type == HNAE3_FLR_RESET)
+		return hclgevf_flr_poll_timeout(hdev,
+						HCLGEVF_RESET_WAIT_US,
+						HCLGEVF_RESET_WAIT_CNT);
+
 	ret = readl_poll_timeout(hdev->hw.io_base + HCLGEVF_RST_ING, val,
 				 !(val & HCLGEVF_RST_ING_BITS),
 				 HCLGEVF_RESET_WAIT_US,
@@ -1168,6 +1199,9 @@ static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev)
 		ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_RESET, 0, NULL,
 					   0, true, NULL, sizeof(u8));
 		break;
+	case HNAE3_FLR_RESET:
+		set_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
+		break;
 	default:
 		break;
 	}
@@ -1267,6 +1301,9 @@ static enum hnae3_reset_type hclgevf_get_reset_level(struct hclgevf_dev *hdev,
 	} else if (test_bit(HNAE3_VF_FUNC_RESET, addr)) {
 		rst_level = HNAE3_VF_FUNC_RESET;
 		clear_bit(HNAE3_VF_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_FLR_RESET, addr)) {
+		rst_level = HNAE3_FLR_RESET;
+		clear_bit(HNAE3_FLR_RESET, addr);
 	}
 
 	return rst_level;
@@ -1275,11 +1312,12 @@ static enum hnae3_reset_type hclgevf_get_reset_level(struct hclgevf_dev *hdev,
 static void hclgevf_reset_event(struct pci_dev *pdev,
 				struct hnae3_handle *handle)
 {
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
+	struct hclgevf_dev *hdev = ae_dev->priv;
 
 	dev_info(&hdev->pdev->dev, "received reset request from VF enet\n");
 
-	if (!hdev->default_reset_request)
+	if (hdev->default_reset_request)
 		hdev->reset_level =
 			hclgevf_get_reset_level(hdev,
 						&hdev->default_reset_request);
@@ -1301,6 +1339,27 @@ static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
 	set_bit(rst_type, &hdev->default_reset_request);
 }
 
+static void hclgevf_flr_prepare(struct hnae3_ae_dev *ae_dev)
+{
+#define HCLGEVF_FLR_WAIT_MS	100
+#define HCLGEVF_FLR_WAIT_CNT	50
+	struct hclgevf_dev *hdev = ae_dev->priv;
+	int cnt = 0;
+
+	clear_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
+	clear_bit(HNAE3_FLR_DONE, &hdev->flr_state);
+	set_bit(HNAE3_FLR_RESET, &hdev->default_reset_request);
+	hclgevf_reset_event(hdev->pdev, NULL);
+
+	while (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state) &&
+	       cnt++ < HCLGEVF_FLR_WAIT_CNT)
+		msleep(HCLGEVF_FLR_WAIT_MS);
+
+	if (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state))
+		dev_err(&hdev->pdev->dev,
+			"flr wait down timeout: %d\n", cnt);
+}
+
 static u32 hclgevf_get_fw_version(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
@@ -2310,6 +2369,8 @@ static unsigned long hclgevf_ae_dev_reset_cnt(struct hnae3_handle *handle)
 static const struct hnae3_ae_ops hclgevf_ops = {
 	.init_ae_dev = hclgevf_init_ae_dev,
 	.uninit_ae_dev = hclgevf_uninit_ae_dev,
+	.flr_prepare = hclgevf_flr_prepare,
+	.flr_done = hclgevf_flr_done,
 	.init_client_instance = hclgevf_init_client_instance,
 	.uninit_client_instance = hclgevf_uninit_client_instance,
 	.start = hclgevf_ae_start,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 028c52ecb6b9..4c5ea7edcbb1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -161,6 +161,7 @@ struct hclgevf_dev {
 	struct hclgevf_misc_vector misc_vector;
 	struct hclgevf_rss_cfg rss_cfg;
 	unsigned long state;
+	unsigned long flr_state;
 	unsigned long default_reset_request;
 	unsigned long last_reset_time;
 	enum hnae3_reset_type reset_level;
-- 
cgit v1.2.3


From fbb960ac26172215b8dc6635eac13c3a0739d6ed Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Fri, 9 Nov 2018 11:14:42 +0100
Subject: ptp: reorder declarations in ptp_ioctl()

Reorder declarations of variables as reversed Christmas tree.

Cc: Richard Cochran <richardcochran@gmail.com>
Suggested-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 2012551d93e0..b54b8158ff8a 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -121,18 +121,18 @@ int ptp_open(struct posix_clock *pc, fmode_t fmode)
 
 long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 {
-	struct ptp_clock_caps caps;
-	struct ptp_clock_request req;
-	struct ptp_sys_offset *sysoff = NULL;
-	struct ptp_sys_offset_precise precise_offset;
-	struct ptp_pin_desc pd;
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+	struct ptp_sys_offset_precise precise_offset;
+	struct system_device_crosststamp xtstamp;
 	struct ptp_clock_info *ops = ptp->info;
+	struct ptp_sys_offset *sysoff = NULL;
+	struct ptp_clock_request req;
+	struct ptp_clock_caps caps;
 	struct ptp_clock_time *pct;
+	unsigned int i, pin_index;
+	struct ptp_pin_desc pd;
 	struct timespec64 ts;
-	struct system_device_crosststamp xtstamp;
 	int enable, err = 0;
-	unsigned int i, pin_index;
 
 	switch (cmd) {
 
-- 
cgit v1.2.3


From 83d0bdc7390b890905634186baaa294475cd6a06 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Fri, 9 Nov 2018 11:14:43 +0100
Subject: ptp: check gettime64 return code in PTP_SYS_OFFSET ioctl

If a gettime64 call fails, return the error and avoid copying data back
to user.

Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index b54b8158ff8a..3c681bed5703 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -228,7 +228,9 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 			pct->sec = ts.tv_sec;
 			pct->nsec = ts.tv_nsec;
 			pct++;
-			ptp->info->gettime64(ptp->info, &ts);
+			err = ptp->info->gettime64(ptp->info, &ts);
+			if (err)
+				goto out;
 			pct->sec = ts.tv_sec;
 			pct->nsec = ts.tv_nsec;
 			pct++;
@@ -281,6 +283,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 		break;
 	}
 
+out:
 	kfree(sysoff);
 	return err;
 }
-- 
cgit v1.2.3


From 361800876f80da3915c46e388fc682532228b2c3 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Fri, 9 Nov 2018 11:14:44 +0100
Subject: ptp: add PTP_SYS_OFFSET_EXTENDED ioctl

The PTP_SYS_OFFSET ioctl, which can be used to measure the offset
between a PHC and the system clock, includes the total time that the
driver needs to read the PHC timestamp.

This typically involves reading of multiple PCI registers (sometimes in
multiple iterations) and the register that contains the lowest bits of
the timestamp is not read in the middle between the two readings of the
system clock. This asymmetry causes the measured offset to have a
significant error.

Introduce a new ioctl, driver function, and helper functions, which
allow the reading of the lowest register to be isolated from the other
readings in order to reduce the asymmetry. The ioctl returns three
timestamps for each measurement:
- system time right before reading the lowest bits of the PHC timestamp
- PHC time
- system time immediately after reading the lowest bits of the PHC
  timestamp

Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Jacob Keller <jacob.e.keller@intel.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c        | 33 +++++++++++++++++++++++++++++++++
 include/linux/ptp_clock_kernel.h | 31 +++++++++++++++++++++++++++++++
 include/uapi/linux/ptp_clock.h   | 12 ++++++++++++
 3 files changed, 76 insertions(+)

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 3c681bed5703..aad0d36cf5c0 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -122,10 +122,12 @@ int ptp_open(struct posix_clock *pc, fmode_t fmode)
 long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 {
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+	struct ptp_sys_offset_extended *extoff = NULL;
 	struct ptp_sys_offset_precise precise_offset;
 	struct system_device_crosststamp xtstamp;
 	struct ptp_clock_info *ops = ptp->info;
 	struct ptp_sys_offset *sysoff = NULL;
+	struct ptp_system_timestamp sts;
 	struct ptp_clock_request req;
 	struct ptp_clock_caps caps;
 	struct ptp_clock_time *pct;
@@ -211,6 +213,36 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 			err = -EFAULT;
 		break;
 
+	case PTP_SYS_OFFSET_EXTENDED:
+		if (!ptp->info->gettimex64) {
+			err = -EOPNOTSUPP;
+			break;
+		}
+		extoff = memdup_user((void __user *)arg, sizeof(*extoff));
+		if (IS_ERR(extoff)) {
+			err = PTR_ERR(extoff);
+			extoff = NULL;
+			break;
+		}
+		if (extoff->n_samples > PTP_MAX_SAMPLES) {
+			err = -EINVAL;
+			break;
+		}
+		for (i = 0; i < extoff->n_samples; i++) {
+			err = ptp->info->gettimex64(ptp->info, &ts, &sts);
+			if (err)
+				goto out;
+			extoff->ts[i][0].sec = sts.pre_ts.tv_sec;
+			extoff->ts[i][0].nsec = sts.pre_ts.tv_nsec;
+			extoff->ts[i][1].sec = ts.tv_sec;
+			extoff->ts[i][1].nsec = ts.tv_nsec;
+			extoff->ts[i][2].sec = sts.post_ts.tv_sec;
+			extoff->ts[i][2].nsec = sts.post_ts.tv_nsec;
+		}
+		if (copy_to_user((void __user *)arg, extoff, sizeof(*extoff)))
+			err = -EFAULT;
+		break;
+
 	case PTP_SYS_OFFSET:
 		sysoff = memdup_user((void __user *)arg, sizeof(*sysoff));
 		if (IS_ERR(sysoff)) {
@@ -284,6 +316,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 	}
 
 out:
+	kfree(extoff);
 	kfree(sysoff);
 	return err;
 }
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 51349d124ee5..a1ec0448e341 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -39,6 +39,15 @@ struct ptp_clock_request {
 };
 
 struct system_device_crosststamp;
+
+/**
+ * struct ptp_system_timestamp - system time corresponding to a PHC timestamp
+ */
+struct ptp_system_timestamp {
+	struct timespec64 pre_ts;
+	struct timespec64 post_ts;
+};
+
 /**
  * struct ptp_clock_info - decribes a PTP hardware clock
  *
@@ -75,6 +84,14 @@ struct system_device_crosststamp;
  * @gettime64:  Reads the current time from the hardware clock.
  *              parameter ts: Holds the result.
  *
+ * @gettimex64:  Reads the current time from the hardware clock and optionally
+ *               also the system clock.
+ *               parameter ts: Holds the PHC timestamp.
+ *               parameter sts: If not NULL, it holds a pair of timestamps from
+ *               the system clock. The first reading is made right before
+ *               reading the lowest bits of the PHC timestamp and the second
+ *               reading immediately follows that.
+ *
  * @getcrosststamp:  Reads the current time from the hardware clock and
  *                   system clock simultaneously.
  *                   parameter cts: Contains timestamp (device,system) pair,
@@ -124,6 +141,8 @@ struct ptp_clock_info {
 	int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta);
 	int (*adjtime)(struct ptp_clock_info *ptp, s64 delta);
 	int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts);
+	int (*gettimex64)(struct ptp_clock_info *ptp, struct timespec64 *ts,
+			  struct ptp_system_timestamp *sts);
 	int (*getcrosststamp)(struct ptp_clock_info *ptp,
 			      struct system_device_crosststamp *cts);
 	int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts);
@@ -247,4 +266,16 @@ static inline int ptp_schedule_worker(struct ptp_clock *ptp,
 
 #endif
 
+static inline void ptp_read_system_prets(struct ptp_system_timestamp *sts)
+{
+	if (sts)
+		ktime_get_real_ts64(&sts->pre_ts);
+}
+
+static inline void ptp_read_system_postts(struct ptp_system_timestamp *sts)
+{
+	if (sts)
+		ktime_get_real_ts64(&sts->post_ts);
+}
+
 #endif
diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h
index 3039bf6a742e..d73d83950265 100644
--- a/include/uapi/linux/ptp_clock.h
+++ b/include/uapi/linux/ptp_clock.h
@@ -84,6 +84,16 @@ struct ptp_sys_offset {
 	struct ptp_clock_time ts[2 * PTP_MAX_SAMPLES + 1];
 };
 
+struct ptp_sys_offset_extended {
+	unsigned int n_samples; /* Desired number of measurements. */
+	unsigned int rsv[3];    /* Reserved for future use. */
+	/*
+	 * Array of [system, phc, system] time stamps. The kernel will provide
+	 * 3*n_samples time stamps.
+	 */
+	struct ptp_clock_time ts[PTP_MAX_SAMPLES][3];
+};
+
 struct ptp_sys_offset_precise {
 	struct ptp_clock_time device;
 	struct ptp_clock_time sys_realtime;
@@ -136,6 +146,8 @@ struct ptp_pin_desc {
 #define PTP_PIN_SETFUNC    _IOW(PTP_CLK_MAGIC, 7, struct ptp_pin_desc)
 #define PTP_SYS_OFFSET_PRECISE \
 	_IOWR(PTP_CLK_MAGIC, 8, struct ptp_sys_offset_precise)
+#define PTP_SYS_OFFSET_EXTENDED \
+	_IOW(PTP_CLK_MAGIC, 9, struct ptp_sys_offset_extended)
 
 struct ptp_extts_event {
 	struct ptp_clock_time t; /* Time event occured. */
-- 
cgit v1.2.3


From 916444df305ef5b8a7d824aac7dd2aeba3a4db3b Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Fri, 9 Nov 2018 11:14:45 +0100
Subject: ptp: deprecate gettime64() in favor of gettimex64()

When a driver provides gettimex64(), use it in the PTP_SYS_OFFSET ioctl
and POSIX clock's gettime() instead of gettime64(). Drivers should
provide only one of the functions.

Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c        | 5 ++++-
 drivers/ptp/ptp_clock.c          | 5 ++++-
 include/linux/ptp_clock_kernel.h | 2 ++
 3 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index aad0d36cf5c0..797fab33bb98 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -260,7 +260,10 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 			pct->sec = ts.tv_sec;
 			pct->nsec = ts.tv_nsec;
 			pct++;
-			err = ptp->info->gettime64(ptp->info, &ts);
+			if (ops->gettimex64)
+				err = ops->gettimex64(ops, &ts, NULL);
+			else
+				err = ops->gettime64(ops, &ts);
 			if (err)
 				goto out;
 			pct->sec = ts.tv_sec;
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 5419a89d300e..40fda23e4b05 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -117,7 +117,10 @@ static int ptp_clock_gettime(struct posix_clock *pc, struct timespec64 *tp)
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
 	int err;
 
-	err = ptp->info->gettime64(ptp->info, tp);
+	if (ptp->info->gettimex64)
+		err = ptp->info->gettimex64(ptp->info, tp, NULL);
+	else
+		err = ptp->info->gettime64(ptp->info, tp);
 	return err;
 }
 
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index a1ec0448e341..7121bbe76979 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -82,6 +82,8 @@ struct ptp_system_timestamp {
  *            parameter delta: Desired change in nanoseconds.
  *
  * @gettime64:  Reads the current time from the hardware clock.
+ *              This method is deprecated.  New drivers should implement
+ *              the @gettimex64 method instead.
  *              parameter ts: Holds the result.
  *
  * @gettimex64:  Reads the current time from the hardware clock and optionally
-- 
cgit v1.2.3


From 98942d70538a16cdc06389456a4cd0ea62559432 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Fri, 9 Nov 2018 11:14:46 +0100
Subject: e1000e: extend PTP gettime function to read system clock

This adds support for the PTP_SYS_OFFSET_EXTENDED ioctl.

Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Jacob Keller <jacob.e.keller@intel.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/e1000e/e1000.h  |  3 +++
 drivers/net/ethernet/intel/e1000e/netdev.c | 42 +++++++++++++++++++++++-------
 drivers/net/ethernet/intel/e1000e/ptp.c    | 16 +++++++-----
 3 files changed, 45 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index c760dc72c520..be13227f1697 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -505,6 +505,9 @@ extern const struct e1000_info e1000_es2_info;
 void e1000e_ptp_init(struct e1000_adapter *adapter);
 void e1000e_ptp_remove(struct e1000_adapter *adapter);
 
+u64 e1000e_read_systim(struct e1000_adapter *adapter,
+		       struct ptp_system_timestamp *sts);
+
 static inline s32 e1000_phy_hw_reset(struct e1000_hw *hw)
 {
 	return hw->phy.ops.reset(hw);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 16a73bd9f4cb..59bd587d809d 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -4319,13 +4319,16 @@ void e1000e_reinit_locked(struct e1000_adapter *adapter)
 /**
  * e1000e_sanitize_systim - sanitize raw cycle counter reads
  * @hw: pointer to the HW structure
- * @systim: time value read, sanitized and returned
+ * @systim: PHC time value read, sanitized and returned
+ * @sts: structure to hold system time before and after reading SYSTIML,
+ * may be NULL
  *
  * Errata for 82574/82583 possible bad bits read from SYSTIMH/L:
  * check to see that the time is incrementing at a reasonable
  * rate and is a multiple of incvalue.
  **/
-static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim)
+static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim,
+				  struct ptp_system_timestamp *sts)
 {
 	u64 time_delta, rem, temp;
 	u64 systim_next;
@@ -4335,7 +4338,9 @@ static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim)
 	incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK;
 	for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) {
 		/* latch SYSTIMH on read of SYSTIML */
+		ptp_read_system_prets(sts);
 		systim_next = (u64)er32(SYSTIML);
+		ptp_read_system_postts(sts);
 		systim_next |= (u64)er32(SYSTIMH) << 32;
 
 		time_delta = systim_next - systim;
@@ -4353,15 +4358,16 @@ static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim)
 }
 
 /**
- * e1000e_cyclecounter_read - read raw cycle counter (used by time counter)
- * @cc: cyclecounter structure
+ * e1000e_read_systim - read SYSTIM register
+ * @adapter: board private structure
+ * @sts: structure which will contain system time before and after reading
+ * SYSTIML, may be NULL
  **/
-static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
+u64 e1000e_read_systim(struct e1000_adapter *adapter,
+		       struct ptp_system_timestamp *sts)
 {
-	struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter,
-						     cc);
 	struct e1000_hw *hw = &adapter->hw;
-	u32 systimel, systimeh;
+	u32 systimel, systimel_2, systimeh;
 	u64 systim;
 	/* SYSTIMH latching upon SYSTIML read does not work well.
 	 * This means that if SYSTIML overflows after we read it but before
@@ -4369,11 +4375,15 @@ static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
 	 * will experience a huge non linear increment in the systime value
 	 * to fix that we test for overflow and if true, we re-read systime.
 	 */
+	ptp_read_system_prets(sts);
 	systimel = er32(SYSTIML);
+	ptp_read_system_postts(sts);
 	systimeh = er32(SYSTIMH);
 	/* Is systimel is so large that overflow is possible? */
 	if (systimel >= (u32)0xffffffff - E1000_TIMINCA_INCVALUE_MASK) {
-		u32 systimel_2 = er32(SYSTIML);
+		ptp_read_system_prets(sts);
+		systimel_2 = er32(SYSTIML);
+		ptp_read_system_postts(sts);
 		if (systimel > systimel_2) {
 			/* There was an overflow, read again SYSTIMH, and use
 			 * systimel_2
@@ -4386,11 +4396,23 @@ static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
 	systim |= (u64)systimeh << 32;
 
 	if (adapter->flags2 & FLAG2_CHECK_SYSTIM_OVERFLOW)
-		systim = e1000e_sanitize_systim(hw, systim);
+		systim = e1000e_sanitize_systim(hw, systim, sts);
 
 	return systim;
 }
 
+/**
+ * e1000e_cyclecounter_read - read raw cycle counter (used by time counter)
+ * @cc: cyclecounter structure
+ **/
+static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
+{
+	struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter,
+						     cc);
+
+	return e1000e_read_systim(adapter, NULL);
+}
+
 /**
  * e1000_sw_init - Initialize general software structures (struct e1000_adapter)
  * @adapter: board private structure to initialize
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index e1f821edbc21..1a4c65d9feb4 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -161,14 +161,18 @@ static int e1000e_phc_getcrosststamp(struct ptp_clock_info *ptp,
 #endif/*CONFIG_E1000E_HWTS*/
 
 /**
- * e1000e_phc_gettime - Reads the current time from the hardware clock
+ * e1000e_phc_gettimex - Reads the current time from the hardware clock and
+ *                       system clock
  * @ptp: ptp clock structure
- * @ts: timespec structure to hold the current time value
+ * @ts: timespec structure to hold the current PHC time
+ * @sts: structure to hold the current system time
  *
  * Read the timecounter and return the correct value in ns after converting
  * it into a struct timespec.
  **/
-static int e1000e_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int e1000e_phc_gettimex(struct ptp_clock_info *ptp,
+			       struct timespec64 *ts,
+			       struct ptp_system_timestamp *sts)
 {
 	struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter,
 						     ptp_clock_info);
@@ -177,8 +181,8 @@ static int e1000e_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
 
 	spin_lock_irqsave(&adapter->systim_lock, flags);
 
-	/* Use timecounter_cyc2time() to allow non-monotonic SYSTIM readings */
-	cycles = adapter->cc.read(&adapter->cc);
+	/* NOTE: Non-monotonic SYSTIM readings may be returned */
+	cycles = e1000e_read_systim(adapter, sts);
 	ns = timecounter_cyc2time(&adapter->tc, cycles);
 
 	spin_unlock_irqrestore(&adapter->systim_lock, flags);
@@ -258,7 +262,7 @@ static const struct ptp_clock_info e1000e_ptp_clock_info = {
 	.pps		= 0,
 	.adjfreq	= e1000e_phc_adjfreq,
 	.adjtime	= e1000e_phc_adjtime,
-	.gettime64	= e1000e_phc_gettime,
+	.gettimex64	= e1000e_phc_gettimex,
 	.settime64	= e1000e_phc_settime,
 	.enable		= e1000e_phc_enable,
 };
-- 
cgit v1.2.3


From cff8ba28dbf96f16c9941369234db9d4ca9d7d58 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Fri, 9 Nov 2018 11:14:47 +0100
Subject: igb: extend PTP gettime function to read system clock

This adds support for the PTP_SYS_OFFSET_EXTENDED ioctl.

Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Jacob Keller <jacob.e.keller@intel.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_ptp.c | 65 +++++++++++++++++++++++++++-----
 1 file changed, 55 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index 29ced6b74d36..8c1833a157d3 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -275,17 +275,53 @@ static int igb_ptp_adjtime_i210(struct ptp_clock_info *ptp, s64 delta)
 	return 0;
 }
 
-static int igb_ptp_gettime_82576(struct ptp_clock_info *ptp,
-				 struct timespec64 *ts)
+static int igb_ptp_gettimex_82576(struct ptp_clock_info *ptp,
+				  struct timespec64 *ts,
+				  struct ptp_system_timestamp *sts)
 {
 	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
 					       ptp_caps);
+	struct e1000_hw *hw = &igb->hw;
 	unsigned long flags;
+	u32 lo, hi;
 	u64 ns;
 
 	spin_lock_irqsave(&igb->tmreg_lock, flags);
 
-	ns = timecounter_read(&igb->tc);
+	ptp_read_system_prets(sts);
+	lo = rd32(E1000_SYSTIML);
+	ptp_read_system_postts(sts);
+	hi = rd32(E1000_SYSTIMH);
+
+	ns = timecounter_cyc2time(&igb->tc, ((u64)hi << 32) | lo);
+
+	spin_unlock_irqrestore(&igb->tmreg_lock, flags);
+
+	*ts = ns_to_timespec64(ns);
+
+	return 0;
+}
+
+static int igb_ptp_gettimex_82580(struct ptp_clock_info *ptp,
+				  struct timespec64 *ts,
+				  struct ptp_system_timestamp *sts)
+{
+	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
+					       ptp_caps);
+	struct e1000_hw *hw = &igb->hw;
+	unsigned long flags;
+	u32 lo, hi;
+	u64 ns;
+
+	spin_lock_irqsave(&igb->tmreg_lock, flags);
+
+	ptp_read_system_prets(sts);
+	rd32(E1000_SYSTIMR);
+	ptp_read_system_postts(sts);
+	lo = rd32(E1000_SYSTIML);
+	hi = rd32(E1000_SYSTIMH);
+
+	ns = timecounter_cyc2time(&igb->tc, ((u64)hi << 32) | lo);
 
 	spin_unlock_irqrestore(&igb->tmreg_lock, flags);
 
@@ -294,16 +330,22 @@ static int igb_ptp_gettime_82576(struct ptp_clock_info *ptp,
 	return 0;
 }
 
-static int igb_ptp_gettime_i210(struct ptp_clock_info *ptp,
-				struct timespec64 *ts)
+static int igb_ptp_gettimex_i210(struct ptp_clock_info *ptp,
+				 struct timespec64 *ts,
+				 struct ptp_system_timestamp *sts)
 {
 	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
 					       ptp_caps);
+	struct e1000_hw *hw = &igb->hw;
 	unsigned long flags;
 
 	spin_lock_irqsave(&igb->tmreg_lock, flags);
 
-	igb_ptp_read_i210(igb, ts);
+	ptp_read_system_prets(sts);
+	rd32(E1000_SYSTIMR);
+	ptp_read_system_postts(sts);
+	ts->tv_nsec = rd32(E1000_SYSTIML);
+	ts->tv_sec = rd32(E1000_SYSTIMH);
 
 	spin_unlock_irqrestore(&igb->tmreg_lock, flags);
 
@@ -656,9 +698,12 @@ static void igb_ptp_overflow_check(struct work_struct *work)
 	struct igb_adapter *igb =
 		container_of(work, struct igb_adapter, ptp_overflow_work.work);
 	struct timespec64 ts;
+	u64 ns;
 
-	igb->ptp_caps.gettime64(&igb->ptp_caps, &ts);
+	/* Update the timecounter */
+	ns = timecounter_read(&igb->tc);
 
+	ts = ns_to_timespec64(ns);
 	pr_debug("igb overflow check at %lld.%09lu\n",
 		 (long long) ts.tv_sec, ts.tv_nsec);
 
@@ -1124,7 +1169,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.pps = 0;
 		adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82576;
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
-		adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576;
+		adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_82576;
 		adapter->ptp_caps.settime64 = igb_ptp_settime_82576;
 		adapter->ptp_caps.enable = igb_ptp_feature_enable;
 		adapter->cc.read = igb_ptp_read_82576;
@@ -1143,7 +1188,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.pps = 0;
 		adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
-		adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576;
+		adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_82580;
 		adapter->ptp_caps.settime64 = igb_ptp_settime_82576;
 		adapter->ptp_caps.enable = igb_ptp_feature_enable;
 		adapter->cc.read = igb_ptp_read_82580;
@@ -1171,7 +1216,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.pin_config = adapter->sdp_config;
 		adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210;
-		adapter->ptp_caps.gettime64 = igb_ptp_gettime_i210;
+		adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_i210;
 		adapter->ptp_caps.settime64 = igb_ptp_settime_i210;
 		adapter->ptp_caps.enable = igb_ptp_feature_enable_i210;
 		adapter->ptp_caps.verify = igb_ptp_verify_pin;
-- 
cgit v1.2.3


From 018ed23ddc7aa80834f3953364363ac47ec8d127 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Fri, 9 Nov 2018 11:14:48 +0100
Subject: ixgbe: extend PTP gettime function to read system clock

This adds support for the PTP_SYS_OFFSET_EXTENDED ioctl.

Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Jacob Keller <jacob.e.keller@intel.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 54 ++++++++++++++++++++++------
 1 file changed, 44 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index b3e0d8bb5cbd..d81a50dc9535 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -443,22 +443,52 @@ static int ixgbe_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 }
 
 /**
- * ixgbe_ptp_gettime
+ * ixgbe_ptp_gettimex
  * @ptp: the ptp clock structure
- * @ts: timespec structure to hold the current time value
+ * @ts: timespec to hold the PHC timestamp
+ * @sts: structure to hold the system time before and after reading the PHC
  *
  * read the timecounter and return the correct value on ns,
  * after converting it into a struct timespec.
  */
-static int ixgbe_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int ixgbe_ptp_gettimex(struct ptp_clock_info *ptp,
+			      struct timespec64 *ts,
+			      struct ptp_system_timestamp *sts)
 {
 	struct ixgbe_adapter *adapter =
 		container_of(ptp, struct ixgbe_adapter, ptp_caps);
+	struct ixgbe_hw *hw = &adapter->hw;
 	unsigned long flags;
-	u64 ns;
+	u64 ns, stamp;
 
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
-	ns = timecounter_read(&adapter->hw_tc);
+
+	switch (adapter->hw.mac.type) {
+	case ixgbe_mac_X550:
+	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_x550em_a:
+		/* Upper 32 bits represent billions of cycles, lower 32 bits
+		 * represent cycles. However, we use timespec64_to_ns for the
+		 * correct math even though the units haven't been corrected
+		 * yet.
+		 */
+		ptp_read_system_prets(sts);
+		IXGBE_READ_REG(hw, IXGBE_SYSTIMR);
+		ptp_read_system_postts(sts);
+		ts->tv_nsec = IXGBE_READ_REG(hw, IXGBE_SYSTIML);
+		ts->tv_sec = IXGBE_READ_REG(hw, IXGBE_SYSTIMH);
+		stamp = timespec64_to_ns(ts);
+		break;
+	default:
+		ptp_read_system_prets(sts);
+		stamp = IXGBE_READ_REG(hw, IXGBE_SYSTIML);
+		ptp_read_system_postts(sts);
+		stamp |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) << 32;
+		break;
+	}
+
+	ns = timecounter_cyc2time(&adapter->hw_tc, stamp);
+
 	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
 
 	*ts = ns_to_timespec64(ns);
@@ -567,10 +597,14 @@ void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter)
 {
 	bool timeout = time_is_before_jiffies(adapter->last_overflow_check +
 					     IXGBE_OVERFLOW_PERIOD);
-	struct timespec64 ts;
+	unsigned long flags;
 
 	if (timeout) {
-		ixgbe_ptp_gettime(&adapter->ptp_caps, &ts);
+		/* Update the timecounter */
+		spin_lock_irqsave(&adapter->tmreg_lock, flags);
+		timecounter_read(&adapter->hw_tc);
+		spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+
 		adapter->last_overflow_check = jiffies;
 	}
 }
@@ -1216,7 +1250,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 		adapter->ptp_caps.pps = 1;
 		adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_82599;
 		adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
-		adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime;
+		adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex;
 		adapter->ptp_caps.settime64 = ixgbe_ptp_settime;
 		adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
 		adapter->ptp_setup_sdp = ixgbe_ptp_setup_sdp_x540;
@@ -1233,7 +1267,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 		adapter->ptp_caps.pps = 0;
 		adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_82599;
 		adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
-		adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime;
+		adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex;
 		adapter->ptp_caps.settime64 = ixgbe_ptp_settime;
 		adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
 		break;
@@ -1249,7 +1283,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 		adapter->ptp_caps.pps = 0;
 		adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_X550;
 		adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
-		adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime;
+		adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex;
 		adapter->ptp_caps.settime64 = ixgbe_ptp_settime;
 		adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
 		adapter->ptp_setup_sdp = NULL;
-- 
cgit v1.2.3


From 6fe42e228dc2eb169afcde6f7b70c28175527753 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Fri, 9 Nov 2018 11:14:49 +0100
Subject: tg3: extend PTP gettime function to read system clock

This adds support for the PTP_SYS_OFFSET_EXTENDED ioctl.

Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 89295306f161..ce44d208e137 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6135,10 +6135,16 @@ static int tg3_setup_phy(struct tg3 *tp, bool force_reset)
 }
 
 /* tp->lock must be held */
-static u64 tg3_refclk_read(struct tg3 *tp)
+static u64 tg3_refclk_read(struct tg3 *tp, struct ptp_system_timestamp *sts)
 {
-	u64 stamp = tr32(TG3_EAV_REF_CLCK_LSB);
-	return stamp | (u64)tr32(TG3_EAV_REF_CLCK_MSB) << 32;
+	u64 stamp;
+
+	ptp_read_system_prets(sts);
+	stamp = tr32(TG3_EAV_REF_CLCK_LSB);
+	ptp_read_system_postts(sts);
+	stamp |= (u64)tr32(TG3_EAV_REF_CLCK_MSB) << 32;
+
+	return stamp;
 }
 
 /* tp->lock must be held */
@@ -6229,13 +6235,14 @@ static int tg3_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	return 0;
 }
 
-static int tg3_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int tg3_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
+			    struct ptp_system_timestamp *sts)
 {
 	u64 ns;
 	struct tg3 *tp = container_of(ptp, struct tg3, ptp_info);
 
 	tg3_full_lock(tp, 0);
-	ns = tg3_refclk_read(tp);
+	ns = tg3_refclk_read(tp, sts);
 	ns += tp->ptp_adjust;
 	tg3_full_unlock(tp);
 
@@ -6330,7 +6337,7 @@ static const struct ptp_clock_info tg3_ptp_caps = {
 	.pps		= 0,
 	.adjfreq	= tg3_ptp_adjfreq,
 	.adjtime	= tg3_ptp_adjtime,
-	.gettime64	= tg3_ptp_gettime,
+	.gettimex64	= tg3_ptp_gettimex,
 	.settime64	= tg3_ptp_settime,
 	.enable		= tg3_ptp_enable,
 };
-- 
cgit v1.2.3


From 560f1ba4d8e8cb70f59b704a6edfa094b9bc0266 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 9 Nov 2018 18:50:00 -0800
Subject: nfp: use the new __netdev_tx_sent_queue() BQL optimisation

__netdev_tx_sent_queue() was added in commit e59020abf0f
("net: bql: add __netdev_tx_sent_queue()") and allows for
better GSO performance.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index e00d5a2a41ee..a0343f25068a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -890,8 +890,6 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 		u64_stats_update_end(&r_vec->tx_sync);
 	}
 
-	netdev_tx_sent_queue(nd_q, txbuf->real_len);
-
 	skb_tx_timestamp(skb);
 
 	tx_ring->wr_p += nr_frags + 1;
@@ -899,7 +897,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 		nfp_net_tx_ring_stop(nd_q, tx_ring);
 
 	tx_ring->wr_ptr_add += nr_frags + 1;
-	if (!skb->xmit_more || netif_xmit_stopped(nd_q))
+	if (__netdev_tx_sent_queue(nd_q, txbuf->real_len, skb->xmit_more))
 		nfp_net_tx_xmit_more_flush(tx_ring);
 
 	return NETDEV_TX_OK;
-- 
cgit v1.2.3


From 029a374348807222a872ba4baaf6e3e96846aa16 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 9 Nov 2018 15:52:45 +0100
Subject: udp6: cleanup stats accounting in recvmsg()

In the udp6 code path, we needed multiple tests to select the correct
mib to be updated. Since we touch at least a counter at each iteration,
it's convenient to use the recently introduced __UDPX_MIB() helper once
and remove some code duplication.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 32 +++++++-------------------------
 1 file changed, 7 insertions(+), 25 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 0c0cb1611aef..dde51fc7ac16 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -326,6 +326,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
 	bool checksum_valid = false;
+	struct udp_mib *mib;
 	int is_udp4;
 
 	if (flags & MSG_ERRQUEUE)
@@ -349,6 +350,7 @@ try_again:
 		msg->msg_flags |= MSG_TRUNC;
 
 	is_udp4 = (skb->protocol == htons(ETH_P_IP));
+	mib = __UDPX_MIB(sk, is_udp4);
 
 	/*
 	 * If checksum is needed at all, try to do it while copying the
@@ -377,24 +379,13 @@ try_again:
 	if (unlikely(err)) {
 		if (!peeked) {
 			atomic_inc(&sk->sk_drops);
-			if (is_udp4)
-				UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
-					      is_udplite);
-			else
-				UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
-					       is_udplite);
+			SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
 		}
 		kfree_skb(skb);
 		return err;
 	}
-	if (!peeked) {
-		if (is_udp4)
-			UDP_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS,
-				      is_udplite);
-		else
-			UDP6_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS,
-				       is_udplite);
-	}
+	if (!peeked)
+		SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS);
 
 	sock_recv_ts_and_drops(msg, sk, skb);
 
@@ -443,17 +434,8 @@ try_again:
 csum_copy_err:
 	if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags,
 				 udp_skb_destructor)) {
-		if (is_udp4) {
-			UDP_INC_STATS(sock_net(sk),
-				      UDP_MIB_CSUMERRORS, is_udplite);
-			UDP_INC_STATS(sock_net(sk),
-				      UDP_MIB_INERRORS, is_udplite);
-		} else {
-			UDP6_INC_STATS(sock_net(sk),
-				       UDP_MIB_CSUMERRORS, is_udplite);
-			UDP6_INC_STATS(sock_net(sk),
-				       UDP_MIB_INERRORS, is_udplite);
-		}
+		SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS);
+		SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
 	}
 	kfree_skb(skb);
 
-- 
cgit v1.2.3


From d7f5a9d89a55af68908a013811404971f88d661e Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Fri, 9 Nov 2018 15:26:45 +0000
Subject: dpaa2-eth: defer probe on object allocate

The fsl_mc_object_allocate function can fail because not all allocatable
objects are probed by the fsl_mc_allocator at the call time. Defer the
dpaa2-eth probe when this happens.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 32 ++++++++++++++++--------
 1 file changed, 22 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 88f7acce38dc..bdfb13b71998 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1434,8 +1434,11 @@ static struct fsl_mc_device *setup_dpcon(struct dpaa2_eth_priv *priv)
 	err = fsl_mc_object_allocate(to_fsl_mc_device(dev),
 				     FSL_MC_POOL_DPCON, &dpcon);
 	if (err) {
-		dev_info(dev, "Not enough DPCONs, will go on as-is\n");
-		return NULL;
+		if (err == -ENXIO)
+			err = -EPROBE_DEFER;
+		else
+			dev_info(dev, "Not enough DPCONs, will go on as-is\n");
+		return ERR_PTR(err);
 	}
 
 	err = dpcon_open(priv->mc_io, 0, dpcon->obj_desc.id, &dpcon->mc_handle);
@@ -1493,8 +1496,10 @@ alloc_channel(struct dpaa2_eth_priv *priv)
 		return NULL;
 
 	channel->dpcon = setup_dpcon(priv);
-	if (!channel->dpcon)
+	if (IS_ERR_OR_NULL(channel->dpcon)) {
+		err = PTR_ERR(channel->dpcon);
 		goto err_setup;
+	}
 
 	err = dpcon_get_attributes(priv->mc_io, 0, channel->dpcon->mc_handle,
 				   &attr);
@@ -1513,7 +1518,7 @@ err_get_attr:
 	free_dpcon(priv, channel->dpcon);
 err_setup:
 	kfree(channel);
-	return NULL;
+	return ERR_PTR(err);
 }
 
 static void free_channel(struct dpaa2_eth_priv *priv,
@@ -1547,10 +1552,11 @@ static int setup_dpio(struct dpaa2_eth_priv *priv)
 	for_each_online_cpu(i) {
 		/* Try to allocate a channel */
 		channel = alloc_channel(priv);
-		if (!channel) {
-			dev_info(dev,
-				 "No affine channel for cpu %d and above\n", i);
-			err = -ENODEV;
+		if (IS_ERR_OR_NULL(channel)) {
+			err = PTR_ERR(channel);
+			if (err != -EPROBE_DEFER)
+				dev_info(dev,
+					 "No affine channel for cpu %d and above\n", i);
 			goto err_alloc_ch;
 		}
 
@@ -1608,9 +1614,12 @@ err_set_cdan:
 err_service_reg:
 	free_channel(priv, channel);
 err_alloc_ch:
+	if (err == -EPROBE_DEFER)
+		return err;
+
 	if (cpumask_empty(&priv->dpio_cpumask)) {
 		dev_err(dev, "No cpu with an affine DPIO/DPCON\n");
-		return err;
+		return -ENODEV;
 	}
 
 	dev_info(dev, "Cores %*pbl available for processing ingress traffic\n",
@@ -1732,7 +1741,10 @@ static int setup_dpbp(struct dpaa2_eth_priv *priv)
 	err = fsl_mc_object_allocate(to_fsl_mc_device(dev), FSL_MC_POOL_DPBP,
 				     &dpbp_dev);
 	if (err) {
-		dev_err(dev, "DPBP device allocation failed\n");
+		if (err == -ENXIO)
+			err = -EPROBE_DEFER;
+		else
+			dev_err(dev, "DPBP device allocation failed\n");
 		return err;
 	}
 
-- 
cgit v1.2.3


From 5500598abbfb5b46201b9768bd9ea873a5eeaece Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Fri, 9 Nov 2018 15:26:46 +0000
Subject: dpaa2-ptp: defer probe when portal allocation failed

The fsl_mc_portal_allocate can fail when the requested MC portals are
not yet probed by the fsl_mc_allocator. In this situation, the driver
should defer the probe.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
index 84b942b1eccc..9b150db3b510 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
@@ -140,7 +140,10 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev)
 
 	err = fsl_mc_portal_allocate(mc_dev, 0, &mc_dev->mc_io);
 	if (err) {
-		dev_err(dev, "fsl_mc_portal_allocate err %d\n", err);
+		if (err == -ENXIO)
+			err = -EPROBE_DEFER;
+		else
+			dev_err(dev, "fsl_mc_portal_allocate err %d\n", err);
 		goto err_exit;
 	}
 
-- 
cgit v1.2.3


From 695bce8fd8e994999f40ee279e2fa9979cbae87a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 9 Nov 2018 18:35:52 +0100
Subject: net: phy: improve struct phy_device member interrupts handling

As a heritage from the very early days of phylib member interrupts is
defined as u32 even though it's just a flag whether interrupts are
enabled. So we can change it to a bitfield member. In addition change
the code dealing with this member in a way that it's clear we're
dealing with a bool value.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c |  4 ++--
 include/linux/phy.h   | 10 +++++-----
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index dd5bff955128..8dac890f32bf 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -115,9 +115,9 @@ static int phy_clear_interrupt(struct phy_device *phydev)
  *
  * Returns 0 on success or < 0 on error.
  */
-static int phy_config_interrupt(struct phy_device *phydev, u32 interrupts)
+static int phy_config_interrupt(struct phy_device *phydev, bool interrupts)
 {
-	phydev->interrupts = interrupts;
+	phydev->interrupts = interrupts ? 1 : 0;
 	if (phydev->drv->config_intr)
 		return phydev->drv->config_intr(phydev);
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 2090277eac4f..3299ec6e69f3 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -263,8 +263,8 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev)
 void devm_mdiobus_free(struct device *dev, struct mii_bus *bus);
 struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
 
-#define PHY_INTERRUPT_DISABLED	0x0
-#define PHY_INTERRUPT_ENABLED	0x80000000
+#define PHY_INTERRUPT_DISABLED	false
+#define PHY_INTERRUPT_ENABLED	true
 
 /* PHY state machine states:
  *
@@ -410,6 +410,9 @@ struct phy_device {
 	/* The most recently read link state */
 	unsigned link:1;
 
+	/* Interrupts are enabled */
+	unsigned interrupts:1;
+
 	enum phy_state state;
 
 	u32 dev_flags;
@@ -425,9 +428,6 @@ struct phy_device {
 	int pause;
 	int asym_pause;
 
-	/* Enabled Interrupts */
-	u32 interrupts;
-
 	/* Union of PHY and Attached devices' supported modes */
 	/* See mii.h for more info */
 	u32 supported;
-- 
cgit v1.2.3


From 457937bd2e8e70d3a37eee3eaa45d86d169a6762 Mon Sep 17 00:00:00 2001
From: Kyle Roeschley <kyle.roeschley@ni.com>
Date: Fri, 9 Nov 2018 12:48:03 -0600
Subject: net: phy: leds: Don't make our own link speed names

The phy core provides a handy phy_speed_to_str() helper, so use that
instead of doing our own formatting of the different known link speeds.
To do this, increase PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE to 11 so we can fit
'Unsupported' if necessary.

Signed-off-by: Kyle Roeschley <kyle.roeschley@ni.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_led_triggers.c | 15 ++-------------
 include/linux/phy_led_triggers.h   |  2 +-
 2 files changed, 3 insertions(+), 14 deletions(-)

diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c
index 491efc1bf5c4..263385b75bba 100644
--- a/drivers/net/phy/phy_led_triggers.c
+++ b/drivers/net/phy/phy_led_triggers.c
@@ -67,7 +67,7 @@ void phy_led_trigger_change_speed(struct phy_device *phy)
 EXPORT_SYMBOL_GPL(phy_led_trigger_change_speed);
 
 static void phy_led_trigger_format_name(struct phy_device *phy, char *buf,
-					size_t size, char *suffix)
+					size_t size, const char *suffix)
 {
 	snprintf(buf, size, PHY_ID_FMT ":%s",
 		 phy->mdio.bus->id, phy->mdio.addr, suffix);
@@ -77,20 +77,9 @@ static int phy_led_trigger_register(struct phy_device *phy,
 				    struct phy_led_trigger *plt,
 				    unsigned int speed)
 {
-	char name_suffix[PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE];
-
 	plt->speed = speed;
-
-	if (speed < SPEED_1000)
-		snprintf(name_suffix, sizeof(name_suffix), "%dMbps", speed);
-	else if (speed == SPEED_2500)
-		snprintf(name_suffix, sizeof(name_suffix), "2.5Gbps");
-	else
-		snprintf(name_suffix, sizeof(name_suffix), "%dGbps",
-			 DIV_ROUND_CLOSEST(speed, 1000));
-
 	phy_led_trigger_format_name(phy, plt->name, sizeof(plt->name),
-				    name_suffix);
+				    phy_speed_to_str(speed));
 	plt->trigger.name = plt->name;
 
 	return led_trigger_register(&plt->trigger);
diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h
index b37b05bfd1a6..4587ce362535 100644
--- a/include/linux/phy_led_triggers.h
+++ b/include/linux/phy_led_triggers.h
@@ -20,7 +20,7 @@ struct phy_device;
 #include <linux/leds.h>
 #include <linux/phy.h>
 
-#define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE	10
+#define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE	11
 
 #define PHY_LINK_LED_TRIGGER_NAME_SIZE (MII_BUS_ID_SIZE + \
 				       FIELD_SIZEOF(struct mdio_device, addr)+\
-- 
cgit v1.2.3


From 12ceaf8864c269467846379ebea56a2b996f9e3b Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 9 Nov 2018 21:18:48 -0800
Subject: infiniband: nes: Fix more direct skb list accesses.

The following:

	skb = skb->next;
	...
	if (skb == (struct sk_buff *)queue)

is transformed into:

	skb = skb_peek_next(skb, queue);
	...
	if (!skb)

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/nes/nes_mgt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/nes/nes_mgt.c b/drivers/infiniband/hw/nes/nes_mgt.c
index e96ffff61c3a..fc0c191014e9 100644
--- a/drivers/infiniband/hw/nes/nes_mgt.c
+++ b/drivers/infiniband/hw/nes/nes_mgt.c
@@ -223,11 +223,11 @@ static struct sk_buff *nes_get_next_skb(struct nes_device *nesdev, struct nes_qp
 		}
 
 		old_skb = skb;
-		skb = skb->next;
+		skb = skb_peek_next(skb, &nesqp->pau_list);
 		skb_unlink(old_skb, &nesqp->pau_list);
 		nes_mgt_free_skb(nesdev, old_skb, PCI_DMA_TODEVICE);
 		nes_rem_ref_cm_node(nesqp->cm_node);
-		if (skb == (struct sk_buff *)&nesqp->pau_list)
+		if (!skb)
 			goto out;
 	}
 	return skb;
-- 
cgit v1.2.3


From 6083e28aa02d7c9e6b87f8b944e92793094ae047 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Sat, 10 Nov 2018 19:55:34 +0100
Subject: OVS: remove VLAN_TAG_PRESENT - fixup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It turns out I missed one VLAN_TAG_PRESENT in OVS code while rebasing.
This fixes it.

Fixes: 9df46aefafa6 ("OVS: remove use of VLAN_TAG_PRESENT")
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index fa393815991e..57e07768c9d1 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -597,7 +597,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 		 * skb_vlan_pop(), which will later shift the ethertype into
 		 * skb->protocol.
 		 */
-		if (key->eth.cvlan.tci & htons(VLAN_TAG_PRESENT))
+		if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK))
 			skb->protocol = key->eth.cvlan.tpid;
 		else
 			skb->protocol = key->eth.type;
-- 
cgit v1.2.3


From 1da6f5733853fb230265fe1a7d1b5373f13bf5ca Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 9 Nov 2018 13:03:24 +0000
Subject: nfp: bpf: move nfp_bpf_analyzer_ops from verifier.c to offload.c

We are about to add several new callbacks to the struct, all of them
defined in offload.c. Move the struct bpf_prog_offload_ops object in
that file. As a consequence, nfp_verify_insn() and nfp_finalize() can no
longer be static.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/bpf/main.h     |  4 ++++
 drivers/net/ethernet/netronome/nfp/bpf/offload.c  |  5 +++++
 drivers/net/ethernet/netronome/nfp/bpf/verifier.c | 11 +++--------
 3 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 7f591d71ab28..abdd93d14439 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -509,6 +509,10 @@ void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt);
 int nfp_bpf_jit(struct nfp_prog *prog);
 bool nfp_bpf_supported_opcode(u8 code);
 
+int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
+		    int prev_insn_idx);
+int nfp_bpf_finalize(struct bpf_verifier_env *env);
+
 extern const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops;
 
 struct netdev_bpf;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 07bdc1f61996..dc548bb4089e 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -601,3 +601,8 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 
 	return 0;
 }
+
+const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops = {
+	.insn_hook	= nfp_verify_insn,
+	.finalize	= nfp_bpf_finalize,
+};
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 99f977bfd8cc..337bb862ec1d 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -623,8 +623,8 @@ nfp_bpf_check_alu(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	return 0;
 }
 
-static int
-nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
+int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
+		    int prev_insn_idx)
 {
 	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
 	struct nfp_insn_meta *meta = nfp_prog->verifier_meta;
@@ -745,7 +745,7 @@ continue_subprog:
 	goto continue_subprog;
 }
 
-static int nfp_bpf_finalize(struct bpf_verifier_env *env)
+int nfp_bpf_finalize(struct bpf_verifier_env *env)
 {
 	struct bpf_subprog_info *info;
 	struct nfp_prog *nfp_prog;
@@ -788,8 +788,3 @@ static int nfp_bpf_finalize(struct bpf_verifier_env *env)
 
 	return 0;
 }
-
-const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops = {
-	.insn_hook	= nfp_verify_insn,
-	.finalize	= nfp_bpf_finalize,
-};
-- 
cgit v1.2.3


From 1385d755cfb42f596ef1cf9f5c761010ff3b34e7 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 9 Nov 2018 13:03:25 +0000
Subject: bpf: pass a struct with offload callbacks to bpf_offload_dev_create()

For passing device functions for offloaded eBPF programs, there used to
be no place where to store the pointer without making the non-offloaded
programs pay a memory price.

As a consequence, three functions were called with ndo_bpf() through
specific commands. Now that we have struct bpf_offload_dev, and since
none of those operations rely on RTNL, we can turn these three commands
into hooks inside the struct bpf_prog_offload_ops, and pass them as part
of bpf_offload_dev_create().

This commit effectively passes a pointer to the struct to
bpf_offload_dev_create(). We temporarily have two struct
bpf_prog_offload_ops instances, one under offdev->ops and one under
offload->dev_ops. The next patches will make the transition towards the
former, so that offload->dev_ops can be removed, and callbacks relying
on ndo_bpf() added to offdev->ops as well.

While at it, rename "nfp_bpf_analyzer_ops" as "nfp_bpf_dev_ops" (and
similarly for netdevsim).

Suggested-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/bpf/main.c    | 2 +-
 drivers/net/ethernet/netronome/nfp/bpf/main.h    | 2 +-
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 4 ++--
 drivers/net/netdevsim/bpf.c                      | 6 +++---
 include/linux/bpf.h                              | 3 ++-
 kernel/bpf/offload.c                             | 5 ++++-
 6 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 6243af0ab025..dccae0319204 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -465,7 +465,7 @@ static int nfp_bpf_init(struct nfp_app *app)
 		app->ctrl_mtu = nfp_bpf_ctrl_cmsg_mtu(bpf);
 	}
 
-	bpf->bpf_dev = bpf_offload_dev_create();
+	bpf->bpf_dev = bpf_offload_dev_create(&nfp_bpf_dev_ops);
 	err = PTR_ERR_OR_ZERO(bpf->bpf_dev);
 	if (err)
 		goto err_free_neutral_maps;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index abdd93d14439..941277936475 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -513,7 +513,7 @@ int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
 		    int prev_insn_idx);
 int nfp_bpf_finalize(struct bpf_verifier_env *env);
 
-extern const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops;
+extern const struct bpf_prog_offload_ops nfp_bpf_dev_ops;
 
 struct netdev_bpf;
 struct nfp_app;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index dc548bb4089e..2fca996a7e77 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -209,7 +209,7 @@ nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn,
 		goto err_free;
 
 	nfp_prog->verifier_meta = nfp_prog_first_meta(nfp_prog);
-	bpf->verifier.ops = &nfp_bpf_analyzer_ops;
+	bpf->verifier.ops = &nfp_bpf_dev_ops;
 
 	return 0;
 
@@ -602,7 +602,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 	return 0;
 }
 
-const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops = {
+const struct bpf_prog_offload_ops nfp_bpf_dev_ops = {
 	.insn_hook	= nfp_verify_insn,
 	.finalize	= nfp_bpf_finalize,
 };
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index cb3518474f0e..135aee864162 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -91,7 +91,7 @@ static int nsim_bpf_finalize(struct bpf_verifier_env *env)
 	return 0;
 }
 
-static const struct bpf_prog_offload_ops nsim_bpf_analyzer_ops = {
+static const struct bpf_prog_offload_ops nsim_bpf_dev_ops = {
 	.insn_hook	= nsim_bpf_verify_insn,
 	.finalize	= nsim_bpf_finalize,
 };
@@ -547,7 +547,7 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 		if (err)
 			return err;
 
-		bpf->verifier.ops = &nsim_bpf_analyzer_ops;
+		bpf->verifier.ops = &nsim_bpf_dev_ops;
 		return 0;
 	case BPF_OFFLOAD_TRANSLATE:
 		state = bpf->offload.prog->aux->offload->dev_priv;
@@ -599,7 +599,7 @@ int nsim_bpf_init(struct netdevsim *ns)
 		if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs))
 			return -ENOMEM;
 
-		ns->sdev->bpf_dev = bpf_offload_dev_create();
+		ns->sdev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops);
 		err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev);
 		if (err)
 			return err;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b6a296e01f6a..c0197c37b2b2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -692,7 +692,8 @@ int bpf_map_offload_get_next_key(struct bpf_map *map,
 
 bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map);
 
-struct bpf_offload_dev *bpf_offload_dev_create(void);
+struct bpf_offload_dev *
+bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops);
 void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev);
 int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
 				    struct net_device *netdev);
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 8e93c47f0779..d513fbf9ca53 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -33,6 +33,7 @@
 static DECLARE_RWSEM(bpf_devs_lock);
 
 struct bpf_offload_dev {
+	const struct bpf_prog_offload_ops *ops;
 	struct list_head netdevs;
 };
 
@@ -655,7 +656,8 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
 
-struct bpf_offload_dev *bpf_offload_dev_create(void)
+struct bpf_offload_dev *
+bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops)
 {
 	struct bpf_offload_dev *offdev;
 	int err;
@@ -673,6 +675,7 @@ struct bpf_offload_dev *bpf_offload_dev_create(void)
 	if (!offdev)
 		return ERR_PTR(-ENOMEM);
 
+	offdev->ops = ops;
 	INIT_LIST_HEAD(&offdev->netdevs);
 
 	return offdev;
-- 
cgit v1.2.3


From 341b3e7b7b89315c43d262da3199098bcf9bbe57 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 9 Nov 2018 13:03:26 +0000
Subject: bpf: call verify_insn from its callback in struct bpf_offload_dev

We intend to remove the dev_ops in struct bpf_prog_offload, and to only
keep the ops in struct bpf_offload_dev instead, which is accessible from
more locations for passing function pointers.

But dev_ops is used for calling the verify_insn hook. Switch to the
newly added ops in struct bpf_prog_offload instead.

To avoid table lookups for each eBPF instruction to verify, we remember
the offdev attached to a netdev and modify bpf_offload_find_netdev() to
avoid performing more than once a lookup for a given offload object.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h  | 1 +
 kernel/bpf/offload.c | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c0197c37b2b2..672714cd904f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -273,6 +273,7 @@ struct bpf_prog_offload_ops {
 struct bpf_prog_offload {
 	struct bpf_prog		*prog;
 	struct net_device	*netdev;
+	struct bpf_offload_dev	*offdev;
 	void			*dev_priv;
 	struct list_head	offloads;
 	bool			dev_state;
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index d513fbf9ca53..2cd3c0d0417b 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -107,6 +107,7 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
 		err = -EINVAL;
 		goto err_unlock;
 	}
+	offload->offdev = ondev->offdev;
 	prog->aux->offload = offload;
 	list_add_tail(&offload->offloads, &ondev->progs);
 	dev_put(offload->netdev);
@@ -167,7 +168,8 @@ int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
 	down_read(&bpf_devs_lock);
 	offload = env->prog->aux->offload;
 	if (offload)
-		ret = offload->dev_ops->insn_hook(env, insn_idx, prev_insn_idx);
+		ret = offload->offdev->ops->insn_hook(env, insn_idx,
+						      prev_insn_idx);
 	up_read(&bpf_devs_lock);
 
 	return ret;
-- 
cgit v1.2.3


From 6dc18fa6f4cad69c892d6fb9499f7e41c6a88a8e Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 9 Nov 2018 13:03:27 +0000
Subject: bpf: call finalize() from its callback in struct bpf_offload_dev

In a way similar to the change previously brought to the verify_insn
hook, switch to the newly added ops in struct bpf_prog_offload for
calling the functions used to perform final verification steps for
offloaded programs.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/offload.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 2cd3c0d0417b..2c88cb4ddfd8 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -183,8 +183,8 @@ int bpf_prog_offload_finalize(struct bpf_verifier_env *env)
 	down_read(&bpf_devs_lock);
 	offload = env->prog->aux->offload;
 	if (offload) {
-		if (offload->dev_ops->finalize)
-			ret = offload->dev_ops->finalize(env);
+		if (offload->offdev->ops->finalize)
+			ret = offload->offdev->ops->finalize(env);
 		else
 			ret = 0;
 	}
-- 
cgit v1.2.3


From 00db12c3d141356a4d1e6b6f688e0d5ed3b1f757 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 9 Nov 2018 13:03:28 +0000
Subject: bpf: call verifier_prep from its callback in struct bpf_offload_dev

In a way similar to the change previously brought to the verify_insn
hook and to the finalize callback, switch to the newly added ops in
struct bpf_prog_offload for calling the functions used to prepare driver
verifiers.

Since the dev_ops pointer in struct bpf_prog_offload is no longer used
by any callback, we can now remove it from struct bpf_prog_offload.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 11 ++++----
 drivers/net/netdevsim/bpf.c                      | 32 +++++++++++++-----------
 include/linux/bpf.h                              |  2 +-
 include/linux/netdevice.h                        |  6 -----
 kernel/bpf/offload.c                             | 22 +++++++---------
 5 files changed, 32 insertions(+), 41 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 2fca996a7e77..16a3a9c55852 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -188,10 +188,11 @@ static void nfp_prog_free(struct nfp_prog *nfp_prog)
 }
 
 static int
-nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn,
-		      struct netdev_bpf *bpf)
+nfp_bpf_verifier_prep(struct net_device *netdev, struct bpf_verifier_env *env)
 {
-	struct bpf_prog *prog = bpf->verifier.prog;
+	struct nfp_net *nn = netdev_priv(netdev);
+	struct bpf_prog *prog = env->prog;
+	struct nfp_app *app = nn->app;
 	struct nfp_prog *nfp_prog;
 	int ret;
 
@@ -209,7 +210,6 @@ nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn,
 		goto err_free;
 
 	nfp_prog->verifier_meta = nfp_prog_first_meta(nfp_prog);
-	bpf->verifier.ops = &nfp_bpf_dev_ops;
 
 	return 0;
 
@@ -422,8 +422,6 @@ nfp_bpf_map_free(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap)
 int nfp_ndo_bpf(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *bpf)
 {
 	switch (bpf->command) {
-	case BPF_OFFLOAD_VERIFIER_PREP:
-		return nfp_bpf_verifier_prep(app, nn, bpf);
 	case BPF_OFFLOAD_TRANSLATE:
 		return nfp_bpf_translate(nn, bpf->offload.prog);
 	case BPF_OFFLOAD_DESTROY:
@@ -605,4 +603,5 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 const struct bpf_prog_offload_ops nfp_bpf_dev_ops = {
 	.insn_hook	= nfp_verify_insn,
 	.finalize	= nfp_bpf_finalize,
+	.prepare	= nfp_bpf_verifier_prep,
 };
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 135aee864162..d045b7d666d9 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -91,11 +91,6 @@ static int nsim_bpf_finalize(struct bpf_verifier_env *env)
 	return 0;
 }
 
-static const struct bpf_prog_offload_ops nsim_bpf_dev_ops = {
-	.insn_hook	= nsim_bpf_verify_insn,
-	.finalize	= nsim_bpf_finalize,
-};
-
 static bool nsim_xdp_offload_active(struct netdevsim *ns)
 {
 	return ns->xdp_hw.prog;
@@ -263,6 +258,17 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
 	return 0;
 }
 
+static int
+nsim_bpf_verifier_prep(struct net_device *dev, struct bpf_verifier_env *env)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (!ns->bpf_bind_accept)
+		return -EOPNOTSUPP;
+
+	return nsim_bpf_create_prog(ns, env->prog);
+}
+
 static void nsim_bpf_destroy_prog(struct bpf_prog *prog)
 {
 	struct nsim_bpf_bound_prog *state;
@@ -275,6 +281,12 @@ static void nsim_bpf_destroy_prog(struct bpf_prog *prog)
 	kfree(state);
 }
 
+static const struct bpf_prog_offload_ops nsim_bpf_dev_ops = {
+	.insn_hook	= nsim_bpf_verify_insn,
+	.finalize	= nsim_bpf_finalize,
+	.prepare	= nsim_bpf_verifier_prep,
+};
+
 static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 {
 	if (bpf->prog && bpf->prog->aux->offload) {
@@ -539,16 +551,6 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 	ASSERT_RTNL();
 
 	switch (bpf->command) {
-	case BPF_OFFLOAD_VERIFIER_PREP:
-		if (!ns->bpf_bind_accept)
-			return -EOPNOTSUPP;
-
-		err = nsim_bpf_create_prog(ns, bpf->verifier.prog);
-		if (err)
-			return err;
-
-		bpf->verifier.ops = &nsim_bpf_dev_ops;
-		return 0;
 	case BPF_OFFLOAD_TRANSLATE:
 		state = bpf->offload.prog->aux->offload->dev_priv;
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 672714cd904f..f250494a4f56 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -268,6 +268,7 @@ struct bpf_prog_offload_ops {
 	int (*insn_hook)(struct bpf_verifier_env *env,
 			 int insn_idx, int prev_insn_idx);
 	int (*finalize)(struct bpf_verifier_env *env);
+	int (*prepare)(struct net_device *netdev, struct bpf_verifier_env *env);
 };
 
 struct bpf_prog_offload {
@@ -277,7 +278,6 @@ struct bpf_prog_offload {
 	void			*dev_priv;
 	struct list_head	offloads;
 	bool			dev_state;
-	const struct bpf_prog_offload_ops *dev_ops;
 	void			*jited_image;
 	u32			jited_len;
 };
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 857f8abf7b91..0fa2c2744928 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -863,7 +863,6 @@ enum bpf_netdev_command {
 	XDP_QUERY_PROG,
 	XDP_QUERY_PROG_HW,
 	/* BPF program for offload callbacks, invoked at program load time. */
-	BPF_OFFLOAD_VERIFIER_PREP,
 	BPF_OFFLOAD_TRANSLATE,
 	BPF_OFFLOAD_DESTROY,
 	BPF_OFFLOAD_MAP_ALLOC,
@@ -891,11 +890,6 @@ struct netdev_bpf {
 			/* flags with which program was installed */
 			u32 prog_flags;
 		};
-		/* BPF_OFFLOAD_VERIFIER_PREP */
-		struct {
-			struct bpf_prog *prog;
-			const struct bpf_prog_offload_ops *ops; /* callee set */
-		} verifier;
 		/* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */
 		struct {
 			struct bpf_prog *prog;
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 2c88cb4ddfd8..1f7ac00a494d 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -142,21 +142,17 @@ static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd,
 
 int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env)
 {
-	struct netdev_bpf data = {};
-	int err;
-
-	data.verifier.prog = env->prog;
+	struct bpf_prog_offload *offload;
+	int ret = -ENODEV;
 
-	rtnl_lock();
-	err = __bpf_offload_ndo(env->prog, BPF_OFFLOAD_VERIFIER_PREP, &data);
-	if (err)
-		goto exit_unlock;
+	down_read(&bpf_devs_lock);
+	offload = env->prog->aux->offload;
+	if (offload)
+		ret = offload->offdev->ops->prepare(offload->netdev, env);
+	offload->dev_state = !ret;
+	up_read(&bpf_devs_lock);
 
-	env->prog->aux->offload->dev_ops = data.verifier.ops;
-	env->prog->aux->offload->dev_state = true;
-exit_unlock:
-	rtnl_unlock();
-	return err;
+	return ret;
 }
 
 int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
-- 
cgit v1.2.3


From b07ade27e93360197e453e5ca80eebdc9099dcb5 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 9 Nov 2018 13:03:29 +0000
Subject: bpf: pass translate() as a callback and remove its ndo_bpf subcommand

As part of the transition from ndo_bpf() to callbacks attached to struct
bpf_offload_dev for some of the eBPF offload operations, move the
functions related to code translation to the struct and remove the
subcommand that was used to call them through the NDO.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 11 +++--------
 drivers/net/netdevsim/bpf.c                      | 14 +++++++++-----
 include/linux/bpf.h                              |  1 +
 include/linux/netdevice.h                        |  3 +--
 kernel/bpf/offload.c                             | 14 +++++++-------
 5 files changed, 21 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 16a3a9c55852..8653a2189c19 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -33,9 +33,6 @@ nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 	struct nfp_bpf_neutral_map *record;
 	int err;
 
-	/* Map record paths are entered via ndo, update side is protected. */
-	ASSERT_RTNL();
-
 	/* Reuse path - other offloaded program is already tracking this map. */
 	record = rhashtable_lookup_fast(&bpf->maps_neutral, &map->id,
 					nfp_bpf_maps_neutral_params);
@@ -84,8 +81,6 @@ nfp_map_ptrs_forget(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog)
 	bool freed = false;
 	int i;
 
-	ASSERT_RTNL();
-
 	for (i = 0; i < nfp_prog->map_records_cnt; i++) {
 		if (--nfp_prog->map_records[i]->count) {
 			nfp_prog->map_records[i] = NULL;
@@ -219,9 +214,10 @@ err_free:
 	return ret;
 }
 
-static int nfp_bpf_translate(struct nfp_net *nn, struct bpf_prog *prog)
+static int nfp_bpf_translate(struct net_device *netdev, struct bpf_prog *prog)
 {
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
+	struct nfp_net *nn = netdev_priv(netdev);
 	unsigned int max_instr;
 	int err;
 
@@ -422,8 +418,6 @@ nfp_bpf_map_free(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap)
 int nfp_ndo_bpf(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *bpf)
 {
 	switch (bpf->command) {
-	case BPF_OFFLOAD_TRANSLATE:
-		return nfp_bpf_translate(nn, bpf->offload.prog);
 	case BPF_OFFLOAD_DESTROY:
 		return nfp_bpf_destroy(nn, bpf->offload.prog);
 	case BPF_OFFLOAD_MAP_ALLOC:
@@ -604,4 +598,5 @@ const struct bpf_prog_offload_ops nfp_bpf_dev_ops = {
 	.insn_hook	= nfp_verify_insn,
 	.finalize	= nfp_bpf_finalize,
 	.prepare	= nfp_bpf_verifier_prep,
+	.translate	= nfp_bpf_translate,
 };
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index d045b7d666d9..30c2cd516d1c 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -269,6 +269,14 @@ nsim_bpf_verifier_prep(struct net_device *dev, struct bpf_verifier_env *env)
 	return nsim_bpf_create_prog(ns, env->prog);
 }
 
+static int nsim_bpf_translate(struct net_device *dev, struct bpf_prog *prog)
+{
+	struct nsim_bpf_bound_prog *state = prog->aux->offload->dev_priv;
+
+	state->state = "xlated";
+	return 0;
+}
+
 static void nsim_bpf_destroy_prog(struct bpf_prog *prog)
 {
 	struct nsim_bpf_bound_prog *state;
@@ -285,6 +293,7 @@ static const struct bpf_prog_offload_ops nsim_bpf_dev_ops = {
 	.insn_hook	= nsim_bpf_verify_insn,
 	.finalize	= nsim_bpf_finalize,
 	.prepare	= nsim_bpf_verifier_prep,
+	.translate	= nsim_bpf_translate,
 };
 
 static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
@@ -551,11 +560,6 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 	ASSERT_RTNL();
 
 	switch (bpf->command) {
-	case BPF_OFFLOAD_TRANSLATE:
-		state = bpf->offload.prog->aux->offload->dev_priv;
-
-		state->state = "xlated";
-		return 0;
 	case BPF_OFFLOAD_DESTROY:
 		nsim_bpf_destroy_prog(bpf->offload.prog);
 		return 0;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f250494a4f56..d1eb3c8a3fa9 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -269,6 +269,7 @@ struct bpf_prog_offload_ops {
 			 int insn_idx, int prev_insn_idx);
 	int (*finalize)(struct bpf_verifier_env *env);
 	int (*prepare)(struct net_device *netdev, struct bpf_verifier_env *env);
+	int (*translate)(struct net_device *netdev, struct bpf_prog *prog);
 };
 
 struct bpf_prog_offload {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0fa2c2744928..27499127e038 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -863,7 +863,6 @@ enum bpf_netdev_command {
 	XDP_QUERY_PROG,
 	XDP_QUERY_PROG_HW,
 	/* BPF program for offload callbacks, invoked at program load time. */
-	BPF_OFFLOAD_TRANSLATE,
 	BPF_OFFLOAD_DESTROY,
 	BPF_OFFLOAD_MAP_ALLOC,
 	BPF_OFFLOAD_MAP_FREE,
@@ -890,7 +889,7 @@ struct netdev_bpf {
 			/* flags with which program was installed */
 			u32 prog_flags;
 		};
-		/* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */
+		/* BPF_OFFLOAD_DESTROY */
 		struct {
 			struct bpf_prog *prog;
 		} offload;
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 1f7ac00a494d..ae0167366c12 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -219,14 +219,14 @@ void bpf_prog_offload_destroy(struct bpf_prog *prog)
 
 static int bpf_prog_offload_translate(struct bpf_prog *prog)
 {
-	struct netdev_bpf data = {};
-	int ret;
-
-	data.offload.prog = prog;
+	struct bpf_prog_offload *offload;
+	int ret = -ENODEV;
 
-	rtnl_lock();
-	ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data);
-	rtnl_unlock();
+	down_read(&bpf_devs_lock);
+	offload = prog->aux->offload;
+	if (offload)
+		ret = offload->offdev->ops->translate(offload->netdev, prog);
+	up_read(&bpf_devs_lock);
 
 	return ret;
 }
-- 
cgit v1.2.3


From eb9119471efbf730c8f830f706026b486eb701dd Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 9 Nov 2018 13:03:30 +0000
Subject: bpf: pass destroy() as a callback and remove its ndo_bpf subcommand

As part of the transition from ndo_bpf() to callbacks attached to struct
bpf_offload_dev for some of the eBPF offload operations, move the
functions related to program destruction to the struct and remove the
subcommand that was used to call them through the NDO.

Remove function __bpf_offload_ndo(), which is no longer used.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/bpf/offload.c |  7 ++-----
 drivers/net/netdevsim/bpf.c                      |  4 +---
 include/linux/bpf.h                              |  1 +
 include/linux/netdevice.h                        |  5 -----
 kernel/bpf/offload.c                             | 24 +-----------------------
 5 files changed, 5 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 8653a2189c19..91085cc3c843 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -238,15 +238,13 @@ static int nfp_bpf_translate(struct net_device *netdev, struct bpf_prog *prog)
 	return nfp_map_ptrs_record(nfp_prog->bpf, nfp_prog, prog);
 }
 
-static int nfp_bpf_destroy(struct nfp_net *nn, struct bpf_prog *prog)
+static void nfp_bpf_destroy(struct bpf_prog *prog)
 {
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
 
 	kvfree(nfp_prog->prog);
 	nfp_map_ptrs_forget(nfp_prog->bpf, nfp_prog);
 	nfp_prog_free(nfp_prog);
-
-	return 0;
 }
 
 /* Atomic engine requires values to be in big endian, we need to byte swap
@@ -418,8 +416,6 @@ nfp_bpf_map_free(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap)
 int nfp_ndo_bpf(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *bpf)
 {
 	switch (bpf->command) {
-	case BPF_OFFLOAD_DESTROY:
-		return nfp_bpf_destroy(nn, bpf->offload.prog);
 	case BPF_OFFLOAD_MAP_ALLOC:
 		return nfp_bpf_map_alloc(app->priv, bpf->offmap);
 	case BPF_OFFLOAD_MAP_FREE:
@@ -599,4 +595,5 @@ const struct bpf_prog_offload_ops nfp_bpf_dev_ops = {
 	.finalize	= nfp_bpf_finalize,
 	.prepare	= nfp_bpf_verifier_prep,
 	.translate	= nfp_bpf_translate,
+	.destroy	= nfp_bpf_destroy,
 };
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 30c2cd516d1c..33e3d54c3a0a 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -294,6 +294,7 @@ static const struct bpf_prog_offload_ops nsim_bpf_dev_ops = {
 	.finalize	= nsim_bpf_finalize,
 	.prepare	= nsim_bpf_verifier_prep,
 	.translate	= nsim_bpf_translate,
+	.destroy	= nsim_bpf_destroy_prog,
 };
 
 static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
@@ -560,9 +561,6 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 	ASSERT_RTNL();
 
 	switch (bpf->command) {
-	case BPF_OFFLOAD_DESTROY:
-		nsim_bpf_destroy_prog(bpf->offload.prog);
-		return 0;
 	case XDP_QUERY_PROG:
 		return xdp_attachment_query(&ns->xdp, bpf);
 	case XDP_QUERY_PROG_HW:
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d1eb3c8a3fa9..867d2801db64 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -270,6 +270,7 @@ struct bpf_prog_offload_ops {
 	int (*finalize)(struct bpf_verifier_env *env);
 	int (*prepare)(struct net_device *netdev, struct bpf_verifier_env *env);
 	int (*translate)(struct net_device *netdev, struct bpf_prog *prog);
+	void (*destroy)(struct bpf_prog *prog);
 };
 
 struct bpf_prog_offload {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 27499127e038..17d52a647fe5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -863,7 +863,6 @@ enum bpf_netdev_command {
 	XDP_QUERY_PROG,
 	XDP_QUERY_PROG_HW,
 	/* BPF program for offload callbacks, invoked at program load time. */
-	BPF_OFFLOAD_DESTROY,
 	BPF_OFFLOAD_MAP_ALLOC,
 	BPF_OFFLOAD_MAP_FREE,
 	XDP_QUERY_XSK_UMEM,
@@ -889,10 +888,6 @@ struct netdev_bpf {
 			/* flags with which program was installed */
 			u32 prog_flags;
 		};
-		/* BPF_OFFLOAD_DESTROY */
-		struct {
-			struct bpf_prog *prog;
-		} offload;
 		/* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */
 		struct {
 			struct bpf_offloaded_map *offmap;
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index ae0167366c12..d665e75a0ac3 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -123,23 +123,6 @@ err_maybe_put:
 	return err;
 }
 
-static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd,
-			     struct netdev_bpf *data)
-{
-	struct bpf_prog_offload *offload = prog->aux->offload;
-	struct net_device *netdev;
-
-	ASSERT_RTNL();
-
-	if (!offload)
-		return -ENODEV;
-	netdev = offload->netdev;
-
-	data->command = cmd;
-
-	return netdev->netdev_ops->ndo_bpf(netdev, data);
-}
-
 int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env)
 {
 	struct bpf_prog_offload *offload;
@@ -192,12 +175,9 @@ int bpf_prog_offload_finalize(struct bpf_verifier_env *env)
 static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
 {
 	struct bpf_prog_offload *offload = prog->aux->offload;
-	struct netdev_bpf data = {};
-
-	data.offload.prog = prog;
 
 	if (offload->dev_state)
-		WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data));
+		offload->offdev->ops->destroy(prog);
 
 	/* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */
 	bpf_prog_free_id(prog, true);
@@ -209,12 +189,10 @@ static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
 
 void bpf_prog_offload_destroy(struct bpf_prog *prog)
 {
-	rtnl_lock();
 	down_write(&bpf_devs_lock);
 	if (prog->aux->offload)
 		__bpf_prog_offload_destroy(prog);
 	up_write(&bpf_devs_lock);
-	rtnl_unlock();
 }
 
 static int bpf_prog_offload_translate(struct bpf_prog *prog)
-- 
cgit v1.2.3


From a40a26322a83d4a26a99ad2616cbd77394c19587 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 9 Nov 2018 13:03:31 +0000
Subject: bpf: pass prog instead of env to bpf_prog_offload_verifier_prep()

Function bpf_prog_offload_verifier_prep(), called from the kernel BPF
verifier to run a driver-specific callback for preparing for the
verification step for offloaded programs, takes a pointer to a struct
bpf_verifier_env object. However, no driver callback needs the whole
structure at this time: the two drivers supporting this, nfp and
netdevsim, only need a pointer to the struct bpf_prog instance held by
env.

Update the callback accordingly, on kernel side and in these two
drivers.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 3 +--
 drivers/net/netdevsim/bpf.c                      | 4 ++--
 include/linux/bpf.h                              | 2 +-
 include/linux/bpf_verifier.h                     | 2 +-
 kernel/bpf/offload.c                             | 6 +++---
 kernel/bpf/verifier.c                            | 2 +-
 6 files changed, 9 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 91085cc3c843..e6b26d2f651d 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -183,10 +183,9 @@ static void nfp_prog_free(struct nfp_prog *nfp_prog)
 }
 
 static int
-nfp_bpf_verifier_prep(struct net_device *netdev, struct bpf_verifier_env *env)
+nfp_bpf_verifier_prep(struct net_device *netdev, struct bpf_prog *prog)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
-	struct bpf_prog *prog = env->prog;
 	struct nfp_app *app = nn->app;
 	struct nfp_prog *nfp_prog;
 	int ret;
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 33e3d54c3a0a..560bdaf1c98b 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -259,14 +259,14 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
 }
 
 static int
-nsim_bpf_verifier_prep(struct net_device *dev, struct bpf_verifier_env *env)
+nsim_bpf_verifier_prep(struct net_device *dev, struct bpf_prog *prog)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
 	if (!ns->bpf_bind_accept)
 		return -EOPNOTSUPP;
 
-	return nsim_bpf_create_prog(ns, env->prog);
+	return nsim_bpf_create_prog(ns, prog);
 }
 
 static int nsim_bpf_translate(struct net_device *dev, struct bpf_prog *prog)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 867d2801db64..888111350d0e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -268,7 +268,7 @@ struct bpf_prog_offload_ops {
 	int (*insn_hook)(struct bpf_verifier_env *env,
 			 int insn_idx, int prev_insn_idx);
 	int (*finalize)(struct bpf_verifier_env *env);
-	int (*prepare)(struct net_device *netdev, struct bpf_verifier_env *env);
+	int (*prepare)(struct net_device *netdev, struct bpf_prog *prog);
 	int (*translate)(struct net_device *netdev, struct bpf_prog *prog);
 	void (*destroy)(struct bpf_prog *prog);
 };
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index d93e89761a8b..11f5df1092d9 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -245,7 +245,7 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env)
 	return cur_func(env)->regs;
 }
 
-int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env);
+int bpf_prog_offload_verifier_prep(struct bpf_prog *prog);
 int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
 				 int insn_idx, int prev_insn_idx);
 int bpf_prog_offload_finalize(struct bpf_verifier_env *env);
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index d665e75a0ac3..397d206e184b 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -123,15 +123,15 @@ err_maybe_put:
 	return err;
 }
 
-int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env)
+int bpf_prog_offload_verifier_prep(struct bpf_prog *prog)
 {
 	struct bpf_prog_offload *offload;
 	int ret = -ENODEV;
 
 	down_read(&bpf_devs_lock);
-	offload = env->prog->aux->offload;
+	offload = prog->aux->offload;
 	if (offload)
-		ret = offload->offdev->ops->prepare(offload->netdev, env);
+		ret = offload->offdev->ops->prepare(offload->netdev, prog);
 	offload->dev_state = !ret;
 	up_read(&bpf_devs_lock);
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 75dab40b19a3..8d0977980cfa 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6368,7 +6368,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 		goto skip_full_check;
 
 	if (bpf_prog_is_dev_bound(env->prog->aux)) {
-		ret = bpf_prog_offload_verifier_prep(env);
+		ret = bpf_prog_offload_verifier_prep(env->prog);
 		if (ret)
 			goto skip_full_check;
 	}
-- 
cgit v1.2.3


From 16a8cb5cffd0a2929ae97bc258d2d9c92a4e7f6d Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 9 Nov 2018 13:03:32 +0000
Subject: bpf: do not pass netdev to translate() and prepare() offload
 callbacks

The kernel functions to prepare verifier and translate for offloaded
program retrieve "offload" from "prog", and "netdev" from "offload".
Then both "prog" and "netdev" are passed to the callbacks.

Simplify this by letting the drivers retrieve the net device themselves
from the offload object attached to prog - if they need it at all. There
is currently no need to pass the netdev as an argument to those
functions.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 9 ++++-----
 drivers/net/netdevsim/bpf.c                      | 7 +++----
 include/linux/bpf.h                              | 4 ++--
 kernel/bpf/offload.c                             | 4 ++--
 4 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index e6b26d2f651d..f0283854fade 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -182,10 +182,9 @@ static void nfp_prog_free(struct nfp_prog *nfp_prog)
 	kfree(nfp_prog);
 }
 
-static int
-nfp_bpf_verifier_prep(struct net_device *netdev, struct bpf_prog *prog)
+static int nfp_bpf_verifier_prep(struct bpf_prog *prog)
 {
-	struct nfp_net *nn = netdev_priv(netdev);
+	struct nfp_net *nn = netdev_priv(prog->aux->offload->netdev);
 	struct nfp_app *app = nn->app;
 	struct nfp_prog *nfp_prog;
 	int ret;
@@ -213,10 +212,10 @@ err_free:
 	return ret;
 }
 
-static int nfp_bpf_translate(struct net_device *netdev, struct bpf_prog *prog)
+static int nfp_bpf_translate(struct bpf_prog *prog)
 {
+	struct nfp_net *nn = netdev_priv(prog->aux->offload->netdev);
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
-	struct nfp_net *nn = netdev_priv(netdev);
 	unsigned int max_instr;
 	int err;
 
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 560bdaf1c98b..6a5b7bd9a1f9 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -258,10 +258,9 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
 	return 0;
 }
 
-static int
-nsim_bpf_verifier_prep(struct net_device *dev, struct bpf_prog *prog)
+static int nsim_bpf_verifier_prep(struct bpf_prog *prog)
 {
-	struct netdevsim *ns = netdev_priv(dev);
+	struct netdevsim *ns = netdev_priv(prog->aux->offload->netdev);
 
 	if (!ns->bpf_bind_accept)
 		return -EOPNOTSUPP;
@@ -269,7 +268,7 @@ nsim_bpf_verifier_prep(struct net_device *dev, struct bpf_prog *prog)
 	return nsim_bpf_create_prog(ns, prog);
 }
 
-static int nsim_bpf_translate(struct net_device *dev, struct bpf_prog *prog)
+static int nsim_bpf_translate(struct bpf_prog *prog)
 {
 	struct nsim_bpf_bound_prog *state = prog->aux->offload->dev_priv;
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 888111350d0e..987815152629 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -268,8 +268,8 @@ struct bpf_prog_offload_ops {
 	int (*insn_hook)(struct bpf_verifier_env *env,
 			 int insn_idx, int prev_insn_idx);
 	int (*finalize)(struct bpf_verifier_env *env);
-	int (*prepare)(struct net_device *netdev, struct bpf_prog *prog);
-	int (*translate)(struct net_device *netdev, struct bpf_prog *prog);
+	int (*prepare)(struct bpf_prog *prog);
+	int (*translate)(struct bpf_prog *prog);
 	void (*destroy)(struct bpf_prog *prog);
 };
 
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 397d206e184b..52c5617e3716 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -131,7 +131,7 @@ int bpf_prog_offload_verifier_prep(struct bpf_prog *prog)
 	down_read(&bpf_devs_lock);
 	offload = prog->aux->offload;
 	if (offload)
-		ret = offload->offdev->ops->prepare(offload->netdev, prog);
+		ret = offload->offdev->ops->prepare(prog);
 	offload->dev_state = !ret;
 	up_read(&bpf_devs_lock);
 
@@ -203,7 +203,7 @@ static int bpf_prog_offload_translate(struct bpf_prog *prog)
 	down_read(&bpf_devs_lock);
 	offload = prog->aux->offload;
 	if (offload)
-		ret = offload->offdev->ops->translate(offload->netdev, prog);
+		ret = offload->offdev->ops->translate(prog);
 	up_read(&bpf_devs_lock);
 
 	return ret;
-- 
cgit v1.2.3


From 108d50a976db70c59e6f2fc58d3252fd38ef3fc4 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Fri, 9 Nov 2018 08:21:40 -0800
Subject: selftests/bpf: rename flow dissector section to flow_dissector

Makes it compatible with the logic that derives program type
from section name in libbpf_prog_type_by_name.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpf_flow.c             | 2 +-
 tools/testing/selftests/bpf/test_flow_dissector.sh | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c
index 107350a7821d..b9798f558ca7 100644
--- a/tools/testing/selftests/bpf/bpf_flow.c
+++ b/tools/testing/selftests/bpf/bpf_flow.c
@@ -116,7 +116,7 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 	return BPF_DROP;
 }
 
-SEC("dissect")
+SEC("flow_dissector")
 int _dissect(struct __sk_buff *skb)
 {
 	if (!skb->vlan_present)
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh
index c0fb073b5eab..d23d4da66b83 100755
--- a/tools/testing/selftests/bpf/test_flow_dissector.sh
+++ b/tools/testing/selftests/bpf/test_flow_dissector.sh
@@ -59,7 +59,7 @@ else
 fi
 
 # Attach BPF program
-./flow_dissector_load -p bpf_flow.o -s dissect
+./flow_dissector_load -p bpf_flow.o -s flow_dissector
 
 # Setup
 tc qdisc add dev lo ingress
-- 
cgit v1.2.3


From 0c19a9fbc9cdba29c7effb34fd5a97226bf934e6 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Fri, 9 Nov 2018 08:21:41 -0800
Subject: libbpf: cleanup after partial failure in bpf_object__pin

bpftool will use bpf_object__pin in the next commits to pin all programs
and maps from the file; in case of a partial failure, we need to get
back to the clean state (undo previous program/map pins).

As part of a cleanup, I've added and exported separate routines to
pin all maps (bpf_object__pin_maps) and progs (bpf_object__pin_programs)
of an object.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 324 +++++++++++++++++++++++++++++++++++++++++++++----
 tools/lib/bpf/libbpf.h |  18 +++
 2 files changed, 319 insertions(+), 23 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d6e62e90e8d4..341008f47c8a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1699,6 +1699,34 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 	return 0;
 }
 
+int bpf_program__unpin_instance(struct bpf_program *prog, const char *path,
+				int instance)
+{
+	int err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (prog == NULL) {
+		pr_warning("invalid program pointer\n");
+		return -EINVAL;
+	}
+
+	if (instance < 0 || instance >= prog->instances.nr) {
+		pr_warning("invalid prog instance %d of prog %s (max %d)\n",
+			   instance, prog->section_name, prog->instances.nr);
+		return -EINVAL;
+	}
+
+	err = unlink(path);
+	if (err != 0)
+		return -errno;
+	pr_debug("unpinned program '%s'\n", path);
+
+	return 0;
+}
+
 static int make_dir(const char *path)
 {
 	char *cp, errmsg[STRERR_BUFSIZE];
@@ -1737,6 +1765,64 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 	if (err)
 		return err;
 
+	for (i = 0; i < prog->instances.nr; i++) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+		if (len < 0) {
+			err = -EINVAL;
+			goto err_unpin;
+		} else if (len >= PATH_MAX) {
+			err = -ENAMETOOLONG;
+			goto err_unpin;
+		}
+
+		err = bpf_program__pin_instance(prog, buf, i);
+		if (err)
+			goto err_unpin;
+	}
+
+	return 0;
+
+err_unpin:
+	for (i = i - 1; i >= 0; i--) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+		if (len < 0)
+			continue;
+		else if (len >= PATH_MAX)
+			continue;
+
+		bpf_program__unpin_instance(prog, buf, i);
+	}
+
+	rmdir(path);
+
+	return err;
+}
+
+int bpf_program__unpin(struct bpf_program *prog, const char *path)
+{
+	int i, err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (prog == NULL) {
+		pr_warning("invalid program pointer\n");
+		return -EINVAL;
+	}
+
+	if (prog->instances.nr <= 0) {
+		pr_warning("no instances of prog %s to pin\n",
+			   prog->section_name);
+		return -EINVAL;
+	}
+
 	for (i = 0; i < prog->instances.nr; i++) {
 		char buf[PATH_MAX];
 		int len;
@@ -1747,11 +1833,15 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 		else if (len >= PATH_MAX)
 			return -ENAMETOOLONG;
 
-		err = bpf_program__pin_instance(prog, buf, i);
+		err = bpf_program__unpin_instance(prog, buf, i);
 		if (err)
 			return err;
 	}
 
+	err = rmdir(path);
+	if (err)
+		return -errno;
+
 	return 0;
 }
 
@@ -1776,12 +1866,33 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 	}
 
 	pr_debug("pinned map '%s'\n", path);
+
 	return 0;
 }
 
-int bpf_object__pin(struct bpf_object *obj, const char *path)
+int bpf_map__unpin(struct bpf_map *map, const char *path)
+{
+	int err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (map == NULL) {
+		pr_warning("invalid map pointer\n");
+		return -EINVAL;
+	}
+
+	err = unlink(path);
+	if (err != 0)
+		return -errno;
+	pr_debug("unpinned map '%s'\n", path);
+
+	return 0;
+}
+
+int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
 {
-	struct bpf_program *prog;
 	struct bpf_map *map;
 	int err;
 
@@ -1797,6 +1908,53 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 	if (err)
 		return err;
 
+	bpf_map__for_each(map, obj) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       bpf_map__name(map));
+		if (len < 0) {
+			err = -EINVAL;
+			goto err_unpin_maps;
+		} else if (len >= PATH_MAX) {
+			err = -ENAMETOOLONG;
+			goto err_unpin_maps;
+		}
+
+		err = bpf_map__pin(map, buf);
+		if (err)
+			goto err_unpin_maps;
+	}
+
+	return 0;
+
+err_unpin_maps:
+	while ((map = bpf_map__prev(map, obj))) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       bpf_map__name(map));
+		if (len < 0)
+			continue;
+		else if (len >= PATH_MAX)
+			continue;
+
+		bpf_map__unpin(map, buf);
+	}
+
+	return err;
+}
+
+int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
+{
+	struct bpf_map *map;
+	int err;
+
+	if (!obj)
+		return -ENOENT;
+
 	bpf_map__for_each(map, obj) {
 		char buf[PATH_MAX];
 		int len;
@@ -1808,11 +1966,78 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 		else if (len >= PATH_MAX)
 			return -ENAMETOOLONG;
 
-		err = bpf_map__pin(map, buf);
+		err = bpf_map__unpin(map, buf);
 		if (err)
 			return err;
 	}
 
+	return 0;
+}
+
+int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
+{
+	struct bpf_program *prog;
+	int err;
+
+	if (!obj)
+		return -ENOENT;
+
+	if (!obj->loaded) {
+		pr_warning("object not yet loaded; load it first\n");
+		return -ENOENT;
+	}
+
+	err = make_dir(path);
+	if (err)
+		return err;
+
+	bpf_object__for_each_program(prog, obj) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       prog->section_name);
+		if (len < 0) {
+			err = -EINVAL;
+			goto err_unpin_programs;
+		} else if (len >= PATH_MAX) {
+			err = -ENAMETOOLONG;
+			goto err_unpin_programs;
+		}
+
+		err = bpf_program__pin(prog, buf);
+		if (err)
+			goto err_unpin_programs;
+	}
+
+	return 0;
+
+err_unpin_programs:
+	while ((prog = bpf_program__prev(prog, obj))) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       prog->section_name);
+		if (len < 0)
+			continue;
+		else if (len >= PATH_MAX)
+			continue;
+
+		bpf_program__unpin(prog, buf);
+	}
+
+	return err;
+}
+
+int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
+{
+	struct bpf_program *prog;
+	int err;
+
+	if (!obj)
+		return -ENOENT;
+
 	bpf_object__for_each_program(prog, obj) {
 		char buf[PATH_MAX];
 		int len;
@@ -1824,7 +2049,7 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 		else if (len >= PATH_MAX)
 			return -ENAMETOOLONG;
 
-		err = bpf_program__pin(prog, buf);
+		err = bpf_program__unpin(prog, buf);
 		if (err)
 			return err;
 	}
@@ -1832,6 +2057,23 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 	return 0;
 }
 
+int bpf_object__pin(struct bpf_object *obj, const char *path)
+{
+	int err;
+
+	err = bpf_object__pin_maps(obj, path);
+	if (err)
+		return err;
+
+	err = bpf_object__pin_programs(obj, path);
+	if (err) {
+		bpf_object__unpin_maps(obj, path);
+		return err;
+	}
+
+	return 0;
+}
+
 void bpf_object__close(struct bpf_object *obj)
 {
 	size_t i;
@@ -1918,23 +2160,20 @@ void *bpf_object__priv(struct bpf_object *obj)
 }
 
 static struct bpf_program *
-__bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, int i)
 {
-	size_t idx;
+	ssize_t idx;
 
 	if (!obj->programs)
 		return NULL;
-	/* First handler */
-	if (prev == NULL)
-		return &obj->programs[0];
 
-	if (prev->obj != obj) {
+	if (p->obj != obj) {
 		pr_warning("error: program handler doesn't match object\n");
 		return NULL;
 	}
 
-	idx = (prev - obj->programs) + 1;
-	if (idx >= obj->nr_programs)
+	idx = (p - obj->programs) + i;
+	if (idx >= obj->nr_programs || idx < 0)
 		return NULL;
 	return &obj->programs[idx];
 }
@@ -1944,8 +2183,29 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 {
 	struct bpf_program *prog = prev;
 
+	if (prev == NULL)
+		return obj->programs;
+
 	do {
-		prog = __bpf_program__next(prog, obj);
+		prog = __bpf_program__iter(prog, obj, 1);
+	} while (prog && bpf_program__is_function_storage(prog, obj));
+
+	return prog;
+}
+
+struct bpf_program *
+bpf_program__prev(struct bpf_program *next, struct bpf_object *obj)
+{
+	struct bpf_program *prog = next;
+
+	if (next == NULL) {
+		if (!obj->nr_programs)
+			return NULL;
+		return obj->programs + obj->nr_programs - 1;
+	}
+
+	do {
+		prog = __bpf_program__iter(prog, obj, -1);
 	} while (prog && bpf_program__is_function_storage(prog, obj));
 
 	return prog;
@@ -2272,10 +2532,10 @@ void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 	map->map_ifindex = ifindex;
 }
 
-struct bpf_map *
-bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+static struct bpf_map *
+__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
 {
-	size_t idx;
+	ssize_t idx;
 	struct bpf_map *s, *e;
 
 	if (!obj || !obj->maps)
@@ -2284,21 +2544,39 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
 	s = obj->maps;
 	e = obj->maps + obj->nr_maps;
 
-	if (prev == NULL)
-		return s;
-
-	if ((prev < s) || (prev >= e)) {
+	if ((m < s) || (m >= e)) {
 		pr_warning("error in %s: map handler doesn't belong to object\n",
 			   __func__);
 		return NULL;
 	}
 
-	idx = (prev - obj->maps) + 1;
-	if (idx >= obj->nr_maps)
+	idx = (m - obj->maps) + i;
+	if (idx >= obj->nr_maps || idx < 0)
 		return NULL;
 	return &obj->maps[idx];
 }
 
+struct bpf_map *
+bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+{
+	if (prev == NULL)
+		return obj->maps;
+
+	return __bpf_map__iter(prev, obj, 1);
+}
+
+struct bpf_map *
+bpf_map__prev(struct bpf_map *next, struct bpf_object *obj)
+{
+	if (next == NULL) {
+		if (!obj->nr_maps)
+			return NULL;
+		return obj->maps + obj->nr_maps - 1;
+	}
+
+	return __bpf_map__iter(next, obj, -1);
+}
+
 struct bpf_map *
 bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
 {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 1f3468dad8b2..b1686a787102 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -71,6 +71,13 @@ struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
 LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 						      size_t obj_buf_sz,
 						      const char *name);
+LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path);
+LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj,
+				      const char *path);
+LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj,
+					const char *path);
+LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj,
+					  const char *path);
 LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path);
 LIBBPF_API void bpf_object__close(struct bpf_object *object);
 
@@ -112,6 +119,9 @@ LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
 	     (pos) != NULL;				\
 	     (pos) = bpf_program__next((pos), (obj)))
 
+LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog,
+						 struct bpf_object *obj);
+
 typedef void (*bpf_program_clear_priv_t)(struct bpf_program *,
 					 void *);
 
@@ -131,7 +141,11 @@ LIBBPF_API int bpf_program__fd(struct bpf_program *prog);
 LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog,
 					 const char *path,
 					 int instance);
+LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog,
+					   const char *path,
+					   int instance);
 LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
+LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path);
 LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
 
 struct bpf_insn;
@@ -260,6 +274,9 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
 	     (pos) != NULL;				\
 	     (pos) = bpf_map__next((pos), (obj)))
 
+LIBBPF_API struct bpf_map *
+bpf_map__prev(struct bpf_map *map, struct bpf_object *obj);
+
 LIBBPF_API int bpf_map__fd(struct bpf_map *map);
 LIBBPF_API const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
 LIBBPF_API const char *bpf_map__name(struct bpf_map *map);
@@ -274,6 +291,7 @@ LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
 LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map);
 LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
+LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
 
 LIBBPF_API long libbpf_get_error(const void *ptr);
 
-- 
cgit v1.2.3


From fd734c5cca62b7630703244d3613be135d646a0e Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Fri, 9 Nov 2018 08:21:42 -0800
Subject: libbpf: bpf_program__pin: add special case for instances.nr == 1

When bpf_program has only one instance, don't create a subdirectory with
per-instance pin files (<prog>/0). Instead, just create a single pin file
for that single instance. This simplifies object pinning by not creating
unnecessary subdirectories.

This can potentially break existing users that depend on the case
where '/0' is always created. However, I couldn't find any serious
usage of bpf_program__pin inside the kernel tree and I suppose there
should be none outside.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 341008f47c8a..97ce9f214002 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1761,6 +1761,11 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 		return -EINVAL;
 	}
 
+	if (prog->instances.nr == 1) {
+		/* don't create subdirs when pinning single instance */
+		return bpf_program__pin_instance(prog, path, 0);
+	}
+
 	err = make_dir(path);
 	if (err)
 		return err;
@@ -1823,6 +1828,11 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 		return -EINVAL;
 	}
 
+	if (prog->instances.nr == 1) {
+		/* don't create subdirs when pinning single instance */
+		return bpf_program__unpin_instance(prog, path, 0);
+	}
+
 	for (i = 0; i < prog->instances.nr; i++) {
 		char buf[PATH_MAX];
 		int len;
-- 
cgit v1.2.3


From 33a2c75c55e24aa30ff9fed805ae8bea13c1e2a3 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Fri, 9 Nov 2018 08:21:43 -0800
Subject: libbpf: add internal pin_name

pin_name is the same as section_name where '/' is replaced
by '_'. bpf_object__pin_programs is converted to use pin_name
to avoid the situation where section_name would require creating another
subdirectory for a pin (as, for example, when calling bpf_object__pin_programs
for programs in sections like "cgroup/connect6").

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 97ce9f214002..e827542ffa3a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -124,6 +124,10 @@ struct bpf_program {
 	char *name;
 	int prog_ifindex;
 	char *section_name;
+	/* section_name with / replaced by _; makes recursive pinning
+	 * in bpf_object__pin_programs easier
+	 */
+	char *pin_name;
 	struct bpf_insn *insns;
 	size_t insns_cnt, main_prog_cnt;
 	enum bpf_prog_type type;
@@ -253,6 +257,7 @@ static void bpf_program__exit(struct bpf_program *prog)
 	bpf_program__unload(prog);
 	zfree(&prog->name);
 	zfree(&prog->section_name);
+	zfree(&prog->pin_name);
 	zfree(&prog->insns);
 	zfree(&prog->reloc_desc);
 
@@ -261,6 +266,17 @@ static void bpf_program__exit(struct bpf_program *prog)
 	prog->idx = -1;
 }
 
+static char *__bpf_program__pin_name(struct bpf_program *prog)
+{
+	char *name, *p;
+
+	name = p = strdup(prog->section_name);
+	while ((p = strchr(p, '/')))
+		*p = '_';
+
+	return name;
+}
+
 static int
 bpf_program__init(void *data, size_t size, char *section_name, int idx,
 		  struct bpf_program *prog)
@@ -279,6 +295,13 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx,
 		goto errout;
 	}
 
+	prog->pin_name = __bpf_program__pin_name(prog);
+	if (!prog->pin_name) {
+		pr_warning("failed to alloc pin name for prog under section(%d) %s\n",
+			   idx, section_name);
+		goto errout;
+	}
+
 	prog->insns = malloc(size);
 	if (!prog->insns) {
 		pr_warning("failed to alloc insns for prog under section %s\n",
@@ -2006,7 +2029,7 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
 		int len;
 
 		len = snprintf(buf, PATH_MAX, "%s/%s", path,
-			       prog->section_name);
+			       prog->pin_name);
 		if (len < 0) {
 			err = -EINVAL;
 			goto err_unpin_programs;
@@ -2028,7 +2051,7 @@ err_unpin_programs:
 		int len;
 
 		len = snprintf(buf, PATH_MAX, "%s/%s", path,
-			       prog->section_name);
+			       prog->pin_name);
 		if (len < 0)
 			continue;
 		else if (len >= PATH_MAX)
@@ -2053,7 +2076,7 @@ int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
 		int len;
 
 		len = snprintf(buf, PATH_MAX, "%s/%s", path,
-			       prog->section_name);
+			       prog->pin_name);
 		if (len < 0)
 			return -EINVAL;
 		else if (len >= PATH_MAX)
-- 
cgit v1.2.3


From 77380998d91dee8aafdbe42634776ba1ef692f1e Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Fri, 9 Nov 2018 08:21:44 -0800
Subject: bpftool: add loadall command

This patch adds new *loadall* command which slightly differs from the
existing *load*. *load* command loads all programs from the obj file,
but pins only the first programs. *loadall* pins all programs from the
obj file under specified directory.

The intended usecase is flow_dissector, where we want to load a bunch
of progs, pin them all and after that construct a jump table.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 14 +++--
 tools/bpf/bpftool/bash-completion/bpftool        |  4 +-
 tools/bpf/bpftool/common.c                       | 31 +++++-----
 tools/bpf/bpftool/main.h                         |  1 +
 tools/bpf/bpftool/prog.c                         | 74 +++++++++++++++++-------
 5 files changed, 81 insertions(+), 43 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index ac4e904b10fb..984d125c507a 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -15,7 +15,8 @@ SYNOPSIS
 	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } }
 
 	*COMMANDS* :=
-	{ **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load** | **help** }
+	{ **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load**
+	| **loadall** | **help** }
 
 MAP COMMANDS
 =============
@@ -24,7 +25,7 @@ MAP COMMANDS
 |	**bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
 |	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
 |	**bpftool** **prog pin** *PROG* *FILE*
-|	**bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
+|	**bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
 |       **bpftool** **prog attach** *PROG* *ATTACH_TYPE* *MAP*
 |       **bpftool** **prog detach** *PROG* *ATTACH_TYPE* *MAP*
 |	**bpftool** **prog help**
@@ -79,8 +80,11 @@ DESCRIPTION
 		  contain a dot character ('.'), which is reserved for future
 		  extensions of *bpffs*.
 
-	**bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
-		  Load bpf program from binary *OBJ* and pin as *FILE*.
+	**bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
+		  Load bpf program(s) from binary *OBJ* and pin as *PATH*.
+		  **bpftool prog load** pins only the first program from the
+		  *OBJ* as *PATH*. **bpftool prog loadall** pins all programs
+		  from the *OBJ* under *PATH* directory.
 		  **type** is optional, if not specified program type will be
 		  inferred from section names.
 		  By default bpftool will create new maps as declared in the ELF
@@ -93,7 +97,7 @@ DESCRIPTION
 		  If **dev** *NAME* is specified program will be loaded onto
 		  given networking device (offload).
 
-		  Note: *FILE* must be located in *bpffs* mount. It must not
+		  Note: *PATH* must be located in *bpffs* mount. It must not
 		  contain a dot character ('.'), which is reserved for future
 		  extensions of *bpffs*.
 
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 3f78e6404589..780ebafb756a 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -243,7 +243,7 @@ _bpftool()
     # Completion depends on object and command in use
     case $object in
         prog)
-            if [[ $command != "load" ]]; then
+            if [[ $command != "load" && $command != "loadall" ]]; then
                 case $prev in
                     id)
                         _bpftool_get_prog_ids
@@ -309,7 +309,7 @@ _bpftool()
                     fi
                     return 0
                     ;;
-                load)
+                load|loadall)
                     local obj
 
                     if [[ ${#words[@]} -lt 6 ]]; then
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 1149565be4b1..cb06a5b6e016 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -177,34 +177,23 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
 	return fd;
 }
 
-int do_pin_fd(int fd, const char *name)
+int mount_bpffs_for_pin(const char *name)
 {
 	char err_str[ERR_MAX_LEN];
 	char *file;
 	char *dir;
 	int err = 0;
 
-	err = bpf_obj_pin(fd, name);
-	if (!err)
-		goto out;
-
 	file = malloc(strlen(name) + 1);
 	strcpy(file, name);
 	dir = dirname(file);
 
-	if (errno != EPERM || is_bpffs(dir)) {
-		p_err("can't pin the object (%s): %s", name, strerror(errno));
+	if (is_bpffs(dir))
+		/* nothing to do if already mounted */
 		goto out_free;
-	}
 
-	/* Attempt to mount bpffs, then retry pinning. */
 	err = mnt_bpffs(dir, err_str, ERR_MAX_LEN);
-	if (!err) {
-		err = bpf_obj_pin(fd, name);
-		if (err)
-			p_err("can't pin the object (%s): %s", name,
-			      strerror(errno));
-	} else {
+	if (err) {
 		err_str[ERR_MAX_LEN - 1] = '\0';
 		p_err("can't mount BPF file system to pin the object (%s): %s",
 		      name, err_str);
@@ -212,10 +201,20 @@ int do_pin_fd(int fd, const char *name)
 
 out_free:
 	free(file);
-out:
 	return err;
 }
 
+int do_pin_fd(int fd, const char *name)
+{
+	int err;
+
+	err = mount_bpffs_for_pin(name);
+	if (err)
+		return err;
+
+	return bpf_obj_pin(fd, name);
+}
+
 int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 {
 	unsigned int id;
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 14857c273bf6..61d82020af58 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -131,6 +131,7 @@ const char *get_fd_type_name(enum bpf_obj_type type);
 char *get_fdinfo(int fd, const char *key);
 int open_obj_pinned(char *path);
 int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
+int mount_bpffs_for_pin(const char *name);
 int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32));
 int do_pin_fd(int fd, const char *name);
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index b9b84553bec4..97d930042cd5 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -792,15 +792,16 @@ static int do_detach(int argc, char **argv)
 		jsonw_null(json_wtr);
 	return 0;
 }
-static int do_load(int argc, char **argv)
+
+static int load_with_options(int argc, char **argv, bool first_prog_only)
 {
 	enum bpf_attach_type expected_attach_type;
 	struct bpf_object_open_attr attr = {
 		.prog_type	= BPF_PROG_TYPE_UNSPEC,
 	};
 	struct map_replace *map_replace = NULL;
+	struct bpf_program *prog = NULL, *pos;
 	unsigned int old_map_fds = 0;
-	struct bpf_program *prog;
 	struct bpf_object *obj;
 	struct bpf_map *map;
 	const char *pinfile;
@@ -918,26 +919,25 @@ static int do_load(int argc, char **argv)
 		goto err_free_reuse_maps;
 	}
 
-	prog = bpf_program__next(NULL, obj);
-	if (!prog) {
-		p_err("object file doesn't contain any bpf program");
-		goto err_close_obj;
-	}
+	bpf_object__for_each_program(pos, obj) {
+		enum bpf_prog_type prog_type = attr.prog_type;
 
-	bpf_program__set_ifindex(prog, ifindex);
-	if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) {
-		const char *sec_name = bpf_program__title(prog, false);
+		if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) {
+			const char *sec_name = bpf_program__title(pos, false);
 
-		err = libbpf_prog_type_by_name(sec_name, &attr.prog_type,
-					       &expected_attach_type);
-		if (err < 0) {
-			p_err("failed to guess program type based on section name %s\n",
-			      sec_name);
-			goto err_close_obj;
+			err = libbpf_prog_type_by_name(sec_name, &prog_type,
+						       &expected_attach_type);
+			if (err < 0) {
+				p_err("failed to guess program type based on section name %s\n",
+				      sec_name);
+				goto err_close_obj;
+			}
 		}
+
+		bpf_program__set_ifindex(pos, ifindex);
+		bpf_program__set_type(pos, prog_type);
+		bpf_program__set_expected_attach_type(pos, expected_attach_type);
 	}
-	bpf_program__set_type(prog, attr.prog_type);
-	bpf_program__set_expected_attach_type(prog, expected_attach_type);
 
 	qsort(map_replace, old_map_fds, sizeof(*map_replace),
 	      map_replace_compar);
@@ -1003,9 +1003,31 @@ static int do_load(int argc, char **argv)
 		goto err_close_obj;
 	}
 
-	if (do_pin_fd(bpf_program__fd(prog), pinfile))
+	err = mount_bpffs_for_pin(pinfile);
+	if (err)
 		goto err_close_obj;
 
+	if (first_prog_only) {
+		prog = bpf_program__next(NULL, obj);
+		if (!prog) {
+			p_err("object file doesn't contain any bpf program");
+			goto err_close_obj;
+		}
+
+		err = bpf_obj_pin(bpf_program__fd(prog), pinfile);
+		if (err) {
+			p_err("failed to pin program %s",
+			      bpf_program__title(prog, false));
+			goto err_close_obj;
+		}
+	} else {
+		err = bpf_object__pin_programs(obj, pinfile);
+		if (err) {
+			p_err("failed to pin all programs");
+			goto err_close_obj;
+		}
+	}
+
 	if (json_output)
 		jsonw_null(json_wtr);
 
@@ -1025,6 +1047,16 @@ err_free_reuse_maps:
 	return -1;
 }
 
+static int do_load(int argc, char **argv)
+{
+	return load_with_options(argc, argv, true);
+}
+
+static int do_loadall(int argc, char **argv)
+{
+	return load_with_options(argc, argv, false);
+}
+
 static int do_help(int argc, char **argv)
 {
 	if (json_output) {
@@ -1037,7 +1069,8 @@ static int do_help(int argc, char **argv)
 		"       %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
 		"       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
 		"       %s %s pin   PROG FILE\n"
-		"       %s %s load  OBJ  FILE [type TYPE] [dev NAME] \\\n"
+		"       %s %s { load | loadall } OBJ  PATH \\\n"
+		"                         [type TYPE] [dev NAME] \\\n"
 		"                         [map { idx IDX | name NAME } MAP]\n"
 		"       %s %s attach PROG ATTACH_TYPE MAP\n"
 		"       %s %s detach PROG ATTACH_TYPE MAP\n"
@@ -1069,6 +1102,7 @@ static const struct cmd cmds[] = {
 	{ "dump",	do_dump },
 	{ "pin",	do_pin },
 	{ "load",	do_load },
+	{ "loadall",	do_loadall },
 	{ "attach",	do_attach },
 	{ "detach",	do_detach },
 	{ 0 }
-- 
cgit v1.2.3


From 3767a94b3253fc8c3df96913d7dec796619161c7 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Fri, 9 Nov 2018 08:21:45 -0800
Subject: bpftool: add pinmaps argument to the load/loadall

This new additional argument lets users pin all maps from the object at
specified path.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst |  4 +++-
 tools/bpf/bpftool/bash-completion/bpftool        |  3 ++-
 tools/bpf/bpftool/prog.c                         | 24 +++++++++++++++++++++++-
 3 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 984d125c507a..15e9172f7e55 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -80,7 +80,7 @@ DESCRIPTION
 		  contain a dot character ('.'), which is reserved for future
 		  extensions of *bpffs*.
 
-	**bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
+	**bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*]
 		  Load bpf program(s) from binary *OBJ* and pin as *PATH*.
 		  **bpftool prog load** pins only the first program from the
 		  *OBJ* as *PATH*. **bpftool prog loadall** pins all programs
@@ -96,6 +96,8 @@ DESCRIPTION
 		  use, referring to it by **id** or through a **pinned** file.
 		  If **dev** *NAME* is specified program will be loaded onto
 		  given networking device (offload).
+		  Optional **pinmaps** argument can be provided to pin all
+		  maps under *MAP_DIR* directory.
 
 		  Note: *PATH* must be located in *bpffs* mount. It must not
 		  contain a dot character ('.'), which is reserved for future
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 780ebafb756a..a05d0071f39f 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -346,7 +346,7 @@ _bpftool()
                             _bpftool_get_map_ids
                             return 0
                             ;;
-                        pinned)
+                        pinned|pinmaps)
                             _filedir
                             return 0
                             ;;
@@ -358,6 +358,7 @@ _bpftool()
                             COMPREPLY=( $( compgen -W "map" -- "$cur" ) )
                             _bpftool_once_attr 'type'
                             _bpftool_once_attr 'dev'
+                            _bpftool_once_attr 'pinmaps'
                             return 0
                             ;;
                     esac
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 97d930042cd5..c2ce4220bbca 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -802,6 +802,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 	struct map_replace *map_replace = NULL;
 	struct bpf_program *prog = NULL, *pos;
 	unsigned int old_map_fds = 0;
+	const char *pinmaps = NULL;
 	struct bpf_object *obj;
 	struct bpf_map *map;
 	const char *pinfile;
@@ -906,6 +907,13 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 				goto err_free_reuse_maps;
 			}
 			NEXT_ARG();
+		} else if (is_prefix(*argv, "pinmaps")) {
+			NEXT_ARG();
+
+			if (!REQ_ARGS(1))
+				goto err_free_reuse_maps;
+
+			pinmaps = GET_ARG();
 		} else {
 			p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?",
 			      *argv);
@@ -1028,6 +1036,14 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 		}
 	}
 
+	if (pinmaps) {
+		err = bpf_object__pin_maps(obj, pinmaps);
+		if (err) {
+			p_err("failed to pin all maps");
+			goto err_unpin;
+		}
+	}
+
 	if (json_output)
 		jsonw_null(json_wtr);
 
@@ -1038,6 +1054,11 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 
 	return 0;
 
+err_unpin:
+	if (first_prog_only)
+		unlink(pinfile);
+	else
+		bpf_object__unpin_programs(obj, pinfile);
 err_close_obj:
 	bpf_object__close(obj);
 err_free_reuse_maps:
@@ -1071,7 +1092,8 @@ static int do_help(int argc, char **argv)
 		"       %s %s pin   PROG FILE\n"
 		"       %s %s { load | loadall } OBJ  PATH \\\n"
 		"                         [type TYPE] [dev NAME] \\\n"
-		"                         [map { idx IDX | name NAME } MAP]\n"
+		"                         [map { idx IDX | name NAME } MAP]\\\n"
+		"                         [pinmaps MAP_DIR]\n"
 		"       %s %s attach PROG ATTACH_TYPE MAP\n"
 		"       %s %s detach PROG ATTACH_TYPE MAP\n"
 		"       %s %s help\n"
-- 
cgit v1.2.3


From 092f08927300086b6520dfa3aa4d9450266f27ae Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Fri, 9 Nov 2018 08:21:46 -0800
Subject: bpftool: support loading flow dissector

This commit adds support for loading/attaching/detaching flow
dissector program.

When `bpftool loadall` is called with a flow_dissector prog (i.e. when the
'type flow_dissector' argument is passed), we load and pin all programs.
User is responsible to construct the jump table for the tail calls.

The last argument of `bpftool attach` is made optional for this use
case.

Example:
bpftool prog load tools/testing/selftests/bpf/bpf_flow.o \
        /sys/fs/bpf/flow type flow_dissector \
	pinmaps /sys/fs/bpf/flow

bpftool map update pinned /sys/fs/bpf/flow/jmp_table \
        key 0 0 0 0 \
        value pinned /sys/fs/bpf/flow/IP

bpftool map update pinned /sys/fs/bpf/flow/jmp_table \
        key 1 0 0 0 \
        value pinned /sys/fs/bpf/flow/IPV6

bpftool map update pinned /sys/fs/bpf/flow/jmp_table \
        key 2 0 0 0 \
        value pinned /sys/fs/bpf/flow/IPV6OP

bpftool map update pinned /sys/fs/bpf/flow/jmp_table \
        key 3 0 0 0 \
        value pinned /sys/fs/bpf/flow/IPV6FR

bpftool map update pinned /sys/fs/bpf/flow/jmp_table \
        key 4 0 0 0 \
        value pinned /sys/fs/bpf/flow/MPLS

bpftool map update pinned /sys/fs/bpf/flow/jmp_table \
        key 5 0 0 0 \
        value pinned /sys/fs/bpf/flow/VLAN

bpftool prog attach pinned /sys/fs/bpf/flow/flow_dissector flow_dissector

Tested by using the above lines to load the prog in
the test_flow_dissector.sh selftest.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 26 +++++---
 tools/bpf/bpftool/bash-completion/bpftool        | 14 +++-
 tools/bpf/bpftool/prog.c                         | 85 +++++++++++++-----------
 3 files changed, 74 insertions(+), 51 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 15e9172f7e55..8db78ed82a71 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -26,8 +26,8 @@ MAP COMMANDS
 |	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
 |	**bpftool** **prog pin** *PROG* *FILE*
 |	**bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
-|       **bpftool** **prog attach** *PROG* *ATTACH_TYPE* *MAP*
-|       **bpftool** **prog detach** *PROG* *ATTACH_TYPE* *MAP*
+|       **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*]
+|       **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*]
 |	**bpftool** **prog help**
 |
 |	*MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
@@ -40,7 +40,9 @@ MAP COMMANDS
 |		**cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
 |		**cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6**
 |	}
-|       *ATTACH_TYPE* := { **msg_verdict** | **skb_verdict** | **skb_parse** }
+|       *ATTACH_TYPE* := {
+|		**msg_verdict** | **skb_verdict** | **skb_parse** | **flow_dissector**
+|	}
 
 
 DESCRIPTION
@@ -103,13 +105,17 @@ DESCRIPTION
 		  contain a dot character ('.'), which is reserved for future
 		  extensions of *bpffs*.
 
-        **bpftool prog attach** *PROG* *ATTACH_TYPE* *MAP*
-                  Attach bpf program *PROG* (with type specified by *ATTACH_TYPE*)
-                  to the map *MAP*.
-
-        **bpftool prog detach** *PROG* *ATTACH_TYPE* *MAP*
-                  Detach bpf program *PROG* (with type specified by *ATTACH_TYPE*)
-                  from the map *MAP*.
+	**bpftool prog attach** *PROG* *ATTACH_TYPE* [*MAP*]
+		  Attach bpf program *PROG* (with type specified by
+		  *ATTACH_TYPE*). Most *ATTACH_TYPEs* require a *MAP*
+		  parameter, with the exception of *flow_dissector* which is
+		  attached to current networking name space.
+
+	**bpftool prog detach** *PROG* *ATTACH_TYPE* [*MAP*]
+		  Detach bpf program *PROG* (with type specified by
+		  *ATTACH_TYPE*). Most *ATTACH_TYPEs* require a *MAP*
+		  parameter, with the exception of *flow_dissector* which is
+		  detached from the current networking name space.
 
 	**bpftool prog help**
 		  Print short help message.
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index a05d0071f39f..45c2db257d2b 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -299,7 +299,8 @@ _bpftool()
                     fi
 
                     if [[ ${#words[@]} == 6 ]]; then
-                        COMPREPLY=( $( compgen -W "msg_verdict skb_verdict skb_parse" -- "$cur" ) )
+                        COMPREPLY=( $( compgen -W "msg_verdict skb_verdict \
+                            skb_parse flow_dissector" -- "$cur" ) )
                         return 0
                     fi
 
@@ -338,7 +339,16 @@ _bpftool()
 
                     case $prev in
                         type)
-                            COMPREPLY=( $( compgen -W "socket kprobe kretprobe classifier action tracepoint raw_tracepoint xdp perf_event cgroup/skb cgroup/sock cgroup/dev lwt_in lwt_out lwt_xmit lwt_seg6local sockops sk_skb sk_msg lirc_mode2 cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6 cgroup/post_bind4 cgroup/post_bind6" -- \
+                            COMPREPLY=( $( compgen -W "socket kprobe \
+                                kretprobe classifier flow_dissector \
+                                action tracepoint raw_tracepoint \
+                                xdp perf_event cgroup/skb cgroup/sock \
+                                cgroup/dev lwt_in lwt_out lwt_xmit \
+                                lwt_seg6local sockops sk_skb sk_msg \
+                                lirc_mode2 cgroup/bind4 cgroup/bind6 \
+                                cgroup/connect4 cgroup/connect6 \
+                                cgroup/sendmsg4 cgroup/sendmsg6 \
+                                cgroup/post_bind4 cgroup/post_bind6" -- \
                                                    "$cur" ) )
                             return 0
                             ;;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index c2ce4220bbca..5ff5544596e7 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -81,6 +81,7 @@ static const char * const attach_type_strings[] = {
 	[BPF_SK_SKB_STREAM_PARSER] = "stream_parser",
 	[BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict",
 	[BPF_SK_MSG_VERDICT] = "msg_verdict",
+	[BPF_FLOW_DISSECTOR] = "flow_dissector",
 	[__MAX_BPF_ATTACH_TYPE] = NULL,
 };
 
@@ -721,30 +722,49 @@ int map_replace_compar(const void *p1, const void *p2)
 	return a->idx - b->idx;
 }
 
-static int do_attach(int argc, char **argv)
+static int parse_attach_detach_args(int argc, char **argv, int *progfd,
+				    enum bpf_attach_type *attach_type,
+				    int *mapfd)
 {
-	enum bpf_attach_type attach_type;
-	int err, mapfd, progfd;
-
-	if (!REQ_ARGS(5)) {
-		p_err("too few parameters for map attach");
+	if (!REQ_ARGS(3))
 		return -EINVAL;
-	}
 
-	progfd = prog_parse_fd(&argc, &argv);
-	if (progfd < 0)
-		return progfd;
+	*progfd = prog_parse_fd(&argc, &argv);
+	if (*progfd < 0)
+		return *progfd;
 
-	attach_type = parse_attach_type(*argv);
-	if (attach_type == __MAX_BPF_ATTACH_TYPE) {
-		p_err("invalid attach type");
+	*attach_type = parse_attach_type(*argv);
+	if (*attach_type == __MAX_BPF_ATTACH_TYPE) {
+		p_err("invalid attach/detach type");
 		return -EINVAL;
 	}
+
+	if (*attach_type == BPF_FLOW_DISSECTOR) {
+		*mapfd = -1;
+		return 0;
+	}
+
 	NEXT_ARG();
+	if (!REQ_ARGS(2))
+		return -EINVAL;
+
+	*mapfd = map_parse_fd(&argc, &argv);
+	if (*mapfd < 0)
+		return *mapfd;
+
+	return 0;
+}
 
-	mapfd = map_parse_fd(&argc, &argv);
-	if (mapfd < 0)
-		return mapfd;
+static int do_attach(int argc, char **argv)
+{
+	enum bpf_attach_type attach_type;
+	int err, progfd;
+	int mapfd;
+
+	err = parse_attach_detach_args(argc, argv,
+				       &progfd, &attach_type, &mapfd);
+	if (err)
+		return err;
 
 	err = bpf_prog_attach(progfd, mapfd, attach_type, 0);
 	if (err) {
@@ -760,27 +780,13 @@ static int do_attach(int argc, char **argv)
 static int do_detach(int argc, char **argv)
 {
 	enum bpf_attach_type attach_type;
-	int err, mapfd, progfd;
-
-	if (!REQ_ARGS(5)) {
-		p_err("too few parameters for map detach");
-		return -EINVAL;
-	}
-
-	progfd = prog_parse_fd(&argc, &argv);
-	if (progfd < 0)
-		return progfd;
+	int err, progfd;
+	int mapfd;
 
-	attach_type = parse_attach_type(*argv);
-	if (attach_type == __MAX_BPF_ATTACH_TYPE) {
-		p_err("invalid attach type");
-		return -EINVAL;
-	}
-	NEXT_ARG();
-
-	mapfd = map_parse_fd(&argc, &argv);
-	if (mapfd < 0)
-		return mapfd;
+	err = parse_attach_detach_args(argc, argv,
+				       &progfd, &attach_type, &mapfd);
+	if (err)
+		return err;
 
 	err = bpf_prog_detach2(progfd, mapfd, attach_type);
 	if (err) {
@@ -1094,8 +1100,8 @@ static int do_help(int argc, char **argv)
 		"                         [type TYPE] [dev NAME] \\\n"
 		"                         [map { idx IDX | name NAME } MAP]\\\n"
 		"                         [pinmaps MAP_DIR]\n"
-		"       %s %s attach PROG ATTACH_TYPE MAP\n"
-		"       %s %s detach PROG ATTACH_TYPE MAP\n"
+		"       %s %s attach PROG ATTACH_TYPE [MAP]\n"
+		"       %s %s detach PROG ATTACH_TYPE [MAP]\n"
 		"       %s %s help\n"
 		"\n"
 		"       " HELP_SPEC_MAP "\n"
@@ -1107,7 +1113,8 @@ static int do_help(int argc, char **argv)
 		"                 cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
 		"                 cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
 		"                 cgroup/sendmsg4 | cgroup/sendmsg6 }\n"
-		"       ATTACH_TYPE := { msg_verdict | skb_verdict | skb_parse }\n"
+		"       ATTACH_TYPE := { msg_verdict | skb_verdict | skb_parse |\n"
+		"                        flow_dissector }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
-- 
cgit v1.2.3


From 4a5a553ddef76cbeb346414ddfd91aef8de07532 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 11 Aug 2018 21:14:34 -0700
Subject: brcmfmac: Use standard SKB list accessors in brcmf_sdiod_sglist_rw.

Instead of direct SKB list pointer accesses.

The loops in this function had to be rewritten to accommodate this
more easily.

The first loop iterates now over the target list in the outer loop,
and triggers an mmc data operation when the per-operation limits are
hit.

Then after the loops, if we have any residue, we trigger the last
and final operation.

For the page aligned workaround, where we have to copy the read data
back into the original list of SKBs, we use a two-tiered loop.  The
outer loop stays the same and iterates over pktlist, and then we have
an inner loop which uses skb_peek_next().  The break logic has been
simplified because we know that the aggregate length of the SKBs in
the source and destination lists are the same.

This change also ends up fixing a bug, having to do with the
maintainance of the seg_sz variable and how it drove the outermost
loop.  It begins as:

	seg_sz = target_list->qlen;

ie. the number of packets in the target_list queue.  The loop
structure was then:

	while (seq_sz) {
		...
		while (not at end of target_list) {
			...
			sg_cnt++
			...
		}
		...
		seg_sz -= sg_cnt;

The assumption built into that last statement is that sg_cnt counts
how many packets from target_list have been fully processed by the
inner loop.  But this not true.

If we hit one of the limits, such as the max segment size or the max
request size, we will break and copy a partial packet then contine
back up to the top of the outermost loop.

With the new loops we don't have this problem as we don't guard the
loop exit with a packet count, but instead use the progression of the
pkt_next SKB through the list to the end.  The general structure is:

	sg_cnt = 0;
	skb_queue_walk(target_list, pkt_next) {
		pkt_offset = 0;
		...
		sg_cnt++;
		...
		while (pkt_offset < pkt_next->len) {
			pkt_offset += sg_data_size;
			if (queued up max per request)
				mmc_submit_one();
		}
	}
	if (sg_cnt)
		mmc_submit_one();

The variables that maintain where we are in the MMC command state such
as req_sz, sg_cnt, and sgl are reset when we emit one of these full
sized requests.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c  | 137 +++++++++++----------
 1 file changed, 74 insertions(+), 63 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 3e37c8cf82c6..b2ad2122c8c4 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -342,6 +342,37 @@ static int brcmf_sdiod_skbuff_write(struct brcmf_sdio_dev *sdiodev,
 	return err;
 }
 
+static int mmc_submit_one(struct mmc_data *md, struct mmc_request *mr,
+			  struct mmc_command *mc, int sg_cnt, int req_sz,
+			  int func_blk_sz, u32 *addr,
+			  struct brcmf_sdio_dev *sdiodev,
+			  struct sdio_func *func, int write)
+{
+	int ret;
+
+	md->sg_len = sg_cnt;
+	md->blocks = req_sz / func_blk_sz;
+	mc->arg |= (*addr & 0x1FFFF) << 9;	/* address */
+	mc->arg |= md->blocks & 0x1FF;	/* block count */
+	/* incrementing addr for function 1 */
+	if (func->num == 1)
+		*addr += req_sz;
+
+	mmc_set_data_timeout(md, func->card);
+	mmc_wait_for_req(func->card->host, mr);
+
+	ret = mc->error ? mc->error : md->error;
+	if (ret == -ENOMEDIUM) {
+		brcmf_sdiod_change_state(sdiodev, BRCMF_SDIOD_NOMEDIUM);
+	} else if (ret != 0) {
+		brcmf_err("CMD53 sg block %s failed %d\n",
+			  write ? "write" : "read", ret);
+		ret = -EIO;
+	}
+
+	return ret;
+}
+
 /**
  * brcmf_sdiod_sglist_rw - SDIO interface function for block data access
  * @sdiodev: brcmfmac sdio device
@@ -360,11 +391,11 @@ static int brcmf_sdiod_sglist_rw(struct brcmf_sdio_dev *sdiodev,
 				 struct sk_buff_head *pktlist)
 {
 	unsigned int req_sz, func_blk_sz, sg_cnt, sg_data_sz, pkt_offset;
-	unsigned int max_req_sz, orig_offset, dst_offset;
-	unsigned short max_seg_cnt, seg_sz;
+	unsigned int max_req_sz, src_offset, dst_offset;
 	unsigned char *pkt_data, *orig_data, *dst_data;
-	struct sk_buff *pkt_next = NULL, *local_pkt_next;
 	struct sk_buff_head local_list, *target_list;
+	struct sk_buff *pkt_next = NULL, *src;
+	unsigned short max_seg_cnt;
 	struct mmc_request mmc_req;
 	struct mmc_command mmc_cmd;
 	struct mmc_data mmc_dat;
@@ -404,9 +435,6 @@ static int brcmf_sdiod_sglist_rw(struct brcmf_sdio_dev *sdiodev,
 	max_req_sz = sdiodev->max_request_size;
 	max_seg_cnt = min_t(unsigned short, sdiodev->max_segment_count,
 			    target_list->qlen);
-	seg_sz = target_list->qlen;
-	pkt_offset = 0;
-	pkt_next = target_list->next;
 
 	memset(&mmc_req, 0, sizeof(struct mmc_request));
 	memset(&mmc_cmd, 0, sizeof(struct mmc_command));
@@ -425,12 +453,12 @@ static int brcmf_sdiod_sglist_rw(struct brcmf_sdio_dev *sdiodev,
 	mmc_req.cmd = &mmc_cmd;
 	mmc_req.data = &mmc_dat;
 
-	while (seg_sz) {
-		req_sz = 0;
-		sg_cnt = 0;
-		sgl = sdiodev->sgtable.sgl;
-		/* prep sg table */
-		while (pkt_next != (struct sk_buff *)target_list) {
+	req_sz = 0;
+	sg_cnt = 0;
+	sgl = sdiodev->sgtable.sgl;
+	skb_queue_walk(target_list, pkt_next) {
+		pkt_offset = 0;
+		while (pkt_offset < pkt_next->len) {
 			pkt_data = pkt_next->data + pkt_offset;
 			sg_data_sz = pkt_next->len - pkt_offset;
 			if (sg_data_sz > sdiodev->max_segment_size)
@@ -439,72 +467,55 @@ static int brcmf_sdiod_sglist_rw(struct brcmf_sdio_dev *sdiodev,
 				sg_data_sz = max_req_sz - req_sz;
 
 			sg_set_buf(sgl, pkt_data, sg_data_sz);
-
 			sg_cnt++;
+
 			sgl = sg_next(sgl);
 			req_sz += sg_data_sz;
 			pkt_offset += sg_data_sz;
-			if (pkt_offset == pkt_next->len) {
-				pkt_offset = 0;
-				pkt_next = pkt_next->next;
+			if (req_sz >= max_req_sz || sg_cnt >= max_seg_cnt) {
+				ret = mmc_submit_one(&mmc_dat, &mmc_req, &mmc_cmd,
+						     sg_cnt, req_sz, func_blk_sz,
+						     &addr, sdiodev, func, write);
+				if (ret)
+					goto exit_queue_walk;
+				req_sz = 0;
+				sg_cnt = 0;
+				sgl = sdiodev->sgtable.sgl;
 			}
-
-			if (req_sz >= max_req_sz || sg_cnt >= max_seg_cnt)
-				break;
-		}
-		seg_sz -= sg_cnt;
-
-		if (req_sz % func_blk_sz != 0) {
-			brcmf_err("sg request length %u is not %u aligned\n",
-				  req_sz, func_blk_sz);
-			ret = -ENOTBLK;
-			goto exit;
-		}
-
-		mmc_dat.sg_len = sg_cnt;
-		mmc_dat.blocks = req_sz / func_blk_sz;
-		mmc_cmd.arg |= (addr & 0x1FFFF) << 9;	/* address */
-		mmc_cmd.arg |= mmc_dat.blocks & 0x1FF;	/* block count */
-		/* incrementing addr for function 1 */
-		if (func->num == 1)
-			addr += req_sz;
-
-		mmc_set_data_timeout(&mmc_dat, func->card);
-		mmc_wait_for_req(func->card->host, &mmc_req);
-
-		ret = mmc_cmd.error ? mmc_cmd.error : mmc_dat.error;
-		if (ret == -ENOMEDIUM) {
-			brcmf_sdiod_change_state(sdiodev, BRCMF_SDIOD_NOMEDIUM);
-			break;
-		} else if (ret != 0) {
-			brcmf_err("CMD53 sg block %s failed %d\n",
-				  write ? "write" : "read", ret);
-			ret = -EIO;
-			break;
 		}
 	}
-
+	if (sg_cnt)
+		ret = mmc_submit_one(&mmc_dat, &mmc_req, &mmc_cmd,
+				     sg_cnt, req_sz, func_blk_sz,
+				     &addr, sdiodev, func, write);
+exit_queue_walk:
 	if (!write && sdiodev->settings->bus.sdio.broken_sg_support) {
-		local_pkt_next = local_list.next;
-		orig_offset = 0;
+		src = __skb_peek(&local_list);
+		src_offset = 0;
 		skb_queue_walk(pktlist, pkt_next) {
 			dst_offset = 0;
-			do {
-				req_sz = local_pkt_next->len - orig_offset;
-				req_sz = min_t(uint, pkt_next->len - dst_offset,
-					       req_sz);
-				orig_data = local_pkt_next->data + orig_offset;
+
+			/* This is safe because we must have enough SKB data
+			 * in the local list to cover everything in pktlist.
+			 */
+			while (1) {
+				req_sz = pkt_next->len - dst_offset;
+				if (req_sz > src->len - src_offset)
+					req_sz = src->len - src_offset;
+
+				orig_data = src->data + src_offset;
 				dst_data = pkt_next->data + dst_offset;
 				memcpy(dst_data, orig_data, req_sz);
-				orig_offset += req_sz;
-				dst_offset += req_sz;
-				if (orig_offset == local_pkt_next->len) {
-					orig_offset = 0;
-					local_pkt_next = local_pkt_next->next;
+
+				src_offset += req_sz;
+				if (src_offset == src->len) {
+					src_offset = 0;
+					src = skb_peek_next(src, &local_list);
 				}
+				dst_offset += req_sz;
 				if (dst_offset == pkt_next->len)
 					break;
-			} while (!skb_queue_empty(&local_list));
+			}
 		}
 	}
 
-- 
cgit v1.2.3


From 9e733177c71a81ae9be22dbacc79a0dd60a99f21 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 22 Aug 2018 17:01:51 -0700
Subject: iucv: Remove SKB list assumptions.

Eliminate the assumption that SKBs and SKB list heads can
be cast to eachother in SKB list handling code.

This change also appears to fix a bug since the list->next pointer is
sampled outside of holding the SKB queue lock.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/iucv/af_iucv.c | 41 +++++++++++++++--------------------------
 1 file changed, 15 insertions(+), 26 deletions(-)

diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 0bed4cc20603..78ea5a739d10 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1873,30 +1873,26 @@ static void iucv_callback_txdone(struct iucv_path *path,
 	struct sock *sk = path->private;
 	struct sk_buff *this = NULL;
 	struct sk_buff_head *list = &iucv_sk(sk)->send_skb_q;
-	struct sk_buff *list_skb = list->next;
+	struct sk_buff *list_skb;
 	unsigned long flags;
 
 	bh_lock_sock(sk);
-	if (!skb_queue_empty(list)) {
-		spin_lock_irqsave(&list->lock, flags);
 
-		while (list_skb != (struct sk_buff *)list) {
-			if (msg->tag == IUCV_SKB_CB(list_skb)->tag) {
-				this = list_skb;
-				break;
-			}
-			list_skb = list_skb->next;
+	spin_lock_irqsave(&list->lock, flags);
+	skb_queue_walk(list, list_skb) {
+		if (msg->tag == IUCV_SKB_CB(list_skb)->tag) {
+			this = list_skb;
+			break;
 		}
-		if (this)
-			__skb_unlink(this, list);
-
-		spin_unlock_irqrestore(&list->lock, flags);
+	}
+	if (this)
+		__skb_unlink(this, list);
+	spin_unlock_irqrestore(&list->lock, flags);
 
-		if (this) {
-			kfree_skb(this);
-			/* wake up any process waiting for sending */
-			iucv_sock_wake_msglim(sk);
-		}
+	if (this) {
+		kfree_skb(this);
+		/* wake up any process waiting for sending */
+		iucv_sock_wake_msglim(sk);
 	}
 
 	if (sk->sk_state == IUCV_CLOSING) {
@@ -2284,11 +2280,7 @@ static void afiucv_hs_callback_txnotify(struct sk_buff *skb,
 
 	list = &iucv->send_skb_q;
 	spin_lock_irqsave(&list->lock, flags);
-	if (skb_queue_empty(list))
-		goto out_unlock;
-	list_skb = list->next;
-	nskb = list_skb->next;
-	while (list_skb != (struct sk_buff *)list) {
+	skb_queue_walk_safe(list, list_skb, nskb) {
 		if (skb_shinfo(list_skb) == skb_shinfo(skb)) {
 			switch (n) {
 			case TX_NOTIFY_OK:
@@ -2321,10 +2313,7 @@ static void afiucv_hs_callback_txnotify(struct sk_buff *skb,
 			}
 			break;
 		}
-		list_skb = nskb;
-		nskb = nskb->next;
 	}
-out_unlock:
 	spin_unlock_irqrestore(&list->lock, flags);
 
 	if (sk->sk_state == IUCV_CLOSING) {
-- 
cgit v1.2.3


From 348bbc25c40844c5efa083a3842c7f53d70a815e Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 10 Nov 2018 19:28:27 -0800
Subject: sctp: Fix SKB list traversal in sctp_intl_store_reasm().

To be fully correct, an iterator has an undefined value when something
like skb_queue_walk() naturally terminates.

This will actually matter when SKB queues are converted over to
list_head.

Formalize what this code ends up doing with the current
implementation.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream_interleave.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c
index 0a78cdf86463..368d9c33fde1 100644
--- a/net/sctp/stream_interleave.c
+++ b/net/sctp/stream_interleave.c
@@ -140,7 +140,7 @@ static void sctp_intl_store_reasm(struct sctp_ulpq *ulpq,
 				  struct sctp_ulpevent *event)
 {
 	struct sctp_ulpevent *cevent;
-	struct sk_buff *pos;
+	struct sk_buff *pos, *loc;
 
 	pos = skb_peek_tail(&ulpq->reasm);
 	if (!pos) {
@@ -166,23 +166,30 @@ static void sctp_intl_store_reasm(struct sctp_ulpq *ulpq,
 		return;
 	}
 
+	loc = NULL;
 	skb_queue_walk(&ulpq->reasm, pos) {
 		cevent = sctp_skb2event(pos);
 
 		if (event->stream < cevent->stream ||
 		    (event->stream == cevent->stream &&
-		     MID_lt(event->mid, cevent->mid)))
+		     MID_lt(event->mid, cevent->mid))) {
+			loc = pos;
 			break;
-
+		}
 		if (event->stream == cevent->stream &&
 		    event->mid == cevent->mid &&
 		    !(cevent->msg_flags & SCTP_DATA_FIRST_FRAG) &&
 		    (event->msg_flags & SCTP_DATA_FIRST_FRAG ||
-		     event->fsn < cevent->fsn))
+		     event->fsn < cevent->fsn)) {
+			loc = pos;
 			break;
+		}
 	}
 
-	__skb_queue_before(&ulpq->reasm, pos, sctp_event2skb(event));
+	if (!loc)
+		__skb_queue_tail(&ulpq->reasm, sctp_event2skb(event));
+	else
+		__skb_queue_before(&ulpq->reasm, loc, sctp_event2skb(event));
 }
 
 static struct sctp_ulpevent *sctp_intl_retrieve_partial(
-- 
cgit v1.2.3


From e15e067d0656625c77c52b4e5f0cfbf0c0c3583f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 10 Nov 2018 19:32:23 -0800
Subject: sctp: Fix SKB list traversal in sctp_intl_store_ordered().

Same change as made to sctp_intl_store_reasm().

To be fully correct, an iterator has an undefined value when something
like skb_queue_walk() naturally terminates.

This will actually matter when SKB queues are converted over to
list_head.

Formalize what this code ends up doing with the current
implementation.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream_interleave.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c
index 368d9c33fde1..2b499a85db0e 100644
--- a/net/sctp/stream_interleave.c
+++ b/net/sctp/stream_interleave.c
@@ -390,7 +390,7 @@ static void sctp_intl_store_ordered(struct sctp_ulpq *ulpq,
 				    struct sctp_ulpevent *event)
 {
 	struct sctp_ulpevent *cevent;
-	struct sk_buff *pos;
+	struct sk_buff *pos, *loc;
 
 	pos = skb_peek_tail(&ulpq->lobby);
 	if (!pos) {
@@ -410,18 +410,25 @@ static void sctp_intl_store_ordered(struct sctp_ulpq *ulpq,
 		return;
 	}
 
+	loc = NULL;
 	skb_queue_walk(&ulpq->lobby, pos) {
 		cevent = (struct sctp_ulpevent *)pos->cb;
 
-		if (cevent->stream > event->stream)
+		if (cevent->stream > event->stream) {
+			loc = pos;
 			break;
-
+		}
 		if (cevent->stream == event->stream &&
-		    MID_lt(event->mid, cevent->mid))
+		    MID_lt(event->mid, cevent->mid)) {
+			loc = pos;
 			break;
+		}
 	}
 
-	__skb_queue_before(&ulpq->lobby, pos, sctp_event2skb(event));
+	if (!loc)
+		__skb_queue_tail(&ulpq->lobby, sctp_event2skb(event));
+	else
+		__skb_queue_before(&ulpq->lobby, loc, sctp_event2skb(event));
 }
 
 static void sctp_intl_retrieve_ordered(struct sctp_ulpq *ulpq,
-- 
cgit v1.2.3


From 46f53a65d2de3e1591636c22b626b09d8684fd71 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Sat, 10 Nov 2018 22:15:13 -0800
Subject: bpf: Allow narrow loads with offset > 0

Currently BPF verifier allows narrow loads for a context field only with
offset zero. E.g. if there is a __u32 field then only the following
loads are permitted:
  * off=0, size=1 (narrow);
  * off=0, size=2 (narrow);
  * off=0, size=4 (full).

On the other hand LLVM can generate a load with offset different than
zero that make sense from program logic point of view, but verifier
doesn't accept it.

E.g. tools/testing/selftests/bpf/sendmsg4_prog.c has code:

  #define DST_IP4			0xC0A801FEU /* 192.168.1.254 */
  ...
  	if ((ctx->user_ip4 >> 24) == (bpf_htonl(DST_IP4) >> 24) &&

where ctx is struct bpf_sock_addr.

Some versions of LLVM can produce the following byte code for it:

       8:       71 12 07 00 00 00 00 00         r2 = *(u8 *)(r1 + 7)
       9:       67 02 00 00 18 00 00 00         r2 <<= 24
      10:       18 03 00 00 00 00 00 fe 00 00 00 00 00 00 00 00         r3 = 4261412864 ll
      12:       5d 32 07 00 00 00 00 00         if r2 != r3 goto +7 <LBB0_6>

where `*(u8 *)(r1 + 7)` means narrow load for ctx->user_ip4 with size=1
and offset=3 (7 - sizeof(ctx->user_family) = 3). This load is currently
rejected by verifier.

Verifier code that rejects such loads is in bpf_ctx_narrow_access_ok()
what means any is_valid_access implementation, that uses the function,
works this way, e.g. bpf_skb_is_valid_access() for __sk_buff or
sock_addr_is_valid_access() for bpf_sock_addr.

The patch makes such loads supported. Offset can be in [0; size_default)
but has to be multiple of load size. E.g. for __u32 field the following
loads are supported now:
  * off=0, size=1 (narrow);
  * off=1, size=1 (narrow);
  * off=2, size=1 (narrow);
  * off=3, size=1 (narrow);
  * off=0, size=2 (narrow);
  * off=2, size=2 (narrow);
  * off=0, size=4 (full).

Reported-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/filter.h | 16 +---------------
 kernel/bpf/verifier.c  | 21 ++++++++++++++++-----
 2 files changed, 17 insertions(+), 20 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index de629b706d1d..cc17f5f32fbb 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -668,24 +668,10 @@ static inline u32 bpf_ctx_off_adjust_machine(u32 size)
 	return size;
 }
 
-static inline bool bpf_ctx_narrow_align_ok(u32 off, u32 size_access,
-					   u32 size_default)
-{
-	size_default = bpf_ctx_off_adjust_machine(size_default);
-	size_access  = bpf_ctx_off_adjust_machine(size_access);
-
-#ifdef __LITTLE_ENDIAN
-	return (off & (size_default - 1)) == 0;
-#else
-	return (off & (size_default - 1)) + size_access == size_default;
-#endif
-}
-
 static inline bool
 bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 {
-	return bpf_ctx_narrow_align_ok(off, size, size_default) &&
-	       size <= size_default && (size & (size - 1)) == 0;
+	return size <= size_default && (size & (size - 1)) == 0;
 }
 
 #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8d0977980cfa..b5222aa61d54 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5718,10 +5718,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 	int i, cnt, size, ctx_field_size, delta = 0;
 	const int insn_cnt = env->prog->len;
 	struct bpf_insn insn_buf[16], *insn;
+	u32 target_size, size_default, off;
 	struct bpf_prog *new_prog;
 	enum bpf_access_type type;
 	bool is_narrower_load;
-	u32 target_size;
 
 	if (ops->gen_prologue || env->seen_direct_write) {
 		if (!ops->gen_prologue) {
@@ -5814,9 +5814,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		 * we will apply proper mask to the result.
 		 */
 		is_narrower_load = size < ctx_field_size;
+		size_default = bpf_ctx_off_adjust_machine(ctx_field_size);
+		off = insn->off;
 		if (is_narrower_load) {
-			u32 size_default = bpf_ctx_off_adjust_machine(ctx_field_size);
-			u32 off = insn->off;
 			u8 size_code;
 
 			if (type == BPF_WRITE) {
@@ -5844,12 +5844,23 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		}
 
 		if (is_narrower_load && size < target_size) {
-			if (ctx_field_size <= 4)
+			u8 shift = (off & (size_default - 1)) * 8;
+
+			if (ctx_field_size <= 4) {
+				if (shift)
+					insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH,
+									insn->dst_reg,
+									shift);
 				insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg,
 								(1 << size * 8) - 1);
-			else
+			} else {
+				if (shift)
+					insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH,
+									insn->dst_reg,
+									shift);
 				insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg,
 								(1 << size * 8) - 1);
+			}
 		}
 
 		new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
-- 
cgit v1.2.3


From 6c2afb674dbda9b736b8f09c976516e1e788860a Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Sat, 10 Nov 2018 22:15:14 -0800
Subject: selftests/bpf: Test narrow loads with off > 0 in test_verifier

Test the following narrow loads in test_verifier for context __sk_buff:
* off=1, size=1 - ok;
* off=2, size=1 - ok;
* off=3, size=1 - ok;
* off=0, size=2 - ok;
* off=1, size=2 - fail;
* off=0, size=2 - ok;
* off=3, size=2 - fail.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 48 +++++++++++++++++++++++------
 1 file changed, 38 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 6f61df62f690..54d16fbdef8b 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -2026,29 +2026,27 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 	},
 	{
-		"check skb->hash byte load not permitted 1",
+		"check skb->hash byte load permitted 1",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
 				    offsetof(struct __sk_buff, hash) + 1),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid bpf_context access",
-		.result = REJECT,
+		.result = ACCEPT,
 	},
 	{
-		"check skb->hash byte load not permitted 2",
+		"check skb->hash byte load permitted 2",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
 				    offsetof(struct __sk_buff, hash) + 2),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid bpf_context access",
-		.result = REJECT,
+		.result = ACCEPT,
 	},
 	{
-		"check skb->hash byte load not permitted 3",
+		"check skb->hash byte load permitted 3",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 #if __BYTE_ORDER == __LITTLE_ENDIAN
@@ -2060,8 +2058,7 @@ static struct bpf_test tests[] = {
 #endif
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid bpf_context access",
-		.result = REJECT,
+		.result = ACCEPT,
 	},
 	{
 		"check cb access: byte, wrong type",
@@ -2173,7 +2170,7 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 	},
 	{
-		"check skb->hash half load not permitted",
+		"check skb->hash half load permitted 2",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 #if __BYTE_ORDER == __LITTLE_ENDIAN
@@ -2182,6 +2179,37 @@ static struct bpf_test tests[] = {
 #else
 			BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
 				    offsetof(struct __sk_buff, hash)),
+#endif
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+	},
+	{
+		"check skb->hash half load not permitted, unaligned 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+			BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash) + 1),
+#else
+			BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash) + 3),
+#endif
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_context access",
+		.result = REJECT,
+	},
+	{
+		"check skb->hash half load not permitted, unaligned 3",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+			BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash) + 3),
+#else
+			BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash) + 1),
 #endif
 			BPF_EXIT_INSN(),
 		},
-- 
cgit v1.2.3


From e7605475f5f1af58668701b5ffe7763bdeb28527 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Sat, 10 Nov 2018 22:15:15 -0800
Subject: selftests/bpf: Test narrow loads with off > 0 for bpf_sock_addr

Add more test cases for context bpf_sock_addr to test narrow loads with
offset > 0 for ctx->user_ip4 field (__u32):
* off=1, size=1;
* off=2, size=1;
* off=3, size=1;
* off=2, size=2.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_sock_addr.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index aeeb76a54d63..73b7493d4120 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -574,24 +574,44 @@ static int bind4_prog_load(const struct sock_addr_test *test)
 		/* if (sk.family == AF_INET && */
 		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, family)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 16),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 24),
 
 		/*     (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */
 		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, type)),
 		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1),
 		BPF_JMP_A(1),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 12),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 20),
 
 		/*     1st_byte_of_user_ip4 == expected && */
 		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, user_ip4)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 10),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 18),
+
+		/*     2nd_byte_of_user_ip4 == expected && */
+		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, user_ip4) + 1),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 16),
+
+		/*     3rd_byte_of_user_ip4 == expected && */
+		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, user_ip4) + 2),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 14),
+
+		/*     4th_byte_of_user_ip4 == expected && */
+		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, user_ip4) + 3),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 12),
 
 		/*     1st_half_of_user_ip4 == expected && */
 		BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, user_ip4)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 8),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 10),
+
+		/*     2nd_half_of_user_ip4 == expected && */
+		BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, user_ip4) + 2),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 8),
 
 		/*     whole_user_ip4 == expected) { */
 		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-- 
cgit v1.2.3


From 41c4588b06180aaa46dfc1a7d435befbbf269a93 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 5 Oct 2018 10:47:01 +0000
Subject: iwlwifi: mvm: remove set but not used variable 'he_phy_data'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c: In function 'iwl_mvm_rx_mpdu_mq':
drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c:1386:7: warning:
 variable 'he_phy_data' set but not used [-Wunused-but-set-variable]
   u64 he_phy_data;

'he_phy_data' never used since be introduce in
commit 18ead597daa1 ("iwlwifi: support new rx_mpdu_desc api")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 26ac9402568d..d5ad390da8f0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -1422,12 +1422,6 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	/* update aggregation data for monitor sake on default queue */
 	if (!queue && (phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
 		bool toggle_bit = phy_info & IWL_RX_MPDU_PHY_AMPDU_TOGGLE;
-		u64 he_phy_data;
-
-		if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
-			he_phy_data = le64_to_cpu(desc->v3.he_phy_data);
-		else
-			he_phy_data = le64_to_cpu(desc->v1.he_phy_data);
 
 		rx_status->flag |= RX_FLAG_AMPDU_DETAILS;
 		rx_status->ampdu_reference = mvm->ampdu_ref;
-- 
cgit v1.2.3


From 06bc6f6ed4ae0246a5e52094d1be90906a1361c7 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 4 Jul 2018 23:12:33 +0200
Subject: iwlwifi: mvm: synchronize TID queue removal

When we mark a TID as no longer having a queue, there's no
guarantee the TX path isn't using this txq_id right now,
having accessed it just before we reset the value. To fix
this, add synchronize_net() when we change the TIDs from
having a queue to not having one, so that we can then be
sure that the TX path is no longer accessing that queue.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 1887d2b9f185..c2b7bb5d107c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -545,6 +545,16 @@ static int iwl_mvm_remove_sta_queue_marking(struct iwl_mvm *mvm, int queue)
 
 	rcu_read_unlock();
 
+	/*
+	 * The TX path may have been using this TXQ_ID from the tid_data,
+	 * so make sure it's no longer running so that we can safely reuse
+	 * this TXQ later. We've set all the TIDs to IWL_MVM_INVALID_QUEUE
+	 * above, but nothing guarantees we've stopped using them. Thus,
+	 * without this, we could get to iwl_mvm_disable_txq() and remove
+	 * the queue while still sending frames to it.
+	 */
+	synchronize_net();
+
 	return disable_agg_tids;
 }
 
-- 
cgit v1.2.3


From f3f240f973d103069d91e559561436e4148a7bac Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 4 Jul 2018 23:19:13 +0200
Subject: iwlwifi: mvm: remove queue_info_lock

All the queue management code runs under mvm->mutex, so there are
only very few cases of accessing the data structures without it:
 * TX path, which doesn't take any locks anyway
 * iwl_mvm_wake_sw_queue() and iwl_mvm_stop_sw_queue() where we
   just (atomically) read a bitmap, so the lock isn't needed.

Therefore, we can remove the spinlock. This enables some cleanup
in the ugly locking in iwl_mvm_inactivity_check().

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h   |   1 -
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c   |  13 +---
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c   | 102 +++----------------------
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c    |  10 +--
 drivers/net/wireless/intel/iwlwifi/mvm/utils.c |   6 +-
 5 files changed, 19 insertions(+), 113 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 7ba5bc2ed1c4..8a933774a934 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -844,7 +844,6 @@ struct iwl_mvm {
 	u16 hw_queue_to_mac80211[IWL_MAX_TVQM_QUEUES];
 
 	struct iwl_mvm_dqa_txq_info queue_info[IWL_MAX_HW_QUEUES];
-	spinlock_t queue_info_lock; /* For syncing queue mgmt operations */
 	struct work_struct add_stream_wk; /* To add streams to queues */
 
 	atomic_t mac80211_queue_stop_count[IEEE80211_MAX_QUEUES];
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 0e2092526fae..758aa1f75ca1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -676,7 +676,6 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	INIT_LIST_HEAD(&mvm->aux_roc_te_list);
 	INIT_LIST_HEAD(&mvm->async_handlers_list);
 	spin_lock_init(&mvm->time_event_lock);
-	spin_lock_init(&mvm->queue_info_lock);
 
 	INIT_WORK(&mvm->async_handlers_wk, iwl_mvm_async_handlers_wk);
 	INIT_WORK(&mvm->roc_done_wk, iwl_mvm_roc_done_wk);
@@ -1108,11 +1107,7 @@ static void iwl_mvm_async_cb(struct iwl_op_mode *op_mode,
 static void iwl_mvm_stop_sw_queue(struct iwl_op_mode *op_mode, int hw_queue)
 {
 	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
-	unsigned long mq;
-
-	spin_lock_bh(&mvm->queue_info_lock);
-	mq = mvm->hw_queue_to_mac80211[hw_queue];
-	spin_unlock_bh(&mvm->queue_info_lock);
+	unsigned long mq = mvm->hw_queue_to_mac80211[hw_queue];
 
 	iwl_mvm_stop_mac_queues(mvm, mq);
 }
@@ -1138,11 +1133,7 @@ void iwl_mvm_start_mac_queues(struct iwl_mvm *mvm, unsigned long mq)
 static void iwl_mvm_wake_sw_queue(struct iwl_op_mode *op_mode, int hw_queue)
 {
 	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
-	unsigned long mq;
-
-	spin_lock_bh(&mvm->queue_info_lock);
-	mq = mvm->hw_queue_to_mac80211[hw_queue];
-	spin_unlock_bh(&mvm->queue_info_lock);
+	unsigned long mq = mvm->hw_queue_to_mac80211[hw_queue];
 
 	iwl_mvm_start_mac_queues(mvm, mq);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index c2b7bb5d107c..79ccc698ad83 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -319,9 +319,7 @@ static int iwl_mvm_invalidate_sta_queue(struct iwl_mvm *mvm, int queue,
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
 		return -EINVAL;
 
-	spin_lock_bh(&mvm->queue_info_lock);
 	sta_id = mvm->queue_info[queue].ra_sta_id;
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	rcu_read_lock();
 
@@ -372,25 +370,17 @@ static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue,
 		return -EINVAL;
 
 	if (iwl_mvm_has_new_tx_api(mvm)) {
-		spin_lock_bh(&mvm->queue_info_lock);
-
 		if (remove_mac_queue)
 			mvm->hw_queue_to_mac80211[queue] &=
 				~BIT(mac80211_queue);
 
-		spin_unlock_bh(&mvm->queue_info_lock);
-
 		iwl_trans_txq_free(mvm->trans, queue);
 
 		return 0;
 	}
 
-	spin_lock_bh(&mvm->queue_info_lock);
-
-	if (WARN_ON(mvm->queue_info[queue].tid_bitmap == 0)) {
-		spin_unlock_bh(&mvm->queue_info_lock);
+	if (WARN_ON(mvm->queue_info[queue].tid_bitmap == 0))
 		return 0;
-	}
 
 	mvm->queue_info[queue].tid_bitmap &= ~BIT(tid);
 
@@ -426,10 +416,8 @@ static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue,
 			    mvm->hw_queue_to_mac80211[queue]);
 
 	/* If the queue is still enabled - nothing left to do in this func */
-	if (cmd.action == SCD_CFG_ENABLE_QUEUE) {
-		spin_unlock_bh(&mvm->queue_info_lock);
+	if (cmd.action == SCD_CFG_ENABLE_QUEUE)
 		return 0;
-	}
 
 	cmd.sta_id = mvm->queue_info[queue].ra_sta_id;
 	cmd.tid = mvm->queue_info[queue].txq_tid;
@@ -448,8 +436,6 @@ static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue,
 	/* Regardless if this is a reserved TXQ for a STA - mark it as false */
 	mvm->queue_info[queue].reserved = false;
 
-	spin_unlock_bh(&mvm->queue_info_lock);
-
 	iwl_trans_txq_disable(mvm->trans, queue, false);
 	ret = iwl_mvm_send_cmd_pdu(mvm, SCD_QUEUE_CFG, flags,
 				   sizeof(struct iwl_scd_txq_cfg_cmd), &cmd);
@@ -474,10 +460,8 @@ static int iwl_mvm_get_queue_agg_tids(struct iwl_mvm *mvm, int queue)
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
 		return -EINVAL;
 
-	spin_lock_bh(&mvm->queue_info_lock);
 	sta_id = mvm->queue_info[queue].ra_sta_id;
 	tid_bitmap = mvm->queue_info[queue].tid_bitmap;
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id],
 					lockdep_is_held(&mvm->mutex));
@@ -516,10 +500,8 @@ static int iwl_mvm_remove_sta_queue_marking(struct iwl_mvm *mvm, int queue)
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
 		return -EINVAL;
 
-	spin_lock_bh(&mvm->queue_info_lock);
 	sta_id = mvm->queue_info[queue].ra_sta_id;
 	tid_bitmap = mvm->queue_info[queue].tid_bitmap;
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	rcu_read_lock();
 
@@ -572,11 +554,9 @@ static int iwl_mvm_free_inactive_queue(struct iwl_mvm *mvm, int queue,
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
 		return -EINVAL;
 
-	spin_lock_bh(&mvm->queue_info_lock);
 	txq_curr_ac = mvm->queue_info[queue].mac80211_ac;
 	sta_id = mvm->queue_info[queue].ra_sta_id;
 	tid = mvm->queue_info[queue].txq_tid;
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	same_sta = sta_id == new_sta_id;
 
@@ -620,7 +600,6 @@ static int iwl_mvm_get_shared_queue(struct iwl_mvm *mvm,
 	 * by the inactivity checker.
 	 */
 	lockdep_assert_held(&mvm->mutex);
-	lockdep_assert_held(&mvm->queue_info_lock);
 
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
 		return -EINVAL;
@@ -706,10 +685,7 @@ static int iwl_mvm_scd_queue_redirect(struct iwl_mvm *mvm, int queue, int tid,
 	 * value 3 and VO with value 0, so to check if ac X is lower than ac Y
 	 * we need to check if the numerical value of X is LARGER than of Y.
 	 */
-	spin_lock_bh(&mvm->queue_info_lock);
 	if (ac <= mvm->queue_info[queue].mac80211_ac && !force) {
-		spin_unlock_bh(&mvm->queue_info_lock);
-
 		IWL_DEBUG_TX_QUEUES(mvm,
 				    "No redirection needed on TXQ #%d\n",
 				    queue);
@@ -721,7 +697,6 @@ static int iwl_mvm_scd_queue_redirect(struct iwl_mvm *mvm, int queue, int tid,
 	cmd.tid = mvm->queue_info[queue].txq_tid;
 	mq = mvm->hw_queue_to_mac80211[queue];
 	shared_queue = hweight16(mvm->queue_info[queue].tid_bitmap) > 1;
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	IWL_DEBUG_TX_QUEUES(mvm, "Redirecting TXQ #%d to FIFO #%d\n",
 			    queue, iwl_mvm_ac_to_tx_fifo[ac]);
@@ -747,9 +722,7 @@ static int iwl_mvm_scd_queue_redirect(struct iwl_mvm *mvm, int queue, int tid,
 	iwl_trans_txq_enable_cfg(mvm->trans, queue, ssn, NULL, wdg_timeout);
 
 	/* Update the TID "owner" of the queue */
-	spin_lock_bh(&mvm->queue_info_lock);
 	mvm->queue_info[queue].txq_tid = tid;
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	/* TODO: Work-around SCD bug when moving back by multiples of 0x40 */
 
@@ -758,9 +731,7 @@ static int iwl_mvm_scd_queue_redirect(struct iwl_mvm *mvm, int queue, int tid,
 			     cmd.sta_id, tid, IWL_FRAME_LIMIT, ssn);
 
 	/* Update AC marking of the queue */
-	spin_lock_bh(&mvm->queue_info_lock);
 	mvm->queue_info[queue].mac80211_ac = ac;
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	/*
 	 * Mark queue as shared in transport if shared
@@ -783,7 +754,7 @@ static int iwl_mvm_find_free_queue(struct iwl_mvm *mvm, u8 sta_id,
 {
 	int i;
 
-	lockdep_assert_held(&mvm->queue_info_lock);
+	lockdep_assert_held(&mvm->mutex);
 
 	/* This should not be hit with new TX path */
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
@@ -863,11 +834,8 @@ static bool iwl_mvm_update_txq_mapping(struct iwl_mvm *mvm, int queue,
 {
 	bool enable_queue = true;
 
-	spin_lock_bh(&mvm->queue_info_lock);
-
 	/* Make sure this TID isn't already enabled */
 	if (mvm->queue_info[queue].tid_bitmap & BIT(tid)) {
-		spin_unlock_bh(&mvm->queue_info_lock);
 		IWL_ERR(mvm, "Trying to enable TXQ %d with existing TID %d\n",
 			queue, tid);
 		return false;
@@ -903,8 +871,6 @@ static bool iwl_mvm_update_txq_mapping(struct iwl_mvm *mvm, int queue,
 			    queue, mvm->queue_info[queue].tid_bitmap,
 			    mvm->hw_queue_to_mac80211[queue]);
 
-	spin_unlock_bh(&mvm->queue_info_lock);
-
 	return enable_queue;
 }
 
@@ -959,9 +925,7 @@ static void iwl_mvm_change_queue_tid(struct iwl_mvm *mvm, int queue)
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
 		return;
 
-	spin_lock_bh(&mvm->queue_info_lock);
 	tid_bitmap = mvm->queue_info[queue].tid_bitmap;
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	if (WARN(!tid_bitmap, "TXQ %d has no tids assigned to it\n", queue))
 		return;
@@ -978,9 +942,7 @@ static void iwl_mvm_change_queue_tid(struct iwl_mvm *mvm, int queue)
 		return;
 	}
 
-	spin_lock_bh(&mvm->queue_info_lock);
 	mvm->queue_info[queue].txq_tid = tid;
-	spin_unlock_bh(&mvm->queue_info_lock);
 	IWL_DEBUG_TX_QUEUES(mvm, "Changed TXQ %d ownership to tid %d\n",
 			    queue, tid);
 }
@@ -1002,10 +964,8 @@ static void iwl_mvm_unshare_queue(struct iwl_mvm *mvm, int queue)
 
 	lockdep_assert_held(&mvm->mutex);
 
-	spin_lock_bh(&mvm->queue_info_lock);
 	sta_id = mvm->queue_info[queue].ra_sta_id;
 	tid_bitmap = mvm->queue_info[queue].tid_bitmap;
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	/* Find TID for queue, and make sure it is the only one on the queue */
 	tid = find_first_bit(&tid_bitmap, IWL_MAX_TID_COUNT + 1);
@@ -1062,9 +1022,7 @@ static void iwl_mvm_unshare_queue(struct iwl_mvm *mvm, int queue)
 		}
 	}
 
-	spin_lock_bh(&mvm->queue_info_lock);
 	mvm->queue_info[queue].status = IWL_MVM_QUEUE_READY;
-	spin_unlock_bh(&mvm->queue_info_lock);
 }
 
 /*
@@ -1083,7 +1041,7 @@ static bool iwl_mvm_remove_inactive_tids(struct iwl_mvm *mvm,
 	int tid;
 
 	lockdep_assert_held(&mvmsta->lock);
-	lockdep_assert_held(&mvm->queue_info_lock);
+	lockdep_assert_held(&mvm->mutex);
 
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
 		return false;
@@ -1184,8 +1142,6 @@ static int iwl_mvm_inactivity_check(struct iwl_mvm *mvm, u8 alloc_for_sta)
 	if (iwl_mvm_has_new_tx_api(mvm))
 		return -ENOSPC;
 
-	spin_lock_bh(&mvm->queue_info_lock);
-
 	rcu_read_lock();
 
 	/* we skip the CMD queue below by starting at 1 */
@@ -1240,12 +1196,7 @@ static int iwl_mvm_inactivity_check(struct iwl_mvm *mvm, u8 alloc_for_sta)
 
 		mvmsta = iwl_mvm_sta_from_mac80211(sta);
 
-		/* this isn't so nice, but works OK due to the way we loop */
-		spin_unlock(&mvm->queue_info_lock);
-
-		/* and we need this locking order */
-		spin_lock(&mvmsta->lock);
-		spin_lock(&mvm->queue_info_lock);
+		spin_lock_bh(&mvmsta->lock);
 		ret = iwl_mvm_remove_inactive_tids(mvm, mvmsta, i,
 						   inactive_tid_bitmap,
 						   &unshare_queues,
@@ -1253,11 +1204,10 @@ static int iwl_mvm_inactivity_check(struct iwl_mvm *mvm, u8 alloc_for_sta)
 		if (ret >= 0 && free_queue < 0)
 			free_queue = ret;
 		/* only unlock sta lock - we still need the queue info lock */
-		spin_unlock(&mvmsta->lock);
+		spin_unlock_bh(&mvmsta->lock);
 	}
 
 	rcu_read_unlock();
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	/* Reconfigure queues requiring reconfiguation */
 	for_each_set_bit(i, &unshare_queues, IWL_MAX_HW_QUEUES)
@@ -1306,8 +1256,6 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 	tfd_queue_mask = mvmsta->tfd_queue_msk;
 	spin_unlock_bh(&mvmsta->lock);
 
-	spin_lock_bh(&mvm->queue_info_lock);
-
 	/*
 	 * Non-QoS, QoS NDP and MGMT frames should go to a MGMT queue, if one
 	 * exists
@@ -1337,12 +1285,8 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 						IWL_MVM_DQA_MIN_DATA_QUEUE,
 						IWL_MVM_DQA_MAX_DATA_QUEUE);
 	if (queue < 0) {
-		spin_unlock_bh(&mvm->queue_info_lock);
-
 		/* try harder - perhaps kill an inactive queue */
 		queue = iwl_mvm_inactivity_check(mvm, mvmsta->sta_id);
-
-		spin_lock_bh(&mvm->queue_info_lock);
 	}
 
 	/* No free queue - we'll have to share */
@@ -1363,8 +1307,6 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 	if (queue > 0 && !shared_queue)
 		mvm->queue_info[queue].status = IWL_MVM_QUEUE_READY;
 
-	spin_unlock_bh(&mvm->queue_info_lock);
-
 	/* This shouldn't happen - out of queues */
 	if (WARN_ON(queue <= 0)) {
 		IWL_ERR(mvm, "No available queues for tid %d on sta_id %d\n",
@@ -1566,8 +1508,6 @@ static int iwl_mvm_reserve_sta_stream(struct iwl_mvm *mvm,
 	/* run the general cleanup/unsharing of queues */
 	iwl_mvm_inactivity_check(mvm, IWL_MVM_INVALID_STA);
 
-	spin_lock_bh(&mvm->queue_info_lock);
-
 	/* Make sure we have free resources for this STA */
 	if (vif_type == NL80211_IFTYPE_STATION && !sta->tdls &&
 	    !mvm->queue_info[IWL_MVM_DQA_BSS_CLIENT_QUEUE].tid_bitmap &&
@@ -1579,19 +1519,15 @@ static int iwl_mvm_reserve_sta_stream(struct iwl_mvm *mvm,
 						IWL_MVM_DQA_MIN_DATA_QUEUE,
 						IWL_MVM_DQA_MAX_DATA_QUEUE);
 	if (queue < 0) {
-		spin_unlock_bh(&mvm->queue_info_lock);
 		/* try again - this time kick out a queue if needed */
 		queue = iwl_mvm_inactivity_check(mvm, mvmsta->sta_id);
 		if (queue < 0) {
 			IWL_ERR(mvm, "No available queues for new station\n");
 			return -ENOSPC;
 		}
-		spin_lock_bh(&mvm->queue_info_lock);
 	}
 	mvm->queue_info[queue].status = IWL_MVM_QUEUE_RESERVED;
 
-	spin_unlock_bh(&mvm->queue_info_lock);
-
 	mvmsta->reserved_queue = queue;
 
 	IWL_DEBUG_TX_QUEUES(mvm, "Reserving data queue #%d for sta_id %d\n",
@@ -2014,18 +1950,14 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm,
 		 * is still marked as IWL_MVM_QUEUE_RESERVED, and
 		 * should be manually marked as free again
 		 */
-		spin_lock_bh(&mvm->queue_info_lock);
 		status = &mvm->queue_info[reserved_txq].status;
 		if (WARN((*status != IWL_MVM_QUEUE_RESERVED) &&
 			 (*status != IWL_MVM_QUEUE_FREE),
 			 "sta_id %d reserved txq %d status %d",
-			 sta_id, reserved_txq, *status)) {
-			spin_unlock_bh(&mvm->queue_info_lock);
+			 sta_id, reserved_txq, *status))
 			return -EINVAL;
-		}
 
 		*status = IWL_MVM_QUEUE_FREE;
-		spin_unlock_bh(&mvm->queue_info_lock);
 	}
 
 	if (vif->type == NL80211_IFTYPE_STATION &&
@@ -2883,8 +2815,6 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		return -EIO;
 	}
 
-	spin_lock(&mvm->queue_info_lock);
-
 	/*
 	 * Note the possible cases:
 	 *  1. An enabled TXQ - TXQ needs to become agg'ed
@@ -2899,7 +2829,7 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		if (txq_id < 0) {
 			ret = txq_id;
 			IWL_ERR(mvm, "Failed to allocate agg queue\n");
-			goto release_locks;
+			goto out;
 		}
 
 		/* TXQ hasn't yet been enabled, so mark it only as reserved */
@@ -2910,11 +2840,9 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		IWL_DEBUG_TX_QUEUES(mvm,
 				    "Can't start tid %d agg on shared queue!\n",
 				    tid);
-		goto release_locks;
+		goto out;
 	}
 
-	spin_unlock(&mvm->queue_info_lock);
-
 	IWL_DEBUG_TX_QUEUES(mvm,
 			    "AGG for tid %d will be on queue #%d\n",
 			    tid, txq_id);
@@ -2945,10 +2873,7 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	}
 
 	ret = 0;
-	goto out;
 
-release_locks:
-	spin_unlock(&mvm->queue_info_lock);
 out:
 	spin_unlock_bh(&mvmsta->lock);
 
@@ -3017,9 +2942,7 @@ int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	cfg.fifo = iwl_mvm_ac_to_tx_fifo[tid_to_mac80211_ac[tid]];
 
-	spin_lock_bh(&mvm->queue_info_lock);
 	queue_status = mvm->queue_info[queue].status;
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	/* Maybe there is no need to even alloc a queue... */
 	if (mvm->queue_info[queue].status == IWL_MVM_QUEUE_READY)
@@ -3065,9 +2988,7 @@ int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	}
 
 	/* No need to mark as reserved */
-	spin_lock_bh(&mvm->queue_info_lock);
 	mvm->queue_info[queue].status = IWL_MVM_QUEUE_READY;
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 out:
 	/*
@@ -3093,10 +3014,11 @@ static void iwl_mvm_unreserve_agg_queue(struct iwl_mvm *mvm,
 {
 	u16 txq_id = tid_data->txq_id;
 
+	lockdep_assert_held(&mvm->mutex);
+
 	if (iwl_mvm_has_new_tx_api(mvm))
 		return;
 
-	spin_lock_bh(&mvm->queue_info_lock);
 	/*
 	 * The TXQ is marked as reserved only if no traffic came through yet
 	 * This means no traffic has been sent on this TID (agg'd or not), so
@@ -3108,8 +3030,6 @@ static void iwl_mvm_unreserve_agg_queue(struct iwl_mvm *mvm,
 		mvm->queue_info[txq_id].status = IWL_MVM_QUEUE_FREE;
 		tid_data->txq_id = IWL_MVM_INVALID_QUEUE;
 	}
-
-	spin_unlock_bh(&mvm->queue_info_lock);
 }
 
 int iwl_mvm_sta_tx_agg_stop(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index ec57682efe54..320453f51ec7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1160,11 +1160,11 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 		 * If we have timed-out TIDs - schedule the worker that will
 		 * reconfig the queues and update them
 		 *
-		 * Note that the mvm->queue_info_lock isn't being taken here in
-		 * order to not serialize the TX flow. This isn't dangerous
-		 * because scheduling mvm->add_stream_wk can't ruin the state,
-		 * and if we DON'T schedule it due to some race condition then
-		 * next TX we get here we will.
+		 * Note that the no lock is taken here in order to not serialize
+		 * the TX flow. This isn't dangerous because scheduling
+		 * mvm->add_stream_wk can't ruin the state, and if we DON'T
+		 * schedule it due to some race condition then next TX we get
+		 * here we will.
 		 */
 		if (unlikely(mvm->queue_info[txq_id].status ==
 			     IWL_MVM_QUEUE_SHARED &&
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index 818e1180bbdd..11730d018e20 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -618,13 +618,9 @@ int iwl_mvm_reconfig_scd(struct iwl_mvm *mvm, int queue, int fifo, int sta_id,
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
 		return -EINVAL;
 
-	spin_lock_bh(&mvm->queue_info_lock);
 	if (WARN(mvm->queue_info[queue].tid_bitmap == 0,
-		 "Trying to reconfig unallocated queue %d\n", queue)) {
-		spin_unlock_bh(&mvm->queue_info_lock);
+		 "Trying to reconfig unallocated queue %d\n", queue))
 		return -ENXIO;
-	}
-	spin_unlock_bh(&mvm->queue_info_lock);
 
 	IWL_DEBUG_TX_QUEUES(mvm, "Reconfig SCD for TXQ #%d\n", queue);
 
-- 
cgit v1.2.3


From 8954e1eb2270fa2effffd031b4839253952c76f2 Mon Sep 17 00:00:00 2001
From: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Date: Wed, 4 Jul 2018 15:31:36 +0300
Subject: iwlwifi: trans: Clear persistence bit when starting the FW

In D3 suspend flow in 9260 gen2 HW, the NIC receives two PERST signals.
The first PERST is expected and indicates the device on coming resume flow.
The second PERST causes FW restart FW restart.
In order to avoid this issue, the FW set the persistence bit on.
Once this bit is set, the FW ignores reset attempts.
The problem is when the FW gets assert during D3 and then the persistence
bit is set and causes the FW to ignore reset.
To handle this issue, the FW opens the preg bit which allows access
to the persistence bit, so that the driver clear the persistence bit
and reset the NIC.

The flow is as follows:
the driver checks if the persistence bit is set.
If the bit is set, the driver checks if he can clear the bit.
If the driver can not clear the bit then there is no point to continue
configuring the NIC since it will fail.

The fix was added is in start HW flow instead of the resume flow since in
general, if the persistence bit is set, the driver can not start the FW.
So it is good to check it when we start configuring the NIC.

The driver does not need to close the preg bit since the FW close it
during the start flow.

Signed-off-by: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-prph.h   |  7 +++++++
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 12 ++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
index 0f51c7bea8d0..2084c63dc670 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
@@ -8,6 +8,7 @@
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -394,6 +396,7 @@ enum aux_misc_master1_en {
 #define AUX_MISC_MASTER1_SMPHR_STATUS	0xA20800
 #define RSA_ENABLE			0xA24B08
 #define PREG_AUX_BUS_WPROT_0		0xA04CC0
+#define PREG_PRPH_WPROT_0		0xA04CE0
 #define SB_CPU_1_STATUS			0xA01E30
 #define SB_CPU_2_STATUS			0xA01E34
 #define UMAG_SB_CPU_1_STATUS		0xA038C0
@@ -420,4 +423,8 @@ enum {
 #define UREG_CHICK		(0xA05C00)
 #define UREG_CHICK_MSI_ENABLE	BIT(24)
 #define UREG_CHICK_MSIX_ENABLE	BIT(25)
+
+#define HPM_DEBUG			0xA03440
+#define PERSISTENCE_BIT			BIT(12)
+#define PREG_WFPM_ACCESS		BIT(12)
 #endif				/* __iwl_prph_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 5bafb3f46eb8..890b51b223a1 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1729,6 +1729,7 @@ static int iwl_pcie_init_msix_handler(struct pci_dev *pdev,
 static int _iwl_trans_pcie_start_hw(struct iwl_trans *trans, bool low_power)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	u32 hpm;
 	int err;
 
 	lockdep_assert_held(&trans_pcie->mutex);
@@ -1739,6 +1740,17 @@ static int _iwl_trans_pcie_start_hw(struct iwl_trans *trans, bool low_power)
 		return err;
 	}
 
+	hpm = iwl_trans_read_prph(trans, HPM_DEBUG);
+	if (hpm != 0xa5a5a5a0 && (hpm & PERSISTENCE_BIT)) {
+		if (iwl_trans_read_prph(trans, PREG_PRPH_WPROT_0) &
+		    PREG_WFPM_ACCESS) {
+			IWL_ERR(trans,
+				"Error, can not clear persistence bit\n");
+			return -EPERM;
+		}
+		iwl_trans_write_prph(trans, HPM_DEBUG, hpm & ~PERSISTENCE_BIT);
+	}
+
 	iwl_trans_pcie_sw_reset(trans);
 
 	err = iwl_pcie_apm_init(trans);
-- 
cgit v1.2.3


From 47242744109d50175b2fc6134de14e4195effe17 Mon Sep 17 00:00:00 2001
From: Tova Mussai <tova.mussai@intel.com>
Date: Mon, 2 Jul 2018 09:08:29 +0300
Subject: iwlwifi: mvm: enable low latency for soft ap

Enable low latency for softAP in all modes (standalone, SCM
and DCM).
This is in order to minimize the time the softAP leaves the channel for
other operations

Signed-off-by: Tova Mussai <tova.mussai@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 .../net/wireless/intel/iwlwifi/mvm/debugfs-vif.c   |  5 +--
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c  | 12 +++++++
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h       |  4 +++
 drivers/net/wireless/intel/iwlwifi/mvm/utils.c     | 42 ++++++++++++----------
 4 files changed, 43 insertions(+), 20 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
index 1aa6c7e93088..e9767bbdea1e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
@@ -1299,10 +1299,11 @@ static ssize_t iwl_dbgfs_low_latency_read(struct file *file,
 	int len;
 
 	len = scnprintf(buf, sizeof(buf) - 1,
-			"traffic=%d\ndbgfs=%d\nvcmd=%d\n",
+			"traffic=%d\ndbgfs=%d\nvcmd=%d\nvif_type=%d\n",
 			!!(mvmvif->low_latency & LOW_LATENCY_TRAFFIC),
 			!!(mvmvif->low_latency & LOW_LATENCY_DEBUGFS),
-			!!(mvmvif->low_latency & LOW_LATENCY_VCMD));
+			!!(mvmvif->low_latency & LOW_LATENCY_VCMD),
+			!!(mvmvif->low_latency & LOW_LATENCY_VIF_TYPE));
 	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 505b0385d800..5bdc638fc999 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -2379,6 +2379,12 @@ static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw,
 	/* must be set before quota calculations */
 	mvmvif->ap_ibss_active = true;
 
+	if (vif->type == NL80211_IFTYPE_AP && !vif->p2p) {
+		iwl_mvm_vif_set_low_latency(mvmvif, true,
+					    LOW_LATENCY_VIF_TYPE);
+		iwl_mvm_send_low_latency_cmd(mvm, true, mvmvif->id);
+	}
+
 	/* power updated needs to be done before quotas */
 	iwl_mvm_power_update_mac(mvm);
 
@@ -2441,6 +2447,12 @@ static void iwl_mvm_stop_ap_ibss(struct ieee80211_hw *hw,
 	mvmvif->ap_ibss_active = false;
 	mvm->ap_last_beacon_gp2 = 0;
 
+	if (vif->type == NL80211_IFTYPE_AP && !vif->p2p) {
+		iwl_mvm_vif_set_low_latency(mvmvif, false,
+					    LOW_LATENCY_VIF_TYPE);
+		iwl_mvm_send_low_latency_cmd(mvm, false,  mvmvif->id);
+	}
+
 	iwl_mvm_bt_coex_vif_change(mvm);
 
 	iwl_mvm_unref(mvm, IWL_MVM_REF_AP_IBSS);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 8a933774a934..03fdc8b1892d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -303,11 +303,13 @@ enum iwl_bt_force_ant_mode {
 * @LOW_LATENCY_TRAFFIC: indicates low latency traffic was detected
 * @LOW_LATENCY_DEBUGFS: low latency mode set from debugfs
 * @LOW_LATENCY_VCMD: low latency mode set from vendor command
+* @LOW_LATENCY_VIF_TYPE: low latency mode set because of vif type (ap)
 */
 enum iwl_mvm_low_latency_cause {
 	LOW_LATENCY_TRAFFIC = BIT(0),
 	LOW_LATENCY_DEBUGFS = BIT(1),
 	LOW_LATENCY_VCMD = BIT(2),
+	LOW_LATENCY_VIF_TYPE = BIT(3),
 };
 
 /**
@@ -1845,6 +1847,8 @@ int iwl_mvm_update_low_latency(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 /* get SystemLowLatencyMode - only needed for beacon threshold? */
 bool iwl_mvm_low_latency(struct iwl_mvm *mvm);
 bool iwl_mvm_low_latency_band(struct iwl_mvm *mvm, enum nl80211_band band);
+void iwl_mvm_send_low_latency_cmd(struct iwl_mvm *mvm, bool low_latency,
+				  u16 mac_id);
 
 /* get VMACLowLatencyMode */
 static inline bool iwl_mvm_vif_low_latency(struct iwl_mvm_vif *mvmvif)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index 11730d018e20..3fd673128d51 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -764,6 +764,29 @@ bool iwl_mvm_rx_diversity_allowed(struct iwl_mvm *mvm)
 	return result;
 }
 
+void iwl_mvm_send_low_latency_cmd(struct iwl_mvm *mvm,
+				  bool low_latency, u16 mac_id)
+{
+	struct iwl_mac_low_latency_cmd cmd = {
+		.mac_id = cpu_to_le32(mac_id)
+	};
+
+	if (!fw_has_capa(&mvm->fw->ucode_capa,
+			 IWL_UCODE_TLV_CAPA_DYNAMIC_QUOTA))
+		return;
+
+	if (low_latency) {
+		/* currently we don't care about the direction */
+		cmd.low_latency_rx = 1;
+		cmd.low_latency_tx = 1;
+	}
+
+	if (iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(LOW_LATENCY_CMD,
+						 MAC_CONF_GROUP, 0),
+				 0, sizeof(cmd), &cmd))
+		IWL_ERR(mvm, "Failed to send low latency command\n");
+}
+
 int iwl_mvm_update_low_latency(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			       bool low_latency,
 			       enum iwl_mvm_low_latency_cause cause)
@@ -782,24 +805,7 @@ int iwl_mvm_update_low_latency(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	if (low_latency == prev)
 		return 0;
 
-	if (fw_has_capa(&mvm->fw->ucode_capa,
-			IWL_UCODE_TLV_CAPA_DYNAMIC_QUOTA)) {
-		struct iwl_mac_low_latency_cmd cmd = {
-			.mac_id = cpu_to_le32(mvmvif->id)
-		};
-
-		if (low_latency) {
-			/* currently we don't care about the direction */
-			cmd.low_latency_rx = 1;
-			cmd.low_latency_tx = 1;
-		}
-		res = iwl_mvm_send_cmd_pdu(mvm,
-					   iwl_cmd_id(LOW_LATENCY_CMD,
-						      MAC_CONF_GROUP, 0),
-					   0, sizeof(cmd), &cmd);
-		if (res)
-			IWL_ERR(mvm, "Failed to send low latency command\n");
-	}
+	iwl_mvm_send_low_latency_cmd(mvm, low_latency, mvmvif->id);
 
 	res = iwl_mvm_update_quotas(mvm, false, NULL);
 	if (res)
-- 
cgit v1.2.3


From 656fca00f317011dad2f089b3aa1fb0c22558e30 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Thu, 5 Jul 2018 17:34:03 +0300
Subject: iwlwifi: mvm: switch management tx antenna only on tx failure

Switch the antenna used for management tx only if previous tx failed.
If previous tx succeeded, there is no reason to switch antennas.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 7 ++-----
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h      | 5 +++++
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c      | 2 ++
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c     | 4 +---
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c       | 8 ++++----
 5 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 6486cfb33f40..b9c45a40e251 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -965,11 +965,8 @@ static void iwl_mvm_mac_ctxt_set_tx(struct iwl_mvm *mvm,
 	tx->tx_flags = cpu_to_le32(tx_flags);
 
 	if (!fw_has_capa(&mvm->fw->ucode_capa,
-			 IWL_UCODE_TLV_CAPA_BEACON_ANT_SELECTION)) {
-		mvm->mgmt_last_antenna_idx =
-			iwl_mvm_next_antenna(mvm, iwl_mvm_get_valid_tx_ant(mvm),
-					     mvm->mgmt_last_antenna_idx);
-	}
+			 IWL_UCODE_TLV_CAPA_BEACON_ANT_SELECTION))
+		iwl_mvm_toggle_tx_ant(mvm, &mvm->mgmt_last_antenna_idx);
 
 	tx->rate_n_flags =
 		cpu_to_le32(BIT(mvm->mgmt_last_antenna_idx) <<
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 03fdc8b1892d..707bc7d1f37f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1522,6 +1522,11 @@ static inline u8 iwl_mvm_get_valid_rx_ant(struct iwl_mvm *mvm)
 	       mvm->fw->valid_rx_ant;
 }
 
+static inline void iwl_mvm_toggle_tx_ant(struct iwl_mvm *mvm, u8 *ant)
+{
+	*ant = iwl_mvm_next_antenna(mvm, iwl_mvm_get_valid_tx_ant(mvm), *ant);
+}
+
 static inline u32 iwl_mvm_get_phy_config(struct iwl_mvm *mvm)
 {
 	u32 phy_config = ~(FW_PHY_CFG_TX_CHAIN |
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 758aa1f75ca1..0d5b55ed8dda 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -845,6 +845,8 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 	iwl_mvm_tof_init(mvm);
 
+	iwl_mvm_toggle_tx_ant(mvm, &mvm->mgmt_last_antenna_idx);
+
 	return op_mode;
 
  out_unregister:
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index cfb784fea77b..cb376e869144 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -205,9 +205,7 @@ iwl_mvm_scan_rate_n_flags(struct iwl_mvm *mvm, enum nl80211_band band,
 {
 	u32 tx_ant;
 
-	mvm->scan_last_antenna_idx =
-		iwl_mvm_next_antenna(mvm, iwl_mvm_get_valid_tx_ant(mvm),
-				     mvm->scan_last_antenna_idx);
+	iwl_mvm_toggle_tx_ant(mvm, &mvm->scan_last_antenna_idx);
 	tx_ant = BIT(mvm->scan_last_antenna_idx) << RATE_MCS_ANT_POS;
 
 	if (band == NL80211_BAND_2GHZ && !no_cck)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 320453f51ec7..ac4fa0363942 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -381,10 +381,6 @@ void iwl_mvm_set_tx_cmd_rate(struct iwl_mvm *mvm, struct iwl_tx_cmd *tx_cmd,
 			cpu_to_le32(TX_CMD_FLG_ACK | TX_CMD_FLG_BAR);
 	}
 
-	mvm->mgmt_last_antenna_idx =
-		iwl_mvm_next_antenna(mvm, iwl_mvm_get_valid_tx_ant(mvm),
-				     mvm->mgmt_last_antenna_idx);
-
 	/* Set the rate in the TX cmd */
 	tx_cmd->rate_n_flags = cpu_to_le32(iwl_mvm_get_tx_rate(mvm, info, sta));
 }
@@ -1501,6 +1497,10 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 			break;
 		}
 
+		if ((status & TX_STATUS_MSK) != TX_STATUS_SUCCESS &&
+		    ieee80211_is_mgmt(hdr->frame_control))
+			iwl_mvm_toggle_tx_ant(mvm, &mvm->mgmt_last_antenna_idx);
+
 		/*
 		 * If we are freeing multiple frames, mark all the frames
 		 * but the first one as acked, since they were acknowledged
-- 
cgit v1.2.3


From 5c2dbebb446539eb9640bf59a02756d6e7f1fc53 Mon Sep 17 00:00:00 2001
From: Naftali Goldstein <naftali.goldstein@intel.com>
Date: Sun, 15 Jul 2018 15:26:27 +0300
Subject: iwlwifi: fw: do not set sgi bits for HE connection

If the association supports HE, HT/VHT rates will never be used for Tx
and therefore there's no need to set the sgi-per-channel-width-support
bits, so don't set them in this case.

Fixes: 110b32f065f3 ("iwlwifi: mvm: rs: add basic implementation of the new RS API handlers")
Signed-off-by: Naftali Goldstein <naftali.goldstein@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
index 7a98e1a1dc40..dabbc04853ac 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
@@ -98,8 +98,12 @@ static u8 rs_fw_sgi_cw_support(struct ieee80211_sta *sta)
 {
 	struct ieee80211_sta_ht_cap *ht_cap = &sta->ht_cap;
 	struct ieee80211_sta_vht_cap *vht_cap = &sta->vht_cap;
+	struct ieee80211_sta_he_cap *he_cap = &sta->he_cap;
 	u8 supp = 0;
 
+	if (he_cap && he_cap->has_he)
+		return 0;
+
 	if (ht_cap->cap & IEEE80211_HT_CAP_SGI_20)
 		supp |= BIT(IWL_TLC_MNG_CH_WIDTH_20MHZ);
 	if (ht_cap->cap & IEEE80211_HT_CAP_SGI_40)
-- 
cgit v1.2.3


From 0dde2440a77fe48495c8e99108003291db81e1a5 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Wed, 11 Jul 2018 10:30:20 +0300
Subject: iwlwifi: mvm: toggle tx antenna if tx fails during connection
 establishment

If tx fails during connection establishment, try another antenna for
the next tx. This will increase the chance to establish connection if
one of the antennas is blocked.  Note that the antenna is toggled even
when failing to tx data frames since connection establishment may use
EAPOLs for 802.1X authentication/ 4 way handshake.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c |  2 +
 drivers/net/wireless/intel/iwlwifi/mvm/sta.h |  4 ++
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c  | 65 +++++++++++++++++++++-------
 3 files changed, 56 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 79ccc698ad83..e82194836f03 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1768,6 +1768,8 @@ int iwl_mvm_add_sta(struct iwl_mvm *mvm,
 	if (iwl_mvm_has_tlc_offload(mvm))
 		iwl_mvm_rs_add_sta(mvm, mvm_sta);
 
+	iwl_mvm_toggle_tx_ant(mvm, &mvm_sta->tx_ant);
+
 update_fw:
 	ret = iwl_mvm_sta_send_to_fw(mvm, sta, sta_update, sta_flags);
 	if (ret)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index de1a0a2d8723..d52cd888f77d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -397,6 +397,9 @@ struct iwl_mvm_rxq_dup_data {
  * @ptk_pn: per-queue PTK PN data structures
  * @dup_data: per queue duplicate packet detection data
  * @deferred_traffic_tid_map: indication bitmap of deferred traffic per-TID
+ * @tx_ant: the index of the antenna to use for data tx to this station. Only
+ *	used during connection establishment (e.g. for the 4 way handshake
+ *	exchange).
  *
  * When mac80211 creates a station it reserves some space (hw->sta_data_size)
  * in the structure for use by driver. This structure is placed in that
@@ -439,6 +442,7 @@ struct iwl_mvm_sta {
 	u8 agg_tids;
 	u8 sleep_tx_count;
 	u8 avg_energy;
+	u8 tx_ant;
 };
 
 u16 iwl_mvm_tid_queued(struct iwl_mvm *mvm, struct iwl_mvm_tid_data *tid_data);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index ac4fa0363942..09cabf336310 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -302,13 +302,30 @@ void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb,
 					    offload_assist));
 }
 
+static u32 iwl_mvm_get_tx_ant(struct iwl_mvm *mvm,
+			      struct ieee80211_tx_info *info,
+			      struct ieee80211_sta *sta, __le16 fc)
+{
+	if (info->band == NL80211_BAND_2GHZ &&
+	    !iwl_mvm_bt_coex_is_shared_ant_avail(mvm))
+		return mvm->cfg->non_shared_ant << RATE_MCS_ANT_POS;
+
+	if (sta && ieee80211_is_data(fc)) {
+		struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
+
+		return BIT(mvmsta->tx_ant) << RATE_MCS_ANT_POS;
+	}
+
+	return BIT(mvm->mgmt_last_antenna_idx) << RATE_MCS_ANT_POS;
+}
+
 static u32 iwl_mvm_get_tx_rate(struct iwl_mvm *mvm,
 			       struct ieee80211_tx_info *info,
 			       struct ieee80211_sta *sta)
 {
 	int rate_idx;
 	u8 rate_plcp;
-	u32 rate_flags;
+	u32 rate_flags = 0;
 
 	/* HT rate doesn't make sense for a non data frame */
 	WARN_ONCE(info->control.rates[0].flags & IEEE80211_TX_RC_MCS,
@@ -332,13 +349,6 @@ static u32 iwl_mvm_get_tx_rate(struct iwl_mvm *mvm,
 	/* Get PLCP rate for tx_cmd->rate_n_flags */
 	rate_plcp = iwl_mvm_mac80211_idx_to_hwrate(rate_idx);
 
-	if (info->band == NL80211_BAND_2GHZ &&
-	    !iwl_mvm_bt_coex_is_shared_ant_avail(mvm))
-		rate_flags = mvm->cfg->non_shared_ant << RATE_MCS_ANT_POS;
-	else
-		rate_flags =
-			BIT(mvm->mgmt_last_antenna_idx) << RATE_MCS_ANT_POS;
-
 	/* Set CCK flag as needed */
 	if ((rate_idx >= IWL_FIRST_CCK_RATE) && (rate_idx <= IWL_LAST_CCK_RATE))
 		rate_flags |= RATE_MCS_CCK_MSK;
@@ -346,6 +356,14 @@ static u32 iwl_mvm_get_tx_rate(struct iwl_mvm *mvm,
 	return (u32)rate_plcp | rate_flags;
 }
 
+static u32 iwl_mvm_get_tx_rate_n_flags(struct iwl_mvm *mvm,
+				       struct ieee80211_tx_info *info,
+				       struct ieee80211_sta *sta, __le16 fc)
+{
+	return iwl_mvm_get_tx_rate(mvm, info, sta) |
+		iwl_mvm_get_tx_ant(mvm, info, sta, fc);
+}
+
 /*
  * Sets the fields in the Tx cmd that are rate related
  */
@@ -373,16 +391,21 @@ void iwl_mvm_set_tx_cmd_rate(struct iwl_mvm *mvm, struct iwl_tx_cmd *tx_cmd,
 	 */
 
 	if (ieee80211_is_data(fc) && sta) {
-		tx_cmd->initial_rate_index = 0;
-		tx_cmd->tx_flags |= cpu_to_le32(TX_CMD_FLG_STA_RATE);
-		return;
+		struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
+
+		if (mvmsta->sta_state >= IEEE80211_STA_AUTHORIZED) {
+			tx_cmd->initial_rate_index = 0;
+			tx_cmd->tx_flags |= cpu_to_le32(TX_CMD_FLG_STA_RATE);
+			return;
+		}
 	} else if (ieee80211_is_back_req(fc)) {
 		tx_cmd->tx_flags |=
 			cpu_to_le32(TX_CMD_FLG_ACK | TX_CMD_FLG_BAR);
 	}
 
 	/* Set the rate in the TX cmd */
-	tx_cmd->rate_n_flags = cpu_to_le32(iwl_mvm_get_tx_rate(mvm, info, sta));
+	tx_cmd->rate_n_flags =
+		cpu_to_le32(iwl_mvm_get_tx_rate_n_flags(mvm, info, sta, fc));
 }
 
 static inline void iwl_mvm_set_tx_cmd_pn(struct ieee80211_tx_info *info,
@@ -487,6 +510,8 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 		u16 offload_assist = 0;
 		u32 rate_n_flags = 0;
 		u16 flags = 0;
+		struct iwl_mvm_sta *mvmsta = sta ?
+			iwl_mvm_sta_from_mac80211(sta) : NULL;
 
 		if (ieee80211_is_data_qos(hdr->frame_control)) {
 			u8 *qc = ieee80211_get_qos_ctl(hdr);
@@ -506,10 +531,16 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 		if (!info->control.hw_key)
 			flags |= IWL_TX_FLAGS_ENCRYPT_DIS;
 
-		/* For data packets rate info comes from the fw */
-		if (!(ieee80211_is_data(hdr->frame_control) && sta)) {
+		/*
+		 * For data packets rate info comes from the fw. Only
+		 * set rate/antenna during connection establishment.
+		 */
+		if (sta && (!ieee80211_is_data(hdr->frame_control) ||
+			    mvmsta->sta_state < IEEE80211_STA_AUTHORIZED)) {
 			flags |= IWL_TX_FLAGS_CMD_RATE;
-			rate_n_flags = iwl_mvm_get_tx_rate(mvm, info, sta);
+			rate_n_flags =
+				iwl_mvm_get_tx_rate_n_flags(mvm, info, sta,
+							    hdr->frame_control);
 		}
 
 		if (mvm->trans->cfg->device_family >=
@@ -1600,6 +1631,10 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 		iwl_mvm_tx_airtime(mvm, mvmsta,
 				   le16_to_cpu(tx_resp->wireless_media_time));
 
+		if ((status & TX_STATUS_MSK) != TX_STATUS_SUCCESS &&
+		    mvmsta->sta_state < IEEE80211_STA_AUTHORIZED)
+			iwl_mvm_toggle_tx_ant(mvm, &mvmsta->tx_ant);
+
 		if (sta->wme && tid != IWL_MGMT_TID) {
 			struct iwl_mvm_tid_data *tid_data =
 				&mvmsta->tid_data[tid];
-- 
cgit v1.2.3


From f09450e32adeb4f1a878b23275571a532ab9d99e Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Thu, 19 Jul 2018 09:15:11 +0300
Subject: iwlwifi: pcie: don't reset TXQ write pointer

Currently code sets the write pointer when getting the TX queue
allocate response. This causes a redundant interrupt with any actual
change in the pointer. Remove this write altogether.

Fixes: 310181ec34e2 ("iwlwifi: move to TVQM mode")
Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index e880f69eac26..0c5f11d2c5da 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -1228,8 +1228,7 @@ int iwl_trans_pcie_txq_alloc_response(struct iwl_trans *trans,
 	/* Place first TFD at index corresponding to start sequence number */
 	txq->read_ptr = wr_ptr;
 	txq->write_ptr = wr_ptr;
-	iwl_write_direct32(trans, HBUS_TARG_WRPTR,
-			   (txq->write_ptr) | (qid << 16));
+
 	IWL_DEBUG_TX_QUEUES(trans, "Activate queue %d\n", qid);
 
 	iwl_free_resp(hcmd);
-- 
cgit v1.2.3


From 124e0eba908b061e5d7e0c60e87e6325e7555117 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 23 Jul 2018 13:50:02 +0300
Subject: iwlwifi: dbg: avoid passing trigger around

The trigger structure is being passed around, when
all we care about is whether to dump only monitor
or not. Pass a bool instead.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c     | 20 +++++++++-----------
 drivers/net/wireless/intel/iwlwifi/fw/dbg.h     |  3 +--
 drivers/net/wireless/intel/iwlwifi/fw/runtime.h |  2 +-
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h  |  8 +++-----
 drivers/net/wireless/intel/iwlwifi/mvm/d3.c     |  2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c    |  2 +-
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c |  4 ++--
 7 files changed, 18 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index c16757051f16..310af0d60101 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -655,13 +655,8 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 	u32 smem_len = fwrt->fw->dbg.n_mem_tlv ? 0 : fwrt->trans->cfg->smem_len;
 	u32 sram2_len = fwrt->fw->dbg.n_mem_tlv ?
 				0 : fwrt->trans->cfg->dccm2_len;
-	bool monitor_dump_only = false;
 	int i;
 
-	if (fwrt->dump.trig &&
-	    fwrt->dump.trig->mode & IWL_FW_DBG_TRIGGER_MONITOR_ONLY)
-		monitor_dump_only = true;
-
 	/* SRAM - include stack CCM if driver knows the values for it */
 	if (!fwrt->trans->cfg->dccm_offset || !fwrt->trans->cfg->dccm_len) {
 		const struct fw_img *img;
@@ -727,7 +722,7 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 	}
 
 	/* If we only want a monitor dump, reset the file length */
-	if (monitor_dump_only) {
+	if (fwrt->dump.monitor_only) {
 		file_len = sizeof(*dump_file) + sizeof(*dump_data) * 2 +
 			   sizeof(*dump_info) + sizeof(*dump_smem_cfg);
 	}
@@ -817,7 +812,7 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 	}
 
 	/* In case we only want monitor dump, skip to dump trasport data */
-	if (monitor_dump_only)
+	if (fwrt->dump.monitor_only)
 		goto out;
 
 	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)) {
@@ -932,7 +927,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	}
 
 	fw_error_dump->trans_ptr = iwl_trans_dump_data(fwrt->trans,
-						       fwrt->dump.trig);
+						       fwrt->dump.monitor_only);
 	file_len = le32_to_cpu(dump_file->file_len);
 	fw_error_dump->fwrt_len = file_len;
 	if (fw_error_dump->trans_ptr) {
@@ -998,7 +993,8 @@ void iwl_fw_alive_error_dump(struct iwl_fw_runtime *fwrt)
 IWL_EXPORT_SYMBOL(iwl_fw_alive_error_dump);
 
 int iwl_fw_dbg_collect_desc(struct iwl_fw_runtime *fwrt,
-			    const struct iwl_fw_dump_desc *desc, void *trigger,
+			    const struct iwl_fw_dump_desc *desc,
+			    bool monitor_only,
 			    unsigned int delay)
 {
 	/*
@@ -1028,7 +1024,7 @@ int iwl_fw_dbg_collect_desc(struct iwl_fw_runtime *fwrt,
 		 le32_to_cpu(desc->trig_desc.type));
 
 	fwrt->dump.desc = desc;
-	fwrt->dump.trig = trigger;
+	fwrt->dump.monitor_only = monitor_only;
 
 	schedule_delayed_work(&fwrt->dump.wk, delay);
 
@@ -1043,6 +1039,7 @@ int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
 {
 	struct iwl_fw_dump_desc *desc;
 	unsigned int delay = 0;
+	bool monitor_only = false;
 
 	if (trigger) {
 		u16 occurrences = le16_to_cpu(trigger->occurrences) - 1;
@@ -1059,6 +1056,7 @@ int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
 
 		trigger->occurrences = cpu_to_le16(occurrences);
 		delay = le16_to_cpu(trigger->trig_dis_ms);
+		monitor_only = trigger->mode & IWL_FW_DBG_TRIGGER_MONITOR_ONLY;
 	}
 
 	desc = kzalloc(sizeof(*desc) + len, GFP_ATOMIC);
@@ -1070,7 +1068,7 @@ int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
 	desc->trig_desc.type = cpu_to_le32(trig);
 	memcpy(desc->trig_desc.data, str, len);
 
-	return iwl_fw_dbg_collect_desc(fwrt, desc, trigger, delay);
+	return iwl_fw_dbg_collect_desc(fwrt, desc, monitor_only, delay);
 }
 IWL_EXPORT_SYMBOL(iwl_fw_dbg_collect);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index 6f8d3256f7b0..b56d787ffc1e 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -101,13 +101,12 @@ static inline void iwl_fw_free_dump_desc(struct iwl_fw_runtime *fwrt)
 	if (fwrt->dump.desc != &iwl_dump_desc_assert)
 		kfree(fwrt->dump.desc);
 	fwrt->dump.desc = NULL;
-	fwrt->dump.trig = NULL;
 }
 
 void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt);
 int iwl_fw_dbg_collect_desc(struct iwl_fw_runtime *fwrt,
 			    const struct iwl_fw_dump_desc *desc,
-			    void *trigger, unsigned int delay);
+			    bool monitor_only, unsigned int delay);
 int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
 		       enum iwl_fw_dbg_trigger trig,
 		       const char *str, size_t len,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index 6b95d0e75889..8a139431e7be 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -131,7 +131,7 @@ struct iwl_fw_runtime {
 	/* debug */
 	struct {
 		const struct iwl_fw_dump_desc *desc;
-		const struct iwl_fw_dbg_trigger_tlv *trig;
+		bool monitor_only;
 		struct delayed_work wk;
 
 		u8 conf;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 26b3c73051ca..f384a98a021c 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -602,8 +602,7 @@ struct iwl_trans_ops {
 	void (*resume)(struct iwl_trans *trans);
 
 	struct iwl_trans_dump_data *(*dump_data)(struct iwl_trans *trans,
-						 const struct iwl_fw_dbg_trigger_tlv
-						 *trigger);
+						 bool monitor_only);
 };
 
 /**
@@ -897,12 +896,11 @@ static inline void iwl_trans_resume(struct iwl_trans *trans)
 }
 
 static inline struct iwl_trans_dump_data *
-iwl_trans_dump_data(struct iwl_trans *trans,
-		    const struct iwl_fw_dbg_trigger_tlv *trigger)
+iwl_trans_dump_data(struct iwl_trans *trans, bool monitor_only)
 {
 	if (!trans->ops->dump_data)
 		return NULL;
-	return trans->ops->dump_data(trans, trigger);
+	return trans->ops->dump_data(trans, monitor_only);
 }
 
 static inline struct iwl_device_cmd *
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 843f3b41b72e..9b018d00f78f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -1956,7 +1956,7 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test)
 		set_bit(STATUS_FW_ERROR, &mvm->trans->status);
 		iwl_mvm_dump_nic_error_log(mvm);
 		iwl_fw_dbg_collect_desc(&mvm->fwrt, &iwl_dump_desc_assert,
-					NULL, 0);
+					false, 0);
 		ret = 1;
 		goto err;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 0d5b55ed8dda..2291661dd72d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -1233,7 +1233,7 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error)
 	 */
 	if (!mvm->fw_restart && fw_error) {
 		iwl_fw_dbg_collect_desc(&mvm->fwrt, &iwl_dump_desc_assert,
-					NULL, 0);
+					false, 0);
 	} else if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) {
 		struct iwl_mvm_reprobe *reprobe;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 890b51b223a1..551ce439647b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2990,7 +2990,7 @@ static int iwl_trans_get_fw_monitor_len(struct iwl_trans *trans, int *len)
 
 static struct iwl_trans_dump_data
 *iwl_trans_pcie_dump_data(struct iwl_trans *trans,
-			  const struct iwl_fw_dbg_trigger_tlv *trigger)
+			  bool monitor_only)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_fw_error_dump_data *data;
@@ -3014,7 +3014,7 @@ static struct iwl_trans_dump_data
 	/* FW monitor */
 	monitor_len = iwl_trans_get_fw_monitor_len(trans, &len);
 
-	if (trigger && (trigger->mode & IWL_FW_DBG_TRIGGER_MONITOR_ONLY)) {
+	if (monitor_only) {
 		if (!(trans->dbg_dump_mask &
 		      BIT(IWL_FW_ERROR_DUMP_FW_MONITOR)))
 			return NULL;
-- 
cgit v1.2.3


From 18ab513ebfd34d4422ad8923ff610ae35033acd6 Mon Sep 17 00:00:00 2001
From: Naftali Goldstein <naftali.goldstein@intel.com>
Date: Wed, 25 Jul 2018 15:52:20 +0300
Subject: iwlwifi: mvm: add description to a few generic assert numbers

FW asserts 0x70, 0x71, and 0x73 all just mean that the real error
happened in another MAC, and to look there for the problem. Add their
descriptions to the assert number lookup table so users get a nicer
error message in the logs.
Also, since the 4 most-significant bits of the assert number are
dynamic, and depend on which MAC the assert occurred on, ignore those
bits when looking up the assert name.

Signed-off-by: Naftali Goldstein <naftali.goldstein@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/utils.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index 3fd673128d51..3761fbfff292 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -285,6 +285,7 @@ u8 iwl_mvm_next_antenna(struct iwl_mvm *mvm, u8 valid, u8 last_idx)
 	return last_idx;
 }
 
+#define FW_SYSASSERT_CPU_MASK 0xf0000000
 static const struct {
 	const char *name;
 	u8 num;
@@ -301,6 +302,9 @@ static const struct {
 	{ "NMI_INTERRUPT_WDG_RXF_FULL", 0x5C },
 	{ "NMI_INTERRUPT_WDG_NO_RBD_RXF_FULL", 0x64 },
 	{ "NMI_INTERRUPT_HOST", 0x66 },
+	{ "NMI_INTERRUPT_LMAC_FATAL", 0x70 },
+	{ "NMI_INTERRUPT_UMAC_FATAL", 0x71 },
+	{ "NMI_INTERRUPT_OTHER_LMAC_FATAL", 0x73 },
 	{ "NMI_INTERRUPT_ACTION_PT", 0x7C },
 	{ "NMI_INTERRUPT_UNKNOWN", 0x84 },
 	{ "NMI_INTERRUPT_INST_ACTION_PT", 0x86 },
@@ -312,7 +316,7 @@ static const char *desc_lookup(u32 num)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(advanced_lookup) - 1; i++)
-		if (advanced_lookup[i].num == num)
+		if (advanced_lookup[i].num == (num & ~FW_SYSASSERT_CPU_MASK))
 			return advanced_lookup[i].name;
 
 	/* No entry matches 'num', so it is the last: ADVANCED_SYSASSERT */
-- 
cgit v1.2.3


From dc1aca22f8f38b7e2ad7b118db87404d11e68771 Mon Sep 17 00:00:00 2001
From: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Date: Tue, 24 Jul 2018 21:57:50 +0300
Subject: iwlwifi: mvm: Send non offchannel traffic via AP sta

TDLS discovery response frame is a unicast direct frame to the peer.
Since we don't have a STA for this peer, this frame goes through
iwl_tx_skb_non_sta(). As the result aux_sta and some completely
arbitrary queue would be selected for this frame, resulting in a queue
hang.  Fix that by sending such frames through AP sta instead.

Signed-off-by: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 5bdc638fc999..55b965629e33 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -809,6 +809,21 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw,
 	    !ieee80211_is_bufferable_mmpdu(hdr->frame_control))
 		sta = NULL;
 
+	/* If there is no sta, and it's not offchannel - send through AP */
+	if (info->control.vif->type == NL80211_IFTYPE_STATION &&
+	    info->hw_queue != IWL_MVM_OFFCHANNEL_QUEUE && !sta) {
+		struct iwl_mvm_vif *mvmvif =
+			iwl_mvm_vif_from_mac80211(info->control.vif);
+		u8 ap_sta_id = READ_ONCE(mvmvif->ap_sta_id);
+
+		if (ap_sta_id < IWL_MVM_STATION_COUNT) {
+			/* mac80211 holds rcu read lock */
+			sta = rcu_dereference(mvm->fw_id_to_mac_id[ap_sta_id]);
+			if (IS_ERR_OR_NULL(sta))
+				goto drop;
+		}
+	}
+
 	if (sta) {
 		if (iwl_mvm_defer_tx(mvm, sta, skb))
 			return;
-- 
cgit v1.2.3


From e488e593a79f4238156d2c0f5cbba2fd6457344f Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 30 Jul 2018 09:43:24 +0300
Subject: iwlwifi: dbg: use helper to check if debug type is set

This enables to incorporate more logic in one place.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 36 ++++++++++++++---------------
 drivers/net/wireless/intel/iwlwifi/fw/dbg.h |  7 +++++-
 2 files changed, 24 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 310af0d60101..aebdf433b409 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -240,7 +240,7 @@ static void iwl_fw_dump_fifos(struct iwl_fw_runtime *fwrt,
 	if (!iwl_trans_grab_nic_access(fwrt->trans, &flags))
 		return;
 
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_RXF)) {
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_RXF)) {
 		/* Pull RXF1 */
 		iwl_fwrt_dump_rxf(fwrt, dump_data,
 				  cfg->lmac[0].rxfifo1_size, 0, 0);
@@ -254,7 +254,7 @@ static void iwl_fw_dump_fifos(struct iwl_fw_runtime *fwrt,
 					  LMAC2_PRPH_OFFSET, 2);
 	}
 
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_TXF)) {
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_TXF)) {
 		/* Pull TXF data from LMAC1 */
 		for (i = 0; i < fwrt->smem_cfg.num_txfifo_entries; i++) {
 			/* Mark the number of TXF we're pulling now */
@@ -279,7 +279,7 @@ static void iwl_fw_dump_fifos(struct iwl_fw_runtime *fwrt,
 		}
 	}
 
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_INTERNAL_TXF) &&
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_INTERNAL_TXF) &&
 	    fw_has_capa(&fwrt->fw->ucode_capa,
 			IWL_UCODE_TLV_CAPA_EXTEND_SHARED_MEM_CFG)) {
 		/* Pull UMAC internal TXF data from all TXFs */
@@ -603,7 +603,7 @@ static int iwl_fw_fifo_len(struct iwl_fw_runtime *fwrt,
 	u32 fifo_len = 0;
 	int i;
 
-	if (!(fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_RXF)))
+	if (!iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_RXF))
 		goto dump_txf;
 
 	/* Count RXF2 size */
@@ -614,7 +614,7 @@ static int iwl_fw_fifo_len(struct iwl_fw_runtime *fwrt,
 		ADD_LEN(fifo_len, mem_cfg->lmac[i].rxfifo1_size, hdr_len);
 
 dump_txf:
-	if (!(fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_TXF)))
+	if (!iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_TXF))
 		goto dump_internal_txf;
 
 	/* Count TXF sizes */
@@ -627,7 +627,7 @@ dump_txf:
 	}
 
 dump_internal_txf:
-	if (!((fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_INTERNAL_TXF)) &&
+	if (!(iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_INTERNAL_TXF) &&
 	      fw_has_capa(&fwrt->fw->ucode_capa,
 			  IWL_UCODE_TLV_CAPA_EXTEND_SHARED_MEM_CFG)))
 		goto out;
@@ -675,22 +675,22 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 
 		/* Make room for PRPH registers */
 		if (!fwrt->trans->cfg->gen2 &&
-		    fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_PRPH))
+		   iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_PRPH))
 			prph_len += iwl_fw_get_prph_len(fwrt);
 
 		if (fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_7000 &&
-		    fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_RADIO_REG))
+		    iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_RADIO_REG))
 			radio_len = sizeof(*dump_data) + RADIO_REG_MAX_READ;
 	}
 
 	file_len = sizeof(*dump_file) + fifo_len + prph_len + radio_len;
 
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_DEV_FW_INFO))
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_DEV_FW_INFO))
 		file_len += sizeof(*dump_data) + sizeof(*dump_info);
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM_CFG))
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_MEM_CFG))
 		file_len += sizeof(*dump_data) + sizeof(*dump_smem_cfg);
 
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)) {
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_MEM)) {
 		size_t hdr_len = sizeof(*dump_data) +
 				 sizeof(struct iwl_fw_error_dump_mem);
 
@@ -707,7 +707,7 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 	}
 
 	/* Make room for fw's virtual image pages, if it exists */
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING) &&
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_PAGING) &&
 	    !fwrt->trans->cfg->gen2 &&
 	    fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size &&
 	    fwrt->fw_paging_db[0].fw_paging_block)
@@ -727,7 +727,7 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 			   sizeof(*dump_info) + sizeof(*dump_smem_cfg);
 	}
 
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_ERROR_INFO) &&
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_ERROR_INFO) &&
 	    fwrt->dump.desc)
 		file_len += sizeof(*dump_data) + sizeof(*dump_trig) +
 			    fwrt->dump.desc->len;
@@ -741,7 +741,7 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 	dump_file->barker = cpu_to_le32(IWL_FW_ERROR_DUMP_BARKER);
 	dump_data = (void *)dump_file->data;
 
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_DEV_FW_INFO)) {
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_DEV_FW_INFO)) {
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_DEV_FW_INFO);
 		dump_data->len = cpu_to_le32(sizeof(*dump_info));
 		dump_info = (void *)dump_data->data;
@@ -762,7 +762,7 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 		dump_data = iwl_fw_error_next_data(dump_data);
 	}
 
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM_CFG)) {
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_MEM_CFG)) {
 		/* Dump shared memory configuration */
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM_CFG);
 		dump_data->len = cpu_to_le32(sizeof(*dump_smem_cfg));
@@ -799,7 +799,7 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 			iwl_read_radio_regs(fwrt, &dump_data);
 	}
 
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_ERROR_INFO) &&
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_ERROR_INFO) &&
 	    fwrt->dump.desc) {
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_ERROR_INFO);
 		dump_data->len = cpu_to_le32(sizeof(*dump_trig) +
@@ -815,7 +815,7 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 	if (fwrt->dump.monitor_only)
 		goto out;
 
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)) {
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_MEM)) {
 		const struct iwl_fw_dbg_mem_seg_tlv *fw_dbg_mem =
 			fwrt->fw->dbg.mem_tlv;
 
@@ -860,7 +860,7 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 	}
 
 	/* Dump fw's virtual image */
-	if (fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING) &&
+	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_PAGING) &&
 	    !fwrt->trans->cfg->gen2 &&
 	    fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size &&
 	    fwrt->fw_paging_db[0].fw_paging_block) {
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index b56d787ffc1e..0d5169c4cf51 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -309,12 +309,17 @@ static inline void iwl_fw_dump_conf_clear(struct iwl_fw_runtime *fwrt)
 
 void iwl_fw_error_dump_wk(struct work_struct *work);
 
+static inline bool iwl_fw_dbg_type_on(struct iwl_fw_runtime *fwrt, u32 type)
+{
+	return (fwrt->fw->dbg.dump_mask & BIT(type));
+}
+
 static inline bool iwl_fw_dbg_is_d3_debug_enabled(struct iwl_fw_runtime *fwrt)
 {
 	return fw_has_capa(&fwrt->fw->ucode_capa,
 			   IWL_UCODE_TLV_CAPA_D3_DEBUG) &&
 		fwrt->trans->cfg->d3_debug_data_length &&
-		fwrt->fw->dbg.dump_mask & BIT(IWL_FW_ERROR_DUMP_D3_DEBUG_DATA);
+		iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_D3_DEBUG_DATA);
 }
 
 void iwl_fw_dbg_read_d3_debug_data(struct iwl_fw_runtime *fwrt);
-- 
cgit v1.2.3


From 618e1701a2a41b2cf79d6e10d41dc23178f59597 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 30 Jul 2018 15:57:08 +0300
Subject: iwlwifi: mvm: remove unused conversion table

chanwidths isn't used now in debugfs-vif.c.  Remove it.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
index e9767bbdea1e..33b0af24a537 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
@@ -1441,15 +1441,6 @@ static ssize_t iwl_dbgfs_quota_min_read(struct file *file,
 	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
 }
 
-static const char * const chanwidths[] = {
-	[NL80211_CHAN_WIDTH_20_NOHT] = "noht",
-	[NL80211_CHAN_WIDTH_20] = "ht20",
-	[NL80211_CHAN_WIDTH_40] = "ht40",
-	[NL80211_CHAN_WIDTH_80] = "vht80",
-	[NL80211_CHAN_WIDTH_80P80] = "vht80p80",
-	[NL80211_CHAN_WIDTH_160] = "vht160",
-};
-
 #define MVM_DEBUGFS_WRITE_FILE_OPS(name, bufsz) \
 	_MVM_DEBUGFS_WRITE_FILE_OPS(name, bufsz, struct ieee80211_vif)
 #define MVM_DEBUGFS_READ_WRITE_FILE_OPS(name, bufsz) \
-- 
cgit v1.2.3


From f108703cb5f199d0fc98517ac29a997c4c646c94 Mon Sep 17 00:00:00 2001
From: Ihab Zhaika <ihab.zhaika@intel.com>
Date: Tue, 31 Jul 2018 09:53:09 +0300
Subject: iwlwifi: add new cards for 9560, 9462, 9461 and killer series

add few PCI ID'S for 9560, 9462, 9461 and killer series.

Cc: stable@vger.kernel.org
Signed-off-by: Ihab Zhaika <ihab.zhaika@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 50 +++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 9e015212c2c0..8d4711590dfc 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -513,6 +513,56 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x24FD, 0x9074, iwl8265_2ac_cfg)},
 
 /* 9000 Series */
+	{IWL_PCI_DEVICE(0x02F0, 0x0030, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0034, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0038, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x003C, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0060, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0064, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x00A0, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x00A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0230, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0234, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0238, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x023C, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0260, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0264, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x02A0, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x02A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x2030, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x2034, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x4030, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x4034, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x40A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x4234, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x42A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x0030, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x0034, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x0038, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x003C, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x0060, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x0064, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x00A0, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x00A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x0230, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x0234, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x0238, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x023C, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x0260, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x0264, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x02A0, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x02A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x2030, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x2034, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x4030, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x4034, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x40A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x4234, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x06F0, 0x42A4, iwl9462_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2526, 0x0010, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x0014, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x0018, iwl9260_2ac_cfg)},
-- 
cgit v1.2.3


From 56b657f7f9c07421a4f910b7e2b382184f1ddbc8 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 30 Jul 2018 11:06:09 +0300
Subject: iwlwifi: fw: use helper to determine whether to dump paging

Logic is there twice, and we'll need a third place
soon for ini dumping. In addition move the dumping
to a function, also to enable reuse.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 57 +++++++++++++++--------------
 drivers/net/wireless/intel/iwlwifi/fw/dbg.h |  8 ++++
 2 files changed, 37 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index aebdf433b409..58a980070445 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -639,6 +639,32 @@ out:
 	return fifo_len;
 }
 
+static void iwl_dump_paging(struct iwl_fw_runtime *fwrt,
+			    struct iwl_fw_error_dump_data **data)
+{
+	int i;
+
+	IWL_DEBUG_INFO(fwrt, "WRT paging dump\n");
+	for (i = 1; i < fwrt->num_of_paging_blk + 1; i++) {
+		struct iwl_fw_error_dump_paging *paging;
+		struct page *pages =
+			fwrt->fw_paging_db[i].fw_paging_block;
+		dma_addr_t addr = fwrt->fw_paging_db[i].fw_paging_phys;
+
+		(*data)->type = cpu_to_le32(IWL_FW_ERROR_DUMP_PAGING);
+		(*data)->len = cpu_to_le32(sizeof(*paging) +
+					     PAGING_BLOCK_SIZE);
+		paging =  (void *)(*data)->data;
+		paging->index = cpu_to_le32(i);
+		dma_sync_single_for_cpu(fwrt->trans->dev, addr,
+					PAGING_BLOCK_SIZE,
+					DMA_BIDIRECTIONAL);
+		memcpy(paging->data, page_address(pages),
+		       PAGING_BLOCK_SIZE);
+		(*data) = iwl_fw_error_next_data(*data);
+	}
+}
+
 static struct iwl_fw_error_dump_file *
 _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 		   struct iwl_fw_dump_ptrs *fw_error_dump)
@@ -707,10 +733,7 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 	}
 
 	/* Make room for fw's virtual image pages, if it exists */
-	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_PAGING) &&
-	    !fwrt->trans->cfg->gen2 &&
-	    fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size &&
-	    fwrt->fw_paging_db[0].fw_paging_block)
+	if (iwl_fw_dbg_is_paging_enabled(fwrt))
 		file_len += fwrt->num_of_paging_blk *
 			(sizeof(*dump_data) +
 			 sizeof(struct iwl_fw_error_dump_paging) +
@@ -860,30 +883,8 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 	}
 
 	/* Dump fw's virtual image */
-	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_PAGING) &&
-	    !fwrt->trans->cfg->gen2 &&
-	    fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size &&
-	    fwrt->fw_paging_db[0].fw_paging_block) {
-		IWL_DEBUG_INFO(fwrt, "WRT paging dump\n");
-		for (i = 1; i < fwrt->num_of_paging_blk + 1; i++) {
-			struct iwl_fw_error_dump_paging *paging;
-			struct page *pages =
-				fwrt->fw_paging_db[i].fw_paging_block;
-			dma_addr_t addr = fwrt->fw_paging_db[i].fw_paging_phys;
-
-			dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_PAGING);
-			dump_data->len = cpu_to_le32(sizeof(*paging) +
-						     PAGING_BLOCK_SIZE);
-			paging = (void *)dump_data->data;
-			paging->index = cpu_to_le32(i);
-			dma_sync_single_for_cpu(fwrt->trans->dev, addr,
-						PAGING_BLOCK_SIZE,
-						DMA_BIDIRECTIONAL);
-			memcpy(paging->data, page_address(pages),
-			       PAGING_BLOCK_SIZE);
-			dump_data = iwl_fw_error_next_data(dump_data);
-		}
-	}
+	if (iwl_fw_dbg_is_paging_enabled(fwrt))
+		iwl_dump_paging(fwrt, &dump_data);
 
 	if (prph_len) {
 		iwl_dump_prph(fwrt->trans, &dump_data,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index 0d5169c4cf51..4a5fa05c7ac2 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -322,6 +322,14 @@ static inline bool iwl_fw_dbg_is_d3_debug_enabled(struct iwl_fw_runtime *fwrt)
 		iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_D3_DEBUG_DATA);
 }
 
+static inline bool iwl_fw_dbg_is_paging_enabled(struct iwl_fw_runtime *fwrt)
+{
+	return iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_PAGING) &&
+		!fwrt->trans->cfg->gen2 &&
+		fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size &&
+		fwrt->fw_paging_db[0].fw_paging_block;
+}
+
 void iwl_fw_dbg_read_d3_debug_data(struct iwl_fw_runtime *fwrt);
 
 static inline void iwl_fw_flush_dump(struct iwl_fw_runtime *fwrt)
-- 
cgit v1.2.3


From 0d2e778e38e0ddffab4bb2b0e9ed2ad5165c4bf7 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 9 Nov 2018 18:16:28 +0100
Subject: net: phy: replace PHY_HAS_INTERRUPT with a check for config_intr and
 ack_interrupt

Flag PHY_HAS_INTERRUPT is used only here for this small check. I think
using interrupts isn't possible if a driver defines neither
config_intr nor ack_interrupts callback. So we can replace checking
flag PHY_HAS_INTERRUPT with checking for these callbacks.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index ab33d1777132..00a46218c3a2 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2074,6 +2074,11 @@ static void of_set_phy_eee_broken(struct phy_device *phydev)
 	phydev->eee_broken_modes = broken;
 }
 
+static bool phy_drv_supports_irq(struct phy_driver *phydrv)
+{
+	return phydrv->config_intr || phydrv->ack_interrupt;
+}
+
 /**
  * phy_probe - probe and init a PHY device
  * @dev: device to probe and init
@@ -2095,8 +2100,7 @@ static int phy_probe(struct device *dev)
 	/* Disable the interrupt if the PHY doesn't support it
 	 * but the interrupt is still a valid one
 	 */
-	if (!(phydrv->flags & PHY_HAS_INTERRUPT) &&
-	    phy_interrupt_is_valid(phydev))
+	 if (!phy_drv_supports_irq(phydrv) && phy_interrupt_is_valid(phydev))
 		phydev->irq = PHY_POLL;
 
 	if (phydrv->flags & PHY_IS_INTERNAL)
-- 
cgit v1.2.3


From a4307c0ec66131e722a8fa0f1da09646c46ee924 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 9 Nov 2018 18:17:22 +0100
Subject: net: phy: remove flag PHY_HAS_INTERRUPT from driver configs

Now that flag PHY_HAS_INTERRUPT has been replaced with a check for
callbacks config_intr and ack_interrupt, we can remove setting this
flag from all driver configs.
Last but not least remove flag PHY_HAS_INTERRUPT completely.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/amd.c          |  1 -
 drivers/net/phy/aquantia.c     |  6 ------
 drivers/net/phy/at803x.c       |  3 ---
 drivers/net/phy/bcm63xx.c      |  4 ++--
 drivers/net/phy/bcm87xx.c      |  2 --
 drivers/net/phy/broadcom.c     | 16 ----------------
 drivers/net/phy/cicada.c       |  2 --
 drivers/net/phy/davicom.c      |  4 ----
 drivers/net/phy/dp83640.c      |  1 -
 drivers/net/phy/dp83822.c      |  1 -
 drivers/net/phy/dp83848.c      |  1 -
 drivers/net/phy/dp83867.c      |  1 -
 drivers/net/phy/dp83tc811.c    |  1 -
 drivers/net/phy/icplus.c       |  1 -
 drivers/net/phy/intel-xway.c   | 10 ----------
 drivers/net/phy/lxt.c          |  2 --
 drivers/net/phy/marvell.c      | 15 ---------------
 drivers/net/phy/meson-gxl.c    |  2 +-
 drivers/net/phy/micrel.c       | 14 --------------
 drivers/net/phy/microchip.c    |  1 -
 drivers/net/phy/microchip_t1.c |  1 -
 drivers/net/phy/mscc.c         |  6 ------
 drivers/net/phy/national.c     |  1 -
 drivers/net/phy/qsemi.c        |  1 -
 drivers/net/phy/realtek.c      |  7 -------
 drivers/net/phy/smsc.c         |  7 +------
 drivers/net/phy/ste10Xp.c      |  2 --
 drivers/net/phy/vitesse.c      |  9 ---------
 include/linux/phy.h            |  5 ++---
 29 files changed, 6 insertions(+), 121 deletions(-)

diff --git a/drivers/net/phy/amd.c b/drivers/net/phy/amd.c
index 6fe5dc9201d0..9d0504f3e3b2 100644
--- a/drivers/net/phy/amd.c
+++ b/drivers/net/phy/amd.c
@@ -66,7 +66,6 @@ static struct phy_driver am79c_driver[] = { {
 	.name		= "AM79C874",
 	.phy_id_mask	= 0xfffffff0,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= am79c_config_init,
 	.ack_interrupt	= am79c_ack_interrupt,
 	.config_intr	= am79c_config_intr,
diff --git a/drivers/net/phy/aquantia.c b/drivers/net/phy/aquantia.c
index 632472cab3bb..efc0fbde97a1 100644
--- a/drivers/net/phy/aquantia.c
+++ b/drivers/net/phy/aquantia.c
@@ -116,7 +116,6 @@ static struct phy_driver aquantia_driver[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Aquantia AQ1202",
 	.features	= PHY_10GBIT_FULL_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.aneg_done	= genphy_c45_aneg_done,
 	.config_aneg    = aquantia_config_aneg,
 	.config_intr	= aquantia_config_intr,
@@ -128,7 +127,6 @@ static struct phy_driver aquantia_driver[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Aquantia AQ2104",
 	.features	= PHY_10GBIT_FULL_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.aneg_done	= genphy_c45_aneg_done,
 	.config_aneg    = aquantia_config_aneg,
 	.config_intr	= aquantia_config_intr,
@@ -140,7 +138,6 @@ static struct phy_driver aquantia_driver[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Aquantia AQR105",
 	.features	= PHY_10GBIT_FULL_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.aneg_done	= genphy_c45_aneg_done,
 	.config_aneg    = aquantia_config_aneg,
 	.config_intr	= aquantia_config_intr,
@@ -152,7 +149,6 @@ static struct phy_driver aquantia_driver[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Aquantia AQR106",
 	.features	= PHY_10GBIT_FULL_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.aneg_done	= genphy_c45_aneg_done,
 	.config_aneg    = aquantia_config_aneg,
 	.config_intr	= aquantia_config_intr,
@@ -164,7 +160,6 @@ static struct phy_driver aquantia_driver[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Aquantia AQR107",
 	.features	= PHY_10GBIT_FULL_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.aneg_done	= genphy_c45_aneg_done,
 	.config_aneg    = aquantia_config_aneg,
 	.config_intr	= aquantia_config_intr,
@@ -176,7 +171,6 @@ static struct phy_driver aquantia_driver[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Aquantia AQR405",
 	.features	= PHY_10GBIT_FULL_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.aneg_done	= genphy_c45_aneg_done,
 	.config_aneg    = aquantia_config_aneg,
 	.config_intr	= aquantia_config_intr,
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index e74a047a846e..f9432d053a22 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -379,7 +379,6 @@ static struct phy_driver at803x_driver[] = {
 	.suspend		= at803x_suspend,
 	.resume			= at803x_resume,
 	.features		= PHY_GBIT_FEATURES,
-	.flags			= PHY_HAS_INTERRUPT,
 	.ack_interrupt		= at803x_ack_interrupt,
 	.config_intr		= at803x_config_intr,
 }, {
@@ -395,7 +394,6 @@ static struct phy_driver at803x_driver[] = {
 	.suspend		= at803x_suspend,
 	.resume			= at803x_resume,
 	.features		= PHY_BASIC_FEATURES,
-	.flags			= PHY_HAS_INTERRUPT,
 	.ack_interrupt		= at803x_ack_interrupt,
 	.config_intr		= at803x_config_intr,
 }, {
@@ -410,7 +408,6 @@ static struct phy_driver at803x_driver[] = {
 	.suspend		= at803x_suspend,
 	.resume			= at803x_resume,
 	.features		= PHY_GBIT_FEATURES,
-	.flags			= PHY_HAS_INTERRUPT,
 	.aneg_done		= at803x_aneg_done,
 	.ack_interrupt		= &at803x_ack_interrupt,
 	.config_intr		= &at803x_config_intr,
diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index d95bffdec4c1..6a547b87ff04 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -69,7 +69,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	.phy_id_mask	= 0xfffffc00,
 	.name		= "Broadcom BCM63XX (1)",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT | PHY_IS_INTERNAL,
+	.flags		= PHY_IS_INTERNAL,
 	.config_init	= bcm63xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm63xx_config_intr,
@@ -78,7 +78,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	.phy_id		= 0x002bdc00,
 	.phy_id_mask	= 0xfffffc00,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT | PHY_IS_INTERNAL,
+	.flags		= PHY_IS_INTERNAL,
 	.config_init	= bcm63xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm63xx_config_intr,
diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c
index f7ebdcff53e4..64d5ba7bf94f 100644
--- a/drivers/net/phy/bcm87xx.c
+++ b/drivers/net/phy/bcm87xx.c
@@ -193,7 +193,6 @@ static struct phy_driver bcm87xx_driver[] = {
 	.phy_id		= PHY_ID_BCM8706,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Broadcom BCM8706",
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm87xx_config_init,
 	.config_aneg	= bcm87xx_config_aneg,
 	.read_status	= bcm87xx_read_status,
@@ -205,7 +204,6 @@ static struct phy_driver bcm87xx_driver[] = {
 	.phy_id		= PHY_ID_BCM8727,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Broadcom BCM8727",
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm87xx_config_init,
 	.config_aneg	= bcm87xx_config_aneg,
 	.read_status	= bcm87xx_read_status,
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index e86ea105c802..c73e265cd907 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -589,7 +589,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM5411",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm54xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm_phy_config_intr,
@@ -598,7 +597,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM5421",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm54xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm_phy_config_intr,
@@ -607,7 +605,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM54210E",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm54xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm_phy_config_intr,
@@ -616,7 +613,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM5461",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm54xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm_phy_config_intr,
@@ -625,7 +621,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM54612E",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm54xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm_phy_config_intr,
@@ -634,7 +629,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM54616S",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm54xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm_phy_config_intr,
@@ -643,7 +637,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM5464",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm54xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm_phy_config_intr,
@@ -652,7 +645,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM5481",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm54xx_config_init,
 	.config_aneg	= bcm5481_config_aneg,
 	.ack_interrupt	= bcm_phy_ack_intr,
@@ -662,7 +654,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask    = 0xfffffff0,
 	.name           = "Broadcom BCM54810",
 	.features       = PHY_GBIT_FEATURES,
-	.flags          = PHY_HAS_INTERRUPT,
 	.config_init    = bcm54xx_config_init,
 	.config_aneg    = bcm5481_config_aneg,
 	.ack_interrupt  = bcm_phy_ack_intr,
@@ -672,7 +663,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM5482",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm5482_config_init,
 	.read_status	= bcm5482_read_status,
 	.ack_interrupt	= bcm_phy_ack_intr,
@@ -682,7 +672,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM50610",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm54xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm_phy_config_intr,
@@ -691,7 +680,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM50610M",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm54xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm_phy_config_intr,
@@ -700,7 +688,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM57780",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm54xx_config_init,
 	.ack_interrupt	= bcm_phy_ack_intr,
 	.config_intr	= bcm_phy_config_intr,
@@ -709,7 +696,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCMAC131",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= brcm_fet_config_init,
 	.ack_interrupt	= brcm_fet_ack_interrupt,
 	.config_intr	= brcm_fet_config_intr,
@@ -718,7 +704,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Broadcom BCM5241",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= brcm_fet_config_init,
 	.ack_interrupt	= brcm_fet_ack_interrupt,
 	.config_intr	= brcm_fet_config_intr,
@@ -737,7 +722,6 @@ static struct phy_driver broadcom_drivers[] = {
 	.phy_id_mask    = 0xfffffff0,
 	.name           = "Broadcom BCM89610",
 	.features       = PHY_GBIT_FEATURES,
-	.flags          = PHY_HAS_INTERRUPT,
 	.config_init    = bcm54xx_config_init,
 	.ack_interrupt  = bcm_phy_ack_intr,
 	.config_intr    = bcm_phy_config_intr,
diff --git a/drivers/net/phy/cicada.c b/drivers/net/phy/cicada.c
index c05af00bf4b6..fea61c81bda9 100644
--- a/drivers/net/phy/cicada.c
+++ b/drivers/net/phy/cicada.c
@@ -108,7 +108,6 @@ static struct phy_driver cis820x_driver[] = {
 	.name		= "Cicada Cis8201",
 	.phy_id_mask	= 0x000ffff0,
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= &cis820x_config_init,
 	.ack_interrupt	= &cis820x_ack_interrupt,
 	.config_intr	= &cis820x_config_intr,
@@ -117,7 +116,6 @@ static struct phy_driver cis820x_driver[] = {
 	.name		= "Cicada Cis8204",
 	.phy_id_mask	= 0x000fffc0,
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= &cis820x_config_init,
 	.ack_interrupt	= &cis820x_ack_interrupt,
 	.config_intr	= &cis820x_config_intr,
diff --git a/drivers/net/phy/davicom.c b/drivers/net/phy/davicom.c
index 5ee99b3b428c..97162008f42b 100644
--- a/drivers/net/phy/davicom.c
+++ b/drivers/net/phy/davicom.c
@@ -150,7 +150,6 @@ static struct phy_driver dm91xx_driver[] = {
 	.name		= "Davicom DM9161E",
 	.phy_id_mask	= 0x0ffffff0,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= dm9161_config_init,
 	.config_aneg	= dm9161_config_aneg,
 	.ack_interrupt	= dm9161_ack_interrupt,
@@ -160,7 +159,6 @@ static struct phy_driver dm91xx_driver[] = {
 	.name		= "Davicom DM9161B/C",
 	.phy_id_mask	= 0x0ffffff0,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= dm9161_config_init,
 	.config_aneg	= dm9161_config_aneg,
 	.ack_interrupt	= dm9161_ack_interrupt,
@@ -170,7 +168,6 @@ static struct phy_driver dm91xx_driver[] = {
 	.name		= "Davicom DM9161A",
 	.phy_id_mask	= 0x0ffffff0,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= dm9161_config_init,
 	.config_aneg	= dm9161_config_aneg,
 	.ack_interrupt	= dm9161_ack_interrupt,
@@ -180,7 +177,6 @@ static struct phy_driver dm91xx_driver[] = {
 	.name		= "Davicom DM9131",
 	.phy_id_mask	= 0x0ffffff0,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.ack_interrupt	= dm9161_ack_interrupt,
 	.config_intr	= dm9161_config_intr,
 } };
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index edd4d44a386d..18b41bc345ab 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1521,7 +1521,6 @@ static struct phy_driver dp83640_driver = {
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "NatSemi DP83640",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.probe		= dp83640_probe,
 	.remove		= dp83640_remove,
 	.soft_reset	= dp83640_soft_reset,
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index 6e8a2a4f3a6e..24c7f149f3e6 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -318,7 +318,6 @@ static struct phy_driver dp83822_driver[] = {
 		.phy_id_mask = 0xfffffff0,
 		.name = "TI DP83822",
 		.features = PHY_BASIC_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.config_init = dp83822_config_init,
 		.soft_reset = dp83822_phy_reset,
 		.get_wol = dp83822_get_wol,
diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c
index 6e8e42361fd5..a6b55909d1dc 100644
--- a/drivers/net/phy/dp83848.c
+++ b/drivers/net/phy/dp83848.c
@@ -108,7 +108,6 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 		.phy_id_mask	= 0xfffffff0,			\
 		.name		= _name,			\
 		.features	= PHY_BASIC_FEATURES,		\
-		.flags		= PHY_HAS_INTERRUPT,		\
 								\
 		.soft_reset	= genphy_soft_reset,		\
 		.config_init	= _config_init,			\
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index b3935778b19f..da6a67d47ce9 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -334,7 +334,6 @@ static struct phy_driver dp83867_driver[] = {
 		.phy_id_mask	= 0xfffffff0,
 		.name		= "TI DP83867",
 		.features	= PHY_GBIT_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 
 		.config_init	= dp83867_config_init,
 		.soft_reset	= dp83867_phy_reset,
diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c
index 78cad134a79e..da13356999e5 100644
--- a/drivers/net/phy/dp83tc811.c
+++ b/drivers/net/phy/dp83tc811.c
@@ -346,7 +346,6 @@ static struct phy_driver dp83811_driver[] = {
 		.phy_id_mask = 0xfffffff0,
 		.name = "TI DP83TC811",
 		.features = PHY_BASIC_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.config_init = dp83811_config_init,
 		.config_aneg = dp83811_config_aneg,
 		.soft_reset = dp83811_phy_reset,
diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index 791587a49215..21ce68964204 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -234,7 +234,6 @@ static struct phy_driver icplus_driver[] = {
 	.name		= "ICPlus IP101A/G",
 	.phy_id_mask	= 0x0ffffff0,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.ack_interrupt	= ip101a_g_ack_interrupt,
 	.config_init	= &ip101a_g_config_init,
 	.suspend	= genphy_suspend,
diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c
index 7d936fb61c22..fc0f5024a29e 100644
--- a/drivers/net/phy/intel-xway.c
+++ b/drivers/net/phy/intel-xway.c
@@ -242,7 +242,6 @@ static struct phy_driver xway_gphy[] = {
 		.phy_id_mask	= 0xffffffff,
 		.name		= "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.3",
 		.features	= PHY_GBIT_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= xway_gphy_config_init,
 		.config_aneg	= xway_gphy14_config_aneg,
 		.ack_interrupt	= xway_gphy_ack_interrupt,
@@ -255,7 +254,6 @@ static struct phy_driver xway_gphy[] = {
 		.phy_id_mask	= 0xffffffff,
 		.name		= "Intel XWAY PHY22F (PEF 7061) v1.3",
 		.features	= PHY_BASIC_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= xway_gphy_config_init,
 		.config_aneg	= xway_gphy14_config_aneg,
 		.ack_interrupt	= xway_gphy_ack_interrupt,
@@ -268,7 +266,6 @@ static struct phy_driver xway_gphy[] = {
 		.phy_id_mask	= 0xffffffff,
 		.name		= "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.4",
 		.features	= PHY_GBIT_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= xway_gphy_config_init,
 		.config_aneg	= xway_gphy14_config_aneg,
 		.ack_interrupt	= xway_gphy_ack_interrupt,
@@ -281,7 +278,6 @@ static struct phy_driver xway_gphy[] = {
 		.phy_id_mask	= 0xffffffff,
 		.name		= "Intel XWAY PHY22F (PEF 7061) v1.4",
 		.features	= PHY_BASIC_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= xway_gphy_config_init,
 		.config_aneg	= xway_gphy14_config_aneg,
 		.ack_interrupt	= xway_gphy_ack_interrupt,
@@ -294,7 +290,6 @@ static struct phy_driver xway_gphy[] = {
 		.phy_id_mask	= 0xffffffff,
 		.name		= "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.5 / v1.6",
 		.features	= PHY_GBIT_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= xway_gphy_config_init,
 		.ack_interrupt	= xway_gphy_ack_interrupt,
 		.did_interrupt	= xway_gphy_did_interrupt,
@@ -306,7 +301,6 @@ static struct phy_driver xway_gphy[] = {
 		.phy_id_mask	= 0xffffffff,
 		.name		= "Intel XWAY PHY22F (PEF 7061) v1.5 / v1.6",
 		.features	= PHY_BASIC_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= xway_gphy_config_init,
 		.ack_interrupt	= xway_gphy_ack_interrupt,
 		.did_interrupt	= xway_gphy_did_interrupt,
@@ -318,7 +312,6 @@ static struct phy_driver xway_gphy[] = {
 		.phy_id_mask	= 0xffffffff,
 		.name		= "Intel XWAY PHY11G (xRX v1.1 integrated)",
 		.features	= PHY_GBIT_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= xway_gphy_config_init,
 		.ack_interrupt	= xway_gphy_ack_interrupt,
 		.did_interrupt	= xway_gphy_did_interrupt,
@@ -330,7 +323,6 @@ static struct phy_driver xway_gphy[] = {
 		.phy_id_mask	= 0xffffffff,
 		.name		= "Intel XWAY PHY22F (xRX v1.1 integrated)",
 		.features	= PHY_BASIC_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= xway_gphy_config_init,
 		.ack_interrupt	= xway_gphy_ack_interrupt,
 		.did_interrupt	= xway_gphy_did_interrupt,
@@ -342,7 +334,6 @@ static struct phy_driver xway_gphy[] = {
 		.phy_id_mask	= 0xffffffff,
 		.name		= "Intel XWAY PHY11G (xRX v1.2 integrated)",
 		.features	= PHY_GBIT_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= xway_gphy_config_init,
 		.ack_interrupt	= xway_gphy_ack_interrupt,
 		.did_interrupt	= xway_gphy_did_interrupt,
@@ -354,7 +345,6 @@ static struct phy_driver xway_gphy[] = {
 		.phy_id_mask	= 0xffffffff,
 		.name		= "Intel XWAY PHY22F (xRX v1.2 integrated)",
 		.features	= PHY_BASIC_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= xway_gphy_config_init,
 		.ack_interrupt	= xway_gphy_ack_interrupt,
 		.did_interrupt	= xway_gphy_did_interrupt,
diff --git a/drivers/net/phy/lxt.c b/drivers/net/phy/lxt.c
index c14b254b2879..c9e2c84c25c0 100644
--- a/drivers/net/phy/lxt.c
+++ b/drivers/net/phy/lxt.c
@@ -257,7 +257,6 @@ static struct phy_driver lxt97x_driver[] = {
 	.name		= "LXT970",
 	.phy_id_mask	= 0xfffffff0,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= lxt970_config_init,
 	.ack_interrupt	= lxt970_ack_interrupt,
 	.config_intr	= lxt970_config_intr,
@@ -266,7 +265,6 @@ static struct phy_driver lxt97x_driver[] = {
 	.name		= "LXT971",
 	.phy_id_mask	= 0xfffffff0,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.ack_interrupt	= lxt971_ack_interrupt,
 	.config_intr	= lxt971_config_intr,
 }, {
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index cbec296107bd..463c616a7281 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -2005,7 +2005,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1101",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1101_config_aneg,
@@ -2024,7 +2023,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1112",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &m88e1111_config_init,
 		.config_aneg = &marvell_config_aneg,
@@ -2043,7 +2041,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1111",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &m88e1111_config_init,
 		.config_aneg = &marvell_config_aneg,
@@ -2063,7 +2060,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1118",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &m88e1118_config_init,
 		.config_aneg = &m88e1118_config_aneg,
@@ -2082,7 +2078,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1121R",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = &m88e1121_probe,
 		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1121_config_aneg,
@@ -2103,7 +2098,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1318S",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &m88e1318_config_init,
 		.config_aneg = &m88e1318_config_aneg,
@@ -2126,7 +2120,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1145",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &m88e1145_config_init,
 		.config_aneg = &m88e1101_config_aneg,
@@ -2146,7 +2139,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1149R",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &m88e1149_config_init,
 		.config_aneg = &m88e1118_config_aneg,
@@ -2165,7 +2157,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1240",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &m88e1111_config_init,
 		.config_aneg = &marvell_config_aneg,
@@ -2184,7 +2175,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1116R",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &m88e1116r_config_init,
 		.ack_interrupt = &marvell_ack_interrupt,
@@ -2202,7 +2192,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1510",
 		.features = PHY_GBIT_FIBRE_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = &m88e1510_probe,
 		.config_init = &m88e1510_config_init,
 		.config_aneg = &m88e1510_config_aneg,
@@ -2226,7 +2215,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1540",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = m88e1510_probe,
 		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1510_config_aneg,
@@ -2248,7 +2236,6 @@ static struct phy_driver marvell_drivers[] = {
 		.name = "Marvell 88E1545",
 		.probe = m88e1510_probe,
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1510_config_aneg,
 		.read_status = &marvell_read_status,
@@ -2268,7 +2255,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E3016",
 		.features = PHY_BASIC_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &m88e3016_config_init,
 		.aneg_done = &marvell_aneg_done,
@@ -2289,7 +2275,6 @@ static struct phy_driver marvell_drivers[] = {
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E6390",
 		.features = PHY_GBIT_FEATURES,
-		.flags = PHY_HAS_INTERRUPT,
 		.probe = m88e6390_probe,
 		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1510_config_aneg,
diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c
index ddc2c5ea3787..b03bcf2c388a 100644
--- a/drivers/net/phy/meson-gxl.c
+++ b/drivers/net/phy/meson-gxl.c
@@ -232,7 +232,7 @@ static struct phy_driver meson_gxl_phy[] = {
 		.phy_id_mask	= 0xfffffff0,
 		.name		= "Meson GXL Internal PHY",
 		.features	= PHY_BASIC_FEATURES,
-		.flags		= PHY_IS_INTERNAL | PHY_HAS_INTERRUPT,
+		.flags		= PHY_IS_INTERNAL,
 		.config_init	= meson_gxl_config_init,
 		.aneg_done      = genphy_aneg_done,
 		.read_status	= meson_gxl_read_status,
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 9265dea79412..cb5783905a25 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -918,7 +918,6 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KS8737",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ks8737_type,
 	.config_init	= kszphy_config_init,
 	.ack_interrupt	= kszphy_ack_interrupt,
@@ -930,7 +929,6 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= 0x00ffffff,
 	.name		= "Micrel KSZ8021 or KSZ8031",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz8021_type,
 	.probe		= kszphy_probe,
 	.config_init	= kszphy_config_init,
@@ -946,7 +944,6 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= 0x00ffffff,
 	.name		= "Micrel KSZ8031",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz8021_type,
 	.probe		= kszphy_probe,
 	.config_init	= kszphy_config_init,
@@ -962,7 +959,6 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ8041",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz8041_type,
 	.probe		= kszphy_probe,
 	.config_init	= ksz8041_config_init,
@@ -979,7 +975,6 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ8041RNLI",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz8041_type,
 	.probe		= kszphy_probe,
 	.config_init	= kszphy_config_init,
@@ -995,7 +990,6 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ8051",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz8051_type,
 	.probe		= kszphy_probe,
 	.config_init	= kszphy_config_init,
@@ -1011,7 +1005,6 @@ static struct phy_driver ksphy_driver[] = {
 	.name		= "Micrel KSZ8001 or KS8721",
 	.phy_id_mask	= 0x00fffffc,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz8041_type,
 	.probe		= kszphy_probe,
 	.config_init	= kszphy_config_init,
@@ -1027,7 +1020,6 @@ static struct phy_driver ksphy_driver[] = {
 	.name		= "Micrel KSZ8081 or KSZ8091",
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz8081_type,
 	.probe		= kszphy_probe,
 	.config_init	= kszphy_config_init,
@@ -1043,7 +1035,6 @@ static struct phy_driver ksphy_driver[] = {
 	.name		= "Micrel KSZ8061",
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= kszphy_config_init,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
@@ -1054,7 +1045,6 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= 0x000ffffe,
 	.name		= "Micrel KSZ9021 Gigabit PHY",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz9021_type,
 	.probe		= kszphy_probe,
 	.config_init	= ksz9021_config_init,
@@ -1072,7 +1062,6 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ9031 Gigabit PHY",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz9021_type,
 	.probe		= kszphy_probe,
 	.config_init	= ksz9031_config_init,
@@ -1089,7 +1078,6 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Microchip KSZ9131 Gigabit PHY",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz9021_type,
 	.probe		= kszphy_probe,
 	.config_init	= ksz9131_config_init,
@@ -1115,7 +1103,6 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ886X Switch",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= kszphy_config_init,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
@@ -1124,7 +1111,6 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ8795",
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= kszphy_config_init,
 	.config_aneg	= ksz8873mll_config_aneg,
 	.read_status	= ksz8873mll_read_status,
diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 04b12e34da58..7557bebd5d7f 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -346,7 +346,6 @@ static struct phy_driver microchip_phy_driver[] = {
 	.name		= "Microchip LAN88xx",
 
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 
 	.probe		= lan88xx_probe,
 	.remove		= lan88xx_remove,
diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c
index c600a8509d60..3d09b471632c 100644
--- a/drivers/net/phy/microchip_t1.c
+++ b/drivers/net/phy/microchip_t1.c
@@ -47,7 +47,6 @@ static struct phy_driver microchip_t1_phy_driver[] = {
 		.name           = "Microchip LAN87xx T1",
 
 		.features       = PHY_BASIC_T1_FEATURES,
-		.flags          = PHY_HAS_INTERRUPT,
 
 		.config_init    = genphy_config_init,
 		.config_aneg    = genphy_config_aneg,
diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c
index a2e59f4f6f01..62269e578718 100644
--- a/drivers/net/phy/mscc.c
+++ b/drivers/net/phy/mscc.c
@@ -1833,7 +1833,6 @@ static struct phy_driver vsc85xx_driver[] = {
 	.name		= "Microsemi FE VSC8530",
 	.phy_id_mask	= 0xfffffff0,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.soft_reset	= &genphy_soft_reset,
 	.config_init	= &vsc85xx_config_init,
 	.config_aneg    = &vsc85xx_config_aneg,
@@ -1859,7 +1858,6 @@ static struct phy_driver vsc85xx_driver[] = {
 	.name		= "Microsemi VSC8531",
 	.phy_id_mask    = 0xfffffff0,
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.soft_reset	= &genphy_soft_reset,
 	.config_init    = &vsc85xx_config_init,
 	.config_aneg    = &vsc85xx_config_aneg,
@@ -1885,7 +1883,6 @@ static struct phy_driver vsc85xx_driver[] = {
 	.name		= "Microsemi FE VSC8540 SyncE",
 	.phy_id_mask	= 0xfffffff0,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.soft_reset	= &genphy_soft_reset,
 	.config_init	= &vsc85xx_config_init,
 	.config_aneg	= &vsc85xx_config_aneg,
@@ -1911,7 +1908,6 @@ static struct phy_driver vsc85xx_driver[] = {
 	.name		= "Microsemi VSC8541 SyncE",
 	.phy_id_mask    = 0xfffffff0,
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.soft_reset	= &genphy_soft_reset,
 	.config_init    = &vsc85xx_config_init,
 	.config_aneg    = &vsc85xx_config_aneg,
@@ -1937,7 +1933,6 @@ static struct phy_driver vsc85xx_driver[] = {
 	.name		= "Microsemi GE VSC8574 SyncE",
 	.phy_id_mask	= 0xfffffff0,
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.soft_reset	= &genphy_soft_reset,
 	.config_init    = &vsc8584_config_init,
 	.config_aneg    = &vsc85xx_config_aneg,
@@ -1964,7 +1959,6 @@ static struct phy_driver vsc85xx_driver[] = {
 	.name		= "Microsemi GE VSC8584 SyncE",
 	.phy_id_mask	= 0xfffffff0,
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.soft_reset	= &genphy_soft_reset,
 	.config_init    = &vsc8584_config_init,
 	.config_aneg    = &vsc85xx_config_aneg,
diff --git a/drivers/net/phy/national.c b/drivers/net/phy/national.c
index 2b1e336961f9..139bed2c8ab4 100644
--- a/drivers/net/phy/national.c
+++ b/drivers/net/phy/national.c
@@ -134,7 +134,6 @@ static struct phy_driver dp83865_driver[] = { {
 	.phy_id_mask = 0xfffffff0,
 	.name = "NatSemi DP83865",
 	.features = PHY_GBIT_FEATURES,
-	.flags = PHY_HAS_INTERRUPT,
 	.config_init = ns_config_init,
 	.ack_interrupt = ns_ack_interrupt,
 	.config_intr = ns_config_intr,
diff --git a/drivers/net/phy/qsemi.c b/drivers/net/phy/qsemi.c
index 889a4dce1648..cfe2313dbefd 100644
--- a/drivers/net/phy/qsemi.c
+++ b/drivers/net/phy/qsemi.c
@@ -116,7 +116,6 @@ static struct phy_driver qs6612_driver[] = { {
 	.name		= "QS6612",
 	.phy_id_mask	= 0xfffffff0,
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= qs6612_config_init,
 	.ack_interrupt	= qs6612_ack_interrupt,
 	.config_intr	= qs6612_config_intr,
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 7b1c89b3833c..0f8e5b1c9cb6 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -217,13 +217,11 @@ static struct phy_driver realtek_drvs[] = {
 		.name           = "RTL8201CP Ethernet",
 		.phy_id_mask    = 0x0000ffff,
 		.features       = PHY_BASIC_FEATURES,
-		.flags          = PHY_HAS_INTERRUPT,
 	}, {
 		.phy_id		= 0x001cc816,
 		.name		= "RTL8201F Fast Ethernet",
 		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_BASIC_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.ack_interrupt	= &rtl8201_ack_interrupt,
 		.config_intr	= &rtl8201_config_intr,
 		.suspend	= genphy_suspend,
@@ -243,7 +241,6 @@ static struct phy_driver realtek_drvs[] = {
 		.name		= "RTL8211B Gigabit Ethernet",
 		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.ack_interrupt	= &rtl821x_ack_interrupt,
 		.config_intr	= &rtl8211b_config_intr,
 		.read_mmd	= &genphy_read_mmd_unsupported,
@@ -263,7 +260,6 @@ static struct phy_driver realtek_drvs[] = {
 		.name		= "RTL8211DN Gigabit Ethernet",
 		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.ack_interrupt	= rtl821x_ack_interrupt,
 		.config_intr	= rtl8211e_config_intr,
 		.suspend	= genphy_suspend,
@@ -273,7 +269,6 @@ static struct phy_driver realtek_drvs[] = {
 		.name		= "RTL8211E Gigabit Ethernet",
 		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.ack_interrupt	= &rtl821x_ack_interrupt,
 		.config_intr	= &rtl8211e_config_intr,
 		.suspend	= genphy_suspend,
@@ -283,7 +278,6 @@ static struct phy_driver realtek_drvs[] = {
 		.name		= "RTL8211F Gigabit Ethernet",
 		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= &rtl8211f_config_init,
 		.ack_interrupt	= &rtl8211f_ack_interrupt,
 		.config_intr	= &rtl8211f_config_intr,
@@ -296,7 +290,6 @@ static struct phy_driver realtek_drvs[] = {
 		.name		= "RTL8366RB Gigabit Ethernet",
 		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
-		.flags		= PHY_HAS_INTERRUPT,
 		.config_init	= &rtl8366rb_config_init,
 		.suspend	= genphy_suspend,
 		.resume		= genphy_resume,
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index c328208388da..f9477ff55545 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -219,7 +219,6 @@ static struct phy_driver smsc_phy_driver[] = {
 	.name		= "SMSC LAN83C185",
 
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 
 	.probe		= smsc_phy_probe,
 
@@ -239,7 +238,6 @@ static struct phy_driver smsc_phy_driver[] = {
 	.name		= "SMSC LAN8187",
 
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 
 	.probe		= smsc_phy_probe,
 
@@ -264,7 +262,6 @@ static struct phy_driver smsc_phy_driver[] = {
 	.name		= "SMSC LAN8700",
 
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 
 	.probe		= smsc_phy_probe,
 
@@ -290,7 +287,6 @@ static struct phy_driver smsc_phy_driver[] = {
 	.name		= "SMSC LAN911x Internal PHY",
 
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 
 	.probe		= smsc_phy_probe,
 
@@ -309,7 +305,7 @@ static struct phy_driver smsc_phy_driver[] = {
 	.name		= "SMSC LAN8710/LAN8720",
 
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT | PHY_RST_AFTER_CLK_EN,
+	.flags		= PHY_RST_AFTER_CLK_EN,
 
 	.probe		= smsc_phy_probe,
 
@@ -335,7 +331,6 @@ static struct phy_driver smsc_phy_driver[] = {
 	.name		= "SMSC LAN8740",
 
 	.features	= PHY_BASIC_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 
 	.probe		= smsc_phy_probe,
 
diff --git a/drivers/net/phy/ste10Xp.c b/drivers/net/phy/ste10Xp.c
index 2fe9a87b55b5..33d733684f5b 100644
--- a/drivers/net/phy/ste10Xp.c
+++ b/drivers/net/phy/ste10Xp.c
@@ -87,7 +87,6 @@ static struct phy_driver ste10xp_pdriver[] = {
 	.phy_id_mask = 0xfffffff0,
 	.name = "STe101p",
 	.features = PHY_BASIC_FEATURES,
-	.flags = PHY_HAS_INTERRUPT,
 	.config_init = ste10Xp_config_init,
 	.ack_interrupt = ste10Xp_ack_interrupt,
 	.config_intr = ste10Xp_config_intr,
@@ -98,7 +97,6 @@ static struct phy_driver ste10xp_pdriver[] = {
 	.phy_id_mask = 0xffffffff,
 	.name = "STe100p",
 	.features = PHY_BASIC_FEATURES,
-	.flags = PHY_HAS_INTERRUPT,
 	.config_init = ste10Xp_config_init,
 	.ack_interrupt = ste10Xp_ack_interrupt,
 	.config_intr = ste10Xp_config_intr,
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index fbf9ad429593..4ca513feba0e 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -399,7 +399,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.name           = "Vitesse VSC8234",
 	.phy_id_mask    = 0x000ffff0,
 	.features       = PHY_GBIT_FEATURES,
-	.flags          = PHY_HAS_INTERRUPT,
 	.config_init    = &vsc824x_config_init,
 	.config_aneg    = &vsc82x4_config_aneg,
 	.ack_interrupt  = &vsc824x_ack_interrupt,
@@ -409,7 +408,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.name		= "Vitesse VSC8244",
 	.phy_id_mask	= 0x000fffc0,
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= &vsc824x_config_init,
 	.config_aneg	= &vsc82x4_config_aneg,
 	.ack_interrupt	= &vsc824x_ack_interrupt,
@@ -419,7 +417,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.name		= "Vitesse VSC8514",
 	.phy_id_mask	= 0x000ffff0,
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= &vsc824x_config_init,
 	.config_aneg	= &vsc82x4_config_aneg,
 	.ack_interrupt	= &vsc824x_ack_interrupt,
@@ -429,7 +426,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.name           = "Vitesse VSC8572",
 	.phy_id_mask    = 0x000ffff0,
 	.features       = PHY_GBIT_FEATURES,
-	.flags          = PHY_HAS_INTERRUPT,
 	.config_init    = &vsc824x_config_init,
 	.config_aneg    = &vsc82x4_config_aneg,
 	.ack_interrupt  = &vsc824x_ack_interrupt,
@@ -439,7 +435,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.name           = "Vitesse VSC8574",
 	.phy_id_mask    = 0x000ffff0,
 	.features       = PHY_GBIT_FEATURES,
-	.flags          = PHY_HAS_INTERRUPT,
 	.config_init    = &vsc824x_config_init,
 	.config_aneg    = &vsc82x4_config_aneg,
 	.ack_interrupt  = &vsc824x_ack_interrupt,
@@ -449,7 +444,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.name           = "Vitesse VSC8601",
 	.phy_id_mask    = 0x000ffff0,
 	.features       = PHY_GBIT_FEATURES,
-	.flags          = PHY_HAS_INTERRUPT,
 	.config_init    = &vsc8601_config_init,
 	.ack_interrupt  = &vsc824x_ack_interrupt,
 	.config_intr    = &vsc82xx_config_intr,
@@ -494,7 +488,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.name           = "Vitesse VSC8662",
 	.phy_id_mask    = 0x000ffff0,
 	.features       = PHY_GBIT_FEATURES,
-	.flags          = PHY_HAS_INTERRUPT,
 	.config_init    = &vsc824x_config_init,
 	.config_aneg    = &vsc82x4_config_aneg,
 	.ack_interrupt  = &vsc824x_ack_interrupt,
@@ -505,7 +498,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.phy_id_mask	= 0x000ffff0,
 	.name		= "Vitesse VSC8221",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= &vsc8221_config_init,
 	.ack_interrupt	= &vsc824x_ack_interrupt,
 	.config_intr	= &vsc82xx_config_intr,
@@ -515,7 +507,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.phy_id_mask	= 0x000ffff0,
 	.name		= "Vitesse VSC8211",
 	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= &vsc8221_config_init,
 	.ack_interrupt	= &vsc824x_ack_interrupt,
 	.config_intr	= &vsc82xx_config_intr,
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3299ec6e69f3..59bb31ee132f 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -66,9 +66,8 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini
 #define PHY_POLL		-1
 #define PHY_IGNORE_INTERRUPT	-2
 
-#define PHY_HAS_INTERRUPT	0x00000001
-#define PHY_IS_INTERNAL		0x00000002
-#define PHY_RST_AFTER_CLK_EN	0x00000004
+#define PHY_IS_INTERNAL		0x00000001
+#define PHY_RST_AFTER_CLK_EN	0x00000002
 #define MDIO_DEVICE_IS_PHY	0x80000000
 
 /* Interface Mode definitions */
-- 
cgit v1.2.3


From 8deeb6309cc447b9b35939558f18e2164dd110df Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 9 Nov 2018 18:55:50 +0100
Subject: net: phy: don't set state PHY_CHANGELINK in phy_change

State PHY_CHANGELINK isn't needed here, we can call the state machine
directly. We just have to remove the check for phy_polling_mode() to
make this work also in interrupt mode. Removing this check doesn't
cause any overhead because when not polling the state machine is
called only if required by some event.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 8 --------
 include/linux/phy.h   | 7 ++-----
 2 files changed, 2 insertions(+), 13 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 8dac890f32bf..da41420dfd11 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -738,11 +738,6 @@ static irqreturn_t phy_change(struct phy_device *phydev)
 				goto phy_err;
 	}
 
-	mutex_lock(&phydev->lock);
-	if ((PHY_RUNNING == phydev->state) || (PHY_NOLINK == phydev->state))
-		phydev->state = PHY_CHANGELINK;
-	mutex_unlock(&phydev->lock);
-
 	/* reschedule state queue work to run as soon as possible */
 	phy_trigger_machine(phydev);
 
@@ -946,9 +941,6 @@ void phy_state_machine(struct work_struct *work)
 		break;
 	case PHY_NOLINK:
 	case PHY_RUNNING:
-		if (!phy_polling_mode(phydev))
-			break;
-		/* fall through */
 	case PHY_CHANGELINK:
 	case PHY_RESUMING:
 		err = phy_check_link_status(phydev);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 59bb31ee132f..7db07e69c88f 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -298,7 +298,7 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
  * - timer moves to NOLINK or RUNNING
  *
  * NOLINK: PHY is up, but not currently plugged in.
- * - If the timer notes that the link comes back, we move to RUNNING
+ * - irq or timer will set RUNNING if link comes back
  * - phy_stop moves to HALTED
  *
  * FORCING: PHY is being configured with forced settings
@@ -309,10 +309,7 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
  *
  * RUNNING: PHY is currently up, running, and possibly sending
  * and/or receiving packets
- * - timer will set CHANGELINK if we're polling (this ensures the
- *   link state is polled every other cycle of this state machine,
- *   which makes it every other second)
- * - irq will set CHANGELINK
+ * - irq or timer will set NOLINK if link goes down
  * - phy_stop moves to HALTED
  *
  * CHANGELINK: PHY experienced a change in link state
-- 
cgit v1.2.3


From d73a2156bdad6bdf7e0c42051c5ebbea11f6271e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 9 Nov 2018 18:56:52 +0100
Subject: net: phy: simplify phy_mac_interrupt and related functions

When using phy_mac_interrupt() the irq number is set to
PHY_IGNORE_INTERRUPT, therefore phy_interrupt_is_valid() returns false.
As a result phy_change() effectively just calls phy_trigger_machine()
when called from phy_mac_interrupt() via phy_change_work(). So we can
call phy_trigger_machine() from phy_mac_interrupt() directly and
remove some now unneeded code.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c        | 14 +-------------
 drivers/net/phy/phy_device.c |  1 -
 include/linux/phy.h          |  3 ---
 3 files changed, 1 insertion(+), 17 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index da41420dfd11..ce1e8130a38f 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -750,18 +750,6 @@ phy_err:
 	return IRQ_NONE;
 }
 
-/**
- * phy_change_work - Scheduled by the phy_mac_interrupt to handle PHY changes
- * @work: work_struct that describes the work to be done
- */
-void phy_change_work(struct work_struct *work)
-{
-	struct phy_device *phydev =
-		container_of(work, struct phy_device, phy_queue);
-
-	phy_change(phydev);
-}
-
 /**
  * phy_interrupt - PHY interrupt handler
  * @irq: interrupt line
@@ -1005,7 +993,7 @@ void phy_state_machine(struct work_struct *work)
 void phy_mac_interrupt(struct phy_device *phydev)
 {
 	/* Trigger a state machine change */
-	queue_work(system_power_efficient_wq, &phydev->phy_queue);
+	phy_trigger_machine(phydev);
 }
 EXPORT_SYMBOL(phy_mac_interrupt);
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 00a46218c3a2..0f56d408b033 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -587,7 +587,6 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
 
 	mutex_init(&dev->lock);
 	INIT_DELAYED_WORK(&dev->state_queue, phy_state_machine);
-	INIT_WORK(&dev->phy_queue, phy_change_work);
 
 	/* Request the appropriate module unconditionally; don't
 	 * bother trying to do so only if it isn't already loaded,
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 7db07e69c88f..17d1f64723e4 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -369,7 +369,6 @@ struct phy_c45_device_ids {
  * giving up on the current attempt at acquiring a link
  * irq: IRQ number of the PHY's interrupt (-1 if none)
  * phy_timer: The timer for handling the state machine
- * phy_queue: A work_queue for the phy_mac_interrupt
  * attached_dev: The attached enet driver's device instance ptr
  * adjust_link: Callback for the enet controller to respond to
  * changes in the link state.
@@ -454,7 +453,6 @@ struct phy_device {
 	void *priv;
 
 	/* Interrupt and Polling infrastructure */
-	struct work_struct phy_queue;
 	struct delayed_work state_queue;
 
 	struct mutex lock;
@@ -1029,7 +1027,6 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner);
 int phy_drivers_register(struct phy_driver *new_driver, int n,
 			 struct module *owner);
 void phy_state_machine(struct work_struct *work);
-void phy_change_work(struct work_struct *work);
 void phy_mac_interrupt(struct phy_device *phydev);
 void phy_start_machine(struct phy_device *phydev);
 void phy_stop_machine(struct phy_device *phydev);
-- 
cgit v1.2.3


From 34d884e3dae6ecf0f9e9cc9be7632703a23f9f96 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 9 Nov 2018 18:58:01 +0100
Subject: net: phy: improve and inline phy_change

Now that phy_mac_interrupt() doesn't call phy_change() any longer it's
called from phy_interrupt() only. Therefore phy_interrupt_is_valid()
returns true always and the check can be removed.
In case of PHY_HALTED phy_interrupt() bails out immediately,
therefore the second check for PHY_HALTED including the call to
phy_disable_interrupts() can be removed.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 47 +++++++++++++++--------------------------------
 1 file changed, 15 insertions(+), 32 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index ce1e8130a38f..083977d2f187 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -722,41 +722,12 @@ static int phy_disable_interrupts(struct phy_device *phydev)
 	return phy_clear_interrupt(phydev);
 }
 
-/**
- * phy_change - Called by the phy_interrupt to handle PHY changes
- * @phydev: phy_device struct that interrupted
- */
-static irqreturn_t phy_change(struct phy_device *phydev)
-{
-	if (phy_interrupt_is_valid(phydev)) {
-		if (phydev->drv->did_interrupt &&
-		    !phydev->drv->did_interrupt(phydev))
-			return IRQ_NONE;
-
-		if (phydev->state == PHY_HALTED)
-			if (phy_disable_interrupts(phydev))
-				goto phy_err;
-	}
-
-	/* reschedule state queue work to run as soon as possible */
-	phy_trigger_machine(phydev);
-
-	if (phy_interrupt_is_valid(phydev) && phy_clear_interrupt(phydev))
-		goto phy_err;
-	return IRQ_HANDLED;
-
-phy_err:
-	phy_error(phydev);
-	return IRQ_NONE;
-}
-
 /**
  * phy_interrupt - PHY interrupt handler
  * @irq: interrupt line
  * @phy_dat: phy_device pointer
  *
- * Description: When a PHY interrupt occurs, the handler disables
- * interrupts, and uses phy_change to handle the interrupt.
+ * Description: Handle PHY interrupt
  */
 static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 {
@@ -765,7 +736,19 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 	if (PHY_HALTED == phydev->state)
 		return IRQ_NONE;		/* It can't be ours.  */
 
-	return phy_change(phydev);
+	if (phydev->drv->did_interrupt && !phydev->drv->did_interrupt(phydev))
+		return IRQ_NONE;
+
+	/* reschedule state queue work to run as soon as possible */
+	phy_trigger_machine(phydev);
+
+	if (phy_clear_interrupt(phydev))
+		goto phy_err;
+	return IRQ_HANDLED;
+
+phy_err:
+	phy_error(phydev);
+	return IRQ_NONE;
 }
 
 /**
@@ -846,7 +829,7 @@ out_unlock:
 	phy_state_machine(&phydev->state_queue.work);
 
 	/* Cannot call flush_scheduled_work() here as desired because
-	 * of rtnl_lock(), but PHY_HALTED shall guarantee phy_change()
+	 * of rtnl_lock(), but PHY_HALTED shall guarantee irq handler
 	 * will not reenable interrupts.
 	 */
 }
-- 
cgit v1.2.3


From aa2af2eb447c9a21c8c9e8d2336672bb620cf900 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 10 Nov 2018 00:39:14 +0100
Subject: net: phy: add macros for PHYID matching

Add macros for PHYID matching to be used in PHY driver configs.
By using these macros some boilerplate code can be avoided.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phy.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 17d1f64723e4..03005c65e02d 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -651,6 +651,10 @@ struct phy_driver {
 #define PHY_ANY_ID "MATCH ANY PHY"
 #define PHY_ANY_UID 0xffffffff
 
+#define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 0)
+#define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 4)
+#define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 10)
+
 /* A Structure for boards to register fixups with the PHY Lib */
 struct phy_fixup {
 	struct list_head list;
-- 
cgit v1.2.3


From ca49493633fc3f50836cc6ee690721f2c3527084 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 10 Nov 2018 00:40:37 +0100
Subject: net: phy: realtek: use new PHYID matching macros

Use new macros for PHYID matching to avoid boilerplate code.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/realtek.c | 29 ++++++++++-------------------
 1 file changed, 10 insertions(+), 19 deletions(-)

diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 0f8e5b1c9cb6..c6010fb1aa0f 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -213,14 +213,12 @@ static int rtl8366rb_config_init(struct phy_device *phydev)
 
 static struct phy_driver realtek_drvs[] = {
 	{
-		.phy_id         = 0x00008201,
+		PHY_ID_MATCH_EXACT(0x00008201),
 		.name           = "RTL8201CP Ethernet",
-		.phy_id_mask    = 0x0000ffff,
 		.features       = PHY_BASIC_FEATURES,
 	}, {
-		.phy_id		= 0x001cc816,
+		PHY_ID_MATCH_EXACT(0x001cc816),
 		.name		= "RTL8201F Fast Ethernet",
-		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_BASIC_FEATURES,
 		.ack_interrupt	= &rtl8201_ack_interrupt,
 		.config_intr	= &rtl8201_config_intr,
@@ -229,17 +227,15 @@ static struct phy_driver realtek_drvs[] = {
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
 	}, {
-		.phy_id		= 0x001cc910,
+		PHY_ID_MATCH_EXACT(0x001cc910),
 		.name		= "RTL8211 Gigabit Ethernet",
-		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
 		.config_aneg	= rtl8211_config_aneg,
 		.read_mmd	= &genphy_read_mmd_unsupported,
 		.write_mmd	= &genphy_write_mmd_unsupported,
 	}, {
-		.phy_id		= 0x001cc912,
+		PHY_ID_MATCH_EXACT(0x001cc912),
 		.name		= "RTL8211B Gigabit Ethernet",
-		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
 		.ack_interrupt	= &rtl821x_ack_interrupt,
 		.config_intr	= &rtl8211b_config_intr,
@@ -248,35 +244,31 @@ static struct phy_driver realtek_drvs[] = {
 		.suspend	= rtl8211b_suspend,
 		.resume		= rtl8211b_resume,
 	}, {
-		.phy_id		= 0x001cc913,
+		PHY_ID_MATCH_EXACT(0x001cc913),
 		.name		= "RTL8211C Gigabit Ethernet",
-		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
 		.config_init	= rtl8211c_config_init,
 		.read_mmd	= &genphy_read_mmd_unsupported,
 		.write_mmd	= &genphy_write_mmd_unsupported,
 	}, {
-		.phy_id		= 0x001cc914,
+		PHY_ID_MATCH_EXACT(0x001cc914),
 		.name		= "RTL8211DN Gigabit Ethernet",
-		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
 		.ack_interrupt	= rtl821x_ack_interrupt,
 		.config_intr	= rtl8211e_config_intr,
 		.suspend	= genphy_suspend,
 		.resume		= genphy_resume,
 	}, {
-		.phy_id		= 0x001cc915,
+		PHY_ID_MATCH_EXACT(0x001cc915),
 		.name		= "RTL8211E Gigabit Ethernet",
-		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
 		.ack_interrupt	= &rtl821x_ack_interrupt,
 		.config_intr	= &rtl8211e_config_intr,
 		.suspend	= genphy_suspend,
 		.resume		= genphy_resume,
 	}, {
-		.phy_id		= 0x001cc916,
+		PHY_ID_MATCH_EXACT(0x001cc916),
 		.name		= "RTL8211F Gigabit Ethernet",
-		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
 		.config_init	= &rtl8211f_config_init,
 		.ack_interrupt	= &rtl8211f_ack_interrupt,
@@ -286,9 +278,8 @@ static struct phy_driver realtek_drvs[] = {
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
 	}, {
-		.phy_id		= 0x001cc961,
+		PHY_ID_MATCH_EXACT(0x001cc961),
 		.name		= "RTL8366RB Gigabit Ethernet",
-		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_GBIT_FEATURES,
 		.config_init	= &rtl8366rb_config_init,
 		.suspend	= genphy_suspend,
@@ -299,7 +290,7 @@ static struct phy_driver realtek_drvs[] = {
 module_phy_driver(realtek_drvs);
 
 static const struct mdio_device_id __maybe_unused realtek_tbl[] = {
-	{ 0x001cc800, GENMASK(31, 10) },
+	{ PHY_ID_MATCH_VENDOR(0x001cc800) },
 	{ }
 };
 
-- 
cgit v1.2.3


From 7f76fa36754b08d9709ae50cd0a9477a6f998b21 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Fri, 9 Nov 2018 21:21:26 -0800
Subject: net: sched: register callbacks for indirect tc block binds

Currently drivers can register to receive TC block bind/unbind callbacks
by implementing the setup_tc ndo in any of their given netdevs. However,
drivers may also be interested in binds to higher level devices (e.g.
tunnel drivers) to potentially offload filters applied to them.

Introduce indirect block devs which allows drivers to register callbacks
for block binds on other devices. The callback is triggered when the
device is bound to a block, allowing the driver to register for rules
applied to that block using already available functions.

Freeing an indirect block callback will trigger an unbind event (if
necessary) to direct the driver to remove any offloaded rules and unreg
any block rule callbacks. It is the responsibility of the implementing
driver to clean any registered indirect block callbacks before exiting,
if the block it still active at such a time.

Allow registering an indirect block dev callback for a device that is
already bound to a block. In this case (if it is an ingress block),
register and also trigger the callback meaning that any already installed
rules can be replayed to the calling driver.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h     |  34 ++++++
 include/net/sch_generic.h |   3 +
 net/sched/cls_api.c       | 256 +++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 292 insertions(+), 1 deletion(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 00f71644fbcd..f6c0cd29dea4 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -81,6 +81,14 @@ void __tcf_block_cb_unregister(struct tcf_block *block,
 			       struct tcf_block_cb *block_cb);
 void tcf_block_cb_unregister(struct tcf_block *block,
 			     tc_setup_cb_t *cb, void *cb_ident);
+int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
+				tc_indr_block_bind_cb_t *cb, void *cb_ident);
+int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
+			      tc_indr_block_bind_cb_t *cb, void *cb_ident);
+void __tc_indr_block_cb_unregister(struct net_device *dev,
+				   tc_indr_block_bind_cb_t *cb, void *cb_ident);
+void tc_indr_block_cb_unregister(struct net_device *dev,
+				 tc_indr_block_bind_cb_t *cb, void *cb_ident);
 
 int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		 struct tcf_result *res, bool compat_mode);
@@ -183,6 +191,32 @@ void tcf_block_cb_unregister(struct tcf_block *block,
 {
 }
 
+static inline
+int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
+				tc_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+	return 0;
+}
+
+static inline
+int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
+			      tc_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+	return 0;
+}
+
+static inline
+void __tc_indr_block_cb_unregister(struct net_device *dev,
+				   tc_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+}
+
+static inline
+void tc_indr_block_cb_unregister(struct net_device *dev,
+				 tc_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+}
+
 static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			       struct tcf_result *res, bool compat_mode)
 {
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index a8dd1fc141b6..9481f2c142e2 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -24,6 +24,9 @@ struct bpf_flow_keys;
 typedef int tc_setup_cb_t(enum tc_setup_type type,
 			  void *type_data, void *cb_priv);
 
+typedef int tc_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv,
+				    enum tc_setup_type type, void *type_data);
+
 struct qdisc_rate_table {
 	struct tc_ratespec rate;
 	u32		data[256];
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index f427a1e00e7e..d92f44ac4c39 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -25,6 +25,7 @@
 #include <linux/kmod.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
+#include <linux/rhashtable.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -365,6 +366,245 @@ static void tcf_chain_flush(struct tcf_chain *chain)
 	}
 }
 
+static struct tcf_block *tc_dev_ingress_block(struct net_device *dev)
+{
+	const struct Qdisc_class_ops *cops;
+	struct Qdisc *qdisc;
+
+	if (!dev_ingress_queue(dev))
+		return NULL;
+
+	qdisc = dev_ingress_queue(dev)->qdisc_sleeping;
+	if (!qdisc)
+		return NULL;
+
+	cops = qdisc->ops->cl_ops;
+	if (!cops)
+		return NULL;
+
+	if (!cops->tcf_block)
+		return NULL;
+
+	return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL);
+}
+
+static struct rhashtable indr_setup_block_ht;
+
+struct tc_indr_block_dev {
+	struct rhash_head ht_node;
+	struct net_device *dev;
+	unsigned int refcnt;
+	struct list_head cb_list;
+	struct tcf_block *block;
+};
+
+struct tc_indr_block_cb {
+	struct list_head list;
+	void *cb_priv;
+	tc_indr_block_bind_cb_t *cb;
+	void *cb_ident;
+};
+
+static const struct rhashtable_params tc_indr_setup_block_ht_params = {
+	.key_offset	= offsetof(struct tc_indr_block_dev, dev),
+	.head_offset	= offsetof(struct tc_indr_block_dev, ht_node),
+	.key_len	= sizeof(struct net_device *),
+};
+
+static struct tc_indr_block_dev *
+tc_indr_block_dev_lookup(struct net_device *dev)
+{
+	return rhashtable_lookup_fast(&indr_setup_block_ht, &dev,
+				      tc_indr_setup_block_ht_params);
+}
+
+static struct tc_indr_block_dev *tc_indr_block_dev_get(struct net_device *dev)
+{
+	struct tc_indr_block_dev *indr_dev;
+
+	indr_dev = tc_indr_block_dev_lookup(dev);
+	if (indr_dev)
+		goto inc_ref;
+
+	indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL);
+	if (!indr_dev)
+		return NULL;
+
+	INIT_LIST_HEAD(&indr_dev->cb_list);
+	indr_dev->dev = dev;
+	indr_dev->block = tc_dev_ingress_block(dev);
+	if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node,
+				   tc_indr_setup_block_ht_params)) {
+		kfree(indr_dev);
+		return NULL;
+	}
+
+inc_ref:
+	indr_dev->refcnt++;
+	return indr_dev;
+}
+
+static void tc_indr_block_dev_put(struct tc_indr_block_dev *indr_dev)
+{
+	if (--indr_dev->refcnt)
+		return;
+
+	rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node,
+			       tc_indr_setup_block_ht_params);
+	kfree(indr_dev);
+}
+
+static struct tc_indr_block_cb *
+tc_indr_block_cb_lookup(struct tc_indr_block_dev *indr_dev,
+			tc_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+	struct tc_indr_block_cb *indr_block_cb;
+
+	list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
+		if (indr_block_cb->cb == cb &&
+		    indr_block_cb->cb_ident == cb_ident)
+			return indr_block_cb;
+	return NULL;
+}
+
+static struct tc_indr_block_cb *
+tc_indr_block_cb_add(struct tc_indr_block_dev *indr_dev, void *cb_priv,
+		     tc_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+	struct tc_indr_block_cb *indr_block_cb;
+
+	indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident);
+	if (indr_block_cb)
+		return ERR_PTR(-EEXIST);
+
+	indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL);
+	if (!indr_block_cb)
+		return ERR_PTR(-ENOMEM);
+
+	indr_block_cb->cb_priv = cb_priv;
+	indr_block_cb->cb = cb;
+	indr_block_cb->cb_ident = cb_ident;
+	list_add(&indr_block_cb->list, &indr_dev->cb_list);
+
+	return indr_block_cb;
+}
+
+static void tc_indr_block_cb_del(struct tc_indr_block_cb *indr_block_cb)
+{
+	list_del(&indr_block_cb->list);
+	kfree(indr_block_cb);
+}
+
+static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev,
+				  struct tc_indr_block_cb *indr_block_cb,
+				  enum tc_block_command command)
+{
+	struct tc_block_offload bo = {
+		.command	= command,
+		.binder_type	= TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
+		.block		= indr_dev->block,
+	};
+
+	if (!indr_dev->block)
+		return;
+
+	indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
+			  &bo);
+}
+
+int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
+				tc_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+	struct tc_indr_block_cb *indr_block_cb;
+	struct tc_indr_block_dev *indr_dev;
+	int err;
+
+	indr_dev = tc_indr_block_dev_get(dev);
+	if (!indr_dev)
+		return -ENOMEM;
+
+	indr_block_cb = tc_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident);
+	err = PTR_ERR_OR_ZERO(indr_block_cb);
+	if (err)
+		goto err_dev_put;
+
+	tc_indr_block_ing_cmd(indr_dev, indr_block_cb, TC_BLOCK_BIND);
+	return 0;
+
+err_dev_put:
+	tc_indr_block_dev_put(indr_dev);
+	return err;
+}
+EXPORT_SYMBOL_GPL(__tc_indr_block_cb_register);
+
+int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
+			      tc_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+	int err;
+
+	rtnl_lock();
+	err = __tc_indr_block_cb_register(dev, cb_priv, cb, cb_ident);
+	rtnl_unlock();
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(tc_indr_block_cb_register);
+
+void __tc_indr_block_cb_unregister(struct net_device *dev,
+				   tc_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+	struct tc_indr_block_cb *indr_block_cb;
+	struct tc_indr_block_dev *indr_dev;
+
+	indr_dev = tc_indr_block_dev_lookup(dev);
+	if (!indr_dev)
+		return;
+
+	indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident);
+	if (!indr_block_cb)
+		return;
+
+	/* Send unbind message if required to free any block cbs. */
+	tc_indr_block_ing_cmd(indr_dev, indr_block_cb, TC_BLOCK_UNBIND);
+	tc_indr_block_cb_del(indr_block_cb);
+	tc_indr_block_dev_put(indr_dev);
+}
+EXPORT_SYMBOL_GPL(__tc_indr_block_cb_unregister);
+
+void tc_indr_block_cb_unregister(struct net_device *dev,
+				 tc_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+	rtnl_lock();
+	__tc_indr_block_cb_unregister(dev, cb, cb_ident);
+	rtnl_unlock();
+}
+EXPORT_SYMBOL_GPL(tc_indr_block_cb_unregister);
+
+static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
+			       struct tcf_block_ext_info *ei,
+			       enum tc_block_command command,
+			       struct netlink_ext_ack *extack)
+{
+	struct tc_indr_block_cb *indr_block_cb;
+	struct tc_indr_block_dev *indr_dev;
+	struct tc_block_offload bo = {
+		.command	= command,
+		.binder_type	= ei->binder_type,
+		.block		= block,
+		.extack		= extack,
+	};
+
+	indr_dev = tc_indr_block_dev_lookup(dev);
+	if (!indr_dev)
+		return;
+
+	indr_dev->block = command == TC_BLOCK_BIND ? block : NULL;
+
+	list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
+		indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
+				  &bo);
+}
+
 static bool tcf_block_offload_in_use(struct tcf_block *block)
 {
 	return block->offloadcnt;
@@ -406,12 +646,17 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
 	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND, extack);
 	if (err == -EOPNOTSUPP)
 		goto no_offload_dev_inc;
-	return err;
+	if (err)
+		return err;
+
+	tc_indr_block_call(block, dev, ei, TC_BLOCK_BIND, extack);
+	return 0;
 
 no_offload_dev_inc:
 	if (tcf_block_offload_in_use(block))
 		return -EOPNOTSUPP;
 	block->nooffloaddevcnt++;
+	tc_indr_block_call(block, dev, ei, TC_BLOCK_BIND, extack);
 	return 0;
 }
 
@@ -421,6 +666,8 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
 	struct net_device *dev = q->dev_queue->dev;
 	int err;
 
+	tc_indr_block_call(block, dev, ei, TC_BLOCK_UNBIND, NULL);
+
 	if (!dev->netdev_ops->ndo_setup_tc)
 		goto no_offload_dev_dec;
 	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND, NULL);
@@ -2355,6 +2602,11 @@ static int __init tc_filter_init(void)
 	if (err)
 		goto err_register_pernet_subsys;
 
+	err = rhashtable_init(&indr_setup_block_ht,
+			      &tc_indr_setup_block_ht_params);
+	if (err)
+		goto err_rhash_setup_block_ht;
+
 	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter,
@@ -2366,6 +2618,8 @@ static int __init tc_filter_init(void)
 
 	return 0;
 
+err_rhash_setup_block_ht:
+	unregister_pernet_subsys(&tcf_net_ops);
 err_register_pernet_subsys:
 	destroy_workqueue(tc_filter_wq);
 	return err;
-- 
cgit v1.2.3


From 7885b4fc8d8e3d0e489f08144f3d4eb2952cb852 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Fri, 9 Nov 2018 21:21:27 -0800
Subject: nfp: flower: allow non repr netdev offload

Previously the offload functions in NFP assumed that the ingress (or
egress) netdev passed to them was an nfp repr.

Modify the driver to permit the passing of non repr netdevs as the ingress
device for an offload rule candidate. This may include devices such as
tunnels. The driver should then base its offload decision on a combination
of ingress device and egress port for a rule.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 14 ++++----
 drivers/net/ethernet/netronome/nfp/flower/main.h   |  3 +-
 drivers/net/ethernet/netronome/nfp/flower/match.c  | 38 ++++++++++++----------
 .../net/ethernet/netronome/nfp/flower/offload.c    | 33 +++++++++++--------
 4 files changed, 49 insertions(+), 39 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index fbc052d5bb47..2e64fe878da6 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -149,11 +149,12 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
 		/* Set action output parameters. */
 		output->flags = cpu_to_be16(tmp_flags);
 
-		/* Only offload if egress ports are on the same device as the
-		 * ingress port.
-		 */
-		if (!switchdev_port_same_parent_id(in_dev, out_dev))
-			return -EOPNOTSUPP;
+		if (nfp_netdev_is_nfp_repr(in_dev)) {
+			/* Confirm ingress and egress are on same device. */
+			if (!switchdev_port_same_parent_id(in_dev, out_dev))
+				return -EOPNOTSUPP;
+		}
+
 		if (!nfp_netdev_is_nfp_repr(out_dev))
 			return -EOPNOTSUPP;
 
@@ -840,9 +841,8 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
 		*a_len += sizeof(struct nfp_fl_push_vlan);
 	} else if (is_tcf_tunnel_set(a)) {
 		struct ip_tunnel_info *ip_tun = tcf_tunnel_info(a);
-		struct nfp_repr *repr = netdev_priv(netdev);
 
-		*tun_type = nfp_fl_get_tun_from_act_l4_port(repr->app, a);
+		*tun_type = nfp_fl_get_tun_from_act_l4_port(app, a);
 		if (*tun_type == NFP_FL_TUNNEL_NONE)
 			return -EOPNOTSUPP;
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 0f6f1675f6f1..4a2b1a915131 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -222,7 +222,8 @@ void nfp_flower_metadata_cleanup(struct nfp_app *app);
 
 int nfp_flower_setup_tc(struct nfp_app *app, struct net_device *netdev,
 			enum tc_setup_type type, void *type_data);
-int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
+int nfp_flower_compile_flow_match(struct nfp_app *app,
+				  struct tc_cls_flower_offload *flow,
 				  struct nfp_fl_key_ls *key_ls,
 				  struct net_device *netdev,
 				  struct nfp_fl_payload *nfp_flow,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index e54fb6034326..cdf75595f627 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -52,10 +52,13 @@ nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
 		return 0;
 	}
 
-	if (tun_type)
+	if (tun_type) {
 		frame->in_port = cpu_to_be32(NFP_FL_PORT_TYPE_TUN | tun_type);
-	else
+	} else {
+		if (!cmsg_port)
+			return -EOPNOTSUPP;
 		frame->in_port = cpu_to_be32(cmsg_port);
+	}
 
 	return 0;
 }
@@ -289,17 +292,21 @@ nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *frame,
 	}
 }
 
-int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
+int nfp_flower_compile_flow_match(struct nfp_app *app,
+				  struct tc_cls_flower_offload *flow,
 				  struct nfp_fl_key_ls *key_ls,
 				  struct net_device *netdev,
 				  struct nfp_fl_payload *nfp_flow,
 				  enum nfp_flower_tun_type tun_type)
 {
-	struct nfp_repr *netdev_repr;
+	u32 cmsg_port = 0;
 	int err;
 	u8 *ext;
 	u8 *msk;
 
+	if (nfp_netdev_is_nfp_repr(netdev))
+		cmsg_port = nfp_repr_get_port_id(netdev);
+
 	memset(nfp_flow->unmasked_data, 0, key_ls->key_size);
 	memset(nfp_flow->mask_data, 0, key_ls->key_size);
 
@@ -327,15 +334,13 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
 
 	/* Populate Exact Port data. */
 	err = nfp_flower_compile_port((struct nfp_flower_in_port *)ext,
-				      nfp_repr_get_port_id(netdev),
-				      false, tun_type);
+				      cmsg_port, false, tun_type);
 	if (err)
 		return err;
 
 	/* Populate Mask Port Data. */
 	err = nfp_flower_compile_port((struct nfp_flower_in_port *)msk,
-				      nfp_repr_get_port_id(netdev),
-				      true, tun_type);
+				      cmsg_port, true, tun_type);
 	if (err)
 		return err;
 
@@ -399,16 +404,13 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
 		msk += sizeof(struct nfp_flower_ipv4_udp_tun);
 
 		/* Configure tunnel end point MAC. */
-		if (nfp_netdev_is_nfp_repr(netdev)) {
-			netdev_repr = netdev_priv(netdev);
-			nfp_tunnel_write_macs(netdev_repr->app);
-
-			/* Store the tunnel destination in the rule data.
-			 * This must be present and be an exact match.
-			 */
-			nfp_flow->nfp_tun_ipv4_addr = tun_dst;
-			nfp_tunnel_add_ipv4_off(netdev_repr->app, tun_dst);
-		}
+		nfp_tunnel_write_macs(app);
+
+		/* Store the tunnel destination in the rule data.
+		 * This must be present and be an exact match.
+		 */
+		nfp_flow->nfp_tun_ipv4_addr = tun_dst;
+		nfp_tunnel_add_ipv4_off(app, tun_dst);
 
 		if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) {
 			err = nfp_flower_compile_geneve_opt(ext, flow, false);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 29c95423ab64..2c32edfc1a9d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -56,11 +56,10 @@
 	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))
 
 static int
-nfp_flower_xmit_flow(struct net_device *netdev,
-		     struct nfp_fl_payload *nfp_flow, u8 mtype)
+nfp_flower_xmit_flow(struct nfp_app *app, struct nfp_fl_payload *nfp_flow,
+		     u8 mtype)
 {
 	u32 meta_len, key_len, mask_len, act_len, tot_len;
-	struct nfp_repr *priv = netdev_priv(netdev);
 	struct sk_buff *skb;
 	unsigned char *msg;
 
@@ -78,7 +77,7 @@ nfp_flower_xmit_flow(struct net_device *netdev,
 	nfp_flow->meta.mask_len >>= NFP_FL_LW_SIZ;
 	nfp_flow->meta.act_len >>= NFP_FL_LW_SIZ;
 
-	skb = nfp_flower_cmsg_alloc(priv->app, tot_len, mtype, GFP_KERNEL);
+	skb = nfp_flower_cmsg_alloc(app, tot_len, mtype, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
@@ -96,7 +95,7 @@ nfp_flower_xmit_flow(struct net_device *netdev,
 	nfp_flow->meta.mask_len <<= NFP_FL_LW_SIZ;
 	nfp_flow->meta.act_len <<= NFP_FL_LW_SIZ;
 
-	nfp_ctrl_tx(priv->app->ctrl, skb);
+	nfp_ctrl_tx(app->ctrl, skb);
 
 	return 0;
 }
@@ -427,13 +426,16 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 		       struct tc_cls_flower_offload *flow, bool egress)
 {
 	enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE;
-	struct nfp_port *port = nfp_port_from_netdev(netdev);
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_payload *flow_pay;
 	struct nfp_fl_key_ls *key_layer;
+	struct nfp_port *port = NULL;
 	struct net_device *ingr_dev;
 	int err;
 
+	if (nfp_netdev_is_nfp_repr(netdev))
+		port = nfp_port_from_netdev(netdev);
+
 	ingr_dev = egress ? NULL : netdev;
 	flow_pay = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev,
 					      NFP_FL_STATS_CTX_DONT_CARE);
@@ -462,8 +464,8 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 
 	flow_pay->ingress_dev = egress ? NULL : netdev;
 
-	err = nfp_flower_compile_flow_match(flow, key_layer, netdev, flow_pay,
-					    tun_type);
+	err = nfp_flower_compile_flow_match(app, flow, key_layer, netdev,
+					    flow_pay, tun_type);
 	if (err)
 		goto err_destroy_flow;
 
@@ -476,7 +478,7 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 	if (err)
 		goto err_destroy_flow;
 
-	err = nfp_flower_xmit_flow(netdev, flow_pay,
+	err = nfp_flower_xmit_flow(app, flow_pay,
 				   NFP_FLOWER_CMSG_TYPE_FLOW_ADD);
 	if (err)
 		goto err_destroy_flow;
@@ -487,7 +489,8 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 	if (err)
 		goto err_destroy_flow;
 
-	port->tc_offload_cnt++;
+	if (port)
+		port->tc_offload_cnt++;
 
 	/* Deallocate flow payload when flower rule has been destroyed. */
 	kfree(key_layer);
@@ -520,12 +523,15 @@ static int
 nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
 		       struct tc_cls_flower_offload *flow, bool egress)
 {
-	struct nfp_port *port = nfp_port_from_netdev(netdev);
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_payload *nfp_flow;
+	struct nfp_port *port = NULL;
 	struct net_device *ingr_dev;
 	int err;
 
+	if (nfp_netdev_is_nfp_repr(netdev))
+		port = nfp_port_from_netdev(netdev);
+
 	ingr_dev = egress ? NULL : netdev;
 	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev,
 					      NFP_FL_STATS_CTX_DONT_CARE);
@@ -539,13 +545,14 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
 	if (nfp_flow->nfp_tun_ipv4_addr)
 		nfp_tunnel_del_ipv4_off(app, nfp_flow->nfp_tun_ipv4_addr);
 
-	err = nfp_flower_xmit_flow(netdev, nfp_flow,
+	err = nfp_flower_xmit_flow(app, nfp_flow,
 				   NFP_FLOWER_CMSG_TYPE_FLOW_DEL);
 	if (err)
 		goto err_free_flow;
 
 err_free_flow:
-	port->tc_offload_cnt--;
+	if (port)
+		port->tc_offload_cnt--;
 	kfree(nfp_flow->action_data);
 	kfree(nfp_flow->mask_data);
 	kfree(nfp_flow->unmasked_data);
-- 
cgit v1.2.3


From 65b7970edf870c8b52fb2f3e847a9a4f0720a019 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Fri, 9 Nov 2018 21:21:28 -0800
Subject: nfp: flower: increase scope of netdev checking functions

Both the actions and tunnel_conf files contain local functions that check
the type of an input netdev. In preparation for re-use with tunnel offload
via indirect blocks, move these to static inline functions in a header
file.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 14 -----------
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h   | 27 ++++++++++++++++++++++
 .../ethernet/netronome/nfp/flower/tunnel_conf.c    | 19 ++-------------
 3 files changed, 29 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 2e64fe878da6..8d54b36afee8 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -2,7 +2,6 @@
 /* Copyright (C) 2017-2018 Netronome Systems, Inc. */
 
 #include <linux/bitfield.h>
-#include <net/geneve.h>
 #include <net/pkt_cls.h>
 #include <net/switchdev.h>
 #include <net/tc_act/tc_csum.h>
@@ -11,7 +10,6 @@
 #include <net/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_vlan.h>
 #include <net/tc_act/tc_tunnel_key.h>
-#include <net/vxlan.h>
 
 #include "cmsg.h"
 #include "main.h"
@@ -92,18 +90,6 @@ nfp_fl_pre_lag(struct nfp_app *app, const struct tc_action *action,
 	return act_size;
 }
 
-static bool nfp_fl_netdev_is_tunnel_type(struct net_device *out_dev,
-					 enum nfp_flower_tun_type tun_type)
-{
-	if (netif_is_vxlan(out_dev))
-		return tun_type == NFP_FL_TUNNEL_VXLAN;
-
-	if (netif_is_geneve(out_dev))
-		return tun_type == NFP_FL_TUNNEL_GENEVE;
-
-	return false;
-}
-
 static int
 nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
 	      const struct tc_action *action, struct nfp_fl_payload *nfp_flow,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 3e391555e191..15f41cfef9f1 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -8,6 +8,7 @@
 #include <linux/skbuff.h>
 #include <linux/types.h>
 #include <net/geneve.h>
+#include <net/vxlan.h>
 
 #include "../nfp_app.h"
 #include "../nfpcore/nfp_cpp.h"
@@ -499,6 +500,32 @@ static inline int nfp_flower_cmsg_get_data_len(struct sk_buff *skb)
 	return skb->len - NFP_FLOWER_CMSG_HLEN;
 }
 
+static inline bool
+nfp_fl_netdev_is_tunnel_type(struct net_device *netdev,
+			     enum nfp_flower_tun_type tun_type)
+{
+	if (netif_is_vxlan(netdev))
+		return tun_type == NFP_FL_TUNNEL_VXLAN;
+	if (netif_is_geneve(netdev))
+		return tun_type == NFP_FL_TUNNEL_GENEVE;
+
+	return false;
+}
+
+static inline bool nfp_fl_is_netdev_to_offload(struct net_device *netdev)
+{
+	if (!netdev->rtnl_link_ops)
+		return false;
+	if (!strcmp(netdev->rtnl_link_ops->kind, "openvswitch"))
+		return true;
+	if (netif_is_vxlan(netdev))
+		return true;
+	if (netif_is_geneve(netdev))
+		return true;
+
+	return false;
+}
+
 struct sk_buff *
 nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports);
 void
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 5d641d7dabff..2d9f26a725c2 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -4,7 +4,6 @@
 #include <linux/etherdevice.h>
 #include <linux/inetdevice.h>
 #include <net/netevent.h>
-#include <net/vxlan.h>
 #include <linux/idr.h>
 #include <net/dst_metadata.h>
 #include <net/arp.h>
@@ -182,20 +181,6 @@ void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
 	}
 }
 
-static bool nfp_tun_is_netdev_to_offload(struct net_device *netdev)
-{
-	if (!netdev->rtnl_link_ops)
-		return false;
-	if (!strcmp(netdev->rtnl_link_ops->kind, "openvswitch"))
-		return true;
-	if (netif_is_vxlan(netdev))
-		return true;
-	if (netif_is_geneve(netdev))
-		return true;
-
-	return false;
-}
-
 static int
 nfp_flower_xmit_tun_conf(struct nfp_app *app, u8 mtype, u16 plen, void *pdata,
 			 gfp_t flag)
@@ -617,7 +602,7 @@ static void nfp_tun_add_to_mac_offload_list(struct net_device *netdev,
 
 	if (nfp_netdev_is_nfp_repr(netdev))
 		port = nfp_repr_get_port_id(netdev);
-	else if (!nfp_tun_is_netdev_to_offload(netdev))
+	else if (!nfp_fl_is_netdev_to_offload(netdev))
 		return;
 
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
@@ -660,7 +645,7 @@ int nfp_tunnel_mac_event_handler(struct nfp_app *app,
 {
 	if (event == NETDEV_DOWN || event == NETDEV_UNREGISTER) {
 		/* If non-nfp netdev then free its offload index. */
-		if (nfp_tun_is_netdev_to_offload(netdev))
+		if (nfp_fl_is_netdev_to_offload(netdev))
 			nfp_tun_del_mac_idx(app, netdev->ifindex);
 	} else if (event == NETDEV_UP || event == NETDEV_CHANGEADDR ||
 		   event == NETDEV_REGISTER) {
-- 
cgit v1.2.3


From 3166dd07a9cba5447a9d7507a988e2eb37a04f95 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Fri, 9 Nov 2018 21:21:29 -0800
Subject: nfp: flower: offload tunnel decap rules via indirect TC blocks

Previously, TC block tunnel decap rules were only offloaded when a
callback was triggered through registration of the rules egress device.
This meant that the driver had no access to the ingress netdev and so
could not verify it was the same tunnel type that the rule implied.

Register tunnel devices for indirect TC block offloads in NFP, giving
access to new rules based on the ingress device rather than egress. Use
this to verify the netdev type of VXLAN and Geneve based rules and offload
the rules to HW if applicable.

Tunnel registration is done via a netdev notifier. On notifier
registration, this is triggered for already existing netdevs. This means
that NFP can register for offloads from devices that exist before it is
loaded (filter rules will be replayed from the TC core). Similarly, on
notifier unregister, a call is triggered for each currently active netdev.
This allows the driver to unregister any indirect block callbacks that may
still be active.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.c   |   6 +
 drivers/net/ethernet/netronome/nfp/flower/main.h   |   5 +
 .../net/ethernet/netronome/nfp/flower/offload.c    | 137 ++++++++++++++++++++-
 3 files changed, 144 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 2ad00773750f..d1c3c2081461 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -568,6 +568,8 @@ static int nfp_flower_init(struct nfp_app *app)
 		goto err_cleanup_metadata;
 	}
 
+	INIT_LIST_HEAD(&app_priv->indr_block_cb_priv);
+
 	return 0;
 
 err_cleanup_metadata:
@@ -684,6 +686,10 @@ nfp_flower_netdev_event(struct nfp_app *app, struct net_device *netdev,
 			return ret;
 	}
 
+	ret = nfp_flower_reg_indir_block_handler(app, netdev, event);
+	if (ret & NOTIFY_STOP_MASK)
+		return ret;
+
 	return nfp_tunnel_mac_event_handler(app, netdev, event, ptr);
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 4a2b1a915131..8c84829ebd21 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -130,6 +130,7 @@ struct nfp_fl_lag {
  * @reify_wait_queue:	wait queue for repr reify response counting
  * @mtu_conf:		Configuration of repr MTU value
  * @nfp_lag:		Link aggregation data block
+ * @indr_block_cb_priv:	List of priv data passed to indirect block cbs
  */
 struct nfp_flower_priv {
 	struct nfp_app *app;
@@ -162,6 +163,7 @@ struct nfp_flower_priv {
 	wait_queue_head_t reify_wait_queue;
 	struct nfp_mtu_conf mtu_conf;
 	struct nfp_fl_lag nfp_lag;
+	struct list_head indr_block_cb_priv;
 };
 
 /**
@@ -271,5 +273,8 @@ int nfp_flower_lag_populate_pre_action(struct nfp_app *app,
 				       struct nfp_fl_pre_lag *pre_act);
 int nfp_flower_lag_get_output_id(struct nfp_app *app,
 				 struct net_device *master);
+int nfp_flower_reg_indir_block_handler(struct nfp_app *app,
+				       struct net_device *netdev,
+				       unsigned long event);
 
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 2c32edfc1a9d..222e1a98cf16 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -128,6 +128,7 @@ nfp_flower_calc_opt_layer(struct flow_dissector_key_enc_opts *enc_opts,
 
 static int
 nfp_flower_calculate_key_layers(struct nfp_app *app,
+				struct net_device *netdev,
 				struct nfp_fl_key_ls *ret_key_ls,
 				struct tc_cls_flower_offload *flow,
 				bool egress,
@@ -186,8 +187,6 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 			skb_flow_dissector_target(flow->dissector,
 						  FLOW_DISSECTOR_KEY_ENC_CONTROL,
 						  flow->key);
-		if (!egress)
-			return -EOPNOTSUPP;
 
 		if (mask_enc_ctl->addr_type != 0xffff ||
 		    enc_ctl->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS)
@@ -250,6 +249,10 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		default:
 			return -EOPNOTSUPP;
 		}
+
+		/* Ensure the ingress netdev matches the expected tun type. */
+		if (!nfp_fl_netdev_is_tunnel_type(netdev, *tun_type))
+			return -EOPNOTSUPP;
 	} else if (egress) {
 		/* Reject non tunnel matches offloaded to egress repr. */
 		return -EOPNOTSUPP;
@@ -451,8 +454,8 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 	if (!key_layer)
 		return -ENOMEM;
 
-	err = nfp_flower_calculate_key_layers(app, key_layer, flow, egress,
-					      &tun_type);
+	err = nfp_flower_calculate_key_layers(app, netdev, key_layer, flow,
+					      egress, &tun_type);
 	if (err)
 		goto err_free_key_ls;
 
@@ -693,3 +696,129 @@ int nfp_flower_setup_tc(struct nfp_app *app, struct net_device *netdev,
 		return -EOPNOTSUPP;
 	}
 }
+
+struct nfp_flower_indr_block_cb_priv {
+	struct net_device *netdev;
+	struct nfp_app *app;
+	struct list_head list;
+};
+
+static struct nfp_flower_indr_block_cb_priv *
+nfp_flower_indr_block_cb_priv_lookup(struct nfp_app *app,
+				     struct net_device *netdev)
+{
+	struct nfp_flower_indr_block_cb_priv *cb_priv;
+	struct nfp_flower_priv *priv = app->priv;
+
+	/* All callback list access should be protected by RTNL. */
+	ASSERT_RTNL();
+
+	list_for_each_entry(cb_priv, &priv->indr_block_cb_priv, list)
+		if (cb_priv->netdev == netdev)
+			return cb_priv;
+
+	return NULL;
+}
+
+static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
+					  void *type_data, void *cb_priv)
+{
+	struct nfp_flower_indr_block_cb_priv *priv = cb_priv;
+	struct tc_cls_flower_offload *flower = type_data;
+
+	if (flower->common.chain_index)
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return nfp_flower_repr_offload(priv->app, priv->netdev,
+					       type_data, false);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
+			       struct tc_block_offload *f)
+{
+	struct nfp_flower_indr_block_cb_priv *cb_priv;
+	struct nfp_flower_priv *priv = app->priv;
+	int err;
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		cb_priv = kmalloc(sizeof(*cb_priv), GFP_KERNEL);
+		if (!cb_priv)
+			return -ENOMEM;
+
+		cb_priv->netdev = netdev;
+		cb_priv->app = app;
+		list_add(&cb_priv->list, &priv->indr_block_cb_priv);
+
+		err = tcf_block_cb_register(f->block,
+					    nfp_flower_setup_indr_block_cb,
+					    netdev, cb_priv, f->extack);
+		if (err) {
+			list_del(&cb_priv->list);
+			kfree(cb_priv);
+		}
+
+		return err;
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block,
+					nfp_flower_setup_indr_block_cb, netdev);
+		cb_priv = nfp_flower_indr_block_cb_priv_lookup(app, netdev);
+		if (cb_priv) {
+			list_del(&cb_priv->list);
+			kfree(cb_priv);
+		}
+
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int
+nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
+			    enum tc_setup_type type, void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return nfp_flower_setup_indr_tc_block(netdev, cb_priv,
+						      type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int nfp_flower_reg_indir_block_handler(struct nfp_app *app,
+				       struct net_device *netdev,
+				       unsigned long event)
+{
+	int err;
+
+	if (!nfp_fl_is_netdev_to_offload(netdev))
+		return NOTIFY_OK;
+
+	if (event == NETDEV_REGISTER) {
+		err = __tc_indr_block_cb_register(netdev, app,
+						  nfp_flower_indr_setup_tc_cb,
+						  netdev);
+		if (err)
+			nfp_flower_cmsg_warn(app,
+					     "Indirect block reg failed - %s\n",
+					     netdev->name);
+	} else if (event == NETDEV_UNREGISTER) {
+		__tc_indr_block_cb_unregister(netdev,
+					      nfp_flower_indr_setup_tc_cb,
+					      netdev);
+	}
+
+	return NOTIFY_OK;
+}
-- 
cgit v1.2.3


From 4f63fde3fc08045a232923cc83fb08defbd7ca4b Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Fri, 9 Nov 2018 21:21:30 -0800
Subject: nfp: flower: remove TC egdev offloads

Previously, only tunnel decap rules required egdev registration for
offload in NFP. These are now supported via indirect TC block callbacks.

Remove the egdev code from NFP.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.c   | 12 ----
 drivers/net/ethernet/netronome/nfp/flower/main.h   |  3 -
 .../net/ethernet/netronome/nfp/flower/metadata.c   |  1 +
 .../net/ethernet/netronome/nfp/flower/offload.c    | 79 +++++-----------------
 4 files changed, 17 insertions(+), 78 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index d1c3c2081461..5059110a1768 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -146,23 +146,12 @@ nfp_flower_repr_netdev_stop(struct nfp_app *app, struct nfp_repr *repr)
 	return nfp_flower_cmsg_portmod(repr, false, repr->netdev->mtu, false);
 }
 
-static int
-nfp_flower_repr_netdev_init(struct nfp_app *app, struct net_device *netdev)
-{
-	return tc_setup_cb_egdev_register(netdev,
-					  nfp_flower_setup_tc_egress_cb,
-					  netdev_priv(netdev));
-}
-
 static void
 nfp_flower_repr_netdev_clean(struct nfp_app *app, struct net_device *netdev)
 {
 	struct nfp_repr *repr = netdev_priv(netdev);
 
 	kfree(repr->app_priv);
-
-	tc_setup_cb_egdev_unregister(netdev, nfp_flower_setup_tc_egress_cb,
-				     netdev_priv(netdev));
 }
 
 static void
@@ -711,7 +700,6 @@ const struct nfp_app_type app_flower = {
 	.vnic_init	= nfp_flower_vnic_init,
 	.vnic_clean	= nfp_flower_vnic_clean,
 
-	.repr_init	= nfp_flower_repr_netdev_init,
 	.repr_preclean	= nfp_flower_repr_netdev_preclean,
 	.repr_clean	= nfp_flower_repr_netdev_clean,
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 8c84829ebd21..9d134aa871fc 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -207,7 +207,6 @@ struct nfp_fl_payload {
 	char *unmasked_data;
 	char *mask_data;
 	char *action_data;
-	bool ingress_offload;
 };
 
 extern const struct rhashtable_params nfp_flower_table_params;
@@ -259,8 +258,6 @@ void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4);
 void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4);
 void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb);
 void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb);
-int nfp_flower_setup_tc_egress_cb(enum tc_setup_type type, void *type_data,
-				  void *cb_priv);
 void nfp_flower_lag_init(struct nfp_fl_lag *lag);
 void nfp_flower_lag_cleanup(struct nfp_fl_lag *lag);
 int nfp_flower_lag_reset(struct nfp_fl_lag *lag);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 48729bf171e0..9b4711ce98f0 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -287,6 +287,7 @@ int nfp_compile_flow_metadata(struct nfp_app *app,
 
 	nfp_flow->meta.host_ctx_id = cpu_to_be32(stats_cxt);
 	nfp_flow->meta.host_cookie = cpu_to_be64(flow->cookie);
+	nfp_flow->ingress_dev = netdev;
 
 	new_mask_id = 0;
 	if (!nfp_check_mask_add(app, nfp_flow->mask_data,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 222e1a98cf16..0e2dfbb3ef86 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -131,7 +131,6 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 				struct net_device *netdev,
 				struct nfp_fl_key_ls *ret_key_ls,
 				struct tc_cls_flower_offload *flow,
-				bool egress,
 				enum nfp_flower_tun_type *tun_type)
 {
 	struct flow_dissector_key_basic *mask_basic = NULL;
@@ -253,9 +252,6 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		/* Ensure the ingress netdev matches the expected tun type. */
 		if (!nfp_fl_netdev_is_tunnel_type(netdev, *tun_type))
 			return -EOPNOTSUPP;
-	} else if (egress) {
-		/* Reject non tunnel matches offloaded to egress repr. */
-		return -EOPNOTSUPP;
 	}
 
 	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
@@ -376,7 +372,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 }
 
 static struct nfp_fl_payload *
-nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer, bool egress)
+nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer)
 {
 	struct nfp_fl_payload *flow_pay;
 
@@ -400,7 +396,6 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer, bool egress)
 
 	flow_pay->nfp_tun_ipv4_addr = 0;
 	flow_pay->meta.flags = 0;
-	flow_pay->ingress_offload = !egress;
 
 	return flow_pay;
 
@@ -418,7 +413,6 @@ err_free_flow:
  * @app:	Pointer to the APP handle
  * @netdev:	netdev structure.
  * @flow:	TC flower classifier offload structure.
- * @egress:	NFP netdev is the egress.
  *
  * Adds a new flow to the repeated hash structure and action payload.
  *
@@ -426,47 +420,33 @@ err_free_flow:
  */
 static int
 nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
-		       struct tc_cls_flower_offload *flow, bool egress)
+		       struct tc_cls_flower_offload *flow)
 {
 	enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE;
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_payload *flow_pay;
 	struct nfp_fl_key_ls *key_layer;
 	struct nfp_port *port = NULL;
-	struct net_device *ingr_dev;
 	int err;
 
 	if (nfp_netdev_is_nfp_repr(netdev))
 		port = nfp_port_from_netdev(netdev);
 
-	ingr_dev = egress ? NULL : netdev;
-	flow_pay = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev,
-					      NFP_FL_STATS_CTX_DONT_CARE);
-	if (flow_pay) {
-		/* Ignore as duplicate if it has been added by different cb. */
-		if (flow_pay->ingress_offload && egress)
-			return 0;
-		else
-			return -EOPNOTSUPP;
-	}
-
 	key_layer = kmalloc(sizeof(*key_layer), GFP_KERNEL);
 	if (!key_layer)
 		return -ENOMEM;
 
 	err = nfp_flower_calculate_key_layers(app, netdev, key_layer, flow,
-					      egress, &tun_type);
+					      &tun_type);
 	if (err)
 		goto err_free_key_ls;
 
-	flow_pay = nfp_flower_allocate_new(key_layer, egress);
+	flow_pay = nfp_flower_allocate_new(key_layer);
 	if (!flow_pay) {
 		err = -ENOMEM;
 		goto err_free_key_ls;
 	}
 
-	flow_pay->ingress_dev = egress ? NULL : netdev;
-
 	err = nfp_flower_compile_flow_match(app, flow, key_layer, netdev,
 					    flow_pay, tun_type);
 	if (err)
@@ -476,8 +456,7 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 	if (err)
 		goto err_destroy_flow;
 
-	err = nfp_compile_flow_metadata(app, flow, flow_pay,
-					flow_pay->ingress_dev);
+	err = nfp_compile_flow_metadata(app, flow, flow_pay, netdev);
 	if (err)
 		goto err_destroy_flow;
 
@@ -515,7 +494,6 @@ err_free_key_ls:
  * @app:	Pointer to the APP handle
  * @netdev:	netdev structure.
  * @flow:	TC flower classifier offload structure
- * @egress:	Netdev is the egress dev.
  *
  * Removes a flow from the repeated hash structure and clears the
  * action payload.
@@ -524,22 +502,20 @@ err_free_key_ls:
  */
 static int
 nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
-		       struct tc_cls_flower_offload *flow, bool egress)
+		       struct tc_cls_flower_offload *flow)
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_payload *nfp_flow;
 	struct nfp_port *port = NULL;
-	struct net_device *ingr_dev;
 	int err;
 
 	if (nfp_netdev_is_nfp_repr(netdev))
 		port = nfp_port_from_netdev(netdev);
 
-	ingr_dev = egress ? NULL : netdev;
-	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev,
+	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev,
 					      NFP_FL_STATS_CTX_DONT_CARE);
 	if (!nfp_flow)
-		return egress ? 0 : -ENOENT;
+		return -ENOENT;
 
 	err = nfp_modify_flow_metadata(app, nfp_flow);
 	if (err)
@@ -571,7 +547,6 @@ err_free_flow:
  * @app:	Pointer to the APP handle
  * @netdev:	Netdev structure.
  * @flow:	TC flower classifier offload structure
- * @egress:	Netdev is the egress dev.
  *
  * Populates a flow statistics structure which which corresponds to a
  * specific flow.
@@ -580,22 +555,17 @@ err_free_flow:
  */
 static int
 nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
-		     struct tc_cls_flower_offload *flow, bool egress)
+		     struct tc_cls_flower_offload *flow)
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_payload *nfp_flow;
-	struct net_device *ingr_dev;
 	u32 ctx_id;
 
-	ingr_dev = egress ? NULL : netdev;
-	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev,
+	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev,
 					      NFP_FL_STATS_CTX_DONT_CARE);
 	if (!nfp_flow)
 		return -EINVAL;
 
-	if (nfp_flow->ingress_offload && egress)
-		return 0;
-
 	ctx_id = be32_to_cpu(nfp_flow->meta.host_ctx_id);
 
 	spin_lock_bh(&priv->stats_lock);
@@ -612,35 +582,18 @@ nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
 
 static int
 nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev,
-			struct tc_cls_flower_offload *flower, bool egress)
+			struct tc_cls_flower_offload *flower)
 {
 	if (!eth_proto_is_802_3(flower->common.protocol))
 		return -EOPNOTSUPP;
 
 	switch (flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		return nfp_flower_add_offload(app, netdev, flower, egress);
+		return nfp_flower_add_offload(app, netdev, flower);
 	case TC_CLSFLOWER_DESTROY:
-		return nfp_flower_del_offload(app, netdev, flower, egress);
+		return nfp_flower_del_offload(app, netdev, flower);
 	case TC_CLSFLOWER_STATS:
-		return nfp_flower_get_stats(app, netdev, flower, egress);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-int nfp_flower_setup_tc_egress_cb(enum tc_setup_type type, void *type_data,
-				  void *cb_priv)
-{
-	struct nfp_repr *repr = cb_priv;
-
-	if (!tc_cls_can_offload_and_chain0(repr->netdev, type_data))
-		return -EOPNOTSUPP;
-
-	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		return nfp_flower_repr_offload(repr->app, repr->netdev,
-					       type_data, true);
+		return nfp_flower_get_stats(app, netdev, flower);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -657,7 +610,7 @@ static int nfp_flower_setup_tc_block_cb(enum tc_setup_type type,
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return nfp_flower_repr_offload(repr->app, repr->netdev,
-					       type_data, false);
+					       type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -732,7 +685,7 @@ static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return nfp_flower_repr_offload(priv->app, priv->netdev,
-					       type_data, false);
+					       type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3


From d4b69bad61e0fc4055c108fa28846ae981948d54 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Fri, 9 Nov 2018 21:21:31 -0800
Subject: nfp: flower: remove unnecessary code in flow lookup

Recent changes to NFP mean that stats updates from fw to driver no longer
require a flow lookup and (because egdev offload has been removed) the
ingress netdev for a lookup is now always known.

Remove obsolete code in a flow lookup that matches on host context and
that allows for a netdev to be NULL.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.h     |  3 +--
 drivers/net/ethernet/netronome/nfp/flower/metadata.c | 11 +++--------
 drivers/net/ethernet/netronome/nfp/flower/offload.c  |  6 ++----
 3 files changed, 6 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 9d134aa871fc..b858bac47621 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -20,7 +20,6 @@ struct nfp_fl_pre_lag;
 struct net_device;
 struct nfp_app;
 
-#define NFP_FL_STATS_CTX_DONT_CARE	cpu_to_be32(0xffffffff)
 #define NFP_FL_STATS_ELEM_RS		FIELD_SIZEOF(struct nfp_fl_stats_id, \
 						     init_unalloc)
 #define NFP_FLOWER_MASK_ENTRY_RS	256
@@ -242,7 +241,7 @@ int nfp_modify_flow_metadata(struct nfp_app *app,
 
 struct nfp_fl_payload *
 nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie,
-			   struct net_device *netdev, __be32 host_ctx);
+			   struct net_device *netdev);
 struct nfp_fl_payload *
 nfp_flower_remove_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie);
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 9b4711ce98f0..573a4400a26c 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -21,7 +21,6 @@ struct nfp_mask_id_table {
 struct nfp_fl_flow_table_cmp_arg {
 	struct net_device *netdev;
 	unsigned long cookie;
-	__be32 host_ctx;
 };
 
 static int nfp_release_stats_entry(struct nfp_app *app, u32 stats_context_id)
@@ -76,14 +75,13 @@ static int nfp_get_stats_entry(struct nfp_app *app, u32 *stats_context_id)
 /* Must be called with either RTNL or rcu_read_lock */
 struct nfp_fl_payload *
 nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie,
-			   struct net_device *netdev, __be32 host_ctx)
+			   struct net_device *netdev)
 {
 	struct nfp_fl_flow_table_cmp_arg flower_cmp_arg;
 	struct nfp_flower_priv *priv = app->priv;
 
 	flower_cmp_arg.netdev = netdev;
 	flower_cmp_arg.cookie = tc_flower_cookie;
-	flower_cmp_arg.host_ctx = host_ctx;
 
 	return rhashtable_lookup_fast(&priv->flow_table, &flower_cmp_arg,
 				      nfp_flower_table_params);
@@ -307,8 +305,7 @@ int nfp_compile_flow_metadata(struct nfp_app *app,
 	priv->stats[stats_cxt].bytes = 0;
 	priv->stats[stats_cxt].used = jiffies;
 
-	check_entry = nfp_flower_search_fl_table(app, flow->cookie, netdev,
-						 NFP_FL_STATS_CTX_DONT_CARE);
+	check_entry = nfp_flower_search_fl_table(app, flow->cookie, netdev);
 	if (check_entry) {
 		if (nfp_release_stats_entry(app, stats_cxt))
 			return -EINVAL;
@@ -353,9 +350,7 @@ static int nfp_fl_obj_cmpfn(struct rhashtable_compare_arg *arg,
 	const struct nfp_fl_flow_table_cmp_arg *cmp_arg = arg->key;
 	const struct nfp_fl_payload *flow_entry = obj;
 
-	if ((!cmp_arg->netdev || flow_entry->ingress_dev == cmp_arg->netdev) &&
-	    (cmp_arg->host_ctx == NFP_FL_STATS_CTX_DONT_CARE ||
-	     flow_entry->meta.host_ctx_id == cmp_arg->host_ctx))
+	if (flow_entry->ingress_dev == cmp_arg->netdev)
 		return flow_entry->tc_flower_cookie != cmp_arg->cookie;
 
 	return 1;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 0e2dfbb3ef86..545d94168874 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -512,8 +512,7 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
 	if (nfp_netdev_is_nfp_repr(netdev))
 		port = nfp_port_from_netdev(netdev);
 
-	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev,
-					      NFP_FL_STATS_CTX_DONT_CARE);
+	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev);
 	if (!nfp_flow)
 		return -ENOENT;
 
@@ -561,8 +560,7 @@ nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
 	struct nfp_fl_payload *nfp_flow;
 	u32 ctx_id;
 
-	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev,
-					      NFP_FL_STATS_CTX_DONT_CARE);
+	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev);
 	if (!nfp_flow)
 		return -EINVAL;
 
-- 
cgit v1.2.3


From 31c4f4cc32f7ba956dbeb0eb2208f1bda2468704 Mon Sep 17 00:00:00 2001
From: LUU Duc Canh <canh.d.luu@dektech.com.au>
Date: Sat, 10 Nov 2018 14:23:50 -0500
Subject: tipc: improve broadcast retransmission algorithm

Currently, the broadcast retransmission algorithm is using the
'prev_retr' field in struct tipc_link to time stamp the latest broadcast
retransmission occasion. This helps to restrict retransmission of
individual broadcast packets to max once per 10 milliseconds, even
though all other criteria for retransmission are met.

We now move this time stamp to the control block of each individual
packet, and remove other limiting criteria. This simplifies the
retransmission algorithm, and eliminates any risk of logical errors
in selecting which packets can be retransmitted.

Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: LUU Duc Canh <canh.d.luu@dektech.com.au>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c | 59 +++++++++++++--------------------------------------------
 net/tipc/msg.h  |  1 +
 2 files changed, 14 insertions(+), 46 deletions(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 201c3b5bc96b..aefb5b40c535 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -105,7 +105,7 @@ struct tipc_stats {
  * @transmitq: queue for sent, non-acked messages
  * @backlogq: queue for messages waiting to be sent
  * @snt_nxt: next sequence number to use for outbound messages
- * @last_retransmitted: sequence number of most recently retransmitted message
+ * @prev_from: sequence number of most previous retransmission request
  * @stale_cnt: counter for number of identical retransmit attempts
  * @stale_limit: time when repeated identical retransmits must force link reset
  * @ackers: # of peers that needs to ack each packet before it can be released
@@ -163,7 +163,7 @@ struct tipc_link {
 		u16 limit;
 	} backlog[5];
 	u16 snd_nxt;
-	u16 last_retransm;
+	u16 prev_from;
 	u16 window;
 	u16 stale_cnt;
 	unsigned long stale_limit;
@@ -186,9 +186,6 @@ struct tipc_link {
 	u16 acked;
 	struct tipc_link *bc_rcvlink;
 	struct tipc_link *bc_sndlink;
-	unsigned long prev_retr;
-	u16 prev_from;
-	u16 prev_to;
 	u8 nack_state;
 	bool bc_peer_is_up;
 
@@ -210,7 +207,7 @@ enum {
 	BC_NACK_SND_SUPPRESS,
 };
 
-#define TIPC_BC_RETR_LIMIT 10   /* [ms] */
+#define TIPC_BC_RETR_LIM msecs_to_jiffies(10)   /* [ms] */
 
 /*
  * Interval between NACKs when packets arrive out of order
@@ -1036,10 +1033,12 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
 
 	if (!skb)
 		return 0;
+	if (less(to, from))
+		return 0;
 
 	/* Detect repeated retransmit failures on same packet */
-	if (r->last_retransm != buf_seqno(skb)) {
-		r->last_retransm = buf_seqno(skb);
+	if (r->prev_from != from) {
+		r->prev_from = from;
 		r->stale_limit = jiffies + msecs_to_jiffies(r->tolerance);
 		r->stale_cnt = 0;
 	} else if (++r->stale_cnt > 99 && time_after(jiffies, r->stale_limit)) {
@@ -1055,6 +1054,11 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
 			continue;
 		if (more(msg_seqno(hdr), to))
 			break;
+		if (link_is_bc_sndlink(l)) {
+			if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
+				continue;
+			TIPC_SKB_CB(skb)->nxt_retr = jiffies + TIPC_BC_RETR_LIM;
+		}
 		_skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC);
 		if (!_skb)
 			return 0;
@@ -1734,42 +1738,6 @@ void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr)
 		l->rcv_nxt = peers_snd_nxt;
 }
 
-/* link_bc_retr eval()- check if the indicated range can be retransmitted now
- * - Adjust permitted range if there is overlap with previous retransmission
- */
-static bool link_bc_retr_eval(struct tipc_link *l, u16 *from, u16 *to)
-{
-	unsigned long elapsed = jiffies_to_msecs(jiffies - l->prev_retr);
-
-	if (less(*to, *from))
-		return false;
-
-	/* New retransmission request */
-	if ((elapsed > TIPC_BC_RETR_LIMIT) ||
-	    less(*to, l->prev_from) || more(*from, l->prev_to)) {
-		l->prev_from = *from;
-		l->prev_to = *to;
-		l->prev_retr = jiffies;
-		return true;
-	}
-
-	/* Inside range of previous retransmit */
-	if (!less(*from, l->prev_from) && !more(*to, l->prev_to))
-		return false;
-
-	/* Fully or partially outside previous range => exclude overlap */
-	if (less(*from, l->prev_from)) {
-		*to = l->prev_from - 1;
-		l->prev_from = *from;
-	}
-	if (more(*to, l->prev_to)) {
-		*from = l->prev_to + 1;
-		l->prev_to = *to;
-	}
-	l->prev_retr = jiffies;
-	return true;
-}
-
 /* tipc_link_bc_sync_rcv - update rcv link according to peer's send state
  */
 int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr,
@@ -1800,8 +1768,7 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr,
 	if (more(peers_snd_nxt, l->rcv_nxt + l->window))
 		return rc;
 
-	if (link_bc_retr_eval(snd_l, &from, &to))
-		rc = tipc_link_retrans(snd_l, l, from, to, xmitq);
+	rc = tipc_link_retrans(snd_l, l, from, to, xmitq);
 
 	l->snd_nxt = peers_snd_nxt;
 	if (link_bc_rcv_gap(l))
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index a2879e6ec5b6..a0924956bb61 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -105,6 +105,7 @@ struct tipc_skb_cb {
 	u32 bytes_read;
 	u32 orig_member;
 	struct sk_buff *tail;
+	unsigned long nxt_retr;
 	bool validated;
 	u16 chain_imp;
 	u16 ackers;
-- 
cgit v1.2.3


From b08794a922c4202bbfee658dee2731f948a4975e Mon Sep 17 00:00:00 2001
From: yupeng <yupeng0921@gmail.com>
Date: Sat, 10 Nov 2018 13:38:12 -0800
Subject: documentation of some IP/ICMP snmp counters

The snmp_counter.rst explains the meanings of snmp counters. It also
provides a set of experiments (only 1 for this initial patch),
combines the experiments' resutls and the snmp counters'
meanings. This is an initial path, only explains a part of IP/ICMP
counters and provide a simple ping test.

Signed-off-by: yupeng <yupeng0921@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/index.rst        |   1 +
 Documentation/networking/snmp_counter.rst | 222 ++++++++++++++++++++++++++++++
 2 files changed, 223 insertions(+)
 create mode 100644 Documentation/networking/snmp_counter.rst

diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index bd89dae8d578..6a47629ef8ed 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -31,6 +31,7 @@ Contents:
    net_failover
    alias
    bridge
+   snmp_counter
 
 .. only::  subproject
 
diff --git a/Documentation/networking/snmp_counter.rst b/Documentation/networking/snmp_counter.rst
new file mode 100644
index 000000000000..e0d588fcb67f
--- /dev/null
+++ b/Documentation/networking/snmp_counter.rst
@@ -0,0 +1,222 @@
+===========
+SNMP counter
+===========
+
+This document explains the meaning of SNMP counters.
+
+General IPv4 counters
+====================
+All layer 4 packets and ICMP packets will change these counters, but
+these counters won't be changed by layer 2 packets (such as STP) or
+ARP packets.
+
+* IpInReceives
+Defined in `RFC1213 ipInReceives`_
+
+.. _RFC1213 ipInReceives: https://tools.ietf.org/html/rfc1213#page-26
+
+The number of packets received by the IP layer. It gets increasing at the
+beginning of ip_rcv function, always be updated together with
+IpExtInOctets. It indicates the number of aggregated segments after
+GRO/LRO.
+
+* IpInDelivers
+Defined in `RFC1213 ipInDelivers`_
+
+.. _RFC1213 ipInDelivers: https://tools.ietf.org/html/rfc1213#page-28
+
+The number of packets delivers to the upper layer protocols. E.g. TCP, UDP,
+ICMP and so on. If no one listens on a raw socket, only kernel
+supported protocols will be delivered, if someone listens on the raw
+socket, all valid IP packets will be delivered.
+
+* IpOutRequests
+Defined in `RFC1213 ipOutRequests`_
+
+.. _RFC1213 ipOutRequests: https://tools.ietf.org/html/rfc1213#page-28
+
+The number of packets sent via IP layer, for both single cast and
+multicast packets, and would always be updated together with
+IpExtOutOctets.
+
+* IpExtInOctets and IpExtOutOctets
+They are linux kernel extensions, no RFC definitions. Please note,
+RFC1213 indeed defines ifInOctets  and ifOutOctets, but they
+are different things. The ifInOctets and ifOutOctets include the MAC
+layer header size but IpExtInOctets and IpExtOutOctets don't, they
+only include the IP layer header and the IP layer data.
+
+* IpExtInNoECTPkts, IpExtInECT1Pkts, IpExtInECT0Pkts, IpExtInCEPkts
+They indicate the number of four kinds of ECN IP packets, please refer
+`Explicit Congestion Notification`_ for more details.
+
+.. _Explicit Congestion Notification: https://tools.ietf.org/html/rfc3168#page-6
+
+These 4 counters calculate how many packets received per ECN
+status. They count the real frame number regardless the LRO/GRO. So
+for the same packet, you might find that IpInReceives count 1, but
+IpExtInNoECTPkts counts 2 or more.
+
+ICMP counters
+============
+* IcmpInMsgs and IcmpOutMsgs
+Defined by `RFC1213 icmpInMsgs`_ and `RFC1213 icmpOutMsgs`_
+
+.. _RFC1213 icmpInMsgs: https://tools.ietf.org/html/rfc1213#page-41
+.. _RFC1213 icmpOutMsgs: https://tools.ietf.org/html/rfc1213#page-43
+
+As mentioned in the RFC1213, these two counters include errors, they
+would be increased even if the ICMP packet has an invalid type. The
+ICMP output path will check the header of a raw socket, so the
+IcmpOutMsgs would still be updated if the IP header is constructed by
+a userspace program.
+
+* ICMP named types
+| These counters include most of common ICMP types, they are:
+| IcmpInDestUnreachs: `RFC1213 icmpInDestUnreachs`_
+| IcmpInTimeExcds: `RFC1213 icmpInTimeExcds`_
+| IcmpInParmProbs: `RFC1213 icmpInParmProbs`_
+| IcmpInSrcQuenchs: `RFC1213 icmpInSrcQuenchs`_
+| IcmpInRedirects: `RFC1213 icmpInRedirects`_
+| IcmpInEchos: `RFC1213 icmpInEchos`_
+| IcmpInEchoReps: `RFC1213 icmpInEchoReps`_
+| IcmpInTimestamps: `RFC1213 icmpInTimestamps`_
+| IcmpInTimestampReps: `RFC1213 icmpInTimestampReps`_
+| IcmpInAddrMasks: `RFC1213 icmpInAddrMasks`_
+| IcmpInAddrMaskReps: `RFC1213 icmpInAddrMaskReps`_
+| IcmpOutDestUnreachs: `RFC1213 icmpOutDestUnreachs`_
+| IcmpOutTimeExcds: `RFC1213 icmpOutTimeExcds`_
+| IcmpOutParmProbs: `RFC1213 icmpOutParmProbs`_
+| IcmpOutSrcQuenchs: `RFC1213 icmpOutSrcQuenchs`_
+| IcmpOutRedirects: `RFC1213 icmpOutRedirects`_
+| IcmpOutEchos: `RFC1213 icmpOutEchos`_
+| IcmpOutEchoReps: `RFC1213 icmpOutEchoReps`_
+| IcmpOutTimestamps: `RFC1213 icmpOutTimestamps`_
+| IcmpOutTimestampReps: `RFC1213 icmpOutTimestampReps`_
+| IcmpOutAddrMasks: `RFC1213 icmpOutAddrMasks`_
+| IcmpOutAddrMaskReps: `RFC1213 icmpOutAddrMaskReps`_
+
+.. _RFC1213 icmpInDestUnreachs: https://tools.ietf.org/html/rfc1213#page-41
+.. _RFC1213 icmpInTimeExcds: https://tools.ietf.org/html/rfc1213#page-41
+.. _RFC1213 icmpInParmProbs: https://tools.ietf.org/html/rfc1213#page-42
+.. _RFC1213 icmpInSrcQuenchs: https://tools.ietf.org/html/rfc1213#page-42
+.. _RFC1213 icmpInRedirects: https://tools.ietf.org/html/rfc1213#page-42
+.. _RFC1213 icmpInEchos: https://tools.ietf.org/html/rfc1213#page-42
+.. _RFC1213 icmpInEchoReps: https://tools.ietf.org/html/rfc1213#page-42
+.. _RFC1213 icmpInTimestamps: https://tools.ietf.org/html/rfc1213#page-42
+.. _RFC1213 icmpInTimestampReps: https://tools.ietf.org/html/rfc1213#page-43
+.. _RFC1213 icmpInAddrMasks: https://tools.ietf.org/html/rfc1213#page-43
+.. _RFC1213 icmpInAddrMaskReps: https://tools.ietf.org/html/rfc1213#page-43
+
+.. _RFC1213 icmpOutDestUnreachs: https://tools.ietf.org/html/rfc1213#page-44
+.. _RFC1213 icmpOutTimeExcds: https://tools.ietf.org/html/rfc1213#page-44
+.. _RFC1213 icmpOutParmProbs: https://tools.ietf.org/html/rfc1213#page-44
+.. _RFC1213 icmpOutSrcQuenchs: https://tools.ietf.org/html/rfc1213#page-44
+.. _RFC1213 icmpOutRedirects: https://tools.ietf.org/html/rfc1213#page-44
+.. _RFC1213 icmpOutEchos: https://tools.ietf.org/html/rfc1213#page-45
+.. _RFC1213 icmpOutEchoReps: https://tools.ietf.org/html/rfc1213#page-45
+.. _RFC1213 icmpOutTimestamps: https://tools.ietf.org/html/rfc1213#page-45
+.. _RFC1213 icmpOutTimestampReps: https://tools.ietf.org/html/rfc1213#page-45
+.. _RFC1213 icmpOutAddrMasks: https://tools.ietf.org/html/rfc1213#page-45
+.. _RFC1213 icmpOutAddrMaskReps: https://tools.ietf.org/html/rfc1213#page-46
+
+Every ICMP type has two counters: 'In' and 'Out'. E.g., for the ICMP
+Echo packet, they are IcmpInEchos and IcmpOutEchos. Their meanings are
+straightforward. The 'In' counter means kernel receives such a packet
+and the 'Out' counter means kernel sends such a packet.
+
+* ICMP numeric types
+They are IcmpMsgInType[N] and IcmpMsgOutType[N], the [N] indicates the
+ICMP type number. These counters track all kinds of ICMP packets. The
+ICMP type number definition could be found in the `ICMP parameters`_
+document.
+
+.. _ICMP parameters: https://www.iana.org/assignments/icmp-parameters/icmp-parameters.xhtml
+
+For example, if the Linux kernel sends an ICMP Echo packet, the
+IcmpMsgOutType8 would increase 1. And if kernel gets an ICMP Echo Reply
+packet, IcmpMsgInType0 would increase 1.
+
+* IcmpInCsumErrors
+This counter indicates the checksum of the ICMP packet is
+wrong. Kernel verifies the checksum after updating the IcmpInMsgs and
+before updating IcmpMsgInType[N]. If a packet has bad checksum, the
+IcmpInMsgs would be updated but none of IcmpMsgInType[N] would be updated.
+
+* IcmpInErrors and IcmpOutErrors
+Defined by `RFC1213 icmpInErrors`_ and `RFC1213 icmpOutErrors`_
+
+.. _RFC1213 icmpInErrors: https://tools.ietf.org/html/rfc1213#page-41
+.. _RFC1213 icmpOutErrors: https://tools.ietf.org/html/rfc1213#page-43
+
+When an error occurs in the ICMP packet handler path, these two
+counters would be updated. The receiving packet path use IcmpInErrors
+and the sending packet path use IcmpOutErrors. When IcmpInCsumErrors
+is increased, IcmpInErrors would always be increased too.
+
+relationship of the ICMP counters
+-------------------------------
+The sum of IcmpMsgOutType[N] is always equal to IcmpOutMsgs, as they
+are updated at the same time. The sum of IcmpMsgInType[N] plus
+IcmpInErrors should be equal or larger than IcmpInMsgs. When kernel
+receives an ICMP packet, kernel follows below logic:
+
+1. increase IcmpInMsgs
+2. if has any error, update IcmpInErrors and finish the process
+3. update IcmpMsgOutType[N]
+4. handle the packet depending on the type, if has any error, update
+   IcmpInErrors and finish the process
+
+So if all errors occur in step (2), IcmpInMsgs should be equal to the
+sum of IcmpMsgOutType[N] plus IcmpInErrors. If all errors occur in
+step (4), IcmpInMsgs should be equal to the sum of
+IcmpMsgOutType[N]. If the errors occur in both step (2) and step (4),
+IcmpInMsgs should be less than the sum of IcmpMsgOutType[N] plus
+IcmpInErrors.
+
+examples
+=======
+
+ping test
+--------
+Run the ping command against the public dns server 8.8.8.8::
+
+  nstatuser@nstat-a:~$ ping 8.8.8.8 -c 1
+  PING 8.8.8.8 (8.8.8.8) 56(84) bytes of data.
+  64 bytes from 8.8.8.8: icmp_seq=1 ttl=119 time=17.8 ms
+
+  --- 8.8.8.8 ping statistics ---
+  1 packets transmitted, 1 received, 0% packet loss, time 0ms
+  rtt min/avg/max/mdev = 17.875/17.875/17.875/0.000 ms
+
+The nstayt result::
+
+  nstatuser@nstat-a:~$ nstat
+  #kernel
+  IpInReceives                    1                  0.0
+  IpInDelivers                    1                  0.0
+  IpOutRequests                   1                  0.0
+  IcmpInMsgs                      1                  0.0
+  IcmpInEchoReps                  1                  0.0
+  IcmpOutMsgs                     1                  0.0
+  IcmpOutEchos                    1                  0.0
+  IcmpMsgInType0                  1                  0.0
+  IcmpMsgOutType8                 1                  0.0
+  IpExtInOctets                   84                 0.0
+  IpExtOutOctets                  84                 0.0
+  IpExtInNoECTPkts                1                  0.0
+
+The Linux server sent an ICMP Echo packet, so IpOutRequests,
+IcmpOutMsgs, IcmpOutEchos and IcmpMsgOutType8 were increased 1. The
+server got ICMP Echo Reply from 8.8.8.8, so IpInReceives, IcmpInMsgs,
+IcmpInEchoReps and IcmpMsgInType0 were increased 1. The ICMP Echo Reply
+was passed to the ICMP layer via IP layer, so IpInDelivers was
+increased 1. The default ping data size is 48, so an ICMP Echo packet
+and its corresponding Echo Reply packet are constructed by:
+
+* 14 bytes MAC header
+* 20 bytes IP header
+* 16 bytes ICMP header
+* 48 bytes data (default value of the ping command)
+
+So the IpExtInOctets and IpExtOutOctets are 20+16+48=84.
-- 
cgit v1.2.3


From 899a3cbbf77a2a3d6d53d67ff6f10ad59eb03605 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 10 Nov 2018 23:40:50 +0100
Subject: net: phy: remove states PHY_STARTING and PHY_PENDING

Both states aren't used. Most likely they result from an idea that
never materialized. So remove them.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c |  7 -------
 include/linux/phy.h   | 22 ++--------------------
 2 files changed, 2 insertions(+), 27 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 083977d2f187..627e66ab60eb 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -46,9 +46,7 @@ static const char *phy_state_to_str(enum phy_state st)
 {
 	switch (st) {
 	PHY_STATE_STR(DOWN)
-	PHY_STATE_STR(STARTING)
 	PHY_STATE_STR(READY)
-	PHY_STATE_STR(PENDING)
 	PHY_STATE_STR(UP)
 	PHY_STATE_STR(RUNNING)
 	PHY_STATE_STR(NOLINK)
@@ -852,9 +850,6 @@ void phy_start(struct phy_device *phydev)
 	mutex_lock(&phydev->lock);
 
 	switch (phydev->state) {
-	case PHY_STARTING:
-		phydev->state = PHY_PENDING;
-		break;
 	case PHY_READY:
 		phydev->state = PHY_UP;
 		break;
@@ -902,9 +897,7 @@ void phy_state_machine(struct work_struct *work)
 
 	switch (phydev->state) {
 	case PHY_DOWN:
-	case PHY_STARTING:
 	case PHY_READY:
-	case PHY_PENDING:
 		break;
 	case PHY_UP:
 		needs_aneg = true;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 03005c65e02d..a5bcb4aaa48e 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -270,29 +270,13 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
  * DOWN: PHY device and driver are not ready for anything.  probe
  * should be called if and only if the PHY is in this state,
  * given that the PHY device exists.
- * - PHY driver probe function will, depending on the PHY, set
- * the state to STARTING or READY
- *
- * STARTING:  PHY device is coming up, and the ethernet driver is
- * not ready.  PHY drivers may set this in the probe function.
- * If they do, they are responsible for making sure the state is
- * eventually set to indicate whether the PHY is UP or READY,
- * depending on the state when the PHY is done starting up.
- * - PHY driver will set the state to READY
- * - start will set the state to PENDING
+ * - PHY driver probe function will set the state to READY
  *
  * READY: PHY is ready to send and receive packets, but the
  * controller is not.  By default, PHYs which do not implement
- * probe will be set to this state by phy_probe().  If the PHY
- * driver knows the PHY is ready, and the PHY state is STARTING,
- * then it sets this STATE.
+ * probe will be set to this state by phy_probe().
  * - start will set the state to UP
  *
- * PENDING: PHY device is coming up, but the ethernet driver is
- * ready.  phy_start will set this state if the PHY state is
- * STARTING.
- * - PHY driver will set the state to UP when the PHY is ready
- *
  * UP: The PHY and attached device are ready to do work.
  * Interrupts should be started here.
  * - timer moves to NOLINK or RUNNING
@@ -329,9 +313,7 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
  */
 enum phy_state {
 	PHY_DOWN = 0,
-	PHY_STARTING,
 	PHY_READY,
-	PHY_PENDING,
 	PHY_UP,
 	PHY_RUNNING,
 	PHY_NOLINK,
-- 
cgit v1.2.3


From 3c1bcc8614db10803f1f57ef0295363917448cb2 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 10 Nov 2018 23:43:33 +0100
Subject: net: ethernet: Convert phydev advertize and supported from u32 to
 link mode

There are a few MAC/PHYs combinations which now support > 1Gbps. These
may need to make use of link modes with bits > 31. Thus their
supported PHY features or advertised features cannot be implemented
using the current bitmap in a u32. Convert to using a linkmode bitmap,
which can support all the currently devices link modes, and is future
proof as more modes are added.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c                           |   3 +-
 drivers/net/ethernet/aeroflex/greth.c              |   2 +-
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c        |  41 +++--
 drivers/net/ethernet/apm/xgene-v2/mdio.c           |  22 +--
 drivers/net/ethernet/arc/emac_main.c               |   3 +-
 drivers/net/ethernet/broadcom/b44.c                |  12 +-
 drivers/net/ethernet/broadcom/genet/bcmmii.c       |   5 +-
 drivers/net/ethernet/broadcom/tg3.c                |  44 ++++--
 drivers/net/ethernet/cavium/octeon/octeon_mgmt.c   |   7 +-
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c     |   5 +-
 drivers/net/ethernet/freescale/fman/mac.c          |   2 +-
 drivers/net/ethernet/freescale/gianfar.c           |  18 ++-
 drivers/net/ethernet/freescale/ucc_geth.c          |   7 +-
 drivers/net/ethernet/hisilicon/hns/hns_enet.c      |   6 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    |   2 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c    |  13 +-
 drivers/net/ethernet/ibm/emac/core.c               |   9 +-
 drivers/net/ethernet/marvell/mv643xx_eth.c         |  21 +--
 drivers/net/ethernet/mediatek/mtk_eth_soc.c        |   7 +-
 drivers/net/ethernet/nxp/lpc_eth.c                 |   2 -
 drivers/net/ethernet/realtek/r8169.c               |   2 +-
 drivers/net/ethernet/socionext/sni_ave.c           |   2 +-
 .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c   |  12 +-
 drivers/net/ethernet/toshiba/tc35815.c             |  29 ++--
 drivers/net/phy/aquantia.c                         |   9 +-
 drivers/net/phy/bcm63xx.c                          |   2 +-
 drivers/net/phy/bcm87xx.c                          |   8 +-
 drivers/net/phy/fixed_phy.c                        |  19 ++-
 drivers/net/phy/marvell.c                          |  50 +++---
 drivers/net/phy/marvell10g.c                       |  33 ++--
 drivers/net/phy/micrel.c                           |  17 +-
 drivers/net/phy/phy-c45.c                          |   7 +-
 drivers/net/phy/phy-core.c                         |  38 +++--
 drivers/net/phy/phy.c                              | 154 ++++++++++++------
 drivers/net/phy/phy_device.c                       | 175 ++++++++++++++-------
 drivers/net/phy/phylink.c                          |  19 +--
 drivers/net/usb/lan78xx.c                          |  27 ++--
 include/linux/mii.h                                |  14 +-
 include/linux/phy.h                                |  18 ++-
 39 files changed, 536 insertions(+), 330 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index a5de9bffe5be..74547f43b938 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -658,7 +658,8 @@ static void mt7530_adjust_link(struct dsa_switch *ds, int port,
 			if (phydev->asym_pause)
 				rmt_adv |= LPA_PAUSE_ASYM;
 
-			lcl_adv = ethtool_adv_to_lcl_adv_t(phydev->advertising);
+			lcl_adv = linkmode_adv_to_lcl_adv_t(
+				phydev->advertising);
 			flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
 
 			if (flowctrl & FLOW_CTRL_TX)
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index 7c9348a26cbb..91fc64c1145e 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -1283,7 +1283,7 @@ static int greth_mdio_probe(struct net_device *dev)
 	else
 		phy_set_max_speed(phy, SPEED_100);
 
-	phy->advertising = phy->supported;
+	linkmode_copy(phy->advertising, phy->supported);
 
 	greth->link = 0;
 	greth->speed = 0;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 151bdb629e8a..128cd648ba99 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -857,6 +857,7 @@ static void xgbe_phy_free_phy_device(struct xgbe_prv_data *pdata)
 
 static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	unsigned int phy_id = phy_data->phydev->phy_id;
 
@@ -878,9 +879,15 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 	phy_write(phy_data->phydev, 0x04, 0x0d01);
 	phy_write(phy_data->phydev, 0x00, 0x9140);
 
-	phy_data->phydev->supported = PHY_10BT_FEATURES |
-				      PHY_100BT_FEATURES |
-				      PHY_1000BT_FEATURES;
+	linkmode_set_bit_array(phy_10_100_features_array,
+			       ARRAY_SIZE(phy_10_100_features_array),
+			       supported);
+	linkmode_set_bit_array(phy_gbit_features_array,
+			       ARRAY_SIZE(phy_gbit_features_array),
+			       supported);
+
+	linkmode_copy(phy_data->phydev->supported, supported);
+
 	phy_support_asym_pause(phy_data->phydev);
 
 	netif_dbg(pdata, drv, pdata->netdev,
@@ -891,6 +898,7 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 
 static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	struct xgbe_sfp_eeprom *sfp_eeprom = &phy_data->sfp_eeprom;
 	unsigned int phy_id = phy_data->phydev->phy_id;
@@ -951,9 +959,13 @@ static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata)
 	reg = phy_read(phy_data->phydev, 0x00);
 	phy_write(phy_data->phydev, 0x00, reg & ~0x00800);
 
-	phy_data->phydev->supported = (PHY_10BT_FEATURES |
-				       PHY_100BT_FEATURES |
-				       PHY_1000BT_FEATURES);
+	linkmode_set_bit_array(phy_10_100_features_array,
+			       ARRAY_SIZE(phy_10_100_features_array),
+			       supported);
+	linkmode_set_bit_array(phy_gbit_features_array,
+			       ARRAY_SIZE(phy_gbit_features_array),
+			       supported);
+	linkmode_copy(phy_data->phydev->supported, supported);
 	phy_support_asym_pause(phy_data->phydev);
 
 	netif_dbg(pdata, drv, pdata->netdev,
@@ -976,7 +988,6 @@ static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata)
 	struct ethtool_link_ksettings *lks = &pdata->phy.lks;
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	struct phy_device *phydev;
-	u32 advertising;
 	int ret;
 
 	/* If we already have a PHY, just return */
@@ -1036,9 +1047,8 @@ static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata)
 
 	xgbe_phy_external_phy_quirks(pdata);
 
-	ethtool_convert_link_mode_to_legacy_u32(&advertising,
-						lks->link_modes.advertising);
-	phydev->advertising &= advertising;
+	linkmode_and(phydev->advertising, phydev->advertising,
+		     lks->link_modes.advertising);
 
 	phy_start_aneg(phy_data->phydev);
 
@@ -1497,7 +1507,7 @@ static void xgbe_phy_phydev_flowctrl(struct xgbe_prv_data *pdata)
 	if (!phy_data->phydev)
 		return;
 
-	lcl_adv = ethtool_adv_to_lcl_adv_t(phy_data->phydev->advertising);
+	lcl_adv = linkmode_adv_to_lcl_adv_t(phy_data->phydev->advertising);
 
 	if (phy_data->phydev->pause) {
 		XGBE_SET_LP_ADV(lks, Pause);
@@ -1815,7 +1825,6 @@ static int xgbe_phy_an_config(struct xgbe_prv_data *pdata)
 {
 	struct ethtool_link_ksettings *lks = &pdata->phy.lks;
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	u32 advertising;
 	int ret;
 
 	ret = xgbe_phy_find_phy_device(pdata);
@@ -1825,12 +1834,10 @@ static int xgbe_phy_an_config(struct xgbe_prv_data *pdata)
 	if (!phy_data->phydev)
 		return 0;
 
-	ethtool_convert_link_mode_to_legacy_u32(&advertising,
-						lks->link_modes.advertising);
-
 	phy_data->phydev->autoneg = pdata->phy.autoneg;
-	phy_data->phydev->advertising = phy_data->phydev->supported &
-					advertising;
+	linkmode_and(phy_data->phydev->advertising,
+		     phy_data->phydev->supported,
+		     lks->link_modes.advertising);
 
 	if (pdata->phy.autoneg != AUTONEG_ENABLE) {
 		phy_data->phydev->speed = pdata->phy.speed;
diff --git a/drivers/net/ethernet/apm/xgene-v2/mdio.c b/drivers/net/ethernet/apm/xgene-v2/mdio.c
index f5fe3bb2e59d..53529cd85162 100644
--- a/drivers/net/ethernet/apm/xgene-v2/mdio.c
+++ b/drivers/net/ethernet/apm/xgene-v2/mdio.c
@@ -109,6 +109,7 @@ void xge_mdio_remove(struct net_device *ndev)
 
 int xge_mdio_config(struct net_device *ndev)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct xge_pdata *pdata = netdev_priv(ndev);
 	struct device *dev = &pdata->pdev->dev;
 	struct mii_bus *mdio_bus;
@@ -148,16 +149,17 @@ int xge_mdio_config(struct net_device *ndev)
 		goto err;
 	}
 
-	phydev->supported &= ~(SUPPORTED_10baseT_Half |
-			       SUPPORTED_10baseT_Full |
-			       SUPPORTED_100baseT_Half |
-			       SUPPORTED_100baseT_Full |
-			       SUPPORTED_1000baseT_Half |
-			       SUPPORTED_AUI |
-			       SUPPORTED_MII |
-			       SUPPORTED_FIBRE |
-			       SUPPORTED_BNC);
-	phydev->advertising = phydev->supported;
+	linkmode_set_bit_array(phy_10_100_features_array,
+			       ARRAY_SIZE(phy_10_100_features_array),
+			       mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_AUI_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_BNC_BIT, mask);
+
+	linkmode_andnot(phydev->supported, phydev->supported, mask);
+	linkmode_copy(phydev->advertising, phydev->supported);
 	pdata->phy_speed = SPEED_UNKNOWN;
 
 	return 0;
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index bd277b0dc615..4406325fdd9f 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -432,7 +432,8 @@ static int arc_emac_open(struct net_device *ndev)
 	phy_dev->autoneg = AUTONEG_ENABLE;
 	phy_dev->speed = 0;
 	phy_dev->duplex = 0;
-	phy_dev->advertising &= phy_dev->supported;
+	linkmode_and(phy_dev->advertising, phy_dev->advertising,
+		     phy_dev->supported);
 
 	priv->last_rx_bd = 0;
 
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index e445ab724827..f44808959ff3 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -2248,6 +2248,7 @@ static void b44_adjust_link(struct net_device *dev)
 
 static int b44_register_phy_one(struct b44 *bp)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct mii_bus *mii_bus;
 	struct ssb_device *sdev = bp->sdev;
 	struct phy_device *phydev;
@@ -2303,11 +2304,12 @@ static int b44_register_phy_one(struct b44 *bp)
 	}
 
 	/* mask with MAC supported features */
-	phydev->supported &= (SUPPORTED_100baseT_Half |
-			      SUPPORTED_100baseT_Full |
-			      SUPPORTED_Autoneg |
-			      SUPPORTED_MII);
-	phydev->advertising = phydev->supported;
+	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
+	linkmode_and(phydev->supported, phydev->supported, mask);
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	bp->old_link = 0;
 	bp->phy_addr = phydev->mdio.addr;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index a6cbaca37e94..aceb9b7b55bd 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -226,7 +226,8 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 		 * capabilities, use that knowledge to also configure the
 		 * Reverse MII interface correctly.
 		 */
-		if (dev->phydev->supported & PHY_1000BT_FEATURES)
+		if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				      dev->phydev->supported))
 			port_ctrl = PORT_MODE_EXT_RVMII_50;
 		else
 			port_ctrl = PORT_MODE_EXT_RVMII_25;
@@ -317,7 +318,7 @@ int bcmgenet_mii_probe(struct net_device *dev)
 		return ret;
 	}
 
-	phydev->advertising = phydev->supported;
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	/* The internal PHY has its link interrupts routed to the
 	 * Ethernet MAC ISRs. On GENETv5 there is a hardware issue
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index ce44d208e137..79b881d9cdb0 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -2157,7 +2157,8 @@ static void tg3_phy_start(struct tg3 *tp)
 		phydev->speed = tp->link_config.speed;
 		phydev->duplex = tp->link_config.duplex;
 		phydev->autoneg = tp->link_config.autoneg;
-		phydev->advertising = tp->link_config.advertising;
+		ethtool_convert_legacy_u32_to_link_mode(
+			phydev->advertising, tp->link_config.advertising);
 	}
 
 	phy_start(phydev);
@@ -4057,8 +4058,9 @@ static int tg3_power_down_prepare(struct tg3 *tp)
 		do_low_power = false;
 		if ((tp->phy_flags & TG3_PHYFLG_IS_CONNECTED) &&
 		    !(tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER)) {
+			__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising) = { 0, };
 			struct phy_device *phydev;
-			u32 phyid, advertising;
+			u32 phyid;
 
 			phydev = mdiobus_get_phy(tp->mdio_bus, tp->phy_addr);
 
@@ -4067,25 +4069,33 @@ static int tg3_power_down_prepare(struct tg3 *tp)
 			tp->link_config.speed = phydev->speed;
 			tp->link_config.duplex = phydev->duplex;
 			tp->link_config.autoneg = phydev->autoneg;
-			tp->link_config.advertising = phydev->advertising;
-
-			advertising = ADVERTISED_TP |
-				      ADVERTISED_Pause |
-				      ADVERTISED_Autoneg |
-				      ADVERTISED_10baseT_Half;
+			ethtool_convert_link_mode_to_legacy_u32(
+				&tp->link_config.advertising,
+				phydev->advertising);
+
+			linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, advertising);
+			linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+					 advertising);
+			linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+					 advertising);
+			linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
+					 advertising);
 
 			if (tg3_flag(tp, ENABLE_ASF) || device_should_wake) {
-				if (tg3_flag(tp, WOL_SPEED_100MB))
-					advertising |=
-						ADVERTISED_100baseT_Half |
-						ADVERTISED_100baseT_Full |
-						ADVERTISED_10baseT_Full;
-				else
-					advertising |= ADVERTISED_10baseT_Full;
+				if (tg3_flag(tp, WOL_SPEED_100MB)) {
+					linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+							 advertising);
+					linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+							 advertising);
+					linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
+							 advertising);
+				} else {
+					linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
+							 advertising);
+				}
 			}
 
-			phydev->advertising = advertising;
-
+			linkmode_copy(phydev->advertising, advertising);
 			phy_start_aneg(phydev);
 
 			phyid = phydev->drv->phy_id & phydev->drv->phy_id_mask;
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 4b3aecf98f2a..5359c1021f42 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -1080,8 +1080,11 @@ static int octeon_mgmt_open(struct net_device *netdev)
 	/* Set the mode of the interface, RGMII/MII. */
 	if (OCTEON_IS_MODEL(OCTEON_CN6XXX) && netdev->phydev) {
 		union cvmx_agl_prtx_ctl agl_prtx_ctl;
-		int rgmii_mode = (netdev->phydev->supported &
-				  (SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full)) != 0;
+		int rgmii_mode =
+			(linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+					   netdev->phydev->supported) |
+			 linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+					   netdev->phydev->supported)) != 0;
 
 		agl_prtx_ctl.u64 = cvmx_read_csr(p->agl_prt_ctl);
 		agl_prtx_ctl.s.mode = rgmii_mode ? 0 : 1;
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 6e0f47f2c8a3..9510c9d78858 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2475,6 +2475,7 @@ static void dpaa_adjust_link(struct net_device *net_dev)
 
 static int dpaa_phy_init(struct net_device *net_dev)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct mac_device *mac_dev;
 	struct phy_device *phy_dev;
 	struct dpaa_priv *priv;
@@ -2491,7 +2492,9 @@ static int dpaa_phy_init(struct net_device *net_dev)
 	}
 
 	/* Remove any features not supported by the controller */
-	phy_dev->supported &= mac_dev->if_support;
+	ethtool_convert_legacy_u32_to_link_mode(mask, mac_dev->if_support);
+	linkmode_and(phy_dev->supported, phy_dev->supported, mask);
+
 	phy_support_asym_pause(phy_dev);
 
 	mac_dev->phy_dev = phy_dev;
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index d79e4e009d63..71f4205f14e7 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -393,7 +393,7 @@ void fman_get_pause_cfg(struct mac_device *mac_dev, bool *rx_pause,
 	 */
 
 	/* get local capabilities */
-	lcl_adv = ethtool_adv_to_lcl_adv_t(phy_dev->advertising);
+	lcl_adv = linkmode_adv_to_lcl_adv_t(phy_dev->advertising);
 
 	/* get link partner capabilities */
 	rmt_adv = 0;
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 3c8da1a18ba0..0e102c764b13 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1784,14 +1784,20 @@ static phy_interface_t gfar_get_interface(struct net_device *dev)
  */
 static int init_phy(struct net_device *dev)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct gfar_private *priv = netdev_priv(dev);
-	uint gigabit_support =
-		priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT ?
-		GFAR_SUPPORTED_GBIT : 0;
 	phy_interface_t interface;
 	struct phy_device *phydev;
 	struct ethtool_eee edata;
 
+	linkmode_set_bit_array(phy_10_100_features_array,
+			       ARRAY_SIZE(phy_10_100_features_array),
+			       mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
+	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, mask);
+
 	priv->oldlink = 0;
 	priv->oldspeed = 0;
 	priv->oldduplex = -1;
@@ -1809,8 +1815,8 @@ static int init_phy(struct net_device *dev)
 		gfar_configure_serdes(dev);
 
 	/* Remove any features not supported by the controller */
-	phydev->supported &= (GFAR_SUPPORTED | gigabit_support);
-	phydev->advertising = phydev->supported;
+	linkmode_and(phydev->supported, phydev->supported, mask);
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	/* Add support for flow control */
 	phy_support_asym_pause(phydev);
@@ -3656,7 +3662,7 @@ static u32 gfar_get_flowctrl_cfg(struct gfar_private *priv)
 		if (phydev->asym_pause)
 			rmt_adv |= LPA_PAUSE_ASYM;
 
-		lcl_adv = ethtool_adv_to_lcl_adv_t(phydev->advertising);
+		lcl_adv = linkmode_adv_to_lcl_adv_t(phydev->advertising);
 		flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
 		if (flowctrl & FLOW_CTRL_TX)
 			val |= MACCFG1_TX_FLOW;
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 32e02700feaa..2e978cb8b28c 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1742,12 +1742,7 @@ static int init_phy(struct net_device *dev)
 	if (priv->phy_interface == PHY_INTERFACE_MODE_SGMII)
 		uec_configure_serdes(dev);
 
-	phy_set_max_speed(phydev, SPEED_100);
-
-	if (priv->max_speed == SPEED_1000)
-		phydev->supported |= ADVERTISED_1000baseT_Full;
-
-	phydev->advertising = phydev->supported;
+	phy_set_max_speed(phydev, priv->max_speed);
 
 	priv->phydev = phydev;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 28e907831b0e..c62378c07e70 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1163,6 +1163,7 @@ static void hns_nic_adjust_link(struct net_device *ndev)
  */
 int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct phy_device *phy_dev = h->phy_dev;
 	int ret;
 
@@ -1180,8 +1181,9 @@ int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h)
 	if (unlikely(ret))
 		return -ENODEV;
 
-	phy_dev->supported &= h->if_support;
-	phy_dev->advertising = phy_dev->supported;
+	ethtool_convert_legacy_u32_to_link_mode(supported, h->if_support);
+	linkmode_and(phy_dev->supported, phy_dev->supported, supported);
+	linkmode_copy(phy_dev->advertising, phy_dev->supported);
 
 	if (h->phy_if == PHY_INTERFACE_MODE_XGMII)
 		phy_dev->autoneg = false;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index ab90108db1c9..43bfc730a62d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6582,7 +6582,7 @@ int hclge_cfg_flowctrl(struct hclge_dev *hdev)
 	if (!phydev->link || !phydev->autoneg)
 		return 0;
 
-	local_advertising = ethtool_adv_to_lcl_adv_t(phydev->advertising);
+	local_advertising = linkmode_adv_to_lcl_adv_t(phydev->advertising);
 
 	if (phydev->pause)
 		remote_advertising = LPA_PAUSE_CAP;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 03018638f701..741cb3b9519d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -195,12 +195,13 @@ int hclge_mac_connect_phy(struct hclge_dev *hdev)
 {
 	struct net_device *netdev = hdev->vport[0].nic.netdev;
 	struct phy_device *phydev = hdev->hw.mac.phydev;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	int ret;
 
 	if (!phydev)
 		return 0;
 
-	phydev->supported &= ~SUPPORTED_FIBRE;
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, phydev->supported);
 
 	ret = phy_connect_direct(netdev, phydev,
 				 hclge_mac_adjust_link,
@@ -210,7 +211,15 @@ int hclge_mac_connect_phy(struct hclge_dev *hdev)
 		return ret;
 	}
 
-	phydev->supported &= HCLGE_PHY_SUPPORTED_FEATURES;
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, mask);
+	linkmode_set_bit_array(phy_10_100_features_array,
+			       ARRAY_SIZE(phy_10_100_features_array),
+			       mask);
+	linkmode_set_bit_array(phy_gbit_features_array,
+			       ARRAY_SIZE(phy_gbit_features_array),
+			       mask);
+	linkmode_and(phydev->supported, phydev->supported, mask);
 	phy_support_asym_pause(phydev);
 
 	return 0;
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 760b2ad8e295..209255495bc9 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2455,7 +2455,8 @@ static void emac_adjust_link(struct net_device *ndev)
 	dev->phy.duplex = phy->duplex;
 	dev->phy.pause = phy->pause;
 	dev->phy.asym_pause = phy->asym_pause;
-	dev->phy.advertising = phy->advertising;
+	ethtool_convert_link_mode_to_legacy_u32(&dev->phy.advertising,
+						phy->advertising);
 }
 
 static int emac_mii_bus_read(struct mii_bus *bus, int addr, int regnum)
@@ -2490,7 +2491,8 @@ static int emac_mdio_phy_start_aneg(struct mii_phy *phy,
 	phy_dev->autoneg = phy->autoneg;
 	phy_dev->speed = phy->speed;
 	phy_dev->duplex = phy->duplex;
-	phy_dev->advertising = phy->advertising;
+	ethtool_convert_legacy_u32_to_link_mode(phy_dev->advertising,
+						phy->advertising);
 	return phy_start_aneg(phy_dev);
 }
 
@@ -2624,7 +2626,8 @@ static int emac_dt_phy_connect(struct emac_instance *dev,
 	dev->phy.def->phy_id_mask = dev->phy_dev->drv->phy_id_mask;
 	dev->phy.def->name = dev->phy_dev->drv->name;
 	dev->phy.def->ops = &emac_dt_mdio_phy_ops;
-	dev->phy.features = dev->phy_dev->supported;
+	ethtool_convert_link_mode_to_legacy_u32(&dev->phy.features,
+						dev->phy_dev->supported);
 	dev->phy.address = dev->phy_dev->mdio.addr;
 	dev->phy.mode = dev->phy_dev->interface;
 	return 0;
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 1e9bcbdc6a90..2f427271a793 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -1499,23 +1499,16 @@ mv643xx_eth_get_link_ksettings_phy(struct mv643xx_eth_private *mp,
 				   struct ethtool_link_ksettings *cmd)
 {
 	struct net_device *dev = mp->dev;
-	u32 supported, advertising;
 
 	phy_ethtool_ksettings_get(dev->phydev, cmd);
 
 	/*
 	 * The MAC does not support 1000baseT_Half.
 	 */
-	ethtool_convert_link_mode_to_legacy_u32(&supported,
-						cmd->link_modes.supported);
-	ethtool_convert_link_mode_to_legacy_u32(&advertising,
-						cmd->link_modes.advertising);
-	supported &= ~SUPPORTED_1000baseT_Half;
-	advertising &= ~ADVERTISED_1000baseT_Half;
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
-						supported);
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
-						advertising);
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+			   cmd->link_modes.supported);
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+			   cmd->link_modes.advertising);
 
 	return 0;
 }
@@ -3031,10 +3024,12 @@ static void phy_init(struct mv643xx_eth_private *mp, int speed, int duplex)
 		phy->autoneg = AUTONEG_ENABLE;
 		phy->speed = 0;
 		phy->duplex = 0;
-		phy->advertising = phy->supported | ADVERTISED_Autoneg;
+		linkmode_copy(phy->advertising, phy->supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+				 phy->advertising);
 	} else {
 		phy->autoneg = AUTONEG_DISABLE;
-		phy->advertising = 0;
+		linkmode_zero(phy->advertising);
 		phy->speed = speed;
 		phy->duplex = duplex;
 	}
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 7dbfdac4067a..399f565dd85a 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -243,7 +243,7 @@ static void mtk_phy_link_adjust(struct net_device *dev)
 		if (dev->phydev->asym_pause)
 			rmt_adv |= LPA_PAUSE_ASYM;
 
-		lcl_adv = ethtool_adv_to_lcl_adv_t(dev->phydev->advertising);
+		lcl_adv = linkmode_adv_to_lcl_adv_t(dev->phydev->advertising);
 		flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
 
 		if (flowctrl & FLOW_CTRL_TX)
@@ -353,8 +353,9 @@ static int mtk_phy_connect(struct net_device *dev)
 
 	phy_set_max_speed(dev->phydev, SPEED_1000);
 	phy_support_asym_pause(dev->phydev);
-	dev->phydev->advertising = dev->phydev->supported |
-				    ADVERTISED_Autoneg;
+	linkmode_copy(dev->phydev->advertising, dev->phydev->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+			 dev->phydev->advertising);
 	phy_start_aneg(dev->phydev);
 
 	of_node_put(np);
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 25382f8fbb70..bd8695a4faaa 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -783,8 +783,6 @@ static int lpc_mii_probe(struct net_device *ndev)
 
 	phy_set_max_speed(phydev, SPEED_100);
 
-	phydev->advertising = phydev->supported;
-
 	pldat->link = 0;
 	pldat->speed = 0;
 	pldat->duplex = -1;
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 1fd01688d37b..56de045268f8 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6584,7 +6584,7 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
 		phy_set_max_speed(phydev, SPEED_100);
 
 	/* Ensure to advertise everything, incl. pause */
-	phydev->advertising = phydev->supported;
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	phy_attached_info(phydev);
 
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 6732f5cbde08..9e7391faa1dc 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -1117,7 +1117,7 @@ static void ave_phy_adjust_link(struct net_device *ndev)
 		if (phydev->asym_pause)
 			rmt_adv |= LPA_PAUSE_ASYM;
 
-		lcl_adv = ethtool_adv_to_lcl_adv_t(phydev->advertising);
+		lcl_adv = linkmode_adv_to_lcl_adv_t(phydev->advertising);
 		cap = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
 		if (cap & FLOW_CTRL_TX)
 			txcr |= AVE_TXCR_FLOCTR;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 5710864fa809..d1f61c25d82b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -458,8 +458,10 @@ stmmac_get_pauseparam(struct net_device *netdev,
 		if (!adv_lp.pause)
 			return;
 	} else {
-		if (!(netdev->phydev->supported & SUPPORTED_Pause) ||
-		    !(netdev->phydev->supported & SUPPORTED_Asym_Pause))
+		if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				       netdev->phydev->supported) ||
+		    linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				      netdev->phydev->supported))
 			return;
 	}
 
@@ -487,8 +489,10 @@ stmmac_set_pauseparam(struct net_device *netdev,
 		if (!adv_lp.pause)
 			return -EOPNOTSUPP;
 	} else {
-		if (!(phy->supported & SUPPORTED_Pause) ||
-		    !(phy->supported & SUPPORTED_Asym_Pause))
+		if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				       phy->supported) ||
+		    linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				      phy->supported))
 			return -EOPNOTSUPP;
 	}
 
diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index 6a71c2c0f17d..c50a9772f4af 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -607,9 +607,9 @@ static void tc_handle_link_change(struct net_device *dev)
 
 static int tc_mii_probe(struct net_device *dev)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct tc35815_local *lp = netdev_priv(dev);
 	struct phy_device *phydev;
-	u32 dropmask;
 
 	phydev = phy_find_first(lp->mii_bus);
 	if (!phydev) {
@@ -630,17 +630,22 @@ static int tc_mii_probe(struct net_device *dev)
 
 	/* mask with MAC supported features */
 	phy_set_max_speed(phydev, SPEED_100);
-	dropmask = 0;
-	if (options.speed == 10)
-		dropmask |= SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full;
-	else if (options.speed == 100)
-		dropmask |= SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full;
-	if (options.duplex == 1)
-		dropmask |= SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Full;
-	else if (options.duplex == 2)
-		dropmask |= SUPPORTED_10baseT_Half | SUPPORTED_100baseT_Half;
-	phydev->supported &= ~dropmask;
-	phydev->advertising = phydev->supported;
+	if (options.speed == 10) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, mask);
+	} else if (options.speed == 100) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, mask);
+	}
+	if (options.duplex == 1) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, mask);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, mask);
+	} else if (options.duplex == 2) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask);
+	}
+	linkmode_and(phydev->supported, phydev->supported, mask);
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	lp->link = 0;
 	lp->speed = 0;
diff --git a/drivers/net/phy/aquantia.c b/drivers/net/phy/aquantia.c
index efc0fbde97a1..beb3309bb0f0 100644
--- a/drivers/net/phy/aquantia.c
+++ b/drivers/net/phy/aquantia.c
@@ -25,15 +25,10 @@
 #define PHY_ID_AQR107	0x03a1b4e0
 #define PHY_ID_AQR405	0x03a1b4b0
 
-#define PHY_AQUANTIA_FEATURES	(SUPPORTED_10000baseT_Full | \
-				 SUPPORTED_1000baseT_Full | \
-				 SUPPORTED_100baseT_Full | \
-				 PHY_DEFAULT_FEATURES)
-
 static int aquantia_config_aneg(struct phy_device *phydev)
 {
-	phydev->supported = PHY_AQUANTIA_FEATURES;
-	phydev->advertising = phydev->supported;
+	linkmode_copy(phydev->supported, phy_10gbit_features);
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	return 0;
 }
diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index 6a547b87ff04..a88dd14a25c0 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -43,7 +43,7 @@ static int bcm63xx_config_init(struct phy_device *phydev)
 	int reg, err;
 
 	/* ASYM_PAUSE bit is marked RO in datasheet, so don't cheat */
-	phydev->supported |= SUPPORTED_Pause;
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported);
 
 	reg = phy_read(phydev, MII_BCM63XX_IR);
 	if (reg < 0)
diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c
index 64d5ba7bf94f..1b350183bffb 100644
--- a/drivers/net/phy/bcm87xx.c
+++ b/drivers/net/phy/bcm87xx.c
@@ -86,8 +86,12 @@ static int bcm87xx_of_reg_init(struct phy_device *phydev)
 
 static int bcm87xx_config_init(struct phy_device *phydev)
 {
-	phydev->supported = SUPPORTED_10000baseR_FEC;
-	phydev->advertising = ADVERTISED_10000baseR_FEC;
+	linkmode_zero(phydev->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseR_FEC_BIT,
+			 phydev->supported);
+	linkmode_zero(phydev->advertising);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseR_FEC_BIT,
+			 phydev->advertising);
 	phydev->state = PHY_NOLINK;
 	phydev->autoneg = AUTONEG_DISABLE;
 
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 67b260877f30..f7fb62712cd8 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -223,14 +223,23 @@ struct phy_device *fixed_phy_register(unsigned int irq,
 
 	switch (status->speed) {
 	case SPEED_1000:
-		phy->supported = PHY_1000BT_FEATURES;
-		break;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+				 phy->supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				 phy->supported);
+		/* fall through */
 	case SPEED_100:
-		phy->supported = PHY_100BT_FEATURES;
-		break;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+				 phy->supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+				 phy->supported);
+		/* fall through */
 	case SPEED_10:
 	default:
-		phy->supported = PHY_10BT_FEATURES;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
+				 phy->supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
+				 phy->supported);
 	}
 
 	ret = phy_device_register(phy);
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 463c616a7281..96f33831ea99 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -491,25 +491,26 @@ static int m88e1318_config_aneg(struct phy_device *phydev)
 }
 
 /**
- * ethtool_adv_to_fiber_adv_t
- * @ethadv: the ethtool advertisement settings
+ * linkmode_adv_to_fiber_adv_t
+ * @advertise: the linkmode advertisement settings
  *
- * A small helper function that translates ethtool advertisement
- * settings to phy autonegotiation advertisements for the
- * MII_ADV register for fiber link.
+ * A small helper function that translates linkmode advertisement
+ * settings to phy autonegotiation advertisements for the MII_ADV
+ * register for fiber link.
  */
-static inline u32 ethtool_adv_to_fiber_adv_t(u32 ethadv)
+static inline u32 linkmode_adv_to_fiber_adv_t(unsigned long *advertise)
 {
 	u32 result = 0;
 
-	if (ethadv & ADVERTISED_1000baseT_Half)
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, advertise))
 		result |= ADVERTISE_FIBER_1000HALF;
-	if (ethadv & ADVERTISED_1000baseT_Full)
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, advertise))
 		result |= ADVERTISE_FIBER_1000FULL;
 
-	if ((ethadv & ADVERTISE_PAUSE_ASYM) && (ethadv & ADVERTISE_PAUSE_CAP))
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertise) &&
+	    linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertise))
 		result |= LPA_PAUSE_ASYM_FIBER;
-	else if (ethadv & ADVERTISE_PAUSE_CAP)
+	else if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertise))
 		result |= (ADVERTISE_PAUSE_FIBER
 			   & (~ADVERTISE_PAUSE_ASYM_FIBER));
 
@@ -530,14 +531,13 @@ static int marvell_config_aneg_fiber(struct phy_device *phydev)
 	int changed = 0;
 	int err;
 	int adv, oldadv;
-	u32 advertise;
 
 	if (phydev->autoneg != AUTONEG_ENABLE)
 		return genphy_setup_forced(phydev);
 
 	/* Only allow advertising what this PHY supports */
-	phydev->advertising &= phydev->supported;
-	advertise = phydev->advertising;
+	linkmode_and(phydev->advertising, phydev->advertising,
+		     phydev->supported);
 
 	/* Setup fiber advertisement */
 	adv = phy_read(phydev, MII_ADVERTISE);
@@ -547,7 +547,7 @@ static int marvell_config_aneg_fiber(struct phy_device *phydev)
 	oldadv = adv;
 	adv &= ~(ADVERTISE_FIBER_1000HALF | ADVERTISE_FIBER_1000FULL
 		| LPA_PAUSE_FIBER);
-	adv |= ethtool_adv_to_fiber_adv_t(advertise);
+	adv |= linkmode_adv_to_fiber_adv_t(phydev->advertising);
 
 	if (adv != oldadv) {
 		err = phy_write(phydev, MII_ADVERTISE, adv);
@@ -879,8 +879,14 @@ static int m88e1510_config_init(struct phy_device *phydev)
 		 * so disable Pause support.
 		 */
 		pause = SUPPORTED_Pause | SUPPORTED_Asym_Pause;
-		phydev->supported &= ~pause;
-		phydev->advertising &= ~pause;
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				   phydev->supported);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				   phydev->supported);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				   phydev->advertising);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				   phydev->advertising);
 	}
 
 	return m88e1318_config_init(phydev);
@@ -1235,7 +1241,8 @@ static int marvell_read_status(struct phy_device *phydev)
 	int err;
 
 	/* Check the fiber mode first */
-	if (phydev->supported & SUPPORTED_FIBRE &&
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_FIBRE_BIT,
+			      phydev->supported) &&
 	    phydev->interface != PHY_INTERFACE_MODE_SGMII) {
 		err = marvell_set_page(phydev, MII_MARVELL_FIBER_PAGE);
 		if (err < 0)
@@ -1278,7 +1285,8 @@ static int marvell_suspend(struct phy_device *phydev)
 	int err;
 
 	/* Suspend the fiber mode first */
-	if (!(phydev->supported & SUPPORTED_FIBRE)) {
+	if (!linkmode_test_bit(ETHTOOL_LINK_MODE_FIBRE_BIT,
+			       phydev->supported)) {
 		err = marvell_set_page(phydev, MII_MARVELL_FIBER_PAGE);
 		if (err < 0)
 			goto error;
@@ -1312,7 +1320,8 @@ static int marvell_resume(struct phy_device *phydev)
 	int err;
 
 	/* Resume the fiber mode first */
-	if (!(phydev->supported & SUPPORTED_FIBRE)) {
+	if (!linkmode_test_bit(ETHTOOL_LINK_MODE_FIBRE_BIT,
+			       phydev->supported)) {
 		err = marvell_set_page(phydev, MII_MARVELL_FIBER_PAGE);
 		if (err < 0)
 			goto error;
@@ -1463,7 +1472,8 @@ error:
 
 static int marvell_get_sset_count(struct phy_device *phydev)
 {
-	if (phydev->supported & SUPPORTED_FIBRE)
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_FIBRE_BIT,
+			      phydev->supported))
 		return ARRAY_SIZE(marvell_hw_stats);
 	else
 		return ARRAY_SIZE(marvell_hw_stats) - NB_FIBER_STATS;
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 1c9d039eec63..d939dce16b35 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -252,7 +252,6 @@ static int mv3310_resume(struct phy_device *phydev)
 static int mv3310_config_init(struct phy_device *phydev)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
-	u32 mask;
 	int val;
 
 	/* Check that the PHY interface type is compatible */
@@ -336,13 +335,9 @@ static int mv3310_config_init(struct phy_device *phydev)
 		}
 	}
 
-	if (!ethtool_convert_link_mode_to_legacy_u32(&mask, supported))
-		phydev_warn(phydev,
-			    "PHY supports (%*pb) more modes than phylib supports, some modes not supported.\n",
-			    __ETHTOOL_LINK_MODE_MASK_NBITS, supported);
-
-	phydev->supported &= mask;
-	phydev->advertising &= phydev->supported;
+	linkmode_copy(phydev->supported, supported);
+	linkmode_and(phydev->advertising, phydev->advertising,
+		     phydev->supported);
 
 	return 0;
 }
@@ -350,7 +345,7 @@ static int mv3310_config_init(struct phy_device *phydev)
 static int mv3310_config_aneg(struct phy_device *phydev)
 {
 	bool changed = false;
-	u32 advertising;
+	u16 reg;
 	int ret;
 
 	/* We don't support manual MDI control */
@@ -364,31 +359,35 @@ static int mv3310_config_aneg(struct phy_device *phydev)
 		return genphy_c45_an_disable_aneg(phydev);
 	}
 
-	phydev->advertising &= phydev->supported;
-	advertising = phydev->advertising;
+	linkmode_and(phydev->advertising, phydev->advertising,
+		     phydev->supported);
 
 	ret = mv3310_modify(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE,
 			    ADVERTISE_ALL | ADVERTISE_100BASE4 |
 			    ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM,
-			    ethtool_adv_to_mii_adv_t(advertising));
+			    linkmode_adv_to_mii_adv_t(phydev->advertising));
 	if (ret < 0)
 		return ret;
 	if (ret > 0)
 		changed = true;
 
+	reg = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising);
 	ret = mv3310_modify(phydev, MDIO_MMD_AN, MV_AN_CTRL1000,
-			    ADVERTISE_1000FULL | ADVERTISE_1000HALF,
-			    ethtool_adv_to_mii_ctrl1000_t(advertising));
+			    ADVERTISE_1000FULL | ADVERTISE_1000HALF, reg);
 	if (ret < 0)
 		return ret;
 	if (ret > 0)
 		changed = true;
 
 	/* 10G control register */
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+			      phydev->advertising))
+		reg = MDIO_AN_10GBT_CTRL_ADV10G;
+	else
+		reg = 0;
+
 	ret = mv3310_modify(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_CTRL,
-			    MDIO_AN_10GBT_CTRL_ADV10G,
-			    advertising & ADVERTISED_10000baseT_Full ?
-				MDIO_AN_10GBT_CTRL_ADV10G : 0);
+			    MDIO_AN_10GBT_CTRL_ADV10G, reg);
 	if (ret < 0)
 		return ret;
 	if (ret > 0)
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index cb5783905a25..c33384710d26 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -311,17 +311,22 @@ static int kszphy_config_init(struct phy_device *phydev)
 
 static int ksz8041_config_init(struct phy_device *phydev)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+
 	struct device_node *of_node = phydev->mdio.dev.of_node;
 
 	/* Limit supported and advertised modes in fiber mode */
 	if (of_property_read_bool(of_node, "micrel,fiber-mode")) {
 		phydev->dev_flags |= MICREL_PHY_FXEN;
-		phydev->supported &= SUPPORTED_100baseT_Full |
-				     SUPPORTED_100baseT_Half;
-		phydev->supported |= SUPPORTED_FIBRE;
-		phydev->advertising &= ADVERTISED_100baseT_Full |
-				       ADVERTISED_100baseT_Half;
-		phydev->advertising |= ADVERTISED_FIBRE;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, mask);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask);
+
+		linkmode_and(phydev->supported, phydev->supported, mask);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT,
+				 phydev->supported);
+		linkmode_and(phydev->advertising, phydev->advertising, mask);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT,
+				 phydev->advertising);
 		phydev->autoneg = AUTONEG_DISABLE;
 	}
 
diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index d7636ff03bc7..a19f4dfa7470 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -304,8 +304,11 @@ EXPORT_SYMBOL_GPL(gen10g_no_soft_reset);
 int gen10g_config_init(struct phy_device *phydev)
 {
 	/* Temporarily just say we support everything */
-	phydev->supported = SUPPORTED_10000baseT_Full;
-	phydev->advertising = SUPPORTED_10000baseT_Full;
+	linkmode_zero(phydev->supported);
+
+	linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+			 phydev->supported);
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	return 0;
 }
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index c7da4cbb1103..9d192b660b07 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -129,7 +129,6 @@ static const struct phy_setting settings[] = {
  * @speed: speed to match
  * @duplex: duplex to match
  * @mask: allowed link modes
- * @maxbit: bit size of link modes
  * @exact: an exact match is required
  *
  * Search the settings array for a setting that matches the speed and
@@ -143,14 +142,14 @@ static const struct phy_setting settings[] = {
  * they all fail, %NULL will be returned.
  */
 const struct phy_setting *
-phy_lookup_setting(int speed, int duplex, const unsigned long *mask,
-		   size_t maxbit, bool exact)
+phy_lookup_setting(int speed, int duplex, const unsigned long *mask, bool exact)
 {
 	const struct phy_setting *p, *match = NULL, *last = NULL;
 	int i;
 
 	for (i = 0, p = settings; i < ARRAY_SIZE(settings); i++, p++) {
-		if (p->bit < maxbit && test_bit(p->bit, mask)) {
+		if (p->bit < __ETHTOOL_LINK_MODE_MASK_NBITS &&
+		    test_bit(p->bit, mask)) {
 			last = p;
 			if (p->speed == speed && p->duplex == duplex) {
 				/* Exact match for speed and duplex */
@@ -175,13 +174,13 @@ phy_lookup_setting(int speed, int duplex, const unsigned long *mask,
 EXPORT_SYMBOL_GPL(phy_lookup_setting);
 
 size_t phy_speeds(unsigned int *speeds, size_t size,
-		  unsigned long *mask, size_t maxbit)
+		  unsigned long *mask)
 {
 	size_t count;
 	int i;
 
 	for (i = 0, count = 0; i < ARRAY_SIZE(settings) && count < size; i++)
-		if (settings[i].bit < maxbit &&
+		if (settings[i].bit < __ETHTOOL_LINK_MODE_MASK_NBITS &&
 		    test_bit(settings[i].bit, mask) &&
 		    (count == 0 || speeds[count - 1] != settings[i].speed))
 			speeds[count++] = settings[i].speed;
@@ -199,27 +198,38 @@ size_t phy_speeds(unsigned int *speeds, size_t size,
  */
 void phy_resolve_aneg_linkmode(struct phy_device *phydev)
 {
-	u32 common = phydev->lp_advertising & phydev->advertising;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(common);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(lp);
 
-	if (common & ADVERTISED_10000baseT_Full) {
+	ethtool_convert_legacy_u32_to_link_mode(lp, phydev->lp_advertising);
+
+	linkmode_and(common, lp, phydev->advertising);
+
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, common)) {
 		phydev->speed = SPEED_10000;
 		phydev->duplex = DUPLEX_FULL;
-	} else if (common & ADVERTISED_1000baseT_Full) {
+	} else if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				     common)) {
 		phydev->speed = SPEED_1000;
 		phydev->duplex = DUPLEX_FULL;
-	} else if (common & ADVERTISED_1000baseT_Half) {
+	} else if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+				     common)) {
 		phydev->speed = SPEED_1000;
 		phydev->duplex = DUPLEX_HALF;
-	} else if (common & ADVERTISED_100baseT_Full) {
+	} else if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+				     common)) {
 		phydev->speed = SPEED_100;
 		phydev->duplex = DUPLEX_FULL;
-	} else if (common & ADVERTISED_100baseT_Half) {
+	} else if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+				     common)) {
 		phydev->speed = SPEED_100;
 		phydev->duplex = DUPLEX_HALF;
-	} else if (common & ADVERTISED_10baseT_Full) {
+	} else if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
+				     common)) {
 		phydev->speed = SPEED_10;
 		phydev->duplex = DUPLEX_FULL;
-	} else if (common & ADVERTISED_10baseT_Half) {
+	} else if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
+				     common)) {
 		phydev->speed = SPEED_10;
 		phydev->duplex = DUPLEX_HALF;
 	}
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 627e66ab60eb..ecc8a7d5306c 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -179,11 +179,9 @@ EXPORT_SYMBOL(phy_aneg_done);
  * settings were found.
  */
 static const struct phy_setting *
-phy_find_valid(int speed, int duplex, u32 supported)
+phy_find_valid(int speed, int duplex, unsigned long *supported)
 {
-	unsigned long mask = supported;
-
-	return phy_lookup_setting(speed, duplex, &mask, BITS_PER_LONG, false);
+	return phy_lookup_setting(speed, duplex, supported, false);
 }
 
 /**
@@ -200,9 +198,7 @@ unsigned int phy_supported_speeds(struct phy_device *phy,
 				  unsigned int *speeds,
 				  unsigned int size)
 {
-	unsigned long supported = phy->supported;
-
-	return phy_speeds(speeds, size, &supported, BITS_PER_LONG);
+	return phy_speeds(speeds, size, phy->supported);
 }
 
 /**
@@ -214,11 +210,10 @@ unsigned int phy_supported_speeds(struct phy_device *phy,
  *
  * Description: Returns true if there is a valid setting, false otherwise.
  */
-static inline bool phy_check_valid(int speed, int duplex, u32 features)
+static inline bool phy_check_valid(int speed, int duplex,
+				   unsigned long *features)
 {
-	unsigned long mask = features;
-
-	return !!phy_lookup_setting(speed, duplex, &mask, BITS_PER_LONG, true);
+	return !!phy_lookup_setting(speed, duplex, features, true);
 }
 
 /**
@@ -232,13 +227,13 @@ static inline bool phy_check_valid(int speed, int duplex, u32 features)
 static void phy_sanitize_settings(struct phy_device *phydev)
 {
 	const struct phy_setting *setting;
-	u32 features = phydev->supported;
 
 	/* Sanitize settings based on PHY capabilities */
-	if ((features & SUPPORTED_Autoneg) == 0)
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported))
 		phydev->autoneg = AUTONEG_DISABLE;
 
-	setting = phy_find_valid(phydev->speed, phydev->duplex, features);
+	setting = phy_find_valid(phydev->speed, phydev->duplex,
+				 phydev->supported);
 	if (setting) {
 		phydev->speed = setting->speed;
 		phydev->duplex = setting->duplex;
@@ -264,13 +259,15 @@ static void phy_sanitize_settings(struct phy_device *phydev)
  */
 int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
 	u32 speed = ethtool_cmd_speed(cmd);
 
 	if (cmd->phy_address != phydev->mdio.addr)
 		return -EINVAL;
 
 	/* We make sure that we don't pass unsupported values in to the PHY */
-	cmd->advertising &= phydev->supported;
+	ethtool_convert_legacy_u32_to_link_mode(advertising, cmd->advertising);
+	linkmode_and(advertising, advertising, phydev->supported);
 
 	/* Verify the settings we care about. */
 	if (cmd->autoneg != AUTONEG_ENABLE && cmd->autoneg != AUTONEG_DISABLE)
@@ -291,12 +288,14 @@ int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd)
 
 	phydev->speed = speed;
 
-	phydev->advertising = cmd->advertising;
+	linkmode_copy(phydev->advertising, advertising);
 
 	if (AUTONEG_ENABLE == cmd->autoneg)
-		phydev->advertising |= ADVERTISED_Autoneg;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+				 phydev->advertising);
 	else
-		phydev->advertising &= ~ADVERTISED_Autoneg;
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+				   phydev->advertising);
 
 	phydev->duplex = cmd->duplex;
 
@@ -312,19 +311,18 @@ EXPORT_SYMBOL(phy_ethtool_sset);
 int phy_ethtool_ksettings_set(struct phy_device *phydev,
 			      const struct ethtool_link_ksettings *cmd)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
 	u8 autoneg = cmd->base.autoneg;
 	u8 duplex = cmd->base.duplex;
 	u32 speed = cmd->base.speed;
-	u32 advertising;
 
 	if (cmd->base.phy_address != phydev->mdio.addr)
 		return -EINVAL;
 
-	ethtool_convert_link_mode_to_legacy_u32(&advertising,
-						cmd->link_modes.advertising);
+	linkmode_copy(advertising, cmd->link_modes.advertising);
 
 	/* We make sure that we don't pass unsupported values in to the PHY */
-	advertising &= phydev->supported;
+	linkmode_and(advertising, advertising, phydev->supported);
 
 	/* Verify the settings we care about. */
 	if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE)
@@ -345,12 +343,14 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev,
 
 	phydev->speed = speed;
 
-	phydev->advertising = advertising;
+	linkmode_copy(phydev->advertising, advertising);
 
 	if (autoneg == AUTONEG_ENABLE)
-		phydev->advertising |= ADVERTISED_Autoneg;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+				 phydev->advertising);
 	else
-		phydev->advertising &= ~ADVERTISED_Autoneg;
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+				   phydev->advertising);
 
 	phydev->duplex = duplex;
 
@@ -366,11 +366,8 @@ EXPORT_SYMBOL(phy_ethtool_ksettings_set);
 void phy_ethtool_ksettings_get(struct phy_device *phydev,
 			       struct ethtool_link_ksettings *cmd)
 {
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
-						phydev->supported);
-
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
-						phydev->advertising);
+	linkmode_copy(cmd->link_modes.supported, phydev->supported);
+	linkmode_copy(cmd->link_modes.advertising, phydev->advertising);
 
 	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.lp_advertising,
 						phydev->lp_advertising);
@@ -442,7 +439,8 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 				}
 				break;
 			case MII_ADVERTISE:
-				phydev->advertising = mii_adv_to_ethtool_adv_t(val);
+				mii_adv_to_linkmode_adv_t(phydev->advertising,
+							  val);
 				change_autoneg = true;
 				break;
 			default:
@@ -604,20 +602,38 @@ static int phy_poll_aneg_done(struct phy_device *phydev)
  */
 int phy_speed_down(struct phy_device *phydev, bool sync)
 {
-	u32 adv = phydev->lp_advertising & phydev->supported;
-	u32 adv_old = phydev->advertising;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(adv);
 	int ret;
 
 	if (phydev->autoneg != AUTONEG_ENABLE)
 		return 0;
 
-	if (adv & PHY_10BT_FEATURES)
-		phydev->advertising &= ~(PHY_100BT_FEATURES |
-					 PHY_1000BT_FEATURES);
-	else if (adv & PHY_100BT_FEATURES)
-		phydev->advertising &= ~PHY_1000BT_FEATURES;
+	linkmode_copy(adv_old, phydev->advertising);
+	ethtool_convert_legacy_u32_to_link_mode(adv, phydev->lp_advertising);
+	linkmode_and(adv, adv, phydev->supported);
+
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, adv) ||
+	    linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, adv)) {
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+				   phydev->advertising);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+				   phydev->advertising);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+				   phydev->advertising);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				   phydev->advertising);
+	} else if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+				     adv) ||
+		   linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+				     adv)) {
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+				   phydev->advertising);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				   phydev->advertising);
+	}
 
-	if (phydev->advertising == adv_old)
+	if (linkmode_equal(phydev->advertising, adv_old))
 		return 0;
 
 	ret = phy_config_aneg(phydev);
@@ -636,15 +652,30 @@ EXPORT_SYMBOL_GPL(phy_speed_down);
  */
 int phy_speed_up(struct phy_device *phydev)
 {
-	u32 mask = PHY_10BT_FEATURES | PHY_100BT_FEATURES | PHY_1000BT_FEATURES;
-	u32 adv_old = phydev->advertising;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(all_speeds) = { 0, };
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(not_speeds);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(speeds);
+
+	linkmode_copy(adv_old, phydev->advertising);
 
 	if (phydev->autoneg != AUTONEG_ENABLE)
 		return 0;
 
-	phydev->advertising = (adv_old & ~mask) | (phydev->supported & mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, all_speeds);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, all_speeds);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, all_speeds);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, all_speeds);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, all_speeds);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, all_speeds);
 
-	if (phydev->advertising == adv_old)
+	linkmode_andnot(not_speeds, adv_old, all_speeds);
+	linkmode_copy(supported, phydev->supported);
+	linkmode_and(speeds, supported, all_speeds);
+	linkmode_or(phydev->advertising, not_speeds, speeds);
+
+	if (linkmode_equal(phydev->advertising, adv_old))
 		return 0;
 
 	return phy_config_aneg(phydev);
@@ -973,6 +1004,30 @@ void phy_mac_interrupt(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_mac_interrupt);
 
+static void mmd_eee_adv_to_linkmode(unsigned long *advertising, u16 eee_adv)
+{
+	linkmode_zero(advertising);
+
+	if (eee_adv & MDIO_EEE_100TX)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+				 advertising);
+	if (eee_adv & MDIO_EEE_1000T)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				 advertising);
+	if (eee_adv & MDIO_EEE_10GT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+				 advertising);
+	if (eee_adv & MDIO_EEE_1000KX)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+				 advertising);
+	if (eee_adv & MDIO_EEE_10GKX4)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
+				 advertising);
+	if (eee_adv & MDIO_EEE_10GKR)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+				 advertising);
+}
+
 /**
  * phy_init_eee - init and check the EEE feature
  * @phydev: target phy_device struct
@@ -991,9 +1046,12 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 	/* According to 802.3az,the EEE is supported only in full duplex-mode.
 	 */
 	if (phydev->duplex == DUPLEX_FULL) {
+		__ETHTOOL_DECLARE_LINK_MODE_MASK(common);
+		__ETHTOOL_DECLARE_LINK_MODE_MASK(lp);
+		__ETHTOOL_DECLARE_LINK_MODE_MASK(adv);
 		int eee_lp, eee_cap, eee_adv;
-		u32 lp, cap, adv;
 		int status;
+		u32 cap;
 
 		/* Read phy status to properly get the right settings */
 		status = phy_read_status(phydev);
@@ -1020,9 +1078,11 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 		if (eee_adv <= 0)
 			goto eee_exit_err;
 
-		adv = mmd_eee_adv_to_ethtool_adv_t(eee_adv);
-		lp = mmd_eee_adv_to_ethtool_adv_t(eee_lp);
-		if (!phy_check_valid(phydev->speed, phydev->duplex, lp & adv))
+		mmd_eee_adv_to_linkmode(adv, eee_adv);
+		mmd_eee_adv_to_linkmode(lp, eee_lp);
+		linkmode_and(common, adv, lp);
+
+		if (!phy_check_valid(phydev->speed, phydev->duplex, common))
 			goto eee_exit_err;
 
 		if (clk_stop_enable) {
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 0f56d408b033..09a1c2d835b2 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -66,10 +66,12 @@ static const int phy_basic_ports_array[] = {
 	ETHTOOL_LINK_MODE_TP_BIT,
 	ETHTOOL_LINK_MODE_MII_BIT,
 };
+EXPORT_SYMBOL_GPL(phy_basic_ports_array);
 
 static const int phy_fibre_port_array[] = {
 	ETHTOOL_LINK_MODE_FIBRE_BIT,
 };
+EXPORT_SYMBOL_GPL(phy_fibre_port_array);
 
 static const int phy_all_ports_features_array[] = {
 	ETHTOOL_LINK_MODE_Autoneg_BIT,
@@ -80,27 +82,32 @@ static const int phy_all_ports_features_array[] = {
 	ETHTOOL_LINK_MODE_BNC_BIT,
 	ETHTOOL_LINK_MODE_Backplane_BIT,
 };
+EXPORT_SYMBOL_GPL(phy_all_ports_features_array);
 
-static const int phy_10_100_features_array[] = {
+const int phy_10_100_features_array[4] = {
 	ETHTOOL_LINK_MODE_10baseT_Half_BIT,
 	ETHTOOL_LINK_MODE_10baseT_Full_BIT,
 	ETHTOOL_LINK_MODE_100baseT_Half_BIT,
 	ETHTOOL_LINK_MODE_100baseT_Full_BIT,
 };
+EXPORT_SYMBOL_GPL(phy_10_100_features_array);
 
-static const int phy_basic_t1_features_array[] = {
+const int phy_basic_t1_features_array[2] = {
 	ETHTOOL_LINK_MODE_TP_BIT,
 	ETHTOOL_LINK_MODE_100baseT_Full_BIT,
 };
+EXPORT_SYMBOL_GPL(phy_basic_t1_features_array);
 
-static const int phy_gbit_features_array[] = {
+const int phy_gbit_features_array[2] = {
 	ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
 	ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
 };
+EXPORT_SYMBOL_GPL(phy_gbit_features_array);
 
-static const int phy_10gbit_features_array[] = {
+const int phy_10gbit_features_array[1] = {
 	ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
 };
+EXPORT_SYMBOL_GPL(phy_10gbit_features_array);
 
 __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init;
 EXPORT_SYMBOL_GPL(phy_10gbit_full_features);
@@ -1441,8 +1448,13 @@ static int genphy_config_advert(struct phy_device *phydev)
 	int err, changed = 0;
 
 	/* Only allow advertising what this PHY supports */
-	phydev->advertising &= phydev->supported;
-	advertise = phydev->advertising;
+	linkmode_and(phydev->advertising, phydev->advertising,
+		     phydev->supported);
+	if (!ethtool_convert_link_mode_to_legacy_u32(&advertise,
+						     phydev->advertising))
+		phydev_warn(phydev, "PHY advertising (%*pb) more modes than genphy supports, some modes not advertised.\n",
+			    __ETHTOOL_LINK_MODE_MASK_NBITS,
+			    phydev->advertising);
 
 	/* Setup standard advertisement */
 	adv = phy_read(phydev, MII_ADVERTISE);
@@ -1481,10 +1493,11 @@ static int genphy_config_advert(struct phy_device *phydev)
 	oldadv = adv;
 	adv &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF);
 
-	if (phydev->supported & (SUPPORTED_1000baseT_Half |
-				 SUPPORTED_1000baseT_Full)) {
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+			      phydev->supported) ||
+	    linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+			      phydev->supported))
 		adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
-	}
 
 	if (adv != oldadv)
 		changed = 1;
@@ -1692,8 +1705,10 @@ int genphy_read_status(struct phy_device *phydev)
 	phydev->lp_advertising = 0;
 
 	if (AUTONEG_ENABLE == phydev->autoneg) {
-		if (phydev->supported & (SUPPORTED_1000baseT_Half
-					| SUPPORTED_1000baseT_Full)) {
+		if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+				      phydev->supported) ||
+		    linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				      phydev->supported)) {
 			lpagb = phy_read(phydev, MII_STAT1000);
 			if (lpagb < 0)
 				return lpagb;
@@ -1800,11 +1815,13 @@ EXPORT_SYMBOL(genphy_soft_reset);
 int genphy_config_init(struct phy_device *phydev)
 {
 	int val;
-	u32 features;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(features) = { 0, };
 
-	features = (SUPPORTED_TP | SUPPORTED_MII
-			| SUPPORTED_AUI | SUPPORTED_FIBRE |
-			SUPPORTED_BNC | SUPPORTED_Pause | SUPPORTED_Asym_Pause);
+	linkmode_set_bit_array(phy_basic_ports_array,
+			       ARRAY_SIZE(phy_basic_ports_array),
+			       features);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, features);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, features);
 
 	/* Do we support autonegotiation? */
 	val = phy_read(phydev, MII_BMSR);
@@ -1812,16 +1829,16 @@ int genphy_config_init(struct phy_device *phydev)
 		return val;
 
 	if (val & BMSR_ANEGCAPABLE)
-		features |= SUPPORTED_Autoneg;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, features);
 
 	if (val & BMSR_100FULL)
-		features |= SUPPORTED_100baseT_Full;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, features);
 	if (val & BMSR_100HALF)
-		features |= SUPPORTED_100baseT_Half;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, features);
 	if (val & BMSR_10FULL)
-		features |= SUPPORTED_10baseT_Full;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, features);
 	if (val & BMSR_10HALF)
-		features |= SUPPORTED_10baseT_Half;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, features);
 
 	if (val & BMSR_ESTATEN) {
 		val = phy_read(phydev, MII_ESTATUS);
@@ -1829,13 +1846,15 @@ int genphy_config_init(struct phy_device *phydev)
 			return val;
 
 		if (val & ESTATUS_1000_TFULL)
-			features |= SUPPORTED_1000baseT_Full;
+			linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+					 features);
 		if (val & ESTATUS_1000_THALF)
-			features |= SUPPORTED_1000baseT_Half;
+			linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+					 features);
 	}
 
-	phydev->supported &= features;
-	phydev->advertising &= features;
+	linkmode_and(phydev->supported, phydev->supported, features);
+	linkmode_and(phydev->advertising, phydev->advertising, features);
 
 	return 0;
 }
@@ -1879,20 +1898,37 @@ EXPORT_SYMBOL(genphy_loopback);
 
 static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
-	phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES |
-			       PHY_10BT_FEATURES);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(speeds) = { 0, };
+
+	linkmode_set_bit_array(phy_10_100_features_array,
+			       ARRAY_SIZE(phy_10_100_features_array),
+			       speeds);
+	linkmode_set_bit_array(phy_gbit_features_array,
+			       ARRAY_SIZE(phy_gbit_features_array),
+			       speeds);
+
+	linkmode_andnot(phydev->supported, phydev->supported, speeds);
 
 	switch (max_speed) {
 	default:
 		return -ENOTSUPP;
 	case SPEED_1000:
-		phydev->supported |= PHY_1000BT_FEATURES;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+				 phydev->supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				 phydev->supported);
 		/* fall through */
 	case SPEED_100:
-		phydev->supported |= PHY_100BT_FEATURES;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+				 phydev->supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+				 phydev->supported);
 		/* fall through */
 	case SPEED_10:
-		phydev->supported |= PHY_10BT_FEATURES;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
+				 phydev->supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
+				 phydev->supported);
 	}
 
 	return 0;
@@ -1906,7 +1942,7 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed)
 	if (err)
 		return err;
 
-	phydev->advertising = phydev->supported;
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	return 0;
 }
@@ -1923,10 +1959,8 @@ EXPORT_SYMBOL(phy_set_max_speed);
  */
 void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode)
 {
-	WARN_ON(link_mode > 31);
-
-	phydev->supported &= ~BIT(link_mode);
-	phydev->advertising = phydev->supported;
+	linkmode_clear_bit(link_mode, phydev->supported);
+	linkmode_copy(phydev->advertising, phydev->supported);
 }
 EXPORT_SYMBOL(phy_remove_link_mode);
 
@@ -1939,9 +1973,9 @@ EXPORT_SYMBOL(phy_remove_link_mode);
  */
 void phy_support_sym_pause(struct phy_device *phydev)
 {
-	phydev->supported &= ~SUPPORTED_Asym_Pause;
-	phydev->supported |= SUPPORTED_Pause;
-	phydev->advertising = phydev->supported;
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported);
+	linkmode_copy(phydev->advertising, phydev->supported);
 }
 EXPORT_SYMBOL(phy_support_sym_pause);
 
@@ -1953,8 +1987,9 @@ EXPORT_SYMBOL(phy_support_sym_pause);
  */
 void phy_support_asym_pause(struct phy_device *phydev)
 {
-	phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
-	phydev->advertising = phydev->supported;
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->supported);
+	linkmode_copy(phydev->advertising, phydev->supported);
 }
 EXPORT_SYMBOL(phy_support_asym_pause);
 
@@ -1972,12 +2007,13 @@ EXPORT_SYMBOL(phy_support_asym_pause);
 void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx,
 		       bool autoneg)
 {
-	phydev->supported &= ~SUPPORTED_Pause;
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported);
 
 	if (rx && tx && autoneg)
-		phydev->supported |= SUPPORTED_Pause;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				 phydev->supported);
 
-	phydev->advertising = phydev->supported;
+	linkmode_copy(phydev->advertising, phydev->supported);
 }
 EXPORT_SYMBOL(phy_set_sym_pause);
 
@@ -1994,20 +2030,29 @@ EXPORT_SYMBOL(phy_set_sym_pause);
  */
 void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx)
 {
-	u16 oldadv = phydev->advertising;
-	u16 newadv = oldadv &= ~(SUPPORTED_Pause | SUPPORTED_Asym_Pause);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(oldadv);
 
-	if (rx)
-		newadv |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
-	if (tx)
-		newadv ^= SUPPORTED_Asym_Pause;
+	linkmode_copy(oldadv, phydev->advertising);
 
-	if (oldadv != newadv) {
-		phydev->advertising = newadv;
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+			   phydev->advertising);
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+			   phydev->advertising);
 
-		if (phydev->autoneg)
-			phy_start_aneg(phydev);
+	if (rx) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				 phydev->advertising);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				 phydev->advertising);
 	}
+
+	if (tx)
+		linkmode_change_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				    phydev->advertising);
+
+	if (!linkmode_equal(oldadv, phydev->advertising) &&
+	    phydev->autoneg)
+		phy_start_aneg(phydev);
 }
 EXPORT_SYMBOL(phy_set_asym_pause);
 
@@ -2023,8 +2068,10 @@ EXPORT_SYMBOL(phy_set_asym_pause);
 bool phy_validate_pause(struct phy_device *phydev,
 			struct ethtool_pauseparam *pp)
 {
-	if (!(phydev->supported & SUPPORTED_Pause) ||
-	    (!(phydev->supported & SUPPORTED_Asym_Pause) &&
+	if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+			       phydev->supported) ||
+	    (!linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				phydev->supported) &&
 	     pp->rx_pause != pp->tx_pause))
 		return false;
 	return true;
@@ -2112,9 +2159,9 @@ static int phy_probe(struct device *dev)
 	 * or both of these values
 	 */
 	ethtool_convert_link_mode_to_legacy_u32(&features, phydrv->features);
-	phydev->supported = features;
+	linkmode_copy(phydev->supported, phydrv->features);
 	of_set_phy_supported(phydev);
-	phydev->advertising = phydev->supported;
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	/* Get the EEE modes we want to prohibit. We will ask
 	 * the PHY stop advertising these mode later on
@@ -2134,14 +2181,22 @@ static int phy_probe(struct device *dev)
 	 */
 	if (test_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydrv->features) ||
 	    test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydrv->features)) {
-		phydev->supported &= ~(SUPPORTED_Pause | SUPPORTED_Asym_Pause);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				   phydev->supported);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				   phydev->supported);
 		if (test_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydrv->features))
-			phydev->supported |= SUPPORTED_Pause;
+			linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+					 phydev->supported);
 		if (test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
 			     phydrv->features))
-			phydev->supported |= SUPPORTED_Asym_Pause;
+			linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+					 phydev->supported);
 	} else {
-		phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				 phydev->supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				 phydev->supported);
 	}
 
 	/* Set the state to READY by default */
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 9b8dd0d0ee42..e7becc7379d7 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -191,8 +191,7 @@ static int phylink_parse_fixedlink(struct phylink *pl,
 	phylink_validate(pl, pl->supported, &pl->link_config);
 
 	s = phy_lookup_setting(pl->link_config.speed, pl->link_config.duplex,
-			       pl->supported,
-			       __ETHTOOL_LINK_MODE_MASK_NBITS, true);
+			       pl->supported, true);
 	linkmode_zero(pl->supported);
 	phylink_set(pl->supported, MII);
 	if (s) {
@@ -634,13 +633,11 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy)
 {
 	struct phylink_link_state config;
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
-	u32 advertising;
 	int ret;
 
 	memset(&config, 0, sizeof(config));
-	ethtool_convert_legacy_u32_to_link_mode(supported, phy->supported);
-	ethtool_convert_legacy_u32_to_link_mode(config.advertising,
-						phy->advertising);
+	linkmode_copy(supported, phy->supported);
+	linkmode_copy(config.advertising, phy->advertising);
 	config.interface = pl->link_config.interface;
 
 	/*
@@ -673,15 +670,14 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy)
 	linkmode_copy(pl->link_config.advertising, config.advertising);
 
 	/* Restrict the phy advertisement according to the MAC support. */
-	ethtool_convert_link_mode_to_legacy_u32(&advertising, config.advertising);
-	phy->advertising = advertising;
+	linkmode_copy(phy->advertising, config.advertising);
 	mutex_unlock(&pl->state_mutex);
 	mutex_unlock(&phy->lock);
 
 	netdev_dbg(pl->netdev,
-		   "phy: setting supported %*pb advertising 0x%08x\n",
+		   "phy: setting supported %*pb advertising %*pb\n",
 		   __ETHTOOL_LINK_MODE_MASK_NBITS, pl->supported,
-		   phy->advertising);
+		   __ETHTOOL_LINK_MODE_MASK_NBITS, phy->advertising);
 
 	phy_start_machine(phy);
 	if (phy->irq > 0)
@@ -1088,8 +1084,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl,
 		 * duplex.
 		 */
 		s = phy_lookup_setting(kset->base.speed, kset->base.duplex,
-				       pl->supported,
-				       __ETHTOOL_LINK_MODE_MASK_NBITS, false);
+				       pl->supported, false);
 		if (!s)
 			return -EINVAL;
 
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index be1917be28f2..3c8bdac78866 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/if_vlan.h>
 #include <linux/uaccess.h>
+#include <linux/linkmode.h>
 #include <linux/list.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
@@ -1586,18 +1587,17 @@ static int lan78xx_set_pause(struct net_device *net,
 		dev->fc_request_control |= FLOW_CTRL_TX;
 
 	if (ecmd.base.autoneg) {
+		__ETHTOOL_DECLARE_LINK_MODE_MASK(fc) = { 0, };
 		u32 mii_adv;
-		u32 advertising;
 
-		ethtool_convert_link_mode_to_legacy_u32(
-			&advertising, ecmd.link_modes.advertising);
-
-		advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				   ecmd.link_modes.advertising);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				   ecmd.link_modes.advertising);
 		mii_adv = (u32)mii_advertise_flowctrl(dev->fc_request_control);
-		advertising |= mii_adv_to_ethtool_adv_t(mii_adv);
-
-		ethtool_convert_legacy_u32_to_link_mode(
-			ecmd.link_modes.advertising, advertising);
+		mii_adv_to_linkmode_adv_t(fc, mii_adv);
+		linkmode_or(ecmd.link_modes.advertising, fc,
+			    ecmd.link_modes.advertising);
 
 		phy_ethtool_ksettings_set(phydev, &ecmd);
 	}
@@ -2095,6 +2095,7 @@ static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev)
 
 static int lan78xx_phy_init(struct lan78xx_net *dev)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(fc) = { 0, };
 	int ret;
 	u32 mii_adv;
 	struct phy_device *phydev;
@@ -2158,9 +2159,13 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 
 	/* support both flow controls */
 	dev->fc_request_control = (FLOW_CTRL_RX | FLOW_CTRL_TX);
-	phydev->advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause);
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+			   phydev->advertising);
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+			   phydev->advertising);
 	mii_adv = (u32)mii_advertise_flowctrl(dev->fc_request_control);
-	phydev->advertising |= mii_adv_to_ethtool_adv_t(mii_adv);
+	mii_adv_to_linkmode_adv_t(fc, mii_adv);
+	linkmode_or(phydev->advertising, fc, phydev->advertising);
 
 	if (phydev->mdio.dev.of_node) {
 		u32 reg;
diff --git a/include/linux/mii.h b/include/linux/mii.h
index 2da85b02e1c0..aaa458bbef2a 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -385,19 +385,21 @@ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising,
 }
 
 /**
- * ethtool_adv_to_lcl_adv_t
- * @advertising:pointer to ethtool advertising
+ * linkmode_adv_to_lcl_adv_t
+ * @advertising:pointer to linkmode advertising
  *
- * A small helper function that translates ethtool advertising to LVL
+ * A small helper function that translates linkmode advertising to LVL
  * pause capabilities.
  */
-static inline u32 ethtool_adv_to_lcl_adv_t(u32 advertising)
+static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising)
 {
 	u32 lcl_adv = 0;
 
-	if (advertising & ADVERTISED_Pause)
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+			      advertising))
 		lcl_adv |= ADVERTISE_PAUSE_CAP;
-	if (advertising & ADVERTISED_Asym_Pause)
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+			      advertising))
 		lcl_adv |= ADVERTISE_PAUSE_ASYM;
 
 	return lcl_adv;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index a5bcb4aaa48e..cbc66ac3b560 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -58,6 +58,11 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini
 #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features)
 #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features)
 
+extern const int phy_10_100_features_array[4];
+extern const int phy_basic_t1_features_array[2];
+extern const int phy_gbit_features_array[2];
+extern const int phy_10gbit_features_array[1];
+
 /*
  * Set phydev->irq to PHY_POLL if interrupts are not supported,
  * or not desired for this PHY.  Set to PHY_IGNORE_INTERRUPT if
@@ -405,10 +410,11 @@ struct phy_device {
 	int pause;
 	int asym_pause;
 
-	/* Union of PHY and Attached devices' supported modes */
-	/* See mii.h for more info */
-	u32 supported;
-	u32 advertising;
+	/* Union of PHY and Attached devices' supported link modes */
+	/* See ethtool.h for more info */
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
+
 	u32 lp_advertising;
 
 	/* Energy efficient ethernet modes which should be prohibited */
@@ -660,9 +666,9 @@ struct phy_setting {
 
 const struct phy_setting *
 phy_lookup_setting(int speed, int duplex, const unsigned long *mask,
-		   size_t maxbit, bool exact);
+		   bool exact);
 size_t phy_speeds(unsigned int *speeds, size_t size,
-		  unsigned long *mask, size_t maxbit);
+		  unsigned long *mask);
 
 void phy_resolve_aneg_linkmode(struct phy_device *phydev);
 
-- 
cgit v1.2.3


From c0ec3c2736774c69bf5c641aea7712132c0f0eba Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 10 Nov 2018 23:43:34 +0100
Subject: net: phy: Convert u32 phydev->lp_advertising to linkmode

Convert phy drivers to report the link partner advertised modes using
a linkmode bitmap. This allows them to report the higher speeds which
don't fit in a u32.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/lxt.c        |  4 ++--
 drivers/net/phy/marvell.c    | 26 ++++++++++++--------------
 drivers/net/phy/marvell10g.c |  4 ++--
 drivers/net/phy/phy-c45.c    |  5 +++--
 drivers/net/phy/phy-core.c   | 13 ++++++-------
 drivers/net/phy/phy.c        |  8 +++-----
 drivers/net/phy/phy_device.c |  8 ++++----
 drivers/net/phy/uPD60620.c   |  6 +++---
 include/linux/mii.h          | 36 ++++++++++++++++++++++++++++++++++++
 include/linux/phy.h          |  3 +--
 10 files changed, 72 insertions(+), 41 deletions(-)

diff --git a/drivers/net/phy/lxt.c b/drivers/net/phy/lxt.c
index c9e2c84c25c0..c8bb29ae1a2a 100644
--- a/drivers/net/phy/lxt.c
+++ b/drivers/net/phy/lxt.c
@@ -177,7 +177,7 @@ static int lxt973a2_read_status(struct phy_device *phydev)
 			*/
 		} while (lpa == adv && retry--);
 
-		phydev->lp_advertising = mii_lpa_to_ethtool_lpa_t(lpa);
+		mii_lpa_to_linkmode_lpa_t(phydev->lp_advertising, lpa);
 
 		lpa &= adv;
 
@@ -218,7 +218,7 @@ static int lxt973a2_read_status(struct phy_device *phydev)
 			phydev->speed = SPEED_10;
 
 		phydev->pause = phydev->asym_pause = 0;
-		phydev->lp_advertising = 0;
+		linkmode_zero(phydev->lp_advertising);
 	}
 
 	return 0;
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 96f33831ea99..36a0db86c6f4 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1049,22 +1049,21 @@ static int m88e1145_config_init(struct phy_device *phydev)
 }
 
 /**
- * fiber_lpa_to_ethtool_lpa_t
+ * fiber_lpa_to_linkmode_lpa_t
+ * @advertising: the linkmode advertisement settings
  * @lpa: value of the MII_LPA register for fiber link
  *
  * A small helper function that translates MII_LPA
- * bits to ethtool LP advertisement settings.
+ * bits to linkmode LP advertisement settings.
  */
-static u32 fiber_lpa_to_ethtool_lpa_t(u32 lpa)
+static void fiber_lpa_to_linkmode_lpa_t(unsigned long *advertising, u32 lpa)
 {
-	u32 result = 0;
-
 	if (lpa & LPA_FIBER_1000HALF)
-		result |= ADVERTISED_1000baseT_Half;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+				 advertising);
 	if (lpa & LPA_FIBER_1000FULL)
-		result |= ADVERTISED_1000baseT_Full;
-
-	return result;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				 advertising);
 }
 
 /**
@@ -1140,9 +1139,8 @@ static int marvell_read_status_page_an(struct phy_device *phydev,
 	}
 
 	if (!fiber) {
-		phydev->lp_advertising =
-			mii_stat1000_to_ethtool_lpa_t(lpagb) |
-			mii_lpa_to_ethtool_lpa_t(lpa);
+		mii_lpa_to_linkmode_lpa_t(phydev->lp_advertising, lpa);
+		mii_stat1000_to_linkmode_lpa_t(phydev->lp_advertising, lpagb);
 
 		if (phydev->duplex == DUPLEX_FULL) {
 			phydev->pause = lpa & LPA_PAUSE_CAP ? 1 : 0;
@@ -1150,7 +1148,7 @@ static int marvell_read_status_page_an(struct phy_device *phydev,
 		}
 	} else {
 		/* The fiber link is only 1000M capable */
-		phydev->lp_advertising = fiber_lpa_to_ethtool_lpa_t(lpa);
+		fiber_lpa_to_linkmode_lpa_t(phydev->lp_advertising, lpa);
 
 		if (phydev->duplex == DUPLEX_FULL) {
 			if (!(lpa & LPA_PAUSE_FIBER)) {
@@ -1189,7 +1187,7 @@ static int marvell_read_status_page_fixed(struct phy_device *phydev)
 
 	phydev->pause = 0;
 	phydev->asym_pause = 0;
-	phydev->lp_advertising = 0;
+	linkmode_zero(phydev->lp_advertising);
 
 	return 0;
 }
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index d939dce16b35..6f6e886fc836 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -457,7 +457,7 @@ static int mv3310_read_status(struct phy_device *phydev)
 
 	phydev->speed = SPEED_UNKNOWN;
 	phydev->duplex = DUPLEX_UNKNOWN;
-	phydev->lp_advertising = 0;
+	linkmode_zero(phydev->lp_advertising);
 	phydev->link = 0;
 	phydev->pause = 0;
 	phydev->asym_pause = 0;
@@ -490,7 +490,7 @@ static int mv3310_read_status(struct phy_device *phydev)
 		if (val < 0)
 			return val;
 
-		phydev->lp_advertising |= mii_stat1000_to_ethtool_lpa_t(val);
+		mii_stat1000_to_linkmode_lpa_t(phydev->lp_advertising, val);
 
 		if (phydev->autoneg == AUTONEG_ENABLE)
 			phy_resolve_aneg_linkmode(phydev);
diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index a19f4dfa7470..03af927fa5ad 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -181,7 +181,7 @@ int genphy_c45_read_lpa(struct phy_device *phydev)
 	if (val < 0)
 		return val;
 
-	phydev->lp_advertising = mii_lpa_to_ethtool_lpa_t(val);
+	mii_lpa_to_linkmode_lpa_t(phydev->lp_advertising, val);
 	phydev->pause = val & LPA_PAUSE_CAP ? 1 : 0;
 	phydev->asym_pause = val & LPA_PAUSE_ASYM ? 1 : 0;
 
@@ -191,7 +191,8 @@ int genphy_c45_read_lpa(struct phy_device *phydev)
 		return val;
 
 	if (val & MDIO_AN_10GBT_STAT_LP10G)
-		phydev->lp_advertising |= ADVERTISED_10000baseT_Full;
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+				 phydev->lp_advertising);
 
 	return 0;
 }
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 9d192b660b07..2c3a13d1c421 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -199,11 +199,8 @@ size_t phy_speeds(unsigned int *speeds, size_t size,
 void phy_resolve_aneg_linkmode(struct phy_device *phydev)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(common);
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(lp);
 
-	ethtool_convert_legacy_u32_to_link_mode(lp, phydev->lp_advertising);
-
-	linkmode_and(common, lp, phydev->advertising);
+	linkmode_and(common, phydev->lp_advertising, phydev->advertising);
 
 	if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, common)) {
 		phydev->speed = SPEED_10000;
@@ -235,9 +232,11 @@ void phy_resolve_aneg_linkmode(struct phy_device *phydev)
 	}
 
 	if (phydev->duplex == DUPLEX_FULL) {
-		phydev->pause = !!(phydev->lp_advertising & ADVERTISED_Pause);
-		phydev->asym_pause = !!(phydev->lp_advertising &
-					ADVERTISED_Asym_Pause);
+		phydev->pause = linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+						  phydev->lp_advertising);
+		phydev->asym_pause = linkmode_test_bit(
+			ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+			phydev->lp_advertising);
 	}
 }
 EXPORT_SYMBOL_GPL(phy_resolve_aneg_linkmode);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index ecc8a7d5306c..d73873334e47 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -368,9 +368,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev,
 {
 	linkmode_copy(cmd->link_modes.supported, phydev->supported);
 	linkmode_copy(cmd->link_modes.advertising, phydev->advertising);
-
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.lp_advertising,
-						phydev->lp_advertising);
+	linkmode_copy(cmd->link_modes.lp_advertising, phydev->lp_advertising);
 
 	cmd->base.speed = phydev->speed;
 	cmd->base.duplex = phydev->duplex;
@@ -549,7 +547,7 @@ int phy_start_aneg(struct phy_device *phydev)
 		phy_sanitize_settings(phydev);
 
 	/* Invalidate LP advertising flags */
-	phydev->lp_advertising = 0;
+	linkmode_zero(phydev->lp_advertising);
 
 	err = phy_config_aneg(phydev);
 	if (err < 0)
@@ -610,7 +608,7 @@ int phy_speed_down(struct phy_device *phydev, bool sync)
 		return 0;
 
 	linkmode_copy(adv_old, phydev->advertising);
-	ethtool_convert_legacy_u32_to_link_mode(adv, phydev->lp_advertising);
+	linkmode_copy(adv, phydev->lp_advertising);
 	linkmode_and(adv, adv, phydev->supported);
 
 	if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, adv) ||
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 09a1c2d835b2..55202a0ac476 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1702,7 +1702,7 @@ int genphy_read_status(struct phy_device *phydev)
 	if (err)
 		return err;
 
-	phydev->lp_advertising = 0;
+	linkmode_zero(phydev->lp_advertising);
 
 	if (AUTONEG_ENABLE == phydev->autoneg) {
 		if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
@@ -1725,8 +1725,8 @@ int genphy_read_status(struct phy_device *phydev)
 				return -ENOLINK;
 			}
 
-			phydev->lp_advertising =
-				mii_stat1000_to_ethtool_lpa_t(lpagb);
+			mii_stat1000_to_linkmode_lpa_t(phydev->lp_advertising,
+						       lpagb);
 			common_adv_gb = lpagb & adv << 2;
 		}
 
@@ -1734,7 +1734,7 @@ int genphy_read_status(struct phy_device *phydev)
 		if (lpa < 0)
 			return lpa;
 
-		phydev->lp_advertising |= mii_lpa_to_ethtool_lpa_t(lpa);
+		mii_lpa_to_linkmode_lpa_t(phydev->lp_advertising, lpa);
 
 		adv = phy_read(phydev, MII_ADVERTISE);
 		if (adv < 0)
diff --git a/drivers/net/phy/uPD60620.c b/drivers/net/phy/uPD60620.c
index 55f48ee3595a..1e4fc42e4629 100644
--- a/drivers/net/phy/uPD60620.c
+++ b/drivers/net/phy/uPD60620.c
@@ -47,7 +47,7 @@ static int upd60620_read_status(struct phy_device *phydev)
 		return phy_state;
 
 	phydev->link = 0;
-	phydev->lp_advertising = 0;
+	linkmode_zero(phydev->lp_advertising);
 	phydev->pause = 0;
 	phydev->asym_pause = 0;
 
@@ -70,8 +70,8 @@ static int upd60620_read_status(struct phy_device *phydev)
 			if (phy_state < 0)
 				return phy_state;
 
-			phydev->lp_advertising
-				= mii_lpa_to_ethtool_lpa_t(phy_state);
+			mii_lpa_to_linkmode_lpa_t(phydev->lp_advertising,
+						  phy_state);
 
 			if (phydev->duplex == DUPLEX_FULL) {
 				if (phy_state & LPA_PAUSE_CAP)
diff --git a/include/linux/mii.h b/include/linux/mii.h
index aaa458bbef2a..e7112e878bb0 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -287,6 +287,25 @@ static inline u32 mii_stat1000_to_ethtool_lpa_t(u32 lpa)
 	return result;
 }
 
+/**
+ * mii_stat1000_to_linkmode_lpa_t
+ * @advertising: target the linkmode advertisement settings
+ * @adv: value of the MII_STAT1000 register
+ *
+ * A small helper function that translates MII_STAT1000 bits, when in
+ * 1000Base-T mode, to linkmode advertisement settings.
+ */
+static inline void mii_stat1000_to_linkmode_lpa_t(unsigned long *advertising,
+						  u32 lpa)
+{
+	if (lpa & LPA_1000HALF)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+				 advertising);
+	if (lpa & LPA_1000FULL)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				 advertising);
+}
+
 /**
  * ethtool_adv_to_mii_adv_x
  * @ethadv: the ethtool advertisement settings
@@ -384,6 +403,23 @@ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising,
 		linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising);
 }
 
+/**
+ * mii_lpa_to_linkmode_lpa_t
+ * @adv: value of the MII_LPA register
+ *
+ * A small helper function that translates MII_LPA bits, when in
+ * 1000Base-T mode, to linkmode LP advertisement settings.
+ */
+static inline void mii_lpa_to_linkmode_lpa_t(unsigned long *lp_advertising,
+					     u32 lpa)
+{
+	if (lpa & LPA_LPACK)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+				 lp_advertising);
+
+	mii_adv_to_linkmode_adv_t(lp_advertising, lpa);
+}
+
 /**
  * linkmode_adv_to_lcl_adv_t
  * @advertising:pointer to linkmode advertising
diff --git a/include/linux/phy.h b/include/linux/phy.h
index cbc66ac3b560..8f927246acdb 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -414,8 +414,7 @@ struct phy_device {
 	/* See ethtool.h for more info */
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
-
-	u32 lp_advertising;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising);
 
 	/* Energy efficient ethernet modes which should be prohibited */
 	u32 eee_broken_modes;
-- 
cgit v1.2.3


From fe1919147c69c3b820f801eb99bcc50cec0fb5a5 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 10 Nov 2018 23:43:35 +0100
Subject: net: phy: Fixup kerneldoc markup.

Add missing markup for function parameters

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mii.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/mii.h b/include/linux/mii.h
index e7112e878bb0..fb7ae4ae8ce3 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -209,7 +209,7 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv)
 
 /**
  * linkmode_adv_to_mii_ctrl1000_t
- * advertising: the linkmode advertisement settings
+ * @advertising: the linkmode advertisement settings
  *
  * A small helper function that translates linkmode advertisement
  * settings to phy autonegotiation advertisements for the
-- 
cgit v1.2.3


From 3c6b59d6f07c69dbe9d9e0191d158820bdda7f60 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 10 Nov 2018 23:43:36 +0100
Subject: net: phy: Add more link modes to the settings table

Now that PHYs and MAC can support more than 32 bit masks, add link
modes which are > 31 to the PHY settings table.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-core.c | 162 +++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 158 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 2c3a13d1c421..6d274cdc2796 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -62,6 +62,124 @@ EXPORT_SYMBOL_GPL(phy_duplex_to_str);
  * must be grouped by speed and sorted in descending match priority
  * - iow, descending speed. */
 static const struct phy_setting settings[] = {
+	/* 100G */
+	{
+		.speed = SPEED_100000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+	},
+	{
+		.speed = SPEED_100000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+	},
+	{
+		.speed = SPEED_100000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
+	},
+	{
+		.speed = SPEED_100000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
+	},
+	/* 56G */
+	{
+		.speed = SPEED_56000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT,
+	},
+	{
+		.speed = SPEED_56000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT,
+	},
+	{
+		.speed = SPEED_56000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT,
+	},
+	{
+		.speed = SPEED_56000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT,
+	},
+	/* 50G */
+	{
+		.speed = SPEED_50000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
+	},
+	{
+		.speed = SPEED_50000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT,
+	},
+	{
+		.speed = SPEED_50000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
+	},
+	/* 40G */
+	{
+		.speed = SPEED_40000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+	},
+	{
+		.speed = SPEED_40000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+	},
+	{
+		.speed = SPEED_40000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT,
+	},
+	{
+		.speed = SPEED_40000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
+	},
+	/* 25G */
+	{
+		.speed = SPEED_25000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+	},
+	{
+		.speed = SPEED_25000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+	},
+	{
+		.speed = SPEED_25000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
+	},
+
+	/* 20G */
+	{
+		.speed = SPEED_20000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT,
+	},
+	{
+		.speed = SPEED_20000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT,
+	},
+	/* 10G */
+	{
+		.speed = SPEED_10000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT,
+	},
+	{
+		.speed = SPEED_10000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_10000baseER_Full_BIT,
+	},
 	{
 		.speed = SPEED_10000,
 		.duplex = DUPLEX_FULL,
@@ -72,25 +190,54 @@ static const struct phy_setting settings[] = {
 		.duplex = DUPLEX_FULL,
 		.bit = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
 	},
+	{
+		.speed = SPEED_10000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_10000baseLR_Full_BIT,
+	},
+	{
+		.speed = SPEED_10000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT,
+	},
+	{
+		.speed = SPEED_10000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_10000baseR_FEC_BIT,
+	},
+	{
+		.speed = SPEED_10000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
+	},
 	{
 		.speed = SPEED_10000,
 		.duplex = DUPLEX_FULL,
 		.bit = ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
 	},
+	/* 5G */
+	{
+		.speed = SPEED_5000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
+	},
+
+	/* 2.5G */
 	{
 		.speed = SPEED_2500,
 		.duplex = DUPLEX_FULL,
-		.bit = ETHTOOL_LINK_MODE_2500baseX_Full_BIT,
+		.bit = ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
 	},
 	{
-		.speed = SPEED_1000,
+		.speed = SPEED_2500,
 		.duplex = DUPLEX_FULL,
-		.bit = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+		.bit = ETHTOOL_LINK_MODE_2500baseX_Full_BIT,
 	},
+	/* 1G */
 	{
 		.speed = SPEED_1000,
 		.duplex = DUPLEX_FULL,
-		.bit = ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
+		.bit = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
 	},
 	{
 		.speed = SPEED_1000,
@@ -102,6 +249,12 @@ static const struct phy_setting settings[] = {
 		.duplex = DUPLEX_HALF,
 		.bit = ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
 	},
+	{
+		.speed = SPEED_1000,
+		.duplex = DUPLEX_FULL,
+		.bit = ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
+	},
+	/* 100M */
 	{
 		.speed = SPEED_100,
 		.duplex = DUPLEX_FULL,
@@ -112,6 +265,7 @@ static const struct phy_setting settings[] = {
 		.duplex = DUPLEX_HALF,
 		.bit = ETHTOOL_LINK_MODE_100baseT_Half_BIT,
 	},
+	/* 10M */
 	{
 		.speed = SPEED_10,
 		.duplex = DUPLEX_FULL,
-- 
cgit v1.2.3


From cb6402fe26358a33e32fb71054b248c76dcfe491 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 10 Nov 2018 23:43:37 +0100
Subject: net: phy: Add support for resolving 5G and 2.5G autoneg

Now that 2.5G and 5G can be represented in phydev->advertising and
phydev->lp_advertising, add these two links modes as possible
resolutions to auto negotiation.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-core.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 6d274cdc2796..20fbd5eb56fd 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -359,6 +359,14 @@ void phy_resolve_aneg_linkmode(struct phy_device *phydev)
 	if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, common)) {
 		phydev->speed = SPEED_10000;
 		phydev->duplex = DUPLEX_FULL;
+	} else if (linkmode_test_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
+				     common)) {
+		phydev->speed = SPEED_5000;
+		phydev->duplex = DUPLEX_FULL;
+	} else if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
+				     common)) {
+		phydev->speed = SPEED_2500;
+		phydev->duplex = DUPLEX_FULL;
 	} else if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
 				     common)) {
 		phydev->speed = SPEED_1000;
-- 
cgit v1.2.3


From b3dce4da5bb4c4c991b10c9899e6dd6ce29e8b3e Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 11 Nov 2018 00:32:14 +0100
Subject: net: dsa: mv88e6xxx: Group cmode ops together

Move .port_set_cmode next to .port_get_cmode.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index e05d4eddc935..13c6d76d9150 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3405,11 +3405,11 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_pause_limit = mv88e6390_port_pause_limit,
-	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
 	.port_get_cmode = mv88e6352_port_get_cmode,
+	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3710,11 +3710,11 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.port_set_jumbo_size = mv88e6165_port_set_jumbo_size,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_limit = mv88e6390_port_pause_limit,
-	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
 	.port_get_cmode = mv88e6352_port_get_cmode,
+	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3757,11 +3757,11 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.port_set_jumbo_size = mv88e6165_port_set_jumbo_size,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_limit = mv88e6390_port_pause_limit,
-	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
 	.port_get_cmode = mv88e6352_port_get_cmode,
+	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
-- 
cgit v1.2.3


From fdc71eea8c0aefab80020044f8abf5c3c6814b44 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 11 Nov 2018 00:32:15 +0100
Subject: net: dsa: mv88e6xxx: Differentiate between 6390 and 6390X cmodes

The X family variants support additional ports modes, for 10G
operation, which the non-X variants don't have. Add a port_set_cmode()
for non-X variants to enforce this.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c |  7 +++++--
 drivers/net/dsa/mv88e6xxx/port.c | 15 +++++++++++++++
 drivers/net/dsa/mv88e6xxx/port.h |  2 ++
 3 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 13c6d76d9150..733bb137efbf 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3234,6 +3234,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
 	.port_get_cmode = mv88e6352_port_get_cmode,
+	.port_set_cmode = mv88e6390_port_set_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3276,6 +3277,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
 	.port_get_cmode = mv88e6352_port_get_cmode,
+	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3318,6 +3320,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
 	.port_get_cmode = mv88e6352_port_get_cmode,
+	.port_set_cmode = mv88e6390_port_set_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3409,7 +3412,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
 	.port_get_cmode = mv88e6352_port_get_cmode,
-	.port_set_cmode = mv88e6390x_port_set_cmode,
+	.port_set_cmode = mv88e6390_port_set_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3714,7 +3717,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
 	.port_get_cmode = mv88e6352_port_get_cmode,
-	.port_set_cmode = mv88e6390x_port_set_cmode,
+	.port_set_cmode = mv88e6390_port_set_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index cd7db60a508b..e718404a5e03 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -437,6 +437,21 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 	return 0;
 }
 
+int mv88e6390_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
+			     phy_interface_t mode)
+{
+	switch (mode) {
+	case PHY_INTERFACE_MODE_XGMII:
+	case PHY_INTERFACE_MODE_XAUI:
+	case PHY_INTERFACE_MODE_RXAUI:
+		return -EINVAL;
+	default:
+		break;
+	}
+
+	return mv88e6390x_port_set_cmode(chip, port, mode);
+}
+
 int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
 {
 	int err;
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index 36904c9bf955..0d81866d0e4a 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -310,6 +310,8 @@ int mv88e6097_port_pause_limit(struct mv88e6xxx_chip *chip, int port, u8 in,
 			       u8 out);
 int mv88e6390_port_pause_limit(struct mv88e6xxx_chip *chip, int port, u8 in,
 			       u8 out);
+int mv88e6390_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
+			     phy_interface_t mode);
 int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 			      phy_interface_t mode);
 int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
-- 
cgit v1.2.3


From 787799a9d5557f9494bf79b7052d3b9ee68f3b80 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 11 Nov 2018 00:32:16 +0100
Subject: net: dsa: mv88e6xxx: Default ports 9/10 6390X CMODE to 1000BaseX

The 6390X family has 8 SERDES interfaces. This allows ports 9 and 10
to support up to 10Gbps using 4 SERDES interfaces. However, when lower
speeds are used, which need fewer SERDES interfaces, the unused SERDES
interfaces can be used by ports 2-8.

The hardware defaults to ports 9 and 10 having all 4 SERDES interfaces
assigned to them. This only gets changed when the interface is
configured after what the SFP supports has been determined, or the 10G
PHY completes auto-neg.

For hardware designs which limit ports 9 and 10 to one or two SERDES
interfaces, and place SFPs on the lower interfaces, this is too
late. Those ports with SFP should not wait until ports 9/10 are up in
order to get access to the SERDES interface. So change the default
configuration when the driver is initialised. Configure ports 9 and 10
to 1000BaseX, so they use a single SERDES interface, freeing up the
others. They can steal them back if they need them.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/port.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index e718404a5e03..ebd26b6a93e6 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -368,12 +368,15 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 	u16 reg;
 	int err;
 
-	if (mode == PHY_INTERFACE_MODE_NA)
-		return 0;
-
 	if (port != 9 && port != 10)
 		return -EOPNOTSUPP;
 
+	/* Default to a slow mode, so freeing up SERDES interfaces for
+	 * other ports which might use them for SFPs.
+	 */
+	if (mode == PHY_INTERFACE_MODE_NA)
+		mode = PHY_INTERFACE_MODE_1000BASEX;
+
 	switch (mode) {
 	case PHY_INTERFACE_MODE_1000BASEX:
 		cmode = MV88E6XXX_PORT_STS_CMODE_1000BASE_X;
-- 
cgit v1.2.3


From 2defda1f4b91f83a449de29cac7722afb0c57444 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 11 Nov 2018 00:32:17 +0100
Subject: net: dsa: mv88e6xxx: Add support for SERDES on ports 2-8 for 6390X

The 6390X family has 8 SERDES interfaces. When ports 9 and 10 are not
using all their SERDES interfaces, the unused ones can be assigned to
ports 2-8. Add support for interrupts from SERDES interfaces connected
to these lower ports.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c   |  8 ++++----
 drivers/net/dsa/mv88e6xxx/serdes.c | 26 +++++++++++++++++++-------
 drivers/net/dsa/mv88e6xxx/serdes.h |  2 ++
 3 files changed, 25 insertions(+), 11 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 733bb137efbf..fc0f508879d4 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3293,8 +3293,8 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390x_serdes_power,
-	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
-	.serdes_irq_free = mv88e6390_serdes_irq_free,
+	.serdes_irq_setup = mv88e6390x_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390x_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.phylink_validate = mv88e6390x_phylink_validate,
 };
@@ -3780,8 +3780,8 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390x_serdes_power,
-	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
-	.serdes_irq_free = mv88e6390_serdes_irq_free,
+	.serdes_irq_setup = mv88e6390x_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390x_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index bb69650ff772..2caa8c8b4b55 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -619,15 +619,11 @@ out:
 	return ret;
 }
 
-int mv88e6390_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port)
+int mv88e6390x_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port)
 {
 	int lane;
 	int err;
 
-	/* Only support ports 9 and 10 at the moment */
-	if (port < 9)
-		return 0;
-
 	lane = mv88e6390x_serdes_get_lane(chip, port);
 
 	if (lane == -ENODEV)
@@ -663,11 +659,19 @@ int mv88e6390_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port)
 	return mv88e6390_serdes_irq_enable(chip, port, lane);
 }
 
-void mv88e6390_serdes_irq_free(struct mv88e6xxx_chip *chip, int port)
+int mv88e6390_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port)
+{
+	if (port < 9)
+		return 0;
+
+	return mv88e6390_serdes_irq_setup(chip, port);
+}
+
+void mv88e6390x_serdes_irq_free(struct mv88e6xxx_chip *chip, int port)
 {
 	int lane = mv88e6390x_serdes_get_lane(chip, port);
 
-	if (port < 9)
+	if (lane == -ENODEV)
 		return;
 
 	if (lane < 0)
@@ -685,6 +689,14 @@ void mv88e6390_serdes_irq_free(struct mv88e6xxx_chip *chip, int port)
 	chip->ports[port].serdes_irq = 0;
 }
 
+void mv88e6390_serdes_irq_free(struct mv88e6xxx_chip *chip, int port)
+{
+	if (port < 9)
+		return;
+
+	mv88e6390x_serdes_irq_free(chip, port);
+}
+
 int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
 {
 	u8 cmode = chip->ports[port].cmode;
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index 7870c5a9ef12..573dce8b1eb4 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -77,6 +77,8 @@ int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6390x_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6390_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port);
 void mv88e6390_serdes_irq_free(struct mv88e6xxx_chip *chip, int port);
+int mv88e6390x_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port);
+void mv88e6390x_serdes_irq_free(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip,
 				 int port, uint8_t *data);
-- 
cgit v1.2.3


From 5e13a0d3f5c11df7eb297e6583cf874a79a00374 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 11 Nov 2018 20:10:10 +0800
Subject: tcp: minor optimization in tcp ack fast path processing

Bitwise operation is a little faster.
So I replace after() with using the flag FLAG_SND_UNA_ADVANCED as it is
already set before.

In addtion, there's another similar improvement in tcp_cwnd_reduction().

Cc: Joe Perches <joe@perches.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2868ef28ce52..edaaebfbcd46 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2457,8 +2457,8 @@ void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag)
 		u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +
 			       tp->prior_cwnd - 1;
 		sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out;
-	} else if ((flag & FLAG_RETRANS_DATA_ACKED) &&
-		   !(flag & FLAG_LOST_RETRANS)) {
+	} else if ((flag & (FLAG_RETRANS_DATA_ACKED | FLAG_LOST_RETRANS)) ==
+		   FLAG_RETRANS_DATA_ACKED) {
 		sndcnt = min_t(int, delta,
 			       max_t(int, tp->prr_delivered - tp->prr_out,
 				     newly_acked_sacked) + 1);
@@ -3610,7 +3610,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if (flag & FLAG_UPDATE_TS_RECENT)
 		tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
 
-	if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) {
+	if ((flag & (FLAG_SLOWPATH | FLAG_SND_UNA_ADVANCED)) ==
+	    FLAG_SND_UNA_ADVANCED) {
 		/* Window is constant, pure forward advance.
 		 * No more checks are required.
 		 * Note, we use the fact that SND.UNA>=SND.WL2.
-- 
cgit v1.2.3


From 1c09f7d073b1d1ce85765c5552e4b40a6b6ba770 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 11 Nov 2018 06:41:29 -0800
Subject: tcp: do not try to defer skbs with eor mark (MSG_EOR)

Applications using MSG_EOR are giving a strong hint to TCP stack :

Subsequent sendmsg() can not append more bytes to skbs having
the EOR mark.

Do not try to TSO defer suchs skbs, there is really no hope.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9c34b97d365d..35feadf48030 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1944,6 +1944,10 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
 		goto send_now;
 
+	/* If this packet won't get more data, do not wait. */
+	if (TCP_SKB_CB(skb)->eor)
+		goto send_now;
+
 	win_divisor = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_win_divisor);
 	if (win_divisor) {
 		u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
-- 
cgit v1.2.3


From f1c6ea3827b5e5ec62e297bcf4ccfd065326e8f7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 11 Nov 2018 06:41:30 -0800
Subject: tcp: refine tcp_tso_should_defer() after EDT adoption

tcp_tso_should_defer() last step tries to check if the probable
next ACK packet is coming in less than half rtt.

Problem is that the head->tstamp might be in the future,
so we need to use signed arithmetics to avoid overflows.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 35feadf48030..78a56cef7e39 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1907,10 +1907,11 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 				 bool *is_cwnd_limited, u32 max_segs)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 age, send_win, cong_win, limit, in_flight;
+	u32 send_win, cong_win, limit, in_flight;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *head;
 	int win_divisor;
+	s64 delta;
 
 	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 		goto send_now;
@@ -1972,9 +1973,9 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	head = tcp_rtx_queue_head(sk);
 	if (!head)
 		goto send_now;
-	age = tcp_stamp_us_delta(tp->tcp_mstamp, tcp_skb_timestamp_us(head));
+	delta = tp->tcp_clock_cache - head->tstamp;
 	/* If next ACK is likely to come too late (half srtt), do not defer */
-	if (age < (tp->srtt_us >> 4))
+	if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0)
 		goto send_now;
 
 	/* Ok, it looks like it is advisable to defer. */
-- 
cgit v1.2.3


From a682850a114aef947da5d603f7fd2cfe7eabbd72 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 11 Nov 2018 06:41:31 -0800
Subject: tcp: get rid of tcp_tso_should_defer() dependency on HZ/jiffies

tcp_tso_should_defer() first heuristic is to not defer
if last send is "old enough".

Its current implementation uses jiffies and its low granularity.

TSO autodefer performance should not rely on kernel HZ :/

After EDT conversion, we have state variables in nanoseconds that
can allow us to properly implement the heuristic.

This patch increases TSO chunk sizes on medium rate flows,
especially when receivers do not use GRO or similar aggregation.

It also reduces bursts for HZ=100 or HZ=250 kernels, making TCP
behavior more uniform.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 78a56cef7e39..75dcf4daca72 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1920,9 +1920,12 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 		goto send_now;
 
 	/* Avoid bursty behavior by allowing defer
-	 * only if the last write was recent.
+	 * only if the last write was recent (1 ms).
+	 * Note that tp->tcp_wstamp_ns can be in the future if we have
+	 * packets waiting in a qdisc or device for EDT delivery.
 	 */
-	if ((s32)(tcp_jiffies32 - tp->lsndtime) > 0)
+	delta = tp->tcp_clock_cache - tp->tcp_wstamp_ns - NSEC_PER_MSEC;
+	if (delta > 0)
 		goto send_now;
 
 	in_flight = tcp_packets_in_flight(tp);
-- 
cgit v1.2.3


From c73e5807e4f6fc6d373a5db55b45f639f8bb6328 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 11 Nov 2018 07:34:28 -0800
Subject: tcp: tsq: no longer use limit_output_bytes for paced flows

FQ pacing guarantees that paced packets queued by one flow do not
add head-of-line blocking for other flows.

After TCP GSO conversion, increasing limit_output_bytes to 1 MB is safe,
since this maps to 16 skbs at most in qdisc or device queues.
(or slightly more if some drivers lower {gso_max_segs|size})

We still can queue at most 1 ms worth of traffic (this can be scaled
by wifi drivers if they need to)

Tested:

# ethtool -c eth0 | egrep "tx-usecs:|tx-frames:" # 40 Gbit mlx4 NIC
tx-usecs: 16
tx-frames: 16
# tc qdisc replace dev eth0 root fq
# for f in {1..10};do netperf -P0 -H lpaa24,6 -o THROUGHPUT;done

Before patch:
27711
26118
27107
27377
27712
27388
27340
27117
27278
27509

After patch:
37434
36949
36658
36998
37711
37291
37605
36659
36544
37349

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 2 +-
 net/ipv4/tcp_ipv4.c                    | 4 ++--
 net/ipv4/tcp_output.c                  | 5 +++--
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index aa9e6a331679..af2a69439b93 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -759,7 +759,7 @@ tcp_limit_output_bytes - INTEGER
 	flows, for typical pfifo_fast qdiscs.  tcp_limit_output_bytes
 	limits the number of bytes on qdisc or device to reduce artificial
 	RTT/cwnd and reduce bufferbloat.
-	Default: 262144
+	Default: 1048576 (16 * 65536)
 
 tcp_challenge_ack_limit - INTEGER
 	Limits number of Challenge ACK sent per second, as recommended
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5424a4077c27..0952d4b772e7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2574,8 +2574,8 @@ static int __net_init tcp_sk_init(struct net *net)
 	 * which are too large can cause TCP streams to be bursty.
 	 */
 	net->ipv4.sysctl_tcp_tso_win_divisor = 3;
-	/* Default TSQ limit of four TSO segments */
-	net->ipv4.sysctl_tcp_limit_output_bytes = 262144;
+	/* Default TSQ limit of 16 TSO segments */
+	net->ipv4.sysctl_tcp_limit_output_bytes = 16 * 65536;
 	/* rfc5961 challenge ack rate limiting */
 	net->ipv4.sysctl_tcp_challenge_ack_limit = 1000;
 	net->ipv4.sysctl_tcp_min_tso_segs = 2;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 75dcf4daca72..d40d4cc53319 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2220,8 +2220,9 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 	limit = max_t(unsigned long,
 		      2 * skb->truesize,
 		      sk->sk_pacing_rate >> sk->sk_pacing_shift);
-	limit = min_t(unsigned long, limit,
-		      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+	if (sk->sk_pacing_status == SK_PACING_NONE)
+		limit = min_t(unsigned long, limit,
+			      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
 	limit <<= factor;
 
 	if (refcount_read(&sk->sk_wmem_alloc) > limit) {
-- 
cgit v1.2.3


From 48872c11b77271ef9b070bdc50afe6655c4eb9aa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 11 Nov 2018 09:11:31 -0800
Subject: net_sched: sch_fq: add dctcp-like marking

Similar to 80ba92fa1a92 ("codel: add ce_threshold attribute")

After EDT adoption, it became easier to implement DCTCP-like CE marking.

In many cases, queues are not building in the network fabric but on
the hosts themselves.

If packets leaving fq missed their Earliest Departure Time by XXX usec,
we mark them with ECN CE. This gives a feedback (after one RTT) to
the sender to slow down and find better operating mode.

Example :

tc qd replace dev eth0 root fq ce_threshold 2.5ms

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  3 +++
 net/sched/sch_fq.c             | 21 +++++++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 89ee47c2f17d..ee017bc057a3 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -864,6 +864,8 @@ enum {
 
 	TCA_FQ_LOW_RATE_THRESHOLD, /* per packet delay under this rate */
 
+	TCA_FQ_CE_THRESHOLD,	/* DCTCP-like CE-marking threshold */
+
 	__TCA_FQ_MAX
 };
 
@@ -882,6 +884,7 @@ struct tc_fq_qd_stats {
 	__u32	inactive_flows;
 	__u32	throttled_flows;
 	__u32	unthrottle_latency_ns;
+	__u64	ce_mark;		/* packets above ce_threshold */
 };
 
 /* Heavy-Hitter Filter */
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 4b1af706896c..3671eab91107 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -94,6 +94,7 @@ struct fq_sched_data {
 	u32		flow_refill_delay;
 	u32		flow_plimit;	/* max packets per flow */
 	unsigned long	flow_max_rate;	/* optional max rate per flow */
+	u64		ce_threshold;
 	u32		orphan_mask;	/* mask for orphaned skb */
 	u32		low_rate_threshold;
 	struct rb_root	*fq_root;
@@ -107,6 +108,7 @@ struct fq_sched_data {
 	u64		stat_gc_flows;
 	u64		stat_internal_packets;
 	u64		stat_throttled;
+	u64		stat_ce_mark;
 	u64		stat_flows_plimit;
 	u64		stat_pkts_too_long;
 	u64		stat_allocation_errors;
@@ -454,6 +456,11 @@ begin:
 			fq_flow_set_throttled(q, f);
 			goto begin;
 		}
+		if (time_next_packet &&
+		    (s64)(now - time_next_packet - q->ce_threshold) > 0) {
+			INET_ECN_set_ce(skb);
+			q->stat_ce_mark++;
+		}
 	}
 
 	skb = fq_dequeue_head(sch, f);
@@ -650,6 +657,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = {
 	[TCA_FQ_BUCKETS_LOG]		= { .type = NLA_U32 },
 	[TCA_FQ_FLOW_REFILL_DELAY]	= { .type = NLA_U32 },
 	[TCA_FQ_LOW_RATE_THRESHOLD]	= { .type = NLA_U32 },
+	[TCA_FQ_CE_THRESHOLD]		= { .type = NLA_U32 },
 };
 
 static int fq_change(struct Qdisc *sch, struct nlattr *opt,
@@ -729,6 +737,10 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_FQ_ORPHAN_MASK])
 		q->orphan_mask = nla_get_u32(tb[TCA_FQ_ORPHAN_MASK]);
 
+	if (tb[TCA_FQ_CE_THRESHOLD])
+		q->ce_threshold = (u64)NSEC_PER_USEC *
+				  nla_get_u32(tb[TCA_FQ_CE_THRESHOLD]);
+
 	if (!err) {
 		sch_tree_unlock(sch);
 		err = fq_resize(sch, fq_log);
@@ -779,6 +791,10 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt,
 	q->fq_trees_log		= ilog2(1024);
 	q->orphan_mask		= 1024 - 1;
 	q->low_rate_threshold	= 550000 / 8;
+
+	/* Default ce_threshold of 4294 seconds */
+	q->ce_threshold		= (u64)NSEC_PER_USEC * ~0U;
+
 	qdisc_watchdog_init_clockid(&q->watchdog, sch, CLOCK_MONOTONIC);
 
 	if (opt)
@@ -792,6 +808,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt,
 static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct fq_sched_data *q = qdisc_priv(sch);
+	u64 ce_threshold = q->ce_threshold;
 	struct nlattr *opts;
 
 	opts = nla_nest_start(skb, TCA_OPTIONS);
@@ -800,6 +817,8 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 
 	/* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore */
 
+	do_div(ce_threshold, NSEC_PER_USEC);
+
 	if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) ||
 	    nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) ||
 	    nla_put_u32(skb, TCA_FQ_QUANTUM, q->quantum) ||
@@ -812,6 +831,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	    nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, q->orphan_mask) ||
 	    nla_put_u32(skb, TCA_FQ_LOW_RATE_THRESHOLD,
 			q->low_rate_threshold) ||
+	    nla_put_u32(skb, TCA_FQ_CE_THRESHOLD, (u32)ce_threshold) ||
 	    nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log))
 		goto nla_put_failure;
 
@@ -841,6 +861,7 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 	st.throttled_flows	  = q->throttled_flows;
 	st.unthrottle_latency_ns  = min_t(unsigned long,
 					  q->unthrottle_latency_ns, ~0U);
+	st.ce_mark		  = q->stat_ce_mark;
 	sch_tree_unlock(sch);
 
 	return gnet_stats_copy_app(d, &st, sizeof(st));
-- 
cgit v1.2.3


From 9206eb0bc5679d06d2f54b9db86fe2b9a55e07e4 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 11 Nov 2018 20:31:21 +0100
Subject: PCI: add USR vendor id and use it in r8169 and w6692 driver

The PCI vendor id of U.S. Robotics isn't defined in pci_ids.h so far,
only ISDN driver w6692 has a private definition. Move the definition
to pci_ids.h and use it in the r8169 driver too.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hardware/mISDN/w6692.c  | 3 ---
 drivers/net/ethernet/realtek/r8169.c | 2 +-
 include/linux/pci_ids.h              | 2 ++
 3 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c
index 5acf6ab67cd3..6f60aced11c5 100644
--- a/drivers/isdn/hardware/mISDN/w6692.c
+++ b/drivers/isdn/hardware/mISDN/w6692.c
@@ -52,10 +52,7 @@ static const struct w6692map  w6692_map[] =
 	{W6692_USR, "USR W6692"}
 };
 
-#ifndef PCI_VENDOR_ID_USR
-#define PCI_VENDOR_ID_USR	0x16ec
 #define PCI_DEVICE_ID_USR_6692	0x3409
-#endif
 
 struct w6692_ch {
 	struct bchannel		bch;
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 56de045268f8..b3010cc51cdd 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -224,7 +224,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_DLINK,	0x4300), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_DLINK,	0x4302), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AT,		0xc107), 0, 0, RTL_CFG_0 },
-	{ PCI_DEVICE(0x16ec,			0x0116), 0, 0, RTL_CFG_0 },
+	{ PCI_DEVICE(PCI_VENDOR_ID_USR,		0x0116), 0, 0, RTL_CFG_0 },
 	{ PCI_VENDOR_ID_LINKSYS,		0x1032,
 		PCI_ANY_ID, 0x0024, 0, 0, RTL_CFG_0 },
 	{ 0x0001,				0x8168,
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 69f0abe1ba1a..144de2e89531 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2359,6 +2359,8 @@
 
 #define PCI_VENDOR_ID_SYNOPSYS		0x16c3
 
+#define PCI_VENDOR_ID_USR		0x16ec
+
 #define PCI_VENDOR_ID_VITESSE		0x1725
 #define PCI_DEVICE_ID_VITESSE_VSC7174	0x7174
 
-- 
cgit v1.2.3


From 30beabb3c32122d533ce0e2fc712f9d720a82f9f Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 12 Nov 2018 01:47:30 +0000
Subject: net: phy: marvell: remove set but not used variable 'pause'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/phy/marvell.c: In function 'm88e1510_config_init':
drivers/net/phy/marvell.c:850:7: warning:
 variable 'pause' set but not used [-Wunused-but-set-variable]

It not used any more after commit 3c1bcc8614db ("net: ethernet: Convert phydev
advertize and supported from u32 to link mode")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 36a0db86c6f4..6a9881942e53 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -847,7 +847,6 @@ static int m88e1510_config_init(struct phy_device *phydev)
 
 	/* SGMII-to-Copper mode initialization */
 	if (phydev->interface == PHY_INTERFACE_MODE_SGMII) {
-		u32 pause;
 
 		/* Select page 18 */
 		err = marvell_set_page(phydev, 18);
@@ -878,7 +877,6 @@ static int m88e1510_config_init(struct phy_device *phydev)
 		 * This means we can never be truely sure what was advertised,
 		 * so disable Pause support.
 		 */
-		pause = SUPPORTED_Pause | SUPPORTED_Asym_Pause;
 		linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
 				   phydev->supported);
 		linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT,
-- 
cgit v1.2.3


From 58fc419be2313f8831ec75ad95263f050b69f476 Mon Sep 17 00:00:00 2001
From: Andreas Jaggi <andreas.jaggi@waterwave.ch>
Date: Thu, 1 Nov 2018 06:50:33 +0100
Subject: netfilter: ctnetlink: always honor CTA_MARK_MASK

Useful to only set a particular range of the conntrack mark while
leaving existing parts of the value alone, e.g. when updating
conntrack marks via netlink from userspace.

For NFQUEUE it was already implemented in commit 534473c6080e
("netfilter: ctnetlink: honor CTA_MARK_MASK when setting ctmark").

This now adds the same functionality also for the other netlink
conntrack mark changes.

Signed-off-by: Andreas Jaggi <andreas.jaggi@waterwave.ch>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_netlink.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 4ae8e528943a..4f54c4355d33 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1688,6 +1688,22 @@ static int ctnetlink_change_timeout(struct nf_conn *ct,
 	return 0;
 }
 
+#if defined(CONFIG_NF_CONNTRACK_MARK)
+static void ctnetlink_change_mark(struct nf_conn *ct,
+				    const struct nlattr * const cda[])
+{
+	u32 mark, newmark, mask = 0;
+
+	if (cda[CTA_MARK_MASK])
+		mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK]));
+
+	mark = ntohl(nla_get_be32(cda[CTA_MARK]));
+	newmark = (ct->mark & mask) ^ mark;
+	if (newmark != ct->mark)
+		ct->mark = newmark;
+}
+#endif
+
 static const struct nla_policy protoinfo_policy[CTA_PROTOINFO_MAX+1] = {
 	[CTA_PROTOINFO_TCP]	= { .type = NLA_NESTED },
 	[CTA_PROTOINFO_DCCP]	= { .type = NLA_NESTED },
@@ -1883,7 +1899,7 @@ ctnetlink_change_conntrack(struct nf_conn *ct,
 
 #if defined(CONFIG_NF_CONNTRACK_MARK)
 	if (cda[CTA_MARK])
-		ct->mark = ntohl(nla_get_be32(cda[CTA_MARK]));
+		ctnetlink_change_mark(ct, cda);
 #endif
 
 	if (cda[CTA_SEQ_ADJ_ORIG] || cda[CTA_SEQ_ADJ_REPLY]) {
@@ -2027,7 +2043,7 @@ ctnetlink_create_conntrack(struct net *net,
 
 #if defined(CONFIG_NF_CONNTRACK_MARK)
 	if (cda[CTA_MARK])
-		ct->mark = ntohl(nla_get_be32(cda[CTA_MARK]));
+		ctnetlink_change_mark(ct, cda);
 #endif
 
 	/* setup master conntrack: this is a confirmed expectation */
@@ -2524,14 +2540,7 @@ ctnetlink_glue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct)
 	}
 #if defined(CONFIG_NF_CONNTRACK_MARK)
 	if (cda[CTA_MARK]) {
-		u32 mask = 0, mark, newmark;
-		if (cda[CTA_MARK_MASK])
-			mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK]));
-
-		mark = ntohl(nla_get_be32(cda[CTA_MARK]));
-		newmark = (ct->mark & mask) ^ mark;
-		if (newmark != ct->mark)
-			ct->mark = newmark;
+		ctnetlink_change_mark(ct, cda);
 	}
 #endif
 	return 0;
-- 
cgit v1.2.3


From 3987b6a4ccf849c3e2b3d581a22ebf55eae995cb Mon Sep 17 00:00:00 2001
From: Simon Wunderlich <sw@simonwunderlich.de>
Date: Mon, 5 Nov 2018 07:11:52 +0100
Subject: batman-adv: Start new development cycle

Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/main.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 2002b70e18db..b68a41190eb0 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -25,7 +25,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2018.4"
+#define BATADV_SOURCE_VERSION "2019.0"
 #endif
 
 /* B.A.T.M.A.N. parameters */
-- 
cgit v1.2.3


From 01468225f305f3607868171b1abc2929a4501fad Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 21 Oct 2018 11:30:28 +0200
Subject: batman-adv: Drop unused lockdep include

The commit dee222c7b20c ("batman-adv: Move OGM rebroadcast stats to
orig_ifinfo") removed all used functionality of the include linux/lockdep.h
from batadv_iv_ogm.c.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_iv_ogm.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index d2227091029f..1d31ac84dec7 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -34,7 +34,6 @@
 #include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/list.h>
-#include <linux/lockdep.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <linux/pkt_sched.h>
-- 
cgit v1.2.3


From a5dac4da72f59f9565af747f0e4a2d943f902240 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 21 Oct 2018 11:30:29 +0200
Subject: batman-adv: Add includes for deprecation warning

The commit 00caf6a2b318 ("batman-adv: Mark debugfs functionality as
deprecated") introduced various messages to inform the user about the
deprecation of the debugfs based functionality. The messages also include
the context/task in which this problem was observed.

The datastructures and functions to access this information require special
headers. These should be included directly instead of depending on a more
complex and fragile include chain.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/debugfs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index 8b608a2e2653..d4a7702e48d8 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -19,6 +19,7 @@
 #include "debugfs.h"
 #include "main.h"
 
+#include <asm/current.h>
 #include <linux/dcache.h>
 #include <linux/debugfs.h>
 #include <linux/err.h>
@@ -27,6 +28,7 @@
 #include <linux/fs.h>
 #include <linux/netdevice.h>
 #include <linux/printk.h>
+#include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/stat.h>
 #include <linux/stddef.h>
-- 
cgit v1.2.3


From 95d8f85c911331fc4b4a6039295b3fe1673c73e7 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 21 Oct 2018 11:30:30 +0200
Subject: batman-adv: Improve includes for trace functionality

The batadv_dbg trace event uses different functionality and datastructures
which are not directly associated with the trace infrastructure. It should
not be expected that the trace headers indirectly provide them and instead
include the required headers directly.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/trace.c | 2 --
 net/batman-adv/trace.h | 6 ++++++
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/batman-adv/trace.c b/net/batman-adv/trace.c
index 3d57f9981f25..8e1024217cff 100644
--- a/net/batman-adv/trace.c
+++ b/net/batman-adv/trace.c
@@ -16,7 +16,5 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <linux/module.h>
-
 #define CREATE_TRACE_POINTS
 #include "trace.h"
diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h
index 3acda26a30ca..104784be94d7 100644
--- a/net/batman-adv/trace.h
+++ b/net/batman-adv/trace.h
@@ -21,7 +21,13 @@
 
 #include "main.h"
 
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/percpu.h>
+#include <linux/printk.h>
 #include <linux/tracepoint.h>
+#include <linux/types.h>
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM batadv
-- 
cgit v1.2.3


From 0dacc7fab623be97bda7aefe0d1d8d68cebb4218 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 21 Oct 2018 11:30:31 +0200
Subject: batman-adv: Allow to use BATMAN_ADV_DEBUG without BATMAN_ADV_DEBUGFS

The BATMAN_ADV_DEBUGFS portion of batman-adv is marked as deprecated. Thus
all required functionality should be available without it. The debug log
was already modified to also output via the kernel tracing function but
still retained its BATMAN_ADV_DEBUGFS functionality.

Separate the entry point for the debug log from the debugfs portions to
make it possible to build with BATMAN_ADV_DEBUG and without
BATMAN_ADV_DEBUGFS.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/Kconfig |  2 +-
 net/batman-adv/log.c   | 60 +++++++++++++++++++++++++++-----------------------
 2 files changed, 34 insertions(+), 28 deletions(-)

diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index f75816f58107..7b0e1fcddfa7 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -100,7 +100,7 @@ config BATMAN_ADV_DEBUGFS
 
 config BATMAN_ADV_DEBUG
 	bool "B.A.T.M.A.N. debugging"
-	depends on BATMAN_ADV_DEBUGFS
+	depends on BATMAN_ADV
 	help
 	  This is an option for use by developers; most people should
 	  say N here. This enables compilation of support for
diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c
index 6beb5f067810..02e55b78132f 100644
--- a/net/batman-adv/log.c
+++ b/net/batman-adv/log.c
@@ -43,6 +43,8 @@
 #include "debugfs.h"
 #include "trace.h"
 
+#ifdef CONFIG_BATMAN_ADV_DEBUGFS
+
 #define BATADV_LOG_BUFF_MASK (batadv_log_buff_len - 1)
 
 static const int batadv_log_buff_len = BATADV_LOG_BUF_LEN;
@@ -92,33 +94,6 @@ static int batadv_fdebug_log(struct batadv_priv_debug_log *debug_log,
 	return 0;
 }
 
-/**
- * batadv_debug_log() - Add debug log entry
- * @bat_priv: the bat priv with all the soft interface information
- * @fmt: format string
- *
- * Return: 0 on success or negative error number in case of failure
- */
-int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-
-	va_start(args, fmt);
-
-	vaf.fmt = fmt;
-	vaf.va = &args;
-
-	batadv_fdebug_log(bat_priv->debug_log, "[%10u] %pV",
-			  jiffies_to_msecs(jiffies), &vaf);
-
-	trace_batadv_dbg(bat_priv, &vaf);
-
-	va_end(args);
-
-	return 0;
-}
-
 static int batadv_log_open(struct inode *inode, struct file *file)
 {
 	if (!try_module_get(THIS_MODULE))
@@ -259,3 +234,34 @@ void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
 	kfree(bat_priv->debug_log);
 	bat_priv->debug_log = NULL;
 }
+
+#endif /* CONFIG_BATMAN_ADV_DEBUGFS */
+
+/**
+ * batadv_debug_log() - Add debug log entry
+ * @bat_priv: the bat priv with all the soft interface information
+ * @fmt: format string
+ *
+ * Return: 0 on success or negative error number in case of failure
+ */
+int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+#ifdef CONFIG_BATMAN_ADV_DEBUGFS
+	batadv_fdebug_log(bat_priv->debug_log, "[%10u] %pV",
+			  jiffies_to_msecs(jiffies), &vaf);
+#endif
+
+	trace_batadv_dbg(bat_priv, &vaf);
+
+	va_end(args);
+
+	return 0;
+}
-- 
cgit v1.2.3


From 694127c1dd494d3796e1627389a4cff7ee19e613 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 21 Oct 2018 11:30:32 +0200
Subject: batman-adv: Fix description for BATMAN_ADV_DEBUG

The debug messages of batman-adv are not printed to the kernel log at all
but can be stored (depending on the compile setting) in the tracing buffer
or the batadv specific log buffer. There is also no debug module parameter
but a batadv netdev specific log_level setting to enable/disable different
classes of debug messages at runtime.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/Kconfig | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index 7b0e1fcddfa7..082e96060bc2 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -104,8 +104,9 @@ config BATMAN_ADV_DEBUG
 	help
 	  This is an option for use by developers; most people should
 	  say N here. This enables compilation of support for
-	  outputting debugging information to the kernel log. The
-	  output is controlled via the module parameter debug.
+	  outputting debugging information to the debugfs log or tracing
+	  buffer. The output is controlled via the batadv netdev specific
+	  log_level setting.
 
 config BATMAN_ADV_TRACING
 	bool "B.A.T.M.A.N. tracing support"
-- 
cgit v1.2.3


From 9264c85c8b42d76862ae4ed307f4523e8bbab100 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 30 Oct 2018 22:01:23 +0100
Subject: batman-adv: Add inconsistent gateway netlink dump detection

The netlink dump functionality transfers a large number of entries from the
kernel to userspace. It is rather likely that the transfer has to
interrupted and later continued. During that time, it can happen that
either new entries are added or removed. The userspace could than either
receive some entries multiple times or miss entries.

Commit 670dc2833d14 ("netlink: advertise incomplete dumps") introduced a
mechanism to inform userspace about this problem. Userspace can then decide
whether it is necessary or not to retry dumping the information again.

The netlink dump functions have to be switched to exclusive locks to avoid
changes while the current message is prepared. And an external generation
sequence counter is introduced which tracks all modifications of the list.

Reported-by: Matthias Schiffer <mschiffer@universe-factory.net>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_iv_ogm.c     | 24 +++++++++++++++---------
 net/batman-adv/bat_v.c          | 26 +++++++++++++++++---------
 net/batman-adv/gateway_client.c |  3 +++
 net/batman-adv/main.c           |  2 ++
 net/batman-adv/types.h          |  5 ++++-
 5 files changed, 41 insertions(+), 19 deletions(-)

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 1d31ac84dec7..f97e566f0402 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -2584,13 +2584,14 @@ static void batadv_iv_gw_print(struct batadv_priv *bat_priv,
  * batadv_iv_gw_dump_entry() - Dump a gateway into a message
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @bat_priv: The bat priv with all the soft interface information
  * @gw_node: Gateway to be dumped
  *
  * Return: Error code, or 0 on success
  */
-static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
+static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid,
+				   struct netlink_callback *cb,
 				   struct batadv_priv *bat_priv,
 				   struct batadv_gw_node *gw_node)
 {
@@ -2610,13 +2611,16 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 
 	curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
 
-	hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family,
-			  NLM_F_MULTI, BATADV_CMD_GET_GATEWAYS);
+	hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq,
+			  &batadv_netlink_family, NLM_F_MULTI,
+			  BATADV_CMD_GET_GATEWAYS);
 	if (!hdr) {
 		ret = -ENOBUFS;
 		goto out;
 	}
 
+	genl_dump_check_consistent(cb, hdr);
+
 	ret = -EMSGSIZE;
 
 	if (curr_gw == gw_node)
@@ -2667,13 +2671,15 @@ static void batadv_iv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb,
 	int idx_skip = cb->args[0];
 	int idx = 0;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.gateway_list, list) {
+	spin_lock_bh(&bat_priv->gw.list_lock);
+	cb->seq = bat_priv->gw.generation << 1 | 1;
+
+	hlist_for_each_entry(gw_node, &bat_priv->gw.gateway_list, list) {
 		if (idx++ < idx_skip)
 			continue;
 
-		if (batadv_iv_gw_dump_entry(msg, portid, cb->nlh->nlmsg_seq,
-					    bat_priv, gw_node)) {
+		if (batadv_iv_gw_dump_entry(msg, portid, cb, bat_priv,
+					    gw_node)) {
 			idx_skip = idx - 1;
 			goto unlock;
 		}
@@ -2681,7 +2687,7 @@ static void batadv_iv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb,
 
 	idx_skip = idx;
 unlock:
-	rcu_read_unlock();
+	spin_unlock_bh(&bat_priv->gw.list_lock);
 
 	cb->args[0] = idx_skip;
 }
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 6baec4e68898..90e33f84d37a 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -27,11 +27,13 @@
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/kref.h>
+#include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
 #include <linux/seq_file.h>
+#include <linux/spinlock.h>
 #include <linux/stddef.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
@@ -915,13 +917,14 @@ static void batadv_v_gw_print(struct batadv_priv *bat_priv,
  * batadv_v_gw_dump_entry() - Dump a gateway into a message
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @bat_priv: The bat priv with all the soft interface information
  * @gw_node: Gateway to be dumped
  *
  * Return: Error code, or 0 on success
  */
-static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
+static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid,
+				  struct netlink_callback *cb,
 				  struct batadv_priv *bat_priv,
 				  struct batadv_gw_node *gw_node)
 {
@@ -941,13 +944,16 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 
 	curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
 
-	hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family,
-			  NLM_F_MULTI, BATADV_CMD_GET_GATEWAYS);
+	hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq,
+			  &batadv_netlink_family, NLM_F_MULTI,
+			  BATADV_CMD_GET_GATEWAYS);
 	if (!hdr) {
 		ret = -ENOBUFS;
 		goto out;
 	}
 
+	genl_dump_check_consistent(cb, hdr);
+
 	ret = -EMSGSIZE;
 
 	if (curr_gw == gw_node) {
@@ -1018,13 +1024,15 @@ static void batadv_v_gw_dump(struct sk_buff *msg, struct netlink_callback *cb,
 	int idx_skip = cb->args[0];
 	int idx = 0;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.gateway_list, list) {
+	spin_lock_bh(&bat_priv->gw.list_lock);
+	cb->seq = bat_priv->gw.generation << 1 | 1;
+
+	hlist_for_each_entry(gw_node, &bat_priv->gw.gateway_list, list) {
 		if (idx++ < idx_skip)
 			continue;
 
-		if (batadv_v_gw_dump_entry(msg, portid, cb->nlh->nlmsg_seq,
-					   bat_priv, gw_node)) {
+		if (batadv_v_gw_dump_entry(msg, portid, cb, bat_priv,
+					   gw_node)) {
 			idx_skip = idx - 1;
 			goto unlock;
 		}
@@ -1032,7 +1040,7 @@ static void batadv_v_gw_dump(struct sk_buff *msg, struct netlink_callback *cb,
 
 	idx_skip = idx;
 unlock:
-	rcu_read_unlock();
+	spin_unlock_bh(&bat_priv->gw.list_lock);
 
 	cb->args[0] = idx_skip;
 }
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 140c61a3f1ec..9d8e5eda2314 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -377,6 +377,7 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv,
 
 	kref_get(&gw_node->refcount);
 	hlist_add_head_rcu(&gw_node->list, &bat_priv->gw.gateway_list);
+	bat_priv->gw.generation++;
 
 	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 		   "Found new gateway %pM -> gw bandwidth: %u.%u/%u.%u MBit\n",
@@ -472,6 +473,7 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv,
 		if (!hlist_unhashed(&gw_node->list)) {
 			hlist_del_init_rcu(&gw_node->list);
 			batadv_gw_node_put(gw_node);
+			bat_priv->gw.generation++;
 		}
 		spin_unlock_bh(&bat_priv->gw.list_lock);
 
@@ -518,6 +520,7 @@ void batadv_gw_node_free(struct batadv_priv *bat_priv)
 				  &bat_priv->gw.gateway_list, list) {
 		hlist_del_init_rcu(&gw_node->list);
 		batadv_gw_node_put(gw_node);
+		bat_priv->gw.generation++;
 	}
 	spin_unlock_bh(&bat_priv->gw.list_lock);
 }
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 69c0d85bceb3..c75e47826949 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -186,6 +186,8 @@ int batadv_mesh_init(struct net_device *soft_iface)
 	INIT_HLIST_HEAD(&bat_priv->softif_vlan_list);
 	INIT_HLIST_HEAD(&bat_priv->tp_list);
 
+	bat_priv->gw.generation = 0;
+
 	ret = batadv_v_mesh_init(bat_priv);
 	if (ret < 0)
 		goto err;
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 45b5592de816..cbe17da36fcb 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1096,12 +1096,15 @@ struct batadv_priv_gw {
 	/** @gateway_list: list of available gateway nodes */
 	struct hlist_head gateway_list;
 
-	/** @list_lock: lock protecting gateway_list & curr_gw */
+	/** @list_lock: lock protecting gateway_list, curr_gw, generation */
 	spinlock_t list_lock;
 
 	/** @curr_gw: pointer to currently selected gateway node */
 	struct batadv_gw_node __rcu *curr_gw;
 
+	/** @generation: current (generation) sequence number */
+	unsigned int generation;
+
 	/**
 	 * @mode: gateway operation: off, client or server (see batadv_gw_modes)
 	 */
-- 
cgit v1.2.3


From fb69be697916a2d0a9badcdef7f20fcfad1233bc Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 30 Oct 2018 22:01:24 +0100
Subject: batman-adv: Add inconsistent hardif netlink dump detection

The netlink dump functionality transfers a large number of entries from the
kernel to userspace. It is rather likely that the transfer has to
interrupted and later continued. During that time, it can happen that
either new entries are added or removed. The userspace could than either
receive some entries multiple times or miss entries.

Commit 670dc2833d14 ("netlink: advertise incomplete dumps") introduced a
mechanism to inform userspace about this problem. Userspace can then decide
whether it is necessary or not to retry dumping the information again.

The netlink dump functions have to be switched to exclusive locks to avoid
changes while the current message is prepared. And an external generation
sequence counter is introduced which tracks all modifications of the list.

Reported-by: Matthias Schiffer <mschiffer@universe-factory.net>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/hard-interface.c |  3 +++
 net/batman-adv/main.c           |  1 +
 net/batman-adv/main.h           |  1 +
 net/batman-adv/netlink.c        | 24 ++++++++++++++----------
 4 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 781c5b6e6e8e..508f4416dfc9 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -951,6 +951,7 @@ batadv_hardif_add_interface(struct net_device *net_dev)
 	batadv_check_known_mac_addr(hard_iface->net_dev);
 	kref_get(&hard_iface->refcount);
 	list_add_tail_rcu(&hard_iface->list, &batadv_hardif_list);
+	batadv_hardif_generation++;
 
 	return hard_iface;
 
@@ -993,6 +994,7 @@ void batadv_hardif_remove_interfaces(void)
 	list_for_each_entry_safe(hard_iface, hard_iface_tmp,
 				 &batadv_hardif_list, list) {
 		list_del_rcu(&hard_iface->list);
+		batadv_hardif_generation++;
 		batadv_hardif_remove_interface(hard_iface);
 	}
 	rtnl_unlock();
@@ -1054,6 +1056,7 @@ static int batadv_hard_if_event(struct notifier_block *this,
 	case NETDEV_UNREGISTER:
 	case NETDEV_PRE_TYPE_CHANGE:
 		list_del_rcu(&hard_iface->list);
+		batadv_hardif_generation++;
 
 		batadv_hardif_remove_interface(hard_iface);
 		break;
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index c75e47826949..d1ed839fd32b 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -74,6 +74,7 @@
  * list traversals just rcu-locked
  */
 struct list_head batadv_hardif_list;
+unsigned int batadv_hardif_generation;
 static int (*batadv_rx_handler[256])(struct sk_buff *skb,
 				     struct batadv_hard_iface *recv_if);
 
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index b68a41190eb0..b572066325e4 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -247,6 +247,7 @@ static inline int batadv_print_vid(unsigned short vid)
 }
 
 extern struct list_head batadv_hardif_list;
+extern unsigned int batadv_hardif_generation;
 
 extern unsigned char batadv_broadcast_addr[];
 extern struct workqueue_struct *batadv_event_workqueue;
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 0d9459b69bdb..2dc3304cee54 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -29,11 +29,11 @@
 #include <linux/if_ether.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <linux/printk.h>
-#include <linux/rculist.h>
-#include <linux/rcupdate.h>
+#include <linux/rtnetlink.h>
 #include <linux/skbuff.h>
 #include <linux/stddef.h>
 #include <linux/types.h>
@@ -445,23 +445,27 @@ out:
  * batadv_netlink_dump_hardif_entry() - Dump one hard interface into a message
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @hard_iface: Hard interface to dump
  *
  * Return: error code, or 0 on success
  */
 static int
-batadv_netlink_dump_hardif_entry(struct sk_buff *msg, u32 portid, u32 seq,
+batadv_netlink_dump_hardif_entry(struct sk_buff *msg, u32 portid,
+				 struct netlink_callback *cb,
 				 struct batadv_hard_iface *hard_iface)
 {
 	struct net_device *net_dev = hard_iface->net_dev;
 	void *hdr;
 
-	hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, NLM_F_MULTI,
+	hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq,
+			  &batadv_netlink_family, NLM_F_MULTI,
 			  BATADV_CMD_GET_HARDIFS);
 	if (!hdr)
 		return -EMSGSIZE;
 
+	genl_dump_check_consistent(cb, hdr);
+
 	if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
 			net_dev->ifindex) ||
 	    nla_put_string(msg, BATADV_ATTR_HARD_IFNAME,
@@ -498,7 +502,6 @@ batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb)
 	struct batadv_hard_iface *hard_iface;
 	int ifindex;
 	int portid = NETLINK_CB(cb->skb).portid;
-	int seq = cb->nlh->nlmsg_seq;
 	int skip = cb->args[0];
 	int i = 0;
 
@@ -516,23 +519,24 @@ batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb)
 		return -ENODEV;
 	}
 
-	rcu_read_lock();
+	rtnl_lock();
+	cb->seq = batadv_hardif_generation << 1 | 1;
 
-	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
+	list_for_each_entry(hard_iface, &batadv_hardif_list, list) {
 		if (hard_iface->soft_iface != soft_iface)
 			continue;
 
 		if (i++ < skip)
 			continue;
 
-		if (batadv_netlink_dump_hardif_entry(msg, portid, seq,
+		if (batadv_netlink_dump_hardif_entry(msg, portid, cb,
 						     hard_iface)) {
 			i--;
 			break;
 		}
 	}
 
-	rcu_read_unlock();
+	rtnl_unlock();
 
 	dev_put(soft_iface);
 
-- 
cgit v1.2.3


From 05abd7bcc9cdbedf9deff27fe0766c70c4f2ae0d Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 30 Oct 2018 22:01:25 +0100
Subject: batman-adv: Store modification counter via hash helpers

Multiple datastructures use the hash helper functions to add and remove
entries from the simple hlist based hashes. These are often also dumped to
userspace via netlink and thus should have a generation sequence counter.

Reported-by: Matthias Schiffer <mschiffer@universe-factory.net>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/hash.c | 2 ++
 net/batman-adv/hash.h | 6 ++++++
 2 files changed, 8 insertions(+)

diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c
index 7b49e4001778..9194f4d891b1 100644
--- a/net/batman-adv/hash.c
+++ b/net/batman-adv/hash.c
@@ -32,6 +32,8 @@ static void batadv_hash_init(struct batadv_hashtable *hash)
 		INIT_HLIST_HEAD(&hash->table[i]);
 		spin_lock_init(&hash->list_locks[i]);
 	}
+
+	atomic_set(&hash->generation, 0);
 }
 
 /**
diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h
index 9490a7ca2ba6..0e36fa1c7c3e 100644
--- a/net/batman-adv/hash.h
+++ b/net/batman-adv/hash.h
@@ -21,6 +21,7 @@
 
 #include "main.h"
 
+#include <linux/atomic.h>
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rculist.h>
@@ -58,6 +59,9 @@ struct batadv_hashtable {
 
 	/** @size: size of hashtable */
 	u32 size;
+
+	/** @generation: current (generation) sequence number */
+	atomic_t generation;
 };
 
 /* allocates and clears the hash */
@@ -112,6 +116,7 @@ static inline int batadv_hash_add(struct batadv_hashtable *hash,
 
 	/* no duplicate found in list, add new element */
 	hlist_add_head_rcu(data_node, head);
+	atomic_inc(&hash->generation);
 
 	ret = 0;
 
@@ -154,6 +159,7 @@ static inline void *batadv_hash_remove(struct batadv_hashtable *hash,
 
 		data_save = node;
 		hlist_del_rcu(node);
+		atomic_inc(&hash->generation);
 		break;
 	}
 	spin_unlock_bh(&hash->list_locks[index]);
-- 
cgit v1.2.3


From b00d0e6a2cb143ccc2b75a930f0d5a46033ea7aa Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 30 Oct 2018 22:01:26 +0100
Subject: batman-adv: Add inconsistent backbone netlink dump detection

The netlink dump functionality transfers a large number of entries from the
kernel to userspace. It is rather likely that the transfer has to
interrupted and later continued. During that time, it can happen that
either new entries are added or removed. The userspace could than either
receive some entries multiple times or miss entries.

Commit 670dc2833d14 ("netlink: advertise incomplete dumps") introduced a
mechanism to inform userspace about this problem. Userspace can then decide
whether it is necessary or not to retry dumping the information again.

The netlink dump functions have to be switched to exclusive locks to avoid
changes while the current message is prepared. The already existing
generation sequence counter from the hash helper can be used for this
simple hash.

Reported-by: Matthias Schiffer <mschiffer@universe-factory.net>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bridge_loop_avoidance.c | 41 +++++++++++++++++++---------------
 1 file changed, 23 insertions(+), 18 deletions(-)

diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 5f1aeeded0e3..9f3747346d29 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -2325,14 +2325,15 @@ out:
  *  netlink socket
  * @msg: buffer for the message
  * @portid: netlink port
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @primary_if: primary interface
  * @backbone_gw: entry to dump
  *
  * Return: 0 or error code.
  */
 static int
-batadv_bla_backbone_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
+batadv_bla_backbone_dump_entry(struct sk_buff *msg, u32 portid,
+			       struct netlink_callback *cb,
 			       struct batadv_hard_iface *primary_if,
 			       struct batadv_bla_backbone_gw *backbone_gw)
 {
@@ -2343,13 +2344,16 @@ batadv_bla_backbone_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 	void *hdr;
 	int ret = -EINVAL;
 
-	hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family,
-			  NLM_F_MULTI, BATADV_CMD_GET_BLA_BACKBONE);
+	hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq,
+			  &batadv_netlink_family, NLM_F_MULTI,
+			  BATADV_CMD_GET_BLA_BACKBONE);
 	if (!hdr) {
 		ret = -ENOBUFS;
 		goto out;
 	}
 
+	genl_dump_check_consistent(cb, hdr);
+
 	is_own = batadv_compare_eth(backbone_gw->orig, primary_addr);
 
 	spin_lock_bh(&backbone_gw->crc_lock);
@@ -2386,28 +2390,33 @@ out:
  *  a netlink socket
  * @msg: buffer for the message
  * @portid: netlink port
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @primary_if: primary interface
- * @head: bucket to dump
+ * @hash: hash to dump
+ * @bucket: bucket index to dump
  * @idx_skip: How many entries to skip
  *
  * Return: always 0.
  */
 static int
-batadv_bla_backbone_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
+batadv_bla_backbone_dump_bucket(struct sk_buff *msg, u32 portid,
+				struct netlink_callback *cb,
 				struct batadv_hard_iface *primary_if,
-				struct hlist_head *head, int *idx_skip)
+				struct batadv_hashtable *hash,
+				unsigned int bucket, int *idx_skip)
 {
 	struct batadv_bla_backbone_gw *backbone_gw;
 	int idx = 0;
 	int ret = 0;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) {
+	spin_lock_bh(&hash->list_locks[bucket]);
+	cb->seq = atomic_read(&hash->generation) << 1 | 1;
+
+	hlist_for_each_entry(backbone_gw, &hash->table[bucket], hash_entry) {
 		if (idx++ < *idx_skip)
 			continue;
 
-		ret = batadv_bla_backbone_dump_entry(msg, portid, seq,
+		ret = batadv_bla_backbone_dump_entry(msg, portid, cb,
 						     primary_if, backbone_gw);
 		if (ret) {
 			*idx_skip = idx - 1;
@@ -2417,7 +2426,7 @@ batadv_bla_backbone_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
 
 	*idx_skip = 0;
 unlock:
-	rcu_read_unlock();
+	spin_unlock_bh(&hash->list_locks[bucket]);
 	return ret;
 }
 
@@ -2437,7 +2446,6 @@ int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	struct batadv_hashtable *hash;
 	struct batadv_priv *bat_priv;
 	int bucket = cb->args[0];
-	struct hlist_head *head;
 	int idx = cb->args[1];
 	int ifindex;
 	int ret = 0;
@@ -2463,11 +2471,8 @@ int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	}
 
 	while (bucket < hash->size) {
-		head = &hash->table[bucket];
-
-		if (batadv_bla_backbone_dump_bucket(msg, portid,
-						    cb->nlh->nlmsg_seq,
-						    primary_if, head, &idx))
+		if (batadv_bla_backbone_dump_bucket(msg, portid, cb, primary_if,
+						    hash, bucket, &idx))
 			break;
 		bucket++;
 	}
-- 
cgit v1.2.3


From 24d71b92321ab994585c816ede8c12857985d924 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 30 Oct 2018 22:01:27 +0100
Subject: batman-adv: Add inconsistent claim netlink dump detection

The netlink dump functionality transfers a large number of entries from the
kernel to userspace. It is rather likely that the transfer has to
interrupted and later continued. During that time, it can happen that
either new entries are added or removed. The userspace could than either
receive some entries multiple times or miss entries.

Commit 670dc2833d14 ("netlink: advertise incomplete dumps") introduced a
mechanism to inform userspace about this problem. Userspace can then decide
whether it is necessary or not to retry dumping the information again.

The netlink dump functions have to be switched to exclusive locks to avoid
changes while the current message is prepared. The already existing
generation sequence counter from the hash helper can be used for this
simple hash.

Reported-by: Matthias Schiffer <mschiffer@universe-factory.net>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bridge_loop_avoidance.c | 41 +++++++++++++++++++---------------
 1 file changed, 23 insertions(+), 18 deletions(-)

diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 9f3747346d29..5fdde2947802 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -2094,14 +2094,15 @@ out:
  * to a netlink socket
  * @msg: buffer for the message
  * @portid: netlink port
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @primary_if: primary interface
  * @claim: entry to dump
  *
  * Return: 0 or error code.
  */
 static int
-batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
+batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid,
+			    struct netlink_callback *cb,
 			    struct batadv_hard_iface *primary_if,
 			    struct batadv_bla_claim *claim)
 {
@@ -2111,13 +2112,16 @@ batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 	void *hdr;
 	int ret = -EINVAL;
 
-	hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family,
-			  NLM_F_MULTI, BATADV_CMD_GET_BLA_CLAIM);
+	hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq,
+			  &batadv_netlink_family, NLM_F_MULTI,
+			  BATADV_CMD_GET_BLA_CLAIM);
 	if (!hdr) {
 		ret = -ENOBUFS;
 		goto out;
 	}
 
+	genl_dump_check_consistent(cb, hdr);
+
 	is_own = batadv_compare_eth(claim->backbone_gw->orig,
 				    primary_addr);
 
@@ -2153,28 +2157,33 @@ out:
  * to a netlink socket
  * @msg: buffer for the message
  * @portid: netlink port
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @primary_if: primary interface
- * @head: bucket to dump
+ * @hash: hash to dump
+ * @bucket: bucket index to dump
  * @idx_skip: How many entries to skip
  *
  * Return: always 0.
  */
 static int
-batadv_bla_claim_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
+batadv_bla_claim_dump_bucket(struct sk_buff *msg, u32 portid,
+			     struct netlink_callback *cb,
 			     struct batadv_hard_iface *primary_if,
-			     struct hlist_head *head, int *idx_skip)
+			     struct batadv_hashtable *hash, unsigned int bucket,
+			     int *idx_skip)
 {
 	struct batadv_bla_claim *claim;
 	int idx = 0;
 	int ret = 0;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(claim, head, hash_entry) {
+	spin_lock_bh(&hash->list_locks[bucket]);
+	cb->seq = atomic_read(&hash->generation) << 1 | 1;
+
+	hlist_for_each_entry(claim, &hash->table[bucket], hash_entry) {
 		if (idx++ < *idx_skip)
 			continue;
 
-		ret = batadv_bla_claim_dump_entry(msg, portid, seq,
+		ret = batadv_bla_claim_dump_entry(msg, portid, cb,
 						  primary_if, claim);
 		if (ret) {
 			*idx_skip = idx - 1;
@@ -2184,7 +2193,7 @@ batadv_bla_claim_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
 
 	*idx_skip = 0;
 unlock:
-	rcu_read_unlock();
+	spin_unlock_bh(&hash->list_locks[bucket]);
 	return ret;
 }
 
@@ -2204,7 +2213,6 @@ int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	struct batadv_hashtable *hash;
 	struct batadv_priv *bat_priv;
 	int bucket = cb->args[0];
-	struct hlist_head *head;
 	int idx = cb->args[1];
 	int ifindex;
 	int ret = 0;
@@ -2230,11 +2238,8 @@ int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	}
 
 	while (bucket < hash->size) {
-		head = &hash->table[bucket];
-
-		if (batadv_bla_claim_dump_bucket(msg, portid,
-						 cb->nlh->nlmsg_seq,
-						 primary_if, head, &idx))
+		if (batadv_bla_claim_dump_bucket(msg, portid, cb, primary_if,
+						 hash, bucket, &idx))
 			break;
 		bucket++;
 	}
-- 
cgit v1.2.3


From 6f81652a4713e49afa4e1f6923c61e2e165afa08 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 30 Oct 2018 22:01:28 +0100
Subject: batman-adv: Add inconsistent dat netlink dump detection

The netlink dump functionality transfers a large number of entries from the
kernel to userspace. It is rather likely that the transfer has to
interrupted and later continued. During that time, it can happen that
either new entries are added or removed. The userspace could than either
receive some entries multiple times or miss entries.

Commit 670dc2833d14 ("netlink: advertise incomplete dumps") introduced a
mechanism to inform userspace about this problem. Userspace can then decide
whether it is necessary or not to retry dumping the information again.

The netlink dump functions have to be switched to exclusive locks to avoid
changes while the current message is prepared. The already existing
generation sequence counter from the hash helper can be used for this
simple hash.

Reported-by: Matthias Schiffer <mschiffer@universe-factory.net>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/distributed-arp-table.c | 42 +++++++++++++++++++---------------
 1 file changed, 23 insertions(+), 19 deletions(-)

diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index a60bacf7120b..b9ffe1826527 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -863,23 +863,27 @@ out:
  *  netlink socket
  * @msg: buffer for the message
  * @portid: netlink port
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @dat_entry: entry to dump
  *
  * Return: 0 or error code.
  */
 static int
-batadv_dat_cache_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
+batadv_dat_cache_dump_entry(struct sk_buff *msg, u32 portid,
+			    struct netlink_callback *cb,
 			    struct batadv_dat_entry *dat_entry)
 {
 	int msecs;
 	void *hdr;
 
-	hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family,
-			  NLM_F_MULTI, BATADV_CMD_GET_DAT_CACHE);
+	hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq,
+			  &batadv_netlink_family, NLM_F_MULTI,
+			  BATADV_CMD_GET_DAT_CACHE);
 	if (!hdr)
 		return -ENOBUFS;
 
+	genl_dump_check_consistent(cb, hdr);
+
 	msecs = jiffies_to_msecs(jiffies - dat_entry->last_update);
 
 	if (nla_put_in_addr(msg, BATADV_ATTR_DAT_CACHE_IP4ADDRESS,
@@ -901,27 +905,31 @@ batadv_dat_cache_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
  *  a netlink socket
  * @msg: buffer for the message
  * @portid: netlink port
- * @seq: Sequence number of netlink message
- * @head: bucket to dump
+ * @cb: Control block containing additional options
+ * @hash: hash to dump
+ * @bucket: bucket index to dump
  * @idx_skip: How many entries to skip
  *
  * Return: 0 or error code.
  */
 static int
-batadv_dat_cache_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
-			     struct hlist_head *head, int *idx_skip)
+batadv_dat_cache_dump_bucket(struct sk_buff *msg, u32 portid,
+			     struct netlink_callback *cb,
+			     struct batadv_hashtable *hash, unsigned int bucket,
+			     int *idx_skip)
 {
 	struct batadv_dat_entry *dat_entry;
 	int idx = 0;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(dat_entry, head, hash_entry) {
+	spin_lock_bh(&hash->list_locks[bucket]);
+	cb->seq = atomic_read(&hash->generation) << 1 | 1;
+
+	hlist_for_each_entry(dat_entry, &hash->table[bucket], hash_entry) {
 		if (idx < *idx_skip)
 			goto skip;
 
-		if (batadv_dat_cache_dump_entry(msg, portid, seq,
-						dat_entry)) {
-			rcu_read_unlock();
+		if (batadv_dat_cache_dump_entry(msg, portid, cb, dat_entry)) {
+			spin_unlock_bh(&hash->list_locks[bucket]);
 			*idx_skip = idx;
 
 			return -EMSGSIZE;
@@ -930,7 +938,7 @@ batadv_dat_cache_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
 skip:
 		idx++;
 	}
-	rcu_read_unlock();
+	spin_unlock_bh(&hash->list_locks[bucket]);
 
 	return 0;
 }
@@ -951,7 +959,6 @@ int batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	struct batadv_hashtable *hash;
 	struct batadv_priv *bat_priv;
 	int bucket = cb->args[0];
-	struct hlist_head *head;
 	int idx = cb->args[1];
 	int ifindex;
 	int ret = 0;
@@ -977,10 +984,7 @@ int batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	}
 
 	while (bucket < hash->size) {
-		head = &hash->table[bucket];
-
-		if (batadv_dat_cache_dump_bucket(msg, portid,
-						 cb->nlh->nlmsg_seq, head,
+		if (batadv_dat_cache_dump_bucket(msg, portid, cb, hash, bucket,
 						 &idx))
 			break;
 
-- 
cgit v1.2.3


From 6b7b40aad5cd2d7b59fbbd60537ce2eaea2f980d Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 30 Oct 2018 22:01:29 +0100
Subject: batman-adv: Add inconsistent local TT netlink dump detection

The netlink dump functionality transfers a large number of entries from the
kernel to userspace. It is rather likely that the transfer has to
interrupted and later continued. During that time, it can happen that
either new entries are added or removed. The userspace could than either
receive some entries multiple times or miss entries.

Commit 670dc2833d14 ("netlink: advertise incomplete dumps") introduced a
mechanism to inform userspace about this problem. Userspace can then decide
whether it is necessary or not to retry dumping the information again.

The netlink dump functions have to be switched to exclusive locks to avoid
changes while the current message is prepared. The already existing
generation sequence counter from the hash helper can be used for this
simple hash.

Reported-by: Matthias Schiffer <mschiffer@universe-factory.net>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/translation-table.c | 41 +++++++++++++++++++++-----------------
 1 file changed, 23 insertions(+), 18 deletions(-)

diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index d21624c44665..8dcd4968cde7 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -1145,14 +1145,15 @@ out:
  * batadv_tt_local_dump_entry() - Dump one TT local entry into a message
  * @msg :Netlink message to dump into
  * @portid: Port making netlink request
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @bat_priv: The bat priv with all the soft interface information
  * @common: tt local & tt global common data
  *
  * Return: Error code, or 0 on success
  */
 static int
-batadv_tt_local_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
+batadv_tt_local_dump_entry(struct sk_buff *msg, u32 portid,
+			   struct netlink_callback *cb,
 			   struct batadv_priv *bat_priv,
 			   struct batadv_tt_common_entry *common)
 {
@@ -1173,12 +1174,14 @@ batadv_tt_local_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 
 	batadv_softif_vlan_put(vlan);
 
-	hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family,
-			  NLM_F_MULTI,
+	hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq,
+			  &batadv_netlink_family,  NLM_F_MULTI,
 			  BATADV_CMD_GET_TRANSTABLE_LOCAL);
 	if (!hdr)
 		return -ENOBUFS;
 
+	genl_dump_check_consistent(cb, hdr);
+
 	if (nla_put(msg, BATADV_ATTR_TT_ADDRESS, ETH_ALEN, common->addr) ||
 	    nla_put_u32(msg, BATADV_ATTR_TT_CRC32, crc) ||
 	    nla_put_u16(msg, BATADV_ATTR_TT_VID, common->vid) ||
@@ -1201,34 +1204,39 @@ batadv_tt_local_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
  * batadv_tt_local_dump_bucket() - Dump one TT local bucket into a message
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @bat_priv: The bat priv with all the soft interface information
- * @head: Pointer to the list containing the local tt entries
+ * @hash: hash to dump
+ * @bucket: bucket index to dump
  * @idx_s: Number of entries to skip
  *
  * Return: Error code, or 0 on success
  */
 static int
-batadv_tt_local_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
+batadv_tt_local_dump_bucket(struct sk_buff *msg, u32 portid,
+			    struct netlink_callback *cb,
 			    struct batadv_priv *bat_priv,
-			    struct hlist_head *head, int *idx_s)
+			    struct batadv_hashtable *hash, unsigned int bucket,
+			    int *idx_s)
 {
 	struct batadv_tt_common_entry *common;
 	int idx = 0;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(common, head, hash_entry) {
+	spin_lock_bh(&hash->list_locks[bucket]);
+	cb->seq = atomic_read(&hash->generation) << 1 | 1;
+
+	hlist_for_each_entry(common, &hash->table[bucket], hash_entry) {
 		if (idx++ < *idx_s)
 			continue;
 
-		if (batadv_tt_local_dump_entry(msg, portid, seq, bat_priv,
+		if (batadv_tt_local_dump_entry(msg, portid, cb, bat_priv,
 					       common)) {
-			rcu_read_unlock();
+			spin_unlock_bh(&hash->list_locks[bucket]);
 			*idx_s = idx - 1;
 			return -EMSGSIZE;
 		}
 	}
-	rcu_read_unlock();
+	spin_unlock_bh(&hash->list_locks[bucket]);
 
 	*idx_s = 0;
 	return 0;
@@ -1248,7 +1256,6 @@ int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	struct batadv_priv *bat_priv;
 	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_hashtable *hash;
-	struct hlist_head *head;
 	int ret;
 	int ifindex;
 	int bucket = cb->args[0];
@@ -1276,10 +1283,8 @@ int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	hash = bat_priv->tt.local_hash;
 
 	while (bucket < hash->size) {
-		head = &hash->table[bucket];
-
-		if (batadv_tt_local_dump_bucket(msg, portid, cb->nlh->nlmsg_seq,
-						bat_priv, head, &idx))
+		if (batadv_tt_local_dump_bucket(msg, portid, cb, bat_priv,
+						hash, bucket, &idx))
 			break;
 
 		bucket++;
-- 
cgit v1.2.3


From d2d489b7d851785dd4833880d31d80bd70ffa6c3 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 30 Oct 2018 22:01:30 +0100
Subject: batman-adv: Add inconsistent multicast netlink dump detection

The netlink dump functionality transfers a large number of entries from the
kernel to userspace. It is rather likely that the transfer has to
interrupted and later continued. During that time, it can happen that
either new entries are added or removed. The userspace could than either
receive some entries multiple times or miss entries.

Commit 670dc2833d14 ("netlink: advertise incomplete dumps") introduced a
mechanism to inform userspace about this problem. Userspace can then decide
whether it is necessary or not to retry dumping the information again.

The netlink dump functions have to be switched to exclusive locks to avoid
changes while the current message is prepared. The already existing
generation sequence counter from the hash helper can be used for this
simple hash.

Reported-by: Matthias Schiffer <mschiffer@universe-factory.net>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/multicast.c | 51 +++++++++++++++++++++++++---------------------
 1 file changed, 28 insertions(+), 23 deletions(-)

diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 86725d792e15..69244e4598f5 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -1365,22 +1365,26 @@ int batadv_mcast_mesh_info_put(struct sk_buff *msg,
  *  to a netlink socket
  * @msg: buffer for the message
  * @portid: netlink port
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @orig_node: originator to dump the multicast flags of
  *
  * Return: 0 or error code.
  */
 static int
-batadv_mcast_flags_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
+batadv_mcast_flags_dump_entry(struct sk_buff *msg, u32 portid,
+			      struct netlink_callback *cb,
 			      struct batadv_orig_node *orig_node)
 {
 	void *hdr;
 
-	hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family,
-			  NLM_F_MULTI, BATADV_CMD_GET_MCAST_FLAGS);
+	hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq,
+			  &batadv_netlink_family, NLM_F_MULTI,
+			  BATADV_CMD_GET_MCAST_FLAGS);
 	if (!hdr)
 		return -ENOBUFS;
 
+	genl_dump_check_consistent(cb, hdr);
+
 	if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN,
 		    orig_node->orig)) {
 		genlmsg_cancel(msg, hdr);
@@ -1405,21 +1409,26 @@ batadv_mcast_flags_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
  *  table to a netlink socket
  * @msg: buffer for the message
  * @portid: netlink port
- * @seq: Sequence number of netlink message
- * @head: bucket to dump
+ * @cb: Control block containing additional options
+ * @hash: hash to dump
+ * @bucket: bucket index to dump
  * @idx_skip: How many entries to skip
  *
  * Return: 0 or error code.
  */
 static int
-batadv_mcast_flags_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
-			       struct hlist_head *head, long *idx_skip)
+batadv_mcast_flags_dump_bucket(struct sk_buff *msg, u32 portid,
+			       struct netlink_callback *cb,
+			       struct batadv_hashtable *hash,
+			       unsigned int bucket, long *idx_skip)
 {
 	struct batadv_orig_node *orig_node;
 	long idx = 0;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
+	spin_lock_bh(&hash->list_locks[bucket]);
+	cb->seq = atomic_read(&hash->generation) << 1 | 1;
+
+	hlist_for_each_entry(orig_node, &hash->table[bucket], hash_entry) {
 		if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST,
 			      &orig_node->capa_initialized))
 			continue;
@@ -1427,9 +1436,8 @@ batadv_mcast_flags_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
 		if (idx < *idx_skip)
 			goto skip;
 
-		if (batadv_mcast_flags_dump_entry(msg, portid, seq,
-						  orig_node)) {
-			rcu_read_unlock();
+		if (batadv_mcast_flags_dump_entry(msg, portid, cb, orig_node)) {
+			spin_unlock_bh(&hash->list_locks[bucket]);
 			*idx_skip = idx;
 
 			return -EMSGSIZE;
@@ -1438,7 +1446,7 @@ batadv_mcast_flags_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
 skip:
 		idx++;
 	}
-	rcu_read_unlock();
+	spin_unlock_bh(&hash->list_locks[bucket]);
 
 	return 0;
 }
@@ -1447,7 +1455,7 @@ skip:
  * __batadv_mcast_flags_dump() - dump multicast flags table to a netlink socket
  * @msg: buffer for the message
  * @portid: netlink port
- * @seq: Sequence number of netlink message
+ * @cb: Control block containing additional options
  * @bat_priv: the bat priv with all the soft interface information
  * @bucket: current bucket to dump
  * @idx: index in current bucket to the next entry to dump
@@ -1455,19 +1463,17 @@ skip:
  * Return: 0 or error code.
  */
 static int
-__batadv_mcast_flags_dump(struct sk_buff *msg, u32 portid, u32 seq,
+__batadv_mcast_flags_dump(struct sk_buff *msg, u32 portid,
+			  struct netlink_callback *cb,
 			  struct batadv_priv *bat_priv, long *bucket, long *idx)
 {
 	struct batadv_hashtable *hash = bat_priv->orig_hash;
 	long bucket_tmp = *bucket;
-	struct hlist_head *head;
 	long idx_tmp = *idx;
 
 	while (bucket_tmp < hash->size) {
-		head = &hash->table[bucket_tmp];
-
-		if (batadv_mcast_flags_dump_bucket(msg, portid, seq, head,
-						   &idx_tmp))
+		if (batadv_mcast_flags_dump_bucket(msg, portid, cb, hash,
+						   *bucket, &idx_tmp))
 			break;
 
 		bucket_tmp++;
@@ -1550,8 +1556,7 @@ int batadv_mcast_flags_dump(struct sk_buff *msg, struct netlink_callback *cb)
 		return ret;
 
 	bat_priv = netdev_priv(primary_if->soft_iface);
-	ret = __batadv_mcast_flags_dump(msg, portid, cb->nlh->nlmsg_seq,
-					bat_priv, bucket, idx);
+	ret = __batadv_mcast_flags_dump(msg, portid, cb, bat_priv, bucket, idx);
 
 	batadv_hardif_put(primary_if);
 	return ret;
-- 
cgit v1.2.3


From fb939135a6cf77a26831d23e6d22e4b9602cfce7 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 14 Oct 2018 17:16:14 +0200
Subject: batman-adv: Move CRC16 dependency to BATMAN_ADV_BLA

The commit ced72933a5e8 ("batman-adv: use CRC32C instead of CRC16 in TT
code") switched the translation table code from crc16 to crc32c. The
(optional) bridge loop avoidance code is the only user of this function.

batman-adv should only select CRC16 when it is actually using it.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index 082e96060bc2..d6b94559f888 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -22,7 +22,6 @@
 config BATMAN_ADV
 	tristate "B.A.T.M.A.N. Advanced Meshing Protocol"
 	depends on NET
-	select CRC16
 	select LIBCRC32C
 	help
           B.A.T.M.A.N. (better approach to mobile ad-hoc networking) is
@@ -48,6 +47,7 @@ config BATMAN_ADV_BATMAN_V
 config BATMAN_ADV_BLA
 	bool "Bridge Loop Avoidance"
 	depends on BATMAN_ADV && INET
+	select CRC16
 	default y
 	help
 	  This option enables BLA (Bridge Loop Avoidance), a mechanism
-- 
cgit v1.2.3


From 016fd285682952b943641c074d1cc0d02b3e6889 Mon Sep 17 00:00:00 2001
From: Linus Lüssing <linus.luessing@c0d3.blue>
Date: Tue, 6 Nov 2018 10:01:50 +0100
Subject: batman-adv: enable MCAST by default at compile time
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Thanks to rigorous testing in wireless community mesh networks several
issues with multicast entries in the translation table were found and
fixed in the last 1.5 years. Now we see the first larger networks
(a few hundred nodes) with a batman-adv version with multicast
optimizations enabled arising, with no TT / multicast optimization
related issues so far.

Therefore it seems safe to enable multicast optimizations by default.

Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index d6b94559f888..c386e6981416 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -82,6 +82,7 @@ config BATMAN_ADV_NC
 config BATMAN_ADV_MCAST
 	bool "Multicast optimisation"
 	depends on BATMAN_ADV && INET && !(BRIDGE=m && BATMAN_ADV=y)
+	default y
 	help
 	  This option enables the multicast optimisation which aims to
 	  reduce the air overhead while improving the reliability of
-- 
cgit v1.2.3


From 49de9c090f3cc747cb7f2dc79c175d7bd1d3f1e7 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 7 Nov 2018 00:32:49 +0900
Subject: netfilter: nf_flow_table: make nf_flow_table_iterate() static

nf_flow_table_iterate() is local function, make it static.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_flow_table.h | 4 ----
 net/netfilter/nf_flow_table_core.c    | 8 ++++----
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 77e2761d4f2f..7d5cda7ce32a 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -95,10 +95,6 @@ void flow_offload_free(struct flow_offload *flow);
 int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow);
 struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table,
 						     struct flow_offload_tuple *tuple);
-int nf_flow_table_iterate(struct nf_flowtable *flow_table,
-			  void (*iter)(struct flow_offload *flow, void *data),
-			  void *data);
-
 void nf_flow_table_cleanup(struct net_device *dev);
 
 int nf_flow_table_init(struct nf_flowtable *flow_table);
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index b7a4816add76..58bb006cf1b8 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -247,9 +247,10 @@ flow_offload_lookup(struct nf_flowtable *flow_table,
 }
 EXPORT_SYMBOL_GPL(flow_offload_lookup);
 
-int nf_flow_table_iterate(struct nf_flowtable *flow_table,
-			  void (*iter)(struct flow_offload *flow, void *data),
-			  void *data)
+static int
+nf_flow_table_iterate(struct nf_flowtable *flow_table,
+		      void (*iter)(struct flow_offload *flow, void *data),
+		      void *data)
 {
 	struct flow_offload_tuple_rhash *tuplehash;
 	struct rhashtable_iter hti;
@@ -279,7 +280,6 @@ int nf_flow_table_iterate(struct nf_flowtable *flow_table,
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(nf_flow_table_iterate);
 
 static inline bool nf_flow_has_expired(const struct flow_offload *flow)
 {
-- 
cgit v1.2.3


From b9660987692230b381b64c1f1e912febe142c390 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 7 Nov 2018 00:33:07 +0900
Subject: netfilter: nf_flow_table: simplify nf_flow_offload_gc_step()

nf_flow_offload_gc_step() and nf_flow_table_iterate() are very similar.
so that many duplicate code can be removed.
After this patch, nf_flow_offload_gc_step() is simple callback function of
nf_flow_table_iterate() like nf_flow_table_do_cleanup().

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_flow_table_core.c | 34 +++++++---------------------------
 1 file changed, 7 insertions(+), 27 deletions(-)

diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 58bb006cf1b8..fa0844e2a68d 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -286,33 +286,13 @@ static inline bool nf_flow_has_expired(const struct flow_offload *flow)
 	return (__s32)(flow->timeout - (u32)jiffies) <= 0;
 }
 
-static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table)
+static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
 {
-	struct flow_offload_tuple_rhash *tuplehash;
-	struct rhashtable_iter hti;
-	struct flow_offload *flow;
-
-	rhashtable_walk_enter(&flow_table->rhashtable, &hti);
-	rhashtable_walk_start(&hti);
+	struct nf_flowtable *flow_table = data;
 
-	while ((tuplehash = rhashtable_walk_next(&hti))) {
-		if (IS_ERR(tuplehash)) {
-			if (PTR_ERR(tuplehash) != -EAGAIN)
-				break;
-			continue;
-		}
-		if (tuplehash->tuple.dir)
-			continue;
-
-		flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);
-
-		if (nf_flow_has_expired(flow) ||
-		    (flow->flags & (FLOW_OFFLOAD_DYING |
-				    FLOW_OFFLOAD_TEARDOWN)))
-			flow_offload_del(flow_table, flow);
-	}
-	rhashtable_walk_stop(&hti);
-	rhashtable_walk_exit(&hti);
+	if (nf_flow_has_expired(flow) ||
+	    (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN)))
+		flow_offload_del(flow_table, flow);
 }
 
 static void nf_flow_offload_work_gc(struct work_struct *work)
@@ -320,7 +300,7 @@ static void nf_flow_offload_work_gc(struct work_struct *work)
 	struct nf_flowtable *flow_table;
 
 	flow_table = container_of(work, struct nf_flowtable, gc_work.work);
-	nf_flow_offload_gc_step(flow_table);
+	nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, flow_table);
 	queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
 }
 
@@ -504,7 +484,7 @@ void nf_flow_table_free(struct nf_flowtable *flow_table)
 	mutex_unlock(&flowtable_lock);
 	cancel_delayed_work_sync(&flow_table->gc_work);
 	nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
-	nf_flow_offload_gc_step(flow_table);
+	nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, flow_table);
 	rhashtable_destroy(&flow_table->rhashtable);
 }
 EXPORT_SYMBOL_GPL(nf_flow_table_free);
-- 
cgit v1.2.3


From 532ae2f10e6eab2ec66ecad805d57d3d70cea020 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 12 Nov 2018 18:27:15 +0800
Subject: sctp: do reuseport_select_sock in __sctp_rcv_lookup_endpoint

This is a part of sk_reuseport support for sctp, and it selects a
sock by the hashkey of lport, paddr and dport by default. It will
work until sk_reuseport support is added in sctp_get_port_local()
in the next patch.

v1->v2:
  - define lport as __be16 instead of __be32 as Marcelo pointed in
    __sctp_rcv_lookup_endpoint().

Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/input.c | 69 +++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 41 insertions(+), 28 deletions(-)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index 7ab08a5b36dc..00f995e37795 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -57,6 +57,7 @@
 #include <net/sctp/checksum.h>
 #include <net/net_namespace.h>
 #include <linux/rhashtable.h>
+#include <net/sock_reuseport.h>
 
 /* Forward declarations for internal helpers. */
 static int sctp_rcv_ootb(struct sk_buff *);
@@ -65,8 +66,10 @@ static struct sctp_association *__sctp_rcv_lookup(struct net *net,
 				      const union sctp_addr *paddr,
 				      const union sctp_addr *laddr,
 				      struct sctp_transport **transportp);
-static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(struct net *net,
-						const union sctp_addr *laddr);
+static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(
+					struct net *net, struct sk_buff *skb,
+					const union sctp_addr *laddr,
+					const union sctp_addr *daddr);
 static struct sctp_association *__sctp_lookup_association(
 					struct net *net,
 					const union sctp_addr *local,
@@ -171,7 +174,7 @@ int sctp_rcv(struct sk_buff *skb)
 	asoc = __sctp_rcv_lookup(net, skb, &src, &dest, &transport);
 
 	if (!asoc)
-		ep = __sctp_rcv_lookup_endpoint(net, &dest);
+		ep = __sctp_rcv_lookup_endpoint(net, skb, &dest, &src);
 
 	/* Retrieve the common input handling substructure. */
 	rcvr = asoc ? &asoc->base : &ep->base;
@@ -771,16 +774,35 @@ void sctp_unhash_endpoint(struct sctp_endpoint *ep)
 	local_bh_enable();
 }
 
+static inline __u32 sctp_hashfn(const struct net *net, __be16 lport,
+				const union sctp_addr *paddr, __u32 seed)
+{
+	__u32 addr;
+
+	if (paddr->sa.sa_family == AF_INET6)
+		addr = jhash(&paddr->v6.sin6_addr, 16, seed);
+	else
+		addr = (__force __u32)paddr->v4.sin_addr.s_addr;
+
+	return  jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 |
+			     (__force __u32)lport, net_hash_mix(net), seed);
+}
+
 /* Look up an endpoint. */
-static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(struct net *net,
-						const union sctp_addr *laddr)
+static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(
+					struct net *net, struct sk_buff *skb,
+					const union sctp_addr *laddr,
+					const union sctp_addr *paddr)
 {
 	struct sctp_hashbucket *head;
 	struct sctp_ep_common *epb;
 	struct sctp_endpoint *ep;
+	struct sock *sk;
+	__be16 lport;
 	int hash;
 
-	hash = sctp_ep_hashfn(net, ntohs(laddr->v4.sin_port));
+	lport = laddr->v4.sin_port;
+	hash = sctp_ep_hashfn(net, ntohs(lport));
 	head = &sctp_ep_hashtable[hash];
 	read_lock(&head->lock);
 	sctp_for_each_hentry(epb, &head->chain) {
@@ -792,6 +814,15 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(struct net *net,
 	ep = sctp_sk(net->sctp.ctl_sock)->ep;
 
 hit:
+	sk = ep->base.sk;
+	if (sk->sk_reuseport) {
+		__u32 phash = sctp_hashfn(net, lport, paddr, 0);
+
+		sk = reuseport_select_sock(sk, phash, skb,
+					   sizeof(struct sctphdr));
+		if (sk)
+			ep = sctp_sk(sk)->ep;
+	}
 	sctp_endpoint_hold(ep);
 	read_unlock(&head->lock);
 	return ep;
@@ -830,35 +861,17 @@ out:
 static inline __u32 sctp_hash_obj(const void *data, u32 len, u32 seed)
 {
 	const struct sctp_transport *t = data;
-	const union sctp_addr *paddr = &t->ipaddr;
-	const struct net *net = sock_net(t->asoc->base.sk);
-	__be16 lport = htons(t->asoc->base.bind_addr.port);
-	__u32 addr;
-
-	if (paddr->sa.sa_family == AF_INET6)
-		addr = jhash(&paddr->v6.sin6_addr, 16, seed);
-	else
-		addr = (__force __u32)paddr->v4.sin_addr.s_addr;
 
-	return  jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 |
-			     (__force __u32)lport, net_hash_mix(net), seed);
+	return sctp_hashfn(sock_net(t->asoc->base.sk),
+			   htons(t->asoc->base.bind_addr.port),
+			   &t->ipaddr, seed);
 }
 
 static inline __u32 sctp_hash_key(const void *data, u32 len, u32 seed)
 {
 	const struct sctp_hash_cmp_arg *x = data;
-	const union sctp_addr *paddr = x->paddr;
-	const struct net *net = x->net;
-	__be16 lport = x->lport;
-	__u32 addr;
-
-	if (paddr->sa.sa_family == AF_INET6)
-		addr = jhash(&paddr->v6.sin6_addr, 16, seed);
-	else
-		addr = (__force __u32)paddr->v4.sin_addr.s_addr;
 
-	return  jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 |
-			     (__force __u32)lport, net_hash_mix(net), seed);
+	return sctp_hashfn(x->net, x->lport, x->paddr, seed);
 }
 
 static const struct rhashtable_params sctp_hash_params = {
-- 
cgit v1.2.3


From 76c6d988aeb3c15d57ea0c245a3b5f27802c1fbe Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 12 Nov 2018 18:27:16 +0800
Subject: sctp: add sock_reuseport for the sock in __sctp_hash_endpoint

This is a part of sk_reuseport support for sctp. It defines a helper
sctp_bind_addrs_check() to check if the bind_addrs in two socks are
matched. It will add sock_reuseport if they are completely matched,
and return err if they are partly matched, and alloc sock_reuseport
if all socks are not matched at all.

It will work until sk_reuseport support is added in
sctp_get_port_local() in the next patch.

v1->v2:
  - use 'laddr->valid && laddr2->valid' check instead as Marcelo
    pointed in sctp_bind_addrs_check().

Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h    |  2 +-
 include/net/sctp/structs.h |  2 ++
 net/core/sock_reuseport.c  |  1 +
 net/sctp/bind_addr.c       | 28 ++++++++++++++++++++++
 net/sctp/input.c           | 60 +++++++++++++++++++++++++++++++++++++++-------
 net/sctp/socket.c          |  3 +--
 6 files changed, 85 insertions(+), 11 deletions(-)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 9a3b48a35e90..cdf2e80abc44 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -152,7 +152,7 @@ int sctp_primitive_RECONF(struct net *net, struct sctp_association *asoc,
  */
 int sctp_rcv(struct sk_buff *skb);
 int sctp_v4_err(struct sk_buff *skb, u32 info);
-void sctp_hash_endpoint(struct sctp_endpoint *);
+int sctp_hash_endpoint(struct sctp_endpoint *ep);
 void sctp_unhash_endpoint(struct sctp_endpoint *);
 struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *,
 			     struct sctphdr *, struct sctp_association **,
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index a11f93790476..15d017f33a46 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1190,6 +1190,8 @@ int sctp_bind_addr_conflict(struct sctp_bind_addr *, const union sctp_addr *,
 			 struct sctp_sock *, struct sctp_sock *);
 int sctp_bind_addr_state(const struct sctp_bind_addr *bp,
 			 const union sctp_addr *addr);
+int sctp_bind_addrs_check(struct sctp_sock *sp,
+			  struct sctp_sock *sp2, int cnt2);
 union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr	*bp,
 					const union sctp_addr	*addrs,
 					int			addrcnt,
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index ba5cba56f574..d8fe3e549373 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -187,6 +187,7 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
 		call_rcu(&old_reuse->rcu, reuseport_free_rcu);
 	return 0;
 }
+EXPORT_SYMBOL(reuseport_add_sock);
 
 void reuseport_detach_sock(struct sock *sk)
 {
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index 7df3704982f5..ebf28adba789 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -337,6 +337,34 @@ int sctp_bind_addr_match(struct sctp_bind_addr *bp,
 	return match;
 }
 
+int sctp_bind_addrs_check(struct sctp_sock *sp,
+			  struct sctp_sock *sp2, int cnt2)
+{
+	struct sctp_bind_addr *bp2 = &sp2->ep->base.bind_addr;
+	struct sctp_bind_addr *bp = &sp->ep->base.bind_addr;
+	struct sctp_sockaddr_entry *laddr, *laddr2;
+	bool exist = false;
+	int cnt = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
+		list_for_each_entry_rcu(laddr2, &bp2->address_list, list) {
+			if (sp->pf->af->cmp_addr(&laddr->a, &laddr2->a) &&
+			    laddr->valid && laddr2->valid) {
+				exist = true;
+				goto next;
+			}
+		}
+		cnt = 0;
+		break;
+next:
+		cnt++;
+	}
+	rcu_read_unlock();
+
+	return (cnt == cnt2) ? 0 : (exist ? -EEXIST : 1);
+}
+
 /* Does the address 'addr' conflict with any addresses in
  * the bp.
  */
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 00f995e37795..d7a649d240e5 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -724,43 +724,87 @@ discard:
 }
 
 /* Insert endpoint into the hash table.  */
-static void __sctp_hash_endpoint(struct sctp_endpoint *ep)
+static int __sctp_hash_endpoint(struct sctp_endpoint *ep)
 {
-	struct net *net = sock_net(ep->base.sk);
-	struct sctp_ep_common *epb;
+	struct sock *sk = ep->base.sk;
+	struct net *net = sock_net(sk);
 	struct sctp_hashbucket *head;
+	struct sctp_ep_common *epb;
 
 	epb = &ep->base;
-
 	epb->hashent = sctp_ep_hashfn(net, epb->bind_addr.port);
 	head = &sctp_ep_hashtable[epb->hashent];
 
+	if (sk->sk_reuseport) {
+		bool any = sctp_is_ep_boundall(sk);
+		struct sctp_ep_common *epb2;
+		struct list_head *list;
+		int cnt = 0, err = 1;
+
+		list_for_each(list, &ep->base.bind_addr.address_list)
+			cnt++;
+
+		sctp_for_each_hentry(epb2, &head->chain) {
+			struct sock *sk2 = epb2->sk;
+
+			if (!net_eq(sock_net(sk2), net) || sk2 == sk ||
+			    !uid_eq(sock_i_uid(sk2), sock_i_uid(sk)) ||
+			    !sk2->sk_reuseport)
+				continue;
+
+			err = sctp_bind_addrs_check(sctp_sk(sk2),
+						    sctp_sk(sk), cnt);
+			if (!err) {
+				err = reuseport_add_sock(sk, sk2, any);
+				if (err)
+					return err;
+				break;
+			} else if (err < 0) {
+				return err;
+			}
+		}
+
+		if (err) {
+			err = reuseport_alloc(sk, any);
+			if (err)
+				return err;
+		}
+	}
+
 	write_lock(&head->lock);
 	hlist_add_head(&epb->node, &head->chain);
 	write_unlock(&head->lock);
+	return 0;
 }
 
 /* Add an endpoint to the hash. Local BH-safe. */
-void sctp_hash_endpoint(struct sctp_endpoint *ep)
+int sctp_hash_endpoint(struct sctp_endpoint *ep)
 {
+	int err;
+
 	local_bh_disable();
-	__sctp_hash_endpoint(ep);
+	err = __sctp_hash_endpoint(ep);
 	local_bh_enable();
+
+	return err;
 }
 
 /* Remove endpoint from the hash table.  */
 static void __sctp_unhash_endpoint(struct sctp_endpoint *ep)
 {
-	struct net *net = sock_net(ep->base.sk);
+	struct sock *sk = ep->base.sk;
 	struct sctp_hashbucket *head;
 	struct sctp_ep_common *epb;
 
 	epb = &ep->base;
 
-	epb->hashent = sctp_ep_hashfn(net, epb->bind_addr.port);
+	epb->hashent = sctp_ep_hashfn(sock_net(sk), epb->bind_addr.port);
 
 	head = &sctp_ep_hashtable[epb->hashent];
 
+	if (rcu_access_pointer(sk->sk_reuseport_cb))
+		reuseport_detach_sock(sk);
+
 	write_lock(&head->lock);
 	hlist_del_init(&epb->node);
 	write_unlock(&head->lock);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 739f3e50120d..2e955f1dbe3f 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7852,8 +7852,7 @@ static int sctp_listen_start(struct sock *sk, int backlog)
 	}
 
 	sk->sk_max_ack_backlog = backlog;
-	sctp_hash_endpoint(ep);
-	return 0;
+	return sctp_hash_endpoint(ep);
 }
 
 /*
-- 
cgit v1.2.3


From 6ba84574026792ce33a40c7da721dea36d0f3973 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 12 Nov 2018 18:27:17 +0800
Subject: sctp: process sk_reuseport in sctp_get_port_local

When socks' sk_reuseport is set, the same port and address are allowed
to be bound into these socks who have the same uid.

Note that the difference from sk_reuse is that it allows multiple socks
to listen on the same port and address.

Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h |  4 +++-
 net/sctp/socket.c          | 46 +++++++++++++++++++++++++++++++++-------------
 2 files changed, 36 insertions(+), 14 deletions(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 15d017f33a46..af9d494120ba 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -96,7 +96,9 @@ struct sctp_stream;
 
 struct sctp_bind_bucket {
 	unsigned short	port;
-	unsigned short	fastreuse;
+	signed char	fastreuse;
+	signed char	fastreuseport;
+	kuid_t		fastuid;
 	struct hlist_node	node;
 	struct hlist_head	owner;
 	struct net	*net;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 2e955f1dbe3f..5299add6d7aa 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7644,8 +7644,10 @@ static struct sctp_bind_bucket *sctp_bucket_create(
 
 static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 {
-	bool reuse = (sk->sk_reuse || sctp_sk(sk)->reuse);
+	struct sctp_sock *sp = sctp_sk(sk);
+	bool reuse = (sk->sk_reuse || sp->reuse);
 	struct sctp_bind_hashbucket *head; /* hash list */
+	kuid_t uid = sock_i_uid(sk);
 	struct sctp_bind_bucket *pp;
 	unsigned short snum;
 	int ret;
@@ -7721,7 +7723,10 @@ pp_found:
 
 		pr_debug("%s: found a possible match\n", __func__);
 
-		if (pp->fastreuse && reuse && sk->sk_state != SCTP_SS_LISTENING)
+		if ((pp->fastreuse && reuse &&
+		     sk->sk_state != SCTP_SS_LISTENING) ||
+		    (pp->fastreuseport && sk->sk_reuseport &&
+		     uid_eq(pp->fastuid, uid)))
 			goto success;
 
 		/* Run through the list of sockets bound to the port
@@ -7735,16 +7740,18 @@ pp_found:
 		 * in an endpoint.
 		 */
 		sk_for_each_bound(sk2, &pp->owner) {
-			struct sctp_endpoint *ep2;
-			ep2 = sctp_sk(sk2)->ep;
+			struct sctp_sock *sp2 = sctp_sk(sk2);
+			struct sctp_endpoint *ep2 = sp2->ep;
 
 			if (sk == sk2 ||
-			    (reuse && (sk2->sk_reuse || sctp_sk(sk2)->reuse) &&
-			     sk2->sk_state != SCTP_SS_LISTENING))
+			    (reuse && (sk2->sk_reuse || sp2->reuse) &&
+			     sk2->sk_state != SCTP_SS_LISTENING) ||
+			    (sk->sk_reuseport && sk2->sk_reuseport &&
+			     uid_eq(uid, sock_i_uid(sk2))))
 				continue;
 
-			if (sctp_bind_addr_conflict(&ep2->base.bind_addr, addr,
-						 sctp_sk(sk2), sctp_sk(sk))) {
+			if (sctp_bind_addr_conflict(&ep2->base.bind_addr,
+						    addr, sp2, sp)) {
 				ret = (long)sk2;
 				goto fail_unlock;
 			}
@@ -7767,19 +7774,32 @@ pp_not_found:
 			pp->fastreuse = 1;
 		else
 			pp->fastreuse = 0;
-	} else if (pp->fastreuse &&
-		   (!reuse || sk->sk_state == SCTP_SS_LISTENING))
-		pp->fastreuse = 0;
+
+		if (sk->sk_reuseport) {
+			pp->fastreuseport = 1;
+			pp->fastuid = uid;
+		} else {
+			pp->fastreuseport = 0;
+		}
+	} else {
+		if (pp->fastreuse &&
+		    (!reuse || sk->sk_state == SCTP_SS_LISTENING))
+			pp->fastreuse = 0;
+
+		if (pp->fastreuseport &&
+		    (!sk->sk_reuseport || !uid_eq(pp->fastuid, uid)))
+			pp->fastreuseport = 0;
+	}
 
 	/* We are set, so fill up all the data in the hash table
 	 * entry, tie the socket list information with the rest of the
 	 * sockets FIXME: Blurry, NPI (ipg).
 	 */
 success:
-	if (!sctp_sk(sk)->bind_hash) {
+	if (!sp->bind_hash) {
 		inet_sk(sk)->inet_num = snum;
 		sk_add_bind_node(sk, &pp->owner);
-		sctp_sk(sk)->bind_hash = pp;
+		sp->bind_hash = pp;
 	}
 	ret = 0;
 
-- 
cgit v1.2.3


From 698114968a22f6c0c9f42e983ba033cc36bb7217 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Thu, 8 Nov 2018 21:10:08 +0200
Subject: net/mlx5: Release resource on error flow

Fix reference counting leakage when the event handler aborts due to an
unsupported event for the resource type.

Fixes: a14c2d4beee5 ("net/mlx5_core: Warn on unsupported events of QP/RQ/SQ")
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/qp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 91b8139a388d..690dc1dd9391 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -132,7 +132,7 @@ void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
 	if (!is_event_type_allowed((rsn >> MLX5_USER_INDEX_LEN), event_type)) {
 		mlx5_core_warn(dev, "event 0x%.2x is not allowed on resource 0x%.8x\n",
 			       event_type, rsn);
-		return;
+		goto out;
 	}
 
 	switch (common->res) {
@@ -150,7 +150,7 @@ void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
 	default:
 		mlx5_core_warn(dev, "invalid resource type for 0x%x\n", rsn);
 	}
-
+out:
 	mlx5_core_put_rsc(common);
 }
 
-- 
cgit v1.2.3


From 27e95603f4dfec470c6d26bea5174aa71b30e971 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Thu, 8 Nov 2018 21:10:10 +0200
Subject: net/mlx5: Add interface to hold and release core resources

Sometimes upper layers may want to prevent the destruction of a core
resource for a period of time while work on that resource is in
progress.  Add API to support this.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/qp.c | 16 ++++++++++++++++
 include/linux/mlx5/qp.h                      |  5 +++++
 2 files changed, 21 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 690dc1dd9391..cba4a435043a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -670,3 +670,19 @@ int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
 }
 EXPORT_SYMBOL_GPL(mlx5_core_query_q_counter);
+
+struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
+						int res_num,
+						enum mlx5_res_type res_type)
+{
+	u32 rsn = res_num | (res_type << MLX5_USER_INDEX_LEN);
+
+	return mlx5_get_rsc(dev, rsn);
+}
+EXPORT_SYMBOL_GPL(mlx5_core_res_hold);
+
+void mlx5_core_res_put(struct mlx5_core_rsc_common *res)
+{
+	mlx5_core_put_rsc(res);
+}
+EXPORT_SYMBOL_GPL(mlx5_core_res_put);
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index fbe322c966bc..b26ea9077384 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -596,6 +596,11 @@ int mlx5_core_dealloc_q_counter(struct mlx5_core_dev *dev, u16 counter_id);
 int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id,
 			      int reset, void *out, int out_size);
 
+struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
+						int res_num,
+						enum mlx5_res_type res_type);
+void mlx5_core_res_put(struct mlx5_core_rsc_common *res);
+
 static inline const char *mlx5_qp_type_str(int type)
 {
 	switch (type) {
-- 
cgit v1.2.3


From c99fefea2cc907c98e7f39b3571bb697c8d42106 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Thu, 8 Nov 2018 21:10:11 +0200
Subject: net/mlx5: Enumerate page fault types

Give meaningful names to type of WQE page faults.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 include/linux/mlx5/device.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index b4c0457fbebd..e326524bafcc 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -212,6 +212,13 @@ enum {
 	MLX5_PFAULT_SUBTYPE_RDMA = 1,
 };
 
+enum wqe_page_fault_type {
+	MLX5_WQE_PF_TYPE_RMP = 0,
+	MLX5_WQE_PF_TYPE_REQ_SEND_OR_WRITE = 1,
+	MLX5_WQE_PF_TYPE_RESP = 2,
+	MLX5_WQE_PF_TYPE_REQ_READ_OR_ATOMIC = 3,
+};
+
 enum {
 	MLX5_PERM_LOCAL_READ	= 1 << 2,
 	MLX5_PERM_LOCAL_WRITE	= 1 << 3,
-- 
cgit v1.2.3


From 032080ab43ac02cf7446b3954ace7ccce1abcad6 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Thu, 8 Nov 2018 21:10:12 +0200
Subject: IB/mlx5: Lock QP during page fault handling

When page fault event for a WQE arrives, the event data contains the
resource (e.g. QP) number which will later be used by the page fault
handler to retrieve the resource. Meanwhile, another context can destroy
the resource and cause use-after-free. To avoid that, take a reference on the
resource when handler starts and release it when it ends.

Page fault events for RDMA operations don't need to be protected because
the driver doesn't need to access the QP in the page fault handler.

Fixes: d9aaed838765 ("{net,IB}/mlx5: Refactor page fault handling")
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/odp.c | 46 ++++++++++++++++++++++++++++++++--------
 1 file changed, 37 insertions(+), 9 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index b04eb6775326..abce55b8b9ba 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -1016,16 +1016,31 @@ invalid_transport_or_opcode:
 	return 0;
 }
 
-static struct mlx5_ib_qp *mlx5_ib_odp_find_qp(struct mlx5_ib_dev *dev,
-					      u32 wq_num)
+static inline struct mlx5_core_rsc_common *odp_get_rsc(struct mlx5_ib_dev *dev,
+						       u32 wq_num, int pf_type)
 {
-	struct mlx5_core_qp *mqp = __mlx5_qp_lookup(dev->mdev, wq_num);
+	enum mlx5_res_type res_type;
 
-	if (!mqp) {
-		mlx5_ib_err(dev, "QPN 0x%6x not found\n", wq_num);
+	switch (pf_type) {
+	case MLX5_WQE_PF_TYPE_RMP:
+		res_type = MLX5_RES_SRQ;
+		break;
+	case MLX5_WQE_PF_TYPE_REQ_SEND_OR_WRITE:
+	case MLX5_WQE_PF_TYPE_RESP:
+	case MLX5_WQE_PF_TYPE_REQ_READ_OR_ATOMIC:
+		res_type = MLX5_RES_QP;
+		break;
+	default:
 		return NULL;
 	}
 
+	return mlx5_core_res_hold(dev->mdev, wq_num, res_type);
+}
+
+static inline struct mlx5_ib_qp *res_to_qp(struct mlx5_core_rsc_common *res)
+{
+	struct mlx5_core_qp *mqp = (struct mlx5_core_qp *)res;
+
 	return to_mibqp(mqp);
 }
 
@@ -1039,18 +1054,30 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_dev *dev,
 	int resume_with_error = 1;
 	u16 wqe_index = pfault->wqe.wqe_index;
 	int requestor = pfault->type & MLX5_PFAULT_REQUESTOR;
+	struct mlx5_core_rsc_common *res;
 	struct mlx5_ib_qp *qp;
 
+	res = odp_get_rsc(dev, pfault->wqe.wq_num, pfault->type);
+	if (!res) {
+		mlx5_ib_dbg(dev, "wqe page fault for missing resource %d\n", pfault->wqe.wq_num);
+		return;
+	}
+
+	switch (res->res) {
+	case MLX5_RES_QP:
+		qp = res_to_qp(res);
+		break;
+	default:
+		mlx5_ib_err(dev, "wqe page fault for unsupported type %d\n", pfault->type);
+		goto resolve_page_fault;
+	}
+
 	buffer = (char *)__get_free_page(GFP_KERNEL);
 	if (!buffer) {
 		mlx5_ib_err(dev, "Error allocating memory for IO page fault handling.\n");
 		goto resolve_page_fault;
 	}
 
-	qp = mlx5_ib_odp_find_qp(dev, pfault->wqe.wq_num);
-	if (!qp)
-		goto resolve_page_fault;
-
 	ret = mlx5_ib_read_user_wqe(qp, requestor, wqe_index, buffer,
 				    PAGE_SIZE, &qp->trans_qp.base);
 	if (ret < 0) {
@@ -1090,6 +1117,7 @@ resolve_page_fault:
 	mlx5_ib_dbg(dev, "PAGE FAULT completed. QP 0x%x resume_with_error=%d, type: 0x%x\n",
 		    pfault->wqe.wq_num, resume_with_error,
 		    pfault->type);
+	mlx5_core_res_put(res);
 	free_page((unsigned long)buffer);
 }
 
-- 
cgit v1.2.3


From ef90c5e9757d5abc80b947cbcaacc43d1e916488 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Thu, 8 Nov 2018 21:10:13 +0200
Subject: net/mlx5: Return success for PAGE_FAULT_RESUME in internal error
 state

When the device is in internal error state, command interface isn't
accessible and the driver decides which commands to fail and which to
pass.
Move the PAGE_FAULT_RESUME command to the pass list in order to avoid
redundant failure messages.

Fixes: 89d44f0a6c73 ("net/mlx5_core: Add pci error handlers to mlx5_core driver")
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index a5a0823e5ada..7b18aff955f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -313,6 +313,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_FPGA_DESTROY_QP:
 	case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT:
 	case MLX5_CMD_OP_DEALLOC_MEMIC:
+	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -326,7 +327,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_CREATE_MKEY:
 	case MLX5_CMD_OP_QUERY_MKEY:
 	case MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS:
-	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
 	case MLX5_CMD_OP_CREATE_EQ:
 	case MLX5_CMD_OP_QUERY_EQ:
 	case MLX5_CMD_OP_GEN_EQE:
-- 
cgit v1.2.3


From 90290db7669ba680b37b7006cbf6e5cee6cba779 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Thu, 8 Nov 2018 21:10:14 +0200
Subject: net/mlx5: Use multi threaded workqueue for page fault handling

Page fault events are processed in a workqueue context. Since each QP
can have up to two concurrent unrelated page-faults, one for requester
and one for responder, page-fault handling can be done in parallel.
Achieve this by changing the workqueue to be multi-threaded.
The number of threads is the same as the number of command interface
channels to avoid command interface bottlenecks.

In addition to multi-threads, change the workqueue flags to give it high
priority.

Stress benchmark shows that before this change 85% of page faults were
waiting in queue 8 seconds or more while after the change 98% of page
faults were waiting in queue 64 milliseconds or less. The number of threads
was chosen as the number of channels to the command interface.

Fixes: d9aaed838765 ("{net,IB}/mlx5: Refactor page fault handling")
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index c1e1a16a9b07..aeab0c4f60f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -356,8 +356,9 @@ static int init_pf_ctx(struct mlx5_eq_pagefault *pf_ctx, const char *name)
 	spin_lock_init(&pf_ctx->lock);
 	INIT_WORK(&pf_ctx->work, eq_pf_action);
 
-	pf_ctx->wq = alloc_ordered_workqueue(name,
-					     WQ_MEM_RECLAIM);
+	pf_ctx->wq = alloc_workqueue(name,
+				     WQ_HIGHPRI | WQ_UNBOUND | WQ_MEM_RECLAIM,
+				     MLX5_NUM_CMD_EQE);
 	if (!pf_ctx->wq)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From b02394aa75e3942bea8dac6efc7f1a179fbe011f Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Thu, 8 Nov 2018 21:10:17 +0200
Subject: IB/mlx5: Improve ODP debugging messages

Add and modify debug messages to ODP related error flows.
In that context, return code EAGAIN is considered less severe and print
level for it is set debug instead of warn.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/umem_odp.c | 14 ++++++++++++--
 drivers/infiniband/hw/mlx5/odp.c   |  4 ++--
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 2b4c5e7dd5a1..e334480b56bf 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -655,8 +655,13 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 				flags, local_page_list, NULL, NULL);
 		up_read(&owning_mm->mmap_sem);
 
-		if (npages < 0)
+		if (npages < 0) {
+			if (npages != -EAGAIN)
+				pr_warn("fail to get %zu user pages with error %d\n", gup_num_pages, npages);
+			else
+				pr_debug("fail to get %zu user pages with error %d\n", gup_num_pages, npages);
 			break;
+		}
 
 		bcnt -= min_t(size_t, npages << PAGE_SHIFT, bcnt);
 		mutex_lock(&umem_odp->umem_mutex);
@@ -674,8 +679,13 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 			ret = ib_umem_odp_map_dma_single_page(
 					umem_odp, k, local_page_list[j],
 					access_mask, current_seq);
-			if (ret < 0)
+			if (ret < 0) {
+				if (ret != -EAGAIN)
+					pr_warn("ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
+				else
+					pr_debug("ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
 				break;
+			}
 
 			p = page_to_phys(local_page_list[j]);
 			k++;
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index abce55b8b9ba..7d784b40e017 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -607,8 +607,8 @@ out:
 			if (!wait_for_completion_timeout(
 					&odp->notifier_completion,
 					timeout)) {
-				mlx5_ib_warn(dev, "timeout waiting for mmu notifier. seq %d against %d\n",
-					     current_seq, odp->notifiers_seq);
+				mlx5_ib_warn(dev, "timeout waiting for mmu notifier. seq %d against %d. notifiers_count=%d\n",
+					     current_seq, odp->notifiers_seq, odp->notifiers_count);
 			}
 		} else {
 			/* The MR is being killed, kill the QP as well. */
-- 
cgit v1.2.3


From 3e536cff34244959c81575733c9ca60633f74e1b Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 12 Nov 2018 23:45:56 +0000
Subject: net: phy: check if advertising is zero using linkmode_empty

A recent change modified variable advertising from a u32 to a link mode
array and left the u32 zero comparison, so essential we now have an array
being compared to null which is not the intention. Fix this by using the
call to linkmode_empty to check if advertising is all zero.

Detected by CoverityScan, CID#1475424 ("Array compared against 0")

Fixes: 3c1bcc8614db ("net: ethernet: Convert phydev advertize and supported from u32 to link mode")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index d73873334e47..376a0d8a2b61 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -328,7 +328,7 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev,
 	if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE)
 		return -EINVAL;
 
-	if (autoneg == AUTONEG_ENABLE && advertising == 0)
+	if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising))
 		return -EINVAL;
 
 	if (autoneg == AUTONEG_DISABLE &&
-- 
cgit v1.2.3


From 807bc98d31097bfe22fbf8236413db5490932456 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 26 Oct 2018 10:41:00 -0700
Subject: ice: Fix debug print in ice_tx_timeout

Currently the debug print in ice_tx_timeout is printing useless and
duplicate values. First, head is being assigned to tx_ring->next_to_clean
and we are printing both of those values, but naming them HWB and NTC
respectively. Also, reading tail always returns 0 so remove that as well.

Instead of assigning the SW head (NTC) read to head, use the actual head
register and change the debug print to note that this is HW_HEAD. Also
reduce the scope of a couple variables.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_hw_autogen.h |  3 +++
 drivers/net/ethernet/intel/ice/ice_main.c       | 15 +++++++++------
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 596b9fb1c510..5507928c8fbe 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -7,6 +7,9 @@
 #define _ICE_HW_AUTOGEN_H_
 
 #define QTX_COMM_DBELL(_DBQM)			(0x002C0000 + ((_DBQM) * 4))
+#define QTX_COMM_HEAD(_DBQM)			(0x000E0000 + ((_DBQM) * 4))
+#define QTX_COMM_HEAD_HEAD_S			0
+#define QTX_COMM_HEAD_HEAD_M			ICE_M(0x1FFF, 0)
 #define PF_FW_ARQBAH				0x00080180
 #define PF_FW_ARQBAL				0x00080080
 #define PF_FW_ARQH				0x00080380
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 333312a1d595..8584061e1bc6 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3691,8 +3691,8 @@ static void ice_tx_timeout(struct net_device *netdev)
 	struct ice_ring *tx_ring = NULL;
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
-	u32 head, val = 0, i;
 	int hung_queue = -1;
+	u32 i;
 
 	pf->tx_timeout_count++;
 
@@ -3736,17 +3736,20 @@ static void ice_tx_timeout(struct net_device *netdev)
 		return;
 
 	if (tx_ring) {
-		head = tx_ring->next_to_clean;
+		struct ice_hw *hw = &pf->hw;
+		u32 head, val = 0;
+
+		head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[hung_queue])) &
+			QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S;
 		/* Read interrupt register */
 		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-			val = rd32(&pf->hw,
+			val = rd32(hw,
 				   GLINT_DYN_CTL(tx_ring->q_vector->v_idx +
 					tx_ring->vsi->hw_base_vector));
 
-		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n",
+		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
 			    vsi->vsi_num, hung_queue, tx_ring->next_to_clean,
-			    head, tx_ring->next_to_use,
-			    readl(tx_ring->tail), val);
+			    head, tx_ring->next_to_use, val);
 	}
 
 	pf->tx_timeout_last_recovery = jiffies;
-- 
cgit v1.2.3


From b354e98f49ce84b969e2c0e2bb44d026ea3c4900 Mon Sep 17 00:00:00 2001
From: Tony Nguyen <anthony.l.nguyen@intel.com>
Date: Fri, 26 Oct 2018 10:41:01 -0700
Subject: ice: Check for q_vector when stopping rings

There is a gap in time between a VF reset, which sets the q_vector to
NULL, and the VF requesting mapping of the q_vectors. If
ice_vsi_stop_tx_rings() is called during this time, a NULL pointer
dereference is encountered. Add a check in ice_vsi_stop_tx_rings()
to ensure the q_vector is set to avoid this situation from occurring.

Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 1041fa2a7767..11d0ab185dd2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1908,7 +1908,8 @@ int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 	ice_for_each_txq(vsi, i) {
 		u16 v_idx;
 
-		if (!vsi->tx_rings || !vsi->tx_rings[i]) {
+		if (!vsi->tx_rings || !vsi->tx_rings[i] ||
+		    !vsi->tx_rings[i]->q_vector) {
 			err = -EINVAL;
 			goto err_out;
 		}
-- 
cgit v1.2.3


From 10e03a22de45699b6208592b85437d87a4741b9b Mon Sep 17 00:00:00 2001
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Date: Fri, 26 Oct 2018 10:41:02 -0700
Subject: ice: Remove node before releasing VSI

Before releasing the VSI, remove the VSI scheduler node. If not,
the node is left in the scheduler tree and, on subsequent load, the
scheduler tree contains the node so it does not set it in vsi_ctx.
This, later, causes the node to not be found in ice_sched_get_free_qparent
which leads to a "Failed to set LAN Tx queue context, error: -1".

To remove the scheduler node, this patch introduces ice_rm_vsi_lan_cfg
and related helpers.

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c   |   1 +
 drivers/net/ethernet/intel/ice/ice_sched.c | 108 ++++++++++++++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_sched.h |   2 +
 3 files changed, 110 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 11d0ab185dd2..1efd760debc2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2492,6 +2492,7 @@ int ice_vsi_release(struct ice_vsi *vsi)
 	}
 
 	ice_remove_vsi_fltr(&pf->hw, vsi->idx);
+	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	ice_vsi_delete(vsi);
 	ice_vsi_free_q_vectors(vsi);
 	ice_vsi_clear_rings(vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 7cc8aa18a22b..7e807b0e7514 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -1527,7 +1527,7 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 }
 
 /**
- * ice_sched_cfg_vsi - configure the new/exisiting VSI
+ * ice_sched_cfg_vsi - configure the new/existing VSI
  * @pi: port information structure
  * @vsi_handle: software VSI handle
  * @tc: TC number
@@ -1605,3 +1605,109 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
 
 	return status;
 }
+
+/**
+ * ice_sched_rm_agg_vsi_entry - remove agg related VSI info entry
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ *
+ * This function removes single aggregator VSI info entry from
+ * aggregator list.
+ */
+static void
+ice_sched_rm_agg_vsi_info(struct ice_port_info *pi, u16 vsi_handle)
+{
+	struct ice_sched_agg_info *agg_info;
+	struct ice_sched_agg_info *atmp;
+
+	list_for_each_entry_safe(agg_info, atmp, &pi->agg_list, list_entry) {
+		struct ice_sched_agg_vsi_info *agg_vsi_info;
+		struct ice_sched_agg_vsi_info *vtmp;
+
+		list_for_each_entry_safe(agg_vsi_info, vtmp,
+					 &agg_info->agg_vsi_list, list_entry)
+			if (agg_vsi_info->vsi_handle == vsi_handle) {
+				list_del(&agg_vsi_info->list_entry);
+				devm_kfree(ice_hw_to_dev(pi->hw),
+					   agg_vsi_info);
+				return;
+			}
+	}
+}
+
+/**
+ * ice_sched_rm_vsi_cfg - remove the VSI and its children nodes
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ * @owner: LAN or RDMA
+ *
+ * This function removes the VSI and its LAN or RDMA children nodes from the
+ * scheduler tree.
+ */
+static enum ice_status
+ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
+{
+	enum ice_status status = ICE_ERR_PARAM;
+	struct ice_vsi_ctx *vsi_ctx;
+	u8 i, j = 0;
+
+	if (!ice_is_vsi_valid(pi->hw, vsi_handle))
+		return status;
+	mutex_lock(&pi->sched_lock);
+	vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle);
+	if (!vsi_ctx)
+		goto exit_sched_rm_vsi_cfg;
+
+	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
+		struct ice_sched_node *vsi_node, *tc_node;
+
+		tc_node = ice_sched_get_tc_node(pi, i);
+		if (!tc_node)
+			continue;
+
+		vsi_node = ice_sched_get_vsi_node(pi->hw, tc_node, vsi_handle);
+		if (!vsi_node)
+			continue;
+
+		while (j < vsi_node->num_children) {
+			if (vsi_node->children[j]->owner == owner) {
+				ice_free_sched_node(pi, vsi_node->children[j]);
+
+				/* reset the counter again since the num
+				 * children will be updated after node removal
+				 */
+				j = 0;
+			} else {
+				j++;
+			}
+		}
+		/* remove the VSI if it has no children */
+		if (!vsi_node->num_children) {
+			ice_free_sched_node(pi, vsi_node);
+			vsi_ctx->sched.vsi_node[i] = NULL;
+
+			/* clean up agg related vsi info if any */
+			ice_sched_rm_agg_vsi_info(pi, vsi_handle);
+		}
+		if (owner == ICE_SCHED_NODE_OWNER_LAN)
+			vsi_ctx->sched.max_lanq[i] = 0;
+	}
+	status = 0;
+
+exit_sched_rm_vsi_cfg:
+	mutex_unlock(&pi->sched_lock);
+	return status;
+}
+
+/**
+ * ice_rm_vsi_lan_cfg - remove VSI and its LAN children nodes
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ *
+ * This function clears the VSI and its LAN children nodes from scheduler tree
+ * for all TCs.
+ */
+enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle)
+{
+	return ice_sched_rm_vsi_cfg(pi, vsi_handle, ICE_SCHED_NODE_OWNER_LAN);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h
index 5dc9cfa04c58..dc59fbac7dde 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.h
+++ b/drivers/net/ethernet/intel/ice/ice_sched.h
@@ -12,6 +12,7 @@
 struct ice_sched_agg_vsi_info {
 	struct list_head list_entry;
 	DECLARE_BITMAP(tc_bitmap, ICE_MAX_TRAFFIC_CLASS);
+	u16 vsi_handle;
 };
 
 struct ice_sched_agg_info {
@@ -39,4 +40,5 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 enum ice_status
 ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
 		  u8 owner, bool enable);
+enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle);
 #endif /* _ICE_SCHED_H_ */
-- 
cgit v1.2.3


From 995c90f2de819b020bdb0758ea4d486b0851e11a Mon Sep 17 00:00:00 2001
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Date: Fri, 26 Oct 2018 10:41:03 -0700
Subject: ice: Calculate guaranteed VSIs per function and use it

Currently we are setting the guar_num_vsi to equal to ICE_MAX_VSI
which is the device limit of 768. This is incorrect and could have
unintended consequences. To fix this use the valid_function's 8-bit
bitmap returned from discovering device capabilities to determine the
guar_num_vsi per function. guar_num_vsi value is then passed on to
pf->num_alloc_vsi.

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h            |  1 -
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h |  1 +
 drivers/net/ethernet/intel/ice/ice_common.c     | 31 +++++++++++++++++++++++--
 drivers/net/ethernet/intel/ice/ice_main.c       |  3 +--
 drivers/net/ethernet/intel/ice/ice_type.h       |  4 +++-
 5 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index b8548370f1c7..ba03cbd3638e 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -52,7 +52,6 @@ extern const char ice_drv_ver[];
 #define ICE_MBXQ_LEN		64
 #define ICE_MIN_MSIX		2
 #define ICE_NO_VSI		0xffff
-#define ICE_MAX_VSI_ALLOC	130
 #define ICE_MAX_TXQS		2048
 #define ICE_MAX_RXQS		2048
 #define ICE_VSI_MAP_CONTIG	0
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 6653555f55dd..602f02a0a2d1 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -87,6 +87,7 @@ struct ice_aqc_list_caps {
 /* Device/Function buffer entry, repeated per reported capability */
 struct ice_aqc_list_caps_elem {
 	__le16 cap;
+#define ICE_AQC_CAPS_VALID_FUNCTIONS			0x0005
 #define ICE_AQC_CAPS_SRIOV				0x0012
 #define ICE_AQC_CAPS_VF					0x0013
 #define ICE_AQC_CAPS_VSI				0x0017
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 554fd707a6d6..9de5a3aac77d 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1386,6 +1386,27 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res)
 	}
 }
 
+/**
+ * ice_get_guar_num_vsi - determine number of guar VSI for a PF
+ * @hw: pointer to the hw structure
+ *
+ * Determine the number of valid functions by going through the bitmap returned
+ * from parsing capabilities and use this to calculate the number of VSI per PF.
+ */
+static u32 ice_get_guar_num_vsi(struct ice_hw *hw)
+{
+	u8 funcs;
+
+#define ICE_CAPS_VALID_FUNCS_M	0xFF
+	funcs = hweight8(hw->dev_caps.common_cap.valid_functions &
+			 ICE_CAPS_VALID_FUNCS_M);
+
+	if (!funcs)
+		return 0;
+
+	return ICE_MAX_VSI / funcs;
+}
+
 /**
  * ice_parse_caps - parse function/device capabilities
  * @hw: pointer to the hw struct
@@ -1428,6 +1449,12 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 		u16 cap = le16_to_cpu(cap_resp->cap);
 
 		switch (cap) {
+		case ICE_AQC_CAPS_VALID_FUNCTIONS:
+			caps->valid_functions = number;
+			ice_debug(hw, ICE_DBG_INIT,
+				  "HW caps: Valid Functions = %d\n",
+				  caps->valid_functions);
+			break;
 		case ICE_AQC_CAPS_SRIOV:
 			caps->sr_iov_1_1 = (number == 1);
 			ice_debug(hw, ICE_DBG_INIT,
@@ -1457,10 +1484,10 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 					  "HW caps: Dev.VSI cnt = %d\n",
 					  dev_p->num_vsi_allocd_to_host);
 			} else if (func_p) {
-				func_p->guaranteed_num_vsi = number;
+				func_p->guar_num_vsi = ice_get_guar_num_vsi(hw);
 				ice_debug(hw, ICE_DBG_INIT,
 					  "HW caps: Func.VSI cnt = %d\n",
-					  func_p->guaranteed_num_vsi);
+					  number);
 			}
 			break;
 		case ICE_AQC_CAPS_RSS:
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 8584061e1bc6..ea79e5e1f589 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2091,8 +2091,7 @@ static int ice_probe(struct pci_dev *pdev,
 
 	ice_determine_q_usage(pf);
 
-	pf->num_alloc_vsi = min_t(u16, ICE_MAX_VSI_ALLOC,
-				  hw->func_caps.guaranteed_num_vsi);
+	pf->num_alloc_vsi = hw->func_caps.guar_num_vsi;
 	if (!pf->num_alloc_vsi) {
 		err = -EIO;
 		goto err_init_pf_unroll;
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index f4dbc81c1988..0ea428104215 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -124,6 +124,8 @@ struct ice_phy_info {
 
 /* Common HW capabilities for SW use */
 struct ice_hw_common_caps {
+	u32 valid_functions;
+
 	/* TX/RX queues */
 	u16 num_rxq;		/* Number/Total RX queues */
 	u16 rxq_first_id;	/* First queue ID for RX queues */
@@ -150,7 +152,7 @@ struct ice_hw_func_caps {
 	struct ice_hw_common_caps common_cap;
 	u32 num_allocd_vfs;		/* Number of allocated VFs */
 	u32 vf_base_id;			/* Logical ID of the first VF */
-	u32 guaranteed_num_vsi;
+	u32 guar_num_vsi;
 };
 
 /* Device wide capabilities */
-- 
cgit v1.2.3


From d09e2693b689cc82cd9bae0c4f19f5122708f83e Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Fri, 26 Oct 2018 10:41:04 -0700
Subject: ice: Avoid nested RTNL locking in ice_dis_vsi

ice_dis_vsi() performs an rtnl_lock() if it detects a netdev that is
running on the VSI. In cases where the RTNL lock has already been
acquired, a deadlock results. Add a boolean to pass to ice_dis_vsi to
tell it if the RTNL lock is already held.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index ea79e5e1f589..089b0f0b2e71 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3137,8 +3137,9 @@ static void ice_vsi_release_all(struct ice_pf *pf)
 /**
  * ice_dis_vsi - pause a VSI
  * @vsi: the VSI being paused
+ * @locked: is the rtnl_lock already held
  */
-static void ice_dis_vsi(struct ice_vsi *vsi)
+static void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
 {
 	if (test_bit(__ICE_DOWN, vsi->state))
 		return;
@@ -3147,9 +3148,13 @@ static void ice_dis_vsi(struct ice_vsi *vsi)
 
 	if (vsi->type == ICE_VSI_PF && vsi->netdev) {
 		if (netif_running(vsi->netdev)) {
-			rtnl_lock();
-			vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
-			rtnl_unlock();
+			if (!locked) {
+				rtnl_lock();
+				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+				rtnl_unlock();
+			} else {
+				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+			}
 		} else {
 			ice_vsi_close(vsi);
 		}
@@ -3188,7 +3193,7 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf)
 
 	ice_for_each_vsi(pf, v)
 		if (pf->vsi[v])
-			ice_dis_vsi(pf->vsi[v]);
+			ice_dis_vsi(pf->vsi[v], false);
 }
 
 /**
-- 
cgit v1.2.3


From 6263e811f4d4418660c20b36a08063c6d2c3fb9d Mon Sep 17 00:00:00 2001
From: Lev Faerman <lev.faerman@intel.com>
Date: Fri, 26 Oct 2018 10:41:05 -0700
Subject: ice: Fix NVM mask defines

Fixes bad masks that would break compilation when evaluated.

Signed-off-by: Lev Faerman <lev.faerman@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 602f02a0a2d1..4078070881ce 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1066,10 +1066,10 @@ struct ice_aqc_nvm {
 #define ICE_AQC_NVM_LAST_CMD		BIT(0)
 #define ICE_AQC_NVM_PCIR_REQ		BIT(0)	/* Used by NVM Update reply */
 #define ICE_AQC_NVM_PRESERVATION_S	1
-#define ICE_AQC_NVM_PRESERVATION_M	(3 << CSR_AQ_NVM_PRESERVATION_S)
-#define ICE_AQC_NVM_NO_PRESERVATION	(0 << CSR_AQ_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_PRESERVATION_M	(3 << ICE_AQC_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_NO_PRESERVATION	(0 << ICE_AQC_NVM_PRESERVATION_S)
 #define ICE_AQC_NVM_PRESERVE_ALL	BIT(1)
-#define ICE_AQC_NVM_PRESERVE_SELECTED	(3 << CSR_AQ_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_PRESERVE_SELECTED	(3 << ICE_AQC_NVM_PRESERVATION_S)
 #define ICE_AQC_NVM_FLASH_ONLY		BIT(7)
 	__le16 module_typeid;
 	__le16 length;
-- 
cgit v1.2.3


From 7b8ff0f9cc531ce4367827e335c8bf0488d245f8 Mon Sep 17 00:00:00 2001
From: Piotr Raczynski <piotr.raczynski@intel.com>
Date: Fri, 26 Oct 2018 11:44:33 -0700
Subject: ice: Increase Rx queue disable timeout

With much traffic coming into the port, Rx queue disable
procedure can take more time until all pending queue
requests on PCIe finish. Reuse ICE_Q_WAIT_MAX_RETRY macro
and increase the delay itself.

Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 1efd760debc2..f6e21363c8d6 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -174,15 +174,15 @@ static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena)
 {
 	int i;
 
-	for (i = 0; i < ICE_Q_WAIT_RETRY_LIMIT; i++) {
+	for (i = 0; i < ICE_Q_WAIT_MAX_RETRY; i++) {
 		u32 rx_reg = rd32(&pf->hw, QRX_CTRL(pf_q));
 
 		if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M))
 			break;
 
-		usleep_range(10, 20);
+		usleep_range(20, 40);
 	}
-	if (i >= ICE_Q_WAIT_RETRY_LIMIT)
+	if (i >= ICE_Q_WAIT_MAX_RETRY)
 		return -ETIMEDOUT;
 
 	return 0;
-- 
cgit v1.2.3


From 99fc1057b4d4e2a95c24b3b1ea4d6140eb2712a2 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 26 Oct 2018 11:44:34 -0700
Subject: ice: Call pci_disable_sriov before stopping queues for VF

Previous to this commit the driver was immediately stopping Tx/Rx
queues when doing the following "echo 0 > sriov_numvfs" and then it was
calling pci_disable_sriov if the VFs are not assigned. This was causing
the VIRTCHNL_OP_DISABLE_QUEUES to fail because it was trying to stop
the queues for a second time.

Fix this by calling pci_disable_sriov before stopping the Tx/Rx queues.
This allows the VIRTCHNL_OP_DISABLE_QUEUES to get processed before the
driver tries to stop the Rx/Tx queues in ice_free_vfs.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index e71065f9d391..20b94dee0036 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -215,6 +215,15 @@ void ice_free_vfs(struct ice_pf *pf)
 	while (test_and_set_bit(__ICE_VF_DIS, pf->state))
 		usleep_range(1000, 2000);
 
+	/* Disable IOV before freeing resources. This lets any VF drivers
+	 * running in the host get themselves cleaned up before we yank
+	 * the carpet out from underneath their feet.
+	 */
+	if (!pci_vfs_assigned(pf->pdev))
+		pci_disable_sriov(pf->pdev);
+	else
+		dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n");
+
 	/* Avoid wait time by stopping all VFs at the same time */
 	for (i = 0; i < pf->num_alloc_vfs; i++) {
 		if (!test_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states))
@@ -228,15 +237,6 @@ void ice_free_vfs(struct ice_pf *pf)
 		clear_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states);
 	}
 
-	/* Disable IOV before freeing resources. This lets any VF drivers
-	 * running in the host get themselves cleaned up before we yank
-	 * the carpet out from underneath their feet.
-	 */
-	if (!pci_vfs_assigned(pf->pdev))
-		pci_disable_sriov(pf->pdev);
-	else
-		dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n");
-
 	tmp = pf->num_alloc_vfs;
 	pf->num_vf_qps = 0;
 	pf->num_alloc_vfs = 0;
-- 
cgit v1.2.3


From c5a2a4a38856faed6fa6654746c838231289e8d6 Mon Sep 17 00:00:00 2001
From: Usha Ketineni <usha.k.ketineni@intel.com>
Date: Fri, 26 Oct 2018 11:44:35 -0700
Subject: ice: Fix to make VLAN priority tagged traffic to appear on all TCs

This patch includes below changes to resolve the issue of ETS bandwidth
shaping to work.

1. Allocation of Tx queues is accounted for based on the enabled TC's
   in ice_vsi_setup_q_map() and enabled the Tx queues on those TC's via
   ice_vsi_cfg_txqs()

2. Get the mapped netdev TC # for the user priority and set the priority
   to TC mapping for the VSI.

Signed-off-by: Usha Ketineni <usha.k.ketineni@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h       |   4 +-
 drivers/net/ethernet/intel/ice/ice_lib.c   | 121 +++++++++++++++++------------
 drivers/net/ethernet/intel/ice/ice_main.c  |   4 +-
 drivers/net/ethernet/intel/ice/ice_sched.c |   2 +-
 drivers/net/ethernet/intel/ice/ice_sched.h |   1 +
 5 files changed, 81 insertions(+), 51 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index ba03cbd3638e..7d8575d11786 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -112,7 +112,9 @@ extern const char ice_drv_ver[];
 
 struct ice_tc_info {
 	u16 qoffset;
-	u16 qcount;
+	u16 qcount_tx;
+	u16 qcount_rx;
+	u8 netdev_tc;
 };
 
 struct ice_tc_cfg {
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index f6e21363c8d6..597005f39919 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -774,11 +774,13 @@ static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt)
  */
 static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 {
-	u16 offset = 0, qmap = 0, numq_tc;
-	u16 pow = 0, max_rss = 0, qcount;
+	u16 offset = 0, qmap = 0, tx_count = 0;
 	u16 qcount_tx = vsi->alloc_txq;
 	u16 qcount_rx = vsi->alloc_rxq;
+	u16 tx_numq_tc, rx_numq_tc;
+	u16 pow = 0, max_rss = 0;
 	bool ena_tc0 = false;
+	u8 netdev_tc = 0;
 	int i;
 
 	/* at least TC0 should be enabled by default */
@@ -794,7 +796,12 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 		vsi->tc_cfg.ena_tc |= 1;
 	}
 
-	numq_tc = qcount_rx / vsi->tc_cfg.numtc;
+	rx_numq_tc = qcount_rx / vsi->tc_cfg.numtc;
+	if (!rx_numq_tc)
+		rx_numq_tc = 1;
+	tx_numq_tc = qcount_tx / vsi->tc_cfg.numtc;
+	if (!tx_numq_tc)
+		tx_numq_tc = 1;
 
 	/* TC mapping is a function of the number of Rx queues assigned to the
 	 * VSI for each traffic class and the offset of these queues.
@@ -808,7 +815,8 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 	 * Setup number and offset of Rx queues for all TCs for the VSI
 	 */
 
-	qcount = numq_tc;
+	qcount_rx = rx_numq_tc;
+
 	/* qcount will change if RSS is enabled */
 	if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) {
 		if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_VF) {
@@ -816,37 +824,41 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 				max_rss = ICE_MAX_LG_RSS_QS;
 			else
 				max_rss = ICE_MAX_SMALL_RSS_QS;
-			qcount = min_t(int, numq_tc, max_rss);
-			qcount = min_t(int, qcount, vsi->rss_size);
+			qcount_rx = min_t(int, rx_numq_tc, max_rss);
+			qcount_rx = min_t(int, qcount_rx, vsi->rss_size);
 		}
 	}
 
 	/* find the (rounded up) power-of-2 of qcount */
-	pow = order_base_2(qcount);
+	pow = order_base_2(qcount_rx);
 
 	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
 		if (!(vsi->tc_cfg.ena_tc & BIT(i))) {
 			/* TC is not enabled */
 			vsi->tc_cfg.tc_info[i].qoffset = 0;
-			vsi->tc_cfg.tc_info[i].qcount = 1;
+			vsi->tc_cfg.tc_info[i].qcount_rx = 1;
+			vsi->tc_cfg.tc_info[i].qcount_tx = 1;
+			vsi->tc_cfg.tc_info[i].netdev_tc = 0;
 			ctxt->info.tc_mapping[i] = 0;
 			continue;
 		}
 
 		/* TC is enabled */
 		vsi->tc_cfg.tc_info[i].qoffset = offset;
-		vsi->tc_cfg.tc_info[i].qcount = qcount;
+		vsi->tc_cfg.tc_info[i].qcount_rx = qcount_rx;
+		vsi->tc_cfg.tc_info[i].qcount_tx = tx_numq_tc;
+		vsi->tc_cfg.tc_info[i].netdev_tc = netdev_tc++;
 
 		qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) &
 			ICE_AQ_VSI_TC_Q_OFFSET_M) |
 			((pow << ICE_AQ_VSI_TC_Q_NUM_S) &
 			 ICE_AQ_VSI_TC_Q_NUM_M);
-		offset += qcount;
+		offset += qcount_rx;
+		tx_count += tx_numq_tc;
 		ctxt->info.tc_mapping[i] = cpu_to_le16(qmap);
 	}
-
-	vsi->num_txq = qcount_tx;
 	vsi->num_rxq = offset;
+	vsi->num_txq = tx_count;
 
 	if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) {
 		dev_dbg(&vsi->back->pdev->dev, "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n");
@@ -1611,10 +1623,10 @@ int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
 	struct ice_aqc_add_tx_qgrp *qg_buf;
 	struct ice_aqc_add_txqs_perq *txq;
 	struct ice_pf *pf = vsi->back;
+	u8 num_q_grps, q_idx = 0;
 	enum ice_status status;
 	u16 buf_len, i, pf_q;
 	int err = 0, tc = 0;
-	u8 num_q_grps;
 
 	buf_len = sizeof(struct ice_aqc_add_tx_qgrp);
 	qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL);
@@ -1628,38 +1640,49 @@ int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
 	qg_buf->num_txqs = 1;
 	num_q_grps = 1;
 
-	/* set up and configure the Tx queues */
-	ice_for_each_txq(vsi, i) {
-		struct ice_tlan_ctx tlan_ctx = { 0 };
+	/* set up and configure the Tx queues for each enabled TC */
+	for (tc = 0; tc < ICE_MAX_TRAFFIC_CLASS; tc++) {
+		if (!(vsi->tc_cfg.ena_tc & BIT(tc)))
+			break;
 
-		pf_q = vsi->txq_map[i];
-		ice_setup_tx_ctx(vsi->tx_rings[i], &tlan_ctx, pf_q);
-		/* copy context contents into the qg_buf */
-		qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
-		ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
-			    ice_tlan_ctx_info);
+		for (i = 0; i < vsi->tc_cfg.tc_info[tc].qcount_tx; i++) {
+			struct ice_tlan_ctx tlan_ctx = { 0 };
+
+			pf_q = vsi->txq_map[q_idx];
+			ice_setup_tx_ctx(vsi->tx_rings[q_idx], &tlan_ctx,
+					 pf_q);
+			/* copy context contents into the qg_buf */
+			qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
+			ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
+				    ice_tlan_ctx_info);
+
+			/* init queue specific tail reg. It is referred as
+			 * transmit comm scheduler queue doorbell.
+			 */
+			vsi->tx_rings[q_idx]->tail =
+				pf->hw.hw_addr + QTX_COMM_DBELL(pf_q);
+			status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc,
+						 num_q_grps, qg_buf, buf_len,
+						 NULL);
+			if (status) {
+				dev_err(&vsi->back->pdev->dev,
+					"Failed to set LAN Tx queue context, error: %d\n",
+					status);
+				err = -ENODEV;
+				goto err_cfg_txqs;
+			}
 
-		/* init queue specific tail reg. It is referred as transmit
-		 * comm scheduler queue doorbell.
-		 */
-		vsi->tx_rings[i]->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q);
-		status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc,
-					 num_q_grps, qg_buf, buf_len, NULL);
-		if (status) {
-			dev_err(&vsi->back->pdev->dev,
-				"Failed to set LAN Tx queue context, error: %d\n",
-				status);
-			err = -ENODEV;
-			goto err_cfg_txqs;
-		}
+			/* Add Tx Queue TEID into the VSI Tx ring from the
+			 * response. This will complete configuring and
+			 * enabling the queue.
+			 */
+			txq = &qg_buf->txqs[0];
+			if (pf_q == le16_to_cpu(txq->txq_id))
+				vsi->tx_rings[q_idx]->txq_teid =
+					le32_to_cpu(txq->q_teid);
 
-		/* Add Tx Queue TEID into the VSI Tx ring from the response
-		 * This will complete configuring and enabling the queue.
-		 */
-		txq = &qg_buf->txqs[0];
-		if (pf_q == le16_to_cpu(txq->txq_id))
-			vsi->tx_rings[i]->txq_teid =
-				le32_to_cpu(txq->q_teid);
+			q_idx++;
+		}
 	}
 err_cfg_txqs:
 	devm_kfree(&pf->pdev->dev, qg_buf);
@@ -2057,6 +2080,9 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	/* set RSS capabilities */
 	ice_vsi_set_rss_params(vsi);
 
+	/* set tc configuration */
+	ice_vsi_set_tc_cfg(vsi);
+
 	/* create the VSI */
 	ret = ice_vsi_init(vsi);
 	if (ret)
@@ -2120,11 +2146,9 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 		goto unroll_vsi_init;
 	}
 
-	ice_vsi_set_tc_cfg(vsi);
-
 	/* configure VSI nodes based on number of queues and TC's */
 	for (i = 0; i < vsi->tc_cfg.numtc; i++)
-		max_txqs[i] = vsi->num_txq;
+		max_txqs[i] = pf->num_lan_tx;
 
 	ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
 			      max_txqs);
@@ -2520,11 +2544,13 @@ int ice_vsi_release(struct ice_vsi *vsi)
 int ice_vsi_rebuild(struct ice_vsi *vsi)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+	struct ice_pf *pf;
 	int ret, i;
 
 	if (!vsi)
 		return -EINVAL;
 
+	pf = vsi->back;
 	ice_vsi_free_q_vectors(vsi);
 	ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx);
 	ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx);
@@ -2534,6 +2560,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 	ice_vsi_free_arrays(vsi, false);
 	ice_dev_onetime_setup(&vsi->back->hw);
 	ice_vsi_set_num_qs(vsi);
+	ice_vsi_set_tc_cfg(vsi);
 
 	/* Initialize VSI struct elements and create VSI in FW */
 	ret = ice_vsi_init(vsi);
@@ -2580,11 +2607,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 		break;
 	}
 
-	ice_vsi_set_tc_cfg(vsi);
-
 	/* configure VSI nodes based on number of queues and TC's */
 	for (i = 0; i < vsi->tc_cfg.numtc; i++)
-		max_txqs[i] = vsi->num_txq;
+		max_txqs[i] = pf->num_lan_tx;
 
 	ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
 			      max_txqs);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 089b0f0b2e71..292d19e65af0 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -349,6 +349,9 @@ ice_prepare_for_reset(struct ice_pf *pf)
 	/* disable the VSIs and their queues that are not already DOWN */
 	ice_pf_dis_all_vsi(pf);
 
+	if (hw->port_info)
+		ice_sched_clear_port(hw->port_info);
+
 	ice_shutdown_all_ctrlq(hw);
 
 	set_bit(__ICE_PREPARED_FOR_RESET, pf->state);
@@ -2543,7 +2546,6 @@ static int ice_vsi_cfg(struct ice_vsi *vsi)
 		if (err)
 			return err;
 	}
-
 	err = ice_vsi_cfg_txqs(vsi);
 	if (!err)
 		err = ice_vsi_cfg_rxqs(vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 7e807b0e7514..7293e4f4d758 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -630,7 +630,7 @@ static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
  *
  * Cleanup scheduling elements from SW DB
  */
-static void ice_sched_clear_port(struct ice_port_info *pi)
+void ice_sched_clear_port(struct ice_port_info *pi)
 {
 	if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY)
 		return;
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h
index dc59fbac7dde..da5b4c166da8 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.h
+++ b/drivers/net/ethernet/intel/ice/ice_sched.h
@@ -26,6 +26,7 @@ struct ice_sched_agg_info {
 /* FW AQ command calls */
 enum ice_status ice_sched_init_port(struct ice_port_info *pi);
 enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw);
+void ice_sched_clear_port(struct ice_port_info *pi);
 void ice_sched_cleanup_all(struct ice_hw *hw);
 struct ice_sched_node *
 ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid);
-- 
cgit v1.2.3


From 47e3e53ceadc568c038e457661d836f2259ed774 Mon Sep 17 00:00:00 2001
From: Henry Tieman <henry.w.tieman@intel.com>
Date: Fri, 26 Oct 2018 11:44:36 -0700
Subject: ice: Destroy scheduler tree in reset path

The scheduler tree is is always rebuilt during reset. The existing code
adds new scheduler nodes for queues but may not clean up earlier nodes.
This patch removed the old scheduler tree during reset before it is
rebuilt.

Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 597005f39919..53685a66125b 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2551,6 +2551,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 		return -EINVAL;
 
 	pf = vsi->back;
+	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	ice_vsi_free_q_vectors(vsi);
 	ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx);
 	ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx);
-- 
cgit v1.2.3


From ef878d6086611eda90755e1f17426f0030000fb1 Mon Sep 17 00:00:00 2001
From: Md Fahad Iqbal Polash <md.fahad.iqbal.polash@intel.com>
Date: Fri, 26 Oct 2018 11:44:37 -0700
Subject: ice: Remove ICE_MAX_TXQ_PER_TXQG check when configuring Tx queue

This patch removes the condition checking of VSI TX queue number to
ICE_MAX_TXQ_PER_TXQG. This is an unnecessary check and causes a driver
load error on hosts that have more than 128 cores.

Signed-off-by: Md Fahad Iqbal Polash <md.fahad.iqbal.polash@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 53685a66125b..a5961a8fe73c 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1633,10 +1633,6 @@ int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
 	if (!qg_buf)
 		return -ENOMEM;
 
-	if (vsi->num_txq > ICE_MAX_TXQ_PER_TXQG) {
-		err = -EINVAL;
-		goto err_cfg_txqs;
-	}
 	qg_buf->num_txqs = 1;
 	num_q_grps = 1;
 
-- 
cgit v1.2.3


From d0e14c4d9bcef0d4aa1057d2959adaa6f18d4a17 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Mon, 12 Nov 2018 16:00:20 +0200
Subject: net: ethernet: ti: cpts: correct debug for expired txq skb

The msgtype and seqid that is smth that belongs to event for
comparison but not for staled txq skb.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index b96b93c686bf..dac4c528a1ff 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -119,9 +119,7 @@ static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
 
 		if (time_after(jiffies, skb_cb->tmo)) {
 			/* timeout any expired skbs over 1s */
-			dev_dbg(cpts->dev,
-				"expiring tx timestamp mtype %u seqid %04x\n",
-				mtype, seqid);
+			dev_dbg(cpts->dev, "expiring tx timestamp from txq\n");
 			__skb_unlink(skb, &cpts->txq);
 			dev_consume_skb_any(skb);
 		}
-- 
cgit v1.2.3


From f19dcd5f118d1795307e28e6e99f482469303edc Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Mon, 12 Nov 2018 16:00:21 +0200
Subject: net: ethernet: ti: cpts: purge staled skbs from txq

The overflow event is running with 1 jiffy in case if txq is not
empty, but it can be emptied completely only if next tx event
consumes skb or deletes staled skb from the txq. In case of staled
skb, that can happen for some unpredictable reason (the ts event was
lost or timed out), the overflow event can be generated quite long
time consuming CPU w/o reason before next tx event happens. To avoid
it, purge txq before increasing overflow event rate.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index dac4c528a1ff..63232b35024e 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -86,6 +86,25 @@ static int cpts_purge_events(struct cpts *cpts)
 	return removed ? 0 : -1;
 }
 
+static void cpts_purge_txq(struct cpts *cpts)
+{
+	struct cpts_skb_cb_data *skb_cb;
+	struct sk_buff *skb, *tmp;
+	int removed = 0;
+
+	skb_queue_walk_safe(&cpts->txq, skb, tmp) {
+		skb_cb = (struct cpts_skb_cb_data *)skb->cb;
+		if (time_after(jiffies, skb_cb->tmo)) {
+			__skb_unlink(skb, &cpts->txq);
+			dev_consume_skb_any(skb);
+			++removed;
+		}
+	}
+
+	if (removed)
+		dev_dbg(cpts->dev, "txq cleaned up %d\n", removed);
+}
+
 static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
 {
 	struct sk_buff *skb, *tmp;
@@ -292,8 +311,11 @@ static long cpts_overflow_check(struct ptp_clock_info *ptp)
 	spin_lock_irqsave(&cpts->lock, flags);
 	ts = ns_to_timespec64(timecounter_read(&cpts->tc));
 
-	if (!skb_queue_empty(&cpts->txq))
-		delay = CPTS_SKB_TX_WORK_TIMEOUT;
+	if (!skb_queue_empty(&cpts->txq)) {
+		cpts_purge_txq(cpts);
+		if (!skb_queue_empty(&cpts->txq))
+			delay = CPTS_SKB_TX_WORK_TIMEOUT;
+	}
 	spin_unlock_irqrestore(&cpts->lock, flags);
 
 	pr_debug("cpts overflow check at %lld.%09ld\n",
-- 
cgit v1.2.3


From a9423120343cb52efea6f471ff780eba7aab9b9f Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Mon, 12 Nov 2018 16:00:22 +0200
Subject: net: ethernet: ti: cpts: move enable/disable flags outside of cpts
 module

Each slave has it's own receive timestamp filter. But cpts rx/tx
timestamp enable flags are used to allow ts retrieve only for one
user. This limitation causes data path redundancy and setting overlap
if cpsw module is in dual-mac mode for instance.

If rx ts is enabled only for one port - the second interface must expect
every incoming packet to be PTP packet w/o absolutely any reason, and if
it's PTP - do unneeded stuff, as rx filter for second port is not set
and cpts fifo is not supposed to contain appropriate ts event.
That's not correct.

So, to fix control overlap and avoid redundant CPU cycles, the patch
splits rx/tx ts enable flags between network devices. After the patch,
PTP timestamping still should be used for only one port (or PTP id
counter has to be different for both ports as cpts IP is common).

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c        | 46 ++++++++++++++++++-----------------
 drivers/net/ethernet/ti/cpts.c        |  2 --
 drivers/net/ethernet/ti/cpts.h        | 38 -----------------------------
 drivers/net/ethernet/ti/netcp_ethss.c | 32 ++++++++++++------------
 4 files changed, 41 insertions(+), 77 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 9434fd5a5477..48ea21e7e0cb 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -466,6 +466,8 @@ struct cpsw_priv {
 	bool				mqprio_hw;
 	int				fifo_bw[CPSW_TC_NUM];
 	int				shp_cfg_speed;
+	int				tx_ts_enabled;
+	int				rx_ts_enabled;
 	u32 emac_port;
 	struct cpsw_common *cpsw;
 };
@@ -905,6 +907,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	struct net_device	*ndev = skb->dev;
 	int			ret = 0, port;
 	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_priv	*priv;
 
 	if (cpsw->data.dual_emac) {
 		port = CPDMA_RX_SOURCE_PORT(status);
@@ -939,7 +942,9 @@ static void cpsw_rx_handler(void *token, int len, int status)
 		skb_put(skb, len);
 		if (status & CPDMA_RX_VLAN_ENCAP)
 			cpsw_rx_vlan_encap(skb);
-		cpts_rx_timestamp(cpsw->cpts, skb);
+		priv = netdev_priv(ndev);
+		if (priv->rx_ts_enabled)
+			cpts_rx_timestamp(cpsw->cpts, skb);
 		skb->protocol = eth_type_trans(skb, ndev);
 		netif_receive_skb(skb);
 		ndev->stats.rx_bytes += len;
@@ -2126,7 +2131,7 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
 	}
 
 	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
-	    cpts_is_tx_enabled(cpts) && cpts_can_timestamp(cpts, skb))
+	    priv->tx_ts_enabled && cpts_can_timestamp(cpts, skb))
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 
 	q_idx = skb_get_queue_mapping(skb);
@@ -2170,13 +2175,13 @@ fail:
 
 #if IS_ENABLED(CONFIG_TI_CPTS)
 
-static void cpsw_hwtstamp_v1(struct cpsw_common *cpsw)
+static void cpsw_hwtstamp_v1(struct cpsw_priv *priv)
 {
+	struct cpsw_common *cpsw = priv->cpsw;
 	struct cpsw_slave *slave = &cpsw->slaves[cpsw->data.active_slave];
 	u32 ts_en, seq_id;
 
-	if (!cpts_is_tx_enabled(cpsw->cpts) &&
-	    !cpts_is_rx_enabled(cpsw->cpts)) {
+	if (!priv->tx_ts_enabled && !priv->rx_ts_enabled) {
 		slave_write(slave, 0, CPSW1_TS_CTL);
 		return;
 	}
@@ -2184,10 +2189,10 @@ static void cpsw_hwtstamp_v1(struct cpsw_common *cpsw)
 	seq_id = (30 << CPSW_V1_SEQ_ID_OFS_SHIFT) | ETH_P_1588;
 	ts_en = EVENT_MSG_BITS << CPSW_V1_MSG_TYPE_OFS;
 
-	if (cpts_is_tx_enabled(cpsw->cpts))
+	if (priv->tx_ts_enabled)
 		ts_en |= CPSW_V1_TS_TX_EN;
 
-	if (cpts_is_rx_enabled(cpsw->cpts))
+	if (priv->rx_ts_enabled)
 		ts_en |= CPSW_V1_TS_RX_EN;
 
 	slave_write(slave, ts_en, CPSW1_TS_CTL);
@@ -2207,20 +2212,20 @@ static void cpsw_hwtstamp_v2(struct cpsw_priv *priv)
 	case CPSW_VERSION_2:
 		ctrl &= ~CTRL_V2_ALL_TS_MASK;
 
-		if (cpts_is_tx_enabled(cpsw->cpts))
+		if (priv->tx_ts_enabled)
 			ctrl |= CTRL_V2_TX_TS_BITS;
 
-		if (cpts_is_rx_enabled(cpsw->cpts))
+		if (priv->rx_ts_enabled)
 			ctrl |= CTRL_V2_RX_TS_BITS;
 		break;
 	case CPSW_VERSION_3:
 	default:
 		ctrl &= ~CTRL_V3_ALL_TS_MASK;
 
-		if (cpts_is_tx_enabled(cpsw->cpts))
+		if (priv->tx_ts_enabled)
 			ctrl |= CTRL_V3_TX_TS_BITS;
 
-		if (cpts_is_rx_enabled(cpsw->cpts))
+		if (priv->rx_ts_enabled)
 			ctrl |= CTRL_V3_RX_TS_BITS;
 		break;
 	}
@@ -2237,7 +2242,6 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	struct cpsw_priv *priv = netdev_priv(dev);
 	struct hwtstamp_config cfg;
 	struct cpsw_common *cpsw = priv->cpsw;
-	struct cpts *cpts = cpsw->cpts;
 
 	if (cpsw->version != CPSW_VERSION_1 &&
 	    cpsw->version != CPSW_VERSION_2 &&
@@ -2256,7 +2260,7 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 	switch (cfg.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		cpts_rx_enable(cpts, 0);
+		priv->rx_ts_enabled = 0;
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_NTP_ALL:
@@ -2264,7 +2268,7 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-		cpts_rx_enable(cpts, HWTSTAMP_FILTER_PTP_V1_L4_EVENT);
+		priv->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
@@ -2276,18 +2280,18 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		cpts_rx_enable(cpts, HWTSTAMP_FILTER_PTP_V2_EVENT);
+		priv->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	cpts_tx_enable(cpts, cfg.tx_type == HWTSTAMP_TX_ON);
+	priv->tx_ts_enabled = cfg.tx_type == HWTSTAMP_TX_ON;
 
 	switch (cpsw->version) {
 	case CPSW_VERSION_1:
-		cpsw_hwtstamp_v1(cpsw);
+		cpsw_hwtstamp_v1(priv);
 		break;
 	case CPSW_VERSION_2:
 	case CPSW_VERSION_3:
@@ -2303,7 +2307,7 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 static int cpsw_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
 {
 	struct cpsw_common *cpsw = ndev_to_cpsw(dev);
-	struct cpts *cpts = cpsw->cpts;
+	struct cpsw_priv *priv = netdev_priv(dev);
 	struct hwtstamp_config cfg;
 
 	if (cpsw->version != CPSW_VERSION_1 &&
@@ -2312,10 +2316,8 @@ static int cpsw_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
 		return -EOPNOTSUPP;
 
 	cfg.flags = 0;
-	cfg.tx_type = cpts_is_tx_enabled(cpts) ?
-		      HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	cfg.rx_filter = (cpts_is_rx_enabled(cpts) ?
-			 cpts->rx_enable : HWTSTAMP_FILTER_NONE);
+	cfg.tx_type = priv->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	cfg.rx_filter = priv->rx_ts_enabled;
 
 	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
 }
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 63232b35024e..054f78295d1d 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -430,8 +430,6 @@ void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb)
 	u64 ns;
 	struct skb_shared_hwtstamps *ssh;
 
-	if (!cpts->rx_enable)
-		return;
 	ns = cpts_find_ts(cpts, skb, CPTS_EV_RX);
 	if (!ns)
 		return;
diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h
index 73d73faf0f38..d2c7decd59b6 100644
--- a/drivers/net/ethernet/ti/cpts.h
+++ b/drivers/net/ethernet/ti/cpts.h
@@ -136,26 +136,6 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 			 struct device_node *node);
 void cpts_release(struct cpts *cpts);
 
-static inline void cpts_rx_enable(struct cpts *cpts, int enable)
-{
-	cpts->rx_enable = enable;
-}
-
-static inline bool cpts_is_rx_enabled(struct cpts *cpts)
-{
-	return !!cpts->rx_enable;
-}
-
-static inline void cpts_tx_enable(struct cpts *cpts, int enable)
-{
-	cpts->tx_enable = enable;
-}
-
-static inline bool cpts_is_tx_enabled(struct cpts *cpts)
-{
-	return !!cpts->tx_enable;
-}
-
 static inline bool cpts_can_timestamp(struct cpts *cpts, struct sk_buff *skb)
 {
 	unsigned int class = ptp_classify_raw(skb);
@@ -197,24 +177,6 @@ static inline void cpts_unregister(struct cpts *cpts)
 {
 }
 
-static inline void cpts_rx_enable(struct cpts *cpts, int enable)
-{
-}
-
-static inline bool cpts_is_rx_enabled(struct cpts *cpts)
-{
-	return false;
-}
-
-static inline void cpts_tx_enable(struct cpts *cpts, int enable)
-{
-}
-
-static inline bool cpts_is_tx_enabled(struct cpts *cpts)
-{
-	return false;
-}
-
 static inline bool cpts_can_timestamp(struct cpts *cpts, struct sk_buff *skb)
 {
 	return false;
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 0397ccb6597e..20d81e0b1c29 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -763,6 +763,8 @@ struct gbe_priv {
 
 	int                             cpts_registered;
 	struct cpts                     *cpts;
+	int				rx_ts_enabled;
+	int				tx_ts_enabled;
 };
 
 struct gbe_intf {
@@ -2564,7 +2566,7 @@ static int gbe_txtstamp_mark_pkt(struct gbe_intf *gbe_intf,
 	struct gbe_priv *gbe_dev = gbe_intf->gbe_dev;
 
 	if (!(skb_shinfo(p_info->skb)->tx_flags & SKBTX_HW_TSTAMP) ||
-	    !cpts_is_tx_enabled(gbe_dev->cpts))
+	    !gbe_dev->tx_ts_enabled)
 		return 0;
 
 	/* If phy has the txtstamp api, assume it will do it.
@@ -2598,7 +2600,9 @@ static int gbe_rxtstamp(struct gbe_intf *gbe_intf, struct netcp_packet *p_info)
 		return 0;
 	}
 
-	cpts_rx_timestamp(gbe_dev->cpts, p_info->skb);
+	if (gbe_dev->rx_ts_enabled)
+		cpts_rx_timestamp(gbe_dev->cpts, p_info->skb);
+
 	p_info->rxtstamp_complete = true;
 
 	return 0;
@@ -2614,10 +2618,8 @@ static int gbe_hwtstamp_get(struct gbe_intf *gbe_intf, struct ifreq *ifr)
 		return -EOPNOTSUPP;
 
 	cfg.flags = 0;
-	cfg.tx_type = cpts_is_tx_enabled(cpts) ?
-		      HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	cfg.rx_filter = (cpts_is_rx_enabled(cpts) ?
-			 cpts->rx_enable : HWTSTAMP_FILTER_NONE);
+	cfg.tx_type = gbe_dev->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	cfg.rx_filter = gbe_dev->rx_ts_enabled;
 
 	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
 }
@@ -2628,8 +2630,8 @@ static void gbe_hwtstamp(struct gbe_intf *gbe_intf)
 	struct gbe_slave *slave = gbe_intf->slave;
 	u32 ts_en, seq_id, ctl;
 
-	if (!cpts_is_rx_enabled(gbe_dev->cpts) &&
-	    !cpts_is_tx_enabled(gbe_dev->cpts)) {
+	if (!gbe_dev->rx_ts_enabled &&
+	    !gbe_dev->tx_ts_enabled) {
 		writel(0, GBE_REG_ADDR(slave, port_regs, ts_ctl));
 		return;
 	}
@@ -2641,10 +2643,10 @@ static void gbe_hwtstamp(struct gbe_intf *gbe_intf)
 		(slave->ts_ctl.uni ?  TS_UNI_EN :
 			slave->ts_ctl.maddr_map << TS_CTL_MADDR_SHIFT);
 
-	if (cpts_is_tx_enabled(gbe_dev->cpts))
+	if (gbe_dev->tx_ts_enabled)
 		ts_en |= (TS_TX_ANX_ALL_EN | TS_TX_VLAN_LT1_EN);
 
-	if (cpts_is_rx_enabled(gbe_dev->cpts))
+	if (gbe_dev->rx_ts_enabled)
 		ts_en |= (TS_RX_ANX_ALL_EN | TS_RX_VLAN_LT1_EN);
 
 	writel(ts_en,  GBE_REG_ADDR(slave, port_regs, ts_ctl));
@@ -2670,10 +2672,10 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr)
 
 	switch (cfg.tx_type) {
 	case HWTSTAMP_TX_OFF:
-		cpts_tx_enable(cpts, 0);
+		gbe_dev->tx_ts_enabled = 0;
 		break;
 	case HWTSTAMP_TX_ON:
-		cpts_tx_enable(cpts, 1);
+		gbe_dev->tx_ts_enabled = 1;
 		break;
 	default:
 		return -ERANGE;
@@ -2681,12 +2683,12 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr)
 
 	switch (cfg.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		cpts_rx_enable(cpts, 0);
+		gbe_dev->rx_ts_enabled = HWTSTAMP_FILTER_NONE;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-		cpts_rx_enable(cpts, HWTSTAMP_FILTER_PTP_V1_L4_EVENT);
+		gbe_dev->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
@@ -2698,7 +2700,7 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		cpts_rx_enable(cpts, HWTSTAMP_FILTER_PTP_V2_EVENT);
+		gbe_dev->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
-- 
cgit v1.2.3


From 1ebb2446c3032682ffce0c665265885f46286038 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Mon, 12 Nov 2018 16:00:23 +0200
Subject: net: ethernet: ti: cpsw: allow vlan tagged packets to be timestamped

Allow vlan tagged packets to be timestamped, as no any restrictions
for this.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 48ea21e7e0cb..e4aa030f1726 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -283,7 +283,7 @@ struct cpsw_ss_regs {
 
 #define CTRL_V2_TS_BITS \
 	(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
-	 TS_TTL_NONZERO  | TS_ANNEX_D_EN | TS_LTYPE1_EN)
+	 TS_TTL_NONZERO  | TS_ANNEX_D_EN | TS_LTYPE1_EN | VLAN_LTYPE1_EN)
 
 #define CTRL_V2_ALL_TS_MASK (CTRL_V2_TS_BITS | TS_TX_EN | TS_RX_EN)
 #define CTRL_V2_TX_TS_BITS  (CTRL_V2_TS_BITS | TS_TX_EN)
@@ -293,7 +293,7 @@ struct cpsw_ss_regs {
 #define CTRL_V3_TS_BITS \
 	(TS_107 | TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
 	 TS_TTL_NONZERO | TS_ANNEX_F_EN | TS_ANNEX_D_EN |\
-	 TS_LTYPE1_EN)
+	 TS_LTYPE1_EN | VLAN_LTYPE1_EN)
 
 #define CTRL_V3_ALL_TS_MASK (CTRL_V3_TS_BITS | TS_TX_EN | TS_RX_EN)
 #define CTRL_V3_TX_TS_BITS  (CTRL_V3_TS_BITS | TS_TX_EN)
@@ -2235,6 +2235,7 @@ static void cpsw_hwtstamp_v2(struct cpsw_priv *priv)
 	slave_write(slave, mtype, CPSW2_TS_SEQ_MTYPE);
 	slave_write(slave, ctrl, CPSW2_CONTROL);
 	writel_relaxed(ETH_P_1588, &cpsw->regs->ts_ltype);
+	writel_relaxed(ETH_P_8021Q, &cpsw->regs->vlan_ltype);
 }
 
 static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
-- 
cgit v1.2.3


From 23e7a718a49bf94d8ffe802a4327d93f6be8335f Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Mon, 12 Nov 2018 15:45:58 +0000
Subject: net: aquantia: add rx-flow filter definitions

Add missing register definitions and the functions accessing them
related to rx-flow filters.

Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c | 109 +++++++++++++++++
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h |  48 ++++++++
 .../aquantia/atlantic/hw_atl/hw_atl_llh_internal.h | 135 ++++++++++++++++++---
 3 files changed, 275 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index 5502ec5f0f69..939f77e2e117 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -898,6 +898,24 @@ void hw_atl_rpf_vlan_id_flr_set(struct aq_hw_s *aq_hw, u32 vlan_id_flr,
 			    vlan_id_flr);
 }
 
+void hw_atl_rpf_vlan_rxq_en_flr_set(struct aq_hw_s *aq_hw, u32 vlan_rxq_en,
+				    u32 filter)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_RPF_VL_RXQ_EN_F_ADR(filter),
+			    HW_ATL_RPF_VL_RXQ_EN_F_MSK,
+			    HW_ATL_RPF_VL_RXQ_EN_F_SHIFT,
+			    vlan_rxq_en);
+}
+
+void hw_atl_rpf_vlan_rxq_flr_set(struct aq_hw_s *aq_hw, u32 vlan_rxq,
+				 u32 filter)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_RPF_VL_RXQ_F_ADR(filter),
+			    HW_ATL_RPF_VL_RXQ_F_MSK,
+			    HW_ATL_RPF_VL_RXQ_F_SHIFT,
+			    vlan_rxq);
+};
+
 void hw_atl_rpf_etht_flr_en_set(struct aq_hw_s *aq_hw, u32 etht_flr_en,
 				u32 filter)
 {
@@ -965,6 +983,20 @@ void hw_atl_rpf_etht_flr_set(struct aq_hw_s *aq_hw, u32 etht_flr, u32 filter)
 			    HW_ATL_RPF_ET_VALF_SHIFT, etht_flr);
 }
 
+void hw_atl_rpf_l4_spd_set(struct aq_hw_s *aq_hw, u32 val, u32 filter)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_RPF_L4_SPD_ADR(filter),
+			    HW_ATL_RPF_L4_SPD_MSK,
+			    HW_ATL_RPF_L4_SPD_SHIFT, val);
+}
+
+void hw_atl_rpf_l4_dpd_set(struct aq_hw_s *aq_hw, u32 val, u32 filter)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_RPF_L4_DPD_ADR(filter),
+			    HW_ATL_RPF_L4_DPD_MSK,
+			    HW_ATL_RPF_L4_DPD_SHIFT, val);
+}
+
 /* RPO: rx packet offload */
 void hw_atl_rpo_ipv4header_crc_offload_en_set(struct aq_hw_s *aq_hw,
 					      u32 ipv4header_crc_offload_en)
@@ -1476,3 +1508,80 @@ void hw_atl_mcp_up_force_intr_set(struct aq_hw_s *aq_hw, u32 up_force_intr)
 			    HW_ATL_MCP_UP_FORCE_INTERRUPT_SHIFT,
 			    up_force_intr);
 }
+
+void hw_atl_rpfl3l4_ipv4_dest_addr_clear(struct aq_hw_s *aq_hw, u8 location)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_DSTA_ADR(location), 0U);
+}
+
+void hw_atl_rpfl3l4_ipv4_src_addr_clear(struct aq_hw_s *aq_hw, u8 location)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_SRCA_ADR(location), 0U);
+}
+
+void hw_atl_rpfl3l4_cmd_clear(struct aq_hw_s *aq_hw, u8 location)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_REG_CTRL_ADR(location), 0U);
+}
+
+void hw_atl_rpfl3l4_ipv6_dest_addr_clear(struct aq_hw_s *aq_hw, u8 location)
+{
+	int i;
+
+	for (i = 0; i < 4; ++i)
+		aq_hw_write_reg(aq_hw,
+				HW_ATL_RPF_L3_DSTA_ADR(location + i),
+				0U);
+}
+
+void hw_atl_rpfl3l4_ipv6_src_addr_clear(struct aq_hw_s *aq_hw, u8 location)
+{
+	int i;
+
+	for (i = 0; i < 4; ++i)
+		aq_hw_write_reg(aq_hw,
+				HW_ATL_RPF_L3_SRCA_ADR(location + i),
+				0U);
+}
+
+void hw_atl_rpfl3l4_ipv4_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				       u32 ipv4_dest)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_DSTA_ADR(location),
+			ipv4_dest);
+}
+
+void hw_atl_rpfl3l4_ipv4_src_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				      u32 ipv4_src)
+{
+	aq_hw_write_reg(aq_hw,
+			HW_ATL_RPF_L3_SRCA_ADR(location),
+			ipv4_src);
+}
+
+void hw_atl_rpfl3l4_cmd_set(struct aq_hw_s *aq_hw, u8 location, u32 cmd)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_REG_CTRL_ADR(location), cmd);
+}
+
+void hw_atl_rpfl3l4_ipv6_src_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				      u32 *ipv6_src)
+{
+	int i;
+
+	for (i = 0; i < 4; ++i)
+		aq_hw_write_reg(aq_hw,
+				HW_ATL_RPF_L3_SRCA_ADR(location + i),
+				ipv6_src[i]);
+}
+
+void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				       u32 *ipv6_dest)
+{
+	int i;
+
+	for (i = 0; i < 4; ++i)
+		aq_hw_write_reg(aq_hw,
+				HW_ATL_RPF_L3_DSTA_ADR(location + i),
+				ipv6_dest[i]);
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
index 41f239928c15..03c570d115fe 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
@@ -441,6 +441,14 @@ void hw_atl_rpf_vlan_flr_act_set(struct aq_hw_s *aq_hw, u32 vlan_filter_act,
 void hw_atl_rpf_vlan_id_flr_set(struct aq_hw_s *aq_hw, u32 vlan_id_flr,
 				u32 filter);
 
+/* Set VLAN RX queue assignment enable */
+void hw_atl_rpf_vlan_rxq_en_flr_set(struct aq_hw_s *aq_hw, u32 vlan_rxq_en,
+				    u32 filter);
+
+/* Set VLAN RX queue */
+void hw_atl_rpf_vlan_rxq_flr_set(struct aq_hw_s *aq_hw, u32 vlan_rxq,
+				 u32 filter);
+
 /* set ethertype filter enable */
 void hw_atl_rpf_etht_flr_en_set(struct aq_hw_s *aq_hw, u32 etht_flr_en,
 				u32 filter);
@@ -475,6 +483,12 @@ void hw_atl_rpf_etht_flr_act_set(struct aq_hw_s *aq_hw, u32 etht_flr_act,
 /* set ethertype filter */
 void hw_atl_rpf_etht_flr_set(struct aq_hw_s *aq_hw, u32 etht_flr, u32 filter);
 
+/* set L4 source port */
+void hw_atl_rpf_l4_spd_set(struct aq_hw_s *aq_hw, u32 val, u32 filter);
+
+/* set L4 destination port */
+void hw_atl_rpf_l4_dpd_set(struct aq_hw_s *aq_hw, u32 val, u32 filter);
+
 /* rpo */
 
 /* set ipv4 header checksum offload enable */
@@ -704,4 +718,38 @@ void hw_atl_pci_pci_reg_res_dis_set(struct aq_hw_s *aq_hw, u32 pci_reg_res_dis);
 /* set uP Force Interrupt */
 void hw_atl_mcp_up_force_intr_set(struct aq_hw_s *aq_hw, u32 up_force_intr);
 
+/* clear ipv4 filter destination address */
+void hw_atl_rpfl3l4_ipv4_dest_addr_clear(struct aq_hw_s *aq_hw, u8 location);
+
+/* clear ipv4 filter source address */
+void hw_atl_rpfl3l4_ipv4_src_addr_clear(struct aq_hw_s *aq_hw, u8 location);
+
+/* clear command for filter l3-l4 */
+void hw_atl_rpfl3l4_cmd_clear(struct aq_hw_s *aq_hw, u8 location);
+
+/* clear ipv6 filter destination address */
+void hw_atl_rpfl3l4_ipv6_dest_addr_clear(struct aq_hw_s *aq_hw, u8 location);
+
+/* clear ipv6 filter source address */
+void hw_atl_rpfl3l4_ipv6_src_addr_clear(struct aq_hw_s *aq_hw, u8 location);
+
+/* set ipv4 filter destination address */
+void hw_atl_rpfl3l4_ipv4_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				       u32 ipv4_dest);
+
+/* set ipv4 filter source address */
+void hw_atl_rpfl3l4_ipv4_src_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				      u32 ipv4_src);
+
+/* set command for filter l3-l4 */
+void hw_atl_rpfl3l4_cmd_set(struct aq_hw_s *aq_hw, u8 location, u32 cmd);
+
+/* set ipv6 filter source address */
+void hw_atl_rpfl3l4_ipv6_src_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				      u32 *ipv6_src);
+
+/* set ipv6 filter destination address */
+void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				       u32 *ipv6_dest);
+
 #endif /* HW_ATL_LLH_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
index a715fa317b1c..8470d92db812 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
@@ -1092,24 +1092,43 @@
 /* Default value of bitfield vl_id{F}[B:0] */
 #define HW_ATL_RPF_VL_ID_F_DEFAULT 0x0
 
-/* RX et_en{F} Bitfield Definitions
- * Preprocessor definitions for the bitfield "et_en{F}".
+/* RX vl_rxq_en{F} Bitfield Definitions
+ * Preprocessor definitions for the bitfield "vl_rxq{F}".
  * Parameter: filter {F} | stride size 0x4 | range [0, 15]
- * PORT="pif_rpf_et_en_i[0]"
- */
-
-/* Register address for bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_ADR(filter) (0x00005300 + (filter) * 0x4)
-/* Bitmask for bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_MSK 0x80000000
-/* Inverted bitmask for bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_MSKN 0x7FFFFFFF
-/* Lower bit position of bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_SHIFT 31
-/* Width of bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_WIDTH 1
-/* Default value of bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_DEFAULT 0x0
+ * PORT="pif_rpf_vl_rxq_en_i"
+ */
+
+/* Register address for bitfield vl_rxq_en{F} */
+#define HW_ATL_RPF_VL_RXQ_EN_F_ADR(filter) (0x00005290 + (filter) * 0x4)
+/* Bitmask for bitfield vl_rxq_en{F} */
+#define HW_ATL_RPF_VL_RXQ_EN_F_MSK 0x10000000
+/* Inverted bitmask for bitfield vl_rxq_en{F}[ */
+#define HW_ATL_RPF_VL_RXQ_EN_F_MSKN 0xEFFFFFFF
+/* Lower bit position of bitfield vl_rxq_en{F} */
+#define HW_ATL_RPF_VL_RXQ_EN_F_SHIFT 28
+/* Width of bitfield vl_rxq_en{F} */
+#define HW_ATL_RPF_VL_RXQ_EN_F_WIDTH 1
+/* Default value of bitfield vl_rxq_en{F} */
+#define HW_ATL_RPF_VL_RXQ_EN_F_DEFAULT 0x0
+
+/* RX vl_rxq{F}[4:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "vl_rxq{F}[4:0]".
+ * Parameter: filter {F} | stride size 0x4 | range [0, 15]
+ * PORT="pif_rpf_vl_rxq0_i[4:0]"
+ */
+
+/* Register address for bitfield vl_rxq{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_ADR(filter) (0x00005290 + (filter) * 0x4)
+/* Bitmask for bitfield vl_rxq{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_MSK 0x01F00000
+/* Inverted bitmask for bitfield vl_rxq{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_MSKN 0xFE0FFFFF
+/* Lower bit position of bitfield vl_rxq{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_SHIFT 20
+/* Width of bitfield vl_rxw{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_WIDTH 5
+/* Default value of bitfield vl_rxq{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_DEFAULT 0x0
 
 /* rx et_en{f} bitfield definitions
  * preprocessor definitions for the bitfield "et_en{f}".
@@ -1263,6 +1282,44 @@
 /* default value of bitfield et_val{f}[f:0] */
 #define HW_ATL_RPF_ET_VALF_DEFAULT 0x0
 
+/* RX l4_sp{D}[F:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "l4_sp{D}[F:0]".
+ * Parameter: srcport {D} | stride size 0x4 | range [0, 7]
+ * PORT="pif_rpf_l4_sp0_i[15:0]"
+ */
+
+/* Register address for bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_ADR(srcport) (0x00005400u + (srcport) * 0x4)
+/* Bitmask for bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_MSK 0x0000FFFFu
+/* Inverted bitmask for bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_MSKN 0xFFFF0000u
+/* Lower bit position of bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_SHIFT 0
+/* Width of bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_WIDTH 16
+/* Default value of bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_DEFAULT 0x0
+
+/* RX l4_dp{D}[F:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "l4_dp{D}[F:0]".
+ * Parameter: destport {D} | stride size 0x4 | range [0, 7]
+ * PORT="pif_rpf_l4_dp0_i[15:0]"
+ */
+
+/* Register address for bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_ADR(destport) (0x00005420u + (destport) * 0x4)
+/* Bitmask for bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_MSK 0x0000FFFFu
+/* Inverted bitmask for bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_MSKN 0xFFFF0000u
+/* Lower bit position of bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_SHIFT 0
+/* Width of bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_WIDTH 16
+/* Default value of bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_DEFAULT 0x0
+
 /* rx ipv4_chk_en bitfield definitions
  * preprocessor definitions for the bitfield "ipv4_chk_en".
  * port="pif_rpo_ipv4_chk_en_i"
@@ -2418,4 +2475,48 @@
 /* default value of bitfield uP Force Interrupt */
 #define HW_ATL_MCP_UP_FORCE_INTERRUPT_DEFAULT 0x0
 
+#define HW_ATL_RX_CTRL_ADDR_BEGIN_FL3L4   0x00005380
+#define HW_ATL_RX_SRCA_ADDR_BEGIN_FL3L4   0x000053B0
+#define HW_ATL_RX_DESTA_ADDR_BEGIN_FL3L4  0x000053D0
+
+#define HW_ATL_RPF_L3_REG_CTRL_ADR(location) (0x00005380 + (location) * 0x4)
+
+/* RX rpf_l3_sa{D}[1F:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "l3_sa{D}[1F:0]".
+ * Parameter: location {D} | stride size 0x4 | range [0, 7]
+ * PORT="pif_rpf_l3_sa0_i[31:0]"
+ */
+
+/* Register address for bitfield pif_rpf_l3_sa0_i[31:0] */
+#define HW_ATL_RPF_L3_SRCA_ADR(location) (0x000053B0 + (location) * 0x4)
+/* Bitmask for bitfield l3_sa0[1F:0] */
+#define HW_ATL_RPF_L3_SRCA_MSK 0xFFFFFFFFu
+/* Inverted bitmask for bitfield l3_sa0[1F:0] */
+#define HW_ATL_RPF_L3_SRCA_MSKN 0xFFFFFFFFu
+/* Lower bit position of bitfield l3_sa0[1F:0] */
+#define HW_ATL_RPF_L3_SRCA_SHIFT 0
+/* Width of bitfield l3_sa0[1F:0] */
+#define HW_ATL_RPF_L3_SRCA_WIDTH 32
+/* Default value of bitfield l3_sa0[1F:0] */
+#define HW_ATL_RPF_L3_SRCA_DEFAULT 0x0
+
+/* RX rpf_l3_da{D}[1F:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "l3_da{D}[1F:0]".
+ * Parameter: location {D} | stride size 0x4 | range [0, 7]
+ * PORT="pif_rpf_l3_da0_i[31:0]"
+ */
+
+ /* Register address for bitfield pif_rpf_l3_da0_i[31:0] */
+#define HW_ATL_RPF_L3_DSTA_ADR(location) (0x000053B0 + (location) * 0x4)
+/* Bitmask for bitfield l3_da0[1F:0] */
+#define HW_ATL_RPF_L3_DSTA_MSK 0xFFFFFFFFu
+/* Inverted bitmask for bitfield l3_da0[1F:0] */
+#define HW_ATL_RPF_L3_DSTA_MSKN 0xFFFFFFFFu
+/* Lower bit position of bitfield l3_da0[1F:0] */
+#define HW_ATL_RPF_L3_DSTA_SHIFT 0
+/* Width of bitfield l3_da0[1F:0] */
+#define HW_ATL_RPF_L3_DSTA_WIDTH 32
+/* Default value of bitfield l3_da0[1F:0] */
+#define HW_ATL_RPF_L3_DSTA_DEFAULT 0x0
+
 #endif /* HW_ATL_LLH_INTERNAL_H */
-- 
cgit v1.2.3


From 8d0bcb012f57729e44991a45f5ba3266a58de268 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Mon, 12 Nov 2018 15:46:00 +0000
Subject: net: aquantia: add infrastructure for ntuple rules

Add infrastructure to support ntuple filter configuration.
Add rule, remove rule, reapply on interface up.

Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/Makefile    |   1 +
 .../net/ethernet/aquantia/atlantic/aq_ethtool.c    |  31 ++
 .../net/ethernet/aquantia/atlantic/aq_filters.c    | 413 +++++++++++++++++++++
 .../net/ethernet/aquantia/atlantic/aq_filters.h    |  31 ++
 drivers/net/ethernet/aquantia/atlantic/aq_main.c   |  15 +
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h    |   6 +
 .../net/ethernet/aquantia/atlantic/aq_pci_func.c   |   2 +
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  |   3 +-
 8 files changed, 501 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/aquantia/atlantic/aq_filters.c
 create mode 100644 drivers/net/ethernet/aquantia/atlantic/aq_filters.h

diff --git a/drivers/net/ethernet/aquantia/atlantic/Makefile b/drivers/net/ethernet/aquantia/atlantic/Makefile
index 686f6d8c9e79..4556630ee286 100644
--- a/drivers/net/ethernet/aquantia/atlantic/Makefile
+++ b/drivers/net/ethernet/aquantia/atlantic/Makefile
@@ -36,6 +36,7 @@ atlantic-objs := aq_main.o \
 	aq_ring.o \
 	aq_hw_utils.o \
 	aq_ethtool.o \
+	aq_filters.o \
 	hw_atl/hw_atl_a0.o \
 	hw_atl/hw_atl_b0.o \
 	hw_atl/hw_atl_utils.o \
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 99ef1daaa4d8..a5fd71692c8b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -12,6 +12,7 @@
 #include "aq_ethtool.h"
 #include "aq_nic.h"
 #include "aq_vec.h"
+#include "aq_filters.h"
 
 static void aq_ethtool_get_regs(struct net_device *ndev,
 				struct ethtool_regs *regs, void *p)
@@ -213,7 +214,36 @@ static int aq_ethtool_get_rxnfc(struct net_device *ndev,
 	case ETHTOOL_GRXRINGS:
 		cmd->data = cfg->vecs;
 		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		cmd->rule_cnt = aq_get_rxnfc_count_all_rules(aq_nic);
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		err = aq_get_rxnfc_rule(aq_nic, cmd);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		err = aq_get_rxnfc_all_rules(aq_nic, cmd, rule_locs);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
 
+	return err;
+}
+
+static int aq_ethtool_set_rxnfc(struct net_device *ndev,
+				struct ethtool_rxnfc *cmd)
+{
+	int err = 0;
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		err = aq_add_rxnfc_rule(aq_nic, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		err = aq_del_rxnfc_rule(aq_nic, cmd);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
@@ -520,6 +550,7 @@ const struct ethtool_ops aq_ethtool_ops = {
 	.get_rxfh_key_size   = aq_ethtool_get_rss_key_size,
 	.get_rxfh            = aq_ethtool_get_rss,
 	.get_rxnfc           = aq_ethtool_get_rxnfc,
+	.set_rxnfc           = aq_ethtool_set_rxnfc,
 	.get_sset_count      = aq_ethtool_get_sset_count,
 	.get_ethtool_stats   = aq_ethtool_stats,
 	.get_link_ksettings  = aq_ethtool_get_link_ksettings,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
new file mode 100644
index 000000000000..8cb4eaefd6e1
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -0,0 +1,413 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Copyright (C) 2014-2017 aQuantia Corporation. */
+
+/* File aq_filters.c: RX filters related functions. */
+
+#include "aq_filters.h"
+
+static bool __must_check
+aq_rule_is_approve(struct ethtool_rx_flow_spec *fsp)
+{
+	if (fsp->flow_type & FLOW_MAC_EXT)
+		return false;
+
+	switch (fsp->flow_type & ~FLOW_EXT) {
+	case ETHER_FLOW:
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case IPV4_FLOW:
+	case IPV6_FLOW:
+		return true;
+	case IP_USER_FLOW:
+		switch (fsp->h_u.usr_ip4_spec.proto) {
+		case IPPROTO_TCP:
+		case IPPROTO_UDP:
+		case IPPROTO_SCTP:
+		case IPPROTO_IP:
+			return true;
+		default:
+			return false;
+			}
+	case IPV6_USER_FLOW:
+		switch (fsp->h_u.usr_ip6_spec.l4_proto) {
+		case IPPROTO_TCP:
+		case IPPROTO_UDP:
+		case IPPROTO_SCTP:
+		case IPPROTO_IP:
+			return true;
+		default:
+			return false;
+			}
+	default:
+		return false;
+	}
+
+	return false;
+}
+
+static bool __must_check
+aq_match_filter(struct ethtool_rx_flow_spec *fsp1,
+		struct ethtool_rx_flow_spec *fsp2)
+{
+	if (fsp1->flow_type != fsp2->flow_type ||
+	    memcmp(&fsp1->h_u, &fsp2->h_u, sizeof(fsp2->h_u)) ||
+	    memcmp(&fsp1->h_ext, &fsp2->h_ext, sizeof(fsp2->h_ext)) ||
+	    memcmp(&fsp1->m_u, &fsp2->m_u, sizeof(fsp2->m_u)) ||
+	    memcmp(&fsp1->m_ext, &fsp2->m_ext, sizeof(fsp2->m_ext)))
+		return false;
+
+	return true;
+}
+
+static bool __must_check
+aq_rule_already_exists(struct aq_nic_s *aq_nic,
+		       struct ethtool_rx_flow_spec *fsp)
+{
+	struct aq_rx_filter *rule;
+	struct hlist_node *aq_node2;
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		if (rule->aq_fsp.location == fsp->location)
+			continue;
+		if (aq_match_filter(&rule->aq_fsp, fsp)) {
+			netdev_err(aq_nic->ndev,
+				   "ethtool: This filter is already set\n");
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static int __must_check
+aq_check_filter(struct aq_nic_s *aq_nic,
+		struct ethtool_rx_flow_spec *fsp)
+{
+	int err = 0;
+
+	if (fsp->flow_type & FLOW_EXT) {
+		err = -EOPNOTSUPP;
+	} else {
+		switch (fsp->flow_type & ~FLOW_EXT) {
+		case ETHER_FLOW:
+			err = -EOPNOTSUPP;
+			break;
+		case TCP_V4_FLOW:
+		case UDP_V4_FLOW:
+		case SCTP_V4_FLOW:
+		case IPV4_FLOW:
+		case IP_USER_FLOW:
+			err = -EOPNOTSUPP;
+			break;
+		case TCP_V6_FLOW:
+		case UDP_V6_FLOW:
+		case SCTP_V6_FLOW:
+		case IPV6_FLOW:
+		case IPV6_USER_FLOW:
+			err = -EOPNOTSUPP;
+			break;
+		default:
+			netdev_err(aq_nic->ndev,
+				   "ethtool: unknown flow-type specified");
+			err = -EINVAL;
+		}
+	}
+
+	return err;
+}
+
+static bool __must_check
+aq_rule_is_not_support(struct aq_nic_s *aq_nic,
+		       struct ethtool_rx_flow_spec *fsp)
+{
+	bool rule_is_not_support = false;
+
+	if (!(aq_nic->ndev->features & NETIF_F_NTUPLE)) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: Please, to enable the RX flow control:\n"
+			   "ethtool -K %s ntuple on\n", aq_nic->ndev->name);
+		rule_is_not_support = true;
+	} else if (!aq_rule_is_approve(fsp)) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: The specified flow type is not supported\n");
+		rule_is_not_support = true;
+	} else if ((fsp->flow_type & ~FLOW_EXT) != ETHER_FLOW &&
+		   (fsp->h_u.tcp_ip4_spec.tos ||
+		    fsp->h_u.tcp_ip6_spec.tclass)) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: The specified tos tclass are not supported\n");
+		rule_is_not_support = true;
+	}
+
+	return rule_is_not_support;
+}
+
+static bool __must_check
+aq_rule_is_not_correct(struct aq_nic_s *aq_nic,
+		       struct ethtool_rx_flow_spec *fsp)
+{
+	bool rule_is_not_correct = false;
+
+	if (!aq_nic) {
+		rule_is_not_correct = true;
+	} else if (aq_check_filter(aq_nic, fsp)) {
+		rule_is_not_correct = true;
+	} else if (fsp->ring_cookie != RX_CLS_FLOW_DISC) {
+		if (fsp->ring_cookie >= aq_nic->aq_nic_cfg.num_rss_queues) {
+			netdev_err(aq_nic->ndev,
+				   "ethtool: The specified action is invalid.\n"
+				   "Maximum allowable value action is %u.\n",
+				   aq_nic->aq_nic_cfg.num_rss_queues - 1);
+			rule_is_not_correct = true;
+		}
+	}
+
+	return rule_is_not_correct;
+}
+
+static int __must_check
+aq_check_rule(struct aq_nic_s *aq_nic,
+	      struct ethtool_rx_flow_spec *fsp)
+{
+	int err = 0;
+
+	if (aq_rule_is_not_correct(aq_nic, fsp))
+		err = -EINVAL;
+	else if (aq_rule_is_not_support(aq_nic, fsp))
+		err = -EOPNOTSUPP;
+	else if (aq_rule_already_exists(aq_nic, fsp))
+		err = -EEXIST;
+
+	return err;
+}
+
+static int aq_add_del_rule(struct aq_nic_s *aq_nic,
+			   struct aq_rx_filter *aq_rx_fltr, bool add)
+{
+	int err = -EINVAL;
+
+	if (aq_rx_fltr->aq_fsp.flow_type & FLOW_EXT) {
+		err = -EOPNOTSUPP;
+	} else {
+		switch (aq_rx_fltr->aq_fsp.flow_type & ~FLOW_EXT) {
+		case ETHER_FLOW:
+			err = -EOPNOTSUPP;
+			break;
+		case TCP_V4_FLOW:
+		case UDP_V4_FLOW:
+		case SCTP_V4_FLOW:
+		case IP_USER_FLOW:
+		case TCP_V6_FLOW:
+		case UDP_V6_FLOW:
+		case SCTP_V6_FLOW:
+		case IPV6_USER_FLOW:
+			err = -EOPNOTSUPP;
+			break;
+		default:
+			err = -EINVAL;
+			break;
+		}
+	}
+
+	return err;
+}
+
+static int aq_update_table_filters(struct aq_nic_s *aq_nic,
+				   struct aq_rx_filter *aq_rx_fltr, u16 index,
+				   struct ethtool_rxnfc *cmd)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct aq_rx_filter *rule = NULL, *parent = NULL;
+	struct hlist_node *aq_node2;
+	int err = -EINVAL;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		if (rule->aq_fsp.location >= index)
+			break;
+		parent = rule;
+	}
+
+	if (rule && rule->aq_fsp.location == index) {
+		err = aq_add_del_rule(aq_nic, rule, false);
+		hlist_del(&rule->aq_node);
+		kfree(rule);
+		--rx_fltrs->active_filters;
+	}
+
+	if (unlikely(!aq_rx_fltr))
+		return err;
+
+	INIT_HLIST_NODE(&aq_rx_fltr->aq_node);
+
+	if (parent)
+		hlist_add_behind(&aq_rx_fltr->aq_node, &parent->aq_node);
+	else
+		hlist_add_head(&aq_rx_fltr->aq_node, &rx_fltrs->filter_list);
+
+	++rx_fltrs->active_filters;
+
+	return 0;
+}
+
+u16 aq_get_rxnfc_count_all_rules(struct aq_nic_s *aq_nic)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+
+	return rx_fltrs->active_filters;
+}
+
+struct aq_hw_rx_fltrs_s *aq_get_hw_rx_fltrs(struct aq_nic_s *aq_nic)
+{
+	return &aq_nic->aq_hw_rx_fltrs;
+}
+
+int aq_add_rxnfc_rule(struct aq_nic_s *aq_nic, const struct ethtool_rxnfc *cmd)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct ethtool_rx_flow_spec *fsp =
+		(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct aq_rx_filter *aq_rx_fltr;
+	int err = 0;
+
+	err = aq_check_rule(aq_nic, fsp);
+	if (err)
+		goto err_exit;
+
+	aq_rx_fltr = kzalloc(sizeof(*aq_rx_fltr), GFP_KERNEL);
+	if (unlikely(!aq_rx_fltr)) {
+		err = -ENOMEM;
+		goto err_exit;
+	}
+
+	memcpy(&aq_rx_fltr->aq_fsp, fsp, sizeof(*fsp));
+
+	err = aq_update_table_filters(aq_nic, aq_rx_fltr, fsp->location, NULL);
+	if (unlikely(err))
+		goto err_free;
+
+	err = aq_add_del_rule(aq_nic, aq_rx_fltr, true);
+	if (unlikely(err)) {
+		hlist_del(&aq_rx_fltr->aq_node);
+		--rx_fltrs->active_filters;
+		goto err_free;
+	}
+
+	return 0;
+
+err_free:
+	kfree(aq_rx_fltr);
+err_exit:
+	return err;
+}
+
+int aq_del_rxnfc_rule(struct aq_nic_s *aq_nic, const struct ethtool_rxnfc *cmd)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct aq_rx_filter *rule = NULL;
+	struct hlist_node *aq_node2;
+	int err = -EINVAL;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		if (rule->aq_fsp.location == cmd->fs.location)
+			break;
+	}
+
+	if (rule && rule->aq_fsp.location == cmd->fs.location) {
+		err = aq_add_del_rule(aq_nic, rule, false);
+		hlist_del(&rule->aq_node);
+		kfree(rule);
+		--rx_fltrs->active_filters;
+	}
+	return err;
+}
+
+int aq_get_rxnfc_rule(struct aq_nic_s *aq_nic, struct ethtool_rxnfc *cmd)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct ethtool_rx_flow_spec *fsp =
+			(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct aq_rx_filter *rule = NULL;
+	struct hlist_node *aq_node2;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node)
+		if (fsp->location <= rule->aq_fsp.location)
+			break;
+
+	if (unlikely(!rule || fsp->location != rule->aq_fsp.location))
+		return -EINVAL;
+
+	memcpy(fsp, &rule->aq_fsp, sizeof(*fsp));
+
+	return 0;
+}
+
+int aq_get_rxnfc_all_rules(struct aq_nic_s *aq_nic, struct ethtool_rxnfc *cmd,
+			   u32 *rule_locs)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct hlist_node *aq_node2;
+	struct aq_rx_filter *rule;
+	int count = 0;
+
+	cmd->data = aq_get_rxnfc_count_all_rules(aq_nic);
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		if (unlikely(count == cmd->rule_cnt))
+			return -EMSGSIZE;
+
+		rule_locs[count++] = rule->aq_fsp.location;
+	}
+
+	cmd->rule_cnt = count;
+
+	return 0;
+}
+
+int aq_clear_rxnfc_all_rules(struct aq_nic_s *aq_nic)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct hlist_node *aq_node2;
+	struct aq_rx_filter *rule;
+	int err = 0;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		err = aq_add_del_rule(aq_nic, rule, false);
+		if (err)
+			goto err_exit;
+		hlist_del(&rule->aq_node);
+		kfree(rule);
+		--rx_fltrs->active_filters;
+	}
+
+err_exit:
+	return err;
+}
+
+int aq_reapply_rxnfc_all_rules(struct aq_nic_s *aq_nic)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct hlist_node *aq_node2;
+	struct aq_rx_filter *rule;
+	int err = 0;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		err = aq_add_del_rule(aq_nic, rule, true);
+		if (err)
+			goto err_exit;
+	}
+
+err_exit:
+	return err;
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.h b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
new file mode 100644
index 000000000000..1f1368b08a5b
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright (C) 2014-2017 aQuantia Corporation. */
+
+/* File aq_filters.h: RX filters related functions. */
+
+#ifndef AQ_FILTERS_H
+#define AQ_FILTERS_H
+
+#include "aq_nic.h"
+
+enum aq_rx_filter_type {
+	aq_rx_filter_l3l4
+};
+
+struct aq_rx_filter {
+	struct hlist_node aq_node;
+	enum aq_rx_filter_type type;
+	struct ethtool_rx_flow_spec aq_fsp;
+};
+
+u16 aq_get_rxnfc_count_all_rules(struct aq_nic_s *aq_nic);
+struct aq_hw_rx_fltrs_s *aq_get_hw_rx_fltrs(struct aq_nic_s *aq_nic);
+int aq_add_rxnfc_rule(struct aq_nic_s *aq_nic, const struct ethtool_rxnfc *cmd);
+int aq_del_rxnfc_rule(struct aq_nic_s *aq_nic, const struct ethtool_rxnfc *cmd);
+int aq_get_rxnfc_rule(struct aq_nic_s *aq_nic, struct ethtool_rxnfc *cmd);
+int aq_get_rxnfc_all_rules(struct aq_nic_s *aq_nic, struct ethtool_rxnfc *cmd,
+			   u32 *rule_locs);
+int aq_clear_rxnfc_all_rules(struct aq_nic_s *aq_nic);
+int aq_reapply_rxnfc_all_rules(struct aq_nic_s *aq_nic);
+
+#endif /* AQ_FILTERS_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index 7c07eef275eb..ff15d3388add 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -13,6 +13,7 @@
 #include "aq_nic.h"
 #include "aq_pci_func.h"
 #include "aq_ethtool.h"
+#include "aq_filters.h"
 
 #include <linux/netdevice.h>
 #include <linux/module.h>
@@ -49,6 +50,11 @@ static int aq_ndev_open(struct net_device *ndev)
 	err = aq_nic_init(aq_nic);
 	if (err < 0)
 		goto err_exit;
+
+	err = aq_reapply_rxnfc_all_rules(aq_nic);
+	if (err < 0)
+		goto err_exit;
+
 	err = aq_nic_start(aq_nic);
 	if (err < 0)
 		goto err_exit;
@@ -101,6 +107,14 @@ static int aq_ndev_set_features(struct net_device *ndev,
 	bool is_lro = false;
 	int err = 0;
 
+	if (!(features & NETIF_F_NTUPLE)) {
+		if (aq_nic->ndev->features & NETIF_F_NTUPLE) {
+			err = aq_clear_rxnfc_all_rules(aq_nic);
+			if (unlikely(err))
+				goto err_exit;
+		}
+	}
+
 	aq_cfg->features = features;
 
 	if (aq_cfg->aq_hw_caps->hw_features & NETIF_F_LRO) {
@@ -119,6 +133,7 @@ static int aq_ndev_set_features(struct net_device *ndev,
 		err = aq_nic->aq_hw_ops->hw_set_offload(aq_nic->aq_hw,
 							aq_cfg);
 
+err_exit:
 	return err;
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 44ec47a3d60a..c4a20dca181a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -61,6 +61,11 @@ struct aq_nic_cfg_s {
 #define AQ_NIC_TCVEC2RING(_NIC_, _TC_, _VEC_) \
 	((_TC_) * AQ_CFG_TCS_MAX + (_VEC_))
 
+struct aq_hw_rx_fltrs_s {
+	struct hlist_head     filter_list;
+	u16                   active_filters;
+};
+
 struct aq_nic_s {
 	atomic_t flags;
 	struct aq_vec_s *aq_vec[AQ_CFG_VECS_MAX];
@@ -85,6 +90,7 @@ struct aq_nic_s {
 	struct pci_dev *pdev;
 	unsigned int msix_entry_mask;
 	u32 irqvecs;
+	struct aq_hw_rx_fltrs_s aq_hw_rx_fltrs;
 };
 
 static inline struct device *aq_nic_get_dev(struct aq_nic_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 1d5d6b8df855..c8b44cdb91c1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -19,6 +19,7 @@
 #include "aq_pci_func.h"
 #include "hw_atl/hw_atl_a0.h"
 #include "hw_atl/hw_atl_b0.h"
+#include "aq_filters.h"
 
 static const struct pci_device_id aq_pci_tbl[] = {
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_0001), },
@@ -309,6 +310,7 @@ static void aq_pci_remove(struct pci_dev *pdev)
 	struct aq_nic_s *self = pci_get_drvdata(pdev);
 
 	if (self->ndev) {
+		aq_clear_rxnfc_all_rules(self);
 		if (self->ndev->reg_state == NETREG_REGISTERED)
 			unregister_netdev(self->ndev);
 		aq_nic_free_vectors(self);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index f02592f43fe3..eba1eb78dd59 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -41,7 +41,8 @@
 			NETIF_F_RXHASH |  \
 			NETIF_F_SG |      \
 			NETIF_F_TSO |     \
-			NETIF_F_LRO,      \
+			NETIF_F_LRO |     \
+			NETIF_F_NTUPLE,   \
 	.hw_priv_flags = IFF_UNICAST_FLT, \
 	.flow_control = true,		  \
 	.mtu = HW_ATL_B0_MTU_JUMBO,	  \
-- 
cgit v1.2.3


From a6ed6f2269d64b0eb65e27eac16c9852ff05e50f Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Mon, 12 Nov 2018 15:46:02 +0000
Subject: net: aquantia: add support of L3/L4 ntuple filters

Add support of L3/L4 5-tuple {protocol, src-ip, dst-ip, src-port, dst-port}
filters. Mask is not supported. Src-port and dst-port are only compared for
TCP/UDP/SCTP packets. Both IPv4 and IPv6 are supported.
The supported actions are the drop and the queue assignment.
Due to fixed order of the rules in the NIC, the location 32-39 are
reserved for L3/L4 5-tuple filters. The locations 32 and 36 are
reserved for IPv6 filters.

Examples:
sudo ethtool -N eth0 flow-type ip6 src-ip 2001:db8:0:f101::2 \
dst-ip 2001:db8:0:f101::5 action -1 loc 36

sudo ethtool -N eth0 flow-type udp4 src-ip 10.0.0.4 \
dst-ip 10.0.0.7 src-port 2000 dst-port 2001 action 2 loc 32

Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_filters.c    | 168 ++++++++++++++++++++-
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |  11 ++
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h    |   7 +
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  |  58 +++++++
 .../aquantia/atlantic/hw_atl/hw_atl_utils.h        |  43 ++++++
 5 files changed, 284 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
index 8cb4eaefd6e1..34e2a28d344a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -85,11 +85,46 @@ aq_rule_already_exists(struct aq_nic_s *aq_nic,
 	return false;
 }
 
+static int aq_check_approve_fl3l4(struct aq_nic_s *aq_nic,
+				  struct aq_hw_rx_fltrs_s *rx_fltrs,
+				  struct ethtool_rx_flow_spec *fsp)
+{
+	if (fsp->location < AQ_RX_FIRST_LOC_FL3L4 ||
+	    fsp->location > AQ_RX_LAST_LOC_FL3L4) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: location must be in range [%d, %d]",
+			   AQ_RX_FIRST_LOC_FL3L4,
+			   AQ_RX_LAST_LOC_FL3L4);
+		return -EINVAL;
+	}
+	if (rx_fltrs->fl3l4.is_ipv6 && rx_fltrs->fl3l4.active_ipv4) {
+		rx_fltrs->fl3l4.is_ipv6 = false;
+		netdev_err(aq_nic->ndev,
+			   "ethtool: mixing ipv4 and ipv6 is not allowed");
+		return -EINVAL;
+	} else if (!rx_fltrs->fl3l4.is_ipv6 && rx_fltrs->fl3l4.active_ipv6) {
+		rx_fltrs->fl3l4.is_ipv6 = true;
+		netdev_err(aq_nic->ndev,
+			   "ethtool: mixing ipv4 and ipv6 is not allowed");
+		return -EINVAL;
+	} else if (rx_fltrs->fl3l4.is_ipv6		      &&
+		   fsp->location != AQ_RX_FIRST_LOC_FL3L4 + 4 &&
+		   fsp->location != AQ_RX_FIRST_LOC_FL3L4) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: The specified location for ipv6 must be %d or %d",
+			   AQ_RX_FIRST_LOC_FL3L4, AQ_RX_FIRST_LOC_FL3L4 + 4);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int __must_check
 aq_check_filter(struct aq_nic_s *aq_nic,
 		struct ethtool_rx_flow_spec *fsp)
 {
 	int err = 0;
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
 
 	if (fsp->flow_type & FLOW_EXT) {
 		err = -EOPNOTSUPP;
@@ -103,14 +138,16 @@ aq_check_filter(struct aq_nic_s *aq_nic,
 		case SCTP_V4_FLOW:
 		case IPV4_FLOW:
 		case IP_USER_FLOW:
-			err = -EOPNOTSUPP;
+			rx_fltrs->fl3l4.is_ipv6 = false;
+			err = aq_check_approve_fl3l4(aq_nic, rx_fltrs, fsp);
 			break;
 		case TCP_V6_FLOW:
 		case UDP_V6_FLOW:
 		case SCTP_V6_FLOW:
 		case IPV6_FLOW:
 		case IPV6_USER_FLOW:
-			err = -EOPNOTSUPP;
+			rx_fltrs->fl3l4.is_ipv6 = true;
+			err = aq_check_approve_fl3l4(aq_nic, rx_fltrs, fsp);
 			break;
 		default:
 			netdev_err(aq_nic->ndev,
@@ -156,6 +193,11 @@ aq_rule_is_not_correct(struct aq_nic_s *aq_nic,
 
 	if (!aq_nic) {
 		rule_is_not_correct = true;
+	} else if (fsp->location > AQ_RX_MAX_RXNFC_LOC) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: The specified number %u rule is invalid\n",
+			   fsp->location);
+		rule_is_not_correct = true;
 	} else if (aq_check_filter(aq_nic, fsp)) {
 		rule_is_not_correct = true;
 	} else if (fsp->ring_cookie != RX_CLS_FLOW_DISC) {
@@ -187,6 +229,125 @@ aq_check_rule(struct aq_nic_s *aq_nic,
 	return err;
 }
 
+static int aq_set_data_fl3l4(struct aq_nic_s *aq_nic,
+			     struct aq_rx_filter *aq_rx_fltr,
+			     struct aq_rx_filter_l3l4 *data, bool add)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	const struct ethtool_rx_flow_spec *fsp = &aq_rx_fltr->aq_fsp;
+
+	memset(data, 0, sizeof(*data));
+
+	data->is_ipv6 = rx_fltrs->fl3l4.is_ipv6;
+	data->location = HW_ATL_GET_REG_LOCATION_FL3L4(fsp->location);
+
+	if (!add) {
+		if (!data->is_ipv6)
+			rx_fltrs->fl3l4.active_ipv4 &= ~BIT(data->location);
+		else
+			rx_fltrs->fl3l4.active_ipv6 &=
+				~BIT((data->location) / 4);
+
+		return 0;
+	}
+
+	data->cmd |= HW_ATL_RX_ENABLE_FLTR_L3L4;
+
+	switch (fsp->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_PROT_L4;
+		break;
+	case UDP_V4_FLOW:
+	case UDP_V6_FLOW:
+		data->cmd |= HW_ATL_RX_UDP;
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_PROT_L4;
+		break;
+	case SCTP_V4_FLOW:
+	case SCTP_V6_FLOW:
+		data->cmd |= HW_ATL_RX_SCTP;
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_PROT_L4;
+		break;
+	default:
+		break;
+	}
+
+	if (!data->is_ipv6) {
+		data->ip_src[0] =
+			ntohl(fsp->h_u.tcp_ip4_spec.ip4src);
+		data->ip_dst[0] =
+			ntohl(fsp->h_u.tcp_ip4_spec.ip4dst);
+		rx_fltrs->fl3l4.active_ipv4 |= BIT(data->location);
+	} else {
+		int i;
+
+		rx_fltrs->fl3l4.active_ipv6 |= BIT((data->location) / 4);
+		for (i = 0; i < HW_ATL_RX_CNT_REG_ADDR_IPV6; ++i) {
+			data->ip_dst[i] =
+				ntohl(fsp->h_u.tcp_ip6_spec.ip6dst[i]);
+			data->ip_src[i] =
+				ntohl(fsp->h_u.tcp_ip6_spec.ip6src[i]);
+		}
+		data->cmd |= HW_ATL_RX_ENABLE_L3_IPV6;
+	}
+	if (fsp->flow_type != IP_USER_FLOW &&
+	    fsp->flow_type != IPV6_USER_FLOW) {
+		if (!data->is_ipv6) {
+			data->p_dst =
+				ntohs(fsp->h_u.tcp_ip4_spec.pdst);
+			data->p_src =
+				ntohs(fsp->h_u.tcp_ip4_spec.psrc);
+		} else {
+			data->p_dst =
+				ntohs(fsp->h_u.tcp_ip6_spec.pdst);
+			data->p_src =
+				ntohs(fsp->h_u.tcp_ip6_spec.psrc);
+		}
+	}
+	if (data->ip_src[0] && !data->is_ipv6)
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_SRC_ADDR_L3;
+	if (data->ip_dst[0] && !data->is_ipv6)
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_DEST_ADDR_L3;
+	if (data->p_dst)
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_DEST_PORT_L4;
+	if (data->p_src)
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_SRC_PORT_L4;
+	if (fsp->ring_cookie != RX_CLS_FLOW_DISC) {
+		data->cmd |= HW_ATL_RX_HOST << HW_ATL_RX_ACTION_FL3F4_SHIFT;
+		data->cmd |= fsp->ring_cookie << HW_ATL_RX_QUEUE_FL3L4_SHIFT;
+		data->cmd |= HW_ATL_RX_ENABLE_QUEUE_L3L4;
+	} else {
+		data->cmd |= HW_ATL_RX_DISCARD << HW_ATL_RX_ACTION_FL3F4_SHIFT;
+	}
+
+	return 0;
+}
+
+static int aq_set_fl3l4(struct aq_hw_s *aq_hw,
+			const struct aq_hw_ops *aq_hw_ops,
+			struct aq_rx_filter_l3l4 *data)
+{
+	if (unlikely(!aq_hw_ops->hw_filter_l3l4_set))
+		return -EOPNOTSUPP;
+
+	return aq_hw_ops->hw_filter_l3l4_set(aq_hw, data);
+}
+
+static int aq_add_del_fl3l4(struct aq_nic_s *aq_nic,
+			    struct aq_rx_filter *aq_rx_fltr, bool add)
+{
+	const struct aq_hw_ops *aq_hw_ops = aq_nic->aq_hw_ops;
+	struct aq_hw_s *aq_hw = aq_nic->aq_hw;
+	struct aq_rx_filter_l3l4 data;
+
+	if (unlikely(aq_rx_fltr->aq_fsp.location < AQ_RX_FIRST_LOC_FL3L4 ||
+		     aq_rx_fltr->aq_fsp.location > AQ_RX_LAST_LOC_FL3L4  ||
+		     aq_set_data_fl3l4(aq_nic, aq_rx_fltr, &data, add)))
+		return -EINVAL;
+
+	return aq_set_fl3l4(aq_hw, aq_hw_ops, &data);
+}
+
 static int aq_add_del_rule(struct aq_nic_s *aq_nic,
 			   struct aq_rx_filter *aq_rx_fltr, bool add)
 {
@@ -207,7 +368,8 @@ static int aq_add_del_rule(struct aq_nic_s *aq_nic,
 		case UDP_V6_FLOW:
 		case SCTP_V6_FLOW:
 		case IPV6_USER_FLOW:
-			err = -EOPNOTSUPP;
+			aq_rx_fltr->type = aq_rx_filter_l3l4;
+			err = aq_add_del_fl3l4(aq_nic, aq_rx_fltr, add);
 			break;
 		default:
 			err = -EINVAL;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index a1e70da358ca..edc7d60a0e51 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -18,6 +18,10 @@
 #include "aq_rss.h"
 #include "hw_atl/hw_atl_utils.h"
 
+#define AQ_RX_FIRST_LOC_FL3L4	   32U
+#define AQ_RX_LAST_LOC_FL3L4	   39U
+#define AQ_RX_MAX_RXNFC_LOC	   AQ_RX_LAST_LOC_FL3L4
+
 /* NIC H/W capabilities */
 struct aq_hw_caps_s {
 	u64 hw_features;
@@ -130,6 +134,7 @@ struct aq_hw_s {
 struct aq_ring_s;
 struct aq_ring_param_s;
 struct sk_buff;
+struct aq_rx_filter_l3l4;
 
 struct aq_hw_ops {
 
@@ -183,6 +188,12 @@ struct aq_hw_ops {
 	int (*hw_packet_filter_set)(struct aq_hw_s *self,
 				    unsigned int packet_filter);
 
+	int (*hw_filter_l3l4_set)(struct aq_hw_s *self,
+				  struct aq_rx_filter_l3l4 *data);
+
+	int (*hw_filter_l3l4_clear)(struct aq_hw_s *self,
+				    struct aq_rx_filter_l3l4 *data);
+
 	int (*hw_multicast_list_set)(struct aq_hw_s *self,
 				     u8 ar_mac[AQ_HW_MULTICAST_ADDRESS_MAX]
 				     [ETH_ALEN],
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index c4a20dca181a..d3a087ef4b9f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -61,9 +61,16 @@ struct aq_nic_cfg_s {
 #define AQ_NIC_TCVEC2RING(_NIC_, _TC_, _VEC_) \
 	((_TC_) * AQ_CFG_TCS_MAX + (_VEC_))
 
+struct aq_hw_rx_fl3l4 {
+	u8   active_ipv4;
+	u8   active_ipv6:2;
+	u8 is_ipv6;
+};
+
 struct aq_hw_rx_fltrs_s {
 	struct hlist_head     filter_list;
 	u16                   active_filters;
+	struct aq_hw_rx_fl3l4 fl3l4;
 };
 
 struct aq_nic_s {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index eba1eb78dd59..b4bfe667ef02 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -946,6 +946,63 @@ static int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
+static int hw_atl_b0_hw_fl3l4_clear(struct aq_hw_s *self,
+				    struct aq_rx_filter_l3l4 *data)
+{
+	u8 location = data->location;
+
+	if (!data->is_ipv6) {
+		hw_atl_rpfl3l4_cmd_clear(self, location);
+		hw_atl_rpf_l4_spd_set(self, 0U, location);
+		hw_atl_rpf_l4_dpd_set(self, 0U, location);
+		hw_atl_rpfl3l4_ipv4_src_addr_clear(self, location);
+		hw_atl_rpfl3l4_ipv4_dest_addr_clear(self, location);
+	} else {
+		int i;
+
+		for (i = 0; i < HW_ATL_RX_CNT_REG_ADDR_IPV6; ++i) {
+			hw_atl_rpfl3l4_cmd_clear(self, location + i);
+			hw_atl_rpf_l4_spd_set(self, 0U, location + i);
+			hw_atl_rpf_l4_dpd_set(self, 0U, location + i);
+		}
+		hw_atl_rpfl3l4_ipv6_src_addr_clear(self, location);
+		hw_atl_rpfl3l4_ipv6_dest_addr_clear(self, location);
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
+static int hw_atl_b0_hw_fl3l4_set(struct aq_hw_s *self,
+				  struct aq_rx_filter_l3l4 *data)
+{
+	u8 location = data->location;
+
+	hw_atl_b0_hw_fl3l4_clear(self, data);
+
+	if (data->cmd) {
+		if (!data->is_ipv6) {
+			hw_atl_rpfl3l4_ipv4_dest_addr_set(self,
+							  location,
+							  data->ip_dst[0]);
+			hw_atl_rpfl3l4_ipv4_src_addr_set(self,
+							 location,
+							 data->ip_src[0]);
+		} else {
+			hw_atl_rpfl3l4_ipv6_dest_addr_set(self,
+							  location,
+							  data->ip_dst);
+			hw_atl_rpfl3l4_ipv6_src_addr_set(self,
+							 location,
+							 data->ip_src);
+		}
+	}
+	hw_atl_rpf_l4_dpd_set(self, data->p_dst, location);
+	hw_atl_rpf_l4_spd_set(self, data->p_src, location);
+	hw_atl_rpfl3l4_cmd_set(self, location, data->cmd);
+
+	return aq_hw_err_from_flags(self);
+}
+
 const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_set_mac_address   = hw_atl_b0_hw_mac_addr_set,
 	.hw_init              = hw_atl_b0_hw_init,
@@ -970,6 +1027,7 @@ const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_ring_rx_init             = hw_atl_b0_hw_ring_rx_init,
 	.hw_ring_tx_init             = hw_atl_b0_hw_ring_tx_init,
 	.hw_packet_filter_set        = hw_atl_b0_hw_packet_filter_set,
+	.hw_filter_l3l4_set          = hw_atl_b0_hw_fl3l4_set,
 	.hw_multicast_list_set       = hw_atl_b0_hw_multicast_list_set,
 	.hw_interrupt_moderation_set = hw_atl_b0_hw_interrupt_moderation_set,
 	.hw_rss_set                  = hw_atl_b0_hw_rss_set,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index 3613fca64b58..0da227fc9399 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -240,6 +240,49 @@ struct __packed offload_info {
 	u8 buf[0];
 };
 
+enum hw_atl_rx_action_with_traffic {
+	HW_ATL_RX_DISCARD,
+	HW_ATL_RX_HOST,
+};
+
+struct aq_rx_filter_l3l4 {
+	u32 cmd;
+	u8 location;
+	u32 ip_dst[4];
+	u32 ip_src[4];
+	u16 p_dst;
+	u16 p_src;
+	u8 is_ipv6;
+};
+
+enum hw_atl_rx_protocol_value_l3l4 {
+	HW_ATL_RX_TCP,
+	HW_ATL_RX_UDP,
+	HW_ATL_RX_SCTP,
+	HW_ATL_RX_ICMP
+};
+
+enum hw_atl_rx_ctrl_registers_l3l4 {
+	HW_ATL_RX_ENABLE_MNGMNT_QUEUE_L3L4 = BIT(22),
+	HW_ATL_RX_ENABLE_QUEUE_L3L4        = BIT(23),
+	HW_ATL_RX_ENABLE_ARP_FLTR_L3       = BIT(24),
+	HW_ATL_RX_ENABLE_CMP_PROT_L4       = BIT(25),
+	HW_ATL_RX_ENABLE_CMP_DEST_PORT_L4  = BIT(26),
+	HW_ATL_RX_ENABLE_CMP_SRC_PORT_L4   = BIT(27),
+	HW_ATL_RX_ENABLE_CMP_DEST_ADDR_L3  = BIT(28),
+	HW_ATL_RX_ENABLE_CMP_SRC_ADDR_L3   = BIT(29),
+	HW_ATL_RX_ENABLE_L3_IPV6           = BIT(30),
+	HW_ATL_RX_ENABLE_FLTR_L3L4         = BIT(31)
+};
+
+#define HW_ATL_RX_QUEUE_FL3L4_SHIFT       8U
+#define HW_ATL_RX_ACTION_FL3F4_SHIFT      16U
+
+#define HW_ATL_RX_CNT_REG_ADDR_IPV6       4U
+
+#define HW_ATL_GET_REG_LOCATION_FL3L4(location) \
+	((location) - AQ_RX_FIRST_LOC_FL3L4)
+
 #define HAL_ATLANTIC_UTILS_CHIP_MIPS         0x00000001U
 #define HAL_ATLANTIC_UTILS_CHIP_TPO2         0x00000002U
 #define HAL_ATLANTIC_UTILS_CHIP_RPF2         0x00000004U
-- 
cgit v1.2.3


From 54bcb3d162a884adb91a53cc58412093ad64dc11 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Mon, 12 Nov 2018 15:46:05 +0000
Subject: net: aquantia: add vlan id to rx flow filters

The VLAN filter (VLAN id) is compared against 16 filters.
VLAN id must be accompanied by mask 0xF000. That is to distinguish
VLAN filter from L2 Ethertype filter with UserPriority since both
User Priority and VLAN ID are passed in the same 'vlan' parameter.
Flow type may be any as  it is not matched for VLAN filter.
Due to fixed order of the rules in the NIC, the location 0-15 are
reserved for vlan filters.

Example:
To add a rule that directs packets from VLAN 2001 to queue 5:
ethtool -N <ethX> flow-type ip4 vlan 2001 m 0xF000 action 5 loc 0

Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_common.h |  2 +-
 .../net/ethernet/aquantia/atlantic/aq_filters.c    | 92 +++++++++++++++++++++-
 .../net/ethernet/aquantia/atlantic/aq_filters.h    |  2 +
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |  9 +++
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h    |  5 ++
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  | 37 +++++++++
 .../aquantia/atlantic/hw_atl/hw_atl_utils.h        |  7 ++
 7 files changed, 151 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
index becb578211ed..6b6d1724676e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
@@ -14,7 +14,7 @@
 
 #include <linux/etherdevice.h>
 #include <linux/pci.h>
-
+#include <linux/if_vlan.h>
 #include "ver.h"
 #include "aq_cfg.h"
 #include "aq_utils.h"
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
index 34e2a28d344a..c5240bc487b4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -119,6 +119,29 @@ static int aq_check_approve_fl3l4(struct aq_nic_s *aq_nic,
 	return 0;
 }
 
+static int __must_check
+aq_check_approve_fvlan(struct aq_nic_s *aq_nic,
+		       struct aq_hw_rx_fltrs_s *rx_fltrs,
+		       struct ethtool_rx_flow_spec *fsp)
+{
+	if (fsp->location < AQ_RX_FIRST_LOC_FVLANID ||
+	    fsp->location > AQ_RX_LAST_LOC_FVLANID) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: location must be in range [%d, %d]",
+			   AQ_RX_FIRST_LOC_FVLANID,
+			   AQ_RX_LAST_LOC_FVLANID);
+		return -EINVAL;
+	}
+
+	if (fsp->ring_cookie > aq_nic->aq_nic_cfg.num_rss_queues) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: queue number must be in range [0, %d]",
+			   aq_nic->aq_nic_cfg.num_rss_queues - 1);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int __must_check
 aq_check_filter(struct aq_nic_s *aq_nic,
 		struct ethtool_rx_flow_spec *fsp)
@@ -127,7 +150,14 @@ aq_check_filter(struct aq_nic_s *aq_nic,
 	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
 
 	if (fsp->flow_type & FLOW_EXT) {
-		err = -EOPNOTSUPP;
+		if (be16_to_cpu(fsp->m_ext.vlan_tci) == VLAN_VID_MASK) {
+			err = aq_check_approve_fvlan(aq_nic, rx_fltrs, fsp);
+		} else {
+			netdev_err(aq_nic->ndev,
+				   "ethtool: invalid vlan mask 0x%x specified",
+				   be16_to_cpu(fsp->m_ext.vlan_tci));
+			err = -EINVAL;
+		}
 	} else {
 		switch (fsp->flow_type & ~FLOW_EXT) {
 		case ETHER_FLOW:
@@ -229,6 +259,42 @@ aq_check_rule(struct aq_nic_s *aq_nic,
 	return err;
 }
 
+static int aq_set_data_fvlan(struct aq_nic_s *aq_nic,
+			     struct aq_rx_filter *aq_rx_fltr,
+			     struct aq_rx_filter_vlan *aq_vlans, bool add)
+{
+	const struct ethtool_rx_flow_spec *fsp = &aq_rx_fltr->aq_fsp;
+	int location = fsp->location - AQ_RX_FIRST_LOC_FVLANID;
+
+	memset(&aq_vlans[location], 0, sizeof(aq_vlans[location]));
+
+	if (!add)
+		return 0;
+
+	aq_vlans[location].location = location;
+	aq_vlans[location].vlan_id = be16_to_cpu(fsp->h_ext.vlan_tci)
+				     & VLAN_VID_MASK;
+	aq_vlans[location].queue = fsp->ring_cookie & 0x1FU;
+	aq_vlans[location].enable = 1U;
+	return 0;
+}
+
+static int aq_add_del_fvlan(struct aq_nic_s *aq_nic,
+			    struct aq_rx_filter *aq_rx_fltr, bool add)
+{
+	const struct aq_hw_ops *aq_hw_ops = aq_nic->aq_hw_ops;
+
+	if (unlikely(!aq_hw_ops->hw_filter_vlan_set))
+		return -EOPNOTSUPP;
+
+	aq_set_data_fvlan(aq_nic,
+			  aq_rx_fltr,
+			  aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans,
+			  add);
+
+	return aq_filters_vlans_update(aq_nic);
+}
+
 static int aq_set_data_fl3l4(struct aq_nic_s *aq_nic,
 			     struct aq_rx_filter *aq_rx_fltr,
 			     struct aq_rx_filter_l3l4 *data, bool add)
@@ -354,7 +420,13 @@ static int aq_add_del_rule(struct aq_nic_s *aq_nic,
 	int err = -EINVAL;
 
 	if (aq_rx_fltr->aq_fsp.flow_type & FLOW_EXT) {
-		err = -EOPNOTSUPP;
+		if (be16_to_cpu(aq_rx_fltr->aq_fsp.m_ext.vlan_tci)
+		    == VLAN_VID_MASK) {
+			aq_rx_fltr->type = aq_rx_filter_vlan;
+			err = aq_add_del_fvlan(aq_nic, aq_rx_fltr, add);
+		} else {
+			err = -EINVAL;
+		}
 	} else {
 		switch (aq_rx_fltr->aq_fsp.flow_type & ~FLOW_EXT) {
 		case ETHER_FLOW:
@@ -573,3 +645,19 @@ int aq_reapply_rxnfc_all_rules(struct aq_nic_s *aq_nic)
 err_exit:
 	return err;
 }
+
+int aq_filters_vlans_update(struct aq_nic_s *aq_nic)
+{
+	const struct aq_hw_ops *aq_hw_ops = aq_nic->aq_hw_ops;
+	struct aq_hw_s *aq_hw = aq_nic->aq_hw;
+	int err = 0;
+
+	if (unlikely(!aq_hw_ops->hw_filter_vlan_set))
+		return -EOPNOTSUPP;
+
+	err = aq_hw_ops->hw_filter_vlan_set(aq_hw,
+					    aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans
+					   );
+
+	return err;
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.h b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
index 1f1368b08a5b..bbaf331a55bb 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
@@ -9,6 +9,7 @@
 #include "aq_nic.h"
 
 enum aq_rx_filter_type {
+	aq_rx_filter_vlan,
 	aq_rx_filter_l3l4
 };
 
@@ -27,5 +28,6 @@ int aq_get_rxnfc_all_rules(struct aq_nic_s *aq_nic, struct ethtool_rxnfc *cmd,
 			   u32 *rule_locs);
 int aq_clear_rxnfc_all_rules(struct aq_nic_s *aq_nic);
 int aq_reapply_rxnfc_all_rules(struct aq_nic_s *aq_nic);
+int aq_filters_vlans_update(struct aq_nic_s *aq_nic);
 
 #endif /* AQ_FILTERS_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index edc7d60a0e51..d31474c8a498 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -18,9 +18,13 @@
 #include "aq_rss.h"
 #include "hw_atl/hw_atl_utils.h"
 
+#define AQ_RX_FIRST_LOC_FVLANID     0U
+#define AQ_RX_LAST_LOC_FVLANID	   15U
 #define AQ_RX_FIRST_LOC_FL3L4	   32U
 #define AQ_RX_LAST_LOC_FL3L4	   39U
 #define AQ_RX_MAX_RXNFC_LOC	   AQ_RX_LAST_LOC_FL3L4
+#define AQ_VLAN_MAX_FILTERS   \
+			(AQ_RX_LAST_LOC_FVLANID - AQ_RX_FIRST_LOC_FVLANID + 1U)
 
 /* NIC H/W capabilities */
 struct aq_hw_caps_s {
@@ -194,6 +198,11 @@ struct aq_hw_ops {
 	int (*hw_filter_l3l4_clear)(struct aq_hw_s *self,
 				    struct aq_rx_filter_l3l4 *data);
 
+	int (*hw_filter_vlan_set)(struct aq_hw_s *self,
+				  struct aq_rx_filter_vlan *aq_vlans);
+
+	int (*hw_filter_vlan_ctrl)(struct aq_hw_s *self, bool enable);
+
 	int (*hw_multicast_list_set)(struct aq_hw_s *self,
 				     u8 ar_mac[AQ_HW_MULTICAST_ADDRESS_MAX]
 				     [ETH_ALEN],
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index d3a087ef4b9f..6e971bd7f7b9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -61,6 +61,10 @@ struct aq_nic_cfg_s {
 #define AQ_NIC_TCVEC2RING(_NIC_, _TC_, _VEC_) \
 	((_TC_) * AQ_CFG_TCS_MAX + (_VEC_))
 
+struct aq_hw_rx_fl2 {
+	struct aq_rx_filter_vlan aq_vlans[AQ_VLAN_MAX_FILTERS];
+};
+
 struct aq_hw_rx_fl3l4 {
 	u8   active_ipv4;
 	u8   active_ipv6:2;
@@ -70,6 +74,7 @@ struct aq_hw_rx_fl3l4 {
 struct aq_hw_rx_fltrs_s {
 	struct hlist_head     filter_list;
 	u16                   active_filters;
+	struct aq_hw_rx_fl2   fl2;
 	struct aq_hw_rx_fl3l4 fl3l4;
 };
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index b4bfe667ef02..4ee30fa2e36b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -1003,6 +1003,42 @@ static int hw_atl_b0_hw_fl3l4_set(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
+/**
+ * @brief Set VLAN filter table
+ * @details Configure VLAN filter table to accept (and assign the queue) traffic
+ *  for the particular vlan ids.
+ * Note: use this function under vlan promisc mode not to lost the traffic
+ *
+ * @param aq_hw_s
+ * @param aq_rx_filter_vlan VLAN filter configuration
+ * @return 0 - OK, <0 - error
+ */
+static int hw_atl_b0_hw_vlan_set(struct aq_hw_s *self,
+				 struct aq_rx_filter_vlan *aq_vlans)
+{
+	int i;
+
+	for (i = 0; i < AQ_VLAN_MAX_FILTERS; i++) {
+		hw_atl_rpf_vlan_flr_en_set(self, 0U, i);
+		hw_atl_rpf_vlan_rxq_en_flr_set(self, 0U, i);
+		if (aq_vlans[i].enable) {
+			hw_atl_rpf_vlan_id_flr_set(self,
+						   aq_vlans[i].vlan_id,
+						   i);
+			hw_atl_rpf_vlan_flr_act_set(self, 1U, i);
+			hw_atl_rpf_vlan_flr_en_set(self, 1U, i);
+			if (aq_vlans[i].queue != 0xFF) {
+				hw_atl_rpf_vlan_rxq_flr_set(self,
+							    aq_vlans[i].queue,
+							    i);
+				hw_atl_rpf_vlan_rxq_en_flr_set(self, 1U, i);
+			}
+		}
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
 const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_set_mac_address   = hw_atl_b0_hw_mac_addr_set,
 	.hw_init              = hw_atl_b0_hw_init,
@@ -1028,6 +1064,7 @@ const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_ring_tx_init             = hw_atl_b0_hw_ring_tx_init,
 	.hw_packet_filter_set        = hw_atl_b0_hw_packet_filter_set,
 	.hw_filter_l3l4_set          = hw_atl_b0_hw_fl3l4_set,
+	.hw_filter_vlan_set          = hw_atl_b0_hw_vlan_set,
 	.hw_multicast_list_set       = hw_atl_b0_hw_multicast_list_set,
 	.hw_interrupt_moderation_set = hw_atl_b0_hw_interrupt_moderation_set,
 	.hw_rss_set                  = hw_atl_b0_hw_rss_set,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index 0da227fc9399..3c5b81420361 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -245,6 +245,13 @@ enum hw_atl_rx_action_with_traffic {
 	HW_ATL_RX_HOST,
 };
 
+struct aq_rx_filter_vlan {
+	u8 enable;
+	u8 location;
+	u16 vlan_id;
+	u8 queue;
+};
+
 struct aq_rx_filter_l3l4 {
 	u32 cmd;
 	u8 location;
-- 
cgit v1.2.3


From 9a8cac4b4dae9d5717d4e5f38e0a5ce41de501ee Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Mon, 12 Nov 2018 15:46:07 +0000
Subject: net: aquantia: add ethertype and PCP to rx flow filters

L2 EtherType filters allows to filter packet by EtherType field or
both EtherType and User Priority (PCP) field of 802.1Q.
UserPriority (vlan) parameter must be accompanied by mask 0x1FFF. That
is to distinguish VLAN filter from L2 Ethertype filter with
UserPriority since both User Priority and VLAN ID are passed in the
same 'vlan' parameter.

Example:
To add a filter that directs IP4 packess of priority 3 to queue 3:
ethtool -N <ethX> flow-type ether proto 0x800 vlan 0x600 m 0x1FFF \
action 3 loc 16

Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_filters.c    | 83 ++++++++++++++++++++--
 .../net/ethernet/aquantia/atlantic/aq_filters.h    |  1 +
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |  8 +++
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  | 37 ++++++++++
 .../aquantia/atlantic/hw_atl/hw_atl_utils.h        |  8 +++
 5 files changed, 133 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
index c5240bc487b4..b987c6717af6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -119,6 +119,30 @@ static int aq_check_approve_fl3l4(struct aq_nic_s *aq_nic,
 	return 0;
 }
 
+static int __must_check
+aq_check_approve_fl2(struct aq_nic_s *aq_nic,
+		     struct aq_hw_rx_fltrs_s *rx_fltrs,
+		     struct ethtool_rx_flow_spec *fsp)
+{
+	if (fsp->location < AQ_RX_FIRST_LOC_FETHERT ||
+	    fsp->location > AQ_RX_LAST_LOC_FETHERT) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: location must be in range [%d, %d]",
+			   AQ_RX_FIRST_LOC_FETHERT,
+			   AQ_RX_LAST_LOC_FETHERT);
+		return -EINVAL;
+	}
+
+	if (be16_to_cpu(fsp->m_ext.vlan_tci) == VLAN_PRIO_MASK &&
+	    fsp->m_u.ether_spec.h_proto == 0U) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: proto (ether_type) parameter must be specfied");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int __must_check
 aq_check_approve_fvlan(struct aq_nic_s *aq_nic,
 		       struct aq_hw_rx_fltrs_s *rx_fltrs,
@@ -152,6 +176,8 @@ aq_check_filter(struct aq_nic_s *aq_nic,
 	if (fsp->flow_type & FLOW_EXT) {
 		if (be16_to_cpu(fsp->m_ext.vlan_tci) == VLAN_VID_MASK) {
 			err = aq_check_approve_fvlan(aq_nic, rx_fltrs, fsp);
+		} else if (be16_to_cpu(fsp->m_ext.vlan_tci) == VLAN_PRIO_MASK) {
+			err = aq_check_approve_fl2(aq_nic, rx_fltrs, fsp);
 		} else {
 			netdev_err(aq_nic->ndev,
 				   "ethtool: invalid vlan mask 0x%x specified",
@@ -161,7 +187,7 @@ aq_check_filter(struct aq_nic_s *aq_nic,
 	} else {
 		switch (fsp->flow_type & ~FLOW_EXT) {
 		case ETHER_FLOW:
-			err = -EOPNOTSUPP;
+			err = aq_check_approve_fl2(aq_nic, rx_fltrs, fsp);
 			break;
 		case TCP_V4_FLOW:
 		case UDP_V4_FLOW:
@@ -210,6 +236,10 @@ aq_rule_is_not_support(struct aq_nic_s *aq_nic,
 		netdev_err(aq_nic->ndev,
 			   "ethtool: The specified tos tclass are not supported\n");
 		rule_is_not_support = true;
+	} else if (fsp->flow_type & FLOW_MAC_EXT) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: MAC_EXT is not supported");
+		rule_is_not_support = true;
 	}
 
 	return rule_is_not_support;
@@ -259,6 +289,48 @@ aq_check_rule(struct aq_nic_s *aq_nic,
 	return err;
 }
 
+static void aq_set_data_fl2(struct aq_nic_s *aq_nic,
+			    struct aq_rx_filter *aq_rx_fltr,
+			    struct aq_rx_filter_l2 *data, bool add)
+{
+	const struct ethtool_rx_flow_spec *fsp = &aq_rx_fltr->aq_fsp;
+
+	memset(data, 0, sizeof(*data));
+
+	data->location = fsp->location - AQ_RX_FIRST_LOC_FETHERT;
+
+	if (fsp->ring_cookie != RX_CLS_FLOW_DISC)
+		data->queue = fsp->ring_cookie;
+	else
+		data->queue = -1;
+
+	data->ethertype = be16_to_cpu(fsp->h_u.ether_spec.h_proto);
+	data->user_priority_en = be16_to_cpu(fsp->m_ext.vlan_tci)
+				 == VLAN_PRIO_MASK;
+	data->user_priority = (be16_to_cpu(fsp->h_ext.vlan_tci)
+			       & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+}
+
+static int aq_add_del_fether(struct aq_nic_s *aq_nic,
+			     struct aq_rx_filter *aq_rx_fltr, bool add)
+{
+	struct aq_rx_filter_l2 data;
+	struct aq_hw_s *aq_hw = aq_nic->aq_hw;
+	const struct aq_hw_ops *aq_hw_ops = aq_nic->aq_hw_ops;
+
+	aq_set_data_fl2(aq_nic, aq_rx_fltr, &data, add);
+
+	if (unlikely(!aq_hw_ops->hw_filter_l2_set))
+		return -EOPNOTSUPP;
+	if (unlikely(!aq_hw_ops->hw_filter_l2_clear))
+		return -EOPNOTSUPP;
+
+	if (add)
+		return aq_hw_ops->hw_filter_l2_set(aq_hw, &data);
+	else
+		return aq_hw_ops->hw_filter_l2_clear(aq_hw, &data);
+}
+
 static int aq_set_data_fvlan(struct aq_nic_s *aq_nic,
 			     struct aq_rx_filter *aq_rx_fltr,
 			     struct aq_rx_filter_vlan *aq_vlans, bool add)
@@ -424,13 +496,16 @@ static int aq_add_del_rule(struct aq_nic_s *aq_nic,
 		    == VLAN_VID_MASK) {
 			aq_rx_fltr->type = aq_rx_filter_vlan;
 			err = aq_add_del_fvlan(aq_nic, aq_rx_fltr, add);
-		} else {
-			err = -EINVAL;
+		} else if (be16_to_cpu(aq_rx_fltr->aq_fsp.m_ext.vlan_tci)
+			== VLAN_PRIO_MASK) {
+			aq_rx_fltr->type = aq_rx_filter_ethertype;
+			err = aq_add_del_fether(aq_nic, aq_rx_fltr, add);
 		}
 	} else {
 		switch (aq_rx_fltr->aq_fsp.flow_type & ~FLOW_EXT) {
 		case ETHER_FLOW:
-			err = -EOPNOTSUPP;
+			aq_rx_fltr->type = aq_rx_filter_ethertype;
+			err = aq_add_del_fether(aq_nic, aq_rx_fltr, add);
 			break;
 		case TCP_V4_FLOW:
 		case UDP_V4_FLOW:
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.h b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
index bbaf331a55bb..4c57c26fd3f0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
@@ -9,6 +9,7 @@
 #include "aq_nic.h"
 
 enum aq_rx_filter_type {
+	aq_rx_filter_ethertype,
 	aq_rx_filter_vlan,
 	aq_rx_filter_l3l4
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index d31474c8a498..b0a48956e22f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -20,6 +20,8 @@
 
 #define AQ_RX_FIRST_LOC_FVLANID     0U
 #define AQ_RX_LAST_LOC_FVLANID	   15U
+#define AQ_RX_FIRST_LOC_FETHERT    16U
+#define AQ_RX_LAST_LOC_FETHERT	   31U
 #define AQ_RX_FIRST_LOC_FL3L4	   32U
 #define AQ_RX_LAST_LOC_FL3L4	   39U
 #define AQ_RX_MAX_RXNFC_LOC	   AQ_RX_LAST_LOC_FL3L4
@@ -198,6 +200,12 @@ struct aq_hw_ops {
 	int (*hw_filter_l3l4_clear)(struct aq_hw_s *self,
 				    struct aq_rx_filter_l3l4 *data);
 
+	int (*hw_filter_l2_set)(struct aq_hw_s *self,
+				struct aq_rx_filter_l2 *data);
+
+	int (*hw_filter_l2_clear)(struct aq_hw_s *self,
+				  struct aq_rx_filter_l2 *data);
+
 	int (*hw_filter_vlan_set)(struct aq_hw_s *self,
 				  struct aq_rx_filter_vlan *aq_vlans);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 4ee30fa2e36b..a8777751d09b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -1003,6 +1003,41 @@ static int hw_atl_b0_hw_fl3l4_set(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
+static int hw_atl_b0_hw_fl2_set(struct aq_hw_s *self,
+				struct aq_rx_filter_l2 *data)
+{
+	hw_atl_rpf_etht_flr_en_set(self, 1U, data->location);
+	hw_atl_rpf_etht_flr_set(self, data->ethertype, data->location);
+	hw_atl_rpf_etht_user_priority_en_set(self,
+					     !!data->user_priority_en,
+					     data->location);
+	if (data->user_priority_en)
+		hw_atl_rpf_etht_user_priority_set(self,
+						  data->user_priority,
+						  data->location);
+
+	if (data->queue < 0) {
+		hw_atl_rpf_etht_flr_act_set(self, 0U, data->location);
+		hw_atl_rpf_etht_rx_queue_en_set(self, 0U, data->location);
+	} else {
+		hw_atl_rpf_etht_flr_act_set(self, 1U, data->location);
+		hw_atl_rpf_etht_rx_queue_en_set(self, 1U, data->location);
+		hw_atl_rpf_etht_rx_queue_set(self, data->queue, data->location);
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
+static int hw_atl_b0_hw_fl2_clear(struct aq_hw_s *self,
+				  struct aq_rx_filter_l2 *data)
+{
+	hw_atl_rpf_etht_flr_en_set(self, 0U, data->location);
+	hw_atl_rpf_etht_flr_set(self, 0U, data->location);
+	hw_atl_rpf_etht_user_priority_en_set(self, 0U, data->location);
+
+	return aq_hw_err_from_flags(self);
+}
+
 /**
  * @brief Set VLAN filter table
  * @details Configure VLAN filter table to accept (and assign the queue) traffic
@@ -1063,6 +1098,8 @@ const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_ring_rx_init             = hw_atl_b0_hw_ring_rx_init,
 	.hw_ring_tx_init             = hw_atl_b0_hw_ring_tx_init,
 	.hw_packet_filter_set        = hw_atl_b0_hw_packet_filter_set,
+	.hw_filter_l2_set            = hw_atl_b0_hw_fl2_set,
+	.hw_filter_l2_clear          = hw_atl_b0_hw_fl2_clear,
 	.hw_filter_l3l4_set          = hw_atl_b0_hw_fl3l4_set,
 	.hw_filter_vlan_set          = hw_atl_b0_hw_vlan_set,
 	.hw_multicast_list_set       = hw_atl_b0_hw_multicast_list_set,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index 3c5b81420361..48278e333462 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -252,6 +252,14 @@ struct aq_rx_filter_vlan {
 	u8 queue;
 };
 
+struct aq_rx_filter_l2 {
+	s8 queue;
+	u8 location;
+	u8 user_priority_en;
+	u8 user_priority;
+	u16 ethertype;
+};
+
 struct aq_rx_filter_l3l4 {
 	u32 cmd;
 	u8 location;
-- 
cgit v1.2.3


From 7975d2aff5afb691fbd5db812a2e00bc2ad69f20 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Mon, 12 Nov 2018 15:46:09 +0000
Subject: net: aquantia: add support of rx-vlan-filter offload

Since it uses the same NIC table as rx flow vlan filter therefore
rx-flow vlan filter accepts only vlans that present on the interface
in case of rx-vlan-filter is on.

Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_filters.c    | 138 +++++++++++++++++++++
 .../net/ethernet/aquantia/atlantic/aq_filters.h    |   2 +
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |   1 +
 drivers/net/ethernet/aquantia/atlantic/aq_main.c   |  40 +++++-
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    |   2 -
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h    |   3 +-
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  |  29 ++---
 7 files changed, 197 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
index b987c6717af6..f6145e7473b1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -157,6 +157,14 @@ aq_check_approve_fvlan(struct aq_nic_s *aq_nic,
 		return -EINVAL;
 	}
 
+	if ((aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
+	    (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci),
+		       aq_nic->active_vlans))) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: unknown vlan-id specified");
+		return -EINVAL;
+	}
+
 	if (fsp->ring_cookie > aq_nic->aq_nic_cfg.num_rss_queues) {
 		netdev_err(aq_nic->ndev,
 			   "ethtool: queue number must be in range [0, %d]",
@@ -331,26 +339,108 @@ static int aq_add_del_fether(struct aq_nic_s *aq_nic,
 		return aq_hw_ops->hw_filter_l2_clear(aq_hw, &data);
 }
 
+static bool aq_fvlan_is_busy(struct aq_rx_filter_vlan *aq_vlans, int vlan)
+{
+	int i;
+
+	for (i = 0; i < AQ_VLAN_MAX_FILTERS; ++i) {
+		if (aq_vlans[i].enable &&
+		    aq_vlans[i].queue != AQ_RX_QUEUE_NOT_ASSIGNED &&
+		    aq_vlans[i].vlan_id == vlan) {
+			return true;
+		}
+	}
+
+	return false;
+}
+
+/* Function rebuilds array of vlan filters so that filters with assigned
+ * queue have a precedence over just vlans on the interface.
+ */
+static void aq_fvlan_rebuild(struct aq_nic_s *aq_nic,
+			     unsigned long *active_vlans,
+			     struct aq_rx_filter_vlan *aq_vlans)
+{
+	bool vlan_busy = false;
+	int vlan = -1;
+	int i;
+
+	for (i = 0; i < AQ_VLAN_MAX_FILTERS; ++i) {
+		if (aq_vlans[i].enable &&
+		    aq_vlans[i].queue != AQ_RX_QUEUE_NOT_ASSIGNED)
+			continue;
+		do {
+			vlan = find_next_bit(active_vlans,
+					     VLAN_N_VID,
+					     vlan + 1);
+			if (vlan == VLAN_N_VID) {
+				aq_vlans[i].enable = 0U;
+				aq_vlans[i].queue = AQ_RX_QUEUE_NOT_ASSIGNED;
+				aq_vlans[i].vlan_id = 0;
+				continue;
+			}
+
+			vlan_busy = aq_fvlan_is_busy(aq_vlans, vlan);
+			if (!vlan_busy) {
+				aq_vlans[i].enable = 1U;
+				aq_vlans[i].queue = AQ_RX_QUEUE_NOT_ASSIGNED;
+				aq_vlans[i].vlan_id = vlan;
+			}
+		} while (vlan_busy && vlan != VLAN_N_VID);
+	}
+}
+
 static int aq_set_data_fvlan(struct aq_nic_s *aq_nic,
 			     struct aq_rx_filter *aq_rx_fltr,
 			     struct aq_rx_filter_vlan *aq_vlans, bool add)
 {
 	const struct ethtool_rx_flow_spec *fsp = &aq_rx_fltr->aq_fsp;
 	int location = fsp->location - AQ_RX_FIRST_LOC_FVLANID;
+	int i;
 
 	memset(&aq_vlans[location], 0, sizeof(aq_vlans[location]));
 
 	if (!add)
 		return 0;
 
+	/* remove vlan if it was in table without queue assignment */
+	for (i = 0; i < AQ_VLAN_MAX_FILTERS; ++i) {
+		if (aq_vlans[i].vlan_id ==
+		   (be16_to_cpu(fsp->h_ext.vlan_tci) & VLAN_VID_MASK)) {
+			aq_vlans[i].enable = false;
+		}
+	}
+
 	aq_vlans[location].location = location;
 	aq_vlans[location].vlan_id = be16_to_cpu(fsp->h_ext.vlan_tci)
 				     & VLAN_VID_MASK;
 	aq_vlans[location].queue = fsp->ring_cookie & 0x1FU;
 	aq_vlans[location].enable = 1U;
+
 	return 0;
 }
 
+int aq_del_fvlan_by_vlan(struct aq_nic_s *aq_nic, u16 vlan_id)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct aq_rx_filter *rule = NULL;
+	struct hlist_node *aq_node2;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		if (be16_to_cpu(rule->aq_fsp.h_ext.vlan_tci) == vlan_id)
+			break;
+	}
+	if (rule && be16_to_cpu(rule->aq_fsp.h_ext.vlan_tci) == vlan_id) {
+		struct ethtool_rxnfc cmd;
+
+		cmd.fs.location = rule->aq_fsp.location;
+		return aq_del_rxnfc_rule(aq_nic, &cmd);
+	}
+
+	return -ENOENT;
+}
+
 static int aq_add_del_fvlan(struct aq_nic_s *aq_nic,
 			    struct aq_rx_filter *aq_rx_fltr, bool add)
 {
@@ -725,14 +815,62 @@ int aq_filters_vlans_update(struct aq_nic_s *aq_nic)
 {
 	const struct aq_hw_ops *aq_hw_ops = aq_nic->aq_hw_ops;
 	struct aq_hw_s *aq_hw = aq_nic->aq_hw;
+	int hweight = 0;
 	int err = 0;
+	int i;
 
 	if (unlikely(!aq_hw_ops->hw_filter_vlan_set))
 		return -EOPNOTSUPP;
+	if (unlikely(!aq_hw_ops->hw_filter_vlan_ctrl))
+		return -EOPNOTSUPP;
+
+	aq_fvlan_rebuild(aq_nic, aq_nic->active_vlans,
+			 aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans);
+
+	if (aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		for (i = 0; i < BITS_TO_LONGS(VLAN_N_VID); i++)
+			hweight += hweight_long(aq_nic->active_vlans[i]);
+
+		err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, false);
+		if (err)
+			return err;
+	}
 
 	err = aq_hw_ops->hw_filter_vlan_set(aq_hw,
 					    aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans
 					   );
+	if (err)
+		return err;
+
+	if (aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		if (hweight < AQ_VLAN_MAX_FILTERS)
+			err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, true);
+		/* otherwise left in promiscue mode */
+	}
+
+	return err;
+}
 
+int aq_filters_vlan_offload_off(struct aq_nic_s *aq_nic)
+{
+	const struct aq_hw_ops *aq_hw_ops = aq_nic->aq_hw_ops;
+	struct aq_hw_s *aq_hw = aq_nic->aq_hw;
+	int err = 0;
+
+	memset(aq_nic->active_vlans, 0, sizeof(aq_nic->active_vlans));
+	aq_fvlan_rebuild(aq_nic, aq_nic->active_vlans,
+			 aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans);
+
+	if (unlikely(!aq_hw_ops->hw_filter_vlan_set))
+		return -EOPNOTSUPP;
+	if (unlikely(!aq_hw_ops->hw_filter_vlan_ctrl))
+		return -EOPNOTSUPP;
+
+	err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, false);
+	if (err)
+		return err;
+	err = aq_hw_ops->hw_filter_vlan_set(aq_hw,
+					    aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans
+					   );
 	return err;
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.h b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
index 4c57c26fd3f0..c6a08c6585d5 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
@@ -27,8 +27,10 @@ int aq_del_rxnfc_rule(struct aq_nic_s *aq_nic, const struct ethtool_rxnfc *cmd);
 int aq_get_rxnfc_rule(struct aq_nic_s *aq_nic, struct ethtool_rxnfc *cmd);
 int aq_get_rxnfc_all_rules(struct aq_nic_s *aq_nic, struct ethtool_rxnfc *cmd,
 			   u32 *rule_locs);
+int aq_del_fvlan_by_vlan(struct aq_nic_s *aq_nic, u16 vlan_id);
 int aq_clear_rxnfc_all_rules(struct aq_nic_s *aq_nic);
 int aq_reapply_rxnfc_all_rules(struct aq_nic_s *aq_nic);
 int aq_filters_vlans_update(struct aq_nic_s *aq_nic);
+int aq_filters_vlan_offload_off(struct aq_nic_s *aq_nic);
 
 #endif /* AQ_FILTERS_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index b0a48956e22f..81aab73dc22f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -27,6 +27,7 @@
 #define AQ_RX_MAX_RXNFC_LOC	   AQ_RX_LAST_LOC_FL3L4
 #define AQ_VLAN_MAX_FILTERS   \
 			(AQ_RX_LAST_LOC_FVLANID - AQ_RX_FIRST_LOC_FVLANID + 1U)
+#define AQ_RX_QUEUE_NOT_ASSIGNED   0xFFU
 
 /* NIC H/W capabilities */
 struct aq_hw_caps_s {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index ff15d3388add..2a11c1eefd8f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -114,6 +114,13 @@ static int aq_ndev_set_features(struct net_device *ndev,
 				goto err_exit;
 		}
 	}
+	if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER)) {
+		if (aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) {
+			err = aq_filters_vlan_offload_off(aq_nic);
+			if (unlikely(err))
+				goto err_exit;
+		}
+	}
 
 	aq_cfg->features = features;
 
@@ -162,6 +169,35 @@ static void aq_ndev_set_multicast_settings(struct net_device *ndev)
 	aq_nic_set_multicast_list(aq_nic, ndev);
 }
 
+static int aq_ndo_vlan_rx_add_vid(struct net_device *ndev, __be16 proto,
+				  u16 vid)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+
+	if (!aq_nic->aq_hw_ops->hw_filter_vlan_set)
+		return -EOPNOTSUPP;
+
+	set_bit(vid, aq_nic->active_vlans);
+
+	return aq_filters_vlans_update(aq_nic);
+}
+
+static int aq_ndo_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto,
+				   u16 vid)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+
+	if (!aq_nic->aq_hw_ops->hw_filter_vlan_set)
+		return -EOPNOTSUPP;
+
+	clear_bit(vid, aq_nic->active_vlans);
+
+	if (-ENOENT == aq_del_fvlan_by_vlan(aq_nic, vid))
+		return aq_filters_vlans_update(aq_nic);
+
+	return 0;
+}
+
 static const struct net_device_ops aq_ndev_ops = {
 	.ndo_open = aq_ndev_open,
 	.ndo_stop = aq_ndev_close,
@@ -169,5 +205,7 @@ static const struct net_device_ops aq_ndev_ops = {
 	.ndo_set_rx_mode = aq_ndev_set_multicast_settings,
 	.ndo_change_mtu = aq_ndev_change_mtu,
 	.ndo_set_mac_address = aq_ndev_set_mac_address,
-	.ndo_set_features = aq_ndev_set_features
+	.ndo_set_features = aq_ndev_set_features,
+	.ndo_vlan_rx_add_vid = aq_ndo_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid = aq_ndo_vlan_rx_kill_vid,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 7abdc0952425..279ea58f4a9e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -84,8 +84,6 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 
 	cfg->is_lro = AQ_CFG_IS_LRO_DEF;
 
-	cfg->vlan_id = 0U;
-
 	aq_nic_rss_init(self, cfg->num_rss_queues);
 
 	/*descriptors */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 6e971bd7f7b9..8e34c1e49bf2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -35,7 +35,6 @@ struct aq_nic_cfg_s {
 	u32 mtu;
 	u32 flow_control;
 	u32 link_speed_msk;
-	u32 vlan_id;
 	u32 wol;
 	u16 is_mc_list_enabled;
 	u16 mc_list_count;
@@ -98,6 +97,8 @@ struct aq_nic_s {
 		u32 count;
 		u8 ar[AQ_HW_MULTICAST_ADDRESS_MAX][ETH_ALEN];
 	} mc_list;
+	/* Bitmask of currently assigned vlans from linux */
+	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 
 	struct pci_dev *pdev;
 	unsigned int msix_entry_mask;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index a8777751d09b..6af7d7f0cdca 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -42,7 +42,8 @@
 			NETIF_F_SG |      \
 			NETIF_F_TSO |     \
 			NETIF_F_LRO |     \
-			NETIF_F_NTUPLE,   \
+			NETIF_F_NTUPLE |  \
+			NETIF_F_HW_VLAN_CTAG_FILTER, \
 	.hw_priv_flags = IFF_UNICAST_FLT, \
 	.flow_control = true,		  \
 	.mtu = HW_ATL_B0_MTU_JUMBO,	  \
@@ -320,20 +321,11 @@ static int hw_atl_b0_hw_init_rx_path(struct aq_hw_s *self)
 	hw_atl_rpf_vlan_outer_etht_set(self, 0x88A8U);
 	hw_atl_rpf_vlan_inner_etht_set(self, 0x8100U);
 
-	if (cfg->vlan_id) {
-		hw_atl_rpf_vlan_flr_act_set(self, 1U, 0U);
-		hw_atl_rpf_vlan_id_flr_set(self, 0U, 0U);
-		hw_atl_rpf_vlan_flr_en_set(self, 0U, 0U);
+	hw_atl_rpf_vlan_prom_mode_en_set(self, 1);
 
-		hw_atl_rpf_vlan_accept_untagged_packets_set(self, 1U);
-		hw_atl_rpf_vlan_untagged_act_set(self, 1U);
-
-		hw_atl_rpf_vlan_flr_act_set(self, 1U, 1U);
-		hw_atl_rpf_vlan_id_flr_set(self, cfg->vlan_id, 0U);
-		hw_atl_rpf_vlan_flr_en_set(self, 1U, 1U);
-	} else {
-		hw_atl_rpf_vlan_prom_mode_en_set(self, 1);
-	}
+	// Always accept untagged packets
+	hw_atl_rpf_vlan_accept_untagged_packets_set(self, 1U);
+	hw_atl_rpf_vlan_untagged_act_set(self, 1U);
 
 	/* Rx Interrupts */
 	hw_atl_rdm_rx_desc_wr_wb_irq_en_set(self, 1U);
@@ -1074,6 +1066,14 @@ static int hw_atl_b0_hw_vlan_set(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
+static int hw_atl_b0_hw_vlan_ctrl(struct aq_hw_s *self, bool enable)
+{
+	/* set promisc in case of disabing the vland filter */
+	hw_atl_rpf_vlan_prom_mode_en_set(self, !!!enable);
+
+	return aq_hw_err_from_flags(self);
+}
+
 const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_set_mac_address   = hw_atl_b0_hw_mac_addr_set,
 	.hw_init              = hw_atl_b0_hw_init,
@@ -1102,6 +1102,7 @@ const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_filter_l2_clear          = hw_atl_b0_hw_fl2_clear,
 	.hw_filter_l3l4_set          = hw_atl_b0_hw_fl3l4_set,
 	.hw_filter_vlan_set          = hw_atl_b0_hw_vlan_set,
+	.hw_filter_vlan_ctrl         = hw_atl_b0_hw_vlan_ctrl,
 	.hw_multicast_list_set       = hw_atl_b0_hw_multicast_list_set,
 	.hw_interrupt_moderation_set = hw_atl_b0_hw_interrupt_moderation_set,
 	.hw_rss_set                  = hw_atl_b0_hw_rss_set,
-- 
cgit v1.2.3


From 08990494e59d1ee43f02a687042b7b30ca260bad Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:07 -0800
Subject: nfp: abm: rename qdiscs -> red_qdiscs

Rename qdiscs member to red_qdiscs.  One of following patches will
use the name qdiscs for tracking all qdisc types.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.c  | 11 ++++----
 drivers/net/ethernet/netronome/nfp/abm/main.h  |  4 +--
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 38 ++++++++++++++------------
 3 files changed, 29 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 3d15de0ae271..5e749602989e 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -309,9 +309,10 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 	alink->id = id;
 	alink->parent = TC_H_ROOT;
 	alink->total_queues = alink->vnic->max_rx_rings;
-	alink->qdiscs = kvcalloc(alink->total_queues, sizeof(*alink->qdiscs),
-				 GFP_KERNEL);
-	if (!alink->qdiscs) {
+	alink->red_qdiscs = kvcalloc(alink->total_queues,
+				     sizeof(*alink->red_qdiscs),
+				     GFP_KERNEL);
+	if (!alink->red_qdiscs) {
 		err = -ENOMEM;
 		goto err_free_alink;
 	}
@@ -331,7 +332,7 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 	return 0;
 
 err_free_qdiscs:
-	kvfree(alink->qdiscs);
+	kvfree(alink->red_qdiscs);
 err_free_alink:
 	kfree(alink);
 	return err;
@@ -342,7 +343,7 @@ static void nfp_abm_vnic_free(struct nfp_app *app, struct nfp_net *nn)
 	struct nfp_abm_link *alink = nn->app_priv;
 
 	nfp_abm_kill_reprs(alink->abm, alink);
-	kvfree(alink->qdiscs);
+	kvfree(alink->red_qdiscs);
 	kfree(alink);
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 3774c063e419..a09090004f82 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -82,7 +82,7 @@ struct nfp_red_qdisc {
  * @total_queues:	number of PF queues
  * @parent:	handle of expected parent, i.e. handle of MQ, or TC_H_ROOT
  * @num_qdiscs:	number of currently used qdiscs
- * @qdiscs:	array of qdiscs
+ * @red_qdiscs:	array of qdiscs
  */
 struct nfp_abm_link {
 	struct nfp_abm *abm;
@@ -92,7 +92,7 @@ struct nfp_abm_link {
 	unsigned int total_queues;
 	u32 parent;
 	unsigned int num_qdiscs;
-	struct nfp_red_qdisc *qdiscs;
+	struct nfp_red_qdisc *red_qdiscs;
 };
 
 int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index bb05f9ee0401..abda392880e0 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -18,7 +18,8 @@ __nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
 	int ret;
 
 	ret = nfp_abm_ctrl_set_all_q_lvls(alink, init_val);
-	memset(alink->qdiscs, 0, sizeof(*alink->qdiscs) * alink->num_qdiscs);
+	memset(alink->red_qdiscs, 0,
+	       sizeof(*alink->red_qdiscs) * alink->num_qdiscs);
 
 	alink->parent = handle;
 	alink->num_qdiscs = qs;
@@ -46,7 +47,8 @@ nfp_abm_red_find(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
 	else
 		return -EOPNOTSUPP;
 
-	if (i >= alink->num_qdiscs || opt->handle != alink->qdiscs[i].handle)
+	if (i >= alink->num_qdiscs ||
+	    opt->handle != alink->red_qdiscs[i].handle)
 		return -EOPNOTSUPP;
 
 	return i;
@@ -59,7 +61,7 @@ nfp_abm_red_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
 	unsigned int i;
 
 	for (i = 0; i < alink->num_qdiscs; i++)
-		if (handle == alink->qdiscs[i].handle)
+		if (handle == alink->red_qdiscs[i].handle)
 			break;
 	if (i == alink->num_qdiscs)
 		return;
@@ -68,7 +70,7 @@ nfp_abm_red_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
 		nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
 	} else {
 		nfp_abm_ctrl_set_q_lvl(alink, i, NFP_ABM_LVL_INFINITY);
-		memset(&alink->qdiscs[i], 0, sizeof(*alink->qdiscs));
+		memset(&alink->red_qdiscs[i], 0, sizeof(*alink->red_qdiscs));
 	}
 }
 
@@ -139,37 +141,39 @@ nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 		return -EINVAL;
 	}
 	/* Set the handle to try full clean up, in case IO failed */
-	alink->qdiscs[i].handle = opt->handle;
+	alink->red_qdiscs[i].handle = opt->handle;
 	if (err)
 		goto err_destroy;
 
 	if (opt->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_stats(alink, &alink->qdiscs[i].stats);
+		err = nfp_abm_ctrl_read_stats(alink,
+					      &alink->red_qdiscs[i].stats);
 	else
 		err = nfp_abm_ctrl_read_q_stats(alink, i,
-						&alink->qdiscs[i].stats);
+						&alink->red_qdiscs[i].stats);
 	if (err)
 		goto err_destroy;
 
 	if (opt->parent == TC_H_ROOT)
 		err = nfp_abm_ctrl_read_xstats(alink,
-					       &alink->qdiscs[i].xstats);
+					       &alink->red_qdiscs[i].xstats);
 	else
 		err = nfp_abm_ctrl_read_q_xstats(alink, i,
-						 &alink->qdiscs[i].xstats);
+						 &alink->red_qdiscs[i].xstats);
 	if (err)
 		goto err_destroy;
 
-	alink->qdiscs[i].stats.backlog_pkts = 0;
-	alink->qdiscs[i].stats.backlog_bytes = 0;
+	alink->red_qdiscs[i].stats.backlog_pkts = 0;
+	alink->red_qdiscs[i].stats.backlog_bytes = 0;
 
 	return 0;
 err_destroy:
 	/* If the qdisc keeps on living, but we can't offload undo changes */
 	if (existing) {
-		opt->set.qstats->qlen -= alink->qdiscs[i].stats.backlog_pkts;
+		opt->set.qstats->qlen -=
+			alink->red_qdiscs[i].stats.backlog_pkts;
 		opt->set.qstats->backlog -=
-			alink->qdiscs[i].stats.backlog_bytes;
+			alink->red_qdiscs[i].stats.backlog_bytes;
 	}
 	nfp_abm_red_destroy(netdev, alink, opt->handle);
 
@@ -198,7 +202,7 @@ nfp_abm_red_stats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
 	i = nfp_abm_red_find(alink, opt);
 	if (i < 0)
 		return i;
-	prev_stats = &alink->qdiscs[i].stats;
+	prev_stats = &alink->red_qdiscs[i].stats;
 
 	if (alink->parent == TC_H_ROOT)
 		err = nfp_abm_ctrl_read_stats(alink, &stats);
@@ -224,7 +228,7 @@ nfp_abm_red_xstats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
 	i = nfp_abm_red_find(alink, opt);
 	if (i < 0)
 		return i;
-	prev_xstats = &alink->qdiscs[i].xstats;
+	prev_xstats = &alink->red_qdiscs[i].xstats;
 
 	if (alink->parent == TC_H_ROOT)
 		err = nfp_abm_ctrl_read_xstats(alink, &xstats);
@@ -267,14 +271,14 @@ nfp_abm_mq_stats(struct nfp_abm_link *alink, struct tc_mq_qopt_offload *opt)
 	int err;
 
 	for (i = 0; i < alink->num_qdiscs; i++) {
-		if (alink->qdiscs[i].handle == TC_H_UNSPEC)
+		if (alink->red_qdiscs[i].handle == TC_H_UNSPEC)
 			continue;
 
 		err = nfp_abm_ctrl_read_q_stats(alink, i, &stats);
 		if (err)
 			return err;
 
-		nfp_abm_update_stats(&stats, &alink->qdiscs[i].stats,
+		nfp_abm_update_stats(&stats, &alink->red_qdiscs[i].stats,
 				     &opt->stats);
 	}
 
-- 
cgit v1.2.3


From 6666f545e9e19bb6b4836b6c5215ceba47d58d3e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:08 -0800
Subject: nfp: abm: keep track of all RED thresholds

Instead of writing the threshold out when Qdisc is configured
and not remembering it move to a scheme where we remember all
thresholds.  When configuration changes parse the offloaded
Qdiscs and set thresholds appropriately.

This will help future extensions.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/ctrl.c  | 32 +++++-----
 drivers/net/ethernet/netronome/nfp/abm/main.c  | 25 +++++++-
 drivers/net/ethernet/netronome/nfp/abm/main.h  | 16 ++++-
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 88 +++++++++++++++++++-------
 4 files changed, 120 insertions(+), 41 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index 3c661f422688..564427e8a6e8 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -71,35 +71,37 @@ nfp_abm_ctrl_stat_all(struct nfp_abm_link *alink, const struct nfp_rtsym *sym,
 	return 0;
 }
 
-int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int i, u32 val)
+int __nfp_abm_ctrl_set_q_lvl(struct nfp_abm *abm, unsigned int id, u32 val)
 {
-	struct nfp_cpp *cpp = alink->abm->app->cpp;
+	struct nfp_cpp *cpp = abm->app->cpp;
 	u64 sym_offset;
 	int err;
 
-	sym_offset = (alink->queue_base + i) * NFP_QLVL_STRIDE + NFP_QLVL_THRS;
-	err = __nfp_rtsym_writel(cpp, alink->abm->q_lvls, 4, 0,
-				 sym_offset, val);
+	__clear_bit(id, abm->threshold_undef);
+	if (abm->thresholds[id] == val)
+		return 0;
+
+	sym_offset = id * NFP_QLVL_STRIDE + NFP_QLVL_THRS;
+	err = __nfp_rtsym_writel(cpp, abm->q_lvls, 4, 0, sym_offset, val);
 	if (err) {
-		nfp_err(cpp, "RED offload setting level failed on vNIC %d queue %d\n",
-			alink->id, i);
+		nfp_err(cpp,
+			"RED offload setting level failed on subqueue %d\n",
+			id);
 		return err;
 	}
 
+	abm->thresholds[id] = val;
 	return 0;
 }
 
-int nfp_abm_ctrl_set_all_q_lvls(struct nfp_abm_link *alink, u32 val)
+int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int queue,
+			   u32 val)
 {
-	int i, err;
+	unsigned int threshold;
 
-	for (i = 0; i < alink->vnic->max_rx_rings; i++) {
-		err = nfp_abm_ctrl_set_q_lvl(alink, i, val);
-		if (err)
-			return err;
-	}
+	threshold = alink->queue_base + queue;
 
-	return 0;
+	return __nfp_abm_ctrl_set_q_lvl(alink->abm, threshold, val);
 }
 
 u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int i)
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 5e749602989e..c6ae0ac9a154 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2018 Netronome Systems, Inc. */
 
 #include <linux/bitfield.h>
+#include <linux/bitmap.h>
 #include <linux/etherdevice.h>
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
@@ -399,6 +400,7 @@ static int nfp_abm_init(struct nfp_app *app)
 	struct nfp_pf *pf = app->pf;
 	struct nfp_reprs *reprs;
 	struct nfp_abm *abm;
+	unsigned int i;
 	int err;
 
 	if (!pf->eth_tbl) {
@@ -425,15 +427,28 @@ static int nfp_abm_init(struct nfp_app *app)
 	if (err)
 		goto err_free_abm;
 
+	err = -ENOMEM;
+	abm->num_thresholds = NFP_NET_MAX_RX_RINGS;
+	abm->threshold_undef = bitmap_zalloc(abm->num_thresholds, GFP_KERNEL);
+	if (!abm->threshold_undef)
+		goto err_free_abm;
+
+	abm->thresholds = kvcalloc(abm->num_thresholds,
+				   sizeof(*abm->thresholds), GFP_KERNEL);
+	if (!abm->thresholds)
+		goto err_free_thresh_umap;
+	for (i = 0; i < NFP_NET_MAX_RX_RINGS; i++)
+		__nfp_abm_ctrl_set_q_lvl(abm, i, NFP_ABM_LVL_INFINITY);
+
 	/* We start in legacy mode, make sure advanced queuing is disabled */
 	err = nfp_abm_ctrl_qm_disable(abm);
 	if (err)
-		goto err_free_abm;
+		goto err_free_thresh;
 
 	err = -ENOMEM;
 	reprs = nfp_reprs_alloc(pf->max_data_vnics);
 	if (!reprs)
-		goto err_free_abm;
+		goto err_free_thresh;
 	RCU_INIT_POINTER(app->reprs[NFP_REPR_TYPE_PHYS_PORT], reprs);
 
 	reprs = nfp_reprs_alloc(pf->max_data_vnics);
@@ -445,6 +460,10 @@ static int nfp_abm_init(struct nfp_app *app)
 
 err_free_phys:
 	nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PHYS_PORT);
+err_free_thresh:
+	kvfree(abm->thresholds);
+err_free_thresh_umap:
+	bitmap_free(abm->threshold_undef);
 err_free_abm:
 	kfree(abm);
 	app->priv = NULL;
@@ -458,6 +477,8 @@ static void nfp_abm_clean(struct nfp_app *app)
 	nfp_abm_eswitch_clean_up(abm);
 	nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PF);
 	nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PHYS_PORT);
+	bitmap_free(abm->threshold_undef);
+	kvfree(abm->thresholds);
 	kfree(abm);
 	app->priv = NULL;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index a09090004f82..15732ad7c202 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -20,6 +20,11 @@ struct nfp_net;
  * struct nfp_abm - ABM NIC app structure
  * @app:	back pointer to nfp_app
  * @pf_id:	ID of our PF link
+ *
+ * @thresholds:		current threshold configuration
+ * @threshold_undef:	bitmap of thresholds which have not been set
+ * @num_thresholds:	number of @thresholds and bits in @threshold_undef
+ *
  * @eswitch_mode:	devlink eswitch mode, advanced functions only visible
  *			in switchdev mode
  * @q_lvls:	queue level control area
@@ -28,6 +33,11 @@ struct nfp_net;
 struct nfp_abm {
 	struct nfp_app *app;
 	unsigned int pf_id;
+
+	u32 *thresholds;
+	unsigned long *threshold_undef;
+	size_t num_thresholds;
+
 	enum devlink_eswitch_mode eswitch_mode;
 	const struct nfp_rtsym *q_lvls;
 	const struct nfp_rtsym *qm_stats;
@@ -64,11 +74,13 @@ struct nfp_alink_xstats {
 /**
  * struct nfp_red_qdisc - representation of single RED Qdisc
  * @handle:	handle of currently offloaded RED Qdisc
+ * @threshold:	marking threshold of this Qdisc
  * @stats:	statistics from last refresh
  * @xstats:	base of extended statistics
  */
 struct nfp_red_qdisc {
 	u32 handle;
+	u32 threshold;
 	struct nfp_alink_stats stats;
 	struct nfp_alink_xstats xstats;
 };
@@ -102,8 +114,8 @@ int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 
 void nfp_abm_ctrl_read_params(struct nfp_abm_link *alink);
 int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm);
-int nfp_abm_ctrl_set_all_q_lvls(struct nfp_abm_link *alink, u32 val);
-int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int i,
+int __nfp_abm_ctrl_set_q_lvl(struct nfp_abm *abm, unsigned int id, u32 val);
+int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int queue,
 			   u32 val);
 int nfp_abm_ctrl_read_stats(struct nfp_abm_link *alink,
 			    struct nfp_alink_stats *stats);
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index abda392880e0..abb0a24c7fac 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -7,25 +7,73 @@
 
 #include "../nfpcore/nfp_cpp.h"
 #include "../nfp_app.h"
+#include "../nfp_main.h"
+#include "../nfp_net.h"
 #include "../nfp_port.h"
 #include "main.h"
 
-static int
+static void
+nfp_abm_offload_compile_red(struct nfp_abm_link *alink,
+			    struct nfp_red_qdisc *qdisc, unsigned int queue)
+{
+	if (!qdisc->handle)
+		return;
+
+	nfp_abm_ctrl_set_q_lvl(alink, queue, qdisc->threshold);
+}
+
+static void nfp_abm_offload_compile_one(struct nfp_abm_link *alink)
+{
+	unsigned int i;
+	bool is_mq;
+
+	is_mq = alink->num_qdiscs > 1;
+
+	for (i = 0; i < alink->total_queues; i++) {
+		struct nfp_red_qdisc *next;
+
+		if (is_mq && !alink->red_qdiscs[i].handle)
+			continue;
+
+		next = is_mq ? &alink->red_qdiscs[i] : &alink->red_qdiscs[0];
+		nfp_abm_offload_compile_red(alink, next, i);
+	}
+}
+
+static void nfp_abm_offload_update(struct nfp_abm *abm)
+{
+	struct nfp_abm_link *alink = NULL;
+	struct nfp_pf *pf = abm->app->pf;
+	struct nfp_net *nn;
+	size_t i;
+
+	/* Mark all thresholds as unconfigured */
+	__bitmap_set(abm->threshold_undef, 0, abm->num_thresholds);
+
+	/* Configure all offloads */
+	list_for_each_entry(nn, &pf->vnics, vnic_list) {
+		alink = nn->app_priv;
+		nfp_abm_offload_compile_one(alink);
+	}
+
+	/* Reset the unconfigured thresholds */
+	for (i = 0; i < abm->num_thresholds; i++)
+		if (test_bit(i, abm->threshold_undef))
+			__nfp_abm_ctrl_set_q_lvl(abm, i, NFP_ABM_LVL_INFINITY);
+}
+
+static void
 __nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
 		     u32 handle, unsigned int qs, u32 init_val)
 {
 	struct nfp_port *port = nfp_port_from_netdev(netdev);
-	int ret;
 
-	ret = nfp_abm_ctrl_set_all_q_lvls(alink, init_val);
 	memset(alink->red_qdiscs, 0,
 	       sizeof(*alink->red_qdiscs) * alink->num_qdiscs);
 
 	alink->parent = handle;
 	alink->num_qdiscs = qs;
 	port->tc_offload_cnt = qs;
-
-	return ret;
 }
 
 static void
@@ -66,12 +114,12 @@ nfp_abm_red_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
 	if (i == alink->num_qdiscs)
 		return;
 
-	if (alink->parent == TC_H_ROOT) {
+	if (alink->parent == TC_H_ROOT)
 		nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
-	} else {
-		nfp_abm_ctrl_set_q_lvl(alink, i, NFP_ABM_LVL_INFINITY);
+	else
 		memset(&alink->red_qdiscs[i], 0, sizeof(*alink->red_qdiscs));
-	}
+
+	nfp_abm_offload_update(alink->abm);
 }
 
 static bool
@@ -121,29 +169,19 @@ nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 	}
 
 	if (existing) {
-		if (alink->parent == TC_H_ROOT)
-			err = nfp_abm_ctrl_set_all_q_lvls(alink, opt->set.min);
-		else
-			err = nfp_abm_ctrl_set_q_lvl(alink, i, opt->set.min);
-		if (err)
-			goto err_destroy;
+		nfp_abm_offload_update(alink->abm);
 		return 0;
 	}
 
 	if (opt->parent == TC_H_ROOT) {
 		i = 0;
-		err = __nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 1,
-					   opt->set.min);
+		__nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 1, opt->set.min);
 	} else if (TC_H_MAJ(alink->parent) == TC_H_MAJ(opt->parent)) {
 		i = TC_H_MIN(opt->parent) - 1;
-		err = nfp_abm_ctrl_set_q_lvl(alink, i, opt->set.min);
 	} else {
 		return -EINVAL;
 	}
-	/* Set the handle to try full clean up, in case IO failed */
 	alink->red_qdiscs[i].handle = opt->handle;
-	if (err)
-		goto err_destroy;
 
 	if (opt->parent == TC_H_ROOT)
 		err = nfp_abm_ctrl_read_stats(alink,
@@ -163,9 +201,12 @@ nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 	if (err)
 		goto err_destroy;
 
+	alink->red_qdiscs[i].threshold = opt->set.min;
 	alink->red_qdiscs[i].stats.backlog_pkts = 0;
 	alink->red_qdiscs[i].stats.backlog_bytes = 0;
 
+	nfp_abm_offload_update(alink->abm);
+
 	return 0;
 err_destroy:
 	/* If the qdisc keeps on living, but we can't offload undo changes */
@@ -292,10 +333,13 @@ int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 	case TC_MQ_CREATE:
 		nfp_abm_reset_root(netdev, alink, opt->handle,
 				   alink->total_queues);
+		nfp_abm_offload_update(alink->abm);
 		return 0;
 	case TC_MQ_DESTROY:
-		if (opt->handle == alink->parent)
+		if (opt->handle == alink->parent) {
 			nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
+			nfp_abm_offload_update(alink->abm);
+		}
 		return 0;
 	case TC_MQ_STATS:
 		return nfp_abm_mq_stats(alink, opt);
-- 
cgit v1.2.3


From 4f5681d088ba01f12f63160fa843c915e1ce1358 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:09 -0800
Subject: nfp: abm: track all offload-enabled qdiscs

Allocate an object corresponding to any offloaded qdisc we are
informed about by the kernel.  Not only the qdiscs we have a
chance of offloading.

The count of created objects will be used to decide whether
the ethtool TC offload can be disabled, since otherwise we may
miss destroy commands.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.c  |   2 +
 drivers/net/ethernet/netronome/nfp/abm/main.h  |  23 +++++
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 111 ++++++++++++++++++++++++-
 3 files changed, 132 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index c6ae0ac9a154..35f3a6054569 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -329,6 +329,7 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 
 	nfp_abm_vnic_set_mac(app->pf, abm, nn, id);
 	nfp_abm_ctrl_read_params(alink);
+	INIT_RADIX_TREE(&alink->qdiscs, GFP_KERNEL);
 
 	return 0;
 
@@ -344,6 +345,7 @@ static void nfp_abm_vnic_free(struct nfp_app *app, struct nfp_net *nn)
 	struct nfp_abm_link *alink = nn->app_priv;
 
 	nfp_abm_kill_reprs(alink->abm, alink);
+	WARN(!radix_tree_empty(&alink->qdiscs), "left over qdiscs\n");
 	kvfree(alink->red_qdiscs);
 	kfree(alink);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 15732ad7c202..64cb5ebcf80e 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -5,6 +5,7 @@
 #define __NFP_ABM_H__ 1
 
 #include <linux/bits.h>
+#include <linux/radix-tree.h>
 #include <net/devlink.h>
 #include <net/pkt_cls.h>
 
@@ -71,6 +72,26 @@ struct nfp_alink_xstats {
 	u64 pdrop;
 };
 
+enum nfp_qdisc_type {
+	NFP_QDISC_NONE = 0,
+	NFP_QDISC_MQ,
+	NFP_QDISC_RED,
+};
+
+/**
+ * struct nfp_qdisc - tracked TC Qdisc
+ * @netdev:		netdev on which Qdisc was created
+ * @type:		Qdisc type
+ * @handle:		handle of this Qdisc
+ * @parent_handle:	handle of the parent (unreliable if Qdisc was grafted)
+ */
+struct nfp_qdisc {
+	struct net_device *netdev;
+	enum nfp_qdisc_type type;
+	u32 handle;
+	u32 parent_handle;
+};
+
 /**
  * struct nfp_red_qdisc - representation of single RED Qdisc
  * @handle:	handle of currently offloaded RED Qdisc
@@ -95,6 +116,7 @@ struct nfp_red_qdisc {
  * @parent:	handle of expected parent, i.e. handle of MQ, or TC_H_ROOT
  * @num_qdiscs:	number of currently used qdiscs
  * @red_qdiscs:	array of qdiscs
+ * @qdiscs:	all qdiscs recorded by major part of the handle
  */
 struct nfp_abm_link {
 	struct nfp_abm *abm;
@@ -105,6 +127,7 @@ struct nfp_abm_link {
 	u32 parent;
 	unsigned int num_qdiscs;
 	struct nfp_red_qdisc *red_qdiscs;
+	struct radix_tree_root qdiscs;
 };
 
 int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index abb0a24c7fac..a6f95924656d 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -63,17 +63,97 @@ static void nfp_abm_offload_update(struct nfp_abm *abm)
 }
 
 static void
-__nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
-		     u32 handle, unsigned int qs, u32 init_val)
+nfp_abm_qdisc_free(struct net_device *netdev, struct nfp_abm_link *alink,
+		   struct nfp_qdisc *qdisc)
 {
 	struct nfp_port *port = nfp_port_from_netdev(netdev);
 
+	if (!qdisc)
+		return;
+	WARN_ON(radix_tree_delete(&alink->qdiscs,
+				  TC_H_MAJ(qdisc->handle)) != qdisc);
+	kfree(qdisc);
+
+	port->tc_offload_cnt--;
+}
+
+static struct nfp_qdisc *
+nfp_abm_qdisc_alloc(struct net_device *netdev, struct nfp_abm_link *alink,
+		    enum nfp_qdisc_type type, u32 parent_handle, u32 handle)
+{
+	struct nfp_port *port = nfp_port_from_netdev(netdev);
+	struct nfp_qdisc *qdisc;
+	int err;
+
+	qdisc = kzalloc(sizeof(*qdisc), GFP_KERNEL);
+	if (!qdisc)
+		return NULL;
+
+	qdisc->netdev = netdev;
+	qdisc->type = type;
+	qdisc->parent_handle = parent_handle;
+	qdisc->handle = handle;
+
+	err = radix_tree_insert(&alink->qdiscs, TC_H_MAJ(qdisc->handle), qdisc);
+	if (err) {
+		nfp_err(alink->abm->app->cpp,
+			"Qdisc insertion into radix tree failed: %d\n", err);
+		goto err_free_qdisc;
+	}
+
+	port->tc_offload_cnt++;
+	return qdisc;
+
+err_free_qdisc:
+	kfree(qdisc);
+	return NULL;
+}
+
+static struct nfp_qdisc *
+nfp_abm_qdisc_find(struct nfp_abm_link *alink, u32 handle)
+{
+	return radix_tree_lookup(&alink->qdiscs, TC_H_MAJ(handle));
+}
+
+static int
+nfp_abm_qdisc_replace(struct net_device *netdev, struct nfp_abm_link *alink,
+		      enum nfp_qdisc_type type, u32 parent_handle, u32 handle,
+		      struct nfp_qdisc **qdisc)
+{
+	*qdisc = nfp_abm_qdisc_find(alink, handle);
+	if (*qdisc) {
+		if (WARN_ON((*qdisc)->type != type))
+			return -EINVAL;
+		return 0;
+	}
+
+	*qdisc = nfp_abm_qdisc_alloc(netdev, alink, type, parent_handle,
+				     handle);
+	return *qdisc ? 0 : -ENOMEM;
+}
+
+static void
+nfp_abm_qdisc_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
+		      u32 handle)
+{
+	struct nfp_qdisc *qdisc;
+
+	qdisc = nfp_abm_qdisc_find(alink, handle);
+	if (!qdisc)
+		return;
+
+	nfp_abm_qdisc_free(netdev, alink, qdisc);
+}
+
+static void
+__nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
+		     u32 handle, unsigned int qs, u32 init_val)
+{
 	memset(alink->red_qdiscs, 0,
 	       sizeof(*alink->red_qdiscs) * alink->num_qdiscs);
 
 	alink->parent = handle;
 	alink->num_qdiscs = qs;
-	port->tc_offload_cnt = qs;
 }
 
 static void
@@ -108,6 +188,8 @@ nfp_abm_red_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
 {
 	unsigned int i;
 
+	nfp_abm_qdisc_destroy(netdev, alink, handle);
+
 	for (i = 0; i < alink->num_qdiscs; i++)
 		if (handle == alink->red_qdiscs[i].handle)
 			break;
@@ -157,12 +239,22 @@ static int
 nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 		    struct tc_red_qopt_offload *opt)
 {
+	struct nfp_qdisc *qdisc;
 	bool existing;
 	int i, err;
+	int ret;
+
+	ret = nfp_abm_qdisc_replace(netdev, alink, NFP_QDISC_RED, opt->parent,
+				    opt->handle, &qdisc);
 
 	i = nfp_abm_red_find(alink, opt);
 	existing = i >= 0;
 
+	if (ret) {
+		err = ret;
+		goto err_destroy;
+	}
+
 	if (!nfp_abm_red_check_params(alink, opt)) {
 		err = -EINVAL;
 		goto err_destroy;
@@ -326,6 +418,16 @@ nfp_abm_mq_stats(struct nfp_abm_link *alink, struct tc_mq_qopt_offload *opt)
 	return 0;
 }
 
+static int
+nfp_abm_mq_create(struct net_device *netdev, struct nfp_abm_link *alink,
+		  struct tc_mq_qopt_offload *opt)
+{
+	struct nfp_qdisc *qdisc;
+
+	return nfp_abm_qdisc_replace(netdev, alink, NFP_QDISC_MQ,
+				     TC_H_ROOT, opt->handle, &qdisc);
+}
+
 int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 			struct tc_mq_qopt_offload *opt)
 {
@@ -334,8 +436,9 @@ int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 		nfp_abm_reset_root(netdev, alink, opt->handle,
 				   alink->total_queues);
 		nfp_abm_offload_update(alink->abm);
-		return 0;
+		return nfp_abm_mq_create(netdev, alink, opt);
 	case TC_MQ_DESTROY:
+		nfp_abm_qdisc_destroy(netdev, alink, opt->handle);
 		if (opt->handle == alink->parent) {
 			nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
 			nfp_abm_offload_update(alink->abm);
-- 
cgit v1.2.3


From 98b0e5f6842a9982a793f0837b1bd1495542a3d8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:10 -0800
Subject: net: sched: provide notification for graft on root

Drivers are currently not notified when a Qdisc is grafted as root.
This requires special casing Qdiscs added with parent = TC_H_ROOT in
the driver.  Also there is no notification sent to the driver when
an existing Qdisc is grafted as root.

Add this very simple notifications, drivers should now be able to
track their Qdisc tree fully.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  1 +
 include/net/pkt_cls.h     | 10 ++++++++++
 net/sched/sch_api.c       | 17 +++++++++++++++++
 3 files changed, 28 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 487fa5e0e165..97b4233120e4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -845,6 +845,7 @@ enum tc_setup_type {
 	TC_SETUP_QDISC_PRIO,
 	TC_SETUP_QDISC_MQ,
 	TC_SETUP_QDISC_ETF,
+	TC_SETUP_ROOT_QDISC,
 };
 
 /* These structures hold the attributes of bpf state that are being passed
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index f6c0cd29dea4..fa31d034231d 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -889,4 +889,14 @@ struct tc_prio_qopt_offload {
 	};
 };
 
+enum tc_root_command {
+	TC_ROOT_GRAFT,
+};
+
+struct tc_root_qopt_offload {
+	enum tc_root_command command;
+	u32 handle;
+	bool ingress;
+};
+
 #endif
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index f55bc50cd0a9..9c88cec7e8a2 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -860,6 +860,21 @@ void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch,
 }
 EXPORT_SYMBOL(qdisc_offload_graft_helper);
 
+static void qdisc_offload_graft_root(struct net_device *dev,
+				     struct Qdisc *new, struct Qdisc *old,
+				     struct netlink_ext_ack *extack)
+{
+	struct tc_root_qopt_offload graft_offload = {
+		.command	= TC_ROOT_GRAFT,
+		.handle		= new ? new->handle : 0,
+		.ingress	= (new && new->flags & TCQ_F_INGRESS) ||
+				  (old && old->flags & TCQ_F_INGRESS),
+	};
+
+	qdisc_offload_graft_helper(dev, NULL, new, old,
+				   TC_SETUP_ROOT_QDISC, &graft_offload, extack);
+}
+
 static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 			 u32 portid, u32 seq, u16 flags, int event)
 {
@@ -1026,6 +1041,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 		if (dev->flags & IFF_UP)
 			dev_deactivate(dev);
 
+		qdisc_offload_graft_root(dev, new, old, extack);
+
 		if (new && new->ops->attach)
 			goto skip;
 
-- 
cgit v1.2.3


From 1853125889a397725420e8ef003502141269d08f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:11 -0800
Subject: nfp: abm: remember which Qdisc is root

Keep track of which Qdisc is currently root.  We need to implement
TC_SETUP_ROOT_QDISC handling, and for completeness also clear the
root Qdisc pointer when it's freed.  TC_SETUP_ROOT_QDISC isn't always
sent when device is dismantled.

Remembering the root Qdisc will allow us to build the entire hierarchy
in following patches.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.c  |  2 ++
 drivers/net/ethernet/netronome/nfp/abm/main.h  |  4 ++++
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 13 +++++++++++++
 3 files changed, 19 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 35f3a6054569..da5394886a78 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -37,6 +37,8 @@ nfp_abm_setup_tc(struct nfp_app *app, struct net_device *netdev,
 		return -EOPNOTSUPP;
 
 	switch (type) {
+	case TC_SETUP_ROOT_QDISC:
+		return nfp_abm_setup_root(netdev, repr->app_priv, type_data);
 	case TC_SETUP_QDISC_MQ:
 		return nfp_abm_setup_tc_mq(netdev, repr->app_priv, type_data);
 	case TC_SETUP_QDISC_RED:
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 64cb5ebcf80e..48d519989886 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -116,6 +116,7 @@ struct nfp_red_qdisc {
  * @parent:	handle of expected parent, i.e. handle of MQ, or TC_H_ROOT
  * @num_qdiscs:	number of currently used qdiscs
  * @red_qdiscs:	array of qdiscs
+ * @root_qdisc:	pointer to the current root of the Qdisc hierarchy
  * @qdiscs:	all qdiscs recorded by major part of the handle
  */
 struct nfp_abm_link {
@@ -127,9 +128,12 @@ struct nfp_abm_link {
 	u32 parent;
 	unsigned int num_qdiscs;
 	struct nfp_red_qdisc *red_qdiscs;
+	struct nfp_qdisc *root_qdisc;
 	struct radix_tree_root qdiscs;
 };
 
+int nfp_abm_setup_root(struct net_device *netdev, struct nfp_abm_link *alink,
+		       struct tc_root_qopt_offload *opt);
 int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
 			 struct tc_red_qopt_offload *opt);
 int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index a6f95924656d..ba6ce2d1eda2 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -143,6 +143,9 @@ nfp_abm_qdisc_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
 		return;
 
 	nfp_abm_qdisc_free(netdev, alink, qdisc);
+
+	if (alink->root_qdisc == qdisc)
+		alink->root_qdisc = NULL;
 }
 
 static void
@@ -450,3 +453,13 @@ int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 		return -EOPNOTSUPP;
 	}
 }
+
+int nfp_abm_setup_root(struct net_device *netdev, struct nfp_abm_link *alink,
+		       struct tc_root_qopt_offload *opt)
+{
+	if (opt->ingress)
+		return -EOPNOTSUPP;
+	alink->root_qdisc = nfp_abm_qdisc_find(alink, opt->handle);
+
+	return 0;
+}
-- 
cgit v1.2.3


From aee7539c5876cc65f5ffa88615a88eb724358cc1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:12 -0800
Subject: nfp: abm: allocate Qdisc child table

To keep track of Qdisc hierarchy allocate a table for children
for each Qdisc.  RED Qdisc can only have one child.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.h  |  6 ++++++
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 25 ++++++++++++++++++-------
 2 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 48d519989886..adffa36981e0 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -84,12 +84,18 @@ enum nfp_qdisc_type {
  * @type:		Qdisc type
  * @handle:		handle of this Qdisc
  * @parent_handle:	handle of the parent (unreliable if Qdisc was grafted)
+ * @use_cnt:		number of attachment points in the hierarchy
+ * @num_children:	current size of the @children array
+ * @children:		pointers to children
  */
 struct nfp_qdisc {
 	struct net_device *netdev;
 	enum nfp_qdisc_type type;
 	u32 handle;
 	u32 parent_handle;
+	unsigned int use_cnt;
+	unsigned int num_children;
+	struct nfp_qdisc **children;
 };
 
 /**
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index ba6ce2d1eda2..3ecb63060429 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -72,6 +72,8 @@ nfp_abm_qdisc_free(struct net_device *netdev, struct nfp_abm_link *alink,
 		return;
 	WARN_ON(radix_tree_delete(&alink->qdiscs,
 				  TC_H_MAJ(qdisc->handle)) != qdisc);
+
+	kfree(qdisc->children);
 	kfree(qdisc);
 
 	port->tc_offload_cnt--;
@@ -79,7 +81,8 @@ nfp_abm_qdisc_free(struct net_device *netdev, struct nfp_abm_link *alink,
 
 static struct nfp_qdisc *
 nfp_abm_qdisc_alloc(struct net_device *netdev, struct nfp_abm_link *alink,
-		    enum nfp_qdisc_type type, u32 parent_handle, u32 handle)
+		    enum nfp_qdisc_type type, u32 parent_handle, u32 handle,
+		    unsigned int children)
 {
 	struct nfp_port *port = nfp_port_from_netdev(netdev);
 	struct nfp_qdisc *qdisc;
@@ -89,21 +92,28 @@ nfp_abm_qdisc_alloc(struct net_device *netdev, struct nfp_abm_link *alink,
 	if (!qdisc)
 		return NULL;
 
+	qdisc->children = kcalloc(children, sizeof(void *), GFP_KERNEL);
+	if (!qdisc->children)
+		goto err_free_qdisc;
+
 	qdisc->netdev = netdev;
 	qdisc->type = type;
 	qdisc->parent_handle = parent_handle;
 	qdisc->handle = handle;
+	qdisc->num_children = children;
 
 	err = radix_tree_insert(&alink->qdiscs, TC_H_MAJ(qdisc->handle), qdisc);
 	if (err) {
 		nfp_err(alink->abm->app->cpp,
 			"Qdisc insertion into radix tree failed: %d\n", err);
-		goto err_free_qdisc;
+		goto err_free_child_tbl;
 	}
 
 	port->tc_offload_cnt++;
 	return qdisc;
 
+err_free_child_tbl:
+	kfree(qdisc->children);
 err_free_qdisc:
 	kfree(qdisc);
 	return NULL;
@@ -118,7 +128,7 @@ nfp_abm_qdisc_find(struct nfp_abm_link *alink, u32 handle)
 static int
 nfp_abm_qdisc_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 		      enum nfp_qdisc_type type, u32 parent_handle, u32 handle,
-		      struct nfp_qdisc **qdisc)
+		      unsigned int children, struct nfp_qdisc **qdisc)
 {
 	*qdisc = nfp_abm_qdisc_find(alink, handle);
 	if (*qdisc) {
@@ -127,8 +137,8 @@ nfp_abm_qdisc_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 		return 0;
 	}
 
-	*qdisc = nfp_abm_qdisc_alloc(netdev, alink, type, parent_handle,
-				     handle);
+	*qdisc = nfp_abm_qdisc_alloc(netdev, alink, type, parent_handle, handle,
+				     children);
 	return *qdisc ? 0 : -ENOMEM;
 }
 
@@ -248,7 +258,7 @@ nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 	int ret;
 
 	ret = nfp_abm_qdisc_replace(netdev, alink, NFP_QDISC_RED, opt->parent,
-				    opt->handle, &qdisc);
+				    opt->handle, 1, &qdisc);
 
 	i = nfp_abm_red_find(alink, opt);
 	existing = i >= 0;
@@ -428,7 +438,8 @@ nfp_abm_mq_create(struct net_device *netdev, struct nfp_abm_link *alink,
 	struct nfp_qdisc *qdisc;
 
 	return nfp_abm_qdisc_replace(netdev, alink, NFP_QDISC_MQ,
-				     TC_H_ROOT, opt->handle, &qdisc);
+				     TC_H_ROOT, opt->handle,
+				     alink->total_queues, &qdisc);
 }
 
 int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
-- 
cgit v1.2.3


From bf2a752bea027ec5a0bc5b4042d78b32715ad198 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:13 -0800
Subject: net: sched: red: offload a graft notification

Drivers offloading Qdiscs should have reasonable certainty
the offloaded behaviour matches the SW path.  This is impossible
if the driver does not know about all Qdiscs or when Qdiscs move
and are reused.  Send a graft notification from RED.  The drivers
are expected to simply stop offloading the Qdisc, if a non-standard
child is ever grafted onto it.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h |  2 ++
 net/sched/sch_red.c   | 17 +++++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index fa31d034231d..01f2802b7aee 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -834,6 +834,7 @@ enum tc_red_command {
 	TC_RED_DESTROY,
 	TC_RED_STATS,
 	TC_RED_XSTATS,
+	TC_RED_GRAFT,
 };
 
 struct tc_red_qopt_offload_params {
@@ -853,6 +854,7 @@ struct tc_red_qopt_offload {
 		struct tc_red_qopt_offload_params set;
 		struct tc_qopt_offload_stats stats;
 		struct red_stats *xstats;
+		u32 child_handle;
 	};
 };
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index a1d08bdd9357..4b5ca172ee2d 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -367,6 +367,21 @@ static int red_dump_class(struct Qdisc *sch, unsigned long cl,
 	return 0;
 }
 
+static void red_graft_offload(struct Qdisc *sch,
+			      struct Qdisc *new, struct Qdisc *old,
+			      struct netlink_ext_ack *extack)
+{
+	struct tc_red_qopt_offload graft_offload = {
+		.handle		= sch->handle,
+		.parent		= sch->parent,
+		.child_handle	= new->handle,
+		.command	= TC_RED_GRAFT,
+	};
+
+	qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, old,
+				   TC_SETUP_QDISC_RED, &graft_offload, extack);
+}
+
 static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 		     struct Qdisc **old, struct netlink_ext_ack *extack)
 {
@@ -376,6 +391,8 @@ static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 		new = &noop_qdisc;
 
 	*old = qdisc_replace(sch, new, &q->qdisc);
+
+	red_graft_offload(sch, new, *old, extack);
 	return 0;
 }
 
-- 
cgit v1.2.3


From d577a3d279c3c60adabdcc4b7a414d37dea7b8b2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:14 -0800
Subject: net: sched: mq: offload a graft notification

Drivers offloading Qdiscs should have reasonable certainty
the offloaded behaviour matches the SW path.  This is impossible
if the driver does not know about all Qdiscs or when Qdiscs move
and are reused.  Send a graft notification from MQ.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h | 11 ++++++++++-
 net/sched/sch_mq.c    |  9 +++++++++
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 01f2802b7aee..5d31820b7e80 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -821,12 +821,21 @@ enum tc_mq_command {
 	TC_MQ_CREATE,
 	TC_MQ_DESTROY,
 	TC_MQ_STATS,
+	TC_MQ_GRAFT,
+};
+
+struct tc_mq_opt_offload_graft_params {
+	unsigned long queue;
+	u32 child_handle;
 };
 
 struct tc_mq_qopt_offload {
 	enum tc_mq_command command;
 	u32 handle;
-	struct tc_qopt_offload_stats stats;
+	union {
+		struct tc_qopt_offload_stats stats;
+		struct tc_mq_opt_offload_graft_params graft_params;
+	};
 };
 
 enum tc_red_command {
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 1db5c1bf6ddd..203659bc3906 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -193,6 +193,7 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 		    struct Qdisc **old, struct netlink_ext_ack *extack)
 {
 	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
+	struct tc_mq_qopt_offload graft_offload;
 	struct net_device *dev = qdisc_dev(sch);
 
 	if (dev->flags & IFF_UP)
@@ -203,6 +204,14 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	if (dev->flags & IFF_UP)
 		dev_activate(dev);
+
+	graft_offload.handle = sch->handle;
+	graft_offload.graft_params.queue = cl - 1;
+	graft_offload.graft_params.child_handle = new ? new->handle : 0;
+	graft_offload.command = TC_MQ_GRAFT;
+
+	qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old,
+				   TC_SETUP_QDISC_MQ, &graft_offload, extack);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 6b8417b7e6f5e4da2bfb4dd087d5f7f082d077de Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:15 -0800
Subject: nfp: abm: build full Qdisc hierarchy based on graft notifications

Using graft notifications recreate in the driver the full Qdisc
hierarchy.  Keep track of how many times each Qdisc is attached
to the hierarchy to make sure we don't offload Qdiscs which are
attached multiple times (device queues can't be shared).  For
graft events of Qdiscs we don't know exist make the child as
invalid/untracked.

Note that MQ Qdisc doesn't send destruction events reliably when
device is dismantled, so we need to manually clean out the
children otherwise we'd think Qdiscs which are still in use
are getting freed.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.h  |   2 +
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 105 +++++++++++++++++++++++++
 2 files changed, 107 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index adffa36981e0..daca93e90099 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -78,6 +78,8 @@ enum nfp_qdisc_type {
 	NFP_QDISC_RED,
 };
 
+#define NFP_QDISC_UNTRACKED	((struct nfp_qdisc *)1UL)
+
 /**
  * struct nfp_qdisc - tracked TC Qdisc
  * @netdev:		netdev on which Qdisc was created
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index 3ecb63060429..151d2dafbc76 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (C) 2018 Netronome Systems, Inc. */
 
+#include <linux/rtnetlink.h>
 #include <net/pkt_cls.h>
 #include <net/pkt_sched.h>
 #include <net/red.h>
@@ -12,6 +13,66 @@
 #include "../nfp_port.h"
 #include "main.h"
 
+static bool nfp_abm_qdisc_child_valid(struct nfp_qdisc *qdisc, unsigned int id)
+{
+	return qdisc->children[id] &&
+	       qdisc->children[id] != NFP_QDISC_UNTRACKED;
+}
+
+static void *nfp_abm_qdisc_tree_deref_slot(void __rcu **slot)
+{
+	return rtnl_dereference(*slot);
+}
+
+static void
+nfp_abm_qdisc_unlink_children(struct nfp_qdisc *qdisc,
+			      unsigned int start, unsigned int end)
+{
+	unsigned int i;
+
+	for (i = start; i < end; i++)
+		if (nfp_abm_qdisc_child_valid(qdisc, i)) {
+			qdisc->children[i]->use_cnt--;
+			qdisc->children[i] = NULL;
+		}
+}
+
+static void
+nfp_abm_qdisc_clear_mq(struct net_device *netdev, struct nfp_abm_link *alink,
+		       struct nfp_qdisc *qdisc)
+{
+	struct radix_tree_iter iter;
+	unsigned int mq_refs = 0;
+	void __rcu **slot;
+
+	if (!qdisc->use_cnt)
+		return;
+	/* MQ doesn't notify well on destruction, we need special handling of
+	 * MQ's children.
+	 */
+	if (qdisc->type == NFP_QDISC_MQ &&
+	    qdisc == alink->root_qdisc &&
+	    netdev->reg_state == NETREG_UNREGISTERING)
+		return;
+
+	/* Count refs held by MQ instances and clear pointers */
+	radix_tree_for_each_slot(slot, &alink->qdiscs, &iter, 0) {
+		struct nfp_qdisc *mq = nfp_abm_qdisc_tree_deref_slot(slot);
+		unsigned int i;
+
+		if (mq->type != NFP_QDISC_MQ || mq->netdev != netdev)
+			continue;
+		for (i = 0; i < mq->num_children; i++)
+			if (mq->children[i] == qdisc) {
+				mq->children[i] = NULL;
+				mq_refs++;
+			}
+	}
+
+	WARN(qdisc->use_cnt != mq_refs, "non-zero qdisc use count: %d (- %d)\n",
+	     qdisc->use_cnt, mq_refs);
+}
+
 static void
 nfp_abm_offload_compile_red(struct nfp_abm_link *alink,
 			    struct nfp_red_qdisc *qdisc, unsigned int queue)
@@ -70,6 +131,7 @@ nfp_abm_qdisc_free(struct net_device *netdev, struct nfp_abm_link *alink,
 
 	if (!qdisc)
 		return;
+	nfp_abm_qdisc_clear_mq(netdev, alink, qdisc);
 	WARN_ON(radix_tree_delete(&alink->qdiscs,
 				  TC_H_MAJ(qdisc->handle)) != qdisc);
 
@@ -152,12 +214,44 @@ nfp_abm_qdisc_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
 	if (!qdisc)
 		return;
 
+	/* We don't get TC_SETUP_ROOT_QDISC w/ MQ when netdev is unregistered */
+	if (alink->root_qdisc == qdisc)
+		qdisc->use_cnt--;
+
+	nfp_abm_qdisc_unlink_children(qdisc, 0, qdisc->num_children);
 	nfp_abm_qdisc_free(netdev, alink, qdisc);
 
 	if (alink->root_qdisc == qdisc)
 		alink->root_qdisc = NULL;
 }
 
+static int
+nfp_abm_qdisc_graft(struct nfp_abm_link *alink, u32 handle, u32 child_handle,
+		    unsigned int id)
+{
+	struct nfp_qdisc *parent, *child;
+
+	parent = nfp_abm_qdisc_find(alink, handle);
+	if (!parent)
+		return 0;
+
+	if (WARN(id >= parent->num_children,
+		 "graft child out of bound %d >= %d\n",
+		 id, parent->num_children))
+		return -EINVAL;
+
+	nfp_abm_qdisc_unlink_children(parent, id, id + 1);
+
+	child = nfp_abm_qdisc_find(alink, child_handle);
+	if (child)
+		child->use_cnt++;
+	else
+		child = NFP_QDISC_UNTRACKED;
+	parent->children[id] = child;
+
+	return 0;
+}
+
 static void
 __nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
 		     u32 handle, unsigned int qs, u32 init_val)
@@ -404,6 +498,9 @@ int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
 		return nfp_abm_red_stats(alink, opt);
 	case TC_RED_XSTATS:
 		return nfp_abm_red_xstats(alink, opt);
+	case TC_RED_GRAFT:
+		return nfp_abm_qdisc_graft(alink, opt->handle,
+					   opt->child_handle, 0);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -460,6 +557,10 @@ int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 		return 0;
 	case TC_MQ_STATS:
 		return nfp_abm_mq_stats(alink, opt);
+	case TC_MQ_GRAFT:
+		return nfp_abm_qdisc_graft(alink, opt->handle,
+					   opt->graft_params.child_handle,
+					   opt->graft_params.queue);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -470,7 +571,11 @@ int nfp_abm_setup_root(struct net_device *netdev, struct nfp_abm_link *alink,
 {
 	if (opt->ingress)
 		return -EOPNOTSUPP;
+	if (alink->root_qdisc)
+		alink->root_qdisc->use_cnt--;
 	alink->root_qdisc = nfp_abm_qdisc_find(alink, opt->handle);
+	if (alink->root_qdisc)
+		alink->root_qdisc->use_cnt++;
 
 	return 0;
 }
-- 
cgit v1.2.3


From c0b7490b19f6ab43c3c4ef82c8d5ed3bf19a8913 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:16 -0800
Subject: net: sched: red: notify drivers about RED's limit parameter

RED qdisc's limit parameter changes the behaviour of the qdisc,
for instance if it's set to 0 qdisc will drop all the packets.

When replace operation happens and parameter is set to non-0
a new fifo qdisc will be instantiated and replace the old child
qdisc which will be destroyed.

Drivers need to know the parameter, even if they don't impose
the actual limit to be able to reliably reconstruct the Qdisc
hierarchy.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h | 1 +
 net/sched/sch_red.c   | 1 +
 2 files changed, 2 insertions(+)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 5d31820b7e80..c497ada7f591 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -850,6 +850,7 @@ struct tc_red_qopt_offload_params {
 	u32 min;
 	u32 max;
 	u32 probability;
+	u32 limit;
 	bool is_ecn;
 	bool is_harddrop;
 	struct gnet_stats_queue *qstats;
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 4b5ca172ee2d..9df9942340ea 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -166,6 +166,7 @@ static int red_offload(struct Qdisc *sch, bool enable)
 		opt.set.min = q->parms.qth_min >> q->parms.Wlog;
 		opt.set.max = q->parms.qth_max >> q->parms.Wlog;
 		opt.set.probability = q->parms.max_P;
+		opt.set.limit = q->limit;
 		opt.set.is_ecn = red_use_ecn(q);
 		opt.set.is_harddrop = red_use_harddrop(q);
 		opt.set.qstats = &sch->qstats;
-- 
cgit v1.2.3


From 6c5dbda0d4df000cff88d8bbb382de3d2e034d8f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:17 -0800
Subject: nfp: abm: reset RED's child based on limit

RED qdisc will replace its child Qdisc with a new FIFO queue if
it is reconfigured and the limit parameter is not 0.

This means that when it's created with limit of 0 it will have no FIFO,
and all packets will be dropped.  If it's changed and limit is specified
it will loose its existing child (implicit graft).  Make sure we mark
RED Qdisc child as NFP_QDISC_UNTRACKED if its not the expected FIFO.

nfp_abm_qdisc_replace() will return 1 if Qdisc already existed.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 27 +++++++++++++++++++++-----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index 151d2dafbc76..1b3c0b5b52bf 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -196,7 +196,7 @@ nfp_abm_qdisc_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 	if (*qdisc) {
 		if (WARN_ON((*qdisc)->type != type))
 			return -EINVAL;
-		return 0;
+		return 1;
 	}
 
 	*qdisc = nfp_abm_qdisc_alloc(netdev, alink, type, parent_handle, handle,
@@ -357,11 +357,24 @@ nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 	i = nfp_abm_red_find(alink, opt);
 	existing = i >= 0;
 
-	if (ret) {
+	if (ret < 0) {
 		err = ret;
 		goto err_destroy;
 	}
 
+	/* If limit != 0 child gets reset */
+	if (opt->set.limit) {
+		if (nfp_abm_qdisc_child_valid(qdisc, 0))
+			qdisc->children[0]->use_cnt--;
+		qdisc->children[0] = NULL;
+	} else {
+		/* Qdisc was just allocated without a limit will use noop_qdisc,
+		 * i.e. a block hole.
+		 */
+		if (!ret)
+			qdisc->children[0] = NFP_QDISC_UNTRACKED;
+	}
+
 	if (!nfp_abm_red_check_params(alink, opt)) {
 		err = -EINVAL;
 		goto err_destroy;
@@ -533,10 +546,14 @@ nfp_abm_mq_create(struct net_device *netdev, struct nfp_abm_link *alink,
 		  struct tc_mq_qopt_offload *opt)
 {
 	struct nfp_qdisc *qdisc;
+	int ret;
 
-	return nfp_abm_qdisc_replace(netdev, alink, NFP_QDISC_MQ,
-				     TC_H_ROOT, opt->handle,
-				     alink->total_queues, &qdisc);
+	ret = nfp_abm_qdisc_replace(netdev, alink, NFP_QDISC_MQ,
+				    TC_H_ROOT, opt->handle, alink->total_queues,
+				    &qdisc);
+	if (ret < 0)
+		return ret;
+	return 0;
 }
 
 int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
-- 
cgit v1.2.3


From 52db4eaca59fd2af8f3579ae9361214def014dbe Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:18 -0800
Subject: nfp: abm: save RED's parameters

Use the new driver Qdisc structure to keep track of parameters
of RED Qdiscs.  This way as the Qdisc moves around in the hierarchy
we will be able to configure the HW appropriately.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.h  | 14 ++++++++++++++
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c |  5 ++++-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index daca93e90099..d0d85f82bd1c 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -89,6 +89,11 @@ enum nfp_qdisc_type {
  * @use_cnt:		number of attachment points in the hierarchy
  * @num_children:	current size of the @children array
  * @children:		pointers to children
+ *
+ * @params_ok:		parameters of this Qdisc are OK for offload
+ *
+ * @red:		RED Qdisc specific parameters and state
+ * @red.threshold:	ECN marking threshold
  */
 struct nfp_qdisc {
 	struct net_device *netdev;
@@ -98,6 +103,15 @@ struct nfp_qdisc {
 	unsigned int use_cnt;
 	unsigned int num_children;
 	struct nfp_qdisc **children;
+
+	bool params_ok;
+
+	union {
+		/* TC_SETUP_QDISC_RED */
+		struct {
+			u32 threshold;
+		} red;
+	};
 };
 
 /**
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index 1b3c0b5b52bf..fb68038ec1da 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -375,7 +375,10 @@ nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 			qdisc->children[0] = NFP_QDISC_UNTRACKED;
 	}
 
-	if (!nfp_abm_red_check_params(alink, opt)) {
+	qdisc->params_ok = nfp_abm_red_check_params(alink, opt);
+	if (qdisc->params_ok) {
+		qdisc->red.threshold = opt->set.min;
+	} else {
 		err = -EINVAL;
 		goto err_destroy;
 	}
-- 
cgit v1.2.3


From bd3b5d462add1c703dd02a7a6f498a0f1bea9f4a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Nov 2018 14:58:19 -0800
Subject: nfp: abm: restructure Qdisc handling

In preparation of handling more Qdisc types switch to a different
offload strategy.  We have now recreated the Qdisc hierarchy in
the driver.  Every time the hierarchy changes parse it, and update
the configuration of the HW accordingly.

While at it drop the support of pretending that we can instantiate
a single queue on a multi-queue device in HW/FW.  MQ is now required,
and each queue will have its own instance of RED.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/ctrl.c  |  73 ----
 drivers/net/ethernet/netronome/nfp/abm/main.c  |  14 +-
 drivers/net/ethernet/netronome/nfp/abm/main.h  |  57 +--
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 548 ++++++++++++++-----------
 4 files changed, 340 insertions(+), 352 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index 564427e8a6e8..1629b07f727b 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -50,27 +50,6 @@ nfp_abm_ctrl_stat(struct nfp_abm_link *alink, const struct nfp_rtsym *sym,
 	return 0;
 }
 
-static int
-nfp_abm_ctrl_stat_all(struct nfp_abm_link *alink, const struct nfp_rtsym *sym,
-		      unsigned int stride, unsigned int offset, bool is_u64,
-		      u64 *res)
-{
-	u64 val, sum = 0;
-	unsigned int i;
-	int err;
-
-	for (i = 0; i < alink->vnic->max_rx_rings; i++) {
-		err = nfp_abm_ctrl_stat(alink, sym, stride, offset, i,
-					is_u64, &val);
-		if (err)
-			return err;
-		sum += val;
-	}
-
-	*res = sum;
-	return 0;
-}
-
 int __nfp_abm_ctrl_set_q_lvl(struct nfp_abm *abm, unsigned int id, u32 val)
 {
 	struct nfp_cpp *cpp = abm->app->cpp;
@@ -155,42 +134,6 @@ int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink, unsigned int i,
 				 i, true, &stats->overlimits);
 }
 
-int nfp_abm_ctrl_read_stats(struct nfp_abm_link *alink,
-			    struct nfp_alink_stats *stats)
-{
-	u64 pkts = 0, bytes = 0;
-	int i, err;
-
-	for (i = 0; i < alink->vnic->max_rx_rings; i++) {
-		pkts += nn_readq(alink->vnic, NFP_NET_CFG_RXR_STATS(i));
-		bytes += nn_readq(alink->vnic, NFP_NET_CFG_RXR_STATS(i) + 8);
-	}
-	stats->tx_pkts = pkts;
-	stats->tx_bytes = bytes;
-
-	err = nfp_abm_ctrl_stat_all(alink, alink->abm->q_lvls,
-				    NFP_QLVL_STRIDE, NFP_QLVL_BLOG_BYTES,
-				    false, &stats->backlog_bytes);
-	if (err)
-		return err;
-
-	err = nfp_abm_ctrl_stat_all(alink, alink->abm->q_lvls,
-				    NFP_QLVL_STRIDE, NFP_QLVL_BLOG_PKTS,
-				    false, &stats->backlog_pkts);
-	if (err)
-		return err;
-
-	err = nfp_abm_ctrl_stat_all(alink, alink->abm->qm_stats,
-				    NFP_QMSTAT_STRIDE, NFP_QMSTAT_DROP,
-				    true, &stats->drops);
-	if (err)
-		return err;
-
-	return nfp_abm_ctrl_stat_all(alink, alink->abm->qm_stats,
-				     NFP_QMSTAT_STRIDE, NFP_QMSTAT_ECN,
-				     true, &stats->overlimits);
-}
-
 int nfp_abm_ctrl_read_q_xstats(struct nfp_abm_link *alink, unsigned int i,
 			       struct nfp_alink_xstats *xstats)
 {
@@ -207,22 +150,6 @@ int nfp_abm_ctrl_read_q_xstats(struct nfp_abm_link *alink, unsigned int i,
 				 i, true, &xstats->ecn_marked);
 }
 
-int nfp_abm_ctrl_read_xstats(struct nfp_abm_link *alink,
-			     struct nfp_alink_xstats *xstats)
-{
-	int err;
-
-	err = nfp_abm_ctrl_stat_all(alink, alink->abm->qm_stats,
-				    NFP_QMSTAT_STRIDE, NFP_QMSTAT_DROP,
-				    true, &xstats->pdrop);
-	if (err)
-		return err;
-
-	return nfp_abm_ctrl_stat_all(alink, alink->abm->qm_stats,
-				     NFP_QMSTAT_STRIDE, NFP_QMSTAT_ECN,
-				     true, &xstats->ecn_marked);
-}
-
 int nfp_abm_ctrl_qm_enable(struct nfp_abm *abm)
 {
 	return nfp_mbox_cmd(abm->app->pf, NFP_MBOX_PCIE_ABM_ENABLE,
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index da5394886a78..a5732d3bd1b7 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -7,6 +7,7 @@
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
 #include <linux/rcupdate.h>
+#include <linux/rtnetlink.h>
 #include <linux/slab.h>
 
 #include "../nfpcore/nfp.h"
@@ -310,22 +311,14 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 	alink->abm = abm;
 	alink->vnic = nn;
 	alink->id = id;
-	alink->parent = TC_H_ROOT;
 	alink->total_queues = alink->vnic->max_rx_rings;
-	alink->red_qdiscs = kvcalloc(alink->total_queues,
-				     sizeof(*alink->red_qdiscs),
-				     GFP_KERNEL);
-	if (!alink->red_qdiscs) {
-		err = -ENOMEM;
-		goto err_free_alink;
-	}
 
 	/* This is a multi-host app, make sure MAC/PHY is up, but don't
 	 * make the MAC/PHY state follow the state of any of the ports.
 	 */
 	err = nfp_eth_set_configured(app->cpp, eth_port->index, true);
 	if (err < 0)
-		goto err_free_qdiscs;
+		goto err_free_alink;
 
 	netif_keep_dst(nn->dp.netdev);
 
@@ -335,8 +328,6 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 
 	return 0;
 
-err_free_qdiscs:
-	kvfree(alink->red_qdiscs);
 err_free_alink:
 	kfree(alink);
 	return err;
@@ -348,7 +339,6 @@ static void nfp_abm_vnic_free(struct nfp_app *app, struct nfp_net *nn)
 
 	nfp_abm_kill_reprs(alink->abm, alink);
 	WARN(!radix_tree_empty(&alink->qdiscs), "left over qdiscs\n");
-	kvfree(alink->red_qdiscs);
 	kfree(alink);
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index d0d85f82bd1c..240e2c8683fe 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -9,6 +9,11 @@
 #include <net/devlink.h>
 #include <net/pkt_cls.h>
 
+/* Dump of 64 PRIOs and 256 REDs seems to take 850us on Xeon v4 @ 2.20GHz;
+ * 2.5ms / 400Hz seems more than sufficient for stats resolution.
+ */
+#define NFP_ABM_STATS_REFRESH_IVAL	(2500 * 1000) /* ns */
+
 #define NFP_ABM_LVL_INFINITY		S32_MAX
 
 struct nfp_app;
@@ -91,9 +96,19 @@ enum nfp_qdisc_type {
  * @children:		pointers to children
  *
  * @params_ok:		parameters of this Qdisc are OK for offload
+ * @offload_mark:	offload refresh state - selected for offload
+ * @offloaded:		Qdisc is currently offloaded to the HW
+ *
+ * @mq:			MQ Qdisc specific parameters and state
+ * @mq.stats:		current stats of the MQ Qdisc
+ * @mq.prev_stats:	previously reported @mq.stats
  *
  * @red:		RED Qdisc specific parameters and state
  * @red.threshold:	ECN marking threshold
+ * @red.stats:		current stats of the RED Qdisc
+ * @red.prev_stats:	previously reported @red.stats
+ * @red.xstats:		extended stats for RED - current
+ * @red.prev_xstats:	extended stats for RED - previously reported
  */
 struct nfp_qdisc {
 	struct net_device *netdev;
@@ -105,29 +120,26 @@ struct nfp_qdisc {
 	struct nfp_qdisc **children;
 
 	bool params_ok;
+	bool offload_mark;
+	bool offloaded;
 
 	union {
+		/* NFP_QDISC_MQ */
+		struct {
+			struct nfp_alink_stats stats;
+			struct nfp_alink_stats prev_stats;
+		} mq;
 		/* TC_SETUP_QDISC_RED */
 		struct {
 			u32 threshold;
+			struct nfp_alink_stats stats;
+			struct nfp_alink_stats prev_stats;
+			struct nfp_alink_xstats xstats;
+			struct nfp_alink_xstats prev_xstats;
 		} red;
 	};
 };
 
-/**
- * struct nfp_red_qdisc - representation of single RED Qdisc
- * @handle:	handle of currently offloaded RED Qdisc
- * @threshold:	marking threshold of this Qdisc
- * @stats:	statistics from last refresh
- * @xstats:	base of extended statistics
- */
-struct nfp_red_qdisc {
-	u32 handle;
-	u32 threshold;
-	struct nfp_alink_stats stats;
-	struct nfp_alink_xstats xstats;
-};
-
 /**
  * struct nfp_abm_link - port tuple of a ABM NIC
  * @abm:	back pointer to nfp_abm
@@ -135,9 +147,9 @@ struct nfp_red_qdisc {
  * @id:		id of the data vNIC
  * @queue_base:	id of base to host queue within PCIe (not QC idx)
  * @total_queues:	number of PF queues
- * @parent:	handle of expected parent, i.e. handle of MQ, or TC_H_ROOT
- * @num_qdiscs:	number of currently used qdiscs
- * @red_qdiscs:	array of qdiscs
+ *
+ * @last_stats_update:	ktime of last stats update
+ *
  * @root_qdisc:	pointer to the current root of the Qdisc hierarchy
  * @qdiscs:	all qdiscs recorded by major part of the handle
  */
@@ -147,13 +159,14 @@ struct nfp_abm_link {
 	unsigned int id;
 	unsigned int queue_base;
 	unsigned int total_queues;
-	u32 parent;
-	unsigned int num_qdiscs;
-	struct nfp_red_qdisc *red_qdiscs;
+
+	u64 last_stats_update;
+
 	struct nfp_qdisc *root_qdisc;
 	struct radix_tree_root qdiscs;
 };
 
+void nfp_abm_qdisc_offload_update(struct nfp_abm_link *alink);
 int nfp_abm_setup_root(struct net_device *netdev, struct nfp_abm_link *alink,
 		       struct tc_root_qopt_offload *opt);
 int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
@@ -166,12 +179,8 @@ int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm);
 int __nfp_abm_ctrl_set_q_lvl(struct nfp_abm *abm, unsigned int id, u32 val);
 int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int queue,
 			   u32 val);
-int nfp_abm_ctrl_read_stats(struct nfp_abm_link *alink,
-			    struct nfp_alink_stats *stats);
 int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink, unsigned int i,
 			      struct nfp_alink_stats *stats);
-int nfp_abm_ctrl_read_xstats(struct nfp_abm_link *alink,
-			     struct nfp_alink_xstats *xstats);
 int nfp_abm_ctrl_read_q_xstats(struct nfp_abm_link *alink, unsigned int i,
 			       struct nfp_alink_xstats *xstats);
 u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int i);
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index fb68038ec1da..16c4afe3a37f 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -13,6 +13,11 @@
 #include "../nfp_port.h"
 #include "main.h"
 
+static bool nfp_abm_qdisc_is_red(struct nfp_qdisc *qdisc)
+{
+	return qdisc->type == NFP_QDISC_RED;
+}
+
 static bool nfp_abm_qdisc_child_valid(struct nfp_qdisc *qdisc, unsigned int id)
 {
 	return qdisc->children[id] &&
@@ -24,6 +29,74 @@ static void *nfp_abm_qdisc_tree_deref_slot(void __rcu **slot)
 	return rtnl_dereference(*slot);
 }
 
+static void
+nfp_abm_stats_propagate(struct nfp_alink_stats *parent,
+			struct nfp_alink_stats *child)
+{
+	parent->tx_pkts		+= child->tx_pkts;
+	parent->tx_bytes	+= child->tx_bytes;
+	parent->backlog_pkts	+= child->backlog_pkts;
+	parent->backlog_bytes	+= child->backlog_bytes;
+	parent->overlimits	+= child->overlimits;
+	parent->drops		+= child->drops;
+}
+
+static void
+nfp_abm_stats_update_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
+			 unsigned int queue)
+{
+	struct nfp_cpp *cpp = alink->abm->app->cpp;
+	int err;
+
+	if (!qdisc->offloaded)
+		return;
+
+	err = nfp_abm_ctrl_read_q_stats(alink, queue, &qdisc->red.stats);
+	if (err)
+		nfp_err(cpp, "RED stats (%d) read failed with error %d\n",
+			queue, err);
+
+	err = nfp_abm_ctrl_read_q_xstats(alink, queue, &qdisc->red.xstats);
+	if (err)
+		nfp_err(cpp, "RED xstats (%d) read failed with error %d\n",
+			queue, err);
+}
+
+static void
+nfp_abm_stats_update_mq(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc)
+{
+	unsigned int i;
+
+	if (qdisc->type != NFP_QDISC_MQ)
+		return;
+
+	for (i = 0; i < alink->total_queues; i++)
+		if (nfp_abm_qdisc_child_valid(qdisc, i))
+			nfp_abm_stats_update_red(alink, qdisc->children[i], i);
+}
+
+static void __nfp_abm_stats_update(struct nfp_abm_link *alink, u64 time_now)
+{
+	alink->last_stats_update = time_now;
+	if (alink->root_qdisc)
+		nfp_abm_stats_update_mq(alink, alink->root_qdisc);
+}
+
+static void nfp_abm_stats_update(struct nfp_abm_link *alink)
+{
+	u64 now;
+
+	/* Limit the frequency of updates - stats of non-leaf qdiscs are a sum
+	 * of all their leafs, so we would read the same stat multiple times
+	 * for every dump.
+	 */
+	now = ktime_get();
+	if (now - alink->last_stats_update < NFP_ABM_STATS_REFRESH_IVAL)
+		return;
+
+	__nfp_abm_stats_update(alink, now);
+}
+
 static void
 nfp_abm_qdisc_unlink_children(struct nfp_qdisc *qdisc,
 			      unsigned int start, unsigned int end)
@@ -38,89 +111,174 @@ nfp_abm_qdisc_unlink_children(struct nfp_qdisc *qdisc,
 }
 
 static void
-nfp_abm_qdisc_clear_mq(struct net_device *netdev, struct nfp_abm_link *alink,
-		       struct nfp_qdisc *qdisc)
+nfp_abm_qdisc_offload_stop(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc)
 {
-	struct radix_tree_iter iter;
-	unsigned int mq_refs = 0;
-	void __rcu **slot;
+	/* Don't complain when qdisc is getting unlinked */
+	if (qdisc->use_cnt)
+		nfp_warn(alink->abm->app->cpp, "Offload of '%08x' stopped\n",
+			 qdisc->handle);
 
-	if (!qdisc->use_cnt)
+	if (!nfp_abm_qdisc_is_red(qdisc))
 		return;
-	/* MQ doesn't notify well on destruction, we need special handling of
-	 * MQ's children.
+
+	qdisc->red.stats.backlog_pkts = 0;
+	qdisc->red.stats.backlog_bytes = 0;
+}
+
+static int
+__nfp_abm_stats_init(struct nfp_abm_link *alink,
+		     unsigned int queue, struct nfp_alink_stats *prev_stats,
+		     struct nfp_alink_xstats *prev_xstats)
+{
+	u64 backlog_pkts, backlog_bytes;
+	int err;
+
+	/* Don't touch the backlog, backlog can only be reset after it has
+	 * been reported back to the tc qdisc stats.
 	 */
-	if (qdisc->type == NFP_QDISC_MQ &&
-	    qdisc == alink->root_qdisc &&
-	    netdev->reg_state == NETREG_UNREGISTERING)
-		return;
+	backlog_pkts = prev_stats->backlog_pkts;
+	backlog_bytes = prev_stats->backlog_bytes;
 
-	/* Count refs held by MQ instances and clear pointers */
-	radix_tree_for_each_slot(slot, &alink->qdiscs, &iter, 0) {
-		struct nfp_qdisc *mq = nfp_abm_qdisc_tree_deref_slot(slot);
-		unsigned int i;
+	err = nfp_abm_ctrl_read_q_stats(alink, queue, prev_stats);
+	if (err) {
+		nfp_err(alink->abm->app->cpp,
+			"RED stats init (%d) failed with error %d\n",
+			queue, err);
+		return err;
+	}
 
-		if (mq->type != NFP_QDISC_MQ || mq->netdev != netdev)
-			continue;
-		for (i = 0; i < mq->num_children; i++)
-			if (mq->children[i] == qdisc) {
-				mq->children[i] = NULL;
-				mq_refs++;
-			}
+	err = nfp_abm_ctrl_read_q_xstats(alink, queue, prev_xstats);
+	if (err) {
+		nfp_err(alink->abm->app->cpp,
+			"RED xstats init (%d) failed with error %d\n",
+			queue, err);
+		return err;
 	}
 
-	WARN(qdisc->use_cnt != mq_refs, "non-zero qdisc use count: %d (- %d)\n",
-	     qdisc->use_cnt, mq_refs);
+	prev_stats->backlog_pkts = backlog_pkts;
+	prev_stats->backlog_bytes = backlog_bytes;
+	return 0;
+}
+
+static int
+nfp_abm_stats_init(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
+		   unsigned int queue)
+{
+	return __nfp_abm_stats_init(alink, queue,
+				    &qdisc->red.prev_stats,
+				    &qdisc->red.prev_xstats);
 }
 
 static void
-nfp_abm_offload_compile_red(struct nfp_abm_link *alink,
-			    struct nfp_red_qdisc *qdisc, unsigned int queue)
+nfp_abm_offload_compile_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
+			    unsigned int queue)
 {
-	if (!qdisc->handle)
+	qdisc->offload_mark = qdisc->type == NFP_QDISC_RED &&
+			      qdisc->params_ok &&
+			      qdisc->use_cnt == 1 &&
+			      !qdisc->children[0];
+
+	/* If we are starting offload init prev_stats */
+	if (qdisc->offload_mark && !qdisc->offloaded)
+		if (nfp_abm_stats_init(alink, qdisc, queue))
+			qdisc->offload_mark = false;
+
+	if (!qdisc->offload_mark)
 		return;
 
-	nfp_abm_ctrl_set_q_lvl(alink, queue, qdisc->threshold);
+	nfp_abm_ctrl_set_q_lvl(alink, queue, qdisc->red.threshold);
 }
 
-static void nfp_abm_offload_compile_one(struct nfp_abm_link *alink)
+static void
+nfp_abm_offload_compile_mq(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc)
 {
 	unsigned int i;
-	bool is_mq;
 
-	is_mq = alink->num_qdiscs > 1;
+	qdisc->offload_mark = qdisc->type == NFP_QDISC_MQ;
+	if (!qdisc->offload_mark)
+		return;
 
 	for (i = 0; i < alink->total_queues; i++) {
-		struct nfp_red_qdisc *next;
+		struct nfp_qdisc *child = qdisc->children[i];
 
-		if (is_mq && !alink->red_qdiscs[i].handle)
+		if (!nfp_abm_qdisc_child_valid(qdisc, i))
 			continue;
 
-		next = is_mq ? &alink->red_qdiscs[i] : &alink->red_qdiscs[0];
-		nfp_abm_offload_compile_red(alink, next, i);
+		nfp_abm_offload_compile_red(alink, child, i);
 	}
 }
 
-static void nfp_abm_offload_update(struct nfp_abm *abm)
+void nfp_abm_qdisc_offload_update(struct nfp_abm_link *alink)
 {
-	struct nfp_abm_link *alink = NULL;
-	struct nfp_pf *pf = abm->app->pf;
-	struct nfp_net *nn;
+	struct nfp_abm *abm = alink->abm;
+	struct radix_tree_iter iter;
+	struct nfp_qdisc *qdisc;
+	void __rcu **slot;
 	size_t i;
 
 	/* Mark all thresholds as unconfigured */
-	__bitmap_set(abm->threshold_undef, 0, abm->num_thresholds);
+	__bitmap_set(abm->threshold_undef,
+		     alink->queue_base, alink->total_queues);
 
-	/* Configure all offloads */
-	list_for_each_entry(nn, &pf->vnics, vnic_list) {
-		alink = nn->app_priv;
-		nfp_abm_offload_compile_one(alink);
+	/* Clear offload marks */
+	radix_tree_for_each_slot(slot, &alink->qdiscs, &iter, 0) {
+		qdisc = nfp_abm_qdisc_tree_deref_slot(slot);
+		qdisc->offload_mark = false;
+	}
+
+	if (alink->root_qdisc)
+		nfp_abm_offload_compile_mq(alink, alink->root_qdisc);
+
+	/* Refresh offload status */
+	radix_tree_for_each_slot(slot, &alink->qdiscs, &iter, 0) {
+		qdisc = nfp_abm_qdisc_tree_deref_slot(slot);
+		if (!qdisc->offload_mark && qdisc->offloaded)
+			nfp_abm_qdisc_offload_stop(alink, qdisc);
+		qdisc->offloaded = qdisc->offload_mark;
 	}
 
 	/* Reset the unconfigured thresholds */
 	for (i = 0; i < abm->num_thresholds; i++)
 		if (test_bit(i, abm->threshold_undef))
 			__nfp_abm_ctrl_set_q_lvl(abm, i, NFP_ABM_LVL_INFINITY);
+
+	__nfp_abm_stats_update(alink, ktime_get());
+}
+
+static void
+nfp_abm_qdisc_clear_mq(struct net_device *netdev, struct nfp_abm_link *alink,
+		       struct nfp_qdisc *qdisc)
+{
+	struct radix_tree_iter iter;
+	unsigned int mq_refs = 0;
+	void __rcu **slot;
+
+	if (!qdisc->use_cnt)
+		return;
+	/* MQ doesn't notify well on destruction, we need special handling of
+	 * MQ's children.
+	 */
+	if (qdisc->type == NFP_QDISC_MQ &&
+	    qdisc == alink->root_qdisc &&
+	    netdev->reg_state == NETREG_UNREGISTERING)
+		return;
+
+	/* Count refs held by MQ instances and clear pointers */
+	radix_tree_for_each_slot(slot, &alink->qdiscs, &iter, 0) {
+		struct nfp_qdisc *mq = nfp_abm_qdisc_tree_deref_slot(slot);
+		unsigned int i;
+
+		if (mq->type != NFP_QDISC_MQ || mq->netdev != netdev)
+			continue;
+		for (i = 0; i < mq->num_children; i++)
+			if (mq->children[i] == qdisc) {
+				mq->children[i] = NULL;
+				mq_refs++;
+			}
+	}
+
+	WARN(qdisc->use_cnt != mq_refs, "non-zero qdisc use count: %d (- %d)\n",
+	     qdisc->use_cnt, mq_refs);
 }
 
 static void
@@ -221,8 +379,13 @@ nfp_abm_qdisc_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
 	nfp_abm_qdisc_unlink_children(qdisc, 0, qdisc->num_children);
 	nfp_abm_qdisc_free(netdev, alink, qdisc);
 
-	if (alink->root_qdisc == qdisc)
+	if (alink->root_qdisc == qdisc) {
 		alink->root_qdisc = NULL;
+		/* Only root change matters, other changes are acted upon on
+		 * the graft notification.
+		 */
+		nfp_abm_qdisc_offload_update(alink);
+	}
 }
 
 static int
@@ -249,66 +412,73 @@ nfp_abm_qdisc_graft(struct nfp_abm_link *alink, u32 handle, u32 child_handle,
 		child = NFP_QDISC_UNTRACKED;
 	parent->children[id] = child;
 
+	nfp_abm_qdisc_offload_update(alink);
+
 	return 0;
 }
 
 static void
-__nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
-		     u32 handle, unsigned int qs, u32 init_val)
+nfp_abm_stats_calculate(struct nfp_alink_stats *new,
+			struct nfp_alink_stats *old,
+			struct gnet_stats_basic_packed *bstats,
+			struct gnet_stats_queue *qstats)
 {
-	memset(alink->red_qdiscs, 0,
-	       sizeof(*alink->red_qdiscs) * alink->num_qdiscs);
-
-	alink->parent = handle;
-	alink->num_qdiscs = qs;
+	_bstats_update(bstats, new->tx_bytes - old->tx_bytes,
+		       new->tx_pkts - old->tx_pkts);
+	qstats->qlen += new->backlog_pkts - old->backlog_pkts;
+	qstats->backlog += new->backlog_bytes - old->backlog_bytes;
+	qstats->overlimits += new->overlimits - old->overlimits;
+	qstats->drops += new->drops - old->drops;
 }
 
 static void
-nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
-		   u32 handle, unsigned int qs)
+nfp_abm_stats_red_calculate(struct nfp_alink_xstats *new,
+			    struct nfp_alink_xstats *old,
+			    struct red_stats *stats)
 {
-	__nfp_abm_reset_root(netdev, alink, handle, qs, NFP_ABM_LVL_INFINITY);
+	stats->forced_mark += new->ecn_marked - old->ecn_marked;
+	stats->pdrop += new->pdrop - old->pdrop;
 }
 
 static int
-nfp_abm_red_find(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
+nfp_abm_red_xstats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
 {
-	unsigned int i = TC_H_MIN(opt->parent) - 1;
+	struct nfp_qdisc *qdisc;
 
-	if (opt->parent == TC_H_ROOT)
-		i = 0;
-	else if (TC_H_MAJ(alink->parent) == TC_H_MAJ(opt->parent))
-		i = TC_H_MIN(opt->parent) - 1;
-	else
-		return -EOPNOTSUPP;
+	nfp_abm_stats_update(alink);
 
-	if (i >= alink->num_qdiscs ||
-	    opt->handle != alink->red_qdiscs[i].handle)
+	qdisc = nfp_abm_qdisc_find(alink, opt->handle);
+	if (!qdisc || !qdisc->offloaded)
 		return -EOPNOTSUPP;
 
-	return i;
+	nfp_abm_stats_red_calculate(&qdisc->red.xstats,
+				    &qdisc->red.prev_xstats,
+				    opt->xstats);
+	qdisc->red.prev_xstats = qdisc->red.xstats;
+	return 0;
 }
 
-static void
-nfp_abm_red_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
-		    u32 handle)
+static int
+nfp_abm_red_stats(struct nfp_abm_link *alink, u32 handle,
+		  struct tc_qopt_offload_stats *stats)
 {
-	unsigned int i;
+	struct nfp_qdisc *qdisc;
 
-	nfp_abm_qdisc_destroy(netdev, alink, handle);
+	nfp_abm_stats_update(alink);
 
-	for (i = 0; i < alink->num_qdiscs; i++)
-		if (handle == alink->red_qdiscs[i].handle)
-			break;
-	if (i == alink->num_qdiscs)
-		return;
+	qdisc = nfp_abm_qdisc_find(alink, handle);
+	if (!qdisc)
+		return -EOPNOTSUPP;
+	/* If the qdisc offload has stopped we may need to adjust the backlog
+	 * counters back so carry on even if qdisc is not currently offloaded.
+	 */
 
-	if (alink->parent == TC_H_ROOT)
-		nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
-	else
-		memset(&alink->red_qdiscs[i], 0, sizeof(*alink->red_qdiscs));
+	nfp_abm_stats_calculate(&qdisc->red.stats,
+				&qdisc->red.prev_stats,
+				stats->bstats, stats->qstats);
+	qdisc->red.prev_stats = qdisc->red.stats;
 
-	nfp_abm_offload_update(alink->abm);
+	return qdisc->offloaded ? 0 : -EOPNOTSUPP;
 }
 
 static bool
@@ -347,20 +517,12 @@ nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 		    struct tc_red_qopt_offload *opt)
 {
 	struct nfp_qdisc *qdisc;
-	bool existing;
-	int i, err;
 	int ret;
 
 	ret = nfp_abm_qdisc_replace(netdev, alink, NFP_QDISC_RED, opt->parent,
 				    opt->handle, 1, &qdisc);
-
-	i = nfp_abm_red_find(alink, opt);
-	existing = i >= 0;
-
-	if (ret < 0) {
-		err = ret;
-		goto err_destroy;
-	}
+	if (ret < 0)
+		return ret;
 
 	/* If limit != 0 child gets reset */
 	if (opt->set.limit) {
@@ -376,127 +538,11 @@ nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 	}
 
 	qdisc->params_ok = nfp_abm_red_check_params(alink, opt);
-	if (qdisc->params_ok) {
+	if (qdisc->params_ok)
 		qdisc->red.threshold = opt->set.min;
-	} else {
-		err = -EINVAL;
-		goto err_destroy;
-	}
-
-	if (existing) {
-		nfp_abm_offload_update(alink->abm);
-		return 0;
-	}
-
-	if (opt->parent == TC_H_ROOT) {
-		i = 0;
-		__nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 1, opt->set.min);
-	} else if (TC_H_MAJ(alink->parent) == TC_H_MAJ(opt->parent)) {
-		i = TC_H_MIN(opt->parent) - 1;
-	} else {
-		return -EINVAL;
-	}
-	alink->red_qdiscs[i].handle = opt->handle;
-
-	if (opt->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_stats(alink,
-					      &alink->red_qdiscs[i].stats);
-	else
-		err = nfp_abm_ctrl_read_q_stats(alink, i,
-						&alink->red_qdiscs[i].stats);
-	if (err)
-		goto err_destroy;
-
-	if (opt->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_xstats(alink,
-					       &alink->red_qdiscs[i].xstats);
-	else
-		err = nfp_abm_ctrl_read_q_xstats(alink, i,
-						 &alink->red_qdiscs[i].xstats);
-	if (err)
-		goto err_destroy;
-
-	alink->red_qdiscs[i].threshold = opt->set.min;
-	alink->red_qdiscs[i].stats.backlog_pkts = 0;
-	alink->red_qdiscs[i].stats.backlog_bytes = 0;
-
-	nfp_abm_offload_update(alink->abm);
-
-	return 0;
-err_destroy:
-	/* If the qdisc keeps on living, but we can't offload undo changes */
-	if (existing) {
-		opt->set.qstats->qlen -=
-			alink->red_qdiscs[i].stats.backlog_pkts;
-		opt->set.qstats->backlog -=
-			alink->red_qdiscs[i].stats.backlog_bytes;
-	}
-	nfp_abm_red_destroy(netdev, alink, opt->handle);
-
-	return err;
-}
-
-static void
-nfp_abm_update_stats(struct nfp_alink_stats *new, struct nfp_alink_stats *old,
-		     struct tc_qopt_offload_stats *stats)
-{
-	_bstats_update(stats->bstats, new->tx_bytes - old->tx_bytes,
-		       new->tx_pkts - old->tx_pkts);
-	stats->qstats->qlen += new->backlog_pkts - old->backlog_pkts;
-	stats->qstats->backlog += new->backlog_bytes - old->backlog_bytes;
-	stats->qstats->overlimits += new->overlimits - old->overlimits;
-	stats->qstats->drops += new->drops - old->drops;
-}
-
-static int
-nfp_abm_red_stats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
-{
-	struct nfp_alink_stats *prev_stats;
-	struct nfp_alink_stats stats;
-	int i, err;
-
-	i = nfp_abm_red_find(alink, opt);
-	if (i < 0)
-		return i;
-	prev_stats = &alink->red_qdiscs[i].stats;
-
-	if (alink->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_stats(alink, &stats);
-	else
-		err = nfp_abm_ctrl_read_q_stats(alink, i, &stats);
-	if (err)
-		return err;
-
-	nfp_abm_update_stats(&stats, prev_stats, &opt->stats);
 
-	*prev_stats = stats;
-
-	return 0;
-}
-
-static int
-nfp_abm_red_xstats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
-{
-	struct nfp_alink_xstats *prev_xstats;
-	struct nfp_alink_xstats xstats;
-	int i, err;
-
-	i = nfp_abm_red_find(alink, opt);
-	if (i < 0)
-		return i;
-	prev_xstats = &alink->red_qdiscs[i].xstats;
-
-	if (alink->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_xstats(alink, &xstats);
-	else
-		err = nfp_abm_ctrl_read_q_xstats(alink, i, &xstats);
-	if (err)
-		return err;
-
-	opt->xstats->forced_mark += xstats.ecn_marked - prev_xstats->ecn_marked;
-	opt->xstats->pdrop += xstats.pdrop - prev_xstats->pdrop;
-
-	*prev_xstats = xstats;
+	if (qdisc->use_cnt == 1)
+		nfp_abm_qdisc_offload_update(alink);
 
 	return 0;
 }
@@ -508,10 +554,10 @@ int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
 	case TC_RED_REPLACE:
 		return nfp_abm_red_replace(netdev, alink, opt);
 	case TC_RED_DESTROY:
-		nfp_abm_red_destroy(netdev, alink, opt->handle);
+		nfp_abm_qdisc_destroy(netdev, alink, opt->handle);
 		return 0;
 	case TC_RED_STATS:
-		return nfp_abm_red_stats(alink, opt);
+		return nfp_abm_red_stats(alink, opt->handle, &opt->stats);
 	case TC_RED_XSTATS:
 		return nfp_abm_red_xstats(alink, opt);
 	case TC_RED_GRAFT:
@@ -522,28 +568,6 @@ int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
 	}
 }
 
-static int
-nfp_abm_mq_stats(struct nfp_abm_link *alink, struct tc_mq_qopt_offload *opt)
-{
-	struct nfp_alink_stats stats;
-	unsigned int i;
-	int err;
-
-	for (i = 0; i < alink->num_qdiscs; i++) {
-		if (alink->red_qdiscs[i].handle == TC_H_UNSPEC)
-			continue;
-
-		err = nfp_abm_ctrl_read_q_stats(alink, i, &stats);
-		if (err)
-			return err;
-
-		nfp_abm_update_stats(&stats, &alink->red_qdiscs[i].stats,
-				     &opt->stats);
-	}
-
-	return 0;
-}
-
 static int
 nfp_abm_mq_create(struct net_device *netdev, struct nfp_abm_link *alink,
 		  struct tc_mq_qopt_offload *opt)
@@ -556,27 +580,63 @@ nfp_abm_mq_create(struct net_device *netdev, struct nfp_abm_link *alink,
 				    &qdisc);
 	if (ret < 0)
 		return ret;
+
+	qdisc->params_ok = true;
+	qdisc->offloaded = true;
+	nfp_abm_qdisc_offload_update(alink);
 	return 0;
 }
 
+static int
+nfp_abm_mq_stats(struct nfp_abm_link *alink, u32 handle,
+		 struct tc_qopt_offload_stats *stats)
+{
+	struct nfp_qdisc *qdisc, *red;
+	unsigned int i;
+
+	qdisc = nfp_abm_qdisc_find(alink, handle);
+	if (!qdisc)
+		return -EOPNOTSUPP;
+
+	nfp_abm_stats_update(alink);
+
+	/* MQ stats are summed over the children in the core, so we need
+	 * to add up the unreported child values.
+	 */
+	memset(&qdisc->mq.stats, 0, sizeof(qdisc->mq.stats));
+	memset(&qdisc->mq.prev_stats, 0, sizeof(qdisc->mq.prev_stats));
+
+	for (i = 0; i < qdisc->num_children; i++) {
+		if (!nfp_abm_qdisc_child_valid(qdisc, i))
+			continue;
+
+		if (!nfp_abm_qdisc_is_red(qdisc->children[i]))
+			continue;
+		red = qdisc->children[i];
+
+		nfp_abm_stats_propagate(&qdisc->mq.stats,
+					&red->red.stats);
+		nfp_abm_stats_propagate(&qdisc->mq.prev_stats,
+					&red->red.prev_stats);
+	}
+
+	nfp_abm_stats_calculate(&qdisc->mq.stats, &qdisc->mq.prev_stats,
+				stats->bstats, stats->qstats);
+
+	return qdisc->offloaded ? 0 : -EOPNOTSUPP;
+}
+
 int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 			struct tc_mq_qopt_offload *opt)
 {
 	switch (opt->command) {
 	case TC_MQ_CREATE:
-		nfp_abm_reset_root(netdev, alink, opt->handle,
-				   alink->total_queues);
-		nfp_abm_offload_update(alink->abm);
 		return nfp_abm_mq_create(netdev, alink, opt);
 	case TC_MQ_DESTROY:
 		nfp_abm_qdisc_destroy(netdev, alink, opt->handle);
-		if (opt->handle == alink->parent) {
-			nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
-			nfp_abm_offload_update(alink->abm);
-		}
 		return 0;
 	case TC_MQ_STATS:
-		return nfp_abm_mq_stats(alink, opt);
+		return nfp_abm_mq_stats(alink, opt->handle, &opt->stats);
 	case TC_MQ_GRAFT:
 		return nfp_abm_qdisc_graft(alink, opt->handle,
 					   opt->graft_params.child_handle,
@@ -597,5 +657,7 @@ int nfp_abm_setup_root(struct net_device *netdev, struct nfp_abm_link *alink,
 	if (alink->root_qdisc)
 		alink->root_qdisc->use_cnt++;
 
+	nfp_abm_qdisc_offload_update(alink);
+
 	return 0;
 }
-- 
cgit v1.2.3


From 6a9a5ec10e79425a4df26122705ecf24763b7f2d Mon Sep 17 00:00:00 2001
From: Lance Roy <ldr709@gmail.com>
Date: Tue, 2 Oct 2018 22:38:50 -0700
Subject: i40e: Replace spin_is_locked() with lockdep

lockdep_assert_held() is better suited to checking locking requirements,
since it won't get confused when someone else holds the lock. This is
also a step towards possibly removing spin_is_locked().

Signed-off-by: Lance Roy <ldr709@gmail.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 21c2688d6308..7e4c07227832 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1493,8 +1493,7 @@ int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr)
 	bool found = false;
 	int bkt;
 
-	WARN(!spin_is_locked(&vsi->mac_filter_hash_lock),
-	     "Missing mac_filter_hash_lock\n");
+	lockdep_assert_held(&vsi->mac_filter_hash_lock);
 	hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
 		if (ether_addr_equal(macaddr, f->macaddr)) {
 			__i40e_del_filter(vsi, f);
-- 
cgit v1.2.3


From 8554768c2c3d8a8aa4eacaabb35140aa8fd03e35 Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Tue, 30 Oct 2018 10:50:42 -0700
Subject: i40e: Use a local variable for readability

Use a local variable to make the code a bit more readable.

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 1384a5a006a4..c4d44096cdaf 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3528,6 +3528,7 @@ static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
 	u16 i = xdp_ring->next_to_use;
 	struct i40e_tx_buffer *tx_bi;
 	struct i40e_tx_desc *tx_desc;
+	void *data = xdpf->data;
 	u32 size = xdpf->len;
 	dma_addr_t dma;
 
@@ -3535,8 +3536,7 @@ static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
 		xdp_ring->tx_stats.tx_busy++;
 		return I40E_XDP_CONSUMED;
 	}
-
-	dma = dma_map_single(xdp_ring->dev, xdpf->data, size, DMA_TO_DEVICE);
+	dma = dma_map_single(xdp_ring->dev, data, size, DMA_TO_DEVICE);
 	if (dma_mapping_error(xdp_ring->dev, dma))
 		return I40E_XDP_CONSUMED;
 
-- 
cgit v1.2.3


From de10933e37039e1b9d67a3d21d4e0a14c734eaac Mon Sep 17 00:00:00 2001
From: Krzysztof Galazka <krzysztof.galazka@intel.com>
Date: Tue, 30 Oct 2018 10:50:43 -0700
Subject: i40e: Add capability flag for stopping FW LLDP

Add HW capability flag to indicate that firmware supports stopping
LLDP agent. This feature has been added in FW API 1.7 for XL710
devices and 1.6 for X722. Also raise expected minor version number
for X722 FW API to 6.

Signed-off-by: Krzysztof Galazka <krzysztof.galazka@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_adminq.c     | 6 ++++++
 drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h | 4 +++-
 drivers/net/ethernet/intel/i40e/i40e_type.h       | 1 +
 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 501ee718177f..7ab61f6ebb5f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -588,6 +588,12 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw)
 	    hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
 	    hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) {
 		hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE;
+		hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE;
+	}
+	if (hw->mac.type == I40E_MAC_X722 &&
+	    hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
+	    hw->aq.api_min_ver >= I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722) {
+		hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE;
 	}
 
 	/* Newer versions of firmware require lock when reading the NVM */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 80e3eec6134e..11506102471c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -11,7 +11,7 @@
  */
 
 #define I40E_FW_API_VERSION_MAJOR	0x0001
-#define I40E_FW_API_VERSION_MINOR_X722	0x0005
+#define I40E_FW_API_VERSION_MINOR_X722	0x0006
 #define I40E_FW_API_VERSION_MINOR_X710	0x0007
 
 #define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
@@ -20,6 +20,8 @@
 
 /* API version 1.7 implements additional link and PHY-specific APIs  */
 #define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007
+/* API version 1.6 for X722 devices adds ability to stop FW LLDP agent */
+#define I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722 0x0006
 
 struct i40e_aq_desc {
 	__le16 flags;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 7df969c59855..2781ab91ca82 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -615,6 +615,7 @@ struct i40e_hw {
 #define I40E_HW_FLAG_802_1AD_CAPABLE        BIT_ULL(1)
 #define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE  BIT_ULL(2)
 #define I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK BIT_ULL(3)
+#define I40E_HW_FLAG_FW_LLDP_STOPPABLE      BIT_ULL(4)
 	u64 flags;
 
 	/* Used in set switch config AQ command */
-- 
cgit v1.2.3


From 4ff2d8540321324e04c1306f85d4fe68a0c2d0ae Mon Sep 17 00:00:00 2001
From: Patryk Małek <patryk.malek@intel.com>
Date: Tue, 30 Oct 2018 10:50:44 -0700
Subject: i40e: Replace strncpy with strlcpy to ensure null termination
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Using strncpy allows destination buffer to be not null terminated
after the copying takes place. strlcpy ensures that's not the
case by explicitly setting last element in the buffer as '\0'.

Signed-off-by: Patryk Małek <patryk.malek@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 14 +++++++-------
 drivers/net/ethernet/intel/i40e/i40e_ptp.c  |  2 +-
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7e4c07227832..b6f4ebb4557e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -14301,23 +14301,23 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 		switch (hw->bus.speed) {
 		case i40e_bus_speed_8000:
-			strncpy(speed, "8.0", PCI_SPEED_SIZE); break;
+			strlcpy(speed, "8.0", PCI_SPEED_SIZE); break;
 		case i40e_bus_speed_5000:
-			strncpy(speed, "5.0", PCI_SPEED_SIZE); break;
+			strlcpy(speed, "5.0", PCI_SPEED_SIZE); break;
 		case i40e_bus_speed_2500:
-			strncpy(speed, "2.5", PCI_SPEED_SIZE); break;
+			strlcpy(speed, "2.5", PCI_SPEED_SIZE); break;
 		default:
 			break;
 		}
 		switch (hw->bus.width) {
 		case i40e_bus_width_pcie_x8:
-			strncpy(width, "8", PCI_WIDTH_SIZE); break;
+			strlcpy(width, "8", PCI_WIDTH_SIZE); break;
 		case i40e_bus_width_pcie_x4:
-			strncpy(width, "4", PCI_WIDTH_SIZE); break;
+			strlcpy(width, "4", PCI_WIDTH_SIZE); break;
 		case i40e_bus_width_pcie_x2:
-			strncpy(width, "2", PCI_WIDTH_SIZE); break;
+			strlcpy(width, "2", PCI_WIDTH_SIZE); break;
 		case i40e_bus_width_pcie_x1:
-			strncpy(width, "1", PCI_WIDTH_SIZE); break;
+			strlcpy(width, "1", PCI_WIDTH_SIZE); break;
 		default:
 			break;
 		}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index 1199f0502d6d..e6fc0aff8c99 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -694,7 +694,7 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf)
 	if (!IS_ERR_OR_NULL(pf->ptp_clock))
 		return 0;
 
-	strncpy(pf->ptp_caps.name, i40e_driver_name,
+	strlcpy(pf->ptp_caps.name, i40e_driver_name,
 		sizeof(pf->ptp_caps.name) - 1);
 	pf->ptp_caps.owner = THIS_MODULE;
 	pf->ptp_caps.max_adj = 999999999;
-- 
cgit v1.2.3


From f5a7b21b243952d4d26a2c91a041d122c0306504 Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Tue, 30 Oct 2018 10:50:45 -0700
Subject: i40e: Protect access to VF control methods

A scenario has been found in which simultaneous
addition/removal and modification of VF's might cause
unstable behaviour, up to and including kernel panics.

Protect the methods that create/modify/destroy VF's
by locking them behind an atomically set bit in PF status
bitfield.

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h             |  1 +
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 64 ++++++++++++++++++++--
 2 files changed, 60 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 876cac317e79..5595a4614206 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -146,6 +146,7 @@ enum i40e_state_t {
 	__I40E_CLIENT_SERVICE_REQUESTED,
 	__I40E_CLIENT_L2_CHANGE,
 	__I40E_CLIENT_RESET,
+	__I40E_VIRTCHNL_OP_PENDING,
 	/* This must be last as it determines the size of the BITMAP */
 	__I40E_STATE_SIZE__,
 };
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index ac5698ed0b11..8e0a247e7e5a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1675,13 +1675,20 @@ err_out:
 int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 {
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
+	int ret = 0;
+
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
 
 	if (num_vfs) {
 		if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
 			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
 			i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
 		}
-		return i40e_pci_sriov_enable(pdev, num_vfs);
+		ret = i40e_pci_sriov_enable(pdev, num_vfs);
+		goto sriov_configure_out;
 	}
 
 	if (!pci_vfs_assigned(pf->pdev)) {
@@ -1690,9 +1697,12 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 		i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
 	} else {
 		dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto sriov_configure_out;
 	}
-	return 0;
+sriov_configure_out:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
+	return ret;
 }
 
 /***********************virtual channel routines******************/
@@ -3893,6 +3903,11 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 		goto error_param;
 	}
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	if (is_multicast_ether_addr(mac)) {
 		dev_err(&pf->pdev->dev,
 			"Invalid Ethernet address %pM for VF %d\n", mac, vf_id);
@@ -3941,6 +3956,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	dev_info(&pf->pdev->dev, "Bring down and up the VF interface to make this change effective.\n");
 
 error_param:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -3992,6 +4008,11 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 	struct i40e_vf *vf;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	ret = i40e_validate_vf(pf, vf_id);
 	if (ret)
@@ -4107,6 +4128,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 	ret = 0;
 
 error_pvid:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -4128,6 +4150,11 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
 	struct i40e_vf *vf;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	ret = i40e_validate_vf(pf, vf_id);
 	if (ret)
@@ -4154,6 +4181,7 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
 
 	vf->tx_rate = max_tx_rate;
 error:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -4174,6 +4202,11 @@ int i40e_ndo_get_vf_config(struct net_device *netdev,
 	struct i40e_vf *vf;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	ret = i40e_validate_vf(pf, vf_id);
 	if (ret)
@@ -4209,6 +4242,7 @@ int i40e_ndo_get_vf_config(struct net_device *netdev,
 	ret = 0;
 
 error_param:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -4230,6 +4264,11 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 	int abs_vf_id;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	if (vf_id >= pf->num_alloc_vfs) {
 		dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
@@ -4273,6 +4312,7 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 			       0, (u8 *)&pfe, sizeof(pfe), NULL);
 
 error_out:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -4294,6 +4334,11 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable)
 	struct i40e_vf *vf;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	if (vf_id >= pf->num_alloc_vfs) {
 		dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
@@ -4327,6 +4372,7 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable)
 		ret = -EIO;
 	}
 out:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -4345,15 +4391,22 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting)
 	struct i40e_vf *vf;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	if (vf_id >= pf->num_alloc_vfs) {
 		dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	if (pf->flags & I40E_FLAG_MFP_ENABLED) {
 		dev_err(&pf->pdev->dev, "Trusted VF not supported in MFP mode.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	vf = &pf->vf[vf_id];
@@ -4376,5 +4429,6 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting)
 	}
 
 out:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
-- 
cgit v1.2.3


From c95cb7b25f25b8145407cf89ae45dfac113760e4 Mon Sep 17 00:00:00 2001
From: Alice Michael <alice.michael@intel.com>
Date: Tue, 30 Oct 2018 10:50:46 -0700
Subject: i40e: update driver version

The version numbers have not been kept up to date and this is
an effort to ammend that.

Signed-off-by: Alice Michael <alice.michael@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b6f4ebb4557e..dbd6fffd9b85 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -26,8 +26,8 @@ static const char i40e_driver_string[] =
 #define DRV_KERN "-k"
 
 #define DRV_VERSION_MAJOR 2
-#define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 2
+#define DRV_VERSION_MINOR 7
+#define DRV_VERSION_BUILD 6
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
-- 
cgit v1.2.3


From 5734fe87486e858124ec30d73be0a265e02c042c Mon Sep 17 00:00:00 2001
From: Patryk Małek <patryk.malek@intel.com>
Date: Tue, 30 Oct 2018 10:50:47 -0700
Subject: i40e: Allow disabling FW LLDP on X722 devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch allows disabling FW LLDP agent on X722 devices.
It also changes a source of information for this feature from
pf->hw_features to pf->hw.flags which are set in i40e_init_adminq.

Signed-off-by: Patryk Małek <patryk.malek@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h         |  1 -
 drivers/net/ethernet/intel/i40e/i40e_common.c  |  3 +++
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 13 +++++++------
 drivers/net/ethernet/intel/i40e/i40e_main.c    | 15 +++++++--------
 4 files changed, 17 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 5595a4614206..cda37d7ae5d6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -495,7 +495,6 @@ struct i40e_pf {
 #define I40E_HW_STOP_FW_LLDP			BIT(16)
 #define I40E_HW_PORT_ID_VALID			BIT(17)
 #define I40E_HW_RESTART_AUTONEG			BIT(18)
-#define I40E_HW_STOPPABLE_FW_LLDP		BIT(19)
 
 	u32 flags;
 #define I40E_FLAG_RX_CSUM_ENABLED		BIT(0)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 85f75b5978fc..97a9b1fb4763 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -3723,6 +3723,9 @@ i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable,
 		(struct i40e_aqc_set_dcb_parameters *)&desc.params.raw;
 	i40e_status status;
 
+	if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE))
+		return I40E_ERR_DEVICE_NOT_SUPPORTED;
+
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_dcb_parameters);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 9c1211ad2c6b..311edac272aa 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -4660,14 +4660,15 @@ flags_complete:
 		return -EOPNOTSUPP;
 
 	/* If the driver detected FW LLDP was disabled on init, this flag could
-	 * be set, however we do not support _changing_ the flag if NPAR is
-	 * enabled or FW API version < 1.7.  There are situations where older
-	 * FW versions/NPAR enabled PFs could disable LLDP, however we _must_
-	 * not allow the user to enable/disable LLDP with this flag on
-	 * unsupported FW versions.
+	 * be set, however we do not support _changing_ the flag:
+	 * - on XL710 if NPAR is enabled or FW API version < 1.7
+	 * - on X722 with FW API version < 1.6
+	 * There are situations where older FW versions/NPAR enabled PFs could
+	 * disable LLDP, however we _must_ not allow the user to enable/disable
+	 * LLDP with this flag on unsupported FW versions.
 	 */
 	if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) {
-		if (!(pf->hw_features & I40E_HW_STOPPABLE_FW_LLDP)) {
+		if (!(pf->hw.flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE)) {
 			dev_warn(&pf->pdev->dev,
 				 "Device does not support changing FW LLDP\n");
 			return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index dbd6fffd9b85..d4461eec26bd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11331,16 +11331,15 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		/* IWARP needs one extra vector for CQP just like MISC.*/
 		pf->num_iwarp_msix = (int)num_online_cpus() + 1;
 	}
-	/* Stopping the FW LLDP engine is only supported on the
-	 * XL710 with a FW ver >= 1.7.  Also, stopping FW LLDP
-	 * engine is not supported if NPAR is functioning on this
-	 * part
+	/* Stopping FW LLDP engine is supported on XL710 and X722
+	 * starting from FW versions determined in i40e_init_adminq.
+	 * Stopping the FW LLDP engine is not supported on XL710
+	 * if NPAR is functioning so unset this hw flag in this case.
 	 */
 	if (pf->hw.mac.type == I40E_MAC_XL710 &&
-	    !pf->hw.func_caps.npar_enable &&
-	    (pf->hw.aq.api_maj_ver > 1 ||
-	     (pf->hw.aq.api_maj_ver == 1 && pf->hw.aq.api_min_ver > 6)))
-		pf->hw_features |= I40E_HW_STOPPABLE_FW_LLDP;
+	    pf->hw.func_caps.npar_enable &&
+	    (pf->hw.flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE))
+		pf->hw.flags &= ~I40E_HW_FLAG_FW_LLDP_STOPPABLE;
 
 #ifdef CONFIG_PCI_IOV
 	if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) {
-- 
cgit v1.2.3


From 7c3758f7839377ab67529cc50264a640636c47af Mon Sep 17 00:00:00 2001
From: Mitch Williams <mitch.a.williams@intel.com>
Date: Fri, 26 Oct 2018 14:33:28 -0700
Subject: i40e: don't restart nway if autoneg not supported

On link types that do not support autoneg, we cannot attempt to restart
nway negotiation. This results in a dead link that requires a power
cycle to remedy.

Fix this by saving off the autoneg state and checking this value before
we try to restart nway.

Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 311edac272aa..1ed241a5c3f4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1335,6 +1335,7 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 	i40e_status status;
 	u8 aq_failures;
 	int err = 0;
+	u32 is_an;
 
 	/* Changing the port's flow control is not supported if this isn't the
 	 * port's controlling PF
@@ -1347,15 +1348,14 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 	if (vsi != pf->vsi[pf->lan_vsi])
 		return -EOPNOTSUPP;
 
-	if (pause->autoneg != ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
-	    AUTONEG_ENABLE : AUTONEG_DISABLE)) {
+	is_an = hw_link_info->an_info & I40E_AQ_AN_COMPLETED;
+	if (pause->autoneg != is_an) {
 		netdev_info(netdev, "To change autoneg please use: ethtool -s <dev> autoneg <on|off>\n");
 		return -EOPNOTSUPP;
 	}
 
 	/* If we have link and don't have autoneg */
-	if (!test_bit(__I40E_DOWN, pf->state) &&
-	    !(hw_link_info->an_info & I40E_AQ_AN_COMPLETED)) {
+	if (!test_bit(__I40E_DOWN, pf->state) && !is_an) {
 		/* Send message that it might not necessarily work*/
 		netdev_info(netdev, "Autoneg did not complete so changing settings may not result in an actual change.\n");
 	}
@@ -1406,7 +1406,7 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 		err = -EAGAIN;
 	}
 
-	if (!test_bit(__I40E_DOWN, pf->state)) {
+	if (!test_bit(__I40E_DOWN, pf->state) && is_an) {
 		/* Give it a little more time to try to come back */
 		msleep(75);
 		if (!test_bit(__I40E_DOWN, pf->state))
-- 
cgit v1.2.3


From 61bfb0600551808ff12a1e06795ef960f0544a36 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 26 Oct 2018 14:33:29 -0700
Subject: i40e: always set ks->base.speed in i40e_get_settings_link_up

In i40e_get_settings_link_up, set ks->base.speed to SPEED_UNKNOWN
in the case where we don't know the link speed.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 1ed241a5c3f4..a6bc7847346b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -906,6 +906,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 		ks->base.speed = SPEED_100;
 		break;
 	default:
+		ks->base.speed = SPEED_UNKNOWN;
 		break;
 	}
 	ks->base.duplex = DUPLEX_FULL;
-- 
cgit v1.2.3


From c9a983058ad6ffa59b950b87e4888a43c12ebb26 Mon Sep 17 00:00:00 2001
From: Alice Michael <alice.michael@intel.com>
Date: Fri, 26 Oct 2018 14:33:30 -0700
Subject: virtchnl: white space and reorder

White space change.

Move the check on the virtchnl_vsi_queue_config_info struct
to be close to the struct like all the other similar checks.
This keeps it clearer and easier to read.

Signed-off-by: Alice Michael <alice.michael@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 include/linux/avf/virtchnl.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index b2488055fd1d..3130dec40b93 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -171,7 +171,7 @@ struct virtchnl_msg {
 
 VIRTCHNL_CHECK_STRUCT_LEN(20, virtchnl_msg);
 
-/* Message descriptions and data structures.*/
+/* Message descriptions and data structures. */
 
 /* VIRTCHNL_OP_VERSION
  * VF posts its version number to the PF. PF responds with its version number
@@ -342,6 +342,8 @@ struct virtchnl_vsi_queue_config_info {
 	struct virtchnl_queue_pair_info qpair[1];
 };
 
+VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info);
+
 /* VIRTCHNL_OP_REQUEST_QUEUES
  * VF sends this message to request the PF to allocate additional queues to
  * this VF.  Each VF gets a guaranteed number of queues on init but asking for
@@ -357,8 +359,6 @@ struct virtchnl_vf_res_request {
 	u16 num_queue_pairs;
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info);
-
 /* VIRTCHNL_OP_CONFIG_IRQ_MAP
  * VF uses this message to map vectors to queues.
  * The rxq_map and txq_map fields are bitmaps used to indicate which queues
-- 
cgit v1.2.3


From 843faff87af261bf55eda719a06087af0486a168 Mon Sep 17 00:00:00 2001
From: Alice Michael <alice.michael@intel.com>
Date: Fri, 26 Oct 2018 14:33:31 -0700
Subject: virtchnl: Fix off by one error

When calculating the valid length for a VIRTCHNL_OP_ENABLE_CHANNELS
message, we accidentally allowed messages with one extra
virtchnl_channel_info structure on the end. This happened due
to an off by one error, because we forgot that valid_len already
accounted for one virtchnl_channel_info structure, so we need to
subtract one from the num_tc value.

Signed-off-by: Alice Michael <alice.michael@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 include/linux/avf/virtchnl.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 3130dec40b93..7605b5919c3a 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -819,8 +819,8 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 		if (msglen >= valid_len) {
 			struct virtchnl_tc_info *vti =
 				(struct virtchnl_tc_info *)msg;
-			valid_len += vti->num_tc *
-				sizeof(struct virtchnl_channel_info);
+			valid_len += (vti->num_tc - 1) *
+				     sizeof(struct virtchnl_channel_info);
 			if (vti->num_tc == 0)
 				err_msg_format = true;
 		}
-- 
cgit v1.2.3


From 211257a499c632052669526c7e643f6ac51e3fc8 Mon Sep 17 00:00:00 2001
From: Richard Rodriguez <richard.rodriguez@intel.com>
Date: Fri, 26 Oct 2018 14:33:32 -0700
Subject: i40e: Use correct shift for VLAN priority

When using port VLAN, for VFs, and setting priority bits, the device
was sending out incorrect priority bits, and also setting the CFI
bit incorrectly.

To fix this, changed shift and mask bit definition for this function, to
use the correct ones.

Signed-off-by: Richard Rodriguez <richard.rodriguez@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index bf67d62e2b5f..f9621026beef 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -13,9 +13,9 @@
 #define I40E_DEFAULT_NUM_MDD_EVENTS_ALLOWED	3
 #define I40E_DEFAULT_NUM_INVALID_MSGS_ALLOWED	10
 
-#define I40E_VLAN_PRIORITY_SHIFT	12
+#define I40E_VLAN_PRIORITY_SHIFT	13
 #define I40E_VLAN_MASK			0xFFF
-#define I40E_PRIORITY_MASK		0x7000
+#define I40E_PRIORITY_MASK		0xE000
 
 /* Various queue ctrls */
 enum i40e_queue_ctrl {
-- 
cgit v1.2.3


From 7cd8eb0861981ad212ce4242a1870c4b5831ceff Mon Sep 17 00:00:00 2001
From: Mitch Williams <mitch.a.williams@intel.com>
Date: Fri, 26 Oct 2018 14:33:33 -0700
Subject: i40e: suppress bogus error message

The i40e driver complains about unprivileged VFs trying to configure
promiscuous mode each time a VF reset occurs. This isn't the fault of
the poor VF driver - the PF driver itself is making the request.

To fix this, skip the privilege check if the request is to disable all
promiscuous activity. This gets rid of the bogus message, but doesn't
affect privilege checks, since we really only care if the unprivileged
VF is trying to enable promiscuous mode.

Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 8e0a247e7e5a..2ac23ebfbf31 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1112,7 +1112,8 @@ static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf,
 	if (!i40e_vc_isvalid_vsi_id(vf, vsi_id) || !vsi)
 		return I40E_ERR_PARAM;
 
-	if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) {
+	if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) &&
+	    (allmulti || alluni)) {
 		dev_err(&pf->pdev->dev,
 			"Unprivileged VF %d is attempting to configure promiscuous mode\n",
 			vf->vf_id);
-- 
cgit v1.2.3


From d5585b7b6846a6d0f9517afe57be3843150719da Mon Sep 17 00:00:00 2001
From: Alan Brady <alan.brady@intel.com>
Date: Mon, 29 Oct 2018 11:27:21 -0700
Subject: i40e: prevent overlapping tx_timeout recover

If a TX hang occurs, we attempt to recover by incrementally resetting.
If we're starved for CPU time, it's possible the reset doesn't actually
complete (or even fire) before another tx_timeout fires causing us to
fly through the different resets without actually doing them.

This adds a bit to set and check if a timeout recovery is already
pending and, if so, bail out of tx_timeout.  The bit will get cleared at
the end of i40e_rebuild when reset is complete.

Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h      | 1 +
 drivers/net/ethernet/intel/i40e/i40e_main.c | 5 +++++
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index cda37d7ae5d6..8de9085bba9e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -122,6 +122,7 @@ enum i40e_state_t {
 	__I40E_MDD_EVENT_PENDING,
 	__I40E_VFLR_EVENT_PENDING,
 	__I40E_RESET_RECOVERY_PENDING,
+	__I40E_TIMEOUT_RECOVERY_PENDING,
 	__I40E_MISC_IRQ_REQUESTED,
 	__I40E_RESET_INTR_RECEIVED,
 	__I40E_REINIT_REQUESTED,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index d4461eec26bd..47f0fdadbac9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -338,6 +338,10 @@ static void i40e_tx_timeout(struct net_device *netdev)
 		      (pf->tx_timeout_last_recovery + netdev->watchdog_timeo)))
 		return;   /* don't do any new action before the next timeout */
 
+	/* don't kick off another recovery if one is already pending */
+	if (test_and_set_bit(__I40E_TIMEOUT_RECOVERY_PENDING, pf->state))
+		return;
+
 	if (tx_ring) {
 		head = i40e_get_head(tx_ring);
 		/* Read interrupt register */
@@ -9631,6 +9635,7 @@ end_core_reset:
 	clear_bit(__I40E_RESET_FAILED, pf->state);
 clear_recovery:
 	clear_bit(__I40E_RESET_RECOVERY_PENDING, pf->state);
+	clear_bit(__I40E_TIMEOUT_RECOVERY_PENDING, pf->state);
 }
 
 /**
-- 
cgit v1.2.3


From 4fc735d934ef8afb2f12d19293e3418d14ba6ba2 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 13 Nov 2018 14:23:28 +0000
Subject: af_key: fix indentation on declaration statement

There is an indentation issue before the declaration of xfrm_ctx. Remove
spaces and replace with a tab.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/key/af_key.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/key/af_key.c b/net/key/af_key.c
index 9d61266526e7..655c787f9d54 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2020,7 +2020,7 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol)
 
 static inline int pfkey_xfrm_policy2sec_ctx_size(const struct xfrm_policy *xp)
 {
-  struct xfrm_sec_ctx *xfrm_ctx = xp->security;
+	struct xfrm_sec_ctx *xfrm_ctx = xp->security;
 
 	if (xfrm_ctx) {
 		int len = sizeof(struct sadb_x_sec_ctx);
-- 
cgit v1.2.3


From 7759d6a837edf3e2cc627d3bd7167c6fec637d64 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 13 Nov 2018 14:28:42 +0000
Subject: xfrm: policy: add missing indentation

There is a missing indentation before the goto statement. Add it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index bd80b8a4322f..e8b8e722da62 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2782,7 +2782,7 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 		pq->timeout = pq->timeout << 1;
 		if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout))
 			xfrm_pol_hold(pol);
-	goto out;
+		goto out;
 	}
 
 	dst_release(dst);
-- 
cgit v1.2.3


From 39aa6928d462d0f4fd809ff8109f98f24843b28b Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 15 Nov 2018 02:51:57 +0100
Subject: xfrm: policy: fix netlink/pf_key policy lookups

Colin Ian King says:
 Static analysis with CoverityScan found a potential issue [..]
 It seems that pointer pol is set to NULL and then a check to see if it
 is non-null is used to set pol to tmp; howeverm this check is always
 going to be false because pol is always NULL.

Fix this and update test script to catch this.  Updated script only:
./xfrm_policy.sh ; echo $?
RTNETLINK answers: No such file or directory
FAIL: ip -net ns3 xfrm policy get src 10.0.1.0/24 dst 10.0.2.0/24 dir out
RTNETLINK answers: No such file or directory
[..]
PASS: policy before exception matches
PASS: ping to .254 bypassed ipsec tunnel
PASS: direct policy matches
PASS: policy matches
1

Fixes: 6be3b0db6db ("xfrm: policy: add inexact policy search tree infrastructure")
Reported-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c                     |  5 +++-
 tools/testing/selftests/net/xfrm_policy.sh | 38 +++++++++++++++++++++++++-----
 2 files changed, 36 insertions(+), 7 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index e8b8e722da62..ddc3335dd552 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1663,7 +1663,10 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 			tmp = __xfrm_policy_bysel_ctx(cand.res[i], mark,
 						      if_id, type, dir,
 						      sel, ctx);
-			if (tmp && pol && tmp->pos < pol->pos)
+			if (!tmp)
+				continue;
+
+			if (!pol || tmp->pos < pol->pos)
 				pol = tmp;
 		}
 	} else {
diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh
index 6ca63a6e50e9..8db35b99457c 100755
--- a/tools/testing/selftests/net/xfrm_policy.sh
+++ b/tools/testing/selftests/net/xfrm_policy.sh
@@ -21,6 +21,7 @@
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 ret=0
+policy_checks_ok=1
 
 KEY_SHA=0xdeadbeef1234567890abcdefabcdefabcdefabcd
 KEY_AES=0x0123456789abcdef0123456789012345
@@ -45,6 +46,26 @@ do_esp() {
     ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow
 }
 
+do_esp_policy_get_check() {
+    local ns=$1
+    local lnet=$2
+    local rnet=$3
+
+    ip -net $ns xfrm policy get src $lnet dst $rnet dir out > /dev/null
+    if [ $? -ne 0 ] && [ $policy_checks_ok -eq 1 ] ;then
+        policy_checks_ok=0
+        echo "FAIL: ip -net $ns xfrm policy get src $lnet dst $rnet dir out"
+        ret=1
+    fi
+
+    ip -net $ns xfrm policy get src $rnet dst $lnet dir fwd > /dev/null
+    if [ $? -ne 0 ] && [ $policy_checks_ok -eq 1 ] ;then
+        policy_checks_ok=0
+        echo "FAIL: ip -net $ns xfrm policy get src $rnet dst $lnet dir fwd"
+        ret=1
+    fi
+}
+
 do_exception() {
     local ns=$1
     local me=$2
@@ -112,31 +133,31 @@ check_xfrm() {
 	# 1: iptables -m policy rule count != 0
 	rval=$1
 	ip=$2
-	ret=0
+	lret=0
 
 	ip netns exec ns1 ping -q -c 1 10.0.2.$ip > /dev/null
 
 	check_ipt_policy_count ns3
 	if [ $? -ne $rval ] ; then
-		ret=1
+		lret=1
 	fi
 	check_ipt_policy_count ns4
 	if [ $? -ne $rval ] ; then
-		ret=1
+		lret=1
 	fi
 
 	ip netns exec ns2 ping -q -c 1 10.0.1.$ip > /dev/null
 
 	check_ipt_policy_count ns3
 	if [ $? -ne $rval ] ; then
-		ret=1
+		lret=1
 	fi
 	check_ipt_policy_count ns4
 	if [ $? -ne $rval ] ; then
-		ret=1
+		lret=1
 	fi
 
-	return $ret
+	return $lret
 }
 
 #check for needed privileges
@@ -227,6 +248,11 @@ do_esp ns4 dead:3::10 dead:3::1 dead:2::/64 dead:1::/64 $SPI2 $SPI1
 do_dummies4 ns3
 do_dummies6 ns4
 
+do_esp_policy_get_check ns3 10.0.1.0/24 10.0.2.0/24
+do_esp_policy_get_check ns4 10.0.2.0/24 10.0.1.0/24
+do_esp_policy_get_check ns3 dead:1::/64 dead:2::/64
+do_esp_policy_get_check ns4 dead:2::/64 dead:1::/64
+
 # ping to .254 should use ipsec, exception is not installed.
 check_xfrm 1 254
 if [ $? -ne 0 ]; then
-- 
cgit v1.2.3


From ba2f55b06826fb51f15e3cb04b4457be5f66e0ef Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 11 Nov 2018 21:49:12 +0100
Subject: net: phy: icplus: add config_intr callback

Move IRQ configuration for IP101A/G from config_init to config_intr
callback. Reasons:

1. This allows phylib to disable interrupts if needed.
2. Icplus was the only driver supporting interrupts w/o defining a
   config_intr callback. Now we can add a phylib plausibility check
   disabling interrupt mode if one of the two irq-related callbacks
   isn't defined.

I don't own hardware with this PHY, and the change is based on the
datasheet for IP101A LF (which is supposed to be register-compatible
with IP101A/G). Change is compile-tested only.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/icplus.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index 21ce68964204..ad87bd3280d7 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -42,8 +42,8 @@ MODULE_LICENSE("GPL");
 #define IP1001_APS_ON			11	/* IP1001 APS Mode  bit */
 #define IP101A_G_APS_ON			2	/* IP101A/G APS Mode bit */
 #define IP101A_G_IRQ_CONF_STATUS	0x11	/* Conf Info IRQ & Status Reg */
-#define	IP101A_G_IRQ_PIN_USED		(1<<15) /* INTR pin used */
-#define	IP101A_G_IRQ_DEFAULT		IP101A_G_IRQ_PIN_USED
+#define	IP101A_G_IRQ_PIN_USED		BIT(15) /* INTR pin used */
+#define	IP101A_G_NO_IRQ			BIT(11) /* IRQ's inactive */
 
 static int ip175c_config_init(struct phy_device *phydev)
 {
@@ -170,11 +170,6 @@ static int ip101a_g_config_init(struct phy_device *phydev)
 	if (c < 0)
 		return c;
 
-	/* INTR pin used: speed/link/duplex will cause an interrupt */
-	c = phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, IP101A_G_IRQ_DEFAULT);
-	if (c < 0)
-		return c;
-
 	/* Enable Auto Power Saving mode */
 	c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS);
 	c |= IP101A_G_APS_ON;
@@ -201,6 +196,19 @@ static int ip175c_config_aneg(struct phy_device *phydev)
 	return 0;
 }
 
+static int ip101a_g_config_intr(struct phy_device *phydev)
+{
+	u16 val;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		/* INTR pin used: Speed/link/duplex will cause an interrupt */
+		val = IP101A_G_IRQ_PIN_USED;
+	else
+		val = IP101A_G_NO_IRQ;
+
+	return phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, val);
+}
+
 static int ip101a_g_ack_interrupt(struct phy_device *phydev)
 {
 	int err = phy_read(phydev, IP101A_G_IRQ_CONF_STATUS);
@@ -234,6 +242,7 @@ static struct phy_driver icplus_driver[] = {
 	.name		= "ICPlus IP101A/G",
 	.phy_id_mask	= 0x0ffffff0,
 	.features	= PHY_BASIC_FEATURES,
+	.config_intr	= ip101a_g_config_intr,
 	.ack_interrupt	= ip101a_g_ack_interrupt,
 	.config_init	= &ip101a_g_config_init,
 	.suspend	= genphy_suspend,
-- 
cgit v1.2.3


From b26a6fea229885e98e9383c53b5c5dcfc45f76d8 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 15 Nov 2018 09:29:21 +0000
Subject: net: hns3: Enable HW GRO for Rev B(=0x21) HNS3 hardware

HNS3 hardware Revision B(=0x21) supports Hardware GRO feature. This
patch enables this feature in the HNS3 PF/VF driver.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  4 +++
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    |  4 ++-
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |  7 +++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 30 +++++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h   |  8 ++++++
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 31 ++++++++++++++++++++++
 6 files changed, 83 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index f69d39f17bdd..21d934b7a2a3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -52,6 +52,7 @@
 #define HNAE3_UNIC_CLIENT_INITED_B		0x4
 #define HNAE3_ROCE_CLIENT_INITED_B		0x5
 #define HNAE3_DEV_SUPPORT_FD_B			0x6
+#define HNAE3_DEV_SUPPORT_GRO_B			0x7
 
 #define HNAE3_DEV_SUPPORT_ROCE_DCB_BITS (BIT(HNAE3_DEV_SUPPORT_DCB_B) |\
 		BIT(HNAE3_DEV_SUPPORT_ROCE_B))
@@ -65,6 +66,9 @@
 #define hnae3_dev_fd_supported(hdev) \
 	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B)
 
+#define hnae3_dev_gro_supported(hdev) \
+	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_GRO_B)
+
 #define ring_ptr_move_fw(ring, p) \
 	((ring)->p = ((ring)->p + 1) % (ring)->desc_num)
 #define ring_ptr_move_bw(ring, p) \
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 8d07ec668d5d..a510ddfd45a5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1714,8 +1714,10 @@ static void hns3_disable_sriov(struct pci_dev *pdev)
 static void hns3_get_dev_capability(struct pci_dev *pdev,
 				    struct hnae3_ae_dev *ae_dev)
 {
-	if (pdev->revision >= 0x21)
+	if (pdev->revision >= 0x21) {
 		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B, 1);
+		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_SUPPORT_GRO_B, 1);
+	}
 }
 
 /* hns3_probe - Device initialization routine
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 872cd4bdd70d..aef044d08b11 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -152,6 +152,7 @@ enum hclge_opcode_type {
 
 	/* TSO command */
 	HCLGE_OPC_TSO_GENERIC_CONFIG	= 0x0C01,
+	HCLGE_OPC_GRO_GENERIC_CONFIG    = 0x0C10,
 
 	/* RSS commands */
 	HCLGE_OPC_RSS_GENERIC_CONFIG	= 0x0D01,
@@ -758,6 +759,12 @@ struct hclge_cfg_tso_status_cmd {
 	u8 rsv[20];
 };
 
+#define HCLGE_GRO_EN_B		0
+struct hclge_cfg_gro_status_cmd {
+	__le16 gro_en;
+	u8 rsv[22];
+};
+
 #define HCLGE_TSO_MSS_MIN	256
 #define HCLGE_TSO_MSS_MAX	9668
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 43bfc730a62d..3f8bd11d0824 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -921,6 +921,28 @@ static int hclge_config_tso(struct hclge_dev *hdev, int tso_mss_min,
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
 
+static int hclge_config_gro(struct hclge_dev *hdev, bool en)
+{
+	struct hclge_cfg_gro_status_cmd *req;
+	struct hclge_desc desc;
+	int ret;
+
+	if (!hnae3_dev_gro_supported(hdev))
+		return 0;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_GRO_GENERIC_CONFIG, false);
+	req = (struct hclge_cfg_gro_status_cmd *)desc.data;
+
+	req->gro_en = cpu_to_le16(en ? 1 : 0);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"GRO hardware config cmd failed, ret = %d\n", ret);
+
+	return ret;
+}
+
 static int hclge_alloc_tqps(struct hclge_dev *hdev)
 {
 	struct hclge_tqp *tqp;
@@ -7090,6 +7112,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		goto err_mdiobus_unreg;
 	}
 
+	ret = hclge_config_gro(hdev, true);
+	if (ret)
+		goto err_mdiobus_unreg;
+
 	ret = hclge_init_vlan_config(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret);
@@ -7221,6 +7247,10 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
+	ret = hclge_config_gro(hdev, true);
+	if (ret)
+		return ret;
+
 	ret = hclge_init_vlan_config(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index 090541de0c7d..47030b42341f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -87,6 +87,8 @@ enum hclgevf_opcode_type {
 	HCLGEVF_OPC_QUERY_TX_STATUS	= 0x0B03,
 	HCLGEVF_OPC_QUERY_RX_STATUS	= 0x0B13,
 	HCLGEVF_OPC_CFG_COM_TQP_QUEUE	= 0x0B20,
+	/* GRO command */
+	HCLGEVF_OPC_GRO_GENERIC_CONFIG  = 0x0C10,
 	/* RSS cmd */
 	HCLGEVF_OPC_RSS_GENERIC_CONFIG	= 0x0D01,
 	HCLGEVF_OPC_RSS_INPUT_TUPLE     = 0x0D02,
@@ -149,6 +151,12 @@ struct hclgevf_query_res_cmd {
 	__le16 rsv[7];
 };
 
+#define HCLGEVF_GRO_EN_B               0
+struct hclgevf_cfg_gro_status_cmd {
+	__le16 gro_en;
+	u8 rsv[22];
+};
+
 #define HCLGEVF_RSS_DEFAULT_OUTPORT_B	4
 #define HCLGEVF_RSS_HASH_KEY_OFFSET_B	4
 #define HCLGEVF_RSS_HASH_KEY_NUM	16
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 6b4d1477055f..2e889b829976 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1655,6 +1655,29 @@ static int hclgevf_init_roce_base_info(struct hclgevf_dev *hdev)
 	return 0;
 }
 
+static int hclgevf_config_gro(struct hclgevf_dev *hdev, bool en)
+{
+	struct hclgevf_cfg_gro_status_cmd *req;
+	struct hclgevf_desc desc;
+	int ret;
+
+	if (!hnae3_dev_gro_supported(hdev))
+		return 0;
+
+	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_GRO_GENERIC_CONFIG,
+				     false);
+	req = (struct hclgevf_cfg_gro_status_cmd *)desc.data;
+
+	req->gro_en = cpu_to_le16(en ? 1 : 0);
+
+	ret = hclgevf_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"VF GRO hardware config cmd failed, ret = %d.\n", ret);
+
+	return ret;
+}
+
 static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
 {
 	struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg;
@@ -2122,6 +2145,10 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 		return ret;
 	}
 
+	ret = hclgevf_config_gro(hdev, true);
+	if (ret)
+		return ret;
+
 	ret = hclgevf_init_vlan_config(hdev);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
@@ -2199,6 +2226,10 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_config;
 	}
 
+	ret = hclgevf_config_gro(hdev, true);
+	if (ret)
+		goto err_config;
+
 	/* Initialize RSS for this VF */
 	ret = hclgevf_rss_init_hw(hdev);
 	if (ret) {
-- 
cgit v1.2.3


From e5597095055622c248c2f5135a5328f86ac6bb14 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 15 Nov 2018 09:29:22 +0000
Subject: net: hns3: Add handling of GRO Pkts not fully RX'ed in NAPI poll

The "FE bit" in the description means the last description for
a packets. When HW GRO enable, HW write data to ring every
packet/buffer, there is greater probability that driver handle
with the describtion but HW still not set the "FE bit".

When drier handle the packet and HW still not set "FE bit",
driver stores skb and bd_num in rx ring, and continue to use the
skb and bd_num in next napi.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 196 ++++++++++++++++--------
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h |   6 +
 2 files changed, 140 insertions(+), 62 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index a510ddfd45a5..d8c5e1198670 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2383,6 +2383,90 @@ static bool hns3_parse_vlan_tag(struct hns3_enet_ring *ring,
 	}
 }
 
+static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length,
+			  unsigned char *va)
+{
+#define HNS3_NEED_ADD_FRAG	1
+	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_clean];
+	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
+	struct sk_buff *skb;
+
+	ring->skb = napi_alloc_skb(&ring->tqp_vector->napi, HNS3_RX_HEAD_SIZE);
+	skb = ring->skb;
+	if (unlikely(!skb)) {
+		netdev_err(netdev, "alloc rx skb fail\n");
+
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.sw_err_cnt++;
+		u64_stats_update_end(&ring->syncp);
+
+		return -ENOMEM;
+	}
+
+	prefetchw(skb->data);
+
+	ring->pending_buf = 1;
+	if (length <= HNS3_RX_HEAD_SIZE) {
+		memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long)));
+
+		/* We can reuse buffer as-is, just make sure it is local */
+		if (likely(page_to_nid(desc_cb->priv) == numa_node_id()))
+			desc_cb->reuse_flag = 1;
+		else /* This page cannot be reused so discard it */
+			put_page(desc_cb->priv);
+
+		ring_ptr_move_fw(ring, next_to_clean);
+		return 0;
+	}
+	u64_stats_update_begin(&ring->syncp);
+	ring->stats.seg_pkt_cnt++;
+	u64_stats_update_end(&ring->syncp);
+
+	ring->pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE);
+	__skb_put(skb, ring->pull_len);
+	hns3_nic_reuse_page(skb, 0, ring, ring->pull_len,
+			    desc_cb);
+	ring_ptr_move_fw(ring, next_to_clean);
+
+	return HNS3_NEED_ADD_FRAG;
+}
+
+static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
+			 struct sk_buff **out_skb, bool pending)
+{
+	struct sk_buff *skb = *out_skb;
+	struct hns3_desc_cb *desc_cb;
+	struct hns3_desc *pre_desc;
+	u32 bd_base_info;
+	int pre_bd;
+
+	/* if there is pending bd, the SW param next_to_clean has moved
+	 * to next and the next is NULL
+	 */
+	if (pending) {
+		pre_bd = (ring->next_to_clean - 1 + ring->desc_num) %
+			ring->desc_num;
+		pre_desc = &ring->desc[pre_bd];
+		bd_base_info = le32_to_cpu(pre_desc->rx.bd_base_info);
+	} else {
+		bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
+	}
+
+	while (!hnae3_get_bit(bd_base_info, HNS3_RXD_FE_B)) {
+		desc = &ring->desc[ring->next_to_clean];
+		desc_cb = &ring->desc_cb[ring->next_to_clean];
+		bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
+		if (!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))
+			return -ENXIO;
+
+		hns3_nic_reuse_page(skb, ring->pending_buf, ring, 0, desc_cb);
+		ring_ptr_move_fw(ring, next_to_clean);
+		ring->pending_buf++;
+	}
+
+	return 0;
+}
+
 static void hns3_set_rx_skb_rss_type(struct hns3_enet_ring *ring,
 				     struct sk_buff *skb)
 {
@@ -2399,18 +2483,16 @@ static void hns3_set_rx_skb_rss_type(struct hns3_enet_ring *ring,
 }
 
 static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
-			     struct sk_buff **out_skb, int *out_bnum)
+			     struct sk_buff **out_skb)
 {
 	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
+	struct sk_buff *skb = ring->skb;
 	struct hns3_desc_cb *desc_cb;
 	struct hns3_desc *desc;
-	struct sk_buff *skb;
-	unsigned char *va;
 	u32 bd_base_info;
-	int pull_len;
 	u32 l234info;
 	int length;
-	int bnum;
+	int ret;
 
 	desc = &ring->desc[ring->next_to_clean];
 	desc_cb = &ring->desc_cb[ring->next_to_clean];
@@ -2422,9 +2504,10 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 
 	/* Check valid BD */
 	if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B)))
-		return -EFAULT;
+		return -ENXIO;
 
-	va = (unsigned char *)desc_cb->buf + desc_cb->page_offset;
+	if (!skb)
+		ring->va = (unsigned char *)desc_cb->buf + desc_cb->page_offset;
 
 	/* Prefetch first cache line of first page
 	 * Idea is to cache few bytes of the header of the packet. Our L1 Cache
@@ -2433,62 +2516,42 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	 * lines. In such a case, single fetch would suffice to cache in the
 	 * relevant part of the header.
 	 */
-	prefetch(va);
+	prefetch(ring->va);
 #if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
+	prefetch(ring->va + L1_CACHE_BYTES);
 #endif
 
-	skb = *out_skb = napi_alloc_skb(&ring->tqp_vector->napi,
-					HNS3_RX_HEAD_SIZE);
-	if (unlikely(!skb)) {
-		netdev_err(netdev, "alloc rx skb fail\n");
+	if (!skb) {
+		ret = hns3_alloc_skb(ring, length, ring->va);
+		*out_skb = skb = ring->skb;
 
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.sw_err_cnt++;
-		u64_stats_update_end(&ring->syncp);
-
-		return -ENOMEM;
-	}
-
-	prefetchw(skb->data);
-
-	bnum = 1;
-	if (length <= HNS3_RX_HEAD_SIZE) {
-		memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long)));
-
-		/* We can reuse buffer as-is, just make sure it is local */
-		if (likely(page_to_nid(desc_cb->priv) == numa_node_id()))
-			desc_cb->reuse_flag = 1;
-		else /* This page cannot be reused so discard it */
-			put_page(desc_cb->priv);
+		if (ret < 0) /* alloc buffer fail */
+			return ret;
+		if (ret > 0) { /* need add frag */
+			ret = hns3_add_frag(ring, desc, &skb, false);
+			if (ret)
+				return ret;
 
-		ring_ptr_move_fw(ring, next_to_clean);
+			/* As the head data may be changed when GRO enable, copy
+			 * the head data in after other data rx completed
+			 */
+			memcpy(skb->data, ring->va,
+			       ALIGN(ring->pull_len, sizeof(long)));
+		}
 	} else {
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.seg_pkt_cnt++;
-		u64_stats_update_end(&ring->syncp);
-
-		pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE);
-
-		memcpy(__skb_put(skb, pull_len), va,
-		       ALIGN(pull_len, sizeof(long)));
-
-		hns3_nic_reuse_page(skb, 0, ring, pull_len, desc_cb);
-		ring_ptr_move_fw(ring, next_to_clean);
+		ret = hns3_add_frag(ring, desc, &skb, true);
+		if (ret)
+			return ret;
 
-		while (!hnae3_get_bit(bd_base_info, HNS3_RXD_FE_B)) {
-			desc = &ring->desc[ring->next_to_clean];
-			desc_cb = &ring->desc_cb[ring->next_to_clean];
-			bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
-			hns3_nic_reuse_page(skb, bnum, ring, 0, desc_cb);
-			ring_ptr_move_fw(ring, next_to_clean);
-			bnum++;
-		}
+		/* As the head data may be changed when GRO enable, copy
+		 * the head data in after other data rx completed
+		 */
+		memcpy(skb->data, ring->va,
+		       ALIGN(ring->pull_len, sizeof(long)));
 	}
 
-	*out_bnum = bnum;
-
 	l234info = le32_to_cpu(desc->rx.l234_info);
+	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
 
 	/* Based on hw strategy, the tag offloaded will be stored at
 	 * ot_vlan_tag in two layer tag case, and stored at vlan_tag
@@ -2539,6 +2602,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	ring->tqp_vector->rx_group.total_bytes += skb->len;
 
 	hns3_rx_checksum(ring, skb, desc);
+	*out_skb = skb;
 	hns3_set_rx_skb_rss_type(ring, skb);
 
 	return 0;
@@ -2551,9 +2615,9 @@ int hns3_clean_rx_ring(
 #define RCB_NOF_ALLOC_RX_BUFF_ONCE 16
 	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
 	int recv_pkts, recv_bds, clean_count, err;
-	int unused_count = hns3_desc_unused(ring);
-	struct sk_buff *skb = NULL;
-	int num, bnum = 0;
+	int unused_count = hns3_desc_unused(ring) - ring->pending_buf;
+	struct sk_buff *skb = ring->skb;
+	int num;
 
 	num = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG);
 	rmb(); /* Make sure num taken effect before the other data is touched */
@@ -2567,24 +2631,32 @@ int hns3_clean_rx_ring(
 			hns3_nic_alloc_rx_buffers(ring,
 						  clean_count + unused_count);
 			clean_count = 0;
-			unused_count = hns3_desc_unused(ring);
+			unused_count = hns3_desc_unused(ring) -
+					ring->pending_buf;
 		}
 
 		/* Poll one pkt */
-		err = hns3_handle_rx_bd(ring, &skb, &bnum);
+		err = hns3_handle_rx_bd(ring, &skb);
 		if (unlikely(!skb)) /* This fault cannot be repaired */
 			goto out;
 
-		recv_bds += bnum;
-		clean_count += bnum;
-		if (unlikely(err)) {  /* Do jump the err */
-			recv_pkts++;
+		if (err == -ENXIO) { /* Do not get FE for the packet */
+			goto out;
+		} else if (unlikely(err)) {  /* Do jump the err */
+			recv_bds += ring->pending_buf;
+			clean_count += ring->pending_buf;
+			ring->skb = NULL;
+			ring->pending_buf = 0;
 			continue;
 		}
 
 		/* Do update ip stack process */
 		skb->protocol = eth_type_trans(skb, netdev);
 		rx_fn(ring, skb);
+		recv_bds += ring->pending_buf;
+		clean_count += ring->pending_buf;
+		ring->skb = NULL;
+		ring->pending_buf = 0;
 
 		recv_pkts++;
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 10ff18af3cc7..d8c0998127be 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -401,11 +401,17 @@ struct hns3_enet_ring {
 	 */
 	int next_to_clean;
 
+	int pull_len; /* head length for current packet */
+	unsigned char *va; /* first buffer address for current packet */
+
 	u32 flag;          /* ring attribute */
 	int irq_init_flag;
 
 	int numa_node;
 	cpumask_t affinity_mask;
+
+	int pending_buf;
+	struct sk_buff *skb;
 };
 
 struct hns_queue;
-- 
cgit v1.2.3


From 5c9f6b3935f808afdabac560250bcf4333311efc Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 15 Nov 2018 09:29:23 +0000
Subject: net: hns3: Add support for ethtool -K to enable/disable HW GRO

This patch adds support of ethtool -K to enable/disable
hardware GRO in HNS3 PF/VF driver.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h               |  3 +++
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c           | 13 ++++++++++++-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c   |  9 +++++++++
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c |  8 ++++++++
 4 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 21d934b7a2a3..1746172ffbf7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -305,6 +305,8 @@ struct hnae3_ae_dev {
  *   Set vlan filter config of vf
  * enable_hw_strip_rxvtag()
  *   Enable/disable hardware strip vlan tag of packets received
+ * set_gro_en
+ *   Enable/disable HW GRO
  */
 struct hnae3_ae_ops {
 	int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev);
@@ -449,6 +451,7 @@ struct hnae3_ae_ops {
 	bool (*get_hw_reset_stat)(struct hnae3_handle *handle);
 	bool (*ae_dev_resetting)(struct hnae3_handle *handle);
 	unsigned long (*ae_dev_reset_cnt)(struct hnae3_handle *handle);
+	int (*set_gro_en)(struct hnae3_handle *handle, int enable);
 };
 
 struct hnae3_dcb_ops {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index d8c5e1198670..860067898471 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1345,6 +1345,15 @@ static int hns3_nic_set_features(struct net_device *netdev,
 			priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tx;
 	}
 
+	if (changed & (NETIF_F_GRO_HW) && h->ae_algo->ops->set_gro_en) {
+		if (features & NETIF_F_GRO_HW)
+			ret = h->ae_algo->ops->set_gro_en(h, true);
+		else
+			ret = h->ae_algo->ops->set_gro_en(h, false);
+		if (ret)
+			return ret;
+	}
+
 	if ((changed & NETIF_F_HW_VLAN_CTAG_FILTER) &&
 	    h->ae_algo->ops->enable_vlan_filter) {
 		if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
@@ -1929,7 +1938,9 @@ static void hns3_set_default_feature(struct net_device *netdev)
 		NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC;
 
 	if (pdev->revision >= 0x21) {
-		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER |
+			NETIF_F_GRO_HW;
+		netdev->features |= NETIF_F_GRO_HW;
 
 		if (!(h->flags & HNAE3_SUPPORT_VF)) {
 			netdev->hw_features |= NETIF_F_NTUPLE;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 3f8bd11d0824..eb6b6a5f744f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7667,6 +7667,14 @@ static void hclge_get_link_mode(struct hnae3_handle *handle,
 	}
 }
 
+static int hclge_gro_en(struct hnae3_handle *handle, int enable)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	return hclge_config_gro(hdev, enable);
+}
+
 static const struct hnae3_ae_ops hclge_ops = {
 	.init_ae_dev = hclge_init_ae_dev,
 	.uninit_ae_dev = hclge_uninit_ae_dev,
@@ -7738,6 +7746,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.get_hw_reset_stat = hclge_get_hw_reset_stat,
 	.ae_dev_resetting = hclge_ae_dev_resetting,
 	.ae_dev_reset_cnt = hclge_ae_dev_reset_cnt,
+	.set_gro_en = hclge_gro_en,
 };
 
 static struct hnae3_ae_algo ae_algo = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 2e889b829976..e27d6fa85a74 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2368,6 +2368,13 @@ void hclgevf_update_speed_duplex(struct hclgevf_dev *hdev, u32 speed,
 	hdev->hw.mac.duplex = duplex;
 }
 
+static int hclgevf_gro_en(struct hnae3_handle *handle, int enable)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return hclgevf_config_gro(hdev, enable);
+}
+
 static void hclgevf_get_media_type(struct hnae3_handle *handle,
 				  u8 *media_type)
 {
@@ -2442,6 +2449,7 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.get_hw_reset_stat = hclgevf_get_hw_reset_stat,
 	.ae_dev_resetting = hclgevf_ae_dev_resetting,
 	.ae_dev_reset_cnt = hclgevf_ae_dev_reset_cnt,
+	.set_gro_en = hclgevf_gro_en,
 };
 
 static struct hnae3_ae_algo ae_algovf = {
-- 
cgit v1.2.3


From 81ae0e0491f31775d086e24a7cd2a4a4ec29f346 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 15 Nov 2018 09:29:24 +0000
Subject: net: hns3: Add skb chain when num of RX buf exceeds MAX_SKB_FRAGS

MAX_SKB_FRAGS in protocol stack is defined as:

MAX_SKB_FRAGS is 17 when PAGE_SIZE is 4K. If HW enable GRO, it may
merge small packets and the rx buffer may be more than
MAX_SKB_FRAGS. So driver will add skb chain when RX buffer num.
more than MAX_SKB_FRAGS.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 37 +++++++++++++++++++++++--
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h |  2 ++
 2 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 860067898471..7776089b6bc2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2361,6 +2361,9 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 
 static void hns3_rx_skb(struct hns3_enet_ring *ring, struct sk_buff *skb)
 {
+	if (skb_has_frag_list(skb))
+		napi_gro_flush(&ring->tqp_vector->napi, false);
+
 	napi_gro_receive(&ring->tqp_vector->napi, skb);
 }
 
@@ -2417,6 +2420,8 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length,
 	prefetchw(skb->data);
 
 	ring->pending_buf = 1;
+	ring->frag_num = 0;
+	ring->tail_skb = NULL;
 	if (length <= HNS3_RX_HEAD_SIZE) {
 		memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long)));
 
@@ -2435,7 +2440,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length,
 
 	ring->pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE);
 	__skb_put(skb, ring->pull_len);
-	hns3_nic_reuse_page(skb, 0, ring, ring->pull_len,
+	hns3_nic_reuse_page(skb, ring->frag_num++, ring, ring->pull_len,
 			    desc_cb);
 	ring_ptr_move_fw(ring, next_to_clean);
 
@@ -2446,6 +2451,8 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
 			 struct sk_buff **out_skb, bool pending)
 {
 	struct sk_buff *skb = *out_skb;
+	struct sk_buff *head_skb = *out_skb;
+	struct sk_buff *new_skb;
 	struct hns3_desc_cb *desc_cb;
 	struct hns3_desc *pre_desc;
 	u32 bd_base_info;
@@ -2470,7 +2477,33 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
 		if (!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))
 			return -ENXIO;
 
-		hns3_nic_reuse_page(skb, ring->pending_buf, ring, 0, desc_cb);
+		if (unlikely(ring->frag_num >= MAX_SKB_FRAGS)) {
+			new_skb = napi_alloc_skb(&ring->tqp_vector->napi,
+						 HNS3_RX_HEAD_SIZE);
+			if (unlikely(!new_skb)) {
+				netdev_err(ring->tqp->handle->kinfo.netdev,
+					   "alloc rx skb frag fail\n");
+				return -ENXIO;
+			}
+			ring->frag_num = 0;
+
+			if (ring->tail_skb) {
+				ring->tail_skb->next = new_skb;
+				ring->tail_skb = new_skb;
+			} else {
+				skb_shinfo(skb)->frag_list = new_skb;
+				ring->tail_skb = new_skb;
+			}
+		}
+
+		if (ring->tail_skb) {
+			head_skb->truesize += hnae3_buf_size(ring);
+			head_skb->data_len += le16_to_cpu(desc->rx.size);
+			head_skb->len += le16_to_cpu(desc->rx.size);
+			skb = ring->tail_skb;
+		}
+
+		hns3_nic_reuse_page(skb, ring->frag_num++, ring, 0, desc_cb);
 		ring_ptr_move_fw(ring, next_to_clean);
 		ring->pending_buf++;
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index d8c0998127be..8e56b7e44978 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -402,6 +402,7 @@ struct hns3_enet_ring {
 	int next_to_clean;
 
 	int pull_len; /* head length for current packet */
+	u32 frag_num;
 	unsigned char *va; /* first buffer address for current packet */
 
 	u32 flag;          /* ring attribute */
@@ -412,6 +413,7 @@ struct hns3_enet_ring {
 
 	int pending_buf;
 	struct sk_buff *skb;
+	struct sk_buff *tail_skb;
 };
 
 struct hns_queue;
-- 
cgit v1.2.3


From a6d53b97a2e7a70220658dcb3ca06206867a393e Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 15 Nov 2018 09:29:25 +0000
Subject: net: hns3: Adds GRO params to SKB for the stack

When HW GRO enable, protocol stack will not do GRO again,
driver should add gro param to the skb for the protocol
stack..

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 43 +++++++++++++++++++++++++
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h |  9 ++++--
 2 files changed, 49 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 7776089b6bc2..22220af92aa9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -15,6 +15,7 @@
 #include <linux/vermagic.h>
 #include <net/gre.h>
 #include <net/pkt_cls.h>
+#include <net/tcp.h>
 #include <net/vxlan.h>
 
 #include "hnae3.h"
@@ -2318,6 +2319,12 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 	if (!(netdev->features & NETIF_F_RXCSUM))
 		return;
 
+	/* We MUST enable hardware checksum before enabling hardware GRO */
+	if (skb_shinfo(skb)->gso_size) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		return;
+	}
+
 	/* check if hardware has done checksum */
 	if (!hnae3_get_bit(bd_base_info, HNS3_RXD_L3L4P_B))
 		return;
@@ -2511,6 +2518,39 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
 	return 0;
 }
 
+static void hns3_set_gro_param(struct sk_buff *skb, u32 l234info,
+			       u32 bd_base_info)
+{
+	u16 gro_count;
+	u32 l3_type;
+
+	gro_count = hnae3_get_field(l234info, HNS3_RXD_GRO_COUNT_M,
+				    HNS3_RXD_GRO_COUNT_S);
+	/* if there is no HW GRO, do not set gro params */
+	if (!gro_count)
+		return;
+
+	/* tcp_gro_complete() will copy NAPI_GRO_CB(skb)->count
+	 * to skb_shinfo(skb)->gso_segs
+	 */
+	NAPI_GRO_CB(skb)->count = gro_count;
+
+	l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
+				  HNS3_RXD_L3ID_S);
+	if (l3_type == HNS3_L3_TYPE_IPV4)
+		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+	else if (l3_type == HNS3_L3_TYPE_IPV6)
+		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+	else
+		return;
+
+	skb_shinfo(skb)->gso_size = hnae3_get_field(bd_base_info,
+						    HNS3_RXD_GRO_SIZE_M,
+						    HNS3_RXD_GRO_SIZE_S);
+	if (skb_shinfo(skb)->gso_size)
+		tcp_gro_complete(skb);
+}
+
 static void hns3_set_rx_skb_rss_type(struct hns3_enet_ring *ring,
 				     struct sk_buff *skb)
 {
@@ -2645,6 +2685,9 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 
 	ring->tqp_vector->rx_group.total_bytes += skb->len;
 
+	/* This is needed in order to enable forwarding support */
+	hns3_set_gro_param(skb, l234info, bd_base_info);
+
 	hns3_rx_checksum(ring, skb, desc);
 	*out_skb = skb;
 	hns3_set_rx_skb_rss_type(ring, skb);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 8e56b7e44978..3365c9596983 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -109,6 +109,10 @@ enum hns3_nic_state {
 #define HNS3_RXD_DOI_B				21
 #define HNS3_RXD_OL3E_B				22
 #define HNS3_RXD_OL4E_B				23
+#define HNS3_RXD_GRO_COUNT_S			24
+#define HNS3_RXD_GRO_COUNT_M			(0x3f << HNS3_RXD_GRO_COUNT_S)
+#define HNS3_RXD_GRO_FIXID_B			30
+#define HNS3_RXD_GRO_ECN_B			31
 
 #define HNS3_RXD_ODMAC_S			0
 #define HNS3_RXD_ODMAC_M			(0x3 << HNS3_RXD_ODMAC_S)
@@ -135,9 +139,8 @@ enum hns3_nic_state {
 #define HNS3_RXD_TSIND_S			12
 #define HNS3_RXD_TSIND_M			(0x7 << HNS3_RXD_TSIND_S)
 #define HNS3_RXD_LKBK_B				15
-#define HNS3_RXD_HDL_S				16
-#define HNS3_RXD_HDL_M				(0x7ff << HNS3_RXD_HDL_S)
-#define HNS3_RXD_HSIND_B			31
+#define HNS3_RXD_GRO_SIZE_S			16
+#define HNS3_RXD_GRO_SIZE_M			(0x3ff << HNS3_RXD_GRO_SIZE_S)
 
 #define HNS3_TXD_L3T_S				0
 #define HNS3_TXD_L3T_M				(0x3 << HNS3_TXD_L3T_S)
-- 
cgit v1.2.3


From ddc49acb659a2d8bfc5fdb0de0ef197712c11d75 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Mon, 12 Nov 2018 18:51:01 +0100
Subject: net: dsa: mv88e6xxx: Work around mv886e6161 SERDES missing
 MII_PHYSID2

We already have a workaround for a couple of switches whose internal
PHYs only have the Marvel OUI, but no model number. We detect such
PHYs and give them the 6390 ID as the model number. However the
mv88e6161 has two SERDES interfaces in the same address range as its
internal PHYs. These suffer from the same problem, the Marvell OUI,
but no model number. As a result, these SERDES interfaces were getting
the same PHY ID as the mv88e6390, even though they are not PHYs, and
the Marvell PHY driver was trying to drive them.

Add a special case to stop this from happen.

Reported-by: Chris Healy <Chris.Healy@zii.aero>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index fc0f508879d4..b603f8d6ee3e 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2524,11 +2524,22 @@ static int mv88e6xxx_mdio_read(struct mii_bus *bus, int phy, int reg)
 	mutex_unlock(&chip->reg_lock);
 
 	if (reg == MII_PHYSID2) {
-		/* Some internal PHYS don't have a model number.  Use
-		 * the mv88e6390 family model number instead.
-		 */
-		if (!(val & 0x3f0))
-			val |= MV88E6XXX_PORT_SWITCH_ID_PROD_6390 >> 4;
+		/* Some internal PHYs don't have a model number. */
+		if (chip->info->family != MV88E6XXX_FAMILY_6165)
+			/* Then there is the 6165 family. It gets is
+			 * PHYs correct. But it can also have two
+			 * SERDES interfaces in the PHY address
+			 * space. And these don't have a model
+			 * number. But they are not PHYs, so we don't
+			 * want to give them something a PHY driver
+			 * will recognise.
+			 *
+			 * Use the mv88e6390 family model number
+			 * instead, for anything which really could be
+			 * a PHY,
+			 */
+			if (!(val & 0x3f0))
+				val |= MV88E6XXX_PORT_SWITCH_ID_PROD_6390 >> 4;
 	}
 
 	return err ? err : val;
-- 
cgit v1.2.3


From 7fe50ac83f4319c18ed7c634d85cad16bd0bf509 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 12 Nov 2018 14:47:18 -0800
Subject: net: dump more useful information in netdev_rx_csum_fault()

Currently netdev_rx_csum_fault() only shows a device name,
we need more information about the skb for debugging csum
failures.

Sample output:

 ens3: hw csum failure
 dev features: 0x0000000000014b89
 skb len=84 data_len=0 pkt_type=0 gso_size=0 gso_type=0 nr_frags=0 ip_summed=0 csum=0 csum_complete_sw=0 csum_valid=0 csum_level=0

Note, I use pr_err() just to be consistent with the existing one.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  5 +++--
 net/core/datagram.c       |  2 +-
 net/core/dev.c            | 11 +++++++++--
 net/core/skbuff.c         |  4 ++--
 net/sunrpc/socklib.c      |  2 +-
 5 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 97b4233120e4..917ae7b6263e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4343,9 +4343,10 @@ static inline bool can_checksum_protocol(netdev_features_t features,
 }
 
 #ifdef CONFIG_BUG
-void netdev_rx_csum_fault(struct net_device *dev);
+void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb);
 #else
-static inline void netdev_rx_csum_fault(struct net_device *dev)
+static inline void netdev_rx_csum_fault(struct net_device *dev,
+					struct sk_buff *skb)
 {
 }
 #endif
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 07983b90d2bd..4bf62b1afa3b 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -767,7 +767,7 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
 
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
 		    !skb->csum_complete_sw)
-			netdev_rx_csum_fault(NULL);
+			netdev_rx_csum_fault(NULL, skb);
 	}
 	return 0;
 fault:
diff --git a/net/core/dev.c b/net/core/dev.c
index bf7e0a471186..5927f6a7c301 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3091,10 +3091,17 @@ EXPORT_SYMBOL(__skb_gso_segment);
 
 /* Take action when hardware reception checksum errors are detected. */
 #ifdef CONFIG_BUG
-void netdev_rx_csum_fault(struct net_device *dev)
+void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb)
 {
 	if (net_ratelimit()) {
 		pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>");
+		if (dev)
+			pr_err("dev features: %pNF\n", &dev->features);
+		pr_err("skb len=%u data_len=%u pkt_type=%u gso_size=%u gso_type=%u nr_frags=%u ip_summed=%u csum=%x csum_complete_sw=%d csum_valid=%d csum_level=%u\n",
+		       skb->len, skb->data_len, skb->pkt_type,
+		       skb_shinfo(skb)->gso_size, skb_shinfo(skb)->gso_type,
+		       skb_shinfo(skb)->nr_frags, skb->ip_summed, skb->csum,
+		       skb->csum_complete_sw, skb->csum_valid, skb->csum_level);
 		dump_stack();
 	}
 }
@@ -5781,7 +5788,7 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb)
 	if (likely(!sum)) {
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
 		    !skb->csum_complete_sw)
-			netdev_rx_csum_fault(skb->dev);
+			netdev_rx_csum_fault(skb->dev, skb);
 	}
 
 	NAPI_GRO_CB(skb)->csum = wsum;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 396fcb3baad0..fcb1155a00ec 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2653,7 +2653,7 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 	if (likely(!sum)) {
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
 		    !skb->csum_complete_sw)
-			netdev_rx_csum_fault(skb->dev);
+			netdev_rx_csum_fault(skb->dev, skb);
 	}
 	if (!skb_shared(skb))
 		skb->csum_valid = !sum;
@@ -2673,7 +2673,7 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
 	if (likely(!sum)) {
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
 		    !skb->csum_complete_sw)
-			netdev_rx_csum_fault(skb->dev);
+			netdev_rx_csum_fault(skb->dev, skb);
 	}
 
 	if (!skb_shared(skb)) {
diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c
index 9062967575c4..7e55cfc69697 100644
--- a/net/sunrpc/socklib.c
+++ b/net/sunrpc/socklib.c
@@ -175,7 +175,7 @@ int csum_partial_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
 		return -1;
 	if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
 	    !skb->csum_complete_sw)
-		netdev_rx_csum_fault(skb->dev);
+		netdev_rx_csum_fault(skb->dev, skb);
 	return 0;
 no_checksum:
 	if (xdr_partial_copy_from_skb(xdr, 0, &desc, xdr_skb_read_bits) < 0)
-- 
cgit v1.2.3


From 5c72299fba9df407c2f2994e194edebf878996ee Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Mon, 12 Nov 2018 16:15:55 -0800
Subject: net: sched: cls_flower: Classify packets using port ranges

Added support in tc flower for filtering based on port ranges.

Example:
1. Match on a port range:
-------------------------
$ tc filter add dev enp4s0 protocol ip parent ffff:\
  prio 1 flower ip_proto tcp dst_port range 20-30 skip_hw\
  action drop

$ tc -s filter show dev enp4s0 parent ffff:
filter protocol ip pref 1 flower chain 0
filter protocol ip pref 1 flower chain 0 handle 0x1
  eth_type ipv4
  ip_proto tcp
  dst_port range 20-30
  skip_hw
  not_in_hw
        action order 1: gact action drop
         random type none pass val 0
         index 1 ref 1 bind 1 installed 85 sec used 3 sec
        Action statistics:
        Sent 460 bytes 10 pkt (dropped 10, overlimits 0 requeues 0)
        backlog 0b 0p requeues 0

2. Match on IP address and port range:
--------------------------------------
$ tc filter add dev enp4s0 protocol ip parent ffff:\
  prio 1 flower dst_ip 192.168.1.1 ip_proto tcp dst_port range 100-200\
  skip_hw action drop

$ tc -s filter show dev enp4s0 parent ffff:
filter protocol ip pref 1 flower chain 0 handle 0x2
  eth_type ipv4
  ip_proto tcp
  dst_ip 192.168.1.1
  dst_port range 100-200
  skip_hw
  not_in_hw
        action order 1: gact action drop
         random type none pass val 0
         index 2 ref 1 bind 1 installed 58 sec used 2 sec
        Action statistics:
        Sent 920 bytes 20 pkt (dropped 20, overlimits 0 requeues 0)
        backlog 0b 0p requeues 0

v4:
1. Added condition before setting port key.
2. Organized setting and dumping port range keys into functions
   and added validation of input range.

v3:
1. Moved new fields in UAPI enum to the end of enum.
2. Removed couple of empty lines.

v2:
Addressed Jiri's comments:
1. Added separate functions for dst and src comparisons.
2. Removed endpoint enum.
3. Added new bit TCA_FLOWER_FLAGS_RANGE to decide normal/range
  lookup.
4. Cleaned up fl_lookup function.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_cls.h |   7 ++
 net/sched/cls_flower.c       | 155 +++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 156 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 401d0c1e612d..95d0db2a8350 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -485,6 +485,11 @@ enum {
 
 	TCA_FLOWER_IN_HW_COUNT,
 
+	TCA_FLOWER_KEY_PORT_SRC_MIN,	/* be16 */
+	TCA_FLOWER_KEY_PORT_SRC_MAX,	/* be16 */
+	TCA_FLOWER_KEY_PORT_DST_MIN,	/* be16 */
+	TCA_FLOWER_KEY_PORT_DST_MAX,	/* be16 */
+
 	__TCA_FLOWER_MAX,
 };
 
@@ -518,6 +523,8 @@ enum {
 	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
 };
 
+#define TCA_FLOWER_MASK_FLAGS_RANGE	(1 << 0) /* Range-based match */
+
 /* Match-all classifier */
 
 enum {
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index c6c327874abc..85e9f8e1da10 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -55,6 +55,8 @@ struct fl_flow_key {
 	struct flow_dissector_key_ip ip;
 	struct flow_dissector_key_ip enc_ip;
 	struct flow_dissector_key_enc_opts enc_opts;
+	struct flow_dissector_key_ports tp_min;
+	struct flow_dissector_key_ports tp_max;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -65,6 +67,7 @@ struct fl_flow_mask_range {
 struct fl_flow_mask {
 	struct fl_flow_key key;
 	struct fl_flow_mask_range range;
+	u32 flags;
 	struct rhash_head ht_node;
 	struct rhashtable ht;
 	struct rhashtable_params filter_ht_params;
@@ -179,13 +182,89 @@ static void fl_clear_masked_range(struct fl_flow_key *key,
 	memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask));
 }
 
-static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask,
-				       struct fl_flow_key *mkey)
+static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter,
+				  struct fl_flow_key *key,
+				  struct fl_flow_key *mkey)
+{
+	__be16 min_mask, max_mask, min_val, max_val;
+
+	min_mask = htons(filter->mask->key.tp_min.dst);
+	max_mask = htons(filter->mask->key.tp_max.dst);
+	min_val = htons(filter->key.tp_min.dst);
+	max_val = htons(filter->key.tp_max.dst);
+
+	if (min_mask && max_mask) {
+		if (htons(key->tp.dst) < min_val ||
+		    htons(key->tp.dst) > max_val)
+			return false;
+
+		/* skb does not have min and max values */
+		mkey->tp_min.dst = filter->mkey.tp_min.dst;
+		mkey->tp_max.dst = filter->mkey.tp_max.dst;
+	}
+	return true;
+}
+
+static bool fl_range_port_src_cmp(struct cls_fl_filter *filter,
+				  struct fl_flow_key *key,
+				  struct fl_flow_key *mkey)
+{
+	__be16 min_mask, max_mask, min_val, max_val;
+
+	min_mask = htons(filter->mask->key.tp_min.src);
+	max_mask = htons(filter->mask->key.tp_max.src);
+	min_val = htons(filter->key.tp_min.src);
+	max_val = htons(filter->key.tp_max.src);
+
+	if (min_mask && max_mask) {
+		if (htons(key->tp.src) < min_val ||
+		    htons(key->tp.src) > max_val)
+			return false;
+
+		/* skb does not have min and max values */
+		mkey->tp_min.src = filter->mkey.tp_min.src;
+		mkey->tp_max.src = filter->mkey.tp_max.src;
+	}
+	return true;
+}
+
+static struct cls_fl_filter *__fl_lookup(struct fl_flow_mask *mask,
+					 struct fl_flow_key *mkey)
 {
 	return rhashtable_lookup_fast(&mask->ht, fl_key_get_start(mkey, mask),
 				      mask->filter_ht_params);
 }
 
+static struct cls_fl_filter *fl_lookup_range(struct fl_flow_mask *mask,
+					     struct fl_flow_key *mkey,
+					     struct fl_flow_key *key)
+{
+	struct cls_fl_filter *filter, *f;
+
+	list_for_each_entry_rcu(filter, &mask->filters, list) {
+		if (!fl_range_port_dst_cmp(filter, key, mkey))
+			continue;
+
+		if (!fl_range_port_src_cmp(filter, key, mkey))
+			continue;
+
+		f = __fl_lookup(mask, mkey);
+		if (f)
+			return f;
+	}
+	return NULL;
+}
+
+static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask,
+				       struct fl_flow_key *mkey,
+				       struct fl_flow_key *key)
+{
+	if ((mask->flags & TCA_FLOWER_MASK_FLAGS_RANGE))
+		return fl_lookup_range(mask, mkey, key);
+
+	return __fl_lookup(mask, mkey);
+}
+
 static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		       struct tcf_result *res)
 {
@@ -208,7 +287,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 
 		fl_set_masked_key(&skb_mkey, &skb_key, mask);
 
-		f = fl_lookup(mask, &skb_mkey);
+		f = fl_lookup(mask, &skb_mkey, &skb_key);
 		if (f && !tc_skip_sw(f->flags)) {
 			*res = f->res;
 			return tcf_exts_exec(skb, &f->exts, res);
@@ -514,6 +593,31 @@ static void fl_set_key_val(struct nlattr **tb,
 		memcpy(mask, nla_data(tb[mask_type]), len);
 }
 
+static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key,
+				 struct fl_flow_key *mask)
+{
+	fl_set_key_val(tb, &key->tp_min.dst,
+		       TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_min.dst,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_min.dst));
+	fl_set_key_val(tb, &key->tp_max.dst,
+		       TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_max.dst,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_max.dst));
+	fl_set_key_val(tb, &key->tp_min.src,
+		       TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_min.src,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_min.src));
+	fl_set_key_val(tb, &key->tp_max.src,
+		       TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_max.src,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_max.src));
+
+	if ((mask->tp_min.dst && mask->tp_max.dst &&
+	     htons(key->tp_max.dst) <= htons(key->tp_min.dst)) ||
+	     (mask->tp_min.src && mask->tp_max.src &&
+	      htons(key->tp_max.src) <= htons(key->tp_min.src)))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int fl_set_key_mpls(struct nlattr **tb,
 			   struct flow_dissector_key_mpls *key_val,
 			   struct flow_dissector_key_mpls *key_mask)
@@ -921,6 +1025,14 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 			       sizeof(key->arp.tha));
 	}
 
+	if (key->basic.ip_proto == IPPROTO_TCP ||
+	    key->basic.ip_proto == IPPROTO_UDP ||
+	    key->basic.ip_proto == IPPROTO_SCTP) {
+		ret = fl_set_key_port_range(tb, key, mask);
+		if (ret)
+			return ret;
+	}
+
 	if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] ||
 	    tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) {
 		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
@@ -1038,8 +1150,9 @@ static void fl_init_dissector(struct flow_dissector *dissector,
 			     FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
-	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
-			     FLOW_DISSECTOR_KEY_PORTS, tp);
+	if (FL_KEY_IS_MASKED(mask, tp) ||
+	    FL_KEY_IS_MASKED(mask, tp_min) || FL_KEY_IS_MASKED(mask, tp_max))
+		FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_IP, ip);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
@@ -1086,6 +1199,10 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
 
 	fl_mask_copy(newmask, mask);
 
+	if ((newmask->key.tp_min.dst && newmask->key.tp_max.dst) ||
+	    (newmask->key.tp_min.src && newmask->key.tp_max.src))
+		newmask->flags |= TCA_FLOWER_MASK_FLAGS_RANGE;
+
 	err = fl_init_mask_hashtable(newmask);
 	if (err)
 		goto errout_free;
@@ -1239,7 +1356,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 		goto errout_idr;
 
 	if (!tc_skip_sw(fnew->flags)) {
-		if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) {
+		if (!fold && __fl_lookup(fnew->mask, &fnew->mkey)) {
 			err = -EEXIST;
 			goto errout_mask;
 		}
@@ -1476,6 +1593,26 @@ static int fl_dump_key_val(struct sk_buff *skb,
 	return 0;
 }
 
+static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key,
+				  struct fl_flow_key *mask)
+{
+	if (fl_dump_key_val(skb, &key->tp_min.dst, TCA_FLOWER_KEY_PORT_DST_MIN,
+			    &mask->tp_min.dst, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_min.dst)) ||
+	    fl_dump_key_val(skb, &key->tp_max.dst, TCA_FLOWER_KEY_PORT_DST_MAX,
+			    &mask->tp_max.dst, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_max.dst)) ||
+	    fl_dump_key_val(skb, &key->tp_min.src, TCA_FLOWER_KEY_PORT_SRC_MIN,
+			    &mask->tp_min.src, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_min.src)) ||
+	    fl_dump_key_val(skb, &key->tp_max.src, TCA_FLOWER_KEY_PORT_SRC_MAX,
+			    &mask->tp_max.src, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_max.src)))
+		return -1;
+
+	return 0;
+}
+
 static int fl_dump_key_mpls(struct sk_buff *skb,
 			    struct flow_dissector_key_mpls *mpls_key,
 			    struct flow_dissector_key_mpls *mpls_mask)
@@ -1812,6 +1949,12 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
 				  sizeof(key->arp.tha))))
 		goto nla_put_failure;
 
+	if ((key->basic.ip_proto == IPPROTO_TCP ||
+	     key->basic.ip_proto == IPPROTO_UDP ||
+	     key->basic.ip_proto == IPPROTO_SCTP) &&
+	     fl_dump_key_port_range(skb, key, mask))
+		goto nla_put_failure;
+
 	if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
 	    (fl_dump_key_val(skb, &key->enc_ipv4.src,
 			    TCA_FLOWER_KEY_ENC_IPV4_SRC, &mask->enc_ipv4.src,
-- 
cgit v1.2.3


From 6ab6dfa6bb500f5cbb9b7a0f23a1613417ca2d12 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 12 Nov 2018 16:17:00 -0800
Subject: net: get rid of __tcp_checksum_complete()

__tcp_checksum_complete() is 100% same with __skb_checksum_complete()
and there is no other caller except tcp_checksum_complete().
So, just use __skb_checksum_complete() there.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4743836bed2e..b84b694e8b3d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1315,15 +1315,10 @@ static inline __sum16 tcp_v4_check(int len, __be32 saddr,
 	return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base);
 }
 
-static inline __sum16 __tcp_checksum_complete(struct sk_buff *skb)
-{
-	return __skb_checksum_complete(skb);
-}
-
 static inline bool tcp_checksum_complete(struct sk_buff *skb)
 {
 	return !skb_csum_unnecessary(skb) &&
-		__tcp_checksum_complete(skb);
+		__skb_checksum_complete(skb);
 }
 
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb);
-- 
cgit v1.2.3


From 36107c485f5efabe92ec4e0743724df5205511a4 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 14 Nov 2018 08:22:26 +0000
Subject: selftests: Adjust spectrum-2 two_mask_test

In order for this to behave as required with delta bits, change the mask
for rule with handle 103.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index 3b75180f455d..6b96eb6f6e74 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -142,7 +142,7 @@ two_masks_test()
 	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
 		$tcflags dst_ip 192.0.2.2 action drop
 	tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
-		$tcflags dst_ip 192.0.0.0/16 action drop
+		$tcflags dst_ip 192.0.0.0/8 action drop
 
 	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
 		-t ip -q
-- 
cgit v1.2.3


From 7dc5a0eeea185e5f3af3f97a86e76419791cdd60 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 14 Nov 2018 08:22:27 +0000
Subject: selftests: Adjust spectrum-2 ctcam_two_atcam_masks_test

In order for this to behave as required with delta bits, change the mask
for rule with handle 103.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index 6b96eb6f6e74..84ef95320c96 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -235,7 +235,7 @@ ctcam_two_atcam_masks_test()
 		$tcflags dst_ip 192.0.2.2 action drop
 	# Filter goes into A-TCAM
 	tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
-		$tcflags dst_ip 192.0.2.0/24 action drop
+		$tcflags dst_ip 192.0.0.0/16 action drop
 
 	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
 		-t ip -q
-- 
cgit v1.2.3


From 0a020d416d0af0b0c782e2a8363896e756e9121e Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 14 Nov 2018 08:22:28 +0000
Subject: lib: introduce initial implementation of object aggregation manager

This lib tracks objects which could be of two types:
1) root object
2) nested object - with a "delta" which differentiates it from
                   the associated root object
The objects are tracked by a hashtable and reference-counted. User is
responsible of implementing callbacks to create/destroy root entity
related to each root object and callback to create/destroy nested object
delta.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                   |   8 +
 include/linux/objagg.h        |  46 +++
 include/trace/events/objagg.h | 228 ++++++++++++
 lib/Kconfig                   |   3 +
 lib/Kconfig.debug             |  10 +
 lib/Makefile                  |   2 +
 lib/objagg.c                  | 501 +++++++++++++++++++++++++
 lib/test_objagg.c             | 835 ++++++++++++++++++++++++++++++++++++++++++
 8 files changed, 1633 insertions(+)
 create mode 100644 include/linux/objagg.h
 create mode 100644 include/trace/events/objagg.h
 create mode 100644 lib/objagg.c
 create mode 100644 lib/test_objagg.c

diff --git a/MAINTAINERS b/MAINTAINERS
index e110e327bf38..3bd775ba51ce 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10679,6 +10679,14 @@ L:	linux-nfc@lists.01.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/nfc/nxp-nci
 
+OBJAGG
+M:	Jiri Pirko <jiri@mellanox.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	lib/objagg.c
+F:	lib/test_objagg.c
+F:	include/linux/objagg.h
+
 OBJTOOL
 M:	Josh Poimboeuf <jpoimboe@redhat.com>
 M:	Peter Zijlstra <peterz@infradead.org>
diff --git a/include/linux/objagg.h b/include/linux/objagg.h
new file mode 100644
index 000000000000..34f38c186ea0
--- /dev/null
+++ b/include/linux/objagg.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#ifndef _OBJAGG_H
+#define _OBJAGG_H
+
+struct objagg_ops {
+	size_t obj_size;
+	void * (*delta_create)(void *priv, void *parent_obj, void *obj);
+	void (*delta_destroy)(void *priv, void *delta_priv);
+	void * (*root_create)(void *priv, void *obj);
+	void (*root_destroy)(void *priv, void *root_priv);
+};
+
+struct objagg;
+struct objagg_obj;
+
+const void *objagg_obj_root_priv(const struct objagg_obj *objagg_obj);
+const void *objagg_obj_delta_priv(const struct objagg_obj *objagg_obj);
+const void *objagg_obj_raw(const struct objagg_obj *objagg_obj);
+
+struct objagg_obj *objagg_obj_get(struct objagg *objagg, void *obj);
+void objagg_obj_put(struct objagg *objagg, struct objagg_obj *objagg_obj);
+struct objagg *objagg_create(const struct objagg_ops *ops, void *priv);
+void objagg_destroy(struct objagg *objagg);
+
+struct objagg_obj_stats {
+	unsigned int user_count;
+	unsigned int delta_user_count; /* includes delta object users */
+};
+
+struct objagg_obj_stats_info {
+	struct objagg_obj_stats stats;
+	struct objagg_obj *objagg_obj; /* associated object */
+	bool is_root;
+};
+
+struct objagg_stats {
+	unsigned int stats_info_count;
+	struct objagg_obj_stats_info stats_info[];
+};
+
+const struct objagg_stats *objagg_stats_get(struct objagg *objagg);
+void objagg_stats_put(const struct objagg_stats *objagg_stats);
+
+#endif
diff --git a/include/trace/events/objagg.h b/include/trace/events/objagg.h
new file mode 100644
index 000000000000..fcec0fc9eb0c
--- /dev/null
+++ b/include/trace/events/objagg.h
@@ -0,0 +1,228 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM objagg
+
+#if !defined(__TRACE_OBJAGG_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __TRACE_OBJAGG_H
+
+#include <linux/tracepoint.h>
+
+struct objagg;
+struct objagg_obj;
+
+TRACE_EVENT(objagg_create,
+	TP_PROTO(const struct objagg *objagg),
+
+	TP_ARGS(objagg),
+
+	TP_STRUCT__entry(
+		__field(const void *, objagg)
+	),
+
+	TP_fast_assign(
+		__entry->objagg = objagg;
+	),
+
+	TP_printk("objagg %p", __entry->objagg)
+);
+
+TRACE_EVENT(objagg_destroy,
+	TP_PROTO(const struct objagg *objagg),
+
+	TP_ARGS(objagg),
+
+	TP_STRUCT__entry(
+		__field(const void *, objagg)
+	),
+
+	TP_fast_assign(
+		__entry->objagg = objagg;
+	),
+
+	TP_printk("objagg %p", __entry->objagg)
+);
+
+TRACE_EVENT(objagg_obj_create,
+	TP_PROTO(const struct objagg *objagg,
+		 const struct objagg_obj *obj),
+
+	TP_ARGS(objagg, obj),
+
+	TP_STRUCT__entry(
+		__field(const void *, objagg)
+		__field(const void *, obj)
+	),
+
+	TP_fast_assign(
+		__entry->objagg = objagg;
+		__entry->obj = obj;
+	),
+
+	TP_printk("objagg %p, obj %p", __entry->objagg, __entry->obj)
+);
+
+TRACE_EVENT(objagg_obj_destroy,
+	TP_PROTO(const struct objagg *objagg,
+		 const struct objagg_obj *obj),
+
+	TP_ARGS(objagg, obj),
+
+	TP_STRUCT__entry(
+		__field(const void *, objagg)
+		__field(const void *, obj)
+	),
+
+	TP_fast_assign(
+		__entry->objagg = objagg;
+		__entry->obj = obj;
+	),
+
+	TP_printk("objagg %p, obj %p", __entry->objagg, __entry->obj)
+);
+
+TRACE_EVENT(objagg_obj_get,
+	TP_PROTO(const struct objagg *objagg,
+		 const struct objagg_obj *obj,
+		 unsigned int refcount),
+
+	TP_ARGS(objagg, obj, refcount),
+
+	TP_STRUCT__entry(
+		__field(const void *, objagg)
+		__field(const void *, obj)
+		__field(unsigned int, refcount)
+	),
+
+	TP_fast_assign(
+		__entry->objagg = objagg;
+		__entry->obj = obj;
+		__entry->refcount = refcount;
+	),
+
+	TP_printk("objagg %p, obj %p, refcount %u",
+		  __entry->objagg, __entry->obj, __entry->refcount)
+);
+
+TRACE_EVENT(objagg_obj_put,
+	TP_PROTO(const struct objagg *objagg,
+		 const struct objagg_obj *obj,
+		 unsigned int refcount),
+
+	TP_ARGS(objagg, obj, refcount),
+
+	TP_STRUCT__entry(
+		__field(const void *, objagg)
+		__field(const void *, obj)
+		__field(unsigned int, refcount)
+	),
+
+	TP_fast_assign(
+		__entry->objagg = objagg;
+		__entry->obj = obj;
+		__entry->refcount = refcount;
+	),
+
+	TP_printk("objagg %p, obj %p, refcount %u",
+		  __entry->objagg, __entry->obj, __entry->refcount)
+);
+
+TRACE_EVENT(objagg_obj_parent_assign,
+	TP_PROTO(const struct objagg *objagg,
+		 const struct objagg_obj *obj,
+		 const struct objagg_obj *parent,
+		 unsigned int parent_refcount),
+
+	TP_ARGS(objagg, obj, parent, parent_refcount),
+
+	TP_STRUCT__entry(
+		__field(const void *, objagg)
+		__field(const void *, obj)
+		__field(const void *, parent)
+		__field(unsigned int, parent_refcount)
+	),
+
+	TP_fast_assign(
+		__entry->objagg = objagg;
+		__entry->obj = obj;
+		__entry->parent = parent;
+		__entry->parent_refcount = parent_refcount;
+	),
+
+	TP_printk("objagg %p, obj %p, parent %p, parent_refcount %u",
+		  __entry->objagg, __entry->obj,
+		  __entry->parent, __entry->parent_refcount)
+);
+
+TRACE_EVENT(objagg_obj_parent_unassign,
+	TP_PROTO(const struct objagg *objagg,
+		 const struct objagg_obj *obj,
+		 const struct objagg_obj *parent,
+		 unsigned int parent_refcount),
+
+	TP_ARGS(objagg, obj, parent, parent_refcount),
+
+	TP_STRUCT__entry(
+		__field(const void *, objagg)
+		__field(const void *, obj)
+		__field(const void *, parent)
+		__field(unsigned int, parent_refcount)
+	),
+
+	TP_fast_assign(
+		__entry->objagg = objagg;
+		__entry->obj = obj;
+		__entry->parent = parent;
+		__entry->parent_refcount = parent_refcount;
+	),
+
+	TP_printk("objagg %p, obj %p, parent %p, parent_refcount %u",
+		  __entry->objagg, __entry->obj,
+		  __entry->parent, __entry->parent_refcount)
+);
+
+TRACE_EVENT(objagg_obj_root_create,
+	TP_PROTO(const struct objagg *objagg,
+		 const struct objagg_obj *obj),
+
+	TP_ARGS(objagg, obj),
+
+	TP_STRUCT__entry(
+		__field(const void *, objagg)
+		__field(const void *, obj)
+	),
+
+	TP_fast_assign(
+		__entry->objagg = objagg;
+		__entry->obj = obj;
+	),
+
+	TP_printk("objagg %p, obj %p",
+		  __entry->objagg, __entry->obj)
+);
+
+TRACE_EVENT(objagg_obj_root_destroy,
+	TP_PROTO(const struct objagg *objagg,
+		 const struct objagg_obj *obj),
+
+	TP_ARGS(objagg, obj),
+
+	TP_STRUCT__entry(
+		__field(const void *, objagg)
+		__field(const void *, obj)
+	),
+
+	TP_fast_assign(
+		__entry->objagg = objagg;
+		__entry->obj = obj;
+	),
+
+	TP_printk("objagg %p, obj %p",
+		  __entry->objagg, __entry->obj)
+);
+
+#endif /* __TRACE_OBJAGG_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/lib/Kconfig b/lib/Kconfig
index a9965f4af4dd..7dbbcfe9cd90 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -624,3 +624,6 @@ config GENERIC_LIB_CMPDI2
 
 config GENERIC_LIB_UCMPDI2
 	bool
+
+config OBJAGG
+	tristate "objagg" if COMPILE_TEST
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 1af29b8224fd..b3c91b9e32f8 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1976,6 +1976,16 @@ config TEST_MEMCAT_P
 
 	  If unsure, say N.
 
+config TEST_OBJAGG
+	tristate "Perform selftest on object aggreration manager"
+	default n
+	depends on OBJAGG
+	help
+	  Enable this option to test object aggregation manager on boot
+	  (or module load).
+
+	  If unsure, say N.
+
 endif # RUNTIME_TESTING_MENU
 
 config MEMTEST
diff --git a/lib/Makefile b/lib/Makefile
index db06d1237898..f5262d30bfe6 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -75,6 +75,7 @@ obj-$(CONFIG_TEST_PARMAN) += test_parman.o
 obj-$(CONFIG_TEST_KMOD) += test_kmod.o
 obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o
 obj-$(CONFIG_TEST_MEMCAT_P) += test_memcat_p.o
+obj-$(CONFIG_TEST_OBJAGG) += test_objagg.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG
@@ -274,3 +275,4 @@ obj-$(CONFIG_GENERIC_LIB_LSHRDI3) += lshrdi3.o
 obj-$(CONFIG_GENERIC_LIB_MULDI3) += muldi3.o
 obj-$(CONFIG_GENERIC_LIB_CMPDI2) += cmpdi2.o
 obj-$(CONFIG_GENERIC_LIB_UCMPDI2) += ucmpdi2.o
+obj-$(CONFIG_OBJAGG) += objagg.o
diff --git a/lib/objagg.c b/lib/objagg.c
new file mode 100644
index 000000000000..c9b457a91153
--- /dev/null
+++ b/lib/objagg.c
@@ -0,0 +1,501 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/rhashtable.h>
+#include <linux/list.h>
+#include <linux/sort.h>
+#include <linux/objagg.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/objagg.h>
+
+struct objagg {
+	const struct objagg_ops *ops;
+	void *priv;
+	struct rhashtable obj_ht;
+	struct rhashtable_params ht_params;
+	struct list_head obj_list;
+	unsigned int obj_count;
+};
+
+struct objagg_obj {
+	struct rhash_head ht_node; /* member of objagg->obj_ht */
+	struct list_head list; /* member of objagg->obj_list */
+	struct objagg_obj *parent; /* if the object is nested, this
+				    * holds pointer to parent, otherwise NULL
+				    */
+	union {
+		void *delta_priv; /* user delta private */
+		void *root_priv; /* user root private */
+	};
+	unsigned int refcount; /* counts number of users of this object
+				* including nested objects
+				*/
+	struct objagg_obj_stats stats;
+	unsigned long obj[0];
+};
+
+static unsigned int objagg_obj_ref_inc(struct objagg_obj *objagg_obj)
+{
+	return ++objagg_obj->refcount;
+}
+
+static unsigned int objagg_obj_ref_dec(struct objagg_obj *objagg_obj)
+{
+	return --objagg_obj->refcount;
+}
+
+static void objagg_obj_stats_inc(struct objagg_obj *objagg_obj)
+{
+	objagg_obj->stats.user_count++;
+	objagg_obj->stats.delta_user_count++;
+	if (objagg_obj->parent)
+		objagg_obj->parent->stats.delta_user_count++;
+}
+
+static void objagg_obj_stats_dec(struct objagg_obj *objagg_obj)
+{
+	objagg_obj->stats.user_count--;
+	objagg_obj->stats.delta_user_count--;
+	if (objagg_obj->parent)
+		objagg_obj->parent->stats.delta_user_count--;
+}
+
+static bool objagg_obj_is_root(const struct objagg_obj *objagg_obj)
+{
+	/* Nesting is not supported, so we can use ->parent
+	 * to figure out if the object is root.
+	 */
+	return !objagg_obj->parent;
+}
+
+/**
+ * objagg_obj_root_priv - obtains root private for an object
+ * @objagg_obj:	objagg object instance
+ *
+ * Note: all locking must be provided by the caller.
+ *
+ * Either the object is root itself when the private is returned
+ * directly, or the parent is root and its private is returned
+ * instead.
+ *
+ * Returns a user private root pointer.
+ */
+const void *objagg_obj_root_priv(const struct objagg_obj *objagg_obj)
+{
+	if (objagg_obj_is_root(objagg_obj))
+		return objagg_obj->root_priv;
+	WARN_ON(!objagg_obj_is_root(objagg_obj->parent));
+	return objagg_obj->parent->root_priv;
+}
+EXPORT_SYMBOL(objagg_obj_root_priv);
+
+/**
+ * objagg_obj_delta_priv - obtains delta private for an object
+ * @objagg_obj:	objagg object instance
+ *
+ * Note: all locking must be provided by the caller.
+ *
+ * Returns user private delta pointer or NULL in case the passed
+ * object is root.
+ */
+const void *objagg_obj_delta_priv(const struct objagg_obj *objagg_obj)
+{
+	if (objagg_obj_is_root(objagg_obj))
+		return NULL;
+	return objagg_obj->delta_priv;
+}
+EXPORT_SYMBOL(objagg_obj_delta_priv);
+
+/**
+ * objagg_obj_raw - obtains object user private pointer
+ * @objagg_obj:	objagg object instance
+ *
+ * Note: all locking must be provided by the caller.
+ *
+ * Returns user private pointer as was passed to objagg_obj_get() by "obj" arg.
+ */
+const void *objagg_obj_raw(const struct objagg_obj *objagg_obj)
+{
+	return objagg_obj->obj;
+}
+EXPORT_SYMBOL(objagg_obj_raw);
+
+static struct objagg_obj *objagg_obj_lookup(struct objagg *objagg, void *obj)
+{
+	return rhashtable_lookup_fast(&objagg->obj_ht, obj, objagg->ht_params);
+}
+
+static int objagg_obj_parent_assign(struct objagg *objagg,
+				    struct objagg_obj *objagg_obj,
+				    struct objagg_obj *parent)
+{
+	void *delta_priv;
+
+	delta_priv = objagg->ops->delta_create(objagg->priv, parent->obj,
+					       objagg_obj->obj);
+	if (IS_ERR(delta_priv))
+		return PTR_ERR(delta_priv);
+
+	/* User returned a delta private, that means that
+	 * our object can be aggregated into the parent.
+	 */
+	objagg_obj->parent = parent;
+	objagg_obj->delta_priv = delta_priv;
+	objagg_obj_ref_inc(objagg_obj->parent);
+	trace_objagg_obj_parent_assign(objagg, objagg_obj,
+				       parent,
+				       parent->refcount);
+	return 0;
+}
+
+static int objagg_obj_parent_lookup_assign(struct objagg *objagg,
+					   struct objagg_obj *objagg_obj)
+{
+	struct objagg_obj *objagg_obj_cur;
+	int err;
+
+	list_for_each_entry(objagg_obj_cur, &objagg->obj_list, list) {
+		/* Nesting is not supported. In case the object
+		 * is not root, it cannot be assigned as parent.
+		 */
+		if (!objagg_obj_is_root(objagg_obj_cur))
+			continue;
+		err = objagg_obj_parent_assign(objagg, objagg_obj,
+					       objagg_obj_cur);
+		if (!err)
+			return 0;
+	}
+	return -ENOENT;
+}
+
+static void __objagg_obj_put(struct objagg *objagg,
+			     struct objagg_obj *objagg_obj);
+
+static void objagg_obj_parent_unassign(struct objagg *objagg,
+				       struct objagg_obj *objagg_obj)
+{
+	trace_objagg_obj_parent_unassign(objagg, objagg_obj,
+					 objagg_obj->parent,
+					 objagg_obj->parent->refcount);
+	objagg->ops->delta_destroy(objagg->priv, objagg_obj->delta_priv);
+	__objagg_obj_put(objagg, objagg_obj->parent);
+}
+
+static int objagg_obj_root_create(struct objagg *objagg,
+				  struct objagg_obj *objagg_obj)
+{
+	objagg_obj->root_priv = objagg->ops->root_create(objagg->priv,
+							 objagg_obj->obj);
+	if (IS_ERR(objagg_obj->root_priv))
+		return PTR_ERR(objagg_obj->root_priv);
+
+	trace_objagg_obj_root_create(objagg, objagg_obj);
+	return 0;
+}
+
+static void objagg_obj_root_destroy(struct objagg *objagg,
+				    struct objagg_obj *objagg_obj)
+{
+	trace_objagg_obj_root_destroy(objagg, objagg_obj);
+	objagg->ops->root_destroy(objagg->priv, objagg_obj->root_priv);
+}
+
+static int objagg_obj_init(struct objagg *objagg,
+			   struct objagg_obj *objagg_obj)
+{
+	int err;
+
+	/* Try to find if the object can be aggregated under an existing one. */
+	err = objagg_obj_parent_lookup_assign(objagg, objagg_obj);
+	if (!err)
+		return 0;
+	/* If aggregation is not possible, make the object a root. */
+	return objagg_obj_root_create(objagg, objagg_obj);
+}
+
+static void objagg_obj_fini(struct objagg *objagg,
+			    struct objagg_obj *objagg_obj)
+{
+	if (!objagg_obj_is_root(objagg_obj))
+		objagg_obj_parent_unassign(objagg, objagg_obj);
+	else
+		objagg_obj_root_destroy(objagg, objagg_obj);
+}
+
+static struct objagg_obj *objagg_obj_create(struct objagg *objagg, void *obj)
+{
+	struct objagg_obj *objagg_obj;
+	int err;
+
+	objagg_obj = kzalloc(sizeof(*objagg_obj) + objagg->ops->obj_size,
+			     GFP_KERNEL);
+	if (!objagg_obj)
+		return ERR_PTR(-ENOMEM);
+	objagg_obj_ref_inc(objagg_obj);
+	memcpy(objagg_obj->obj, obj, objagg->ops->obj_size);
+
+	err = objagg_obj_init(objagg, objagg_obj);
+	if (err)
+		goto err_obj_init;
+
+	err = rhashtable_insert_fast(&objagg->obj_ht, &objagg_obj->ht_node,
+				     objagg->ht_params);
+	if (err)
+		goto err_ht_insert;
+	list_add(&objagg_obj->list, &objagg->obj_list);
+	objagg->obj_count++;
+	trace_objagg_obj_create(objagg, objagg_obj);
+
+	return objagg_obj;
+
+err_ht_insert:
+	objagg_obj_fini(objagg, objagg_obj);
+err_obj_init:
+	kfree(objagg_obj);
+	return ERR_PTR(err);
+}
+
+static struct objagg_obj *__objagg_obj_get(struct objagg *objagg, void *obj)
+{
+	struct objagg_obj *objagg_obj;
+
+	/* First, try to find the object exactly as user passed it,
+	 * perhaps it is already in use.
+	 */
+	objagg_obj = objagg_obj_lookup(objagg, obj);
+	if (objagg_obj) {
+		objagg_obj_ref_inc(objagg_obj);
+		return objagg_obj;
+	}
+
+	return objagg_obj_create(objagg, obj);
+}
+
+/**
+ * objagg_obj_get - gets an object within objagg instance
+ * @objagg:	objagg instance
+ * @obj:	user-specific private object pointer
+ *
+ * Note: all locking must be provided by the caller.
+ *
+ * Size of the "obj" memory is specified in "objagg->ops".
+ *
+ * There are 3 main options this function wraps:
+ * 1) The object according to "obj" already exist. In that case
+ *    the reference counter is incrementes and the object is returned.
+ * 2) The object does not exist, but it can be aggregated within
+ *    another object. In that case, user ops->delta_create() is called
+ *    to obtain delta data and a new object is created with returned
+ *    user-delta private pointer.
+ * 3) The object does not exist and cannot be aggregated into
+ *    any of the existing objects. In that case, user ops->root_create()
+ *    is called to create the root and a new object is created with
+ *    returned user-root private pointer.
+ *
+ * Returns a pointer to objagg object instance in case of success,
+ * otherwise it returns pointer error using ERR_PTR macro.
+ */
+struct objagg_obj *objagg_obj_get(struct objagg *objagg, void *obj)
+{
+	struct objagg_obj *objagg_obj;
+
+	objagg_obj = __objagg_obj_get(objagg, obj);
+	if (IS_ERR(objagg_obj))
+		return objagg_obj;
+	objagg_obj_stats_inc(objagg_obj);
+	trace_objagg_obj_get(objagg, objagg_obj, objagg_obj->refcount);
+	return objagg_obj;
+}
+EXPORT_SYMBOL(objagg_obj_get);
+
+static void objagg_obj_destroy(struct objagg *objagg,
+			       struct objagg_obj *objagg_obj)
+{
+	trace_objagg_obj_destroy(objagg, objagg_obj);
+	--objagg->obj_count;
+	list_del(&objagg_obj->list);
+	rhashtable_remove_fast(&objagg->obj_ht, &objagg_obj->ht_node,
+			       objagg->ht_params);
+	objagg_obj_fini(objagg, objagg_obj);
+	kfree(objagg_obj);
+}
+
+static void __objagg_obj_put(struct objagg *objagg,
+			     struct objagg_obj *objagg_obj)
+{
+	if (!objagg_obj_ref_dec(objagg_obj))
+		objagg_obj_destroy(objagg, objagg_obj);
+}
+
+/**
+ * objagg_obj_put - puts an object within objagg instance
+ * @objagg:	objagg instance
+ * @objagg_obj:	objagg object instance
+ *
+ * Note: all locking must be provided by the caller.
+ *
+ * Symmetric to objagg_obj_get().
+ */
+void objagg_obj_put(struct objagg *objagg, struct objagg_obj *objagg_obj)
+{
+	trace_objagg_obj_put(objagg, objagg_obj, objagg_obj->refcount);
+	objagg_obj_stats_dec(objagg_obj);
+	__objagg_obj_put(objagg, objagg_obj);
+}
+EXPORT_SYMBOL(objagg_obj_put);
+
+/**
+ * objagg_create - creates a new objagg instance
+ * @ops:	user-specific callbacks
+ * @priv:	pointer to a private data passed to the ops
+ *
+ * Note: all locking must be provided by the caller.
+ *
+ * The purpose of the library is to provide an infrastructure to
+ * aggregate user-specified objects. Library does not care about the type
+ * of the object. User fills-up ops which take care of the specific
+ * user object manipulation.
+ *
+ * As a very stupid example, consider integer numbers. For example
+ * number 8 as a root object. That can aggregate number 9 with delta 1,
+ * number 10 with delta 2, etc. This example is implemented as
+ * a part of a testing module in test_objagg.c file.
+ *
+ * Each objagg instance contains multiple trees. Each tree node is
+ * represented by "an object". In the current implementation there can be
+ * only roots and leafs nodes. Leaf nodes are called deltas.
+ * But in general, this can be easily extended for intermediate nodes.
+ * In that extension, a delta would be associated with all non-root
+ * nodes.
+ *
+ * Returns a pointer to newly created objagg instance in case of success,
+ * otherwise it returns pointer error using ERR_PTR macro.
+ */
+struct objagg *objagg_create(const struct objagg_ops *ops, void *priv)
+{
+	struct objagg *objagg;
+	int err;
+
+	if (WARN_ON(!ops || !ops->root_create || !ops->root_destroy ||
+		    !ops->delta_create || !ops->delta_destroy))
+		return ERR_PTR(-EINVAL);
+	objagg = kzalloc(sizeof(*objagg), GFP_KERNEL);
+	if (!objagg)
+		return ERR_PTR(-ENOMEM);
+	objagg->ops = ops;
+	objagg->priv = priv;
+	INIT_LIST_HEAD(&objagg->obj_list);
+
+	objagg->ht_params.key_len = ops->obj_size;
+	objagg->ht_params.key_offset = offsetof(struct objagg_obj, obj);
+	objagg->ht_params.head_offset = offsetof(struct objagg_obj, ht_node);
+
+	err = rhashtable_init(&objagg->obj_ht, &objagg->ht_params);
+	if (err)
+		goto err_rhashtable_init;
+
+	trace_objagg_create(objagg);
+	return objagg;
+
+err_rhashtable_init:
+	kfree(objagg);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(objagg_create);
+
+/**
+ * objagg_destroy - destroys a new objagg instance
+ * @objagg:	objagg instance
+ *
+ * Note: all locking must be provided by the caller.
+ */
+void objagg_destroy(struct objagg *objagg)
+{
+	trace_objagg_destroy(objagg);
+	WARN_ON(!list_empty(&objagg->obj_list));
+	rhashtable_destroy(&objagg->obj_ht);
+	kfree(objagg);
+}
+EXPORT_SYMBOL(objagg_destroy);
+
+static int objagg_stats_info_sort_cmp_func(const void *a, const void *b)
+{
+	const struct objagg_obj_stats_info *stats_info1 = a;
+	const struct objagg_obj_stats_info *stats_info2 = b;
+
+	if (stats_info1->is_root != stats_info2->is_root)
+		return stats_info2->is_root - stats_info1->is_root;
+	if (stats_info1->stats.delta_user_count !=
+	    stats_info2->stats.delta_user_count)
+		return stats_info2->stats.delta_user_count -
+		       stats_info1->stats.delta_user_count;
+	return stats_info2->stats.user_count - stats_info1->stats.user_count;
+}
+
+/**
+ * objagg_stats_get - obtains stats of the objagg instance
+ * @objagg:	objagg instance
+ *
+ * Note: all locking must be provided by the caller.
+ *
+ * The returned structure contains statistics of all object
+ * currently in use, ordered by following rules:
+ * 1) Root objects are always on lower indexes than the rest.
+ * 2) Objects with higher delta user count are always on lower
+ *    indexes.
+ * 3) In case more objects have the same delta user count,
+ *    the objects are ordered by user count.
+ *
+ * Returns a pointer to stats instance in case of success,
+ * otherwise it returns pointer error using ERR_PTR macro.
+ */
+const struct objagg_stats *objagg_stats_get(struct objagg *objagg)
+{
+	struct objagg_stats *objagg_stats;
+	struct objagg_obj *objagg_obj;
+	size_t alloc_size;
+	int i;
+
+	alloc_size = sizeof(*objagg_stats) +
+		     sizeof(objagg_stats->stats_info[0]) * objagg->obj_count;
+	objagg_stats = kzalloc(alloc_size, GFP_KERNEL);
+	if (!objagg_stats)
+		return ERR_PTR(-ENOMEM);
+
+	i = 0;
+	list_for_each_entry(objagg_obj, &objagg->obj_list, list) {
+		memcpy(&objagg_stats->stats_info[i].stats, &objagg_obj->stats,
+		       sizeof(objagg_stats->stats_info[0].stats));
+		objagg_stats->stats_info[i].objagg_obj = objagg_obj;
+		objagg_stats->stats_info[i].is_root =
+					objagg_obj_is_root(objagg_obj);
+		i++;
+	}
+	objagg_stats->stats_info_count = i;
+
+	sort(objagg_stats->stats_info, objagg_stats->stats_info_count,
+	     sizeof(struct objagg_obj_stats_info),
+	     objagg_stats_info_sort_cmp_func, NULL);
+
+	return objagg_stats;
+}
+EXPORT_SYMBOL(objagg_stats_get);
+
+/**
+ * objagg_stats_puts - puts stats of the objagg instance
+ * @objagg_stats:	objagg instance stats
+ *
+ * Note: all locking must be provided by the caller.
+ */
+void objagg_stats_put(const struct objagg_stats *objagg_stats)
+{
+	kfree(objagg_stats);
+}
+EXPORT_SYMBOL(objagg_stats_put);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>");
+MODULE_DESCRIPTION("Object aggregation manager");
diff --git a/lib/test_objagg.c b/lib/test_objagg.c
new file mode 100644
index 000000000000..aac5d8e8800c
--- /dev/null
+++ b/lib/test_objagg.c
@@ -0,0 +1,835 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/objagg.h>
+
+struct tokey {
+	unsigned int id;
+};
+
+#define NUM_KEYS 32
+
+static int key_id_index(unsigned int key_id)
+{
+	if (key_id >= NUM_KEYS) {
+		WARN_ON(1);
+		return 0;
+	}
+	return key_id;
+}
+
+#define BUF_LEN 128
+
+struct world {
+	unsigned int root_count;
+	unsigned int delta_count;
+	char next_root_buf[BUF_LEN];
+	struct objagg_obj *objagg_objs[NUM_KEYS];
+	unsigned int key_refs[NUM_KEYS];
+};
+
+struct root {
+	struct tokey key;
+	char buf[BUF_LEN];
+};
+
+struct delta {
+	unsigned int key_id_diff;
+};
+
+static struct objagg_obj *world_obj_get(struct world *world,
+					struct objagg *objagg,
+					unsigned int key_id)
+{
+	struct objagg_obj *objagg_obj;
+	struct tokey key;
+	int err;
+
+	key.id = key_id;
+	objagg_obj = objagg_obj_get(objagg, &key);
+	if (IS_ERR(objagg_obj)) {
+		pr_err("Key %u: Failed to get object.\n", key_id);
+		return objagg_obj;
+	}
+	if (!world->key_refs[key_id_index(key_id)]) {
+		world->objagg_objs[key_id_index(key_id)] = objagg_obj;
+	} else if (world->objagg_objs[key_id_index(key_id)] != objagg_obj) {
+		pr_err("Key %u: God another object for the same key.\n",
+		       key_id);
+		err = -EINVAL;
+		goto err_key_id_check;
+	}
+	world->key_refs[key_id_index(key_id)]++;
+	return objagg_obj;
+
+err_key_id_check:
+	objagg_obj_put(objagg, objagg_obj);
+	return ERR_PTR(err);
+}
+
+static void world_obj_put(struct world *world, struct objagg *objagg,
+			  unsigned int key_id)
+{
+	struct objagg_obj *objagg_obj;
+
+	if (!world->key_refs[key_id_index(key_id)])
+		return;
+	objagg_obj = world->objagg_objs[key_id_index(key_id)];
+	objagg_obj_put(objagg, objagg_obj);
+	world->key_refs[key_id_index(key_id)]--;
+}
+
+#define MAX_KEY_ID_DIFF 5
+
+static void *delta_create(void *priv, void *parent_obj, void *obj)
+{
+	struct tokey *parent_key = parent_obj;
+	struct world *world = priv;
+	struct tokey *key = obj;
+	int diff = key->id - parent_key->id;
+	struct delta *delta;
+
+	if (diff < 0 || diff > MAX_KEY_ID_DIFF)
+		return ERR_PTR(-EINVAL);
+
+	delta = kzalloc(sizeof(*delta), GFP_KERNEL);
+	if (!delta)
+		return ERR_PTR(-ENOMEM);
+	delta->key_id_diff = diff;
+	world->delta_count++;
+	return delta;
+}
+
+static void delta_destroy(void *priv, void *delta_priv)
+{
+	struct delta *delta = delta_priv;
+	struct world *world = priv;
+
+	world->delta_count--;
+	kfree(delta);
+}
+
+static void *root_create(void *priv, void *obj)
+{
+	struct world *world = priv;
+	struct tokey *key = obj;
+	struct root *root;
+
+	root = kzalloc(sizeof(*root), GFP_KERNEL);
+	if (!root)
+		return ERR_PTR(-ENOMEM);
+	memcpy(&root->key, key, sizeof(root->key));
+	memcpy(root->buf, world->next_root_buf, sizeof(root->buf));
+	world->root_count++;
+	return root;
+}
+
+static void root_destroy(void *priv, void *root_priv)
+{
+	struct root *root = root_priv;
+	struct world *world = priv;
+
+	world->root_count--;
+	kfree(root);
+}
+
+static int test_nodelta_obj_get(struct world *world, struct objagg *objagg,
+				unsigned int key_id, bool should_create_root)
+{
+	unsigned int orig_root_count = world->root_count;
+	struct objagg_obj *objagg_obj;
+	const struct root *root;
+	int err;
+
+	if (should_create_root)
+		prandom_bytes(world->next_root_buf,
+			      sizeof(world->next_root_buf));
+
+	objagg_obj = world_obj_get(world, objagg, key_id);
+	if (IS_ERR(objagg_obj)) {
+		pr_err("Key %u: Failed to get object.\n", key_id);
+		return PTR_ERR(objagg_obj);
+	}
+	if (should_create_root) {
+		if (world->root_count != orig_root_count + 1) {
+			pr_err("Key %u: Root was not created\n", key_id);
+			err = -EINVAL;
+			goto err_check_root_count;
+		}
+	} else {
+		if (world->root_count != orig_root_count) {
+			pr_err("Key %u: Root was incorrectly created\n",
+			       key_id);
+			err = -EINVAL;
+			goto err_check_root_count;
+		}
+	}
+	root = objagg_obj_root_priv(objagg_obj);
+	if (root->key.id != key_id) {
+		pr_err("Key %u: Root has unexpected key id\n", key_id);
+		err = -EINVAL;
+		goto err_check_key_id;
+	}
+	if (should_create_root &&
+	    memcmp(world->next_root_buf, root->buf, sizeof(root->buf))) {
+		pr_err("Key %u: Buffer does not match the expected content\n",
+		       key_id);
+		err = -EINVAL;
+		goto err_check_buf;
+	}
+	return 0;
+
+err_check_buf:
+err_check_key_id:
+err_check_root_count:
+	objagg_obj_put(objagg, objagg_obj);
+	return err;
+}
+
+static int test_nodelta_obj_put(struct world *world, struct objagg *objagg,
+				unsigned int key_id, bool should_destroy_root)
+{
+	unsigned int orig_root_count = world->root_count;
+
+	world_obj_put(world, objagg, key_id);
+
+	if (should_destroy_root) {
+		if (world->root_count != orig_root_count - 1) {
+			pr_err("Key %u: Root was not destroyed\n", key_id);
+			return -EINVAL;
+		}
+	} else {
+		if (world->root_count != orig_root_count) {
+			pr_err("Key %u: Root was incorrectly destroyed\n",
+			       key_id);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static int check_stats_zero(struct objagg *objagg)
+{
+	const struct objagg_stats *stats;
+	int err = 0;
+
+	stats = objagg_stats_get(objagg);
+	if (IS_ERR(stats))
+		return PTR_ERR(stats);
+
+	if (stats->stats_info_count != 0) {
+		pr_err("Stats: Object count is not zero while it should be\n");
+		err = -EINVAL;
+	}
+
+	objagg_stats_put(stats);
+	return err;
+}
+
+static int check_stats_nodelta(struct objagg *objagg)
+{
+	const struct objagg_stats *stats;
+	int i;
+	int err;
+
+	stats = objagg_stats_get(objagg);
+	if (IS_ERR(stats))
+		return PTR_ERR(stats);
+
+	if (stats->stats_info_count != NUM_KEYS) {
+		pr_err("Stats: Unexpected object count (%u expected, %u returned)\n",
+		       NUM_KEYS, stats->stats_info_count);
+		err = -EINVAL;
+		goto stats_put;
+	}
+
+	for (i = 0; i < stats->stats_info_count; i++) {
+		if (stats->stats_info[i].stats.user_count != 2) {
+			pr_err("Stats: incorrect user count\n");
+			err = -EINVAL;
+			goto stats_put;
+		}
+		if (stats->stats_info[i].stats.delta_user_count != 2) {
+			pr_err("Stats: incorrect delta user count\n");
+			err = -EINVAL;
+			goto stats_put;
+		}
+	}
+	err = 0;
+
+stats_put:
+	objagg_stats_put(stats);
+	return err;
+}
+
+static void *delta_create_dummy(void *priv, void *parent_obj, void *obj)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static void delta_destroy_dummy(void *priv, void *delta_priv)
+{
+}
+
+static const struct objagg_ops nodelta_ops = {
+	.obj_size = sizeof(struct tokey),
+	.delta_create = delta_create_dummy,
+	.delta_destroy = delta_destroy_dummy,
+	.root_create = root_create,
+	.root_destroy = root_destroy,
+};
+
+static int test_nodelta(void)
+{
+	struct world world = {};
+	struct objagg *objagg;
+	int i;
+	int err;
+
+	objagg = objagg_create(&nodelta_ops, &world);
+	if (IS_ERR(objagg))
+		return PTR_ERR(objagg);
+
+	err = check_stats_zero(objagg);
+	if (err)
+		goto err_stats_first_zero;
+
+	/* First round of gets, the root objects should be created */
+	for (i = 0; i < NUM_KEYS; i++) {
+		err = test_nodelta_obj_get(&world, objagg, i, true);
+		if (err)
+			goto err_obj_first_get;
+	}
+
+	/* Do the second round of gets, all roots are already created,
+	 * make sure that no new root is created
+	 */
+	for (i = 0; i < NUM_KEYS; i++) {
+		err = test_nodelta_obj_get(&world, objagg, i, false);
+		if (err)
+			goto err_obj_second_get;
+	}
+
+	err = check_stats_nodelta(objagg);
+	if (err)
+		goto err_stats_nodelta;
+
+	for (i = NUM_KEYS - 1; i >= 0; i--) {
+		err = test_nodelta_obj_put(&world, objagg, i, false);
+		if (err)
+			goto err_obj_first_put;
+	}
+	for (i = NUM_KEYS - 1; i >= 0; i--) {
+		err = test_nodelta_obj_put(&world, objagg, i, true);
+		if (err)
+			goto err_obj_second_put;
+	}
+
+	err = check_stats_zero(objagg);
+	if (err)
+		goto err_stats_second_zero;
+
+	objagg_destroy(objagg);
+	return 0;
+
+err_stats_nodelta:
+err_obj_first_put:
+err_obj_second_get:
+	for (i--; i >= 0; i--)
+		world_obj_put(&world, objagg, i);
+
+	i = NUM_KEYS;
+err_obj_first_get:
+err_obj_second_put:
+	for (i--; i >= 0; i--)
+		world_obj_put(&world, objagg, i);
+err_stats_first_zero:
+err_stats_second_zero:
+	objagg_destroy(objagg);
+	return err;
+}
+
+static const struct objagg_ops delta_ops = {
+	.obj_size = sizeof(struct tokey),
+	.delta_create = delta_create,
+	.delta_destroy = delta_destroy,
+	.root_create = root_create,
+	.root_destroy = root_destroy,
+};
+
+enum action {
+	ACTION_GET,
+	ACTION_PUT,
+};
+
+enum expect_delta {
+	EXPECT_DELTA_SAME,
+	EXPECT_DELTA_INC,
+	EXPECT_DELTA_DEC,
+};
+
+enum expect_root {
+	EXPECT_ROOT_SAME,
+	EXPECT_ROOT_INC,
+	EXPECT_ROOT_DEC,
+};
+
+struct expect_stats_info {
+	struct objagg_obj_stats stats;
+	bool is_root;
+	unsigned int key_id;
+};
+
+struct expect_stats {
+	unsigned int info_count;
+	struct expect_stats_info info[NUM_KEYS];
+};
+
+struct action_item {
+	unsigned int key_id;
+	enum action action;
+	enum expect_delta expect_delta;
+	enum expect_root expect_root;
+	struct expect_stats expect_stats;
+};
+
+#define EXPECT_STATS(count, ...)		\
+{						\
+	.info_count = count,			\
+	.info = { __VA_ARGS__ }			\
+}
+
+#define ROOT(key_id, user_count, delta_user_count)	\
+	{{user_count, delta_user_count}, true, key_id}
+
+#define DELTA(key_id, user_count)			\
+	{{user_count, user_count}, false, key_id}
+
+static const struct action_item action_items[] = {
+	{
+		1, ACTION_GET, EXPECT_DELTA_SAME, EXPECT_ROOT_INC,
+		EXPECT_STATS(1, ROOT(1, 1, 1)),
+	},	/* r: 1			d: */
+	{
+		7, ACTION_GET, EXPECT_DELTA_SAME, EXPECT_ROOT_INC,
+		EXPECT_STATS(2, ROOT(1, 1, 1), ROOT(7, 1, 1)),
+	},	/* r: 1, 7		d: */
+	{
+		3, ACTION_GET, EXPECT_DELTA_INC, EXPECT_ROOT_SAME,
+		EXPECT_STATS(3, ROOT(1, 1, 2), ROOT(7, 1, 1),
+				DELTA(3, 1)),
+	},	/* r: 1, 7		d: 3^1 */
+	{
+		5, ACTION_GET, EXPECT_DELTA_INC, EXPECT_ROOT_SAME,
+		EXPECT_STATS(4, ROOT(1, 1, 3), ROOT(7, 1, 1),
+				DELTA(3, 1), DELTA(5, 1)),
+	},	/* r: 1, 7		d: 3^1, 5^1 */
+	{
+		3, ACTION_GET, EXPECT_DELTA_SAME, EXPECT_ROOT_SAME,
+		EXPECT_STATS(4, ROOT(1, 1, 4), ROOT(7, 1, 1),
+				DELTA(3, 2), DELTA(5, 1)),
+	},	/* r: 1, 7		d: 3^1, 3^1, 5^1 */
+	{
+		1, ACTION_GET, EXPECT_DELTA_SAME, EXPECT_ROOT_SAME,
+		EXPECT_STATS(4, ROOT(1, 2, 5), ROOT(7, 1, 1),
+				DELTA(3, 2), DELTA(5, 1)),
+	},	/* r: 1, 1, 7		d: 3^1, 3^1, 5^1 */
+	{
+		30, ACTION_GET, EXPECT_DELTA_SAME, EXPECT_ROOT_INC,
+		EXPECT_STATS(5, ROOT(1, 2, 5), ROOT(7, 1, 1), ROOT(30, 1, 1),
+				DELTA(3, 2), DELTA(5, 1)),
+	},	/* r: 1, 1, 7, 30	d: 3^1, 3^1, 5^1 */
+	{
+		8, ACTION_GET, EXPECT_DELTA_INC, EXPECT_ROOT_SAME,
+		EXPECT_STATS(6, ROOT(1, 2, 5), ROOT(7, 1, 2), ROOT(30, 1, 1),
+				DELTA(3, 2), DELTA(5, 1), DELTA(8, 1)),
+	},	/* r: 1, 1, 7, 30	d: 3^1, 3^1, 5^1, 8^7 */
+	{
+		8, ACTION_GET, EXPECT_DELTA_SAME, EXPECT_ROOT_SAME,
+		EXPECT_STATS(6, ROOT(1, 2, 5), ROOT(7, 1, 3), ROOT(30, 1, 1),
+				DELTA(3, 2), DELTA(8, 2), DELTA(5, 1)),
+	},	/* r: 1, 1, 7, 30	d: 3^1, 3^1, 5^1, 8^7, 8^7 */
+	{
+		3, ACTION_PUT, EXPECT_DELTA_SAME, EXPECT_ROOT_SAME,
+		EXPECT_STATS(6, ROOT(1, 2, 4), ROOT(7, 1, 3), ROOT(30, 1, 1),
+				DELTA(8, 2), DELTA(3, 1), DELTA(5, 1)),
+	},	/* r: 1, 1, 7, 30	d: 3^1, 5^1, 8^7, 8^7 */
+	{
+		3, ACTION_PUT, EXPECT_DELTA_DEC, EXPECT_ROOT_SAME,
+		EXPECT_STATS(5, ROOT(1, 2, 3), ROOT(7, 1, 3), ROOT(30, 1, 1),
+				DELTA(8, 2), DELTA(5, 1)),
+	},	/* r: 1, 1, 7, 30	d: 5^1, 8^7, 8^7 */
+	{
+		1, ACTION_PUT, EXPECT_DELTA_SAME, EXPECT_ROOT_SAME,
+		EXPECT_STATS(5, ROOT(7, 1, 3), ROOT(1, 1, 2), ROOT(30, 1, 1),
+				DELTA(8, 2), DELTA(5, 1)),
+	},	/* r: 1, 7, 30		d: 5^1, 8^7, 8^7 */
+	{
+		1, ACTION_PUT, EXPECT_DELTA_SAME, EXPECT_ROOT_SAME,
+		EXPECT_STATS(5, ROOT(7, 1, 3), ROOT(30, 1, 1), ROOT(1, 0, 1),
+				DELTA(8, 2), DELTA(5, 1)),
+	},	/* r: 7, 30		d: 5^1, 8^7, 8^7 */
+	{
+		5, ACTION_PUT, EXPECT_DELTA_DEC, EXPECT_ROOT_DEC,
+		EXPECT_STATS(3, ROOT(7, 1, 3), ROOT(30, 1, 1),
+				DELTA(8, 2)),
+	},	/* r: 7, 30		d: 8^7, 8^7 */
+	{
+		5, ACTION_GET, EXPECT_DELTA_SAME, EXPECT_ROOT_INC,
+		EXPECT_STATS(4, ROOT(7, 1, 3), ROOT(30, 1, 1), ROOT(5, 1, 1),
+				DELTA(8, 2)),
+	},	/* r: 7, 30, 5		d: 8^7, 8^7 */
+	{
+		6, ACTION_GET, EXPECT_DELTA_INC, EXPECT_ROOT_SAME,
+		EXPECT_STATS(5, ROOT(7, 1, 3), ROOT(5, 1, 2), ROOT(30, 1, 1),
+				DELTA(8, 2), DELTA(6, 1)),
+	},	/* r: 7, 30, 5		d: 8^7, 8^7, 6^5 */
+	{
+		8, ACTION_GET, EXPECT_DELTA_SAME, EXPECT_ROOT_SAME,
+		EXPECT_STATS(5, ROOT(7, 1, 4), ROOT(5, 1, 2), ROOT(30, 1, 1),
+				DELTA(8, 3), DELTA(6, 1)),
+	},	/* r: 7, 30, 5		d: 8^7, 8^7, 8^7, 6^5 */
+	{
+		8, ACTION_PUT, EXPECT_DELTA_SAME, EXPECT_ROOT_SAME,
+		EXPECT_STATS(5, ROOT(7, 1, 3), ROOT(5, 1, 2), ROOT(30, 1, 1),
+				DELTA(8, 2), DELTA(6, 1)),
+	},	/* r: 7, 30, 5		d: 8^7, 8^7, 6^5 */
+	{
+		8, ACTION_PUT, EXPECT_DELTA_SAME, EXPECT_ROOT_SAME,
+		EXPECT_STATS(5, ROOT(7, 1, 2), ROOT(5, 1, 2), ROOT(30, 1, 1),
+				DELTA(8, 1), DELTA(6, 1)),
+	},	/* r: 7, 30, 5		d: 8^7, 6^5 */
+	{
+		8, ACTION_PUT, EXPECT_DELTA_DEC, EXPECT_ROOT_SAME,
+		EXPECT_STATS(4, ROOT(5, 1, 2), ROOT(7, 1, 1), ROOT(30, 1, 1),
+				DELTA(6, 1)),
+	},	/* r: 7, 30, 5		d: 6^5 */
+	{
+		8, ACTION_GET, EXPECT_DELTA_INC, EXPECT_ROOT_SAME,
+		EXPECT_STATS(5, ROOT(5, 1, 3), ROOT(7, 1, 1), ROOT(30, 1, 1),
+				DELTA(6, 1), DELTA(8, 1)),
+	},	/* r: 7, 30, 5		d: 6^5, 8^5 */
+	{
+		7, ACTION_PUT, EXPECT_DELTA_SAME, EXPECT_ROOT_DEC,
+		EXPECT_STATS(4, ROOT(5, 1, 3), ROOT(30, 1, 1),
+				DELTA(6, 1), DELTA(8, 1)),
+	},	/* r: 30, 5		d: 6^5, 8^5 */
+	{
+		30, ACTION_PUT, EXPECT_DELTA_SAME, EXPECT_ROOT_DEC,
+		EXPECT_STATS(3, ROOT(5, 1, 3),
+				DELTA(6, 1), DELTA(8, 1)),
+	},	/* r: 5			d: 6^5, 8^5 */
+	{
+		5, ACTION_PUT, EXPECT_DELTA_SAME, EXPECT_ROOT_SAME,
+		EXPECT_STATS(3, ROOT(5, 0, 2),
+				DELTA(6, 1), DELTA(8, 1)),
+	},	/* r:			d: 6^5, 8^5 */
+	{
+		6, ACTION_PUT, EXPECT_DELTA_DEC, EXPECT_ROOT_SAME,
+		EXPECT_STATS(2, ROOT(5, 0, 1),
+				DELTA(8, 1)),
+	},	/* r:			d: 6^5 */
+	{
+		8, ACTION_PUT, EXPECT_DELTA_DEC, EXPECT_ROOT_DEC,
+		EXPECT_STATS(0, ),
+	},	/* r:			d: */
+};
+
+static int check_expect(struct world *world,
+			const struct action_item *action_item,
+			unsigned int orig_delta_count,
+			unsigned int orig_root_count)
+{
+	unsigned int key_id = action_item->key_id;
+
+	switch (action_item->expect_delta) {
+	case EXPECT_DELTA_SAME:
+		if (orig_delta_count != world->delta_count) {
+			pr_err("Key %u: Delta count changed while expected to remain the same.\n",
+			       key_id);
+			return -EINVAL;
+		}
+		break;
+	case EXPECT_DELTA_INC:
+		if (WARN_ON(action_item->action == ACTION_PUT))
+			return -EINVAL;
+		if (orig_delta_count + 1 != world->delta_count) {
+			pr_err("Key %u: Delta count was not incremented.\n",
+			       key_id);
+			return -EINVAL;
+		}
+		break;
+	case EXPECT_DELTA_DEC:
+		if (WARN_ON(action_item->action == ACTION_GET))
+			return -EINVAL;
+		if (orig_delta_count - 1 != world->delta_count) {
+			pr_err("Key %u: Delta count was not decremented.\n",
+			       key_id);
+			return -EINVAL;
+		}
+		break;
+	}
+
+	switch (action_item->expect_root) {
+	case EXPECT_ROOT_SAME:
+		if (orig_root_count != world->root_count) {
+			pr_err("Key %u: Root count changed while expected to remain the same.\n",
+			       key_id);
+			return -EINVAL;
+		}
+		break;
+	case EXPECT_ROOT_INC:
+		if (WARN_ON(action_item->action == ACTION_PUT))
+			return -EINVAL;
+		if (orig_root_count + 1 != world->root_count) {
+			pr_err("Key %u: Root count was not incremented.\n",
+			       key_id);
+			return -EINVAL;
+		}
+		break;
+	case EXPECT_ROOT_DEC:
+		if (WARN_ON(action_item->action == ACTION_GET))
+			return -EINVAL;
+		if (orig_root_count - 1 != world->root_count) {
+			pr_err("Key %u: Root count was not decremented.\n",
+			       key_id);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static unsigned int obj_to_key_id(struct objagg_obj *objagg_obj)
+{
+	const struct tokey *root_key;
+	const struct delta *delta;
+	unsigned int key_id;
+
+	root_key = objagg_obj_root_priv(objagg_obj);
+	key_id = root_key->id;
+	delta = objagg_obj_delta_priv(objagg_obj);
+	if (delta)
+		key_id += delta->key_id_diff;
+	return key_id;
+}
+
+static int
+check_expect_stats_nums(const struct objagg_obj_stats_info *stats_info,
+			const struct expect_stats_info *expect_stats_info,
+			const char **errmsg)
+{
+	if (stats_info->is_root != expect_stats_info->is_root) {
+		if (errmsg)
+			*errmsg = "Incorrect root/delta indication";
+		return -EINVAL;
+	}
+	if (stats_info->stats.user_count !=
+	    expect_stats_info->stats.user_count) {
+		if (errmsg)
+			*errmsg = "Incorrect user count";
+		return -EINVAL;
+	}
+	if (stats_info->stats.delta_user_count !=
+	    expect_stats_info->stats.delta_user_count) {
+		if (errmsg)
+			*errmsg = "Incorrect delta user count";
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int
+check_expect_stats_key_id(const struct objagg_obj_stats_info *stats_info,
+			  const struct expect_stats_info *expect_stats_info,
+			  const char **errmsg)
+{
+	if (obj_to_key_id(stats_info->objagg_obj) !=
+	    expect_stats_info->key_id) {
+		if (errmsg)
+			*errmsg = "incorrect key id";
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int check_expect_stats_neigh(const struct objagg_stats *stats,
+				    const struct expect_stats *expect_stats,
+				    int pos)
+{
+	int i;
+	int err;
+
+	for (i = pos - 1; i >= 0; i--) {
+		err = check_expect_stats_nums(&stats->stats_info[i],
+					      &expect_stats->info[pos], NULL);
+		if (err)
+			break;
+		err = check_expect_stats_key_id(&stats->stats_info[i],
+						&expect_stats->info[pos], NULL);
+		if (!err)
+			return 0;
+	}
+	for (i = pos + 1; i < stats->stats_info_count; i++) {
+		err = check_expect_stats_nums(&stats->stats_info[i],
+					      &expect_stats->info[pos], NULL);
+		if (err)
+			break;
+		err = check_expect_stats_key_id(&stats->stats_info[i],
+						&expect_stats->info[pos], NULL);
+		if (!err)
+			return 0;
+	}
+	return -EINVAL;
+}
+
+static int __check_expect_stats(const struct objagg_stats *stats,
+				const struct expect_stats *expect_stats,
+				const char **errmsg)
+{
+	int i;
+	int err;
+
+	if (stats->stats_info_count != expect_stats->info_count) {
+		*errmsg = "Unexpected object count";
+		return -EINVAL;
+	}
+
+	for (i = 0; i < stats->stats_info_count; i++) {
+		err = check_expect_stats_nums(&stats->stats_info[i],
+					      &expect_stats->info[i], errmsg);
+		if (err)
+			return err;
+		err = check_expect_stats_key_id(&stats->stats_info[i],
+						&expect_stats->info[i], errmsg);
+		if (err) {
+			/* It is possible that one of the neighbor stats with
+			 * same numbers have the correct key id, so check it
+			 */
+			err = check_expect_stats_neigh(stats, expect_stats, i);
+			if (err)
+				return err;
+		}
+	}
+	return 0;
+}
+
+static int check_expect_stats(struct objagg *objagg,
+			      const struct expect_stats *expect_stats,
+			      const char **errmsg)
+{
+	const struct objagg_stats *stats;
+	int err;
+
+	stats = objagg_stats_get(objagg);
+	if (IS_ERR(stats))
+		return PTR_ERR(stats);
+	err = __check_expect_stats(stats, expect_stats, errmsg);
+	objagg_stats_put(stats);
+	return err;
+}
+
+static int test_delta_action_item(struct world *world,
+				  struct objagg *objagg,
+				  const struct action_item *action_item,
+				  bool inverse)
+{
+	unsigned int orig_delta_count = world->delta_count;
+	unsigned int orig_root_count = world->root_count;
+	unsigned int key_id = action_item->key_id;
+	enum action action = action_item->action;
+	struct objagg_obj *objagg_obj;
+	const char *errmsg;
+	int err;
+
+	if (inverse)
+		action = action == ACTION_GET ? ACTION_PUT : ACTION_GET;
+
+	switch (action) {
+	case ACTION_GET:
+		objagg_obj = world_obj_get(world, objagg, key_id);
+		if (IS_ERR(objagg_obj))
+			return PTR_ERR(objagg_obj);
+		break;
+	case ACTION_PUT:
+		world_obj_put(world, objagg, key_id);
+		break;
+	}
+
+	if (inverse)
+		return 0;
+	err = check_expect(world, action_item,
+			   orig_delta_count, orig_root_count);
+	if (err)
+		goto errout;
+
+	err = check_expect_stats(objagg, &action_item->expect_stats, &errmsg);
+	if (err) {
+		pr_err("Key %u: Stats: %s\n", action_item->key_id, errmsg);
+		goto errout;
+	}
+
+	return 0;
+
+errout:
+	/* This can only happen when action is not inversed.
+	 * So in case of an error, cleanup by doing inverse action.
+	 */
+	test_delta_action_item(world, objagg, action_item, true);
+	return err;
+}
+
+static int test_delta(void)
+{
+	struct world world = {};
+	struct objagg *objagg;
+	int i;
+	int err;
+
+	objagg = objagg_create(&delta_ops, &world);
+	if (IS_ERR(objagg))
+		return PTR_ERR(objagg);
+
+	for (i = 0; i < ARRAY_SIZE(action_items); i++) {
+		err = test_delta_action_item(&world, objagg,
+					     &action_items[i], false);
+		if (err)
+			goto err_do_action_item;
+	}
+
+	objagg_destroy(objagg);
+	return 0;
+
+err_do_action_item:
+	for (i--; i >= 0; i--)
+		test_delta_action_item(&world, objagg, &action_items[i], true);
+
+	objagg_destroy(objagg);
+	return err;
+}
+
+static int __init test_objagg_init(void)
+{
+	int err;
+
+	err = test_nodelta();
+	if (err)
+		return err;
+	return test_delta();
+}
+
+static void __exit test_objagg_exit(void)
+{
+}
+
+module_init(test_objagg_init);
+module_exit(test_objagg_exit);
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>");
+MODULE_DESCRIPTION("Test module for objagg");
-- 
cgit v1.2.3


From c71abd7d9414d059005391120e2166d61e7905ca Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 14 Nov 2018 08:22:29 +0000
Subject: mlxsw: spectrum: acl_erp: Convert to use objagg for tracking ERPs

Currently the ERPs are tracked internally in a hashtable. Benefit from
the newly introduced objagg library and use it to track ERPs. At this
point, there is no nesting of objects done, as the delta_create callback
always returns -EOPNOTSUPP. On the way, add "mask" into ERP mask get and
set functions and struct names.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Kconfig        |   1 +
 .../ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c   |  12 +-
 .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c   |  22 ++--
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 135 +++++++++++----------
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |  19 +--
 5 files changed, 99 insertions(+), 90 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index 8a291eb36c64..080ddd1942ec 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -80,6 +80,7 @@ config MLXSW_SPECTRUM
 	depends on IPV6_GRE || IPV6_GRE=n
 	select GENERIC_ALLOCATOR
 	select PARMAN
+	select OBJAGG
 	select MLXFW
 	default m
 	---help---
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 8ca77f3e8f27..62e6cf4bc16e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -34,15 +34,15 @@ mlxsw_sp2_acl_ctcam_region_entry_insert(struct mlxsw_sp_acl_ctcam_region *cregio
 {
 	struct mlxsw_sp_acl_atcam_region *aregion;
 	struct mlxsw_sp_acl_atcam_entry *aentry;
-	struct mlxsw_sp_acl_erp *erp;
+	struct mlxsw_sp_acl_erp_mask *erp_mask;
 
 	aregion = mlxsw_sp_acl_tcam_cregion_aregion(cregion);
 	aentry = mlxsw_sp_acl_tcam_centry_aentry(centry);
 
-	erp = mlxsw_sp_acl_erp_get(aregion, mask, true);
-	if (IS_ERR(erp))
-		return PTR_ERR(erp);
-	aentry->erp = erp;
+	erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, true);
+	if (IS_ERR(erp_mask))
+		return PTR_ERR(erp_mask);
+	aentry->erp_mask = erp_mask;
 
 	return 0;
 }
@@ -57,7 +57,7 @@ mlxsw_sp2_acl_ctcam_region_entry_remove(struct mlxsw_sp_acl_ctcam_region *cregio
 	aregion = mlxsw_sp_acl_tcam_cregion_aregion(cregion);
 	aentry = mlxsw_sp_acl_tcam_centry_aentry(centry);
 
-	mlxsw_sp_acl_erp_put(aregion, aentry->erp);
+	mlxsw_sp_acl_erp_mask_put(aregion, aentry->erp_mask);
 }
 
 static const struct mlxsw_sp_acl_ctcam_region_ops
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index 2dda028f94db..5a0b88707269 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -64,7 +64,7 @@ static const struct rhashtable_params mlxsw_sp_acl_atcam_entries_ht_params = {
 static bool
 mlxsw_sp_acl_atcam_is_centry(const struct mlxsw_sp_acl_atcam_entry *aentry)
 {
-	return mlxsw_sp_acl_erp_is_ctcam_erp(aentry->erp);
+	return mlxsw_sp_acl_erp_mask_is_ctcam(aentry->erp_mask);
 }
 
 static int
@@ -379,7 +379,7 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 				       struct mlxsw_sp_acl_rule_info *rulei)
 {
 	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
-	u8 erp_id = mlxsw_sp_acl_erp_id(aentry->erp);
+	u8 erp_id = mlxsw_sp_acl_erp_mask_erp_id(aentry->erp_mask);
 	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
 	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
 	u32 kvdl_index, priority;
@@ -418,7 +418,7 @@ mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id = aentry->lkey_id;
 	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
-	u8 erp_id = mlxsw_sp_acl_erp_id(aentry->erp);
+	u8 erp_id = mlxsw_sp_acl_erp_mask_erp_id(aentry->erp_mask);
 	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
 
 	mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0,
@@ -438,7 +438,7 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
 	char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN] = { 0 };
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
-	struct mlxsw_sp_acl_erp *erp;
+	struct mlxsw_sp_acl_erp_mask *erp_mask;
 	unsigned int blocks_count;
 	int err;
 
@@ -446,11 +446,11 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_afk_encode(afk, region->key_info, &rulei->values,
 			 aentry->ht_key.enc_key, mask, 0, blocks_count - 1);
 
-	erp = mlxsw_sp_acl_erp_get(aregion, mask, false);
-	if (IS_ERR(erp))
-		return PTR_ERR(erp);
-	aentry->erp = erp;
-	aentry->ht_key.erp_id = mlxsw_sp_acl_erp_id(erp);
+	erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, false);
+	if (IS_ERR(erp_mask))
+		return PTR_ERR(erp_mask);
+	aentry->erp_mask = erp_mask;
+	aentry->ht_key.erp_id = mlxsw_sp_acl_erp_mask_erp_id(erp_mask);
 
 	/* We can't insert identical rules into the A-TCAM, so fail and
 	 * let the rule spill into C-TCAM
@@ -472,7 +472,7 @@ err_rule_insert:
 	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
 			       mlxsw_sp_acl_atcam_entries_ht_params);
 err_rhashtable_insert:
-	mlxsw_sp_acl_erp_put(aregion, erp);
+	mlxsw_sp_acl_erp_mask_put(aregion, erp_mask);
 	return err;
 }
 
@@ -484,7 +484,7 @@ __mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_atcam_region_entry_remove(mlxsw_sp, aregion, aentry);
 	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
 			       mlxsw_sp_acl_atcam_entries_ht_params);
-	mlxsw_sp_acl_erp_put(aregion, aentry->erp);
+	mlxsw_sp_acl_erp_mask_put(aregion, aentry->erp_mask);
 }
 
 int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 0a4fd3c8662a..52cbdf79bc18 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -7,7 +7,7 @@
 #include <linux/gfp.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
-#include <linux/rhashtable.h>
+#include <linux/objagg.h>
 #include <linux/rtnetlink.h>
 #include <linux/slab.h>
 
@@ -36,10 +36,8 @@ struct mlxsw_sp_acl_erp {
 	struct mlxsw_sp_acl_erp_key key;
 	u8 id;
 	u8 index;
-	refcount_t refcnt;
 	DECLARE_BITMAP(mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN);
 	struct list_head list;
-	struct rhash_head ht_node;
 	struct mlxsw_sp_acl_erp_table *erp_table;
 };
 
@@ -53,7 +51,6 @@ struct mlxsw_sp_acl_erp_table {
 	DECLARE_BITMAP(erp_id_bitmap, MLXSW_SP_ACL_ERP_MAX_PER_REGION);
 	DECLARE_BITMAP(erp_index_bitmap, MLXSW_SP_ACL_ERP_MAX_PER_REGION);
 	struct list_head atcam_erps_list;
-	struct rhashtable erp_ht;
 	struct mlxsw_sp_acl_erp_core *erp_core;
 	struct mlxsw_sp_acl_atcam_region *aregion;
 	const struct mlxsw_sp_acl_erp_table_ops *ops;
@@ -61,12 +58,7 @@ struct mlxsw_sp_acl_erp_table {
 	unsigned int num_atcam_erps;
 	unsigned int num_max_atcam_erps;
 	unsigned int num_ctcam_erps;
-};
-
-static const struct rhashtable_params mlxsw_sp_acl_erp_ht_params = {
-	.key_len = sizeof(struct mlxsw_sp_acl_erp_key),
-	.key_offset = offsetof(struct mlxsw_sp_acl_erp, key),
-	.head_offset = offsetof(struct mlxsw_sp_acl_erp, ht_node),
+	struct objagg *objagg;
 };
 
 struct mlxsw_sp_acl_erp_table_ops {
@@ -119,16 +111,6 @@ static const struct mlxsw_sp_acl_erp_table_ops erp_no_mask_ops = {
 	.erp_destroy = mlxsw_sp_acl_erp_no_mask_destroy,
 };
 
-bool mlxsw_sp_acl_erp_is_ctcam_erp(const struct mlxsw_sp_acl_erp *erp)
-{
-	return erp->key.ctcam;
-}
-
-u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp)
-{
-	return erp->id;
-}
-
 static unsigned int
 mlxsw_sp_acl_erp_table_entry_size(const struct mlxsw_sp_acl_erp_table *erp_table)
 {
@@ -259,7 +241,6 @@ mlxsw_sp_acl_erp_generic_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask,
 			  MLXSW_SP_ACL_TCAM_MASK_LEN);
 	list_add(&erp->list, &erp_table->atcam_erps_list);
-	refcount_set(&erp->refcnt, 1);
 	erp_table->num_atcam_erps++;
 	erp->erp_table = erp_table;
 
@@ -267,15 +248,8 @@ mlxsw_sp_acl_erp_generic_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	if (err)
 		goto err_master_mask_set;
 
-	err = rhashtable_insert_fast(&erp_table->erp_ht, &erp->ht_node,
-				     mlxsw_sp_acl_erp_ht_params);
-	if (err)
-		goto err_rhashtable_insert;
-
 	return erp;
 
-err_rhashtable_insert:
-	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
 err_master_mask_set:
 	erp_table->num_atcam_erps--;
 	list_del(&erp->list);
@@ -290,8 +264,6 @@ mlxsw_sp_acl_erp_generic_destroy(struct mlxsw_sp_acl_erp *erp)
 {
 	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
 
-	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
-			       mlxsw_sp_acl_erp_ht_params);
 	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
 	erp_table->num_atcam_erps--;
 	list_del(&erp->list);
@@ -697,7 +669,6 @@ __mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	memcpy(&erp->key, key, sizeof(*key));
 	bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask,
 			  MLXSW_SP_ACL_TCAM_MASK_LEN);
-	refcount_set(&erp->refcnt, 1);
 	erp_table->num_ctcam_erps++;
 	erp->erp_table = erp_table;
 
@@ -705,11 +676,6 @@ __mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	if (err)
 		goto err_master_mask_set;
 
-	err = rhashtable_insert_fast(&erp_table->erp_ht, &erp->ht_node,
-				     mlxsw_sp_acl_erp_ht_params);
-	if (err)
-		goto err_rhashtable_insert;
-
 	err = mlxsw_sp_acl_erp_region_ctcam_enable(erp_table);
 	if (err)
 		goto err_erp_region_ctcam_enable;
@@ -720,9 +686,6 @@ __mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	return erp;
 
 err_erp_region_ctcam_enable:
-	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
-			       mlxsw_sp_acl_erp_ht_params);
-err_rhashtable_insert:
 	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
 err_master_mask_set:
 	erp_table->num_ctcam_erps--;
@@ -767,8 +730,6 @@ mlxsw_sp_acl_erp_ctcam_mask_destroy(struct mlxsw_sp_acl_erp *erp)
 	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
 
 	mlxsw_sp_acl_erp_region_ctcam_disable(erp_table);
-	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
-			       mlxsw_sp_acl_erp_ht_params);
 	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
 	erp_table->num_ctcam_erps--;
 	kfree(erp);
@@ -940,13 +901,12 @@ mlxsw_sp_acl_erp_no_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
 	WARN_ON(1);
 }
 
-struct mlxsw_sp_acl_erp *
-mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
-		     const char *mask, bool ctcam)
+struct mlxsw_sp_acl_erp_mask *
+mlxsw_sp_acl_erp_mask_get(struct mlxsw_sp_acl_atcam_region *aregion,
+			  const char *mask, bool ctcam)
 {
-	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
 	struct mlxsw_sp_acl_erp_key key;
-	struct mlxsw_sp_acl_erp *erp;
+	struct objagg_obj *objagg_obj;
 
 	/* eRPs are allocated from a shared resource, but currently all
 	 * allocations are done under RTNL.
@@ -955,29 +915,73 @@ mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
 
 	memcpy(key.mask, mask, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
 	key.ctcam = ctcam;
-	erp = rhashtable_lookup_fast(&erp_table->erp_ht, &key,
-				     mlxsw_sp_acl_erp_ht_params);
-	if (erp) {
-		refcount_inc(&erp->refcnt);
-		return erp;
-	}
+	objagg_obj = objagg_obj_get(aregion->erp_table->objagg, &key);
+	if (IS_ERR(objagg_obj))
+		return ERR_CAST(objagg_obj);
+	return (struct mlxsw_sp_acl_erp_mask *) objagg_obj;
+}
+
+void mlxsw_sp_acl_erp_mask_put(struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_erp_mask *erp_mask)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+
+	ASSERT_RTNL();
+	objagg_obj_put(aregion->erp_table->objagg, objagg_obj);
+}
+
+bool
+mlxsw_sp_acl_erp_mask_is_ctcam(const struct mlxsw_sp_acl_erp_mask *erp_mask)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	const struct mlxsw_sp_acl_erp_key *key = objagg_obj_raw(objagg_obj);
+
+	return key->ctcam;
+}
+
+u8 mlxsw_sp_acl_erp_mask_erp_id(const struct mlxsw_sp_acl_erp_mask *erp_mask)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	const struct mlxsw_sp_acl_erp *erp = objagg_obj_root_priv(objagg_obj);
+
+	return erp->id;
+}
 
-	return erp_table->ops->erp_create(erp_table, &key);
+static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj,
+					   void *obj)
+{
+	return ERR_PTR(-EOPNOTSUPP);
 }
 
-void mlxsw_sp_acl_erp_put(struct mlxsw_sp_acl_atcam_region *aregion,
-			  struct mlxsw_sp_acl_erp *erp)
+static void mlxsw_sp_acl_erp_delta_destroy(void *priv, void *delta_priv)
 {
+}
+
+static void *mlxsw_sp_acl_erp_root_create(void *priv, void *obj)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion = priv;
 	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+	struct mlxsw_sp_acl_erp_key *key = obj;
 
-	ASSERT_RTNL();
+	return erp_table->ops->erp_create(erp_table, key);
+}
 
-	if (!refcount_dec_and_test(&erp->refcnt))
-		return;
+static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion = priv;
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
 
-	erp_table->ops->erp_destroy(erp_table, erp);
+	erp_table->ops->erp_destroy(erp_table, root_priv);
 }
 
+static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = {
+	.obj_size = sizeof(struct mlxsw_sp_acl_erp_key),
+	.delta_create = mlxsw_sp_acl_erp_delta_create,
+	.delta_destroy = mlxsw_sp_acl_erp_delta_destroy,
+	.root_create = mlxsw_sp_acl_erp_root_create,
+	.root_destroy = mlxsw_sp_acl_erp_root_destroy,
+};
+
 static struct mlxsw_sp_acl_erp_table *
 mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion)
 {
@@ -988,9 +992,12 @@ mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion)
 	if (!erp_table)
 		return ERR_PTR(-ENOMEM);
 
-	err = rhashtable_init(&erp_table->erp_ht, &mlxsw_sp_acl_erp_ht_params);
-	if (err)
-		goto err_rhashtable_init;
+	erp_table->objagg = objagg_create(&mlxsw_sp_acl_erp_objagg_ops,
+					  aregion);
+	if (IS_ERR(erp_table->objagg)) {
+		err = PTR_ERR(erp_table->objagg);
+		goto err_objagg_create;
+	}
 
 	erp_table->erp_core = aregion->atcam->erp_core;
 	erp_table->ops = &erp_no_mask_ops;
@@ -999,7 +1006,7 @@ mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion)
 
 	return erp_table;
 
-err_rhashtable_init:
+err_objagg_create:
 	kfree(erp_table);
 	return ERR_PTR(err);
 }
@@ -1008,7 +1015,7 @@ static void
 mlxsw_sp_acl_erp_table_destroy(struct mlxsw_sp_acl_erp_table *erp_table)
 {
 	WARN_ON(!list_empty(&erp_table->atcam_erps_list));
-	rhashtable_destroy(&erp_table->erp_ht);
+	objagg_destroy(erp_table->objagg);
 	kfree(erp_table);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 219a4e26c332..854436c5ea93 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -167,7 +167,7 @@ struct mlxsw_sp_acl_atcam_entry {
 	struct mlxsw_sp_acl_atcam_entry_ht_key ht_key;
 	struct mlxsw_sp_acl_ctcam_entry centry;
 	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
-	struct mlxsw_sp_acl_erp *erp;
+	struct mlxsw_sp_acl_erp_mask *erp_mask;
 };
 
 static inline struct mlxsw_sp_acl_atcam_region *
@@ -209,15 +209,16 @@ int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
 void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
 			     struct mlxsw_sp_acl_atcam *atcam);
 
-struct mlxsw_sp_acl_erp;
+struct mlxsw_sp_acl_erp_mask;
 
-bool mlxsw_sp_acl_erp_is_ctcam_erp(const struct mlxsw_sp_acl_erp *erp);
-u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp);
-struct mlxsw_sp_acl_erp *
-mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
-		     const char *mask, bool ctcam);
-void mlxsw_sp_acl_erp_put(struct mlxsw_sp_acl_atcam_region *aregion,
-			  struct mlxsw_sp_acl_erp *erp);
+bool
+mlxsw_sp_acl_erp_mask_is_ctcam(const struct mlxsw_sp_acl_erp_mask *erp_mask);
+u8 mlxsw_sp_acl_erp_mask_erp_id(const struct mlxsw_sp_acl_erp_mask *erp_mask);
+struct mlxsw_sp_acl_erp_mask *
+mlxsw_sp_acl_erp_mask_get(struct mlxsw_sp_acl_atcam_region *aregion,
+			  const char *mask, bool ctcam);
+void mlxsw_sp_acl_erp_mask_put(struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_erp_mask *erp_mask);
 int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion);
 void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
 int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp,
-- 
cgit v1.2.3


From d07cd660603349df100e56ef98ee31ae7a5e1423 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 14 Nov 2018 08:22:30 +0000
Subject: mlxsw: spectrum: acl: Pass key pointer to master_mask_set/clear

The device requires that the master mask of each region will be
composed from a logical OR between all the unmasked bits in the region.
Currently, this is just a logical OR between all the eRPs used in the
region, but the next patch is going to introduce delta bits support
which need to be taken into account as well.

Since the eRP does not include the delta bits, pass the key pointer to
mlxsw_sp_acl_erp_master_mask_set/clear instead. Convert key->mask to
the bitmap on fly.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 30 ++++++++++++----------
 1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 52cbdf79bc18..818e03cf9add 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -176,12 +176,15 @@ mlxsw_sp_acl_erp_master_mask_update(struct mlxsw_sp_acl_erp_table *erp_table)
 
 static int
 mlxsw_sp_acl_erp_master_mask_set(struct mlxsw_sp_acl_erp_table *erp_table,
-				 const struct mlxsw_sp_acl_erp *erp)
+				 struct mlxsw_sp_acl_erp_key *key)
 {
+	DECLARE_BITMAP(mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN);
 	unsigned long bit;
 	int err;
 
-	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+	bitmap_from_arr32(mask_bitmap, (u32 *) key->mask,
+			  MLXSW_SP_ACL_TCAM_MASK_LEN);
+	for_each_set_bit(bit, mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
 		mlxsw_sp_acl_erp_master_mask_bit_set(bit,
 						     &erp_table->master_mask);
 
@@ -192,7 +195,7 @@ mlxsw_sp_acl_erp_master_mask_set(struct mlxsw_sp_acl_erp_table *erp_table,
 	return 0;
 
 err_master_mask_update:
-	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+	for_each_set_bit(bit, mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
 		mlxsw_sp_acl_erp_master_mask_bit_clear(bit,
 						       &erp_table->master_mask);
 	return err;
@@ -200,12 +203,15 @@ err_master_mask_update:
 
 static int
 mlxsw_sp_acl_erp_master_mask_clear(struct mlxsw_sp_acl_erp_table *erp_table,
-				   const struct mlxsw_sp_acl_erp *erp)
+				   struct mlxsw_sp_acl_erp_key *key)
 {
+	DECLARE_BITMAP(mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN);
 	unsigned long bit;
 	int err;
 
-	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+	bitmap_from_arr32(mask_bitmap, (u32 *) key->mask,
+			  MLXSW_SP_ACL_TCAM_MASK_LEN);
+	for_each_set_bit(bit, mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
 		mlxsw_sp_acl_erp_master_mask_bit_clear(bit,
 						       &erp_table->master_mask);
 
@@ -216,7 +222,7 @@ mlxsw_sp_acl_erp_master_mask_clear(struct mlxsw_sp_acl_erp_table *erp_table,
 	return 0;
 
 err_master_mask_update:
-	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+	for_each_set_bit(bit, mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
 		mlxsw_sp_acl_erp_master_mask_bit_set(bit,
 						     &erp_table->master_mask);
 	return err;
@@ -238,13 +244,11 @@ mlxsw_sp_acl_erp_generic_create(struct mlxsw_sp_acl_erp_table *erp_table,
 		goto err_erp_id_get;
 
 	memcpy(&erp->key, key, sizeof(*key));
-	bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask,
-			  MLXSW_SP_ACL_TCAM_MASK_LEN);
 	list_add(&erp->list, &erp_table->atcam_erps_list);
 	erp_table->num_atcam_erps++;
 	erp->erp_table = erp_table;
 
-	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, erp);
+	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, &erp->key);
 	if (err)
 		goto err_master_mask_set;
 
@@ -264,7 +268,7 @@ mlxsw_sp_acl_erp_generic_destroy(struct mlxsw_sp_acl_erp *erp)
 {
 	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
 
-	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, &erp->key);
 	erp_table->num_atcam_erps--;
 	list_del(&erp->list);
 	mlxsw_sp_acl_erp_id_put(erp_table, erp->id);
@@ -672,7 +676,7 @@ __mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	erp_table->num_ctcam_erps++;
 	erp->erp_table = erp_table;
 
-	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, erp);
+	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, &erp->key);
 	if (err)
 		goto err_master_mask_set;
 
@@ -686,7 +690,7 @@ __mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	return erp;
 
 err_erp_region_ctcam_enable:
-	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, &erp->key);
 err_master_mask_set:
 	erp_table->num_ctcam_erps--;
 	kfree(erp);
@@ -730,7 +734,7 @@ mlxsw_sp_acl_erp_ctcam_mask_destroy(struct mlxsw_sp_acl_erp *erp)
 	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
 
 	mlxsw_sp_acl_erp_region_ctcam_disable(erp_table);
-	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, &erp->key);
 	erp_table->num_ctcam_erps--;
 	kfree(erp);
 
-- 
cgit v1.2.3


From 3bc6f3858a0d25667164f9b58667d7f3fbce98b6 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 14 Nov 2018 08:22:31 +0000
Subject: mlxsw: core_acl: Change order of args of ops->encode_block()

Change order so it is aligned with the usual case where the "write_to"
buffer comes as the first arg.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c     | 4 ++--
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h     | 2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c | 8 ++++----
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index 785bf01fe2be..98c00ea9c398 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -452,9 +452,9 @@ void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 		}
 
 		if (key)
-			mlxsw_afk->ops->encode_block(block_key, i, key);
+			mlxsw_afk->ops->encode_block(key, i, block_key);
 		if (mask)
-			mlxsw_afk->ops->encode_block(block_mask, i, mask);
+			mlxsw_afk->ops->encode_block(mask, i, block_mask);
 	}
 }
 EXPORT_SYMBOL(mlxsw_afk_encode);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index c29c045d826d..6a44501d8af7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -188,7 +188,7 @@ struct mlxsw_afk;
 struct mlxsw_afk_ops {
 	const struct mlxsw_afk_block *blocks;
 	unsigned int blocks_count;
-	void (*encode_block)(char *block, int block_index, char *output);
+	void (*encode_block)(char *output, int block_index, char *block);
 };
 
 struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index d409b09ba8df..9b93c6c3c89b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -98,8 +98,8 @@ static const struct mlxsw_afk_block mlxsw_sp1_afk_blocks[] = {
 
 #define MLXSW_SP1_AFK_KEY_BLOCK_SIZE 16
 
-static void mlxsw_sp1_afk_encode_block(char *block, int block_index,
-				       char *output)
+static void mlxsw_sp1_afk_encode_block(char *output, int block_index,
+				       char *block)
 {
 	unsigned int offset = block_index * MLXSW_SP1_AFK_KEY_BLOCK_SIZE;
 	char *output_indexed = output + offset;
@@ -263,8 +263,8 @@ static const struct mlxsw_sp2_afk_block_layout mlxsw_sp2_afk_blocks_layout[] = {
 	MLXSW_SP2_AFK_BLOCK_LAYOUT(block11, 0x00, 12),
 };
 
-static void mlxsw_sp2_afk_encode_block(char *block, int block_index,
-				       char *output)
+static void mlxsw_sp2_afk_encode_block(char *output, int block_index,
+				       char *block)
 {
 	u64 block_value = mlxsw_sp2_afk_block_value_get(block);
 	const struct mlxsw_sp2_afk_block_layout *block_layout;
-- 
cgit v1.2.3


From b1ce60e6214d93fbeffa39e6f9db21c0a4591b1e Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 14 Nov 2018 08:22:32 +0000
Subject: mlxsw: spectrum: acl: Don't encode the key again in
 mlxsw_sp_acl_atcam_12kb_lkey_id_get()

No need to do key encoding again in
mlxsw_sp_acl_atcam_12kb_lkey_id_get(). Instead of that, introduce
a new helper that would just clear unused blocks.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/core_acl_flex_keys.c   | 10 ++++++++
 .../ethernet/mellanox/mlxsw/core_acl_flex_keys.h   |  3 +++
 .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c   | 22 ++++++++---------
 .../mellanox/mlxsw/spectrum_acl_flex_keys.c        | 28 +++++++++++++++++++---
 4 files changed, 49 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index 98c00ea9c398..0900ccfdf315 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -458,3 +458,13 @@ void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 	}
 }
 EXPORT_SYMBOL(mlxsw_afk_encode);
+
+void mlxsw_afk_clear(struct mlxsw_afk *mlxsw_afk, char *key,
+		     int block_start, int block_end)
+{
+	int i;
+
+	for (i = block_start; i <= block_end; i++)
+		mlxsw_afk->ops->clear_block(key, i);
+}
+EXPORT_SYMBOL(mlxsw_afk_clear);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index 6a44501d8af7..a5303c0b53b4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -189,6 +189,7 @@ struct mlxsw_afk_ops {
 	const struct mlxsw_afk_block *blocks;
 	unsigned int blocks_count;
 	void (*encode_block)(char *output, int block_index, char *block);
+	void (*clear_block)(char *output, int block_index);
 };
 
 struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
@@ -229,5 +230,7 @@ void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
 		      char *key, char *mask, int block_start, int block_end);
+void mlxsw_afk_clear(struct mlxsw_afk *mlxsw_afk, char *key,
+		     int block_start, int block_end);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index 5a0b88707269..ffdf464660be 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -14,8 +14,8 @@
 #include "spectrum_acl_tcam.h"
 #include "core_acl_flex_keys.h"
 
-#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_START	6
-#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_END	11
+#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_CLEAR_START	0
+#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_CLEAR_END	5
 
 struct mlxsw_sp_acl_atcam_lkey_id_ht_key {
 	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* MSB blocks */
@@ -34,7 +34,7 @@ struct mlxsw_sp_acl_atcam_region_ops {
 	void (*fini)(struct mlxsw_sp_acl_atcam_region *aregion);
 	struct mlxsw_sp_acl_atcam_lkey_id *
 		(*lkey_id_get)(struct mlxsw_sp_acl_atcam_region *aregion,
-			       struct mlxsw_sp_acl_rule_info *rulei, u8 erp_id);
+			       char *enc_key, u8 erp_id);
 	void (*lkey_id_put)(struct mlxsw_sp_acl_atcam_region *aregion,
 			    struct mlxsw_sp_acl_atcam_lkey_id *lkey_id);
 };
@@ -90,8 +90,7 @@ mlxsw_sp_acl_atcam_region_generic_fini(struct mlxsw_sp_acl_atcam_region *aregion
 
 static struct mlxsw_sp_acl_atcam_lkey_id *
 mlxsw_sp_acl_atcam_generic_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion,
-				       struct mlxsw_sp_acl_rule_info *rulei,
-				       u8 erp_id)
+				       char *enc_key, u8 erp_id)
 {
 	struct mlxsw_sp_acl_atcam_region_generic *region_generic;
 
@@ -220,8 +219,7 @@ mlxsw_sp_acl_atcam_lkey_id_destroy(struct mlxsw_sp_acl_atcam_region *aregion,
 
 static struct mlxsw_sp_acl_atcam_lkey_id *
 mlxsw_sp_acl_atcam_12kb_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion,
-				    struct mlxsw_sp_acl_rule_info *rulei,
-				    u8 erp_id)
+				    char *enc_key, u8 erp_id)
 {
 	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv;
 	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
@@ -230,9 +228,10 @@ mlxsw_sp_acl_atcam_12kb_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion,
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
 
-	mlxsw_afk_encode(afk, region->key_info, &rulei->values, ht_key.enc_key,
-			 NULL, MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_START,
-			 MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_END);
+	memcpy(ht_key.enc_key, enc_key, sizeof(ht_key.enc_key));
+	mlxsw_afk_clear(afk, ht_key.enc_key,
+			MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_CLEAR_START,
+			MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_CLEAR_END);
 	ht_key.erp_id = erp_id;
 	lkey_id = rhashtable_lookup_fast(&region_12kb->lkey_ht, &ht_key,
 					 mlxsw_sp_acl_atcam_lkey_id_ht_params);
@@ -389,7 +388,8 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	lkey_id = aregion->ops->lkey_id_get(aregion, rulei, erp_id);
+	lkey_id = aregion->ops->lkey_id_get(aregion, aentry->ht_key.enc_key,
+					    erp_id);
 	if (IS_ERR(lkey_id))
 		return PTR_ERR(lkey_id);
 	aentry->lkey_id = lkey_id;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index 9b93c6c3c89b..2e1e8c4b3922 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -107,10 +107,19 @@ static void mlxsw_sp1_afk_encode_block(char *output, int block_index,
 	memcpy(output_indexed, block, MLXSW_SP1_AFK_KEY_BLOCK_SIZE);
 }
 
+static void mlxsw_sp1_afk_clear_block(char *output, int block_index)
+{
+	unsigned int offset = block_index * MLXSW_SP1_AFK_KEY_BLOCK_SIZE;
+	char *output_indexed = output + offset;
+
+	memset(output_indexed, 0, MLXSW_SP1_AFK_KEY_BLOCK_SIZE);
+}
+
 const struct mlxsw_afk_ops mlxsw_sp1_afk_ops = {
 	.blocks		= mlxsw_sp1_afk_blocks,
 	.blocks_count	= ARRAY_SIZE(mlxsw_sp1_afk_blocks),
 	.encode_block	= mlxsw_sp1_afk_encode_block,
+	.clear_block	= mlxsw_sp1_afk_clear_block,
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_0[] = {
@@ -263,10 +272,9 @@ static const struct mlxsw_sp2_afk_block_layout mlxsw_sp2_afk_blocks_layout[] = {
 	MLXSW_SP2_AFK_BLOCK_LAYOUT(block11, 0x00, 12),
 };
 
-static void mlxsw_sp2_afk_encode_block(char *output, int block_index,
-				       char *block)
+static void __mlxsw_sp2_afk_block_value_set(char *output, int block_index,
+					    u64 block_value)
 {
-	u64 block_value = mlxsw_sp2_afk_block_value_get(block);
 	const struct mlxsw_sp2_afk_block_layout *block_layout;
 
 	if (WARN_ON(block_index < 0 ||
@@ -278,8 +286,22 @@ static void mlxsw_sp2_afk_encode_block(char *output, int block_index,
 			   &block_layout->item, 0, block_value);
 }
 
+static void mlxsw_sp2_afk_encode_block(char *output, int block_index,
+				       char *block)
+{
+	u64 block_value = mlxsw_sp2_afk_block_value_get(block);
+
+	__mlxsw_sp2_afk_block_value_set(output, block_index, block_value);
+}
+
+static void mlxsw_sp2_afk_clear_block(char *output, int block_index)
+{
+	__mlxsw_sp2_afk_block_value_set(output, block_index, 0);
+}
+
 const struct mlxsw_afk_ops mlxsw_sp2_afk_ops = {
 	.blocks		= mlxsw_sp2_afk_blocks,
 	.blocks_count	= ARRAY_SIZE(mlxsw_sp2_afk_blocks),
 	.encode_block	= mlxsw_sp2_afk_encode_block,
+	.clear_block	= mlxsw_sp2_afk_clear_block,
 };
-- 
cgit v1.2.3


From 59600844cf4ef6acf65166ef6e47e89f7a79717c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 14 Nov 2018 08:22:33 +0000
Subject: mlxsw: spectrum: acl: Remove mlxsw_afk_encode() block range args and
 key/mask check

Since two remaining users of mlxsw_afk_encode() do not specify
block ranges to work on, remove the args. Also, key/mask is always
non-NULL now, so skip the checks.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c | 12 ++++++------
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c |  4 +---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c |  5 +----
 4 files changed, 9 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index 0900ccfdf315..df78d23b3ec3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -426,15 +426,17 @@ mlxsw_sp_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
 void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
-		      char *key, char *mask, int block_start, int block_end)
+		      char *key, char *mask)
 {
+	unsigned int blocks_count =
+			mlxsw_afk_key_info_blocks_count_get(key_info);
 	char block_mask[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE];
 	char block_key[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE];
 	const struct mlxsw_afk_element_inst *elinst;
 	enum mlxsw_afk_element element;
 	int block_index, i;
 
-	for (i = block_start; i <= block_end; i++) {
+	for (i = 0; i < blocks_count; i++) {
 		memset(block_key, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE);
 		memset(block_mask, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE);
 
@@ -451,10 +453,8 @@ void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 						values->storage.mask);
 		}
 
-		if (key)
-			mlxsw_afk->ops->encode_block(key, i, block_key);
-		if (mask)
-			mlxsw_afk->ops->encode_block(mask, i, block_mask);
+		mlxsw_afk->ops->encode_block(key, i, block_key);
+		mlxsw_afk->ops->encode_block(mask, i, block_mask);
 	}
 }
 EXPORT_SYMBOL(mlxsw_afk_encode);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index a5303c0b53b4..bcd264135af7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -229,7 +229,7 @@ void mlxsw_afk_values_add_buf(struct mlxsw_afk_element_values *values,
 void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
-		      char *key, char *mask, int block_start, int block_end);
+		      char *key, char *mask);
 void mlxsw_afk_clear(struct mlxsw_afk *mlxsw_afk, char *key,
 		     int block_start, int block_end);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index ffdf464660be..12798ce33a60 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -439,12 +439,10 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN] = { 0 };
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	struct mlxsw_sp_acl_erp_mask *erp_mask;
-	unsigned int blocks_count;
 	int err;
 
-	blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info);
 	mlxsw_afk_encode(afk, region->key_info, &rulei->values,
-			 aentry->ht_key.enc_key, mask, 0, blocks_count - 1);
+			 aentry->ht_key.enc_key, mask);
 
 	erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, false);
 	if (IS_ERR(erp_mask))
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index e3c6fe8b1d40..f3e834bfea1a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -46,7 +46,6 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_tcam_region *region = cregion->region;
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
-	unsigned int blocks_count;
 	char *act_set;
 	u32 priority;
 	char *mask;
@@ -63,9 +62,7 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 			     centry->parman_item.index, priority);
 	key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
 	mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
-	blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info);
-	mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask, 0,
-			 blocks_count - 1);
+	mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask);
 
 	err = cregion->ops->entry_insert(cregion, centry, mask);
 	if (err)
-- 
cgit v1.2.3


From c293ba3403566c771fd80fc10800a200ef8539e8 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 14 Nov 2018 08:22:34 +0000
Subject: mlxsw: spectrum: acl: Push code related to num_ctcam_erps inc/dec
 into separate helpers

Later on the same code is going to be needed for deltas as well. So push
the procedures related to increment and decrement of num_ctcam_erps
into a separate helpers.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 108 +++++++++++----------
 1 file changed, 59 insertions(+), 49 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 818e03cf9add..bfd0c8a6cabf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -623,9 +623,50 @@ mlxsw_sp_acl_erp_region_ctcam_disable(struct mlxsw_sp_acl_erp_table *erp_table)
 	mlxsw_sp_acl_erp_table_enable(erp_table, false);
 }
 
+static int
+__mlxsw_sp_acl_erp_table_other_inc(struct mlxsw_sp_acl_erp_table *erp_table,
+				   unsigned int *inc_num)
+{
+	int err;
+
+	/* If there are C-TCAM eRPs in use we need to transition
+	 * the region to use eRP table, if it is not already done
+	 */
+	if (erp_table->ops != &erp_two_masks_ops &&
+	    erp_table->ops != &erp_multiple_masks_ops) {
+		err = mlxsw_sp_acl_erp_region_table_trans(erp_table);
+		if (err)
+			return err;
+	}
+
+	/* When C-TCAM is used, the eRP table must be used */
+	if (erp_table->ops != &erp_multiple_masks_ops)
+		erp_table->ops = &erp_multiple_masks_ops;
+
+	(*inc_num)++;
+
+	return 0;
+}
+
+static int mlxsw_sp_acl_erp_ctcam_inc(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	return __mlxsw_sp_acl_erp_table_other_inc(erp_table,
+						  &erp_table->num_ctcam_erps);
+}
+
 static void
-mlxsw_sp_acl_erp_ctcam_table_ops_set(struct mlxsw_sp_acl_erp_table *erp_table)
+__mlxsw_sp_acl_erp_table_other_dec(struct mlxsw_sp_acl_erp_table *erp_table,
+				   unsigned int *dec_num)
 {
+	(*dec_num)--;
+
+	/* If there are no C-TCAM eRPs in use, the state we
+	 * transition to depends on the number of A-TCAM eRPs currently
+	 * in use.
+	 */
+	if (erp_table->num_ctcam_erps > 0)
+		return;
+
 	switch (erp_table->num_atcam_erps) {
 	case 2:
 		/* Keep using the eRP table, but correctly set the
@@ -659,9 +700,15 @@ mlxsw_sp_acl_erp_ctcam_table_ops_set(struct mlxsw_sp_acl_erp_table *erp_table)
 	}
 }
 
+static void mlxsw_sp_acl_erp_ctcam_dec(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	__mlxsw_sp_acl_erp_table_other_dec(erp_table,
+					   &erp_table->num_ctcam_erps);
+}
+
 static struct mlxsw_sp_acl_erp *
-__mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
-				     struct mlxsw_sp_acl_erp_key *key)
+mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				   struct mlxsw_sp_acl_erp_key *key)
 {
 	struct mlxsw_sp_acl_erp *erp;
 	int err;
@@ -673,7 +720,11 @@ __mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	memcpy(&erp->key, key, sizeof(*key));
 	bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask,
 			  MLXSW_SP_ACL_TCAM_MASK_LEN);
-	erp_table->num_ctcam_erps++;
+
+	err = mlxsw_sp_acl_erp_ctcam_inc(erp_table);
+	if (err)
+		goto err_erp_ctcam_inc;
+
 	erp->erp_table = erp_table;
 
 	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, &erp->key);
@@ -684,50 +735,17 @@ __mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	if (err)
 		goto err_erp_region_ctcam_enable;
 
-	/* When C-TCAM is used, the eRP table must be used */
-	erp_table->ops = &erp_multiple_masks_ops;
-
 	return erp;
 
 err_erp_region_ctcam_enable:
 	mlxsw_sp_acl_erp_master_mask_clear(erp_table, &erp->key);
 err_master_mask_set:
-	erp_table->num_ctcam_erps--;
+	mlxsw_sp_acl_erp_ctcam_dec(erp_table);
+err_erp_ctcam_inc:
 	kfree(erp);
 	return ERR_PTR(err);
 }
 
-static struct mlxsw_sp_acl_erp *
-mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
-				   struct mlxsw_sp_acl_erp_key *key)
-{
-	struct mlxsw_sp_acl_erp *erp;
-	int err;
-
-	/* There is a special situation where we need to spill rules
-	 * into the C-TCAM, yet the region is still using a master
-	 * mask and thus not performing a lookup in the C-TCAM. This
-	 * can happen when two rules that only differ in priority - and
-	 * thus sharing the same key - are programmed. In this case
-	 * we transition the region to use an eRP table
-	 */
-	err = mlxsw_sp_acl_erp_region_table_trans(erp_table);
-	if (err)
-		return ERR_PTR(err);
-
-	erp = __mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
-	if (IS_ERR(erp)) {
-		err = PTR_ERR(erp);
-		goto err_erp_create;
-	}
-
-	return erp;
-
-err_erp_create:
-	mlxsw_sp_acl_erp_region_master_mask_trans(erp_table);
-	return ERR_PTR(err);
-}
-
 static void
 mlxsw_sp_acl_erp_ctcam_mask_destroy(struct mlxsw_sp_acl_erp *erp)
 {
@@ -735,16 +753,8 @@ mlxsw_sp_acl_erp_ctcam_mask_destroy(struct mlxsw_sp_acl_erp *erp)
 
 	mlxsw_sp_acl_erp_region_ctcam_disable(erp_table);
 	mlxsw_sp_acl_erp_master_mask_clear(erp_table, &erp->key);
-	erp_table->num_ctcam_erps--;
+	mlxsw_sp_acl_erp_ctcam_dec(erp_table);
 	kfree(erp);
-
-	/* Once the last C-TCAM eRP was destroyed, the state we
-	 * transition to depends on the number of A-TCAM eRPs currently
-	 * in use
-	 */
-	if (erp_table->num_ctcam_erps > 0)
-		return;
-	mlxsw_sp_acl_erp_ctcam_table_ops_set(erp_table);
 }
 
 static struct mlxsw_sp_acl_erp *
@@ -755,7 +765,7 @@ mlxsw_sp_acl_erp_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	int err;
 
 	if (key->ctcam)
-		return __mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
+		return mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
 
 	/* Expand the eRP table for the new eRP, if needed */
 	err = mlxsw_sp_acl_erp_table_expand(erp_table);
-- 
cgit v1.2.3


From c22291f7cf45f82a4cd1a82f780922cbbcf004b3 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 14 Nov 2018 08:22:35 +0000
Subject: mlxsw: spectrum: acl: Implement delta for ERP

Allow ERP sharing for multiple mask. Do it by properly implementing
delta_create() objagg object. Use the computed delta info for inserting
rules in A-TCAM.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h          |   8 +-
 .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c   |  27 ++-
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 193 ++++++++++++++++++++-
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |  21 ++-
 4 files changed, 237 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index db3d2790aeec..d3babcc49fd2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2834,8 +2834,9 @@ static inline void mlxsw_reg_ptce3_pack(char *payload, bool valid,
 					u32 priority,
 					const char *tcam_region_info,
 					const char *key, u8 erp_id,
-					bool large_exists, u32 lkey_id,
-					u32 action_pointer)
+					u16 delta_start, u8 delta_mask,
+					u8 delta_value, bool large_exists,
+					u32 lkey_id, u32 action_pointer)
 {
 	MLXSW_REG_ZERO(ptce3, payload);
 	mlxsw_reg_ptce3_v_set(payload, valid);
@@ -2844,6 +2845,9 @@ static inline void mlxsw_reg_ptce3_pack(char *payload, bool valid,
 	mlxsw_reg_ptce3_tcam_region_info_memcpy_to(payload, tcam_region_info);
 	mlxsw_reg_ptce3_flex2_key_blocks_memcpy_to(payload, key);
 	mlxsw_reg_ptce3_erp_id_set(payload, erp_id);
+	mlxsw_reg_ptce3_delta_start_set(payload, delta_start);
+	mlxsw_reg_ptce3_delta_mask_set(payload, delta_mask);
+	mlxsw_reg_ptce3_delta_value_set(payload, delta_value);
 	mlxsw_reg_ptce3_large_exists_set(payload, large_exists);
 	mlxsw_reg_ptce3_large_entry_key_id_set(payload, lkey_id);
 	mlxsw_reg_ptce3_action_pointer_set(payload, action_pointer);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index 12798ce33a60..e7bd8733e58e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -398,6 +398,9 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_WRITE,
 			     priority, region->tcam_region_info,
 			     aentry->ht_key.enc_key, erp_id,
+			     aentry->delta_info.start,
+			     aentry->delta_info.mask,
+			     aentry->delta_info.value,
 			     refcount_read(&lkey_id->refcnt) != 1, lkey_id->id,
 			     kvdl_index);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl);
@@ -419,11 +422,16 @@ mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id = aentry->lkey_id;
 	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
 	u8 erp_id = mlxsw_sp_acl_erp_mask_erp_id(aentry->erp_mask);
+	char *enc_key = aentry->ht_key.enc_key;
 	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
 
 	mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0,
-			     region->tcam_region_info, aentry->ht_key.enc_key,
-			     erp_id, refcount_read(&lkey_id->refcnt) != 1,
+			     region->tcam_region_info,
+			     enc_key, erp_id,
+			     aentry->delta_info.start,
+			     aentry->delta_info.mask,
+			     aentry->delta_info.value,
+			     refcount_read(&lkey_id->refcnt) != 1,
 			     lkey_id->id, 0);
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl);
 	aregion->ops->lkey_id_put(aregion, lkey_id);
@@ -438,17 +446,30 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
 	char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN] = { 0 };
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
+	const struct mlxsw_sp_acl_erp_delta *delta;
 	struct mlxsw_sp_acl_erp_mask *erp_mask;
 	int err;
 
 	mlxsw_afk_encode(afk, region->key_info, &rulei->values,
-			 aentry->ht_key.enc_key, mask);
+			 aentry->full_enc_key, mask);
 
 	erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, false);
 	if (IS_ERR(erp_mask))
 		return PTR_ERR(erp_mask);
 	aentry->erp_mask = erp_mask;
 	aentry->ht_key.erp_id = mlxsw_sp_acl_erp_mask_erp_id(erp_mask);
+	memcpy(aentry->ht_key.enc_key, aentry->full_enc_key,
+	       sizeof(aentry->ht_key.enc_key));
+
+	/* Compute all needed delta information and clear the delta bits
+	 * from the encrypted key.
+	 */
+	delta = mlxsw_sp_acl_erp_delta(aentry->erp_mask);
+	aentry->delta_info.start = mlxsw_sp_acl_erp_delta_start(delta);
+	aentry->delta_info.mask = mlxsw_sp_acl_erp_delta_mask(delta);
+	aentry->delta_info.value =
+		mlxsw_sp_acl_erp_delta_value(delta, aentry->full_enc_key);
+	mlxsw_sp_acl_erp_delta_clear(delta, aentry->ht_key.enc_key);
 
 	/* We can't insert identical rules into the A-TCAM, so fail and
 	 * let the rule spill into C-TCAM
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index bfd0c8a6cabf..d9a4b7e8434b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -29,6 +29,8 @@ struct mlxsw_sp_acl_erp_core {
 
 struct mlxsw_sp_acl_erp_key {
 	char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN];
+#define __MASK_LEN 0x38
+#define __MASK_IDX(i) (__MASK_LEN - (i) - 1)
 	bool ctcam;
 };
 
@@ -58,6 +60,7 @@ struct mlxsw_sp_acl_erp_table {
 	unsigned int num_atcam_erps;
 	unsigned int num_max_atcam_erps;
 	unsigned int num_ctcam_erps;
+	unsigned int num_deltas;
 	struct objagg *objagg;
 };
 
@@ -629,7 +632,7 @@ __mlxsw_sp_acl_erp_table_other_inc(struct mlxsw_sp_acl_erp_table *erp_table,
 {
 	int err;
 
-	/* If there are C-TCAM eRPs in use we need to transition
+	/* If there are C-TCAM eRP or deltas in use we need to transition
 	 * the region to use eRP table, if it is not already done
 	 */
 	if (erp_table->ops != &erp_two_masks_ops &&
@@ -639,7 +642,7 @@ __mlxsw_sp_acl_erp_table_other_inc(struct mlxsw_sp_acl_erp_table *erp_table,
 			return err;
 	}
 
-	/* When C-TCAM is used, the eRP table must be used */
+	/* When C-TCAM or deltas are used, the eRP table must be used */
 	if (erp_table->ops != &erp_multiple_masks_ops)
 		erp_table->ops = &erp_multiple_masks_ops;
 
@@ -654,17 +657,23 @@ static int mlxsw_sp_acl_erp_ctcam_inc(struct mlxsw_sp_acl_erp_table *erp_table)
 						  &erp_table->num_ctcam_erps);
 }
 
+static int mlxsw_sp_acl_erp_delta_inc(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	return __mlxsw_sp_acl_erp_table_other_inc(erp_table,
+						  &erp_table->num_deltas);
+}
+
 static void
 __mlxsw_sp_acl_erp_table_other_dec(struct mlxsw_sp_acl_erp_table *erp_table,
 				   unsigned int *dec_num)
 {
 	(*dec_num)--;
 
-	/* If there are no C-TCAM eRPs in use, the state we
+	/* If there are no C-TCAM eRP or deltas in use, the state we
 	 * transition to depends on the number of A-TCAM eRPs currently
 	 * in use.
 	 */
-	if (erp_table->num_ctcam_erps > 0)
+	if (erp_table->num_ctcam_erps > 0 || erp_table->num_deltas > 0)
 		return;
 
 	switch (erp_table->num_atcam_erps) {
@@ -706,6 +715,12 @@ static void mlxsw_sp_acl_erp_ctcam_dec(struct mlxsw_sp_acl_erp_table *erp_table)
 					   &erp_table->num_ctcam_erps);
 }
 
+static void mlxsw_sp_acl_erp_delta_dec(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	__mlxsw_sp_acl_erp_table_other_dec(erp_table,
+					   &erp_table->num_deltas);
+}
+
 static struct mlxsw_sp_acl_erp *
 mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 				   struct mlxsw_sp_acl_erp_key *key)
@@ -813,7 +828,8 @@ mlxsw_sp_acl_erp_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
 	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
 	mlxsw_sp_acl_erp_generic_destroy(erp);
 
-	if (erp_table->num_atcam_erps == 2 && erp_table->num_ctcam_erps == 0)
+	if (erp_table->num_atcam_erps == 2 && erp_table->num_ctcam_erps == 0 &&
+	    erp_table->num_deltas == 0)
 		erp_table->ops = &erp_two_masks_ops;
 }
 
@@ -961,14 +977,179 @@ u8 mlxsw_sp_acl_erp_mask_erp_id(const struct mlxsw_sp_acl_erp_mask *erp_mask)
 	return erp->id;
 }
 
+struct mlxsw_sp_acl_erp_delta {
+	struct mlxsw_sp_acl_erp_key key;
+	u16 start;
+	u8 mask;
+};
+
+u16 mlxsw_sp_acl_erp_delta_start(const struct mlxsw_sp_acl_erp_delta *delta)
+{
+	return delta->start;
+}
+
+u8 mlxsw_sp_acl_erp_delta_mask(const struct mlxsw_sp_acl_erp_delta *delta)
+{
+	return delta->mask;
+}
+
+u8 mlxsw_sp_acl_erp_delta_value(const struct mlxsw_sp_acl_erp_delta *delta,
+				const char *enc_key)
+{
+	u16 start = delta->start;
+	u8 mask = delta->mask;
+	u16 tmp;
+
+	if (!mask)
+		return 0;
+
+	tmp = (unsigned char) enc_key[__MASK_IDX(start / 8)];
+	if (start / 8 + 1 < __MASK_LEN)
+		tmp |= (unsigned char) enc_key[__MASK_IDX(start / 8 + 1)] << 8;
+	tmp >>= start % 8;
+	tmp &= mask;
+	return tmp;
+}
+
+void mlxsw_sp_acl_erp_delta_clear(const struct mlxsw_sp_acl_erp_delta *delta,
+				  const char *enc_key)
+{
+	u16 start = delta->start;
+	u8 mask = delta->mask;
+	unsigned char *byte;
+	u16 tmp;
+
+	tmp = mask;
+	tmp <<= start % 8;
+	tmp = ~tmp;
+
+	byte = (unsigned char *) &enc_key[__MASK_IDX(start / 8)];
+	*byte &= tmp & 0xff;
+	if (start / 8 + 1 < __MASK_LEN) {
+		byte = (unsigned char *) &enc_key[__MASK_IDX(start / 8 + 1)];
+		*byte &= (tmp >> 8) & 0xff;
+	}
+}
+
+static const struct mlxsw_sp_acl_erp_delta
+mlxsw_sp_acl_erp_delta_default = {};
+
+const struct mlxsw_sp_acl_erp_delta *
+mlxsw_sp_acl_erp_delta(const struct mlxsw_sp_acl_erp_mask *erp_mask)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	const struct mlxsw_sp_acl_erp_delta *delta;
+
+	delta = objagg_obj_delta_priv(objagg_obj);
+	if (!delta)
+		delta = &mlxsw_sp_acl_erp_delta_default;
+	return delta;
+}
+
+static int
+mlxsw_sp_acl_erp_delta_fill(const struct mlxsw_sp_acl_erp_key *parent_key,
+			    const struct mlxsw_sp_acl_erp_key *key,
+			    u16 *delta_start, u8 *delta_mask)
+{
+	int offset = 0;
+	int si = -1;
+	u16 pmask;
+	u16 mask;
+	int i;
+
+	/* The difference between 2 masks can be up to 8 consecutive bits. */
+	for (i = 0; i < __MASK_LEN; i++) {
+		if (parent_key->mask[__MASK_IDX(i)] == key->mask[__MASK_IDX(i)])
+			continue;
+		if (si == -1)
+			si = i;
+		else if (si != i - 1)
+			return -EINVAL;
+	}
+	if (si == -1) {
+		/* The masks are the same, this cannot happen.
+		 * That means the caller is broken.
+		 */
+		WARN_ON(1);
+		*delta_start = 0;
+		*delta_mask = 0;
+		return 0;
+	}
+	pmask = (unsigned char) parent_key->mask[__MASK_IDX(si)];
+	mask = (unsigned char) key->mask[__MASK_IDX(si)];
+	if (si + 1 < __MASK_LEN) {
+		pmask |= (unsigned char) parent_key->mask[__MASK_IDX(si + 1)] << 8;
+		mask |= (unsigned char) key->mask[__MASK_IDX(si + 1)] << 8;
+	}
+
+	if ((pmask ^ mask) & pmask)
+		return -EINVAL;
+	mask &= ~pmask;
+	while (!(mask & (1 << offset)))
+		offset++;
+	while (!(mask & 1))
+		mask >>= 1;
+	if (mask & 0xff00)
+		return -EINVAL;
+
+	*delta_start = si * 8 + offset;
+	*delta_mask = mask;
+
+	return 0;
+}
+
 static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj,
 					   void *obj)
 {
-	return ERR_PTR(-EOPNOTSUPP);
+	struct mlxsw_sp_acl_erp_key *parent_key = parent_obj;
+	struct mlxsw_sp_acl_atcam_region *aregion = priv;
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+	struct mlxsw_sp_acl_erp_key *key = obj;
+	struct mlxsw_sp_acl_erp_delta *delta;
+	u16 delta_start;
+	u8 delta_mask;
+	int err;
+
+	if (parent_key->ctcam || key->ctcam)
+		return ERR_PTR(-EINVAL);
+	err = mlxsw_sp_acl_erp_delta_fill(parent_key, key,
+					  &delta_start, &delta_mask);
+	if (err)
+		return ERR_PTR(-EINVAL);
+
+	delta = kzalloc(sizeof(*delta), GFP_KERNEL);
+	if (!delta)
+		return ERR_PTR(-ENOMEM);
+	delta->start = delta_start;
+	delta->mask = delta_mask;
+
+	err = mlxsw_sp_acl_erp_delta_inc(erp_table);
+	if (err)
+		goto err_erp_delta_inc;
+
+	memcpy(&delta->key, key, sizeof(*key));
+	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, &delta->key);
+	if (err)
+		goto err_master_mask_set;
+
+	return delta;
+
+err_master_mask_set:
+	mlxsw_sp_acl_erp_delta_dec(erp_table);
+err_erp_delta_inc:
+	kfree(delta);
+	return ERR_PTR(err);
 }
 
 static void mlxsw_sp_acl_erp_delta_destroy(void *priv, void *delta_priv)
 {
+	struct mlxsw_sp_acl_erp_delta *delta = delta_priv;
+	struct mlxsw_sp_acl_atcam_region *aregion = priv;
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, &delta->key);
+	mlxsw_sp_acl_erp_delta_dec(erp_table);
+	kfree(delta);
 }
 
 static void *mlxsw_sp_acl_erp_root_create(void *priv, void *obj)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 854436c5ea93..9a73759d901f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -154,7 +154,9 @@ struct mlxsw_sp_acl_atcam_region {
 };
 
 struct mlxsw_sp_acl_atcam_entry_ht_key {
-	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key */
+	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key,
+							    * minus delta bits.
+							    */
 	u8 erp_id;
 };
 
@@ -165,6 +167,12 @@ struct mlxsw_sp_acl_atcam_chunk {
 struct mlxsw_sp_acl_atcam_entry {
 	struct rhash_head ht_node;
 	struct mlxsw_sp_acl_atcam_entry_ht_key ht_key;
+	char full_enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key */
+	struct {
+		u16 start;
+		u8 mask;
+		u8 value;
+	} delta_info;
 	struct mlxsw_sp_acl_ctcam_entry centry;
 	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
 	struct mlxsw_sp_acl_erp_mask *erp_mask;
@@ -209,11 +217,22 @@ int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
 void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
 			     struct mlxsw_sp_acl_atcam *atcam);
 
+struct mlxsw_sp_acl_erp_delta;
+
+u16 mlxsw_sp_acl_erp_delta_start(const struct mlxsw_sp_acl_erp_delta *delta);
+u8 mlxsw_sp_acl_erp_delta_mask(const struct mlxsw_sp_acl_erp_delta *delta);
+u8 mlxsw_sp_acl_erp_delta_value(const struct mlxsw_sp_acl_erp_delta *delta,
+				const char *enc_key);
+void mlxsw_sp_acl_erp_delta_clear(const struct mlxsw_sp_acl_erp_delta *delta,
+				  const char *enc_key);
+
 struct mlxsw_sp_acl_erp_mask;
 
 bool
 mlxsw_sp_acl_erp_mask_is_ctcam(const struct mlxsw_sp_acl_erp_mask *erp_mask);
 u8 mlxsw_sp_acl_erp_mask_erp_id(const struct mlxsw_sp_acl_erp_mask *erp_mask);
+const struct mlxsw_sp_acl_erp_delta *
+mlxsw_sp_acl_erp_delta(const struct mlxsw_sp_acl_erp_mask *erp_mask);
 struct mlxsw_sp_acl_erp_mask *
 mlxsw_sp_acl_erp_mask_get(struct mlxsw_sp_acl_atcam_region *aregion,
 			  const char *mask, bool ctcam);
-- 
cgit v1.2.3


From 3b423271b89a78757ad49725e131472e4fe1a49c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 14 Nov 2018 08:22:36 +0000
Subject: selftests: mlxsw: spectrum-2: Add simple delta test

Track the basic codepaths of delta handling, using objagg tracepoints.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/spectrum-2/tc_flower.sh      | 82 +++++++++++++++++++++-
 1 file changed, 81 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index 84ef95320c96..00ae99fbc253 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -8,7 +8,7 @@
 lib_dir=$(dirname $0)/../../../../net/forwarding
 
 ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
-	multiple_masks_test ctcam_edge_cases_test"
+	multiple_masks_test ctcam_edge_cases_test delta_simple_test"
 NUM_NETIFS=2
 source $lib_dir/tc_common.sh
 source $lib_dir/lib.sh
@@ -324,6 +324,86 @@ ctcam_edge_cases_test()
 	ctcam_no_atcam_masks_test
 }
 
+tp_record()
+{
+	local tracepoint=$1
+	local cmd=$2
+
+	perf record -q -e $tracepoint $cmd
+	return $?
+}
+
+tp_check_hits()
+{
+	local tracepoint=$1
+	local count=$2
+
+	perf_output=`perf script -F trace:event,trace`
+	hits=`echo $perf_output | grep "$tracepoint:" | wc -l`
+	if [[ "$count" -ne "$hits" ]]; then
+		return 1
+	fi
+	return 0
+}
+
+delta_simple_test()
+{
+	# The first filter will create eRP, the second filter will fit into
+	# the first eRP with delta. Remove the first rule then and check that
+        # the eRP stays (referenced by the second filter).
+
+	RET=0
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	tp_record "objagg:*" "tc filter add dev $h2 ingress protocol ip \
+		   pref 1 handle 101 flower $tcflags dst_ip 192.0.0.0/24 \
+		   action drop"
+	tp_check_hits "objagg:objagg_obj_root_create" 1
+	check_err $? "eRP was not created"
+
+	tp_record "objagg:*" "tc filter add dev $h2 ingress protocol ip \
+		   pref 2 handle 102 flower $tcflags dst_ip 192.0.2.2 \
+		   action drop"
+	tp_check_hits "objagg:objagg_obj_root_create" 0
+	check_err $? "eRP was incorrectly created"
+	tp_check_hits "objagg:objagg_obj_parent_assign" 1
+	check_err $? "delta was not created"
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 101 1
+	check_fail $? "Matched a wrong filter"
+
+	tc_check_packets "dev $h2 ingress" 102 1
+	check_err $? "Did not match on correct filter"
+
+	tp_record "objagg:*" "tc filter del dev $h2 ingress protocol ip \
+		   pref 1 handle 101 flower"
+	tp_check_hits "objagg:objagg_obj_root_destroy" 0
+	check_err $? "eRP was incorrectly destroyed"
+	tp_check_hits "objagg:objagg_obj_parent_unassign" 0
+	check_err $? "delta was incorrectly destroyed"
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 102 2
+	check_err $? "Did not match on correct filter after the first was removed"
+
+	tp_record "objagg:*" "tc filter del dev $h2 ingress protocol ip \
+		   pref 2 handle 102 flower"
+	tp_check_hits "objagg:objagg_obj_parent_unassign" 1
+	check_err $? "delta was not destroyed"
+	tp_check_hits "objagg:objagg_obj_root_destroy" 1
+	check_err $? "eRP was not destroyed"
+
+	log_test "delta simple test ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
cgit v1.2.3


From 110e2b4b94c623b36d0345a604970db34935f158 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 15 Nov 2018 14:57:09 -0800
Subject: test_objagg: Fix warning.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

lib/test_objagg.c: In function ‘test_delta_action_item’:
./include/linux/printk.h:308:2: warning: ‘errmsg’ may be used uninitialized in this function [-Wmaybe-uninitialized]

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/test_objagg.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/test_objagg.c b/lib/test_objagg.c
index aac5d8e8800c..ab57144bb0cd 100644
--- a/lib/test_objagg.c
+++ b/lib/test_objagg.c
@@ -769,6 +769,7 @@ static int test_delta_action_item(struct world *world,
 	if (err)
 		goto errout;
 
+	errmsg = NULL;
 	err = check_expect_stats(objagg, &action_item->expect_stats, &errmsg);
 	if (err) {
 		pr_err("Key %u: Stats: %s\n", action_item->key_id, errmsg);
-- 
cgit v1.2.3


From 982c17b9e3c27389a8d214333c686dab0e95cf63 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Tue, 13 Nov 2018 09:16:52 +0800
Subject: net: remove BUG_ON from __pskb_pull_tail

if list is NULL pointer, and the following access of list
will trigger panic, which is same as BUG_ON

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index fcb1155a00ec..f95ab41c9fb9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1925,8 +1925,6 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
 		struct sk_buff *insp = NULL;
 
 		do {
-			BUG_ON(!list);
-
 			if (list->len <= eat) {
 				/* Eaten as whole. */
 				eat -= list->len;
-- 
cgit v1.2.3


From 45cf7959c30402d7c4ea43568a6f1bab0ba6ca63 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Tue, 13 Nov 2018 09:34:31 +0800
Subject: net: slightly optimize eth_type_trans

netperf udp stream shows that eth_type_trans takes certain cpu,
so adjust the mac address check order, and firstly check if it
is device address, and only check if it is multicast address
only if not the device address.

After this change:
To unicast, and skb dst mac is device mac, this is most of time
reduce a comparision
To unicast, and skb dst mac is not device mac, nothing change
To multicast, increase a comparision

Before:
1.03%  [kernel]          [k] eth_type_trans

After:
0.78%  [kernel]          [k] eth_type_trans

Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethernet/eth.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index fd8faa0dfa61..58933fa50bb5 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -165,15 +165,17 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
 	eth = (struct ethhdr *)skb->data;
 	skb_pull_inline(skb, ETH_HLEN);
 
-	if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) {
-		if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
-			skb->pkt_type = PACKET_BROADCAST;
-		else
-			skb->pkt_type = PACKET_MULTICAST;
+	if (unlikely(!ether_addr_equal_64bits(eth->h_dest,
+					      dev->dev_addr))) {
+		if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) {
+			if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
+				skb->pkt_type = PACKET_BROADCAST;
+			else
+				skb->pkt_type = PACKET_MULTICAST;
+		} else {
+			skb->pkt_type = PACKET_OTHERHOST;
+		}
 	}
-	else if (unlikely(!ether_addr_equal_64bits(eth->h_dest,
-						   dev->dev_addr)))
-		skb->pkt_type = PACKET_OTHERHOST;
 
 	/*
 	 * Some variants of DSA tagging don't have an ethertype field
-- 
cgit v1.2.3


From 5c86d2125b58949122e03f04ce940e6f5b8534ba Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Fri, 9 Nov 2018 10:18:16 -0800
Subject: selftests/bpf: Fix uninitialized duration warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Daniel Borkmann reports:

test_progs.c: In function ‘main’:
test_progs.c:81:3: warning: ‘duration’ may be used uninitialized in this function [-Wmaybe-uninitialized]
   printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\
   ^~~~~~
test_progs.c:1706:8: note: ‘duration’ was declared here
  __u32 duration;
        ^~~~~~~~

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_progs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 2d3c04f45530..c1e688f61061 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1703,7 +1703,7 @@ static void test_reference_tracking()
 	const char *file = "./test_sk_lookup_kern.o";
 	struct bpf_object *obj;
 	struct bpf_program *prog;
-	__u32 duration;
+	__u32 duration = 0;
 	int err = 0;
 
 	obj = bpf_object__open(file);
-- 
cgit v1.2.3


From a83d6e76a67424ebbbbed643f51e97934ffc2bc2 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 12 Nov 2018 15:44:53 -0800
Subject: bpf: libbpf: Fix bpf_program__next() API

This patch restores the behavior in
commit eac7d84519a3 ("tools: libbpf: don't return '.text' as a program for multi-function programs")
such that bpf_program__next() does not return pseudo programs in ".text".

Fixes: 0c19a9fbc9cd ("libbpf: cleanup after partial failure in bpf_object__pin")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e827542ffa3a..a01eb9584e52 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2193,19 +2193,25 @@ void *bpf_object__priv(struct bpf_object *obj)
 }
 
 static struct bpf_program *
-__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, int i)
+__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward)
 {
+	size_t nr_programs = obj->nr_programs;
 	ssize_t idx;
 
-	if (!obj->programs)
+	if (!nr_programs)
 		return NULL;
 
+	if (!p)
+		/* Iter from the beginning */
+		return forward ? &obj->programs[0] :
+			&obj->programs[nr_programs - 1];
+
 	if (p->obj != obj) {
 		pr_warning("error: program handler doesn't match object\n");
 		return NULL;
 	}
 
-	idx = (p - obj->programs) + i;
+	idx = (p - obj->programs) + (forward ? 1 : -1);
 	if (idx >= obj->nr_programs || idx < 0)
 		return NULL;
 	return &obj->programs[idx];
@@ -2216,11 +2222,8 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 {
 	struct bpf_program *prog = prev;
 
-	if (prev == NULL)
-		return obj->programs;
-
 	do {
-		prog = __bpf_program__iter(prog, obj, 1);
+		prog = __bpf_program__iter(prog, obj, true);
 	} while (prog && bpf_program__is_function_storage(prog, obj));
 
 	return prog;
@@ -2231,14 +2234,8 @@ bpf_program__prev(struct bpf_program *next, struct bpf_object *obj)
 {
 	struct bpf_program *prog = next;
 
-	if (next == NULL) {
-		if (!obj->nr_programs)
-			return NULL;
-		return obj->programs + obj->nr_programs - 1;
-	}
-
 	do {
-		prog = __bpf_program__iter(prog, obj, -1);
+		prog = __bpf_program__iter(prog, obj, false);
 	} while (prog && bpf_program__is_function_storage(prog, obj));
 
 	return prog;
-- 
cgit v1.2.3


From ac8acec9912a93be9953446766e0bb73aeeecc64 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Mon, 12 Nov 2018 15:10:42 -0700
Subject: bpf: Remove unused variable in nsim_bpf

Clang warns:

drivers/net/netdevsim/bpf.c:557:30: error: unused variable 'state'
[-Werror,-Wunused-variable]
        struct nsim_bpf_bound_prog *state;
                                    ^
1 error generated.

The declaration should have been removed in commit b07ade27e933 ("bpf:
pass translate() as a callback and remove its ndo_bpf subcommand").

Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/netdevsim/bpf.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 6a5b7bd9a1f9..a1b29173ca1c 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -554,7 +554,6 @@ static void nsim_bpf_map_free(struct bpf_offloaded_map *offmap)
 int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 {
 	struct netdevsim *ns = netdev_priv(dev);
-	struct nsim_bpf_bound_prog *state;
 	int err;
 
 	ASSERT_RTNL();
-- 
cgit v1.2.3


From cac6cc2f5ac710334ae0f6bba5630d791c253574 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Fri, 9 Nov 2018 10:54:00 -0800
Subject: bpf: Fix IPv6 dport byte order in bpf_sk_lookup_udp

Lookup functions in sk_lookup have different expectations about byte
order of provided arguments.

Specifically __inet_lookup, __udp4_lib_lookup and __udp6_lib_lookup
expect dport to be in network byte order and do ntohs(dport) internally.

At the same time __inet6_lookup expects dport to be in host byte order
and correspondingly name the argument hnum.

sk_lookup works correctly with __inet_lookup, __udp4_lib_lookup and
__inet6_lookup with regard to dport. But in __udp6_lib_lookup case it
uses host instead of expected network byte order. It makes result
returned by bpf_sk_lookup_udp for IPv6 incorrect.

The patch fixes byte order of dport passed to __udp6_lib_lookup.

Originally sk_lookup properly handled UDPv6, but not TCPv6. 5ef0ae84f02a
fixes TCPv6 but breaks UDPv6.

Fixes: 5ef0ae84f02a ("bpf: Fix IPv6 dport byte-order in bpf_sk_lookup")
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Joe Stringer <joe@wand.net.nz>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/core/filter.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 53d50fb75ea1..f4ae933edf61 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4867,17 +4867,16 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 	} else {
 		struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
 		struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
-		u16 hnum = ntohs(tuple->ipv6.dport);
 
 		if (proto == IPPROTO_TCP)
 			sk = __inet6_lookup(net, &tcp_hashinfo, NULL, 0,
 					    src6, tuple->ipv6.sport,
-					    dst6, hnum,
+					    dst6, ntohs(tuple->ipv6.dport),
 					    dif, sdif, &refcounted);
 		else if (likely(ipv6_bpf_stub))
 			sk = ipv6_bpf_stub->udp6_lib_lookup(net,
 							    src6, tuple->ipv6.sport,
-							    dst6, hnum,
+							    dst6, tuple->ipv6.dport,
 							    dif, sdif,
 							    &udp_table, NULL);
 #endif
-- 
cgit v1.2.3


From 6c49e65e0d462963b4fac97ebd87014342167027 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Fri, 9 Nov 2018 10:54:01 -0800
Subject: bpf: Support socket lookup in CGROUP_SOCK_ADDR progs

Make bpf_sk_lookup_tcp, bpf_sk_lookup_udp and bpf_sk_release helpers
available in programs of type BPF_PROG_TYPE_CGROUP_SOCK_ADDR.

Such programs operate on sockets and have access to socket and struct
sockaddr passed by user to system calls such as sys_bind, sys_connect,
sys_sendmsg.

It's useful to be able to lookup other sockets from these programs.
E.g. sys_connect may lookup IP:port endpoint and if there is a server
socket bound to that endpoint ("server" can be defined by saddr & sport
being zero), redirect client connection to it by rewriting IP:port in
sockaddr passed to sys_connect.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/core/filter.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index f4ae933edf61..f6ca38a7d433 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5042,6 +5042,43 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
 	.arg4_type      = ARG_ANYTHING,
 	.arg5_type      = ARG_ANYTHING,
 };
+
+BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0,
+			       IPPROTO_TCP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
+	.func		= bpf_sock_addr_sk_lookup_tcp,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0,
+			       IPPROTO_UDP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
+	.func		= bpf_sock_addr_sk_lookup_udp,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -5148,6 +5185,14 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_socket_cookie_sock_addr_proto;
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
+#ifdef CONFIG_INET
+	case BPF_FUNC_sk_lookup_tcp:
+		return &bpf_sock_addr_sk_lookup_tcp_proto;
+	case BPF_FUNC_sk_lookup_udp:
+		return &bpf_sock_addr_sk_lookup_udp_proto;
+	case BPF_FUNC_sk_release:
+		return &bpf_sk_release_proto;
+#endif /* CONFIG_INET */
 	default:
 		return bpf_base_func_proto(func_id);
 	}
-- 
cgit v1.2.3


From 9108e3a023d3e4e77d94b589b07d397b0a790285 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Fri, 9 Nov 2018 10:54:02 -0800
Subject: selftest/bpf: Use bpf_sk_lookup_{tcp, udp} in test_sock_addr

Use bpf_sk_lookup_tcp, bpf_sk_lookup_udp and bpf_sk_release helpers from
test_sock_addr programs to make sure they're available and can lookup
and release socket properly for IPv4/IPv4, TCP/UDP.

Reading from a few fields of returned struct bpf_sock is also tested.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/connect4_prog.c | 43 +++++++++++++++++-----
 tools/testing/selftests/bpf/connect6_prog.c | 56 ++++++++++++++++++++++-------
 2 files changed, 78 insertions(+), 21 deletions(-)

diff --git a/tools/testing/selftests/bpf/connect4_prog.c b/tools/testing/selftests/bpf/connect4_prog.c
index 5a88a681d2ab..b8395f3c43e9 100644
--- a/tools/testing/selftests/bpf/connect4_prog.c
+++ b/tools/testing/selftests/bpf/connect4_prog.c
@@ -21,23 +21,48 @@ int _version SEC("version") = 1;
 SEC("cgroup/connect4")
 int connect_v4_prog(struct bpf_sock_addr *ctx)
 {
+	struct bpf_sock_tuple tuple = {};
 	struct sockaddr_in sa;
+	struct bpf_sock *sk;
+
+	/* Verify that new destination is available. */
+	memset(&tuple.ipv4.saddr, 0, sizeof(tuple.ipv4.saddr));
+	memset(&tuple.ipv4.sport, 0, sizeof(tuple.ipv4.sport));
+
+	tuple.ipv4.daddr = bpf_htonl(DST_REWRITE_IP4);
+	tuple.ipv4.dport = bpf_htons(DST_REWRITE_PORT4);
+
+	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
+		return 0;
+	else if (ctx->type == SOCK_STREAM)
+		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv4), 0, 0);
+	else
+		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv4), 0, 0);
+
+	if (!sk)
+		return 0;
+
+	if (sk->src_ip4 != tuple.ipv4.daddr ||
+	    sk->src_port != DST_REWRITE_PORT4) {
+		bpf_sk_release(sk);
+		return 0;
+	}
+
+	bpf_sk_release(sk);
 
 	/* Rewrite destination. */
 	ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
 	ctx->user_port = bpf_htons(DST_REWRITE_PORT4);
 
-	if (ctx->type == SOCK_DGRAM || ctx->type == SOCK_STREAM) {
-		///* Rewrite source. */
-		memset(&sa, 0, sizeof(sa));
+	/* Rewrite source. */
+	memset(&sa, 0, sizeof(sa));
 
-		sa.sin_family = AF_INET;
-		sa.sin_port = bpf_htons(0);
-		sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
+	sa.sin_family = AF_INET;
+	sa.sin_port = bpf_htons(0);
+	sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
 
-		if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
-			return 0;
-	}
+	if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+		return 0;
 
 	return 1;
 }
diff --git a/tools/testing/selftests/bpf/connect6_prog.c b/tools/testing/selftests/bpf/connect6_prog.c
index 8ea3f7d12dee..25f5dc7b7aa0 100644
--- a/tools/testing/selftests/bpf/connect6_prog.c
+++ b/tools/testing/selftests/bpf/connect6_prog.c
@@ -29,7 +29,41 @@ int _version SEC("version") = 1;
 SEC("cgroup/connect6")
 int connect_v6_prog(struct bpf_sock_addr *ctx)
 {
+	struct bpf_sock_tuple tuple = {};
 	struct sockaddr_in6 sa;
+	struct bpf_sock *sk;
+
+	/* Verify that new destination is available. */
+	memset(&tuple.ipv6.saddr, 0, sizeof(tuple.ipv6.saddr));
+	memset(&tuple.ipv6.sport, 0, sizeof(tuple.ipv6.sport));
+
+	tuple.ipv6.daddr[0] = bpf_htonl(DST_REWRITE_IP6_0);
+	tuple.ipv6.daddr[1] = bpf_htonl(DST_REWRITE_IP6_1);
+	tuple.ipv6.daddr[2] = bpf_htonl(DST_REWRITE_IP6_2);
+	tuple.ipv6.daddr[3] = bpf_htonl(DST_REWRITE_IP6_3);
+
+	tuple.ipv6.dport = bpf_htons(DST_REWRITE_PORT6);
+
+	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
+		return 0;
+	else if (ctx->type == SOCK_STREAM)
+		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv6), 0, 0);
+	else
+		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv6), 0, 0);
+
+	if (!sk)
+		return 0;
+
+	if (sk->src_ip6[0] != tuple.ipv6.daddr[0] ||
+	    sk->src_ip6[1] != tuple.ipv6.daddr[1] ||
+	    sk->src_ip6[2] != tuple.ipv6.daddr[2] ||
+	    sk->src_ip6[3] != tuple.ipv6.daddr[3] ||
+	    sk->src_port != DST_REWRITE_PORT6) {
+		bpf_sk_release(sk);
+		return 0;
+	}
+
+	bpf_sk_release(sk);
 
 	/* Rewrite destination. */
 	ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0);
@@ -39,21 +73,19 @@ int connect_v6_prog(struct bpf_sock_addr *ctx)
 
 	ctx->user_port = bpf_htons(DST_REWRITE_PORT6);
 
-	if (ctx->type == SOCK_DGRAM || ctx->type == SOCK_STREAM) {
-		/* Rewrite source. */
-		memset(&sa, 0, sizeof(sa));
+	/* Rewrite source. */
+	memset(&sa, 0, sizeof(sa));
 
-		sa.sin6_family = AF_INET6;
-		sa.sin6_port = bpf_htons(0);
+	sa.sin6_family = AF_INET6;
+	sa.sin6_port = bpf_htons(0);
 
-		sa.sin6_addr.s6_addr32[0] = bpf_htonl(SRC_REWRITE_IP6_0);
-		sa.sin6_addr.s6_addr32[1] = bpf_htonl(SRC_REWRITE_IP6_1);
-		sa.sin6_addr.s6_addr32[2] = bpf_htonl(SRC_REWRITE_IP6_2);
-		sa.sin6_addr.s6_addr32[3] = bpf_htonl(SRC_REWRITE_IP6_3);
+	sa.sin6_addr.s6_addr32[0] = bpf_htonl(SRC_REWRITE_IP6_0);
+	sa.sin6_addr.s6_addr32[1] = bpf_htonl(SRC_REWRITE_IP6_1);
+	sa.sin6_addr.s6_addr32[2] = bpf_htonl(SRC_REWRITE_IP6_2);
+	sa.sin6_addr.s6_addr32[3] = bpf_htonl(SRC_REWRITE_IP6_3);
 
-		if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
-			return 0;
-	}
+	if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+		return 0;
 
 	return 1;
 }
-- 
cgit v1.2.3


From 5109f9fd6a76116090b34a192d4a957d2ad0621e Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Sat, 10 Nov 2018 19:58:34 +0100
Subject: net/skbuff: add macros for VLAN_PRESENT bit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Wrap VLAN_PRESENT bit using macro like PKT_TYPE_* and CLONED_*,
as used by BPF code.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7dcfb5591dc3..99f38779332c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -816,6 +816,12 @@ struct sk_buff {
 	__u32			priority;
 	int			skb_iif;
 	__u32			hash;
+#define PKT_VLAN_PRESENT_BIT	4	// CFI (12-th bit) in TCI
+#ifdef __BIG_ENDIAN
+#define PKT_VLAN_PRESENT_OFFSET()	offsetof(struct sk_buff, vlan_tci)
+#else
+#define PKT_VLAN_PRESENT_OFFSET()	(offsetof(struct sk_buff, vlan_tci) + 1)
+#endif
 	__be16			vlan_proto;
 	__u16			vlan_tci;
 #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS)
-- 
cgit v1.2.3


From 9c2122559709fe35f493634bc61065b8c0ecb2ad Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Sat, 10 Nov 2018 19:58:35 +0100
Subject: net/bpf: split VLAN_PRESENT bit handling from VLAN_TCI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 40 +++++++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 19 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index e521c5ebc7d1..c151b906df53 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -296,22 +296,21 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
 		break;
 
 	case SKF_AD_VLAN_TAG:
-	case SKF_AD_VLAN_TAG_PRESENT:
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
-		BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
 
 		/* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */
 		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
 				      offsetof(struct sk_buff, vlan_tci));
-		if (skb_field == SKF_AD_VLAN_TAG) {
-			*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg,
-						~VLAN_TAG_PRESENT);
-		} else {
-			/* dst_reg >>= 12 */
-			*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 12);
-			/* dst_reg &= 1 */
+#ifdef VLAN_TAG_PRESENT
+		*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, ~VLAN_TAG_PRESENT);
+#endif
+		break;
+	case SKF_AD_VLAN_TAG_PRESENT:
+		*insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_VLAN_PRESENT_OFFSET());
+		if (PKT_VLAN_PRESENT_BIT)
+			*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, PKT_VLAN_PRESENT_BIT);
+		if (PKT_VLAN_PRESENT_BIT < 7)
 			*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1);
-		}
 		break;
 	}
 
@@ -6140,19 +6139,22 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 		break;
 
 	case offsetof(struct __sk_buff, vlan_present):
-	case offsetof(struct __sk_buff, vlan_tci):
-		BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+		*target_size = 1;
+		*insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg,
+				      PKT_VLAN_PRESENT_OFFSET());
+		if (PKT_VLAN_PRESENT_BIT)
+			*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, PKT_VLAN_PRESENT_BIT);
+		if (PKT_VLAN_PRESENT_BIT < 7)
+			*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, 1);
+		break;
 
+	case offsetof(struct __sk_buff, vlan_tci):
 		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
 				      bpf_target_off(struct sk_buff, vlan_tci, 2,
 						     target_size));
-		if (si->off == offsetof(struct __sk_buff, vlan_tci)) {
-			*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg,
-						~VLAN_TAG_PRESENT);
-		} else {
-			*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, 12);
-			*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, 1);
-		}
+#ifdef VLAN_TAG_PRESENT
+		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, ~VLAN_TAG_PRESENT);
+#endif
 		break;
 
 	case offsetof(struct __sk_buff, cb[0]) ...
-- 
cgit v1.2.3


From 4ef3a142d8db8b2136435061cbeb2c11fe31df24 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Sat, 10 Nov 2018 19:58:35 +0100
Subject: net/bpf_jit: PPC: split VLAN_PRESENT bit handling from VLAN_TCI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/powerpc/net/bpf_jit_comp.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index d5bfe24bb3b5..dc4a2f54e829 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -379,18 +379,20 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 							  hash));
 			break;
 		case BPF_ANC | SKF_AD_VLAN_TAG:
-		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
-			BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
 
 			PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  vlan_tci));
-			if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) {
-				PPC_ANDI(r_A, r_A, ~VLAN_TAG_PRESENT);
-			} else {
-				PPC_ANDI(r_A, r_A, VLAN_TAG_PRESENT);
-				PPC_SRWI(r_A, r_A, 12);
-			}
+#ifdef VLAN_TAG_PRESENT
+			PPC_ANDI(r_A, r_A, ~VLAN_TAG_PRESENT);
+#endif
+			break;
+		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
+			PPC_LBZ_OFFS(r_A, r_skb, PKT_VLAN_PRESENT_OFFSET());
+			if (PKT_VLAN_PRESENT_BIT)
+				PPC_SRWI(r_A, r_A, PKT_VLAN_PRESENT_BIT);
+			if (PKT_VLAN_PRESENT_BIT < 7)
+				PPC_ANDI(r_A, r_A, 1);
 			break;
 		case BPF_ANC | SKF_AD_QUEUE:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
-- 
cgit v1.2.3


From 3955dec5376b9fc29f76273b7b92921ecefca99f Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Sat, 10 Nov 2018 19:58:35 +0100
Subject: net/bpf_jit: MIPS: split VLAN_PRESENT bit handling from VLAN_TCI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/mips/net/bpf_jit.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 4d8cb9bb8365..de4c6372ad9a 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -1159,19 +1159,22 @@ jmp_cmp:
 			emit_load(r_A, r_skb, off, ctx);
 			break;
 		case BPF_ANC | SKF_AD_VLAN_TAG:
-		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 			ctx->flags |= SEEN_SKB | SEEN_A;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
 						  vlan_tci) != 2);
 			off = offsetof(struct sk_buff, vlan_tci);
-			emit_half_load_unsigned(r_s0, r_skb, off, ctx);
-			if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) {
-				emit_andi(r_A, r_s0, (u16)~VLAN_TAG_PRESENT, ctx);
-			} else {
-				emit_andi(r_A, r_s0, VLAN_TAG_PRESENT, ctx);
-				/* return 1 if present */
-				emit_sltu(r_A, r_zero, r_A, ctx);
-			}
+			emit_half_load_unsigned(r_A, r_skb, off, ctx);
+#ifdef VLAN_TAG_PRESENT
+			emit_andi(r_A, r_A, (u16)~VLAN_TAG_PRESENT, ctx);
+#endif
+			break;
+		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			emit_load_byte(r_A, r_skb, PKT_VLAN_PRESENT_OFFSET(), ctx);
+			if (PKT_VLAN_PRESENT_BIT)
+				emit_srl(r_A, r_A, PKT_VLAN_PRESENT_BIT, ctx);
+			if (PKT_VLAN_PRESENT_BIT < 7)
+				emit_andi(r_A, r_A, 1, ctx);
 			break;
 		case BPF_ANC | SKF_AD_PKTTYPE:
 			ctx->flags |= SEEN_SKB;
-- 
cgit v1.2.3


From 4b50d23179737e4b5f5f16e4bb58bedcf437addc Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Sat, 10 Nov 2018 19:58:36 +0100
Subject: net/bpf_jit: SPARC: split VLAN_PRESENT bit handling from VLAN_TCI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/net/bpf_jit_comp_32.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c
index a5ff88643d5c..48f3c04dd179 100644
--- a/arch/sparc/net/bpf_jit_comp_32.c
+++ b/arch/sparc/net/bpf_jit_comp_32.c
@@ -552,15 +552,18 @@ void bpf_jit_compile(struct bpf_prog *fp)
 				emit_skb_load32(hash, r_A);
 				break;
 			case BPF_ANC | SKF_AD_VLAN_TAG:
-			case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 				emit_skb_load16(vlan_tci, r_A);
-				if (code != (BPF_ANC | SKF_AD_VLAN_TAG)) {
-					emit_alu_K(SRL, 12);
+#ifdef VLAN_TAG_PRESENT
+				emit_loadimm(~VLAN_TAG_PRESENT, r_TMP);
+				emit_and(r_A, r_TMP, r_A);
+#endif
+				break;
+			case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
+				__emit_skb_load8(__pkt_vlan_present_offset, r_A);
+				if (PKT_VLAN_PRESENT_BIT)
+					emit_alu_K(SRL, PKT_VLAN_PRESENT_BIT);
+				if (PKT_VLAN_PRESENT_BIT < 7)
 					emit_andi(r_A, 1, r_A);
-				} else {
-					emit_loadimm(~VLAN_TAG_PRESENT, r_TMP);
-					emit_and(r_A, r_TMP, r_A);
-				}
 				break;
 			case BPF_LD | BPF_W | BPF_LEN:
 				emit_skb_load32(len, r_A);
-- 
cgit v1.2.3


From 0c4b2d370514cb4f3454dd3b18f031d2651fab73 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Sat, 10 Nov 2018 19:58:36 +0100
Subject: net: remove VLAN_TAG_PRESENT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace VLAN_TAG_PRESENT with single bit flag and free up
VLAN.CFI overload. Now VLAN.CFI is visible in networking stack
and can be passed around intact.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/mips/net/bpf_jit.c          |  3 ---
 arch/powerpc/net/bpf_jit_comp.c  |  3 ---
 arch/sparc/net/bpf_jit_comp_32.c |  4 ----
 include/linux/if_vlan.h          | 11 ++++++-----
 include/linux/skbuff.h           | 16 +++++++++-------
 lib/test_bpf.c                   | 14 ++++++++------
 net/core/filter.c                |  6 ------
 7 files changed, 23 insertions(+), 34 deletions(-)

diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index de4c6372ad9a..3a0e34f4e615 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -1164,9 +1164,6 @@ jmp_cmp:
 						  vlan_tci) != 2);
 			off = offsetof(struct sk_buff, vlan_tci);
 			emit_half_load_unsigned(r_A, r_skb, off, ctx);
-#ifdef VLAN_TAG_PRESENT
-			emit_andi(r_A, r_A, (u16)~VLAN_TAG_PRESENT, ctx);
-#endif
 			break;
 		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 			ctx->flags |= SEEN_SKB | SEEN_A;
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index dc4a2f54e829..91d223cf512b 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -383,9 +383,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 
 			PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  vlan_tci));
-#ifdef VLAN_TAG_PRESENT
-			PPC_ANDI(r_A, r_A, ~VLAN_TAG_PRESENT);
-#endif
 			break;
 		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 			PPC_LBZ_OFFS(r_A, r_skb, PKT_VLAN_PRESENT_OFFSET());
diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c
index 48f3c04dd179..84cc8f7f83e9 100644
--- a/arch/sparc/net/bpf_jit_comp_32.c
+++ b/arch/sparc/net/bpf_jit_comp_32.c
@@ -553,10 +553,6 @@ void bpf_jit_compile(struct bpf_prog *fp)
 				break;
 			case BPF_ANC | SKF_AD_VLAN_TAG:
 				emit_skb_load16(vlan_tci, r_A);
-#ifdef VLAN_TAG_PRESENT
-				emit_loadimm(~VLAN_TAG_PRESENT, r_TMP);
-				emit_and(r_A, r_TMP, r_A);
-#endif
 				break;
 			case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 				__emit_skb_load8(__pkt_vlan_present_offset, r_A);
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 1be5230921b5..7a541eadf78e 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -66,7 +66,6 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb)
 #define VLAN_PRIO_MASK		0xe000 /* Priority Code Point */
 #define VLAN_PRIO_SHIFT		13
 #define VLAN_CFI_MASK		0x1000 /* Canonical Format Indicator */
-#define VLAN_TAG_PRESENT	VLAN_CFI_MASK
 #define VLAN_VID_MASK		0x0fff /* VLAN Identifier */
 #define VLAN_N_VID		4096
 
@@ -78,8 +77,8 @@ static inline bool is_vlan_dev(const struct net_device *dev)
         return dev->priv_flags & IFF_802_1Q_VLAN;
 }
 
-#define skb_vlan_tag_present(__skb)	((__skb)->vlan_tci & VLAN_TAG_PRESENT)
-#define skb_vlan_tag_get(__skb)		((__skb)->vlan_tci & ~VLAN_TAG_PRESENT)
+#define skb_vlan_tag_present(__skb)	((__skb)->vlan_present)
+#define skb_vlan_tag_get(__skb)		((__skb)->vlan_tci)
 #define skb_vlan_tag_get_id(__skb)	((__skb)->vlan_tci & VLAN_VID_MASK)
 #define skb_vlan_tag_get_prio(__skb)	(((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT)
 
@@ -480,7 +479,7 @@ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb,
  */
 static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb)
 {
-	skb->vlan_tci = 0;
+	skb->vlan_present = 0;
 }
 
 /**
@@ -492,6 +491,7 @@ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb)
  */
 static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src)
 {
+	dst->vlan_present = src->vlan_present;
 	dst->vlan_proto = src->vlan_proto;
 	dst->vlan_tci = src->vlan_tci;
 }
@@ -526,7 +526,8 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb,
 					  __be16 vlan_proto, u16 vlan_tci)
 {
 	skb->vlan_proto = vlan_proto;
-	skb->vlan_tci = VLAN_TAG_PRESENT | vlan_tci;
+	skb->vlan_tci = vlan_tci;
+	skb->vlan_present = 1;
 }
 
 /**
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 99f38779332c..b9aa0d1b21cf 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -777,6 +777,14 @@ struct sk_buff {
 	__u8			encap_hdr_csum:1;
 	__u8			csum_valid:1;
 
+#ifdef __BIG_ENDIAN_BITFIELD
+#define PKT_VLAN_PRESENT_BIT	7
+#else
+#define PKT_VLAN_PRESENT_BIT	0
+#endif
+#define PKT_VLAN_PRESENT_OFFSET()	offsetof(struct sk_buff, __pkt_vlan_present_offset)
+	__u8			__pkt_vlan_present_offset[0];
+	__u8			vlan_present:1;
 	__u8			csum_complete_sw:1;
 	__u8			csum_level:2;
 	__u8			csum_not_inet:1;
@@ -784,8 +792,8 @@ struct sk_buff {
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	__u8			ndisc_nodetype:2;
 #endif
-	__u8			ipvs_property:1;
 
+	__u8			ipvs_property:1;
 	__u8			inner_protocol_type:1;
 	__u8			remcsum_offload:1;
 #ifdef CONFIG_NET_SWITCHDEV
@@ -816,12 +824,6 @@ struct sk_buff {
 	__u32			priority;
 	int			skb_iif;
 	__u32			hash;
-#define PKT_VLAN_PRESENT_BIT	4	// CFI (12-th bit) in TCI
-#ifdef __BIG_ENDIAN
-#define PKT_VLAN_PRESENT_OFFSET()	offsetof(struct sk_buff, vlan_tci)
-#else
-#define PKT_VLAN_PRESENT_OFFSET()	(offsetof(struct sk_buff, vlan_tci) + 1)
-#endif
 	__be16			vlan_proto;
 	__u16			vlan_tci;
 #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS)
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index aa22bcaec1dc..f3e570722a7e 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -39,6 +39,7 @@
 #define SKB_HASH	0x1234aaab
 #define SKB_QUEUE_MAP	123
 #define SKB_VLAN_TCI	0xffff
+#define SKB_VLAN_PRESENT	1
 #define SKB_DEV_IFINDEX	577
 #define SKB_DEV_TYPE	588
 
@@ -725,8 +726,8 @@ static struct bpf_test tests[] = {
 		CLASSIC,
 		{ },
 		{
-			{ 1, SKB_VLAN_TCI & ~VLAN_TAG_PRESENT },
-			{ 10, SKB_VLAN_TCI & ~VLAN_TAG_PRESENT }
+			{ 1, SKB_VLAN_TCI },
+			{ 10, SKB_VLAN_TCI }
 		},
 	},
 	{
@@ -739,8 +740,8 @@ static struct bpf_test tests[] = {
 		CLASSIC,
 		{ },
 		{
-			{ 1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) },
-			{ 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }
+			{ 1, SKB_VLAN_PRESENT },
+			{ 10, SKB_VLAN_PRESENT }
 		},
 	},
 	{
@@ -5289,8 +5290,8 @@ static struct bpf_test tests[] = {
 #endif
 		{ },
 		{
-			{  1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) },
-			{ 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }
+			{  1, SKB_VLAN_PRESENT },
+			{ 10, SKB_VLAN_PRESENT }
 		},
 		.fill_helper = bpf_fill_maxinsns6,
 		.expected_errcode = -ENOTSUPP,
@@ -6493,6 +6494,7 @@ static struct sk_buff *populate_skb(char *buf, int size)
 	skb->hash = SKB_HASH;
 	skb->queue_mapping = SKB_QUEUE_MAP;
 	skb->vlan_tci = SKB_VLAN_TCI;
+	skb->vlan_present = SKB_VLAN_PRESENT;
 	skb->vlan_proto = htons(ETH_P_IP);
 	dev_net_set(&dev, &init_net);
 	skb->dev = &dev;
diff --git a/net/core/filter.c b/net/core/filter.c
index c151b906df53..10acbc00ff6c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -301,9 +301,6 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
 		/* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */
 		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
 				      offsetof(struct sk_buff, vlan_tci));
-#ifdef VLAN_TAG_PRESENT
-		*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, ~VLAN_TAG_PRESENT);
-#endif
 		break;
 	case SKF_AD_VLAN_TAG_PRESENT:
 		*insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_VLAN_PRESENT_OFFSET());
@@ -6152,9 +6149,6 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
 				      bpf_target_off(struct sk_buff, vlan_tci, 2,
 						     target_size));
-#ifdef VLAN_TAG_PRESENT
-		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, ~VLAN_TAG_PRESENT);
-#endif
 		break;
 
 	case offsetof(struct __sk_buff, cb[0]) ...
-- 
cgit v1.2.3


From a21ff3c83b1a7e110bae208221ef817251ef564c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 12 Nov 2018 21:16:06 +0100
Subject: net: phy: check for implementation of both callbacks in
 phy_drv_supports_irq

Now that the icplus driver has been fixed all PHY drivers supporting
interrupts have both callbacks (config_intr and ack_interrupt)
implemented - as it should be. Therefore phy_drv_supports_irq()
can be changed now to check for both callbacks being implemented.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 55202a0ac476..e06613f2d431 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2122,7 +2122,7 @@ static void of_set_phy_eee_broken(struct phy_device *phydev)
 
 static bool phy_drv_supports_irq(struct phy_driver *phydrv)
 {
-	return phydrv->config_intr || phydrv->ack_interrupt;
+	return phydrv->config_intr && phydrv->ack_interrupt;
 }
 
 /**
-- 
cgit v1.2.3


From 7f600f14dfac4ba4aee6283a415cdad2925d7791 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 12 Nov 2018 18:05:24 -0800
Subject: net: remove unused skb_send_sock()

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  1 -
 net/core/skbuff.c      | 13 -------------
 2 files changed, 14 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b9aa0d1b21cf..a2e8297a5b00 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3335,7 +3335,6 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
 		    unsigned int flags);
 int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset,
 			 int len);
-int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len);
 void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
 unsigned int skb_zerocopy_headlen(const struct sk_buff *from);
 int skb_zerocopy(struct sk_buff *to, struct sk_buff *from,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f95ab41c9fb9..a1be7f19d998 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2364,19 +2364,6 @@ error:
 }
 EXPORT_SYMBOL_GPL(skb_send_sock_locked);
 
-/* Send skb data on a socket. */
-int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len)
-{
-	int ret = 0;
-
-	lock_sock(sk);
-	ret = skb_send_sock_locked(sk, skb, offset, len);
-	release_sock(sk);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(skb_send_sock);
-
 /**
  *	skb_store_bits - store bits from kernel buffer to skb
  *	@skb: destination buffer
-- 
cgit v1.2.3


From 790cd1a8f0022c8e9fe7d856b2866bb9088825f7 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 13 Nov 2018 11:50:57 +0000
Subject: net: hns3: fix spelling mistake "failded" -> "failed"

Trivial fix, the spelling of "failded" is incorrect in dev_err and
dev_warn messages. Fix this.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index eb6b6a5f744f..33885a7529fc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2462,7 +2462,7 @@ int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset)
 		ret = hclge_set_vf_rst(hdev, vport->vport_id, reset);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
-				"set vf(%d) rst failded %d!\n",
+				"set vf(%d) rst failed %d!\n",
 				vport->vport_id, ret);
 			return ret;
 		}
@@ -2477,7 +2477,7 @@ int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset)
 		ret = hclge_inform_reset_assert_to_vf(vport);
 		if (ret)
 			dev_warn(&hdev->pdev->dev,
-				 "inform reset to vf(%d) failded %d!\n",
+				 "inform reset to vf(%d) failed %d!\n",
 				 vport->vport_id, ret);
 	}
 
-- 
cgit v1.2.3


From 99310e732a75c40fc9843f52b306fc9943bcce9d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 13 Nov 2018 14:18:17 +0000
Subject: net/decnet: add missing indentation

There is a missing indentation before the declaration of port. Add
it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/decnet/af_decnet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 7d6ff983ba2c..7aab5d088c72 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -192,7 +192,7 @@ static int check_port(__le16 port)
 static unsigned short port_alloc(struct sock *sk)
 {
 	struct dn_scp *scp = DN_SK(sk);
-static unsigned short port = 0x2000;
+	static unsigned short port = 0x2000;
 	unsigned short i_port = port;
 
 	while(check_port(cpu_to_le16(++port)) != 0) {
-- 
cgit v1.2.3


From 32764c66faba8fff950346776eb46801b67c610f Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Tue, 13 Nov 2018 23:22:48 +0100
Subject: net: 8021q: move vlan offload registrations into vlan_core

Currently, the vlan packet offloads are registered only upon 8021q module
load. However, even without this module loaded, the offloads could be
utilized, for example by openvswitch datapath. As reported by Michael,
that causes 2x to 5x performance improvement, depending on a testcase.

So move the vlan offload registrations into vlan_core and make this
available even without 8021q module loaded.

Reported-by: Michael Shteinbok <michaelsh86@gmail.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Tested-by: Michael Shteinbok <michaelsh86@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan.c      | 96 -------------------------------------------------
 net/8021q/vlan_core.c | 99 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 99 insertions(+), 96 deletions(-)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 1b7a375c6616..aef1a977279c 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -648,93 +648,6 @@ out:
 	return err;
 }
 
-static struct sk_buff *vlan_gro_receive(struct list_head *head,
-					struct sk_buff *skb)
-{
-	const struct packet_offload *ptype;
-	unsigned int hlen, off_vlan;
-	struct sk_buff *pp = NULL;
-	struct vlan_hdr *vhdr;
-	struct sk_buff *p;
-	__be16 type;
-	int flush = 1;
-
-	off_vlan = skb_gro_offset(skb);
-	hlen = off_vlan + sizeof(*vhdr);
-	vhdr = skb_gro_header_fast(skb, off_vlan);
-	if (skb_gro_header_hard(skb, hlen)) {
-		vhdr = skb_gro_header_slow(skb, hlen, off_vlan);
-		if (unlikely(!vhdr))
-			goto out;
-	}
-
-	type = vhdr->h_vlan_encapsulated_proto;
-
-	rcu_read_lock();
-	ptype = gro_find_receive_by_type(type);
-	if (!ptype)
-		goto out_unlock;
-
-	flush = 0;
-
-	list_for_each_entry(p, head, list) {
-		struct vlan_hdr *vhdr2;
-
-		if (!NAPI_GRO_CB(p)->same_flow)
-			continue;
-
-		vhdr2 = (struct vlan_hdr *)(p->data + off_vlan);
-		if (compare_vlan_header(vhdr, vhdr2))
-			NAPI_GRO_CB(p)->same_flow = 0;
-	}
-
-	skb_gro_pull(skb, sizeof(*vhdr));
-	skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr));
-	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
-
-out_unlock:
-	rcu_read_unlock();
-out:
-	skb_gro_flush_final(skb, pp, flush);
-
-	return pp;
-}
-
-static int vlan_gro_complete(struct sk_buff *skb, int nhoff)
-{
-	struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + nhoff);
-	__be16 type = vhdr->h_vlan_encapsulated_proto;
-	struct packet_offload *ptype;
-	int err = -ENOENT;
-
-	rcu_read_lock();
-	ptype = gro_find_complete_by_type(type);
-	if (ptype)
-		err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(*vhdr));
-
-	rcu_read_unlock();
-	return err;
-}
-
-static struct packet_offload vlan_packet_offloads[] __read_mostly = {
-	{
-		.type = cpu_to_be16(ETH_P_8021Q),
-		.priority = 10,
-		.callbacks = {
-			.gro_receive = vlan_gro_receive,
-			.gro_complete = vlan_gro_complete,
-		},
-	},
-	{
-		.type = cpu_to_be16(ETH_P_8021AD),
-		.priority = 10,
-		.callbacks = {
-			.gro_receive = vlan_gro_receive,
-			.gro_complete = vlan_gro_complete,
-		},
-	},
-};
-
 static int __net_init vlan_init_net(struct net *net)
 {
 	struct vlan_net *vn = net_generic(net, vlan_net_id);
@@ -762,7 +675,6 @@ static struct pernet_operations vlan_net_ops = {
 static int __init vlan_proto_init(void)
 {
 	int err;
-	unsigned int i;
 
 	pr_info("%s v%s\n", vlan_fullname, vlan_version);
 
@@ -786,9 +698,6 @@ static int __init vlan_proto_init(void)
 	if (err < 0)
 		goto err5;
 
-	for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++)
-		dev_add_offload(&vlan_packet_offloads[i]);
-
 	vlan_ioctl_set(vlan_ioctl_handler);
 	return 0;
 
@@ -806,13 +715,8 @@ err0:
 
 static void __exit vlan_cleanup_module(void)
 {
-	unsigned int i;
-
 	vlan_ioctl_set(NULL);
 
-	for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++)
-		dev_remove_offload(&vlan_packet_offloads[i]);
-
 	vlan_netlink_fini();
 
 	unregister_netdevice_notifier(&vlan_notifier_block);
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 57425049faf2..a313165e7a67 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -453,3 +453,102 @@ bool vlan_uses_dev(const struct net_device *dev)
 	return vlan_info->grp.nr_vlan_devs ? true : false;
 }
 EXPORT_SYMBOL(vlan_uses_dev);
+
+static struct sk_buff *vlan_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
+{
+	const struct packet_offload *ptype;
+	unsigned int hlen, off_vlan;
+	struct sk_buff *pp = NULL;
+	struct vlan_hdr *vhdr;
+	struct sk_buff *p;
+	__be16 type;
+	int flush = 1;
+
+	off_vlan = skb_gro_offset(skb);
+	hlen = off_vlan + sizeof(*vhdr);
+	vhdr = skb_gro_header_fast(skb, off_vlan);
+	if (skb_gro_header_hard(skb, hlen)) {
+		vhdr = skb_gro_header_slow(skb, hlen, off_vlan);
+		if (unlikely(!vhdr))
+			goto out;
+	}
+
+	type = vhdr->h_vlan_encapsulated_proto;
+
+	rcu_read_lock();
+	ptype = gro_find_receive_by_type(type);
+	if (!ptype)
+		goto out_unlock;
+
+	flush = 0;
+
+	list_for_each_entry(p, head, list) {
+		struct vlan_hdr *vhdr2;
+
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		vhdr2 = (struct vlan_hdr *)(p->data + off_vlan);
+		if (compare_vlan_header(vhdr, vhdr2))
+			NAPI_GRO_CB(p)->same_flow = 0;
+	}
+
+	skb_gro_pull(skb, sizeof(*vhdr));
+	skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr));
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	skb_gro_flush_final(skb, pp, flush);
+
+	return pp;
+}
+
+static int vlan_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + nhoff);
+	__be16 type = vhdr->h_vlan_encapsulated_proto;
+	struct packet_offload *ptype;
+	int err = -ENOENT;
+
+	rcu_read_lock();
+	ptype = gro_find_complete_by_type(type);
+	if (ptype)
+		err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(*vhdr));
+
+	rcu_read_unlock();
+	return err;
+}
+
+static struct packet_offload vlan_packet_offloads[] __read_mostly = {
+	{
+		.type = cpu_to_be16(ETH_P_8021Q),
+		.priority = 10,
+		.callbacks = {
+			.gro_receive = vlan_gro_receive,
+			.gro_complete = vlan_gro_complete,
+		},
+	},
+	{
+		.type = cpu_to_be16(ETH_P_8021AD),
+		.priority = 10,
+		.callbacks = {
+			.gro_receive = vlan_gro_receive,
+			.gro_complete = vlan_gro_complete,
+		},
+	},
+};
+
+static int __init vlan_offload_init(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++)
+		dev_add_offload(&vlan_packet_offloads[i]);
+
+	return 0;
+}
+
+fs_initcall(vlan_offload_init);
-- 
cgit v1.2.3


From b0e4f37b0175e60a475a6b94c2b7f010860dc357 Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Wed, 14 Nov 2018 11:48:35 +0000
Subject: dpaa2-eth: Don't use multiple queues per channel

The DPNI object on which we build a network interface has a
certain number of {Rx, Tx, Tx confirmation} frame queues as
resources. The default hardware setup offers one queue of each
type, as well as one DPCON channel, for each core available
in the system.

There are however cases where the number of queues is greater
than the number of cores or channels. Until now, we configured
and used all the frame queues associated with a DPNI, even if it
meant assigning multiple queues of one type to the same channel.

Update the driver to only use a number of queues equal to the
number of channels, ensuring each channel will contain exactly
one Rx and one Tx confirmation queue.

>From the user viewpoint, this change is completely transparent.
Performance wise there is no impact in most scenarios. In case
the number of queues is larger than and not a multiple of the
number of channels, Rx hash distribution offers now better load
balancing between cores, which can have a positive impact on
overall system performance.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 2 +-
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index bdfb13b71998..7a4a315fc1aa 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1603,7 +1603,7 @@ static int setup_dpio(struct dpaa2_eth_priv *priv)
 		/* Stop if we already have enough channels to accommodate all
 		 * RX and TX conf queues
 		 */
-		if (priv->num_channels == dpaa2_eth_queue_count(priv))
+		if (priv->num_channels == priv->dpni_attrs.num_queues)
 			break;
 	}
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 452a8e9c4f0e..b7837cf01a5d 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -434,9 +434,10 @@ static inline unsigned int dpaa2_eth_rx_head_room(struct dpaa2_eth_priv *priv)
 	       DPAA2_ETH_RX_HWA_SIZE;
 }
 
+/* We have exactly one {Rx, Tx conf} queue per channel */
 static int dpaa2_eth_queue_count(struct dpaa2_eth_priv *priv)
 {
-	return priv->dpni_attrs.num_queues;
+	return priv->num_channels;
 }
 
 int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags);
-- 
cgit v1.2.3


From dbcdf7289870611a97cac996c2cc82b2ffbc044b Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Wed, 14 Nov 2018 11:48:35 +0000
Subject: dpaa2-eth: Update callback signature

Change the frame consume callback signature:
* the entire FQ structure is passed to the callback instead
of just the queue index
* the NAPI structure can be easily obtained from the channel
it is associated to, so we don't need to pass it explicitly

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 12 +++++-------
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h |  3 +--
 2 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 7a4a315fc1aa..be312876a704 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -203,8 +203,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			 struct dpaa2_eth_channel *ch,
 			 const struct dpaa2_fd *fd,
-			 struct napi_struct *napi,
-			 u16 queue_id)
+			 struct dpaa2_eth_fq *fq)
 {
 	dma_addr_t addr = dpaa2_fd_get_addr(fd);
 	u8 fd_format = dpaa2_fd_get_format(fd);
@@ -267,12 +266,12 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	}
 
 	skb->protocol = eth_type_trans(skb, priv->net_dev);
-	skb_record_rx_queue(skb, queue_id);
+	skb_record_rx_queue(skb, fq->flowid);
 
 	percpu_stats->rx_packets++;
 	percpu_stats->rx_bytes += dpaa2_fd_get_len(fd);
 
-	napi_gro_receive(napi, skb);
+	napi_gro_receive(&ch->napi, skb);
 
 	return;
 
@@ -312,7 +311,7 @@ static int consume_frames(struct dpaa2_eth_channel *ch,
 		fd = dpaa2_dq_fd(dq);
 		fq = (struct dpaa2_eth_fq *)(uintptr_t)dpaa2_dq_fqd_ctx(dq);
 
-		fq->consume(priv, ch, fd, &ch->napi, fq->flowid);
+		fq->consume(priv, ch, fd, fq);
 		cleaned++;
 	} while (!is_last);
 
@@ -661,8 +660,7 @@ err_alloc_headroom:
 static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv,
 			      struct dpaa2_eth_channel *ch __always_unused,
 			      const struct dpaa2_fd *fd,
-			      struct napi_struct *napi __always_unused,
-			      u16 queue_id __always_unused)
+			      struct dpaa2_eth_fq *fq __always_unused)
 {
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa2_eth_drv_stats *percpu_extras;
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index b7837cf01a5d..3af706a88491 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -277,8 +277,7 @@ struct dpaa2_eth_fq {
 	void (*consume)(struct dpaa2_eth_priv *priv,
 			struct dpaa2_eth_channel *ch,
 			const struct dpaa2_fd *fd,
-			struct napi_struct *napi,
-			u16 queue_id);
+			struct dpaa2_eth_fq *fq);
 	struct dpaa2_eth_fq_stats stats;
 };
 
-- 
cgit v1.2.3


From 569dac6a5a0da48b7dd3e9439fbb5d57bc8fe72d Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Wed, 14 Nov 2018 11:48:36 +0000
Subject: dpaa2-eth: bql support

Add support for byte queue limit.

On NAPI poll, we save the total number of Tx confirmed frames/bytes
and register them with bql at the end of the poll function.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 59 ++++++++++++++++++------
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h |  2 +
 2 files changed, 46 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index be312876a704..640967a4d50d 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -288,7 +288,7 @@ err_frame_format:
  * Observance of NAPI budget is not our concern, leaving that to the caller.
  */
 static int consume_frames(struct dpaa2_eth_channel *ch,
-			  enum dpaa2_eth_fq_type *type)
+			  struct dpaa2_eth_fq **src)
 {
 	struct dpaa2_eth_priv *priv = ch->priv;
 	struct dpaa2_eth_fq *fq = NULL;
@@ -322,10 +322,10 @@ static int consume_frames(struct dpaa2_eth_channel *ch,
 	ch->stats.frames += cleaned;
 
 	/* A dequeue operation only pulls frames from a single queue
-	 * into the store. Return the frame queue type as an out param.
+	 * into the store. Return the frame queue as an out param.
 	 */
-	if (type)
-		*type = fq->type;
+	if (src)
+		*src = fq;
 
 	return cleaned;
 }
@@ -570,8 +570,10 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa2_eth_drv_stats *percpu_extras;
 	struct dpaa2_eth_fq *fq;
+	struct netdev_queue *nq;
 	u16 queue_mapping;
 	unsigned int needed_headroom;
+	u32 fd_len;
 	int err, i;
 
 	percpu_stats = this_cpu_ptr(priv->percpu_stats);
@@ -643,8 +645,12 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 		/* Clean up everything, including freeing the skb */
 		free_tx_fd(priv, &fd);
 	} else {
+		fd_len = dpaa2_fd_get_len(&fd);
 		percpu_stats->tx_packets++;
-		percpu_stats->tx_bytes += dpaa2_fd_get_len(&fd);
+		percpu_stats->tx_bytes += fd_len;
+
+		nq = netdev_get_tx_queue(net_dev, queue_mapping);
+		netdev_tx_sent_queue(nq, fd_len);
 	}
 
 	return NETDEV_TX_OK;
@@ -660,10 +666,11 @@ err_alloc_headroom:
 static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv,
 			      struct dpaa2_eth_channel *ch __always_unused,
 			      const struct dpaa2_fd *fd,
-			      struct dpaa2_eth_fq *fq __always_unused)
+			      struct dpaa2_eth_fq *fq)
 {
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa2_eth_drv_stats *percpu_extras;
+	u32 fd_len = dpaa2_fd_get_len(fd);
 	u32 fd_errors;
 
 	/* Tracing point */
@@ -671,7 +678,10 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv,
 
 	percpu_extras = this_cpu_ptr(priv->percpu_extras);
 	percpu_extras->tx_conf_frames++;
-	percpu_extras->tx_conf_bytes += dpaa2_fd_get_len(fd);
+	percpu_extras->tx_conf_bytes += fd_len;
+
+	fq->dq_frames++;
+	fq->dq_bytes += fd_len;
 
 	/* Check frame errors in the FD field */
 	fd_errors = dpaa2_fd_get_ctrl(fd) & DPAA2_FD_TX_ERR_MASK;
@@ -932,8 +942,9 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 	struct dpaa2_eth_channel *ch;
 	struct dpaa2_eth_priv *priv;
 	int rx_cleaned = 0, txconf_cleaned = 0;
-	enum dpaa2_eth_fq_type type = 0;
-	int store_cleaned;
+	struct dpaa2_eth_fq *fq, *txc_fq = NULL;
+	struct netdev_queue *nq;
+	int store_cleaned, work_done;
 	int err;
 
 	ch = container_of(napi, struct dpaa2_eth_channel, napi);
@@ -947,18 +958,25 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 		/* Refill pool if appropriate */
 		refill_pool(priv, ch, priv->bpid);
 
-		store_cleaned = consume_frames(ch, &type);
-		if (type == DPAA2_RX_FQ)
+		store_cleaned = consume_frames(ch, &fq);
+		if (!store_cleaned)
+			break;
+		if (fq->type == DPAA2_RX_FQ) {
 			rx_cleaned += store_cleaned;
-		else
+		} else {
 			txconf_cleaned += store_cleaned;
+			/* We have a single Tx conf FQ on this channel */
+			txc_fq = fq;
+		}
 
 		/* If we either consumed the whole NAPI budget with Rx frames
 		 * or we reached the Tx confirmations threshold, we're done.
 		 */
 		if (rx_cleaned >= budget ||
-		    txconf_cleaned >= DPAA2_ETH_TXCONF_PER_NAPI)
-			return budget;
+		    txconf_cleaned >= DPAA2_ETH_TXCONF_PER_NAPI) {
+			work_done = budget;
+			goto out;
+		}
 	} while (store_cleaned);
 
 	/* We didn't consume the entire budget, so finish napi and
@@ -972,7 +990,18 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 	WARN_ONCE(err, "CDAN notifications rearm failed on core %d",
 		  ch->nctx.desired_cpu);
 
-	return max(rx_cleaned, 1);
+	work_done = max(rx_cleaned, 1);
+
+out:
+	if (txc_fq) {
+		nq = netdev_get_tx_queue(priv->net_dev, txc_fq->flowid);
+		netdev_tx_completed_queue(nq, txc_fq->dq_frames,
+					  txc_fq->dq_bytes);
+		txc_fq->dq_frames = 0;
+		txc_fq->dq_bytes = 0;
+	}
+
+	return work_done;
 }
 
 static void enable_ch_napi(struct dpaa2_eth_priv *priv)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 3af706a88491..16545e9386cd 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -271,6 +271,8 @@ struct dpaa2_eth_fq {
 	u32 tx_qdbin;
 	u16 flowid;
 	int target_cpu;
+	u32 dq_frames;
+	u32 dq_bytes;
 	struct dpaa2_eth_channel *channel;
 	enum dpaa2_eth_fq_type type;
 
-- 
cgit v1.2.3


From 810eeb1f41a9a272eedc94ca18c072e75678ede4 Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Wed, 14 Nov 2018 11:50:19 +0000
Subject: usbnet: smsc95xx: fix rx packet alignment

The smsc95xx driver already takes into account the NET_IP_ALIGN
parameter when setting up the receive packet data, which means
we do not need to worry about aligning the packets in the usbnet
driver.

Adding the EVENT_NO_IP_ALIGN means that the IPv4 header is now
passed to the ip_rcv() routine with the start on an aligned address.

Tested on Raspberry Pi B3.

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/smsc95xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index f2d01cb6f958..6e971628bb50 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1295,6 +1295,7 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 		dev->net->features |= NETIF_F_RXCSUM;
 
 	dev->net->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM;
+	set_bit(EVENT_NO_IP_ALIGN, &dev->flags);
 
 	smsc95xx_init_mac_address(dev);
 
-- 
cgit v1.2.3


From 0c8b26556c6f6abf84bca67ce2c2e010953bba81 Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Wed, 14 Nov 2018 11:50:20 +0000
Subject: usbnet: smsc95xx: simplify tx_fixup code

The smsc95xx_tx_fixup is doing multiple calls to skb_push() to
put an 8-byte command header onto the packet. It would be easier
to do one skb_push() and then copy the data in once the push is
done.

We also make the code smaller by using proper unaligned puts for
the header. This merges in the CPU to LE32 conversion as well and
makes the whole sequence easier to understand hopefully.

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/smsc95xx.c | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 6e971628bb50..924ca94d3495 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -2018,6 +2018,7 @@ static struct sk_buff *smsc95xx_tx_fixup(struct usbnet *dev,
 	bool csum = skb->ip_summed == CHECKSUM_PARTIAL;
 	int overhead = csum ? SMSC95XX_TX_OVERHEAD_CSUM : SMSC95XX_TX_OVERHEAD;
 	u32 tx_cmd_a, tx_cmd_b;
+	void *ptr;
 
 	/* We do not advertise SG, so skbs should be already linearized */
 	BUG_ON(skb_shinfo(skb)->nr_frags);
@@ -2031,6 +2032,9 @@ static struct sk_buff *smsc95xx_tx_fixup(struct usbnet *dev,
 		return NULL;
 	}
 
+	tx_cmd_b = (u32)skb->len;
+	tx_cmd_a = tx_cmd_b | TX_CMD_A_FIRST_SEG_ | TX_CMD_A_LAST_SEG_;
+
 	if (csum) {
 		if (skb->len <= 45) {
 			/* workaround - hardware tx checksum does not work
@@ -2044,24 +2048,18 @@ static struct sk_buff *smsc95xx_tx_fixup(struct usbnet *dev,
 			csum = false;
 		} else {
 			u32 csum_preamble = smsc95xx_calc_csum_preamble(skb);
-			skb_push(skb, 4);
-			cpu_to_le32s(&csum_preamble);
-			memcpy(skb->data, &csum_preamble, 4);
+			ptr = skb_push(skb, 4);
+			put_unaligned_le32(csum_preamble, ptr);
+
+			tx_cmd_a += 4;
+			tx_cmd_b += 4;
+			tx_cmd_b |= TX_CMD_B_CSUM_ENABLE;
 		}
 	}
 
-	skb_push(skb, 4);
-	tx_cmd_b = (u32)(skb->len - 4);
-	if (csum)
-		tx_cmd_b |= TX_CMD_B_CSUM_ENABLE;
-	cpu_to_le32s(&tx_cmd_b);
-	memcpy(skb->data, &tx_cmd_b, 4);
-
-	skb_push(skb, 4);
-	tx_cmd_a = (u32)(skb->len - 8) | TX_CMD_A_FIRST_SEG_ |
-		TX_CMD_A_LAST_SEG_;
-	cpu_to_le32s(&tx_cmd_a);
-	memcpy(skb->data, &tx_cmd_a, 4);
+	ptr = skb_push(skb, 8);
+	put_unaligned_le32(tx_cmd_a, ptr);
+	put_unaligned_le32(tx_cmd_b, ptr+4);
 
 	return skb;
 }
-- 
cgit v1.2.3


From 6809d2167c404c2c8cbbbe1667c70ea88576ccac Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Wed, 14 Nov 2018 11:50:21 +0000
Subject: usbnet: smsc95xx: fix memcpy for accessing rx-data

Change the RX code to use get_unaligned_le32() instead of the combo
of memcpy and cpu_to_le32s(&var).

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/smsc95xx.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 924ca94d3495..a50cb9fd10fb 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -618,9 +618,7 @@ static void smsc95xx_status(struct usbnet *dev, struct urb *urb)
 		return;
 	}
 
-	memcpy(&intdata, urb->transfer_buffer, 4);
-	le32_to_cpus(&intdata);
-
+	intdata = get_unaligned_le32(urb->transfer_buffer);
 	netif_dbg(dev, link, dev->net, "intdata: 0x%08X\n", intdata);
 
 	if (intdata & INT_ENP_PHY_INT_)
@@ -1934,8 +1932,7 @@ static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		unsigned char *packet;
 		u16 size;
 
-		memcpy(&header, skb->data, sizeof(header));
-		le32_to_cpus(&header);
+		header = get_unaligned_le32(skb->data);
 		skb_pull(skb, 4 + NET_IP_ALIGN);
 		packet = skb->data;
 
-- 
cgit v1.2.3


From 75938f77105fcede560b9b6967389cdbd6b83361 Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Wed, 14 Nov 2018 11:50:22 +0000
Subject: usbnet: smsc95xx: check for csum being in last four bytes

The manual states that the checksum cannot lie in the last DWORD of the
transmission, so add a basic check for this and fall back to software
checksumming the packet.

This only seems to trigger for ACK packets with no options or data to
return to the other end, and the use of the tx-alignment option makes
it more likely to happen.

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/smsc95xx.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index a50cb9fd10fb..e3d08626828e 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -2009,6 +2009,23 @@ static u32 smsc95xx_calc_csum_preamble(struct sk_buff *skb)
 	return (high_16 << 16) | low_16;
 }
 
+/* The TX CSUM won't work if the checksum lies in the last 4 bytes of the
+ * transmission. This is fairly unlikely, only seems to trigger with some
+ * short TCP ACK packets sent.
+ *
+ * Note, this calculation should probably check for the alignment of the
+ * data as well, but a straight check for csum being in the last four bytes
+ * of the packet should be ok for now.
+ */
+static bool smsc95xx_can_tx_checksum(struct sk_buff *skb)
+{
+       unsigned int len = skb->len - skb_checksum_start_offset(skb);
+
+       if (skb->len <= 45)
+	       return false;
+       return skb->csum_offset < (len - (4 + 1));
+}
+
 static struct sk_buff *smsc95xx_tx_fixup(struct usbnet *dev,
 					 struct sk_buff *skb, gfp_t flags)
 {
@@ -2033,7 +2050,7 @@ static struct sk_buff *smsc95xx_tx_fixup(struct usbnet *dev,
 	tx_cmd_a = tx_cmd_b | TX_CMD_A_FIRST_SEG_ | TX_CMD_A_LAST_SEG_;
 
 	if (csum) {
-		if (skb->len <= 45) {
+		if (!smsc95xx_can_tx_checksum(skb)) {
 			/* workaround - hardware tx checksum does not work
 			 * properly with extremely small packets */
 			long csstart = skb_checksum_start_offset(skb);
-- 
cgit v1.2.3


From 213d7767af02a079e6d485daab30167d5d675a57 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Wed, 14 Nov 2018 22:26:17 +0800
Subject: tcp: clean up STATE_TRACE

Currently we can use bpf or tcp tracepoint to conveniently trace the tcp
state transition at the run time.
So we don't need to do this stuff at the compile time anymore.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 12 ------------
 net/ipv4/tcp.c    |  4 ----
 2 files changed, 16 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index b84b694e8b3d..63e37dd1c274 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1323,20 +1323,8 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb)
 
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb);
 int tcp_filter(struct sock *sk, struct sk_buff *skb);
-
-#undef STATE_TRACE
-
-#ifdef STATE_TRACE
-static const char *statename[]={
-	"Unused","Established","Syn Sent","Syn Recv",
-	"Fin Wait 1","Fin Wait 2","Time Wait", "Close",
-	"Close Wait","Last ACK","Listen","Closing"
-};
-#endif
 void tcp_set_state(struct sock *sk, int state);
-
 void tcp_done(struct sock *sk);
-
 int tcp_abort(struct sock *sk, int err);
 
 static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9e6bc4d6daa7..ca2b08c0b4a0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2241,10 +2241,6 @@ void tcp_set_state(struct sock *sk, int state)
 	 * socket sitting in hash tables.
 	 */
 	inet_sk_state_store(sk, state);
-
-#ifdef STATE_TRACE
-	SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]);
-#endif
 }
 EXPORT_SYMBOL_GPL(tcp_set_state);
 
-- 
cgit v1.2.3


From 3fcbdaee3b5c4a7f8ea4c7c11fecc009d2a1e7e4 Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Wed, 14 Nov 2018 17:26:32 -0800
Subject: etf: Cancel timer if there are no pending skbs

There is no point in firing the qdisc watchdog if there are no future
skbs pending in the queue and the watchdog had been set previously.

Signed-off-by: Jesus Sanchez-Palencia <jesus.s.palencia@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_etf.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index 1538d6fa8165..fa85b24ac794 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -117,8 +117,10 @@ static void reset_watchdog(struct Qdisc *sch)
 	struct sk_buff *skb = etf_peek_timesortedlist(sch);
 	ktime_t next;
 
-	if (!skb)
+	if (!skb) {
+		qdisc_watchdog_cancel(&q->watchdog);
 		return;
+	}
 
 	next = ktime_sub_ns(skb->tstamp, q->delta);
 	qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next));
-- 
cgit v1.2.3


From 09fd4860ea258d9666f852c213875e6bcdb1204e Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Wed, 14 Nov 2018 17:26:33 -0800
Subject: etf: Use cached rb_root

ETF's peek() operation is heavily used so use an rb_root_cached instead
and leverage rb_first_cached() which will run in O(1) instead of
O(log n).

Even if on 'timesortedlist_clear()' we could be using rb_erase(), we
choose to use rb_erase_cached(), because if in the future we allow
runtime changes to ETF parameters, and need to do a '_clear()', this
might cause some hard to debug issues.

Signed-off-by: Jesus Sanchez-Palencia <jesus.s.palencia@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_etf.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index fa85b24ac794..52452b546564 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -30,7 +30,7 @@ struct etf_sched_data {
 	int queue;
 	s32 delta; /* in ns */
 	ktime_t last; /* The txtime of the last skb sent to the netdevice. */
-	struct rb_root head;
+	struct rb_root_cached head;
 	struct qdisc_watchdog watchdog;
 	ktime_t (*get_time)(void);
 };
@@ -104,7 +104,7 @@ static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch)
 	struct etf_sched_data *q = qdisc_priv(sch);
 	struct rb_node *p;
 
-	p = rb_first(&q->head);
+	p = rb_first_cached(&q->head);
 	if (!p)
 		return NULL;
 
@@ -156,8 +156,9 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
 				      struct sk_buff **to_free)
 {
 	struct etf_sched_data *q = qdisc_priv(sch);
-	struct rb_node **p = &q->head.rb_node, *parent = NULL;
+	struct rb_node **p = &q->head.rb_root.rb_node, *parent = NULL;
 	ktime_t txtime = nskb->tstamp;
+	bool leftmost = true;
 
 	if (!is_packet_valid(sch, nskb)) {
 		report_sock_error(nskb, EINVAL,
@@ -170,13 +171,15 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
 
 		parent = *p;
 		skb = rb_to_skb(parent);
-		if (ktime_after(txtime, skb->tstamp))
+		if (ktime_after(txtime, skb->tstamp)) {
 			p = &parent->rb_right;
-		else
+			leftmost = false;
+		} else {
 			p = &parent->rb_left;
+		}
 	}
 	rb_link_node(&nskb->rbnode, parent, p);
-	rb_insert_color(&nskb->rbnode, &q->head);
+	rb_insert_color_cached(&nskb->rbnode, &q->head, leftmost);
 
 	qdisc_qstats_backlog_inc(sch, nskb);
 	sch->q.qlen++;
@@ -192,7 +195,7 @@ static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb,
 {
 	struct etf_sched_data *q = qdisc_priv(sch);
 
-	rb_erase(&skb->rbnode, &q->head);
+	rb_erase_cached(&skb->rbnode, &q->head);
 
 	/* The rbnode field in the skb re-uses these fields, now that
 	 * we are done with the rbnode, reset them.
@@ -388,14 +391,14 @@ static int etf_init(struct Qdisc *sch, struct nlattr *opt,
 static void timesortedlist_clear(struct Qdisc *sch)
 {
 	struct etf_sched_data *q = qdisc_priv(sch);
-	struct rb_node *p = rb_first(&q->head);
+	struct rb_node *p = rb_first_cached(&q->head);
 
 	while (p) {
 		struct sk_buff *skb = rb_to_skb(p);
 
 		p = rb_next(p);
 
-		rb_erase(&skb->rbnode, &q->head);
+		rb_erase_cached(&skb->rbnode, &q->head);
 		rtnl_kfree_skbs(skb, skb);
 		sch->q.qlen--;
 	}
-- 
cgit v1.2.3


From cbeeb8efec821188c770f582be345ed7b04a0b60 Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Wed, 14 Nov 2018 17:26:34 -0800
Subject: etf: Split timersortedlist_erase()

This is just a refactor that will simplify the implementation of the
next patch in this series which will drop all expired packets on the
dequeue flow.

Signed-off-by: Jesus Sanchez-Palencia <jesus.s.palencia@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_etf.c | 44 +++++++++++++++++++++++++++++---------------
 1 file changed, 29 insertions(+), 15 deletions(-)

diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index 52452b546564..bfe04748d5f0 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -190,10 +190,10 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
 	return NET_XMIT_SUCCESS;
 }
 
-static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb,
-				 bool drop)
+static void timesortedlist_drop(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct etf_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *to_free = NULL;
 
 	rb_erase_cached(&skb->rbnode, &q->head);
 
@@ -206,19 +206,33 @@ static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb,
 
 	qdisc_qstats_backlog_dec(sch, skb);
 
-	if (drop) {
-		struct sk_buff *to_free = NULL;
+	report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED);
 
-		report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED);
+	qdisc_drop(skb, sch, &to_free);
+	kfree_skb_list(to_free);
+	qdisc_qstats_overlimit(sch);
 
-		qdisc_drop(skb, sch, &to_free);
-		kfree_skb_list(to_free);
-		qdisc_qstats_overlimit(sch);
-	} else {
-		qdisc_bstats_update(sch, skb);
+	sch->q.qlen--;
+}
 
-		q->last = skb->tstamp;
-	}
+static void timesortedlist_remove(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+
+	rb_erase_cached(&skb->rbnode, &q->head);
+
+	/* The rbnode field in the skb re-uses these fields, now that
+	 * we are done with the rbnode, reset them.
+	 */
+	skb->next = NULL;
+	skb->prev = NULL;
+	skb->dev = qdisc_dev(sch);
+
+	qdisc_qstats_backlog_dec(sch, skb);
+
+	qdisc_bstats_update(sch, skb);
+
+	q->last = skb->tstamp;
 
 	sch->q.qlen--;
 }
@@ -237,7 +251,7 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
 
 	/* Drop if packet has expired while in queue. */
 	if (ktime_before(skb->tstamp, now)) {
-		timesortedlist_erase(sch, skb, true);
+		timesortedlist_drop(sch, skb);
 		skb = NULL;
 		goto out;
 	}
@@ -246,7 +260,7 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
 	 * txtime from deadline to (now + delta).
 	 */
 	if (q->deadline_mode) {
-		timesortedlist_erase(sch, skb, false);
+		timesortedlist_remove(sch, skb);
 		skb->tstamp = now;
 		goto out;
 	}
@@ -255,7 +269,7 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
 
 	/* Dequeue only if now is within the [txtime - delta, txtime] range. */
 	if (ktime_after(now, next))
-		timesortedlist_erase(sch, skb, false);
+		timesortedlist_remove(sch, skb);
 	else
 		skb = NULL;
 
-- 
cgit v1.2.3


From 37342bdaf5b363cf2e1bd170ce7d1de34ecf57e7 Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Wed, 14 Nov 2018 17:26:35 -0800
Subject: etf: Drop all expired packets

Currently on dequeue() ETF only drops the first expired packet, which
causes a problem if the next packet is already expired. When this
happens, the watchdog will be configured with a time in the past, fire
straight way and the packet will finally be dropped once the dequeue()
function of the qdisc is called again.

We can save quite a few cycles and improve the overall behavior of the
qdisc if we drop all expired packets if the next packet is expired.
This should allow ETF to recover faster from bad situations. But
packet drops are still a very serious warning that the requirements
imposed on the system aren't reasonable.

This was inspired by how the implementation of hrtimers use the
rb_tree inside the kernel.

Signed-off-by: Jesus Sanchez-Palencia <jesus.s.palencia@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_etf.c | 36 +++++++++++++++++++++---------------
 1 file changed, 21 insertions(+), 15 deletions(-)

diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index bfe04748d5f0..1150f22983df 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -190,29 +190,35 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
 	return NET_XMIT_SUCCESS;
 }
 
-static void timesortedlist_drop(struct Qdisc *sch, struct sk_buff *skb)
+static void timesortedlist_drop(struct Qdisc *sch, struct sk_buff *skb,
+				ktime_t now)
 {
 	struct etf_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *to_free = NULL;
+	struct sk_buff *tmp = NULL;
 
-	rb_erase_cached(&skb->rbnode, &q->head);
+	skb_rbtree_walk_from_safe(skb, tmp) {
+		if (ktime_after(skb->tstamp, now))
+			break;
 
-	/* The rbnode field in the skb re-uses these fields, now that
-	 * we are done with the rbnode, reset them.
-	 */
-	skb->next = NULL;
-	skb->prev = NULL;
-	skb->dev = qdisc_dev(sch);
+		rb_erase_cached(&skb->rbnode, &q->head);
 
-	qdisc_qstats_backlog_dec(sch, skb);
+		/* The rbnode field in the skb re-uses these fields, now that
+		 * we are done with the rbnode, reset them.
+		 */
+		skb->next = NULL;
+		skb->prev = NULL;
+		skb->dev = qdisc_dev(sch);
 
-	report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED);
+		report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED);
 
-	qdisc_drop(skb, sch, &to_free);
-	kfree_skb_list(to_free);
-	qdisc_qstats_overlimit(sch);
+		qdisc_qstats_backlog_dec(sch, skb);
+		qdisc_drop(skb, sch, &to_free);
+		qdisc_qstats_overlimit(sch);
+		sch->q.qlen--;
+	}
 
-	sch->q.qlen--;
+	kfree_skb_list(to_free);
 }
 
 static void timesortedlist_remove(struct Qdisc *sch, struct sk_buff *skb)
@@ -251,7 +257,7 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
 
 	/* Drop if packet has expired while in queue. */
 	if (ktime_before(skb->tstamp, now)) {
-		timesortedlist_drop(sch, skb);
+		timesortedlist_drop(sch, skb, now);
 		skb = NULL;
 		goto out;
 	}
-- 
cgit v1.2.3


From 29a9c10e4110e368443f0b606d71557edee7f2cc Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 12 Nov 2018 13:44:10 -0800
Subject: bpftool: make libbfd optional

Make it possible to build bpftool without libbfd. libbfd and libopcodes are
typically provided in dev/dbg packages (binutils-dev in debian) which we
usually don't have installed on the fleet machines and we'd like a way to have
bpftool version that works without installing any additional packages.
This excludes support for disassembling jit-ted code and prints an error if
the user tries to use these features.

Tested by:
cat > FEATURES_DUMP.bpftool <<EOF
feature-libbfd=0
feature-disassembler-four-args=1
feature-reallocarray=0
feature-libelf=1
feature-libelf-mmap=1
feature-bpf=1
EOF
FEATURES_DUMP=$PWD/FEATURES_DUMP.bpftool make
ldd bpftool | grep libbfd

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Makefile     | 13 +++++++++++--
 tools/bpf/bpftool/jit_disasm.c |  8 +++++++-
 tools/bpf/bpftool/main.c       |  3 ---
 tools/bpf/bpftool/main.h       | 14 ++++++++++++++
 tools/bpf/bpftool/prog.c       |  3 +++
 5 files changed, 35 insertions(+), 6 deletions(-)

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index dac7eff4c7e5..1bea6b979082 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -53,7 +53,7 @@ ifneq ($(EXTRA_LDFLAGS),)
 LDFLAGS += $(EXTRA_LDFLAGS)
 endif
 
-LIBS = -lelf -lbfd -lopcodes $(LIBBPF)
+LIBS = -lelf $(LIBBPF)
 
 INSTALL ?= install
 RM ?= rm -f
@@ -90,7 +90,16 @@ include $(wildcard $(OUTPUT)*.d)
 
 all: $(OUTPUT)bpftool
 
-SRCS = $(wildcard *.c)
+BFD_SRCS = jit_disasm.c
+
+SRCS = $(filter-out $(BFD_SRCS),$(wildcard *.c))
+
+ifeq ($(feature-libbfd),1)
+CFLAGS += -DHAVE_LIBBFD_SUPPORT
+SRCS += $(BFD_SRCS)
+LIBS += -lbfd -lopcodes
+endif
+
 OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
 
 $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index c75ffd9ce2bb..b2ed5ee1af5f 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -109,7 +109,7 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 		if (inf) {
 			bfdf->arch_info = inf;
 		} else {
-			p_err("No libfd support for %s", arch);
+			p_err("No libbfd support for %s", arch);
 			return;
 		}
 	}
@@ -183,3 +183,9 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 
 	bfd_close(bfdf);
 }
+
+int disasm_init(void)
+{
+	bfd_init();
+	return 0;
+}
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 75a3296dc0bc..5c4c1cd5a7ba 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -31,7 +31,6 @@
  * SOFTWARE.
  */
 
-#include <bfd.h>
 #include <ctype.h>
 #include <errno.h>
 #include <getopt.h>
@@ -399,8 +398,6 @@ int main(int argc, char **argv)
 	if (argc < 0)
 		usage();
 
-	bfd_init();
-
 	ret = cmd_select(cmds, argc, argv, do_help);
 
 	if (json_output)
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 61d82020af58..10c6c16fae29 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -147,8 +147,22 @@ int prog_parse_fd(int *argc, char ***argv);
 int map_parse_fd(int *argc, char ***argv);
 int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
 
+#ifdef HAVE_LIBBFD_SUPPORT
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 		       const char *arch, const char *disassembler_options);
+int disasm_init(void);
+#else
+static inline
+void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
+		       const char *arch, const char *disassembler_options)
+{
+}
+static inline int disasm_init(void)
+{
+	p_err("No libbfd support");
+	return -1;
+}
+#endif
 void print_data_json(uint8_t *data, size_t len);
 void print_hex_data_json(uint8_t *data, size_t len);
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 5ff5544596e7..c176e1aa66fe 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -467,6 +467,9 @@ static int do_dump(int argc, char **argv)
 	int fd;
 
 	if (is_prefix(*argv, "jited")) {
+		if (disasm_init())
+			return -1;
+
 		member_len = &info.jited_prog_len;
 		member_ptr = &info.jited_prog_insns;
 	} else if (is_prefix(*argv, "xlated")) {
-- 
cgit v1.2.3


From 592ee43faf860c1f2c0a4c11838db6fdb974bb78 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 13 Nov 2018 09:29:26 +0000
Subject: bpf: fix null pointer dereference on pointer offload

Pointer offload is being null checked however the following statement
dereferences the potentially null pointer offload when assigning
offload->dev_state.  Fix this by only assigning it if offload is not
null.

Detected by CoverityScan, CID#1475437 ("Dereference after null check")

Fixes: 00db12c3d141 ("bpf: call verifier_prep from its callback in struct bpf_offload_dev")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/offload.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 52c5617e3716..54cf2b9c44a4 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -130,9 +130,10 @@ int bpf_prog_offload_verifier_prep(struct bpf_prog *prog)
 
 	down_read(&bpf_devs_lock);
 	offload = prog->aux->offload;
-	if (offload)
+	if (offload) {
 		ret = offload->offdev->ops->prepare(prog);
-	offload->dev_state = !ret;
+		offload->dev_state = !ret;
+	}
 	up_read(&bpf_devs_lock);
 
 	return ret;
-- 
cgit v1.2.3


From 9c48060141bd937497774546e4bb89b8992be383 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 15 Nov 2018 02:34:50 +0100
Subject: udp: fix jump label misuse

The commit 60fb9567bf30 ("udp: implement complete book-keeping for
encap_needed") introduced a severe misuse of jump label APIs, which
syzbot, as reported by Eric, was able to exploit.

When multiple sockets/process can concurrently request (and than
disable) the udp encap, we need to track the activation counter with
*_inc()/*_dec() jump label variants, or we can experience bad things
at disable time.

Fixes: 60fb9567bf30 ("udp: implement complete book-keeping for encap_needed")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 4 ++--
 net/ipv6/udp.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 6f8890c5bc7e..aff2a8e99e01 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -587,7 +587,7 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
 DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
 void udp_encap_enable(void)
 {
-	static_branch_enable(&udp_encap_needed_key);
+	static_branch_inc(&udp_encap_needed_key);
 }
 EXPORT_SYMBOL(udp_encap_enable);
 
@@ -2524,7 +2524,7 @@ void udp_destroy_sock(struct sock *sk)
 				encap_destroy(sk);
 		}
 		if (up->encap_enabled)
-			static_branch_disable(&udp_encap_needed_key);
+			static_branch_dec(&udp_encap_needed_key);
 	}
 }
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index dde51fc7ac16..09cba4cfe31f 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -448,7 +448,7 @@ csum_copy_err:
 DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
 void udpv6_encap_enable(void)
 {
-	static_branch_enable(&udpv6_encap_needed_key);
+	static_branch_inc(&udpv6_encap_needed_key);
 }
 EXPORT_SYMBOL(udpv6_encap_enable);
 
@@ -1579,7 +1579,7 @@ void udpv6_destroy_sock(struct sock *sk)
 				encap_destroy(sk);
 		}
 		if (up->encap_enabled)
-			static_branch_disable(&udpv6_encap_needed_key);
+			static_branch_dec(&udpv6_encap_needed_key);
 	}
 
 	inet6_destroy_sock(sk);
-- 
cgit v1.2.3


From b24b767fb1b37da7e630460db4a8121caf5ae4d2 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 15 Nov 2018 10:23:03 +0800
Subject: isdn/hisax: remove set but not used variable 'total'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/isdn/hisax/hfc_pci.c:277:6: warning:
 variable ‘total’ set but not used [-Wunused-but-set-variable]

It never used since git history start.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hisax/hfc_pci.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c
index ea0e4c6de3fb..5b719b561860 100644
--- a/drivers/isdn/hisax/hfc_pci.c
+++ b/drivers/isdn/hisax/hfc_pci.c
@@ -274,7 +274,7 @@ hfcpci_empty_fifo(struct BCState *bcs, bzfifo_type *bz, u_char *bdata, int count
 	u_char *ptr, *ptr1, new_f2;
 	struct sk_buff *skb;
 	struct IsdnCardState *cs = bcs->cs;
-	int total, maxlen, new_z2;
+	int maxlen, new_z2;
 	z_type *zp;
 
 	if ((cs->debug & L1_DEB_HSCX) && !(cs->debug & L1_DEB_HSCX_FIFO))
@@ -297,7 +297,6 @@ hfcpci_empty_fifo(struct BCState *bcs, bzfifo_type *bz, u_char *bdata, int count
 	} else if (!(skb = dev_alloc_skb(count - 3)))
 		printk(KERN_WARNING "HFCPCI: receive out of memory\n");
 	else {
-		total = count;
 		count -= 3;
 		ptr = skb_put(skb, count);
 
-- 
cgit v1.2.3


From 9c549a6b057386df478e4307902cbc84f1eee058 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 15 Nov 2018 03:24:05 +0100
Subject: selftests: add explicit test for multiple concurrent GRO sockets

This covers for proper accounting of encap needed static keys

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/udpgro.sh | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index e94ef8067173..aeac53a99aeb 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -91,6 +91,28 @@ run_one_nat() {
 	wait $(jobs -p)
 }
 
+run_one_2sock() {
+	# use 'rx' as separator between sender args and receiver args
+	local -r all="$@"
+	local -r tx_args=${all%rx*}
+	local -r rx_args=${all#*rx}
+
+	cfg_veth
+
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -p 12345 &
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \
+		echo "ok" || \
+		echo "failed" &
+
+	# Hack: let bg programs complete the startup
+	sleep 0.1
+	./udpgso_bench_tx ${tx_args} -p 12345
+	sleep 0.1
+	# first UDP GSO socket should be closed at this point
+	./udpgso_bench_tx ${tx_args}
+	wait $(jobs -p)
+}
+
 run_nat_test() {
 	local -r args=$@
 
@@ -98,6 +120,13 @@ run_nat_test() {
 	./in_netns.sh $0 __subprocess_nat $2 rx -r $3
 }
 
+run_2sock_test() {
+	local -r args=$@
+
+	printf " %-40s" "$1"
+	./in_netns.sh $0 __subprocess_2sock $2 rx -G -r $3
+}
+
 run_all() {
 	local -r core_args="-l 4"
 	local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
@@ -120,6 +149,7 @@ run_all() {
 	run_test "GRO with custom segment size cmsg" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720 -S 500"
 
 	run_nat_test "bad GRO lookup" "${ipv4_args} -M 1 -s 14720 -S 0" "-n 10 -l 1472"
+	run_2sock_test "multiple GRO socks" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
 
 	echo "ipv6"
 	run_test "no GRO" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400"
@@ -130,6 +160,7 @@ run_all() {
 	run_test "GRO with custom segment size cmsg" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520 -S 500"
 
 	run_nat_test "bad GRO lookup" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 10 -l 1452"
+	run_2sock_test "multiple GRO socks" "${ipv6_args} -M 1 -s 14520 -S 0 " "-n 1 -l 14520 -S 1452"
 }
 
 if [ ! -f ../bpf/xdp_dummy.o ]; then
@@ -145,4 +176,7 @@ elif [[ $1 == "__subprocess" ]]; then
 elif [[ $1 == "__subprocess_nat" ]]; then
 	shift
 	run_one_nat $@
+elif [[ $1 == "__subprocess_2sock" ]]; then
+	shift
+	run_one_2sock $@
 fi
-- 
cgit v1.2.3


From 255f4803ecc490319596d73f24ed775f99923a53 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 14 Nov 2018 22:23:45 -0800
Subject: net: sched: gred: separate error and non-error path in gred_change()

We will soon want to add more code to the non-error path, separate
it from the error handling flow.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_gred.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 4a042abf844c..22110be9d285 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -423,12 +423,11 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 
 	max_P = tb[TCA_GRED_MAX_P] ? nla_get_u32(tb[TCA_GRED_MAX_P]) : 0;
 
-	err = -EINVAL;
 	ctl = nla_data(tb[TCA_GRED_PARMS]);
 	stab = nla_data(tb[TCA_GRED_STAB]);
 
 	if (ctl->DP >= table->DPs)
-		goto errout;
+		return -EINVAL;
 
 	if (gred_rio_mode(table)) {
 		if (ctl->prio == 0) {
@@ -450,7 +449,7 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 
 	err = gred_change_vq(sch, ctl->DP, ctl, prio, stab, max_P, &prealloc);
 	if (err < 0)
-		goto errout_locked;
+		goto err_unlock_free;
 
 	if (gred_rio_mode(table)) {
 		gred_disable_wred_mode(table);
@@ -458,12 +457,13 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 			gred_enable_wred_mode(table);
 	}
 
-	err = 0;
+	sch_tree_unlock(sch);
+	kfree(prealloc);
+	return 0;
 
-errout_locked:
+err_unlock_free:
 	sch_tree_unlock(sch);
 	kfree(prealloc);
-errout:
 	return err;
 }
 
-- 
cgit v1.2.3


From 79c59fe01e70f595f0d67be76ae8309a32a3760d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 14 Nov 2018 22:23:46 -0800
Subject: net: sched: gred: pass extack to nla_parse_nested()

In case netlink wants to provide parsing error pass extack
to nla_parse_nested().

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_gred.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 22110be9d285..9f6a4ddd262a 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -406,7 +406,7 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, NULL);
+	err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -476,7 +476,7 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt,
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, NULL);
+	err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, extack);
 	if (err < 0)
 		return err;
 
-- 
cgit v1.2.3


From 4777be08b8aab41286efdf5362a02f8e26d1a84e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 14 Nov 2018 22:23:47 -0800
Subject: net: sched: gred: use extack to provide more details on configuration
 errors

Add extack messages to -EINVAL errors, to help users identify
their mistakes.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_gred.c | 44 +++++++++++++++++++++++++++++++++-----------
 1 file changed, 33 insertions(+), 11 deletions(-)

diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 9f6a4ddd262a..3d7bd374b303 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -300,7 +300,8 @@ static inline void gred_destroy_vq(struct gred_sched_data *q)
 	kfree(q);
 }
 
-static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps)
+static int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps,
+				 struct netlink_ext_ack *extack)
 {
 	struct gred_sched *table = qdisc_priv(sch);
 	struct tc_gred_sopt *sopt;
@@ -311,9 +312,19 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps)
 
 	sopt = nla_data(dps);
 
-	if (sopt->DPs > MAX_DPs || sopt->DPs == 0 ||
-	    sopt->def_DP >= sopt->DPs)
+	if (sopt->DPs > MAX_DPs) {
+		NL_SET_ERR_MSG_MOD(extack, "number of virtual queues too high");
 		return -EINVAL;
+	}
+	if (sopt->DPs == 0) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "number of virtual queues can't be 0");
+		return -EINVAL;
+	}
+	if (sopt->def_DP >= sopt->DPs) {
+		NL_SET_ERR_MSG_MOD(extack, "default virtual queue above virtual queue count");
+		return -EINVAL;
+	}
 
 	sch_tree_lock(sch);
 	table->DPs = sopt->DPs;
@@ -352,13 +363,16 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps)
 static inline int gred_change_vq(struct Qdisc *sch, int dp,
 				 struct tc_gred_qopt *ctl, int prio,
 				 u8 *stab, u32 max_P,
-				 struct gred_sched_data **prealloc)
+				 struct gred_sched_data **prealloc,
+				 struct netlink_ext_ack *extack)
 {
 	struct gred_sched *table = qdisc_priv(sch);
 	struct gred_sched_data *q = table->tab[dp];
 
-	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog))
+	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) {
+		NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters");
 		return -EINVAL;
+	}
 
 	if (!q) {
 		table->tab[dp] = q = *prealloc;
@@ -413,21 +427,25 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) {
 		if (tb[TCA_GRED_LIMIT] != NULL)
 			sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]);
-		return gred_change_table_def(sch, tb[TCA_GRED_DPS]);
+		return gred_change_table_def(sch, tb[TCA_GRED_DPS], extack);
 	}
 
 	if (tb[TCA_GRED_PARMS] == NULL ||
 	    tb[TCA_GRED_STAB] == NULL ||
-	    tb[TCA_GRED_LIMIT] != NULL)
+	    tb[TCA_GRED_LIMIT] != NULL) {
+		NL_SET_ERR_MSG_MOD(extack, "can't configure Qdisc and virtual queue at the same time");
 		return -EINVAL;
+	}
 
 	max_P = tb[TCA_GRED_MAX_P] ? nla_get_u32(tb[TCA_GRED_MAX_P]) : 0;
 
 	ctl = nla_data(tb[TCA_GRED_PARMS]);
 	stab = nla_data(tb[TCA_GRED_STAB]);
 
-	if (ctl->DP >= table->DPs)
+	if (ctl->DP >= table->DPs) {
+		NL_SET_ERR_MSG_MOD(extack, "virtual queue index above virtual queue count");
 		return -EINVAL;
+	}
 
 	if (gred_rio_mode(table)) {
 		if (ctl->prio == 0) {
@@ -447,7 +465,8 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 	prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL);
 	sch_tree_lock(sch);
 
-	err = gred_change_vq(sch, ctl->DP, ctl, prio, stab, max_P, &prealloc);
+	err = gred_change_vq(sch, ctl->DP, ctl, prio, stab, max_P, &prealloc,
+			     extack);
 	if (err < 0)
 		goto err_unlock_free;
 
@@ -480,8 +499,11 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt,
 	if (err < 0)
 		return err;
 
-	if (tb[TCA_GRED_PARMS] || tb[TCA_GRED_STAB])
+	if (tb[TCA_GRED_PARMS] || tb[TCA_GRED_STAB]) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "virtual queue configuration can't be specified at initialization time");
 		return -EINVAL;
+	}
 
 	if (tb[TCA_GRED_LIMIT])
 		sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]);
@@ -489,7 +511,7 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt,
 		sch->limit = qdisc_dev(sch)->tx_queue_len
 		             * psched_mtu(qdisc_dev(sch));
 
-	return gred_change_table_def(sch, tb[TCA_GRED_DPS]);
+	return gred_change_table_def(sch, tb[TCA_GRED_DPS], extack);
 }
 
 static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
-- 
cgit v1.2.3


From 9f5cd0c8066997b77ba98fc5355faa425f14b381 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 14 Nov 2018 22:23:48 -0800
Subject: net: sched: gred: store bytesin as a 64 bit value

32 bit counters for bytes are not really going to last long in modern
world.  Make sch_gred count bytes on a 64 bit counter.  It will still
get truncated during dump but follow up patch will add set of new
stat dump attributes.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_gred.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 3d7bd374b303..6f209c83ee7a 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -35,7 +35,7 @@ struct gred_sched;
 struct gred_sched_data {
 	u32		limit;		/* HARD maximal queue length	*/
 	u32		DP;		/* the drop parameters */
-	u32		bytesin;	/* bytes seen on virtualQ so far*/
+	u64		bytesin;	/* bytes seen on virtualQ so far*/
 	u32		packetsin;	/* packets seen on virtualQ so far*/
 	u32		backlog;	/* bytes on the virtualQ */
 	u8		prio;		/* the prio of this vq */
-- 
cgit v1.2.3


From 80e22e961dfd15530215f6f6dcd94cd8f65ba1ea Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 14 Nov 2018 22:23:49 -0800
Subject: net: sched: gred: provide a better structured dump and expose stats

Currently all GRED's virtual queue data is dumped in a single
array in a single attribute.  This makes it pretty much impossible
to add new fields.  In order to expose more detailed stats add a
new set of attributes.  We can now expose the 64 bit value of bytesin
and all the mark stats which were not part of the original design.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h | 26 +++++++++++++++++++++
 net/sched/sch_gred.c           | 53 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 78 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index ee017bc057a3..c8f717346b60 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -291,11 +291,37 @@ enum {
        TCA_GRED_DPS,
        TCA_GRED_MAX_P,
        TCA_GRED_LIMIT,
+       TCA_GRED_VQ_LIST,	/* nested TCA_GRED_VQ_ENTRY */
        __TCA_GRED_MAX,
 };
 
 #define TCA_GRED_MAX (__TCA_GRED_MAX - 1)
 
+enum {
+	TCA_GRED_VQ_ENTRY_UNSPEC,
+	TCA_GRED_VQ_ENTRY,	/* nested TCA_GRED_VQ_* */
+	__TCA_GRED_VQ_ENTRY_MAX,
+};
+#define TCA_GRED_VQ_ENTRY_MAX (__TCA_GRED_VQ_ENTRY_MAX - 1)
+
+enum {
+	TCA_GRED_VQ_UNSPEC,
+	TCA_GRED_VQ_PAD,
+	TCA_GRED_VQ_DP,			/* u32 */
+	TCA_GRED_VQ_STAT_BYTES,		/* u64 */
+	TCA_GRED_VQ_STAT_PACKETS,	/* u32 */
+	TCA_GRED_VQ_STAT_BACKLOG,	/* u32 */
+	TCA_GRED_VQ_STAT_PROB_DROP,	/* u32 */
+	TCA_GRED_VQ_STAT_PROB_MARK,	/* u32 */
+	TCA_GRED_VQ_STAT_FORCED_DROP,	/* u32 */
+	TCA_GRED_VQ_STAT_FORCED_MARK,	/* u32 */
+	TCA_GRED_VQ_STAT_PDROP,		/* u32 */
+	TCA_GRED_VQ_STAT_OTHER,		/* u32 */
+	__TCA_GRED_VQ_MAX
+};
+
+#define TCA_GRED_VQ_MAX (__TCA_GRED_VQ_MAX - 1)
+
 struct tc_gred_qopt {
 	__u32		limit;        /* HARD maximal queue length (bytes)    */
 	__u32		qth_min;      /* Min average length threshold (bytes) */
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 6f209c83ee7a..dc09a32c4b4f 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -404,6 +404,7 @@ static const struct nla_policy gred_policy[TCA_GRED_MAX + 1] = {
 	[TCA_GRED_DPS]		= { .len = sizeof(struct tc_gred_sopt) },
 	[TCA_GRED_MAX_P]	= { .type = NLA_U32 },
 	[TCA_GRED_LIMIT]	= { .type = NLA_U32 },
+	[TCA_GRED_VQ_LIST]	= { .type = NLA_REJECT },
 };
 
 static int gred_change(struct Qdisc *sch, struct nlattr *opt,
@@ -517,7 +518,7 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt,
 static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct gred_sched *table = qdisc_priv(sch);
-	struct nlattr *parms, *opts = NULL;
+	struct nlattr *parms, *vqs, *opts = NULL;
 	int i;
 	u32 max_p[MAX_DPs];
 	struct tc_gred_sopt sopt = {
@@ -544,6 +545,7 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (nla_put_u32(skb, TCA_GRED_LIMIT, sch->limit))
 		goto nla_put_failure;
 
+	/* Old style all-in-one dump of VQs */
 	parms = nla_nest_start(skb, TCA_GRED_PARMS);
 	if (parms == NULL)
 		goto nla_put_failure;
@@ -594,6 +596,55 @@ append_opt:
 
 	nla_nest_end(skb, parms);
 
+	/* Dump the VQs again, in more structured way */
+	vqs = nla_nest_start(skb, TCA_GRED_VQ_LIST);
+	if (!vqs)
+		goto nla_put_failure;
+
+	for (i = 0; i < MAX_DPs; i++) {
+		struct gred_sched_data *q = table->tab[i];
+		struct nlattr *vq;
+
+		if (!q)
+			continue;
+
+		vq = nla_nest_start(skb, TCA_GRED_VQ_ENTRY);
+		if (!vq)
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, TCA_GRED_VQ_DP, q->DP))
+			goto nla_put_failure;
+
+		/* Stats */
+		if (nla_put_u64_64bit(skb, TCA_GRED_VQ_STAT_BYTES, q->bytesin,
+				      TCA_GRED_VQ_PAD))
+			goto nla_put_failure;
+		if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PACKETS, q->packetsin))
+			goto nla_put_failure;
+		if (nla_put_u32(skb, TCA_GRED_VQ_STAT_BACKLOG,
+				gred_backlog(table, q, sch)))
+			goto nla_put_failure;
+		if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PROB_DROP,
+				q->stats.prob_drop))
+			goto nla_put_failure;
+		if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PROB_MARK,
+				q->stats.prob_mark))
+			goto nla_put_failure;
+		if (nla_put_u32(skb, TCA_GRED_VQ_STAT_FORCED_DROP,
+				q->stats.forced_drop))
+			goto nla_put_failure;
+		if (nla_put_u32(skb, TCA_GRED_VQ_STAT_FORCED_MARK,
+				q->stats.forced_mark))
+			goto nla_put_failure;
+		if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PDROP, q->stats.pdrop))
+			goto nla_put_failure;
+		if (nla_put_u32(skb, TCA_GRED_VQ_STAT_OTHER, q->stats.other))
+			goto nla_put_failure;
+
+		nla_nest_end(skb, vq);
+	}
+	nla_nest_end(skb, vqs);
+
 	return nla_nest_end(skb, opts);
 
 nla_put_failure:
-- 
cgit v1.2.3


From 25fc1989077e71be9fdbe6b78670cf90df2fb789 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 14 Nov 2018 22:23:50 -0800
Subject: net: sched: gred: store red flags per virtual queue

Right now ECN marking and HARD drop (the common RED flags) can only
be configured for the entire Qdisc.  In preparation for per-vq flags
store the values in the virtual queue structure.  Setting per-vq
flags will only be allowed when no flags are set for the entire Qdisc.
For the new flags we will also make sure undefined bits are 0.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_gred.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index dc09a32c4b4f..47133106c7e2 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -29,12 +29,15 @@
 #define GRED_DEF_PRIO (MAX_DPs / 2)
 #define GRED_VQ_MASK (MAX_DPs - 1)
 
+#define GRED_VQ_RED_FLAGS	(TC_RED_ECN | TC_RED_HARDDROP)
+
 struct gred_sched_data;
 struct gred_sched;
 
 struct gred_sched_data {
 	u32		limit;		/* HARD maximal queue length	*/
 	u32		DP;		/* the drop parameters */
+	u32		red_flags;	/* virtualQ version of red_flags */
 	u64		bytesin;	/* bytes seen on virtualQ so far*/
 	u32		packetsin;	/* packets seen on virtualQ so far*/
 	u32		backlog;	/* bytes on the virtualQ */
@@ -139,14 +142,14 @@ static inline void gred_store_wred_set(struct gred_sched *table,
 	table->wred_set.qidlestart = q->vars.qidlestart;
 }
 
-static inline int gred_use_ecn(struct gred_sched *t)
+static int gred_use_ecn(struct gred_sched_data *q)
 {
-	return t->red_flags & TC_RED_ECN;
+	return q->red_flags & TC_RED_ECN;
 }
 
-static inline int gred_use_harddrop(struct gred_sched *t)
+static int gred_use_harddrop(struct gred_sched_data *q)
 {
-	return t->red_flags & TC_RED_HARDDROP;
+	return q->red_flags & TC_RED_HARDDROP;
 }
 
 static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch,
@@ -212,7 +215,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 
 	case RED_PROB_MARK:
 		qdisc_qstats_overlimit(sch);
-		if (!gred_use_ecn(t) || !INET_ECN_set_ce(skb)) {
+		if (!gred_use_ecn(q) || !INET_ECN_set_ce(skb)) {
 			q->stats.prob_drop++;
 			goto congestion_drop;
 		}
@@ -222,7 +225,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 
 	case RED_HARD_MARK:
 		qdisc_qstats_overlimit(sch);
-		if (gred_use_harddrop(t) || !gred_use_ecn(t) ||
+		if (gred_use_harddrop(q) || !gred_use_ecn(q) ||
 		    !INET_ECN_set_ce(skb)) {
 			q->stats.forced_drop++;
 			goto congestion_drop;
@@ -305,6 +308,7 @@ static int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps,
 {
 	struct gred_sched *table = qdisc_priv(sch);
 	struct tc_gred_sopt *sopt;
+	bool red_flags_changed;
 	int i;
 
 	if (!dps)
@@ -329,6 +333,7 @@ static int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps,
 	sch_tree_lock(sch);
 	table->DPs = sopt->DPs;
 	table->def = sopt->def_DP;
+	red_flags_changed = table->red_flags != sopt->flags;
 	table->red_flags = sopt->flags;
 
 	/*
@@ -348,6 +353,12 @@ static int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps,
 		gred_disable_wred_mode(table);
 	}
 
+	if (red_flags_changed)
+		for (i = 0; i < table->DPs; i++)
+			if (table->tab[i])
+				table->tab[i]->red_flags =
+					table->red_flags & GRED_VQ_RED_FLAGS;
+
 	for (i = table->DPs; i < MAX_DPs; i++) {
 		if (table->tab[i]) {
 			pr_warn("GRED: Warning: Destroying shadowed VQ 0x%x\n",
@@ -379,6 +390,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp,
 		*prealloc = NULL;
 		if (!q)
 			return -ENOMEM;
+		q->red_flags = table->red_flags & GRED_VQ_RED_FLAGS;
 	}
 
 	q->DP = dp;
-- 
cgit v1.2.3


From 72111015024f4eddb5aac400ddbe38a4f8f0279a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 14 Nov 2018 22:23:51 -0800
Subject: net: sched: gred: allow manipulating per-DP RED flags

Allow users to set and dump RED flags (ECN enabled and harddrop)
on per-virtual queue basis.  Validation of attributes is split
from changes to make sure we won't have to undo previous operations
when we find out configuration is invalid.

The objective is to allow changing per-Qdisc parameters without
overwriting the per-vq configured flags.

Old user space will not pass the TCA_GRED_VQ_FLAGS attribute and
per-Qdisc flags will always get propagated to the virtual queues.

New user space which wants to make use of per-vq flags should set
per-Qdisc flags to 0 and then configure per-vq flags as it
sees fit.  Once per-vq flags are set per-Qdisc flags can't be
changed to non-zero.  Vice versa - if the per-Qdisc flags are
non-zero the TCA_GRED_VQ_FLAGS attribute has to either be omitted
or set to the same value as per-Qdisc flags.

Update per-Qdisc parameters:
per-Qdisc | per-VQ | result
        0 |      0 | all vq flags updated
	0 |  non-0 | error (vq flags in use)
    non-0 |      0 | -- impossible --
    non-0 |  non-0 | all vq flags updated

Update per-VQ state (flags parameter not specified):
   no change to flags

Update per-VQ state (flags parameter set):
per-Qdisc | per-VQ | result
        0 |   any  | per-vq flags updated
    non-0 |      0 | -- impossible --
    non-0 |  non-0 | error (per-Qdisc flags in use)

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |   1 +
 net/sched/sch_gred.c           | 144 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 144 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index c8f717346b60..0d18b1d1fbbc 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -317,6 +317,7 @@ enum {
 	TCA_GRED_VQ_STAT_FORCED_MARK,	/* u32 */
 	TCA_GRED_VQ_STAT_PDROP,		/* u32 */
 	TCA_GRED_VQ_STAT_OTHER,		/* u32 */
+	TCA_GRED_VQ_FLAGS,		/* u32 */
 	__TCA_GRED_VQ_MAX
 };
 
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 47133106c7e2..8b8c325f48bc 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -152,6 +152,19 @@ static int gred_use_harddrop(struct gred_sched_data *q)
 	return q->red_flags & TC_RED_HARDDROP;
 }
 
+static bool gred_per_vq_red_flags_used(struct gred_sched *table)
+{
+	unsigned int i;
+
+	/* Local per-vq flags couldn't have been set unless global are 0 */
+	if (table->red_flags)
+		return false;
+	for (i = 0; i < MAX_DPs; i++)
+		if (table->tab[i] && table->tab[i]->red_flags)
+			return true;
+	return false;
+}
+
 static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			struct sk_buff **to_free)
 {
@@ -329,6 +342,10 @@ static int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps,
 		NL_SET_ERR_MSG_MOD(extack, "default virtual queue above virtual queue count");
 		return -EINVAL;
 	}
+	if (sopt->flags && gred_per_vq_red_flags_used(table)) {
+		NL_SET_ERR_MSG_MOD(extack, "can't set per-Qdisc RED flags when per-virtual queue flags are used");
+		return -EINVAL;
+	}
 
 	sch_tree_lock(sch);
 	table->DPs = sopt->DPs;
@@ -410,15 +427,127 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp,
 	return 0;
 }
 
+static const struct nla_policy gred_vq_policy[TCA_GRED_VQ_MAX + 1] = {
+	[TCA_GRED_VQ_DP]	= { .type = NLA_U32 },
+	[TCA_GRED_VQ_FLAGS]	= { .type = NLA_U32 },
+};
+
+static const struct nla_policy gred_vqe_policy[TCA_GRED_VQ_ENTRY_MAX + 1] = {
+	[TCA_GRED_VQ_ENTRY]	= { .type = NLA_NESTED },
+};
+
 static const struct nla_policy gred_policy[TCA_GRED_MAX + 1] = {
 	[TCA_GRED_PARMS]	= { .len = sizeof(struct tc_gred_qopt) },
 	[TCA_GRED_STAB]		= { .len = 256 },
 	[TCA_GRED_DPS]		= { .len = sizeof(struct tc_gred_sopt) },
 	[TCA_GRED_MAX_P]	= { .type = NLA_U32 },
 	[TCA_GRED_LIMIT]	= { .type = NLA_U32 },
-	[TCA_GRED_VQ_LIST]	= { .type = NLA_REJECT },
+	[TCA_GRED_VQ_LIST]	= { .type = NLA_NESTED },
 };
 
+static void gred_vq_apply(struct gred_sched *table, const struct nlattr *entry)
+{
+	struct nlattr *tb[TCA_GRED_VQ_MAX + 1];
+	u32 dp;
+
+	nla_parse_nested(tb, TCA_GRED_VQ_MAX, entry, gred_vq_policy, NULL);
+
+	dp = nla_get_u32(tb[TCA_GRED_VQ_DP]);
+
+	if (tb[TCA_GRED_VQ_FLAGS])
+		table->tab[dp]->red_flags = nla_get_u32(tb[TCA_GRED_VQ_FLAGS]);
+}
+
+static void gred_vqs_apply(struct gred_sched *table, struct nlattr *vqs)
+{
+	const struct nlattr *attr;
+	int rem;
+
+	nla_for_each_nested(attr, vqs, rem) {
+		switch (nla_type(attr)) {
+		case TCA_GRED_VQ_ENTRY:
+			gred_vq_apply(table, attr);
+			break;
+		}
+	}
+}
+
+static int gred_vq_validate(struct gred_sched *table, u32 cdp,
+			    const struct nlattr *entry,
+			    struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_GRED_VQ_MAX + 1];
+	int err;
+	u32 dp;
+
+	err = nla_parse_nested(tb, TCA_GRED_VQ_MAX, entry, gred_vq_policy,
+			       extack);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_GRED_VQ_DP]) {
+		NL_SET_ERR_MSG_MOD(extack, "Virtual queue with no index specified");
+		return -EINVAL;
+	}
+	dp = nla_get_u32(tb[TCA_GRED_VQ_DP]);
+	if (dp >= table->DPs) {
+		NL_SET_ERR_MSG_MOD(extack, "Virtual queue with index out of bounds");
+		return -EINVAL;
+	}
+	if (dp != cdp && !table->tab[dp]) {
+		NL_SET_ERR_MSG_MOD(extack, "Virtual queue not yet instantiated");
+		return -EINVAL;
+	}
+
+	if (tb[TCA_GRED_VQ_FLAGS]) {
+		u32 red_flags = nla_get_u32(tb[TCA_GRED_VQ_FLAGS]);
+
+		if (table->red_flags && table->red_flags != red_flags) {
+			NL_SET_ERR_MSG_MOD(extack, "can't change per-virtual queue RED flags when per-Qdisc flags are used");
+			return -EINVAL;
+		}
+		if (red_flags & ~GRED_VQ_RED_FLAGS) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "invalid RED flags specified");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int gred_vqs_validate(struct gred_sched *table, u32 cdp,
+			     struct nlattr *vqs, struct netlink_ext_ack *extack)
+{
+	const struct nlattr *attr;
+	int rem, err;
+
+	err = nla_validate_nested(vqs, TCA_GRED_VQ_ENTRY_MAX,
+				  gred_vqe_policy, extack);
+	if (err < 0)
+		return err;
+
+	nla_for_each_nested(attr, vqs, rem) {
+		switch (nla_type(attr)) {
+		case TCA_GRED_VQ_ENTRY:
+			err = gred_vq_validate(table, cdp, attr, extack);
+			if (err)
+				return err;
+			break;
+		default:
+			NL_SET_ERR_MSG_MOD(extack, "GRED_VQ_LIST can contain only entry attributes");
+			return -EINVAL;
+		}
+	}
+
+	if (rem > 0) {
+		NL_SET_ERR_MSG_MOD(extack, "Trailing data after parsing virtual queue list");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 		       struct netlink_ext_ack *extack)
 {
@@ -460,6 +589,13 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 		return -EINVAL;
 	}
 
+	if (tb[TCA_GRED_VQ_LIST]) {
+		err = gred_vqs_validate(table, ctl->DP, tb[TCA_GRED_VQ_LIST],
+					extack);
+		if (err)
+			return err;
+	}
+
 	if (gred_rio_mode(table)) {
 		if (ctl->prio == 0) {
 			int def_prio = GRED_DEF_PRIO;
@@ -483,6 +619,9 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 	if (err < 0)
 		goto err_unlock_free;
 
+	if (tb[TCA_GRED_VQ_LIST])
+		gred_vqs_apply(table, tb[TCA_GRED_VQ_LIST]);
+
 	if (gred_rio_mode(table)) {
 		gred_disable_wred_mode(table);
 		if (gred_wred_mode_check(sch))
@@ -627,6 +766,9 @@ append_opt:
 		if (nla_put_u32(skb, TCA_GRED_VQ_DP, q->DP))
 			goto nla_put_failure;
 
+		if (nla_put_u32(skb, TCA_GRED_VQ_FLAGS, q->red_flags))
+			goto nla_put_failure;
+
 		/* Stats */
 		if (nla_put_u64_64bit(skb, TCA_GRED_VQ_STAT_BYTES, q->bytesin,
 				      TCA_GRED_VQ_PAD))
-- 
cgit v1.2.3


From e4dab1e6ea64376ebd3b59281ecaaeb788116be3 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 15 Nov 2018 17:43:09 +0800
Subject: vhost_net: mitigate page reference counting during page frag refill

We do a get_page() which involves a atomic operation. This patch tries
to mitigate a per packet atomic operation by maintaining a reference
bias which is initially USHRT_MAX. Each time a page is got, instead of
calling get_page() we decrease the bias and when we find it's time to
use a new page we will decrease the bias at one time through
__page_cache_drain_cache().

Testpmd(virtio_user + vhost_net) + XDP_DROP on TAP shows about 1.6%
improvement.

Before: 4.63Mpps
After:  4.71Mpps

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 51 insertions(+), 3 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index ab11b2bee273..d919284f103b 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -141,6 +141,10 @@ struct vhost_net {
 	unsigned tx_zcopy_err;
 	/* Flush in progress. Protected by tx vq lock. */
 	bool tx_flush;
+	/* Private page frag */
+	struct page_frag page_frag;
+	/* Refcount bias of page frag */
+	int refcnt_bias;
 };
 
 static unsigned vhost_net_zcopy_mask __read_mostly;
@@ -637,14 +641,53 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len)
 	       !vhost_vq_avail_empty(vq->dev, vq);
 }
 
+#define SKB_FRAG_PAGE_ORDER     get_order(32768)
+
+static bool vhost_net_page_frag_refill(struct vhost_net *net, unsigned int sz,
+				       struct page_frag *pfrag, gfp_t gfp)
+{
+	if (pfrag->page) {
+		if (pfrag->offset + sz <= pfrag->size)
+			return true;
+		__page_frag_cache_drain(pfrag->page, net->refcnt_bias);
+	}
+
+	pfrag->offset = 0;
+	net->refcnt_bias = 0;
+	if (SKB_FRAG_PAGE_ORDER) {
+		/* Avoid direct reclaim but allow kswapd to wake */
+		pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) |
+					  __GFP_COMP | __GFP_NOWARN |
+					  __GFP_NORETRY,
+					  SKB_FRAG_PAGE_ORDER);
+		if (likely(pfrag->page)) {
+			pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER;
+			goto done;
+		}
+	}
+	pfrag->page = alloc_page(gfp);
+	if (likely(pfrag->page)) {
+		pfrag->size = PAGE_SIZE;
+		goto done;
+	}
+	return false;
+
+done:
+	net->refcnt_bias = USHRT_MAX;
+	page_ref_add(pfrag->page, USHRT_MAX - 1);
+	return true;
+}
+
 #define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD)
 
 static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 			       struct iov_iter *from)
 {
 	struct vhost_virtqueue *vq = &nvq->vq;
+	struct vhost_net *net = container_of(vq->dev, struct vhost_net,
+					     dev);
 	struct socket *sock = vq->private_data;
-	struct page_frag *alloc_frag = &current->task_frag;
+	struct page_frag *alloc_frag = &net->page_frag;
 	struct virtio_net_hdr *gso;
 	struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp];
 	struct tun_xdp_hdr *hdr;
@@ -665,7 +708,8 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 
 	buflen += SKB_DATA_ALIGN(len + pad);
 	alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES);
-	if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL)))
+	if (unlikely(!vhost_net_page_frag_refill(net, buflen,
+						 alloc_frag, GFP_KERNEL)))
 		return -ENOMEM;
 
 	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
@@ -703,7 +747,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 	xdp->data_end = xdp->data + len;
 	hdr->buflen = buflen;
 
-	get_page(alloc_frag->page);
+	--net->refcnt_bias;
 	alloc_frag->offset += buflen;
 
 	++nvq->batched_xdp;
@@ -1292,6 +1336,8 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev);
 
 	f->private_data = n;
+	n->page_frag.page = NULL;
+	n->refcnt_bias = 0;
 
 	return 0;
 }
@@ -1366,6 +1412,8 @@ static int vhost_net_release(struct inode *inode, struct file *f)
 	kfree(n->vqs[VHOST_NET_VQ_RX].rxq.queue);
 	kfree(n->vqs[VHOST_NET_VQ_TX].xdp);
 	kfree(n->dev.vqs);
+	if (n->page_frag.page)
+		__page_frag_cache_drain(n->page_frag.page, n->refcnt_bias);
 	kvfree(n);
 	return 0;
 }
-- 
cgit v1.2.3


From f9e06c45cb28beb30a6a474952ead7da2b8940f3 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 15 Nov 2018 17:43:10 +0800
Subject: tuntap: free XDP dropped packets in a batch

Thanks to the batched XDP buffs through msg_control. Instead of
calling put_page() for each page which involves a atomic operation,
let's batch them by record the last page that needs to be freed and
its refcnt count and free them in a batch.

Testpmd(virtio-user + vhost_net) + XDP_DROP shows 3.8% improvement.

Before: 4.71Mpps
After : 4.89Mpps

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a65779c6d72f..e90a7923a5f6 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -188,6 +188,11 @@ struct tun_file {
 	struct xdp_rxq_info xdp_rxq;
 };
 
+struct tun_page {
+	struct page *page;
+	int count;
+};
+
 struct tun_flow_entry {
 	struct hlist_node hash_link;
 	struct rcu_head rcu;
@@ -2377,9 +2382,16 @@ static void tun_sock_write_space(struct sock *sk)
 	kill_fasync(&tfile->fasync, SIGIO, POLL_OUT);
 }
 
+static void tun_put_page(struct tun_page *tpage)
+{
+	if (tpage->page)
+		__page_frag_cache_drain(tpage->page, tpage->count);
+}
+
 static int tun_xdp_one(struct tun_struct *tun,
 		       struct tun_file *tfile,
-		       struct xdp_buff *xdp, int *flush)
+		       struct xdp_buff *xdp, int *flush,
+		       struct tun_page *tpage)
 {
 	struct tun_xdp_hdr *hdr = xdp->data_hard_start;
 	struct virtio_net_hdr *gso = &hdr->gso;
@@ -2390,6 +2402,7 @@ static int tun_xdp_one(struct tun_struct *tun,
 	int buflen = hdr->buflen;
 	int err = 0;
 	bool skb_xdp = false;
+	struct page *page;
 
 	xdp_prog = rcu_dereference(tun->xdp_prog);
 	if (xdp_prog) {
@@ -2416,7 +2429,14 @@ static int tun_xdp_one(struct tun_struct *tun,
 		case XDP_PASS:
 			break;
 		default:
-			put_page(virt_to_head_page(xdp->data));
+			page = virt_to_head_page(xdp->data);
+			if (tpage->page == page) {
+				++tpage->count;
+			} else {
+				tun_put_page(tpage);
+				tpage->page = page;
+				tpage->count = 1;
+			}
 			return 0;
 		}
 	}
@@ -2480,6 +2500,7 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 		return -EBADFD;
 
 	if (ctl && (ctl->type == TUN_MSG_PTR)) {
+		struct tun_page tpage = {0};
 		int n = ctl->num;
 		int flush = 0;
 
@@ -2488,7 +2509,7 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 
 		for (i = 0; i < n; i++) {
 			xdp = &((struct xdp_buff *)ctl->ptr)[i];
-			tun_xdp_one(tun, tfile, xdp, &flush);
+			tun_xdp_one(tun, tfile, xdp, &flush, &tpage);
 		}
 
 		if (flush)
@@ -2497,6 +2518,8 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 		rcu_read_unlock();
 		local_bh_enable();
 
+		tun_put_page(&tpage);
+
 		ret = total_len;
 		goto out;
 	}
-- 
cgit v1.2.3


From 6f0271d92963bc8588ad7058622ec7b1e94852de Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 17 Nov 2018 16:53:46 -0800
Subject: tun: Adjust on-stack tun_page initialization.

Instead of constantly playing with the struct initializer
syntax trying to make gcc and CLang both happy, just clear
it out using memset().

>> drivers/net/tun.c:2503:42: warning: Using plain integer as NULL pointer

Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e90a7923a5f6..36163a147d39 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2500,10 +2500,12 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 		return -EBADFD;
 
 	if (ctl && (ctl->type == TUN_MSG_PTR)) {
-		struct tun_page tpage = {0};
+		struct tun_page tpage;
 		int n = ctl->num;
 		int flush = 0;
 
+		memset(&tpage, 0, sizeof(tpage));
+
 		local_bh_disable();
 		rcu_read_lock();
 
-- 
cgit v1.2.3


From 54e8cb786130949a4d37792383cb528176771e5d Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Thu, 15 Nov 2018 15:26:51 -0800
Subject: uapi/ethtool: fix spelling errors

Trivial spelling errors found by codespell.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ethtool.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index c8f8e2455bf3..17be76aeb468 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -882,7 +882,7 @@ struct ethtool_rx_flow_spec {
 	__u32		location;
 };
 
-/* How rings are layed out when accessing virtual functions or
+/* How rings are laid out when accessing virtual functions or
  * offloaded queues is device specific. To allow users to do flow
  * steering and specify these queues the ring cookie is partitioned
  * into a 32bit queue index with an 8 bit virtual function id.
@@ -891,7 +891,7 @@ struct ethtool_rx_flow_spec {
  * devices start supporting PCIe w/ARI. However at the moment I
  * do not know of any devices that support this so I do not reserve
  * space for this at this time. If a future patch consumes the next
- * byte it should be aware of this possiblity.
+ * byte it should be aware of this possibility.
  */
 #define ETHTOOL_RX_FLOW_SPEC_RING	0x00000000FFFFFFFFLL
 #define ETHTOOL_RX_FLOW_SPEC_RING_VF	0x000000FF00000000LL
-- 
cgit v1.2.3


From e8bd8fca6773ef49390269bd467bf940a0841ccf Mon Sep 17 00:00:00 2001
From: Yousuk Seung <ysseung@google.com>
Date: Thu, 15 Nov 2018 16:44:12 -0800
Subject: tcp: add SRTT to SCM_TIMESTAMPING_OPT_STATS

Add TCP_NLA_SRTT to SCM_TIMESTAMPING_OPT_STATS that reports the smoothed
round trip time in microseconds (tcp_sock.srtt_us >> 3).

Signed-off-by: Yousuk Seung <ysseung@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tcp.h | 1 +
 net/ipv4/tcp.c           | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index e02d31986ff9..8bb6cc5f3235 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -266,6 +266,7 @@ enum {
 	TCP_NLA_BYTES_RETRANS,	/* Data bytes retransmitted */
 	TCP_NLA_DSACK_DUPS,	/* DSACK blocks received */
 	TCP_NLA_REORD_SEEN,	/* reordering events seen */
+	TCP_NLA_SRTT,		/* smoothed RTT in usecs */
 };
 
 /* for TCP_MD5SIG socket option */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ca2b08c0b4a0..252048776dbb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3242,6 +3242,7 @@ static size_t tcp_opt_stats_get_size(void)
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */
 		0;
 }
 
@@ -3295,6 +3296,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 			  TCP_NLA_PAD);
 	nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups);
 	nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen);
+	nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3);
 
 	return stats;
 }
-- 
cgit v1.2.3


From 2391b0030e241386d710df10e53e2cfc3c5d4fc1 Mon Sep 17 00:00:00 2001
From: Arjun Vynipadath <arjun@chelsio.com>
Date: Fri, 16 Nov 2018 09:15:42 +0530
Subject: cxgb4: Remove SGE_HOST_PAGE_SIZE dependency on page size

The SGE Host Page Size has nothing to do with the actual
Host Page Size. It's the SGE's BAR2 Doorbell/GTS Page Size
for interpreting the SGE Ingress/Egress Queue per Page values.
Firmware reads all of these things and makes all the
subsequent changes necessary. The Host Driver uses the SGE
Host Page Size in order to properly calculate BAR2 Offsets.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Arjun Vynipadath <arjun@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index cb523949c812..fc6a08789835 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -7141,21 +7141,10 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
 			 unsigned int cache_line_size)
 {
 	unsigned int page_shift = fls(page_size) - 1;
-	unsigned int sge_hps = page_shift - 10;
 	unsigned int stat_len = cache_line_size > 64 ? 128 : 64;
 	unsigned int fl_align = cache_line_size < 32 ? 32 : cache_line_size;
 	unsigned int fl_align_log = fls(fl_align) - 1;
 
-	t4_write_reg(adap, SGE_HOST_PAGE_SIZE_A,
-		     HOSTPAGESIZEPF0_V(sge_hps) |
-		     HOSTPAGESIZEPF1_V(sge_hps) |
-		     HOSTPAGESIZEPF2_V(sge_hps) |
-		     HOSTPAGESIZEPF3_V(sge_hps) |
-		     HOSTPAGESIZEPF4_V(sge_hps) |
-		     HOSTPAGESIZEPF5_V(sge_hps) |
-		     HOSTPAGESIZEPF6_V(sge_hps) |
-		     HOSTPAGESIZEPF7_V(sge_hps));
-
 	if (is_t4(adap->params.chip)) {
 		t4_set_reg_field(adap, SGE_CONTROL_A,
 				 INGPADBOUNDARY_V(INGPADBOUNDARY_M) |
-- 
cgit v1.2.3


From 60ab49bfe4fa576c5b1d98b9dfc523bfcb3c610c Mon Sep 17 00:00:00 2001
From: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Date: Fri, 16 Nov 2018 15:51:54 +1100
Subject: net/ncsi: Don't enable all channels when HWA available

NCSI hardware arbitration allows multiple packages to be enabled at once
and share the same wiring. If the NCSI driver recognises that HWA is
available it unconditionally enables all packages and channels; but that
is a configuration decision rather than something required by HWA.
Additionally the current implementation will not failover on link events
which can cause connectivity to be lost unless the interface is manually
bounced.

Retain basic HWA support but remove the separate configuration path to
enable all channels, leaving this to be handled by a later
implementation.

Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ncsi/ncsi-aen.c    |  3 +--
 net/ncsi/ncsi-manage.c | 50 ++++----------------------------------------------
 2 files changed, 5 insertions(+), 48 deletions(-)

diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index 25e483e8278b..65f47a648be3 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -86,8 +86,7 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
 	    !(state == NCSI_CHANNEL_ACTIVE && !(data & 0x1)))
 		return 0;
 
-	if (!(ndp->flags & NCSI_DEV_HWA) &&
-	    state == NCSI_CHANNEL_ACTIVE)
+	if (state == NCSI_CHANNEL_ACTIVE)
 		ndp->flags |= NCSI_DEV_RESHUFFLE;
 
 	ncsi_stop_channel_monitor(nc);
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index bfc43b28c7a6..d4e6e0f99097 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -113,10 +113,8 @@ static void ncsi_channel_monitor(struct timer_list *t)
 	default:
 		netdev_err(ndp->ndev.dev, "NCSI Channel %d timed out!\n",
 			   nc->id);
-		if (!(ndp->flags & NCSI_DEV_HWA)) {
-			ncsi_report_link(ndp, true);
-			ndp->flags |= NCSI_DEV_RESHUFFLE;
-		}
+		ncsi_report_link(ndp, true);
+		ndp->flags |= NCSI_DEV_RESHUFFLE;
 
 		ncsi_stop_channel_monitor(nc);
 
@@ -1050,35 +1048,6 @@ static bool ncsi_check_hwa(struct ncsi_dev_priv *ndp)
 	return false;
 }
 
-static int ncsi_enable_hwa(struct ncsi_dev_priv *ndp)
-{
-	struct ncsi_package *np;
-	struct ncsi_channel *nc;
-	unsigned long flags;
-
-	/* Move all available channels to processing queue */
-	spin_lock_irqsave(&ndp->lock, flags);
-	NCSI_FOR_EACH_PACKAGE(ndp, np) {
-		NCSI_FOR_EACH_CHANNEL(np, nc) {
-			WARN_ON_ONCE(nc->state != NCSI_CHANNEL_INACTIVE ||
-				     !list_empty(&nc->link));
-			ncsi_stop_channel_monitor(nc);
-			list_add_tail_rcu(&nc->link, &ndp->channel_queue);
-		}
-	}
-	spin_unlock_irqrestore(&ndp->lock, flags);
-
-	/* We can have no channels in extremely case */
-	if (list_empty(&ndp->channel_queue)) {
-		netdev_err(ndp->ndev.dev,
-			   "NCSI: No available channels for HWA\n");
-		ncsi_report_link(ndp, false);
-		return -ENOENT;
-	}
-
-	return ncsi_process_next_channel(ndp);
-}
-
 static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 {
 	struct ncsi_dev *nd = &ndp->ndev;
@@ -1156,10 +1125,7 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 		 */
 		if (!ndp->active_package) {
 			ndp->flags |= NCSI_DEV_PROBED;
-			if (ncsi_check_hwa(ndp))
-				ncsi_enable_hwa(ndp);
-			else
-				ncsi_choose_active_channel(ndp);
+			ncsi_choose_active_channel(ndp);
 			return;
 		}
 
@@ -1592,7 +1558,6 @@ EXPORT_SYMBOL_GPL(ncsi_register_dev);
 int ncsi_start_dev(struct ncsi_dev *nd)
 {
 	struct ncsi_dev_priv *ndp = TO_NCSI_DEV_PRIV(nd);
-	int ret;
 
 	if (nd->state != ncsi_dev_state_registered &&
 	    nd->state != ncsi_dev_state_functional)
@@ -1604,14 +1569,7 @@ int ncsi_start_dev(struct ncsi_dev *nd)
 		return 0;
 	}
 
-	if (ndp->flags & NCSI_DEV_HWA) {
-		netdev_info(ndp->ndev.dev, "NCSI: Enabling HWA mode\n");
-		ret = ncsi_enable_hwa(ndp);
-	} else {
-		ret = ncsi_choose_active_channel(ndp);
-	}
-
-	return ret;
+	return ncsi_choose_active_channel(ndp);
 }
 EXPORT_SYMBOL_GPL(ncsi_start_dev);
 
-- 
cgit v1.2.3


From 8e13f70be05ee49985dfc3c766868bc85ed43b8a Mon Sep 17 00:00:00 2001
From: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Date: Fri, 16 Nov 2018 15:51:55 +1100
Subject: net/ncsi: Probe single packages to avoid conflict

Currently the NCSI driver sends a select-package command to all possible
packages simultaneously to discover what packages are available. However
at this stage in the probe process the driver does not know if
hardware arbitration is available: if it isn't then this process could
cause collisions on the RMII bus when packages try to respond.

Update the probe loop to probe each package one by one, and once
complete check if HWA is universally supported.

Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ncsi/internal.h    |  1 +
 net/ncsi/ncsi-manage.c | 85 ++++++++++++++++++--------------------------------
 2 files changed, 31 insertions(+), 55 deletions(-)

diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index 1dae77c54009..ec65778c41f3 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -292,6 +292,7 @@ struct ncsi_dev_priv {
 #if IS_ENABLED(CONFIG_IPV6)
 	unsigned int        inet6_addr_num;  /* Number of IPv6 addresses   */
 #endif
+	unsigned int        package_probe_id;/* Current ID during probe    */
 	unsigned int        package_num;     /* Number of packages         */
 	struct list_head    packages;        /* List of packages           */
 	struct ncsi_channel *hot_channel;    /* Channel was ever active    */
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index d4e6e0f99097..02421d1a22c9 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -1079,67 +1079,28 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 		nd->state = ncsi_dev_state_probe_package;
 		break;
 	case ncsi_dev_state_probe_package:
-		ndp->pending_req_num = 16;
+		ndp->pending_req_num = 1;
 
-		/* Select all possible packages */
 		nca.type = NCSI_PKT_CMD_SP;
 		nca.bytes[0] = 1;
+		nca.package = ndp->package_probe_id;
 		nca.channel = NCSI_RESERVED_CHANNEL;
-		for (index = 0; index < 8; index++) {
-			nca.package = index;
-			ret = ncsi_xmit_cmd(&nca);
-			if (ret)
-				goto error;
-		}
-
-		/* Disable all possible packages */
-		nca.type = NCSI_PKT_CMD_DP;
-		for (index = 0; index < 8; index++) {
-			nca.package = index;
-			ret = ncsi_xmit_cmd(&nca);
-			if (ret)
-				goto error;
-		}
-
+		ret = ncsi_xmit_cmd(&nca);
+		if (ret)
+			goto error;
 		nd->state = ncsi_dev_state_probe_channel;
 		break;
 	case ncsi_dev_state_probe_channel:
-		if (!ndp->active_package)
-			ndp->active_package = list_first_or_null_rcu(
-				&ndp->packages, struct ncsi_package, node);
-		else if (list_is_last(&ndp->active_package->node,
-				      &ndp->packages))
-			ndp->active_package = NULL;
-		else
-			ndp->active_package = list_next_entry(
-				ndp->active_package, node);
-
-		/* All available packages and channels are enumerated. The
-		 * enumeration happens for once when the NCSI interface is
-		 * started. So we need continue to start the interface after
-		 * the enumeration.
-		 *
-		 * We have to choose an active channel before configuring it.
-		 * Note that we possibly don't have active channel in extreme
-		 * situation.
-		 */
+		ndp->active_package = ncsi_find_package(ndp,
+							ndp->package_probe_id);
 		if (!ndp->active_package) {
-			ndp->flags |= NCSI_DEV_PROBED;
-			ncsi_choose_active_channel(ndp);
-			return;
+			/* No response */
+			nd->state = ncsi_dev_state_probe_dp;
+			schedule_work(&ndp->work);
+			break;
 		}
-
-		/* Select the active package */
-		ndp->pending_req_num = 1;
-		nca.type = NCSI_PKT_CMD_SP;
-		nca.bytes[0] = 1;
-		nca.package = ndp->active_package->id;
-		nca.channel = NCSI_RESERVED_CHANNEL;
-		ret = ncsi_xmit_cmd(&nca);
-		if (ret)
-			goto error;
-
 		nd->state = ncsi_dev_state_probe_cis;
+		schedule_work(&ndp->work);
 		break;
 	case ncsi_dev_state_probe_cis:
 		ndp->pending_req_num = NCSI_RESERVED_CHANNEL;
@@ -1188,22 +1149,35 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 	case ncsi_dev_state_probe_dp:
 		ndp->pending_req_num = 1;
 
-		/* Deselect the active package */
+		/* Deselect the current package */
 		nca.type = NCSI_PKT_CMD_DP;
-		nca.package = ndp->active_package->id;
+		nca.package = ndp->package_probe_id;
 		nca.channel = NCSI_RESERVED_CHANNEL;
 		ret = ncsi_xmit_cmd(&nca);
 		if (ret)
 			goto error;
 
-		/* Scan channels in next package */
-		nd->state = ncsi_dev_state_probe_channel;
+		/* Probe next package */
+		ndp->package_probe_id++;
+		if (ndp->package_probe_id >= 8) {
+			/* Probe finished */
+			ndp->flags |= NCSI_DEV_PROBED;
+			break;
+		}
+		nd->state = ncsi_dev_state_probe_package;
+		ndp->active_package = NULL;
 		break;
 	default:
 		netdev_warn(nd->dev, "Wrong NCSI state 0x%0x in enumeration\n",
 			    nd->state);
 	}
 
+	if (ndp->flags & NCSI_DEV_PROBED) {
+		/* Check if all packages have HWA support */
+		ncsi_check_hwa(ndp);
+		ncsi_choose_active_channel(ndp);
+	}
+
 	return;
 error:
 	netdev_err(ndp->ndev.dev,
@@ -1564,6 +1538,7 @@ int ncsi_start_dev(struct ncsi_dev *nd)
 		return -ENOTTY;
 
 	if (!(ndp->flags & NCSI_DEV_PROBED)) {
+		ndp->package_probe_id = 0;
 		nd->state = ncsi_dev_state_probe;
 		schedule_work(&ndp->work);
 		return 0;
-- 
cgit v1.2.3


From cd09ab095c6dc4b2b0860f968a0f3ae8d752e76a Mon Sep 17 00:00:00 2001
From: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Date: Fri, 16 Nov 2018 15:51:56 +1100
Subject: net/ncsi: Don't deselect package in suspend if active

When a package is deselected all channels of that package cease
communication. If there are other channels active on the package of the
suspended channel this will disable them as well, so only send a
deselect-package command if no other channels are active.

Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ncsi/ncsi-manage.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 02421d1a22c9..b8b4e765a04c 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -440,12 +440,14 @@ static void ncsi_request_timeout(struct timer_list *t)
 static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
 {
 	struct ncsi_dev *nd = &ndp->ndev;
-	struct ncsi_package *np = ndp->active_package;
-	struct ncsi_channel *nc = ndp->active_channel;
+	struct ncsi_package *np;
+	struct ncsi_channel *nc, *tmp;
 	struct ncsi_cmd_arg nca;
 	unsigned long flags;
 	int ret;
 
+	np = ndp->active_package;
+	nc = ndp->active_channel;
 	nca.ndp = ndp;
 	nca.req_flags = NCSI_REQ_FLAG_EVENT_DRIVEN;
 	switch (nd->state) {
@@ -521,6 +523,15 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
 		if (ret)
 			goto error;
 
+		NCSI_FOR_EACH_CHANNEL(np, tmp) {
+			/* If there is another channel active on this package
+			 * do not deselect the package.
+			 */
+			if (tmp != nc && tmp->state == NCSI_CHANNEL_ACTIVE) {
+				nd->state = ncsi_dev_state_suspend_done;
+				break;
+			}
+		}
 		break;
 	case ncsi_dev_state_suspend_deselect:
 		ndp->pending_req_num = 1;
-- 
cgit v1.2.3


From 0b970e1b040c10d0e2a252943a2feaa6ee3cacdf Mon Sep 17 00:00:00 2001
From: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Date: Fri, 16 Nov 2018 15:51:57 +1100
Subject: net/ncsi: Don't mark configured channels inactive

The concepts of a channel being 'active' and it having link are slightly
muddled in the NCSI driver. Tweak this slightly so that
NCSI_CHANNEL_ACTIVE represents a channel that has been configured and
enabled, and NCSI_CHANNEL_INACTIVE represents a de-configured channel.
This distinction is important because a channel can be 'active' but have
its link down; in this case the channel may still need to be configured
so that it may receive AEN link-state-change packets.

Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ncsi/ncsi-aen.c    | 17 +++++++++++------
 net/ncsi/ncsi-manage.c |  3 +--
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index 65f47a648be3..57f77e5d381a 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -57,6 +57,7 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
 	int state;
 	unsigned long old_data, data;
 	unsigned long flags;
+	bool had_link, has_link;
 
 	/* Find the NCSI channel */
 	ncsi_find_package_and_channel(ndp, h->common.channel, NULL, &nc);
@@ -73,6 +74,9 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
 	ncm->data[2] = data;
 	ncm->data[4] = ntohl(lsc->oem_status);
 
+	had_link = !!(old_data & 0x1);
+	has_link = !!(data & 0x1);
+
 	netdev_dbg(ndp->ndev.dev, "NCSI: LSC AEN - channel %u state %s\n",
 		   nc->id, data & 0x1 ? "up" : "down");
 
@@ -80,15 +84,16 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
 	state = nc->state;
 	spin_unlock_irqrestore(&nc->lock, flags);
 
-	if (!((old_data ^ data) & 0x1) || chained)
-		return 0;
-	if (!(state == NCSI_CHANNEL_INACTIVE && (data & 0x1)) &&
-	    !(state == NCSI_CHANNEL_ACTIVE && !(data & 0x1)))
+	if (state == NCSI_CHANNEL_INACTIVE)
+		netdev_warn(ndp->ndev.dev,
+			    "NCSI: Inactive channel %u received AEN!\n",
+			    nc->id);
+
+	if ((had_link == has_link) || chained)
 		return 0;
 
-	if (state == NCSI_CHANNEL_ACTIVE)
+	if (had_link)
 		ndp->flags |= NCSI_DEV_RESHUFFLE;
-
 	ncsi_stop_channel_monitor(nc);
 	spin_lock_irqsave(&ndp->lock, flags);
 	list_add_tail_rcu(&nc->link, &ndp->channel_queue);
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index b8b4e765a04c..b9de5b78c4e9 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -916,12 +916,11 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 			break;
 		}
 
+		nc->state = NCSI_CHANNEL_ACTIVE;
 		if (nc->modes[NCSI_MODE_LINK].data[2] & 0x1) {
 			hot_nc = nc;
-			nc->state = NCSI_CHANNEL_ACTIVE;
 		} else {
 			hot_nc = NULL;
-			nc->state = NCSI_CHANNEL_INACTIVE;
 			netdev_dbg(ndp->ndev.dev,
 				   "NCSI: channel %u link down after config\n",
 				   nc->id);
-- 
cgit v1.2.3


From 2878a2cfe57a5db21844801cf502fe535a3134b2 Mon Sep 17 00:00:00 2001
From: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Date: Fri, 16 Nov 2018 15:51:58 +1100
Subject: net/ncsi: Reset channel state in ncsi_start_dev()

When the NCSI driver is stopped with ncsi_stop_dev() the channel
monitors are stopped and the state set to "inactive". However the
channels are still configured and active from the perspective of the
network controller. We should suspend each active channel but in the
context of ncsi_stop_dev() the transmit queue has been or is about to be
stopped so we won't have time to do so.

Instead when ncsi_start_dev() is called if the NCSI topology has already
been probed then call ncsi_reset_dev() to suspend any channels that were
previously active. This resets the network controller to a known state,
provides an up to date view of channel link state, and makes sure that
mode flags such as NCSI_MODE_TX_ENABLE are properly reset.

In addition to ncsi_start_dev() use ncsi_reset_dev() in ncsi-netlink.c
to update the channel configuration more cleanly.

Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ncsi/internal.h     |   2 +
 net/ncsi/ncsi-manage.c  | 111 +++++++++++++++++++++++++++++++++++++++++++++---
 net/ncsi/ncsi-netlink.c |  12 +++---
 3 files changed, 113 insertions(+), 12 deletions(-)

diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index ec65778c41f3..bda51cb179fe 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -287,6 +287,7 @@ struct ncsi_dev_priv {
 #define NCSI_DEV_PROBED		1            /* Finalized NCSI topology    */
 #define NCSI_DEV_HWA		2            /* Enabled HW arbitration     */
 #define NCSI_DEV_RESHUFFLE	4
+#define NCSI_DEV_RESET		8            /* Reset state of NC          */
 	unsigned int        gma_flag;        /* OEM GMA flag               */
 	spinlock_t          lock;            /* Protect the NCSI device    */
 #if IS_ENABLED(CONFIG_IPV6)
@@ -342,6 +343,7 @@ extern spinlock_t ncsi_dev_lock;
 	list_for_each_entry_rcu(nc, &np->channels, node)
 
 /* Resources */
+int ncsi_reset_dev(struct ncsi_dev *nd);
 void ncsi_start_channel_monitor(struct ncsi_channel *nc);
 void ncsi_stop_channel_monitor(struct ncsi_channel *nc);
 struct ncsi_channel *ncsi_find_channel(struct ncsi_package *np,
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index b9de5b78c4e9..c814ce9bb3de 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -550,8 +550,10 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
 		spin_lock_irqsave(&nc->lock, flags);
 		nc->state = NCSI_CHANNEL_INACTIVE;
 		spin_unlock_irqrestore(&nc->lock, flags);
-		ncsi_process_next_channel(ndp);
-
+		if (ndp->flags & NCSI_DEV_RESET)
+			ncsi_reset_dev(nd);
+		else
+			ncsi_process_next_channel(ndp);
 		break;
 	default:
 		netdev_warn(nd->dev, "Wrong NCSI state 0x%x in suspend\n",
@@ -898,6 +900,16 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 		netdev_dbg(ndp->ndev.dev, "NCSI: channel %u config done\n",
 			   nc->id);
 		spin_lock_irqsave(&nc->lock, flags);
+		nc->state = NCSI_CHANNEL_ACTIVE;
+
+		if (ndp->flags & NCSI_DEV_RESET) {
+			/* A reset event happened during config, start it now */
+			nc->reconfigure_needed = false;
+			spin_unlock_irqrestore(&nc->lock, flags);
+			ncsi_reset_dev(nd);
+			break;
+		}
+
 		if (nc->reconfigure_needed) {
 			/* This channel's configuration has been updated
 			 * part-way during the config state - start the
@@ -916,7 +928,6 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 			break;
 		}
 
-		nc->state = NCSI_CHANNEL_ACTIVE;
 		if (nc->modes[NCSI_MODE_LINK].data[2] & 0x1) {
 			hot_nc = nc;
 		} else {
@@ -1554,7 +1565,7 @@ int ncsi_start_dev(struct ncsi_dev *nd)
 		return 0;
 	}
 
-	return ncsi_choose_active_channel(ndp);
+	return ncsi_reset_dev(nd);
 }
 EXPORT_SYMBOL_GPL(ncsi_start_dev);
 
@@ -1567,7 +1578,10 @@ void ncsi_stop_dev(struct ncsi_dev *nd)
 	int old_state;
 	unsigned long flags;
 
-	/* Stop the channel monitor and reset channel's state */
+	/* Stop the channel monitor on any active channels. Don't reset the
+	 * channel state so we know which were active when ncsi_start_dev()
+	 * is next called.
+	 */
 	NCSI_FOR_EACH_PACKAGE(ndp, np) {
 		NCSI_FOR_EACH_CHANNEL(np, nc) {
 			ncsi_stop_channel_monitor(nc);
@@ -1575,7 +1589,6 @@ void ncsi_stop_dev(struct ncsi_dev *nd)
 			spin_lock_irqsave(&nc->lock, flags);
 			chained = !list_empty(&nc->link);
 			old_state = nc->state;
-			nc->state = NCSI_CHANNEL_INACTIVE;
 			spin_unlock_irqrestore(&nc->lock, flags);
 
 			WARN_ON_ONCE(chained ||
@@ -1588,6 +1601,92 @@ void ncsi_stop_dev(struct ncsi_dev *nd)
 }
 EXPORT_SYMBOL_GPL(ncsi_stop_dev);
 
+int ncsi_reset_dev(struct ncsi_dev *nd)
+{
+	struct ncsi_dev_priv *ndp = TO_NCSI_DEV_PRIV(nd);
+	struct ncsi_channel *nc, *active, *tmp;
+	struct ncsi_package *np;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ndp->lock, flags);
+
+	if (!(ndp->flags & NCSI_DEV_RESET)) {
+		/* Haven't been called yet, check states */
+		switch (nd->state & ncsi_dev_state_major) {
+		case ncsi_dev_state_registered:
+		case ncsi_dev_state_probe:
+			/* Not even probed yet - do nothing */
+			spin_unlock_irqrestore(&ndp->lock, flags);
+			return 0;
+		case ncsi_dev_state_suspend:
+		case ncsi_dev_state_config:
+			/* Wait for the channel to finish its suspend/config
+			 * operation; once it finishes it will check for
+			 * NCSI_DEV_RESET and reset the state.
+			 */
+			ndp->flags |= NCSI_DEV_RESET;
+			spin_unlock_irqrestore(&ndp->lock, flags);
+			return 0;
+		}
+	} else {
+		switch (nd->state) {
+		case ncsi_dev_state_suspend_done:
+		case ncsi_dev_state_config_done:
+		case ncsi_dev_state_functional:
+			/* Ok */
+			break;
+		default:
+			/* Current reset operation happening */
+			spin_unlock_irqrestore(&ndp->lock, flags);
+			return 0;
+		}
+	}
+
+	if (!list_empty(&ndp->channel_queue)) {
+		/* Clear any channel queue we may have interrupted */
+		list_for_each_entry_safe(nc, tmp, &ndp->channel_queue, link)
+			list_del_init(&nc->link);
+	}
+	spin_unlock_irqrestore(&ndp->lock, flags);
+
+	active = NULL;
+	NCSI_FOR_EACH_PACKAGE(ndp, np) {
+		NCSI_FOR_EACH_CHANNEL(np, nc) {
+			spin_lock_irqsave(&nc->lock, flags);
+
+			if (nc->state == NCSI_CHANNEL_ACTIVE) {
+				active = nc;
+				nc->state = NCSI_CHANNEL_INVISIBLE;
+				spin_unlock_irqrestore(&nc->lock, flags);
+				ncsi_stop_channel_monitor(nc);
+				break;
+			}
+
+			spin_unlock_irqrestore(&nc->lock, flags);
+		}
+		if (active)
+			break;
+	}
+
+	if (!active) {
+		/* Done */
+		spin_lock_irqsave(&ndp->lock, flags);
+		ndp->flags &= ~NCSI_DEV_RESET;
+		spin_unlock_irqrestore(&ndp->lock, flags);
+		return ncsi_choose_active_channel(ndp);
+	}
+
+	spin_lock_irqsave(&ndp->lock, flags);
+	ndp->flags |= NCSI_DEV_RESET;
+	ndp->active_channel = active;
+	ndp->active_package = active->package;
+	spin_unlock_irqrestore(&ndp->lock, flags);
+
+	nd->state = ncsi_dev_state_suspend;
+	schedule_work(&ndp->work);
+	return 0;
+}
+
 void ncsi_unregister_dev(struct ncsi_dev *nd)
 {
 	struct ncsi_dev_priv *ndp = TO_NCSI_DEV_PRIV(nd);
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index 33314381b4f5..cde48fe43dba 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -330,9 +330,9 @@ static int ncsi_set_interface_nl(struct sk_buff *msg, struct genl_info *info)
 		    package_id, channel_id,
 		    channel_id == NCSI_RESERVED_CHANNEL ? " (any)" : "");
 
-	/* Bounce the NCSI channel to set changes */
-	ncsi_stop_dev(&ndp->ndev);
-	ncsi_start_dev(&ndp->ndev);
+	/* Update channel configuration */
+	if (!(ndp->flags & NCSI_DEV_RESET))
+		ncsi_reset_dev(&ndp->ndev);
 
 	return 0;
 }
@@ -360,9 +360,9 @@ static int ncsi_clear_interface_nl(struct sk_buff *msg, struct genl_info *info)
 	spin_unlock_irqrestore(&ndp->lock, flags);
 	netdev_info(ndp->ndev.dev, "NCSI: Cleared preferred package/channel\n");
 
-	/* Bounce the NCSI channel to set changes */
-	ncsi_stop_dev(&ndp->ndev);
-	ncsi_start_dev(&ndp->ndev);
+	/* Update channel configuration */
+	if (!(ndp->flags & NCSI_DEV_RESET))
+		ncsi_reset_dev(&ndp->ndev);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 8d951a75d022d94a05f5fa74217670a981e8302d Mon Sep 17 00:00:00 2001
From: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Date: Fri, 16 Nov 2018 15:51:59 +1100
Subject: net/ncsi: Configure multi-package, multi-channel modes with failover

This patch extends the ncsi-netlink interface with two new commands and
three new attributes to configure multiple packages and/or channels at
once, and configure specific failover modes.

NCSI_CMD_SET_PACKAGE mask and NCSI_CMD_SET_CHANNEL_MASK set a whitelist
of packages or channels allowed to be configured with the
NCSI_ATTR_PACKAGE_MASK and NCSI_ATTR_CHANNEL_MASK attributes
respectively. If one of these whitelists is set only packages or
channels matching the whitelist are considered for the channel queue in
ncsi_choose_active_channel().

These commands may also use the NCSI_ATTR_MULTI_FLAG to signal that
multiple packages or channels may be configured simultaneously. NCSI
hardware arbitration (HWA) must be available in order to enable
multi-package mode. Multi-channel mode is always available.

If the NCSI_ATTR_CHANNEL_ID attribute is present in the
NCSI_CMD_SET_CHANNEL_MASK command the it sets the preferred channel as
with the NCSI_CMD_SET_INTERFACE command. The combination of preferred
channel and channel whitelist defines a primary channel and the allowed
failover channels.
If the NCSI_ATTR_MULTI_FLAG attribute is also present then the preferred
channel is configured for Tx/Rx and the other channels are enabled only
for Rx.

Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ncsi.h |  15 +++
 net/ncsi/internal.h       |  16 ++-
 net/ncsi/ncsi-aen.c       |  63 ++++++++---
 net/ncsi/ncsi-manage.c    | 264 ++++++++++++++++++++++++++++++++++++++--------
 net/ncsi/ncsi-netlink.c   | 221 +++++++++++++++++++++++++++++++++-----
 net/ncsi/ncsi-rsp.c       |   2 +-
 6 files changed, 493 insertions(+), 88 deletions(-)

diff --git a/include/uapi/linux/ncsi.h b/include/uapi/linux/ncsi.h
index 0a26a5576645..a3f87c54fdb3 100644
--- a/include/uapi/linux/ncsi.h
+++ b/include/uapi/linux/ncsi.h
@@ -26,6 +26,12 @@
  * @NCSI_CMD_SEND_CMD: send NC-SI command to network card.
  *	Requires NCSI_ATTR_IFINDEX, NCSI_ATTR_PACKAGE_ID
  *	and NCSI_ATTR_CHANNEL_ID.
+ * @NCSI_CMD_SET_PACKAGE_MASK: set a whitelist of allowed packages.
+ *	Requires NCSI_ATTR_IFINDEX and NCSI_ATTR_PACKAGE_MASK.
+ * @NCSI_CMD_SET_CHANNEL_MASK: set a whitelist of allowed channels.
+ *	Requires NCSI_ATTR_IFINDEX, NCSI_ATTR_PACKAGE_ID, and
+ *	NCSI_ATTR_CHANNEL_MASK. If NCSI_ATTR_CHANNEL_ID is present it sets
+ *	the primary channel.
  * @NCSI_CMD_MAX: highest command number
  */
 enum ncsi_nl_commands {
@@ -34,6 +40,8 @@ enum ncsi_nl_commands {
 	NCSI_CMD_SET_INTERFACE,
 	NCSI_CMD_CLEAR_INTERFACE,
 	NCSI_CMD_SEND_CMD,
+	NCSI_CMD_SET_PACKAGE_MASK,
+	NCSI_CMD_SET_CHANNEL_MASK,
 
 	__NCSI_CMD_AFTER_LAST,
 	NCSI_CMD_MAX = __NCSI_CMD_AFTER_LAST - 1
@@ -48,6 +56,10 @@ enum ncsi_nl_commands {
  * @NCSI_ATTR_PACKAGE_ID: package ID
  * @NCSI_ATTR_CHANNEL_ID: channel ID
  * @NCSI_ATTR_DATA: command payload
+ * @NCSI_ATTR_MULTI_FLAG: flag to signal that multi-mode should be enabled with
+ *	NCSI_CMD_SET_PACKAGE_MASK or NCSI_CMD_SET_CHANNEL_MASK.
+ * @NCSI_ATTR_PACKAGE_MASK: 32-bit mask of allowed packages.
+ * @NCSI_ATTR_CHANNEL_MASK: 32-bit mask of allowed channels.
  * @NCSI_ATTR_MAX: highest attribute number
  */
 enum ncsi_nl_attrs {
@@ -57,6 +69,9 @@ enum ncsi_nl_attrs {
 	NCSI_ATTR_PACKAGE_ID,
 	NCSI_ATTR_CHANNEL_ID,
 	NCSI_ATTR_DATA,
+	NCSI_ATTR_MULTI_FLAG,
+	NCSI_ATTR_PACKAGE_MASK,
+	NCSI_ATTR_CHANNEL_MASK,
 
 	__NCSI_ATTR_AFTER_LAST,
 	NCSI_ATTR_MAX = __NCSI_ATTR_AFTER_LAST - 1
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index bda51cb179fe..9e3642b802c4 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -222,6 +222,10 @@ struct ncsi_package {
 	unsigned int         channel_num; /* Number of channels     */
 	struct list_head     channels;    /* List of chanels        */
 	struct list_head     node;        /* Form list of packages  */
+
+	bool                 multi_channel; /* Enable multiple channels  */
+	u32                  channel_whitelist; /* Channels to configure */
+	struct ncsi_channel  *preferred_channel; /* Primary channel      */
 };
 
 struct ncsi_request {
@@ -297,8 +301,6 @@ struct ncsi_dev_priv {
 	unsigned int        package_num;     /* Number of packages         */
 	struct list_head    packages;        /* List of packages           */
 	struct ncsi_channel *hot_channel;    /* Channel was ever active    */
-	struct ncsi_package *force_package;  /* Force a specific package   */
-	struct ncsi_channel *force_channel;  /* Force a specific channel   */
 	struct ncsi_request requests[256];   /* Request table              */
 	unsigned int        request_id;      /* Last used request ID       */
 #define NCSI_REQ_START_IDX	1
@@ -311,6 +313,9 @@ struct ncsi_dev_priv {
 	struct list_head    node;            /* Form NCSI device list      */
 #define NCSI_MAX_VLAN_VIDS	15
 	struct list_head    vlan_vids;       /* List of active VLAN IDs */
+
+	bool                multi_package;   /* Enable multiple packages   */
+	u32                 package_whitelist; /* Packages to configure    */
 };
 
 struct ncsi_cmd_arg {
@@ -364,6 +369,13 @@ struct ncsi_request *ncsi_alloc_request(struct ncsi_dev_priv *ndp,
 void ncsi_free_request(struct ncsi_request *nr);
 struct ncsi_dev *ncsi_find_dev(struct net_device *dev);
 int ncsi_process_next_channel(struct ncsi_dev_priv *ndp);
+bool ncsi_channel_has_link(struct ncsi_channel *channel);
+bool ncsi_channel_is_last(struct ncsi_dev_priv *ndp,
+			  struct ncsi_channel *channel);
+int ncsi_update_tx_channel(struct ncsi_dev_priv *ndp,
+			   struct ncsi_package *np,
+			   struct ncsi_channel *disable,
+			   struct ncsi_channel *enable);
 
 /* Packet handlers */
 u32 ncsi_calculate_checksum(unsigned char *data, int len);
diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index 57f77e5d381a..26d67e27551f 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -50,14 +50,15 @@ static int ncsi_validate_aen_pkt(struct ncsi_aen_pkt_hdr *h,
 static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
 				struct ncsi_aen_pkt_hdr *h)
 {
-	struct ncsi_aen_lsc_pkt *lsc;
-	struct ncsi_channel *nc;
+	struct ncsi_channel *nc, *tmp;
 	struct ncsi_channel_mode *ncm;
-	bool chained;
-	int state;
 	unsigned long old_data, data;
-	unsigned long flags;
+	struct ncsi_aen_lsc_pkt *lsc;
+	struct ncsi_package *np;
 	bool had_link, has_link;
+	unsigned long flags;
+	bool chained;
+	int state;
 
 	/* Find the NCSI channel */
 	ncsi_find_package_and_channel(ndp, h->common.channel, NULL, &nc);
@@ -92,14 +93,52 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
 	if ((had_link == has_link) || chained)
 		return 0;
 
-	if (had_link)
-		ndp->flags |= NCSI_DEV_RESHUFFLE;
-	ncsi_stop_channel_monitor(nc);
-	spin_lock_irqsave(&ndp->lock, flags);
-	list_add_tail_rcu(&nc->link, &ndp->channel_queue);
-	spin_unlock_irqrestore(&ndp->lock, flags);
+	if (!ndp->multi_package && !nc->package->multi_channel) {
+		if (had_link) {
+			ndp->flags |= NCSI_DEV_RESHUFFLE;
+			ncsi_stop_channel_monitor(nc);
+			spin_lock_irqsave(&ndp->lock, flags);
+			list_add_tail_rcu(&nc->link, &ndp->channel_queue);
+			spin_unlock_irqrestore(&ndp->lock, flags);
+			return ncsi_process_next_channel(ndp);
+		}
+		/* Configured channel came up */
+		return 0;
+	}
 
-	return ncsi_process_next_channel(ndp);
+	if (had_link) {
+		ncm = &nc->modes[NCSI_MODE_TX_ENABLE];
+		if (ncsi_channel_is_last(ndp, nc)) {
+			/* No channels left, reconfigure */
+			return ncsi_reset_dev(&ndp->ndev);
+		} else if (ncm->enable) {
+			/* Need to failover Tx channel */
+			ncsi_update_tx_channel(ndp, nc->package, nc, NULL);
+		}
+	} else if (has_link && nc->package->preferred_channel == nc) {
+		/* Return Tx to preferred channel */
+		ncsi_update_tx_channel(ndp, nc->package, NULL, nc);
+	} else if (has_link) {
+		NCSI_FOR_EACH_PACKAGE(ndp, np) {
+			NCSI_FOR_EACH_CHANNEL(np, tmp) {
+				/* Enable Tx on this channel if the current Tx
+				 * channel is down.
+				 */
+				ncm = &tmp->modes[NCSI_MODE_TX_ENABLE];
+				if (ncm->enable &&
+				    !ncsi_channel_has_link(tmp)) {
+					ncsi_update_tx_channel(ndp, nc->package,
+							       tmp, nc);
+					break;
+				}
+			}
+		}
+	}
+
+	/* Leave configured channels active in a multi-channel scenario so
+	 * AEN events are still received.
+	 */
+	return 0;
 }
 
 static int ncsi_aen_handler_cr(struct ncsi_dev_priv *ndp,
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index c814ce9bb3de..92e59f07f9a7 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -28,6 +28,29 @@
 LIST_HEAD(ncsi_dev_list);
 DEFINE_SPINLOCK(ncsi_dev_lock);
 
+bool ncsi_channel_has_link(struct ncsi_channel *channel)
+{
+	return !!(channel->modes[NCSI_MODE_LINK].data[2] & 0x1);
+}
+
+bool ncsi_channel_is_last(struct ncsi_dev_priv *ndp,
+			  struct ncsi_channel *channel)
+{
+	struct ncsi_package *np;
+	struct ncsi_channel *nc;
+
+	NCSI_FOR_EACH_PACKAGE(ndp, np)
+		NCSI_FOR_EACH_CHANNEL(np, nc) {
+			if (nc == channel)
+				continue;
+			if (nc->state == NCSI_CHANNEL_ACTIVE &&
+			    ncsi_channel_has_link(nc))
+				return false;
+		}
+
+	return true;
+}
+
 static void ncsi_report_link(struct ncsi_dev_priv *ndp, bool force_down)
 {
 	struct ncsi_dev *nd = &ndp->ndev;
@@ -52,7 +75,7 @@ static void ncsi_report_link(struct ncsi_dev_priv *ndp, bool force_down)
 				continue;
 			}
 
-			if (nc->modes[NCSI_MODE_LINK].data[2] & 0x1) {
+			if (ncsi_channel_has_link(nc)) {
 				spin_unlock_irqrestore(&nc->lock, flags);
 				nd->link_up = 1;
 				goto report;
@@ -267,6 +290,7 @@ struct ncsi_package *ncsi_add_package(struct ncsi_dev_priv *ndp,
 	np->ndp = ndp;
 	spin_lock_init(&np->lock);
 	INIT_LIST_HEAD(&np->channels);
+	np->channel_whitelist = UINT_MAX;
 
 	spin_lock_irqsave(&ndp->lock, flags);
 	tmp = ncsi_find_package(ndp, id);
@@ -728,13 +752,144 @@ static int ncsi_gma_handler(struct ncsi_cmd_arg *nca, unsigned int mf_id)
 
 #endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */
 
+/* Determine if a given channel from the channel_queue should be used for Tx */
+static bool ncsi_channel_is_tx(struct ncsi_dev_priv *ndp,
+			       struct ncsi_channel *nc)
+{
+	struct ncsi_channel_mode *ncm;
+	struct ncsi_channel *channel;
+	struct ncsi_package *np;
+
+	/* Check if any other channel has Tx enabled; a channel may have already
+	 * been configured and removed from the channel queue.
+	 */
+	NCSI_FOR_EACH_PACKAGE(ndp, np) {
+		if (!ndp->multi_package && np != nc->package)
+			continue;
+		NCSI_FOR_EACH_CHANNEL(np, channel) {
+			ncm = &channel->modes[NCSI_MODE_TX_ENABLE];
+			if (ncm->enable)
+				return false;
+		}
+	}
+
+	/* This channel is the preferred channel and has link */
+	list_for_each_entry_rcu(channel, &ndp->channel_queue, link) {
+		np = channel->package;
+		if (np->preferred_channel &&
+		    ncsi_channel_has_link(np->preferred_channel)) {
+			return np->preferred_channel == nc;
+		}
+	}
+
+	/* This channel has link */
+	if (ncsi_channel_has_link(nc))
+		return true;
+
+	list_for_each_entry_rcu(channel, &ndp->channel_queue, link)
+		if (ncsi_channel_has_link(channel))
+			return false;
+
+	/* No other channel has link; default to this one */
+	return true;
+}
+
+/* Change the active Tx channel in a multi-channel setup */
+int ncsi_update_tx_channel(struct ncsi_dev_priv *ndp,
+			   struct ncsi_package *package,
+			   struct ncsi_channel *disable,
+			   struct ncsi_channel *enable)
+{
+	struct ncsi_cmd_arg nca;
+	struct ncsi_channel *nc;
+	struct ncsi_package *np;
+	int ret = 0;
+
+	if (!package->multi_channel && !ndp->multi_package)
+		netdev_warn(ndp->ndev.dev,
+			    "NCSI: Trying to update Tx channel in single-channel mode\n");
+	nca.ndp = ndp;
+	nca.req_flags = 0;
+
+	/* Find current channel with Tx enabled */
+	NCSI_FOR_EACH_PACKAGE(ndp, np) {
+		if (disable)
+			break;
+		if (!ndp->multi_package && np != package)
+			continue;
+
+		NCSI_FOR_EACH_CHANNEL(np, nc)
+			if (nc->modes[NCSI_MODE_TX_ENABLE].enable) {
+				disable = nc;
+				break;
+			}
+	}
+
+	/* Find a suitable channel for Tx */
+	NCSI_FOR_EACH_PACKAGE(ndp, np) {
+		if (enable)
+			break;
+		if (!ndp->multi_package && np != package)
+			continue;
+		if (!(ndp->package_whitelist & (0x1 << np->id)))
+			continue;
+
+		if (np->preferred_channel &&
+		    ncsi_channel_has_link(np->preferred_channel)) {
+			enable = np->preferred_channel;
+			break;
+		}
+
+		NCSI_FOR_EACH_CHANNEL(np, nc) {
+			if (!(np->channel_whitelist & 0x1 << nc->id))
+				continue;
+			if (nc->state != NCSI_CHANNEL_ACTIVE)
+				continue;
+			if (ncsi_channel_has_link(nc)) {
+				enable = nc;
+				break;
+			}
+		}
+	}
+
+	if (disable == enable)
+		return -1;
+
+	if (!enable)
+		return -1;
+
+	if (disable) {
+		nca.channel = disable->id;
+		nca.package = disable->package->id;
+		nca.type = NCSI_PKT_CMD_DCNT;
+		ret = ncsi_xmit_cmd(&nca);
+		if (ret)
+			netdev_err(ndp->ndev.dev,
+				   "Error %d sending DCNT\n",
+				   ret);
+	}
+
+	netdev_info(ndp->ndev.dev, "NCSI: channel %u enables Tx\n", enable->id);
+
+	nca.channel = enable->id;
+	nca.package = enable->package->id;
+	nca.type = NCSI_PKT_CMD_ECNT;
+	ret = ncsi_xmit_cmd(&nca);
+	if (ret)
+		netdev_err(ndp->ndev.dev,
+			   "Error %d sending ECNT\n",
+			   ret);
+
+	return ret;
+}
+
 static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 {
-	struct ncsi_dev *nd = &ndp->ndev;
-	struct net_device *dev = nd->dev;
 	struct ncsi_package *np = ndp->active_package;
 	struct ncsi_channel *nc = ndp->active_channel;
 	struct ncsi_channel *hot_nc = NULL;
+	struct ncsi_dev *nd = &ndp->ndev;
+	struct net_device *dev = nd->dev;
 	struct ncsi_cmd_arg nca;
 	unsigned char index;
 	unsigned long flags;
@@ -856,20 +1011,29 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 		} else if (nd->state == ncsi_dev_state_config_ebf) {
 			nca.type = NCSI_PKT_CMD_EBF;
 			nca.dwords[0] = nc->caps[NCSI_CAP_BC].cap;
-			nd->state = ncsi_dev_state_config_ecnt;
+			if (ncsi_channel_is_tx(ndp, nc))
+				nd->state = ncsi_dev_state_config_ecnt;
+			else
+				nd->state = ncsi_dev_state_config_ec;
 #if IS_ENABLED(CONFIG_IPV6)
 			if (ndp->inet6_addr_num > 0 &&
 			    (nc->caps[NCSI_CAP_GENERIC].cap &
 			     NCSI_CAP_GENERIC_MC))
 				nd->state = ncsi_dev_state_config_egmf;
-			else
-				nd->state = ncsi_dev_state_config_ecnt;
 		} else if (nd->state == ncsi_dev_state_config_egmf) {
 			nca.type = NCSI_PKT_CMD_EGMF;
 			nca.dwords[0] = nc->caps[NCSI_CAP_MC].cap;
-			nd->state = ncsi_dev_state_config_ecnt;
+			if (ncsi_channel_is_tx(ndp, nc))
+				nd->state = ncsi_dev_state_config_ecnt;
+			else
+				nd->state = ncsi_dev_state_config_ec;
 #endif /* CONFIG_IPV6 */
 		} else if (nd->state == ncsi_dev_state_config_ecnt) {
+			if (np->preferred_channel &&
+			    nc != np->preferred_channel)
+				netdev_info(ndp->ndev.dev,
+					    "NCSI: Tx failed over to channel %u\n",
+					    nc->id);
 			nca.type = NCSI_PKT_CMD_ECNT;
 			nd->state = ncsi_dev_state_config_ec;
 		} else if (nd->state == ncsi_dev_state_config_ec) {
@@ -959,43 +1123,35 @@ error:
 
 static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp)
 {
-	struct ncsi_package *np, *force_package;
-	struct ncsi_channel *nc, *found, *hot_nc, *force_channel;
+	struct ncsi_channel *nc, *found, *hot_nc;
 	struct ncsi_channel_mode *ncm;
-	unsigned long flags;
+	unsigned long flags, cflags;
+	struct ncsi_package *np;
+	bool with_link;
 
 	spin_lock_irqsave(&ndp->lock, flags);
 	hot_nc = ndp->hot_channel;
-	force_channel = ndp->force_channel;
-	force_package = ndp->force_package;
 	spin_unlock_irqrestore(&ndp->lock, flags);
 
-	/* Force a specific channel whether or not it has link if we have been
-	 * configured to do so
-	 */
-	if (force_package && force_channel) {
-		found = force_channel;
-		ncm = &found->modes[NCSI_MODE_LINK];
-		if (!(ncm->data[2] & 0x1))
-			netdev_info(ndp->ndev.dev,
-				    "NCSI: Channel %u forced, but it is link down\n",
-				    found->id);
-		goto out;
-	}
-
-	/* The search is done once an inactive channel with up
-	 * link is found.
+	/* By default the search is done once an inactive channel with up
+	 * link is found, unless a preferred channel is set.
+	 * If multi_package or multi_channel are configured all channels in the
+	 * whitelist are added to the channel queue.
 	 */
 	found = NULL;
+	with_link = false;
 	NCSI_FOR_EACH_PACKAGE(ndp, np) {
-		if (ndp->force_package && np != ndp->force_package)
+		if (!(ndp->package_whitelist & (0x1 << np->id)))
 			continue;
 		NCSI_FOR_EACH_CHANNEL(np, nc) {
-			spin_lock_irqsave(&nc->lock, flags);
+			if (!(np->channel_whitelist & (0x1 << nc->id)))
+				continue;
+
+			spin_lock_irqsave(&nc->lock, cflags);
 
 			if (!list_empty(&nc->link) ||
 			    nc->state != NCSI_CHANNEL_INACTIVE) {
-				spin_unlock_irqrestore(&nc->lock, flags);
+				spin_unlock_irqrestore(&nc->lock, cflags);
 				continue;
 			}
 
@@ -1007,32 +1163,49 @@ static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp)
 
 			ncm = &nc->modes[NCSI_MODE_LINK];
 			if (ncm->data[2] & 0x1) {
-				spin_unlock_irqrestore(&nc->lock, flags);
 				found = nc;
-				goto out;
+				with_link = true;
 			}
 
-			spin_unlock_irqrestore(&nc->lock, flags);
+			/* If multi_channel is enabled configure all valid
+			 * channels whether or not they currently have link
+			 * so they will have AENs enabled.
+			 */
+			if (with_link || np->multi_channel) {
+				spin_lock_irqsave(&ndp->lock, flags);
+				list_add_tail_rcu(&nc->link,
+						  &ndp->channel_queue);
+				spin_unlock_irqrestore(&ndp->lock, flags);
+
+				netdev_dbg(ndp->ndev.dev,
+					   "NCSI: Channel %u added to queue (link %s)\n",
+					   nc->id,
+					   ncm->data[2] & 0x1 ? "up" : "down");
+			}
+
+			spin_unlock_irqrestore(&nc->lock, cflags);
+
+			if (with_link && !np->multi_channel)
+				break;
 		}
+		if (with_link && !ndp->multi_package)
+			break;
 	}
 
-	if (!found) {
+	if (list_empty(&ndp->channel_queue) && found) {
+		netdev_info(ndp->ndev.dev,
+			    "NCSI: No channel with link found, configuring channel %u\n",
+			    found->id);
+		spin_lock_irqsave(&ndp->lock, flags);
+		list_add_tail_rcu(&found->link, &ndp->channel_queue);
+		spin_unlock_irqrestore(&ndp->lock, flags);
+	} else if (!found) {
 		netdev_warn(ndp->ndev.dev,
-			    "NCSI: No channel found with link\n");
+			    "NCSI: No channel found to configure!\n");
 		ncsi_report_link(ndp, true);
 		return -ENODEV;
 	}
 
-	ncm = &found->modes[NCSI_MODE_LINK];
-	netdev_dbg(ndp->ndev.dev,
-		   "NCSI: Channel %u added to queue (link %s)\n",
-		   found->id, ncm->data[2] & 0x1 ? "up" : "down");
-
-out:
-	spin_lock_irqsave(&ndp->lock, flags);
-	list_add_tail_rcu(&found->link, &ndp->channel_queue);
-	spin_unlock_irqrestore(&ndp->lock, flags);
-
 	return ncsi_process_next_channel(ndp);
 }
 
@@ -1517,6 +1690,7 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev,
 	INIT_LIST_HEAD(&ndp->channel_queue);
 	INIT_LIST_HEAD(&ndp->vlan_vids);
 	INIT_WORK(&ndp->work, ncsi_dev_work);
+	ndp->package_whitelist = UINT_MAX;
 
 	/* Initialize private NCSI device */
 	spin_lock_init(&ndp->lock);
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index cde48fe43dba..5d782445d2fc 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -30,6 +30,9 @@ static const struct nla_policy ncsi_genl_policy[NCSI_ATTR_MAX + 1] = {
 	[NCSI_ATTR_PACKAGE_ID] =	{ .type = NLA_U32 },
 	[NCSI_ATTR_CHANNEL_ID] =	{ .type = NLA_U32 },
 	[NCSI_ATTR_DATA] =		{ .type = NLA_BINARY, .len = 2048 },
+	[NCSI_ATTR_MULTI_FLAG] =	{ .type = NLA_FLAG },
+	[NCSI_ATTR_PACKAGE_MASK] =	{ .type = NLA_U32 },
+	[NCSI_ATTR_CHANNEL_MASK] =	{ .type = NLA_U32 },
 };
 
 static struct ncsi_dev_priv *ndp_from_ifindex(struct net *net, u32 ifindex)
@@ -69,7 +72,7 @@ static int ncsi_write_channel_info(struct sk_buff *skb,
 	nla_put_u32(skb, NCSI_CHANNEL_ATTR_LINK_STATE, m->data[2]);
 	if (nc->state == NCSI_CHANNEL_ACTIVE)
 		nla_put_flag(skb, NCSI_CHANNEL_ATTR_ACTIVE);
-	if (ndp->force_channel == nc)
+	if (nc == nc->package->preferred_channel)
 		nla_put_flag(skb, NCSI_CHANNEL_ATTR_FORCED);
 
 	nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MAJOR, nc->version.version);
@@ -114,7 +117,7 @@ static int ncsi_write_package_info(struct sk_buff *skb,
 		if (!pnest)
 			return -ENOMEM;
 		nla_put_u32(skb, NCSI_PKG_ATTR_ID, np->id);
-		if (ndp->force_package == np)
+		if ((0x1 << np->id) == ndp->package_whitelist)
 			nla_put_flag(skb, NCSI_PKG_ATTR_FORCED);
 		cnest = nla_nest_start(skb, NCSI_PKG_ATTR_CHANNEL_LIST);
 		if (!cnest) {
@@ -290,45 +293,54 @@ static int ncsi_set_interface_nl(struct sk_buff *msg, struct genl_info *info)
 	package_id = nla_get_u32(info->attrs[NCSI_ATTR_PACKAGE_ID]);
 	package = NULL;
 
-	spin_lock_irqsave(&ndp->lock, flags);
-
 	NCSI_FOR_EACH_PACKAGE(ndp, np)
 		if (np->id == package_id)
 			package = np;
 	if (!package) {
 		/* The user has set a package that does not exist */
-		spin_unlock_irqrestore(&ndp->lock, flags);
 		return -ERANGE;
 	}
 
 	channel = NULL;
-	if (!info->attrs[NCSI_ATTR_CHANNEL_ID]) {
-		/* Allow any channel */
-		channel_id = NCSI_RESERVED_CHANNEL;
-	} else {
+	if (info->attrs[NCSI_ATTR_CHANNEL_ID]) {
 		channel_id = nla_get_u32(info->attrs[NCSI_ATTR_CHANNEL_ID]);
 		NCSI_FOR_EACH_CHANNEL(package, nc)
-			if (nc->id == channel_id)
+			if (nc->id == channel_id) {
 				channel = nc;
+				break;
+			}
+		if (!channel) {
+			netdev_info(ndp->ndev.dev,
+				    "NCSI: Channel %u does not exist!\n",
+				    channel_id);
+			return -ERANGE;
+		}
 	}
 
-	if (channel_id != NCSI_RESERVED_CHANNEL && !channel) {
-		/* The user has set a channel that does not exist on this
-		 * package
-		 */
-		spin_unlock_irqrestore(&ndp->lock, flags);
-		netdev_info(ndp->ndev.dev, "NCSI: Channel %u does not exist!\n",
-			    channel_id);
-		return -ERANGE;
-	}
-
-	ndp->force_package = package;
-	ndp->force_channel = channel;
+	spin_lock_irqsave(&ndp->lock, flags);
+	ndp->package_whitelist = 0x1 << package->id;
+	ndp->multi_package = false;
 	spin_unlock_irqrestore(&ndp->lock, flags);
 
-	netdev_info(ndp->ndev.dev, "Set package 0x%x, channel 0x%x%s as preferred\n",
-		    package_id, channel_id,
-		    channel_id == NCSI_RESERVED_CHANNEL ? " (any)" : "");
+	spin_lock_irqsave(&package->lock, flags);
+	package->multi_channel = false;
+	if (channel) {
+		package->channel_whitelist = 0x1 << channel->id;
+		package->preferred_channel = channel;
+	} else {
+		/* Allow any channel */
+		package->channel_whitelist = UINT_MAX;
+		package->preferred_channel = NULL;
+	}
+	spin_unlock_irqrestore(&package->lock, flags);
+
+	if (channel)
+		netdev_info(ndp->ndev.dev,
+			    "Set package 0x%x, channel 0x%x as preferred\n",
+			    package_id, channel_id);
+	else
+		netdev_info(ndp->ndev.dev, "Set package 0x%x as preferred\n",
+			    package_id);
 
 	/* Update channel configuration */
 	if (!(ndp->flags & NCSI_DEV_RESET))
@@ -340,6 +352,7 @@ static int ncsi_set_interface_nl(struct sk_buff *msg, struct genl_info *info)
 static int ncsi_clear_interface_nl(struct sk_buff *msg, struct genl_info *info)
 {
 	struct ncsi_dev_priv *ndp;
+	struct ncsi_package *np;
 	unsigned long flags;
 
 	if (!info || !info->attrs)
@@ -353,11 +366,19 @@ static int ncsi_clear_interface_nl(struct sk_buff *msg, struct genl_info *info)
 	if (!ndp)
 		return -ENODEV;
 
-	/* Clear any override */
+	/* Reset any whitelists and disable multi mode */
 	spin_lock_irqsave(&ndp->lock, flags);
-	ndp->force_package = NULL;
-	ndp->force_channel = NULL;
+	ndp->package_whitelist = UINT_MAX;
+	ndp->multi_package = false;
 	spin_unlock_irqrestore(&ndp->lock, flags);
+
+	NCSI_FOR_EACH_PACKAGE(ndp, np) {
+		spin_lock_irqsave(&np->lock, flags);
+		np->multi_channel = false;
+		np->channel_whitelist = UINT_MAX;
+		np->preferred_channel = NULL;
+		spin_unlock_irqrestore(&np->lock, flags);
+	}
 	netdev_info(ndp->ndev.dev, "NCSI: Cleared preferred package/channel\n");
 
 	/* Update channel configuration */
@@ -563,6 +584,138 @@ int ncsi_send_netlink_err(struct net_device *dev,
 	return nlmsg_unicast(net->genl_sock, skb, snd_portid);
 }
 
+static int ncsi_set_package_mask_nl(struct sk_buff *msg,
+				    struct genl_info *info)
+{
+	struct ncsi_dev_priv *ndp;
+	unsigned long flags;
+	int rc;
+
+	if (!info || !info->attrs)
+		return -EINVAL;
+
+	if (!info->attrs[NCSI_ATTR_IFINDEX])
+		return -EINVAL;
+
+	if (!info->attrs[NCSI_ATTR_PACKAGE_MASK])
+		return -EINVAL;
+
+	ndp = ndp_from_ifindex(get_net(sock_net(msg->sk)),
+			       nla_get_u32(info->attrs[NCSI_ATTR_IFINDEX]));
+	if (!ndp)
+		return -ENODEV;
+
+	spin_lock_irqsave(&ndp->lock, flags);
+	if (nla_get_flag(info->attrs[NCSI_ATTR_MULTI_FLAG])) {
+		if (ndp->flags & NCSI_DEV_HWA) {
+			ndp->multi_package = true;
+			rc = 0;
+		} else {
+			netdev_err(ndp->ndev.dev,
+				   "NCSI: Can't use multiple packages without HWA\n");
+			rc = -EPERM;
+		}
+	} else {
+		ndp->multi_package = false;
+		rc = 0;
+	}
+
+	if (!rc)
+		ndp->package_whitelist =
+			nla_get_u32(info->attrs[NCSI_ATTR_PACKAGE_MASK]);
+	spin_unlock_irqrestore(&ndp->lock, flags);
+
+	if (!rc) {
+		/* Update channel configuration */
+		if (!(ndp->flags & NCSI_DEV_RESET))
+			ncsi_reset_dev(&ndp->ndev);
+	}
+
+	return rc;
+}
+
+static int ncsi_set_channel_mask_nl(struct sk_buff *msg,
+				    struct genl_info *info)
+{
+	struct ncsi_package *np, *package;
+	struct ncsi_channel *nc, *channel;
+	u32 package_id, channel_id;
+	struct ncsi_dev_priv *ndp;
+	unsigned long flags;
+
+	if (!info || !info->attrs)
+		return -EINVAL;
+
+	if (!info->attrs[NCSI_ATTR_IFINDEX])
+		return -EINVAL;
+
+	if (!info->attrs[NCSI_ATTR_PACKAGE_ID])
+		return -EINVAL;
+
+	if (!info->attrs[NCSI_ATTR_CHANNEL_MASK])
+		return -EINVAL;
+
+	ndp = ndp_from_ifindex(get_net(sock_net(msg->sk)),
+			       nla_get_u32(info->attrs[NCSI_ATTR_IFINDEX]));
+	if (!ndp)
+		return -ENODEV;
+
+	package_id = nla_get_u32(info->attrs[NCSI_ATTR_PACKAGE_ID]);
+	package = NULL;
+	NCSI_FOR_EACH_PACKAGE(ndp, np)
+		if (np->id == package_id) {
+			package = np;
+			break;
+		}
+	if (!package)
+		return -ERANGE;
+
+	spin_lock_irqsave(&package->lock, flags);
+
+	channel = NULL;
+	if (info->attrs[NCSI_ATTR_CHANNEL_ID]) {
+		channel_id = nla_get_u32(info->attrs[NCSI_ATTR_CHANNEL_ID]);
+		NCSI_FOR_EACH_CHANNEL(np, nc)
+			if (nc->id == channel_id) {
+				channel = nc;
+				break;
+			}
+		if (!channel) {
+			spin_unlock_irqrestore(&package->lock, flags);
+			return -ERANGE;
+		}
+		netdev_dbg(ndp->ndev.dev,
+			   "NCSI: Channel %u set as preferred channel\n",
+			   channel->id);
+	}
+
+	package->channel_whitelist =
+		nla_get_u32(info->attrs[NCSI_ATTR_CHANNEL_MASK]);
+	if (package->channel_whitelist == 0)
+		netdev_dbg(ndp->ndev.dev,
+			   "NCSI: Package %u set to all channels disabled\n",
+			   package->id);
+
+	package->preferred_channel = channel;
+
+	if (nla_get_flag(info->attrs[NCSI_ATTR_MULTI_FLAG])) {
+		package->multi_channel = true;
+		netdev_info(ndp->ndev.dev,
+			    "NCSI: Multi-channel enabled on package %u\n",
+			    package_id);
+	} else {
+		package->multi_channel = false;
+	}
+
+	spin_unlock_irqrestore(&package->lock, flags);
+
+	/* Update channel configuration */
+	if (!(ndp->flags & NCSI_DEV_RESET))
+		ncsi_reset_dev(&ndp->ndev);
+
+	return 0;
+}
+
 static const struct genl_ops ncsi_ops[] = {
 	{
 		.cmd = NCSI_CMD_PKG_INFO,
@@ -589,6 +742,18 @@ static const struct genl_ops ncsi_ops[] = {
 		.doit = ncsi_send_cmd_nl,
 		.flags = GENL_ADMIN_PERM,
 	},
+	{
+		.cmd = NCSI_CMD_SET_PACKAGE_MASK,
+		.policy = ncsi_genl_policy,
+		.doit = ncsi_set_package_mask_nl,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = NCSI_CMD_SET_CHANNEL_MASK,
+		.policy = ncsi_genl_policy,
+		.doit = ncsi_set_channel_mask_nl,
+		.flags = GENL_ADMIN_PERM,
+	},
 };
 
 static struct genl_family ncsi_genl_family __ro_after_init = {
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 77e07ba3f493..de7737a27889 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -256,7 +256,7 @@ static int ncsi_rsp_handler_dcnt(struct ncsi_request *nr)
 	if (!ncm->enable)
 		return 0;
 
-	ncm->enable = 1;
+	ncm->enable = 0;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 098aafaa68b35c857f1ae9bc17f8e8b195a02e65 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 16 Nov 2018 18:25:27 +0800
Subject: net: aquantia: cleanup err handing in hw_atl_utils_fw_rpc_wait

'err' always be 0 in the two places.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 7def1cb8ab9d..1af6606a9166 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -454,8 +454,6 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self,
 			       (fw.val =
 				aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR),
 				fw.tid), 1000U, 100U);
-		if (err < 0)
-			goto err_exit;
 
 		if (fw.len == 0xFFFFU) {
 			err = hw_atl_utils_fw_rpc_call(self, sw.len);
@@ -463,8 +461,6 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self,
 				goto err_exit;
 		}
 	} while (sw.tid != fw.tid || 0xFFFFU == fw.len);
-	if (err < 0)
-		goto err_exit;
 
 	if (rpc) {
 		if (fw.len) {
-- 
cgit v1.2.3


From 7c460cf9cd1a4edec0c2c4aa121c3aab9c0a17f1 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 16 Nov 2018 13:36:36 +0000
Subject: net: aquantia: fix spelling mistake "specfield" -> "specified"

There is a spelling mistake in a netdev_err message. Fix this.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_filters.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
index f6145e7473b1..18bc035da850 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -136,7 +136,7 @@ aq_check_approve_fl2(struct aq_nic_s *aq_nic,
 	if (be16_to_cpu(fsp->m_ext.vlan_tci) == VLAN_PRIO_MASK &&
 	    fsp->m_u.ether_spec.h_proto == 0U) {
 		netdev_err(aq_nic->ndev,
-			   "ethtool: proto (ether_type) parameter must be specfied");
+			   "ethtool: proto (ether_type) parameter must be specified");
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From 9a5ee462302512b7f3929c19f0711715613ac418 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 16 Nov 2018 07:24:24 -0800
Subject: net: align pcpu_sw_netstats and pcpu_lstats structs

Do not risk spanning these small structures on two cache lines,
it is absolutely not worth it.

For 32bit arches, the hint might not be enough, but we do not
really care anymore.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 917ae7b6263e..086e64d88597 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2389,13 +2389,13 @@ struct pcpu_sw_netstats {
 	u64     tx_packets;
 	u64     tx_bytes;
 	struct u64_stats_sync   syncp;
-};
+} __aligned(4 * sizeof(u64));
 
 struct pcpu_lstats {
 	u64 packets;
 	u64 bytes;
 	struct u64_stats_sync syncp;
-};
+} __aligned(2 * sizeof(u64));
 
 #define __netdev_alloc_pcpu_stats(type, gfp)				\
 ({									\
-- 
cgit v1.2.3


From 001c96db0181263740215a7f5fec7e937b800a94 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 16 Nov 2018 07:43:29 -0800
Subject: net: align gnet_stats_basic_cpu struct

This structure is small (12 or 16 bytes depending on 64bit
or 32bit kernels), but we do not want it spanning two cache lines.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gen_stats.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index 946bd53a9f81..ca23860adbb9 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -10,7 +10,7 @@
 struct gnet_stats_basic_cpu {
 	struct gnet_stats_basic_packed bstats;
 	struct u64_stats_sync syncp;
-};
+} __aligned(2 * sizeof(u64));
 
 struct net_rate_estimator;
 
-- 
cgit v1.2.3


From ee5b60eba73bd9f854c6d810c582a8097bdca0ef Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 16 Nov 2018 16:05:37 -0600
Subject: atm: Convert to using %pOFn instead of device_node.name

In preparation to remove the node name pointer from struct device_node,
convert printf users to use the %pOFn format specifier.

Cc: Chas Williams <3chas3@gmail.com>
Cc: linux-atm-general@lists.sourceforge.net
Cc: netdev@vger.kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/fore200e.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c
index f55ffde877b5..14053e01a2cc 100644
--- a/drivers/atm/fore200e.c
+++ b/drivers/atm/fore200e.c
@@ -754,8 +754,8 @@ static int fore200e_sba_proc_read(struct fore200e *fore200e, char *page)
 
 	regs = of_get_property(op->dev.of_node, "reg", NULL);
 
-	return sprintf(page, "   SBUS slot/device:\t\t%d/'%s'\n",
-		       (regs ? regs->which_io : 0), op->dev.of_node->name);
+	return sprintf(page, "   SBUS slot/device:\t\t%d/'%pOFn'\n",
+		       (regs ? regs->which_io : 0), op->dev.of_node);
 }
 
 static const struct fore200e_bus fore200e_sbus_ops = {
-- 
cgit v1.2.3


From d7b4a2f2329e1727b31b898dba1d397e5d90a5d8 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 16 Nov 2018 16:11:03 -0600
Subject: net: fsl: Use device_type helpers to access the node type

Remove directly accessing device_node.type pointer and use the accessors
instead. This will eventually allow removing the type pointer.

Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fsl_pq_mdio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 82722d05fedb..88a396fd242f 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -473,7 +473,7 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev)
 
 	if (data->get_tbipa) {
 		for_each_child_of_node(np, tbi) {
-			if (strcmp(tbi->type, "tbi-phy") == 0) {
+			if (of_node_is_type(tbi, "tbi-phy")) {
 				dev_dbg(&pdev->dev, "found TBI PHY node %pOFP\n",
 					tbi);
 				break;
-- 
cgit v1.2.3


From a0b4371751bf836fb438877c981bda733f918988 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Sun, 18 Nov 2018 03:19:10 +0000
Subject: net: hns3: Support two vlan header when setting mtu

This patch adds supports for two vlan header when setting mtu.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c         | 5 +++--
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 2 +-
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 22220af92aa9..c944090d3adf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3609,8 +3609,9 @@ static int hns3_client_init(struct hnae3_handle *handle)
 
 	hns3_dcbnl_setup(handle);
 
-	/* MTU range: (ETH_MIN_MTU(kernel default) - 9706) */
-	netdev->max_mtu = HNS3_MAX_MTU - (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
+	/* MTU range: (ETH_MIN_MTU(kernel default) - 9702) */
+	netdev->max_mtu =
+		HNS3_MAX_MTU - (ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN);
 
 	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 33885a7529fc..019f747e486a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6364,7 +6364,7 @@ static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mtu)
 	int max_frm_size;
 	int ret;
 
-	max_frm_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+	max_frm_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN;
 
 	if (max_frm_size < HCLGE_MAC_MIN_FRAME ||
 	    max_frm_size > HCLGE_MAC_MAX_FRAME)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index ca90b662e33b..279661764910 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -120,7 +120,7 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_VECTOR0_IMP_RESET_INT_B	1
 
 #define HCLGE_MAC_DEFAULT_FRAME \
-	(ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN + ETH_DATA_LEN)
+	(ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN + ETH_DATA_LEN)
 #define HCLGE_MAC_MIN_FRAME		64
 #define HCLGE_MAC_MAX_FRAME		9728
 
-- 
cgit v1.2.3


From e6d7d79d3ed6034f9b1ffc768fdff9257b6f7fd5 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Sun, 18 Nov 2018 03:19:11 +0000
Subject: net: hns3: Refactor mac mtu setting related functions

This patch refactors mac mtu setting related functions,
normalizes the use of mps and mtu.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    |  3 +-
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    |  5 ++-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 52 +++++++++-------------
 3 files changed, 27 insertions(+), 33 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index c944090d3adf..d58d3c193ab7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3610,8 +3610,7 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	hns3_dcbnl_setup(handle);
 
 	/* MTU range: (ETH_MIN_MTU(kernel default) - 9702) */
-	netdev->max_mtu =
-		HNS3_MAX_MTU - (ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN);
+	netdev->max_mtu = HNS3_MAX_MTU;
 
 	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 3365c9596983..bbf227ba30f8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -76,7 +76,10 @@ enum hns3_nic_state {
 #define HNS3_RING_MAX_PENDING			32768
 #define HNS3_RING_MIN_PENDING			8
 #define HNS3_RING_BD_MULTIPLE			8
-#define HNS3_MAX_MTU				9728
+/* max frame size of mac */
+#define HNS3_MAC_MAX_FRAME			9728
+#define HNS3_MAX_MTU \
+	(HNS3_MAC_MAX_FRAME - (ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN))
 
 #define HNS3_BD_SIZE_512_TYPE			0
 #define HNS3_BD_SIZE_1024_TYPE			1
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 019f747e486a..0a8297f67b06 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -26,7 +26,7 @@
 #define HCLGE_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset))))
 #define HCLGE_MAC_STATS_FIELD_OFF(f) (offsetof(struct hclge_mac_stats, f))
 
-static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu);
+static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps);
 static int hclge_init_vlan_config(struct hclge_dev *hdev);
 static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev);
 static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
@@ -1969,10 +1969,7 @@ static int hclge_get_autoneg(struct hnae3_handle *handle)
 
 static int hclge_mac_init(struct hclge_dev *hdev)
 {
-	struct hnae3_handle *handle = &hdev->vport[0].nic;
-	struct net_device *netdev = handle->kinfo.netdev;
 	struct hclge_mac *mac = &hdev->hw.mac;
-	int mtu;
 	int ret;
 
 	hdev->hw.mac.duplex = HCLGE_MAC_FULL;
@@ -1986,15 +1983,16 @@ static int hclge_mac_init(struct hclge_dev *hdev)
 
 	mac->link = 0;
 
-	if (netdev)
-		mtu = netdev->mtu;
-	else
-		mtu = ETH_DATA_LEN;
+	ret = hclge_set_mac_mtu(hdev, hdev->mps);
+	if (ret) {
+		dev_err(&hdev->pdev->dev, "set mtu failed ret=%d\n", ret);
+		return ret;
+	}
 
-	ret = hclge_set_mtu(handle, mtu);
+	ret = hclge_buffer_alloc(hdev);
 	if (ret)
 		dev_err(&hdev->pdev->dev,
-			"set mtu failed ret=%d\n", ret);
+			"allocate buffer fail, ret=%d\n", ret);
 
 	return ret;
 }
@@ -6357,49 +6355,42 @@ int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 	return hclge_set_vlan_rx_offload_cfg(vport);
 }
 
-static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mtu)
+static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps)
 {
 	struct hclge_config_max_frm_size_cmd *req;
 	struct hclge_desc desc;
-	int max_frm_size;
-	int ret;
-
-	max_frm_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN;
-
-	if (max_frm_size < HCLGE_MAC_MIN_FRAME ||
-	    max_frm_size > HCLGE_MAC_MAX_FRAME)
-		return -EINVAL;
 
-	max_frm_size = max(max_frm_size, HCLGE_MAC_DEFAULT_FRAME);
+	new_mps = max(new_mps, HCLGE_MAC_DEFAULT_FRAME);
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAX_FRM_SIZE, false);
 
 	req = (struct hclge_config_max_frm_size_cmd *)desc.data;
-	req->max_frm_size = cpu_to_le16(max_frm_size);
+	req->max_frm_size = cpu_to_le16(new_mps);
 	req->min_frm_size = HCLGE_MAC_MIN_FRAME;
 
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		dev_err(&hdev->pdev->dev, "set mtu fail, ret =%d.\n", ret);
-	else
-		hdev->mps = max_frm_size;
-
-	return ret;
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
 
 static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	int ret;
+	int max_frm_size, ret;
 
-	ret = hclge_set_mac_mtu(hdev, new_mtu);
+	max_frm_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN;
+	if (max_frm_size < HCLGE_MAC_MIN_FRAME ||
+	    max_frm_size > HCLGE_MAC_MAX_FRAME)
+		return -EINVAL;
+
+	ret = hclge_set_mac_mtu(hdev, max_frm_size);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Change mtu fail, ret =%d\n", ret);
 		return ret;
 	}
 
+	hdev->mps = max_frm_size;
+
 	ret = hclge_buffer_alloc(hdev);
 	if (ret)
 		dev_err(&hdev->pdev->dev,
@@ -7021,6 +7012,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hdev->reset_type = HNAE3_NONE_RESET;
 	hdev->reset_level = HNAE3_FUNC_RESET;
 	ae_dev->priv = hdev;
+	hdev->mps = ETH_FRAME_LEN + ETH_FCS_LEN + 2 * VLAN_HLEN;
 
 	ret = hclge_pci_init(hdev);
 	if (ret) {
-- 
cgit v1.2.3


From a6d818e31d08bae09c417e579c4a39cf3d6dde2e Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Sun, 18 Nov 2018 03:19:12 +0000
Subject: net: hns3: Add vport alive state checking support

Currently there is no way for pf to know if a vf device is
alive or not, so PF does not know which vf to notify when
reset happens, or which vf's mtu is invalid when vf and pf
share the same hardware mtu setting.

This patch adds vport alive state checking support, in order
to support the above scenario.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h    |  2 +
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  6 ++
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 24 ++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 55 ++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    | 10 ++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 31 ++++++++++
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 67 +++++++++++++++++++++-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  2 +
 8 files changed, 195 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index 3bb313cdbc9f..fd2338f0c34e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -36,6 +36,8 @@ enum HCLGE_MBX_OPCODE {
 	HCLGE_MBX_BIND_FUNC_QUEUE,	/* (VF -> PF) bind function and queue */
 	HCLGE_MBX_GET_LINK_STATUS,	/* (VF -> PF) get link status */
 	HCLGE_MBX_QUEUE_RESET,		/* (VF -> PF) reset queue */
+	HCLGE_MBX_KEEP_ALIVE,		/* (VF -> PF) send keep alive cmd */
+	HCLGE_MBX_SET_ALIVE,		/* (VF -> PF) set alive state */
 };
 
 /* below are per-VF mac-vlan subcodes */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 1746172ffbf7..4a39feaba8b2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -210,6 +210,10 @@ struct hnae3_ae_dev {
  *   Enable the hardware
  * stop()
  *   Disable the hardware
+ * start_client()
+ *   Inform the hclge that client has been started
+ * stop_client()
+ *   Inform the hclge that client has been stopped
  * get_status()
  *   Get the carrier state of the back channel of the handle, 1 for ok, 0 for
  *   non-ok
@@ -319,6 +323,8 @@ struct hnae3_ae_ops {
 				       struct hnae3_ae_dev *ae_dev);
 	int (*start)(struct hnae3_handle *handle);
 	void (*stop)(struct hnae3_handle *handle);
+	int (*client_start)(struct hnae3_handle *handle);
+	void (*client_stop)(struct hnae3_handle *handle);
 	int (*get_status)(struct hnae3_handle *handle);
 	void (*get_ksettings_an_result)(struct hnae3_handle *handle,
 					u8 *auto_neg, u32 *speed, u8 *duplex);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index d58d3c193ab7..5cae14c991ee 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3540,6 +3540,22 @@ static void hns3_nic_set_priv_ops(struct net_device *netdev)
 		priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tx;
 }
 
+static int hns3_client_start(struct hnae3_handle *handle)
+{
+	if (!handle->ae_algo->ops->client_start)
+		return 0;
+
+	return handle->ae_algo->ops->client_start(handle);
+}
+
+static void hns3_client_stop(struct hnae3_handle *handle)
+{
+	if (!handle->ae_algo->ops->client_stop)
+		return;
+
+	handle->ae_algo->ops->client_stop(handle);
+}
+
 static int hns3_client_init(struct hnae3_handle *handle)
 {
 	struct pci_dev *pdev = handle->pdev;
@@ -3607,6 +3623,12 @@ static int hns3_client_init(struct hnae3_handle *handle)
 		goto out_reg_netdev_fail;
 	}
 
+	ret = hns3_client_start(handle);
+	if (ret) {
+		dev_err(priv->dev, "hns3_client_start fail! ret=%d\n", ret);
+			goto out_reg_netdev_fail;
+	}
+
 	hns3_dcbnl_setup(handle);
 
 	/* MTU range: (ETH_MIN_MTU(kernel default) - 9702) */
@@ -3635,6 +3657,8 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	int ret;
 
+	hns3_client_stop(handle);
+
 	hns3_remove_hw_addr(netdev);
 
 	if (netdev->reg_state != NETREG_UNINITIALIZED)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 0a8297f67b06..9bb7a1c21e00 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2911,6 +2911,19 @@ static void hclge_mailbox_service_task(struct work_struct *work)
 	clear_bit(HCLGE_STATE_MBX_HANDLING, &hdev->state);
 }
 
+static void hclge_update_vport_alive(struct hclge_dev *hdev)
+{
+	int i;
+
+	/* start from vport 1 for PF is always alive */
+	for (i = 1; i < hdev->num_alloc_vport; i++) {
+		struct hclge_vport *vport = &hdev->vport[i];
+
+		if (time_after(jiffies, vport->last_active_jiffies + 8 * HZ))
+			clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+	}
+}
+
 static void hclge_service_task(struct work_struct *work)
 {
 	struct hclge_dev *hdev =
@@ -2923,6 +2936,7 @@ static void hclge_service_task(struct work_struct *work)
 
 	hclge_update_speed_duplex(hdev);
 	hclge_update_link_status(hdev);
+	hclge_update_vport_alive(hdev);
 	hclge_service_complete(hdev);
 }
 
@@ -5208,6 +5222,32 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 	hclge_update_link_status(hdev);
 }
 
+int hclge_vport_start(struct hclge_vport *vport)
+{
+	set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+	vport->last_active_jiffies = jiffies;
+	return 0;
+}
+
+void hclge_vport_stop(struct hclge_vport *vport)
+{
+	clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+}
+
+static int hclge_client_start(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+
+	return hclge_vport_start(vport);
+}
+
+static void hclge_client_stop(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+
+	hclge_vport_stop(vport);
+}
+
 static int hclge_get_mac_vlan_cmd_status(struct hclge_vport *vport,
 					 u16 cmdq_resp, u8  resp_code,
 					 enum hclge_mac_vlan_tbl_opcode op)
@@ -7189,6 +7229,17 @@ static void hclge_stats_clear(struct hclge_dev *hdev)
 	memset(&hdev->hw_stats, 0, sizeof(hdev->hw_stats));
 }
 
+static void hclge_reset_vport_state(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport = hdev->vport;
+	int i;
+
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		hclge_vport_start(vport);
+		vport++;
+	}
+}
+
 static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct hclge_dev *hdev = ae_dev->priv;
@@ -7274,6 +7325,8 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 	if (hclge_enable_tm_hw_error(hdev, true))
 		dev_err(&pdev->dev, "failed to enable TM hw error interrupts\n");
 
+	hclge_reset_vport_state(hdev);
+
 	dev_info(&pdev->dev, "Reset done, %s driver initialization finished.\n",
 		 HCLGE_DRIVER_NAME);
 
@@ -7682,6 +7735,8 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_loopback = hclge_set_loopback,
 	.start = hclge_ae_start,
 	.stop = hclge_ae_stop,
+	.client_start = hclge_client_start,
+	.client_stop = hclge_client_stop,
 	.get_status = hclge_get_status,
 	.get_ksettings_an_result = hclge_get_ksettings_an_result,
 	.update_speed_duplex_h = hclge_update_speed_duplex_h,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 279661764910..5617770c9eb8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -728,6 +728,11 @@ struct hclge_rss_tuple_cfg {
 	u8 ipv6_fragment_en;
 };
 
+enum HCLGE_VPORT_STATE {
+	HCLGE_VPORT_STATE_ALIVE,
+	HCLGE_VPORT_STATE_MAX
+};
+
 struct hclge_vport {
 	u16 alloc_tqps;	/* Allocated Tx/Rx queues */
 
@@ -753,6 +758,9 @@ struct hclge_vport {
 	struct hclge_dev *back;  /* Back reference to associated dev */
 	struct hnae3_handle nic;
 	struct hnae3_handle roce;
+
+	unsigned long state;
+	unsigned long last_active_jiffies;
 };
 
 void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc,
@@ -800,4 +808,6 @@ int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id);
 void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id);
 int hclge_cfg_flowctrl(struct hclge_dev *hdev);
 int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id);
+int hclge_vport_start(struct hclge_vport *vport);
+void hclge_vport_stop(struct hclge_vport *vport);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 4c7e7bd3c847..b64f4424837d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -301,6 +301,21 @@ static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport,
 	return status;
 }
 
+static int hclge_set_vf_alive(struct hclge_vport *vport,
+			      struct hclge_mbx_vf_to_pf_cmd *mbx_req,
+			      bool gen_resp)
+{
+	bool alive = !!mbx_req->msg[2];
+	int ret = 0;
+
+	if (alive)
+		ret = hclge_vport_start(vport);
+	else
+		hclge_vport_stop(vport);
+
+	return ret;
+}
+
 static int hclge_get_vf_tcinfo(struct hclge_vport *vport,
 			       struct hclge_mbx_vf_to_pf_cmd *mbx_req,
 			       bool gen_resp)
@@ -380,6 +395,12 @@ static void hclge_reset_vf(struct hclge_vport *vport,
 	hclge_gen_resp_to_vf(vport, mbx_req, ret, NULL, 0);
 }
 
+static void hclge_vf_keep_alive(struct hclge_vport *vport,
+				struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+	vport->last_active_jiffies = jiffies;
+}
+
 static bool hclge_cmd_crq_empty(struct hclge_hw *hw)
 {
 	u32 tail = hclge_read_dev(hw, HCLGE_NIC_CRQ_TAIL_REG);
@@ -457,6 +478,13 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 					"PF failed(%d) to config VF's VLAN\n",
 					ret);
 			break;
+		case HCLGE_MBX_SET_ALIVE:
+			ret = hclge_set_vf_alive(vport, req, false);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"PF failed(%d) to set VF's ALIVE\n",
+					ret);
+			break;
 		case HCLGE_MBX_GET_QINFO:
 			ret = hclge_get_vf_queue_info(vport, req, true);
 			if (ret)
@@ -484,6 +512,9 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 		case HCLGE_MBX_RESET:
 			hclge_reset_vf(vport, req);
 			break;
+		case HCLGE_MBX_KEEP_ALIVE:
+			hclge_vf_keep_alive(vport, req);
+			break;
 		default:
 			dev_err(&hdev->pdev->dev,
 				"un-supported mailbox message, code = %d\n",
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index e27d6fa85a74..cdaa7e4207ea 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1515,6 +1515,28 @@ static void hclgevf_mailbox_service_task(struct work_struct *work)
 	clear_bit(HCLGEVF_STATE_MBX_HANDLING, &hdev->state);
 }
 
+static void hclgevf_keep_alive_timer(struct timer_list *t)
+{
+	struct hclgevf_dev *hdev = from_timer(hdev, t, keep_alive_timer);
+
+	schedule_work(&hdev->keep_alive_task);
+	mod_timer(&hdev->keep_alive_timer, jiffies + 2 * HZ);
+}
+
+static void hclgevf_keep_alive_task(struct work_struct *work)
+{
+	struct hclgevf_dev *hdev;
+	u8 respmsg;
+	int ret;
+
+	hdev = container_of(work, struct hclgevf_dev, keep_alive_task);
+	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_KEEP_ALIVE, 0, NULL,
+				   0, false, &respmsg, sizeof(u8));
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"VF sends keep alive cmd failed(=%d)\n", ret);
+}
+
 static void hclgevf_service_task(struct work_struct *work)
 {
 	struct hclgevf_dev *hdev;
@@ -1767,6 +1789,38 @@ static void hclgevf_ae_stop(struct hnae3_handle *handle)
 	hclgevf_update_link_status(hdev, 0);
 }
 
+static int hclgevf_set_alive(struct hnae3_handle *handle, bool alive)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	u8 msg_data;
+
+	msg_data = alive ? 1 : 0;
+	return hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_ALIVE,
+				    0, &msg_data, 1, false, NULL, 0);
+}
+
+static int hclgevf_client_start(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	mod_timer(&hdev->keep_alive_timer, jiffies + 2 * HZ);
+	return hclgevf_set_alive(handle, true);
+}
+
+static void hclgevf_client_stop(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int ret;
+
+	ret = hclgevf_set_alive(handle, false);
+	if (ret)
+		dev_warn(&hdev->pdev->dev,
+			 "%s failed %d\n", __func__, ret);
+
+	del_timer_sync(&hdev->keep_alive_timer);
+	cancel_work_sync(&hdev->keep_alive_task);
+}
+
 static void hclgevf_state_init(struct hclgevf_dev *hdev)
 {
 	/* setup tasks for the MBX */
@@ -2279,6 +2333,7 @@ static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev)
 static int hclgevf_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct pci_dev *pdev = ae_dev->pdev;
+	struct hclgevf_dev *hdev;
 	int ret;
 
 	ret = hclgevf_alloc_hdev(ae_dev);
@@ -2288,10 +2343,16 @@ static int hclgevf_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	}
 
 	ret = hclgevf_init_hdev(ae_dev->priv);
-	if (ret)
+	if (ret) {
 		dev_err(&pdev->dev, "hclge device initialization failed\n");
+		return ret;
+	}
 
-	return ret;
+	hdev = ae_dev->priv;
+	timer_setup(&hdev->keep_alive_timer, hclgevf_keep_alive_timer, 0);
+	INIT_WORK(&hdev->keep_alive_task, hclgevf_keep_alive_task);
+
+	return 0;
 }
 
 static void hclgevf_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
@@ -2413,6 +2474,8 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.uninit_client_instance = hclgevf_uninit_client_instance,
 	.start = hclgevf_ae_start,
 	.stop = hclgevf_ae_stop,
+	.client_start = hclgevf_client_start,
+	.client_stop = hclgevf_client_stop,
 	.map_ring_to_vector = hclgevf_map_ring_to_vector,
 	.unmap_ring_from_vector = hclgevf_unmap_ring_from_vector,
 	.get_vector = hclgevf_get_vector,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 4c5ea7edcbb1..4517b7ea5817 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -201,7 +201,9 @@ struct hclgevf_dev {
 	struct hclgevf_mbx_arq_ring arq; /* mailbox async rx queue */
 
 	struct timer_list service_timer;
+	struct timer_list keep_alive_timer;
 	struct work_struct service_task;
+	struct work_struct keep_alive_task;
 	struct work_struct rst_service_task;
 	struct work_struct mbx_service_task;
 
-- 
cgit v1.2.3


From 818f167587f402aedcf406ba57d0caff739dcad8 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Sun, 18 Nov 2018 03:19:13 +0000
Subject: net: hns3: Add mtu setting support for vf

The patch adds mtu setting support for vf, currently
vf and pf share the same hardware mtu setting. Mtu set
by vf must be less than or equal to pf' mtu, and mtu
set by pf must be greater than or equal to vf' mtu.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h    |  1 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 42 +++++++++++++++++++---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  4 +++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 18 ++++++++++
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  |  9 +++++
 5 files changed, 70 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index fd2338f0c34e..4d9cf39da48c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -38,6 +38,7 @@ enum HCLGE_MBX_OPCODE {
 	HCLGE_MBX_QUEUE_RESET,		/* (VF -> PF) reset queue */
 	HCLGE_MBX_KEEP_ALIVE,		/* (VF -> PF) send keep alive cmd */
 	HCLGE_MBX_SET_ALIVE,		/* (VF -> PF) set alive state */
+	HCLGE_MBX_SET_MTU,		/* (VF -> PF) set mtu */
 };
 
 /* below are per-VF mac-vlan subcodes */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 9bb7a1c21e00..967cb83f32d6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1166,6 +1166,7 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
 	for (i = 0; i < num_vport; i++) {
 		vport->back = hdev;
 		vport->vport_id = i;
+		vport->mps = HCLGE_MAC_DEFAULT_FRAME;
 
 		if (i == 0)
 			ret = hclge_vport_setup(vport, tqp_main_vport);
@@ -2921,6 +2922,10 @@ static void hclge_update_vport_alive(struct hclge_dev *hdev)
 
 		if (time_after(jiffies, vport->last_active_jiffies + 8 * HZ))
 			clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+
+		/* If vf is not alive, set to default value */
+		if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+			vport->mps = HCLGE_MAC_DEFAULT_FRAME;
 	}
 }
 
@@ -6400,8 +6405,6 @@ static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps)
 	struct hclge_config_max_frm_size_cmd *req;
 	struct hclge_desc desc;
 
-	new_mps = max(new_mps, HCLGE_MAC_DEFAULT_FRAME);
-
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAX_FRM_SIZE, false);
 
 	req = (struct hclge_config_max_frm_size_cmd *)desc.data;
@@ -6414,28 +6417,56 @@ static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps)
 static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
+
+	return hclge_set_vport_mtu(vport, new_mtu);
+}
+
+int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu)
+{
 	struct hclge_dev *hdev = vport->back;
-	int max_frm_size, ret;
+	int i, max_frm_size, ret = 0;
 
 	max_frm_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN;
 	if (max_frm_size < HCLGE_MAC_MIN_FRAME ||
 	    max_frm_size > HCLGE_MAC_MAX_FRAME)
 		return -EINVAL;
 
+	max_frm_size = max(max_frm_size, HCLGE_MAC_DEFAULT_FRAME);
+	mutex_lock(&hdev->vport_lock);
+	/* VF's mps must fit within hdev->mps */
+	if (vport->vport_id && max_frm_size > hdev->mps) {
+		mutex_unlock(&hdev->vport_lock);
+		return -EINVAL;
+	} else if (vport->vport_id) {
+		vport->mps = max_frm_size;
+		mutex_unlock(&hdev->vport_lock);
+		return 0;
+	}
+
+	/* PF's mps must be greater then VF's mps */
+	for (i = 1; i < hdev->num_alloc_vport; i++)
+		if (max_frm_size < hdev->vport[i].mps) {
+			mutex_unlock(&hdev->vport_lock);
+			return -EINVAL;
+		}
+
 	ret = hclge_set_mac_mtu(hdev, max_frm_size);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Change mtu fail, ret =%d\n", ret);
-		return ret;
+		goto out;
 	}
 
 	hdev->mps = max_frm_size;
+	vport->mps = max_frm_size;
 
 	ret = hclge_buffer_alloc(hdev);
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Allocate buffer fail, ret =%d\n", ret);
 
+out:
+	mutex_unlock(&hdev->vport_lock);
 	return ret;
 }
 
@@ -7054,6 +7085,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	ae_dev->priv = hdev;
 	hdev->mps = ETH_FRAME_LEN + ETH_FCS_LEN + 2 * VLAN_HLEN;
 
+	mutex_init(&hdev->vport_lock);
+
 	ret = hclge_pci_init(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "PCI init failed\n");
@@ -7353,6 +7386,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_destroy_cmd_queue(&hdev->hw);
 	hclge_misc_irq_uninit(hdev);
 	hclge_pci_uninit(hdev);
+	mutex_destroy(&hdev->vport_lock);
 	ae_dev->priv = NULL;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 5617770c9eb8..5f24dd41d7eb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -678,6 +678,8 @@ struct hclge_dev {
 
 	u32 pkt_buf_size; /* Total pf buf size for tx/rx */
 	u32 mps; /* Max packet size */
+	/* vport_lock protect resource shared by vports */
+	struct mutex vport_lock;
 
 	struct hclge_vlan_type_cfg vlan_type_cfg;
 
@@ -761,6 +763,7 @@ struct hclge_vport {
 
 	unsigned long state;
 	unsigned long last_active_jiffies;
+	u32 mps; /* Max packet size */
 };
 
 void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc,
@@ -810,4 +813,5 @@ int hclge_cfg_flowctrl(struct hclge_dev *hdev);
 int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id);
 int hclge_vport_start(struct hclge_vport *vport);
 void hclge_vport_stop(struct hclge_vport *vport);
+int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index b64f4424837d..e16a730a5f54 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -401,6 +401,18 @@ static void hclge_vf_keep_alive(struct hclge_vport *vport,
 	vport->last_active_jiffies = jiffies;
 }
 
+static int hclge_set_vf_mtu(struct hclge_vport *vport,
+			    struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+	int ret;
+	u32 mtu;
+
+	memcpy(&mtu, &mbx_req->msg[2], sizeof(mtu));
+	ret = hclge_set_vport_mtu(vport, mtu);
+
+	return hclge_gen_resp_to_vf(vport, mbx_req, ret, NULL, 0);
+}
+
 static bool hclge_cmd_crq_empty(struct hclge_hw *hw)
 {
 	u32 tail = hclge_read_dev(hw, HCLGE_NIC_CRQ_TAIL_REG);
@@ -515,6 +527,12 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 		case HCLGE_MBX_KEEP_ALIVE:
 			hclge_vf_keep_alive(vport, req);
 			break;
+		case HCLGE_MBX_SET_MTU:
+			ret = hclge_set_vf_mtu(vport, req);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"VF fail(%d) to set mtu\n", ret);
+			break;
 		default:
 			dev_err(&hdev->pdev->dev,
 				"un-supported mailbox message, code = %d\n",
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index cdaa7e4207ea..efec1b7a6a64 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1081,6 +1081,14 @@ static int hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
 				    2, true, NULL, 0);
 }
 
+static int hclgevf_set_mtu(struct hnae3_handle *handle, int new_mtu)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_MTU, 0, (u8 *)&new_mtu,
+				    sizeof(new_mtu), true, NULL, 0);
+}
+
 static int hclgevf_notify_client(struct hclgevf_dev *hdev,
 				 enum hnae3_reset_notify_type type)
 {
@@ -2513,6 +2521,7 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.ae_dev_resetting = hclgevf_ae_dev_resetting,
 	.ae_dev_reset_cnt = hclgevf_ae_dev_reset_cnt,
 	.set_gro_en = hclgevf_gro_en,
+	.set_mtu = hclgevf_set_mtu,
 };
 
 static struct hnae3_ae_algo ae_algovf = {
-- 
cgit v1.2.3


From cdca4c485d0c6467211f7181710122100552b4b9 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Sun, 18 Nov 2018 03:19:14 +0000
Subject: net: hns3: up/down netdev in hclge module when setting mtu

Currently netdev is down in enet module, and it is before
mtu range checking in hclge module, which may be cause
netdev being down unnecessarily.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c         | 11 -----------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c |  3 +++
 2 files changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 5cae14c991ee..7f81db3df041 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1573,18 +1573,11 @@ static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
 static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	bool if_running = netif_running(netdev);
 	int ret;
 
 	if (!h->ae_algo->ops->set_mtu)
 		return -EOPNOTSUPP;
 
-	/* if this was called with netdev up then bring netdevice down */
-	if (if_running) {
-		(void)hns3_nic_net_stop(netdev);
-		msleep(100);
-	}
-
 	ret = h->ae_algo->ops->set_mtu(h, new_mtu);
 	if (ret)
 		netdev_err(netdev, "failed to change MTU in hardware %d\n",
@@ -1592,10 +1585,6 @@ static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
 	else
 		netdev->mtu = new_mtu;
 
-	/* if the netdev was running earlier, bring it up again */
-	if (if_running && hns3_nic_net_open(netdev))
-		ret = -EINVAL;
-
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 967cb83f32d6..f78b8e188443 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6450,6 +6450,8 @@ int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu)
 			return -EINVAL;
 		}
 
+	hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+
 	ret = hclge_set_mac_mtu(hdev, max_frm_size);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
@@ -6466,6 +6468,7 @@ int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu)
 			"Allocate buffer fail, ret =%d\n", ret);
 
 out:
+	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
 	mutex_unlock(&hdev->vport_lock);
 	return ret;
 }
-- 
cgit v1.2.3


From 8a962c4aa1e6c0836985a5843f44d74fe3cced12 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Fri, 16 Nov 2018 18:36:27 -0700
Subject: geneve: Initialize addr6 with memset

Clang warns:

drivers/net/geneve.c:428:29: error: suggest braces around initialization
of subobject [-Werror,-Wmissing-braces]
                struct in6_addr addr6 = { 0 };
                                          ^
                                          {}

Rather than trying to appease the various compilers that support the
kernel, use memset, which is unambiguous.

Fixes: a07966447f39 ("geneve: ICMP error lookup handler")
Suggested-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 7c53e06b31c3..58bbba8582b0 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -425,7 +425,9 @@ static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_IPV6)
 	if (geneve_get_sk_family(gs) == AF_INET6) {
 		struct ipv6hdr *ip6h = ipv6_hdr(skb);
-		struct in6_addr addr6 = { 0 };
+		struct in6_addr addr6;
+
+		memset(&addr6, 0, sizeof(struct in6_addr));
 
 		if (!gs->collect_md) {
 			vni = geneve_hdr(skb)->vni;
-- 
cgit v1.2.3


From a94cbf03eb514d4d64d8c4f4caa0616b7ce5040a Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Fri, 16 Nov 2018 18:00:21 -0800
Subject: net: bcmgenet: code movement

This commit switches the order of bcmgenet_suspend and bcmgenet_resume
in the file to prevent the need for a forward declaration in the next
commit and to make the review of that commit easier.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 60 +++++++++++++-------------
 1 file changed, 30 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index bf88749505a9..01c8499fd87f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3612,36 +3612,6 @@ static int bcmgenet_remove(struct platform_device *pdev)
 }
 
 #ifdef CONFIG_PM_SLEEP
-static int bcmgenet_suspend(struct device *d)
-{
-	struct net_device *dev = dev_get_drvdata(d);
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int ret = 0;
-
-	if (!netif_running(dev))
-		return 0;
-
-	netif_device_detach(dev);
-
-	bcmgenet_netif_stop(dev);
-
-	if (!device_may_wakeup(d))
-		phy_suspend(dev->phydev);
-
-	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
-	if (device_may_wakeup(d) && priv->wolopts) {
-		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);
-		clk_prepare_enable(priv->clk_wol);
-	} else if (priv->internal_phy) {
-		ret = bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
-	}
-
-	/* Turn off the clocks */
-	clk_disable_unprepare(priv->clk);
-
-	return ret;
-}
-
 static int bcmgenet_resume(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
@@ -3719,6 +3689,36 @@ out_clk_disable:
 	clk_disable_unprepare(priv->clk);
 	return ret;
 }
+
+static int bcmgenet_suspend(struct device *d)
+{
+	struct net_device *dev = dev_get_drvdata(d);
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	int ret = 0;
+
+	if (!netif_running(dev))
+		return 0;
+
+	netif_device_detach(dev);
+
+	bcmgenet_netif_stop(dev);
+
+	if (!device_may_wakeup(d))
+		phy_suspend(dev->phydev);
+
+	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
+	if (device_may_wakeup(d) && priv->wolopts) {
+		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);
+		clk_prepare_enable(priv->clk_wol);
+	} else if (priv->internal_phy) {
+		ret = bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
+	}
+
+	/* Turn off the clocks */
+	clk_disable_unprepare(priv->clk);
+
+	return ret;
+}
 #endif /* CONFIG_PM_SLEEP */
 
 static SIMPLE_DEV_PM_OPS(bcmgenet_pm_ops, bcmgenet_suspend, bcmgenet_resume);
-- 
cgit v1.2.3


From c5a54bbcececa36852807c36157a86d808b62310 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Fri, 16 Nov 2018 18:00:22 -0800
Subject: net: bcmgenet: abort suspend on error

If an error occurs during suspension of the driver the driver should
restore the hardware configuration and return an error to force the
system to resume.

Fixes: 0db55093b566 ("net: bcmgenet: return correct value 'ret' from bcmgenet_power_down")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c     | 3 +++
 drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c | 6 ++++++
 2 files changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 01c8499fd87f..983245c0867c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3717,6 +3717,9 @@ static int bcmgenet_suspend(struct device *d)
 	/* Turn off the clocks */
 	clk_disable_unprepare(priv->clk);
 
+	if (ret)
+		bcmgenet_resume(d);
+
 	return ret;
 }
 #endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 2fbd027f0148..b3596e0ee47b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -186,9 +186,15 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	}
 
 	reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
+	if (!(reg & MPD_EN))
+		return;	/* already powered up so skip the rest */
 	reg &= ~MPD_EN;
 	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 
+	reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+	reg &= ~(RBUF_HFB_EN | RBUF_ACPI_EN);
+	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+
 	/* Disable CRC Forward */
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
 	reg &= ~CMD_CRC_FWD;
-- 
cgit v1.2.3


From 80cc49507ba48f85929f499734e4dbe2d50ecdf8 Mon Sep 17 00:00:00 2001
From: yupeng <yupeng0921@gmail.com>
Date: Fri, 16 Nov 2018 11:17:40 -0800
Subject: net: Add part of TCP counts explanations in snmp_counters.rst

Add explanations of some generic TCP counters, fast open
related counters and TCP abort related counters and several
examples.

Signed-off-by: yupeng <yupeng0921@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/snmp_counter.rst | 525 +++++++++++++++++++++++++++++-
 1 file changed, 524 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/snmp_counter.rst b/Documentation/networking/snmp_counter.rst
index e0d588fcb67f..a262d32ed710 100644
--- a/Documentation/networking/snmp_counter.rst
+++ b/Documentation/networking/snmp_counter.rst
@@ -40,7 +40,7 @@ multicast packets, and would always be updated together with
 IpExtOutOctets.
 
 * IpExtInOctets and IpExtOutOctets
-They are linux kernel extensions, no RFC definitions. Please note,
+They are Linux kernel extensions, no RFC definitions. Please note,
 RFC1213 indeed defines ifInOctets  and ifOutOctets, but they
 are different things. The ifInOctets and ifOutOctets include the MAC
 layer header size but IpExtInOctets and IpExtOutOctets don't, they
@@ -174,6 +174,163 @@ IcmpMsgOutType[N]. If the errors occur in both step (2) and step (4),
 IcmpInMsgs should be less than the sum of IcmpMsgOutType[N] plus
 IcmpInErrors.
 
+General TCP counters
+==================
+* TcpInSegs
+Defined in `RFC1213 tcpInSegs`_
+
+.. _RFC1213 tcpInSegs: https://tools.ietf.org/html/rfc1213#page-48
+
+The number of packets received by the TCP layer. As mentioned in
+RFC1213, it includes the packets received in error, such as checksum
+error, invalid TCP header and so on. Only one error won't be included:
+if the layer 2 destination address is not the NIC's layer 2
+address. It might happen if the packet is a multicast or broadcast
+packet, or the NIC is in promiscuous mode. In these situations, the
+packets would be delivered to the TCP layer, but the TCP layer will discard
+these packets before increasing TcpInSegs. The TcpInSegs counter
+isn't aware of GRO. So if two packets are merged by GRO, the TcpInSegs
+counter would only increase 1.
+
+* TcpOutSegs
+Defined in `RFC1213 tcpOutSegs`_
+
+.. _RFC1213 tcpOutSegs: https://tools.ietf.org/html/rfc1213#page-48
+
+The number of packets sent by the TCP layer. As mentioned in RFC1213,
+it excludes the retransmitted packets. But it includes the SYN, ACK
+and RST packets. Doesn't like TcpInSegs, the TcpOutSegs is aware of
+GSO, so if a packet would be split to 2 by GSO, TcpOutSegs will
+increase 2.
+
+* TcpActiveOpens
+Defined in `RFC1213 tcpActiveOpens`_
+
+.. _RFC1213 tcpActiveOpens: https://tools.ietf.org/html/rfc1213#page-47
+
+It means the TCP layer sends a SYN, and come into the SYN-SENT
+state. Every time TcpActiveOpens increases 1, TcpOutSegs should always
+increase 1.
+
+* TcpPassiveOpens
+Defined in `RFC1213 tcpPassiveOpens`_
+
+.. _RFC1213 tcpPassiveOpens: https://tools.ietf.org/html/rfc1213#page-47
+
+It means the TCP layer receives a SYN, replies a SYN+ACK, come into
+the SYN-RCVD state.
+
+TCP Fast Open
+============
+When kernel receives a TCP packet, it has two paths to handler the
+packet, one is fast path, another is slow path. The comment in kernel
+code provides a good explanation of them, I pasted them below::
+
+  It is split into a fast path and a slow path. The fast path is
+  disabled when:
+
+  - A zero window was announced from us
+  - zero window probing
+    is only handled properly on the slow path.
+  - Out of order segments arrived.
+  - Urgent data is expected.
+  - There is no buffer space left
+  - Unexpected TCP flags/window values/header lengths are received
+    (detected by checking the TCP header against pred_flags)
+  - Data is sent in both directions. The fast path only supports pure senders
+    or pure receivers (this means either the sequence number or the ack
+    value must stay constant)
+  - Unexpected TCP option.
+
+Kernel will try to use fast path unless any of the above conditions
+are satisfied. If the packets are out of order, kernel will handle
+them in slow path, which means the performance might be not very
+good. Kernel would also come into slow path if the "Delayed ack" is
+used, because when using "Delayed ack", the data is sent in both
+directions. When the TCP window scale option is not used, kernel will
+try to enable fast path immediately when the connection comes into the
+established state, but if the TCP window scale option is used, kernel
+will disable the fast path at first, and try to enable it after kernel
+receives packets.
+
+* TcpExtTCPPureAcks and TcpExtTCPHPAcks
+If a packet set ACK flag and has no data, it is a pure ACK packet, if
+kernel handles it in the fast path, TcpExtTCPHPAcks will increase 1,
+if kernel handles it in the slow path, TcpExtTCPPureAcks will
+increase 1.
+
+* TcpExtTCPHPHits
+If a TCP packet has data (which means it is not a pure ACK packet),
+and this packet is handled in the fast path, TcpExtTCPHPHits will
+increase 1.
+
+
+TCP abort
+========
+
+
+* TcpExtTCPAbortOnData
+It means TCP layer has data in flight, but need to close the
+connection. So TCP layer sends a RST to the other side, indicate the
+connection is not closed very graceful. An easy way to increase this
+counter is using the SO_LINGER option. Please refer to the SO_LINGER
+section of the `socket man page`_:
+
+.. _socket man page: http://man7.org/linux/man-pages/man7/socket.7.html
+
+By default, when an application closes a connection, the close function
+will return immediately and kernel will try to send the in-flight data
+async. If you use the SO_LINGER option, set l_onoff to 1, and l_linger
+to a positive number, the close function won't return immediately, but
+wait for the in-flight data are acked by the other side, the max wait
+time is l_linger seconds. If set l_onoff to 1 and set l_linger to 0,
+when the application closes a connection, kernel will send a RST
+immediately and increase the TcpExtTCPAbortOnData counter.
+
+* TcpExtTCPAbortOnClose
+This counter means the application has unread data in the TCP layer when
+the application wants to close the TCP connection. In such a situation,
+kernel will send a RST to the other side of the TCP connection.
+
+* TcpExtTCPAbortOnMemory
+When an application closes a TCP connection, kernel still need to track
+the connection, let it complete the TCP disconnect process. E.g. an
+app calls the close method of a socket, kernel sends fin to the other
+side of the connection, then the app has no relationship with the
+socket any more, but kernel need to keep the socket, this socket
+becomes an orphan socket, kernel waits for the reply of the other side,
+and would come to the TIME_WAIT state finally. When kernel has no
+enough memory to keep the orphan socket, kernel would send an RST to
+the other side, and delete the socket, in such situation, kernel will
+increase 1 to the TcpExtTCPAbortOnMemory. Two conditions would trigger
+TcpExtTCPAbortOnMemory:
+
+1. the memory used by the TCP protocol is higher than the third value of
+the tcp_mem. Please refer the tcp_mem section in the `TCP man page`_:
+
+.. _TCP man page: http://man7.org/linux/man-pages/man7/tcp.7.html
+
+2. the orphan socket count is higher than net.ipv4.tcp_max_orphans
+
+
+* TcpExtTCPAbortOnTimeout
+This counter will increase when any of the TCP timers expire. In such
+situation, kernel won't send RST, just give up the connection.
+
+* TcpExtTCPAbortOnLinger
+When a TCP connection comes into FIN_WAIT_2 state, instead of waiting
+for the fin packet from the other side, kernel could send a RST and
+delete the socket immediately. This is not the default behavior of
+Linux kernel TCP stack. By configuring the TCP_LINGER2 socket option,
+you could let kernel follow this behavior.
+
+* TcpExtTCPAbortFailed
+The kernel TCP layer will send RST if the `RFC2525 2.17 section`_ is
+satisfied. If an internal error occurs during this process,
+TcpExtTCPAbortFailed will be increased.
+
+.. _RFC2525 2.17 section: https://tools.ietf.org/html/rfc2525#page-50
+
 examples
 =======
 
@@ -220,3 +377,369 @@ and its corresponding Echo Reply packet are constructed by:
 * 48 bytes data (default value of the ping command)
 
 So the IpExtInOctets and IpExtOutOctets are 20+16+48=84.
+
+tcp 3-way handshake
+------------------
+On server side, we run::
+
+  nstatuser@nstat-b:~$ nc -lknv 0.0.0.0 9000
+  Listening on [0.0.0.0] (family 0, port 9000)
+
+On client side, we run::
+
+  nstatuser@nstat-a:~$ nc -nv 192.168.122.251 9000
+  Connection to 192.168.122.251 9000 port [tcp/*] succeeded!
+
+The server listened on tcp 9000 port, the client connected to it, they
+completed the 3-way handshake.
+
+On server side, we can find below nstat output::
+
+  nstatuser@nstat-b:~$ nstat | grep -i tcp
+  TcpPassiveOpens                 1                  0.0
+  TcpInSegs                       2                  0.0
+  TcpOutSegs                      1                  0.0
+  TcpExtTCPPureAcks               1                  0.0
+
+On client side, we can find below nstat output::
+
+  nstatuser@nstat-a:~$ nstat | grep -i tcp
+  TcpActiveOpens                  1                  0.0
+  TcpInSegs                       1                  0.0
+  TcpOutSegs                      2                  0.0
+
+When the server received the first SYN, it replied a SYN+ACK, and came into
+SYN-RCVD state, so TcpPassiveOpens increased 1. The server received
+SYN, sent SYN+ACK, received ACK, so server sent 1 packet, received 2
+packets, TcpInSegs increased 2, TcpOutSegs increased 1. The last ACK
+of the 3-way handshake is a pure ACK without data, so
+TcpExtTCPPureAcks increased 1.
+
+When the client sent SYN, the client came into the SYN-SENT state, so
+TcpActiveOpens increased 1, the client sent SYN, received SYN+ACK, sent
+ACK, so client sent 2 packets, received 1 packet, TcpInSegs increased
+1, TcpOutSegs increased 2.
+
+TCP normal traffic
+-----------------
+Run nc on server::
+
+  nstatuser@nstat-b:~$ nc -lkv 0.0.0.0 9000
+  Listening on [0.0.0.0] (family 0, port 9000)
+
+Run nc on client::
+
+  nstatuser@nstat-a:~$ nc -v nstat-b 9000
+  Connection to nstat-b 9000 port [tcp/*] succeeded!
+
+Input a string in the nc client ('hello' in our example)::
+
+  nstatuser@nstat-a:~$ nc -v nstat-b 9000
+  Connection to nstat-b 9000 port [tcp/*] succeeded!
+  hello
+
+The client side nstat output::
+
+  nstatuser@nstat-a:~$ nstat
+  #kernel
+  IpInReceives                    1                  0.0
+  IpInDelivers                    1                  0.0
+  IpOutRequests                   1                  0.0
+  TcpInSegs                       1                  0.0
+  TcpOutSegs                      1                  0.0
+  TcpExtTCPPureAcks               1                  0.0
+  TcpExtTCPOrigDataSent           1                  0.0
+  IpExtInOctets                   52                 0.0
+  IpExtOutOctets                  58                 0.0
+  IpExtInNoECTPkts                1                  0.0
+
+The server side nstat output::
+
+  nstatuser@nstat-b:~$ nstat
+  #kernel
+  IpInReceives                    1                  0.0
+  IpInDelivers                    1                  0.0
+  IpOutRequests                   1                  0.0
+  TcpInSegs                       1                  0.0
+  TcpOutSegs                      1                  0.0
+  IpExtInOctets                   58                 0.0
+  IpExtOutOctets                  52                 0.0
+  IpExtInNoECTPkts                1                  0.0
+
+Input a string in nc client side again ('world' in our exmaple)::
+
+  nstatuser@nstat-a:~$ nc -v nstat-b 9000
+  Connection to nstat-b 9000 port [tcp/*] succeeded!
+  hello
+  world
+
+Client side nstat output::
+
+  nstatuser@nstat-a:~$ nstat
+  #kernel
+  IpInReceives                    1                  0.0
+  IpInDelivers                    1                  0.0
+  IpOutRequests                   1                  0.0
+  TcpInSegs                       1                  0.0
+  TcpOutSegs                      1                  0.0
+  TcpExtTCPHPAcks                 1                  0.0
+  TcpExtTCPOrigDataSent           1                  0.0
+  IpExtInOctets                   52                 0.0
+  IpExtOutOctets                  58                 0.0
+  IpExtInNoECTPkts                1                  0.0
+
+
+Server side nstat output::
+
+  nstatuser@nstat-b:~$ nstat
+  #kernel
+  IpInReceives                    1                  0.0
+  IpInDelivers                    1                  0.0
+  IpOutRequests                   1                  0.0
+  TcpInSegs                       1                  0.0
+  TcpOutSegs                      1                  0.0
+  TcpExtTCPHPHits                 1                  0.0
+  IpExtInOctets                   58                 0.0
+  IpExtOutOctets                  52                 0.0
+  IpExtInNoECTPkts                1                  0.0
+
+Compare the first client-side nstat and the second client-side nstat,
+we could find one difference: the first one had a 'TcpExtTCPPureAcks',
+but the second one had a 'TcpExtTCPHPAcks'. The first server-side
+nstat and the second server-side nstat had a difference too: the
+second server-side nstat had a TcpExtTCPHPHits, but the first
+server-side nstat didn't have it. The network traffic patterns were
+exactly the same: the client sent a packet to the server, the server
+replied an ACK. But kernel handled them in different ways. When the
+TCP window scale option is not used, kernel will try to enable fast
+path immediately when the connection comes into the established state,
+but if the TCP window scale option is used, kernel will disable the
+fast path at first, and try to enable it after kerenl receives
+packets. We could use the 'ss' command to verify whether the window
+scale option is used. e.g. run below command on either server or
+client::
+
+  nstatuser@nstat-a:~$ ss -o state established -i '( dport = :9000 or sport = :9000 )
+  Netid    Recv-Q     Send-Q            Local Address:Port             Peer Address:Port
+  tcp      0          0               192.168.122.250:40654         192.168.122.251:9000
+             ts sack cubic wscale:7,7 rto:204 rtt:0.98/0.49 mss:1448 pmtu:1500 rcvmss:536 advmss:1448 cwnd:10 bytes_acked:1 segs_out:2 segs_in:1 send 118.2Mbps lastsnd:46572 lastrcv:46572 lastack:46572 pacing_rate 236.4Mbps rcv_space:29200 rcv_ssthresh:29200 minrtt:0.98
+
+The 'wscale:7,7' means both server and client set the window scale
+option to 7. Now we could explain the nstat output in our test:
+
+In the first nstat output of client side, the client sent a packet, server
+reply an ACK, when kernel handled this ACK, the fast path was not
+enabled, so the ACK was counted into 'TcpExtTCPPureAcks'.
+
+In the second nstat output of client side, the client sent a packet again,
+and received another ACK from the server, in this time, the fast path is
+enabled, and the ACK was qualified for fast path, so it was handled by
+the fast path, so this ACK was counted into TcpExtTCPHPAcks.
+
+In the first nstat output of server side, fast path was not enabled,
+so there was no 'TcpExtTCPHPHits'.
+
+In the second nstat output of server side, the fast path was enabled,
+and the packet received from client qualified for fast path, so it
+was counted into 'TcpExtTCPHPHits'.
+
+TcpExtTCPAbortOnClose
+--------------------
+On the server side, we run below python script::
+
+  import socket
+  import time
+
+  port = 9000
+
+  s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+  s.bind(('0.0.0.0', port))
+  s.listen(1)
+  sock, addr = s.accept()
+  while True:
+      time.sleep(9999999)
+
+This python script listen on 9000 port, but doesn't read anything from
+the connection.
+
+On the client side, we send the string "hello" by nc::
+
+  nstatuser@nstat-a:~$ echo "hello" | nc nstat-b 9000
+
+Then, we come back to the server side, the server has received the "hello"
+packet, and the TCP layer has acked this packet, but the application didn't
+read it yet. We type Ctrl-C to terminate the server script. Then we
+could find TcpExtTCPAbortOnClose increased 1 on the server side::
+
+  nstatuser@nstat-b:~$ nstat | grep -i abort
+  TcpExtTCPAbortOnClose           1                  0.0
+
+If we run tcpdump on the server side, we could find the server sent a
+RST after we type Ctrl-C.
+
+TcpExtTCPAbortOnMemory and TcpExtTCPAbortOnTimeout
+-----------------------------------------------
+Below is an example which let the orphan socket count be higher than
+net.ipv4.tcp_max_orphans.
+Change tcp_max_orphans to a smaller value on client::
+
+  sudo bash -c "echo 10 > /proc/sys/net/ipv4/tcp_max_orphans"
+
+Client code (create 64 connection to server)::
+
+  nstatuser@nstat-a:~$ cat client_orphan.py
+  import socket
+  import time
+
+  server = 'nstat-b' # server address
+  port = 9000
+
+  count = 64
+
+  connection_list = []
+
+  for i in range(64):
+      s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+      s.connect((server, port))
+      connection_list.append(s)
+      print("connection_count: %d" % len(connection_list))
+
+  while True:
+      time.sleep(99999)
+
+Server code (accept 64 connection from client)::
+
+  nstatuser@nstat-b:~$ cat server_orphan.py
+  import socket
+  import time
+
+  port = 9000
+  count = 64
+
+  s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+  s.bind(('0.0.0.0', port))
+  s.listen(count)
+  connection_list = []
+  while True:
+      sock, addr = s.accept()
+      connection_list.append((sock, addr))
+      print("connection_count: %d" % len(connection_list))
+
+Run the python scripts on server and client.
+
+On server::
+
+  python3 server_orphan.py
+
+On client::
+
+  python3 client_orphan.py
+
+Run iptables on server::
+
+  sudo iptables -A INPUT -i ens3 -p tcp --destination-port 9000 -j DROP
+
+Type Ctrl-C on client, stop client_orphan.py.
+
+Check TcpExtTCPAbortOnMemory on client::
+
+  nstatuser@nstat-a:~$ nstat | grep -i abort
+  TcpExtTCPAbortOnMemory          54                 0.0
+
+Check orphane socket count on client::
+
+  nstatuser@nstat-a:~$ ss -s
+  Total: 131 (kernel 0)
+  TCP:   14 (estab 1, closed 0, orphaned 10, synrecv 0, timewait 0/0), ports 0
+
+  Transport Total     IP        IPv6
+  *         0         -         -
+  RAW       1         0         1
+  UDP       1         1         0
+  TCP       14        13        1
+  INET      16        14        2
+  FRAG      0         0         0
+
+The explanation of the test: after run server_orphan.py and
+client_orphan.py, we set up 64 connections between server and
+client. Run the iptables command, the server will drop all packets from
+the client, type Ctrl-C on client_orphan.py, the system of the client
+would try to close these connections, and before they are closed
+gracefully, these connections became orphan sockets. As the iptables
+of the server blocked packets from the client, the server won't receive fin
+from the client, so all connection on clients would be stuck on FIN_WAIT_1
+stage, so they will keep as orphan sockets until timeout. We have echo
+10 to /proc/sys/net/ipv4/tcp_max_orphans, so the client system would
+only keep 10 orphan sockets, for all other orphan sockets, the client
+system sent RST for them and delete them. We have 64 connections, so
+the 'ss -s' command shows the system has 10 orphan sockets, and the
+value of TcpExtTCPAbortOnMemory was 54.
+
+An additional explanation about orphan socket count: You could find the
+exactly orphan socket count by the 'ss -s' command, but when kernel
+decide whither increases TcpExtTCPAbortOnMemory and sends RST, kernel
+doesn't always check the exactly orphan socket count. For increasing
+performance, kernel checks an approximate count firstly, if the
+approximate count is more than tcp_max_orphans, kernel checks the
+exact count again. So if the approximate count is less than
+tcp_max_orphans, but exactly count is more than tcp_max_orphans, you
+would find TcpExtTCPAbortOnMemory is not increased at all. If
+tcp_max_orphans is large enough, it won't occur, but if you decrease
+tcp_max_orphans to a small value like our test, you might find this
+issue. So in our test, the client set up 64 connections although the
+tcp_max_orphans is 10. If the client only set up 11 connections, we
+can't find the change of TcpExtTCPAbortOnMemory.
+
+Continue the previous test, we wait for several minutes. Because of the
+iptables on the server blocked the traffic, the server wouldn't receive
+fin, and all the client's orphan sockets would timeout on the
+FIN_WAIT_1 state finally. So we wait for a few minutes, we could find
+10 timeout on the client::
+
+  nstatuser@nstat-a:~$ nstat | grep -i abort
+  TcpExtTCPAbortOnTimeout         10                 0.0
+
+TcpExtTCPAbortOnLinger
+---------------------
+The server side code::
+
+  nstatuser@nstat-b:~$ cat server_linger.py
+  import socket
+  import time
+
+  port = 9000
+
+  s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+  s.bind(('0.0.0.0', port))
+  s.listen(1)
+  sock, addr = s.accept()
+  while True:
+      time.sleep(9999999)
+
+The client side code::
+
+  nstatuser@nstat-a:~$ cat client_linger.py
+  import socket
+  import struct
+
+  server = 'nstat-b' # server address
+  port = 9000
+
+  s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+  s.setsockopt(socket.SOL_SOCKET, socket.SO_LINGER, struct.pack('ii', 1, 10))
+  s.setsockopt(socket.SOL_TCP, socket.TCP_LINGER2, struct.pack('i', -1))
+  s.connect((server, port))
+  s.close()
+
+Run server_linger.py on server::
+
+  nstatuser@nstat-b:~$ python3 server_linger.py
+
+Run client_linger.py on client::
+
+  nstatuser@nstat-a:~$ python3 client_linger.py
+
+After run client_linger.py, check the output of nstat::
+
+  nstatuser@nstat-a:~$ nstat | grep -i abort
+  TcpExtTCPAbortOnLinger          1                  0.0
-- 
cgit v1.2.3


From cddaf02bcb7313a23b06e46683a1381b85840687 Mon Sep 17 00:00:00 2001
From: "thesven73@gmail.com" <thesven73@gmail.com>
Date: Sat, 17 Nov 2018 10:56:18 -0500
Subject: tg3: optionally use eth_platform_get_mac_address() to get mac address

This function will try to determine the mac address via the devicetree,
or via an architecture-specific method (e.g. a PROM on SPARC).

The SPARC-specific code in this driver (#ifdef SPARC) did exactly this,
and is therefore removed.

Note that you can now specify the tg3 mac address via the devicetree,
on any platform, not just SPARC:

Devicetree example:
(see Documentation/devicetree/bindings/pci/pci.txt)

&pcie {
	host@0 {
		#address-cells = <3>;
		#size-cells = <2>;
		reg = <0 0 0 0 0>;
		bcm5778: bcm5778@0 {
			reg = <0 0 0 0 0>;
			mac-address = [CA 11 AB 1E 10 01];
		};
	};
};

Signed-off-by: Sven Van Asbroeck <svendev@arcx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 42 ++-----------------------------------
 1 file changed, 2 insertions(+), 40 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 79b881d9cdb0..dc155c692c40 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -66,11 +66,6 @@
 #include <uapi/linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 
-#ifdef CONFIG_SPARC
-#include <asm/idprom.h>
-#include <asm/prom.h>
-#endif
-
 #define BAR_0	0
 #define BAR_2	2
 
@@ -16976,32 +16971,6 @@ static int tg3_get_invariants(struct tg3 *tp, const struct pci_device_id *ent)
 	return err;
 }
 
-#ifdef CONFIG_SPARC
-static int tg3_get_macaddr_sparc(struct tg3 *tp)
-{
-	struct net_device *dev = tp->dev;
-	struct pci_dev *pdev = tp->pdev;
-	struct device_node *dp = pci_device_to_OF_node(pdev);
-	const unsigned char *addr;
-	int len;
-
-	addr = of_get_property(dp, "local-mac-address", &len);
-	if (addr && len == ETH_ALEN) {
-		memcpy(dev->dev_addr, addr, ETH_ALEN);
-		return 0;
-	}
-	return -ENODEV;
-}
-
-static int tg3_get_default_macaddr_sparc(struct tg3 *tp)
-{
-	struct net_device *dev = tp->dev;
-
-	memcpy(dev->dev_addr, idprom->id_ethaddr, ETH_ALEN);
-	return 0;
-}
-#endif
-
 static int tg3_get_device_address(struct tg3 *tp)
 {
 	struct net_device *dev = tp->dev;
@@ -17009,10 +16978,8 @@ static int tg3_get_device_address(struct tg3 *tp)
 	int addr_ok = 0;
 	int err;
 
-#ifdef CONFIG_SPARC
-	if (!tg3_get_macaddr_sparc(tp))
+	if (!eth_platform_get_mac_address(&tp->pdev->dev, dev->dev_addr))
 		return 0;
-#endif
 
 	if (tg3_flag(tp, IS_SSB_CORE)) {
 		err = ssb_gige_get_macaddr(tp->pdev, &dev->dev_addr[0]);
@@ -17074,13 +17041,8 @@ static int tg3_get_device_address(struct tg3 *tp)
 		}
 	}
 
-	if (!is_valid_ether_addr(&dev->dev_addr[0])) {
-#ifdef CONFIG_SPARC
-		if (!tg3_get_default_macaddr_sparc(tp))
-			return 0;
-#endif
+	if (!is_valid_ether_addr(&dev->dev_addr[0]))
 		return -EINVAL;
-	}
 	return 0;
 }
 
-- 
cgit v1.2.3


From 8a49f9db47af69f736dc119c5dbd20227abd22ff Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 18 Nov 2018 22:23:53 +0100
Subject: dt-bindings: vendor-prefix: add prefix for IC Plus Corp.

IC Plus Corp. has various Ethernet related products such as Ethernet
transceivers, Ethernet controllers, Ethernet switches, etc.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/vendor-prefixes.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 4b1a2a8fcc16..cc6b2c0d3b49 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -170,6 +170,7 @@ holtek	Holtek Semiconductor, Inc.
 hwacom	HwaCom Systems Inc.
 i2se	I2SE GmbH
 ibm	International Business Machines (IBM)
+icplus	IC Plus Corp.
 idt	Integrated Device Technologies, Inc.
 ifi	Ingenieurburo Fur Ic-Technologie (I/F/I)
 ilitek	ILI Technology Corporation (ILITEK)
-- 
cgit v1.2.3


From fdc13a9effd5359ae00705708c8c846b1cb2b69c Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 18 Nov 2018 22:23:54 +0100
Subject: dt-bindings: net: phy: add bindings for the IC Plus Corp. IP101A/G
 PHYs

The IP101A and IP101G series both have various models. Depending on the
board implementation we need a special property for the IP101GR (32-pin
LQFP package) PHY:
pin 21 ("RXER/INTR_32") outputs the "receive error" signal by default
(LOW means "normal operation", HIGH means that there's either a decoding
error of the received signal or that the PHY is receiving LPI). This pin
can also be switched to INTR32 mode, where the interrupt signal is
routed to this pin. The other PHYs don't need this special handling
because they have more pins available so the interrupt function gets a
dedicated pin.

This adds two properties to either select the "receive error" or
"interrupt" function of pin 21. Not specifying any function means that
the default set by the bootloader is used. This is required because the
IP101GR cannot be differentiated between other IP101 PHYs as the PHY
identification registers on all of these is 0x02430c54.

The IP101G (sold as die only, without package) may suffer from the same
issue depending on how it's integrated into a multi chip package by
another manufacturer. If only the RXER/INTR_32 pin is routed then the
users of the die-only variant may also have to explicitly configure the
mode of hte RXER/INTR_32 pin. This is the reason why no "is-ip101gr"
property was added. I have no evidence though which would confirm this
theory - so the binding itself is independent of that.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../devicetree/bindings/net/icplus-ip101ag.txt        | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/icplus-ip101ag.txt

diff --git a/Documentation/devicetree/bindings/net/icplus-ip101ag.txt b/Documentation/devicetree/bindings/net/icplus-ip101ag.txt
new file mode 100644
index 000000000000..a784592bbb15
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/icplus-ip101ag.txt
@@ -0,0 +1,19 @@
+IC Plus Corp. IP101A / IP101G Ethernet PHYs
+
+There are different models of the IP101G Ethernet PHY:
+- IP101GR (32-pin QFN package)
+- IP101G (die only, no package)
+- IP101GA (48-pin LQFP package)
+
+There are different models of the IP101A Ethernet PHY (which is the
+predecessor of the IP101G):
+- IP101A (48-pin LQFP package)
+- IP101AH (48-pin LQFP package)
+
+Optional properties for the IP101GR (32-pin QFN package):
+
+- icplus,select-rx-error:
+  pin 21 ("RXER/INTR_32") will output the receive error status.
+  interrupts are not routed outside the PHY in this mode.
+- icplus,select-interrupt:
+  pin 21 ("RXER/INTR_32") will output the interrupt signal.
-- 
cgit v1.2.3


From 034289b2d7cf29c8ddb79cf73d4886edabcff05e Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 18 Nov 2018 22:23:55 +0100
Subject: net: phy: icplus: keep all ip101a_g functions together

This simply moves ip101a_g_config_init right above
ip101a_g_config_intr so all functions for the ICPlus IP101A/G PHYs are
grouped together.
No functional changes.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/icplus.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index ad87bd3280d7..3d3e9134c762 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -162,21 +162,6 @@ static int ip1001_config_init(struct phy_device *phydev)
 	return 0;
 }
 
-static int ip101a_g_config_init(struct phy_device *phydev)
-{
-	int c;
-
-	c = ip1xx_reset(phydev);
-	if (c < 0)
-		return c;
-
-	/* Enable Auto Power Saving mode */
-	c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS);
-	c |= IP101A_G_APS_ON;
-
-	return phy_write(phydev, IP10XX_SPEC_CTRL_STATUS, c);
-}
-
 static int ip175c_read_status(struct phy_device *phydev)
 {
 	if (phydev->mdio.addr == 4) /* WAN port */
@@ -196,6 +181,21 @@ static int ip175c_config_aneg(struct phy_device *phydev)
 	return 0;
 }
 
+static int ip101a_g_config_init(struct phy_device *phydev)
+{
+	int c;
+
+	c = ip1xx_reset(phydev);
+	if (c < 0)
+		return c;
+
+	/* Enable Auto Power Saving mode */
+	c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS);
+	c |= IP101A_G_APS_ON;
+
+	return phy_write(phydev, IP10XX_SPEC_CTRL_STATUS, c);
+}
+
 static int ip101a_g_config_intr(struct phy_device *phydev)
 {
 	u16 val;
-- 
cgit v1.2.3


From ee336140864d069d95194e8a007827363bd36da4 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 18 Nov 2018 22:23:56 +0100
Subject: net: phy: icplus: use the BIT macro where possible

This makes the code consistent by using the BIT() macro instead of
manual bit-shifting for some of the fields. No functional changes.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/icplus.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index 3d3e9134c762..3ec470adde3d 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -36,11 +36,11 @@ MODULE_LICENSE("GPL");
 
 /* IP101A/G - IP1001 */
 #define IP10XX_SPEC_CTRL_STATUS		16	/* Spec. Control Register */
-#define IP1001_RXPHASE_SEL		(1<<0)	/* Add delay on RX_CLK */
-#define IP1001_TXPHASE_SEL		(1<<1)	/* Add delay on TX_CLK */
+#define IP1001_RXPHASE_SEL		BIT(0)	/* Add delay on RX_CLK */
+#define IP1001_TXPHASE_SEL		BIT(1)	/* Add delay on TX_CLK */
 #define IP1001_SPEC_CTRL_STATUS_2	20	/* IP1001 Spec. Control Reg 2 */
 #define IP1001_APS_ON			11	/* IP1001 APS Mode  bit */
-#define IP101A_G_APS_ON			2	/* IP101A/G APS Mode bit */
+#define IP101A_G_APS_ON			BIT(1)	/* IP101A/G APS Mode bit */
 #define IP101A_G_IRQ_CONF_STATUS	0x11	/* Conf Info IRQ & Status Reg */
 #define	IP101A_G_IRQ_PIN_USED		BIT(15) /* INTR pin used */
 #define	IP101A_G_NO_IRQ			BIT(11) /* IRQ's inactive */
-- 
cgit v1.2.3


From a872c388f9d9e515d9c4102110d0bf0fd7a9778a Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 18 Nov 2018 22:23:57 +0100
Subject: net: phy: icplus: rename IP101A_G_NO_IRQ to IP101A_G_IRQ_ALL_MASK

The datasheet uses the name "All Mask" for this bit. Change the name of
our #define to be consistent with the datasheet. While here also replace
the tab between the #define and IP101A_G_IRQ_ALL_MASK with a space.
No functional changes.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/icplus.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index 3ec470adde3d..c9489ec77cef 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -43,7 +43,7 @@ MODULE_LICENSE("GPL");
 #define IP101A_G_APS_ON			BIT(1)	/* IP101A/G APS Mode bit */
 #define IP101A_G_IRQ_CONF_STATUS	0x11	/* Conf Info IRQ & Status Reg */
 #define	IP101A_G_IRQ_PIN_USED		BIT(15) /* INTR pin used */
-#define	IP101A_G_NO_IRQ			BIT(11) /* IRQ's inactive */
+#define IP101A_G_IRQ_ALL_MASK		BIT(11) /* IRQ's inactive */
 
 static int ip175c_config_init(struct phy_device *phydev)
 {
@@ -204,7 +204,7 @@ static int ip101a_g_config_intr(struct phy_device *phydev)
 		/* INTR pin used: Speed/link/duplex will cause an interrupt */
 		val = IP101A_G_IRQ_PIN_USED;
 	else
-		val = IP101A_G_NO_IRQ;
+		val = IP101A_G_IRQ_ALL_MASK;
 
 	return phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, val);
 }
-- 
cgit v1.2.3


From f7e290fbeb336421ba6237548b693c9afb4d75fa Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 18 Nov 2018 22:23:58 +0100
Subject: net: phy: icplus: implement .did_interrupt for IP101A/G

The IP101A_G_IRQ_CONF_STATUS register has bits to detect which
interrupts have fired. Implement the .did_interrupt callback to let the
PHY core know whether the interrupt was for this specific PHY.

This is useful for debugging interrupt problems with 32-pin IP101GR PHYs
where the interrupt line is shared with the RX_ERR (receive error
status) signal. The default values are:
- RX_ERR is enabled by default (LOW means that there is no receive
  error)
- the PHY's interrupt line is configured "active low" by default

Without any additional changes there is a flood of interrupts if the
RX_ERR/INTR32 signal is configured in RX_ERR mode (which is the
default). Having a did_interrupt ensures that the PHY core returns
IRQ_NONE instead of endlessly triggering the PHY state machine.
Additionally the kernel will report this after a while:
  irq 28: nobody cared (try booting with the "irqpoll" option)

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/icplus.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index c9489ec77cef..3dc8bbbe746b 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -44,6 +44,9 @@ MODULE_LICENSE("GPL");
 #define IP101A_G_IRQ_CONF_STATUS	0x11	/* Conf Info IRQ & Status Reg */
 #define	IP101A_G_IRQ_PIN_USED		BIT(15) /* INTR pin used */
 #define IP101A_G_IRQ_ALL_MASK		BIT(11) /* IRQ's inactive */
+#define IP101A_G_IRQ_SPEED_CHANGE	BIT(2)
+#define IP101A_G_IRQ_DUPLEX_CHANGE	BIT(1)
+#define IP101A_G_IRQ_LINK_CHANGE	BIT(0)
 
 static int ip175c_config_init(struct phy_device *phydev)
 {
@@ -209,6 +212,18 @@ static int ip101a_g_config_intr(struct phy_device *phydev)
 	return phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, val);
 }
 
+static int ip101a_g_did_interrupt(struct phy_device *phydev)
+{
+	int val = phy_read(phydev, IP101A_G_IRQ_CONF_STATUS);
+
+	if (val < 0)
+		return 0;
+
+	return val & (IP101A_G_IRQ_SPEED_CHANGE |
+		      IP101A_G_IRQ_DUPLEX_CHANGE |
+		      IP101A_G_IRQ_LINK_CHANGE);
+}
+
 static int ip101a_g_ack_interrupt(struct phy_device *phydev)
 {
 	int err = phy_read(phydev, IP101A_G_IRQ_CONF_STATUS);
@@ -243,6 +258,7 @@ static struct phy_driver icplus_driver[] = {
 	.phy_id_mask	= 0x0ffffff0,
 	.features	= PHY_BASIC_FEATURES,
 	.config_intr	= ip101a_g_config_intr,
+	.did_interrupt	= ip101a_g_did_interrupt,
 	.ack_interrupt	= ip101a_g_ack_interrupt,
 	.config_init	= &ip101a_g_config_init,
 	.suspend	= genphy_suspend,
-- 
cgit v1.2.3


From f2f1a847e74f61fb151e0f6f689a8485345ed1fc Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 18 Nov 2018 22:23:59 +0100
Subject: net: phy: icplus: allow configuring the interrupt function on IP101GR

The IP101GR is a 32-pin QFN package variant of the IP101G/IP101GA
Ethernet PHY. Due to it's limited amount of pins the RXER (receive
error) and INTR32 (interrupt) functions share pin 21.
By default the PHY is configured to output the "receive error" status on
pin 21. Depending on the board layout and requirements we may want to
re-configure the PHY to output the interrupt signal there.

The mode of pin 21 can be configured in the "Digital I/O Specific
Control Register" (register 29), bit 2:
- 0 = RXER function
- 1 = INTR(32) function

Depending on the devicetree configuration we will now:
- change the mode to either ther RXER or INTR32 function
- keep the SEL_INTR32 value set by the bootloader (default) if no
  configuration is provided (to ensure that we're not breaking existing
  boards)
- error out if conflicting configuration is given (RXER and INTR32 mode
  are enabled at the same time)

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/icplus.c | 81 +++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 80 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index 3dc8bbbe746b..7d5938b87660 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -25,6 +25,7 @@
 #include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/phy.h>
+#include <linux/property.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
@@ -48,6 +49,23 @@ MODULE_LICENSE("GPL");
 #define IP101A_G_IRQ_DUPLEX_CHANGE	BIT(1)
 #define IP101A_G_IRQ_LINK_CHANGE	BIT(0)
 
+#define IP101G_DIGITAL_IO_SPEC_CTRL			0x1d
+#define IP101G_DIGITAL_IO_SPEC_CTRL_SEL_INTR32		BIT(2)
+
+/* The 32-pin IP101GR package can re-configure the mode of the RXER/INTR_32 pin
+ * (pin number 21). The hardware default is RXER (receive error) mode. But it
+ * can be configured to interrupt mode manually.
+ */
+enum ip101gr_sel_intr32 {
+	IP101GR_SEL_INTR32_KEEP,
+	IP101GR_SEL_INTR32_INTR,
+	IP101GR_SEL_INTR32_RXER,
+};
+
+struct ip101a_g_phy_priv {
+	enum ip101gr_sel_intr32 sel_intr32;
+};
+
 static int ip175c_config_init(struct phy_device *phydev)
 {
 	int err, i;
@@ -184,14 +202,74 @@ static int ip175c_config_aneg(struct phy_device *phydev)
 	return 0;
 }
 
+static int ip101a_g_probe(struct phy_device *phydev)
+{
+	struct device *dev = &phydev->mdio.dev;
+	struct ip101a_g_phy_priv *priv;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	/* Both functions (RX error and interrupt status) are sharing the same
+	 * pin on the 32-pin IP101GR, so this is an exclusive choice.
+	 */
+	if (device_property_read_bool(dev, "icplus,select-rx-error") &&
+	    device_property_read_bool(dev, "icplus,select-interrupt")) {
+		dev_err(dev,
+			"RXER and INTR mode cannot be selected together\n");
+		return -EINVAL;
+	}
+
+	if (device_property_read_bool(dev, "icplus,select-rx-error"))
+		priv->sel_intr32 = IP101GR_SEL_INTR32_RXER;
+	else if (device_property_read_bool(dev, "icplus,select-interrupt"))
+		priv->sel_intr32 = IP101GR_SEL_INTR32_INTR;
+	else
+		priv->sel_intr32 = IP101GR_SEL_INTR32_KEEP;
+
+	phydev->priv = priv;
+
+	return 0;
+}
+
 static int ip101a_g_config_init(struct phy_device *phydev)
 {
-	int c;
+	struct ip101a_g_phy_priv *priv = phydev->priv;
+	int err, c;
 
 	c = ip1xx_reset(phydev);
 	if (c < 0)
 		return c;
 
+	/* configure the RXER/INTR_32 pin of the 32-pin IP101GR if needed: */
+	switch (priv->sel_intr32) {
+	case IP101GR_SEL_INTR32_RXER:
+		err = phy_modify(phydev, IP101G_DIGITAL_IO_SPEC_CTRL,
+				 IP101G_DIGITAL_IO_SPEC_CTRL_SEL_INTR32, 0);
+		if (err < 0)
+			return err;
+		break;
+
+	case IP101GR_SEL_INTR32_INTR:
+		err = phy_modify(phydev, IP101G_DIGITAL_IO_SPEC_CTRL,
+				 IP101G_DIGITAL_IO_SPEC_CTRL_SEL_INTR32,
+				 IP101G_DIGITAL_IO_SPEC_CTRL_SEL_INTR32);
+		if (err < 0)
+			return err;
+		break;
+
+	default:
+		/* Don't touch IP101G_DIGITAL_IO_SPEC_CTRL because it's not
+		 * documented on IP101A and it's not clear whether this would
+		 * cause problems.
+		 * For the 32-pin IP101GR we simply keep the SEL_INTR32
+		 * configuration as set by the bootloader when not configured
+		 * to one of the special functions.
+		 */
+		break;
+	}
+
 	/* Enable Auto Power Saving mode */
 	c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS);
 	c |= IP101A_G_APS_ON;
@@ -257,6 +335,7 @@ static struct phy_driver icplus_driver[] = {
 	.name		= "ICPlus IP101A/G",
 	.phy_id_mask	= 0x0ffffff0,
 	.features	= PHY_BASIC_FEATURES,
+	.probe		= ip101a_g_probe,
 	.config_intr	= ip101a_g_config_intr,
 	.did_interrupt	= ip101a_g_did_interrupt,
 	.ack_interrupt	= ip101a_g_ack_interrupt,
-- 
cgit v1.2.3


From aa6daacaa113cda96760c8d3157bae937908f6e3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 18 Nov 2018 07:37:33 -0800
Subject: tun: use netdev_alloc_frag() in tun_napi_alloc_frags()

In order to cook skbs in the same way than Ethernet drivers,
it is probably better to not use GFP_KERNEL, but rather
use the GFP_ATOMIC and PFMEMALLOC mechanisms provided by
netdev_alloc_frag().

This would allow to use tun driver even in memory stress
situations, especially if swap is used over this tun channel.

Fixes: 90e33d459407 ("tun: enable napi_gro_frags() for TUN/TAP driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Petar Penkov <peterpenkov96@gmail.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 36163a147d39..1e9da697081d 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1478,23 +1478,22 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile,
 	skb->truesize += skb->data_len;
 
 	for (i = 1; i < it->nr_segs; i++) {
-		struct page_frag *pfrag = &current->task_frag;
 		size_t fragsz = it->iov[i].iov_len;
+		struct page *page;
+		void *frag;
 
 		if (fragsz == 0 || fragsz > PAGE_SIZE) {
 			err = -EINVAL;
 			goto free;
 		}
-
-		if (!skb_page_frag_refill(fragsz, pfrag, GFP_KERNEL)) {
+		frag = netdev_alloc_frag(fragsz);
+		if (!frag) {
 			err = -ENOMEM;
 			goto free;
 		}
-
-		skb_fill_page_desc(skb, i - 1, pfrag->page,
-				   pfrag->offset, fragsz);
-		page_ref_inc(pfrag->page);
-		pfrag->offset += fragsz;
+		page = virt_to_head_page(frag);
+		skb_fill_page_desc(skb, i - 1, page,
+				   frag - page_address(page), fragsz);
 	}
 
 	return skb;
-- 
cgit v1.2.3


From bae4e109837b419b93fbddcb414c86673b1c90a5 Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Sun, 18 Nov 2018 16:43:03 +0000
Subject: mlxsw: spectrum: Expose discard counters via ethtool

Expose packets discard counters via ethtool to help with debugging.

Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      | 142 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 155 +++++++++++++++++++++++++
 2 files changed, 297 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index d3babcc49fd2..be2ffbd19e3a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -4235,8 +4235,11 @@ MLXSW_ITEM32(reg, ppcnt, pnat, 0x00, 14, 2);
 
 enum mlxsw_reg_ppcnt_grp {
 	MLXSW_REG_PPCNT_IEEE_8023_CNT = 0x0,
+	MLXSW_REG_PPCNT_RFC_2863_CNT = 0x1,
 	MLXSW_REG_PPCNT_RFC_2819_CNT = 0x2,
+	MLXSW_REG_PPCNT_RFC_3635_CNT = 0x3,
 	MLXSW_REG_PPCNT_EXT_CNT = 0x5,
+	MLXSW_REG_PPCNT_DISCARD_CNT = 0x6,
 	MLXSW_REG_PPCNT_PRIO_CNT = 0x10,
 	MLXSW_REG_PPCNT_TC_CNT = 0x11,
 	MLXSW_REG_PPCNT_TC_CONG_TC = 0x13,
@@ -4251,6 +4254,7 @@ enum mlxsw_reg_ppcnt_grp {
  * 0x2: RFC 2819 Counters
  * 0x3: RFC 3635 Counters
  * 0x5: Ethernet Extended Counters
+ * 0x6: Ethernet Discard Counters
  * 0x8: Link Level Retransmission Counters
  * 0x10: Per Priority Counters
  * 0x11: Per Traffic Class Counters
@@ -4394,8 +4398,46 @@ MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_received,
 MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_transmitted,
 	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x90, 0, 64);
 
+/* Ethernet RFC 2863 Counter Group */
+
+/* reg_ppcnt_if_in_discards
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, if_in_discards,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x10, 0, 64);
+
+/* reg_ppcnt_if_out_discards
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, if_out_discards,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x38, 0, 64);
+
+/* reg_ppcnt_if_out_errors
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, if_out_errors,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x40, 0, 64);
+
 /* Ethernet RFC 2819 Counter Group */
 
+/* reg_ppcnt_ether_stats_undersize_pkts
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_undersize_pkts,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x30, 0, 64);
+
+/* reg_ppcnt_ether_stats_oversize_pkts
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_oversize_pkts,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x38, 0, 64);
+
+/* reg_ppcnt_ether_stats_fragments
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_fragments,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x40, 0, 64);
+
 /* reg_ppcnt_ether_stats_pkts64octets
  * Access: RO
  */
@@ -4456,6 +4498,32 @@ MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts4096to8191octets,
 MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts8192to10239octets,
 	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0xA0, 0, 64);
 
+/* Ethernet RFC 3635 Counter Group */
+
+/* reg_ppcnt_dot3stats_fcs_errors
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, dot3stats_fcs_errors,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x08, 0, 64);
+
+/* reg_ppcnt_dot3stats_symbol_errors
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, dot3stats_symbol_errors,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x60, 0, 64);
+
+/* reg_ppcnt_dot3control_in_unknown_opcodes
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, dot3control_in_unknown_opcodes,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x68, 0, 64);
+
+/* reg_ppcnt_dot3in_pause_frames
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, dot3in_pause_frames,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64);
+
 /* Ethernet Extended Counter Group Counters */
 
 /* reg_ppcnt_ecn_marked
@@ -4464,6 +4532,80 @@ MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts8192to10239octets,
 MLXSW_ITEM64(reg, ppcnt, ecn_marked,
 	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x08, 0, 64);
 
+/* Ethernet Discard Counter Group Counters */
+
+/* reg_ppcnt_ingress_general
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ingress_general,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x00, 0, 64);
+
+/* reg_ppcnt_ingress_policy_engine
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ingress_policy_engine,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x08, 0, 64);
+
+/* reg_ppcnt_ingress_vlan_membership
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ingress_vlan_membership,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x10, 0, 64);
+
+/* reg_ppcnt_ingress_tag_frame_type
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ingress_tag_frame_type,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x18, 0, 64);
+
+/* reg_ppcnt_egress_vlan_membership
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_vlan_membership,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x20, 0, 64);
+
+/* reg_ppcnt_loopback_filter
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, loopback_filter,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x28, 0, 64);
+
+/* reg_ppcnt_egress_general
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_general,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x30, 0, 64);
+
+/* reg_ppcnt_egress_hoq
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_hoq,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x40, 0, 64);
+
+/* reg_ppcnt_egress_policy_engine
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_policy_engine,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x50, 0, 64);
+
+/* reg_ppcnt_ingress_tx_link_down
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ingress_tx_link_down,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x58, 0, 64);
+
+/* reg_ppcnt_egress_stp_filter
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_stp_filter,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x60, 0, 64);
+
+/* reg_ppcnt_egress_sll
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_sll,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64);
+
 /* Ethernet Per Priority Group Counters */
 
 /* reg_ppcnt_rx_octets
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 9bec940330a4..637e2ef76abe 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1876,7 +1876,37 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = {
 
 #define MLXSW_SP_PORT_HW_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_stats)
 
+static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_2863_stats[] = {
+	{
+		.str = "if_in_discards",
+		.getter = mlxsw_reg_ppcnt_if_in_discards_get,
+	},
+	{
+		.str = "if_out_discards",
+		.getter = mlxsw_reg_ppcnt_if_out_discards_get,
+	},
+	{
+		.str = "if_out_errors",
+		.getter = mlxsw_reg_ppcnt_if_out_errors_get,
+	},
+};
+
+#define MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN \
+	ARRAY_SIZE(mlxsw_sp_port_hw_rfc_2863_stats)
+
 static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_2819_stats[] = {
+	{
+		.str = "ether_stats_undersize_pkts",
+		.getter = mlxsw_reg_ppcnt_ether_stats_undersize_pkts_get,
+	},
+	{
+		.str = "ether_stats_oversize_pkts",
+		.getter = mlxsw_reg_ppcnt_ether_stats_oversize_pkts_get,
+	},
+	{
+		.str = "ether_stats_fragments",
+		.getter = mlxsw_reg_ppcnt_ether_stats_fragments_get,
+	},
 	{
 		.str = "ether_pkts64octets",
 		.getter = mlxsw_reg_ppcnt_ether_stats_pkts64octets_get,
@@ -1922,6 +1952,82 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_2819_stats[] = {
 #define MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN \
 	ARRAY_SIZE(mlxsw_sp_port_hw_rfc_2819_stats)
 
+static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_3635_stats[] = {
+	{
+		.str = "dot3stats_fcs_errors",
+		.getter = mlxsw_reg_ppcnt_dot3stats_fcs_errors_get,
+	},
+	{
+		.str = "dot3stats_symbol_errors",
+		.getter = mlxsw_reg_ppcnt_dot3stats_symbol_errors_get,
+	},
+	{
+		.str = "dot3control_in_unknown_opcodes",
+		.getter = mlxsw_reg_ppcnt_dot3control_in_unknown_opcodes_get,
+	},
+	{
+		.str = "dot3in_pause_frames",
+		.getter = mlxsw_reg_ppcnt_dot3in_pause_frames_get,
+	},
+};
+
+#define MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN \
+	ARRAY_SIZE(mlxsw_sp_port_hw_rfc_3635_stats)
+
+static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_discard_stats[] = {
+	{
+		.str = "discard_ingress_general",
+		.getter = mlxsw_reg_ppcnt_ingress_general_get,
+	},
+	{
+		.str = "discard_ingress_policy_engine",
+		.getter = mlxsw_reg_ppcnt_ingress_policy_engine_get,
+	},
+	{
+		.str = "discard_ingress_vlan_membership",
+		.getter = mlxsw_reg_ppcnt_ingress_vlan_membership_get,
+	},
+	{
+		.str = "discard_ingress_tag_frame_type",
+		.getter = mlxsw_reg_ppcnt_ingress_tag_frame_type_get,
+	},
+	{
+		.str = "discard_egress_vlan_membership",
+		.getter = mlxsw_reg_ppcnt_egress_vlan_membership_get,
+	},
+	{
+		.str = "discard_loopback_filter",
+		.getter = mlxsw_reg_ppcnt_loopback_filter_get,
+	},
+	{
+		.str = "discard_egress_general",
+		.getter = mlxsw_reg_ppcnt_egress_general_get,
+	},
+	{
+		.str = "discard_egress_hoq",
+		.getter = mlxsw_reg_ppcnt_egress_hoq_get,
+	},
+	{
+		.str = "discard_egress_policy_engine",
+		.getter = mlxsw_reg_ppcnt_egress_policy_engine_get,
+	},
+	{
+		.str = "discard_ingress_tx_link_down",
+		.getter = mlxsw_reg_ppcnt_ingress_tx_link_down_get,
+	},
+	{
+		.str = "discard_egress_stp_filter",
+		.getter = mlxsw_reg_ppcnt_egress_stp_filter_get,
+	},
+	{
+		.str = "discard_egress_sll",
+		.getter = mlxsw_reg_ppcnt_egress_sll_get,
+	},
+};
+
+#define MLXSW_SP_PORT_HW_DISCARD_STATS_LEN \
+	ARRAY_SIZE(mlxsw_sp_port_hw_discard_stats)
+
 static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_prio_stats[] = {
 	{
 		.str = "rx_octets_prio",
@@ -1974,7 +2080,10 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = {
 #define MLXSW_SP_PORT_HW_TC_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_tc_stats)
 
 #define MLXSW_SP_PORT_ETHTOOL_STATS_LEN (MLXSW_SP_PORT_HW_STATS_LEN + \
+					 MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN + \
 					 MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN + \
+					 MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN + \
+					 MLXSW_SP_PORT_HW_DISCARD_STATS_LEN + \
 					 (MLXSW_SP_PORT_HW_PRIO_STATS_LEN * \
 					  IEEE_8021QAZ_MAX_TCS) + \
 					 (MLXSW_SP_PORT_HW_TC_STATS_LEN * \
@@ -2015,12 +2124,31 @@ static void mlxsw_sp_port_get_strings(struct net_device *dev,
 			       ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
+
+		for (i = 0; i < MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN; i++) {
+			memcpy(p, mlxsw_sp_port_hw_rfc_2863_stats[i].str,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+
 		for (i = 0; i < MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN; i++) {
 			memcpy(p, mlxsw_sp_port_hw_rfc_2819_stats[i].str,
 			       ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
 
+		for (i = 0; i < MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN; i++) {
+			memcpy(p, mlxsw_sp_port_hw_rfc_3635_stats[i].str,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+
+		for (i = 0; i < MLXSW_SP_PORT_HW_DISCARD_STATS_LEN; i++) {
+			memcpy(p, mlxsw_sp_port_hw_discard_stats[i].str,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+
 		for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
 			mlxsw_sp_port_get_prio_strings(&p, i);
 
@@ -2063,10 +2191,22 @@ mlxsw_sp_get_hw_stats_by_group(struct mlxsw_sp_port_hw_stats **p_hw_stats,
 		*p_hw_stats = mlxsw_sp_port_hw_stats;
 		*p_len = MLXSW_SP_PORT_HW_STATS_LEN;
 		break;
+	case MLXSW_REG_PPCNT_RFC_2863_CNT:
+		*p_hw_stats = mlxsw_sp_port_hw_rfc_2863_stats;
+		*p_len = MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN;
+		break;
 	case MLXSW_REG_PPCNT_RFC_2819_CNT:
 		*p_hw_stats = mlxsw_sp_port_hw_rfc_2819_stats;
 		*p_len = MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN;
 		break;
+	case MLXSW_REG_PPCNT_RFC_3635_CNT:
+		*p_hw_stats = mlxsw_sp_port_hw_rfc_3635_stats;
+		*p_len = MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN;
+		break;
+	case MLXSW_REG_PPCNT_DISCARD_CNT:
+		*p_hw_stats = mlxsw_sp_port_hw_discard_stats;
+		*p_len = MLXSW_SP_PORT_HW_DISCARD_STATS_LEN;
+		break;
 	case MLXSW_REG_PPCNT_PRIO_CNT:
 		*p_hw_stats = mlxsw_sp_port_hw_prio_stats;
 		*p_len = MLXSW_SP_PORT_HW_PRIO_STATS_LEN;
@@ -2116,11 +2256,26 @@ static void mlxsw_sp_port_get_stats(struct net_device *dev,
 				  data, data_index);
 	data_index = MLXSW_SP_PORT_HW_STATS_LEN;
 
+	/* RFC 2863 Counters */
+	__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_RFC_2863_CNT, 0,
+				  data, data_index);
+	data_index += MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN;
+
 	/* RFC 2819 Counters */
 	__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_RFC_2819_CNT, 0,
 				  data, data_index);
 	data_index += MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN;
 
+	/* RFC 3635 Counters */
+	__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_RFC_3635_CNT, 0,
+				  data, data_index);
+	data_index += MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN;
+
+	/* Discard Counters */
+	__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_DISCARD_CNT, 0,
+				  data, data_index);
+	data_index += MLXSW_SP_PORT_HW_DISCARD_STATS_LEN;
+
 	/* Per-Priority Counters */
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
 		__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_PRIO_CNT, i,
-- 
cgit v1.2.3


From 2cc0eeb67636e0339ad7b6cdfa305f63983642af Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 18 Nov 2018 16:08:51 +0800
Subject: sctp: define subscribe in sctp_sock as __u16

The member subscribe in sctp_sock is used to indicate to which of
the events it is subscribed, more like a group of flags. So it's
better to be defined as __u16 (2 bytpes), instead of struct
sctp_event_subscribe (13 bytes).

Note that sctp_event_subscribe is an UAPI struct, used on sockopt
calls, and thus it will not be removed. This patch only changes
the internal storage of the flags.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h   |  2 +-
 include/net/sctp/ulpevent.h  | 39 ++++++++++++++++++++++++---------------
 include/uapi/linux/sctp.h    |  6 +++++-
 net/sctp/chunk.c             |  4 ++--
 net/sctp/socket.c            | 35 ++++++++++++++++++++++++++---------
 net/sctp/stream_interleave.c | 11 ++++++-----
 net/sctp/ulpqueue.c          |  8 ++++----
 7 files changed, 68 insertions(+), 37 deletions(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index af9d494120ba..bc7808aa2760 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -217,7 +217,7 @@ struct sctp_sock {
 	 * These two structures must be grouped together for the usercopy
 	 * whitelist region.
 	 */
-	struct sctp_event_subscribe subscribe;
+	__u16 subscribe;
 	struct sctp_initmsg initmsg;
 
 	int user_frag;
diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h
index 51b4e0626c34..bd922a0fe914 100644
--- a/include/net/sctp/ulpevent.h
+++ b/include/net/sctp/ulpevent.h
@@ -164,30 +164,39 @@ void sctp_ulpevent_read_nxtinfo(const struct sctp_ulpevent *event,
 
 __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event);
 
+static inline void sctp_ulpevent_type_set(__u16 *subscribe,
+					  __u16 sn_type, __u8 on)
+{
+	if (sn_type > SCTP_SN_TYPE_MAX)
+		return;
+
+	if (on)
+		*subscribe |=  (1 << (sn_type - SCTP_SN_TYPE_BASE));
+	else
+		*subscribe &= ~(1 << (sn_type - SCTP_SN_TYPE_BASE));
+}
+
 /* Is this event type enabled? */
-static inline int sctp_ulpevent_type_enabled(__u16 sn_type,
-					     struct sctp_event_subscribe *mask)
+static inline bool sctp_ulpevent_type_enabled(__u16 subscribe, __u16 sn_type)
 {
-	int offset = sn_type - SCTP_SN_TYPE_BASE;
-	char *amask = (char *) mask;
+	if (sn_type > SCTP_SN_TYPE_MAX)
+		return false;
 
-	if (offset >= sizeof(struct sctp_event_subscribe))
-		return 0;
-	return amask[offset];
+	return subscribe & (1 << (sn_type - SCTP_SN_TYPE_BASE));
 }
 
 /* Given an event subscription, is this event enabled? */
-static inline int sctp_ulpevent_is_enabled(const struct sctp_ulpevent *event,
-					   struct sctp_event_subscribe *mask)
+static inline bool sctp_ulpevent_is_enabled(const struct sctp_ulpevent *event,
+					    __u16 subscribe)
 {
 	__u16 sn_type;
-	int enabled = 1;
 
-	if (sctp_ulpevent_is_notification(event)) {
-		sn_type = sctp_ulpevent_get_notification_type(event);
-		enabled = sctp_ulpevent_type_enabled(sn_type, mask);
-	}
-	return enabled;
+	if (!sctp_ulpevent_is_notification(event))
+		return true;
+
+	sn_type = sctp_ulpevent_get_notification_type(event);
+
+	return sctp_ulpevent_type_enabled(subscribe, sn_type);
 }
 
 #endif /* __sctp_ulpevent_h__ */
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index c81feb373d3e..66afa5b4ab6b 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -632,7 +632,9 @@ union sctp_notification {
  */
 
 enum sctp_sn_type {
-	SCTP_SN_TYPE_BASE     = (1<<15),
+	SCTP_SN_TYPE_BASE	= (1<<15),
+	SCTP_DATA_IO_EVENT	= SCTP_SN_TYPE_BASE,
+#define SCTP_DATA_IO_EVENT		SCTP_DATA_IO_EVENT
 	SCTP_ASSOC_CHANGE,
 #define SCTP_ASSOC_CHANGE		SCTP_ASSOC_CHANGE
 	SCTP_PEER_ADDR_CHANGE,
@@ -657,6 +659,8 @@ enum sctp_sn_type {
 #define SCTP_ASSOC_RESET_EVENT		SCTP_ASSOC_RESET_EVENT
 	SCTP_STREAM_CHANGE_EVENT,
 #define SCTP_STREAM_CHANGE_EVENT	SCTP_STREAM_CHANGE_EVENT
+	SCTP_SN_TYPE_MAX	= SCTP_STREAM_CHANGE_EVENT,
+#define SCTP_SN_TYPE_MAX		SCTP_SN_TYPE_MAX
 };
 
 /* Notification error codes used to fill up the error fields in some
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index ce8087846f05..6c761af960fd 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -109,8 +109,8 @@ static void sctp_datamsg_destroy(struct sctp_datamsg *msg)
 				error = asoc->outqueue.error;
 
 			sp = sctp_sk(asoc->base.sk);
-			notify = sctp_ulpevent_type_enabled(SCTP_SEND_FAILED,
-							    &sp->subscribe);
+			notify = sctp_ulpevent_type_enabled(sp->subscribe,
+							    SCTP_SEND_FAILED);
 		}
 
 		/* Generate a SEND FAILED event only if enabled. */
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 5299add6d7aa..9d7512958a6a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2230,7 +2230,7 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (sp->recvrcvinfo)
 		sctp_ulpevent_read_rcvinfo(event, msg);
 	/* Check if we allow SCTP_SNDRCVINFO. */
-	if (sp->subscribe.sctp_data_io_event)
+	if (sctp_ulpevent_type_enabled(sp->subscribe, SCTP_DATA_IO_EVENT))
 		sctp_ulpevent_read_sndrcvinfo(event, msg);
 
 	err = copied;
@@ -2304,21 +2304,28 @@ static int sctp_setsockopt_disable_fragments(struct sock *sk,
 static int sctp_setsockopt_events(struct sock *sk, char __user *optval,
 				  unsigned int optlen)
 {
-	struct sctp_association *asoc;
-	struct sctp_ulpevent *event;
+	struct sctp_event_subscribe subscribe;
+	__u8 *sn_type = (__u8 *)&subscribe;
+	struct sctp_sock *sp = sctp_sk(sk);
+	int i;
 
 	if (optlen > sizeof(struct sctp_event_subscribe))
 		return -EINVAL;
-	if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen))
+
+	if (copy_from_user(&subscribe, optval, optlen))
 		return -EFAULT;
 
+	for (i = 0; i < optlen; i++)
+		sctp_ulpevent_type_set(&sp->subscribe, SCTP_SN_TYPE_BASE + i,
+				       sn_type[i]);
+
 	/* At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT,
 	 * if there is no data to be sent or retransmit, the stack will
 	 * immediately send up this notification.
 	 */
-	if (sctp_ulpevent_type_enabled(SCTP_SENDER_DRY_EVENT,
-				       &sctp_sk(sk)->subscribe)) {
-		asoc = sctp_id2assoc(sk, 0);
+	if (sctp_ulpevent_type_enabled(sp->subscribe, SCTP_SENDER_DRY_EVENT)) {
+		struct sctp_association *asoc = sctp_id2assoc(sk, 0);
+		struct sctp_ulpevent *event;
 
 		if (asoc && sctp_outq_is_empty(&asoc->outqueue)) {
 			event = sctp_ulpevent_make_sender_dry_event(asoc,
@@ -4722,7 +4729,7 @@ static int sctp_init_sock(struct sock *sk)
 	/* Initialize default event subscriptions. By default, all the
 	 * options are off.
 	 */
-	memset(&sp->subscribe, 0, sizeof(struct sctp_event_subscribe));
+	sp->subscribe = 0;
 
 	/* Default Peer Address Parameters.  These defaults can
 	 * be modified via SCTP_PEER_ADDR_PARAMS
@@ -5267,14 +5274,24 @@ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len,
 static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval,
 				  int __user *optlen)
 {
+	struct sctp_event_subscribe subscribe;
+	__u8 *sn_type = (__u8 *)&subscribe;
+	int i;
+
 	if (len == 0)
 		return -EINVAL;
 	if (len > sizeof(struct sctp_event_subscribe))
 		len = sizeof(struct sctp_event_subscribe);
 	if (put_user(len, optlen))
 		return -EFAULT;
-	if (copy_to_user(optval, &sctp_sk(sk)->subscribe, len))
+
+	for (i = 0; i < len; i++)
+		sn_type[i] = sctp_ulpevent_type_enabled(sctp_sk(sk)->subscribe,
+							SCTP_SN_TYPE_BASE + i);
+
+	if (copy_to_user(optval, &subscribe, len))
 		return -EFAULT;
+
 	return 0;
 }
 
diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c
index 2b499a85db0e..ceef5a3a5aac 100644
--- a/net/sctp/stream_interleave.c
+++ b/net/sctp/stream_interleave.c
@@ -503,7 +503,7 @@ static int sctp_enqueue_event(struct sctp_ulpq *ulpq,
 		sk_incoming_cpu_update(sk);
 	}
 
-	if (!sctp_ulpevent_is_enabled(event, &sp->subscribe))
+	if (!sctp_ulpevent_is_enabled(event, sp->subscribe))
 		goto out_free;
 
 	if (skb_list)
@@ -992,10 +992,11 @@ static void sctp_intl_stream_abort_pd(struct sctp_ulpq *ulpq, __u16 sid,
 				      __u32 mid, __u16 flags, gfp_t gfp)
 {
 	struct sock *sk = ulpq->asoc->base.sk;
+	struct sctp_sock *sp = sctp_sk(sk);
 	struct sctp_ulpevent *ev = NULL;
 
-	if (!sctp_ulpevent_type_enabled(SCTP_PARTIAL_DELIVERY_EVENT,
-					&sctp_sk(sk)->subscribe))
+	if (!sctp_ulpevent_type_enabled(sp->subscribe,
+					SCTP_PARTIAL_DELIVERY_EVENT))
 		return;
 
 	ev = sctp_ulpevent_make_pdapi(ulpq->asoc, SCTP_PARTIAL_DELIVERY_ABORTED,
@@ -1003,8 +1004,8 @@ static void sctp_intl_stream_abort_pd(struct sctp_ulpq *ulpq, __u16 sid,
 	if (ev) {
 		__skb_queue_tail(&sk->sk_receive_queue, sctp_event2skb(ev));
 
-		if (!sctp_sk(sk)->data_ready_signalled) {
-			sctp_sk(sk)->data_ready_signalled = 1;
+		if (!sp->data_ready_signalled) {
+			sp->data_ready_signalled = 1;
 			sk->sk_data_ready(sk);
 		}
 	}
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 331cc734e3db..b36dd9024da3 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -219,7 +219,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		sk_incoming_cpu_update(sk);
 	}
 	/* Check if the user wishes to receive this event.  */
-	if (!sctp_ulpevent_is_enabled(event, &sp->subscribe))
+	if (!sctp_ulpevent_is_enabled(event, sp->subscribe))
 		goto out_free;
 
 	/* If we are in partial delivery mode, post to the lobby until
@@ -1129,16 +1129,16 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 void sctp_ulpq_abort_pd(struct sctp_ulpq *ulpq, gfp_t gfp)
 {
 	struct sctp_ulpevent *ev = NULL;
-	struct sock *sk;
 	struct sctp_sock *sp;
+	struct sock *sk;
 
 	if (!ulpq->pd_mode)
 		return;
 
 	sk = ulpq->asoc->base.sk;
 	sp = sctp_sk(sk);
-	if (sctp_ulpevent_type_enabled(SCTP_PARTIAL_DELIVERY_EVENT,
-				       &sctp_sk(sk)->subscribe))
+	if (sctp_ulpevent_type_enabled(sp->subscribe,
+				       SCTP_PARTIAL_DELIVERY_EVENT))
 		ev = sctp_ulpevent_make_pdapi(ulpq->asoc,
 					      SCTP_PARTIAL_DELIVERY_ABORTED,
 					      0, 0, 0, gfp);
-- 
cgit v1.2.3


From a1e3a0590f9bd232f3a03fd87226a4a99bd5ec92 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 18 Nov 2018 16:08:52 +0800
Subject: sctp: add subscribe per asoc

The member subscribe should be per asoc, so that sockopt SCTP_EVENT
in the next patch can subscribe a event from one asoc only.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h   | 2 ++
 net/sctp/associola.c         | 2 ++
 net/sctp/chunk.c             | 6 ++----
 net/sctp/socket.c            | 6 +++++-
 net/sctp/stream_interleave.c | 7 ++++---
 net/sctp/ulpqueue.c          | 4 ++--
 6 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index bc7808aa2760..7eaa294d938d 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -2077,6 +2077,8 @@ struct sctp_association {
 
 	int sent_cnt_removable;
 
+	__u16 subscribe;
+
 	__u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
 	__u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
 };
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 6a28b96e779e..685c7ef11eb4 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -135,6 +135,8 @@ static struct sctp_association *sctp_association_init(
 	 */
 	asoc->max_burst = sp->max_burst;
 
+	asoc->subscribe = sp->subscribe;
+
 	/* initialize association timers */
 	asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE] = asoc->rto_initial;
 	asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT] = asoc->rto_initial;
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 6c761af960fd..0b203b821709 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -86,11 +86,10 @@ void sctp_datamsg_free(struct sctp_datamsg *msg)
 /* Final destructruction of datamsg memory. */
 static void sctp_datamsg_destroy(struct sctp_datamsg *msg)
 {
+	struct sctp_association *asoc = NULL;
 	struct list_head *pos, *temp;
 	struct sctp_chunk *chunk;
-	struct sctp_sock *sp;
 	struct sctp_ulpevent *ev;
-	struct sctp_association *asoc = NULL;
 	int error = 0, notify;
 
 	/* If we failed, we may need to notify. */
@@ -108,8 +107,7 @@ static void sctp_datamsg_destroy(struct sctp_datamsg *msg)
 			else
 				error = asoc->outqueue.error;
 
-			sp = sctp_sk(asoc->base.sk);
-			notify = sctp_ulpevent_type_enabled(sp->subscribe,
+			notify = sctp_ulpevent_type_enabled(asoc->subscribe,
 							    SCTP_SEND_FAILED);
 		}
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9d7512958a6a..c7718272d69b 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2307,6 +2307,7 @@ static int sctp_setsockopt_events(struct sock *sk, char __user *optval,
 	struct sctp_event_subscribe subscribe;
 	__u8 *sn_type = (__u8 *)&subscribe;
 	struct sctp_sock *sp = sctp_sk(sk);
+	struct sctp_association *asoc;
 	int i;
 
 	if (optlen > sizeof(struct sctp_event_subscribe))
@@ -2319,14 +2320,17 @@ static int sctp_setsockopt_events(struct sock *sk, char __user *optval,
 		sctp_ulpevent_type_set(&sp->subscribe, SCTP_SN_TYPE_BASE + i,
 				       sn_type[i]);
 
+	list_for_each_entry(asoc, &sp->ep->asocs, asocs)
+		asoc->subscribe = sctp_sk(sk)->subscribe;
+
 	/* At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT,
 	 * if there is no data to be sent or retransmit, the stack will
 	 * immediately send up this notification.
 	 */
 	if (sctp_ulpevent_type_enabled(sp->subscribe, SCTP_SENDER_DRY_EVENT)) {
-		struct sctp_association *asoc = sctp_id2assoc(sk, 0);
 		struct sctp_ulpevent *event;
 
+		asoc = sctp_id2assoc(sk, 0);
 		if (asoc && sctp_outq_is_empty(&asoc->outqueue)) {
 			event = sctp_ulpevent_make_sender_dry_event(asoc,
 					GFP_USER | __GFP_NOWARN);
diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c
index ceef5a3a5aac..a6bf21579466 100644
--- a/net/sctp/stream_interleave.c
+++ b/net/sctp/stream_interleave.c
@@ -503,7 +503,7 @@ static int sctp_enqueue_event(struct sctp_ulpq *ulpq,
 		sk_incoming_cpu_update(sk);
 	}
 
-	if (!sctp_ulpevent_is_enabled(event, sp->subscribe))
+	if (!sctp_ulpevent_is_enabled(event, ulpq->asoc->subscribe))
 		goto out_free;
 
 	if (skb_list)
@@ -992,16 +992,17 @@ static void sctp_intl_stream_abort_pd(struct sctp_ulpq *ulpq, __u16 sid,
 				      __u32 mid, __u16 flags, gfp_t gfp)
 {
 	struct sock *sk = ulpq->asoc->base.sk;
-	struct sctp_sock *sp = sctp_sk(sk);
 	struct sctp_ulpevent *ev = NULL;
 
-	if (!sctp_ulpevent_type_enabled(sp->subscribe,
+	if (!sctp_ulpevent_type_enabled(ulpq->asoc->subscribe,
 					SCTP_PARTIAL_DELIVERY_EVENT))
 		return;
 
 	ev = sctp_ulpevent_make_pdapi(ulpq->asoc, SCTP_PARTIAL_DELIVERY_ABORTED,
 				      sid, mid, flags, gfp);
 	if (ev) {
+		struct sctp_sock *sp = sctp_sk(sk);
+
 		__skb_queue_tail(&sk->sk_receive_queue, sctp_event2skb(ev));
 
 		if (!sp->data_ready_signalled) {
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index b36dd9024da3..5dde92101743 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -219,7 +219,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		sk_incoming_cpu_update(sk);
 	}
 	/* Check if the user wishes to receive this event.  */
-	if (!sctp_ulpevent_is_enabled(event, sp->subscribe))
+	if (!sctp_ulpevent_is_enabled(event, ulpq->asoc->subscribe))
 		goto out_free;
 
 	/* If we are in partial delivery mode, post to the lobby until
@@ -1137,7 +1137,7 @@ void sctp_ulpq_abort_pd(struct sctp_ulpq *ulpq, gfp_t gfp)
 
 	sk = ulpq->asoc->base.sk;
 	sp = sctp_sk(sk);
-	if (sctp_ulpevent_type_enabled(sp->subscribe,
+	if (sctp_ulpevent_type_enabled(ulpq->asoc->subscribe,
 				       SCTP_PARTIAL_DELIVERY_EVENT))
 		ev = sctp_ulpevent_make_pdapi(ulpq->asoc,
 					      SCTP_PARTIAL_DELIVERY_ABORTED,
-- 
cgit v1.2.3


From 88ee48c1f3b7092414fb93c3cf0838ba24f62e16 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 18 Nov 2018 16:08:53 +0800
Subject: sctp: rename enum sctp_event to sctp_event_type

sctp_event is a structure name defined in RFC for sockopt
SCTP_EVENT. To avoid the conflict, rename it.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/constants.h |  2 +-
 include/net/sctp/sm.h        |  4 ++--
 net/sctp/primitive.c         |  2 +-
 net/sctp/sm_sideeffect.c     | 12 ++++++------
 net/sctp/sm_statetable.c     |  2 +-
 5 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 8dadc74c22e7..4588bdc2b8f0 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -71,7 +71,7 @@ enum { SCTP_DEFAULT_INSTREAMS = SCTP_MAX_STREAM };
 					 SCTP_NUM_AUTH_CHUNK_TYPES)
 
 /* These are the different flavours of event.  */
-enum sctp_event {
+enum sctp_event_type {
 	SCTP_EVENT_T_CHUNK = 1,
 	SCTP_EVENT_T_TIMEOUT,
 	SCTP_EVENT_T_OTHER,
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 9e3d32746430..24825a81829e 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -173,7 +173,7 @@ sctp_state_fn_t sctp_sf_autoclose_timer_expire;
 __u8 sctp_get_chunk_type(struct sctp_chunk *chunk);
 const struct sctp_sm_table_entry *sctp_sm_lookup_event(
 					struct net *net,
-					enum sctp_event event_type,
+					enum sctp_event_type event_type,
 					enum sctp_state state,
 					union sctp_subtype event_subtype);
 int sctp_chunk_iif(const struct sctp_chunk *);
@@ -313,7 +313,7 @@ struct sctp_chunk *sctp_process_strreset_resp(
 
 /* Prototypes for statetable processing. */
 
-int sctp_do_sm(struct net *net, enum sctp_event event_type,
+int sctp_do_sm(struct net *net, enum sctp_event_type event_type,
 	       union sctp_subtype subtype, enum sctp_state state,
 	       struct sctp_endpoint *ep, struct sctp_association *asoc,
 	       void *event_arg, gfp_t gfp);
diff --git a/net/sctp/primitive.c b/net/sctp/primitive.c
index c0817f7a8964..a8c4c33377bc 100644
--- a/net/sctp/primitive.c
+++ b/net/sctp/primitive.c
@@ -53,7 +53,7 @@
 int sctp_primitive_ ## name(struct net *net, struct sctp_association *asoc, \
 			    void *arg) { \
 	int error = 0; \
-	enum sctp_event event_type; union sctp_subtype subtype; \
+	enum sctp_event_type event_type; union sctp_subtype subtype; \
 	enum sctp_state state; \
 	struct sctp_endpoint *ep; \
 	\
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 85d393090238..1d143bc3f73d 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -52,7 +52,7 @@
 #include <net/sctp/sm.h>
 #include <net/sctp/stream_sched.h>
 
-static int sctp_cmd_interpreter(enum sctp_event event_type,
+static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 				union sctp_subtype subtype,
 				enum sctp_state state,
 				struct sctp_endpoint *ep,
@@ -61,7 +61,7 @@ static int sctp_cmd_interpreter(enum sctp_event event_type,
 				enum sctp_disposition status,
 				struct sctp_cmd_seq *commands,
 				gfp_t gfp);
-static int sctp_side_effects(enum sctp_event event_type,
+static int sctp_side_effects(enum sctp_event_type event_type,
 			     union sctp_subtype subtype,
 			     enum sctp_state state,
 			     struct sctp_endpoint *ep,
@@ -623,7 +623,7 @@ static void sctp_cmd_init_failed(struct sctp_cmd_seq *commands,
 /* Worker routine to handle SCTP_CMD_ASSOC_FAILED.  */
 static void sctp_cmd_assoc_failed(struct sctp_cmd_seq *commands,
 				  struct sctp_association *asoc,
-				  enum sctp_event event_type,
+				  enum sctp_event_type event_type,
 				  union sctp_subtype subtype,
 				  struct sctp_chunk *chunk,
 				  unsigned int error)
@@ -1162,7 +1162,7 @@ static void sctp_cmd_send_asconf(struct sctp_association *asoc)
  * If you want to understand all of lksctp, this is a
  * good place to start.
  */
-int sctp_do_sm(struct net *net, enum sctp_event event_type,
+int sctp_do_sm(struct net *net, enum sctp_event_type event_type,
 	       union sctp_subtype subtype, enum sctp_state state,
 	       struct sctp_endpoint *ep, struct sctp_association *asoc,
 	       void *event_arg, gfp_t gfp)
@@ -1199,7 +1199,7 @@ int sctp_do_sm(struct net *net, enum sctp_event event_type,
 /*****************************************************************
  * This the master state function side effect processing function.
  *****************************************************************/
-static int sctp_side_effects(enum sctp_event event_type,
+static int sctp_side_effects(enum sctp_event_type event_type,
 			     union sctp_subtype subtype,
 			     enum sctp_state state,
 			     struct sctp_endpoint *ep,
@@ -1285,7 +1285,7 @@ bail:
  ********************************************************************/
 
 /* This is the side-effect interpreter.  */
-static int sctp_cmd_interpreter(enum sctp_event event_type,
+static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 				union sctp_subtype subtype,
 				enum sctp_state state,
 				struct sctp_endpoint *ep,
diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c
index 691d9dc620e3..d239b94aa48c 100644
--- a/net/sctp/sm_statetable.c
+++ b/net/sctp/sm_statetable.c
@@ -79,7 +79,7 @@ static const struct sctp_sm_table_entry bug = {
 
 const struct sctp_sm_table_entry *sctp_sm_lookup_event(
 					struct net *net,
-					enum sctp_event event_type,
+					enum sctp_event_type event_type,
 					enum sctp_state state,
 					union sctp_subtype event_subtype)
 {
-- 
cgit v1.2.3


From 480ba9c18a27ff77b02a2012e50dfd3e20ee9f7a Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 18 Nov 2018 16:08:54 +0800
Subject: sctp: add sockopt SCTP_EVENT

This patch adds sockopt SCTP_EVENT described in rfc6525#section-6.2.
With this sockopt users can subscribe to an event from a specified
asoc.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/sctp.h |  7 ++++
 net/sctp/socket.c         | 88 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 95 insertions(+)

diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 66afa5b4ab6b..d584073532b8 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -129,6 +129,7 @@ typedef __s32 sctp_assoc_t;
 #define SCTP_STREAM_SCHEDULER_VALUE	124
 #define SCTP_INTERLEAVING_SUPPORTED	125
 #define SCTP_SENDMSG_CONNECT	126
+#define SCTP_EVENT	127
 
 /* PR-SCTP policies */
 #define SCTP_PR_SCTP_NONE	0x0000
@@ -1154,6 +1155,12 @@ struct sctp_add_streams {
 	uint16_t sas_outstrms;
 };
 
+struct sctp_event {
+	sctp_assoc_t se_assoc_id;
+	uint16_t se_type;
+	uint8_t se_on;
+};
+
 /* SCTP Stream schedulers */
 enum sctp_sched_type {
 	SCTP_SS_FCFS,
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index c7718272d69b..e16c090e89f0 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4288,6 +4288,57 @@ static int sctp_setsockopt_reuse_port(struct sock *sk, char __user *optval,
 	return 0;
 }
 
+static int sctp_setsockopt_event(struct sock *sk, char __user *optval,
+				 unsigned int optlen)
+{
+	struct sctp_association *asoc;
+	struct sctp_ulpevent *event;
+	struct sctp_event param;
+	int retval = 0;
+
+	if (optlen < sizeof(param)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	optlen = sizeof(param);
+	if (copy_from_user(&param, optval, optlen)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	if (param.se_type < SCTP_SN_TYPE_BASE ||
+	    param.se_type > SCTP_SN_TYPE_MAX) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	asoc = sctp_id2assoc(sk, param.se_assoc_id);
+	if (!asoc) {
+		sctp_ulpevent_type_set(&sctp_sk(sk)->subscribe,
+				       param.se_type, param.se_on);
+		goto out;
+	}
+
+	sctp_ulpevent_type_set(&asoc->subscribe, param.se_type, param.se_on);
+
+	if (param.se_type == SCTP_SENDER_DRY_EVENT && param.se_on) {
+		if (sctp_outq_is_empty(&asoc->outqueue)) {
+			event = sctp_ulpevent_make_sender_dry_event(asoc,
+					GFP_USER | __GFP_NOWARN);
+			if (!event) {
+				retval = -ENOMEM;
+				goto out;
+			}
+
+			asoc->stream.si->enqueue_event(&asoc->ulpq, event);
+		}
+	}
+
+out:
+	return retval;
+}
+
 /* API 6.2 setsockopt(), getsockopt()
  *
  * Applications use setsockopt() and getsockopt() to set or retrieve
@@ -4485,6 +4536,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_REUSE_PORT:
 		retval = sctp_setsockopt_reuse_port(sk, optval, optlen);
 		break;
+	case SCTP_EVENT:
+		retval = sctp_setsockopt_event(sk, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -7430,6 +7484,37 @@ static int sctp_getsockopt_reuse_port(struct sock *sk, int len,
 	return 0;
 }
 
+static int sctp_getsockopt_event(struct sock *sk, int len, char __user *optval,
+				 int __user *optlen)
+{
+	struct sctp_association *asoc;
+	struct sctp_event param;
+	__u16 subscribe;
+
+	if (len < sizeof(param))
+		return -EINVAL;
+
+	len = sizeof(param);
+	if (copy_from_user(&param, optval, len))
+		return -EFAULT;
+
+	if (param.se_type < SCTP_SN_TYPE_BASE ||
+	    param.se_type > SCTP_SN_TYPE_MAX)
+		return -EINVAL;
+
+	asoc = sctp_id2assoc(sk, param.se_assoc_id);
+	subscribe = asoc ? asoc->subscribe : sctp_sk(sk)->subscribe;
+	param.se_on = sctp_ulpevent_type_enabled(subscribe, param.se_type);
+
+	if (put_user(len, optlen))
+		return -EFAULT;
+
+	if (copy_to_user(optval, &param, len))
+		return -EFAULT;
+
+	return 0;
+}
+
 static int sctp_getsockopt(struct sock *sk, int level, int optname,
 			   char __user *optval, int __user *optlen)
 {
@@ -7628,6 +7713,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	case SCTP_REUSE_PORT:
 		retval = sctp_getsockopt_reuse_port(sk, len, optval, optlen);
 		break;
+	case SCTP_EVENT:
+		retval = sctp_getsockopt_event(sk, len, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
-- 
cgit v1.2.3


From 23499442c319412aa8e54e7a939e2eb531bdd77d Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 19 Nov 2018 14:49:01 -0800
Subject: bpf: libbpf: retry map creation without the name

Since commit 88cda1c9da02 ("bpf: libbpf: Provide basic API support
to specify BPF obj name"), libbpf unconditionally sets bpf_attr->name
for maps. Pre v4.14 kernels don't know about map names and return an
error about unexpected non-zero data. Retry sys_bpf without a map
name to cover older kernels.

v2 changes:
* check for errno == EINVAL as suggested by Daniel Borkmann

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/bpf.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 03f9bcc4ef50..961e1b9fc592 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -69,6 +69,7 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 {
 	__u32 name_len = create_attr->name ? strlen(create_attr->name) : 0;
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, '\0', sizeof(attr));
 
@@ -86,7 +87,15 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 	attr.map_ifindex = create_attr->map_ifindex;
 	attr.inner_map_fd = create_attr->inner_map_fd;
 
-	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	if (ret < 0 && errno == EINVAL && create_attr->name) {
+		/* Retry the same syscall, but without the name.
+		 * Pre v4.14 kernels don't support map names.
+		 */
+		memset(attr.map_name, 0, sizeof(attr.map_name));
+		return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	}
+	return ret;
 }
 
 int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
-- 
cgit v1.2.3


From 96b3b6c9091d23289721350e32c63cc8749686be Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Fri, 16 Nov 2018 11:41:08 +0000
Subject: bpf: allow zero-initializing hash map seed

Add a new flag BPF_F_ZERO_SEED, which forces a hash map
to initialize the seed to zero. This is useful when doing
performance analysis both on individual BPF programs, as
well as the kernel's hash table implementation.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h |  3 +++
 kernel/bpf/hashtab.c     | 13 +++++++++++--
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 47d606d744cc..8c01b89a4cb4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -269,6 +269,9 @@ enum bpf_attach_type {
 /* Flag for stack_map, store build_id+offset instead of pointer */
 #define BPF_F_STACK_BUILD_ID	(1U << 5)
 
+/* Zero-initialize hash function seed. This should only be used for testing. */
+#define BPF_F_ZERO_SEED		(1U << 6)
+
 enum bpf_stack_build_id_status {
 	/* user space need an empty entry to identify end of a trace */
 	BPF_STACK_BUILD_ID_EMPTY = 0,
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 2c1790288138..4b7c76765d9d 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -23,7 +23,7 @@
 
 #define HTAB_CREATE_FLAG_MASK						\
 	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE |	\
-	 BPF_F_RDONLY | BPF_F_WRONLY)
+	 BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED)
 
 struct bucket {
 	struct hlist_nulls_head head;
@@ -244,6 +244,7 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 	 */
 	bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
 	bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
+	bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED);
 	int numa_node = bpf_map_attr_numa_node(attr);
 
 	BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
@@ -257,6 +258,10 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 		 */
 		return -EPERM;
 
+	if (zero_seed && !capable(CAP_SYS_ADMIN))
+		/* Guard against local DoS, and discourage production use. */
+		return -EPERM;
+
 	if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
 		/* reserved bits should not be used */
 		return -EINVAL;
@@ -373,7 +378,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	if (!htab->buckets)
 		goto free_htab;
 
-	htab->hashrnd = get_random_int();
+	if (htab->map.map_flags & BPF_F_ZERO_SEED)
+		htab->hashrnd = 0;
+	else
+		htab->hashrnd = get_random_int();
+
 	for (i = 0; i < htab->n_buckets; i++) {
 		INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
 		raw_spin_lock_init(&htab->buckets[i].lock);
-- 
cgit v1.2.3


From 2f1833607aed6a9c1e1729bf0e2588c341ceb409 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Fri, 16 Nov 2018 11:41:09 +0000
Subject: bpf: move BPF_F_QUERY_EFFECTIVE after map flags

BPF_F_QUERY_EFFECTIVE is in the middle of the flags valid
for BPF_MAP_CREATE. Move it to its own section to reduce confusion.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8c01b89a4cb4..05d95290b848 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -257,9 +257,6 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
-/* flags for BPF_PROG_QUERY */
-#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
-
 #define BPF_OBJ_NAME_LEN 16U
 
 /* Flags for accessing BPF object */
@@ -272,6 +269,9 @@ enum bpf_attach_type {
 /* Zero-initialize hash function seed. This should only be used for testing. */
 #define BPF_F_ZERO_SEED		(1U << 6)
 
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
+
 enum bpf_stack_build_id_status {
 	/* user space need an empty entry to identify end of a trace */
 	BPF_STACK_BUILD_ID_EMPTY = 0,
-- 
cgit v1.2.3


From 608114e441ad3a4fa1fced4d6d00653a34765eee Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Fri, 16 Nov 2018 11:41:10 +0000
Subject: tools: sync linux/bpf.h

Synchronize changes to linux/bpf.h from
* "bpf: allow zero-initializing hash map seed"
* "bpf: move BPF_F_QUERY_EFFECTIVE after map flags"

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 852dc17ab47a..05d95290b848 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -257,9 +257,6 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
-/* flags for BPF_PROG_QUERY */
-#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
-
 #define BPF_OBJ_NAME_LEN 16U
 
 /* Flags for accessing BPF object */
@@ -269,6 +266,12 @@ enum bpf_attach_type {
 /* Flag for stack_map, store build_id+offset instead of pointer */
 #define BPF_F_STACK_BUILD_ID	(1U << 5)
 
+/* Zero-initialize hash function seed. This should only be used for testing. */
+#define BPF_F_ZERO_SEED		(1U << 6)
+
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
+
 enum bpf_stack_build_id_status {
 	/* user space need an empty entry to identify end of a trace */
 	BPF_STACK_BUILD_ID_EMPTY = 0,
@@ -2201,6 +2204,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, *struct bpf_sock*
+ *		return is from reuse->socks[] using hash of the packet.
  *
  * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
  *	Description
@@ -2233,6 +2238,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, *struct bpf_sock*
+ *		return is from reuse->socks[] using hash of the packet.
  *
  * int bpf_sk_release(struct bpf_sock *sk)
  *	Description
-- 
cgit v1.2.3


From bf5d68c7304008ef838f1a2ca1aae8fab74d633d Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Fri, 16 Nov 2018 11:41:11 +0000
Subject: tools: add selftest for BPF_F_ZERO_SEED

Check that iterating two separate hash maps produces the same
order of keys if BPF_F_ZERO_SEED is used.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_maps.c | 64 ++++++++++++++++++++++++++++-----
 1 file changed, 55 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 4db2116e52be..9f0a5b16a246 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -258,24 +258,36 @@ static void test_hashmap_percpu(int task, void *data)
 	close(fd);
 }
 
-static void test_hashmap_walk(int task, void *data)
+static int helper_fill_hashmap(int max_entries)
 {
-	int fd, i, max_entries = 1000;
-	long long key, value, next_key;
-	bool next_key_valid = true;
+	int i, fd, ret;
+	long long key, value;
 
 	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
 			    max_entries, map_flags);
-	if (fd < 0) {
-		printf("Failed to create hashmap '%s'!\n", strerror(errno));
-		exit(1);
-	}
+	CHECK(fd < 0,
+	      "failed to create hashmap",
+	      "err: %s, flags: 0x%x\n", strerror(errno), map_flags);
 
 	for (i = 0; i < max_entries; i++) {
 		key = i; value = key;
-		assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == 0);
+		ret = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+		CHECK(ret != 0,
+		      "can't update hashmap",
+		      "err: %s\n", strerror(ret));
 	}
 
+	return fd;
+}
+
+static void test_hashmap_walk(int task, void *data)
+{
+	int fd, i, max_entries = 1000;
+	long long key, value, next_key;
+	bool next_key_valid = true;
+
+	fd = helper_fill_hashmap(max_entries);
+
 	for (i = 0; bpf_map_get_next_key(fd, !i ? NULL : &key,
 					 &next_key) == 0; i++) {
 		key = next_key;
@@ -306,6 +318,39 @@ static void test_hashmap_walk(int task, void *data)
 	close(fd);
 }
 
+static void test_hashmap_zero_seed(void)
+{
+	int i, first, second, old_flags;
+	long long key, next_first, next_second;
+
+	old_flags = map_flags;
+	map_flags |= BPF_F_ZERO_SEED;
+
+	first = helper_fill_hashmap(3);
+	second = helper_fill_hashmap(3);
+
+	for (i = 0; ; i++) {
+		void *key_ptr = !i ? NULL : &key;
+
+		if (bpf_map_get_next_key(first, key_ptr, &next_first) != 0)
+			break;
+
+		CHECK(bpf_map_get_next_key(second, key_ptr, &next_second) != 0,
+		      "next_key for second map must succeed",
+		      "key_ptr: %p", key_ptr);
+		CHECK(next_first != next_second,
+		      "keys must match",
+		      "i: %d first: %lld second: %lld\n", i,
+		      next_first, next_second);
+
+		key = next_first;
+	}
+
+	map_flags = old_flags;
+	close(first);
+	close(second);
+}
+
 static void test_arraymap(int task, void *data)
 {
 	int key, next_key, fd;
@@ -1534,6 +1579,7 @@ static void run_all_tests(void)
 	test_hashmap(0, NULL);
 	test_hashmap_percpu(0, NULL);
 	test_hashmap_walk(0, NULL);
+	test_hashmap_zero_seed();
 
 	test_arraymap(0, NULL);
 	test_arraymap_percpu(0, NULL);
-- 
cgit v1.2.3


From fe716f8a33abf1ce14e0982bb02cd6e429bd25b7 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 19 Nov 2018 22:31:32 +0100
Subject: r8169: merge rtl_irq_enable and rtl_irq_enable_all

After the recent changes to the interrupt handler rtl_irq_enable and
rtl_irq_enable_all can be merged.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index b3010cc51cdd..f235d184e55b 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1334,18 +1334,13 @@ static void rtl_irq_disable(struct rtl8169_private *tp)
 	mmiowb();
 }
 
-static void rtl_irq_enable(struct rtl8169_private *tp, u16 bits)
-{
-	RTL_W16(tp, IntrMask, bits);
-}
-
 #define RTL_EVENT_NAPI_RX	(RxOK | RxErr)
 #define RTL_EVENT_NAPI_TX	(TxOK | TxErr)
 #define RTL_EVENT_NAPI		(RTL_EVENT_NAPI_RX | RTL_EVENT_NAPI_TX)
 
-static void rtl_irq_enable_all(struct rtl8169_private *tp)
+static void rtl_irq_enable(struct rtl8169_private *tp)
 {
-	rtl_irq_enable(tp, RTL_EVENT_NAPI | tp->event_slow);
+	RTL_W16(tp, IntrMask, RTL_EVENT_NAPI | tp->event_slow);
 }
 
 static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
@@ -4643,7 +4638,7 @@ static void rtl_hw_start(struct  rtl8169_private *tp)
 	rtl_set_rx_mode(tp->dev);
 	/* no early-rx interrupts */
 	RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000);
-	rtl_irq_enable_all(tp);
+	rtl_irq_enable(tp);
 }
 
 static void rtl_hw_start_8169(struct rtl8169_private *tp)
@@ -6533,7 +6528,7 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
 
-		rtl_irq_enable_all(tp);
+		rtl_irq_enable(tp);
 		mmiowb();
 	}
 
-- 
cgit v1.2.3


From 0f07bd850d3656b2a02815ba7965dc30d30f49f0 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 19 Nov 2018 22:32:18 +0100
Subject: r8169: use dev_get_drvdata where possible

Using dev_get_drvdata directly is simpler here.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f235d184e55b..8d5e9ac9d406 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6819,8 +6819,7 @@ static void rtl8169_net_suspend(struct net_device *dev)
 
 static int rtl8169_suspend(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct rtl8169_private *tp = netdev_priv(dev);
 
 	rtl8169_net_suspend(dev);
@@ -6850,8 +6849,7 @@ static void __rtl8169_resume(struct net_device *dev)
 
 static int rtl8169_resume(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct rtl8169_private *tp = netdev_priv(dev);
 
 	clk_prepare_enable(tp->clk);
@@ -6864,8 +6862,7 @@ static int rtl8169_resume(struct device *device)
 
 static int rtl8169_runtime_suspend(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct rtl8169_private *tp = netdev_priv(dev);
 
 	if (!tp->TxDescArray)
@@ -6886,8 +6883,7 @@ static int rtl8169_runtime_suspend(struct device *device)
 
 static int rtl8169_runtime_resume(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct rtl8169_private *tp = netdev_priv(dev);
 	rtl_rar_set(tp, dev->dev_addr);
 
@@ -6905,8 +6901,7 @@ static int rtl8169_runtime_resume(struct device *device)
 
 static int rtl8169_runtime_idle(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 
 	if (!netif_running(dev) || !netif_carrier_ok(dev))
 		pm_schedule_suspend(device, 10000);
-- 
cgit v1.2.3


From 97ad92f28342ffd6be1452eafbc0b7f6a9028747 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 19 Nov 2018 22:33:00 +0100
Subject: r8169: remove unused interrupt sources

Setting PCSTimeout interrupt source was copied from the vendor driver
which uses the chip programmable timer interrupt. The mainline driver
doesn't use this timer interrupt.

SYSErr indicates a PCI error and isn't defined on the PCIe models.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 8d5e9ac9d406..bf36b4ed04fb 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5389,7 +5389,7 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp)
 
 	/* Work around for RxFIFO overflow. */
 	if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
-		tp->event_slow |= RxFIFOOver | PCSTimeout;
+		tp->event_slow |= RxFIFOOver;
 		tp->event_slow &= ~RxOverflow;
 	}
 
@@ -7027,15 +7027,14 @@ static const struct rtl_cfg_info {
 	},
 	[RTL_CFG_1] = {
 		.hw_start	= rtl_hw_start_8168,
-		.event_slow	= SYSErr | LinkChg | RxOverflow,
+		.event_slow	= LinkChg | RxOverflow,
 		.has_gmii	= 1,
 		.coalesce_info	= rtl_coalesce_info_8168_8136,
 		.default_ver	= RTL_GIGA_MAC_VER_11,
 	},
 	[RTL_CFG_2] = {
 		.hw_start	= rtl_hw_start_8101,
-		.event_slow	= SYSErr | LinkChg | RxOverflow | RxFIFOOver |
-				  PCSTimeout,
+		.event_slow	= LinkChg | RxOverflow | RxFIFOOver,
 		.coalesce_info	= rtl_coalesce_info_8168_8136,
 		.default_ver	= RTL_GIGA_MAC_VER_13,
 	}
-- 
cgit v1.2.3


From 559c3c046d4b4f52715ffdac7572302010b6d648 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 19 Nov 2018 22:34:17 +0100
Subject: r8169: replace event_slow with irq_mask

Recently the "slow event" handler was removed, therefore the member
name isn't appropriate any longer. In addition store the full mask,
including the RTL_EVENT_NAPI interrupt source bits.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index bf36b4ed04fb..5d6eb38c635b 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -661,7 +661,7 @@ struct rtl8169_private {
 	struct ring_info tx_skb[NUM_TX_DESC];	/* Tx data buffers */
 	u16 cp_cmd;
 
-	u16 event_slow;
+	u16 irq_mask;
 	const struct rtl_coalesce_info *coalesce_info;
 	struct clk *clk;
 
@@ -1340,7 +1340,7 @@ static void rtl_irq_disable(struct rtl8169_private *tp)
 
 static void rtl_irq_enable(struct rtl8169_private *tp)
 {
-	RTL_W16(tp, IntrMask, RTL_EVENT_NAPI | tp->event_slow);
+	RTL_W16(tp, IntrMask, tp->irq_mask);
 }
 
 static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
@@ -5389,8 +5389,8 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp)
 
 	/* Work around for RxFIFO overflow. */
 	if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
-		tp->event_slow |= RxFIFOOver;
-		tp->event_slow &= ~RxOverflow;
+		tp->irq_mask |= RxFIFOOver;
+		tp->irq_mask &= ~RxOverflow;
 	}
 
 	switch (tp->mac_version) {
@@ -5627,7 +5627,7 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp)
 static void rtl_hw_start_8101(struct rtl8169_private *tp)
 {
 	if (tp->mac_version >= RTL_GIGA_MAC_VER_30)
-		tp->event_slow &= ~RxFIFOOver;
+		tp->irq_mask &= ~RxFIFOOver;
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_13 ||
 	    tp->mac_version == RTL_GIGA_MAC_VER_16)
@@ -6456,7 +6456,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 	struct rtl8169_private *tp = dev_instance;
 	u16 status = rtl_get_events(tp);
 
-	if (status == 0xffff || !(status & (RTL_EVENT_NAPI | tp->event_slow)))
+	if (status == 0xffff || !(status & tp->irq_mask))
 		return IRQ_NONE;
 
 	if (unlikely(status & SYSErr)) {
@@ -7013,28 +7013,28 @@ static const struct net_device_ops rtl_netdev_ops = {
 
 static const struct rtl_cfg_info {
 	void (*hw_start)(struct rtl8169_private *tp);
-	u16 event_slow;
+	u16 irq_mask;
 	unsigned int has_gmii:1;
 	const struct rtl_coalesce_info *coalesce_info;
 	u8 default_ver;
 } rtl_cfg_infos [] = {
 	[RTL_CFG_0] = {
 		.hw_start	= rtl_hw_start_8169,
-		.event_slow	= SYSErr | LinkChg | RxOverflow | RxFIFOOver,
+		.irq_mask	= SYSErr | LinkChg | RxOverflow | RxFIFOOver,
 		.has_gmii	= 1,
 		.coalesce_info	= rtl_coalesce_info_8169,
 		.default_ver	= RTL_GIGA_MAC_VER_01,
 	},
 	[RTL_CFG_1] = {
 		.hw_start	= rtl_hw_start_8168,
-		.event_slow	= LinkChg | RxOverflow,
+		.irq_mask	= LinkChg | RxOverflow,
 		.has_gmii	= 1,
 		.coalesce_info	= rtl_coalesce_info_8168_8136,
 		.default_ver	= RTL_GIGA_MAC_VER_11,
 	},
 	[RTL_CFG_2] = {
 		.hw_start	= rtl_hw_start_8101,
-		.event_slow	= LinkChg | RxOverflow | RxFIFOOver,
+		.irq_mask	= LinkChg | RxOverflow | RxFIFOOver,
 		.coalesce_info	= rtl_coalesce_info_8168_8136,
 		.default_ver	= RTL_GIGA_MAC_VER_13,
 	}
@@ -7415,7 +7415,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->max_mtu = jumbo_max;
 
 	tp->hw_start = cfg->hw_start;
-	tp->event_slow = cfg->event_slow;
+	tp->irq_mask = RTL_EVENT_NAPI | cfg->irq_mask;
 	tp->coalesce_info = cfg->coalesce_info;
 
 	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
-- 
cgit v1.2.3


From 6f0d308855a26fd20c1994a322a3ebee768e0615 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 19 Nov 2018 22:35:08 +0100
Subject: r8169: use PCI_VDEVICE macro

Using macro PCI_VDEVICE helps to simplify the PCI ID table.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 5d6eb38c635b..243aa60ad4c0 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -212,24 +212,24 @@ enum cfg_version {
 };
 
 static const struct pci_device_id rtl8169_pci_tbl[] = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8129), 0, 0, RTL_CFG_0 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8136), 0, 0, RTL_CFG_2 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8161), 0, 0, RTL_CFG_1 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8167), 0, 0, RTL_CFG_0 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8168), 0, 0, RTL_CFG_1 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_NCUBE,	0x8168), 0, 0, RTL_CFG_1 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8169), 0, 0, RTL_CFG_0 },
-	{ PCI_VENDOR_ID_DLINK,			0x4300,
-		PCI_VENDOR_ID_DLINK, 0x4b10,		 0, 0, RTL_CFG_1 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_DLINK,	0x4300), 0, 0, RTL_CFG_0 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_DLINK,	0x4302), 0, 0, RTL_CFG_0 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_AT,		0xc107), 0, 0, RTL_CFG_0 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_USR,		0x0116), 0, 0, RTL_CFG_0 },
+	{ PCI_VDEVICE(REALTEK,	0x8129), RTL_CFG_0 },
+	{ PCI_VDEVICE(REALTEK,	0x8136), RTL_CFG_2 },
+	{ PCI_VDEVICE(REALTEK,	0x8161), RTL_CFG_1 },
+	{ PCI_VDEVICE(REALTEK,	0x8167), RTL_CFG_0 },
+	{ PCI_VDEVICE(REALTEK,	0x8168), RTL_CFG_1 },
+	{ PCI_VDEVICE(NCUBE,	0x8168), RTL_CFG_1 },
+	{ PCI_VDEVICE(REALTEK,	0x8169), RTL_CFG_0 },
+	{ PCI_VENDOR_ID_DLINK,	0x4300,
+		PCI_VENDOR_ID_DLINK, 0x4b10, 0, 0, RTL_CFG_1 },
+	{ PCI_VDEVICE(DLINK,	0x4300), RTL_CFG_0 },
+	{ PCI_VDEVICE(DLINK,	0x4302), RTL_CFG_0 },
+	{ PCI_VDEVICE(AT,	0xc107), RTL_CFG_0 },
+	{ PCI_VDEVICE(USR,	0x0116), RTL_CFG_0 },
 	{ PCI_VENDOR_ID_LINKSYS,		0x1032,
 		PCI_ANY_ID, 0x0024, 0, 0, RTL_CFG_0 },
 	{ 0x0001,				0x8168,
 		PCI_ANY_ID, 0x2410, 0, 0, RTL_CFG_2 },
-	{0,},
+	{}
 };
 
 MODULE_DEVICE_TABLE(pci, rtl8169_pci_tbl);
-- 
cgit v1.2.3


From 8c0511ec52c8f5030602b2e8f9ab5a4913949bfe Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 19 Nov 2018 22:36:15 +0100
Subject: r8169: remove print_mac_version

The syslog message printed on driver load allows to easily identify
the mac version number (based on chip name and XID). So we don't
need this extra debug message which is wrong anyway because e.g.
RTL_GIGA_MAC_VER_01 has value 0.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 243aa60ad4c0..cf1f75f602be 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -2170,11 +2170,6 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 	}
 }
 
-static void rtl8169_print_mac_version(struct rtl8169_private *tp)
-{
-	netif_dbg(tp, drv, tp->dev, "mac_version = 0x%02x\n", tp->mac_version);
-}
-
 struct phy_reg {
 	u16 reg;
 	u16 val;
@@ -3897,8 +3892,6 @@ static void rtl_hw_phy_config(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	rtl8169_print_mac_version(tp);
-
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_01:
 		break;
@@ -7340,8 +7333,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	rtl_init_mdio_ops(tp);
 	rtl_init_jumbo_ops(tp);
 
-	rtl8169_print_mac_version(tp);
-
 	chipset = tp->mac_version;
 
 	rc = rtl_alloc_irq(tp);
-- 
cgit v1.2.3


From b10ceb55710dd2574fd61ed54fd94aab263f4af3 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 19 Nov 2018 22:37:34 +0100
Subject: r8169: remove "not PCI Express" message

The ones who want to know can easily identify whether chip is PCI or
PCIe based on the chip name. I doubt there's any benefit in this
message, so remove it.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index cf1f75f602be..f7a6b18ee42d 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -7291,9 +7291,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	tp->mmio_addr = pcim_iomap_table(pdev)[region];
 
-	if (!pci_is_pcie(pdev))
-		dev_info(&pdev->dev, "not PCI Express\n");
-
 	/* Identify chip attached to board */
 	rtl8169_get_mac_version(tp, cfg->default_ver);
 
-- 
cgit v1.2.3


From ad45ff0c12e530dd52b8c9ecc46959fb4e468e2b Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 19 Nov 2018 22:38:22 +0100
Subject: r8169: remove manual padding in struct ring_info

The compiler takes care of alignment and padding, I see no need to
bother him with manual hints.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f7a6b18ee42d..0f74576db989 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -603,7 +603,6 @@ struct RxDesc {
 struct ring_info {
 	struct sk_buff	*skb;
 	u32		len;
-	u8		__pad[sizeof(void *) - sizeof(u32)];
 };
 
 struct rtl8169_counters {
-- 
cgit v1.2.3


From 8b6dd85666e217c1e16396b08ccb855524025f28 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 19 Nov 2018 22:39:14 +0100
Subject: r8169: remove workaround for ancient gcc bug

The kernel can't be built any longer with this ancient GCC version.
Eventually it becomes clear what this statement actually does.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 0f74576db989..3eb01a40fba2 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5903,9 +5903,9 @@ static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb,
 			goto err_out;
 		}
 
-		/* Anti gcc 2.95.3 bugware (sic) */
-		status = opts[0] | len |
-			(RingEnd * !((entry + 1) % NUM_TX_DESC));
+		status = opts[0] | len;
+		if (entry == NUM_TX_DESC - 1)
+			status |= RingEnd;
 
 		txd->opts1 = cpu_to_le32(status);
 		txd->opts2 = cpu_to_le32(opts[1]);
-- 
cgit v1.2.3


From 3c72bf71a97fe4125270b2b618aaa6266f80a825 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 19 Nov 2018 22:40:04 +0100
Subject: r8169: simplify ocp functions

rtl8168_oob_notify is used in rtl8168dp_driver_start and
rtl8168dp_driver_stop only, so we can rename it to r8168dp_oob_notify.
The same applies to condition rtl_ocp_read_cond which can be renamed
to rtl_dp_ocp_read_cond. This allows to simplify the code.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 68 +++++++++---------------------------
 1 file changed, 17 insertions(+), 51 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 3eb01a40fba2..b3937eb5af5e 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1101,23 +1101,6 @@ static u32 r8168ep_ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
 	return rtl_eri_read(tp, reg, ERIAR_OOB);
 }
 
-static u32 ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
-{
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_27:
-	case RTL_GIGA_MAC_VER_28:
-	case RTL_GIGA_MAC_VER_31:
-		return r8168dp_ocp_read(tp, mask, reg);
-	case RTL_GIGA_MAC_VER_49:
-	case RTL_GIGA_MAC_VER_50:
-	case RTL_GIGA_MAC_VER_51:
-		return r8168ep_ocp_read(tp, mask, reg);
-	default:
-		BUG();
-		return ~0;
-	}
-}
-
 static void r8168dp_ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg,
 			      u32 data)
 {
@@ -1133,30 +1116,11 @@ static void r8168ep_ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg,
 		      data, ERIAR_OOB);
 }
 
-static void ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg, u32 data)
-{
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_27:
-	case RTL_GIGA_MAC_VER_28:
-	case RTL_GIGA_MAC_VER_31:
-		r8168dp_ocp_write(tp, mask, reg, data);
-		break;
-	case RTL_GIGA_MAC_VER_49:
-	case RTL_GIGA_MAC_VER_50:
-	case RTL_GIGA_MAC_VER_51:
-		r8168ep_ocp_write(tp, mask, reg, data);
-		break;
-	default:
-		BUG();
-		break;
-	}
-}
-
-static void rtl8168_oob_notify(struct rtl8169_private *tp, u8 cmd)
+static void r8168dp_oob_notify(struct rtl8169_private *tp, u8 cmd)
 {
 	rtl_eri_write(tp, 0xe8, ERIAR_MASK_0001, cmd, ERIAR_EXGMAC);
 
-	ocp_write(tp, 0x1, 0x30, 0x00000001);
+	r8168dp_ocp_write(tp, 0x1, 0x30, 0x00000001);
 }
 
 #define OOB_CMD_RESET		0x00
@@ -1168,18 +1132,18 @@ static u16 rtl8168_get_ocp_reg(struct rtl8169_private *tp)
 	return (tp->mac_version == RTL_GIGA_MAC_VER_31) ? 0xb8 : 0x10;
 }
 
-DECLARE_RTL_COND(rtl_ocp_read_cond)
+DECLARE_RTL_COND(rtl_dp_ocp_read_cond)
 {
 	u16 reg;
 
 	reg = rtl8168_get_ocp_reg(tp);
 
-	return ocp_read(tp, 0x0f, reg) & 0x00000800;
+	return r8168dp_ocp_read(tp, 0x0f, reg) & 0x00000800;
 }
 
 DECLARE_RTL_COND(rtl_ep_ocp_read_cond)
 {
-	return ocp_read(tp, 0x0f, 0x124) & 0x00000001;
+	return r8168ep_ocp_read(tp, 0x0f, 0x124) & 0x00000001;
 }
 
 DECLARE_RTL_COND(rtl_ocp_tx_cond)
@@ -1197,14 +1161,15 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp)
 
 static void rtl8168dp_driver_start(struct rtl8169_private *tp)
 {
-	rtl8168_oob_notify(tp, OOB_CMD_DRIVER_START);
-	rtl_msleep_loop_wait_high(tp, &rtl_ocp_read_cond, 10, 10);
+	r8168dp_oob_notify(tp, OOB_CMD_DRIVER_START);
+	rtl_msleep_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10, 10);
 }
 
 static void rtl8168ep_driver_start(struct rtl8169_private *tp)
 {
-	ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START);
-	ocp_write(tp, 0x01, 0x30, ocp_read(tp, 0x01, 0x30) | 0x01);
+	r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START);
+	r8168ep_ocp_write(tp, 0x01, 0x30,
+			  r8168ep_ocp_read(tp, 0x01, 0x30) | 0x01);
 	rtl_msleep_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10, 10);
 }
 
@@ -1229,15 +1194,16 @@ static void rtl8168_driver_start(struct rtl8169_private *tp)
 
 static void rtl8168dp_driver_stop(struct rtl8169_private *tp)
 {
-	rtl8168_oob_notify(tp, OOB_CMD_DRIVER_STOP);
-	rtl_msleep_loop_wait_low(tp, &rtl_ocp_read_cond, 10, 10);
+	r8168dp_oob_notify(tp, OOB_CMD_DRIVER_STOP);
+	rtl_msleep_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10, 10);
 }
 
 static void rtl8168ep_driver_stop(struct rtl8169_private *tp)
 {
 	rtl8168ep_stop_cmac(tp);
-	ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_STOP);
-	ocp_write(tp, 0x01, 0x30, ocp_read(tp, 0x01, 0x30) | 0x01);
+	r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_STOP);
+	r8168ep_ocp_write(tp, 0x01, 0x30,
+			  r8168ep_ocp_read(tp, 0x01, 0x30) | 0x01);
 	rtl_msleep_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10, 10);
 }
 
@@ -1264,12 +1230,12 @@ static bool r8168dp_check_dash(struct rtl8169_private *tp)
 {
 	u16 reg = rtl8168_get_ocp_reg(tp);
 
-	return !!(ocp_read(tp, 0x0f, reg) & 0x00008000);
+	return !!(r8168dp_ocp_read(tp, 0x0f, reg) & 0x00008000);
 }
 
 static bool r8168ep_check_dash(struct rtl8169_private *tp)
 {
-	return !!(ocp_read(tp, 0x0f, 0x128) & 0x00000001);
+	return !!(r8168ep_ocp_read(tp, 0x0f, 0x128) & 0x00000001);
 }
 
 static bool r8168_check_dash(struct rtl8169_private *tp)
-- 
cgit v1.2.3


From 55d2ad7b907225e476dd10b69683e508a6bed7f4 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 19 Nov 2018 22:41:35 +0100
Subject: r8169: improve chip version identification

Only the upper 12 bits are used for chip identification, this helps
to reduce the size of array mac_info.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 119 +++++++++++++++++------------------
 1 file changed, 59 insertions(+), 60 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index b3937eb5af5e..b15cb1ca88b8 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -2026,92 +2026,91 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 	 * (RTL_R32(tp, TxConfig) & 0x700000) == 0x200000 ? 8101Eb : 8101Ec
 	 */
 	static const struct rtl_mac_info {
-		u32 mask;
-		u32 val;
-		int mac_version;
+		u16 mask;
+		u16 val;
+		u16 mac_version;
 	} mac_info[] = {
 		/* 8168EP family. */
-		{ 0x7cf00000, 0x50200000,	RTL_GIGA_MAC_VER_51 },
-		{ 0x7cf00000, 0x50100000,	RTL_GIGA_MAC_VER_50 },
-		{ 0x7cf00000, 0x50000000,	RTL_GIGA_MAC_VER_49 },
+		{ 0x7cf, 0x502,	RTL_GIGA_MAC_VER_51 },
+		{ 0x7cf, 0x501,	RTL_GIGA_MAC_VER_50 },
+		{ 0x7cf, 0x500,	RTL_GIGA_MAC_VER_49 },
 
 		/* 8168H family. */
-		{ 0x7cf00000, 0x54100000,	RTL_GIGA_MAC_VER_46 },
-		{ 0x7cf00000, 0x54000000,	RTL_GIGA_MAC_VER_45 },
+		{ 0x7cf, 0x541,	RTL_GIGA_MAC_VER_46 },
+		{ 0x7cf, 0x540,	RTL_GIGA_MAC_VER_45 },
 
 		/* 8168G family. */
-		{ 0x7cf00000, 0x5c800000,	RTL_GIGA_MAC_VER_44 },
-		{ 0x7cf00000, 0x50900000,	RTL_GIGA_MAC_VER_42 },
-		{ 0x7cf00000, 0x4c100000,	RTL_GIGA_MAC_VER_41 },
-		{ 0x7cf00000, 0x4c000000,	RTL_GIGA_MAC_VER_40 },
+		{ 0x7cf, 0x5c8,	RTL_GIGA_MAC_VER_44 },
+		{ 0x7cf, 0x509,	RTL_GIGA_MAC_VER_42 },
+		{ 0x7cf, 0x4c1,	RTL_GIGA_MAC_VER_41 },
+		{ 0x7cf, 0x4c0,	RTL_GIGA_MAC_VER_40 },
 
 		/* 8168F family. */
-		{ 0x7c800000, 0x48800000,	RTL_GIGA_MAC_VER_38 },
-		{ 0x7cf00000, 0x48100000,	RTL_GIGA_MAC_VER_36 },
-		{ 0x7cf00000, 0x48000000,	RTL_GIGA_MAC_VER_35 },
+		{ 0x7c8, 0x488,	RTL_GIGA_MAC_VER_38 },
+		{ 0x7cf, 0x481,	RTL_GIGA_MAC_VER_36 },
+		{ 0x7cf, 0x480,	RTL_GIGA_MAC_VER_35 },
 
 		/* 8168E family. */
-		{ 0x7c800000, 0x2c800000,	RTL_GIGA_MAC_VER_34 },
-		{ 0x7cf00000, 0x2c100000,	RTL_GIGA_MAC_VER_32 },
-		{ 0x7c800000, 0x2c000000,	RTL_GIGA_MAC_VER_33 },
+		{ 0x7c8, 0x2c8,	RTL_GIGA_MAC_VER_34 },
+		{ 0x7cf, 0x2c1,	RTL_GIGA_MAC_VER_32 },
+		{ 0x7c8, 0x2c0,	RTL_GIGA_MAC_VER_33 },
 
 		/* 8168D family. */
-		{ 0x7cf00000, 0x28100000,	RTL_GIGA_MAC_VER_25 },
-		{ 0x7c800000, 0x28000000,	RTL_GIGA_MAC_VER_26 },
+		{ 0x7cf, 0x281,	RTL_GIGA_MAC_VER_25 },
+		{ 0x7c8, 0x280,	RTL_GIGA_MAC_VER_26 },
 
 		/* 8168DP family. */
-		{ 0x7cf00000, 0x28800000,	RTL_GIGA_MAC_VER_27 },
-		{ 0x7cf00000, 0x28a00000,	RTL_GIGA_MAC_VER_28 },
-		{ 0x7cf00000, 0x28b00000,	RTL_GIGA_MAC_VER_31 },
+		{ 0x7cf, 0x288,	RTL_GIGA_MAC_VER_27 },
+		{ 0x7cf, 0x28a,	RTL_GIGA_MAC_VER_28 },
+		{ 0x7cf, 0x28b,	RTL_GIGA_MAC_VER_31 },
 
 		/* 8168C family. */
-		{ 0x7cf00000, 0x3c900000,	RTL_GIGA_MAC_VER_23 },
-		{ 0x7cf00000, 0x3c800000,	RTL_GIGA_MAC_VER_18 },
-		{ 0x7c800000, 0x3c800000,	RTL_GIGA_MAC_VER_24 },
-		{ 0x7cf00000, 0x3c000000,	RTL_GIGA_MAC_VER_19 },
-		{ 0x7cf00000, 0x3c200000,	RTL_GIGA_MAC_VER_20 },
-		{ 0x7cf00000, 0x3c300000,	RTL_GIGA_MAC_VER_21 },
-		{ 0x7c800000, 0x3c000000,	RTL_GIGA_MAC_VER_22 },
+		{ 0x7cf, 0x3c9,	RTL_GIGA_MAC_VER_23 },
+		{ 0x7cf, 0x3c8,	RTL_GIGA_MAC_VER_18 },
+		{ 0x7c8, 0x3c8,	RTL_GIGA_MAC_VER_24 },
+		{ 0x7cf, 0x3c0,	RTL_GIGA_MAC_VER_19 },
+		{ 0x7cf, 0x3c2,	RTL_GIGA_MAC_VER_20 },
+		{ 0x7cf, 0x3c3,	RTL_GIGA_MAC_VER_21 },
+		{ 0x7c8, 0x3c0,	RTL_GIGA_MAC_VER_22 },
 
 		/* 8168B family. */
-		{ 0x7cf00000, 0x38000000,	RTL_GIGA_MAC_VER_12 },
-		{ 0x7c800000, 0x38000000,	RTL_GIGA_MAC_VER_17 },
-		{ 0x7c800000, 0x30000000,	RTL_GIGA_MAC_VER_11 },
+		{ 0x7cf, 0x380,	RTL_GIGA_MAC_VER_12 },
+		{ 0x7c8, 0x380,	RTL_GIGA_MAC_VER_17 },
+		{ 0x7c8, 0x300,	RTL_GIGA_MAC_VER_11 },
 
 		/* 8101 family. */
-		{ 0x7c800000, 0x44800000,	RTL_GIGA_MAC_VER_39 },
-		{ 0x7c800000, 0x44000000,	RTL_GIGA_MAC_VER_37 },
-		{ 0x7cf00000, 0x40900000,	RTL_GIGA_MAC_VER_29 },
-		{ 0x7c800000, 0x40800000,	RTL_GIGA_MAC_VER_30 },
-		{ 0x7cf00000, 0x34900000,	RTL_GIGA_MAC_VER_08 },
-		{ 0x7cf00000, 0x24900000,	RTL_GIGA_MAC_VER_08 },
-		{ 0x7cf00000, 0x34800000,	RTL_GIGA_MAC_VER_07 },
-		{ 0x7cf00000, 0x24800000,	RTL_GIGA_MAC_VER_07 },
-		{ 0x7cf00000, 0x34000000,	RTL_GIGA_MAC_VER_13 },
-		{ 0x7cf00000, 0x34300000,	RTL_GIGA_MAC_VER_10 },
-		{ 0x7cf00000, 0x34200000,	RTL_GIGA_MAC_VER_16 },
-		{ 0x7c800000, 0x34800000,	RTL_GIGA_MAC_VER_09 },
-		{ 0x7c800000, 0x24800000,	RTL_GIGA_MAC_VER_09 },
-		{ 0x7c800000, 0x34000000,	RTL_GIGA_MAC_VER_16 },
+		{ 0x7c8, 0x448,	RTL_GIGA_MAC_VER_39 },
+		{ 0x7c8, 0x440,	RTL_GIGA_MAC_VER_37 },
+		{ 0x7cf, 0x409,	RTL_GIGA_MAC_VER_29 },
+		{ 0x7c8, 0x408,	RTL_GIGA_MAC_VER_30 },
+		{ 0x7cf, 0x349,	RTL_GIGA_MAC_VER_08 },
+		{ 0x7cf, 0x249,	RTL_GIGA_MAC_VER_08 },
+		{ 0x7cf, 0x348,	RTL_GIGA_MAC_VER_07 },
+		{ 0x7cf, 0x248,	RTL_GIGA_MAC_VER_07 },
+		{ 0x7cf, 0x340,	RTL_GIGA_MAC_VER_13 },
+		{ 0x7cf, 0x343,	RTL_GIGA_MAC_VER_10 },
+		{ 0x7cf, 0x342,	RTL_GIGA_MAC_VER_16 },
+		{ 0x7c8, 0x348,	RTL_GIGA_MAC_VER_09 },
+		{ 0x7c8, 0x248,	RTL_GIGA_MAC_VER_09 },
+		{ 0x7c8, 0x340,	RTL_GIGA_MAC_VER_16 },
 		/* FIXME: where did these entries come from ? -- FR */
-		{ 0xfc800000, 0x38800000,	RTL_GIGA_MAC_VER_15 },
-		{ 0xfc800000, 0x30800000,	RTL_GIGA_MAC_VER_14 },
+		{ 0xfc8, 0x388,	RTL_GIGA_MAC_VER_15 },
+		{ 0xfc8, 0x308,	RTL_GIGA_MAC_VER_14 },
 
 		/* 8110 family. */
-		{ 0xfc800000, 0x98000000,	RTL_GIGA_MAC_VER_06 },
-		{ 0xfc800000, 0x18000000,	RTL_GIGA_MAC_VER_05 },
-		{ 0xfc800000, 0x10000000,	RTL_GIGA_MAC_VER_04 },
-		{ 0xfc800000, 0x04000000,	RTL_GIGA_MAC_VER_03 },
-		{ 0xfc800000, 0x00800000,	RTL_GIGA_MAC_VER_02 },
-		{ 0xfc800000, 0x00000000,	RTL_GIGA_MAC_VER_01 },
+		{ 0xfc8, 0x980,	RTL_GIGA_MAC_VER_06 },
+		{ 0xfc8, 0x180,	RTL_GIGA_MAC_VER_05 },
+		{ 0xfc8, 0x100,	RTL_GIGA_MAC_VER_04 },
+		{ 0xfc8, 0x040,	RTL_GIGA_MAC_VER_03 },
+		{ 0xfc8, 0x008,	RTL_GIGA_MAC_VER_02 },
+		{ 0xfc8, 0x000,	RTL_GIGA_MAC_VER_01 },
 
 		/* Catch-all */
-		{ 0x00000000, 0x00000000,	RTL_GIGA_MAC_NONE   }
+		{ 0x000, 0x000,	RTL_GIGA_MAC_NONE   }
 	};
 	const struct rtl_mac_info *p = mac_info;
-	u32 reg;
+	u16 reg = RTL_R32(tp, TxConfig) >> 20;
 
-	reg = RTL_R32(tp, TxConfig);
 	while ((reg & p->mask) != p->val)
 		p++;
 	tp->mac_version = p->mac_version;
@@ -7392,9 +7391,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto err_mdio_unregister;
 
-	netif_info(tp, probe, dev, "%s, %pM, XID %08x, IRQ %d\n",
+	netif_info(tp, probe, dev, "%s, %pM, XID %03x, IRQ %d\n",
 		   rtl_chip_infos[chipset].name, dev->dev_addr,
-		   (u32)(RTL_R32(tp, TxConfig) & 0xfcf0f8ff),
+		   (RTL_R32(tp, TxConfig) >> 20) & 0xfcf,
 		   pci_irq_vector(pdev, 0));
 
 	if (jumbo_max > JUMBO_1K)
-- 
cgit v1.2.3


From eac66686c60b7559e7343ce31f18e12665c6c3bd Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Mon, 19 Nov 2018 16:17:23 +0530
Subject: octeontx2-af: Convert mbox handlers APIs to lowercase

This patch converts all mailbox message handler API
names to lowercase.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.c   |  2 +-
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   | 73 ++++++++++++----------
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c    | 16 ++---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    | 56 ++++++++---------
 .../net/ethernet/marvell/octeontx2/af/rvu_cgx.c    | 30 ++++-----
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 24 +++----
 .../net/ethernet/marvell/octeontx2/af/rvu_npa.c    |  8 +--
 7 files changed, 107 insertions(+), 102 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
index 85ba24a05774..d6f9ed8ea966 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -290,7 +290,7 @@ EXPORT_SYMBOL(otx2_mbox_nonempty);
 const char *otx2_mbox_id2name(u16 id)
 {
 	switch (id) {
-#define M(_name, _id, _1, _2) case _id: return # _name;
+#define M(_name, _id, _1, _2, _3) case _id: return # _name;
 	MBOX_MESSAGES
 #undef M
 	default:
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index a15a59c9a239..90097a1b6a75 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -120,54 +120,59 @@ static inline struct mbox_msghdr *otx2_mbox_alloc_msg(struct otx2_mbox *mbox,
 
 #define MBOX_MESSAGES							\
 /* Generic mbox IDs (range 0x000 - 0x1FF) */				\
-M(READY,		0x001, msg_req, ready_msg_rsp)			\
-M(ATTACH_RESOURCES,	0x002, rsrc_attach, msg_rsp)			\
-M(DETACH_RESOURCES,	0x003, rsrc_detach, msg_rsp)			\
-M(MSIX_OFFSET,		0x004, msg_req, msix_offset_rsp)		\
+M(READY,		0x001, ready, msg_req, ready_msg_rsp)		\
+M(ATTACH_RESOURCES,	0x002, attach_resources, rsrc_attach, msg_rsp)	\
+M(DETACH_RESOURCES,	0x003, detach_resources, rsrc_detach, msg_rsp)	\
+M(MSIX_OFFSET,		0x004, msix_offset, msg_req, msix_offset_rsp)	\
 /* CGX mbox IDs (range 0x200 - 0x3FF) */				\
-M(CGX_START_RXTX,	0x200, msg_req, msg_rsp)			\
-M(CGX_STOP_RXTX,	0x201, msg_req, msg_rsp)			\
-M(CGX_STATS,		0x202, msg_req, cgx_stats_rsp)			\
-M(CGX_MAC_ADDR_SET,	0x203, cgx_mac_addr_set_or_get,			\
+M(CGX_START_RXTX,	0x200, cgx_start_rxtx, msg_req, msg_rsp)	\
+M(CGX_STOP_RXTX,	0x201, cgx_stop_rxtx, msg_req, msg_rsp)		\
+M(CGX_STATS,		0x202, cgx_stats, msg_req, cgx_stats_rsp)	\
+M(CGX_MAC_ADDR_SET,	0x203, cgx_mac_addr_set, cgx_mac_addr_set_or_get,    \
 				cgx_mac_addr_set_or_get)		\
-M(CGX_MAC_ADDR_GET,	0x204, cgx_mac_addr_set_or_get,			\
+M(CGX_MAC_ADDR_GET,	0x204, cgx_mac_addr_get, cgx_mac_addr_set_or_get,    \
 				cgx_mac_addr_set_or_get)		\
-M(CGX_PROMISC_ENABLE,	0x205, msg_req, msg_rsp)			\
-M(CGX_PROMISC_DISABLE,	0x206, msg_req, msg_rsp)			\
-M(CGX_START_LINKEVENTS, 0x207, msg_req, msg_rsp)			\
-M(CGX_STOP_LINKEVENTS,	0x208, msg_req, msg_rsp)			\
-M(CGX_GET_LINKINFO,	0x209, msg_req, cgx_link_info_msg)		\
-M(CGX_INTLBK_ENABLE,	0x20A, msg_req, msg_rsp)			\
-M(CGX_INTLBK_DISABLE,	0x20B, msg_req, msg_rsp)			\
+M(CGX_PROMISC_ENABLE,	0x205, cgx_promisc_enable, msg_req, msg_rsp)	\
+M(CGX_PROMISC_DISABLE,	0x206, cgx_promisc_disable, msg_req, msg_rsp)	\
+M(CGX_START_LINKEVENTS, 0x207, cgx_start_linkevents, msg_req, msg_rsp)	\
+M(CGX_STOP_LINKEVENTS,	0x208, cgx_stop_linkevents, msg_req, msg_rsp)	\
+M(CGX_GET_LINKINFO,	0x209, cgx_get_linkinfo, msg_req, cgx_link_info_msg) \
+M(CGX_INTLBK_ENABLE,	0x20A, cgx_intlbk_enable, msg_req, msg_rsp)	\
+M(CGX_INTLBK_DISABLE,	0x20B, cgx_intlbk_disable, msg_req, msg_rsp)	\
 /* NPA mbox IDs (range 0x400 - 0x5FF) */				\
-M(NPA_LF_ALLOC,		0x400, npa_lf_alloc_req, npa_lf_alloc_rsp)	\
-M(NPA_LF_FREE,		0x401, msg_req, msg_rsp)			\
-M(NPA_AQ_ENQ,		0x402, npa_aq_enq_req, npa_aq_enq_rsp)		\
-M(NPA_HWCTX_DISABLE,	0x403, hwctx_disable_req, msg_rsp)		\
+M(NPA_LF_ALLOC,		0x400, npa_lf_alloc,				\
+				npa_lf_alloc_req, npa_lf_alloc_rsp)	\
+M(NPA_LF_FREE,		0x401, npa_lf_free, msg_req, msg_rsp)		\
+M(NPA_AQ_ENQ,		0x402, npa_aq_enq, npa_aq_enq_req, npa_aq_enq_rsp)   \
+M(NPA_HWCTX_DISABLE,	0x403, npa_hwctx_disable, hwctx_disable_req, msg_rsp)\
 /* SSO/SSOW mbox IDs (range 0x600 - 0x7FF) */				\
 /* TIM mbox IDs (range 0x800 - 0x9FF) */				\
 /* CPT mbox IDs (range 0xA00 - 0xBFF) */				\
 /* NPC mbox IDs (range 0x6000 - 0x7FFF) */				\
 /* NIX mbox IDs (range 0x8000 - 0xFFFF) */				\
-M(NIX_LF_ALLOC,		0x8000, nix_lf_alloc_req, nix_lf_alloc_rsp)	\
-M(NIX_LF_FREE,		0x8001, msg_req, msg_rsp)			\
-M(NIX_AQ_ENQ,		0x8002, nix_aq_enq_req, nix_aq_enq_rsp)		\
-M(NIX_HWCTX_DISABLE,	0x8003, hwctx_disable_req, msg_rsp)		\
-M(NIX_TXSCH_ALLOC,	0x8004, nix_txsch_alloc_req, nix_txsch_alloc_rsp) \
-M(NIX_TXSCH_FREE,	0x8005, nix_txsch_free_req, msg_rsp)		\
-M(NIX_TXSCHQ_CFG,	0x8006, nix_txschq_config, msg_rsp)		\
-M(NIX_STATS_RST,	0x8007, msg_req, msg_rsp)			\
-M(NIX_VTAG_CFG,	0x8008, nix_vtag_config, msg_rsp)		\
-M(NIX_RSS_FLOWKEY_CFG,  0x8009, nix_rss_flowkey_cfg, msg_rsp)		\
-M(NIX_SET_MAC_ADDR,	0x800a, nix_set_mac_addr, msg_rsp)		\
-M(NIX_SET_RX_MODE,	0x800b, nix_rx_mode, msg_rsp)
+M(NIX_LF_ALLOC,		0x8000, nix_lf_alloc,				\
+				 nix_lf_alloc_req, nix_lf_alloc_rsp)	\
+M(NIX_LF_FREE,		0x8001, nix_lf_free, msg_req, msg_rsp)		\
+M(NIX_AQ_ENQ,		0x8002, nix_aq_enq, nix_aq_enq_req, nix_aq_enq_rsp)  \
+M(NIX_HWCTX_DISABLE,	0x8003, nix_hwctx_disable,			\
+				 hwctx_disable_req, msg_rsp)		\
+M(NIX_TXSCH_ALLOC,	0x8004, nix_txsch_alloc,			\
+				 nix_txsch_alloc_req, nix_txsch_alloc_rsp)   \
+M(NIX_TXSCH_FREE,	0x8005, nix_txsch_free, nix_txsch_free_req, msg_rsp) \
+M(NIX_TXSCHQ_CFG,	0x8006, nix_txschq_cfg, nix_txschq_config, msg_rsp)  \
+M(NIX_STATS_RST,	0x8007, nix_stats_rst, msg_req, msg_rsp)	\
+M(NIX_VTAG_CFG,		0x8008, nix_vtag_cfg, nix_vtag_config, msg_rsp)	\
+M(NIX_RSS_FLOWKEY_CFG,  0x8009, nix_rss_flowkey_cfg,			\
+				 nix_rss_flowkey_cfg, msg_rsp)		\
+M(NIX_SET_MAC_ADDR,	0x800a, nix_set_mac_addr, nix_set_mac_addr, msg_rsp) \
+M(NIX_SET_RX_MODE,	0x800b, nix_set_rx_mode, nix_rx_mode, msg_rsp)
 
 /* Messages initiated by AF (range 0xC00 - 0xDFF) */
 #define MBOX_UP_CGX_MESSAGES						\
-M(CGX_LINK_EVENT,		0xC00, cgx_link_info_msg, msg_rsp)
+M(CGX_LINK_EVENT,	0xC00, cgx_link_event, cgx_link_info_msg, msg_rsp)
 
 enum {
-#define M(_name, _id, _1, _2) MBOX_MSG_ ## _name = _id,
+#define M(_name, _id, _1, _2, _3) MBOX_MSG_ ## _name = _id,
 MBOX_MESSAGES
 MBOX_UP_CGX_MESSAGES
 #undef M
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index dc28fa2b9481..37bc3b80b60c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -830,7 +830,7 @@ int rvu_aq_alloc(struct rvu *rvu, struct admin_queue **ad_queue,
 	return 0;
 }
 
-static int rvu_mbox_handler_READY(struct rvu *rvu, struct msg_req *req,
+static int rvu_mbox_handler_ready(struct rvu *rvu, struct msg_req *req,
 				  struct ready_msg_rsp *rsp)
 {
 	return 0;
@@ -960,7 +960,7 @@ static int rvu_detach_rsrcs(struct rvu *rvu, struct rsrc_detach *detach,
 	return 0;
 }
 
-static int rvu_mbox_handler_DETACH_RESOURCES(struct rvu *rvu,
+static int rvu_mbox_handler_detach_resources(struct rvu *rvu,
 					     struct rsrc_detach *detach,
 					     struct msg_rsp *rsp)
 {
@@ -1108,7 +1108,7 @@ fail:
 	return -ENOSPC;
 }
 
-static int rvu_mbox_handler_ATTACH_RESOURCES(struct rvu *rvu,
+static int rvu_mbox_handler_attach_resources(struct rvu *rvu,
 					     struct rsrc_attach *attach,
 					     struct msg_rsp *rsp)
 {
@@ -1231,7 +1231,7 @@ static void rvu_clear_msix_offset(struct rvu *rvu, struct rvu_pfvf *pfvf,
 	rvu_free_rsrc_contig(&pfvf->msix, nvecs, offset);
 }
 
-static int rvu_mbox_handler_MSIX_OFFSET(struct rvu *rvu, struct msg_req *req,
+static int rvu_mbox_handler_msix_offset(struct rvu *rvu, struct msg_req *req,
 					struct msix_offset_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -1288,7 +1288,7 @@ static int rvu_process_mbox_msg(struct rvu *rvu, int devid,
 		goto bad_message;
 
 	switch (req->id) {
-#define M(_name, _id, _req_type, _rsp_type)				\
+#define M(_name, _id, _fn_name, _req_type, _rsp_type)			\
 	case _id: {							\
 		struct _rsp_type *rsp;					\
 		int err;						\
@@ -1303,9 +1303,9 @@ static int rvu_process_mbox_msg(struct rvu *rvu, int devid,
 			rsp->hdr.rc = 0;				\
 		}							\
 									\
-		err = rvu_mbox_handler_ ## _name(rvu,			\
-						 (struct _req_type *)req, \
-						 rsp);			\
+		err = rvu_mbox_handler_ ## _fn_name(rvu,		\
+						    (struct _req_type *)req, \
+						    rsp);		\
 		if (rsp && err)						\
 			rsp->hdr.rc = err;				\
 									\
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 2c0580cd2807..705c31ab2ea5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -270,84 +270,84 @@ int rvu_cgx_probe(struct rvu *rvu);
 void rvu_cgx_wq_destroy(struct rvu *rvu);
 void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu);
 int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start);
-int rvu_mbox_handler_CGX_START_RXTX(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_start_rxtx(struct rvu *rvu, struct msg_req *req,
 				    struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_STOP_RXTX(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stop_rxtx(struct rvu *rvu, struct msg_req *req,
 				   struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_STATS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stats(struct rvu *rvu, struct msg_req *req,
 			       struct cgx_stats_rsp *rsp);
-int rvu_mbox_handler_CGX_MAC_ADDR_SET(struct rvu *rvu,
+int rvu_mbox_handler_cgx_mac_addr_set(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp);
-int rvu_mbox_handler_CGX_MAC_ADDR_GET(struct rvu *rvu,
+int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp);
-int rvu_mbox_handler_CGX_PROMISC_ENABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req,
 					struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_PROMISC_DISABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req,
 					 struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_START_LINKEVENTS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_start_linkevents(struct rvu *rvu, struct msg_req *req,
 					  struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_STOP_LINKEVENTS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stop_linkevents(struct rvu *rvu, struct msg_req *req,
 					 struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_GET_LINKINFO(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_get_linkinfo(struct rvu *rvu, struct msg_req *req,
 				      struct cgx_link_info_msg *rsp);
-int rvu_mbox_handler_CGX_INTLBK_ENABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_intlbk_enable(struct rvu *rvu, struct msg_req *req,
 				       struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_INTLBK_DISABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_intlbk_disable(struct rvu *rvu, struct msg_req *req,
 					struct msg_rsp *rsp);
 
 /* NPA APIs */
 int rvu_npa_init(struct rvu *rvu);
 void rvu_npa_freemem(struct rvu *rvu);
-int rvu_mbox_handler_NPA_AQ_ENQ(struct rvu *rvu,
+int rvu_mbox_handler_npa_aq_enq(struct rvu *rvu,
 				struct npa_aq_enq_req *req,
 				struct npa_aq_enq_rsp *rsp);
-int rvu_mbox_handler_NPA_HWCTX_DISABLE(struct rvu *rvu,
+int rvu_mbox_handler_npa_hwctx_disable(struct rvu *rvu,
 				       struct hwctx_disable_req *req,
 				       struct msg_rsp *rsp);
-int rvu_mbox_handler_NPA_LF_ALLOC(struct rvu *rvu,
+int rvu_mbox_handler_npa_lf_alloc(struct rvu *rvu,
 				  struct npa_lf_alloc_req *req,
 				  struct npa_lf_alloc_rsp *rsp);
-int rvu_mbox_handler_NPA_LF_FREE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_npa_lf_free(struct rvu *rvu, struct msg_req *req,
 				 struct msg_rsp *rsp);
 
 /* NIX APIs */
 int rvu_nix_init(struct rvu *rvu);
 void rvu_nix_freemem(struct rvu *rvu);
 int rvu_get_nixlf_count(struct rvu *rvu);
-int rvu_mbox_handler_NIX_LF_ALLOC(struct rvu *rvu,
+int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 				  struct nix_lf_alloc_req *req,
 				  struct nix_lf_alloc_rsp *rsp);
-int rvu_mbox_handler_NIX_LF_FREE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_nix_lf_free(struct rvu *rvu, struct msg_req *req,
 				 struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_AQ_ENQ(struct rvu *rvu,
+int rvu_mbox_handler_nix_aq_enq(struct rvu *rvu,
 				struct nix_aq_enq_req *req,
 				struct nix_aq_enq_rsp *rsp);
-int rvu_mbox_handler_NIX_HWCTX_DISABLE(struct rvu *rvu,
+int rvu_mbox_handler_nix_hwctx_disable(struct rvu *rvu,
 				       struct hwctx_disable_req *req,
 				       struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_TXSCH_ALLOC(struct rvu *rvu,
+int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 				     struct nix_txsch_alloc_req *req,
 				     struct nix_txsch_alloc_rsp *rsp);
-int rvu_mbox_handler_NIX_TXSCH_FREE(struct rvu *rvu,
+int rvu_mbox_handler_nix_txsch_free(struct rvu *rvu,
 				    struct nix_txsch_free_req *req,
 				    struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_TXSCHQ_CFG(struct rvu *rvu,
+int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 				    struct nix_txschq_config *req,
 				    struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_STATS_RST(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_nix_stats_rst(struct rvu *rvu, struct msg_req *req,
 				   struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_VTAG_CFG(struct rvu *rvu,
+int rvu_mbox_handler_nix_vtag_cfg(struct rvu *rvu,
 				  struct nix_vtag_config *req,
 				  struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_RSS_FLOWKEY_CFG(struct rvu *rvu,
+int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
 					 struct nix_rss_flowkey_cfg *req,
 					 struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_SET_MAC_ADDR(struct rvu *rvu,
+int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu,
 				      struct nix_set_mac_addr *req,
 				      struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_SET_RX_MODE(struct rvu *rvu, struct nix_rx_mode *req,
+int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 				     struct msg_rsp *rsp);
 
 /* NPC APIs */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 188185c15b4a..52d776dfcbe8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -20,9 +20,9 @@ struct cgx_evq_entry {
 	struct cgx_link_event link_event;
 };
 
-#define M(_name, _id, _req_type, _rsp_type)				\
+#define M(_name, _id, _fn_name, _req_type, _rsp_type)			\
 static struct _req_type __maybe_unused					\
-*otx2_mbox_alloc_msg_ ## _name(struct rvu *rvu, int devid)		\
+*otx2_mbox_alloc_msg_ ## _fn_name(struct rvu *rvu, int devid)		\
 {									\
 	struct _req_type *req;						\
 									\
@@ -177,7 +177,7 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu)
 		}
 
 		/* Send mbox message to PF */
-		msg = otx2_mbox_alloc_msg_CGX_LINK_EVENT(rvu, pfid);
+		msg = otx2_mbox_alloc_msg_cgx_link_event(rvu, pfid);
 		if (!msg)
 			continue;
 		msg->link_info = *linfo;
@@ -303,21 +303,21 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start)
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_START_RXTX(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_start_rxtx(struct rvu *rvu, struct msg_req *req,
 				    struct msg_rsp *rsp)
 {
 	rvu_cgx_config_rxtx(rvu, req->hdr.pcifunc, true);
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_STOP_RXTX(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stop_rxtx(struct rvu *rvu, struct msg_req *req,
 				   struct msg_rsp *rsp)
 {
 	rvu_cgx_config_rxtx(rvu, req->hdr.pcifunc, false);
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_STATS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stats(struct rvu *rvu, struct msg_req *req,
 			       struct cgx_stats_rsp *rsp)
 {
 	int pf = rvu_get_pf(req->hdr.pcifunc);
@@ -354,7 +354,7 @@ int rvu_mbox_handler_CGX_STATS(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_MAC_ADDR_SET(struct rvu *rvu,
+int rvu_mbox_handler_cgx_mac_addr_set(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp)
 {
@@ -368,7 +368,7 @@ int rvu_mbox_handler_CGX_MAC_ADDR_SET(struct rvu *rvu,
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_MAC_ADDR_GET(struct rvu *rvu,
+int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp)
 {
@@ -387,7 +387,7 @@ int rvu_mbox_handler_CGX_MAC_ADDR_GET(struct rvu *rvu,
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_PROMISC_ENABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req,
 					struct msg_rsp *rsp)
 {
 	u16 pcifunc = req->hdr.pcifunc;
@@ -407,7 +407,7 @@ int rvu_mbox_handler_CGX_PROMISC_ENABLE(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_PROMISC_DISABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req,
 					 struct msg_rsp *rsp)
 {
 	u16 pcifunc = req->hdr.pcifunc;
@@ -451,21 +451,21 @@ static int rvu_cgx_config_linkevents(struct rvu *rvu, u16 pcifunc, bool en)
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_START_LINKEVENTS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_start_linkevents(struct rvu *rvu, struct msg_req *req,
 					  struct msg_rsp *rsp)
 {
 	rvu_cgx_config_linkevents(rvu, req->hdr.pcifunc, true);
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_STOP_LINKEVENTS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stop_linkevents(struct rvu *rvu, struct msg_req *req,
 					 struct msg_rsp *rsp)
 {
 	rvu_cgx_config_linkevents(rvu, req->hdr.pcifunc, false);
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_GET_LINKINFO(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_get_linkinfo(struct rvu *rvu, struct msg_req *req,
 				      struct cgx_link_info_msg *rsp)
 {
 	u8 cgx_id, lmac_id;
@@ -500,14 +500,14 @@ static int rvu_cgx_config_intlbk(struct rvu *rvu, u16 pcifunc, bool en)
 					  lmac_id, en);
 }
 
-int rvu_mbox_handler_CGX_INTLBK_ENABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_intlbk_enable(struct rvu *rvu, struct msg_req *req,
 				       struct msg_rsp *rsp)
 {
 	rvu_cgx_config_intlbk(rvu, req->hdr.pcifunc, true);
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_INTLBK_DISABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_intlbk_disable(struct rvu *rvu, struct msg_req *req,
 					struct msg_rsp *rsp)
 {
 	rvu_cgx_config_intlbk(rvu, req->hdr.pcifunc, false);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index a5ab7eff2301..4a33104d57b0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -637,21 +637,21 @@ static int nix_lf_hwctx_disable(struct rvu *rvu, struct hwctx_disable_req *req)
 	return err;
 }
 
-int rvu_mbox_handler_NIX_AQ_ENQ(struct rvu *rvu,
+int rvu_mbox_handler_nix_aq_enq(struct rvu *rvu,
 				struct nix_aq_enq_req *req,
 				struct nix_aq_enq_rsp *rsp)
 {
 	return rvu_nix_aq_enq_inst(rvu, req, rsp);
 }
 
-int rvu_mbox_handler_NIX_HWCTX_DISABLE(struct rvu *rvu,
+int rvu_mbox_handler_nix_hwctx_disable(struct rvu *rvu,
 				       struct hwctx_disable_req *req,
 				       struct msg_rsp *rsp)
 {
 	return nix_lf_hwctx_disable(rvu, req);
 }
 
-int rvu_mbox_handler_NIX_LF_ALLOC(struct rvu *rvu,
+int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 				  struct nix_lf_alloc_req *req,
 				  struct nix_lf_alloc_rsp *rsp)
 {
@@ -826,7 +826,7 @@ exit:
 	return rc;
 }
 
-int rvu_mbox_handler_NIX_LF_FREE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_nix_lf_free(struct rvu *rvu, struct msg_req *req,
 				 struct msg_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -918,7 +918,7 @@ static void nix_reset_tx_linkcfg(struct rvu *rvu, int blkaddr,
 			    NIX_AF_TL3_TL2X_LINKX_CFG(schq, link), 0x00);
 }
 
-int rvu_mbox_handler_NIX_TXSCH_ALLOC(struct rvu *rvu,
+int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 				     struct nix_txsch_alloc_req *req,
 				     struct nix_txsch_alloc_rsp *rsp)
 {
@@ -1073,7 +1073,7 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 	return 0;
 }
 
-int rvu_mbox_handler_NIX_TXSCH_FREE(struct rvu *rvu,
+int rvu_mbox_handler_nix_txsch_free(struct rvu *rvu,
 				    struct nix_txsch_free_req *req,
 				    struct msg_rsp *rsp)
 {
@@ -1118,7 +1118,7 @@ static bool is_txschq_config_valid(struct rvu *rvu, u16 pcifunc, int blkaddr,
 	return true;
 }
 
-int rvu_mbox_handler_NIX_TXSCHQ_CFG(struct rvu *rvu,
+int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 				    struct nix_txschq_config *req,
 				    struct msg_rsp *rsp)
 {
@@ -1209,7 +1209,7 @@ static int nix_rx_vtag_cfg(struct rvu *rvu, int nixlf, int blkaddr,
 	return 0;
 }
 
-int rvu_mbox_handler_NIX_VTAG_CFG(struct rvu *rvu,
+int rvu_mbox_handler_nix_vtag_cfg(struct rvu *rvu,
 				  struct nix_vtag_config *req,
 				  struct msg_rsp *rsp)
 {
@@ -1506,7 +1506,7 @@ static int nix_setup_txschq(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 	return 0;
 }
 
-int rvu_mbox_handler_NIX_STATS_RST(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_nix_stats_rst(struct rvu *rvu, struct msg_req *req,
 				   struct msg_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -1564,7 +1564,7 @@ static int get_flowkey_alg_idx(u32 flow_cfg)
 	return FLOW_KEY_ALG_PORT;
 }
 
-int rvu_mbox_handler_NIX_RSS_FLOWKEY_CFG(struct rvu *rvu,
+int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
 					 struct nix_rss_flowkey_cfg *req,
 					 struct msg_rsp *rsp)
 {
@@ -1720,7 +1720,7 @@ static void nix_rx_flowkey_alg_cfg(struct rvu *rvu, int blkaddr)
 	}
 }
 
-int rvu_mbox_handler_NIX_SET_MAC_ADDR(struct rvu *rvu,
+int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu,
 				      struct nix_set_mac_addr *req,
 				      struct msg_rsp *rsp)
 {
@@ -1745,7 +1745,7 @@ int rvu_mbox_handler_NIX_SET_MAC_ADDR(struct rvu *rvu,
 	return 0;
 }
 
-int rvu_mbox_handler_NIX_SET_RX_MODE(struct rvu *rvu, struct nix_rx_mode *req,
+int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 				     struct msg_rsp *rsp)
 {
 	bool allmulti = false, disable_promisc = false;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
index 7531fdc54fa1..77b8c2e00d86 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
@@ -241,14 +241,14 @@ static int npa_lf_hwctx_disable(struct rvu *rvu, struct hwctx_disable_req *req)
 	return err;
 }
 
-int rvu_mbox_handler_NPA_AQ_ENQ(struct rvu *rvu,
+int rvu_mbox_handler_npa_aq_enq(struct rvu *rvu,
 				struct npa_aq_enq_req *req,
 				struct npa_aq_enq_rsp *rsp)
 {
 	return rvu_npa_aq_enq_inst(rvu, req, rsp);
 }
 
-int rvu_mbox_handler_NPA_HWCTX_DISABLE(struct rvu *rvu,
+int rvu_mbox_handler_npa_hwctx_disable(struct rvu *rvu,
 				       struct hwctx_disable_req *req,
 				       struct msg_rsp *rsp)
 {
@@ -273,7 +273,7 @@ static void npa_ctx_free(struct rvu *rvu, struct rvu_pfvf *pfvf)
 	pfvf->npa_qints_ctx = NULL;
 }
 
-int rvu_mbox_handler_NPA_LF_ALLOC(struct rvu *rvu,
+int rvu_mbox_handler_npa_lf_alloc(struct rvu *rvu,
 				  struct npa_lf_alloc_req *req,
 				  struct npa_lf_alloc_rsp *rsp)
 {
@@ -372,7 +372,7 @@ exit:
 	return rc;
 }
 
-int rvu_mbox_handler_NPA_LF_FREE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_npa_lf_free(struct rvu *rvu, struct msg_req *req,
 				 struct msg_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
-- 
cgit v1.2.3


From 9b7dd87ac07119036d7c74c67160c496ddd8bfc4 Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Mon, 19 Nov 2018 16:17:24 +0530
Subject: octeontx2-af: Support to modify min/max allowed packet lengths

This patch adds support for RVU PF/VFs to modify min/max
packet lengths allowed by HW. For VFs on PF0, settings will
be automatically applied on LBK link. RX link's min/maxlen
is configured to min/max of PF and it's all VFs. On the TX side
if requested all SMQs attached to the requesting NIXLF will be
updated with new min/max lengths.

Also updates transmit credits for Tx links based on new maxlen.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.h    |   1 +
 drivers/net/ethernet/marvell/octeontx2/af/common.h |   5 +
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  12 +-
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |   4 +
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 199 +++++++++++++++++++++
 5 files changed, 220 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index 0a66d2717442..3bd38ed6d68b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -22,6 +22,7 @@
 
 #define MAX_CGX				3
 #define MAX_LMAC_PER_CGX		4
+#define CGX_FIFO_LEN			65536 /* 64K for both Rx & Tx */
 #define CGX_OFFSET(x)			((x) * MAX_LMAC_PER_CGX)
 
 /* Registers */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index d39ada404c8f..a8c89df07886 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -143,6 +143,11 @@ enum nix_scheduler {
 	NIX_TXSCH_LVL_CNT = 0x5,
 };
 
+/* Min/Max packet sizes, excluding FCS */
+#define	NIC_HW_MIN_FRS			40
+#define	NIC_HW_MAX_FRS			9212
+#define	SDP_HW_MAX_FRS			65535
+
 /* NIX RX action operation*/
 #define NIX_RX_ACTIONOP_DROP		(0x0ull)
 #define NIX_RX_ACTIONOP_UCAST		(0x1ull)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 90097a1b6a75..1e362d458768 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -165,7 +165,8 @@ M(NIX_VTAG_CFG,		0x8008, nix_vtag_cfg, nix_vtag_config, msg_rsp)	\
 M(NIX_RSS_FLOWKEY_CFG,  0x8009, nix_rss_flowkey_cfg,			\
 				 nix_rss_flowkey_cfg, msg_rsp)		\
 M(NIX_SET_MAC_ADDR,	0x800a, nix_set_mac_addr, nix_set_mac_addr, msg_rsp) \
-M(NIX_SET_RX_MODE,	0x800b, nix_set_rx_mode, nix_rx_mode, msg_rsp)
+M(NIX_SET_RX_MODE,	0x800b, nix_set_rx_mode, nix_rx_mode, msg_rsp)	\
+M(NIX_SET_HW_FRS,	0x800c, nix_set_hw_frs, nix_frs_cfg, msg_rsp)
 
 /* Messages initiated by AF (range 0xC00 - 0xDFF) */
 #define MBOX_UP_CGX_MESSAGES						\
@@ -527,4 +528,13 @@ struct nix_rx_mode {
 	u16	mode;
 };
 
+struct nix_frs_cfg {
+	struct mbox_msghdr hdr;
+	u8	update_smq;    /* Update SMQ's min/max lens */
+	u8	update_minlen; /* Set minlen also */
+	u8	sdp_link;      /* Set SDP RX link */
+	u16	maxlen;
+	u16	minlen;
+};
+
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 705c31ab2ea5..308884c41eff 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -122,6 +122,8 @@ struct rvu_pfvf {
 	u16		tx_chan_base;
 	u8              rx_chan_cnt; /* total number of RX channels */
 	u8              tx_chan_cnt; /* total number of TX channels */
+	u16		maxlen;
+	u16		minlen;
 
 	u8		mac_addr[ETH_ALEN]; /* MAC address of this PF/VF */
 
@@ -349,6 +351,8 @@ int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu,
 				      struct msg_rsp *rsp);
 int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 				     struct msg_rsp *rsp);
+int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
+				    struct msg_rsp *rsp);
 
 /* NPC APIs */
 int rvu_npc_init(struct rvu *rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 4a33104d57b0..e010fe798209 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -168,14 +168,20 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
 
 	rvu_npc_install_bcast_match_entry(rvu, pcifunc,
 					  nixlf, pfvf->rx_chan_base);
+	pfvf->maxlen = NIC_HW_MIN_FRS;
+	pfvf->minlen = NIC_HW_MIN_FRS;
 
 	return 0;
 }
 
 static void nix_interface_deinit(struct rvu *rvu, u16 pcifunc, u8 nixlf)
 {
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	int err;
 
+	pfvf->maxlen = 0;
+	pfvf->minlen = 0;
+
 	/* Remove this PF_FUNC from bcast pkt replication list */
 	err = nix_update_bcast_mce_list(rvu, pcifunc, false);
 	if (err) {
@@ -1778,6 +1784,196 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 	return 0;
 }
 
+static void nix_find_link_frs(struct rvu *rvu,
+			      struct nix_frs_cfg *req, u16 pcifunc)
+{
+	int pf = rvu_get_pf(pcifunc);
+	struct rvu_pfvf *pfvf;
+	int maxlen, minlen;
+	int numvfs, hwvf;
+	int vf;
+
+	/* Update with requester's min/max lengths */
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	pfvf->maxlen = req->maxlen;
+	if (req->update_minlen)
+		pfvf->minlen = req->minlen;
+
+	maxlen = req->maxlen;
+	minlen = req->update_minlen ? req->minlen : 0;
+
+	/* Get this PF's numVFs and starting hwvf */
+	rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvf);
+
+	/* For each VF, compare requested max/minlen */
+	for (vf = 0; vf < numvfs; vf++) {
+		pfvf =  &rvu->hwvf[hwvf + vf];
+		if (pfvf->maxlen > maxlen)
+			maxlen = pfvf->maxlen;
+		if (req->update_minlen &&
+		    pfvf->minlen && pfvf->minlen < minlen)
+			minlen = pfvf->minlen;
+	}
+
+	/* Compare requested max/minlen with PF's max/minlen */
+	pfvf = &rvu->pf[pf];
+	if (pfvf->maxlen > maxlen)
+		maxlen = pfvf->maxlen;
+	if (req->update_minlen &&
+	    pfvf->minlen && pfvf->minlen < minlen)
+		minlen = pfvf->minlen;
+
+	/* Update the request with max/min PF's and it's VF's max/min */
+	req->maxlen = maxlen;
+	if (req->update_minlen)
+		req->minlen = minlen;
+}
+
+int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
+				    struct msg_rsp *rsp)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	u16 pcifunc = req->hdr.pcifunc;
+	int pf = rvu_get_pf(pcifunc);
+	int blkaddr, schq, link = -1;
+	struct nix_txsch *txsch;
+	u64 cfg, lmac_fifo_len;
+	struct nix_hw *nix_hw;
+	u8 cgx = 0, lmac = 0;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	if (!req->sdp_link && req->maxlen > NIC_HW_MAX_FRS)
+		return NIX_AF_ERR_FRS_INVALID;
+
+	if (req->update_minlen && req->minlen < NIC_HW_MIN_FRS)
+		return NIX_AF_ERR_FRS_INVALID;
+
+	/* Check if requester wants to update SMQ's */
+	if (!req->update_smq)
+		goto rx_frscfg;
+
+	/* Update min/maxlen in each of the SMQ attached to this PF/VF */
+	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ];
+	spin_lock(&rvu->rsrc_lock);
+	for (schq = 0; schq < txsch->schq.max; schq++) {
+		if (txsch->pfvf_map[schq] != pcifunc)
+			continue;
+		cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq));
+		cfg = (cfg & ~(0xFFFFULL << 8)) | ((u64)req->maxlen << 8);
+		if (req->update_minlen)
+			cfg = (cfg & ~0x7FULL) | ((u64)req->minlen & 0x7F);
+		rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq), cfg);
+	}
+	spin_unlock(&rvu->rsrc_lock);
+
+rx_frscfg:
+	/* Check if config is for SDP link */
+	if (req->sdp_link) {
+		if (!hw->sdp_links)
+			return NIX_AF_ERR_RX_LINK_INVALID;
+		link = hw->cgx_links + hw->lbk_links;
+		goto linkcfg;
+	}
+
+	/* Check if the request is from CGX mapped RVU PF */
+	if (is_pf_cgxmapped(rvu, pf)) {
+		/* Get CGX and LMAC to which this PF is mapped and find link */
+		rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx, &lmac);
+		link = (cgx * hw->lmac_per_cgx) + lmac;
+	} else if (pf == 0) {
+		/* For VFs of PF0 ingress is LBK port, so config LBK link */
+		link = hw->cgx_links;
+	}
+
+	if (link < 0)
+		return NIX_AF_ERR_RX_LINK_INVALID;
+
+	nix_find_link_frs(rvu, req, pcifunc);
+
+linkcfg:
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link));
+	cfg = (cfg & ~(0xFFFFULL << 16)) | ((u64)req->maxlen << 16);
+	if (req->update_minlen)
+		cfg = (cfg & ~0xFFFFULL) | req->minlen;
+	rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link), cfg);
+
+	if (req->sdp_link || pf == 0)
+		return 0;
+
+	/* Update transmit credits for CGX links */
+	lmac_fifo_len =
+		CGX_FIFO_LEN / cgx_get_lmac_cnt(rvu_cgx_pdata(cgx, rvu));
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link));
+	cfg &= ~(0xFFFFFULL << 12);
+	cfg |=  ((lmac_fifo_len - req->maxlen) / 16) << 12;
+	rvu_write64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link), cfg);
+	rvu_write64(rvu, blkaddr, NIX_AF_TX_LINKX_EXPR_CREDIT(link), cfg);
+
+	return 0;
+}
+
+static void nix_link_config(struct rvu *rvu, int blkaddr)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	int cgx, lmac_cnt, slink, link;
+	u64 tx_credits;
+
+	/* Set default min/max packet lengths allowed on NIX Rx links.
+	 *
+	 * With HW reset minlen value of 60byte, HW will treat ARP pkts
+	 * as undersize and report them to SW as error pkts, hence
+	 * setting it to 40 bytes.
+	 */
+	for (link = 0; link < (hw->cgx_links + hw->lbk_links); link++) {
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link),
+			    NIC_HW_MAX_FRS << 16 | NIC_HW_MIN_FRS);
+	}
+
+	if (hw->sdp_links) {
+		link = hw->cgx_links + hw->lbk_links;
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link),
+			    SDP_HW_MAX_FRS << 16 | NIC_HW_MIN_FRS);
+	}
+
+	/* Set credits for Tx links assuming max packet length allowed.
+	 * This will be reconfigured based on MTU set for PF/VF.
+	 */
+	for (cgx = 0; cgx < hw->cgx; cgx++) {
+		lmac_cnt = cgx_get_lmac_cnt(rvu_cgx_pdata(cgx, rvu));
+		tx_credits = ((CGX_FIFO_LEN / lmac_cnt) - NIC_HW_MAX_FRS) / 16;
+		/* Enable credits and set credit pkt count to max allowed */
+		tx_credits =  (tx_credits << 12) | (0x1FF << 2) | BIT_ULL(1);
+		slink = cgx * hw->lmac_per_cgx;
+		for (link = slink; link < (slink + lmac_cnt); link++) {
+			rvu_write64(rvu, blkaddr,
+				    NIX_AF_TX_LINKX_NORM_CREDIT(link),
+				    tx_credits);
+			rvu_write64(rvu, blkaddr,
+				    NIX_AF_TX_LINKX_EXPR_CREDIT(link),
+				    tx_credits);
+		}
+	}
+
+	/* Set Tx credits for LBK link */
+	slink = hw->cgx_links;
+	for (link = slink; link < (slink + hw->lbk_links); link++) {
+		tx_credits = 1000; /* 10 * max LBK datarate = 10 * 100Gbps */
+		/* Enable credits and set credit pkt count to max allowed */
+		tx_credits =  (tx_credits << 12) | (0x1FF << 2) | BIT_ULL(1);
+		rvu_write64(rvu, blkaddr,
+			    NIX_AF_TX_LINKX_NORM_CREDIT(link), tx_credits);
+		rvu_write64(rvu, blkaddr,
+			    NIX_AF_TX_LINKX_EXPR_CREDIT(link), tx_credits);
+	}
+}
+
 static int nix_calibrate_x2p(struct rvu *rvu, int blkaddr)
 {
 	int idx, err;
@@ -1922,6 +2118,9 @@ int rvu_nix_init(struct rvu *rvu)
 			    (NPC_LID_LC << 8) | (NPC_LT_LC_IP << 4) | 0x0F);
 
 		nix_rx_flowkey_alg_cfg(rvu, blkaddr);
+
+		/* Initialize CGX/LBK/SDP link credits, min/max pkt lengths */
+		nix_link_config(rvu, blkaddr);
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 34425e8c7589b87fea3659c35d8a217110fcbd4b Mon Sep 17 00:00:00 2001
From: Kiran Kumar <kirankumark@marvell.com>
Date: Mon, 19 Nov 2018 16:17:25 +0530
Subject: octeontx2-af: Support to get NIX HW constants from AF

This patch adds reading HW limits like number of Rx/Tx stats,
number of queue IRQs supported per NIX LF from AF registers
and sync them to PF/VF.

Signed-off-by: Kiran Kumar <kirankumark@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h    | 4 ++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c | 8 ++++++++
 2 files changed, 12 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 1e362d458768..7a229a54b9a3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -398,6 +398,10 @@ struct nix_lf_alloc_rsp {
 	u8	lso_tsov4_idx;
 	u8	lso_tsov6_idx;
 	u8      mac_addr[ETH_ALEN];
+	u8	lf_rx_stats; /* NIX_AF_CONST1::LF_RX_STATS */
+	u8	lf_tx_stats; /* NIX_AF_CONST1::LF_TX_STATS */
+	u16	cints; /* NIX_AF_CONST2::CINTS */
+	u16	qints; /* NIX_AF_CONST2::QINTS */
 };
 
 /* NIX AQ enqueue msg */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index e010fe798209..c779a0a2166d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -829,6 +829,14 @@ exit:
 	rsp->tx_chan_cnt = pfvf->tx_chan_cnt;
 	rsp->lso_tsov4_idx = NIX_LSO_FORMAT_IDX_TSOV4;
 	rsp->lso_tsov6_idx = NIX_LSO_FORMAT_IDX_TSOV6;
+	/* Get HW supported stat count */
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST1);
+	rsp->lf_rx_stats = ((cfg >> 32) & 0xFF);
+	rsp->lf_tx_stats = ((cfg >> 24) & 0xFF);
+	/* Get count of CQ IRQs and error IRQs supported per LF */
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST2);
+	rsp->qints = ((cfg >> 12) & 0xFFF);
+	rsp->cints = ((cfg >> 24) & 0xFFF);
 	return rc;
 }
 
-- 
cgit v1.2.3


From 0964fc8f5f30f4ec7cce4c7a09c547ac87b4ed25 Mon Sep 17 00:00:00 2001
From: Stanislaw Kardach <skardach@marvell.com>
Date: Mon, 19 Nov 2018 16:17:26 +0530
Subject: octeontx2-af: Relax resource lock into mutex

Mailbox message handling is done in a workqueue context scheduled
from interrupt handler. So resource locks does not need to be a spinlock.
Therefore relax them into a mutex so that later on we may use them
in routines that might sleep.

Signed-off-by: Stanislaw Kardach <skardach@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c    | 18 ++++++++-------
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  6 ++---
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 27 +++++++++++-----------
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    |  4 +++-
 4 files changed, 30 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 37bc3b80b60c..e59dfd34e76a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -153,17 +153,17 @@ int rvu_get_lf(struct rvu *rvu, struct rvu_block *block, u16 pcifunc, u16 slot)
 	u16 match = 0;
 	int lf;
 
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 	for (lf = 0; lf < block->lf.max; lf++) {
 		if (block->fn_map[lf] == pcifunc) {
 			if (slot == match) {
-				spin_unlock(&rvu->rsrc_lock);
+				mutex_unlock(&rvu->rsrc_lock);
 				return lf;
 			}
 			match++;
 		}
 	}
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 	return -ENODEV;
 }
 
@@ -597,6 +597,8 @@ static void rvu_free_hw_resources(struct rvu *rvu)
 	dma_unmap_resource(rvu->dev, rvu->msix_base_iova,
 			   max_msix * PCI_MSIX_ENTRY_SIZE,
 			   DMA_BIDIRECTIONAL, 0);
+
+	mutex_destroy(&rvu->rsrc_lock);
 }
 
 static int rvu_setup_hw_resources(struct rvu *rvu)
@@ -752,7 +754,7 @@ init:
 	if (!rvu->hwvf)
 		return -ENOMEM;
 
-	spin_lock_init(&rvu->rsrc_lock);
+	mutex_init(&rvu->rsrc_lock);
 
 	err = rvu_setup_msix_resources(rvu);
 	if (err)
@@ -926,7 +928,7 @@ static int rvu_detach_rsrcs(struct rvu *rvu, struct rsrc_detach *detach,
 	struct rvu_block *block;
 	int blkid;
 
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 
 	/* Check for partial resource detach */
 	if (detach && detach->partial)
@@ -956,7 +958,7 @@ static int rvu_detach_rsrcs(struct rvu *rvu, struct rsrc_detach *detach,
 		rvu_detach_block(rvu, pcifunc, block->type);
 	}
 
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 	return 0;
 }
 
@@ -1119,7 +1121,7 @@ static int rvu_mbox_handler_attach_resources(struct rvu *rvu,
 	if (!attach->modify)
 		rvu_detach_rsrcs(rvu, NULL, pcifunc);
 
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 
 	/* Check if the request can be accommodated */
 	err = rvu_check_rsrc_availability(rvu, attach, pcifunc);
@@ -1163,7 +1165,7 @@ static int rvu_mbox_handler_attach_resources(struct rvu *rvu,
 	}
 
 exit:
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 308884c41eff..2795767f054e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -64,7 +64,7 @@ struct nix_mcast {
 	struct qmem	*mcast_buf;
 	int		replay_pkind;
 	int		next_free_mce;
-	spinlock_t	mce_lock; /* Serialize MCE updates */
+	struct mutex	mce_lock; /* Serialize MCE updates */
 };
 
 struct nix_mce_list {
@@ -74,7 +74,7 @@ struct nix_mce_list {
 };
 
 struct npc_mcam {
-	spinlock_t	lock;	/* MCAM entries and counters update lock */
+	struct mutex	lock;	/* MCAM entries and counters update lock */
 	u8	keysize;	/* MCAM keysize 112/224/448 bits */
 	u8	banks;		/* Number of MCAM banks */
 	u8	banks_per_entry;/* Number of keywords in key */
@@ -174,7 +174,7 @@ struct rvu {
 	struct rvu_hwinfo       *hw;
 	struct rvu_pfvf		*pf;
 	struct rvu_pfvf		*hwvf;
-	spinlock_t		rsrc_lock; /* Serialize resource alloc/free */
+	struct mutex            rsrc_lock; /* Serialize resource alloc/free */
 
 	/* Mbox */
 	struct otx2_mbox	mbox;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index c779a0a2166d..ff7f8f3cedb5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -109,12 +109,12 @@ static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
 	if (schq >= txsch->schq.max)
 		return false;
 
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 	if (txsch->pfvf_map[schq] != pcifunc) {
-		spin_unlock(&rvu->rsrc_lock);
+		mutex_unlock(&rvu->rsrc_lock);
 		return false;
 	}
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 	return true;
 }
 
@@ -953,7 +953,7 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 	if (!nix_hw)
 		return -EINVAL;
 
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 	for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
 		txsch = &nix_hw->txsch[lvl];
 		req_schq = req->schq_contig[lvl] + req->schq[lvl];
@@ -1009,7 +1009,7 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 err:
 	rc = NIX_AF_ERR_TLX_ALLOC_FAIL;
 exit:
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 	return rc;
 }
 
@@ -1034,7 +1034,7 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 		return NIX_AF_ERR_AF_LF_INVALID;
 
 	/* Disable TL2/3 queue links before SMQ flush*/
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 	for (lvl = NIX_TXSCH_LVL_TL4; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
 		if (lvl != NIX_TXSCH_LVL_TL2 && lvl != NIX_TXSCH_LVL_TL4)
 			continue;
@@ -1076,7 +1076,7 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 			txsch->pfvf_map[schq] = 0;
 		}
 	}
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 
 	/* Sync cached info for this LF in NDC-TX to LLC/DRAM */
 	rvu_write64(rvu, blkaddr, NIX_AF_NDC_TX_SYNC, BIT_ULL(12) | nixlf);
@@ -1308,7 +1308,7 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list,
 		return 0;
 
 	/* Add a new one to the list, at the tail */
-	mce = kzalloc(sizeof(*mce), GFP_ATOMIC);
+	mce = kzalloc(sizeof(*mce), GFP_KERNEL);
 	if (!mce)
 		return -ENOMEM;
 	mce->idx = idx;
@@ -1354,7 +1354,7 @@ static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
 		return -EINVAL;
 	}
 
-	spin_lock(&mcast->mce_lock);
+	mutex_lock(&mcast->mce_lock);
 
 	err = nix_update_mce_list(mce_list, pcifunc, idx, add);
 	if (err)
@@ -1384,7 +1384,7 @@ static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
 	}
 
 end:
-	spin_unlock(&mcast->mce_lock);
+	mutex_unlock(&mcast->mce_lock);
 	return err;
 }
 
@@ -1469,7 +1469,7 @@ static int nix_setup_mcast(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 		    BIT_ULL(63) | (mcast->replay_pkind << 24) |
 		    BIT_ULL(20) | MC_BUF_CNT);
 
-	spin_lock_init(&mcast->mce_lock);
+	mutex_init(&mcast->mce_lock);
 
 	return nix_setup_bcast_tables(rvu, nix_hw);
 }
@@ -1869,7 +1869,7 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
 
 	/* Update min/maxlen in each of the SMQ attached to this PF/VF */
 	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ];
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 	for (schq = 0; schq < txsch->schq.max; schq++) {
 		if (txsch->pfvf_map[schq] != pcifunc)
 			continue;
@@ -1879,7 +1879,7 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
 			cfg = (cfg & ~0x7FULL) | ((u64)req->minlen & 0x7F);
 		rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq), cfg);
 	}
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 
 rx_frscfg:
 	/* Check if config is for SDP link */
@@ -2162,5 +2162,6 @@ void rvu_nix_freemem(struct rvu *rvu)
 		mcast = &nix_hw->mcast;
 		qmem_free(rvu->dev, mcast->mce_ctx);
 		qmem_free(rvu->dev, mcast->mcast_buf);
+		mutex_destroy(&mcast->mce_lock);
 	}
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 23ff47f7efc5..3a96dfd2b737 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -732,7 +732,7 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	mcam->nixlf_offset = mcam->entries;
 	mcam->pf_offset = mcam->nixlf_offset + nixlf_count;
 
-	spin_lock_init(&mcam->lock);
+	mutex_init(&mcam->lock);
 
 	return 0;
 }
@@ -811,6 +811,8 @@ int rvu_npc_init(struct rvu *rvu)
 void rvu_npc_freemem(struct rvu *rvu)
 {
 	struct npc_pkind *pkind = &rvu->hw->pkind;
+	struct npc_mcam *mcam = &rvu->hw->mcam;
 
 	kfree(pkind->rsrc.bmap);
+	mutex_destroy(&mcam->lock);
 }
-- 
cgit v1.2.3


From f92749586176f884044f47da62dcc231f6b43cd5 Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Mon, 19 Nov 2018 16:17:27 +0530
Subject: octeontx2-af: NPC MCAM entry alloc/free support

This patch adds NPC MCAM entry management and support for
allocating and freeing them via mailbox. Both contiguous and
non-contiguous allocations are supported. Incase of contiguous,
if request cannot be met then max contiguous number of available
entries are allocated.

High or low priority index allocation w.r.t a reference MCAM index
is also supported.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  49 ++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  19 +-
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    |  11 +
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 514 ++++++++++++++++++++-
 4 files changed, 588 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 7a229a54b9a3..5a635828493b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -149,6 +149,10 @@ M(NPA_HWCTX_DISABLE,	0x403, npa_hwctx_disable, hwctx_disable_req, msg_rsp)\
 /* TIM mbox IDs (range 0x800 - 0x9FF) */				\
 /* CPT mbox IDs (range 0xA00 - 0xBFF) */				\
 /* NPC mbox IDs (range 0x6000 - 0x7FFF) */				\
+M(NPC_MCAM_ALLOC_ENTRY,	0x6000, npc_mcam_alloc_entry, npc_mcam_alloc_entry_req,\
+				npc_mcam_alloc_entry_rsp)		\
+M(NPC_MCAM_FREE_ENTRY,	0x6001, npc_mcam_free_entry,			\
+				 npc_mcam_free_entry_req, msg_rsp)	\
 /* NIX mbox IDs (range 0x8000 - 0xFFFF) */				\
 M(NIX_LF_ALLOC,		0x8000, nix_lf_alloc,				\
 				 nix_lf_alloc_req, nix_lf_alloc_rsp)	\
@@ -353,6 +357,8 @@ struct hwctx_disable_req {
 	u8 ctype;
 };
 
+/* NIX mbox message formats */
+
 /* NIX mailbox error codes
  * Range 401 - 500.
  */
@@ -541,4 +547,47 @@ struct nix_frs_cfg {
 	u16	minlen;
 };
 
+/* NPC mbox message structs */
+
+#define NPC_MCAM_ENTRY_INVALID	0xFFFF
+#define NPC_MCAM_INVALID_MAP	0xFFFF
+
+/* NPC mailbox error codes
+ * Range 701 - 800.
+ */
+enum npc_af_status {
+	NPC_MCAM_INVALID_REQ	= -701,
+	NPC_MCAM_ALLOC_DENIED	= -702,
+	NPC_MCAM_ALLOC_FAILED	= -703,
+	NPC_MCAM_PERM_DENIED	= -704,
+};
+
+struct npc_mcam_alloc_entry_req {
+	struct mbox_msghdr hdr;
+#define NPC_MAX_NONCONTIG_ENTRIES	256
+	u8  contig;   /* Contiguous entries ? */
+#define NPC_MCAM_ANY_PRIO		0
+#define NPC_MCAM_LOWER_PRIO		1
+#define NPC_MCAM_HIGHER_PRIO		2
+	u8  priority; /* Lower or higher w.r.t ref_entry */
+	u16 ref_entry;
+	u16 count;    /* Number of entries requested */
+};
+
+struct npc_mcam_alloc_entry_rsp {
+	struct mbox_msghdr hdr;
+	u16 entry; /* Entry allocated or start index if contiguous.
+		    * Invalid incase of non-contiguous.
+		    */
+	u16 count; /* Number of entries allocated */
+	u16 free_count; /* Number of entries available */
+	u16 entry_list[NPC_MAX_NONCONTIG_ENTRIES];
+};
+
+struct npc_mcam_free_entry_req {
+	struct mbox_msghdr hdr;
+	u16 entry; /* Entry index to be freed */
+	u8  all;   /* If all entries allocated to this PFVF to be freed */
+};
+
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 2795767f054e..541c05cc8cc3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -74,15 +74,25 @@ struct nix_mce_list {
 };
 
 struct npc_mcam {
+	struct rsrc_bmap counters;
 	struct mutex	lock;	/* MCAM entries and counters update lock */
+	unsigned long	*bmap;		/* bitmap, 0 => bmap_entries */
+	unsigned long	*bmap_reverse;	/* Reverse bitmap, bmap_entries => 0 */
+	u16	bmap_entries;	/* Number of unreserved MCAM entries */
+	u16	bmap_fcnt;	/* MCAM entries free count */
+	u16	*entry2pfvf_map;
+	u16	*cntr2pfvf_map;
 	u8	keysize;	/* MCAM keysize 112/224/448 bits */
 	u8	banks;		/* Number of MCAM banks */
 	u8	banks_per_entry;/* Number of keywords in key */
 	u16	banksize;	/* Number of MCAM entries in each bank */
 	u16	total_entries;	/* Total number of MCAM entries */
-	u16     entries;	/* Total minus reserved for NIX LFs */
 	u16	nixlf_offset;	/* Offset of nixlf rsvd uncast entries */
 	u16	pf_offset;	/* Offset of PF's rsvd bcast, promisc entries */
+	u16	lprio_count;
+	u16	lprio_start;
+	u16	hprio_count;
+	u16	hprio_end;
 };
 
 /* Structure for per RVU func info ie PF/VF */
@@ -315,6 +325,7 @@ int rvu_mbox_handler_npa_lf_free(struct rvu *rvu, struct msg_req *req,
 				 struct msg_rsp *rsp);
 
 /* NIX APIs */
+bool is_nixlf_attached(struct rvu *rvu, u16 pcifunc);
 int rvu_nix_init(struct rvu *rvu);
 void rvu_nix_freemem(struct rvu *rvu);
 int rvu_get_nixlf_count(struct rvu *rvu);
@@ -369,4 +380,10 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    int group, int alg_idx, int mcam_index);
+int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu,
+					  struct npc_mcam_alloc_entry_req *req,
+					  struct npc_mcam_alloc_entry_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu,
+					 struct npc_mcam_free_entry_req *req,
+					 struct msg_rsp *rsp);
 #endif /* RVU_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index ff7f8f3cedb5..0491e358b769 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -55,6 +55,17 @@ struct mce {
 	u16			pcifunc;
 };
 
+bool is_nixlf_attached(struct rvu *rvu, u16 pcifunc)
+{
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	int blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (!pfvf->nixlf || blkaddr < 0)
+		return false;
+	return true;
+}
+
 int rvu_get_nixlf_count(struct rvu *rvu)
 {
 	struct rvu_block *block;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 3a96dfd2b737..4176aed3fd19 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -26,6 +26,9 @@
 
 #define NPC_PARSE_RESULT_DMAC_OFFSET	8
 
+static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam,
+				      int blkaddr, u16 pcifunc);
+
 struct mcam_entry {
 #define NPC_MAX_KWS_IN_KEY	7 /* Number of keywords in max keywidth */
 	u64	kw[NPC_MAX_KWS_IN_KEY];
@@ -466,6 +469,13 @@ void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
 	if (blkaddr < 0)
 		return;
 
+	mutex_lock(&mcam->lock);
+
+	/* Disable and free all MCAM entries mapped to this 'pcifunc' */
+	npc_mcam_free_all_entries(rvu, mcam, blkaddr, pcifunc);
+
+	mutex_unlock(&mcam->lock);
+
 	/* Disable ucast MCAM match entry of this PF/VF */
 	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
 					 nixlf, NIXLF_UCAST_ENTRY);
@@ -690,13 +700,14 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 {
 	int nixlf_count = rvu_get_nixlf_count(rvu);
 	struct npc_mcam *mcam = &rvu->hw->mcam;
-	int rsvd;
+	int rsvd, err;
 	u64 cfg;
 
 	/* Get HW limits */
 	cfg = rvu_read64(rvu, blkaddr, NPC_AF_CONST);
 	mcam->banks = (cfg >> 44) & 0xF;
 	mcam->banksize = (cfg >> 28) & 0xFFFF;
+	mcam->counters.max = (cfg >> 48) & 0xFFFF;
 
 	/* Actual number of MCAM entries vary by entry size */
 	cfg = (rvu_read64(rvu, blkaddr,
@@ -728,20 +739,69 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 		return -ENOMEM;
 	}
 
-	mcam->entries = mcam->total_entries - rsvd;
-	mcam->nixlf_offset = mcam->entries;
+	mcam->bmap_entries = mcam->total_entries - rsvd;
+	mcam->nixlf_offset = mcam->bmap_entries;
 	mcam->pf_offset = mcam->nixlf_offset + nixlf_count;
 
+	/* Allocate bitmaps for managing MCAM entries */
+	mcam->bmap = devm_kcalloc(rvu->dev, BITS_TO_LONGS(mcam->bmap_entries),
+				  sizeof(long), GFP_KERNEL);
+	if (!mcam->bmap)
+		return -ENOMEM;
+
+	mcam->bmap_reverse = devm_kcalloc(rvu->dev,
+					  BITS_TO_LONGS(mcam->bmap_entries),
+					  sizeof(long), GFP_KERNEL);
+	if (!mcam->bmap_reverse)
+		return -ENOMEM;
+
+	mcam->bmap_fcnt = mcam->bmap_entries;
+
+	/* Alloc memory for saving entry to RVU PFFUNC allocation mapping */
+	mcam->entry2pfvf_map = devm_kcalloc(rvu->dev, mcam->bmap_entries,
+					    sizeof(u16), GFP_KERNEL);
+	if (!mcam->entry2pfvf_map)
+		return -ENOMEM;
+
+	/* Reserve 1/8th of MCAM entries at the bottom for low priority
+	 * allocations and another 1/8th at the top for high priority
+	 * allocations.
+	 */
+	mcam->lprio_count = mcam->bmap_entries / 8;
+	if (mcam->lprio_count > BITS_PER_LONG)
+		mcam->lprio_count = round_down(mcam->lprio_count,
+					       BITS_PER_LONG);
+	mcam->lprio_start = mcam->bmap_entries - mcam->lprio_count;
+	mcam->hprio_count = mcam->lprio_count;
+	mcam->hprio_end = mcam->hprio_count;
+
+	/* Allocate bitmap for managing MCAM counters and memory
+	 * for saving counter to RVU PFFUNC allocation mapping.
+	 */
+	err = rvu_alloc_bitmap(&mcam->counters);
+	if (err)
+		return err;
+
+	mcam->cntr2pfvf_map = devm_kcalloc(rvu->dev, mcam->counters.max,
+					   sizeof(u16), GFP_KERNEL);
+	if (!mcam->cntr2pfvf_map)
+		goto free_mem;
+
 	mutex_init(&mcam->lock);
 
 	return 0;
+
+free_mem:
+	kfree(mcam->counters.bmap);
+	return -ENOMEM;
 }
 
 int rvu_npc_init(struct rvu *rvu)
 {
 	struct npc_pkind *pkind = &rvu->hw->pkind;
 	u64 keyz = NPC_MCAM_KEY_X2;
-	int blkaddr, err;
+	int blkaddr, entry, bank, err;
+	u64 cfg;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0) {
@@ -749,6 +809,14 @@ int rvu_npc_init(struct rvu *rvu)
 		return -ENODEV;
 	}
 
+	/* First disable all MCAM entries, to stop traffic towards NIXLFs */
+	cfg = rvu_read64(rvu, blkaddr, NPC_AF_CONST);
+	for (bank = 0; bank < ((cfg >> 44) & 0xF); bank++) {
+		for (entry = 0; entry < ((cfg >> 28) & 0xFFFF); entry++)
+			rvu_write64(rvu, blkaddr,
+				    NPC_AF_MCAMEX_BANKX_CFG(entry, bank), 0);
+	}
+
 	/* Allocate resource bimap for pkind*/
 	pkind->rsrc.max = (rvu_read64(rvu, blkaddr,
 				      NPC_AF_CONST1) >> 12) & 0xFF;
@@ -814,5 +882,443 @@ void rvu_npc_freemem(struct rvu *rvu)
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 
 	kfree(pkind->rsrc.bmap);
+	kfree(mcam->counters.bmap);
 	mutex_destroy(&mcam->lock);
 }
+
+static int npc_mcam_verify_entry(struct npc_mcam *mcam,
+				 u16 pcifunc, int entry)
+{
+	/* Verify if entry is valid and if it is indeed
+	 * allocated to the requesting PFFUNC.
+	 */
+	if (entry >= mcam->bmap_entries)
+		return NPC_MCAM_INVALID_REQ;
+
+	if (pcifunc != mcam->entry2pfvf_map[entry])
+		return NPC_MCAM_PERM_DENIED;
+
+	return 0;
+}
+
+/* Sets MCAM entry in bitmap as used. Update
+ * reverse bitmap too. Should be called with
+ * 'mcam->lock' held.
+ */
+static void npc_mcam_set_bit(struct npc_mcam *mcam, u16 index)
+{
+	u16 entry, rentry;
+
+	entry = index;
+	rentry = mcam->bmap_entries - index - 1;
+
+	__set_bit(entry, mcam->bmap);
+	__set_bit(rentry, mcam->bmap_reverse);
+	mcam->bmap_fcnt--;
+}
+
+/* Sets MCAM entry in bitmap as free. Update
+ * reverse bitmap too. Should be called with
+ * 'mcam->lock' held.
+ */
+static void npc_mcam_clear_bit(struct npc_mcam *mcam, u16 index)
+{
+	u16 entry, rentry;
+
+	entry = index;
+	rentry = mcam->bmap_entries - index - 1;
+
+	__clear_bit(entry, mcam->bmap);
+	__clear_bit(rentry, mcam->bmap_reverse);
+	mcam->bmap_fcnt++;
+}
+
+static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam,
+				      int blkaddr, u16 pcifunc)
+{
+	u16 index;
+
+	/* Scan all MCAM entries and free the ones mapped to 'pcifunc' */
+	for (index = 0; index < mcam->bmap_entries; index++) {
+		if (mcam->entry2pfvf_map[index] == pcifunc) {
+			mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP;
+			/* Free the entry in bitmap */
+			npc_mcam_clear_bit(mcam, index);
+			/* Disable the entry */
+			npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
+		}
+	}
+}
+
+/* Find area of contiguous free entries of size 'nr'.
+ * If not found return max contiguous free entries available.
+ */
+static u16 npc_mcam_find_zero_area(unsigned long *map, u16 size, u16 start,
+				   u16 nr, u16 *max_area)
+{
+	u16 max_area_start = 0;
+	u16 index, next, end;
+
+	*max_area = 0;
+
+again:
+	index = find_next_zero_bit(map, size, start);
+	if (index >= size)
+		return max_area_start;
+
+	end = ((index + nr) >= size) ? size : index + nr;
+	next = find_next_bit(map, end, index);
+	if (*max_area < (next - index)) {
+		*max_area = next - index;
+		max_area_start = index;
+	}
+
+	if (next < end) {
+		start = next + 1;
+		goto again;
+	}
+
+	return max_area_start;
+}
+
+/* Find number of free MCAM entries available
+ * within range i.e in between 'start' and 'end'.
+ */
+static u16 npc_mcam_get_free_count(unsigned long *map, u16 start, u16 end)
+{
+	u16 index, next;
+	u16 fcnt = 0;
+
+again:
+	if (start >= end)
+		return fcnt;
+
+	index = find_next_zero_bit(map, end, start);
+	if (index >= end)
+		return fcnt;
+
+	next = find_next_bit(map, end, index);
+	if (next <= end) {
+		fcnt += next - index;
+		start = next + 1;
+		goto again;
+	}
+
+	fcnt += end - index;
+	return fcnt;
+}
+
+static void
+npc_get_mcam_search_range_priority(struct npc_mcam *mcam,
+				   struct npc_mcam_alloc_entry_req *req,
+				   u16 *start, u16 *end, bool *reverse)
+{
+	u16 fcnt;
+
+	if (req->priority == NPC_MCAM_HIGHER_PRIO)
+		goto hprio;
+
+	/* For a low priority entry allocation
+	 * - If reference entry is not in hprio zone then
+	 *      search range: ref_entry to end.
+	 * - If reference entry is in hprio zone and if
+	 *   request can be accomodated in non-hprio zone then
+	 *      search range: 'start of middle zone' to 'end'
+	 * - else search in reverse, so that less number of hprio
+	 *   zone entries are allocated.
+	 */
+
+	*reverse = false;
+	*start = req->ref_entry + 1;
+	*end = mcam->bmap_entries;
+
+	if (req->ref_entry >= mcam->hprio_end)
+		return;
+
+	fcnt = npc_mcam_get_free_count(mcam->bmap,
+				       mcam->hprio_end, mcam->bmap_entries);
+	if (fcnt > req->count)
+		*start = mcam->hprio_end;
+	else
+		*reverse = true;
+	return;
+
+hprio:
+	/* For a high priority entry allocation, search is always
+	 * in reverse to preserve hprio zone entries.
+	 * - If reference entry is not in lprio zone then
+	 *      search range: 0 to ref_entry.
+	 * - If reference entry is in lprio zone and if
+	 *   request can be accomodated in middle zone then
+	 *      search range: 'hprio_end' to 'lprio_start'
+	 */
+
+	*reverse = true;
+	*start = 0;
+	*end = req->ref_entry;
+
+	if (req->ref_entry <= mcam->lprio_start)
+		return;
+
+	fcnt = npc_mcam_get_free_count(mcam->bmap,
+				       mcam->hprio_end, mcam->lprio_start);
+	if (fcnt < req->count)
+		return;
+	*start = mcam->hprio_end;
+	*end = mcam->lprio_start;
+}
+
+static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc,
+				  struct npc_mcam_alloc_entry_req *req,
+				  struct npc_mcam_alloc_entry_rsp *rsp)
+{
+	u16 entry_list[NPC_MAX_NONCONTIG_ENTRIES];
+	u16 fcnt, hp_fcnt, lp_fcnt;
+	u16 start, end, index;
+	int entry, next_start;
+	bool reverse = false;
+	unsigned long *bmap;
+	u16 max_contig;
+
+	mutex_lock(&mcam->lock);
+
+	/* Check if there are any free entries */
+	if (!mcam->bmap_fcnt) {
+		mutex_unlock(&mcam->lock);
+		return NPC_MCAM_ALLOC_FAILED;
+	}
+
+	/* MCAM entries are divided into high priority, middle and
+	 * low priority zones. Idea is to not allocate top and lower
+	 * most entries as much as possible, this is to increase
+	 * probability of honouring priority allocation requests.
+	 *
+	 * Two bitmaps are used for mcam entry management,
+	 * mcam->bmap for forward search i.e '0 to mcam->bmap_entries'.
+	 * mcam->bmap_reverse for reverse search i.e 'mcam->bmap_entries to 0'.
+	 *
+	 * Reverse bitmap is used to allocate entries
+	 * - when a higher priority entry is requested
+	 * - when available free entries are less.
+	 * Lower priority ones out of avaialble free entries are always
+	 * chosen when 'high vs low' question arises.
+	 */
+
+	/* Get the search range for priority allocation request */
+	if (req->priority) {
+		npc_get_mcam_search_range_priority(mcam, req,
+						   &start, &end, &reverse);
+		goto alloc;
+	}
+
+	/* Find out the search range for non-priority allocation request
+	 *
+	 * Get MCAM free entry count in middle zone.
+	 */
+	lp_fcnt = npc_mcam_get_free_count(mcam->bmap,
+					  mcam->lprio_start,
+					  mcam->bmap_entries);
+	hp_fcnt = npc_mcam_get_free_count(mcam->bmap, 0, mcam->hprio_end);
+	fcnt = mcam->bmap_fcnt - lp_fcnt - hp_fcnt;
+
+	/* Check if request can be accomodated in the middle zone */
+	if (fcnt > req->count) {
+		start = mcam->hprio_end;
+		end = mcam->lprio_start;
+	} else if ((fcnt + (hp_fcnt / 2) + (lp_fcnt / 2)) > req->count) {
+		/* Expand search zone from half of hprio zone to
+		 * half of lprio zone.
+		 */
+		start = mcam->hprio_end / 2;
+		end = mcam->bmap_entries - (mcam->lprio_count / 2);
+		reverse = true;
+	} else {
+		/* Not enough free entries, search all entries in reverse,
+		 * so that low priority ones will get used up.
+		 */
+		reverse = true;
+		start = 0;
+		end = mcam->bmap_entries;
+	}
+
+alloc:
+	if (reverse) {
+		bmap = mcam->bmap_reverse;
+		start = mcam->bmap_entries - start;
+		end = mcam->bmap_entries - end;
+		index = start;
+		start = end;
+		end = index;
+	} else {
+		bmap = mcam->bmap;
+	}
+
+	if (req->contig) {
+		/* Allocate requested number of contiguous entries, if
+		 * unsuccessful find max contiguous entries available.
+		 */
+		index = npc_mcam_find_zero_area(bmap, end, start,
+						req->count, &max_contig);
+		rsp->count = max_contig;
+		if (reverse)
+			rsp->entry = mcam->bmap_entries - index - max_contig;
+		else
+			rsp->entry = index;
+	} else {
+		/* Allocate requested number of non-contiguous entries,
+		 * if unsuccessful allocate as many as possible.
+		 */
+		rsp->count = 0;
+		next_start = start;
+		for (entry = 0; entry < req->count; entry++) {
+			index = find_next_zero_bit(bmap, end, next_start);
+			if (index >= end)
+				break;
+
+			next_start = start + (index - start) + 1;
+
+			/* Save the entry's index */
+			if (reverse)
+				index = mcam->bmap_entries - index - 1;
+			entry_list[entry] = index;
+			rsp->count++;
+		}
+	}
+
+	/* If allocating requested no of entries is unsucessful,
+	 * expand the search range to full bitmap length and retry.
+	 */
+	if (!req->priority && (rsp->count < req->count) &&
+	    ((end - start) != mcam->bmap_entries)) {
+		reverse = true;
+		start = 0;
+		end = mcam->bmap_entries;
+		goto alloc;
+	}
+
+	/* For priority entry allocation requests, if allocation is
+	 * failed then expand search to max possible range and retry.
+	 */
+	if (req->priority && rsp->count < req->count) {
+		if (req->priority == NPC_MCAM_LOWER_PRIO &&
+		    (start != (req->ref_entry + 1))) {
+			start = req->ref_entry + 1;
+			end = mcam->bmap_entries;
+			reverse = false;
+			goto alloc;
+		} else if ((req->priority == NPC_MCAM_HIGHER_PRIO) &&
+			   ((end - start) != req->ref_entry)) {
+			start = 0;
+			end = req->ref_entry;
+			reverse = true;
+			goto alloc;
+		}
+	}
+
+	/* Copy MCAM entry indices into mbox response entry_list.
+	 * Requester always expects indices in ascending order, so
+	 * so reverse the list if reverse bitmap is used for allocation.
+	 */
+	if (!req->contig && rsp->count) {
+		index = 0;
+		for (entry = rsp->count - 1; entry >= 0; entry--) {
+			if (reverse)
+				rsp->entry_list[index++] = entry_list[entry];
+			else
+				rsp->entry_list[entry] = entry_list[entry];
+		}
+	}
+
+	/* Mark the allocated entries as used and set nixlf mapping */
+	for (entry = 0; entry < rsp->count; entry++) {
+		index = req->contig ?
+			(rsp->entry + entry) : rsp->entry_list[entry];
+		npc_mcam_set_bit(mcam, index);
+		mcam->entry2pfvf_map[index] = pcifunc;
+	}
+
+	/* Update available free count in mbox response */
+	rsp->free_count = mcam->bmap_fcnt;
+
+	mutex_unlock(&mcam->lock);
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu,
+					  struct npc_mcam_alloc_entry_req *req,
+					  struct npc_mcam_alloc_entry_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	rsp->entry = NPC_MCAM_ENTRY_INVALID;
+	rsp->free_count = 0;
+
+	/* Check if ref_entry is within range */
+	if (req->priority && req->ref_entry >= mcam->bmap_entries)
+		return NPC_MCAM_INVALID_REQ;
+
+	/* ref_entry can't be '0' if requested priority is high.
+	 * Can't be last entry if requested priority is low.
+	 */
+	if ((!req->ref_entry && req->priority == NPC_MCAM_HIGHER_PRIO) ||
+	    ((req->ref_entry == (mcam->bmap_entries - 1)) &&
+	     req->priority == NPC_MCAM_LOWER_PRIO))
+		return NPC_MCAM_INVALID_REQ;
+
+	/* Since list of allocated indices needs to be sent to requester,
+	 * max number of non-contiguous entries per mbox msg is limited.
+	 */
+	if (!req->contig && req->count > NPC_MAX_NONCONTIG_ENTRIES)
+		return NPC_MCAM_INVALID_REQ;
+
+	/* Alloc request from PFFUNC with no NIXLF attached should be denied */
+	if (!is_nixlf_attached(rvu, pcifunc))
+		return NPC_MCAM_ALLOC_DENIED;
+
+	return npc_mcam_alloc_entries(mcam, pcifunc, req, rsp);
+}
+
+int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu,
+					 struct npc_mcam_free_entry_req *req,
+					 struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr, rc = 0;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	/* Free request from PFFUNC with no NIXLF attached, ignore */
+	if (!is_nixlf_attached(rvu, pcifunc))
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+
+	if (req->all)
+		goto free_all;
+
+	rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry);
+	if (rc)
+		goto exit;
+
+	mcam->entry2pfvf_map[req->entry] = 0;
+	npc_mcam_clear_bit(mcam, req->entry);
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, false);
+
+	goto exit;
+
+free_all:
+	/* Free up all entries allocated to requesting PFFUNC */
+	npc_mcam_free_all_entries(rvu, mcam, blkaddr, pcifunc);
+exit:
+	mutex_unlock(&mcam->lock);
+	return rc;
+}
-- 
cgit v1.2.3


From 651cd2652339d5223bab9802faaf0a7f14c870b7 Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Mon, 19 Nov 2018 16:17:28 +0530
Subject: octeontx2-af: MCAM entry installation support

Add support for a RVU PF/VF to enable, disable, configure
and shuffle MCAM entries via mbox commands. This patch adds
mailbox message formats and handling of these commands.

As of now otherthan validating MCAM entry index, info like
channel number e.t.c in MCAM config data sent by PF/VF are
not validated.

Also a max of 64 MCAM entries can be shuffled with a single
mbox command.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  45 ++++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  12 ++
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 179 ++++++++++++++++++++-
 3 files changed, 228 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 5a635828493b..f0b1a90317a6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -153,6 +153,14 @@ M(NPC_MCAM_ALLOC_ENTRY,	0x6000, npc_mcam_alloc_entry, npc_mcam_alloc_entry_req,\
 				npc_mcam_alloc_entry_rsp)		\
 M(NPC_MCAM_FREE_ENTRY,	0x6001, npc_mcam_free_entry,			\
 				 npc_mcam_free_entry_req, msg_rsp)	\
+M(NPC_MCAM_WRITE_ENTRY,	0x6002, npc_mcam_write_entry,			\
+				 npc_mcam_write_entry_req, msg_rsp)	\
+M(NPC_MCAM_ENA_ENTRY,   0x6003, npc_mcam_ena_entry,			\
+				 npc_mcam_ena_dis_entry_req, msg_rsp)	\
+M(NPC_MCAM_DIS_ENTRY,   0x6004, npc_mcam_dis_entry,			\
+				 npc_mcam_ena_dis_entry_req, msg_rsp)	\
+M(NPC_MCAM_SHIFT_ENTRY, 0x6005, npc_mcam_shift_entry, npc_mcam_shift_entry_req,\
+				npc_mcam_shift_entry_rsp)		\
 /* NIX mbox IDs (range 0x8000 - 0xFFFF) */				\
 M(NIX_LF_ALLOC,		0x8000, nix_lf_alloc,				\
 				 nix_lf_alloc_req, nix_lf_alloc_rsp)	\
@@ -590,4 +598,41 @@ struct npc_mcam_free_entry_req {
 	u8  all;   /* If all entries allocated to this PFVF to be freed */
 };
 
+struct mcam_entry {
+#define NPC_MAX_KWS_IN_KEY	7 /* Number of keywords in max keywidth */
+	u64	kw[NPC_MAX_KWS_IN_KEY];
+	u64	kw_mask[NPC_MAX_KWS_IN_KEY];
+	u64	action;
+	u64	vtag_action;
+};
+
+struct npc_mcam_write_entry_req {
+	struct mbox_msghdr hdr;
+	struct mcam_entry entry_data;
+	u16 entry;	 /* MCAM entry to write this match key */
+	u16 cntr;	 /* Counter for this MCAM entry */
+	u8  intf;	 /* Rx or Tx interface */
+	u8  enable_entry;/* Enable this MCAM entry ? */
+	u8  set_cntr;    /* Set counter for this entry ? */
+};
+
+/* Enable/Disable a given entry */
+struct npc_mcam_ena_dis_entry_req {
+	struct mbox_msghdr hdr;
+	u16 entry;
+};
+
+struct npc_mcam_shift_entry_req {
+	struct mbox_msghdr hdr;
+#define NPC_MCAM_MAX_SHIFTS	64
+	u16 curr_entry[NPC_MCAM_MAX_SHIFTS];
+	u16 new_entry[NPC_MCAM_MAX_SHIFTS];
+	u16 shift_count; /* Number of entries to shift */
+};
+
+struct npc_mcam_shift_entry_rsp {
+	struct mbox_msghdr hdr;
+	u16 failed_entry_idx; /* Index in 'curr_entry', not entry itself */
+};
+
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 541c05cc8cc3..cfe49541b6e2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -386,4 +386,16 @@ int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu,
 int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu,
 					 struct npc_mcam_free_entry_req *req,
 					 struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
+					  struct npc_mcam_write_entry_req *req,
+					  struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_ena_entry(struct rvu *rvu,
+					struct npc_mcam_ena_dis_entry_req *req,
+					struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_dis_entry(struct rvu *rvu,
+					struct npc_mcam_ena_dis_entry_req *req,
+					struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu,
+					  struct npc_mcam_shift_entry_req *req,
+					  struct npc_mcam_shift_entry_rsp *rsp);
 #endif /* RVU_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 4176aed3fd19..801c37a9a46d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -29,14 +29,6 @@
 static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam,
 				      int blkaddr, u16 pcifunc);
 
-struct mcam_entry {
-#define NPC_MAX_KWS_IN_KEY	7 /* Number of keywords in max keywidth */
-	u64	kw[NPC_MAX_KWS_IN_KEY];
-	u64	kw_mask[NPC_MAX_KWS_IN_KEY];
-	u64	action;
-	u64	vtag_action;
-};
-
 void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf)
 {
 	int blkaddr;
@@ -259,6 +251,46 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 		npc_enable_mcam_entry(rvu, mcam, blkaddr, actindex, false);
 }
 
+static void npc_copy_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
+				int blkaddr, u16 src, u16 dest)
+{
+	int dbank = npc_get_bank(mcam, dest);
+	int sbank = npc_get_bank(mcam, src);
+	u64 cfg, sreg, dreg;
+	int bank, i;
+
+	src &= (mcam->banksize - 1);
+	dest &= (mcam->banksize - 1);
+
+	/* Copy INTF's, W0's, W1's CAM0 and CAM1 configuration */
+	for (bank = 0; bank < mcam->banks_per_entry; bank++) {
+		sreg = NPC_AF_MCAMEX_BANKX_CAMX_INTF(src, sbank + bank, 0);
+		dreg = NPC_AF_MCAMEX_BANKX_CAMX_INTF(dest, dbank + bank, 0);
+		for (i = 0; i < 6; i++) {
+			cfg = rvu_read64(rvu, blkaddr, sreg + (i * 8));
+			rvu_write64(rvu, blkaddr, dreg + (i * 8), cfg);
+		}
+	}
+
+	/* Copy action */
+	cfg = rvu_read64(rvu, blkaddr,
+			 NPC_AF_MCAMEX_BANKX_ACTION(src, sbank));
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_ACTION(dest, dbank), cfg);
+
+	/* Copy TAG action */
+	cfg = rvu_read64(rvu, blkaddr,
+			 NPC_AF_MCAMEX_BANKX_TAG_ACT(src, sbank));
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_TAG_ACT(dest, dbank), cfg);
+
+	/* Enable or disable */
+	cfg = rvu_read64(rvu, blkaddr,
+			 NPC_AF_MCAMEX_BANKX_CFG(src, sbank));
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_CFG(dest, dbank), cfg);
+}
+
 static u64 npc_get_mcam_action(struct rvu *rvu, struct npc_mcam *mcam,
 			       int blkaddr, int index)
 {
@@ -1322,3 +1354,134 @@ exit:
 	mutex_unlock(&mcam->lock);
 	return rc;
 }
+
+int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
+					  struct npc_mcam_write_entry_req *req,
+					  struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr, rc;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry);
+	if (rc)
+		goto exit;
+
+	if (req->intf != NIX_INTF_RX && req->intf != NIX_INTF_TX) {
+		rc = NPC_MCAM_INVALID_REQ;
+		goto exit;
+	}
+
+	npc_config_mcam_entry(rvu, mcam, blkaddr, req->entry, req->intf,
+			      &req->entry_data, req->enable_entry);
+
+	rc = 0;
+exit:
+	mutex_unlock(&mcam->lock);
+	return rc;
+}
+
+int rvu_mbox_handler_npc_mcam_ena_entry(struct rvu *rvu,
+					struct npc_mcam_ena_dis_entry_req *req,
+					struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr, rc;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry);
+	mutex_unlock(&mcam->lock);
+	if (rc)
+		return rc;
+
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, true);
+
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_dis_entry(struct rvu *rvu,
+					struct npc_mcam_ena_dis_entry_req *req,
+					struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr, rc;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry);
+	mutex_unlock(&mcam->lock);
+	if (rc)
+		return rc;
+
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, false);
+
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu,
+					  struct npc_mcam_shift_entry_req *req,
+					  struct npc_mcam_shift_entry_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	u16 old_entry, new_entry;
+	int blkaddr, rc;
+	u16 index;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	if (req->shift_count > NPC_MCAM_MAX_SHIFTS)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	for (index = 0; index < req->shift_count; index++) {
+		old_entry = req->curr_entry[index];
+		new_entry = req->new_entry[index];
+
+		/* Check if both old and new entries are valid and
+		 * does belong to this PFFUNC or not.
+		 */
+		rc = npc_mcam_verify_entry(mcam, pcifunc, old_entry);
+		if (rc)
+			break;
+
+		rc = npc_mcam_verify_entry(mcam, pcifunc, new_entry);
+		if (rc)
+			break;
+
+		/* Disable the new_entry */
+		npc_enable_mcam_entry(rvu, mcam, blkaddr, new_entry, false);
+
+		/* Copy rule from old entry to new entry */
+		npc_copy_mcam_entry(rvu, mcam, blkaddr, old_entry, new_entry);
+
+		/* Enable new_entry and disable old_entry */
+		npc_enable_mcam_entry(rvu, mcam, blkaddr, new_entry, true);
+		npc_enable_mcam_entry(rvu, mcam, blkaddr, old_entry, false);
+	}
+
+	/* If shift has failed then report the failed index */
+	if (index != req->shift_count) {
+		rc = NPC_MCAM_PERM_DENIED;
+		rsp->failed_entry_idx = index;
+	}
+
+	mutex_unlock(&mcam->lock);
+	return rc;
+}
-- 
cgit v1.2.3


From 7fbb3f238c09e8fcd4ce21284ed20baeaf4805cc Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Mon, 19 Nov 2018 16:17:29 +0530
Subject: octeontx2-af: Support for NPC MCAM counters

NPC HW has counters which can be mapped to MCAM
entries to gather entry match statistics. This
patch adds support to allocate, free, clear and retrieve
stats of NPC MCAM counters. New mailbox messages have
been added for this. Similar to MCAM entries both
contiguous and non-contiguous counter allocation is
supported.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  36 ++++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  10 ++
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 144 +++++++++++++++++++++
 3 files changed, 190 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index f0b1a90317a6..0ab74ee77eb3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -161,6 +161,16 @@ M(NPC_MCAM_DIS_ENTRY,   0x6004, npc_mcam_dis_entry,			\
 				 npc_mcam_ena_dis_entry_req, msg_rsp)	\
 M(NPC_MCAM_SHIFT_ENTRY, 0x6005, npc_mcam_shift_entry, npc_mcam_shift_entry_req,\
 				npc_mcam_shift_entry_rsp)		\
+M(NPC_MCAM_ALLOC_COUNTER, 0x6006, npc_mcam_alloc_counter,		\
+					npc_mcam_alloc_counter_req,	\
+					npc_mcam_alloc_counter_rsp)	\
+M(NPC_MCAM_FREE_COUNTER,  0x6007, npc_mcam_free_counter,		\
+				    npc_mcam_oper_counter_req, msg_rsp)	\
+M(NPC_MCAM_CLEAR_COUNTER, 0x6009, npc_mcam_clear_counter,		\
+				   npc_mcam_oper_counter_req, msg_rsp)	\
+M(NPC_MCAM_COUNTER_STATS, 0x600a, npc_mcam_counter_stats,		\
+				   npc_mcam_oper_counter_req,		\
+				   npc_mcam_oper_counter_rsp)		\
 /* NIX mbox IDs (range 0x8000 - 0xFFFF) */				\
 M(NIX_LF_ALLOC,		0x8000, nix_lf_alloc,				\
 				 nix_lf_alloc_req, nix_lf_alloc_rsp)	\
@@ -635,4 +645,30 @@ struct npc_mcam_shift_entry_rsp {
 	u16 failed_entry_idx; /* Index in 'curr_entry', not entry itself */
 };
 
+struct npc_mcam_alloc_counter_req {
+	struct mbox_msghdr hdr;
+	u8  contig;	/* Contiguous counters ? */
+#define NPC_MAX_NONCONTIG_COUNTERS       64
+	u16 count;	/* Number of counters requested */
+};
+
+struct npc_mcam_alloc_counter_rsp {
+	struct mbox_msghdr hdr;
+	u16 cntr;   /* Counter allocated or start index if contiguous.
+		     * Invalid incase of non-contiguous.
+		     */
+	u16 count;  /* Number of counters allocated */
+	u16 cntr_list[NPC_MAX_NONCONTIG_COUNTERS];
+};
+
+struct npc_mcam_oper_counter_req {
+	struct mbox_msghdr hdr;
+	u16 cntr;   /* Free a counter or clear/fetch it's stats */
+};
+
+struct npc_mcam_oper_counter_rsp {
+	struct mbox_msghdr hdr;
+	u64 stat;  /* valid only while fetching counter's stats */
+};
+
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index cfe49541b6e2..898b59c4a9cf 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -398,4 +398,14 @@ int rvu_mbox_handler_npc_mcam_dis_entry(struct rvu *rvu,
 int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu,
 					  struct npc_mcam_shift_entry_req *req,
 					  struct npc_mcam_shift_entry_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_alloc_counter(struct rvu *rvu,
+				struct npc_mcam_alloc_counter_req *req,
+				struct npc_mcam_alloc_counter_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu,
+		   struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_clear_counter(struct rvu *rvu,
+		struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_counter_stats(struct rvu *rvu,
+			struct npc_mcam_oper_counter_req *req,
+			struct npc_mcam_oper_counter_rsp *rsp);
 #endif /* RVU_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 801c37a9a46d..1ec508e41653 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -933,6 +933,21 @@ static int npc_mcam_verify_entry(struct npc_mcam *mcam,
 	return 0;
 }
 
+static int npc_mcam_verify_counter(struct npc_mcam *mcam,
+				   u16 pcifunc, int cntr)
+{
+	/* Verify if counter is valid and if it is indeed
+	 * allocated to the requesting PFFUNC.
+	 */
+	if (cntr >= mcam->counters.max)
+		return NPC_MCAM_INVALID_REQ;
+
+	if (pcifunc != mcam->cntr2pfvf_map[cntr])
+		return NPC_MCAM_PERM_DENIED;
+
+	return 0;
+}
+
 /* Sets MCAM entry in bitmap as used. Update
  * reverse bitmap too. Should be called with
  * 'mcam->lock' held.
@@ -1485,3 +1500,132 @@ int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu,
 	mutex_unlock(&mcam->lock);
 	return rc;
 }
+
+int rvu_mbox_handler_npc_mcam_alloc_counter(struct rvu *rvu,
+			struct npc_mcam_alloc_counter_req *req,
+			struct npc_mcam_alloc_counter_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	u16 max_contig, cntr;
+	int blkaddr, index;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	/* If the request is from a PFFUNC with no NIXLF attached, ignore */
+	if (!is_nixlf_attached(rvu, pcifunc))
+		return NPC_MCAM_INVALID_REQ;
+
+	/* Since list of allocated counter IDs needs to be sent to requester,
+	 * max number of non-contiguous counters per mbox msg is limited.
+	 */
+	if (!req->contig && req->count > NPC_MAX_NONCONTIG_COUNTERS)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+
+	/* Check if unused counters are available or not */
+	if (!rvu_rsrc_free_count(&mcam->counters)) {
+		mutex_unlock(&mcam->lock);
+		return NPC_MCAM_ALLOC_FAILED;
+	}
+
+	rsp->count = 0;
+
+	if (req->contig) {
+		/* Allocate requested number of contiguous counters, if
+		 * unsuccessful find max contiguous entries available.
+		 */
+		index = npc_mcam_find_zero_area(mcam->counters.bmap,
+						mcam->counters.max, 0,
+						req->count, &max_contig);
+		rsp->count = max_contig;
+		rsp->cntr = index;
+		for (cntr = index; cntr < (index + max_contig); cntr++) {
+			__set_bit(cntr, mcam->counters.bmap);
+			mcam->cntr2pfvf_map[cntr] = pcifunc;
+		}
+	} else {
+		/* Allocate requested number of non-contiguous counters,
+		 * if unsuccessful allocate as many as possible.
+		 */
+		for (cntr = 0; cntr < req->count; cntr++) {
+			index = rvu_alloc_rsrc(&mcam->counters);
+			if (index < 0)
+				break;
+			rsp->cntr_list[cntr] = index;
+			rsp->count++;
+			mcam->cntr2pfvf_map[index] = pcifunc;
+		}
+	}
+
+	mutex_unlock(&mcam->lock);
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu,
+		struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int err;
+
+	mutex_lock(&mcam->lock);
+	err = npc_mcam_verify_counter(mcam, req->hdr.pcifunc, req->cntr);
+	if (err) {
+		mutex_unlock(&mcam->lock);
+		return err;
+	}
+
+	/* Mark counter as free/unused */
+	mcam->cntr2pfvf_map[req->cntr] = NPC_MCAM_INVALID_MAP;
+	rvu_free_rsrc(&mcam->counters, req->cntr);
+	mutex_unlock(&mcam->lock);
+
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_clear_counter(struct rvu *rvu,
+		struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr, err;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	err = npc_mcam_verify_counter(mcam, req->hdr.pcifunc, req->cntr);
+	mutex_unlock(&mcam->lock);
+	if (err)
+		return err;
+
+	rvu_write64(rvu, blkaddr, NPC_AF_MATCH_STATX(req->cntr), 0x00);
+
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_counter_stats(struct rvu *rvu,
+			struct npc_mcam_oper_counter_req *req,
+			struct npc_mcam_oper_counter_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr, err;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	err = npc_mcam_verify_counter(mcam, req->hdr.pcifunc, req->cntr);
+	mutex_unlock(&mcam->lock);
+	if (err)
+		return err;
+
+	rsp->stat = rvu_read64(rvu, blkaddr, NPC_AF_MATCH_STATX(req->cntr));
+	rsp->stat &= BIT_ULL(48) - 1;
+
+	return 0;
+}
-- 
cgit v1.2.3


From a958dd59f9cef9fa7b38258a559a162a09b3ae00 Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Mon, 19 Nov 2018 16:17:30 +0530
Subject: octeontx2-af: Map or unmap NPC MCAM entry and counter

Alloc memory to save MCAM 'entry to counter' mapping and since
multiple entries can map to same counter, added counter's reference
count tracking.

Do 'entry to counter' mapping when a entry is being installed
and mbox msg sender requested to configure a counter as well.
Mapping is removed when a entry or counter is being freed or
a explicit mbox msg is received to unmap them.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |   9 +
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |   4 +
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 183 ++++++++++++++++++++-
 3 files changed, 192 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 0ab74ee77eb3..2caf43011d9b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -166,6 +166,8 @@ M(NPC_MCAM_ALLOC_COUNTER, 0x6006, npc_mcam_alloc_counter,		\
 					npc_mcam_alloc_counter_rsp)	\
 M(NPC_MCAM_FREE_COUNTER,  0x6007, npc_mcam_free_counter,		\
 				    npc_mcam_oper_counter_req, msg_rsp)	\
+M(NPC_MCAM_UNMAP_COUNTER, 0x6008, npc_mcam_unmap_counter,		\
+				   npc_mcam_unmap_counter_req, msg_rsp)	\
 M(NPC_MCAM_CLEAR_COUNTER, 0x6009, npc_mcam_clear_counter,		\
 				   npc_mcam_oper_counter_req, msg_rsp)	\
 M(NPC_MCAM_COUNTER_STATS, 0x600a, npc_mcam_counter_stats,		\
@@ -671,4 +673,11 @@ struct npc_mcam_oper_counter_rsp {
 	u64 stat;  /* valid only while fetching counter's stats */
 };
 
+struct npc_mcam_unmap_counter_req {
+	struct mbox_msghdr hdr;
+	u16 cntr;
+	u16 entry; /* Entry and counter to be unmapped */
+	u8  all;   /* Unmap all entries using this counter ? */
+};
+
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 898b59c4a9cf..e34f1bf451c7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -81,7 +81,9 @@ struct npc_mcam {
 	u16	bmap_entries;	/* Number of unreserved MCAM entries */
 	u16	bmap_fcnt;	/* MCAM entries free count */
 	u16	*entry2pfvf_map;
+	u16	*entry2cntr_map;
 	u16	*cntr2pfvf_map;
+	u16	*cntr_refcnt;
 	u8	keysize;	/* MCAM keysize 112/224/448 bits */
 	u8	banks;		/* Number of MCAM banks */
 	u8	banks_per_entry;/* Number of keywords in key */
@@ -405,6 +407,8 @@ int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu,
 		   struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp);
 int rvu_mbox_handler_npc_mcam_clear_counter(struct rvu *rvu,
 		struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_unmap_counter(struct rvu *rvu,
+		struct npc_mcam_unmap_counter_req *req, struct msg_rsp *rsp);
 int rvu_mbox_handler_npc_mcam_counter_stats(struct rvu *rvu,
 			struct npc_mcam_oper_counter_req *req,
 			struct npc_mcam_oper_counter_rsp *rsp);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 1ec508e41653..6d03c72cae67 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -28,6 +28,8 @@
 
 static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam,
 				      int blkaddr, u16 pcifunc);
+static void npc_mcam_free_all_counters(struct rvu *rvu, struct npc_mcam *mcam,
+				       u16 pcifunc);
 
 void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf)
 {
@@ -506,6 +508,9 @@ void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
 	/* Disable and free all MCAM entries mapped to this 'pcifunc' */
 	npc_mcam_free_all_entries(rvu, mcam, blkaddr, pcifunc);
 
+	/* Free all MCAM counters mapped to this 'pcifunc' */
+	npc_mcam_free_all_counters(rvu, mcam, pcifunc);
+
 	mutex_unlock(&mcam->lock);
 
 	/* Disable ucast MCAM match entry of this PF/VF */
@@ -819,6 +824,19 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	if (!mcam->cntr2pfvf_map)
 		goto free_mem;
 
+	/* Alloc memory for MCAM entry to counter mapping and for tracking
+	 * counter's reference count.
+	 */
+	mcam->entry2cntr_map = devm_kcalloc(rvu->dev, mcam->bmap_entries,
+					    sizeof(u16), GFP_KERNEL);
+	if (!mcam->entry2cntr_map)
+		goto free_mem;
+
+	mcam->cntr_refcnt = devm_kcalloc(rvu->dev, mcam->counters.max,
+					 sizeof(u16), GFP_KERNEL);
+	if (!mcam->cntr_refcnt)
+		goto free_mem;
+
 	mutex_init(&mcam->lock);
 
 	return 0;
@@ -948,6 +966,36 @@ static int npc_mcam_verify_counter(struct npc_mcam *mcam,
 	return 0;
 }
 
+static void npc_map_mcam_entry_and_cntr(struct rvu *rvu, struct npc_mcam *mcam,
+					int blkaddr, u16 entry, u16 cntr)
+{
+	u16 index = entry & (mcam->banksize - 1);
+	u16 bank = npc_get_bank(mcam, entry);
+
+	/* Set mapping and increment counter's refcnt */
+	mcam->entry2cntr_map[entry] = cntr;
+	mcam->cntr_refcnt[cntr]++;
+	/* Enable stats */
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_STAT_ACT(index, bank),
+		    BIT_ULL(9) | cntr);
+}
+
+static void npc_unmap_mcam_entry_and_cntr(struct rvu *rvu,
+					  struct npc_mcam *mcam,
+					  int blkaddr, u16 entry, u16 cntr)
+{
+	u16 index = entry & (mcam->banksize - 1);
+	u16 bank = npc_get_bank(mcam, entry);
+
+	/* Remove mapping and reduce counter's refcnt */
+	mcam->entry2cntr_map[entry] = NPC_MCAM_INVALID_MAP;
+	mcam->cntr_refcnt[cntr]--;
+	/* Disable stats */
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_STAT_ACT(index, bank), 0x00);
+}
+
 /* Sets MCAM entry in bitmap as used. Update
  * reverse bitmap too. Should be called with
  * 'mcam->lock' held.
@@ -983,7 +1031,7 @@ static void npc_mcam_clear_bit(struct npc_mcam *mcam, u16 index)
 static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam,
 				      int blkaddr, u16 pcifunc)
 {
-	u16 index;
+	u16 index, cntr;
 
 	/* Scan all MCAM entries and free the ones mapped to 'pcifunc' */
 	for (index = 0; index < mcam->bmap_entries; index++) {
@@ -993,6 +1041,33 @@ static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam,
 			npc_mcam_clear_bit(mcam, index);
 			/* Disable the entry */
 			npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
+
+			/* Update entry2counter mapping */
+			cntr = mcam->entry2cntr_map[index];
+			if (cntr != NPC_MCAM_INVALID_MAP)
+				npc_unmap_mcam_entry_and_cntr(rvu, mcam,
+							      blkaddr, index,
+							      cntr);
+		}
+	}
+}
+
+static void npc_mcam_free_all_counters(struct rvu *rvu, struct npc_mcam *mcam,
+				       u16 pcifunc)
+{
+	u16 cntr;
+
+	/* Scan all MCAM counters and free the ones mapped to 'pcifunc' */
+	for (cntr = 0; cntr < mcam->counters.max; cntr++) {
+		if (mcam->cntr2pfvf_map[cntr] == pcifunc) {
+			mcam->cntr2pfvf_map[cntr] = NPC_MCAM_INVALID_MAP;
+			mcam->cntr_refcnt[cntr] = 0;
+			rvu_free_rsrc(&mcam->counters, cntr);
+			/* This API is expected to be called after freeing
+			 * MCAM entries, which inturn will remove
+			 * 'entry to counter' mapping.
+			 * No need to do it again.
+			 */
 		}
 	}
 }
@@ -1282,6 +1357,7 @@ alloc:
 			(rsp->entry + entry) : rsp->entry_list[entry];
 		npc_mcam_set_bit(mcam, index);
 		mcam->entry2pfvf_map[index] = pcifunc;
+		mcam->entry2cntr_map[index] = NPC_MCAM_INVALID_MAP;
 	}
 
 	/* Update available free count in mbox response */
@@ -1338,6 +1414,7 @@ int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu,
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	u16 pcifunc = req->hdr.pcifunc;
 	int blkaddr, rc = 0;
+	u16 cntr;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0)
@@ -1360,6 +1437,12 @@ int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu,
 	npc_mcam_clear_bit(mcam, req->entry);
 	npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, false);
 
+	/* Update entry2counter mapping */
+	cntr = mcam->entry2cntr_map[req->entry];
+	if (cntr != NPC_MCAM_INVALID_MAP)
+		npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+					      req->entry, cntr);
+
 	goto exit;
 
 free_all:
@@ -1387,6 +1470,12 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
 	if (rc)
 		goto exit;
 
+	if (req->set_cntr &&
+	    npc_mcam_verify_counter(mcam, pcifunc, req->cntr)) {
+		rc = NPC_MCAM_INVALID_REQ;
+		goto exit;
+	}
+
 	if (req->intf != NIX_INTF_RX && req->intf != NIX_INTF_TX) {
 		rc = NPC_MCAM_INVALID_REQ;
 		goto exit;
@@ -1395,6 +1484,10 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
 	npc_config_mcam_entry(rvu, mcam, blkaddr, req->entry, req->intf,
 			      &req->entry_data, req->enable_entry);
 
+	if (req->set_cntr)
+		npc_map_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+					    req->entry, req->cntr);
+
 	rc = 0;
 exit:
 	mutex_unlock(&mcam->lock);
@@ -1454,8 +1547,8 @@ int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu,
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	u16 pcifunc = req->hdr.pcifunc;
 	u16 old_entry, new_entry;
+	u16 index, cntr;
 	int blkaddr, rc;
-	u16 index;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0)
@@ -1480,12 +1573,27 @@ int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu,
 		if (rc)
 			break;
 
+		/* new_entry should not have a counter mapped */
+		if (mcam->entry2cntr_map[new_entry] != NPC_MCAM_INVALID_MAP) {
+			rc = NPC_MCAM_PERM_DENIED;
+			break;
+		}
+
 		/* Disable the new_entry */
 		npc_enable_mcam_entry(rvu, mcam, blkaddr, new_entry, false);
 
 		/* Copy rule from old entry to new entry */
 		npc_copy_mcam_entry(rvu, mcam, blkaddr, old_entry, new_entry);
 
+		/* Copy counter mapping, if any */
+		cntr = mcam->entry2cntr_map[old_entry];
+		if (cntr != NPC_MCAM_INVALID_MAP) {
+			npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+						      old_entry, cntr);
+			npc_map_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+						    new_entry, cntr);
+		}
+
 		/* Enable new_entry and disable old_entry */
 		npc_enable_mcam_entry(rvu, mcam, blkaddr, new_entry, true);
 		npc_enable_mcam_entry(rvu, mcam, blkaddr, old_entry, false);
@@ -1569,7 +1677,12 @@ int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu,
 		struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
-	int err;
+	u16 index, entry = 0;
+	int blkaddr, err;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
 
 	mutex_lock(&mcam->lock);
 	err = npc_mcam_verify_counter(mcam, req->hdr.pcifunc, req->cntr);
@@ -1581,11 +1694,73 @@ int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu,
 	/* Mark counter as free/unused */
 	mcam->cntr2pfvf_map[req->cntr] = NPC_MCAM_INVALID_MAP;
 	rvu_free_rsrc(&mcam->counters, req->cntr);
-	mutex_unlock(&mcam->lock);
 
+	/* Disable all MCAM entry's stats which are using this counter */
+	while (entry < mcam->bmap_entries) {
+		if (!mcam->cntr_refcnt[req->cntr])
+			break;
+
+		index = find_next_bit(mcam->bmap, mcam->bmap_entries, entry);
+		if (index >= mcam->bmap_entries)
+			break;
+		if (mcam->entry2cntr_map[index] != req->cntr)
+			continue;
+
+		entry = index + 1;
+		npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+					      index, req->cntr);
+	}
+
+	mutex_unlock(&mcam->lock);
 	return 0;
 }
 
+int rvu_mbox_handler_npc_mcam_unmap_counter(struct rvu *rvu,
+		struct npc_mcam_unmap_counter_req *req, struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 index, entry = 0;
+	int blkaddr, rc;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	rc = npc_mcam_verify_counter(mcam, req->hdr.pcifunc, req->cntr);
+	if (rc)
+		goto exit;
+
+	/* Unmap the MCAM entry and counter */
+	if (!req->all) {
+		rc = npc_mcam_verify_entry(mcam, req->hdr.pcifunc, req->entry);
+		if (rc)
+			goto exit;
+		npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+					      req->entry, req->cntr);
+		goto exit;
+	}
+
+	/* Disable all MCAM entry's stats which are using this counter */
+	while (entry < mcam->bmap_entries) {
+		if (!mcam->cntr_refcnt[req->cntr])
+			break;
+
+		index = find_next_bit(mcam->bmap, mcam->bmap_entries, entry);
+		if (index >= mcam->bmap_entries)
+			break;
+		if (mcam->entry2cntr_map[index] != req->cntr)
+			continue;
+
+		entry = index + 1;
+		npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+					      index, req->cntr);
+	}
+exit:
+	mutex_unlock(&mcam->lock);
+	return rc;
+}
+
 int rvu_mbox_handler_npc_mcam_clear_counter(struct rvu *rvu,
 		struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp)
 {
-- 
cgit v1.2.3


From 63be91c89dd435fa5e88e7bae5390bfea5d54743 Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Mon, 19 Nov 2018 16:17:31 +0530
Subject: octeontx2-af: Alloc and config NPC MCAM entry at a time

A new mailbox message is added to support allocating a MCAM entry
along with a counter and configuring it in one go. This reduces
the amount of mailbox communication involved in installing a new
MCAM rule.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   | 19 ++++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  3 +
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 72 ++++++++++++++++++++++
 3 files changed, 94 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 2caf43011d9b..bc1011059542 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -173,6 +173,9 @@ M(NPC_MCAM_CLEAR_COUNTER, 0x6009, npc_mcam_clear_counter,		\
 M(NPC_MCAM_COUNTER_STATS, 0x600a, npc_mcam_counter_stats,		\
 				   npc_mcam_oper_counter_req,		\
 				   npc_mcam_oper_counter_rsp)		\
+M(NPC_MCAM_ALLOC_AND_WRITE_ENTRY, 0x600b, npc_mcam_alloc_and_write_entry,      \
+					  npc_mcam_alloc_and_write_entry_req,  \
+					  npc_mcam_alloc_and_write_entry_rsp)  \
 /* NIX mbox IDs (range 0x8000 - 0xFFFF) */				\
 M(NIX_LF_ALLOC,		0x8000, nix_lf_alloc,				\
 				 nix_lf_alloc_req, nix_lf_alloc_rsp)	\
@@ -680,4 +683,20 @@ struct npc_mcam_unmap_counter_req {
 	u8  all;   /* Unmap all entries using this counter ? */
 };
 
+struct npc_mcam_alloc_and_write_entry_req {
+	struct mbox_msghdr hdr;
+	struct mcam_entry entry_data;
+	u16 ref_entry;
+	u8  priority;    /* Lower or higher w.r.t ref_entry */
+	u8  intf;	 /* Rx or Tx interface */
+	u8  enable_entry;/* Enable this MCAM entry ? */
+	u8  alloc_cntr;  /* Allocate counter and map ? */
+};
+
+struct npc_mcam_alloc_and_write_entry_rsp {
+	struct mbox_msghdr hdr;
+	u16 entry;
+	u16 cntr;
+};
+
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index e34f1bf451c7..ca13c1648ca1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -412,4 +412,7 @@ int rvu_mbox_handler_npc_mcam_unmap_counter(struct rvu *rvu,
 int rvu_mbox_handler_npc_mcam_counter_stats(struct rvu *rvu,
 			struct npc_mcam_oper_counter_req *req,
 			struct npc_mcam_oper_counter_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
+			  struct npc_mcam_alloc_and_write_entry_req *req,
+			  struct npc_mcam_alloc_and_write_entry_rsp *rsp);
 #endif /* RVU_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 6d03c72cae67..b74e5a691f9e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -1804,3 +1804,75 @@ int rvu_mbox_handler_npc_mcam_counter_stats(struct rvu *rvu,
 
 	return 0;
 }
+
+int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
+			  struct npc_mcam_alloc_and_write_entry_req *req,
+			  struct npc_mcam_alloc_and_write_entry_rsp *rsp)
+{
+	struct npc_mcam_alloc_counter_req cntr_req;
+	struct npc_mcam_alloc_counter_rsp cntr_rsp;
+	struct npc_mcam_alloc_entry_req entry_req;
+	struct npc_mcam_alloc_entry_rsp entry_rsp;
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 entry = NPC_MCAM_ENTRY_INVALID;
+	u16 cntr = NPC_MCAM_ENTRY_INVALID;
+	int blkaddr, rc;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	if (req->intf != NIX_INTF_RX && req->intf != NIX_INTF_TX)
+		return NPC_MCAM_INVALID_REQ;
+
+	/* Try to allocate a MCAM entry */
+	entry_req.hdr.pcifunc = req->hdr.pcifunc;
+	entry_req.contig = true;
+	entry_req.priority = req->priority;
+	entry_req.ref_entry = req->ref_entry;
+	entry_req.count = 1;
+
+	rc = rvu_mbox_handler_npc_mcam_alloc_entry(rvu,
+						   &entry_req, &entry_rsp);
+	if (rc)
+		return rc;
+
+	if (!entry_rsp.count)
+		return NPC_MCAM_ALLOC_FAILED;
+
+	entry = entry_rsp.entry;
+
+	if (!req->alloc_cntr)
+		goto write_entry;
+
+	/* Now allocate counter */
+	cntr_req.hdr.pcifunc = req->hdr.pcifunc;
+	cntr_req.contig = true;
+	cntr_req.count = 1;
+
+	rc = rvu_mbox_handler_npc_mcam_alloc_counter(rvu, &cntr_req, &cntr_rsp);
+	if (rc) {
+		/* Free allocated MCAM entry */
+		mutex_lock(&mcam->lock);
+		mcam->entry2pfvf_map[entry] = 0;
+		npc_mcam_clear_bit(mcam, entry);
+		mutex_unlock(&mcam->lock);
+		return rc;
+	}
+
+	cntr = cntr_rsp.cntr;
+
+write_entry:
+	mutex_lock(&mcam->lock);
+	npc_config_mcam_entry(rvu, mcam, blkaddr, entry, req->intf,
+			      &req->entry_data, req->enable_entry);
+
+	if (req->alloc_cntr)
+		npc_map_mcam_entry_and_cntr(rvu, mcam, blkaddr, entry, cntr);
+	mutex_unlock(&mcam->lock);
+
+	rsp->entry = entry;
+	rsp->cntr = cntr;
+
+	return 0;
+}
-- 
cgit v1.2.3


From 631e70bb84e08d4b2c14119f9d2a1cb9ea6dbf30 Mon Sep 17 00:00:00 2001
From: Santosh Shukla <sshukla@marvell.com>
Date: Mon, 19 Nov 2018 16:17:32 +0530
Subject: octeontx2-af: Add MKEX default profile

Added basic default MKEX profile. This profile tells
hardware what data to extract from packet and where to
place it (bit offset) in final KEY generated for the
parsed packet. Based on the bit placement of the packet
data, MCAM entries have to programmed for matching.

Also added a msg to retrieve this MKEX profile from PF/VF
which inturn can process it to determine how MCAM entry
has to be populated.

Signed-off-by: Santosh Shukla <sshukla@marvell.com>
Signed-off-by: Yuri Tolstov <ytolstov@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  19 +++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |   2 +
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 155 +++++++++++++++++----
 3 files changed, 151 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index bc1011059542..bef1605364e3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -176,6 +176,8 @@ M(NPC_MCAM_COUNTER_STATS, 0x600a, npc_mcam_counter_stats,		\
 M(NPC_MCAM_ALLOC_AND_WRITE_ENTRY, 0x600b, npc_mcam_alloc_and_write_entry,      \
 					  npc_mcam_alloc_and_write_entry_req,  \
 					  npc_mcam_alloc_and_write_entry_rsp)  \
+M(NPC_GET_KEX_CFG,	  0x600c, npc_get_kex_cfg,			\
+				   msg_req, npc_get_kex_cfg_rsp)	\
 /* NIX mbox IDs (range 0x8000 - 0xFFFF) */				\
 M(NIX_LF_ALLOC,		0x8000, nix_lf_alloc,				\
 				 nix_lf_alloc_req, nix_lf_alloc_rsp)	\
@@ -699,4 +701,21 @@ struct npc_mcam_alloc_and_write_entry_rsp {
 	u16 cntr;
 };
 
+struct npc_get_kex_cfg_rsp {
+	struct mbox_msghdr hdr;
+	u64 rx_keyx_cfg;   /* NPC_AF_INTF(0)_KEX_CFG */
+	u64 tx_keyx_cfg;   /* NPC_AF_INTF(1)_KEX_CFG */
+#define NPC_MAX_INTF	2
+#define NPC_MAX_LID	8
+#define NPC_MAX_LT	16
+#define NPC_MAX_LD	2
+#define NPC_MAX_LFL	16
+	/* NPC_AF_KEX_LDATA(0..1)_FLAGS_CFG */
+	u64 kex_ld_flags[NPC_MAX_LD];
+	/* NPC_AF_INTF(0..1)_LID(0..7)_LT(0..15)_LD(0..1)_CFG */
+	u64 intf_lid_lt_ld[NPC_MAX_INTF][NPC_MAX_LID][NPC_MAX_LT][NPC_MAX_LD];
+	/* NPC_AF_INTF(0..1)_LDATA(0..1)_FLAGS(0..15)_CFG */
+	u64 intf_ld_flags[NPC_MAX_INTF][NPC_MAX_LD][NPC_MAX_LFL];
+};
+
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index ca13c1648ca1..93a74b6803f5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -415,4 +415,6 @@ int rvu_mbox_handler_npc_mcam_counter_stats(struct rvu *rvu,
 int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
 			  struct npc_mcam_alloc_and_write_entry_req *req,
 			  struct npc_mcam_alloc_and_write_entry_rsp *rsp);
+int rvu_mbox_handler_npc_get_kex_cfg(struct rvu *rvu, struct msg_req *req,
+				     struct npc_get_kex_cfg_rsp *rsp);
 #endif /* RVU_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index b74e5a691f9e..d749611b23cd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -427,9 +427,28 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
 					 nixlf, NIXLF_BCAST_ENTRY);
 
-	/* Check for L2B bit and LMAC channel */
-	entry.kw[0] = BIT_ULL(25) | chan;
-	entry.kw_mask[0] = BIT_ULL(25) | 0xFFFULL;
+	/* Check for L2B bit and LMAC channel
+	 * NOTE: Since MKEX default profile(a reduced version intended to
+	 * accommodate more capability but igoring few bits) a stap-gap
+	 * approach.
+	 * Since we care for L2B which by HRM NPC_PARSE_KEX_S at BIT_POS[25], So
+	 * moved to BIT_POS[13], ignoring ERRCODE, ERRLEV as we'll loose out
+	 * on capability features needed for CoS (/from ODP PoV) e.g: VLAN,
+	 * DSCP.
+	 *
+	 * Reduced layout of MKEX default profile -
+	 * Includes following are (i.e.CHAN, L2/3{B/M}, LA, LB, LC, LD):
+	 *
+	 * BIT_POS[31:28] : LD
+	 * BIT_POS[27:24] : LC
+	 * BIT_POS[23:20] : LB
+	 * BIT_POS[19:16] : LA
+	 * BIT_POS[15:12] : L3B, L3M, L2B, L2M
+	 * BIT_POS[11:00] : CHAN
+	 *
+	 */
+	entry.kw[0] = BIT_ULL(13) | chan;
+	entry.kw_mask[0] = ~entry.kw[0] & (BIT_ULL(13) | 0xFFFULL);
 
 	*(u64 *)&action = 0x00;
 #ifdef MCAST_MCE
@@ -538,14 +557,18 @@ void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
 	}
 }
 
-#define LDATA_EXTRACT_CONFIG(intf, lid, ltype, ld, cfg) \
+#define SET_KEX_LD(intf, lid, ltype, ld, cfg)	\
 	rvu_write64(rvu, blkaddr,			\
 		NPC_AF_INTFX_LIDX_LTX_LDX_CFG(intf, lid, ltype, ld), cfg)
 
-#define LDATA_FLAGS_CONFIG(intf, ld, flags, cfg)	\
+#define SET_KEX_LDFLAGS(intf, ld, flags, cfg)	\
 	rvu_write64(rvu, blkaddr,			\
 		NPC_AF_INTFX_LDATAX_FLAGSX_CFG(intf, ld, flags), cfg)
 
+#define KEX_LD_CFG(bytesm1, hdr_ofs, ena, flags_ena, key_ofs)		\
+			(((bytesm1) << 16) | ((hdr_ofs) << 8) | ((ena) << 7) | \
+			 ((flags_ena) << 6) | ((key_ofs) & 0x3F))
+
 static void npc_config_ldata_extract(struct rvu *rvu, int blkaddr)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
@@ -561,28 +584,66 @@ static void npc_config_ldata_extract(struct rvu *rvu, int blkaddr)
 	 */
 	for (lid = 0; lid < lid_count; lid++) {
 		for (ltype = 0; ltype < 16; ltype++) {
-			LDATA_EXTRACT_CONFIG(NIX_INTF_RX, lid, ltype, 0, 0ULL);
-			LDATA_EXTRACT_CONFIG(NIX_INTF_RX, lid, ltype, 1, 0ULL);
-			LDATA_EXTRACT_CONFIG(NIX_INTF_TX, lid, ltype, 0, 0ULL);
-			LDATA_EXTRACT_CONFIG(NIX_INTF_TX, lid, ltype, 1, 0ULL);
-
-			LDATA_FLAGS_CONFIG(NIX_INTF_RX, 0, ltype, 0ULL);
-			LDATA_FLAGS_CONFIG(NIX_INTF_RX, 1, ltype, 0ULL);
-			LDATA_FLAGS_CONFIG(NIX_INTF_TX, 0, ltype, 0ULL);
-			LDATA_FLAGS_CONFIG(NIX_INTF_TX, 1, ltype, 0ULL);
+			SET_KEX_LD(NIX_INTF_RX, lid, ltype, 0, 0ULL);
+			SET_KEX_LD(NIX_INTF_RX, lid, ltype, 1, 0ULL);
+			SET_KEX_LD(NIX_INTF_TX, lid, ltype, 0, 0ULL);
+			SET_KEX_LD(NIX_INTF_TX, lid, ltype, 1, 0ULL);
+
+			SET_KEX_LDFLAGS(NIX_INTF_RX, 0, ltype, 0ULL);
+			SET_KEX_LDFLAGS(NIX_INTF_RX, 1, ltype, 0ULL);
+			SET_KEX_LDFLAGS(NIX_INTF_TX, 0, ltype, 0ULL);
+			SET_KEX_LDFLAGS(NIX_INTF_TX, 1, ltype, 0ULL);
 		}
 	}
 
-	/* If we plan to extract Outer IPv4 tuple for TCP/UDP pkts
-	 * then 112bit key is not sufficient
-	 */
 	if (mcam->keysize != NPC_MCAM_KEY_X2)
 		return;
 
-	/* Start placing extracted data/flags from 64bit onwards, for now */
-	/* Extract DMAC from the packet */
-	cfg = (0x05 << 16) | BIT_ULL(7) | NPC_PARSE_RESULT_DMAC_OFFSET;
-	LDATA_EXTRACT_CONFIG(NIX_INTF_RX, NPC_LID_LA, NPC_LT_LA_ETHER, 0, cfg);
+	/* Default MCAM KEX profile */
+	/* Layer A: Ethernet: */
+
+	/* DMAC: 6 bytes, KW1[47:0] */
+	cfg = KEX_LD_CFG(0x05, 0x0, 0x1, 0x0, NPC_PARSE_RESULT_DMAC_OFFSET);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LA, NPC_LT_LA_ETHER, 0, cfg);
+
+	/* Ethertype: 2 bytes, KW0[47:32] */
+	cfg = KEX_LD_CFG(0x01, 0xc, 0x1, 0x0, 0x4);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LA, NPC_LT_LA_ETHER, 1, cfg);
+
+	/* Layer B: Single VLAN (CTAG) */
+	/* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
+	cfg = KEX_LD_CFG(0x03, 0x0, 0x1, 0x0, 0x4);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LB, NPC_LT_LB_CTAG, 0, cfg);
+
+	/* Layer B: Stacked VLAN (STAG|QinQ) */
+	/* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
+	cfg = KEX_LD_CFG(0x03, 0x4, 0x1, 0x0, 0x4);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LB, NPC_LT_LB_STAG, 0, cfg);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LB, NPC_LT_LB_QINQ, 0, cfg);
+
+	/* Layer C: IPv4 */
+	/* SIP+DIP: 8 bytes, KW2[63:0] */
+	cfg = KEX_LD_CFG(0x07, 0xc, 0x1, 0x0, 0x10);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LC, NPC_LT_LC_IP, 0, cfg);
+	/* TOS: 1 byte, KW1[63:56] */
+	cfg = KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0xf);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LC, NPC_LT_LC_IP, 1, cfg);
+
+	/* Layer D:UDP */
+	/* SPORT: 2 bytes, KW3[15:0] */
+	cfg = KEX_LD_CFG(0x1, 0x0, 0x1, 0x0, 0x18);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_UDP, 0, cfg);
+	/* DPORT: 2 bytes, KW3[31:16] */
+	cfg = KEX_LD_CFG(0x1, 0x2, 0x1, 0x0, 0x1a);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_UDP, 1, cfg);
+
+	/* Layer D:TCP */
+	/* SPORT: 2 bytes, KW3[15:0] */
+	cfg = KEX_LD_CFG(0x1, 0x0, 0x1, 0x0, 0x18);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_TCP, 0, cfg);
+	/* DPORT: 2 bytes, KW3[31:16] */
+	cfg = KEX_LD_CFG(0x1, 0x2, 0x1, 0x0, 0x1a);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_TCP, 1, cfg);
 }
 
 static void npc_config_kpuaction(struct rvu *rvu, int blkaddr,
@@ -898,13 +959,12 @@ int rvu_npc_init(struct rvu *rvu)
 		    BIT_ULL(6) | BIT_ULL(2));
 
 	/* Set RX and TX side MCAM search key size.
-	 * Also enable parse key extract nibbles suchthat except
-	 * layer E to H, rest of the key is included for MCAM search.
+	 * LA..LD (ltype only) + Channel
 	 */
 	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX),
-		    ((keyz & 0x3) << 32) | ((1ULL << 20) - 1));
+			((keyz & 0x3) << 32) | 0x49247);
 	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX),
-		    ((keyz & 0x3) << 32) | ((1ULL << 20) - 1));
+			((keyz & 0x3) << 32) | ((1ULL << 19) - 1));
 
 	err = npc_mcam_rsrcs_init(rvu, blkaddr);
 	if (err)
@@ -1876,3 +1936,48 @@ write_entry:
 
 	return 0;
 }
+
+#define GET_KEX_CFG(intf) \
+	rvu_read64(rvu, BLKADDR_NPC, NPC_AF_INTFX_KEX_CFG(intf))
+
+#define GET_KEX_FLAGS(ld) \
+	rvu_read64(rvu, BLKADDR_NPC, NPC_AF_KEX_LDATAX_FLAGS_CFG(ld))
+
+#define GET_KEX_LD(intf, lid, lt, ld)	\
+	rvu_read64(rvu, BLKADDR_NPC,	\
+		NPC_AF_INTFX_LIDX_LTX_LDX_CFG(intf, lid, lt, ld))
+
+#define GET_KEX_LDFLAGS(intf, ld, fl)	\
+	rvu_read64(rvu, BLKADDR_NPC,	\
+		NPC_AF_INTFX_LDATAX_FLAGSX_CFG(intf, ld, fl))
+
+int rvu_mbox_handler_npc_get_kex_cfg(struct rvu *rvu, struct msg_req *req,
+				     struct npc_get_kex_cfg_rsp *rsp)
+{
+	int lid, lt, ld, fl;
+
+	rsp->rx_keyx_cfg = GET_KEX_CFG(NIX_INTF_RX);
+	rsp->tx_keyx_cfg = GET_KEX_CFG(NIX_INTF_TX);
+	for (lid = 0; lid < NPC_MAX_LID; lid++) {
+		for (lt = 0; lt < NPC_MAX_LT; lt++) {
+			for (ld = 0; ld < NPC_MAX_LD; ld++) {
+				rsp->intf_lid_lt_ld[NIX_INTF_RX][lid][lt][ld] =
+					GET_KEX_LD(NIX_INTF_RX, lid, lt, ld);
+				rsp->intf_lid_lt_ld[NIX_INTF_TX][lid][lt][ld] =
+					GET_KEX_LD(NIX_INTF_TX, lid, lt, ld);
+			}
+		}
+	}
+	for (ld = 0; ld < NPC_MAX_LD; ld++)
+		rsp->kex_ld_flags[ld] = GET_KEX_FLAGS(ld);
+
+	for (ld = 0; ld < NPC_MAX_LD; ld++) {
+		for (fl = 0; fl < NPC_MAX_LFL; fl++) {
+			rsp->intf_ld_flags[NIX_INTF_RX][ld][fl] =
+					GET_KEX_LDFLAGS(NIX_INTF_RX, ld, fl);
+			rsp->intf_ld_flags[NIX_INTF_TX][ld][fl] =
+					GET_KEX_LDFLAGS(NIX_INTF_TX, ld, fl);
+		}
+	}
+	return 0;
+}
-- 
cgit v1.2.3


From 40df309e4166c69600968c93846aa0b1821e83f0 Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Mon, 19 Nov 2018 16:17:33 +0530
Subject: octeontx2-af: Support to enable/disable default MCAM entries

For a PF/VF with a NIXLF attached has default/reserved MCAM entries
for receiving Ucast/Bcast/Promisc traffic. Ideally traffic should be
forwarded to NIXLF only after it's contexts are initialized. This
patch keeps these default entries disabled and adds mbox messages
for a PF/VF to enable these once NPA/NIXLF initialization is done.
Likewise while PF/VF is being teared down, it can send the disable
mailbox message to stop receiving traffic.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  4 +-
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  7 ++
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 48 ++++++++++++
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 91 +++++++++++++++-------
 4 files changed, 122 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index bef1605364e3..39fe62a838ef 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -195,7 +195,9 @@ M(NIX_RSS_FLOWKEY_CFG,  0x8009, nix_rss_flowkey_cfg,			\
 				 nix_rss_flowkey_cfg, msg_rsp)		\
 M(NIX_SET_MAC_ADDR,	0x800a, nix_set_mac_addr, nix_set_mac_addr, msg_rsp) \
 M(NIX_SET_RX_MODE,	0x800b, nix_set_rx_mode, nix_rx_mode, msg_rsp)	\
-M(NIX_SET_HW_FRS,	0x800c, nix_set_hw_frs, nix_frs_cfg, msg_rsp)
+M(NIX_SET_HW_FRS,	0x800c, nix_set_hw_frs, nix_frs_cfg, msg_rsp)	\
+M(NIX_LF_START_RX,	0x800d, nix_lf_start_rx, msg_req, msg_rsp)	\
+M(NIX_LF_STOP_RX,	0x800e, nix_lf_stop_rx, msg_req, msg_rsp)
 
 /* Messages initiated by AF (range 0xC00 - 0xDFF) */
 #define MBOX_UP_CGX_MESSAGES						\
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 93a74b6803f5..19d5f16244f6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -366,6 +366,10 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 				     struct msg_rsp *rsp);
 int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
 				    struct msg_rsp *rsp);
+int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
+				     struct msg_rsp *rsp);
+int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
+				    struct msg_rsp *rsp);
 
 /* NPC APIs */
 int rvu_npc_init(struct rvu *rvu);
@@ -377,9 +381,12 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 				   int nixlf, u64 chan, bool allmulti);
 void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf);
+void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, u64 chan);
 void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
+void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
+void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    int group, int alg_idx, int mcam_index);
 int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 0491e358b769..fb8456eb59af 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -821,6 +821,9 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 	if (err)
 		goto free_mem;
 
+	/* Disable NPC entries as NIXLF's contexts are not initialized yet */
+	rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
+
 	goto exit;
 
 free_mem:
@@ -2176,3 +2179,48 @@ void rvu_nix_freemem(struct rvu *rvu)
 		mutex_destroy(&mcast->mce_lock);
 	}
 }
+
+static int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf)
+{
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	struct rvu_hwinfo *hw = rvu->hw;
+	int blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (!pfvf->nixlf || blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	*nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
+	if (*nixlf < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	return 0;
+}
+
+int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
+				     struct msg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	int nixlf, err;
+
+	err = nix_get_nixlf(rvu, pcifunc, &nixlf);
+	if (err)
+		return err;
+
+	rvu_npc_enable_default_entries(rvu, pcifunc, nixlf);
+	return 0;
+}
+
+int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
+				    struct msg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	int nixlf, err;
+
+	err = nix_get_nixlf(rvu, pcifunc, &nixlf);
+	if (err)
+		return err;
+
+	rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
+	return 0;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index d749611b23cd..af5135242e67 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -384,7 +384,8 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 			      NIX_INTF_RX, &entry, true);
 }
 
-void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf)
+static void npc_enadis_promisc_entry(struct rvu *rvu, u16 pcifunc,
+				     int nixlf, bool enable)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	int blkaddr, index;
@@ -399,7 +400,17 @@ void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf)
 
 	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
 					 nixlf, NIXLF_PROMISC_ENTRY);
-	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+}
+
+void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	npc_enadis_promisc_entry(rvu, pcifunc, nixlf, false);
+}
+
+void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	npc_enadis_promisc_entry(rvu, pcifunc, nixlf, true);
 }
 
 void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
@@ -512,11 +523,59 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 		    NPC_AF_MCAMEX_BANKX_ACTION(index, bank), *(u64 *)&action);
 }
 
-void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
+static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
+				       int nixlf, bool enable)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct nix_rx_action action;
-	int blkaddr, index, bank;
+	int index, bank, blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return;
+
+	/* Ucast MCAM match entry of this PF/VF */
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					 nixlf, NIXLF_UCAST_ENTRY);
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+
+	/* For PF, ena/dis promisc and bcast MCAM match entries */
+	if (pcifunc & RVU_PFVF_FUNC_MASK)
+		return;
+
+	/* For bcast, enable/disable only if it's action is not
+	 * packet replication, incase if action is replication
+	 * then this PF's nixlf is removed from bcast replication
+	 * list.
+	 */
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					 nixlf, NIXLF_BCAST_ENTRY);
+	bank = npc_get_bank(mcam, index);
+	*(u64 *)&action = rvu_read64(rvu, blkaddr,
+	     NPC_AF_MCAMEX_BANKX_ACTION(index & (mcam->banksize - 1), bank));
+	if (action.op != NIX_RX_ACTIONOP_MCAST)
+		npc_enable_mcam_entry(rvu, mcam,
+				      blkaddr, index, enable);
+	if (enable)
+		rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf);
+	else
+		rvu_npc_disable_promisc_entry(rvu, pcifunc, nixlf);
+}
+
+void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	npc_enadis_default_entries(rvu, pcifunc, nixlf, false);
+}
+
+void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	npc_enadis_default_entries(rvu, pcifunc, nixlf, true);
+}
+
+void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0)
@@ -532,29 +591,7 @@ void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
 
 	mutex_unlock(&mcam->lock);
 
-	/* Disable ucast MCAM match entry of this PF/VF */
-	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
-					 nixlf, NIXLF_UCAST_ENTRY);
-	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
-
-	/* For PF, disable promisc and bcast MCAM match entries */
-	if (!(pcifunc & RVU_PFVF_FUNC_MASK)) {
-		index = npc_get_nixlf_mcam_index(mcam, pcifunc,
-						 nixlf, NIXLF_BCAST_ENTRY);
-		/* For bcast, disable only if it's action is not
-		 * packet replication, incase if action is replication
-		 * then this PF's nixlf is removed from bcast replication
-		 * list.
-		 */
-		bank = npc_get_bank(mcam, index);
-		index &= (mcam->banksize - 1);
-		*(u64 *)&action = rvu_read64(rvu, blkaddr,
-				     NPC_AF_MCAMEX_BANKX_ACTION(index, bank));
-		if (action.op != NIX_RX_ACTIONOP_MCAST)
-			npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
-
-		rvu_npc_disable_promisc_entry(rvu, pcifunc, nixlf);
-	}
+	rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
 }
 
 #define SET_KEX_LD(intf, lid, ltype, ld, cfg)	\
-- 
cgit v1.2.3


From 86cea61d3f38826e885f35084daa376ece308295 Mon Sep 17 00:00:00 2001
From: Tomasz Duszynski <tduszynski@marvell.com>
Date: Mon, 19 Nov 2018 16:17:34 +0530
Subject: octeontx2-af: Add support for stripping STAG/CTAG

This works by shadowing existing UCAST MCAM entry
with a new one additionally matching either NPC_LT_LB_CTAG
or NPC_LT_LB_STAG. For this to fully work one needs to
send properly configured NIX_VTAG_CFG message afterwards i.e with
strip and capture enabled and type set to 0.

On receiving tagged packet NIX will remove outer VLAN and capture
TCI in NIX_RX_PARSE_S.

Also simplified RX Vtag configuration flow
With this setting STRIP/CAPTURE VTAG actions separately would be
possible. Following combinations are possible: STRIP,
STRIP and CAPTURE, CAPTURE or nothing (0 disables respective actions).

Signed-off-by: Tomasz Duszynski <tduszynski@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  6 +-
 drivers/net/ethernet/marvell/octeontx2/af/npc.h    |  6 ++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  8 +++
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 83 +++++++++++++++++-----
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 43 ++++++++++-
 5 files changed, 125 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 39fe62a838ef..3c38e32e1ecd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -197,7 +197,8 @@ M(NIX_SET_MAC_ADDR,	0x800a, nix_set_mac_addr, nix_set_mac_addr, msg_rsp) \
 M(NIX_SET_RX_MODE,	0x800b, nix_set_rx_mode, nix_rx_mode, msg_rsp)	\
 M(NIX_SET_HW_FRS,	0x800c, nix_set_hw_frs, nix_frs_cfg, msg_rsp)	\
 M(NIX_LF_START_RX,	0x800d, nix_lf_start_rx, msg_req, msg_rsp)	\
-M(NIX_LF_STOP_RX,	0x800e, nix_lf_stop_rx, msg_req, msg_rsp)
+M(NIX_LF_STOP_RX,	0x800e, nix_lf_stop_rx, msg_req, msg_rsp)	\
+M(NIX_RXVLAN_ALLOC,	0x8012, nix_rxvlan_alloc, msg_req, msg_rsp)
 
 /* Messages initiated by AF (range 0xC00 - 0xDFF) */
 #define MBOX_UP_CGX_MESSAGES						\
@@ -515,6 +516,7 @@ struct nix_txschq_config {
 
 struct nix_vtag_config {
 	struct mbox_msghdr hdr;
+	/* '0' for 4 octet VTAG, '1' for 8 octet VTAG */
 	u8 vtag_size;
 	/* cfg_type is '0' for tx vlan cfg
 	 * cfg_type is '1' for rx vlan cfg
@@ -535,7 +537,7 @@ struct nix_vtag_config {
 
 		/* valid when cfg_type is '1' */
 		struct {
-			/* rx vtag type index */
+			/* rx vtag type index, valid values are in 0..7 range */
 			u8 vtag_type;
 			/* rx vtag strip */
 			u8 strip_vtag :1;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index f98b0113def3..a7a20afb3ba0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -259,4 +259,10 @@ struct nix_rx_action {
 #endif
 };
 
+/* NIX Receive Vtag Action Structure */
+#define VTAG0_VALID_BIT		BIT_ULL(15)
+#define VTAG0_TYPE_MASK		GENMASK_ULL(14, 12)
+#define VTAG0_LID_MASK		GENMASK_ULL(10, 8)
+#define VTAG0_RELPTR_MASK	GENMASK_ULL(7, 0)
+
 #endif /* NPC_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 19d5f16244f6..9727164dfbfc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -142,6 +142,11 @@ struct rvu_pfvf {
 	/* Broadcast pkt replication info */
 	u16			bcast_mce_idx;
 	struct nix_mce_list	bcast_mce_list;
+
+	/* VLAN offload */
+	struct mcam_entry entry;
+	int rxvlan_index;
+	bool rxvlan;
 };
 
 struct nix_txsch {
@@ -356,6 +361,8 @@ int rvu_mbox_handler_nix_stats_rst(struct rvu *rvu, struct msg_req *req,
 int rvu_mbox_handler_nix_vtag_cfg(struct rvu *rvu,
 				  struct nix_vtag_config *req,
 				  struct msg_rsp *rsp);
+int rvu_mbox_handler_nix_rxvlan_alloc(struct rvu *rvu, struct msg_req *req,
+				      struct msg_rsp *rsp);
 int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
 					 struct nix_rss_flowkey_cfg *req,
 					 struct msg_rsp *rsp);
@@ -384,6 +391,7 @@ void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, u64 chan);
+int rvu_npc_update_rxvlan(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index fb8456eb59af..a8d9fdf41648 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -192,6 +192,7 @@ static void nix_interface_deinit(struct rvu *rvu, u16 pcifunc, u8 nixlf)
 
 	pfvf->maxlen = 0;
 	pfvf->minlen = 0;
+	pfvf->rxvlan = false;
 
 	/* Remove this PF_FUNC from bcast pkt replication list */
 	err = nix_update_bcast_mce_list(rvu, pcifunc, false);
@@ -1209,28 +1210,15 @@ int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 static int nix_rx_vtag_cfg(struct rvu *rvu, int nixlf, int blkaddr,
 			   struct nix_vtag_config *req)
 {
-	u64 regval = 0;
+	u64 regval = req->vtag_size;
 
-#define NIX_VTAGTYPE_MAX 0x8ull
-#define NIX_VTAGSIZE_MASK 0x7ull
-#define NIX_VTAGSTRIP_CAP_MASK 0x30ull
-
-	if (req->rx.vtag_type >= NIX_VTAGTYPE_MAX ||
-	    req->vtag_size > VTAGSIZE_T8)
+	if (req->rx.vtag_type > 7 || req->vtag_size > VTAGSIZE_T8)
 		return -EINVAL;
 
-	regval = rvu_read64(rvu, blkaddr,
-			    NIX_AF_LFX_RX_VTAG_TYPEX(nixlf, req->rx.vtag_type));
-
-	if (req->rx.strip_vtag && req->rx.capture_vtag)
-		regval |= BIT_ULL(4) | BIT_ULL(5);
-	else if (req->rx.strip_vtag)
+	if (req->rx.capture_vtag)
+		regval |= BIT_ULL(5);
+	if (req->rx.strip_vtag)
 		regval |= BIT_ULL(4);
-	else
-		regval &= ~(BIT_ULL(4) | BIT_ULL(5));
-
-	regval &= ~NIX_VTAGSIZE_MASK;
-	regval |= req->vtag_size & NIX_VTAGSIZE_MASK;
 
 	rvu_write64(rvu, blkaddr,
 		    NIX_AF_LFX_RX_VTAG_TYPEX(nixlf, req->rx.vtag_type), regval);
@@ -1770,6 +1758,9 @@ int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu,
 
 	rvu_npc_install_ucast_entry(rvu, pcifunc, nixlf,
 				    pfvf->rx_chan_base, req->mac_addr);
+
+	rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
+
 	return 0;
 }
 
@@ -1803,6 +1794,9 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 	else
 		rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
 					      pfvf->rx_chan_base, allmulti);
+
+	rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
+
 	return 0;
 }
 
@@ -1941,6 +1935,59 @@ linkcfg:
 	return 0;
 }
 
+int rvu_mbox_handler_nix_rxvlan_alloc(struct rvu *rvu, struct msg_req *req,
+				      struct msg_rsp *rsp)
+{
+	struct npc_mcam_alloc_entry_req alloc_req = { };
+	struct npc_mcam_alloc_entry_rsp alloc_rsp = { };
+	struct npc_mcam_free_entry_req free_req = { };
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr, nixlf, err;
+	struct rvu_pfvf *pfvf;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	if (pfvf->rxvlan)
+		return 0;
+
+	/* alloc new mcam entry */
+	alloc_req.hdr.pcifunc = pcifunc;
+	alloc_req.count = 1;
+
+	err = rvu_mbox_handler_npc_mcam_alloc_entry(rvu, &alloc_req,
+						    &alloc_rsp);
+	if (err)
+		return err;
+
+	/* update entry to enable rxvlan offload */
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0) {
+		err = NIX_AF_ERR_AF_LF_INVALID;
+		goto free_entry;
+	}
+
+	nixlf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr], pcifunc, 0);
+	if (nixlf < 0) {
+		err = NIX_AF_ERR_AF_LF_INVALID;
+		goto free_entry;
+	}
+
+	pfvf->rxvlan_index = alloc_rsp.entry_list[0];
+	/* all it means is that rxvlan_index is valid */
+	pfvf->rxvlan = true;
+
+	err = rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
+	if (err)
+		goto free_entry;
+
+	return 0;
+free_entry:
+	free_req.hdr.pcifunc = pcifunc;
+	free_req.entry = alloc_rsp.entry_list[0];
+	rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, rsp);
+	pfvf->rxvlan = false;
+	return err;
+}
+
 static void nix_link_config(struct rvu *rvu, int blkaddr)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index af5135242e67..738314067a9e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -8,6 +8,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/bitfield.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 
@@ -306,6 +307,7 @@ static u64 npc_get_mcam_action(struct rvu *rvu, struct npc_mcam *mcam,
 void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 				 int nixlf, u64 chan, u8 *mac_addr)
 {
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct mcam_entry entry = { {0} };
 	struct nix_rx_action action;
@@ -345,6 +347,17 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 	entry.action = *(u64 *)&action;
 	npc_config_mcam_entry(rvu, mcam, blkaddr, index,
 			      NIX_INTF_RX, &entry, true);
+
+	/* add VLAN matching, setup action and save entry back for later */
+	entry.kw[0] |= (NPC_LT_LB_STAG | NPC_LT_LB_CTAG) << 20;
+	entry.kw_mask[0] |= (NPC_LT_LB_STAG & NPC_LT_LB_CTAG) << 20;
+
+	entry.vtag_action = VTAG0_VALID_BIT |
+			    FIELD_PREP(VTAG0_TYPE_MASK, 0) |
+			    FIELD_PREP(VTAG0_LID_MASK, NPC_LID_LA) |
+			    FIELD_PREP(VTAG0_RELPTR_MASK, 12);
+
+	memcpy(&pfvf->entry, &entry, sizeof(entry));
 }
 
 void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
@@ -352,7 +365,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct mcam_entry entry = { {0} };
-	struct nix_rx_action action;
+	struct nix_rx_action action = { };
 	int blkaddr, index, kwi;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
@@ -521,6 +534,8 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 
 	rvu_write64(rvu, blkaddr,
 		    NPC_AF_MCAMEX_BANKX_ACTION(index, bank), *(u64 *)&action);
+
+	rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
 }
 
 static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
@@ -560,6 +575,8 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
 		rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf);
 	else
 		rvu_npc_disable_promisc_entry(rvu, pcifunc, nixlf);
+
+	rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
 }
 
 void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
@@ -2018,3 +2035,27 @@ int rvu_mbox_handler_npc_get_kex_cfg(struct rvu *rvu, struct msg_req *req,
 	}
 	return 0;
 }
+
+int rvu_npc_update_rxvlan(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr, index;
+	bool enable;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	if (!pfvf->rxvlan)
+		return 0;
+
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf,
+					 NIXLF_UCAST_ENTRY);
+	pfvf->entry.action = npc_get_mcam_action(rvu, mcam, blkaddr, index);
+	enable = is_mcam_entry_enabled(rvu, mcam, blkaddr, index);
+	npc_config_mcam_entry(rvu, mcam, blkaddr, pfvf->rxvlan_index,
+			      NIX_INTF_RX, &pfvf->entry, enable);
+
+	return 0;
+}
-- 
cgit v1.2.3


From f325d3f4cb190a944239072650d842fad6156a9c Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Mon, 19 Nov 2018 16:17:35 +0530
Subject: octeontx2-af: Verify NPA/SSO/NIX PF_FUNC mapping

While mapping a NIX LF to a NPA LF attached PF_FUNC or
SSO LF attached PF_FUNC, verify if PF_FUNC is valid and
if that PF_FUNC has a LF of that block attached to it or not.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  2 ++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c    | 38 ++++++++++++++++++++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  1 +
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 32 +++++++++++-------
 4 files changed, 62 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 3c38e32e1ecd..de31857bab9b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -405,6 +405,8 @@ enum nix_af_status {
 	NIX_AF_INVAL_TXSCHQ_CFG     = -412,
 	NIX_AF_SMQ_FLUSH_FAILED     = -413,
 	NIX_AF_ERR_LF_RESET         = -414,
+	NIX_AF_INVAL_NPA_PF_FUNC    = -419,
+	NIX_AF_INVAL_SSO_PF_FUNC    = -420,
 };
 
 /* For NIX LF context alloc and init */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index e59dfd34e76a..517922fe95b1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -337,6 +337,28 @@ struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc)
 		return &rvu->pf[rvu_get_pf(pcifunc)];
 }
 
+static bool is_pf_func_valid(struct rvu *rvu, u16 pcifunc)
+{
+	int pf, vf, nvfs;
+	u64 cfg;
+
+	pf = rvu_get_pf(pcifunc);
+	if (pf >= rvu->hw->total_pfs)
+		return false;
+
+	if (!(pcifunc & RVU_PFVF_FUNC_MASK))
+		return true;
+
+	/* Check if VF is within number of VFs attached to this PF */
+	vf = (pcifunc & RVU_PFVF_FUNC_MASK) - 1;
+	cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
+	nvfs = (cfg >> 12) & 0xFF;
+	if (vf >= nvfs)
+		return false;
+
+	return true;
+}
+
 bool is_block_implemented(struct rvu_hwinfo *hw, int blkaddr)
 {
 	struct rvu_block *block;
@@ -860,6 +882,22 @@ static u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blktype)
 	return 0;
 }
 
+bool is_pffunc_map_valid(struct rvu *rvu, u16 pcifunc, int blktype)
+{
+	struct rvu_pfvf *pfvf;
+
+	if (!is_pf_func_valid(rvu, pcifunc))
+		return false;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+
+	/* Check if this PFFUNC has a LF of type blktype attached */
+	if (!rvu_get_rsrc_mapcount(pfvf, blktype))
+		return false;
+
+	return true;
+}
+
 static int rvu_lookup_rsrc(struct rvu *rvu, struct rvu_block *block,
 			   int pcifunc, int slot)
 {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 9727164dfbfc..7c96942582b2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -255,6 +255,7 @@ int rvu_get_pf(u16 pcifunc);
 struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc);
 void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf);
 bool is_block_implemented(struct rvu_hwinfo *hw, int blkaddr);
+bool is_pffunc_map_valid(struct rvu *rvu, u16 pcifunc, int blktype);
 int rvu_get_lf(struct rvu *rvu, struct rvu_block *block, u16 pcifunc, u16 slot);
 int rvu_lf_reset(struct rvu *rvu, struct rvu_block *block, int lf);
 int rvu_get_blkaddr(struct rvu *rvu, int blktype, u16 pcifunc);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index a8d9fdf41648..55fd2fd9918a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -694,6 +694,24 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 	if (nixlf < 0)
 		return NIX_AF_ERR_AF_LF_INVALID;
 
+	/* Check if requested 'NIXLF <=> NPALF' mapping is valid */
+	if (req->npa_func) {
+		/* If default, use 'this' NIXLF's PFFUNC */
+		if (req->npa_func == RVU_DEFAULT_PF_FUNC)
+			req->npa_func = pcifunc;
+		if (!is_pffunc_map_valid(rvu, req->npa_func, BLKTYPE_NPA))
+			return NIX_AF_INVAL_NPA_PF_FUNC;
+	}
+
+	/* Check if requested 'NIXLF <=> SSOLF' mapping is valid */
+	if (req->sso_func) {
+		/* If default, use 'this' NIXLF's PFFUNC */
+		if (req->sso_func == RVU_DEFAULT_PF_FUNC)
+			req->sso_func = pcifunc;
+		if (!is_pffunc_map_valid(rvu, req->sso_func, BLKTYPE_SSO))
+			return NIX_AF_INVAL_SSO_PF_FUNC;
+	}
+
 	/* If RSS is being enabled, check if requested config is valid.
 	 * RSS table size should be power of two, otherwise
 	 * RSS_GRP::OFFSET + adder might go beyond that group or
@@ -798,18 +816,10 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 	/* Enable LMTST for this NIX LF */
 	rvu_write64(rvu, blkaddr, NIX_AF_LFX_TX_CFG2(nixlf), BIT_ULL(0));
 
-	/* Set CQE/WQE size, NPA_PF_FUNC for SQBs and also SSO_PF_FUNC
-	 * If requester has sent a 'RVU_DEFAULT_PF_FUNC' use this NIX LF's
-	 * PCIFUNC itself.
-	 */
-	if (req->npa_func == RVU_DEFAULT_PF_FUNC)
-		cfg = pcifunc;
-	else
+	/* Set CQE/WQE size, NPA_PF_FUNC for SQBs and also SSO_PF_FUNC */
+	if (req->npa_func)
 		cfg = req->npa_func;
-
-	if (req->sso_func == RVU_DEFAULT_PF_FUNC)
-		cfg |= (u64)pcifunc << 16;
-	else
+	if (req->sso_func)
 		cfg |= (u64)req->sso_func << 16;
 
 	cfg |= (u64)req->xqe_sz << 33;
-- 
cgit v1.2.3


From 9fe4ebf7176edea8f9761dbad900804f37aa04f9 Mon Sep 17 00:00:00 2001
From: Geetha sowjanya <gakula@marvell.com>
Date: Mon, 19 Nov 2018 16:17:36 +0530
Subject: octeontx2-af: Add FLR interrupt handler

RVU admin function (AF) has all the priviliges to cleanup
HW state when VFIO triggers a PCIe function level reset (FLR)
due to either reset or a VM crash. FLR for RVU PF1-PFn will
trigger an IRQ to AF.

This patch enables all RVU PF's FLR interrupts and registers a
handler. Upon receiving an interrupt, a workqueue is scheduled
to cleanup all hardware blocks being used by the PF which
received the FLR.

Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 117 +++++++++++++++++++++++-
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h |   5 +
 2 files changed, 121 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 517922fe95b1..73ed2654e413 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -1601,6 +1601,44 @@ static void rvu_enable_mbox_intr(struct rvu *rvu)
 		    INTR_MASK(hw->total_pfs) & ~1ULL);
 }
 
+static void rvu_flr_handler(struct work_struct *work)
+{
+	struct rvu_work *flrwork = container_of(work, struct rvu_work, work);
+	struct rvu *rvu = flrwork->rvu;
+	u16 pf;
+
+	pf = flrwork - rvu->flr_wrk;
+
+	/* Signal FLR finish */
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFTRPEND, BIT_ULL(pf));
+
+	/* Enable interrupt */
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1S,  BIT_ULL(pf));
+}
+
+static irqreturn_t rvu_flr_intr_handler(int irq, void *rvu_irq)
+{
+	struct rvu *rvu = (struct rvu *)rvu_irq;
+	u64 intr;
+	u8  pf;
+
+	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT);
+
+	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
+		if (intr & (1ULL << pf)) {
+			/* PF is already dead do only AF related operations */
+			queue_work(rvu->flr_wq, &rvu->flr_wrk[pf].work);
+			/* clear interrupt */
+			rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT,
+				    BIT_ULL(pf));
+			/* Disable the interrupt */
+			rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1C,
+				    BIT_ULL(pf));
+		}
+	}
+	return IRQ_HANDLED;
+}
+
 static void rvu_unregister_interrupts(struct rvu *rvu)
 {
 	int irq;
@@ -1609,6 +1647,10 @@ static void rvu_unregister_interrupts(struct rvu *rvu)
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT_ENA_W1C,
 		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
 
+	/* Disable the PF FLR interrupt */
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1C,
+		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+
 	for (irq = 0; irq < rvu->num_vec; irq++) {
 		if (rvu->irq_allocated[irq])
 			free_irq(pci_irq_vector(rvu->pdev, irq), rvu);
@@ -1660,6 +1702,27 @@ static int rvu_register_interrupts(struct rvu *rvu)
 	/* Enable mailbox interrupts from all PFs */
 	rvu_enable_mbox_intr(rvu);
 
+	/* Register FLR interrupt handler */
+	sprintf(&rvu->irq_name[RVU_AF_INT_VEC_PFFLR * NAME_SIZE],
+		"RVUAF FLR");
+	ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_PFFLR),
+			  rvu_flr_intr_handler, 0,
+			  &rvu->irq_name[RVU_AF_INT_VEC_PFFLR * NAME_SIZE],
+			  rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for FLR\n");
+		goto fail;
+	}
+	rvu->irq_allocated[RVU_AF_INT_VEC_PFFLR] = true;
+
+	/* Enable FLR interrupt for all PFs*/
+	rvu_write64(rvu, BLKADDR_RVUM,
+		    RVU_AF_PFFLR_INT, INTR_MASK(rvu->hw->total_pfs));
+
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1S,
+		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+
 	return 0;
 
 fail:
@@ -1667,6 +1730,51 @@ fail:
 	return ret;
 }
 
+static void rvu_flr_wq_destroy(struct rvu *rvu)
+{
+	if (rvu->flr_wq) {
+		flush_workqueue(rvu->flr_wq);
+		destroy_workqueue(rvu->flr_wq);
+		rvu->flr_wq = NULL;
+	}
+	kfree(rvu->flr_wrk);
+}
+
+static int rvu_flr_init(struct rvu *rvu)
+{
+	u64 cfg;
+	int pf;
+
+	/* Enable FLR for all PFs*/
+	for (pf = 1; pf < rvu->hw->total_pfs; pf++) {
+		cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
+		rvu_write64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf),
+			    cfg | BIT_ULL(22));
+	}
+
+	rvu->flr_wq = alloc_workqueue("rvu_afpf_flr",
+				      WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM,
+				       1);
+	if (!rvu->flr_wq)
+		return -ENOMEM;
+
+	rvu->flr_wrk = devm_kcalloc(rvu->dev, rvu->hw->total_pfs,
+				    sizeof(struct rvu_work), GFP_KERNEL);
+	if (!rvu->flr_wrk) {
+		destroy_workqueue(rvu->flr_wq);
+		return -ENOMEM;
+	}
+
+	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
+		rvu->flr_wrk[pf].rvu = rvu;
+		INIT_WORK(&rvu->flr_wrk[pf].work, rvu_flr_handler);
+	}
+
+	mutex_init(&rvu->flr_lock);
+
+	return 0;
+}
+
 static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct device *dev = &pdev->dev;
@@ -1737,11 +1845,17 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_mbox;
 
-	err = rvu_register_interrupts(rvu);
+	err = rvu_flr_init(rvu);
 	if (err)
 		goto err_cgx;
 
+	err = rvu_register_interrupts(rvu);
+	if (err)
+		goto err_flr;
+
 	return 0;
+err_flr:
+	rvu_flr_wq_destroy(rvu);
 err_cgx:
 	rvu_cgx_wq_destroy(rvu);
 err_mbox:
@@ -1765,6 +1879,7 @@ static void rvu_remove(struct pci_dev *pdev)
 	struct rvu *rvu = pci_get_drvdata(pdev);
 
 	rvu_unregister_interrupts(rvu);
+	rvu_flr_wq_destroy(rvu);
 	rvu_cgx_wq_destroy(rvu);
 	rvu_mbox_destroy(rvu);
 	rvu_reset_all_blocks(rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 7c96942582b2..335ba1d83c50 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -200,6 +200,11 @@ struct rvu {
 	struct rvu_work		*mbox_wrk_up;
 	struct workqueue_struct *mbox_wq;
 
+	/* PF FLR */
+	struct rvu_work		*flr_wrk;
+	struct workqueue_struct *flr_wq;
+	struct mutex		flr_lock; /* Serialize FLRs */
+
 	/* MSI-X */
 	u16			num_vec;
 	char			*irq_name;
-- 
cgit v1.2.3


From c554f9c1574e022821260b24b043a4277e8ec5d8 Mon Sep 17 00:00:00 2001
From: Geetha sowjanya <gakula@marvell.com>
Date: Mon, 19 Nov 2018 16:17:37 +0530
Subject: octeontx2-af: Teardown NPA, NIX LF upon receiving FLR

Upon receiving FLR IRQ for a RVU PF, teardown or cleanup
resources held by that PF_FUNC. This patch cleans up,
NIX LF
 - Stop ingress/egress traffic
 - Disable NPC MCAM entries being used.
 - Free Tx scheduler queues
 - Disable RQ/SQ/CQ HW contexts
NPA LF
 - Disable Pool/Aura HW contexts
In future teardown of SSO/SSOW/TIM/CPT will be added.

Also added a mailbox message for a RVU PF to request
AF, to perform FLR for a RVU VF under it.

Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: Stanislaw Kardach <skardach@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  8 +++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c    | 82 +++++++++++++++++++++-
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  2 +
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 48 +++++++++++++
 .../net/ethernet/marvell/octeontx2/af/rvu_npa.c    | 17 +++++
 5 files changed, 156 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index de31857bab9b..292c13a901df 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -124,6 +124,7 @@ M(READY,		0x001, ready, msg_req, ready_msg_rsp)		\
 M(ATTACH_RESOURCES,	0x002, attach_resources, rsrc_attach, msg_rsp)	\
 M(DETACH_RESOURCES,	0x003, detach_resources, rsrc_detach, msg_rsp)	\
 M(MSIX_OFFSET,		0x004, msix_offset, msg_req, msix_offset_rsp)	\
+M(VF_FLR,		0x006, vf_flr, msg_req, msg_rsp)		\
 /* CGX mbox IDs (range 0x200 - 0x3FF) */				\
 M(CGX_START_RXTX,	0x200, cgx_start_rxtx, msg_req, msg_rsp)	\
 M(CGX_STOP_RXTX,	0x201, cgx_stop_rxtx, msg_req, msg_rsp)		\
@@ -229,6 +230,13 @@ struct msg_rsp {
 	struct mbox_msghdr hdr;
 };
 
+/* RVU mailbox error codes
+ * Range 256 - 300.
+ */
+enum rvu_af_status {
+	RVU_INVALID_VF_ID           = -256,
+};
+
 struct ready_msg_rsp {
 	struct mbox_msghdr hdr;
 	u16    sclk_feq;	/* SCLK frequency */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 73ed2654e413..eb1b69f27dd5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -29,6 +29,7 @@ static void rvu_set_msix_offset(struct rvu *rvu, struct rvu_pfvf *pfvf,
 				struct rvu_block *block, int lf);
 static void rvu_clear_msix_offset(struct rvu *rvu, struct rvu_pfvf *pfvf,
 				  struct rvu_block *block, int lf);
+static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc);
 
 /* Supported devices */
 static const struct pci_device_id rvu_id_table[] = {
@@ -1320,6 +1321,26 @@ static int rvu_mbox_handler_msix_offset(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
+static int rvu_mbox_handler_vf_flr(struct rvu *rvu, struct msg_req *req,
+				   struct msg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	u16 vf, numvfs;
+	u64 cfg;
+
+	vf = pcifunc & RVU_PFVF_FUNC_MASK;
+	cfg = rvu_read64(rvu, BLKADDR_RVUM,
+			 RVU_PRIV_PFX_CFG(rvu_get_pf(pcifunc)));
+	numvfs = (cfg >> 12) & 0xFF;
+
+	if (vf && vf <= numvfs)
+		__rvu_flr_handler(rvu, pcifunc);
+	else
+		return RVU_INVALID_VF_ID;
+
+	return 0;
+}
+
 static int rvu_process_mbox_msg(struct rvu *rvu, int devid,
 				struct mbox_msghdr *req)
 {
@@ -1601,14 +1622,73 @@ static void rvu_enable_mbox_intr(struct rvu *rvu)
 		    INTR_MASK(hw->total_pfs) & ~1ULL);
 }
 
+static void rvu_blklf_teardown(struct rvu *rvu, u16 pcifunc, u8 blkaddr)
+{
+	struct rvu_block *block;
+	int slot, lf, num_lfs;
+	int err;
+
+	block = &rvu->hw->block[blkaddr];
+	num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, pcifunc),
+					block->type);
+	if (!num_lfs)
+		return;
+	for (slot = 0; slot < num_lfs; slot++) {
+		lf = rvu_get_lf(rvu, block, pcifunc, slot);
+		if (lf < 0)
+			continue;
+
+		/* Cleanup LF and reset it */
+		if (block->addr == BLKADDR_NIX0)
+			rvu_nix_lf_teardown(rvu, pcifunc, block->addr, lf);
+		else if (block->addr == BLKADDR_NPA)
+			rvu_npa_lf_teardown(rvu, pcifunc, lf);
+
+		err = rvu_lf_reset(rvu, block, lf);
+		if (err) {
+			dev_err(rvu->dev, "Failed to reset blkaddr %d LF%d\n",
+				block->addr, lf);
+		}
+	}
+}
+
+static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc)
+{
+	mutex_lock(&rvu->flr_lock);
+	/* Reset order should reflect inter-block dependencies:
+	 * 1. Reset any packet/work sources (NIX, CPT, TIM)
+	 * 2. Flush and reset SSO/SSOW
+	 * 3. Cleanup pools (NPA)
+	 */
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NIX0);
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_CPT0);
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_TIM);
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSOW);
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSO);
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NPA);
+	rvu_detach_rsrcs(rvu, NULL, pcifunc);
+	mutex_unlock(&rvu->flr_lock);
+}
+
 static void rvu_flr_handler(struct work_struct *work)
 {
 	struct rvu_work *flrwork = container_of(work, struct rvu_work, work);
 	struct rvu *rvu = flrwork->rvu;
-	u16 pf;
+	u16 pcifunc, numvfs, vf;
+	u64 cfg;
+	int pf;
 
 	pf = flrwork - rvu->flr_wrk;
 
+	cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
+	numvfs = (cfg >> 12) & 0xFF;
+	pcifunc  = pf << RVU_PFVF_PF_SHIFT;
+
+	for (vf = 0; vf < numvfs; vf++)
+		__rvu_flr_handler(rvu, (pcifunc | (vf + 1)));
+
+	__rvu_flr_handler(rvu, pcifunc);
+
 	/* Signal FLR finish */
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFTRPEND, BIT_ULL(pf));
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 335ba1d83c50..5d986e1f6beb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -325,6 +325,7 @@ int rvu_mbox_handler_cgx_intlbk_disable(struct rvu *rvu, struct msg_req *req,
 /* NPA APIs */
 int rvu_npa_init(struct rvu *rvu);
 void rvu_npa_freemem(struct rvu *rvu);
+void rvu_npa_lf_teardown(struct rvu *rvu, u16 pcifunc, int npalf);
 int rvu_mbox_handler_npa_aq_enq(struct rvu *rvu,
 				struct npa_aq_enq_req *req,
 				struct npa_aq_enq_rsp *rsp);
@@ -342,6 +343,7 @@ bool is_nixlf_attached(struct rvu *rvu, u16 pcifunc);
 int rvu_nix_init(struct rvu *rvu);
 void rvu_nix_freemem(struct rvu *rvu);
 int rvu_get_nixlf_count(struct rvu *rvu);
+void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf);
 int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 				  struct nix_lf_alloc_req *req,
 				  struct nix_lf_alloc_rsp *rsp);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 55fd2fd9918a..58c672014152 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -105,6 +105,17 @@ static inline struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr)
 	return NULL;
 }
 
+static void nix_rx_sync(struct rvu *rvu, int blkaddr)
+{
+	int err;
+
+	/*Sync all in flight RX packets to LLC/DRAM */
+	rvu_write64(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0));
+	err = rvu_poll_reg(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0), true);
+	if (err)
+		dev_err(rvu->dev, "NIX RX software sync failed\n");
+}
+
 static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
 			    int lvl, u16 pcifunc, u16 schq)
 {
@@ -2281,3 +2292,40 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
 	rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
 	return 0;
 }
+
+void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf)
+{
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	struct hwctx_disable_req ctx_req;
+	int err;
+
+	ctx_req.hdr.pcifunc = pcifunc;
+
+	/* Cleanup NPC MCAM entries, free Tx scheduler queues being used */
+	nix_interface_deinit(rvu, pcifunc, nixlf);
+	nix_rx_sync(rvu, blkaddr);
+	nix_txschq_free(rvu, pcifunc);
+
+	if (pfvf->sq_ctx) {
+		ctx_req.ctype = NIX_AQ_CTYPE_SQ;
+		err = nix_lf_hwctx_disable(rvu, &ctx_req);
+		if (err)
+			dev_err(rvu->dev, "SQ ctx disable failed\n");
+	}
+
+	if (pfvf->rq_ctx) {
+		ctx_req.ctype = NIX_AQ_CTYPE_RQ;
+		err = nix_lf_hwctx_disable(rvu, &ctx_req);
+		if (err)
+			dev_err(rvu->dev, "RQ ctx disable failed\n");
+	}
+
+	if (pfvf->cq_ctx) {
+		ctx_req.ctype = NIX_AQ_CTYPE_CQ;
+		err = nix_lf_hwctx_disable(rvu, &ctx_req);
+		if (err)
+			dev_err(rvu->dev, "CQ ctx disable failed\n");
+	}
+
+	nix_ctx_free(rvu, pfvf);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
index 77b8c2e00d86..c0e165dfc403 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
@@ -470,3 +470,20 @@ void rvu_npa_freemem(struct rvu *rvu)
 	block = &hw->block[blkaddr];
 	rvu_aq_free(rvu, block->aq);
 }
+
+void rvu_npa_lf_teardown(struct rvu *rvu, u16 pcifunc, int npalf)
+{
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	struct hwctx_disable_req ctx_req;
+
+	/* Disable all pools */
+	ctx_req.hdr.pcifunc = pcifunc;
+	ctx_req.ctype = NPA_AQ_CTYPE_POOL;
+	npa_lf_hwctx_disable(rvu, &ctx_req);
+
+	/* Disable all auras */
+	ctx_req.ctype = NPA_AQ_CTYPE_AURA;
+	npa_lf_hwctx_disable(rvu, &ctx_req);
+
+	npa_ctx_free(rvu, pfvf);
+}
-- 
cgit v1.2.3


From 9bdc47a6e3288b65947af841bb5b76998d097b18 Mon Sep 17 00:00:00 2001
From: Tomasz Duszynski <tduszynski@marvell.com>
Date: Mon, 19 Nov 2018 16:17:38 +0530
Subject: octeontx2-af: Mbox communication support btw AF and it's VFs

VFs attached to PFs other than AF can not communicate with AF
directly. Instead they are supposed to first send message to
the PF they are residing on and PF forwards it to the AF.
Responses to messages are handled in the reverse order.

On the other hand if VFs are on AF (PF0) itself then direct mailbox
communication is possible since there's no other PF in the way.

This patch addresses this particular case and adds support for
handling it.

Signed-off-by: Tomasz Duszynski <tduszynski@marvell.com>
Signed-off-by: Marko Kallio <mkallio@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c    | 295 +++++++++++++++------
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  17 +-
 .../net/ethernet/marvell/octeontx2/af/rvu_cgx.c    |   6 +-
 3 files changed, 223 insertions(+), 95 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index eb1b69f27dd5..1e6c8bc4036c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -31,6 +31,15 @@ static void rvu_clear_msix_offset(struct rvu *rvu, struct rvu_pfvf *pfvf,
 				  struct rvu_block *block, int lf);
 static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc);
 
+static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
+			 int type, int num,
+			 void (mbox_handler)(struct work_struct *),
+			 void (mbox_up_handler)(struct work_struct *));
+enum {
+	TYPE_AFVF,
+	TYPE_AFPF,
+};
+
 /* Supported devices */
 static const struct pci_device_id rvu_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_RVU_AF) },
@@ -1341,9 +1350,11 @@ static int rvu_mbox_handler_vf_flr(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
-static int rvu_process_mbox_msg(struct rvu *rvu, int devid,
+static int rvu_process_mbox_msg(struct otx2_mbox *mbox, int devid,
 				struct mbox_msghdr *req)
 {
+	struct rvu *rvu = pci_get_drvdata(mbox->pdev);
+
 	/* Check if valid, if not reply with a invalid msg */
 	if (req->sig != OTX2_MBOX_REQ_SIG)
 		goto bad_message;
@@ -1355,8 +1366,15 @@ static int rvu_process_mbox_msg(struct rvu *rvu, int devid,
 		int err;						\
 									\
 		rsp = (struct _rsp_type *)otx2_mbox_alloc_msg(		\
-			&rvu->mbox, devid,				\
+			mbox, devid,					\
 			sizeof(struct _rsp_type));			\
+		/* some handlers should complete even if reply */	\
+		/* could not be allocated */				\
+		if (!rsp &&						\
+		    _id != MBOX_MSG_DETACH_RESOURCES &&			\
+		    _id != MBOX_MSG_NIX_TXSCH_FREE &&			\
+		    _id != MBOX_MSG_VF_FLR)				\
+			return -ENOMEM;					\
 		if (rsp) {						\
 			rsp->hdr.id = _id;				\
 			rsp->hdr.sig = OTX2_MBOX_RSP_SIG;		\
@@ -1374,29 +1392,38 @@ static int rvu_process_mbox_msg(struct rvu *rvu, int devid,
 	}
 MBOX_MESSAGES
 #undef M
-		break;
+
 bad_message:
 	default:
-		otx2_reply_invalid_msg(&rvu->mbox, devid, req->pcifunc,
-				       req->id);
+		otx2_reply_invalid_msg(mbox, devid, req->pcifunc, req->id);
 		return -ENODEV;
 	}
 }
 
-static void rvu_mbox_handler(struct work_struct *work)
+static void __rvu_mbox_handler(struct rvu_work *mwork, int type)
 {
-	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
 	struct rvu *rvu = mwork->rvu;
+	int offset, err, id, devid;
 	struct otx2_mbox_dev *mdev;
 	struct mbox_hdr *req_hdr;
 	struct mbox_msghdr *msg;
+	struct mbox_wq_info *mw;
 	struct otx2_mbox *mbox;
-	int offset, id, err;
-	u16 pf;
 
-	mbox = &rvu->mbox;
-	pf = mwork - rvu->mbox_wrk;
-	mdev = &mbox->dev[pf];
+	switch (type) {
+	case TYPE_AFPF:
+		mw = &rvu->afpf_wq_info;
+		break;
+	case TYPE_AFVF:
+		mw = &rvu->afvf_wq_info;
+		break;
+	default:
+		return;
+	}
+
+	devid = mwork - mw->mbox_wrk;
+	mbox = &mw->mbox;
+	mdev = &mbox->dev[devid];
 
 	/* Process received mbox messages */
 	req_hdr = mdev->mbase + mbox->rx_start;
@@ -1408,10 +1435,21 @@ static void rvu_mbox_handler(struct work_struct *work)
 	for (id = 0; id < req_hdr->num_msgs; id++) {
 		msg = mdev->mbase + offset;
 
-		/* Set which PF sent this message based on mbox IRQ */
-		msg->pcifunc &= ~(RVU_PFVF_PF_MASK << RVU_PFVF_PF_SHIFT);
-		msg->pcifunc |= (pf << RVU_PFVF_PF_SHIFT);
-		err = rvu_process_mbox_msg(rvu, pf, msg);
+		/* Set which PF/VF sent this message based on mbox IRQ */
+		switch (type) {
+		case TYPE_AFPF:
+			msg->pcifunc &=
+				~(RVU_PFVF_PF_MASK << RVU_PFVF_PF_SHIFT);
+			msg->pcifunc |= (devid << RVU_PFVF_PF_SHIFT);
+			break;
+		case TYPE_AFVF:
+			msg->pcifunc &=
+				~(RVU_PFVF_FUNC_MASK << RVU_PFVF_FUNC_SHIFT);
+			msg->pcifunc |= (devid << RVU_PFVF_FUNC_SHIFT) + 1;
+			break;
+		}
+
+		err = rvu_process_mbox_msg(mbox, devid, msg);
 		if (!err) {
 			offset = mbox->rx_start + msg->next_msgoff;
 			continue;
@@ -1419,31 +1457,57 @@ static void rvu_mbox_handler(struct work_struct *work)
 
 		if (msg->pcifunc & RVU_PFVF_FUNC_MASK)
 			dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d:VF%d\n",
-				 err, otx2_mbox_id2name(msg->id), msg->id, pf,
+				 err, otx2_mbox_id2name(msg->id),
+				 msg->id, devid,
 				 (msg->pcifunc & RVU_PFVF_FUNC_MASK) - 1);
 		else
 			dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d\n",
-				 err, otx2_mbox_id2name(msg->id), msg->id, pf);
+				 err, otx2_mbox_id2name(msg->id),
+				 msg->id, devid);
 	}
 
-	/* Send mbox responses to PF */
-	otx2_mbox_msg_send(mbox, pf);
+	/* Send mbox responses to VF/PF */
+	otx2_mbox_msg_send(mbox, devid);
 }
 
-static void rvu_mbox_up_handler(struct work_struct *work)
+static inline void rvu_afpf_mbox_handler(struct work_struct *work)
 {
 	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
+
+	__rvu_mbox_handler(mwork, TYPE_AFPF);
+}
+
+static inline void rvu_afvf_mbox_handler(struct work_struct *work)
+{
+	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
+
+	__rvu_mbox_handler(mwork, TYPE_AFVF);
+}
+
+static void __rvu_mbox_up_handler(struct rvu_work *mwork, int type)
+{
 	struct rvu *rvu = mwork->rvu;
 	struct otx2_mbox_dev *mdev;
 	struct mbox_hdr *rsp_hdr;
 	struct mbox_msghdr *msg;
+	struct mbox_wq_info *mw;
 	struct otx2_mbox *mbox;
-	int offset, id;
-	u16 pf;
+	int offset, id, devid;
+
+	switch (type) {
+	case TYPE_AFPF:
+		mw = &rvu->afpf_wq_info;
+		break;
+	case TYPE_AFVF:
+		mw = &rvu->afvf_wq_info;
+		break;
+	default:
+		return;
+	}
 
-	mbox = &rvu->mbox_up;
-	pf = mwork - rvu->mbox_wrk_up;
-	mdev = &mbox->dev[pf];
+	devid = mwork - mw->mbox_wrk_up;
+	mbox = &mw->mbox_up;
+	mdev = &mbox->dev[devid];
 
 	rsp_hdr = mdev->mbase + mbox->rx_start;
 	if (rsp_hdr->num_msgs == 0) {
@@ -1484,128 +1548,182 @@ end:
 		mdev->msgs_acked++;
 	}
 
-	otx2_mbox_reset(mbox, 0);
+	otx2_mbox_reset(mbox, devid);
 }
 
-static int rvu_mbox_init(struct rvu *rvu)
+static inline void rvu_afpf_mbox_up_handler(struct work_struct *work)
 {
-	struct rvu_hwinfo *hw = rvu->hw;
-	void __iomem *hwbase = NULL;
+	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
+
+	__rvu_mbox_up_handler(mwork, TYPE_AFPF);
+}
+
+static inline void rvu_afvf_mbox_up_handler(struct work_struct *work)
+{
+	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
+
+	__rvu_mbox_up_handler(mwork, TYPE_AFVF);
+}
+
+static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
+			 int type, int num,
+			 void (mbox_handler)(struct work_struct *),
+			 void (mbox_up_handler)(struct work_struct *))
+{
+	void __iomem *hwbase = NULL, *reg_base;
+	int err, i, dir, dir_up;
 	struct rvu_work *mwork;
+	const char *name;
 	u64 bar4_addr;
-	int err, pf;
 
-	rvu->mbox_wq = alloc_workqueue("rvu_afpf_mailbox",
-				       WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM,
-				       hw->total_pfs);
-	if (!rvu->mbox_wq)
+	switch (type) {
+	case TYPE_AFPF:
+		name = "rvu_afpf_mailbox";
+		bar4_addr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PF_BAR4_ADDR);
+		dir = MBOX_DIR_AFPF;
+		dir_up = MBOX_DIR_AFPF_UP;
+		reg_base = rvu->afreg_base;
+		break;
+	case TYPE_AFVF:
+		name = "rvu_afvf_mailbox";
+		bar4_addr = rvupf_read64(rvu, RVU_PF_VF_BAR4_ADDR);
+		dir = MBOX_DIR_PFVF;
+		dir_up = MBOX_DIR_PFVF_UP;
+		reg_base = rvu->pfreg_base;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	mw->mbox_wq = alloc_workqueue(name,
+				      WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM,
+				      num);
+	if (!mw->mbox_wq)
 		return -ENOMEM;
 
-	rvu->mbox_wrk = devm_kcalloc(rvu->dev, hw->total_pfs,
-				     sizeof(struct rvu_work), GFP_KERNEL);
-	if (!rvu->mbox_wrk) {
+	mw->mbox_wrk = devm_kcalloc(rvu->dev, num,
+				    sizeof(struct rvu_work), GFP_KERNEL);
+	if (!mw->mbox_wrk) {
 		err = -ENOMEM;
 		goto exit;
 	}
 
-	rvu->mbox_wrk_up = devm_kcalloc(rvu->dev, hw->total_pfs,
-					sizeof(struct rvu_work), GFP_KERNEL);
-	if (!rvu->mbox_wrk_up) {
+	mw->mbox_wrk_up = devm_kcalloc(rvu->dev, num,
+				       sizeof(struct rvu_work), GFP_KERNEL);
+	if (!mw->mbox_wrk_up) {
 		err = -ENOMEM;
 		goto exit;
 	}
 
-	/* Map mbox region shared with PFs */
-	bar4_addr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PF_BAR4_ADDR);
 	/* Mailbox is a reserved memory (in RAM) region shared between
 	 * RVU devices, shouldn't be mapped as device memory to allow
 	 * unaligned accesses.
 	 */
-	hwbase = ioremap_wc(bar4_addr, MBOX_SIZE * hw->total_pfs);
+	hwbase = ioremap_wc(bar4_addr, MBOX_SIZE * num);
 	if (!hwbase) {
 		dev_err(rvu->dev, "Unable to map mailbox region\n");
 		err = -ENOMEM;
 		goto exit;
 	}
 
-	err = otx2_mbox_init(&rvu->mbox, hwbase, rvu->pdev, rvu->afreg_base,
-			     MBOX_DIR_AFPF, hw->total_pfs);
+	err = otx2_mbox_init(&mw->mbox, hwbase, rvu->pdev, reg_base, dir, num);
 	if (err)
 		goto exit;
 
-	err = otx2_mbox_init(&rvu->mbox_up, hwbase, rvu->pdev, rvu->afreg_base,
-			     MBOX_DIR_AFPF_UP, hw->total_pfs);
+	err = otx2_mbox_init(&mw->mbox_up, hwbase, rvu->pdev,
+			     reg_base, dir_up, num);
 	if (err)
 		goto exit;
 
-	for (pf = 0; pf < hw->total_pfs; pf++) {
-		mwork = &rvu->mbox_wrk[pf];
+	for (i = 0; i < num; i++) {
+		mwork = &mw->mbox_wrk[i];
 		mwork->rvu = rvu;
-		INIT_WORK(&mwork->work, rvu_mbox_handler);
-	}
+		INIT_WORK(&mwork->work, mbox_handler);
 
-	for (pf = 0; pf < hw->total_pfs; pf++) {
-		mwork = &rvu->mbox_wrk_up[pf];
+		mwork = &mw->mbox_wrk_up[i];
 		mwork->rvu = rvu;
-		INIT_WORK(&mwork->work, rvu_mbox_up_handler);
+		INIT_WORK(&mwork->work, mbox_up_handler);
 	}
 
 	return 0;
 exit:
 	if (hwbase)
 		iounmap((void __iomem *)hwbase);
-	destroy_workqueue(rvu->mbox_wq);
+	destroy_workqueue(mw->mbox_wq);
 	return err;
 }
 
-static void rvu_mbox_destroy(struct rvu *rvu)
+static void rvu_mbox_destroy(struct mbox_wq_info *mw)
 {
-	if (rvu->mbox_wq) {
-		flush_workqueue(rvu->mbox_wq);
-		destroy_workqueue(rvu->mbox_wq);
-		rvu->mbox_wq = NULL;
+	if (mw->mbox_wq) {
+		flush_workqueue(mw->mbox_wq);
+		destroy_workqueue(mw->mbox_wq);
+		mw->mbox_wq = NULL;
 	}
 
-	if (rvu->mbox.hwbase)
-		iounmap((void __iomem *)rvu->mbox.hwbase);
+	if (mw->mbox.hwbase)
+		iounmap((void __iomem *)mw->mbox.hwbase);
 
-	otx2_mbox_destroy(&rvu->mbox);
-	otx2_mbox_destroy(&rvu->mbox_up);
+	otx2_mbox_destroy(&mw->mbox);
+	otx2_mbox_destroy(&mw->mbox_up);
 }
 
-static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
+static void rvu_queue_work(struct mbox_wq_info *mw, int first,
+			   int mdevs, u64 intr)
 {
-	struct rvu *rvu = (struct rvu *)rvu_irq;
 	struct otx2_mbox_dev *mdev;
 	struct otx2_mbox *mbox;
 	struct mbox_hdr *hdr;
+	int i;
+
+	for (i = first; i < mdevs; i++) {
+		/* start from 0 */
+		if (!(intr & BIT_ULL(i - first)))
+			continue;
+
+		mbox = &mw->mbox;
+		mdev = &mbox->dev[i];
+		hdr = mdev->mbase + mbox->rx_start;
+		if (hdr->num_msgs)
+			queue_work(mw->mbox_wq, &mw->mbox_wrk[i].work);
+
+		mbox = &mw->mbox_up;
+		mdev = &mbox->dev[i];
+		hdr = mdev->mbase + mbox->rx_start;
+		if (hdr->num_msgs)
+			queue_work(mw->mbox_wq, &mw->mbox_wrk_up[i].work);
+	}
+}
+
+static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
+{
+	struct rvu *rvu = (struct rvu *)rvu_irq;
+	int vfs = pci_num_vf(rvu->pdev);
 	u64 intr;
-	u8  pf;
 
 	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT);
 	/* Clear interrupts */
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT, intr);
 
 	/* Sync with mbox memory region */
-	smp_wmb();
+	rmb();
 
-	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
-		if (intr & (1ULL << pf)) {
-			mbox = &rvu->mbox;
-			mdev = &mbox->dev[pf];
-			hdr = mdev->mbase + mbox->rx_start;
-			if (hdr->num_msgs)
-				queue_work(rvu->mbox_wq,
-					   &rvu->mbox_wrk[pf].work);
-			mbox = &rvu->mbox_up;
-			mdev = &mbox->dev[pf];
-			hdr = mdev->mbase + mbox->rx_start;
-			if (hdr->num_msgs)
-				queue_work(rvu->mbox_wq,
-					   &rvu->mbox_wrk_up[pf].work);
-		}
+	rvu_queue_work(&rvu->afpf_wq_info, 0, rvu->hw->total_pfs, intr);
+
+	/* Handle VF interrupts */
+	if (vfs > 64) {
+		intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(1));
+		rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(1), intr);
+
+		rvu_queue_work(&rvu->afvf_wq_info, 64, vfs, intr);
+		vfs -= 64;
 	}
 
+	intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(0));
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(0), intr);
+
+	rvu_queue_work(&rvu->afvf_wq_info, 0, vfs, intr);
+
 	return IRQ_HANDLED;
 }
 
@@ -1917,7 +2035,10 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_release_regions;
 
-	err = rvu_mbox_init(rvu);
+	/* Init mailbox btw AF and PFs */
+	err = rvu_mbox_init(rvu, &rvu->afpf_wq_info, TYPE_AFPF,
+			    rvu->hw->total_pfs, rvu_afpf_mbox_handler,
+			    rvu_afpf_mbox_up_handler);
 	if (err)
 		goto err_hwsetup;
 
@@ -1939,7 +2060,7 @@ err_flr:
 err_cgx:
 	rvu_cgx_wq_destroy(rvu);
 err_mbox:
-	rvu_mbox_destroy(rvu);
+	rvu_mbox_destroy(&rvu->afpf_wq_info);
 err_hwsetup:
 	rvu_reset_all_blocks(rvu);
 	rvu_free_hw_resources(rvu);
@@ -1961,7 +2082,7 @@ static void rvu_remove(struct pci_dev *pdev)
 	rvu_unregister_interrupts(rvu);
 	rvu_flr_wq_destroy(rvu);
 	rvu_cgx_wq_destroy(rvu);
-	rvu_mbox_destroy(rvu);
+	rvu_mbox_destroy(&rvu->afpf_wq_info);
 	rvu_reset_all_blocks(rvu);
 	rvu_free_hw_resources(rvu);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 5d986e1f6beb..87c29fc7ea5e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -183,6 +183,16 @@ struct rvu_hwinfo {
 	struct npc_mcam  mcam;
 };
 
+struct mbox_wq_info {
+	struct otx2_mbox mbox;
+	struct rvu_work *mbox_wrk;
+
+	struct otx2_mbox mbox_up;
+	struct rvu_work *mbox_wrk_up;
+
+	struct workqueue_struct *mbox_wq;
+};
+
 struct rvu {
 	void __iomem		*afreg_base;
 	void __iomem		*pfreg_base;
@@ -194,11 +204,8 @@ struct rvu {
 	struct mutex            rsrc_lock; /* Serialize resource alloc/free */
 
 	/* Mbox */
-	struct otx2_mbox	mbox;
-	struct rvu_work		*mbox_wrk;
-	struct otx2_mbox        mbox_up;
-	struct rvu_work		*mbox_wrk_up;
-	struct workqueue_struct *mbox_wq;
+	struct mbox_wq_info	afpf_wq_info;
+	struct mbox_wq_info	afvf_wq_info;
 
 	/* PF FLR */
 	struct rvu_work		*flr_wrk;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 52d776dfcbe8..1de6eb528d08 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -27,7 +27,7 @@ static struct _req_type __maybe_unused					\
 	struct _req_type *req;						\
 									\
 	req = (struct _req_type *)otx2_mbox_alloc_msg_rsp(		\
-		&rvu->mbox_up, devid, sizeof(struct _req_type),		\
+		&rvu->afpf_wq_info.mbox_up, devid, sizeof(struct _req_type), \
 		sizeof(struct _rsp_type));				\
 	if (!req)							\
 		return NULL;						\
@@ -181,8 +181,8 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu)
 		if (!msg)
 			continue;
 		msg->link_info = *linfo;
-		otx2_mbox_msg_send(&rvu->mbox_up, pfid);
-		err = otx2_mbox_wait_for_rsp(&rvu->mbox_up, pfid);
+		otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, pfid);
+		err = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pfid);
 		if (err)
 			dev_warn(rvu->dev, "notification to pf %d failed\n",
 				 pfid);
-- 
cgit v1.2.3


From 9bd6caf33567f2326ac66a7030df11fb32a3fbea Mon Sep 17 00:00:00 2001
From: Tomasz Duszynski <tduszynski@marvell.com>
Date: Mon, 19 Nov 2018 16:17:39 +0530
Subject: octeontx2-af: Enable sriov on AF to create VFs

Enable all AF VFs during probe. Since AF's VFs work in pairs
(eg: Pkts sent on VF0 are received by VF1 and viceversa),
enable only even number of VFs out of totalVFs, which should
again be less than number of loopback (LBK) channels.

Also enable VF's mailbox interrupts.

Signed-off-by: Tomasz Duszynski <tduszynski@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 185 +++++++++++++++++++++++-
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h |   3 +-
 2 files changed, 185 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 1e6c8bc4036c..34e87e66c259 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -1698,7 +1698,7 @@ static void rvu_queue_work(struct mbox_wq_info *mw, int first,
 static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
 {
 	struct rvu *rvu = (struct rvu *)rvu_irq;
-	int vfs = pci_num_vf(rvu->pdev);
+	int vfs = rvu->vfs;
 	u64 intr;
 
 	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT);
@@ -1858,9 +1858,25 @@ static void rvu_unregister_interrupts(struct rvu *rvu)
 	rvu->num_vec = 0;
 }
 
+static int rvu_afvf_msix_vectors_num_ok(struct rvu *rvu)
+{
+	struct rvu_pfvf *pfvf = &rvu->pf[0];
+	int offset;
+
+	pfvf = &rvu->pf[0];
+	offset = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_INT_CFG(0)) & 0x3ff;
+
+	/* Make sure there are enough MSIX vectors configured so that
+	 * VF interrupts can be handled. Offset equal to zero means
+	 * that PF vectors are not configured and overlapping AF vectors.
+	 */
+	return (pfvf->msix.max >= RVU_AF_INT_VEC_CNT + RVU_PF_INT_VEC_CNT) &&
+	       offset;
+}
+
 static int rvu_register_interrupts(struct rvu *rvu)
 {
-	int ret;
+	int ret, offset;
 
 	rvu->num_vec = pci_msix_vec_count(rvu->pdev);
 
@@ -1921,6 +1937,40 @@ static int rvu_register_interrupts(struct rvu *rvu)
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1S,
 		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
 
+	if (!rvu_afvf_msix_vectors_num_ok(rvu))
+		return 0;
+
+	/* Get PF MSIX vectors offset. */
+	offset = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_INT_CFG(0)) & 0x3ff;
+
+	/* Register MBOX0 interrupt. */
+	offset += RVU_PF_INT_VEC_VFPF_MBOX0;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox0");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_mbox_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE],
+			  rvu);
+	if (ret)
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for Mbox0\n");
+
+	rvu->irq_allocated[offset] = true;
+
+	/* Register MBOX1 interrupt. MBOX1 IRQ number follows MBOX0 so
+	 * simply increment current offset by 1.
+	 */
+	offset += 1;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox1");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_mbox_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE],
+			  rvu);
+	if (ret)
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for Mbox1\n");
+
+	rvu->irq_allocated[offset] = true;
+
 	return 0;
 
 fail:
@@ -1973,6 +2023,129 @@ static int rvu_flr_init(struct rvu *rvu)
 	return 0;
 }
 
+static void rvu_disable_afvf_mbox_intr(struct rvu *rvu)
+{
+	int vfs = rvu->vfs;
+
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), INTR_MASK(vfs));
+	if (vfs > 64)
+		rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(1),
+			      INTR_MASK(vfs - 64));
+}
+
+static void rvu_enable_afvf_mbox_intr(struct rvu *rvu)
+{
+	int vfs = rvu->vfs;
+
+	/* Clear any pending interrupts and enable AF VF interrupts for
+	 * the first 64 VFs.
+	 */
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1SX(0), INTR_MASK(vfs));
+
+	/* Same for remaining VFs, if any. */
+	if (vfs <= 64)
+		return;
+
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1SX(1),
+		      INTR_MASK(vfs - 64));
+}
+
+#define PCI_DEVID_OCTEONTX2_LBK 0xA061
+
+static int lbk_get_num_chans(void)
+{
+	struct pci_dev *pdev;
+	void __iomem *base;
+	int ret = -EIO;
+
+	pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_LBK,
+			      NULL);
+	if (!pdev)
+		goto err;
+
+	base = pci_ioremap_bar(pdev, 0);
+	if (!base)
+		goto err_put;
+
+	/* Read number of available LBK channels from LBK(0)_CONST register. */
+	ret = (readq(base + 0x10) >> 32) & 0xffff;
+	iounmap(base);
+err_put:
+	pci_dev_put(pdev);
+err:
+	return ret;
+}
+
+static int rvu_enable_sriov(struct rvu *rvu)
+{
+	struct pci_dev *pdev = rvu->pdev;
+	int err, chans, vfs;
+
+	if (!rvu_afvf_msix_vectors_num_ok(rvu)) {
+		dev_warn(&pdev->dev,
+			 "Skipping SRIOV enablement since not enough IRQs are available\n");
+		return 0;
+	}
+
+	chans = lbk_get_num_chans();
+	if (chans < 0)
+		return chans;
+
+	vfs = pci_sriov_get_totalvfs(pdev);
+
+	/* Limit VFs in case we have more VFs than LBK channels available. */
+	if (vfs > chans)
+		vfs = chans;
+
+	/* AF's VFs work in pairs and talk over consecutive loopback channels.
+	 * Thus we want to enable maximum even number of VFs. In case
+	 * odd number of VFs are available then the last VF on the list
+	 * remains disabled.
+	 */
+	if (vfs & 0x1) {
+		dev_warn(&pdev->dev,
+			 "Number of VFs should be even. Enabling %d out of %d.\n",
+			 vfs - 1, vfs);
+		vfs--;
+	}
+
+	if (!vfs)
+		return 0;
+
+	/* Save VFs number for reference in VF interrupts handlers.
+	 * Since interrupts might start arriving during SRIOV enablement
+	 * ordinary API cannot be used to get number of enabled VFs.
+	 */
+	rvu->vfs = vfs;
+
+	err = rvu_mbox_init(rvu, &rvu->afvf_wq_info, TYPE_AFVF, vfs,
+			    rvu_afvf_mbox_handler, rvu_afvf_mbox_up_handler);
+	if (err)
+		return err;
+
+	rvu_enable_afvf_mbox_intr(rvu);
+	/* Make sure IRQs are enabled before SRIOV. */
+	mb();
+
+	err = pci_enable_sriov(pdev, vfs);
+	if (err) {
+		rvu_disable_afvf_mbox_intr(rvu);
+		rvu_mbox_destroy(&rvu->afvf_wq_info);
+		return err;
+	}
+
+	return 0;
+}
+
+static void rvu_disable_sriov(struct rvu *rvu)
+{
+	rvu_disable_afvf_mbox_intr(rvu);
+	rvu_mbox_destroy(&rvu->afvf_wq_info);
+	pci_disable_sriov(rvu->pdev);
+}
+
 static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct device *dev = &pdev->dev;
@@ -2054,7 +2227,14 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_flr;
 
+	/* Enable AF's VFs (if any) */
+	err = rvu_enable_sriov(rvu);
+	if (err)
+		goto err_irq;
+
 	return 0;
+err_irq:
+	rvu_unregister_interrupts(rvu);
 err_flr:
 	rvu_flr_wq_destroy(rvu);
 err_cgx:
@@ -2083,6 +2263,7 @@ static void rvu_remove(struct pci_dev *pdev)
 	rvu_flr_wq_destroy(rvu);
 	rvu_cgx_wq_destroy(rvu);
 	rvu_mbox_destroy(&rvu->afpf_wq_info);
+	rvu_disable_sriov(rvu);
 	rvu_reset_all_blocks(rvu);
 	rvu_free_hw_resources(rvu);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 87c29fc7ea5e..d5743e472fb8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -201,7 +201,8 @@ struct rvu {
 	struct rvu_hwinfo       *hw;
 	struct rvu_pfvf		*pf;
 	struct rvu_pfvf		*hwvf;
-	struct mutex            rsrc_lock; /* Serialize resource alloc/free */
+	struct mutex		rsrc_lock; /* Serialize resource alloc/free */
+	int			vfs; /* Number of VFs attached to RVU */
 
 	/* Mbox */
 	struct mbox_wq_info	afpf_wq_info;
-- 
cgit v1.2.3


From 8bb991c5e7c697b968abd9e8f6ad1c5fe8962536 Mon Sep 17 00:00:00 2001
From: Tomasz Duszynski <tduszynski@marvell.com>
Date: Mon, 19 Nov 2018 16:17:40 +0530
Subject: octeontx2-af: Configure AF VFs to talk over LBK channels

Configure AF VFs such that they are able to talk over consecutive
loopback channels.

If 8 VFs are attached to AF then communication will work as below:

TX      RX
lbk0 -> lbk1
lbk1 -> lbk0

lbk2 -> lbk3
lbk3 -> lbk2

lbk4 -> lbk5
lbk5 -> lbk4

lbk6 -> lbk7
lbk7 -> lbk6

Signed-off-by: Tomasz Duszynski <tduszynski@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/common.h |  2 ++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  5 +++++
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 25 +++++++++++++++++++---
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 12 +++++++----
 4 files changed, 37 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index a8c89df07886..9bddb032dd7e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -174,7 +174,9 @@ enum nix_scheduler {
 
 #define MAX_LMAC_PKIND			12
 #define NIX_LINK_CGX_LMAC(a, b)		(0 + 4 * (a) + (b))
+#define NIX_LINK_LBK(a)			(12 + (a))
 #define NIX_CHAN_CGX_LMAC_CHX(a, b, c)	(0x800 + 0x100 * (a) + 0x10 * (b) + (c))
+#define NIX_CHAN_LBK_CHX(a, b)		(0 + 0x100 * (a) + (b))
 
 /* NIX LSO format indices.
  * As of now TSO is the only one using, so statically assigning indices.
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index d5743e472fb8..8936cfbf10e0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -258,6 +258,11 @@ static inline u64 rvupf_read64(struct rvu *rvu, u64 offset)
 /* Function Prototypes
  * RVU
  */
+static inline int is_afvf(u16 pcifunc)
+{
+	return !(pcifunc & ~RVU_PFVF_FUNC_MASK);
+}
+
 int rvu_alloc_bitmap(struct rsrc_bmap *rsrc);
 int rvu_alloc_rsrc(struct rsrc_bmap *rsrc);
 void rvu_free_rsrc(struct rsrc_bmap *rsrc, int id);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 58c672014152..e46db89e91f9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -144,7 +144,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
 {
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	u8 cgx_id, lmac_id;
-	int pkind, pf;
+	int pkind, pf, vf;
 	int err;
 
 	pf = rvu_get_pf(pcifunc);
@@ -170,6 +170,14 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
 		rvu_npc_set_pkind(rvu, pkind, pfvf);
 		break;
 	case NIX_INTF_TYPE_LBK:
+		vf = (pcifunc & RVU_PFVF_FUNC_MASK) - 1;
+		pfvf->rx_chan_base = NIX_CHAN_LBK_CHX(0, vf);
+		pfvf->tx_chan_base = vf & 0x1 ? NIX_CHAN_LBK_CHX(0, vf - 1) :
+						NIX_CHAN_LBK_CHX(0, vf + 1);
+		pfvf->rx_chan_cnt = 1;
+		pfvf->tx_chan_cnt = 1;
+		rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
+					      pfvf->rx_chan_base, false);
 		break;
 	}
 
@@ -684,7 +692,7 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 				  struct nix_lf_alloc_req *req,
 				  struct nix_lf_alloc_rsp *rsp)
 {
-	int nixlf, qints, hwctx_size, err, rc = 0;
+	int nixlf, qints, hwctx_size, intf, err, rc = 0;
 	struct rvu_hwinfo *hw = rvu->hw;
 	u16 pcifunc = req->hdr.pcifunc;
 	struct rvu_block *block;
@@ -839,7 +847,8 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 	/* Config Rx pkt length, csum checks and apad  enable / disable */
 	rvu_write64(rvu, blkaddr, NIX_AF_LFX_RX_CFG(nixlf), req->rx_cfg);
 
-	err = nix_interface_init(rvu, pcifunc, NIX_INTF_TYPE_CGX, nixlf);
+	intf = is_afvf(pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
+	err = nix_interface_init(rvu, pcifunc, intf, nixlf);
 	if (err)
 		goto free_mem;
 
@@ -1354,6 +1363,10 @@ static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
 	struct rvu_pfvf *pfvf;
 	int blkaddr;
 
+	/* Broadcast pkt replication is not needed for AF's VFs, hence skip */
+	if (is_afvf(pcifunc))
+		return 0;
+
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
 	if (blkaddr < 0)
 		return 0;
@@ -1966,6 +1979,12 @@ int rvu_mbox_handler_nix_rxvlan_alloc(struct rvu *rvu, struct msg_req *req,
 	int blkaddr, nixlf, err;
 	struct rvu_pfvf *pfvf;
 
+	/* LBK VFs do not have separate MCAM UCAST entry hence
+	 * skip allocating rxvlan for them
+	 */
+	if (is_afvf(pcifunc))
+		return 0;
+
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	if (pfvf->rxvlan)
 		return 0;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 738314067a9e..d93397e27e05 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -314,6 +314,10 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 	int blkaddr, index, kwi;
 	u64 mac = 0;
 
+	/* AF's VFs work in promiscuous mode */
+	if (is_afvf(pcifunc))
+		return;
+
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0)
 		return;
@@ -368,12 +372,12 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 	struct nix_rx_action action = { };
 	int blkaddr, index, kwi;
 
-	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
-	if (blkaddr < 0)
+	/* Only PF or AF VF can add a promiscuous entry */
+	if ((pcifunc & RVU_PFVF_FUNC_MASK) && !is_afvf(pcifunc))
 		return;
 
-	/* Only PF or AF VF can add a promiscuous entry */
-	if (pcifunc & RVU_PFVF_FUNC_MASK)
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
 		return;
 
 	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
-- 
cgit v1.2.3


From 465ed9c1fc3b8f091c978b8a80ada5953a15b45c Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Mon, 19 Nov 2018 16:17:41 +0530
Subject: octeontx2-af: Add FLR handling support for AF's VFs

Added support to handle FLR for AF's VFs (i.e LBK VFs).
Just the FLR interrupt enable/disable, handler registration
etc, actual HW resource cleanup or LFs teardown logic is
already there.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 129 ++++++++++++++++++++----
 1 file changed, 110 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 34e87e66c259..6154f675d47b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -1788,6 +1788,23 @@ static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc)
 	mutex_unlock(&rvu->flr_lock);
 }
 
+static void rvu_afvf_flr_handler(struct rvu *rvu, int vf)
+{
+	int reg = 0;
+
+	/* pcifunc = 0(PF0) | (vf + 1) */
+	__rvu_flr_handler(rvu, vf + 1);
+
+	if (vf >= 64) {
+		reg = 1;
+		vf = vf - 64;
+	}
+
+	/* Signal FLR finish and enable IRQ */
+	rvupf_write64(rvu, RVU_PF_VFTRPENDX(reg), BIT_ULL(vf));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(reg), BIT_ULL(vf));
+}
+
 static void rvu_flr_handler(struct work_struct *work)
 {
 	struct rvu_work *flrwork = container_of(work, struct rvu_work, work);
@@ -1797,6 +1814,10 @@ static void rvu_flr_handler(struct work_struct *work)
 	int pf;
 
 	pf = flrwork - rvu->flr_wrk;
+	if (pf >= rvu->hw->total_pfs) {
+		rvu_afvf_flr_handler(rvu, pf - rvu->hw->total_pfs);
+		return;
+	}
 
 	cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
 	numvfs = (cfg >> 12) & 0xFF;
@@ -1814,6 +1835,29 @@ static void rvu_flr_handler(struct work_struct *work)
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1S,  BIT_ULL(pf));
 }
 
+static void rvu_afvf_queue_flr_work(struct rvu *rvu, int start_vf, int numvfs)
+{
+	int dev, vf, reg = 0;
+	u64 intr;
+
+	if (start_vf >= 64)
+		reg = 1;
+
+	intr = rvupf_read64(rvu, RVU_PF_VFFLR_INTX(reg));
+	if (!intr)
+		return;
+
+	for (vf = 0; vf < numvfs; vf++) {
+		if (!(intr & BIT_ULL(vf)))
+			continue;
+		dev = vf + start_vf + rvu->hw->total_pfs;
+		queue_work(rvu->flr_wq, &rvu->flr_wrk[dev].work);
+		/* Clear and disable the interrupt */
+		rvupf_write64(rvu, RVU_PF_VFFLR_INTX(reg), BIT_ULL(vf));
+		rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(reg), BIT_ULL(vf));
+	}
+}
+
 static irqreturn_t rvu_flr_intr_handler(int irq, void *rvu_irq)
 {
 	struct rvu *rvu = (struct rvu *)rvu_irq;
@@ -1821,6 +1865,8 @@ static irqreturn_t rvu_flr_intr_handler(int irq, void *rvu_irq)
 	u8  pf;
 
 	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT);
+	if (!intr)
+		goto afvf_flr;
 
 	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
 		if (intr & (1ULL << pf)) {
@@ -1834,6 +1880,12 @@ static irqreturn_t rvu_flr_intr_handler(int irq, void *rvu_irq)
 				    BIT_ULL(pf));
 		}
 	}
+
+afvf_flr:
+	rvu_afvf_queue_flr_work(rvu, 0, 64);
+	if (rvu->vfs > 64)
+		rvu_afvf_queue_flr_work(rvu, 64, rvu->vfs - 64);
+
 	return IRQ_HANDLED;
 }
 
@@ -1876,7 +1928,7 @@ static int rvu_afvf_msix_vectors_num_ok(struct rvu *rvu)
 
 static int rvu_register_interrupts(struct rvu *rvu)
 {
-	int ret, offset;
+	int ret, offset, pf_vec_start;
 
 	rvu->num_vec = pci_msix_vec_count(rvu->pdev);
 
@@ -1941,10 +1993,11 @@ static int rvu_register_interrupts(struct rvu *rvu)
 		return 0;
 
 	/* Get PF MSIX vectors offset. */
-	offset = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_INT_CFG(0)) & 0x3ff;
+	pf_vec_start = rvu_read64(rvu, BLKADDR_RVUM,
+				  RVU_PRIV_PFX_INT_CFG(0)) & 0x3ff;
 
 	/* Register MBOX0 interrupt. */
-	offset += RVU_PF_INT_VEC_VFPF_MBOX0;
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX0;
 	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox0");
 	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
 			  rvu_mbox_intr_handler, 0,
@@ -1959,7 +2012,7 @@ static int rvu_register_interrupts(struct rvu *rvu)
 	/* Register MBOX1 interrupt. MBOX1 IRQ number follows MBOX0 so
 	 * simply increment current offset by 1.
 	 */
-	offset += 1;
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX1;
 	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox1");
 	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
 			  rvu_mbox_intr_handler, 0,
@@ -1971,10 +2024,35 @@ static int rvu_register_interrupts(struct rvu *rvu)
 
 	rvu->irq_allocated[offset] = true;
 
+	/* Register FLR interrupt handler for AF's VFs */
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFFLR0;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF FLR0");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_flr_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE], rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for RVUAFVF FLR0\n");
+		goto fail;
+	}
+	rvu->irq_allocated[offset] = true;
+
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFFLR1;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF FLR1");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_flr_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE], rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for RVUAFVF FLR1\n");
+		goto fail;
+	}
+	rvu->irq_allocated[offset] = true;
+
 	return 0;
 
 fail:
-	pci_free_irq_vectors(rvu->pdev);
+	rvu_unregister_interrupts(rvu);
 	return ret;
 }
 
@@ -1985,16 +2063,16 @@ static void rvu_flr_wq_destroy(struct rvu *rvu)
 		destroy_workqueue(rvu->flr_wq);
 		rvu->flr_wq = NULL;
 	}
-	kfree(rvu->flr_wrk);
 }
 
 static int rvu_flr_init(struct rvu *rvu)
 {
+	int dev, num_devs;
 	u64 cfg;
 	int pf;
 
 	/* Enable FLR for all PFs*/
-	for (pf = 1; pf < rvu->hw->total_pfs; pf++) {
+	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
 		cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
 		rvu_write64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf),
 			    cfg | BIT_ULL(22));
@@ -2006,16 +2084,17 @@ static int rvu_flr_init(struct rvu *rvu)
 	if (!rvu->flr_wq)
 		return -ENOMEM;
 
-	rvu->flr_wrk = devm_kcalloc(rvu->dev, rvu->hw->total_pfs,
+	num_devs = rvu->hw->total_pfs + pci_sriov_get_totalvfs(rvu->pdev);
+	rvu->flr_wrk = devm_kcalloc(rvu->dev, num_devs,
 				    sizeof(struct rvu_work), GFP_KERNEL);
 	if (!rvu->flr_wrk) {
 		destroy_workqueue(rvu->flr_wq);
 		return -ENOMEM;
 	}
 
-	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
-		rvu->flr_wrk[pf].rvu = rvu;
-		INIT_WORK(&rvu->flr_wrk[pf].work, rvu_flr_handler);
+	for (dev = 0; dev < num_devs; dev++) {
+		rvu->flr_wrk[dev].rvu = rvu;
+		INIT_WORK(&rvu->flr_wrk[dev].work, rvu_flr_handler);
 	}
 
 	mutex_init(&rvu->flr_lock);
@@ -2023,26 +2102,35 @@ static int rvu_flr_init(struct rvu *rvu)
 	return 0;
 }
 
-static void rvu_disable_afvf_mbox_intr(struct rvu *rvu)
+static void rvu_disable_afvf_intr(struct rvu *rvu)
 {
 	int vfs = rvu->vfs;
 
 	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), INTR_MASK(vfs));
-	if (vfs > 64)
-		rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(1),
-			      INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(0), INTR_MASK(vfs));
+	if (vfs <= 64)
+		return;
+
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(1),
+		      INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(1), INTR_MASK(vfs - 64));
 }
 
-static void rvu_enable_afvf_mbox_intr(struct rvu *rvu)
+static void rvu_enable_afvf_intr(struct rvu *rvu)
 {
 	int vfs = rvu->vfs;
 
 	/* Clear any pending interrupts and enable AF VF interrupts for
 	 * the first 64 VFs.
 	 */
+	/* Mbox */
 	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(0), INTR_MASK(vfs));
 	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1SX(0), INTR_MASK(vfs));
 
+	/* FLR */
+	rvupf_write64(rvu, RVU_PF_VFFLR_INTX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(0), INTR_MASK(vfs));
+
 	/* Same for remaining VFs, if any. */
 	if (vfs <= 64)
 		return;
@@ -2050,6 +2138,9 @@ static void rvu_enable_afvf_mbox_intr(struct rvu *rvu)
 	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(1), INTR_MASK(vfs - 64));
 	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1SX(1),
 		      INTR_MASK(vfs - 64));
+
+	rvupf_write64(rvu, RVU_PF_VFFLR_INTX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(1), INTR_MASK(vfs - 64));
 }
 
 #define PCI_DEVID_OCTEONTX2_LBK 0xA061
@@ -2125,13 +2216,13 @@ static int rvu_enable_sriov(struct rvu *rvu)
 	if (err)
 		return err;
 
-	rvu_enable_afvf_mbox_intr(rvu);
+	rvu_enable_afvf_intr(rvu);
 	/* Make sure IRQs are enabled before SRIOV. */
 	mb();
 
 	err = pci_enable_sriov(pdev, vfs);
 	if (err) {
-		rvu_disable_afvf_mbox_intr(rvu);
+		rvu_disable_afvf_intr(rvu);
 		rvu_mbox_destroy(&rvu->afvf_wq_info);
 		return err;
 	}
@@ -2141,7 +2232,7 @@ static int rvu_enable_sriov(struct rvu *rvu)
 
 static void rvu_disable_sriov(struct rvu *rvu)
 {
-	rvu_disable_afvf_mbox_intr(rvu);
+	rvu_disable_afvf_intr(rvu);
 	rvu_mbox_destroy(&rvu->afvf_wq_info);
 	pci_disable_sriov(rvu->pdev);
 }
-- 
cgit v1.2.3


From 4fa9121046ce7e6b917405ddbdd51e2ead0c2bb2 Mon Sep 17 00:00:00 2001
From: Linu Cherian <lcherian@marvell.com>
Date: Mon, 19 Nov 2018 16:17:42 +0530
Subject: octeontx2-af: Add interrupt handlers for Master Enable event

- Add interrupt handlers for Master Enable events from PFs
  and Master Enable events from VFs of AF
- Master Enable is required for the MSIX delivery to work
- Master Enable bit trap handler doesn't have to do any anything
  other than clearing the TRPEND bit, since the enable/disable
  requirements are already taken care using mbox requests/flr handler.

Signed-off-by: Linu Cherian <lcherian@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 113 ++++++++++++++++++++++++
 1 file changed, 113 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 6154f675d47b..40eb3ad725f5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -1889,6 +1889,67 @@ afvf_flr:
 	return IRQ_HANDLED;
 }
 
+static void rvu_me_handle_vfset(struct rvu *rvu, int idx, u64 intr)
+{
+	int vf;
+
+	/* Nothing to be done here other than clearing the
+	 * TRPEND bit.
+	 */
+	for (vf = 0; vf < 64; vf++) {
+		if (intr & (1ULL << vf)) {
+			/* clear the trpend due to ME(master enable) */
+			rvupf_write64(rvu, RVU_PF_VFTRPENDX(idx), BIT_ULL(vf));
+			/* clear interrupt */
+			rvupf_write64(rvu, RVU_PF_VFME_INTX(idx), BIT_ULL(vf));
+		}
+	}
+}
+
+/* Handles ME interrupts from VFs of AF */
+static irqreturn_t rvu_me_vf_intr_handler(int irq, void *rvu_irq)
+{
+	struct rvu *rvu = (struct rvu *)rvu_irq;
+	int vfset;
+	u64 intr;
+
+	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFME_INT);
+
+	for (vfset = 0; vfset <= 1; vfset++) {
+		intr = rvupf_read64(rvu, RVU_PF_VFME_INTX(vfset));
+		if (intr)
+			rvu_me_handle_vfset(rvu, vfset, intr);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/* Handles ME interrupts from PFs */
+static irqreturn_t rvu_me_pf_intr_handler(int irq, void *rvu_irq)
+{
+	struct rvu *rvu = (struct rvu *)rvu_irq;
+	u64 intr;
+	u8  pf;
+
+	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFME_INT);
+
+	/* Nothing to be done here other than clearing the
+	 * TRPEND bit.
+	 */
+	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
+		if (intr & (1ULL << pf)) {
+			/* clear the trpend due to ME(master enable) */
+			rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFTRPEND,
+				    BIT_ULL(pf));
+			/* clear interrupt */
+			rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFME_INT,
+				    BIT_ULL(pf));
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
 static void rvu_unregister_interrupts(struct rvu *rvu)
 {
 	int irq;
@@ -1901,6 +1962,10 @@ static void rvu_unregister_interrupts(struct rvu *rvu)
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1C,
 		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
 
+	/* Disable the PF ME interrupt */
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFME_INT_ENA_W1C,
+		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+
 	for (irq = 0; irq < rvu->num_vec; irq++) {
 		if (rvu->irq_allocated[irq])
 			free_irq(pci_irq_vector(rvu->pdev, irq), rvu);
@@ -1989,6 +2054,26 @@ static int rvu_register_interrupts(struct rvu *rvu)
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1S,
 		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
 
+	/* Register ME interrupt handler */
+	sprintf(&rvu->irq_name[RVU_AF_INT_VEC_PFME * NAME_SIZE],
+		"RVUAF ME");
+	ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_PFME),
+			  rvu_me_pf_intr_handler, 0,
+			  &rvu->irq_name[RVU_AF_INT_VEC_PFME * NAME_SIZE],
+			  rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for ME\n");
+	}
+	rvu->irq_allocated[RVU_AF_INT_VEC_PFME] = true;
+
+	/* Enable ME interrupt for all PFs*/
+	rvu_write64(rvu, BLKADDR_RVUM,
+		    RVU_AF_PFME_INT, INTR_MASK(rvu->hw->total_pfs));
+
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFME_INT_ENA_W1S,
+		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+
 	if (!rvu_afvf_msix_vectors_num_ok(rvu))
 		return 0;
 
@@ -2049,6 +2134,30 @@ static int rvu_register_interrupts(struct rvu *rvu)
 	}
 	rvu->irq_allocated[offset] = true;
 
+	/* Register ME interrupt handler for AF's VFs */
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFME0;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF ME0");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_me_vf_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE], rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for RVUAFVF ME0\n");
+		goto fail;
+	}
+	rvu->irq_allocated[offset] = true;
+
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFME1;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF ME1");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_me_vf_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE], rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for RVUAFVF ME1\n");
+		goto fail;
+	}
+	rvu->irq_allocated[offset] = true;
 	return 0;
 
 fail:
@@ -2108,12 +2217,14 @@ static void rvu_disable_afvf_intr(struct rvu *rvu)
 
 	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), INTR_MASK(vfs));
 	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1CX(0), INTR_MASK(vfs));
 	if (vfs <= 64)
 		return;
 
 	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(1),
 		      INTR_MASK(vfs - 64));
 	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1CX(1), INTR_MASK(vfs - 64));
 }
 
 static void rvu_enable_afvf_intr(struct rvu *rvu)
@@ -2130,6 +2241,7 @@ static void rvu_enable_afvf_intr(struct rvu *rvu)
 	/* FLR */
 	rvupf_write64(rvu, RVU_PF_VFFLR_INTX(0), INTR_MASK(vfs));
 	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1SX(0), INTR_MASK(vfs));
 
 	/* Same for remaining VFs, if any. */
 	if (vfs <= 64)
@@ -2141,6 +2253,7 @@ static void rvu_enable_afvf_intr(struct rvu *rvu)
 
 	rvupf_write64(rvu, RVU_PF_VFFLR_INTX(1), INTR_MASK(vfs - 64));
 	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1SX(1), INTR_MASK(vfs - 64));
 }
 
 #define PCI_DEVID_OCTEONTX2_LBK 0xA061
-- 
cgit v1.2.3


From e12890f44ca22a853df3be0eb7b25819162bdc72 Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Mon, 19 Nov 2018 16:17:43 +0530
Subject: octeontx2-af: Workarounds for HW errata

Errata 35038
  Software sets NIX_AF_RX_SW_SYNC[ENA] to sync (flush) in-flight packets
  the RX data path before configuration changes (e.g. disabling one or
  more RQs). Hardware clears [ENA] to indicate sync is done

  An issue exists whereby NIX may clear NIX_AF_RX_SW_SYNC [ENA] too
  early.

Errata 35057
  NIX may corrupt internal state when conditional clocks turn off.
  So turnon all clocks by default.

Errata 35786
 Parse nibble enable NPC configuration for KEY generation has to be
 identical for both Rx and Tx interfaces.

Also corrected endianness configuration for NIX i.e NIX_AF_CFG[AF_BE]
is bit8 and not bit1.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h     | 12 ++++++++++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c | 18 ++++++++++++++++--
 drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c | 12 +++++++++---
 3 files changed, 37 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 8936cfbf10e0..c8409bc5d9c3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -11,6 +11,7 @@
 #ifndef RVU_H
 #define RVU_H
 
+#include <linux/pci.h>
 #include "rvu_struct.h"
 #include "common.h"
 #include "mbox.h"
@@ -18,6 +19,9 @@
 /* PCI device IDs */
 #define	PCI_DEVID_OCTEONTX2_RVU_AF		0xA065
 
+/* Subsystem Device ID */
+#define PCI_SUBSYS_DEVID_96XX                  0xB200
+
 /* PCI BAR nos */
 #define	PCI_AF_REG_BAR_NUM			0
 #define	PCI_PF_REG_BAR_NUM			2
@@ -255,6 +259,14 @@ static inline u64 rvupf_read64(struct rvu *rvu, u64 offset)
 	return readq(rvu->pfreg_base + offset);
 }
 
+static inline bool is_rvu_9xxx_A0(struct rvu *rvu)
+{
+	struct pci_dev *pdev = rvu->pdev;
+
+	return (pdev->revision == 0x00) &&
+		(pdev->subsystem_device == PCI_SUBSYS_DEVID_96XX);
+}
+
 /* Function Prototypes
  * RVU
  */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index e46db89e91f9..b7998f6be386 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -114,6 +114,12 @@ static void nix_rx_sync(struct rvu *rvu, int blkaddr)
 	err = rvu_poll_reg(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0), true);
 	if (err)
 		dev_err(rvu->dev, "NIX RX software sync failed\n");
+
+	/* As per a HW errata in 9xxx A0 silicon, HW may clear SW_SYNC[ENA]
+	 * bit too early. Hence wait for 50us more.
+	 */
+	if (is_rvu_9xxx_A0(rvu))
+		usleep_range(50, 60);
 }
 
 static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
@@ -2135,10 +2141,10 @@ static int nix_aq_init(struct rvu *rvu, struct rvu_block *block)
 	/* Set admin queue endianness */
 	cfg = rvu_read64(rvu, block->addr, NIX_AF_CFG);
 #ifdef __BIG_ENDIAN
-	cfg |= BIT_ULL(1);
+	cfg |= BIT_ULL(8);
 	rvu_write64(rvu, block->addr, NIX_AF_CFG, cfg);
 #else
-	cfg &= ~BIT_ULL(1);
+	cfg &= ~BIT_ULL(8);
 	rvu_write64(rvu, block->addr, NIX_AF_CFG, cfg);
 #endif
 
@@ -2175,6 +2181,14 @@ int rvu_nix_init(struct rvu *rvu)
 		return 0;
 	block = &hw->block[blkaddr];
 
+	/* As per a HW errata in 9xxx A0 silicon, NIX may corrupt
+	 * internal state when conditional clocks are turned off.
+	 * Hence enable them.
+	 */
+	if (is_rvu_9xxx_A0(rvu))
+		rvu_write64(rvu, blkaddr, NIX_AF_CFG,
+			    rvu_read64(rvu, blkaddr, NIX_AF_CFG) | 0x5EULL);
+
 	/* Calibrate X2P bus to check if CGX/LBK links are fine */
 	err = nix_calibrate_x2p(rvu, blkaddr);
 	if (err)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index d93397e27e05..6ea2b0e2df42 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -970,7 +970,7 @@ int rvu_npc_init(struct rvu *rvu)
 	struct npc_pkind *pkind = &rvu->hw->pkind;
 	u64 keyz = NPC_MCAM_KEY_X2;
 	int blkaddr, entry, bank, err;
-	u64 cfg;
+	u64 cfg, nibble_ena;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0) {
@@ -1019,10 +1019,16 @@ int rvu_npc_init(struct rvu *rvu)
 	/* Set RX and TX side MCAM search key size.
 	 * LA..LD (ltype only) + Channel
 	 */
+	nibble_ena = 0x49247;
 	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX),
-			((keyz & 0x3) << 32) | 0x49247);
+			((keyz & 0x3) << 32) | nibble_ena);
+	/* Due to an errata (35786) in A0 pass silicon, parse nibble enable
+	 * configuration has to be identical for both Rx and Tx interfaces.
+	 */
+	if (!is_rvu_9xxx_A0(rvu))
+		nibble_ena = (1ULL << 19) - 1;
 	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX),
-			((keyz & 0x3) << 32) | ((1ULL << 19) - 1));
+			((keyz & 0x3) << 32) | nibble_ena);
 
 	err = npc_mcam_rsrcs_init(rvu, blkaddr);
 	if (err)
-- 
cgit v1.2.3


From 6f9a50691055618b1042ead4d84f80755d1b9315 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:07 +0000
Subject: net: skb_scrub_packet(): Scrub offload_fwd_mark

When a packet is trapped and the corresponding SKB marked as
already-forwarded, it retains this marking even after it is forwarded
across veth links into another bridge. There, since it ingresses the
bridge over veth, which doesn't have offload_fwd_mark, it triggers a
warning in nbp_switchdev_frame_mark().

Then nbp_switchdev_allowed_egress() decides not to allow egress from
this bridge through another veth, because the SKB is already marked, and
the mark (of 0) of course matches. Thus the packet is incorrectly
blocked.

Solve by resetting offload_fwd_mark() in skb_scrub_packet(). That
function is called from tunnels and also from veth, and thus catches the
cases where traffic is forwarded between bridges and transformed in a
way that invalidates the marking.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Suggested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a1be7f19d998..9a8a72cefe9b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4882,6 +4882,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	nf_reset(skb);
 	nf_reset_trace(skb);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+	skb->offload_mr_fwd_mark = 0;
+#endif
+
 	if (!xnet)
 		return;
 
-- 
cgit v1.2.3


From 601bc1c13916899a14e682ada3dfa3ec21b13318 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:08 +0000
Subject: selftests: forwarding: lib: Support NUM_NETIFS of 0

So far the case of NUM_NETIFS of 0 has not been interesting. However if
one wishes to reuse the lib.sh routines in a setup of a separate
namespace, being able to import like this is handy.

Therefore replace the {1..$NUM_NETIFS} references, which cause iteration
over 1 and 0, with an explicit for loop like we do in setup_wait() and
tc_offload_check(), so that for NUM_NETIFS of 0 no iteration is done.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 85d253546684..bb0e9fdf893e 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -104,7 +104,7 @@ create_netif_veth()
 {
 	local i
 
-	for i in $(eval echo {1..$NUM_NETIFS}); do
+	for ((i = 1; i <= NUM_NETIFS; ++i)); do
 		local j=$((i+1))
 
 		ip link show dev ${NETIFS[p$i]} &> /dev/null
@@ -135,7 +135,7 @@ if [[ "$NETIF_CREATE" = "yes" ]]; then
 	create_netif
 fi
 
-for i in $(eval echo {1..$NUM_NETIFS}); do
+for ((i = 1; i <= NUM_NETIFS; ++i)); do
 	ip link show dev ${NETIFS[p$i]} &> /dev/null
 	if [[ $? -ne 0 ]]; then
 		echo "SKIP: could not find all required interfaces"
-- 
cgit v1.2.3


From d0540d1706c3cfbb51769de02858f846d3836389 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:10 +0000
Subject: selftests: forwarding: lib: Add in_ns()

In order to run a certain command inside another network namespace, it's
possible to use "ip netns exec ns command". However then one can't use
functions defined in lib.sh or a test suite.

One option is to do "ip netns exec ns bash -c command", provided that
all functions that one wishes to use (and their dependencies) are
published using "export -f". That may not be practical.

Therefore, introduce a helper in_ns(), which wraps a given command in a
boilerplate of "ip netns exec" and "source lib.sh", thus making all
library functions available. (Custom functions that a script wishes to
run within a namespace still need to be exported.)

Because quotes in "$@" aren't recognized in heredoc, hand-expand the
array in an explicit for loop, leveraging printf %q to handle proper
quoting.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index bb0e9fdf893e..93d6e9df483e 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -783,6 +783,17 @@ multipath_eval()
 	log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
 }
 
+in_ns()
+{
+	local name=$1; shift
+
+	ip netns exec $name bash <<-EOF
+		NUM_NETIFS=0
+		source lib.sh
+		$(for a in "$@"; do printf "%q${IFS:0:1}" "$a"; done)
+	EOF
+}
+
 ##############################################################################
 # Tests
 
-- 
cgit v1.2.3


From 58c7a2d19e90a6ec3fbe6cd0c6b1025b731bc000 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:11 +0000
Subject: selftests: forwarding: ping{6, }_test(): Add description argument

Have ping_test() recognize an optional argument with a description of
the test. This is handy if there are several ping test, to make it clear
which is which.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 93d6e9df483e..fa734ddce2e9 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -813,7 +813,7 @@ ping_test()
 
 	ping_do $1 $2
 	check_err $?
-	log_test "ping"
+	log_test "ping$3"
 }
 
 ping6_do()
@@ -832,7 +832,7 @@ ping6_test()
 
 	ping6_do $1 $2
 	check_err $?
-	log_test "ping6"
+	log_test "ping6$3"
 }
 
 learning_test()
-- 
cgit v1.2.3


From d20b0f214aa74a3f6b28b8d522f273e1fd2abea3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:12 +0000
Subject: selftests: forwarding: ping{6, }_do(): Allow passing ping arguments

Make the ping routine more generic by allowing passing arbitrary ping
command-line arguments.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index fa734ddce2e9..e916663a1019 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -801,10 +801,11 @@ ping_do()
 {
 	local if_name=$1
 	local dip=$2
+	local args=$3
 	local vrf_name
 
 	vrf_name=$(master_name_get $if_name)
-	ip vrf exec $vrf_name $PING $dip -c 10 -i 0.1 -w 2 &> /dev/null
+	ip vrf exec $vrf_name $PING $args $dip -c 10 -i 0.1 -w 2 &> /dev/null
 }
 
 ping_test()
@@ -820,10 +821,11 @@ ping6_do()
 {
 	local if_name=$1
 	local dip=$2
+	local args=$3
 	local vrf_name
 
 	vrf_name=$(master_name_get $if_name)
-	ip vrf exec $vrf_name $PING6 $dip -c 10 -i 0.1 -w 2 &> /dev/null
+	ip vrf exec $vrf_name $PING6 $args $dip -c 10 -i 0.1 -w 2 &> /dev/null
 }
 
 ping6_test()
-- 
cgit v1.2.3


From d1038cd0f67e542f2744782f958b95c4909fb63a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:13 +0000
Subject: selftests: forwarding: lib: Add link_stats_rx_errors_get()

Such a function will be useful for counting malformed packets in the ECN
decap test.

To that end, introduce a common handler for handling stat-fetching, and
reuse it in link_stats_tx_packets_get() and link_stats_rx_errors_get().

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index e916663a1019..7af5a03bcb32 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -477,11 +477,24 @@ master_name_get()
 	ip -j link show dev $if_name | jq -r '.[]["master"]'
 }
 
+link_stats_get()
+{
+	local if_name=$1; shift
+	local dir=$1; shift
+	local stat=$1; shift
+
+	ip -j -s link show dev $if_name \
+		| jq '.[]["stats64"]["'$dir'"]["'$stat'"]'
+}
+
 link_stats_tx_packets_get()
 {
-       local if_name=$1
+	link_stats_get $1 tx packets
+}
 
-       ip -j -s link show dev $if_name | jq '.[]["stats64"]["tx"]["packets"]'
+link_stats_rx_errors_get()
+{
+	link_stats_get $1 rx errors
 }
 
 tc_rule_stats_get()
-- 
cgit v1.2.3


From fd64d5a2e383568bb0d6b7b8c619358e68b6718c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:14 +0000
Subject: selftests: forwarding: Add a skeleton of vxlan_bridge_1d

This skeleton sets up a topology with three VXLAN endpoints: one
"local", possibly offloaded, and two "remote", formed using veth pairs
and likely purely software bridges. The "local" endpoint is connected to
host systems by a VLAN-unaware bridge.

Since VXLAN tunnels must be unique per namespace, each of the "remote"
endpoints is in its own namespace. H3 forms the bridge between the three
domains.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1d.sh    | 296 +++++++++++++++++++++
 1 file changed, 296 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
new file mode 100755
index 000000000000..af88e1c146a7
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -0,0 +1,296 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +--------------------+                               +----------------------+
+# | H1 (vrf)           |                               |             H2 (vrf) |
+# |    + $h1           |                               |  + $h2               |
+# |    | 192.0.2.1/28  |                               |  | 192.0.2.2/28      |
+# +----|---------------+                               +--|-------------------+
+#      |                                                  |
+# +----|--------------------------------------------------|-------------------+
+# | SW |                                                  |                   |
+# | +--|--------------------------------------------------|-----------------+ |
+# | |  + $swp1                   BR1 (802.1d)             + $swp2           | |
+# | |                                                                       | |
+# | |  + vx1 (vxlan)                                                        | |
+# | |    local 192.0.2.17                                                   | |
+# | |    remote 192.0.2.34 192.0.2.50                                       | |
+# | |    id 1000 dstport $VXPORT                                            | |
+# | +-----------------------------------------------------------------------+ |
+# |                                                                           |
+# |  192.0.2.32/28 via 192.0.2.18                                             |
+# |  192.0.2.48/28 via 192.0.2.18                                             |
+# |                                                                           |
+# |    + $rp1                                                                 |
+# |    | 192.0.2.17/28                                                        |
+# +----|----------------------------------------------------------------------+
+#      |
+# +----|--------------------------------------------------------+
+# |    |                                             VRP2 (vrf) |
+# |    + $rp2                                                   |
+# |      192.0.2.18/28                                          |
+# |                                                             |   (maybe) HW
+# =============================================================================
+# |                                                             |  (likely) SW
+# |    + v1 (veth)                             + v3 (veth)      |
+# |    | 192.0.2.33/28                         | 192.0.2.49/28  |
+# +----|---------------------------------------|----------------+
+#      |                                       |
+# +----|------------------------------+   +----|------------------------------+
+# |    + v2 (veth)        NS1 (netns) |   |    + v4 (veth)        NS2 (netns) |
+# |      192.0.2.34/28                |   |      192.0.2.50/28                |
+# |                                   |   |                                   |
+# |   192.0.2.16/28 via 192.0.2.33    |   |   192.0.2.16/28 via 192.0.2.49    |
+# |   192.0.2.50/32 via 192.0.2.33    |   |   192.0.2.34/32 via 192.0.2.49    |
+# |                                   |   |                                   |
+# | +-------------------------------+ |   | +-------------------------------+ |
+# | |                  BR2 (802.1d) | |   | |                  BR2 (802.1d) | |
+# | |  + vx2 (vxlan)                | |   | |  + vx2 (vxlan)                | |
+# | |    local 192.0.2.34           | |   | |    local 192.0.2.50           | |
+# | |    remote 192.0.2.17          | |   | |    remote 192.0.2.17          | |
+# | |    remote 192.0.2.50          | |   | |    remote 192.0.2.34          | |
+# | |    id 1000 dstport $VXPORT    | |   | |    id 1000 dstport $VXPORT    | |
+# | |                               | |   | |                               | |
+# | |  + w1 (veth)                  | |   | |  + w1 (veth)                  | |
+# | +--|----------------------------+ |   | +--|----------------------------+ |
+# |    |                              |   |    |                              |
+# | +--|----------------------------+ |   | +--|----------------------------+ |
+# | |  |                  VW2 (vrf) | |   | |  |                  VW2 (vrf) | |
+# | |  + w2 (veth)                  | |   | |  + w2 (veth)                  | |
+# | |    192.0.2.3/28               | |   | |    192.0.2.4/28               | |
+# | +-------------------------------+ |   | +-------------------------------+ |
+# +-----------------------------------+   +-----------------------------------+
+
+: ${VXPORT:=4789}
+export VXPORT
+
+: ${ALL_TESTS:="
+    "}
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28
+	tc qdisc add dev $h1 clsact
+}
+
+h1_destroy()
+{
+	tc qdisc del dev $h1 clsact
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/28
+	tc qdisc add dev $h2 clsact
+}
+
+h2_destroy()
+{
+	tc qdisc del dev $h2 clsact
+	simple_if_fini $h2 192.0.2.2/28
+}
+
+rp1_set_addr()
+{
+	ip address add dev $rp1 192.0.2.17/28
+
+	ip route add 192.0.2.32/28 nexthop via 192.0.2.18
+	ip route add 192.0.2.48/28 nexthop via 192.0.2.18
+}
+
+rp1_unset_addr()
+{
+	ip route del 192.0.2.48/28 nexthop via 192.0.2.18
+	ip route del 192.0.2.32/28 nexthop via 192.0.2.18
+
+	ip address del dev $rp1 192.0.2.17/28
+}
+
+switch_create()
+{
+	ip link add name br1 type bridge vlan_filtering 0 mcast_snooping 0
+	# Make sure the bridge uses the MAC address of the local port and not
+	# that of the VxLAN's device.
+	ip link set dev br1 address $(mac_get $swp1)
+	ip link set dev br1 up
+
+	ip link set dev $rp1 up
+	rp1_set_addr
+
+	ip link add name vx1 type vxlan id 1000		\
+		local 192.0.2.17 dstport "$VXPORT"	\
+		nolearning noudpcsum tos inherit ttl 100
+	ip link set dev vx1 up
+
+	ip link set dev vx1 master br1
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 master br1
+	ip link set dev $swp2 up
+
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+}
+
+switch_destroy()
+{
+	rp1_unset_addr
+	ip link set dev $rp1 down
+
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+
+	ip link set dev vx1 nomaster
+	ip link set dev vx1 down
+	ip link del dev vx1
+
+	ip link set dev $swp2 down
+	ip link set dev $swp2 nomaster
+
+	ip link set dev $swp1 down
+	ip link set dev $swp1 nomaster
+
+	ip link set dev br1 down
+	ip link del dev br1
+}
+
+vrp2_create()
+{
+	simple_if_init $rp2 192.0.2.18/28
+	__simple_if_init v1 v$rp2 192.0.2.33/28
+	__simple_if_init v3 v$rp2 192.0.2.49/28
+	tc qdisc add dev v1 clsact
+}
+
+vrp2_destroy()
+{
+	tc qdisc del dev v1 clsact
+	__simple_if_fini v3 192.0.2.49/28
+	__simple_if_fini v1 192.0.2.33/28
+	simple_if_fini $rp2 192.0.2.18/28
+}
+
+ns_init_common()
+{
+	local in_if=$1; shift
+	local in_addr=$1; shift
+	local other_in_addr=$1; shift
+	local nh_addr=$1; shift
+	local host_addr=$1; shift
+
+	ip link set dev $in_if up
+	ip address add dev $in_if $in_addr/28
+	tc qdisc add dev $in_if clsact
+
+	ip link add name br2 type bridge vlan_filtering 0
+	ip link set dev br2 up
+
+	ip link add name w1 type veth peer name w2
+
+	ip link set dev w1 master br2
+	ip link set dev w1 up
+
+	ip link add name vx2 type vxlan id 1000 local $in_addr dstport "$VXPORT"
+	ip link set dev vx2 up
+	bridge fdb append dev vx2 00:00:00:00:00:00 dst 192.0.2.17 self
+	bridge fdb append dev vx2 00:00:00:00:00:00 dst $other_in_addr self
+
+	ip link set dev vx2 master br2
+	tc qdisc add dev vx2 clsact
+
+	simple_if_init w2 $host_addr/28
+
+	ip route add 192.0.2.16/28 nexthop via $nh_addr
+	ip route add $other_in_addr/32 nexthop via $nh_addr
+}
+export -f ns_init_common
+
+ns1_create()
+{
+	ip netns add ns1
+	ip link set dev v2 netns ns1
+	in_ns ns1 \
+	      ns_init_common v2 192.0.2.34 192.0.2.50 192.0.2.33 192.0.2.3
+}
+
+ns1_destroy()
+{
+	ip netns exec ns1 ip link set dev v2 netns 1
+	ip netns del ns1
+}
+
+ns2_create()
+{
+	ip netns add ns2
+	ip link set dev v4 netns ns2
+	in_ns ns2 \
+	      ns_init_common v4 192.0.2.50 192.0.2.34 192.0.2.49 192.0.2.4
+}
+
+ns2_destroy()
+{
+	ip netns exec ns2 ip link set dev v4 netns 1
+	ip netns del ns2
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp1=${NETIFS[p5]}
+	rp2=${NETIFS[p6]}
+
+	vrf_prepare
+	forwarding_enable
+
+	h1_create
+	h2_create
+	switch_create
+
+	ip link add name v1 type veth peer name v2
+	ip link add name v3 type veth peer name v4
+	vrp2_create
+	ns1_create
+	ns2_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ns2_destroy
+	ns1_destroy
+	vrp2_destroy
+	ip link del dev v3
+	ip link del dev v1
+
+	switch_destroy
+	h2_destroy
+	h1_destroy
+
+	forwarding_restore
+	vrf_cleanup
+}
+
+test_all()
+{
+	echo "Running tests with UDP port $VXPORT"
+	tests_run
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+test_all
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 5852fd07c441bc7c2e720440d8df2e2b80aea58b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:15 +0000
Subject: selftests: forwarding: vxlan_bridge_1d: Add ping test

Test end-to-end reachability between local and remote endpoints.

Note that because learning is disabled on the VXLAN device, the ICMP
requests will end up being flooded to all remotes.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index af88e1c146a7..0e3d7abc70d3 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -65,6 +65,7 @@
 export VXPORT
 
 : ${ALL_TESTS:="
+	ping_ipv4
     "}
 
 NUM_NETIFS=6
@@ -281,6 +282,13 @@ cleanup()
 	vrf_cleanup
 }
 
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.2 ": local->local"
+	ping_test $h1 192.0.2.3 ": local->remote 1"
+	ping_test $h1 192.0.2.4 ": local->remote 2"
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"
-- 
cgit v1.2.3


From edaa117efe46845e17275c51f61591df15d9e9a9 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:17 +0000
Subject: selftests: forwarding: vxlan_bridge_1d: Add flood test

Test that when sending traffic to an unlearned MAC address, the traffic
is flooded to both remote VXLAN endpoints.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1d.sh    | 105 +++++++++++++++++++++
 1 file changed, 105 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 0e3d7abc70d3..1edd5189c41c 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -66,6 +66,7 @@ export VXPORT
 
 : ${ALL_TESTS:="
 	ping_ipv4
+	test_flood
     "}
 
 NUM_NETIFS=6
@@ -289,6 +290,110 @@ ping_ipv4()
 	ping_test $h1 192.0.2.4 ": local->remote 2"
 }
 
+maybe_in_ns()
+{
+	echo ${1:+in_ns} $1
+}
+
+__flood_counter_add_del()
+{
+	local add_del=$1; shift
+	local dev=$1; shift
+	local ns=$1; shift
+
+	# Putting the ICMP capture both to HW and to SW will end up
+	# double-counting the packets that are trapped to slow path, such as for
+	# the unicast test. Adding either skip_hw or skip_sw fixes this problem,
+	# but with skip_hw, the flooded packets are not counted at all, because
+	# those are dropped due to MAC address mismatch; and skip_sw is a no-go
+	# for veth-based topologies.
+	#
+	# So try to install with skip_sw and fall back to skip_sw if that fails.
+
+	$(maybe_in_ns $ns) __icmp_capture_add_del          \
+			   $add_del 100 "" $dev skip_sw 2>/dev/null || \
+	$(maybe_in_ns $ns) __icmp_capture_add_del          \
+			   $add_del 100 "" $dev skip_hw
+}
+
+flood_counter_install()
+{
+	__flood_counter_add_del add "$@"
+}
+
+flood_counter_uninstall()
+{
+	__flood_counter_add_del del "$@"
+}
+
+flood_fetch_stat()
+{
+	local dev=$1; shift
+	local ns=$1; shift
+
+	$(maybe_in_ns $ns) tc_rule_stats_get $dev 100 ingress
+}
+
+flood_fetch_stats()
+{
+	local counters=("${@}")
+	local counter
+
+	for counter in "${counters[@]}"; do
+		flood_fetch_stat $counter
+	done
+}
+
+vxlan_flood_test()
+{
+	local mac=$1; shift
+	local dst=$1; shift
+	local -a expects=("${@}")
+
+	local -a counters=($h2 "vx2 ns1" "vx2 ns2")
+	local counter
+	local key
+
+	for counter in "${counters[@]}"; do
+		flood_counter_install $counter
+	done
+
+	local -a t0s=($(flood_fetch_stats "${counters[@]}"))
+	$MZ $h1 -c 10 -d 100msec -p 64 -b $mac -B $dst -t icmp -q
+	sleep 1
+	local -a t1s=($(flood_fetch_stats "${counters[@]}"))
+
+	for key in ${!t0s[@]}; do
+		local delta=$((t1s[$key] - t0s[$key]))
+		local expect=${expects[$key]}
+
+		((expect == delta))
+		check_err $? "${counters[$key]}: Expected to capture $expect packets, got $delta."
+	done
+
+	for counter in "${counters[@]}"; do
+		flood_counter_uninstall $counter
+	done
+}
+
+__test_flood()
+{
+	local mac=$1; shift
+	local dst=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	vxlan_flood_test $mac $dst 10 10 10
+
+	log_test "VXLAN: $what"
+}
+
+test_flood()
+{
+	__test_flood de:ad:be:ef:13:37 192.0.2.100 "flood"
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"
-- 
cgit v1.2.3


From bfd1e27038ab7e9ee3f730667cd0ae0e0eb23f88 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:18 +0000
Subject: selftests: forwarding: vxlan_bridge_1d: Add unicast test

Test that when sending traffic to a learned MAC address, the traffic is
forwarded accurately only to the right endpoint.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1d.sh    | 54 ++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 1edd5189c41c..1a3486ec1d21 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -67,6 +67,7 @@ export VXPORT
 : ${ALL_TESTS:="
 	ping_ipv4
 	test_flood
+	test_unicast
     "}
 
 NUM_NETIFS=6
@@ -263,6 +264,10 @@ setup_prepare()
 	vrp2_create
 	ns1_create
 	ns2_create
+
+	r1_mac=$(in_ns ns1 mac_get w2)
+	r2_mac=$(in_ns ns2 mac_get w2)
+	h2_mac=$(mac_get $h2)
 }
 
 cleanup()
@@ -394,6 +399,55 @@ test_flood()
 	__test_flood de:ad:be:ef:13:37 192.0.2.100 "flood"
 }
 
+vxlan_fdb_add_del()
+{
+	local add_del=$1; shift
+	local mac=$1; shift
+	local dev=$1; shift
+	local dst=$1; shift
+
+	bridge fdb $add_del dev $dev $mac self static permanent \
+		${dst:+dst} $dst 2>/dev/null
+	bridge fdb $add_del dev $dev $mac master static 2>/dev/null
+}
+
+__test_unicast()
+{
+	local mac=$1; shift
+	local dst=$1; shift
+	local hit_idx=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	local -a expects=(0 0 0)
+	expects[$hit_idx]=10
+
+	vxlan_flood_test $mac $dst "${expects[@]}"
+
+	log_test "VXLAN: $what"
+}
+
+test_unicast()
+{
+	local -a targets=("$h2_mac $h2"
+			  "$r1_mac vx1 192.0.2.34"
+			  "$r2_mac vx1 192.0.2.50")
+	local target
+
+	for target in "${targets[@]}"; do
+		vxlan_fdb_add_del add $target
+	done
+
+	__test_unicast $h2_mac 192.0.2.2 0 "local MAC unicast"
+	__test_unicast $r1_mac 192.0.2.3 1 "remote MAC 1 unicast"
+	__test_unicast $r2_mac 192.0.2.4 2 "remote MAC 2 unicast"
+
+	for target in "${targets[@]}"; do
+		vxlan_fdb_add_del del $target
+	done
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"
-- 
cgit v1.2.3


From 50a02b0825668fe96884d47914fa082c91bda504 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:19 +0000
Subject: selftests: forwarding: vxlan_bridge_1d: Reconfigure & rerun tests

The ordering of the topology creation can have impact on whether a
driver is successful in offloading VXLAN. Therefore add a pseudo-test
that reshuffles bits of the topology, and then reruns the same suite of
tests again to make sure that the new setup is supported as well.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1d.sh    | 26 ++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 1a3486ec1d21..a943d8da14b9 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -68,6 +68,10 @@ export VXPORT
 	ping_ipv4
 	test_flood
 	test_unicast
+	reapply_config
+	ping_ipv4
+	test_flood
+	test_unicast
     "}
 
 NUM_NETIFS=6
@@ -288,6 +292,28 @@ cleanup()
 	vrf_cleanup
 }
 
+# For the first round of tests, vx1 is the first device to get attached to the
+# bridge, and that at the point that the local IP is already configured. Try the
+# other scenario of attaching the device to an already-offloaded bridge, and
+# only then attach the local IP.
+reapply_config()
+{
+	echo "Reapplying configuration"
+
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+	rp1_unset_addr
+	ip link set dev vx1 nomaster
+	sleep 5
+
+	ip link set dev vx1 master br1
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+	sleep 1
+	rp1_set_addr
+	sleep 5
+}
+
 ping_ipv4()
 {
 	ping_test $h1 192.0.2.2 ": local->local"
-- 
cgit v1.2.3


From b3a7ee74ee659c789b6e6254d0839789477f5c3e Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:20 +0000
Subject: selftests: forwarding: vxlan_bridge_1d: Add a TTL test

This tests whether TTL of VXLAN envelope packets is properly set based
on the device configuration.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1d.sh    | 33 ++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index a943d8da14b9..0c17b0d427ba 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -68,6 +68,7 @@ export VXPORT
 	ping_ipv4
 	test_flood
 	test_unicast
+	test_ttl
 	reapply_config
 	ping_ipv4
 	test_flood
@@ -474,6 +475,38 @@ test_unicast()
 	done
 }
 
+vxlan_ping_test()
+{
+	local ping_dev=$1; shift
+	local ping_dip=$1; shift
+	local ping_args=$1; shift
+	local capture_dev=$1; shift
+	local capture_dir=$1; shift
+	local capture_pref=$1; shift
+	local expect=$1; shift
+
+	local t0=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir)
+	ping_do $ping_dev $ping_dip "$ping_args"
+	local t1=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir)
+	local delta=$((t1 - t0))
+
+	# Tolerate a couple stray extra packets.
+	((expect <= delta && delta <= expect + 2))
+	check_err $? "$capture_dev: Expected to capture $expect packets, got $delta."
+}
+
+test_ttl()
+{
+	RET=0
+
+	tc filter add dev v1 egress pref 77 prot ip \
+		flower ip_ttl 99 action pass
+	vxlan_ping_test $h1 192.0.2.3 "" v1 egress 77 10
+	tc filter del dev v1 egress pref 77 prot ip
+
+	log_test "VXLAN: envelope TTL"
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"
-- 
cgit v1.2.3


From d417ecf533fe014de667705f58ae5c579f7740b9 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:21 +0000
Subject: selftests: forwarding: vxlan_bridge_1d: Add a TOS test

Test that TOS is inherited from the tunneled packet into the envelope as
configured at the VXLAN device.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 0c17b0d427ba..ac1070937ae7 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -69,6 +69,7 @@ export VXPORT
 	test_flood
 	test_unicast
 	test_ttl
+	test_tos
 	reapply_config
 	ping_ipv4
 	test_flood
@@ -507,6 +508,19 @@ test_ttl()
 	log_test "VXLAN: envelope TTL"
 }
 
+test_tos()
+{
+	RET=0
+
+	tc filter add dev v1 egress pref 77 prot ip \
+		flower ip_tos 0x40 action pass
+	vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10
+	vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0
+	tc filter del dev v1 egress pref 77 prot ip
+
+	log_test "VXLAN: envelope TOS inheritance"
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"
-- 
cgit v1.2.3


From 1e5abfb3ff41a532f687875ada9ea2af7a1069b3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:22 +0000
Subject: selftests: forwarding: vxlan_bridge_1d: Add an ECN encap test

Test that ECN bits in the VXLAN envelope are correctly deduced from the
overlay packet.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1d.sh    | 26 ++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index ac1070937ae7..82a124cbd523 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -70,6 +70,7 @@ export VXPORT
 	test_unicast
 	test_ttl
 	test_tos
+	test_ecn_encap
 	reapply_config
 	ping_ipv4
 	test_flood
@@ -521,6 +522,31 @@ test_tos()
 	log_test "VXLAN: envelope TOS inheritance"
 }
 
+__test_ecn_encap()
+{
+	local q=$1; shift
+	local tos=$1; shift
+
+	RET=0
+
+	tc filter add dev v1 egress pref 77 prot ip \
+		flower ip_tos $tos action pass
+	sleep 1
+	vxlan_ping_test $h1 192.0.2.3 "-Q $q" v1 egress 77 10
+	tc filter del dev v1 egress pref 77 prot ip
+
+	log_test "VXLAN: ECN encap: $q->$tos"
+}
+
+test_ecn_encap()
+{
+	# In accordance with INET_ECN_encapsulate()
+	__test_ecn_encap 0x00 0x00
+	__test_ecn_encap 0x01 0x01
+	__test_ecn_encap 0x02 0x02
+	__test_ecn_encap 0x03 0x02
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"
-- 
cgit v1.2.3


From a0b61f3d8ebfe927d596c1aaca9b6e23bd185f55 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:24 +0000
Subject: selftests: forwarding: vxlan_bridge_1d: Add an ECN decap test

Test that when decapsulating from VXLAN, the values of inner and outer
TOS are handled appropriately. Because VXLAN driver on its own won't
produce the arbitrary TOS combinations necessary to test this feature,
simply open-code a single ICMP packet and have mausezahn assemble it.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1d.sh    | 116 +++++++++++++++++++++
 1 file changed, 116 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 82a124cbd523..5cc6ac74eb74 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -71,6 +71,7 @@ export VXPORT
 	test_ttl
 	test_tos
 	test_ecn_encap
+	test_ecn_decap
 	reapply_config
 	ping_ipv4
 	test_flood
@@ -547,6 +548,121 @@ test_ecn_encap()
 	__test_ecn_encap 0x03 0x02
 }
 
+vxlan_encapped_ping_do()
+{
+	local count=$1; shift
+	local dev=$1; shift
+	local next_hop_mac=$1; shift
+	local dest_ip=$1; shift
+	local dest_mac=$1; shift
+	local inner_tos=$1; shift
+	local outer_tos=$1; shift
+
+	$MZ $dev -c $count -d 100msec -q \
+		-b $next_hop_mac -B $dest_ip \
+		-t udp tos=$outer_tos,sp=23456,dp=$VXPORT,p=$(:
+		    )"08:"$(                      : VXLAN flags
+		    )"00:00:00:"$(                : VXLAN reserved
+		    )"00:03:e8:"$(                : VXLAN VNI
+		    )"00:"$(                      : VXLAN reserved
+		    )"$dest_mac:"$(               : ETH daddr
+		    )"$(mac_get w2):"$(           : ETH saddr
+		    )"08:00:"$(                   : ETH type
+		    )"45:"$(                      : IP version + IHL
+		    )"$inner_tos:"$(              : IP TOS
+		    )"00:54:"$(                   : IP total length
+		    )"99:83:"$(                   : IP identification
+		    )"40:00:"$(                   : IP flags + frag off
+		    )"40:"$(                      : IP TTL
+		    )"01:"$(                      : IP proto
+		    )"00:00:"$(                   : IP header csum
+		    )"c0:00:02:03:"$(             : IP saddr: 192.0.2.3
+		    )"c0:00:02:01:"$(             : IP daddr: 192.0.2.1
+		    )"08:"$(                      : ICMP type
+		    )"00:"$(                      : ICMP code
+		    )"8b:f2:"$(                   : ICMP csum
+		    )"1f:6a:"$(                   : ICMP request identifier
+		    )"00:01:"$(                   : ICMP request sequence number
+		    )"4f:ff:c5:5b:00:00:00:00:"$( : ICMP payload
+		    )"6d:74:0b:00:00:00:00:00:"$( :
+		    )"10:11:12:13:14:15:16:17:"$( :
+		    )"18:19:1a:1b:1c:1d:1e:1f:"$( :
+		    )"20:21:22:23:24:25:26:27:"$( :
+		    )"28:29:2a:2b:2c:2d:2e:2f:"$( :
+		    )"30:31:32:33:34:35:36:37"
+}
+export -f vxlan_encapped_ping_do
+
+vxlan_encapped_ping_test()
+{
+	local ping_dev=$1; shift
+	local nh_dev=$1; shift
+	local ping_dip=$1; shift
+	local inner_tos=$1; shift
+	local outer_tos=$1; shift
+	local stat_get=$1; shift
+	local expect=$1; shift
+
+	local t0=$($stat_get)
+
+	in_ns ns1 \
+		vxlan_encapped_ping_do 10 $ping_dev $(mac_get $nh_dev) \
+			$ping_dip $(mac_get $h1) \
+			$inner_tos $outer_tos
+
+	local t1=$($stat_get)
+	local delta=$((t1 - t0))
+
+	# Tolerate a couple stray extra packets.
+	((expect <= delta && delta <= expect + 2))
+	check_err $? "Expected to capture $expect packets, got $delta."
+}
+export -f vxlan_encapped_ping_test
+
+__test_ecn_decap()
+{
+	local orig_inner_tos=$1; shift
+	local orig_outer_tos=$1; shift
+	local decapped_tos=$1; shift
+
+	RET=0
+
+	tc filter add dev $h1 ingress pref 77 prot ip \
+		flower ip_tos $decapped_tos action pass
+	sleep 1
+	vxlan_encapped_ping_test v2 v1 192.0.2.17 \
+				 $orig_inner_tos $orig_outer_tos \
+				 "tc_rule_stats_get $h1 77 ingress" 10
+	tc filter del dev $h1 ingress pref 77
+
+	log_test "VXLAN: ECN decap: $orig_outer_tos/$orig_inner_tos->$decapped_tos"
+}
+
+test_ecn_decap_error()
+{
+	local orig_inner_tos=00
+	local orig_outer_tos=03
+
+	RET=0
+
+	vxlan_encapped_ping_test v2 v1 192.0.2.17 \
+				 $orig_inner_tos $orig_outer_tos \
+				 "link_stats_rx_errors_get vx1" 10
+
+	log_test "VXLAN: ECN decap: $orig_outer_tos/$orig_inner_tos->error"
+}
+
+test_ecn_decap()
+{
+	# In accordance with INET_ECN_decapsulate()
+	__test_ecn_decap 00 00 0x00
+	__test_ecn_decap 01 01 0x01
+	__test_ecn_decap 02 01 0x02
+	__test_ecn_decap 01 03 0x03
+	__test_ecn_decap 02 03 0x03
+	test_ecn_decap_error
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"
-- 
cgit v1.2.3


From 3485f87cb7f82434cb6526a2ab5088012378dcb6 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:25 +0000
Subject: selftests: forwarding: vxlan_bridge_1d_port_8472: New test

This simple wrapper reruns the VXLAN ping test with a port number of
8472.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh      | 10 ++++++++++
 1 file changed, 10 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh
new file mode 100755
index 000000000000..3bf3da69195f
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh
@@ -0,0 +1,10 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# A wrapper to run VXLAN tests with an unusual port number.
+
+VXPORT=8472
+ALL_TESTS="
+	ping_ipv4
+"
+source vxlan_bridge_1d.sh
-- 
cgit v1.2.3


From 99c9b084f0bec000ef394d1bb58f33c4910752d9 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:26 +0000
Subject: selftests: mlxsw: Add a test for VxLAN configuration

Test various aspects of VxLAN offloading which are specific to mlxsw,
such as sanitization of invalid configurations and offload indication.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/vxlan.sh | 664 +++++++++++++++++++++
 1 file changed, 664 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/vxlan.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
new file mode 100755
index 000000000000..52e78adfe081
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
@@ -0,0 +1,664 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test various aspects of VxLAN offloading which are specific to mlxsw, such
+# as sanitization of invalid configurations and offload indication.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="sanitization_test offload_indication_test"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+
+	ip link set dev $swp1 up
+	ip link set dev $swp2 up
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link set dev $swp2 down
+	ip link set dev $swp1 down
+}
+
+sanitization_single_dev_test_pass()
+{
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev vxlan0 master br0
+	check_err $?
+
+	ip link set dev $swp1 nomaster
+
+	ip link set dev $swp1 master br0
+	check_err $?
+}
+
+sanitization_single_dev_test_fail()
+{
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev vxlan0 master br0 &> /dev/null
+	check_fail $?
+
+	ip link set dev $swp1 nomaster
+
+	ip link set dev vxlan0 master br0
+	check_err $?
+	ip link set dev $swp1 master br0 &> /dev/null
+	check_fail $?
+}
+
+sanitization_single_dev_valid_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_pass
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device - valid configuration"
+}
+
+sanitization_single_dev_vlan_aware_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0 vlan_filtering 1
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with a vlan-aware bridge"
+}
+
+sanitization_single_dev_mcast_enabled_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with a multicast enabled bridge"
+}
+
+sanitization_single_dev_mcast_group_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789 \
+		dev $swp2 group 239.0.0.1
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with a multicast group"
+}
+
+sanitization_single_dev_no_local_ip_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with no local ip"
+}
+
+sanitization_single_dev_local_ipv6_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 2001:db8::1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with local ipv6 address"
+}
+
+sanitization_single_dev_learning_enabled_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 learning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with learning enabled"
+}
+
+sanitization_single_dev_local_interface_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789 dev $swp2
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with local interface"
+}
+
+sanitization_single_dev_port_range_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789 \
+		srcport 4000 5000
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with udp source port range"
+}
+
+sanitization_single_dev_tos_static_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos 20 local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with static tos"
+}
+
+sanitization_single_dev_ttl_inherit_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl inherit tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with inherit ttl"
+}
+
+sanitization_single_dev_udp_checksum_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning udpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with udp checksum"
+}
+
+sanitization_single_dev_test()
+{
+	# These tests make sure that we correctly sanitize VxLAN device
+	# configurations we do not support
+	sanitization_single_dev_valid_test
+	sanitization_single_dev_vlan_aware_test
+	sanitization_single_dev_mcast_enabled_test
+	sanitization_single_dev_mcast_group_test
+	sanitization_single_dev_no_local_ip_test
+	sanitization_single_dev_local_ipv6_test
+	sanitization_single_dev_learning_enabled_test
+	sanitization_single_dev_local_interface_test
+	sanitization_single_dev_port_range_test
+	sanitization_single_dev_tos_static_test
+	sanitization_single_dev_ttl_inherit_test
+	sanitization_single_dev_udp_checksum_test
+}
+
+sanitization_multi_devs_test_pass()
+{
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev vxlan0 master br0
+	check_err $?
+	ip link set dev $swp2 master br1
+	check_err $?
+	ip link set dev vxlan1 master br1
+	check_err $?
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 nomaster
+
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev $swp2 master br1
+	check_err $?
+}
+
+sanitization_multi_devs_test_fail()
+{
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev vxlan0 master br0
+	check_err $?
+	ip link set dev $swp2 master br1
+	check_err $?
+	ip link set dev vxlan1 master br1 &> /dev/null
+	check_fail $?
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 nomaster
+
+	ip link set dev vxlan1 master br1
+	check_err $?
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev $swp2 master br1 &> /dev/null
+	check_fail $?
+}
+
+sanitization_multi_devs_valid_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link add dev br1 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_multi_devs_test_pass
+
+	ip link del dev vxlan1
+	ip link del dev vxlan0
+	ip link del dev br1
+	ip link del dev br0
+
+	log_test "multiple vxlan devices - valid configuration"
+}
+
+sanitization_multi_devs_ttl_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link add dev br1 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+		ttl 40 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_multi_devs_test_fail
+
+	ip link del dev vxlan1
+	ip link del dev vxlan0
+	ip link del dev br1
+	ip link del dev br0
+
+	log_test "multiple vxlan devices with different ttl"
+}
+
+sanitization_multi_devs_udp_dstport_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link add dev br1 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 5789
+
+	sanitization_multi_devs_test_fail
+
+	ip link del dev vxlan1
+	ip link del dev vxlan0
+	ip link del dev br1
+	ip link del dev br0
+
+	log_test "multiple vxlan devices with different udp destination port"
+}
+
+sanitization_multi_devs_local_ip_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link add dev br1 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.2 dstport 4789
+
+	sanitization_multi_devs_test_fail
+
+	ip link del dev vxlan1
+	ip link del dev vxlan0
+	ip link del dev br1
+	ip link del dev br0
+
+	log_test "multiple vxlan devices with different local ip"
+}
+
+sanitization_multi_devs_test()
+{
+	# The device has a single VTEP, which means all the VxLAN devices
+	# we offload must share certain properties such as source IP and
+	# UDP destination port. These tests make sure that we forbid
+	# configurations that violate this limitation
+	sanitization_multi_devs_valid_test
+	sanitization_multi_devs_ttl_test
+	sanitization_multi_devs_udp_dstport_test
+	sanitization_multi_devs_local_ip_test
+}
+
+sanitization_test()
+{
+	sanitization_single_dev_test
+	sanitization_multi_devs_test
+}
+
+offload_indication_setup_create()
+{
+	# Create a simple setup with two bridges, each with a VxLAN device
+	# and one local port
+	ip link add name br0 up type bridge mcast_snooping 0
+	ip link add name br1 up type bridge mcast_snooping 0
+
+	ip link set dev $swp1 master br0
+	ip link set dev $swp2 master br1
+
+	ip address add 198.51.100.1/32 dev lo
+
+	ip link add name vxlan0 up master br0 type vxlan id 10 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up master br1 type vxlan id 20 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+}
+
+offload_indication_setup_destroy()
+{
+	ip link del dev vxlan1
+	ip link del dev vxlan0
+
+	ip address del 198.51.100.1/32 dev lo
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 nomaster
+
+	ip link del dev br1
+	ip link del dev br0
+}
+
+offload_indication_fdb_flood_test()
+{
+	RET=0
+
+	bridge fdb append 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.2
+
+	bridge fdb show brport vxlan0 | grep 00:00:00:00:00:00 \
+		| grep -q offload
+	check_err $?
+
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self
+
+	log_test "vxlan flood entry offload indication"
+}
+
+offload_indication_fdb_bridge_test()
+{
+	RET=0
+
+	bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self master static \
+		dst 198.51.100.2
+
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_err $?
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_err $?
+
+	log_test "vxlan entry offload indication - initial state"
+
+	# Remove FDB entry from the bridge driver and check that corresponding
+	# entry in the VxLAN driver is not marked as offloaded
+	RET=0
+
+	bridge fdb del de:ad:be:ef:13:37 dev vxlan0 master
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_fail $?
+
+	log_test "vxlan entry offload indication - after removal from bridge"
+
+	# Add the FDB entry back to the bridge driver and make sure it is
+	# marked as offloaded in both drivers
+	RET=0
+
+	bridge fdb add de:ad:be:ef:13:37 dev vxlan0 master static
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_err $?
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_err $?
+
+	log_test "vxlan entry offload indication - after re-add to bridge"
+
+	# Remove FDB entry from the VxLAN driver and check that corresponding
+	# entry in the bridge driver is not marked as offloaded
+	RET=0
+
+	bridge fdb del de:ad:be:ef:13:37 dev vxlan0 self
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_fail $?
+
+	log_test "vxlan entry offload indication - after removal from vxlan"
+
+	# Add the FDB entry back to the VxLAN driver and make sure it is
+	# marked as offloaded in both drivers
+	RET=0
+
+	bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self dst 198.51.100.2
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_err $?
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_err $?
+
+	log_test "vxlan entry offload indication - after re-add to vxlan"
+
+	bridge fdb del de:ad:be:ef:13:37 dev vxlan0 self master
+}
+
+offload_indication_fdb_test()
+{
+	offload_indication_fdb_flood_test
+	offload_indication_fdb_bridge_test
+}
+
+offload_indication_decap_route_test()
+{
+	RET=0
+
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link set dev vxlan0 down
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link set dev vxlan1 down
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_fail $?
+
+	log_test "vxlan decap route - vxlan device down"
+
+	RET=0
+
+	ip link set dev vxlan1 up
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link set dev vxlan0 up
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	log_test "vxlan decap route - vxlan device up"
+
+	RET=0
+
+	ip address delete 198.51.100.1/32 dev lo
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_fail $?
+
+	ip address add 198.51.100.1/32 dev lo
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	log_test "vxlan decap route - add local route"
+
+	RET=0
+
+	ip link set dev $swp1 nomaster
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link set dev $swp2 nomaster
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_fail $?
+
+	ip link set dev $swp1 master br0
+	ip link set dev $swp2 master br1
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	log_test "vxlan decap route - local ports enslavement"
+
+	RET=0
+
+	ip link del dev br0
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link del dev br1
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_fail $?
+
+	log_test "vxlan decap route - bridge device deletion"
+
+	RET=0
+
+	ip link add name br0 up type bridge mcast_snooping 0
+	ip link add name br1 up type bridge mcast_snooping 0
+	ip link set dev $swp1 master br0
+	ip link set dev $swp2 master br1
+	ip link set dev vxlan0 master br0
+	ip link set dev vxlan1 master br1
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link del dev vxlan0
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link del dev vxlan1
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_fail $?
+
+	log_test "vxlan decap route - vxlan device deletion"
+
+	ip link add name vxlan0 up master br0 type vxlan id 10 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up master br1 type vxlan id 20 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+}
+
+offload_indication_test()
+{
+	offload_indication_setup_create
+	offload_indication_fdb_test
+	offload_indication_decap_route_test
+	offload_indication_setup_destroy
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 94d302deae25a0925dc736e444005918522be730 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:27 +0000
Subject: selftests: mlxsw: Add a test for VxLAN flooding

The device stores flood records in a singly linked list where each
record stores up to three IPv4 addresses of remote VTEPs. The test
verifies that packets are correctly flooded in various cases such as
deletion of a record in the middle of the list.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/vxlan_flooding.sh  | 309 +++++++++++++++++++++
 1 file changed, 309 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
new file mode 100755
index 000000000000..fedcb7b35af9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
@@ -0,0 +1,309 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test VxLAN flooding. The device stores flood records in a singly linked list
+# where each record stores up to three IPv4 addresses of remote VTEPs. The test
+# verifies that packets are correctly flooded in various cases such as deletion
+# of a record in the middle of the list.
+#
+# +--------------------+
+# | H1 (vrf)           |
+# |    + $h1           |
+# |    | 203.0.113.1/24|
+# +----|---------------+
+#      |
+# +----|----------------------------------------------------------------------+
+# | SW |                                                                      |
+# | +--|--------------------------------------------------------------------+ |
+# | |  + $swp1                   BR0 (802.1d)                               | |
+# | |                                                                       | |
+# | |  + vxlan0 (vxlan)                                                     | |
+# | |    local 198.51.100.1                                                 | |
+# | |    remote 198.51.100.{2..13}                                          | |
+# | |    id 10 dstport 4789                                                 | |
+# | +-----------------------------------------------------------------------+ |
+# |                                                                           |
+# |  198.51.100.0/24 via 192.0.2.2                                            |
+# |                                                                           |
+# |    + $rp1                                                                 |
+# |    | 192.0.2.1/24                                                         |
+# +----|----------------------------------------------------------------------+
+#      |
+# +----|--------------------------------------------------------+
+# |    |                                               R2 (vrf) |
+# |    + $rp2                                                   |
+# |      192.0.2.2/24                                           |
+# |                                                             |
+# +-------------------------------------------------------------+
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="flooding_test"
+NUM_NETIFS=4
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 203.0.113.1/24
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 203.0.113.1/24
+}
+
+switch_create()
+{
+	# Make sure the bridge uses the MAC address of the local port and
+	# not that of the VxLAN's device
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link set dev br0 address $(mac_get $swp1)
+
+	ip link add name vxlan0 type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	ip address add 198.51.100.1/32 dev lo
+
+	ip link set dev $swp1 master br0
+	ip link set dev vxlan0 master br0
+
+	ip link set dev br0 up
+	ip link set dev $swp1 up
+	ip link set dev vxlan0 up
+}
+
+switch_destroy()
+{
+	ip link set dev vxlan0 down
+	ip link set dev $swp1 down
+	ip link set dev br0 down
+
+	ip link set dev vxlan0 nomaster
+	ip link set dev $swp1 nomaster
+
+	ip address del 198.51.100.1/32 dev lo
+
+	ip link del dev vxlan0
+
+	ip link del dev br0
+}
+
+router1_create()
+{
+	# This router is in the default VRF, where the VxLAN device is
+	# performing the L3 lookup
+	ip link set dev $rp1 up
+	ip address add 192.0.2.1/24 dev $rp1
+	ip route add 198.51.100.0/24 via 192.0.2.2
+}
+
+router1_destroy()
+{
+	ip route del 198.51.100.0/24 via 192.0.2.2
+	ip address del 192.0.2.1/24 dev $rp1
+	ip link set dev $rp1 down
+}
+
+router2_create()
+{
+	# This router is not in the default VRF, so use simple_if_init()
+	simple_if_init $rp2 192.0.2.2/24
+}
+
+router2_destroy()
+{
+	simple_if_fini $rp2 192.0.2.2/24
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	rp1=${NETIFS[p3]}
+	rp2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+
+	switch_create
+
+	router1_create
+	router2_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router2_destroy
+	router1_destroy
+
+	switch_destroy
+
+	h1_destroy
+
+	vrf_cleanup
+}
+
+flooding_remotes_add()
+{
+	local num_remotes=$1
+	local lsb
+	local i
+
+	for i in $(eval echo {1..$num_remotes}); do
+		lsb=$((i + 1))
+
+		bridge fdb append 00:00:00:00:00:00 dev vxlan0 self \
+			dst 198.51.100.$lsb
+	done
+}
+
+flooding_filters_add()
+{
+	local num_remotes=$1
+	local lsb
+	local i
+
+	tc qdisc add dev $rp2 clsact
+
+	for i in $(eval echo {1..$num_remotes}); do
+		lsb=$((i + 1))
+
+		tc filter add dev $rp2 ingress protocol ip pref $i handle $i \
+			flower ip_proto udp dst_ip 198.51.100.$lsb \
+			dst_port 4789 skip_sw action drop
+	done
+}
+
+flooding_filters_del()
+{
+	local num_remotes=$1
+	local i
+
+	for i in $(eval echo {1..$num_remotes}); do
+		tc filter del dev $rp2 ingress protocol ip pref $i \
+			handle $i flower
+	done
+
+	tc qdisc del dev $rp2 clsact
+}
+
+flooding_check_packets()
+{
+	local packets=("$@")
+	local num_remotes=${#packets[@]}
+	local i
+
+	for i in $(eval echo {1..$num_remotes}); do
+		tc_check_packets "dev $rp2 ingress" $i ${packets[i - 1]}
+		check_err $? "remote $i - did not get expected number of packets"
+	done
+}
+
+flooding_test()
+{
+	# Use 12 remote VTEPs that will be stored in 4 records. The array
+	# 'packets' will store how many packets are expected to be received
+	# by each remote VTEP at each stage of the test
+	declare -a packets=(1 1 1 1 1 1 1 1 1 1 1 1)
+	local num_remotes=12
+
+	RET=0
+
+	# Add FDB entries for remote VTEPs and corresponding tc filters on the
+	# ingress of the nexthop router. These filters will count how many
+	# packets were flooded to each remote VTEP
+	flooding_remotes_add $num_remotes
+	flooding_filters_add $num_remotes
+
+	# Send one packet and make sure it is flooded to all the remote VTEPs
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 1 packet"
+
+	# Delete the third record which corresponds to VTEPs with LSB 8..10
+	# and check that packet is flooded correctly when we remove a record
+	# from the middle of the list
+	RET=0
+
+	packets=(2 2 2 2 2 2 1 1 1 2 2 2)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.8
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.9
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.10
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 2 packets"
+
+	# Delete the first record and make sure the packet is flooded correctly
+	RET=0
+
+	packets=(2 2 2 3 3 3 1 1 1 3 3 3)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.2
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.3
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.4
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 3 packets"
+
+	# Delete the last record and make sure the packet is flooded correctly
+	RET=0
+
+	packets=(2 2 2 4 4 4 1 1 1 3 3 3)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.11
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.12
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.13
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 4 packets"
+
+	# Delete the last record, one entry at a time and make sure single
+	# entries are correctly removed
+	RET=0
+
+	packets=(2 2 2 4 5 5 1 1 1 3 3 3)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.5
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 5 packets"
+
+	RET=0
+
+	packets=(2 2 2 4 5 6 1 1 1 3 3 3)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.6
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 6 packets"
+
+	RET=0
+
+	packets=(2 2 2 4 5 6 1 1 1 3 3 3)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.7
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 7 packets"
+
+	flooding_filters_del $num_remotes
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From e432abfb99e5642a7e7fcaa1c8cb0e80c8fcf58e Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Mon, 19 Nov 2018 21:02:15 +0800
Subject: net: hns3: add common validation in hclge_dcb

Before setting tm related configuration to hardware, driver
needs to check the configuration provided by user is valid.
Currently hclge_ieee_setets and hclge_setup_tc both implement
their own checking, which has a lot in common.

This patch addes hclge_dcb_common_validate to do the common
checking. The checking in hclge_tm_prio_tc_info_update
and hclge_tm_schd_info_update is unnecessary now, so change
the return type to void, which removes the need to do error
handling when one of the checking fails.

Also, ets->prio_tc is indexed by user prio and ets->tc_tsa is
indexed by tc num, so this patch changes them to use different
index.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Tan Xiaojun <tanxiaojun@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c | 70 +++++++++++++++-------
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c  | 14 +----
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h  |  4 +-
 3 files changed, 53 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index e72f724123d7..f6323b2501dc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -35,7 +35,9 @@ static int hclge_ieee_ets_to_tm_info(struct hclge_dev *hdev,
 		}
 	}
 
-	return hclge_tm_prio_tc_info_update(hdev, ets->prio_tc);
+	hclge_tm_prio_tc_info_update(hdev, ets->prio_tc);
+
+	return 0;
 }
 
 static void hclge_tm_info_to_ieee_ets(struct hclge_dev *hdev,
@@ -70,25 +72,61 @@ static int hclge_ieee_getets(struct hnae3_handle *h, struct ieee_ets *ets)
 	return 0;
 }
 
+static int hclge_dcb_common_validate(struct hclge_dev *hdev, u8 num_tc,
+				     u8 *prio_tc)
+{
+	int i;
+
+	if (num_tc > hdev->tc_max) {
+		dev_err(&hdev->pdev->dev,
+			"tc num checking failed, %u > tc_max(%u)\n",
+			num_tc, hdev->tc_max);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
+		if (prio_tc[i] >= num_tc) {
+			dev_err(&hdev->pdev->dev,
+				"prio_tc[%u] checking failed, %u >= num_tc(%u)\n",
+				i, prio_tc[i], num_tc);
+			return -EINVAL;
+		}
+	}
+
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		if (num_tc > hdev->vport[i].alloc_tqps) {
+			dev_err(&hdev->pdev->dev,
+				"allocated tqp(%u) checking failed, %u > tqp(%u)\n",
+				i, num_tc, hdev->vport[i].alloc_tqps);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
 			      u8 *tc, bool *changed)
 {
 	bool has_ets_tc = false;
 	u32 total_ets_bw = 0;
 	u8 max_tc = 0;
+	int ret;
 	u8 i;
 
-	for (i = 0; i < HNAE3_MAX_TC; i++) {
-		if (ets->prio_tc[i] >= hdev->tc_max ||
-		    i >= hdev->tc_max)
-			return -EINVAL;
-
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
 		if (ets->prio_tc[i] != hdev->tm_info.prio_tc[i])
 			*changed = true;
 
 		if (ets->prio_tc[i] > max_tc)
 			max_tc = ets->prio_tc[i];
+	}
 
+	ret = hclge_dcb_common_validate(hdev, max_tc + 1, ets->prio_tc);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
 		switch (ets->tc_tsa[i]) {
 		case IEEE_8021QAZ_TSA_STRICT:
 			if (hdev->tm_info.tc_info[i].tc_sch_mode !=
@@ -184,9 +222,7 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
 	if (ret)
 		return ret;
 
-	ret = hclge_tm_schd_info_update(hdev, num_tc);
-	if (ret)
-		return ret;
+	hclge_tm_schd_info_update(hdev, num_tc);
 
 	ret = hclge_ieee_ets_to_tm_info(hdev, ets);
 	if (ret)
@@ -305,20 +341,12 @@ static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc)
 	if (hdev->flag & HCLGE_FLAG_DCB_ENABLE)
 		return -EINVAL;
 
-	if (tc > hdev->tc_max) {
-		dev_err(&hdev->pdev->dev,
-			"setup tc failed, tc(%u) > tc_max(%u)\n",
-			tc, hdev->tc_max);
-		return -EINVAL;
-	}
-
-	ret = hclge_tm_schd_info_update(hdev, tc);
+	ret = hclge_dcb_common_validate(hdev, tc, prio_tc);
 	if (ret)
-		return ret;
+		return -EINVAL;
 
-	ret = hclge_tm_prio_tc_info_update(hdev, prio_tc);
-	if (ret)
-		return ret;
+	hclge_tm_schd_info_update(hdev, tc);
+	hclge_tm_prio_tc_info_update(hdev, prio_tc);
 
 	ret = hclge_tm_init_hw(hdev);
 	if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 494e562fe8c7..00458da67503 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -1259,15 +1259,13 @@ int hclge_pause_setup_hw(struct hclge_dev *hdev)
 	return 0;
 }
 
-int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc)
+void hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc)
 {
 	struct hclge_vport *vport = hdev->vport;
 	struct hnae3_knic_private_info *kinfo;
 	u32 i, k;
 
 	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
-		if (prio_tc[i] >= hdev->tm_info.num_tc)
-			return -EINVAL;
 		hdev->tm_info.prio_tc[i] = prio_tc[i];
 
 		for (k = 0;  k < hdev->num_alloc_vport; k++) {
@@ -1275,18 +1273,12 @@ int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc)
 			kinfo->prio_tc[i] = prio_tc[i];
 		}
 	}
-	return 0;
 }
 
-int hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc)
+void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc)
 {
 	u8 i, bit_map = 0;
 
-	for (i = 0; i < hdev->num_alloc_vport; i++) {
-		if (num_tc > hdev->vport[i].alloc_tqps)
-			return -EINVAL;
-	}
-
 	hdev->tm_info.num_tc = num_tc;
 
 	for (i = 0; i < hdev->tm_info.num_tc; i++)
@@ -1300,8 +1292,6 @@ int hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc)
 	hdev->hw_tc_map = bit_map;
 
 	hclge_tm_schd_info_init(hdev);
-
-	return 0;
 }
 
 int hclge_tm_init_hw(struct hclge_dev *hdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 25eef13a3e14..4bd916a77ae2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -131,8 +131,8 @@ struct hclge_port_shapping_cmd {
 int hclge_tm_schd_init(struct hclge_dev *hdev);
 int hclge_pause_setup_hw(struct hclge_dev *hdev);
 int hclge_tm_schd_mode_hw(struct hclge_dev *hdev);
-int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc);
-int hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc);
+void hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc);
+void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc);
 int hclge_tm_dwrr_cfg(struct hclge_dev *hdev);
 int hclge_tm_map_cfg(struct hclge_dev *hdev);
 int hclge_tm_init_hw(struct hclge_dev *hdev);
-- 
cgit v1.2.3


From 3a44820591c276ab74a3bba710742dccc9a39d73 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:37 -0800
Subject: nfp: abm: map per-band symbols

In preparation for multi-band RED offload if FW is capable map
the extended symbols which will allow us to set per-band parameters
and read stats.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/ctrl.c | 56 ++++++++++++++++++++-------
 drivers/net/ethernet/netronome/nfp/abm/main.h | 11 ++++++
 2 files changed, 54 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index 1629b07f727b..d9c5fff97547 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2018 Netronome Systems, Inc. */
 
 #include <linux/kernel.h>
+#include <linux/log2.h>
 
 #include "../nfpcore/nfp_cpp.h"
 #include "../nfpcore/nfp_nffw.h"
@@ -11,13 +12,16 @@
 #include "../nfp_net.h"
 #include "main.h"
 
-#define NFP_QLVL_SYM_NAME	"_abi_nfd_out_q_lvls_%u"
+#define NFP_NUM_PRIOS_SYM_NAME	"_abi_pci_dscp_num_prio_%u"
+#define NFP_NUM_BANDS_SYM_NAME	"_abi_pci_dscp_num_band_%u"
+
+#define NFP_QLVL_SYM_NAME	"_abi_nfd_out_q_lvls_%u%s"
 #define NFP_QLVL_STRIDE		16
 #define NFP_QLVL_BLOG_BYTES	0
 #define NFP_QLVL_BLOG_PKTS	4
 #define NFP_QLVL_THRS		8
 
-#define NFP_QMSTAT_SYM_NAME	"_abi_nfdqm%u_stats"
+#define NFP_QMSTAT_SYM_NAME	"_abi_nfdqm%u_stats%s"
 #define NFP_QMSTAT_STRIDE	32
 #define NFP_QMSTAT_NON_STO	0
 #define NFP_QMSTAT_STO		8
@@ -189,30 +193,56 @@ nfp_abm_ctrl_find_rtsym(struct nfp_pf *pf, const char *name, unsigned int size)
 }
 
 static const struct nfp_rtsym *
-nfp_abm_ctrl_find_q_rtsym(struct nfp_pf *pf, const char *name,
-			  unsigned int size)
+nfp_abm_ctrl_find_q_rtsym(struct nfp_abm *abm, const char *name_fmt,
+			  size_t size)
 {
-	return nfp_abm_ctrl_find_rtsym(pf, name, size * NFP_NET_MAX_RX_RINGS);
+	char pf_symbol[64];
+
+	size = array3_size(size, abm->num_bands, NFP_NET_MAX_RX_RINGS);
+	snprintf(pf_symbol, sizeof(pf_symbol), name_fmt,
+		 abm->pf_id, nfp_abm_has_prio(abm) ? "_per_band" : "");
+
+	return nfp_abm_ctrl_find_rtsym(abm->app->pf, pf_symbol, size);
 }
 
 int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm)
 {
 	struct nfp_pf *pf = abm->app->pf;
 	const struct nfp_rtsym *sym;
-	unsigned int pf_id;
-	char pf_symbol[64];
+	int res;
 
-	pf_id =	nfp_cppcore_pcie_unit(pf->cpp);
-	abm->pf_id = pf_id;
+	abm->pf_id = nfp_cppcore_pcie_unit(pf->cpp);
+
+	/* Read count of prios and prio bands */
+	res = nfp_pf_rtsym_read_optional(pf, NFP_NUM_BANDS_SYM_NAME, 1);
+	if (res < 0)
+		return res;
+	abm->num_bands = res;
+
+	res = nfp_pf_rtsym_read_optional(pf, NFP_NUM_PRIOS_SYM_NAME, 1);
+	if (res < 0)
+		return res;
+	abm->num_prios = res;
+
+	/* Check values are sane, U16_MAX is arbitrarily chosen as max */
+	if (!is_power_of_2(abm->num_bands) || !is_power_of_2(abm->num_prios) ||
+	    abm->num_bands > U16_MAX || abm->num_prios > U16_MAX ||
+	    (abm->num_bands == 1) != (abm->num_prios == 1)) {
+		nfp_err(pf->cpp,
+			"invalid priomap description num bands: %u and num prios: %u\n",
+			abm->num_bands, abm->num_prios);
+		return -EINVAL;
+	}
 
-	snprintf(pf_symbol, sizeof(pf_symbol), NFP_QLVL_SYM_NAME, pf_id);
-	sym = nfp_abm_ctrl_find_q_rtsym(pf, pf_symbol, NFP_QLVL_STRIDE);
+	/* Find level and stat symbols */
+	sym = nfp_abm_ctrl_find_q_rtsym(abm, NFP_QLVL_SYM_NAME,
+					NFP_QLVL_STRIDE);
 	if (IS_ERR(sym))
 		return PTR_ERR(sym);
 	abm->q_lvls = sym;
 
-	snprintf(pf_symbol, sizeof(pf_symbol), NFP_QMSTAT_SYM_NAME, pf_id);
-	sym = nfp_abm_ctrl_find_q_rtsym(pf, pf_symbol, NFP_QMSTAT_STRIDE);
+	sym = nfp_abm_ctrl_find_q_rtsym(abm, NFP_QMSTAT_SYM_NAME,
+					NFP_QMSTAT_STRIDE);
 	if (IS_ERR(sym))
 		return PTR_ERR(sym);
 	abm->qm_stats = sym;
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 240e2c8683fe..b10c067b15c8 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -27,6 +27,9 @@ struct nfp_net;
  * @app:	back pointer to nfp_app
  * @pf_id:	ID of our PF link
  *
+ * @num_prios:	number of supported DSCP priorities
+ * @num_bands:	number of supported DSCP priority bands
+ *
  * @thresholds:		current threshold configuration
  * @threshold_undef:	bitmap of thresholds which have not been set
  * @num_thresholds:	number of @thresholds and bits in @threshold_undef
@@ -40,6 +43,9 @@ struct nfp_abm {
 	struct nfp_app *app;
 	unsigned int pf_id;
 
+	unsigned int num_prios;
+	unsigned int num_bands;
+
 	u32 *thresholds;
 	unsigned long *threshold_undef;
 	size_t num_thresholds;
@@ -166,6 +172,11 @@ struct nfp_abm_link {
 	struct radix_tree_root qdiscs;
 };
 
+static inline bool nfp_abm_has_prio(struct nfp_abm *abm)
+{
+	return abm->num_bands > 1;
+}
+
 void nfp_abm_qdisc_offload_update(struct nfp_abm_link *alink);
 int nfp_abm_setup_root(struct net_device *netdev, struct nfp_abm_link *alink,
 		       struct tc_root_qopt_offload *opt);
-- 
cgit v1.2.3


From 5720769609fbc244c67ccbcf817db44e3fa5f50c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:38 -0800
Subject: nfp: abm: pass band parameter to functions

In preparation for per-band RED offload pass band parameter to
functions.  For now it will always be 0.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/ctrl.c  | 52 ++++++++++++++------------
 drivers/net/ethernet/netronome/nfp/abm/main.h  | 10 +++--
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 30 +++++++--------
 3 files changed, 49 insertions(+), 43 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index d9c5fff97547..8b2598a223de 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -30,23 +30,25 @@
 
 static int
 nfp_abm_ctrl_stat(struct nfp_abm_link *alink, const struct nfp_rtsym *sym,
-		  unsigned int stride, unsigned int offset, unsigned int i,
-		  bool is_u64, u64 *res)
+		  unsigned int stride, unsigned int offset, unsigned int band,
+		  unsigned int queue, bool is_u64, u64 *res)
 {
 	struct nfp_cpp *cpp = alink->abm->app->cpp;
 	u64 val, sym_offset;
+	unsigned int qid;
 	u32 val32;
 	int err;
 
-	sym_offset = (alink->queue_base + i) * stride + offset;
+	qid = band * NFP_NET_MAX_RX_RINGS + alink->queue_base + queue;
+
+	sym_offset = qid * stride + offset;
 	if (is_u64)
 		err = __nfp_rtsym_readq(cpp, sym, 3, 0, sym_offset, &val);
 	else
 		err = __nfp_rtsym_readl(cpp, sym, 3, 0, sym_offset, &val32);
 	if (err) {
-		nfp_err(cpp,
-			"RED offload reading stat failed on vNIC %d queue %d\n",
-			alink->id, i);
+		nfp_err(cpp, "RED offload reading stat failed on vNIC %d band %d queue %d (+ %d)\n",
+			alink->id, band, queue, alink->queue_base);
 		return err;
 	}
 
@@ -77,12 +79,12 @@ int __nfp_abm_ctrl_set_q_lvl(struct nfp_abm *abm, unsigned int id, u32 val)
 	return 0;
 }
 
-int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int queue,
-			   u32 val)
+int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int band,
+			   unsigned int queue, u32 val)
 {
 	unsigned int threshold;
 
-	threshold = alink->queue_base + queue;
+	threshold = band * NFP_NET_MAX_RX_RINGS + alink->queue_base + queue;
 
 	return __nfp_abm_ctrl_set_q_lvl(alink->abm, threshold, val);
 }
@@ -92,7 +94,7 @@ u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int i)
 	u64 val;
 
 	if (nfp_abm_ctrl_stat(alink, alink->abm->qm_stats, NFP_QMSTAT_STRIDE,
-			      NFP_QMSTAT_NON_STO, i, true, &val))
+			      NFP_QMSTAT_NON_STO, 0, i, true, &val))
 		return 0;
 	return val;
 }
@@ -102,56 +104,58 @@ u64 nfp_abm_ctrl_stat_sto(struct nfp_abm_link *alink, unsigned int i)
 	u64 val;
 
 	if (nfp_abm_ctrl_stat(alink, alink->abm->qm_stats, NFP_QMSTAT_STRIDE,
-			      NFP_QMSTAT_STO, i, true, &val))
+			      NFP_QMSTAT_STO, 0, i, true, &val))
 		return 0;
 	return val;
 }
 
-int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink, unsigned int i,
-			      struct nfp_alink_stats *stats)
+int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink, unsigned int band,
+			      unsigned int queue, struct nfp_alink_stats *stats)
 {
 	int err;
 
-	stats->tx_pkts = nn_readq(alink->vnic, NFP_NET_CFG_RXR_STATS(i));
-	stats->tx_bytes = nn_readq(alink->vnic, NFP_NET_CFG_RXR_STATS(i) + 8);
+	stats->tx_pkts += nn_readq(alink->vnic, NFP_NET_CFG_RXR_STATS(queue));
+	stats->tx_bytes += nn_readq(alink->vnic,
+				    NFP_NET_CFG_RXR_STATS(queue) + 8);
 
-	err = nfp_abm_ctrl_stat(alink, alink->abm->q_lvls,
-				NFP_QLVL_STRIDE, NFP_QLVL_BLOG_BYTES,
-				i, false, &stats->backlog_bytes);
+	err = nfp_abm_ctrl_stat(alink, alink->abm->q_lvls, NFP_QLVL_STRIDE,
+				NFP_QLVL_BLOG_BYTES, band, queue, false,
+				&stats->backlog_bytes);
 	if (err)
 		return err;
 
 	err = nfp_abm_ctrl_stat(alink, alink->abm->q_lvls,
 				NFP_QLVL_STRIDE, NFP_QLVL_BLOG_PKTS,
-				i, false, &stats->backlog_pkts);
+				band, queue, false, &stats->backlog_pkts);
 	if (err)
 		return err;
 
 	err = nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
 				NFP_QMSTAT_STRIDE, NFP_QMSTAT_DROP,
-				i, true, &stats->drops);
+				band, queue, true, &stats->drops);
 	if (err)
 		return err;
 
 	return nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
 				 NFP_QMSTAT_STRIDE, NFP_QMSTAT_ECN,
-				 i, true, &stats->overlimits);
+				 band, queue, true, &stats->overlimits);
 }
 
-int nfp_abm_ctrl_read_q_xstats(struct nfp_abm_link *alink, unsigned int i,
+int nfp_abm_ctrl_read_q_xstats(struct nfp_abm_link *alink,
+			       unsigned int band, unsigned int queue,
 			       struct nfp_alink_xstats *xstats)
 {
 	int err;
 
 	err = nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
 				NFP_QMSTAT_STRIDE, NFP_QMSTAT_DROP,
-				i, true, &xstats->pdrop);
+				band, queue, true, &xstats->pdrop);
 	if (err)
 		return err;
 
 	return nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
 				 NFP_QMSTAT_STRIDE, NFP_QMSTAT_ECN,
-				 i, true, &xstats->ecn_marked);
+				 band, queue, true, &xstats->ecn_marked);
 }
 
 int nfp_abm_ctrl_qm_enable(struct nfp_abm *abm)
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index b10c067b15c8..b18a699dac50 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -188,11 +188,13 @@ int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 void nfp_abm_ctrl_read_params(struct nfp_abm_link *alink);
 int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm);
 int __nfp_abm_ctrl_set_q_lvl(struct nfp_abm *abm, unsigned int id, u32 val);
-int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int queue,
-			   u32 val);
-int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink, unsigned int i,
+int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int band,
+			   unsigned int queue, u32 val);
+int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink,
+			      unsigned int band, unsigned int queue,
 			      struct nfp_alink_stats *stats);
-int nfp_abm_ctrl_read_q_xstats(struct nfp_abm_link *alink, unsigned int i,
+int nfp_abm_ctrl_read_q_xstats(struct nfp_abm_link *alink,
+			       unsigned int band, unsigned int queue,
 			       struct nfp_alink_xstats *xstats);
 u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int i);
 u64 nfp_abm_ctrl_stat_sto(struct nfp_abm_link *alink, unsigned int i);
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index 16c4afe3a37f..251ce3070564 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -51,15 +51,15 @@ nfp_abm_stats_update_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
 	if (!qdisc->offloaded)
 		return;
 
-	err = nfp_abm_ctrl_read_q_stats(alink, queue, &qdisc->red.stats);
+	err = nfp_abm_ctrl_read_q_stats(alink, 0, queue, &qdisc->red.stats);
 	if (err)
-		nfp_err(cpp, "RED stats (%d) read failed with error %d\n",
-			queue, err);
+		nfp_err(cpp, "RED stats (%d, %d) read failed with error %d\n",
+			0, queue, err);
 
-	err = nfp_abm_ctrl_read_q_xstats(alink, queue, &qdisc->red.xstats);
+	err = nfp_abm_ctrl_read_q_xstats(alink, 0, queue, &qdisc->red.xstats);
 	if (err)
-		nfp_err(cpp, "RED xstats (%d) read failed with error %d\n",
-			queue, err);
+		nfp_err(cpp, "RED xstats (%d, %d) read failed with error %d\n",
+			0, queue, err);
 }
 
 static void
@@ -126,7 +126,7 @@ nfp_abm_qdisc_offload_stop(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc)
 }
 
 static int
-__nfp_abm_stats_init(struct nfp_abm_link *alink,
+__nfp_abm_stats_init(struct nfp_abm_link *alink, unsigned int band,
 		     unsigned int queue, struct nfp_alink_stats *prev_stats,
 		     struct nfp_alink_xstats *prev_xstats)
 {
@@ -139,19 +139,19 @@ __nfp_abm_stats_init(struct nfp_abm_link *alink,
 	backlog_pkts = prev_stats->backlog_pkts;
 	backlog_bytes = prev_stats->backlog_bytes;
 
-	err = nfp_abm_ctrl_read_q_stats(alink, queue, prev_stats);
+	err = nfp_abm_ctrl_read_q_stats(alink, band, queue, prev_stats);
 	if (err) {
 		nfp_err(alink->abm->app->cpp,
-			"RED stats init (%d) failed with error %d\n",
-			queue, err);
+			"RED stats init (%d, %d) failed with error %d\n",
+			band, queue, err);
 		return err;
 	}
 
-	err = nfp_abm_ctrl_read_q_xstats(alink, queue, prev_xstats);
+	err = nfp_abm_ctrl_read_q_xstats(alink, band, queue, prev_xstats);
 	if (err) {
 		nfp_err(alink->abm->app->cpp,
-			"RED xstats init (%d) failed with error %d\n",
-			queue, err);
+			"RED xstats init (%d, %d) failed with error %d\n",
+			band, queue, err);
 		return err;
 	}
 
@@ -164,7 +164,7 @@ static int
 nfp_abm_stats_init(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
 		   unsigned int queue)
 {
-	return __nfp_abm_stats_init(alink, queue,
+	return __nfp_abm_stats_init(alink, 0, queue,
 				    &qdisc->red.prev_stats,
 				    &qdisc->red.prev_xstats);
 }
@@ -186,7 +186,7 @@ nfp_abm_offload_compile_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
 	if (!qdisc->offload_mark)
 		return;
 
-	nfp_abm_ctrl_set_q_lvl(alink, queue, qdisc->red.threshold);
+	nfp_abm_ctrl_set_q_lvl(alink, 0, queue, qdisc->red.threshold);
 }
 
 static void
-- 
cgit v1.2.3


From 68e9864221cae716680f64ac2832c4bfa50006f0 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:39 -0800
Subject: nfp: abm: size threshold table to account for bands

Make sure the threshold table is large enough to hold information
for all bands.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index a5732d3bd1b7..b21250b95475 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -422,7 +422,7 @@ static int nfp_abm_init(struct nfp_app *app)
 		goto err_free_abm;
 
 	err = -ENOMEM;
-	abm->num_thresholds = NFP_NET_MAX_RX_RINGS;
+	abm->num_thresholds = array_size(abm->num_bands, NFP_NET_MAX_RX_RINGS);
 	abm->threshold_undef = bitmap_zalloc(abm->num_thresholds, GFP_KERNEL);
 	if (!abm->threshold_undef)
 		goto err_free_abm;
@@ -431,7 +431,7 @@ static int nfp_abm_init(struct nfp_app *app)
 				   sizeof(*abm->thresholds), GFP_KERNEL);
 	if (!abm->thresholds)
 		goto err_free_thresh_umap;
-	for (i = 0; i < NFP_NET_MAX_RX_RINGS; i++)
+	for (i = 0; i < abm->num_bands * NFP_NET_MAX_RX_RINGS; i++)
 		__nfp_abm_ctrl_set_q_lvl(abm, i, NFP_ABM_LVL_INFINITY);
 
 	/* We start in legacy mode, make sure advanced queuing is disabled */
-- 
cgit v1.2.3


From 57f31bbaa9c1576118c020aef67ca9de97f14392 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:40 -0800
Subject: nfp: abm: switch to extended stats for reading packet/byte counts

In PRIO-enabled FW read the statistics from per-band symbol, rather
than from the standard per-PCIe-queue counters.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/ctrl.c | 47 +++++++++++++++++++++++++--
 drivers/net/ethernet/netronome/nfp/abm/main.h |  2 ++
 2 files changed, 46 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index 8b2598a223de..013ba6c85d2b 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -28,6 +28,11 @@
 #define NFP_QMSTAT_DROP		16
 #define NFP_QMSTAT_ECN		24
 
+#define NFP_Q_STAT_SYM_NAME	"_abi_nfd_rxq_stats%u%s"
+#define NFP_Q_STAT_STRIDE	16
+#define NFP_Q_STAT_PKTS		0
+#define NFP_Q_STAT_BYTES	8
+
 static int
 nfp_abm_ctrl_stat(struct nfp_abm_link *alink, const struct nfp_rtsym *sym,
 		  unsigned int stride, unsigned int offset, unsigned int band,
@@ -109,14 +114,42 @@ u64 nfp_abm_ctrl_stat_sto(struct nfp_abm_link *alink, unsigned int i)
 	return val;
 }
 
+static int
+nfp_abm_ctrl_stat_basic(struct nfp_abm_link *alink, unsigned int band,
+			unsigned int queue, unsigned int off, u64 *val)
+{
+	if (!nfp_abm_has_prio(alink->abm)) {
+		if (!band) {
+			unsigned int id = alink->queue_base + queue;
+
+			*val = nn_readq(alink->vnic,
+					NFP_NET_CFG_RXR_STATS(id) + off);
+		} else {
+			*val = 0;
+		}
+
+		return 0;
+	} else {
+		return nfp_abm_ctrl_stat(alink, alink->abm->q_stats,
+					 NFP_Q_STAT_STRIDE, off, band, queue,
+					 true, val);
+	}
+}
+
 int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink, unsigned int band,
 			      unsigned int queue, struct nfp_alink_stats *stats)
 {
 	int err;
 
-	stats->tx_pkts += nn_readq(alink->vnic, NFP_NET_CFG_RXR_STATS(queue));
-	stats->tx_bytes += nn_readq(alink->vnic,
-				    NFP_NET_CFG_RXR_STATS(queue) + 8);
+	err = nfp_abm_ctrl_stat_basic(alink, band, queue, NFP_Q_STAT_PKTS,
+				      &stats->tx_pkts);
+	if (err)
+		return err;
+
+	err = nfp_abm_ctrl_stat_basic(alink, band, queue, NFP_Q_STAT_BYTES,
+				      &stats->tx_bytes);
+	if (err)
+		return err;
 
 	err = nfp_abm_ctrl_stat(alink, alink->abm->q_lvls, NFP_QLVL_STRIDE,
 				NFP_QLVL_BLOG_BYTES, band, queue, false,
@@ -251,5 +284,13 @@ int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm)
 		return PTR_ERR(sym);
 	abm->qm_stats = sym;
 
+	if (nfp_abm_has_prio(abm)) {
+		sym = nfp_abm_ctrl_find_q_rtsym(abm, NFP_Q_STAT_SYM_NAME,
+						NFP_Q_STAT_STRIDE);
+		if (IS_ERR(sym))
+			return PTR_ERR(sym);
+		abm->q_stats = sym;
+	}
+
 	return 0;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index b18a699dac50..054228c29184 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -38,6 +38,7 @@ struct nfp_net;
  *			in switchdev mode
  * @q_lvls:	queue level control area
  * @qm_stats:	queue statistics symbol
+ * @q_stats:	basic queue statistics (only in per-band case)
  */
 struct nfp_abm {
 	struct nfp_app *app;
@@ -53,6 +54,7 @@ struct nfp_abm {
 	enum devlink_eswitch_mode eswitch_mode;
 	const struct nfp_rtsym *q_lvls;
 	const struct nfp_rtsym *qm_stats;
+	const struct nfp_rtsym *q_stats;
 };
 
 /**
-- 
cgit v1.2.3


From 184ec856cad966688e98072a1a7edae6af5d23f3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:41 -0800
Subject: nfp: abm: add up bands for sto/non-sto stats

Add up stats for all bands for the extra ethtool statistics.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/ctrl.c | 36 ++++++++++++++++++---------
 1 file changed, 24 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index 013ba6c85d2b..10a571b5b565 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -94,24 +94,36 @@ int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int band,
 	return __nfp_abm_ctrl_set_q_lvl(alink->abm, threshold, val);
 }
 
-u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int i)
+u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int queue)
 {
-	u64 val;
+	unsigned int band;
+	u64 val, sum = 0;
+
+	for (band = 0; band < alink->abm->num_bands; band++) {
+		if (nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
+				      NFP_QMSTAT_STRIDE, NFP_QMSTAT_NON_STO,
+				      band, queue, true, &val))
+			return 0;
+		sum += val;
+	}
 
-	if (nfp_abm_ctrl_stat(alink, alink->abm->qm_stats, NFP_QMSTAT_STRIDE,
-			      NFP_QMSTAT_NON_STO, 0, i, true, &val))
-		return 0;
-	return val;
+	return sum;
 }
 
-u64 nfp_abm_ctrl_stat_sto(struct nfp_abm_link *alink, unsigned int i)
+u64 nfp_abm_ctrl_stat_sto(struct nfp_abm_link *alink, unsigned int queue)
 {
-	u64 val;
+	unsigned int band;
+	u64 val, sum = 0;
+
+	for (band = 0; band < alink->abm->num_bands; band++) {
+		if (nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
+				      NFP_QMSTAT_STRIDE, NFP_QMSTAT_STO,
+				      band, queue, true, &val))
+			return 0;
+		sum += val;
+	}
 
-	if (nfp_abm_ctrl_stat(alink, alink->abm->qm_stats, NFP_QMSTAT_STRIDE,
-			      NFP_QMSTAT_STO, 0, i, true, &val))
-		return 0;
-	return val;
+	return sum;
 }
 
 static int
-- 
cgit v1.2.3


From 890d8d23ec3c9eca847be0593c0cf5f650b97271 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:42 -0800
Subject: net: sched: gred: add basic Qdisc offload

Add basic offload for the GRED Qdisc.  Inform the drivers any
time Qdisc or virtual queue configuration changes.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  1 +
 include/net/pkt_cls.h     | 36 ++++++++++++++++++++++++++++++++++++
 net/sched/sch_gred.c      | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 84 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 086e64d88597..4b4207ebd5c0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -846,6 +846,7 @@ enum tc_setup_type {
 	TC_SETUP_QDISC_MQ,
 	TC_SETUP_QDISC_ETF,
 	TC_SETUP_ROOT_QDISC,
+	TC_SETUP_QDISC_GRED,
 };
 
 /* These structures hold the attributes of bpf state that are being passed
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index c497ada7f591..c9198797aaed 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -868,6 +868,42 @@ struct tc_red_qopt_offload {
 	};
 };
 
+enum tc_gred_command {
+	TC_GRED_REPLACE,
+	TC_GRED_DESTROY,
+};
+
+struct tc_gred_vq_qopt_offload_params {
+	bool present;
+	u32 limit;
+	u32 prio;
+	u32 min;
+	u32 max;
+	bool is_ecn;
+	bool is_harddrop;
+	u32 probability;
+	/* Only need backlog, see struct tc_prio_qopt_offload_params */
+	u32 *backlog;
+};
+
+struct tc_gred_qopt_offload_params {
+	bool grio_on;
+	bool wred_on;
+	unsigned int dp_cnt;
+	unsigned int dp_def;
+	struct gnet_stats_queue *qstats;
+	struct tc_gred_vq_qopt_offload_params tab[MAX_DPs];
+};
+
+struct tc_gred_qopt_offload {
+	enum tc_gred_command command;
+	u32 handle;
+	u32 parent;
+	union {
+		struct tc_gred_qopt_offload_params set;
+	};
+};
+
 enum tc_prio_command {
 	TC_PRIO_REPLACE,
 	TC_PRIO_DESTROY,
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 8b8c325f48bc..908c9d1dfdf8 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
+#include <net/pkt_cls.h>
 #include <net/pkt_sched.h>
 #include <net/red.h>
 
@@ -311,6 +312,48 @@ static void gred_reset(struct Qdisc *sch)
 	}
 }
 
+static void gred_offload(struct Qdisc *sch, enum tc_gred_command command)
+{
+	struct gred_sched *table = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct tc_gred_qopt_offload opt = {
+		.command	= command,
+		.handle		= sch->handle,
+		.parent		= sch->parent,
+	};
+
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return;
+
+	if (command == TC_GRED_REPLACE) {
+		unsigned int i;
+
+		opt.set.grio_on = gred_rio_mode(table);
+		opt.set.wred_on = gred_wred_mode(table);
+		opt.set.dp_cnt = table->DPs;
+		opt.set.dp_def = table->def;
+
+		for (i = 0; i < table->DPs; i++) {
+			struct gred_sched_data *q = table->tab[i];
+
+			if (!q)
+				continue;
+			opt.set.tab[i].present = true;
+			opt.set.tab[i].limit = q->limit;
+			opt.set.tab[i].prio = q->prio;
+			opt.set.tab[i].min = q->parms.qth_min >> q->parms.Wlog;
+			opt.set.tab[i].max = q->parms.qth_max >> q->parms.Wlog;
+			opt.set.tab[i].is_ecn = gred_use_ecn(q);
+			opt.set.tab[i].is_harddrop = gred_use_harddrop(q);
+			opt.set.tab[i].probability = q->parms.max_P;
+			opt.set.tab[i].backlog = &q->backlog;
+		}
+		opt.set.qstats = &sch->qstats;
+	}
+
+	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_GRED, &opt);
+}
+
 static inline void gred_destroy_vq(struct gred_sched_data *q)
 {
 	kfree(q);
@@ -385,6 +428,7 @@ static int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps,
 		}
 	}
 
+	gred_offload(sch, TC_GRED_REPLACE);
 	return 0;
 }
 
@@ -630,6 +674,8 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 
 	sch_tree_unlock(sch);
 	kfree(prealloc);
+
+	gred_offload(sch, TC_GRED_REPLACE);
 	return 0;
 
 err_unlock_free:
@@ -815,6 +861,7 @@ static void gred_destroy(struct Qdisc *sch)
 		if (table->tab[i])
 			gred_destroy_vq(table->tab[i]);
 	}
+	gred_offload(sch, TC_GRED_DESTROY);
 }
 
 static struct Qdisc_ops gred_qdisc_ops __read_mostly = {
-- 
cgit v1.2.3


From e49efd5288bd6670cc05860fe04ef611c3887399 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:43 -0800
Subject: net: sched: gred: support reporting stats from offloads

Allow drivers which offload GRED to report back statistics.  Since
A lot of GRED stats is fairly ad hoc in nature pass to drivers the
standard struct gnet_stats_basic/gnet_stats_queue pairs, and
untangle the values in the core.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h |  8 ++++++++
 net/sched/sch_gred.c  | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index c9198797aaed..d0e9a8091426 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -871,6 +871,7 @@ struct tc_red_qopt_offload {
 enum tc_gred_command {
 	TC_GRED_REPLACE,
 	TC_GRED_DESTROY,
+	TC_GRED_STATS,
 };
 
 struct tc_gred_vq_qopt_offload_params {
@@ -895,12 +896,19 @@ struct tc_gred_qopt_offload_params {
 	struct tc_gred_vq_qopt_offload_params tab[MAX_DPs];
 };
 
+struct tc_gred_qopt_offload_stats {
+	struct gnet_stats_basic_packed bstats[MAX_DPs];
+	struct gnet_stats_queue qstats[MAX_DPs];
+	struct red_stats *xstats[MAX_DPs];
+};
+
 struct tc_gred_qopt_offload {
 	enum tc_gred_command command;
 	u32 handle;
 	u32 parent;
 	union {
 		struct tc_gred_qopt_offload_params set;
+		struct tc_gred_qopt_offload_stats stats;
 	};
 };
 
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 908c9d1dfdf8..234afbf9115b 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -354,6 +354,50 @@ static void gred_offload(struct Qdisc *sch, enum tc_gred_command command)
 	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_GRED, &opt);
 }
 
+static int gred_offload_dump_stats(struct Qdisc *sch)
+{
+	struct gred_sched *table = qdisc_priv(sch);
+	struct tc_gred_qopt_offload *hw_stats;
+	unsigned int i;
+	int ret;
+
+	hw_stats = kzalloc(sizeof(*hw_stats), GFP_KERNEL);
+	if (!hw_stats)
+		return -ENOMEM;
+
+	hw_stats->command = TC_GRED_STATS;
+	hw_stats->handle = sch->handle;
+	hw_stats->parent = sch->parent;
+
+	for (i = 0; i < MAX_DPs; i++)
+		if (table->tab[i])
+			hw_stats->stats.xstats[i] = &table->tab[i]->stats;
+
+	ret = qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_GRED, hw_stats);
+	/* Even if driver returns failure adjust the stats - in case offload
+	 * ended but driver still wants to adjust the values.
+	 */
+	for (i = 0; i < MAX_DPs; i++) {
+		if (!table->tab[i])
+			continue;
+		table->tab[i]->packetsin += hw_stats->stats.bstats[i].packets;
+		table->tab[i]->bytesin += hw_stats->stats.bstats[i].bytes;
+		table->tab[i]->backlog += hw_stats->stats.qstats[i].backlog;
+
+		_bstats_update(&sch->bstats,
+			       hw_stats->stats.bstats[i].bytes,
+			       hw_stats->stats.bstats[i].packets);
+		sch->qstats.qlen += hw_stats->stats.qstats[i].qlen;
+		sch->qstats.backlog += hw_stats->stats.qstats[i].backlog;
+		sch->qstats.drops += hw_stats->stats.qstats[i].drops;
+		sch->qstats.requeues += hw_stats->stats.qstats[i].requeues;
+		sch->qstats.overlimits += hw_stats->stats.qstats[i].overlimits;
+	}
+
+	kfree(hw_stats);
+	return ret;
+}
+
 static inline void gred_destroy_vq(struct gred_sched_data *q)
 {
 	kfree(q);
@@ -725,6 +769,9 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
 		.flags	= table->red_flags,
 	};
 
+	if (gred_offload_dump_stats(sch))
+		goto nla_put_failure;
+
 	opts = nla_nest_start(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
-- 
cgit v1.2.3


From 990b50a53ad80fe4e0357c7cc41a393eea2b0d76 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:44 -0800
Subject: nfp: abm: wrap RED parameters in bands

Wrap RED parameters and stats into a structure, and a 1-element
array.  Upcoming GRED offload will add the support for more bands.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.h  | 26 +++++---
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 88 +++++++++++++++++---------
 2 files changed, 74 insertions(+), 40 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 054228c29184..47888288a706 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -112,11 +112,13 @@ enum nfp_qdisc_type {
  * @mq.prev_stats:	previously reported @mq.stats
  *
  * @red:		RED Qdisc specific parameters and state
- * @red.threshold:	ECN marking threshold
- * @red.stats:		current stats of the RED Qdisc
- * @red.prev_stats:	previously reported @red.stats
- * @red.xstats:		extended stats for RED - current
- * @red.prev_xstats:	extended stats for RED - previously reported
+ * @red.num_bands:	Number of valid entries in the @red.band table
+ * @red.band:		Per-band array of RED instances
+ * @red.band.threshold:		ECN marking threshold
+ * @red.band.stats:		current stats of the RED Qdisc
+ * @red.band.prev_stats:	previously reported @red.stats
+ * @red.band.xstats:		extended stats for RED - current
+ * @red.band.prev_xstats:	extended stats for RED - previously reported
  */
 struct nfp_qdisc {
 	struct net_device *netdev;
@@ -139,11 +141,15 @@ struct nfp_qdisc {
 		} mq;
 		/* TC_SETUP_QDISC_RED */
 		struct {
-			u32 threshold;
-			struct nfp_alink_stats stats;
-			struct nfp_alink_stats prev_stats;
-			struct nfp_alink_xstats xstats;
-			struct nfp_alink_xstats prev_xstats;
+			unsigned int num_bands;
+
+			struct {
+				u32 threshold;
+				struct nfp_alink_stats stats;
+				struct nfp_alink_stats prev_stats;
+				struct nfp_alink_xstats xstats;
+				struct nfp_alink_xstats prev_xstats;
+			} band[1];
 		} red;
 	};
 };
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index 251ce3070564..b65b3177c94a 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -46,20 +46,25 @@ nfp_abm_stats_update_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
 			 unsigned int queue)
 {
 	struct nfp_cpp *cpp = alink->abm->app->cpp;
+	unsigned int i;
 	int err;
 
 	if (!qdisc->offloaded)
 		return;
 
-	err = nfp_abm_ctrl_read_q_stats(alink, 0, queue, &qdisc->red.stats);
-	if (err)
-		nfp_err(cpp, "RED stats (%d, %d) read failed with error %d\n",
-			0, queue, err);
-
-	err = nfp_abm_ctrl_read_q_xstats(alink, 0, queue, &qdisc->red.xstats);
-	if (err)
-		nfp_err(cpp, "RED xstats (%d, %d) read failed with error %d\n",
-			0, queue, err);
+	for (i = 0; i < qdisc->red.num_bands; i++) {
+		err = nfp_abm_ctrl_read_q_stats(alink, i, queue,
+						&qdisc->red.band[i].stats);
+		if (err)
+			nfp_err(cpp, "RED stats (%d, %d) read failed with error %d\n",
+				i, queue, err);
+
+		err = nfp_abm_ctrl_read_q_xstats(alink, i, queue,
+						 &qdisc->red.band[i].xstats);
+		if (err)
+			nfp_err(cpp, "RED xstats (%d, %d) read failed with error %d\n",
+				i, queue, err);
+	}
 }
 
 static void
@@ -113,6 +118,8 @@ nfp_abm_qdisc_unlink_children(struct nfp_qdisc *qdisc,
 static void
 nfp_abm_qdisc_offload_stop(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc)
 {
+	unsigned int i;
+
 	/* Don't complain when qdisc is getting unlinked */
 	if (qdisc->use_cnt)
 		nfp_warn(alink->abm->app->cpp, "Offload of '%08x' stopped\n",
@@ -121,8 +128,10 @@ nfp_abm_qdisc_offload_stop(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc)
 	if (!nfp_abm_qdisc_is_red(qdisc))
 		return;
 
-	qdisc->red.stats.backlog_pkts = 0;
-	qdisc->red.stats.backlog_bytes = 0;
+	for (i = 0; i < qdisc->red.num_bands; i++) {
+		qdisc->red.band[i].stats.backlog_pkts = 0;
+		qdisc->red.band[i].stats.backlog_bytes = 0;
+	}
 }
 
 static int
@@ -164,15 +173,26 @@ static int
 nfp_abm_stats_init(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
 		   unsigned int queue)
 {
-	return __nfp_abm_stats_init(alink, 0, queue,
-				    &qdisc->red.prev_stats,
-				    &qdisc->red.prev_xstats);
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < qdisc->red.num_bands; i++) {
+		err = __nfp_abm_stats_init(alink, i, queue,
+					   &qdisc->red.band[i].prev_stats,
+					   &qdisc->red.band[i].prev_xstats);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 static void
 nfp_abm_offload_compile_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
 			    unsigned int queue)
 {
+	unsigned int i;
+
 	qdisc->offload_mark = qdisc->type == NFP_QDISC_RED &&
 			      qdisc->params_ok &&
 			      qdisc->use_cnt == 1 &&
@@ -186,7 +206,9 @@ nfp_abm_offload_compile_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
 	if (!qdisc->offload_mark)
 		return;
 
-	nfp_abm_ctrl_set_q_lvl(alink, 0, queue, qdisc->red.threshold);
+	for (i = 0; i < alink->abm->num_bands; i++)
+		nfp_abm_ctrl_set_q_lvl(alink, i, queue,
+				       qdisc->red.band[i].threshold);
 }
 
 static void
@@ -217,8 +239,10 @@ void nfp_abm_qdisc_offload_update(struct nfp_abm_link *alink)
 	size_t i;
 
 	/* Mark all thresholds as unconfigured */
-	__bitmap_set(abm->threshold_undef,
-		     alink->queue_base, alink->total_queues);
+	for (i = 0; i < abm->num_bands; i++)
+		__bitmap_set(abm->threshold_undef,
+			     i * NFP_NET_MAX_RX_RINGS + alink->queue_base,
+			     alink->total_queues);
 
 	/* Clear offload marks */
 	radix_tree_for_each_slot(slot, &alink->qdiscs, &iter, 0) {
@@ -451,10 +475,10 @@ nfp_abm_red_xstats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
 	if (!qdisc || !qdisc->offloaded)
 		return -EOPNOTSUPP;
 
-	nfp_abm_stats_red_calculate(&qdisc->red.xstats,
-				    &qdisc->red.prev_xstats,
+	nfp_abm_stats_red_calculate(&qdisc->red.band[0].xstats,
+				    &qdisc->red.band[0].prev_xstats,
 				    opt->xstats);
-	qdisc->red.prev_xstats = qdisc->red.xstats;
+	qdisc->red.band[0].prev_xstats = qdisc->red.band[0].xstats;
 	return 0;
 }
 
@@ -473,10 +497,10 @@ nfp_abm_red_stats(struct nfp_abm_link *alink, u32 handle,
 	 * counters back so carry on even if qdisc is not currently offloaded.
 	 */
 
-	nfp_abm_stats_calculate(&qdisc->red.stats,
-				&qdisc->red.prev_stats,
+	nfp_abm_stats_calculate(&qdisc->red.band[0].stats,
+				&qdisc->red.band[0].prev_stats,
 				stats->bstats, stats->qstats);
-	qdisc->red.prev_stats = qdisc->red.stats;
+	qdisc->red.band[0].prev_stats = qdisc->red.band[0].stats;
 
 	return qdisc->offloaded ? 0 : -EOPNOTSUPP;
 }
@@ -538,8 +562,10 @@ nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 	}
 
 	qdisc->params_ok = nfp_abm_red_check_params(alink, opt);
-	if (qdisc->params_ok)
-		qdisc->red.threshold = opt->set.min;
+	if (qdisc->params_ok) {
+		qdisc->red.num_bands = 1;
+		qdisc->red.band[0].threshold = opt->set.min;
+	}
 
 	if (qdisc->use_cnt == 1)
 		nfp_abm_qdisc_offload_update(alink);
@@ -592,7 +618,7 @@ nfp_abm_mq_stats(struct nfp_abm_link *alink, u32 handle,
 		 struct tc_qopt_offload_stats *stats)
 {
 	struct nfp_qdisc *qdisc, *red;
-	unsigned int i;
+	unsigned int i, j;
 
 	qdisc = nfp_abm_qdisc_find(alink, handle);
 	if (!qdisc)
@@ -614,10 +640,12 @@ nfp_abm_mq_stats(struct nfp_abm_link *alink, u32 handle,
 			continue;
 		red = qdisc->children[i];
 
-		nfp_abm_stats_propagate(&qdisc->mq.stats,
-					&red->red.stats);
-		nfp_abm_stats_propagate(&qdisc->mq.prev_stats,
-					&red->red.prev_stats);
+		for (j = 0; j < red->red.num_bands; j++) {
+			nfp_abm_stats_propagate(&qdisc->mq.stats,
+						&red->red.band[j].stats);
+			nfp_abm_stats_propagate(&qdisc->mq.prev_stats,
+						&red->red.band[j].prev_stats);
+		}
 	}
 
 	nfp_abm_stats_calculate(&qdisc->mq.stats, &qdisc->mq.prev_stats,
-- 
cgit v1.2.3


From f3d63720649413ac60f4723f117280391acd5015 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:45 -0800
Subject: nfp: abm: add GRED offload

Add support for GRED offload.  It behaves much like RED, but
can apply different parameters to different bands.  GRED operates
pretty much exactly like our HW/FW with a single FIFO and different
RED state instances.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.c  |   2 +
 drivers/net/ethernet/netronome/nfp/abm/main.h  |  12 +-
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 154 +++++++++++++++++++++++--
 3 files changed, 158 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index b21250b95475..4f95f7b4430b 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -44,6 +44,8 @@ nfp_abm_setup_tc(struct nfp_app *app, struct net_device *netdev,
 		return nfp_abm_setup_tc_mq(netdev, repr->app_priv, type_data);
 	case TC_SETUP_QDISC_RED:
 		return nfp_abm_setup_tc_red(netdev, repr->app_priv, type_data);
+	case TC_SETUP_QDISC_GRED:
+		return nfp_abm_setup_tc_gred(netdev, repr->app_priv, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 47888288a706..6bb4e60c1ad8 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -8,6 +8,7 @@
 #include <linux/radix-tree.h>
 #include <net/devlink.h>
 #include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
 
 /* Dump of 64 PRIOs and 256 REDs seems to take 850us on Xeon v4 @ 2.20GHz;
  * 2.5ms / 400Hz seems more than sufficient for stats resolution.
@@ -89,6 +90,7 @@ enum nfp_qdisc_type {
 	NFP_QDISC_NONE = 0,
 	NFP_QDISC_MQ,
 	NFP_QDISC_RED,
+	NFP_QDISC_GRED,
 };
 
 #define NFP_QDISC_UNTRACKED	((struct nfp_qdisc *)1UL)
@@ -139,7 +141,7 @@ struct nfp_qdisc {
 			struct nfp_alink_stats stats;
 			struct nfp_alink_stats prev_stats;
 		} mq;
-		/* TC_SETUP_QDISC_RED */
+		/* TC_SETUP_QDISC_RED, TC_SETUP_QDISC_GRED */
 		struct {
 			unsigned int num_bands;
 
@@ -149,7 +151,7 @@ struct nfp_qdisc {
 				struct nfp_alink_stats prev_stats;
 				struct nfp_alink_xstats xstats;
 				struct nfp_alink_xstats prev_xstats;
-			} band[1];
+			} band[MAX_DPs];
 		} red;
 	};
 };
@@ -164,6 +166,8 @@ struct nfp_qdisc {
  *
  * @last_stats_update:	ktime of last stats update
  *
+ * @def_band:		default band to use
+ *
  * @root_qdisc:	pointer to the current root of the Qdisc hierarchy
  * @qdiscs:	all qdiscs recorded by major part of the handle
  */
@@ -176,6 +180,8 @@ struct nfp_abm_link {
 
 	u64 last_stats_update;
 
+	u8 def_band;
+
 	struct nfp_qdisc *root_qdisc;
 	struct radix_tree_root qdiscs;
 };
@@ -192,6 +198,8 @@ int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
 			 struct tc_red_qopt_offload *opt);
 int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 			struct tc_mq_qopt_offload *opt);
+int nfp_abm_setup_tc_gred(struct net_device *netdev, struct nfp_abm_link *alink,
+			  struct tc_gred_qopt_offload *opt);
 
 void nfp_abm_ctrl_read_params(struct nfp_abm_link *alink);
 int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm);
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index b65b3177c94a..e80a3d40a48b 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -15,7 +15,7 @@
 
 static bool nfp_abm_qdisc_is_red(struct nfp_qdisc *qdisc)
 {
-	return qdisc->type == NFP_QDISC_RED;
+	return qdisc->type == NFP_QDISC_RED || qdisc->type == NFP_QDISC_GRED;
 }
 
 static bool nfp_abm_qdisc_child_valid(struct nfp_qdisc *qdisc, unsigned int id)
@@ -191,12 +191,17 @@ static void
 nfp_abm_offload_compile_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
 			    unsigned int queue)
 {
+	bool good_red, good_gred;
 	unsigned int i;
 
-	qdisc->offload_mark = qdisc->type == NFP_QDISC_RED &&
-			      qdisc->params_ok &&
-			      qdisc->use_cnt == 1 &&
-			      !qdisc->children[0];
+	good_red = qdisc->type == NFP_QDISC_RED &&
+		   qdisc->params_ok &&
+		   qdisc->use_cnt == 1 &&
+		   !qdisc->children[0];
+	good_gred = qdisc->type == NFP_QDISC_GRED &&
+		    qdisc->params_ok &&
+		    qdisc->use_cnt == 1;
+	qdisc->offload_mark = good_red || good_gred;
 
 	/* If we are starting offload init prev_stats */
 	if (qdisc->offload_mark && !qdisc->offloaded)
@@ -336,9 +341,11 @@ nfp_abm_qdisc_alloc(struct net_device *netdev, struct nfp_abm_link *alink,
 	if (!qdisc)
 		return NULL;
 
-	qdisc->children = kcalloc(children, sizeof(void *), GFP_KERNEL);
-	if (!qdisc->children)
-		goto err_free_qdisc;
+	if (children) {
+		qdisc->children = kcalloc(children, sizeof(void *), GFP_KERNEL);
+		if (!qdisc->children)
+			goto err_free_qdisc;
+	}
 
 	qdisc->netdev = netdev;
 	qdisc->type = type;
@@ -464,6 +471,137 @@ nfp_abm_stats_red_calculate(struct nfp_alink_xstats *new,
 	stats->pdrop += new->pdrop - old->pdrop;
 }
 
+static int
+nfp_abm_gred_stats(struct nfp_abm_link *alink, u32 handle,
+		   struct tc_gred_qopt_offload_stats *stats)
+{
+	struct nfp_qdisc *qdisc;
+	unsigned int i;
+
+	nfp_abm_stats_update(alink);
+
+	qdisc = nfp_abm_qdisc_find(alink, handle);
+	if (!qdisc)
+		return -EOPNOTSUPP;
+	/* If the qdisc offload has stopped we may need to adjust the backlog
+	 * counters back so carry on even if qdisc is not currently offloaded.
+	 */
+
+	for (i = 0; i < qdisc->red.num_bands; i++) {
+		if (!stats->xstats[i])
+			continue;
+
+		nfp_abm_stats_calculate(&qdisc->red.band[i].stats,
+					&qdisc->red.band[i].prev_stats,
+					&stats->bstats[i], &stats->qstats[i]);
+		qdisc->red.band[i].prev_stats = qdisc->red.band[i].stats;
+
+		nfp_abm_stats_red_calculate(&qdisc->red.band[i].xstats,
+					    &qdisc->red.band[i].prev_xstats,
+					    stats->xstats[i]);
+		qdisc->red.band[i].prev_xstats = qdisc->red.band[i].xstats;
+	}
+
+	return qdisc->offloaded ? 0 : -EOPNOTSUPP;
+}
+
+static bool
+nfp_abm_gred_check_params(struct nfp_abm_link *alink,
+			  struct tc_gred_qopt_offload *opt)
+{
+	struct nfp_cpp *cpp = alink->abm->app->cpp;
+	struct nfp_abm *abm = alink->abm;
+	unsigned int i;
+
+	if (opt->set.grio_on || opt->set.wred_on) {
+		nfp_warn(cpp, "GRED offload failed - GRIO and WRED not supported (p:%08x h:%08x)\n",
+			 opt->parent, opt->handle);
+		return false;
+	}
+	if (opt->set.dp_def != alink->def_band) {
+		nfp_warn(cpp, "GRED offload failed - default band must be %d (p:%08x h:%08x)\n",
+			 alink->def_band, opt->parent, opt->handle);
+		return false;
+	}
+	if (opt->set.dp_cnt != abm->num_bands) {
+		nfp_warn(cpp, "GRED offload failed - band count must be %d (p:%08x h:%08x)\n",
+			 abm->num_bands, opt->parent, opt->handle);
+		return false;
+	}
+
+	for (i = 0; i < abm->num_bands; i++) {
+		struct tc_gred_vq_qopt_offload_params *band = &opt->set.tab[i];
+
+		if (!band->present)
+			return false;
+		if (!band->is_ecn) {
+			nfp_warn(cpp, "GRED offload failed - drop is not supported (ECN option required) (p:%08x h:%08x vq:%d)\n",
+				 opt->parent, opt->handle, i);
+			return false;
+		}
+		if (band->is_harddrop) {
+			nfp_warn(cpp, "GRED offload failed - harddrop is not supported (p:%08x h:%08x vq:%d)\n",
+				 opt->parent, opt->handle, i);
+			return false;
+		}
+		if (band->min != band->max) {
+			nfp_warn(cpp, "GRED offload failed - threshold mismatch (p:%08x h:%08x vq:%d)\n",
+				 opt->parent, opt->handle, i);
+			return false;
+		}
+		if (band->min > S32_MAX) {
+			nfp_warn(cpp, "GRED offload failed - threshold too large %d > %d (p:%08x h:%08x vq:%d)\n",
+				 band->min, S32_MAX, opt->parent, opt->handle,
+				 i);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static int
+nfp_abm_gred_replace(struct net_device *netdev, struct nfp_abm_link *alink,
+		     struct tc_gred_qopt_offload *opt)
+{
+	struct nfp_qdisc *qdisc;
+	unsigned int i;
+	int ret;
+
+	ret = nfp_abm_qdisc_replace(netdev, alink, NFP_QDISC_GRED, opt->parent,
+				    opt->handle, 0, &qdisc);
+	if (ret < 0)
+		return ret;
+
+	qdisc->params_ok = nfp_abm_gred_check_params(alink, opt);
+	if (qdisc->params_ok) {
+		qdisc->red.num_bands = opt->set.dp_cnt;
+		for (i = 0; i < qdisc->red.num_bands; i++)
+			qdisc->red.band[i].threshold = opt->set.tab[i].min;
+	}
+
+	if (qdisc->use_cnt)
+		nfp_abm_qdisc_offload_update(alink);
+
+	return 0;
+}
+
+int nfp_abm_setup_tc_gred(struct net_device *netdev, struct nfp_abm_link *alink,
+			  struct tc_gred_qopt_offload *opt)
+{
+	switch (opt->command) {
+	case TC_GRED_REPLACE:
+		return nfp_abm_gred_replace(netdev, alink, opt);
+	case TC_GRED_DESTROY:
+		nfp_abm_qdisc_destroy(netdev, alink, opt->handle);
+		return 0;
+	case TC_GRED_STATS:
+		return nfp_abm_gred_stats(alink, opt->handle, &opt->stats);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int
 nfp_abm_red_xstats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
 {
-- 
cgit v1.2.3


From 068ceb3555397dbd82593fb505688c5bd200a4ad Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:46 -0800
Subject: net: sched: cls_u32: add res to offload information

In case of egress offloads the class/flowid assigned by the filter
may be very important for offloaded Qdisc selection.  Provide this
info to drivers.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h | 1 +
 net/sched/cls_u32.c   | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index d0e9a8091426..ea191d8cfcc9 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -643,6 +643,7 @@ struct tc_cls_common_offload {
 
 struct tc_cls_u32_knode {
 	struct tcf_exts *exts;
+	struct tcf_result *res;
 	struct tc_u32_sel *sel;
 	u32 handle;
 	u32 val;
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 4b28fd44576d..4c54bc440798 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -558,6 +558,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	cls_u32.knode.mask = 0;
 #endif
 	cls_u32.knode.sel = &n->sel;
+	cls_u32.knode.res = &n->res;
 	cls_u32.knode.exts = &n->exts;
 	if (n->ht_down)
 		cls_u32.knode.link_handle = ht->handle;
@@ -1206,6 +1207,7 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 		cls_u32.knode.mask = 0;
 #endif
 		cls_u32.knode.sel = &n->sel;
+		cls_u32.knode.res = &n->res;
 		cls_u32.knode.exts = &n->exts;
 		if (n->ht_down)
 			cls_u32.knode.link_handle = ht->handle;
-- 
cgit v1.2.3


From 14780c34294f41da8f02d99d7b6ada990e685561 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:47 -0800
Subject: nfp: abm: calculate PRIO map len and check mailbox size

In preparation for PRIO offload calculate how long the prio map
for FW will be and make sure the configuration can be performed
via the vNIC mailbox.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/ctrl.c | 42 ++++++++++++++++++++++++++-
 drivers/net/ethernet/netronome/nfp/abm/main.c |  5 +++-
 drivers/net/ethernet/netronome/nfp/abm/main.h |  6 +++-
 3 files changed, 50 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index 10a571b5b565..ef10a2e730bc 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -33,6 +33,12 @@
 #define NFP_Q_STAT_PKTS		0
 #define NFP_Q_STAT_BYTES	8
 
+#define NFP_NET_ABM_MBOX_CMD		NFP_NET_CFG_MBOX_SIMPLE_CMD
+#define NFP_NET_ABM_MBOX_RET		NFP_NET_CFG_MBOX_SIMPLE_RET
+#define NFP_NET_ABM_MBOX_DATALEN	NFP_NET_CFG_MBOX_SIMPLE_VAL
+#define NFP_NET_ABM_MBOX_RESERVED	(NFP_NET_CFG_MBOX_SIMPLE_VAL + 4)
+#define NFP_NET_ABM_MBOX_DATA		(NFP_NET_CFG_MBOX_SIMPLE_VAL + 8)
+
 static int
 nfp_abm_ctrl_stat(struct nfp_abm_link *alink, const struct nfp_rtsym *sym,
 		  unsigned int stride, unsigned int offset, unsigned int band,
@@ -215,10 +221,42 @@ int nfp_abm_ctrl_qm_disable(struct nfp_abm *abm)
 			    NULL, 0, NULL, 0);
 }
 
-void nfp_abm_ctrl_read_params(struct nfp_abm_link *alink)
+static int nfp_abm_ctrl_prio_check_params(struct nfp_abm_link *alink)
+{
+	struct nfp_abm *abm = alink->abm;
+	struct nfp_net *nn = alink->vnic;
+	unsigned int min_mbox_sz;
+
+	if (!nfp_abm_has_prio(alink->abm))
+		return 0;
+
+	min_mbox_sz = NFP_NET_ABM_MBOX_DATA + alink->abm->prio_map_len;
+	if (nn->tlv_caps.mbox_len < min_mbox_sz) {
+		nfp_err(abm->app->pf->cpp, "vNIC mailbox too small for prio offload: %u, need: %u\n",
+			nn->tlv_caps.mbox_len,  min_mbox_sz);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int nfp_abm_ctrl_read_params(struct nfp_abm_link *alink)
 {
 	alink->queue_base = nn_readl(alink->vnic, NFP_NET_CFG_START_RXQ);
 	alink->queue_base /= alink->vnic->stride_rx;
+
+	return nfp_abm_ctrl_prio_check_params(alink);
+}
+
+static unsigned int nfp_abm_ctrl_prio_map_size(struct nfp_abm *abm)
+{
+	unsigned int size;
+
+	size = roundup_pow_of_two(order_base_2(abm->num_bands));
+	size = DIV_ROUND_UP(size * abm->num_prios, BITS_PER_BYTE);
+	size = round_up(size, sizeof(u32));
+
+	return size;
 }
 
 static const struct nfp_rtsym *
@@ -273,6 +311,8 @@ int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm)
 		return res;
 	abm->num_prios = res;
 
+	abm->prio_map_len = nfp_abm_ctrl_prio_map_size(abm);
+
 	/* Check values are sane, U16_MAX is arbitrarily chosen as max */
 	if (!is_power_of_2(abm->num_bands) || !is_power_of_2(abm->num_prios) ||
 	    abm->num_bands > U16_MAX || abm->num_prios > U16_MAX ||
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 4f95f7b4430b..aeb0c9a1f260 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -315,6 +315,10 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 	alink->id = id;
 	alink->total_queues = alink->vnic->max_rx_rings;
 
+	err = nfp_abm_ctrl_read_params(alink);
+	if (err)
+		goto err_free_alink;
+
 	/* This is a multi-host app, make sure MAC/PHY is up, but don't
 	 * make the MAC/PHY state follow the state of any of the ports.
 	 */
@@ -325,7 +329,6 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 	netif_keep_dst(nn->dp.netdev);
 
 	nfp_abm_vnic_set_mac(app->pf, abm, nn, id);
-	nfp_abm_ctrl_read_params(alink);
 	INIT_RADIX_TREE(&alink->qdiscs, GFP_KERNEL);
 
 	return 0;
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 6bb4e60c1ad8..1ca2768cd5a2 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -34,9 +34,11 @@ struct nfp_net;
  * @thresholds:		current threshold configuration
  * @threshold_undef:	bitmap of thresholds which have not been set
  * @num_thresholds:	number of @thresholds and bits in @threshold_undef
+ * @prio_map_len:	computed length of FW priority map (in bytes)
  *
  * @eswitch_mode:	devlink eswitch mode, advanced functions only visible
  *			in switchdev mode
+ *
  * @q_lvls:	queue level control area
  * @qm_stats:	queue statistics symbol
  * @q_stats:	basic queue statistics (only in per-band case)
@@ -51,8 +53,10 @@ struct nfp_abm {
 	u32 *thresholds;
 	unsigned long *threshold_undef;
 	size_t num_thresholds;
+	unsigned int prio_map_len;
 
 	enum devlink_eswitch_mode eswitch_mode;
+
 	const struct nfp_rtsym *q_lvls;
 	const struct nfp_rtsym *qm_stats;
 	const struct nfp_rtsym *q_stats;
@@ -201,7 +205,7 @@ int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 int nfp_abm_setup_tc_gred(struct net_device *netdev, struct nfp_abm_link *alink,
 			  struct tc_gred_qopt_offload *opt);
 
-void nfp_abm_ctrl_read_params(struct nfp_abm_link *alink);
+int nfp_abm_ctrl_read_params(struct nfp_abm_link *alink);
 int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm);
 int __nfp_abm_ctrl_set_q_lvl(struct nfp_abm *abm, unsigned int id, u32 val);
 int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int band,
-- 
cgit v1.2.3


From 6a80240571800ba4ea2487f0531553424b6922e0 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:48 -0800
Subject: nfp: abm: add functions to update DSCP -> virtual queue map

Learn how to set the DSCP map.  FW uses a packed array which
geometry depends on the number of supported priorities and
virtual queues.  Write code to assemble this map and to communicate
the setting to the FW via mailbox.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/ctrl.c      | 23 ++++++++++++++++++++++
 drivers/net/ethernet/netronome/nfp/abm/main.h      |  1 +
 drivers/net/ethernet/netronome/nfp/nfp_net.h       |  1 +
 .../net/ethernet/netronome/nfp/nfp_net_common.c    |  2 +-
 drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h  |  2 ++
 5 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index ef10a2e730bc..77dbc509a637 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (C) 2018 Netronome Systems, Inc. */
 
+#include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/log2.h>
 
@@ -221,6 +222,28 @@ int nfp_abm_ctrl_qm_disable(struct nfp_abm *abm)
 			    NULL, 0, NULL, 0);
 }
 
+int nfp_abm_ctrl_prio_map_update(struct nfp_abm_link *alink, u32 *packed)
+{
+	struct nfp_net *nn = alink->vnic;
+	unsigned int i;
+	int err;
+
+	/* Write data_len and wipe reserved */
+	nn_writeq(nn, nn->tlv_caps.mbox_off + NFP_NET_ABM_MBOX_DATALEN,
+		  alink->abm->prio_map_len);
+
+	for (i = 0; i < alink->abm->prio_map_len; i += sizeof(u32))
+		nn_writel(nn, nn->tlv_caps.mbox_off + NFP_NET_ABM_MBOX_DATA + i,
+			  packed[i / sizeof(u32)]);
+
+	err = nfp_net_reconfig_mbox(nn,
+				    NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET);
+	if (err)
+		nfp_err(alink->abm->app->cpp,
+			"setting DSCP -> VQ map failed with error %d\n", err);
+	return err;
+}
+
 static int nfp_abm_ctrl_prio_check_params(struct nfp_abm_link *alink)
 {
 	struct nfp_abm *abm = alink->abm;
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 1ca2768cd5a2..bc378b464f2c 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -220,4 +220,5 @@ u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int i);
 u64 nfp_abm_ctrl_stat_sto(struct nfp_abm_link *alink, unsigned int i);
 int nfp_abm_ctrl_qm_enable(struct nfp_abm *abm);
 int nfp_abm_ctrl_qm_disable(struct nfp_abm *abm);
+int nfp_abm_ctrl_prio_map_update(struct nfp_abm_link *alink, u32 *packed);
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index dda02fefc806..bb3dbd74583b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -868,6 +868,7 @@ unsigned int nfp_net_rss_key_sz(struct nfp_net *nn);
 void nfp_net_rss_write_itbl(struct nfp_net *nn);
 void nfp_net_rss_write_key(struct nfp_net *nn);
 void nfp_net_coalesce_write_cfg(struct nfp_net *nn);
+int nfp_net_reconfig_mbox(struct nfp_net *nn, u32 mbox_cmd);
 
 unsigned int
 nfp_net_irqs_alloc(struct pci_dev *pdev, struct msix_entry *irq_entries,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index a0343f25068a..9aa6265bf4de 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -279,7 +279,7 @@ int nfp_net_reconfig(struct nfp_net *nn, u32 update)
  *
  * Return: Negative errno on error, 0 on success
  */
-static int nfp_net_reconfig_mbox(struct nfp_net *nn, u32 mbox_cmd)
+int nfp_net_reconfig_mbox(struct nfp_net *nn, u32 mbox_cmd)
 {
 	u32 mbox = nn->tlv_caps.mbox_off;
 	int ret;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index d7c8518ac952..ccec69944de5 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -397,6 +397,8 @@
 #define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_ADD 1
 #define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL 2
 
+#define NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET	5
+
 /**
  * VLAN filtering using general use mailbox
  * %NFP_NET_CFG_VLAN_FILTER:		Base address of VLAN filter mailbox
-- 
cgit v1.2.3


From 174ab544e3bc0b0c944b8e642618203dd0c2ecdf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:49 -0800
Subject: nfp: abm: add cls_u32 offload for simple band classification

Use offload of very simple u32 filters to direct packets to GRED
bands based on the DSCP marking.  No u32 hashing is supported,
just plain simple filters matching on ToS or Priority with
appropriate mask device can support.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/Makefile    |   1 +
 drivers/net/ethernet/netronome/nfp/abm/cls.c   | 283 +++++++++++++++++++++++++
 drivers/net/ethernet/netronome/nfp/abm/ctrl.c  |   1 +
 drivers/net/ethernet/netronome/nfp/abm/main.c  |  23 +-
 drivers/net/ethernet/netronome/nfp/abm/main.h  |  16 ++
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c |   1 +
 6 files changed, 324 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/netronome/nfp/abm/cls.c

diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile
index 190e8b56a41f..47c708f08ade 100644
--- a/drivers/net/ethernet/netronome/nfp/Makefile
+++ b/drivers/net/ethernet/netronome/nfp/Makefile
@@ -56,6 +56,7 @@ endif
 
 ifeq ($(CONFIG_NFP_APP_ABM_NIC),y)
 nfp-objs += \
+	    abm/cls.o \
 	    abm/ctrl.o \
 	    abm/qdisc.o \
 	    abm/main.o
diff --git a/drivers/net/ethernet/netronome/nfp/abm/cls.c b/drivers/net/ethernet/netronome/nfp/abm/cls.c
new file mode 100644
index 000000000000..9852080cf454
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/abm/cls.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2018 Netronome Systems, Inc. */
+
+#include <linux/bitfield.h>
+#include <net/pkt_cls.h>
+
+#include "../nfpcore/nfp_cpp.h"
+#include "../nfp_app.h"
+#include "../nfp_net_repr.h"
+#include "main.h"
+
+struct nfp_abm_u32_match {
+	u32 handle;
+	u32 band;
+	u8 mask;
+	u8 val;
+	struct list_head list;
+};
+
+static bool
+nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode,
+			__be16 proto, struct netlink_ext_ack *extack)
+{
+	struct tc_u32_key *k;
+	unsigned int tos_off;
+
+	if (knode->exts && tcf_exts_has_actions(knode->exts)) {
+		NL_SET_ERR_MSG_MOD(extack, "action offload not supported");
+		return false;
+	}
+	if (knode->link_handle) {
+		NL_SET_ERR_MSG_MOD(extack, "linking not supported");
+		return false;
+	}
+	if (knode->sel->flags != TC_U32_TERMINAL) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "flags must be equal to TC_U32_TERMINAL");
+		return false;
+	}
+	if (knode->sel->off || knode->sel->offshift || knode->sel->offmask ||
+	    knode->sel->offoff || knode->fshift) {
+		NL_SET_ERR_MSG_MOD(extack, "variable offseting not supported");
+		return false;
+	}
+	if (knode->sel->hoff || knode->sel->hmask) {
+		NL_SET_ERR_MSG_MOD(extack, "hashing not supported");
+		return false;
+	}
+	if (knode->val || knode->mask) {
+		NL_SET_ERR_MSG_MOD(extack, "matching on mark not supported");
+		return false;
+	}
+	if (knode->res && knode->res->class) {
+		NL_SET_ERR_MSG_MOD(extack, "setting non-0 class not supported");
+		return false;
+	}
+	if (knode->res && knode->res->classid >= abm->num_bands) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "classid higher than number of bands");
+		return false;
+	}
+	if (knode->sel->nkeys != 1) {
+		NL_SET_ERR_MSG_MOD(extack, "exactly one key required");
+		return false;
+	}
+
+	switch (proto) {
+	case htons(ETH_P_IP):
+		tos_off = 16;
+		break;
+	case htons(ETH_P_IPV6):
+		tos_off = 20;
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "only IP and IPv6 supported as filter protocol");
+		return false;
+	}
+
+	k = &knode->sel->keys[0];
+	if (k->offmask) {
+		NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offseting not supported");
+		return false;
+	}
+	if (k->off) {
+		NL_SET_ERR_MSG_MOD(extack, "only DSCP fields can be matched");
+		return false;
+	}
+	if (k->val & ~k->mask) {
+		NL_SET_ERR_MSG_MOD(extack, "mask does not cover the key");
+		return false;
+	}
+	if (be32_to_cpu(k->mask) >> tos_off & ~abm->dscp_mask) {
+		NL_SET_ERR_MSG_MOD(extack, "only high DSCP class selector bits can be used");
+		nfp_err(abm->app->cpp,
+			"u32 offload: requested mask %x FW can support only %x\n",
+			be32_to_cpu(k->mask) >> tos_off, abm->dscp_mask);
+		return false;
+	}
+
+	return true;
+}
+
+/* This filter list -> map conversion is O(n * m), we expect single digit or
+ * low double digit number of prios and likewise for the filters.  Also u32
+ * doesn't report stats, so it's really only setup time cost.
+ */
+static unsigned int
+nfp_abm_find_band_for_prio(struct nfp_abm_link *alink, unsigned int prio)
+{
+	struct nfp_abm_u32_match *iter;
+
+	list_for_each_entry(iter, &alink->dscp_map, list)
+		if ((prio & iter->mask) == iter->val)
+			return iter->band;
+
+	return alink->def_band;
+}
+
+static int nfp_abm_update_band_map(struct nfp_abm_link *alink)
+{
+	unsigned int i, bits_per_prio, prios_per_word, base_shift;
+	struct nfp_abm *abm = alink->abm;
+	u32 field_mask;
+
+	alink->has_prio = !list_empty(&alink->dscp_map);
+
+	bits_per_prio = roundup_pow_of_two(order_base_2(abm->num_bands));
+	field_mask = (1 << bits_per_prio) - 1;
+	prios_per_word = sizeof(u32) * BITS_PER_BYTE / bits_per_prio;
+
+	/* FW mask applies from top bits */
+	base_shift = 8 - order_base_2(abm->num_prios);
+
+	for (i = 0; i < abm->num_prios; i++) {
+		unsigned int offset;
+		u32 *word;
+		u8 band;
+
+		word = &alink->prio_map[i / prios_per_word];
+		offset = (i % prios_per_word) * bits_per_prio;
+
+		band = nfp_abm_find_band_for_prio(alink, i << base_shift);
+
+		*word &= ~(field_mask << offset);
+		*word |= band << offset;
+	}
+
+	/* Qdisc offload status may change if has_prio changed */
+	nfp_abm_qdisc_offload_update(alink);
+
+	return nfp_abm_ctrl_prio_map_update(alink, alink->prio_map);
+}
+
+static void
+nfp_abm_u32_knode_delete(struct nfp_abm_link *alink,
+			 struct tc_cls_u32_knode *knode)
+{
+	struct nfp_abm_u32_match *iter;
+
+	list_for_each_entry(iter, &alink->dscp_map, list)
+		if (iter->handle == knode->handle) {
+			list_del(&iter->list);
+			kfree(iter);
+			nfp_abm_update_band_map(alink);
+			return;
+		}
+}
+
+static int
+nfp_abm_u32_knode_replace(struct nfp_abm_link *alink,
+			  struct tc_cls_u32_knode *knode,
+			  __be16 proto, struct netlink_ext_ack *extack)
+{
+	struct nfp_abm_u32_match *match = NULL, *iter;
+	unsigned int tos_off;
+	u8 mask, val;
+	int err;
+
+	if (!nfp_abm_u32_check_knode(alink->abm, knode, proto, extack))
+		goto err_delete;
+
+	tos_off = proto == htons(ETH_P_IP) ? 16 : 20;
+
+	/* Extract the DSCP Class Selector bits */
+	val = be32_to_cpu(knode->sel->keys[0].val) >> tos_off & 0xff;
+	mask = be32_to_cpu(knode->sel->keys[0].mask) >> tos_off & 0xff;
+
+	/* Check if there is no conflicting mapping and find match by handle */
+	list_for_each_entry(iter, &alink->dscp_map, list) {
+		u32 cmask;
+
+		if (iter->handle == knode->handle) {
+			match = iter;
+			continue;
+		}
+
+		cmask = iter->mask & mask;
+		if ((iter->val & cmask) == (val & cmask) &&
+		    iter->band != knode->res->classid) {
+			NL_SET_ERR_MSG_MOD(extack, "conflict with already offloaded filter");
+			goto err_delete;
+		}
+	}
+
+	if (!match) {
+		match = kzalloc(sizeof(*match), GFP_KERNEL);
+		if (!match)
+			return -ENOMEM;
+		list_add(&match->list, &alink->dscp_map);
+	}
+	match->handle = knode->handle;
+	match->band = knode->res->classid;
+	match->mask = mask;
+	match->val = val;
+
+	err = nfp_abm_update_band_map(alink);
+	if (err)
+		goto err_delete;
+
+	return 0;
+
+err_delete:
+	nfp_abm_u32_knode_delete(alink, knode);
+	return -EOPNOTSUPP;
+}
+
+static int nfp_abm_setup_tc_block_cb(enum tc_setup_type type,
+				     void *type_data, void *cb_priv)
+{
+	struct tc_cls_u32_offload *cls_u32 = type_data;
+	struct nfp_repr *repr = cb_priv;
+	struct nfp_abm_link *alink;
+
+	alink = repr->app_priv;
+
+	if (type != TC_SETUP_CLSU32) {
+		NL_SET_ERR_MSG_MOD(cls_u32->common.extack,
+				   "only offload of u32 classifier supported");
+		return -EOPNOTSUPP;
+	}
+	if (!tc_cls_can_offload_and_chain0(repr->netdev, &cls_u32->common))
+		return -EOPNOTSUPP;
+
+	if (cls_u32->common.protocol != htons(ETH_P_IP) &&
+	    cls_u32->common.protocol != htons(ETH_P_IPV6)) {
+		NL_SET_ERR_MSG_MOD(cls_u32->common.extack,
+				   "only IP and IPv6 supported as filter protocol");
+		return -EOPNOTSUPP;
+	}
+
+	switch (cls_u32->command) {
+	case TC_CLSU32_NEW_KNODE:
+	case TC_CLSU32_REPLACE_KNODE:
+		return nfp_abm_u32_knode_replace(alink, &cls_u32->knode,
+						 cls_u32->common.protocol,
+						 cls_u32->common.extack);
+	case TC_CLSU32_DELETE_KNODE:
+		nfp_abm_u32_knode_delete(alink, &cls_u32->knode);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int nfp_abm_setup_cls_block(struct net_device *netdev, struct nfp_repr *repr,
+			    struct tc_block_offload *f)
+{
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block,
+					     nfp_abm_setup_tc_block_cb,
+					     repr, repr, f->extack);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, nfp_abm_setup_tc_block_cb,
+					repr);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index 77dbc509a637..2447e935e2d9 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -335,6 +335,7 @@ int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm)
 	abm->num_prios = res;
 
 	abm->prio_map_len = nfp_abm_ctrl_prio_map_size(abm);
+	abm->dscp_mask = GENMASK(7, 8 - order_base_2(abm->num_prios));
 
 	/* Check values are sane, U16_MAX is arbitrarily chosen as max */
 	if (!is_power_of_2(abm->num_bands) || !is_power_of_2(abm->num_prios) ||
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index aeb0c9a1f260..ecdef63a20f3 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -46,6 +46,8 @@ nfp_abm_setup_tc(struct nfp_app *app, struct net_device *netdev,
 		return nfp_abm_setup_tc_red(netdev, repr->app_priv, type_data);
 	case TC_SETUP_QDISC_GRED:
 		return nfp_abm_setup_tc_gred(netdev, repr->app_priv, type_data);
+	case TC_SETUP_BLOCK:
+		return nfp_abm_setup_cls_block(netdev, repr, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -315,16 +317,22 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 	alink->id = id;
 	alink->total_queues = alink->vnic->max_rx_rings;
 
+	INIT_LIST_HEAD(&alink->dscp_map);
+
 	err = nfp_abm_ctrl_read_params(alink);
 	if (err)
 		goto err_free_alink;
 
+	alink->prio_map = kzalloc(abm->prio_map_len, GFP_KERNEL);
+	if (!alink->prio_map)
+		goto err_free_alink;
+
 	/* This is a multi-host app, make sure MAC/PHY is up, but don't
 	 * make the MAC/PHY state follow the state of any of the ports.
 	 */
 	err = nfp_eth_set_configured(app->cpp, eth_port->index, true);
 	if (err < 0)
-		goto err_free_alink;
+		goto err_free_priomap;
 
 	netif_keep_dst(nn->dp.netdev);
 
@@ -333,6 +341,8 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 
 	return 0;
 
+err_free_priomap:
+	kfree(alink->prio_map);
 err_free_alink:
 	kfree(alink);
 	return err;
@@ -344,9 +354,19 @@ static void nfp_abm_vnic_free(struct nfp_app *app, struct nfp_net *nn)
 
 	nfp_abm_kill_reprs(alink->abm, alink);
 	WARN(!radix_tree_empty(&alink->qdiscs), "left over qdiscs\n");
+	kfree(alink->prio_map);
 	kfree(alink);
 }
 
+static int nfp_abm_vnic_init(struct nfp_app *app, struct nfp_net *nn)
+{
+	struct nfp_abm_link *alink = nn->app_priv;
+
+	if (nfp_abm_has_prio(alink->abm))
+		return nfp_abm_ctrl_prio_map_update(alink, alink->prio_map);
+	return 0;
+}
+
 static u64 *
 nfp_abm_port_get_stats(struct nfp_app *app, struct nfp_port *port, u64 *data)
 {
@@ -491,6 +511,7 @@ const struct nfp_app_type app_abm = {
 
 	.vnic_alloc	= nfp_abm_vnic_alloc,
 	.vnic_free	= nfp_abm_vnic_free,
+	.vnic_init	= nfp_abm_vnic_init,
 
 	.port_get_stats		= nfp_abm_port_get_stats,
 	.port_get_stats_count	= nfp_abm_port_get_stats_count,
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index bc378b464f2c..9352992ab386 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -5,6 +5,7 @@
 #define __NFP_ABM_H__ 1
 
 #include <linux/bits.h>
+#include <linux/list.h>
 #include <linux/radix-tree.h>
 #include <net/devlink.h>
 #include <net/pkt_cls.h>
@@ -34,7 +35,9 @@ struct nfp_net;
  * @thresholds:		current threshold configuration
  * @threshold_undef:	bitmap of thresholds which have not been set
  * @num_thresholds:	number of @thresholds and bits in @threshold_undef
+ *
  * @prio_map_len:	computed length of FW priority map (in bytes)
+ * @dscp_mask:		mask FW will apply on DSCP field
  *
  * @eswitch_mode:	devlink eswitch mode, advanced functions only visible
  *			in switchdev mode
@@ -53,7 +56,9 @@ struct nfp_abm {
 	u32 *thresholds;
 	unsigned long *threshold_undef;
 	size_t num_thresholds;
+
 	unsigned int prio_map_len;
+	u8 dscp_mask;
 
 	enum devlink_eswitch_mode eswitch_mode;
 
@@ -170,7 +175,11 @@ struct nfp_qdisc {
  *
  * @last_stats_update:	ktime of last stats update
  *
+ * @prio_map:		current map of priorities
+ * @has_prio:		@prio_map is valid
+ *
  * @def_band:		default band to use
+ * @dscp_map:		list of DSCP to band mappings
  *
  * @root_qdisc:	pointer to the current root of the Qdisc hierarchy
  * @qdiscs:	all qdiscs recorded by major part of the handle
@@ -184,7 +193,11 @@ struct nfp_abm_link {
 
 	u64 last_stats_update;
 
+	u32 *prio_map;
+	bool has_prio;
+
 	u8 def_band;
+	struct list_head dscp_map;
 
 	struct nfp_qdisc *root_qdisc;
 	struct radix_tree_root qdiscs;
@@ -204,6 +217,8 @@ int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 			struct tc_mq_qopt_offload *opt);
 int nfp_abm_setup_tc_gred(struct net_device *netdev, struct nfp_abm_link *alink,
 			  struct tc_gred_qopt_offload *opt);
+int nfp_abm_setup_cls_block(struct net_device *netdev, struct nfp_repr *repr,
+			    struct tc_block_offload *opt);
 
 int nfp_abm_ctrl_read_params(struct nfp_abm_link *alink);
 int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm);
@@ -220,5 +235,6 @@ u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int i);
 u64 nfp_abm_ctrl_stat_sto(struct nfp_abm_link *alink, unsigned int i);
 int nfp_abm_ctrl_qm_enable(struct nfp_abm *abm);
 int nfp_abm_ctrl_qm_disable(struct nfp_abm *abm);
+void nfp_abm_prio_map_update(struct nfp_abm *abm);
 int nfp_abm_ctrl_prio_map_update(struct nfp_abm_link *alink, u32 *packed);
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index e80a3d40a48b..8f6e43667757 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -197,6 +197,7 @@ nfp_abm_offload_compile_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
 	good_red = qdisc->type == NFP_QDISC_RED &&
 		   qdisc->params_ok &&
 		   qdisc->use_cnt == 1 &&
+		   !alink->has_prio &&
 		   !qdisc->children[0];
 	good_gred = qdisc->type == NFP_QDISC_GRED &&
 		    qdisc->params_ok &&
-- 
cgit v1.2.3


From 340a4864d538ab718b0e888a1d5933bc13e6a372 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 19 Nov 2018 15:21:50 -0800
Subject: nfp: abm: add support for more threshold actions

Original FW only allowed us to perform ECN marking.  Newer releases
also support plain old drop.  Add the ability to configure drop
policy.  This is particularly useful in combination with GRED,
because different bands can have different ECN marking setting.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/ctrl.c  | 42 ++++++++++++++++++++++++++
 drivers/net/ethernet/netronome/nfp/abm/main.c  | 14 +++++++--
 drivers/net/ethernet/netronome/nfp/abm/main.h  | 31 +++++++++++++++++++
 drivers/net/ethernet/netronome/nfp/abm/qdisc.c | 28 ++++++++++++++---
 4 files changed, 109 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index 2447e935e2d9..ad6c2a621c7a 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -15,12 +15,14 @@
 
 #define NFP_NUM_PRIOS_SYM_NAME	"_abi_pci_dscp_num_prio_%u"
 #define NFP_NUM_BANDS_SYM_NAME	"_abi_pci_dscp_num_band_%u"
+#define NFP_ACT_MASK_SYM_NAME	"_abi_nfd_out_q_actions_%u"
 
 #define NFP_QLVL_SYM_NAME	"_abi_nfd_out_q_lvls_%u%s"
 #define NFP_QLVL_STRIDE		16
 #define NFP_QLVL_BLOG_BYTES	0
 #define NFP_QLVL_BLOG_PKTS	4
 #define NFP_QLVL_THRS		8
+#define NFP_QLVL_ACT		12
 
 #define NFP_QMSTAT_SYM_NAME	"_abi_nfdqm%u_stats%s"
 #define NFP_QMSTAT_STRIDE	32
@@ -101,6 +103,39 @@ int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int band,
 	return __nfp_abm_ctrl_set_q_lvl(alink->abm, threshold, val);
 }
 
+int __nfp_abm_ctrl_set_q_act(struct nfp_abm *abm, unsigned int id,
+			     enum nfp_abm_q_action act)
+{
+	struct nfp_cpp *cpp = abm->app->cpp;
+	u64 sym_offset;
+	int err;
+
+	if (abm->actions[id] == act)
+		return 0;
+
+	sym_offset = id * NFP_QLVL_STRIDE + NFP_QLVL_ACT;
+	err = __nfp_rtsym_writel(cpp, abm->q_lvls, 4, 0, sym_offset, act);
+	if (err) {
+		nfp_err(cpp,
+			"RED offload setting action failed on subqueue %d\n",
+			id);
+		return err;
+	}
+
+	abm->actions[id] = act;
+	return 0;
+}
+
+int nfp_abm_ctrl_set_q_act(struct nfp_abm_link *alink, unsigned int band,
+			   unsigned int queue, enum nfp_abm_q_action act)
+{
+	unsigned int qid;
+
+	qid = band * NFP_NET_MAX_RX_RINGS + alink->queue_base + queue;
+
+	return __nfp_abm_ctrl_set_q_act(alink->abm, qid, act);
+}
+
 u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int queue)
 {
 	unsigned int band;
@@ -334,6 +369,13 @@ int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm)
 		return res;
 	abm->num_prios = res;
 
+	/* Read available actions */
+	res = nfp_pf_rtsym_read_optional(pf, NFP_ACT_MASK_SYM_NAME,
+					 BIT(NFP_ABM_ACT_MARK_DROP));
+	if (res < 0)
+		return res;
+	abm->action_mask = res;
+
 	abm->prio_map_len = nfp_abm_ctrl_prio_map_size(abm);
 	abm->dscp_mask = GENMASK(7, 8 - order_base_2(abm->num_prios));
 
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index ecdef63a20f3..7a4d55f794c2 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -459,15 +459,22 @@ static int nfp_abm_init(struct nfp_app *app)
 	for (i = 0; i < abm->num_bands * NFP_NET_MAX_RX_RINGS; i++)
 		__nfp_abm_ctrl_set_q_lvl(abm, i, NFP_ABM_LVL_INFINITY);
 
+	abm->actions = kvcalloc(abm->num_thresholds, sizeof(*abm->actions),
+				GFP_KERNEL);
+	if (!abm->actions)
+		goto err_free_thresh;
+	for (i = 0; i < abm->num_bands * NFP_NET_MAX_RX_RINGS; i++)
+		__nfp_abm_ctrl_set_q_act(abm, i, NFP_ABM_ACT_DROP);
+
 	/* We start in legacy mode, make sure advanced queuing is disabled */
 	err = nfp_abm_ctrl_qm_disable(abm);
 	if (err)
-		goto err_free_thresh;
+		goto err_free_act;
 
 	err = -ENOMEM;
 	reprs = nfp_reprs_alloc(pf->max_data_vnics);
 	if (!reprs)
-		goto err_free_thresh;
+		goto err_free_act;
 	RCU_INIT_POINTER(app->reprs[NFP_REPR_TYPE_PHYS_PORT], reprs);
 
 	reprs = nfp_reprs_alloc(pf->max_data_vnics);
@@ -479,6 +486,8 @@ static int nfp_abm_init(struct nfp_app *app)
 
 err_free_phys:
 	nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PHYS_PORT);
+err_free_act:
+	kvfree(abm->actions);
 err_free_thresh:
 	kvfree(abm->thresholds);
 err_free_thresh_umap:
@@ -497,6 +506,7 @@ static void nfp_abm_clean(struct nfp_app *app)
 	nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PF);
 	nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PHYS_PORT);
 	bitmap_free(abm->threshold_undef);
+	kvfree(abm->actions);
 	kvfree(abm->thresholds);
 	kfree(abm);
 	app->priv = NULL;
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 9352992ab386..4dcf5881fb4b 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -24,6 +24,17 @@ struct nfp_net;
 #define NFP_ABM_PORTID_TYPE	GENMASK(23, 16)
 #define NFP_ABM_PORTID_ID	GENMASK(7, 0)
 
+/* The possible actions if thresholds are exceeded */
+enum nfp_abm_q_action {
+	/* mark if ECN capable, otherwise drop */
+	NFP_ABM_ACT_MARK_DROP		= 0,
+	/* mark if ECN capable, otherwise goto QM */
+	NFP_ABM_ACT_MARK_QUEUE		= 1,
+	NFP_ABM_ACT_DROP		= 2,
+	NFP_ABM_ACT_QUEUE		= 3,
+	NFP_ABM_ACT_NOQUEUE		= 4,
+};
+
 /**
  * struct nfp_abm - ABM NIC app structure
  * @app:	back pointer to nfp_app
@@ -31,9 +42,11 @@ struct nfp_net;
  *
  * @num_prios:	number of supported DSCP priorities
  * @num_bands:	number of supported DSCP priority bands
+ * @action_mask:	bitmask of supported actions
  *
  * @thresholds:		current threshold configuration
  * @threshold_undef:	bitmap of thresholds which have not been set
+ * @actions:		current FW action configuration
  * @num_thresholds:	number of @thresholds and bits in @threshold_undef
  *
  * @prio_map_len:	computed length of FW priority map (in bytes)
@@ -52,9 +65,11 @@ struct nfp_abm {
 
 	unsigned int num_prios;
 	unsigned int num_bands;
+	unsigned int action_mask;
 
 	u32 *thresholds;
 	unsigned long *threshold_undef;
+	u8 *actions;
 	size_t num_thresholds;
 
 	unsigned int prio_map_len;
@@ -125,6 +140,7 @@ enum nfp_qdisc_type {
  * @red:		RED Qdisc specific parameters and state
  * @red.num_bands:	Number of valid entries in the @red.band table
  * @red.band:		Per-band array of RED instances
+ * @red.band.ecn:		ECN marking is enabled (rather than drop)
  * @red.band.threshold:		ECN marking threshold
  * @red.band.stats:		current stats of the RED Qdisc
  * @red.band.prev_stats:	previously reported @red.stats
@@ -155,6 +171,7 @@ struct nfp_qdisc {
 			unsigned int num_bands;
 
 			struct {
+				bool ecn;
 				u32 threshold;
 				struct nfp_alink_stats stats;
 				struct nfp_alink_stats prev_stats;
@@ -208,6 +225,16 @@ static inline bool nfp_abm_has_prio(struct nfp_abm *abm)
 	return abm->num_bands > 1;
 }
 
+static inline bool nfp_abm_has_drop(struct nfp_abm *abm)
+{
+	return abm->action_mask & BIT(NFP_ABM_ACT_DROP);
+}
+
+static inline bool nfp_abm_has_mark(struct nfp_abm *abm)
+{
+	return abm->action_mask & BIT(NFP_ABM_ACT_MARK_DROP);
+}
+
 void nfp_abm_qdisc_offload_update(struct nfp_abm_link *alink);
 int nfp_abm_setup_root(struct net_device *netdev, struct nfp_abm_link *alink,
 		       struct tc_root_qopt_offload *opt);
@@ -225,6 +252,10 @@ int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm);
 int __nfp_abm_ctrl_set_q_lvl(struct nfp_abm *abm, unsigned int id, u32 val);
 int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int band,
 			   unsigned int queue, u32 val);
+int __nfp_abm_ctrl_set_q_act(struct nfp_abm *abm, unsigned int id,
+			     enum nfp_abm_q_action act);
+int nfp_abm_ctrl_set_q_act(struct nfp_abm_link *alink, unsigned int band,
+			   unsigned int queue, enum nfp_abm_q_action act);
 int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink,
 			      unsigned int band, unsigned int queue,
 			      struct nfp_alink_stats *stats);
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
index 8f6e43667757..2473fb5f75e5 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -212,9 +212,15 @@ nfp_abm_offload_compile_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
 	if (!qdisc->offload_mark)
 		return;
 
-	for (i = 0; i < alink->abm->num_bands; i++)
+	for (i = 0; i < alink->abm->num_bands; i++) {
+		enum nfp_abm_q_action act;
+
 		nfp_abm_ctrl_set_q_lvl(alink, i, queue,
 				       qdisc->red.band[i].threshold);
+		act = qdisc->red.band[i].ecn ?
+			NFP_ABM_ACT_MARK_DROP : NFP_ABM_ACT_DROP;
+		nfp_abm_ctrl_set_q_act(alink, i, queue, act);
+	}
 }
 
 static void
@@ -535,11 +541,16 @@ nfp_abm_gred_check_params(struct nfp_abm_link *alink,
 
 		if (!band->present)
 			return false;
-		if (!band->is_ecn) {
+		if (!band->is_ecn && !nfp_abm_has_drop(abm)) {
 			nfp_warn(cpp, "GRED offload failed - drop is not supported (ECN option required) (p:%08x h:%08x vq:%d)\n",
 				 opt->parent, opt->handle, i);
 			return false;
 		}
+		if (band->is_ecn && !nfp_abm_has_mark(abm)) {
+			nfp_warn(cpp, "GRED offload failed - ECN marking not supported (p:%08x h:%08x vq:%d)\n",
+				 opt->parent, opt->handle, i);
+			return false;
+		}
 		if (band->is_harddrop) {
 			nfp_warn(cpp, "GRED offload failed - harddrop is not supported (p:%08x h:%08x vq:%d)\n",
 				 opt->parent, opt->handle, i);
@@ -577,8 +588,10 @@ nfp_abm_gred_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 	qdisc->params_ok = nfp_abm_gred_check_params(alink, opt);
 	if (qdisc->params_ok) {
 		qdisc->red.num_bands = opt->set.dp_cnt;
-		for (i = 0; i < qdisc->red.num_bands; i++)
+		for (i = 0; i < qdisc->red.num_bands; i++) {
+			qdisc->red.band[i].ecn = opt->set.tab[i].is_ecn;
 			qdisc->red.band[i].threshold = opt->set.tab[i].min;
+		}
 	}
 
 	if (qdisc->use_cnt)
@@ -649,12 +662,18 @@ nfp_abm_red_check_params(struct nfp_abm_link *alink,
 			 struct tc_red_qopt_offload *opt)
 {
 	struct nfp_cpp *cpp = alink->abm->app->cpp;
+	struct nfp_abm *abm = alink->abm;
 
-	if (!opt->set.is_ecn) {
+	if (!opt->set.is_ecn && !nfp_abm_has_drop(abm)) {
 		nfp_warn(cpp, "RED offload failed - drop is not supported (ECN option required) (p:%08x h:%08x)\n",
 			 opt->parent, opt->handle);
 		return false;
 	}
+	if (opt->set.is_ecn && !nfp_abm_has_mark(abm)) {
+		nfp_warn(cpp, "RED offload failed - ECN marking not supported (p:%08x h:%08x)\n",
+			 opt->parent, opt->handle);
+		return false;
+	}
 	if (opt->set.is_harddrop) {
 		nfp_warn(cpp, "RED offload failed - harddrop is not supported (p:%08x h:%08x)\n",
 			 opt->parent, opt->handle);
@@ -703,6 +722,7 @@ nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
 	qdisc->params_ok = nfp_abm_red_check_params(alink, opt);
 	if (qdisc->params_ok) {
 		qdisc->red.num_bands = 1;
+		qdisc->red.band[0].ecn = opt->set.is_ecn;
 		qdisc->red.band[0].threshold = opt->set.min;
 	}
 
-- 
cgit v1.2.3


From 6b015a523fa3ba57ccd9c72697163b560fcdedb4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 19 Nov 2018 17:30:19 -0800
Subject: net_sched: sch_fq: avoid calling ktime_get_ns() if not needed

There are two cases were we can avoid calling ktime_get_ns() :

1) Queue is empty.
2) Internal queue is not empty.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 1da8864502d4..1a662f2bb7bb 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -414,16 +414,21 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now)
 static struct sk_buff *fq_dequeue(struct Qdisc *sch)
 {
 	struct fq_sched_data *q = qdisc_priv(sch);
-	u64 now = ktime_get_ns();
 	struct fq_flow_head *head;
 	struct sk_buff *skb;
 	struct fq_flow *f;
 	unsigned long rate;
 	u32 plen;
+	u64 now;
+
+	if (!sch->q.qlen)
+		return NULL;
 
 	skb = fq_dequeue_head(sch, &q->internal);
 	if (skb)
 		goto out;
+
+	now = ktime_get_ns();
 	fq_check_throttled(q, now);
 begin:
 	head = &q->new_flows;
-- 
cgit v1.2.3


From 1e86ace4c140fd5a693e266c9b23409358f25381 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:31 -0800
Subject: net/mlx5: EQ, Use the right place to store/read IRQ affinity hint

Currently the cpu affinity hint mask for completion EQs is stored and
read from the wrong place, since reading and storing is done from the
same index, there is no actual issue with that, but internal irq_info
for completion EQs stars at MLX5_EQ_VEC_COMP_BASE offset in irq_info
array, this patch changes the code to use the correct offset to store
and read the IRQ affinity hint.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c    | 14 ++++++++------
 include/linux/mlx5/driver.h                       |  2 +-
 3 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 1243edbedc9e..2839c30dd3a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1760,7 +1760,7 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
 
 static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
 {
-	return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
+	return cpumask_first(priv->mdev->priv.irq_info[ix + MLX5_EQ_VEC_COMP_BASE].mask);
 }
 
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 28132c7dc05f..d5cea0a36e6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -640,18 +640,19 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
 static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 {
 	struct mlx5_priv *priv  = &mdev->priv;
-	int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
+	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
+	int irq = pci_irq_vector(mdev->pdev, vecidx);
 
-	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
+	if (!zalloc_cpumask_var(&priv->irq_info[vecidx].mask, GFP_KERNEL)) {
 		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
 		return -ENOMEM;
 	}
 
 	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
-			priv->irq_info[i].mask);
+			priv->irq_info[vecidx].mask);
 
 	if (IS_ENABLED(CONFIG_SMP) &&
-	    irq_set_affinity_hint(irq, priv->irq_info[i].mask))
+	    irq_set_affinity_hint(irq, priv->irq_info[vecidx].mask))
 		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
 
 	return 0;
@@ -659,11 +660,12 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 
 static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
 {
+	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
 	struct mlx5_priv *priv  = &mdev->priv;
-	int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
+	int irq = pci_irq_vector(mdev->pdev, vecidx);
 
 	irq_set_affinity_hint(irq, NULL);
-	free_cpumask_var(priv->irq_info[i].mask);
+	free_cpumask_var(priv->irq_info[vecidx].mask);
 }
 
 static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index aa5963b5d38e..7d4ed995b4ce 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1309,7 +1309,7 @@ enum {
 static inline const struct cpumask *
 mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector)
 {
-	return dev->priv.irq_info[vector].mask;
+	return dev->priv.irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask;
 }
 
 #endif /* MLX5_DRIVER_H */
-- 
cgit v1.2.3


From 4de45c758636c37efd313589f91c739f613fbe7d Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:32 -0800
Subject: net/mlx5: EQ, Remove unused fields and structures

Some fields and structures are not referenced nor used by the driver,
remove them.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 11 -----------
 include/linux/mlx5/driver.h                  |  3 ---
 2 files changed, 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index aeab0c4f60f4..fd5926daa0a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -78,17 +78,6 @@ enum {
 			       (1ull << MLX5_EVENT_TYPE_SRQ_LAST_WQE)	    | \
 			       (1ull << MLX5_EVENT_TYPE_SRQ_RQ_LIMIT))
 
-struct map_eq_in {
-	u64	mask;
-	u32	reserved;
-	u32	unmap_eqn;
-};
-
-struct cre_des_eq {
-	u8	reserved[15];
-	u8	eqn;
-};
-
 static int mlx5_cmd_destroy_eq(struct mlx5_core_dev *dev, u8 eqn)
 {
 	u32 out[MLX5_ST_SZ_DW(destroy_eq_out)] = {0};
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 7d4ed995b4ce..15cf6727a62d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -398,7 +398,6 @@ struct mlx5_eq {
 	unsigned int		irqn;
 	u8			eqn;
 	int			nent;
-	u64			mask;
 	struct list_head	list;
 	int			index;
 	struct mlx5_rsc_debug	*dbg;
@@ -478,8 +477,6 @@ struct mlx5_core_srq {
 };
 
 struct mlx5_eq_table {
-	void __iomem	       *update_ci;
-	void __iomem	       *update_arm_ci;
 	struct list_head	comp_eqs_list;
 	struct mlx5_eq		pages_eq;
 	struct mlx5_eq		async_eq;
-- 
cgit v1.2.3


From 2883f352571b9b830561ca21b8a666936366a120 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:33 -0800
Subject: net/mlx5: EQ, No need to store eq index as a field

eq->index is used only for completion EQs and is assigned to be
the completion eq index, it is used only when traversing the completion
eqs list, and it can be calculated dynamically, thus remove the
eq->index field.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 4 ++--
 include/linux/mlx5/driver.h                    | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d5cea0a36e6a..f5e6d375a8cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -702,10 +702,11 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	struct mlx5_eq *eq, *n;
 	int err = -ENOENT;
+	int i = 0;
 
 	spin_lock(&table->lock);
 	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
-		if (eq->index == vector) {
+		if (i++ == vector) {
 			*eqn = eq->eqn;
 			*irqn = eq->irqn;
 			err = 0;
@@ -797,7 +798,6 @@ static int alloc_comp_eqs(struct mlx5_core_dev *dev)
 			goto clean;
 		}
 		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->eqn);
-		eq->index = i;
 		spin_lock(&table->lock);
 		list_add_tail(&eq->list, &table->comp_eqs_list);
 		spin_unlock(&table->lock);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 15cf6727a62d..4b62d71825c1 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -399,7 +399,6 @@ struct mlx5_eq {
 	u8			eqn;
 	int			nent;
 	struct list_head	list;
-	int			index;
 	struct mlx5_rsc_debug	*dbg;
 	enum mlx5_eq_type	type;
 	union {
-- 
cgit v1.2.3


From aaa553a64438640ee4e41a2c1027c3435a75c0e7 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:34 -0800
Subject: net/mlx5: EQ, Remove redundant completion EQ list lock

Completion EQs list is only modified on driver load/unload, locking is
not required, remove it.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c   |  2 --
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 17 +++--------------
 include/linux/mlx5/driver.h                    |  3 ---
 3 files changed, 3 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index fd5926daa0a6..e75272503027 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -810,8 +810,6 @@ int mlx5_eq_init(struct mlx5_core_dev *dev)
 {
 	int err;
 
-	spin_lock_init(&dev->priv.eq_table.lock);
-
 	err = mlx5_eq_debugfs_init(dev);
 
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f5e6d375a8cc..f692c2a42130 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -704,7 +704,6 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 	int err = -ENOENT;
 	int i = 0;
 
-	spin_lock(&table->lock);
 	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
 		if (i++ == vector) {
 			*eqn = eq->eqn;
@@ -713,7 +712,6 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 			break;
 		}
 	}
-	spin_unlock(&table->lock);
 
 	return err;
 }
@@ -724,14 +722,11 @@ struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn)
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	struct mlx5_eq *eq;
 
-	spin_lock(&table->lock);
-	list_for_each_entry(eq, &table->comp_eqs_list, list)
-		if (eq->eqn == eqn) {
-			spin_unlock(&table->lock);
+	list_for_each_entry(eq, &table->comp_eqs_list, list) {
+		if (eq->eqn == eqn)
 			return eq;
-		}
+	}
 
-	spin_unlock(&table->lock);
 
 	return ERR_PTR(-ENOENT);
 }
@@ -747,17 +742,13 @@ static void free_comp_eqs(struct mlx5_core_dev *dev)
 		dev->rmap = NULL;
 	}
 #endif
-	spin_lock(&table->lock);
 	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
 		list_del(&eq->list);
-		spin_unlock(&table->lock);
 		if (mlx5_destroy_unmap_eq(dev, eq))
 			mlx5_core_warn(dev, "failed to destroy EQ 0x%x\n",
 				       eq->eqn);
 		kfree(eq);
-		spin_lock(&table->lock);
 	}
-	spin_unlock(&table->lock);
 }
 
 static int alloc_comp_eqs(struct mlx5_core_dev *dev)
@@ -798,9 +789,7 @@ static int alloc_comp_eqs(struct mlx5_core_dev *dev)
 			goto clean;
 		}
 		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->eqn);
-		spin_lock(&table->lock);
 		list_add_tail(&eq->list, &table->comp_eqs_list);
-		spin_unlock(&table->lock);
 	}
 
 	return 0;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 4b62d71825c1..852e397c7624 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -484,9 +484,6 @@ struct mlx5_eq_table {
 	struct mlx5_eq		pfault_eq;
 #endif
 	int			num_comp_vectors;
-	/* protect EQs list
-	 */
-	spinlock_t		lock;
 };
 
 struct mlx5_uars_page {
-- 
cgit v1.2.3


From ca828cb4686f1aece8d30541e11b8e21de1a7b0e Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:35 -0800
Subject: net/mlx5: EQ, Move all EQ logic to eq.c

Move completion EQs flows from main.c to eq.c, reasons:
1) It is where this logic belongs.
2) It will help centralize the EQ logic in one file for downstream
refactoring, and future extensions/updates.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       | 176 ++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c     | 179 +--------------------
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |   2 +
 3 files changed, 181 insertions(+), 176 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index e75272503027..4d79a4ccb758 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -820,6 +820,8 @@ void mlx5_eq_cleanup(struct mlx5_core_dev *dev)
 	mlx5_eq_debugfs_cleanup(dev);
 }
 
+/* Async EQs */
+
 int mlx5_start_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
@@ -953,12 +955,186 @@ int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
 }
 
+/* Completion EQs */
+
+static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	struct mlx5_priv *priv  = &mdev->priv;
+	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
+	int irq = pci_irq_vector(mdev->pdev, vecidx);
+
+	if (!zalloc_cpumask_var(&priv->irq_info[vecidx].mask, GFP_KERNEL)) {
+		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
+		return -ENOMEM;
+	}
+
+	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
+			priv->irq_info[vecidx].mask);
+
+	if (IS_ENABLED(CONFIG_SMP) &&
+	    irq_set_affinity_hint(irq, priv->irq_info[vecidx].mask))
+		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
+
+	return 0;
+}
+
+static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
+	struct mlx5_priv *priv  = &mdev->priv;
+	int irq = pci_irq_vector(mdev->pdev, vecidx);
+
+	irq_set_affinity_hint(irq, NULL);
+	free_cpumask_var(priv->irq_info[vecidx].mask);
+}
+
+static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
+		err = mlx5_irq_set_affinity_hint(mdev, i);
+		if (err)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	for (i--; i >= 0; i--)
+		mlx5_irq_clear_affinity_hint(mdev, i);
+
+	return err;
+}
+
+static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int i;
+
+	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
+		mlx5_irq_clear_affinity_hint(mdev, i);
+}
+
+void mlx5_free_comp_eqs(struct mlx5_core_dev *dev)
+{
+	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq *eq, *n;
+
+	mlx5_irq_clear_affinity_hints(dev);
+
+#ifdef CONFIG_RFS_ACCEL
+	if (dev->rmap) {
+		free_irq_cpu_rmap(dev->rmap);
+		dev->rmap = NULL;
+	}
+#endif
+	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
+		list_del(&eq->list);
+		if (mlx5_destroy_unmap_eq(dev, eq))
+			mlx5_core_warn(dev, "failed to destroy EQ 0x%x\n",
+				       eq->eqn);
+		kfree(eq);
+	}
+}
+
+int mlx5_alloc_comp_eqs(struct mlx5_core_dev *dev)
+{
+	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	char name[MLX5_MAX_IRQ_NAME];
+	struct mlx5_eq *eq;
+	int ncomp_vec;
+	int nent;
+	int err;
+	int i;
+
+	INIT_LIST_HEAD(&table->comp_eqs_list);
+	ncomp_vec = table->num_comp_vectors;
+	nent = MLX5_COMP_EQ_SIZE;
+#ifdef CONFIG_RFS_ACCEL
+	dev->rmap = alloc_irq_cpu_rmap(ncomp_vec);
+	if (!dev->rmap)
+		return -ENOMEM;
+#endif
+	for (i = 0; i < ncomp_vec; i++) {
+		int vecidx = i + MLX5_EQ_VEC_COMP_BASE;
+
+		eq = kzalloc(sizeof(*eq), GFP_KERNEL);
+		if (!eq) {
+			err = -ENOMEM;
+			goto clean;
+		}
+
+#ifdef CONFIG_RFS_ACCEL
+		irq_cpu_rmap_add(dev->rmap, pci_irq_vector(dev->pdev, vecidx));
+#endif
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
+		err = mlx5_create_map_eq(dev, eq, vecidx, nent, 0,
+					 name, MLX5_EQ_TYPE_COMP);
+		if (err) {
+			kfree(eq);
+			goto clean;
+		}
+		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->eqn);
+		/* add tail, to keep the list ordered, for mlx5_vector2eqn to work */
+		list_add_tail(&eq->list, &table->comp_eqs_list);
+	}
+
+	err = mlx5_irq_set_affinity_hints(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to alloc affinity hint cpumask\n");
+		goto clean;
+	}
+
+	return 0;
+
+clean:
+	mlx5_free_comp_eqs(dev);
+	return err;
+}
+
+int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
+		    unsigned int *irqn)
+{
+	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq *eq, *n;
+	int err = -ENOENT;
+	int i = 0;
+
+	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
+		if (i++ == vector) {
+			*eqn = eq->eqn;
+			*irqn = eq->irqn;
+			err = 0;
+			break;
+		}
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(mlx5_vector2eqn);
+
+struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn)
+{
+	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq *eq;
+
+	list_for_each_entry(eq, &table->comp_eqs_list, list) {
+		if (eq->eqn == eqn)
+			return eq;
+	}
+
+	return ERR_PTR(-ENOENT);
+}
+
 /* This function should only be called after mlx5_cmd_force_teardown_hca */
 void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	struct mlx5_eq *eq;
 
+	mlx5_irq_clear_affinity_hints(dev);
+
 #ifdef CONFIG_RFS_ACCEL
 	if (dev->rmap) {
 		free_irq_cpu_rmap(dev->rmap);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f692c2a42130..244fec4b2ef2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -637,168 +637,6 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
 	return (u64)timer_l | (u64)timer_h1 << 32;
 }
 
-static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	struct mlx5_priv *priv  = &mdev->priv;
-	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
-	int irq = pci_irq_vector(mdev->pdev, vecidx);
-
-	if (!zalloc_cpumask_var(&priv->irq_info[vecidx].mask, GFP_KERNEL)) {
-		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
-		return -ENOMEM;
-	}
-
-	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
-			priv->irq_info[vecidx].mask);
-
-	if (IS_ENABLED(CONFIG_SMP) &&
-	    irq_set_affinity_hint(irq, priv->irq_info[vecidx].mask))
-		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
-
-	return 0;
-}
-
-static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
-	struct mlx5_priv *priv  = &mdev->priv;
-	int irq = pci_irq_vector(mdev->pdev, vecidx);
-
-	irq_set_affinity_hint(irq, NULL);
-	free_cpumask_var(priv->irq_info[vecidx].mask);
-}
-
-static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int err;
-	int i;
-
-	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
-		err = mlx5_irq_set_affinity_hint(mdev, i);
-		if (err)
-			goto err_out;
-	}
-
-	return 0;
-
-err_out:
-	for (i--; i >= 0; i--)
-		mlx5_irq_clear_affinity_hint(mdev, i);
-
-	return err;
-}
-
-static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int i;
-
-	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
-		mlx5_irq_clear_affinity_hint(mdev, i);
-}
-
-int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
-		    unsigned int *irqn)
-{
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	struct mlx5_eq *eq, *n;
-	int err = -ENOENT;
-	int i = 0;
-
-	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
-		if (i++ == vector) {
-			*eqn = eq->eqn;
-			*irqn = eq->irqn;
-			err = 0;
-			break;
-		}
-	}
-
-	return err;
-}
-EXPORT_SYMBOL(mlx5_vector2eqn);
-
-struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn)
-{
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	struct mlx5_eq *eq;
-
-	list_for_each_entry(eq, &table->comp_eqs_list, list) {
-		if (eq->eqn == eqn)
-			return eq;
-	}
-
-
-	return ERR_PTR(-ENOENT);
-}
-
-static void free_comp_eqs(struct mlx5_core_dev *dev)
-{
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	struct mlx5_eq *eq, *n;
-
-#ifdef CONFIG_RFS_ACCEL
-	if (dev->rmap) {
-		free_irq_cpu_rmap(dev->rmap);
-		dev->rmap = NULL;
-	}
-#endif
-	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
-		list_del(&eq->list);
-		if (mlx5_destroy_unmap_eq(dev, eq))
-			mlx5_core_warn(dev, "failed to destroy EQ 0x%x\n",
-				       eq->eqn);
-		kfree(eq);
-	}
-}
-
-static int alloc_comp_eqs(struct mlx5_core_dev *dev)
-{
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	char name[MLX5_MAX_IRQ_NAME];
-	struct mlx5_eq *eq;
-	int ncomp_vec;
-	int nent;
-	int err;
-	int i;
-
-	INIT_LIST_HEAD(&table->comp_eqs_list);
-	ncomp_vec = table->num_comp_vectors;
-	nent = MLX5_COMP_EQ_SIZE;
-#ifdef CONFIG_RFS_ACCEL
-	dev->rmap = alloc_irq_cpu_rmap(ncomp_vec);
-	if (!dev->rmap)
-		return -ENOMEM;
-#endif
-	for (i = 0; i < ncomp_vec; i++) {
-		eq = kzalloc(sizeof(*eq), GFP_KERNEL);
-		if (!eq) {
-			err = -ENOMEM;
-			goto clean;
-		}
-
-#ifdef CONFIG_RFS_ACCEL
-		irq_cpu_rmap_add(dev->rmap, pci_irq_vector(dev->pdev,
-				 MLX5_EQ_VEC_COMP_BASE + i));
-#endif
-		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
-		err = mlx5_create_map_eq(dev, eq,
-					 i + MLX5_EQ_VEC_COMP_BASE, nent, 0,
-					 name, MLX5_EQ_TYPE_COMP);
-		if (err) {
-			kfree(eq);
-			goto clean;
-		}
-		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->eqn);
-		list_add_tail(&eq->list, &table->comp_eqs_list);
-	}
-
-	return 0;
-
-clean:
-	free_comp_eqs(dev);
-	return err;
-}
-
 static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
 {
 	u32 query_in[MLX5_ST_SZ_DW(query_issi_in)]   = {0};
@@ -1177,18 +1015,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_fw_tracer;
 	}
 
-	err = alloc_comp_eqs(dev);
+	err = mlx5_alloc_comp_eqs(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to alloc completion EQs\n");
 		goto err_comp_eqs;
 	}
 
-	err = mlx5_irq_set_affinity_hints(dev);
-	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n");
-		goto err_affinity_hints;
-	}
-
 	err = mlx5_fpga_device_start(dev);
 	if (err) {
 		dev_err(&pdev->dev, "fpga device start failed %d\n", err);
@@ -1257,10 +1089,7 @@ err_ipsec_start:
 	mlx5_fpga_device_stop(dev);
 
 err_fpga_start:
-	mlx5_irq_clear_affinity_hints(dev);
-
-err_affinity_hints:
-	free_comp_eqs(dev);
+	mlx5_free_comp_eqs(dev);
 
 err_comp_eqs:
 	mlx5_fw_tracer_cleanup(dev->tracer);
@@ -1331,8 +1160,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_accel_ipsec_cleanup(dev);
 	mlx5_accel_tls_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
-	mlx5_irq_clear_affinity_hints(dev);
-	free_comp_eqs(dev);
+	mlx5_free_comp_eqs(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
 	mlx5_stop_eqs(dev);
 	mlx5_put_uars_page(dev, priv->uar);
@@ -1628,7 +1456,6 @@ succeed:
 	 * kexec. There is no need to cleanup the mlx5_core software
 	 * contexts.
 	 */
-	mlx5_irq_clear_affinity_hints(dev);
 	mlx5_core_eq_free_irqs(dev);
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 0594d0961cb3..22cff00faa5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -136,6 +136,8 @@ int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 		       u32 *out, int outlen);
 int mlx5_start_eqs(struct mlx5_core_dev *dev);
 void mlx5_stop_eqs(struct mlx5_core_dev *dev);
+int mlx5_alloc_comp_eqs(struct mlx5_core_dev *dev);
+void mlx5_free_comp_eqs(struct mlx5_core_dev *dev);
 /* This function should only be called after mlx5_cmd_force_teardown_hca */
 void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
 struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
-- 
cgit v1.2.3


From c8e21b3b576b78fe1b07522aea046af2634a24e8 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:36 -0800
Subject: net/mlx5: EQ, Create all EQs in one place

Instead of creating the EQ table in three steps at driver load,
 - allocate irq vectors
 - allocate async EQs
 - allocate completion EQs
Gather all of the procedures into one function in eq.c and call it from
driver load.

This will help us reduce the EQ and EQ table private structures
visibility to eq.c in downstream refactoring.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c  |  10 ++
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       | 121 ++++++++++++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  81 ++------------
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |   8 +-
 4 files changed, 116 insertions(+), 104 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 90fabd612b6c..b76766fb6c67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -349,6 +349,16 @@ out:
 	return param;
 }
 
+static int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
+			      u32 *out, int outlen)
+{
+	u32 in[MLX5_ST_SZ_DW(query_eq_in)] = {};
+
+	MLX5_SET(query_eq_in, in, opcode, MLX5_CMD_OP_QUERY_EQ);
+	MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
 static u64 eq_read_field(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 			 int index)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 4d79a4ccb758..44ccd4206104 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -822,7 +822,7 @@ void mlx5_eq_cleanup(struct mlx5_core_dev *dev)
 
 /* Async EQs */
 
-int mlx5_start_eqs(struct mlx5_core_dev *dev)
+static int create_async_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
@@ -914,7 +914,7 @@ err1:
 	return err;
 }
 
-void mlx5_stop_eqs(struct mlx5_core_dev *dev)
+static void destroy_async_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	int err;
@@ -945,19 +945,9 @@ void mlx5_stop_eqs(struct mlx5_core_dev *dev)
 			      err);
 }
 
-int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
-		       u32 *out, int outlen)
-{
-	u32 in[MLX5_ST_SZ_DW(query_eq_in)] = {0};
-
-	MLX5_SET(query_eq_in, in, opcode, MLX5_CMD_OP_QUERY_EQ);
-	MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
-}
-
 /* Completion EQs */
 
-static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
+static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
 {
 	struct mlx5_priv *priv  = &mdev->priv;
 	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
@@ -978,7 +968,7 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	return 0;
 }
 
-static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
+static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
 {
 	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
 	struct mlx5_priv *priv  = &mdev->priv;
@@ -988,13 +978,13 @@ static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	free_cpumask_var(priv->irq_info[vecidx].mask);
 }
 
-static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
+static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev)
 {
 	int err;
 	int i;
 
 	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
-		err = mlx5_irq_set_affinity_hint(mdev, i);
+		err = set_comp_irq_affinity_hint(mdev, i);
 		if (err)
 			goto err_out;
 	}
@@ -1003,25 +993,25 @@ static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
 
 err_out:
 	for (i--; i >= 0; i--)
-		mlx5_irq_clear_affinity_hint(mdev, i);
+		clear_comp_irq_affinity_hint(mdev, i);
 
 	return err;
 }
 
-static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
+static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev)
 {
 	int i;
 
 	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
-		mlx5_irq_clear_affinity_hint(mdev, i);
+		clear_comp_irq_affinity_hint(mdev, i);
 }
 
-void mlx5_free_comp_eqs(struct mlx5_core_dev *dev)
+static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	struct mlx5_eq *eq, *n;
 
-	mlx5_irq_clear_affinity_hints(dev);
+	clear_comp_irqs_affinity_hints(dev);
 
 #ifdef CONFIG_RFS_ACCEL
 	if (dev->rmap) {
@@ -1038,7 +1028,7 @@ void mlx5_free_comp_eqs(struct mlx5_core_dev *dev)
 	}
 }
 
-int mlx5_alloc_comp_eqs(struct mlx5_core_dev *dev)
+static int create_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	char name[MLX5_MAX_IRQ_NAME];
@@ -1080,7 +1070,7 @@ int mlx5_alloc_comp_eqs(struct mlx5_core_dev *dev)
 		list_add_tail(&eq->list, &table->comp_eqs_list);
 	}
 
-	err = mlx5_irq_set_affinity_hints(dev);
+	err = set_comp_irq_affinity_hints(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to alloc affinity hint cpumask\n");
 		goto clean;
@@ -1089,7 +1079,7 @@ int mlx5_alloc_comp_eqs(struct mlx5_core_dev *dev)
 	return 0;
 
 clean:
-	mlx5_free_comp_eqs(dev);
+	destroy_comp_eqs(dev);
 	return err;
 }
 
@@ -1133,7 +1123,7 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	struct mlx5_eq *eq;
 
-	mlx5_irq_clear_affinity_hints(dev);
+	clear_comp_irqs_affinity_hints(dev);
 
 #ifdef CONFIG_RFS_ACCEL
 	if (dev->rmap) {
@@ -1153,3 +1143,84 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 #endif
 	pci_free_irq_vectors(dev->pdev);
 }
+
+static int alloc_irq_vectors(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+	struct mlx5_eq_table *table = &priv->eq_table;
+	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+		      MLX5_CAP_GEN(dev, max_num_eqs) :
+		      1 << MLX5_CAP_GEN(dev, log_max_eq);
+	int nvec;
+	int err;
+
+	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
+	       MLX5_EQ_VEC_COMP_BASE;
+	nvec = min_t(int, nvec, num_eqs);
+	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
+		return -ENOMEM;
+
+	priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL);
+	if (!priv->irq_info)
+		return -ENOMEM;
+
+	nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1,
+				     nvec, PCI_IRQ_MSIX);
+	if (nvec < 0) {
+		err = nvec;
+		goto err_free_irq_info;
+	}
+
+	table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE;
+
+	return 0;
+
+err_free_irq_info:
+	kfree(priv->irq_info);
+	return err;
+}
+
+static void free_irq_vectors(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+
+	pci_free_irq_vectors(dev->pdev);
+	kfree(priv->irq_info);
+}
+
+int mlx5_eq_table_create(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = alloc_irq_vectors(dev);
+	if (err) {
+		mlx5_core_err(dev, "alloc irq vectors failed\n");
+		return err;
+	}
+
+	err = create_async_eqs(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to create async EQs\n");
+		goto err_async_eqs;
+	}
+
+	err = create_comp_eqs(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to create completion EQs\n");
+		goto err_comp_eqs;
+	}
+
+	return 0;
+err_comp_eqs:
+	destroy_async_eqs(dev);
+err_async_eqs:
+	free_irq_vectors(dev);
+	return err;
+}
+
+void mlx5_eq_table_destroy(struct mlx5_core_dev *dev)
+{
+	destroy_comp_eqs(dev);
+	destroy_async_eqs(dev);
+	free_irq_vectors(dev);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 244fec4b2ef2..21cc9bbc2563 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -319,51 +319,6 @@ static void release_bar(struct pci_dev *pdev)
 	pci_release_regions(pdev);
 }
 
-static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
-{
-	struct mlx5_priv *priv = &dev->priv;
-	struct mlx5_eq_table *table = &priv->eq_table;
-	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
-		      MLX5_CAP_GEN(dev, max_num_eqs) :
-		      1 << MLX5_CAP_GEN(dev, log_max_eq);
-	int nvec;
-	int err;
-
-	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
-	       MLX5_EQ_VEC_COMP_BASE;
-	nvec = min_t(int, nvec, num_eqs);
-	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
-		return -ENOMEM;
-
-	priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL);
-	if (!priv->irq_info)
-		return -ENOMEM;
-
-	nvec = pci_alloc_irq_vectors(dev->pdev,
-			MLX5_EQ_VEC_COMP_BASE + 1, nvec,
-			PCI_IRQ_MSIX);
-	if (nvec < 0) {
-		err = nvec;
-		goto err_free_irq_info;
-	}
-
-	table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE;
-
-	return 0;
-
-err_free_irq_info:
-	kfree(priv->irq_info);
-	return err;
-}
-
-static void mlx5_free_irq_vectors(struct mlx5_core_dev *dev)
-{
-	struct mlx5_priv *priv = &dev->priv;
-
-	pci_free_irq_vectors(dev->pdev);
-	kfree(priv->irq_info);
-}
-
 struct mlx5_reg_host_endianness {
 	u8	he;
 	u8      rsvd[15];
@@ -990,23 +945,17 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		}
 	}
 
-	err = mlx5_alloc_irq_vectors(dev);
-	if (err) {
-		dev_err(&pdev->dev, "alloc irq vectors failed\n");
-		goto err_cleanup_once;
-	}
-
 	dev->priv.uar = mlx5_get_uars_page(dev);
 	if (IS_ERR(dev->priv.uar)) {
 		dev_err(&pdev->dev, "Failed allocating uar, aborting\n");
 		err = PTR_ERR(dev->priv.uar);
-		goto err_disable_msix;
+		goto err_get_uars;
 	}
 
-	err = mlx5_start_eqs(dev);
+	err = mlx5_eq_table_create(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to start pages and async EQs\n");
-		goto err_put_uars;
+		dev_err(&pdev->dev, "Failed to create EQs\n");
+		goto err_eq_table;
 	}
 
 	err = mlx5_fw_tracer_init(dev->tracer);
@@ -1015,12 +964,6 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_fw_tracer;
 	}
 
-	err = mlx5_alloc_comp_eqs(dev);
-	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc completion EQs\n");
-		goto err_comp_eqs;
-	}
-
 	err = mlx5_fpga_device_start(dev);
 	if (err) {
 		dev_err(&pdev->dev, "fpga device start failed %d\n", err);
@@ -1089,21 +1032,15 @@ err_ipsec_start:
 	mlx5_fpga_device_stop(dev);
 
 err_fpga_start:
-	mlx5_free_comp_eqs(dev);
-
-err_comp_eqs:
 	mlx5_fw_tracer_cleanup(dev->tracer);
 
 err_fw_tracer:
-	mlx5_stop_eqs(dev);
+	mlx5_eq_table_destroy(dev);
 
-err_put_uars:
+err_eq_table:
 	mlx5_put_uars_page(dev, priv->uar);
 
-err_disable_msix:
-	mlx5_free_irq_vectors(dev);
-
-err_cleanup_once:
+err_get_uars:
 	if (boot)
 		mlx5_cleanup_once(dev);
 
@@ -1160,11 +1097,9 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_accel_ipsec_cleanup(dev);
 	mlx5_accel_tls_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
-	mlx5_free_comp_eqs(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
-	mlx5_stop_eqs(dev);
+	mlx5_eq_table_destroy(dev);
 	mlx5_put_uars_page(dev, priv->uar);
-	mlx5_free_irq_vectors(dev);
 	if (cleanup)
 		mlx5_cleanup_once(dev);
 	mlx5_stop_health_poll(dev, cleanup);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 22cff00faa5a..3fa6d26875fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -132,12 +132,8 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
 int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
 int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
-		       u32 *out, int outlen);
-int mlx5_start_eqs(struct mlx5_core_dev *dev);
-void mlx5_stop_eqs(struct mlx5_core_dev *dev);
-int mlx5_alloc_comp_eqs(struct mlx5_core_dev *dev);
-void mlx5_free_comp_eqs(struct mlx5_core_dev *dev);
+int mlx5_eq_table_create(struct mlx5_core_dev *dev);
+void mlx5_eq_table_destroy(struct mlx5_core_dev *dev);
 /* This function should only be called after mlx5_cmd_force_teardown_hca */
 void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
 struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
-- 
cgit v1.2.3


From d674a9aa434409826b2408609be493739e61e6f6 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:37 -0800
Subject: net/mlx5: EQ, irq_info and rmap belong to eq_table

irq_info and rmap are EQ properties of the driver, and only needed for
EQ objects, move them to the eq_table EQs database structure.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |  4 +--
 drivers/net/ethernet/mellanox/mlx5/core/eq.c      | 40 ++++++++++++-----------
 include/linux/mlx5/driver.h                       | 10 +++---
 3 files changed, 28 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2839c30dd3a0..32ea47c28324 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1760,7 +1760,7 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
 
 static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
 {
-	return cpumask_first(priv->mdev->priv.irq_info[ix + MLX5_EQ_VEC_COMP_BASE].mask);
+	return cpumask_first(priv->mdev->priv.eq_table.irq_info[ix + MLX5_EQ_VEC_COMP_BASE].mask);
 }
 
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
@@ -4960,7 +4960,7 @@ int mlx5e_netdev_init(struct net_device *netdev,
 	netif_carrier_off(netdev);
 
 #ifdef CONFIG_MLX5_EN_ARFS
-	netdev->rx_cpu_rmap = mdev->rmap;
+	netdev->rx_cpu_rmap = mdev->priv.eq_table.rmap;
 #endif
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 44ccd4206104..70f62f10065e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -694,7 +694,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	if (err)
 		goto err_in;
 
-	snprintf(priv->irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s",
+	snprintf(priv->eq_table.irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s",
 		 name, pci_name(dev->pdev));
 
 	eq->eqn = MLX5_GET(create_eq_out, out, eq_number);
@@ -702,7 +702,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	eq->dev = dev;
 	eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET;
 	err = request_irq(eq->irqn, handler, 0,
-			  priv->irq_info[vecidx].name, eq);
+			  priv->eq_table.irq_info[vecidx].name, eq);
 	if (err)
 		goto err_eq;
 
@@ -952,17 +952,18 @@ static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	struct mlx5_priv *priv  = &mdev->priv;
 	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
 	int irq = pci_irq_vector(mdev->pdev, vecidx);
+	struct mlx5_irq_info *irq_info = &priv->eq_table.irq_info[vecidx];
 
-	if (!zalloc_cpumask_var(&priv->irq_info[vecidx].mask, GFP_KERNEL)) {
+	if (!zalloc_cpumask_var(&irq_info->mask, GFP_KERNEL)) {
 		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
 		return -ENOMEM;
 	}
 
 	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
-			priv->irq_info[vecidx].mask);
+			irq_info->mask);
 
 	if (IS_ENABLED(CONFIG_SMP) &&
-	    irq_set_affinity_hint(irq, priv->irq_info[vecidx].mask))
+	    irq_set_affinity_hint(irq, irq_info->mask))
 		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
 
 	return 0;
@@ -973,9 +974,10 @@ static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
 	struct mlx5_priv *priv  = &mdev->priv;
 	int irq = pci_irq_vector(mdev->pdev, vecidx);
+	struct mlx5_irq_info *irq_info = &priv->eq_table.irq_info[vecidx];
 
 	irq_set_affinity_hint(irq, NULL);
-	free_cpumask_var(priv->irq_info[vecidx].mask);
+	free_cpumask_var(irq_info->mask);
 }
 
 static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev)
@@ -1014,9 +1016,9 @@ static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 	clear_comp_irqs_affinity_hints(dev);
 
 #ifdef CONFIG_RFS_ACCEL
-	if (dev->rmap) {
-		free_irq_cpu_rmap(dev->rmap);
-		dev->rmap = NULL;
+	if (table->rmap) {
+		free_irq_cpu_rmap(table->rmap);
+		table->rmap = NULL;
 	}
 #endif
 	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
@@ -1042,8 +1044,8 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 	ncomp_vec = table->num_comp_vectors;
 	nent = MLX5_COMP_EQ_SIZE;
 #ifdef CONFIG_RFS_ACCEL
-	dev->rmap = alloc_irq_cpu_rmap(ncomp_vec);
-	if (!dev->rmap)
+	table->rmap = alloc_irq_cpu_rmap(ncomp_vec);
+	if (!table->rmap)
 		return -ENOMEM;
 #endif
 	for (i = 0; i < ncomp_vec; i++) {
@@ -1056,7 +1058,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 		}
 
 #ifdef CONFIG_RFS_ACCEL
-		irq_cpu_rmap_add(dev->rmap, pci_irq_vector(dev->pdev, vecidx));
+		irq_cpu_rmap_add(table->rmap, pci_irq_vector(dev->pdev, vecidx));
 #endif
 		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
 		err = mlx5_create_map_eq(dev, eq, vecidx, nent, 0,
@@ -1126,9 +1128,9 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 	clear_comp_irqs_affinity_hints(dev);
 
 #ifdef CONFIG_RFS_ACCEL
-	if (dev->rmap) {
-		free_irq_cpu_rmap(dev->rmap);
-		dev->rmap = NULL;
+	if (table->rmap) {
+		free_irq_cpu_rmap(table->rmap);
+		table->rmap = NULL;
 	}
 #endif
 	list_for_each_entry(eq, &table->comp_eqs_list, list)
@@ -1160,8 +1162,8 @@ static int alloc_irq_vectors(struct mlx5_core_dev *dev)
 	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
 		return -ENOMEM;
 
-	priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL);
-	if (!priv->irq_info)
+	table->irq_info = kcalloc(nvec, sizeof(*table->irq_info), GFP_KERNEL);
+	if (!table->irq_info)
 		return -ENOMEM;
 
 	nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1,
@@ -1176,7 +1178,7 @@ static int alloc_irq_vectors(struct mlx5_core_dev *dev)
 	return 0;
 
 err_free_irq_info:
-	kfree(priv->irq_info);
+	kfree(table->irq_info);
 	return err;
 }
 
@@ -1185,7 +1187,7 @@ static void free_irq_vectors(struct mlx5_core_dev *dev)
 	struct mlx5_priv *priv = &dev->priv;
 
 	pci_free_irq_vectors(dev->pdev);
-	kfree(priv->irq_info);
+	kfree(priv->eq_table.irq_info);
 }
 
 int mlx5_eq_table_create(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 852e397c7624..dcc3f7aa8572 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -484,6 +484,10 @@ struct mlx5_eq_table {
 	struct mlx5_eq		pfault_eq;
 #endif
 	int			num_comp_vectors;
+	struct mlx5_irq_info	*irq_info;
+#ifdef CONFIG_RFS_ACCEL
+	struct cpu_rmap         *rmap;
+#endif
 };
 
 struct mlx5_uars_page {
@@ -640,7 +644,6 @@ struct mlx5_port_module_event_stats {
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	eq_table;
-	struct mlx5_irq_info	*irq_info;
 
 	/* pages stuff */
 	struct workqueue_struct *pg_wq;
@@ -851,9 +854,6 @@ struct mlx5_core_dev {
 	} roce;
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
-#endif
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap         *rmap;
 #endif
 	struct mlx5_clock        clock;
 	struct mlx5_ib_clock_info  *clock_info;
@@ -1302,7 +1302,7 @@ enum {
 static inline const struct cpumask *
 mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector)
 {
-	return dev->priv.irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask;
+	return dev->priv.eq_table.irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask;
 }
 
 #endif /* MLX5_DRIVER_H */
-- 
cgit v1.2.3


From f2f3df5501391bc784c8462dc97d989c2194fb74 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:38 -0800
Subject: net/mlx5: EQ, Privatize eq_table and friends

Move unnecessary EQ table structures and declaration from the
public include/linux/mlx5/driver.h into the private area of mlx5_core
and into eq.c/eq.h.

Introduce new mlx5 EQ APIs:

mlx5_comp_vectors_count(dev);
mlx5_comp_irq_get_affinity_mask(dev, vector);

And use them from mlx5_ib or mlx5e netdevice instead of direct access to
mlx5_core internal structures.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c                  |   5 +-
 drivers/net/ethernet/mellanox/mlx5/core/cq.c       |   5 +-
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c  |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   3 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  10 +-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       | 102 ++++++++++++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/health.c   |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h   |  77 ++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |   7 +-
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |  15 ---
 include/linux/mlx5/driver.h                        |  87 +-----------------
 12 files changed, 179 insertions(+), 135 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index e9c428071df3..6fbc0cba1bac 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -5337,7 +5337,7 @@ mlx5_ib_get_vector_affinity(struct ib_device *ibdev, int comp_vector)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 
-	return mlx5_get_vector_affinity_hint(dev->mdev, comp_vector);
+	return mlx5_comp_irq_get_affinity_mask(dev->mdev, comp_vector);
 }
 
 /* The mlx5_ib_multiport_mutex should be held when calling this function */
@@ -5701,8 +5701,7 @@ int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	dev->ib_dev.node_type		= RDMA_NODE_IB_CA;
 	dev->ib_dev.local_dma_lkey	= 0 /* not supported for now */;
 	dev->ib_dev.phys_port_cnt	= dev->num_ports;
-	dev->ib_dev.num_comp_vectors    =
-		dev->mdev->priv.eq_table.num_comp_vectors;
+	dev->ib_dev.num_comp_vectors    = mlx5_comp_vectors_count(mdev);
 	dev->ib_dev.dev.parent		= &mdev->pdev->dev;
 
 	mutex_init(&dev->cap_mask_mutex);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 4b85abb5c9f7..6e55d2f37c6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -38,6 +38,7 @@
 #include <rdma/ib_verbs.h>
 #include <linux/mlx5/cq.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 #define TASKLET_MAX_TIME 2
 #define TASKLET_MAX_TIME_JIFFIES msecs_to_jiffies(TASKLET_MAX_TIME)
@@ -124,7 +125,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 		goto err_cmd;
 
 	/* Add to async EQ CQ tree to recv async events */
-	err = mlx5_eq_add_cq(&dev->priv.eq_table.async_eq, cq);
+	err = mlx5_eq_add_cq(mlx5_get_async_eq(dev), cq);
 	if (err)
 		goto err_cq_add;
 
@@ -157,7 +158,7 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 	u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {0};
 	int err;
 
-	err = mlx5_eq_del_cq(&dev->priv.eq_table.async_eq, cq);
+	err = mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index b76766fb6c67..a11e22d0b0cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -36,6 +36,7 @@
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/driver.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 enum {
 	QP_PID,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index d7fbd5b6ac95..aea74856c702 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -178,8 +178,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 {
 	return is_kdump_kernel() ?
 		MLX5E_MIN_NUM_CHANNELS :
-		min_t(int, mdev->priv.eq_table.num_comp_vectors,
-		      MLX5E_MAX_NUM_CHANNELS);
+		min_t(int, mlx5_comp_vectors_count(mdev), MLX5E_MAX_NUM_CHANNELS);
 }
 
 /* Use this function to get max num channels after netdev was created */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 32ea47c28324..c23caade31bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -49,6 +49,7 @@
 #include "lib/clock.h"
 #include "en/port.h"
 #include "en/xdp.h"
+#include "lib/eq.h"
 
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
@@ -1758,11 +1759,6 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
 	mlx5e_free_cq(cq);
 }
 
-static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
-{
-	return cpumask_first(priv->mdev->priv.eq_table.irq_info[ix + MLX5_EQ_VEC_COMP_BASE].mask);
-}
-
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_channel_param *cparam)
@@ -1913,9 +1909,9 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 			      struct mlx5e_channel_param *cparam,
 			      struct mlx5e_channel **cp)
 {
+	int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
 	struct net_dim_cq_moder icocq_moder = {0, 0};
 	struct net_device *netdev = priv->netdev;
-	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
 	unsigned int irq;
 	int err;
@@ -4960,7 +4956,7 @@ int mlx5e_netdev_init(struct net_device *netdev,
 	netif_carrier_off(netdev);
 
 #ifdef CONFIG_MLX5_EN_ARFS
-	netdev->rx_cpu_rmap = mdev->priv.eq_table.rmap;
+	netdev->rx_cpu_rmap =  mlx5_eq_table_get_rmap(mdev);
 #endif
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 70f62f10065e..32ce20221c44 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -38,6 +38,7 @@
 #include <linux/cpu_rmap.h>
 #endif
 #include "mlx5_core.h"
+#include "lib/eq.h"
 #include "fpga/core.h"
 #include "eswitch.h"
 #include "lib/clock.h"
@@ -65,6 +66,26 @@ enum {
 	MLX5_EQ_DOORBEL_OFFSET	= 0x40,
 };
 
+struct mlx5_irq_info {
+	cpumask_var_t mask;
+	char name[MLX5_MAX_IRQ_NAME];
+};
+
+struct mlx5_eq_table {
+	struct list_head	comp_eqs_list;
+	struct mlx5_eq		pages_eq;
+	struct mlx5_eq		async_eq;
+	struct mlx5_eq		cmd_eq;
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	struct mlx5_eq		pfault_eq;
+#endif
+	int			num_comp_vectors;
+	struct mlx5_irq_info	*irq_info;
+#ifdef CONFIG_RFS_ACCEL
+	struct cpu_rmap         *rmap;
+#endif
+};
+
 #define MLX5_ASYNC_EVENT_MASK ((1ull << MLX5_EVENT_TYPE_PATH_MIG)	    | \
 			       (1ull << MLX5_EVENT_TYPE_COMM_EST)	    | \
 			       (1ull << MLX5_EVENT_TYPE_SQ_DRAINED)	    | \
@@ -633,10 +654,11 @@ static void init_eq_buf(struct mlx5_eq *eq)
 	}
 }
 
-int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
-		       int nent, u64 mask, const char *name,
-		       enum mlx5_eq_type type)
+static int
+mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
+		   int nent, u64 mask, const char *name, enum mlx5_eq_type type)
 {
+	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	struct mlx5_cq_table *cq_table = &eq->cq_table;
 	u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0};
 	struct mlx5_priv *priv = &dev->priv;
@@ -694,7 +716,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	if (err)
 		goto err_in;
 
-	snprintf(priv->eq_table.irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s",
+	snprintf(eq_table->irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s",
 		 name, pci_name(dev->pdev));
 
 	eq->eqn = MLX5_GET(create_eq_out, out, eq_number);
@@ -702,7 +724,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	eq->dev = dev;
 	eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET;
 	err = request_irq(eq->irqn, handler, 0,
-			  priv->eq_table.irq_info[vecidx].name, eq);
+			  eq_table->irq_info[vecidx].name, eq);
 	if (err)
 		goto err_eq;
 
@@ -746,7 +768,7 @@ err_buf:
 	return err;
 }
 
-int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+static int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 {
 	int err;
 
@@ -806,25 +828,35 @@ int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 	return 0;
 }
 
-int mlx5_eq_init(struct mlx5_core_dev *dev)
+int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 {
+	struct mlx5_eq_table *eq_table;
 	int err;
 
+	eq_table = kvzalloc(sizeof(*eq_table), GFP_KERNEL);
+	if (!eq_table)
+		return -ENOMEM;
+
+	dev->priv.eq_table = eq_table;
+
 	err = mlx5_eq_debugfs_init(dev);
+	if (err)
+		kvfree(eq_table);
 
 	return err;
 }
 
-void mlx5_eq_cleanup(struct mlx5_core_dev *dev)
+void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev)
 {
 	mlx5_eq_debugfs_cleanup(dev);
+	kvfree(dev->priv.eq_table);
 }
 
 /* Async EQs */
 
 static int create_async_eqs(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq_table *table = dev->priv.eq_table;
 	u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
 	int err;
 
@@ -916,7 +948,7 @@ err1:
 
 static void destroy_async_eqs(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq_table *table = dev->priv.eq_table;
 	int err;
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
@@ -945,6 +977,11 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev)
 			      err);
 }
 
+struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev)
+{
+	return &dev->priv.eq_table->async_eq;
+}
+
 /* Completion EQs */
 
 static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
@@ -952,7 +989,7 @@ static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	struct mlx5_priv *priv  = &mdev->priv;
 	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
 	int irq = pci_irq_vector(mdev->pdev, vecidx);
-	struct mlx5_irq_info *irq_info = &priv->eq_table.irq_info[vecidx];
+	struct mlx5_irq_info *irq_info = &priv->eq_table->irq_info[vecidx];
 
 	if (!zalloc_cpumask_var(&irq_info->mask, GFP_KERNEL)) {
 		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
@@ -974,7 +1011,7 @@ static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
 	struct mlx5_priv *priv  = &mdev->priv;
 	int irq = pci_irq_vector(mdev->pdev, vecidx);
-	struct mlx5_irq_info *irq_info = &priv->eq_table.irq_info[vecidx];
+	struct mlx5_irq_info *irq_info = &priv->eq_table->irq_info[vecidx];
 
 	irq_set_affinity_hint(irq, NULL);
 	free_cpumask_var(irq_info->mask);
@@ -985,7 +1022,7 @@ static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev)
 	int err;
 	int i;
 
-	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
+	for (i = 0; i < mdev->priv.eq_table->num_comp_vectors; i++) {
 		err = set_comp_irq_affinity_hint(mdev, i);
 		if (err)
 			goto err_out;
@@ -1004,13 +1041,13 @@ static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev)
 {
 	int i;
 
-	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
+	for (i = 0; i < mdev->priv.eq_table->num_comp_vectors; i++)
 		clear_comp_irq_affinity_hint(mdev, i);
 }
 
 static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_eq *eq, *n;
 
 	clear_comp_irqs_affinity_hints(dev);
@@ -1032,7 +1069,7 @@ static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 
 static int create_comp_eqs(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq_table *table = dev->priv.eq_table;
 	char name[MLX5_MAX_IRQ_NAME];
 	struct mlx5_eq *eq;
 	int ncomp_vec;
@@ -1088,7 +1125,7 @@ clean:
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 		    unsigned int *irqn)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_eq *eq, *n;
 	int err = -ENOENT;
 	int i = 0;
@@ -1106,9 +1143,32 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 }
 EXPORT_SYMBOL(mlx5_vector2eqn);
 
+unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev)
+{
+	return dev->priv.eq_table->num_comp_vectors;
+}
+EXPORT_SYMBOL(mlx5_comp_vectors_count);
+
+struct cpumask *
+mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector)
+{
+	/* TODO: consider irq_get_affinity_mask(irq) */
+	return dev->priv.eq_table->irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask;
+}
+EXPORT_SYMBOL(mlx5_comp_irq_get_affinity_mask);
+
+struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev)
+{
+#ifdef CONFIG_RFS_ACCEL
+	return dev->priv.eq_table->rmap;
+#else
+	return NULL;
+#endif
+}
+
 struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_eq *eq;
 
 	list_for_each_entry(eq, &table->comp_eqs_list, list) {
@@ -1122,7 +1182,7 @@ struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn)
 /* This function should only be called after mlx5_cmd_force_teardown_hca */
 void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_eq *eq;
 
 	clear_comp_irqs_affinity_hints(dev);
@@ -1149,7 +1209,7 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 static int alloc_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
-	struct mlx5_eq_table *table = &priv->eq_table;
+	struct mlx5_eq_table *table = priv->eq_table;
 	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
 		      MLX5_CAP_GEN(dev, max_num_eqs) :
 		      1 << MLX5_CAP_GEN(dev, log_max_eq);
@@ -1187,7 +1247,7 @@ static void free_irq_vectors(struct mlx5_core_dev *dev)
 	struct mlx5_priv *priv = &dev->priv;
 
 	pci_free_irq_vectors(dev->pdev);
-	kfree(priv->eq_table.irq_info);
+	kfree(priv->eq_table->irq_info);
 }
 
 int mlx5_eq_table_create(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index d004957328f9..324606227b1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -38,6 +38,7 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 #include "fs_core.h"
+#include "lib/eq.h"
 
 #define UPLINK_VPORT 0xFFFF
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 43118de8ee99..b5be6f0b9ed5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -38,6 +38,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 enum {
 	MLX5_HEALTH_POLL_INTERVAL	= 2 * HZ,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
new file mode 100644
index 000000000000..48ee37797b3f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies */
+
+#ifndef __LIB_MLX5_EQ_H__
+#define __LIB_MLX5_EQ_H__
+#include <linux/mlx5/driver.h>
+
+#define MLX5_MAX_IRQ_NAME       (32)
+
+enum {
+	MLX5_EQ_VEC_PAGES	 = 0,
+	MLX5_EQ_VEC_CMD		 = 1,
+	MLX5_EQ_VEC_ASYNC	 = 2,
+	MLX5_EQ_VEC_PFAULT	 = 3,
+	MLX5_EQ_VEC_COMP_BASE,
+};
+
+struct mlx5_eq_tasklet {
+	struct list_head      list;
+	struct list_head      process_list;
+	struct tasklet_struct task;
+	spinlock_t            lock; /* lock completion tasklet list */
+};
+
+struct mlx5_eq_pagefault {
+	struct work_struct       work;
+	spinlock_t               lock; /* Pagefaults spinlock */
+	struct workqueue_struct  *wq;
+	mempool_t                *pool;
+};
+
+struct mlx5_cq_table {
+	spinlock_t              lock;	/* protect radix tree */
+	struct radix_tree_root  tree;
+};
+
+struct mlx5_eq {
+	struct mlx5_core_dev    *dev;
+	struct mlx5_cq_table    cq_table;
+	__be32 __iomem	        *doorbell;
+	u32                     cons_index;
+	struct mlx5_frag_buf    buf;
+	int                     size;
+	unsigned int            irqn;
+	u8                      eqn;
+	int                     nent;
+	struct list_head        list;
+	struct mlx5_rsc_debug   *dbg;
+	enum mlx5_eq_type       type;
+	union {
+		struct mlx5_eq_tasklet   tasklet_ctx;
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+		struct mlx5_eq_pagefault pf_ctx;
+#endif
+	};
+};
+
+int mlx5_eq_table_init(struct mlx5_core_dev *dev);
+void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev);
+int mlx5_eq_table_create(struct mlx5_core_dev *dev);
+void mlx5_eq_table_destroy(struct mlx5_core_dev *dev);
+int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
+int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
+struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
+struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev);
+u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq);
+void mlx5_cq_tasklet_cb(unsigned long data);
+struct cpumask *mlx5_eq_comp_cpumask(struct mlx5_core_dev *dev, int ix);
+
+/* This function should only be called after mlx5_cmd_force_teardown_hca */
+void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
+
+#ifdef CONFIG_RFS_ACCEL
+struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev);
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 21cc9bbc2563..5d11ef92c8b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -54,6 +54,7 @@
 #include <net/devlink.h>
 #include "mlx5_core.h"
 #include "fs_core.h"
+#include "lib/eq.h"
 #include "lib/mpfs.h"
 #include "eswitch.h"
 #include "lib/mlx5.h"
@@ -728,7 +729,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 		goto out;
 	}
 
-	err = mlx5_eq_init(dev);
+	err = mlx5_eq_table_init(dev);
 	if (err) {
 		dev_err(&pdev->dev, "failed to initialize eq\n");
 		goto out;
@@ -802,7 +803,7 @@ err_tables_cleanup:
 	mlx5_cq_debugfs_cleanup(dev);
 
 err_eq_cleanup:
-	mlx5_eq_cleanup(dev);
+	mlx5_eq_table_cleanup(dev);
 
 out:
 	return err;
@@ -823,7 +824,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
 	mlx5_cq_debugfs_cleanup(dev);
-	mlx5_eq_cleanup(dev);
+	mlx5_eq_table_cleanup(dev);
 }
 
 static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 3fa6d26875fe..4d39adcfb0eb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -124,21 +124,6 @@ int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
 u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
 
-int mlx5_eq_init(struct mlx5_core_dev *dev);
-void mlx5_eq_cleanup(struct mlx5_core_dev *dev);
-int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
-		       int nent, u64 mask, const char *name,
-		       enum mlx5_eq_type type);
-int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-int mlx5_eq_table_create(struct mlx5_core_dev *dev);
-void mlx5_eq_table_destroy(struct mlx5_core_dev *dev);
-/* This function should only be called after mlx5_cmd_force_teardown_hca */
-void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
-struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
-u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq);
-void mlx5_cq_tasklet_cb(unsigned long data);
 void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
 int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
 void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index dcc3f7aa8572..4d6246cb6c19 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -84,18 +84,6 @@ enum {
 	MLX5_MAX_PORTS	= 2,
 };
 
-enum {
-	MLX5_EQ_VEC_PAGES	 = 0,
-	MLX5_EQ_VEC_CMD		 = 1,
-	MLX5_EQ_VEC_ASYNC	 = 2,
-	MLX5_EQ_VEC_PFAULT	 = 3,
-	MLX5_EQ_VEC_COMP_BASE,
-};
-
-enum {
-	MLX5_MAX_IRQ_NAME	= 32
-};
-
 enum {
 	MLX5_ATOMIC_MODE_OFFSET = 16,
 	MLX5_ATOMIC_MODE_IB_COMP = 1,
@@ -366,49 +354,6 @@ struct mlx5_frag_buf_ctrl {
 	u8			log_frag_strides;
 };
 
-struct mlx5_eq_tasklet {
-	struct list_head list;
-	struct list_head process_list;
-	struct tasklet_struct task;
-	/* lock on completion tasklet list */
-	spinlock_t lock;
-};
-
-struct mlx5_eq_pagefault {
-	struct work_struct       work;
-	/* Pagefaults lock */
-	spinlock_t		 lock;
-	struct workqueue_struct *wq;
-	mempool_t		*pool;
-};
-
-struct mlx5_cq_table {
-	/* protect radix tree */
-	spinlock_t		lock;
-	struct radix_tree_root	tree;
-};
-
-struct mlx5_eq {
-	struct mlx5_core_dev   *dev;
-	struct mlx5_cq_table	cq_table;
-	__be32 __iomem	       *doorbell;
-	u32			cons_index;
-	struct mlx5_frag_buf	buf;
-	int			size;
-	unsigned int		irqn;
-	u8			eqn;
-	int			nent;
-	struct list_head	list;
-	struct mlx5_rsc_debug	*dbg;
-	enum mlx5_eq_type	type;
-	union {
-		struct mlx5_eq_tasklet   tasklet_ctx;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-		struct mlx5_eq_pagefault pf_ctx;
-#endif
-	};
-};
-
 struct mlx5_core_psv {
 	u32	psv_idx;
 	struct psv_layout {
@@ -475,21 +420,6 @@ struct mlx5_core_srq {
 	u16		uid;
 };
 
-struct mlx5_eq_table {
-	struct list_head	comp_eqs_list;
-	struct mlx5_eq		pages_eq;
-	struct mlx5_eq		async_eq;
-	struct mlx5_eq		cmd_eq;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	struct mlx5_eq		pfault_eq;
-#endif
-	int			num_comp_vectors;
-	struct mlx5_irq_info	*irq_info;
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap         *rmap;
-#endif
-};
-
 struct mlx5_uars_page {
 	void __iomem	       *map;
 	bool			wc;
@@ -572,11 +502,6 @@ struct mlx5_core_sriov {
 	int			enabled_vfs;
 };
 
-struct mlx5_irq_info {
-	cpumask_var_t mask;
-	char name[MLX5_MAX_IRQ_NAME];
-};
-
 struct mlx5_fc_stats {
 	spinlock_t counters_idr_lock; /* protects counters_idr */
 	struct idr counters_idr;
@@ -594,6 +519,7 @@ struct mlx5_mpfs;
 struct mlx5_eswitch;
 struct mlx5_lag;
 struct mlx5_pagefault;
+struct mlx5_eq_table;
 
 struct mlx5_rate_limit {
 	u32			rate;
@@ -643,7 +569,7 @@ struct mlx5_port_module_event_stats {
 
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
-	struct mlx5_eq_table	eq_table;
+	struct mlx5_eq_table	*eq_table;
 
 	/* pages stuff */
 	struct workqueue_struct *pg_wq;
@@ -1148,6 +1074,9 @@ int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg,
 		     bool map_wc, bool fast_path);
 void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg);
 
+unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev);
+struct cpumask *
+mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector);
 unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev);
 int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index,
 			   u8 roce_version, u8 roce_l3_type, const u8 *gid,
@@ -1299,10 +1228,4 @@ enum {
 	MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32,
 };
 
-static inline const struct cpumask *
-mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector)
-{
-	return dev->priv.eq_table.irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask;
-}
-
 #endif /* MLX5_DRIVER_H */
-- 
cgit v1.2.3


From 16d760839ceef510cf95cbfadc069c4473c7a277 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:39 -0800
Subject: net/mlx5: EQ, Different EQ types

In mlx5 we have three types of usages for EQs,
1. Asynchronous EQs, used internally by mlx5 core for
 a. FW command completions
 b. FW page requests
 c. one EQ for all other Asynchronous events

2. Completion EQs, used for CQ completion (we create one per core)

3. *Special type of EQ (page fault) used for RDMA on demand paging
(ODP).

*The 3rd type shouldn't be special at least in mlx5 core, it is yet
another async events EQ with specific use case, it will be removed in
the next two patches, and will completely move its logic to mlx5_ib,
as it is rdma specific.

In this patch we remove use case (eq type) specific fields from
struct mlx5_eq into a new eq type specific structures.

struct mlx5_eq_async;
truct mlx5_eq_comp;
struct mlx5_eq_pagefault;

Separate between their type specific flows.

In the future we will allow users to create there own generic EQs.
for now we will allow only one for ODP in next patches.

We will introduce event listeners registration API for those who
want to receive mlx5 async events.
After that mlx5 eq handling will be clean from feature/user specific
handling.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cq.c       |  10 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |   8 +-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       | 376 ++++++++++++---------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/health.c   |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h   |  53 +--
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |   2 +-
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |   4 -
 include/linux/mlx5/cq.h                            |   2 +-
 include/linux/mlx5/driver.h                        |  10 +-
 10 files changed, 270 insertions(+), 199 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 6e55d2f37c6d..713a17ee3751 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -93,10 +93,10 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	u32 dout[MLX5_ST_SZ_DW(destroy_cq_out)];
 	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
 	u32 din[MLX5_ST_SZ_DW(destroy_cq_in)];
-	struct mlx5_eq *eq;
+	struct mlx5_eq_comp *eq;
 	int err;
 
-	eq = mlx5_eqn2eq(dev, eqn);
+	eq = mlx5_eqn2comp_eq(dev, eqn);
 	if (IS_ERR(eq))
 		return PTR_ERR(eq);
 
@@ -120,7 +120,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	INIT_LIST_HEAD(&cq->tasklet_ctx.list);
 
 	/* Add to comp EQ CQ tree to recv comp events */
-	err = mlx5_eq_add_cq(eq, cq);
+	err = mlx5_eq_add_cq(&eq->core, cq);
 	if (err)
 		goto err_cmd;
 
@@ -140,7 +140,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	return 0;
 
 err_cq_add:
-	mlx5_eq_del_cq(eq, cq);
+	mlx5_eq_del_cq(&eq->core, cq);
 err_cmd:
 	memset(din, 0, sizeof(din));
 	memset(dout, 0, sizeof(dout));
@@ -162,7 +162,7 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 	if (err)
 		return err;
 
-	err = mlx5_eq_del_cq(cq->eq, cq);
+	err = mlx5_eq_del_cq(&cq->eq->core, cq);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c23caade31bf..0d495a6b3949 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -320,7 +320,7 @@ static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
 static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
 {
 	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
-	synchronize_irq(pci_irq_vector(priv->mdev->pdev, MLX5_EQ_VEC_ASYNC));
+	mlx5_eq_synchronize_async_irq(priv->mdev);
 }
 
 static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
@@ -4117,17 +4117,17 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
 					struct mlx5e_txqsq *sq)
 {
-	struct mlx5_eq *eq = sq->cq.mcq.eq;
+	struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
 	u32 eqe_count;
 
 	netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
-		   eq->eqn, eq->cons_index, eq->irqn);
+		   eq->core.eqn, eq->core.cons_index, eq->core.irqn);
 
 	eqe_count = mlx5_eq_poll_irq_disabled(eq);
 	if (!eqe_count)
 		return false;
 
-	netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->eqn);
+	netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->core.eqn);
 	sq->channel->stats->eq_rearm++;
 	return true;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 32ce20221c44..252c9f0569b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -72,13 +72,16 @@ struct mlx5_irq_info {
 };
 
 struct mlx5_eq_table {
-	struct list_head	comp_eqs_list;
-	struct mlx5_eq		pages_eq;
-	struct mlx5_eq		async_eq;
-	struct mlx5_eq		cmd_eq;
+	struct list_head        comp_eqs_list;
+	struct mlx5_eq          pages_eq;
+	struct mlx5_eq          async_eq;
+	struct mlx5_eq	        cmd_eq;
+
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	struct mlx5_eq		pfault_eq;
+	struct mlx5_eq_pagefault pfault_eq;
 #endif
+	struct mutex            lock; /* sync async eqs creations */
+	u8			num_async_eqs;
 	int			num_comp_vectors;
 	struct mlx5_irq_info	*irq_info;
 #ifdef CONFIG_RFS_ACCEL
@@ -224,24 +227,24 @@ static void eqe_pf_action(struct work_struct *work)
 	struct mlx5_pagefault *pfault = container_of(work,
 						     struct mlx5_pagefault,
 						     work);
-	struct mlx5_eq *eq = pfault->eq;
+	struct mlx5_eq_pagefault *eq = pfault->eq;
 
-	mlx5_core_page_fault(eq->dev, pfault);
-	mempool_free(pfault, eq->pf_ctx.pool);
+	mlx5_core_page_fault(eq->core.dev, pfault);
+	mempool_free(pfault, eq->pool);
 }
 
-static void eq_pf_process(struct mlx5_eq *eq)
+static void eq_pf_process(struct mlx5_eq_pagefault *eq)
 {
-	struct mlx5_core_dev *dev = eq->dev;
+	struct mlx5_core_dev *dev = eq->core.dev;
 	struct mlx5_eqe_page_fault *pf_eqe;
 	struct mlx5_pagefault *pfault;
 	struct mlx5_eqe *eqe;
 	int set_ci = 0;
 
-	while ((eqe = next_eqe_sw(eq))) {
-		pfault = mempool_alloc(eq->pf_ctx.pool, GFP_ATOMIC);
+	while ((eqe = next_eqe_sw(&eq->core))) {
+		pfault = mempool_alloc(eq->pool, GFP_ATOMIC);
 		if (!pfault) {
-			schedule_work(&eq->pf_ctx.work);
+			schedule_work(&eq->work);
 			break;
 		}
 
@@ -311,30 +314,30 @@ static void eq_pf_process(struct mlx5_eq *eq)
 
 		pfault->eq = eq;
 		INIT_WORK(&pfault->work, eqe_pf_action);
-		queue_work(eq->pf_ctx.wq, &pfault->work);
+		queue_work(eq->wq, &pfault->work);
 
-		++eq->cons_index;
+		++eq->core.cons_index;
 		++set_ci;
 
 		if (unlikely(set_ci >= MLX5_NUM_SPARE_EQE)) {
-			eq_update_ci(eq, 0);
+			eq_update_ci(&eq->core, 0);
 			set_ci = 0;
 		}
 	}
 
-	eq_update_ci(eq, 1);
+	eq_update_ci(&eq->core, 1);
 }
 
 static irqreturn_t mlx5_eq_pf_int(int irq, void *eq_ptr)
 {
-	struct mlx5_eq *eq = eq_ptr;
+	struct mlx5_eq_pagefault *eq = eq_ptr;
 	unsigned long flags;
 
-	if (spin_trylock_irqsave(&eq->pf_ctx.lock, flags)) {
+	if (spin_trylock_irqsave(&eq->lock, flags)) {
 		eq_pf_process(eq);
-		spin_unlock_irqrestore(&eq->pf_ctx.lock, flags);
+		spin_unlock_irqrestore(&eq->lock, flags);
 	} else {
-		schedule_work(&eq->pf_ctx.work);
+		schedule_work(&eq->work);
 	}
 
 	return IRQ_HANDLED;
@@ -352,35 +355,61 @@ static void mempool_refill(mempool_t *pool)
 
 static void eq_pf_action(struct work_struct *work)
 {
-	struct mlx5_eq *eq = container_of(work, struct mlx5_eq, pf_ctx.work);
+	struct mlx5_eq_pagefault *eq =
+		container_of(work, struct mlx5_eq_pagefault, work);
 
-	mempool_refill(eq->pf_ctx.pool);
+	mempool_refill(eq->pool);
 
-	spin_lock_irq(&eq->pf_ctx.lock);
+	spin_lock_irq(&eq->lock);
 	eq_pf_process(eq);
-	spin_unlock_irq(&eq->pf_ctx.lock);
+	spin_unlock_irq(&eq->lock);
 }
 
-static int init_pf_ctx(struct mlx5_eq_pagefault *pf_ctx, const char *name)
+static int
+create_pf_eq(struct mlx5_core_dev *dev, struct mlx5_eq_pagefault *eq)
 {
-	spin_lock_init(&pf_ctx->lock);
-	INIT_WORK(&pf_ctx->work, eq_pf_action);
+	int err;
 
-	pf_ctx->wq = alloc_workqueue(name,
-				     WQ_HIGHPRI | WQ_UNBOUND | WQ_MEM_RECLAIM,
-				     MLX5_NUM_CMD_EQE);
-	if (!pf_ctx->wq)
+	spin_lock_init(&eq->lock);
+	INIT_WORK(&eq->work, eq_pf_action);
+
+	eq->pool = mempool_create_kmalloc_pool(MLX5_NUM_PF_DRAIN,
+					       sizeof(struct mlx5_pagefault));
+	if (!eq->pool)
 		return -ENOMEM;
 
-	pf_ctx->pool = mempool_create_kmalloc_pool
-		(MLX5_NUM_PF_DRAIN, sizeof(struct mlx5_pagefault));
-	if (!pf_ctx->pool)
+	eq->wq = alloc_workqueue("mlx5_page_fault",
+				 WQ_HIGHPRI | WQ_UNBOUND | WQ_MEM_RECLAIM,
+				 MLX5_NUM_CMD_EQE);
+	if (!eq->wq) {
+		err = -ENOMEM;
+		goto err_mempool;
+	}
+
+	err = mlx5_create_async_eq(dev, &eq->core, MLX5_NUM_ASYNC_EQE,
+				   1 << MLX5_EVENT_TYPE_PAGE_FAULT,
+				   "mlx5_page_fault_eq", mlx5_eq_pf_int);
+	if (err)
 		goto err_wq;
 
 	return 0;
 err_wq:
-	destroy_workqueue(pf_ctx->wq);
-	return -ENOMEM;
+	destroy_workqueue(eq->wq);
+err_mempool:
+	mempool_destroy(eq->pool);
+	return err;
+}
+
+static int destroy_pf_eq(struct mlx5_core_dev *dev, struct mlx5_eq_pagefault *eq)
+{
+	int err;
+
+	err = mlx5_destroy_async_eq(dev, &eq->core);
+	cancel_work_sync(&eq->work);
+	destroy_workqueue(eq->wq);
+	mempool_destroy(eq->pool);
+
+	return err;
 }
 
 int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 token,
@@ -444,37 +473,88 @@ static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn)
 	return cq;
 }
 
-static void mlx5_eq_cq_completion(struct mlx5_eq *eq, u32 cqn)
+static void mlx5_eq_cq_event(struct mlx5_eq *eq, u32 cqn, int event_type)
 {
 	struct mlx5_core_cq *cq = mlx5_eq_cq_get(eq, cqn);
 
 	if (unlikely(!cq)) {
-		mlx5_core_warn(eq->dev, "Completion event for bogus CQ 0x%x\n", cqn);
+		mlx5_core_warn(eq->dev, "Async event for bogus CQ 0x%x\n", cqn);
 		return;
 	}
 
-	++cq->arm_sn;
-
-	cq->comp(cq);
+	cq->event(cq, event_type);
 
 	mlx5_cq_put(cq);
 }
 
-static void mlx5_eq_cq_event(struct mlx5_eq *eq, u32 cqn, int event_type)
+static irqreturn_t mlx5_eq_comp_int(int irq, void *eq_ptr)
 {
-	struct mlx5_core_cq *cq = mlx5_eq_cq_get(eq, cqn);
+	struct mlx5_eq_comp *eq_comp = eq_ptr;
+	struct mlx5_eq *eq = eq_ptr;
+	struct mlx5_eqe *eqe;
+	int set_ci = 0;
+	u32 cqn = -1;
 
-	if (unlikely(!cq)) {
-		mlx5_core_warn(eq->dev, "Async event for bogus CQ 0x%x\n", cqn);
-		return;
+	while ((eqe = next_eqe_sw(eq))) {
+		struct mlx5_core_cq *cq;
+		/* Make sure we read EQ entry contents after we've
+		 * checked the ownership bit.
+		 */
+		dma_rmb();
+		/* Assume (eqe->type) is always MLX5_EVENT_TYPE_COMP */
+		cqn = be32_to_cpu(eqe->data.comp.cqn) & 0xffffff;
+
+		cq = mlx5_eq_cq_get(eq, cqn);
+		if (likely(cq)) {
+			++cq->arm_sn;
+			cq->comp(cq);
+			mlx5_cq_put(cq);
+		} else {
+			mlx5_core_warn(eq->dev, "Completion event for bogus CQ 0x%x\n", cqn);
+		}
+
+		++eq->cons_index;
+		++set_ci;
+
+		/* The HCA will think the queue has overflowed if we
+		 * don't tell it we've been processing events.  We
+		 * create our EQs with MLX5_NUM_SPARE_EQE extra
+		 * entries, so we must update our consumer index at
+		 * least that often.
+		 */
+		if (unlikely(set_ci >= MLX5_NUM_SPARE_EQE)) {
+			eq_update_ci(eq, 0);
+			set_ci = 0;
+		}
 	}
 
-	cq->event(cq, event_type);
+	eq_update_ci(eq, 1);
 
-	mlx5_cq_put(cq);
+	if (cqn != -1)
+		tasklet_schedule(&eq_comp->tasklet_ctx.task);
+
+	return IRQ_HANDLED;
 }
 
-static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
+/* Some architectures don't latch interrupts when they are disabled, so using
+ * mlx5_eq_poll_irq_disabled could end up losing interrupts while trying to
+ * avoid losing them.  It is not recommended to use it, unless this is the last
+ * resort.
+ */
+u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq)
+{
+	u32 count_eqe;
+
+	disable_irq(eq->core.irqn);
+	count_eqe = eq->core.cons_index;
+	mlx5_eq_comp_int(eq->core.irqn, eq);
+	count_eqe = eq->core.cons_index - count_eqe;
+	enable_irq(eq->core.irqn);
+
+	return count_eqe;
+}
+
+static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 {
 	struct mlx5_eq *eq = eq_ptr;
 	struct mlx5_core_dev *dev = eq->dev;
@@ -494,10 +574,6 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 		mlx5_core_dbg(eq->dev, "eqn %d, eqe type %s\n",
 			      eq->eqn, eqe_type_str(eqe->type));
 		switch (eqe->type) {
-		case MLX5_EVENT_TYPE_COMP:
-			cqn = be32_to_cpu(eqe->data.comp.cqn) & 0xffffff;
-			mlx5_eq_cq_completion(eq, cqn);
-			break;
 		case MLX5_EVENT_TYPE_DCT_DRAINED:
 			rsn = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
 			rsn |= (MLX5_RES_DCT << MLX5_USER_INDEX_LEN);
@@ -619,30 +695,9 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 
 	eq_update_ci(eq, 1);
 
-	if (cqn != -1)
-		tasklet_schedule(&eq->tasklet_ctx.task);
-
 	return IRQ_HANDLED;
 }
 
-/* Some architectures don't latch interrupts when they are disabled, so using
- * mlx5_eq_poll_irq_disabled could end up losing interrupts while trying to
- * avoid losing them.  It is not recommended to use it, unless this is the last
- * resort.
- */
-u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq)
-{
-	u32 count_eqe;
-
-	disable_irq(eq->irqn);
-	count_eqe = eq->cons_index;
-	mlx5_eq_int(eq->irqn, eq);
-	count_eqe = eq->cons_index - count_eqe;
-	enable_irq(eq->irqn);
-
-	return count_eqe;
-}
-
 static void init_eq_buf(struct mlx5_eq *eq)
 {
 	struct mlx5_eqe *eqe;
@@ -656,13 +711,12 @@ static void init_eq_buf(struct mlx5_eq *eq)
 
 static int
 mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
-		   int nent, u64 mask, const char *name, enum mlx5_eq_type type)
+		   int nent, u64 mask, const char *name, irq_handler_t handler)
 {
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	struct mlx5_cq_table *cq_table = &eq->cq_table;
 	u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0};
 	struct mlx5_priv *priv = &dev->priv;
-	irq_handler_t handler;
 	__be64 *pas;
 	void *eqc;
 	int inlen;
@@ -674,20 +728,12 @@ mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	spin_lock_init(&cq_table->lock);
 	INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
 
-	eq->type = type;
 	eq->nent = roundup_pow_of_two(nent + MLX5_NUM_SPARE_EQE);
 	eq->cons_index = 0;
 	err = mlx5_buf_alloc(dev, eq->nent * MLX5_EQE_SIZE, &eq->buf);
 	if (err)
 		return err;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (type == MLX5_EQ_TYPE_PF)
-		handler = mlx5_eq_pf_int;
-	else
-#endif
-		handler = mlx5_eq_int;
-
 	init_eq_buf(eq);
 
 	inlen = MLX5_ST_SZ_BYTES(create_eq_in) +
@@ -732,21 +778,6 @@ mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	if (err)
 		goto err_irq;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (type == MLX5_EQ_TYPE_PF) {
-		err = init_pf_ctx(&eq->pf_ctx, name);
-		if (err)
-			goto err_irq;
-	} else
-#endif
-	{
-		INIT_LIST_HEAD(&eq->tasklet_ctx.list);
-		INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
-		spin_lock_init(&eq->tasklet_ctx.lock);
-		tasklet_init(&eq->tasklet_ctx.task, mlx5_cq_tasklet_cb,
-			     (unsigned long)&eq->tasklet_ctx);
-	}
-
 	/* EQs are created in ARMED state
 	 */
 	eq_update_ci(eq, 1);
@@ -780,15 +811,6 @@ static int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 			       eq->eqn);
 	synchronize_irq(eq->irqn);
 
-	if (eq->type == MLX5_EQ_TYPE_COMP) {
-		tasklet_disable(&eq->tasklet_ctx.task);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	} else if (eq->type == MLX5_EQ_TYPE_PF) {
-		cancel_work_sync(&eq->pf_ctx.work);
-		destroy_workqueue(eq->pf_ctx.wq);
-		mempool_destroy(eq->pf_ctx.pool);
-#endif
-	}
 	mlx5_buf_free(dev, &eq->buf);
 
 	return err;
@@ -841,8 +863,15 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 
 	err = mlx5_eq_debugfs_init(dev);
 	if (err)
-		kvfree(eq_table);
+		goto kvfree_eq_table;
 
+	mutex_init(&eq_table->lock);
+
+	return 0;
+
+kvfree_eq_table:
+	kvfree(eq_table);
+	dev->priv.eq_table = NULL;
 	return err;
 }
 
@@ -854,6 +883,43 @@ void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev)
 
 /* Async EQs */
 
+int mlx5_create_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
+			 int nent, u64 mask, const char *name, irq_handler_t handler)
+{
+	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+	u8 vecdix;
+	int err;
+
+	mutex_lock(&eq_table->lock);
+	if (eq_table->num_async_eqs >= MLX5_EQ_MAX_ASYNC_EQS) {
+		err = -ENOSPC;
+		goto unlock;
+	}
+
+	vecdix = eq_table->num_async_eqs + 1;
+
+	err = mlx5_create_map_eq(dev, eq, vecdix, nent, mask, name, handler);
+	if (!err)
+		eq_table->num_async_eqs++;
+
+unlock:
+	mutex_unlock(&eq_table->lock);
+	return err;
+}
+
+int mlx5_destroy_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+{
+	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+	int err;
+
+	mutex_lock(&eq_table->lock);
+	err = mlx5_destroy_unmap_eq(dev, eq);
+	if (!err)
+		eq_table->num_async_eqs--;
+	mutex_unlock(&eq_table->lock);
+	return err;
+}
+
 static int create_async_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
@@ -887,9 +953,9 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_MCAM_REG(dev, tracer_registers))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_DEVICE_TRACER);
 
-	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
-				 MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,
-				 "mlx5_cmd_eq", MLX5_EQ_TYPE_ASYNC);
+	err = mlx5_create_async_eq(dev, &table->cmd_eq, MLX5_NUM_CMD_EQE,
+				   1ull << MLX5_EVENT_TYPE_CMD, "mlx5_cmd_eq",
+				   mlx5_eq_async_int);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create cmd EQ %d\n", err);
 		return err;
@@ -897,19 +963,15 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 
 	mlx5_cmd_use_events(dev);
 
-	err = mlx5_create_map_eq(dev, &table->async_eq, MLX5_EQ_VEC_ASYNC,
-				 MLX5_NUM_ASYNC_EQE, async_event_mask,
-				 "mlx5_async_eq", MLX5_EQ_TYPE_ASYNC);
+	err = mlx5_create_async_eq(dev, &table->async_eq, MLX5_NUM_ASYNC_EQE,
+				   async_event_mask, "mlx5_async_eq", mlx5_eq_async_int);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create async EQ %d\n", err);
 		goto err1;
 	}
 
-	err = mlx5_create_map_eq(dev, &table->pages_eq,
-				 MLX5_EQ_VEC_PAGES,
-				 /* TODO: sriov max_vf + */ 1,
-				 1 << MLX5_EVENT_TYPE_PAGE_REQUEST, "mlx5_pages_eq",
-				 MLX5_EQ_TYPE_ASYNC);
+	err = mlx5_create_async_eq(dev, &table->pages_eq, /* TODO: sriov max_vf + */ 1,
+				   1 << MLX5_EVENT_TYPE_PAGE_REQUEST, "mlx5_pages_eq", mlx5_eq_async_int);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create pages EQ %d\n", err);
 		goto err2;
@@ -917,12 +979,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	if (MLX5_CAP_GEN(dev, pg)) {
-		err = mlx5_create_map_eq(dev, &table->pfault_eq,
-					 MLX5_EQ_VEC_PFAULT,
-					 MLX5_NUM_ASYNC_EQE,
-					 1 << MLX5_EVENT_TYPE_PAGE_FAULT,
-					 "mlx5_page_fault_eq",
-					 MLX5_EQ_TYPE_PF);
+		err = create_pf_eq(dev, &table->pfault_eq);
 		if (err) {
 			mlx5_core_warn(dev, "failed to create page fault EQ %d\n",
 				       err);
@@ -932,17 +989,17 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 
 	return err;
 err3:
-	mlx5_destroy_unmap_eq(dev, &table->pages_eq);
+	mlx5_destroy_async_eq(dev, &table->pages_eq);
 #else
 	return err;
 #endif
 
 err2:
-	mlx5_destroy_unmap_eq(dev, &table->async_eq);
+	mlx5_destroy_async_eq(dev, &table->async_eq);
 
 err1:
 	mlx5_cmd_use_polling(dev);
-	mlx5_destroy_unmap_eq(dev, &table->cmd_eq);
+	mlx5_destroy_async_eq(dev, &table->cmd_eq);
 	return err;
 }
 
@@ -953,25 +1010,25 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev)
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	if (MLX5_CAP_GEN(dev, pg)) {
-		err = mlx5_destroy_unmap_eq(dev, &table->pfault_eq);
+		err = destroy_pf_eq(dev, &table->pfault_eq);
 		if (err)
 			mlx5_core_err(dev, "failed to destroy page fault eq, err(%d)\n",
 				      err);
 	}
 #endif
 
-	err = mlx5_destroy_unmap_eq(dev, &table->pages_eq);
+	err = mlx5_destroy_async_eq(dev, &table->pages_eq);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n",
 			      err);
 
-	err = mlx5_destroy_unmap_eq(dev, &table->async_eq);
+	err = mlx5_destroy_async_eq(dev, &table->async_eq);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n",
 			      err);
 	mlx5_cmd_use_polling(dev);
 
-	err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq);
+	err = mlx5_destroy_async_eq(dev, &table->cmd_eq);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n",
 			      err);
@@ -982,6 +1039,16 @@ struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev)
 	return &dev->priv.eq_table->async_eq;
 }
 
+void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev)
+{
+	synchronize_irq(dev->priv.eq_table->async_eq.irqn);
+}
+
+void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev)
+{
+	synchronize_irq(dev->priv.eq_table->cmd_eq.irqn);
+}
+
 /* Completion EQs */
 
 static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
@@ -1048,7 +1115,7 @@ static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev)
 static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	struct mlx5_eq *eq, *n;
+	struct mlx5_eq_comp *eq, *n;
 
 	clear_comp_irqs_affinity_hints(dev);
 
@@ -1060,9 +1127,10 @@ static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 #endif
 	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
 		list_del(&eq->list);
-		if (mlx5_destroy_unmap_eq(dev, eq))
-			mlx5_core_warn(dev, "failed to destroy EQ 0x%x\n",
-				       eq->eqn);
+		if (mlx5_destroy_unmap_eq(dev, &eq->core))
+			mlx5_core_warn(dev, "failed to destroy comp EQ 0x%x\n",
+				       eq->core.eqn);
+		tasklet_disable(&eq->tasklet_ctx.task);
 		kfree(eq);
 	}
 }
@@ -1071,7 +1139,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	char name[MLX5_MAX_IRQ_NAME];
-	struct mlx5_eq *eq;
+	struct mlx5_eq_comp *eq;
 	int ncomp_vec;
 	int nent;
 	int err;
@@ -1094,17 +1162,23 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 			goto clean;
 		}
 
+		INIT_LIST_HEAD(&eq->tasklet_ctx.list);
+		INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
+		spin_lock_init(&eq->tasklet_ctx.lock);
+		tasklet_init(&eq->tasklet_ctx.task, mlx5_cq_tasklet_cb,
+			     (unsigned long)&eq->tasklet_ctx);
+
 #ifdef CONFIG_RFS_ACCEL
 		irq_cpu_rmap_add(table->rmap, pci_irq_vector(dev->pdev, vecidx));
 #endif
 		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
-		err = mlx5_create_map_eq(dev, eq, vecidx, nent, 0,
-					 name, MLX5_EQ_TYPE_COMP);
+		err = mlx5_create_map_eq(dev, &eq->core, vecidx, nent, 0,
+					 name, mlx5_eq_comp_int);
 		if (err) {
 			kfree(eq);
 			goto clean;
 		}
-		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->eqn);
+		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->core.eqn);
 		/* add tail, to keep the list ordered, for mlx5_vector2eqn to work */
 		list_add_tail(&eq->list, &table->comp_eqs_list);
 	}
@@ -1126,14 +1200,14 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 		    unsigned int *irqn)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	struct mlx5_eq *eq, *n;
+	struct mlx5_eq_comp *eq, *n;
 	int err = -ENOENT;
 	int i = 0;
 
 	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
 		if (i++ == vector) {
-			*eqn = eq->eqn;
-			*irqn = eq->irqn;
+			*eqn = eq->core.eqn;
+			*irqn = eq->core.irqn;
 			err = 0;
 			break;
 		}
@@ -1166,13 +1240,13 @@ struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev)
 #endif
 }
 
-struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn)
+struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	struct mlx5_eq *eq;
+	struct mlx5_eq_comp *eq;
 
 	list_for_each_entry(eq, &table->comp_eqs_list, list) {
-		if (eq->eqn == eqn)
+		if (eq->core.eqn == eqn)
 			return eq;
 	}
 
@@ -1183,7 +1257,7 @@ struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn)
 void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	struct mlx5_eq *eq;
+	struct mlx5_eq_comp *eq;
 
 	clear_comp_irqs_affinity_hints(dev);
 
@@ -1194,14 +1268,14 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 	}
 #endif
 	list_for_each_entry(eq, &table->comp_eqs_list, list)
-		free_irq(eq->irqn, eq);
+		free_irq(eq->core.irqn, eq);
 
 	free_irq(table->pages_eq.irqn, &table->pages_eq);
 	free_irq(table->async_eq.irqn, &table->async_eq);
 	free_irq(table->cmd_eq.irqn, &table->cmd_eq);
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	if (MLX5_CAP_GEN(dev, pg))
-		free_irq(table->pfault_eq.irqn, &table->pfault_eq);
+		free_irq(table->pfault_eq.core.irqn, &table->pfault_eq.core);
 #endif
 	pci_free_irq_vectors(dev->pdev);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 324606227b1a..2346b6ba3d54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1568,7 +1568,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	/* Mark this vport as disabled to discard new events */
 	vport->enabled = false;
 
-	synchronize_irq(pci_irq_vector(esw->dev->pdev, MLX5_EQ_VEC_ASYNC));
+	mlx5_eq_synchronize_async_irq(esw->dev);
 	/* Wait for current already scheduled events to complete */
 	flush_workqueue(esw->work_queue);
 	/* Disable events from this vport */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index b5be6f0b9ed5..066883003aea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -85,7 +85,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev)
 	u64 vector;
 
 	/* wait for pending handlers to complete */
-	synchronize_irq(pci_irq_vector(dev->pdev, MLX5_EQ_VEC_CMD));
+	mlx5_eq_synchronize_cmd_irq(dev);
 	spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
 	vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
 	if (!vector)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index 48ee37797b3f..706d58383dbd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -8,11 +8,8 @@
 #define MLX5_MAX_IRQ_NAME       (32)
 
 enum {
-	MLX5_EQ_VEC_PAGES	 = 0,
-	MLX5_EQ_VEC_CMD		 = 1,
-	MLX5_EQ_VEC_ASYNC	 = 2,
-	MLX5_EQ_VEC_PFAULT	 = 3,
-	MLX5_EQ_VEC_COMP_BASE,
+	MLX5_EQ_MAX_ASYNC_EQS = 4, /* mlx5_core needs at least 3 */
+	MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS,
 };
 
 struct mlx5_eq_tasklet {
@@ -22,13 +19,6 @@ struct mlx5_eq_tasklet {
 	spinlock_t            lock; /* lock completion tasklet list */
 };
 
-struct mlx5_eq_pagefault {
-	struct work_struct       work;
-	spinlock_t               lock; /* Pagefaults spinlock */
-	struct workqueue_struct  *wq;
-	mempool_t                *pool;
-};
-
 struct mlx5_cq_table {
 	spinlock_t              lock;	/* protect radix tree */
 	struct radix_tree_root  tree;
@@ -44,29 +34,48 @@ struct mlx5_eq {
 	unsigned int            irqn;
 	u8                      eqn;
 	int                     nent;
-	struct list_head        list;
 	struct mlx5_rsc_debug   *dbg;
-	enum mlx5_eq_type       type;
-	union {
-		struct mlx5_eq_tasklet   tasklet_ctx;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-		struct mlx5_eq_pagefault pf_ctx;
-#endif
-	};
+};
+
+struct mlx5_eq_comp {
+	struct mlx5_eq          core; /* Must be first */
+	struct mlx5_eq_tasklet  tasklet_ctx;
+	struct list_head        list;
+};
+
+struct mlx5_eq_pagefault {
+	struct mlx5_eq           core; /* Must be first */
+	struct work_struct       work;
+	spinlock_t               lock; /* Pagefaults spinlock */
+	struct workqueue_struct  *wq;
+	mempool_t                *pool;
 };
 
 int mlx5_eq_table_init(struct mlx5_core_dev *dev);
 void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev);
 int mlx5_eq_table_create(struct mlx5_core_dev *dev);
 void mlx5_eq_table_destroy(struct mlx5_core_dev *dev);
+int mlx5_create_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
+			 int nent, u64 mask, const char *name,
+			 irq_handler_t handler);
+int mlx5_destroy_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+
 int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
 int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
+struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn);
 struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev);
-u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq);
 void mlx5_cq_tasklet_cb(unsigned long data);
 struct cpumask *mlx5_eq_comp_cpumask(struct mlx5_core_dev *dev, int ix);
 
+u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq);
+void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev);
+void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev);
+
+int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev);
+void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev);
+
 /* This function should only be called after mlx5_cmd_force_teardown_hca */
 void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 5d11ef92c8b6..3de83fe65f2b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -53,8 +53,8 @@
 #endif
 #include <net/devlink.h>
 #include "mlx5_core.h"
-#include "fs_core.h"
 #include "lib/eq.h"
+#include "fs_core.h"
 #include "lib/mpfs.h"
 #include "eswitch.h"
 #include "lib/mlx5.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 4d39adcfb0eb..4728b027cb9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -125,10 +125,6 @@ int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
 u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
 
 void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
-int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev);
-void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev);
 int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev);
 void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev);
 
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 31a750570c38..28b757a64029 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -60,7 +60,7 @@ struct mlx5_core_cq {
 	} tasklet_ctx;
 	int			reset_notify_added;
 	struct list_head	reset_notify;
-	struct mlx5_eq		*eq;
+	struct mlx5_eq_comp	*eq;
 	u16 uid;
 };
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 4d6246cb6c19..fe9b552aa649 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -210,14 +210,6 @@ enum mlx5_port_status {
 	MLX5_PORT_DOWN      = 2,
 };
 
-enum mlx5_eq_type {
-	MLX5_EQ_TYPE_COMP,
-	MLX5_EQ_TYPE_ASYNC,
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	MLX5_EQ_TYPE_PF,
-#endif
-};
-
 struct mlx5_bfreg_info {
 	u32		       *sys_pages;
 	int			num_low_latency_bfregs;
@@ -692,7 +684,7 @@ struct mlx5_pagefault {
 		} rdma;
 	};
 
-	struct mlx5_eq	       *eq;
+	struct mlx5_eq_pagefault *eq;
 	struct work_struct	work;
 };
 
-- 
cgit v1.2.3


From 7701707cb94ed4d1e63ae4fa5ef62a2345ef9db7 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:40 -0800
Subject: net/mlx5: EQ, Generic EQ

Add mlx5_eq_{create/destroy}_generic APIs and EQE access methods, for
mlx5 core consumers generic EQs.

This API will be used in downstream patch to move page fault (RDMA ODP)
EQ logic into mlx5_ib rdma driver, hence it will use a generic EQ.

Current mlx5 EQ allocation scheme:
On load mlx5 allocates 4 (for async) + #cores (for data completions)
MSIX vectors, mlx5 core will assign 3 MSIX vectors for internal async
EQs and will use all of the #cores MSIX vectors for completion EQs,
(One vector is going to be reserved for a generic EQ).

After this patch an external user (e.g mlx5_ib) of mlx5_core
can use this new API to create new generic EQs with the reserved msix
vector index for that eq.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c     | 243 +++++++++++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h |  12 +-
 include/linux/mlx5/eq.h                          |  39 ++++
 3 files changed, 221 insertions(+), 73 deletions(-)
 create mode 100644 include/linux/mlx5/eq.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 252c9f0569b1..ec1f5018546e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -33,6 +33,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/eq.h>
 #include <linux/mlx5/cmd.h>
 #ifdef CONFIG_RFS_ACCEL
 #include <linux/cpu_rmap.h>
@@ -69,6 +70,7 @@ enum {
 struct mlx5_irq_info {
 	cpumask_var_t mask;
 	char name[MLX5_MAX_IRQ_NAME];
+	void *context; /* dev_id provided to request_irq */
 };
 
 struct mlx5_eq_table {
@@ -81,7 +83,6 @@ struct mlx5_eq_table {
 	struct mlx5_eq_pagefault pfault_eq;
 #endif
 	struct mutex            lock; /* sync async eqs creations */
-	u8			num_async_eqs;
 	int			num_comp_vectors;
 	struct mlx5_irq_info	*irq_info;
 #ifdef CONFIG_RFS_ACCEL
@@ -229,19 +230,19 @@ static void eqe_pf_action(struct work_struct *work)
 						     work);
 	struct mlx5_eq_pagefault *eq = pfault->eq;
 
-	mlx5_core_page_fault(eq->core.dev, pfault);
+	mlx5_core_page_fault(eq->core->dev, pfault);
 	mempool_free(pfault, eq->pool);
 }
 
 static void eq_pf_process(struct mlx5_eq_pagefault *eq)
 {
-	struct mlx5_core_dev *dev = eq->core.dev;
+	struct mlx5_core_dev *dev = eq->core->dev;
 	struct mlx5_eqe_page_fault *pf_eqe;
 	struct mlx5_pagefault *pfault;
 	struct mlx5_eqe *eqe;
 	int set_ci = 0;
 
-	while ((eqe = next_eqe_sw(&eq->core))) {
+	while ((eqe = next_eqe_sw(eq->core))) {
 		pfault = mempool_alloc(eq->pool, GFP_ATOMIC);
 		if (!pfault) {
 			schedule_work(&eq->work);
@@ -316,16 +317,16 @@ static void eq_pf_process(struct mlx5_eq_pagefault *eq)
 		INIT_WORK(&pfault->work, eqe_pf_action);
 		queue_work(eq->wq, &pfault->work);
 
-		++eq->core.cons_index;
+		++eq->core->cons_index;
 		++set_ci;
 
 		if (unlikely(set_ci >= MLX5_NUM_SPARE_EQE)) {
-			eq_update_ci(&eq->core, 0);
+			eq_update_ci(eq->core, 0);
 			set_ci = 0;
 		}
 	}
 
-	eq_update_ci(&eq->core, 1);
+	eq_update_ci(eq->core, 1);
 }
 
 static irqreturn_t mlx5_eq_pf_int(int irq, void *eq_ptr)
@@ -368,6 +369,7 @@ static void eq_pf_action(struct work_struct *work)
 static int
 create_pf_eq(struct mlx5_core_dev *dev, struct mlx5_eq_pagefault *eq)
 {
+	struct mlx5_eq_param param = {};
 	int err;
 
 	spin_lock_init(&eq->lock);
@@ -386,11 +388,19 @@ create_pf_eq(struct mlx5_core_dev *dev, struct mlx5_eq_pagefault *eq)
 		goto err_mempool;
 	}
 
-	err = mlx5_create_async_eq(dev, &eq->core, MLX5_NUM_ASYNC_EQE,
-				   1 << MLX5_EVENT_TYPE_PAGE_FAULT,
-				   "mlx5_page_fault_eq", mlx5_eq_pf_int);
-	if (err)
+	param = (struct mlx5_eq_param) {
+		.index = MLX5_EQ_PFAULT_IDX,
+		.mask = 1 << MLX5_EVENT_TYPE_PAGE_FAULT,
+		.nent = MLX5_NUM_ASYNC_EQE,
+		.context = eq,
+		.handler = mlx5_eq_pf_int
+	};
+
+	eq->core = mlx5_eq_create_generic(dev, "mlx5_page_fault_eq", &param);
+	if (IS_ERR(eq->core)) {
+		err = PTR_ERR(eq->core);
 		goto err_wq;
+	}
 
 	return 0;
 err_wq:
@@ -404,7 +414,7 @@ static int destroy_pf_eq(struct mlx5_core_dev *dev, struct mlx5_eq_pagefault *eq
 {
 	int err;
 
-	err = mlx5_destroy_async_eq(dev, &eq->core);
+	err = mlx5_eq_destroy_generic(dev, eq->core);
 	cancel_work_sync(&eq->work);
 	destroy_workqueue(eq->wq);
 	mempool_destroy(eq->pool);
@@ -710,25 +720,29 @@ static void init_eq_buf(struct mlx5_eq *eq)
 }
 
 static int
-mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
-		   int nent, u64 mask, const char *name, irq_handler_t handler)
+create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, const char *name,
+	      struct mlx5_eq_param *param)
 {
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	struct mlx5_cq_table *cq_table = &eq->cq_table;
 	u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0};
 	struct mlx5_priv *priv = &dev->priv;
+	u8 vecidx = param->index;
 	__be64 *pas;
 	void *eqc;
 	int inlen;
 	u32 *in;
 	int err;
 
+	if (eq_table->irq_info[vecidx].context)
+		return -EEXIST;
+
 	/* Init CQ table */
 	memset(cq_table, 0, sizeof(*cq_table));
 	spin_lock_init(&cq_table->lock);
 	INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
 
-	eq->nent = roundup_pow_of_two(nent + MLX5_NUM_SPARE_EQE);
+	eq->nent = roundup_pow_of_two(param->nent + MLX5_NUM_SPARE_EQE);
 	eq->cons_index = 0;
 	err = mlx5_buf_alloc(dev, eq->nent * MLX5_EQE_SIZE, &eq->buf);
 	if (err)
@@ -749,7 +763,7 @@ mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	mlx5_fill_page_array(&eq->buf, pas);
 
 	MLX5_SET(create_eq_in, in, opcode, MLX5_CMD_OP_CREATE_EQ);
-	MLX5_SET64(create_eq_in, in, event_bitmask, mask);
+	MLX5_SET64(create_eq_in, in, event_bitmask, param->mask);
 
 	eqc = MLX5_ADDR_OF(create_eq_in, in, eq_context_entry);
 	MLX5_SET(eqc, eqc, log_eq_size, ilog2(eq->nent));
@@ -764,13 +778,15 @@ mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 
 	snprintf(eq_table->irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s",
 		 name, pci_name(dev->pdev));
+	eq_table->irq_info[vecidx].context = param->context;
 
+	eq->vecidx = vecidx;
 	eq->eqn = MLX5_GET(create_eq_out, out, eq_number);
 	eq->irqn = pci_irq_vector(dev->pdev, vecidx);
 	eq->dev = dev;
 	eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET;
-	err = request_irq(eq->irqn, handler, 0,
-			  eq_table->irq_info[vecidx].name, eq);
+	err = request_irq(eq->irqn, param->handler, 0,
+			  eq_table->irq_info[vecidx].name, param->context);
 	if (err)
 		goto err_eq;
 
@@ -799,12 +815,19 @@ err_buf:
 	return err;
 }
 
-static int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+static int destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 {
+	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+	struct mlx5_irq_info *irq_info;
 	int err;
 
+	irq_info = &eq_table->irq_info[eq->vecidx];
+
 	mlx5_debug_eq_remove(dev, eq);
-	free_irq(eq->irqn, eq);
+
+	free_irq(eq->irqn, irq_info->context);
+	irq_info->context = NULL;
+
 	err = mlx5_cmd_destroy_eq(dev, eq->eqn);
 	if (err)
 		mlx5_core_warn(dev, "failed to destroy a previously created eq: eqn %d\n",
@@ -883,48 +906,38 @@ void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev)
 
 /* Async EQs */
 
-int mlx5_create_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
-			 int nent, u64 mask, const char *name, irq_handler_t handler)
+static int create_async_eq(struct mlx5_core_dev *dev, const char *name,
+			   struct mlx5_eq *eq, struct mlx5_eq_param *param)
 {
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
-	u8 vecdix;
 	int err;
 
 	mutex_lock(&eq_table->lock);
-	if (eq_table->num_async_eqs >= MLX5_EQ_MAX_ASYNC_EQS) {
+	if (param->index >= MLX5_EQ_MAX_ASYNC_EQS) {
 		err = -ENOSPC;
 		goto unlock;
 	}
 
-	vecdix = eq_table->num_async_eqs + 1;
-
-	err = mlx5_create_map_eq(dev, eq, vecdix, nent, mask, name, handler);
-	if (!err)
-		eq_table->num_async_eqs++;
-
+	err = create_map_eq(dev, eq, name, param);
 unlock:
 	mutex_unlock(&eq_table->lock);
 	return err;
 }
 
-int mlx5_destroy_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+static int destroy_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 {
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	int err;
 
 	mutex_lock(&eq_table->lock);
-	err = mlx5_destroy_unmap_eq(dev, eq);
-	if (!err)
-		eq_table->num_async_eqs--;
+	err = destroy_unmap_eq(dev, eq);
 	mutex_unlock(&eq_table->lock);
 	return err;
 }
 
-static int create_async_eqs(struct mlx5_core_dev *dev)
+static u64 gather_async_events_mask(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = dev->priv.eq_table;
 	u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
-	int err;
 
 	if (MLX5_VPORT_MANAGER(dev))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_NIC_VPORT_CHANGE);
@@ -953,9 +966,23 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_MCAM_REG(dev, tracer_registers))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_DEVICE_TRACER);
 
-	err = mlx5_create_async_eq(dev, &table->cmd_eq, MLX5_NUM_CMD_EQE,
-				   1ull << MLX5_EVENT_TYPE_CMD, "mlx5_cmd_eq",
-				   mlx5_eq_async_int);
+	return async_event_mask;
+}
+
+static int create_async_eqs(struct mlx5_core_dev *dev)
+{
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_eq_param param = {};
+	int err;
+
+	param = (struct mlx5_eq_param) {
+		.index = MLX5_EQ_CMD_IDX,
+		.mask = 1ull << MLX5_EVENT_TYPE_CMD,
+		.nent = MLX5_NUM_CMD_EQE,
+		.context = &table->cmd_eq,
+		.handler = mlx5_eq_async_int,
+	};
+	err = create_async_eq(dev, "mlx5_cmd_eq", &table->cmd_eq, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create cmd EQ %d\n", err);
 		return err;
@@ -963,15 +990,27 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 
 	mlx5_cmd_use_events(dev);
 
-	err = mlx5_create_async_eq(dev, &table->async_eq, MLX5_NUM_ASYNC_EQE,
-				   async_event_mask, "mlx5_async_eq", mlx5_eq_async_int);
+	param = (struct mlx5_eq_param) {
+		.index = MLX5_EQ_ASYNC_IDX,
+		.mask = gather_async_events_mask(dev),
+		.nent = MLX5_NUM_ASYNC_EQE,
+		.context = &table->async_eq,
+		.handler = mlx5_eq_async_int,
+	};
+	err = create_async_eq(dev, "mlx5_async_eq", &table->async_eq, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create async EQ %d\n", err);
 		goto err1;
 	}
 
-	err = mlx5_create_async_eq(dev, &table->pages_eq, /* TODO: sriov max_vf + */ 1,
-				   1 << MLX5_EVENT_TYPE_PAGE_REQUEST, "mlx5_pages_eq", mlx5_eq_async_int);
+	param = (struct mlx5_eq_param) {
+		.index = MLX5_EQ_PAGEREQ_IDX,
+		.mask =  1 << MLX5_EVENT_TYPE_PAGE_REQUEST,
+		.nent = /* TODO: sriov max_vf + */ 1,
+		.context = &table->pages_eq,
+		.handler = mlx5_eq_async_int,
+	};
+	err = create_async_eq(dev, "mlx5_pages_eq", &table->pages_eq, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create pages EQ %d\n", err);
 		goto err2;
@@ -989,17 +1028,17 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 
 	return err;
 err3:
-	mlx5_destroy_async_eq(dev, &table->pages_eq);
+	destroy_async_eq(dev, &table->pages_eq);
 #else
 	return err;
 #endif
 
 err2:
-	mlx5_destroy_async_eq(dev, &table->async_eq);
+	destroy_async_eq(dev, &table->async_eq);
 
 err1:
 	mlx5_cmd_use_polling(dev);
-	mlx5_destroy_async_eq(dev, &table->cmd_eq);
+	destroy_async_eq(dev, &table->cmd_eq);
 	return err;
 }
 
@@ -1017,18 +1056,18 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev)
 	}
 #endif
 
-	err = mlx5_destroy_async_eq(dev, &table->pages_eq);
+	err = destroy_async_eq(dev, &table->pages_eq);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n",
 			      err);
 
-	err = mlx5_destroy_async_eq(dev, &table->async_eq);
+	err = destroy_async_eq(dev, &table->async_eq);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n",
 			      err);
 	mlx5_cmd_use_polling(dev);
 
-	err = mlx5_destroy_async_eq(dev, &table->cmd_eq);
+	err = destroy_async_eq(dev, &table->cmd_eq);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n",
 			      err);
@@ -1049,6 +1088,77 @@ void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev)
 	synchronize_irq(dev->priv.eq_table->cmd_eq.irqn);
 }
 
+/* Generic EQ API for mlx5_core consumers
+ * Needed For RDMA ODP EQ for now
+ */
+struct mlx5_eq *
+mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name,
+		       struct mlx5_eq_param *param)
+{
+	struct mlx5_eq *eq = kvzalloc(sizeof(*eq), GFP_KERNEL);
+	int err;
+
+	if (!eq)
+		return ERR_PTR(-ENOMEM);
+
+	err = create_async_eq(dev, name, eq, param);
+	if (err) {
+		kvfree(eq);
+		eq = ERR_PTR(err);
+	}
+
+	return eq;
+}
+EXPORT_SYMBOL(mlx5_eq_create_generic);
+
+int mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+{
+	int err;
+
+	if (IS_ERR(eq))
+		return -EINVAL;
+
+	err = destroy_async_eq(dev, eq);
+	if (err)
+		goto out;
+
+	kvfree(eq);
+out:
+	return err;
+}
+EXPORT_SYMBOL(mlx5_eq_destroy_generic);
+
+struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc)
+{
+	u32 ci = eq->cons_index + cc;
+	struct mlx5_eqe *eqe;
+
+	eqe = get_eqe(eq, ci & (eq->nent - 1));
+	eqe = ((eqe->owner & 1) ^ !!(ci & eq->nent)) ? NULL : eqe;
+	/* Make sure we read EQ entry contents after we've
+	 * checked the ownership bit.
+	 */
+	if (eqe)
+		dma_rmb();
+
+	return eqe;
+}
+EXPORT_SYMBOL(mlx5_eq_get_eqe);
+
+void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm)
+{
+	__be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2);
+	u32 val;
+
+	eq->cons_index += cc;
+	val = (eq->cons_index & 0xffffff) | (eq->eqn << 24);
+
+	__raw_writel((__force u32)cpu_to_be32(val), addr);
+	/* We still want ordering, just not swabbing, so add a barrier */
+	mb();
+}
+EXPORT_SYMBOL(mlx5_eq_update_ci);
+
 /* Completion EQs */
 
 static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
@@ -1127,7 +1237,7 @@ static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 #endif
 	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
 		list_del(&eq->list);
-		if (mlx5_destroy_unmap_eq(dev, &eq->core))
+		if (destroy_unmap_eq(dev, &eq->core))
 			mlx5_core_warn(dev, "failed to destroy comp EQ 0x%x\n",
 				       eq->core.eqn);
 		tasklet_disable(&eq->tasklet_ctx.task);
@@ -1155,6 +1265,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 #endif
 	for (i = 0; i < ncomp_vec; i++) {
 		int vecidx = i + MLX5_EQ_VEC_COMP_BASE;
+		struct mlx5_eq_param param = {};
 
 		eq = kzalloc(sizeof(*eq), GFP_KERNEL);
 		if (!eq) {
@@ -1172,8 +1283,14 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 		irq_cpu_rmap_add(table->rmap, pci_irq_vector(dev->pdev, vecidx));
 #endif
 		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
-		err = mlx5_create_map_eq(dev, &eq->core, vecidx, nent, 0,
-					 name, mlx5_eq_comp_int);
+		param = (struct mlx5_eq_param) {
+			.index = vecidx,
+			.mask = 0,
+			.nent = nent,
+			.context = &eq->core,
+			.handler = mlx5_eq_comp_int
+		};
+		err = create_map_eq(dev, &eq->core, name, &param);
 		if (err) {
 			kfree(eq);
 			goto clean;
@@ -1257,7 +1374,7 @@ struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn)
 void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	struct mlx5_eq_comp *eq;
+	int i, max_eqs;
 
 	clear_comp_irqs_affinity_hints(dev);
 
@@ -1267,16 +1384,16 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 		table->rmap = NULL;
 	}
 #endif
-	list_for_each_entry(eq, &table->comp_eqs_list, list)
-		free_irq(eq->core.irqn, eq);
 
-	free_irq(table->pages_eq.irqn, &table->pages_eq);
-	free_irq(table->async_eq.irqn, &table->async_eq);
-	free_irq(table->cmd_eq.irqn, &table->cmd_eq);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (MLX5_CAP_GEN(dev, pg))
-		free_irq(table->pfault_eq.core.irqn, &table->pfault_eq.core);
-#endif
+	mutex_lock(&table->lock); /* sync with create/destroy_async_eq */
+	max_eqs = table->num_comp_vectors + MLX5_EQ_VEC_COMP_BASE;
+	for (i = max_eqs - 1; i >= 0; i--) {
+		if (!table->irq_info[i].context)
+			continue;
+		free_irq(pci_irq_vector(dev->pdev, i), table->irq_info[i].context);
+		table->irq_info[i].context = NULL;
+	}
+	mutex_unlock(&table->lock);
 	pci_free_irq_vectors(dev->pdev);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index 706d58383dbd..db32057ad054 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -7,11 +7,6 @@
 
 #define MLX5_MAX_IRQ_NAME       (32)
 
-enum {
-	MLX5_EQ_MAX_ASYNC_EQS = 4, /* mlx5_core needs at least 3 */
-	MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS,
-};
-
 struct mlx5_eq_tasklet {
 	struct list_head      list;
 	struct list_head      process_list;
@@ -31,6 +26,7 @@ struct mlx5_eq {
 	u32                     cons_index;
 	struct mlx5_frag_buf    buf;
 	int                     size;
+	unsigned int            vecidx;
 	unsigned int            irqn;
 	u8                      eqn;
 	int                     nent;
@@ -44,7 +40,7 @@ struct mlx5_eq_comp {
 };
 
 struct mlx5_eq_pagefault {
-	struct mlx5_eq           core; /* Must be first */
+	struct mlx5_eq          *core;
 	struct work_struct       work;
 	spinlock_t               lock; /* Pagefaults spinlock */
 	struct workqueue_struct  *wq;
@@ -55,10 +51,6 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev);
 void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev);
 int mlx5_eq_table_create(struct mlx5_core_dev *dev);
 void mlx5_eq_table_destroy(struct mlx5_core_dev *dev);
-int mlx5_create_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
-			 int nent, u64 mask, const char *name,
-			 irq_handler_t handler);
-int mlx5_destroy_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
 
 int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
 int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h
new file mode 100644
index 000000000000..c733673ba5f6
--- /dev/null
+++ b/include/linux/mlx5/eq.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef MLX5_CORE_EQ_H
+#define MLX5_CORE_EQ_H
+
+#include <linux/mlx5/driver.h>
+
+enum {
+	MLX5_EQ_PAGEREQ_IDX        = 0,
+	MLX5_EQ_CMD_IDX            = 1,
+	MLX5_EQ_ASYNC_IDX          = 2,
+	/* reserved to be used by mlx5_core ulps (mlx5e/mlx5_ib) */
+	MLX5_EQ_PFAULT_IDX         = 3,
+	MLX5_EQ_MAX_ASYNC_EQS,
+	/* completion eqs vector indices start here */
+	MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS,
+};
+
+struct mlx5_eq;
+
+struct mlx5_eq_param {
+	u8             index;
+	int            nent;
+	u64            mask;
+	void          *context;
+	irq_handler_t  handler;
+};
+
+struct mlx5_eq *
+mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name,
+		       struct mlx5_eq_param *param);
+int
+mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+
+struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc);
+void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm);
+
+#endif /* MLX5_CORE_EQ_H */
-- 
cgit v1.2.3


From d5d284b829a6eb7127df24d1bd3896a698981e62 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:41 -0800
Subject: {net,IB}/mlx5: Move Page fault EQ and ODP logic to RDMA

Use the new generic EQ API to move all ODP RDMA data structures and logic
form mlx5 core driver into mlx5_ib driver.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c                  |  10 +-
 drivers/infiniband/hw/mlx5/mlx5_ib.h               |  15 +-
 drivers/infiniband/hw/mlx5/odp.c                   | 281 ++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/dev.c      |  34 ---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       | 252 ------------------
 drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h   |   8 -
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  17 +-
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |   2 -
 include/linux/mlx5/driver.h                        |  49 ----
 include/linux/mlx5/eq.h                            |  21 ++
 10 files changed, 308 insertions(+), 381 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 6fbc0cba1bac..fcf4a0328a90 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -6040,6 +6040,11 @@ static int mlx5_ib_stage_odp_init(struct mlx5_ib_dev *dev)
 	return mlx5_ib_odp_init_one(dev);
 }
 
+void mlx5_ib_stage_odp_cleanup(struct mlx5_ib_dev *dev)
+{
+	mlx5_ib_odp_cleanup_one(dev);
+}
+
 int mlx5_ib_stage_counters_init(struct mlx5_ib_dev *dev)
 {
 	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) {
@@ -6225,7 +6230,7 @@ static const struct mlx5_ib_profile pf_profile = {
 		     mlx5_ib_stage_dev_res_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_ODP,
 		     mlx5_ib_stage_odp_init,
-		     NULL),
+		     mlx5_ib_stage_odp_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_COUNTERS,
 		     mlx5_ib_stage_counters_init,
 		     mlx5_ib_stage_counters_cleanup),
@@ -6395,9 +6400,6 @@ static struct mlx5_interface mlx5_ib_interface = {
 	.add            = mlx5_ib_add,
 	.remove         = mlx5_ib_remove,
 	.event          = mlx5_ib_event,
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	.pfault		= mlx5_ib_pfault,
-#endif
 	.protocol	= MLX5_INTERFACE_PROTOCOL_IB,
 };
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index b651a7a6fde9..27999fd32356 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -880,6 +880,15 @@ struct mlx5_ib_lb_state {
 	bool			enabled;
 };
 
+struct mlx5_ib_pf_eq {
+	struct mlx5_ib_dev *dev;
+	struct mlx5_eq *core;
+	struct work_struct work;
+	spinlock_t lock; /* Pagefaults spinlock */
+	struct workqueue_struct *wq;
+	mempool_t *pool;
+};
+
 struct mlx5_ib_dev {
 	struct ib_device		ib_dev;
 	const struct uverbs_object_tree_def *driver_trees[7];
@@ -902,6 +911,8 @@ struct mlx5_ib_dev {
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	struct ib_odp_caps	odp_caps;
 	u64			odp_max_size;
+	struct mlx5_ib_pf_eq	odp_pf_eq;
+
 	/*
 	 * Sleepable RCU that prevents destruction of MRs while they are still
 	 * being used by a page fault handler.
@@ -1158,9 +1169,8 @@ struct ib_mr *mlx5_ib_reg_dm_mr(struct ib_pd *pd, struct ib_dm *dm,
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev);
-void mlx5_ib_pfault(struct mlx5_core_dev *mdev, void *context,
-		    struct mlx5_pagefault *pfault);
 int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev);
+void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev);
 int __init mlx5_ib_odp_init(void);
 void mlx5_ib_odp_cleanup(void);
 void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
@@ -1175,6 +1185,7 @@ static inline void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
 }
 
 static inline int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev) { return 0; }
+static inline void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev) {}
 static inline int mlx5_ib_odp_init(void) { return 0; }
 static inline void mlx5_ib_odp_cleanup(void)				    {}
 static inline void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent) {}
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 7d784b40e017..416d141322a0 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -37,6 +37,46 @@
 #include "mlx5_ib.h"
 #include "cmd.h"
 
+#include <linux/mlx5/eq.h>
+
+/* Contains the details of a pagefault. */
+struct mlx5_pagefault {
+	u32			bytes_committed;
+	u32			token;
+	u8			event_subtype;
+	u8			type;
+	union {
+		/* Initiator or send message responder pagefault details. */
+		struct {
+			/* Received packet size, only valid for responders. */
+			u32	packet_size;
+			/*
+			 * Number of resource holding WQE, depends on type.
+			 */
+			u32	wq_num;
+			/*
+			 * WQE index. Refers to either the send queue or
+			 * receive queue, according to event_subtype.
+			 */
+			u16	wqe_index;
+		} wqe;
+		/* RDMA responder pagefault details */
+		struct {
+			u32	r_key;
+			/*
+			 * Received packet size, minimal size page fault
+			 * resolution required for forward progress.
+			 */
+			u32	packet_size;
+			u32	rdma_op_len;
+			u64	rdma_va;
+		} rdma;
+	};
+
+	struct mlx5_ib_pf_eq	*eq;
+	struct work_struct	work;
+};
+
 #define MAX_PREFETCH_LEN (4*1024*1024U)
 
 /* Timeout in ms to wait for an active mmu notifier to complete when handling
@@ -304,14 +344,20 @@ static void mlx5_ib_page_fault_resume(struct mlx5_ib_dev *dev,
 {
 	int wq_num = pfault->event_subtype == MLX5_PFAULT_SUBTYPE_WQE ?
 		     pfault->wqe.wq_num : pfault->token;
-	int ret = mlx5_core_page_fault_resume(dev->mdev,
-					      pfault->token,
-					      wq_num,
-					      pfault->type,
-					      error);
-	if (ret)
-		mlx5_ib_err(dev, "Failed to resolve the page fault on WQ 0x%x\n",
-			    wq_num);
+	u32 out[MLX5_ST_SZ_DW(page_fault_resume_out)] = { };
+	u32 in[MLX5_ST_SZ_DW(page_fault_resume_in)]   = { };
+	int err;
+
+	MLX5_SET(page_fault_resume_in, in, opcode, MLX5_CMD_OP_PAGE_FAULT_RESUME);
+	MLX5_SET(page_fault_resume_in, in, page_fault_type, pfault->type);
+	MLX5_SET(page_fault_resume_in, in, token, pfault->token);
+	MLX5_SET(page_fault_resume_in, in, wq_number, wq_num);
+	MLX5_SET(page_fault_resume_in, in, error, !!error);
+
+	err = mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		mlx5_ib_err(dev, "Failed to resolve the page fault on WQ 0x%x err %d\n",
+			    wq_num, err);
 }
 
 static struct mlx5_ib_mr *implicit_mr_alloc(struct ib_pd *pd,
@@ -1196,10 +1242,8 @@ static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_dev *dev,
 	}
 }
 
-void mlx5_ib_pfault(struct mlx5_core_dev *mdev, void *context,
-		    struct mlx5_pagefault *pfault)
+static void mlx5_ib_pfault(struct mlx5_ib_dev *dev, struct mlx5_pagefault *pfault)
 {
-	struct mlx5_ib_dev *dev = context;
 	u8 event_subtype = pfault->event_subtype;
 
 	switch (event_subtype) {
@@ -1216,6 +1260,203 @@ void mlx5_ib_pfault(struct mlx5_core_dev *mdev, void *context,
 	}
 }
 
+static void mlx5_ib_eqe_pf_action(struct work_struct *work)
+{
+	struct mlx5_pagefault *pfault = container_of(work,
+						     struct mlx5_pagefault,
+						     work);
+	struct mlx5_ib_pf_eq *eq = pfault->eq;
+
+	mlx5_ib_pfault(eq->dev, pfault);
+	mempool_free(pfault, eq->pool);
+}
+
+static void mlx5_ib_eq_pf_process(struct mlx5_ib_pf_eq *eq)
+{
+	struct mlx5_eqe_page_fault *pf_eqe;
+	struct mlx5_pagefault *pfault;
+	struct mlx5_eqe *eqe;
+	int cc = 0;
+
+	while ((eqe = mlx5_eq_get_eqe(eq->core, cc))) {
+		pfault = mempool_alloc(eq->pool, GFP_ATOMIC);
+		if (!pfault) {
+			schedule_work(&eq->work);
+			break;
+		}
+
+		pf_eqe = &eqe->data.page_fault;
+		pfault->event_subtype = eqe->sub_type;
+		pfault->bytes_committed = be32_to_cpu(pf_eqe->bytes_committed);
+
+		mlx5_ib_dbg(eq->dev,
+			    "PAGE_FAULT: subtype: 0x%02x, bytes_committed: 0x%06x\n",
+			    eqe->sub_type, pfault->bytes_committed);
+
+		switch (eqe->sub_type) {
+		case MLX5_PFAULT_SUBTYPE_RDMA:
+			/* RDMA based event */
+			pfault->type =
+				be32_to_cpu(pf_eqe->rdma.pftype_token) >> 24;
+			pfault->token =
+				be32_to_cpu(pf_eqe->rdma.pftype_token) &
+				MLX5_24BIT_MASK;
+			pfault->rdma.r_key =
+				be32_to_cpu(pf_eqe->rdma.r_key);
+			pfault->rdma.packet_size =
+				be16_to_cpu(pf_eqe->rdma.packet_length);
+			pfault->rdma.rdma_op_len =
+				be32_to_cpu(pf_eqe->rdma.rdma_op_len);
+			pfault->rdma.rdma_va =
+				be64_to_cpu(pf_eqe->rdma.rdma_va);
+			mlx5_ib_dbg(eq->dev,
+				    "PAGE_FAULT: type:0x%x, token: 0x%06x, r_key: 0x%08x\n",
+				    pfault->type, pfault->token,
+				    pfault->rdma.r_key);
+			mlx5_ib_dbg(eq->dev,
+				    "PAGE_FAULT: rdma_op_len: 0x%08x, rdma_va: 0x%016llx\n",
+				    pfault->rdma.rdma_op_len,
+				    pfault->rdma.rdma_va);
+			break;
+
+		case MLX5_PFAULT_SUBTYPE_WQE:
+			/* WQE based event */
+			pfault->type =
+				(be32_to_cpu(pf_eqe->wqe.pftype_wq) >> 24) & 0x7;
+			pfault->token =
+				be32_to_cpu(pf_eqe->wqe.token);
+			pfault->wqe.wq_num =
+				be32_to_cpu(pf_eqe->wqe.pftype_wq) &
+				MLX5_24BIT_MASK;
+			pfault->wqe.wqe_index =
+				be16_to_cpu(pf_eqe->wqe.wqe_index);
+			pfault->wqe.packet_size =
+				be16_to_cpu(pf_eqe->wqe.packet_length);
+			mlx5_ib_dbg(eq->dev,
+				    "PAGE_FAULT: type:0x%x, token: 0x%06x, wq_num: 0x%06x, wqe_index: 0x%04x\n",
+				    pfault->type, pfault->token,
+				    pfault->wqe.wq_num,
+				    pfault->wqe.wqe_index);
+			break;
+
+		default:
+			mlx5_ib_warn(eq->dev,
+				     "Unsupported page fault event sub-type: 0x%02hhx\n",
+				     eqe->sub_type);
+			/* Unsupported page faults should still be
+			 * resolved by the page fault handler
+			 */
+		}
+
+		pfault->eq = eq;
+		INIT_WORK(&pfault->work, mlx5_ib_eqe_pf_action);
+		queue_work(eq->wq, &pfault->work);
+
+		cc = mlx5_eq_update_cc(eq->core, ++cc);
+	}
+
+	mlx5_eq_update_ci(eq->core, cc, 1);
+}
+
+static irqreturn_t mlx5_ib_eq_pf_int(int irq, void *eq_ptr)
+{
+	struct mlx5_ib_pf_eq *eq = eq_ptr;
+	unsigned long flags;
+
+	if (spin_trylock_irqsave(&eq->lock, flags)) {
+		mlx5_ib_eq_pf_process(eq);
+		spin_unlock_irqrestore(&eq->lock, flags);
+	} else {
+		schedule_work(&eq->work);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/* mempool_refill() was proposed but unfortunately wasn't accepted
+ * http://lkml.iu.edu/hypermail/linux/kernel/1512.1/05073.html
+ * Cheap workaround.
+ */
+static void mempool_refill(mempool_t *pool)
+{
+	while (pool->curr_nr < pool->min_nr)
+		mempool_free(mempool_alloc(pool, GFP_KERNEL), pool);
+}
+
+static void mlx5_ib_eq_pf_action(struct work_struct *work)
+{
+	struct mlx5_ib_pf_eq *eq =
+		container_of(work, struct mlx5_ib_pf_eq, work);
+
+	mempool_refill(eq->pool);
+
+	spin_lock_irq(&eq->lock);
+	mlx5_ib_eq_pf_process(eq);
+	spin_unlock_irq(&eq->lock);
+}
+
+enum {
+	MLX5_IB_NUM_PF_EQE	= 0x1000,
+	MLX5_IB_NUM_PF_DRAIN	= 64,
+};
+
+static int
+mlx5_ib_create_pf_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq)
+{
+	struct mlx5_eq_param param = {};
+	int err;
+
+	INIT_WORK(&eq->work, mlx5_ib_eq_pf_action);
+	spin_lock_init(&eq->lock);
+	eq->dev = dev;
+
+	eq->pool = mempool_create_kmalloc_pool(MLX5_IB_NUM_PF_DRAIN,
+					       sizeof(struct mlx5_pagefault));
+	if (!eq->pool)
+		return -ENOMEM;
+
+	eq->wq = alloc_workqueue("mlx5_ib_page_fault",
+				 WQ_HIGHPRI | WQ_UNBOUND | WQ_MEM_RECLAIM,
+				 MLX5_NUM_CMD_EQE);
+	if (!eq->wq) {
+		err = -ENOMEM;
+		goto err_mempool;
+	}
+
+	param = (struct mlx5_eq_param) {
+		.index = MLX5_EQ_PFAULT_IDX,
+		.mask = 1 << MLX5_EVENT_TYPE_PAGE_FAULT,
+		.nent = MLX5_IB_NUM_PF_EQE,
+		.context = eq,
+		.handler = mlx5_ib_eq_pf_int
+	};
+	eq->core = mlx5_eq_create_generic(dev->mdev, "mlx5_ib_page_fault_eq", &param);
+	if (IS_ERR(eq->core)) {
+		err = PTR_ERR(eq->core);
+		goto err_wq;
+	}
+
+	return 0;
+err_wq:
+	destroy_workqueue(eq->wq);
+err_mempool:
+	mempool_destroy(eq->pool);
+	return err;
+}
+
+static int
+mlx5_ib_destroy_pf_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq)
+{
+	int err;
+
+	err = mlx5_eq_destroy_generic(dev->mdev, eq->core);
+	cancel_work_sync(&eq->work);
+	destroy_workqueue(eq->wq);
+	mempool_destroy(eq->pool);
+
+	return err;
+}
+
 void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent)
 {
 	if (!(ent->dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT))
@@ -1244,7 +1485,7 @@ void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent)
 
 int mlx5_ib_odp_init_one(struct mlx5_ib_dev *dev)
 {
-	int ret;
+	int ret = 0;
 
 	if (dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT) {
 		ret = mlx5_cmd_null_mkey(dev->mdev, &dev->null_mkey);
@@ -1254,7 +1495,20 @@ int mlx5_ib_odp_init_one(struct mlx5_ib_dev *dev)
 		}
 	}
 
-	return 0;
+	if (!MLX5_CAP_GEN(dev->mdev, pg))
+		return ret;
+
+	ret = mlx5_ib_create_pf_eq(dev, &dev->odp_pf_eq);
+
+	return ret;
+}
+
+void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *dev)
+{
+	if (!MLX5_CAP_GEN(dev->mdev, pg))
+		return;
+
+	mlx5_ib_destroy_pf_eq(dev, &dev->odp_pf_eq);
 }
 
 int mlx5_ib_odp_init(void)
@@ -1264,4 +1518,3 @@ int mlx5_ib_odp_init(void)
 
 	return 0;
 }
-
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 37ba7c78859d..7eedbea38a78 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -139,17 +139,6 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 
 		spin_lock_irq(&priv->ctx_lock);
 		list_add_tail(&dev_ctx->list, &priv->ctx_list);
-
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-		if (dev_ctx->intf->pfault) {
-			if (priv->pfault) {
-				mlx5_core_err(dev, "multiple page fault handlers not supported");
-			} else {
-				priv->pfault_ctx = dev_ctx->context;
-				priv->pfault = dev_ctx->intf->pfault;
-			}
-		}
-#endif
 		spin_unlock_irq(&priv->ctx_lock);
 	}
 
@@ -179,15 +168,6 @@ void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 	if (!dev_ctx)
 		return;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	spin_lock_irq(&priv->ctx_lock);
-	if (priv->pfault == dev_ctx->intf->pfault)
-		priv->pfault = NULL;
-	spin_unlock_irq(&priv->ctx_lock);
-
-	synchronize_srcu(&priv->pfault_srcu);
-#endif
-
 	spin_lock_irq(&priv->ctx_lock);
 	list_del(&dev_ctx->list);
 	spin_unlock_irq(&priv->ctx_lock);
@@ -447,20 +427,6 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 	spin_unlock_irqrestore(&priv->ctx_lock, flags);
 }
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-void mlx5_core_page_fault(struct mlx5_core_dev *dev,
-			  struct mlx5_pagefault *pfault)
-{
-	struct mlx5_priv *priv = &dev->priv;
-	int srcu_idx;
-
-	srcu_idx = srcu_read_lock(&priv->pfault_srcu);
-	if (priv->pfault)
-		priv->pfault(dev, priv->pfault_ctx, pfault);
-	srcu_read_unlock(&priv->pfault_srcu, srcu_idx);
-}
-#endif
-
 void mlx5_dev_list_lock(void)
 {
 	mutex_lock(&mlx5_intf_mutex);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index ec1f5018546e..895401609c63 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -56,13 +56,6 @@ enum {
 	MLX5_EQ_STATE_ALWAYS_ARMED	= 0xb,
 };
 
-enum {
-	MLX5_NUM_SPARE_EQE	= 0x80,
-	MLX5_NUM_ASYNC_EQE	= 0x1000,
-	MLX5_NUM_CMD_EQE	= 32,
-	MLX5_NUM_PF_DRAIN	= 64,
-};
-
 enum {
 	MLX5_EQ_DOORBEL_OFFSET	= 0x40,
 };
@@ -79,9 +72,6 @@ struct mlx5_eq_table {
 	struct mlx5_eq          async_eq;
 	struct mlx5_eq	        cmd_eq;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	struct mlx5_eq_pagefault pfault_eq;
-#endif
 	struct mutex            lock; /* sync async eqs creations */
 	int			num_comp_vectors;
 	struct mlx5_irq_info	*irq_info;
@@ -222,224 +212,6 @@ static void eq_update_ci(struct mlx5_eq *eq, int arm)
 	mb();
 }
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-static void eqe_pf_action(struct work_struct *work)
-{
-	struct mlx5_pagefault *pfault = container_of(work,
-						     struct mlx5_pagefault,
-						     work);
-	struct mlx5_eq_pagefault *eq = pfault->eq;
-
-	mlx5_core_page_fault(eq->core->dev, pfault);
-	mempool_free(pfault, eq->pool);
-}
-
-static void eq_pf_process(struct mlx5_eq_pagefault *eq)
-{
-	struct mlx5_core_dev *dev = eq->core->dev;
-	struct mlx5_eqe_page_fault *pf_eqe;
-	struct mlx5_pagefault *pfault;
-	struct mlx5_eqe *eqe;
-	int set_ci = 0;
-
-	while ((eqe = next_eqe_sw(eq->core))) {
-		pfault = mempool_alloc(eq->pool, GFP_ATOMIC);
-		if (!pfault) {
-			schedule_work(&eq->work);
-			break;
-		}
-
-		dma_rmb();
-		pf_eqe = &eqe->data.page_fault;
-		pfault->event_subtype = eqe->sub_type;
-		pfault->bytes_committed = be32_to_cpu(pf_eqe->bytes_committed);
-
-		mlx5_core_dbg(dev,
-			      "PAGE_FAULT: subtype: 0x%02x, bytes_committed: 0x%06x\n",
-			      eqe->sub_type, pfault->bytes_committed);
-
-		switch (eqe->sub_type) {
-		case MLX5_PFAULT_SUBTYPE_RDMA:
-			/* RDMA based event */
-			pfault->type =
-				be32_to_cpu(pf_eqe->rdma.pftype_token) >> 24;
-			pfault->token =
-				be32_to_cpu(pf_eqe->rdma.pftype_token) &
-				MLX5_24BIT_MASK;
-			pfault->rdma.r_key =
-				be32_to_cpu(pf_eqe->rdma.r_key);
-			pfault->rdma.packet_size =
-				be16_to_cpu(pf_eqe->rdma.packet_length);
-			pfault->rdma.rdma_op_len =
-				be32_to_cpu(pf_eqe->rdma.rdma_op_len);
-			pfault->rdma.rdma_va =
-				be64_to_cpu(pf_eqe->rdma.rdma_va);
-			mlx5_core_dbg(dev,
-				      "PAGE_FAULT: type:0x%x, token: 0x%06x, r_key: 0x%08x\n",
-				      pfault->type, pfault->token,
-				      pfault->rdma.r_key);
-			mlx5_core_dbg(dev,
-				      "PAGE_FAULT: rdma_op_len: 0x%08x, rdma_va: 0x%016llx\n",
-				      pfault->rdma.rdma_op_len,
-				      pfault->rdma.rdma_va);
-			break;
-
-		case MLX5_PFAULT_SUBTYPE_WQE:
-			/* WQE based event */
-			pfault->type =
-				(be32_to_cpu(pf_eqe->wqe.pftype_wq) >> 24) & 0x7;
-			pfault->token =
-				be32_to_cpu(pf_eqe->wqe.token);
-			pfault->wqe.wq_num =
-				be32_to_cpu(pf_eqe->wqe.pftype_wq) &
-				MLX5_24BIT_MASK;
-			pfault->wqe.wqe_index =
-				be16_to_cpu(pf_eqe->wqe.wqe_index);
-			pfault->wqe.packet_size =
-				be16_to_cpu(pf_eqe->wqe.packet_length);
-			mlx5_core_dbg(dev,
-				      "PAGE_FAULT: type:0x%x, token: 0x%06x, wq_num: 0x%06x, wqe_index: 0x%04x\n",
-				      pfault->type, pfault->token,
-				      pfault->wqe.wq_num,
-				      pfault->wqe.wqe_index);
-			break;
-
-		default:
-			mlx5_core_warn(dev,
-				       "Unsupported page fault event sub-type: 0x%02hhx\n",
-				       eqe->sub_type);
-			/* Unsupported page faults should still be
-			 * resolved by the page fault handler
-			 */
-		}
-
-		pfault->eq = eq;
-		INIT_WORK(&pfault->work, eqe_pf_action);
-		queue_work(eq->wq, &pfault->work);
-
-		++eq->core->cons_index;
-		++set_ci;
-
-		if (unlikely(set_ci >= MLX5_NUM_SPARE_EQE)) {
-			eq_update_ci(eq->core, 0);
-			set_ci = 0;
-		}
-	}
-
-	eq_update_ci(eq->core, 1);
-}
-
-static irqreturn_t mlx5_eq_pf_int(int irq, void *eq_ptr)
-{
-	struct mlx5_eq_pagefault *eq = eq_ptr;
-	unsigned long flags;
-
-	if (spin_trylock_irqsave(&eq->lock, flags)) {
-		eq_pf_process(eq);
-		spin_unlock_irqrestore(&eq->lock, flags);
-	} else {
-		schedule_work(&eq->work);
-	}
-
-	return IRQ_HANDLED;
-}
-
-/* mempool_refill() was proposed but unfortunately wasn't accepted
- * http://lkml.iu.edu/hypermail/linux/kernel/1512.1/05073.html
- * Chip workaround.
- */
-static void mempool_refill(mempool_t *pool)
-{
-	while (pool->curr_nr < pool->min_nr)
-		mempool_free(mempool_alloc(pool, GFP_KERNEL), pool);
-}
-
-static void eq_pf_action(struct work_struct *work)
-{
-	struct mlx5_eq_pagefault *eq =
-		container_of(work, struct mlx5_eq_pagefault, work);
-
-	mempool_refill(eq->pool);
-
-	spin_lock_irq(&eq->lock);
-	eq_pf_process(eq);
-	spin_unlock_irq(&eq->lock);
-}
-
-static int
-create_pf_eq(struct mlx5_core_dev *dev, struct mlx5_eq_pagefault *eq)
-{
-	struct mlx5_eq_param param = {};
-	int err;
-
-	spin_lock_init(&eq->lock);
-	INIT_WORK(&eq->work, eq_pf_action);
-
-	eq->pool = mempool_create_kmalloc_pool(MLX5_NUM_PF_DRAIN,
-					       sizeof(struct mlx5_pagefault));
-	if (!eq->pool)
-		return -ENOMEM;
-
-	eq->wq = alloc_workqueue("mlx5_page_fault",
-				 WQ_HIGHPRI | WQ_UNBOUND | WQ_MEM_RECLAIM,
-				 MLX5_NUM_CMD_EQE);
-	if (!eq->wq) {
-		err = -ENOMEM;
-		goto err_mempool;
-	}
-
-	param = (struct mlx5_eq_param) {
-		.index = MLX5_EQ_PFAULT_IDX,
-		.mask = 1 << MLX5_EVENT_TYPE_PAGE_FAULT,
-		.nent = MLX5_NUM_ASYNC_EQE,
-		.context = eq,
-		.handler = mlx5_eq_pf_int
-	};
-
-	eq->core = mlx5_eq_create_generic(dev, "mlx5_page_fault_eq", &param);
-	if (IS_ERR(eq->core)) {
-		err = PTR_ERR(eq->core);
-		goto err_wq;
-	}
-
-	return 0;
-err_wq:
-	destroy_workqueue(eq->wq);
-err_mempool:
-	mempool_destroy(eq->pool);
-	return err;
-}
-
-static int destroy_pf_eq(struct mlx5_core_dev *dev, struct mlx5_eq_pagefault *eq)
-{
-	int err;
-
-	err = mlx5_eq_destroy_generic(dev, eq->core);
-	cancel_work_sync(&eq->work);
-	destroy_workqueue(eq->wq);
-	mempool_destroy(eq->pool);
-
-	return err;
-}
-
-int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 token,
-				u32 wq_num, u8 type, int error)
-{
-	u32 out[MLX5_ST_SZ_DW(page_fault_resume_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(page_fault_resume_in)]   = {0};
-
-	MLX5_SET(page_fault_resume_in, in, opcode,
-		 MLX5_CMD_OP_PAGE_FAULT_RESUME);
-	MLX5_SET(page_fault_resume_in, in, error, !!error);
-	MLX5_SET(page_fault_resume_in, in, page_fault_type, type);
-	MLX5_SET(page_fault_resume_in, in, wq_number, wq_num);
-	MLX5_SET(page_fault_resume_in, in, token, token);
-
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-EXPORT_SYMBOL_GPL(mlx5_core_page_fault_resume);
-#endif
-
 static void general_event_handler(struct mlx5_core_dev *dev,
 				  struct mlx5_eqe *eqe)
 {
@@ -1016,22 +788,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 		goto err2;
 	}
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (MLX5_CAP_GEN(dev, pg)) {
-		err = create_pf_eq(dev, &table->pfault_eq);
-		if (err) {
-			mlx5_core_warn(dev, "failed to create page fault EQ %d\n",
-				       err);
-			goto err3;
-		}
-	}
-
-	return err;
-err3:
-	destroy_async_eq(dev, &table->pages_eq);
-#else
 	return err;
-#endif
 
 err2:
 	destroy_async_eq(dev, &table->async_eq);
@@ -1047,15 +804,6 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev)
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	int err;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (MLX5_CAP_GEN(dev, pg)) {
-		err = destroy_pf_eq(dev, &table->pfault_eq);
-		if (err)
-			mlx5_core_err(dev, "failed to destroy page fault eq, err(%d)\n",
-				      err);
-	}
-#endif
-
 	err = destroy_async_eq(dev, &table->pages_eq);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n",
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index db32057ad054..4cc2d442cef6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -39,14 +39,6 @@ struct mlx5_eq_comp {
 	struct list_head        list;
 };
 
-struct mlx5_eq_pagefault {
-	struct mlx5_eq          *core;
-	struct work_struct       work;
-	spinlock_t               lock; /* Pagefaults spinlock */
-	struct workqueue_struct  *wq;
-	mempool_t                *pool;
-};
-
 int mlx5_eq_table_init(struct mlx5_core_dev *dev);
 void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev);
 int mlx5_eq_table_create(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 3de83fe65f2b..91022f141855 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1169,14 +1169,6 @@ static int init_one(struct pci_dev *pdev,
 	INIT_LIST_HEAD(&priv->waiting_events_list);
 	priv->is_accum_events = false;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	err = init_srcu_struct(&priv->pfault_srcu);
-	if (err) {
-		dev_err(&pdev->dev, "init_srcu_struct failed with error code %d\n",
-			err);
-		goto clean_dev;
-	}
-#endif
 	mutex_init(&priv->bfregs.reg_head.lock);
 	mutex_init(&priv->bfregs.wc_head.lock);
 	INIT_LIST_HEAD(&priv->bfregs.reg_head.list);
@@ -1185,7 +1177,7 @@ static int init_one(struct pci_dev *pdev,
 	err = mlx5_pci_init(dev, priv);
 	if (err) {
 		dev_err(&pdev->dev, "mlx5_pci_init failed with error code %d\n", err);
-		goto clean_srcu;
+		goto clean_dev;
 	}
 
 	err = mlx5_health_init(dev);
@@ -1218,11 +1210,7 @@ clean_health:
 	mlx5_health_cleanup(dev);
 close_pci:
 	mlx5_pci_close(dev, priv);
-clean_srcu:
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	cleanup_srcu_struct(&priv->pfault_srcu);
 clean_dev:
-#endif
 	devlink_free(devlink);
 
 	return err;
@@ -1246,9 +1234,6 @@ static void remove_one(struct pci_dev *pdev)
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_health_cleanup(dev);
 	mlx5_pci_close(dev, priv);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	cleanup_srcu_struct(&priv->pfault_srcu);
-#endif
 	devlink_free(devlink);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 4728b027cb9e..21727d9eeb84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -100,8 +100,6 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev);
 
 void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 		     unsigned long param);
-void mlx5_core_page_fault(struct mlx5_core_dev *dev,
-			  struct mlx5_pagefault *pfault);
 void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index fe9b552aa649..f41e6713df10 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -510,7 +510,6 @@ struct mlx5_fc_stats {
 struct mlx5_mpfs;
 struct mlx5_eswitch;
 struct mlx5_lag;
-struct mlx5_pagefault;
 struct mlx5_eq_table;
 
 struct mlx5_rate_limit {
@@ -619,13 +618,6 @@ struct mlx5_priv {
 
 	struct mlx5_port_module_event_stats  pme_stats;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	void		      (*pfault)(struct mlx5_core_dev *dev,
-					void *context,
-					struct mlx5_pagefault *pfault);
-	void		       *pfault_ctx;
-	struct srcu_struct      pfault_srcu;
-#endif
 	struct mlx5_bfreg_data		bfregs;
 	struct mlx5_uars_page	       *uar;
 };
@@ -650,44 +642,6 @@ enum mlx5_pagefault_type_flags {
 	MLX5_PFAULT_RDMA      = 1 << 2,
 };
 
-/* Contains the details of a pagefault. */
-struct mlx5_pagefault {
-	u32			bytes_committed;
-	u32			token;
-	u8			event_subtype;
-	u8			type;
-	union {
-		/* Initiator or send message responder pagefault details. */
-		struct {
-			/* Received packet size, only valid for responders. */
-			u32	packet_size;
-			/*
-			 * Number of resource holding WQE, depends on type.
-			 */
-			u32	wq_num;
-			/*
-			 * WQE index. Refers to either the send queue or
-			 * receive queue, according to event_subtype.
-			 */
-			u16	wqe_index;
-		} wqe;
-		/* RDMA responder pagefault details */
-		struct {
-			u32	r_key;
-			/*
-			 * Received packet size, minimal size page fault
-			 * resolution required for forward progress.
-			 */
-			u32	packet_size;
-			u32	rdma_op_len;
-			u64	rdma_va;
-		} rdma;
-	};
-
-	struct mlx5_eq_pagefault *eq;
-	struct work_struct	work;
-};
-
 struct mlx5_td {
 	struct list_head tirs_list;
 	u32              tdn;
@@ -1118,9 +1072,6 @@ struct mlx5_interface {
 	void			(*detach)(struct mlx5_core_dev *dev, void *context);
 	void			(*event)(struct mlx5_core_dev *dev, void *context,
 					 enum mlx5_dev_event event, unsigned long param);
-	void			(*pfault)(struct mlx5_core_dev *dev,
-					  void *context,
-					  struct mlx5_pagefault *pfault);
 	void *                  (*get_dev)(void *context);
 	int			protocol;
 	struct list_head	list;
diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h
index c733673ba5f6..71d82c5a1a02 100644
--- a/include/linux/mlx5/eq.h
+++ b/include/linux/mlx5/eq.h
@@ -17,6 +17,10 @@ enum {
 	MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS,
 };
 
+#define MLX5_NUM_CMD_EQE   (32)
+#define MLX5_NUM_ASYNC_EQE (0x1000)
+#define MLX5_NUM_SPARE_EQE (0x80)
+
 struct mlx5_eq;
 
 struct mlx5_eq_param {
@@ -36,4 +40,21 @@ mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
 struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc);
 void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm);
 
+/* The HCA will think the queue has overflowed if we
+ * don't tell it we've been processing events.  We
+ * create EQs with MLX5_NUM_SPARE_EQE extra entries,
+ * so we must update our consumer index at
+ * least that often.
+ *
+ * mlx5_eq_update_cc must be called on every EQE @EQ irq handler
+ */
+static inline u32 mlx5_eq_update_cc(struct mlx5_eq *eq, u32 cc)
+{
+	if (unlikely(cc >= MLX5_NUM_SPARE_EQE)) {
+		mlx5_eq_update_ci(eq, cc, 0);
+		cc = 0;
+	}
+	return cc;
+}
+
 #endif /* MLX5_CORE_EQ_H */
-- 
cgit v1.2.3


From 6d2d6fc83a281d51863fb5d08b59333ed1b46cc1 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 19 Nov 2018 10:52:42 -0800
Subject: net/mlx5: EQ, Make EQE access methods inline

These are one/two liner generic EQ access methods, better have them
declared static inline in eq.h.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c     | 23 ----------------------
 drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h | 25 +++++++++++++++++++++++-
 2 files changed, 24 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 895401609c63..6ba8e401a0c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -46,7 +46,6 @@
 #include "diag/fw_tracer.h"
 
 enum {
-	MLX5_EQE_SIZE		= sizeof(struct mlx5_eqe),
 	MLX5_EQE_OWNER_INIT_VAL	= 0x1,
 };
 
@@ -103,18 +102,6 @@ static int mlx5_cmd_destroy_eq(struct mlx5_core_dev *dev, u8 eqn)
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-static struct mlx5_eqe *get_eqe(struct mlx5_eq *eq, u32 entry)
-{
-	return mlx5_buf_offset(&eq->buf, entry * MLX5_EQE_SIZE);
-}
-
-static struct mlx5_eqe *next_eqe_sw(struct mlx5_eq *eq)
-{
-	struct mlx5_eqe *eqe = get_eqe(eq, eq->cons_index & (eq->nent - 1));
-
-	return ((eqe->owner & 1) ^ !!(eq->cons_index & eq->nent)) ? NULL : eqe;
-}
-
 static const char *eqe_type_str(u8 type)
 {
 	switch (type) {
@@ -202,16 +189,6 @@ static enum mlx5_dev_event port_subtype_event(u8 subtype)
 	return -1;
 }
 
-static void eq_update_ci(struct mlx5_eq *eq, int arm)
-{
-	__be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2);
-	u32 val = (eq->cons_index & 0xffffff) | (eq->eqn << 24);
-
-	__raw_writel((__force u32)cpu_to_be32(val), addr);
-	/* We still want ordering, just not swabbing, so add a barrier */
-	mb();
-}
-
 static void general_event_handler(struct mlx5_core_dev *dev,
 				  struct mlx5_eqe *eqe)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index 4cc2d442cef6..6d8c8a57d52b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -5,7 +5,8 @@
 #define __LIB_MLX5_EQ_H__
 #include <linux/mlx5/driver.h>
 
-#define MLX5_MAX_IRQ_NAME       (32)
+#define MLX5_MAX_IRQ_NAME   (32)
+#define MLX5_EQE_SIZE       (sizeof(struct mlx5_eqe))
 
 struct mlx5_eq_tasklet {
 	struct list_head      list;
@@ -39,6 +40,28 @@ struct mlx5_eq_comp {
 	struct list_head        list;
 };
 
+static inline struct mlx5_eqe *get_eqe(struct mlx5_eq *eq, u32 entry)
+{
+	return mlx5_buf_offset(&eq->buf, entry * MLX5_EQE_SIZE);
+}
+
+static inline struct mlx5_eqe *next_eqe_sw(struct mlx5_eq *eq)
+{
+	struct mlx5_eqe *eqe = get_eqe(eq, eq->cons_index & (eq->nent - 1));
+
+	return ((eqe->owner & 1) ^ !!(eq->cons_index & eq->nent)) ? NULL : eqe;
+}
+
+static inline void eq_update_ci(struct mlx5_eq *eq, int arm)
+{
+	__be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2);
+	u32 val = (eq->cons_index & 0xffffff) | (eq->eqn << 24);
+
+	__raw_writel((__force u32)cpu_to_be32(val), addr);
+	/* We still want ordering, just not swabbing, so add a barrier */
+	mb();
+}
+
 int mlx5_eq_table_init(struct mlx5_core_dev *dev);
 void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev);
 int mlx5_eq_table_create(struct mlx5_core_dev *dev);
-- 
cgit v1.2.3


From b2c851006386c1c5c0e55eab4a7f60da2a3e25b3 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 20 Nov 2018 10:15:36 -0800
Subject: ipv4: Don't try to print ASCII of link level header in martian dumps.

This has no value whatsoever.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c0a9d26c06ce..c4ddbc5f01fc 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1677,7 +1677,7 @@ static void ip_handle_martian_source(struct net_device *dev,
 			print_hex_dump(KERN_WARNING, "ll header: ",
 				       DUMP_PREFIX_OFFSET, 16, 1,
 				       skb_mac_header(skb),
-				       dev->hard_header_len, true);
+				       dev->hard_header_len, false);
 		}
 	}
 #endif
-- 
cgit v1.2.3


From ade9628ed049242fac5dd94730881f8c5e244634 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 19 Nov 2018 17:45:55 -0800
Subject: tcp: drop dst in tcp_add_backlog()

Under stress, softirq rx handler often hits a socket owned by the user,
and has to queue the packet into socket backlog.

When this happens, skb dst refcount is taken before we escape rcu
protected region. This is done from __sk_add_backlog() calling
skb_dst_force().

Consumer will have to perform the opposite costly operation.

AFAIK nothing in tcp stack requests the dst after skb was stored
in the backlog. If this was the case, we would have had failures
already since skb_dst_force() can end up clearing skb dst anyway.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0952d4b772e7..795605a23275 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1634,6 +1634,8 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	 */
 	skb_condense(skb);
 
+	skb_dst_drop(skb);
+
 	if (unlikely(sk_add_backlog(sk, skb, limit))) {
 		bh_unlock_sock(sk);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP);
-- 
cgit v1.2.3


From b539ea60f5043b9acd7562f04fa2117f18776cbb Mon Sep 17 00:00:00 2001
From: Arjun Vynipadath <arjun@chelsio.com>
Date: Tue, 20 Nov 2018 12:11:39 +0530
Subject: cxgb4/cxgb4vf: Fix mac_hlist initialization and free

Null pointer dereference seen when cxgb4vf driver is unloaded
without bringing up any interfaces, moving mac_hlist initialization
to driver probe and free the mac_hlist in remove to fix the issue.

Fixes: 24357e06ba51 ("cxgb4vf: fix memleak in mac_hlist initialization")
Signed-off-by: Arjun Vynipadath <arjun@chelsio.com>
Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c     | 19 ++++++++++---------
 drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c |  6 +++---
 2 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 649bf7c586c1..4fbe04d5f207 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2280,8 +2280,6 @@ static int cxgb_up(struct adapter *adap)
 #if IS_ENABLED(CONFIG_IPV6)
 	update_clip(adap);
 #endif
-	/* Initialize hash mac addr list*/
-	INIT_LIST_HEAD(&adap->mac_hlist);
 	return err;
 
  irq_err:
@@ -2295,8 +2293,6 @@ static int cxgb_up(struct adapter *adap)
 
 static void cxgb_down(struct adapter *adapter)
 {
-	struct hash_mac_addr *entry, *tmp;
-
 	cancel_work_sync(&adapter->tid_release_task);
 	cancel_work_sync(&adapter->db_full_task);
 	cancel_work_sync(&adapter->db_drop_task);
@@ -2306,11 +2302,6 @@ static void cxgb_down(struct adapter *adapter)
 	t4_sge_stop(adapter);
 	t4_free_sge_resources(adapter);
 
-	list_for_each_entry_safe(entry, tmp, &adapter->mac_hlist, list) {
-		list_del(&entry->list);
-		kfree(entry);
-	}
-
 	adapter->flags &= ~FULL_INIT_DONE;
 }
 
@@ -5629,6 +5620,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			     (is_t5(adapter->params.chip) ? STATMODE_V(0) :
 			      T6_STATMODE_V(0)));
 
+	/* Initialize hash mac addr list */
+	INIT_LIST_HEAD(&adapter->mac_hlist);
+
 	for_each_port(adapter, i) {
 		netdev = alloc_etherdev_mq(sizeof(struct port_info),
 					   MAX_ETH_QSETS);
@@ -5907,6 +5901,7 @@ fw_attach_fail:
 static void remove_one(struct pci_dev *pdev)
 {
 	struct adapter *adapter = pci_get_drvdata(pdev);
+	struct hash_mac_addr *entry, *tmp;
 
 	if (!adapter) {
 		pci_release_regions(pdev);
@@ -5956,6 +5951,12 @@ static void remove_one(struct pci_dev *pdev)
 		if (adapter->num_uld || adapter->num_ofld_uld)
 			t4_uld_mem_free(adapter);
 		free_some_resources(adapter);
+		list_for_each_entry_safe(entry, tmp, &adapter->mac_hlist,
+					 list) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
+
 #if IS_ENABLED(CONFIG_IPV6)
 		t4_cleanup_clip_tbl(adapter);
 #endif
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 8ec503c88c06..8a2ad6b387ea 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -723,9 +723,6 @@ static int adapter_up(struct adapter *adapter)
 		if (adapter->flags & USING_MSIX)
 			name_msix_vecs(adapter);
 
-		/* Initialize hash mac addr list*/
-		INIT_LIST_HEAD(&adapter->mac_hlist);
-
 		adapter->flags |= FULL_INIT_DONE;
 	}
 
@@ -3038,6 +3035,9 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	if (err)
 		goto err_unmap_bar;
 
+	/* Initialize hash mac addr list */
+	INIT_LIST_HEAD(&adapter->mac_hlist);
+
 	/*
 	 * Allocate our "adapter ports" and stitch everything together.
 	 */
-- 
cgit v1.2.3


From a421ce088ac8eb3591d2a1ae0ded2dcece72018f Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@mellanox.com>
Date: Tue, 20 Nov 2018 06:52:03 +0000
Subject: mlxsw: core: Extend cooling device with cooling levels

Extend cooling device with cooling levels vector to allow more
flexibility of PWM setting.

Thermal zone algorithm operates with the numerical states for PWM
setting. Each state is the index, defined in range from 0 to 10 and it's
mapped to the relevant duty cycle value, which is written to PWM
controller. With the current definition fan speed is set to 0% for state
0, 10% for state 1, and so on up to 100% for the maximum state 10.

Some systems have limitation for the PWM speed minimum. For such systems
PWM setting speed to 0% will just disable the ability to increase speed
anymore and such device will be stall on zero speed.  Cooling levels
allow to configure state vector according to the particular system
requirements. For example, if PWM speed is not allowed to be below 30%,
cooling levels could be configured as 30%, 30%, 30%, 30%, 40%, 50% and
so on.

Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 56 +++++++++++++++++++++-
 1 file changed, 55 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 6d29dc428608..61f897b40f82 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -16,6 +16,15 @@
 #define MLXSW_THERMAL_MAX_TEMP	110000	/* 110C */
 #define MLXSW_THERMAL_MAX_STATE	10
 #define MLXSW_THERMAL_MAX_DUTY	255
+/* Minimum and maximum fan allowed speed in percent: from 20% to 100%. Values
+ * MLXSW_THERMAL_MAX_STATE + x, where x is between 2 and 10 are used for
+ * setting fan speed dynamic minimum. For example, if value is set to 14 (40%)
+ * cooling levels vector will be set to 4, 4, 4, 4, 4, 5, 6, 7, 8, 9, 10 to
+ * introduce PWM speed in percent: 40, 40, 40, 40, 40, 50, 60. 70, 80, 90, 100.
+ */
+#define MLXSW_THERMAL_SPEED_MIN		(MLXSW_THERMAL_MAX_STATE + 2)
+#define MLXSW_THERMAL_SPEED_MAX		(MLXSW_THERMAL_MAX_STATE * 2)
+#define MLXSW_THERMAL_SPEED_MIN_LEVEL	2		/* 20% */
 
 struct mlxsw_thermal_trip {
 	int	type;
@@ -68,6 +77,7 @@ struct mlxsw_thermal {
 	const struct mlxsw_bus_info *bus_info;
 	struct thermal_zone_device *tzdev;
 	struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX];
+	u8 cooling_levels[MLXSW_THERMAL_MAX_STATE + 1];
 	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
 	enum thermal_device_mode mode;
 };
@@ -285,12 +295,51 @@ static int mlxsw_thermal_set_cur_state(struct thermal_cooling_device *cdev,
 	struct mlxsw_thermal *thermal = cdev->devdata;
 	struct device *dev = thermal->bus_info->dev;
 	char mfsc_pl[MLXSW_REG_MFSC_LEN];
-	int err, idx;
+	unsigned long cur_state, i;
+	int idx;
+	u8 duty;
+	int err;
 
 	idx = mlxsw_get_cooling_device_idx(thermal, cdev);
 	if (idx < 0)
 		return idx;
 
+	/* Verify if this request is for changing allowed fan dynamical
+	 * minimum. If it is - update cooling levels accordingly and update
+	 * state, if current state is below the newly requested minimum state.
+	 * For example, if current state is 5, and minimal state is to be
+	 * changed from 4 to 6, thermal->cooling_levels[0 to 5] will be changed
+	 * all from 4 to 6. And state 5 (thermal->cooling_levels[4]) should be
+	 * overwritten.
+	 */
+	if (state >= MLXSW_THERMAL_SPEED_MIN &&
+	    state <= MLXSW_THERMAL_SPEED_MAX) {
+		state -= MLXSW_THERMAL_MAX_STATE;
+		for (i = 0; i <= MLXSW_THERMAL_MAX_STATE; i++)
+			thermal->cooling_levels[i] = max(state, i);
+
+		mlxsw_reg_mfsc_pack(mfsc_pl, idx, 0);
+		err = mlxsw_reg_query(thermal->core, MLXSW_REG(mfsc), mfsc_pl);
+		if (err)
+			return err;
+
+		duty = mlxsw_reg_mfsc_pwm_duty_cycle_get(mfsc_pl);
+		cur_state = mlxsw_duty_to_state(duty);
+
+		/* If current fan state is lower than requested dynamical
+		 * minimum, increase fan speed up to dynamical minimum.
+		 */
+		if (state < cur_state)
+			return 0;
+
+		state = cur_state;
+	}
+
+	if (state > MLXSW_THERMAL_MAX_STATE)
+		return -EINVAL;
+
+	/* Normalize the state to the valid speed range. */
+	state = thermal->cooling_levels[state];
 	mlxsw_reg_mfsc_pack(mfsc_pl, idx, mlxsw_state_to_duty(state));
 	err = mlxsw_reg_write(thermal->core, MLXSW_REG(mfsc), mfsc_pl);
 	if (err) {
@@ -369,6 +418,11 @@ int mlxsw_thermal_init(struct mlxsw_core *core,
 		}
 	}
 
+	/* Initialize cooling levels per PWM state. */
+	for (i = 0; i < MLXSW_THERMAL_MAX_STATE; i++)
+		thermal->cooling_levels[i] = max(MLXSW_THERMAL_SPEED_MIN_LEVEL,
+						 i);
+
 	thermal->tzdev = thermal_zone_device_register("mlxsw",
 						      MLXSW_THERMAL_NUM_TRIPS,
 						      MLXSW_THERMAL_TRIP_MASK,
-- 
cgit v1.2.3


From ebda9b46cebc9c1245fcfe96c76525717ef984cc Mon Sep 17 00:00:00 2001
From: Xue Chaojing <xuechaojing@huawei.com>
Date: Tue, 20 Nov 2018 05:47:31 +0000
Subject: net-next/hinic:replace multiply and division operators

To improve performance, this patch uses bit operations to replace
multiply and division operators.

Signed-off-by: Xue Chaojing <xuechaojing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c | 55 ++++++++++++++++---------
 drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h |  3 +-
 2 files changed, 38 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
index f92f1bf3901a..1dfa7eb05c10 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
@@ -74,12 +74,6 @@
 			((void *)((cmdq_pages)->shadow_page_vaddr) \
 				+ (wq)->block_idx * CMDQ_BLOCK_SIZE)
 
-#define WQE_PAGE_OFF(wq, idx)   (((idx) & ((wq)->num_wqebbs_per_page - 1)) * \
-					(wq)->wqebb_size)
-
-#define WQE_PAGE_NUM(wq, idx)   (((idx) / ((wq)->num_wqebbs_per_page)) \
-					& ((wq)->num_q_pages - 1))
-
 #define WQ_PAGE_ADDR(wq, idx)           \
 			((wq)->shadow_block_vaddr[WQE_PAGE_NUM(wq, idx)])
 
@@ -93,6 +87,17 @@
 		(((unsigned long)(wqe) - (unsigned long)(wq)->shadow_wqe) \
 			/ (wq)->max_wqe_size)
 
+static inline int WQE_PAGE_OFF(struct hinic_wq *wq, u16 idx)
+{
+	return (((idx) & ((wq)->num_wqebbs_per_page - 1))
+		<< (wq)->wqebb_size_shift);
+}
+
+static inline int WQE_PAGE_NUM(struct hinic_wq *wq, u16 idx)
+{
+	return (((idx) >> ((wq)->wqebbs_per_page_shift))
+		& ((wq)->num_q_pages - 1));
+}
 /**
  * queue_alloc_page - allocate page for Queue
  * @hwif: HW interface for allocating DMA
@@ -513,10 +518,11 @@ int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq,
 	struct hinic_hwif *hwif = wqs->hwif;
 	struct pci_dev *pdev = hwif->pdev;
 	u16 num_wqebbs_per_page;
+	u16 wqebb_size_shift;
 	int err;
 
-	if (wqebb_size == 0) {
-		dev_err(&pdev->dev, "wqebb_size must be > 0\n");
+	if (!is_power_of_2(wqebb_size)) {
+		dev_err(&pdev->dev, "wqebb_size must be power of 2\n");
 		return -EINVAL;
 	}
 
@@ -530,9 +536,11 @@ int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq,
 		return -EINVAL;
 	}
 
-	num_wqebbs_per_page = ALIGN(wq_page_size, wqebb_size) / wqebb_size;
+	wqebb_size_shift = ilog2(wqebb_size);
+	num_wqebbs_per_page = ALIGN(wq_page_size, wqebb_size)
+				>> wqebb_size_shift;
 
-	if (num_wqebbs_per_page & (num_wqebbs_per_page - 1)) {
+	if (!is_power_of_2(num_wqebbs_per_page)) {
 		dev_err(&pdev->dev, "num wqebbs per page must be power of 2\n");
 		return -EINVAL;
 	}
@@ -550,7 +558,8 @@ int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq,
 	wq->q_depth = q_depth;
 	wq->max_wqe_size = max_wqe_size;
 	wq->num_wqebbs_per_page = num_wqebbs_per_page;
-
+	wq->wqebbs_per_page_shift = ilog2(num_wqebbs_per_page);
+	wq->wqebb_size_shift = wqebb_size_shift;
 	wq->block_vaddr = WQ_BASE_VADDR(wqs, wq);
 	wq->shadow_block_vaddr = WQ_BASE_ADDR(wqs, wq);
 	wq->block_paddr = WQ_BASE_PADDR(wqs, wq);
@@ -604,11 +613,13 @@ int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages,
 			 u16 q_depth, u16 max_wqe_size)
 {
 	struct pci_dev *pdev = hwif->pdev;
+	u16 num_wqebbs_per_page_shift;
 	u16 num_wqebbs_per_page;
+	u16 wqebb_size_shift;
 	int i, j, err = -ENOMEM;
 
-	if (wqebb_size == 0) {
-		dev_err(&pdev->dev, "wqebb_size must be > 0\n");
+	if (!is_power_of_2(wqebb_size)) {
+		dev_err(&pdev->dev, "wqebb_size must be power of 2\n");
 		return -EINVAL;
 	}
 
@@ -622,9 +633,11 @@ int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages,
 		return -EINVAL;
 	}
 
-	num_wqebbs_per_page = ALIGN(wq_page_size, wqebb_size) / wqebb_size;
+	wqebb_size_shift = ilog2(wqebb_size);
+	num_wqebbs_per_page = ALIGN(wq_page_size, wqebb_size)
+				>> wqebb_size_shift;
 
-	if (num_wqebbs_per_page & (num_wqebbs_per_page - 1)) {
+	if (!is_power_of_2(num_wqebbs_per_page)) {
 		dev_err(&pdev->dev, "num wqebbs per page must be power of 2\n");
 		return -EINVAL;
 	}
@@ -636,6 +649,7 @@ int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages,
 		dev_err(&pdev->dev, "Failed to allocate CMDQ page\n");
 		return err;
 	}
+	num_wqebbs_per_page_shift = ilog2(num_wqebbs_per_page);
 
 	for (i = 0; i < cmdq_blocks; i++) {
 		wq[i].hwif = hwif;
@@ -647,7 +661,8 @@ int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages,
 		wq[i].q_depth = q_depth;
 		wq[i].max_wqe_size = max_wqe_size;
 		wq[i].num_wqebbs_per_page = num_wqebbs_per_page;
-
+		wq[i].wqebbs_per_page_shift = num_wqebbs_per_page_shift;
+		wq[i].wqebb_size_shift = wqebb_size_shift;
 		wq[i].block_vaddr = CMDQ_BASE_VADDR(cmdq_pages, &wq[i]);
 		wq[i].shadow_block_vaddr = CMDQ_BASE_ADDR(cmdq_pages, &wq[i]);
 		wq[i].block_paddr = CMDQ_BASE_PADDR(cmdq_pages, &wq[i]);
@@ -741,7 +756,7 @@ struct hinic_hw_wqe *hinic_get_wqe(struct hinic_wq *wq, unsigned int wqe_size,
 
 	*prod_idx = MASKED_WQE_IDX(wq, atomic_read(&wq->prod_idx));
 
-	num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size;
+	num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) >> wq->wqebb_size_shift;
 
 	if (atomic_sub_return(num_wqebbs, &wq->delta) <= 0) {
 		atomic_add(num_wqebbs, &wq->delta);
@@ -795,7 +810,8 @@ void hinic_return_wqe(struct hinic_wq *wq, unsigned int wqe_size)
  **/
 void hinic_put_wqe(struct hinic_wq *wq, unsigned int wqe_size)
 {
-	int num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size;
+	int num_wqebbs = ALIGN(wqe_size, wq->wqebb_size)
+			>> wq->wqebb_size_shift;
 
 	atomic_add(num_wqebbs, &wq->cons_idx);
 
@@ -813,7 +829,8 @@ void hinic_put_wqe(struct hinic_wq *wq, unsigned int wqe_size)
 struct hinic_hw_wqe *hinic_read_wqe(struct hinic_wq *wq, unsigned int wqe_size,
 				    u16 *cons_idx)
 {
-	int num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size;
+	int num_wqebbs = ALIGN(wqe_size, wq->wqebb_size)
+			>> wq->wqebb_size_shift;
 	u16 curr_cons_idx, end_cons_idx;
 	int curr_pg, end_pg;
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
index 9b66545ba563..0a936cd6709b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
@@ -39,7 +39,8 @@ struct hinic_wq {
 	u16             q_depth;
 	u16             max_wqe_size;
 	u16             num_wqebbs_per_page;
-
+	u16		wqebbs_per_page_shift;
+	u16		wqebb_size_shift;
 	/* The addresses are 64 bit in the HW */
 	u64             block_paddr;
 	void            **shadow_block_vaddr;
-- 
cgit v1.2.3


From 4a61abb100c8a647959147034f60e9fce17ce9af Mon Sep 17 00:00:00 2001
From: Xue Chaojing <xuechaojing@huawei.com>
Date: Tue, 20 Nov 2018 05:47:32 +0000
Subject: net-next/hinic:add rx checksum offload for HiNIC

In order to improve performance, this patch adds rx checksum offload
for the HiNIC driver. Performance test(Iperf) shows more than 80%
improvement in TCP streams.

Signed-off-by: Xue Chaojing <xuechaojing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h |  2 ++
 drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h |  4 ++++
 drivers/net/ethernet/huawei/hinic/hinic_main.c   |  7 +++++-
 drivers/net/ethernet/huawei/hinic/hinic_port.c   | 28 ++++++++++++++++++++++++
 drivers/net/ethernet/huawei/hinic/hinic_port.h   | 10 +++++++++
 drivers/net/ethernet/huawei/hinic/hinic_rx.c     | 24 ++++++++++++++++++++
 drivers/net/ethernet/huawei/hinic/hinic_rx.h     |  4 ++++
 7 files changed, 78 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index 097b5502603f..d1a7d2522d82 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -50,6 +50,8 @@ enum hinic_port_cmd {
 
 	HINIC_PORT_CMD_GET_LINK_STATE   = 24,
 
+	HINIC_PORT_CMD_SET_RX_CSUM	= 26,
+
 	HINIC_PORT_CMD_SET_PORT_STATE   = 41,
 
 	HINIC_PORT_CMD_FWCTXT_INIT      = 69,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h
index 9754d6ed5f4a..138941527872 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h
@@ -170,6 +170,10 @@
 
 #define HINIC_RQ_CQE_STATUS_RXDONE_MASK         0x1
 
+#define HINIC_RQ_CQE_STATUS_CSUM_ERR_SHIFT	0
+
+#define HINIC_RQ_CQE_STATUS_CSUM_ERR_MASK	0xFFFFU
+
 #define HINIC_RQ_CQE_STATUS_GET(val, member)    \
 		(((val) >> HINIC_RQ_CQE_STATUS_##member##_SHIFT) & \
 		 HINIC_RQ_CQE_STATUS_##member##_MASK)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index fdf2bdb6b0d0..c675077f9774 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -806,7 +806,8 @@ static const struct net_device_ops hinic_netdev_ops = {
 static void netdev_features_init(struct net_device *netdev)
 {
 	netdev->hw_features = NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_IP_CSUM |
-			      NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
+			      NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+			      NETIF_F_RXCSUM;
 
 	netdev->vlan_features = netdev->hw_features;
 
@@ -869,12 +870,16 @@ static int set_features(struct hinic_dev *nic_dev,
 			netdev_features_t features, bool force_change)
 {
 	netdev_features_t changed = force_change ? ~0 : pre_features ^ features;
+	u32 csum_en = HINIC_RX_CSUM_OFFLOAD_EN;
 	int err = 0;
 
 	if (changed & NETIF_F_TSO)
 		err = hinic_port_set_tso(nic_dev, (features & NETIF_F_TSO) ?
 					 HINIC_TSO_ENABLE : HINIC_TSO_DISABLE);
 
+	if (changed & NETIF_F_RXCSUM)
+		err = hinic_set_rx_csum_offload(nic_dev, csum_en);
+
 	return err;
 }
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index 7575a7d3bd9f..e9f76e904610 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -409,3 +409,31 @@ int hinic_port_set_tso(struct hinic_dev *nic_dev, enum hinic_tso_state state)
 
 	return 0;
 }
+
+int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en)
+{
+	struct hinic_checksum_offload rx_csum_cfg = {0};
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct pci_dev *pdev = hwif->pdev;
+	u16 out_size;
+	int err;
+
+	if (!hwdev)
+		return -EINVAL;
+
+	rx_csum_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	rx_csum_cfg.rx_csum_offload = en;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_RX_CSUM,
+				 &rx_csum_cfg, sizeof(rx_csum_cfg),
+				 &rx_csum_cfg, &out_size);
+	if (err || !out_size || rx_csum_cfg.status) {
+		dev_err(&pdev->dev,
+			"Failed to set rx csum offload, ret = %d\n",
+			rx_csum_cfg.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h
index f6e3220fe28f..02d896eed455 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h
@@ -183,6 +183,15 @@ struct hinic_tso_config {
 	u8	resv2[3];
 };
 
+struct hinic_checksum_offload {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	rsvd1;
+	u32	rx_csum_offload;
+};
 int hinic_port_add_mac(struct hinic_dev *nic_dev, const u8 *addr,
 		       u16 vlan_id);
 
@@ -213,4 +222,5 @@ int hinic_port_get_cap(struct hinic_dev *nic_dev,
 
 int hinic_port_set_tso(struct hinic_dev *nic_dev, enum hinic_tso_state state);
 
+int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en);
 #endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index 4c0f7eda1166..93e8f207f6da 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -89,6 +89,28 @@ static void rxq_stats_init(struct hinic_rxq *rxq)
 	hinic_rxq_clean_stats(rxq);
 }
 
+static void rx_csum(struct hinic_rxq *rxq, u16 cons_idx,
+		    struct sk_buff *skb)
+{
+	struct net_device *netdev = rxq->netdev;
+	struct hinic_rq_cqe *cqe;
+	struct hinic_rq *rq;
+	u32 csum_err;
+	u32 status;
+
+	rq = rxq->rq;
+	cqe = rq->cqe[cons_idx];
+	status = be32_to_cpu(cqe->status);
+	csum_err = HINIC_RQ_CQE_STATUS_GET(status, CSUM_ERR);
+
+	if (!(netdev->features & NETIF_F_RXCSUM))
+		return;
+
+	if (!csum_err)
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	else
+		skb->ip_summed = CHECKSUM_NONE;
+}
 /**
  * rx_alloc_skb - allocate skb and map it to dma address
  * @rxq: rx queue
@@ -328,6 +350,8 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 
 		rx_unmap_skb(rxq, hinic_sge_to_dma(&sge));
 
+		rx_csum(rxq, ci, skb);
+
 		prefetch(skb->data);
 
 		pkt_len = sge.len;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.h b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
index 27c9af4b1c12..ab3fabab91b2 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
@@ -23,6 +23,10 @@
 
 #include "hinic_hw_qp.h"
 
+#define HINIC_RX_CSUM_OFFLOAD_EN	0xFFF
+#define HINIC_RX_CSUM_HW_CHECK_NONE	BIT(7)
+#define HINIC_RX_CSUM_IPSU_OTHER_ERR	BIT(8)
+
 struct hinic_rxq_stats {
 	u64                     pkts;
 	u64                     bytes;
-- 
cgit v1.2.3


From 9ea72dc9430306b77c73a8a21beb51437cde1d6d Mon Sep 17 00:00:00 2001
From: Xue Chaojing <xuechaojing@huawei.com>
Date: Tue, 20 Nov 2018 05:47:33 +0000
Subject: net-next/hinic:fix a bug in set mac address

In add_mac_addr(), if the MAC address is a muliticast address,
it will not be set, which causes the network card fail to receive
the multicast packet. This patch fixes this bug.

Signed-off-by: Xue Chaojing <xuechaojing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_main.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index c675077f9774..6d48dc62a44b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -600,9 +600,6 @@ static int add_mac_addr(struct net_device *netdev, const u8 *addr)
 	u16 vid = 0;
 	int err;
 
-	if (!is_valid_ether_addr(addr))
-		return -EADDRNOTAVAIL;
-
 	netif_info(nic_dev, drv, netdev, "set mac addr = %02x %02x %02x %02x %02x %02x\n",
 		   addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]);
 
@@ -726,6 +723,7 @@ static void set_rx_mode(struct work_struct *work)
 {
 	struct hinic_rx_mode_work *rx_mode_work = work_to_rx_mode_work(work);
 	struct hinic_dev *nic_dev = rx_mode_work_to_nic_dev(rx_mode_work);
+	struct netdev_hw_addr *ha;
 
 	netif_info(nic_dev, drv, nic_dev->netdev, "set rx mode work\n");
 
@@ -733,6 +731,9 @@ static void set_rx_mode(struct work_struct *work)
 
 	__dev_uc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr);
 	__dev_mc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr);
+
+	netdev_for_each_mc_addr(ha, nic_dev->netdev)
+		add_mac_addr(nic_dev->netdev, ha->addr);
 }
 
 static void hinic_set_rx_mode(struct net_device *netdev)
-- 
cgit v1.2.3


From b1a200484143a727ce293e0f200a543cc7584152 Mon Sep 17 00:00:00 2001
From: Xue Chaojing <xuechaojing@huawei.com>
Date: Tue, 20 Nov 2018 05:47:34 +0000
Subject: net-next/hinic: fix a bug in rx data flow

In rx_alloc_pkts(), there is a loop call of tasklet, which causes
100% cpu utilization, even no packets are being received. This patch
fixes this bug.

Signed-off-by: Xue Chaojing <xuechaojing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index 93e8f207f6da..f86f2e693224 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -229,9 +229,9 @@ skb_out:
 		wmb();  /* write all the wqes before update PI */
 
 		hinic_rq_update(rxq->rq, prod_idx);
+		tasklet_schedule(&rxq->rx_task);
 	}
 
-	tasklet_schedule(&rxq->rx_task);
 	return i;
 }
 
-- 
cgit v1.2.3


From b47a0bd23e34022aa0d4b812fcebe85cb0c54d49 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 19 Nov 2018 15:29:06 -0800
Subject: bpf: btf: Break up btf_type_is_void()

This patch breaks up btf_type_is_void() into
btf_type_is_void() and btf_type_is_fwd().

It also adds btf_type_nosize() to better describe it is
testing a type has nosize info.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c | 37 ++++++++++++++++++++++---------------
 1 file changed, 22 insertions(+), 15 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index ee4c82667d65..2a50d87de485 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -306,15 +306,22 @@ static bool btf_type_is_modifier(const struct btf_type *t)
 
 static bool btf_type_is_void(const struct btf_type *t)
 {
-	/* void => no type and size info.
-	 * Hence, FWD is also treated as void.
-	 */
-	return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
+	return t == &btf_void;
+}
+
+static bool btf_type_is_fwd(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
+}
+
+static bool btf_type_nosize(const struct btf_type *t)
+{
+	return btf_type_is_void(t) || btf_type_is_fwd(t);
 }
 
-static bool btf_type_is_void_or_null(const struct btf_type *t)
+static bool btf_type_nosize_or_null(const struct btf_type *t)
 {
-	return !t || btf_type_is_void(t);
+	return !t || btf_type_nosize(t);
 }
 
 /* union is only a special case of struct:
@@ -826,7 +833,7 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
 	u32 size = 0;
 
 	size_type = btf_type_by_id(btf, size_type_id);
-	if (btf_type_is_void_or_null(size_type))
+	if (btf_type_nosize_or_null(size_type))
 		return NULL;
 
 	if (btf_type_has_size(size_type)) {
@@ -842,7 +849,7 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
 		size = btf->resolved_sizes[size_type_id];
 		size_type_id = btf->resolved_ids[size_type_id];
 		size_type = btf_type_by_id(btf, size_type_id);
-		if (btf_type_is_void(size_type))
+		if (btf_type_nosize_or_null(size_type))
 			return NULL;
 	}
 
@@ -1164,7 +1171,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 	}
 
 	/* "typedef void new_void", "const void"...etc */
-	if (btf_type_is_void(next_type))
+	if (btf_type_is_void(next_type) || btf_type_is_fwd(next_type))
 		goto resolved;
 
 	if (!env_type_is_resolve_sink(env, next_type) &&
@@ -1178,7 +1185,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 	 * pretty print).
 	 */
 	if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
-	    !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) {
+	    !btf_type_nosize(btf_type_id_resolve(btf, &next_type_id))) {
 		btf_verifier_log_type(env, v->t, "Invalid type_id");
 		return -EINVAL;
 	}
@@ -1205,7 +1212,7 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 	}
 
 	/* "void *" */
-	if (btf_type_is_void(next_type))
+	if (btf_type_is_void(next_type) || btf_type_is_fwd(next_type))
 		goto resolved;
 
 	if (!env_type_is_resolve_sink(env, next_type) &&
@@ -1235,7 +1242,7 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 	}
 
 	if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
-	    !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) {
+	    !btf_type_nosize(btf_type_id_resolve(btf, &next_type_id))) {
 		btf_verifier_log_type(env, v->t, "Invalid type_id");
 		return -EINVAL;
 	}
@@ -1396,7 +1403,7 @@ static int btf_array_resolve(struct btf_verifier_env *env,
 	/* Check array->index_type */
 	index_type_id = array->index_type;
 	index_type = btf_type_by_id(btf, index_type_id);
-	if (btf_type_is_void_or_null(index_type)) {
+	if (btf_type_nosize_or_null(index_type)) {
 		btf_verifier_log_type(env, v->t, "Invalid index");
 		return -EINVAL;
 	}
@@ -1415,7 +1422,7 @@ static int btf_array_resolve(struct btf_verifier_env *env,
 	/* Check array->type */
 	elem_type_id = array->type;
 	elem_type = btf_type_by_id(btf, elem_type_id);
-	if (btf_type_is_void_or_null(elem_type)) {
+	if (btf_type_nosize_or_null(elem_type)) {
 		btf_verifier_log_type(env, v->t,
 				      "Invalid elem");
 		return -EINVAL;
@@ -1615,7 +1622,7 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
 		const struct btf_type *member_type = btf_type_by_id(env->btf,
 								member_type_id);
 
-		if (btf_type_is_void_or_null(member_type)) {
+		if (btf_type_nosize_or_null(member_type)) {
 			btf_verifier_log_member(env, v->t, member,
 						"Invalid member");
 			return -EINVAL;
-- 
cgit v1.2.3


From 2667a2626f4da370409c2830552f6e8c8b8c41e2 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 19 Nov 2018 15:29:08 -0800
Subject: bpf: btf: Add BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO

This patch adds BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO
to support the function debug info.

BTF_KIND_FUNC_PROTO must not have a name (i.e. !t->name_off)
and it is followed by >= 0 'struct bpf_param' objects to
describe the function arguments.

The BTF_KIND_FUNC must have a valid name and it must
refer back to a BTF_KIND_FUNC_PROTO.

The above is the conclusion after the discussion between
Edward Cree, Alexei, Daniel, Yonghong and Martin.

By combining BTF_KIND_FUNC and BTF_LIND_FUNC_PROTO,
a complete function signature can be obtained.  It will be
used in the later patches to learn the function signature of
a running bpf program.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/btf.h |  18 ++-
 kernel/bpf/btf.c         | 389 +++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 354 insertions(+), 53 deletions(-)

diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
index 972265f32871..14f66948fc95 100644
--- a/include/uapi/linux/btf.h
+++ b/include/uapi/linux/btf.h
@@ -40,7 +40,8 @@ struct btf_type {
 	/* "size" is used by INT, ENUM, STRUCT and UNION.
 	 * "size" tells the size of the type it is describing.
 	 *
-	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
+	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
+	 * FUNC and FUNC_PROTO.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -64,8 +65,10 @@ struct btf_type {
 #define BTF_KIND_VOLATILE	9	/* Volatile	*/
 #define BTF_KIND_CONST		10	/* Const	*/
 #define BTF_KIND_RESTRICT	11	/* Restrict	*/
-#define BTF_KIND_MAX		11
-#define NR_BTF_KINDS		12
+#define BTF_KIND_FUNC		12	/* Function	*/
+#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
+#define BTF_KIND_MAX		13
+#define NR_BTF_KINDS		14
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -110,4 +113,13 @@ struct btf_member {
 	__u32	offset;	/* offset in bits */
 };
 
+/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
+ * The exact number of btf_param is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_param {
+	__u32	name_off;
+	__u32	type;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2a50d87de485..6a2be79b73fc 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5,6 +5,7 @@
 #include <uapi/linux/types.h>
 #include <linux/seq_file.h>
 #include <linux/compiler.h>
+#include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/anon_inodes.h>
@@ -259,6 +260,8 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_VOLATILE]	= "VOLATILE",
 	[BTF_KIND_CONST]	= "CONST",
 	[BTF_KIND_RESTRICT]	= "RESTRICT",
+	[BTF_KIND_FUNC]		= "FUNC",
+	[BTF_KIND_FUNC_PROTO]	= "FUNC_PROTO",
 };
 
 struct btf_kind_operations {
@@ -281,6 +284,9 @@ struct btf_kind_operations {
 static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS];
 static struct btf_type btf_void;
 
+static int btf_resolve(struct btf_verifier_env *env,
+		       const struct btf_type *t, u32 type_id);
+
 static bool btf_type_is_modifier(const struct btf_type *t)
 {
 	/* Some of them is not strictly a C modifier
@@ -314,9 +320,20 @@ static bool btf_type_is_fwd(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
 }
 
+static bool btf_type_is_func(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC;
+}
+
+static bool btf_type_is_func_proto(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO;
+}
+
 static bool btf_type_nosize(const struct btf_type *t)
 {
-	return btf_type_is_void(t) || btf_type_is_fwd(t);
+	return btf_type_is_void(t) || btf_type_is_fwd(t) ||
+	       btf_type_is_func(t) || btf_type_is_func_proto(t);
 }
 
 static bool btf_type_nosize_or_null(const struct btf_type *t)
@@ -433,6 +450,30 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
 		offset < btf->hdr.str_len;
 }
 
+/* Only C-style identifier is permitted. This can be relaxed if
+ * necessary.
+ */
+static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
+{
+	/* offset must be valid */
+	const char *src = &btf->strings[offset];
+	const char *src_limit;
+
+	if (!isalpha(*src) && *src != '_')
+		return false;
+
+	/* set a limit on identifier length */
+	src_limit = src + KSYM_NAME_LEN;
+	src++;
+	while (*src && src < src_limit) {
+		if (!isalnum(*src) && *src != '_')
+			return false;
+		src++;
+	}
+
+	return !*src;
+}
+
 static const char *btf_name_by_offset(const struct btf *btf, u32 offset)
 {
 	if (!offset)
@@ -747,11 +788,15 @@ static bool env_type_is_resolve_sink(const struct btf_verifier_env *env,
 		/* int, enum or void is a sink */
 		return !btf_type_needs_resolve(next_type);
 	case RESOLVE_PTR:
-		/* int, enum, void, struct or array is a sink for ptr */
+		/* int, enum, void, struct, array, func or func_proto is a sink
+		 * for ptr
+		 */
 		return !btf_type_is_modifier(next_type) &&
 			!btf_type_is_ptr(next_type);
 	case RESOLVE_STRUCT_OR_ARRAY:
-		/* int, enum, void or ptr is a sink for struct and array */
+		/* int, enum, void, ptr, func or func_proto is a sink
+		 * for struct and array
+		 */
 		return !btf_type_is_modifier(next_type) &&
 			!btf_type_is_array(next_type) &&
 			!btf_type_is_struct(next_type);
@@ -1170,10 +1215,6 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	/* "typedef void new_void", "const void"...etc */
-	if (btf_type_is_void(next_type) || btf_type_is_fwd(next_type))
-		goto resolved;
-
 	if (!env_type_is_resolve_sink(env, next_type) &&
 	    !env_type_is_resolved(env, next_type_id))
 		return env_stack_push(env, next_type, next_type_id);
@@ -1184,13 +1225,18 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 	 * save us a few type-following when we use it later (e.g. in
 	 * pretty print).
 	 */
-	if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
-	    !btf_type_nosize(btf_type_id_resolve(btf, &next_type_id))) {
-		btf_verifier_log_type(env, v->t, "Invalid type_id");
-		return -EINVAL;
+	if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) {
+		if (env_type_is_resolved(env, next_type_id))
+			next_type = btf_type_id_resolve(btf, &next_type_id);
+
+		/* "typedef void new_void", "const void"...etc */
+		if (!btf_type_is_void(next_type) &&
+		    !btf_type_is_fwd(next_type)) {
+			btf_verifier_log_type(env, v->t, "Invalid type_id");
+			return -EINVAL;
+		}
 	}
 
-resolved:
 	env_stack_pop_resolved(env, next_type_id, next_type_size);
 
 	return 0;
@@ -1203,7 +1249,6 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 	const struct btf_type *t = v->t;
 	u32 next_type_id = t->type;
 	struct btf *btf = env->btf;
-	u32 next_type_size = 0;
 
 	next_type = btf_type_by_id(btf, next_type_id);
 	if (!next_type) {
@@ -1211,10 +1256,6 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	/* "void *" */
-	if (btf_type_is_void(next_type) || btf_type_is_fwd(next_type))
-		goto resolved;
-
 	if (!env_type_is_resolve_sink(env, next_type) &&
 	    !env_type_is_resolved(env, next_type_id))
 		return env_stack_push(env, next_type, next_type_id);
@@ -1241,13 +1282,18 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 					      resolved_type_id);
 	}
 
-	if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
-	    !btf_type_nosize(btf_type_id_resolve(btf, &next_type_id))) {
-		btf_verifier_log_type(env, v->t, "Invalid type_id");
-		return -EINVAL;
+	if (!btf_type_id_size(btf, &next_type_id, NULL)) {
+		if (env_type_is_resolved(env, next_type_id))
+			next_type = btf_type_id_resolve(btf, &next_type_id);
+
+		if (!btf_type_is_void(next_type) &&
+		    !btf_type_is_fwd(next_type) &&
+		    !btf_type_is_func_proto(next_type)) {
+			btf_verifier_log_type(env, v->t, "Invalid type_id");
+			return -EINVAL;
+		}
 	}
 
-resolved:
 	env_stack_pop_resolved(env, next_type_id, 0);
 
 	return 0;
@@ -1787,6 +1833,232 @@ static struct btf_kind_operations enum_ops = {
 	.seq_show = btf_enum_seq_show,
 };
 
+static s32 btf_func_proto_check_meta(struct btf_verifier_env *env,
+				     const struct btf_type *t,
+				     u32 meta_left)
+{
+	u32 meta_needed = btf_type_vlen(t) * sizeof(struct btf_param);
+
+	if (meta_left < meta_needed) {
+		btf_verifier_log_basic(env, t,
+				       "meta_left:%u meta_needed:%u",
+				       meta_left, meta_needed);
+		return -EINVAL;
+	}
+
+	if (t->name_off) {
+		btf_verifier_log_type(env, t, "Invalid name");
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	return meta_needed;
+}
+
+static void btf_func_proto_log(struct btf_verifier_env *env,
+			       const struct btf_type *t)
+{
+	const struct btf_param *args = (const struct btf_param *)(t + 1);
+	u16 nr_args = btf_type_vlen(t), i;
+
+	btf_verifier_log(env, "return=%u args=(", t->type);
+	if (!nr_args) {
+		btf_verifier_log(env, "void");
+		goto done;
+	}
+
+	if (nr_args == 1 && !args[0].type) {
+		/* Only one vararg */
+		btf_verifier_log(env, "vararg");
+		goto done;
+	}
+
+	btf_verifier_log(env, "%u %s", args[0].type,
+			 btf_name_by_offset(env->btf,
+					    args[0].name_off));
+	for (i = 1; i < nr_args - 1; i++)
+		btf_verifier_log(env, ", %u %s", args[i].type,
+				 btf_name_by_offset(env->btf,
+						    args[i].name_off));
+
+	if (nr_args > 1) {
+		const struct btf_param *last_arg = &args[nr_args - 1];
+
+		if (last_arg->type)
+			btf_verifier_log(env, ", %u %s", last_arg->type,
+					 btf_name_by_offset(env->btf,
+							    last_arg->name_off));
+		else
+			btf_verifier_log(env, ", vararg");
+	}
+
+done:
+	btf_verifier_log(env, ")");
+}
+
+static struct btf_kind_operations func_proto_ops = {
+	.check_meta = btf_func_proto_check_meta,
+	.resolve = btf_df_resolve,
+	/*
+	 * BTF_KIND_FUNC_PROTO cannot be directly referred by
+	 * a struct's member.
+	 *
+	 * It should be a funciton pointer instead.
+	 * (i.e. struct's member -> BTF_KIND_PTR -> BTF_KIND_FUNC_PROTO)
+	 *
+	 * Hence, there is no btf_func_check_member().
+	 */
+	.check_member = btf_df_check_member,
+	.log_details = btf_func_proto_log,
+	.seq_show = btf_df_seq_show,
+};
+
+static s32 btf_func_check_meta(struct btf_verifier_env *env,
+			       const struct btf_type *t,
+			       u32 meta_left)
+{
+	if (!t->name_off ||
+	    !btf_name_valid_identifier(env->btf, t->name_off)) {
+		btf_verifier_log_type(env, t, "Invalid name");
+		return -EINVAL;
+	}
+
+	if (btf_type_vlen(t)) {
+		btf_verifier_log_type(env, t, "vlen != 0");
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	return 0;
+}
+
+static struct btf_kind_operations func_ops = {
+	.check_meta = btf_func_check_meta,
+	.resolve = btf_df_resolve,
+	.check_member = btf_df_check_member,
+	.log_details = btf_ref_type_log,
+	.seq_show = btf_df_seq_show,
+};
+
+static int btf_func_proto_check(struct btf_verifier_env *env,
+				const struct btf_type *t)
+{
+	const struct btf_type *ret_type;
+	const struct btf_param *args;
+	const struct btf *btf;
+	u16 nr_args, i;
+	int err;
+
+	btf = env->btf;
+	args = (const struct btf_param *)(t + 1);
+	nr_args = btf_type_vlen(t);
+
+	/* Check func return type which could be "void" (t->type == 0) */
+	if (t->type) {
+		u32 ret_type_id = t->type;
+
+		ret_type = btf_type_by_id(btf, ret_type_id);
+		if (!ret_type) {
+			btf_verifier_log_type(env, t, "Invalid return type");
+			return -EINVAL;
+		}
+
+		if (btf_type_needs_resolve(ret_type) &&
+		    !env_type_is_resolved(env, ret_type_id)) {
+			err = btf_resolve(env, ret_type, ret_type_id);
+			if (err)
+				return err;
+		}
+
+		/* Ensure the return type is a type that has a size */
+		if (!btf_type_id_size(btf, &ret_type_id, NULL)) {
+			btf_verifier_log_type(env, t, "Invalid return type");
+			return -EINVAL;
+		}
+	}
+
+	if (!nr_args)
+		return 0;
+
+	/* Last func arg type_id could be 0 if it is a vararg */
+	if (!args[nr_args - 1].type) {
+		if (args[nr_args - 1].name_off) {
+			btf_verifier_log_type(env, t, "Invalid arg#%u",
+					      nr_args);
+			return -EINVAL;
+		}
+		nr_args--;
+	}
+
+	err = 0;
+	for (i = 0; i < nr_args; i++) {
+		const struct btf_type *arg_type;
+		u32 arg_type_id;
+
+		arg_type_id = args[i].type;
+		arg_type = btf_type_by_id(btf, arg_type_id);
+		if (!arg_type) {
+			btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1);
+			err = -EINVAL;
+			break;
+		}
+
+		if (args[i].name_off &&
+		    (!btf_name_offset_valid(btf, args[i].name_off) ||
+		     !btf_name_valid_identifier(btf, args[i].name_off))) {
+			btf_verifier_log_type(env, t,
+					      "Invalid arg#%u", i + 1);
+			err = -EINVAL;
+			break;
+		}
+
+		if (btf_type_needs_resolve(arg_type) &&
+		    !env_type_is_resolved(env, arg_type_id)) {
+			err = btf_resolve(env, arg_type, arg_type_id);
+			if (err)
+				break;
+		}
+
+		if (!btf_type_id_size(btf, &arg_type_id, NULL)) {
+			btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1);
+			err = -EINVAL;
+			break;
+		}
+	}
+
+	return err;
+}
+
+static int btf_func_check(struct btf_verifier_env *env,
+			  const struct btf_type *t)
+{
+	const struct btf_type *proto_type;
+	const struct btf_param *args;
+	const struct btf *btf;
+	u16 nr_args, i;
+
+	btf = env->btf;
+	proto_type = btf_type_by_id(btf, t->type);
+
+	if (!proto_type || !btf_type_is_func_proto(proto_type)) {
+		btf_verifier_log_type(env, t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+	args = (const struct btf_param *)(proto_type + 1);
+	nr_args = btf_type_vlen(proto_type);
+	for (i = 0; i < nr_args; i++) {
+		if (!args[i].name_off && args[i].type) {
+			btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
 	[BTF_KIND_INT] = &int_ops,
 	[BTF_KIND_PTR] = &ptr_ops,
@@ -1799,6 +2071,8 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
 	[BTF_KIND_VOLATILE] = &modifier_ops,
 	[BTF_KIND_CONST] = &modifier_ops,
 	[BTF_KIND_RESTRICT] = &modifier_ops,
+	[BTF_KIND_FUNC] = &func_ops,
+	[BTF_KIND_FUNC_PROTO] = &func_proto_ops,
 };
 
 static s32 btf_check_meta(struct btf_verifier_env *env,
@@ -1870,30 +2144,6 @@ static int btf_check_all_metas(struct btf_verifier_env *env)
 	return 0;
 }
 
-static int btf_resolve(struct btf_verifier_env *env,
-		       const struct btf_type *t, u32 type_id)
-{
-	const struct resolve_vertex *v;
-	int err = 0;
-
-	env->resolve_mode = RESOLVE_TBD;
-	env_stack_push(env, t, type_id);
-	while (!err && (v = env_stack_peak(env))) {
-		env->log_type_id = v->type_id;
-		err = btf_type_ops(v->t)->resolve(env, v);
-	}
-
-	env->log_type_id = type_id;
-	if (err == -E2BIG)
-		btf_verifier_log_type(env, t,
-				      "Exceeded max resolving depth:%u",
-				      MAX_RESOLVE_DEPTH);
-	else if (err == -EEXIST)
-		btf_verifier_log_type(env, t, "Loop detected");
-
-	return err;
-}
-
 static bool btf_resolve_valid(struct btf_verifier_env *env,
 			      const struct btf_type *t,
 			      u32 type_id)
@@ -1927,6 +2177,39 @@ static bool btf_resolve_valid(struct btf_verifier_env *env,
 	return false;
 }
 
+static int btf_resolve(struct btf_verifier_env *env,
+		       const struct btf_type *t, u32 type_id)
+{
+	u32 save_log_type_id = env->log_type_id;
+	const struct resolve_vertex *v;
+	int err = 0;
+
+	env->resolve_mode = RESOLVE_TBD;
+	env_stack_push(env, t, type_id);
+	while (!err && (v = env_stack_peak(env))) {
+		env->log_type_id = v->type_id;
+		err = btf_type_ops(v->t)->resolve(env, v);
+	}
+
+	env->log_type_id = type_id;
+	if (err == -E2BIG) {
+		btf_verifier_log_type(env, t,
+				      "Exceeded max resolving depth:%u",
+				      MAX_RESOLVE_DEPTH);
+	} else if (err == -EEXIST) {
+		btf_verifier_log_type(env, t, "Loop detected");
+	}
+
+	/* Final sanity check */
+	if (!err && !btf_resolve_valid(env, t, type_id)) {
+		btf_verifier_log_type(env, t, "Invalid resolve state");
+		err = -EINVAL;
+	}
+
+	env->log_type_id = save_log_type_id;
+	return err;
+}
+
 static int btf_check_all_types(struct btf_verifier_env *env)
 {
 	struct btf *btf = env->btf;
@@ -1949,10 +2232,16 @@ static int btf_check_all_types(struct btf_verifier_env *env)
 				return err;
 		}
 
-		if (btf_type_needs_resolve(t) &&
-		    !btf_resolve_valid(env, t, type_id)) {
-			btf_verifier_log_type(env, t, "Invalid resolve state");
-			return -EINVAL;
+		if (btf_type_is_func_proto(t)) {
+			err = btf_func_proto_check(env, t);
+			if (err)
+				return err;
+		}
+
+		if (btf_type_is_func(t)) {
+			err = btf_func_check(env, t);
+			if (err)
+				return err;
 		}
 	}
 
-- 
cgit v1.2.3


From 781e775e296ce3aabe0a4a0f773dccda02267695 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 19 Nov 2018 15:29:09 -0800
Subject: tools/bpf: Sync kernel btf.h header

The kernel uapi btf.h is synced to the tools directory.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/btf.h | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 972265f32871..14f66948fc95 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -40,7 +40,8 @@ struct btf_type {
 	/* "size" is used by INT, ENUM, STRUCT and UNION.
 	 * "size" tells the size of the type it is describing.
 	 *
-	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
+	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
+	 * FUNC and FUNC_PROTO.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -64,8 +65,10 @@ struct btf_type {
 #define BTF_KIND_VOLATILE	9	/* Volatile	*/
 #define BTF_KIND_CONST		10	/* Const	*/
 #define BTF_KIND_RESTRICT	11	/* Restrict	*/
-#define BTF_KIND_MAX		11
-#define NR_BTF_KINDS		12
+#define BTF_KIND_FUNC		12	/* Function	*/
+#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
+#define BTF_KIND_MAX		13
+#define NR_BTF_KINDS		14
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -110,4 +113,13 @@ struct btf_member {
 	__u32	offset;	/* offset in bits */
 };
 
+/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
+ * The exact number of btf_param is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_param {
+	__u32	name_off;
+	__u32	type;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */
-- 
cgit v1.2.3


From 78a2540e8945678b390a5f41eb82459bc6f0f36c Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 19 Nov 2018 15:29:10 -0800
Subject: tools/bpf: Add tests for BTF_KIND_FUNC_PROTO and BTF_KIND_FUNC

This patch adds unit tests for BTF_KIND_FUNC_PROTO and
BTF_KIND_FUNC to test_btf.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/btf.c                    |   4 +
 tools/testing/selftests/bpf/test_btf.c | 474 ++++++++++++++++++++++++++++++++-
 2 files changed, 476 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 449591aa9900..31225e64766f 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -165,6 +165,10 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
 		case BTF_KIND_ENUM:
 			next_type += vlen * sizeof(struct btf_enum);
 			break;
+		case BTF_KIND_FUNC_PROTO:
+			next_type += vlen * sizeof(struct btf_param);
+			break;
+		case BTF_KIND_FUNC:
 		case BTF_KIND_TYPEDEF:
 		case BTF_KIND_PTR:
 		case BTF_KIND_FWD:
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index f42b3396d622..e0eeee5c8c04 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -85,8 +85,20 @@ static int __base_pr(const char *format, ...)
 #define BTF_TYPEDEF_ENC(name, type) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type)
 
-#define BTF_PTR_ENC(name, type) \
-	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type)
+#define BTF_PTR_ENC(type) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type)
+
+#define BTF_CONST_ENC(type) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type)
+
+#define BTF_FUNC_PROTO_ENC(ret_type, nargs) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type)
+
+#define BTF_FUNC_PROTO_ARG_ENC(name, type) \
+	(name), (type)
+
+#define BTF_FUNC_ENC(name, func_proto) \
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), func_proto)
 
 #define BTF_END_RAW 0xdeadbeef
 #define NAME_TBD 0xdeadb33f
@@ -1374,6 +1386,464 @@ static struct btf_raw_test raw_tests[] = {
 	.map_create_err = true,
 },
 
+{
+	.descr = "func proto (int (*)(int, unsigned int))",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* int (*)(int, unsigned int) */
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func proto (vararg)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int, unsigned int, ...) */
+		BTF_FUNC_PROTO_ENC(0, 3),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+			BTF_FUNC_PROTO_ARG_ENC(0, 0),
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func proto (vararg with name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int b, ... c) */
+		BTF_FUNC_PROTO_ENC(0, 3),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 0),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b\0c",
+	.str_sec_size = sizeof("\0a\0b\0c"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#3",
+},
+
+{
+	.descr = "func proto (arg after vararg)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, ..., unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 3),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 0),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b",
+	.str_sec_size = sizeof("\0a\0b"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#2",
+},
+
+{
+	.descr = "func proto (CONST=>TYPEDEF=>PTR=>FUNC_PROTO)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* typedef void (*func_ptr)(int, unsigned int) */
+		BTF_TYPEDEF_ENC(NAME_TBD, 5),			/* [3] */
+		/* const func_ptr */
+		BTF_CONST_ENC(3),				/* [4] */
+		BTF_PTR_ENC(6),					/* [5] */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [6] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0func_ptr",
+	.str_sec_size = sizeof("\0func_ptr"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func proto (CONST=>TYPEDEF=>FUNC_PROTO)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		BTF_CONST_ENC(4),				/* [3] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 5),			/* [4] */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [5] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0func_typedef",
+	.str_sec_size = sizeof("\0func_typedef"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid type_id",
+},
+
+{
+	.descr = "func proto (btf_resolve(arg))",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* void (*)(const void *) */
+		BTF_FUNC_PROTO_ENC(0, 1),			/* [2] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 3),
+		BTF_CONST_ENC(4),				/* [3] */
+		BTF_PTR_ENC(0),					/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func proto (Not all arg has name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int, unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0b",
+	.str_sec_size = sizeof("\0b"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func proto (Bad arg name_off)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int <bad_name_off>) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0xffffffff, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a",
+	.str_sec_size = sizeof("\0a"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#2",
+},
+
+{
+	.descr = "func proto (Bad arg name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int !!!) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0!!!",
+	.str_sec_size = sizeof("\0a\0!!!"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#2",
+},
+
+{
+	.descr = "func proto (Invalid return type)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* <bad_ret_type> (*)(int, unsigned int) */
+		BTF_FUNC_PROTO_ENC(100, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid return type",
+},
+
+{
+	.descr = "func proto (with func name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void func_proto(int, unsigned int) */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 2), 0),	/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0func_proto",
+	.str_sec_size = sizeof("\0func_proto"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid name",
+},
+
+{
+	.descr = "func proto (const void arg)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(const void) */
+		BTF_FUNC_PROTO_ENC(0, 1),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 4),
+		BTF_CONST_ENC(0),				/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#1",
+},
+
+{
+	.descr = "func (void func(int a, unsigned int b))",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		/* void func(int a, unsigned int b) */
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b\0func",
+	.str_sec_size = sizeof("\0a\0b\0func"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func (No func name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		/* void <no_name>(int a, unsigned int b) */
+		BTF_FUNC_ENC(0, 3),				/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b",
+	.str_sec_size = sizeof("\0a\0b"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid name",
+},
+
+{
+	.descr = "func (Invalid func name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		/* void !!!(int a, unsigned int b) */
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b\0!!!",
+	.str_sec_size = sizeof("\0a\0b\0!!!"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid name",
+},
+
+{
+	.descr = "func (Some arg has no name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		/* void func(int a, unsigned int) */
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0func",
+	.str_sec_size = sizeof("\0a\0func"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#2",
+},
+
+{
+	.descr = "func (Non zero vlen)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		/* void func(int a, unsigned int b) */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 2), 3), 	/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b\0func",
+	.str_sec_size = sizeof("\0a\0b\0func"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "vlen != 0",
+},
+
+{
+	.descr = "func (Not referring to FUNC_PROTO)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_FUNC_ENC(NAME_TBD, 1),			/* [2] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0func",
+	.str_sec_size = sizeof("\0func"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid type_id",
+},
+
 }; /* struct btf_raw_test raw_tests[] */
 
 static const char *get_next_str(const char *start, const char *end)
-- 
cgit v1.2.3


From 838e96904ff3fc6c30e5ebbc611474669856e3c0 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 19 Nov 2018 15:29:11 -0800
Subject: bpf: Introduce bpf_func_info

This patch added interface to load a program with the following
additional information:
   . prog_btf_fd
   . func_info, func_info_rec_size and func_info_cnt
where func_info will provide function range and type_id
corresponding to each function.

The func_info_rec_size is introduced in the UAPI to specify
struct bpf_func_info size passed from user space. This
intends to make bpf_func_info structure growable in the future.
If the kernel gets a different bpf_func_info size from userspace,
it will try to handle user request with part of bpf_func_info
it can understand. In this patch, kernel can understand
  struct bpf_func_info {
       __u32   insn_offset;
       __u32   type_id;
  };
If user passed a bpf func_info record size of 16 bytes, the
kernel can still handle part of records with the above definition.

If verifier agrees with function range provided by the user,
the bpf_prog ksym for each function will use the func name
provided in the type_id, which is supposed to provide better
encoding as it is not limited by 16 bytes program name
limitation and this is better for bpf program which contains
multiple subprograms.

The bpf_prog_info interface is also extended to
return btf_id, func_info, func_info_rec_size and func_info_cnt
to userspace, so userspace can print out the function prototype
for each xlated function. The insn_offset in the returned
func_info corresponds to the insn offset for xlated functions.
With other jit related fields in bpf_prog_info, userspace can also
print out function prototypes for each jited function.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h          |   5 +-
 include/linux/bpf_verifier.h |   1 +
 include/linux/btf.h          |   2 +
 include/uapi/linux/bpf.h     |  13 +++++
 kernel/bpf/btf.c             |   4 +-
 kernel/bpf/core.c            |  13 +++++
 kernel/bpf/syscall.c         |  59 +++++++++++++++++++--
 kernel/bpf/verifier.c        | 120 ++++++++++++++++++++++++++++++++++++++++++-
 8 files changed, 209 insertions(+), 8 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 987815152629..7f0e225bf630 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -316,6 +316,8 @@ struct bpf_prog_aux {
 	void *security;
 #endif
 	struct bpf_prog_offload *offload;
+	struct btf *btf;
+	u32 type_id; /* type id for this prog/func */
 	union {
 		struct work_struct work;
 		struct rcu_head	rcu;
@@ -527,7 +529,8 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
 }
 
 /* verify correctness of eBPF program */
-int bpf_check(struct bpf_prog **fp, union bpf_attr *attr);
+int bpf_check(struct bpf_prog **fp, union bpf_attr *attr,
+	      union bpf_attr __user *uattr);
 void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
 
 /* Map specifics */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 11f5df1092d9..204382f46fd8 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -204,6 +204,7 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 struct bpf_subprog_info {
 	u32 start; /* insn idx of function entry point */
 	u16 stack_depth; /* max. stack depth used by this function */
+	u32 type_id; /* btf type_id for this subprog */
 };
 
 /* single container for all structs
diff --git a/include/linux/btf.h b/include/linux/btf.h
index e076c4697049..7f2c0a4a45ea 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -46,5 +46,7 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
 int btf_get_fd_by_id(u32 id);
 u32 btf_id(const struct btf *btf);
+const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
+const char *btf_name_by_offset(const struct btf *btf, u32 offset);
 
 #endif
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 05d95290b848..c1554aa07465 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -338,6 +338,10 @@ union bpf_attr {
 		 * (context accesses, allowed helpers, etc).
 		 */
 		__u32		expected_attach_type;
+		__u32		prog_btf_fd;	/* fd pointing to BTF type data */
+		__u32		func_info_rec_size;	/* userspace bpf_func_info size */
+		__aligned_u64	func_info;	/* func info */
+		__u32		func_info_cnt;	/* number of bpf_func_info records */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -2638,6 +2642,10 @@ struct bpf_prog_info {
 	__u32 nr_jited_func_lens;
 	__aligned_u64 jited_ksyms;
 	__aligned_u64 jited_func_lens;
+	__u32 btf_id;
+	__u32 func_info_rec_size;
+	__aligned_u64 func_info;
+	__u32 func_info_cnt;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -2949,4 +2957,9 @@ struct bpf_flow_keys {
 	};
 };
 
+struct bpf_func_info {
+	__u32	insn_offset;
+	__u32	type_id;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 6a2be79b73fc..69da9169819a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -474,7 +474,7 @@ static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
 	return !*src;
 }
 
-static const char *btf_name_by_offset(const struct btf *btf, u32 offset)
+const char *btf_name_by_offset(const struct btf *btf, u32 offset)
 {
 	if (!offset)
 		return "(anon)";
@@ -484,7 +484,7 @@ static const char *btf_name_by_offset(const struct btf *btf, u32 offset)
 		return "(invalid-name-offset)";
 }
 
-static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
+const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
 {
 	if (type_id > btf->nr_types)
 		return NULL;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 1a796e0799ec..16d77012ad3e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -21,12 +21,14 @@
  * Kris Katterjohn - Added many additional checks in bpf_check_classic()
  */
 
+#include <uapi/linux/btf.h>
 #include <linux/filter.h>
 #include <linux/skbuff.h>
 #include <linux/vmalloc.h>
 #include <linux/random.h>
 #include <linux/moduleloader.h>
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/frame.h>
 #include <linux/rbtree_latch.h>
 #include <linux/kallsyms.h>
@@ -390,6 +392,8 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog,
 static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
 {
 	const char *end = sym + KSYM_NAME_LEN;
+	const struct btf_type *type;
+	const char *func_name;
 
 	BUILD_BUG_ON(sizeof("bpf_prog_") +
 		     sizeof(prog->tag) * 2 +
@@ -404,6 +408,15 @@ static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
 
 	sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_");
 	sym  = bin2hex(sym, prog->tag, sizeof(prog->tag));
+
+	/* prog->aux->name will be ignored if full btf name is available */
+	if (prog->aux->btf) {
+		type = btf_type_by_id(prog->aux->btf, prog->aux->type_id);
+		func_name = btf_name_by_offset(prog->aux->btf, type->name_off);
+		snprintf(sym, (size_t)(end - sym), "_%s", func_name);
+		return;
+	}
+
 	if (prog->aux->name[0])
 		snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name);
 	else
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index cf5040fd5434..998377808102 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1213,6 +1213,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 		/* bpf_prog_free_id() must be called first */
 		bpf_prog_free_id(prog, do_idr_lock);
 		bpf_prog_kallsyms_del_all(prog);
+		btf_put(prog->aux->btf);
 
 		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
 	}
@@ -1437,9 +1438,9 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD expected_attach_type
+#define	BPF_PROG_LOAD_LAST_FIELD func_info_cnt
 
-static int bpf_prog_load(union bpf_attr *attr)
+static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 {
 	enum bpf_prog_type type = attr->prog_type;
 	struct bpf_prog *prog;
@@ -1525,7 +1526,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 		goto free_prog;
 
 	/* run eBPF verifier */
-	err = bpf_check(&prog, attr);
+	err = bpf_check(&prog, attr, uattr);
 	if (err < 0)
 		goto free_used_maps;
 
@@ -2079,6 +2080,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		info.xlated_prog_len = 0;
 		info.nr_jited_ksyms = 0;
 		info.nr_jited_func_lens = 0;
+		info.func_info_cnt = 0;
 		goto done;
 	}
 
@@ -2216,6 +2218,55 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		}
 	}
 
+	if (prog->aux->btf) {
+		u32 ucnt, urec_size;
+
+		info.btf_id = btf_id(prog->aux->btf);
+
+		ucnt = info.func_info_cnt;
+		info.func_info_cnt = prog->aux->func_cnt ? : 1;
+		urec_size = info.func_info_rec_size;
+		info.func_info_rec_size = sizeof(struct bpf_func_info);
+		if (ucnt) {
+			/* expect passed-in urec_size is what the kernel expects */
+			if (urec_size != info.func_info_rec_size)
+				return -EINVAL;
+
+			if (bpf_dump_raw_ok()) {
+				struct bpf_func_info kern_finfo;
+				char __user *user_finfo;
+				u32 i, insn_offset;
+
+				user_finfo = u64_to_user_ptr(info.func_info);
+				if (prog->aux->func_cnt) {
+					ucnt = min_t(u32, info.func_info_cnt, ucnt);
+					insn_offset = 0;
+					for (i = 0; i < ucnt; i++) {
+						kern_finfo.insn_offset = insn_offset;
+						kern_finfo.type_id = prog->aux->func[i]->aux->type_id;
+						if (copy_to_user(user_finfo, &kern_finfo,
+								 sizeof(kern_finfo)))
+							return -EFAULT;
+
+						/* func[i]->len holds the prog len */
+						insn_offset += prog->aux->func[i]->len;
+						user_finfo += urec_size;
+					}
+				} else {
+					kern_finfo.insn_offset = 0;
+					kern_finfo.type_id = prog->aux->type_id;
+					if (copy_to_user(user_finfo, &kern_finfo,
+							 sizeof(kern_finfo)))
+						return -EFAULT;
+				}
+			} else {
+				info.func_info_cnt = 0;
+			}
+		}
+	} else {
+		info.func_info_cnt = 0;
+	}
+
 done:
 	if (copy_to_user(uinfo, &info, info_len) ||
 	    put_user(info_len, &uattr->info.info_len))
@@ -2501,7 +2552,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = map_get_next_key(&attr);
 		break;
 	case BPF_PROG_LOAD:
-		err = bpf_prog_load(&attr);
+		err = bpf_prog_load(&attr, uattr);
 		break;
 	case BPF_OBJ_PIN:
 		err = bpf_obj_pin(&attr);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b5222aa61d54..f102c4fd0c5a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11,10 +11,12 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  * General Public License for more details.
  */
+#include <uapi/linux/btf.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/bpf_verifier.h>
 #include <linux/filter.h>
 #include <net/netlink.h>
@@ -4639,6 +4641,114 @@ err_free:
 	return ret;
 }
 
+/* The minimum supported BTF func info size */
+#define MIN_BPF_FUNCINFO_SIZE	8
+#define MAX_FUNCINFO_REC_SIZE	252
+
+static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
+			  union bpf_attr *attr, union bpf_attr __user *uattr)
+{
+	u32 i, nfuncs, urec_size, min_size, prev_offset;
+	u32 krec_size = sizeof(struct bpf_func_info);
+	struct bpf_func_info krecord = {};
+	const struct btf_type *type;
+	void __user *urecord;
+	struct btf *btf;
+	int ret = 0;
+
+	nfuncs = attr->func_info_cnt;
+	if (!nfuncs)
+		return 0;
+
+	if (nfuncs != env->subprog_cnt) {
+		verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
+		return -EINVAL;
+	}
+
+	urec_size = attr->func_info_rec_size;
+	if (urec_size < MIN_BPF_FUNCINFO_SIZE ||
+	    urec_size > MAX_FUNCINFO_REC_SIZE ||
+	    urec_size % sizeof(u32)) {
+		verbose(env, "invalid func info rec size %u\n", urec_size);
+		return -EINVAL;
+	}
+
+	btf = btf_get_by_fd(attr->prog_btf_fd);
+	if (IS_ERR(btf)) {
+		verbose(env, "unable to get btf from fd\n");
+		return PTR_ERR(btf);
+	}
+
+	urecord = u64_to_user_ptr(attr->func_info);
+	min_size = min_t(u32, krec_size, urec_size);
+
+	for (i = 0; i < nfuncs; i++) {
+		ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
+		if (ret) {
+			if (ret == -E2BIG) {
+				verbose(env, "nonzero tailing record in func info");
+				/* set the size kernel expects so loader can zero
+				 * out the rest of the record.
+				 */
+				if (put_user(min_size, &uattr->func_info_rec_size))
+					ret = -EFAULT;
+			}
+			goto free_btf;
+		}
+
+		if (copy_from_user(&krecord, urecord, min_size)) {
+			ret = -EFAULT;
+			goto free_btf;
+		}
+
+		/* check insn_offset */
+		if (i == 0) {
+			if (krecord.insn_offset) {
+				verbose(env,
+					"nonzero insn_offset %u for the first func info record",
+					krecord.insn_offset);
+				ret = -EINVAL;
+				goto free_btf;
+			}
+		} else if (krecord.insn_offset <= prev_offset) {
+			verbose(env,
+				"same or smaller insn offset (%u) than previous func info record (%u)",
+				krecord.insn_offset, prev_offset);
+			ret = -EINVAL;
+			goto free_btf;
+		}
+
+		if (env->subprog_info[i].start != krecord.insn_offset) {
+			verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
+			ret = -EINVAL;
+			goto free_btf;
+		}
+
+		/* check type_id */
+		type = btf_type_by_id(btf, krecord.type_id);
+		if (!type || BTF_INFO_KIND(type->info) != BTF_KIND_FUNC) {
+			verbose(env, "invalid type id %d in func info",
+				krecord.type_id);
+			ret = -EINVAL;
+			goto free_btf;
+		}
+
+		if (i == 0)
+			prog->aux->type_id = krecord.type_id;
+		env->subprog_info[i].type_id = krecord.type_id;
+
+		prev_offset = krecord.insn_offset;
+		urecord += urec_size;
+	}
+
+	prog->aux->btf = btf;
+	return 0;
+
+free_btf:
+	btf_put(btf);
+	return ret;
+}
+
 /* check %cur's range satisfies %old's */
 static bool range_within(struct bpf_reg_state *old,
 			 struct bpf_reg_state *cur)
@@ -5939,6 +6049,9 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->name[0] = 'F';
 		func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
 		func[i]->jit_requested = 1;
+		/* the btf will be freed only at prog->aux */
+		func[i]->aux->btf = prog->aux->btf;
+		func[i]->aux->type_id = env->subprog_info[i].type_id;
 		func[i] = bpf_int_jit_compile(func[i]);
 		if (!func[i]->jited) {
 			err = -ENOTSUPP;
@@ -6325,7 +6438,8 @@ static void free_states(struct bpf_verifier_env *env)
 	kfree(env->explored_states);
 }
 
-int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
+int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
+	      union bpf_attr __user *uattr)
 {
 	struct bpf_verifier_env *env;
 	struct bpf_verifier_log *log;
@@ -6397,6 +6511,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 	if (ret < 0)
 		goto skip_full_check;
 
+	ret = check_btf_func(env->prog, env, attr, uattr);
+	if (ret < 0)
+		goto skip_full_check;
+
 	ret = do_check(env);
 	if (env->cur_state) {
 		free_verifier_state(env->cur_state, true);
-- 
cgit v1.2.3


From cc19435cb2ee34a3663f0be69f3a4647795b0417 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 19 Nov 2018 15:29:13 -0800
Subject: tools/bpf: sync kernel uapi bpf.h header to tools directory

The kernel uapi bpf.h is synced to tools directory.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 05d95290b848..c1554aa07465 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -338,6 +338,10 @@ union bpf_attr {
 		 * (context accesses, allowed helpers, etc).
 		 */
 		__u32		expected_attach_type;
+		__u32		prog_btf_fd;	/* fd pointing to BTF type data */
+		__u32		func_info_rec_size;	/* userspace bpf_func_info size */
+		__aligned_u64	func_info;	/* func info */
+		__u32		func_info_cnt;	/* number of bpf_func_info records */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -2638,6 +2642,10 @@ struct bpf_prog_info {
 	__u32 nr_jited_func_lens;
 	__aligned_u64 jited_ksyms;
 	__aligned_u64 jited_func_lens;
+	__u32 btf_id;
+	__u32 func_info_rec_size;
+	__aligned_u64 func_info;
+	__u32 func_info_cnt;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -2949,4 +2957,9 @@ struct bpf_flow_keys {
 	};
 };
 
+struct bpf_func_info {
+	__u32	insn_offset;
+	__u32	type_id;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
-- 
cgit v1.2.3


From 7e0d0fb5522a388700ceff723af98c47ffa8a0a9 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 19 Nov 2018 15:29:14 -0800
Subject: tools/bpf: add new fields for program load in lib/bpf

The new fields are added for program load in lib/bpf so
application uses api bpf_load_program_xattr() is able
to load program with btf and func_info data.

This functionality will be used in next patch
by bpf selftest test_btf.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c | 4 ++++
 tools/lib/bpf/bpf.h | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 961e1b9fc592..9b5cf22c4e64 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -205,6 +205,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	attr.log_level = 0;
 	attr.kern_version = load_attr->kern_version;
 	attr.prog_ifindex = load_attr->prog_ifindex;
+	attr.prog_btf_fd = load_attr->prog_btf_fd;
+	attr.func_info_rec_size = load_attr->func_info_rec_size;
+	attr.func_info_cnt = load_attr->func_info_cnt;
+	attr.func_info = ptr_to_u64(load_attr->func_info);
 	memcpy(attr.prog_name, load_attr->name,
 	       min(name_len, BPF_OBJ_NAME_LEN - 1));
 
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 26a51538213c..8bdfd806253a 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -74,6 +74,10 @@ struct bpf_load_program_attr {
 	const char *license;
 	__u32 kern_version;
 	__u32 prog_ifindex;
+	__u32 prog_btf_fd;
+	__u32 func_info_rec_size;
+	const void *func_info;
+	__u32 func_info_cnt;
 };
 
 /* Flags to direct loading requirements */
-- 
cgit v1.2.3


From 4798c4ba3ba94e4da37b2557dfda04f80a94e8d5 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 19 Nov 2018 15:29:15 -0800
Subject: tools/bpf: extends test_btf to test load/retrieve func_type info

A two function bpf program is loaded with btf and func_info.
After successful prog load, the bpf_get_info syscall is called
to retrieve prog info to ensure the types returned from the
kernel matches the types passed to the kernel from the
user space.

Several negative tests are also added to test loading/retriving
of func_type info.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_btf.c | 332 ++++++++++++++++++++++++++++++++-
 1 file changed, 329 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index e0eeee5c8c04..8fd3a16fea4d 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -5,6 +5,7 @@
 #include <linux/btf.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
+#include <linux/filter.h>
 #include <bpf/bpf.h>
 #include <sys/resource.h>
 #include <libelf.h>
@@ -22,9 +23,13 @@
 #include "bpf_rlimit.h"
 #include "bpf_util.h"
 
+#define MAX_INSNS	512
+#define MAX_SUBPROGS	16
+
 static uint32_t pass_cnt;
 static uint32_t error_cnt;
 static uint32_t skip_cnt;
+static bool jit_enabled;
 
 #define CHECK(condition, format...) ({					\
 	int __ret = !!(condition);					\
@@ -60,6 +65,24 @@ static int __base_pr(const char *format, ...)
 	return err;
 }
 
+static bool is_jit_enabled(void)
+{
+	const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
+	bool enabled = false;
+	int sysctl_fd;
+
+	sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
+	if (sysctl_fd != -1) {
+		char tmpc;
+
+		if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
+			enabled = (tmpc != '0');
+		close(sysctl_fd);
+	}
+
+	return enabled;
+}
+
 #define BTF_INFO_ENC(kind, root, vlen)			\
 	((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
 
@@ -115,6 +138,7 @@ static struct args {
 	bool get_info_test;
 	bool pprint_test;
 	bool always_log;
+	bool func_type_test;
 } args;
 
 static char btf_log_buf[BTF_LOG_BUF_SIZE];
@@ -2947,16 +2971,310 @@ static int test_pprint(void)
 	return err;
 }
 
+static struct btf_func_type_test {
+	const char *descr;
+	const char *str_sec;
+	__u32 raw_types[MAX_NR_RAW_TYPES];
+	__u32 str_sec_size;
+	struct bpf_insn insns[MAX_INSNS];
+	__u32 prog_type;
+	__u32 func_info[MAX_SUBPROGS][2];
+	__u32 func_info_rec_size;
+	__u32 func_info_cnt;
+	bool expected_prog_load_failure;
+} func_type_test[] = {
+{
+	.descr = "func_type (main func + one sub)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),	/* [2] */
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [4] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [5] */
+		BTF_FUNC_ENC(NAME_TBD, 4),			/* [6] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+	.str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info = { {0, 5}, {3, 6} },
+	.func_info_rec_size = 8,
+	.func_info_cnt = 2,
+},
+
+{
+	.descr = "func_type (Incorrect func_info_rec_size)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),	/* [2] */
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [4] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [5] */
+		BTF_FUNC_ENC(NAME_TBD, 4),			/* [6] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+	.str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info = { {0, 5}, {3, 6} },
+	.func_info_rec_size = 4,
+	.func_info_cnt = 2,
+	.expected_prog_load_failure = true,
+},
+
+{
+	.descr = "func_type (Incorrect func_info_cnt)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),	/* [2] */
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [4] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [5] */
+		BTF_FUNC_ENC(NAME_TBD, 4),			/* [6] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+	.str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info = { {0, 5}, {3, 6} },
+	.func_info_rec_size = 8,
+	.func_info_cnt = 1,
+	.expected_prog_load_failure = true,
+},
+
+{
+	.descr = "func_type (Incorrect bpf_func_info.insn_offset)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),	/* [2] */
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [4] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [5] */
+		BTF_FUNC_ENC(NAME_TBD, 4),			/* [6] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+	.str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info = { {0, 5}, {2, 6} },
+	.func_info_rec_size = 8,
+	.func_info_cnt = 2,
+	.expected_prog_load_failure = true,
+},
+
+};
+
+static size_t probe_prog_length(const struct bpf_insn *fp)
+{
+	size_t len;
+
+	for (len = MAX_INSNS - 1; len > 0; --len)
+		if (fp[len].code != 0 || fp[len].imm != 0)
+			break;
+	return len + 1;
+}
+
+static int do_test_func_type(int test_num)
+{
+	const struct btf_func_type_test *test = &func_type_test[test_num];
+	unsigned int raw_btf_size, info_len, rec_size;
+	int i, btf_fd = -1, prog_fd = -1, err = 0;
+	struct bpf_load_program_attr attr = {};
+	void *raw_btf, *func_info = NULL;
+	struct bpf_prog_info info = {};
+	struct bpf_func_info *finfo;
+
+	fprintf(stderr, "%s......", test->descr);
+	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
+				 test->str_sec, test->str_sec_size,
+				 &raw_btf_size);
+
+	if (!raw_btf)
+		return -1;
+
+	*btf_log_buf = '\0';
+	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
+			      btf_log_buf, BTF_LOG_BUF_SIZE,
+			      args.always_log);
+	free(raw_btf);
+
+	if (CHECK(btf_fd == -1, "invalid btf_fd errno:%d", errno)) {
+		err = -1;
+		goto done;
+	}
+
+	if (*btf_log_buf && args.always_log)
+		fprintf(stderr, "\n%s", btf_log_buf);
+
+	attr.prog_type = test->prog_type;
+	attr.insns = test->insns;
+	attr.insns_cnt = probe_prog_length(attr.insns);
+	attr.license = "GPL";
+	attr.prog_btf_fd = btf_fd;
+	attr.func_info_rec_size = test->func_info_rec_size;
+	attr.func_info_cnt = test->func_info_cnt;
+	attr.func_info = test->func_info;
+
+	*btf_log_buf = '\0';
+	prog_fd = bpf_load_program_xattr(&attr, btf_log_buf,
+					 BTF_LOG_BUF_SIZE);
+	if (test->expected_prog_load_failure && prog_fd == -1) {
+		err = 0;
+		goto done;
+	}
+	if (CHECK(prog_fd == -1, "invalid prog_id errno:%d", errno)) {
+		fprintf(stderr, "%s\n", btf_log_buf);
+		err = -1;
+		goto done;
+	}
+	if (!jit_enabled) {
+		skip_cnt++;
+		fprintf(stderr, "SKIPPED, please enable sysctl bpf_jit_enable\n");
+		err = 0;
+		goto done;
+	}
+
+	/* get necessary lens */
+	info_len = sizeof(struct bpf_prog_info);
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) {
+		fprintf(stderr, "%s\n", btf_log_buf);
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_cnt != 2,
+		  "incorrect info.func_info_cnt (1st) %d\n",
+		  info.func_info_cnt)) {
+		err = -1;
+		goto done;
+	}
+	rec_size = info.func_info_rec_size;
+	if (CHECK(rec_size < 4,
+		  "incorrect info.func_info_rec_size (1st) %d\n", rec_size)) {
+		err = -1;
+		goto done;
+	}
+
+	func_info = malloc(info.func_info_cnt * rec_size);
+	if (CHECK(!func_info, "out of memeory")) {
+		err = -1;
+		goto done;
+	}
+
+	/* reset info to only retrieve func_info related data */
+	memset(&info, 0, sizeof(info));
+	info.func_info_cnt = 2;
+	info.func_info_rec_size = rec_size;
+	info.func_info = ptr_to_u64(func_info);
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) {
+		fprintf(stderr, "%s\n", btf_log_buf);
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_cnt != 2,
+		  "incorrect info.func_info_cnt (2nd) %d\n",
+		  info.func_info_cnt)) {
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_rec_size != rec_size,
+		  "incorrect info.func_info_rec_size (2nd) %d\n",
+		  info.func_info_rec_size)) {
+		err = -1;
+		goto done;
+	}
+
+	finfo = func_info;
+	for (i = 0; i < 2; i++) {
+		if (CHECK(finfo->type_id != test->func_info[i][1],
+			  "incorrect func_type %u expected %u",
+			  finfo->type_id, test->func_info[i][1])) {
+			err = -1;
+			goto done;
+		}
+		finfo = (void *)finfo + rec_size;
+	}
+
+done:
+	if (*btf_log_buf && (err || args.always_log))
+		fprintf(stderr, "\n%s", btf_log_buf);
+
+	if (btf_fd != -1)
+		close(btf_fd);
+	if (prog_fd != -1)
+		close(prog_fd);
+	free(func_info);
+	return err;
+}
+
+static int test_func_type(void)
+{
+	unsigned int i;
+	int err = 0;
+
+	for (i = 0; i < ARRAY_SIZE(func_type_test); i++)
+		err |= count_result(do_test_func_type(i));
+
+	return err;
+}
+
 static void usage(const char *cmd)
 {
-	fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] | [-g test_num (1 - %zu)] | [-f test_num (1 - %zu)] | [-p]]\n",
+	fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] |"
+			" [-g test_num (1 - %zu)] |"
+			" [-f test_num (1 - %zu)] | [-p] | [-k] ]\n",
 		cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests),
 		ARRAY_SIZE(file_tests));
 }
 
 static int parse_args(int argc, char **argv)
 {
-	const char *optstr = "lpf:r:g:";
+	const char *optstr = "lpkf:r:g:";
 	int opt;
 
 	while ((opt = getopt(argc, argv, optstr)) != -1) {
@@ -2979,6 +3297,9 @@ static int parse_args(int argc, char **argv)
 		case 'p':
 			args.pprint_test = true;
 			break;
+		case 'k':
+			args.func_type_test = true;
+			break;
 		case 'h':
 			usage(argv[0]);
 			exit(0);
@@ -3032,6 +3353,8 @@ int main(int argc, char **argv)
 	if (args.always_log)
 		libbpf_set_print(__base_pr, __base_pr, __base_pr);
 
+	jit_enabled = is_jit_enabled();
+
 	if (args.raw_test)
 		err |= test_raw();
 
@@ -3044,8 +3367,11 @@ int main(int argc, char **argv)
 	if (args.pprint_test)
 		err |= test_pprint();
 
+	if (args.func_type_test)
+		err |= test_func_type();
+
 	if (args.raw_test || args.get_info_test || args.file_test ||
-	    args.pprint_test)
+	    args.pprint_test || args.func_type_test)
 		goto done;
 
 	err |= test_raw();
-- 
cgit v1.2.3


From 2993e0515bb44e157c17c9ba7309ba46366b6add Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 19 Nov 2018 15:29:16 -0800
Subject: tools/bpf: add support to read .BTF.ext sections

The .BTF section is already available to encode types.
These types can be used for map
pretty print. The whole .BTF will be passed to the
kernel as well for which kernel can verify and return
to the user space for pretty print etc.

The llvm patch at https://reviews.llvm.org/D53736
will generate .BTF section and one more section .BTF.ext.
The .BTF.ext section encodes function type
information and line information. Note that
this patch set only supports function type info.
The functionality is implemented in libbpf.

The .BTF section can be directly loaded into the
kernel, and the .BTF.ext section cannot. The loader
may need to do some relocation and merging,
similar to merging multiple code sections, before
loading into the kernel.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    |  46 ++++++++-
 tools/lib/bpf/btf.c    | 274 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/btf.h    |  50 +++++++++
 tools/lib/bpf/libbpf.c |  87 +++++++++++++---
 4 files changed, 442 insertions(+), 15 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9b5cf22c4e64..836447bb4f14 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -186,6 +186,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 			   char *log_buf, size_t log_buf_sz)
 {
 	union bpf_attr attr;
+	void *finfo = NULL;
 	__u32 name_len;
 	int fd;
 
@@ -216,12 +217,55 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	if (fd >= 0 || !log_buf || !log_buf_sz)
 		return fd;
 
+	/* After bpf_prog_load, the kernel may modify certain attributes
+	 * to give user space a hint how to deal with loading failure.
+	 * Check to see whether we can make some changes and load again.
+	 */
+	if (errno == E2BIG && attr.func_info_cnt &&
+	    attr.func_info_rec_size < load_attr->func_info_rec_size) {
+		__u32 actual_rec_size = load_attr->func_info_rec_size;
+		__u32 expected_rec_size = attr.func_info_rec_size;
+		__u32 finfo_cnt = load_attr->func_info_cnt;
+		__u64 finfo_len = actual_rec_size * finfo_cnt;
+		const void *orecord;
+		void *nrecord;
+		int i;
+
+		finfo = malloc(finfo_len);
+		if (!finfo)
+			/* further try with log buffer won't help */
+			return fd;
+
+		/* zero out bytes kernel does not understand */
+		orecord = load_attr->func_info;
+		nrecord = finfo;
+		for (i = 0; i < load_attr->func_info_cnt; i++) {
+			memcpy(nrecord, orecord, expected_rec_size);
+			memset(nrecord + expected_rec_size, 0,
+			       actual_rec_size - expected_rec_size);
+			orecord += actual_rec_size;
+			nrecord += actual_rec_size;
+		}
+
+		/* try with corrected func info records */
+		attr.func_info = ptr_to_u64(finfo);
+		attr.func_info_rec_size = load_attr->func_info_rec_size;
+
+		fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+
+		if (fd >= 0 || !log_buf || !log_buf_sz)
+			goto done;
+	}
+
 	/* Try again with log */
 	attr.log_buf = ptr_to_u64(log_buf);
 	attr.log_size = log_buf_sz;
 	attr.log_level = 1;
 	log_buf[0] = 0;
-	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+done:
+	free(finfo);
+	return fd;
 }
 
 int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 31225e64766f..fe87cb48a6a9 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -37,6 +37,18 @@ struct btf {
 	int fd;
 };
 
+struct btf_ext {
+	void *func_info;
+	__u32 func_info_rec_size;
+	__u32 func_info_len;
+};
+
+/* The minimum bpf_func_info checked by the loader */
+struct bpf_func_info_min {
+	__u32   insn_offset;
+	__u32   type_id;
+};
+
 static int btf_add_type(struct btf *btf, struct btf_type *t)
 {
 	if (btf->types_size - btf->nr_types < 2) {
@@ -397,3 +409,265 @@ const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
 	else
 		return NULL;
 }
+
+static int btf_ext_validate_func_info(const void *finfo, __u32 size,
+				      btf_print_fn_t err_log)
+{
+	int sec_hdrlen = sizeof(struct btf_sec_func_info);
+	__u32 size_left, num_records, record_size;
+	const struct btf_sec_func_info *sinfo;
+	__u64 total_record_size;
+
+	/* At least a func_info record size */
+	if (size < sizeof(__u32)) {
+		elog("BTF.ext func_info record size not found");
+		return -EINVAL;
+	}
+
+	/* The record size needs to meet below minimum standard */
+	record_size = *(__u32 *)finfo;
+	if (record_size < sizeof(struct bpf_func_info_min) ||
+	    record_size % sizeof(__u32)) {
+		elog("BTF.ext func_info invalid record size");
+		return -EINVAL;
+	}
+
+	sinfo = finfo + sizeof(__u32);
+	size_left = size - sizeof(__u32);
+
+	/* If no func_info records, return failure now so .BTF.ext
+	 * won't be used.
+	 */
+	if (!size_left) {
+		elog("BTF.ext no func info records");
+		return -EINVAL;
+	}
+
+	while (size_left) {
+		if (size_left < sec_hdrlen) {
+			elog("BTF.ext func_info header not found");
+			return -EINVAL;
+		}
+
+		num_records = sinfo->num_func_info;
+		if (num_records == 0) {
+			elog("incorrect BTF.ext num_func_info");
+			return -EINVAL;
+		}
+
+		total_record_size = sec_hdrlen +
+				    (__u64)num_records * record_size;
+		if (size_left < total_record_size) {
+			elog("incorrect BTF.ext num_func_info");
+			return -EINVAL;
+		}
+
+		size_left -= total_record_size;
+		sinfo = (void *)sinfo + total_record_size;
+	}
+
+	return 0;
+}
+
+static int btf_ext_parse_hdr(__u8 *data, __u32 data_size,
+			     btf_print_fn_t err_log)
+{
+	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
+	__u32 meta_left, last_func_info_pos;
+	void *finfo;
+
+	if (data_size < offsetof(struct btf_ext_header, func_info_off) ||
+	    data_size < hdr->hdr_len) {
+		elog("BTF.ext header not found");
+		return -EINVAL;
+	}
+
+	if (hdr->magic != BTF_MAGIC) {
+		elog("Invalid BTF.ext magic:%x\n", hdr->magic);
+		return -EINVAL;
+	}
+
+	if (hdr->version != BTF_VERSION) {
+		elog("Unsupported BTF.ext version:%u\n", hdr->version);
+		return -ENOTSUP;
+	}
+
+	if (hdr->flags) {
+		elog("Unsupported BTF.ext flags:%x\n", hdr->flags);
+		return -ENOTSUP;
+	}
+
+	meta_left = data_size - hdr->hdr_len;
+	if (!meta_left) {
+		elog("BTF.ext has no data\n");
+		return -EINVAL;
+	}
+
+	if (meta_left < hdr->func_info_off) {
+		elog("Invalid BTF.ext func_info section offset:%u\n",
+		     hdr->func_info_off);
+		return -EINVAL;
+	}
+
+	if (hdr->func_info_off & 0x03) {
+		elog("BTF.ext func_info section is not aligned to 4 bytes\n");
+		return -EINVAL;
+	}
+
+	last_func_info_pos = hdr->hdr_len + hdr->func_info_off +
+			     hdr->func_info_len;
+	if (last_func_info_pos > data_size) {
+		elog("Invalid BTF.ext func_info section size:%u\n",
+		     hdr->func_info_len);
+		return -EINVAL;
+	}
+
+	finfo = data + hdr->hdr_len + hdr->func_info_off;
+	return btf_ext_validate_func_info(finfo, hdr->func_info_len,
+					  err_log);
+}
+
+void btf_ext__free(struct btf_ext *btf_ext)
+{
+	if (!btf_ext)
+		return;
+
+	free(btf_ext->func_info);
+	free(btf_ext);
+}
+
+struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
+{
+	const struct btf_ext_header *hdr;
+	struct btf_ext *btf_ext;
+	void *org_fdata, *fdata;
+	__u32 hdrlen, size_u32;
+	int err;
+
+	err = btf_ext_parse_hdr(data, size, err_log);
+	if (err)
+		return ERR_PTR(err);
+
+	btf_ext = calloc(1, sizeof(struct btf_ext));
+	if (!btf_ext)
+		return ERR_PTR(-ENOMEM);
+
+	hdr = (const struct btf_ext_header *)data;
+	hdrlen = hdr->hdr_len;
+	size_u32 = sizeof(__u32);
+	fdata = malloc(hdr->func_info_len - size_u32);
+	if (!fdata) {
+		free(btf_ext);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* remember record size and copy rest of func_info data */
+	org_fdata = data + hdrlen + hdr->func_info_off;
+	btf_ext->func_info_rec_size = *(__u32 *)org_fdata;
+	memcpy(fdata, org_fdata + size_u32, hdr->func_info_len - size_u32);
+	btf_ext->func_info = fdata;
+	btf_ext->func_info_len = hdr->func_info_len - size_u32;
+
+	return btf_ext;
+}
+
+int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext,
+			const char *sec_name, void **func_info,
+			__u32 *func_info_rec_size, __u32 *func_info_len)
+{
+	__u32 sec_hdrlen = sizeof(struct btf_sec_func_info);
+	__u32 i, record_size, records_len;
+	struct btf_sec_func_info *sinfo;
+	const char *info_sec_name;
+	__s64 remain_len;
+	void *data;
+
+	record_size = btf_ext->func_info_rec_size;
+	sinfo = btf_ext->func_info;
+	remain_len = btf_ext->func_info_len;
+
+	while (remain_len > 0) {
+		records_len = sinfo->num_func_info * record_size;
+		info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off);
+		if (strcmp(info_sec_name, sec_name)) {
+			remain_len -= sec_hdrlen + records_len;
+			sinfo = (void *)sinfo + sec_hdrlen + records_len;
+			continue;
+		}
+
+		data = malloc(records_len);
+		if (!data)
+			return -ENOMEM;
+
+		memcpy(data, sinfo->data, records_len);
+
+		/* adjust the insn_offset, the data in .BTF.ext is
+		 * the actual byte offset, and the kernel expects
+		 * the offset in term of bpf_insn.
+		 *
+		 * adjust the insn offset only, the rest data will
+		 * be passed to kernel.
+		 */
+		for (i = 0; i < sinfo->num_func_info; i++) {
+			struct bpf_func_info_min *record;
+
+			record = data + i * record_size;
+			record->insn_offset /= sizeof(struct bpf_insn);
+		}
+
+		*func_info = data;
+		*func_info_len = records_len;
+		*func_info_rec_size = record_size;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
+		   const char *sec_name, __u32 insns_cnt,
+		   void **func_info, __u32 *func_info_len)
+{
+	__u32 sec_hdrlen = sizeof(struct btf_sec_func_info);
+	__u32 i, record_size, existing_flen, records_len;
+	struct btf_sec_func_info *sinfo;
+	const char *info_sec_name;
+	__u64 remain_len;
+	void *data;
+
+	record_size = btf_ext->func_info_rec_size;
+	sinfo = btf_ext->func_info;
+	remain_len = btf_ext->func_info_len;
+	while (remain_len > 0) {
+		records_len = sinfo->num_func_info * record_size;
+		info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off);
+		if (strcmp(info_sec_name, sec_name)) {
+			remain_len -= sec_hdrlen + records_len;
+			sinfo = (void *)sinfo + sec_hdrlen + records_len;
+			continue;
+		}
+
+		existing_flen = *func_info_len;
+		data = realloc(*func_info, existing_flen + records_len);
+		if (!data)
+			return -ENOMEM;
+
+		memcpy(data + existing_flen, sinfo->data, records_len);
+		/* adjust insn_offset only, the rest data will be passed
+		 * to the kernel.
+		 */
+		for (i = 0; i < sinfo->num_func_info; i++) {
+			struct bpf_func_info_min *record;
+
+			record = data + existing_flen + i * record_size;
+			record->insn_offset =
+				record->insn_offset / sizeof(struct bpf_insn) +
+				insns_cnt;
+		}
+		*func_info = data;
+		*func_info_len = existing_flen + records_len;
+		return 0;
+	}
+
+	return -EINVAL;
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index b77e7080f7e7..578171e8cb26 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -11,10 +11,51 @@
 #endif
 
 #define BTF_ELF_SEC ".BTF"
+#define BTF_EXT_ELF_SEC ".BTF.ext"
 
 struct btf;
+struct btf_ext;
 struct btf_type;
 
+/*
+ * The .BTF.ext ELF section layout defined as
+ *   struct btf_ext_header
+ *   func_info subsection
+ *
+ * The func_info subsection layout:
+ *   record size for struct bpf_func_info in the func_info subsection
+ *   struct btf_sec_func_info for section #1
+ *   a list of bpf_func_info records for section #1
+ *     where struct bpf_func_info mimics one in include/uapi/linux/bpf.h
+ *     but may not be identical
+ *   struct btf_sec_func_info for section #2
+ *   a list of bpf_func_info records for section #2
+ *   ......
+ *
+ * Note that the bpf_func_info record size in .BTF.ext may not
+ * be the same as the one defined in include/uapi/linux/bpf.h.
+ * The loader should ensure that record_size meets minimum
+ * requirement and pass the record as is to the kernel. The
+ * kernel will handle the func_info properly based on its contents.
+ */
+struct btf_ext_header {
+	__u16	magic;
+	__u8	version;
+	__u8	flags;
+	__u32	hdr_len;
+
+	/* All offsets are in bytes relative to the end of this header */
+	__u32	func_info_off;
+	__u32	func_info_len;
+};
+
+struct btf_sec_func_info {
+	__u32	sec_name_off;
+	__u32	num_func_info;
+	/* Followed by num_func_info number of bpf func_info records */
+	__u8	data[0];
+};
+
 typedef int (*btf_print_fn_t)(const char *, ...)
 	__attribute__((format(printf, 1, 2)));
 
@@ -29,4 +70,13 @@ LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__fd(const struct btf *btf);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 
+struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
+void btf_ext__free(struct btf_ext *btf_ext);
+int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext,
+			const char *sec_name, void **func_info,
+			__u32 *func_info_rec_size, __u32 *func_info_len);
+int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
+		   const char *sec_name, __u32 insns_cnt, void **func_info,
+		   __u32 *func_info_len);
+
 #endif /* __LIBBPF_BTF_H */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a01eb9584e52..cb6565d79603 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -156,6 +156,10 @@ struct bpf_program {
 	bpf_program_clear_priv_t clear_priv;
 
 	enum bpf_attach_type expected_attach_type;
+	int btf_fd;
+	void *func_info;
+	__u32 func_info_rec_size;
+	__u32 func_info_len;
 };
 
 struct bpf_map {
@@ -212,6 +216,7 @@ struct bpf_object {
 	struct list_head list;
 
 	struct btf *btf;
+	struct btf_ext *btf_ext;
 
 	void *priv;
 	bpf_object_clear_priv_t clear_priv;
@@ -241,6 +246,9 @@ void bpf_program__unload(struct bpf_program *prog)
 
 	prog->instances.nr = -1;
 	zfree(&prog->instances.fds);
+
+	zclose(prog->btf_fd);
+	zfree(&prog->func_info);
 }
 
 static void bpf_program__exit(struct bpf_program *prog)
@@ -315,6 +323,7 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx,
 	prog->instances.fds = NULL;
 	prog->instances.nr = -1;
 	prog->type = BPF_PROG_TYPE_KPROBE;
+	prog->btf_fd = -1;
 
 	return 0;
 errout:
@@ -807,6 +816,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 					   BTF_ELF_SEC, PTR_ERR(obj->btf));
 				obj->btf = NULL;
 			}
+		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
+			obj->btf_ext = btf_ext__new(data->d_buf, data->d_size,
+						    __pr_debug);
+			if (IS_ERR(obj->btf_ext)) {
+				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
+					   BTF_EXT_ELF_SEC,
+					   PTR_ERR(obj->btf_ext));
+				obj->btf_ext = NULL;
+			}
 		} else if (sh.sh_type == SHT_SYMTAB) {
 			if (obj->efile.symbols) {
 				pr_warning("bpf: multiple SYMTAB in %s\n",
@@ -1190,6 +1208,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 	struct bpf_insn *insn, *new_insn;
 	struct bpf_program *text;
 	size_t new_cnt;
+	int err;
 
 	if (relo->type != RELO_CALL)
 		return -LIBBPF_ERRNO__RELOC;
@@ -1212,6 +1231,20 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			pr_warning("oom in prog realloc\n");
 			return -ENOMEM;
 		}
+
+		if (obj->btf && obj->btf_ext) {
+			err = btf_ext__reloc(obj->btf, obj->btf_ext,
+					     text->section_name,
+					     prog->insns_cnt,
+					     &prog->func_info,
+					     &prog->func_info_len);
+			if (err) {
+				pr_warning("error in btf_ext__reloc for sec %s\n",
+					   text->section_name);
+				return err;
+			}
+		}
+
 		memcpy(new_insn + prog->insns_cnt, text->insns,
 		       text->insns_cnt * sizeof(*insn));
 		prog->insns = new_insn;
@@ -1231,7 +1264,24 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 {
 	int i, err;
 
-	if (!prog || !prog->reloc_desc)
+	if (!prog)
+		return 0;
+
+	if (obj->btf && obj->btf_ext) {
+		err = btf_ext__reloc_init(obj->btf, obj->btf_ext,
+					  prog->section_name,
+					  &prog->func_info,
+					  &prog->func_info_rec_size,
+					  &prog->func_info_len);
+		if (err) {
+			pr_warning("err in btf_ext__reloc_init for sec %s\n",
+				   prog->section_name);
+			return err;
+		}
+		prog->btf_fd = btf__fd(obj->btf);
+	}
+
+	if (!prog->reloc_desc)
 		return 0;
 
 	for (i = 0; i < prog->nr_reloc; i++) {
@@ -1319,9 +1369,9 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 }
 
 static int
-load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
-	     const char *name, struct bpf_insn *insns, int insns_cnt,
-	     char *license, __u32 kern_version, int *pfd, int prog_ifindex)
+load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
+	     char *license, __u32 kern_version, int *pfd,
+	     __u32 func_info_cnt)
 {
 	struct bpf_load_program_attr load_attr;
 	char *cp, errmsg[STRERR_BUFSIZE];
@@ -1329,14 +1379,18 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 	int ret;
 
 	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
-	load_attr.prog_type = type;
-	load_attr.expected_attach_type = expected_attach_type;
-	load_attr.name = name;
+	load_attr.prog_type = prog->type;
+	load_attr.expected_attach_type = prog->expected_attach_type;
+	load_attr.name = prog->name;
 	load_attr.insns = insns;
 	load_attr.insns_cnt = insns_cnt;
 	load_attr.license = license;
 	load_attr.kern_version = kern_version;
-	load_attr.prog_ifindex = prog_ifindex;
+	load_attr.prog_ifindex = prog->prog_ifindex;
+	load_attr.prog_btf_fd = prog->btf_fd;
+	load_attr.func_info = prog->func_info;
+	load_attr.func_info_rec_size = prog->func_info_rec_size;
+	load_attr.func_info_cnt = func_info_cnt;
 
 	if (!load_attr.insns || !load_attr.insns_cnt)
 		return -EINVAL;
@@ -1394,8 +1448,14 @@ int
 bpf_program__load(struct bpf_program *prog,
 		  char *license, __u32 kern_version)
 {
+	__u32 func_info_cnt;
 	int err = 0, fd, i;
 
+	if (prog->func_info_len == 0)
+		func_info_cnt = 0;
+	else
+		func_info_cnt = prog->func_info_len / prog->func_info_rec_size;
+
 	if (prog->instances.nr < 0 || !prog->instances.fds) {
 		if (prog->preprocessor) {
 			pr_warning("Internal error: can't load program '%s'\n",
@@ -1417,10 +1477,9 @@ bpf_program__load(struct bpf_program *prog,
 			pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
 				   prog->section_name, prog->instances.nr);
 		}
-		err = load_program(prog->type, prog->expected_attach_type,
-				   prog->name, prog->insns, prog->insns_cnt,
+		err = load_program(prog, prog->insns, prog->insns_cnt,
 				   license, kern_version, &fd,
-				   prog->prog_ifindex);
+				   func_info_cnt);
 		if (!err)
 			prog->instances.fds[0] = fd;
 		goto out;
@@ -1448,11 +1507,10 @@ bpf_program__load(struct bpf_program *prog,
 			continue;
 		}
 
-		err = load_program(prog->type, prog->expected_attach_type,
-				   prog->name, result.new_insn_ptr,
+		err = load_program(prog, result.new_insn_ptr,
 				   result.new_insn_cnt,
 				   license, kern_version, &fd,
-				   prog->prog_ifindex);
+				   func_info_cnt);
 
 		if (err) {
 			pr_warning("Loading the %dth instance of program '%s' failed\n",
@@ -2120,6 +2178,7 @@ void bpf_object__close(struct bpf_object *obj)
 	bpf_object__elf_finish(obj);
 	bpf_object__unload(obj);
 	btf__free(obj->btf);
+	btf_ext__free(obj->btf_ext);
 
 	for (i = 0; i < obj->nr_maps; i++) {
 		zfree(&obj->maps[i].name);
-- 
cgit v1.2.3


From 9ce6ae22c8e878aee7a96836b2ed9fd9a8173e41 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 19 Nov 2018 15:29:17 -0800
Subject: tools/bpf: do not use pahole if clang/llvm can generate BTF sections

Add additional checks in tools/testing/selftests/bpf and
samples/bpf such that if clang/llvm compiler can generate
BTF sections, do not use pahole.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/Makefile                 | 8 ++++++++
 tools/testing/selftests/bpf/Makefile | 8 ++++++++
 2 files changed, 16 insertions(+)

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index be0a961450bc..35444f4a846b 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -208,12 +208,20 @@ endif
 BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
 BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
+BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
+			  $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \
+			  readelf -S ./llvm_btf_verify.o | grep BTF; \
+			  /bin/rm -f ./llvm_btf_verify.o)
 
+ifneq ($(BTF_LLVM_PROBE),)
+	EXTRA_CFLAGS += -g
+else
 ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),)
 	EXTRA_CFLAGS += -g
 	LLC_FLAGS += -mattr=dwarfris
 	DWARF2BTF = y
 endif
+endif
 
 # Trick to allow make to be run from this directory
 all:
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 57b4712a6276..1dde03ea1484 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -126,7 +126,14 @@ $(OUTPUT)/test_stack_map.o: test_queue_stack_map.h
 BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
 BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
+BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
+			  $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \
+			  readelf -S ./llvm_btf_verify.o | grep BTF; \
+			  /bin/rm -f ./llvm_btf_verify.o)
 
+ifneq ($(BTF_LLVM_PROBE),)
+	CLANG_FLAGS += -g
+else
 ifneq ($(BTF_LLC_PROBE),)
 ifneq ($(BTF_PAHOLE_PROBE),)
 ifneq ($(BTF_OBJCOPY_PROBE),)
@@ -136,6 +143,7 @@ ifneq ($(BTF_OBJCOPY_PROBE),)
 endif
 endif
 endif
+endif
 
 # Have one program compiled without "-target bpf" to test whether libbpf loads
 # it successfully
-- 
cgit v1.2.3


From d7f5b5e051554c91bab995b67101af4625af591a Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 19 Nov 2018 15:29:18 -0800
Subject: tools/bpf: refactor to implement btf_get_from_id() in lib/bpf

The function get_btf() is implemented in tools/bpf/bpftool/map.c
to get a btf structure given a map_info. This patch
refactored this function to be function btf_get_from_id()
in tools/lib/bpf so that it can be used later.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/map.c | 68 ++----------------------------------------------
 tools/lib/bpf/btf.c     | 69 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/btf.h     |  1 +
 3 files changed, 72 insertions(+), 66 deletions(-)

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index dc9a8967ab8c..a1ae2a3e9fef 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -215,70 +215,6 @@ err_end_obj:
 	return ret;
 }
 
-static int get_btf(struct bpf_map_info *map_info, struct btf **btf)
-{
-	struct bpf_btf_info btf_info = { 0 };
-	__u32 len = sizeof(btf_info);
-	__u32 last_size;
-	int btf_fd;
-	void *ptr;
-	int err;
-
-	err = 0;
-	*btf = NULL;
-	btf_fd = bpf_btf_get_fd_by_id(map_info->btf_id);
-	if (btf_fd < 0)
-		return 0;
-
-	/* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
-	 * let's start with a sane default - 4KiB here - and resize it only if
-	 * bpf_obj_get_info_by_fd() needs a bigger buffer.
-	 */
-	btf_info.btf_size = 4096;
-	last_size = btf_info.btf_size;
-	ptr = malloc(last_size);
-	if (!ptr) {
-		err = -ENOMEM;
-		goto exit_free;
-	}
-
-	bzero(ptr, last_size);
-	btf_info.btf = ptr_to_u64(ptr);
-	err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
-
-	if (!err && btf_info.btf_size > last_size) {
-		void *temp_ptr;
-
-		last_size = btf_info.btf_size;
-		temp_ptr = realloc(ptr, last_size);
-		if (!temp_ptr) {
-			err = -ENOMEM;
-			goto exit_free;
-		}
-		ptr = temp_ptr;
-		bzero(ptr, last_size);
-		btf_info.btf = ptr_to_u64(ptr);
-		err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
-	}
-
-	if (err || btf_info.btf_size > last_size) {
-		err = errno;
-		goto exit_free;
-	}
-
-	*btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL);
-	if (IS_ERR(*btf)) {
-		err = PTR_ERR(*btf);
-		*btf = NULL;
-	}
-
-exit_free:
-	close(btf_fd);
-	free(ptr);
-
-	return err;
-}
-
 static json_writer_t *get_btf_writer(void)
 {
 	json_writer_t *jw = jsonw_new(stdout);
@@ -775,7 +711,7 @@ static int do_dump(int argc, char **argv)
 
 	prev_key = NULL;
 
-	err = get_btf(&info, &btf);
+	err = btf_get_from_id(info.btf_id, &btf);
 	if (err) {
 		p_err("failed to get btf");
 		goto exit_free;
@@ -919,7 +855,7 @@ static int do_lookup(int argc, char **argv)
 	}
 
 	/* here means bpf_map_lookup_elem() succeeded */
-	err = get_btf(&info, &btf);
+	err = btf_get_from_id(info.btf_id, &btf);
 	if (err) {
 		p_err("failed to get btf");
 		goto exit_free;
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index fe87cb48a6a9..13ddc4bd24ee 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -49,6 +49,11 @@ struct bpf_func_info_min {
 	__u32   type_id;
 };
 
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
 static int btf_add_type(struct btf *btf, struct btf_type *t)
 {
 	if (btf->types_size - btf->nr_types < 2) {
@@ -410,6 +415,70 @@ const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
 		return NULL;
 }
 
+int btf_get_from_id(__u32 id, struct btf **btf)
+{
+	struct bpf_btf_info btf_info = { 0 };
+	__u32 len = sizeof(btf_info);
+	__u32 last_size;
+	int btf_fd;
+	void *ptr;
+	int err;
+
+	err = 0;
+	*btf = NULL;
+	btf_fd = bpf_btf_get_fd_by_id(id);
+	if (btf_fd < 0)
+		return 0;
+
+	/* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
+	 * let's start with a sane default - 4KiB here - and resize it only if
+	 * bpf_obj_get_info_by_fd() needs a bigger buffer.
+	 */
+	btf_info.btf_size = 4096;
+	last_size = btf_info.btf_size;
+	ptr = malloc(last_size);
+	if (!ptr) {
+		err = -ENOMEM;
+		goto exit_free;
+	}
+
+	bzero(ptr, last_size);
+	btf_info.btf = ptr_to_u64(ptr);
+	err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+
+	if (!err && btf_info.btf_size > last_size) {
+		void *temp_ptr;
+
+		last_size = btf_info.btf_size;
+		temp_ptr = realloc(ptr, last_size);
+		if (!temp_ptr) {
+			err = -ENOMEM;
+			goto exit_free;
+		}
+		ptr = temp_ptr;
+		bzero(ptr, last_size);
+		btf_info.btf = ptr_to_u64(ptr);
+		err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+	}
+
+	if (err || btf_info.btf_size > last_size) {
+		err = errno;
+		goto exit_free;
+	}
+
+	*btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL);
+	if (IS_ERR(*btf)) {
+		err = PTR_ERR(*btf);
+		*btf = NULL;
+	}
+
+exit_free:
+	close(btf_fd);
+	free(ptr);
+
+	return err;
+}
+
 static int btf_ext_validate_func_info(const void *finfo, __u32 size,
 				      btf_print_fn_t err_log)
 {
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 578171e8cb26..386b2ffc32a3 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -69,6 +69,7 @@ LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__fd(const struct btf *btf);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+LIBBPF_API int btf_get_from_id(__u32 id, struct btf **btf);
 
 struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
 void btf_ext__free(struct btf_ext *btf_ext);
-- 
cgit v1.2.3


From 999d82cbc04416cc7f2b5cb6daab947c16f0fd3a Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 19 Nov 2018 15:29:20 -0800
Subject: tools/bpf: enhance test_btf file testing to test func info

Change the bpf programs test_btf_haskv.c and test_btf_nokv.c to
have two sections, and enhance test_btf.c test_file feature
to test btf func_info returned by the kernel.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_btf.c       | 117 ++++++++++++++++++++++++---
 tools/testing/selftests/bpf/test_btf_haskv.c |  16 +++-
 tools/testing/selftests/bpf/test_btf_nokv.c  |  16 +++-
 3 files changed, 136 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 8fd3a16fea4d..7b1b160d6e67 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -2434,13 +2434,13 @@ static struct btf_file_test file_tests[] = {
 },
 };
 
-static int file_has_btf_elf(const char *fn)
+static int file_has_btf_elf(const char *fn, bool *has_btf_ext)
 {
 	Elf_Scn *scn = NULL;
 	GElf_Ehdr ehdr;
+	int ret = 0;
 	int elf_fd;
 	Elf *elf;
-	int ret;
 
 	if (CHECK(elf_version(EV_CURRENT) == EV_NONE,
 		  "elf_version(EV_CURRENT) == EV_NONE"))
@@ -2472,14 +2472,12 @@ static int file_has_btf_elf(const char *fn)
 		}
 
 		sh_name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
-		if (!strcmp(sh_name, BTF_ELF_SEC)) {
+		if (!strcmp(sh_name, BTF_ELF_SEC))
 			ret = 1;
-			goto done;
-		}
+		if (!strcmp(sh_name, BTF_EXT_ELF_SEC))
+			*has_btf_ext = true;
 	}
 
-	ret = 0;
-
 done:
 	close(elf_fd);
 	elf_end(elf);
@@ -2489,15 +2487,24 @@ done:
 static int do_test_file(unsigned int test_num)
 {
 	const struct btf_file_test *test = &file_tests[test_num - 1];
+	const char *expected_fnames[] = {"_dummy_tracepoint",
+					 "test_long_fname_1",
+					 "test_long_fname_2"};
+	struct bpf_prog_info info = {};
 	struct bpf_object *obj = NULL;
+	struct bpf_func_info *finfo;
 	struct bpf_program *prog;
+	__u32 info_len, rec_size;
+	bool has_btf_ext = false;
+	struct btf *btf = NULL;
+	void *func_info = NULL;
 	struct bpf_map *map;
-	int err;
+	int i, err, prog_fd;
 
 	fprintf(stderr, "BTF libbpf test[%u] (%s): ", test_num,
 		test->file);
 
-	err = file_has_btf_elf(test->file);
+	err = file_has_btf_elf(test->file, &has_btf_ext);
 	if (err == -1)
 		return err;
 
@@ -2525,6 +2532,7 @@ static int do_test_file(unsigned int test_num)
 	err = bpf_object__load(obj);
 	if (CHECK(err < 0, "bpf_object__load: %d", err))
 		goto done;
+	prog_fd = bpf_program__fd(prog);
 
 	map = bpf_object__find_map_by_name(obj, "btf_map");
 	if (CHECK(!map, "btf_map not found")) {
@@ -2539,9 +2547,100 @@ static int do_test_file(unsigned int test_num)
 		  test->btf_kv_notfound))
 		goto done;
 
+	if (!jit_enabled || !has_btf_ext)
+		goto skip_jit;
+
+	/* get necessary program info */
+	info_len = sizeof(struct bpf_prog_info);
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+
+	if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) {
+		fprintf(stderr, "%s\n", btf_log_buf);
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_cnt != 3,
+		  "incorrect info.func_info_cnt (1st) %d",
+		  info.func_info_cnt)) {
+		err = -1;
+		goto done;
+	}
+	rec_size = info.func_info_rec_size;
+	if (CHECK(rec_size < 4,
+		  "incorrect info.func_info_rec_size (1st) %d\n", rec_size)) {
+		err = -1;
+		goto done;
+	}
+
+	func_info = malloc(info.func_info_cnt * rec_size);
+	if (CHECK(!func_info, "out of memeory")) {
+		err = -1;
+		goto done;
+	}
+
+	/* reset info to only retrieve func_info related data */
+	memset(&info, 0, sizeof(info));
+	info.func_info_cnt = 3;
+	info.func_info_rec_size = rec_size;
+	info.func_info = ptr_to_u64(func_info);
+
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+
+	if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) {
+		fprintf(stderr, "%s\n", btf_log_buf);
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_cnt != 3,
+		  "incorrect info.func_info_cnt (2nd) %d",
+		  info.func_info_cnt)) {
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_rec_size != rec_size,
+		  "incorrect info.func_info_rec_size (2nd) %d",
+		  info.func_info_rec_size)) {
+		err = -1;
+		goto done;
+	}
+
+	err = btf_get_from_id(info.btf_id, &btf);
+	if (CHECK(err, "cannot get btf from kernel, err: %d", err))
+		goto done;
+
+	/* check three functions */
+	finfo = func_info;
+	for (i = 0; i < 3; i++) {
+		const struct btf_type *t;
+		const char *fname;
+
+		t = btf__type_by_id(btf, finfo->type_id);
+		if (CHECK(!t, "btf__type_by_id failure: id %u",
+			  finfo->type_id)) {
+			err = -1;
+			goto done;
+		}
+
+		fname = btf__name_by_offset(btf, t->name_off);
+		err = strcmp(fname, expected_fnames[i]);
+		/* for the second and third functions in .text section,
+		 * the compiler may order them either way.
+		 */
+		if (i && err)
+			err = strcmp(fname, expected_fnames[3 - i]);
+		if (CHECK(err, "incorrect fname %s", fname ? : "")) {
+			err = -1;
+			goto done;
+		}
+
+		finfo = (void *)finfo + rec_size;
+	}
+
+skip_jit:
 	fprintf(stderr, "OK");
 
 done:
+	free(func_info);
 	bpf_object__close(obj);
 	return err;
 }
diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c
index b21b876f475d..e5c79fe0ffdb 100644
--- a/tools/testing/selftests/bpf/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/test_btf_haskv.c
@@ -24,8 +24,8 @@ struct dummy_tracepoint_args {
 	struct sock *sock;
 };
 
-SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+__attribute__((noinline))
+static int test_long_fname_2(struct dummy_tracepoint_args *arg)
 {
 	struct ipv_counts *counts;
 	int key = 0;
@@ -42,4 +42,16 @@ int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
 	return 0;
 }
 
+__attribute__((noinline))
+static int test_long_fname_1(struct dummy_tracepoint_args *arg)
+{
+	return test_long_fname_2(arg);
+}
+
+SEC("dummy_tracepoint")
+int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+{
+	return test_long_fname_1(arg);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_btf_nokv.c b/tools/testing/selftests/bpf/test_btf_nokv.c
index 0ed8e088eebf..434188c37774 100644
--- a/tools/testing/selftests/bpf/test_btf_nokv.c
+++ b/tools/testing/selftests/bpf/test_btf_nokv.c
@@ -22,8 +22,8 @@ struct dummy_tracepoint_args {
 	struct sock *sock;
 };
 
-SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+__attribute__((noinline))
+static int test_long_fname_2(struct dummy_tracepoint_args *arg)
 {
 	struct ipv_counts *counts;
 	int key = 0;
@@ -40,4 +40,16 @@ int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
 	return 0;
 }
 
+__attribute__((noinline))
+static int test_long_fname_1(struct dummy_tracepoint_args *arg)
+{
+	return test_long_fname_2(arg);
+}
+
+SEC("dummy_tracepoint")
+int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+{
+	return test_long_fname_1(arg);
+}
+
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 254471e57a86b8dc1a2cc19848e99f5d7c0558f4 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 19 Nov 2018 15:29:21 -0800
Subject: tools/bpf: bpftool: add support for func types

This patch added support to print function signature
if btf func_info is available. Note that ksym
now uses function name instead of prog_name as
prog_name has a limit of 16 bytes including
ending '\0'.

The following is a sample output for selftests
test_btf with file test_btf_haskv.o for translated insns
and jited insns respectively.

  $ bpftool prog dump xlated id 1
  int _dummy_tracepoint(struct dummy_tracepoint_args * arg):
     0: (85) call pc+2#bpf_prog_2dcecc18072623fc_test_long_fname_1
     1: (b7) r0 = 0
     2: (95) exit
  int test_long_fname_1(struct dummy_tracepoint_args * arg):
     3: (85) call pc+1#bpf_prog_89d64e4abf0f0126_test_long_fname_2
     4: (95) exit
  int test_long_fname_2(struct dummy_tracepoint_args * arg):
     5: (b7) r2 = 0
     6: (63) *(u32 *)(r10 -4) = r2
     7: (79) r1 = *(u64 *)(r1 +8)
     ...
     22: (07) r1 += 1
     23: (63) *(u32 *)(r0 +4) = r1
     24: (95) exit

  $ bpftool prog dump jited id 1
  int _dummy_tracepoint(struct dummy_tracepoint_args * arg):
  bpf_prog_b07ccb89267cf242__dummy_tracepoint:
     0:   push   %rbp
     1:   mov    %rsp,%rbp
    ......
    3c:   add    $0x28,%rbp
    40:   leaveq
    41:   retq

  int test_long_fname_1(struct dummy_tracepoint_args * arg):
  bpf_prog_2dcecc18072623fc_test_long_fname_1:
     0:   push   %rbp
     1:   mov    %rsp,%rbp
    ......
    3a:   add    $0x28,%rbp
    3e:   leaveq
    3f:   retq

  int test_long_fname_2(struct dummy_tracepoint_args * arg):
  bpf_prog_89d64e4abf0f0126_test_long_fname_2:
     0:   push   %rbp
     1:   mov    %rsp,%rbp
    ......
    80:   add    $0x28,%rbp
    84:   leaveq
    85:   retq

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/btf_dumper.c    | 136 ++++++++++++++++++++++++++++++++++++++
 tools/bpf/bpftool/main.h          |   2 +
 tools/bpf/bpftool/prog.c          |  56 ++++++++++++++++
 tools/bpf/bpftool/xlated_dumper.c |  33 +++++++++
 tools/bpf/bpftool/xlated_dumper.h |   3 +
 5 files changed, 230 insertions(+)

diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index 55bc512a1831..c3fd3a7cb787 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -249,3 +249,139 @@ int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
 {
 	return btf_dumper_do_type(d, type_id, 0, data);
 }
+
+#define BTF_PRINT_ARG(...)						\
+	do {								\
+		pos += snprintf(func_sig + pos, size - pos,		\
+				__VA_ARGS__);				\
+		if (pos >= size)					\
+			return -1;					\
+	} while (0)
+#define BTF_PRINT_TYPE(type)					\
+	do {								\
+		pos = __btf_dumper_type_only(btf, type, func_sig,	\
+					     pos, size);		\
+		if (pos == -1)						\
+			return -1;					\
+	} while (0)
+
+static int btf_dump_func(const struct btf *btf, char *func_sig,
+			 const struct btf_type *func_proto,
+			 const struct btf_type *func, int pos, int size);
+
+static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
+				  char *func_sig, int pos, int size)
+{
+	const struct btf_type *proto_type;
+	const struct btf_array *array;
+	const struct btf_type *t;
+
+	if (!type_id) {
+		BTF_PRINT_ARG("void ");
+		return pos;
+	}
+
+	t = btf__type_by_id(btf, type_id);
+
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_INT:
+		BTF_PRINT_ARG("%s ", btf__name_by_offset(btf, t->name_off));
+		break;
+	case BTF_KIND_STRUCT:
+		BTF_PRINT_ARG("struct %s ",
+			      btf__name_by_offset(btf, t->name_off));
+		break;
+	case BTF_KIND_UNION:
+		BTF_PRINT_ARG("union %s ",
+			      btf__name_by_offset(btf, t->name_off));
+		break;
+	case BTF_KIND_ENUM:
+		BTF_PRINT_ARG("enum %s ",
+			      btf__name_by_offset(btf, t->name_off));
+		break;
+	case BTF_KIND_ARRAY:
+		array = (struct btf_array *)(t + 1);
+		BTF_PRINT_TYPE(array->type);
+		BTF_PRINT_ARG("[%d]", array->nelems);
+		break;
+	case BTF_KIND_PTR:
+		BTF_PRINT_TYPE(t->type);
+		BTF_PRINT_ARG("* ");
+		break;
+	case BTF_KIND_UNKN:
+	case BTF_KIND_FWD:
+	case BTF_KIND_TYPEDEF:
+		return -1;
+	case BTF_KIND_VOLATILE:
+		BTF_PRINT_ARG("volatile ");
+		BTF_PRINT_TYPE(t->type);
+		break;
+	case BTF_KIND_CONST:
+		BTF_PRINT_ARG("const ");
+		BTF_PRINT_TYPE(t->type);
+		break;
+	case BTF_KIND_RESTRICT:
+		BTF_PRINT_ARG("restrict ");
+		BTF_PRINT_TYPE(t->type);
+		break;
+	case BTF_KIND_FUNC_PROTO:
+		pos = btf_dump_func(btf, func_sig, t, NULL, pos, size);
+		if (pos == -1)
+			return -1;
+		break;
+	case BTF_KIND_FUNC:
+		proto_type = btf__type_by_id(btf, t->type);
+		pos = btf_dump_func(btf, func_sig, proto_type, t, pos, size);
+		if (pos == -1)
+			return -1;
+		break;
+	default:
+		return -1;
+	}
+
+	return pos;
+}
+
+static int btf_dump_func(const struct btf *btf, char *func_sig,
+			 const struct btf_type *func_proto,
+			 const struct btf_type *func, int pos, int size)
+{
+	int i, vlen;
+
+	BTF_PRINT_TYPE(func_proto->type);
+	if (func)
+		BTF_PRINT_ARG("%s(", btf__name_by_offset(btf, func->name_off));
+	else
+		BTF_PRINT_ARG("(");
+	vlen = BTF_INFO_VLEN(func_proto->info);
+	for (i = 0; i < vlen; i++) {
+		struct btf_param *arg = &((struct btf_param *)(func_proto + 1))[i];
+
+		if (i)
+			BTF_PRINT_ARG(", ");
+		if (arg->type) {
+			BTF_PRINT_TYPE(arg->type);
+			BTF_PRINT_ARG("%s",
+				      btf__name_by_offset(btf, arg->name_off));
+		} else {
+			BTF_PRINT_ARG("...");
+		}
+	}
+	BTF_PRINT_ARG(")");
+
+	return pos;
+}
+
+void btf_dumper_type_only(const struct btf *btf, __u32 type_id, char *func_sig,
+			  int size)
+{
+	int err;
+
+	func_sig[0] = '\0';
+	if (!btf)
+		return;
+
+	err = __btf_dumper_type_only(btf, type_id, func_sig, 0, size);
+	if (err < 0)
+		func_sig[0] = '\0';
+}
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 10c6c16fae29..3e8979567cf1 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -187,6 +187,8 @@ struct btf_dumper {
  */
 int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
 		    const void *data);
+void btf_dumper_type_only(const struct btf *btf, __u32 func_type_id,
+			  char *func_only, int size);
 
 struct nlattr;
 struct ifinfomsg;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index c176e1aa66fe..37b1daf19da6 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -47,6 +47,7 @@
 #include <linux/err.h>
 
 #include <bpf.h>
+#include <btf.h>
 #include <libbpf.h>
 
 #include "cfg.h"
@@ -451,14 +452,19 @@ static int do_dump(int argc, char **argv)
 	struct bpf_prog_info info = {};
 	unsigned int *func_lens = NULL;
 	const char *disasm_opt = NULL;
+	unsigned int finfo_rec_size;
 	unsigned int nr_func_ksyms;
 	unsigned int nr_func_lens;
 	struct dump_data dd = {};
 	__u32 len = sizeof(info);
+	struct btf *btf = NULL;
+	void *func_info = NULL;
+	unsigned int finfo_cnt;
 	unsigned int buf_size;
 	char *filepath = NULL;
 	bool opcodes = false;
 	bool visual = false;
+	char func_sig[1024];
 	unsigned char *buf;
 	__u32 *member_len;
 	__u64 *member_ptr;
@@ -551,6 +557,17 @@ static int do_dump(int argc, char **argv)
 		}
 	}
 
+	finfo_cnt = info.func_info_cnt;
+	finfo_rec_size = info.func_info_rec_size;
+	if (finfo_cnt && finfo_rec_size) {
+		func_info = malloc(finfo_cnt * finfo_rec_size);
+		if (!func_info) {
+			p_err("mem alloc failed");
+			close(fd);
+			goto err_free;
+		}
+	}
+
 	memset(&info, 0, sizeof(info));
 
 	*member_ptr = ptr_to_u64(buf);
@@ -559,6 +576,9 @@ static int do_dump(int argc, char **argv)
 	info.nr_jited_ksyms = nr_func_ksyms;
 	info.jited_func_lens = ptr_to_u64(func_lens);
 	info.nr_jited_func_lens = nr_func_lens;
+	info.func_info_cnt = finfo_cnt;
+	info.func_info_rec_size = finfo_rec_size;
+	info.func_info = ptr_to_u64(func_info);
 
 	err = bpf_obj_get_info_by_fd(fd, &info, &len);
 	close(fd);
@@ -582,6 +602,18 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
+	if (info.func_info_cnt != finfo_cnt) {
+		p_err("incorrect func_info_cnt %d vs. expected %d",
+		      info.func_info_cnt, finfo_cnt);
+		goto err_free;
+	}
+
+	if (info.func_info_rec_size != finfo_rec_size) {
+		p_err("incorrect func_info_rec_size %d vs. expected %d",
+		      info.func_info_rec_size, finfo_rec_size);
+		goto err_free;
+	}
+
 	if ((member_len == &info.jited_prog_len &&
 	     info.jited_prog_insns == 0) ||
 	    (member_len == &info.xlated_prog_len &&
@@ -590,6 +622,11 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
+	if (info.btf_id && btf_get_from_id(info.btf_id, &btf)) {
+		p_err("failed to get btf");
+		goto err_free;
+	}
+
 	if (filepath) {
 		fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600);
 		if (fd < 0) {
@@ -622,6 +659,7 @@ static int do_dump(int argc, char **argv)
 
 		if (info.nr_jited_func_lens && info.jited_func_lens) {
 			struct kernel_sym *sym = NULL;
+			struct bpf_func_info *record;
 			char sym_name[SYM_MAX_NAME];
 			unsigned char *img = buf;
 			__u64 *ksyms = NULL;
@@ -648,12 +686,25 @@ static int do_dump(int argc, char **argv)
 					strcpy(sym_name, "unknown");
 				}
 
+				if (func_info) {
+					record = func_info + i * finfo_rec_size;
+					btf_dumper_type_only(btf, record->type_id,
+							     func_sig,
+							     sizeof(func_sig));
+				}
+
 				if (json_output) {
 					jsonw_start_object(json_wtr);
+					if (func_info && func_sig[0] != '\0') {
+						jsonw_name(json_wtr, "proto");
+						jsonw_string(json_wtr, func_sig);
+					}
 					jsonw_name(json_wtr, "name");
 					jsonw_string(json_wtr, sym_name);
 					jsonw_name(json_wtr, "insns");
 				} else {
+					if (func_info && func_sig[0] != '\0')
+						printf("%s:\n", func_sig);
 					printf("%s:\n", sym_name);
 				}
 
@@ -682,6 +733,9 @@ static int do_dump(int argc, char **argv)
 		kernel_syms_load(&dd);
 		dd.nr_jited_ksyms = info.nr_jited_ksyms;
 		dd.jited_ksyms = (__u64 *) info.jited_ksyms;
+		dd.btf = btf;
+		dd.func_info = func_info;
+		dd.finfo_rec_size = finfo_rec_size;
 
 		if (json_output)
 			dump_xlated_json(&dd, buf, *member_len, opcodes);
@@ -693,12 +747,14 @@ static int do_dump(int argc, char **argv)
 	free(buf);
 	free(func_ksyms);
 	free(func_lens);
+	free(func_info);
 	return 0;
 
 err_free:
 	free(buf);
 	free(func_ksyms);
 	free(func_lens);
+	free(func_info);
 	return -1;
 }
 
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 3284759df98a..e06ac0286a75 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -242,11 +242,15 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len,
 		.cb_imm		= print_imm,
 		.private_data	= dd,
 	};
+	struct bpf_func_info *record;
 	struct bpf_insn *insn = buf;
+	struct btf *btf = dd->btf;
 	bool double_insn = false;
+	char func_sig[1024];
 	unsigned int i;
 
 	jsonw_start_array(json_wtr);
+	record = dd->func_info;
 	for (i = 0; i < len / sizeof(*insn); i++) {
 		if (double_insn) {
 			double_insn = false;
@@ -255,6 +259,20 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len,
 		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
 
 		jsonw_start_object(json_wtr);
+
+		if (btf && record) {
+			if (record->insn_offset == i) {
+				btf_dumper_type_only(btf, record->type_id,
+						     func_sig,
+						     sizeof(func_sig));
+				if (func_sig[0] != '\0') {
+					jsonw_name(json_wtr, "proto");
+					jsonw_string(json_wtr, func_sig);
+				}
+				record = (void *)record + dd->finfo_rec_size;
+			}
+		}
+
 		jsonw_name(json_wtr, "disasm");
 		print_bpf_insn(&cbs, insn + i, true);
 
@@ -297,16 +315,31 @@ void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len,
 		.cb_imm		= print_imm,
 		.private_data	= dd,
 	};
+	struct bpf_func_info *record;
 	struct bpf_insn *insn = buf;
+	struct btf *btf = dd->btf;
 	bool double_insn = false;
+	char func_sig[1024];
 	unsigned int i;
 
+	record = dd->func_info;
 	for (i = 0; i < len / sizeof(*insn); i++) {
 		if (double_insn) {
 			double_insn = false;
 			continue;
 		}
 
+		if (btf && record) {
+			if (record->insn_offset == i) {
+				btf_dumper_type_only(btf, record->type_id,
+						     func_sig,
+						     sizeof(func_sig));
+				if (func_sig[0] != '\0')
+					printf("%s:\n", func_sig);
+				record = (void *)record + dd->finfo_rec_size;
+			}
+		}
+
 		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
 
 		printf("% 4d: ", i);
diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h
index 33d86e2b369b..aec31723e1e5 100644
--- a/tools/bpf/bpftool/xlated_dumper.h
+++ b/tools/bpf/bpftool/xlated_dumper.h
@@ -51,6 +51,9 @@ struct dump_data {
 	__u32 sym_count;
 	__u64 *jited_ksyms;
 	__u32 nr_jited_ksyms;
+	struct btf *btf;
+	void *func_info;
+	__u32 finfo_rec_size;
 	char scratch_buff[SYM_MAX_NAME + 8];
 };
 
-- 
cgit v1.2.3


From d38b08834fc35720ad685e9e2f6d865f681fbc34 Mon Sep 17 00:00:00 2001
From: Akeem G Abodunrin <akeem.g.abodunrin@intel.com>
Date: Fri, 26 Oct 2018 11:44:38 -0700
Subject: ice: Do autoneg based on VSI state

If VSI state is up, we should do autoneg with link up, otherwise
with link down.

Signed-off-by: Akeem G Abodunrin <akeem.g.abodunrin@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 648acdb4c644..4d3e3113741d 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -1392,17 +1392,17 @@ static int ice_nway_reset(struct net_device *netdev)
 {
 	/* restart autonegotiation */
 	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_link_status *hw_link_info;
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_port_info *pi;
 	enum ice_status status;
-	bool link_up;
 
 	pi = vsi->port_info;
-	hw_link_info = &pi->phy.link_info;
-	link_up = hw_link_info->link_info & ICE_AQ_LINK_UP;
+	/* If VSI state is up, then restart autoneg with link up */
+	if (!test_bit(__ICE_DOWN, vsi->back->state))
+		status = ice_aq_set_link_restart_an(pi, true, NULL);
+	else
+		status = ice_aq_set_link_restart_an(pi, false, NULL);
 
-	status = ice_aq_set_link_restart_an(pi, link_up, NULL);
 	if (status) {
 		netdev_info(netdev, "link restart failed, err %d aq_err %d\n",
 			    status, pi->hw->adminq.sq_last_status);
-- 
cgit v1.2.3


From 7afdbc903a7c22510bbf5a82866e1a607e2f0997 Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Fri, 26 Oct 2018 11:44:39 -0700
Subject: ice: Cleanup duplicate control queue code

1. Assigning the register offset and mask values contains duplicate code
   that can easily be replaced with a macro.

2. Separate functions for freeing send queue and receive queue rings are
   not needed; replace with a single function that uses a pointer to the
   struct ice_ctl_q_ring structure as a parameter instead of a pointer to
   the struct ice_ctl_q_info structure.

3. Initializing register settings for both send queue and receive queue
   contains duplicate code that can easily be replaced with a helper
   function.

4. Separate functions for freeing send queue and receive queue buffers are
   not needed; duplicate code can easily be replaced with a macro.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_controlq.c | 218 +++++++++-----------------
 1 file changed, 76 insertions(+), 142 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 84c967294eaf..b920403c6616 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -3,6 +3,26 @@
 
 #include "ice_common.h"
 
+#define ICE_CQ_INIT_REGS(qinfo, prefix)				\
+do {								\
+	(qinfo)->sq.head = prefix##_ATQH;			\
+	(qinfo)->sq.tail = prefix##_ATQT;			\
+	(qinfo)->sq.len = prefix##_ATQLEN;			\
+	(qinfo)->sq.bah = prefix##_ATQBAH;			\
+	(qinfo)->sq.bal = prefix##_ATQBAL;			\
+	(qinfo)->sq.len_mask = prefix##_ATQLEN_ATQLEN_M;	\
+	(qinfo)->sq.len_ena_mask = prefix##_ATQLEN_ATQENABLE_M;	\
+	(qinfo)->sq.head_mask = prefix##_ATQH_ATQH_M;		\
+	(qinfo)->rq.head = prefix##_ARQH;			\
+	(qinfo)->rq.tail = prefix##_ARQT;			\
+	(qinfo)->rq.len = prefix##_ARQLEN;			\
+	(qinfo)->rq.bah = prefix##_ARQBAH;			\
+	(qinfo)->rq.bal = prefix##_ARQBAL;			\
+	(qinfo)->rq.len_mask = prefix##_ARQLEN_ARQLEN_M;	\
+	(qinfo)->rq.len_ena_mask = prefix##_ARQLEN_ARQENABLE_M;	\
+	(qinfo)->rq.head_mask = prefix##_ARQH_ARQH_M;		\
+} while (0)
+
 /**
  * ice_adminq_init_regs - Initialize AdminQ registers
  * @hw: pointer to the hardware structure
@@ -13,23 +33,7 @@ static void ice_adminq_init_regs(struct ice_hw *hw)
 {
 	struct ice_ctl_q_info *cq = &hw->adminq;
 
-	cq->sq.head = PF_FW_ATQH;
-	cq->sq.tail = PF_FW_ATQT;
-	cq->sq.len = PF_FW_ATQLEN;
-	cq->sq.bah = PF_FW_ATQBAH;
-	cq->sq.bal = PF_FW_ATQBAL;
-	cq->sq.len_mask = PF_FW_ATQLEN_ATQLEN_M;
-	cq->sq.len_ena_mask = PF_FW_ATQLEN_ATQENABLE_M;
-	cq->sq.head_mask = PF_FW_ATQH_ATQH_M;
-
-	cq->rq.head = PF_FW_ARQH;
-	cq->rq.tail = PF_FW_ARQT;
-	cq->rq.len = PF_FW_ARQLEN;
-	cq->rq.bah = PF_FW_ARQBAH;
-	cq->rq.bal = PF_FW_ARQBAL;
-	cq->rq.len_mask = PF_FW_ARQLEN_ARQLEN_M;
-	cq->rq.len_ena_mask = PF_FW_ARQLEN_ARQENABLE_M;
-	cq->rq.head_mask = PF_FW_ARQH_ARQH_M;
+	ICE_CQ_INIT_REGS(cq, PF_FW);
 }
 
 /**
@@ -42,24 +46,7 @@ static void ice_mailbox_init_regs(struct ice_hw *hw)
 {
 	struct ice_ctl_q_info *cq = &hw->mailboxq;
 
-	/* set head and tail registers in our local struct */
-	cq->sq.head = PF_MBX_ATQH;
-	cq->sq.tail = PF_MBX_ATQT;
-	cq->sq.len = PF_MBX_ATQLEN;
-	cq->sq.bah = PF_MBX_ATQBAH;
-	cq->sq.bal = PF_MBX_ATQBAL;
-	cq->sq.len_mask = PF_MBX_ATQLEN_ATQLEN_M;
-	cq->sq.len_ena_mask = PF_MBX_ATQLEN_ATQENABLE_M;
-	cq->sq.head_mask = PF_MBX_ATQH_ATQH_M;
-
-	cq->rq.head = PF_MBX_ARQH;
-	cq->rq.tail = PF_MBX_ARQT;
-	cq->rq.len = PF_MBX_ARQLEN;
-	cq->rq.bah = PF_MBX_ARQBAH;
-	cq->rq.bal = PF_MBX_ARQBAL;
-	cq->rq.len_mask = PF_MBX_ARQLEN_ARQLEN_M;
-	cq->rq.len_ena_mask = PF_MBX_ARQLEN_ARQENABLE_M;
-	cq->rq.head_mask = PF_MBX_ARQH_ARQH_M;
+	ICE_CQ_INIT_REGS(cq, PF_MBX);
 }
 
 /**
@@ -131,37 +118,20 @@ ice_alloc_ctrlq_rq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 }
 
 /**
- * ice_free_ctrlq_sq_ring - Free Control Transmit Queue (ATQ) rings
- * @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
- *
- * This assumes the posted send buffers have already been cleaned
- * and de-allocated
- */
-static void ice_free_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
-{
-	dmam_free_coherent(ice_hw_to_dev(hw), cq->sq.desc_buf.size,
-			   cq->sq.desc_buf.va, cq->sq.desc_buf.pa);
-	cq->sq.desc_buf.va = NULL;
-	cq->sq.desc_buf.pa = 0;
-	cq->sq.desc_buf.size = 0;
-}
-
-/**
- * ice_free_ctrlq_rq_ring - Free Control Receive Queue (ARQ) rings
+ * ice_free_cq_ring - Free control queue ring
  * @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
+ * @ring: pointer to the specific control queue ring
  *
- * This assumes the posted receive buffers have already been cleaned
+ * This assumes the posted buffers have already been cleaned
  * and de-allocated
  */
-static void ice_free_ctrlq_rq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
+static void ice_free_cq_ring(struct ice_hw *hw, struct ice_ctl_q_ring *ring)
 {
-	dmam_free_coherent(ice_hw_to_dev(hw), cq->rq.desc_buf.size,
-			   cq->rq.desc_buf.va, cq->rq.desc_buf.pa);
-	cq->rq.desc_buf.va = NULL;
-	cq->rq.desc_buf.pa = 0;
-	cq->rq.desc_buf.size = 0;
+	dmam_free_coherent(ice_hw_to_dev(hw), ring->desc_buf.size,
+			   ring->desc_buf.va, ring->desc_buf.pa);
+	ring->desc_buf.va = NULL;
+	ring->desc_buf.pa = 0;
+	ring->desc_buf.size = 0;
 }
 
 /**
@@ -280,54 +250,23 @@ unwind_alloc_sq_bufs:
 	return ICE_ERR_NO_MEMORY;
 }
 
-/**
- * ice_free_rq_bufs - Free ARQ buffer info elements
- * @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
- */
-static void ice_free_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
-{
-	int i;
-
-	/* free descriptors */
-	for (i = 0; i < cq->num_rq_entries; i++) {
-		dmam_free_coherent(ice_hw_to_dev(hw), cq->rq.r.rq_bi[i].size,
-				   cq->rq.r.rq_bi[i].va, cq->rq.r.rq_bi[i].pa);
-		cq->rq.r.rq_bi[i].va = NULL;
-		cq->rq.r.rq_bi[i].pa = 0;
-		cq->rq.r.rq_bi[i].size = 0;
-	}
-
-	/* free the dma header */
-	devm_kfree(ice_hw_to_dev(hw), cq->rq.dma_head);
-}
-
-/**
- * ice_free_sq_bufs - Free ATQ buffer info elements
- * @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
- */
-static void ice_free_sq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
+static enum ice_status
+ice_cfg_cq_regs(struct ice_hw *hw, struct ice_ctl_q_ring *ring, u16 num_entries)
 {
-	int i;
+	/* Clear Head and Tail */
+	wr32(hw, ring->head, 0);
+	wr32(hw, ring->tail, 0);
 
-	/* only unmap if the address is non-NULL */
-	for (i = 0; i < cq->num_sq_entries; i++)
-		if (cq->sq.r.sq_bi[i].pa) {
-			dmam_free_coherent(ice_hw_to_dev(hw),
-					   cq->sq.r.sq_bi[i].size,
-					   cq->sq.r.sq_bi[i].va,
-					   cq->sq.r.sq_bi[i].pa);
-			cq->sq.r.sq_bi[i].va = NULL;
-			cq->sq.r.sq_bi[i].pa = 0;
-			cq->sq.r.sq_bi[i].size = 0;
-		}
+	/* set starting point */
+	wr32(hw, ring->len, (num_entries | ring->len_ena_mask));
+	wr32(hw, ring->bal, lower_32_bits(ring->desc_buf.pa));
+	wr32(hw, ring->bah, upper_32_bits(ring->desc_buf.pa));
 
-	/* free the buffer info list */
-	devm_kfree(ice_hw_to_dev(hw), cq->sq.cmd_buf);
+	/* Check one register to verify that config was applied */
+	if (rd32(hw, ring->bal) != lower_32_bits(ring->desc_buf.pa))
+		return ICE_ERR_AQ_ERROR;
 
-	/* free the dma header */
-	devm_kfree(ice_hw_to_dev(hw), cq->sq.dma_head);
+	return 0;
 }
 
 /**
@@ -340,23 +279,7 @@ static void ice_free_sq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 static enum ice_status
 ice_cfg_sq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
-	u32 reg = 0;
-
-	/* Clear Head and Tail */
-	wr32(hw, cq->sq.head, 0);
-	wr32(hw, cq->sq.tail, 0);
-
-	/* set starting point */
-	wr32(hw, cq->sq.len, (cq->num_sq_entries | cq->sq.len_ena_mask));
-	wr32(hw, cq->sq.bal, lower_32_bits(cq->sq.desc_buf.pa));
-	wr32(hw, cq->sq.bah, upper_32_bits(cq->sq.desc_buf.pa));
-
-	/* Check one register to verify that config was applied */
-	reg = rd32(hw, cq->sq.bal);
-	if (reg != lower_32_bits(cq->sq.desc_buf.pa))
-		return ICE_ERR_AQ_ERROR;
-
-	return 0;
+	return ice_cfg_cq_regs(hw, &cq->sq, cq->num_sq_entries);
 }
 
 /**
@@ -369,25 +292,15 @@ ice_cfg_sq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 static enum ice_status
 ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
-	u32 reg = 0;
-
-	/* Clear Head and Tail */
-	wr32(hw, cq->rq.head, 0);
-	wr32(hw, cq->rq.tail, 0);
+	enum ice_status status;
 
-	/* set starting point */
-	wr32(hw, cq->rq.len, (cq->num_rq_entries | cq->rq.len_ena_mask));
-	wr32(hw, cq->rq.bal, lower_32_bits(cq->rq.desc_buf.pa));
-	wr32(hw, cq->rq.bah, upper_32_bits(cq->rq.desc_buf.pa));
+	status = ice_cfg_cq_regs(hw, &cq->rq, cq->num_rq_entries);
+	if (status)
+		return status;
 
 	/* Update tail in the HW to post pre-allocated buffers */
 	wr32(hw, cq->rq.tail, (u32)(cq->num_rq_entries - 1));
 
-	/* Check one register to verify that config was applied */
-	reg = rd32(hw, cq->rq.bal);
-	if (reg != lower_32_bits(cq->rq.desc_buf.pa))
-		return ICE_ERR_AQ_ERROR;
-
 	return 0;
 }
 
@@ -444,7 +357,7 @@ static enum ice_status ice_init_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	goto init_ctrlq_exit;
 
 init_ctrlq_free_rings:
-	ice_free_ctrlq_sq_ring(hw, cq);
+	ice_free_cq_ring(hw, &cq->sq);
 
 init_ctrlq_exit:
 	return ret_code;
@@ -503,12 +416,33 @@ static enum ice_status ice_init_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	goto init_ctrlq_exit;
 
 init_ctrlq_free_rings:
-	ice_free_ctrlq_rq_ring(hw, cq);
+	ice_free_cq_ring(hw, &cq->rq);
 
 init_ctrlq_exit:
 	return ret_code;
 }
 
+#define ICE_FREE_CQ_BUFS(hw, qi, ring)					\
+do {									\
+	int i;								\
+	/* free descriptors */						\
+	for (i = 0; i < (qi)->num_##ring##_entries; i++)		\
+		if ((qi)->ring.r.ring##_bi[i].pa) {			\
+			dmam_free_coherent(ice_hw_to_dev(hw),		\
+					   (qi)->ring.r.ring##_bi[i].size,\
+					   (qi)->ring.r.ring##_bi[i].va,\
+					   (qi)->ring.r.ring##_bi[i].pa);\
+			(qi)->ring.r.ring##_bi[i].va = NULL;		\
+			(qi)->ring.r.ring##_bi[i].pa = 0;		\
+			(qi)->ring.r.ring##_bi[i].size = 0;		\
+		}							\
+	/* free the buffer info list */					\
+	if ((qi)->ring.cmd_buf)						\
+		devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf);	\
+	/* free dma head */						\
+	devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head);		\
+} while (0)
+
 /**
  * ice_shutdown_sq - shutdown the Control ATQ
  * @hw: pointer to the hardware structure
@@ -538,8 +472,8 @@ ice_shutdown_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	cq->sq.count = 0;	/* to indicate uninitialized queue */
 
 	/* free ring buffers and the ring itself */
-	ice_free_sq_bufs(hw, cq);
-	ice_free_ctrlq_sq_ring(hw, cq);
+	ICE_FREE_CQ_BUFS(hw, cq, sq);
+	ice_free_cq_ring(hw, &cq->sq);
 
 shutdown_sq_out:
 	mutex_unlock(&cq->sq_lock);
@@ -606,8 +540,8 @@ ice_shutdown_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	cq->rq.count = 0;
 
 	/* free ring buffers and the ring itself */
-	ice_free_rq_bufs(hw, cq);
-	ice_free_ctrlq_rq_ring(hw, cq);
+	ICE_FREE_CQ_BUFS(hw, cq, rq);
+	ice_free_cq_ring(hw, &cq->rq);
 
 shutdown_rq_out:
 	mutex_unlock(&cq->rq_lock);
-- 
cgit v1.2.3


From 5fb597d7c83310716be185f36a8b153e2457ea7f Mon Sep 17 00:00:00 2001
From: Jaroslaw Ilgiewicz <jaroslaw.ilgiewicz@intel.com>
Date: Fri, 26 Oct 2018 11:44:40 -0700
Subject: ice: Pass the return value of ice_init_def_sw_recp()

Added check of return value for ice_init_def_sw_recp().
Now we know if memory was correctly allocated.

Signed-off-by: Jaroslaw Ilgiewicz <jaroslaw.ilgiewicz@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 9de5a3aac77d..0b528602c4c9 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -405,9 +405,7 @@ static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw)
 
 	INIT_LIST_HEAD(&sw->vsi_list_map_head);
 
-	ice_init_def_sw_recp(hw);
-
-	return 0;
+	return ice_init_def_sw_recp(hw);
 }
 
 /**
-- 
cgit v1.2.3


From 6a7e69936992104e7abbf12c7f619a39bf139a48 Mon Sep 17 00:00:00 2001
From: Yashaswini Raghuram Prathivadi Bhayankaram
 <yashaswini.raghuram.prathivadi.bhayankaram@intel.com>
Date: Fri, 26 Oct 2018 11:44:41 -0700
Subject: ice: Do not set LAN_EN for MAC-VLAN filters

In the action fields for a MAC-VLAN filter, do not set the LAN_EN flag
if the MAC in the MAC-VLAN is unicast MAC. The unicast packets that
match should not be forwarded to the wire.

Signed-off-by: Yashaswini Raghuram Prathivadi Bhayankaram <yashaswini.raghuram.prathivadi.bhayankaram@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_switch.c | 37 +++++++++++++++++++----------
 1 file changed, 24 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 40c9c6558956..107ca08899b6 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -629,25 +629,36 @@ enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw)
 /**
  * ice_fill_sw_info - Helper function to populate lb_en and lan_en
  * @hw: pointer to the hardware structure
- * @f_info: filter info structure to fill/update
+ * @fi: filter info structure to fill/update
  *
  * This helper function populates the lb_en and lan_en elements of the provided
  * ice_fltr_info struct using the switch's type and characteristics of the
  * switch rule being configured.
  */
-static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *f_info)
+static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi)
 {
-	f_info->lb_en = false;
-	f_info->lan_en = false;
-	if ((f_info->flag & ICE_FLTR_TX) &&
-	    (f_info->fltr_act == ICE_FWD_TO_VSI ||
-	     f_info->fltr_act == ICE_FWD_TO_VSI_LIST ||
-	     f_info->fltr_act == ICE_FWD_TO_Q ||
-	     f_info->fltr_act == ICE_FWD_TO_QGRP)) {
-		f_info->lb_en = true;
-		if (!(hw->evb_veb && f_info->lkup_type == ICE_SW_LKUP_MAC &&
-		      is_unicast_ether_addr(f_info->l_data.mac.mac_addr)))
-			f_info->lan_en = true;
+	fi->lb_en = false;
+	fi->lan_en = false;
+	if ((fi->flag & ICE_FLTR_TX) &&
+	    (fi->fltr_act == ICE_FWD_TO_VSI ||
+	     fi->fltr_act == ICE_FWD_TO_VSI_LIST ||
+	     fi->fltr_act == ICE_FWD_TO_Q ||
+	     fi->fltr_act == ICE_FWD_TO_QGRP)) {
+		fi->lb_en = true;
+		/* Do not set lan_en to TRUE if
+		 * 1. The switch is a VEB AND
+		 * 2
+		 * 2.1 The lookup is MAC with unicast addr for MAC, OR
+		 * 2.2 The lookup is MAC_VLAN with unicast addr for MAC
+		 *
+		 * In all other cases, the LAN enable has to be set to true.
+		 */
+		if (!(hw->evb_veb &&
+		      ((fi->lkup_type == ICE_SW_LKUP_MAC &&
+			is_unicast_ether_addr(fi->l_data.mac.mac_addr)) ||
+		       (fi->lkup_type == ICE_SW_LKUP_MAC_VLAN &&
+			is_unicast_ether_addr(fi->l_data.mac_vlan.mac_addr)))))
+			fi->lan_en = true;
 	}
 }
 
-- 
cgit v1.2.3


From 55aa141ed909711939ee4546b85d09d2f2894532 Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Fri, 26 Oct 2018 11:44:42 -0700
Subject: ice: Constify global structures that can/should be

Indicate these structs should not be modified and take advantage of some
compiler optimizations by making these structs const.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 4d3e3113741d..990d660f527a 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -62,7 +62,7 @@ static const struct ice_stats ice_gstrings_vsi_stats[] = {
  * The PF_STATs are appended to the netdev stats only when ethtool -S
  * is queried on the base PF netdev.
  */
-static struct ice_stats ice_gstrings_pf_stats[] = {
+static const struct ice_stats ice_gstrings_pf_stats[] = {
 	ICE_PF_STAT("tx_bytes", stats.eth.tx_bytes),
 	ICE_PF_STAT("rx_bytes", stats.eth.rx_bytes),
 	ICE_PF_STAT("tx_unicast", stats.eth.tx_unicast),
@@ -104,7 +104,7 @@ static struct ice_stats ice_gstrings_pf_stats[] = {
 	ICE_PF_STAT("mac_remote_faults", stats.mac_remote_faults),
 };
 
-static u32 ice_regs_dump_list[] = {
+static const u32 ice_regs_dump_list[] = {
 	PFGEN_STATE,
 	PRTGEN_STATUS,
 	QRX_CTRL(0),
-- 
cgit v1.2.3


From e0c9fd9b77a7334032ec407d9e14d7c3cac1ac4f Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Fri, 26 Oct 2018 11:44:43 -0700
Subject: ice: Fix return value from NAPI poll

ice_napi_poll is hard-coded to return zero when it's done. It should
instead return the work done (if any work was done). The only time it
should return zero is if an interrupt or poll is handled and no work
is performed. So change the return value to be the minimum of work
done or budget-1.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index fe5bbabbb41e..99954089a7fb 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1107,7 +1107,8 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	napi_complete_done(napi, work_done);
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
 		ice_irq_dynamic_ena(&vsi->back->hw, vsi, q_vector);
-	return 0;
+
+	return min(work_done, budget - 1);
 }
 
 /* helper function for building cmd/type/offset */
-- 
cgit v1.2.3


From bc0c6fab8a1e0d6eb3309b5b0512b5cd06f07979 Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Fri, 26 Oct 2018 11:44:44 -0700
Subject: ice: Cleanup ice_tx_timeout()

Clean up number of formatting issues and a comment that could use
clarification.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 22 +++++++++-------------
 1 file changed, 9 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 292d19e65af0..54ded5d9ab4f 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3702,35 +3702,31 @@ static void ice_tx_timeout(struct net_device *netdev)
 
 	pf->tx_timeout_count++;
 
-	/* find the stopped queue the same way the stack does */
+	/* find the stopped queue the same way dev_watchdog() does */
 	for (i = 0; i < netdev->num_tx_queues; i++) {
-		struct netdev_queue *q;
 		unsigned long trans_start;
+		struct netdev_queue *q;
 
 		q = netdev_get_tx_queue(netdev, i);
 		trans_start = q->trans_start;
 		if (netif_xmit_stopped(q) &&
 		    time_after(jiffies,
-			       (trans_start + netdev->watchdog_timeo))) {
+			       trans_start + netdev->watchdog_timeo)) {
 			hung_queue = i;
 			break;
 		}
 	}
 
-	if (i == netdev->num_tx_queues) {
+	if (i == netdev->num_tx_queues)
 		netdev_info(netdev, "tx_timeout: no netdev hung queue found\n");
-	} else {
+	else
 		/* now that we have an index, find the tx_ring struct */
-		for (i = 0; i < vsi->num_txq; i++) {
-			if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) {
-				if (hung_queue ==
-				    vsi->tx_rings[i]->q_index) {
+		for (i = 0; i < vsi->num_txq; i++)
+			if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
+				if (hung_queue == vsi->tx_rings[i]->q_index) {
 					tx_ring = vsi->tx_rings[i];
 					break;
 				}
-			}
-		}
-	}
 
 	/* Reset recovery level if enough time has elapsed after last timeout.
 	 * Also ensure no new reset action happens before next timeout period.
@@ -3751,7 +3747,7 @@ static void ice_tx_timeout(struct net_device *netdev)
 		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
 			val = rd32(hw,
 				   GLINT_DYN_CTL(tx_ring->q_vector->v_idx +
-					tx_ring->vsi->hw_base_vector));
+						 tx_ring->vsi->hw_base_vector));
 
 		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
 			    vsi->vsi_num, hung_queue, tx_ring->next_to_clean,
-- 
cgit v1.2.3


From 2c5492de8770b72cb9c97c91fbcbb90c16470819 Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Fri, 26 Oct 2018 11:44:45 -0700
Subject: ice: Cleanup short function signatures

Function signatures that do not exceed 80-characters should be on a single
line.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 3 +--
 drivers/net/ethernet/intel/ice/ice_sched.c  | 6 ++----
 drivers/net/ethernet/intel/ice/ice_switch.c | 3 +--
 3 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 0b528602c4c9..b3d73be9f649 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1713,8 +1713,7 @@ void ice_clear_pxe_mode(struct ice_hw *hw)
  * If no bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned
  * If more than one bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned
  */
-static u16
-ice_get_link_speed_based_on_phy_type(u64 phy_type_low)
+static u16 ice_get_link_speed_based_on_phy_type(u64 phy_type_low)
 {
 	u16 speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 7293e4f4d758..84a552ab3e26 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -894,8 +894,7 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw)
  * This function removes the leaf node that was created by the FW
  * during initialization
  */
-static void
-ice_rm_dflt_leaf_node(struct ice_port_info *pi)
+static void ice_rm_dflt_leaf_node(struct ice_port_info *pi)
 {
 	struct ice_sched_node *node;
 
@@ -923,8 +922,7 @@ ice_rm_dflt_leaf_node(struct ice_port_info *pi)
  * This function frees all the nodes except root and TC that were created by
  * the FW during initialization
  */
-static void
-ice_sched_rm_dflt_nodes(struct ice_port_info *pi)
+static void ice_sched_rm_dflt_nodes(struct ice_port_info *pi)
 {
 	struct ice_sched_node *node;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 107ca08899b6..af55c74c2378 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -92,8 +92,7 @@ ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries,
  * Allocate memory for the entire recipe table and initialize the structures/
  * entries corresponding to basic recipes.
  */
-enum ice_status
-ice_init_def_sw_recp(struct ice_hw *hw)
+enum ice_status ice_init_def_sw_recp(struct ice_hw *hw)
 {
 	struct ice_sw_recipe *recps;
 	u8 i;
-- 
cgit v1.2.3


From df17b7e02f0fa3a13c5aac26c317447d72612e1c Mon Sep 17 00:00:00 2001
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Date: Fri, 26 Oct 2018 11:44:46 -0700
Subject: ice: Cosmetic formatting changes

1. Fix several cases of double spacing
2. Fix typos
3. Capitalize abbreviations

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h             | 10 +--
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h  | 16 ++---
 drivers/net/ethernet/intel/ice/ice_controlq.c    |  4 +-
 drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h   | 79 ++++++++++++------------
 drivers/net/ethernet/intel/ice/ice_lib.c         |  8 +--
 drivers/net/ethernet/intel/ice/ice_main.c        | 14 ++---
 drivers/net/ethernet/intel/ice/ice_sriov.c       |  2 +-
 drivers/net/ethernet/intel/ice/ice_switch.c      |  4 +-
 drivers/net/ethernet/intel/ice/ice_txrx.c        | 12 ++--
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 16 +++--
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h |  2 +-
 11 files changed, 83 insertions(+), 84 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 7d8575d11786..60b2e0c9faf5 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -150,10 +150,10 @@ enum ice_state {
 	__ICE_RESET_FAILED,		/* set by reset/rebuild */
 	/* When checking for the PF to be in a nominal operating state, the
 	 * bits that are grouped at the beginning of the list need to be
-	 * checked.  Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will
-	 * be checked.  If you need to add a bit into consideration for nominal
+	 * checked. Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will
+	 * be checked. If you need to add a bit into consideration for nominal
 	 * operating state, it must be added before
-	 * __ICE_STATE_NOMINAL_CHECK_BITS.  Do not move this entry's position
+	 * __ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position
 	 * without appropriate consideration.
 	 */
 	__ICE_STATE_NOMINAL_CHECK_BITS,
@@ -201,8 +201,8 @@ struct ice_vsi {
 	int sw_base_vector;		/* Irq base for OS reserved vectors */
 	int hw_base_vector;		/* HW (absolute) index of a vector */
 	enum ice_vsi_type type;
-	u16 vsi_num;			 /* HW (absolute) index of this VSI */
-	u16 idx;			 /* software index in pf->vsi[] */
+	u16 vsi_num;			/* HW (absolute) index of this VSI */
+	u16 idx;			/* software index in pf->vsi[] */
 
 	/* Interrupt thresholds */
 	u16 work_lmt;
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 4078070881ce..fcdcd80b18e7 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -5,7 +5,7 @@
 #define _ICE_ADMINQ_CMD_H_
 
 /* This header file defines the Admin Queue commands, error codes and
- * descriptor format.  It is shared between Firmware and Software.
+ * descriptor format. It is shared between Firmware and Software.
  */
 
 #define ICE_MAX_VSI			768
@@ -463,7 +463,7 @@ struct ice_aqc_sw_rules {
 };
 
 /* Add/Update/Get/Remove lookup Rx/Tx command/response entry
- * This structures describes the lookup rules and associated actions.  "index"
+ * This structures describes the lookup rules and associated actions. "index"
  * is returned as part of a response to a successful Add command, and can be
  * used to identify the rule for Update/Get/Remove commands.
  */
@@ -1111,7 +1111,7 @@ struct ice_aqc_get_set_rss_keys {
 };
 
 /* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */
-struct  ice_aqc_get_set_rss_lut {
+struct ice_aqc_get_set_rss_lut {
 #define ICE_AQC_GSET_RSS_LUT_VSI_VALID	BIT(15)
 #define ICE_AQC_GSET_RSS_LUT_VSI_ID_S	0
 #define ICE_AQC_GSET_RSS_LUT_VSI_ID_M	(0x1FF << ICE_AQC_GSET_RSS_LUT_VSI_ID_S)
@@ -1315,10 +1315,10 @@ struct ice_aqc_get_clear_fw_log {
  * @params: command-specific parameters
  *
  * Descriptor format for commands the driver posts on the Admin Transmit Queue
- * (ATQ).  The firmware writes back onto the command descriptor and returns
- * the result of the command.  Asynchronous events that are not an immediate
+ * (ATQ). The firmware writes back onto the command descriptor and returns
+ * the result of the command. Asynchronous events that are not an immediate
  * result of the command are written to the Admin Receive Queue (ARQ) using
- * the same descriptor format.  Descriptors are in little-endian notation with
+ * the same descriptor format. Descriptors are in little-endian notation with
  * 32-bit words.
  */
 struct ice_aq_desc {
@@ -1380,10 +1380,10 @@ struct ice_aq_desc {
 
 /* error codes */
 enum ice_aq_err {
-	ICE_AQ_RC_OK		= 0,  /* success */
+	ICE_AQ_RC_OK		= 0,  /* Success */
 	ICE_AQ_RC_ENOMEM	= 9,  /* Out of memory */
 	ICE_AQ_RC_EBUSY		= 12, /* Device or resource busy */
-	ICE_AQ_RC_EEXIST	= 13, /* object already exists */
+	ICE_AQ_RC_EEXIST	= 13, /* Object already exists */
 	ICE_AQ_RC_ENOSPC	= 16, /* No space left or allocation failure */
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index b920403c6616..1831771a7969 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -775,7 +775,7 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq)
  * @buf_size: size of buffer for indirect commands (or 0 for direct commands)
  * @cd: pointer to command details structure
  *
- * This is the main send command routine for the ATQ.  It runs the q,
+ * This is the main send command routine for the ATQ. It runs the queue,
  * cleans the queue, etc.
  */
 enum ice_status
@@ -969,7 +969,7 @@ void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode)
  * @pending: number of events that could be left to process
  *
  * This function cleans one Admin Receive Queue element and returns
- * the contents through e.  It can also return how many events are
+ * the contents through e. It can also return how many events are
  * left to process through 'pending'.
  */
 enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 7d2a66739e3f..bb51dd7defb5 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -6,11 +6,11 @@
 
 union ice_32byte_rx_desc {
 	struct {
-		__le64  pkt_addr; /* Packet buffer address */
-		__le64  hdr_addr; /* Header buffer address */
+		__le64 pkt_addr; /* Packet buffer address */
+		__le64 hdr_addr; /* Header buffer address */
 			/* bit 0 of hdr_addr is DD bit */
-		__le64  rsvd1;
-		__le64  rsvd2;
+		__le64 rsvd1;
+		__le64 rsvd2;
 	} read;
 	struct {
 		struct {
@@ -105,11 +105,11 @@ enum ice_rx_ptype_payload_layer {
  */
 union ice_32b_rx_flex_desc {
 	struct {
-		__le64  pkt_addr; /* Packet buffer address */
-		__le64  hdr_addr; /* Header buffer address */
-				  /* bit 0 of hdr_addr is DD bit */
-		__le64  rsvd1;
-		__le64  rsvd2;
+		__le64 pkt_addr; /* Packet buffer address */
+		__le64 hdr_addr; /* Header buffer address */
+				 /* bit 0 of hdr_addr is DD bit */
+		__le64 rsvd1;
+		__le64 rsvd2;
 	} read;
 	struct {
 		/* Qword 0 */
@@ -256,6 +256,9 @@ enum ice_rx_flex_desc_status_error_0_bits {
 
 #define ICE_RXQ_CTX_SIZE_DWORDS		8
 #define ICE_RXQ_CTX_SZ			(ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32))
+#define ICE_TX_CMPLTNQ_CTX_SIZE_DWORDS	22
+#define ICE_TX_DRBELL_Q_CTX_SIZE_DWORDS	5
+#define GLTCLAN_CQ_CNTX(i, CQ)		(GLTCLAN_CQ_CNTX0(CQ) + ((i) * 0x0800))
 
 /* RLAN Rx queue context data
  *
@@ -274,18 +277,18 @@ struct ice_rlan_ctx {
 	u16 dbuf; /* bigger than needed, see above for reason */
 #define ICE_RLAN_CTX_HBUF_S 6
 	u16 hbuf; /* bigger than needed, see above for reason */
-	u8  dtype;
-	u8  dsize;
-	u8  crcstrip;
-	u8  l2tsel;
-	u8  hsplit_0;
-	u8  hsplit_1;
-	u8  showiv;
+	u8 dtype;
+	u8 dsize;
+	u8 crcstrip;
+	u8 l2tsel;
+	u8 hsplit_0;
+	u8 hsplit_1;
+	u8 showiv;
 	u32 rxmax; /* bigger than needed, see above for reason */
-	u8  tphrdesc_ena;
-	u8  tphwdesc_ena;
-	u8  tphdata_ena;
-	u8  tphhead_ena;
+	u8 tphrdesc_ena;
+	u8 tphwdesc_ena;
+	u8 tphdata_ena;
+	u8 tphhead_ena;
 	u16 lrxqthresh; /* bigger than needed, see above for reason */
 };
 
@@ -413,35 +416,35 @@ enum ice_tx_ctx_desc_cmd_bits {
 struct ice_tlan_ctx {
 #define ICE_TLAN_CTX_BASE_S	7
 	u64 base;		/* base is defined in 128-byte units */
-	u8  port_num;
+	u8 port_num;
 	u16 cgd_num;		/* bigger than needed, see above for reason */
-	u8  pf_num;
+	u8 pf_num;
 	u16 vmvf_num;
-	u8  vmvf_type;
+	u8 vmvf_type;
 #define ICE_TLAN_CTX_VMVF_TYPE_VF	0
 #define ICE_TLAN_CTX_VMVF_TYPE_VMQ	1
 #define ICE_TLAN_CTX_VMVF_TYPE_PF	2
 	u16 src_vsi;
-	u8  tsyn_ena;
-	u8  alt_vlan;
+	u8 tsyn_ena;
+	u8 alt_vlan;
 	u16 cpuid;		/* bigger than needed, see above for reason */
-	u8  wb_mode;
-	u8  tphrd_desc;
-	u8  tphrd;
-	u8  tphwr_desc;
+	u8 wb_mode;
+	u8 tphrd_desc;
+	u8 tphrd;
+	u8 tphwr_desc;
 	u16 cmpq_id;
 	u16 qnum_in_func;
-	u8  itr_notification_mode;
-	u8  adjust_prof_id;
+	u8 itr_notification_mode;
+	u8 adjust_prof_id;
 	u32 qlen;		/* bigger than needed, see above for reason */
-	u8  quanta_prof_idx;
-	u8  tso_ena;
+	u8 quanta_prof_idx;
+	u8 tso_ena;
 	u16 tso_qnum;
-	u8  legacy_int;
-	u8  drop_ena;
-	u8  cache_prof_idx;
-	u8  pkt_shaper_prof_idx;
-	u8  int_q_state;	/* width not needed - internal do not write */
+	u8 legacy_int;
+	u8 drop_ena;
+	u8 cache_prof_idx;
+	u8 pkt_shaper_prof_idx;
+	u8 int_q_state;	/* width not needed - internal do not write */
 };
 
 /* macro to make the table lines short */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index a5961a8fe73c..534221d80200 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1012,7 +1012,7 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi)
  * @vsi: the VSI being configured
  * @v_idx: index of the vector in the VSI struct
  *
- * We allocate one q_vector.  If allocation fails we return -ENOMEM.
+ * We allocate one q_vector. If allocation fails we return -ENOMEM.
  */
 static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx)
 {
@@ -1051,7 +1051,7 @@ out:
  * ice_vsi_alloc_q_vectors - Allocate memory for interrupt vectors
  * @vsi: the VSI being configured
  *
- * We allocate one q_vector per queue interrupt.  If allocation fails we
+ * We allocate one q_vector per queue interrupt. If allocation fails we
  * return -ENOMEM.
  */
 static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
@@ -2136,9 +2136,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 		pf->q_left_rx -= vsi->alloc_rxq;
 		break;
 	default:
-		/* if VSI type is not recognized, clean up the resources and
-		 * exit
-		 */
+		/* clean up the resources and exit */
 		goto unroll_vsi_init;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 54ded5d9ab4f..9f85d6534520 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -408,7 +408,7 @@ static void ice_reset_subtask(struct ice_pf *pf)
 	/* When a CORER/GLOBR/EMPR is about to happen, the hardware triggers an
 	 * OICR interrupt. The OICR handler (ice_misc_intr) determines what type
 	 * of reset is pending and sets bits in pf->state indicating the reset
-	 * type and __ICE_RESET_OICR_RECV.  So, if the latter bit is set
+	 * type and __ICE_RESET_OICR_RECV. So, if the latter bit is set
 	 * prepare for pending reset if not already (for PF software-initiated
 	 * global resets the software should already be prepared for it as
 	 * indicated by __ICE_PREPARED_FOR_RESET; for global resets initiated
@@ -1382,7 +1382,7 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf)
  * @pf: board private structure
  *
  * This sets up the handler for MSIX 0, which is used to manage the
- * non-queue interrupts, e.g. AdminQ and errors.  This is not used
+ * non-queue interrupts, e.g. AdminQ and errors. This is not used
  * when in MSI or Legacy interrupt mode.
  */
 static int ice_req_irq_msix_misc(struct ice_pf *pf)
@@ -3674,7 +3674,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 		 */
 		status = ice_update_sw_rule_bridge_mode(hw);
 		if (status) {
-			netdev_err(dev, "update SW_RULE for bridge mode failed,  = %d err %d aq_err %d\n",
+			netdev_err(dev, "switch rule update failed, mode = %d err %d aq_err %d\n",
 				   mode, status, hw->adminq.sq_last_status);
 			/* revert hw->evb_veb */
 			hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB);
@@ -3785,7 +3785,7 @@ static void ice_tx_timeout(struct net_device *netdev)
  * @netdev: network interface device structure
  *
  * The open entry point is called when a network interface is made
- * active by the system (IFF_UP).  At this point all resources needed
+ * active by the system (IFF_UP). At this point all resources needed
  * for transmit and receive operations are allocated, the interrupt
  * handler is registered with the OS, the netdev watchdog is enabled,
  * and the stack is notified that the interface is ready.
@@ -3818,7 +3818,7 @@ static int ice_open(struct net_device *netdev)
  * @netdev: network interface device structure
  *
  * The stop entry point is called when an interface is de-activated by the OS,
- * and the netdevice enters the DOWN state.  The hardware is still under the
+ * and the netdevice enters the DOWN state. The hardware is still under the
  * driver's control, but the netdev interface is disabled.
  *
  * Returns success only - not allowed to fail
@@ -3847,14 +3847,14 @@ ice_features_check(struct sk_buff *skb,
 	size_t len;
 
 	/* No point in doing any of this if neither checksum nor GSO are
-	 * being requested for this frame.  We can rule out both by just
+	 * being requested for this frame. We can rule out both by just
 	 * checking for CHECKSUM_PARTIAL
 	 */
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
 		return features;
 
 	/* We cannot support GSO if the MSS is going to be less than
-	 * 64 bytes.  If it is then we need to drop support for GSO.
+	 * 64 bytes. If it is then we need to drop support for GSO.
 	 */
 	if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64))
 		features &= ~NETIF_F_GSO_MASK;
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index 027eba4e13f8..533b989a23e1 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -46,7 +46,7 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval,
  * @link_speed: variable containing the link_speed to be converted
  *
  * Convert link speed supported by HW to link speed supported by virtchnl.
- * If adv_link_support is true, then return link speed in Mbps.  Else return
+ * If adv_link_support is true, then return link speed in Mbps. Else return
  * link speed as a VIRTCHNL_LINK_SPEED_* casted to a u32. Note that the caller
  * needs to cast back to an enum virtchnl_link_speed in the case where
  * adv_link_support is false, but when adv_link_support is true the caller can
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index af55c74c2378..286a1a7afdc2 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -129,7 +129,7 @@ enum ice_status ice_init_def_sw_recp(struct ice_hw *hw)
  *
  * NOTE: *req_desc is both an input/output parameter.
  * The caller of this function first calls this function with *request_desc set
- * to 0.  If the response from f/w has *req_desc set to 0, all the switch
+ * to 0. If the response from f/w has *req_desc set to 0, all the switch
  * configuration information has been returned; if non-zero (meaning not all
  * the information was returned), the caller should call this function again
  * with *req_desc set to the previous value returned by f/w to get the
@@ -1863,7 +1863,7 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry)
 		tmp_fltr.fwd_id.vsi_list_id = vsi_list_id;
 		tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST;
 		/* Update the previous switch rule to a new VSI list which
-		 * includes current VSI thats requested
+		 * includes current VSI that is requested
 		 */
 		status = ice_update_pkt_fwd_rule(hw, &tmp_fltr);
 		if (status)
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 99954089a7fb..939510b7e8f3 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -377,7 +377,7 @@ static void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val)
 	rx_ring->next_to_alloc = val;
 
 	/* Force memory writes to complete before letting h/w
-	 * know there are new descriptors to fetch.  (Only
+	 * know there are new descriptors to fetch. (Only
 	 * applicable for weak-ordered memory model archs,
 	 * such as IA-64).
 	 */
@@ -686,7 +686,7 @@ static struct sk_buff *ice_fetch_rx_buf(struct ice_ring *rx_ring,
  * ice_pull_tail - ice specific version of skb_pull_tail
  * @skb: pointer to current skb being adjusted
  *
- * This function is an ice specific version of __pskb_pull_tail.  The
+ * This function is an ice specific version of __pskb_pull_tail. The
  * main difference between this version and the original function is that
  * this function can make several assumptions about the state of things
  * that allow for significant optimizations versus the standard function.
@@ -768,7 +768,7 @@ static bool ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc,
  * @rx_desc: Rx descriptor for current buffer
  * @skb: Current socket buffer containing buffer in progress
  *
- * This function updates next to clean.  If the buffer is an EOP buffer
+ * This function updates next to clean. If the buffer is an EOP buffer
  * this function exits returning false, otherwise it will place the
  * sk_buff in the next buffer to be chained and return true indicating
  * that this is in fact a non-EOP buffer.
@@ -950,7 +950,7 @@ static void ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb,
  * @budget: Total limit on number of packets to process
  *
  * This function provides a "bounce buffer" approach to Rx interrupt
- * processing.  The advantage to this is that on systems that have
+ * processing. The advantage to this is that on systems that have
  * expensive overhead for IOMMU access this provides a means of avoiding
  * it by maintaining the mapping of the page to the system.
  *
@@ -1553,7 +1553,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
  * Finally, we add one to round up. Because 256 isn't an exact multiple of
  * 3, we'll underestimate near each multiple of 12K. This is actually more
  * accurate as we have 4K - 1 of wiggle room that we can fit into the last
- * segment.  For our purposes this is accurate out to 1M which is orders of
+ * segment. For our purposes this is accurate out to 1M which is orders of
  * magnitude greater than our largest possible GSO size.
  *
  * This would then be implemented as:
@@ -1621,7 +1621,7 @@ static bool __ice_chk_linearize(struct sk_buff *skb)
 	nr_frags -= ICE_MAX_BUF_TXD - 2;
 	frag = &skb_shinfo(skb)->frags[0];
 
-	/* Initialize size to the negative value of gso_size minus 1.  We
+	/* Initialize size to the negative value of gso_size minus 1. We
 	 * use this as the worst case scenerio in which the frag ahead
 	 * of us only provides one byte which is why we are limited to 6
 	 * descriptors for a single transmit as the header and previous
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 20b94dee0036..05ff4f910649 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -156,8 +156,6 @@ static void ice_free_vf_res(struct ice_vf *vf)
 	clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states);
 }
 
-/***********************enable_vf routines*****************************/
-
 /**
  * ice_dis_vf_mappings
  * @vf: pointer to the VF structure
@@ -454,7 +452,7 @@ static int ice_alloc_vsi_res(struct ice_vf *vf)
 
 	/* Clear this bit after VF initialization since we shouldn't reclaim
 	 * and reassign interrupts for synchronous or asynchronous VFR events.
-	 * We don't want to reconfigure interrupts since AVF driver doesn't
+	 * We dont want to reconfigure interrupts since AVF driver doesn't
 	 * expect vector assignment to be changed unless there is a request for
 	 * more vectors.
 	 */
@@ -1105,7 +1103,7 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs)
  * ice_process_vflr_event - Free VF resources via IRQ calls
  * @pf: pointer to the PF structure
  *
- * called from the VLFR IRQ handler to
+ * called from the VFLR IRQ handler to
  * free up VF resources and state variables
  */
 void ice_process_vflr_event(struct ice_pf *pf)
@@ -1764,7 +1762,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 		/* copy Tx queue info from VF into VSI */
 		vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr;
 		vsi->tx_rings[i]->count = qpi->txq.ring_len;
-		/* copy Rx queue info from VF into vsi */
+		/* copy Rx queue info from VF into VSI */
 		vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr;
 		vsi->rx_rings[i]->count = qpi->rxq.ring_len;
 		if (qpi->rxq.databuffer_size > ((16 * 1024) - 128)) {
@@ -1830,7 +1828,7 @@ static bool ice_can_vf_change_mac(struct ice_vf *vf)
  * @msg: pointer to the msg buffer
  * @set: true if mac filters are being set, false otherwise
  *
- * add guest mac address filter
+ * add guest MAC address filter
  */
 static int
 ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
@@ -1968,9 +1966,9 @@ static int ice_vc_del_mac_addr_msg(struct ice_vf *vf, u8 *msg)
  * @msg: pointer to the msg buffer
  *
  * VFs get a default number of queues but can use this message to request a
- * different number.  If the request is successful, PF will reset the VF and
+ * different number. If the request is successful, PF will reset the VF and
  * return 0. If unsuccessful, PF will send message informing VF of number of
- * available queue pairs via virtchnl message response to VF.
+ * available queue pairs via virtchnl message response to vf.
  */
 static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
 {
@@ -1991,7 +1989,7 @@ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
 	tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx);
 	if (req_queues <= 0) {
 		dev_err(&pf->pdev->dev,
-			"VF %d tried to request %d queues.  Ignoring.\n",
+			"VF %d tried to request %d queues. Ignoring.\n",
 			vf->vf_id, req_queues);
 	} else if (req_queues > ICE_MAX_QS_PER_VF) {
 		dev_err(&pf->pdev->dev,
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
index 10131e0180f9..01470a8ee03a 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
@@ -70,7 +70,7 @@ struct ice_vf {
 	u8 spoofchk;
 	u16 num_mac;
 	u16 num_vlan;
-	u8 num_req_qs;		/* num of queue pairs requested by VF */
+	u8 num_req_qs;			/* num of queue pairs requested by VF */
 };
 
 #ifdef CONFIG_PCI_IOV
-- 
cgit v1.2.3


From d337f2afb7aceb16840a2621c5e2f9e868630653 Mon Sep 17 00:00:00 2001
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Date: Fri, 26 Oct 2018 11:44:47 -0700
Subject: ice: Use Tx|Rx in comments

In code comments, use Tx|Rx instead of tx|rx

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h          | 20 ++++++++++----------
 drivers/net/ethernet/intel/ice/ice_common.c   |  6 +++---
 drivers/net/ethernet/intel/ice/ice_controlq.c |  1 -
 drivers/net/ethernet/intel/ice/ice_ethtool.c  | 12 ++++++------
 drivers/net/ethernet/intel/ice/ice_lib.c      |  8 ++++----
 drivers/net/ethernet/intel/ice/ice_main.c     |  2 +-
 drivers/net/ethernet/intel/ice/ice_sched.c    |  6 +++---
 drivers/net/ethernet/intel/ice/ice_switch.c   |  8 ++++----
 drivers/net/ethernet/intel/ice/ice_txrx.c     | 21 +++++++++++----------
 9 files changed, 42 insertions(+), 42 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 60b2e0c9faf5..a385575600f6 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -96,14 +96,14 @@ extern const char ice_drv_ver[];
 #define ice_for_each_vsi(pf, i) \
 	for ((i) = 0; (i) < (pf)->num_alloc_vsi; (i)++)
 
-/* Macros for each tx/rx ring in a VSI */
+/* Macros for each Tx/Rx ring in a VSI */
 #define ice_for_each_txq(vsi, i) \
 	for ((i) = 0; (i) < (vsi)->num_txq; (i)++)
 
 #define ice_for_each_rxq(vsi, i) \
 	for ((i) = 0; (i) < (vsi)->num_rxq; (i)++)
 
-/* Macros for each allocated tx/rx ring whether used or not in a VSI */
+/* Macros for each allocated Tx/Rx ring whether used or not in a VSI */
 #define ice_for_each_alloc_txq(vsi, i) \
 	for ((i) = 0; (i) < (vsi)->alloc_txq; (i)++)
 
@@ -183,8 +183,8 @@ struct ice_vsi {
 	struct ice_sw *vsw;		 /* switch this VSI is on */
 	struct ice_pf *back;		 /* back pointer to PF */
 	struct ice_port_info *port_info; /* back pointer to port_info */
-	struct ice_ring **rx_rings;	 /* rx ring array */
-	struct ice_ring **tx_rings;	 /* tx ring array */
+	struct ice_ring **rx_rings;	 /* Rx ring array */
+	struct ice_ring **tx_rings;	 /* Tx ring array */
 	struct ice_q_vector **q_vectors; /* q_vector array */
 
 	irqreturn_t (*irq_handler)(int irq, void *data);
@@ -255,8 +255,8 @@ struct ice_q_vector {
 	struct ice_ring_container tx;
 	struct irq_affinity_notify affinity_notify;
 	u16 v_idx;			/* index in the vsi->q_vector array. */
-	u8 num_ring_tx;			/* total number of tx rings in vector */
-	u8 num_ring_rx;			/* total number of rx rings in vector */
+	u8 num_ring_tx;			/* total number of Tx rings in vector */
+	u8 num_ring_rx;			/* total number of Rx rings in vector */
 	char name[ICE_INT_NAME_STR_LEN];
 	/* in usecs, need to use ice_intrl_to_usecs_reg() before writing this
 	 * value to the device
@@ -308,10 +308,10 @@ struct ice_pf {
 	u32 hw_oicr_idx;	/* Other interrupt cause vector HW index */
 	u32 num_avail_hw_msix;	/* remaining HW MSIX vectors left unclaimed */
 	u32 num_lan_msix;	/* Total MSIX vectors for base driver */
-	u16 num_lan_tx;		/* num lan tx queues setup */
-	u16 num_lan_rx;		/* num lan rx queues setup */
-	u16 q_left_tx;		/* remaining num tx queues left unclaimed */
-	u16 q_left_rx;		/* remaining num rx queues left unclaimed */
+	u16 num_lan_tx;		/* num lan Tx queues setup */
+	u16 num_lan_rx;		/* num lan Rx queues setup */
+	u16 q_left_tx;		/* remaining num Tx queues left unclaimed */
+	u16 q_left_rx;		/* remaining num Rx queues left unclaimed */
 	u16 next_vsi;		/* Next free slot in pf->vsi[] - 0-based! */
 	u16 num_alloc_vsi;
 	u16 corer_count;	/* Core reset count */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index b3d73be9f649..4c1d35da940d 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -713,7 +713,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 
 	hw->evb_veb = true;
 
-	/* Query the allocated resources for tx scheduler */
+	/* Query the allocated resources for Tx scheduler */
 	status = ice_sched_query_res_alloc(hw);
 	if (status) {
 		ice_debug(hw, ICE_DBG_SCHED,
@@ -956,7 +956,7 @@ enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req)
  * ice_copy_rxq_ctx_to_hw
  * @hw: pointer to the hardware structure
  * @ice_rxq_ctx: pointer to the rxq context
- * @rxq_index: the index of the rx queue
+ * @rxq_index: the index of the Rx queue
  *
  * Copies rxq context from dense structure to hw register space
  */
@@ -1012,7 +1012,7 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = {
  * ice_write_rxq_ctx
  * @hw: pointer to the hardware structure
  * @rlan_ctx: pointer to the rxq context
- * @rxq_index: the index of the rx queue
+ * @rxq_index: the index of the Rx queue
  *
  * Converts rxq context from sparse to dense structure and then writes
  * it to hw register space
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 1831771a7969..2bf5e11f559a 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -591,7 +591,6 @@ init_ctrlq_free_rq:
  *     - cq->num_rq_entries
  *     - cq->rq_buf_size
  *     - cq->sq_buf_size
- *
  */
 static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 990d660f527a..3b6e387f5440 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -260,10 +260,10 @@ static int ice_get_sset_count(struct net_device *netdev, int sset)
 		 * a private ethtool flag). This is due to the nature of the
 		 * ethtool stats API.
 		 *
-		 * User space programs such as ethtool must make 3 separate
+		 * Userspace programs such as ethtool must make 3 separate
 		 * ioctl requests, one for size, one for the strings, and
 		 * finally one for the stats. Since these cross into
-		 * user space, changes to the number or size could result in
+		 * userspace, changes to the number or size could result in
 		 * undefined memory access or incorrect string<->value
 		 * correlations for statistics.
 		 *
@@ -1441,7 +1441,7 @@ ice_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 /**
  * ice_set_pauseparam - Set Flow Control parameter
  * @netdev: network interface device structure
- * @pause: return tx/rx flow control status
+ * @pause: return Tx/Rx flow control status
  */
 static int
 ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
@@ -1543,7 +1543,7 @@ static u32 ice_get_rxfh_key_size(struct net_device __always_unused *netdev)
 }
 
 /**
- * ice_get_rxfh_indir_size - get the rx flow hash indirection table size
+ * ice_get_rxfh_indir_size - get the Rx flow hash indirection table size
  * @netdev: network interface device structure
  *
  * Returns the table size.
@@ -1556,7 +1556,7 @@ static u32 ice_get_rxfh_indir_size(struct net_device *netdev)
 }
 
 /**
- * ice_get_rxfh - get the rx flow hash indirection table
+ * ice_get_rxfh - get the Rx flow hash indirection table
  * @netdev: network interface device structure
  * @indir: indirection table
  * @key: hash key
@@ -1603,7 +1603,7 @@ out:
 }
 
 /**
- * ice_set_rxfh - set the rx flow hash indirection table
+ * ice_set_rxfh - set the Rx flow hash indirection table
  * @netdev: network interface device structure
  * @indir: indirection table
  * @key: hash key
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 534221d80200..29b1dcfd4331 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -20,7 +20,7 @@ static int ice_setup_rx_ctx(struct ice_ring *ring)
 	u16 pf_q;
 	int err;
 
-	/* what is RX queue number in global space of 2K Rx queues */
+	/* what is Rx queue number in global space of 2K Rx queues */
 	pf_q = vsi->rxq_map[ring->q_index];
 
 	/* clear the context structure first */
@@ -1200,7 +1200,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 	struct ice_pf *pf = vsi->back;
 	int i;
 
-	/* Allocate tx_rings */
+	/* Allocate Tx rings */
 	for (i = 0; i < vsi->alloc_txq; i++) {
 		struct ice_ring *ring;
 
@@ -1219,7 +1219,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		vsi->tx_rings[i] = ring;
 	}
 
-	/* Allocate rx_rings */
+	/* Allocate Rx rings */
 	for (i = 0; i < vsi->alloc_rxq; i++) {
 		struct ice_ring *ring;
 
@@ -2333,7 +2333,7 @@ static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id)
 	int start = res->search_hint;
 	int end = start;
 
-	if ((start + needed) >  res->num_entries)
+	if ((start + needed) > res->num_entries)
 		return -ENOMEM;
 
 	id |= ICE_RES_VALID_BIT;
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 9f85d6534520..e45e57499d91 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1786,7 +1786,7 @@ static void ice_determine_q_usage(struct ice_pf *pf)
 
 	pf->num_lan_tx = min_t(int, q_left_tx, num_online_cpus());
 
-	/* only 1 rx queue unless RSS is enabled */
+	/* only 1 Rx queue unless RSS is enabled */
 	if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags))
 		pf->num_lan_rx = 1;
 	else
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 84a552ab3e26..a1681853df2e 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -1337,7 +1337,7 @@ ice_sched_rm_vsi_child_nodes(struct ice_port_info *pi,
  * @num_nodes: pointer to num nodes array
  *
  * This function calculates the number of supported nodes needed to add this
- * VSI into tx tree including the VSI, parent and intermediate nodes in below
+ * VSI into Tx tree including the VSI, parent and intermediate nodes in below
  * layers
  */
 static void
@@ -1374,13 +1374,13 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw,
 }
 
 /**
- * ice_sched_add_vsi_support_nodes - add VSI supported nodes into tx tree
+ * ice_sched_add_vsi_support_nodes - add VSI supported nodes into Tx tree
  * @pi: port information structure
  * @vsi_handle: software VSI handle
  * @tc_node: pointer to TC node
  * @num_nodes: pointer to num nodes array
  *
- * This function adds the VSI supported nodes into tx tree including the
+ * This function adds the VSI supported nodes into Tx tree including the
  * VSI, its parent and intermediate nodes in below layers
  */
 static enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 286a1a7afdc2..091047f7ac02 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -827,7 +827,7 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent,
 	/* Create two back-to-back switch rules and submit them to the HW using
 	 * one memory buffer:
 	 *    1. Large Action
-	 *    2. Look up tx rx
+	 *    2. Look up Tx Rx
 	 */
 	lg_act_size = (u16)ICE_SW_RULE_LG_ACT_SIZE(num_lg_acts);
 	rules_size = lg_act_size + ICE_SW_RULE_RX_TX_ETH_HDR_SIZE;
@@ -871,7 +871,7 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent,
 
 	lg_act->pdata.lg_act.act[2] = cpu_to_le32(act);
 
-	/* call the fill switch rule to fill the lookup tx rx structure */
+	/* call the fill switch rule to fill the lookup Tx Rx structure */
 	ice_fill_sw_rule(hw, &m_ent->fltr_info, rx_tx,
 			 ice_aqc_opc_update_sw_rules);
 
@@ -1168,8 +1168,8 @@ enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw)
  * Call AQ command to add or update previously created VSI list with new VSI.
  *
  * Helper function to do book keeping associated with adding filter information
- * The algorithm to do the booking keeping is described below :
- * When a VSI needs to subscribe to a given filter( MAC/VLAN/Ethtype etc.)
+ * The algorithm to do the book keeping is described below :
+ * When a VSI needs to subscribe to a given filter (MAC/VLAN/Ethtype etc.)
  *	if only one VSI has been added till now
  *		Allocate a new VSI list and add two VSIs
  *		to this list using switch rule command
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 939510b7e8f3..4b92863b3500 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -219,7 +219,7 @@ static bool ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring,
 
 /**
  * ice_setup_tx_ring - Allocate the Tx descriptors
- * @tx_ring: the tx ring to set up
+ * @tx_ring: the Tx ring to set up
  *
  * Return 0 on success, negative on error
  */
@@ -324,7 +324,7 @@ void ice_free_rx_ring(struct ice_ring *rx_ring)
 
 /**
  * ice_setup_rx_ring - Allocate the Rx descriptors
- * @rx_ring: the rx ring to set up
+ * @rx_ring: the Rx ring to set up
  *
  * Return 0 on success, negative on error
  */
@@ -586,7 +586,7 @@ static bool ice_add_rx_frag(struct ice_rx_buf *rx_buf,
 
 /**
  * ice_reuse_rx_page - page flip buffer and store it back on the ring
- * @rx_ring: rx descriptor ring to store buffers on
+ * @rx_ring: Rx descriptor ring to store buffers on
  * @old_buf: donor buffer to have page reused
  *
  * Synchronizes page for reuse by the adapter
@@ -609,7 +609,7 @@ static void ice_reuse_rx_page(struct ice_ring *rx_ring,
 
 /**
  * ice_fetch_rx_buf - Allocate skb and populate it
- * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_ring: Rx descriptor ring to transact packets on
  * @rx_desc: descriptor containing info written by hardware
  *
  * This function allocates an skb on the fly, and populates it with the page
@@ -904,7 +904,7 @@ checksum_fail:
 
 /**
  * ice_process_skb_fields - Populate skb header fields from Rx descriptor
- * @rx_ring: rx descriptor ring packet is being transacted on
+ * @rx_ring: Rx descriptor ring packet is being transacted on
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being populated
  * @ptype: the packet type decoded by hardware
@@ -927,7 +927,7 @@ static void ice_process_skb_fields(struct ice_ring *rx_ring,
 
 /**
  * ice_receive_skb - Send a completed packet up the stack
- * @rx_ring: rx ring in play
+ * @rx_ring: Rx ring in play
  * @skb: packet to send up
  * @vlan_tag: vlan tag for packet
  *
@@ -946,7 +946,7 @@ static void ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb,
 
 /**
  * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
- * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_ring: Rx descriptor ring to transact packets on
  * @budget: Total limit on number of packets to process
  *
  * This function provides a "bounce buffer" approach to Rx interrupt
@@ -1123,7 +1123,7 @@ build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag)
 }
 
 /**
- * __ice_maybe_stop_tx - 2nd level check for tx stop conditions
+ * __ice_maybe_stop_tx - 2nd level check for Tx stop conditions
  * @tx_ring: the ring to be checked
  * @size: the size buffer we want to assure is available
  *
@@ -1146,7 +1146,7 @@ static int __ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size)
 }
 
 /**
- * ice_maybe_stop_tx - 1st level check for tx stop conditions
+ * ice_maybe_stop_tx - 1st level check for Tx stop conditions
  * @tx_ring: the ring to be checked
  * @size:    the size buffer we want to assure is available
  *
@@ -1156,6 +1156,7 @@ static int ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size)
 {
 	if (likely(ICE_DESC_UNUSED(tx_ring) >= size))
 		return 0;
+
 	return __ice_maybe_stop_tx(tx_ring, size);
 }
 
@@ -1569,7 +1570,7 @@ static unsigned int ice_txd_use_count(unsigned int size)
 }
 
 /**
- * ice_xmit_desc_count - calculate number of tx descriptors needed
+ * ice_xmit_desc_count - calculate number of Tx descriptors needed
  * @skb: send buffer
  *
  * Returns number of data descriptors needed for this skb.
-- 
cgit v1.2.3


From f25dad19ba70f7cc135da78ec013325042cd8c52 Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Wed, 7 Nov 2018 10:19:35 -0800
Subject: ice: Fix possible NULL pointer de-reference

A recent update to smatch is causing it to report the error "we previously
assumed 'm_entry->vsi_list_info' could be null". Fix that.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_switch.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 091047f7ac02..2e5693107fa4 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -1247,6 +1247,9 @@ ice_add_update_vsi_list(struct ice_hw *hw,
 		u16 vsi_handle = new_fltr->vsi_handle;
 		enum ice_adminq_opc opcode;
 
+		if (!m_entry->vsi_list_info)
+			return ICE_ERR_CFG;
+
 		/* A rule already exists with the new VSI being added */
 		if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map))
 			return 0;
-- 
cgit v1.2.3


From f6161a8f3036caa45f225486be39783e99e0fa29 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 20 Nov 2018 14:08:20 -0800
Subject: bpf: fix a compilation error when CONFIG_BPF_SYSCALL is not defined

Kernel test robot (lkp@intel.com) reports a compilation error at
  https://www.spinics.net/lists/netdev/msg534913.html
introduced by commit 838e96904ff3 ("bpf: Introduce bpf_func_info").

If CONFIG_BPF is defined and CONFIG_BPF_SYSCALL is not defined,
the following error will appear:
  kernel/bpf/core.c:414: undefined reference to `btf_type_by_id'
  kernel/bpf/core.c:415: undefined reference to `btf_name_by_offset'

When CONFIG_BPF_SYSCALL is not defined,
let us define stub inline functions for btf_type_by_id()
and btf_name_by_offset() in include/linux/btf.h.
This way, the compilation failure can be avoided.

Fixes: 838e96904ff3 ("bpf: Introduce bpf_func_info")
Reported-by: kbuild test robot <lkp@intel.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/btf.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 7f2c0a4a45ea..8c2199b5d250 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -46,7 +46,21 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
 int btf_get_fd_by_id(u32 id);
 u32 btf_id(const struct btf *btf);
+
+#ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
+#else
+static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
+						    u32 type_id)
+{
+	return NULL;
+}
+static inline const char *btf_name_by_offset(const struct btf *btf,
+					     u32 offset)
+{
+	return NULL;
+}
+#endif
 
 #endif
-- 
cgit v1.2.3


From 5b79c72e965a21da08f1e498649d514cdb82712e Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Tue, 20 Nov 2018 15:55:05 -0800
Subject: net: dsa: microchip: replace license with GPL

Replace license with GPL.

Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Reviewed-by: Woojung Huh <Woojung.Huh@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz_9477_reg.h | 17 +++--------------
 drivers/net/dsa/microchip/ksz_common.c   | 15 ++-------------
 drivers/net/dsa/microchip/ksz_priv.h     | 17 +++--------------
 drivers/net/dsa/microchip/ksz_spi.c      | 15 ++-------------
 4 files changed, 10 insertions(+), 54 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz_9477_reg.h b/drivers/net/dsa/microchip/ksz_9477_reg.h
index 6aa6752035a1..2938e892b631 100644
--- a/drivers/net/dsa/microchip/ksz_9477_reg.h
+++ b/drivers/net/dsa/microchip/ksz_9477_reg.h
@@ -1,19 +1,8 @@
-/*
- * Microchip KSZ9477 register definitions
- *
- * Copyright (C) 2017
+/* SPDX-License-Identifier: GPL-2.0
  *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
+ * Microchip KSZ9477 register definitions
  *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ * Copyright (C) 2017-2018 Microchip Technology Inc.
  */
 
 #ifndef __KSZ9477_REGS_H
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 86b6464b4525..d47d03b2623b 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Microchip switch driver main logic
  *
- * Copyright (C) 2017
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ * Copyright (C) 2017-2018 Microchip Technology Inc.
  */
 
 #include <linux/delay.h>
diff --git a/drivers/net/dsa/microchip/ksz_priv.h b/drivers/net/dsa/microchip/ksz_priv.h
index 2a98dbd51456..6a27933bef74 100644
--- a/drivers/net/dsa/microchip/ksz_priv.h
+++ b/drivers/net/dsa/microchip/ksz_priv.h
@@ -1,19 +1,8 @@
-/*
- * Microchip KSZ series switch common definitions
- *
- * Copyright (C) 2017
+/* SPDX-License-Identifier: GPL-2.0
  *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
+ * Microchip KSZ series switch common definitions
  *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ * Copyright (C) 2017-2018 Microchip Technology Inc.
  */
 
 #ifndef __KSZ_PRIV_H
diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c
index 8c1778b42701..dc70f486719c 100644
--- a/drivers/net/dsa/microchip/ksz_spi.c
+++ b/drivers/net/dsa/microchip/ksz_spi.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Microchip KSZ series register access through SPI
  *
- * Copyright (C) 2017
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ * Copyright (C) 2017-2018 Microchip Technology Inc.
  */
 
 #include <asm/unaligned.h>
-- 
cgit v1.2.3


From 9bc981c35530c136e61934f682dfef765fadcb5a Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Tue, 20 Nov 2018 15:55:06 -0800
Subject: net: dsa: microchip: clean up code

Clean up code according to patch check suggestions.

Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Reviewed-by: Woojung Huh <Woojung.Huh@microchip.com>
Reviewed-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz_common.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index d47d03b2623b..eb833dfeb26c 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -890,9 +890,9 @@ static void ksz_port_mdb_add(struct dsa_switch *ds, int port,
 
 		if (static_table[0] & ALU_V_STATIC_VALID) {
 			/* check this has same vid & mac address */
-			if (((static_table[2] >> ALU_V_FID_S) == (mdb->vid)) &&
+			if (((static_table[2] >> ALU_V_FID_S) == mdb->vid) &&
 			    ((static_table[2] & ALU_V_MAC_ADDR_HI) == mac_hi) &&
-			    (static_table[3] == mac_lo)) {
+			    static_table[3] == mac_lo) {
 				/* found matching one */
 				break;
 			}
@@ -963,9 +963,9 @@ static int ksz_port_mdb_del(struct dsa_switch *ds, int port,
 		if (static_table[0] & ALU_V_STATIC_VALID) {
 			/* check this has same vid & mac address */
 
-			if (((static_table[2] >> ALU_V_FID_S) == (mdb->vid)) &&
+			if (((static_table[2] >> ALU_V_FID_S) == mdb->vid) &&
 			    ((static_table[2] & ALU_V_MAC_ADDR_HI) == mac_hi) &&
-			    (static_table[3] == mac_lo)) {
+			    static_table[3] == mac_lo) {
 				/* found matching one */
 				break;
 			}
-- 
cgit v1.2.3


From 353592781d44d2900931b4e30059661cb5183af8 Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Tue, 20 Nov 2018 15:55:07 -0800
Subject: net: dsa: microchip: rename some functions with ksz9477 prefix

Rename some functions with ksz9477 prefix to separate chip specific code
from common code.

Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Reviewed-by: Woojung Huh <Woojung.Huh@microchip.com>
Reviewed-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz_common.c | 116 +++++++++++++++++----------------
 1 file changed, 59 insertions(+), 57 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index eb833dfeb26c..50b24dc39962 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -253,9 +253,8 @@ static int wait_alu_sta_ready(struct ksz_device *dev, u32 waiton, int timeout)
 	return 0;
 }
 
-static int ksz_reset_switch(struct dsa_switch *ds)
+static int ksz9477_reset_switch(struct ksz_device *dev)
 {
-	struct ksz_device *dev = ds->priv;
 	u8 data8;
 	u16 data16;
 	u32 data32;
@@ -288,7 +287,7 @@ static int ksz_reset_switch(struct dsa_switch *ds)
 	return 0;
 }
 
-static void port_setup(struct ksz_device *dev, int port, bool cpu_port)
+static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 {
 	u8 data8;
 	u16 data16;
@@ -334,7 +333,7 @@ static void port_setup(struct ksz_device *dev, int port, bool cpu_port)
 	ksz_pread16(dev, port, REG_PORT_PHY_INT_ENABLE, &data16);
 }
 
-static void ksz_config_cpu_port(struct dsa_switch *ds)
+static void ksz9477_config_cpu_port(struct dsa_switch *ds)
 {
 	struct ksz_device *dev = ds->priv;
 	int i;
@@ -346,12 +345,12 @@ static void ksz_config_cpu_port(struct dsa_switch *ds)
 			dev->cpu_port = i;
 
 			/* enable cpu port */
-			port_setup(dev, i, true);
+			ksz9477_port_setup(dev, i, true);
 		}
 	}
 }
 
-static int ksz_setup(struct dsa_switch *ds)
+static int ksz9477_setup(struct dsa_switch *ds)
 {
 	struct ksz_device *dev = ds->priv;
 	int ret = 0;
@@ -361,7 +360,7 @@ static int ksz_setup(struct dsa_switch *ds)
 	if (!dev->vlan_cache)
 		return -ENOMEM;
 
-	ret = ksz_reset_switch(ds);
+	ret = ksz9477_reset_switch(dev);
 	if (ret) {
 		dev_err(ds->dev, "failed to reset switch\n");
 		return ret;
@@ -370,7 +369,7 @@ static int ksz_setup(struct dsa_switch *ds)
 	/* accept packet up to 2000bytes */
 	ksz_cfg(dev, REG_SW_MAC_CTRL_1, SW_LEGAL_PACKET_DISABLE, true);
 
-	ksz_config_cpu_port(ds);
+	ksz9477_config_cpu_port(ds);
 
 	ksz_cfg(dev, REG_SW_MAC_CTRL_1, MULTICAST_STORM_DISABLE, true);
 
@@ -383,13 +382,13 @@ static int ksz_setup(struct dsa_switch *ds)
 	return 0;
 }
 
-static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds,
-						  int port)
+static enum dsa_tag_protocol ksz9477_get_tag_protocol(struct dsa_switch *ds,
+						      int port)
 {
 	return DSA_TAG_PROTO_KSZ;
 }
 
-static int ksz_phy_read16(struct dsa_switch *ds, int addr, int reg)
+static int ksz9477_phy_read16(struct dsa_switch *ds, int addr, int reg)
 {
 	struct ksz_device *dev = ds->priv;
 	u16 val = 0;
@@ -399,7 +398,8 @@ static int ksz_phy_read16(struct dsa_switch *ds, int addr, int reg)
 	return val;
 }
 
-static int ksz_phy_write16(struct dsa_switch *ds, int addr, int reg, u16 val)
+static int ksz9477_phy_write16(struct dsa_switch *ds, int addr, int reg,
+			       u16 val)
 {
 	struct ksz_device *dev = ds->priv;
 
@@ -414,7 +414,7 @@ static int ksz_enable_port(struct dsa_switch *ds, int port,
 	struct ksz_device *dev = ds->priv;
 
 	/* setup slave port */
-	port_setup(dev, port, false);
+	ksz9477_port_setup(dev, port, false);
 
 	return 0;
 }
@@ -436,8 +436,8 @@ static int ksz_sset_count(struct dsa_switch *ds, int port, int sset)
 	return TOTAL_SWITCH_COUNTER_NUM;
 }
 
-static void ksz_get_strings(struct dsa_switch *ds, int port,
-			    u32 stringset, uint8_t *buf)
+static void ksz9477_get_strings(struct dsa_switch *ds, int port,
+				u32 stringset, uint8_t *buf)
 {
 	int i;
 
@@ -490,7 +490,8 @@ static void ksz_get_ethtool_stats(struct dsa_switch *ds, int port,
 	mutex_unlock(&dev->stats_mutex);
 }
 
-static void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
+static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port,
+				       u8 state)
 {
 	struct ksz_device *dev = ds->priv;
 	u8 data;
@@ -535,7 +536,8 @@ static void ksz_port_fast_age(struct dsa_switch *ds, int port)
 	ksz_write8(dev, REG_SW_LUE_CTRL_1, data8);
 }
 
-static int ksz_port_vlan_filtering(struct dsa_switch *ds, int port, bool flag)
+static int ksz9477_port_vlan_filtering(struct dsa_switch *ds, int port,
+				       bool flag)
 {
 	struct ksz_device *dev = ds->priv;
 
@@ -562,8 +564,8 @@ static int ksz_port_vlan_prepare(struct dsa_switch *ds, int port,
 	return 0;
 }
 
-static void ksz_port_vlan_add(struct dsa_switch *ds, int port,
-			      const struct switchdev_obj_port_vlan *vlan)
+static void ksz9477_port_vlan_add(struct dsa_switch *ds, int port,
+				  const struct switchdev_obj_port_vlan *vlan)
 {
 	struct ksz_device *dev = ds->priv;
 	u32 vlan_table[3];
@@ -596,8 +598,8 @@ static void ksz_port_vlan_add(struct dsa_switch *ds, int port,
 	}
 }
 
-static int ksz_port_vlan_del(struct dsa_switch *ds, int port,
-			     const struct switchdev_obj_port_vlan *vlan)
+static int ksz9477_port_vlan_del(struct dsa_switch *ds, int port,
+				 const struct switchdev_obj_port_vlan *vlan)
 {
 	struct ksz_device *dev = ds->priv;
 	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
@@ -652,8 +654,8 @@ struct alu_struct {
 	u8	mac[ETH_ALEN];
 };
 
-static int ksz_port_fdb_add(struct dsa_switch *ds, int port,
-			    const unsigned char *addr, u16 vid)
+static int ksz9477_port_fdb_add(struct dsa_switch *ds, int port,
+				const unsigned char *addr, u16 vid)
 {
 	struct ksz_device *dev = ds->priv;
 	u32 alu_table[4];
@@ -709,8 +711,8 @@ exit:
 	return ret;
 }
 
-static int ksz_port_fdb_del(struct dsa_switch *ds, int port,
-			    const unsigned char *addr, u16 vid)
+static int ksz9477_port_fdb_del(struct dsa_switch *ds, int port,
+				const unsigned char *addr, u16 vid)
 {
 	struct ksz_device *dev = ds->priv;
 	u32 alu_table[4];
@@ -799,8 +801,8 @@ static void convert_alu(struct alu_struct *alu, u32 *alu_table)
 	alu->mac[5] = alu_table[3] & 0xFF;
 }
 
-static int ksz_port_fdb_dump(struct dsa_switch *ds, int port,
-			     dsa_fdb_dump_cb_t *cb, void *data)
+static int ksz9477_port_fdb_dump(struct dsa_switch *ds, int port,
+				 dsa_fdb_dump_cb_t *cb, void *data)
 {
 	struct ksz_device *dev = ds->priv;
 	int ret = 0;
@@ -858,8 +860,8 @@ static int ksz_port_mdb_prepare(struct dsa_switch *ds, int port,
 	return 0;
 }
 
-static void ksz_port_mdb_add(struct dsa_switch *ds, int port,
-			     const struct switchdev_obj_port_mdb *mdb)
+static void ksz9477_port_mdb_add(struct dsa_switch *ds, int port,
+				 const struct switchdev_obj_port_mdb *mdb)
 {
 	struct ksz_device *dev = ds->priv;
 	u32 static_table[4];
@@ -928,8 +930,8 @@ exit:
 	mutex_unlock(&dev->alu_mutex);
 }
 
-static int ksz_port_mdb_del(struct dsa_switch *ds, int port,
-			    const struct switchdev_obj_port_mdb *mdb)
+static int ksz9477_port_mdb_del(struct dsa_switch *ds, int port,
+				const struct switchdev_obj_port_mdb *mdb)
 {
 	struct ksz_device *dev = ds->priv;
 	u32 static_table[4];
@@ -1005,9 +1007,9 @@ exit:
 	return ret;
 }
 
-static int ksz_port_mirror_add(struct dsa_switch *ds, int port,
-			       struct dsa_mall_mirror_tc_entry *mirror,
-			       bool ingress)
+static int ksz9477_port_mirror_add(struct dsa_switch *ds, int port,
+				   struct dsa_mall_mirror_tc_entry *mirror,
+				   bool ingress)
 {
 	struct ksz_device *dev = ds->priv;
 
@@ -1027,8 +1029,8 @@ static int ksz_port_mirror_add(struct dsa_switch *ds, int port,
 	return 0;
 }
 
-static void ksz_port_mirror_del(struct dsa_switch *ds, int port,
-				struct dsa_mall_mirror_tc_entry *mirror)
+static void ksz9477_port_mirror_del(struct dsa_switch *ds, int port,
+				    struct dsa_mall_mirror_tc_entry *mirror)
 {
 	struct ksz_device *dev = ds->priv;
 	u8 data;
@@ -1046,29 +1048,29 @@ static void ksz_port_mirror_del(struct dsa_switch *ds, int port,
 }
 
 static const struct dsa_switch_ops ksz_switch_ops = {
-	.get_tag_protocol	= ksz_get_tag_protocol,
-	.setup			= ksz_setup,
-	.phy_read		= ksz_phy_read16,
-	.phy_write		= ksz_phy_write16,
+	.get_tag_protocol	= ksz9477_get_tag_protocol,
+	.setup			= ksz9477_setup,
+	.phy_read		= ksz9477_phy_read16,
+	.phy_write		= ksz9477_phy_write16,
 	.port_enable		= ksz_enable_port,
 	.port_disable		= ksz_disable_port,
-	.get_strings		= ksz_get_strings,
+	.get_strings		= ksz9477_get_strings,
 	.get_ethtool_stats	= ksz_get_ethtool_stats,
 	.get_sset_count		= ksz_sset_count,
-	.port_stp_state_set	= ksz_port_stp_state_set,
+	.port_stp_state_set	= ksz9477_port_stp_state_set,
 	.port_fast_age		= ksz_port_fast_age,
-	.port_vlan_filtering	= ksz_port_vlan_filtering,
+	.port_vlan_filtering	= ksz9477_port_vlan_filtering,
 	.port_vlan_prepare	= ksz_port_vlan_prepare,
-	.port_vlan_add		= ksz_port_vlan_add,
-	.port_vlan_del		= ksz_port_vlan_del,
-	.port_fdb_dump		= ksz_port_fdb_dump,
-	.port_fdb_add		= ksz_port_fdb_add,
-	.port_fdb_del		= ksz_port_fdb_del,
+	.port_vlan_add		= ksz9477_port_vlan_add,
+	.port_vlan_del		= ksz9477_port_vlan_del,
+	.port_fdb_dump		= ksz9477_port_fdb_dump,
+	.port_fdb_add		= ksz9477_port_fdb_add,
+	.port_fdb_del		= ksz9477_port_fdb_del,
 	.port_mdb_prepare       = ksz_port_mdb_prepare,
-	.port_mdb_add           = ksz_port_mdb_add,
-	.port_mdb_del           = ksz_port_mdb_del,
-	.port_mirror_add	= ksz_port_mirror_add,
-	.port_mirror_del	= ksz_port_mirror_del,
+	.port_mdb_add           = ksz9477_port_mdb_add,
+	.port_mdb_del           = ksz9477_port_mdb_del,
+	.port_mirror_add	= ksz9477_port_mirror_add,
+	.port_mirror_del	= ksz9477_port_mirror_del,
 };
 
 struct ksz_chip_data {
@@ -1081,7 +1083,7 @@ struct ksz_chip_data {
 	int port_cnt;
 };
 
-static const struct ksz_chip_data ksz_switch_chips[] = {
+static const struct ksz_chip_data ksz9477_switch_chips[] = {
 	{
 		.chip_id = 0x00947700,
 		.dev_name = "KSZ9477",
@@ -1102,14 +1104,14 @@ static const struct ksz_chip_data ksz_switch_chips[] = {
 	},
 };
 
-static int ksz_switch_init(struct ksz_device *dev)
+static int ksz9477_switch_init(struct ksz_device *dev)
 {
 	int i;
 
 	dev->ds->ops = &ksz_switch_ops;
 
-	for (i = 0; i < ARRAY_SIZE(ksz_switch_chips); i++) {
-		const struct ksz_chip_data *chip = &ksz_switch_chips[i];
+	for (i = 0; i < ARRAY_SIZE(ksz9477_switch_chips); i++) {
+		const struct ksz_chip_data *chip = &ksz9477_switch_chips[i];
 
 		if (dev->chip_id == chip->chip_id) {
 			dev->name = chip->dev_name;
@@ -1198,7 +1200,7 @@ int ksz_switch_register(struct ksz_device *dev)
 	if (ksz_switch_detect(dev))
 		return -EINVAL;
 
-	ret = ksz_switch_init(dev);
+	ret = ksz9477_switch_init(dev);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 74a7194f15b33789f2423391d4c4e26fa96db752 Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Tue, 20 Nov 2018 15:55:08 -0800
Subject: net: dsa: microchip: rename ksz_spi.c to ksz9477_spi.c

Rename ksz_spi.c to ksz9477_spi.c and update Kconfig in preparation to add
more KSZ switch drivers.

Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Reviewed-by: Woojung Huh <Woojung.Huh@microchip.com>
Reviewed-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/Kconfig       |  12 +-
 drivers/net/dsa/microchip/Makefile      |   4 +-
 drivers/net/dsa/microchip/ksz9477_spi.c | 206 ++++++++++++++++++++++++++++++++
 drivers/net/dsa/microchip/ksz_spi.c     | 206 --------------------------------
 4 files changed, 214 insertions(+), 214 deletions(-)
 create mode 100644 drivers/net/dsa/microchip/ksz9477_spi.c
 delete mode 100644 drivers/net/dsa/microchip/ksz_spi.c

diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig
index a8b8f59099ce..4e25fe4d7979 100644
--- a/drivers/net/dsa/microchip/Kconfig
+++ b/drivers/net/dsa/microchip/Kconfig
@@ -1,12 +1,12 @@
-menuconfig MICROCHIP_KSZ
-	tristate "Microchip KSZ series switch support"
+menuconfig NET_DSA_MICROCHIP_KSZ9477
+	tristate "Microchip KSZ9477 series switch support"
 	depends on NET_DSA
 	select NET_DSA_TAG_KSZ
 	help
-	  This driver adds support for Microchip KSZ switch chips.
+	  This driver adds support for Microchip KSZ9477 switch chips.
 
-config MICROCHIP_KSZ_SPI_DRIVER
-	tristate "KSZ series SPI connected switch driver"
-	depends on MICROCHIP_KSZ && SPI
+config NET_DSA_MICROCHIP_KSZ9477_SPI
+	tristate "KSZ9477 series SPI connected switch driver"
+	depends on NET_DSA_MICROCHIP_KSZ9477 && SPI
 	help
 	  Select to enable support for registering switches configured through SPI.
diff --git a/drivers/net/dsa/microchip/Makefile b/drivers/net/dsa/microchip/Makefile
index ed335e29fae8..9393e73e8c97 100644
--- a/drivers/net/dsa/microchip/Makefile
+++ b/drivers/net/dsa/microchip/Makefile
@@ -1,2 +1,2 @@
-obj-$(CONFIG_MICROCHIP_KSZ)	        += ksz_common.o
-obj-$(CONFIG_MICROCHIP_KSZ_SPI_DRIVER)	+= ksz_spi.o
+obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ9477)		+= ksz_common.o
+obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ9477_SPI)	+= ksz9477_spi.o
diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c
new file mode 100644
index 000000000000..dc70f486719c
--- /dev/null
+++ b/drivers/net/dsa/microchip/ksz9477_spi.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Microchip KSZ series register access through SPI
+ *
+ * Copyright (C) 2017-2018 Microchip Technology Inc.
+ */
+
+#include <asm/unaligned.h>
+
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/spi/spi.h>
+
+#include "ksz_priv.h"
+
+/* SPI frame opcodes */
+#define KS_SPIOP_RD			3
+#define KS_SPIOP_WR			2
+
+#define SPI_ADDR_SHIFT			24
+#define SPI_ADDR_MASK			(BIT(SPI_ADDR_SHIFT) - 1)
+#define SPI_TURNAROUND_SHIFT		5
+
+static int ksz_spi_read_reg(struct spi_device *spi, u32 reg, u8 *val,
+			    unsigned int len)
+{
+	u32 txbuf;
+	int ret;
+
+	txbuf = reg & SPI_ADDR_MASK;
+	txbuf |= KS_SPIOP_RD << SPI_ADDR_SHIFT;
+	txbuf <<= SPI_TURNAROUND_SHIFT;
+	txbuf = cpu_to_be32(txbuf);
+
+	ret = spi_write_then_read(spi, &txbuf, 4, val, len);
+	return ret;
+}
+
+static int ksz_spi_read(struct ksz_device *dev, u32 reg, u8 *data,
+			unsigned int len)
+{
+	struct spi_device *spi = dev->priv;
+
+	return ksz_spi_read_reg(spi, reg, data, len);
+}
+
+static int ksz_spi_read8(struct ksz_device *dev, u32 reg, u8 *val)
+{
+	return ksz_spi_read(dev, reg, val, 1);
+}
+
+static int ksz_spi_read16(struct ksz_device *dev, u32 reg, u16 *val)
+{
+	int ret = ksz_spi_read(dev, reg, (u8 *)val, 2);
+
+	if (!ret)
+		*val = be16_to_cpu(*val);
+
+	return ret;
+}
+
+static int ksz_spi_read24(struct ksz_device *dev, u32 reg, u32 *val)
+{
+	int ret;
+
+	*val = 0;
+	ret = ksz_spi_read(dev, reg, (u8 *)val, 3);
+	if (!ret) {
+		*val = be32_to_cpu(*val);
+		/* convert to 24bit */
+		*val >>= 8;
+	}
+
+	return ret;
+}
+
+static int ksz_spi_read32(struct ksz_device *dev, u32 reg, u32 *val)
+{
+	int ret = ksz_spi_read(dev, reg, (u8 *)val, 4);
+
+	if (!ret)
+		*val = be32_to_cpu(*val);
+
+	return ret;
+}
+
+static int ksz_spi_write_reg(struct spi_device *spi, u32 reg, u8 *val,
+			     unsigned int len)
+{
+	u32 txbuf;
+	u8 data[12];
+	int i;
+
+	txbuf = reg & SPI_ADDR_MASK;
+	txbuf |= (KS_SPIOP_WR << SPI_ADDR_SHIFT);
+	txbuf <<= SPI_TURNAROUND_SHIFT;
+	txbuf = cpu_to_be32(txbuf);
+
+	data[0] = txbuf & 0xFF;
+	data[1] = (txbuf & 0xFF00) >> 8;
+	data[2] = (txbuf & 0xFF0000) >> 16;
+	data[3] = (txbuf & 0xFF000000) >> 24;
+	for (i = 0; i < len; i++)
+		data[i + 4] = val[i];
+
+	return spi_write(spi, &data, 4 + len);
+}
+
+static int ksz_spi_write8(struct ksz_device *dev, u32 reg, u8 value)
+{
+	struct spi_device *spi = dev->priv;
+
+	return ksz_spi_write_reg(spi, reg, &value, 1);
+}
+
+static int ksz_spi_write16(struct ksz_device *dev, u32 reg, u16 value)
+{
+	struct spi_device *spi = dev->priv;
+
+	value = cpu_to_be16(value);
+	return ksz_spi_write_reg(spi, reg, (u8 *)&value, 2);
+}
+
+static int ksz_spi_write24(struct ksz_device *dev, u32 reg, u32 value)
+{
+	struct spi_device *spi = dev->priv;
+
+	/* make it to big endian 24bit from MSB */
+	value <<= 8;
+	value = cpu_to_be32(value);
+	return ksz_spi_write_reg(spi, reg, (u8 *)&value, 3);
+}
+
+static int ksz_spi_write32(struct ksz_device *dev, u32 reg, u32 value)
+{
+	struct spi_device *spi = dev->priv;
+
+	value = cpu_to_be32(value);
+	return ksz_spi_write_reg(spi, reg, (u8 *)&value, 4);
+}
+
+static const struct ksz_io_ops ksz_spi_ops = {
+	.read8 = ksz_spi_read8,
+	.read16 = ksz_spi_read16,
+	.read24 = ksz_spi_read24,
+	.read32 = ksz_spi_read32,
+	.write8 = ksz_spi_write8,
+	.write16 = ksz_spi_write16,
+	.write24 = ksz_spi_write24,
+	.write32 = ksz_spi_write32,
+};
+
+static int ksz_spi_probe(struct spi_device *spi)
+{
+	struct ksz_device *dev;
+	int ret;
+
+	dev = ksz_switch_alloc(&spi->dev, &ksz_spi_ops, spi);
+	if (!dev)
+		return -ENOMEM;
+
+	if (spi->dev.platform_data)
+		dev->pdata = spi->dev.platform_data;
+
+	ret = ksz_switch_register(dev);
+	if (ret)
+		return ret;
+
+	spi_set_drvdata(spi, dev);
+
+	return 0;
+}
+
+static int ksz_spi_remove(struct spi_device *spi)
+{
+	struct ksz_device *dev = spi_get_drvdata(spi);
+
+	if (dev)
+		ksz_switch_remove(dev);
+
+	return 0;
+}
+
+static const struct of_device_id ksz_dt_ids[] = {
+	{ .compatible = "microchip,ksz9477" },
+	{ .compatible = "microchip,ksz9897" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, ksz_dt_ids);
+
+static struct spi_driver ksz_spi_driver = {
+	.driver = {
+		.name	= "ksz9477-switch",
+		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(ksz_dt_ids),
+	},
+	.probe	= ksz_spi_probe,
+	.remove	= ksz_spi_remove,
+};
+
+module_spi_driver(ksz_spi_driver);
+
+MODULE_AUTHOR("Woojung Huh <Woojung.Huh@microchip.com>");
+MODULE_DESCRIPTION("Microchip KSZ Series Switch SPI access Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c
deleted file mode 100644
index dc70f486719c..000000000000
--- a/drivers/net/dsa/microchip/ksz_spi.c
+++ /dev/null
@@ -1,206 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Microchip KSZ series register access through SPI
- *
- * Copyright (C) 2017-2018 Microchip Technology Inc.
- */
-
-#include <asm/unaligned.h>
-
-#include <linux/delay.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/spi/spi.h>
-
-#include "ksz_priv.h"
-
-/* SPI frame opcodes */
-#define KS_SPIOP_RD			3
-#define KS_SPIOP_WR			2
-
-#define SPI_ADDR_SHIFT			24
-#define SPI_ADDR_MASK			(BIT(SPI_ADDR_SHIFT) - 1)
-#define SPI_TURNAROUND_SHIFT		5
-
-static int ksz_spi_read_reg(struct spi_device *spi, u32 reg, u8 *val,
-			    unsigned int len)
-{
-	u32 txbuf;
-	int ret;
-
-	txbuf = reg & SPI_ADDR_MASK;
-	txbuf |= KS_SPIOP_RD << SPI_ADDR_SHIFT;
-	txbuf <<= SPI_TURNAROUND_SHIFT;
-	txbuf = cpu_to_be32(txbuf);
-
-	ret = spi_write_then_read(spi, &txbuf, 4, val, len);
-	return ret;
-}
-
-static int ksz_spi_read(struct ksz_device *dev, u32 reg, u8 *data,
-			unsigned int len)
-{
-	struct spi_device *spi = dev->priv;
-
-	return ksz_spi_read_reg(spi, reg, data, len);
-}
-
-static int ksz_spi_read8(struct ksz_device *dev, u32 reg, u8 *val)
-{
-	return ksz_spi_read(dev, reg, val, 1);
-}
-
-static int ksz_spi_read16(struct ksz_device *dev, u32 reg, u16 *val)
-{
-	int ret = ksz_spi_read(dev, reg, (u8 *)val, 2);
-
-	if (!ret)
-		*val = be16_to_cpu(*val);
-
-	return ret;
-}
-
-static int ksz_spi_read24(struct ksz_device *dev, u32 reg, u32 *val)
-{
-	int ret;
-
-	*val = 0;
-	ret = ksz_spi_read(dev, reg, (u8 *)val, 3);
-	if (!ret) {
-		*val = be32_to_cpu(*val);
-		/* convert to 24bit */
-		*val >>= 8;
-	}
-
-	return ret;
-}
-
-static int ksz_spi_read32(struct ksz_device *dev, u32 reg, u32 *val)
-{
-	int ret = ksz_spi_read(dev, reg, (u8 *)val, 4);
-
-	if (!ret)
-		*val = be32_to_cpu(*val);
-
-	return ret;
-}
-
-static int ksz_spi_write_reg(struct spi_device *spi, u32 reg, u8 *val,
-			     unsigned int len)
-{
-	u32 txbuf;
-	u8 data[12];
-	int i;
-
-	txbuf = reg & SPI_ADDR_MASK;
-	txbuf |= (KS_SPIOP_WR << SPI_ADDR_SHIFT);
-	txbuf <<= SPI_TURNAROUND_SHIFT;
-	txbuf = cpu_to_be32(txbuf);
-
-	data[0] = txbuf & 0xFF;
-	data[1] = (txbuf & 0xFF00) >> 8;
-	data[2] = (txbuf & 0xFF0000) >> 16;
-	data[3] = (txbuf & 0xFF000000) >> 24;
-	for (i = 0; i < len; i++)
-		data[i + 4] = val[i];
-
-	return spi_write(spi, &data, 4 + len);
-}
-
-static int ksz_spi_write8(struct ksz_device *dev, u32 reg, u8 value)
-{
-	struct spi_device *spi = dev->priv;
-
-	return ksz_spi_write_reg(spi, reg, &value, 1);
-}
-
-static int ksz_spi_write16(struct ksz_device *dev, u32 reg, u16 value)
-{
-	struct spi_device *spi = dev->priv;
-
-	value = cpu_to_be16(value);
-	return ksz_spi_write_reg(spi, reg, (u8 *)&value, 2);
-}
-
-static int ksz_spi_write24(struct ksz_device *dev, u32 reg, u32 value)
-{
-	struct spi_device *spi = dev->priv;
-
-	/* make it to big endian 24bit from MSB */
-	value <<= 8;
-	value = cpu_to_be32(value);
-	return ksz_spi_write_reg(spi, reg, (u8 *)&value, 3);
-}
-
-static int ksz_spi_write32(struct ksz_device *dev, u32 reg, u32 value)
-{
-	struct spi_device *spi = dev->priv;
-
-	value = cpu_to_be32(value);
-	return ksz_spi_write_reg(spi, reg, (u8 *)&value, 4);
-}
-
-static const struct ksz_io_ops ksz_spi_ops = {
-	.read8 = ksz_spi_read8,
-	.read16 = ksz_spi_read16,
-	.read24 = ksz_spi_read24,
-	.read32 = ksz_spi_read32,
-	.write8 = ksz_spi_write8,
-	.write16 = ksz_spi_write16,
-	.write24 = ksz_spi_write24,
-	.write32 = ksz_spi_write32,
-};
-
-static int ksz_spi_probe(struct spi_device *spi)
-{
-	struct ksz_device *dev;
-	int ret;
-
-	dev = ksz_switch_alloc(&spi->dev, &ksz_spi_ops, spi);
-	if (!dev)
-		return -ENOMEM;
-
-	if (spi->dev.platform_data)
-		dev->pdata = spi->dev.platform_data;
-
-	ret = ksz_switch_register(dev);
-	if (ret)
-		return ret;
-
-	spi_set_drvdata(spi, dev);
-
-	return 0;
-}
-
-static int ksz_spi_remove(struct spi_device *spi)
-{
-	struct ksz_device *dev = spi_get_drvdata(spi);
-
-	if (dev)
-		ksz_switch_remove(dev);
-
-	return 0;
-}
-
-static const struct of_device_id ksz_dt_ids[] = {
-	{ .compatible = "microchip,ksz9477" },
-	{ .compatible = "microchip,ksz9897" },
-	{},
-};
-MODULE_DEVICE_TABLE(of, ksz_dt_ids);
-
-static struct spi_driver ksz_spi_driver = {
-	.driver = {
-		.name	= "ksz9477-switch",
-		.owner	= THIS_MODULE,
-		.of_match_table = of_match_ptr(ksz_dt_ids),
-	},
-	.probe	= ksz_spi_probe,
-	.remove	= ksz_spi_remove,
-};
-
-module_spi_driver(ksz_spi_driver);
-
-MODULE_AUTHOR("Woojung Huh <Woojung.Huh@microchip.com>");
-MODULE_DESCRIPTION("Microchip KSZ Series Switch SPI access Driver");
-MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From c2e866911e2540677c31ee009d8f75cdb4c023aa Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Tue, 20 Nov 2018 15:55:09 -0800
Subject: net: dsa: microchip: break KSZ9477 DSA driver into two files

Break KSZ9477 DSA driver into two files in preparation to add more KSZ
switch drivers.
Add common functions in ksz_common.h so that other KSZ switch drivers
can access code in ksz_common.c.
Add ksz_spi.h for common functions used by KSZ switch SPI drivers.

Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Reviewed-by: Woojung Huh <Woojung.Huh@microchip.com>
Reviewed-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/Kconfig       |    4 +
 drivers/net/dsa/microchip/Makefile      |    3 +-
 drivers/net/dsa/microchip/ksz9477.c     | 1316 +++++++++++++++++++++++++++++++
 drivers/net/dsa/microchip/ksz9477_spi.c |  143 ++--
 drivers/net/dsa/microchip/ksz_common.c  | 1170 ++++-----------------------
 drivers/net/dsa/microchip/ksz_common.h  |  214 +++++
 drivers/net/dsa/microchip/ksz_priv.h    |  226 +++---
 drivers/net/dsa/microchip/ksz_spi.h     |   69 ++
 8 files changed, 1903 insertions(+), 1242 deletions(-)
 create mode 100644 drivers/net/dsa/microchip/ksz9477.c
 create mode 100644 drivers/net/dsa/microchip/ksz_common.h
 create mode 100644 drivers/net/dsa/microchip/ksz_spi.h

diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig
index 4e25fe4d7979..a8caf9249d50 100644
--- a/drivers/net/dsa/microchip/Kconfig
+++ b/drivers/net/dsa/microchip/Kconfig
@@ -1,7 +1,11 @@
+config NET_DSA_MICROCHIP_KSZ_COMMON
+	tristate
+
 menuconfig NET_DSA_MICROCHIP_KSZ9477
 	tristate "Microchip KSZ9477 series switch support"
 	depends on NET_DSA
 	select NET_DSA_TAG_KSZ
+	select NET_DSA_MICROCHIP_KSZ_COMMON
 	help
 	  This driver adds support for Microchip KSZ9477 switch chips.
 
diff --git a/drivers/net/dsa/microchip/Makefile b/drivers/net/dsa/microchip/Makefile
index 9393e73e8c97..3142c18b8f57 100644
--- a/drivers/net/dsa/microchip/Makefile
+++ b/drivers/net/dsa/microchip/Makefile
@@ -1,2 +1,3 @@
-obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ9477)		+= ksz_common.o
+obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ_COMMON)	+= ksz_common.o
+obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ9477)		+= ksz9477.o
 obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ9477_SPI)	+= ksz9477_spi.o
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
new file mode 100644
index 000000000000..80df6c03b340
--- /dev/null
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -0,0 +1,1316 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Microchip KSZ9477 switch driver main logic
+ *
+ * Copyright (C) 2017-2018 Microchip Technology Inc.
+ */
+
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/gpio.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_data/microchip-ksz.h>
+#include <linux/phy.h>
+#include <linux/etherdevice.h>
+#include <linux/if_bridge.h>
+#include <net/dsa.h>
+#include <net/switchdev.h>
+
+#include "ksz_priv.h"
+#include "ksz_common.h"
+#include "ksz_9477_reg.h"
+
+static const struct {
+	int index;
+	char string[ETH_GSTRING_LEN];
+} ksz9477_mib_names[TOTAL_SWITCH_COUNTER_NUM] = {
+	{ 0x00, "rx_hi" },
+	{ 0x01, "rx_undersize" },
+	{ 0x02, "rx_fragments" },
+	{ 0x03, "rx_oversize" },
+	{ 0x04, "rx_jabbers" },
+	{ 0x05, "rx_symbol_err" },
+	{ 0x06, "rx_crc_err" },
+	{ 0x07, "rx_align_err" },
+	{ 0x08, "rx_mac_ctrl" },
+	{ 0x09, "rx_pause" },
+	{ 0x0A, "rx_bcast" },
+	{ 0x0B, "rx_mcast" },
+	{ 0x0C, "rx_ucast" },
+	{ 0x0D, "rx_64_or_less" },
+	{ 0x0E, "rx_65_127" },
+	{ 0x0F, "rx_128_255" },
+	{ 0x10, "rx_256_511" },
+	{ 0x11, "rx_512_1023" },
+	{ 0x12, "rx_1024_1522" },
+	{ 0x13, "rx_1523_2000" },
+	{ 0x14, "rx_2001" },
+	{ 0x15, "tx_hi" },
+	{ 0x16, "tx_late_col" },
+	{ 0x17, "tx_pause" },
+	{ 0x18, "tx_bcast" },
+	{ 0x19, "tx_mcast" },
+	{ 0x1A, "tx_ucast" },
+	{ 0x1B, "tx_deferred" },
+	{ 0x1C, "tx_total_col" },
+	{ 0x1D, "tx_exc_col" },
+	{ 0x1E, "tx_single_col" },
+	{ 0x1F, "tx_mult_col" },
+	{ 0x80, "rx_total" },
+	{ 0x81, "tx_total" },
+	{ 0x82, "rx_discards" },
+	{ 0x83, "tx_discards" },
+};
+
+static void ksz9477_cfg32(struct ksz_device *dev, u32 addr, u32 bits, bool set)
+{
+	u32 data;
+
+	ksz_read32(dev, addr, &data);
+	if (set)
+		data |= bits;
+	else
+		data &= ~bits;
+	ksz_write32(dev, addr, data);
+}
+
+static void ksz9477_port_cfg32(struct ksz_device *dev, int port, int offset,
+			       u32 bits, bool set)
+{
+	u32 addr;
+	u32 data;
+
+	addr = PORT_CTRL_ADDR(port, offset);
+	ksz_read32(dev, addr, &data);
+
+	if (set)
+		data |= bits;
+	else
+		data &= ~bits;
+
+	ksz_write32(dev, addr, data);
+}
+
+static int ksz9477_wait_vlan_ctrl_ready(struct ksz_device *dev, u32 waiton,
+					int timeout)
+{
+	u8 data;
+
+	do {
+		ksz_read8(dev, REG_SW_VLAN_CTRL, &data);
+		if (!(data & waiton))
+			break;
+		usleep_range(1, 10);
+	} while (timeout-- > 0);
+
+	if (timeout <= 0)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int ksz9477_get_vlan_table(struct ksz_device *dev, u16 vid,
+				  u32 *vlan_table)
+{
+	int ret;
+
+	mutex_lock(&dev->vlan_mutex);
+
+	ksz_write16(dev, REG_SW_VLAN_ENTRY_INDEX__2, vid & VLAN_INDEX_M);
+	ksz_write8(dev, REG_SW_VLAN_CTRL, VLAN_READ | VLAN_START);
+
+	/* wait to be cleared */
+	ret = ksz9477_wait_vlan_ctrl_ready(dev, VLAN_START, 1000);
+	if (ret < 0) {
+		dev_dbg(dev->dev, "Failed to read vlan table\n");
+		goto exit;
+	}
+
+	ksz_read32(dev, REG_SW_VLAN_ENTRY__4, &vlan_table[0]);
+	ksz_read32(dev, REG_SW_VLAN_ENTRY_UNTAG__4, &vlan_table[1]);
+	ksz_read32(dev, REG_SW_VLAN_ENTRY_PORTS__4, &vlan_table[2]);
+
+	ksz_write8(dev, REG_SW_VLAN_CTRL, 0);
+
+exit:
+	mutex_unlock(&dev->vlan_mutex);
+
+	return ret;
+}
+
+static int ksz9477_set_vlan_table(struct ksz_device *dev, u16 vid,
+				  u32 *vlan_table)
+{
+	int ret;
+
+	mutex_lock(&dev->vlan_mutex);
+
+	ksz_write32(dev, REG_SW_VLAN_ENTRY__4, vlan_table[0]);
+	ksz_write32(dev, REG_SW_VLAN_ENTRY_UNTAG__4, vlan_table[1]);
+	ksz_write32(dev, REG_SW_VLAN_ENTRY_PORTS__4, vlan_table[2]);
+
+	ksz_write16(dev, REG_SW_VLAN_ENTRY_INDEX__2, vid & VLAN_INDEX_M);
+	ksz_write8(dev, REG_SW_VLAN_CTRL, VLAN_START | VLAN_WRITE);
+
+	/* wait to be cleared */
+	ret = ksz9477_wait_vlan_ctrl_ready(dev, VLAN_START, 1000);
+	if (ret < 0) {
+		dev_dbg(dev->dev, "Failed to write vlan table\n");
+		goto exit;
+	}
+
+	ksz_write8(dev, REG_SW_VLAN_CTRL, 0);
+
+	/* update vlan cache table */
+	dev->vlan_cache[vid].table[0] = vlan_table[0];
+	dev->vlan_cache[vid].table[1] = vlan_table[1];
+	dev->vlan_cache[vid].table[2] = vlan_table[2];
+
+exit:
+	mutex_unlock(&dev->vlan_mutex);
+
+	return ret;
+}
+
+static void ksz9477_read_table(struct ksz_device *dev, u32 *table)
+{
+	ksz_read32(dev, REG_SW_ALU_VAL_A, &table[0]);
+	ksz_read32(dev, REG_SW_ALU_VAL_B, &table[1]);
+	ksz_read32(dev, REG_SW_ALU_VAL_C, &table[2]);
+	ksz_read32(dev, REG_SW_ALU_VAL_D, &table[3]);
+}
+
+static void ksz9477_write_table(struct ksz_device *dev, u32 *table)
+{
+	ksz_write32(dev, REG_SW_ALU_VAL_A, table[0]);
+	ksz_write32(dev, REG_SW_ALU_VAL_B, table[1]);
+	ksz_write32(dev, REG_SW_ALU_VAL_C, table[2]);
+	ksz_write32(dev, REG_SW_ALU_VAL_D, table[3]);
+}
+
+static int ksz9477_wait_alu_ready(struct ksz_device *dev, u32 waiton,
+				  int timeout)
+{
+	u32 data;
+
+	do {
+		ksz_read32(dev, REG_SW_ALU_CTRL__4, &data);
+		if (!(data & waiton))
+			break;
+		usleep_range(1, 10);
+	} while (timeout-- > 0);
+
+	if (timeout <= 0)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int ksz9477_wait_alu_sta_ready(struct ksz_device *dev, u32 waiton,
+				      int timeout)
+{
+	u32 data;
+
+	do {
+		ksz_read32(dev, REG_SW_ALU_STAT_CTRL__4, &data);
+		if (!(data & waiton))
+			break;
+		usleep_range(1, 10);
+	} while (timeout-- > 0);
+
+	if (timeout <= 0)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int ksz9477_reset_switch(struct ksz_device *dev)
+{
+	u8 data8;
+	u16 data16;
+	u32 data32;
+
+	/* reset switch */
+	ksz_cfg(dev, REG_SW_OPERATION, SW_RESET, true);
+
+	/* turn off SPI DO Edge select */
+	ksz_read8(dev, REG_SW_GLOBAL_SERIAL_CTRL_0, &data8);
+	data8 &= ~SPI_AUTO_EDGE_DETECTION;
+	ksz_write8(dev, REG_SW_GLOBAL_SERIAL_CTRL_0, data8);
+
+	/* default configuration */
+	ksz_read8(dev, REG_SW_LUE_CTRL_1, &data8);
+	data8 = SW_AGING_ENABLE | SW_LINK_AUTO_AGING |
+	      SW_SRC_ADDR_FILTER | SW_FLUSH_STP_TABLE | SW_FLUSH_MSTP_TABLE;
+	ksz_write8(dev, REG_SW_LUE_CTRL_1, data8);
+
+	/* disable interrupts */
+	ksz_write32(dev, REG_SW_INT_MASK__4, SWITCH_INT_MASK);
+	ksz_write32(dev, REG_SW_PORT_INT_MASK__4, 0x7F);
+	ksz_read32(dev, REG_SW_PORT_INT_STATUS__4, &data32);
+
+	/* set broadcast storm protection 10% rate */
+	ksz_read16(dev, REG_SW_MAC_CTRL_2, &data16);
+	data16 &= ~BROADCAST_STORM_RATE;
+	data16 |= (BROADCAST_STORM_VALUE * BROADCAST_STORM_PROT_RATE) / 100;
+	ksz_write16(dev, REG_SW_MAC_CTRL_2, data16);
+
+	return 0;
+}
+
+static enum dsa_tag_protocol ksz9477_get_tag_protocol(struct dsa_switch *ds,
+						      int port)
+{
+	return DSA_TAG_PROTO_KSZ;
+}
+
+static int ksz9477_phy_read16(struct dsa_switch *ds, int addr, int reg)
+{
+	struct ksz_device *dev = ds->priv;
+	u16 val = 0xffff;
+
+	/* No real PHY after this. Simulate the PHY.
+	 * A fixed PHY can be setup in the device tree, but this function is
+	 * still called for that port during initialization.
+	 * For RGMII PHY there is no way to access it so the fixed PHY should
+	 * be used.  For SGMII PHY the supporting code will be added later.
+	 */
+	if (addr >= dev->phy_port_cnt) {
+		struct ksz_port *p = &dev->ports[addr];
+
+		switch (reg) {
+		case MII_BMCR:
+			val = 0x1140;
+			break;
+		case MII_BMSR:
+			val = 0x796d;
+			break;
+		case MII_PHYSID1:
+			val = 0x0022;
+			break;
+		case MII_PHYSID2:
+			val = 0x1631;
+			break;
+		case MII_ADVERTISE:
+			val = 0x05e1;
+			break;
+		case MII_LPA:
+			val = 0xc5e1;
+			break;
+		case MII_CTRL1000:
+			val = 0x0700;
+			break;
+		case MII_STAT1000:
+			if (p->phydev.speed == SPEED_1000)
+				val = 0x3800;
+			else
+				val = 0;
+			break;
+		}
+	} else {
+		ksz_pread16(dev, addr, 0x100 + (reg << 1), &val);
+	}
+
+	return val;
+}
+
+static int ksz9477_phy_write16(struct dsa_switch *ds, int addr, int reg,
+			       u16 val)
+{
+	struct ksz_device *dev = ds->priv;
+
+	/* No real PHY after this. */
+	if (addr >= dev->phy_port_cnt)
+		return 0;
+	ksz_pwrite16(dev, addr, 0x100 + (reg << 1), val);
+
+	return 0;
+}
+
+static void ksz9477_get_strings(struct dsa_switch *ds, int port,
+				u32 stringset, uint8_t *buf)
+{
+	int i;
+
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	for (i = 0; i < TOTAL_SWITCH_COUNTER_NUM; i++) {
+		memcpy(buf + i * ETH_GSTRING_LEN, ksz9477_mib_names[i].string,
+		       ETH_GSTRING_LEN);
+	}
+}
+
+static void ksz_get_ethtool_stats(struct dsa_switch *ds, int port,
+				  uint64_t *buf)
+{
+	struct ksz_device *dev = ds->priv;
+	int i;
+	u32 data;
+	int timeout;
+
+	mutex_lock(&dev->stats_mutex);
+
+	for (i = 0; i < TOTAL_SWITCH_COUNTER_NUM; i++) {
+		data = MIB_COUNTER_READ;
+		data |= ((ksz9477_mib_names[i].index & 0xFF) <<
+			MIB_COUNTER_INDEX_S);
+		ksz_pwrite32(dev, port, REG_PORT_MIB_CTRL_STAT__4, data);
+
+		timeout = 1000;
+		do {
+			ksz_pread32(dev, port, REG_PORT_MIB_CTRL_STAT__4,
+				    &data);
+			usleep_range(1, 10);
+			if (!(data & MIB_COUNTER_READ))
+				break;
+		} while (timeout-- > 0);
+
+		/* failed to read MIB. get out of loop */
+		if (!timeout) {
+			dev_dbg(dev->dev, "Failed to get MIB\n");
+			break;
+		}
+
+		/* count resets upon read */
+		ksz_pread32(dev, port, REG_PORT_MIB_DATA, &data);
+
+		dev->mib_value[i] += (uint64_t)data;
+		buf[i] = dev->mib_value[i];
+	}
+
+	mutex_unlock(&dev->stats_mutex);
+}
+
+static void ksz9477_cfg_port_member(struct ksz_device *dev, int port,
+				    u8 member)
+{
+	ksz_pwrite32(dev, port, REG_PORT_VLAN_MEMBERSHIP__4, member);
+	dev->ports[port].member = member;
+}
+
+static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port,
+				       u8 state)
+{
+	struct ksz_device *dev = ds->priv;
+	struct ksz_port *p = &dev->ports[port];
+	u8 data;
+	int member = -1;
+
+	ksz_pread8(dev, port, P_STP_CTRL, &data);
+	data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE);
+
+	switch (state) {
+	case BR_STATE_DISABLED:
+		data |= PORT_LEARN_DISABLE;
+		if (port != dev->cpu_port)
+			member = 0;
+		break;
+	case BR_STATE_LISTENING:
+		data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE);
+		if (port != dev->cpu_port &&
+		    p->stp_state == BR_STATE_DISABLED)
+			member = dev->host_mask | p->vid_member;
+		break;
+	case BR_STATE_LEARNING:
+		data |= PORT_RX_ENABLE;
+		break;
+	case BR_STATE_FORWARDING:
+		data |= (PORT_TX_ENABLE | PORT_RX_ENABLE);
+
+		/* This function is also used internally. */
+		if (port == dev->cpu_port)
+			break;
+
+		member = dev->host_mask | p->vid_member;
+
+		/* Port is a member of a bridge. */
+		if (dev->br_member & (1 << port)) {
+			dev->member |= (1 << port);
+			member = dev->member;
+		}
+		break;
+	case BR_STATE_BLOCKING:
+		data |= PORT_LEARN_DISABLE;
+		if (port != dev->cpu_port &&
+		    p->stp_state == BR_STATE_DISABLED)
+			member = dev->host_mask | p->vid_member;
+		break;
+	default:
+		dev_err(ds->dev, "invalid STP state: %d\n", state);
+		return;
+	}
+
+	ksz_pwrite8(dev, port, P_STP_CTRL, data);
+	p->stp_state = state;
+	if (data & PORT_RX_ENABLE)
+		dev->rx_ports |= (1 << port);
+	else
+		dev->rx_ports &= ~(1 << port);
+	if (data & PORT_TX_ENABLE)
+		dev->tx_ports |= (1 << port);
+	else
+		dev->tx_ports &= ~(1 << port);
+
+	/* Port membership may share register with STP state. */
+	if (member >= 0 && member != p->member)
+		ksz9477_cfg_port_member(dev, port, (u8)member);
+
+	/* Check if forwarding needs to be updated. */
+	if (state != BR_STATE_FORWARDING) {
+		if (dev->br_member & (1 << port))
+			dev->member &= ~(1 << port);
+	}
+
+	/* When topology has changed the function ksz_update_port_member
+	 * should be called to modify port forwarding behavior.  However
+	 * as the offload_fwd_mark indication cannot be reported here
+	 * the switch forwarding function is not enabled.
+	 */
+}
+
+static void ksz9477_flush_dyn_mac_table(struct ksz_device *dev, int port)
+{
+	u8 data;
+
+	ksz_read8(dev, REG_SW_LUE_CTRL_2, &data);
+	data &= ~(SW_FLUSH_OPTION_M << SW_FLUSH_OPTION_S);
+	data |= (SW_FLUSH_OPTION_DYN_MAC << SW_FLUSH_OPTION_S);
+	ksz_write8(dev, REG_SW_LUE_CTRL_2, data);
+	if (port < dev->mib_port_cnt) {
+		/* flush individual port */
+		ksz_pread8(dev, port, P_STP_CTRL, &data);
+		if (!(data & PORT_LEARN_DISABLE))
+			ksz_pwrite8(dev, port, P_STP_CTRL,
+				    data | PORT_LEARN_DISABLE);
+		ksz_cfg(dev, S_FLUSH_TABLE_CTRL, SW_FLUSH_DYN_MAC_TABLE, true);
+		ksz_pwrite8(dev, port, P_STP_CTRL, data);
+	} else {
+		/* flush all */
+		ksz_cfg(dev, S_FLUSH_TABLE_CTRL, SW_FLUSH_STP_TABLE, true);
+	}
+}
+
+static int ksz9477_port_vlan_filtering(struct dsa_switch *ds, int port,
+				       bool flag)
+{
+	struct ksz_device *dev = ds->priv;
+
+	if (flag) {
+		ksz_port_cfg(dev, port, REG_PORT_LUE_CTRL,
+			     PORT_VLAN_LOOKUP_VID_0, true);
+		ksz9477_cfg32(dev, REG_SW_QM_CTRL__4, UNICAST_VLAN_BOUNDARY,
+			      true);
+		ksz_cfg(dev, REG_SW_LUE_CTRL_0, SW_VLAN_ENABLE, true);
+	} else {
+		ksz_cfg(dev, REG_SW_LUE_CTRL_0, SW_VLAN_ENABLE, false);
+		ksz9477_cfg32(dev, REG_SW_QM_CTRL__4, UNICAST_VLAN_BOUNDARY,
+			      false);
+		ksz_port_cfg(dev, port, REG_PORT_LUE_CTRL,
+			     PORT_VLAN_LOOKUP_VID_0, false);
+	}
+
+	return 0;
+}
+
+static void ksz9477_port_vlan_add(struct dsa_switch *ds, int port,
+				  const struct switchdev_obj_port_vlan *vlan)
+{
+	struct ksz_device *dev = ds->priv;
+	u32 vlan_table[3];
+	u16 vid;
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		if (ksz9477_get_vlan_table(dev, vid, vlan_table)) {
+			dev_dbg(dev->dev, "Failed to get vlan table\n");
+			return;
+		}
+
+		vlan_table[0] = VLAN_VALID | (vid & VLAN_FID_M);
+		if (untagged)
+			vlan_table[1] |= BIT(port);
+		else
+			vlan_table[1] &= ~BIT(port);
+		vlan_table[1] &= ~(BIT(dev->cpu_port));
+
+		vlan_table[2] |= BIT(port) | BIT(dev->cpu_port);
+
+		if (ksz9477_set_vlan_table(dev, vid, vlan_table)) {
+			dev_dbg(dev->dev, "Failed to set vlan table\n");
+			return;
+		}
+
+		/* change PVID */
+		if (vlan->flags & BRIDGE_VLAN_INFO_PVID)
+			ksz_pwrite16(dev, port, REG_PORT_DEFAULT_VID, vid);
+	}
+}
+
+static int ksz9477_port_vlan_del(struct dsa_switch *ds, int port,
+				 const struct switchdev_obj_port_vlan *vlan)
+{
+	struct ksz_device *dev = ds->priv;
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	u32 vlan_table[3];
+	u16 vid;
+	u16 pvid;
+
+	ksz_pread16(dev, port, REG_PORT_DEFAULT_VID, &pvid);
+	pvid = pvid & 0xFFF;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		if (ksz9477_get_vlan_table(dev, vid, vlan_table)) {
+			dev_dbg(dev->dev, "Failed to get vlan table\n");
+			return -ETIMEDOUT;
+		}
+
+		vlan_table[2] &= ~BIT(port);
+
+		if (pvid == vid)
+			pvid = 1;
+
+		if (untagged)
+			vlan_table[1] &= ~BIT(port);
+
+		if (ksz9477_set_vlan_table(dev, vid, vlan_table)) {
+			dev_dbg(dev->dev, "Failed to set vlan table\n");
+			return -ETIMEDOUT;
+		}
+	}
+
+	ksz_pwrite16(dev, port, REG_PORT_DEFAULT_VID, pvid);
+
+	return 0;
+}
+
+static int ksz9477_port_fdb_add(struct dsa_switch *ds, int port,
+				const unsigned char *addr, u16 vid)
+{
+	struct ksz_device *dev = ds->priv;
+	u32 alu_table[4];
+	u32 data;
+	int ret = 0;
+
+	mutex_lock(&dev->alu_mutex);
+
+	/* find any entry with mac & vid */
+	data = vid << ALU_FID_INDEX_S;
+	data |= ((addr[0] << 8) | addr[1]);
+	ksz_write32(dev, REG_SW_ALU_INDEX_0, data);
+
+	data = ((addr[2] << 24) | (addr[3] << 16));
+	data |= ((addr[4] << 8) | addr[5]);
+	ksz_write32(dev, REG_SW_ALU_INDEX_1, data);
+
+	/* start read operation */
+	ksz_write32(dev, REG_SW_ALU_CTRL__4, ALU_READ | ALU_START);
+
+	/* wait to be finished */
+	ret = ksz9477_wait_alu_ready(dev, ALU_START, 1000);
+	if (ret < 0) {
+		dev_dbg(dev->dev, "Failed to read ALU\n");
+		goto exit;
+	}
+
+	/* read ALU entry */
+	ksz9477_read_table(dev, alu_table);
+
+	/* update ALU entry */
+	alu_table[0] = ALU_V_STATIC_VALID;
+	alu_table[1] |= BIT(port);
+	if (vid)
+		alu_table[1] |= ALU_V_USE_FID;
+	alu_table[2] = (vid << ALU_V_FID_S);
+	alu_table[2] |= ((addr[0] << 8) | addr[1]);
+	alu_table[3] = ((addr[2] << 24) | (addr[3] << 16));
+	alu_table[3] |= ((addr[4] << 8) | addr[5]);
+
+	ksz9477_write_table(dev, alu_table);
+
+	ksz_write32(dev, REG_SW_ALU_CTRL__4, ALU_WRITE | ALU_START);
+
+	/* wait to be finished */
+	ret = ksz9477_wait_alu_ready(dev, ALU_START, 1000);
+	if (ret < 0)
+		dev_dbg(dev->dev, "Failed to write ALU\n");
+
+exit:
+	mutex_unlock(&dev->alu_mutex);
+
+	return ret;
+}
+
+static int ksz9477_port_fdb_del(struct dsa_switch *ds, int port,
+				const unsigned char *addr, u16 vid)
+{
+	struct ksz_device *dev = ds->priv;
+	u32 alu_table[4];
+	u32 data;
+	int ret = 0;
+
+	mutex_lock(&dev->alu_mutex);
+
+	/* read any entry with mac & vid */
+	data = vid << ALU_FID_INDEX_S;
+	data |= ((addr[0] << 8) | addr[1]);
+	ksz_write32(dev, REG_SW_ALU_INDEX_0, data);
+
+	data = ((addr[2] << 24) | (addr[3] << 16));
+	data |= ((addr[4] << 8) | addr[5]);
+	ksz_write32(dev, REG_SW_ALU_INDEX_1, data);
+
+	/* start read operation */
+	ksz_write32(dev, REG_SW_ALU_CTRL__4, ALU_READ | ALU_START);
+
+	/* wait to be finished */
+	ret = ksz9477_wait_alu_ready(dev, ALU_START, 1000);
+	if (ret < 0) {
+		dev_dbg(dev->dev, "Failed to read ALU\n");
+		goto exit;
+	}
+
+	ksz_read32(dev, REG_SW_ALU_VAL_A, &alu_table[0]);
+	if (alu_table[0] & ALU_V_STATIC_VALID) {
+		ksz_read32(dev, REG_SW_ALU_VAL_B, &alu_table[1]);
+		ksz_read32(dev, REG_SW_ALU_VAL_C, &alu_table[2]);
+		ksz_read32(dev, REG_SW_ALU_VAL_D, &alu_table[3]);
+
+		/* clear forwarding port */
+		alu_table[2] &= ~BIT(port);
+
+		/* if there is no port to forward, clear table */
+		if ((alu_table[2] & ALU_V_PORT_MAP) == 0) {
+			alu_table[0] = 0;
+			alu_table[1] = 0;
+			alu_table[2] = 0;
+			alu_table[3] = 0;
+		}
+	} else {
+		alu_table[0] = 0;
+		alu_table[1] = 0;
+		alu_table[2] = 0;
+		alu_table[3] = 0;
+	}
+
+	ksz9477_write_table(dev, alu_table);
+
+	ksz_write32(dev, REG_SW_ALU_CTRL__4, ALU_WRITE | ALU_START);
+
+	/* wait to be finished */
+	ret = ksz9477_wait_alu_ready(dev, ALU_START, 1000);
+	if (ret < 0)
+		dev_dbg(dev->dev, "Failed to write ALU\n");
+
+exit:
+	mutex_unlock(&dev->alu_mutex);
+
+	return ret;
+}
+
+static void ksz9477_convert_alu(struct alu_struct *alu, u32 *alu_table)
+{
+	alu->is_static = !!(alu_table[0] & ALU_V_STATIC_VALID);
+	alu->is_src_filter = !!(alu_table[0] & ALU_V_SRC_FILTER);
+	alu->is_dst_filter = !!(alu_table[0] & ALU_V_DST_FILTER);
+	alu->prio_age = (alu_table[0] >> ALU_V_PRIO_AGE_CNT_S) &
+			ALU_V_PRIO_AGE_CNT_M;
+	alu->mstp = alu_table[0] & ALU_V_MSTP_M;
+
+	alu->is_override = !!(alu_table[1] & ALU_V_OVERRIDE);
+	alu->is_use_fid = !!(alu_table[1] & ALU_V_USE_FID);
+	alu->port_forward = alu_table[1] & ALU_V_PORT_MAP;
+
+	alu->fid = (alu_table[2] >> ALU_V_FID_S) & ALU_V_FID_M;
+
+	alu->mac[0] = (alu_table[2] >> 8) & 0xFF;
+	alu->mac[1] = alu_table[2] & 0xFF;
+	alu->mac[2] = (alu_table[3] >> 24) & 0xFF;
+	alu->mac[3] = (alu_table[3] >> 16) & 0xFF;
+	alu->mac[4] = (alu_table[3] >> 8) & 0xFF;
+	alu->mac[5] = alu_table[3] & 0xFF;
+}
+
+static int ksz9477_port_fdb_dump(struct dsa_switch *ds, int port,
+				 dsa_fdb_dump_cb_t *cb, void *data)
+{
+	struct ksz_device *dev = ds->priv;
+	int ret = 0;
+	u32 ksz_data;
+	u32 alu_table[4];
+	struct alu_struct alu;
+	int timeout;
+
+	mutex_lock(&dev->alu_mutex);
+
+	/* start ALU search */
+	ksz_write32(dev, REG_SW_ALU_CTRL__4, ALU_START | ALU_SEARCH);
+
+	do {
+		timeout = 1000;
+		do {
+			ksz_read32(dev, REG_SW_ALU_CTRL__4, &ksz_data);
+			if ((ksz_data & ALU_VALID) || !(ksz_data & ALU_START))
+				break;
+			usleep_range(1, 10);
+		} while (timeout-- > 0);
+
+		if (!timeout) {
+			dev_dbg(dev->dev, "Failed to search ALU\n");
+			ret = -ETIMEDOUT;
+			goto exit;
+		}
+
+		/* read ALU table */
+		ksz9477_read_table(dev, alu_table);
+
+		ksz9477_convert_alu(&alu, alu_table);
+
+		if (alu.port_forward & BIT(port)) {
+			ret = cb(alu.mac, alu.fid, alu.is_static, data);
+			if (ret)
+				goto exit;
+		}
+	} while (ksz_data & ALU_START);
+
+exit:
+
+	/* stop ALU search */
+	ksz_write32(dev, REG_SW_ALU_CTRL__4, 0);
+
+	mutex_unlock(&dev->alu_mutex);
+
+	return ret;
+}
+
+static void ksz9477_port_mdb_add(struct dsa_switch *ds, int port,
+				 const struct switchdev_obj_port_mdb *mdb)
+{
+	struct ksz_device *dev = ds->priv;
+	u32 static_table[4];
+	u32 data;
+	int index;
+	u32 mac_hi, mac_lo;
+
+	mac_hi = ((mdb->addr[0] << 8) | mdb->addr[1]);
+	mac_lo = ((mdb->addr[2] << 24) | (mdb->addr[3] << 16));
+	mac_lo |= ((mdb->addr[4] << 8) | mdb->addr[5]);
+
+	mutex_lock(&dev->alu_mutex);
+
+	for (index = 0; index < dev->num_statics; index++) {
+		/* find empty slot first */
+		data = (index << ALU_STAT_INDEX_S) |
+			ALU_STAT_READ | ALU_STAT_START;
+		ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data);
+
+		/* wait to be finished */
+		if (ksz9477_wait_alu_sta_ready(dev, ALU_STAT_START, 1000) < 0) {
+			dev_dbg(dev->dev, "Failed to read ALU STATIC\n");
+			goto exit;
+		}
+
+		/* read ALU static table */
+		ksz9477_read_table(dev, static_table);
+
+		if (static_table[0] & ALU_V_STATIC_VALID) {
+			/* check this has same vid & mac address */
+			if (((static_table[2] >> ALU_V_FID_S) == mdb->vid) &&
+			    ((static_table[2] & ALU_V_MAC_ADDR_HI) == mac_hi) &&
+			    static_table[3] == mac_lo) {
+				/* found matching one */
+				break;
+			}
+		} else {
+			/* found empty one */
+			break;
+		}
+	}
+
+	/* no available entry */
+	if (index == dev->num_statics)
+		goto exit;
+
+	/* add entry */
+	static_table[0] = ALU_V_STATIC_VALID;
+	static_table[1] |= BIT(port);
+	if (mdb->vid)
+		static_table[1] |= ALU_V_USE_FID;
+	static_table[2] = (mdb->vid << ALU_V_FID_S);
+	static_table[2] |= mac_hi;
+	static_table[3] = mac_lo;
+
+	ksz9477_write_table(dev, static_table);
+
+	data = (index << ALU_STAT_INDEX_S) | ALU_STAT_START;
+	ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data);
+
+	/* wait to be finished */
+	if (ksz9477_wait_alu_sta_ready(dev, ALU_STAT_START, 1000) < 0)
+		dev_dbg(dev->dev, "Failed to read ALU STATIC\n");
+
+exit:
+	mutex_unlock(&dev->alu_mutex);
+}
+
+static int ksz9477_port_mdb_del(struct dsa_switch *ds, int port,
+				const struct switchdev_obj_port_mdb *mdb)
+{
+	struct ksz_device *dev = ds->priv;
+	u32 static_table[4];
+	u32 data;
+	int index;
+	int ret = 0;
+	u32 mac_hi, mac_lo;
+
+	mac_hi = ((mdb->addr[0] << 8) | mdb->addr[1]);
+	mac_lo = ((mdb->addr[2] << 24) | (mdb->addr[3] << 16));
+	mac_lo |= ((mdb->addr[4] << 8) | mdb->addr[5]);
+
+	mutex_lock(&dev->alu_mutex);
+
+	for (index = 0; index < dev->num_statics; index++) {
+		/* find empty slot first */
+		data = (index << ALU_STAT_INDEX_S) |
+			ALU_STAT_READ | ALU_STAT_START;
+		ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data);
+
+		/* wait to be finished */
+		ret = ksz9477_wait_alu_sta_ready(dev, ALU_STAT_START, 1000);
+		if (ret < 0) {
+			dev_dbg(dev->dev, "Failed to read ALU STATIC\n");
+			goto exit;
+		}
+
+		/* read ALU static table */
+		ksz9477_read_table(dev, static_table);
+
+		if (static_table[0] & ALU_V_STATIC_VALID) {
+			/* check this has same vid & mac address */
+
+			if (((static_table[2] >> ALU_V_FID_S) == mdb->vid) &&
+			    ((static_table[2] & ALU_V_MAC_ADDR_HI) == mac_hi) &&
+			    static_table[3] == mac_lo) {
+				/* found matching one */
+				break;
+			}
+		}
+	}
+
+	/* no available entry */
+	if (index == dev->num_statics)
+		goto exit;
+
+	/* clear port */
+	static_table[1] &= ~BIT(port);
+
+	if ((static_table[1] & ALU_V_PORT_MAP) == 0) {
+		/* delete entry */
+		static_table[0] = 0;
+		static_table[1] = 0;
+		static_table[2] = 0;
+		static_table[3] = 0;
+	}
+
+	ksz9477_write_table(dev, static_table);
+
+	data = (index << ALU_STAT_INDEX_S) | ALU_STAT_START;
+	ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data);
+
+	/* wait to be finished */
+	ret = ksz9477_wait_alu_sta_ready(dev, ALU_STAT_START, 1000);
+	if (ret < 0)
+		dev_dbg(dev->dev, "Failed to read ALU STATIC\n");
+
+exit:
+	mutex_unlock(&dev->alu_mutex);
+
+	return ret;
+}
+
+static int ksz9477_port_mirror_add(struct dsa_switch *ds, int port,
+				   struct dsa_mall_mirror_tc_entry *mirror,
+				   bool ingress)
+{
+	struct ksz_device *dev = ds->priv;
+
+	if (ingress)
+		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, true);
+	else
+		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, true);
+
+	ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, false);
+
+	/* configure mirror port */
+	ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL,
+		     PORT_MIRROR_SNIFFER, true);
+
+	ksz_cfg(dev, S_MIRROR_CTRL, SW_MIRROR_RX_TX, false);
+
+	return 0;
+}
+
+static void ksz9477_port_mirror_del(struct dsa_switch *ds, int port,
+				    struct dsa_mall_mirror_tc_entry *mirror)
+{
+	struct ksz_device *dev = ds->priv;
+	u8 data;
+
+	if (mirror->ingress)
+		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, false);
+	else
+		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, false);
+
+	ksz_pread8(dev, port, P_MIRROR_CTRL, &data);
+
+	if (!(data & (PORT_MIRROR_RX | PORT_MIRROR_TX)))
+		ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL,
+			     PORT_MIRROR_SNIFFER, false);
+}
+
+static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port)
+{
+	u8 data8;
+	u8 member;
+	u16 data16;
+	struct ksz_port *p = &dev->ports[port];
+
+	/* enable tag tail for host port */
+	if (cpu_port)
+		ksz_port_cfg(dev, port, REG_PORT_CTRL_0, PORT_TAIL_TAG_ENABLE,
+			     true);
+
+	ksz_port_cfg(dev, port, REG_PORT_CTRL_0, PORT_MAC_LOOPBACK, false);
+
+	/* set back pressure */
+	ksz_port_cfg(dev, port, REG_PORT_MAC_CTRL_1, PORT_BACK_PRESSURE, true);
+
+	/* enable broadcast storm limit */
+	ksz_port_cfg(dev, port, P_BCAST_STORM_CTRL, PORT_BROADCAST_STORM, true);
+
+	/* disable DiffServ priority */
+	ksz_port_cfg(dev, port, P_PRIO_CTRL, PORT_DIFFSERV_PRIO_ENABLE, false);
+
+	/* replace priority */
+	ksz_port_cfg(dev, port, REG_PORT_MRI_MAC_CTRL, PORT_USER_PRIO_CEILING,
+		     false);
+	ksz9477_port_cfg32(dev, port, REG_PORT_MTI_QUEUE_CTRL_0__4,
+			   MTI_PVID_REPLACE, false);
+
+	/* enable 802.1p priority */
+	ksz_port_cfg(dev, port, P_PRIO_CTRL, PORT_802_1P_PRIO_ENABLE, true);
+
+	if (port < dev->phy_port_cnt) {
+		/* do not force flow control */
+		ksz_port_cfg(dev, port, REG_PORT_CTRL_0,
+			     PORT_FORCE_TX_FLOW_CTRL | PORT_FORCE_RX_FLOW_CTRL,
+			     false);
+
+	} else {
+		/* force flow control */
+		ksz_port_cfg(dev, port, REG_PORT_CTRL_0,
+			     PORT_FORCE_TX_FLOW_CTRL | PORT_FORCE_RX_FLOW_CTRL,
+			     true);
+
+		/* configure MAC to 1G & RGMII mode */
+		ksz_pread8(dev, port, REG_PORT_XMII_CTRL_1, &data8);
+		data8 &= ~PORT_MII_NOT_1GBIT;
+		data8 &= ~PORT_MII_SEL_M;
+		switch (dev->interface) {
+		case PHY_INTERFACE_MODE_MII:
+			data8 |= PORT_MII_NOT_1GBIT;
+			data8 |= PORT_MII_SEL;
+			p->phydev.speed = SPEED_100;
+			break;
+		case PHY_INTERFACE_MODE_RMII:
+			data8 |= PORT_MII_NOT_1GBIT;
+			data8 |= PORT_RMII_SEL;
+			p->phydev.speed = SPEED_100;
+			break;
+		case PHY_INTERFACE_MODE_GMII:
+			data8 |= PORT_GMII_SEL;
+			p->phydev.speed = SPEED_1000;
+			break;
+		default:
+			data8 &= ~PORT_RGMII_ID_IG_ENABLE;
+			data8 &= ~PORT_RGMII_ID_EG_ENABLE;
+			if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+			    dev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
+				data8 |= PORT_RGMII_ID_IG_ENABLE;
+			if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+			    dev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
+				data8 |= PORT_RGMII_ID_EG_ENABLE;
+			data8 |= PORT_RGMII_SEL;
+			p->phydev.speed = SPEED_1000;
+			break;
+		}
+		ksz_pwrite8(dev, port, REG_PORT_XMII_CTRL_1, data8);
+		p->phydev.duplex = 1;
+	}
+	if (cpu_port) {
+		member = dev->port_mask;
+		dev->on_ports = dev->host_mask;
+		dev->live_ports = dev->host_mask;
+	} else {
+		member = dev->host_mask | p->vid_member;
+		dev->on_ports |= (1 << port);
+
+		/* Link was detected before port is enabled. */
+		if (p->phydev.link)
+			dev->live_ports |= (1 << port);
+	}
+	ksz9477_cfg_port_member(dev, port, member);
+
+	/* clear pending interrupts */
+	if (port < dev->phy_port_cnt)
+		ksz_pread16(dev, port, REG_PORT_PHY_INT_ENABLE, &data16);
+}
+
+static void ksz9477_config_cpu_port(struct dsa_switch *ds)
+{
+	struct ksz_device *dev = ds->priv;
+	struct ksz_port *p;
+	int i;
+
+	ds->num_ports = dev->port_cnt;
+
+	for (i = 0; i < dev->port_cnt; i++) {
+		if (dsa_is_cpu_port(ds, i) && (dev->cpu_ports & (1 << i))) {
+			dev->cpu_port = i;
+			dev->host_mask = (1 << dev->cpu_port);
+			dev->port_mask |= dev->host_mask;
+
+			/* enable cpu port */
+			ksz9477_port_setup(dev, i, true);
+			p = &dev->ports[dev->cpu_port];
+			p->vid_member = dev->port_mask;
+			p->on = 1;
+		}
+	}
+
+	dev->member = dev->host_mask;
+
+	for (i = 0; i < dev->mib_port_cnt; i++) {
+		if (i == dev->cpu_port)
+			continue;
+		p = &dev->ports[i];
+
+		/* Initialize to non-zero so that ksz_cfg_port_member() will
+		 * be called.
+		 */
+		p->vid_member = (1 << i);
+		p->member = dev->port_mask;
+		ksz9477_port_stp_state_set(ds, i, BR_STATE_DISABLED);
+		p->on = 1;
+		if (i < dev->phy_port_cnt)
+			p->phy = 1;
+		if (dev->chip_id == 0x00947700 && i == 6) {
+			p->sgmii = 1;
+
+			/* SGMII PHY detection code is not implemented yet. */
+			p->phy = 0;
+		}
+	}
+}
+
+static int ksz9477_setup(struct dsa_switch *ds)
+{
+	struct ksz_device *dev = ds->priv;
+	int ret = 0;
+
+	dev->vlan_cache = devm_kcalloc(dev->dev, sizeof(struct vlan_table),
+				       dev->num_vlans, GFP_KERNEL);
+	if (!dev->vlan_cache)
+		return -ENOMEM;
+
+	ret = ksz9477_reset_switch(dev);
+	if (ret) {
+		dev_err(ds->dev, "failed to reset switch\n");
+		return ret;
+	}
+
+	/* accept packet up to 2000bytes */
+	ksz_cfg(dev, REG_SW_MAC_CTRL_1, SW_LEGAL_PACKET_DISABLE, true);
+
+	ksz9477_config_cpu_port(ds);
+
+	ksz_cfg(dev, REG_SW_MAC_CTRL_1, MULTICAST_STORM_DISABLE, true);
+
+	/* queue based egress rate limit */
+	ksz_cfg(dev, REG_SW_MAC_CTRL_5, SW_OUT_RATE_LIMIT_QUEUE_BASED, true);
+
+	/* start switch */
+	ksz_cfg(dev, REG_SW_OPERATION, SW_START, true);
+
+	return 0;
+}
+
+static const struct dsa_switch_ops ksz9477_switch_ops = {
+	.get_tag_protocol	= ksz9477_get_tag_protocol,
+	.setup			= ksz9477_setup,
+	.phy_read		= ksz9477_phy_read16,
+	.phy_write		= ksz9477_phy_write16,
+	.port_enable		= ksz_enable_port,
+	.port_disable		= ksz_disable_port,
+	.get_strings		= ksz9477_get_strings,
+	.get_ethtool_stats	= ksz_get_ethtool_stats,
+	.get_sset_count		= ksz_sset_count,
+	.port_bridge_join	= ksz_port_bridge_join,
+	.port_bridge_leave	= ksz_port_bridge_leave,
+	.port_stp_state_set	= ksz9477_port_stp_state_set,
+	.port_fast_age		= ksz_port_fast_age,
+	.port_vlan_filtering	= ksz9477_port_vlan_filtering,
+	.port_vlan_prepare	= ksz_port_vlan_prepare,
+	.port_vlan_add		= ksz9477_port_vlan_add,
+	.port_vlan_del		= ksz9477_port_vlan_del,
+	.port_fdb_dump		= ksz9477_port_fdb_dump,
+	.port_fdb_add		= ksz9477_port_fdb_add,
+	.port_fdb_del		= ksz9477_port_fdb_del,
+	.port_mdb_prepare       = ksz_port_mdb_prepare,
+	.port_mdb_add           = ksz9477_port_mdb_add,
+	.port_mdb_del           = ksz9477_port_mdb_del,
+	.port_mirror_add	= ksz9477_port_mirror_add,
+	.port_mirror_del	= ksz9477_port_mirror_del,
+};
+
+static u32 ksz9477_get_port_addr(int port, int offset)
+{
+	return PORT_CTRL_ADDR(port, offset);
+}
+
+static int ksz9477_switch_detect(struct ksz_device *dev)
+{
+	u8 data8;
+	u32 id32;
+	int ret;
+
+	/* turn off SPI DO Edge select */
+	ret = ksz_read8(dev, REG_SW_GLOBAL_SERIAL_CTRL_0, &data8);
+	if (ret)
+		return ret;
+
+	data8 &= ~SPI_AUTO_EDGE_DETECTION;
+	ret = ksz_write8(dev, REG_SW_GLOBAL_SERIAL_CTRL_0, data8);
+	if (ret)
+		return ret;
+
+	/* read chip id */
+	ret = ksz_read32(dev, REG_CHIP_ID0__1, &id32);
+	if (ret)
+		return ret;
+
+	/* Number of ports can be reduced depending on chip. */
+	dev->mib_port_cnt = TOTAL_PORT_NUM;
+	dev->phy_port_cnt = 5;
+
+	dev->chip_id = id32;
+
+	return 0;
+}
+
+struct ksz_chip_data {
+	u32 chip_id;
+	const char *dev_name;
+	int num_vlans;
+	int num_alus;
+	int num_statics;
+	int cpu_ports;
+	int port_cnt;
+};
+
+static const struct ksz_chip_data ksz9477_switch_chips[] = {
+	{
+		.chip_id = 0x00947700,
+		.dev_name = "KSZ9477",
+		.num_vlans = 4096,
+		.num_alus = 4096,
+		.num_statics = 16,
+		.cpu_ports = 0x7F,	/* can be configured as cpu port */
+		.port_cnt = 7,		/* total physical port count */
+	},
+	{
+		.chip_id = 0x00989700,
+		.dev_name = "KSZ9897",
+		.num_vlans = 4096,
+		.num_alus = 4096,
+		.num_statics = 16,
+		.cpu_ports = 0x7F,	/* can be configured as cpu port */
+		.port_cnt = 7,		/* total physical port count */
+	},
+};
+
+static int ksz9477_switch_init(struct ksz_device *dev)
+{
+	int i;
+
+	dev->ds->ops = &ksz9477_switch_ops;
+
+	for (i = 0; i < ARRAY_SIZE(ksz9477_switch_chips); i++) {
+		const struct ksz_chip_data *chip = &ksz9477_switch_chips[i];
+
+		if (dev->chip_id == chip->chip_id) {
+			dev->name = chip->dev_name;
+			dev->num_vlans = chip->num_vlans;
+			dev->num_alus = chip->num_alus;
+			dev->num_statics = chip->num_statics;
+			dev->port_cnt = chip->port_cnt;
+			dev->cpu_ports = chip->cpu_ports;
+
+			break;
+		}
+	}
+
+	/* no switch found */
+	if (!dev->port_cnt)
+		return -ENODEV;
+
+	dev->port_mask = (1 << dev->port_cnt) - 1;
+
+	dev->reg_mib_cnt = SWITCH_COUNTER_NUM;
+	dev->mib_cnt = TOTAL_SWITCH_COUNTER_NUM;
+
+	i = dev->mib_port_cnt;
+	dev->ports = devm_kzalloc(dev->dev, sizeof(struct ksz_port) * i,
+				  GFP_KERNEL);
+	if (!dev->ports)
+		return -ENOMEM;
+	for (i = 0; i < dev->mib_port_cnt; i++) {
+		dev->ports[i].mib.counters =
+			devm_kzalloc(dev->dev,
+				     sizeof(u64) *
+				     (TOTAL_SWITCH_COUNTER_NUM + 1),
+				     GFP_KERNEL);
+		if (!dev->ports[i].mib.counters)
+			return -ENOMEM;
+	}
+	dev->interface = PHY_INTERFACE_MODE_RGMII_TXID;
+
+	return 0;
+}
+
+static void ksz9477_switch_exit(struct ksz_device *dev)
+{
+	ksz9477_reset_switch(dev);
+}
+
+static const struct ksz_dev_ops ksz9477_dev_ops = {
+	.get_port_addr = ksz9477_get_port_addr,
+	.cfg_port_member = ksz9477_cfg_port_member,
+	.flush_dyn_mac_table = ksz9477_flush_dyn_mac_table,
+	.port_setup = ksz9477_port_setup,
+	.shutdown = ksz9477_reset_switch,
+	.detect = ksz9477_switch_detect,
+	.init = ksz9477_switch_init,
+	.exit = ksz9477_switch_exit,
+};
+
+int ksz9477_switch_register(struct ksz_device *dev)
+{
+	return ksz_switch_register(dev, &ksz9477_dev_ops);
+}
+EXPORT_SYMBOL(ksz9477_switch_register);
+
+MODULE_AUTHOR("Woojung Huh <Woojung.Huh@microchip.com>");
+MODULE_DESCRIPTION("Microchip KSZ9477 Series Switch DSA Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c
index dc70f486719c..d757ba151cb1 100644
--- a/drivers/net/dsa/microchip/ksz9477_spi.c
+++ b/drivers/net/dsa/microchip/ksz9477_spi.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Microchip KSZ series register access through SPI
+ * Microchip KSZ9477 series register access through SPI
  *
  * Copyright (C) 2017-2018 Microchip Technology Inc.
  */
@@ -13,6 +13,7 @@
 #include <linux/spi/spi.h>
 
 #include "ksz_priv.h"
+#include "ksz_spi.h"
 
 /* SPI frame opcodes */
 #define KS_SPIOP_RD			3
@@ -22,8 +23,11 @@
 #define SPI_ADDR_MASK			(BIT(SPI_ADDR_SHIFT) - 1)
 #define SPI_TURNAROUND_SHIFT		5
 
-static int ksz_spi_read_reg(struct spi_device *spi, u32 reg, u8 *val,
-			    unsigned int len)
+/* Enough to read all switch port registers. */
+#define SPI_TX_BUF_LEN			0x100
+
+static int ksz9477_spi_read_reg(struct spi_device *spi, u32 reg, u8 *val,
+				unsigned int len)
 {
 	u32 txbuf;
 	int ret;
@@ -37,27 +41,36 @@ static int ksz_spi_read_reg(struct spi_device *spi, u32 reg, u8 *val,
 	return ret;
 }
 
-static int ksz_spi_read(struct ksz_device *dev, u32 reg, u8 *data,
-			unsigned int len)
+static int ksz9477_spi_write_reg(struct spi_device *spi, u32 reg, u8 *val,
+				 unsigned int len)
 {
-	struct spi_device *spi = dev->priv;
+	u32 *txbuf = (u32 *)val;
 
-	return ksz_spi_read_reg(spi, reg, data, len);
+	*txbuf = reg & SPI_ADDR_MASK;
+	*txbuf |= (KS_SPIOP_WR << SPI_ADDR_SHIFT);
+	*txbuf <<= SPI_TURNAROUND_SHIFT;
+	*txbuf = cpu_to_be32(*txbuf);
+
+	return spi_write(spi, txbuf, 4 + len);
 }
 
-static int ksz_spi_read8(struct ksz_device *dev, u32 reg, u8 *val)
+static int ksz_spi_read(struct ksz_device *dev, u32 reg, u8 *data,
+			unsigned int len)
 {
-	return ksz_spi_read(dev, reg, val, 1);
+	struct spi_device *spi = dev->priv;
+
+	return ksz9477_spi_read_reg(spi, reg, data, len);
 }
 
-static int ksz_spi_read16(struct ksz_device *dev, u32 reg, u16 *val)
+static int ksz_spi_write(struct ksz_device *dev, u32 reg, void *data,
+			 unsigned int len)
 {
-	int ret = ksz_spi_read(dev, reg, (u8 *)val, 2);
-
-	if (!ret)
-		*val = be16_to_cpu(*val);
+	struct spi_device *spi = dev->priv;
 
-	return ret;
+	if (len > SPI_TX_BUF_LEN)
+		len = SPI_TX_BUF_LEN;
+	memcpy(&dev->txbuf[4], data, len);
+	return ksz9477_spi_write_reg(spi, reg, dev->txbuf, len);
 }
 
 static int ksz_spi_read24(struct ksz_device *dev, u32 reg, u32 *val)
@@ -75,72 +88,15 @@ static int ksz_spi_read24(struct ksz_device *dev, u32 reg, u32 *val)
 	return ret;
 }
 
-static int ksz_spi_read32(struct ksz_device *dev, u32 reg, u32 *val)
-{
-	int ret = ksz_spi_read(dev, reg, (u8 *)val, 4);
-
-	if (!ret)
-		*val = be32_to_cpu(*val);
-
-	return ret;
-}
-
-static int ksz_spi_write_reg(struct spi_device *spi, u32 reg, u8 *val,
-			     unsigned int len)
-{
-	u32 txbuf;
-	u8 data[12];
-	int i;
-
-	txbuf = reg & SPI_ADDR_MASK;
-	txbuf |= (KS_SPIOP_WR << SPI_ADDR_SHIFT);
-	txbuf <<= SPI_TURNAROUND_SHIFT;
-	txbuf = cpu_to_be32(txbuf);
-
-	data[0] = txbuf & 0xFF;
-	data[1] = (txbuf & 0xFF00) >> 8;
-	data[2] = (txbuf & 0xFF0000) >> 16;
-	data[3] = (txbuf & 0xFF000000) >> 24;
-	for (i = 0; i < len; i++)
-		data[i + 4] = val[i];
-
-	return spi_write(spi, &data, 4 + len);
-}
-
-static int ksz_spi_write8(struct ksz_device *dev, u32 reg, u8 value)
-{
-	struct spi_device *spi = dev->priv;
-
-	return ksz_spi_write_reg(spi, reg, &value, 1);
-}
-
-static int ksz_spi_write16(struct ksz_device *dev, u32 reg, u16 value)
-{
-	struct spi_device *spi = dev->priv;
-
-	value = cpu_to_be16(value);
-	return ksz_spi_write_reg(spi, reg, (u8 *)&value, 2);
-}
-
 static int ksz_spi_write24(struct ksz_device *dev, u32 reg, u32 value)
 {
-	struct spi_device *spi = dev->priv;
-
 	/* make it to big endian 24bit from MSB */
 	value <<= 8;
 	value = cpu_to_be32(value);
-	return ksz_spi_write_reg(spi, reg, (u8 *)&value, 3);
+	return ksz_spi_write(dev, reg, &value, 3);
 }
 
-static int ksz_spi_write32(struct ksz_device *dev, u32 reg, u32 value)
-{
-	struct spi_device *spi = dev->priv;
-
-	value = cpu_to_be32(value);
-	return ksz_spi_write_reg(spi, reg, (u8 *)&value, 4);
-}
-
-static const struct ksz_io_ops ksz_spi_ops = {
+static const struct ksz_io_ops ksz9477_spi_ops = {
 	.read8 = ksz_spi_read8,
 	.read16 = ksz_spi_read16,
 	.read24 = ksz_spi_read24,
@@ -149,21 +105,27 @@ static const struct ksz_io_ops ksz_spi_ops = {
 	.write16 = ksz_spi_write16,
 	.write24 = ksz_spi_write24,
 	.write32 = ksz_spi_write32,
+	.get = ksz_spi_get,
+	.set = ksz_spi_set,
 };
 
-static int ksz_spi_probe(struct spi_device *spi)
+static int ksz9477_spi_probe(struct spi_device *spi)
 {
 	struct ksz_device *dev;
 	int ret;
 
-	dev = ksz_switch_alloc(&spi->dev, &ksz_spi_ops, spi);
+	dev = ksz_switch_alloc(&spi->dev, &ksz9477_spi_ops, spi);
 	if (!dev)
 		return -ENOMEM;
 
 	if (spi->dev.platform_data)
 		dev->pdata = spi->dev.platform_data;
 
-	ret = ksz_switch_register(dev);
+	dev->txbuf = devm_kzalloc(dev->dev, 4 + SPI_TX_BUF_LEN, GFP_KERNEL);
+
+	ret = ksz9477_switch_register(dev);
+
+	/* Main DSA driver may not be started yet. */
 	if (ret)
 		return ret;
 
@@ -172,7 +134,7 @@ static int ksz_spi_probe(struct spi_device *spi)
 	return 0;
 }
 
-static int ksz_spi_remove(struct spi_device *spi)
+static int ksz9477_spi_remove(struct spi_device *spi)
 {
 	struct ksz_device *dev = spi_get_drvdata(spi);
 
@@ -182,25 +144,34 @@ static int ksz_spi_remove(struct spi_device *spi)
 	return 0;
 }
 
-static const struct of_device_id ksz_dt_ids[] = {
+static void ksz9477_spi_shutdown(struct spi_device *spi)
+{
+	struct ksz_device *dev = spi_get_drvdata(spi);
+
+	if (dev && dev->dev_ops->shutdown)
+		dev->dev_ops->shutdown(dev);
+}
+
+static const struct of_device_id ksz9477_dt_ids[] = {
 	{ .compatible = "microchip,ksz9477" },
 	{ .compatible = "microchip,ksz9897" },
 	{},
 };
-MODULE_DEVICE_TABLE(of, ksz_dt_ids);
+MODULE_DEVICE_TABLE(of, ksz9477_dt_ids);
 
-static struct spi_driver ksz_spi_driver = {
+static struct spi_driver ksz9477_spi_driver = {
 	.driver = {
 		.name	= "ksz9477-switch",
 		.owner	= THIS_MODULE,
-		.of_match_table = of_match_ptr(ksz_dt_ids),
+		.of_match_table = of_match_ptr(ksz9477_dt_ids),
 	},
-	.probe	= ksz_spi_probe,
-	.remove	= ksz_spi_remove,
+	.probe	= ksz9477_spi_probe,
+	.remove	= ksz9477_spi_remove,
+	.shutdown = ksz9477_spi_shutdown,
 };
 
-module_spi_driver(ksz_spi_driver);
+module_spi_driver(ksz9477_spi_driver);
 
 MODULE_AUTHOR("Woojung Huh <Woojung.Huh@microchip.com>");
-MODULE_DESCRIPTION("Microchip KSZ Series Switch SPI access Driver");
+MODULE_DESCRIPTION("Microchip KSZ9477 Series Switch SPI access Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 50b24dc39962..9705808c3af7 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -14,1123 +14,251 @@
 #include <linux/phy.h>
 #include <linux/etherdevice.h>
 #include <linux/if_bridge.h>
+#include <linux/of_net.h>
 #include <net/dsa.h>
 #include <net/switchdev.h>
 
 #include "ksz_priv.h"
 
-static const struct {
-	int index;
-	char string[ETH_GSTRING_LEN];
-} mib_names[TOTAL_SWITCH_COUNTER_NUM] = {
-	{ 0x00, "rx_hi" },
-	{ 0x01, "rx_undersize" },
-	{ 0x02, "rx_fragments" },
-	{ 0x03, "rx_oversize" },
-	{ 0x04, "rx_jabbers" },
-	{ 0x05, "rx_symbol_err" },
-	{ 0x06, "rx_crc_err" },
-	{ 0x07, "rx_align_err" },
-	{ 0x08, "rx_mac_ctrl" },
-	{ 0x09, "rx_pause" },
-	{ 0x0A, "rx_bcast" },
-	{ 0x0B, "rx_mcast" },
-	{ 0x0C, "rx_ucast" },
-	{ 0x0D, "rx_64_or_less" },
-	{ 0x0E, "rx_65_127" },
-	{ 0x0F, "rx_128_255" },
-	{ 0x10, "rx_256_511" },
-	{ 0x11, "rx_512_1023" },
-	{ 0x12, "rx_1024_1522" },
-	{ 0x13, "rx_1523_2000" },
-	{ 0x14, "rx_2001" },
-	{ 0x15, "tx_hi" },
-	{ 0x16, "tx_late_col" },
-	{ 0x17, "tx_pause" },
-	{ 0x18, "tx_bcast" },
-	{ 0x19, "tx_mcast" },
-	{ 0x1A, "tx_ucast" },
-	{ 0x1B, "tx_deferred" },
-	{ 0x1C, "tx_total_col" },
-	{ 0x1D, "tx_exc_col" },
-	{ 0x1E, "tx_single_col" },
-	{ 0x1F, "tx_mult_col" },
-	{ 0x80, "rx_total" },
-	{ 0x81, "tx_total" },
-	{ 0x82, "rx_discards" },
-	{ 0x83, "tx_discards" },
-};
-
-static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set)
-{
-	u8 data;
-
-	ksz_read8(dev, addr, &data);
-	if (set)
-		data |= bits;
-	else
-		data &= ~bits;
-	ksz_write8(dev, addr, data);
-}
-
-static void ksz_cfg32(struct ksz_device *dev, u32 addr, u32 bits, bool set)
-{
-	u32 data;
-
-	ksz_read32(dev, addr, &data);
-	if (set)
-		data |= bits;
-	else
-		data &= ~bits;
-	ksz_write32(dev, addr, data);
-}
-
-static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits,
-			 bool set)
-{
-	u32 addr;
-	u8 data;
-
-	addr = PORT_CTRL_ADDR(port, offset);
-	ksz_read8(dev, addr, &data);
-
-	if (set)
-		data |= bits;
-	else
-		data &= ~bits;
-
-	ksz_write8(dev, addr, data);
-}
-
-static void ksz_port_cfg32(struct ksz_device *dev, int port, int offset,
-			   u32 bits, bool set)
-{
-	u32 addr;
-	u32 data;
-
-	addr = PORT_CTRL_ADDR(port, offset);
-	ksz_read32(dev, addr, &data);
-
-	if (set)
-		data |= bits;
-	else
-		data &= ~bits;
-
-	ksz_write32(dev, addr, data);
-}
-
-static int wait_vlan_ctrl_ready(struct ksz_device *dev, u32 waiton, int timeout)
-{
-	u8 data;
-
-	do {
-		ksz_read8(dev, REG_SW_VLAN_CTRL, &data);
-		if (!(data & waiton))
-			break;
-		usleep_range(1, 10);
-	} while (timeout-- > 0);
-
-	if (timeout <= 0)
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-static int get_vlan_table(struct dsa_switch *ds, u16 vid, u32 *vlan_table)
-{
-	struct ksz_device *dev = ds->priv;
-	int ret;
-
-	mutex_lock(&dev->vlan_mutex);
-
-	ksz_write16(dev, REG_SW_VLAN_ENTRY_INDEX__2, vid & VLAN_INDEX_M);
-	ksz_write8(dev, REG_SW_VLAN_CTRL, VLAN_READ | VLAN_START);
-
-	/* wait to be cleared */
-	ret = wait_vlan_ctrl_ready(dev, VLAN_START, 1000);
-	if (ret < 0) {
-		dev_dbg(dev->dev, "Failed to read vlan table\n");
-		goto exit;
-	}
-
-	ksz_read32(dev, REG_SW_VLAN_ENTRY__4, &vlan_table[0]);
-	ksz_read32(dev, REG_SW_VLAN_ENTRY_UNTAG__4, &vlan_table[1]);
-	ksz_read32(dev, REG_SW_VLAN_ENTRY_PORTS__4, &vlan_table[2]);
-
-	ksz_write8(dev, REG_SW_VLAN_CTRL, 0);
-
-exit:
-	mutex_unlock(&dev->vlan_mutex);
-
-	return ret;
-}
-
-static int set_vlan_table(struct dsa_switch *ds, u16 vid, u32 *vlan_table)
-{
-	struct ksz_device *dev = ds->priv;
-	int ret;
-
-	mutex_lock(&dev->vlan_mutex);
-
-	ksz_write32(dev, REG_SW_VLAN_ENTRY__4, vlan_table[0]);
-	ksz_write32(dev, REG_SW_VLAN_ENTRY_UNTAG__4, vlan_table[1]);
-	ksz_write32(dev, REG_SW_VLAN_ENTRY_PORTS__4, vlan_table[2]);
-
-	ksz_write16(dev, REG_SW_VLAN_ENTRY_INDEX__2, vid & VLAN_INDEX_M);
-	ksz_write8(dev, REG_SW_VLAN_CTRL, VLAN_START | VLAN_WRITE);
-
-	/* wait to be cleared */
-	ret = wait_vlan_ctrl_ready(dev, VLAN_START, 1000);
-	if (ret < 0) {
-		dev_dbg(dev->dev, "Failed to write vlan table\n");
-		goto exit;
-	}
-
-	ksz_write8(dev, REG_SW_VLAN_CTRL, 0);
-
-	/* update vlan cache table */
-	dev->vlan_cache[vid].table[0] = vlan_table[0];
-	dev->vlan_cache[vid].table[1] = vlan_table[1];
-	dev->vlan_cache[vid].table[2] = vlan_table[2];
-
-exit:
-	mutex_unlock(&dev->vlan_mutex);
-
-	return ret;
-}
-
-static void read_table(struct dsa_switch *ds, u32 *table)
-{
-	struct ksz_device *dev = ds->priv;
-
-	ksz_read32(dev, REG_SW_ALU_VAL_A, &table[0]);
-	ksz_read32(dev, REG_SW_ALU_VAL_B, &table[1]);
-	ksz_read32(dev, REG_SW_ALU_VAL_C, &table[2]);
-	ksz_read32(dev, REG_SW_ALU_VAL_D, &table[3]);
-}
-
-static void write_table(struct dsa_switch *ds, u32 *table)
-{
-	struct ksz_device *dev = ds->priv;
-
-	ksz_write32(dev, REG_SW_ALU_VAL_A, table[0]);
-	ksz_write32(dev, REG_SW_ALU_VAL_B, table[1]);
-	ksz_write32(dev, REG_SW_ALU_VAL_C, table[2]);
-	ksz_write32(dev, REG_SW_ALU_VAL_D, table[3]);
-}
-
-static int wait_alu_ready(struct ksz_device *dev, u32 waiton, int timeout)
-{
-	u32 data;
-
-	do {
-		ksz_read32(dev, REG_SW_ALU_CTRL__4, &data);
-		if (!(data & waiton))
-			break;
-		usleep_range(1, 10);
-	} while (timeout-- > 0);
-
-	if (timeout <= 0)
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-static int wait_alu_sta_ready(struct ksz_device *dev, u32 waiton, int timeout)
-{
-	u32 data;
-
-	do {
-		ksz_read32(dev, REG_SW_ALU_STAT_CTRL__4, &data);
-		if (!(data & waiton))
-			break;
-		usleep_range(1, 10);
-	} while (timeout-- > 0);
-
-	if (timeout <= 0)
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-static int ksz9477_reset_switch(struct ksz_device *dev)
-{
-	u8 data8;
-	u16 data16;
-	u32 data32;
-
-	/* reset switch */
-	ksz_cfg(dev, REG_SW_OPERATION, SW_RESET, true);
-
-	/* turn off SPI DO Edge select */
-	ksz_read8(dev, REG_SW_GLOBAL_SERIAL_CTRL_0, &data8);
-	data8 &= ~SPI_AUTO_EDGE_DETECTION;
-	ksz_write8(dev, REG_SW_GLOBAL_SERIAL_CTRL_0, data8);
-
-	/* default configuration */
-	ksz_read8(dev, REG_SW_LUE_CTRL_1, &data8);
-	data8 = SW_AGING_ENABLE | SW_LINK_AUTO_AGING |
-	      SW_SRC_ADDR_FILTER | SW_FLUSH_STP_TABLE | SW_FLUSH_MSTP_TABLE;
-	ksz_write8(dev, REG_SW_LUE_CTRL_1, data8);
-
-	/* disable interrupts */
-	ksz_write32(dev, REG_SW_INT_MASK__4, SWITCH_INT_MASK);
-	ksz_write32(dev, REG_SW_PORT_INT_MASK__4, 0x7F);
-	ksz_read32(dev, REG_SW_PORT_INT_STATUS__4, &data32);
-
-	/* set broadcast storm protection 10% rate */
-	ksz_read16(dev, REG_SW_MAC_CTRL_2, &data16);
-	data16 &= ~BROADCAST_STORM_RATE;
-	data16 |= (BROADCAST_STORM_VALUE * BROADCAST_STORM_PROT_RATE) / 100;
-	ksz_write16(dev, REG_SW_MAC_CTRL_2, data16);
-
-	return 0;
-}
-
-static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port)
-{
-	u8 data8;
-	u16 data16;
-
-	/* enable tag tail for host port */
-	if (cpu_port)
-		ksz_port_cfg(dev, port, REG_PORT_CTRL_0, PORT_TAIL_TAG_ENABLE,
-			     true);
-
-	ksz_port_cfg(dev, port, REG_PORT_CTRL_0, PORT_MAC_LOOPBACK, false);
-
-	/* set back pressure */
-	ksz_port_cfg(dev, port, REG_PORT_MAC_CTRL_1, PORT_BACK_PRESSURE, true);
-
-	/* set flow control */
-	ksz_port_cfg(dev, port, REG_PORT_CTRL_0,
-		     PORT_FORCE_TX_FLOW_CTRL | PORT_FORCE_RX_FLOW_CTRL, true);
-
-	/* enable broadcast storm limit */
-	ksz_port_cfg(dev, port, P_BCAST_STORM_CTRL, PORT_BROADCAST_STORM, true);
-
-	/* disable DiffServ priority */
-	ksz_port_cfg(dev, port, P_PRIO_CTRL, PORT_DIFFSERV_PRIO_ENABLE, false);
-
-	/* replace priority */
-	ksz_port_cfg(dev, port, REG_PORT_MRI_MAC_CTRL, PORT_USER_PRIO_CEILING,
-		     false);
-	ksz_port_cfg32(dev, port, REG_PORT_MTI_QUEUE_CTRL_0__4,
-		       MTI_PVID_REPLACE, false);
-
-	/* enable 802.1p priority */
-	ksz_port_cfg(dev, port, P_PRIO_CTRL, PORT_802_1P_PRIO_ENABLE, true);
-
-	/* configure MAC to 1G & RGMII mode */
-	ksz_pread8(dev, port, REG_PORT_XMII_CTRL_1, &data8);
-	data8 |= PORT_RGMII_ID_EG_ENABLE;
-	data8 &= ~PORT_MII_NOT_1GBIT;
-	data8 &= ~PORT_MII_SEL_M;
-	data8 |= PORT_RGMII_SEL;
-	ksz_pwrite8(dev, port, REG_PORT_XMII_CTRL_1, data8);
-
-	/* clear pending interrupts */
-	ksz_pread16(dev, port, REG_PORT_PHY_INT_ENABLE, &data16);
-}
-
-static void ksz9477_config_cpu_port(struct dsa_switch *ds)
+void ksz_update_port_member(struct ksz_device *dev, int port)
 {
-	struct ksz_device *dev = ds->priv;
+	struct ksz_port *p;
 	int i;
 
-	ds->num_ports = dev->port_cnt;
-
-	for (i = 0; i < ds->num_ports; i++) {
-		if (dsa_is_cpu_port(ds, i) && (dev->cpu_ports & (1 << i))) {
-			dev->cpu_port = i;
-
-			/* enable cpu port */
-			ksz9477_port_setup(dev, i, true);
-		}
+	for (i = 0; i < dev->port_cnt; i++) {
+		if (i == port || i == dev->cpu_port)
+			continue;
+		p = &dev->ports[i];
+		if (!(dev->member & (1 << i)))
+			continue;
+
+		/* Port is a member of the bridge and is forwarding. */
+		if (p->stp_state == BR_STATE_FORWARDING &&
+		    p->member != dev->member)
+			dev->dev_ops->cfg_port_member(dev, i, dev->member);
 	}
 }
+EXPORT_SYMBOL_GPL(ksz_update_port_member);
 
-static int ksz9477_setup(struct dsa_switch *ds)
+int ksz_phy_read16(struct dsa_switch *ds, int addr, int reg)
 {
 	struct ksz_device *dev = ds->priv;
-	int ret = 0;
-
-	dev->vlan_cache = devm_kcalloc(dev->dev, sizeof(struct vlan_table),
-				       dev->num_vlans, GFP_KERNEL);
-	if (!dev->vlan_cache)
-		return -ENOMEM;
-
-	ret = ksz9477_reset_switch(dev);
-	if (ret) {
-		dev_err(ds->dev, "failed to reset switch\n");
-		return ret;
-	}
-
-	/* accept packet up to 2000bytes */
-	ksz_cfg(dev, REG_SW_MAC_CTRL_1, SW_LEGAL_PACKET_DISABLE, true);
-
-	ksz9477_config_cpu_port(ds);
-
-	ksz_cfg(dev, REG_SW_MAC_CTRL_1, MULTICAST_STORM_DISABLE, true);
-
-	/* queue based egress rate limit */
-	ksz_cfg(dev, REG_SW_MAC_CTRL_5, SW_OUT_RATE_LIMIT_QUEUE_BASED, true);
+	u16 val = 0xffff;
 
-	/* start switch */
-	ksz_cfg(dev, REG_SW_OPERATION, SW_START, true);
-
-	return 0;
-}
-
-static enum dsa_tag_protocol ksz9477_get_tag_protocol(struct dsa_switch *ds,
-						      int port)
-{
-	return DSA_TAG_PROTO_KSZ;
-}
-
-static int ksz9477_phy_read16(struct dsa_switch *ds, int addr, int reg)
-{
-	struct ksz_device *dev = ds->priv;
-	u16 val = 0;
-
-	ksz_pread16(dev, addr, 0x100 + (reg << 1), &val);
+	dev->dev_ops->r_phy(dev, addr, reg, &val);
 
 	return val;
 }
+EXPORT_SYMBOL_GPL(ksz_phy_read16);
 
-static int ksz9477_phy_write16(struct dsa_switch *ds, int addr, int reg,
-			       u16 val)
-{
-	struct ksz_device *dev = ds->priv;
-
-	ksz_pwrite16(dev, addr, 0x100 + (reg << 1), val);
-
-	return 0;
-}
-
-static int ksz_enable_port(struct dsa_switch *ds, int port,
-			   struct phy_device *phy)
+int ksz_phy_write16(struct dsa_switch *ds, int addr, int reg, u16 val)
 {
 	struct ksz_device *dev = ds->priv;
 
-	/* setup slave port */
-	ksz9477_port_setup(dev, port, false);
+	dev->dev_ops->w_phy(dev, addr, reg, val);
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ksz_phy_write16);
 
-static void ksz_disable_port(struct dsa_switch *ds, int port,
-			     struct phy_device *phy)
+int ksz_sset_count(struct dsa_switch *ds, int port, int sset)
 {
 	struct ksz_device *dev = ds->priv;
 
-	/* there is no port disable */
-	ksz_port_cfg(dev, port, REG_PORT_CTRL_0, PORT_MAC_LOOPBACK, true);
-}
-
-static int ksz_sset_count(struct dsa_switch *ds, int port, int sset)
-{
 	if (sset != ETH_SS_STATS)
 		return 0;
 
-	return TOTAL_SWITCH_COUNTER_NUM;
+	return dev->mib_cnt;
 }
+EXPORT_SYMBOL_GPL(ksz_sset_count);
 
-static void ksz9477_get_strings(struct dsa_switch *ds, int port,
-				u32 stringset, uint8_t *buf)
-{
-	int i;
-
-	if (stringset != ETH_SS_STATS)
-		return;
-
-	for (i = 0; i < TOTAL_SWITCH_COUNTER_NUM; i++) {
-		memcpy(buf + i * ETH_GSTRING_LEN, mib_names[i].string,
-		       ETH_GSTRING_LEN);
-	}
-}
-
-static void ksz_get_ethtool_stats(struct dsa_switch *ds, int port,
-				  uint64_t *buf)
+int ksz_port_bridge_join(struct dsa_switch *ds, int port,
+			 struct net_device *br)
 {
 	struct ksz_device *dev = ds->priv;
-	int i;
-	u32 data;
-	int timeout;
 
-	mutex_lock(&dev->stats_mutex);
+	dev->br_member |= (1 << port);
 
-	for (i = 0; i < TOTAL_SWITCH_COUNTER_NUM; i++) {
-		data = MIB_COUNTER_READ;
-		data |= ((mib_names[i].index & 0xFF) << MIB_COUNTER_INDEX_S);
-		ksz_pwrite32(dev, port, REG_PORT_MIB_CTRL_STAT__4, data);
+	/* port_stp_state_set() will be called after to put the port in
+	 * appropriate state so there is no need to do anything.
+	 */
 
-		timeout = 1000;
-		do {
-			ksz_pread32(dev, port, REG_PORT_MIB_CTRL_STAT__4,
-				    &data);
-			usleep_range(1, 10);
-			if (!(data & MIB_COUNTER_READ))
-				break;
-		} while (timeout-- > 0);
-
-		/* failed to read MIB. get out of loop */
-		if (!timeout) {
-			dev_dbg(dev->dev, "Failed to get MIB\n");
-			break;
-		}
-
-		/* count resets upon read */
-		ksz_pread32(dev, port, REG_PORT_MIB_DATA, &data);
-
-		dev->mib_value[i] += (uint64_t)data;
-		buf[i] = dev->mib_value[i];
-	}
-
-	mutex_unlock(&dev->stats_mutex);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(ksz_port_bridge_join);
 
-static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port,
-				       u8 state)
+void ksz_port_bridge_leave(struct dsa_switch *ds, int port,
+			   struct net_device *br)
 {
 	struct ksz_device *dev = ds->priv;
-	u8 data;
 
-	ksz_pread8(dev, port, P_STP_CTRL, &data);
-	data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE);
+	dev->br_member &= ~(1 << port);
+	dev->member &= ~(1 << port);
 
-	switch (state) {
-	case BR_STATE_DISABLED:
-		data |= PORT_LEARN_DISABLE;
-		break;
-	case BR_STATE_LISTENING:
-		data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE);
-		break;
-	case BR_STATE_LEARNING:
-		data |= PORT_RX_ENABLE;
-		break;
-	case BR_STATE_FORWARDING:
-		data |= (PORT_TX_ENABLE | PORT_RX_ENABLE);
-		break;
-	case BR_STATE_BLOCKING:
-		data |= PORT_LEARN_DISABLE;
-		break;
-	default:
-		dev_err(ds->dev, "invalid STP state: %d\n", state);
-		return;
-	}
-
-	ksz_pwrite8(dev, port, P_STP_CTRL, data);
+	/* port_stp_state_set() will be called after to put the port in
+	 * forwarding state so there is no need to do anything.
+	 */
 }
+EXPORT_SYMBOL_GPL(ksz_port_bridge_leave);
 
-static void ksz_port_fast_age(struct dsa_switch *ds, int port)
+void ksz_port_fast_age(struct dsa_switch *ds, int port)
 {
 	struct ksz_device *dev = ds->priv;
-	u8 data8;
 
-	ksz_read8(dev, REG_SW_LUE_CTRL_1, &data8);
-	data8 |= SW_FAST_AGING;
-	ksz_write8(dev, REG_SW_LUE_CTRL_1, data8);
-
-	data8 &= ~SW_FAST_AGING;
-	ksz_write8(dev, REG_SW_LUE_CTRL_1, data8);
+	dev->dev_ops->flush_dyn_mac_table(dev, port);
 }
+EXPORT_SYMBOL_GPL(ksz_port_fast_age);
 
-static int ksz9477_port_vlan_filtering(struct dsa_switch *ds, int port,
-				       bool flag)
-{
-	struct ksz_device *dev = ds->priv;
-
-	if (flag) {
-		ksz_port_cfg(dev, port, REG_PORT_LUE_CTRL,
-			     PORT_VLAN_LOOKUP_VID_0, true);
-		ksz_cfg32(dev, REG_SW_QM_CTRL__4, UNICAST_VLAN_BOUNDARY, true);
-		ksz_cfg(dev, REG_SW_LUE_CTRL_0, SW_VLAN_ENABLE, true);
-	} else {
-		ksz_cfg(dev, REG_SW_LUE_CTRL_0, SW_VLAN_ENABLE, false);
-		ksz_cfg32(dev, REG_SW_QM_CTRL__4, UNICAST_VLAN_BOUNDARY, false);
-		ksz_port_cfg(dev, port, REG_PORT_LUE_CTRL,
-			     PORT_VLAN_LOOKUP_VID_0, false);
-	}
-
-	return 0;
-}
-
-static int ksz_port_vlan_prepare(struct dsa_switch *ds, int port,
-				 const struct switchdev_obj_port_vlan *vlan)
+int ksz_port_vlan_prepare(struct dsa_switch *ds, int port,
+			  const struct switchdev_obj_port_vlan *vlan)
 {
 	/* nothing needed */
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ksz_port_vlan_prepare);
 
-static void ksz9477_port_vlan_add(struct dsa_switch *ds, int port,
-				  const struct switchdev_obj_port_vlan *vlan)
-{
-	struct ksz_device *dev = ds->priv;
-	u32 vlan_table[3];
-	u16 vid;
-	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
-
-	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
-		if (get_vlan_table(ds, vid, vlan_table)) {
-			dev_dbg(dev->dev, "Failed to get vlan table\n");
-			return;
-		}
-
-		vlan_table[0] = VLAN_VALID | (vid & VLAN_FID_M);
-		if (untagged)
-			vlan_table[1] |= BIT(port);
-		else
-			vlan_table[1] &= ~BIT(port);
-		vlan_table[1] &= ~(BIT(dev->cpu_port));
-
-		vlan_table[2] |= BIT(port) | BIT(dev->cpu_port);
-
-		if (set_vlan_table(ds, vid, vlan_table)) {
-			dev_dbg(dev->dev, "Failed to set vlan table\n");
-			return;
-		}
-
-		/* change PVID */
-		if (vlan->flags & BRIDGE_VLAN_INFO_PVID)
-			ksz_pwrite16(dev, port, REG_PORT_DEFAULT_VID, vid);
-	}
-}
-
-static int ksz9477_port_vlan_del(struct dsa_switch *ds, int port,
-				 const struct switchdev_obj_port_vlan *vlan)
-{
-	struct ksz_device *dev = ds->priv;
-	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
-	u32 vlan_table[3];
-	u16 vid;
-	u16 pvid;
-
-	ksz_pread16(dev, port, REG_PORT_DEFAULT_VID, &pvid);
-	pvid = pvid & 0xFFF;
-
-	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
-		if (get_vlan_table(ds, vid, vlan_table)) {
-			dev_dbg(dev->dev, "Failed to get vlan table\n");
-			return -ETIMEDOUT;
-		}
-
-		vlan_table[2] &= ~BIT(port);
-
-		if (pvid == vid)
-			pvid = 1;
-
-		if (untagged)
-			vlan_table[1] &= ~BIT(port);
-
-		if (set_vlan_table(ds, vid, vlan_table)) {
-			dev_dbg(dev->dev, "Failed to set vlan table\n");
-			return -ETIMEDOUT;
-		}
-	}
-
-	ksz_pwrite16(dev, port, REG_PORT_DEFAULT_VID, pvid);
-
-	return 0;
-}
-
-struct alu_struct {
-	/* entry 1 */
-	u8	is_static:1;
-	u8	is_src_filter:1;
-	u8	is_dst_filter:1;
-	u8	prio_age:3;
-	u32	_reserv_0_1:23;
-	u8	mstp:3;
-	/* entry 2 */
-	u8	is_override:1;
-	u8	is_use_fid:1;
-	u32	_reserv_1_1:23;
-	u8	port_forward:7;
-	/* entry 3 & 4*/
-	u32	_reserv_2_1:9;
-	u8	fid:7;
-	u8	mac[ETH_ALEN];
-};
-
-static int ksz9477_port_fdb_add(struct dsa_switch *ds, int port,
-				const unsigned char *addr, u16 vid)
+int ksz_port_fdb_dump(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb,
+		      void *data)
 {
 	struct ksz_device *dev = ds->priv;
-	u32 alu_table[4];
-	u32 data;
 	int ret = 0;
-
-	mutex_lock(&dev->alu_mutex);
-
-	/* find any entry with mac & vid */
-	data = vid << ALU_FID_INDEX_S;
-	data |= ((addr[0] << 8) | addr[1]);
-	ksz_write32(dev, REG_SW_ALU_INDEX_0, data);
-
-	data = ((addr[2] << 24) | (addr[3] << 16));
-	data |= ((addr[4] << 8) | addr[5]);
-	ksz_write32(dev, REG_SW_ALU_INDEX_1, data);
-
-	/* start read operation */
-	ksz_write32(dev, REG_SW_ALU_CTRL__4, ALU_READ | ALU_START);
-
-	/* wait to be finished */
-	ret = wait_alu_ready(dev, ALU_START, 1000);
-	if (ret < 0) {
-		dev_dbg(dev->dev, "Failed to read ALU\n");
-		goto exit;
-	}
-
-	/* read ALU entry */
-	read_table(ds, alu_table);
-
-	/* update ALU entry */
-	alu_table[0] = ALU_V_STATIC_VALID;
-	alu_table[1] |= BIT(port);
-	if (vid)
-		alu_table[1] |= ALU_V_USE_FID;
-	alu_table[2] = (vid << ALU_V_FID_S);
-	alu_table[2] |= ((addr[0] << 8) | addr[1]);
-	alu_table[3] = ((addr[2] << 24) | (addr[3] << 16));
-	alu_table[3] |= ((addr[4] << 8) | addr[5]);
-
-	write_table(ds, alu_table);
-
-	ksz_write32(dev, REG_SW_ALU_CTRL__4, ALU_WRITE | ALU_START);
-
-	/* wait to be finished */
-	ret = wait_alu_ready(dev, ALU_START, 1000);
-	if (ret < 0)
-		dev_dbg(dev->dev, "Failed to write ALU\n");
-
-exit:
-	mutex_unlock(&dev->alu_mutex);
-
-	return ret;
-}
-
-static int ksz9477_port_fdb_del(struct dsa_switch *ds, int port,
-				const unsigned char *addr, u16 vid)
-{
-	struct ksz_device *dev = ds->priv;
-	u32 alu_table[4];
-	u32 data;
-	int ret = 0;
-
-	mutex_lock(&dev->alu_mutex);
-
-	/* read any entry with mac & vid */
-	data = vid << ALU_FID_INDEX_S;
-	data |= ((addr[0] << 8) | addr[1]);
-	ksz_write32(dev, REG_SW_ALU_INDEX_0, data);
-
-	data = ((addr[2] << 24) | (addr[3] << 16));
-	data |= ((addr[4] << 8) | addr[5]);
-	ksz_write32(dev, REG_SW_ALU_INDEX_1, data);
-
-	/* start read operation */
-	ksz_write32(dev, REG_SW_ALU_CTRL__4, ALU_READ | ALU_START);
-
-	/* wait to be finished */
-	ret = wait_alu_ready(dev, ALU_START, 1000);
-	if (ret < 0) {
-		dev_dbg(dev->dev, "Failed to read ALU\n");
-		goto exit;
-	}
-
-	ksz_read32(dev, REG_SW_ALU_VAL_A, &alu_table[0]);
-	if (alu_table[0] & ALU_V_STATIC_VALID) {
-		ksz_read32(dev, REG_SW_ALU_VAL_B, &alu_table[1]);
-		ksz_read32(dev, REG_SW_ALU_VAL_C, &alu_table[2]);
-		ksz_read32(dev, REG_SW_ALU_VAL_D, &alu_table[3]);
-
-		/* clear forwarding port */
-		alu_table[2] &= ~BIT(port);
-
-		/* if there is no port to forward, clear table */
-		if ((alu_table[2] & ALU_V_PORT_MAP) == 0) {
-			alu_table[0] = 0;
-			alu_table[1] = 0;
-			alu_table[2] = 0;
-			alu_table[3] = 0;
-		}
-	} else {
-		alu_table[0] = 0;
-		alu_table[1] = 0;
-		alu_table[2] = 0;
-		alu_table[3] = 0;
-	}
-
-	write_table(ds, alu_table);
-
-	ksz_write32(dev, REG_SW_ALU_CTRL__4, ALU_WRITE | ALU_START);
-
-	/* wait to be finished */
-	ret = wait_alu_ready(dev, ALU_START, 1000);
-	if (ret < 0)
-		dev_dbg(dev->dev, "Failed to write ALU\n");
-
-exit:
-	mutex_unlock(&dev->alu_mutex);
-
-	return ret;
-}
-
-static void convert_alu(struct alu_struct *alu, u32 *alu_table)
-{
-	alu->is_static = !!(alu_table[0] & ALU_V_STATIC_VALID);
-	alu->is_src_filter = !!(alu_table[0] & ALU_V_SRC_FILTER);
-	alu->is_dst_filter = !!(alu_table[0] & ALU_V_DST_FILTER);
-	alu->prio_age = (alu_table[0] >> ALU_V_PRIO_AGE_CNT_S) &
-			ALU_V_PRIO_AGE_CNT_M;
-	alu->mstp = alu_table[0] & ALU_V_MSTP_M;
-
-	alu->is_override = !!(alu_table[1] & ALU_V_OVERRIDE);
-	alu->is_use_fid = !!(alu_table[1] & ALU_V_USE_FID);
-	alu->port_forward = alu_table[1] & ALU_V_PORT_MAP;
-
-	alu->fid = (alu_table[2] >> ALU_V_FID_S) & ALU_V_FID_M;
-
-	alu->mac[0] = (alu_table[2] >> 8) & 0xFF;
-	alu->mac[1] = alu_table[2] & 0xFF;
-	alu->mac[2] = (alu_table[3] >> 24) & 0xFF;
-	alu->mac[3] = (alu_table[3] >> 16) & 0xFF;
-	alu->mac[4] = (alu_table[3] >> 8) & 0xFF;
-	alu->mac[5] = alu_table[3] & 0xFF;
-}
-
-static int ksz9477_port_fdb_dump(struct dsa_switch *ds, int port,
-				 dsa_fdb_dump_cb_t *cb, void *data)
-{
-	struct ksz_device *dev = ds->priv;
-	int ret = 0;
-	u32 ksz_data;
-	u32 alu_table[4];
+	u16 i = 0;
+	u16 entries = 0;
+	u8 timestamp = 0;
+	u8 fid;
+	u8 member;
 	struct alu_struct alu;
-	int timeout;
-
-	mutex_lock(&dev->alu_mutex);
-
-	/* start ALU search */
-	ksz_write32(dev, REG_SW_ALU_CTRL__4, ALU_START | ALU_SEARCH);
 
 	do {
-		timeout = 1000;
-		do {
-			ksz_read32(dev, REG_SW_ALU_CTRL__4, &ksz_data);
-			if ((ksz_data & ALU_VALID) || !(ksz_data & ALU_START))
-				break;
-			usleep_range(1, 10);
-		} while (timeout-- > 0);
-
-		if (!timeout) {
-			dev_dbg(dev->dev, "Failed to search ALU\n");
-			ret = -ETIMEDOUT;
-			goto exit;
-		}
-
-		/* read ALU table */
-		read_table(ds, alu_table);
-
-		convert_alu(&alu, alu_table);
-
-		if (alu.port_forward & BIT(port)) {
+		alu.is_static = false;
+		ret = dev->dev_ops->r_dyn_mac_table(dev, i, alu.mac, &fid,
+						    &member, &timestamp,
+						    &entries);
+		if (!ret && (member & BIT(port))) {
 			ret = cb(alu.mac, alu.fid, alu.is_static, data);
 			if (ret)
-				goto exit;
+				break;
 		}
-	} while (ksz_data & ALU_START);
-
-exit:
-
-	/* stop ALU search */
-	ksz_write32(dev, REG_SW_ALU_CTRL__4, 0);
-
-	mutex_unlock(&dev->alu_mutex);
+		i++;
+	} while (i < entries);
+	if (i >= entries)
+		ret = 0;
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(ksz_port_fdb_dump);
 
-static int ksz_port_mdb_prepare(struct dsa_switch *ds, int port,
-				const struct switchdev_obj_port_mdb *mdb)
+int ksz_port_mdb_prepare(struct dsa_switch *ds, int port,
+			 const struct switchdev_obj_port_mdb *mdb)
 {
 	/* nothing to do */
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ksz_port_mdb_prepare);
 
-static void ksz9477_port_mdb_add(struct dsa_switch *ds, int port,
-				 const struct switchdev_obj_port_mdb *mdb)
+void ksz_port_mdb_add(struct dsa_switch *ds, int port,
+		      const struct switchdev_obj_port_mdb *mdb)
 {
 	struct ksz_device *dev = ds->priv;
-	u32 static_table[4];
-	u32 data;
+	struct alu_struct alu;
 	int index;
-	u32 mac_hi, mac_lo;
-
-	mac_hi = ((mdb->addr[0] << 8) | mdb->addr[1]);
-	mac_lo = ((mdb->addr[2] << 24) | (mdb->addr[3] << 16));
-	mac_lo |= ((mdb->addr[4] << 8) | mdb->addr[5]);
-
-	mutex_lock(&dev->alu_mutex);
+	int empty = 0;
 
+	alu.port_forward = 0;
 	for (index = 0; index < dev->num_statics; index++) {
-		/* find empty slot first */
-		data = (index << ALU_STAT_INDEX_S) |
-			ALU_STAT_READ | ALU_STAT_START;
-		ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data);
-
-		/* wait to be finished */
-		if (wait_alu_sta_ready(dev, ALU_STAT_START, 1000) < 0) {
-			dev_dbg(dev->dev, "Failed to read ALU STATIC\n");
-			goto exit;
-		}
-
-		/* read ALU static table */
-		read_table(ds, static_table);
-
-		if (static_table[0] & ALU_V_STATIC_VALID) {
-			/* check this has same vid & mac address */
-			if (((static_table[2] >> ALU_V_FID_S) == mdb->vid) &&
-			    ((static_table[2] & ALU_V_MAC_ADDR_HI) == mac_hi) &&
-			    static_table[3] == mac_lo) {
-				/* found matching one */
+		if (!dev->dev_ops->r_sta_mac_table(dev, index, &alu)) {
+			/* Found one already in static MAC table. */
+			if (!memcmp(alu.mac, mdb->addr, ETH_ALEN) &&
+			    alu.fid == mdb->vid)
 				break;
-			}
-		} else {
-			/* found empty one */
-			break;
+		/* Remember the first empty entry. */
+		} else if (!empty) {
+			empty = index + 1;
 		}
 	}
 
 	/* no available entry */
-	if (index == dev->num_statics)
-		goto exit;
+	if (index == dev->num_statics && !empty)
+		return;
 
 	/* add entry */
-	static_table[0] = ALU_V_STATIC_VALID;
-	static_table[1] |= BIT(port);
-	if (mdb->vid)
-		static_table[1] |= ALU_V_USE_FID;
-	static_table[2] = (mdb->vid << ALU_V_FID_S);
-	static_table[2] |= mac_hi;
-	static_table[3] = mac_lo;
-
-	write_table(ds, static_table);
-
-	data = (index << ALU_STAT_INDEX_S) | ALU_STAT_START;
-	ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data);
-
-	/* wait to be finished */
-	if (wait_alu_sta_ready(dev, ALU_STAT_START, 1000) < 0)
-		dev_dbg(dev->dev, "Failed to read ALU STATIC\n");
+	if (index == dev->num_statics) {
+		index = empty - 1;
+		memset(&alu, 0, sizeof(alu));
+		memcpy(alu.mac, mdb->addr, ETH_ALEN);
+		alu.is_static = true;
+	}
+	alu.port_forward |= BIT(port);
+	if (mdb->vid) {
+		alu.is_use_fid = true;
 
-exit:
-	mutex_unlock(&dev->alu_mutex);
+		/* Need a way to map VID to FID. */
+		alu.fid = mdb->vid;
+	}
+	dev->dev_ops->w_sta_mac_table(dev, index, &alu);
 }
+EXPORT_SYMBOL_GPL(ksz_port_mdb_add);
 
-static int ksz9477_port_mdb_del(struct dsa_switch *ds, int port,
-				const struct switchdev_obj_port_mdb *mdb)
+int ksz_port_mdb_del(struct dsa_switch *ds, int port,
+		     const struct switchdev_obj_port_mdb *mdb)
 {
 	struct ksz_device *dev = ds->priv;
-	u32 static_table[4];
-	u32 data;
+	struct alu_struct alu;
 	int index;
 	int ret = 0;
-	u32 mac_hi, mac_lo;
-
-	mac_hi = ((mdb->addr[0] << 8) | mdb->addr[1]);
-	mac_lo = ((mdb->addr[2] << 24) | (mdb->addr[3] << 16));
-	mac_lo |= ((mdb->addr[4] << 8) | mdb->addr[5]);
-
-	mutex_lock(&dev->alu_mutex);
 
 	for (index = 0; index < dev->num_statics; index++) {
-		/* find empty slot first */
-		data = (index << ALU_STAT_INDEX_S) |
-			ALU_STAT_READ | ALU_STAT_START;
-		ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data);
-
-		/* wait to be finished */
-		ret = wait_alu_sta_ready(dev, ALU_STAT_START, 1000);
-		if (ret < 0) {
-			dev_dbg(dev->dev, "Failed to read ALU STATIC\n");
-			goto exit;
-		}
-
-		/* read ALU static table */
-		read_table(ds, static_table);
-
-		if (static_table[0] & ALU_V_STATIC_VALID) {
-			/* check this has same vid & mac address */
-
-			if (((static_table[2] >> ALU_V_FID_S) == mdb->vid) &&
-			    ((static_table[2] & ALU_V_MAC_ADDR_HI) == mac_hi) &&
-			    static_table[3] == mac_lo) {
-				/* found matching one */
+		if (!dev->dev_ops->r_sta_mac_table(dev, index, &alu)) {
+			/* Found one already in static MAC table. */
+			if (!memcmp(alu.mac, mdb->addr, ETH_ALEN) &&
+			    alu.fid == mdb->vid)
 				break;
-			}
 		}
 	}
 
 	/* no available entry */
-	if (index == dev->num_statics) {
-		ret = -EINVAL;
+	if (index == dev->num_statics)
 		goto exit;
-	}
 
 	/* clear port */
-	static_table[1] &= ~BIT(port);
-
-	if ((static_table[1] & ALU_V_PORT_MAP) == 0) {
-		/* delete entry */
-		static_table[0] = 0;
-		static_table[1] = 0;
-		static_table[2] = 0;
-		static_table[3] = 0;
-	}
-
-	write_table(ds, static_table);
-
-	data = (index << ALU_STAT_INDEX_S) | ALU_STAT_START;
-	ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data);
-
-	/* wait to be finished */
-	ret = wait_alu_sta_ready(dev, ALU_STAT_START, 1000);
-	if (ret < 0)
-		dev_dbg(dev->dev, "Failed to read ALU STATIC\n");
+	alu.port_forward &= ~BIT(port);
+	if (!alu.port_forward)
+		alu.is_static = false;
+	dev->dev_ops->w_sta_mac_table(dev, index, &alu);
 
 exit:
-	mutex_unlock(&dev->alu_mutex);
-
 	return ret;
 }
+EXPORT_SYMBOL_GPL(ksz_port_mdb_del);
 
-static int ksz9477_port_mirror_add(struct dsa_switch *ds, int port,
-				   struct dsa_mall_mirror_tc_entry *mirror,
-				   bool ingress)
+int ksz_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 {
 	struct ksz_device *dev = ds->priv;
 
-	if (ingress)
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, true);
-	else
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, true);
-
-	ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, false);
-
-	/* configure mirror port */
-	ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL,
-		     PORT_MIRROR_SNIFFER, true);
+	/* setup slave port */
+	dev->dev_ops->port_setup(dev, port, false);
 
-	ksz_cfg(dev, S_MIRROR_CTRL, SW_MIRROR_RX_TX, false);
+	/* port_stp_state_set() will be called after to enable the port so
+	 * there is no need to do anything.
+	 */
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ksz_enable_port);
 
-static void ksz9477_port_mirror_del(struct dsa_switch *ds, int port,
-				    struct dsa_mall_mirror_tc_entry *mirror)
+void ksz_disable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 {
 	struct ksz_device *dev = ds->priv;
-	u8 data;
-
-	if (mirror->ingress)
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, false);
-	else
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, false);
-
-	ksz_pread8(dev, port, P_MIRROR_CTRL, &data);
-
-	if (!(data & (PORT_MIRROR_RX | PORT_MIRROR_TX)))
-		ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL,
-			     PORT_MIRROR_SNIFFER, false);
-}
-
-static const struct dsa_switch_ops ksz_switch_ops = {
-	.get_tag_protocol	= ksz9477_get_tag_protocol,
-	.setup			= ksz9477_setup,
-	.phy_read		= ksz9477_phy_read16,
-	.phy_write		= ksz9477_phy_write16,
-	.port_enable		= ksz_enable_port,
-	.port_disable		= ksz_disable_port,
-	.get_strings		= ksz9477_get_strings,
-	.get_ethtool_stats	= ksz_get_ethtool_stats,
-	.get_sset_count		= ksz_sset_count,
-	.port_stp_state_set	= ksz9477_port_stp_state_set,
-	.port_fast_age		= ksz_port_fast_age,
-	.port_vlan_filtering	= ksz9477_port_vlan_filtering,
-	.port_vlan_prepare	= ksz_port_vlan_prepare,
-	.port_vlan_add		= ksz9477_port_vlan_add,
-	.port_vlan_del		= ksz9477_port_vlan_del,
-	.port_fdb_dump		= ksz9477_port_fdb_dump,
-	.port_fdb_add		= ksz9477_port_fdb_add,
-	.port_fdb_del		= ksz9477_port_fdb_del,
-	.port_mdb_prepare       = ksz_port_mdb_prepare,
-	.port_mdb_add           = ksz9477_port_mdb_add,
-	.port_mdb_del           = ksz9477_port_mdb_del,
-	.port_mirror_add	= ksz9477_port_mirror_add,
-	.port_mirror_del	= ksz9477_port_mirror_del,
-};
-
-struct ksz_chip_data {
-	u32 chip_id;
-	const char *dev_name;
-	int num_vlans;
-	int num_alus;
-	int num_statics;
-	int cpu_ports;
-	int port_cnt;
-};
-
-static const struct ksz_chip_data ksz9477_switch_chips[] = {
-	{
-		.chip_id = 0x00947700,
-		.dev_name = "KSZ9477",
-		.num_vlans = 4096,
-		.num_alus = 4096,
-		.num_statics = 16,
-		.cpu_ports = 0x7F,	/* can be configured as cpu port */
-		.port_cnt = 7,		/* total physical port count */
-	},
-	{
-		.chip_id = 0x00989700,
-		.dev_name = "KSZ9897",
-		.num_vlans = 4096,
-		.num_alus = 4096,
-		.num_statics = 16,
-		.cpu_ports = 0x7F,	/* can be configured as cpu port */
-		.port_cnt = 7,		/* total physical port count */
-	},
-};
-
-static int ksz9477_switch_init(struct ksz_device *dev)
-{
-	int i;
-
-	dev->ds->ops = &ksz_switch_ops;
-
-	for (i = 0; i < ARRAY_SIZE(ksz9477_switch_chips); i++) {
-		const struct ksz_chip_data *chip = &ksz9477_switch_chips[i];
 
-		if (dev->chip_id == chip->chip_id) {
-			dev->name = chip->dev_name;
-			dev->num_vlans = chip->num_vlans;
-			dev->num_alus = chip->num_alus;
-			dev->num_statics = chip->num_statics;
-			dev->port_cnt = chip->port_cnt;
-			dev->cpu_ports = chip->cpu_ports;
-
-			break;
-		}
-	}
+	dev->on_ports &= ~(1 << port);
+	dev->live_ports &= ~(1 << port);
 
-	/* no switch found */
-	if (!dev->port_cnt)
-		return -ENODEV;
-
-	return 0;
+	/* port_stp_state_set() will be called after to disable the port so
+	 * there is no need to do anything.
+	 */
 }
+EXPORT_SYMBOL_GPL(ksz_disable_port);
 
 struct ksz_device *ksz_switch_alloc(struct device *base,
 				    const struct ksz_io_ops *ops,
@@ -1158,34 +286,8 @@ struct ksz_device *ksz_switch_alloc(struct device *base,
 }
 EXPORT_SYMBOL(ksz_switch_alloc);
 
-int ksz_switch_detect(struct ksz_device *dev)
-{
-	u8 data8;
-	u32 id32;
-	int ret;
-
-	/* turn off SPI DO Edge select */
-	ret = ksz_read8(dev, REG_SW_GLOBAL_SERIAL_CTRL_0, &data8);
-	if (ret)
-		return ret;
-
-	data8 &= ~SPI_AUTO_EDGE_DETECTION;
-	ret = ksz_write8(dev, REG_SW_GLOBAL_SERIAL_CTRL_0, data8);
-	if (ret)
-		return ret;
-
-	/* read chip id */
-	ret = ksz_read32(dev, REG_CHIP_ID0__1, &id32);
-	if (ret)
-		return ret;
-
-	dev->chip_id = id32;
-
-	return 0;
-}
-EXPORT_SYMBOL(ksz_switch_detect);
-
-int ksz_switch_register(struct ksz_device *dev)
+int ksz_switch_register(struct ksz_device *dev,
+			const struct ksz_dev_ops *ops)
 {
 	int ret;
 
@@ -1197,19 +299,35 @@ int ksz_switch_register(struct ksz_device *dev)
 	mutex_init(&dev->alu_mutex);
 	mutex_init(&dev->vlan_mutex);
 
-	if (ksz_switch_detect(dev))
+	dev->dev_ops = ops;
+
+	if (dev->dev_ops->detect(dev))
 		return -EINVAL;
 
-	ret = ksz9477_switch_init(dev);
+	ret = dev->dev_ops->init(dev);
 	if (ret)
 		return ret;
 
-	return dsa_register_switch(dev->ds);
+	dev->interface = PHY_INTERFACE_MODE_MII;
+	if (dev->dev->of_node) {
+		ret = of_get_phy_mode(dev->dev->of_node);
+		if (ret >= 0)
+			dev->interface = ret;
+	}
+
+	ret = dsa_register_switch(dev->ds);
+	if (ret) {
+		dev->dev_ops->exit(dev);
+		return ret;
+	}
+
+	return 0;
 }
 EXPORT_SYMBOL(ksz_switch_register);
 
 void ksz_switch_remove(struct ksz_device *dev)
 {
+	dev->dev_ops->exit(dev);
 	dsa_unregister_switch(dev->ds);
 }
 EXPORT_SYMBOL(ksz_switch_remove);
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
new file mode 100644
index 000000000000..2dd832de0d52
--- /dev/null
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -0,0 +1,214 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Microchip switch driver common header
+ *
+ * Copyright (C) 2017-2018 Microchip Technology Inc.
+ */
+
+#ifndef __KSZ_COMMON_H
+#define __KSZ_COMMON_H
+
+void ksz_update_port_member(struct ksz_device *dev, int port);
+
+/* Common DSA access functions */
+
+int ksz_phy_read16(struct dsa_switch *ds, int addr, int reg);
+int ksz_phy_write16(struct dsa_switch *ds, int addr, int reg, u16 val);
+int ksz_sset_count(struct dsa_switch *ds, int port, int sset);
+int ksz_port_bridge_join(struct dsa_switch *ds, int port,
+			 struct net_device *br);
+void ksz_port_bridge_leave(struct dsa_switch *ds, int port,
+			   struct net_device *br);
+void ksz_port_fast_age(struct dsa_switch *ds, int port);
+int ksz_port_vlan_prepare(struct dsa_switch *ds, int port,
+			  const struct switchdev_obj_port_vlan *vlan);
+int ksz_port_fdb_dump(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb,
+		      void *data);
+int ksz_port_mdb_prepare(struct dsa_switch *ds, int port,
+			 const struct switchdev_obj_port_mdb *mdb);
+void ksz_port_mdb_add(struct dsa_switch *ds, int port,
+		      const struct switchdev_obj_port_mdb *mdb);
+int ksz_port_mdb_del(struct dsa_switch *ds, int port,
+		     const struct switchdev_obj_port_mdb *mdb);
+int ksz_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
+void ksz_disable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
+
+/* Common register access functions */
+
+static inline int ksz_read8(struct ksz_device *dev, u32 reg, u8 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read8(dev, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int ksz_read16(struct ksz_device *dev, u32 reg, u16 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read16(dev, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int ksz_read24(struct ksz_device *dev, u32 reg, u32 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read24(dev, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int ksz_read32(struct ksz_device *dev, u32 reg, u32 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read32(dev, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int ksz_write8(struct ksz_device *dev, u32 reg, u8 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write8(dev, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int ksz_write16(struct ksz_device *dev, u32 reg, u16 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write16(dev, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int ksz_write24(struct ksz_device *dev, u32 reg, u32 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write24(dev, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int ksz_write32(struct ksz_device *dev, u32 reg, u32 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write32(dev, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int ksz_get(struct ksz_device *dev, u32 reg, void *data,
+			  size_t len)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->get(dev, reg, data, len);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int ksz_set(struct ksz_device *dev, u32 reg, void *data,
+			  size_t len)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->set(dev, reg, data, len);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline void ksz_pread8(struct ksz_device *dev, int port, int offset,
+			      u8 *data)
+{
+	ksz_read8(dev, dev->dev_ops->get_port_addr(port, offset), data);
+}
+
+static inline void ksz_pread16(struct ksz_device *dev, int port, int offset,
+			       u16 *data)
+{
+	ksz_read16(dev, dev->dev_ops->get_port_addr(port, offset), data);
+}
+
+static inline void ksz_pread32(struct ksz_device *dev, int port, int offset,
+			       u32 *data)
+{
+	ksz_read32(dev, dev->dev_ops->get_port_addr(port, offset), data);
+}
+
+static inline void ksz_pwrite8(struct ksz_device *dev, int port, int offset,
+			       u8 data)
+{
+	ksz_write8(dev, dev->dev_ops->get_port_addr(port, offset), data);
+}
+
+static inline void ksz_pwrite16(struct ksz_device *dev, int port, int offset,
+				u16 data)
+{
+	ksz_write16(dev, dev->dev_ops->get_port_addr(port, offset), data);
+}
+
+static inline void ksz_pwrite32(struct ksz_device *dev, int port, int offset,
+				u32 data)
+{
+	ksz_write32(dev, dev->dev_ops->get_port_addr(port, offset), data);
+}
+
+static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set)
+{
+	u8 data;
+
+	ksz_read8(dev, addr, &data);
+	if (set)
+		data |= bits;
+	else
+		data &= ~bits;
+	ksz_write8(dev, addr, data);
+}
+
+static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits,
+			 bool set)
+{
+	u32 addr;
+	u8 data;
+
+	addr = dev->dev_ops->get_port_addr(port, offset);
+	ksz_read8(dev, addr, &data);
+
+	if (set)
+		data |= bits;
+	else
+		data &= ~bits;
+
+	ksz_write8(dev, addr, data);
+}
+
+#endif
diff --git a/drivers/net/dsa/microchip/ksz_priv.h b/drivers/net/dsa/microchip/ksz_priv.h
index 6a27933bef74..74c5c1a68d6a 100644
--- a/drivers/net/dsa/microchip/ksz_priv.h
+++ b/drivers/net/dsa/microchip/ksz_priv.h
@@ -22,6 +22,27 @@ struct vlan_table {
 	u32 table[3];
 };
 
+struct ksz_port_mib {
+	u8 cnt_ptr;
+	u64 *counters;
+};
+
+struct ksz_port {
+	u16 member;
+	u16 vid_member;
+	int stp_state;
+	struct phy_device phydev;
+
+	u32 on:1;			/* port is not disabled by hardware */
+	u32 phy:1;			/* port has a PHY */
+	u32 fiber:1;			/* port is fiber */
+	u32 sgmii:1;			/* port is SGMII */
+	u32 force:1;
+	u32 link_just_down:1;		/* link just goes down */
+
+	struct ksz_port_mib mib;
+};
+
 struct ksz_device {
 	struct dsa_switch *ds;
 	struct ksz_platform_data *pdata;
@@ -32,6 +53,7 @@ struct ksz_device {
 	struct mutex alu_mutex;		/* ALU access */
 	struct mutex vlan_mutex;	/* vlan access */
 	const struct ksz_io_ops *ops;
+	const struct ksz_dev_ops *dev_ops;
 
 	struct device *dev;
 
@@ -44,11 +66,37 @@ struct ksz_device {
 	int num_statics;
 	int cpu_port;			/* port connected to CPU */
 	int cpu_ports;			/* port bitmap can be cpu port */
+	int phy_port_cnt;
 	int port_cnt;
+	int reg_mib_cnt;
+	int mib_cnt;
+	int mib_port_cnt;
+	int last_port;			/* ports after that not used */
+	phy_interface_t interface;
+	u32 regs_size;
 
 	struct vlan_table *vlan_cache;
 
 	u64 mib_value[TOTAL_SWITCH_COUNTER_NUM];
+
+	u8 *txbuf;
+
+	struct ksz_port *ports;
+	struct timer_list mib_read_timer;
+	struct work_struct mib_read;
+	unsigned long mib_read_interval;
+	u16 br_member;
+	u16 member;
+	u16 live_ports;
+	u16 on_ports;			/* ports enabled by DSA */
+	u16 rx_ports;
+	u16 tx_ports;
+	u16 mirror_rx;
+	u16 mirror_tx;
+	u32 features;			/* chip specific features */
+	u32 overrides;			/* chip functions set by user */
+	u16 host_mask;
+	u16 port_mask;
 };
 
 struct ksz_io_ops {
@@ -60,140 +108,60 @@ struct ksz_io_ops {
 	int (*write16)(struct ksz_device *dev, u32 reg, u16 value);
 	int (*write24)(struct ksz_device *dev, u32 reg, u32 value);
 	int (*write32)(struct ksz_device *dev, u32 reg, u32 value);
-	int (*phy_read16)(struct ksz_device *dev, int addr, int reg,
-			  u16 *value);
-	int (*phy_write16)(struct ksz_device *dev, int addr, int reg,
-			   u16 value);
+	int (*get)(struct ksz_device *dev, u32 reg, void *data, size_t len);
+	int (*set)(struct ksz_device *dev, u32 reg, void *data, size_t len);
+};
+
+struct alu_struct {
+	/* entry 1 */
+	u8	is_static:1;
+	u8	is_src_filter:1;
+	u8	is_dst_filter:1;
+	u8	prio_age:3;
+	u32	_reserv_0_1:23;
+	u8	mstp:3;
+	/* entry 2 */
+	u8	is_override:1;
+	u8	is_use_fid:1;
+	u32	_reserv_1_1:23;
+	u8	port_forward:7;
+	/* entry 3 & 4*/
+	u32	_reserv_2_1:9;
+	u8	fid:7;
+	u8	mac[ETH_ALEN];
+};
+
+struct ksz_dev_ops {
+	u32 (*get_port_addr)(int port, int offset);
+	void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member);
+	void (*flush_dyn_mac_table)(struct ksz_device *dev, int port);
+	void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port);
+	void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val);
+	void (*w_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 val);
+	int (*r_dyn_mac_table)(struct ksz_device *dev, u16 addr, u8 *mac_addr,
+			       u8 *fid, u8 *src_port, u8 *timestamp,
+			       u16 *entries);
+	int (*r_sta_mac_table)(struct ksz_device *dev, u16 addr,
+			       struct alu_struct *alu);
+	void (*w_sta_mac_table)(struct ksz_device *dev, u16 addr,
+				struct alu_struct *alu);
+	void (*r_mib_cnt)(struct ksz_device *dev, int port, u16 addr,
+			  u64 *cnt);
+	void (*r_mib_pkt)(struct ksz_device *dev, int port, u16 addr,
+			  u64 *dropped, u64 *cnt);
+	void (*port_init_cnt)(struct ksz_device *dev, int port);
+	int (*shutdown)(struct ksz_device *dev);
+	int (*detect)(struct ksz_device *dev);
+	int (*init)(struct ksz_device *dev);
+	void (*exit)(struct ksz_device *dev);
 };
 
 struct ksz_device *ksz_switch_alloc(struct device *base,
 				    const struct ksz_io_ops *ops, void *priv);
-int ksz_switch_detect(struct ksz_device *dev);
-int ksz_switch_register(struct ksz_device *dev);
+int ksz_switch_register(struct ksz_device *dev,
+			const struct ksz_dev_ops *ops);
 void ksz_switch_remove(struct ksz_device *dev);
 
-static inline int ksz_read8(struct ksz_device *dev, u32 reg, u8 *val)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->read8(dev, reg, val);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int ksz_read16(struct ksz_device *dev, u32 reg, u16 *val)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->read16(dev, reg, val);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int ksz_read24(struct ksz_device *dev, u32 reg, u32 *val)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->read24(dev, reg, val);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int ksz_read32(struct ksz_device *dev, u32 reg, u32 *val)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->read32(dev, reg, val);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int ksz_write8(struct ksz_device *dev, u32 reg, u8 value)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->write8(dev, reg, value);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int ksz_write16(struct ksz_device *dev, u32 reg, u16 value)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->write16(dev, reg, value);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int ksz_write24(struct ksz_device *dev, u32 reg, u32 value)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->write24(dev, reg, value);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int ksz_write32(struct ksz_device *dev, u32 reg, u32 value)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->write32(dev, reg, value);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline void ksz_pread8(struct ksz_device *dev, int port, int offset,
-			      u8 *data)
-{
-	ksz_read8(dev, PORT_CTRL_ADDR(port, offset), data);
-}
-
-static inline void ksz_pread16(struct ksz_device *dev, int port, int offset,
-			       u16 *data)
-{
-	ksz_read16(dev, PORT_CTRL_ADDR(port, offset), data);
-}
-
-static inline void ksz_pread32(struct ksz_device *dev, int port, int offset,
-			       u32 *data)
-{
-	ksz_read32(dev, PORT_CTRL_ADDR(port, offset), data);
-}
-
-static inline void ksz_pwrite8(struct ksz_device *dev, int port, int offset,
-			       u8 data)
-{
-	ksz_write8(dev, PORT_CTRL_ADDR(port, offset), data);
-}
-
-static inline void ksz_pwrite16(struct ksz_device *dev, int port, int offset,
-				u16 data)
-{
-	ksz_write16(dev, PORT_CTRL_ADDR(port, offset), data);
-}
-
-static inline void ksz_pwrite32(struct ksz_device *dev, int port, int offset,
-				u32 data)
-{
-	ksz_write32(dev, PORT_CTRL_ADDR(port, offset), data);
-}
+int ksz9477_switch_register(struct ksz_device *dev);
 
 #endif
diff --git a/drivers/net/dsa/microchip/ksz_spi.h b/drivers/net/dsa/microchip/ksz_spi.h
new file mode 100644
index 000000000000..427811bd60b3
--- /dev/null
+++ b/drivers/net/dsa/microchip/ksz_spi.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Microchip KSZ series SPI access common header
+ *
+ * Copyright (C) 2017-2018 Microchip Technology Inc.
+ *	Tristram Ha <Tristram.Ha@microchip.com>
+ */
+
+#ifndef __KSZ_SPI_H
+#define __KSZ_SPI_H
+
+/* Chip dependent SPI access */
+static int ksz_spi_read(struct ksz_device *dev, u32 reg, u8 *data,
+			unsigned int len);
+static int ksz_spi_write(struct ksz_device *dev, u32 reg, void *data,
+			 unsigned int len);
+
+static int ksz_spi_read8(struct ksz_device *dev, u32 reg, u8 *val)
+{
+	return ksz_spi_read(dev, reg, val, 1);
+}
+
+static int ksz_spi_read16(struct ksz_device *dev, u32 reg, u16 *val)
+{
+	int ret = ksz_spi_read(dev, reg, (u8 *)val, 2);
+
+	if (!ret)
+		*val = be16_to_cpu(*val);
+
+	return ret;
+}
+
+static int ksz_spi_read32(struct ksz_device *dev, u32 reg, u32 *val)
+{
+	int ret = ksz_spi_read(dev, reg, (u8 *)val, 4);
+
+	if (!ret)
+		*val = be32_to_cpu(*val);
+
+	return ret;
+}
+
+static int ksz_spi_write8(struct ksz_device *dev, u32 reg, u8 value)
+{
+	return ksz_spi_write(dev, reg, &value, 1);
+}
+
+static int ksz_spi_write16(struct ksz_device *dev, u32 reg, u16 value)
+{
+	value = cpu_to_be16(value);
+	return ksz_spi_write(dev, reg, &value, 2);
+}
+
+static int ksz_spi_write32(struct ksz_device *dev, u32 reg, u32 value)
+{
+	value = cpu_to_be32(value);
+	return ksz_spi_write(dev, reg, &value, 4);
+}
+
+static int ksz_spi_get(struct ksz_device *dev, u32 reg, void *data, size_t len)
+{
+	return ksz_spi_read(dev, reg, data, len);
+}
+
+static int ksz_spi_set(struct ksz_device *dev, u32 reg, void *data, size_t len)
+{
+	return ksz_spi_write(dev, reg, data, len);
+}
+
+#endif
-- 
cgit v1.2.3


From 84bd1908192ffa5231ca6709c8cd87efaf57226c Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Tue, 20 Nov 2018 15:55:10 -0800
Subject: net: dsa: microchip: rename ksz_9477_reg.h to ksz9477_reg.h

Rename ksz_9477_reg.h to ksz9477_reg.h for consistency as the product
name is always KSZ####.

Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Reviewed-by: Woojung Huh <Woojung.Huh@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz9477.c      |    2 +-
 drivers/net/dsa/microchip/ksz9477_reg.h  | 1665 ++++++++++++++++++++++++++++++
 drivers/net/dsa/microchip/ksz_9477_reg.h | 1665 ------------------------------
 drivers/net/dsa/microchip/ksz_priv.h     |    2 +-
 4 files changed, 1667 insertions(+), 1667 deletions(-)
 create mode 100644 drivers/net/dsa/microchip/ksz9477_reg.h
 delete mode 100644 drivers/net/dsa/microchip/ksz_9477_reg.h

diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 80df6c03b340..0684657fbf9a 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -19,7 +19,7 @@
 
 #include "ksz_priv.h"
 #include "ksz_common.h"
-#include "ksz_9477_reg.h"
+#include "ksz9477_reg.h"
 
 static const struct {
 	int index;
diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h
new file mode 100644
index 000000000000..2938e892b631
--- /dev/null
+++ b/drivers/net/dsa/microchip/ksz9477_reg.h
@@ -0,0 +1,1665 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Microchip KSZ9477 register definitions
+ *
+ * Copyright (C) 2017-2018 Microchip Technology Inc.
+ */
+
+#ifndef __KSZ9477_REGS_H
+#define __KSZ9477_REGS_H
+
+#define KS_PRIO_M			0x7
+#define KS_PRIO_S			4
+
+/* 0 - Operation */
+#define REG_CHIP_ID0__1			0x0000
+
+#define REG_CHIP_ID1__1			0x0001
+
+#define FAMILY_ID			0x95
+#define FAMILY_ID_94			0x94
+#define FAMILY_ID_95			0x95
+#define FAMILY_ID_85			0x85
+#define FAMILY_ID_98			0x98
+#define FAMILY_ID_88			0x88
+
+#define REG_CHIP_ID2__1			0x0002
+
+#define CHIP_ID_63			0x63
+#define CHIP_ID_66			0x66
+#define CHIP_ID_67			0x67
+#define CHIP_ID_77			0x77
+#define CHIP_ID_93			0x93
+#define CHIP_ID_96			0x96
+#define CHIP_ID_97			0x97
+
+#define REG_CHIP_ID3__1			0x0003
+
+#define SWITCH_REVISION_M		0x0F
+#define SWITCH_REVISION_S		4
+#define SWITCH_RESET			0x01
+
+#define REG_SW_PME_CTRL			0x0006
+
+#define PME_ENABLE			BIT(1)
+#define PME_POLARITY			BIT(0)
+
+#define REG_GLOBAL_OPTIONS		0x000F
+
+#define SW_GIGABIT_ABLE			BIT(6)
+#define SW_REDUNDANCY_ABLE		BIT(5)
+#define SW_AVB_ABLE			BIT(4)
+#define SW_9567_RL_5_2			0xC
+#define SW_9477_SL_5_2			0xD
+
+#define SW_9896_GL_5_1			0xB
+#define SW_9896_RL_5_1			0x8
+#define SW_9896_SL_5_1			0x9
+
+#define SW_9895_GL_4_1			0x7
+#define SW_9895_RL_4_1			0x4
+#define SW_9895_SL_4_1			0x5
+
+#define SW_9896_RL_4_2			0x6
+
+#define SW_9893_RL_2_1			0x0
+#define SW_9893_SL_2_1			0x1
+#define SW_9893_GL_2_1			0x3
+
+#define SW_QW_ABLE			BIT(5)
+#define SW_9893_RN_2_1			0xC
+
+#define REG_SW_INT_STATUS__4		0x0010
+#define REG_SW_INT_MASK__4		0x0014
+
+#define LUE_INT				BIT(31)
+#define TRIG_TS_INT			BIT(30)
+#define APB_TIMEOUT_INT			BIT(29)
+
+#define SWITCH_INT_MASK			(TRIG_TS_INT | APB_TIMEOUT_INT)
+
+#define REG_SW_PORT_INT_STATUS__4	0x0018
+#define REG_SW_PORT_INT_MASK__4		0x001C
+#define REG_SW_PHY_INT_STATUS		0x0020
+#define REG_SW_PHY_INT_ENABLE		0x0024
+
+/* 1 - Global */
+#define REG_SW_GLOBAL_SERIAL_CTRL_0	0x0100
+#define SW_SPARE_REG_2			BIT(7)
+#define SW_SPARE_REG_1			BIT(6)
+#define SW_SPARE_REG_0			BIT(5)
+#define SW_BIG_ENDIAN			BIT(4)
+#define SPI_AUTO_EDGE_DETECTION		BIT(1)
+#define SPI_CLOCK_OUT_RISING_EDGE	BIT(0)
+
+#define REG_SW_GLOBAL_OUTPUT_CTRL__1	0x0103
+#define SW_ENABLE_REFCLKO		BIT(1)
+#define SW_REFCLKO_IS_125MHZ		BIT(0)
+
+#define REG_SW_IBA__4			0x0104
+
+#define SW_IBA_ENABLE			BIT(31)
+#define SW_IBA_DA_MATCH			BIT(30)
+#define SW_IBA_INIT			BIT(29)
+#define SW_IBA_QID_M			0xF
+#define SW_IBA_QID_S			22
+#define SW_IBA_PORT_M			0x2F
+#define SW_IBA_PORT_S			16
+#define SW_IBA_FRAME_TPID_M		0xFFFF
+
+#define REG_SW_APB_TIMEOUT_ADDR__4	0x0108
+
+#define APB_TIMEOUT_ACKNOWLEDGE		BIT(31)
+
+#define REG_SW_IBA_SYNC__1		0x010C
+
+#define REG_SW_IO_STRENGTH__1		0x010D
+#define SW_DRIVE_STRENGTH_M		0x7
+#define SW_DRIVE_STRENGTH_2MA		0
+#define SW_DRIVE_STRENGTH_4MA		1
+#define SW_DRIVE_STRENGTH_8MA		2
+#define SW_DRIVE_STRENGTH_12MA		3
+#define SW_DRIVE_STRENGTH_16MA		4
+#define SW_DRIVE_STRENGTH_20MA		5
+#define SW_DRIVE_STRENGTH_24MA		6
+#define SW_DRIVE_STRENGTH_28MA		7
+#define SW_HI_SPEED_DRIVE_STRENGTH_S	4
+#define SW_LO_SPEED_DRIVE_STRENGTH_S	0
+
+#define REG_SW_IBA_STATUS__4		0x0110
+
+#define SW_IBA_REQ			BIT(31)
+#define SW_IBA_RESP			BIT(30)
+#define SW_IBA_DA_MISMATCH		BIT(14)
+#define SW_IBA_FMT_MISMATCH		BIT(13)
+#define SW_IBA_CODE_ERROR		BIT(12)
+#define SW_IBA_CMD_ERROR		BIT(11)
+#define SW_IBA_CMD_LOC_M		(BIT(6) - 1)
+
+#define REG_SW_IBA_STATES__4		0x0114
+
+#define SW_IBA_BUF_STATE_S		30
+#define SW_IBA_CMD_STATE_S		28
+#define SW_IBA_RESP_STATE_S		26
+#define SW_IBA_STATE_M			0x3
+#define SW_IBA_PACKET_SIZE_M		0x7F
+#define SW_IBA_PACKET_SIZE_S		16
+#define SW_IBA_FMT_ID_M			0xFFFF
+
+#define REG_SW_IBA_RESULT__4		0x0118
+
+#define SW_IBA_SIZE_S			24
+
+#define SW_IBA_RETRY_CNT_M		(BIT(5) - 1)
+
+/* 2 - PHY */
+#define REG_SW_POWER_MANAGEMENT_CTRL	0x0201
+
+#define SW_PLL_POWER_DOWN		BIT(5)
+#define SW_POWER_DOWN_MODE		0x3
+#define SW_ENERGY_DETECTION		1
+#define SW_SOFT_POWER_DOWN		2
+#define SW_POWER_SAVING			3
+
+/* 3 - Operation Control */
+#define REG_SW_OPERATION		0x0300
+
+#define SW_DOUBLE_TAG			BIT(7)
+#define SW_RESET			BIT(1)
+#define SW_START			BIT(0)
+
+#define REG_SW_MAC_ADDR_0		0x0302
+#define REG_SW_MAC_ADDR_1		0x0303
+#define REG_SW_MAC_ADDR_2		0x0304
+#define REG_SW_MAC_ADDR_3		0x0305
+#define REG_SW_MAC_ADDR_4		0x0306
+#define REG_SW_MAC_ADDR_5		0x0307
+
+#define REG_SW_MTU__2			0x0308
+
+#define REG_SW_ISP_TPID__2		0x030A
+
+#define REG_SW_HSR_TPID__2		0x030C
+
+#define REG_AVB_STRATEGY__2		0x030E
+
+#define SW_SHAPING_CREDIT_ACCT		BIT(1)
+#define SW_POLICING_CREDIT_ACCT		BIT(0)
+
+#define REG_SW_LUE_CTRL_0		0x0310
+
+#define SW_VLAN_ENABLE			BIT(7)
+#define SW_DROP_INVALID_VID		BIT(6)
+#define SW_AGE_CNT_M			0x7
+#define SW_AGE_CNT_S			3
+#define SW_RESV_MCAST_ENABLE		BIT(2)
+#define SW_HASH_OPTION_M		0x03
+#define SW_HASH_OPTION_CRC		1
+#define SW_HASH_OPTION_XOR		2
+#define SW_HASH_OPTION_DIRECT		3
+
+#define REG_SW_LUE_CTRL_1		0x0311
+
+#define UNICAST_LEARN_DISABLE		BIT(7)
+#define SW_SRC_ADDR_FILTER		BIT(6)
+#define SW_FLUSH_STP_TABLE		BIT(5)
+#define SW_FLUSH_MSTP_TABLE		BIT(4)
+#define SW_FWD_MCAST_SRC_ADDR		BIT(3)
+#define SW_AGING_ENABLE			BIT(2)
+#define SW_FAST_AGING			BIT(1)
+#define SW_LINK_AUTO_AGING		BIT(0)
+
+#define REG_SW_LUE_CTRL_2		0x0312
+
+#define SW_TRAP_DOUBLE_TAG		BIT(6)
+#define SW_EGRESS_VLAN_FILTER_DYN	BIT(5)
+#define SW_EGRESS_VLAN_FILTER_STA	BIT(4)
+#define SW_FLUSH_OPTION_M		0x3
+#define SW_FLUSH_OPTION_S		2
+#define SW_FLUSH_OPTION_DYN_MAC		1
+#define SW_FLUSH_OPTION_STA_MAC		2
+#define SW_FLUSH_OPTION_BOTH		3
+#define SW_PRIO_M			0x3
+#define SW_PRIO_DA			0
+#define SW_PRIO_SA			1
+#define SW_PRIO_HIGHEST_DA_SA		2
+#define SW_PRIO_LOWEST_DA_SA		3
+
+#define REG_SW_LUE_CTRL_3		0x0313
+
+#define REG_SW_LUE_INT_STATUS		0x0314
+#define REG_SW_LUE_INT_ENABLE		0x0315
+
+#define LEARN_FAIL_INT			BIT(2)
+#define ALMOST_FULL_INT			BIT(1)
+#define WRITE_FAIL_INT			BIT(0)
+
+#define REG_SW_LUE_INDEX_0__2		0x0316
+
+#define ENTRY_INDEX_M			0x0FFF
+
+#define REG_SW_LUE_INDEX_1__2		0x0318
+
+#define FAIL_INDEX_M			0x03FF
+
+#define REG_SW_LUE_INDEX_2__2		0x031A
+
+#define REG_SW_LUE_UNK_UCAST_CTRL__4	0x0320
+
+#define SW_UNK_UCAST_ENABLE		BIT(31)
+
+#define REG_SW_LUE_UNK_MCAST_CTRL__4	0x0324
+
+#define SW_UNK_MCAST_ENABLE		BIT(31)
+
+#define REG_SW_LUE_UNK_VID_CTRL__4	0x0328
+
+#define SW_UNK_VID_ENABLE		BIT(31)
+
+#define REG_SW_MAC_CTRL_0		0x0330
+
+#define SW_NEW_BACKOFF			BIT(7)
+#define SW_CHECK_LENGTH			BIT(3)
+#define SW_PAUSE_UNH_MODE		BIT(1)
+#define SW_AGGR_BACKOFF			BIT(0)
+
+#define REG_SW_MAC_CTRL_1		0x0331
+
+#define MULTICAST_STORM_DISABLE		BIT(6)
+#define SW_BACK_PRESSURE		BIT(5)
+#define FAIR_FLOW_CTRL			BIT(4)
+#define NO_EXC_COLLISION_DROP		BIT(3)
+#define SW_JUMBO_PACKET			BIT(2)
+#define SW_LEGAL_PACKET_DISABLE		BIT(1)
+#define SW_PASS_SHORT_FRAME		BIT(0)
+
+#define REG_SW_MAC_CTRL_2		0x0332
+
+#define SW_REPLACE_VID			BIT(3)
+#define BROADCAST_STORM_RATE_HI		0x07
+
+#define REG_SW_MAC_CTRL_3		0x0333
+
+#define BROADCAST_STORM_RATE_LO		0xFF
+#define BROADCAST_STORM_RATE		0x07FF
+
+#define REG_SW_MAC_CTRL_4		0x0334
+
+#define SW_PASS_PAUSE			BIT(3)
+
+#define REG_SW_MAC_CTRL_5		0x0335
+
+#define SW_OUT_RATE_LIMIT_QUEUE_BASED	BIT(3)
+
+#define REG_SW_MAC_CTRL_6		0x0336
+
+#define SW_MIB_COUNTER_FLUSH		BIT(7)
+#define SW_MIB_COUNTER_FREEZE		BIT(6)
+
+#define REG_SW_MAC_802_1P_MAP_0		0x0338
+#define REG_SW_MAC_802_1P_MAP_1		0x0339
+#define REG_SW_MAC_802_1P_MAP_2		0x033A
+#define REG_SW_MAC_802_1P_MAP_3		0x033B
+
+#define SW_802_1P_MAP_M			KS_PRIO_M
+#define SW_802_1P_MAP_S			KS_PRIO_S
+
+#define REG_SW_MAC_ISP_CTRL		0x033C
+
+#define REG_SW_MAC_TOS_CTRL		0x033E
+
+#define SW_TOS_DSCP_REMARK		BIT(1)
+#define SW_TOS_DSCP_REMAP		BIT(0)
+
+#define REG_SW_MAC_TOS_PRIO_0		0x0340
+#define REG_SW_MAC_TOS_PRIO_1		0x0341
+#define REG_SW_MAC_TOS_PRIO_2		0x0342
+#define REG_SW_MAC_TOS_PRIO_3		0x0343
+#define REG_SW_MAC_TOS_PRIO_4		0x0344
+#define REG_SW_MAC_TOS_PRIO_5		0x0345
+#define REG_SW_MAC_TOS_PRIO_6		0x0346
+#define REG_SW_MAC_TOS_PRIO_7		0x0347
+#define REG_SW_MAC_TOS_PRIO_8		0x0348
+#define REG_SW_MAC_TOS_PRIO_9		0x0349
+#define REG_SW_MAC_TOS_PRIO_10		0x034A
+#define REG_SW_MAC_TOS_PRIO_11		0x034B
+#define REG_SW_MAC_TOS_PRIO_12		0x034C
+#define REG_SW_MAC_TOS_PRIO_13		0x034D
+#define REG_SW_MAC_TOS_PRIO_14		0x034E
+#define REG_SW_MAC_TOS_PRIO_15		0x034F
+#define REG_SW_MAC_TOS_PRIO_16		0x0350
+#define REG_SW_MAC_TOS_PRIO_17		0x0351
+#define REG_SW_MAC_TOS_PRIO_18		0x0352
+#define REG_SW_MAC_TOS_PRIO_19		0x0353
+#define REG_SW_MAC_TOS_PRIO_20		0x0354
+#define REG_SW_MAC_TOS_PRIO_21		0x0355
+#define REG_SW_MAC_TOS_PRIO_22		0x0356
+#define REG_SW_MAC_TOS_PRIO_23		0x0357
+#define REG_SW_MAC_TOS_PRIO_24		0x0358
+#define REG_SW_MAC_TOS_PRIO_25		0x0359
+#define REG_SW_MAC_TOS_PRIO_26		0x035A
+#define REG_SW_MAC_TOS_PRIO_27		0x035B
+#define REG_SW_MAC_TOS_PRIO_28		0x035C
+#define REG_SW_MAC_TOS_PRIO_29		0x035D
+#define REG_SW_MAC_TOS_PRIO_30		0x035E
+#define REG_SW_MAC_TOS_PRIO_31		0x035F
+
+#define REG_SW_MRI_CTRL_0		0x0370
+
+#define SW_IGMP_SNOOP			BIT(6)
+#define SW_IPV6_MLD_OPTION		BIT(3)
+#define SW_IPV6_MLD_SNOOP		BIT(2)
+#define SW_MIRROR_RX_TX			BIT(0)
+
+#define REG_SW_CLASS_D_IP_CTRL__4	0x0374
+
+#define SW_CLASS_D_IP_ENABLE		BIT(31)
+
+#define REG_SW_MRI_CTRL_8		0x0378
+
+#define SW_NO_COLOR_S			6
+#define SW_RED_COLOR_S			4
+#define SW_YELLOW_COLOR_S		2
+#define SW_GREEN_COLOR_S		0
+#define SW_COLOR_M			0x3
+
+#define REG_SW_QM_CTRL__4		0x0390
+
+#define PRIO_SCHEME_SELECT_M		KS_PRIO_M
+#define PRIO_SCHEME_SELECT_S		6
+#define PRIO_MAP_3_HI			0
+#define PRIO_MAP_2_HI			2
+#define PRIO_MAP_0_LO			3
+#define UNICAST_VLAN_BOUNDARY		BIT(1)
+
+#define REG_SW_EEE_QM_CTRL__2		0x03C0
+
+#define REG_SW_EEE_TXQ_WAIT_TIME__2	0x03C2
+
+/* 4 - */
+#define REG_SW_VLAN_ENTRY__4		0x0400
+
+#define VLAN_VALID			BIT(31)
+#define VLAN_FORWARD_OPTION		BIT(27)
+#define VLAN_PRIO_M			KS_PRIO_M
+#define VLAN_PRIO_S			24
+#define VLAN_MSTP_M			0x7
+#define VLAN_MSTP_S			12
+#define VLAN_FID_M			0x7F
+
+#define REG_SW_VLAN_ENTRY_UNTAG__4	0x0404
+#define REG_SW_VLAN_ENTRY_PORTS__4	0x0408
+
+#define REG_SW_VLAN_ENTRY_INDEX__2	0x040C
+
+#define VLAN_INDEX_M			0x0FFF
+
+#define REG_SW_VLAN_CTRL		0x040E
+
+#define VLAN_START			BIT(7)
+#define VLAN_ACTION			0x3
+#define VLAN_WRITE			1
+#define VLAN_READ			2
+#define VLAN_CLEAR			3
+
+#define REG_SW_ALU_INDEX_0		0x0410
+
+#define ALU_FID_INDEX_S			16
+#define ALU_MAC_ADDR_HI			0xFFFF
+
+#define REG_SW_ALU_INDEX_1		0x0414
+
+#define ALU_DIRECT_INDEX_M		(BIT(12) - 1)
+
+#define REG_SW_ALU_CTRL__4		0x0418
+
+#define ALU_VALID_CNT_M			(BIT(14) - 1)
+#define ALU_VALID_CNT_S			16
+#define ALU_START			BIT(7)
+#define ALU_VALID			BIT(6)
+#define ALU_DIRECT			BIT(2)
+#define ALU_ACTION			0x3
+#define ALU_WRITE			1
+#define ALU_READ			2
+#define ALU_SEARCH			3
+
+#define REG_SW_ALU_STAT_CTRL__4		0x041C
+
+#define ALU_STAT_INDEX_M		(BIT(4) - 1)
+#define ALU_STAT_INDEX_S		16
+#define ALU_RESV_MCAST_INDEX_M		(BIT(6) - 1)
+#define ALU_STAT_START			BIT(7)
+#define ALU_RESV_MCAST_ADDR		BIT(1)
+#define ALU_STAT_READ			BIT(0)
+
+#define REG_SW_ALU_VAL_A		0x0420
+
+#define ALU_V_STATIC_VALID		BIT(31)
+#define ALU_V_SRC_FILTER		BIT(30)
+#define ALU_V_DST_FILTER		BIT(29)
+#define ALU_V_PRIO_AGE_CNT_M		(BIT(3) - 1)
+#define ALU_V_PRIO_AGE_CNT_S		26
+#define ALU_V_MSTP_M			0x7
+
+#define REG_SW_ALU_VAL_B		0x0424
+
+#define ALU_V_OVERRIDE			BIT(31)
+#define ALU_V_USE_FID			BIT(30)
+#define ALU_V_PORT_MAP			(BIT(24) - 1)
+
+#define REG_SW_ALU_VAL_C		0x0428
+
+#define ALU_V_FID_M			(BIT(16) - 1)
+#define ALU_V_FID_S			16
+#define ALU_V_MAC_ADDR_HI		0xFFFF
+
+#define REG_SW_ALU_VAL_D		0x042C
+
+#define REG_HSR_ALU_INDEX_0		0x0440
+
+#define REG_HSR_ALU_INDEX_1		0x0444
+
+#define HSR_DST_MAC_INDEX_LO_S		16
+#define HSR_SRC_MAC_INDEX_HI		0xFFFF
+
+#define REG_HSR_ALU_INDEX_2		0x0448
+
+#define HSR_INDEX_MAX			BIT(9)
+#define HSR_DIRECT_INDEX_M		(HSR_INDEX_MAX - 1)
+
+#define REG_HSR_ALU_INDEX_3		0x044C
+
+#define HSR_PATH_INDEX_M		(BIT(4) - 1)
+
+#define REG_HSR_ALU_CTRL__4		0x0450
+
+#define HSR_VALID_CNT_M			(BIT(14) - 1)
+#define HSR_VALID_CNT_S			16
+#define HSR_START			BIT(7)
+#define HSR_VALID			BIT(6)
+#define HSR_SEARCH_END			BIT(5)
+#define HSR_DIRECT			BIT(2)
+#define HSR_ACTION			0x3
+#define HSR_WRITE			1
+#define HSR_READ			2
+#define HSR_SEARCH			3
+
+#define REG_HSR_ALU_VAL_A		0x0454
+
+#define HSR_V_STATIC_VALID		BIT(31)
+#define HSR_V_AGE_CNT_M			(BIT(3) - 1)
+#define HSR_V_AGE_CNT_S			26
+#define HSR_V_PATH_ID_M			(BIT(4) - 1)
+
+#define REG_HSR_ALU_VAL_B		0x0458
+
+#define REG_HSR_ALU_VAL_C		0x045C
+
+#define HSR_V_DST_MAC_ADDR_LO_S		16
+#define HSR_V_SRC_MAC_ADDR_HI		0xFFFF
+
+#define REG_HSR_ALU_VAL_D		0x0460
+
+#define REG_HSR_ALU_VAL_E		0x0464
+
+#define HSR_V_START_SEQ_1_S		16
+#define HSR_V_START_SEQ_2_S		0
+
+#define REG_HSR_ALU_VAL_F		0x0468
+
+#define HSR_V_EXP_SEQ_1_S		16
+#define HSR_V_EXP_SEQ_2_S		0
+
+#define REG_HSR_ALU_VAL_G		0x046C
+
+#define HSR_V_SEQ_CNT_1_S		16
+#define HSR_V_SEQ_CNT_2_S		0
+
+#define HSR_V_SEQ_M			(BIT(16) - 1)
+
+/* 5 - PTP Clock */
+#define REG_PTP_CLK_CTRL		0x0500
+
+#define PTP_STEP_ADJ			BIT(6)
+#define PTP_STEP_DIR			BIT(5)
+#define PTP_READ_TIME			BIT(4)
+#define PTP_LOAD_TIME			BIT(3)
+#define PTP_CLK_ADJ_ENABLE		BIT(2)
+#define PTP_CLK_ENABLE			BIT(1)
+#define PTP_CLK_RESET			BIT(0)
+
+#define REG_PTP_RTC_SUB_NANOSEC__2	0x0502
+
+#define PTP_RTC_SUB_NANOSEC_M		0x0007
+
+#define REG_PTP_RTC_NANOSEC		0x0504
+#define REG_PTP_RTC_NANOSEC_H		0x0504
+#define REG_PTP_RTC_NANOSEC_L		0x0506
+
+#define REG_PTP_RTC_SEC			0x0508
+#define REG_PTP_RTC_SEC_H		0x0508
+#define REG_PTP_RTC_SEC_L		0x050A
+
+#define REG_PTP_SUBNANOSEC_RATE		0x050C
+#define REG_PTP_SUBNANOSEC_RATE_H	0x050C
+
+#define PTP_RATE_DIR			BIT(31)
+#define PTP_TMP_RATE_ENABLE		BIT(30)
+
+#define REG_PTP_SUBNANOSEC_RATE_L	0x050E
+
+#define REG_PTP_RATE_DURATION		0x0510
+#define REG_PTP_RATE_DURATION_H		0x0510
+#define REG_PTP_RATE_DURATION_L		0x0512
+
+#define REG_PTP_MSG_CONF1		0x0514
+
+#define PTP_802_1AS			BIT(7)
+#define PTP_ENABLE			BIT(6)
+#define PTP_ETH_ENABLE			BIT(5)
+#define PTP_IPV4_UDP_ENABLE		BIT(4)
+#define PTP_IPV6_UDP_ENABLE		BIT(3)
+#define PTP_TC_P2P			BIT(2)
+#define PTP_MASTER			BIT(1)
+#define PTP_1STEP			BIT(0)
+
+#define REG_PTP_MSG_CONF2		0x0516
+
+#define PTP_UNICAST_ENABLE		BIT(12)
+#define PTP_ALTERNATE_MASTER		BIT(11)
+#define PTP_ALL_HIGH_PRIO		BIT(10)
+#define PTP_SYNC_CHECK			BIT(9)
+#define PTP_DELAY_CHECK			BIT(8)
+#define PTP_PDELAY_CHECK		BIT(7)
+#define PTP_DROP_SYNC_DELAY_REQ		BIT(5)
+#define PTP_DOMAIN_CHECK		BIT(4)
+#define PTP_UDP_CHECKSUM		BIT(2)
+
+#define REG_PTP_DOMAIN_VERSION		0x0518
+#define PTP_VERSION_M			0xFF00
+#define PTP_DOMAIN_M			0x00FF
+
+#define REG_PTP_UNIT_INDEX__4		0x0520
+
+#define PTP_UNIT_M			0xF
+
+#define PTP_GPIO_INDEX_S		16
+#define PTP_TSI_INDEX_S			8
+#define PTP_TOU_INDEX_S			0
+
+#define REG_PTP_TRIG_STATUS__4		0x0524
+
+#define TRIG_ERROR_S			16
+#define TRIG_DONE_S			0
+
+#define REG_PTP_INT_STATUS__4		0x0528
+
+#define TRIG_INT_S			16
+#define TS_INT_S			0
+
+#define TRIG_UNIT_M			0x7
+#define TS_UNIT_M			0x3
+
+#define REG_PTP_CTRL_STAT__4		0x052C
+
+#define GPIO_IN				BIT(7)
+#define GPIO_OUT			BIT(6)
+#define TS_INT_ENABLE			BIT(5)
+#define TRIG_ACTIVE			BIT(4)
+#define TRIG_ENABLE			BIT(3)
+#define TRIG_RESET			BIT(2)
+#define TS_ENABLE			BIT(1)
+#define TS_RESET			BIT(0)
+
+#define GPIO_CTRL_M			(GPIO_IN | GPIO_OUT)
+
+#define TRIG_CTRL_M			\
+	(TRIG_ACTIVE | TRIG_ENABLE | TRIG_RESET)
+
+#define TS_CTRL_M			\
+	(TS_INT_ENABLE | TS_ENABLE | TS_RESET)
+
+#define REG_TRIG_TARGET_NANOSEC		0x0530
+#define REG_TRIG_TARGET_SEC		0x0534
+
+#define REG_TRIG_CTRL__4		0x0538
+
+#define TRIG_CASCADE_ENABLE		BIT(31)
+#define TRIG_CASCADE_TAIL		BIT(30)
+#define TRIG_CASCADE_UPS_M		0xF
+#define TRIG_CASCADE_UPS_S		26
+#define TRIG_NOW			BIT(25)
+#define TRIG_NOTIFY			BIT(24)
+#define TRIG_EDGE			BIT(23)
+#define TRIG_PATTERN_S			20
+#define TRIG_PATTERN_M			0x7
+#define TRIG_NEG_EDGE			0
+#define TRIG_POS_EDGE			1
+#define TRIG_NEG_PULSE			2
+#define TRIG_POS_PULSE			3
+#define TRIG_NEG_PERIOD			4
+#define TRIG_POS_PERIOD			5
+#define TRIG_REG_OUTPUT			6
+#define TRIG_GPO_S			16
+#define TRIG_GPO_M			0xF
+#define TRIG_CASCADE_ITERATE_CNT_M	0xFFFF
+
+#define REG_TRIG_CYCLE_WIDTH		0x053C
+
+#define REG_TRIG_CYCLE_CNT		0x0540
+
+#define TRIG_CYCLE_CNT_M		0xFFFF
+#define TRIG_CYCLE_CNT_S		16
+#define TRIG_BIT_PATTERN_M		0xFFFF
+
+#define REG_TRIG_ITERATE_TIME		0x0544
+
+#define REG_TRIG_PULSE_WIDTH__4		0x0548
+
+#define TRIG_PULSE_WIDTH_M		0x00FFFFFF
+
+#define REG_TS_CTRL_STAT__4		0x0550
+
+#define TS_EVENT_DETECT_M		0xF
+#define TS_EVENT_DETECT_S		17
+#define TS_EVENT_OVERFLOW		BIT(16)
+#define TS_GPI_M			0xF
+#define TS_GPI_S			8
+#define TS_DETECT_RISE			BIT(7)
+#define TS_DETECT_FALL			BIT(6)
+#define TS_DETECT_S			6
+#define TS_CASCADE_TAIL			BIT(5)
+#define TS_CASCADE_UPS_M		0xF
+#define TS_CASCADE_UPS_S		1
+#define TS_CASCADE_ENABLE		BIT(0)
+
+#define DETECT_RISE			(TS_DETECT_RISE >> TS_DETECT_S)
+#define DETECT_FALL			(TS_DETECT_FALL >> TS_DETECT_S)
+
+#define REG_TS_EVENT_0_NANOSEC		0x0554
+#define REG_TS_EVENT_0_SEC		0x0558
+#define REG_TS_EVENT_0_SUB_NANOSEC	0x055C
+
+#define REG_TS_EVENT_1_NANOSEC		0x0560
+#define REG_TS_EVENT_1_SEC		0x0564
+#define REG_TS_EVENT_1_SUB_NANOSEC	0x0568
+
+#define REG_TS_EVENT_2_NANOSEC		0x056C
+#define REG_TS_EVENT_2_SEC		0x0570
+#define REG_TS_EVENT_2_SUB_NANOSEC	0x0574
+
+#define REG_TS_EVENT_3_NANOSEC		0x0578
+#define REG_TS_EVENT_3_SEC		0x057C
+#define REG_TS_EVENT_3_SUB_NANOSEC	0x0580
+
+#define REG_TS_EVENT_4_NANOSEC		0x0584
+#define REG_TS_EVENT_4_SEC		0x0588
+#define REG_TS_EVENT_4_SUB_NANOSEC	0x058C
+
+#define REG_TS_EVENT_5_NANOSEC		0x0590
+#define REG_TS_EVENT_5_SEC		0x0594
+#define REG_TS_EVENT_5_SUB_NANOSEC	0x0598
+
+#define REG_TS_EVENT_6_NANOSEC		0x059C
+#define REG_TS_EVENT_6_SEC		0x05A0
+#define REG_TS_EVENT_6_SUB_NANOSEC	0x05A4
+
+#define REG_TS_EVENT_7_NANOSEC		0x05A8
+#define REG_TS_EVENT_7_SEC		0x05AC
+#define REG_TS_EVENT_7_SUB_NANOSEC	0x05B0
+
+#define TS_EVENT_EDGE_M			0x1
+#define TS_EVENT_EDGE_S			30
+#define TS_EVENT_NANOSEC_M		(BIT(30) - 1)
+
+#define TS_EVENT_SUB_NANOSEC_M		0x7
+
+#define TS_EVENT_SAMPLE			\
+	(REG_TS_EVENT_1_NANOSEC - REG_TS_EVENT_0_NANOSEC)
+
+#define PORT_CTRL_ADDR(port, addr)	((addr) | (((port) + 1) << 12))
+
+#define REG_GLOBAL_RR_INDEX__1		0x0600
+
+/* DLR */
+#define REG_DLR_SRC_PORT__4		0x0604
+
+#define DLR_SRC_PORT_UNICAST		BIT(31)
+#define DLR_SRC_PORT_M			0x3
+#define DLR_SRC_PORT_BOTH		0
+#define DLR_SRC_PORT_EACH		1
+
+#define REG_DLR_IP_ADDR__4		0x0608
+
+#define REG_DLR_CTRL__1			0x0610
+
+#define DLR_RESET_SEQ_ID		BIT(3)
+#define DLR_BACKUP_AUTO_ON		BIT(2)
+#define DLR_BEACON_TX_ENABLE		BIT(1)
+#define DLR_ASSIST_ENABLE		BIT(0)
+
+#define REG_DLR_STATE__1		0x0611
+
+#define DLR_NODE_STATE_M		0x3
+#define DLR_NODE_STATE_S		1
+#define DLR_NODE_STATE_IDLE		0
+#define DLR_NODE_STATE_FAULT		1
+#define DLR_NODE_STATE_NORMAL		2
+#define DLR_RING_STATE_FAULT		0
+#define DLR_RING_STATE_NORMAL		1
+
+#define REG_DLR_PRECEDENCE__1		0x0612
+
+#define REG_DLR_BEACON_INTERVAL__4	0x0614
+
+#define REG_DLR_BEACON_TIMEOUT__4	0x0618
+
+#define REG_DLR_TIMEOUT_WINDOW__4	0x061C
+
+#define DLR_TIMEOUT_WINDOW_M		(BIT(22) - 1)
+
+#define REG_DLR_VLAN_ID__2		0x0620
+
+#define DLR_VLAN_ID_M			(BIT(12) - 1)
+
+#define REG_DLR_DEST_ADDR_0		0x0622
+#define REG_DLR_DEST_ADDR_1		0x0623
+#define REG_DLR_DEST_ADDR_2		0x0624
+#define REG_DLR_DEST_ADDR_3		0x0625
+#define REG_DLR_DEST_ADDR_4		0x0626
+#define REG_DLR_DEST_ADDR_5		0x0627
+
+#define REG_DLR_PORT_MAP__4		0x0628
+
+#define REG_DLR_CLASS__1		0x062C
+
+#define DLR_FRAME_QID_M			0x3
+
+/* HSR */
+#define REG_HSR_PORT_MAP__4		0x0640
+
+#define REG_HSR_ALU_CTRL_0__1		0x0644
+
+#define HSR_DUPLICATE_DISCARD		BIT(7)
+#define HSR_NODE_UNICAST		BIT(6)
+#define HSR_AGE_CNT_DEFAULT_M		0x7
+#define HSR_AGE_CNT_DEFAULT_S		3
+#define HSR_LEARN_MCAST_DISABLE		BIT(2)
+#define HSR_HASH_OPTION_M		0x3
+#define HSR_HASH_DISABLE		0
+#define HSR_HASH_UPPER_BITS		1
+#define HSR_HASH_LOWER_BITS		2
+#define HSR_HASH_XOR_BOTH_BITS		3
+
+#define REG_HSR_ALU_CTRL_1__1		0x0645
+
+#define HSR_LEARN_UCAST_DISABLE		BIT(7)
+#define HSR_FLUSH_TABLE			BIT(5)
+#define HSR_PROC_MCAST_SRC		BIT(3)
+#define HSR_AGING_ENABLE		BIT(2)
+
+#define REG_HSR_ALU_CTRL_2__2		0x0646
+
+#define REG_HSR_ALU_AGE_PERIOD__4	0x0648
+
+#define REG_HSR_ALU_INT_STATUS__1	0x064C
+#define REG_HSR_ALU_INT_MASK__1		0x064D
+
+#define HSR_WINDOW_OVERFLOW_INT		BIT(3)
+#define HSR_LEARN_FAIL_INT		BIT(2)
+#define HSR_ALMOST_FULL_INT		BIT(1)
+#define HSR_WRITE_FAIL_INT		BIT(0)
+
+#define REG_HSR_ALU_ENTRY_0__2		0x0650
+
+#define HSR_ENTRY_INDEX_M		(BIT(10) - 1)
+#define HSR_FAIL_INDEX_M		(BIT(8) - 1)
+
+#define REG_HSR_ALU_ENTRY_1__2		0x0652
+
+#define HSR_FAIL_LEARN_INDEX_M		(BIT(8) - 1)
+
+#define REG_HSR_ALU_ENTRY_3__2		0x0654
+
+#define HSR_CPU_ACCESS_ENTRY_INDEX_M	(BIT(8) - 1)
+
+/* 0 - Operation */
+#define REG_PORT_DEFAULT_VID		0x0000
+
+#define REG_PORT_CUSTOM_VID		0x0002
+#define REG_PORT_AVB_SR_1_VID		0x0004
+#define REG_PORT_AVB_SR_2_VID		0x0006
+
+#define REG_PORT_AVB_SR_1_TYPE		0x0008
+#define REG_PORT_AVB_SR_2_TYPE		0x000A
+
+#define REG_PORT_PME_STATUS		0x0013
+#define REG_PORT_PME_CTRL		0x0017
+
+#define PME_WOL_MAGICPKT		BIT(2)
+#define PME_WOL_LINKUP			BIT(1)
+#define PME_WOL_ENERGY			BIT(0)
+
+#define REG_PORT_INT_STATUS		0x001B
+#define REG_PORT_INT_MASK		0x001F
+
+#define PORT_SGMII_INT			BIT(3)
+#define PORT_PTP_INT			BIT(2)
+#define PORT_PHY_INT			BIT(1)
+#define PORT_ACL_INT			BIT(0)
+
+#define PORT_INT_MASK			\
+	(PORT_SGMII_INT | PORT_PTP_INT | PORT_PHY_INT | PORT_ACL_INT)
+
+#define REG_PORT_CTRL_0			0x0020
+
+#define PORT_MAC_LOOPBACK		BIT(7)
+#define PORT_FORCE_TX_FLOW_CTRL		BIT(4)
+#define PORT_FORCE_RX_FLOW_CTRL		BIT(3)
+#define PORT_TAIL_TAG_ENABLE		BIT(2)
+#define PORT_QUEUE_SPLIT_ENABLE		0x3
+
+#define REG_PORT_CTRL_1			0x0021
+
+#define PORT_SRP_ENABLE			0x3
+
+#define REG_PORT_STATUS_0		0x0030
+
+#define PORT_INTF_SPEED_M		0x3
+#define PORT_INTF_SPEED_S		3
+#define PORT_INTF_FULL_DUPLEX		BIT(2)
+#define PORT_TX_FLOW_CTRL		BIT(1)
+#define PORT_RX_FLOW_CTRL		BIT(0)
+
+#define REG_PORT_STATUS_1		0x0034
+
+/* 1 - PHY */
+#define REG_PORT_PHY_CTRL		0x0100
+
+#define PORT_PHY_RESET			BIT(15)
+#define PORT_PHY_LOOPBACK		BIT(14)
+#define PORT_SPEED_100MBIT		BIT(13)
+#define PORT_AUTO_NEG_ENABLE		BIT(12)
+#define PORT_POWER_DOWN			BIT(11)
+#define PORT_ISOLATE			BIT(10)
+#define PORT_AUTO_NEG_RESTART		BIT(9)
+#define PORT_FULL_DUPLEX		BIT(8)
+#define PORT_COLLISION_TEST		BIT(7)
+#define PORT_SPEED_1000MBIT		BIT(6)
+
+#define REG_PORT_PHY_STATUS		0x0102
+
+#define PORT_100BT4_CAPABLE		BIT(15)
+#define PORT_100BTX_FD_CAPABLE		BIT(14)
+#define PORT_100BTX_CAPABLE		BIT(13)
+#define PORT_10BT_FD_CAPABLE		BIT(12)
+#define PORT_10BT_CAPABLE		BIT(11)
+#define PORT_EXTENDED_STATUS		BIT(8)
+#define PORT_MII_SUPPRESS_CAPABLE	BIT(6)
+#define PORT_AUTO_NEG_ACKNOWLEDGE	BIT(5)
+#define PORT_REMOTE_FAULT		BIT(4)
+#define PORT_AUTO_NEG_CAPABLE		BIT(3)
+#define PORT_LINK_STATUS		BIT(2)
+#define PORT_JABBER_DETECT		BIT(1)
+#define PORT_EXTENDED_CAPABILITY	BIT(0)
+
+#define REG_PORT_PHY_ID_HI		0x0104
+#define REG_PORT_PHY_ID_LO		0x0106
+
+#define KSZ9477_ID_HI			0x0022
+#define KSZ9477_ID_LO			0x1622
+
+#define REG_PORT_PHY_AUTO_NEGOTIATION	0x0108
+
+#define PORT_AUTO_NEG_NEXT_PAGE		BIT(15)
+#define PORT_AUTO_NEG_REMOTE_FAULT	BIT(13)
+#define PORT_AUTO_NEG_ASYM_PAUSE	BIT(11)
+#define PORT_AUTO_NEG_SYM_PAUSE		BIT(10)
+#define PORT_AUTO_NEG_100BT4		BIT(9)
+#define PORT_AUTO_NEG_100BTX_FD		BIT(8)
+#define PORT_AUTO_NEG_100BTX		BIT(7)
+#define PORT_AUTO_NEG_10BT_FD		BIT(6)
+#define PORT_AUTO_NEG_10BT		BIT(5)
+#define PORT_AUTO_NEG_SELECTOR		0x001F
+#define PORT_AUTO_NEG_802_3		0x0001
+
+#define PORT_AUTO_NEG_PAUSE		\
+	(PORT_AUTO_NEG_ASYM_PAUSE | PORT_AUTO_NEG_SYM_PAUSE)
+
+#define REG_PORT_PHY_REMOTE_CAPABILITY	0x010A
+
+#define PORT_REMOTE_NEXT_PAGE		BIT(15)
+#define PORT_REMOTE_ACKNOWLEDGE		BIT(14)
+#define PORT_REMOTE_REMOTE_FAULT	BIT(13)
+#define PORT_REMOTE_ASYM_PAUSE		BIT(11)
+#define PORT_REMOTE_SYM_PAUSE		BIT(10)
+#define PORT_REMOTE_100BTX_FD		BIT(8)
+#define PORT_REMOTE_100BTX		BIT(7)
+#define PORT_REMOTE_10BT_FD		BIT(6)
+#define PORT_REMOTE_10BT		BIT(5)
+
+#define REG_PORT_PHY_1000_CTRL		0x0112
+
+#define PORT_AUTO_NEG_MANUAL		BIT(12)
+#define PORT_AUTO_NEG_MASTER		BIT(11)
+#define PORT_AUTO_NEG_MASTER_PREFERRED	BIT(10)
+#define PORT_AUTO_NEG_1000BT_FD		BIT(9)
+#define PORT_AUTO_NEG_1000BT		BIT(8)
+
+#define REG_PORT_PHY_1000_STATUS	0x0114
+
+#define PORT_MASTER_FAULT		BIT(15)
+#define PORT_LOCAL_MASTER		BIT(14)
+#define PORT_LOCAL_RX_OK		BIT(13)
+#define PORT_REMOTE_RX_OK		BIT(12)
+#define PORT_REMOTE_1000BT_FD		BIT(11)
+#define PORT_REMOTE_1000BT		BIT(10)
+#define PORT_REMOTE_IDLE_CNT_M		0x0F
+
+#define PORT_PHY_1000_STATIC_STATUS	\
+	(PORT_LOCAL_RX_OK |		\
+	PORT_REMOTE_RX_OK |		\
+	PORT_REMOTE_1000BT_FD |		\
+	PORT_REMOTE_1000BT)
+
+#define REG_PORT_PHY_MMD_SETUP		0x011A
+
+#define PORT_MMD_OP_MODE_M		0x3
+#define PORT_MMD_OP_MODE_S		14
+#define PORT_MMD_OP_INDEX		0
+#define PORT_MMD_OP_DATA_NO_INCR	1
+#define PORT_MMD_OP_DATA_INCR_RW	2
+#define PORT_MMD_OP_DATA_INCR_W		3
+#define PORT_MMD_DEVICE_ID_M		0x1F
+
+#define MMD_SETUP(mode, dev)		\
+	(((u16)(mode) << PORT_MMD_OP_MODE_S) | (dev))
+
+#define REG_PORT_PHY_MMD_INDEX_DATA	0x011C
+
+#define MMD_DEVICE_ID_DSP		1
+
+#define MMD_DSP_SQI_CHAN_A		0xAC
+#define MMD_DSP_SQI_CHAN_B		0xAD
+#define MMD_DSP_SQI_CHAN_C		0xAE
+#define MMD_DSP_SQI_CHAN_D		0xAF
+
+#define DSP_SQI_ERR_DETECTED		BIT(15)
+#define DSP_SQI_AVG_ERR			0x7FFF
+
+#define MMD_DEVICE_ID_COMMON		2
+
+#define MMD_DEVICE_ID_EEE_ADV		7
+
+#define MMD_EEE_ADV			0x3C
+#define EEE_ADV_100MBIT			BIT(1)
+#define EEE_ADV_1GBIT			BIT(2)
+
+#define MMD_EEE_LP_ADV			0x3D
+#define MMD_EEE_MSG_CODE		0x3F
+
+#define MMD_DEVICE_ID_AFED		0x1C
+
+#define REG_PORT_PHY_EXTENDED_STATUS	0x011E
+
+#define PORT_100BTX_FD_ABLE		BIT(15)
+#define PORT_100BTX_ABLE		BIT(14)
+#define PORT_10BT_FD_ABLE		BIT(13)
+#define PORT_10BT_ABLE			BIT(12)
+
+#define REG_PORT_SGMII_ADDR__4		0x0200
+#define PORT_SGMII_AUTO_INCR		BIT(23)
+#define PORT_SGMII_DEVICE_ID_M		0x1F
+#define PORT_SGMII_DEVICE_ID_S		16
+#define PORT_SGMII_ADDR_M		(BIT(21) - 1)
+
+#define REG_PORT_SGMII_DATA__4		0x0204
+#define PORT_SGMII_DATA_M		(BIT(16) - 1)
+
+#define MMD_DEVICE_ID_PMA		0x01
+#define MMD_DEVICE_ID_PCS		0x03
+#define MMD_DEVICE_ID_PHY_XS		0x04
+#define MMD_DEVICE_ID_DTE_XS		0x05
+#define MMD_DEVICE_ID_AN		0x07
+#define MMD_DEVICE_ID_VENDOR_CTRL	0x1E
+#define MMD_DEVICE_ID_VENDOR_MII	0x1F
+
+#define SR_MII				MMD_DEVICE_ID_VENDOR_MII
+
+#define MMD_SR_MII_CTRL			0x0000
+
+#define SR_MII_RESET			BIT(15)
+#define SR_MII_LOOPBACK			BIT(14)
+#define SR_MII_SPEED_100MBIT		BIT(13)
+#define SR_MII_AUTO_NEG_ENABLE		BIT(12)
+#define SR_MII_POWER_DOWN		BIT(11)
+#define SR_MII_AUTO_NEG_RESTART		BIT(9)
+#define SR_MII_FULL_DUPLEX		BIT(8)
+#define SR_MII_SPEED_1000MBIT		BIT(6)
+
+#define MMD_SR_MII_STATUS		0x0001
+#define MMD_SR_MII_ID_1			0x0002
+#define MMD_SR_MII_ID_2			0x0003
+#define MMD_SR_MII_AUTO_NEGOTIATION	0x0004
+
+#define SR_MII_AUTO_NEG_NEXT_PAGE	BIT(15)
+#define SR_MII_AUTO_NEG_REMOTE_FAULT_M	0x3
+#define SR_MII_AUTO_NEG_REMOTE_FAULT_S	12
+#define SR_MII_AUTO_NEG_NO_ERROR	0
+#define SR_MII_AUTO_NEG_OFFLINE		1
+#define SR_MII_AUTO_NEG_LINK_FAILURE	2
+#define SR_MII_AUTO_NEG_ERROR		3
+#define SR_MII_AUTO_NEG_PAUSE_M		0x3
+#define SR_MII_AUTO_NEG_PAUSE_S		7
+#define SR_MII_AUTO_NEG_NO_PAUSE	0
+#define SR_MII_AUTO_NEG_ASYM_PAUSE_TX	1
+#define SR_MII_AUTO_NEG_SYM_PAUSE	2
+#define SR_MII_AUTO_NEG_ASYM_PAUSE_RX	3
+#define SR_MII_AUTO_NEG_HALF_DUPLEX	BIT(6)
+#define SR_MII_AUTO_NEG_FULL_DUPLEX	BIT(5)
+
+#define MMD_SR_MII_REMOTE_CAPABILITY	0x0005
+#define MMD_SR_MII_AUTO_NEG_EXP		0x0006
+#define MMD_SR_MII_AUTO_NEG_EXT		0x000F
+
+#define MMD_SR_MII_DIGITAL_CTRL_1	0x8000
+
+#define MMD_SR_MII_AUTO_NEG_CTRL	0x8001
+
+#define SR_MII_8_BIT			BIT(8)
+#define SR_MII_SGMII_LINK_UP		BIT(4)
+#define SR_MII_TX_CFG_PHY_MASTER	BIT(3)
+#define SR_MII_PCS_MODE_M		0x3
+#define SR_MII_PCS_MODE_S		1
+#define SR_MII_PCS_SGMII		2
+#define SR_MII_AUTO_NEG_COMPLETE_INTR	BIT(0)
+
+#define MMD_SR_MII_AUTO_NEG_STATUS	0x8002
+
+#define SR_MII_STAT_LINK_UP		BIT(4)
+#define SR_MII_STAT_M			0x3
+#define SR_MII_STAT_S			2
+#define SR_MII_STAT_10_MBPS		0
+#define SR_MII_STAT_100_MBPS		1
+#define SR_MII_STAT_1000_MBPS		2
+#define SR_MII_STAT_FULL_DUPLEX		BIT(1)
+
+#define MMD_SR_MII_PHY_CTRL		0x80A0
+
+#define SR_MII_PHY_LANE_SEL_M		0xF
+#define SR_MII_PHY_LANE_SEL_S		8
+#define SR_MII_PHY_WRITE		BIT(1)
+#define SR_MII_PHY_START_BUSY		BIT(0)
+
+#define MMD_SR_MII_PHY_ADDR		0x80A1
+
+#define SR_MII_PHY_ADDR_M		(BIT(16) - 1)
+
+#define MMD_SR_MII_PHY_DATA		0x80A2
+
+#define SR_MII_PHY_DATA_M		(BIT(16) - 1)
+
+#define SR_MII_PHY_JTAG_CHIP_ID_HI	0x000C
+#define SR_MII_PHY_JTAG_CHIP_ID_LO	0x000D
+
+#define REG_PORT_PHY_REMOTE_LB_LED	0x0122
+
+#define PORT_REMOTE_LOOPBACK		BIT(8)
+#define PORT_LED_SELECT			(3 << 6)
+#define PORT_LED_CTRL			(3 << 4)
+#define PORT_LED_CTRL_TEST		BIT(3)
+#define PORT_10BT_PREAMBLE		BIT(2)
+#define PORT_LINK_MD_10BT_ENABLE	BIT(1)
+#define PORT_LINK_MD_PASS		BIT(0)
+
+#define REG_PORT_PHY_LINK_MD		0x0124
+
+#define PORT_START_CABLE_DIAG		BIT(15)
+#define PORT_TX_DISABLE			BIT(14)
+#define PORT_CABLE_DIAG_PAIR_M		0x3
+#define PORT_CABLE_DIAG_PAIR_S		12
+#define PORT_CABLE_DIAG_SELECT_M	0x3
+#define PORT_CABLE_DIAG_SELECT_S	10
+#define PORT_CABLE_DIAG_RESULT_M	0x3
+#define PORT_CABLE_DIAG_RESULT_S	8
+#define PORT_CABLE_STAT_NORMAL		0
+#define PORT_CABLE_STAT_OPEN		1
+#define PORT_CABLE_STAT_SHORT		2
+#define PORT_CABLE_STAT_FAILED		3
+#define PORT_CABLE_FAULT_COUNTER	0x00FF
+
+#define REG_PORT_PHY_PMA_STATUS		0x0126
+
+#define PORT_1000_LINK_GOOD		BIT(1)
+#define PORT_100_LINK_GOOD		BIT(0)
+
+#define REG_PORT_PHY_DIGITAL_STATUS	0x0128
+
+#define PORT_LINK_DETECT		BIT(14)
+#define PORT_SIGNAL_DETECT		BIT(13)
+#define PORT_PHY_STAT_MDI		BIT(12)
+#define PORT_PHY_STAT_MASTER		BIT(11)
+
+#define REG_PORT_PHY_RXER_COUNTER	0x012A
+
+#define REG_PORT_PHY_INT_ENABLE		0x0136
+#define REG_PORT_PHY_INT_STATUS		0x0137
+
+#define JABBER_INT			BIT(7)
+#define RX_ERR_INT			BIT(6)
+#define PAGE_RX_INT			BIT(5)
+#define PARALLEL_DETECT_FAULT_INT	BIT(4)
+#define LINK_PARTNER_ACK_INT		BIT(3)
+#define LINK_DOWN_INT			BIT(2)
+#define REMOTE_FAULT_INT		BIT(1)
+#define LINK_UP_INT			BIT(0)
+
+#define REG_PORT_PHY_DIGITAL_DEBUG_1	0x0138
+
+#define PORT_REG_CLK_SPEED_25_MHZ	BIT(14)
+#define PORT_PHY_FORCE_MDI		BIT(7)
+#define PORT_PHY_AUTO_MDIX_DISABLE	BIT(6)
+
+/* Same as PORT_PHY_LOOPBACK */
+#define PORT_PHY_PCS_LOOPBACK		BIT(0)
+
+#define REG_PORT_PHY_DIGITAL_DEBUG_2	0x013A
+
+#define REG_PORT_PHY_DIGITAL_DEBUG_3	0x013C
+
+#define PORT_100BT_FIXED_LATENCY	BIT(15)
+
+#define REG_PORT_PHY_PHY_CTRL		0x013E
+
+#define PORT_INT_PIN_HIGH		BIT(14)
+#define PORT_ENABLE_JABBER		BIT(9)
+#define PORT_STAT_SPEED_1000MBIT	BIT(6)
+#define PORT_STAT_SPEED_100MBIT		BIT(5)
+#define PORT_STAT_SPEED_10MBIT		BIT(4)
+#define PORT_STAT_FULL_DUPLEX		BIT(3)
+
+/* Same as PORT_PHY_STAT_MASTER */
+#define PORT_STAT_MASTER		BIT(2)
+#define PORT_RESET			BIT(1)
+#define PORT_LINK_STATUS_FAIL		BIT(0)
+
+/* 3 - xMII */
+#define REG_PORT_XMII_CTRL_0		0x0300
+
+#define PORT_SGMII_SEL			BIT(7)
+#define PORT_MII_FULL_DUPLEX		BIT(6)
+#define PORT_MII_100MBIT		BIT(4)
+#define PORT_GRXC_ENABLE		BIT(0)
+
+#define REG_PORT_XMII_CTRL_1		0x0301
+
+#define PORT_RMII_CLK_SEL		BIT(7)
+/* S1 */
+#define PORT_MII_1000MBIT_S1		BIT(6)
+/* S2 */
+#define PORT_MII_NOT_1GBIT		BIT(6)
+#define PORT_MII_SEL_EDGE		BIT(5)
+#define PORT_RGMII_ID_IG_ENABLE		BIT(4)
+#define PORT_RGMII_ID_EG_ENABLE		BIT(3)
+#define PORT_MII_MAC_MODE		BIT(2)
+#define PORT_MII_SEL_M			0x3
+/* S1 */
+#define PORT_MII_SEL_S1			0x0
+#define PORT_RMII_SEL_S1		0x1
+#define PORT_GMII_SEL_S1		0x2
+#define PORT_RGMII_SEL_S1		0x3
+/* S2 */
+#define PORT_RGMII_SEL			0x0
+#define PORT_RMII_SEL			0x1
+#define PORT_GMII_SEL			0x2
+#define PORT_MII_SEL			0x3
+
+/* 4 - MAC */
+#define REG_PORT_MAC_CTRL_0		0x0400
+
+#define PORT_BROADCAST_STORM		BIT(1)
+#define PORT_JUMBO_FRAME		BIT(0)
+
+#define REG_PORT_MAC_CTRL_1		0x0401
+
+#define PORT_BACK_PRESSURE		BIT(3)
+#define PORT_PASS_ALL			BIT(0)
+
+#define REG_PORT_MAC_CTRL_2		0x0402
+
+#define PORT_100BT_EEE_DISABLE		BIT(7)
+#define PORT_1000BT_EEE_DISABLE		BIT(6)
+
+#define REG_PORT_MAC_IN_RATE_LIMIT	0x0403
+
+#define PORT_IN_PORT_BASED_S		6
+#define PORT_RATE_PACKET_BASED_S	5
+#define PORT_IN_FLOW_CTRL_S		4
+#define PORT_COUNT_IFG_S		1
+#define PORT_COUNT_PREAMBLE_S		0
+#define PORT_IN_PORT_BASED		BIT(6)
+#define PORT_IN_PACKET_BASED		BIT(5)
+#define PORT_IN_FLOW_CTRL		BIT(4)
+#define PORT_IN_LIMIT_MODE_M		0x3
+#define PORT_IN_LIMIT_MODE_S		2
+#define PORT_IN_ALL			0
+#define PORT_IN_UNICAST			1
+#define PORT_IN_MULTICAST		2
+#define PORT_IN_BROADCAST		3
+#define PORT_COUNT_IFG			BIT(1)
+#define PORT_COUNT_PREAMBLE		BIT(0)
+
+#define REG_PORT_IN_RATE_0		0x0410
+#define REG_PORT_IN_RATE_1		0x0411
+#define REG_PORT_IN_RATE_2		0x0412
+#define REG_PORT_IN_RATE_3		0x0413
+#define REG_PORT_IN_RATE_4		0x0414
+#define REG_PORT_IN_RATE_5		0x0415
+#define REG_PORT_IN_RATE_6		0x0416
+#define REG_PORT_IN_RATE_7		0x0417
+
+#define REG_PORT_OUT_RATE_0		0x0420
+#define REG_PORT_OUT_RATE_1		0x0421
+#define REG_PORT_OUT_RATE_2		0x0422
+#define REG_PORT_OUT_RATE_3		0x0423
+
+#define PORT_RATE_LIMIT_M		(BIT(7) - 1)
+
+/* 5 - MIB Counters */
+#define REG_PORT_MIB_CTRL_STAT__4	0x0500
+
+#define MIB_COUNTER_OVERFLOW		BIT(31)
+#define MIB_COUNTER_VALID		BIT(30)
+#define MIB_COUNTER_READ		BIT(25)
+#define MIB_COUNTER_FLUSH_FREEZE	BIT(24)
+#define MIB_COUNTER_INDEX_M		(BIT(8) - 1)
+#define MIB_COUNTER_INDEX_S		16
+#define MIB_COUNTER_DATA_HI_M		0xF
+
+#define REG_PORT_MIB_DATA		0x0504
+
+/* 6 - ACL */
+#define REG_PORT_ACL_0			0x0600
+
+#define ACL_FIRST_RULE_M		0xF
+
+#define REG_PORT_ACL_1			0x0601
+
+#define ACL_MODE_M			0x3
+#define ACL_MODE_S			4
+#define ACL_MODE_DISABLE		0
+#define ACL_MODE_LAYER_2		1
+#define ACL_MODE_LAYER_3		2
+#define ACL_MODE_LAYER_4		3
+#define ACL_ENABLE_M			0x3
+#define ACL_ENABLE_S			2
+#define ACL_ENABLE_2_COUNT		0
+#define ACL_ENABLE_2_TYPE		1
+#define ACL_ENABLE_2_MAC		2
+#define ACL_ENABLE_2_BOTH		3
+#define ACL_ENABLE_3_IP			1
+#define ACL_ENABLE_3_SRC_DST_COMP	2
+#define ACL_ENABLE_4_PROTOCOL		0
+#define ACL_ENABLE_4_TCP_PORT_COMP	1
+#define ACL_ENABLE_4_UDP_PORT_COMP	2
+#define ACL_ENABLE_4_TCP_SEQN_COMP	3
+#define ACL_SRC				BIT(1)
+#define ACL_EQUAL			BIT(0)
+
+#define REG_PORT_ACL_2			0x0602
+#define REG_PORT_ACL_3			0x0603
+
+#define ACL_MAX_PORT			0xFFFF
+
+#define REG_PORT_ACL_4			0x0604
+#define REG_PORT_ACL_5			0x0605
+
+#define ACL_MIN_PORT			0xFFFF
+#define ACL_IP_ADDR			0xFFFFFFFF
+#define ACL_TCP_SEQNUM			0xFFFFFFFF
+
+#define REG_PORT_ACL_6			0x0606
+
+#define ACL_RESERVED			0xF8
+#define ACL_PORT_MODE_M			0x3
+#define ACL_PORT_MODE_S			1
+#define ACL_PORT_MODE_DISABLE		0
+#define ACL_PORT_MODE_EITHER		1
+#define ACL_PORT_MODE_IN_RANGE		2
+#define ACL_PORT_MODE_OUT_OF_RANGE	3
+
+#define REG_PORT_ACL_7			0x0607
+
+#define ACL_TCP_FLAG_ENABLE		BIT(0)
+
+#define REG_PORT_ACL_8			0x0608
+
+#define ACL_TCP_FLAG_M			0xFF
+
+#define REG_PORT_ACL_9			0x0609
+
+#define ACL_TCP_FLAG			0xFF
+#define ACL_ETH_TYPE			0xFFFF
+#define ACL_IP_M			0xFFFFFFFF
+
+#define REG_PORT_ACL_A			0x060A
+
+#define ACL_PRIO_MODE_M			0x3
+#define ACL_PRIO_MODE_S			6
+#define ACL_PRIO_MODE_DISABLE		0
+#define ACL_PRIO_MODE_HIGHER		1
+#define ACL_PRIO_MODE_LOWER		2
+#define ACL_PRIO_MODE_REPLACE		3
+#define ACL_PRIO_M			KS_PRIO_M
+#define ACL_PRIO_S			3
+#define ACL_VLAN_PRIO_REPLACE		BIT(2)
+#define ACL_VLAN_PRIO_M			KS_PRIO_M
+#define ACL_VLAN_PRIO_HI_M		0x3
+
+#define REG_PORT_ACL_B			0x060B
+
+#define ACL_VLAN_PRIO_LO_M		0x8
+#define ACL_VLAN_PRIO_S			7
+#define ACL_MAP_MODE_M			0x3
+#define ACL_MAP_MODE_S			5
+#define ACL_MAP_MODE_DISABLE		0
+#define ACL_MAP_MODE_OR			1
+#define ACL_MAP_MODE_AND		2
+#define ACL_MAP_MODE_REPLACE		3
+
+#define ACL_CNT_M			(BIT(11) - 1)
+#define ACL_CNT_S			5
+
+#define REG_PORT_ACL_C			0x060C
+
+#define REG_PORT_ACL_D			0x060D
+#define ACL_MSEC_UNIT			BIT(6)
+#define ACL_INTR_MODE			BIT(5)
+#define ACL_PORT_MAP			0x7F
+
+#define REG_PORT_ACL_E			0x060E
+#define REG_PORT_ACL_F			0x060F
+
+#define REG_PORT_ACL_BYTE_EN_MSB	0x0610
+#define REG_PORT_ACL_BYTE_EN_LSB	0x0611
+
+#define ACL_ACTION_START		0xA
+#define ACL_ACTION_LEN			4
+#define ACL_INTR_CNT_START		0xD
+#define ACL_RULESET_START		0xE
+#define ACL_RULESET_LEN			2
+#define ACL_TABLE_LEN			16
+
+#define ACL_ACTION_ENABLE		0x003C
+#define ACL_MATCH_ENABLE		0x7FC3
+#define ACL_RULESET_ENABLE		0x8003
+#define ACL_BYTE_ENABLE			0xFFFF
+
+#define REG_PORT_ACL_CTRL_0		0x0612
+
+#define PORT_ACL_WRITE_DONE		BIT(6)
+#define PORT_ACL_READ_DONE		BIT(5)
+#define PORT_ACL_WRITE			BIT(4)
+#define PORT_ACL_INDEX_M		0xF
+
+#define REG_PORT_ACL_CTRL_1		0x0613
+
+/* 8 - Classification and Policing */
+#define REG_PORT_MRI_MIRROR_CTRL	0x0800
+
+#define PORT_MIRROR_RX			BIT(6)
+#define PORT_MIRROR_TX			BIT(5)
+#define PORT_MIRROR_SNIFFER		BIT(1)
+
+#define REG_PORT_MRI_PRIO_CTRL		0x0801
+
+#define PORT_HIGHEST_PRIO		BIT(7)
+#define PORT_OR_PRIO			BIT(6)
+#define PORT_MAC_PRIO_ENABLE		BIT(4)
+#define PORT_VLAN_PRIO_ENABLE		BIT(3)
+#define PORT_802_1P_PRIO_ENABLE		BIT(2)
+#define PORT_DIFFSERV_PRIO_ENABLE	BIT(1)
+#define PORT_ACL_PRIO_ENABLE		BIT(0)
+
+#define REG_PORT_MRI_MAC_CTRL		0x0802
+
+#define PORT_USER_PRIO_CEILING		BIT(7)
+#define PORT_DROP_NON_VLAN		BIT(4)
+#define PORT_DROP_TAG			BIT(3)
+#define PORT_BASED_PRIO_M		KS_PRIO_M
+#define PORT_BASED_PRIO_S		0
+
+#define REG_PORT_MRI_AUTHEN_CTRL	0x0803
+
+#define PORT_ACL_ENABLE			BIT(2)
+#define PORT_AUTHEN_MODE		0x3
+#define PORT_AUTHEN_PASS		0
+#define PORT_AUTHEN_BLOCK		1
+#define PORT_AUTHEN_TRAP		2
+
+#define REG_PORT_MRI_INDEX__4		0x0804
+
+#define MRI_INDEX_P_M			0x7
+#define MRI_INDEX_P_S			16
+#define MRI_INDEX_Q_M			0x3
+#define MRI_INDEX_Q_S			0
+
+#define REG_PORT_MRI_TC_MAP__4		0x0808
+
+#define PORT_TC_MAP_M			0xf
+#define PORT_TC_MAP_S			4
+
+#define REG_PORT_MRI_POLICE_CTRL__4	0x080C
+
+#define POLICE_DROP_ALL			BIT(10)
+#define POLICE_PACKET_TYPE_M		0x3
+#define POLICE_PACKET_TYPE_S		8
+#define POLICE_PACKET_DROPPED		0
+#define POLICE_PACKET_GREEN		1
+#define POLICE_PACKET_YELLOW		2
+#define POLICE_PACKET_RED		3
+#define PORT_BASED_POLICING		BIT(7)
+#define NON_DSCP_COLOR_M		0x3
+#define NON_DSCP_COLOR_S		5
+#define COLOR_MARK_ENABLE		BIT(4)
+#define COLOR_REMAP_ENABLE		BIT(3)
+#define POLICE_DROP_SRP			BIT(2)
+#define POLICE_COLOR_NOT_AWARE		BIT(1)
+#define POLICE_ENABLE			BIT(0)
+
+#define REG_PORT_POLICE_COLOR_0__4	0x0810
+#define REG_PORT_POLICE_COLOR_1__4	0x0814
+#define REG_PORT_POLICE_COLOR_2__4	0x0818
+#define REG_PORT_POLICE_COLOR_3__4	0x081C
+
+#define POLICE_COLOR_MAP_S		2
+#define POLICE_COLOR_MAP_M		(BIT(POLICE_COLOR_MAP_S) - 1)
+
+#define REG_PORT_POLICE_RATE__4		0x0820
+
+#define POLICE_CIR_S			16
+#define POLICE_PIR_S			0
+
+#define REG_PORT_POLICE_BURST_SIZE__4	0x0824
+
+#define POLICE_BURST_SIZE_M		0x3FFF
+#define POLICE_CBS_S			16
+#define POLICE_PBS_S			0
+
+#define REG_PORT_WRED_PM_CTRL_0__4	0x0830
+
+#define WRED_PM_CTRL_M			(BIT(11) - 1)
+
+#define WRED_PM_MAX_THRESHOLD_S		16
+#define WRED_PM_MIN_THRESHOLD_S		0
+
+#define REG_PORT_WRED_PM_CTRL_1__4	0x0834
+
+#define WRED_PM_MULTIPLIER_S		16
+#define WRED_PM_AVG_QUEUE_SIZE_S	0
+
+#define REG_PORT_WRED_QUEUE_CTRL_0__4	0x0840
+#define REG_PORT_WRED_QUEUE_CTRL_1__4	0x0844
+
+#define REG_PORT_WRED_QUEUE_PMON__4	0x0848
+
+#define WRED_RANDOM_DROP_ENABLE		BIT(31)
+#define WRED_PMON_FLUSH			BIT(30)
+#define WRED_DROP_GYR_DISABLE		BIT(29)
+#define WRED_DROP_YR_DISABLE		BIT(28)
+#define WRED_DROP_R_DISABLE		BIT(27)
+#define WRED_DROP_ALL			BIT(26)
+#define WRED_PMON_M			(BIT(24) - 1)
+
+/* 9 - Shaping */
+
+#define REG_PORT_MTI_QUEUE_INDEX__4	0x0900
+
+#define REG_PORT_MTI_QUEUE_CTRL_0__4	0x0904
+
+#define MTI_PVID_REPLACE		BIT(0)
+
+#define REG_PORT_MTI_QUEUE_CTRL_0	0x0914
+
+#define MTI_SCHEDULE_MODE_M		0x3
+#define MTI_SCHEDULE_MODE_S		6
+#define MTI_SCHEDULE_STRICT_PRIO	0
+#define MTI_SCHEDULE_WRR		2
+#define MTI_SHAPING_M			0x3
+#define MTI_SHAPING_S			4
+#define MTI_SHAPING_OFF			0
+#define MTI_SHAPING_SRP			1
+#define MTI_SHAPING_TIME_AWARE		2
+
+#define REG_PORT_MTI_QUEUE_CTRL_1	0x0915
+
+#define MTI_TX_RATIO_M			(BIT(7) - 1)
+
+#define REG_PORT_MTI_QUEUE_CTRL_2__2	0x0916
+#define REG_PORT_MTI_HI_WATER_MARK	0x0916
+#define REG_PORT_MTI_QUEUE_CTRL_3__2	0x0918
+#define REG_PORT_MTI_LO_WATER_MARK	0x0918
+#define REG_PORT_MTI_QUEUE_CTRL_4__2	0x091A
+#define REG_PORT_MTI_CREDIT_INCREMENT	0x091A
+
+/* A - QM */
+
+#define REG_PORT_QM_CTRL__4		0x0A00
+
+#define PORT_QM_DROP_PRIO_M		0x3
+
+#define REG_PORT_VLAN_MEMBERSHIP__4	0x0A04
+
+#define REG_PORT_QM_QUEUE_INDEX__4	0x0A08
+
+#define PORT_QM_QUEUE_INDEX_S		24
+#define PORT_QM_BURST_SIZE_S		16
+#define PORT_QM_MIN_RESV_SPACE_M	(BIT(11) - 1)
+
+#define REG_PORT_QM_WATER_MARK__4	0x0A0C
+
+#define PORT_QM_HI_WATER_MARK_S		16
+#define PORT_QM_LO_WATER_MARK_S		0
+#define PORT_QM_WATER_MARK_M		(BIT(11) - 1)
+
+#define REG_PORT_QM_TX_CNT_0__4		0x0A10
+
+#define PORT_QM_TX_CNT_USED_S		0
+#define PORT_QM_TX_CNT_M		(BIT(11) - 1)
+
+#define REG_PORT_QM_TX_CNT_1__4		0x0A14
+
+#define PORT_QM_TX_CNT_CALCULATED_S	16
+#define PORT_QM_TX_CNT_AVAIL_S		0
+
+/* B - LUE */
+#define REG_PORT_LUE_CTRL		0x0B00
+
+#define PORT_VLAN_LOOKUP_VID_0		BIT(7)
+#define PORT_INGRESS_FILTER		BIT(6)
+#define PORT_DISCARD_NON_VID		BIT(5)
+#define PORT_MAC_BASED_802_1X		BIT(4)
+#define PORT_SRC_ADDR_FILTER		BIT(3)
+
+#define REG_PORT_LUE_MSTP_INDEX		0x0B01
+
+#define REG_PORT_LUE_MSTP_STATE		0x0B04
+
+#define PORT_TX_ENABLE			BIT(2)
+#define PORT_RX_ENABLE			BIT(1)
+#define PORT_LEARN_DISABLE		BIT(0)
+
+/* C - PTP */
+
+#define REG_PTP_PORT_RX_DELAY__2	0x0C00
+#define REG_PTP_PORT_TX_DELAY__2	0x0C02
+#define REG_PTP_PORT_ASYM_DELAY__2	0x0C04
+
+#define REG_PTP_PORT_XDELAY_TS		0x0C08
+#define REG_PTP_PORT_XDELAY_TS_H	0x0C08
+#define REG_PTP_PORT_XDELAY_TS_L	0x0C0A
+
+#define REG_PTP_PORT_SYNC_TS		0x0C0C
+#define REG_PTP_PORT_SYNC_TS_H		0x0C0C
+#define REG_PTP_PORT_SYNC_TS_L		0x0C0E
+
+#define REG_PTP_PORT_PDRESP_TS		0x0C10
+#define REG_PTP_PORT_PDRESP_TS_H	0x0C10
+#define REG_PTP_PORT_PDRESP_TS_L	0x0C12
+
+#define REG_PTP_PORT_TX_INT_STATUS__2	0x0C14
+#define REG_PTP_PORT_TX_INT_ENABLE__2	0x0C16
+
+#define PTP_PORT_SYNC_INT		BIT(15)
+#define PTP_PORT_XDELAY_REQ_INT		BIT(14)
+#define PTP_PORT_PDELAY_RESP_INT	BIT(13)
+
+#define REG_PTP_PORT_LINK_DELAY__4	0x0C18
+
+#define PRIO_QUEUES			4
+#define RX_PRIO_QUEUES			8
+
+#define KS_PRIO_IN_REG			2
+
+#define TOTAL_PORT_NUM			7
+
+#define KSZ9477_COUNTER_NUM		0x20
+#define TOTAL_KSZ9477_COUNTER_NUM	(KSZ9477_COUNTER_NUM + 2 + 2)
+
+#define SWITCH_COUNTER_NUM		KSZ9477_COUNTER_NUM
+#define TOTAL_SWITCH_COUNTER_NUM	TOTAL_KSZ9477_COUNTER_NUM
+
+#define P_BCAST_STORM_CTRL		REG_PORT_MAC_CTRL_0
+#define P_PRIO_CTRL			REG_PORT_MRI_PRIO_CTRL
+#define P_MIRROR_CTRL			REG_PORT_MRI_MIRROR_CTRL
+#define P_STP_CTRL			REG_PORT_LUE_MSTP_STATE
+#define P_PHY_CTRL			REG_PORT_PHY_CTRL
+#define P_NEG_RESTART_CTRL		REG_PORT_PHY_CTRL
+#define P_LINK_STATUS			REG_PORT_PHY_STATUS
+#define P_SPEED_STATUS			REG_PORT_PHY_PHY_CTRL
+#define P_RATE_LIMIT_CTRL		REG_PORT_MAC_IN_RATE_LIMIT
+
+#define S_LINK_AGING_CTRL		REG_SW_LUE_CTRL_1
+#define S_MIRROR_CTRL			REG_SW_MRI_CTRL_0
+#define S_REPLACE_VID_CTRL		REG_SW_MAC_CTRL_2
+#define S_802_1P_PRIO_CTRL		REG_SW_MAC_802_1P_MAP_0
+#define S_TOS_PRIO_CTRL			REG_SW_MAC_TOS_PRIO_0
+#define S_FLUSH_TABLE_CTRL		REG_SW_LUE_CTRL_1
+
+#define SW_FLUSH_DYN_MAC_TABLE		SW_FLUSH_MSTP_TABLE
+
+#define MAX_TIMESTAMP_UNIT		2
+#define MAX_TRIG_UNIT			3
+#define MAX_TIMESTAMP_EVENT_UNIT	8
+#define MAX_GPIO			4
+
+#define PTP_TRIG_UNIT_M			(BIT(MAX_TRIG_UNIT) - 1)
+#define PTP_TS_UNIT_M			(BIT(MAX_TIMESTAMP_UNIT) - 1)
+
+/* Driver set switch broadcast storm protection at 10% rate. */
+#define BROADCAST_STORM_PROT_RATE	10
+
+/* 148,800 frames * 67 ms / 100 */
+#define BROADCAST_STORM_VALUE		9969
+
+#endif /* KSZ9477_REGS_H */
diff --git a/drivers/net/dsa/microchip/ksz_9477_reg.h b/drivers/net/dsa/microchip/ksz_9477_reg.h
deleted file mode 100644
index 2938e892b631..000000000000
--- a/drivers/net/dsa/microchip/ksz_9477_reg.h
+++ /dev/null
@@ -1,1665 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
- * Microchip KSZ9477 register definitions
- *
- * Copyright (C) 2017-2018 Microchip Technology Inc.
- */
-
-#ifndef __KSZ9477_REGS_H
-#define __KSZ9477_REGS_H
-
-#define KS_PRIO_M			0x7
-#define KS_PRIO_S			4
-
-/* 0 - Operation */
-#define REG_CHIP_ID0__1			0x0000
-
-#define REG_CHIP_ID1__1			0x0001
-
-#define FAMILY_ID			0x95
-#define FAMILY_ID_94			0x94
-#define FAMILY_ID_95			0x95
-#define FAMILY_ID_85			0x85
-#define FAMILY_ID_98			0x98
-#define FAMILY_ID_88			0x88
-
-#define REG_CHIP_ID2__1			0x0002
-
-#define CHIP_ID_63			0x63
-#define CHIP_ID_66			0x66
-#define CHIP_ID_67			0x67
-#define CHIP_ID_77			0x77
-#define CHIP_ID_93			0x93
-#define CHIP_ID_96			0x96
-#define CHIP_ID_97			0x97
-
-#define REG_CHIP_ID3__1			0x0003
-
-#define SWITCH_REVISION_M		0x0F
-#define SWITCH_REVISION_S		4
-#define SWITCH_RESET			0x01
-
-#define REG_SW_PME_CTRL			0x0006
-
-#define PME_ENABLE			BIT(1)
-#define PME_POLARITY			BIT(0)
-
-#define REG_GLOBAL_OPTIONS		0x000F
-
-#define SW_GIGABIT_ABLE			BIT(6)
-#define SW_REDUNDANCY_ABLE		BIT(5)
-#define SW_AVB_ABLE			BIT(4)
-#define SW_9567_RL_5_2			0xC
-#define SW_9477_SL_5_2			0xD
-
-#define SW_9896_GL_5_1			0xB
-#define SW_9896_RL_5_1			0x8
-#define SW_9896_SL_5_1			0x9
-
-#define SW_9895_GL_4_1			0x7
-#define SW_9895_RL_4_1			0x4
-#define SW_9895_SL_4_1			0x5
-
-#define SW_9896_RL_4_2			0x6
-
-#define SW_9893_RL_2_1			0x0
-#define SW_9893_SL_2_1			0x1
-#define SW_9893_GL_2_1			0x3
-
-#define SW_QW_ABLE			BIT(5)
-#define SW_9893_RN_2_1			0xC
-
-#define REG_SW_INT_STATUS__4		0x0010
-#define REG_SW_INT_MASK__4		0x0014
-
-#define LUE_INT				BIT(31)
-#define TRIG_TS_INT			BIT(30)
-#define APB_TIMEOUT_INT			BIT(29)
-
-#define SWITCH_INT_MASK			(TRIG_TS_INT | APB_TIMEOUT_INT)
-
-#define REG_SW_PORT_INT_STATUS__4	0x0018
-#define REG_SW_PORT_INT_MASK__4		0x001C
-#define REG_SW_PHY_INT_STATUS		0x0020
-#define REG_SW_PHY_INT_ENABLE		0x0024
-
-/* 1 - Global */
-#define REG_SW_GLOBAL_SERIAL_CTRL_0	0x0100
-#define SW_SPARE_REG_2			BIT(7)
-#define SW_SPARE_REG_1			BIT(6)
-#define SW_SPARE_REG_0			BIT(5)
-#define SW_BIG_ENDIAN			BIT(4)
-#define SPI_AUTO_EDGE_DETECTION		BIT(1)
-#define SPI_CLOCK_OUT_RISING_EDGE	BIT(0)
-
-#define REG_SW_GLOBAL_OUTPUT_CTRL__1	0x0103
-#define SW_ENABLE_REFCLKO		BIT(1)
-#define SW_REFCLKO_IS_125MHZ		BIT(0)
-
-#define REG_SW_IBA__4			0x0104
-
-#define SW_IBA_ENABLE			BIT(31)
-#define SW_IBA_DA_MATCH			BIT(30)
-#define SW_IBA_INIT			BIT(29)
-#define SW_IBA_QID_M			0xF
-#define SW_IBA_QID_S			22
-#define SW_IBA_PORT_M			0x2F
-#define SW_IBA_PORT_S			16
-#define SW_IBA_FRAME_TPID_M		0xFFFF
-
-#define REG_SW_APB_TIMEOUT_ADDR__4	0x0108
-
-#define APB_TIMEOUT_ACKNOWLEDGE		BIT(31)
-
-#define REG_SW_IBA_SYNC__1		0x010C
-
-#define REG_SW_IO_STRENGTH__1		0x010D
-#define SW_DRIVE_STRENGTH_M		0x7
-#define SW_DRIVE_STRENGTH_2MA		0
-#define SW_DRIVE_STRENGTH_4MA		1
-#define SW_DRIVE_STRENGTH_8MA		2
-#define SW_DRIVE_STRENGTH_12MA		3
-#define SW_DRIVE_STRENGTH_16MA		4
-#define SW_DRIVE_STRENGTH_20MA		5
-#define SW_DRIVE_STRENGTH_24MA		6
-#define SW_DRIVE_STRENGTH_28MA		7
-#define SW_HI_SPEED_DRIVE_STRENGTH_S	4
-#define SW_LO_SPEED_DRIVE_STRENGTH_S	0
-
-#define REG_SW_IBA_STATUS__4		0x0110
-
-#define SW_IBA_REQ			BIT(31)
-#define SW_IBA_RESP			BIT(30)
-#define SW_IBA_DA_MISMATCH		BIT(14)
-#define SW_IBA_FMT_MISMATCH		BIT(13)
-#define SW_IBA_CODE_ERROR		BIT(12)
-#define SW_IBA_CMD_ERROR		BIT(11)
-#define SW_IBA_CMD_LOC_M		(BIT(6) - 1)
-
-#define REG_SW_IBA_STATES__4		0x0114
-
-#define SW_IBA_BUF_STATE_S		30
-#define SW_IBA_CMD_STATE_S		28
-#define SW_IBA_RESP_STATE_S		26
-#define SW_IBA_STATE_M			0x3
-#define SW_IBA_PACKET_SIZE_M		0x7F
-#define SW_IBA_PACKET_SIZE_S		16
-#define SW_IBA_FMT_ID_M			0xFFFF
-
-#define REG_SW_IBA_RESULT__4		0x0118
-
-#define SW_IBA_SIZE_S			24
-
-#define SW_IBA_RETRY_CNT_M		(BIT(5) - 1)
-
-/* 2 - PHY */
-#define REG_SW_POWER_MANAGEMENT_CTRL	0x0201
-
-#define SW_PLL_POWER_DOWN		BIT(5)
-#define SW_POWER_DOWN_MODE		0x3
-#define SW_ENERGY_DETECTION		1
-#define SW_SOFT_POWER_DOWN		2
-#define SW_POWER_SAVING			3
-
-/* 3 - Operation Control */
-#define REG_SW_OPERATION		0x0300
-
-#define SW_DOUBLE_TAG			BIT(7)
-#define SW_RESET			BIT(1)
-#define SW_START			BIT(0)
-
-#define REG_SW_MAC_ADDR_0		0x0302
-#define REG_SW_MAC_ADDR_1		0x0303
-#define REG_SW_MAC_ADDR_2		0x0304
-#define REG_SW_MAC_ADDR_3		0x0305
-#define REG_SW_MAC_ADDR_4		0x0306
-#define REG_SW_MAC_ADDR_5		0x0307
-
-#define REG_SW_MTU__2			0x0308
-
-#define REG_SW_ISP_TPID__2		0x030A
-
-#define REG_SW_HSR_TPID__2		0x030C
-
-#define REG_AVB_STRATEGY__2		0x030E
-
-#define SW_SHAPING_CREDIT_ACCT		BIT(1)
-#define SW_POLICING_CREDIT_ACCT		BIT(0)
-
-#define REG_SW_LUE_CTRL_0		0x0310
-
-#define SW_VLAN_ENABLE			BIT(7)
-#define SW_DROP_INVALID_VID		BIT(6)
-#define SW_AGE_CNT_M			0x7
-#define SW_AGE_CNT_S			3
-#define SW_RESV_MCAST_ENABLE		BIT(2)
-#define SW_HASH_OPTION_M		0x03
-#define SW_HASH_OPTION_CRC		1
-#define SW_HASH_OPTION_XOR		2
-#define SW_HASH_OPTION_DIRECT		3
-
-#define REG_SW_LUE_CTRL_1		0x0311
-
-#define UNICAST_LEARN_DISABLE		BIT(7)
-#define SW_SRC_ADDR_FILTER		BIT(6)
-#define SW_FLUSH_STP_TABLE		BIT(5)
-#define SW_FLUSH_MSTP_TABLE		BIT(4)
-#define SW_FWD_MCAST_SRC_ADDR		BIT(3)
-#define SW_AGING_ENABLE			BIT(2)
-#define SW_FAST_AGING			BIT(1)
-#define SW_LINK_AUTO_AGING		BIT(0)
-
-#define REG_SW_LUE_CTRL_2		0x0312
-
-#define SW_TRAP_DOUBLE_TAG		BIT(6)
-#define SW_EGRESS_VLAN_FILTER_DYN	BIT(5)
-#define SW_EGRESS_VLAN_FILTER_STA	BIT(4)
-#define SW_FLUSH_OPTION_M		0x3
-#define SW_FLUSH_OPTION_S		2
-#define SW_FLUSH_OPTION_DYN_MAC		1
-#define SW_FLUSH_OPTION_STA_MAC		2
-#define SW_FLUSH_OPTION_BOTH		3
-#define SW_PRIO_M			0x3
-#define SW_PRIO_DA			0
-#define SW_PRIO_SA			1
-#define SW_PRIO_HIGHEST_DA_SA		2
-#define SW_PRIO_LOWEST_DA_SA		3
-
-#define REG_SW_LUE_CTRL_3		0x0313
-
-#define REG_SW_LUE_INT_STATUS		0x0314
-#define REG_SW_LUE_INT_ENABLE		0x0315
-
-#define LEARN_FAIL_INT			BIT(2)
-#define ALMOST_FULL_INT			BIT(1)
-#define WRITE_FAIL_INT			BIT(0)
-
-#define REG_SW_LUE_INDEX_0__2		0x0316
-
-#define ENTRY_INDEX_M			0x0FFF
-
-#define REG_SW_LUE_INDEX_1__2		0x0318
-
-#define FAIL_INDEX_M			0x03FF
-
-#define REG_SW_LUE_INDEX_2__2		0x031A
-
-#define REG_SW_LUE_UNK_UCAST_CTRL__4	0x0320
-
-#define SW_UNK_UCAST_ENABLE		BIT(31)
-
-#define REG_SW_LUE_UNK_MCAST_CTRL__4	0x0324
-
-#define SW_UNK_MCAST_ENABLE		BIT(31)
-
-#define REG_SW_LUE_UNK_VID_CTRL__4	0x0328
-
-#define SW_UNK_VID_ENABLE		BIT(31)
-
-#define REG_SW_MAC_CTRL_0		0x0330
-
-#define SW_NEW_BACKOFF			BIT(7)
-#define SW_CHECK_LENGTH			BIT(3)
-#define SW_PAUSE_UNH_MODE		BIT(1)
-#define SW_AGGR_BACKOFF			BIT(0)
-
-#define REG_SW_MAC_CTRL_1		0x0331
-
-#define MULTICAST_STORM_DISABLE		BIT(6)
-#define SW_BACK_PRESSURE		BIT(5)
-#define FAIR_FLOW_CTRL			BIT(4)
-#define NO_EXC_COLLISION_DROP		BIT(3)
-#define SW_JUMBO_PACKET			BIT(2)
-#define SW_LEGAL_PACKET_DISABLE		BIT(1)
-#define SW_PASS_SHORT_FRAME		BIT(0)
-
-#define REG_SW_MAC_CTRL_2		0x0332
-
-#define SW_REPLACE_VID			BIT(3)
-#define BROADCAST_STORM_RATE_HI		0x07
-
-#define REG_SW_MAC_CTRL_3		0x0333
-
-#define BROADCAST_STORM_RATE_LO		0xFF
-#define BROADCAST_STORM_RATE		0x07FF
-
-#define REG_SW_MAC_CTRL_4		0x0334
-
-#define SW_PASS_PAUSE			BIT(3)
-
-#define REG_SW_MAC_CTRL_5		0x0335
-
-#define SW_OUT_RATE_LIMIT_QUEUE_BASED	BIT(3)
-
-#define REG_SW_MAC_CTRL_6		0x0336
-
-#define SW_MIB_COUNTER_FLUSH		BIT(7)
-#define SW_MIB_COUNTER_FREEZE		BIT(6)
-
-#define REG_SW_MAC_802_1P_MAP_0		0x0338
-#define REG_SW_MAC_802_1P_MAP_1		0x0339
-#define REG_SW_MAC_802_1P_MAP_2		0x033A
-#define REG_SW_MAC_802_1P_MAP_3		0x033B
-
-#define SW_802_1P_MAP_M			KS_PRIO_M
-#define SW_802_1P_MAP_S			KS_PRIO_S
-
-#define REG_SW_MAC_ISP_CTRL		0x033C
-
-#define REG_SW_MAC_TOS_CTRL		0x033E
-
-#define SW_TOS_DSCP_REMARK		BIT(1)
-#define SW_TOS_DSCP_REMAP		BIT(0)
-
-#define REG_SW_MAC_TOS_PRIO_0		0x0340
-#define REG_SW_MAC_TOS_PRIO_1		0x0341
-#define REG_SW_MAC_TOS_PRIO_2		0x0342
-#define REG_SW_MAC_TOS_PRIO_3		0x0343
-#define REG_SW_MAC_TOS_PRIO_4		0x0344
-#define REG_SW_MAC_TOS_PRIO_5		0x0345
-#define REG_SW_MAC_TOS_PRIO_6		0x0346
-#define REG_SW_MAC_TOS_PRIO_7		0x0347
-#define REG_SW_MAC_TOS_PRIO_8		0x0348
-#define REG_SW_MAC_TOS_PRIO_9		0x0349
-#define REG_SW_MAC_TOS_PRIO_10		0x034A
-#define REG_SW_MAC_TOS_PRIO_11		0x034B
-#define REG_SW_MAC_TOS_PRIO_12		0x034C
-#define REG_SW_MAC_TOS_PRIO_13		0x034D
-#define REG_SW_MAC_TOS_PRIO_14		0x034E
-#define REG_SW_MAC_TOS_PRIO_15		0x034F
-#define REG_SW_MAC_TOS_PRIO_16		0x0350
-#define REG_SW_MAC_TOS_PRIO_17		0x0351
-#define REG_SW_MAC_TOS_PRIO_18		0x0352
-#define REG_SW_MAC_TOS_PRIO_19		0x0353
-#define REG_SW_MAC_TOS_PRIO_20		0x0354
-#define REG_SW_MAC_TOS_PRIO_21		0x0355
-#define REG_SW_MAC_TOS_PRIO_22		0x0356
-#define REG_SW_MAC_TOS_PRIO_23		0x0357
-#define REG_SW_MAC_TOS_PRIO_24		0x0358
-#define REG_SW_MAC_TOS_PRIO_25		0x0359
-#define REG_SW_MAC_TOS_PRIO_26		0x035A
-#define REG_SW_MAC_TOS_PRIO_27		0x035B
-#define REG_SW_MAC_TOS_PRIO_28		0x035C
-#define REG_SW_MAC_TOS_PRIO_29		0x035D
-#define REG_SW_MAC_TOS_PRIO_30		0x035E
-#define REG_SW_MAC_TOS_PRIO_31		0x035F
-
-#define REG_SW_MRI_CTRL_0		0x0370
-
-#define SW_IGMP_SNOOP			BIT(6)
-#define SW_IPV6_MLD_OPTION		BIT(3)
-#define SW_IPV6_MLD_SNOOP		BIT(2)
-#define SW_MIRROR_RX_TX			BIT(0)
-
-#define REG_SW_CLASS_D_IP_CTRL__4	0x0374
-
-#define SW_CLASS_D_IP_ENABLE		BIT(31)
-
-#define REG_SW_MRI_CTRL_8		0x0378
-
-#define SW_NO_COLOR_S			6
-#define SW_RED_COLOR_S			4
-#define SW_YELLOW_COLOR_S		2
-#define SW_GREEN_COLOR_S		0
-#define SW_COLOR_M			0x3
-
-#define REG_SW_QM_CTRL__4		0x0390
-
-#define PRIO_SCHEME_SELECT_M		KS_PRIO_M
-#define PRIO_SCHEME_SELECT_S		6
-#define PRIO_MAP_3_HI			0
-#define PRIO_MAP_2_HI			2
-#define PRIO_MAP_0_LO			3
-#define UNICAST_VLAN_BOUNDARY		BIT(1)
-
-#define REG_SW_EEE_QM_CTRL__2		0x03C0
-
-#define REG_SW_EEE_TXQ_WAIT_TIME__2	0x03C2
-
-/* 4 - */
-#define REG_SW_VLAN_ENTRY__4		0x0400
-
-#define VLAN_VALID			BIT(31)
-#define VLAN_FORWARD_OPTION		BIT(27)
-#define VLAN_PRIO_M			KS_PRIO_M
-#define VLAN_PRIO_S			24
-#define VLAN_MSTP_M			0x7
-#define VLAN_MSTP_S			12
-#define VLAN_FID_M			0x7F
-
-#define REG_SW_VLAN_ENTRY_UNTAG__4	0x0404
-#define REG_SW_VLAN_ENTRY_PORTS__4	0x0408
-
-#define REG_SW_VLAN_ENTRY_INDEX__2	0x040C
-
-#define VLAN_INDEX_M			0x0FFF
-
-#define REG_SW_VLAN_CTRL		0x040E
-
-#define VLAN_START			BIT(7)
-#define VLAN_ACTION			0x3
-#define VLAN_WRITE			1
-#define VLAN_READ			2
-#define VLAN_CLEAR			3
-
-#define REG_SW_ALU_INDEX_0		0x0410
-
-#define ALU_FID_INDEX_S			16
-#define ALU_MAC_ADDR_HI			0xFFFF
-
-#define REG_SW_ALU_INDEX_1		0x0414
-
-#define ALU_DIRECT_INDEX_M		(BIT(12) - 1)
-
-#define REG_SW_ALU_CTRL__4		0x0418
-
-#define ALU_VALID_CNT_M			(BIT(14) - 1)
-#define ALU_VALID_CNT_S			16
-#define ALU_START			BIT(7)
-#define ALU_VALID			BIT(6)
-#define ALU_DIRECT			BIT(2)
-#define ALU_ACTION			0x3
-#define ALU_WRITE			1
-#define ALU_READ			2
-#define ALU_SEARCH			3
-
-#define REG_SW_ALU_STAT_CTRL__4		0x041C
-
-#define ALU_STAT_INDEX_M		(BIT(4) - 1)
-#define ALU_STAT_INDEX_S		16
-#define ALU_RESV_MCAST_INDEX_M		(BIT(6) - 1)
-#define ALU_STAT_START			BIT(7)
-#define ALU_RESV_MCAST_ADDR		BIT(1)
-#define ALU_STAT_READ			BIT(0)
-
-#define REG_SW_ALU_VAL_A		0x0420
-
-#define ALU_V_STATIC_VALID		BIT(31)
-#define ALU_V_SRC_FILTER		BIT(30)
-#define ALU_V_DST_FILTER		BIT(29)
-#define ALU_V_PRIO_AGE_CNT_M		(BIT(3) - 1)
-#define ALU_V_PRIO_AGE_CNT_S		26
-#define ALU_V_MSTP_M			0x7
-
-#define REG_SW_ALU_VAL_B		0x0424
-
-#define ALU_V_OVERRIDE			BIT(31)
-#define ALU_V_USE_FID			BIT(30)
-#define ALU_V_PORT_MAP			(BIT(24) - 1)
-
-#define REG_SW_ALU_VAL_C		0x0428
-
-#define ALU_V_FID_M			(BIT(16) - 1)
-#define ALU_V_FID_S			16
-#define ALU_V_MAC_ADDR_HI		0xFFFF
-
-#define REG_SW_ALU_VAL_D		0x042C
-
-#define REG_HSR_ALU_INDEX_0		0x0440
-
-#define REG_HSR_ALU_INDEX_1		0x0444
-
-#define HSR_DST_MAC_INDEX_LO_S		16
-#define HSR_SRC_MAC_INDEX_HI		0xFFFF
-
-#define REG_HSR_ALU_INDEX_2		0x0448
-
-#define HSR_INDEX_MAX			BIT(9)
-#define HSR_DIRECT_INDEX_M		(HSR_INDEX_MAX - 1)
-
-#define REG_HSR_ALU_INDEX_3		0x044C
-
-#define HSR_PATH_INDEX_M		(BIT(4) - 1)
-
-#define REG_HSR_ALU_CTRL__4		0x0450
-
-#define HSR_VALID_CNT_M			(BIT(14) - 1)
-#define HSR_VALID_CNT_S			16
-#define HSR_START			BIT(7)
-#define HSR_VALID			BIT(6)
-#define HSR_SEARCH_END			BIT(5)
-#define HSR_DIRECT			BIT(2)
-#define HSR_ACTION			0x3
-#define HSR_WRITE			1
-#define HSR_READ			2
-#define HSR_SEARCH			3
-
-#define REG_HSR_ALU_VAL_A		0x0454
-
-#define HSR_V_STATIC_VALID		BIT(31)
-#define HSR_V_AGE_CNT_M			(BIT(3) - 1)
-#define HSR_V_AGE_CNT_S			26
-#define HSR_V_PATH_ID_M			(BIT(4) - 1)
-
-#define REG_HSR_ALU_VAL_B		0x0458
-
-#define REG_HSR_ALU_VAL_C		0x045C
-
-#define HSR_V_DST_MAC_ADDR_LO_S		16
-#define HSR_V_SRC_MAC_ADDR_HI		0xFFFF
-
-#define REG_HSR_ALU_VAL_D		0x0460
-
-#define REG_HSR_ALU_VAL_E		0x0464
-
-#define HSR_V_START_SEQ_1_S		16
-#define HSR_V_START_SEQ_2_S		0
-
-#define REG_HSR_ALU_VAL_F		0x0468
-
-#define HSR_V_EXP_SEQ_1_S		16
-#define HSR_V_EXP_SEQ_2_S		0
-
-#define REG_HSR_ALU_VAL_G		0x046C
-
-#define HSR_V_SEQ_CNT_1_S		16
-#define HSR_V_SEQ_CNT_2_S		0
-
-#define HSR_V_SEQ_M			(BIT(16) - 1)
-
-/* 5 - PTP Clock */
-#define REG_PTP_CLK_CTRL		0x0500
-
-#define PTP_STEP_ADJ			BIT(6)
-#define PTP_STEP_DIR			BIT(5)
-#define PTP_READ_TIME			BIT(4)
-#define PTP_LOAD_TIME			BIT(3)
-#define PTP_CLK_ADJ_ENABLE		BIT(2)
-#define PTP_CLK_ENABLE			BIT(1)
-#define PTP_CLK_RESET			BIT(0)
-
-#define REG_PTP_RTC_SUB_NANOSEC__2	0x0502
-
-#define PTP_RTC_SUB_NANOSEC_M		0x0007
-
-#define REG_PTP_RTC_NANOSEC		0x0504
-#define REG_PTP_RTC_NANOSEC_H		0x0504
-#define REG_PTP_RTC_NANOSEC_L		0x0506
-
-#define REG_PTP_RTC_SEC			0x0508
-#define REG_PTP_RTC_SEC_H		0x0508
-#define REG_PTP_RTC_SEC_L		0x050A
-
-#define REG_PTP_SUBNANOSEC_RATE		0x050C
-#define REG_PTP_SUBNANOSEC_RATE_H	0x050C
-
-#define PTP_RATE_DIR			BIT(31)
-#define PTP_TMP_RATE_ENABLE		BIT(30)
-
-#define REG_PTP_SUBNANOSEC_RATE_L	0x050E
-
-#define REG_PTP_RATE_DURATION		0x0510
-#define REG_PTP_RATE_DURATION_H		0x0510
-#define REG_PTP_RATE_DURATION_L		0x0512
-
-#define REG_PTP_MSG_CONF1		0x0514
-
-#define PTP_802_1AS			BIT(7)
-#define PTP_ENABLE			BIT(6)
-#define PTP_ETH_ENABLE			BIT(5)
-#define PTP_IPV4_UDP_ENABLE		BIT(4)
-#define PTP_IPV6_UDP_ENABLE		BIT(3)
-#define PTP_TC_P2P			BIT(2)
-#define PTP_MASTER			BIT(1)
-#define PTP_1STEP			BIT(0)
-
-#define REG_PTP_MSG_CONF2		0x0516
-
-#define PTP_UNICAST_ENABLE		BIT(12)
-#define PTP_ALTERNATE_MASTER		BIT(11)
-#define PTP_ALL_HIGH_PRIO		BIT(10)
-#define PTP_SYNC_CHECK			BIT(9)
-#define PTP_DELAY_CHECK			BIT(8)
-#define PTP_PDELAY_CHECK		BIT(7)
-#define PTP_DROP_SYNC_DELAY_REQ		BIT(5)
-#define PTP_DOMAIN_CHECK		BIT(4)
-#define PTP_UDP_CHECKSUM		BIT(2)
-
-#define REG_PTP_DOMAIN_VERSION		0x0518
-#define PTP_VERSION_M			0xFF00
-#define PTP_DOMAIN_M			0x00FF
-
-#define REG_PTP_UNIT_INDEX__4		0x0520
-
-#define PTP_UNIT_M			0xF
-
-#define PTP_GPIO_INDEX_S		16
-#define PTP_TSI_INDEX_S			8
-#define PTP_TOU_INDEX_S			0
-
-#define REG_PTP_TRIG_STATUS__4		0x0524
-
-#define TRIG_ERROR_S			16
-#define TRIG_DONE_S			0
-
-#define REG_PTP_INT_STATUS__4		0x0528
-
-#define TRIG_INT_S			16
-#define TS_INT_S			0
-
-#define TRIG_UNIT_M			0x7
-#define TS_UNIT_M			0x3
-
-#define REG_PTP_CTRL_STAT__4		0x052C
-
-#define GPIO_IN				BIT(7)
-#define GPIO_OUT			BIT(6)
-#define TS_INT_ENABLE			BIT(5)
-#define TRIG_ACTIVE			BIT(4)
-#define TRIG_ENABLE			BIT(3)
-#define TRIG_RESET			BIT(2)
-#define TS_ENABLE			BIT(1)
-#define TS_RESET			BIT(0)
-
-#define GPIO_CTRL_M			(GPIO_IN | GPIO_OUT)
-
-#define TRIG_CTRL_M			\
-	(TRIG_ACTIVE | TRIG_ENABLE | TRIG_RESET)
-
-#define TS_CTRL_M			\
-	(TS_INT_ENABLE | TS_ENABLE | TS_RESET)
-
-#define REG_TRIG_TARGET_NANOSEC		0x0530
-#define REG_TRIG_TARGET_SEC		0x0534
-
-#define REG_TRIG_CTRL__4		0x0538
-
-#define TRIG_CASCADE_ENABLE		BIT(31)
-#define TRIG_CASCADE_TAIL		BIT(30)
-#define TRIG_CASCADE_UPS_M		0xF
-#define TRIG_CASCADE_UPS_S		26
-#define TRIG_NOW			BIT(25)
-#define TRIG_NOTIFY			BIT(24)
-#define TRIG_EDGE			BIT(23)
-#define TRIG_PATTERN_S			20
-#define TRIG_PATTERN_M			0x7
-#define TRIG_NEG_EDGE			0
-#define TRIG_POS_EDGE			1
-#define TRIG_NEG_PULSE			2
-#define TRIG_POS_PULSE			3
-#define TRIG_NEG_PERIOD			4
-#define TRIG_POS_PERIOD			5
-#define TRIG_REG_OUTPUT			6
-#define TRIG_GPO_S			16
-#define TRIG_GPO_M			0xF
-#define TRIG_CASCADE_ITERATE_CNT_M	0xFFFF
-
-#define REG_TRIG_CYCLE_WIDTH		0x053C
-
-#define REG_TRIG_CYCLE_CNT		0x0540
-
-#define TRIG_CYCLE_CNT_M		0xFFFF
-#define TRIG_CYCLE_CNT_S		16
-#define TRIG_BIT_PATTERN_M		0xFFFF
-
-#define REG_TRIG_ITERATE_TIME		0x0544
-
-#define REG_TRIG_PULSE_WIDTH__4		0x0548
-
-#define TRIG_PULSE_WIDTH_M		0x00FFFFFF
-
-#define REG_TS_CTRL_STAT__4		0x0550
-
-#define TS_EVENT_DETECT_M		0xF
-#define TS_EVENT_DETECT_S		17
-#define TS_EVENT_OVERFLOW		BIT(16)
-#define TS_GPI_M			0xF
-#define TS_GPI_S			8
-#define TS_DETECT_RISE			BIT(7)
-#define TS_DETECT_FALL			BIT(6)
-#define TS_DETECT_S			6
-#define TS_CASCADE_TAIL			BIT(5)
-#define TS_CASCADE_UPS_M		0xF
-#define TS_CASCADE_UPS_S		1
-#define TS_CASCADE_ENABLE		BIT(0)
-
-#define DETECT_RISE			(TS_DETECT_RISE >> TS_DETECT_S)
-#define DETECT_FALL			(TS_DETECT_FALL >> TS_DETECT_S)
-
-#define REG_TS_EVENT_0_NANOSEC		0x0554
-#define REG_TS_EVENT_0_SEC		0x0558
-#define REG_TS_EVENT_0_SUB_NANOSEC	0x055C
-
-#define REG_TS_EVENT_1_NANOSEC		0x0560
-#define REG_TS_EVENT_1_SEC		0x0564
-#define REG_TS_EVENT_1_SUB_NANOSEC	0x0568
-
-#define REG_TS_EVENT_2_NANOSEC		0x056C
-#define REG_TS_EVENT_2_SEC		0x0570
-#define REG_TS_EVENT_2_SUB_NANOSEC	0x0574
-
-#define REG_TS_EVENT_3_NANOSEC		0x0578
-#define REG_TS_EVENT_3_SEC		0x057C
-#define REG_TS_EVENT_3_SUB_NANOSEC	0x0580
-
-#define REG_TS_EVENT_4_NANOSEC		0x0584
-#define REG_TS_EVENT_4_SEC		0x0588
-#define REG_TS_EVENT_4_SUB_NANOSEC	0x058C
-
-#define REG_TS_EVENT_5_NANOSEC		0x0590
-#define REG_TS_EVENT_5_SEC		0x0594
-#define REG_TS_EVENT_5_SUB_NANOSEC	0x0598
-
-#define REG_TS_EVENT_6_NANOSEC		0x059C
-#define REG_TS_EVENT_6_SEC		0x05A0
-#define REG_TS_EVENT_6_SUB_NANOSEC	0x05A4
-
-#define REG_TS_EVENT_7_NANOSEC		0x05A8
-#define REG_TS_EVENT_7_SEC		0x05AC
-#define REG_TS_EVENT_7_SUB_NANOSEC	0x05B0
-
-#define TS_EVENT_EDGE_M			0x1
-#define TS_EVENT_EDGE_S			30
-#define TS_EVENT_NANOSEC_M		(BIT(30) - 1)
-
-#define TS_EVENT_SUB_NANOSEC_M		0x7
-
-#define TS_EVENT_SAMPLE			\
-	(REG_TS_EVENT_1_NANOSEC - REG_TS_EVENT_0_NANOSEC)
-
-#define PORT_CTRL_ADDR(port, addr)	((addr) | (((port) + 1) << 12))
-
-#define REG_GLOBAL_RR_INDEX__1		0x0600
-
-/* DLR */
-#define REG_DLR_SRC_PORT__4		0x0604
-
-#define DLR_SRC_PORT_UNICAST		BIT(31)
-#define DLR_SRC_PORT_M			0x3
-#define DLR_SRC_PORT_BOTH		0
-#define DLR_SRC_PORT_EACH		1
-
-#define REG_DLR_IP_ADDR__4		0x0608
-
-#define REG_DLR_CTRL__1			0x0610
-
-#define DLR_RESET_SEQ_ID		BIT(3)
-#define DLR_BACKUP_AUTO_ON		BIT(2)
-#define DLR_BEACON_TX_ENABLE		BIT(1)
-#define DLR_ASSIST_ENABLE		BIT(0)
-
-#define REG_DLR_STATE__1		0x0611
-
-#define DLR_NODE_STATE_M		0x3
-#define DLR_NODE_STATE_S		1
-#define DLR_NODE_STATE_IDLE		0
-#define DLR_NODE_STATE_FAULT		1
-#define DLR_NODE_STATE_NORMAL		2
-#define DLR_RING_STATE_FAULT		0
-#define DLR_RING_STATE_NORMAL		1
-
-#define REG_DLR_PRECEDENCE__1		0x0612
-
-#define REG_DLR_BEACON_INTERVAL__4	0x0614
-
-#define REG_DLR_BEACON_TIMEOUT__4	0x0618
-
-#define REG_DLR_TIMEOUT_WINDOW__4	0x061C
-
-#define DLR_TIMEOUT_WINDOW_M		(BIT(22) - 1)
-
-#define REG_DLR_VLAN_ID__2		0x0620
-
-#define DLR_VLAN_ID_M			(BIT(12) - 1)
-
-#define REG_DLR_DEST_ADDR_0		0x0622
-#define REG_DLR_DEST_ADDR_1		0x0623
-#define REG_DLR_DEST_ADDR_2		0x0624
-#define REG_DLR_DEST_ADDR_3		0x0625
-#define REG_DLR_DEST_ADDR_4		0x0626
-#define REG_DLR_DEST_ADDR_5		0x0627
-
-#define REG_DLR_PORT_MAP__4		0x0628
-
-#define REG_DLR_CLASS__1		0x062C
-
-#define DLR_FRAME_QID_M			0x3
-
-/* HSR */
-#define REG_HSR_PORT_MAP__4		0x0640
-
-#define REG_HSR_ALU_CTRL_0__1		0x0644
-
-#define HSR_DUPLICATE_DISCARD		BIT(7)
-#define HSR_NODE_UNICAST		BIT(6)
-#define HSR_AGE_CNT_DEFAULT_M		0x7
-#define HSR_AGE_CNT_DEFAULT_S		3
-#define HSR_LEARN_MCAST_DISABLE		BIT(2)
-#define HSR_HASH_OPTION_M		0x3
-#define HSR_HASH_DISABLE		0
-#define HSR_HASH_UPPER_BITS		1
-#define HSR_HASH_LOWER_BITS		2
-#define HSR_HASH_XOR_BOTH_BITS		3
-
-#define REG_HSR_ALU_CTRL_1__1		0x0645
-
-#define HSR_LEARN_UCAST_DISABLE		BIT(7)
-#define HSR_FLUSH_TABLE			BIT(5)
-#define HSR_PROC_MCAST_SRC		BIT(3)
-#define HSR_AGING_ENABLE		BIT(2)
-
-#define REG_HSR_ALU_CTRL_2__2		0x0646
-
-#define REG_HSR_ALU_AGE_PERIOD__4	0x0648
-
-#define REG_HSR_ALU_INT_STATUS__1	0x064C
-#define REG_HSR_ALU_INT_MASK__1		0x064D
-
-#define HSR_WINDOW_OVERFLOW_INT		BIT(3)
-#define HSR_LEARN_FAIL_INT		BIT(2)
-#define HSR_ALMOST_FULL_INT		BIT(1)
-#define HSR_WRITE_FAIL_INT		BIT(0)
-
-#define REG_HSR_ALU_ENTRY_0__2		0x0650
-
-#define HSR_ENTRY_INDEX_M		(BIT(10) - 1)
-#define HSR_FAIL_INDEX_M		(BIT(8) - 1)
-
-#define REG_HSR_ALU_ENTRY_1__2		0x0652
-
-#define HSR_FAIL_LEARN_INDEX_M		(BIT(8) - 1)
-
-#define REG_HSR_ALU_ENTRY_3__2		0x0654
-
-#define HSR_CPU_ACCESS_ENTRY_INDEX_M	(BIT(8) - 1)
-
-/* 0 - Operation */
-#define REG_PORT_DEFAULT_VID		0x0000
-
-#define REG_PORT_CUSTOM_VID		0x0002
-#define REG_PORT_AVB_SR_1_VID		0x0004
-#define REG_PORT_AVB_SR_2_VID		0x0006
-
-#define REG_PORT_AVB_SR_1_TYPE		0x0008
-#define REG_PORT_AVB_SR_2_TYPE		0x000A
-
-#define REG_PORT_PME_STATUS		0x0013
-#define REG_PORT_PME_CTRL		0x0017
-
-#define PME_WOL_MAGICPKT		BIT(2)
-#define PME_WOL_LINKUP			BIT(1)
-#define PME_WOL_ENERGY			BIT(0)
-
-#define REG_PORT_INT_STATUS		0x001B
-#define REG_PORT_INT_MASK		0x001F
-
-#define PORT_SGMII_INT			BIT(3)
-#define PORT_PTP_INT			BIT(2)
-#define PORT_PHY_INT			BIT(1)
-#define PORT_ACL_INT			BIT(0)
-
-#define PORT_INT_MASK			\
-	(PORT_SGMII_INT | PORT_PTP_INT | PORT_PHY_INT | PORT_ACL_INT)
-
-#define REG_PORT_CTRL_0			0x0020
-
-#define PORT_MAC_LOOPBACK		BIT(7)
-#define PORT_FORCE_TX_FLOW_CTRL		BIT(4)
-#define PORT_FORCE_RX_FLOW_CTRL		BIT(3)
-#define PORT_TAIL_TAG_ENABLE		BIT(2)
-#define PORT_QUEUE_SPLIT_ENABLE		0x3
-
-#define REG_PORT_CTRL_1			0x0021
-
-#define PORT_SRP_ENABLE			0x3
-
-#define REG_PORT_STATUS_0		0x0030
-
-#define PORT_INTF_SPEED_M		0x3
-#define PORT_INTF_SPEED_S		3
-#define PORT_INTF_FULL_DUPLEX		BIT(2)
-#define PORT_TX_FLOW_CTRL		BIT(1)
-#define PORT_RX_FLOW_CTRL		BIT(0)
-
-#define REG_PORT_STATUS_1		0x0034
-
-/* 1 - PHY */
-#define REG_PORT_PHY_CTRL		0x0100
-
-#define PORT_PHY_RESET			BIT(15)
-#define PORT_PHY_LOOPBACK		BIT(14)
-#define PORT_SPEED_100MBIT		BIT(13)
-#define PORT_AUTO_NEG_ENABLE		BIT(12)
-#define PORT_POWER_DOWN			BIT(11)
-#define PORT_ISOLATE			BIT(10)
-#define PORT_AUTO_NEG_RESTART		BIT(9)
-#define PORT_FULL_DUPLEX		BIT(8)
-#define PORT_COLLISION_TEST		BIT(7)
-#define PORT_SPEED_1000MBIT		BIT(6)
-
-#define REG_PORT_PHY_STATUS		0x0102
-
-#define PORT_100BT4_CAPABLE		BIT(15)
-#define PORT_100BTX_FD_CAPABLE		BIT(14)
-#define PORT_100BTX_CAPABLE		BIT(13)
-#define PORT_10BT_FD_CAPABLE		BIT(12)
-#define PORT_10BT_CAPABLE		BIT(11)
-#define PORT_EXTENDED_STATUS		BIT(8)
-#define PORT_MII_SUPPRESS_CAPABLE	BIT(6)
-#define PORT_AUTO_NEG_ACKNOWLEDGE	BIT(5)
-#define PORT_REMOTE_FAULT		BIT(4)
-#define PORT_AUTO_NEG_CAPABLE		BIT(3)
-#define PORT_LINK_STATUS		BIT(2)
-#define PORT_JABBER_DETECT		BIT(1)
-#define PORT_EXTENDED_CAPABILITY	BIT(0)
-
-#define REG_PORT_PHY_ID_HI		0x0104
-#define REG_PORT_PHY_ID_LO		0x0106
-
-#define KSZ9477_ID_HI			0x0022
-#define KSZ9477_ID_LO			0x1622
-
-#define REG_PORT_PHY_AUTO_NEGOTIATION	0x0108
-
-#define PORT_AUTO_NEG_NEXT_PAGE		BIT(15)
-#define PORT_AUTO_NEG_REMOTE_FAULT	BIT(13)
-#define PORT_AUTO_NEG_ASYM_PAUSE	BIT(11)
-#define PORT_AUTO_NEG_SYM_PAUSE		BIT(10)
-#define PORT_AUTO_NEG_100BT4		BIT(9)
-#define PORT_AUTO_NEG_100BTX_FD		BIT(8)
-#define PORT_AUTO_NEG_100BTX		BIT(7)
-#define PORT_AUTO_NEG_10BT_FD		BIT(6)
-#define PORT_AUTO_NEG_10BT		BIT(5)
-#define PORT_AUTO_NEG_SELECTOR		0x001F
-#define PORT_AUTO_NEG_802_3		0x0001
-
-#define PORT_AUTO_NEG_PAUSE		\
-	(PORT_AUTO_NEG_ASYM_PAUSE | PORT_AUTO_NEG_SYM_PAUSE)
-
-#define REG_PORT_PHY_REMOTE_CAPABILITY	0x010A
-
-#define PORT_REMOTE_NEXT_PAGE		BIT(15)
-#define PORT_REMOTE_ACKNOWLEDGE		BIT(14)
-#define PORT_REMOTE_REMOTE_FAULT	BIT(13)
-#define PORT_REMOTE_ASYM_PAUSE		BIT(11)
-#define PORT_REMOTE_SYM_PAUSE		BIT(10)
-#define PORT_REMOTE_100BTX_FD		BIT(8)
-#define PORT_REMOTE_100BTX		BIT(7)
-#define PORT_REMOTE_10BT_FD		BIT(6)
-#define PORT_REMOTE_10BT		BIT(5)
-
-#define REG_PORT_PHY_1000_CTRL		0x0112
-
-#define PORT_AUTO_NEG_MANUAL		BIT(12)
-#define PORT_AUTO_NEG_MASTER		BIT(11)
-#define PORT_AUTO_NEG_MASTER_PREFERRED	BIT(10)
-#define PORT_AUTO_NEG_1000BT_FD		BIT(9)
-#define PORT_AUTO_NEG_1000BT		BIT(8)
-
-#define REG_PORT_PHY_1000_STATUS	0x0114
-
-#define PORT_MASTER_FAULT		BIT(15)
-#define PORT_LOCAL_MASTER		BIT(14)
-#define PORT_LOCAL_RX_OK		BIT(13)
-#define PORT_REMOTE_RX_OK		BIT(12)
-#define PORT_REMOTE_1000BT_FD		BIT(11)
-#define PORT_REMOTE_1000BT		BIT(10)
-#define PORT_REMOTE_IDLE_CNT_M		0x0F
-
-#define PORT_PHY_1000_STATIC_STATUS	\
-	(PORT_LOCAL_RX_OK |		\
-	PORT_REMOTE_RX_OK |		\
-	PORT_REMOTE_1000BT_FD |		\
-	PORT_REMOTE_1000BT)
-
-#define REG_PORT_PHY_MMD_SETUP		0x011A
-
-#define PORT_MMD_OP_MODE_M		0x3
-#define PORT_MMD_OP_MODE_S		14
-#define PORT_MMD_OP_INDEX		0
-#define PORT_MMD_OP_DATA_NO_INCR	1
-#define PORT_MMD_OP_DATA_INCR_RW	2
-#define PORT_MMD_OP_DATA_INCR_W		3
-#define PORT_MMD_DEVICE_ID_M		0x1F
-
-#define MMD_SETUP(mode, dev)		\
-	(((u16)(mode) << PORT_MMD_OP_MODE_S) | (dev))
-
-#define REG_PORT_PHY_MMD_INDEX_DATA	0x011C
-
-#define MMD_DEVICE_ID_DSP		1
-
-#define MMD_DSP_SQI_CHAN_A		0xAC
-#define MMD_DSP_SQI_CHAN_B		0xAD
-#define MMD_DSP_SQI_CHAN_C		0xAE
-#define MMD_DSP_SQI_CHAN_D		0xAF
-
-#define DSP_SQI_ERR_DETECTED		BIT(15)
-#define DSP_SQI_AVG_ERR			0x7FFF
-
-#define MMD_DEVICE_ID_COMMON		2
-
-#define MMD_DEVICE_ID_EEE_ADV		7
-
-#define MMD_EEE_ADV			0x3C
-#define EEE_ADV_100MBIT			BIT(1)
-#define EEE_ADV_1GBIT			BIT(2)
-
-#define MMD_EEE_LP_ADV			0x3D
-#define MMD_EEE_MSG_CODE		0x3F
-
-#define MMD_DEVICE_ID_AFED		0x1C
-
-#define REG_PORT_PHY_EXTENDED_STATUS	0x011E
-
-#define PORT_100BTX_FD_ABLE		BIT(15)
-#define PORT_100BTX_ABLE		BIT(14)
-#define PORT_10BT_FD_ABLE		BIT(13)
-#define PORT_10BT_ABLE			BIT(12)
-
-#define REG_PORT_SGMII_ADDR__4		0x0200
-#define PORT_SGMII_AUTO_INCR		BIT(23)
-#define PORT_SGMII_DEVICE_ID_M		0x1F
-#define PORT_SGMII_DEVICE_ID_S		16
-#define PORT_SGMII_ADDR_M		(BIT(21) - 1)
-
-#define REG_PORT_SGMII_DATA__4		0x0204
-#define PORT_SGMII_DATA_M		(BIT(16) - 1)
-
-#define MMD_DEVICE_ID_PMA		0x01
-#define MMD_DEVICE_ID_PCS		0x03
-#define MMD_DEVICE_ID_PHY_XS		0x04
-#define MMD_DEVICE_ID_DTE_XS		0x05
-#define MMD_DEVICE_ID_AN		0x07
-#define MMD_DEVICE_ID_VENDOR_CTRL	0x1E
-#define MMD_DEVICE_ID_VENDOR_MII	0x1F
-
-#define SR_MII				MMD_DEVICE_ID_VENDOR_MII
-
-#define MMD_SR_MII_CTRL			0x0000
-
-#define SR_MII_RESET			BIT(15)
-#define SR_MII_LOOPBACK			BIT(14)
-#define SR_MII_SPEED_100MBIT		BIT(13)
-#define SR_MII_AUTO_NEG_ENABLE		BIT(12)
-#define SR_MII_POWER_DOWN		BIT(11)
-#define SR_MII_AUTO_NEG_RESTART		BIT(9)
-#define SR_MII_FULL_DUPLEX		BIT(8)
-#define SR_MII_SPEED_1000MBIT		BIT(6)
-
-#define MMD_SR_MII_STATUS		0x0001
-#define MMD_SR_MII_ID_1			0x0002
-#define MMD_SR_MII_ID_2			0x0003
-#define MMD_SR_MII_AUTO_NEGOTIATION	0x0004
-
-#define SR_MII_AUTO_NEG_NEXT_PAGE	BIT(15)
-#define SR_MII_AUTO_NEG_REMOTE_FAULT_M	0x3
-#define SR_MII_AUTO_NEG_REMOTE_FAULT_S	12
-#define SR_MII_AUTO_NEG_NO_ERROR	0
-#define SR_MII_AUTO_NEG_OFFLINE		1
-#define SR_MII_AUTO_NEG_LINK_FAILURE	2
-#define SR_MII_AUTO_NEG_ERROR		3
-#define SR_MII_AUTO_NEG_PAUSE_M		0x3
-#define SR_MII_AUTO_NEG_PAUSE_S		7
-#define SR_MII_AUTO_NEG_NO_PAUSE	0
-#define SR_MII_AUTO_NEG_ASYM_PAUSE_TX	1
-#define SR_MII_AUTO_NEG_SYM_PAUSE	2
-#define SR_MII_AUTO_NEG_ASYM_PAUSE_RX	3
-#define SR_MII_AUTO_NEG_HALF_DUPLEX	BIT(6)
-#define SR_MII_AUTO_NEG_FULL_DUPLEX	BIT(5)
-
-#define MMD_SR_MII_REMOTE_CAPABILITY	0x0005
-#define MMD_SR_MII_AUTO_NEG_EXP		0x0006
-#define MMD_SR_MII_AUTO_NEG_EXT		0x000F
-
-#define MMD_SR_MII_DIGITAL_CTRL_1	0x8000
-
-#define MMD_SR_MII_AUTO_NEG_CTRL	0x8001
-
-#define SR_MII_8_BIT			BIT(8)
-#define SR_MII_SGMII_LINK_UP		BIT(4)
-#define SR_MII_TX_CFG_PHY_MASTER	BIT(3)
-#define SR_MII_PCS_MODE_M		0x3
-#define SR_MII_PCS_MODE_S		1
-#define SR_MII_PCS_SGMII		2
-#define SR_MII_AUTO_NEG_COMPLETE_INTR	BIT(0)
-
-#define MMD_SR_MII_AUTO_NEG_STATUS	0x8002
-
-#define SR_MII_STAT_LINK_UP		BIT(4)
-#define SR_MII_STAT_M			0x3
-#define SR_MII_STAT_S			2
-#define SR_MII_STAT_10_MBPS		0
-#define SR_MII_STAT_100_MBPS		1
-#define SR_MII_STAT_1000_MBPS		2
-#define SR_MII_STAT_FULL_DUPLEX		BIT(1)
-
-#define MMD_SR_MII_PHY_CTRL		0x80A0
-
-#define SR_MII_PHY_LANE_SEL_M		0xF
-#define SR_MII_PHY_LANE_SEL_S		8
-#define SR_MII_PHY_WRITE		BIT(1)
-#define SR_MII_PHY_START_BUSY		BIT(0)
-
-#define MMD_SR_MII_PHY_ADDR		0x80A1
-
-#define SR_MII_PHY_ADDR_M		(BIT(16) - 1)
-
-#define MMD_SR_MII_PHY_DATA		0x80A2
-
-#define SR_MII_PHY_DATA_M		(BIT(16) - 1)
-
-#define SR_MII_PHY_JTAG_CHIP_ID_HI	0x000C
-#define SR_MII_PHY_JTAG_CHIP_ID_LO	0x000D
-
-#define REG_PORT_PHY_REMOTE_LB_LED	0x0122
-
-#define PORT_REMOTE_LOOPBACK		BIT(8)
-#define PORT_LED_SELECT			(3 << 6)
-#define PORT_LED_CTRL			(3 << 4)
-#define PORT_LED_CTRL_TEST		BIT(3)
-#define PORT_10BT_PREAMBLE		BIT(2)
-#define PORT_LINK_MD_10BT_ENABLE	BIT(1)
-#define PORT_LINK_MD_PASS		BIT(0)
-
-#define REG_PORT_PHY_LINK_MD		0x0124
-
-#define PORT_START_CABLE_DIAG		BIT(15)
-#define PORT_TX_DISABLE			BIT(14)
-#define PORT_CABLE_DIAG_PAIR_M		0x3
-#define PORT_CABLE_DIAG_PAIR_S		12
-#define PORT_CABLE_DIAG_SELECT_M	0x3
-#define PORT_CABLE_DIAG_SELECT_S	10
-#define PORT_CABLE_DIAG_RESULT_M	0x3
-#define PORT_CABLE_DIAG_RESULT_S	8
-#define PORT_CABLE_STAT_NORMAL		0
-#define PORT_CABLE_STAT_OPEN		1
-#define PORT_CABLE_STAT_SHORT		2
-#define PORT_CABLE_STAT_FAILED		3
-#define PORT_CABLE_FAULT_COUNTER	0x00FF
-
-#define REG_PORT_PHY_PMA_STATUS		0x0126
-
-#define PORT_1000_LINK_GOOD		BIT(1)
-#define PORT_100_LINK_GOOD		BIT(0)
-
-#define REG_PORT_PHY_DIGITAL_STATUS	0x0128
-
-#define PORT_LINK_DETECT		BIT(14)
-#define PORT_SIGNAL_DETECT		BIT(13)
-#define PORT_PHY_STAT_MDI		BIT(12)
-#define PORT_PHY_STAT_MASTER		BIT(11)
-
-#define REG_PORT_PHY_RXER_COUNTER	0x012A
-
-#define REG_PORT_PHY_INT_ENABLE		0x0136
-#define REG_PORT_PHY_INT_STATUS		0x0137
-
-#define JABBER_INT			BIT(7)
-#define RX_ERR_INT			BIT(6)
-#define PAGE_RX_INT			BIT(5)
-#define PARALLEL_DETECT_FAULT_INT	BIT(4)
-#define LINK_PARTNER_ACK_INT		BIT(3)
-#define LINK_DOWN_INT			BIT(2)
-#define REMOTE_FAULT_INT		BIT(1)
-#define LINK_UP_INT			BIT(0)
-
-#define REG_PORT_PHY_DIGITAL_DEBUG_1	0x0138
-
-#define PORT_REG_CLK_SPEED_25_MHZ	BIT(14)
-#define PORT_PHY_FORCE_MDI		BIT(7)
-#define PORT_PHY_AUTO_MDIX_DISABLE	BIT(6)
-
-/* Same as PORT_PHY_LOOPBACK */
-#define PORT_PHY_PCS_LOOPBACK		BIT(0)
-
-#define REG_PORT_PHY_DIGITAL_DEBUG_2	0x013A
-
-#define REG_PORT_PHY_DIGITAL_DEBUG_3	0x013C
-
-#define PORT_100BT_FIXED_LATENCY	BIT(15)
-
-#define REG_PORT_PHY_PHY_CTRL		0x013E
-
-#define PORT_INT_PIN_HIGH		BIT(14)
-#define PORT_ENABLE_JABBER		BIT(9)
-#define PORT_STAT_SPEED_1000MBIT	BIT(6)
-#define PORT_STAT_SPEED_100MBIT		BIT(5)
-#define PORT_STAT_SPEED_10MBIT		BIT(4)
-#define PORT_STAT_FULL_DUPLEX		BIT(3)
-
-/* Same as PORT_PHY_STAT_MASTER */
-#define PORT_STAT_MASTER		BIT(2)
-#define PORT_RESET			BIT(1)
-#define PORT_LINK_STATUS_FAIL		BIT(0)
-
-/* 3 - xMII */
-#define REG_PORT_XMII_CTRL_0		0x0300
-
-#define PORT_SGMII_SEL			BIT(7)
-#define PORT_MII_FULL_DUPLEX		BIT(6)
-#define PORT_MII_100MBIT		BIT(4)
-#define PORT_GRXC_ENABLE		BIT(0)
-
-#define REG_PORT_XMII_CTRL_1		0x0301
-
-#define PORT_RMII_CLK_SEL		BIT(7)
-/* S1 */
-#define PORT_MII_1000MBIT_S1		BIT(6)
-/* S2 */
-#define PORT_MII_NOT_1GBIT		BIT(6)
-#define PORT_MII_SEL_EDGE		BIT(5)
-#define PORT_RGMII_ID_IG_ENABLE		BIT(4)
-#define PORT_RGMII_ID_EG_ENABLE		BIT(3)
-#define PORT_MII_MAC_MODE		BIT(2)
-#define PORT_MII_SEL_M			0x3
-/* S1 */
-#define PORT_MII_SEL_S1			0x0
-#define PORT_RMII_SEL_S1		0x1
-#define PORT_GMII_SEL_S1		0x2
-#define PORT_RGMII_SEL_S1		0x3
-/* S2 */
-#define PORT_RGMII_SEL			0x0
-#define PORT_RMII_SEL			0x1
-#define PORT_GMII_SEL			0x2
-#define PORT_MII_SEL			0x3
-
-/* 4 - MAC */
-#define REG_PORT_MAC_CTRL_0		0x0400
-
-#define PORT_BROADCAST_STORM		BIT(1)
-#define PORT_JUMBO_FRAME		BIT(0)
-
-#define REG_PORT_MAC_CTRL_1		0x0401
-
-#define PORT_BACK_PRESSURE		BIT(3)
-#define PORT_PASS_ALL			BIT(0)
-
-#define REG_PORT_MAC_CTRL_2		0x0402
-
-#define PORT_100BT_EEE_DISABLE		BIT(7)
-#define PORT_1000BT_EEE_DISABLE		BIT(6)
-
-#define REG_PORT_MAC_IN_RATE_LIMIT	0x0403
-
-#define PORT_IN_PORT_BASED_S		6
-#define PORT_RATE_PACKET_BASED_S	5
-#define PORT_IN_FLOW_CTRL_S		4
-#define PORT_COUNT_IFG_S		1
-#define PORT_COUNT_PREAMBLE_S		0
-#define PORT_IN_PORT_BASED		BIT(6)
-#define PORT_IN_PACKET_BASED		BIT(5)
-#define PORT_IN_FLOW_CTRL		BIT(4)
-#define PORT_IN_LIMIT_MODE_M		0x3
-#define PORT_IN_LIMIT_MODE_S		2
-#define PORT_IN_ALL			0
-#define PORT_IN_UNICAST			1
-#define PORT_IN_MULTICAST		2
-#define PORT_IN_BROADCAST		3
-#define PORT_COUNT_IFG			BIT(1)
-#define PORT_COUNT_PREAMBLE		BIT(0)
-
-#define REG_PORT_IN_RATE_0		0x0410
-#define REG_PORT_IN_RATE_1		0x0411
-#define REG_PORT_IN_RATE_2		0x0412
-#define REG_PORT_IN_RATE_3		0x0413
-#define REG_PORT_IN_RATE_4		0x0414
-#define REG_PORT_IN_RATE_5		0x0415
-#define REG_PORT_IN_RATE_6		0x0416
-#define REG_PORT_IN_RATE_7		0x0417
-
-#define REG_PORT_OUT_RATE_0		0x0420
-#define REG_PORT_OUT_RATE_1		0x0421
-#define REG_PORT_OUT_RATE_2		0x0422
-#define REG_PORT_OUT_RATE_3		0x0423
-
-#define PORT_RATE_LIMIT_M		(BIT(7) - 1)
-
-/* 5 - MIB Counters */
-#define REG_PORT_MIB_CTRL_STAT__4	0x0500
-
-#define MIB_COUNTER_OVERFLOW		BIT(31)
-#define MIB_COUNTER_VALID		BIT(30)
-#define MIB_COUNTER_READ		BIT(25)
-#define MIB_COUNTER_FLUSH_FREEZE	BIT(24)
-#define MIB_COUNTER_INDEX_M		(BIT(8) - 1)
-#define MIB_COUNTER_INDEX_S		16
-#define MIB_COUNTER_DATA_HI_M		0xF
-
-#define REG_PORT_MIB_DATA		0x0504
-
-/* 6 - ACL */
-#define REG_PORT_ACL_0			0x0600
-
-#define ACL_FIRST_RULE_M		0xF
-
-#define REG_PORT_ACL_1			0x0601
-
-#define ACL_MODE_M			0x3
-#define ACL_MODE_S			4
-#define ACL_MODE_DISABLE		0
-#define ACL_MODE_LAYER_2		1
-#define ACL_MODE_LAYER_3		2
-#define ACL_MODE_LAYER_4		3
-#define ACL_ENABLE_M			0x3
-#define ACL_ENABLE_S			2
-#define ACL_ENABLE_2_COUNT		0
-#define ACL_ENABLE_2_TYPE		1
-#define ACL_ENABLE_2_MAC		2
-#define ACL_ENABLE_2_BOTH		3
-#define ACL_ENABLE_3_IP			1
-#define ACL_ENABLE_3_SRC_DST_COMP	2
-#define ACL_ENABLE_4_PROTOCOL		0
-#define ACL_ENABLE_4_TCP_PORT_COMP	1
-#define ACL_ENABLE_4_UDP_PORT_COMP	2
-#define ACL_ENABLE_4_TCP_SEQN_COMP	3
-#define ACL_SRC				BIT(1)
-#define ACL_EQUAL			BIT(0)
-
-#define REG_PORT_ACL_2			0x0602
-#define REG_PORT_ACL_3			0x0603
-
-#define ACL_MAX_PORT			0xFFFF
-
-#define REG_PORT_ACL_4			0x0604
-#define REG_PORT_ACL_5			0x0605
-
-#define ACL_MIN_PORT			0xFFFF
-#define ACL_IP_ADDR			0xFFFFFFFF
-#define ACL_TCP_SEQNUM			0xFFFFFFFF
-
-#define REG_PORT_ACL_6			0x0606
-
-#define ACL_RESERVED			0xF8
-#define ACL_PORT_MODE_M			0x3
-#define ACL_PORT_MODE_S			1
-#define ACL_PORT_MODE_DISABLE		0
-#define ACL_PORT_MODE_EITHER		1
-#define ACL_PORT_MODE_IN_RANGE		2
-#define ACL_PORT_MODE_OUT_OF_RANGE	3
-
-#define REG_PORT_ACL_7			0x0607
-
-#define ACL_TCP_FLAG_ENABLE		BIT(0)
-
-#define REG_PORT_ACL_8			0x0608
-
-#define ACL_TCP_FLAG_M			0xFF
-
-#define REG_PORT_ACL_9			0x0609
-
-#define ACL_TCP_FLAG			0xFF
-#define ACL_ETH_TYPE			0xFFFF
-#define ACL_IP_M			0xFFFFFFFF
-
-#define REG_PORT_ACL_A			0x060A
-
-#define ACL_PRIO_MODE_M			0x3
-#define ACL_PRIO_MODE_S			6
-#define ACL_PRIO_MODE_DISABLE		0
-#define ACL_PRIO_MODE_HIGHER		1
-#define ACL_PRIO_MODE_LOWER		2
-#define ACL_PRIO_MODE_REPLACE		3
-#define ACL_PRIO_M			KS_PRIO_M
-#define ACL_PRIO_S			3
-#define ACL_VLAN_PRIO_REPLACE		BIT(2)
-#define ACL_VLAN_PRIO_M			KS_PRIO_M
-#define ACL_VLAN_PRIO_HI_M		0x3
-
-#define REG_PORT_ACL_B			0x060B
-
-#define ACL_VLAN_PRIO_LO_M		0x8
-#define ACL_VLAN_PRIO_S			7
-#define ACL_MAP_MODE_M			0x3
-#define ACL_MAP_MODE_S			5
-#define ACL_MAP_MODE_DISABLE		0
-#define ACL_MAP_MODE_OR			1
-#define ACL_MAP_MODE_AND		2
-#define ACL_MAP_MODE_REPLACE		3
-
-#define ACL_CNT_M			(BIT(11) - 1)
-#define ACL_CNT_S			5
-
-#define REG_PORT_ACL_C			0x060C
-
-#define REG_PORT_ACL_D			0x060D
-#define ACL_MSEC_UNIT			BIT(6)
-#define ACL_INTR_MODE			BIT(5)
-#define ACL_PORT_MAP			0x7F
-
-#define REG_PORT_ACL_E			0x060E
-#define REG_PORT_ACL_F			0x060F
-
-#define REG_PORT_ACL_BYTE_EN_MSB	0x0610
-#define REG_PORT_ACL_BYTE_EN_LSB	0x0611
-
-#define ACL_ACTION_START		0xA
-#define ACL_ACTION_LEN			4
-#define ACL_INTR_CNT_START		0xD
-#define ACL_RULESET_START		0xE
-#define ACL_RULESET_LEN			2
-#define ACL_TABLE_LEN			16
-
-#define ACL_ACTION_ENABLE		0x003C
-#define ACL_MATCH_ENABLE		0x7FC3
-#define ACL_RULESET_ENABLE		0x8003
-#define ACL_BYTE_ENABLE			0xFFFF
-
-#define REG_PORT_ACL_CTRL_0		0x0612
-
-#define PORT_ACL_WRITE_DONE		BIT(6)
-#define PORT_ACL_READ_DONE		BIT(5)
-#define PORT_ACL_WRITE			BIT(4)
-#define PORT_ACL_INDEX_M		0xF
-
-#define REG_PORT_ACL_CTRL_1		0x0613
-
-/* 8 - Classification and Policing */
-#define REG_PORT_MRI_MIRROR_CTRL	0x0800
-
-#define PORT_MIRROR_RX			BIT(6)
-#define PORT_MIRROR_TX			BIT(5)
-#define PORT_MIRROR_SNIFFER		BIT(1)
-
-#define REG_PORT_MRI_PRIO_CTRL		0x0801
-
-#define PORT_HIGHEST_PRIO		BIT(7)
-#define PORT_OR_PRIO			BIT(6)
-#define PORT_MAC_PRIO_ENABLE		BIT(4)
-#define PORT_VLAN_PRIO_ENABLE		BIT(3)
-#define PORT_802_1P_PRIO_ENABLE		BIT(2)
-#define PORT_DIFFSERV_PRIO_ENABLE	BIT(1)
-#define PORT_ACL_PRIO_ENABLE		BIT(0)
-
-#define REG_PORT_MRI_MAC_CTRL		0x0802
-
-#define PORT_USER_PRIO_CEILING		BIT(7)
-#define PORT_DROP_NON_VLAN		BIT(4)
-#define PORT_DROP_TAG			BIT(3)
-#define PORT_BASED_PRIO_M		KS_PRIO_M
-#define PORT_BASED_PRIO_S		0
-
-#define REG_PORT_MRI_AUTHEN_CTRL	0x0803
-
-#define PORT_ACL_ENABLE			BIT(2)
-#define PORT_AUTHEN_MODE		0x3
-#define PORT_AUTHEN_PASS		0
-#define PORT_AUTHEN_BLOCK		1
-#define PORT_AUTHEN_TRAP		2
-
-#define REG_PORT_MRI_INDEX__4		0x0804
-
-#define MRI_INDEX_P_M			0x7
-#define MRI_INDEX_P_S			16
-#define MRI_INDEX_Q_M			0x3
-#define MRI_INDEX_Q_S			0
-
-#define REG_PORT_MRI_TC_MAP__4		0x0808
-
-#define PORT_TC_MAP_M			0xf
-#define PORT_TC_MAP_S			4
-
-#define REG_PORT_MRI_POLICE_CTRL__4	0x080C
-
-#define POLICE_DROP_ALL			BIT(10)
-#define POLICE_PACKET_TYPE_M		0x3
-#define POLICE_PACKET_TYPE_S		8
-#define POLICE_PACKET_DROPPED		0
-#define POLICE_PACKET_GREEN		1
-#define POLICE_PACKET_YELLOW		2
-#define POLICE_PACKET_RED		3
-#define PORT_BASED_POLICING		BIT(7)
-#define NON_DSCP_COLOR_M		0x3
-#define NON_DSCP_COLOR_S		5
-#define COLOR_MARK_ENABLE		BIT(4)
-#define COLOR_REMAP_ENABLE		BIT(3)
-#define POLICE_DROP_SRP			BIT(2)
-#define POLICE_COLOR_NOT_AWARE		BIT(1)
-#define POLICE_ENABLE			BIT(0)
-
-#define REG_PORT_POLICE_COLOR_0__4	0x0810
-#define REG_PORT_POLICE_COLOR_1__4	0x0814
-#define REG_PORT_POLICE_COLOR_2__4	0x0818
-#define REG_PORT_POLICE_COLOR_3__4	0x081C
-
-#define POLICE_COLOR_MAP_S		2
-#define POLICE_COLOR_MAP_M		(BIT(POLICE_COLOR_MAP_S) - 1)
-
-#define REG_PORT_POLICE_RATE__4		0x0820
-
-#define POLICE_CIR_S			16
-#define POLICE_PIR_S			0
-
-#define REG_PORT_POLICE_BURST_SIZE__4	0x0824
-
-#define POLICE_BURST_SIZE_M		0x3FFF
-#define POLICE_CBS_S			16
-#define POLICE_PBS_S			0
-
-#define REG_PORT_WRED_PM_CTRL_0__4	0x0830
-
-#define WRED_PM_CTRL_M			(BIT(11) - 1)
-
-#define WRED_PM_MAX_THRESHOLD_S		16
-#define WRED_PM_MIN_THRESHOLD_S		0
-
-#define REG_PORT_WRED_PM_CTRL_1__4	0x0834
-
-#define WRED_PM_MULTIPLIER_S		16
-#define WRED_PM_AVG_QUEUE_SIZE_S	0
-
-#define REG_PORT_WRED_QUEUE_CTRL_0__4	0x0840
-#define REG_PORT_WRED_QUEUE_CTRL_1__4	0x0844
-
-#define REG_PORT_WRED_QUEUE_PMON__4	0x0848
-
-#define WRED_RANDOM_DROP_ENABLE		BIT(31)
-#define WRED_PMON_FLUSH			BIT(30)
-#define WRED_DROP_GYR_DISABLE		BIT(29)
-#define WRED_DROP_YR_DISABLE		BIT(28)
-#define WRED_DROP_R_DISABLE		BIT(27)
-#define WRED_DROP_ALL			BIT(26)
-#define WRED_PMON_M			(BIT(24) - 1)
-
-/* 9 - Shaping */
-
-#define REG_PORT_MTI_QUEUE_INDEX__4	0x0900
-
-#define REG_PORT_MTI_QUEUE_CTRL_0__4	0x0904
-
-#define MTI_PVID_REPLACE		BIT(0)
-
-#define REG_PORT_MTI_QUEUE_CTRL_0	0x0914
-
-#define MTI_SCHEDULE_MODE_M		0x3
-#define MTI_SCHEDULE_MODE_S		6
-#define MTI_SCHEDULE_STRICT_PRIO	0
-#define MTI_SCHEDULE_WRR		2
-#define MTI_SHAPING_M			0x3
-#define MTI_SHAPING_S			4
-#define MTI_SHAPING_OFF			0
-#define MTI_SHAPING_SRP			1
-#define MTI_SHAPING_TIME_AWARE		2
-
-#define REG_PORT_MTI_QUEUE_CTRL_1	0x0915
-
-#define MTI_TX_RATIO_M			(BIT(7) - 1)
-
-#define REG_PORT_MTI_QUEUE_CTRL_2__2	0x0916
-#define REG_PORT_MTI_HI_WATER_MARK	0x0916
-#define REG_PORT_MTI_QUEUE_CTRL_3__2	0x0918
-#define REG_PORT_MTI_LO_WATER_MARK	0x0918
-#define REG_PORT_MTI_QUEUE_CTRL_4__2	0x091A
-#define REG_PORT_MTI_CREDIT_INCREMENT	0x091A
-
-/* A - QM */
-
-#define REG_PORT_QM_CTRL__4		0x0A00
-
-#define PORT_QM_DROP_PRIO_M		0x3
-
-#define REG_PORT_VLAN_MEMBERSHIP__4	0x0A04
-
-#define REG_PORT_QM_QUEUE_INDEX__4	0x0A08
-
-#define PORT_QM_QUEUE_INDEX_S		24
-#define PORT_QM_BURST_SIZE_S		16
-#define PORT_QM_MIN_RESV_SPACE_M	(BIT(11) - 1)
-
-#define REG_PORT_QM_WATER_MARK__4	0x0A0C
-
-#define PORT_QM_HI_WATER_MARK_S		16
-#define PORT_QM_LO_WATER_MARK_S		0
-#define PORT_QM_WATER_MARK_M		(BIT(11) - 1)
-
-#define REG_PORT_QM_TX_CNT_0__4		0x0A10
-
-#define PORT_QM_TX_CNT_USED_S		0
-#define PORT_QM_TX_CNT_M		(BIT(11) - 1)
-
-#define REG_PORT_QM_TX_CNT_1__4		0x0A14
-
-#define PORT_QM_TX_CNT_CALCULATED_S	16
-#define PORT_QM_TX_CNT_AVAIL_S		0
-
-/* B - LUE */
-#define REG_PORT_LUE_CTRL		0x0B00
-
-#define PORT_VLAN_LOOKUP_VID_0		BIT(7)
-#define PORT_INGRESS_FILTER		BIT(6)
-#define PORT_DISCARD_NON_VID		BIT(5)
-#define PORT_MAC_BASED_802_1X		BIT(4)
-#define PORT_SRC_ADDR_FILTER		BIT(3)
-
-#define REG_PORT_LUE_MSTP_INDEX		0x0B01
-
-#define REG_PORT_LUE_MSTP_STATE		0x0B04
-
-#define PORT_TX_ENABLE			BIT(2)
-#define PORT_RX_ENABLE			BIT(1)
-#define PORT_LEARN_DISABLE		BIT(0)
-
-/* C - PTP */
-
-#define REG_PTP_PORT_RX_DELAY__2	0x0C00
-#define REG_PTP_PORT_TX_DELAY__2	0x0C02
-#define REG_PTP_PORT_ASYM_DELAY__2	0x0C04
-
-#define REG_PTP_PORT_XDELAY_TS		0x0C08
-#define REG_PTP_PORT_XDELAY_TS_H	0x0C08
-#define REG_PTP_PORT_XDELAY_TS_L	0x0C0A
-
-#define REG_PTP_PORT_SYNC_TS		0x0C0C
-#define REG_PTP_PORT_SYNC_TS_H		0x0C0C
-#define REG_PTP_PORT_SYNC_TS_L		0x0C0E
-
-#define REG_PTP_PORT_PDRESP_TS		0x0C10
-#define REG_PTP_PORT_PDRESP_TS_H	0x0C10
-#define REG_PTP_PORT_PDRESP_TS_L	0x0C12
-
-#define REG_PTP_PORT_TX_INT_STATUS__2	0x0C14
-#define REG_PTP_PORT_TX_INT_ENABLE__2	0x0C16
-
-#define PTP_PORT_SYNC_INT		BIT(15)
-#define PTP_PORT_XDELAY_REQ_INT		BIT(14)
-#define PTP_PORT_PDELAY_RESP_INT	BIT(13)
-
-#define REG_PTP_PORT_LINK_DELAY__4	0x0C18
-
-#define PRIO_QUEUES			4
-#define RX_PRIO_QUEUES			8
-
-#define KS_PRIO_IN_REG			2
-
-#define TOTAL_PORT_NUM			7
-
-#define KSZ9477_COUNTER_NUM		0x20
-#define TOTAL_KSZ9477_COUNTER_NUM	(KSZ9477_COUNTER_NUM + 2 + 2)
-
-#define SWITCH_COUNTER_NUM		KSZ9477_COUNTER_NUM
-#define TOTAL_SWITCH_COUNTER_NUM	TOTAL_KSZ9477_COUNTER_NUM
-
-#define P_BCAST_STORM_CTRL		REG_PORT_MAC_CTRL_0
-#define P_PRIO_CTRL			REG_PORT_MRI_PRIO_CTRL
-#define P_MIRROR_CTRL			REG_PORT_MRI_MIRROR_CTRL
-#define P_STP_CTRL			REG_PORT_LUE_MSTP_STATE
-#define P_PHY_CTRL			REG_PORT_PHY_CTRL
-#define P_NEG_RESTART_CTRL		REG_PORT_PHY_CTRL
-#define P_LINK_STATUS			REG_PORT_PHY_STATUS
-#define P_SPEED_STATUS			REG_PORT_PHY_PHY_CTRL
-#define P_RATE_LIMIT_CTRL		REG_PORT_MAC_IN_RATE_LIMIT
-
-#define S_LINK_AGING_CTRL		REG_SW_LUE_CTRL_1
-#define S_MIRROR_CTRL			REG_SW_MRI_CTRL_0
-#define S_REPLACE_VID_CTRL		REG_SW_MAC_CTRL_2
-#define S_802_1P_PRIO_CTRL		REG_SW_MAC_802_1P_MAP_0
-#define S_TOS_PRIO_CTRL			REG_SW_MAC_TOS_PRIO_0
-#define S_FLUSH_TABLE_CTRL		REG_SW_LUE_CTRL_1
-
-#define SW_FLUSH_DYN_MAC_TABLE		SW_FLUSH_MSTP_TABLE
-
-#define MAX_TIMESTAMP_UNIT		2
-#define MAX_TRIG_UNIT			3
-#define MAX_TIMESTAMP_EVENT_UNIT	8
-#define MAX_GPIO			4
-
-#define PTP_TRIG_UNIT_M			(BIT(MAX_TRIG_UNIT) - 1)
-#define PTP_TS_UNIT_M			(BIT(MAX_TIMESTAMP_UNIT) - 1)
-
-/* Driver set switch broadcast storm protection at 10% rate. */
-#define BROADCAST_STORM_PROT_RATE	10
-
-/* 148,800 frames * 67 ms / 100 */
-#define BROADCAST_STORM_VALUE		9969
-
-#endif /* KSZ9477_REGS_H */
diff --git a/drivers/net/dsa/microchip/ksz_priv.h b/drivers/net/dsa/microchip/ksz_priv.h
index 74c5c1a68d6a..a38ff0841ed4 100644
--- a/drivers/net/dsa/microchip/ksz_priv.h
+++ b/drivers/net/dsa/microchip/ksz_priv.h
@@ -14,7 +14,7 @@
 #include <linux/etherdevice.h>
 #include <net/dsa.h>
 
-#include "ksz_9477_reg.h"
+#include "ksz9477_reg.h"
 
 struct ksz_io_ops;
 
-- 
cgit v1.2.3


From b3c4d7c93e45f2cb9265c40e874c7ea56828d8df Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Mon, 29 Oct 2018 15:54:12 -0700
Subject: ixgbe: add ipsec hw offload note to ixgbe Documentation

Add a short note about using IPsec Hardware Offload with
the ixgbe driver.

Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 Documentation/networking/ixgbe.rst | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/Documentation/networking/ixgbe.rst b/Documentation/networking/ixgbe.rst
index 725fc697fd8f..86d887a63606 100644
--- a/Documentation/networking/ixgbe.rst
+++ b/Documentation/networking/ixgbe.rst
@@ -501,6 +501,19 @@ NOTE: This feature can be disabled for a specific Virtual Function (VF)::
 
   ip link set <pf dev> vf <vf id> spoofchk {off|on}
 
+IPsec Offload
+-------------
+The ixgbe driver supports IPsec Hardware Offload.  When creating Security
+Associations with "ip xfrm ..." the 'offload' tag option can be used to
+register the IPsec SA with the driver in order to get higher throughput in
+the secure communications.
+
+The offload is also supported for ixgbe's VFs, but the VF must be set as
+'trusted' and the support must be enabled with::
+
+  ethtool --set-priv-flags eth<x> vf-ipsec on
+  ip link set eth<x> vf <y> trust on
+
 
 Known Issues/Troubleshooting
 ============================
-- 
cgit v1.2.3


From 4df3c543a72585fdcac8fed9547d2ce395729221 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Thu, 1 Nov 2018 00:03:31 -0700
Subject: igb: Fix format with line continuation whitespace

The line continuation unintentionally adds whitespace so
instead use a coalesced format to remove the whitespace.

Miscellanea:

o Use a more typical style for ternaries and arguments
  for this logging message

Signed-off-by: Joe Perches <joe@perches.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 4584ebc9e8fe..4331ea71b86e 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1850,13 +1850,12 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 	 * configuration' in respect to these parameters.
 	 */
 
-	netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d \
-			    idleslope %d sendslope %d hiCredit %d \
-			    locredit %d\n",
-		   (ring->cbs_enable) ? "enabled" : "disabled",
-		   (ring->launchtime_enable) ? "enabled" : "disabled", queue,
-		   ring->idleslope, ring->sendslope, ring->hicredit,
-		   ring->locredit);
+	netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
+		   ring->cbs_enable ? "enabled" : "disabled",
+		   ring->launchtime_enable ? "enabled" : "disabled",
+		   queue,
+		   ring->idleslope, ring->sendslope,
+		   ring->hicredit, ring->locredit);
 }
 
 static int igb_save_txtime_params(struct igb_adapter *adapter, int queue,
-- 
cgit v1.2.3


From 09e58b2d538cfd4fa3f48bc4fc78ba1c1b28b05a Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Wed, 7 Nov 2018 21:40:17 -0800
Subject: docs-networking: fix typo in define

The #define for NETIF_F_GSO_UDP_L4 was incorrect in the
documentation, fix it by making it match the actual code.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 Documentation/networking/netdev-features.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/networking/netdev-features.txt b/Documentation/networking/netdev-features.txt
index c4a54c162547..58dd1c1e3c65 100644
--- a/Documentation/networking/netdev-features.txt
+++ b/Documentation/networking/netdev-features.txt
@@ -115,7 +115,7 @@ set, be it TCPv4 (when NETIF_F_TSO is enabled) or TCPv6 (NETIF_F_TSO6).
 
  * Transmit UDP segmentation offload
 
-NETIF_F_GSO_UDP_GSO_L4 accepts a single UDP header with a payload that exceeds
+NETIF_F_GSO_UDP_L4 accepts a single UDP header with a payload that exceeds
 gso_size. On segmentation, it segments the payload on gso_size boundaries and
 replicates the network and UDP headers (fixing up the last one if less than
 gso_size).
-- 
cgit v1.2.3


From 0bcd952feec7042d9a5383b639c8edc943402add Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Thu, 8 Nov 2018 14:55:32 -0800
Subject: ethernet/intel: consolidate NAPI and NAPI exit

While reviewing code, I noticed that Eric Dumazet recommends that
drivers check the return code of napi_complete_done, and use that
to decide to enable interrupts or not when exiting poll.  One of
the Intel drivers was already fixed (ixgbe).

Upon looking at the Intel drivers as a whole, we are handling our
polling and NAPI exit in a few different ways based on whether we
have multiqueue and whether we have Tx cleanup included. Several
drivers had the bug of exiting NAPI with return 0, which appears
to mess up the accounting in the stack.

Consolidate all the NAPI routines to do best known way of exiting
and to just mostly look like each other.
1) check return code of napi_complete_done to control interrupt enable
2) return the actual amount of work done.
3) return budget immediately if need NAPI poll again

Tested the changes on e1000e with a high interrupt rate set, and
it shows about an 8% reduction in the CPU utilization when busy
polling because we aren't re-enabling interrupts when we're about
to be polled.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e100.c                 | 10 ++++++----
 drivers/net/ethernet/intel/e1000/e1000_main.c     | 11 ++++++-----
 drivers/net/ethernet/intel/e1000e/netdev.c        | 17 +++++++++--------
 drivers/net/ethernet/intel/fm10k/fm10k_main.c     | 10 +++++-----
 drivers/net/ethernet/intel/i40e/i40e_txrx.c       |  9 +++++----
 drivers/net/ethernet/intel/iavf/iavf_txrx.c       |  9 +++++----
 drivers/net/ethernet/intel/ice/ice_txrx.c         | 10 ++++++----
 drivers/net/ethernet/intel/igb/igb_main.c         | 10 ++++++----
 drivers/net/ethernet/intel/igbvf/netdev.c         |  9 ++++++---
 drivers/net/ethernet/intel/igc/igc_main.c         | 10 ++++++----
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 22 +++++++++++++---------
 11 files changed, 73 insertions(+), 54 deletions(-)

diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 7c4b55482f72..5e5c57db0d3f 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -2225,11 +2225,13 @@ static int e100_poll(struct napi_struct *napi, int budget)
 	e100_rx_clean(nic, &work_done, budget);
 	e100_tx_clean(nic);
 
-	/* If budget not fully consumed, exit the polling mode */
-	if (work_done < budget) {
-		napi_complete_done(napi, work_done);
+	/* If budget fully consumed, continue polling */
+	if (work_done == budget)
+		return budget;
+
+	/* only re-enable interrupt if stack agrees polling is really done */
+	if (likely(napi_complete_done(napi, work_done)))
 		e100_enable_irq(nic);
-	}
 
 	return work_done;
 }
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 43b6d3cec3b3..8fe9af0e2ab7 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3803,14 +3803,15 @@ static int e1000_clean(struct napi_struct *napi, int budget)
 
 	adapter->clean_rx(adapter, &adapter->rx_ring[0], &work_done, budget);
 
-	if (!tx_clean_complete)
-		work_done = budget;
+	if (!tx_clean_complete || work_done == budget)
+		return budget;
 
-	/* If budget not fully consumed, exit the polling mode */
-	if (work_done < budget) {
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done))) {
 		if (likely(adapter->itr_setting & 3))
 			e1000_set_itr(adapter);
-		napi_complete_done(napi, work_done);
 		if (!test_bit(__E1000_DOWN, &adapter->flags))
 			e1000_irq_enable(adapter);
 	}
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 59bd587d809d..308c006cb41d 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -2651,9 +2651,9 @@ err:
 /**
  * e1000e_poll - NAPI Rx polling callback
  * @napi: struct associated with this polling callback
- * @weight: number of packets driver is allowed to process this poll
+ * @budget: number of packets driver is allowed to process this poll
  **/
-static int e1000e_poll(struct napi_struct *napi, int weight)
+static int e1000e_poll(struct napi_struct *napi, int budget)
 {
 	struct e1000_adapter *adapter = container_of(napi, struct e1000_adapter,
 						     napi);
@@ -2667,16 +2667,17 @@ static int e1000e_poll(struct napi_struct *napi, int weight)
 	    (adapter->rx_ring->ims_val & adapter->tx_ring->ims_val))
 		tx_cleaned = e1000_clean_tx_irq(adapter->tx_ring);
 
-	adapter->clean_rx(adapter->rx_ring, &work_done, weight);
+	adapter->clean_rx(adapter->rx_ring, &work_done, budget);
 
-	if (!tx_cleaned)
-		work_done = weight;
+	if (!tx_cleaned || work_done == budget)
+		return budget;
 
-	/* If weight not fully consumed, exit the polling mode */
-	if (work_done < weight) {
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done))) {
 		if (adapter->itr_setting & 3)
 			e1000_set_itr(adapter);
-		napi_complete_done(napi, work_done);
 		if (!test_bit(__E1000_DOWN, &adapter->state)) {
 			if (adapter->msix_entries)
 				ew32(IMS, adapter->rx_ring->ims_val);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 5b2a50e5798f..6fd15a734324 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -1465,11 +1465,11 @@ static int fm10k_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 
-	/* all work done, exit the polling mode */
-	napi_complete_done(napi, work_done);
-
-	/* re-enable the q_vector */
-	fm10k_qv_enable(q_vector);
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		fm10k_qv_enable(q_vector);
 
 	return min(work_done, budget - 1);
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index c4d44096cdaf..a0b1575468fc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2667,10 +2667,11 @@ tx_only:
 	if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR)
 		q_vector->arm_wb_state = false;
 
-	/* Work is done so exit the polling mode and re-enable the interrupt */
-	napi_complete_done(napi, work_done);
-
-	i40e_update_enable_itr(vsi, q_vector);
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		i40e_update_enable_itr(vsi, q_vector);
 
 	return min(work_done, budget - 1);
 }
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 3b1dc77ae368..9b4d7cec2e18 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -1761,10 +1761,11 @@ tx_only:
 	if (vsi->back->flags & IAVF_TXR_FLAGS_WB_ON_ITR)
 		q_vector->arm_wb_state = false;
 
-	/* Work is done so exit the polling mode and re-enable the interrupt */
-	napi_complete_done(napi, work_done);
-
-	iavf_update_enable_itr(vsi, q_vector);
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		iavf_update_enable_itr(vsi, q_vector);
 
 	return min(work_done, budget - 1);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 4b92863b3500..49fc38094185 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1103,10 +1103,12 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 
-	/* Work is done so exit the polling mode and re-enable the interrupt */
-	napi_complete_done(napi, work_done);
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-		ice_irq_dynamic_ena(&vsi->back->hw, vsi, q_vector);
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
+			ice_irq_dynamic_ena(&vsi->back->hw, vsi, q_vector);
 
 	return min(work_done, budget - 1);
 }
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 4331ea71b86e..453ae1d9e5f3 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -7752,11 +7752,13 @@ static int igb_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 
-	/* If not enough Rx work done, exit the polling mode */
-	napi_complete_done(napi, work_done);
-	igb_ring_irq_enable(q_vector);
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		igb_ring_irq_enable(q_vector);
 
-	return 0;
+	return min(work_done, budget - 1);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 820d49eb41ab..4eab83faec62 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -1186,10 +1186,13 @@ static int igbvf_poll(struct napi_struct *napi, int budget)
 
 	igbvf_clean_rx_irq(adapter, &work_done, budget);
 
-	/* If not enough Rx work done, exit the polling mode */
-	if (work_done < budget) {
-		napi_complete_done(napi, work_done);
+	if (work_done == budget)
+		return budget;
 
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done))) {
 		if (adapter->requested_itr & 3)
 			igbvf_set_itr(adapter);
 
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index d002055c0623..28ffe98f8921 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2852,11 +2852,13 @@ static int igc_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 
-	/* If not enough Rx work done, exit the polling mode */
-	napi_complete_done(napi, work_done);
-	igc_ring_irq_enable(q_vector);
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		igc_ring_irq_enable(q_vector);
 
-	return 0;
+	return min(work_done, budget - 1);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 196b890467b2..2de81f046fb5 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1293,16 +1293,20 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget)
 	/* If all work not completed, return budget and keep polling */
 	if (!clean_complete)
 		return budget;
-	/* all work done, exit the polling mode */
-	napi_complete_done(napi, work_done);
-	if (adapter->rx_itr_setting == 1)
-		ixgbevf_set_itr(q_vector);
-	if (!test_bit(__IXGBEVF_DOWN, &adapter->state) &&
-	    !test_bit(__IXGBEVF_REMOVING, &adapter->state))
-		ixgbevf_irq_enable_queues(adapter,
-					  BIT(q_vector->v_idx));
 
-	return 0;
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done))) {
+		if (adapter->rx_itr_setting == 1)
+			ixgbevf_set_itr(q_vector);
+		if (!test_bit(__IXGBEVF_DOWN, &adapter->state) &&
+		    !test_bit(__IXGBEVF_REMOVING, &adapter->state))
+			ixgbevf_irq_enable_queues(adapter,
+						  BIT(q_vector->v_idx));
+	}
+
+	return min(work_done, budget - 1);
 }
 
 /**
-- 
cgit v1.2.3


From 8166abb1ea7d53a26ac0e2598b77a5440216811a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.ibm.com>
Date: Sun, 11 Nov 2018 11:43:42 -0800
Subject: ixgbe: Replace synchronize_sched() with synchronize_rcu()

Now that synchronize_rcu() waits for preempt-disable regions of code
as well as RCU read-side critical sections, synchronize_sched() can be
replaced by synchronize_rcu().  This commit therefore makes this change.

Signed-off-by: "Paul E. McKenney" <paulmck@linux.ibm.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index cfb83687c3d8..49a4ea38eb07 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6077,9 +6077,9 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 	/* Disable Rx */
 	ixgbe_disable_rx(adapter);
 
-	/* synchronize_sched() needed for pending XDP buffers to drain */
+	/* synchronize_rcu() needed for pending XDP buffers to drain */
 	if (adapter->xdp_ring[0])
-		synchronize_sched();
+		synchronize_rcu();
 
 	ixgbe_irq_disable(adapter);
 
@@ -10476,7 +10476,7 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring)
 	ixgbe_disable_rxr_hw(adapter, rx_ring);
 
 	if (xdp_ring)
-		synchronize_sched();
+		synchronize_rcu();
 
 	/* Rx/Tx/XDP Tx share the same napi context. */
 	napi_disable(&rx_ring->q_vector->napi);
-- 
cgit v1.2.3


From 6ed4babed9cc7eaa71522b5c10265ef3a4a06297 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Mon, 12 Nov 2018 11:05:20 +0200
Subject: igc: Remove obsolete IGC_ERR define

Address community comment.
Remove obsolete IGC_ERR define and use dev_err method.
Suggested by Joe Perches.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h      | 2 --
 drivers/net/ethernet/intel/igc/igc_main.c | 2 +-
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 3b00b109b34a..b1039dd3dd13 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -11,8 +11,6 @@
 #include <linux/ethtool.h>
 #include <linux/sctp.h>
 
-#define IGC_ERR(args...) pr_err("igc: " args)
-
 #include "igc_hw.h"
 
 /* main */
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 28ffe98f8921..f20183037fb2 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3535,7 +3535,7 @@ static int igc_probe(struct pci_dev *pdev,
 			err = dma_set_coherent_mask(&pdev->dev,
 						    DMA_BIT_MASK(32));
 			if (err) {
-				IGC_ERR("Wrong DMA configuration, aborting\n");
+				dev_err(&pdev->dev, "igc: Wrong DMA config\n");
 				goto err_dma;
 			}
 		}
-- 
cgit v1.2.3


From 462c124c590fe633564192dbfa26e99af788a67c Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Wed, 21 Nov 2018 11:22:42 -0800
Subject: bpf: fix a libbpf loader issue

Commit 2993e0515bb4 ("tools/bpf: add support to read .BTF.ext sections")
added support to read .BTF.ext sections from an object file, create
and pass prog_btf_fd and func_info to the kernel.

The program btf_fd (prog->btf_fd) is initialized to be -1 to please
zclose so we do not need special handling dur prog close.
Passing -1 to the kernel, however, will cause loading error.
Passing btf_fd 0 to the kernel if prog->btf_fd is invalid
fixed the problem.

Fixes: 2993e0515bb4 ("tools/bpf: add support to read .BTF.ext sections")
Reported-by: Andrey Ignatov <rdna@fb.com>
Reported-by: Emre Cantimur <haydum@fb.com>
Tested-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index cb6565d79603..f022ac82e882 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1387,7 +1387,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.license = license;
 	load_attr.kern_version = kern_version;
 	load_attr.prog_ifindex = prog->prog_ifindex;
-	load_attr.prog_btf_fd = prog->btf_fd;
+	load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
 	load_attr.func_info = prog->func_info;
 	load_attr.func_info_rec_size = prog->func_info_rec_size;
 	load_attr.func_info_cnt = func_info_cnt;
-- 
cgit v1.2.3


From 8c4905b995c649ac71e21611abc2fcefc904b56a Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Wed, 21 Nov 2018 09:29:44 -0800
Subject: libbpf: make sure bpf headers are c++ include-able

Wrap headers in extern "C", to turn off C++ mangling.
This simplifies including libbpf in c++ and linking against it.

v2 changes:
* do the same for btf.h

v3 changes:
* test_libbpf.cpp to test for possible future c++ breakages

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/Makefile        | 15 ++++++++++++---
 tools/lib/bpf/bpf.h           |  9 +++++++++
 tools/lib/bpf/btf.h           |  8 ++++++++
 tools/lib/bpf/libbpf.h        |  9 +++++++++
 tools/lib/bpf/test_libbpf.cpp | 18 ++++++++++++++++++
 5 files changed, 56 insertions(+), 3 deletions(-)
 create mode 100644 tools/lib/bpf/test_libbpf.cpp

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 425b480bda75..1b4a683a00fc 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -66,7 +66,7 @@ ifndef VERBOSE
 endif
 
 FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-mmap bpf reallocarray
+FEATURE_TESTS = libelf libelf-mmap bpf reallocarray cxx
 FEATURE_DISPLAY = libelf bpf
 
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
@@ -148,6 +148,12 @@ LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
 
 CMD_TARGETS = $(LIB_FILE)
 
+CXX_TEST_TARGET = $(OUTPUT)test_libbpf
+
+ifeq ($(feature-cxx), 1)
+	CMD_TARGETS += $(CXX_TEST_TARGET)
+endif
+
 TARGETS = $(CMD_TARGETS)
 
 all: fixdep all_cmd
@@ -175,6 +181,9 @@ $(OUTPUT)libbpf.so: $(BPF_IN)
 $(OUTPUT)libbpf.a: $(BPF_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
 
+$(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a
+	$(QUIET_LINK)$(CXX) $^ -lelf -o $@
+
 define do_install
 	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
@@ -201,8 +210,8 @@ config-clean:
 	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
 
 clean:
-	$(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so .*.d .*.cmd \
-		$(RM) LIBBPF-CFLAGS
+	$(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \
+		*.o *~ *.a *.so .*.d .*.cmd LIBBPF-CFLAGS
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 8bdfd806253a..09e8bbe111d4 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -27,6 +27,10 @@
 #include <stdbool.h>
 #include <stddef.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
 #endif
@@ -132,4 +136,9 @@ LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf,
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
 				 __u64 *probe_offset, __u64 *probe_addr);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
 #endif /* __LIBBPF_BPF_H */
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 386b2ffc32a3..701ad2b6c41f 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -6,6 +6,10 @@
 
 #include <linux/types.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
 #endif
@@ -80,4 +84,8 @@ int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
 		   const char *sec_name, __u32 insns_cnt, void **func_info,
 		   __u32 *func_info_len);
 
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
 #endif /* __LIBBPF_BTF_H */
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index b1686a787102..74e57e041705 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -16,6 +16,10 @@
 #include <sys/types.h>  // for size_t
 #include <linux/bpf.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
 #endif
@@ -335,4 +339,9 @@ int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
 			libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
 int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
 			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
 #endif /* __LIBBPF_LIBBPF_H */
diff --git a/tools/lib/bpf/test_libbpf.cpp b/tools/lib/bpf/test_libbpf.cpp
new file mode 100644
index 000000000000..abf3fc25c9fa
--- /dev/null
+++ b/tools/lib/bpf/test_libbpf.cpp
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#include "libbpf.h"
+#include "bpf.h"
+#include "btf.h"
+
+/* do nothing, just make sure we can link successfully */
+
+int main(int argc, char *argv[])
+{
+    /* libbpf.h */
+    libbpf_set_print(NULL, NULL, NULL);
+
+    /* bpf.h */
+    bpf_prog_get_fd_by_id(0);
+
+    /* btf.h */
+    btf__new(NULL, 0, NULL);
+}
-- 
cgit v1.2.3


From 47eff61777c7b2db58805f974994713c8acbe9a6 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Tue, 20 Nov 2018 17:11:19 -0800
Subject: bpf, libbpf: introduce bpf_object__probe_caps to test BPF
 capabilities

It currently only checks whether kernel supports map/prog names.
This capability check will be used in the next two commits to
skip setting prog/map names.

Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f022ac82e882..dffdd68b5e6b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -24,6 +24,7 @@
 #include <linux/kernel.h>
 #include <linux/bpf.h>
 #include <linux/btf.h>
+#include <linux/filter.h>
 #include <linux/list.h>
 #include <linux/limits.h>
 #include <linux/perf_event.h>
@@ -114,6 +115,11 @@ void libbpf_set_print(libbpf_print_fn_t warn,
 # define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
 #endif
 
+struct bpf_capabilities {
+	/* v4.14: kernel support for program & map names. */
+	__u32 name:1;
+};
+
 /*
  * bpf_prog should be a better name but it has been used in
  * linux/filter.h.
@@ -160,6 +166,8 @@ struct bpf_program {
 	void *func_info;
 	__u32 func_info_rec_size;
 	__u32 func_info_len;
+
+	struct bpf_capabilities *caps;
 };
 
 struct bpf_map {
@@ -221,6 +229,8 @@ struct bpf_object {
 	void *priv;
 	bpf_object_clear_priv_t clear_priv;
 
+	struct bpf_capabilities caps;
+
 	char path[];
 };
 #define obj_elf_valid(o)	((o)->efile.elf)
@@ -342,6 +352,7 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
 	if (err)
 		return err;
 
+	prog.caps = &obj->caps;
 	progs = obj->programs;
 	nr_progs = obj->nr_programs;
 
@@ -1135,6 +1146,52 @@ err_free_new_name:
 	return -errno;
 }
 
+static int
+bpf_object__probe_name(struct bpf_object *obj)
+{
+	struct bpf_load_program_attr attr;
+	char *cp, errmsg[STRERR_BUFSIZE];
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int ret;
+
+	/* make sure basic loading works */
+
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.insns = insns;
+	attr.insns_cnt = ARRAY_SIZE(insns);
+	attr.license = "GPL";
+
+	ret = bpf_load_program_xattr(&attr, NULL, 0);
+	if (ret < 0) {
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+		pr_warning("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n",
+			   __func__, cp, errno);
+		return -errno;
+	}
+	close(ret);
+
+	/* now try the same program, but with the name */
+
+	attr.name = "test";
+	ret = bpf_load_program_xattr(&attr, NULL, 0);
+	if (ret >= 0) {
+		obj->caps.name = 1;
+		close(ret);
+	}
+
+	return 0;
+}
+
+static int
+bpf_object__probe_caps(struct bpf_object *obj)
+{
+	return bpf_object__probe_name(obj);
+}
+
 static int
 bpf_object__create_maps(struct bpf_object *obj)
 {
@@ -1708,6 +1765,7 @@ int bpf_object__load(struct bpf_object *obj)
 
 	obj->loaded = true;
 
+	CHECK_ERR(bpf_object__probe_caps(obj), err, out);
 	CHECK_ERR(bpf_object__create_maps(obj), err, out);
 	CHECK_ERR(bpf_object__relocate(obj), err, out);
 	CHECK_ERR(bpf_object__load_progs(obj), err, out);
-- 
cgit v1.2.3


From 94cb310cfaa16582cd49ebbeea5925e8f49324a1 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Tue, 20 Nov 2018 17:11:20 -0800
Subject: bpf: libbpf: remove map name retry from bpf_create_map_xattr

Instead, check for a newly created caps.name bpf_object capability.
If kernel doesn't support names, don't specify the attribute.

See commit 23499442c319 ("bpf: libbpf: retry map creation without
the name") for rationale.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/bpf.c    | 11 +----------
 tools/lib/bpf/libbpf.c |  3 ++-
 2 files changed, 3 insertions(+), 11 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 836447bb4f14..ce1822194590 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -69,7 +69,6 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 {
 	__u32 name_len = create_attr->name ? strlen(create_attr->name) : 0;
 	union bpf_attr attr;
-	int ret;
 
 	memset(&attr, '\0', sizeof(attr));
 
@@ -87,15 +86,7 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 	attr.map_ifindex = create_attr->map_ifindex;
 	attr.inner_map_fd = create_attr->inner_map_fd;
 
-	ret = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
-	if (ret < 0 && errno == EINVAL && create_attr->name) {
-		/* Retry the same syscall, but without the name.
-		 * Pre v4.14 kernels don't support map names.
-		 */
-		memset(attr.map_name, 0, sizeof(attr.map_name));
-		return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
-	}
-	return ret;
+	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
 int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index dffdd68b5e6b..f28e64dd8b5a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1211,7 +1211,8 @@ bpf_object__create_maps(struct bpf_object *obj)
 			continue;
 		}
 
-		create_attr.name = map->name;
+		if (obj->caps.name)
+			create_attr.name = map->name;
 		create_attr.map_ifindex = map->map_ifindex;
 		create_attr.map_type = def->type;
 		create_attr.map_flags = def->map_flags;
-- 
cgit v1.2.3


From 5b32a23e1d879b78ee72144311314eccf7581bf4 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Tue, 20 Nov 2018 17:11:21 -0800
Subject: bpf: libbpf: don't specify prog name if kernel doesn't support it

Use recently added capability check.

See commit 23499442c319 ("bpf: libbpf: retry map creation without
the name") for rationale.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f28e64dd8b5a..edbae2b1b046 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1439,7 +1439,8 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
 	load_attr.prog_type = prog->type;
 	load_attr.expected_attach_type = prog->expected_attach_type;
-	load_attr.name = prog->name;
+	if (prog->caps->name)
+		load_attr.name = prog->name;
 	load_attr.insns = insns;
 	load_attr.insns_cnt = insns_cnt;
 	load_attr.license = license;
-- 
cgit v1.2.3


From addb9fc90f13898e7779da54f471792e3dfb0d55 Mon Sep 17 00:00:00 2001
From: "Nikita V. Shirokov" <tehnerd@tehnerd.com>
Date: Tue, 20 Nov 2018 20:55:56 -0800
Subject: bpf: adding support for map in map in libbpf

idea is pretty simple. for specified map (pointed by struct bpf_map)
we would provide descriptor of already loaded map, which is going to be
used as a prototype for inner map. proposed workflow:
1) open bpf's object (bpf_object__open)
2) create bpf's map which is going to be used as a prototype
3) find (by name) map-in-map which you want to load and update w/
descriptor of inner map w/ a new helper from this patch
4) load bpf program w/ bpf_object__load

Signed-off-by: Nikita V. Shirokov <tehnerd@tehnerd.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 40 ++++++++++++++++++++++++++++++++++------
 tools/lib/bpf/libbpf.h |  2 ++
 2 files changed, 36 insertions(+), 6 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index edbae2b1b046..0f14f7c074c2 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -175,6 +175,7 @@ struct bpf_map {
 	char *name;
 	size_t offset;
 	int map_ifindex;
+	int inner_map_fd;
 	struct bpf_map_def def;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
@@ -605,6 +606,14 @@ static int compare_bpf_map(const void *_a, const void *_b)
 	return a->offset - b->offset;
 }
 
+static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
+{
+	if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+	    type == BPF_MAP_TYPE_HASH_OF_MAPS)
+		return true;
+	return false;
+}
+
 static int
 bpf_object__init_maps(struct bpf_object *obj, int flags)
 {
@@ -668,13 +677,15 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 	}
 	obj->nr_maps = nr_maps;
 
-	/*
-	 * fill all fd with -1 so won't close incorrect
-	 * fd (fd=0 is stdin) when failure (zclose won't close
-	 * negative fd)).
-	 */
-	for (i = 0; i < nr_maps; i++)
+	for (i = 0; i < nr_maps; i++) {
+		/*
+		 * fill all fd with -1 so won't close incorrect
+		 * fd (fd=0 is stdin) when failure (zclose won't close
+		 * negative fd)).
+		 */
 		obj->maps[i].fd = -1;
+		obj->maps[i].inner_map_fd = -1;
+	}
 
 	/*
 	 * Fill obj->maps using data in "maps" section.
@@ -1222,6 +1233,9 @@ bpf_object__create_maps(struct bpf_object *obj)
 		create_attr.btf_fd = 0;
 		create_attr.btf_key_type_id = 0;
 		create_attr.btf_value_type_id = 0;
+		if (bpf_map_type__is_map_in_map(def->type) &&
+		    map->inner_map_fd >= 0)
+			create_attr.inner_map_fd = map->inner_map_fd;
 
 		if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
 			create_attr.btf_fd = btf__fd(obj->btf);
@@ -2681,6 +2695,20 @@ void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 	map->map_ifindex = ifindex;
 }
 
+int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd)
+{
+	if (!bpf_map_type__is_map_in_map(map->def.type)) {
+		pr_warning("error: unsupported map type\n");
+		return -EINVAL;
+	}
+	if (map->inner_map_fd != -1) {
+		pr_warning("error: inner_map_fd already specified\n");
+		return -EINVAL;
+	}
+	map->inner_map_fd = fd;
+	return 0;
+}
+
 static struct bpf_map *
 __bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
 {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 74e57e041705..f30c3d07bb7d 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -297,6 +297,8 @@ LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
 LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
 
+LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd);
+
 LIBBPF_API long libbpf_get_error(const void *ptr);
 
 struct bpf_prog_load_attr {
-- 
cgit v1.2.3


From b1957c92eba5acad7d8a0a6f968561e08714e978 Mon Sep 17 00:00:00 2001
From: "Nikita V. Shirokov" <tehnerd@tehnerd.com>
Date: Tue, 20 Nov 2018 20:55:57 -0800
Subject: bpf: adding tests for map_in_map helpber in libbpf

adding test/example of bpf_map__set_inner_map_fd usage

Signed-off-by: Nikita V. Shirokov <tehnerd@tehnerd.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile          |  3 +-
 tools/testing/selftests/bpf/test_map_in_map.c | 49 +++++++++++++++
 tools/testing/selftests/bpf/test_maps.c       | 90 +++++++++++++++++++++++++++
 3 files changed, 141 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/test_map_in_map.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 1dde03ea1484..43157bd89165 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -38,7 +38,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
 	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \
-	test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o
+	test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o \
+	test_map_in_map.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
diff --git a/tools/testing/selftests/bpf/test_map_in_map.c b/tools/testing/selftests/bpf/test_map_in_map.c
new file mode 100644
index 000000000000..ce923e67e08e
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_map_in_map.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") mim_array = {
+	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	.key_size = sizeof(int),
+	/* must be sizeof(__u32) for map in map */
+	.value_size = sizeof(__u32),
+	.max_entries = 1,
+	.map_flags = 0,
+};
+
+struct bpf_map_def SEC("maps") mim_hash = {
+	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
+	.key_size = sizeof(int),
+	/* must be sizeof(__u32) for map in map */
+	.value_size = sizeof(__u32),
+	.max_entries = 1,
+	.map_flags = 0,
+};
+
+SEC("xdp_mimtest")
+int xdp_mimtest0(struct xdp_md *ctx)
+{
+	int value = 123;
+	int key = 0;
+	void *map;
+
+	map = bpf_map_lookup_elem(&mim_array, &key);
+	if (!map)
+		return XDP_DROP;
+
+	bpf_map_update_elem(map, &key, &value, 0);
+
+	map = bpf_map_lookup_elem(&mim_hash, &key);
+	if (!map)
+		return XDP_DROP;
+
+	bpf_map_update_elem(map, &key, &value, 0);
+
+	return XDP_PASS;
+}
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 9f0a5b16a246..9c79ee017df3 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1125,6 +1125,94 @@ out_sockmap:
 	exit(1);
 }
 
+#define MAPINMAP_PROG "./test_map_in_map.o"
+static void test_map_in_map(void)
+{
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	struct bpf_map *map;
+	int mim_fd, fd, err;
+	int pos = 0;
+
+	obj = bpf_object__open(MAPINMAP_PROG);
+
+	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int), sizeof(int),
+			    2, 0);
+	if (fd < 0) {
+		printf("Failed to create hashmap '%s'!\n", strerror(errno));
+		exit(1);
+	}
+
+	map = bpf_object__find_map_by_name(obj, "mim_array");
+	if (IS_ERR(map)) {
+		printf("Failed to load array of maps from test prog\n");
+		goto out_map_in_map;
+	}
+	err = bpf_map__set_inner_map_fd(map, fd);
+	if (err) {
+		printf("Failed to set inner_map_fd for array of maps\n");
+		goto out_map_in_map;
+	}
+
+	map = bpf_object__find_map_by_name(obj, "mim_hash");
+	if (IS_ERR(map)) {
+		printf("Failed to load hash of maps from test prog\n");
+		goto out_map_in_map;
+	}
+	err = bpf_map__set_inner_map_fd(map, fd);
+	if (err) {
+		printf("Failed to set inner_map_fd for hash of maps\n");
+		goto out_map_in_map;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		bpf_program__set_xdp(prog);
+	}
+	bpf_object__load(obj);
+
+	map = bpf_object__find_map_by_name(obj, "mim_array");
+	if (IS_ERR(map)) {
+		printf("Failed to load array of maps from test prog\n");
+		goto out_map_in_map;
+	}
+	mim_fd = bpf_map__fd(map);
+	if (mim_fd < 0) {
+		printf("Failed to get descriptor for array of maps\n");
+		goto out_map_in_map;
+	}
+
+	err = bpf_map_update_elem(mim_fd, &pos, &fd, 0);
+	if (err) {
+		printf("Failed to update array of maps\n");
+		goto out_map_in_map;
+	}
+
+	map = bpf_object__find_map_by_name(obj, "mim_hash");
+	if (IS_ERR(map)) {
+		printf("Failed to load hash of maps from test prog\n");
+		goto out_map_in_map;
+	}
+	mim_fd = bpf_map__fd(map);
+	if (mim_fd < 0) {
+		printf("Failed to get descriptor for hash of maps\n");
+		goto out_map_in_map;
+	}
+
+	err = bpf_map_update_elem(mim_fd, &pos, &fd, 0);
+	if (err) {
+		printf("Failed to update hash of maps\n");
+		goto out_map_in_map;
+	}
+
+	close(fd);
+	bpf_object__close(obj);
+	return;
+
+out_map_in_map:
+	close(fd);
+	exit(1);
+}
+
 #define MAP_SIZE (32 * 1024)
 
 static void test_map_large(void)
@@ -1600,6 +1688,8 @@ static void run_all_tests(void)
 
 	test_queuemap(0, NULL);
 	test_stackmap(0, NULL);
+
+	test_map_in_map();
 }
 
 int main(void)
-- 
cgit v1.2.3


From a2e768b861108d846b6df21074cff738660b45b7 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Tue, 20 Nov 2018 13:20:31 +0100
Subject: net/vlan: introduce skb_vlan_tag_get_cfi() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Abstract CFI/DEI bit access consistently with other VLAN tag fields.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 7a541eadf78e..4cca4da7a6de 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -65,7 +65,7 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb)
 
 #define VLAN_PRIO_MASK		0xe000 /* Priority Code Point */
 #define VLAN_PRIO_SHIFT		13
-#define VLAN_CFI_MASK		0x1000 /* Canonical Format Indicator */
+#define VLAN_CFI_MASK		0x1000 /* Canonical Format Indicator / Drop Eligible Indicator */
 #define VLAN_VID_MASK		0x0fff /* VLAN Identifier */
 #define VLAN_N_VID		4096
 
@@ -80,6 +80,7 @@ static inline bool is_vlan_dev(const struct net_device *dev)
 #define skb_vlan_tag_present(__skb)	((__skb)->vlan_present)
 #define skb_vlan_tag_get(__skb)		((__skb)->vlan_tci)
 #define skb_vlan_tag_get_id(__skb)	((__skb)->vlan_tci & VLAN_VID_MASK)
+#define skb_vlan_tag_get_cfi(__skb)	(!!((__skb)->vlan_tci & VLAN_CFI_MASK))
 #define skb_vlan_tag_get_prio(__skb)	(((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT)
 
 static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev)
-- 
cgit v1.2.3


From 98ba780e4c71b9a66fa5819184879315a946aabb Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Tue, 20 Nov 2018 13:20:32 +0100
Subject: net/hyperv: use skb_vlan_tag_*() helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace open-coded bitfield manipulation with skb_vlan_tag_*() helpers.
This also enables correctly passing of VLAN.CFI bit.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index cf36e7ff3191..85936ed9e952 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -605,9 +605,9 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 				     IEEE_8021Q_INFO);
 
 		vlan->value = 0;
-		vlan->vlanid = skb->vlan_tci & VLAN_VID_MASK;
-		vlan->pri = (skb->vlan_tci & VLAN_PRIO_MASK) >>
-				VLAN_PRIO_SHIFT;
+		vlan->vlanid = skb_vlan_tag_get_id(skb);
+		vlan->cfi = skb_vlan_tag_get_cfi(skb);
+		vlan->pri = skb_vlan_tag_get_prio(skb);
 	}
 
 	if (skb_is_gso(skb)) {
@@ -781,7 +781,8 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
 	}
 
 	if (vlan) {
-		u16 vlan_tci = vlan->vlanid | (vlan->pri << VLAN_PRIO_SHIFT);
+		u16 vlan_tci = vlan->vlanid | (vlan->pri << VLAN_PRIO_SHIFT) |
+			(vlan->cfi ? VLAN_CFI_MASK : 0);
 
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
 				       vlan_tci);
-- 
cgit v1.2.3


From fb1e3df0023051a1be6f857eea80e7476ebb20ac Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Tue, 20 Nov 2018 13:20:32 +0100
Subject: benet: use skb_vlan_tag_get_prio()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 80b2bd3747ce..245abf0d19c0 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -796,7 +796,7 @@ static inline u16 be_get_tx_vlan_tag(struct be_adapter *adapter,
 	u16 vlan_tag;
 
 	vlan_tag = skb_vlan_tag_get(skb);
-	vlan_prio = (vlan_tag & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+	vlan_prio = skb_vlan_tag_get_prio(skb);
 	/* If vlan priority provided by OS is NOT in available bmap */
 	if (!(adapter->vlan_prio_bmap & (1 << vlan_prio)))
 		vlan_tag = (vlan_tag & ~VLAN_PRIO_MASK) |
-- 
cgit v1.2.3


From 6c0fbd726229fabecf8e8b631e3e134713eb30ef Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Tue, 20 Nov 2018 13:20:33 +0100
Subject: mlx5: use skb_vlan_tag_get_prio()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 6dacaeba2fbf..9afdf955f2bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -127,7 +127,7 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 	else
 #endif
 		if (skb_vlan_tag_present(skb))
-			up = skb->vlan_tci >> VLAN_PRIO_SHIFT;
+			up = skb_vlan_tag_get_prio(skb);
 
 	/* channel_ix can be larger than num_channels since
 	 * dev->num_real_tx_queues = num_channels * num_tc
-- 
cgit v1.2.3


From d59da3fbfe3f2bd9cbf29495e818b79d6349b12d Mon Sep 17 00:00:00 2001
From: Andrea Claudi <aclaudi@redhat.com>
Date: Tue, 20 Nov 2018 18:30:30 +0100
Subject: net: lpc_eth: fix trivial comment typo

Fix comment typo rxfliterctrl -> rxfilterctrl

Signed-off-by: Andrea Claudi <aclaudi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/nxp/lpc_eth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index bd8695a4faaa..89d17399fb5a 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -280,7 +280,7 @@
 #define LPC_FCCR_MIRRORCOUNTERCURRENT(n)	((n) & 0xFFFF)
 
 /*
- * rxfliterctrl, rxfilterwolstatus, and rxfilterwolclear shared
+ * rxfilterctrl, rxfilterwolstatus, and rxfilterwolclear shared
  * register definitions
  */
 #define LPC_RXFLTRW_ACCEPTUNICAST		(1 << 0)
@@ -291,7 +291,7 @@
 #define LPC_RXFLTRW_ACCEPTPERFECT		(1 << 5)
 
 /*
- * rxfliterctrl register definitions
+ * rxfilterctrl register definitions
  */
 #define LPC_RXFLTRWSTS_MAGICPACKETENWOL		(1 << 12)
 #define LPC_RXFLTRWSTS_RXFILTERENWOL		(1 << 13)
-- 
cgit v1.2.3


From 5572c815603b316d0807f18fbfabace7572cc0e2 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:34 +0000
Subject: vxlan: __vxlan_fdb_delete(): Drop unused argument vid

This argument is necessary for vxlan_fdb_delete(), the API of which is
prescribed by ndo_fdb_del, but __vxlan_fdb_delete() doesn't need it.
Therefore drop it.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index c3e65e78f015..99ab7844476f 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -977,7 +977,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 static int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 			      const unsigned char *addr, union vxlan_addr ip,
 			      __be16 port, __be32 src_vni, __be32 vni,
-			      u32 ifindex, u16 vid)
+			      u32 ifindex)
 {
 	struct vxlan_fdb *f;
 	struct vxlan_rdst *rd = NULL;
@@ -1024,8 +1024,7 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 		return err;
 
 	spin_lock_bh(&vxlan->hash_lock);
-	err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex,
-				 vid);
+	err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex);
 	spin_unlock_bh(&vxlan->hash_lock);
 
 	return err;
@@ -3611,7 +3610,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					   vxlan->cfg.dst_port,
 					   old_dst.remote_vni,
 					   old_dst.remote_vni,
-					   old_dst.remote_ifindex, 0);
+					   old_dst.remote_ifindex);
 
 		if (!vxlan_addr_any(&dst->remote_ip)) {
 			err = vxlan_fdb_create(vxlan, all_zeros_mac,
-- 
cgit v1.2.3


From 0e6160f3f5a9a817c3100f02e1605c49cbb2fe78 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:35 +0000
Subject: vxlan: vxlan_fdb_notify(): Make switchdev notification configurable

In a following patch, vxlan is extended to allow hardware FDB learning.
For FDB entries learned this way, switchdev notifications should not be
sent again, because the driver already knows about these entries.

To that end, add an argument vxlan_fdb_notify() to determine whether
the switchdev notifications should be sent. Propagate the argument to
all call sites transitively, eventually passing true in all root calls.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 71 +++++++++++++++++++++++++++++++----------------------
 1 file changed, 41 insertions(+), 30 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 99ab7844476f..441290464912 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -384,15 +384,19 @@ static void vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan,
 }
 
 static void vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb,
-			     struct vxlan_rdst *rd, int type)
+			     struct vxlan_rdst *rd, int type, bool swdev_notify)
 {
-	switch (type) {
-	case RTM_NEWNEIGH:
-		vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, true);
-		break;
-	case RTM_DELNEIGH:
-		vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, false);
-		break;
+	if (swdev_notify) {
+		switch (type) {
+		case RTM_NEWNEIGH:
+			vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd,
+							   true);
+			break;
+		case RTM_DELNEIGH:
+			vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd,
+							   false);
+			break;
+		}
 	}
 
 	__vxlan_fdb_notify(vxlan, fdb, rd, type);
@@ -409,7 +413,7 @@ static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa)
 		.remote_vni = cpu_to_be32(VXLAN_N_VID),
 	};
 
-	vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH);
+	vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true);
 }
 
 static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN])
@@ -421,7 +425,7 @@ static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN])
 
 	memcpy(f.eth_addr, eth_addr, ETH_ALEN);
 
-	vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH);
+	vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true);
 }
 
 /* Hash Ethernet address */
@@ -756,7 +760,8 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __u16 flags,
 			    __be16 port, __be32 src_vni, __be32 vni,
-			    __u32 ifindex, __u8 ndm_flags)
+			    __u32 ifindex, __u8 ndm_flags,
+			    bool swdev_notify)
 {
 	__u8 fdb_flags = (ndm_flags & ~NTF_USE);
 	struct vxlan_rdst *rd = NULL;
@@ -822,7 +827,7 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan,
 	if (notify) {
 		if (rd == NULL)
 			rd = first_remote_rtnl(f);
-		vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH);
+		vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH, swdev_notify);
 	}
 
 	return 0;
@@ -841,7 +846,7 @@ static void vxlan_fdb_free(struct rcu_head *head)
 }
 
 static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
-			      bool do_notify)
+			      bool do_notify, bool swdev_notify)
 {
 	struct vxlan_rdst *rd;
 
@@ -851,7 +856,8 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
 	--vxlan->addrcnt;
 	if (do_notify)
 		list_for_each_entry(rd, &f->remotes, list)
-			vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH);
+			vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH,
+					 swdev_notify);
 
 	hlist_del_rcu(&f->hlist);
 	call_rcu(&f->rcu, vxlan_fdb_free);
@@ -866,10 +872,10 @@ static void vxlan_dst_free(struct rcu_head *head)
 }
 
 static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
-				  struct vxlan_rdst *rd)
+				  struct vxlan_rdst *rd, bool swdev_notify)
 {
 	list_del_rcu(&rd->list);
-	vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH);
+	vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify);
 	call_rcu(&rd->rcu, vxlan_dst_free);
 }
 
@@ -968,7 +974,8 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 
 	spin_lock_bh(&vxlan->hash_lock);
 	err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
-			       port, src_vni, vni, ifindex, ndm->ndm_flags);
+			       port, src_vni, vni, ifindex, ndm->ndm_flags,
+			       true);
 	spin_unlock_bh(&vxlan->hash_lock);
 
 	return err;
@@ -977,7 +984,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 static int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 			      const unsigned char *addr, union vxlan_addr ip,
 			      __be16 port, __be32 src_vni, __be32 vni,
-			      u32 ifindex)
+			      u32 ifindex, bool swdev_notify)
 {
 	struct vxlan_fdb *f;
 	struct vxlan_rdst *rd = NULL;
@@ -997,11 +1004,11 @@ static int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 	 * otherwise destroy the fdb entry
 	 */
 	if (rd && !list_is_singular(&f->remotes)) {
-		vxlan_fdb_dst_destroy(vxlan, f, rd);
+		vxlan_fdb_dst_destroy(vxlan, f, rd, swdev_notify);
 		goto out;
 	}
 
-	vxlan_fdb_destroy(vxlan, f, true);
+	vxlan_fdb_destroy(vxlan, f, true, swdev_notify);
 
 out:
 	return 0;
@@ -1024,7 +1031,8 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 		return err;
 
 	spin_lock_bh(&vxlan->hash_lock);
-	err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex);
+	err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex,
+				 true);
 	spin_unlock_bh(&vxlan->hash_lock);
 
 	return err;
@@ -1102,7 +1110,7 @@ static bool vxlan_snoop(struct net_device *dev,
 
 		rdst->remote_ip = *src_ip;
 		f->updated = jiffies;
-		vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH);
+		vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true);
 	} else {
 		/* learned new entry */
 		spin_lock(&vxlan->hash_lock);
@@ -1115,7 +1123,7 @@ static bool vxlan_snoop(struct net_device *dev,
 					 vxlan->cfg.dst_port,
 					 vni,
 					 vxlan->default_dst.remote_vni,
-					 ifindex, NTF_SELF);
+					 ifindex, NTF_SELF, true);
 		spin_unlock(&vxlan->hash_lock);
 	}
 
@@ -2499,7 +2507,7 @@ static void vxlan_cleanup(struct timer_list *t)
 					   "garbage collect %pM\n",
 					   f->eth_addr);
 				f->state = NUD_STALE;
-				vxlan_fdb_destroy(vxlan, f, true);
+				vxlan_fdb_destroy(vxlan, f, true, true);
 			} else if (time_before(timeout, next_timer))
 				next_timer = timeout;
 		}
@@ -2550,7 +2558,7 @@ static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
 	spin_lock_bh(&vxlan->hash_lock);
 	f = __vxlan_find_mac(vxlan, all_zeros_mac, vni);
 	if (f)
-		vxlan_fdb_destroy(vxlan, f, true);
+		vxlan_fdb_destroy(vxlan, f, true, true);
 	spin_unlock_bh(&vxlan->hash_lock);
 }
 
@@ -2604,7 +2612,7 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all)
 				continue;
 			/* the all_zeros_mac entry is deleted at vxlan_uninit */
 			if (!is_zero_ether_addr(f->eth_addr))
-				vxlan_fdb_destroy(vxlan, f, true);
+				vxlan_fdb_destroy(vxlan, f, true, true);
 		}
 	}
 	spin_unlock_bh(&vxlan->hash_lock);
@@ -3342,13 +3350,14 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 
 	/* notify default fdb entry */
 	if (f)
-		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
+		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH,
+				 true);
 
 	list_add(&vxlan->next, &vn->vxlan_list);
 	return 0;
 errout:
 	if (f)
-		vxlan_fdb_destroy(vxlan, f, false);
+		vxlan_fdb_destroy(vxlan, f, false, false);
 	return err;
 }
 
@@ -3610,7 +3619,8 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					   vxlan->cfg.dst_port,
 					   old_dst.remote_vni,
 					   old_dst.remote_vni,
-					   old_dst.remote_ifindex);
+					   old_dst.remote_ifindex,
+					   true);
 
 		if (!vxlan_addr_any(&dst->remote_ip)) {
 			err = vxlan_fdb_create(vxlan, all_zeros_mac,
@@ -3625,7 +3635,8 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 				spin_unlock_bh(&vxlan->hash_lock);
 				return err;
 			}
-			vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
+			vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f),
+					 RTM_NEWNEIGH, true);
 		}
 		spin_unlock_bh(&vxlan->hash_lock);
 	}
-- 
cgit v1.2.3


From 45598c1cee69b9c7ce111fa634226ab335fafabe Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:36 +0000
Subject: vxlan: Mark user-added FDB entries

The VXLAN driver needs to differentiate between FDB entries learned by
the VXLAN driver, and those added by the user. The latter ones shouldn't
be taken over by external learning events. This is in accordance with
bridge behavior.

Therefore, extend the flags bitfield to 16 bits and add a new private
NTF flag to mark the user-added entries.

This seems preferable to adding a dedicated boolean, because passing the
flag, unlike passing e.g. a true, makes it clear what the meaning of the
bit is.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 17 +++++++++++------
 include/net/vxlan.h |  1 +
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 441290464912..9171c1f42fe9 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -79,9 +79,11 @@ struct vxlan_fdb {
 	u8		  eth_addr[ETH_ALEN];
 	u16		  state;	/* see ndm_state */
 	__be32		  vni;
-	u8		  flags;	/* see ndm_flags */
+	u16		  flags;	/* see ndm_flags and below */
 };
 
+#define NTF_VXLAN_ADDED_BY_USER 0x100
+
 /* salt for hash table */
 static u32 vxlan_salt __read_mostly;
 
@@ -376,6 +378,7 @@ static void vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan,
 		.remote_ifindex = rd->remote_ifindex,
 		.vni = fdb->vni,
 		.offloaded = rd->offloaded,
+		.added_by_user = fdb->flags & NTF_VXLAN_ADDED_BY_USER,
 	};
 	memcpy(info.eth_addr, fdb->eth_addr, ETH_ALEN);
 
@@ -544,6 +547,7 @@ int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni,
 	fdb_info->remote_ifindex = rdst->remote_ifindex;
 	fdb_info->vni = vni;
 	fdb_info->offloaded = rdst->offloaded;
+	fdb_info->added_by_user = f->flags & NTF_VXLAN_ADDED_BY_USER;
 	ether_addr_copy(fdb_info->eth_addr, mac);
 
 out:
@@ -704,7 +708,7 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 
 static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
 					 const u8 *mac, __u16 state,
-					 __be32 src_vni, __u8 ndm_flags)
+					 __be32 src_vni, __u16 ndm_flags)
 {
 	struct vxlan_fdb *f;
 
@@ -724,7 +728,7 @@ static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __be16 port, __be32 src_vni,
-			    __be32 vni, __u32 ifindex, __u8 ndm_flags,
+			    __be32 vni, __u32 ifindex, __u16 ndm_flags,
 			    struct vxlan_fdb **fdb)
 {
 	struct vxlan_rdst *rd = NULL;
@@ -760,10 +764,10 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __u16 flags,
 			    __be16 port, __be32 src_vni, __be32 vni,
-			    __u32 ifindex, __u8 ndm_flags,
+			    __u32 ifindex, __u16 ndm_flags,
 			    bool swdev_notify)
 {
-	__u8 fdb_flags = (ndm_flags & ~NTF_USE);
+	__u16 fdb_flags = (ndm_flags & ~NTF_USE);
 	struct vxlan_rdst *rd = NULL;
 	struct vxlan_fdb *f;
 	int notify = 0;
@@ -974,7 +978,8 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 
 	spin_lock_bh(&vxlan->hash_lock);
 	err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
-			       port, src_vni, vni, ifindex, ndm->ndm_flags,
+			       port, src_vni, vni, ifindex,
+			       ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER,
 			       true);
 	spin_unlock_bh(&vxlan->hash_lock);
 
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index ec999c49df1f..b73c670df184 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -421,6 +421,7 @@ struct switchdev_notifier_vxlan_fdb_info {
 	u8 eth_addr[ETH_ALEN];
 	__be32 vni;
 	bool offloaded;
+	bool added_by_user;
 };
 
 #if IS_ENABLED(CONFIG_VXLAN)
-- 
cgit v1.2.3


From 0ec566aacc26da9292cddfe7109a467ac8a8d9a6 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:37 +0000
Subject: vxlan: Don't override user-added entries with ext-learned ones

When an external learning event collides with an user-added entry, the
user-added entry shouldn't be taken over. Otherwise on an unlearn event
the entry would be completely lost, even though the user added it by
hand.

Therefore skip update of FDB flags and state for these cases. This is in
accordance with the bridge behavior.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 9171c1f42fe9..b50705a50686 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -780,16 +780,24 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan,
 				   "lost race to create %pM\n", mac);
 			return -EEXIST;
 		}
-		if (f->state != state) {
-			f->state = state;
-			f->updated = jiffies;
-			notify = 1;
-		}
-		if (f->flags != fdb_flags) {
-			f->flags = fdb_flags;
-			f->updated = jiffies;
-			notify = 1;
+
+		/* Do not allow an externally learned entry to take over an
+		 * entry added by the user.
+		 */
+		if (!(fdb_flags & NTF_EXT_LEARNED) ||
+		    !(f->flags & NTF_VXLAN_ADDED_BY_USER)) {
+			if (f->state != state) {
+				f->state = state;
+				f->updated = jiffies;
+				notify = 1;
+			}
+			if (f->flags != fdb_flags) {
+				f->flags = fdb_flags;
+				f->updated = jiffies;
+				notify = 1;
+			}
 		}
+
 		if ((flags & NLM_F_REPLACE)) {
 			/* Only change unicasts */
 			if (!(is_multicast_ether_addr(f->eth_addr) ||
-- 
cgit v1.2.3


From 5728ae0d17d27e14b7e5034f73a38b562cfcd5c5 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:39 +0000
Subject: vxlan: Add hardware FDB learning

In order to allow devices to signal learning events to VXLAN, introduce
two new switchdev messages: SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE and
SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE.

Listen to these notifications in the vxlan driver. The FDB entries
learned this way have an NTF_EXT_LEARNED flag, and only entries marked
as such can be unlearned by the _DEL_ event. They are also immediately
marked as offloaded. This is the same behavior that the bridge driver
observes.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c     | 73 ++++++++++++++++++++++++++++++++++++++++++++++++-
 include/net/switchdev.h |  2 ++
 2 files changed, 74 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index b50705a50686..03ba1b56ba6d 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3923,18 +3923,89 @@ out:
 	spin_unlock_bh(&vxlan->hash_lock);
 }
 
+static int
+vxlan_fdb_external_learn_add(struct net_device *dev,
+			     struct switchdev_notifier_vxlan_fdb_info *fdb_info)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	int err;
+
+	spin_lock_bh(&vxlan->hash_lock);
+	err = vxlan_fdb_update(vxlan, fdb_info->eth_addr, &fdb_info->remote_ip,
+			       NUD_REACHABLE,
+			       NLM_F_CREATE | NLM_F_REPLACE,
+			       fdb_info->remote_port,
+			       fdb_info->vni,
+			       fdb_info->remote_vni,
+			       fdb_info->remote_ifindex,
+			       NTF_USE | NTF_SELF | NTF_EXT_LEARNED,
+			       false);
+	spin_unlock_bh(&vxlan->hash_lock);
+
+	return err;
+}
+
+static int
+vxlan_fdb_external_learn_del(struct net_device *dev,
+			     struct switchdev_notifier_vxlan_fdb_info *fdb_info)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_fdb *f;
+	int err = 0;
+
+	spin_lock_bh(&vxlan->hash_lock);
+
+	f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
+	if (!f)
+		err = -ENOENT;
+	else if (f->flags & NTF_EXT_LEARNED)
+		err = __vxlan_fdb_delete(vxlan, fdb_info->eth_addr,
+					 fdb_info->remote_ip,
+					 fdb_info->remote_port,
+					 fdb_info->vni,
+					 fdb_info->remote_vni,
+					 fdb_info->remote_ifindex,
+					 false);
+
+	spin_unlock_bh(&vxlan->hash_lock);
+
+	return err;
+}
+
 static int vxlan_switchdev_event(struct notifier_block *unused,
 				 unsigned long event, void *ptr)
 {
 	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	struct switchdev_notifier_vxlan_fdb_info *fdb_info;
+	int err = 0;
 
 	switch (event) {
 	case SWITCHDEV_VXLAN_FDB_OFFLOADED:
 		vxlan_fdb_offloaded_set(dev, ptr);
 		break;
+	case SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE:
+		fdb_info = ptr;
+		err = vxlan_fdb_external_learn_add(dev, fdb_info);
+		if (err) {
+			err = notifier_from_errno(err);
+			break;
+		}
+		fdb_info->offloaded = true;
+		vxlan_fdb_offloaded_set(dev, fdb_info);
+		break;
+	case SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE:
+		fdb_info = ptr;
+		err = vxlan_fdb_external_learn_del(dev, fdb_info);
+		if (err) {
+			err = notifier_from_errno(err);
+			break;
+		}
+		fdb_info->offloaded = false;
+		vxlan_fdb_offloaded_set(dev, fdb_info);
+		break;
 	}
 
-	return 0;
+	return err;
 }
 
 static struct notifier_block vxlan_switchdev_notifier_block __read_mostly = {
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 881ecb1555bf..7b371e7c4bc6 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -146,6 +146,8 @@ enum switchdev_notifier_type {
 	SWITCHDEV_FDB_DEL_TO_DEVICE,
 	SWITCHDEV_FDB_OFFLOADED,
 
+	SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE,
+	SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE,
 	SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE,
 	SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE,
 	SWITCHDEV_VXLAN_FDB_OFFLOADED,
-- 
cgit v1.2.3


From 40051c4dcad5b374156ad9cceae8d15c0ef1cb95 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:40 +0000
Subject: vxlan: Allow changing ageing time

In a similar fashion to the bridge device, allow changing the ageing
time of the VxLAN device by scheduling its timer to fire if the ageing
time changed.

One use case is selftests where learning / ageing of VxLAN FDB entries
is tested. The default ageing time is 5 minutes, which is too long for a
simple selftest.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 03ba1b56ba6d..911066299a83 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3458,11 +3458,8 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 		conf->flags |= VXLAN_F_LEARN;
 	}
 
-	if (data[IFLA_VXLAN_AGEING]) {
-		if (changelink)
-			return -EOPNOTSUPP;
+	if (data[IFLA_VXLAN_AGEING])
 		conf->age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]);
-	}
 
 	if (data[IFLA_VXLAN_PROXY]) {
 		if (changelink)
@@ -3607,6 +3604,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_rdst *dst = &vxlan->default_dst;
+	unsigned long old_age_interval;
 	struct vxlan_rdst old_dst;
 	struct vxlan_config conf;
 	struct vxlan_fdb *f = NULL;
@@ -3617,12 +3615,16 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (err)
 		return err;
 
+	old_age_interval = vxlan->cfg.age_interval;
 	memcpy(&old_dst, dst, sizeof(struct vxlan_rdst));
 
 	err = vxlan_dev_configure(vxlan->net, dev, &conf, true, extack);
 	if (err)
 		return err;
 
+	if (old_age_interval != vxlan->cfg.age_interval)
+		mod_timer(&vxlan->age_timer, jiffies);
+
 	/* handle default dst entry */
 	if (!vxlan_addr_equal(&dst->remote_ip, &old_dst.remote_ip)) {
 		spin_lock_bh(&vxlan->hash_lock);
-- 
cgit v1.2.3


From 085ddc87d05fdf649ccee7a7da42110e9e1c6311 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:41 +0000
Subject: bridge: Allow querying bridge port flags

Allow querying bridge port flags so that drivers capable of performing
VxLAN learning will update the bridge driver only if learning is enabled
on its bridge port corresponding to the VxLAN device.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h |  6 ++++++
 net/bridge/br_if.c        | 12 ++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index c20c7e197d07..ef7c3d376b21 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -119,6 +119,7 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid,
 struct net_device *br_fdb_find_port(const struct net_device *br_dev,
 				    const unsigned char *addr,
 				    __u16 vid);
+bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag);
 #else
 static inline struct net_device *
 br_fdb_find_port(const struct net_device *br_dev,
@@ -127,6 +128,11 @@ br_fdb_find_port(const struct net_device *br_dev,
 {
 	return NULL;
 }
+static inline bool
+br_port_flag_is_set(const struct net_device *dev, unsigned long flag)
+{
+	return false;
+}
 #endif
 
 #endif
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 9b46d2dc4c22..d4863f5679ac 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -741,3 +741,15 @@ void br_port_flags_change(struct net_bridge_port *p, unsigned long mask)
 	if (mask & BR_NEIGH_SUPPRESS)
 		br_recalculate_neigh_suppress_enabled(br);
 }
+
+bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag)
+{
+	struct net_bridge_port *p;
+
+	p = br_port_get_rtnl_rcu(dev);
+	if (!p)
+		return false;
+
+	return p->flags & flag;
+}
+EXPORT_SYMBOL_GPL(br_port_flag_is_set);
-- 
cgit v1.2.3


From 933b1ecd001de3db4e94ba34b83f4eb3c0aa78d8 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:42 +0000
Subject: mlxsw: reg: Add definition of unicast tunnel record for SFN register

Will be used to process learned FDB records from an NVE tunnel.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 64 +++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index be2ffbd19e3a..5c8a38f61a93 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -641,6 +641,10 @@ enum mlxsw_reg_sfn_rec_type {
 	MLXSW_REG_SFN_REC_TYPE_AGED_OUT_MAC = 0x7,
 	/* Aged-out MAC address on a LAG port. */
 	MLXSW_REG_SFN_REC_TYPE_AGED_OUT_MAC_LAG = 0x8,
+	/* Learned unicast tunnel record. */
+	MLXSW_REG_SFN_REC_TYPE_LEARNED_UNICAST_TUNNEL = 0xD,
+	/* Aged-out unicast tunnel record. */
+	MLXSW_REG_SFN_REC_TYPE_AGED_OUT_UNICAST_TUNNEL = 0xE,
 };
 
 /* reg_sfn_rec_type
@@ -704,6 +708,66 @@ static inline void mlxsw_reg_sfn_mac_lag_unpack(char *payload, int rec_index,
 	*p_lag_id = mlxsw_reg_sfn_mac_lag_lag_id_get(payload, rec_index);
 }
 
+/* reg_sfn_uc_tunnel_uip_msb
+ * When protocol is IPv4, the most significant byte of the underlay IPv4
+ * address of the remote VTEP.
+ * When protocol is IPv6, reserved.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, sfn, uc_tunnel_uip_msb, MLXSW_REG_SFN_BASE_LEN, 24,
+		     8, MLXSW_REG_SFN_REC_LEN, 0x08, false);
+
+enum mlxsw_reg_sfn_uc_tunnel_protocol {
+	MLXSW_REG_SFN_UC_TUNNEL_PROTOCOL_IPV4,
+	MLXSW_REG_SFN_UC_TUNNEL_PROTOCOL_IPV6,
+};
+
+/* reg_sfn_uc_tunnel_protocol
+ * IP protocol.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, sfn, uc_tunnel_protocol, MLXSW_REG_SFN_BASE_LEN, 27,
+		     1, MLXSW_REG_SFN_REC_LEN, 0x0C, false);
+
+/* reg_sfn_uc_tunnel_uip_lsb
+ * When protocol is IPv4, the least significant bytes of the underlay
+ * IPv4 address of the remote VTEP.
+ * When protocol is IPv6, ipv6_id to be queried from TNIPSD.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, sfn, uc_tunnel_uip_lsb, MLXSW_REG_SFN_BASE_LEN, 0,
+		     24, MLXSW_REG_SFN_REC_LEN, 0x0C, false);
+
+enum mlxsw_reg_sfn_tunnel_port {
+	MLXSW_REG_SFN_TUNNEL_PORT_NVE,
+	MLXSW_REG_SFN_TUNNEL_PORT_VPLS,
+	MLXSW_REG_SFN_TUNNEL_FLEX_TUNNEL0,
+	MLXSW_REG_SFN_TUNNEL_FLEX_TUNNEL1,
+};
+
+/* reg_sfn_uc_tunnel_port
+ * Tunnel port.
+ * Reserved on Spectrum.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, sfn, tunnel_port, MLXSW_REG_SFN_BASE_LEN, 0, 4,
+		     MLXSW_REG_SFN_REC_LEN, 0x10, false);
+
+static inline void
+mlxsw_reg_sfn_uc_tunnel_unpack(char *payload, int rec_index, char *mac,
+			       u16 *p_fid, u32 *p_uip,
+			       enum mlxsw_reg_sfn_uc_tunnel_protocol *p_proto)
+{
+	u32 uip_msb, uip_lsb;
+
+	mlxsw_reg_sfn_rec_mac_memcpy_from(payload, rec_index, mac);
+	*p_fid = mlxsw_reg_sfn_mac_fid_get(payload, rec_index);
+	uip_msb = mlxsw_reg_sfn_uc_tunnel_uip_msb_get(payload, rec_index);
+	uip_lsb = mlxsw_reg_sfn_uc_tunnel_uip_lsb_get(payload, rec_index);
+	*p_uip = uip_msb << 24 | uip_lsb;
+	*p_proto = mlxsw_reg_sfn_uc_tunnel_protocol_get(payload, rec_index);
+}
+
 /* SPMS - Switch Port MSTP/RSTP State Register
  * -------------------------------------------
  * Configures the spanning tree state of a physical port.
-- 
cgit v1.2.3


From 5bae63d9b7627939eb67a7720548c82562ef7fa3 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:44 +0000
Subject: mlxsw: spectrum_fid: Store ifindex of NVE device in FID

The driver periodically polls for new FDB entries learned by the device.
In the case of an FDB entry learned from a VxLAN tunnel, the
notification includes the IP of the remote VTEP, the filtering
identifier (FID) and the source MAC address of the overlay packet.

Assuming learning is enabled in the VxLAN and bridge drivers, the driver
needs to generate a notification and update them about the new FDB
entry.

Store the ifindex of the NVE device in the FID so that the driver will
be able to update the VxLAN and bridge drivers using it.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  3 ++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c | 14 +++++++++++++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c |  2 +-
 3 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 0875a79cbe7b..b8f00863a0c6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -721,6 +721,7 @@ int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port,
 			   struct tc_prio_qopt_offload *p);
 
 /* spectrum_fid.c */
+int mlxsw_sp_fid_nve_ifindex(const struct mlxsw_sp_fid *fid, int *nve_ifindex);
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_vni(struct mlxsw_sp *mlxsw_sp,
 						__be32 vni);
 int mlxsw_sp_fid_vni(const struct mlxsw_sp_fid *fid, __be32 *vni);
@@ -728,7 +729,7 @@ int mlxsw_sp_fid_nve_flood_index_set(struct mlxsw_sp_fid *fid,
 				     u32 nve_flood_index);
 void mlxsw_sp_fid_nve_flood_index_clear(struct mlxsw_sp_fid *fid);
 bool mlxsw_sp_fid_nve_flood_index_is_set(const struct mlxsw_sp_fid *fid);
-int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, __be32 vni);
+int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, __be32 vni, int nve_ifindex);
 void mlxsw_sp_fid_vni_clear(struct mlxsw_sp_fid *fid);
 bool mlxsw_sp_fid_vni_is_set(const struct mlxsw_sp_fid *fid);
 int mlxsw_sp_fid_flood_set(struct mlxsw_sp_fid *fid,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index a3db033d7399..ad2bc8e3b2ed 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -30,6 +30,7 @@ struct mlxsw_sp_fid {
 	struct rhash_head vni_ht_node;
 	__be32 vni;
 	u32 nve_flood_index;
+	int nve_ifindex;
 	u8 vni_valid:1,
 	   nve_flood_index_valid:1;
 };
@@ -113,6 +114,16 @@ static const int *mlxsw_sp_packet_type_sfgc_types[] = {
 	[MLXSW_SP_FLOOD_TYPE_MC]	= mlxsw_sp_sfgc_mc_packet_types,
 };
 
+int mlxsw_sp_fid_nve_ifindex(const struct mlxsw_sp_fid *fid, int *nve_ifindex)
+{
+	if (!fid->vni_valid)
+		return -EINVAL;
+
+	*nve_ifindex = fid->nve_ifindex;
+
+	return 0;
+}
+
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_vni(struct mlxsw_sp *mlxsw_sp,
 						__be32 vni)
 {
@@ -173,7 +184,7 @@ bool mlxsw_sp_fid_nve_flood_index_is_set(const struct mlxsw_sp_fid *fid)
 	return fid->nve_flood_index_valid;
 }
 
-int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, __be32 vni)
+int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, __be32 vni, int nve_ifindex)
 {
 	struct mlxsw_sp_fid_family *fid_family = fid->fid_family;
 	const struct mlxsw_sp_fid_ops *ops = fid_family->ops;
@@ -183,6 +194,7 @@ int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, __be32 vni)
 	if (WARN_ON(!ops->vni_set || fid->vni_valid))
 		return -EINVAL;
 
+	fid->nve_ifindex = nve_ifindex;
 	fid->vni = vni;
 	err = rhashtable_lookup_insert_fast(&mlxsw_sp->fid_core->vni_ht,
 					    &fid->vni_ht_node,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
index ad06d9969bc1..4498e3b3c3f0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
@@ -803,7 +803,7 @@ int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid,
 		return err;
 	}
 
-	err = mlxsw_sp_fid_vni_set(fid, params->vni);
+	err = mlxsw_sp_fid_vni_set(fid, params->vni, params->dev->ifindex);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed to set VNI on FID");
 		goto err_fid_vni_set;
-- 
cgit v1.2.3


From 5d44a712e6af87842b6d3a01481ff020d1d2fddd Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:45 +0000
Subject: mlxsw: spectrum_fid: Allow FID lookup by its index

When processing a notification about a new FDB entry learned from a
VxLAN tunnel, the driver is provided with the FID index among other
parameters.

The driver potentially needs to update the bridge and VxLAN drivers
about the new entry using a pointer to the VxLAN device and the
corresponding VNI.

These two parameters are stored in the FID, so add a new function that
allows looking up a FID based on its index.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  2 ++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c | 42 ++++++++++++++++++++--
 2 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index b8f00863a0c6..879ac65886af 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -721,6 +721,8 @@ int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port,
 			   struct tc_prio_qopt_offload *p);
 
 /* spectrum_fid.c */
+struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp,
+						  u16 fid_index);
 int mlxsw_sp_fid_nve_ifindex(const struct mlxsw_sp_fid *fid, int *nve_ifindex);
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_vni(struct mlxsw_sp *mlxsw_sp,
 						__be32 vni);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index ad2bc8e3b2ed..71b2d20afcc2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -15,6 +15,7 @@
 struct mlxsw_sp_fid_family;
 
 struct mlxsw_sp_fid_core {
+	struct rhashtable fid_ht;
 	struct rhashtable vni_ht;
 	struct mlxsw_sp_fid_family *fid_family_arr[MLXSW_SP_FID_TYPE_MAX];
 	unsigned int *port_fid_mappings;
@@ -26,6 +27,7 @@ struct mlxsw_sp_fid {
 	unsigned int ref_count;
 	u16 fid_index;
 	struct mlxsw_sp_fid_family *fid_family;
+	struct rhash_head ht_node;
 
 	struct rhash_head vni_ht_node;
 	__be32 vni;
@@ -45,6 +47,12 @@ struct mlxsw_sp_fid_8021d {
 	int br_ifindex;
 };
 
+static const struct rhashtable_params mlxsw_sp_fid_ht_params = {
+	.key_len = sizeof_field(struct mlxsw_sp_fid, fid_index),
+	.key_offset = offsetof(struct mlxsw_sp_fid, fid_index),
+	.head_offset = offsetof(struct mlxsw_sp_fid, ht_node),
+};
+
 static const struct rhashtable_params mlxsw_sp_fid_vni_ht_params = {
 	.key_len = sizeof_field(struct mlxsw_sp_fid, vni),
 	.key_offset = offsetof(struct mlxsw_sp_fid, vni),
@@ -114,6 +122,19 @@ static const int *mlxsw_sp_packet_type_sfgc_types[] = {
 	[MLXSW_SP_FLOOD_TYPE_MC]	= mlxsw_sp_sfgc_mc_packet_types,
 };
 
+struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp,
+						  u16 fid_index)
+{
+	struct mlxsw_sp_fid *fid;
+
+	fid = rhashtable_lookup_fast(&mlxsw_sp->fid_core->fid_ht, &fid_index,
+				     mlxsw_sp_fid_ht_params);
+	if (fid)
+		fid->ref_count++;
+
+	return fid;
+}
+
 int mlxsw_sp_fid_nve_ifindex(const struct mlxsw_sp_fid *fid, int *nve_ifindex)
 {
 	if (!fid->vni_valid)
@@ -956,10 +977,17 @@ static struct mlxsw_sp_fid *mlxsw_sp_fid_get(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_configure;
 
+	err = rhashtable_insert_fast(&mlxsw_sp->fid_core->fid_ht, &fid->ht_node,
+				     mlxsw_sp_fid_ht_params);
+	if (err)
+		goto err_rhashtable_insert;
+
 	list_add(&fid->list, &fid_family->fids_list);
 	fid->ref_count++;
 	return fid;
 
+err_rhashtable_insert:
+	fid->fid_family->ops->deconfigure(fid);
 err_configure:
 	__clear_bit(fid_index - fid_family->start_index,
 		    fid_family->fids_bitmap);
@@ -971,6 +999,7 @@ err_index_alloc:
 void mlxsw_sp_fid_put(struct mlxsw_sp_fid *fid)
 {
 	struct mlxsw_sp_fid_family *fid_family = fid->fid_family;
+	struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp;
 
 	if (--fid->ref_count == 1 && fid->rif) {
 		/* Destroy the associated RIF and let it drop the last
@@ -979,6 +1008,8 @@ void mlxsw_sp_fid_put(struct mlxsw_sp_fid *fid)
 		return mlxsw_sp_rif_destroy(fid->rif);
 	} else if (fid->ref_count == 0) {
 		list_del(&fid->list);
+		rhashtable_remove_fast(&mlxsw_sp->fid_core->fid_ht,
+				       &fid->ht_node, mlxsw_sp_fid_ht_params);
 		fid->fid_family->ops->deconfigure(fid);
 		__clear_bit(fid->fid_index - fid_family->start_index,
 			    fid_family->fids_bitmap);
@@ -1138,9 +1169,13 @@ int mlxsw_sp_fids_init(struct mlxsw_sp *mlxsw_sp)
 		return -ENOMEM;
 	mlxsw_sp->fid_core = fid_core;
 
+	err = rhashtable_init(&fid_core->fid_ht, &mlxsw_sp_fid_ht_params);
+	if (err)
+		goto err_rhashtable_fid_init;
+
 	err = rhashtable_init(&fid_core->vni_ht, &mlxsw_sp_fid_vni_ht_params);
 	if (err)
-		goto err_rhashtable_init;
+		goto err_rhashtable_vni_init;
 
 	fid_core->port_fid_mappings = kcalloc(max_ports, sizeof(unsigned int),
 					      GFP_KERNEL);
@@ -1169,7 +1204,9 @@ err_fid_ops_register:
 	kfree(fid_core->port_fid_mappings);
 err_alloc_port_fid_mappings:
 	rhashtable_destroy(&fid_core->vni_ht);
-err_rhashtable_init:
+err_rhashtable_vni_init:
+	rhashtable_destroy(&fid_core->fid_ht);
+err_rhashtable_fid_init:
 	kfree(fid_core);
 	return err;
 }
@@ -1184,5 +1221,6 @@ void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp)
 					       fid_core->fid_family_arr[i]);
 	kfree(fid_core->port_fid_mappings);
 	rhashtable_destroy(&fid_core->vni_ht);
+	rhashtable_destroy(&fid_core->fid_ht);
 	kfree(fid_core);
 }
-- 
cgit v1.2.3


From 3c55bdaca015839ca1d1e5695e7667a9bcfa6e35 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:46 +0000
Subject: mlxsw: spectrum_nve: Add API to resolve learned IP addresses

FDB notifications for entries learned from an NVE tunnel contain the IP
address of the remote VTEP. In the case of IPv4 underlay, the IP address
is specified as-is. IPv6 addresses on the other hand, are specified as
handles which then need to be used to query the actual address from the
device.

Only IPv4 underlay is currently supported, so we cannot receive
notifications for IPv6 addresses and therefore an error is returned when
one tries to resolve such an address.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  3 +++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c | 14 ++++++++++++++
 2 files changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 879ac65886af..973a9d2901f7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -813,6 +813,9 @@ struct mlxsw_sp_nve_params {
 extern const struct mlxsw_sp_nve_ops *mlxsw_sp1_nve_ops_arr[];
 extern const struct mlxsw_sp_nve_ops *mlxsw_sp2_nve_ops_arr[];
 
+int mlxsw_sp_nve_learned_ip_resolve(struct mlxsw_sp *mlxsw_sp, u32 uip,
+				    enum mlxsw_sp_l3proto proto,
+				    union mlxsw_sp_l3addr *addr);
 int mlxsw_sp_nve_flood_ip_add(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_fid *fid,
 			      enum mlxsw_sp_l3proto proto,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
index 4498e3b3c3f0..c4d5a0865c8f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
@@ -174,6 +174,20 @@ mlxsw_sp_nve_mc_record_ops_arr[] = {
 	[MLXSW_SP_L3_PROTO_IPV6] = &mlxsw_sp_nve_mc_record_ipv6_ops,
 };
 
+int mlxsw_sp_nve_learned_ip_resolve(struct mlxsw_sp *mlxsw_sp, u32 uip,
+				    enum mlxsw_sp_l3proto proto,
+				    union mlxsw_sp_l3addr *addr)
+{
+	switch (proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		addr->addr4 = cpu_to_be32(uip);
+		return 0;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+}
+
 static struct mlxsw_sp_nve_mc_list *
 mlxsw_sp_nve_mc_list_find(struct mlxsw_sp *mlxsw_sp,
 			  const struct mlxsw_sp_nve_mc_list_key *key)
-- 
cgit v1.2.3


From 981f084b36754b4e5179e8a3fbba554ba0183f0a Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:47 +0000
Subject: mlxsw: spectrum_switchdev: Process learned VxLAN FDB entries

Start processing two new entry types in addition to current ones:
* Learned unicast tunnel entry
* Aged-out unicast tunnel entry

In both cases the device reports on a new {MAC, FID, IP address} tuple
that was learned / aged-out. Based on this notification, the driver
instructs the device to add / delete the entry to / from its database.

The driver also makes sure to notify the bridge and VxLAN drivers about
the new entry.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 203 +++++++++++++++++++--
 1 file changed, 189 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 739a51f0a366..d3d1c1d00d98 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2311,6 +2311,71 @@ void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 	bridge_device->ops->vxlan_leave(bridge_device, vxlan_dev);
 }
 
+static void
+mlxsw_sp_switchdev_vxlan_addr_convert(const union vxlan_addr *vxlan_addr,
+				      enum mlxsw_sp_l3proto *proto,
+				      union mlxsw_sp_l3addr *addr)
+{
+	if (vxlan_addr->sa.sa_family == AF_INET) {
+		addr->addr4 = vxlan_addr->sin.sin_addr.s_addr;
+		*proto = MLXSW_SP_L3_PROTO_IPV4;
+	} else {
+		addr->addr6 = vxlan_addr->sin6.sin6_addr;
+		*proto = MLXSW_SP_L3_PROTO_IPV6;
+	}
+}
+
+static void
+mlxsw_sp_switchdev_addr_vxlan_convert(enum mlxsw_sp_l3proto proto,
+				      const union mlxsw_sp_l3addr *addr,
+				      union vxlan_addr *vxlan_addr)
+{
+	switch (proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		vxlan_addr->sa.sa_family = AF_INET;
+		vxlan_addr->sin.sin_addr.s_addr = addr->addr4;
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		vxlan_addr->sa.sa_family = AF_INET6;
+		vxlan_addr->sin6.sin6_addr = addr->addr6;
+		break;
+	}
+}
+
+static void mlxsw_sp_fdb_vxlan_call_notifiers(struct net_device *dev,
+					      const char *mac,
+					      enum mlxsw_sp_l3proto proto,
+					      union mlxsw_sp_l3addr *addr,
+					      __be32 vni, bool adding)
+{
+	struct switchdev_notifier_vxlan_fdb_info info;
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	enum switchdev_notifier_type type;
+
+	type = adding ? SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE :
+			SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE;
+	mlxsw_sp_switchdev_addr_vxlan_convert(proto, addr, &info.remote_ip);
+	info.remote_port = vxlan->cfg.dst_port;
+	info.remote_vni = vni;
+	info.remote_ifindex = 0;
+	ether_addr_copy(info.eth_addr, mac);
+	info.vni = vni;
+	info.offloaded = adding;
+	call_switchdev_notifiers(type, dev, &info.info);
+}
+
+static void mlxsw_sp_fdb_nve_call_notifiers(struct net_device *dev,
+					    const char *mac,
+					    enum mlxsw_sp_l3proto proto,
+					    union mlxsw_sp_l3addr *addr,
+					    __be32 vni,
+					    bool adding)
+{
+	if (netif_is_vxlan(dev))
+		mlxsw_sp_fdb_vxlan_call_notifiers(dev, mac, proto, addr, vni,
+						  adding);
+}
+
 static void
 mlxsw_sp_fdb_call_notifiers(enum switchdev_notifier_type type,
 			    const char *mac, u16 vid,
@@ -2442,6 +2507,122 @@ just_remove:
 	goto do_fdb_op;
 }
 
+static int
+__mlxsw_sp_fdb_notify_mac_uc_tunnel_process(struct mlxsw_sp *mlxsw_sp,
+					    const struct mlxsw_sp_fid *fid,
+					    bool adding,
+					    struct net_device **nve_dev,
+					    u16 *p_vid, __be32 *p_vni)
+{
+	struct mlxsw_sp_bridge_device *bridge_device;
+	struct net_device *br_dev, *dev;
+	int nve_ifindex;
+	int err;
+
+	err = mlxsw_sp_fid_nve_ifindex(fid, &nve_ifindex);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_fid_vni(fid, p_vni);
+	if (err)
+		return err;
+
+	dev = __dev_get_by_index(&init_net, nve_ifindex);
+	if (!dev)
+		return -EINVAL;
+	*nve_dev = dev;
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	if (adding && !br_port_flag_is_set(dev, BR_LEARNING))
+		return -EINVAL;
+
+	if (adding && netif_is_vxlan(dev)) {
+		struct vxlan_dev *vxlan = netdev_priv(dev);
+
+		if (!(vxlan->cfg.flags & VXLAN_F_LEARN))
+			return -EINVAL;
+	}
+
+	br_dev = netdev_master_upper_dev_get(dev);
+	if (!br_dev)
+		return -EINVAL;
+
+	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
+	if (!bridge_device)
+		return -EINVAL;
+
+	*p_vid = bridge_device->ops->fid_vid(bridge_device, fid);
+
+	return 0;
+}
+
+static void mlxsw_sp_fdb_notify_mac_uc_tunnel_process(struct mlxsw_sp *mlxsw_sp,
+						      char *sfn_pl,
+						      int rec_index,
+						      bool adding)
+{
+	enum mlxsw_reg_sfn_uc_tunnel_protocol sfn_proto;
+	enum switchdev_notifier_type type;
+	struct net_device *nve_dev;
+	union mlxsw_sp_l3addr addr;
+	struct mlxsw_sp_fid *fid;
+	char mac[ETH_ALEN];
+	u16 fid_index, vid;
+	__be32 vni;
+	u32 uip;
+	int err;
+
+	mlxsw_reg_sfn_uc_tunnel_unpack(sfn_pl, rec_index, mac, &fid_index,
+				       &uip, &sfn_proto);
+
+	fid = mlxsw_sp_fid_lookup_by_index(mlxsw_sp, fid_index);
+	if (!fid)
+		goto err_fid_lookup;
+
+	err = mlxsw_sp_nve_learned_ip_resolve(mlxsw_sp, uip,
+					      (enum mlxsw_sp_l3proto) sfn_proto,
+					      &addr);
+	if (err)
+		goto err_ip_resolve;
+
+	err = __mlxsw_sp_fdb_notify_mac_uc_tunnel_process(mlxsw_sp, fid, adding,
+							  &nve_dev, &vid, &vni);
+	if (err)
+		goto err_fdb_process;
+
+	err = mlxsw_sp_port_fdb_tunnel_uc_op(mlxsw_sp, mac, fid_index,
+					     (enum mlxsw_sp_l3proto) sfn_proto,
+					     &addr, adding, true);
+	if (err)
+		goto err_fdb_op;
+
+	mlxsw_sp_fdb_nve_call_notifiers(nve_dev, mac,
+					(enum mlxsw_sp_l3proto) sfn_proto,
+					&addr, vni, adding);
+
+	type = adding ? SWITCHDEV_FDB_ADD_TO_BRIDGE :
+			SWITCHDEV_FDB_DEL_TO_BRIDGE;
+	mlxsw_sp_fdb_call_notifiers(type, mac, vid, nve_dev, adding);
+
+	mlxsw_sp_fid_put(fid);
+
+	return;
+
+err_fdb_op:
+err_fdb_process:
+err_ip_resolve:
+	mlxsw_sp_fid_put(fid);
+err_fid_lookup:
+	/* Remove an FDB entry in case we cannot process it. Otherwise the
+	 * device will keep sending the same notification over and over again.
+	 */
+	mlxsw_sp_port_fdb_tunnel_uc_op(mlxsw_sp, mac, fid_index,
+				       (enum mlxsw_sp_l3proto) sfn_proto, &addr,
+				       false, true);
+}
+
 static void mlxsw_sp_fdb_notify_rec_process(struct mlxsw_sp *mlxsw_sp,
 					    char *sfn_pl, int rec_index)
 {
@@ -2462,6 +2643,14 @@ static void mlxsw_sp_fdb_notify_rec_process(struct mlxsw_sp *mlxsw_sp,
 		mlxsw_sp_fdb_notify_mac_lag_process(mlxsw_sp, sfn_pl,
 						    rec_index, false);
 		break;
+	case MLXSW_REG_SFN_REC_TYPE_LEARNED_UNICAST_TUNNEL:
+		mlxsw_sp_fdb_notify_mac_uc_tunnel_process(mlxsw_sp, sfn_pl,
+							  rec_index, true);
+		break;
+	case MLXSW_REG_SFN_REC_TYPE_AGED_OUT_UNICAST_TUNNEL:
+		mlxsw_sp_fdb_notify_mac_uc_tunnel_process(mlxsw_sp, sfn_pl,
+							  rec_index, false);
+		break;
 	}
 }
 
@@ -2516,20 +2705,6 @@ struct mlxsw_sp_switchdev_event_work {
 	unsigned long event;
 };
 
-static void
-mlxsw_sp_switchdev_vxlan_addr_convert(const union vxlan_addr *vxlan_addr,
-				      enum mlxsw_sp_l3proto *proto,
-				      union mlxsw_sp_l3addr *addr)
-{
-	if (vxlan_addr->sa.sa_family == AF_INET) {
-		addr->addr4 = vxlan_addr->sin.sin_addr.s_addr;
-		*proto = MLXSW_SP_L3_PROTO_IPV4;
-	} else {
-		addr->addr6 = vxlan_addr->sin6.sin6_addr;
-		*proto = MLXSW_SP_L3_PROTO_IPV6;
-	}
-}
-
 static void
 mlxsw_sp_switchdev_bridge_vxlan_fdb_event(struct mlxsw_sp *mlxsw_sp,
 					  struct mlxsw_sp_switchdev_event_work *
-- 
cgit v1.2.3


From 8b547a60262121b2b471a8f2fa0e33a50c6c1ecd Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:48 +0000
Subject: mlxsw: spectrum_switchdev: Allow deletion of learned FDB entries

Allow users to delete learned FDB entries from the bridge's FDB before
enabling VxLAN learning.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index d3d1c1d00d98..b32a5ee57fb9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2770,7 +2770,8 @@ mlxsw_sp_switchdev_bridge_nve_fdb_event(struct mlxsw_sp_switchdev_event_work *
 	    switchdev_work->event != SWITCHDEV_FDB_DEL_TO_DEVICE)
 		return;
 
-	if (!switchdev_work->fdb_info.added_by_user)
+	if (switchdev_work->event == SWITCHDEV_FDB_ADD_TO_DEVICE &&
+	    !switchdev_work->fdb_info.added_by_user)
 		return;
 
 	if (!netif_running(dev))
-- 
cgit v1.2.3


From 20134ee9c52677f9dff654a7954a278e691f47cb Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:50 +0000
Subject: mlxsw: spectrum_nve: Allow VxLAN learning

Up until now the driver returned an error when learning was enabled on a
VxLAN device enslaved to an offloaded bridge.

Previous patches added VxLAN learning support, so remove the check.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
index d21c7be5b1c9..4e9cc00a88fd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
@@ -17,7 +17,8 @@
 #define MLXSW_SP_NVE_VXLAN_PARSING_DEPTH 128
 #define MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH 96
 
-#define MLXSW_SP_NVE_VXLAN_SUPPORTED_FLAGS	VXLAN_F_UDP_ZERO_CSUM_TX
+#define MLXSW_SP_NVE_VXLAN_SUPPORTED_FLAGS	(VXLAN_F_UDP_ZERO_CSUM_TX | \
+						 VXLAN_F_LEARN)
 
 static bool mlxsw_sp1_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve,
 					    const struct net_device *dev,
@@ -61,11 +62,6 @@ static bool mlxsw_sp1_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve,
 		return false;
 	}
 
-	if (cfg->flags & VXLAN_F_LEARN) {
-		NL_SET_ERR_MSG_MOD(extack, "VxLAN: Learning is not supported");
-		return false;
-	}
-
 	if (!(cfg->flags & VXLAN_F_UDP_ZERO_CSUM_TX)) {
 		NL_SET_ERR_MSG_MOD(extack, "VxLAN: UDP checksum is not supported");
 		return false;
-- 
cgit v1.2.3


From dbd4485a69e15b850107eea516cd64387dff1f2e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:51 +0000
Subject: selftests: mlxsw: Consider VxLAN learning enabled as valid

The test currently expects that a configuration which includes a VxLAN
device with learning enabled to fail.

Previous patches enabled VxLAN learning in mlxsw, so change the test
accordingly.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/vxlan.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
index 52e78adfe081..ffa79b738f2a 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
@@ -167,7 +167,7 @@ sanitization_single_dev_learning_enabled_test()
 	ip link add name vxlan0 up type vxlan id 10 learning noudpcsum \
 		ttl 20 tos inherit local 198.51.100.1 dstport 4789
 
-	sanitization_single_dev_test_fail
+	sanitization_single_dev_test_pass
 
 	ip link del dev vxlan0
 	ip link del dev br0
-- 
cgit v1.2.3


From c39c56a8c8a06330eacc739fda7d175dd1781db5 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 21 Nov 2018 08:02:52 +0000
Subject: selftests: forwarding: vxlan_bridge_1d: Add learning test

Add a test which checks that the VxLAN driver can learn FDB entries and
that these entries are correctly deleted and aged-out.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1d.sh    | 108 +++++++++++++++++++++
 1 file changed, 108 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 5cc6ac74eb74..56cef3b1c194 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -76,6 +76,7 @@ export VXPORT
 	ping_ipv4
 	test_flood
 	test_unicast
+	test_learning
     "}
 
 NUM_NETIFS=6
@@ -663,6 +664,113 @@ test_ecn_decap()
 	test_ecn_decap_error
 }
 
+test_learning()
+{
+	local mac=de:ad:be:ef:13:37
+	local dst=192.0.2.100
+
+	# Enable learning on the VxLAN device and set ageing time to 10 seconds
+	ip link set dev br1 type bridge ageing_time 1000
+	ip link set dev vx1 type vxlan ageing 10
+	ip link set dev vx1 type vxlan learning
+	reapply_config
+
+	# Check that flooding works
+	RET=0
+
+	vxlan_flood_test $mac $dst 10 10 10
+
+	log_test "VXLAN: flood before learning"
+
+	# Send a packet with source mac set to $mac from host w2 and check that
+	# a corresponding entry is created in VxLAN device vx1
+	RET=0
+
+	in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \
+		-t icmp -q
+	sleep 1
+
+	bridge fdb show brport vx1 | grep $mac | grep -q self
+	check_err $?
+	bridge fdb show brport vx1 | grep $mac | grep -q -v self
+	check_err $?
+
+	log_test "VXLAN: show learned FDB entry"
+
+	# Repeat first test and check that packets only reach host w2 in ns1
+	RET=0
+
+	vxlan_flood_test $mac $dst 0 10 0
+
+	log_test "VXLAN: learned FDB entry"
+
+	# Delete the learned FDB entry from the VxLAN and bridge devices and
+	# check that packets are flooded
+	RET=0
+
+	bridge fdb del dev vx1 $mac master self
+	sleep 1
+
+	vxlan_flood_test $mac $dst 10 10 10
+
+	log_test "VXLAN: deletion of learned FDB entry"
+
+	# Re-learn the first FDB entry and check that it is correctly aged-out
+	RET=0
+
+	in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \
+		-t icmp -q
+	sleep 1
+
+	bridge fdb show brport vx1 | grep $mac | grep -q self
+	check_err $?
+	bridge fdb show brport vx1 | grep $mac | grep -q -v self
+	check_err $?
+
+	vxlan_flood_test $mac $dst 0 10 0
+
+	sleep 20
+
+	bridge fdb show brport vx1 | grep $mac | grep -q self
+	check_fail $?
+	bridge fdb show brport vx1 | grep $mac | grep -q -v self
+	check_fail $?
+
+	vxlan_flood_test $mac $dst 10 10 10
+
+	log_test "VXLAN: Ageing of learned FDB entry"
+
+	# Toggle learning on the bridge port and check that the bridge's FDB
+	# is populated only when it should
+	RET=0
+
+	ip link set dev vx1 type bridge_slave learning off
+
+	in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \
+		-t icmp -q
+	sleep 1
+
+	bridge fdb show brport vx1 | grep $mac | grep -q -v self
+	check_fail $?
+
+	ip link set dev vx1 type bridge_slave learning on
+
+	in_ns ns1 $MZ w2 -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff -B $dst \
+		-t icmp -q
+	sleep 1
+
+	bridge fdb show brport vx1 | grep $mac | grep -q -v self
+	check_err $?
+
+	log_test "VXLAN: learning toggling on bridge port"
+
+	# Restore previous settings
+	ip link set dev vx1 type vxlan nolearning
+	ip link set dev vx1 type vxlan ageing 300
+	ip link set dev br1 type bridge ageing_time 30000
+	reapply_config
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"
-- 
cgit v1.2.3


From 3fcccec008cf095ac61018cfce0e4bb76edddb5b Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Mon, 12 Nov 2018 17:28:22 +0800
Subject: xfrm6: remove BUG_ON from xfrm6_dst_ifdown

if loopback_idev is NULL pointer, and the following access of
loopback_idev will trigger panic, which is same as BUG_ON

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv6/xfrm6_policy.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index d35bcf92969c..769f8f78d3b8 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -262,7 +262,6 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	if (xdst->u.rt6.rt6i_idev->dev == dev) {
 		struct inet6_dev *loopback_idev =
 			in6_dev_get(dev_net(dev)->loopback_dev);
-		BUG_ON(!loopback_idev);
 
 		do {
 			in6_dev_put(xdst->u.rt6.rt6i_idev);
-- 
cgit v1.2.3


From 8d75839b843ae0ef8d9db97ed05b493e687e6b75 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 21 Nov 2018 21:39:52 -0800
Subject: bpf, lpm: make longest_prefix_match() faster

At LPC 2018 in Vancouver, Vlad Dumitrescu mentioned that longest_prefix_match()
has a high cost [1].

One reason for that cost is a loop handling one byte at a time.

We can handle more bytes at a time, if enough attention is paid
to endianness.

I was able to remove ~55 % of longest_prefix_match() cpu costs.

[1] https://linuxplumbersconf.org/event/2/contributions/88/attachments/76/87/lpc-bpf-2018-shaping.pdf

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Vlad Dumitrescu <vladum@google.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/lpm_trie.c | 59 ++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 49 insertions(+), 10 deletions(-)

diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 9058317ba9de..bfd4882e1106 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -168,20 +168,59 @@ static size_t longest_prefix_match(const struct lpm_trie *trie,
 				   const struct lpm_trie_node *node,
 				   const struct bpf_lpm_trie_key *key)
 {
-	size_t prefixlen = 0;
-	size_t i;
+	u32 limit = min(node->prefixlen, key->prefixlen);
+	u32 prefixlen = 0, i = 0;
 
-	for (i = 0; i < trie->data_size; i++) {
-		size_t b;
+	BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32));
+	BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32));
 
-		b = 8 - fls(node->data[i] ^ key->data[i]);
-		prefixlen += b;
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT)
 
-		if (prefixlen >= node->prefixlen || prefixlen >= key->prefixlen)
-			return min(node->prefixlen, key->prefixlen);
+	/* data_size >= 16 has very small probability.
+	 * We do not use a loop for optimal code generation.
+	 */
+	if (trie->data_size >= 8) {
+		u64 diff = be64_to_cpu(*(__be64 *)node->data ^
+				       *(__be64 *)key->data);
+
+		prefixlen = 64 - fls64(diff);
+		if (prefixlen >= limit)
+			return limit;
+		if (diff)
+			return prefixlen;
+		i = 8;
+	}
+#endif
+
+	while (trie->data_size >= i + 4) {
+		u32 diff = be32_to_cpu(*(__be32 *)&node->data[i] ^
+				       *(__be32 *)&key->data[i]);
+
+		prefixlen += 32 - fls(diff);
+		if (prefixlen >= limit)
+			return limit;
+		if (diff)
+			return prefixlen;
+		i += 4;
+	}
 
-		if (b < 8)
-			break;
+	if (trie->data_size >= i + 2) {
+		u16 diff = be16_to_cpu(*(__be16 *)&node->data[i] ^
+				       *(__be16 *)&key->data[i]);
+
+		prefixlen += 16 - fls(diff);
+		if (prefixlen >= limit)
+			return limit;
+		if (diff)
+			return prefixlen;
+		i += 2;
+	}
+
+	if (trie->data_size >= i + 1) {
+		prefixlen += 8 - fls(node->data[i] ^ key->data[i]);
+
+		if (prefixlen >= limit)
+			return limit;
 	}
 
 	return prefixlen;
-- 
cgit v1.2.3


From ab85b0143428739cb0f2533182d5824375b6b66b Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 22 Nov 2018 10:13:45 +0000
Subject: tools/bpf: fix spelling mistake "memeory" -> "memory"

The CHECK message contains a spelling mistake, fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_btf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 7b1b160d6e67..bcbda7037840 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -2573,7 +2573,7 @@ static int do_test_file(unsigned int test_num)
 	}
 
 	func_info = malloc(info.func_info_cnt * rec_size);
-	if (CHECK(!func_info, "out of memeory")) {
+	if (CHECK(!func_info, "out of memory")) {
 		err = -1;
 		goto done;
 	}
@@ -3299,7 +3299,7 @@ static int do_test_func_type(int test_num)
 	}
 
 	func_info = malloc(info.func_info_cnt * rec_size);
-	if (CHECK(!func_info, "out of memeory")) {
+	if (CHECK(!func_info, "out of memory")) {
 		err = -1;
 		goto done;
 	}
-- 
cgit v1.2.3


From 1d0795ea9ca37be0fa0823776e0367b8fc398c91 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 21 Nov 2018 14:31:15 +0100
Subject: selftests: explicitly require kernel features needed by udpgro tests

commit 3327a9c46352f1 ("selftests: add functionals test for UDP GRO")
make use of ipv6 NAT, but such a feature is not currently implied by
selftests. Since the 'ip[6]tables' commands may actually create nft rules,
depending on the specific user-space version, let's pull both NF and
NFT nat modules plus the needed deps.

Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Fixes: 3327a9c46352f1 ("selftests: add functionals test for UDP GRO")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/config | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index cd3a2f1545b5..5821bdd98d20 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -14,3 +14,17 @@ CONFIG_IPV6_VTI=y
 CONFIG_DUMMY=y
 CONFIG_BRIDGE=y
 CONFIG_VLAN_8021Q=y
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_ADVANCED=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_NAT_IPV6=m
+CONFIG_NF_NAT_IPV4=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP6_NF_NAT=m
+CONFIG_IP_NF_NAT=m
+CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_IPV6=y
+CONFIG_NF_TABLES_IPV4=y
+CONFIG_NFT_CHAIN_NAT_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
-- 
cgit v1.2.3


From e45678973dcbb131f29a6c90b0ea3829f38eeab8 Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@mellanox.com>
Date: Wed, 21 Nov 2018 17:12:05 +0200
Subject: {net, IB}/mlx4: Initialize CQ buffers in the driver when possible

Perform CQ initialization in the driver when the capability is supported
by the FW.  When passing the CQ to HW indicate that the CQ buffer has
been pre-initialized.

Doing so decreases CQ creation time.  Testing on P8 showed a single 2048
entry CQ creation time was reduced from ~395us to ~170us, which is
2.3x faster.

Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/cq.c            |  9 +++-
 drivers/net/ethernet/mellanox/mlx4/cq.c    | 71 ++++++++++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx4/en_cq.c |  2 +-
 drivers/net/ethernet/mellanox/mlx4/fw.c    |  3 ++
 include/linux/mlx4/device.h                |  4 +-
 5 files changed, 82 insertions(+), 7 deletions(-)

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 82adc0d1d30e..43512347b4f0 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -181,6 +181,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	struct mlx4_ib_cq *cq;
 	struct mlx4_uar *uar;
+	void *buf_addr;
 	int err;
 
 	if (entries < 1 || entries > dev->dev->caps.max_cqes)
@@ -211,6 +212,8 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
 			goto err_cq;
 		}
 
+		buf_addr = (void *)(unsigned long)ucmd.buf_addr;
+
 		err = mlx4_ib_get_cq_umem(dev, context, &cq->buf, &cq->umem,
 					  ucmd.buf_addr, entries);
 		if (err)
@@ -237,6 +240,8 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
 		if (err)
 			goto err_db;
 
+		buf_addr = &cq->buf.buf;
+
 		uar = &dev->priv_uar;
 		cq->mcq.usage = MLX4_RES_USAGE_DRIVER;
 	}
@@ -246,7 +251,9 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
 
 	err = mlx4_cq_alloc(dev->dev, entries, &cq->buf.mtt, uar,
 			    cq->db.dma, &cq->mcq, vector, 0,
-			    !!(cq->create_flags & IB_UVERBS_CQ_FLAGS_TIMESTAMP_COMPLETION));
+			    !!(cq->create_flags &
+			       IB_UVERBS_CQ_FLAGS_TIMESTAMP_COMPLETION),
+			    buf_addr, !!context);
 	if (err)
 		goto err_dbmap;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index d8e9a323122e..db909b6069b5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -144,9 +144,9 @@ void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type)
 }
 
 static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
-			 int cq_num)
+			 int cq_num, u8 opmod)
 {
-	return mlx4_cmd(dev, mailbox->dma, cq_num, 0,
+	return mlx4_cmd(dev, mailbox->dma, cq_num, opmod,
 			MLX4_CMD_SW2HW_CQ, MLX4_CMD_TIME_CLASS_A,
 			MLX4_CMD_WRAPPED);
 }
@@ -287,11 +287,61 @@ static void mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn)
 		__mlx4_cq_free_icm(dev, cqn);
 }
 
+static int mlx4_init_user_cqes(void *buf, int entries, int cqe_size)
+{
+	int entries_per_copy = PAGE_SIZE / cqe_size;
+	void *init_ents;
+	int err = 0;
+	int i;
+
+	init_ents = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!init_ents)
+		return -ENOMEM;
+
+	/* Populate a list of CQ entries to reduce the number of
+	 * copy_to_user calls. 0xcc is the initialization value
+	 * required by the FW.
+	 */
+	memset(init_ents, 0xcc, PAGE_SIZE);
+
+	if (entries_per_copy < entries) {
+		for (i = 0; i < entries / entries_per_copy; i++) {
+			err = copy_to_user(buf, init_ents, PAGE_SIZE);
+			if (err)
+				goto out;
+
+			buf += PAGE_SIZE;
+		}
+	} else {
+		err = copy_to_user(buf, init_ents, entries * cqe_size);
+	}
+
+out:
+	kfree(init_ents);
+
+	return err;
+}
+
+static void mlx4_init_kernel_cqes(struct mlx4_buf *buf,
+				  int entries,
+				  int cqe_size)
+{
+	int i;
+
+	if (buf->nbufs == 1)
+		memset(buf->direct.buf, 0xcc, entries * cqe_size);
+	else
+		for (i = 0; i < buf->npages; i++)
+			memset(buf->page_list[i].buf, 0xcc,
+			       1UL << buf->page_shift);
+}
+
 int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 		  struct mlx4_mtt *mtt, struct mlx4_uar *uar, u64 db_rec,
 		  struct mlx4_cq *cq, unsigned vector, int collapsed,
-		  int timestamp_en)
+		  int timestamp_en, void *buf_addr, bool user_cq)
 {
+	bool sw_cq_init = dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SW_CQ_INIT;
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_cq_table *cq_table = &priv->cq_table;
 	struct mlx4_cmd_mailbox *mailbox;
@@ -336,7 +386,20 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	cq_context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);
 	cq_context->db_rec_addr     = cpu_to_be64(db_rec);
 
-	err = mlx4_SW2HW_CQ(dev, mailbox, cq->cqn);
+	if (sw_cq_init) {
+		if (user_cq) {
+			err = mlx4_init_user_cqes(buf_addr, nent,
+						  dev->caps.cqe_size);
+			if (err)
+				sw_cq_init = false;
+		} else {
+			mlx4_init_kernel_cqes(buf_addr, nent,
+					      dev->caps.cqe_size);
+		}
+	}
+
+	err = mlx4_SW2HW_CQ(dev, mailbox, cq->cqn, sw_cq_init);
+
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	if (err)
 		goto err_radix;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 1e487acb4667..062a88fcc5d6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -143,7 +143,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	cq->mcq.usage = MLX4_RES_USAGE_DRIVER;
 	err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt,
 			    &mdev->priv_uar, cq->wqres.db.dma, &cq->mcq,
-			    cq->vector, 0, timestamp_en);
+			    cq->vector, 0, timestamp_en, &cq->wqres.buf, false);
 	if (err)
 		goto free_eq;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index babcfd9c0571..7df728f1e5b5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -166,6 +166,7 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[37] = "sl to vl mapping table change event support",
 		[38] = "user MAC support",
 		[39] = "Report driver version to FW support",
+		[40] = "SW CQ initialization support",
 	};
 	int i;
 
@@ -1098,6 +1099,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FSM;
 	if (field32 & (1 << 21))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_80_VFS;
+	if (field32 & (1 << 23))
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_SW_CQ_INIT;
 
 	for (i = 1; i <= dev_cap->num_ports; i++) {
 		err = mlx4_QUERY_PORT(dev, i, dev_cap->port_cap + i);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index dca6ab4eaa99..36e412c3d657 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -226,6 +226,7 @@ enum {
 	MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT = 1ULL << 37,
 	MLX4_DEV_CAP_FLAG2_USER_MAC_EN		= 1ULL << 38,
 	MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW = 1ULL << 39,
+	MLX4_DEV_CAP_FLAG2_SW_CQ_INIT           = 1ULL << 40,
 };
 
 enum {
@@ -1136,7 +1137,8 @@ void mlx4_free_hwq_res(struct mlx4_dev *mdev, struct mlx4_hwq_resources *wqres,
 
 int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 		  struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq,
-		  unsigned vector, int collapsed, int timestamp_en);
+		  unsigned int vector, int collapsed, int timestamp_en,
+		  void *buf_addr, bool user_cq);
 void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq);
 int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
 			  int *base, u8 flags, u8 usage);
-- 
cgit v1.2.3


From f11216b24219ab26d8d159fbfa12dff886b16e32 Mon Sep 17 00:00:00 2001
From: Vlad Dumitrescu <vladum@google.com>
Date: Thu, 22 Nov 2018 14:39:16 -0500
Subject: bpf: add skb->tstamp r/w access from tc clsact and cg skb progs

This could be used to rate limit egress traffic in concert with a qdisc
which supports Earliest Departure Time, such as FQ.

Write access from cg skb progs only with CAP_SYS_ADMIN, since the value
will be used by downstream qdiscs. It might make sense to relax this.

Changes v1 -> v2:
  - allow access from cg skb, write only with CAP_SYS_ADMIN

Signed-off-by: Vlad Dumitrescu <vladum@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h                    |  1 +
 net/core/filter.c                           | 29 +++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h              |  1 +
 tools/testing/selftests/bpf/test_verifier.c | 29 +++++++++++++++++++++++++++++
 4 files changed, 60 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c1554aa07465..23e2031a43d4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2468,6 +2468,7 @@ struct __sk_buff {
 
 	__u32 data_meta;
 	struct bpf_flow_keys *flow_keys;
+	__u64 tstamp;
 };
 
 struct bpf_tunnel_key {
diff --git a/net/core/filter.c b/net/core/filter.c
index f6ca38a7d433..65dc13aeca7c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5573,6 +5573,10 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
 		if (size != sizeof(struct bpf_flow_keys *))
 			return false;
 		break;
+	case bpf_ctx_range(struct __sk_buff, tstamp):
+		if (size != sizeof(__u64))
+			return false;
+		break;
 	default:
 		/* Only narrow read access allowed for now. */
 		if (type == BPF_WRITE) {
@@ -5600,6 +5604,7 @@ static bool sk_filter_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data_end):
 	case bpf_ctx_range(struct __sk_buff, flow_keys):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
+	case bpf_ctx_range(struct __sk_buff, tstamp):
 		return false;
 	}
 
@@ -5638,6 +5643,10 @@ static bool cg_skb_is_valid_access(int off, int size,
 		case bpf_ctx_range(struct __sk_buff, priority):
 		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
 			break;
+		case bpf_ctx_range(struct __sk_buff, tstamp):
+			if (!capable(CAP_SYS_ADMIN))
+				return false;
+			break;
 		default:
 			return false;
 		}
@@ -5665,6 +5674,7 @@ static bool lwt_is_valid_access(int off, int size,
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, flow_keys):
+	case bpf_ctx_range(struct __sk_buff, tstamp):
 		return false;
 	}
 
@@ -5874,6 +5884,7 @@ static bool tc_cls_act_is_valid_access(int off, int size,
 		case bpf_ctx_range(struct __sk_buff, priority):
 		case bpf_ctx_range(struct __sk_buff, tc_classid):
 		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
+		case bpf_ctx_range(struct __sk_buff, tstamp):
 			break;
 		default:
 			return false;
@@ -6093,6 +6104,7 @@ static bool sk_skb_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, flow_keys):
+	case bpf_ctx_range(struct __sk_buff, tstamp):
 		return false;
 	}
 
@@ -6179,6 +6191,7 @@ static bool flow_dissector_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
+	case bpf_ctx_range(struct __sk_buff, tstamp):
 		return false;
 	}
 
@@ -6488,6 +6501,22 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg,
 				      si->src_reg, off);
 		break;
+
+	case offsetof(struct __sk_buff, tstamp):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8);
+
+		if (type == BPF_WRITE)
+			*insn++ = BPF_STX_MEM(BPF_DW,
+					      si->dst_reg, si->src_reg,
+					      bpf_target_off(struct sk_buff,
+							     tstamp, 8,
+							     target_size));
+		else
+			*insn++ = BPF_LDX_MEM(BPF_DW,
+					      si->dst_reg, si->src_reg,
+					      bpf_target_off(struct sk_buff,
+							     tstamp, 8,
+							     target_size));
 	}
 
 	return insn - insn_buf;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c1554aa07465..23e2031a43d4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2468,6 +2468,7 @@ struct __sk_buff {
 
 	__u32 data_meta;
 	struct bpf_flow_keys *flow_keys;
+	__u64 tstamp;
 };
 
 struct bpf_tunnel_key {
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 54d16fbdef8b..537a8f91af02 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -2446,6 +2446,10 @@ static struct bpf_test tests[] = {
 				    offsetof(struct __sk_buff, tc_index)),
 			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
 				    offsetof(struct __sk_buff, cb[3])),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, tstamp)),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+				    offsetof(struct __sk_buff, tstamp)),
 			BPF_EXIT_INSN(),
 		},
 		.errstr_unpriv = "",
@@ -5297,6 +5301,31 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R2 leaks addr into helper function",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
+	{
+		"write tstamp from CGROUP_SKB",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+				    offsetof(struct __sk_buff, tstamp)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.result_unpriv = REJECT,
+		.errstr_unpriv = "invalid bpf_context access off=152 size=8",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"read tstamp from CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, tstamp)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
 	{
 		"multiple registers share map_lookup_elem result",
 		.insns = {
-- 
cgit v1.2.3


From 79f033f6f229e9e1975172f8e766d3549595e0bf Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 30 Jul 2018 11:59:16 +0300
Subject: iwlwifi: dbg: don't limit dump decisions to all or monitor

Currently opmode is limited to asking transport to either
dump all the dumps configured at startup, or monitor only.
Instead, pass to transport a bitmask, to allow flexibility.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c     |  7 ++++--
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h  |  7 +++---
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c    |  1 -
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 31 +++++++++++--------------
 4 files changed, 22 insertions(+), 24 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 58a980070445..67e6a35f14c4 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -908,6 +908,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	struct iwl_fw_error_dump_file *dump_file;
 	struct scatterlist *sg_dump_data;
 	u32 file_len;
+	u32 dump_mask = fwrt->fw->dbg.dump_mask;
 
 	IWL_DEBUG_INFO(fwrt, "WRT dump start\n");
 
@@ -927,8 +928,10 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 		goto out;
 	}
 
-	fw_error_dump->trans_ptr = iwl_trans_dump_data(fwrt->trans,
-						       fwrt->dump.monitor_only);
+	if (fwrt->dump.monitor_only)
+		dump_mask &= IWL_FW_ERROR_DUMP_FW_MONITOR;
+
+	fw_error_dump->trans_ptr = iwl_trans_dump_data(fwrt->trans, dump_mask);
 	file_len = le32_to_cpu(dump_file->file_len);
 	fw_error_dump->fwrt_len = file_len;
 	if (fw_error_dump->trans_ptr) {
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index f384a98a021c..b0300e824815 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -602,7 +602,7 @@ struct iwl_trans_ops {
 	void (*resume)(struct iwl_trans *trans);
 
 	struct iwl_trans_dump_data *(*dump_data)(struct iwl_trans *trans,
-						 bool monitor_only);
+						 u32 dump_mask);
 };
 
 /**
@@ -776,7 +776,6 @@ struct iwl_trans {
 	const struct iwl_fw_dbg_dest_tlv_v1 *dbg_dest_tlv;
 	const struct iwl_fw_dbg_conf_tlv *dbg_conf_tlv[FW_DBG_CONF_MAX];
 	struct iwl_fw_dbg_trigger_tlv * const *dbg_trigger_tlv;
-	u32 dbg_dump_mask;
 	u8 dbg_n_dest_reg;
 	int num_blocks;
 	struct iwl_dram_data fw_mon[IWL_MAX_DEBUG_ALLOCATIONS];
@@ -896,11 +895,11 @@ static inline void iwl_trans_resume(struct iwl_trans *trans)
 }
 
 static inline struct iwl_trans_dump_data *
-iwl_trans_dump_data(struct iwl_trans *trans, bool monitor_only)
+iwl_trans_dump_data(struct iwl_trans *trans, u32 dump_mask)
 {
 	if (!trans->ops->dump_data)
 		return NULL;
-	return trans->ops->dump_data(trans, monitor_only);
+	return trans->ops->dump_data(trans, dump_mask);
 }
 
 static inline struct iwl_device_cmd *
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 2291661dd72d..0a5b35312b59 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -769,7 +769,6 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	memcpy(trans->dbg_conf_tlv, mvm->fw->dbg.conf_tlv,
 	       sizeof(trans->dbg_conf_tlv));
 	trans->dbg_trigger_tlv = mvm->fw->dbg.trigger_tlv;
-	trans->dbg_dump_mask = mvm->fw->dbg.dump_mask;
 
 	trans->iml = mvm->fw->iml;
 	trans->iml_len = mvm->fw->iml_len;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 551ce439647b..16eed9b0f301 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2990,7 +2990,7 @@ static int iwl_trans_get_fw_monitor_len(struct iwl_trans *trans, int *len)
 
 static struct iwl_trans_dump_data
 *iwl_trans_pcie_dump_data(struct iwl_trans *trans,
-			  bool monitor_only)
+			  u32 dump_mask)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_fw_error_dump_data *data;
@@ -3002,7 +3002,10 @@ static struct iwl_trans_dump_data
 	int i, ptr;
 	bool dump_rbs = test_bit(STATUS_FW_ERROR, &trans->status) &&
 			!trans->cfg->mq_rx_supported &&
-			trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_RB);
+			dump_mask & BIT(IWL_FW_ERROR_DUMP_RB);
+
+	if (!dump_mask)
+		return NULL;
 
 	/* transport dump header */
 	len = sizeof(*dump_data);
@@ -3014,11 +3017,7 @@ static struct iwl_trans_dump_data
 	/* FW monitor */
 	monitor_len = iwl_trans_get_fw_monitor_len(trans, &len);
 
-	if (monitor_only) {
-		if (!(trans->dbg_dump_mask &
-		      BIT(IWL_FW_ERROR_DUMP_FW_MONITOR)))
-			return NULL;
-
+	if (dump_mask == BIT(IWL_FW_ERROR_DUMP_FW_MONITOR)) {
 		dump_data = vzalloc(len);
 		if (!dump_data)
 			return NULL;
@@ -3031,11 +3030,11 @@ static struct iwl_trans_dump_data
 	}
 
 	/* CSR registers */
-	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_CSR))
+	if (dump_mask & BIT(IWL_FW_ERROR_DUMP_CSR))
 		len += sizeof(*data) + IWL_CSR_TO_DUMP;
 
 	/* FH registers */
-	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_FH_REGS)) {
+	if (dump_mask & BIT(IWL_FW_ERROR_DUMP_FH_REGS)) {
 		if (trans->cfg->gen2)
 			len += sizeof(*data) +
 			       (FH_MEM_UPPER_BOUND_GEN2 -
@@ -3060,8 +3059,7 @@ static struct iwl_trans_dump_data
 	}
 
 	/* Paged memory for gen2 HW */
-	if (trans->cfg->gen2 &&
-	    trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING))
+	if (trans->cfg->gen2 && dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING))
 		for (i = 0; i < trans_pcie->init_dram.paging_cnt; i++)
 			len += sizeof(*data) +
 			       sizeof(struct iwl_fw_error_dump_paging) +
@@ -3074,7 +3072,7 @@ static struct iwl_trans_dump_data
 	len = 0;
 	data = (void *)dump_data->data;
 
-	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_TXCMD)) {
+	if (dump_mask & BIT(IWL_FW_ERROR_DUMP_TXCMD)) {
 		u16 tfd_size = trans_pcie->tfd_size;
 
 		data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_TXCMD);
@@ -3108,16 +3106,15 @@ static struct iwl_trans_dump_data
 		data = iwl_fw_error_next_data(data);
 	}
 
-	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_CSR))
+	if (dump_mask & BIT(IWL_FW_ERROR_DUMP_CSR))
 		len += iwl_trans_pcie_dump_csr(trans, &data);
-	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_FH_REGS))
+	if (dump_mask & BIT(IWL_FW_ERROR_DUMP_FH_REGS))
 		len += iwl_trans_pcie_fh_regs_dump(trans, &data);
 	if (dump_rbs)
 		len += iwl_trans_pcie_dump_rbs(trans, &data, num_rbs);
 
 	/* Paged memory for gen2 HW */
-	if (trans->cfg->gen2 &&
-	    trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING)) {
+	if (trans->cfg->gen2 && dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING)) {
 		for (i = 0; i < trans_pcie->init_dram.paging_cnt; i++) {
 			struct iwl_fw_error_dump_paging *paging;
 			dma_addr_t addr =
@@ -3137,7 +3134,7 @@ static struct iwl_trans_dump_data
 			len += sizeof(*data) + sizeof(*paging) + page_len;
 		}
 	}
-	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_FW_MONITOR))
+	if (dump_mask & BIT(IWL_FW_ERROR_DUMP_FW_MONITOR))
 		len += iwl_trans_pcie_dump_monitor(trans, &data, monitor_len);
 
 	dump_data->len = len;
-- 
cgit v1.2.3


From 32b258e9e55cffd5f6c4e27285a43a1cdf7385a4 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Tue, 31 Jul 2018 09:54:26 +0300
Subject: iwlwifi: dbg: split fifos dump

Split the dump of RXF and TXF. This is in order to
enable code reuse for INI, which may decide to dump
only RXF and not TXF, and vice versa.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 52 +++++++++++++++++++++--------
 1 file changed, 39 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 67e6a35f14c4..6243b503d0b0 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -225,17 +225,13 @@ static void iwl_fwrt_dump_txf(struct iwl_fw_runtime *fwrt,
 	*dump_data = iwl_fw_error_next_data(*dump_data);
 }
 
-static void iwl_fw_dump_fifos(struct iwl_fw_runtime *fwrt,
-			      struct iwl_fw_error_dump_data **dump_data)
+static void iwl_fw_dump_rxf(struct iwl_fw_runtime *fwrt,
+			    struct iwl_fw_error_dump_data **dump_data)
 {
-	struct iwl_fw_error_dump_fifo *fifo_hdr;
 	struct iwl_fwrt_shared_mem_cfg *cfg = &fwrt->smem_cfg;
-	u32 *fifo_data;
-	u32 fifo_len;
 	unsigned long flags;
-	int i, j;
 
-	IWL_DEBUG_INFO(fwrt, "WRT FIFO dump\n");
+	IWL_DEBUG_INFO(fwrt, "WRT RX FIFO dump\n");
 
 	if (!iwl_trans_grab_nic_access(fwrt->trans, &flags))
 		return;
@@ -254,6 +250,24 @@ static void iwl_fw_dump_fifos(struct iwl_fw_runtime *fwrt,
 					  LMAC2_PRPH_OFFSET, 2);
 	}
 
+	iwl_trans_release_nic_access(fwrt->trans, &flags);
+}
+
+static void iwl_fw_dump_txf(struct iwl_fw_runtime *fwrt,
+			    struct iwl_fw_error_dump_data **dump_data)
+{
+	struct iwl_fw_error_dump_fifo *fifo_hdr;
+	struct iwl_fwrt_shared_mem_cfg *cfg = &fwrt->smem_cfg;
+	u32 *fifo_data;
+	u32 fifo_len;
+	unsigned long flags;
+	int i, j;
+
+	IWL_DEBUG_INFO(fwrt, "WRT TX FIFO dump\n");
+
+	if (!iwl_trans_grab_nic_access(fwrt->trans, &flags))
+		return;
+
 	if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_TXF)) {
 		/* Pull TXF data from LMAC1 */
 		for (i = 0; i < fwrt->smem_cfg.num_txfifo_entries; i++) {
@@ -595,8 +609,8 @@ static void iwl_fw_dump_mem(struct iwl_fw_runtime *fwrt,
 	do {size_t item = item_len; len += (!!item) * const_len + item; } \
 	while (0)
 
-static int iwl_fw_fifo_len(struct iwl_fw_runtime *fwrt,
-			   struct iwl_fwrt_shared_mem_cfg *mem_cfg)
+static int iwl_fw_rxf_len(struct iwl_fw_runtime *fwrt,
+			  struct iwl_fwrt_shared_mem_cfg *mem_cfg)
 {
 	size_t hdr_len = sizeof(struct iwl_fw_error_dump_data) +
 			 sizeof(struct iwl_fw_error_dump_fifo);
@@ -604,7 +618,7 @@ static int iwl_fw_fifo_len(struct iwl_fw_runtime *fwrt,
 	int i;
 
 	if (!iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_RXF))
-		goto dump_txf;
+		return 0;
 
 	/* Count RXF2 size */
 	ADD_LEN(fifo_len, mem_cfg->rxfifo2_size, hdr_len);
@@ -613,7 +627,17 @@ static int iwl_fw_fifo_len(struct iwl_fw_runtime *fwrt,
 	for (i = 0; i < mem_cfg->num_lmacs; i++)
 		ADD_LEN(fifo_len, mem_cfg->lmac[i].rxfifo1_size, hdr_len);
 
-dump_txf:
+	return fifo_len;
+}
+
+static int iwl_fw_txf_len(struct iwl_fw_runtime *fwrt,
+			  struct iwl_fwrt_shared_mem_cfg *mem_cfg)
+{
+	size_t hdr_len = sizeof(struct iwl_fw_error_dump_data) +
+			 sizeof(struct iwl_fw_error_dump_fifo);
+	u32 fifo_len = 0;
+	int i;
+
 	if (!iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_TXF))
 		goto dump_internal_txf;
 
@@ -697,7 +721,8 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 
 	/* reading RXF/TXF sizes */
 	if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status)) {
-		fifo_len = iwl_fw_fifo_len(fwrt, mem_cfg);
+		fifo_len = iwl_fw_rxf_len(fwrt, mem_cfg);
+		fifo_len += iwl_fw_txf_len(fwrt, mem_cfg);
 
 		/* Make room for PRPH registers */
 		if (!fwrt->trans->cfg->gen2 &&
@@ -817,7 +842,8 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 
 	/* We only dump the FIFOs if the FW is in error state */
 	if (fifo_len) {
-		iwl_fw_dump_fifos(fwrt, &dump_data);
+		iwl_fw_dump_rxf(fwrt, &dump_data);
+		iwl_fw_dump_txf(fwrt, &dump_data);
 		if (radio_len)
 			iwl_read_radio_regs(fwrt, &dump_data);
 	}
-- 
cgit v1.2.3


From 8ea20d95899c2bb2aa92193058a4bfef7c8a03b1 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Tue, 31 Jul 2018 15:34:20 +0300
Subject: iwlwifi: mvm: remove assignment of the reciprocal

The firmware stopped looking at this field long ago.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/mac.h   | 27 +++++++++--------------
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 12 ----------
 2 files changed, 10 insertions(+), 29 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
index 1dd23f846fb9..d0b79fb461bf 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
@@ -151,9 +151,9 @@ enum iwl_tsf_id {
  * @beacon_time: beacon transmit time in system time
  * @beacon_tsf: beacon transmit time in TSF
  * @bi: beacon interval in TU
- * @bi_reciprocal: 2^32 / bi
+ * @reserved1: reserved
  * @dtim_interval: dtim transmit time in TU
- * @dtim_reciprocal: 2^32 / dtim_interval
+ * @reserved2: reserved
  * @mcast_qid: queue ID for multicast traffic.
  *	NOTE: obsolete from VER2 and on
  * @beacon_template: beacon template ID
@@ -162,9 +162,9 @@ struct iwl_mac_data_ap {
 	__le32 beacon_time;
 	__le64 beacon_tsf;
 	__le32 bi;
-	__le32 bi_reciprocal;
+	__le32 reserved1;
 	__le32 dtim_interval;
-	__le32 dtim_reciprocal;
+	__le32 reserved2;
 	__le32 mcast_qid;
 	__le32 beacon_template;
 } __packed; /* AP_MAC_DATA_API_S_VER_2 */
@@ -174,14 +174,14 @@ struct iwl_mac_data_ap {
  * @beacon_time: beacon transmit time in system time
  * @beacon_tsf: beacon transmit time in TSF
  * @bi: beacon interval in TU
- * @bi_reciprocal: 2^32 / bi
+ * @reserved: reserved
  * @beacon_template: beacon template ID
  */
 struct iwl_mac_data_ibss {
 	__le32 beacon_time;
 	__le64 beacon_tsf;
 	__le32 bi;
-	__le32 bi_reciprocal;
+	__le32 reserved;
 	__le32 beacon_template;
 } __packed; /* IBSS_MAC_DATA_API_S_VER_1 */
 
@@ -191,9 +191,9 @@ struct iwl_mac_data_ibss {
  * @dtim_time: DTIM arrival time in system time
  * @dtim_tsf: DTIM arrival time in TSF
  * @bi: beacon interval in TU, applicable only when associated
- * @bi_reciprocal: 2^32 / bi , applicable only when associated
+ * @reserved1: reserved
  * @dtim_interval: DTIM interval in TU, applicable only when associated
- * @dtim_reciprocal: 2^32 / dtim_interval , applicable only when associated
+ * @reserved2: reserved
  * @listen_interval: in beacon intervals, applicable only when associated
  * @assoc_id: unique ID assigned by the AP during association
  * @assoc_beacon_arrive_time: TSF of first beacon after association
@@ -203,9 +203,9 @@ struct iwl_mac_data_sta {
 	__le32 dtim_time;
 	__le64 dtim_tsf;
 	__le32 bi;
-	__le32 bi_reciprocal;
+	__le32 reserved1;
 	__le32 dtim_interval;
-	__le32 dtim_reciprocal;
+	__le32 reserved2;
 	__le32 listen_interval;
 	__le32 assoc_id;
 	__le32 assoc_beacon_arrive_time;
@@ -378,13 +378,6 @@ struct iwl_mac_ctx_cmd {
 	};
 } __packed; /* MAC_CONTEXT_CMD_API_S_VER_1 */
 
-static inline u32 iwl_mvm_reciprocal(u32 v)
-{
-	if (!v)
-		return 0;
-	return 0xFFFFFFFF / v;
-}
-
 #define IWL_NONQOS_SEQ_GET	0x1
 #define IWL_NONQOS_SEQ_SET	0x2
 struct iwl_nonqos_seq_query_cmd {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index b9c45a40e251..3b93293d4559 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -767,13 +767,8 @@ static int iwl_mvm_mac_ctxt_cmd_sta(struct iwl_mvm *mvm,
 	}
 
 	ctxt_sta->bi = cpu_to_le32(vif->bss_conf.beacon_int);
-	ctxt_sta->bi_reciprocal =
-		cpu_to_le32(iwl_mvm_reciprocal(vif->bss_conf.beacon_int));
 	ctxt_sta->dtim_interval = cpu_to_le32(vif->bss_conf.beacon_int *
 					      vif->bss_conf.dtim_period);
-	ctxt_sta->dtim_reciprocal =
-		cpu_to_le32(iwl_mvm_reciprocal(vif->bss_conf.beacon_int *
-					       vif->bss_conf.dtim_period));
 
 	ctxt_sta->listen_interval = cpu_to_le32(mvm->hw->conf.listen_interval);
 	ctxt_sta->assoc_id = cpu_to_le32(vif->bss_conf.aid);
@@ -832,8 +827,6 @@ static int iwl_mvm_mac_ctxt_cmd_ibss(struct iwl_mvm *mvm,
 
 	/* cmd.ibss.beacon_time/cmd.ibss.beacon_tsf are curently ignored */
 	cmd.ibss.bi = cpu_to_le32(vif->bss_conf.beacon_int);
-	cmd.ibss.bi_reciprocal =
-		cpu_to_le32(iwl_mvm_reciprocal(vif->bss_conf.beacon_int));
 
 	/* TODO: Assumes that the beacon id == mac context id */
 	cmd.ibss.beacon_template = cpu_to_le32(mvmvif->id);
@@ -1180,13 +1173,8 @@ static void iwl_mvm_mac_ctxt_cmd_fill_ap(struct iwl_mvm *mvm,
 	}
 
 	ctxt_ap->bi = cpu_to_le32(vif->bss_conf.beacon_int);
-	ctxt_ap->bi_reciprocal =
-		cpu_to_le32(iwl_mvm_reciprocal(vif->bss_conf.beacon_int));
 	ctxt_ap->dtim_interval = cpu_to_le32(vif->bss_conf.beacon_int *
 					     vif->bss_conf.dtim_period);
-	ctxt_ap->dtim_reciprocal =
-		cpu_to_le32(iwl_mvm_reciprocal(vif->bss_conf.beacon_int *
-					       vif->bss_conf.dtim_period));
 
 	if (!fw_has_api(&mvm->fw->ucode_capa,
 			IWL_UCODE_TLV_API_STA_TYPE))
-- 
cgit v1.2.3


From b1bbc1a636505ebdd6336ff781e417123226d4f7 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Sat, 4 Aug 2018 14:45:42 +0300
Subject: iwlwifi: fix cfg structs for 22000 with different RF modules

We have to choose different configuration and different firmwares
depending on the external RF module that is installed.  Since the
external module is not represented in the PCI IDs, we need to change
the configuration at runtime, after checking the RF ID of the module
installed.  We have a bit of a mess in the code that does this,
because it applies cfg's according to the RF ID only, ignoring the
integrated module that is in use.

Fix that for some devices by adding correct configurations for them
and not ignoring the integrated module's type when making the
decision.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c  |  1 -
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c   |  2 +-
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 22 ++++++++++++++++++++--
 3 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index da5d5f9b2573..8b2339165bca 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -323,7 +323,6 @@ MODULE_FIRMWARE(IWL_22000_HR_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_JF_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_HR_A_F0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_HR_B_F0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
-MODULE_FIRMWARE(IWL_22000_QU_B_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_HR_B_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_JF_B0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_HR_A0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 8d4711590dfc..353581ccc01e 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -882,7 +882,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x34F0, 0x0040, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x34F0, 0x0070, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x34F0, 0x0078, iwl22000_2ax_cfg_hr)},
-	{IWL_PCI_DEVICE(0x34F0, 0x0310, iwl22000_2ac_cfg_jf)},
+	{IWL_PCI_DEVICE(0x34F0, 0x0310, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x40C0, 0x0000, iwl22560_2ax_cfg_su_cdb)},
 	{IWL_PCI_DEVICE(0x40C0, 0x0010, iwl22560_2ax_cfg_su_cdb)},
 	{IWL_PCI_DEVICE(0x40c0, 0x0090, iwl22560_2ax_cfg_su_cdb)},
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 16eed9b0f301..231ec8131ee8 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -3401,8 +3401,26 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 #if IS_ENABLED(CONFIG_IWLMVM)
 	trans->hw_rf_id = iwl_read32(trans, CSR_HW_RF_ID);
 
-	if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
-	    CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) {
+	if (cfg == &iwl22000_2ax_cfg_hr) {
+		if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
+		    CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) {
+			trans->cfg = &iwl22000_2ax_cfg_hr;
+		} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
+			   CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_JF)) {
+			trans->cfg = &iwl22000_2ax_cfg_jf;
+		} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
+			   CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HRCDB)) {
+			IWL_ERR(trans, "RF ID HRCDB is not supported\n");
+			ret = -EINVAL;
+			goto out_no_pci;
+		} else {
+			IWL_ERR(trans, "Unrecognized RF ID 0x%08x\n",
+				CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id));
+			ret = -EINVAL;
+			goto out_no_pci;
+		}
+	} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
+		   CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) {
 		u32 hw_status;
 
 		hw_status = iwl_read_prph(trans, UMAG_GEN_HW_STATUS);
-- 
cgit v1.2.3


From 7125648074e8134b3f7df2f755156bedc1f54020 Mon Sep 17 00:00:00 2001
From: Lior Cohen <lior2.cohen@intel.com>
Date: Thu, 2 Aug 2018 11:48:18 +0300
Subject: iwlwifi: add fw dump upon RT ucode start failure

FW dump was missing in case the RT FW ucode
section failed to load. This failure happens when
the RT section of the FW file is corrupted.

Signed-off-by: Lior Cohen <lior2.cohen@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 8 ++++++++
 drivers/net/wireless/intel/iwlwifi/fw/dbg.h | 1 +
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 2 ++
 3 files changed, 11 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 6243b503d0b0..efd4ac5bba73 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -998,6 +998,14 @@ const struct iwl_fw_dump_desc iwl_dump_desc_assert = {
 };
 IWL_EXPORT_SYMBOL(iwl_dump_desc_assert);
 
+void iwl_fw_assert_error_dump(struct iwl_fw_runtime *fwrt)
+{
+	IWL_INFO(fwrt, "error dump due to fw assert\n");
+	fwrt->dump.desc = &iwl_dump_desc_assert;
+	iwl_fw_error_dump(fwrt);
+}
+IWL_EXPORT_SYMBOL(iwl_fw_assert_error_dump);
+
 void iwl_fw_alive_error_dump(struct iwl_fw_runtime *fwrt)
 {
 	struct iwl_fw_dump_desc *iwl_dump_desc_no_alive =
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index 4a5fa05c7ac2..544b42f9fb19 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -378,6 +378,7 @@ static inline void iwl_fw_resume_timestamp(struct iwl_fw_runtime *fwrt) {}
 
 #endif /* CONFIG_IWLWIFI_DEBUGFS */
 
+void iwl_fw_assert_error_dump(struct iwl_fw_runtime *fwrt);
 void iwl_fw_alive_error_dump(struct iwl_fw_runtime *fwrt);
 void iwl_fw_dbg_collect_sync(struct iwl_fw_runtime *fwrt);
 #endif  /* __iwl_fw_dbg_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index dade206d5511..2cd07247e0a7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -407,6 +407,7 @@ static int iwl_run_unified_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm)
 	ret = iwl_mvm_load_ucode_wait_alive(mvm, IWL_UCODE_REGULAR);
 	if (ret) {
 		IWL_ERR(mvm, "Failed to start RT ucode: %d\n", ret);
+		iwl_fw_assert_error_dump(&mvm->fwrt);
 		goto error;
 	}
 
@@ -1024,6 +1025,7 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	ret = iwl_mvm_load_rt_fw(mvm);
 	if (ret) {
 		IWL_ERR(mvm, "Failed to start RT ucode: %d\n", ret);
+		iwl_fw_assert_error_dump(&mvm->fwrt);
 		goto error;
 	}
 
-- 
cgit v1.2.3


From d91d9b94492f956a39d86c2efa413076025392e7 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 8 Aug 2018 10:42:23 +0300
Subject: iwlwifi: mvm: add support for TWT capabilities

We need to check the TWT support of the peer and to
propagte the capability to the firmware.
The current implementation will enable TWT only if the TWT
support is advertised in the HE CAP IE and in the Extended
Capability IE.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/mac.h   | 16 +++++++++++----
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 24 ++++++++++++++++++++++-
 2 files changed, 35 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
index d0b79fb461bf..2c9e40eedef5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
@@ -185,6 +185,14 @@ struct iwl_mac_data_ibss {
 	__le32 beacon_template;
 } __packed; /* IBSS_MAC_DATA_API_S_VER_1 */
 
+/**
+ * enum iwl_mac_data_policy - policy of the data path for this MAC
+ * @TWT_SUPPORTED: twt is supported
+ */
+enum iwl_mac_data_policy {
+	TWT_SUPPORTED	= BIT(0),
+};
+
 /**
  * struct iwl_mac_data_sta - configuration data for station MAC context
  * @is_assoc: 1 for associated state, 0 otherwise
@@ -193,7 +201,7 @@ struct iwl_mac_data_ibss {
  * @bi: beacon interval in TU, applicable only when associated
  * @reserved1: reserved
  * @dtim_interval: DTIM interval in TU, applicable only when associated
- * @reserved2: reserved
+ * @data_policy: see &enum iwl_mac_data_policy
  * @listen_interval: in beacon intervals, applicable only when associated
  * @assoc_id: unique ID assigned by the AP during association
  * @assoc_beacon_arrive_time: TSF of first beacon after association
@@ -205,11 +213,11 @@ struct iwl_mac_data_sta {
 	__le32 bi;
 	__le32 reserved1;
 	__le32 dtim_interval;
-	__le32 reserved2;
+	__le32 data_policy;
 	__le32 listen_interval;
 	__le32 assoc_id;
 	__le32 assoc_beacon_arrive_time;
-} __packed; /* STA_MAC_DATA_API_S_VER_1 */
+} __packed; /* STA_MAC_DATA_API_S_VER_2 */
 
 /**
  * struct iwl_mac_data_go - configuration data for P2P GO MAC context
@@ -233,7 +241,7 @@ struct iwl_mac_data_go {
 struct iwl_mac_data_p2p_sta {
 	struct iwl_mac_data_sta sta;
 	__le32 ctwin;
-} __packed; /* P2P_STA_MAC_DATA_API_S_VER_1 */
+} __packed; /* P2P_STA_MAC_DATA_API_S_VER_2 */
 
 /**
  * struct iwl_mac_data_pibss - Pseudo IBSS config data
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 3b93293d4559..990ebf89f342 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -777,8 +777,30 @@ static int iwl_mvm_mac_ctxt_cmd_sta(struct iwl_mvm *mvm,
 		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_PROBE_REQUEST);
 
 	if (vif->bss_conf.assoc && vif->bss_conf.he_support &&
-	    !iwlwifi_mod_params.disable_11ax)
+	    !iwlwifi_mod_params.disable_11ax) {
+		struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+		u8 sta_id = mvmvif->ap_sta_id;
+
 		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_11AX);
+		if (sta_id != IWL_MVM_INVALID_STA) {
+			struct ieee80211_sta *sta;
+
+			sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id],
+				lockdep_is_held(&mvm->mutex));
+
+			/*
+			 * TODO: we should check the ext cap IE but it is
+			 * unclear why the spec requires two bits (one in HE
+			 * cap IE, and one in the ext cap IE). In the meantime
+			 * rely on the HE cap IE only.
+			 */
+			if (sta && (sta->he_cap.he_cap_elem.mac_cap_info[0] &
+				    IEEE80211_HE_MAC_CAP0_TWT_RES))
+				ctxt_sta->data_policy |=
+					cpu_to_le32(TWT_SUPPORTED);
+		}
+	}
+
 
 	return iwl_mvm_mac_ctxt_send_cmd(mvm, &cmd);
 }
-- 
cgit v1.2.3


From bd2944665713e397409dcbde8f22aa6025eb3992 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Wed, 13 Jun 2018 14:58:18 +0300
Subject: iwlwifi: fw: add FW API of new TLV infrastructure

Add the FW API of the new debug infrastructure. Next patches
will introduce the utilization of this infra.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 .../net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h    | 399 +++++++++++++++++++++
 1 file changed, 399 insertions(+)
 create mode 100644 drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
new file mode 100644
index 000000000000..82f3c9bbd9b1
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
@@ -0,0 +1,399 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * Contact Information:
+ *  Intel Linux Wireless <linuxwifi@intel.com>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ * BSD LICENSE
+ *
+ * Copyright (C) 2018 Intel Corporation
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+#ifndef __iwl_fw_dbg_tlv_h__
+#define __iwl_fw_dbg_tlv_h__
+
+#include <linux/bitops.h>
+
+/*
+ * struct iwl_fw_ini_header: Common Header for all debug group TLV's structures
+ * @tlv_version: version info
+ * @apply_point: &enum iwl_fw_ini_apply_point
+ * @data: TLV data followed
+ **/
+struct iwl_fw_ini_header {
+	__le32 tlv_version;
+	__le32 apply_point;
+	u8 data[];
+} __packed; /* FW_INI_HEADER_TLV_S */
+
+/**
+ * struct iwl_fw_ini_allocation_tlv - (IWL_FW_INI_TLV_TYPE_BUFFER_ALLOCATION)
+ * buffer allocation TLV - for debug
+ *
+ * @iwl_fw_ini_header: header
+ * @allocation_id: &enum iwl_fw_ini_allocation_id - to bind allocation and hcmd
+ *	if needed (DBGC1/DBGC2/SDFX/...)
+ * @buffer_location: type of iwl_fw_ini_buffer_location
+ * @size: size in bytes
+ * @max_fragments: the maximum allowed fragmentation in the desired memory
+ *	allocation above
+ * @min_frag_size: the minimum allowed fragmentation size in bytes
+*/
+struct iwl_fw_ini_allocation_tlv {
+	struct iwl_fw_ini_header header;
+	__le32 allocation_id;
+	__le32 buffer_location;
+	__le32 size;
+	__le32 max_fragments;
+	__le32 min_frag_size;
+} __packed; /* FW_INI_BUFFER_ALLOCATION_TLV_S_VER_1 */
+
+/**
+ * struct iwl_fw_ini_hcmd (IWL_FW_INI_TLV_TYPE_HCMD)
+ * Generic Host command pass through TLV
+ *
+ * @id: the debug configuration command type for instance: 0xf6 / 0xf5 / DHC
+ * @group: the desired cmd group
+ * @padding: all zeros for dword alignment
+ * @data: all of the relevant command (0xf6/0xf5) to be sent
+*/
+struct iwl_fw_ini_hcmd {
+	u8 id;
+	u8 group;
+	__le16 padding;
+	u8 data[0];
+} __packed; /* FW_INI_HCMD_S */
+
+/**
+ * struct iwl_fw_ini_hcmd_tlv
+ * @header: header
+ * @hcmd: a variable length host-command to be sent to apply the configuration.
+ */
+struct iwl_fw_ini_hcmd_tlv {
+	struct iwl_fw_ini_header header;
+	struct iwl_fw_ini_hcmd hcmd;
+} __packed; /* FW_INI_HCMD_TLV_S_VER_1 */
+
+/*
+ * struct iwl_fw_ini_debug_flow_tlv (IWL_FW_INI_TLV_TYPE_DEBUG_FLOW)
+ *
+ * @header: header
+ * @debug_flow_cfg: &enum iwl_fw_ini_debug_flow
+ */
+struct iwl_fw_ini_debug_flow_tlv {
+	struct iwl_fw_ini_header header;
+	__le32 debug_flow_cfg;
+} __packed; /* FW_INI_DEBUG_FLOW_TLV_S_VER_1 */
+
+#define IWL_FW_INI_MAX_REGION_ID	20
+#define IWL_FW_INI_MAX_NAME		32
+/**
+ * struct iwl_fw_ini_region_cfg
+ * @region_id: ID of this dump configuration
+ * @region_type: &enum iwl_fw_ini_region_type
+ * @num_regions: amount of regions in the address array.
+ * @allocation_id: For DRAM type field substitutes for allocation_id.
+ * @name_len: name length
+ * @name: file name to use for this region
+ * @size: size of the data, in bytes.(unused for IWL_FW_INI_REGION_DRAM_BUFFER)
+ * @start_addr: array of addresses. (unused for IWL_FW_INI_REGION_DRAM_BUFFER)
+ */
+struct iwl_fw_ini_region_cfg {
+	__le32 region_id;
+	__le32 region_type;
+	__le32 name_len;
+	u8 name[IWL_FW_INI_MAX_NAME];
+	union {
+		__le32 num_regions;
+		__le32 allocation_id;
+	};
+	__le32 size;
+	__le32 start_addr[];
+} __packed; /* FW_INI_REGION_CONFIG_S */
+
+/**
+ * struct iwl_fw_ini_region_tlv - (IWL_FW_INI_TLV_TYPE_REGION_CFG)
+ * DUMP sections define IDs and triggers that use those IDs TLV
+ * @header: header
+ * @num_regions: how many different region section and IDs are coming next
+ * @iwl_fw_ini_dump dump_config: list of dump configurations
+ */
+struct iwl_fw_ini_region_tlv {
+	struct iwl_fw_ini_header header;
+	__le32 num_regions;
+	struct iwl_fw_ini_region_cfg region_config[];
+} __packed; /* FW_INI_REGION_CFG_S */
+
+/**
+ * struct iwl_fw_ini_trigger - (IWL_FW_INI_TLV_TYPE_DUMP_CFG)
+ * Region sections define IDs and triggers that use those IDs TLV
+ *
+ * @trigger_id: enum &iwl_fw_ini_tigger_id
+ * @ignore_default: override FW TLV with binary TLV
+ * @dump_delay: delay from trigger fire to dump, in usec
+ * @occurrences: max amount of times to be fired
+ * @ignore_consec: ignore consecutive triggers, in usec
+ * @force_restart: force FW restart
+ * @trigger_data: generic data to be utilized per trigger
+ * @num_regions: number of dump regions defined for this trigger
+ * @data: region IDs
+ */
+struct iwl_fw_ini_trigger {
+	__le32 trigger_id;
+	__le32 ignore_default;
+	__le32 dump_delay;
+	__le32 occurrences;
+	__le32 ignore_consec;
+	__le32 force_restart;
+	__le32 trigger_data;
+	__le32 num_regions;
+	__le32 data[];
+} __packed; /* FW_INI_TRIGGER_CONFIG_S */
+
+/**
+ * struct iwl_fw_ini_trigger_tlv - (IWL_FW_INI_TLV_TYPE_TRIGGERS_CFG)
+ * DUMP sections define IDs and triggers that use those IDs TLV
+ *
+ * @header: header
+ * @num_triggers: how many different triggers section and IDs are coming next
+ * @trigger_config: list of trigger configurations
+ */
+struct iwl_fw_ini_trigger_tlv {
+	struct iwl_fw_ini_header header;
+	__le32 num_triggers;
+	struct iwl_fw_ini_trigger trigger_config[];
+} __packed; /* FW_INI_TRIGGER_CFG_S */
+
+/**
+ * enum iwl_fw_ini_trigger_id
+ * @IWL_FW_TRIGGER_ID_FW_ASSERT: FW assert
+ * @IWL_FW_TRIGGER_ID_FW_TFD_Q_HANG: TFD queue hang
+ * @IWL_FW_TRIGGER_ID_FW_HW_ERROR: HW assert
+ * @IWL_FW_TRIGGER_ID_FW_TRIGGER_ERROR: FW error notification
+ * @IWL_FW_TRIGGER_ID_FW_TRIGGER_WARNING: FW warning notification
+ * @IWL_FW_TRIGGER_ID_FW_TRIGGER_INFO: FW info notification
+ * @IWL_FW_TRIGGER_ID_FW_TRIGGER_DEBUG: FW debug notification
+ * @IWL_FW_TRIGGER_ID_USER_TRIGGER: User trigger
+ * @IWL_FW_TRIGGER_ID_HOST_PEER_CLIENT_INACTIVITY: peer inactivity
+ * @FW_DEBUG_TLV_TRIGGER_ID_HOST_DID_INITIATED_EVENT: undefined
+ * @IWL_FW_TRIGGER_ID_HOST_TX_LATENCY_THRESHOLD_CROSSED: TX latency
+ *	threshold was crossed
+ * @IWL_FW_TRIGGER_ID_HOST_TX_RESPONSE_STATUS_FAILED: TX failed
+ * @IWL_FW_TRIGGER_ID_HOST_OS_REQ_DEAUTH_PEER: Deauth initiated by host
+ * @IWL_FW_TRIGGER_ID_HOST_STOP_GO_REQUEST: stop GO request
+ * @IWL_FW_TRIGGER_ID_HOST_START_GO_REQUEST: start GO request
+ * @IWL_FW_TRIGGER_ID_HOST_JOIN_GROUP_REQUEST: join P2P group request
+ * @IWL_FW_TRIGGER_ID_HOST_SCAN_START: scan started event
+ * @IWL_FW_TRIGGER_ID_HOST_SCAN_SUBMITTED: undefined
+ * @IWL_FW_TRIGGER_ID_HOST_SCAN_PARAMS: undefined
+ * @IWL_FW_TRIGGER_ID_HOST_CHECK_FOR_HANG: undefined
+ * @IWL_FW_TRIGGER_ID_HOST_BAR_RECEIVED: BAR frame was received
+ * @IWL_FW_TRIGGER_ID_HOST_AGG_TX_RESPONSE_STATUS_FAILED: agg TX failed
+ * @IWL_FW_TRIGGER_ID_HOST_EAPOL_TX_RESPONSE_FAILED: EAPOL TX failed
+ * @IWL_FW_TRIGGER_ID_HOST_FAKE_TX_RESPONSE_SUSPECTED: suspicious TX response
+ * @IWL_FW_TRIGGER_ID_HOST_AUTH_REQ_FROM_ASSOC_CLIENT: received suspicious auth
+ * @IWL_FW_TRIGGER_ID_HOST_ROAM_COMPLETE: roaming was completed
+ * @IWL_FW_TRIGGER_ID_HOST_AUTH_ASSOC_FAST_FAILED: fast assoc failed
+ * @IWL_FW_TRIGGER_ID_HOST_D3_START: D3 start
+ * @IWL_FW_TRIGGER_ID_HOST_D3_END: D3 end
+ * @IWL_FW_TRIGGER_ID_HOST_BSS_MISSED_BEACONS: missed beacon events
+ * @IWL_FW_TRIGGER_ID_HOST_P2P_CLIENT_MISSED_BEACONS: P2P missed beacon events
+ * @IWL_FW_TRIGGER_ID_HOST_PEER_CLIENT_TX_FAILURES:  undefined
+ * @IWL_FW_TRIGGER_ID_HOST_TX_WFD_ACTION_FRAME_FAILED: undefined
+ * @IWL_FW_TRIGGER_ID_HOST_AUTH_ASSOC_FAILED: authentication / association
+ *	failed
+ * @IWL_FW_TRIGGER_ID_HOST_SCAN_COMPLETE: scan complete event
+ * @IWL_FW_TRIGGER_ID_HOST_SCAN_ABORT: scan abort complete
+ * @IWL_FW_TRIGGER_ID_HOST_NIC_ALIVE: nic alive message was received
+ * @IWL_FW_TRIGGER_ID_HOST_CHANNEL_SWITCH_COMPLETE: CSA was completed
+ * @IWL_FW_TRIGGER_ID_NUM: number of trigger IDs
+ */
+enum iwl_fw_ini_trigger_id {
+	/* Errors triggers */
+	IWL_FW_TRIGGER_ID_FW_ASSERT				= 1,
+	IWL_FW_TRIGGER_ID_FW_TFD_Q_HANG				= 2,
+	IWL_FW_TRIGGER_ID_FW_HW_ERROR				= 3,
+	/* Generic triggers */
+	IWL_FW_TRIGGER_ID_FW_TRIGGER_ERROR			= 4,
+	IWL_FW_TRIGGER_ID_FW_TRIGGER_WARNING			= 5,
+	IWL_FW_TRIGGER_ID_FW_TRIGGER_INFO			= 6,
+	IWL_FW_TRIGGER_ID_FW_TRIGGER_DEBUG			= 7,
+	/* User Trigger */
+	IWL_FW_TRIGGER_ID_USER_TRIGGER				= 8,
+	/* Host triggers */
+	IWL_FW_TRIGGER_ID_HOST_PEER_CLIENT_INACTIVITY		= 9,
+	IWL_FW_TRIGGER_ID_HOST_DID_INITIATED_EVENT		= 10,
+	IWL_FW_TRIGGER_ID_HOST_TX_LATENCY_THRESHOLD_CROSSED	= 11,
+	IWL_FW_TRIGGER_ID_HOST_TX_RESPONSE_STATUS_FAILED	= 12,
+	IWL_FW_TRIGGER_ID_HOST_OS_REQ_DEAUTH_PEER		= 13,
+	IWL_FW_TRIGGER_ID_HOST_STOP_GO_REQUEST			= 14,
+	IWL_FW_TRIGGER_ID_HOST_START_GO_REQUEST			= 15,
+	IWL_FW_TRIGGER_ID_HOST_JOIN_GROUP_REQUEST		= 16,
+	IWL_FW_TRIGGER_ID_HOST_SCAN_START			= 17,
+	IWL_FW_TRIGGER_ID_HOST_SCAN_SUBITTED			= 18,
+	IWL_FW_TRIGGER_ID_HOST_SCAN_PARAMS			= 19,
+	IWL_FW_TRIGGER_ID_HOST_CHECK_FOR_HANG			= 20,
+	IWL_FW_TRIGGER_ID_HOST_BAR_RECEIVED			= 21,
+	IWL_FW_TRIGGER_ID_HOST_AGG_TX_RESPONSE_STATUS_FAILED	= 22,
+	IWL_FW_TRIGGER_ID_HOST_EAPOL_TX_RESPONSE_FAILED		= 23,
+	IWL_FW_TRIGGER_ID_HOST_FAKE_TX_RESPONSE_SUSPECTED	= 24,
+	IWL_FW_TRIGGER_ID_HOST_AUTH_REQ_FROM_ASSOC_CLIENT	= 25,
+	IWL_FW_TRIGGER_ID_HOST_ROAM_COMPLETE			= 26,
+	IWL_FW_TRIGGER_ID_HOST_AUTH_ASSOC_FAST_FAILED		= 27,
+	IWL_FW_TRIGGER_ID_HOST_D3_START				= 28,
+	IWL_FW_TRIGGER_ID_HOST_D3_END				= 29,
+	IWL_FW_TRIGGER_ID_HOST_BSS_MISSED_BEACONS		= 30,
+	IWL_FW_TRIGGER_ID_HOST_P2P_CLIENT_MISSED_BEACONS	= 31,
+	IWL_FW_TRIGGER_ID_HOST_PEER_CLIENT_TX_FAILURES		= 32,
+	IWL_FW_TRIGGER_ID_HOST_TX_WFD_ACTION_FRAME_FAILED	= 33,
+	IWL_FW_TRIGGER_ID_HOST_AUTH_ASSOC_FAILED		= 34,
+	IWL_FW_TRIGGER_ID_HOST_SCAN_COMPLETE			= 35,
+	IWL_FW_TRIGGER_ID_HOST_SCAN_ABORT			= 36,
+	IWL_FW_TRIGGER_ID_HOST_NIC_ALIVE			= 37,
+	IWL_FW_TRIGGER_ID_HOST_CHANNEL_SWITCH_COMPLETE          = 38,
+	IWL_FW_TRIGGER_ID_NUM,
+}; /* FW_INI_TRIGGER_ID_E_VER_1 */
+
+/**
+ * enum iwl_fw_ini_apply_point
+ * @IWL_FW_INI_APPLY_INVALID: invalid
+ * @IWL_FW_INI_APPLY_EARLY: pre loading FW
+ * @IWL_FW_INI_APPLY_AFTER_ALIVE: first cmd from host after alive
+ * @IWL_FW_INI_APPLY_POST_INIT: last cmd in initialization sequence
+ * @IWL_FW_INI_APPLY_MISSED_BEACONS: missed beacons notification
+ * @IWL_FW_INI_APPLY_SCAN_COMPLETE: scan completed
+ * @IWL_FW_INI_APPLY_NUM: number of apply points
+*/
+enum iwl_fw_ini_apply_point {
+	IWL_FW_INI_APPLY_INVALID,
+	IWL_FW_INI_APPLY_EARLY,
+	IWL_FW_INI_APPLY_AFTER_ALIVE,
+	IWL_FW_INI_APPLY_POST_INIT,
+	IWL_FW_INI_APPLY_MISSED_BEACONS,
+	IWL_FW_INI_APPLY_SCAN_COMPLETE,
+	IWL_FW_INI_APPLY_NUM,
+}; /* FW_INI_APPLY_POINT_E_VER_1 */
+
+/**
+ * enum iwl_fw_ini_allocation_id
+ * @IWL_FW_INI_ALLOCATION_INVALID: invalid
+ * @IWL_FW_INI_ALLOCATION_ID_DBGC1: allocation meant for DBGC1 configuration
+ * @IWL_FW_INI_ALLOCATION_ID_DBGC2: allocation meant for DBGC2 configuration
+ * @IWL_FW_INI_ALLOCATION_ID_DBGC3: allocation meant for DBGC3 configuration
+ * @IWL_FW_INI_ALLOCATION_ID_SDFX: for SDFX module
+ * @IWL_FW_INI_ALLOCATION_ID_FW_DUMP: used for crash and runtime dumps
+ * @IWL_FW_INI_ALLOCATION_ID_USER_DEFINED: for future user scenarios
+*/
+enum iwl_fw_ini_allocation_id {
+	IWL_FW_INI_ALLOCATION_INVALID,
+	IWL_FW_INI_ALLOCATION_ID_DBGC1,
+	IWL_FW_INI_ALLOCATION_ID_DBGC2,
+	IWL_FW_INI_ALLOCATION_ID_DBGC3,
+	IWL_FW_INI_ALLOCATION_ID_SDFX,
+	IWL_FW_INI_ALLOCATION_ID_FW_DUMP,
+	IWL_FW_INI_ALLOCATION_ID_USER_DEFINED,
+}; /* FW_INI_ALLOCATION_ID_E_VER_1 */
+
+/**
+ * enum iwl_fw_ini_buffer_location
+ * @IWL_FW_INI_LOCATION_INVALID: invalid
+ * @IWL_FW_INI_LOCATION_SRAM_PATH: SRAM location
+ * @IWL_FW_INI_LOCATION_DRAM_PATH: DRAM location
+ */
+enum iwl_fw_ini_buffer_location {
+	IWL_FW_INI_LOCATION_SRAM_INVALID,
+	IWL_FW_INI_LOCATION_SRAM_PATH,
+	IWL_FW_INI_LOCATION_DRAM_PATH,
+}; /* FW_INI_BUFFER_LOCATION_E_VER_1 */
+
+/**
+ * enum iwl_fw_ini_debug_flow
+ * @IWL_FW_INI_DEBUG_INVALID: invalid
+ * @IWL_FW_INI_DEBUG_DBTR_FLOW: undefined
+ * @IWL_FW_INI_DEBUG_TB2DTF_FLOW: undefined
+ */
+enum iwl_fw_ini_debug_flow {
+	IWL_FW_INI_DEBUG_INVALID,
+	IWL_FW_INI_DEBUG_DBTR_FLOW,
+	IWL_FW_INI_DEBUG_TB2DTF_FLOW,
+}; /* FW_INI_DEBUG_FLOW_E_VER_1 */
+
+/**
+ * enum iwl_fw_ini_region_type
+ * @IWL_FW_INI_REGION_INVALID: invalid
+ * @IWL_FW_INI_REGION_DEVICE_MEMORY: device internal memory
+ * @IWL_FW_INI_REGION_PERIPHERY_MAC: periphery registers of MAC
+ * @IWL_FW_INI_REGION_PERIPHERY_PHY: periphery registers of PHY
+ * @IWL_FW_INI_REGION_PERIPHERY_AUX: periphery registers of AUX
+ * @IWL_FW_INI_REGION_DRAM_BUFFER: DRAM buffer
+ * @IWL_FW_INI_REGION_DRAM_IMR: IMR memory
+ * @IWL_FW_INI_REGION_INTERNAL_BUFFER: undefined
+ * @IWL_FW_INI_REGION_TXF: TX fifos
+ * @IWL_FW_INI_REGION_RXF: RX fifo
+ * @IWL_FW_INI_REGION_PAGING: paging memory
+ * @IWL_FW_INI_REGION_CSR: CSR registers
+ * @IWL_FW_INI_REGION_NUM: number of region types
+ */
+enum iwl_fw_ini_region_type {
+	IWL_FW_INI_REGION_INVALID,
+	IWL_FW_INI_REGION_DEVICE_MEMORY,
+	IWL_FW_INI_REGION_PERIPHERY_MAC,
+	IWL_FW_INI_REGION_PERIPHERY_PHY,
+	IWL_FW_INI_REGION_PERIPHERY_AUX,
+	IWL_FW_INI_REGION_DRAM_BUFFER,
+	IWL_FW_INI_REGION_DRAM_IMR,
+	IWL_FW_INI_REGION_INTERNAL_BUFFER,
+	IWL_FW_INI_REGION_TXF,
+	IWL_FW_INI_REGION_RXF,
+	IWL_FW_INI_REGION_PAGING,
+	IWL_FW_INI_REGION_CSR,
+	IWL_FW_INI_REGION_NUM
+}; /* FW_INI_REGION_TYPE_E_VER_1*/
+
+#endif
-- 
cgit v1.2.3


From f14cda6f3b31347d1d814839d7e671dea749f1b0 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Thu, 17 May 2018 10:14:30 +0300
Subject: iwlwifi: trans: parse and store debug ini TLVs

The new debug ini TLVs can be either packed into firmware
binary or written in external file. Support loading them
from both. Store the data per apply point. Apply point is
a point during driver runtime, where the TLV becomes active.
For example, a trigger of hardware error may be configured
to collect a subset of data pre-alive, as a opposed to HW
error that occurs after alive.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/Makefile        |   1 +
 drivers/net/wireless/intel/iwlwifi/fw/file.h       |   7 +
 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c   | 154 +++++++++++++++++++++
 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h   |  84 +++++++++++
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c       |  17 +++
 drivers/net/wireless/intel/iwlwifi/iwl-modparams.h |   2 +
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h     |   4 +
 7 files changed, 269 insertions(+)
 create mode 100644 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h

diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index 04e376cc898c..ff41987a7e35 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -11,6 +11,7 @@ iwlwifi-objs		+= pcie/ctxt-info.o pcie/ctxt-info-gen3.o
 iwlwifi-objs		+= pcie/trans-gen2.o pcie/tx-gen2.o
 iwlwifi-$(CONFIG_IWLDVM) += cfg/1000.o cfg/2000.o cfg/5000.o cfg/6000.o
 iwlwifi-$(CONFIG_IWLMVM) += cfg/7000.o cfg/8000.o cfg/9000.o cfg/22000.o
+iwlwifi-objs		+= iwl-dbg-tlv.o
 iwlwifi-objs		+= iwl-trans.o
 iwlwifi-objs		+= fw/notif-wait.o
 iwlwifi-$(CONFIG_IWLMVM) += fw/paging.o fw/smem.o fw/init.o fw/dbg.o
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index 6005a41c53d1..81f557c0b58d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -91,6 +91,8 @@ struct iwl_ucode_header {
 	} u;
 };
 
+#define IWL_UCODE_INI_TLV_GROUP	BIT(24)
+
 /*
  * new TLV uCode file layout
  *
@@ -141,6 +143,11 @@ enum iwl_ucode_tlv_type {
 	IWL_UCODE_TLV_FW_GSCAN_CAPA	= 50,
 	IWL_UCODE_TLV_FW_MEM_SEG	= 51,
 	IWL_UCODE_TLV_IML		= 52,
+	IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION	= IWL_UCODE_INI_TLV_GROUP | 0x1,
+	IWL_UCODE_TLV_TYPE_HCMD			= IWL_UCODE_INI_TLV_GROUP | 0x2,
+	IWL_UCODE_TLV_TYPE_REGIONS		= IWL_UCODE_INI_TLV_GROUP | 0x3,
+	IWL_UCODE_TLV_TYPE_TRIGGERS		= IWL_UCODE_INI_TLV_GROUP | 0x4,
+	IWL_UCODE_TLV_TYPE_DEBUG_FLOW		= IWL_UCODE_INI_TLV_GROUP | 0x5,
 
 	/* TLVs 0x1000-0x2000 are for internal driver usage */
 	IWL_UCODE_TLV_FW_DBG_DUMP_LST	= 0x1000,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
new file mode 100644
index 000000000000..acefd7d5d099
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -0,0 +1,154 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.
+ *
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * Contact Information:
+ *  Intel Linux Wireless <linuxwifi@intel.com>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ * BSD LICENSE
+ *
+ * Copyright (C) 2018 Intel Corporation
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+
+#include <linux/firmware.h>
+#include "iwl-trans.h"
+#include "iwl-dbg-tlv.h"
+
+void iwl_fw_dbg_copy_tlv(struct iwl_trans *trans, struct iwl_ucode_tlv *tlv)
+{
+	struct iwl_apply_point_data *data;
+	struct iwl_fw_ini_header *header = (void *)&tlv->data[0];
+	u32 apply_point = le32_to_cpu(header->apply_point);
+
+	int copy_size = le32_to_cpu(tlv->length) + sizeof(*tlv);
+
+	if (WARN_ONCE(apply_point >= IWL_FW_INI_APPLY_NUM,
+		      "Invalid apply point id %d\n", apply_point))
+		return;
+
+	data = &trans->apply_points[apply_point];
+
+	/*
+	 * Make sure we still have room to copy this TLV. Offset points to the
+	 * location the last copy ended.
+	 */
+	if (WARN_ONCE(data->offset + copy_size > data->size,
+		      "Not enough memory for apply point %d\n",
+		      apply_point))
+		return;
+
+	memcpy(data->data + data->offset, (void *)tlv, copy_size);
+	data->offset += copy_size;
+}
+
+void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data)
+{
+	struct iwl_ucode_tlv *tlv;
+	u32 size[IWL_FW_INI_APPLY_NUM] = {0};
+	int i;
+
+	while (len >= sizeof(*tlv)) {
+		u32 tlv_len, tlv_type, apply;
+		struct iwl_fw_ini_header *hdr;
+
+		len -= sizeof(*tlv);
+		tlv = (void *)data;
+
+		tlv_len = le32_to_cpu(tlv->length);
+		tlv_type = le32_to_cpu(tlv->type);
+
+		if (len < tlv_len)
+			return;
+
+		len -= ALIGN(tlv_len, 4);
+		data += sizeof(*tlv) + ALIGN(tlv_len, 4);
+
+		if (!(tlv_type & IWL_UCODE_INI_TLV_GROUP))
+			continue;
+
+		hdr = (void *)&tlv->data[0];
+		apply = le32_to_cpu(hdr->apply_point);
+
+		if (WARN_ON(apply >= IWL_FW_INI_APPLY_NUM))
+			continue;
+
+		size[apply] += sizeof(*tlv) + tlv_len;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(size); i++) {
+		void *mem;
+
+		if (!size[i])
+			continue;
+
+		mem = kzalloc(size[i], GFP_KERNEL);
+
+		if (!mem) {
+			IWL_ERR(trans, "No memory for apply point %d\n", i);
+			return;
+		}
+
+		trans->apply_points[i].data = mem;
+		trans->apply_points[i].size = size[i];
+	}
+}
+
+void iwl_fw_dbg_free(struct iwl_trans *trans)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(trans->apply_points); i++) {
+		kfree(trans->apply_points[i].data);
+		trans->apply_points[i].size = 0;
+		trans->apply_points[i].offset = 0;
+	}
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h
new file mode 100644
index 000000000000..a368017af089
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h
@@ -0,0 +1,84 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.
+ *
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * Contact Information:
+ *  Intel Linux Wireless <linuxwifi@intel.com>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ * BSD LICENSE
+ *
+ * Copyright (C) 2018 Intel Corporation
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+#ifndef __iwl_dbg_tlv_h__
+#define __iwl_dbg_tlv_h__
+
+#include <linux/device.h>
+#include <linux/types.h>
+
+/**
+ * struct iwl_apply_point_data
+ * @data: start address of this apply point data
+ * @size total size of the data
+ * @offset: current offset of the copied data
+ */
+struct iwl_apply_point_data {
+	void *data;
+	int size;
+	int offset;
+};
+
+struct iwl_trans;
+void iwl_fw_dbg_free(struct iwl_trans *trans);
+void iwl_fw_dbg_copy_tlv(struct iwl_trans *trans, struct iwl_ucode_tlv *tlv);
+void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data);
+
+#endif /* __iwl_dbg_tlv_h__*/
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index ba41d23b4211..a986e5795831 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -72,6 +72,7 @@
 #include "iwl-op-mode.h"
 #include "iwl-agn-hw.h"
 #include "fw/img.h"
+#include "iwl-dbg-tlv.h"
 #include "iwl-config.h"
 #include "iwl-modparams.h"
 
@@ -645,6 +646,9 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 
 	len -= sizeof(*ucode);
 
+	if (iwlwifi_mod_params.enable_ini)
+		iwl_alloc_dbg_tlv(drv->trans, len, data);
+
 	while (len >= sizeof(*tlv)) {
 		len -= sizeof(*tlv);
 		tlv = (void *)data;
@@ -1086,6 +1090,13 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 				return -ENOMEM;
 			break;
 			}
+		case IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION:
+		case IWL_UCODE_TLV_TYPE_HCMD:
+		case IWL_UCODE_TLV_TYPE_REGIONS:
+		case IWL_UCODE_TLV_TYPE_TRIGGERS:
+		case IWL_UCODE_TLV_TYPE_DEBUG_FLOW:
+			if (iwlwifi_mod_params.enable_ini)
+				iwl_fw_dbg_copy_tlv(drv->trans, tlv);
 		default:
 			IWL_DEBUG_INFO(drv, "unknown TLV: %d\n", tlv_type);
 			break;
@@ -1619,6 +1630,8 @@ void iwl_drv_stop(struct iwl_drv *drv)
 	debugfs_remove_recursive(drv->dbgfs_drv);
 #endif
 
+	iwl_fw_dbg_free(drv->trans);
+
 	kfree(drv);
 }
 
@@ -1749,6 +1762,10 @@ MODULE_PARM_DESC(lar_disable, "disable LAR functionality (default: N)");
 module_param_named(uapsd_disable, iwlwifi_mod_params.uapsd_disable, uint, 0644);
 MODULE_PARM_DESC(uapsd_disable,
 		 "disable U-APSD functionality bitmap 1: BSS 2: P2P Client (default: 3)");
+module_param_named(enable_ini, iwlwifi_mod_params.enable_ini,
+		   bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(enable_ini,
+		 "Enable debug INI TLV FW debug infrastructure (default: 0");
 
 /*
  * set bt_coex_active to true, uCode will do kill/defer
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
index 6fc8dac4aab7..73b1c46f1158 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
@@ -122,6 +122,7 @@ enum iwl_uapsd_disable {
  * @fw_monitor: allow to use firmware monitor
  * @disable_11ac: disable VHT capabilities, default = false.
  * @remove_when_gone: remove an inaccessible device from the PCIe bus.
+ * @enable_ini: enable new FW debug infratructure (INI TLVs)
  */
 struct iwl_mod_params {
 	int swcrypto;
@@ -148,6 +149,7 @@ struct iwl_mod_params {
 	 */
 	bool disable_11ax;
 	bool remove_when_gone;
+	bool enable_ini;
 };
 
 #endif /* #__iwl_modparams_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index b0300e824815..08512305c5ac 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -73,6 +73,8 @@
 #include "iwl-op-mode.h"
 #include "fw/api/cmdhdr.h"
 #include "fw/api/txq.h"
+#include "fw/api/dbg-tlv.h"
+#include "iwl-dbg-tlv.h"
 
 /**
  * DOC: Transport layer - what is it ?
@@ -773,6 +775,8 @@ struct iwl_trans {
 	struct lockdep_map sync_cmd_lockdep_map;
 #endif
 
+	struct iwl_apply_point_data apply_points[IWL_FW_INI_APPLY_NUM];
+
 	const struct iwl_fw_dbg_dest_tlv_v1 *dbg_dest_tlv;
 	const struct iwl_fw_dbg_conf_tlv *dbg_conf_tlv[FW_DBG_CONF_MAX];
 	struct iwl_fw_dbg_trigger_tlv * const *dbg_trigger_tlv;
-- 
cgit v1.2.3


From 68f6f492c4fae8b5f0204de99689408f524c8b14 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Thu, 14 Jun 2018 10:49:03 +0300
Subject: iwlwifi: trans: support loading ini TLVs from external file

Support loading and storing ini TLVs from external
file. Those TLVs are appended to the default TLVs,
so store them separately.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c | 81 ++++++++++++++++++++++--
 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h |  7 +-
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c     |  9 +--
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h   |  3 +
 4 files changed, 89 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index acefd7d5d099..7b2951521c77 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -63,7 +63,8 @@
 #include "iwl-trans.h"
 #include "iwl-dbg-tlv.h"
 
-void iwl_fw_dbg_copy_tlv(struct iwl_trans *trans, struct iwl_ucode_tlv *tlv)
+void iwl_fw_dbg_copy_tlv(struct iwl_trans *trans, struct iwl_ucode_tlv *tlv,
+			 bool ext)
 {
 	struct iwl_apply_point_data *data;
 	struct iwl_fw_ini_header *header = (void *)&tlv->data[0];
@@ -75,7 +76,10 @@ void iwl_fw_dbg_copy_tlv(struct iwl_trans *trans, struct iwl_ucode_tlv *tlv)
 		      "Invalid apply point id %d\n", apply_point))
 		return;
 
-	data = &trans->apply_points[apply_point];
+	if (ext)
+		data = &trans->apply_points_ext[apply_point];
+	else
+		data = &trans->apply_points[apply_point];
 
 	/*
 	 * Make sure we still have room to copy this TLV. Offset points to the
@@ -90,7 +94,8 @@ void iwl_fw_dbg_copy_tlv(struct iwl_trans *trans, struct iwl_ucode_tlv *tlv)
 	data->offset += copy_size;
 }
 
-void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data)
+void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data,
+		       bool ext)
 {
 	struct iwl_ucode_tlv *tlv;
 	u32 size[IWL_FW_INI_APPLY_NUM] = {0};
@@ -137,8 +142,13 @@ void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data)
 			return;
 		}
 
-		trans->apply_points[i].data = mem;
-		trans->apply_points[i].size = size[i];
+		if (ext) {
+			trans->apply_points_ext[i].data = mem;
+			trans->apply_points_ext[i].size = size[i];
+		} else {
+			trans->apply_points[i].data = mem;
+			trans->apply_points[i].size = size[i];
+		}
 	}
 }
 
@@ -150,5 +160,66 @@ void iwl_fw_dbg_free(struct iwl_trans *trans)
 		kfree(trans->apply_points[i].data);
 		trans->apply_points[i].size = 0;
 		trans->apply_points[i].offset = 0;
+
+		kfree(trans->apply_points_ext[i].data);
+		trans->apply_points_ext[i].size = 0;
+		trans->apply_points_ext[i].offset = 0;
+	}
+}
+
+static int iwl_parse_fw_dbg_tlv(struct iwl_trans *trans, const u8 *data,
+				size_t len)
+{
+	struct iwl_ucode_tlv *tlv;
+	enum iwl_ucode_tlv_type tlv_type;
+	u32 tlv_len;
+
+	while (len >= sizeof(*tlv)) {
+		len -= sizeof(*tlv);
+		tlv = (void *)data;
+
+		tlv_len = le32_to_cpu(tlv->length);
+		tlv_type = le32_to_cpu(tlv->type);
+
+		if (len < tlv_len) {
+			IWL_ERR(trans, "invalid TLV len: %zd/%u\n",
+				len, tlv_len);
+			return -EINVAL;
+		}
+		len -= ALIGN(tlv_len, 4);
+		data += sizeof(*tlv) + ALIGN(tlv_len, 4);
+
+		switch (tlv_type) {
+		case IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION:
+		case IWL_UCODE_TLV_TYPE_HCMD:
+		case IWL_UCODE_TLV_TYPE_REGIONS:
+		case IWL_UCODE_TLV_TYPE_TRIGGERS:
+		case IWL_UCODE_TLV_TYPE_DEBUG_FLOW:
+			iwl_fw_dbg_copy_tlv(trans, tlv, true);
+		default:
+			WARN_ONCE(1, "Invalid TLV %x\n", tlv_type);
+			break;
+		}
 	}
+
+	return 0;
+}
+
+void iwl_load_fw_dbg_tlv(struct device *dev, struct iwl_trans *trans)
+{
+	const struct firmware *fw;
+	int res;
+
+	if (trans->external_ini_loaded || !iwlwifi_mod_params.enable_ini)
+		return;
+
+	res = request_firmware(&fw, "iwl-dbg-tlv.ini", dev);
+	if (res)
+		return;
+
+	iwl_alloc_dbg_tlv(trans, fw->size, fw->data, true);
+	iwl_parse_fw_dbg_tlv(trans, fw->data, fw->size);
+
+	trans->external_ini_loaded = true;
+	release_firmware(fw);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h
index a368017af089..222cd789e07a 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h
@@ -77,8 +77,11 @@ struct iwl_apply_point_data {
 };
 
 struct iwl_trans;
+void iwl_load_fw_dbg_tlv(struct device *dev, struct iwl_trans *trans);
 void iwl_fw_dbg_free(struct iwl_trans *trans);
-void iwl_fw_dbg_copy_tlv(struct iwl_trans *trans, struct iwl_ucode_tlv *tlv);
-void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data);
+void iwl_fw_dbg_copy_tlv(struct iwl_trans *trans, struct iwl_ucode_tlv *tlv,
+			 bool ext);
+void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data,
+		       bool ext);
 
 #endif /* __iwl_dbg_tlv_h__*/
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index a986e5795831..7b98125e4eb9 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -647,7 +647,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 	len -= sizeof(*ucode);
 
 	if (iwlwifi_mod_params.enable_ini)
-		iwl_alloc_dbg_tlv(drv->trans, len, data);
+		iwl_alloc_dbg_tlv(drv->trans, len, data, false);
 
 	while (len >= sizeof(*tlv)) {
 		len -= sizeof(*tlv);
@@ -1096,7 +1096,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 		case IWL_UCODE_TLV_TYPE_TRIGGERS:
 		case IWL_UCODE_TLV_TYPE_DEBUG_FLOW:
 			if (iwlwifi_mod_params.enable_ini)
-				iwl_fw_dbg_copy_tlv(drv->trans, tlv);
+				iwl_fw_dbg_copy_tlv(drv->trans, tlv, false);
 		default:
 			IWL_DEBUG_INFO(drv, "unknown TLV: %d\n", tlv_type);
 			break;
@@ -1576,7 +1576,7 @@ struct iwl_drv *iwl_drv_start(struct iwl_trans *trans)
 	if (!drv->dbgfs_drv) {
 		IWL_ERR(drv, "failed to create debugfs directory\n");
 		ret = -ENOMEM;
-		goto err_free_drv;
+		goto err_free_tlv;
 	}
 
 	/* Create transport layer debugfs dir */
@@ -1601,7 +1601,8 @@ err_fw:
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 err_free_dbgfs:
 	debugfs_remove_recursive(drv->dbgfs_drv);
-err_free_drv:
+err_free_tlv:
+	iwl_fw_dbg_free(drv->trans);
 #endif
 	kfree(drv);
 err:
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 08512305c5ac..0c0cd7dccde8 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -776,6 +776,9 @@ struct iwl_trans {
 #endif
 
 	struct iwl_apply_point_data apply_points[IWL_FW_INI_APPLY_NUM];
+	struct iwl_apply_point_data apply_points_ext[IWL_FW_INI_APPLY_NUM];
+
+	bool external_ini_loaded;
 
 	const struct iwl_fw_dbg_dest_tlv_v1 *dbg_dest_tlv;
 	const struct iwl_fw_dbg_conf_tlv *dbg_conf_tlv[FW_DBG_CONF_MAX];
-- 
cgit v1.2.3


From 743742231a79ea068b3897165a74f9a04cf76846 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Wed, 13 Jun 2018 14:41:35 +0300
Subject: iwlwifi: dbg: disable triggers for ini

When ini is loaded, disable all legacy trigger
configuration.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c      | 3 +++
 drivers/net/wireless/intel/iwlwifi/fw/dbg.h      | 3 +++
 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c | 2 ++
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h   | 1 +
 4 files changed, 9 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index efd4ac5bba73..6460b937d331 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1117,6 +1117,9 @@ int iwl_fw_dbg_collect_trig(struct iwl_fw_runtime *fwrt,
 	int ret, len = 0;
 	char buf[64];
 
+	if (fwrt->trans->ini_valid)
+		return 0;
+
 	if (fmt) {
 		va_list ap;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index 544b42f9fb19..07403aa29793 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -192,6 +192,9 @@ _iwl_fw_dbg_trigger_on(struct iwl_fw_runtime *fwrt,
 {
 	struct iwl_fw_dbg_trigger_tlv *trig;
 
+	if (fwrt->trans->ini_valid)
+		return NULL;
+
 	if (!iwl_fw_dbg_trigger_enabled(fwrt->fw, id))
 		return NULL;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index 7b2951521c77..0160662a1749 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -149,6 +149,8 @@ void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data,
 			trans->apply_points[i].data = mem;
 			trans->apply_points[i].size = size[i];
 		}
+
+		trans->ini_valid = true;
 	}
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 0c0cd7dccde8..3d455cf5822b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -779,6 +779,7 @@ struct iwl_trans {
 	struct iwl_apply_point_data apply_points_ext[IWL_FW_INI_APPLY_NUM];
 
 	bool external_ini_loaded;
+	bool ini_valid;
 
 	const struct iwl_fw_dbg_dest_tlv_v1 *dbg_dest_tlv;
 	const struct iwl_fw_dbg_conf_tlv *dbg_conf_tlv[FW_DBG_CONF_MAX];
-- 
cgit v1.2.3


From d47902f9f71d7679b9a2a9d14aa7d4b98d95430b Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Wed, 13 Jun 2018 15:19:47 +0300
Subject: iwlwifi: dbg: add apply point logic

Add a function to be called when apply point occurs.
For each of the TLVs, the function will perform the
apply point logic:
- For HCMD - send the stored host command
- For buffer allocation - allocate the memory and send the
  buffer allocation command
- For trigger and region - update the stored configuration

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c      | 207 +++++++++++++++++++++++
 drivers/net/wireless/intel/iwlwifi/fw/dbg.h      |   4 +
 drivers/net/wireless/intel/iwlwifi/fw/img.h      |  26 +++
 drivers/net/wireless/intel/iwlwifi/fw/runtime.h  |   3 +
 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c |   3 +
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h   |   3 +-
 6 files changed, 244 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 6460b937d331..76050cc3532a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1263,3 +1263,210 @@ void iwl_fw_dbg_read_d3_debug_data(struct iwl_fw_runtime *fwrt)
 				 cfg->d3_debug_data_length);
 }
 IWL_EXPORT_SYMBOL(iwl_fw_dbg_read_d3_debug_data);
+
+static void
+iwl_fw_dbg_buffer_allocation(struct iwl_fw_runtime *fwrt,
+			     struct iwl_fw_ini_allocation_tlv *alloc)
+{
+	struct iwl_trans *trans = fwrt->trans;
+	struct iwl_continuous_record_cmd cont_rec = {};
+	struct iwl_buffer_allocation_cmd *cmd = (void *)&cont_rec.pad[0];
+	struct iwl_host_cmd hcmd = {
+		.id = LDBG_CONFIG_CMD,
+		.flags = CMD_ASYNC,
+		.data[0] = &cont_rec,
+		.len[0] = sizeof(cont_rec),
+	};
+	void *virtual_addr = NULL;
+	u32 size = le32_to_cpu(alloc->size);
+	dma_addr_t phys_addr;
+
+	cont_rec.record_mode.enable_recording = cpu_to_le16(BUFFER_ALLOCATION);
+
+	if (!trans->num_blocks &&
+	    le32_to_cpu(alloc->buffer_location) !=
+	    IWL_FW_INI_LOCATION_DRAM_PATH)
+		return;
+
+	virtual_addr = dma_alloc_coherent(fwrt->trans->dev, size,
+					  &phys_addr, GFP_KERNEL);
+
+	/* TODO: alloc fragments if needed */
+	if (!virtual_addr)
+		IWL_ERR(fwrt, "Failed to allocate debug memory\n");
+
+	if (WARN_ON_ONCE(trans->num_blocks == ARRAY_SIZE(trans->fw_mon)))
+		return;
+
+	trans->fw_mon[trans->num_blocks].block = virtual_addr;
+	trans->fw_mon[trans->num_blocks].physical = phys_addr;
+	trans->fw_mon[trans->num_blocks].size = size;
+	trans->num_blocks++;
+
+	IWL_DEBUG_FW(trans, "Allocated debug block of size %d\n", size);
+
+	/* First block is assigned via registers / context info */
+	if (trans->num_blocks == 1)
+		return;
+
+	cmd->num_frags = cpu_to_le32(1);
+	cmd->fragments[0].address = cpu_to_le64(phys_addr);
+	cmd->fragments[0].size = alloc->size;
+	cmd->allocation_id = alloc->allocation_id;
+	cmd->buffer_location = alloc->buffer_location;
+
+	iwl_trans_send_cmd(trans, &hcmd);
+}
+
+static void iwl_fw_dbg_send_hcmd(struct iwl_fw_runtime *fwrt,
+				 struct iwl_ucode_tlv *tlv)
+{
+	struct iwl_fw_ini_hcmd_tlv *hcmd_tlv = (void *)&tlv->data[0];
+	struct iwl_fw_ini_hcmd *data = &hcmd_tlv->hcmd;
+	u16 len = le32_to_cpu(tlv->length) - sizeof(*hcmd_tlv);
+
+	struct iwl_host_cmd hcmd = {
+		.id = WIDE_ID(data->group, data->id),
+		.len = { len, },
+		.data = { data->data, },
+	};
+
+	iwl_trans_send_cmd(fwrt->trans, &hcmd);
+}
+
+static void iwl_fw_dbg_update_regions(struct iwl_fw_runtime *fwrt,
+				      struct iwl_fw_ini_region_tlv *tlv,
+				      bool ext, enum iwl_fw_ini_apply_point pnt)
+{
+	void *iter = (void *)tlv->region_config;
+	int i, size = le32_to_cpu(tlv->num_regions);
+
+	for (i = 0; i < size; i++) {
+		struct iwl_fw_ini_region_cfg *reg = iter;
+		int id = le32_to_cpu(reg->region_id);
+		struct iwl_fw_ini_active_regs *active;
+
+		if (WARN_ON(id >= ARRAY_SIZE(fwrt->dump.active_regs)))
+			break;
+
+		active = &fwrt->dump.active_regs[id];
+
+		if (ext && active->apply_point == pnt)
+			IWL_WARN(fwrt->trans,
+				 "External region TLV overrides FW default %x\n",
+				 id);
+
+		IWL_DEBUG_FW(fwrt,
+			     "%s: apply point %d, activating region ID %d\n",
+			     __func__, pnt, id);
+
+		active->reg = reg;
+		active->apply_point = pnt;
+
+		if (le32_to_cpu(reg->region_type) !=
+		    IWL_FW_INI_REGION_DRAM_BUFFER)
+			iter += le32_to_cpu(reg->num_regions) * sizeof(__le32);
+
+		iter += sizeof(*reg);
+	}
+}
+
+static void iwl_fw_dbg_update_triggers(struct iwl_fw_runtime *fwrt,
+				       struct iwl_fw_ini_trigger_tlv *tlv,
+				       bool ext,
+				       enum iwl_fw_ini_apply_point apply_point)
+{
+	int i, size = le32_to_cpu(tlv->num_triggers);
+	void *iter = (void *)tlv->trigger_config;
+
+	for (i = 0; i < size; i++) {
+		struct iwl_fw_ini_trigger *trig = iter;
+		struct iwl_fw_ini_active_triggers *active;
+		int id = le32_to_cpu(trig->trigger_id);
+		u32 num;
+
+		if (WARN_ON(id >= ARRAY_SIZE(fwrt->dump.active_trigs)))
+			break;
+
+		active = &fwrt->dump.active_trigs[id];
+
+		if (active->apply_point != apply_point) {
+			active->conf = NULL;
+			active->conf_ext = NULL;
+		}
+
+		num = le32_to_cpu(trig->num_regions);
+
+		if (ext && active->apply_point == apply_point) {
+			num += le32_to_cpu(active->conf->num_regions);
+			if (trig->ignore_default) {
+				active->conf_ext = active->conf;
+				active->conf = trig;
+			} else {
+				active->conf_ext = trig;
+			}
+		} else {
+			active->conf = trig;
+		}
+
+		iter += sizeof(*trig) +
+			le32_to_cpu(trig->num_regions) * sizeof(__le32);
+
+		active->active = num;
+		active->apply_point = apply_point;
+	}
+}
+
+static void _iwl_fw_dbg_apply_point(struct iwl_fw_runtime *fwrt,
+				    struct iwl_apply_point_data *data,
+				    enum iwl_fw_ini_apply_point pnt,
+				    bool ext)
+{
+	void *iter = data->data;
+
+	while (iter && iter < data->data + data->size) {
+		struct iwl_ucode_tlv *tlv = iter;
+		void *ini_tlv = (void *)tlv->data;
+		u32 type = le32_to_cpu(tlv->type);
+
+		switch (type) {
+		case IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION:
+			iwl_fw_dbg_buffer_allocation(fwrt, ini_tlv);
+			break;
+		case IWL_UCODE_TLV_TYPE_HCMD:
+			if (pnt < IWL_FW_INI_APPLY_AFTER_ALIVE) {
+				IWL_ERR(fwrt,
+					"Invalid apply point %x for host command\n",
+					pnt);
+				goto next;
+			}
+			iwl_fw_dbg_send_hcmd(fwrt, tlv);
+			break;
+		case IWL_UCODE_TLV_TYPE_REGIONS:
+			iwl_fw_dbg_update_regions(fwrt, ini_tlv, ext, pnt);
+			break;
+		case IWL_UCODE_TLV_TYPE_TRIGGERS:
+			iwl_fw_dbg_update_triggers(fwrt, ini_tlv, ext, pnt);
+			break;
+		case IWL_UCODE_TLV_TYPE_DEBUG_FLOW:
+			break;
+		default:
+			WARN_ONCE(1, "Invalid TLV %x for apply point\n", type);
+			break;
+		}
+next:
+		iter += sizeof(*tlv) + le32_to_cpu(tlv->length);
+	}
+}
+
+void iwl_fw_dbg_apply_point(struct iwl_fw_runtime *fwrt,
+			    enum iwl_fw_ini_apply_point apply_point)
+{
+	void *data = &fwrt->trans->apply_points[apply_point];
+
+	_iwl_fw_dbg_apply_point(fwrt, data, apply_point, false);
+
+	data = &fwrt->trans->apply_points_ext[apply_point];
+	_iwl_fw_dbg_apply_point(fwrt, data, apply_point, true);
+}
+IWL_EXPORT_SYMBOL(iwl_fw_dbg_apply_point);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index 07403aa29793..6b3c5677c53a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -72,6 +72,7 @@
 #include "file.h"
 #include "error-dump.h"
 #include "api/commands.h"
+#include "api/dbg-tlv.h"
 
 /**
  * struct iwl_fw_dump_desc - describes the dump
@@ -384,4 +385,7 @@ static inline void iwl_fw_resume_timestamp(struct iwl_fw_runtime *fwrt) {}
 void iwl_fw_assert_error_dump(struct iwl_fw_runtime *fwrt);
 void iwl_fw_alive_error_dump(struct iwl_fw_runtime *fwrt);
 void iwl_fw_dbg_collect_sync(struct iwl_fw_runtime *fwrt);
+void iwl_fw_dbg_apply_point(struct iwl_fw_runtime *fwrt,
+			    enum iwl_fw_ini_apply_point apply_point);
+
 #endif  /* __iwl_fw_dbg_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/img.h b/drivers/net/wireless/intel/iwlwifi/fw/img.h
index 54dbbd998abf..12333167ea23 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/img.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/img.h
@@ -65,6 +65,8 @@
 #define __iwl_fw_img_h__
 #include <linux/types.h>
 
+#include "api/dbg-tlv.h"
+
 #include "file.h"
 #include "error-dump.h"
 
@@ -220,6 +222,30 @@ struct iwl_fw_dbg {
 	u32 dump_mask;
 };
 
+/**
+ * struct iwl_fw_ini_active_triggers
+ * @active: is this trigger active
+ * @apply_point: last apply point that updated this trigger
+ * @conf: active trigger
+ * @conf_ext: second trigger, contains extra regions to dump
+ */
+struct iwl_fw_ini_active_triggers {
+	bool active;
+	enum iwl_fw_ini_apply_point apply_point;
+	struct iwl_fw_ini_trigger *conf;
+	struct iwl_fw_ini_trigger *conf_ext;
+};
+
+/**
+ * struct iwl_fw_ini_active_regs
+ * @reg: active region from TLV
+ * @apply_point: apply point where it became active
+ */
+struct iwl_fw_ini_active_regs {
+	struct iwl_fw_ini_region_cfg *reg;
+	enum iwl_fw_ini_apply_point apply_point;
+};
+
 /**
  * struct iwl_fw - variables associated with the firmware
  *
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index 8a139431e7be..886227b7c949 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -64,6 +64,7 @@
 #include "iwl-trans.h"
 #include "img.h"
 #include "fw/api/debug.h"
+#include "fw/api/dbg-tlv.h"
 #include "fw/api/paging.h"
 #include "iwl-eeprom-parse.h"
 
@@ -139,6 +140,8 @@ struct iwl_fw_runtime {
 		/* ts of the beginning of a non-collect fw dbg data period */
 		unsigned long non_collect_ts_start[FW_DBG_TRIGGER_MAX - 1];
 		u32 *d3_debug_data;
+		struct iwl_fw_ini_active_regs active_regs[IWL_FW_INI_MAX_REGION_ID];
+		struct iwl_fw_ini_active_triggers active_trigs[IWL_FW_TRIGGER_ID_NUM];
 	} dump;
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 	struct {
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index 0160662a1749..bc1e4d4bb42d 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -123,6 +123,9 @@ void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data,
 		hdr = (void *)&tlv->data[0];
 		apply = le32_to_cpu(hdr->apply_point);
 
+		IWL_DEBUG_FW(trans, "Read TLV %x, apply point %d\n",
+			     le32_to_cpu(tlv->type), apply);
+
 		if (WARN_ON(apply >= IWL_FW_INI_APPLY_NUM))
 			continue;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 3d455cf5822b..c2531eae5e16 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -680,7 +680,6 @@ enum iwl_plat_pm_mode {
  * enter/exit (in msecs).
  */
 #define IWL_TRANS_IDLE_TIMEOUT 2000
-#define IWL_MAX_DEBUG_ALLOCATIONS	1
 
 /**
  * struct iwl_dram_data
@@ -786,7 +785,7 @@ struct iwl_trans {
 	struct iwl_fw_dbg_trigger_tlv * const *dbg_trigger_tlv;
 	u8 dbg_n_dest_reg;
 	int num_blocks;
-	struct iwl_dram_data fw_mon[IWL_MAX_DEBUG_ALLOCATIONS];
+	struct iwl_dram_data fw_mon[IWL_FW_INI_APPLY_NUM];
 
 	enum iwl_plat_pm_mode system_pm_mode;
 	enum iwl_plat_pm_mode runtime_pm_mode;
-- 
cgit v1.2.3


From f7805b33f9b13a87b1fcf9dfbc3dcbce281a1436 Mon Sep 17 00:00:00 2001
From: Lior Cohen <lior2.cohen@intel.com>
Date: Thu, 3 May 2018 10:17:05 +0300
Subject: iwlwifi: add debugfs file to read fw debug data recording

FW debug data will oneshot read all data available in DRAM
and fill the supplied user buffer. In case the read request
is greater than the new data in DRAM, the driver will write
all data it has and return the buffer immediately.

Signed-off-by: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Signed-off-by: Lior Cohen <lior2.cohen@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.h        |  14 ++
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c       |   2 +
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h     |   5 +
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c        |   3 +
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h |  44 ++++++
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c    | 160 +++++++++++++++++++++
 6 files changed, 228 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index 6b3c5677c53a..ab81ea8b636f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -266,6 +266,9 @@ _iwl_fw_dbg_stop_recording(struct iwl_trans *trans,
 	iwl_write_prph(trans, DBGC_IN_SAMPLE, 0);
 	udelay(100);
 	iwl_write_prph(trans, DBGC_OUT_CTRL, 0);
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	trans->dbg_rec_on = false;
+#endif
 }
 
 static inline void
@@ -296,6 +299,14 @@ _iwl_fw_dbg_restart_recording(struct iwl_trans *trans,
 	}
 }
 
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+static inline void iwl_fw_set_dbg_rec_on(struct iwl_fw_runtime *fwrt)
+{
+	if (fwrt->fw->dbg.dest_tlv && fwrt->cur_fw_img == IWL_UCODE_REGULAR)
+		fwrt->trans->dbg_rec_on = true;
+}
+#endif
+
 static inline void
 iwl_fw_dbg_restart_recording(struct iwl_fw_runtime *fwrt,
 			     struct iwl_fw_dbg_params *params)
@@ -304,6 +315,9 @@ iwl_fw_dbg_restart_recording(struct iwl_fw_runtime *fwrt,
 		_iwl_fw_dbg_restart_recording(fwrt->trans, params);
 	else
 		iwl_fw_dbg_start_stop_hcmd(fwrt, true);
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	iwl_fw_set_dbg_rec_on(fwrt);
+#endif
 }
 
 static inline void iwl_fw_dump_conf_clear(struct iwl_fw_runtime *fwrt)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 7b98125e4eb9..a65ba955783d 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1628,6 +1628,8 @@ void iwl_drv_stop(struct iwl_drv *drv)
 	mutex_unlock(&iwlwifi_opmode_table_mtx);
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
+	drv->trans->ops->debugfs_cleanup(drv->trans);
+
 	debugfs_remove_recursive(drv->dbgfs_drv);
 #endif
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index c2531eae5e16..a7009cd4232d 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -536,6 +536,8 @@ struct iwl_trans_rxq_dma_data {
  * @dump_data: return a vmalloc'ed buffer with debug data, maybe containing last
  *	TX'ed commands and similar. The buffer will be vfree'd by the caller.
  *	Note that the transport must fill in the proper file headers.
+ * @debugfs_cleanup: used in the driver unload flow to make a proper cleanup
+ *	of the trans debugfs
  */
 struct iwl_trans_ops {
 
@@ -605,6 +607,7 @@ struct iwl_trans_ops {
 
 	struct iwl_trans_dump_data *(*dump_data)(struct iwl_trans *trans,
 						 u32 dump_mask);
+	void (*debugfs_cleanup)(struct iwl_trans *trans);
 };
 
 /**
@@ -734,6 +737,7 @@ struct iwl_dram_data {
  * @runtime_pm_mode: the runtime power management mode in use.  This
  *	mode is set during the initialization phase and is not
  *	supposed to change during runtime.
+ * @dbg_rec_on: true iff there is a fw debug recording currently active
  */
 struct iwl_trans {
 	const struct iwl_trans_ops *ops;
@@ -790,6 +794,7 @@ struct iwl_trans {
 	enum iwl_plat_pm_mode system_pm_mode;
 	enum iwl_plat_pm_mode runtime_pm_mode;
 	bool suspending;
+	bool dbg_rec_on;
 
 	/* pointer to trans specific struct */
 	/*Ensure that this pointer will always be aligned to sizeof pointer */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 2cd07247e0a7..263b03b3ea66 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -377,6 +377,9 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 		atomic_set(&mvm->mac80211_queue_stop_count[i], 0);
 
 	set_bit(IWL_MVM_STATUS_FIRMWARE_RUNNING, &mvm->status);
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	iwl_fw_set_dbg_rec_on(&mvm->fwrt);
+#endif
 	clear_bit(IWL_FWRT_STATUS_WAIT_ALIVE, &mvm->fwrt.status);
 
 	return 0;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index f9c4c64dee66..0f816761ca45 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -378,6 +378,23 @@ struct iwl_tso_hdr_page {
 	u8 *pos;
 };
 
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+/**
+ * enum iwl_fw_mon_dbgfs_state - the different states of the monitor_data
+ * debugfs file
+ *
+ * @IWL_FW_MON_DBGFS_STATE_CLOSED: the file is closed.
+ * @IWL_FW_MON_DBGFS_STATE_OPEN: the file is open.
+ * @IWL_FW_MON_DBGFS_STATE_DISABLED: the file is disabled, once this state is
+ *	set the file can no longer be used.
+ */
+enum iwl_fw_mon_dbgfs_state {
+	IWL_FW_MON_DBGFS_STATE_CLOSED,
+	IWL_FW_MON_DBGFS_STATE_OPEN,
+	IWL_FW_MON_DBGFS_STATE_DISABLED,
+};
+#endif
+
 /**
  * enum iwl_shared_irq_flags - level of sharing for irq
  * @IWL_SHARED_IRQ_NON_RX: interrupt vector serves non rx causes.
@@ -414,6 +431,26 @@ struct iwl_self_init_dram {
 	int paging_cnt;
 };
 
+/**
+ * struct cont_rec: continuous recording data structure
+ * @prev_wr_ptr: the last address that was read in monitor_data
+ *	debugfs file
+ * @prev_wrap_cnt: the wrap count that was used during the last read in
+ *	monitor_data debugfs file
+ * @state: the state of monitor_data debugfs file as described
+ *	in &iwl_fw_mon_dbgfs_state enum
+ * @mutex: locked while reading from monitor_data debugfs file
+ */
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+struct cont_rec {
+	u32 prev_wr_ptr;
+	u32 prev_wrap_cnt;
+	u8  state;
+	/* Used to sync monitor_data debugfs file with driver unload flow */
+	struct mutex mutex;
+};
+#endif
+
 /**
  * struct iwl_trans_pcie - PCIe transport specific data
  * @rxq: all the RX queue data
@@ -451,6 +488,9 @@ struct iwl_self_init_dram {
  * @reg_lock: protect hw register access
  * @mutex: to protect stop_device / start_fw / start_hw
  * @cmd_in_flight: true when we have a host command in flight
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+ * @fw_mon_data: fw continuous recording data
+#endif
  * @msix_entries: array of MSI-X entries
  * @msix_enabled: true if managed to enable MSI-X
  * @shared_vec_mask: the type of causes the shared vector handles
@@ -538,6 +578,10 @@ struct iwl_trans_pcie {
 	bool cmd_hold_nic_awake;
 	bool ref_cmd_in_flight;
 
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	struct cont_rec fw_mon_data;
+#endif
+
 	struct msix_entry msix_entries[IWL_MAX_RX_HW_QUEUES];
 	bool msix_enabled;
 	u8 shared_vec_mask;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 231ec8131ee8..166bacc5ea54 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -71,6 +71,7 @@
 #include <linux/vmalloc.h>
 #include <linux/pm_runtime.h>
 #include <linux/module.h>
+#include <linux/wait.h>
 
 #include "iwl-drv.h"
 #include "iwl-trans.h"
@@ -2709,6 +2710,137 @@ static ssize_t iwl_dbgfs_rfkill_write(struct file *file,
 	return count;
 }
 
+static int iwl_dbgfs_monitor_data_open(struct inode *inode,
+				       struct file *file)
+{
+	struct iwl_trans *trans = inode->i_private;
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	if (!trans->dbg_dest_tlv ||
+	    trans->dbg_dest_tlv->monitor_mode != EXTERNAL_MODE) {
+		IWL_ERR(trans, "Debug destination is not set to DRAM\n");
+		return -ENOENT;
+	}
+
+	if (trans_pcie->fw_mon_data.state != IWL_FW_MON_DBGFS_STATE_CLOSED)
+		return -EBUSY;
+
+	trans_pcie->fw_mon_data.state = IWL_FW_MON_DBGFS_STATE_OPEN;
+	return simple_open(inode, file);
+}
+
+static int iwl_dbgfs_monitor_data_release(struct inode *inode,
+					  struct file *file)
+{
+	struct iwl_trans_pcie *trans_pcie =
+		IWL_TRANS_GET_PCIE_TRANS(inode->i_private);
+
+	if (trans_pcie->fw_mon_data.state == IWL_FW_MON_DBGFS_STATE_OPEN)
+		trans_pcie->fw_mon_data.state = IWL_FW_MON_DBGFS_STATE_CLOSED;
+	return 0;
+}
+
+static bool iwl_write_to_user_buf(char __user *user_buf, ssize_t count,
+				  void *buf, ssize_t *size,
+				  ssize_t *bytes_copied)
+{
+	int buf_size_left = count - *bytes_copied;
+
+	buf_size_left = buf_size_left - (buf_size_left % sizeof(u32));
+	if (*size > buf_size_left)
+		*size = buf_size_left;
+
+	*size -= copy_to_user(user_buf, buf, *size);
+	*bytes_copied += *size;
+
+	if (buf_size_left == *size)
+		return true;
+	return false;
+}
+
+static ssize_t iwl_dbgfs_monitor_data_read(struct file *file,
+					   char __user *user_buf,
+					   size_t count, loff_t *ppos)
+{
+	struct iwl_trans *trans = file->private_data;
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	void *cpu_addr = (void *)trans->fw_mon[0].block, *curr_buf;
+	struct cont_rec *data = &trans_pcie->fw_mon_data;
+	u32 write_ptr_addr, wrap_cnt_addr, write_ptr, wrap_cnt;
+	ssize_t size, bytes_copied = 0;
+	bool b_full;
+
+	if (trans->dbg_dest_tlv) {
+		write_ptr_addr =
+			le32_to_cpu(trans->dbg_dest_tlv->write_ptr_reg);
+		wrap_cnt_addr = le32_to_cpu(trans->dbg_dest_tlv->wrap_count);
+	} else {
+		write_ptr_addr = MON_BUFF_WRPTR;
+		wrap_cnt_addr = MON_BUFF_CYCLE_CNT;
+	}
+
+	if (unlikely(!trans->dbg_rec_on))
+		return 0;
+
+	mutex_lock(&data->mutex);
+	if (data->state ==
+	    IWL_FW_MON_DBGFS_STATE_DISABLED) {
+		mutex_unlock(&data->mutex);
+		return 0;
+	}
+
+	/* write_ptr position in bytes rather then DW */
+	write_ptr = iwl_read_prph(trans, write_ptr_addr) * sizeof(u32);
+	wrap_cnt = iwl_read_prph(trans, wrap_cnt_addr);
+
+	if (data->prev_wrap_cnt == wrap_cnt) {
+		size = write_ptr - data->prev_wr_ptr;
+		curr_buf = cpu_addr + data->prev_wr_ptr;
+		b_full = iwl_write_to_user_buf(user_buf, count,
+					       curr_buf, &size,
+					       &bytes_copied);
+		data->prev_wr_ptr += size;
+
+	} else if (data->prev_wrap_cnt == wrap_cnt - 1 &&
+		   write_ptr < data->prev_wr_ptr) {
+		size = trans->fw_mon[0].size - data->prev_wr_ptr;
+		curr_buf = cpu_addr + data->prev_wr_ptr;
+		b_full = iwl_write_to_user_buf(user_buf, count,
+					       curr_buf, &size,
+					       &bytes_copied);
+		data->prev_wr_ptr += size;
+
+		if (!b_full) {
+			size = write_ptr;
+			b_full = iwl_write_to_user_buf(user_buf, count,
+						       cpu_addr, &size,
+						       &bytes_copied);
+			data->prev_wr_ptr = size;
+			data->prev_wrap_cnt++;
+		}
+	} else {
+		if (data->prev_wrap_cnt == wrap_cnt - 1 &&
+		    write_ptr > data->prev_wr_ptr)
+			IWL_WARN(trans,
+				 "write pointer passed previous write pointer, start copying from the beginning\n");
+		else if (!unlikely(data->prev_wrap_cnt == 0 &&
+				   data->prev_wr_ptr == 0))
+			IWL_WARN(trans,
+				 "monitor data is out of sync, start copying from the beginning\n");
+
+		size = write_ptr;
+		b_full = iwl_write_to_user_buf(user_buf, count,
+					       cpu_addr, &size,
+					       &bytes_copied);
+		data->prev_wr_ptr = size;
+		data->prev_wrap_cnt = wrap_cnt;
+	}
+
+	mutex_unlock(&data->mutex);
+
+	return bytes_copied;
+}
+
 DEBUGFS_READ_WRITE_FILE_OPS(interrupt);
 DEBUGFS_READ_FILE_OPS(fh_reg);
 DEBUGFS_READ_FILE_OPS(rx_queue);
@@ -2716,6 +2848,12 @@ DEBUGFS_READ_FILE_OPS(tx_queue);
 DEBUGFS_WRITE_FILE_OPS(csr);
 DEBUGFS_READ_WRITE_FILE_OPS(rfkill);
 
+static const struct file_operations iwl_dbgfs_monitor_data_ops = {
+	.read = iwl_dbgfs_monitor_data_read,
+	.open = iwl_dbgfs_monitor_data_open,
+	.release = iwl_dbgfs_monitor_data_release,
+};
+
 /* Create the debugfs files and directories */
 int iwl_trans_pcie_dbgfs_register(struct iwl_trans *trans)
 {
@@ -2727,12 +2865,23 @@ int iwl_trans_pcie_dbgfs_register(struct iwl_trans *trans)
 	DEBUGFS_ADD_FILE(csr, dir, 0200);
 	DEBUGFS_ADD_FILE(fh_reg, dir, 0400);
 	DEBUGFS_ADD_FILE(rfkill, dir, 0600);
+	DEBUGFS_ADD_FILE(monitor_data, dir, 0400);
 	return 0;
 
 err:
 	IWL_ERR(trans, "failed to create the trans debugfs entry\n");
 	return -ENOMEM;
 }
+
+static void iwl_trans_pcie_debugfs_cleanup(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct cont_rec *data = &trans_pcie->fw_mon_data;
+
+	mutex_lock(&data->mutex);
+	data->state = IWL_FW_MON_DBGFS_STATE_DISABLED;
+	mutex_unlock(&data->mutex);
+}
 #endif /*CONFIG_IWLWIFI_DEBUGFS */
 
 static u32 iwl_trans_pcie_get_cmdlen(struct iwl_trans *trans, void *tfd)
@@ -3211,6 +3360,9 @@ static const struct iwl_trans_ops trans_ops_pcie = {
 
 	.freeze_txq_timer = iwl_trans_pcie_freeze_txq_timer,
 	.block_txq_ptrs = iwl_trans_pcie_block_txq_ptrs,
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	.debugfs_cleanup = iwl_trans_pcie_debugfs_cleanup,
+#endif
 };
 
 static const struct iwl_trans_ops trans_ops_pcie_gen2 = {
@@ -3230,6 +3382,9 @@ static const struct iwl_trans_ops trans_ops_pcie_gen2 = {
 	.txq_free = iwl_trans_pcie_dyn_txq_free,
 	.wait_txq_empty = iwl_trans_pcie_wait_txq_empty,
 	.rxq_dma_data = iwl_trans_pcie_rxq_dma_data,
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	.debugfs_cleanup = iwl_trans_pcie_debugfs_cleanup,
+#endif
 };
 
 struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
@@ -3481,6 +3636,11 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	trans->runtime_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
 #endif /* CONFIG_IWLWIFI_PCIE_RTPM */
 
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	trans_pcie->fw_mon_data.state = IWL_FW_MON_DBGFS_STATE_CLOSED;
+	mutex_init(&trans_pcie->fw_mon_data.mutex);
+#endif
+
 	return trans;
 
 out_free_ict:
-- 
cgit v1.2.3


From a024016fafc4a350db4364e4b6af34d8fd06ea9a Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 13 Aug 2018 08:21:10 +0300
Subject: iwlwifi: fw: support API change to debug TLVs

A new field was added. Since the code isn't operational (yet) no
need to worry about backward compatibility.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
index 82f3c9bbd9b1..ab82b7a67967 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
@@ -180,6 +180,7 @@ struct iwl_fw_ini_region_tlv {
  * @occurrences: max amount of times to be fired
  * @ignore_consec: ignore consecutive triggers, in usec
  * @force_restart: force FW restart
+ * @multi_dut: initiate debug dump data on several DUTs
  * @trigger_data: generic data to be utilized per trigger
  * @num_regions: number of dump regions defined for this trigger
  * @data: region IDs
@@ -191,6 +192,7 @@ struct iwl_fw_ini_trigger {
 	__le32 occurrences;
 	__le32 ignore_consec;
 	__le32 force_restart;
+	__le32 multi_dut;
 	__le32 trigger_data;
 	__le32 num_regions;
 	__le32 data[];
-- 
cgit v1.2.3


From 3b5ee8dd8bb1a0f820eb5c85e31f92a2897bfa3d Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Wed, 8 Aug 2018 13:20:45 +0300
Subject: iwlwifi: mvm: set MAC_FILTER_IN_11AX in AP mode

In AP mode, if AP supports 11ax, add the MAC_FILTER_IN_11AX
flag in MAC_CTXT command (needed for various 11ax stuff).

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 990ebf89f342..e049d34a3553 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1194,6 +1194,9 @@ static void iwl_mvm_mac_ctxt_cmd_fill_ap(struct iwl_mvm *mvm,
 		IWL_DEBUG_HC(mvm, "No need to receive beacons\n");
 	}
 
+	if (vif->bss_conf.he_support && !iwlwifi_mod_params.disable_11ax)
+		cmd->filter_flags |= cpu_to_le32(MAC_FILTER_IN_11AX);
+
 	ctxt_ap->bi = cpu_to_le32(vif->bss_conf.beacon_int);
 	ctxt_ap->dtim_interval = cpu_to_le32(vif->bss_conf.beacon_int *
 					     vif->bss_conf.dtim_period);
-- 
cgit v1.2.3


From 02221a81887a9ed83cd4b355e0342eb241d31dea Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Wed, 8 Aug 2018 13:24:50 +0300
Subject: iwlwifi: mvm: send the STA_HE_CTXT command in AP mode

In AP mode, if AP supports HE (and the STA), send the
STA_HE_CTXT command.

This is needed mainly for PPE (packet extension) params.

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 55b965629e33..64be5fa7eda3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -2968,6 +2968,9 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw,
 		if (vif->type == NL80211_IFTYPE_AP) {
 			mvmvif->ap_assoc_sta_count++;
 			iwl_mvm_mac_ctxt_changed(mvm, vif, false, NULL);
+			if (vif->bss_conf.he_support &&
+			    !iwlwifi_mod_params.disable_11ax)
+				iwl_mvm_cfg_he_sta(mvm, vif, mvm_sta->sta_id);
 		}
 
 		iwl_mvm_rs_rate_init(mvm, sta, mvmvif->phy_ctxt->channel->band,
-- 
cgit v1.2.3


From 520229e4b02dc4f5241a251a569fe0691a2c2e2c Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Wed, 18 Jul 2018 10:29:53 +0300
Subject: iwlwifi: mvm: set HW capability VHT_EXT_NSS_BW

Enable the VHT extended NSS BW feature in iwlwifi/mvm.

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 64be5fa7eda3..6fe48cc31071 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -419,6 +419,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	ieee80211_hw_set(hw, SUPPORTS_AMSDU_IN_AMPDU);
 	ieee80211_hw_set(hw, NEEDS_UNIQUE_STA_ADDR);
 	ieee80211_hw_set(hw, DEAUTH_NEED_MGD_TX_PREP);
+	ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW);
 
 	if (iwl_mvm_has_tlc_offload(mvm)) {
 		ieee80211_hw_set(hw, TX_AMPDU_SETUP_IN_HW);
-- 
cgit v1.2.3


From 24d476db6dfb0f85130e348ca1bbd14afb73a8be Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Tue, 20 Nov 2018 15:17:01 -0800
Subject: net: bcmgenet: remove HFB_CTRL access

Commit c5a54bbcecec ("net: bcmgenet: abort suspend on error")
mistakenly introduced register accesses that should not occur
in bcmgenet_wol_power_up_cfg().

Fixes: c5a54bbcecec ("net: bcmgenet: abort suspend on error")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index b3596e0ee47b..57582efa362d 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -191,10 +191,6 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	reg &= ~MPD_EN;
 	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 
-	reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-	reg &= ~(RBUF_HFB_EN | RBUF_ACPI_EN);
-	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
-
 	/* Disable CRC Forward */
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
 	reg &= ~CMD_CRC_FWD;
-- 
cgit v1.2.3


From 02d805dc5fe34358b8a5e9fc141031a40cd496ed Mon Sep 17 00:00:00 2001
From: Santosh Rastapur <santosh@chelsio.com>
Date: Wed, 21 Nov 2018 13:40:24 +0530
Subject: cxgb4: use new fw interface to get the VIN and smt index

If the fw supports returning VIN/VIVLD in FW_VI_CMD save it
in port_info structure else retrieve these from viid and save
them  in port_info structure. Do the same for smt_idx from
FW_VI_MAC_CMD

Signed-off-by: Santosh Rastapur <santosh@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/crypto/chelsio/chtls/chtls_cm.c         |  3 +-
 drivers/infiniband/hw/cxgb4/cm.c                |  6 +--
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h      | 12 ++++-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 58 ++++++++++++-------------
 drivers/net/ethernet/chelsio/cxgb4/l2t.c        | 13 +++---
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c      | 46 ++++++++++++++++++--
 drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h   | 20 +++++++++
 drivers/scsi/cxgbi/cxgb4i/cxgb4i.c              |  3 +-
 drivers/target/iscsi/cxgbit/cxgbit_cm.c         |  8 ++--
 9 files changed, 114 insertions(+), 55 deletions(-)

diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c
index 20209e29f814..228b91b7d6b5 100644
--- a/drivers/crypto/chelsio/chtls/chtls_cm.c
+++ b/drivers/crypto/chelsio/chtls/chtls_cm.c
@@ -1074,8 +1074,7 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 	csk->txq_idx = (rxq_idx < cdev->lldi->ntxq) ? rxq_idx :
 			port_id * step;
 	csk->sndbuf = newsk->sk_sndbuf;
-	csk->smac_idx = cxgb4_tp_smt_idx(cdev->lldi->adapter_type,
-					 cxgb4_port_viid(ndev));
+	csk->smac_idx = ((struct port_info *)netdev_priv(ndev))->smt_idx;
 	tp->rcv_wnd = select_rcv_wnd(csk);
 	RCV_WSCALE(tp) = select_rcv_wscale(tcp_full_space(newsk),
 					   WSCALE_OK(tp),
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 8ed01e07c463..97ecc8c684f5 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2058,8 +2058,7 @@ static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip,
 		}
 		ep->mtu = pdev->mtu;
 		ep->tx_chan = cxgb4_port_chan(pdev);
-		ep->smac_idx = cxgb4_tp_smt_idx(adapter_type,
-						cxgb4_port_viid(pdev));
+		ep->smac_idx = ((struct port_info *)netdev_priv(pdev))->smt_idx;
 		step = cdev->rdev.lldi.ntxq /
 			cdev->rdev.lldi.nchan;
 		ep->txq_idx = cxgb4_port_idx(pdev) * step;
@@ -2078,8 +2077,7 @@ static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip,
 			goto out;
 		ep->mtu = dst_mtu(dst);
 		ep->tx_chan = cxgb4_port_chan(pdev);
-		ep->smac_idx = cxgb4_tp_smt_idx(adapter_type,
-						cxgb4_port_viid(pdev));
+		ep->smac_idx = ((struct port_info *)netdev_priv(pdev))->smt_idx;
 		step = cdev->rdev.lldi.ntxq /
 			cdev->rdev.lldi.nchan;
 		ep->txq_idx = cxgb4_port_idx(pdev) * step;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index b16f4b3ef4c5..2d1ca920601e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -404,6 +404,7 @@ struct adapter_params {
 	bool fr_nsmr_tpte_wr_support;	  /* FW support for FR_NSMR_TPTE_WR */
 	u8 fw_caps_support;		/* 32-bit Port Capabilities */
 	bool filter2_wr_support;	/* FW support for FILTER2_WR */
+	unsigned int viid_smt_extn_support:1; /* FW returns vin and smt index */
 
 	/* MPS Buffer Group Map[per Port].  Bit i is set if buffer group i is
 	 * used by the Port
@@ -592,6 +593,13 @@ struct port_info {
 	bool ptp_enable;
 	struct sched_table *sched_tbl;
 	u32 eth_flags;
+
+	/* viid and smt fields either returned by fw
+	 * or decoded by parsing viid by driver.
+	 */
+	u8 vin;
+	u8 vivld;
+	u8 smt_idx;
 };
 
 struct dentry;
@@ -1757,7 +1765,7 @@ int t4_cfg_pfvf(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		unsigned int nexact, unsigned int rcaps, unsigned int wxcaps);
 int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 		unsigned int pf, unsigned int vf, unsigned int nmac, u8 *mac,
-		unsigned int *rss_size);
+		unsigned int *rss_size, u8 *vivld, u8 *vin);
 int t4_free_vi(struct adapter *adap, unsigned int mbox,
 	       unsigned int pf, unsigned int vf,
 	       unsigned int viid);
@@ -1783,7 +1791,7 @@ int t4_free_mac_filt(struct adapter *adap, unsigned int mbox,
 		     unsigned int viid, unsigned int naddr,
 		     const u8 **addr, bool sleep_ok);
 int t4_change_mac(struct adapter *adap, unsigned int mbox, unsigned int viid,
-		  int idx, const u8 *addr, bool persist, bool add_smt);
+		  int idx, const u8 *addr, bool persist, u8 *smt_idx);
 int t4_set_addr_hash(struct adapter *adap, unsigned int mbox, unsigned int viid,
 		     bool ucast, u64 vec, bool sleep_ok);
 int t4_enable_vi_params(struct adapter *adap, unsigned int mbox,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 4fbe04d5f207..7f76ad9e1ad6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -453,7 +453,7 @@ static int link_start(struct net_device *dev)
 	if (ret == 0) {
 		ret = t4_change_mac(pi->adapter, mb, pi->viid,
 				    pi->xact_addr_filt, dev->dev_addr, true,
-				    true);
+				    &pi->smt_idx);
 		if (ret >= 0) {
 			pi->xact_addr_filt = ret;
 			ret = 0;
@@ -1584,28 +1584,6 @@ unsigned int cxgb4_best_aligned_mtu(const unsigned short *mtus,
 }
 EXPORT_SYMBOL(cxgb4_best_aligned_mtu);
 
-/**
- *	cxgb4_tp_smt_idx - Get the Source Mac Table index for this VI
- *	@chip: chip type
- *	@viid: VI id of the given port
- *
- *	Return the SMT index for this VI.
- */
-unsigned int cxgb4_tp_smt_idx(enum chip_type chip, unsigned int viid)
-{
-	/* In T4/T5, SMT contains 256 SMAC entries organized in
-	 * 128 rows of 2 entries each.
-	 * In T6, SMT contains 256 SMAC entries in 256 rows.
-	 * TODO: The below code needs to be updated when we add support
-	 * for 256 VFs.
-	 */
-	if (CHELSIO_CHIP_VERSION(chip) <= CHELSIO_T5)
-		return ((viid & 0x7f) << 1);
-	else
-		return (viid & 0x7f);
-}
-EXPORT_SYMBOL(cxgb4_tp_smt_idx);
-
 /**
  *	cxgb4_port_chan - get the HW channel of a port
  *	@dev: the net device for the port
@@ -2862,7 +2840,8 @@ static int cxgb_set_mac_addr(struct net_device *dev, void *p)
 		return -EADDRNOTAVAIL;
 
 	ret = t4_change_mac(pi->adapter, pi->adapter->pf, pi->viid,
-			    pi->xact_addr_filt, addr->sa_data, true, true);
+			    pi->xact_addr_filt, addr->sa_data, true,
+			    &pi->smt_idx);
 	if (ret < 0)
 		return ret;
 
@@ -4466,6 +4445,15 @@ static int adap_init0(struct adapter *adap)
 		adap->params.filter2_wr_support = (ret == 0 && val[0] != 0);
 	}
 
+	/* Check if FW supports returning vin and smt index.
+	 * If this is not supported, driver will interpret
+	 * these values from viid.
+	 */
+	params[0] = FW_PARAM_DEV(OPAQUE_VIID_SMT_EXTN);
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
+			      1, params, val);
+	adap->params.viid_smt_extn_support = (ret == 0 && val[0] != 0);
+
 	/*
 	 * Get device capabilities so we can determine what resources we need
 	 * to manage.
@@ -4776,14 +4764,26 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
 		return PCI_ERS_RESULT_DISCONNECT;
 
 	for_each_port(adap, i) {
-		struct port_info *p = adap2pinfo(adap, i);
+		struct port_info *pi = adap2pinfo(adap, i);
+		u8 vivld = 0, vin = 0;
 
-		ret = t4_alloc_vi(adap, adap->mbox, p->tx_chan, adap->pf, 0, 1,
-				  NULL, NULL);
+		ret = t4_alloc_vi(adap, adap->mbox, pi->tx_chan, adap->pf, 0, 1,
+				  NULL, NULL, &vivld, &vin);
 		if (ret < 0)
 			return PCI_ERS_RESULT_DISCONNECT;
-		p->viid = ret;
-		p->xact_addr_filt = -1;
+		pi->viid = ret;
+		pi->xact_addr_filt = -1;
+		/* If fw supports returning the VIN as part of FW_VI_CMD,
+		 * save the returned values.
+		 */
+		if (adap->params.viid_smt_extn_support) {
+			pi->vivld = vivld;
+			pi->vin = vin;
+		} else {
+			/* Retrieve the values from VIID */
+			pi->vivld = FW_VIID_VIVLD_G(pi->viid);
+			pi->vin = FW_VIID_VIN_G(pi->viid);
+		}
 	}
 
 	t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 99022c0898b5..4852febbfec3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -495,14 +495,11 @@ u64 cxgb4_select_ntuple(struct net_device *dev,
 		ntuple |= (u64)IPPROTO_TCP << tp->protocol_shift;
 
 	if (tp->vnic_shift >= 0 && (tp->ingress_config & VNIC_F)) {
-		u32 viid = cxgb4_port_viid(dev);
-		u32 vf = FW_VIID_VIN_G(viid);
-		u32 pf = FW_VIID_PFN_G(viid);
-		u32 vld = FW_VIID_VIVLD_G(viid);
-
-		ntuple |= (u64)(FT_VNID_ID_VF_V(vf) |
-				FT_VNID_ID_PF_V(pf) |
-				FT_VNID_ID_VLD_V(vld)) << tp->vnic_shift;
+		struct port_info *pi = (struct port_info *)netdev_priv(dev);
+
+		ntuple |= (u64)(FT_VNID_ID_VF_V(pi->vin) |
+				FT_VNID_ID_PF_V(adap->pf) |
+				FT_VNID_ID_VLD_V(pi->vivld)) << tp->vnic_shift;
 	}
 
 	return ntuple;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index fc6a08789835..4cb261d5a077 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -7477,7 +7477,7 @@ int t4_cfg_pfvf(struct adapter *adap, unsigned int mbox, unsigned int pf,
  */
 int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 		unsigned int pf, unsigned int vf, unsigned int nmac, u8 *mac,
-		unsigned int *rss_size)
+		unsigned int *rss_size, u8 *vivld, u8 *vin)
 {
 	int ret;
 	struct fw_vi_cmd c;
@@ -7512,6 +7512,13 @@ int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 	}
 	if (rss_size)
 		*rss_size = FW_VI_CMD_RSSSIZE_G(be16_to_cpu(c.rsssize_pkd));
+
+	if (vivld)
+		*vivld = FW_VI_CMD_VFVLD_G(be32_to_cpu(c.alloc_to_len16));
+
+	if (vin)
+		*vin = FW_VI_CMD_VIN_G(be32_to_cpu(c.alloc_to_len16));
+
 	return FW_VI_CMD_VIID_G(be16_to_cpu(c.type_viid));
 }
 
@@ -7969,7 +7976,7 @@ int t4_free_mac_filt(struct adapter *adap, unsigned int mbox,
  *	MAC value.
  */
 int t4_change_mac(struct adapter *adap, unsigned int mbox, unsigned int viid,
-		  int idx, const u8 *addr, bool persist, bool add_smt)
+		  int idx, const u8 *addr, bool persist, u8 *smt_idx)
 {
 	int ret, mode;
 	struct fw_vi_mac_cmd c;
@@ -7978,7 +7985,7 @@ int t4_change_mac(struct adapter *adap, unsigned int mbox, unsigned int viid,
 
 	if (idx < 0)                             /* new allocation */
 		idx = persist ? FW_VI_MAC_ADD_PERSIST_MAC : FW_VI_MAC_ADD_MAC;
-	mode = add_smt ? FW_VI_MAC_SMT_AND_MPSTCAM : FW_VI_MAC_MPS_TCAM_ENTRY;
+	mode = smt_idx ? FW_VI_MAC_SMT_AND_MPSTCAM : FW_VI_MAC_MPS_TCAM_ENTRY;
 
 	memset(&c, 0, sizeof(c));
 	c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_MAC_CMD) |
@@ -7995,6 +8002,23 @@ int t4_change_mac(struct adapter *adap, unsigned int mbox, unsigned int viid,
 		ret = FW_VI_MAC_CMD_IDX_G(be16_to_cpu(p->valid_to_idx));
 		if (ret >= max_mac_addr)
 			ret = -ENOMEM;
+		if (smt_idx) {
+			if (adap->params.viid_smt_extn_support) {
+				*smt_idx = FW_VI_MAC_CMD_SMTID_G
+						    (be32_to_cpu(c.op_to_viid));
+			} else {
+				/* In T4/T5, SMT contains 256 SMAC entries
+				 * organized in 128 rows of 2 entries each.
+				 * In T6, SMT contains 256 SMAC entries in
+				 * 256 rows.
+				 */
+				if (CHELSIO_CHIP_VERSION(adap->params.chip) <=
+								     CHELSIO_T5)
+					*smt_idx = (viid & FW_VIID_VIN_M) << 1;
+				else
+					*smt_idx = (viid & FW_VIID_VIN_M);
+			}
+		}
 	}
 	return ret;
 }
@@ -9363,6 +9387,7 @@ int t4_init_portinfo(struct port_info *pi, int mbox,
 	enum fw_port_type port_type;
 	int mdio_addr;
 	fw_port_cap32_t pcaps, acaps;
+	u8 vivld = 0, vin = 0;
 	int ret;
 
 	/* If we haven't yet determined whether we're talking to Firmware
@@ -9417,7 +9442,8 @@ int t4_init_portinfo(struct port_info *pi, int mbox,
 		acaps = be32_to_cpu(cmd.u.info32.acaps32);
 	}
 
-	ret = t4_alloc_vi(pi->adapter, mbox, port, pf, vf, 1, mac, &rss_size);
+	ret = t4_alloc_vi(pi->adapter, mbox, port, pf, vf, 1, mac, &rss_size,
+			  &vivld, &vin);
 	if (ret < 0)
 		return ret;
 
@@ -9426,6 +9452,18 @@ int t4_init_portinfo(struct port_info *pi, int mbox,
 	pi->lport = port;
 	pi->rss_size = rss_size;
 
+	/* If fw supports returning the VIN as part of FW_VI_CMD,
+	 * save the returned values.
+	 */
+	if (adapter->params.viid_smt_extn_support) {
+		pi->vivld = vivld;
+		pi->vin = vin;
+	} else {
+		/* Retrieve the values from VIID */
+		pi->vivld = FW_VIID_VIVLD_G(pi->viid);
+		pi->vin =  FW_VIID_VIN_G(pi->viid);
+	}
+
 	pi->port_type = port_type;
 	pi->mdio_addr = mdio_addr;
 	pi->mod_type = FW_PORT_MOD_TYPE_NA;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index 57584ab32043..1d9b3e1e5f94 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -1253,6 +1253,7 @@ enum fw_params_param_dev {
 	FW_PARAMS_PARAM_DEV_HMA_SIZE	= 0x20,
 	FW_PARAMS_PARAM_DEV_RDMA_WRITE_WITH_IMM = 0x21,
 	FW_PARAMS_PARAM_DEV_RI_WRITE_CMPL_WR    = 0x24,
+	FW_PARAMS_PARAM_DEV_OPAQUE_VIID_SMT_EXTN = 0x27,
 };
 
 /*
@@ -2109,6 +2110,19 @@ struct fw_vi_cmd {
 #define FW_VI_CMD_FREE_V(x)	((x) << FW_VI_CMD_FREE_S)
 #define FW_VI_CMD_FREE_F	FW_VI_CMD_FREE_V(1U)
 
+#define FW_VI_CMD_VFVLD_S	24
+#define FW_VI_CMD_VFVLD_M	0x1
+#define FW_VI_CMD_VFVLD_V(x)	((x) << FW_VI_CMD_VFVLD_S)
+#define FW_VI_CMD_VFVLD_G(x)	\
+	(((x) >> FW_VI_CMD_VFVLD_S) & FW_VI_CMD_VFVLD_M)
+#define FW_VI_CMD_VFVLD_F	FW_VI_CMD_VFVLD_V(1U)
+
+#define FW_VI_CMD_VIN_S		16
+#define FW_VI_CMD_VIN_M		0xff
+#define FW_VI_CMD_VIN_V(x)	((x) << FW_VI_CMD_VIN_S)
+#define FW_VI_CMD_VIN_G(x)	\
+	(((x) >> FW_VI_CMD_VIN_S) & FW_VI_CMD_VIN_M)
+
 #define FW_VI_CMD_VIID_S	0
 #define FW_VI_CMD_VIID_M	0xfff
 #define FW_VI_CMD_VIID_V(x)	((x) << FW_VI_CMD_VIID_S)
@@ -2182,6 +2196,12 @@ struct fw_vi_mac_cmd {
 	} u;
 };
 
+#define FW_VI_MAC_CMD_SMTID_S		12
+#define FW_VI_MAC_CMD_SMTID_M		0xff
+#define FW_VI_MAC_CMD_SMTID_V(x)	((x) << FW_VI_MAC_CMD_SMTID_S)
+#define FW_VI_MAC_CMD_SMTID_G(x)	\
+	(((x) >> FW_VI_MAC_CMD_SMTID_S) & FW_VI_MAC_CMD_SMTID_M)
+
 #define FW_VI_MAC_CMD_VIID_S	0
 #define FW_VI_MAC_CMD_VIID_V(x)	((x) << FW_VI_MAC_CMD_VIID_S)
 
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index 064ef5735182..907dd8792a0a 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -1767,8 +1767,7 @@ static int init_act_open(struct cxgbi_sock *csk)
 		csk->mtu = dst_mtu(csk->dst);
 	cxgb4_best_mtu(lldi->mtus, csk->mtu, &csk->mss_idx);
 	csk->tx_chan = cxgb4_port_chan(ndev);
-	csk->smac_idx = cxgb4_tp_smt_idx(lldi->adapter_type,
-					 cxgb4_port_viid(ndev));
+	csk->smac_idx = ((struct port_info *)netdev_priv(ndev))->smt_idx;
 	step = lldi->ntxq / lldi->nchan;
 	csk->txq_idx = cxgb4_port_idx(ndev) * step;
 	step = lldi->nrxq / lldi->nchan;
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
index 71888b979ab5..0376d7328f25 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
@@ -932,8 +932,8 @@ cxgbit_offload_init(struct cxgbit_sock *csk, int iptype, __u8 *peer_ip,
 			goto out;
 		csk->mtu = ndev->mtu;
 		csk->tx_chan = cxgb4_port_chan(ndev);
-		csk->smac_idx = cxgb4_tp_smt_idx(cdev->lldi.adapter_type,
-						 cxgb4_port_viid(ndev));
+		csk->smac_idx =
+			       ((struct port_info *)netdev_priv(ndev))->smt_idx;
 		step = cdev->lldi.ntxq /
 			cdev->lldi.nchan;
 		csk->txq_idx = cxgb4_port_idx(ndev) * step;
@@ -968,8 +968,8 @@ cxgbit_offload_init(struct cxgbit_sock *csk, int iptype, __u8 *peer_ip,
 		port_id = cxgb4_port_idx(ndev);
 		csk->mtu = dst_mtu(dst);
 		csk->tx_chan = cxgb4_port_chan(ndev);
-		csk->smac_idx = cxgb4_tp_smt_idx(cdev->lldi.adapter_type,
-						 cxgb4_port_viid(ndev));
+		csk->smac_idx =
+			       ((struct port_info *)netdev_priv(ndev))->smt_idx;
 		step = cdev->lldi.ntxq /
 			cdev->lldi.nports;
 		csk->txq_idx = (port_id * step) +
-- 
cgit v1.2.3


From ebc227fd91f26406840543074c2e7a55700a5644 Mon Sep 17 00:00:00 2001
From: Magnus Damm <damm+renesas@opensource.se>
Date: Wed, 21 Nov 2018 20:21:17 +0900
Subject: ravb: Do not announce HDX as supported

According to the data sheet the Ethernet-AVB hardware in R-Car Gen3
and R-Car Gen2 SoCs do not support half duplex operation. So update
the driver to mark 100Mbit and 1Gbps HDX as unsupported.

Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper")
Signed-off-by: Magnus Damm <damm+renesas@opensource.se>
Reviewed-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index defed0d0c51d..24ad493ec136 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1088,6 +1088,10 @@ static int ravb_phy_init(struct net_device *ndev)
 	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_Pause_BIT);
 	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_Asym_Pause_BIT);
 
+	/* Half Duplex is not supported */
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT);
+
 	phy_attached_info(phydev);
 
 	return 0;
-- 
cgit v1.2.3


From 08b43857804dd0eca48f5c5a84885cf0079586e0 Mon Sep 17 00:00:00 2001
From: Magnus Damm <damm+renesas@opensource.se>
Date: Wed, 21 Nov 2018 20:21:26 +0900
Subject: ravb: Clean up duplex handling

Since only full-duplex operation is supported by the
hardware, remove duplex handling code and keep the
register setting of ECMR.DM fixed at 1.

This updates the driver implementation to follow the
data sheet text "This bit should always be set to 1."

Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper")
Signed-off-by: Magnus Damm <damm+renesas@opensource.se>
Reviewed-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb.h      |  1 -
 drivers/net/ethernet/renesas/ravb_main.c | 19 +------------------
 2 files changed, 1 insertion(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h
index 1c6e4df94f01..ac9195add811 100644
--- a/drivers/net/ethernet/renesas/ravb.h
+++ b/drivers/net/ethernet/renesas/ravb.h
@@ -1032,7 +1032,6 @@ struct ravb_private {
 	phy_interface_t phy_interface;
 	int msg_enable;
 	int speed;
-	int duplex;
 	int emac_irq;
 	enum ravb_chip_id chip_id;
 	int rx_irqs[NUM_RX_QUEUE];
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 24ad493ec136..ffc1ada4e6da 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -82,13 +82,6 @@ static int ravb_config(struct net_device *ndev)
 	return error;
 }
 
-static void ravb_set_duplex(struct net_device *ndev)
-{
-	struct ravb_private *priv = netdev_priv(ndev);
-
-	ravb_modify(ndev, ECMR, ECMR_DM, priv->duplex ? ECMR_DM : 0);
-}
-
 static void ravb_set_rate(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
@@ -406,13 +399,11 @@ error:
 /* E-MAC init function */
 static void ravb_emac_init(struct net_device *ndev)
 {
-	struct ravb_private *priv = netdev_priv(ndev);
-
 	/* Receive frame limit set register */
 	ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR);
 
 	/* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */
-	ravb_write(ndev, ECMR_ZPF | (priv->duplex ? ECMR_DM : 0) |
+	ravb_write(ndev, ECMR_ZPF | ECMR_DM |
 		   (ndev->features & NETIF_F_RXCSUM ? ECMR_RCSC : 0) |
 		   ECMR_TE | ECMR_RE, ECMR);
 
@@ -995,12 +986,6 @@ static void ravb_adjust_link(struct net_device *ndev)
 		ravb_rcv_snd_disable(ndev);
 
 	if (phydev->link) {
-		if (phydev->duplex != priv->duplex) {
-			new_state = true;
-			priv->duplex = phydev->duplex;
-			ravb_set_duplex(ndev);
-		}
-
 		if (phydev->speed != priv->speed) {
 			new_state = true;
 			priv->speed = phydev->speed;
@@ -1015,7 +1000,6 @@ static void ravb_adjust_link(struct net_device *ndev)
 		new_state = true;
 		priv->link = 0;
 		priv->speed = 0;
-		priv->duplex = -1;
 	}
 
 	/* Enable TX and RX right over here, if E-MAC change is ignored */
@@ -1045,7 +1029,6 @@ static int ravb_phy_init(struct net_device *ndev)
 
 	priv->link = 0;
 	priv->speed = 0;
-	priv->duplex = -1;
 
 	/* Try connecting to PHY */
 	pn = of_parse_phandle(np, "phy-handle", 0);
-- 
cgit v1.2.3


From 830b61ba4ee2b7a33cac160d55275513b1ba4eea Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@nxp.com>
Date: Wed, 21 Nov 2018 13:41:07 +0200
Subject: soc: fsl: qbman: read ithresh from HW

Read the DQRR interrupt threshold directly from the hardware.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: Roy Pledge <roy.pledge@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/soc/fsl/qbman/qman.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index 5ce24718c2fd..ce7c03052e33 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -1025,7 +1025,7 @@ EXPORT_SYMBOL(qman_dqrr_set_ithresh);
 void qman_dqrr_get_ithresh(struct qman_portal *portal, u8 *ithresh)
 {
 	if (portal && ithresh)
-		*ithresh = portal->p.dqrr.ithresh;
+		*ithresh = qm_in(&portal->p, QM_REG_DQRR_ITR);
 }
 EXPORT_SYMBOL(qman_dqrr_get_ithresh);
 
-- 
cgit v1.2.3


From 5c664ace8cdfd947d293b97871a4f1e4bedca5b9 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@nxp.com>
Date: Wed, 21 Nov 2018 13:41:08 +0200
Subject: soc/qman: add return value to interrupt coalesce changing APIs

Check that the values received by the portal interrupt coalesce
change APIs are in range.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: Roy Pledge <roy.pledge@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/soc/fsl/qbman/qman.c | 33 ++++++++++++++++++++++++++-------
 include/soc/fsl/qman.h       |  8 ++++++--
 2 files changed, 32 insertions(+), 9 deletions(-)

diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index ce7c03052e33..52c153cd795a 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -36,6 +36,8 @@
 #define MAX_IRQNAME	16	/* big enough for "QMan portal %d" */
 #define QMAN_POLL_LIMIT 32
 #define QMAN_PIRQ_DQRR_ITHRESH 12
+#define QMAN_DQRR_IT_MAX 15
+#define QMAN_ITP_MAX 0xFFF
 #define QMAN_PIRQ_MR_ITHRESH 4
 #define QMAN_PIRQ_IPERIOD 100
 
@@ -727,9 +729,15 @@ static inline void qm_dqrr_vdqcr_set(struct qm_portal *portal, u32 vdqcr)
 	qm_out(portal, QM_REG_DQRR_VDQCR, vdqcr);
 }
 
-static inline void qm_dqrr_set_ithresh(struct qm_portal *portal, u8 ithresh)
+static inline int qm_dqrr_set_ithresh(struct qm_portal *portal, u8 ithresh)
 {
+
+	if (ithresh > QMAN_DQRR_IT_MAX)
+		return -EINVAL;
+
 	qm_out(portal, QM_REG_DQRR_ITR, ithresh);
+
+	return 0;
 }
 
 /* --- MR API --- */
@@ -1012,13 +1020,20 @@ static inline void put_affine_portal(void)
 
 static struct workqueue_struct *qm_portal_wq;
 
-void qman_dqrr_set_ithresh(struct qman_portal *portal, u8 ithresh)
+int qman_dqrr_set_ithresh(struct qman_portal *portal, u8 ithresh)
 {
+	int res;
+
 	if (!portal)
-		return;
+		return -EINVAL;
+
+	res = qm_dqrr_set_ithresh(&portal->p, ithresh);
+	if (res)
+		return res;
 
-	qm_dqrr_set_ithresh(&portal->p, ithresh);
 	portal->p.dqrr.ithresh = ithresh;
+
+	return 0;
 }
 EXPORT_SYMBOL(qman_dqrr_set_ithresh);
 
@@ -1036,10 +1051,14 @@ void qman_portal_get_iperiod(struct qman_portal *portal, u32 *iperiod)
 }
 EXPORT_SYMBOL(qman_portal_get_iperiod);
 
-void qman_portal_set_iperiod(struct qman_portal *portal, u32 iperiod)
+int qman_portal_set_iperiod(struct qman_portal *portal, u32 iperiod)
 {
-	if (portal)
-		qm_out(&portal->p, QM_REG_ITPR, iperiod);
+	if (!portal || iperiod > QMAN_ITP_MAX)
+		return -EINVAL;
+
+	qm_out(&portal->p, QM_REG_ITPR, iperiod);
+
+	return 0;
 }
 EXPORT_SYMBOL(qman_portal_set_iperiod);
 
diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h
index 56877660d5ba..5cc7af06c1ba 100644
--- a/include/soc/fsl/qman.h
+++ b/include/soc/fsl/qman.h
@@ -1205,8 +1205,10 @@ void qman_dqrr_get_ithresh(struct qman_portal *portal, u8 *ithresh);
  * qman_dqrr_set_ithresh - Set coalesce interrupt threshold
  * @portal: portal to set the new value on
  * @ithresh: new threshold value
+ *
+ * Returns 0 on success, or a negative error code.
  */
-void qman_dqrr_set_ithresh(struct qman_portal *portal, u8 ithresh);
+int qman_dqrr_set_ithresh(struct qman_portal *portal, u8 ithresh);
 
 /**
  * qman_dqrr_get_iperiod - Get coalesce interrupt period
@@ -1219,7 +1221,9 @@ void qman_portal_get_iperiod(struct qman_portal *portal, u32 *iperiod);
  * qman_dqrr_set_iperiod - Set coalesce interrupt period
  * @portal: portal to set the new value on
  * @ithresh: new period value
+ *
+ * Returns 0 on success, or a negative error code.
  */
-void qman_portal_set_iperiod(struct qman_portal *portal, u32 iperiod);
+int qman_portal_set_iperiod(struct qman_portal *portal, u32 iperiod);
 
 #endif	/* __FSL_QMAN_H */
-- 
cgit v1.2.3


From 10f70e9432311540ac252037f9fa7d068e81fbe2 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@nxp.com>
Date: Wed, 21 Nov 2018 13:41:09 +0200
Subject: dpaa_eth: add ethtool coalesce control

Allow ethtool control of the DPAA QMan portal interrupt coalescing
settings.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c | 71 ++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
index 13d6e2272ece..62497119c85f 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -529,6 +529,75 @@ static int dpaa_get_ts_info(struct net_device *net_dev,
 	return 0;
 }
 
+static int dpaa_get_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *c)
+{
+	struct qman_portal *portal;
+	u32 period;
+	u8 thresh;
+
+	portal = qman_get_affine_portal(smp_processor_id());
+	qman_portal_get_iperiod(portal, &period);
+	qman_dqrr_get_ithresh(portal, &thresh);
+
+	c->rx_coalesce_usecs = period;
+	c->rx_max_coalesced_frames = thresh;
+	c->use_adaptive_rx_coalesce = false;
+
+	return 0;
+}
+
+static int dpaa_set_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *c)
+{
+	const cpumask_t *cpus = qman_affine_cpus();
+	bool needs_revert[NR_CPUS] = {false};
+	struct qman_portal *portal;
+	u32 period, prev_period;
+	u8 thresh, prev_thresh;
+	int cpu, res;
+
+	if (c->use_adaptive_rx_coalesce)
+		return -EINVAL;
+
+	period = c->rx_coalesce_usecs;
+	thresh = c->rx_max_coalesced_frames;
+
+	/* save previous values */
+	portal = qman_get_affine_portal(smp_processor_id());
+	qman_portal_get_iperiod(portal, &prev_period);
+	qman_dqrr_get_ithresh(portal, &prev_thresh);
+
+	/* set new values */
+	for_each_cpu(cpu, cpus) {
+		portal = qman_get_affine_portal(cpu);
+		res = qman_portal_set_iperiod(portal, period);
+		if (res)
+			goto revert_values;
+		res = qman_dqrr_set_ithresh(portal, thresh);
+		if (res) {
+			qman_portal_set_iperiod(portal, prev_period);
+			goto revert_values;
+		}
+		needs_revert[cpu] = true;
+	}
+
+	return 0;
+
+revert_values:
+	/* restore previous values */
+	for_each_cpu(cpu, cpus) {
+		if (!needs_revert[cpu])
+			continue;
+		portal = qman_get_affine_portal(cpu);
+		/* previous values will not fail, ignore return value */
+		qman_portal_set_iperiod(portal, prev_period);
+		qman_dqrr_set_ithresh(portal, prev_thresh);
+	}
+
+	return res;
+}
+
 const struct ethtool_ops dpaa_ethtool_ops = {
 	.get_drvinfo = dpaa_get_drvinfo,
 	.get_msglevel = dpaa_get_msglevel,
@@ -545,4 +614,6 @@ const struct ethtool_ops dpaa_ethtool_ops = {
 	.get_rxnfc = dpaa_get_rxnfc,
 	.set_rxnfc = dpaa_set_rxnfc,
 	.get_ts_info = dpaa_get_ts_info,
+	.get_coalesce = dpaa_get_coalesce,
+	.set_coalesce = dpaa_set_coalesce,
 };
-- 
cgit v1.2.3


From 42519ede4fde2a50919215933e0f02c8342aba0f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 21 Nov 2018 11:39:28 -0800
Subject: net-gro: use ffs() to speedup napi_gro_flush()

We very often have few flows/chains to look at, and we
might increase GRO_HASH_BUCKETS to 32 or 64 in the future.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index f2bfd2eda7b2..d83582623cd7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5364,11 +5364,13 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
  */
 void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
-	u32 i;
+	unsigned long bitmask = napi->gro_bitmask;
+	unsigned int i, base = ~0U;
 
-	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
-		if (test_bit(i, &napi->gro_bitmask))
-			__napi_gro_flush_chain(napi, i, flush_old);
+	while ((i = ffs(bitmask)) != 0) {
+		bitmask >>= i;
+		base += i;
+		__napi_gro_flush_chain(napi, base, flush_old);
 	}
 }
 EXPORT_SYMBOL(napi_gro_flush);
-- 
cgit v1.2.3


From 47ae7e3d0be539c6af83b7b349ece31a18001aa6 Mon Sep 17 00:00:00 2001
From: "Nikita V. Shirokov" <tehnerd@tehnerd.com>
Date: Fri, 23 Nov 2018 12:58:12 -0800
Subject: libbpf: make bpf_object__open default to UNSPEC

currently by default libbpf's bpf_object__open requires
bpf's program to specify  version in a code because of two things:
1) default prog type is set to KPROBE
2) KPROBE requires (in kernel/bpf/syscall.c) version to be specified

in this patch i'm changing default prog type to UNSPEC and also changing
requirments for version's section to be present in object file.
now it would reflect what we have today in kernel
(only KPROBE prog type requires for version to be explicitly set).

v1 -> v2:
 - RFC tag has been dropped

Signed-off-by: Nikita V. Shirokov <tehnerd@tehnerd.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 0f14f7c074c2..ed4212a4c5f9 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -333,7 +333,7 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx,
 	prog->idx = idx;
 	prog->instances.fds = NULL;
 	prog->instances.nr = -1;
-	prog->type = BPF_PROG_TYPE_KPROBE;
+	prog->type = BPF_PROG_TYPE_UNSPEC;
 	prog->btf_fd = -1;
 
 	return 0;
@@ -1649,12 +1649,12 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
 	case BPF_PROG_TYPE_LIRC_MODE2:
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-		return false;
 	case BPF_PROG_TYPE_UNSPEC:
-	case BPF_PROG_TYPE_KPROBE:
 	case BPF_PROG_TYPE_TRACEPOINT:
-	case BPF_PROG_TYPE_PERF_EVENT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_PERF_EVENT:
+		return false;
+	case BPF_PROG_TYPE_KPROBE:
 	default:
 		return true;
 	}
-- 
cgit v1.2.3


From 5a863813216ce79e16a8c1503b2543c528b778b6 Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Fri, 23 Nov 2018 07:14:32 +0900
Subject: samples: bpf: fix: error handling regarding kprobe_events

Currently, kprobe_events failure won't be handled properly.
Due to calling system() indirectly to write to kprobe_events,
it can't be identified whether an error is derived from kprobe or system.

    // buf = "echo '%c:%s %s' >> /s/k/d/t/kprobe_events"
    err = system(buf);
    if (err < 0) {
        printf("failed to create kprobe ..");
        return -1;
    }

For example, running ./tracex7 sample in ext4 partition,
"echo p:open_ctree open_ctree >> /s/k/d/t/kprobe_events"
gets 256 error code system() failure.
=> The error comes from kprobe, but it's not handled correctly.

According to man of system(3), it's return value
just passes the termination status of the child shell
rather than treating the error as -1. (don't care success)

Which means, currently it's not working as desired.
(According to the upper code snippet)

    ex) running ./tracex7 with ext4 env.
    # Current Output
    sh: echo: I/O error
    failed to open event open_ctree

    # Desired Output
    failed to create kprobe 'open_ctree' error 'No such file or directory'

The problem is, error can't be verified whether from child ps
or system. But using write() directly can verify the command
failure, and it will treat all error as -1. So I suggest using
write() directly to 'kprobe_events' rather than calling system().

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/bpf_load.c | 33 ++++++++++++++++++++++++---------
 1 file changed, 24 insertions(+), 9 deletions(-)

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 5c052b9ea63f..434ea34a5954 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -54,6 +54,23 @@ static int populate_prog_array(const char *event, int prog_fd)
 	return 0;
 }
 
+static int write_kprobe_events(const char *val)
+{
+	int fd, ret, flags;
+
+	if ((val != NULL) && (val[0] == '\0'))
+		flags = O_WRONLY | O_TRUNC;
+	else
+		flags = O_WRONLY | O_APPEND;
+
+	fd = open("/sys/kernel/debug/tracing/kprobe_events", flags);
+
+	ret = write(fd, val, strlen(val));
+	close(fd);
+
+	return ret;
+}
+
 static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 {
 	bool is_socket = strncmp(event, "socket", 6) == 0;
@@ -165,10 +182,9 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 
 #ifdef __x86_64__
 		if (strncmp(event, "sys_", 4) == 0) {
-			snprintf(buf, sizeof(buf),
-				 "echo '%c:__x64_%s __x64_%s' >> /sys/kernel/debug/tracing/kprobe_events",
-				 is_kprobe ? 'p' : 'r', event, event);
-			err = system(buf);
+			snprintf(buf, sizeof(buf), "%c:__x64_%s __x64_%s",
+				is_kprobe ? 'p' : 'r', event, event);
+			err = write_kprobe_events(buf);
 			if (err >= 0) {
 				need_normal_check = false;
 				event_prefix = "__x64_";
@@ -176,10 +192,9 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		}
 #endif
 		if (need_normal_check) {
-			snprintf(buf, sizeof(buf),
-				 "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events",
-				 is_kprobe ? 'p' : 'r', event, event);
-			err = system(buf);
+			snprintf(buf, sizeof(buf), "%c:%s %s",
+				is_kprobe ? 'p' : 'r', event, event);
+			err = write_kprobe_events(buf);
 			if (err < 0) {
 				printf("failed to create kprobe '%s' error '%s'\n",
 				       event, strerror(errno));
@@ -519,7 +534,7 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
 		return 1;
 
 	/* clear all kprobes */
-	i = system("echo \"\" > /sys/kernel/debug/tracing/kprobe_events");
+	i = write_kprobe_events("");
 
 	/* scan over all elf sections to get license and map info */
 	for (i = 1; i < ehdr.e_shnum; i++) {
-- 
cgit v1.2.3


From 197c2dac74e4ae3158ad10f848c5402236d6b176 Mon Sep 17 00:00:00 2001
From: David Calavera <david.calavera@gmail.com>
Date: Thu, 22 Nov 2018 12:59:45 -0800
Subject: bpf: Add BPF_MAP_TYPE_QUEUE and BPF_MAP_TYPE_STACK to bpftool-map

I noticed that these two new BPF Maps are not defined in bpftool.
This patch defines those two maps and adds their names to the
bpftool-map documentation.

Signed-off-by: David Calavera <david.calavera@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-map.rst | 3 ++-
 tools/bpf/bpftool/map.c                         | 2 ++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index f55a2daed59b..9e827e342d9e 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -42,7 +42,8 @@ MAP COMMANDS
 |		| **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash**
 |		| **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps**
 |		| **devmap** | **sockmap** | **cpumap** | **xskmap** | **sockhash**
-|		| **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** }
+|		| **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage**
+|		| **queue** | **stack** }
 
 DESCRIPTION
 ===========
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index a1ae2a3e9fef..b0ebbed7d1a6 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -74,6 +74,8 @@ static const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_CGROUP_STORAGE]	= "cgroup_storage",
 	[BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray",
 	[BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE]	= "percpu_cgroup_storage",
+	[BPF_MAP_TYPE_QUEUE] = "queue",
+	[BPF_MAP_TYPE_STACK] = "stack",
 };
 
 static bool map_is_per_cpu(__u32 type)
-- 
cgit v1.2.3


From e4a3e9ff5ba9f6b67595ec2768ed4be2054c2aa5 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 22 Nov 2018 14:42:00 +0800
Subject: net: mvneta: remove redundant check for eee->tx_lpi_timer < 0

fixes the smatch warning:

drivers/net/ethernet/marvell/mvneta.c:4252 mvneta_ethtool_set_eee() warn:
 unsigned 'eee->tx_lpi_timer' is never less than zero.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e5397c8197b9..46a0f6b45d84 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4248,8 +4248,7 @@ static int mvneta_ethtool_set_eee(struct net_device *dev,
 
 	/* The Armada 37x documents do not give limits for this other than
 	 * it being an 8-bit register. */
-	if (eee->tx_lpi_enabled &&
-	    (eee->tx_lpi_timer < 0 || eee->tx_lpi_timer > 255))
+	if (eee->tx_lpi_enabled && eee->tx_lpi_timer > 255)
 		return -EINVAL;
 
 	lpi_ctl0 = mvreg_read(pp, MVNETA_LPI_CTRL_0);
-- 
cgit v1.2.3


From 263ffaeef174cc3adb51c87d6bb383d7af0199e7 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 22 Nov 2018 10:26:34 +0100
Subject: net/smc: cleanup tcp_listen_worker initialization

The tcp_listen_worker is already initialized when socket is
created (in smc_sock_alloc()). Get rid of the duplicate
initialization in smc_listen(). No functional change.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 80e2119f1c70..d9b1a0e4446c 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1354,7 +1354,6 @@ static int smc_listen(struct socket *sock, int backlog)
 	sk->sk_max_ack_backlog = backlog;
 	sk->sk_ack_backlog = 0;
 	sk->sk_state = SMC_LISTEN;
-	INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
 	sock_hold(sk); /* sock_hold in tcp_listen_worker */
 	if (!schedule_work(&smc->tcp_listen_work))
 		sock_put(sk);
-- 
cgit v1.2.3


From 3f3f0e364eb8ca18366e462f65dfe303f7449a6f Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 22 Nov 2018 10:26:35 +0100
Subject: net/smc: make smc_lgr_free() static

smc_lgr_free() is just called inside smc_core.c. Make it static.
Just cleanup, no functional change.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_core.c | 4 +++-
 net/smc/smc_core.h | 1 -
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 18daebcef181..4812ca30f1dc 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -149,6 +149,8 @@ static int smc_link_send_delete(struct smc_link *lnk)
 	return -ENOTCONN;
 }
 
+static void smc_lgr_free(struct smc_link_group *lgr);
+
 static void smc_lgr_free_work(struct work_struct *work)
 {
 	struct smc_link_group *lgr = container_of(to_delayed_work(work),
@@ -408,7 +410,7 @@ static void smc_lgr_free_bufs(struct smc_link_group *lgr)
 }
 
 /* remove a link group */
-void smc_lgr_free(struct smc_link_group *lgr)
+static void smc_lgr_free(struct smc_link_group *lgr)
 {
 	smc_lgr_free_bufs(lgr);
 	if (lgr->is_smcd)
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index c156674733c9..07364c0b41a1 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -243,7 +243,6 @@ struct smc_sock;
 struct smc_clc_msg_accept_confirm;
 struct smc_clc_msg_local;
 
-void smc_lgr_free(struct smc_link_group *lgr);
 void smc_lgr_forget(struct smc_link_group *lgr);
 void smc_lgr_terminate(struct smc_link_group *lgr);
 void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport);
-- 
cgit v1.2.3


From 6ae36bff3f511d8b24ebbc126e3f1f23ac202ef4 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 22 Nov 2018 10:26:36 +0100
Subject: net/smc: remove sock_error detour in clc-functions

There is no need to store the return value in sk_err, if it is
afterwards cleared again with sock_error(). This patch sets the
return value directly. Just cleanup, no functional change.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_clc.c | 18 +++++-------------
 1 file changed, 5 insertions(+), 13 deletions(-)

diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 89c3a8c7859a..7278ec0cfa58 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -374,10 +374,8 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
 	len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
 			     sizeof(struct smc_clc_msg_decline));
 	if (len < sizeof(struct smc_clc_msg_decline))
-		smc->sk.sk_err = EPROTO;
-	if (len < 0)
-		smc->sk.sk_err = -len;
-	return sock_error(&smc->sk);
+		len = -EPROTO;
+	return len > 0 ? 0 : len;
 }
 
 /* send CLC PROPOSAL message across internal TCP socket */
@@ -536,7 +534,6 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
 	struct smc_link *link;
 	struct msghdr msg;
 	struct kvec vec;
-	int rc = 0;
 	int len;
 
 	memset(&aclc, 0, sizeof(aclc));
@@ -589,13 +586,8 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
 	vec.iov_len = ntohs(aclc.hdr.length);
 	len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1,
 			     ntohs(aclc.hdr.length));
-	if (len < ntohs(aclc.hdr.length)) {
-		if (len >= 0)
-			new_smc->sk.sk_err = EPROTO;
-		else
-			new_smc->sk.sk_err = new_smc->clcsock->sk->sk_err;
-		rc = sock_error(&new_smc->sk);
-	}
+	if (len < ntohs(aclc.hdr.length))
+		len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err;
 
-	return rc;
+	return len > 0 ? 0 : len;
 }
-- 
cgit v1.2.3


From 9ed28556a388fdb894bdf9bd64c05cf6e7783ba3 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 22 Nov 2018 10:26:37 +0100
Subject: net/smc: allow fallback after clc timeouts

If connection initialization fails for the LLC CONFIRM LINK or the
LLC ADD LINK step, fallback to TCP should be enabled. Thus
the negative return code -EAGAIN should switch to a positive timeout
reason code in these cases, and the internal CLC socket should
not have a set sk_err.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c  | 8 ++++----
 net/smc/smc_clc.c | 9 +++++++--
 2 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index d9b1a0e4446c..66836cfbc587 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -336,7 +336,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 
 		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
 				      SMC_CLC_DECLINE);
-		return rc;
+		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc;
 	}
 
 	if (link->llc_confirm_rc)
@@ -364,7 +364,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 
 		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
 				      SMC_CLC_DECLINE);
-		return rc;
+		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_AL : rc;
 	}
 
 	/* send add link reject message, only one link supported for now */
@@ -966,7 +966,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 
 		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
 				      SMC_CLC_DECLINE);
-		return rc;
+		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc;
 	}
 
 	if (link->llc_confirm_resp_rc)
@@ -987,7 +987,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 
 		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
 				      SMC_CLC_DECLINE);
-		return rc;
+		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_AL : rc;
 	}
 
 	smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 7278ec0cfa58..62043d69e3a3 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -297,7 +297,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	}
 	if (clc_sk->sk_err) {
 		reason_code = -clc_sk->sk_err;
-		smc->sk.sk_err = clc_sk->sk_err;
+		if (clc_sk->sk_err == EAGAIN &&
+		    expected_type == SMC_CLC_DECLINE)
+			clc_sk->sk_err = 0; /* reset for fallback usage */
+		else
+			smc->sk.sk_err = clc_sk->sk_err;
 		goto out;
 	}
 	if (!len) { /* peer has performed orderly shutdown */
@@ -306,7 +310,8 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		goto out;
 	}
 	if (len < 0) {
-		smc->sk.sk_err = -len;
+		if (len != -EAGAIN || expected_type != SMC_CLC_DECLINE)
+			smc->sk.sk_err = -len;
 		reason_code = len;
 		goto out;
 	}
-- 
cgit v1.2.3


From 90d8b29cb4b251cd874aa00a50d11b28a7322986 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 22 Nov 2018 10:26:38 +0100
Subject: net/smc: no link delete for a never active link

If a link is terminated that has never reached the active state,
there is no need to trigger an LLC DELETE LINK.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 4812ca30f1dc..ec7a7ed3b968 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -173,8 +173,11 @@ free:
 	spin_unlock_bh(&smc_lgr_list.lock);
 
 	if (!lgr->is_smcd && !lgr->terminating)	{
+		struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+
 		/* try to send del link msg, on error free lgr immediately */
-		if (!smc_link_send_delete(&lgr->lnk[SMC_SINGLE_LINK])) {
+		if (lnk->state == SMC_LNK_ACTIVE &&
+		    !smc_link_send_delete(lnk)) {
 			/* reschedule in case we never receive a response */
 			smc_lgr_schedule_free_work(lgr);
 			return;
-- 
cgit v1.2.3


From 2b59f58e34e78abec2bccd2413ae9e7ea509a855 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 22 Nov 2018 10:26:39 +0100
Subject: net/smc: short wait for late smc_clc_wait_msg

After sending one of the initial LLC messages CONFIRM LINK or
ADD LINK, there is already a wait for the LLC response. It does
not make sense to wait another long time for a CLC DECLINE. Thus
this patch introduces a shorter wait time for these cases.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c  | 15 ++++++++-------
 net/smc/smc_clc.c |  6 +++---
 net/smc/smc_clc.h |  3 ++-
 3 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 66836cfbc587..93f7ff8f6e88 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -335,7 +335,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 		struct smc_clc_msg_decline dclc;
 
 		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
-				      SMC_CLC_DECLINE);
+				      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
 		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc;
 	}
 
@@ -363,7 +363,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 		struct smc_clc_msg_decline dclc;
 
 		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
-				      SMC_CLC_DECLINE);
+				      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
 		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_AL : rc;
 	}
 
@@ -533,7 +533,8 @@ static int smc_connect_clc(struct smc_sock *smc, int smc_type,
 	if (rc)
 		return rc;
 	/* receive SMC Accept CLC message */
-	return smc_clc_wait_msg(smc, aclc, sizeof(*aclc), SMC_CLC_ACCEPT);
+	return smc_clc_wait_msg(smc, aclc, sizeof(*aclc), SMC_CLC_ACCEPT,
+				CLC_WAIT_TIME);
 }
 
 /* setup for RDMA connection of client */
@@ -965,7 +966,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 		struct smc_clc_msg_decline dclc;
 
 		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
-				      SMC_CLC_DECLINE);
+				      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
 		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc;
 	}
 
@@ -986,7 +987,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 		struct smc_clc_msg_decline dclc;
 
 		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
-				      SMC_CLC_DECLINE);
+				      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
 		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_AL : rc;
 	}
 
@@ -1222,7 +1223,7 @@ static void smc_listen_work(struct work_struct *work)
 	 */
 	pclc = (struct smc_clc_msg_proposal *)&buf;
 	reason_code = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN,
-				       SMC_CLC_PROPOSAL);
+				       SMC_CLC_PROPOSAL, CLC_WAIT_TIME);
 	if (reason_code) {
 		smc_listen_decline(new_smc, reason_code, 0);
 		return;
@@ -1272,7 +1273,7 @@ static void smc_listen_work(struct work_struct *work)
 
 	/* receive SMC Confirm CLC message */
 	reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
-				       SMC_CLC_CONFIRM);
+				       SMC_CLC_CONFIRM, CLC_WAIT_TIME);
 	if (reason_code) {
 		mutex_unlock(&smc_create_lgr_pending);
 		smc_listen_decline(new_smc, reason_code, local_contact);
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 62043d69e3a3..776e9dfc915d 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -265,7 +265,7 @@ out:
  * clcsock error, -EINTR, -ECONNRESET, -EPROTO otherwise.
  */
 int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
-		     u8 expected_type)
+		     u8 expected_type, unsigned long timeout)
 {
 	long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo;
 	struct sock *clc_sk = smc->clcsock->sk;
@@ -285,7 +285,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	 * sizeof(struct smc_clc_msg_hdr)
 	 */
 	krflags = MSG_PEEK | MSG_WAITALL;
-	smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
+	clc_sk->sk_rcvtimeo = timeout;
 	iov_iter_kvec(&msg.msg_iter, READ, &vec, 1,
 			sizeof(struct smc_clc_msg_hdr));
 	len = sock_recvmsg(smc->clcsock, &msg, krflags);
@@ -351,7 +351,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	}
 
 out:
-	smc->clcsock->sk->sk_rcvtimeo = rcvtimeo;
+	clc_sk->sk_rcvtimeo = rcvtimeo;
 	return reason_code;
 }
 
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 18da89b681c2..24658e8c0de4 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -27,6 +27,7 @@
 #define SMC_TYPE_D		1		/* SMC-D only		      */
 #define SMC_TYPE_B		3		/* SMC-R and SMC-D	      */
 #define CLC_WAIT_TIME		(6 * HZ)	/* max. wait time on clcsock  */
+#define CLC_WAIT_TIME_SHORT	HZ		/* short wait time on clcsock */
 #define SMC_CLC_DECL_MEM	0x01010000  /* insufficient memory resources  */
 #define SMC_CLC_DECL_TIMEOUT_CL	0x02010000  /* timeout w4 QP confirm link     */
 #define SMC_CLC_DECL_TIMEOUT_AL	0x02020000  /* timeout w4 QP add link	      */
@@ -182,7 +183,7 @@ struct smcd_dev;
 int smc_clc_prfx_match(struct socket *clcsock,
 		       struct smc_clc_msg_proposal_prefix *prop);
 int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
-		     u8 expected_type);
+		     u8 expected_type, unsigned long timeout);
 int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
 int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
 			  struct smc_ib_device *smcibdev, u8 ibport, u8 gid[],
-- 
cgit v1.2.3


From 587e41dcea357a1ac15e3b31d800900e1c585d7e Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 22 Nov 2018 10:26:40 +0100
Subject: net/smc: cleanup listen worker mutex unlocking

For easier reading move the unlock of mutex smc_create_lgr_pending into
smc_listen_work(), i.e. into the function the mutex has been locked.
No functional change.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 93f7ff8f6e88..7657e249f526 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1182,7 +1182,6 @@ static int smc_listen_rdma_finish(struct smc_sock *new_smc,
 	return 0;
 
 decline:
-	mutex_unlock(&smc_create_lgr_pending);
 	smc_listen_decline(new_smc, reason_code, local_contact);
 	return reason_code;
 }
@@ -1282,8 +1281,10 @@ static void smc_listen_work(struct work_struct *work)
 
 	/* finish worker */
 	if (!ism_supported) {
-		if (smc_listen_rdma_finish(new_smc, &cclc, local_contact))
+		if (smc_listen_rdma_finish(new_smc, &cclc, local_contact)) {
+			mutex_unlock(&smc_create_lgr_pending);
 			return;
+		}
 	}
 	smc_conn_save_peer_info(new_smc, &cclc);
 	mutex_unlock(&smc_create_lgr_pending);
-- 
cgit v1.2.3


From 4600cfc302f70f2b4d89818b4d4c79bd19e5ab87 Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Thu, 22 Nov 2018 10:26:41 +0100
Subject: net/smc: avoid a delay by waiting for nothing

When a send failed then don't start to wait for a response in
smc_llc_do_confirm_rkey.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_llc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 9c916c709ca7..132c6a8e49f8 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -651,7 +651,9 @@ int smc_llc_do_confirm_rkey(struct smc_link *link,
 	int rc;
 
 	reinit_completion(&link->llc_confirm_rkey);
-	smc_llc_send_confirm_rkey(link, rmb_desc);
+	rc = smc_llc_send_confirm_rkey(link, rmb_desc);
+	if (rc)
+		return rc;
 	/* receive CONFIRM RKEY response from server over RoCE fabric */
 	rc = wait_for_completion_interruptible_timeout(&link->llc_confirm_rkey,
 						       SMC_LLC_WAIT_TIME);
-- 
cgit v1.2.3


From 60e03c62c5db22c5eb63bcb6ce226cf05f4ee47c Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Thu, 22 Nov 2018 10:26:42 +0100
Subject: net/smc: add infrastructure to send delete rkey messages

Add the infrastructure to send LLC messages of type DELETE RKEY to
unregister a shared memory region at the peer.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_core.h |  3 +++
 net/smc/smc_llc.c  | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 net/smc/smc_llc.h  |  2 ++
 3 files changed, 57 insertions(+), 1 deletion(-)

diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 07364c0b41a1..bce39d6df45a 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -109,6 +109,9 @@ struct smc_link {
 	int			llc_testlink_time; /* testlink interval */
 	struct completion	llc_confirm_rkey; /* wait 4 rx of cnf rkey */
 	int			llc_confirm_rkey_rc; /* rc from cnf rkey msg */
+	struct completion	llc_delete_rkey; /* wait 4 rx of del rkey */
+	int			llc_delete_rkey_rc; /* rc from del rkey msg */
+	struct mutex		llc_delete_rkey_mutex; /* serialize usage */
 };
 
 /* For now we just allow one parallel link per link group. The SMC protocol
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 132c6a8e49f8..a6d3623d06f4 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -238,6 +238,29 @@ static int smc_llc_send_confirm_rkey(struct smc_link *link,
 	return rc;
 }
 
+/* send LLC delete rkey request */
+static int smc_llc_send_delete_rkey(struct smc_link *link,
+				    struct smc_buf_desc *rmb_desc)
+{
+	struct smc_llc_msg_delete_rkey *rkeyllc;
+	struct smc_wr_tx_pend_priv *pend;
+	struct smc_wr_buf *wr_buf;
+	int rc;
+
+	rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+	if (rc)
+		return rc;
+	rkeyllc = (struct smc_llc_msg_delete_rkey *)wr_buf;
+	memset(rkeyllc, 0, sizeof(*rkeyllc));
+	rkeyllc->hd.common.type = SMC_LLC_DELETE_RKEY;
+	rkeyllc->hd.length = sizeof(struct smc_llc_msg_delete_rkey);
+	rkeyllc->num_rkeys = 1;
+	rkeyllc->rkey[0] = htonl(rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+	/* send llc message */
+	rc = smc_wr_tx_send(link, pend);
+	return rc;
+}
+
 /* prepare an add link message */
 static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc,
 				  struct smc_link *link, u8 mac[], u8 gid[],
@@ -509,7 +532,9 @@ static void smc_llc_rx_delete_rkey(struct smc_link *link,
 	int i, max;
 
 	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
-		/* unused as long as we don't send this type of msg */
+		link->llc_delete_rkey_rc = llc->hd.flags &
+					    SMC_LLC_FLAG_RKEY_NEG;
+		complete(&link->llc_delete_rkey);
 	} else {
 		max = min_t(u8, llc->num_rkeys, SMC_LLC_DEL_RKEY_MAX);
 		for (i = 0; i < max; i++) {
@@ -610,6 +635,8 @@ int smc_llc_link_init(struct smc_link *link)
 	init_completion(&link->llc_add);
 	init_completion(&link->llc_add_resp);
 	init_completion(&link->llc_confirm_rkey);
+	init_completion(&link->llc_delete_rkey);
+	mutex_init(&link->llc_delete_rkey_mutex);
 	init_completion(&link->llc_testlink_resp);
 	INIT_DELAYED_WORK(&link->llc_testlink_wrk, smc_llc_testlink_work);
 	return 0;
@@ -650,6 +677,7 @@ int smc_llc_do_confirm_rkey(struct smc_link *link,
 {
 	int rc;
 
+	/* protected by mutex smc_create_lgr_pending */
 	reinit_completion(&link->llc_confirm_rkey);
 	rc = smc_llc_send_confirm_rkey(link, rmb_desc);
 	if (rc)
@@ -662,6 +690,29 @@ int smc_llc_do_confirm_rkey(struct smc_link *link,
 	return 0;
 }
 
+/* unregister an rtoken at the remote peer */
+int smc_llc_do_delete_rkey(struct smc_link *link,
+			   struct smc_buf_desc *rmb_desc)
+{
+	int rc;
+
+	mutex_lock(&link->llc_delete_rkey_mutex);
+	reinit_completion(&link->llc_delete_rkey);
+	rc = smc_llc_send_delete_rkey(link, rmb_desc);
+	if (rc)
+		goto out;
+	/* receive DELETE RKEY response from server over RoCE fabric */
+	rc = wait_for_completion_interruptible_timeout(&link->llc_delete_rkey,
+						       SMC_LLC_WAIT_TIME);
+	if (rc <= 0 || link->llc_delete_rkey_rc)
+		rc = -EFAULT;
+	else
+		rc = 0;
+out:
+	mutex_unlock(&link->llc_delete_rkey_mutex);
+	return rc;
+}
+
 /***************************** init, exit, misc ******************************/
 
 static struct smc_wr_rx_handler smc_llc_rx_handlers[] = {
diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h
index 9e2ff088e301..461c0c3ef76e 100644
--- a/net/smc/smc_llc.h
+++ b/net/smc/smc_llc.h
@@ -49,6 +49,8 @@ void smc_llc_link_inactive(struct smc_link *link);
 void smc_llc_link_clear(struct smc_link *link);
 int smc_llc_do_confirm_rkey(struct smc_link *link,
 			    struct smc_buf_desc *rmb_desc);
+int smc_llc_do_delete_rkey(struct smc_link *link,
+			   struct smc_buf_desc *rmb_desc);
 int smc_llc_init(void) __init;
 
 #endif /* SMC_LLC_H */
-- 
cgit v1.2.3


From c7674c001b1143a5bc6b36efc7adc4bdd8ff5e76 Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Thu, 22 Nov 2018 10:26:43 +0100
Subject: net/smc: unregister rkeys of unused buffer

When an rmb is no longer in use by a connection, unregister its rkey at
the remote peer with an LLC DELETE RKEY message. With this change,
unused buffers held in the buffer pool are no longer registered at the
remote peer. They are registered before the buffer is actually used and
unregistered when they are no longer used by a connection.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c   | 22 +++++++++++-----------
 net/smc/smc_core.c |  7 ++++++-
 net/smc/smc_core.h |  2 +-
 3 files changed, 18 insertions(+), 13 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 7657e249f526..4b865250e238 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -299,14 +299,17 @@ static void smc_copy_sock_settings_to_smc(struct smc_sock *smc)
 	smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC);
 }
 
-/* register a new rmb, optionally send confirm_rkey msg to register with peer */
+/* register a new rmb, send confirm_rkey msg to register with peer */
 static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc,
 		       bool conf_rkey)
 {
-	/* register memory region for new rmb */
-	if (smc_wr_reg_send(link, rmb_desc->mr_rx[SMC_SINGLE_LINK])) {
-		rmb_desc->regerr = 1;
-		return -EFAULT;
+	if (!rmb_desc->wr_reg) {
+		/* register memory region for new rmb */
+		if (smc_wr_reg_send(link, rmb_desc->mr_rx[SMC_SINGLE_LINK])) {
+			rmb_desc->regerr = 1;
+			return -EFAULT;
+		}
+		rmb_desc->wr_reg = 1;
 	}
 	if (!conf_rkey)
 		return 0;
@@ -581,8 +584,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 			return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK,
 						 local_contact);
 	} else {
-		if (!smc->conn.rmb_desc->reused &&
-		    smc_reg_rmb(link, smc->conn.rmb_desc, true))
+		if (smc_reg_rmb(link, smc->conn.rmb_desc, true))
 			return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB,
 						 local_contact);
 	}
@@ -1143,10 +1145,8 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact)
 	struct smc_link *link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
 
 	if (local_contact != SMC_FIRST_CONTACT) {
-		if (!new_smc->conn.rmb_desc->reused) {
-			if (smc_reg_rmb(link, new_smc->conn.rmb_desc, true))
-				return SMC_CLC_DECL_ERR_REGRMB;
-		}
+		if (smc_reg_rmb(link, new_smc->conn.rmb_desc, true))
+			return SMC_CLC_DECL_ERR_REGRMB;
 	}
 	smc_rmb_sync_sg_for_device(&new_smc->conn);
 
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index ec7a7ed3b968..1382ddae591e 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -298,8 +298,13 @@ static void smc_buf_unuse(struct smc_connection *conn,
 		conn->sndbuf_desc->used = 0;
 	if (conn->rmb_desc) {
 		if (!conn->rmb_desc->regerr) {
-			conn->rmb_desc->reused = 1;
 			conn->rmb_desc->used = 0;
+			if (!lgr->is_smcd) {
+				/* unregister rmb with peer */
+				smc_llc_do_delete_rkey(
+						&lgr->lnk[SMC_SINGLE_LINK],
+						conn->rmb_desc);
+			}
 		} else {
 			/* buf registration failed, reuse not possible */
 			write_lock_bh(&lgr->rmbs_lock);
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index bce39d6df45a..e177c6675038 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -130,7 +130,7 @@ struct smc_buf_desc {
 	struct page		*pages;
 	int			len;		/* length of buffer */
 	u32			used;		/* currently used / unused */
-	u8			reused	: 1;	/* new created / reused */
+	u8			wr_reg	: 1;	/* mem region registered */
 	u8			regerr	: 1;	/* err during registration */
 	union {
 		struct { /* SMC-R */
-- 
cgit v1.2.3


From e159e592872edc0536f55ec242dbc5b70a593265 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 22 Nov 2018 10:05:01 +0000
Subject: net: hinic: fix null pointer dereference on pointer hwdev

Pointer hwdev is being dereferenced when declaring hwif , however, later
on hwdev is being null checked, hence we have dereference before null
check error. Fix this by assigning hwif and pdef only once hwdev has
been null checked.

Detected by CoverityScan, CID#1485581 ("Dereference before null check")

Fixes: 4a61abb100c8 ("net-next/hinic:add rx checksum offload for HiNIC")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_port.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index e9f76e904610..122c93597268 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -414,14 +414,16 @@ int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en)
 {
 	struct hinic_checksum_offload rx_csum_cfg = {0};
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
-	struct hinic_hwif *hwif = hwdev->hwif;
-	struct pci_dev *pdev = hwif->pdev;
+	struct hinic_hwif *hwif;
+	struct pci_dev *pdev;
 	u16 out_size;
 	int err;
 
 	if (!hwdev)
 		return -EINVAL;
 
+	hwif = hwdev->hwif;
+	pdev = hwif->pdev;
 	rx_csum_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif);
 	rx_csum_cfg.rx_csum_offload = en;
 
-- 
cgit v1.2.3


From 44990aaa939439cfd151435e5dcd965494ace8b0 Mon Sep 17 00:00:00 2001
From: Linu Cherian <lcherian@marvell.com>
Date: Thu, 22 Nov 2018 17:18:34 +0530
Subject: octeontx2-af: Misc cleanups in cgx driver

* Do CGX init before NIX init
  This would add consistency in NIX code that depends on cgx ports

* Few other misc cleanups
  - rvu_cgx_probe renamed as rvu_cgx_init for consistency
  - rvu_cgx_exit wrapper added to take care of the exit path
  - Added error check on cgx_lmac_event_handler_init
  - Minor cleanups in cgx.h related to tab alignment
  - Removed redundant ids from enum cgx_cmd_id

Signed-off-by: Linu Cherian <lcherian@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.h    | 28 +++++++++++-----------
 .../net/ethernet/marvell/octeontx2/af/cgx_fw_if.h  |  2 --
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c    | 26 +++++++++++---------
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  4 ++--
 .../net/ethernet/marvell/octeontx2/af/rvu_cgx.c    | 27 ++++++++++++++-------
 5 files changed, 50 insertions(+), 37 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index 3bd38ed6d68b..8d7d77b3035c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -27,34 +27,34 @@
 
 /* Registers */
 #define CGXX_CMRX_CFG			0x00
-#define  CMR_EN					BIT_ULL(55)
-#define  DATA_PKT_TX_EN				BIT_ULL(53)
-#define  DATA_PKT_RX_EN				BIT_ULL(54)
-#define  CGX_LMAC_TYPE_SHIFT			40
-#define  CGX_LMAC_TYPE_MASK			0xF
+#define CMR_EN				BIT_ULL(55)
+#define DATA_PKT_TX_EN			BIT_ULL(53)
+#define DATA_PKT_RX_EN			BIT_ULL(54)
+#define CGX_LMAC_TYPE_SHIFT		40
+#define CGX_LMAC_TYPE_MASK		0xF
 #define CGXX_CMRX_INT			0x040
-#define  FW_CGX_INT				BIT_ULL(1)
+#define FW_CGX_INT			BIT_ULL(1)
 #define CGXX_CMRX_INT_ENA_W1S		0x058
 #define CGXX_CMRX_RX_ID_MAP		0x060
 #define CGXX_CMRX_RX_STAT0		0x070
 #define CGXX_CMRX_RX_LMACS		0x128
 #define CGXX_CMRX_RX_DMAC_CTL0		0x1F8
-#define  CGX_DMAC_CTL0_CAM_ENABLE		BIT_ULL(3)
-#define  CGX_DMAC_CAM_ACCEPT			BIT_ULL(3)
-#define  CGX_DMAC_MCAST_MODE			BIT_ULL(1)
-#define  CGX_DMAC_BCAST_MODE			BIT_ULL(0)
+#define CGX_DMAC_CTL0_CAM_ENABLE	BIT_ULL(3)
+#define CGX_DMAC_CAM_ACCEPT		BIT_ULL(3)
+#define CGX_DMAC_MCAST_MODE		BIT_ULL(1)
+#define CGX_DMAC_BCAST_MODE		BIT_ULL(0)
 #define CGXX_CMRX_RX_DMAC_CAM0		0x200
-#define  CGX_DMAC_CAM_ADDR_ENABLE		BIT_ULL(48)
+#define CGX_DMAC_CAM_ADDR_ENABLE	BIT_ULL(48)
 #define CGXX_CMRX_RX_DMAC_CAM1		0x400
-#define CGX_RX_DMAC_ADR_MASK			GENMASK_ULL(47, 0)
+#define CGX_RX_DMAC_ADR_MASK		GENMASK_ULL(47, 0)
 #define CGXX_CMRX_TX_STAT0		0x700
 #define CGXX_SCRATCH0_REG		0x1050
 #define CGXX_SCRATCH1_REG		0x1058
 #define CGX_CONST			0x2000
 #define CGXX_SPUX_CONTROL1		0x10000
-#define  CGXX_SPUX_CONTROL1_LBK			BIT_ULL(14)
+#define CGXX_SPUX_CONTROL1_LBK		BIT_ULL(14)
 #define CGXX_GMP_PCS_MRX_CTL		0x30000
-#define  CGXX_GMP_PCS_MRX_CTL_LBK		BIT_ULL(14)
+#define CGXX_GMP_PCS_MRX_CTL_LBK	BIT_ULL(14)
 
 #define CGX_COMMAND_REG			CGXX_SCRATCH1_REG
 #define CGX_EVENT_REG			CGXX_SCRATCH0_REG
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
index fa17af3f4ba7..2d9fe51c6616 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
@@ -78,8 +78,6 @@ enum cgx_cmd_id {
 	CGX_CMD_LINK_STATE_CHANGE,
 	CGX_CMD_MODE_CHANGE,		/* hot plug support */
 	CGX_CMD_INTF_SHUTDOWN,
-	CGX_CMD_IRQ_ENABLE,
-	CGX_CMD_IRQ_DISABLE,
 };
 
 /* async event ids */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 40eb3ad725f5..4d061d971956 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -811,17 +811,26 @@ init:
 
 	err = rvu_npc_init(rvu);
 	if (err)
-		return err;
+		goto exit;
+
+	err = rvu_cgx_init(rvu);
+	if (err)
+		goto exit;
 
 	err = rvu_npa_init(rvu);
 	if (err)
-		return err;
+		goto cgx_err;
 
 	err = rvu_nix_init(rvu);
 	if (err)
-		return err;
+		goto cgx_err;
 
 	return 0;
+
+cgx_err:
+	rvu_cgx_exit(rvu);
+exit:
+	return err;
 }
 
 /* NPA and NIX admin queue APIs */
@@ -2419,13 +2428,9 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_hwsetup;
 
-	err = rvu_cgx_probe(rvu);
-	if (err)
-		goto err_mbox;
-
 	err = rvu_flr_init(rvu);
 	if (err)
-		goto err_cgx;
+		goto err_mbox;
 
 	err = rvu_register_interrupts(rvu);
 	if (err)
@@ -2441,11 +2446,10 @@ err_irq:
 	rvu_unregister_interrupts(rvu);
 err_flr:
 	rvu_flr_wq_destroy(rvu);
-err_cgx:
-	rvu_cgx_wq_destroy(rvu);
 err_mbox:
 	rvu_mbox_destroy(&rvu->afpf_wq_info);
 err_hwsetup:
+	rvu_cgx_exit(rvu);
 	rvu_reset_all_blocks(rvu);
 	rvu_free_hw_resources(rvu);
 err_release_regions:
@@ -2465,7 +2469,7 @@ static void rvu_remove(struct pci_dev *pdev)
 
 	rvu_unregister_interrupts(rvu);
 	rvu_flr_wq_destroy(rvu);
-	rvu_cgx_wq_destroy(rvu);
+	rvu_cgx_exit(rvu);
 	rvu_mbox_destroy(&rvu->afpf_wq_info);
 	rvu_disable_sriov(rvu);
 	rvu_reset_all_blocks(rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index c8409bc5d9c3..96049e275335 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -316,8 +316,8 @@ static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id)
 	*lmac_id = (map & 0xF);
 }
 
-int rvu_cgx_probe(struct rvu *rvu);
-void rvu_cgx_wq_destroy(struct rvu *rvu);
+int rvu_cgx_init(struct rvu *rvu);
+int rvu_cgx_exit(struct rvu *rvu);
 void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu);
 int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start);
 int rvu_mbox_handler_cgx_start_rxtx(struct rvu *rvu, struct msg_req *req,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 1de6eb528d08..1f1bc837bcd6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -216,7 +216,7 @@ static void cgx_evhandler_task(struct work_struct *work)
 	} while (1);
 }
 
-static void cgx_lmac_event_handler_init(struct rvu *rvu)
+static int cgx_lmac_event_handler_init(struct rvu *rvu)
 {
 	struct cgx_event_cb cb;
 	int cgx, lmac, err;
@@ -228,7 +228,7 @@ static void cgx_lmac_event_handler_init(struct rvu *rvu)
 	rvu->cgx_evh_wq = alloc_workqueue("rvu_evh_wq", 0, 0);
 	if (!rvu->cgx_evh_wq) {
 		dev_err(rvu->dev, "alloc workqueue failed");
-		return;
+		return -ENOMEM;
 	}
 
 	cb.notify_link_chg = cgx_lmac_postevent; /* link change call back */
@@ -244,9 +244,11 @@ static void cgx_lmac_event_handler_init(struct rvu *rvu)
 					cgx, lmac);
 		}
 	}
+
+	return 0;
 }
 
-void rvu_cgx_wq_destroy(struct rvu *rvu)
+static void rvu_cgx_wq_destroy(struct rvu *rvu)
 {
 	if (rvu->cgx_evh_wq) {
 		flush_workqueue(rvu->cgx_evh_wq);
@@ -255,9 +257,9 @@ void rvu_cgx_wq_destroy(struct rvu *rvu)
 	}
 }
 
-int rvu_cgx_probe(struct rvu *rvu)
+int rvu_cgx_init(struct rvu *rvu)
 {
-	int i, err;
+	int cgx, err;
 
 	/* find available cgx ports */
 	rvu->cgx_cnt = cgx_get_cgx_cnt();
@@ -272,8 +274,8 @@ int rvu_cgx_probe(struct rvu *rvu)
 		return -ENOMEM;
 
 	/* Initialize the cgxdata table */
-	for (i = 0; i < rvu->cgx_cnt; i++)
-		rvu->cgx_idmap[i] = cgx_get_pdata(i);
+	for (cgx = 0; cgx < rvu->cgx_cnt; cgx++)
+		rvu->cgx_idmap[cgx] = cgx_get_pdata(cgx);
 
 	/* Map CGX LMAC interfaces to RVU PFs */
 	err = rvu_map_cgx_lmac_pf(rvu);
@@ -281,7 +283,16 @@ int rvu_cgx_probe(struct rvu *rvu)
 		return err;
 
 	/* Register for CGX events */
-	cgx_lmac_event_handler_init(rvu);
+	err = cgx_lmac_event_handler_init(rvu);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int rvu_cgx_exit(struct rvu *rvu)
+{
+	rvu_cgx_wq_destroy(rvu);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 12e4c9ab2eb3244f9f90b595bb4b988e4d423c62 Mon Sep 17 00:00:00 2001
From: Linu Cherian <lcherian@marvell.com>
Date: Thu, 22 Nov 2018 17:18:35 +0530
Subject: octeontx2-af: Handle non-contiguous CGX LMAC interfaces

For this, cgx_id(struct cgx) definition has been changed to
reflect cgx port id instead of device instance id.
Now cgx_id can be directly used as channel offset for NPC configuration.
Assumptions on contiguous cgx port ids has been removed from
nix_calibrate_x2p as well.

As a side effect, allocation of conversion tables that were based
on cgx count are changed to cgx port id max value.
Tables would return NULL for invalid cgx ports.

Signed-off-by: Linu Cherian <lcherian@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c    | 18 ++++++----
 drivers/net/ethernet/marvell/octeontx2/af/cgx.h    |  4 +--
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  2 +-
 .../net/ethernet/marvell/octeontx2/af/rvu_cgx.c    | 38 ++++++++++++----------
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    |  6 ++--
 5 files changed, 40 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 12db256c8c9f..5c9736d7571e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -92,17 +92,21 @@ static inline struct lmac *lmac_pdata(u8 lmac_id, struct cgx *cgx)
 	return cgx->lmac_idmap[lmac_id];
 }
 
-int cgx_get_cgx_cnt(void)
+int cgx_get_cgxcnt_max(void)
 {
 	struct cgx *cgx_dev;
-	int count = 0;
+	int idmax = -ENODEV;
 
 	list_for_each_entry(cgx_dev, &cgx_list, cgx_list)
-		count++;
+		if (cgx_dev->cgx_id > idmax)
+			idmax = cgx_dev->cgx_id;
 
-	return count;
+	if (idmax < 0)
+		return 0;
+
+	return idmax + 1;
 }
-EXPORT_SYMBOL(cgx_get_cgx_cnt);
+EXPORT_SYMBOL(cgx_get_cgxcnt_max);
 
 int cgx_get_lmac_cnt(void *cgxd)
 {
@@ -679,8 +683,10 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_release_regions;
 	}
 
+	cgx->cgx_id = (pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM) >> 24)
+		& CGX_ID_MASK;
+
 	list_add(&cgx->cgx_list, &cgx_list);
-	cgx->cgx_id = cgx_get_cgx_cnt() - 1;
 
 	cgx_link_usertable_init();
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index 8d7d77b3035c..5f186e4307b1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -20,7 +20,7 @@
 /* PCI BAR nos */
 #define PCI_CFG_REG_BAR_NUM		0
 
-#define MAX_CGX				3
+#define CGX_ID_MASK			0x7
 #define MAX_LMAC_PER_CGX		4
 #define CGX_FIFO_LEN			65536 /* 64K for both Rx & Tx */
 #define CGX_OFFSET(x)			((x) * MAX_LMAC_PER_CGX)
@@ -95,7 +95,7 @@ struct cgx_event_cb {
 
 extern struct pci_driver cgx_driver;
 
-int cgx_get_cgx_cnt(void);
+int cgx_get_cgxcnt_max(void);
 int cgx_get_lmac_cnt(void *cgxd);
 void *cgx_get_pdata(int cgx_id);
 int cgx_set_pkind(void *cgxd, u8 lmac_id, int pkind);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 96049e275335..ae8e2e206c87 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -226,7 +226,7 @@ struct rvu {
 	/* CGX */
 #define PF_CGXMAP_BASE		1 /* PF 0 is reserved for RVU PF */
 	u8			cgx_mapped_pfs;
-	u8			cgx_cnt; /* available cgx ports */
+	u8			cgx_cnt_max;	 /* CGX port count max */
 	u8			*pf2cgxlmac_map; /* pf to cgx_lmac map */
 	u16			*cgxlmac2pf_map; /* bitmap of mapped pfs for
 						  * every cgx lmac port
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 1f1bc837bcd6..d5cca78d5d47 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -52,7 +52,7 @@ static inline u8 cgxlmac_id_to_bmap(u8 cgx_id, u8 lmac_id)
 
 void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu)
 {
-	if (cgx_id >= rvu->cgx_cnt)
+	if (cgx_id >= rvu->cgx_cnt_max)
 		return NULL;
 
 	return rvu->cgx_idmap[cgx_id];
@@ -61,38 +61,40 @@ void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu)
 static int rvu_map_cgx_lmac_pf(struct rvu *rvu)
 {
 	struct npc_pkind *pkind = &rvu->hw->pkind;
-	int cgx_cnt = rvu->cgx_cnt;
+	int cgx_cnt_max = rvu->cgx_cnt_max;
 	int cgx, lmac_cnt, lmac;
 	int pf = PF_CGXMAP_BASE;
 	int size, free_pkind;
 
-	if (!cgx_cnt)
+	if (!cgx_cnt_max)
 		return 0;
 
-	if (cgx_cnt > 0xF || MAX_LMAC_PER_CGX > 0xF)
+	if (cgx_cnt_max > 0xF || MAX_LMAC_PER_CGX > 0xF)
 		return -EINVAL;
 
 	/* Alloc map table
 	 * An additional entry is required since PF id starts from 1 and
 	 * hence entry at offset 0 is invalid.
 	 */
-	size = (cgx_cnt * MAX_LMAC_PER_CGX + 1) * sizeof(u8);
-	rvu->pf2cgxlmac_map = devm_kzalloc(rvu->dev, size, GFP_KERNEL);
+	size = (cgx_cnt_max * MAX_LMAC_PER_CGX + 1) * sizeof(u8);
+	rvu->pf2cgxlmac_map = devm_kmalloc(rvu->dev, size, GFP_KERNEL);
 	if (!rvu->pf2cgxlmac_map)
 		return -ENOMEM;
 
-	/* Initialize offset 0 with an invalid cgx and lmac id */
-	rvu->pf2cgxlmac_map[0] = 0xFF;
+	/* Initialize all entries with an invalid cgx and lmac id */
+	memset(rvu->pf2cgxlmac_map, 0xFF, size);
 
 	/* Reverse map table */
 	rvu->cgxlmac2pf_map = devm_kzalloc(rvu->dev,
-				  cgx_cnt * MAX_LMAC_PER_CGX * sizeof(u16),
+				  cgx_cnt_max * MAX_LMAC_PER_CGX * sizeof(u16),
 				  GFP_KERNEL);
 	if (!rvu->cgxlmac2pf_map)
 		return -ENOMEM;
 
 	rvu->cgx_mapped_pfs = 0;
-	for (cgx = 0; cgx < cgx_cnt; cgx++) {
+	for (cgx = 0; cgx < cgx_cnt_max; cgx++) {
+		if (!rvu_cgx_pdata(cgx, rvu))
+			continue;
 		lmac_cnt = cgx_get_lmac_cnt(rvu_cgx_pdata(cgx, rvu));
 		for (lmac = 0; lmac < lmac_cnt; lmac++, pf++) {
 			rvu->pf2cgxlmac_map[pf] = cgxlmac_id_to_bmap(cgx, lmac);
@@ -234,7 +236,7 @@ static int cgx_lmac_event_handler_init(struct rvu *rvu)
 	cb.notify_link_chg = cgx_lmac_postevent; /* link change call back */
 	cb.data = rvu;
 
-	for (cgx = 0; cgx < rvu->cgx_cnt; cgx++) {
+	for (cgx = 0; cgx <= rvu->cgx_cnt_max; cgx++) {
 		cgxd = rvu_cgx_pdata(cgx, rvu);
 		for (lmac = 0; lmac < cgx_get_lmac_cnt(cgxd); lmac++) {
 			err = cgx_lmac_evh_register(&cb, cgxd, lmac);
@@ -261,20 +263,22 @@ int rvu_cgx_init(struct rvu *rvu)
 {
 	int cgx, err;
 
-	/* find available cgx ports */
-	rvu->cgx_cnt = cgx_get_cgx_cnt();
-	if (!rvu->cgx_cnt) {
+	/* CGX port id starts from 0 and are not necessarily contiguous
+	 * Hence we allocate resources based on the maximum port id value.
+	 */
+	rvu->cgx_cnt_max = cgx_get_cgxcnt_max();
+	if (!rvu->cgx_cnt_max) {
 		dev_info(rvu->dev, "No CGX devices found!\n");
 		return -ENODEV;
 	}
 
-	rvu->cgx_idmap = devm_kzalloc(rvu->dev, rvu->cgx_cnt * sizeof(void *),
-				      GFP_KERNEL);
+	rvu->cgx_idmap = devm_kzalloc(rvu->dev, rvu->cgx_cnt_max *
+				      sizeof(void *), GFP_KERNEL);
 	if (!rvu->cgx_idmap)
 		return -ENOMEM;
 
 	/* Initialize the cgxdata table */
-	for (cgx = 0; cgx < rvu->cgx_cnt; cgx++)
+	for (cgx = 0; cgx < rvu->cgx_cnt_max; cgx++)
 		rvu->cgx_idmap[cgx] = cgx_get_pdata(cgx);
 
 	/* Map CGX LMAC interfaces to RVU PFs */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index b7998f6be386..962a82f7d141 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -2107,8 +2107,10 @@ static int nix_calibrate_x2p(struct rvu *rvu, int blkaddr)
 
 	status = rvu_read64(rvu, blkaddr, NIX_AF_STATUS);
 	/* Check if CGX devices are ready */
-	for (idx = 0; idx < cgx_get_cgx_cnt(); idx++) {
-		if (status & (BIT_ULL(16 + idx)))
+	for (idx = 0; idx < rvu->cgx_cnt_max; idx++) {
+		/* Skip when cgx port is not available */
+		if (!rvu_cgx_pdata(idx, rvu) ||
+		    (status & (BIT_ULL(16 + idx))))
 			continue;
 		dev_err(rvu->dev,
 			"CGX%d didn't respond to NIX X2P calibration\n", idx);
-- 
cgit v1.2.3


From c929323609aefdd6da40d02860c2d59fb4a9d421 Mon Sep 17 00:00:00 2001
From: Linu Cherian <lcherian@marvell.com>
Date: Thu, 22 Nov 2018 17:18:36 +0530
Subject: octeontx2-af: Unregister cgx event callbacks gracefully

Added provision to unregister cgx event callbacks.
This enables the exit path to ensure event callbacks are
unregistered before workqueues get destroyed.

Signed-off-by: Linu Cherian <lcherian@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c    | 29 +++++++++++++++++++++-
 drivers/net/ethernet/marvell/octeontx2/af/cgx.h    |  1 +
 .../net/ethernet/marvell/octeontx2/af/rvu_cgx.c    | 14 +++++++++++
 3 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 5c9736d7571e..5776978a4647 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -31,6 +31,7 @@
  * @resp:		command response
  * @link_info:		link related information
  * @event_cb:		callback for linkchange events
+ * @event_cb_lock:	lock for serializing callback with unregister
  * @cmd_pend:		flag set before new command is started
  *			flag cleared after command response is received
  * @cgx:		parent cgx port
@@ -43,6 +44,7 @@ struct lmac {
 	u64 resp;
 	struct cgx_link_user_info link_info;
 	struct cgx_event_cb event_cb;
+	spinlock_t event_cb_lock;
 	bool cmd_pend;
 	struct cgx *cgx;
 	u8 lmac_id;
@@ -449,6 +451,9 @@ static inline void cgx_link_change_handler(u64 lstat,
 	lmac->link_info = event.link_uinfo;
 	linfo = &lmac->link_info;
 
+	/* Ensure callback doesn't get unregistered until we finish it */
+	spin_lock(&lmac->event_cb_lock);
+
 	if (!lmac->event_cb.notify_link_chg) {
 		dev_dbg(dev, "cgx port %d:%d Link change handler null",
 			cgx->cgx_id, lmac->lmac_id);
@@ -459,11 +464,13 @@ static inline void cgx_link_change_handler(u64 lstat,
 		dev_info(dev, "cgx port %d:%d Link is %s %d Mbps\n",
 			 cgx->cgx_id, lmac->lmac_id,
 			 linfo->link_up ? "UP" : "DOWN", linfo->speed);
-		return;
+		goto err;
 	}
 
 	if (lmac->event_cb.notify_link_chg(&event, lmac->event_cb.data))
 		dev_err(dev, "event notification failure\n");
+err:
+	spin_unlock(&lmac->event_cb_lock);
 }
 
 static inline bool cgx_cmdresp_is_linkevent(u64 event)
@@ -552,6 +559,25 @@ int cgx_lmac_evh_register(struct cgx_event_cb *cb, void *cgxd, int lmac_id)
 }
 EXPORT_SYMBOL(cgx_lmac_evh_register);
 
+int cgx_lmac_evh_unregister(void *cgxd, int lmac_id)
+{
+	struct lmac *lmac;
+	unsigned long flags;
+	struct cgx *cgx = cgxd;
+
+	lmac = lmac_pdata(lmac_id, cgx);
+	if (!lmac)
+		return -ENODEV;
+
+	spin_lock_irqsave(&lmac->event_cb_lock, flags);
+	lmac->event_cb.notify_link_chg = NULL;
+	lmac->event_cb.data = NULL;
+	spin_unlock_irqrestore(&lmac->event_cb_lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(cgx_lmac_evh_unregister);
+
 static inline int cgx_fwi_read_version(u64 *resp, struct cgx *cgx)
 {
 	u64 req = 0;
@@ -606,6 +632,7 @@ static int cgx_lmac_init(struct cgx *cgx)
 		lmac->cgx = cgx;
 		init_waitqueue_head(&lmac->wq_cmd_cmplt);
 		mutex_init(&lmac->cmd_lock);
+		spin_lock_init(&lmac->event_cb_lock);
 		err = request_irq(pci_irq_vector(cgx->pdev,
 						 CGX_LMAC_FWI + i * 9),
 				   cgx_fwi_event_handler, 0, lmac->name, lmac);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index 5f186e4307b1..a2bff00b17cf 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -100,6 +100,7 @@ int cgx_get_lmac_cnt(void *cgxd);
 void *cgx_get_pdata(int cgx_id);
 int cgx_set_pkind(void *cgxd, u8 lmac_id, int pkind);
 int cgx_lmac_evh_register(struct cgx_event_cb *cb, void *cgxd, int lmac_id);
+int cgx_lmac_evh_unregister(void *cgxd, int lmac_id);
 int cgx_get_tx_stats(void *cgxd, int lmac_id, int idx, u64 *tx_stat);
 int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat);
 int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index d5cca78d5d47..66d94df9b8a2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -296,6 +296,20 @@ int rvu_cgx_init(struct rvu *rvu)
 
 int rvu_cgx_exit(struct rvu *rvu)
 {
+	int cgx, lmac;
+	void *cgxd;
+
+	for (cgx = 0; cgx <= rvu->cgx_cnt_max; cgx++) {
+		cgxd = rvu_cgx_pdata(cgx, rvu);
+		if (!cgxd)
+			continue;
+		for (lmac = 0; lmac < cgx_get_lmac_cnt(cgxd); lmac++)
+			cgx_lmac_evh_unregister(cgxd, lmac);
+	}
+
+	/* Ensure event handler unregister is completed */
+	mb();
+
 	rvu_cgx_wq_destroy(rvu);
 	return 0;
 }
-- 
cgit v1.2.3


From d3b2b9ab1ef2ca1d883f3729ceb54503193b7958 Mon Sep 17 00:00:00 2001
From: Linu Cherian <lcherian@marvell.com>
Date: Thu, 22 Nov 2018 17:18:37 +0530
Subject: octeontx2-af: Bringup CGX LMAC links by default

- Added new CGX firmware interface API for sending link up/down
  commands

- Do link up for cgx lmac ports by default at the time of CGX
  driver probe. Since cgx link up in driver probe affects the
  Linux boot time, linkup procedure is kept threaded using
  workqueues.
  For this, a new cgx API cgx_lmac_linkup_start has been added.

Signed-off-by: Linu Cherian <lcherian@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c    | 61 ++++++++++++++++++++++
 drivers/net/ethernet/marvell/octeontx2/af/cgx.h    |  1 +
 .../net/ethernet/marvell/octeontx2/af/rvu_cgx.c    | 20 +++++++
 3 files changed, 82 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 5776978a4647..4c94571e03eb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -57,6 +57,8 @@ struct cgx {
 	u8			cgx_id;
 	u8			lmac_count;
 	struct lmac		*lmac_idmap[MAX_LMAC_PER_CGX];
+	struct			work_struct cgx_cmd_work;
+	struct			workqueue_struct *cgx_cmd_workq;
 	struct list_head	cgx_list;
 };
 
@@ -68,6 +70,9 @@ static u32 cgx_speed_mbps[CGX_LINK_SPEED_MAX];
 /* Convert firmware lmac type encoding to string */
 static char *cgx_lmactype_string[LMAC_MODE_MAX];
 
+/* CGX PHY management internal APIs */
+static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool en);
+
 /* Supported devices */
 static const struct pci_device_id cgx_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_CGX) },
@@ -578,6 +583,19 @@ int cgx_lmac_evh_unregister(void *cgxd, int lmac_id)
 }
 EXPORT_SYMBOL(cgx_lmac_evh_unregister);
 
+static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool enable)
+{
+	u64 req = 0;
+	u64 resp;
+
+	if (enable)
+		req = FIELD_SET(CMDREG_ID, CGX_CMD_LINK_BRING_UP, req);
+	else
+		req = FIELD_SET(CMDREG_ID, CGX_CMD_LINK_BRING_DOWN, req);
+
+	return cgx_fwi_cmd_generic(req, &resp, cgx, lmac_id);
+}
+
 static inline int cgx_fwi_read_version(u64 *resp, struct cgx *cgx)
 {
 	u64 req = 0;
@@ -611,6 +629,34 @@ static int cgx_lmac_verify_fwi_version(struct cgx *cgx)
 		return 0;
 }
 
+static void cgx_lmac_linkup_work(struct work_struct *work)
+{
+	struct cgx *cgx = container_of(work, struct cgx, cgx_cmd_work);
+	struct device *dev = &cgx->pdev->dev;
+	int i, err;
+
+	/* Do Link up for all the lmacs */
+	for (i = 0; i < cgx->lmac_count; i++) {
+		err = cgx_fwi_link_change(cgx, i, true);
+		if (err)
+			dev_info(dev, "cgx port %d:%d Link up command failed\n",
+				 cgx->cgx_id, i);
+	}
+}
+
+int cgx_lmac_linkup_start(void *cgxd)
+{
+	struct cgx *cgx = cgxd;
+
+	if (!cgx)
+		return -ENODEV;
+
+	queue_work(cgx->cgx_cmd_workq, &cgx->cgx_cmd_work);
+
+	return 0;
+}
+EXPORT_SYMBOL(cgx_lmac_linkup_start);
+
 static int cgx_lmac_init(struct cgx *cgx)
 {
 	struct lmac *lmac;
@@ -655,6 +701,12 @@ static int cgx_lmac_exit(struct cgx *cgx)
 	struct lmac *lmac;
 	int i;
 
+	if (cgx->cgx_cmd_workq) {
+		flush_workqueue(cgx->cgx_cmd_workq);
+		destroy_workqueue(cgx->cgx_cmd_workq);
+		cgx->cgx_cmd_workq = NULL;
+	}
+
 	/* Free all lmac related resources */
 	for (i = 0; i < cgx->lmac_count; i++) {
 		lmac = cgx->lmac_idmap[i];
@@ -713,6 +765,15 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	cgx->cgx_id = (pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM) >> 24)
 		& CGX_ID_MASK;
 
+	/* init wq for processing linkup requests */
+	INIT_WORK(&cgx->cgx_cmd_work, cgx_lmac_linkup_work);
+	cgx->cgx_cmd_workq = alloc_workqueue("cgx_cmd_workq", 0, 0);
+	if (!cgx->cgx_cmd_workq) {
+		dev_err(dev, "alloc workqueue failed for cgx cmd");
+		err = -ENOMEM;
+		goto err_release_regions;
+	}
+
 	list_add(&cgx->cgx_list, &cgx_list);
 
 	cgx_link_usertable_init();
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index a2bff00b17cf..8c2be8493321 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -110,4 +110,5 @@ void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable);
 int cgx_lmac_internal_loopback(void *cgxd, int lmac_id, bool enable);
 int cgx_get_link_info(void *cgxd, int lmac_id,
 		      struct cgx_link_user_info *linfo);
+int cgx_lmac_linkup_start(void *cgxd);
 #endif /* CGX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 66d94df9b8a2..7d7133c5f799 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -238,6 +238,8 @@ static int cgx_lmac_event_handler_init(struct rvu *rvu)
 
 	for (cgx = 0; cgx <= rvu->cgx_cnt_max; cgx++) {
 		cgxd = rvu_cgx_pdata(cgx, rvu);
+		if (!cgxd)
+			continue;
 		for (lmac = 0; lmac < cgx_get_lmac_cnt(cgxd); lmac++) {
 			err = cgx_lmac_evh_register(&cb, cgxd, lmac);
 			if (err)
@@ -262,6 +264,7 @@ static void rvu_cgx_wq_destroy(struct rvu *rvu)
 int rvu_cgx_init(struct rvu *rvu)
 {
 	int cgx, err;
+	void *cgxd;
 
 	/* CGX port id starts from 0 and are not necessarily contiguous
 	 * Hence we allocate resources based on the maximum port id value.
@@ -291,6 +294,23 @@ int rvu_cgx_init(struct rvu *rvu)
 	if (err)
 		return err;
 
+	/* Ensure event handler registration is completed, before
+	 * we turn on the links
+	 */
+	mb();
+
+	/* Do link up for all CGX ports */
+	for (cgx = 0; cgx <= rvu->cgx_cnt_max; cgx++) {
+		cgxd = rvu_cgx_pdata(cgx, rvu);
+		if (!cgxd)
+			continue;
+		err = cgx_lmac_linkup_start(cgxd);
+		if (err)
+			dev_err(rvu->dev,
+				"Link up process failed to start on cgx %d\n",
+				cgx);
+	}
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 21f49468466a41340ea389c25770dd38b7cbc748 Mon Sep 17 00:00:00 2001
From: Quentin Schulz <quentin.schulz@bootlin.com>
Date: Thu, 22 Nov 2018 14:24:32 +0100
Subject: net: phy: vitesse: remove duplicate support for VSC8574

A more featureful support for VSC8574 was recently added to the
Microsemi (mscc.c) driver. I checked that features supported in the
Vitesse driver are also supported in the Microsemi driver.

Signed-off-by: Quentin Schulz <quentin.schulz@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/vitesse.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 4ca513feba0e..0646af458f6a 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -70,7 +70,6 @@
 #define PHY_ID_VSC8244			0x000fc6c0
 #define PHY_ID_VSC8514			0x00070670
 #define PHY_ID_VSC8572			0x000704d0
-#define PHY_ID_VSC8574			0x000704a0
 #define PHY_ID_VSC8601			0x00070420
 #define PHY_ID_VSC7385			0x00070450
 #define PHY_ID_VSC7388			0x00070480
@@ -303,7 +302,6 @@ static int vsc82xx_config_intr(struct phy_device *phydev)
 			 phydev->drv->phy_id == PHY_ID_VSC8244 ||
 			 phydev->drv->phy_id == PHY_ID_VSC8514 ||
 			 phydev->drv->phy_id == PHY_ID_VSC8572 ||
-			 phydev->drv->phy_id == PHY_ID_VSC8574 ||
 			 phydev->drv->phy_id == PHY_ID_VSC8601) ?
 				MII_VSC8244_IMASK_MASK :
 				MII_VSC8221_IMASK_MASK);
@@ -430,15 +428,6 @@ static struct phy_driver vsc82xx_driver[] = {
 	.config_aneg    = &vsc82x4_config_aneg,
 	.ack_interrupt  = &vsc824x_ack_interrupt,
 	.config_intr    = &vsc82xx_config_intr,
-}, {
-	.phy_id         = PHY_ID_VSC8574,
-	.name           = "Vitesse VSC8574",
-	.phy_id_mask    = 0x000ffff0,
-	.features       = PHY_GBIT_FEATURES,
-	.config_init    = &vsc824x_config_init,
-	.config_aneg    = &vsc82x4_config_aneg,
-	.ack_interrupt  = &vsc824x_ack_interrupt,
-	.config_intr    = &vsc82xx_config_intr,
 }, {
 	.phy_id         = PHY_ID_VSC8601,
 	.name           = "Vitesse VSC8601",
@@ -519,7 +508,6 @@ static struct mdio_device_id __maybe_unused vitesse_tbl[] = {
 	{ PHY_ID_VSC8244, 0x000fffc0 },
 	{ PHY_ID_VSC8514, 0x000ffff0 },
 	{ PHY_ID_VSC8572, 0x000ffff0 },
-	{ PHY_ID_VSC8574, 0x000ffff0 },
 	{ PHY_ID_VSC7385, 0x000ffff0 },
 	{ PHY_ID_VSC7388, 0x000ffff0 },
 	{ PHY_ID_VSC7395, 0x000ffff0 },
-- 
cgit v1.2.3


From 53b44cb9220e4ff7e3c091d91c94b2872b2f62d1 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 22 Nov 2018 21:27:19 +0800
Subject: net: cavium: clean up return value check in cavium_ptp_probe

ptp_clock_register never return NULL, so no need check this
in cavium_ptp_probe.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/common/cavium_ptp.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/cavium/common/cavium_ptp.c b/drivers/net/ethernet/cavium/common/cavium_ptp.c
index 6aeb1045c302..73632b843749 100644
--- a/drivers/net/ethernet/cavium/common/cavium_ptp.c
+++ b/drivers/net/ethernet/cavium/common/cavium_ptp.c
@@ -277,10 +277,6 @@ static int cavium_ptp_probe(struct pci_dev *pdev,
 	writeq(clock_comp, clock->reg_base + PTP_CLOCK_COMP);
 
 	clock->ptp_clock = ptp_clock_register(&clock->ptp_info, dev);
-	if (!clock->ptp_clock) {
-		err = -ENODEV;
-		goto error_stop;
-	}
 	if (IS_ERR(clock->ptp_clock)) {
 		err = PTR_ERR(clock->ptp_clock);
 		goto error_stop;
-- 
cgit v1.2.3


From b2292360bb2ae50be043c3806e84210f9027f6eb Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Thu, 22 Nov 2018 14:09:41 +0000
Subject: net: hns3: Add debugfs framework registration

Add the debugfs framework to the driver and create a debugfs
command interface for each device.

example command:
"echo queue info > cmd" Query the packet forwarding queue information.

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/Makefile       |   2 +-
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |   1 +
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 136 +++++++++++++++++++++
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    |  17 ++-
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    |   4 +
 5 files changed, 157 insertions(+), 3 deletions(-)
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c

diff --git a/drivers/net/ethernet/hisilicon/hns3/Makefile b/drivers/net/ethernet/hisilicon/hns3/Makefile
index 002534f12b66..d01bf536eb86 100644
--- a/drivers/net/ethernet/hisilicon/hns3/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/Makefile
@@ -9,6 +9,6 @@ obj-$(CONFIG_HNS3) += hns3vf/
 obj-$(CONFIG_HNS3) += hnae3.o
 
 obj-$(CONFIG_HNS3_ENET) += hns3.o
-hns3-objs = hns3_enet.o hns3_ethtool.o
+hns3-objs = hns3_enet.o hns3_ethtool.o hns3_debugfs.o
 
 hns3-$(CONFIG_HNS3_DCB) += hns3_dcbnl.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 4a39feaba8b2..f32f075991f5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -566,6 +566,7 @@ struct hnae3_handle {
 	u32 numa_node_mask;	/* for multi-chip support */
 
 	u8 netdev_flags;
+	struct dentry *hnae3_dbgfs;
 };
 
 #define hnae3_set_field(origin, mask, shift, val) \
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
new file mode 100644
index 000000000000..9d9ad11c3ea1
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (c) 2018-2019 Hisilicon Limited. */
+
+#include <linux/debugfs.h>
+#include <linux/device.h>
+
+#include "hnae3.h"
+#include "hns3_enet.h"
+
+#define HNS3_DBG_READ_LEN 256
+
+static struct dentry *hns3_dbgfs_root;
+
+static void hns3_dbg_help(struct hnae3_handle *h)
+{
+	dev_info(&h->pdev->dev, "available commands\n");
+	dev_info(&h->pdev->dev, "queue info [number]\n");
+	dev_info(&h->pdev->dev, "dump fd tcam\n");
+}
+
+static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
+				 size_t count, loff_t *ppos)
+{
+	int uncopy_bytes;
+	char *buf;
+	int len;
+
+	if (*ppos != 0)
+		return 0;
+
+	if (count < HNS3_DBG_READ_LEN)
+		return -ENOSPC;
+
+	buf = kzalloc(HNS3_DBG_READ_LEN, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	len = snprintf(buf, HNS3_DBG_READ_LEN, "%s\n",
+		       "Please echo help to cmd to get help information");
+	uncopy_bytes = copy_to_user(buffer, buf, len);
+
+	kfree(buf);
+
+	if (uncopy_bytes)
+		return -EFAULT;
+
+	return (*ppos = len);
+}
+
+static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
+				  size_t count, loff_t *ppos)
+{
+	struct hnae3_handle *handle = filp->private_data;
+	char *cmd_buf, *cmd_buf_tmp;
+	int uncopied_bytes;
+	int ret = 0;
+
+	if (*ppos != 0)
+		return 0;
+
+	cmd_buf = kzalloc(count + 1, GFP_KERNEL);
+	if (!cmd_buf)
+		return count;
+
+	uncopied_bytes = copy_from_user(cmd_buf, buffer, count);
+	if (uncopied_bytes) {
+		kfree(cmd_buf);
+		return -EFAULT;
+	}
+
+	cmd_buf[count] = '\0';
+
+	cmd_buf_tmp = strchr(cmd_buf, '\n');
+	if (cmd_buf_tmp) {
+		*cmd_buf_tmp = '\0';
+		count = cmd_buf_tmp - cmd_buf + 1;
+	}
+
+	if (strncmp(cmd_buf, "help", 4) == 0)
+		hns3_dbg_help(handle);
+
+	if (ret)
+		hns3_dbg_help(handle);
+
+	kfree(cmd_buf);
+	cmd_buf = NULL;
+
+	return count;
+}
+
+static const struct file_operations hns3_dbg_cmd_fops = {
+	.owner = THIS_MODULE,
+	.open  = simple_open,
+	.read  = hns3_dbg_cmd_read,
+	.write = hns3_dbg_cmd_write,
+};
+
+void hns3_dbg_init(struct hnae3_handle *handle)
+{
+	const char *name = pci_name(handle->pdev);
+	struct dentry *pfile;
+
+	handle->hnae3_dbgfs = debugfs_create_dir(name, hns3_dbgfs_root);
+	if (!handle->hnae3_dbgfs)
+		return;
+
+	pfile = debugfs_create_file("cmd", 0600, handle->hnae3_dbgfs, handle,
+				    &hns3_dbg_cmd_fops);
+	if (!pfile) {
+		debugfs_remove_recursive(handle->hnae3_dbgfs);
+		handle->hnae3_dbgfs = NULL;
+		dev_warn(&handle->pdev->dev, "create file for %s fail\n",
+			 name);
+	}
+}
+
+void hns3_dbg_uninit(struct hnae3_handle *handle)
+{
+	debugfs_remove_recursive(handle->hnae3_dbgfs);
+	handle->hnae3_dbgfs = NULL;
+}
+
+void hns3_dbg_register_debugfs(const char *debugfs_dir_name)
+{
+	hns3_dbgfs_root = debugfs_create_dir(debugfs_dir_name, NULL);
+	if (!hns3_dbgfs_root) {
+		pr_warn("Register debugfs for %s fail\n", debugfs_dir_name);
+		return;
+	}
+}
+
+void hns3_dbg_unregister_debugfs(void)
+{
+	debugfs_remove_recursive(hns3_dbgfs_root);
+	hns3_dbgfs_root = NULL;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 7f81db3df041..d1b2de2ecc89 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3620,6 +3620,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
 
 	hns3_dcbnl_setup(handle);
 
+	hns3_dbg_init(handle);
+
 	/* MTU range: (ETH_MIN_MTU(kernel default) - 9702) */
 	netdev->max_mtu = HNS3_MAX_MTU;
 
@@ -3676,6 +3678,8 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 
 	hns3_put_ring_config(priv);
 
+	hns3_dbg_uninit(handle);
+
 	priv->ring_data = NULL;
 
 out_netdev_free:
@@ -4245,15 +4249,23 @@ static int __init hns3_init_module(void)
 
 	INIT_LIST_HEAD(&client.node);
 
+	hns3_dbg_register_debugfs(hns3_driver_name);
+
 	ret = hnae3_register_client(&client);
 	if (ret)
-		return ret;
+		goto err_reg_client;
 
 	ret = pci_register_driver(&hns3_driver);
 	if (ret)
-		hnae3_unregister_client(&client);
+		goto err_reg_driver;
 
 	return ret;
+
+err_reg_driver:
+	hnae3_unregister_client(&client);
+err_reg_client:
+	hns3_dbg_unregister_debugfs();
+	return ret;
 }
 module_init(hns3_init_module);
 
@@ -4265,6 +4277,7 @@ static void __exit hns3_exit_module(void)
 {
 	pci_unregister_driver(&hns3_driver);
 	hnae3_unregister_client(&client);
+	hns3_dbg_unregister_debugfs();
 }
 module_exit(hns3_exit_module);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index bbf227ba30f8..4e4b48ba78e3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -683,4 +683,8 @@ void hns3_dcbnl_setup(struct hnae3_handle *handle);
 static inline void hns3_dcbnl_setup(struct hnae3_handle *handle) {}
 #endif
 
+void hns3_dbg_init(struct hnae3_handle *handle);
+void hns3_dbg_uninit(struct hnae3_handle *handle);
+void hns3_dbg_register_debugfs(const char *debugfs_dir_name);
+void hns3_dbg_unregister_debugfs(void);
 #endif
-- 
cgit v1.2.3


From 57ceee2ca71c653de7bf644a54a186a50105c5ac Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Thu, 22 Nov 2018 14:09:42 +0000
Subject: net: hns3: Add "queue info" query function

Query the queue information of the current NIC
such as BD size, queue header and tail pointer.

This  patch adds support for debugfs command:
echo queue info 1 > cmd

it can  print queue config information...

root@(none)# echo queue info 1 > cmd
hns3 0000:7d:00.0: queue info
hns3 0000:7d:00.0: RX(1) BASE ADD: 0x00000000ffb58000
hns3 0000:7d:00.0: RX(1) RING BD NUM: 127
hns3 0000:7d:00.0: RX(1) RING BD LEN: 2
hns3 0000:7d:00.0: RX(1) RING TAIL: 120
hns3 0000:7d:00.0: RX(1) RING HEAD: 0
hns3 0000:7d:00.0: RX(1) RING FBDNUM: 0
hns3 0000:7d:00.0: RX(1) RING PKTNUM: 0
hns3 0000:7d:00.0: TX(1) BASE ADD: 0x00000000fffd8000
hns3 0000:7d:00.0: TX(1) RING BD NUM: 127
hns3 0000:7d:00.0: TX(1) RING TC: 0
hns3 0000:7d:00.0: TX(1) RING TAIL: 2
hns3 0000:7d:00.0: TX(1) RING HEAD: 2
hns3 0000:7d:00.0: TX(1) RING FBDNUM: 0
hns3 0000:7d:00.0: TX(1) RING OFFSET: 0
hns3 0000:7d:00.0: TX(1) RING PKTNUM: 0
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 122 +++++++++++++++++++++
 1 file changed, 122 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 9d9ad11c3ea1..c0685b3ef5c9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -11,6 +11,120 @@
 
 static struct dentry *hns3_dbgfs_root;
 
+static int hns3_dbg_queue_info(struct hnae3_handle *h, char *cmd_buf)
+{
+	struct hns3_nic_priv *priv = h->priv;
+	struct hns3_nic_ring_data *ring_data;
+	struct hns3_enet_ring *ring;
+	u32 base_add_l, base_add_h;
+	u32 queue_num, queue_max;
+	u32 value, i = 0;
+	int cnt;
+
+	if (!priv->ring_data) {
+		dev_err(&h->pdev->dev, "ring_data is NULL\n");
+		return -EFAULT;
+	}
+
+	queue_max = h->kinfo.num_tqps;
+	cnt = kstrtouint(&cmd_buf[11], 0, &queue_num);
+	if (cnt)
+		queue_num = 0;
+	else
+		queue_max = queue_num + 1;
+
+	dev_info(&h->pdev->dev, "queue info\n");
+
+	if (queue_num >= h->kinfo.num_tqps) {
+		dev_err(&h->pdev->dev,
+			"Queue number(%u) is out of range(%u)\n", queue_num,
+			h->kinfo.num_tqps - 1);
+		return -EINVAL;
+	}
+
+	ring_data = priv->ring_data;
+	for (i = queue_num; i < queue_max; i++) {
+		/* Each cycle needs to determine whether the instance is reset,
+		 * to prevent reference to invalid memory. And need to ensure
+		 * that the following code is executed within 100ms.
+		 */
+		if (test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
+		    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
+			return -EPERM;
+
+		ring = ring_data[i + h->kinfo.num_tqps].ring;
+		base_add_h = readl_relaxed(ring->tqp->io_base +
+					   HNS3_RING_RX_RING_BASEADDR_H_REG);
+		base_add_l = readl_relaxed(ring->tqp->io_base +
+					   HNS3_RING_RX_RING_BASEADDR_L_REG);
+		dev_info(&h->pdev->dev, "RX(%d) BASE ADD: 0x%08x%08x\n", i,
+			 base_add_h, base_add_l);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_BD_NUM_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING BD NUM: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_BD_LEN_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING BD LEN: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_TAIL_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING TAIL: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_HEAD_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING HEAD: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_FBDNUM_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING FBDNUM: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_PKTNUM_RECORD_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING PKTNUM: %u\n", i, value);
+
+		ring = ring_data[i].ring;
+		base_add_h = readl_relaxed(ring->tqp->io_base +
+					   HNS3_RING_TX_RING_BASEADDR_H_REG);
+		base_add_l = readl_relaxed(ring->tqp->io_base +
+					   HNS3_RING_TX_RING_BASEADDR_L_REG);
+		dev_info(&h->pdev->dev, "TX(%d) BASE ADD: 0x%08x%08x\n", i,
+			 base_add_h, base_add_l);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_BD_NUM_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING BD NUM: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_TC_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING TC: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_TAIL_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING TAIL: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_HEAD_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING HEAD: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_FBDNUM_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING FBDNUM: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_OFFSET_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING OFFSET: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_PKTNUM_RECORD_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING PKTNUM: %u\n\n", i,
+			 value);
+	}
+
+	return 0;
+}
+
 static void hns3_dbg_help(struct hnae3_handle *h)
 {
 	dev_info(&h->pdev->dev, "available commands\n");
@@ -51,6 +165,7 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
 				  size_t count, loff_t *ppos)
 {
 	struct hnae3_handle *handle = filp->private_data;
+	struct hns3_nic_priv *priv  = handle->priv;
 	char *cmd_buf, *cmd_buf_tmp;
 	int uncopied_bytes;
 	int ret = 0;
@@ -58,6 +173,11 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
 	if (*ppos != 0)
 		return 0;
 
+	/* Judge if the instance is being reset. */
+	if (test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
+	    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
+		return 0;
+
 	cmd_buf = kzalloc(count + 1, GFP_KERNEL);
 	if (!cmd_buf)
 		return count;
@@ -78,6 +198,8 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
 
 	if (strncmp(cmd_buf, "help", 4) == 0)
 		hns3_dbg_help(handle);
+	else if (strncmp(cmd_buf, "queue info", 10) == 0)
+		ret = hns3_dbg_queue_info(handle, cmd_buf);
 
 	if (ret)
 		hns3_dbg_help(handle);
-- 
cgit v1.2.3


From 3c666b586af1c6ed6e352555aec38d2f9478cd47 Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Thu, 22 Nov 2018 14:09:43 +0000
Subject: net: hns3: Add "FD flow table" info query function

All the Flow Director rules are stored in tcam blocks.
For each bit of tcam entry, the match value
depends on two input value(x, y).

debugfs command:
echo dump fd tcam > cmd

Sample output:
root@(none)# echo dump fd tcam > cmd
hns3 0000:7d:00.0: read result tcam key x(31):
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 08000000
hns3 0000:7d:00.0: 00000600
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: read result tcam key y(31):
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: f7ff0000
hns3 0000:7d:00.0: 0000f900
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 00000000
hns3 0000:7d:00.0: 0000fff8
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  1 +
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |  2 +
 .../net/ethernet/hisilicon/hns3/hns3pf/Makefile    |  2 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 77 ++++++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    |  1 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  1 +
 6 files changed, 83 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index f32f075991f5..a1707b77c47f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -453,6 +453,7 @@ struct hnae3_ae_ops {
 				struct ethtool_rxnfc *cmd, u32 *rule_locs);
 	int (*restore_fd_rules)(struct hnae3_handle *handle);
 	void (*enable_fd)(struct hnae3_handle *handle, bool enable);
+	int (*dbg_run_cmd)(struct hnae3_handle *handle, char *cmd_buf);
 	pci_ers_result_t (*process_hw_error)(struct hnae3_ae_dev *ae_dev);
 	bool (*get_hw_reset_stat)(struct hnae3_handle *handle);
 	bool (*ae_dev_resetting)(struct hnae3_handle *handle);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index c0685b3ef5c9..82fe7b97408f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -200,6 +200,8 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
 		hns3_dbg_help(handle);
 	else if (strncmp(cmd_buf, "queue info", 10) == 0)
 		ret = hns3_dbg_queue_info(handle, cmd_buf);
+	else if (handle->ae_algo->ops->dbg_run_cmd)
+		ret = handle->ae_algo->ops->dbg_run_cmd(handle, cmd_buf);
 
 	if (ret)
 		hns3_dbg_help(handle);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
index 580e81743681..fffe8c1c45d3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
@@ -6,6 +6,6 @@
 ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
 
 obj-$(CONFIG_HNS3_HCLGE) += hclge.o
-hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o
+hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o  hclge_debugfs.o
 
 hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
new file mode 100644
index 000000000000..cf1355b01f9c
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (c) 2018-2019 Hisilicon Limited. */
+
+#include <linux/device.h>
+
+#include "hclge_cmd.h"
+#include "hclge_main.h"
+#include "hnae3.h"
+
+static void hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage,
+				   bool sel_x, u32 loc)
+{
+	struct hclge_fd_tcam_config_1_cmd *req1;
+	struct hclge_fd_tcam_config_2_cmd *req2;
+	struct hclge_fd_tcam_config_3_cmd *req3;
+	struct hclge_desc desc[3];
+	int ret, i;
+	u32 *req;
+
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_FD_TCAM_OP, true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_FD_TCAM_OP, true);
+	desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_FD_TCAM_OP, true);
+
+	req1 = (struct hclge_fd_tcam_config_1_cmd *)desc[0].data;
+	req2 = (struct hclge_fd_tcam_config_2_cmd *)desc[1].data;
+	req3 = (struct hclge_fd_tcam_config_3_cmd *)desc[2].data;
+
+	req1->stage  = stage;
+	req1->xy_sel = sel_x ? 1 : 0;
+	req1->index  = cpu_to_le32(loc);
+
+	ret = hclge_cmd_send(&hdev->hw, desc, 3);
+	if (ret)
+		return;
+
+	dev_info(&hdev->pdev->dev, " read result tcam key %s(%u):\n",
+		 sel_x ? "x" : "y", loc);
+
+	req = (u32 *)req1->tcam_data;
+	for (i = 0; i < 2; i++)
+		dev_info(&hdev->pdev->dev, "%08x\n", *req++);
+
+	req = (u32 *)req2->tcam_data;
+	for (i = 0; i < 6; i++)
+		dev_info(&hdev->pdev->dev, "%08x\n", *req++);
+
+	req = (u32 *)req3->tcam_data;
+	for (i = 0; i < 5; i++)
+		dev_info(&hdev->pdev->dev, "%08x\n", *req++);
+}
+
+static void hclge_dbg_fd_tcam(struct hclge_dev *hdev)
+{
+	u32 i;
+
+	for (i = 0; i < hdev->fd_cfg.rule_num[0]; i++) {
+		hclge_dbg_fd_tcam_read(hdev, 0, true, i);
+		hclge_dbg_fd_tcam_read(hdev, 0, false, i);
+	}
+}
+
+int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	if (strncmp(cmd_buf, "dump fd tcam", 12) == 0) {
+		hclge_dbg_fd_tcam(hdev);
+	} else {
+		dev_info(&hdev->pdev->dev, "unknown command\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index f78b8e188443..696cb53013bc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7826,6 +7826,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.get_fd_all_rules = hclge_get_all_rules,
 	.restore_fd_rules = hclge_restore_fd_entries,
 	.enable_fd = hclge_enable_fd,
+	.dbg_run_cmd = hclge_dbg_run_cmd,
 	.process_hw_error = hclge_process_ras_hw_error,
 	.get_hw_reset_stat = hclge_get_hw_reset_stat,
 	.ae_dev_resetting = hclge_ae_dev_resetting,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 5f24dd41d7eb..4122ad1aab1f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -814,4 +814,5 @@ int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id);
 int hclge_vport_start(struct hclge_vport *vport);
 void hclge_vport_stop(struct hclge_vport *vport);
 int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu);
+int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf);
 #endif
-- 
cgit v1.2.3


From 2849d4e7a1beb483e9ebab3904f03010c0bc1daf Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Thu, 22 Nov 2018 14:09:44 +0000
Subject: net: hns3: Add "tc config" info query function

This patch prints tc config information.

debugfs command:
echo dump tc > cmd

Sample Output:
root@(none)# echo dump tc > cmd
hns3 0000:7d:00.0: weight_offset: 14
hns3 0000:7d:00.0: tc(0): no sp mode
hns3 0000:7d:00.0: tc(1): no sp mode
hns3 0000:7d:00.0: tc(2): no sp mode
hns3 0000:7d:00.0: tc(3): no sp mode
hns3 0000:7d:00.0: tc(4): no sp mode
hns3 0000:7d:00.0: tc(5): no sp mode
hns3 0000:7d:00.0: tc(6): no sp mode
hns3 0000:7d:00.0: tc(7): no sp mode
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |  1 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |  1 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 40 ++++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h  |  6 ++++
 4 files changed, 48 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 82fe7b97408f..8acccfbd3481 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -130,6 +130,7 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "available commands\n");
 	dev_info(&h->pdev->dev, "queue info [number]\n");
 	dev_info(&h->pdev->dev, "dump fd tcam\n");
+	dev_info(&h->pdev->dev, "dump tc\n");
 }
 
 static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index aef044d08b11..2b90410eeac2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -126,6 +126,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_TM_PRI_SCH_MODE_CFG   = 0x0813,
 	HCLGE_OPC_TM_QS_SCH_MODE_CFG    = 0x0814,
 	HCLGE_OPC_TM_BP_TO_QSET_MAPPING = 0x0815,
+	HCLGE_OPC_ETS_TC_WEIGHT		= 0x0843,
 
 	/* Packet buffer allocate commands */
 	HCLGE_OPC_TX_BUFF_ALLOC		= 0x0901,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index cf1355b01f9c..050b90e95e00 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -5,8 +5,46 @@
 
 #include "hclge_cmd.h"
 #include "hclge_main.h"
+#include "hclge_tm.h"
 #include "hnae3.h"
 
+static void hclge_title_idx_print(struct hclge_dev *hdev, bool flag, int index,
+				  char *title_buf, char *true_buf,
+				  char *false_buf)
+{
+	if (flag)
+		dev_info(&hdev->pdev->dev, "%s(%d): %s\n", title_buf, index,
+			 true_buf);
+	else
+		dev_info(&hdev->pdev->dev, "%s(%d): %s\n", title_buf, index,
+			 false_buf);
+}
+
+static void hclge_dbg_dump_tc(struct hclge_dev *hdev)
+{
+	struct hclge_ets_tc_weight_cmd *ets_weight;
+	struct hclge_desc desc;
+	int i, ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ETS_TC_WEIGHT, true);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev, "dump tc fail, status is %d.\n", ret);
+		return;
+	}
+
+	ets_weight = (struct hclge_ets_tc_weight_cmd *)desc.data;
+
+	dev_info(&hdev->pdev->dev, "dump tc\n");
+	dev_info(&hdev->pdev->dev, "weight_offset: %u\n",
+		 ets_weight->weight_offset);
+
+	for (i = 0; i < HNAE3_MAX_TC; i++)
+		hclge_title_idx_print(hdev, ets_weight->tc_weight[i], i,
+				      "tc", "no sp mode", "sp mode");
+}
+
 static void hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage,
 				   bool sel_x, u32 loc)
 {
@@ -68,6 +106,8 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
 
 	if (strncmp(cmd_buf, "dump fd tcam", 12) == 0) {
 		hclge_dbg_fd_tcam(hdev);
+	} else if (strncmp(cmd_buf, "dump tc", 7) == 0) {
+		hclge_dbg_dump_tc(hdev);
 	} else {
 		dev_info(&hdev->pdev->dev, "unknown command\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 4bd916a77ae2..9c6192c46aa6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -55,6 +55,12 @@ struct hclge_qs_weight_cmd {
 	u8 dwrr;
 };
 
+struct hclge_ets_tc_weight_cmd {
+	u8 tc_weight[HNAE3_MAX_TC];
+	u8 weight_offset;
+	u8 rsvd[15];
+};
+
 #define HCLGE_TM_SHAP_IR_B_MSK  GENMASK(7, 0)
 #define HCLGE_TM_SHAP_IR_B_LSH	0
 #define HCLGE_TM_SHAP_IR_U_MSK  GENMASK(11, 8)
-- 
cgit v1.2.3


From 96227f4cd701ffb60b66ad22b0ff716bfe3e1317 Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Thu, 22 Nov 2018 14:09:45 +0000
Subject: net: hns3: Add "tm config" info query function

This patch prints Transmit Module's Traffic sched
related config information.

debugfs command:
echo dump tm > cmd

Sample output:
root@(none)# echo dump tm > cmd
hns3 0000:7d:00.0: dump tm
hns3 0000:7d:00.0: PG_TO_PRI gp_id: 0
hns3 0000:7d:00.0: PG_TO_PRI map: 0x1
hns3 0000:7d:00.0: QS_TO_PRI qs_id: 0
hns3 0000:7d:00.0: QS_TO_PRI priority: 0
hns3 0000:7d:00.0: QS_TO_PRI link_vld: 1
hns3 0000:7d:00.0: NQ_TO_QS nq_id: 0
hns3 0000:7d:00.0: NQ_TO_QS qset_id: 1024
hns3 0000:7d:00.0: PG pg_id: 0
hns3 0000:7d:00.0: PG dwrr: 100
hns3 0000:7d:00.0: QS qs_id: 0
hns3 0000:7d:00.0: QS dwrr: 100
hns3 0000:7d:00.0: PRI pri_id: 0
hns3 0000:7d:00.0: PRI dwrr: 100
hns3 0000:7d:00.0: PRI_C pri_id: 0
hns3 0000:7d:00.0: PRI_C pri_shapping: 0x2850000
hns3 0000:7d:00.0: PRI_P pri_id: 0
hns3 0000:7d:00.0: PRI_P pri_shapping: 0x2850796
hns3 0000:7d:00.0: PG_C pg_id: 0
hns3 0000:7d:00.0: PG_C pg_shapping: 0x2850000
hns3 0000:7d:00.0: PG_P pg_id: 0
hns3 0000:7d:00.0: PG_P pg_shapping: 0x2850496
hns3 0000:7d:00.0: PORT port_shapping: 0x2850296
hns3 0000:7d:00.0: PG_SCH pg_id: 0
hns3 0000:7d:00.0: PRI_SCH pg_id: 0
hns3 0000:7d:00.0: QS_SCH pg_id: 0
hns3 0000:7d:00.0: BP_TO_QSET pg_id: 0
hns3 0000:7d:00.0: BP_TO_QSET pg_shapping: 0x0
hns3 0000:7d:00.0: BP_TO_QSET qs_bit_map: 0x0
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |   1 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 199 +++++++++++++++++++++
 2 files changed, 200 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 8acccfbd3481..478c133ec0a9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -131,6 +131,7 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "queue info [number]\n");
 	dev_info(&h->pdev->dev, "dump fd tcam\n");
 	dev_info(&h->pdev->dev, "dump tc\n");
+	dev_info(&h->pdev->dev, "dump tm\n");
 }
 
 static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 050b90e95e00..e8f12333ff1e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -45,6 +45,203 @@ static void hclge_dbg_dump_tc(struct hclge_dev *hdev)
 				      "tc", "no sp mode", "sp mode");
 }
 
+static void hclge_dbg_dump_tm_pg(struct hclge_dev *hdev)
+{
+	struct hclge_port_shapping_cmd *port_shap_cfg_cmd;
+	struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd;
+	struct hclge_pg_shapping_cmd *pg_shap_cfg_cmd;
+	enum hclge_opcode_type cmd;
+	struct hclge_desc desc;
+	int ret;
+
+	cmd = HCLGE_OPC_TM_PG_C_SHAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	pg_shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PG_C pg_id: %u\n", pg_shap_cfg_cmd->pg_id);
+	dev_info(&hdev->pdev->dev, "PG_C pg_shapping: 0x%x\n",
+		 pg_shap_cfg_cmd->pg_shapping_para);
+
+	cmd = HCLGE_OPC_TM_PG_P_SHAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	pg_shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PG_P pg_id: %u\n", pg_shap_cfg_cmd->pg_id);
+	dev_info(&hdev->pdev->dev, "PG_P pg_shapping: 0x%x\n",
+		 pg_shap_cfg_cmd->pg_shapping_para);
+
+	cmd = HCLGE_OPC_TM_PORT_SHAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	port_shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PORT port_shapping: 0x%x\n",
+		 port_shap_cfg_cmd->port_shapping_para);
+
+	cmd = HCLGE_OPC_TM_PG_SCH_MODE_CFG;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "PG_SCH pg_id: %u\n", desc.data[0]);
+
+	cmd = HCLGE_OPC_TM_PRI_SCH_MODE_CFG;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "PRI_SCH pg_id: %u\n", desc.data[0]);
+
+	cmd = HCLGE_OPC_TM_QS_SCH_MODE_CFG;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "QS_SCH pg_id: %u\n", desc.data[0]);
+
+	cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "BP_TO_QSET pg_id: %u\n",
+		 bp_to_qs_map_cmd->tc_id);
+	dev_info(&hdev->pdev->dev, "BP_TO_QSET pg_shapping: 0x%x\n",
+		 bp_to_qs_map_cmd->qs_group_id);
+	dev_info(&hdev->pdev->dev, "BP_TO_QSET qs_bit_map: 0x%x\n",
+		 bp_to_qs_map_cmd->qs_bit_map);
+	return;
+
+err_tm_pg_cmd_send:
+	dev_err(&hdev->pdev->dev, "dump tm_pg fail(0x%x), status is %d\n",
+		cmd, ret);
+}
+
+static void hclge_dbg_dump_tm(struct hclge_dev *hdev)
+{
+	struct hclge_priority_weight_cmd *priority_weight;
+	struct hclge_pg_to_pri_link_cmd *pg_to_pri_map;
+	struct hclge_qs_to_pri_link_cmd *qs_to_pri_map;
+	struct hclge_nq_to_qs_link_cmd *nq_to_qs_map;
+	struct hclge_pri_shapping_cmd *shap_cfg_cmd;
+	struct hclge_pg_weight_cmd *pg_weight;
+	struct hclge_qs_weight_cmd *qs_weight;
+	enum hclge_opcode_type cmd;
+	struct hclge_desc desc;
+	int ret;
+
+	cmd = HCLGE_OPC_TM_PG_TO_PRI_LINK;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	pg_to_pri_map = (struct hclge_pg_to_pri_link_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "dump tm\n");
+	dev_info(&hdev->pdev->dev, "PG_TO_PRI gp_id: %u\n",
+		 pg_to_pri_map->pg_id);
+	dev_info(&hdev->pdev->dev, "PG_TO_PRI map: 0x%x\n",
+		 pg_to_pri_map->pri_bit_map);
+
+	cmd = HCLGE_OPC_TM_QS_TO_PRI_LINK;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	qs_to_pri_map = (struct hclge_qs_to_pri_link_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "QS_TO_PRI qs_id: %u\n",
+		 qs_to_pri_map->qs_id);
+	dev_info(&hdev->pdev->dev, "QS_TO_PRI priority: %u\n",
+		 qs_to_pri_map->priority);
+	dev_info(&hdev->pdev->dev, "QS_TO_PRI link_vld: %u\n",
+		 qs_to_pri_map->link_vld);
+
+	cmd = HCLGE_OPC_TM_NQ_TO_QS_LINK;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	nq_to_qs_map = (struct hclge_nq_to_qs_link_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "NQ_TO_QS nq_id: %u\n", nq_to_qs_map->nq_id);
+	dev_info(&hdev->pdev->dev, "NQ_TO_QS qset_id: %u\n",
+		 nq_to_qs_map->qset_id);
+
+	cmd = HCLGE_OPC_TM_PG_WEIGHT;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	pg_weight = (struct hclge_pg_weight_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PG pg_id: %u\n", pg_weight->pg_id);
+	dev_info(&hdev->pdev->dev, "PG dwrr: %u\n", pg_weight->dwrr);
+
+	cmd = HCLGE_OPC_TM_QS_WEIGHT;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	qs_weight = (struct hclge_qs_weight_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "QS qs_id: %u\n", qs_weight->qs_id);
+	dev_info(&hdev->pdev->dev, "QS dwrr: %u\n", qs_weight->dwrr);
+
+	cmd = HCLGE_OPC_TM_PRI_WEIGHT;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	priority_weight = (struct hclge_priority_weight_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PRI pri_id: %u\n", priority_weight->pri_id);
+	dev_info(&hdev->pdev->dev, "PRI dwrr: %u\n", priority_weight->dwrr);
+
+	cmd = HCLGE_OPC_TM_PRI_C_SHAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	shap_cfg_cmd = (struct hclge_pri_shapping_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PRI_C pri_id: %u\n", shap_cfg_cmd->pri_id);
+	dev_info(&hdev->pdev->dev, "PRI_C pri_shapping: 0x%x\n",
+		 shap_cfg_cmd->pri_shapping_para);
+
+	cmd = HCLGE_OPC_TM_PRI_P_SHAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	shap_cfg_cmd = (struct hclge_pri_shapping_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PRI_P pri_id: %u\n", shap_cfg_cmd->pri_id);
+	dev_info(&hdev->pdev->dev, "PRI_P pri_shapping: 0x%x\n",
+		 shap_cfg_cmd->pri_shapping_para);
+
+	hclge_dbg_dump_tm_pg(hdev);
+
+	return;
+
+err_tm_cmd_send:
+	dev_err(&hdev->pdev->dev, "dump tm fail(0x%x), status is %d\n",
+		cmd, ret);
+}
+
 static void hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage,
 				   bool sel_x, u32 loc)
 {
@@ -108,6 +305,8 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
 		hclge_dbg_fd_tcam(hdev);
 	} else if (strncmp(cmd_buf, "dump tc", 7) == 0) {
 		hclge_dbg_dump_tc(hdev);
+	} else if (strncmp(cmd_buf, "dump tm", 7) == 0) {
+		hclge_dbg_dump_tm(hdev);
 	} else {
 		dev_info(&hdev->pdev->dev, "unknown command\n");
 		return -EINVAL;
-- 
cgit v1.2.3


From d958919dc15c9e315df7d28d08d3ab6f3b909a32 Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Thu, 22 Nov 2018 14:09:46 +0000
Subject: net: hns3: Add "qos pause" config info query function

This patch prints qos pause config information.

debugfs command:
echo dump qos pause cfg > cmd

Sample Command:
root@(none)# echo dump qos pause cfg > cmd
hns3 0000:7d:00.0: dump qos pause cfg
hns3 0000:7d:00.0: pause_trans_gap: 0xff
hns3 0000:7d:00.0: pause_trans_time: 0xffff
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |  1 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 25 ++++++++++++++++++++++
 2 files changed, 26 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 478c133ec0a9..62586958a311 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -132,6 +132,7 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "dump fd tcam\n");
 	dev_info(&h->pdev->dev, "dump tc\n");
 	dev_info(&h->pdev->dev, "dump tm\n");
+	dev_info(&h->pdev->dev, "dump qos pause cfg\n");
 }
 
 static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index e8f12333ff1e..37b312bd3bef 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -242,6 +242,29 @@ err_tm_cmd_send:
 		cmd, ret);
 }
 
+static void hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev)
+{
+	struct hclge_cfg_pause_param_cmd *pause_param;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_MAC_PARA, true);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev, "dump checksum fail, status is %d.\n",
+			ret);
+		return;
+	}
+
+	pause_param = (struct hclge_cfg_pause_param_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "dump qos pause cfg\n");
+	dev_info(&hdev->pdev->dev, "pause_trans_gap: 0x%x\n",
+		 pause_param->pause_trans_gap);
+	dev_info(&hdev->pdev->dev, "pause_trans_time: 0x%x\n",
+		 pause_param->pause_trans_time);
+}
+
 static void hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage,
 				   bool sel_x, u32 loc)
 {
@@ -307,6 +330,8 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
 		hclge_dbg_dump_tc(hdev);
 	} else if (strncmp(cmd_buf, "dump tm", 7) == 0) {
 		hclge_dbg_dump_tm(hdev);
+	} else if (strncmp(cmd_buf, "dump qos pause cfg", 18) == 0) {
+		hclge_dbg_dump_qos_pause_cfg(hdev);
 	} else {
 		dev_info(&hdev->pdev->dev, "unknown command\n");
 		return -EINVAL;
-- 
cgit v1.2.3


From 6fc2244057b0edf77d697a172e0cd6be97344de5 Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Thu, 22 Nov 2018 14:09:47 +0000
Subject: net: hns3: Add "qos prio map" info query function

This patch prints qos priority map information.

debugfs command:
echo dump qos pri map > cmd

Sample Command:
root@(none)# echo dump qos pri map > cmd
hns3 0000:7d:00.0: dump qos pri map
hns3 0000:7d:00.0: vlan_to_pri: 0x0
hns3 0000:7d:00.0: pri_0_to_tc: 0x0
hns3 0000:7d:00.0: pri_1_to_tc: 0x0
hns3 0000:7d:00.0: pri_2_to_tc: 0x0
hns3 0000:7d:00.0: pri_3_to_tc: 0x0
hns3 0000:7d:00.0: pri_4_to_tc: 0x0
hns3 0000:7d:00.0: pri_5_to_tc: 0x0
hns3 0000:7d:00.0: pri_6_to_tc: 0x0
hns3 0000:7d:00.0: pri_7_to_tc: 0x0
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |  1 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 31 ++++++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h | 23 ++++++++++++++++
 3 files changed, 55 insertions(+)
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 62586958a311..ce284c8ddefc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -133,6 +133,7 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "dump tc\n");
 	dev_info(&h->pdev->dev, "dump tm\n");
 	dev_info(&h->pdev->dev, "dump qos pause cfg\n");
+	dev_info(&h->pdev->dev, "dump qos pri map\n");
 }
 
 static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 37b312bd3bef..477acf7299ba 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -3,6 +3,7 @@
 
 #include <linux/device.h>
 
+#include "hclge_debugfs.h"
 #include "hclge_cmd.h"
 #include "hclge_main.h"
 #include "hclge_tm.h"
@@ -265,6 +266,34 @@ static void hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev)
 		 pause_param->pause_trans_time);
 }
 
+static void hclge_dbg_dump_qos_pri_map(struct hclge_dev *hdev)
+{
+	struct hclge_qos_pri_map_cmd *pri_map;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PRI_TO_TC_MAPPING, true);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"dump qos pri map fail, status is %d.\n", ret);
+		return;
+	}
+
+	pri_map = (struct hclge_qos_pri_map_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "dump qos pri map\n");
+	dev_info(&hdev->pdev->dev, "vlan_to_pri: 0x%x\n", pri_map->vlan_pri);
+	dev_info(&hdev->pdev->dev, "pri_0_to_tc: 0x%x\n", pri_map->pri0_tc);
+	dev_info(&hdev->pdev->dev, "pri_1_to_tc: 0x%x\n", pri_map->pri1_tc);
+	dev_info(&hdev->pdev->dev, "pri_2_to_tc: 0x%x\n", pri_map->pri2_tc);
+	dev_info(&hdev->pdev->dev, "pri_3_to_tc: 0x%x\n", pri_map->pri3_tc);
+	dev_info(&hdev->pdev->dev, "pri_4_to_tc: 0x%x\n", pri_map->pri4_tc);
+	dev_info(&hdev->pdev->dev, "pri_5_to_tc: 0x%x\n", pri_map->pri5_tc);
+	dev_info(&hdev->pdev->dev, "pri_6_to_tc: 0x%x\n", pri_map->pri6_tc);
+	dev_info(&hdev->pdev->dev, "pri_7_to_tc: 0x%x\n", pri_map->pri7_tc);
+}
+
 static void hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage,
 				   bool sel_x, u32 loc)
 {
@@ -332,6 +361,8 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
 		hclge_dbg_dump_tm(hdev);
 	} else if (strncmp(cmd_buf, "dump qos pause cfg", 18) == 0) {
 		hclge_dbg_dump_qos_pause_cfg(hdev);
+	} else if (strncmp(cmd_buf, "dump qos pri map", 16) == 0) {
+		hclge_dbg_dump_qos_pri_map(hdev);
 	} else {
 		dev_info(&hdev->pdev->dev, "unknown command\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
new file mode 100644
index 000000000000..50fd0b15fb8e
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2018-2019 Hisilicon Limited. */
+
+#ifndef __HCLGE_DEBUGFS_H
+#define __HCLGE_DEBUGFS_H
+
+#pragma pack(1)
+
+struct hclge_qos_pri_map_cmd {
+	u8 pri0_tc  : 4,
+	   pri1_tc  : 4;
+	u8 pri2_tc  : 4,
+	   pri3_tc  : 4;
+	u8 pri4_tc  : 4,
+	   pri5_tc  : 4;
+	u8 pri6_tc  : 4,
+	   pri7_tc  : 4;
+	u8 vlan_pri : 4,
+	   rev	    : 4;
+};
+
+#pragma pack()
+#endif
-- 
cgit v1.2.3


From 7d9d7f8864bacdf5afd68daa737f4f082fd724c8 Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Thu, 22 Nov 2018 14:09:48 +0000
Subject: net: hns3: Add "qos buffer" config info query function

This patch prints qos buffer config information.

debugfs command:
echo dump qos buf cfg > cmd

Sample Command:
root@(none)# echo dump qos buf cfg > cmd
hns3 0000:7d:00.0: dump qos buf cfg
hns3 0000:7d:00.0: tx_packet_buf_tc_0: 0x1aa
hns3 0000:7d:00.0: tx_packet_buf_tc_1: 0x0
hns3 0000:7d:00.0: tx_packet_buf_tc_2: 0x0
hns3 0000:7d:00.0: tx_packet_buf_tc_3: 0x0
hns3 0000:7d:00.0: tx_packet_buf_tc_4: 0x0
hns3 0000:7d:00.0: tx_packet_buf_tc_5: 0x0
hns3 0000:7d:00.0: tx_packet_buf_tc_6: 0x0
hns3 0000:7d:00.0: tx_packet_buf_tc_7: 0x0
hns3 0000:7d:00.0:
hns3 0000:7d:00.0: rx_packet_buf_tc_0: 0x130
hns3 0000:7d:00.0: rx_packet_buf_tc_1: 0x0
hns3 0000:7d:00.0: rx_packet_buf_tc_2: 0x0
hns3 0000:7d:00.0: rx_packet_buf_tc_3: 0x0
hns3 0000:7d:00.0: rx_packet_buf_tc_4: 0x0
hns3 0000:7d:00.0: rx_packet_buf_tc_5: 0x0
hns3 0000:7d:00.0: rx_packet_buf_tc_6: 0x0
hns3 0000:7d:00.0: rx_packet_buf_tc_7: 0x0
hns3 0000:7d:00.0: rx_share_buf: 0x1e0e
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |   1 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 115 +++++++++++++++++++++
 2 files changed, 116 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index ce284c8ddefc..86d667a3730a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -134,6 +134,7 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "dump tm\n");
 	dev_info(&h->pdev->dev, "dump qos pause cfg\n");
 	dev_info(&h->pdev->dev, "dump qos pri map\n");
+	dev_info(&h->pdev->dev, "dump qos buf cfg\n");
 }
 
 static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 477acf7299ba..14577bbf3e11 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -294,6 +294,119 @@ static void hclge_dbg_dump_qos_pri_map(struct hclge_dev *hdev)
 	dev_info(&hdev->pdev->dev, "pri_7_to_tc: 0x%x\n", pri_map->pri7_tc);
 }
 
+static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev)
+{
+	struct hclge_tx_buff_alloc_cmd *tx_buf_cmd;
+	struct hclge_rx_priv_buff_cmd *rx_buf_cmd;
+	struct hclge_rx_priv_wl_buf *rx_priv_wl;
+	struct hclge_rx_com_wl *rx_packet_cnt;
+	struct hclge_rx_com_thrd *rx_com_thrd;
+	struct hclge_rx_com_wl *rx_com_wl;
+	enum hclge_opcode_type cmd;
+	struct hclge_desc desc[2];
+	int i, ret;
+
+	cmd = HCLGE_OPC_TX_BUFF_ALLOC;
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 1);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "dump qos buf cfg\n");
+
+	tx_buf_cmd = (struct hclge_tx_buff_alloc_cmd *)desc[0].data;
+	for (i = 0; i < HCLGE_TC_NUM; i++)
+		dev_info(&hdev->pdev->dev, "tx_packet_buf_tc_%d: 0x%x\n", i,
+			 tx_buf_cmd->tx_pkt_buff[i]);
+
+	cmd = HCLGE_OPC_RX_PRIV_BUFF_ALLOC;
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 1);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "\n");
+	rx_buf_cmd = (struct hclge_rx_priv_buff_cmd *)desc[0].data;
+	for (i = 0; i < HCLGE_TC_NUM; i++)
+		dev_info(&hdev->pdev->dev, "rx_packet_buf_tc_%d: 0x%x\n", i,
+			 rx_buf_cmd->buf_num[i]);
+
+	dev_info(&hdev->pdev->dev, "rx_share_buf: 0x%x\n",
+		 rx_buf_cmd->shared_buf);
+
+	cmd = HCLGE_OPC_RX_PRIV_WL_ALLOC;
+	hclge_cmd_setup_basic_desc(&desc[0], cmd, true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 2);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "\n");
+	rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[0].data;
+	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
+		dev_info(&hdev->pdev->dev,
+			 "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n", i,
+			 rx_priv_wl->tc_wl[i].high, rx_priv_wl->tc_wl[i].low);
+
+	rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[1].data;
+	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
+		dev_info(&hdev->pdev->dev,
+			 "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n", i + 4,
+			 rx_priv_wl->tc_wl[i].high, rx_priv_wl->tc_wl[i].low);
+
+	cmd = HCLGE_OPC_RX_COM_THRD_ALLOC;
+	hclge_cmd_setup_basic_desc(&desc[0], cmd, true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 2);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "\n");
+	rx_com_thrd = (struct hclge_rx_com_thrd *)desc[0].data;
+	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
+		dev_info(&hdev->pdev->dev,
+			 "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", i,
+			 rx_com_thrd->com_thrd[i].high,
+			 rx_com_thrd->com_thrd[i].low);
+
+	rx_com_thrd = (struct hclge_rx_com_thrd *)desc[1].data;
+	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
+		dev_info(&hdev->pdev->dev,
+			 "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", i + 4,
+			 rx_com_thrd->com_thrd[i].high,
+			 rx_com_thrd->com_thrd[i].low);
+
+	cmd = HCLGE_OPC_RX_COM_WL_ALLOC;
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 1);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	rx_com_wl = (struct hclge_rx_com_wl *)desc[0].data;
+	dev_info(&hdev->pdev->dev, "\n");
+	dev_info(&hdev->pdev->dev, "rx_com_wl: high: 0x%x, low: 0x%x\n",
+		 rx_com_wl->com_wl.high, rx_com_wl->com_wl.low);
+
+	cmd = HCLGE_OPC_RX_GBL_PKT_CNT;
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 1);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	rx_packet_cnt = (struct hclge_rx_com_wl *)desc[0].data;
+	dev_info(&hdev->pdev->dev,
+		 "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n",
+		 rx_packet_cnt->com_wl.high, rx_packet_cnt->com_wl.low);
+
+	return;
+
+err_qos_cmd_send:
+	dev_err(&hdev->pdev->dev,
+		"dump qos buf cfg fail(0x%x), status is %d\n", cmd, ret);
+}
+
 static void hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage,
 				   bool sel_x, u32 loc)
 {
@@ -363,6 +476,8 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
 		hclge_dbg_dump_qos_pause_cfg(hdev);
 	} else if (strncmp(cmd_buf, "dump qos pri map", 16) == 0) {
 		hclge_dbg_dump_qos_pri_map(hdev);
+	} else if (strncmp(cmd_buf, "dump qos buf cfg", 16) == 0) {
+		hclge_dbg_dump_qos_buf_cfg(hdev);
 	} else {
 		dev_info(&hdev->pdev->dev, "unknown command\n");
 		return -EINVAL;
-- 
cgit v1.2.3


From 734c140982ac0c8e97d82b66b94032db28996e21 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 22 Nov 2018 21:56:48 +0100
Subject: r8169: remove ancient GCC bug workaround in a second place

Remove ancient GCC bug workaround in a second place and factor out
rtl_8169_get_txd_opts1.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index b15cb1ca88b8..97bceb35217a 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5840,6 +5840,16 @@ static void rtl8169_tx_timeout(struct net_device *dev)
 	rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 }
 
+static __le32 rtl8169_get_txd_opts1(u32 opts0, u32 len, unsigned int entry)
+{
+	u32 status = opts0 | len;
+
+	if (entry == NUM_TX_DESC - 1)
+		status |= RingEnd;
+
+	return cpu_to_le32(status);
+}
+
 static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb,
 			      u32 *opts)
 {
@@ -5852,7 +5862,7 @@ static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb,
 	for (cur_frag = 0; cur_frag < info->nr_frags; cur_frag++) {
 		const skb_frag_t *frag = info->frags + cur_frag;
 		dma_addr_t mapping;
-		u32 status, len;
+		u32 len;
 		void *addr;
 
 		entry = (entry + 1) % NUM_TX_DESC;
@@ -5868,11 +5878,7 @@ static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb,
 			goto err_out;
 		}
 
-		status = opts[0] | len;
-		if (entry == NUM_TX_DESC - 1)
-			status |= RingEnd;
-
-		txd->opts1 = cpu_to_le32(status);
+		txd->opts1 = rtl8169_get_txd_opts1(opts[0], len, entry);
 		txd->opts2 = cpu_to_le32(opts[1]);
 		txd->addr = cpu_to_le64(mapping);
 
@@ -6068,8 +6074,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	struct TxDesc *txd = tp->TxDescArray + entry;
 	struct device *d = tp_to_dev(tp);
 	dma_addr_t mapping;
-	u32 status, len;
-	u32 opts[2];
+	u32 opts[2], len;
 	int frags;
 
 	if (unlikely(!TX_FRAGS_READY_FOR(tp, skb_shinfo(skb)->nr_frags))) {
@@ -6118,9 +6123,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	/* Force memory writes to complete before releasing descriptor */
 	dma_wmb();
 
-	/* Anti gcc 2.95.3 bugware (sic) */
-	status = opts[0] | len | (RingEnd * !((entry + 1) % NUM_TX_DESC));
-	txd->opts1 = cpu_to_le32(status);
+	txd->opts1 = rtl8169_get_txd_opts1(opts[0], len, entry);
 
 	/* Force all memory writes to complete before notifying device */
 	wmb();
-- 
cgit v1.2.3


From b4cc2dcc9c7c9cea293d1fa6a7b91876c8f23bdf Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 22 Nov 2018 21:58:48 +0100
Subject: r8169: remove default chip versions

Even the chip versions within a family have so many differences that
using a default chip version doesn't really make sense. Instead
of leaving a best case flaky network connectivity, bail out and
report the unknown chip version.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 97bceb35217a..9fd8f4215dff 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -2011,8 +2011,7 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
-static void rtl8169_get_mac_version(struct rtl8169_private *tp,
-				    u8 default_version)
+static void rtl8169_get_mac_version(struct rtl8169_private *tp)
 {
 	/*
 	 * The driver currently handles the 8168Bf and the 8168Be identically
@@ -2116,9 +2115,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 	tp->mac_version = p->mac_version;
 
 	if (tp->mac_version == RTL_GIGA_MAC_NONE) {
-		dev_notice(tp_to_dev(tp),
-			   "unknown MAC, using family default\n");
-		tp->mac_version = default_version;
+		dev_err(tp_to_dev(tp), "unknown chip XID %03x\n", reg & 0xfcf);
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_42) {
 		tp->mac_version = tp->supports_gmii ?
 				  RTL_GIGA_MAC_VER_42 :
@@ -6976,27 +6973,23 @@ static const struct rtl_cfg_info {
 	u16 irq_mask;
 	unsigned int has_gmii:1;
 	const struct rtl_coalesce_info *coalesce_info;
-	u8 default_ver;
 } rtl_cfg_infos [] = {
 	[RTL_CFG_0] = {
 		.hw_start	= rtl_hw_start_8169,
 		.irq_mask	= SYSErr | LinkChg | RxOverflow | RxFIFOOver,
 		.has_gmii	= 1,
 		.coalesce_info	= rtl_coalesce_info_8169,
-		.default_ver	= RTL_GIGA_MAC_VER_01,
 	},
 	[RTL_CFG_1] = {
 		.hw_start	= rtl_hw_start_8168,
 		.irq_mask	= LinkChg | RxOverflow,
 		.has_gmii	= 1,
 		.coalesce_info	= rtl_coalesce_info_8168_8136,
-		.default_ver	= RTL_GIGA_MAC_VER_11,
 	},
 	[RTL_CFG_2] = {
 		.hw_start	= rtl_hw_start_8101,
 		.irq_mask	= LinkChg | RxOverflow | RxFIFOOver,
 		.coalesce_info	= rtl_coalesce_info_8168_8136,
-		.default_ver	= RTL_GIGA_MAC_VER_13,
 	}
 };
 
@@ -7259,7 +7252,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->mmio_addr = pcim_iomap_table(pdev)[region];
 
 	/* Identify chip attached to board */
-	rtl8169_get_mac_version(tp, cfg->default_ver);
+	rtl8169_get_mac_version(tp);
+	if (tp->mac_version == RTL_GIGA_MAC_NONE)
+		return -ENODEV;
 
 	if (rtl_tbi_enabled(tp)) {
 		dev_err(&pdev->dev, "TBI fiber mode not supported\n");
-- 
cgit v1.2.3


From 45f1996f4fd8f289e345c7a4157741100febb47d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 22 Nov 2018 22:00:10 +0100
Subject: r8169: simplify detecting chip versions with same XID

For the GMII chip versions we set the version number which was set
already. This can be simplified.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 9fd8f4215dff..4ed9dabe66fe 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -2116,18 +2116,13 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp)
 
 	if (tp->mac_version == RTL_GIGA_MAC_NONE) {
 		dev_err(tp_to_dev(tp), "unknown chip XID %03x\n", reg & 0xfcf);
-	} else if (tp->mac_version == RTL_GIGA_MAC_VER_42) {
-		tp->mac_version = tp->supports_gmii ?
-				  RTL_GIGA_MAC_VER_42 :
-				  RTL_GIGA_MAC_VER_43;
-	} else if (tp->mac_version == RTL_GIGA_MAC_VER_45) {
-		tp->mac_version = tp->supports_gmii ?
-				  RTL_GIGA_MAC_VER_45 :
-				  RTL_GIGA_MAC_VER_47;
-	} else if (tp->mac_version == RTL_GIGA_MAC_VER_46) {
-		tp->mac_version = tp->supports_gmii ?
-				  RTL_GIGA_MAC_VER_46 :
-				  RTL_GIGA_MAC_VER_48;
+	} else if (!tp->supports_gmii) {
+		if (tp->mac_version == RTL_GIGA_MAC_VER_42)
+			tp->mac_version = RTL_GIGA_MAC_VER_43;
+		else if (tp->mac_version == RTL_GIGA_MAC_VER_45)
+			tp->mac_version = RTL_GIGA_MAC_VER_47;
+		else if (tp->mac_version == RTL_GIGA_MAC_VER_46)
+			tp->mac_version = RTL_GIGA_MAC_VER_48;
 	}
 }
 
-- 
cgit v1.2.3


From 5317d5c6d47eba1a4aa8316610c64329301f20a4 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 22 Nov 2018 22:02:00 +0100
Subject: r8169: use napi_consume_skb where possible

Use napi_consume_skb() where possible to profit from
bulk free infrastructure.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 4ed9dabe66fe..a7e97e365a2d 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6204,7 +6204,8 @@ static void rtl8169_pcierr_interrupt(struct net_device *dev)
 	rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 }
 
-static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
+static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp,
+		   int budget)
 {
 	unsigned int dirty_tx, tx_left, bytes_compl = 0, pkts_compl = 0;
 
@@ -6232,7 +6233,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
 		if (status & LastFrag) {
 			pkts_compl++;
 			bytes_compl += tx_skb->skb->len;
-			dev_consume_skb_any(tx_skb->skb);
+			napi_consume_skb(tx_skb->skb, budget);
 			tx_skb->skb = NULL;
 		}
 		dirty_tx++;
@@ -6475,7 +6476,7 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
 
 	work_done = rtl_rx(dev, tp, (u32) budget);
 
-	rtl_tx(dev, tp);
+	rtl_tx(dev, tp, budget);
 
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
-- 
cgit v1.2.3


From 76085c9e7eaebf0caa2476f77380efc3d55b050c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 22 Nov 2018 22:03:08 +0100
Subject: r8169: replace macro TX_FRAGS_READY_FOR with a function

Replace macro TX_FRAGS_READY_FOR with function rtl_tx_slots_avail
to make code cleaner and type-safe.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index a7e97e365a2d..12811f18c134 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -56,13 +56,6 @@
 #define R8169_MSG_DEFAULT \
 	(NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN)
 
-#define TX_SLOTS_AVAIL(tp) \
-	(tp->dirty_tx + NUM_TX_DESC - tp->cur_tx)
-
-/* A skbuff with nr_frags needs nr_frags+1 entries in the tx queue */
-#define TX_FRAGS_READY_FOR(tp,nr_frags) \
-	(TX_SLOTS_AVAIL(tp) >= (nr_frags + 1))
-
 /* Maximum number of multicast addresses to filter (vs. Rx-all-multicast).
    The RTL chips use a 64 element hash table based on the Ethernet CRC. */
 static const int multicast_filter_limit = 32;
@@ -6058,6 +6051,15 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp,
 	return true;
 }
 
+static bool rtl_tx_slots_avail(struct rtl8169_private *tp,
+			       unsigned int nr_frags)
+{
+	unsigned int slots_avail = tp->dirty_tx + NUM_TX_DESC - tp->cur_tx;
+
+	/* A skbuff with nr_frags needs nr_frags+1 entries in the tx queue */
+	return slots_avail > nr_frags;
+}
+
 static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 				      struct net_device *dev)
 {
@@ -6069,7 +6071,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	u32 opts[2], len;
 	int frags;
 
-	if (unlikely(!TX_FRAGS_READY_FOR(tp, skb_shinfo(skb)->nr_frags))) {
+	if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) {
 		netif_err(tp, drv, dev, "BUG! Tx Ring full when queue awake!\n");
 		goto err_stop_0;
 	}
@@ -6126,7 +6128,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	mmiowb();
 
-	if (!TX_FRAGS_READY_FOR(tp, MAX_SKB_FRAGS)) {
+	if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) {
 		/* Avoid wrongly optimistic queue wake-up: rtl_tx thread must
 		 * not miss a ring update when it notices a stopped queue.
 		 */
@@ -6140,7 +6142,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 		 * can't.
 		 */
 		smp_mb();
-		if (TX_FRAGS_READY_FOR(tp, MAX_SKB_FRAGS))
+		if (rtl_tx_slots_avail(tp, MAX_SKB_FRAGS))
 			netif_wake_queue(dev);
 	}
 
@@ -6258,7 +6260,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp,
 		 */
 		smp_mb();
 		if (netif_queue_stopped(dev) &&
-		    TX_FRAGS_READY_FOR(tp, MAX_SKB_FRAGS)) {
+		    rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) {
 			netif_wake_queue(dev);
 		}
 		/*
-- 
cgit v1.2.3


From ec394af5ea1d8ee62681815d167115ac618bcb42 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:28:07 +0000
Subject: switchdev: SWITCHDEV_OBJ_PORT_{VLAN, MDB}(): Sanitize

The two macros SWITCHDEV_OBJ_PORT_VLAN() and SWITCHDEV_OBJ_PORT_MDB()
expand to a container_of() call, yielding an appropriate container of
their sole argument. However, due to a name collision, the first
argument, i.e. the contained object pointer, is not the only one to get
expanded. The third argument, which is a structure member name, and
should be kept literal, gets expanded as well. The only safe way to use
these two macros is therefore to name the local variable passed to them
"obj".

To fix this, rename the sole argument of the two macros from
"obj" (which collides with the member name) to "OBJ". Additionally,
instead of passing "OBJ" to container_of() verbatim, parenthesize it, so
that a comma in the passed-in expression doesn't pollute the
container_of() invocation.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 7b371e7c4bc6..dd969224a9b9 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -95,8 +95,8 @@ struct switchdev_obj_port_vlan {
 	u16 vid_end;
 };
 
-#define SWITCHDEV_OBJ_PORT_VLAN(obj) \
-	container_of(obj, struct switchdev_obj_port_vlan, obj)
+#define SWITCHDEV_OBJ_PORT_VLAN(OBJ) \
+	container_of((OBJ), struct switchdev_obj_port_vlan, obj)
 
 /* SWITCHDEV_OBJ_ID_PORT_MDB */
 struct switchdev_obj_port_mdb {
@@ -105,8 +105,8 @@ struct switchdev_obj_port_mdb {
 	u16 vid;
 };
 
-#define SWITCHDEV_OBJ_PORT_MDB(obj) \
-	container_of(obj, struct switchdev_obj_port_mdb, obj)
+#define SWITCHDEV_OBJ_PORT_MDB(OBJ) \
+	container_of((OBJ), struct switchdev_obj_port_mdb, obj)
 
 void switchdev_trans_item_enqueue(struct switchdev_trans *trans,
 				  void *data, void (*destructor)(void const *),
-- 
cgit v1.2.3


From a93e3b17227ed8b0db7e44d0302b4da7d07f9a35 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:28:25 +0000
Subject: switchdev: Add a blocking notifier chain

In general one can't assume that a switchdev notifier is called in a
non-atomic context, and correspondingly, the switchdev notifier chain is
an atomic one.

However, port object addition and deletion messages are delivered from a
process context. Even the MDB addition messages, whose delivery is
scheduled from atomic context, are queued and the delivery itself takes
place in blocking context. For VLAN messages in particular, keeping the
blocking nature is important for error reporting.

Therefore introduce a blocking notifier chain and related service
functions to distribute the notifications for which a blocking context
can be assumed.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h   | 27 +++++++++++++++++++++++++++
 net/switchdev/switchdev.c | 26 ++++++++++++++++++++++++++
 2 files changed, 53 insertions(+)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index dd969224a9b9..e021b67b9b32 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -182,10 +182,17 @@ int switchdev_port_obj_add(struct net_device *dev,
 			   const struct switchdev_obj *obj);
 int switchdev_port_obj_del(struct net_device *dev,
 			   const struct switchdev_obj *obj);
+
 int register_switchdev_notifier(struct notifier_block *nb);
 int unregister_switchdev_notifier(struct notifier_block *nb);
 int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
 			     struct switchdev_notifier_info *info);
+
+int register_switchdev_blocking_notifier(struct notifier_block *nb);
+int unregister_switchdev_blocking_notifier(struct notifier_block *nb);
+int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev,
+				      struct switchdev_notifier_info *info);
+
 void switchdev_port_fwd_mark_set(struct net_device *dev,
 				 struct net_device *group_dev,
 				 bool joining);
@@ -241,6 +248,26 @@ static inline int call_switchdev_notifiers(unsigned long val,
 	return NOTIFY_DONE;
 }
 
+static inline int
+register_switchdev_blocking_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int
+unregister_switchdev_blocking_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int
+call_switchdev_blocking_notifiers(unsigned long val,
+				  struct net_device *dev,
+				  struct switchdev_notifier_info *info)
+{
+	return NOTIFY_DONE;
+}
+
 static inline bool switchdev_port_same_parent_id(struct net_device *a,
 						 struct net_device *b)
 {
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 74b9d916a58b..e109bb97ce3f 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -535,6 +535,7 @@ int switchdev_port_obj_del(struct net_device *dev,
 EXPORT_SYMBOL_GPL(switchdev_port_obj_del);
 
 static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain);
+static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain);
 
 /**
  *	register_switchdev_notifier - Register notifier
@@ -576,6 +577,31 @@ int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(call_switchdev_notifiers);
 
+int register_switchdev_blocking_notifier(struct notifier_block *nb)
+{
+	struct blocking_notifier_head *chain = &switchdev_blocking_notif_chain;
+
+	return blocking_notifier_chain_register(chain, nb);
+}
+EXPORT_SYMBOL_GPL(register_switchdev_blocking_notifier);
+
+int unregister_switchdev_blocking_notifier(struct notifier_block *nb)
+{
+	struct blocking_notifier_head *chain = &switchdev_blocking_notif_chain;
+
+	return blocking_notifier_chain_unregister(chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_switchdev_blocking_notifier);
+
+int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev,
+				      struct switchdev_notifier_info *info)
+{
+	info->dev = dev;
+	return blocking_notifier_call_chain(&switchdev_blocking_notif_chain,
+					    val, info);
+}
+EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers);
+
 bool switchdev_port_same_parent_id(struct net_device *a,
 				   struct net_device *b)
 {
-- 
cgit v1.2.3


From aa4efe21393f5c39a72c132d6e0d777d7405b885 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:28:38 +0000
Subject: switchdev: Add SWITCHDEV_PORT_OBJ_ADD, SWITCHDEV_PORT_OBJ_DEL

An offloading driver may need to have access to switchdev events on
ports that aren't directly under its control. An example is a VXLAN port
attached to a bridge offloaded by a driver. The driver needs to know
about VLANs configured on the VXLAN device. However the VXLAN device
isn't stashed between the bridge and a front-panel-port device (such as
is the case e.g. for LAG devices), so the usual switchdev ops don't
reach the driver.

VXLAN is likely not the only device type like this: in theory any L2
tunnel device that needs offloading will prompt requirement of this
sort. This falsifies the assumption that only the lower devices of a
front panel port need to be notified to achieve flawless offloading.

A way to fix this is to give up the notion of port object addition /
deletion as a switchdev operation, which assumes somewhat tight coupling
between the message producer and consumer. And instead send the message
over a notifier chain.

To that end, introduce two new switchdev notifier types,
SWITCHDEV_PORT_OBJ_ADD and SWITCHDEV_PORT_OBJ_DEL. These notifier types
communicate the same event as the corresponding switchdev op, except in
a form of a notification. struct switchdev_notifier_port_obj_info was
added to carry the fields that the switchdev op carries. An additional
field, handled, will be used to communicate back to switchdev that the
event has reached an interested party, which will be important for the
two-phase commit.

The two switchdev operations themselves are kept in place. Following
patches first convert individual clients to the notifier protocol, and
only then are the operations removed.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index e021b67b9b32..a2f3ebf39301 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -146,6 +146,9 @@ enum switchdev_notifier_type {
 	SWITCHDEV_FDB_DEL_TO_DEVICE,
 	SWITCHDEV_FDB_OFFLOADED,
 
+	SWITCHDEV_PORT_OBJ_ADD, /* Blocking. */
+	SWITCHDEV_PORT_OBJ_DEL, /* Blocking. */
+
 	SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE,
 	SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE,
 	SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE,
@@ -165,6 +168,13 @@ struct switchdev_notifier_fdb_info {
 	   offloaded:1;
 };
 
+struct switchdev_notifier_port_obj_info {
+	struct switchdev_notifier_info info; /* must be first */
+	const struct switchdev_obj *obj;
+	struct switchdev_trans *trans;
+	bool handled;
+};
+
 static inline struct net_device *
 switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info)
 {
-- 
cgit v1.2.3


From c6fa35b2370aeed280fccbc02ff24b94ab48fcf9 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:28:51 +0000
Subject: rocker: Handle SWITCHDEV_PORT_OBJ_ADD/_DEL

Following patches will change the way of distributing port object
changes from a switchdev operation to a switchdev notifier. The
switchdev code currently recursively descends through layers of lower
devices, eventually calling the op on a front-panel port device. The
notifier will instead be sent referencing the bridge port device, which
may be a stacking device that's one of front-panel ports uppers, or a
completely unrelated device.

rocker currently doesn't support any uppers other than bridge. Thus the
only case that a stacked device could be validly referenced by port
object notifications are bridge notifications for VLAN objects added to
the bridge itself. But the driver explicitly rejects such notifications
in rocker_world_port_obj_vlan_add(). It is therefore safe to assume that
the only interesting case is that the notification is on a front-panel
port netdevice.

Subscribe to the blocking notifier chain. In the handler, filter out
notifications on any foreign netdevices. Dispatch the new notifiers to
rocker_port_obj_add() resp. _del() to maintain the behavior that the
switchdev operation based code currently has.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker_main.c | 55 +++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index beb06628f22d..806ffe1d906e 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2812,12 +2812,54 @@ static int rocker_switchdev_event(struct notifier_block *unused,
 	return NOTIFY_DONE;
 }
 
+static int
+rocker_switchdev_port_obj_event(unsigned long event, struct net_device *netdev,
+			struct switchdev_notifier_port_obj_info *port_obj_info)
+{
+	int err = -EOPNOTSUPP;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD:
+		err = rocker_port_obj_add(netdev, port_obj_info->obj,
+					  port_obj_info->trans);
+		break;
+	case SWITCHDEV_PORT_OBJ_DEL:
+		err = rocker_port_obj_del(netdev, port_obj_info->obj);
+		break;
+	}
+
+	port_obj_info->handled = true;
+	return notifier_from_errno(err);
+}
+
+static int rocker_switchdev_blocking_event(struct notifier_block *unused,
+					   unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+
+	if (!rocker_port_dev_check(dev))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD:
+	case SWITCHDEV_PORT_OBJ_DEL:
+		return rocker_switchdev_port_obj_event(event, dev, ptr);
+	}
+
+	return NOTIFY_DONE;
+}
+
 static struct notifier_block rocker_switchdev_notifier = {
 	.notifier_call = rocker_switchdev_event,
 };
 
+static struct notifier_block rocker_switchdev_blocking_notifier = {
+	.notifier_call = rocker_switchdev_blocking_event,
+};
+
 static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct notifier_block *nb;
 	struct rocker *rocker;
 	int err;
 
@@ -2933,6 +2975,13 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_register_switchdev_notifier;
 	}
 
+	nb = &rocker_switchdev_blocking_notifier;
+	err = register_switchdev_blocking_notifier(nb);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to register switchdev blocking notifier\n");
+		goto err_register_switchdev_blocking_notifier;
+	}
+
 	rocker->hw.id = rocker_read64(rocker, SWITCH_ID);
 
 	dev_info(&pdev->dev, "Rocker switch with id %*phN\n",
@@ -2940,6 +2989,8 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+err_register_switchdev_blocking_notifier:
+	unregister_switchdev_notifier(&rocker_switchdev_notifier);
 err_register_switchdev_notifier:
 	unregister_fib_notifier(&rocker->fib_nb);
 err_register_fib_notifier:
@@ -2971,6 +3022,10 @@ err_pci_enable_device:
 static void rocker_remove(struct pci_dev *pdev)
 {
 	struct rocker *rocker = pci_get_drvdata(pdev);
+	struct notifier_block *nb;
+
+	nb = &rocker_switchdev_blocking_notifier;
+	unregister_switchdev_blocking_notifier(nb);
 
 	unregister_switchdev_notifier(&rocker_switchdev_notifier);
 	unregister_fib_notifier(&rocker->fib_nb);
-- 
cgit v1.2.3


From 2b239f678079fd8423c3cd7c5b804abadd2fe898 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:29:05 +0000
Subject: net: dsa: slave: Handle SWITCHDEV_PORT_OBJ_ADD/_DEL

Following patches will change the way of distributing port object
changes from a switchdev operation to a switchdev notifier. The
switchdev code currently recursively descends through layers of lower
devices, eventually calling the op on a front-panel port device. The
notifier will instead be sent referencing the bridge port device, which
may be a stacking device that's one of front-panel ports uppers, or a
completely unrelated device.

DSA currently doesn't support any other uppers than bridge.
SWITCHDEV_OBJ_ID_HOST_MDB and _PORT_MDB objects are always notified on
the bridge port device. Thus the only case that a stacked device could
be validly referenced by port object notifications are bridge
notifications for VLAN objects added to the bridge itself. But the
driver explicitly rejects such notifications in dsa_port_vlan_add(). It
is therefore safe to assume that the only interesting case is that the
notification is on a front-panel port netdevice. Therefore keep the
filtering by dsa_slave_dev_check() in place.

To handle SWITCHDEV_PORT_OBJ_ADD and _DEL, subscribe to the blocking
notifier chain. Dispatch to rocker_port_obj_add() resp. _del() to
maintain the behavior that the switchdev operation based code currently
has.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 7d0c19e7edcf..d00a0b6d4ce0 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1557,6 +1557,44 @@ err_fdb_work_init:
 	return NOTIFY_BAD;
 }
 
+static int
+dsa_slave_switchdev_port_obj_event(unsigned long event,
+			struct net_device *netdev,
+			struct switchdev_notifier_port_obj_info *port_obj_info)
+{
+	int err = -EOPNOTSUPP;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD:
+		err = dsa_slave_port_obj_add(netdev, port_obj_info->obj,
+					     port_obj_info->trans);
+		break;
+	case SWITCHDEV_PORT_OBJ_DEL:
+		err = dsa_slave_port_obj_del(netdev, port_obj_info->obj);
+		break;
+	}
+
+	port_obj_info->handled = true;
+	return notifier_from_errno(err);
+}
+
+static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused,
+					      unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+
+	if (!dsa_slave_dev_check(dev))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD: /* fall through */
+	case SWITCHDEV_PORT_OBJ_DEL:
+		return dsa_slave_switchdev_port_obj_event(event, dev, ptr);
+	}
+
+	return NOTIFY_DONE;
+}
+
 static struct notifier_block dsa_slave_nb __read_mostly = {
 	.notifier_call  = dsa_slave_netdevice_event,
 };
@@ -1565,8 +1603,13 @@ static struct notifier_block dsa_slave_switchdev_notifier = {
 	.notifier_call = dsa_slave_switchdev_event,
 };
 
+static struct notifier_block dsa_slave_switchdev_blocking_notifier = {
+	.notifier_call = dsa_slave_switchdev_blocking_event,
+};
+
 int dsa_slave_register_notifier(void)
 {
+	struct notifier_block *nb;
 	int err;
 
 	err = register_netdevice_notifier(&dsa_slave_nb);
@@ -1577,8 +1620,15 @@ int dsa_slave_register_notifier(void)
 	if (err)
 		goto err_switchdev_nb;
 
+	nb = &dsa_slave_switchdev_blocking_notifier;
+	err = register_switchdev_blocking_notifier(nb);
+	if (err)
+		goto err_switchdev_blocking_nb;
+
 	return 0;
 
+err_switchdev_blocking_nb:
+	unregister_switchdev_notifier(&dsa_slave_switchdev_notifier);
 err_switchdev_nb:
 	unregister_netdevice_notifier(&dsa_slave_nb);
 	return err;
@@ -1586,8 +1636,14 @@ err_switchdev_nb:
 
 void dsa_slave_unregister_notifier(void)
 {
+	struct notifier_block *nb;
 	int err;
 
+	nb = &dsa_slave_switchdev_blocking_notifier;
+	err = unregister_switchdev_blocking_notifier(nb);
+	if (err)
+		pr_err("DSA: failed to unregister switchdev blocking notifier (%d)\n", err);
+
 	err = unregister_switchdev_notifier(&dsa_slave_switchdev_notifier);
 	if (err)
 		pr_err("DSA: failed to unregister switchdev notifier (%d)\n", err);
-- 
cgit v1.2.3


From bb896805611fae33a67edb20820147b8a9ca68a5 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:29:18 +0000
Subject: staging: fsl-dpaa2: ethsw: Introduce ethsw_port_dev_check()

ethsw currently uses an open-coded comparison of netdev_ops to determine
whether whether a device represents a front panel port. Wrap this into a
named function to simplify reuse.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index 7a7ca67822c5..e379b0fa936f 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -972,6 +972,11 @@ static int port_bridge_leave(struct net_device *netdev)
 	return err;
 }
 
+static bool ethsw_port_dev_check(const struct net_device *netdev)
+{
+	return netdev->netdev_ops == &ethsw_port_ops;
+}
+
 static int port_netdevice_event(struct notifier_block *unused,
 				unsigned long event, void *ptr)
 {
@@ -980,7 +985,7 @@ static int port_netdevice_event(struct notifier_block *unused,
 	struct net_device *upper_dev;
 	int err = 0;
 
-	if (netdev->netdev_ops != &ethsw_port_ops)
+	if (!ethsw_port_dev_check(netdev))
 		return NOTIFY_DONE;
 
 	/* Handle just upper dev link/unlink for the moment */
-- 
cgit v1.2.3


From a39b888863afef5d43d6262d14b2f153ccda3151 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:29:30 +0000
Subject: staging: fsl-dpaa2: ethsw: Handle SWITCHDEV_PORT_OBJ_ADD/_DEL

Following patches will change the way of distributing port object
changes from a switchdev operation to a switchdev notifier. The
switchdev code currently recursively descends through layers of lower
devices, eventually calling the op on a front-panel port device. The
notifier will instead be sent referencing the bridge port device, which
may be a stacking device that's one of front-panel ports uppers, or a
completely unrelated device.

ethsw currently doesn't support any uppers other than bridge.
SWITCHDEV_OBJ_ID_HOST_MDB and _PORT_MDB objects are always notified on
the bridge port device. Thus the only case that a stacked device could
be validly referenced by port object notifications are bridge
notifications for VLAN objects added to the bridge itself. But the
driver explicitly rejects such notifications in port_vlans_add(). It is
therefore safe to assume that the only interesting case is that the
notification is on a front-panel port netdevice.

To handle SWITCHDEV_PORT_OBJ_ADD and _DEL, subscribe to the blocking
notifier chain. Dispatch to swdev_port_obj_add() resp. _del() to
maintain the behavior that the switchdev operation based code currently
has.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 56 +++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index e379b0fa936f..83e1d92dc7f3 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -1088,10 +1088,51 @@ err_addr_alloc:
 	return NOTIFY_BAD;
 }
 
+static int
+ethsw_switchdev_port_obj_event(unsigned long event, struct net_device *netdev,
+			struct switchdev_notifier_port_obj_info *port_obj_info)
+{
+	int err = -EOPNOTSUPP;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD:
+		err = swdev_port_obj_add(netdev, port_obj_info->obj,
+					 port_obj_info->trans);
+		break;
+	case SWITCHDEV_PORT_OBJ_DEL:
+		err = swdev_port_obj_del(netdev, port_obj_info->obj);
+		break;
+	}
+
+	port_obj_info->handled = true;
+	return notifier_from_errno(err);
+}
+
+static int port_switchdev_blocking_event(struct notifier_block *unused,
+					 unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+
+	if (!ethsw_port_dev_check(dev))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD: /* fall through */
+	case SWITCHDEV_PORT_OBJ_DEL:
+		return ethsw_switchdev_port_obj_event(event, dev, ptr);
+	}
+
+	return NOTIFY_DONE;
+}
+
 static struct notifier_block port_switchdev_nb = {
 	.notifier_call = port_switchdev_event,
 };
 
+static struct notifier_block port_switchdev_blocking_nb = {
+	.notifier_call = port_switchdev_blocking_event,
+};
+
 static int ethsw_register_notifier(struct device *dev)
 {
 	int err;
@@ -1108,8 +1149,16 @@ static int ethsw_register_notifier(struct device *dev)
 		goto err_switchdev_nb;
 	}
 
+	err = register_switchdev_blocking_notifier(&port_switchdev_blocking_nb);
+	if (err) {
+		dev_err(dev, "Failed to register switchdev blocking notifier\n");
+		goto err_switchdev_blocking_nb;
+	}
+
 	return 0;
 
+err_switchdev_blocking_nb:
+	unregister_switchdev_notifier(&port_switchdev_nb);
 err_switchdev_nb:
 	unregister_netdevice_notifier(&port_nb);
 	return err;
@@ -1296,8 +1345,15 @@ static int ethsw_port_init(struct ethsw_port_priv *port_priv, u16 port)
 
 static void ethsw_unregister_notifier(struct device *dev)
 {
+	struct notifier_block *nb;
 	int err;
 
+	nb = &port_switchdev_blocking_nb;
+	err = unregister_switchdev_blocking_notifier(nb);
+	if (err)
+		dev_err(dev,
+			"Failed to unregister switchdev blocking notifier (%d)\n", err);
+
 	err = unregister_switchdev_notifier(&port_switchdev_nb);
 	if (err)
 		dev_err(dev,
-- 
cgit v1.2.3


From f30f0601eb934dda107decd2e57b37168096fd74 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:29:44 +0000
Subject: switchdev: Add helpers to aid traversal through lower devices

After the transition from switchdev operations to notifier chain (which
will take place in following patches), the onus is on the driver to find
its own devices below possible layer of LAG or other uppers.

The logic to do so is fairly repetitive: each driver is looking for its
own devices among the lowers of the notified device. For those that it
finds, it calls a handler. To indicate that the event was handled,
struct switchdev_notifier_port_obj_info.handled is set. The differences
lie only in what constitutes an "own" device and what handler to call.

Therefore abstract this logic into two helpers,
switchdev_handle_port_obj_add() and switchdev_handle_port_obj_del(). If
a driver only supports physical ports under a bridge device, it will
simply avoid this layer of indirection.

One area where this helper diverges from the current switchdev behavior
is the case of mixed lowers, some of which are switchdev ports and some
of which are not. Previously, such scenario would fail with -EOPNOTSUPP.
The helper could do that for lowers for which the passed-in predicate
doesn't hold. That would however break the case that switchdev ports
from several different drivers are stashed under one master, a scenario
that switchdev currently happily supports. Therefore tolerate any and
all unknown netdevices, whether they are backed by a switchdev driver
or not.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h   |  33 +++++++++++++++
 net/switchdev/switchdev.c | 100 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 133 insertions(+)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index a2f3ebf39301..6dc7de576167 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -210,6 +210,18 @@ void switchdev_port_fwd_mark_set(struct net_device *dev,
 bool switchdev_port_same_parent_id(struct net_device *a,
 				   struct net_device *b);
 
+int switchdev_handle_port_obj_add(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			int (*add_cb)(struct net_device *dev,
+				      const struct switchdev_obj *obj,
+				      struct switchdev_trans *trans));
+int switchdev_handle_port_obj_del(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			int (*del_cb)(struct net_device *dev,
+				      const struct switchdev_obj *obj));
+
 #define SWITCHDEV_SET_OPS(netdev, ops) ((netdev)->switchdev_ops = (ops))
 #else
 
@@ -284,6 +296,27 @@ static inline bool switchdev_port_same_parent_id(struct net_device *a,
 	return false;
 }
 
+static inline int
+switchdev_handle_port_obj_add(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			int (*add_cb)(struct net_device *dev,
+				      const struct switchdev_obj *obj,
+				      struct switchdev_trans *trans))
+{
+	return 0;
+}
+
+static inline int
+switchdev_handle_port_obj_del(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			int (*del_cb)(struct net_device *dev,
+				      const struct switchdev_obj *obj))
+{
+	return 0;
+}
+
 #define SWITCHDEV_SET_OPS(netdev, ops) do {} while (0)
 
 #endif
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index e109bb97ce3f..099434ec7996 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -621,3 +621,103 @@ bool switchdev_port_same_parent_id(struct net_device *a,
 	return netdev_phys_item_id_same(&a_attr.u.ppid, &b_attr.u.ppid);
 }
 EXPORT_SYMBOL_GPL(switchdev_port_same_parent_id);
+
+static int __switchdev_handle_port_obj_add(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			int (*add_cb)(struct net_device *dev,
+				      const struct switchdev_obj *obj,
+				      struct switchdev_trans *trans))
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	int err = -EOPNOTSUPP;
+
+	if (check_cb(dev)) {
+		/* This flag is only checked if the return value is success. */
+		port_obj_info->handled = true;
+		return add_cb(dev, port_obj_info->obj, port_obj_info->trans);
+	}
+
+	/* Switch ports might be stacked under e.g. a LAG. Ignore the
+	 * unsupported devices, another driver might be able to handle them. But
+	 * propagate to the callers any hard errors.
+	 *
+	 * If the driver does its own bookkeeping of stacked ports, it's not
+	 * necessary to go through this helper.
+	 */
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = __switchdev_handle_port_obj_add(lower_dev, port_obj_info,
+						      check_cb, add_cb);
+		if (err && err != -EOPNOTSUPP)
+			return err;
+	}
+
+	return err;
+}
+
+int switchdev_handle_port_obj_add(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			int (*add_cb)(struct net_device *dev,
+				      const struct switchdev_obj *obj,
+				      struct switchdev_trans *trans))
+{
+	int err;
+
+	err = __switchdev_handle_port_obj_add(dev, port_obj_info, check_cb,
+					      add_cb);
+	if (err == -EOPNOTSUPP)
+		err = 0;
+	return err;
+}
+EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_add);
+
+static int __switchdev_handle_port_obj_del(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			int (*del_cb)(struct net_device *dev,
+				      const struct switchdev_obj *obj))
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	int err = -EOPNOTSUPP;
+
+	if (check_cb(dev)) {
+		/* This flag is only checked if the return value is success. */
+		port_obj_info->handled = true;
+		return del_cb(dev, port_obj_info->obj);
+	}
+
+	/* Switch ports might be stacked under e.g. a LAG. Ignore the
+	 * unsupported devices, another driver might be able to handle them. But
+	 * propagate to the callers any hard errors.
+	 *
+	 * If the driver does its own bookkeeping of stacked ports, it's not
+	 * necessary to go through this helper.
+	 */
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = __switchdev_handle_port_obj_del(lower_dev, port_obj_info,
+						      check_cb, del_cb);
+		if (err && err != -EOPNOTSUPP)
+			return err;
+	}
+
+	return err;
+}
+
+int switchdev_handle_port_obj_del(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			int (*del_cb)(struct net_device *dev,
+				      const struct switchdev_obj *obj))
+{
+	int err;
+
+	err = __switchdev_handle_port_obj_del(dev, port_obj_info, check_cb,
+					      del_cb);
+	if (err == -EOPNOTSUPP)
+		err = 0;
+	return err;
+}
+EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del);
-- 
cgit v1.2.3


From 52a227b30eba3ad4b8ac06ad187751ced0295c2a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:29:57 +0000
Subject: mlxsw: spectrum_switchdev: Handle SWITCHDEV_PORT_OBJ_ADD/_DEL

Following patches will change the way of distributing port object
changes from a switchdev operation to a switchdev notifier. The
switchdev code currently recursively descends through layers of lower
devices, eventually calling the op on a front-panel port device. The
notifier will instead be sent referencing the bridge port device, which
may be a stacking device that's one of front-panel ports uppers, or a
completely unrelated device.

To handle SWITCHDEV_PORT_OBJ_ADD and _DEL, subscribe to the blocking
notifier chain. Dispatch to mlxsw_sp_port_obj_add() resp. _del() to
maintain the behavior that the switchdev operation based code currently
has. Defer to switchdev_handle_port_obj_add() / _del() to handle the
recursive descend, because mlxsw supports a number of upper types.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 45 +++++++++++++++++++++-
 1 file changed, 44 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index b32a5ee57fb9..3756aaecd39c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -3118,6 +3118,32 @@ static struct notifier_block mlxsw_sp_switchdev_notifier = {
 	.notifier_call = mlxsw_sp_switchdev_event,
 };
 
+static int mlxsw_sp_switchdev_blocking_event(struct notifier_block *unused,
+					     unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD:
+		err = switchdev_handle_port_obj_add(dev, ptr,
+						    mlxsw_sp_port_dev_check,
+						    mlxsw_sp_port_obj_add);
+		return notifier_from_errno(err);
+	case SWITCHDEV_PORT_OBJ_DEL:
+		err = switchdev_handle_port_obj_del(dev, ptr,
+						    mlxsw_sp_port_dev_check,
+						    mlxsw_sp_port_obj_del);
+		return notifier_from_errno(err);
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block mlxsw_sp_switchdev_blocking_notifier = {
+	.notifier_call = mlxsw_sp_switchdev_blocking_event,
+};
+
 u8
 mlxsw_sp_bridge_port_stp_state(struct mlxsw_sp_bridge_port *bridge_port)
 {
@@ -3127,6 +3153,7 @@ mlxsw_sp_bridge_port_stp_state(struct mlxsw_sp_bridge_port *bridge_port)
 static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_bridge *bridge = mlxsw_sp->bridge;
+	struct notifier_block *nb;
 	int err;
 
 	err = mlxsw_sp_ageing_set(mlxsw_sp, MLXSW_SP_DEFAULT_AGEING_TIME);
@@ -3141,17 +3168,33 @@ static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp)
 		return err;
 	}
 
+	nb = &mlxsw_sp_switchdev_blocking_notifier;
+	err = register_switchdev_blocking_notifier(nb);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to register switchdev blocking notifier\n");
+		goto err_register_switchdev_blocking_notifier;
+	}
+
 	INIT_DELAYED_WORK(&bridge->fdb_notify.dw, mlxsw_sp_fdb_notify_work);
 	bridge->fdb_notify.interval = MLXSW_SP_DEFAULT_LEARNING_INTERVAL;
 	mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp);
 	return 0;
+
+err_register_switchdev_blocking_notifier:
+	unregister_switchdev_notifier(&mlxsw_sp_switchdev_notifier);
+	return err;
 }
 
 static void mlxsw_sp_fdb_fini(struct mlxsw_sp *mlxsw_sp)
 {
+	struct notifier_block *nb;
+
 	cancel_delayed_work_sync(&mlxsw_sp->bridge->fdb_notify.dw);
-	unregister_switchdev_notifier(&mlxsw_sp_switchdev_notifier);
 
+	nb = &mlxsw_sp_switchdev_blocking_notifier;
+	unregister_switchdev_blocking_notifier(nb);
+
+	unregister_switchdev_notifier(&mlxsw_sp_switchdev_notifier);
 }
 
 int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
-- 
cgit v1.2.3


From 0e332c854f4118680b6d37b22551f2f16df806d6 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:30:11 +0000
Subject: ocelot: Handle SWITCHDEV_PORT_OBJ_ADD/_DEL

Following patches will change the way of distributing port object
changes from a switchdev operation to a switchdev notifier. The
switchdev code currently recursively descends through layers of lower
devices, eventually calling the op on a front-panel port device. The
notifier will instead be sent referencing the bridge port device, which
may be a stacking device that's one of front-panel ports uppers, or a
completely unrelated device.

Dispatch the new events to ocelot_port_obj_add() resp. _del() to
maintain the same behavior that the switchdev operation based code
currently has. Pass through switchdev_handle_port_obj_add() / _del() to
handle the recursive descend, because Ocelot supports LAG uppers.

Register to the new switchdev blocking notifier chain to get the new
events when they start getting distributed.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c       | 28 ++++++++++++++++++++++++++++
 drivers/net/ethernet/mscc/ocelot.h       |  1 +
 drivers/net/ethernet/mscc/ocelot_board.c |  3 +++
 3 files changed, 32 insertions(+)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 3238b9ee42f3..01403b530522 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1595,6 +1595,34 @@ struct notifier_block ocelot_netdevice_nb __read_mostly = {
 };
 EXPORT_SYMBOL(ocelot_netdevice_nb);
 
+static int ocelot_switchdev_blocking_event(struct notifier_block *unused,
+					   unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
+
+	switch (event) {
+		/* Blocking events. */
+	case SWITCHDEV_PORT_OBJ_ADD:
+		err = switchdev_handle_port_obj_add(dev, ptr,
+						    ocelot_netdevice_dev_check,
+						    ocelot_port_obj_add);
+		return notifier_from_errno(err);
+	case SWITCHDEV_PORT_OBJ_DEL:
+		err = switchdev_handle_port_obj_del(dev, ptr,
+						    ocelot_netdevice_dev_check,
+						    ocelot_port_obj_del);
+		return notifier_from_errno(err);
+	}
+
+	return NOTIFY_DONE;
+}
+
+struct notifier_block ocelot_switchdev_blocking_nb __read_mostly = {
+	.notifier_call = ocelot_switchdev_blocking_event,
+};
+EXPORT_SYMBOL(ocelot_switchdev_blocking_nb);
+
 int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 		      void __iomem *regs,
 		      struct phy_device *phy)
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index 62c7c8eb00d9..086775f7b52f 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -499,5 +499,6 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 		      struct phy_device *phy);
 
 extern struct notifier_block ocelot_netdevice_nb;
+extern struct notifier_block ocelot_switchdev_blocking_nb;
 
 #endif
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index 4c23d18bbf44..ca3ea2fbfcd0 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -12,6 +12,7 @@
 #include <linux/of_platform.h>
 #include <linux/mfd/syscon.h>
 #include <linux/skbuff.h>
+#include <net/switchdev.h>
 
 #include "ocelot.h"
 
@@ -328,6 +329,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 	}
 
 	register_netdevice_notifier(&ocelot_netdevice_nb);
+	register_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
 
 	dev_info(&pdev->dev, "Ocelot switch probed\n");
 
@@ -342,6 +344,7 @@ static int mscc_ocelot_remove(struct platform_device *pdev)
 	struct ocelot *ocelot = platform_get_drvdata(pdev);
 
 	ocelot_deinit(ocelot);
+	unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
 	unregister_netdevice_notifier(&ocelot_netdevice_nb);
 
 	return 0;
-- 
cgit v1.2.3


From d17d9f5e5143125f9274194d8f7368f76b9d141f Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:32:57 +0000
Subject: switchdev: Replace port obj add/del SDO with a notification

Drop switchdev_ops.switchdev_port_obj_add and _del. Drop the uses of
this field from all clients, which were migrated to use switchdev
notification in the previous patches.

Add a new function switchdev_port_obj_notify() that sends the switchdev
notifications SWITCHDEV_PORT_OBJ_ADD and _DEL.

Update switchdev_port_obj_del_now() to dispatch to this new function.
Drop __switchdev_port_obj_add() and update switchdev_port_obj_add()
likewise.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   |  2 -
 drivers/net/ethernet/mscc/ocelot.c                 |  2 -
 drivers/net/ethernet/rocker/rocker_main.c          |  2 -
 drivers/staging/fsl-dpaa2/ethsw/ethsw.c            |  2 -
 include/net/switchdev.h                            |  9 ---
 net/dsa/slave.c                                    |  2 -
 net/switchdev/switchdev.c                          | 67 ++++++++--------------
 7 files changed, 25 insertions(+), 61 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 3756aaecd39c..73e5db176d7e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1968,8 +1968,6 @@ static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp,
 static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = {
 	.switchdev_port_attr_get	= mlxsw_sp_port_attr_get,
 	.switchdev_port_attr_set	= mlxsw_sp_port_attr_set,
-	.switchdev_port_obj_add		= mlxsw_sp_port_obj_add,
-	.switchdev_port_obj_del		= mlxsw_sp_port_obj_del,
 };
 
 static int
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 01403b530522..7f8da8873a96 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1337,8 +1337,6 @@ static int ocelot_port_obj_del(struct net_device *dev,
 static const struct switchdev_ops ocelot_port_switchdev_ops = {
 	.switchdev_port_attr_get	= ocelot_port_attr_get,
 	.switchdev_port_attr_set	= ocelot_port_attr_set,
-	.switchdev_port_obj_add		= ocelot_port_obj_add,
-	.switchdev_port_obj_del		= ocelot_port_obj_del,
 };
 
 static int ocelot_port_bridge_join(struct ocelot_port *ocelot_port,
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 806ffe1d906e..f05d5c1341b6 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2145,8 +2145,6 @@ static int rocker_port_obj_del(struct net_device *dev,
 static const struct switchdev_ops rocker_port_switchdev_ops = {
 	.switchdev_port_attr_get	= rocker_port_attr_get,
 	.switchdev_port_attr_set	= rocker_port_attr_set,
-	.switchdev_port_obj_add		= rocker_port_obj_add,
-	.switchdev_port_obj_del		= rocker_port_obj_del,
 };
 
 struct rocker_fib_event_work {
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index 83e1d92dc7f3..06a233c7cdd3 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -930,8 +930,6 @@ static int swdev_port_obj_del(struct net_device *netdev,
 static const struct switchdev_ops ethsw_port_switchdev_ops = {
 	.switchdev_port_attr_get	= swdev_port_attr_get,
 	.switchdev_port_attr_set	= swdev_port_attr_set,
-	.switchdev_port_obj_add		= swdev_port_obj_add,
-	.switchdev_port_obj_del		= swdev_port_obj_del,
 };
 
 /* For the moment, only flood setting needs to be updated */
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 6dc7de576167..866b6d148b77 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -121,10 +121,6 @@ typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj);
  * @switchdev_port_attr_get: Get a port attribute (see switchdev_attr).
  *
  * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr).
- *
- * @switchdev_port_obj_add: Add an object to port (see switchdev_obj_*).
- *
- * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj_*).
  */
 struct switchdev_ops {
 	int	(*switchdev_port_attr_get)(struct net_device *dev,
@@ -132,11 +128,6 @@ struct switchdev_ops {
 	int	(*switchdev_port_attr_set)(struct net_device *dev,
 					   const struct switchdev_attr *attr,
 					   struct switchdev_trans *trans);
-	int	(*switchdev_port_obj_add)(struct net_device *dev,
-					  const struct switchdev_obj *obj,
-					  struct switchdev_trans *trans);
-	int	(*switchdev_port_obj_del)(struct net_device *dev,
-					  const struct switchdev_obj *obj);
 };
 
 enum switchdev_notifier_type {
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index d00a0b6d4ce0..268119cf7117 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1050,8 +1050,6 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
 static const struct switchdev_ops dsa_slave_switchdev_ops = {
 	.switchdev_port_attr_get	= dsa_slave_port_attr_get,
 	.switchdev_port_attr_set	= dsa_slave_port_attr_set,
-	.switchdev_port_obj_add		= dsa_slave_port_obj_add,
-	.switchdev_port_obj_del		= dsa_slave_port_obj_del,
 };
 
 static struct device_type dsa_type = {
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 099434ec7996..fe23fac4dc4b 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -353,30 +353,29 @@ static size_t switchdev_obj_size(const struct switchdev_obj *obj)
 	return 0;
 }
 
-static int __switchdev_port_obj_add(struct net_device *dev,
-				    const struct switchdev_obj *obj,
-				    struct switchdev_trans *trans)
+static int switchdev_port_obj_notify(enum switchdev_notifier_type nt,
+				     struct net_device *dev,
+				     const struct switchdev_obj *obj,
+				     struct switchdev_trans *trans)
 {
-	const struct switchdev_ops *ops = dev->switchdev_ops;
-	struct net_device *lower_dev;
-	struct list_head *iter;
-	int err = -EOPNOTSUPP;
-
-	if (ops && ops->switchdev_port_obj_add)
-		return ops->switchdev_port_obj_add(dev, obj, trans);
+	int rc;
+	int err;
 
-	/* Switch device port(s) may be stacked under
-	 * bond/team/vlan dev, so recurse down to add object on
-	 * each port.
-	 */
+	struct switchdev_notifier_port_obj_info obj_info = {
+		.obj = obj,
+		.trans = trans,
+		.handled = false,
+	};
 
-	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		err = __switchdev_port_obj_add(lower_dev, obj, trans);
-		if (err)
-			break;
+	rc = call_switchdev_blocking_notifiers(nt, dev, &obj_info.info);
+	err = notifier_to_errno(rc);
+	if (err) {
+		WARN_ON(!obj_info.handled);
+		return err;
 	}
-
-	return err;
+	if (!obj_info.handled)
+		return -EOPNOTSUPP;
+	return 0;
 }
 
 static int switchdev_port_obj_add_now(struct net_device *dev,
@@ -397,7 +396,8 @@ static int switchdev_port_obj_add_now(struct net_device *dev,
 	 */
 
 	trans.ph_prepare = true;
-	err = __switchdev_port_obj_add(dev, obj, &trans);
+	err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD,
+					dev, obj, &trans);
 	if (err) {
 		/* Prepare phase failed: abort the transaction.  Any
 		 * resources reserved in the prepare phase are
@@ -416,7 +416,8 @@ static int switchdev_port_obj_add_now(struct net_device *dev,
 	 */
 
 	trans.ph_prepare = false;
-	err = __switchdev_port_obj_add(dev, obj, &trans);
+	err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD,
+					dev, obj, &trans);
 	WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id);
 	switchdev_trans_items_warn_destroy(dev, &trans);
 
@@ -471,26 +472,8 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_add);
 static int switchdev_port_obj_del_now(struct net_device *dev,
 				      const struct switchdev_obj *obj)
 {
-	const struct switchdev_ops *ops = dev->switchdev_ops;
-	struct net_device *lower_dev;
-	struct list_head *iter;
-	int err = -EOPNOTSUPP;
-
-	if (ops && ops->switchdev_port_obj_del)
-		return ops->switchdev_port_obj_del(dev, obj);
-
-	/* Switch device port(s) may be stacked under
-	 * bond/team/vlan dev, so recurse down to delete object on
-	 * each port.
-	 */
-
-	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		err = switchdev_port_obj_del_now(lower_dev, obj);
-		if (err)
-			break;
-	}
-
-	return err;
+	return switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_DEL,
+					 dev, obj, NULL);
 }
 
 static void switchdev_port_obj_del_deferred(struct net_device *dev,
-- 
cgit v1.2.3


From ab4a16869f25648570976a4d55923d0c9e7effb8 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 22 Nov 2018 23:48:05 +0000
Subject: rocker, dsa, ethsw: Don't filter VLAN events on bridge itself

Due to an explicit check in rocker_world_port_obj_vlan_add(),
dsa_slave_switchdev_event() resp. port_switchdev_event(), VLAN objects
that are added to a device that is not a front-panel port device are
ignored. Therefore this check is immaterial.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker_main.c | 3 ---
 drivers/staging/fsl-dpaa2/ethsw/ethsw.c   | 3 ---
 net/dsa/port.c                            | 3 ---
 3 files changed, 9 deletions(-)

diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index f05d5c1341b6..6213827e3956 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -1632,9 +1632,6 @@ rocker_world_port_obj_vlan_add(struct rocker_port *rocker_port,
 {
 	struct rocker_world_ops *wops = rocker_port->rocker->wops;
 
-	if (netif_is_bridge_master(vlan->obj.orig_dev))
-		return -EOPNOTSUPP;
-
 	if (!wops->port_obj_vlan_add)
 		return -EOPNOTSUPP;
 
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index 06a233c7cdd3..4fa37d6e598b 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -719,9 +719,6 @@ static int port_vlans_add(struct net_device *netdev,
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
 	int vid, err = 0;
 
-	if (netif_is_bridge_master(vlan->obj.orig_dev))
-		return -EOPNOTSUPP;
-
 	if (switchdev_trans_ph_prepare(trans))
 		return 0;
 
diff --git a/net/dsa/port.c b/net/dsa/port.c
index ed0595459df1..2d7e01b23572 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -252,9 +252,6 @@ int dsa_port_vlan_add(struct dsa_port *dp,
 		.vlan = vlan,
 	};
 
-	if (netif_is_bridge_master(vlan->obj.orig_dev))
-		return -EOPNOTSUPP;
-
 	if (br_vlan_enabled(dp->bridge_dev))
 		return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info);
 
-- 
cgit v1.2.3


From aea0a897af9e44c258e8ab9296fad417f1bc063a Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 23 Nov 2018 09:54:55 +0800
Subject: ptp: Fix pass zero to ERR_PTR() in ptp_clock_register

Fix smatch warning:

drivers/ptp/ptp_clock.c:298 ptp_clock_register() warn:
 passing zero to 'ERR_PTR'

'err' should be set while device_create_with_groups and
pps_register_source fails

Fixes: 85a66e550195 ("ptp: create "pins" together with the rest of attributes")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_clock.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 40fda23e4b05..8a81eecc0ecd 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -252,8 +252,10 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 	ptp->dev = device_create_with_groups(ptp_class, parent, ptp->devid,
 					     ptp, ptp->pin_attr_groups,
 					     "ptp%d", ptp->index);
-	if (IS_ERR(ptp->dev))
+	if (IS_ERR(ptp->dev)) {
+		err = PTR_ERR(ptp->dev);
 		goto no_device;
+	}
 
 	/* Register a new PPS source. */
 	if (info->pps) {
@@ -264,6 +266,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 		pps.owner = info->owner;
 		ptp->pps_source = pps_register_source(&pps, PTP_PPS_DEFAULTS);
 		if (!ptp->pps_source) {
+			err = -EINVAL;
 			pr_err("failed to register pps source\n");
 			goto no_pps;
 		}
-- 
cgit v1.2.3


From 2183435c251e09df11e1b431c84416424b5fd2ac Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Sat, 24 Nov 2018 12:01:41 +0300
Subject: net: fixup type in netdev_start_xmit()

Return code should be formally "netdev_tx_t".

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4b4207ebd5c0..1eeb019d85a3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4373,7 +4373,7 @@ static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_devi
 					    struct netdev_queue *txq, bool more)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
-	int rc;
+	netdev_tx_t rc;
 
 	rc = __netdev_start_xmit(ops, skb, dev, more);
 	if (rc == NETDEV_TX_OK)
-- 
cgit v1.2.3


From 21ab664aece634ade40ad9d1cca589895e9f9174 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Sat, 24 Nov 2018 18:36:21 +0800
Subject: cxgb4: remove set but not used variables 'multitrc, speed'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/chelsio/cxgb4/t4_hw.c:5883:6:
 warning: variable 'multitrc' set but not used [-Wunused-but-set-variable]

drivers/net/ethernet/chelsio/cxgb4/t4_hw.c:8585:32:
 warning: variable 'speed' set but not used [-Wunused-but-set-variable]

'multitrc' never used since introduction in
commit 8e3d04fd7d70 ("cxgb4: Add MPS tracing support")

'speed' never used since introduction in
commit c3168cabe1af ("cxgb4/cxgbvf: Handle 32-bit fw port capabilities")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 4cb261d5a077..e8c34292a0ec 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -5880,7 +5880,6 @@ int t4_set_trace_filter(struct adapter *adap, const struct trace_params *tp,
 {
 	int i, ofst = idx * 4;
 	u32 data_reg, mask_reg, cfg;
-	u32 multitrc = TRCMULTIFILTER_F;
 
 	if (!enable) {
 		t4_write_reg(adap, MPS_TRC_FILTER_MATCH_CTL_A_A + ofst, 0);
@@ -5900,7 +5899,6 @@ int t4_set_trace_filter(struct adapter *adap, const struct trace_params *tp,
 		 * maximum packet capture size of 9600 bytes is recommended.
 		 * Also in this mode, only trace0 can be enabled and running.
 		 */
-		multitrc = 0;
 		if (tp->snap_len > 9600 || idx)
 			return -EINVAL;
 	}
@@ -8606,7 +8604,7 @@ int t4_get_link_params(struct port_info *pi, unsigned int *link_okp,
 {
 	unsigned int fw_caps = pi->adapter->params.fw_caps_support;
 	struct fw_port_cmd port_cmd;
-	unsigned int action, link_ok, speed, mtu;
+	unsigned int action, link_ok, mtu;
 	fw_port_cap32_t linkattr;
 	int ret;
 
@@ -8640,7 +8638,6 @@ int t4_get_link_params(struct port_info *pi, unsigned int *link_okp,
 		mtu = FW_PORT_CMD_MTU32_G(
 			be32_to_cpu(port_cmd.u.info32.auxlinfo32_mtu32));
 	}
-	speed = fwcap_to_speed(linkattr);
 
 	*link_okp = link_ok;
 	*speedp = fwcap_to_speed(linkattr);
-- 
cgit v1.2.3


From 3c18aa1464f9232d6abac8d7b4540f61b0658d62 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 24 Nov 2018 15:03:02 +0000
Subject: net: qualcomm: rmnet: move null check on dev before dereferecing it

Currently dev is dereferenced by the call dev_net(dev) before dev is null
checked.  Fix this by null checking dev before the potential null
pointer dereference.

Detected by CoverityScan, CID#1462955 ("Dereference before null check")

Fixes: 23790ef12082 ("net: qualcomm: rmnet: Allow to configure flags for existing devices")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 5f4e447c5dce..b8bbee645f51 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -301,10 +301,13 @@ static int rmnet_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct rmnet_port *port;
 	u16 mux_id;
 
+	if (!dev)
+		return -ENODEV;
+
 	real_dev = __dev_get_by_index(dev_net(dev),
 				      nla_get_u32(tb[IFLA_LINK]));
 
-	if (!real_dev || !dev || !rmnet_is_real_dev_registered(real_dev))
+	if (!real_dev || !rmnet_is_real_dev_registered(real_dev))
 		return -ENODEV;
 
 	port = rmnet_get_port_rtnl(real_dev);
-- 
cgit v1.2.3


From 358be656406dce296fafeac7a913ba33e9a66971 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 24 Nov 2018 21:09:26 -0500
Subject: selftests/net: add txring_overwrite

Packet sockets with PACKET_TX_RING send skbs with user data in frags.

Before commit 5cd8d46ea156 ("packet: copy user buffers before orphan
or clone") ring slots could be released prematurely, possibly allowing
a process to overwrite data still in flight.

This test opens two packet sockets, one to send and one to read.
The sender has a tx ring of one slot. It sends two packets with
different payload, then reads both and verifies their payload.

Before the above commit, both receive calls return the same data as
the send calls use the same buffer. From the commit, the clone
needed for looping onto a packet socket triggers an skb_copy_ubufs
to create a private copy. The separate sends each arrive correctly.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/.gitignore         |   1 +
 tools/testing/selftests/net/Makefile           |   2 +-
 tools/testing/selftests/net/run_afpackettests  |  10 ++
 tools/testing/selftests/net/txring_overwrite.c | 179 +++++++++++++++++++++++++
 4 files changed, 191 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/net/txring_overwrite.c

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 8cf22b3c2563..7f57b916e6b2 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -14,4 +14,5 @@ udpgso_bench_rx
 udpgso_bench_tx
 tcp_inq
 tls
+txring_overwrite
 ip_defrag
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index eec359895feb..7aebbcaa91bf 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -11,7 +11,7 @@ TEST_PROGS += udpgro_bench.sh udpgro.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
-TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd
+TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
 TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests
index bea079edc278..2dc95fda7ef7 100755
--- a/tools/testing/selftests/net/run_afpackettests
+++ b/tools/testing/selftests/net/run_afpackettests
@@ -25,3 +25,13 @@ if [ $? -ne 0 ]; then
 else
 	echo "[PASS]"
 fi
+
+echo "--------------------"
+echo "running txring_overwrite test"
+echo "--------------------"
+./in_netns.sh ./txring_overwrite
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+else
+	echo "[PASS]"
+fi
diff --git a/tools/testing/selftests/net/txring_overwrite.c b/tools/testing/selftests/net/txring_overwrite.c
new file mode 100644
index 000000000000..fd8b1c663c39
--- /dev/null
+++ b/tools/testing/selftests/net/txring_overwrite.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Verify that consecutive sends over packet tx_ring are mirrored
+ * with their original content intact.
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <assert.h>
+#include <error.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/filter.h>
+#include <linux/if_packet.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <pthread.h>
+#include <sched.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/utsname.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+const int eth_off = TPACKET_HDRLEN - sizeof(struct sockaddr_ll);
+const int cfg_frame_size = 1000;
+
+static void build_packet(void *buffer, size_t blen, char payload_char)
+{
+	struct udphdr *udph;
+	struct ethhdr *eth;
+	struct iphdr *iph;
+	size_t off = 0;
+
+	memset(buffer, 0, blen);
+
+	eth = buffer;
+	eth->h_proto = htons(ETH_P_IP);
+
+	off += sizeof(*eth);
+	iph = buffer + off;
+	iph->ttl	= 8;
+	iph->ihl	= 5;
+	iph->version	= 4;
+	iph->saddr	= htonl(INADDR_LOOPBACK);
+	iph->daddr	= htonl(INADDR_LOOPBACK + 1);
+	iph->protocol	= IPPROTO_UDP;
+	iph->tot_len	= htons(blen - off);
+	iph->check	= 0;
+
+	off += sizeof(*iph);
+	udph = buffer + off;
+	udph->dest	= htons(8000);
+	udph->source	= htons(8001);
+	udph->len	= htons(blen - off);
+	udph->check	= 0;
+
+	off += sizeof(*udph);
+	memset(buffer + off, payload_char, blen - off);
+}
+
+static int setup_rx(void)
+{
+	int fdr;
+
+	fdr = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP));
+	if (fdr == -1)
+		error(1, errno, "socket r");
+
+	return fdr;
+}
+
+static int setup_tx(char **ring)
+{
+	struct sockaddr_ll laddr = {};
+	struct tpacket_req req = {};
+	int fdt;
+
+	fdt = socket(PF_PACKET, SOCK_RAW, 0);
+	if (fdt == -1)
+		error(1, errno, "socket t");
+
+	laddr.sll_family = AF_PACKET;
+	laddr.sll_protocol = htons(0);
+	laddr.sll_ifindex = if_nametoindex("lo");
+	if (!laddr.sll_ifindex)
+		error(1, errno, "if_nametoindex");
+
+	if (bind(fdt, (void *)&laddr, sizeof(laddr)))
+		error(1, errno, "bind fdt");
+
+	req.tp_block_size = getpagesize();
+	req.tp_block_nr   = 1;
+	req.tp_frame_size = getpagesize();
+	req.tp_frame_nr   = 1;
+
+	if (setsockopt(fdt, SOL_PACKET, PACKET_TX_RING,
+		       (void *)&req, sizeof(req)))
+		error(1, errno, "setsockopt ring");
+
+	*ring = mmap(0, req.tp_block_size * req.tp_block_nr,
+		     PROT_READ | PROT_WRITE, MAP_SHARED, fdt, 0);
+	if (!*ring)
+		error(1, errno, "mmap");
+
+	return fdt;
+}
+
+static void send_pkt(int fdt, void *slot, char payload_char)
+{
+	struct tpacket_hdr *header = slot;
+	int ret;
+
+	while (header->tp_status != TP_STATUS_AVAILABLE)
+		usleep(1000);
+
+	build_packet(slot + eth_off, cfg_frame_size, payload_char);
+
+	header->tp_len = cfg_frame_size;
+	header->tp_status = TP_STATUS_SEND_REQUEST;
+
+	ret = sendto(fdt, NULL, 0, 0, NULL, 0);
+	if (ret == -1)
+		error(1, errno, "kick tx");
+}
+
+static int read_verify_pkt(int fdr, char payload_char)
+{
+	char buf[100];
+	int ret;
+
+	ret = read(fdr, buf, sizeof(buf));
+	if (ret != sizeof(buf))
+		error(1, errno, "read");
+
+	if (buf[60] != payload_char) {
+		printf("wrong pattern: 0x%x != 0x%x\n", buf[60], payload_char);
+		return 1;
+	}
+
+	printf("read: %c (0x%x)\n", buf[60], buf[60]);
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	const char payload_patterns[] = "ab";
+	char *ring;
+	int fdr, fdt, ret = 0;
+
+	fdr = setup_rx();
+	fdt = setup_tx(&ring);
+
+	send_pkt(fdt, ring, payload_patterns[0]);
+	send_pkt(fdt, ring, payload_patterns[1]);
+
+	ret |= read_verify_pkt(fdr, payload_patterns[0]);
+	ret |= read_verify_pkt(fdr, payload_patterns[1]);
+
+	if (close(fdt))
+		error(1, errno, "close t");
+	if (close(fdr))
+		error(1, errno, "close r");
+
+	return ret;
+}
-- 
cgit v1.2.3


From 620344c43edfa020bbadfd81a144ebe5181fc94f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 25 Nov 2018 14:30:29 +0100
Subject: net: core: add __netdev_sent_queue as variant of
 __netdev_tx_sent_queue

Similar to netdev_sent_queue add helper __netdev_sent_queue as variant
of __netdev_tx_sent_queue.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1eeb019d85a3..9b00043effa3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3226,6 +3226,14 @@ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes)
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes);
 }
 
+static inline bool __netdev_sent_queue(struct net_device *dev,
+				       unsigned int bytes,
+				       bool xmit_more)
+{
+	return __netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes,
+				      xmit_more);
+}
+
 static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
 					     unsigned int pkts, unsigned int bytes)
 {
-- 
cgit v1.2.3


From 2e6eedb4813e34d8d84ac0eb3afb668966f3f356 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 25 Nov 2018 14:31:54 +0100
Subject: r8169: make use of xmit_more and __netdev_sent_queue

Make use of xmit_more and add the functionality introduced with
3e59020abf0f ("net: bql: add __netdev_tx_sent_queue()").
I used the mlx4 driver as template.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 12811f18c134..3624e67aef72 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6069,6 +6069,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	struct device *d = tp_to_dev(tp);
 	dma_addr_t mapping;
 	u32 opts[2], len;
+	bool stop_queue;
 	int frags;
 
 	if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) {
@@ -6110,8 +6111,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	txd->opts2 = cpu_to_le32(opts[1]);
 
-	netdev_sent_queue(dev, skb->len);
-
 	skb_tx_timestamp(skb);
 
 	/* Force memory writes to complete before releasing descriptor */
@@ -6124,16 +6123,16 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	tp->cur_tx += frags + 1;
 
-	RTL_W8(tp, TxPoll, NPQ);
+	stop_queue = !rtl_tx_slots_avail(tp, MAX_SKB_FRAGS);
+	if (unlikely(stop_queue))
+		netif_stop_queue(dev);
 
-	mmiowb();
+	if (__netdev_sent_queue(dev, skb->len, skb->xmit_more)) {
+		RTL_W8(tp, TxPoll, NPQ);
+		mmiowb();
+	}
 
-	if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) {
-		/* Avoid wrongly optimistic queue wake-up: rtl_tx thread must
-		 * not miss a ring update when it notices a stopped queue.
-		 */
-		smp_wmb();
-		netif_stop_queue(dev);
+	if (unlikely(stop_queue)) {
 		/* Sync with rtl_tx:
 		 * - publish queue status and cur_tx ring index (write barrier)
 		 * - refresh dirty_tx ring index (read barrier).
-- 
cgit v1.2.3


From 40b1c813ba8e0aac9ee36b57f2835777506084c6 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sun, 25 Nov 2018 16:08:51 +0000
Subject: net: bridge: remove redundant checks for null p->dev and p->br

A recent change added a null check on p->dev after p->dev was being
dereferenced by the ns_capable check on p->dev. It turns out that
neither the p->dev and p->br null checks are necessary, and can be
removed, which cleans up a static analyis warning.

As Nikolay Aleksandrov noted, these checks can be removed because:

"My reasoning of why it shouldn't be possible:
- On port add new_nbp() sets both p->dev and p->br before creating
  kobj/sysfs

- On port del (trickier) del_nbp() calls kobject_del() before call_rcu()
  to destroy the port which in turn calls sysfs_remove_dir() which uses
  kernfs_remove() which deactivates (shouldn't be able to open new
  files) and calls kernfs_drain() to drain current open/mmaped files in
  the respective dir before continuing, thus making it impossible to
  open a bridge port sysfs file with p->dev and p->br equal to NULL.

So I think it's safe to remove those checks altogether. It'd be nice to
get a second look over my reasoning as I might be missing something in
sysfs/kernfs call path."

Thanks to Nikolay Aleksandrov's suggestion to remove the check and
David Miller for sanity checking this.

Detected by CoverityScan, CID#751490 ("Dereference before null check")

Fixes: a5f3ea54f3cc ("net: bridge: add support for raw sysfs port options")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_sysfs_if.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 7c87a2fe5248..88715edb119a 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -320,9 +320,6 @@ static ssize_t brport_store(struct kobject *kobj,
 	if (!rtnl_trylock())
 		return restart_syscall();
 
-	if (!p->dev || !p->br)
-		goto out_unlock;
-
 	if (brport_attr->store_raw) {
 		char *buf_copy;
 
-- 
cgit v1.2.3


From 4bffc669d6248d655aeb985a0e51bfaaf21c8b40 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 25 Nov 2018 08:26:23 -0800
Subject: net: remove unsafe skb_insert()

I do not see how one can effectively use skb_insert() without holding
some kind of lock. Otherwise other cpus could have changed the list
right before we have a chance of acquiring list->lock.

Only existing user is in drivers/infiniband/hw/nes/nes_mgt.c and this
one probably meant to use __skb_insert() since it appears nesqp->pau_list
is protected by nesqp->pau_lock. This looks like nesqp->pau_lock
could be removed, since nesqp->pau_list.lock could be used instead.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Faisal Latif <faisal.latif@intel.com>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: linux-rdma <linux-rdma@vger.kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/nes/nes_mgt.c |  4 ++--
 include/linux/skbuff.h              |  2 --
 net/core/skbuff.c                   | 22 ----------------------
 3 files changed, 2 insertions(+), 26 deletions(-)

diff --git a/drivers/infiniband/hw/nes/nes_mgt.c b/drivers/infiniband/hw/nes/nes_mgt.c
index fc0c191014e9..cc4dce5c3e5f 100644
--- a/drivers/infiniband/hw/nes/nes_mgt.c
+++ b/drivers/infiniband/hw/nes/nes_mgt.c
@@ -551,14 +551,14 @@ static void queue_fpdus(struct sk_buff *skb, struct nes_vnic *nesvnic, struct ne
 
 	/* Queue skb by sequence number */
 	if (skb_queue_len(&nesqp->pau_list) == 0) {
-		skb_queue_head(&nesqp->pau_list, skb);
+		__skb_queue_head(&nesqp->pau_list, skb);
 	} else {
 		skb_queue_walk(&nesqp->pau_list, tmpskb) {
 			cb = (struct nes_rskb_cb *)&tmpskb->cb[0];
 			if (before(seqnum, cb->seqnum))
 				break;
 		}
-		skb_insert(tmpskb, skb, &nesqp->pau_list);
+		__skb_insert(skb, tmpskb->prev, tmpskb, &nesqp->pau_list);
 	}
 	if (nesqp->pau_state == PAU_READY)
 		process_it = true;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f17a7452ac7b..73902acf2b71 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1749,8 +1749,6 @@ static inline void skb_queue_head_init_class(struct sk_buff_head *list,
  *	The "__skb_xxxx()" functions are the non-atomic ones that
  *	can only be called with interrupts disabled.
  */
-void skb_insert(struct sk_buff *old, struct sk_buff *newsk,
-		struct sk_buff_head *list);
 static inline void __skb_insert(struct sk_buff *newsk,
 				struct sk_buff *prev, struct sk_buff *next,
 				struct sk_buff_head *list)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9a8a72cefe9b..02cd7ae3d0fb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2990,28 +2990,6 @@ void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head
 }
 EXPORT_SYMBOL(skb_append);
 
-/**
- *	skb_insert	-	insert a buffer
- *	@old: buffer to insert before
- *	@newsk: buffer to insert
- *	@list: list to use
- *
- *	Place a packet before a given packet in a list. The list locks are
- * 	taken and this function is atomic with respect to other list locked
- *	calls.
- *
- *	A buffer cannot be placed on two lists at the same time.
- */
-void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&list->lock, flags);
-	__skb_insert(newsk, old->prev, old, list);
-	spin_unlock_irqrestore(&list->lock, flags);
-}
-EXPORT_SYMBOL(skb_insert);
-
 static inline void skb_split_inside_header(struct sk_buff *skb,
 					   struct sk_buff* skb1,
 					   const u32 len, const int pos)
-- 
cgit v1.2.3


From cf0dd411e80f7066cabf69899724e48dd3192b99 Mon Sep 17 00:00:00 2001
From: Rustam Kovhaev <rkovhaev@gmail.com>
Date: Fri, 23 Nov 2018 15:48:16 -0800
Subject: bpf, tags: Fix DEFINE_PER_CPU expansion

Building tags produces warning:

  ctags: Warning: kernel/bpf/local_storage.c:10: null expansion of name pattern "\1"

Let's use the same fix as in commit 25528213fe9f ("tags: Fix DEFINE_PER_CPU
expansions"), even though it violates the usual code style.

Signed-off-by: Rustam Kovhaev <rkovhaev@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/local_storage.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index c97a8f968638..9e94b1cc6cf2 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -7,8 +7,7 @@
 #include <linux/rbtree.h>
 #include <linux/slab.h>
 
-DEFINE_PER_CPU(struct bpf_cgroup_storage*,
-	       bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
+DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
 
 #ifdef CONFIG_CGROUP_BPF
 
-- 
cgit v1.2.3


From 311fe1a813324ea6d8172a3e9eefb1b274c72fea Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sun, 25 Nov 2018 23:32:51 +0000
Subject: bpf: btf: fix spelling mistake "Memmber" -> "Member"

There is a spelling mistake in a btf_verifier_log_member message,
fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/btf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 69da9169819a..a09b2f94ab25 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1621,7 +1621,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 
 		if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
 			btf_verifier_log_member(env, t, member,
-						"Memmber bits_offset exceeds its struct size");
+						"Member bits_offset exceeds its struct size");
 			return -EINVAL;
 		}
 
-- 
cgit v1.2.3


From ffac28f95a98a87db0850801cd98771a08bb1dec Mon Sep 17 00:00:00 2001
From: David Calavera <david.calavera@gmail.com>
Date: Fri, 23 Nov 2018 15:58:39 -0800
Subject: bpf: align map type names formatting.

Make the formatting for map_type_name array consistent.

Signed-off-by: David Calavera <david.calavera@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/map.c | 46 +++++++++++++++++++++++-----------------------
 1 file changed, 23 insertions(+), 23 deletions(-)

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index b0ebbed7d1a6..cbd3080e72c7 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -52,30 +52,30 @@
 #include "main.h"
 
 static const char * const map_type_name[] = {
-	[BPF_MAP_TYPE_UNSPEC]		= "unspec",
-	[BPF_MAP_TYPE_HASH]		= "hash",
-	[BPF_MAP_TYPE_ARRAY]		= "array",
-	[BPF_MAP_TYPE_PROG_ARRAY]	= "prog_array",
-	[BPF_MAP_TYPE_PERF_EVENT_ARRAY]	= "perf_event_array",
-	[BPF_MAP_TYPE_PERCPU_HASH]	= "percpu_hash",
-	[BPF_MAP_TYPE_PERCPU_ARRAY]	= "percpu_array",
-	[BPF_MAP_TYPE_STACK_TRACE]	= "stack_trace",
-	[BPF_MAP_TYPE_CGROUP_ARRAY]	= "cgroup_array",
-	[BPF_MAP_TYPE_LRU_HASH]		= "lru_hash",
-	[BPF_MAP_TYPE_LRU_PERCPU_HASH]	= "lru_percpu_hash",
-	[BPF_MAP_TYPE_LPM_TRIE]		= "lpm_trie",
-	[BPF_MAP_TYPE_ARRAY_OF_MAPS]	= "array_of_maps",
-	[BPF_MAP_TYPE_HASH_OF_MAPS]	= "hash_of_maps",
-	[BPF_MAP_TYPE_DEVMAP]		= "devmap",
-	[BPF_MAP_TYPE_SOCKMAP]		= "sockmap",
-	[BPF_MAP_TYPE_CPUMAP]		= "cpumap",
-	[BPF_MAP_TYPE_XSKMAP]           = "xskmap",
-	[BPF_MAP_TYPE_SOCKHASH]		= "sockhash",
-	[BPF_MAP_TYPE_CGROUP_STORAGE]	= "cgroup_storage",
-	[BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray",
+	[BPF_MAP_TYPE_UNSPEC]			= "unspec",
+	[BPF_MAP_TYPE_HASH]			= "hash",
+	[BPF_MAP_TYPE_ARRAY]			= "array",
+	[BPF_MAP_TYPE_PROG_ARRAY]		= "prog_array",
+	[BPF_MAP_TYPE_PERF_EVENT_ARRAY]		= "perf_event_array",
+	[BPF_MAP_TYPE_PERCPU_HASH]		= "percpu_hash",
+	[BPF_MAP_TYPE_PERCPU_ARRAY]		= "percpu_array",
+	[BPF_MAP_TYPE_STACK_TRACE]		= "stack_trace",
+	[BPF_MAP_TYPE_CGROUP_ARRAY]		= "cgroup_array",
+	[BPF_MAP_TYPE_LRU_HASH]			= "lru_hash",
+	[BPF_MAP_TYPE_LRU_PERCPU_HASH]		= "lru_percpu_hash",
+	[BPF_MAP_TYPE_LPM_TRIE]			= "lpm_trie",
+	[BPF_MAP_TYPE_ARRAY_OF_MAPS]		= "array_of_maps",
+	[BPF_MAP_TYPE_HASH_OF_MAPS]		= "hash_of_maps",
+	[BPF_MAP_TYPE_DEVMAP]			= "devmap",
+	[BPF_MAP_TYPE_SOCKMAP]			= "sockmap",
+	[BPF_MAP_TYPE_CPUMAP]			= "cpumap",
+	[BPF_MAP_TYPE_XSKMAP]			= "xskmap",
+	[BPF_MAP_TYPE_SOCKHASH]			= "sockhash",
+	[BPF_MAP_TYPE_CGROUP_STORAGE]		= "cgroup_storage",
+	[BPF_MAP_TYPE_REUSEPORT_SOCKARRAY]	= "reuseport_sockarray",
 	[BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE]	= "percpu_cgroup_storage",
-	[BPF_MAP_TYPE_QUEUE] = "queue",
-	[BPF_MAP_TYPE_STACK] = "stack",
+	[BPF_MAP_TYPE_QUEUE]			= "queue",
+	[BPF_MAP_TYPE_STACK]			= "stack",
 };
 
 static bool map_is_per_cpu(__u32 type)
-- 
cgit v1.2.3


From 0f597ed435b9ea1296e25474b762bedceba97a50 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 20 Nov 2018 14:12:18 -0800
Subject: net/mlx5: EQ, Introduce atomic notifier chain subscription API

Use atomic_notifier_chain to fire firmware events at internal mlx5 core
components such as eswitch/fpga/clock/FW tracer/etc.., this is to
avoid explicit calls from low level mlx5_core to upper components and to
simplify the mlx5_core API for future developments.

Simply provide register/unregister notifiers API and call the notifier
chain on firmware async events.

Example: to subscribe to a FW event:
struct mlx5_nb port_event;

MLX5_NB_INIT(&port_event, port_event_handler, PORT_CHANGE);
mlx5_eq_notifier_register(mdev, &port_event);

where:
 - port_event_handler is the notifier block callback.
 - PORT_EVENT is the suffix of MLX5_EVENT_TYPE_PORT_CHANGE.

The above will guarantee that port_event_handler will receive all FW
events of the type MLX5_EVENT_TYPE_PORT_CHANGE.

To receive all FW/HW events one can subscribe to
MLX5_EVENT_TYPE_NOTIFY_ANY.

The next few patches will start moving all mlx5 core components to use
this new API and cleanup mlx5_eq_async_int misx handler from component
explicit calls and specific logic.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       | 42 ++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h   |  5 +++
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |  5 +++
 include/linux/mlx5/device.h                        | 10 +++++-
 include/linux/mlx5/eq.h                            | 16 +++++++--
 5 files changed, 72 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 6ba8e401a0c7..34e4b2c246ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -31,6 +31,7 @@
  */
 
 #include <linux/interrupt.h>
+#include <linux/notifier.h>
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/eq.h>
@@ -68,8 +69,10 @@ struct mlx5_irq_info {
 struct mlx5_eq_table {
 	struct list_head        comp_eqs_list;
 	struct mlx5_eq          pages_eq;
-	struct mlx5_eq          async_eq;
 	struct mlx5_eq	        cmd_eq;
+	struct mlx5_eq          async_eq;
+
+	struct atomic_notifier_head nh[MLX5_EVENT_TYPE_MAX];
 
 	struct mutex            lock; /* sync async eqs creations */
 	int			num_comp_vectors;
@@ -316,13 +319,17 @@ u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq)
 static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 {
 	struct mlx5_eq *eq = eq_ptr;
-	struct mlx5_core_dev *dev = eq->dev;
+	struct mlx5_eq_table *eqt;
+	struct mlx5_core_dev *dev;
 	struct mlx5_eqe *eqe;
 	int set_ci = 0;
 	u32 cqn = -1;
 	u32 rsn;
 	u8 port;
 
+	dev = eq->dev;
+	eqt = dev->priv.eq_table;
+
 	while ((eqe = next_eqe_sw(eq))) {
 		/*
 		 * Make sure we read EQ entry contents after we've
@@ -437,6 +444,13 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 			break;
 		}
 
+		if (likely(eqe->type < MLX5_EVENT_TYPE_MAX))
+			atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe);
+		else
+			mlx5_core_warn_once(dev, "notifier_call_chain is not setup for eqe: %d\n", eqe->type);
+
+		atomic_notifier_call_chain(&eqt->nh[MLX5_EVENT_TYPE_NOTIFY_ANY], eqe->type, eqe);
+
 		++eq->cons_index;
 		++set_ci;
 
@@ -625,7 +639,7 @@ int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *eq_table;
-	int err;
+	int i, err;
 
 	eq_table = kvzalloc(sizeof(*eq_table), GFP_KERNEL);
 	if (!eq_table)
@@ -638,6 +652,8 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 		goto kvfree_eq_table;
 
 	mutex_init(&eq_table->lock);
+	for (i = 0; i < MLX5_EVENT_TYPE_MAX; i++)
+		ATOMIC_INIT_NOTIFIER_HEAD(&eq_table->nh[i]);
 
 	return 0;
 
@@ -1202,3 +1218,23 @@ void mlx5_eq_table_destroy(struct mlx5_core_dev *dev)
 	destroy_async_eqs(dev);
 	free_irq_vectors(dev);
 }
+
+int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
+{
+	struct mlx5_eq_table *eqt = dev->priv.eq_table;
+
+	if (nb->event_type >= MLX5_EVENT_TYPE_MAX)
+		return -EINVAL;
+
+	return atomic_notifier_chain_register(&eqt->nh[nb->event_type], &nb->nb);
+}
+
+int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
+{
+	struct mlx5_eq_table *eqt = dev->priv.eq_table;
+
+	if (nb->event_type >= MLX5_EVENT_TYPE_MAX)
+		return -EINVAL;
+
+	return atomic_notifier_chain_unregister(&eqt->nh[nb->event_type], &nb->nb);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index 6d8c8a57d52b..c0fb6d72b695 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -4,6 +4,8 @@
 #ifndef __LIB_MLX5_EQ_H__
 #define __LIB_MLX5_EQ_H__
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/eq.h>
+#include <linux/mlx5/cq.h>
 
 #define MLX5_MAX_IRQ_NAME   (32)
 #define MLX5_EQE_SIZE       (sizeof(struct mlx5_eqe))
@@ -90,4 +92,7 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
 struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev);
 #endif
 
+int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
+int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 21727d9eeb84..e06c6e16ffc9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -78,6 +78,11 @@ do {									\
 		 __func__, __LINE__, current->pid,			\
 		##__VA_ARGS__)
 
+#define mlx5_core_warn_once(__dev, format, ...)				\
+	dev_warn_once(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
+		      __func__, __LINE__, current->pid,			\
+		      ##__VA_ARGS__)
+
 #define mlx5_core_info(__dev, format, ...)				\
 	dev_info(&(__dev)->pdev->dev, format, ##__VA_ARGS__)
 
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index e326524bafcc..f7c8bebfe472 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -301,9 +301,15 @@ enum {
 	MLX5_EVENT_QUEUE_TYPE_DCT = 6,
 };
 
+/* mlx5 components can subscribe to any one of these events via
+ * mlx5_eq_notifier_register API.
+ */
 enum mlx5_event {
+	/* Special value to subscribe to any event */
+	MLX5_EVENT_TYPE_NOTIFY_ANY	   = 0x0,
+	/* HW events enum start: comp events are not subscribable */
 	MLX5_EVENT_TYPE_COMP		   = 0x0,
-
+	/* HW Async events enum start: subscribable events */
 	MLX5_EVENT_TYPE_PATH_MIG	   = 0x01,
 	MLX5_EVENT_TYPE_COMM_EST	   = 0x02,
 	MLX5_EVENT_TYPE_SQ_DRAINED	   = 0x03,
@@ -341,6 +347,8 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_FPGA_QP_ERROR      = 0x21,
 
 	MLX5_EVENT_TYPE_DEVICE_TRACER      = 0x26,
+
+	MLX5_EVENT_TYPE_MAX                = MLX5_EVENT_TYPE_DEVICE_TRACER + 1,
 };
 
 enum {
diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h
index 71d82c5a1a02..00045cc4ea11 100644
--- a/include/linux/mlx5/eq.h
+++ b/include/linux/mlx5/eq.h
@@ -4,8 +4,6 @@
 #ifndef MLX5_CORE_EQ_H
 #define MLX5_CORE_EQ_H
 
-#include <linux/mlx5/driver.h>
-
 enum {
 	MLX5_EQ_PAGEREQ_IDX        = 0,
 	MLX5_EQ_CMD_IDX            = 1,
@@ -22,6 +20,7 @@ enum {
 #define MLX5_NUM_SPARE_EQE (0x80)
 
 struct mlx5_eq;
+struct mlx5_core_dev;
 
 struct mlx5_eq_param {
 	u8             index;
@@ -57,4 +56,17 @@ static inline u32 mlx5_eq_update_cc(struct mlx5_eq *eq, u32 cc)
 	return cc;
 }
 
+struct mlx5_nb {
+	struct notifier_block nb;
+	u8 event_type;
+};
+
+#define mlx5_nb_cof(ptr, type, member) \
+	(container_of(container_of(ptr, struct mlx5_nb, nb), type, member))
+
+#define MLX5_NB_INIT(name, handler, event) do {              \
+	(name)->nb.notifier_call = handler;                  \
+	(name)->event_type = MLX5_EVENT_TYPE_##event;        \
+} while (0)
+
 #endif /* MLX5_CORE_EQ_H */
-- 
cgit v1.2.3


From 720a936d407709dcbcf714293112667677d8c967 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 20 Nov 2018 14:12:19 -0800
Subject: net/mlx5: FWTrace, Use async events chain

Remove the explicit call to mlx5_fw_tracer_event on
MLX5_EVENT_TYPE_DEVICE_TRACER and let fw tracer to register
its own handler when its ready.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c   | 27 ++++++++++++----------
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.h   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  4 ----
 3 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index d4ec93bde4de..6999f4486e9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 #define CREATE_TRACE_POINTS
+#include "lib/eq.h"
 #include "fw_tracer.h"
 #include "fw_tracer_tracepoint.h"
 
@@ -846,9 +847,9 @@ free_tracer:
 	return ERR_PTR(err);
 }
 
-/* Create HW resources + start tracer
- * must be called before Async EQ is created
- */
+static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data);
+
+/* Create HW resources + start tracer */
 int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 {
 	struct mlx5_core_dev *dev;
@@ -874,6 +875,9 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 		goto err_dealloc_pd;
 	}
 
+	MLX5_NB_INIT(&tracer->nb, fw_tracer_event, DEVICE_TRACER);
+	mlx5_eq_notifier_register(dev, &tracer->nb);
+
 	mlx5_fw_tracer_start(tracer);
 
 	return 0;
@@ -883,9 +887,7 @@ err_dealloc_pd:
 	return err;
 }
 
-/* Stop tracer + Cleanup HW resources
- * must be called after Async EQ is destroyed
- */
+/* Stop tracer + Cleanup HW resources */
 void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 {
 	if (IS_ERR_OR_NULL(tracer))
@@ -893,7 +895,7 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 
 	mlx5_core_dbg(tracer->dev, "FWTracer: Cleanup, is owner ? (%d)\n",
 		      tracer->owner);
-
+	mlx5_eq_notifier_unregister(tracer->dev, &tracer->nb);
 	cancel_work_sync(&tracer->ownership_change_work);
 	cancel_work_sync(&tracer->handle_traces_work);
 
@@ -922,12 +924,11 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 	kfree(tracer);
 }
 
-void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
+static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data)
 {
-	struct mlx5_fw_tracer *tracer = dev->tracer;
-
-	if (!tracer)
-		return;
+	struct mlx5_fw_tracer *tracer = mlx5_nb_cof(nb, struct mlx5_fw_tracer, nb);
+	struct mlx5_core_dev *dev = tracer->dev;
+	struct mlx5_eqe *eqe = data;
 
 	switch (eqe->sub_type) {
 	case MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE:
@@ -942,6 +943,8 @@ void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
 		mlx5_core_dbg(dev, "FWTracer: Event with unrecognized subtype: sub_type %d\n",
 			      eqe->sub_type);
 	}
+
+	return NOTIFY_OK;
 }
 
 EXPORT_TRACEPOINT_SYMBOL(mlx5_fw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
index 0347f2dd5cee..a8b8747f2b61 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -55,6 +55,7 @@
 
 struct mlx5_fw_tracer {
 	struct mlx5_core_dev *dev;
+	struct mlx5_nb        nb;
 	bool owner;
 	u8   trc_ver;
 	struct workqueue_struct *work_queue;
@@ -170,6 +171,5 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev);
 int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer);
 void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer);
 void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer);
-void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 34e4b2c246ff..c7c436b0ed2e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -434,10 +434,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 			general_event_handler(dev, eqe);
 			break;
 
-		case MLX5_EVENT_TYPE_DEVICE_TRACER:
-			mlx5_fw_tracer_event(dev, eqe);
-			break;
-
 		default:
 			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
 				       eqe->type, eq->eqn);
-- 
cgit v1.2.3


From a52a7d01fde117bc6d57602e2e7e947037c865b0 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 20 Nov 2018 14:12:20 -0800
Subject: net/mlx5: FPGA, Use async events chain

Remove the explicit call to mlx5_fpga_event on
MLX5_EVENT_TYPE_FPGA_ERROR or MLX5_EVENT_TYPE_FPGA_QP_ERROR
let fpga core to register its own handler when its ready.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  5 ---
 .../net/ethernet/mellanox/mlx5/core/fpga/core.c    | 38 +++++++++++++++++++---
 .../net/ethernet/mellanox/mlx5/core/fpga/core.h    | 11 +++----
 3 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index c7c436b0ed2e..8aabd23d2166 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -421,11 +421,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 			mlx5_pps_event(dev, eqe);
 			break;
 
-		case MLX5_EVENT_TYPE_FPGA_ERROR:
-		case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
-			mlx5_fpga_event(dev, eqe->type, &eqe->data.raw);
-			break;
-
 		case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
 			mlx5_temp_warning_event(dev, eqe);
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
index 436a8136f26f..27c5f6c7d36a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
@@ -36,6 +36,7 @@
 
 #include "mlx5_core.h"
 #include "lib/mlx5.h"
+#include "lib/eq.h"
 #include "fpga/core.h"
 #include "fpga/conn.h"
 
@@ -145,6 +146,22 @@ static int mlx5_fpga_device_brb(struct mlx5_fpga_device *fdev)
 	return 0;
 }
 
+static int mlx5_fpga_event(struct mlx5_fpga_device *, unsigned long, void *);
+
+static int fpga_err_event(struct notifier_block *nb, unsigned long event, void *eqe)
+{
+	struct mlx5_fpga_device *fdev = mlx5_nb_cof(nb, struct mlx5_fpga_device, fpga_err_nb);
+
+	return mlx5_fpga_event(fdev, event, eqe);
+}
+
+static int fpga_qp_err_event(struct notifier_block *nb, unsigned long event, void *eqe)
+{
+	struct mlx5_fpga_device *fdev = mlx5_nb_cof(nb, struct mlx5_fpga_device, fpga_qp_err_nb);
+
+	return mlx5_fpga_event(fdev, event, eqe);
+}
+
 int mlx5_fpga_device_start(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_fpga_device *fdev = mdev->fpga;
@@ -185,6 +202,11 @@ int mlx5_fpga_device_start(struct mlx5_core_dev *mdev)
 	if (err)
 		goto out;
 
+	MLX5_NB_INIT(&fdev->fpga_err_nb, fpga_err_event, FPGA_ERROR);
+	MLX5_NB_INIT(&fdev->fpga_qp_err_nb, fpga_qp_err_event, FPGA_QP_ERROR);
+	mlx5_eq_notifier_register(fdev->mdev, &fdev->fpga_err_nb);
+	mlx5_eq_notifier_register(fdev->mdev, &fdev->fpga_qp_err_nb);
+
 	err = mlx5_fpga_conn_device_init(fdev);
 	if (err)
 		goto err_rsvd_gid;
@@ -201,6 +223,8 @@ err_conn_init:
 	mlx5_fpga_conn_device_cleanup(fdev);
 
 err_rsvd_gid:
+	mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_err_nb);
+	mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_qp_err_nb);
 	mlx5_core_unreserve_gids(mdev, max_num_qps);
 out:
 	spin_lock_irqsave(&fdev->state_lock, flags);
@@ -256,6 +280,9 @@ void mlx5_fpga_device_stop(struct mlx5_core_dev *mdev)
 	}
 
 	mlx5_fpga_conn_device_cleanup(fdev);
+	mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_err_nb);
+	mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_qp_err_nb);
+
 	max_num_qps = MLX5_CAP_FPGA(mdev, shell_caps.max_num_qps);
 	mlx5_core_unreserve_gids(mdev, max_num_qps);
 }
@@ -283,9 +310,10 @@ static const char *mlx5_fpga_qp_syndrome_to_string(u8 syndrome)
 	return "Unknown";
 }
 
-void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data)
+static int mlx5_fpga_event(struct mlx5_fpga_device *fdev,
+			   unsigned long event, void *eqe)
 {
-	struct mlx5_fpga_device *fdev = mdev->fpga;
+	void *data = ((struct mlx5_eqe *)eqe)->data.raw;
 	const char *event_name;
 	bool teardown = false;
 	unsigned long flags;
@@ -303,9 +331,7 @@ void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data)
 		fpga_qpn = MLX5_GET(fpga_qp_error_event, data, fpga_qpn);
 		break;
 	default:
-		mlx5_fpga_warn_ratelimited(fdev, "Unexpected event %u\n",
-					   event);
-		return;
+		return NOTIFY_DONE;
 	}
 
 	spin_lock_irqsave(&fdev->state_lock, flags);
@@ -326,4 +352,6 @@ void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data)
 	 */
 	if (teardown)
 		mlx5_trigger_health_work(fdev->mdev);
+
+	return NOTIFY_OK;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
index 3e2355c8df3f..7e2e871dbf83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
@@ -35,11 +35,16 @@
 
 #ifdef CONFIG_MLX5_FPGA
 
+#include <linux/mlx5/eq.h>
+
+#include "lib/eq.h"
 #include "fpga/cmd.h"
 
 /* Represents an Innova device */
 struct mlx5_fpga_device {
 	struct mlx5_core_dev *mdev;
+	struct mlx5_nb fpga_err_nb;
+	struct mlx5_nb fpga_qp_err_nb;
 	spinlock_t state_lock; /* Protects state transitions */
 	enum mlx5_fpga_status state;
 	enum mlx5_fpga_image last_admin_image;
@@ -82,7 +87,6 @@ int mlx5_fpga_init(struct mlx5_core_dev *mdev);
 void mlx5_fpga_cleanup(struct mlx5_core_dev *mdev);
 int mlx5_fpga_device_start(struct mlx5_core_dev *mdev);
 void mlx5_fpga_device_stop(struct mlx5_core_dev *mdev);
-void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data);
 
 #else
 
@@ -104,11 +108,6 @@ static inline void mlx5_fpga_device_stop(struct mlx5_core_dev *mdev)
 {
 }
 
-static inline void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event,
-				   void *data)
-{
-}
-
 #endif
 
 #endif /* __MLX5_FPGA_CORE_H__ */
-- 
cgit v1.2.3


From 41069256e93045a45a2c359c9715439be0b47bf4 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 20 Nov 2018 14:12:21 -0800
Subject: net/mlx5: Clock, Use async events chain

Remove the explicit call to mlx5_pps_event on MLX5_EVENT_TYPE_PPS_EVENT
and let clock logic to register its own handler when its ready.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  4 ----
 .../net/ethernet/mellanox/mlx5/core/lib/clock.c    | 24 +++++++++++++++-------
 .../net/ethernet/mellanox/mlx5/core/lib/clock.h    |  3 ---
 include/linux/mlx5/driver.h                        |  4 +++-
 4 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 8aabd23d2166..e5fcce9ca107 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -417,10 +417,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 			mlx5_port_module_event(dev, eqe);
 			break;
 
-		case MLX5_EVENT_TYPE_PPS_EVENT:
-			mlx5_pps_event(dev, eqe);
-			break;
-
 		case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
 			mlx5_temp_warning_event(dev, eqe);
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 0d90b1b4a3d3..d27c239e7d6c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -33,6 +33,7 @@
 #include <linux/clocksource.h>
 #include <linux/highmem.h>
 #include <rdma/mlx5-abi.h>
+#include "lib/eq.h"
 #include "en.h"
 #include "clock.h"
 
@@ -439,16 +440,17 @@ static void mlx5_get_pps_caps(struct mlx5_core_dev *mdev)
 	clock->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode);
 }
 
-void mlx5_pps_event(struct mlx5_core_dev *mdev,
-		    struct mlx5_eqe *eqe)
+static int mlx5_pps_event(struct notifier_block *nb,
+			  unsigned long type, void *data)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mlx5_nb_cof(nb, struct mlx5_clock, pps_nb);
+	struct mlx5_core_dev *mdev = clock->mdev;
 	struct ptp_clock_event ptp_event;
-	struct timespec64 ts;
-	u64 nsec_now, nsec_delta;
 	u64 cycles_now, cycles_delta;
+	u64 nsec_now, nsec_delta, ns;
+	struct mlx5_eqe *eqe = data;
 	int pin = eqe->data.pps.pin;
-	s64 ns;
+	struct timespec64 ts;
 	unsigned long flags;
 
 	switch (clock->ptp_info.pin_config[pin].func) {
@@ -463,6 +465,7 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev,
 		} else {
 			ptp_event.type = PTP_CLOCK_EXTTS;
 		}
+		/* TODOL clock->ptp can be NULL if ptp_clock_register failes */
 		ptp_clock_event(clock->ptp, &ptp_event);
 		break;
 	case PTP_PF_PEROUT:
@@ -481,8 +484,11 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev,
 		write_sequnlock_irqrestore(&clock->lock, flags);
 		break;
 	default:
-		mlx5_core_err(mdev, " Unhandled event\n");
+		mlx5_core_err(mdev, " Unhandled clock PPS event, func %d\n",
+			      clock->ptp_info.pin_config[pin].func);
 	}
+
+	return NOTIFY_OK;
 }
 
 void mlx5_init_clock(struct mlx5_core_dev *mdev)
@@ -567,6 +573,9 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 			       PTR_ERR(clock->ptp));
 		clock->ptp = NULL;
 	}
+
+	MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT);
+	mlx5_eq_notifier_register(mdev, &clock->pps_nb);
 }
 
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
@@ -576,6 +585,7 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
 		return;
 
+	mlx5_eq_notifier_unregister(mdev, &clock->pps_nb);
 	if (clock->ptp) {
 		ptp_clock_unregister(clock->ptp);
 		clock->ptp = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index 263cb6e2aeee..31600924bdc3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -36,7 +36,6 @@
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 void mlx5_init_clock(struct mlx5_core_dev *mdev);
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
-void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
@@ -60,8 +59,6 @@ static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
 #else
 static inline void mlx5_init_clock(struct mlx5_core_dev *mdev) {}
 static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
-static inline void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) {}
-
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
 	return -1;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f41e6713df10..99a23db9a929 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -50,6 +50,7 @@
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/doorbell.h>
 #include <linux/mlx5/srq.h>
+#include <linux/mlx5/eq.h>
 #include <linux/timecounter.h>
 #include <linux/ptp_clock_kernel.h>
 
@@ -671,6 +672,8 @@ struct mlx5_pps {
 };
 
 struct mlx5_clock {
+	struct mlx5_core_dev      *mdev;
+	struct mlx5_nb             pps_nb;
 	seqlock_t                  lock;
 	struct cyclecounter        cycles;
 	struct timecounter         tc;
@@ -678,7 +681,6 @@ struct mlx5_clock {
 	u32                        nominal_c_mult;
 	unsigned long              overflow_period;
 	struct delayed_work        overflow_work;
-	struct mlx5_core_dev      *mdev;
 	struct ptp_clock          *ptp;
 	struct ptp_clock_info      ptp_info;
 	struct mlx5_pps            pps_info;
-- 
cgit v1.2.3


From 6933a93795590b51a3056b6d66562ca1da1557ae Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 20 Nov 2018 14:12:22 -0800
Subject: net/mlx5: E-Switch, Use async events chain

Remove the explicit call to mlx5_eswitch_vport_event on
MLX5_EVENT_TYPE_NIC_VPORT_CHANGE and let the eswitch register its own
handler when its ready.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c      |  4 ---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 44 +++++++++++++----------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h |  3 +-
 3 files changed, 26 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index e5fcce9ca107..7c8b2d89645b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -409,10 +409,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 			}
 			break;
 
-		case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE:
-			mlx5_eswitch_vport_event(dev->priv.eswitch, eqe);
-			break;
-
 		case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
 			mlx5_port_module_event(dev, eqe);
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 2346b6ba3d54..e6a9b19d8626 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -36,6 +36,7 @@
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 #include "eswitch.h"
 #include "fs_core.h"
 #include "lib/eq.h"
@@ -1568,7 +1569,6 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	/* Mark this vport as disabled to discard new events */
 	vport->enabled = false;
 
-	mlx5_eq_synchronize_async_irq(esw->dev);
 	/* Wait for current already scheduled events to complete */
 	flush_workqueue(esw->work_queue);
 	/* Disable events from this vport */
@@ -1594,10 +1594,25 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	mutex_unlock(&esw->state_lock);
 }
 
+static int eswitch_vport_event(struct notifier_block *nb,
+			       unsigned long type, void *data)
+{
+	struct mlx5_eswitch *esw = mlx5_nb_cof(nb, struct mlx5_eswitch, nb);
+	struct mlx5_eqe *eqe = data;
+	struct mlx5_vport *vport;
+	u16 vport_num;
+
+	vport_num = be16_to_cpu(eqe->data.vport_change.vport_num);
+	vport = &esw->vports[vport_num];
+	if (vport->enabled)
+		queue_work(esw->work_queue, &vport->vport_change_handler);
+
+	return NOTIFY_OK;
+}
+
 /* Public E-Switch API */
 #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
 
-
 int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 {
 	int err;
@@ -1641,6 +1656,11 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	for (i = 0; i <= nvfs; i++)
 		esw_enable_vport(esw, i, enabled_events);
 
+	if (mode == SRIOV_LEGACY) {
+		MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
+		mlx5_eq_notifier_register(esw->dev, &esw->nb);
+	}
+
 	esw_info(esw->dev, "SRIOV enabled: active vports(%d)\n",
 		 esw->enabled_vports);
 	return 0;
@@ -1670,6 +1690,9 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 	mc_promisc = &esw->mc_promisc;
 	nvports = esw->enabled_vports;
 
+	if (esw->mode == SRIOV_LEGACY)
+		mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
+
 	for (i = 0; i < esw->total_vports; i++)
 		esw_disable_vport(esw, i);
 
@@ -1778,23 +1801,6 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 	kfree(esw);
 }
 
-void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe)
-{
-	struct mlx5_eqe_vport_change *vc_eqe = &eqe->data.vport_change;
-	u16 vport_num = be16_to_cpu(vc_eqe->vport_num);
-	struct mlx5_vport *vport;
-
-	if (!esw) {
-		pr_warn("MLX5 E-Switch: vport %d got an event while eswitch is not initialized\n",
-			vport_num);
-		return;
-	}
-
-	vport = &esw->vports[vport_num];
-	if (vport->enabled)
-		queue_work(esw->work_queue, &vport->vport_change_handler);
-}
-
 /* Vport Administration */
 #define LEGAL_VPORT(esw, vport) (vport >= 0 && vport < esw->total_vports)
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index aaafc9f17115..480ffa294867 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -181,6 +181,7 @@ struct esw_mc_addr { /* SRIOV only */
 
 struct mlx5_eswitch {
 	struct mlx5_core_dev    *dev;
+	struct mlx5_nb          nb;
 	struct mlx5_eswitch_fdb fdb_table;
 	struct hlist_head       mc_table[MLX5_L2_ADDR_HASH_SIZE];
 	struct workqueue_struct *work_queue;
@@ -211,7 +212,6 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw);
 /* E-Switch API */
 int mlx5_eswitch_init(struct mlx5_core_dev *dev);
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw);
-void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe);
 int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode);
 void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw);
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
@@ -352,7 +352,6 @@ static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
-static inline void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe) {}
 static inline int  mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; }
 static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) {}
 
-- 
cgit v1.2.3


From 0cf53c1247565b339a23d82a1853a0c41e9a2a34 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 20 Nov 2018 14:12:23 -0800
Subject: net/mlx5: FWPage, Use async events chain

Remove the explicit call to mlx5_core_req_pages_handler on
MLX5_EVENT_TYPE_PAGE_REQUEST and let FW page logic  to register its own
handler when its ready.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       | 11 ------
 drivers/net/ethernet/mellanox/mlx5/core/main.c     | 27 +++++++------
 .../net/ethernet/mellanox/mlx5/core/pagealloc.c    | 44 +++++++++++++++-------
 include/linux/mlx5/driver.h                        |  5 ++-
 4 files changed, 47 insertions(+), 40 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 7c8b2d89645b..7f6a644700eb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -398,17 +398,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 			mlx5_eq_cq_event(eq, cqn, eqe->type);
 			break;
 
-		case MLX5_EVENT_TYPE_PAGE_REQUEST:
-			{
-				u16 func_id = be16_to_cpu(eqe->data.req_pages.func_id);
-				s32 npages = be32_to_cpu(eqe->data.req_pages.num_pages);
-
-				mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n",
-					      func_id, npages);
-				mlx5_core_req_pages_handler(dev, func_id, npages);
-			}
-			break;
-
 		case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
 			mlx5_port_module_event(dev, eqe);
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 91022f141855..9e4cd2757ea8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -916,16 +916,10 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto reclaim_boot_pages;
 	}
 
-	err = mlx5_pagealloc_start(dev);
-	if (err) {
-		dev_err(&pdev->dev, "mlx5_pagealloc_start failed\n");
-		goto reclaim_boot_pages;
-	}
-
 	err = mlx5_cmd_init_hca(dev, sw_owner_id);
 	if (err) {
 		dev_err(&pdev->dev, "init hca failed\n");
-		goto err_pagealloc_stop;
+		goto reclaim_boot_pages;
 	}
 
 	mlx5_set_driver_version(dev);
@@ -953,6 +947,8 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_get_uars;
 	}
 
+	mlx5_pagealloc_start(dev);
+
 	err = mlx5_eq_table_create(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to create EQs\n");
@@ -1039,6 +1035,7 @@ err_fw_tracer:
 	mlx5_eq_table_destroy(dev);
 
 err_eq_table:
+	mlx5_pagealloc_stop(dev);
 	mlx5_put_uars_page(dev, priv->uar);
 
 err_get_uars:
@@ -1052,9 +1049,6 @@ err_stop_poll:
 		goto out_err;
 	}
 
-err_pagealloc_stop:
-	mlx5_pagealloc_stop(dev);
-
 reclaim_boot_pages:
 	mlx5_reclaim_startup_pages(dev);
 
@@ -1100,16 +1094,18 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_fpga_device_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
 	mlx5_eq_table_destroy(dev);
+	mlx5_pagealloc_stop(dev);
 	mlx5_put_uars_page(dev, priv->uar);
+
 	if (cleanup)
 		mlx5_cleanup_once(dev);
 	mlx5_stop_health_poll(dev, cleanup);
+
 	err = mlx5_cmd_teardown_hca(dev);
 	if (err) {
 		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
 		goto out;
 	}
-	mlx5_pagealloc_stop(dev);
 	mlx5_reclaim_startup_pages(dev);
 	mlx5_core_disable_hca(dev, 0);
 	mlx5_cmd_cleanup(dev);
@@ -1186,12 +1182,14 @@ static int init_one(struct pci_dev *pdev,
 		goto close_pci;
 	}
 
-	mlx5_pagealloc_init(dev);
+	err = mlx5_pagealloc_init(dev);
+	if (err)
+		goto err_pagealloc_init;
 
 	err = mlx5_load_one(dev, priv, true);
 	if (err) {
 		dev_err(&pdev->dev, "mlx5_load_one failed with error code %d\n", err);
-		goto clean_health;
+		goto err_load_one;
 	}
 
 	request_module_nowait(MLX5_IB_MOD);
@@ -1205,8 +1203,9 @@ static int init_one(struct pci_dev *pdev,
 
 clean_load:
 	mlx5_unload_one(dev, priv, true);
-clean_health:
+err_load_one:
 	mlx5_pagealloc_cleanup(dev);
+err_pagealloc_init:
 	mlx5_health_cleanup(dev);
 close_pci:
 	mlx5_pci_close(dev, priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index e36d3e3675f9..a83b517b0714 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -37,6 +37,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 enum {
 	MLX5_PAGES_CANT_GIVE	= 0,
@@ -433,15 +434,28 @@ static void pages_work_handler(struct work_struct *work)
 	kfree(req);
 }
 
-void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
-				 s32 npages)
+static int req_pages_handler(struct notifier_block *nb,
+			     unsigned long type, void *data)
 {
 	struct mlx5_pages_req *req;
-
+	struct mlx5_core_dev *dev;
+	struct mlx5_priv *priv;
+	struct mlx5_eqe *eqe;
+	u16 func_id;
+	s32 npages;
+
+	priv = mlx5_nb_cof(nb, struct mlx5_priv, pg_nb);
+	dev  = container_of(priv, struct mlx5_core_dev, priv);
+	eqe  = data;
+
+	func_id = be16_to_cpu(eqe->data.req_pages.func_id);
+	npages  = be32_to_cpu(eqe->data.req_pages.num_pages);
+	mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n",
+		      func_id, npages);
 	req = kzalloc(sizeof(*req), GFP_ATOMIC);
 	if (!req) {
 		mlx5_core_warn(dev, "failed to allocate pages request\n");
-		return;
+		return NOTIFY_DONE;
 	}
 
 	req->dev = dev;
@@ -449,6 +463,7 @@ void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
 	req->npages = npages;
 	INIT_WORK(&req->work, pages_work_handler);
 	queue_work(dev->priv.pg_wq, &req->work);
+	return NOTIFY_OK;
 }
 
 int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
@@ -524,29 +539,32 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 	return 0;
 }
 
-void mlx5_pagealloc_init(struct mlx5_core_dev *dev)
+int mlx5_pagealloc_init(struct mlx5_core_dev *dev)
 {
 	dev->priv.page_root = RB_ROOT;
 	INIT_LIST_HEAD(&dev->priv.free_list);
+	dev->priv.pg_wq = create_singlethread_workqueue("mlx5_page_allocator");
+	if (!dev->priv.pg_wq)
+		return -ENOMEM;
+
+	return 0;
 }
 
 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev)
 {
-	/* nothing */
+	destroy_workqueue(dev->priv.pg_wq);
 }
 
-int mlx5_pagealloc_start(struct mlx5_core_dev *dev)
+void mlx5_pagealloc_start(struct mlx5_core_dev *dev)
 {
-	dev->priv.pg_wq = create_singlethread_workqueue("mlx5_page_allocator");
-	if (!dev->priv.pg_wq)
-		return -ENOMEM;
-
-	return 0;
+	MLX5_NB_INIT(&dev->priv.pg_nb, req_pages_handler, PAGE_REQUEST);
+	mlx5_eq_notifier_register(dev, &dev->priv.pg_nb);
 }
 
 void mlx5_pagealloc_stop(struct mlx5_core_dev *dev)
 {
-	destroy_workqueue(dev->priv.pg_wq);
+	mlx5_eq_notifier_unregister(dev, &dev->priv.pg_nb);
+	flush_workqueue(dev->priv.pg_wq);
 }
 
 int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 99a23db9a929..61088ad33500 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -564,6 +564,7 @@ struct mlx5_priv {
 	struct mlx5_eq_table	*eq_table;
 
 	/* pages stuff */
+	struct mlx5_nb          pg_nb;
 	struct workqueue_struct *pg_wq;
 	struct rb_root		page_root;
 	int			fw_pages;
@@ -962,9 +963,9 @@ int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn);
 int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn);
 int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
 		      u16 opmod, u8 port);
-void mlx5_pagealloc_init(struct mlx5_core_dev *dev);
+int mlx5_pagealloc_init(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev);
-int mlx5_pagealloc_start(struct mlx5_core_dev *dev);
+void mlx5_pagealloc_start(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_stop(struct mlx5_core_dev *dev);
 void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
 				 s32 npages);
-- 
cgit v1.2.3


From 71edc69ca1a78ce18411a540c550a4ef1eb017cd Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 20 Nov 2018 14:12:24 -0800
Subject: net/mlx5: CmdIF, Use async events chain

Remove the explicit call to mlx5_cmd_comp_handler on MLX5_EVENT_TYPE_CMD
and let command interface to register its own handler when its ready.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c      | 48 +++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  4 --
 drivers/net/ethernet/mellanox/mlx5/core/health.c   | 25 +----------
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |  2 +-
 include/linux/mlx5/driver.h                        |  2 +
 5 files changed, 50 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 7b18aff955f1..8ab636d59edb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -40,9 +40,11 @@
 #include <linux/random.h>
 #include <linux/io-mapping.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/eq.h>
 #include <linux/debugfs.h>
 
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 enum {
 	CMD_IF_REV = 5,
@@ -805,6 +807,8 @@ static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
 	return MLX5_GET(mbox_in, in->first.data, opcode);
 }
 
+static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
+
 static void cb_timeout_handler(struct work_struct *work)
 {
 	struct delayed_work *dwork = container_of(work, struct delayed_work,
@@ -1412,14 +1416,32 @@ static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode)
 		up(&cmd->sem);
 }
 
+static int cmd_comp_notifier(struct notifier_block *nb,
+			     unsigned long type, void *data)
+{
+	struct mlx5_core_dev *dev;
+	struct mlx5_cmd *cmd;
+	struct mlx5_eqe *eqe;
+
+	cmd = mlx5_nb_cof(nb, struct mlx5_cmd, nb);
+	dev = container_of(cmd, struct mlx5_core_dev, cmd);
+	eqe = data;
+
+	mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
+
+	return NOTIFY_OK;
+}
 void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
 {
+	MLX5_NB_INIT(&dev->cmd.nb, cmd_comp_notifier, CMD);
+	mlx5_eq_notifier_register(dev, &dev->cmd.nb);
 	mlx5_cmd_change_mod(dev, CMD_MODE_EVENTS);
 }
 
 void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
 {
 	mlx5_cmd_change_mod(dev, CMD_MODE_POLLING);
+	mlx5_eq_notifier_unregister(dev, &dev->cmd.nb);
 }
 
 static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
@@ -1435,7 +1457,7 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
 	}
 }
 
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
+static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	struct mlx5_cmd_work_ent *ent;
@@ -1533,7 +1555,29 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 		}
 	}
 }
-EXPORT_SYMBOL(mlx5_cmd_comp_handler);
+
+void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev)
+{
+	unsigned long flags;
+	u64 vector;
+
+	/* wait for pending handlers to complete */
+	mlx5_eq_synchronize_cmd_irq(dev);
+	spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
+	vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
+	if (!vector)
+		goto no_trig;
+
+	vector |= MLX5_TRIGGERED_CMD_COMP;
+	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
+
+	mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
+	mlx5_cmd_comp_handler(dev, vector, true);
+	return;
+
+no_trig:
+	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
+}
 
 static int status_to_err(u8 status)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 7f6a644700eb..b28869aa1a4e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -368,10 +368,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 			mlx5_srq_event(dev, rsn, eqe->type);
 			break;
 
-		case MLX5_EVENT_TYPE_CMD:
-			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
-			break;
-
 		case MLX5_EVENT_TYPE_PORT_CHANGE:
 			port = (eqe->data.port.port >> 4) & 0xf;
 			switch (eqe->sub_type) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 066883003aea..4e42bd290959 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -79,29 +79,6 @@ void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state)
 		    &dev->iseg->cmdq_addr_l_sz);
 }
 
-static void trigger_cmd_completions(struct mlx5_core_dev *dev)
-{
-	unsigned long flags;
-	u64 vector;
-
-	/* wait for pending handlers to complete */
-	mlx5_eq_synchronize_cmd_irq(dev);
-	spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
-	vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
-	if (!vector)
-		goto no_trig;
-
-	vector |= MLX5_TRIGGERED_CMD_COMP;
-	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
-
-	mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
-	mlx5_cmd_comp_handler(dev, vector, true);
-	return;
-
-no_trig:
-	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
-}
-
 static int in_fatal(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
@@ -125,7 +102,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 	mlx5_core_err(dev, "start\n");
 	if (pci_channel_offline(dev->pdev) || in_fatal(dev) || force) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
-		trigger_cmd_completions(dev);
+		mlx5_cmd_trigger_completions(dev);
 	}
 
 	mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index e06c6e16ffc9..5dd453e47a04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -127,7 +127,7 @@ int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
 u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
 
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
+void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev);
 int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev);
 void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev);
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 61088ad33500..a8d638134fc8 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -278,6 +278,8 @@ struct mlx5_cmd_stats {
 };
 
 struct mlx5_cmd {
+	struct mlx5_nb    nb;
+
 	void	       *cmd_alloc_buf;
 	dma_addr_t	alloc_dma;
 	int		alloc_size;
-- 
cgit v1.2.3


From 221c14f3d12489ced0f2ca8b31b2221c5dbbf145 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 20 Nov 2018 14:12:25 -0800
Subject: net/mlx5: Resource tables, Use async events chain

Remove the explicit call to QP/SRQ resources events handlers on several FW
events and let resources logic register resources events notifiers via the
new API.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c  | 29 ------------
 drivers/net/ethernet/mellanox/mlx5/core/qp.c  | 68 ++++++++++++++++++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/srq.c | 55 +++++++++++++++++++---
 include/linux/mlx5/driver.h                   |  6 ++-
 4 files changed, 108 insertions(+), 50 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index b28869aa1a4e..0cf448575ebd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -324,7 +324,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 	struct mlx5_eqe *eqe;
 	int set_ci = 0;
 	u32 cqn = -1;
-	u32 rsn;
 	u8 port;
 
 	dev = eq->dev;
@@ -340,34 +339,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 		mlx5_core_dbg(eq->dev, "eqn %d, eqe type %s\n",
 			      eq->eqn, eqe_type_str(eqe->type));
 		switch (eqe->type) {
-		case MLX5_EVENT_TYPE_DCT_DRAINED:
-			rsn = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
-			rsn |= (MLX5_RES_DCT << MLX5_USER_INDEX_LEN);
-			mlx5_rsc_event(dev, rsn, eqe->type);
-			break;
-		case MLX5_EVENT_TYPE_PATH_MIG:
-		case MLX5_EVENT_TYPE_COMM_EST:
-		case MLX5_EVENT_TYPE_SQ_DRAINED:
-		case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
-		case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
-		case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
-		case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
-		case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
-			rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
-			rsn |= (eqe->data.qp_srq.type << MLX5_USER_INDEX_LEN);
-			mlx5_core_dbg(dev, "event %s(%d) arrived on resource 0x%x\n",
-				      eqe_type_str(eqe->type), eqe->type, rsn);
-			mlx5_rsc_event(dev, rsn, eqe->type);
-			break;
-
-		case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
-		case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
-			rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
-			mlx5_core_dbg(dev, "SRQ event %s(%d): srqn 0x%x\n",
-				      eqe_type_str(eqe->type), eqe->type, rsn);
-			mlx5_srq_event(dev, rsn, eqe->type);
-			break;
-
 		case MLX5_EVENT_TYPE_PORT_CHANGE:
 			port = (eqe->data.port.port >> 4) & 0xf;
 			switch (eqe->sub_type) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index cba4a435043a..28726c63101f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -38,11 +38,11 @@
 #include <linux/mlx5/transobj.h>
 
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
-static struct mlx5_core_rsc_common *mlx5_get_rsc(struct mlx5_core_dev *dev,
-						 u32 rsn)
+static struct mlx5_core_rsc_common *
+mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn)
 {
-	struct mlx5_qp_table *table = &dev->priv.qp_table;
 	struct mlx5_core_rsc_common *common;
 
 	spin_lock(&table->lock);
@@ -53,11 +53,6 @@ static struct mlx5_core_rsc_common *mlx5_get_rsc(struct mlx5_core_dev *dev,
 
 	spin_unlock(&table->lock);
 
-	if (!common) {
-		mlx5_core_warn(dev, "Async event for bogus resource 0x%x\n",
-			       rsn);
-		return NULL;
-	}
 	return common;
 }
 
@@ -120,14 +115,52 @@ static bool is_event_type_allowed(int rsc_type, int event_type)
 	}
 }
 
-void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
+static int rsc_event_notifier(struct notifier_block *nb,
+			      unsigned long type, void *data)
 {
-	struct mlx5_core_rsc_common *common = mlx5_get_rsc(dev, rsn);
+	struct mlx5_core_rsc_common *common;
+	struct mlx5_qp_table *table;
+	struct mlx5_core_dev *dev;
 	struct mlx5_core_dct *dct;
+	u8 event_type = (u8)type;
 	struct mlx5_core_qp *qp;
+	struct mlx5_priv *priv;
+	struct mlx5_eqe *eqe;
+	u32 rsn;
+
+	switch (event_type) {
+	case MLX5_EVENT_TYPE_DCT_DRAINED:
+		eqe = data;
+		rsn = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
+		rsn |= (MLX5_RES_DCT << MLX5_USER_INDEX_LEN);
+		break;
+	case MLX5_EVENT_TYPE_PATH_MIG:
+	case MLX5_EVENT_TYPE_COMM_EST:
+	case MLX5_EVENT_TYPE_SQ_DRAINED:
+	case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
+	case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
+	case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
+	case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
+		eqe = data;
+		rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
+		rsn |= (eqe->data.qp_srq.type << MLX5_USER_INDEX_LEN);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	table = mlx5_nb_cof(nb, struct mlx5_qp_table, nb);
+	priv  = container_of(table, struct mlx5_priv, qp_table);
+	dev   = container_of(priv, struct mlx5_core_dev, priv);
 
-	if (!common)
-		return;
+	mlx5_core_dbg(dev, "event (%d) arrived on resource 0x%x\n", eqe->type, rsn);
+
+	common = mlx5_get_rsc(table, rsn);
+	if (!common) {
+		mlx5_core_warn(dev, "Async event for bogus resource 0x%x\n", rsn);
+		return NOTIFY_OK;
+	}
 
 	if (!is_event_type_allowed((rsn >> MLX5_USER_INDEX_LEN), event_type)) {
 		mlx5_core_warn(dev, "event 0x%.2x is not allowed on resource 0x%.8x\n",
@@ -152,6 +185,8 @@ void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
 	}
 out:
 	mlx5_core_put_rsc(common);
+
+	return NOTIFY_OK;
 }
 
 static int create_resource_common(struct mlx5_core_dev *dev,
@@ -487,10 +522,16 @@ void mlx5_init_qp_table(struct mlx5_core_dev *dev)
 	spin_lock_init(&table->lock);
 	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
 	mlx5_qp_debugfs_init(dev);
+
+	MLX5_NB_INIT(&table->nb, rsc_event_notifier, NOTIFY_ANY);
+	mlx5_eq_notifier_register(dev, &table->nb);
 }
 
 void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev)
 {
+	struct mlx5_qp_table *table = &dev->priv.qp_table;
+
+	mlx5_eq_notifier_unregister(dev, &table->nb);
 	mlx5_qp_debugfs_cleanup(dev);
 }
 
@@ -676,8 +717,9 @@ struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
 						enum mlx5_res_type res_type)
 {
 	u32 rsn = res_num | (res_type << MLX5_USER_INDEX_LEN);
+	struct mlx5_qp_table *table = &dev->priv.qp_table;
 
-	return mlx5_get_rsc(dev, rsn);
+	return mlx5_get_rsc(table, rsn);
 }
 EXPORT_SYMBOL_GPL(mlx5_core_res_hold);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
index 6a6fc9be01e6..0563866c13f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
@@ -36,13 +36,25 @@
 #include <linux/mlx5/cmd.h>
 #include <linux/mlx5/srq.h>
 #include <rdma/ib_verbs.h>
-#include "mlx5_core.h"
 #include <linux/mlx5/transobj.h>
+#include "mlx5_core.h"
+#include "lib/eq.h"
 
-void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type)
+static int srq_event_notifier(struct mlx5_srq_table *table,
+			      unsigned long type, void *data)
 {
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
+	struct mlx5_core_dev *dev;
 	struct mlx5_core_srq *srq;
+	struct mlx5_priv *priv;
+	struct mlx5_eqe *eqe;
+	u32 srqn;
+
+	priv  = container_of(table, struct mlx5_priv, srq_table);
+	dev   = container_of(priv, struct mlx5_core_dev, priv);
+
+	eqe = data;
+	srqn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
+	mlx5_core_dbg(dev, "SRQ event (%d): srqn 0x%x\n", eqe->type, srqn);
 
 	spin_lock(&table->lock);
 
@@ -54,13 +66,35 @@ void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type)
 
 	if (!srq) {
 		mlx5_core_warn(dev, "Async event for bogus SRQ 0x%08x\n", srqn);
-		return;
+		return NOTIFY_OK;
 	}
 
-	srq->event(srq, event_type);
+	srq->event(srq, eqe->type);
 
 	if (atomic_dec_and_test(&srq->refcount))
 		complete(&srq->free);
+
+	return NOTIFY_OK;
+}
+
+static int catas_err_notifier(struct notifier_block *nb,
+			      unsigned long type, void *data)
+{
+	struct mlx5_srq_table *table;
+
+	table = mlx5_nb_cof(nb, struct mlx5_srq_table, catas_err_nb);
+	/* type == MLX5_EVENT_TYPE_SRQ_CATAS_ERROR */
+	return srq_event_notifier(table, type, data);
+}
+
+static int rq_limit_notifier(struct notifier_block *nb,
+			     unsigned long type, void *data)
+{
+	struct mlx5_srq_table *table;
+
+	table = mlx5_nb_cof(nb, struct mlx5_srq_table, rq_limit_nb);
+	/* type == MLX5_EVENT_TYPE_SRQ_RQ_LIMIT */
+	return srq_event_notifier(table, type, data);
 }
 
 static int get_pas_size(struct mlx5_srq_attr *in)
@@ -708,9 +742,18 @@ void mlx5_init_srq_table(struct mlx5_core_dev *dev)
 	memset(table, 0, sizeof(*table));
 	spin_lock_init(&table->lock);
 	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
+
+	MLX5_NB_INIT(&table->catas_err_nb, catas_err_notifier, SRQ_CATAS_ERROR);
+	mlx5_eq_notifier_register(dev, &table->catas_err_nb);
+
+	MLX5_NB_INIT(&table->rq_limit_nb, rq_limit_notifier, SRQ_RQ_LIMIT);
+	mlx5_eq_notifier_register(dev, &table->rq_limit_nb);
 }
 
 void mlx5_cleanup_srq_table(struct mlx5_core_dev *dev)
 {
-	/* nothing */
+	struct mlx5_srq_table *table = &dev->priv.srq_table;
+
+	mlx5_eq_notifier_unregister(dev, &table->rq_limit_nb);
+	mlx5_eq_notifier_unregister(dev, &table->catas_err_nb);
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index a8d638134fc8..afba0864f45c 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -464,6 +464,8 @@ struct mlx5_core_health {
 };
 
 struct mlx5_qp_table {
+	struct mlx5_nb          nb;
+
 	/* protect radix tree
 	 */
 	spinlock_t		lock;
@@ -471,6 +473,8 @@ struct mlx5_qp_table {
 };
 
 struct mlx5_srq_table {
+	struct mlx5_nb          catas_err_nb;
+	struct mlx5_nb          rq_limit_nb;
 	/* protect radix tree
 	 */
 	spinlock_t		lock;
@@ -978,8 +982,6 @@ void mlx5_unregister_debugfs(void);
 
 void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas);
 void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas);
-void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type);
-void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type);
 struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 		    unsigned int *irqn);
-- 
cgit v1.2.3


From 2742bc90bc102644d67e17758e234646d91ae696 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 20 Nov 2018 14:12:26 -0800
Subject: net/mlx5: CQ ERR, Use async events chain

Remove the explicit call to mlx5_eq_cq_event on MLX5_EVENT_TYPE_CQ_ERROR
and register a specific CQ ERROR handler via the new API.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 66 ++++++++++++++++++----------
 1 file changed, 44 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 0cf448575ebd..4e3febbf639d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -74,6 +74,9 @@ struct mlx5_eq_table {
 
 	struct atomic_notifier_head nh[MLX5_EVENT_TYPE_MAX];
 
+	/* Since CQ DB is stored in async_eq */
+	struct mlx5_nb          cq_err_nb;
+
 	struct mutex            lock; /* sync async eqs creations */
 	int			num_comp_vectors;
 	struct mlx5_irq_info	*irq_info;
@@ -235,20 +238,6 @@ static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn)
 	return cq;
 }
 
-static void mlx5_eq_cq_event(struct mlx5_eq *eq, u32 cqn, int event_type)
-{
-	struct mlx5_core_cq *cq = mlx5_eq_cq_get(eq, cqn);
-
-	if (unlikely(!cq)) {
-		mlx5_core_warn(eq->dev, "Async event for bogus CQ 0x%x\n", cqn);
-		return;
-	}
-
-	cq->event(cq, event_type);
-
-	mlx5_cq_put(cq);
-}
-
 static irqreturn_t mlx5_eq_comp_int(int irq, void *eq_ptr)
 {
 	struct mlx5_eq_comp *eq_comp = eq_ptr;
@@ -323,7 +312,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 	struct mlx5_core_dev *dev;
 	struct mlx5_eqe *eqe;
 	int set_ci = 0;
-	u32 cqn = -1;
 	u8 port;
 
 	dev = eq->dev;
@@ -358,12 +346,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 					       port, eqe->sub_type);
 			}
 			break;
-		case MLX5_EVENT_TYPE_CQ_ERROR:
-			cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff;
-			mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrome 0x%x\n",
-				       cqn, eqe->data.cq_err.syndrome);
-			mlx5_eq_cq_event(eq, cqn, eqe->type);
-			break;
 
 		case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
 			mlx5_port_module_event(dev, eqe);
@@ -639,6 +621,38 @@ static int destroy_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 	return err;
 }
 
+static int cq_err_event_notifier(struct notifier_block *nb,
+				 unsigned long type, void *data)
+{
+	struct mlx5_eq_table *eqt;
+	struct mlx5_core_cq *cq;
+	struct mlx5_eqe *eqe;
+	struct mlx5_eq *eq;
+	u32 cqn;
+
+	/* type == MLX5_EVENT_TYPE_CQ_ERROR */
+
+	eqt = mlx5_nb_cof(nb, struct mlx5_eq_table, cq_err_nb);
+	eq  = &eqt->async_eq;
+	eqe = data;
+
+	cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff;
+	mlx5_core_warn(eq->dev, "CQ error on CQN 0x%x, syndrome 0x%x\n",
+		       cqn, eqe->data.cq_err.syndrome);
+
+	cq = mlx5_eq_cq_get(eq, cqn);
+	if (unlikely(!cq)) {
+		mlx5_core_warn(eq->dev, "Async event for bogus CQ 0x%x\n", cqn);
+		return NOTIFY_OK;
+	}
+
+	cq->event(cq, type);
+
+	mlx5_cq_put(cq);
+
+	return NOTIFY_OK;
+}
+
 static u64 gather_async_events_mask(struct mlx5_core_dev *dev)
 {
 	u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
@@ -679,6 +693,9 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	struct mlx5_eq_param param = {};
 	int err;
 
+	MLX5_NB_INIT(&table->cq_err_nb, cq_err_event_notifier, CQ_ERROR);
+	mlx5_eq_notifier_register(dev, &table->cq_err_nb);
+
 	param = (struct mlx5_eq_param) {
 		.index = MLX5_EQ_CMD_IDX,
 		.mask = 1ull << MLX5_EVENT_TYPE_CMD,
@@ -689,7 +706,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	err = create_async_eq(dev, "mlx5_cmd_eq", &table->cmd_eq, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create cmd EQ %d\n", err);
-		return err;
+		goto err0;
 	}
 
 	mlx5_cmd_use_events(dev);
@@ -728,6 +745,8 @@ err2:
 err1:
 	mlx5_cmd_use_polling(dev);
 	destroy_async_eq(dev, &table->cmd_eq);
+err0:
+	mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
 	return err;
 }
 
@@ -745,12 +764,15 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev)
 	if (err)
 		mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n",
 			      err);
+
 	mlx5_cmd_use_polling(dev);
 
 	err = destroy_async_eq(dev, &table->cmd_eq);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n",
 			      err);
+
+	mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
 }
 
 struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev)
-- 
cgit v1.2.3


From 69c1280b1f3b9123bc5154b2062507abcc14c3ef Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 20 Nov 2018 14:12:27 -0800
Subject: net/mlx5: Device events, Use async events chain

Move all the generic async events handling into new specific events
handling file events.c to keep eq.c file clean from concrete event logic
handling.

Use new API to register for NOTIFY_ANY to handle generic events and
dispatch allowed events to mlx5_core consumers (mlx5_ib and mlx5e)

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c |   9 +-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       | 157 ------------
 drivers/net/ethernet/mellanox/mlx5/core/events.c   | 283 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h |  34 +++
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  16 +-
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |   6 +-
 drivers/net/ethernet/mellanox/mlx5/core/port.c     |  57 -----
 include/linux/mlx5/driver.h                        |  29 +--
 include/linux/mlx5/port.h                          |   3 -
 10 files changed, 344 insertions(+), 252 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/events.c

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index d324a3884462..26afe0779a0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
 		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
-		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o  \
+		fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
 		diag/fs_tracepoint.o diag/fw_tracer.o
 
 #
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 1e55b9c27ffc..748d23806391 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include "lib/mlx5.h"
 #include "en.h"
 #include "en_accel/ipsec.h"
 #include "en_accel/tls.h"
@@ -1120,15 +1121,17 @@ static int mlx5e_grp_pme_fill_strings(struct mlx5e_priv *priv, u8 *data,
 static int mlx5e_grp_pme_fill_stats(struct mlx5e_priv *priv, u64 *data,
 				    int idx)
 {
-	struct mlx5_priv *mlx5_priv = &priv->mdev->priv;
+	struct mlx5_pme_stats pme_stats;
 	int i;
 
+	mlx5_get_pme_stats(priv->mdev, &pme_stats);
+
 	for (i = 0; i < NUM_PME_STATUS_STATS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.status_counters,
+		data[idx++] = MLX5E_READ_CTR64_CPU(pme_stats.status_counters,
 						   mlx5e_pme_status_desc, i);
 
 	for (i = 0; i < NUM_PME_ERR_STATS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.error_counters,
+		data[idx++] = MLX5E_READ_CTR64_CPU(pme_stats.error_counters,
 						   mlx5e_pme_error_desc, i);
 
 	return idx;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 4e3febbf639d..4aa39a1fe23f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -108,121 +108,6 @@ static int mlx5_cmd_destroy_eq(struct mlx5_core_dev *dev, u8 eqn)
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-static const char *eqe_type_str(u8 type)
-{
-	switch (type) {
-	case MLX5_EVENT_TYPE_COMP:
-		return "MLX5_EVENT_TYPE_COMP";
-	case MLX5_EVENT_TYPE_PATH_MIG:
-		return "MLX5_EVENT_TYPE_PATH_MIG";
-	case MLX5_EVENT_TYPE_COMM_EST:
-		return "MLX5_EVENT_TYPE_COMM_EST";
-	case MLX5_EVENT_TYPE_SQ_DRAINED:
-		return "MLX5_EVENT_TYPE_SQ_DRAINED";
-	case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
-		return "MLX5_EVENT_TYPE_SRQ_LAST_WQE";
-	case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
-		return "MLX5_EVENT_TYPE_SRQ_RQ_LIMIT";
-	case MLX5_EVENT_TYPE_CQ_ERROR:
-		return "MLX5_EVENT_TYPE_CQ_ERROR";
-	case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
-		return "MLX5_EVENT_TYPE_WQ_CATAS_ERROR";
-	case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
-		return "MLX5_EVENT_TYPE_PATH_MIG_FAILED";
-	case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
-		return "MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR";
-	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
-		return "MLX5_EVENT_TYPE_WQ_ACCESS_ERROR";
-	case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
-		return "MLX5_EVENT_TYPE_SRQ_CATAS_ERROR";
-	case MLX5_EVENT_TYPE_INTERNAL_ERROR:
-		return "MLX5_EVENT_TYPE_INTERNAL_ERROR";
-	case MLX5_EVENT_TYPE_PORT_CHANGE:
-		return "MLX5_EVENT_TYPE_PORT_CHANGE";
-	case MLX5_EVENT_TYPE_GPIO_EVENT:
-		return "MLX5_EVENT_TYPE_GPIO_EVENT";
-	case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
-		return "MLX5_EVENT_TYPE_PORT_MODULE_EVENT";
-	case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
-		return "MLX5_EVENT_TYPE_TEMP_WARN_EVENT";
-	case MLX5_EVENT_TYPE_REMOTE_CONFIG:
-		return "MLX5_EVENT_TYPE_REMOTE_CONFIG";
-	case MLX5_EVENT_TYPE_DB_BF_CONGESTION:
-		return "MLX5_EVENT_TYPE_DB_BF_CONGESTION";
-	case MLX5_EVENT_TYPE_STALL_EVENT:
-		return "MLX5_EVENT_TYPE_STALL_EVENT";
-	case MLX5_EVENT_TYPE_CMD:
-		return "MLX5_EVENT_TYPE_CMD";
-	case MLX5_EVENT_TYPE_PAGE_REQUEST:
-		return "MLX5_EVENT_TYPE_PAGE_REQUEST";
-	case MLX5_EVENT_TYPE_PAGE_FAULT:
-		return "MLX5_EVENT_TYPE_PAGE_FAULT";
-	case MLX5_EVENT_TYPE_PPS_EVENT:
-		return "MLX5_EVENT_TYPE_PPS_EVENT";
-	case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE:
-		return "MLX5_EVENT_TYPE_NIC_VPORT_CHANGE";
-	case MLX5_EVENT_TYPE_FPGA_ERROR:
-		return "MLX5_EVENT_TYPE_FPGA_ERROR";
-	case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
-		return "MLX5_EVENT_TYPE_FPGA_QP_ERROR";
-	case MLX5_EVENT_TYPE_GENERAL_EVENT:
-		return "MLX5_EVENT_TYPE_GENERAL_EVENT";
-	case MLX5_EVENT_TYPE_DEVICE_TRACER:
-		return "MLX5_EVENT_TYPE_DEVICE_TRACER";
-	default:
-		return "Unrecognized event";
-	}
-}
-
-static enum mlx5_dev_event port_subtype_event(u8 subtype)
-{
-	switch (subtype) {
-	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
-		return MLX5_DEV_EVENT_PORT_DOWN;
-	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-		return MLX5_DEV_EVENT_PORT_UP;
-	case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
-		return MLX5_DEV_EVENT_PORT_INITIALIZED;
-	case MLX5_PORT_CHANGE_SUBTYPE_LID:
-		return MLX5_DEV_EVENT_LID_CHANGE;
-	case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
-		return MLX5_DEV_EVENT_PKEY_CHANGE;
-	case MLX5_PORT_CHANGE_SUBTYPE_GUID:
-		return MLX5_DEV_EVENT_GUID_CHANGE;
-	case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
-		return MLX5_DEV_EVENT_CLIENT_REREG;
-	}
-	return -1;
-}
-
-static void general_event_handler(struct mlx5_core_dev *dev,
-				  struct mlx5_eqe *eqe)
-{
-	switch (eqe->sub_type) {
-	case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT:
-		if (dev->event)
-			dev->event(dev, MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT, 0);
-		break;
-	default:
-		mlx5_core_dbg(dev, "General event with unrecognized subtype: sub_type %d\n",
-			      eqe->sub_type);
-	}
-}
-
-static void mlx5_temp_warning_event(struct mlx5_core_dev *dev,
-				    struct mlx5_eqe *eqe)
-{
-	u64 value_lsb;
-	u64 value_msb;
-
-	value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
-	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
-
-	mlx5_core_warn(dev,
-		       "High temperature on sensors with bit set %llx %llx",
-		       value_msb, value_lsb);
-}
-
 /* caller must eventually call mlx5_cq_put on the returned cq */
 static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn)
 {
@@ -312,7 +197,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 	struct mlx5_core_dev *dev;
 	struct mlx5_eqe *eqe;
 	int set_ci = 0;
-	u8 port;
 
 	dev = eq->dev;
 	eqt = dev->priv.eq_table;
@@ -324,47 +208,6 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 		 */
 		dma_rmb();
 
-		mlx5_core_dbg(eq->dev, "eqn %d, eqe type %s\n",
-			      eq->eqn, eqe_type_str(eqe->type));
-		switch (eqe->type) {
-		case MLX5_EVENT_TYPE_PORT_CHANGE:
-			port = (eqe->data.port.port >> 4) & 0xf;
-			switch (eqe->sub_type) {
-			case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
-			case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-			case MLX5_PORT_CHANGE_SUBTYPE_LID:
-			case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
-			case MLX5_PORT_CHANGE_SUBTYPE_GUID:
-			case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
-			case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
-				if (dev->event)
-					dev->event(dev, port_subtype_event(eqe->sub_type),
-						   (unsigned long)port);
-				break;
-			default:
-				mlx5_core_warn(dev, "Port event with unrecognized subtype: port %d, sub_type %d\n",
-					       port, eqe->sub_type);
-			}
-			break;
-
-		case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
-			mlx5_port_module_event(dev, eqe);
-			break;
-
-		case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
-			mlx5_temp_warning_event(dev, eqe);
-			break;
-
-		case MLX5_EVENT_TYPE_GENERAL_EVENT:
-			general_event_handler(dev, eqe);
-			break;
-
-		default:
-			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
-				       eqe->type, eq->eqn);
-			break;
-		}
-
 		if (likely(eqe->type < MLX5_EVENT_TYPE_MAX))
 			atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe);
 		else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
new file mode 100644
index 000000000000..d3ab86bd394b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2018 Mellanox Technologies
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+#include "lib/eq.h"
+#include "lib/mlx5.h"
+
+struct mlx5_events {
+	struct mlx5_nb        nb;
+	struct mlx5_core_dev *dev;
+
+	/* port module evetns stats */
+	struct mlx5_pme_stats pme_stats;
+};
+
+static const char *eqe_type_str(u8 type)
+{
+	switch (type) {
+	case MLX5_EVENT_TYPE_COMP:
+		return "MLX5_EVENT_TYPE_COMP";
+	case MLX5_EVENT_TYPE_PATH_MIG:
+		return "MLX5_EVENT_TYPE_PATH_MIG";
+	case MLX5_EVENT_TYPE_COMM_EST:
+		return "MLX5_EVENT_TYPE_COMM_EST";
+	case MLX5_EVENT_TYPE_SQ_DRAINED:
+		return "MLX5_EVENT_TYPE_SQ_DRAINED";
+	case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
+		return "MLX5_EVENT_TYPE_SRQ_LAST_WQE";
+	case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
+		return "MLX5_EVENT_TYPE_SRQ_RQ_LIMIT";
+	case MLX5_EVENT_TYPE_CQ_ERROR:
+		return "MLX5_EVENT_TYPE_CQ_ERROR";
+	case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
+		return "MLX5_EVENT_TYPE_WQ_CATAS_ERROR";
+	case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
+		return "MLX5_EVENT_TYPE_PATH_MIG_FAILED";
+	case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+		return "MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR";
+	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
+		return "MLX5_EVENT_TYPE_WQ_ACCESS_ERROR";
+	case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
+		return "MLX5_EVENT_TYPE_SRQ_CATAS_ERROR";
+	case MLX5_EVENT_TYPE_INTERNAL_ERROR:
+		return "MLX5_EVENT_TYPE_INTERNAL_ERROR";
+	case MLX5_EVENT_TYPE_PORT_CHANGE:
+		return "MLX5_EVENT_TYPE_PORT_CHANGE";
+	case MLX5_EVENT_TYPE_GPIO_EVENT:
+		return "MLX5_EVENT_TYPE_GPIO_EVENT";
+	case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
+		return "MLX5_EVENT_TYPE_PORT_MODULE_EVENT";
+	case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
+		return "MLX5_EVENT_TYPE_TEMP_WARN_EVENT";
+	case MLX5_EVENT_TYPE_REMOTE_CONFIG:
+		return "MLX5_EVENT_TYPE_REMOTE_CONFIG";
+	case MLX5_EVENT_TYPE_DB_BF_CONGESTION:
+		return "MLX5_EVENT_TYPE_DB_BF_CONGESTION";
+	case MLX5_EVENT_TYPE_STALL_EVENT:
+		return "MLX5_EVENT_TYPE_STALL_EVENT";
+	case MLX5_EVENT_TYPE_CMD:
+		return "MLX5_EVENT_TYPE_CMD";
+	case MLX5_EVENT_TYPE_PAGE_REQUEST:
+		return "MLX5_EVENT_TYPE_PAGE_REQUEST";
+	case MLX5_EVENT_TYPE_PAGE_FAULT:
+		return "MLX5_EVENT_TYPE_PAGE_FAULT";
+	case MLX5_EVENT_TYPE_PPS_EVENT:
+		return "MLX5_EVENT_TYPE_PPS_EVENT";
+	case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE:
+		return "MLX5_EVENT_TYPE_NIC_VPORT_CHANGE";
+	case MLX5_EVENT_TYPE_FPGA_ERROR:
+		return "MLX5_EVENT_TYPE_FPGA_ERROR";
+	case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
+		return "MLX5_EVENT_TYPE_FPGA_QP_ERROR";
+	case MLX5_EVENT_TYPE_GENERAL_EVENT:
+		return "MLX5_EVENT_TYPE_GENERAL_EVENT";
+	case MLX5_EVENT_TYPE_DEVICE_TRACER:
+		return "MLX5_EVENT_TYPE_DEVICE_TRACER";
+	default:
+		return "Unrecognized event";
+	}
+}
+
+static enum mlx5_dev_event port_subtype2dev(u8 subtype)
+{
+	switch (subtype) {
+	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+		return MLX5_DEV_EVENT_PORT_DOWN;
+	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+		return MLX5_DEV_EVENT_PORT_UP;
+	case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
+		return MLX5_DEV_EVENT_PORT_INITIALIZED;
+	case MLX5_PORT_CHANGE_SUBTYPE_LID:
+		return MLX5_DEV_EVENT_LID_CHANGE;
+	case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
+		return MLX5_DEV_EVENT_PKEY_CHANGE;
+	case MLX5_PORT_CHANGE_SUBTYPE_GUID:
+		return MLX5_DEV_EVENT_GUID_CHANGE;
+	case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
+		return MLX5_DEV_EVENT_CLIENT_REREG;
+	}
+	return -1;
+}
+
+static void temp_warning_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
+{
+	u64 value_lsb;
+	u64 value_msb;
+
+	value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
+	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
+
+	mlx5_core_warn(dev,
+		       "High temperature on sensors with bit set %llx %llx",
+		       value_msb, value_lsb);
+}
+
+static const char *mlx5_pme_status[MLX5_MODULE_STATUS_NUM] = {
+	"Cable plugged",   /* MLX5_MODULE_STATUS_PLUGGED    = 0x1 */
+	"Cable unplugged", /* MLX5_MODULE_STATUS_UNPLUGGED  = 0x2 */
+	"Cable error",     /* MLX5_MODULE_STATUS_ERROR      = 0x3 */
+};
+
+static const char *mlx5_pme_error[MLX5_MODULE_EVENT_ERROR_NUM] = {
+	"Power budget exceeded",
+	"Long Range for non MLNX cable",
+	"Bus stuck(I2C or data shorted)",
+	"No EEPROM/retry timeout",
+	"Enforce part number list",
+	"Unknown identifier",
+	"High Temperature",
+	"Bad or shorted cable/module",
+	"Unknown status",
+};
+
+static void port_module_event(struct mlx5_events *events, struct mlx5_eqe *eqe)
+{
+	enum port_module_event_status_type module_status;
+	enum port_module_event_error_type error_type;
+	struct mlx5_eqe_port_module *module_event_eqe;
+	struct mlx5_core_dev *dev = events->dev;
+	u8 module_num;
+
+	module_event_eqe = &eqe->data.port_module;
+	module_num = module_event_eqe->module;
+	module_status = module_event_eqe->module_status &
+			PORT_MODULE_EVENT_MODULE_STATUS_MASK;
+	error_type = module_event_eqe->error_type &
+		     PORT_MODULE_EVENT_ERROR_TYPE_MASK;
+
+	if (module_status < MLX5_MODULE_STATUS_ERROR) {
+		events->pme_stats.status_counters[module_status - 1]++;
+	} else if (module_status == MLX5_MODULE_STATUS_ERROR) {
+		if (error_type >= MLX5_MODULE_EVENT_ERROR_UNKNOWN)
+			/* Unknown error type */
+			error_type = MLX5_MODULE_EVENT_ERROR_UNKNOWN;
+		events->pme_stats.error_counters[error_type]++;
+	}
+
+	if (!printk_ratelimit())
+		return;
+
+	if (module_status < MLX5_MODULE_STATUS_ERROR)
+		mlx5_core_info(dev,
+			       "Port module event: module %u, %s\n",
+			       module_num, mlx5_pme_status[module_status - 1]);
+
+	else if (module_status == MLX5_MODULE_STATUS_ERROR)
+		mlx5_core_info(dev,
+			       "Port module event[error]: module %u, %s, %s\n",
+			       module_num, mlx5_pme_status[module_status - 1],
+			       mlx5_pme_error[error_type]);
+}
+
+void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats)
+{
+	*stats = dev->priv.events->pme_stats;
+}
+
+/* Event handler for the low level mlx5_core driver.
+ * This handler will process/filter _some_ events and sometimes dispatch
+ * the equivalent mlx5_dev_event to the HCA interfaces (mlx5_ib and mlx5e)
+ *
+ * Other Major feature specific events such as
+ * clock/eswitch/fpga/FW trace and many others, are handled elsewhere, with
+ * separate notifiers callbacks, specifically by those mlx5 components.
+ */
+static int events_notifier(struct notifier_block *nb,
+			   unsigned long type, void *data)
+{
+	bool dev_event_dispatch = false;
+	enum mlx5_dev_event dev_event;
+	unsigned long dev_event_data;
+
+	struct mlx5_eqe *eqe = data;
+	struct mlx5_events *events;
+	struct mlx5_core_dev *dev;
+	u8 port;
+
+	events = mlx5_nb_cof(nb, struct mlx5_events, nb);
+	dev = events->dev;
+
+	mlx5_core_dbg(dev, "Async eqe type %s, subtype (%d)\n",
+		      eqe_type_str(eqe->type), eqe->sub_type);
+	switch (eqe->type) {
+	case MLX5_EVENT_TYPE_PORT_CHANGE:
+		port = (eqe->data.port.port >> 4) & 0xf;
+		switch (eqe->sub_type) {
+		case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+		case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+		case MLX5_PORT_CHANGE_SUBTYPE_LID:
+		case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
+		case MLX5_PORT_CHANGE_SUBTYPE_GUID:
+		case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
+		case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
+			dev_event = port_subtype2dev(eqe->sub_type);
+			dev_event_data = (unsigned long)port;
+			dev_event_dispatch = true;
+			break;
+		default:
+			mlx5_core_warn(dev, "Port event with unrecognized subtype: port %d, sub_type %d\n",
+				       port, eqe->sub_type);
+		}
+		break;
+	case MLX5_EVENT_TYPE_GENERAL_EVENT:
+		switch (eqe->sub_type) {
+		case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT:
+			dev_event = MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT;
+			dev_event_data = 0;
+			dev_event_dispatch = true;
+			break;
+		default:
+			mlx5_core_dbg(dev, "General event with unrecognized subtype: sub_type %d\n",
+				      eqe->sub_type);
+		}
+		break;
+
+	case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
+		port_module_event(events, eqe);
+		break;
+	case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
+		temp_warning_event(dev, eqe);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	if (dev->event && dev_event_dispatch)
+		dev->event(dev, dev_event, dev_event_data);
+
+	return NOTIFY_OK;
+}
+
+int mlx5_events_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_events *events = kzalloc(sizeof(*events), GFP_KERNEL);
+
+	if (!events)
+		return -ENOMEM;
+
+	events->dev = dev;
+	dev->priv.events = events;
+	return 0;
+}
+
+void mlx5_events_cleanup(struct mlx5_core_dev *dev)
+{
+	kvfree(dev->priv.events);
+}
+
+void mlx5_events_start(struct mlx5_core_dev *dev)
+{
+	struct mlx5_events *events = dev->priv.events;
+
+	MLX5_NB_INIT(&events->nb, events_notifier, NOTIFY_ANY);
+	mlx5_eq_notifier_register(dev, &events->nb);
+}
+
+void mlx5_events_stop(struct mlx5_core_dev *dev)
+{
+	struct mlx5_events *events = dev->priv.events;
+
+	mlx5_eq_notifier_unregister(dev, &events->nb);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 7550b1cc8c6a..23317e328b0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -33,6 +33,8 @@
 #ifndef __LIB_MLX5_H__
 #define __LIB_MLX5_H__
 
+#include "mlx5_core.h"
+
 void mlx5_init_reserved_gids(struct mlx5_core_dev *dev);
 void mlx5_cleanup_reserved_gids(struct mlx5_core_dev *dev);
 int  mlx5_core_reserve_gids(struct mlx5_core_dev *dev, unsigned int count);
@@ -40,4 +42,36 @@ void mlx5_core_unreserve_gids(struct mlx5_core_dev *dev, unsigned int count);
 int  mlx5_core_reserved_gid_alloc(struct mlx5_core_dev *dev, int *gid_index);
 void mlx5_core_reserved_gid_free(struct mlx5_core_dev *dev, int gid_index);
 
+/* TODO move to lib/events.h */
+
+#define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF
+#define PORT_MODULE_EVENT_ERROR_TYPE_MASK    0xF
+
+enum port_module_event_status_type {
+	MLX5_MODULE_STATUS_PLUGGED   = 0x1,
+	MLX5_MODULE_STATUS_UNPLUGGED = 0x2,
+	MLX5_MODULE_STATUS_ERROR     = 0x3,
+	MLX5_MODULE_STATUS_NUM       = 0x3,
+};
+
+enum  port_module_event_error_type {
+	MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED,
+	MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX_CABLE_MODULE,
+	MLX5_MODULE_EVENT_ERROR_BUS_STUCK,
+	MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT,
+	MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST,
+	MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER,
+	MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE,
+	MLX5_MODULE_EVENT_ERROR_BAD_CABLE,
+	MLX5_MODULE_EVENT_ERROR_UNKNOWN,
+	MLX5_MODULE_EVENT_ERROR_NUM,
+};
+
+struct mlx5_pme_stats {
+	u64 status_counters[MLX5_MODULE_STATUS_NUM];
+	u64 error_counters[MLX5_MODULE_EVENT_ERROR_NUM];
+};
+
+void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats);
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 9e4cd2757ea8..e56278ead4eb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -735,10 +735,16 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 		goto out;
 	}
 
+	err = mlx5_events_init(dev);
+	if (err) {
+		dev_err(&pdev->dev, "failed to initialize events\n");
+		goto err_eq_cleanup;
+	}
+
 	err = mlx5_cq_debugfs_init(dev);
 	if (err) {
 		dev_err(&pdev->dev, "failed to initialize cq debugfs\n");
-		goto err_eq_cleanup;
+		goto err_events_cleanup;
 	}
 
 	mlx5_init_qp_table(dev);
@@ -801,7 +807,8 @@ err_tables_cleanup:
 	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
 	mlx5_cq_debugfs_cleanup(dev);
-
+err_events_cleanup:
+	mlx5_events_cleanup(dev);
 err_eq_cleanup:
 	mlx5_eq_table_cleanup(dev);
 
@@ -824,6 +831,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
 	mlx5_cq_debugfs_cleanup(dev);
+	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
 }
 
@@ -947,6 +955,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_get_uars;
 	}
 
+	mlx5_events_start(dev);
 	mlx5_pagealloc_start(dev);
 
 	err = mlx5_eq_table_create(dev);
@@ -1036,6 +1045,7 @@ err_fw_tracer:
 
 err_eq_table:
 	mlx5_pagealloc_stop(dev);
+	mlx5_events_stop(dev);
 	mlx5_put_uars_page(dev, priv->uar);
 
 err_get_uars:
@@ -1095,8 +1105,8 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_fw_tracer_cleanup(dev->tracer);
 	mlx5_eq_table_destroy(dev);
 	mlx5_pagealloc_stop(dev);
+	mlx5_events_stop(dev);
 	mlx5_put_uars_page(dev, priv->uar);
-
 	if (cleanup)
 		mlx5_cleanup_once(dev);
 	mlx5_stop_health_poll(dev, cleanup);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 5dd453e47a04..c70bd94e18d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -105,7 +105,6 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev);
 
 void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 		     unsigned long param);
-void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
 void mlx5_recover_device(struct mlx5_core_dev *dev);
@@ -141,6 +140,11 @@ int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam,
 void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev);
 void mlx5_lag_remove(struct mlx5_core_dev *dev);
 
+int mlx5_events_init(struct mlx5_core_dev *dev);
+void mlx5_events_cleanup(struct mlx5_core_dev *dev);
+void mlx5_events_start(struct mlx5_core_dev *dev);
+void mlx5_events_stop(struct mlx5_core_dev *dev);
+
 void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv);
 void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv);
 void mlx5_attach_device(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 31a9cbd85689..2b82f35f4c35 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -915,63 +915,6 @@ void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported,
 	*enabled = !!(MLX5_GET(pcmr_reg, out, fcs_chk));
 }
 
-static const char *mlx5_pme_status[MLX5_MODULE_STATUS_NUM] = {
-	"Cable plugged",   /* MLX5_MODULE_STATUS_PLUGGED    = 0x1 */
-	"Cable unplugged", /* MLX5_MODULE_STATUS_UNPLUGGED  = 0x2 */
-	"Cable error",     /* MLX5_MODULE_STATUS_ERROR      = 0x3 */
-};
-
-static const char *mlx5_pme_error[MLX5_MODULE_EVENT_ERROR_NUM] = {
-	"Power budget exceeded",
-	"Long Range for non MLNX cable",
-	"Bus stuck(I2C or data shorted)",
-	"No EEPROM/retry timeout",
-	"Enforce part number list",
-	"Unknown identifier",
-	"High Temperature",
-	"Bad or shorted cable/module",
-	"Unknown status",
-};
-
-void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
-{
-	enum port_module_event_status_type module_status;
-	enum port_module_event_error_type error_type;
-	struct mlx5_eqe_port_module *module_event_eqe;
-	struct mlx5_priv *priv = &dev->priv;
-	u8 module_num;
-
-	module_event_eqe = &eqe->data.port_module;
-	module_num = module_event_eqe->module;
-	module_status = module_event_eqe->module_status &
-			PORT_MODULE_EVENT_MODULE_STATUS_MASK;
-	error_type = module_event_eqe->error_type &
-		     PORT_MODULE_EVENT_ERROR_TYPE_MASK;
-
-	if (module_status < MLX5_MODULE_STATUS_ERROR) {
-		priv->pme_stats.status_counters[module_status - 1]++;
-	} else if (module_status == MLX5_MODULE_STATUS_ERROR) {
-		if (error_type >= MLX5_MODULE_EVENT_ERROR_UNKNOWN)
-			/* Unknown error type */
-			error_type = MLX5_MODULE_EVENT_ERROR_UNKNOWN;
-		priv->pme_stats.error_counters[error_type]++;
-	}
-
-	if (!printk_ratelimit())
-		return;
-
-	if (module_status < MLX5_MODULE_STATUS_ERROR)
-		mlx5_core_info(dev,
-			       "Port module event: module %u, %s\n",
-			       module_num, mlx5_pme_status[module_status - 1]);
-
-	else if (module_status == MLX5_MODULE_STATUS_ERROR)
-		mlx5_core_info(dev,
-			       "Port module event[error]: module %u, %s, %s\n",
-			       module_num, mlx5_pme_status[module_status - 1],
-			       mlx5_pme_error[error_type]);
-}
-
 int mlx5_query_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size)
 {
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index afba0864f45c..ba64ecf72478 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -514,6 +514,7 @@ struct mlx5_fc_stats {
 	unsigned long sampling_interval; /* jiffies */
 };
 
+struct mlx5_events;
 struct mlx5_mpfs;
 struct mlx5_eswitch;
 struct mlx5_lag;
@@ -540,31 +541,6 @@ struct mlx5_rl_table {
 	struct mlx5_rl_entry   *rl_entry;
 };
 
-enum port_module_event_status_type {
-	MLX5_MODULE_STATUS_PLUGGED   = 0x1,
-	MLX5_MODULE_STATUS_UNPLUGGED = 0x2,
-	MLX5_MODULE_STATUS_ERROR     = 0x3,
-	MLX5_MODULE_STATUS_NUM       = 0x3,
-};
-
-enum  port_module_event_error_type {
-	MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED,
-	MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX_CABLE_MODULE,
-	MLX5_MODULE_EVENT_ERROR_BUS_STUCK,
-	MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT,
-	MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST,
-	MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER,
-	MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE,
-	MLX5_MODULE_EVENT_ERROR_BAD_CABLE,
-	MLX5_MODULE_EVENT_ERROR_UNKNOWN,
-	MLX5_MODULE_EVENT_ERROR_NUM,
-};
-
-struct mlx5_port_module_event_stats {
-	u64 status_counters[MLX5_MODULE_STATUS_NUM];
-	u64 error_counters[MLX5_MODULE_EVENT_ERROR_NUM];
-};
-
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	*eq_table;
@@ -614,6 +590,7 @@ struct mlx5_priv {
 
 	struct list_head	waiting_events_list;
 	bool			is_accum_events;
+	struct mlx5_events     *events;
 
 	struct mlx5_flow_steering *steering;
 	struct mlx5_mpfs        *mpfs;
@@ -624,8 +601,6 @@ struct mlx5_priv {
 	struct mlx5_fc_stats		fc_stats;
 	struct mlx5_rl_table            rl_table;
 
-	struct mlx5_port_module_event_stats  pme_stats;
-
 	struct mlx5_bfreg_data		bfregs;
 	struct mlx5_uars_page	       *uar;
 };
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 34aed6032f86..bf4bc01ffb0c 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -107,9 +107,6 @@ enum mlx5e_connector_type {
 
 #define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
 
-#define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF
-#define PORT_MODULE_EVENT_ERROR_TYPE_MASK         0xF
-
 int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
 int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
 			 int ptys_size, int proto_mask, u8 local_port);
-- 
cgit v1.2.3


From 2c89156082b3be7a064b09dfb0bcd274609f355d Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 20 Nov 2018 14:12:28 -0800
Subject: net/mlx5: Improve core device events handling

Register a separate handler per event type, rather than listening for all
events and looking for the events to handle in a switch case.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 223 ++++++++++++++---------
 1 file changed, 136 insertions(+), 87 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index d3ab86bd394b..3ad004af37d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -2,15 +2,41 @@
 // Copyright (c) 2018 Mellanox Technologies
 
 #include <linux/mlx5/driver.h>
+
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "lib/mlx5.h"
 
+struct mlx5_event_nb {
+	struct mlx5_nb  nb;
+	void           *ctx;
+};
+
+/* General events handlers for the low level mlx5_core driver
+ *
+ * Other Major feature specific events such as
+ * clock/eswitch/fpga/FW trace and many others, are handled elsewhere, with
+ * separate notifiers callbacks, specifically by those mlx5 components.
+ */
+static int any_notifier(struct notifier_block *, unsigned long, void *);
+static int port_change(struct notifier_block *, unsigned long, void *);
+static int general_event(struct notifier_block *, unsigned long, void *);
+static int temp_warn(struct notifier_block *, unsigned long, void *);
+static int port_module(struct notifier_block *, unsigned long, void *);
+
+static struct mlx5_nb events_nbs_ref[] = {
+	{.nb.notifier_call = any_notifier,  .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY },
+	{.nb.notifier_call = port_change,   .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
+	{.nb.notifier_call = general_event, .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT },
+	{.nb.notifier_call = temp_warn,     .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT },
+	{.nb.notifier_call = port_module,   .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT },
+};
+
 struct mlx5_events {
-	struct mlx5_nb        nb;
 	struct mlx5_core_dev *dev;
+	struct mlx5_event_nb  notifiers[ARRAY_SIZE(events_nbs_ref)];
 
-	/* port module evetns stats */
+	/* port module events stats */
 	struct mlx5_pme_stats pme_stats;
 };
 
@@ -80,6 +106,19 @@ static const char *eqe_type_str(u8 type)
 	}
 }
 
+/* handles all FW events, type == eqe->type */
+static int any_notifier(struct notifier_block *nb,
+			unsigned long type, void *data)
+{
+	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_eqe      *eqe      = data;
+
+	mlx5_core_dbg(events->dev, "Async eqe type %s, subtype (%d)\n",
+		      eqe_type_str(eqe->type), eqe->sub_type);
+	return NOTIFY_OK;
+}
+
 static enum mlx5_dev_event port_subtype2dev(u8 subtype)
 {
 	switch (subtype) {
@@ -101,19 +140,92 @@ static enum mlx5_dev_event port_subtype2dev(u8 subtype)
 	return -1;
 }
 
-static void temp_warning_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
+/* type == MLX5_EVENT_TYPE_PORT_CHANGE */
+static int port_change(struct notifier_block *nb,
+		       unsigned long type, void *data)
 {
+	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_core_dev *dev      = events->dev;
+
+	bool dev_event_dispatch = false;
+	enum mlx5_dev_event dev_event;
+	unsigned long dev_event_data;
+	struct mlx5_eqe *eqe = data;
+	u8 port = (eqe->data.port.port >> 4) & 0xf;
+
+	switch (eqe->sub_type) {
+	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+	case MLX5_PORT_CHANGE_SUBTYPE_LID:
+	case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
+	case MLX5_PORT_CHANGE_SUBTYPE_GUID:
+	case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
+	case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
+		dev_event = port_subtype2dev(eqe->sub_type);
+		dev_event_data = (unsigned long)port;
+		dev_event_dispatch = true;
+		break;
+	default:
+		mlx5_core_warn(dev, "Port event with unrecognized subtype: port %d, sub_type %d\n",
+			       port, eqe->sub_type);
+	}
+
+	if (dev->event && dev_event_dispatch)
+		dev->event(dev, dev_event, dev_event_data);
+
+	return NOTIFY_OK;
+}
+
+/* type == MLX5_EVENT_TYPE_GENERAL_EVENT */
+static int general_event(struct notifier_block *nb, unsigned long type, void *data)
+{
+	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_core_dev *dev      = events->dev;
+
+	bool dev_event_dispatch = false;
+	enum mlx5_dev_event dev_event;
+	unsigned long dev_event_data;
+	struct mlx5_eqe *eqe = data;
+
+	switch (eqe->sub_type) {
+	case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT:
+		dev_event = MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT;
+		dev_event_data = 0;
+		dev_event_dispatch = true;
+		break;
+	default:
+		mlx5_core_dbg(dev, "General event with unrecognized subtype: sub_type %d\n",
+			      eqe->sub_type);
+	}
+
+	if (dev->event && dev_event_dispatch)
+		dev->event(dev, dev_event, dev_event_data);
+
+	return NOTIFY_OK;
+}
+
+/* type == MLX5_EVENT_TYPE_TEMP_WARN_EVENT */
+static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
+{
+	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_eqe      *eqe      = data;
 	u64 value_lsb;
 	u64 value_msb;
 
 	value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
 	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
 
-	mlx5_core_warn(dev,
+	mlx5_core_warn(events->dev,
 		       "High temperature on sensors with bit set %llx %llx",
 		       value_msb, value_lsb);
+
+	return NOTIFY_OK;
 }
 
+/* MLX5_EVENT_TYPE_PORT_MODULE_EVENT */
 static const char *mlx5_pme_status[MLX5_MODULE_STATUS_NUM] = {
 	"Cable plugged",   /* MLX5_MODULE_STATUS_PLUGGED    = 0x1 */
 	"Cable unplugged", /* MLX5_MODULE_STATUS_UNPLUGGED  = 0x2 */
@@ -132,12 +244,16 @@ static const char *mlx5_pme_error[MLX5_MODULE_EVENT_ERROR_NUM] = {
 	"Unknown status",
 };
 
-static void port_module_event(struct mlx5_events *events, struct mlx5_eqe *eqe)
+/* type == MLX5_EVENT_TYPE_PORT_MODULE_EVENT */
+static int port_module(struct notifier_block *nb, unsigned long type, void *data)
 {
+	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_eqe      *eqe      = data;
+
 	enum port_module_event_status_type module_status;
 	enum port_module_event_error_type error_type;
 	struct mlx5_eqe_port_module *module_event_eqe;
-	struct mlx5_core_dev *dev = events->dev;
 	u8 module_num;
 
 	module_event_eqe = &eqe->data.port_module;
@@ -146,7 +262,6 @@ static void port_module_event(struct mlx5_events *events, struct mlx5_eqe *eqe)
 			PORT_MODULE_EVENT_MODULE_STATUS_MASK;
 	error_type = module_event_eqe->error_type &
 		     PORT_MODULE_EVENT_ERROR_TYPE_MASK;
-
 	if (module_status < MLX5_MODULE_STATUS_ERROR) {
 		events->pme_stats.status_counters[module_status - 1]++;
 	} else if (module_status == MLX5_MODULE_STATUS_ERROR) {
@@ -157,18 +272,20 @@ static void port_module_event(struct mlx5_events *events, struct mlx5_eqe *eqe)
 	}
 
 	if (!printk_ratelimit())
-		return;
+		return NOTIFY_OK;
 
 	if (module_status < MLX5_MODULE_STATUS_ERROR)
-		mlx5_core_info(dev,
+		mlx5_core_info(events->dev,
 			       "Port module event: module %u, %s\n",
 			       module_num, mlx5_pme_status[module_status - 1]);
 
 	else if (module_status == MLX5_MODULE_STATUS_ERROR)
-		mlx5_core_info(dev,
+		mlx5_core_info(events->dev,
 			       "Port module event[error]: module %u, %s, %s\n",
 			       module_num, mlx5_pme_status[module_status - 1],
 			       mlx5_pme_error[error_type]);
+
+	return NOTIFY_OK;
 }
 
 void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats)
@@ -176,80 +293,6 @@ void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats)
 	*stats = dev->priv.events->pme_stats;
 }
 
-/* Event handler for the low level mlx5_core driver.
- * This handler will process/filter _some_ events and sometimes dispatch
- * the equivalent mlx5_dev_event to the HCA interfaces (mlx5_ib and mlx5e)
- *
- * Other Major feature specific events such as
- * clock/eswitch/fpga/FW trace and many others, are handled elsewhere, with
- * separate notifiers callbacks, specifically by those mlx5 components.
- */
-static int events_notifier(struct notifier_block *nb,
-			   unsigned long type, void *data)
-{
-	bool dev_event_dispatch = false;
-	enum mlx5_dev_event dev_event;
-	unsigned long dev_event_data;
-
-	struct mlx5_eqe *eqe = data;
-	struct mlx5_events *events;
-	struct mlx5_core_dev *dev;
-	u8 port;
-
-	events = mlx5_nb_cof(nb, struct mlx5_events, nb);
-	dev = events->dev;
-
-	mlx5_core_dbg(dev, "Async eqe type %s, subtype (%d)\n",
-		      eqe_type_str(eqe->type), eqe->sub_type);
-	switch (eqe->type) {
-	case MLX5_EVENT_TYPE_PORT_CHANGE:
-		port = (eqe->data.port.port >> 4) & 0xf;
-		switch (eqe->sub_type) {
-		case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
-		case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-		case MLX5_PORT_CHANGE_SUBTYPE_LID:
-		case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
-		case MLX5_PORT_CHANGE_SUBTYPE_GUID:
-		case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
-		case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
-			dev_event = port_subtype2dev(eqe->sub_type);
-			dev_event_data = (unsigned long)port;
-			dev_event_dispatch = true;
-			break;
-		default:
-			mlx5_core_warn(dev, "Port event with unrecognized subtype: port %d, sub_type %d\n",
-				       port, eqe->sub_type);
-		}
-		break;
-	case MLX5_EVENT_TYPE_GENERAL_EVENT:
-		switch (eqe->sub_type) {
-		case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT:
-			dev_event = MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT;
-			dev_event_data = 0;
-			dev_event_dispatch = true;
-			break;
-		default:
-			mlx5_core_dbg(dev, "General event with unrecognized subtype: sub_type %d\n",
-				      eqe->sub_type);
-		}
-		break;
-
-	case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
-		port_module_event(events, eqe);
-		break;
-	case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
-		temp_warning_event(dev, eqe);
-		break;
-	default:
-		return NOTIFY_DONE;
-	}
-
-	if (dev->event && dev_event_dispatch)
-		dev->event(dev, dev_event, dev_event_data);
-
-	return NOTIFY_OK;
-}
-
 int mlx5_events_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_events *events = kzalloc(sizeof(*events), GFP_KERNEL);
@@ -270,14 +313,20 @@ void mlx5_events_cleanup(struct mlx5_core_dev *dev)
 void mlx5_events_start(struct mlx5_core_dev *dev)
 {
 	struct mlx5_events *events = dev->priv.events;
+	int i;
 
-	MLX5_NB_INIT(&events->nb, events_notifier, NOTIFY_ANY);
-	mlx5_eq_notifier_register(dev, &events->nb);
+	for (i = 0; i < ARRAY_SIZE(events_nbs_ref); i++) {
+		events->notifiers[i].nb  = events_nbs_ref[i];
+		events->notifiers[i].ctx = events;
+		mlx5_eq_notifier_register(dev, &events->notifiers[i].nb);
+	}
 }
 
 void mlx5_events_stop(struct mlx5_core_dev *dev)
 {
 	struct mlx5_events *events = dev->priv.events;
+	int i;
 
-	mlx5_eq_notifier_unregister(dev, &events->nb);
+	for (i = ARRAY_SIZE(events_nbs_ref) - 1; i >= 0 ; i--)
+		mlx5_eq_notifier_unregister(dev, &events->notifiers[i].nb);
 }
-- 
cgit v1.2.3


From d8f3e978bd30014081c599456285ca1d58c2aae1 Mon Sep 17 00:00:00 2001
From: David Miller <davem@redhat.com>
Date: Mon, 26 Nov 2018 13:42:41 -0800
Subject: bpf: Avoid unnecessary instruction in convert_bpf_ld_abs()

'offset' is constant and if it is zero, no need to subtract it
from BPF_REG_TMP.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/core/filter.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index aa274679965d..f50ea971f7a9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -463,7 +463,8 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
 		bool ldx_off_ok = offset <= S16_MAX;
 
 		*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
-		*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
+		if (offset)
+			*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
 		*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP,
 				      size, 2 + endian + (!ldx_off_ok * 2));
 		if (ldx_off_ok) {
-- 
cgit v1.2.3


From ba64e7d8525236aa56ab58ba3a3a71615c4ee289 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 24 Nov 2018 23:20:44 -0800
Subject: bpf: btf: support proper non-jit func info

Commit 838e96904ff3 ("bpf: Introduce bpf_func_info")
added bpf func info support. The userspace is able
to get better ksym's for bpf programs with jit, and
is able to print out func prototypes.

For a program containing func-to-func calls, the existing
implementation returns user specified number of function
calls and BTF types if jit is enabled. If the jit is not
enabled, it only returns the type for the main function.

This is undesirable. Interpreter may still be used
and we should keep feature identical regardless of
whether jit is enabled or not.
This patch fixed this discrepancy.

Fixes: 838e96904ff3 ("bpf: Introduce bpf_func_info")
Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h          |  6 +++--
 include/linux/bpf_verifier.h |  1 -
 kernel/bpf/core.c            |  3 ++-
 kernel/bpf/syscall.c         | 33 +++++++-------------------
 kernel/bpf/verifier.c        | 55 ++++++++++++++++++++++++++++++--------------
 5 files changed, 52 insertions(+), 46 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7f0e225bf630..e82b7039fc66 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -299,7 +299,8 @@ struct bpf_prog_aux {
 	u32 max_pkt_offset;
 	u32 stack_depth;
 	u32 id;
-	u32 func_cnt;
+	u32 func_cnt; /* used by non-func prog as the number of func progs */
+	u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
 	bool offload_requested;
 	struct bpf_prog **func;
 	void *jit_data; /* JIT specific data. arch dependent */
@@ -317,7 +318,8 @@ struct bpf_prog_aux {
 #endif
 	struct bpf_prog_offload *offload;
 	struct btf *btf;
-	u32 type_id; /* type id for this prog/func */
+	struct bpf_func_info *func_info;
+	u32 func_info_cnt;
 	union {
 		struct work_struct work;
 		struct rcu_head	rcu;
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 204382f46fd8..11f5df1092d9 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -204,7 +204,6 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 struct bpf_subprog_info {
 	u32 start; /* insn idx of function entry point */
 	u16 stack_depth; /* max. stack depth used by this function */
-	u32 type_id; /* btf type_id for this subprog */
 };
 
 /* single container for all structs
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 16d77012ad3e..002d67c62c8b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -411,7 +411,8 @@ static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
 
 	/* prog->aux->name will be ignored if full btf name is available */
 	if (prog->aux->btf) {
-		type = btf_type_by_id(prog->aux->btf, prog->aux->type_id);
+		type = btf_type_by_id(prog->aux->btf,
+				      prog->aux->func_info[prog->aux->func_idx].type_id);
 		func_name = btf_name_by_offset(prog->aux->btf, type->name_off);
 		snprintf(sym, (size_t)(end - sym), "_%s", func_name);
 		return;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 998377808102..85cbeec06e50 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1214,6 +1214,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 		bpf_prog_free_id(prog, do_idr_lock);
 		bpf_prog_kallsyms_del_all(prog);
 		btf_put(prog->aux->btf);
+		kvfree(prog->aux->func_info);
 
 		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
 	}
@@ -2219,46 +2220,28 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	}
 
 	if (prog->aux->btf) {
+		u32 krec_size = sizeof(struct bpf_func_info);
 		u32 ucnt, urec_size;
 
 		info.btf_id = btf_id(prog->aux->btf);
 
 		ucnt = info.func_info_cnt;
-		info.func_info_cnt = prog->aux->func_cnt ? : 1;
+		info.func_info_cnt = prog->aux->func_info_cnt;
 		urec_size = info.func_info_rec_size;
-		info.func_info_rec_size = sizeof(struct bpf_func_info);
+		info.func_info_rec_size = krec_size;
 		if (ucnt) {
 			/* expect passed-in urec_size is what the kernel expects */
 			if (urec_size != info.func_info_rec_size)
 				return -EINVAL;
 
 			if (bpf_dump_raw_ok()) {
-				struct bpf_func_info kern_finfo;
 				char __user *user_finfo;
-				u32 i, insn_offset;
 
 				user_finfo = u64_to_user_ptr(info.func_info);
-				if (prog->aux->func_cnt) {
-					ucnt = min_t(u32, info.func_info_cnt, ucnt);
-					insn_offset = 0;
-					for (i = 0; i < ucnt; i++) {
-						kern_finfo.insn_offset = insn_offset;
-						kern_finfo.type_id = prog->aux->func[i]->aux->type_id;
-						if (copy_to_user(user_finfo, &kern_finfo,
-								 sizeof(kern_finfo)))
-							return -EFAULT;
-
-						/* func[i]->len holds the prog len */
-						insn_offset += prog->aux->func[i]->len;
-						user_finfo += urec_size;
-					}
-				} else {
-					kern_finfo.insn_offset = 0;
-					kern_finfo.type_id = prog->aux->type_id;
-					if (copy_to_user(user_finfo, &kern_finfo,
-							 sizeof(kern_finfo)))
-						return -EFAULT;
-				}
+				ucnt = min_t(u32, info.func_info_cnt, ucnt);
+				if (copy_to_user(user_finfo, prog->aux->func_info,
+						 krec_size * ucnt))
+					return -EFAULT;
 			} else {
 				info.func_info_cnt = 0;
 			}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f102c4fd0c5a..05d95c0e4a26 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4650,7 +4650,7 @@ static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
 {
 	u32 i, nfuncs, urec_size, min_size, prev_offset;
 	u32 krec_size = sizeof(struct bpf_func_info);
-	struct bpf_func_info krecord = {};
+	struct bpf_func_info *krecord = NULL;
 	const struct btf_type *type;
 	void __user *urecord;
 	struct btf *btf;
@@ -4682,6 +4682,12 @@ static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
 	urecord = u64_to_user_ptr(attr->func_info);
 	min_size = min_t(u32, krec_size, urec_size);
 
+	krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
+	if (!krecord) {
+		ret = -ENOMEM;
+		goto free_btf;
+	}
+
 	for (i = 0; i < nfuncs; i++) {
 		ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
 		if (ret) {
@@ -4696,59 +4702,69 @@ static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
 			goto free_btf;
 		}
 
-		if (copy_from_user(&krecord, urecord, min_size)) {
+		if (copy_from_user(&krecord[i], urecord, min_size)) {
 			ret = -EFAULT;
 			goto free_btf;
 		}
 
 		/* check insn_offset */
 		if (i == 0) {
-			if (krecord.insn_offset) {
+			if (krecord[i].insn_offset) {
 				verbose(env,
 					"nonzero insn_offset %u for the first func info record",
-					krecord.insn_offset);
+					krecord[i].insn_offset);
 				ret = -EINVAL;
 				goto free_btf;
 			}
-		} else if (krecord.insn_offset <= prev_offset) {
+		} else if (krecord[i].insn_offset <= prev_offset) {
 			verbose(env,
 				"same or smaller insn offset (%u) than previous func info record (%u)",
-				krecord.insn_offset, prev_offset);
+				krecord[i].insn_offset, prev_offset);
 			ret = -EINVAL;
 			goto free_btf;
 		}
 
-		if (env->subprog_info[i].start != krecord.insn_offset) {
+		if (env->subprog_info[i].start != krecord[i].insn_offset) {
 			verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
 			ret = -EINVAL;
 			goto free_btf;
 		}
 
 		/* check type_id */
-		type = btf_type_by_id(btf, krecord.type_id);
+		type = btf_type_by_id(btf, krecord[i].type_id);
 		if (!type || BTF_INFO_KIND(type->info) != BTF_KIND_FUNC) {
 			verbose(env, "invalid type id %d in func info",
-				krecord.type_id);
+				krecord[i].type_id);
 			ret = -EINVAL;
 			goto free_btf;
 		}
 
-		if (i == 0)
-			prog->aux->type_id = krecord.type_id;
-		env->subprog_info[i].type_id = krecord.type_id;
-
-		prev_offset = krecord.insn_offset;
+		prev_offset = krecord[i].insn_offset;
 		urecord += urec_size;
 	}
 
 	prog->aux->btf = btf;
+	prog->aux->func_info = krecord;
+	prog->aux->func_info_cnt = nfuncs;
 	return 0;
 
 free_btf:
 	btf_put(btf);
+	kvfree(krecord);
 	return ret;
 }
 
+static void adjust_btf_func(struct bpf_verifier_env *env)
+{
+	int i;
+
+	if (!env->prog->aux->func_info)
+		return;
+
+	for (i = 0; i < env->subprog_cnt; i++)
+		env->prog->aux->func_info[i].insn_offset = env->subprog_info[i].start;
+}
+
 /* check %cur's range satisfies %old's */
 static bool range_within(struct bpf_reg_state *old,
 			 struct bpf_reg_state *cur)
@@ -6043,15 +6059,17 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		if (bpf_prog_calc_tag(func[i]))
 			goto out_free;
 		func[i]->is_func = 1;
+		func[i]->aux->func_idx = i;
+		/* the btf and func_info will be freed only at prog->aux */
+		func[i]->aux->btf = prog->aux->btf;
+		func[i]->aux->func_info = prog->aux->func_info;
+
 		/* Use bpf_prog_F_tag to indicate functions in stack traces.
 		 * Long term would need debug info to populate names
 		 */
 		func[i]->aux->name[0] = 'F';
 		func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
 		func[i]->jit_requested = 1;
-		/* the btf will be freed only at prog->aux */
-		func[i]->aux->btf = prog->aux->btf;
-		func[i]->aux->type_id = env->subprog_info[i].type_id;
 		func[i] = bpf_int_jit_compile(func[i]);
 		if (!func[i]->jited) {
 			err = -ENOTSUPP;
@@ -6572,6 +6590,9 @@ skip_full_check:
 		convert_pseudo_ld_imm64(env);
 	}
 
+	if (ret == 0)
+		adjust_btf_func(env);
+
 err_release_maps:
 	if (!env->prog->aux->used_maps)
 		/* if we didn't copy map pointers into bpf_prog_info, release
-- 
cgit v1.2.3


From 812dd689da2a9af1208449588e4529c89a9d661d Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 24 Nov 2018 23:20:45 -0800
Subject: tools/bpf: change selftest test_btf for both jit and non-jit

The selftest test_btf is changed to test both jit and non-jit.
The test result should be the same regardless of whether jit
is enabled or not.

Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_btf.c | 33 +++------------------------------
 1 file changed, 3 insertions(+), 30 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index bcbda7037840..b4c8725b3004 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -29,7 +29,6 @@
 static uint32_t pass_cnt;
 static uint32_t error_cnt;
 static uint32_t skip_cnt;
-static bool jit_enabled;
 
 #define CHECK(condition, format...) ({					\
 	int __ret = !!(condition);					\
@@ -65,24 +64,6 @@ static int __base_pr(const char *format, ...)
 	return err;
 }
 
-static bool is_jit_enabled(void)
-{
-	const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
-	bool enabled = false;
-	int sysctl_fd;
-
-	sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
-	if (sysctl_fd != -1) {
-		char tmpc;
-
-		if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
-			enabled = (tmpc != '0');
-		close(sysctl_fd);
-	}
-
-	return enabled;
-}
-
 #define BTF_INFO_ENC(kind, root, vlen)			\
 	((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
 
@@ -2547,8 +2528,8 @@ static int do_test_file(unsigned int test_num)
 		  test->btf_kv_notfound))
 		goto done;
 
-	if (!jit_enabled || !has_btf_ext)
-		goto skip_jit;
+	if (!has_btf_ext)
+		goto skip;
 
 	/* get necessary program info */
 	info_len = sizeof(struct bpf_prog_info);
@@ -2636,7 +2617,7 @@ static int do_test_file(unsigned int test_num)
 		finfo = (void *)finfo + rec_size;
 	}
 
-skip_jit:
+skip:
 	fprintf(stderr, "OK");
 
 done:
@@ -3270,12 +3251,6 @@ static int do_test_func_type(int test_num)
 		err = -1;
 		goto done;
 	}
-	if (!jit_enabled) {
-		skip_cnt++;
-		fprintf(stderr, "SKIPPED, please enable sysctl bpf_jit_enable\n");
-		err = 0;
-		goto done;
-	}
 
 	/* get necessary lens */
 	info_len = sizeof(struct bpf_prog_info);
@@ -3452,8 +3427,6 @@ int main(int argc, char **argv)
 	if (args.always_log)
 		libbpf_set_print(__base_pr, __base_pr, __base_pr);
 
-	jit_enabled = is_jit_enabled();
-
 	if (args.raw_test)
 		err |= test_raw();
 
-- 
cgit v1.2.3


From 1d2f44ca342445f7da56555ca7a43d19aac8996a Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 23 Nov 2018 16:44:32 -0800
Subject: libbpf: Name changing for btf_get_from_id

s/btf_get_from_id/btf__get_from_id/ to restore the API naming convention.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/map.c                | 4 ++--
 tools/bpf/bpftool/prog.c               | 2 +-
 tools/lib/bpf/btf.c                    | 2 +-
 tools/lib/bpf/btf.h                    | 2 +-
 tools/testing/selftests/bpf/test_btf.c | 2 +-
 5 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index cbd3080e72c7..3850f8d65703 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -713,7 +713,7 @@ static int do_dump(int argc, char **argv)
 
 	prev_key = NULL;
 
-	err = btf_get_from_id(info.btf_id, &btf);
+	err = btf__get_from_id(info.btf_id, &btf);
 	if (err) {
 		p_err("failed to get btf");
 		goto exit_free;
@@ -857,7 +857,7 @@ static int do_lookup(int argc, char **argv)
 	}
 
 	/* here means bpf_map_lookup_elem() succeeded */
-	err = btf_get_from_id(info.btf_id, &btf);
+	err = btf__get_from_id(info.btf_id, &btf);
 	if (err) {
 		p_err("failed to get btf");
 		goto exit_free;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 37b1daf19da6..521a1073d1b4 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -622,7 +622,7 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
-	if (info.btf_id && btf_get_from_id(info.btf_id, &btf)) {
+	if (info.btf_id && btf__get_from_id(info.btf_id, &btf)) {
 		p_err("failed to get btf");
 		goto err_free;
 	}
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 13ddc4bd24ee..eadcf8dfd295 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -415,7 +415,7 @@ const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
 		return NULL;
 }
 
-int btf_get_from_id(__u32 id, struct btf **btf)
+int btf__get_from_id(__u32 id, struct btf **btf)
 {
 	struct bpf_btf_info btf_info = { 0 };
 	__u32 len = sizeof(btf_info);
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 701ad2b6c41f..5336b2f37293 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -73,7 +73,7 @@ LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__fd(const struct btf *btf);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
-LIBBPF_API int btf_get_from_id(__u32 id, struct btf **btf);
+LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
 
 struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
 void btf_ext__free(struct btf_ext *btf_ext);
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index b4c8725b3004..bae7308b7ec5 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -2585,7 +2585,7 @@ static int do_test_file(unsigned int test_num)
 		goto done;
 	}
 
-	err = btf_get_from_id(info.btf_id, &btf);
+	err = btf__get_from_id(info.btf_id, &btf);
 	if (CHECK(err, "cannot get btf from kernel, err: %d", err))
 		goto done;
 
-- 
cgit v1.2.3


From 16192a771d8c4d844529cbc920c75d170d16fb14 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Fri, 23 Nov 2018 16:44:33 -0800
Subject: libbpf: Add version script for DSO

More and more projects use libbpf and one day it'll likely be packaged
and distributed as DSO and that requires ABI versioning so that both
compatible and incompatible changes to ABI can be introduced in a safe
way in the future without breaking executables dynamically linked with a
previous version of the library.

Usual way to do ABI versioning is version script for the linker. Add
such a script for libbpf. All global symbols currently exported via
LIBBPF_API macro are added to the version script libbpf.map.

The version name LIBBPF_0.0.1 is constructed from the name of the
library + version specified by $(LIBBPF_VERSION) in Makefile.

Version script does not duplicate the work done by LIBBPF_API macro, it
rather complements it. The macro is used at compile time and can be used
by compiler to do optimization that can't be done at link time, it is
purely about global symbol visibility. The version script, in turn, is
used at link time and takes care of ABI versioning. Both techniques are
described in details in [1].

Whenever ABI is changed in the future, version script should be changed
appropriately.

[1] https://www.akkadia.org/drepper/dsohowto.pdf

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Makefile   |   4 +-
 tools/lib/bpf/libbpf.map | 121 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 124 insertions(+), 1 deletion(-)
 create mode 100644 tools/lib/bpf/libbpf.map

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 1b4a683a00fc..22c5ffe22825 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -145,6 +145,7 @@ include $(srctree)/tools/build/Makefile.include
 
 BPF_IN    := $(OUTPUT)libbpf-in.o
 LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
+VERSION_SCRIPT := libbpf.map
 
 CMD_TARGETS = $(LIB_FILE)
 
@@ -176,7 +177,8 @@ $(BPF_IN): force elfdep bpfdep
 	$(Q)$(MAKE) $(build)=libbpf
 
 $(OUTPUT)libbpf.so: $(BPF_IN)
-	$(QUIET_LINK)$(CC) --shared $^ -o $@
+	$(QUIET_LINK)$(CC) --shared -Wl,--version-script=$(VERSION_SCRIPT) \
+		$^ -o $@
 
 $(OUTPUT)libbpf.a: $(BPF_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
new file mode 100644
index 000000000000..4fb29f6d7a80
--- /dev/null
+++ b/tools/lib/bpf/libbpf.map
@@ -0,0 +1,121 @@
+LIBBPF_0.0.1 {
+	global:
+		bpf_btf_get_fd_by_id;
+		bpf_create_map;
+		bpf_create_map_in_map;
+		bpf_create_map_in_map_node;
+		bpf_create_map_name;
+		bpf_create_map_node;
+		bpf_create_map_xattr;
+		bpf_load_btf;
+		bpf_load_program;
+		bpf_load_program_xattr;
+		bpf_map__btf_key_type_id;
+		bpf_map__btf_value_type_id;
+		bpf_map__def;
+		bpf_map__fd;
+		bpf_map__is_offload_neutral;
+		bpf_map__name;
+		bpf_map__next;
+		bpf_map__pin;
+		bpf_map__prev;
+		bpf_map__priv;
+		bpf_map__reuse_fd;
+		bpf_map__set_ifindex;
+		bpf_map__set_inner_map_fd;
+		bpf_map__set_priv;
+		bpf_map__unpin;
+		bpf_map_delete_elem;
+		bpf_map_get_fd_by_id;
+		bpf_map_get_next_id;
+		bpf_map_get_next_key;
+		bpf_map_lookup_and_delete_elem;
+		bpf_map_lookup_elem;
+		bpf_map_update_elem;
+		bpf_obj_get;
+		bpf_obj_get_info_by_fd;
+		bpf_obj_pin;
+		bpf_object__btf_fd;
+		bpf_object__close;
+		bpf_object__find_map_by_name;
+		bpf_object__find_map_by_offset;
+		bpf_object__find_program_by_title;
+		bpf_object__kversion;
+		bpf_object__load;
+		bpf_object__name;
+		bpf_object__next;
+		bpf_object__open;
+		bpf_object__open_buffer;
+		bpf_object__open_xattr;
+		bpf_object__pin;
+		bpf_object__pin_maps;
+		bpf_object__pin_programs;
+		bpf_object__priv;
+		bpf_object__set_priv;
+		bpf_object__unload;
+		bpf_object__unpin_maps;
+		bpf_object__unpin_programs;
+		bpf_perf_event_read_simple;
+		bpf_prog_attach;
+		bpf_prog_detach;
+		bpf_prog_detach2;
+		bpf_prog_get_fd_by_id;
+		bpf_prog_get_next_id;
+		bpf_prog_load;
+		bpf_prog_load_xattr;
+		bpf_prog_query;
+		bpf_prog_test_run;
+		bpf_program__fd;
+		bpf_program__is_kprobe;
+		bpf_program__is_perf_event;
+		bpf_program__is_raw_tracepoint;
+		bpf_program__is_sched_act;
+		bpf_program__is_sched_cls;
+		bpf_program__is_socket_filter;
+		bpf_program__is_tracepoint;
+		bpf_program__is_xdp;
+		bpf_program__load;
+		bpf_program__next;
+		bpf_program__nth_fd;
+		bpf_program__pin;
+		bpf_program__pin_instance;
+		bpf_program__prev;
+		bpf_program__priv;
+		bpf_program__set_expected_attach_type;
+		bpf_program__set_ifindex;
+		bpf_program__set_kprobe;
+		bpf_program__set_perf_event;
+		bpf_program__set_prep;
+		bpf_program__set_priv;
+		bpf_program__set_raw_tracepoint;
+		bpf_program__set_sched_act;
+		bpf_program__set_sched_cls;
+		bpf_program__set_socket_filter;
+		bpf_program__set_tracepoint;
+		bpf_program__set_type;
+		bpf_program__set_xdp;
+		bpf_program__title;
+		bpf_program__unload;
+		bpf_program__unpin;
+		bpf_program__unpin_instance;
+		bpf_raw_tracepoint_open;
+		bpf_set_link_xdp_fd;
+		bpf_task_fd_query;
+		bpf_verify_program;
+		btf__fd;
+		btf__find_by_name;
+		btf__free;
+		btf__get_from_id;
+		btf__name_by_offset;
+		btf__new;
+		btf__resolve_size;
+		btf__resolve_type;
+		btf__type_by_id;
+		libbpf_attach_type_by_name;
+		libbpf_get_error;
+		libbpf_prog_type_by_name;
+		libbpf_set_print;
+		libbpf_strerror;
+	local:
+		*;
+};
-- 
cgit v1.2.3


From 306b267cb3c4c2a3d12138041fed10478804da82 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Fri, 23 Nov 2018 16:44:34 -0800
Subject: libbpf: Verify versioned symbols

Since ABI versioning info is kept separately from the code it's easy to
forget to update it while adding a new API.

Add simple verification that all global symbols exported with LIBBPF_API
are versioned in libbpf.map version script.

The idea is to check that number of global symbols in libbpf-in.o, that
is the input to the linker, matches with number of unique versioned
symbols in libbpf.so, that is the output of the linker. If these numbers
don't match, it may mean some symbol was not versioned and make will
fail.

"Unique" means that if a symbol is present in more than one version of
ABI due to ABI changes, it'll be counted once.

Another option to calculate number of global symbols in the "input"
could be to count number of LIBBPF_ABI entries in C headers but it seems
to be fragile.

Example of output when a symbol is missing in version script:

    ...
    LD       libbpf-in.o
    LINK     libbpf.a
    LINK     libbpf.so
  Warning: Num of global symbols in libbpf-in.o (115) does NOT match
  with num of versioned symbols in libbpf.so (114). Please make sure all
  LIBBPF_API symbols are versioned in libbpf.map.
  make: *** [check_abi] Error 1

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Makefile | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 22c5ffe22825..34d9c3619c96 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -147,6 +147,11 @@ BPF_IN    := $(OUTPUT)libbpf-in.o
 LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
 VERSION_SCRIPT := libbpf.map
 
+GLOBAL_SYM_COUNT = $(shell readelf -s $(BPF_IN) | \
+			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}')
+VERSIONED_SYM_COUNT = $(shell readelf -s $(OUTPUT)libbpf.so | \
+			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
+
 CMD_TARGETS = $(LIB_FILE)
 
 CXX_TEST_TARGET = $(OUTPUT)test_libbpf
@@ -159,7 +164,7 @@ TARGETS = $(CMD_TARGETS)
 
 all: fixdep all_cmd
 
-all_cmd: $(CMD_TARGETS)
+all_cmd: $(CMD_TARGETS) check
 
 $(BPF_IN): force elfdep bpfdep
 	@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
@@ -186,6 +191,18 @@ $(OUTPUT)libbpf.a: $(BPF_IN)
 $(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a
 	$(QUIET_LINK)$(CXX) $^ -lelf -o $@
 
+check: check_abi
+
+check_abi: $(OUTPUT)libbpf.so
+	@if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then	 \
+		echo "Warning: Num of global symbols in $(BPF_IN)"	 \
+		     "($(GLOBAL_SYM_COUNT)) does NOT match with num of"	 \
+		     "versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \
+		     "Please make sure all LIBBPF_API symbols are"	 \
+		     "versioned in $(VERSION_SCRIPT)." >&2;		 \
+		exit 1;							 \
+	fi
+
 define do_install
 	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
-- 
cgit v1.2.3


From 76d1b894c5155dbc44d24f6df2e0da3726d54bbd Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Fri, 23 Nov 2018 16:44:35 -0800
Subject: libbpf: Document API and ABI conventions

Document API and ABI for libbpf: naming convention, symbol visibility,
ABI versioning.

This is just a starting point. Documentation can be significantly
extended in the future to cover more topics.

ABI versioning section touches only a few basic points with a link to
more comprehensive documentation from Ulrich Drepper. This section can
be extended in the future when there is better understanding what works
well and what not so well in libbpf development process and production
usage.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/README.rst | 139 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 139 insertions(+)
 create mode 100644 tools/lib/bpf/README.rst

diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst
new file mode 100644
index 000000000000..2ced9e061c4b
--- /dev/null
+++ b/tools/lib/bpf/README.rst
@@ -0,0 +1,139 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+libbpf API naming convention
+============================
+
+libbpf API provides access to a few logically separated groups of
+functions and types. Every group has its own naming convention
+described here. It's recommended to follow these conventions whenever a
+new function or type is added to keep libbpf API clean and consistent.
+
+All types and functions provided by libbpf API should have one of the
+following prefixes: ``bpf_``, ``btf_``, ``libbpf_``.
+
+System call wrappers
+--------------------
+
+System call wrappers are simple wrappers for commands supported by
+sys_bpf system call. These wrappers should go to ``bpf.h`` header file
+and map one-on-one to corresponding commands.
+
+For example ``bpf_map_lookup_elem`` wraps ``BPF_MAP_LOOKUP_ELEM``
+command of sys_bpf, ``bpf_prog_attach`` wraps ``BPF_PROG_ATTACH``, etc.
+
+Objects
+-------
+
+Another class of types and functions provided by libbpf API is "objects"
+and functions to work with them. Objects are high-level abstractions
+such as BPF program or BPF map. They're represented by corresponding
+structures such as ``struct bpf_object``, ``struct bpf_program``,
+``struct bpf_map``, etc.
+
+Structures are forward declared and access to their fields should be
+provided via corresponding getters and setters rather than directly.
+
+These objects are associated with corresponding parts of ELF object that
+contains compiled BPF programs.
+
+For example ``struct bpf_object`` represents ELF object itself created
+from an ELF file or from a buffer, ``struct bpf_program`` represents a
+program in ELF object and ``struct bpf_map`` is a map.
+
+Functions that work with an object have names built from object name,
+double underscore and part that describes function purpose.
+
+For example ``bpf_object__open`` consists of the name of corresponding
+object, ``bpf_object``, double underscore and ``open`` that defines the
+purpose of the function to open ELF file and create ``bpf_object`` from
+it.
+
+Another example: ``bpf_program__load`` is named for corresponding
+object, ``bpf_program``, that is separated from other part of the name
+by double underscore.
+
+All objects and corresponding functions other than BTF related should go
+to ``libbpf.h``. BTF types and functions should go to ``btf.h``.
+
+Auxiliary functions
+-------------------
+
+Auxiliary functions and types that don't fit well in any of categories
+described above should have ``libbpf_`` prefix, e.g.
+``libbpf_get_error`` or ``libbpf_prog_type_by_name``.
+
+libbpf ABI
+==========
+
+libbpf can be both linked statically or used as DSO. To avoid possible
+conflicts with other libraries an application is linked with, all
+non-static libbpf symbols should have one of the prefixes mentioned in
+API documentation above. See API naming convention to choose the right
+name for a new symbol.
+
+Symbol visibility
+-----------------
+
+libbpf follow the model when all global symbols have visibility "hidden"
+by default and to make a symbol visible it has to be explicitly
+attributed with ``LIBBPF_API`` macro. For example:
+
+.. code-block:: c
+
+        LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
+
+This prevents from accidentally exporting a symbol, that is not supposed
+to be a part of ABI what, in turn, improves both libbpf developer- and
+user-experiences.
+
+ABI versionning
+---------------
+
+To make future ABI extensions possible libbpf ABI is versioned.
+Versioning is implemented by ``libbpf.map`` version script that is
+passed to linker.
+
+Version name is ``LIBBPF_`` prefix + three-component numeric version,
+starting from ``0.0.1``.
+
+Every time ABI is being changed, e.g. because a new symbol is added or
+semantic of existing symbol is changed, ABI version should be bumped.
+
+For example, if current state of ``libbpf.map`` is:
+
+.. code-block::
+        LIBBPF_0.0.1 {
+        	global:
+                        bpf_func_a;
+                        bpf_func_b;
+        	local:
+        		\*;
+        };
+
+, and a new symbol ``bpf_func_c`` is being introduced, then
+``libbpf.map`` should be changed like this:
+
+.. code-block::
+        LIBBPF_0.0.1 {
+        	global:
+                        bpf_func_a;
+                        bpf_func_b;
+        	local:
+        		\*;
+        };
+        LIBBPF_0.0.2 {
+                global:
+                        bpf_func_c;
+        } LIBBPF_0.0.1;
+
+, where new version ``LIBBPF_0.0.2`` depends on the previous
+``LIBBPF_0.0.1``.
+
+Format of version script and ways to handle ABI changes, including
+incompatible ones, described in details in [1].
+
+Links
+=====
+
+[1] https://www.akkadia.org/drepper/dsohowto.pdf
+    (Chapter 3. Maintaining APIs and ABIs).
-- 
cgit v1.2.3


From 89a9157e1253bb3384a7596cb51bf1ceeac063ed Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:18 +0800
Subject: virtio: add packed ring types and macros

Add types and macros for packed ring.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/virtio_config.h |  3 +++
 include/uapi/linux/virtio_ring.h   | 52 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+)

diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 449132c76b1c..1196e1c1d4f6 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -75,6 +75,9 @@
  */
 #define VIRTIO_F_IOMMU_PLATFORM		33
 
+/* This feature indicates support for the packed virtqueue layout. */
+#define VIRTIO_F_RING_PACKED		34
+
 /*
  * Does the device support Single Root I/O Virtualization?
  */
diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index 6d5d5faa989b..2414f8af26b3 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -44,6 +44,13 @@
 /* This means the buffer contains a list of buffer descriptors. */
 #define VRING_DESC_F_INDIRECT	4
 
+/*
+ * Mark a descriptor as available or used in packed ring.
+ * Notice: they are defined as shifts instead of shifted values.
+ */
+#define VRING_PACKED_DESC_F_AVAIL	7
+#define VRING_PACKED_DESC_F_USED	15
+
 /* The Host uses this in used->flags to advise the Guest: don't kick me when
  * you add a buffer.  It's unreliable, so it's simply an optimization.  Guest
  * will still kick if it's out of buffers. */
@@ -53,6 +60,23 @@
  * optimization.  */
 #define VRING_AVAIL_F_NO_INTERRUPT	1
 
+/* Enable events in packed ring. */
+#define VRING_PACKED_EVENT_FLAG_ENABLE	0x0
+/* Disable events in packed ring. */
+#define VRING_PACKED_EVENT_FLAG_DISABLE	0x1
+/*
+ * Enable events for a specific descriptor in packed ring.
+ * (as specified by Descriptor Ring Change Event Offset/Wrap Counter).
+ * Only valid if VIRTIO_RING_F_EVENT_IDX has been negotiated.
+ */
+#define VRING_PACKED_EVENT_FLAG_DESC	0x2
+
+/*
+ * Wrap counter bit shift in event suppression structure
+ * of packed ring.
+ */
+#define VRING_PACKED_EVENT_F_WRAP_CTR	15
+
 /* We support indirect buffer descriptors */
 #define VIRTIO_RING_F_INDIRECT_DESC	28
 
@@ -171,4 +195,32 @@ static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
 	return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
 }
 
+struct vring_packed_desc_event {
+	/* Descriptor Ring Change Event Offset/Wrap Counter. */
+	__le16 off_wrap;
+	/* Descriptor Ring Change Event Flags. */
+	__le16 flags;
+};
+
+struct vring_packed_desc {
+	/* Buffer Address. */
+	__le64 addr;
+	/* Buffer Length. */
+	__le32 len;
+	/* Buffer ID. */
+	__le16 id;
+	/* The flags depending on descriptor type. */
+	__le16 flags;
+};
+
+struct vring_packed {
+	unsigned int num;
+
+	struct vring_packed_desc *desc;
+
+	struct vring_packed_desc_event *driver;
+
+	struct vring_packed_desc_event *device;
+};
+
 #endif /* _UAPI_LINUX_VIRTIO_RING_H */
-- 
cgit v1.2.3


From 138fd25148638a93313f8ce703dd4aef2704dcea Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:19 +0800
Subject: virtio_ring: add _split suffix for split ring functions

Add _split suffix for split ring specific functions. This
is a preparation for introducing the packed ring support.
There is no functional change.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/virtio/virtio_ring.c | 251 ++++++++++++++++++++++++++-----------------
 1 file changed, 155 insertions(+), 96 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 814b395007b2..29fab2fb39cb 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -200,8 +200,8 @@ static dma_addr_t vring_map_single(const struct vring_virtqueue *vq,
 			      cpu_addr, size, direction);
 }
 
-static void vring_unmap_one(const struct vring_virtqueue *vq,
-			    struct vring_desc *desc)
+static void vring_unmap_one_split(const struct vring_virtqueue *vq,
+				  struct vring_desc *desc)
 {
 	u16 flags;
 
@@ -234,8 +234,9 @@ static int vring_mapping_error(const struct vring_virtqueue *vq,
 	return dma_mapping_error(vring_dma_dev(vq), addr);
 }
 
-static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
-					 unsigned int total_sg, gfp_t gfp)
+static struct vring_desc *alloc_indirect_split(struct virtqueue *_vq,
+					       unsigned int total_sg,
+					       gfp_t gfp)
 {
 	struct vring_desc *desc;
 	unsigned int i;
@@ -256,14 +257,14 @@ static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
 	return desc;
 }
 
-static inline int virtqueue_add(struct virtqueue *_vq,
-				struct scatterlist *sgs[],
-				unsigned int total_sg,
-				unsigned int out_sgs,
-				unsigned int in_sgs,
-				void *data,
-				void *ctx,
-				gfp_t gfp)
+static inline int virtqueue_add_split(struct virtqueue *_vq,
+				      struct scatterlist *sgs[],
+				      unsigned int total_sg,
+				      unsigned int out_sgs,
+				      unsigned int in_sgs,
+				      void *data,
+				      void *ctx,
+				      gfp_t gfp)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	struct scatterlist *sg;
@@ -302,7 +303,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 	/* If the host supports indirect descriptor tables, and we have multiple
 	 * buffers, then go indirect. FIXME: tune this threshold */
 	if (vq->indirect && total_sg > 1 && vq->vq.num_free)
-		desc = alloc_indirect(_vq, total_sg, gfp);
+		desc = alloc_indirect_split(_vq, total_sg, gfp);
 	else {
 		desc = NULL;
 		WARN_ON_ONCE(total_sg > vq->vring.num && !vq->indirect);
@@ -423,7 +424,7 @@ unmap_release:
 	for (n = 0; n < total_sg; n++) {
 		if (i == err_idx)
 			break;
-		vring_unmap_one(vq, &desc[i]);
+		vring_unmap_one_split(vq, &desc[i]);
 		i = virtio16_to_cpu(_vq->vdev, vq->vring.desc[i].next);
 	}
 
@@ -434,6 +435,19 @@ unmap_release:
 	return -EIO;
 }
 
+static inline int virtqueue_add(struct virtqueue *_vq,
+				struct scatterlist *sgs[],
+				unsigned int total_sg,
+				unsigned int out_sgs,
+				unsigned int in_sgs,
+				void *data,
+				void *ctx,
+				gfp_t gfp)
+{
+	return virtqueue_add_split(_vq, sgs, total_sg,
+				   out_sgs, in_sgs, data, ctx, gfp);
+}
+
 /**
  * virtqueue_add_sgs - expose buffers to other end
  * @vq: the struct virtqueue we're talking about.
@@ -536,18 +550,7 @@ int virtqueue_add_inbuf_ctx(struct virtqueue *vq,
 }
 EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx);
 
-/**
- * virtqueue_kick_prepare - first half of split virtqueue_kick call.
- * @vq: the struct virtqueue
- *
- * Instead of virtqueue_kick(), you can do:
- *	if (virtqueue_kick_prepare(vq))
- *		virtqueue_notify(vq);
- *
- * This is sometimes useful because the virtqueue_kick_prepare() needs
- * to be serialized, but the actual virtqueue_notify() call does not.
- */
-bool virtqueue_kick_prepare(struct virtqueue *_vq)
+static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	u16 new, old;
@@ -579,6 +582,22 @@ bool virtqueue_kick_prepare(struct virtqueue *_vq)
 	END_USE(vq);
 	return needs_kick;
 }
+
+/**
+ * virtqueue_kick_prepare - first half of split virtqueue_kick call.
+ * @vq: the struct virtqueue
+ *
+ * Instead of virtqueue_kick(), you can do:
+ *	if (virtqueue_kick_prepare(vq))
+ *		virtqueue_notify(vq);
+ *
+ * This is sometimes useful because the virtqueue_kick_prepare() needs
+ * to be serialized, but the actual virtqueue_notify() call does not.
+ */
+bool virtqueue_kick_prepare(struct virtqueue *_vq)
+{
+	return virtqueue_kick_prepare_split(_vq);
+}
 EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);
 
 /**
@@ -625,8 +644,8 @@ bool virtqueue_kick(struct virtqueue *vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_kick);
 
-static void detach_buf(struct vring_virtqueue *vq, unsigned int head,
-		       void **ctx)
+static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
+			     void **ctx)
 {
 	unsigned int i, j;
 	__virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
@@ -638,12 +657,12 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head,
 	i = head;
 
 	while (vq->vring.desc[i].flags & nextflag) {
-		vring_unmap_one(vq, &vq->vring.desc[i]);
+		vring_unmap_one_split(vq, &vq->vring.desc[i]);
 		i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next);
 		vq->vq.num_free++;
 	}
 
-	vring_unmap_one(vq, &vq->vring.desc[i]);
+	vring_unmap_one_split(vq, &vq->vring.desc[i]);
 	vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head);
 	vq->free_head = head;
 
@@ -665,7 +684,7 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head,
 		BUG_ON(len == 0 || len % sizeof(struct vring_desc));
 
 		for (j = 0; j < len / sizeof(struct vring_desc); j++)
-			vring_unmap_one(vq, &indir_desc[j]);
+			vring_unmap_one_split(vq, &indir_desc[j]);
 
 		kfree(indir_desc);
 		vq->desc_state[head].indir_desc = NULL;
@@ -674,29 +693,14 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head,
 	}
 }
 
-static inline bool more_used(const struct vring_virtqueue *vq)
+static inline bool more_used_split(const struct vring_virtqueue *vq)
 {
 	return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->vring.used->idx);
 }
 
-/**
- * virtqueue_get_buf - get the next used buffer
- * @vq: the struct virtqueue we're talking about.
- * @len: the length written into the buffer
- *
- * If the device wrote data into the buffer, @len will be set to the
- * amount written.  This means you don't need to clear the buffer
- * beforehand to ensure there's no data leakage in the case of short
- * writes.
- *
- * Caller must ensure we don't call this with other virtqueue
- * operations at the same time (except where noted).
- *
- * Returns NULL if there are no used buffers, or the "data" token
- * handed to virtqueue_add_*().
- */
-void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
-			    void **ctx)
+static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
+					 unsigned int *len,
+					 void **ctx)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	void *ret;
@@ -710,7 +714,7 @@ void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
 		return NULL;
 	}
 
-	if (!more_used(vq)) {
+	if (!more_used_split(vq)) {
 		pr_debug("No more buffers in queue\n");
 		END_USE(vq);
 		return NULL;
@@ -732,9 +736,9 @@ void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
 		return NULL;
 	}
 
-	/* detach_buf clears data, so grab it now. */
+	/* detach_buf_split clears data, so grab it now. */
 	ret = vq->desc_state[i].data;
-	detach_buf(vq, i, ctx);
+	detach_buf_split(vq, i, ctx);
 	vq->last_used_idx++;
 	/* If we expect an interrupt for the next entry, tell host
 	 * by writing event index and flush out the write before
@@ -751,6 +755,28 @@ void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
 	END_USE(vq);
 	return ret;
 }
+
+/**
+ * virtqueue_get_buf - get the next used buffer
+ * @vq: the struct virtqueue we're talking about.
+ * @len: the length written into the buffer
+ *
+ * If the device wrote data into the buffer, @len will be set to the
+ * amount written.  This means you don't need to clear the buffer
+ * beforehand to ensure there's no data leakage in the case of short
+ * writes.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ *
+ * Returns NULL if there are no used buffers, or the "data" token
+ * handed to virtqueue_add_*().
+ */
+void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
+			    void **ctx)
+{
+	return virtqueue_get_buf_ctx_split(_vq, len, ctx);
+}
 EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx);
 
 void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
@@ -758,16 +784,8 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 	return virtqueue_get_buf_ctx(_vq, len, NULL);
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_buf);
-/**
- * virtqueue_disable_cb - disable callbacks
- * @vq: the struct virtqueue we're talking about.
- *
- * Note that this is not necessarily synchronous, hence unreliable and only
- * useful as an optimization.
- *
- * Unlike other operations, this need not be serialized.
- */
-void virtqueue_disable_cb(struct virtqueue *_vq)
+
+static void virtqueue_disable_cb_split(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
@@ -776,23 +794,24 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
 		if (!vq->event)
 			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
 	}
-
 }
-EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
 
 /**
- * virtqueue_enable_cb_prepare - restart callbacks after disable_cb
+ * virtqueue_disable_cb - disable callbacks
  * @vq: the struct virtqueue we're talking about.
  *
- * This re-enables callbacks; it returns current queue state
- * in an opaque unsigned value. This value should be later tested by
- * virtqueue_poll, to detect a possible race between the driver checking for
- * more work, and enabling callbacks.
+ * Note that this is not necessarily synchronous, hence unreliable and only
+ * useful as an optimization.
  *
- * Caller must ensure we don't call this with other virtqueue
- * operations at the same time (except where noted).
+ * Unlike other operations, this need not be serialized.
  */
-unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
+void virtqueue_disable_cb(struct virtqueue *_vq)
+{
+	virtqueue_disable_cb_split(_vq);
+}
+EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
+
+static unsigned virtqueue_enable_cb_prepare_split(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	u16 last_used_idx;
@@ -813,8 +832,33 @@ unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
 	END_USE(vq);
 	return last_used_idx;
 }
+
+/**
+ * virtqueue_enable_cb_prepare - restart callbacks after disable_cb
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * This re-enables callbacks; it returns current queue state
+ * in an opaque unsigned value. This value should be later tested by
+ * virtqueue_poll, to detect a possible race between the driver checking for
+ * more work, and enabling callbacks.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ */
+unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
+{
+	return virtqueue_enable_cb_prepare_split(_vq);
+}
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);
 
+static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned last_used_idx)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev,
+			vq->vring.used->idx);
+}
+
 /**
  * virtqueue_poll - query pending used buffers
  * @vq: the struct virtqueue we're talking about.
@@ -829,7 +873,7 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	virtio_mb(vq->weak_barriers);
-	return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
+	return virtqueue_poll_split(_vq, last_used_idx);
 }
 EXPORT_SYMBOL_GPL(virtqueue_poll);
 
@@ -851,20 +895,7 @@ bool virtqueue_enable_cb(struct virtqueue *_vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
 
-/**
- * virtqueue_enable_cb_delayed - restart callbacks after disable_cb.
- * @vq: the struct virtqueue we're talking about.
- *
- * This re-enables callbacks but hints to the other side to delay
- * interrupts until most of the available buffers have been processed;
- * it returns "false" if there are many pending buffers in the queue,
- * to detect a possible race between the driver checking for more work,
- * and enabling callbacks.
- *
- * Caller must ensure we don't call this with other virtqueue
- * operations at the same time (except where noted).
- */
-bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
+static bool virtqueue_enable_cb_delayed_split(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	u16 bufs;
@@ -896,17 +927,27 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 	END_USE(vq);
 	return true;
 }
-EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
 
 /**
- * virtqueue_detach_unused_buf - detach first unused buffer
+ * virtqueue_enable_cb_delayed - restart callbacks after disable_cb.
  * @vq: the struct virtqueue we're talking about.
  *
- * Returns NULL or the "data" token handed to virtqueue_add_*().
- * This is not valid on an active queue; it is useful only for device
- * shutdown.
+ * This re-enables callbacks but hints to the other side to delay
+ * interrupts until most of the available buffers have been processed;
+ * it returns "false" if there are many pending buffers in the queue,
+ * to detect a possible race between the driver checking for more work,
+ * and enabling callbacks.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
  */
-void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
+bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
+{
+	return virtqueue_enable_cb_delayed_split(_vq);
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
+
+static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	unsigned int i;
@@ -917,9 +958,9 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 	for (i = 0; i < vq->vring.num; i++) {
 		if (!vq->desc_state[i].data)
 			continue;
-		/* detach_buf clears data, so grab it now. */
+		/* detach_buf_split clears data, so grab it now. */
 		buf = vq->desc_state[i].data;
-		detach_buf(vq, i, NULL);
+		detach_buf_split(vq, i, NULL);
 		vq->avail_idx_shadow--;
 		vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
 		END_USE(vq);
@@ -931,8 +972,26 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 	END_USE(vq);
 	return NULL;
 }
+
+/**
+ * virtqueue_detach_unused_buf - detach first unused buffer
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * Returns NULL or the "data" token handed to virtqueue_add_*().
+ * This is not valid on an active queue; it is useful only for device
+ * shutdown.
+ */
+void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
+{
+	return virtqueue_detach_unused_buf_split(_vq);
+}
 EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf);
 
+static inline bool more_used(const struct vring_virtqueue *vq)
+{
+	return more_used_split(vq);
+}
+
 irqreturn_t vring_interrupt(int irq, void *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
-- 
cgit v1.2.3


From e6f633e5beab659513297f1210b428ce6f46e69c Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:20 +0800
Subject: virtio_ring: put split ring functions together

Put the xxx_split() functions together to make the
code more readable and avoid misuse after introducing
the packed ring. There is no functional change.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/virtio/virtio_ring.c | 621 ++++++++++++++++++++++---------------------
 1 file changed, 319 insertions(+), 302 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 29fab2fb39cb..7cd40a2a0d21 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -113,6 +113,11 @@ struct vring_virtqueue {
 	struct vring_desc_state desc_state[];
 };
 
+
+/*
+ * Helpers.
+ */
+
 #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
 
 /*
@@ -200,6 +205,20 @@ static dma_addr_t vring_map_single(const struct vring_virtqueue *vq,
 			      cpu_addr, size, direction);
 }
 
+static int vring_mapping_error(const struct vring_virtqueue *vq,
+			       dma_addr_t addr)
+{
+	if (!vring_use_dma_api(vq->vq.vdev))
+		return 0;
+
+	return dma_mapping_error(vring_dma_dev(vq), addr);
+}
+
+
+/*
+ * Split ring specific functions - *_split().
+ */
+
 static void vring_unmap_one_split(const struct vring_virtqueue *vq,
 				  struct vring_desc *desc)
 {
@@ -225,15 +244,6 @@ static void vring_unmap_one_split(const struct vring_virtqueue *vq,
 	}
 }
 
-static int vring_mapping_error(const struct vring_virtqueue *vq,
-			       dma_addr_t addr)
-{
-	if (!vring_use_dma_api(vq->vq.vdev))
-		return 0;
-
-	return dma_mapping_error(vring_dma_dev(vq), addr);
-}
-
 static struct vring_desc *alloc_indirect_split(struct virtqueue *_vq,
 					       unsigned int total_sg,
 					       gfp_t gfp)
@@ -435,121 +445,6 @@ unmap_release:
 	return -EIO;
 }
 
-static inline int virtqueue_add(struct virtqueue *_vq,
-				struct scatterlist *sgs[],
-				unsigned int total_sg,
-				unsigned int out_sgs,
-				unsigned int in_sgs,
-				void *data,
-				void *ctx,
-				gfp_t gfp)
-{
-	return virtqueue_add_split(_vq, sgs, total_sg,
-				   out_sgs, in_sgs, data, ctx, gfp);
-}
-
-/**
- * virtqueue_add_sgs - expose buffers to other end
- * @vq: the struct virtqueue we're talking about.
- * @sgs: array of terminated scatterlists.
- * @out_num: the number of scatterlists readable by other side
- * @in_num: the number of scatterlists which are writable (after readable ones)
- * @data: the token identifying the buffer.
- * @gfp: how to do memory allocations (if necessary).
- *
- * Caller must ensure we don't call this with other virtqueue operations
- * at the same time (except where noted).
- *
- * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
- */
-int virtqueue_add_sgs(struct virtqueue *_vq,
-		      struct scatterlist *sgs[],
-		      unsigned int out_sgs,
-		      unsigned int in_sgs,
-		      void *data,
-		      gfp_t gfp)
-{
-	unsigned int i, total_sg = 0;
-
-	/* Count them first. */
-	for (i = 0; i < out_sgs + in_sgs; i++) {
-		struct scatterlist *sg;
-		for (sg = sgs[i]; sg; sg = sg_next(sg))
-			total_sg++;
-	}
-	return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs,
-			     data, NULL, gfp);
-}
-EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
-
-/**
- * virtqueue_add_outbuf - expose output buffers to other end
- * @vq: the struct virtqueue we're talking about.
- * @sg: scatterlist (must be well-formed and terminated!)
- * @num: the number of entries in @sg readable by other side
- * @data: the token identifying the buffer.
- * @gfp: how to do memory allocations (if necessary).
- *
- * Caller must ensure we don't call this with other virtqueue operations
- * at the same time (except where noted).
- *
- * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
- */
-int virtqueue_add_outbuf(struct virtqueue *vq,
-			 struct scatterlist *sg, unsigned int num,
-			 void *data,
-			 gfp_t gfp)
-{
-	return virtqueue_add(vq, &sg, num, 1, 0, data, NULL, gfp);
-}
-EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
-
-/**
- * virtqueue_add_inbuf - expose input buffers to other end
- * @vq: the struct virtqueue we're talking about.
- * @sg: scatterlist (must be well-formed and terminated!)
- * @num: the number of entries in @sg writable by other side
- * @data: the token identifying the buffer.
- * @gfp: how to do memory allocations (if necessary).
- *
- * Caller must ensure we don't call this with other virtqueue operations
- * at the same time (except where noted).
- *
- * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
- */
-int virtqueue_add_inbuf(struct virtqueue *vq,
-			struct scatterlist *sg, unsigned int num,
-			void *data,
-			gfp_t gfp)
-{
-	return virtqueue_add(vq, &sg, num, 0, 1, data, NULL, gfp);
-}
-EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);
-
-/**
- * virtqueue_add_inbuf_ctx - expose input buffers to other end
- * @vq: the struct virtqueue we're talking about.
- * @sg: scatterlist (must be well-formed and terminated!)
- * @num: the number of entries in @sg writable by other side
- * @data: the token identifying the buffer.
- * @ctx: extra context for the token
- * @gfp: how to do memory allocations (if necessary).
- *
- * Caller must ensure we don't call this with other virtqueue operations
- * at the same time (except where noted).
- *
- * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
- */
-int virtqueue_add_inbuf_ctx(struct virtqueue *vq,
-			struct scatterlist *sg, unsigned int num,
-			void *data,
-			void *ctx,
-			gfp_t gfp)
-{
-	return virtqueue_add(vq, &sg, num, 0, 1, data, ctx, gfp);
-}
-EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx);
-
 static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -583,67 +478,6 @@ static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
 	return needs_kick;
 }
 
-/**
- * virtqueue_kick_prepare - first half of split virtqueue_kick call.
- * @vq: the struct virtqueue
- *
- * Instead of virtqueue_kick(), you can do:
- *	if (virtqueue_kick_prepare(vq))
- *		virtqueue_notify(vq);
- *
- * This is sometimes useful because the virtqueue_kick_prepare() needs
- * to be serialized, but the actual virtqueue_notify() call does not.
- */
-bool virtqueue_kick_prepare(struct virtqueue *_vq)
-{
-	return virtqueue_kick_prepare_split(_vq);
-}
-EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);
-
-/**
- * virtqueue_notify - second half of split virtqueue_kick call.
- * @vq: the struct virtqueue
- *
- * This does not need to be serialized.
- *
- * Returns false if host notify failed or queue is broken, otherwise true.
- */
-bool virtqueue_notify(struct virtqueue *_vq)
-{
-	struct vring_virtqueue *vq = to_vvq(_vq);
-
-	if (unlikely(vq->broken))
-		return false;
-
-	/* Prod other side to tell it about changes. */
-	if (!vq->notify(_vq)) {
-		vq->broken = true;
-		return false;
-	}
-	return true;
-}
-EXPORT_SYMBOL_GPL(virtqueue_notify);
-
-/**
- * virtqueue_kick - update after add_buf
- * @vq: the struct virtqueue
- *
- * After one or more virtqueue_add_* calls, invoke this to kick
- * the other side.
- *
- * Caller must ensure we don't call this with other virtqueue
- * operations at the same time (except where noted).
- *
- * Returns false if kick failed, otherwise true.
- */
-bool virtqueue_kick(struct virtqueue *vq)
-{
-	if (virtqueue_kick_prepare(vq))
-		return virtqueue_notify(vq);
-	return true;
-}
-EXPORT_SYMBOL_GPL(virtqueue_kick);
-
 static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 			     void **ctx)
 {
@@ -756,35 +590,6 @@ static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
 	return ret;
 }
 
-/**
- * virtqueue_get_buf - get the next used buffer
- * @vq: the struct virtqueue we're talking about.
- * @len: the length written into the buffer
- *
- * If the device wrote data into the buffer, @len will be set to the
- * amount written.  This means you don't need to clear the buffer
- * beforehand to ensure there's no data leakage in the case of short
- * writes.
- *
- * Caller must ensure we don't call this with other virtqueue
- * operations at the same time (except where noted).
- *
- * Returns NULL if there are no used buffers, or the "data" token
- * handed to virtqueue_add_*().
- */
-void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
-			    void **ctx)
-{
-	return virtqueue_get_buf_ctx_split(_vq, len, ctx);
-}
-EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx);
-
-void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
-{
-	return virtqueue_get_buf_ctx(_vq, len, NULL);
-}
-EXPORT_SYMBOL_GPL(virtqueue_get_buf);
-
 static void virtqueue_disable_cb_split(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -796,21 +601,6 @@ static void virtqueue_disable_cb_split(struct virtqueue *_vq)
 	}
 }
 
-/**
- * virtqueue_disable_cb - disable callbacks
- * @vq: the struct virtqueue we're talking about.
- *
- * Note that this is not necessarily synchronous, hence unreliable and only
- * useful as an optimization.
- *
- * Unlike other operations, this need not be serialized.
- */
-void virtqueue_disable_cb(struct virtqueue *_vq)
-{
-	virtqueue_disable_cb_split(_vq);
-}
-EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
-
 static unsigned virtqueue_enable_cb_prepare_split(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -833,24 +623,6 @@ static unsigned virtqueue_enable_cb_prepare_split(struct virtqueue *_vq)
 	return last_used_idx;
 }
 
-/**
- * virtqueue_enable_cb_prepare - restart callbacks after disable_cb
- * @vq: the struct virtqueue we're talking about.
- *
- * This re-enables callbacks; it returns current queue state
- * in an opaque unsigned value. This value should be later tested by
- * virtqueue_poll, to detect a possible race between the driver checking for
- * more work, and enabling callbacks.
- *
- * Caller must ensure we don't call this with other virtqueue
- * operations at the same time (except where noted).
- */
-unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
-{
-	return virtqueue_enable_cb_prepare_split(_vq);
-}
-EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);
-
 static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned last_used_idx)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -859,42 +631,6 @@ static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned last_used_idx)
 			vq->vring.used->idx);
 }
 
-/**
- * virtqueue_poll - query pending used buffers
- * @vq: the struct virtqueue we're talking about.
- * @last_used_idx: virtqueue state (from call to virtqueue_enable_cb_prepare).
- *
- * Returns "true" if there are pending used buffers in the queue.
- *
- * This does not need to be serialized.
- */
-bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
-{
-	struct vring_virtqueue *vq = to_vvq(_vq);
-
-	virtio_mb(vq->weak_barriers);
-	return virtqueue_poll_split(_vq, last_used_idx);
-}
-EXPORT_SYMBOL_GPL(virtqueue_poll);
-
-/**
- * virtqueue_enable_cb - restart callbacks after disable_cb.
- * @vq: the struct virtqueue we're talking about.
- *
- * This re-enables callbacks; it returns "false" if there are pending
- * buffers in the queue, to detect a possible race between the driver
- * checking for more work, and enabling callbacks.
- *
- * Caller must ensure we don't call this with other virtqueue
- * operations at the same time (except where noted).
- */
-bool virtqueue_enable_cb(struct virtqueue *_vq)
-{
-	unsigned last_used_idx = virtqueue_enable_cb_prepare(_vq);
-	return !virtqueue_poll(_vq, last_used_idx);
-}
-EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
-
 static bool virtqueue_enable_cb_delayed_split(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -928,25 +664,6 @@ static bool virtqueue_enable_cb_delayed_split(struct virtqueue *_vq)
 	return true;
 }
 
-/**
- * virtqueue_enable_cb_delayed - restart callbacks after disable_cb.
- * @vq: the struct virtqueue we're talking about.
- *
- * This re-enables callbacks but hints to the other side to delay
- * interrupts until most of the available buffers have been processed;
- * it returns "false" if there are many pending buffers in the queue,
- * to detect a possible race between the driver checking for more work,
- * and enabling callbacks.
- *
- * Caller must ensure we don't call this with other virtqueue
- * operations at the same time (except where noted).
- */
-bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
-{
-	return virtqueue_enable_cb_delayed_split(_vq);
-}
-EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
-
 static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -973,6 +690,306 @@ static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
 	return NULL;
 }
 
+
+/*
+ * Generic functions and exported symbols.
+ */
+
+static inline int virtqueue_add(struct virtqueue *_vq,
+				struct scatterlist *sgs[],
+				unsigned int total_sg,
+				unsigned int out_sgs,
+				unsigned int in_sgs,
+				void *data,
+				void *ctx,
+				gfp_t gfp)
+{
+	return virtqueue_add_split(_vq, sgs, total_sg,
+				   out_sgs, in_sgs, data, ctx, gfp);
+}
+
+/**
+ * virtqueue_add_sgs - expose buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sgs: array of terminated scatterlists.
+ * @out_num: the number of scatterlists readable by other side
+ * @in_num: the number of scatterlists which are writable (after readable ones)
+ * @data: the token identifying the buffer.
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
+ */
+int virtqueue_add_sgs(struct virtqueue *_vq,
+		      struct scatterlist *sgs[],
+		      unsigned int out_sgs,
+		      unsigned int in_sgs,
+		      void *data,
+		      gfp_t gfp)
+{
+	unsigned int i, total_sg = 0;
+
+	/* Count them first. */
+	for (i = 0; i < out_sgs + in_sgs; i++) {
+		struct scatterlist *sg;
+
+		for (sg = sgs[i]; sg; sg = sg_next(sg))
+			total_sg++;
+	}
+	return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs,
+			     data, NULL, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
+
+/**
+ * virtqueue_add_outbuf - expose output buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sg: scatterlist (must be well-formed and terminated!)
+ * @num: the number of entries in @sg readable by other side
+ * @data: the token identifying the buffer.
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
+ */
+int virtqueue_add_outbuf(struct virtqueue *vq,
+			 struct scatterlist *sg, unsigned int num,
+			 void *data,
+			 gfp_t gfp)
+{
+	return virtqueue_add(vq, &sg, num, 1, 0, data, NULL, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
+
+/**
+ * virtqueue_add_inbuf - expose input buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sg: scatterlist (must be well-formed and terminated!)
+ * @num: the number of entries in @sg writable by other side
+ * @data: the token identifying the buffer.
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
+ */
+int virtqueue_add_inbuf(struct virtqueue *vq,
+			struct scatterlist *sg, unsigned int num,
+			void *data,
+			gfp_t gfp)
+{
+	return virtqueue_add(vq, &sg, num, 0, 1, data, NULL, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);
+
+/**
+ * virtqueue_add_inbuf_ctx - expose input buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sg: scatterlist (must be well-formed and terminated!)
+ * @num: the number of entries in @sg writable by other side
+ * @data: the token identifying the buffer.
+ * @ctx: extra context for the token
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
+ */
+int virtqueue_add_inbuf_ctx(struct virtqueue *vq,
+			struct scatterlist *sg, unsigned int num,
+			void *data,
+			void *ctx,
+			gfp_t gfp)
+{
+	return virtqueue_add(vq, &sg, num, 0, 1, data, ctx, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx);
+
+/**
+ * virtqueue_kick_prepare - first half of split virtqueue_kick call.
+ * @vq: the struct virtqueue
+ *
+ * Instead of virtqueue_kick(), you can do:
+ *	if (virtqueue_kick_prepare(vq))
+ *		virtqueue_notify(vq);
+ *
+ * This is sometimes useful because the virtqueue_kick_prepare() needs
+ * to be serialized, but the actual virtqueue_notify() call does not.
+ */
+bool virtqueue_kick_prepare(struct virtqueue *_vq)
+{
+	return virtqueue_kick_prepare_split(_vq);
+}
+EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);
+
+/**
+ * virtqueue_notify - second half of split virtqueue_kick call.
+ * @vq: the struct virtqueue
+ *
+ * This does not need to be serialized.
+ *
+ * Returns false if host notify failed or queue is broken, otherwise true.
+ */
+bool virtqueue_notify(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (unlikely(vq->broken))
+		return false;
+
+	/* Prod other side to tell it about changes. */
+	if (!vq->notify(_vq)) {
+		vq->broken = true;
+		return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL_GPL(virtqueue_notify);
+
+/**
+ * virtqueue_kick - update after add_buf
+ * @vq: the struct virtqueue
+ *
+ * After one or more virtqueue_add_* calls, invoke this to kick
+ * the other side.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ *
+ * Returns false if kick failed, otherwise true.
+ */
+bool virtqueue_kick(struct virtqueue *vq)
+{
+	if (virtqueue_kick_prepare(vq))
+		return virtqueue_notify(vq);
+	return true;
+}
+EXPORT_SYMBOL_GPL(virtqueue_kick);
+
+/**
+ * virtqueue_get_buf - get the next used buffer
+ * @vq: the struct virtqueue we're talking about.
+ * @len: the length written into the buffer
+ *
+ * If the device wrote data into the buffer, @len will be set to the
+ * amount written.  This means you don't need to clear the buffer
+ * beforehand to ensure there's no data leakage in the case of short
+ * writes.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ *
+ * Returns NULL if there are no used buffers, or the "data" token
+ * handed to virtqueue_add_*().
+ */
+void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
+			    void **ctx)
+{
+	return virtqueue_get_buf_ctx_split(_vq, len, ctx);
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx);
+
+void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
+{
+	return virtqueue_get_buf_ctx(_vq, len, NULL);
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_buf);
+
+/**
+ * virtqueue_disable_cb - disable callbacks
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * Note that this is not necessarily synchronous, hence unreliable and only
+ * useful as an optimization.
+ *
+ * Unlike other operations, this need not be serialized.
+ */
+void virtqueue_disable_cb(struct virtqueue *_vq)
+{
+	virtqueue_disable_cb_split(_vq);
+}
+EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
+
+/**
+ * virtqueue_enable_cb_prepare - restart callbacks after disable_cb
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * This re-enables callbacks; it returns current queue state
+ * in an opaque unsigned value. This value should be later tested by
+ * virtqueue_poll, to detect a possible race between the driver checking for
+ * more work, and enabling callbacks.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ */
+unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
+{
+	return virtqueue_enable_cb_prepare_split(_vq);
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);
+
+/**
+ * virtqueue_poll - query pending used buffers
+ * @vq: the struct virtqueue we're talking about.
+ * @last_used_idx: virtqueue state (from call to virtqueue_enable_cb_prepare).
+ *
+ * Returns "true" if there are pending used buffers in the queue.
+ *
+ * This does not need to be serialized.
+ */
+bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	virtio_mb(vq->weak_barriers);
+	return virtqueue_poll_split(_vq, last_used_idx);
+}
+EXPORT_SYMBOL_GPL(virtqueue_poll);
+
+/**
+ * virtqueue_enable_cb - restart callbacks after disable_cb.
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * This re-enables callbacks; it returns "false" if there are pending
+ * buffers in the queue, to detect a possible race between the driver
+ * checking for more work, and enabling callbacks.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ */
+bool virtqueue_enable_cb(struct virtqueue *_vq)
+{
+	unsigned last_used_idx = virtqueue_enable_cb_prepare(_vq);
+
+	return !virtqueue_poll(_vq, last_used_idx);
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
+
+/**
+ * virtqueue_enable_cb_delayed - restart callbacks after disable_cb.
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * This re-enables callbacks but hints to the other side to delay
+ * interrupts until most of the available buffers have been processed;
+ * it returns "false" if there are many pending buffers in the queue,
+ * to detect a possible race between the driver checking for more work,
+ * and enabling callbacks.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ */
+bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
+{
+	return virtqueue_enable_cb_delayed_split(_vq);
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
+
 /**
  * virtqueue_detach_unused_buf - detach first unused buffer
  * @vq: the struct virtqueue we're talking about.
-- 
cgit v1.2.3


From e593bf9751566e0ba5a055a976a4abd54101d572 Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:21 +0800
Subject: virtio_ring: put split ring fields in a sub struct

Put the split ring specific fields in a sub-struct named
as "split" to avoid misuse after introducing packed ring.
There is no functional change.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/virtio/virtio_ring.c | 156 +++++++++++++++++++++++++------------------
 1 file changed, 91 insertions(+), 65 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 7cd40a2a0d21..0b97e5c79654 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -63,9 +63,6 @@ struct vring_desc_state {
 struct vring_virtqueue {
 	struct virtqueue vq;
 
-	/* Actual memory layout for this queue */
-	struct vring vring;
-
 	/* Can we use weak barriers? */
 	bool weak_barriers;
 
@@ -86,11 +83,16 @@ struct vring_virtqueue {
 	/* Last used index we've seen. */
 	u16 last_used_idx;
 
-	/* Last written value to avail->flags */
-	u16 avail_flags_shadow;
+	struct {
+		/* Actual memory layout for this queue */
+		struct vring vring;
 
-	/* Last written value to avail->idx in guest byte order */
-	u16 avail_idx_shadow;
+		/* Last written value to avail->flags */
+		u16 avail_flags_shadow;
+
+		/* Last written value to avail->idx in guest byte order */
+		u16 avail_idx_shadow;
+	} split;
 
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	bool (*notify)(struct virtqueue *vq);
@@ -316,7 +318,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 		desc = alloc_indirect_split(_vq, total_sg, gfp);
 	else {
 		desc = NULL;
-		WARN_ON_ONCE(total_sg > vq->vring.num && !vq->indirect);
+		WARN_ON_ONCE(total_sg > vq->split.vring.num && !vq->indirect);
 	}
 
 	if (desc) {
@@ -327,7 +329,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 		descs_used = 1;
 	} else {
 		indirect = false;
-		desc = vq->vring.desc;
+		desc = vq->split.vring.desc;
 		i = head;
 		descs_used = total_sg;
 	}
@@ -383,10 +385,13 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 		if (vring_mapping_error(vq, addr))
 			goto unmap_release;
 
-		vq->vring.desc[head].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT);
-		vq->vring.desc[head].addr = cpu_to_virtio64(_vq->vdev, addr);
+		vq->split.vring.desc[head].flags = cpu_to_virtio16(_vq->vdev,
+				VRING_DESC_F_INDIRECT);
+		vq->split.vring.desc[head].addr = cpu_to_virtio64(_vq->vdev,
+				addr);
 
-		vq->vring.desc[head].len = cpu_to_virtio32(_vq->vdev, total_sg * sizeof(struct vring_desc));
+		vq->split.vring.desc[head].len = cpu_to_virtio32(_vq->vdev,
+				total_sg * sizeof(struct vring_desc));
 	}
 
 	/* We're using some buffers from the free list. */
@@ -394,7 +399,8 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 
 	/* Update free pointer */
 	if (indirect)
-		vq->free_head = virtio16_to_cpu(_vq->vdev, vq->vring.desc[head].next);
+		vq->free_head = virtio16_to_cpu(_vq->vdev,
+					vq->split.vring.desc[head].next);
 	else
 		vq->free_head = i;
 
@@ -407,14 +413,15 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 
 	/* Put entry in available array (but don't update avail->idx until they
 	 * do sync). */
-	avail = vq->avail_idx_shadow & (vq->vring.num - 1);
-	vq->vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head);
+	avail = vq->split.avail_idx_shadow & (vq->split.vring.num - 1);
+	vq->split.vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head);
 
 	/* Descriptors and available array need to be set before we expose the
 	 * new available array entries. */
 	virtio_wmb(vq->weak_barriers);
-	vq->avail_idx_shadow++;
-	vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
+	vq->split.avail_idx_shadow++;
+	vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev,
+						vq->split.avail_idx_shadow);
 	vq->num_added++;
 
 	pr_debug("Added buffer head %i to %p\n", head, vq);
@@ -435,7 +442,7 @@ unmap_release:
 		if (i == err_idx)
 			break;
 		vring_unmap_one_split(vq, &desc[i]);
-		i = virtio16_to_cpu(_vq->vdev, vq->vring.desc[i].next);
+		i = virtio16_to_cpu(_vq->vdev, vq->split.vring.desc[i].next);
 	}
 
 	if (indirect)
@@ -456,8 +463,8 @@ static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
 	 * event. */
 	virtio_mb(vq->weak_barriers);
 
-	old = vq->avail_idx_shadow - vq->num_added;
-	new = vq->avail_idx_shadow;
+	old = vq->split.avail_idx_shadow - vq->num_added;
+	new = vq->split.avail_idx_shadow;
 	vq->num_added = 0;
 
 #ifdef DEBUG
@@ -469,10 +476,13 @@ static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
 #endif
 
 	if (vq->event) {
-		needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev, vring_avail_event(&vq->vring)),
+		needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev,
+					vring_avail_event(&vq->split.vring)),
 					      new, old);
 	} else {
-		needs_kick = !(vq->vring.used->flags & cpu_to_virtio16(_vq->vdev, VRING_USED_F_NO_NOTIFY));
+		needs_kick = !(vq->split.vring.used->flags &
+					cpu_to_virtio16(_vq->vdev,
+						VRING_USED_F_NO_NOTIFY));
 	}
 	END_USE(vq);
 	return needs_kick;
@@ -490,14 +500,15 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 	/* Put back on free list: unmap first-level descriptors and find end */
 	i = head;
 
-	while (vq->vring.desc[i].flags & nextflag) {
-		vring_unmap_one_split(vq, &vq->vring.desc[i]);
-		i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next);
+	while (vq->split.vring.desc[i].flags & nextflag) {
+		vring_unmap_one_split(vq, &vq->split.vring.desc[i]);
+		i = virtio16_to_cpu(vq->vq.vdev, vq->split.vring.desc[i].next);
 		vq->vq.num_free++;
 	}
 
-	vring_unmap_one_split(vq, &vq->vring.desc[i]);
-	vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head);
+	vring_unmap_one_split(vq, &vq->split.vring.desc[i]);
+	vq->split.vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev,
+						vq->free_head);
 	vq->free_head = head;
 
 	/* Plus final descriptor */
@@ -511,9 +522,10 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 		if (!indir_desc)
 			return;
 
-		len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);
+		len = virtio32_to_cpu(vq->vq.vdev,
+				vq->split.vring.desc[head].len);
 
-		BUG_ON(!(vq->vring.desc[head].flags &
+		BUG_ON(!(vq->split.vring.desc[head].flags &
 			 cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
 		BUG_ON(len == 0 || len % sizeof(struct vring_desc));
 
@@ -529,7 +541,8 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 
 static inline bool more_used_split(const struct vring_virtqueue *vq)
 {
-	return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->vring.used->idx);
+	return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev,
+			vq->split.vring.used->idx);
 }
 
 static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
@@ -557,11 +570,13 @@ static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
 	/* Only get used array entries after they have been exposed by host. */
 	virtio_rmb(vq->weak_barriers);
 
-	last_used = (vq->last_used_idx & (vq->vring.num - 1));
-	i = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].id);
-	*len = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].len);
+	last_used = (vq->last_used_idx & (vq->split.vring.num - 1));
+	i = virtio32_to_cpu(_vq->vdev,
+			vq->split.vring.used->ring[last_used].id);
+	*len = virtio32_to_cpu(_vq->vdev,
+			vq->split.vring.used->ring[last_used].len);
 
-	if (unlikely(i >= vq->vring.num)) {
+	if (unlikely(i >= vq->split.vring.num)) {
 		BAD_RING(vq, "id %u out of range\n", i);
 		return NULL;
 	}
@@ -577,9 +592,9 @@ static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
 	/* If we expect an interrupt for the next entry, tell host
 	 * by writing event index and flush out the write before
 	 * the read in the next get_buf call. */
-	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
+	if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
 		virtio_store_mb(vq->weak_barriers,
-				&vring_used_event(&vq->vring),
+				&vring_used_event(&vq->split.vring),
 				cpu_to_virtio16(_vq->vdev, vq->last_used_idx));
 
 #ifdef DEBUG
@@ -594,10 +609,12 @@ static void virtqueue_disable_cb_split(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
-	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
-		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+	if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
+		vq->split.avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
 		if (!vq->event)
-			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+			vq->split.vring.avail->flags =
+				cpu_to_virtio16(_vq->vdev,
+						vq->split.avail_flags_shadow);
 	}
 }
 
@@ -613,12 +630,15 @@ static unsigned virtqueue_enable_cb_prepare_split(struct virtqueue *_vq)
 	/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
 	 * either clear the flags bit or point the event index at the next
 	 * entry. Always do both to keep code simple. */
-	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
-		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+	if (vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+		vq->split.avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
 		if (!vq->event)
-			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+			vq->split.vring.avail->flags =
+				cpu_to_virtio16(_vq->vdev,
+						vq->split.avail_flags_shadow);
 	}
-	vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
+	vring_used_event(&vq->split.vring) = cpu_to_virtio16(_vq->vdev,
+			last_used_idx = vq->last_used_idx);
 	END_USE(vq);
 	return last_used_idx;
 }
@@ -628,7 +648,7 @@ static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned last_used_idx)
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev,
-			vq->vring.used->idx);
+			vq->split.vring.used->idx);
 }
 
 static bool virtqueue_enable_cb_delayed_split(struct virtqueue *_vq)
@@ -643,19 +663,22 @@ static bool virtqueue_enable_cb_delayed_split(struct virtqueue *_vq)
 	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
 	 * either clear the flags bit or point the event index at the next
 	 * entry. Always update the event index to keep code simple. */
-	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
-		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+	if (vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+		vq->split.avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
 		if (!vq->event)
-			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+			vq->split.vring.avail->flags =
+				cpu_to_virtio16(_vq->vdev,
+						vq->split.avail_flags_shadow);
 	}
 	/* TODO: tune this threshold */
-	bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
+	bufs = (u16)(vq->split.avail_idx_shadow - vq->last_used_idx) * 3 / 4;
 
 	virtio_store_mb(vq->weak_barriers,
-			&vring_used_event(&vq->vring),
+			&vring_used_event(&vq->split.vring),
 			cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs));
 
-	if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
+	if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->split.vring.used->idx)
+					- vq->last_used_idx) > bufs)) {
 		END_USE(vq);
 		return false;
 	}
@@ -672,19 +695,20 @@ static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
 
 	START_USE(vq);
 
-	for (i = 0; i < vq->vring.num; i++) {
+	for (i = 0; i < vq->split.vring.num; i++) {
 		if (!vq->desc_state[i].data)
 			continue;
 		/* detach_buf_split clears data, so grab it now. */
 		buf = vq->desc_state[i].data;
 		detach_buf_split(vq, i, NULL);
-		vq->avail_idx_shadow--;
-		vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
+		vq->split.avail_idx_shadow--;
+		vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev,
+				vq->split.avail_idx_shadow);
 		END_USE(vq);
 		return buf;
 	}
 	/* That should have freed everything. */
-	BUG_ON(vq->vq.num_free != vq->vring.num);
+	BUG_ON(vq->vq.num_free != vq->split.vring.num);
 
 	END_USE(vq);
 	return NULL;
@@ -1046,7 +1070,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	if (!vq)
 		return NULL;
 
-	vq->vring = vring;
 	vq->vq.callback = callback;
 	vq->vq.vdev = vdev;
 	vq->vq.name = name;
@@ -1059,8 +1082,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	vq->weak_barriers = weak_barriers;
 	vq->broken = false;
 	vq->last_used_idx = 0;
-	vq->avail_flags_shadow = 0;
-	vq->avail_idx_shadow = 0;
 	vq->num_added = 0;
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
@@ -1072,17 +1093,22 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 		!context;
 	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
+	vq->split.vring = vring;
+	vq->split.avail_flags_shadow = 0;
+	vq->split.avail_idx_shadow = 0;
+
 	/* No callback?  Tell other side not to bother us. */
 	if (!callback) {
-		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+		vq->split.avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
 		if (!vq->event)
-			vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+			vq->split.vring.avail->flags = cpu_to_virtio16(vdev,
+					vq->split.avail_flags_shadow);
 	}
 
 	/* Put everything in free lists. */
 	vq->free_head = 0;
 	for (i = 0; i < vring.num-1; i++)
-		vq->vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
+		vq->split.vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
 	memset(vq->desc_state, 0, vring.num * sizeof(struct vring_desc_state));
 
 	return &vq->vq;
@@ -1218,7 +1244,7 @@ void vring_del_virtqueue(struct virtqueue *_vq)
 
 	if (vq->we_own_ring) {
 		vring_free_queue(vq->vq.vdev, vq->queue_size_in_bytes,
-				 vq->vring.desc, vq->queue_dma_addr);
+				 vq->split.vring.desc, vq->queue_dma_addr);
 	}
 	list_del(&_vq->list);
 	kfree(vq);
@@ -1260,7 +1286,7 @@ unsigned int virtqueue_get_vring_size(struct virtqueue *_vq)
 
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
-	return vq->vring.num;
+	return vq->split.vring.num;
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_vring_size);
 
@@ -1304,7 +1330,7 @@ dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq)
 	BUG_ON(!vq->we_own_ring);
 
 	return vq->queue_dma_addr +
-		((char *)vq->vring.avail - (char *)vq->vring.desc);
+		((char *)vq->split.vring.avail - (char *)vq->split.vring.desc);
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_avail_addr);
 
@@ -1315,13 +1341,13 @@ dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq)
 	BUG_ON(!vq->we_own_ring);
 
 	return vq->queue_dma_addr +
-		((char *)vq->vring.used - (char *)vq->vring.desc);
+		((char *)vq->split.vring.used - (char *)vq->split.vring.desc);
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_used_addr);
 
 const struct vring *virtqueue_get_vring(struct virtqueue *vq)
 {
-	return &to_vvq(vq)->vring;
+	return &to_vvq(vq)->split.vring;
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_vring);
 
-- 
cgit v1.2.3


From 4d6a105eb534b8f1a5ef9215deb1932cd8abacc2 Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:22 +0800
Subject: virtio_ring: introduce debug helpers

Introduce debug helpers for last_add_time update, check and
invalid. They will be used by packed ring too.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/virtio/virtio_ring.c | 49 ++++++++++++++++++++++++--------------------
 1 file changed, 27 insertions(+), 22 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 0b97e5c79654..10d407910aa2 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -44,6 +44,26 @@
 	} while (0)
 #define END_USE(_vq) \
 	do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0)
+#define LAST_ADD_TIME_UPDATE(_vq)				\
+	do {							\
+		ktime_t now = ktime_get();			\
+								\
+		/* No kick or get, with .1 second between?  Warn. */ \
+		if ((_vq)->last_add_time_valid)			\
+			WARN_ON(ktime_to_ms(ktime_sub(now,	\
+				(_vq)->last_add_time)) > 100);	\
+		(_vq)->last_add_time = now;			\
+		(_vq)->last_add_time_valid = true;		\
+	} while (0)
+#define LAST_ADD_TIME_CHECK(_vq)				\
+	do {							\
+		if ((_vq)->last_add_time_valid) {		\
+			WARN_ON(ktime_to_ms(ktime_sub(ktime_get(), \
+				      (_vq)->last_add_time)) > 100); \
+		}						\
+	} while (0)
+#define LAST_ADD_TIME_INVALID(_vq)				\
+	((_vq)->last_add_time_valid = false)
 #else
 #define BAD_RING(_vq, fmt, args...)				\
 	do {							\
@@ -53,6 +73,9 @@
 	} while (0)
 #define START_USE(vq)
 #define END_USE(vq)
+#define LAST_ADD_TIME_UPDATE(vq)
+#define LAST_ADD_TIME_CHECK(vq)
+#define LAST_ADD_TIME_INVALID(vq)
 #endif
 
 struct vring_desc_state {
@@ -295,18 +318,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 		return -EIO;
 	}
 
-#ifdef DEBUG
-	{
-		ktime_t now = ktime_get();
-
-		/* No kick or get, with .1 second between?  Warn. */
-		if (vq->last_add_time_valid)
-			WARN_ON(ktime_to_ms(ktime_sub(now, vq->last_add_time))
-					    > 100);
-		vq->last_add_time = now;
-		vq->last_add_time_valid = true;
-	}
-#endif
+	LAST_ADD_TIME_UPDATE(vq);
 
 	BUG_ON(total_sg == 0);
 
@@ -467,13 +479,8 @@ static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
 	new = vq->split.avail_idx_shadow;
 	vq->num_added = 0;
 
-#ifdef DEBUG
-	if (vq->last_add_time_valid) {
-		WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
-					      vq->last_add_time)) > 100);
-	}
-	vq->last_add_time_valid = false;
-#endif
+	LAST_ADD_TIME_CHECK(vq);
+	LAST_ADD_TIME_INVALID(vq);
 
 	if (vq->event) {
 		needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev,
@@ -597,9 +604,7 @@ static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
 				&vring_used_event(&vq->split.vring),
 				cpu_to_virtio16(_vq->vdev, vq->last_used_idx));
 
-#ifdef DEBUG
-	vq->last_add_time_valid = false;
-#endif
+	LAST_ADD_TIME_INVALID(vq);
 
 	END_USE(vq);
 	return ret;
-- 
cgit v1.2.3


From 2f18c2d153fb6fc889665688f266c780353002ec Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:23 +0800
Subject: virtio_ring: introduce helper for indirect feature

Introduce a helper to check whether we will use indirect
feature. It will be used by packed ring too.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/virtio/virtio_ring.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 10d407910aa2..d1076f28c7e9 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -145,6 +145,18 @@ struct vring_virtqueue {
 
 #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
 
+static inline bool virtqueue_use_indirect(struct virtqueue *_vq,
+					  unsigned int total_sg)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	/*
+	 * If the host supports indirect descriptor tables, and we have multiple
+	 * buffers, then go indirect. FIXME: tune this threshold
+	 */
+	return (vq->indirect && total_sg > 1 && vq->vq.num_free);
+}
+
 /*
  * Modern virtio devices have feature bits to specify whether they need a
  * quirk and bypass the IOMMU. If not there, just use the DMA API.
@@ -324,9 +336,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 
 	head = vq->free_head;
 
-	/* If the host supports indirect descriptor tables, and we have multiple
-	 * buffers, then go indirect. FIXME: tune this threshold */
-	if (vq->indirect && total_sg > 1 && vq->vq.num_free)
+	if (virtqueue_use_indirect(_vq, total_sg))
 		desc = alloc_indirect_split(_vq, total_sg, gfp);
 	else {
 		desc = NULL;
-- 
cgit v1.2.3


From cbeedb72b97ad826e31e68e0717b763e2db0806d Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:24 +0800
Subject: virtio_ring: allocate desc state for split ring separately

Put the split ring's desc state into the .split sub-structure,
and allocate desc state for split ring separately, this makes
the code more readable and more consistent with what we will
do for packed ring.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/virtio/virtio_ring.c | 45 ++++++++++++++++++++++++++------------------
 1 file changed, 27 insertions(+), 18 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index d1076f28c7e9..acd851f3105c 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -78,7 +78,7 @@
 #define LAST_ADD_TIME_INVALID(vq)
 #endif
 
-struct vring_desc_state {
+struct vring_desc_state_split {
 	void *data;			/* Data for callback. */
 	struct vring_desc *indir_desc;	/* Indirect descriptor, if any. */
 };
@@ -115,6 +115,9 @@ struct vring_virtqueue {
 
 		/* Last written value to avail->idx in guest byte order */
 		u16 avail_idx_shadow;
+
+		/* Per-descriptor state. */
+		struct vring_desc_state_split *desc_state;
 	} split;
 
 	/* How to notify other side. FIXME: commonalize hcalls! */
@@ -133,9 +136,6 @@ struct vring_virtqueue {
 	bool last_add_time_valid;
 	ktime_t last_add_time;
 #endif
-
-	/* Per-descriptor state. */
-	struct vring_desc_state desc_state[];
 };
 
 
@@ -427,11 +427,11 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 		vq->free_head = i;
 
 	/* Store token and indirect buffer state. */
-	vq->desc_state[head].data = data;
+	vq->split.desc_state[head].data = data;
 	if (indirect)
-		vq->desc_state[head].indir_desc = desc;
+		vq->split.desc_state[head].indir_desc = desc;
 	else
-		vq->desc_state[head].indir_desc = ctx;
+		vq->split.desc_state[head].indir_desc = ctx;
 
 	/* Put entry in available array (but don't update avail->idx until they
 	 * do sync). */
@@ -512,7 +512,7 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 	__virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
 
 	/* Clear data ptr. */
-	vq->desc_state[head].data = NULL;
+	vq->split.desc_state[head].data = NULL;
 
 	/* Put back on free list: unmap first-level descriptors and find end */
 	i = head;
@@ -532,7 +532,8 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 	vq->vq.num_free++;
 
 	if (vq->indirect) {
-		struct vring_desc *indir_desc = vq->desc_state[head].indir_desc;
+		struct vring_desc *indir_desc =
+				vq->split.desc_state[head].indir_desc;
 		u32 len;
 
 		/* Free the indirect table, if any, now that it's unmapped. */
@@ -550,9 +551,9 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 			vring_unmap_one_split(vq, &indir_desc[j]);
 
 		kfree(indir_desc);
-		vq->desc_state[head].indir_desc = NULL;
+		vq->split.desc_state[head].indir_desc = NULL;
 	} else if (ctx) {
-		*ctx = vq->desc_state[head].indir_desc;
+		*ctx = vq->split.desc_state[head].indir_desc;
 	}
 }
 
@@ -597,13 +598,13 @@ static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
 		BAD_RING(vq, "id %u out of range\n", i);
 		return NULL;
 	}
-	if (unlikely(!vq->desc_state[i].data)) {
+	if (unlikely(!vq->split.desc_state[i].data)) {
 		BAD_RING(vq, "id %u is not a head!\n", i);
 		return NULL;
 	}
 
 	/* detach_buf_split clears data, so grab it now. */
-	ret = vq->desc_state[i].data;
+	ret = vq->split.desc_state[i].data;
 	detach_buf_split(vq, i, ctx);
 	vq->last_used_idx++;
 	/* If we expect an interrupt for the next entry, tell host
@@ -711,10 +712,10 @@ static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
 	START_USE(vq);
 
 	for (i = 0; i < vq->split.vring.num; i++) {
-		if (!vq->desc_state[i].data)
+		if (!vq->split.desc_state[i].data)
 			continue;
 		/* detach_buf_split clears data, so grab it now. */
-		buf = vq->desc_state[i].data;
+		buf = vq->split.desc_state[i].data;
 		detach_buf_split(vq, i, NULL);
 		vq->split.avail_idx_shadow--;
 		vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev,
@@ -1080,8 +1081,7 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	unsigned int i;
 	struct vring_virtqueue *vq;
 
-	vq = kmalloc(sizeof(*vq) + vring.num * sizeof(struct vring_desc_state),
-		     GFP_KERNEL);
+	vq = kmalloc(sizeof(*vq), GFP_KERNEL);
 	if (!vq)
 		return NULL;
 
@@ -1120,11 +1120,19 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 					vq->split.avail_flags_shadow);
 	}
 
+	vq->split.desc_state = kmalloc_array(vring.num,
+			sizeof(struct vring_desc_state_split), GFP_KERNEL);
+	if (!vq->split.desc_state) {
+		kfree(vq);
+		return NULL;
+	}
+
 	/* Put everything in free lists. */
 	vq->free_head = 0;
 	for (i = 0; i < vring.num-1; i++)
 		vq->split.vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
-	memset(vq->desc_state, 0, vring.num * sizeof(struct vring_desc_state));
+	memset(vq->split.desc_state, 0, vring.num *
+			sizeof(struct vring_desc_state_split));
 
 	return &vq->vq;
 }
@@ -1260,6 +1268,7 @@ void vring_del_virtqueue(struct virtqueue *_vq)
 	if (vq->we_own_ring) {
 		vring_free_queue(vq->vq.vdev, vq->queue_size_in_bytes,
 				 vq->split.vring.desc, vq->queue_dma_addr);
+		kfree(vq->split.desc_state);
 	}
 	list_del(&_vq->list);
 	kfree(vq);
-- 
cgit v1.2.3


From d79dca75c79680f52a27a7ee1b6ae75066f36b3e Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:25 +0800
Subject: virtio_ring: extract split ring handling from ring creation

Introduce a specific function to create the split ring.
And also move the DMA allocation and size information to
the .split sub-structure.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/virtio/virtio_ring.c | 220 ++++++++++++++++++++++++-------------------
 1 file changed, 121 insertions(+), 99 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index acd851f3105c..d00a87909a7e 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -118,6 +118,10 @@ struct vring_virtqueue {
 
 		/* Per-descriptor state. */
 		struct vring_desc_state_split *desc_state;
+
+		/* DMA, allocation, and size information */
+		size_t queue_size_in_bytes;
+		dma_addr_t queue_dma_addr;
 	} split;
 
 	/* How to notify other side. FIXME: commonalize hcalls! */
@@ -125,8 +129,6 @@ struct vring_virtqueue {
 
 	/* DMA, allocation, and size information */
 	bool we_own_ring;
-	size_t queue_size_in_bytes;
-	dma_addr_t queue_dma_addr;
 
 #ifdef DEBUG
 	/* They're supposed to lock for us. */
@@ -203,6 +205,48 @@ static bool vring_use_dma_api(struct virtio_device *vdev)
 	return false;
 }
 
+static void *vring_alloc_queue(struct virtio_device *vdev, size_t size,
+			      dma_addr_t *dma_handle, gfp_t flag)
+{
+	if (vring_use_dma_api(vdev)) {
+		return dma_alloc_coherent(vdev->dev.parent, size,
+					  dma_handle, flag);
+	} else {
+		void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
+
+		if (queue) {
+			phys_addr_t phys_addr = virt_to_phys(queue);
+			*dma_handle = (dma_addr_t)phys_addr;
+
+			/*
+			 * Sanity check: make sure we dind't truncate
+			 * the address.  The only arches I can find that
+			 * have 64-bit phys_addr_t but 32-bit dma_addr_t
+			 * are certain non-highmem MIPS and x86
+			 * configurations, but these configurations
+			 * should never allocate physical pages above 32
+			 * bits, so this is fine.  Just in case, throw a
+			 * warning and abort if we end up with an
+			 * unrepresentable address.
+			 */
+			if (WARN_ON_ONCE(*dma_handle != phys_addr)) {
+				free_pages_exact(queue, PAGE_ALIGN(size));
+				return NULL;
+			}
+		}
+		return queue;
+	}
+}
+
+static void vring_free_queue(struct virtio_device *vdev, size_t size,
+			     void *queue, dma_addr_t dma_handle)
+{
+	if (vring_use_dma_api(vdev))
+		dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
+	else
+		free_pages_exact(queue, PAGE_ALIGN(size));
+}
+
 /*
  * The DMA ops on various arches are rather gnarly right now, and
  * making all of the arch DMA ops work on the vring device itself
@@ -730,6 +774,68 @@ static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
 	return NULL;
 }
 
+static struct virtqueue *vring_create_virtqueue_split(
+	unsigned int index,
+	unsigned int num,
+	unsigned int vring_align,
+	struct virtio_device *vdev,
+	bool weak_barriers,
+	bool may_reduce_num,
+	bool context,
+	bool (*notify)(struct virtqueue *),
+	void (*callback)(struct virtqueue *),
+	const char *name)
+{
+	struct virtqueue *vq;
+	void *queue = NULL;
+	dma_addr_t dma_addr;
+	size_t queue_size_in_bytes;
+	struct vring vring;
+
+	/* We assume num is a power of 2. */
+	if (num & (num - 1)) {
+		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
+		return NULL;
+	}
+
+	/* TODO: allocate each queue chunk individually */
+	for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) {
+		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
+					  &dma_addr,
+					  GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+		if (queue)
+			break;
+	}
+
+	if (!num)
+		return NULL;
+
+	if (!queue) {
+		/* Try to get a single page. You are my only hope! */
+		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
+					  &dma_addr, GFP_KERNEL|__GFP_ZERO);
+	}
+	if (!queue)
+		return NULL;
+
+	queue_size_in_bytes = vring_size(num, vring_align);
+	vring_init(&vring, num, queue, vring_align);
+
+	vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
+				   notify, callback, name);
+	if (!vq) {
+		vring_free_queue(vdev, queue_size_in_bytes, queue,
+				 dma_addr);
+		return NULL;
+	}
+
+	to_vvq(vq)->split.queue_dma_addr = dma_addr;
+	to_vvq(vq)->split.queue_size_in_bytes = queue_size_in_bytes;
+	to_vvq(vq)->we_own_ring = true;
+
+	return vq;
+}
+
 
 /*
  * Generic functions and exported symbols.
@@ -1091,8 +1197,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	vq->vq.num_free = vring.num;
 	vq->vq.index = index;
 	vq->we_own_ring = false;
-	vq->queue_dma_addr = 0;
-	vq->queue_size_in_bytes = 0;
 	vq->notify = notify;
 	vq->weak_barriers = weak_barriers;
 	vq->broken = false;
@@ -1108,6 +1212,9 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 		!context;
 	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
+	vq->split.queue_dma_addr = 0;
+	vq->split.queue_size_in_bytes = 0;
+
 	vq->split.vring = vring;
 	vq->split.avail_flags_shadow = 0;
 	vq->split.avail_idx_shadow = 0;
@@ -1138,48 +1245,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 }
 EXPORT_SYMBOL_GPL(__vring_new_virtqueue);
 
-static void *vring_alloc_queue(struct virtio_device *vdev, size_t size,
-			      dma_addr_t *dma_handle, gfp_t flag)
-{
-	if (vring_use_dma_api(vdev)) {
-		return dma_alloc_coherent(vdev->dev.parent, size,
-					  dma_handle, flag);
-	} else {
-		void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
-		if (queue) {
-			phys_addr_t phys_addr = virt_to_phys(queue);
-			*dma_handle = (dma_addr_t)phys_addr;
-
-			/*
-			 * Sanity check: make sure we dind't truncate
-			 * the address.  The only arches I can find that
-			 * have 64-bit phys_addr_t but 32-bit dma_addr_t
-			 * are certain non-highmem MIPS and x86
-			 * configurations, but these configurations
-			 * should never allocate physical pages above 32
-			 * bits, so this is fine.  Just in case, throw a
-			 * warning and abort if we end up with an
-			 * unrepresentable address.
-			 */
-			if (WARN_ON_ONCE(*dma_handle != phys_addr)) {
-				free_pages_exact(queue, PAGE_ALIGN(size));
-				return NULL;
-			}
-		}
-		return queue;
-	}
-}
-
-static void vring_free_queue(struct virtio_device *vdev, size_t size,
-			     void *queue, dma_addr_t dma_handle)
-{
-	if (vring_use_dma_api(vdev)) {
-		dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
-	} else {
-		free_pages_exact(queue, PAGE_ALIGN(size));
-	}
-}
-
 struct virtqueue *vring_create_virtqueue(
 	unsigned int index,
 	unsigned int num,
@@ -1192,54 +1257,9 @@ struct virtqueue *vring_create_virtqueue(
 	void (*callback)(struct virtqueue *),
 	const char *name)
 {
-	struct virtqueue *vq;
-	void *queue = NULL;
-	dma_addr_t dma_addr;
-	size_t queue_size_in_bytes;
-	struct vring vring;
-
-	/* We assume num is a power of 2. */
-	if (num & (num - 1)) {
-		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
-		return NULL;
-	}
-
-	/* TODO: allocate each queue chunk individually */
-	for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) {
-		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
-					  &dma_addr,
-					  GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
-		if (queue)
-			break;
-	}
-
-	if (!num)
-		return NULL;
-
-	if (!queue) {
-		/* Try to get a single page. You are my only hope! */
-		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
-					  &dma_addr, GFP_KERNEL|__GFP_ZERO);
-	}
-	if (!queue)
-		return NULL;
-
-	queue_size_in_bytes = vring_size(num, vring_align);
-	vring_init(&vring, num, queue, vring_align);
-
-	vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
-				   notify, callback, name);
-	if (!vq) {
-		vring_free_queue(vdev, queue_size_in_bytes, queue,
-				 dma_addr);
-		return NULL;
-	}
-
-	to_vvq(vq)->queue_dma_addr = dma_addr;
-	to_vvq(vq)->queue_size_in_bytes = queue_size_in_bytes;
-	to_vvq(vq)->we_own_ring = true;
-
-	return vq;
+	return vring_create_virtqueue_split(index, num, vring_align,
+			vdev, weak_barriers, may_reduce_num,
+			context, notify, callback, name);
 }
 EXPORT_SYMBOL_GPL(vring_create_virtqueue);
 
@@ -1266,8 +1286,10 @@ void vring_del_virtqueue(struct virtqueue *_vq)
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	if (vq->we_own_ring) {
-		vring_free_queue(vq->vq.vdev, vq->queue_size_in_bytes,
-				 vq->split.vring.desc, vq->queue_dma_addr);
+		vring_free_queue(vq->vq.vdev,
+				 vq->split.queue_size_in_bytes,
+				 vq->split.vring.desc,
+				 vq->split.queue_dma_addr);
 		kfree(vq->split.desc_state);
 	}
 	list_del(&_vq->list);
@@ -1343,7 +1365,7 @@ dma_addr_t virtqueue_get_desc_addr(struct virtqueue *_vq)
 
 	BUG_ON(!vq->we_own_ring);
 
-	return vq->queue_dma_addr;
+	return vq->split.queue_dma_addr;
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_desc_addr);
 
@@ -1353,7 +1375,7 @@ dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq)
 
 	BUG_ON(!vq->we_own_ring);
 
-	return vq->queue_dma_addr +
+	return vq->split.queue_dma_addr +
 		((char *)vq->split.vring.avail - (char *)vq->split.vring.desc);
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_avail_addr);
@@ -1364,7 +1386,7 @@ dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq)
 
 	BUG_ON(!vq->we_own_ring);
 
-	return vq->queue_dma_addr +
+	return vq->split.queue_dma_addr +
 		((char *)vq->split.vring.used - (char *)vq->split.vring.desc);
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_used_addr);
-- 
cgit v1.2.3


From fb3fba6b162aaa42aeba6e9034f3e92716c2a749 Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:26 +0800
Subject: virtio_ring: cache whether we will use DMA API

Cache whether we will use DMA API, instead of doing the
check every time. We are going to check whether DMA API
is used more often in packed ring.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/virtio/virtio_ring.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index d00a87909a7e..aafe1969b45e 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -86,6 +86,9 @@ struct vring_desc_state_split {
 struct vring_virtqueue {
 	struct virtqueue vq;
 
+	/* Is DMA API used? */
+	bool use_dma_api;
+
 	/* Can we use weak barriers? */
 	bool weak_barriers;
 
@@ -262,7 +265,7 @@ static dma_addr_t vring_map_one_sg(const struct vring_virtqueue *vq,
 				   struct scatterlist *sg,
 				   enum dma_data_direction direction)
 {
-	if (!vring_use_dma_api(vq->vq.vdev))
+	if (!vq->use_dma_api)
 		return (dma_addr_t)sg_phys(sg);
 
 	/*
@@ -279,7 +282,7 @@ static dma_addr_t vring_map_single(const struct vring_virtqueue *vq,
 				   void *cpu_addr, size_t size,
 				   enum dma_data_direction direction)
 {
-	if (!vring_use_dma_api(vq->vq.vdev))
+	if (!vq->use_dma_api)
 		return (dma_addr_t)virt_to_phys(cpu_addr);
 
 	return dma_map_single(vring_dma_dev(vq),
@@ -289,7 +292,7 @@ static dma_addr_t vring_map_single(const struct vring_virtqueue *vq,
 static int vring_mapping_error(const struct vring_virtqueue *vq,
 			       dma_addr_t addr)
 {
-	if (!vring_use_dma_api(vq->vq.vdev))
+	if (!vq->use_dma_api)
 		return 0;
 
 	return dma_mapping_error(vring_dma_dev(vq), addr);
@@ -305,7 +308,7 @@ static void vring_unmap_one_split(const struct vring_virtqueue *vq,
 {
 	u16 flags;
 
-	if (!vring_use_dma_api(vq->vq.vdev))
+	if (!vq->use_dma_api)
 		return;
 
 	flags = virtio16_to_cpu(vq->vq.vdev, desc->flags);
@@ -1202,6 +1205,7 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	vq->broken = false;
 	vq->last_used_idx = 0;
 	vq->num_added = 0;
+	vq->use_dma_api = vring_use_dma_api(vdev);
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;
-- 
cgit v1.2.3


From 1ce9e6055fa0a9043405c5604cf19169ec5379ff Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:27 +0800
Subject: virtio_ring: introduce packed ring support

Introduce the packed ring support. Packed ring can only be
created by vring_create_virtqueue() and each chunk of packed
ring will be allocated individually. Packed ring can not be
created on preallocated memory by vring_new_virtqueue() or
the likes currently.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/virtio/virtio_ring.c | 900 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 870 insertions(+), 30 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index aafe1969b45e..b63eee2034e7 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -83,9 +83,26 @@ struct vring_desc_state_split {
 	struct vring_desc *indir_desc;	/* Indirect descriptor, if any. */
 };
 
+struct vring_desc_state_packed {
+	void *data;			/* Data for callback. */
+	struct vring_packed_desc *indir_desc; /* Indirect descriptor, if any. */
+	u16 num;			/* Descriptor list length. */
+	u16 next;			/* The next desc state in a list. */
+	u16 last;			/* The last desc state in a list. */
+};
+
+struct vring_desc_extra_packed {
+	dma_addr_t addr;		/* Buffer DMA addr. */
+	u32 len;			/* Buffer length. */
+	u16 flags;			/* Descriptor flags. */
+};
+
 struct vring_virtqueue {
 	struct virtqueue vq;
 
+	/* Is this a packed ring? */
+	bool packed_ring;
+
 	/* Is DMA API used? */
 	bool use_dma_api;
 
@@ -109,23 +126,64 @@ struct vring_virtqueue {
 	/* Last used index we've seen. */
 	u16 last_used_idx;
 
-	struct {
-		/* Actual memory layout for this queue */
-		struct vring vring;
+	union {
+		/* Available for split ring */
+		struct {
+			/* Actual memory layout for this queue. */
+			struct vring vring;
+
+			/* Last written value to avail->flags */
+			u16 avail_flags_shadow;
 
-		/* Last written value to avail->flags */
-		u16 avail_flags_shadow;
+			/*
+			 * Last written value to avail->idx in
+			 * guest byte order.
+			 */
+			u16 avail_idx_shadow;
+
+			/* Per-descriptor state. */
+			struct vring_desc_state_split *desc_state;
+
+			/* DMA address and size information */
+			dma_addr_t queue_dma_addr;
+			size_t queue_size_in_bytes;
+		} split;
 
-		/* Last written value to avail->idx in guest byte order */
-		u16 avail_idx_shadow;
+		/* Available for packed ring */
+		struct {
+			/* Actual memory layout for this queue. */
+			struct vring_packed vring;
 
-		/* Per-descriptor state. */
-		struct vring_desc_state_split *desc_state;
+			/* Driver ring wrap counter. */
+			bool avail_wrap_counter;
 
-		/* DMA, allocation, and size information */
-		size_t queue_size_in_bytes;
-		dma_addr_t queue_dma_addr;
-	} split;
+			/* Device ring wrap counter. */
+			bool used_wrap_counter;
+
+			/* Avail used flags. */
+			u16 avail_used_flags;
+
+			/* Index of the next avail descriptor. */
+			u16 next_avail_idx;
+
+			/*
+			 * Last written value to driver->flags in
+			 * guest byte order.
+			 */
+			u16 event_flags_shadow;
+
+			/* Per-descriptor state. */
+			struct vring_desc_state_packed *desc_state;
+			struct vring_desc_extra_packed *desc_extra;
+
+			/* DMA address and size information */
+			dma_addr_t ring_dma_addr;
+			dma_addr_t driver_event_dma_addr;
+			dma_addr_t device_event_dma_addr;
+			size_t ring_size_in_bytes;
+			size_t event_size_in_bytes;
+		} packed;
+	};
 
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	bool (*notify)(struct virtqueue *vq);
@@ -840,6 +898,717 @@ static struct virtqueue *vring_create_virtqueue_split(
 }
 
 
+/*
+ * Packed ring specific functions - *_packed().
+ */
+
+static void vring_unmap_state_packed(const struct vring_virtqueue *vq,
+				     struct vring_desc_extra_packed *state)
+{
+	u16 flags;
+
+	if (!vq->use_dma_api)
+		return;
+
+	flags = state->flags;
+
+	if (flags & VRING_DESC_F_INDIRECT) {
+		dma_unmap_single(vring_dma_dev(vq),
+				 state->addr, state->len,
+				 (flags & VRING_DESC_F_WRITE) ?
+				 DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	} else {
+		dma_unmap_page(vring_dma_dev(vq),
+			       state->addr, state->len,
+			       (flags & VRING_DESC_F_WRITE) ?
+			       DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+}
+
+static void vring_unmap_desc_packed(const struct vring_virtqueue *vq,
+				   struct vring_packed_desc *desc)
+{
+	u16 flags;
+
+	if (!vq->use_dma_api)
+		return;
+
+	flags = le16_to_cpu(desc->flags);
+
+	if (flags & VRING_DESC_F_INDIRECT) {
+		dma_unmap_single(vring_dma_dev(vq),
+				 le64_to_cpu(desc->addr),
+				 le32_to_cpu(desc->len),
+				 (flags & VRING_DESC_F_WRITE) ?
+				 DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	} else {
+		dma_unmap_page(vring_dma_dev(vq),
+			       le64_to_cpu(desc->addr),
+			       le32_to_cpu(desc->len),
+			       (flags & VRING_DESC_F_WRITE) ?
+			       DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+}
+
+static struct vring_packed_desc *alloc_indirect_packed(unsigned int total_sg,
+						       gfp_t gfp)
+{
+	struct vring_packed_desc *desc;
+
+	/*
+	 * We require lowmem mappings for the descriptors because
+	 * otherwise virt_to_phys will give us bogus addresses in the
+	 * virtqueue.
+	 */
+	gfp &= ~__GFP_HIGHMEM;
+
+	desc = kmalloc_array(total_sg, sizeof(struct vring_packed_desc), gfp);
+
+	return desc;
+}
+
+static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
+				       struct scatterlist *sgs[],
+				       unsigned int total_sg,
+				       unsigned int out_sgs,
+				       unsigned int in_sgs,
+				       void *data,
+				       gfp_t gfp)
+{
+	struct vring_packed_desc *desc;
+	struct scatterlist *sg;
+	unsigned int i, n, err_idx;
+	u16 head, id;
+	dma_addr_t addr;
+
+	head = vq->packed.next_avail_idx;
+	desc = alloc_indirect_packed(total_sg, gfp);
+
+	if (unlikely(vq->vq.num_free < 1)) {
+		pr_debug("Can't add buf len 1 - avail = 0\n");
+		END_USE(vq);
+		return -ENOSPC;
+	}
+
+	i = 0;
+	id = vq->free_head;
+	BUG_ON(id == vq->packed.vring.num);
+
+	for (n = 0; n < out_sgs + in_sgs; n++) {
+		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+			addr = vring_map_one_sg(vq, sg, n < out_sgs ?
+					DMA_TO_DEVICE : DMA_FROM_DEVICE);
+			if (vring_mapping_error(vq, addr))
+				goto unmap_release;
+
+			desc[i].flags = cpu_to_le16(n < out_sgs ?
+						0 : VRING_DESC_F_WRITE);
+			desc[i].addr = cpu_to_le64(addr);
+			desc[i].len = cpu_to_le32(sg->length);
+			i++;
+		}
+	}
+
+	/* Now that the indirect table is filled in, map it. */
+	addr = vring_map_single(vq, desc,
+			total_sg * sizeof(struct vring_packed_desc),
+			DMA_TO_DEVICE);
+	if (vring_mapping_error(vq, addr))
+		goto unmap_release;
+
+	vq->packed.vring.desc[head].addr = cpu_to_le64(addr);
+	vq->packed.vring.desc[head].len = cpu_to_le32(total_sg *
+				sizeof(struct vring_packed_desc));
+	vq->packed.vring.desc[head].id = cpu_to_le16(id);
+
+	if (vq->use_dma_api) {
+		vq->packed.desc_extra[id].addr = addr;
+		vq->packed.desc_extra[id].len = total_sg *
+				sizeof(struct vring_packed_desc);
+		vq->packed.desc_extra[id].flags = VRING_DESC_F_INDIRECT |
+						  vq->packed.avail_used_flags;
+	}
+
+	/*
+	 * A driver MUST NOT make the first descriptor in the list
+	 * available before all subsequent descriptors comprising
+	 * the list are made available.
+	 */
+	virtio_wmb(vq->weak_barriers);
+	vq->packed.vring.desc[head].flags = cpu_to_le16(VRING_DESC_F_INDIRECT |
+						vq->packed.avail_used_flags);
+
+	/* We're using some buffers from the free list. */
+	vq->vq.num_free -= 1;
+
+	/* Update free pointer */
+	n = head + 1;
+	if (n >= vq->packed.vring.num) {
+		n = 0;
+		vq->packed.avail_wrap_counter ^= 1;
+		vq->packed.avail_used_flags ^=
+				1 << VRING_PACKED_DESC_F_AVAIL |
+				1 << VRING_PACKED_DESC_F_USED;
+	}
+	vq->packed.next_avail_idx = n;
+	vq->free_head = vq->packed.desc_state[id].next;
+
+	/* Store token and indirect buffer state. */
+	vq->packed.desc_state[id].num = 1;
+	vq->packed.desc_state[id].data = data;
+	vq->packed.desc_state[id].indir_desc = desc;
+	vq->packed.desc_state[id].last = id;
+
+	vq->num_added += 1;
+
+	pr_debug("Added buffer head %i to %p\n", head, vq);
+	END_USE(vq);
+
+	return 0;
+
+unmap_release:
+	err_idx = i;
+
+	for (i = 0; i < err_idx; i++)
+		vring_unmap_desc_packed(vq, &desc[i]);
+
+	kfree(desc);
+
+	END_USE(vq);
+	return -EIO;
+}
+
+static inline int virtqueue_add_packed(struct virtqueue *_vq,
+				       struct scatterlist *sgs[],
+				       unsigned int total_sg,
+				       unsigned int out_sgs,
+				       unsigned int in_sgs,
+				       void *data,
+				       void *ctx,
+				       gfp_t gfp)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	struct vring_packed_desc *desc;
+	struct scatterlist *sg;
+	unsigned int i, n, c, descs_used, err_idx;
+	__le16 uninitialized_var(head_flags), flags;
+	u16 head, id, uninitialized_var(prev), curr, avail_used_flags;
+
+	START_USE(vq);
+
+	BUG_ON(data == NULL);
+	BUG_ON(ctx && vq->indirect);
+
+	if (unlikely(vq->broken)) {
+		END_USE(vq);
+		return -EIO;
+	}
+
+	LAST_ADD_TIME_UPDATE(vq);
+
+	BUG_ON(total_sg == 0);
+
+	if (virtqueue_use_indirect(_vq, total_sg))
+		return virtqueue_add_indirect_packed(vq, sgs, total_sg,
+				out_sgs, in_sgs, data, gfp);
+
+	head = vq->packed.next_avail_idx;
+	avail_used_flags = vq->packed.avail_used_flags;
+
+	WARN_ON_ONCE(total_sg > vq->packed.vring.num && !vq->indirect);
+
+	desc = vq->packed.vring.desc;
+	i = head;
+	descs_used = total_sg;
+
+	if (unlikely(vq->vq.num_free < descs_used)) {
+		pr_debug("Can't add buf len %i - avail = %i\n",
+			 descs_used, vq->vq.num_free);
+		END_USE(vq);
+		return -ENOSPC;
+	}
+
+	id = vq->free_head;
+	BUG_ON(id == vq->packed.vring.num);
+
+	curr = id;
+	c = 0;
+	for (n = 0; n < out_sgs + in_sgs; n++) {
+		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+			dma_addr_t addr = vring_map_one_sg(vq, sg, n < out_sgs ?
+					DMA_TO_DEVICE : DMA_FROM_DEVICE);
+			if (vring_mapping_error(vq, addr))
+				goto unmap_release;
+
+			flags = cpu_to_le16(vq->packed.avail_used_flags |
+				    (++c == total_sg ? 0 : VRING_DESC_F_NEXT) |
+				    (n < out_sgs ? 0 : VRING_DESC_F_WRITE));
+			if (i == head)
+				head_flags = flags;
+			else
+				desc[i].flags = flags;
+
+			desc[i].addr = cpu_to_le64(addr);
+			desc[i].len = cpu_to_le32(sg->length);
+			desc[i].id = cpu_to_le16(id);
+
+			if (unlikely(vq->use_dma_api)) {
+				vq->packed.desc_extra[curr].addr = addr;
+				vq->packed.desc_extra[curr].len = sg->length;
+				vq->packed.desc_extra[curr].flags =
+					le16_to_cpu(flags);
+			}
+			prev = curr;
+			curr = vq->packed.desc_state[curr].next;
+
+			if ((unlikely(++i >= vq->packed.vring.num))) {
+				i = 0;
+				vq->packed.avail_used_flags ^=
+					1 << VRING_PACKED_DESC_F_AVAIL |
+					1 << VRING_PACKED_DESC_F_USED;
+			}
+		}
+	}
+
+	if (i < head)
+		vq->packed.avail_wrap_counter ^= 1;
+
+	/* We're using some buffers from the free list. */
+	vq->vq.num_free -= descs_used;
+
+	/* Update free pointer */
+	vq->packed.next_avail_idx = i;
+	vq->free_head = curr;
+
+	/* Store token. */
+	vq->packed.desc_state[id].num = descs_used;
+	vq->packed.desc_state[id].data = data;
+	vq->packed.desc_state[id].indir_desc = ctx;
+	vq->packed.desc_state[id].last = prev;
+
+	/*
+	 * A driver MUST NOT make the first descriptor in the list
+	 * available before all subsequent descriptors comprising
+	 * the list are made available.
+	 */
+	virtio_wmb(vq->weak_barriers);
+	vq->packed.vring.desc[head].flags = head_flags;
+	vq->num_added += descs_used;
+
+	pr_debug("Added buffer head %i to %p\n", head, vq);
+	END_USE(vq);
+
+	return 0;
+
+unmap_release:
+	err_idx = i;
+	i = head;
+
+	vq->packed.avail_used_flags = avail_used_flags;
+
+	for (n = 0; n < total_sg; n++) {
+		if (i == err_idx)
+			break;
+		vring_unmap_desc_packed(vq, &desc[i]);
+		i++;
+		if (i >= vq->packed.vring.num)
+			i = 0;
+	}
+
+	END_USE(vq);
+	return -EIO;
+}
+
+static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 flags;
+	bool needs_kick;
+	union {
+		struct {
+			__le16 off_wrap;
+			__le16 flags;
+		};
+		u32 u32;
+	} snapshot;
+
+	START_USE(vq);
+
+	/*
+	 * We need to expose the new flags value before checking notification
+	 * suppressions.
+	 */
+	virtio_mb(vq->weak_barriers);
+
+	vq->num_added = 0;
+
+	snapshot.u32 = *(u32 *)vq->packed.vring.device;
+	flags = le16_to_cpu(snapshot.flags);
+
+	LAST_ADD_TIME_CHECK(vq);
+	LAST_ADD_TIME_INVALID(vq);
+
+	needs_kick = (flags != VRING_PACKED_EVENT_FLAG_DISABLE);
+	END_USE(vq);
+	return needs_kick;
+}
+
+static void detach_buf_packed(struct vring_virtqueue *vq,
+			      unsigned int id, void **ctx)
+{
+	struct vring_desc_state_packed *state = NULL;
+	struct vring_packed_desc *desc;
+	unsigned int i, curr;
+
+	state = &vq->packed.desc_state[id];
+
+	/* Clear data ptr. */
+	state->data = NULL;
+
+	vq->packed.desc_state[state->last].next = vq->free_head;
+	vq->free_head = id;
+	vq->vq.num_free += state->num;
+
+	if (unlikely(vq->use_dma_api)) {
+		curr = id;
+		for (i = 0; i < state->num; i++) {
+			vring_unmap_state_packed(vq,
+				&vq->packed.desc_extra[curr]);
+			curr = vq->packed.desc_state[curr].next;
+		}
+	}
+
+	if (vq->indirect) {
+		u32 len;
+
+		/* Free the indirect table, if any, now that it's unmapped. */
+		desc = state->indir_desc;
+		if (!desc)
+			return;
+
+		if (vq->use_dma_api) {
+			len = vq->packed.desc_extra[id].len;
+			for (i = 0; i < len / sizeof(struct vring_packed_desc);
+					i++)
+				vring_unmap_desc_packed(vq, &desc[i]);
+		}
+		kfree(desc);
+		state->indir_desc = NULL;
+	} else if (ctx) {
+		*ctx = state->indir_desc;
+	}
+}
+
+static inline bool is_used_desc_packed(const struct vring_virtqueue *vq,
+				       u16 idx, bool used_wrap_counter)
+{
+	bool avail, used;
+	u16 flags;
+
+	flags = le16_to_cpu(vq->packed.vring.desc[idx].flags);
+	avail = !!(flags & (1 << VRING_PACKED_DESC_F_AVAIL));
+	used = !!(flags & (1 << VRING_PACKED_DESC_F_USED));
+
+	return avail == used && used == used_wrap_counter;
+}
+
+static inline bool more_used_packed(const struct vring_virtqueue *vq)
+{
+	return is_used_desc_packed(vq, vq->last_used_idx,
+			vq->packed.used_wrap_counter);
+}
+
+static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
+					  unsigned int *len,
+					  void **ctx)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 last_used, id;
+	void *ret;
+
+	START_USE(vq);
+
+	if (unlikely(vq->broken)) {
+		END_USE(vq);
+		return NULL;
+	}
+
+	if (!more_used_packed(vq)) {
+		pr_debug("No more buffers in queue\n");
+		END_USE(vq);
+		return NULL;
+	}
+
+	/* Only get used elements after they have been exposed by host. */
+	virtio_rmb(vq->weak_barriers);
+
+	last_used = vq->last_used_idx;
+	id = le16_to_cpu(vq->packed.vring.desc[last_used].id);
+	*len = le32_to_cpu(vq->packed.vring.desc[last_used].len);
+
+	if (unlikely(id >= vq->packed.vring.num)) {
+		BAD_RING(vq, "id %u out of range\n", id);
+		return NULL;
+	}
+	if (unlikely(!vq->packed.desc_state[id].data)) {
+		BAD_RING(vq, "id %u is not a head!\n", id);
+		return NULL;
+	}
+
+	/* detach_buf_packed clears data, so grab it now. */
+	ret = vq->packed.desc_state[id].data;
+	detach_buf_packed(vq, id, ctx);
+
+	vq->last_used_idx += vq->packed.desc_state[id].num;
+	if (unlikely(vq->last_used_idx >= vq->packed.vring.num)) {
+		vq->last_used_idx -= vq->packed.vring.num;
+		vq->packed.used_wrap_counter ^= 1;
+	}
+
+	LAST_ADD_TIME_INVALID(vq);
+
+	END_USE(vq);
+	return ret;
+}
+
+static void virtqueue_disable_cb_packed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (vq->packed.event_flags_shadow != VRING_PACKED_EVENT_FLAG_DISABLE) {
+		vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE;
+		vq->packed.vring.driver->flags =
+			cpu_to_le16(vq->packed.event_flags_shadow);
+	}
+}
+
+static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	START_USE(vq);
+
+	/*
+	 * We optimistically turn back on interrupts, then check if there was
+	 * more to do.
+	 */
+
+	if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) {
+		vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_ENABLE;
+		vq->packed.vring.driver->flags =
+				cpu_to_le16(vq->packed.event_flags_shadow);
+	}
+
+	END_USE(vq);
+	return vq->last_used_idx | ((u16)vq->packed.used_wrap_counter <<
+			VRING_PACKED_EVENT_F_WRAP_CTR);
+}
+
+static bool virtqueue_poll_packed(struct virtqueue *_vq, u16 off_wrap)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	bool wrap_counter;
+	u16 used_idx;
+
+	wrap_counter = off_wrap >> VRING_PACKED_EVENT_F_WRAP_CTR;
+	used_idx = off_wrap & ~(1 << VRING_PACKED_EVENT_F_WRAP_CTR);
+
+	return is_used_desc_packed(vq, used_idx, wrap_counter);
+}
+
+static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 used_idx, wrap_counter;
+
+	START_USE(vq);
+
+	/*
+	 * We optimistically turn back on interrupts, then check if there was
+	 * more to do.
+	 */
+
+	used_idx = vq->last_used_idx;
+	wrap_counter = vq->packed.used_wrap_counter;
+
+	if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) {
+		vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_ENABLE;
+		vq->packed.vring.driver->flags =
+				cpu_to_le16(vq->packed.event_flags_shadow);
+	}
+
+	/*
+	 * We need to update event suppression structure first
+	 * before re-checking for more used buffers.
+	 */
+	virtio_mb(vq->weak_barriers);
+
+	if (is_used_desc_packed(vq, used_idx, wrap_counter)) {
+		END_USE(vq);
+		return false;
+	}
+
+	END_USE(vq);
+	return true;
+}
+
+static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	unsigned int i;
+	void *buf;
+
+	START_USE(vq);
+
+	for (i = 0; i < vq->packed.vring.num; i++) {
+		if (!vq->packed.desc_state[i].data)
+			continue;
+		/* detach_buf clears data, so grab it now. */
+		buf = vq->packed.desc_state[i].data;
+		detach_buf_packed(vq, i, NULL);
+		END_USE(vq);
+		return buf;
+	}
+	/* That should have freed everything. */
+	BUG_ON(vq->vq.num_free != vq->packed.vring.num);
+
+	END_USE(vq);
+	return NULL;
+}
+
+static struct virtqueue *vring_create_virtqueue_packed(
+	unsigned int index,
+	unsigned int num,
+	unsigned int vring_align,
+	struct virtio_device *vdev,
+	bool weak_barriers,
+	bool may_reduce_num,
+	bool context,
+	bool (*notify)(struct virtqueue *),
+	void (*callback)(struct virtqueue *),
+	const char *name)
+{
+	struct vring_virtqueue *vq;
+	struct vring_packed_desc *ring;
+	struct vring_packed_desc_event *driver, *device;
+	dma_addr_t ring_dma_addr, driver_event_dma_addr, device_event_dma_addr;
+	size_t ring_size_in_bytes, event_size_in_bytes;
+	unsigned int i;
+
+	ring_size_in_bytes = num * sizeof(struct vring_packed_desc);
+
+	ring = vring_alloc_queue(vdev, ring_size_in_bytes,
+				 &ring_dma_addr,
+				 GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+	if (!ring)
+		goto err_ring;
+
+	event_size_in_bytes = sizeof(struct vring_packed_desc_event);
+
+	driver = vring_alloc_queue(vdev, event_size_in_bytes,
+				   &driver_event_dma_addr,
+				   GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+	if (!driver)
+		goto err_driver;
+
+	device = vring_alloc_queue(vdev, event_size_in_bytes,
+				   &device_event_dma_addr,
+				   GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+	if (!device)
+		goto err_device;
+
+	vq = kmalloc(sizeof(*vq), GFP_KERNEL);
+	if (!vq)
+		goto err_vq;
+
+	vq->vq.callback = callback;
+	vq->vq.vdev = vdev;
+	vq->vq.name = name;
+	vq->vq.num_free = num;
+	vq->vq.index = index;
+	vq->we_own_ring = true;
+	vq->notify = notify;
+	vq->weak_barriers = weak_barriers;
+	vq->broken = false;
+	vq->last_used_idx = 0;
+	vq->num_added = 0;
+	vq->packed_ring = true;
+	vq->use_dma_api = vring_use_dma_api(vdev);
+	list_add_tail(&vq->vq.list, &vdev->vqs);
+#ifdef DEBUG
+	vq->in_use = false;
+	vq->last_add_time_valid = false;
+#endif
+
+	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) &&
+		!context;
+	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
+
+	vq->packed.ring_dma_addr = ring_dma_addr;
+	vq->packed.driver_event_dma_addr = driver_event_dma_addr;
+	vq->packed.device_event_dma_addr = device_event_dma_addr;
+
+	vq->packed.ring_size_in_bytes = ring_size_in_bytes;
+	vq->packed.event_size_in_bytes = event_size_in_bytes;
+
+	vq->packed.vring.num = num;
+	vq->packed.vring.desc = ring;
+	vq->packed.vring.driver = driver;
+	vq->packed.vring.device = device;
+
+	vq->packed.next_avail_idx = 0;
+	vq->packed.avail_wrap_counter = 1;
+	vq->packed.used_wrap_counter = 1;
+	vq->packed.event_flags_shadow = 0;
+	vq->packed.avail_used_flags = 1 << VRING_PACKED_DESC_F_AVAIL;
+
+	vq->packed.desc_state = kmalloc_array(num,
+			sizeof(struct vring_desc_state_packed),
+			GFP_KERNEL);
+	if (!vq->packed.desc_state)
+		goto err_desc_state;
+
+	memset(vq->packed.desc_state, 0,
+		num * sizeof(struct vring_desc_state_packed));
+
+	/* Put everything in free lists. */
+	vq->free_head = 0;
+	for (i = 0; i < num-1; i++)
+		vq->packed.desc_state[i].next = i + 1;
+
+	vq->packed.desc_extra = kmalloc_array(num,
+			sizeof(struct vring_desc_extra_packed),
+			GFP_KERNEL);
+	if (!vq->packed.desc_extra)
+		goto err_desc_extra;
+
+	memset(vq->packed.desc_extra, 0,
+		num * sizeof(struct vring_desc_extra_packed));
+
+	/* No callback?  Tell other side not to bother us. */
+	if (!callback) {
+		vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE;
+		vq->packed.vring.driver->flags =
+			cpu_to_le16(vq->packed.event_flags_shadow);
+	}
+
+	return &vq->vq;
+
+err_desc_extra:
+	kfree(vq->packed.desc_state);
+err_desc_state:
+	kfree(vq);
+err_vq:
+	vring_free_queue(vdev, event_size_in_bytes, device, ring_dma_addr);
+err_device:
+	vring_free_queue(vdev, event_size_in_bytes, driver, ring_dma_addr);
+err_driver:
+	vring_free_queue(vdev, ring_size_in_bytes, ring, ring_dma_addr);
+err_ring:
+	return NULL;
+}
+
+
 /*
  * Generic functions and exported symbols.
  */
@@ -853,8 +1622,12 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 				void *ctx,
 				gfp_t gfp)
 {
-	return virtqueue_add_split(_vq, sgs, total_sg,
-				   out_sgs, in_sgs, data, ctx, gfp);
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->packed_ring ? virtqueue_add_packed(_vq, sgs, total_sg,
+					out_sgs, in_sgs, data, ctx, gfp) :
+				 virtqueue_add_split(_vq, sgs, total_sg,
+					out_sgs, in_sgs, data, ctx, gfp);
 }
 
 /**
@@ -973,7 +1746,10 @@ EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx);
  */
 bool virtqueue_kick_prepare(struct virtqueue *_vq)
 {
-	return virtqueue_kick_prepare_split(_vq);
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->packed_ring ? virtqueue_kick_prepare_packed(_vq) :
+				 virtqueue_kick_prepare_split(_vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);
 
@@ -1040,7 +1816,10 @@ EXPORT_SYMBOL_GPL(virtqueue_kick);
 void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
 			    void **ctx)
 {
-	return virtqueue_get_buf_ctx_split(_vq, len, ctx);
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->packed_ring ? virtqueue_get_buf_ctx_packed(_vq, len, ctx) :
+				 virtqueue_get_buf_ctx_split(_vq, len, ctx);
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx);
 
@@ -1049,7 +1828,6 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 	return virtqueue_get_buf_ctx(_vq, len, NULL);
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_buf);
-
 /**
  * virtqueue_disable_cb - disable callbacks
  * @vq: the struct virtqueue we're talking about.
@@ -1061,7 +1839,12 @@ EXPORT_SYMBOL_GPL(virtqueue_get_buf);
  */
 void virtqueue_disable_cb(struct virtqueue *_vq)
 {
-	virtqueue_disable_cb_split(_vq);
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (vq->packed_ring)
+		virtqueue_disable_cb_packed(_vq);
+	else
+		virtqueue_disable_cb_split(_vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
 
@@ -1079,7 +1862,10 @@ EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
  */
 unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
 {
-	return virtqueue_enable_cb_prepare_split(_vq);
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->packed_ring ? virtqueue_enable_cb_prepare_packed(_vq) :
+				 virtqueue_enable_cb_prepare_split(_vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);
 
@@ -1097,7 +1883,8 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	virtio_mb(vq->weak_barriers);
-	return virtqueue_poll_split(_vq, last_used_idx);
+	return vq->packed_ring ? virtqueue_poll_packed(_vq, last_used_idx) :
+				 virtqueue_poll_split(_vq, last_used_idx);
 }
 EXPORT_SYMBOL_GPL(virtqueue_poll);
 
@@ -1135,7 +1922,10 @@ EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
  */
 bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 {
-	return virtqueue_enable_cb_delayed_split(_vq);
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) :
+				 virtqueue_enable_cb_delayed_split(_vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
 
@@ -1149,13 +1939,16 @@ EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
  */
 void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 {
-	return virtqueue_detach_unused_buf_split(_vq);
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->packed_ring ? virtqueue_detach_unused_buf_packed(_vq) :
+				 virtqueue_detach_unused_buf_split(_vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf);
 
 static inline bool more_used(const struct vring_virtqueue *vq)
 {
-	return more_used_split(vq);
+	return vq->packed_ring ? more_used_packed(vq) : more_used_split(vq);
 }
 
 irqreturn_t vring_interrupt(int irq, void *_vq)
@@ -1178,6 +1971,7 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
 }
 EXPORT_SYMBOL_GPL(vring_interrupt);
 
+/* Only available for split ring */
 struct virtqueue *__vring_new_virtqueue(unsigned int index,
 					struct vring vring,
 					struct virtio_device *vdev,
@@ -1190,10 +1984,14 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	unsigned int i;
 	struct vring_virtqueue *vq;
 
+	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
+		return NULL;
+
 	vq = kmalloc(sizeof(*vq), GFP_KERNEL);
 	if (!vq)
 		return NULL;
 
+	vq->packed_ring = false;
 	vq->vq.callback = callback;
 	vq->vq.vdev = vdev;
 	vq->vq.name = name;
@@ -1261,12 +2059,19 @@ struct virtqueue *vring_create_virtqueue(
 	void (*callback)(struct virtqueue *),
 	const char *name)
 {
+
+	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
+		return vring_create_virtqueue_packed(index, num, vring_align,
+				vdev, weak_barriers, may_reduce_num,
+				context, notify, callback, name);
+
 	return vring_create_virtqueue_split(index, num, vring_align,
 			vdev, weak_barriers, may_reduce_num,
 			context, notify, callback, name);
 }
 EXPORT_SYMBOL_GPL(vring_create_virtqueue);
 
+/* Only available for split ring */
 struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      unsigned int num,
 				      unsigned int vring_align,
@@ -1279,6 +2084,10 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      const char *name)
 {
 	struct vring vring;
+
+	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
+		return NULL;
+
 	vring_init(&vring, num, pages, vring_align);
 	return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
 				     notify, callback, name);
@@ -1290,11 +2099,32 @@ void vring_del_virtqueue(struct virtqueue *_vq)
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	if (vq->we_own_ring) {
-		vring_free_queue(vq->vq.vdev,
-				 vq->split.queue_size_in_bytes,
-				 vq->split.vring.desc,
-				 vq->split.queue_dma_addr);
-		kfree(vq->split.desc_state);
+		if (vq->packed_ring) {
+			vring_free_queue(vq->vq.vdev,
+					 vq->packed.ring_size_in_bytes,
+					 vq->packed.vring.desc,
+					 vq->packed.ring_dma_addr);
+
+			vring_free_queue(vq->vq.vdev,
+					 vq->packed.event_size_in_bytes,
+					 vq->packed.vring.driver,
+					 vq->packed.driver_event_dma_addr);
+
+			vring_free_queue(vq->vq.vdev,
+					 vq->packed.event_size_in_bytes,
+					 vq->packed.vring.device,
+					 vq->packed.device_event_dma_addr);
+
+			kfree(vq->packed.desc_state);
+			kfree(vq->packed.desc_extra);
+		} else {
+			vring_free_queue(vq->vq.vdev,
+					 vq->split.queue_size_in_bytes,
+					 vq->split.vring.desc,
+					 vq->split.queue_dma_addr);
+
+			kfree(vq->split.desc_state);
+		}
 	}
 	list_del(&_vq->list);
 	kfree(vq);
@@ -1336,7 +2166,7 @@ unsigned int virtqueue_get_vring_size(struct virtqueue *_vq)
 
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
-	return vq->split.vring.num;
+	return vq->packed_ring ? vq->packed.vring.num : vq->split.vring.num;
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_vring_size);
 
@@ -1369,6 +2199,9 @@ dma_addr_t virtqueue_get_desc_addr(struct virtqueue *_vq)
 
 	BUG_ON(!vq->we_own_ring);
 
+	if (vq->packed_ring)
+		return vq->packed.ring_dma_addr;
+
 	return vq->split.queue_dma_addr;
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_desc_addr);
@@ -1379,6 +2212,9 @@ dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq)
 
 	BUG_ON(!vq->we_own_ring);
 
+	if (vq->packed_ring)
+		return vq->packed.driver_event_dma_addr;
+
 	return vq->split.queue_dma_addr +
 		((char *)vq->split.vring.avail - (char *)vq->split.vring.desc);
 }
@@ -1390,11 +2226,15 @@ dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq)
 
 	BUG_ON(!vq->we_own_ring);
 
+	if (vq->packed_ring)
+		return vq->packed.device_event_dma_addr;
+
 	return vq->split.queue_dma_addr +
 		((char *)vq->split.vring.used - (char *)vq->split.vring.desc);
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_used_addr);
 
+/* Only available for split ring */
 const struct vring *virtqueue_get_vring(struct virtqueue *vq)
 {
 	return &to_vvq(vq)->split.vring;
-- 
cgit v1.2.3


From f51f982682e2a612fa642dfee47cc8da63677148 Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:28 +0800
Subject: virtio_ring: leverage event idx in packed ring

Leverage the EVENT_IDX feature in packed ring to suppress
events when it's available.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/virtio/virtio_ring.c | 77 ++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 71 insertions(+), 6 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index b63eee2034e7..40e4d3798d16 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -1222,7 +1222,7 @@ unmap_release:
 static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
-	u16 flags;
+	u16 new, old, off_wrap, flags, wrap_counter, event_idx;
 	bool needs_kick;
 	union {
 		struct {
@@ -1240,6 +1240,8 @@ static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
 	 */
 	virtio_mb(vq->weak_barriers);
 
+	old = vq->packed.next_avail_idx - vq->num_added;
+	new = vq->packed.next_avail_idx;
 	vq->num_added = 0;
 
 	snapshot.u32 = *(u32 *)vq->packed.vring.device;
@@ -1248,7 +1250,20 @@ static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
 	LAST_ADD_TIME_CHECK(vq);
 	LAST_ADD_TIME_INVALID(vq);
 
-	needs_kick = (flags != VRING_PACKED_EVENT_FLAG_DISABLE);
+	if (flags != VRING_PACKED_EVENT_FLAG_DESC) {
+		needs_kick = (flags != VRING_PACKED_EVENT_FLAG_DISABLE);
+		goto out;
+	}
+
+	off_wrap = le16_to_cpu(snapshot.off_wrap);
+
+	wrap_counter = off_wrap >> VRING_PACKED_EVENT_F_WRAP_CTR;
+	event_idx = off_wrap & ~(1 << VRING_PACKED_EVENT_F_WRAP_CTR);
+	if (wrap_counter != vq->packed.avail_wrap_counter)
+		event_idx -= vq->packed.vring.num;
+
+	needs_kick = vring_need_event(event_idx, new, old);
+out:
 	END_USE(vq);
 	return needs_kick;
 }
@@ -1365,6 +1380,18 @@ static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
 		vq->packed.used_wrap_counter ^= 1;
 	}
 
+	/*
+	 * If we expect an interrupt for the next entry, tell host
+	 * by writing event index and flush out the write before
+	 * the read in the next get_buf call.
+	 */
+	if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DESC)
+		virtio_store_mb(vq->weak_barriers,
+				&vq->packed.vring.driver->off_wrap,
+				cpu_to_le16(vq->last_used_idx |
+					(vq->packed.used_wrap_counter <<
+					 VRING_PACKED_EVENT_F_WRAP_CTR)));
+
 	LAST_ADD_TIME_INVALID(vq);
 
 	END_USE(vq);
@@ -1393,8 +1420,22 @@ static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq)
 	 * more to do.
 	 */
 
+	if (vq->event) {
+		vq->packed.vring.driver->off_wrap =
+			cpu_to_le16(vq->last_used_idx |
+				(vq->packed.used_wrap_counter <<
+				 VRING_PACKED_EVENT_F_WRAP_CTR));
+		/*
+		 * We need to update event offset and event wrap
+		 * counter first before updating event flags.
+		 */
+		virtio_wmb(vq->weak_barriers);
+	}
+
 	if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) {
-		vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_ENABLE;
+		vq->packed.event_flags_shadow = vq->event ?
+				VRING_PACKED_EVENT_FLAG_DESC :
+				VRING_PACKED_EVENT_FLAG_ENABLE;
 		vq->packed.vring.driver->flags =
 				cpu_to_le16(vq->packed.event_flags_shadow);
 	}
@@ -1420,6 +1461,7 @@ static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	u16 used_idx, wrap_counter;
+	u16 bufs;
 
 	START_USE(vq);
 
@@ -1428,11 +1470,34 @@ static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
 	 * more to do.
 	 */
 
-	used_idx = vq->last_used_idx;
-	wrap_counter = vq->packed.used_wrap_counter;
+	if (vq->event) {
+		/* TODO: tune this threshold */
+		bufs = (vq->packed.vring.num - vq->vq.num_free) * 3 / 4;
+		wrap_counter = vq->packed.used_wrap_counter;
+
+		used_idx = vq->last_used_idx + bufs;
+		if (used_idx >= vq->packed.vring.num) {
+			used_idx -= vq->packed.vring.num;
+			wrap_counter ^= 1;
+		}
+
+		vq->packed.vring.driver->off_wrap = cpu_to_le16(used_idx |
+			(wrap_counter << VRING_PACKED_EVENT_F_WRAP_CTR));
+
+		/*
+		 * We need to update event offset and event wrap
+		 * counter first before updating event flags.
+		 */
+		virtio_wmb(vq->weak_barriers);
+	} else {
+		used_idx = vq->last_used_idx;
+		wrap_counter = vq->packed.used_wrap_counter;
+	}
 
 	if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) {
-		vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_ENABLE;
+		vq->packed.event_flags_shadow = vq->event ?
+				VRING_PACKED_EVENT_FLAG_DESC :
+				VRING_PACKED_EVENT_FLAG_ENABLE;
 		vq->packed.vring.driver->flags =
 				cpu_to_le16(vq->packed.event_flags_shadow);
 	}
-- 
cgit v1.2.3


From 3a814fdf271552a5c4641f812ff7e2dd8ad09ee4 Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:29 +0800
Subject: virtio_ring: disable packed ring on unsupported transports

Currently, ccw, vop and remoteproc need some legacy virtio
APIs to create or access virtio rings, which are not supported
by packed ring. So disable packed ring on these transports
for now.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/misc/mic/vop/vop_main.c        | 13 +++++++++++++
 drivers/remoteproc/remoteproc_virtio.c | 13 +++++++++++++
 drivers/s390/virtio/virtio_ccw.c       | 14 ++++++++++++++
 3 files changed, 40 insertions(+)

diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c
index 3633202e18f4..6b212c8b78e7 100644
--- a/drivers/misc/mic/vop/vop_main.c
+++ b/drivers/misc/mic/vop/vop_main.c
@@ -129,6 +129,16 @@ static u64 vop_get_features(struct virtio_device *vdev)
 	return features;
 }
 
+static void vop_transport_features(struct virtio_device *vdev)
+{
+	/*
+	 * Packed ring isn't enabled on virtio_vop for now,
+	 * because virtio_vop uses vring_new_virtqueue() which
+	 * creates virtio rings on preallocated memory.
+	 */
+	__virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
+}
+
 static int vop_finalize_features(struct virtio_device *vdev)
 {
 	unsigned int i, bits;
@@ -141,6 +151,9 @@ static int vop_finalize_features(struct virtio_device *vdev)
 	/* Give virtio_ring a chance to accept features. */
 	vring_transport_features(vdev);
 
+	/* Give virtio_vop a chance to accept features. */
+	vop_transport_features(vdev);
+
 	memset_io(out_features, 0, feature_len);
 	bits = min_t(unsigned, feature_len,
 		     sizeof(vdev->features)) * 8;
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index de21f620b882..183fc42a510a 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -214,6 +214,16 @@ static u64 rproc_virtio_get_features(struct virtio_device *vdev)
 	return rsc->dfeatures;
 }
 
+static void rproc_transport_features(struct virtio_device *vdev)
+{
+	/*
+	 * Packed ring isn't enabled on remoteproc for now,
+	 * because remoteproc uses vring_new_virtqueue() which
+	 * creates virtio rings on preallocated memory.
+	 */
+	__virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
+}
+
 static int rproc_virtio_finalize_features(struct virtio_device *vdev)
 {
 	struct rproc_vdev *rvdev = vdev_to_rvdev(vdev);
@@ -224,6 +234,9 @@ static int rproc_virtio_finalize_features(struct virtio_device *vdev)
 	/* Give virtio_ring a chance to accept features */
 	vring_transport_features(vdev);
 
+	/* Give virtio_rproc a chance to accept features. */
+	rproc_transport_features(vdev);
+
 	/* Make sure we don't have any features > 32 bits! */
 	BUG_ON((u32)vdev->features != vdev->features);
 
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 97b6f197f007..406d1f64ad65 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -765,6 +765,17 @@ out_free:
 	return rc;
 }
 
+static void ccw_transport_features(struct virtio_device *vdev)
+{
+	/*
+	 * Packed ring isn't enabled on virtio_ccw for now,
+	 * because virtio_ccw uses some legacy accessors,
+	 * e.g. virtqueue_get_avail() and virtqueue_get_used()
+	 * which aren't available in packed ring currently.
+	 */
+	__virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
+}
+
 static int virtio_ccw_finalize_features(struct virtio_device *vdev)
 {
 	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
@@ -791,6 +802,9 @@ static int virtio_ccw_finalize_features(struct virtio_device *vdev)
 	/* Give virtio_ring a chance to accept features. */
 	vring_transport_features(vdev);
 
+	/* Give virtio_ccw a chance to accept features. */
+	ccw_transport_features(vdev);
+
 	features->index = 0;
 	features->features = cpu_to_le32((u32)vdev->features);
 	/* Write the first half of the feature bits to the host. */
-- 
cgit v1.2.3


From f959a128fe83090981add69aadc87a4e496e9369 Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.bie@intel.com>
Date: Wed, 21 Nov 2018 18:03:30 +0800
Subject: virtio_ring: advertize packed ring layout

Advertize the packed ring layout support.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/virtio/virtio_ring.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 40e4d3798d16..cd7e755484e3 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2211,6 +2211,8 @@ void vring_transport_features(struct virtio_device *vdev)
 			break;
 		case VIRTIO_F_IOMMU_PLATFORM:
 			break;
+		case VIRTIO_F_RING_PACKED:
+			break;
 		default:
 			/* We don't understand this bit. */
 			__virtio_clear_bit(vdev, i);
-- 
cgit v1.2.3


From a428afe82f98d2ffb31c981671630df1fa25906f Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Sat, 24 Nov 2018 04:34:20 +0200
Subject: net: bridge: add support for user-controlled bool options

We have been adding many new bridge options, a big number of which are
boolean but still take up netlink attribute ids and waste space in the skb.
Recently we discussed learning from link-local packets[1] and decided
yet another new boolean option will be needed, thus introducing this API
to save some bridge nl space.
The API supports changing the value of multiple boolean options at once
via the br_boolopt_multi struct which has an optmask (which options to
set, bit per opt) and optval (options' new values). Future boolean
options will only be added to the br_boolopt_id enum and then will have
to be handled in br_boolopt_toggle/get. The API will automatically
add the ability to change and export them via netlink, sysfs can use the
single boolopt function versions to do the same. The behaviour with
failing/succeeding is the same as with normal netlink option changing.

If an option requires mapping to internal kernel flag or needs special
configuration to be enabled then it should be handled in
br_boolopt_toggle. It should also be able to retrieve an option's current
state via br_boolopt_get.

v2: WARN_ON() on unsupported option as that shouldn't be possible and
    also will help catch people who add new options without handling
    them for both set and get. Pass down extack so if an option desires
    it could set it on error and be more user-friendly.

[1] https://www.spinics.net/lists/netdev/msg532698.html

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h | 18 +++++++++++
 include/uapi/linux/if_link.h   |  1 +
 net/bridge/br.c                | 71 ++++++++++++++++++++++++++++++++++++++++++
 net/bridge/br_netlink.c        | 17 +++++++++-
 net/bridge/br_private.h        |  8 +++++
 net/core/rtnetlink.c           |  2 +-
 6 files changed, 115 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index e41eda3c71f1..6dc02c03bdf8 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -292,4 +292,22 @@ struct br_mcast_stats {
 	__u64 mcast_bytes[BR_MCAST_DIR_SIZE];
 	__u64 mcast_packets[BR_MCAST_DIR_SIZE];
 };
+
+/* bridge boolean options
+ * IMPORTANT: if adding a new option do not forget to handle
+ *            it in br_boolopt_toggle/get and bridge sysfs
+ */
+enum br_boolopt_id {
+	BR_BOOLOPT_MAX
+};
+
+/* struct br_boolopt_multi - change multiple bridge boolean options
+ *
+ * @optval: new option values (bit per option)
+ * @optmask: options to change (bit per option)
+ */
+struct br_boolopt_multi {
+	__u32 optval;
+	__u32 optmask;
+};
 #endif /* _UAPI_LINUX_IF_BRIDGE_H */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index f42c069d81db..d6533828123a 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -288,6 +288,7 @@ enum {
 	IFLA_BR_MCAST_IGMP_VERSION,
 	IFLA_BR_MCAST_MLD_VERSION,
 	IFLA_BR_VLAN_STATS_PER_PORT,
+	IFLA_BR_MULTI_BOOLOPT,
 	__IFLA_BR_MAX,
 };
 
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 360ad66c21e9..c527160c1975 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -175,6 +175,77 @@ static struct notifier_block br_switchdev_notifier = {
 	.notifier_call = br_switchdev_event,
 };
 
+/* br_boolopt_toggle - change user-controlled boolean option
+ *
+ * @br: bridge device
+ * @opt: id of the option to change
+ * @on: new option value
+ * @extack: extack for error messages
+ *
+ * Changes the value of the respective boolean option to @on taking care of
+ * any internal option value mapping and configuration.
+ */
+int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on,
+		      struct netlink_ext_ack *extack)
+{
+	switch (opt) {
+	default:
+		/* shouldn't be called with unsupported options */
+		WARN_ON(1);
+		break;
+	}
+
+	return 0;
+}
+
+int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt)
+{
+	switch (opt) {
+	default:
+		/* shouldn't be called with unsupported options */
+		WARN_ON(1);
+		break;
+	}
+
+	return 0;
+}
+
+int br_boolopt_multi_toggle(struct net_bridge *br,
+			    struct br_boolopt_multi *bm,
+			    struct netlink_ext_ack *extack)
+{
+	unsigned long bitmap = bm->optmask;
+	int err = 0;
+	int opt_id;
+
+	for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) {
+		bool on = !!(bm->optval & BIT(opt_id));
+
+		err = br_boolopt_toggle(br, opt_id, on, extack);
+		if (err) {
+			br_debug(br, "boolopt multi-toggle error: option: %d current: %d new: %d error: %d\n",
+				 opt_id, br_boolopt_get(br, opt_id), on, err);
+			break;
+		}
+	}
+
+	return err;
+}
+
+void br_boolopt_multi_get(const struct net_bridge *br,
+			  struct br_boolopt_multi *bm)
+{
+	u32 optval = 0;
+	int opt_id;
+
+	for (opt_id = 0; opt_id < BR_BOOLOPT_MAX; opt_id++)
+		optval |= (br_boolopt_get(br, opt_id) << opt_id);
+
+	bm->optval = optval;
+	bm->optmask = 0;
+}
+
+/* private bridge options, controlled by the kernel */
 void br_opt_toggle(struct net_bridge *br, enum net_bridge_opts opt, bool on)
 {
 	bool cur = !!br_opt_get(br, opt);
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 3345f1984542..13cd50326af2 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1035,6 +1035,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
 	[IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 },
 	[IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 },
 	[IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 },
+	[IFLA_BR_MULTI_BOOLOPT] = { .type = NLA_EXACT_LEN,
+				    .len = sizeof(struct br_boolopt_multi) },
 };
 
 static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
@@ -1296,6 +1298,15 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	}
 #endif
 
+	if (data[IFLA_BR_MULTI_BOOLOPT]) {
+		struct br_boolopt_multi *bm;
+
+		bm = nla_data(data[IFLA_BR_MULTI_BOOLOPT]);
+		err = br_boolopt_multi_toggle(br, bm, extack);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
@@ -1374,6 +1385,7 @@ static size_t br_get_size(const struct net_device *brdev)
 	       nla_total_size(sizeof(u8)) +     /* IFLA_BR_NF_CALL_IP6TABLES */
 	       nla_total_size(sizeof(u8)) +     /* IFLA_BR_NF_CALL_ARPTABLES */
 #endif
+	       nla_total_size(sizeof(struct br_boolopt_multi)) + /* IFLA_BR_MULTI_BOOLOPT */
 	       0;
 }
 
@@ -1387,6 +1399,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 	u32 stp_enabled = br->stp_enabled;
 	u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1];
 	u8 vlan_enabled = br_vlan_enabled(br->dev);
+	struct br_boolopt_multi bm;
 	u64 clockval;
 
 	clockval = br_timer_value(&br->hello_timer);
@@ -1403,6 +1416,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 	if (nla_put_u64_64bit(skb, IFLA_BR_GC_TIMER, clockval, IFLA_BR_PAD))
 		return -EMSGSIZE;
 
+	br_boolopt_multi_get(br, &bm);
 	if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) ||
 	    nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) ||
 	    nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) ||
@@ -1420,7 +1434,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 	    nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) ||
 	    nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED,
 		       br->topology_change_detected) ||
-	    nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr))
+	    nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr) ||
+	    nla_put(skb, IFLA_BR_MULTI_BOOLOPT, sizeof(bm), &bm))
 		return -EMSGSIZE;
 
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index bc2653738fc3..6d4c208fbf08 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -507,6 +507,14 @@ static inline int br_opt_get(const struct net_bridge *br,
 	return test_bit(opt, &br->options);
 }
 
+int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on,
+		      struct netlink_ext_ack *extack);
+int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt);
+int br_boolopt_multi_toggle(struct net_bridge *br,
+			    struct br_boolopt_multi *bm,
+			    struct netlink_ext_ack *extack);
+void br_boolopt_multi_get(const struct net_bridge *br,
+			  struct br_boolopt_multi *bm);
 void br_opt_toggle(struct net_bridge *br, enum net_bridge_opts opt, bool on);
 
 /* br_device.c */
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 86f2d9cbdae3..a498bb41c9aa 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -59,7 +59,7 @@
 #include <net/rtnetlink.h>
 #include <net/net_namespace.h>
 
-#define RTNL_MAX_TYPE		49
+#define RTNL_MAX_TYPE		50
 #define RTNL_SLAVE_MAX_TYPE	36
 
 struct rtnl_link {
-- 
cgit v1.2.3


From 70e4272b4c81828e7d942209bae83b9d92752cfe Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Sat, 24 Nov 2018 04:34:21 +0200
Subject: net: bridge: add no_linklocal_learn bool option

Use the new boolopt API to add an option which disables learning from
link-local packets. The default is kept as before and learning is
enabled. This is a simple map from a boolopt bit to a bridge private
flag that is tested before learning.

v2: pass NULL for extack via sysfs

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h |  3 +++
 net/bridge/br.c                |  5 +++++
 net/bridge/br_input.c          |  4 +++-
 net/bridge/br_private.h        |  1 +
 net/bridge/br_sysfs_br.c       | 22 ++++++++++++++++++++++
 5 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 6dc02c03bdf8..773e476a8e54 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -294,10 +294,13 @@ struct br_mcast_stats {
 };
 
 /* bridge boolean options
+ * BR_BOOLOPT_NO_LL_LEARN - disable learning from link-local packets
+ *
  * IMPORTANT: if adding a new option do not forget to handle
  *            it in br_boolopt_toggle/get and bridge sysfs
  */
 enum br_boolopt_id {
+	BR_BOOLOPT_NO_LL_LEARN,
 	BR_BOOLOPT_MAX
 };
 
diff --git a/net/bridge/br.c b/net/bridge/br.c
index c527160c1975..b4a51a053586 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -189,6 +189,9 @@ int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on,
 		      struct netlink_ext_ack *extack)
 {
 	switch (opt) {
+	case BR_BOOLOPT_NO_LL_LEARN:
+		br_opt_toggle(br, BROPT_NO_LL_LEARN, on);
+		break;
 	default:
 		/* shouldn't be called with unsupported options */
 		WARN_ON(1);
@@ -201,6 +204,8 @@ int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on,
 int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt)
 {
 	switch (opt) {
+	case BR_BOOLOPT_NO_LL_LEARN:
+		return br_opt_get(br, BROPT_NO_LL_LEARN);
 	default:
 		/* shouldn't be called with unsupported options */
 		WARN_ON(1);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 3ddca11f44c2..5ea7e56119c1 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -188,7 +188,9 @@ static void __br_handle_local_finish(struct sk_buff *skb)
 	u16 vid = 0;
 
 	/* check if vlan is allowed, to avoid spoofing */
-	if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid))
+	if ((p->flags & BR_LEARNING) &&
+	    !br_opt_get(p->br, BROPT_NO_LL_LEARN) &&
+	    br_should_learn(p, skb, &vid))
 		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
 }
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 6d4c208fbf08..d29f837cd7a2 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -328,6 +328,7 @@ enum net_bridge_opts {
 	BROPT_NEIGH_SUPPRESS_ENABLED,
 	BROPT_MTU_SET_BY_USER,
 	BROPT_VLAN_STATS_PER_PORT,
+	BROPT_NO_LL_LEARN,
 };
 
 struct net_bridge {
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index 60182bef6341..6a378a7e16ea 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -328,6 +328,27 @@ static ssize_t flush_store(struct device *d,
 }
 static DEVICE_ATTR_WO(flush);
 
+static ssize_t no_linklocal_learn_show(struct device *d,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%d\n", br_boolopt_get(br, BR_BOOLOPT_NO_LL_LEARN));
+}
+
+static int set_no_linklocal_learn(struct net_bridge *br, unsigned long val)
+{
+	return br_boolopt_toggle(br, BR_BOOLOPT_NO_LL_LEARN, !!val, NULL);
+}
+
+static ssize_t no_linklocal_learn_store(struct device *d,
+					struct device_attribute *attr,
+					const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_no_linklocal_learn);
+}
+static DEVICE_ATTR_RW(no_linklocal_learn);
+
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 static ssize_t multicast_router_show(struct device *d,
 				     struct device_attribute *attr, char *buf)
@@ -841,6 +862,7 @@ static struct attribute *bridge_attrs[] = {
 	&dev_attr_gc_timer.attr,
 	&dev_attr_group_addr.attr,
 	&dev_attr_flush.attr,
+	&dev_attr_no_linklocal_learn.attr,
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	&dev_attr_multicast_router.attr,
 	&dev_attr_multicast_snooping.attr,
-- 
cgit v1.2.3


From 1ed1ccb99e2a6bf3e2eb5f2a9f8420f17ea00e92 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Sat, 24 Nov 2018 04:34:22 +0200
Subject: net: bridge: export supported boolopts

Now that we have at least one bool option, we can export all of the
supported bool options via optmask when dumping them.

v2: new patch

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br.c b/net/bridge/br.c
index b4a51a053586..4e7cd993ce94 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -247,7 +247,7 @@ void br_boolopt_multi_get(const struct net_bridge *br,
 		optval |= (br_boolopt_get(br, opt_id) << opt_id);
 
 	bm->optval = optval;
-	bm->optmask = 0;
+	bm->optmask = GENMASK((BR_BOOLOPT_MAX - 1), 0);
 }
 
 /* private bridge options, controlled by the kernel */
-- 
cgit v1.2.3


From 4e3c7c00bba0636b97eb23d582c20b0f5d95ce20 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Sat, 24 Nov 2018 18:16:41 +0800
Subject: net: aquantia: return 'err' if set MPI_DEINIT state fails

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c:260:7:
 warning: variable 'err' set but not used [-Wunused-but-set-variable]

'err' should be returned while set MPI_DEINIT state fails
in hw_atl_utils_soft_reset.

Fixes: cce96d1883da ("net: aquantia: Regression on reset with 1.x firmware")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 1af6606a9166..9b74a3197d7f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -263,6 +263,8 @@ int hw_atl_utils_soft_reset(struct aq_hw_s *self)
 		AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR) &
 				HW_ATL_MPI_STATE_MSK) == MPI_DEINIT,
 			       10, 1000U);
+		if (err)
+			return err;
 	}
 
 	if (self->rbl_enabled)
-- 
cgit v1.2.3


From 6502be9f04da2df88095e9ff7c964c2d5915bb3a Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 25 Nov 2018 09:43:54 +0000
Subject: mlxsw: spectrum_switchdev: Do not set field when it is reserved

When configuring an FDB entry pointing to a LAG netdev (or its upper),
the driver should only set the 'lag_vid' field when the FID (filtering
identifier) is of 802.1D type.

Extend the 802.1D FID family with an attribute indicating whether this
field should be set and based on its value set the field or leave it
blank.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c       | 7 +++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 3 ++-
 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 973a9d2901f7..244972bf8b0a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -721,6 +721,7 @@ int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port,
 			   struct tc_prio_qopt_offload *p);
 
 /* spectrum_fid.c */
+bool mlxsw_sp_fid_lag_vid_valid(const struct mlxsw_sp_fid *fid);
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp,
 						  u16 fid_index);
 int mlxsw_sp_fid_nve_ifindex(const struct mlxsw_sp_fid *fid, int *nve_ifindex);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index 71b2d20afcc2..5008bf63d73b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -98,6 +98,7 @@ struct mlxsw_sp_fid_family {
 	enum mlxsw_sp_rif_type rif_type;
 	const struct mlxsw_sp_fid_ops *ops;
 	struct mlxsw_sp *mlxsw_sp;
+	u8 lag_vid_valid:1;
 };
 
 static const int mlxsw_sp_sfgc_uc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = {
@@ -122,6 +123,11 @@ static const int *mlxsw_sp_packet_type_sfgc_types[] = {
 	[MLXSW_SP_FLOOD_TYPE_MC]	= mlxsw_sp_sfgc_mc_packet_types,
 };
 
+bool mlxsw_sp_fid_lag_vid_valid(const struct mlxsw_sp_fid *fid)
+{
+	return fid->fid_family->lag_vid_valid;
+}
+
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp,
 						  u16 fid_index)
 {
@@ -792,6 +798,7 @@ static const struct mlxsw_sp_fid_family mlxsw_sp_fid_8021d_family = {
 	.nr_flood_tables	= ARRAY_SIZE(mlxsw_sp_fid_8021d_flood_tables),
 	.rif_type		= MLXSW_SP_RIF_TYPE_FID,
 	.ops			= &mlxsw_sp_fid_8021d_ops,
+	.lag_vid_valid		= 1,
 };
 
 static int mlxsw_sp_fid_rfid_configure(struct mlxsw_sp_fid *fid)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 73e5db176d7e..3c2428404b2e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2482,7 +2482,8 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp,
 
 	bridge_device = bridge_port->bridge_device;
 	vid = bridge_device->vlan_enabled ? mlxsw_sp_port_vlan->vid : 0;
-	lag_vid = mlxsw_sp_port_vlan->vid;
+	lag_vid = mlxsw_sp_fid_lag_vid_valid(mlxsw_sp_port_vlan->fid) ?
+		  mlxsw_sp_port_vlan->vid : 0;
 
 do_fdb_op:
 	err = mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp, lag_id, mac, fid, lag_vid,
-- 
cgit v1.2.3


From 7c4a729221566c3523701c7a08983c580a84012a Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 25 Nov 2018 09:43:55 +0000
Subject: mlxsw: spectrum_fid: Make flood index calculation more robust

802.1D FIDs use a per-FID flood table, where the flood index into the
table is calculated by subtracting 4K from the FID's index.

Currently, 802.1D FIDs start at 4K, so the calculation is correct, but
if it was ever to change, the calculation will no longer be correct.

In addition, this change will allow us to reuse the flood index
calculation function in the next patch, where we are going to emulate
802.1Q FIDs using 802.1D FIDs.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index 5008bf63d73b..e1739cda25cb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -607,7 +607,7 @@ mlxsw_sp_fid_8021d_compare(const struct mlxsw_sp_fid *fid, const void *arg)
 
 static u16 mlxsw_sp_fid_8021d_flood_index(const struct mlxsw_sp_fid *fid)
 {
-	return fid->fid_index - fid->fid_family->start_index;
+	return fid->fid_index - VLAN_N_VID;
 }
 
 static int mlxsw_sp_port_vp_mode_trans(struct mlxsw_sp_port *mlxsw_sp_port)
-- 
cgit v1.2.3


From d62dd8a0c808b6afac5c85547a84aad7b187b108 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 25 Nov 2018 09:43:57 +0000
Subject: mlxsw: spectrum_fid: Introduce emulated 802.1Q FIDs

The driver uses 802.1Q FIDs when offloading a VLAN-aware bridge.
Unfortunately, it is not possible to assign a VNI to such FIDs, which
prompts the driver to forbid the enslavement of VxLAN devices to a
VLAN-aware bridge.

Workaround this hardware limitation by creating a new family of FIDs,
emulated 802.1Q FIDs. These FIDs are emulated using 802.1D FIDs, which
can be assigned a VNI.

The downside of this approach is that multiple {Port, VID}->FID entries
are required, whereas only a single VID->FID is required with "true"
802.1Q FIDs.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c | 33 ++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index e1739cda25cb..99ccb11405a5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -801,6 +801,39 @@ static const struct mlxsw_sp_fid_family mlxsw_sp_fid_8021d_family = {
 	.lag_vid_valid		= 1,
 };
 
+static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021q_emu_ops = {
+	.setup			= mlxsw_sp_fid_8021q_setup,
+	.configure		= mlxsw_sp_fid_8021d_configure,
+	.deconfigure		= mlxsw_sp_fid_8021d_deconfigure,
+	.index_alloc		= mlxsw_sp_fid_8021d_index_alloc,
+	.compare		= mlxsw_sp_fid_8021q_compare,
+	.flood_index		= mlxsw_sp_fid_8021d_flood_index,
+	.port_vid_map		= mlxsw_sp_fid_8021d_port_vid_map,
+	.port_vid_unmap		= mlxsw_sp_fid_8021d_port_vid_unmap,
+	.vni_set		= mlxsw_sp_fid_8021d_vni_set,
+	.vni_clear		= mlxsw_sp_fid_8021d_vni_clear,
+	.nve_flood_index_set	= mlxsw_sp_fid_8021d_nve_flood_index_set,
+	.nve_flood_index_clear	= mlxsw_sp_fid_8021d_nve_flood_index_clear,
+};
+
+/* There are 4K-2 emulated 802.1Q FIDs, starting right after the 802.1D FIDs */
+#define MLXSW_SP_FID_8021Q_EMU_START	(VLAN_N_VID + MLXSW_SP_FID_8021D_MAX)
+#define MLXSW_SP_FID_8021Q_EMU_END	(MLXSW_SP_FID_8021Q_EMU_START + \
+					 VLAN_VID_MASK - 2)
+
+/* Range and flood configuration must match mlxsw_config_profile */
+static const struct mlxsw_sp_fid_family mlxsw_sp_fid_8021q_emu_family = {
+	.type			= MLXSW_SP_FID_TYPE_8021Q,
+	.fid_size		= sizeof(struct mlxsw_sp_fid_8021q),
+	.start_index		= MLXSW_SP_FID_8021Q_EMU_START,
+	.end_index		= MLXSW_SP_FID_8021Q_EMU_END,
+	.flood_tables		= mlxsw_sp_fid_8021d_flood_tables,
+	.nr_flood_tables	= ARRAY_SIZE(mlxsw_sp_fid_8021d_flood_tables),
+	.rif_type		= MLXSW_SP_RIF_TYPE_VLAN,
+	.ops			= &mlxsw_sp_fid_8021q_emu_ops,
+	.lag_vid_valid		= 1,
+};
+
 static int mlxsw_sp_fid_rfid_configure(struct mlxsw_sp_fid *fid)
 {
 	/* rFIDs are allocated by the device during init */
-- 
cgit v1.2.3


From ba6da02a9cffa49f40f8979a6f91e9218a870870 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 25 Nov 2018 09:43:58 +0000
Subject: mlxsw: spectrum_router: Introduce emulated VLAN RIFs

Router interfaces (RIFs) constructed on top of VLAN-aware bridges are of
"VLAN" type, whereas RIFs constructed on top of VLAN-unaware bridges of
"FID" type.

In other words, the RIF type is derived from the underlying FID type.
VLAN RIFs are used on top of 802.1Q FIDs, whereas FID RIFs are used on
top of 802.1D FIDs.

Since the previous patch emulated 802.1Q FIDs using 802.1D FIDs, this
patch emulates VLAN RIFs using FID RIFs.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 9e9bb57134f2..5cdd4ceee7a9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -7296,6 +7296,15 @@ static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_fid_ops = {
 	.fdb_del		= mlxsw_sp_rif_fid_fdb_del,
 };
 
+static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_vlan_emu_ops = {
+	.type			= MLXSW_SP_RIF_TYPE_VLAN,
+	.rif_size		= sizeof(struct mlxsw_sp_rif),
+	.configure		= mlxsw_sp_rif_fid_configure,
+	.deconfigure		= mlxsw_sp_rif_fid_deconfigure,
+	.fid_get		= mlxsw_sp_rif_vlan_fid_get,
+	.fdb_del		= mlxsw_sp_rif_vlan_fdb_del,
+};
+
 static struct mlxsw_sp_rif_ipip_lb *
 mlxsw_sp_rif_ipip_lb_rif(struct mlxsw_sp_rif *rif)
 {
-- 
cgit v1.2.3


From c2e7490c31ff6f53617bae4cd85faf50fa543d56 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 25 Nov 2018 09:43:59 +0000
Subject: mlxsw: spectrum: Flip driver to use emulated 802.1Q FIDs

Replace 802.1Q FIDs and VLAN RIFs with their emulated counterparts.

The emulated 802.1Q FIDs are actually 802.1D FIDs and thus use the same
flood tables, of per-FID type. Therefore, add 4K-1 entries to the
per-FID flood tables for the new FIDs and get rid of the FID-offset
flood tables that were used by the old 802.1Q FIDs.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c        | 14 ++++++++------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c    |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c |  2 +-
 3 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 637e2ef76abe..93378d507962 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4111,16 +4111,20 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 	mlxsw_sp_kvdl_fini(mlxsw_sp);
 }
 
+/* Per-FID flood tables are used for both "true" 802.1D FIDs and emulated
+ * 802.1Q FIDs
+ */
+#define MLXSW_SP_FID_FLOOD_TABLE_SIZE	(MLXSW_SP_FID_8021D_MAX + \
+					 VLAN_VID_MASK - 1)
+
 static const struct mlxsw_config_profile mlxsw_sp1_config_profile = {
 	.used_max_mid			= 1,
 	.max_mid			= MLXSW_SP_MID_MAX,
 	.used_flood_tables		= 1,
 	.used_flood_mode		= 1,
 	.flood_mode			= 3,
-	.max_fid_offset_flood_tables	= 3,
-	.fid_offset_flood_table_size	= VLAN_N_VID - 1,
 	.max_fid_flood_tables		= 3,
-	.fid_flood_table_size		= MLXSW_SP_FID_8021D_MAX,
+	.fid_flood_table_size		= MLXSW_SP_FID_FLOOD_TABLE_SIZE,
 	.used_max_ib_mc			= 1,
 	.max_ib_mc			= 0,
 	.used_max_pkey			= 1,
@@ -4143,10 +4147,8 @@ static const struct mlxsw_config_profile mlxsw_sp2_config_profile = {
 	.used_flood_tables		= 1,
 	.used_flood_mode		= 1,
 	.flood_mode			= 3,
-	.max_fid_offset_flood_tables	= 3,
-	.fid_offset_flood_table_size	= VLAN_N_VID - 1,
 	.max_fid_flood_tables		= 3,
-	.fid_flood_table_size		= MLXSW_SP_FID_8021D_MAX,
+	.fid_flood_table_size		= MLXSW_SP_FID_FLOOD_TABLE_SIZE,
 	.used_max_ib_mc			= 1,
 	.max_ib_mc			= 0,
 	.used_max_pkey			= 1,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index 99ccb11405a5..6830e79aed93 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -961,7 +961,7 @@ static const struct mlxsw_sp_fid_family mlxsw_sp_fid_dummy_family = {
 };
 
 static const struct mlxsw_sp_fid_family *mlxsw_sp_fid_family_arr[] = {
-	[MLXSW_SP_FID_TYPE_8021Q]	= &mlxsw_sp_fid_8021q_family,
+	[MLXSW_SP_FID_TYPE_8021Q]	= &mlxsw_sp_fid_8021q_emu_family,
 	[MLXSW_SP_FID_TYPE_8021D]	= &mlxsw_sp_fid_8021d_family,
 	[MLXSW_SP_FID_TYPE_RFID]	= &mlxsw_sp_fid_rfid_family,
 	[MLXSW_SP_FID_TYPE_DUMMY]	= &mlxsw_sp_fid_dummy_family,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 5cdd4ceee7a9..1557c5fc6d10 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -7373,7 +7373,7 @@ static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_ipip_lb_ops = {
 
 static const struct mlxsw_sp_rif_ops *mlxsw_sp_rif_ops_arr[] = {
 	[MLXSW_SP_RIF_TYPE_SUBPORT]	= &mlxsw_sp_rif_subport_ops,
-	[MLXSW_SP_RIF_TYPE_VLAN]	= &mlxsw_sp_rif_vlan_ops,
+	[MLXSW_SP_RIF_TYPE_VLAN]	= &mlxsw_sp_rif_vlan_emu_ops,
 	[MLXSW_SP_RIF_TYPE_FID]		= &mlxsw_sp_rif_fid_ops,
 	[MLXSW_SP_RIF_TYPE_IPIP_LB]	= &mlxsw_sp_rif_ipip_lb_ops,
 };
-- 
cgit v1.2.3


From 712ee16c230fdddb15e0ff5d7c33a441d43e5787 Mon Sep 17 00:00:00 2001
From: yupeng <yupeng0921@gmail.com>
Date: Sun, 25 Nov 2018 23:35:46 -0800
Subject: add documents for snmp counters

Add explaination of below counters:
TcpExtTCPRcvCoalesce
TcpExtTCPAutoCorking
TcpExtTCPOrigDataSent
TCPSynRetrans
TCPFastOpenActiveFail
TcpExtListenOverflows
TcpExtListenDrops
TcpExtTCPHystartTrainDetect
TcpExtTCPHystartTrainCwnd
TcpExtTCPHystartDelayDetect
TcpExtTCPHystartDelayCwnd

Signed-off-by: yupeng <yupeng0921@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/snmp_counter.rst | 202 ++++++++++++++++++++++++++++++
 1 file changed, 202 insertions(+)

diff --git a/Documentation/networking/snmp_counter.rst b/Documentation/networking/snmp_counter.rst
index a262d32ed710..918a1374af30 100644
--- a/Documentation/networking/snmp_counter.rst
+++ b/Documentation/networking/snmp_counter.rst
@@ -220,6 +220,68 @@ Defined in `RFC1213 tcpPassiveOpens`_
 It means the TCP layer receives a SYN, replies a SYN+ACK, come into
 the SYN-RCVD state.
 
+* TcpExtTCPRcvCoalesce
+When packets are received by the TCP layer and are not be read by the
+application, the TCP layer will try to merge them. This counter
+indicate how many packets are merged in such situation. If GRO is
+enabled, lots of packets would be merged by GRO, these packets
+wouldn't be counted to TcpExtTCPRcvCoalesce.
+
+* TcpExtTCPAutoCorking
+When sending packets, the TCP layer will try to merge small packets to
+a bigger one. This counter increase 1 for every packet merged in such
+situation. Please refer to the LWN article for more details:
+https://lwn.net/Articles/576263/
+
+* TcpExtTCPOrigDataSent
+This counter is explained by `kernel commit f19c29e3e391`_, I pasted the
+explaination below::
+
+  TCPOrigDataSent: number of outgoing packets with original data (excluding
+  retransmission but including data-in-SYN). This counter is different from
+  TcpOutSegs because TcpOutSegs also tracks pure ACKs. TCPOrigDataSent is
+  more useful to track the TCP retransmission rate.
+
+* TCPSynRetrans
+This counter is explained by `kernel commit f19c29e3e391`_, I pasted the
+explaination below::
+
+  TCPSynRetrans: number of SYN and SYN/ACK retransmits to break down
+  retransmissions into SYN, fast-retransmits, timeout retransmits, etc.
+
+* TCPFastOpenActiveFail
+This counter is explained by `kernel commit f19c29e3e391`_, I pasted the
+explaination below::
+
+  TCPFastOpenActiveFail: Fast Open attempts (SYN/data) failed because
+  the remote does not accept it or the attempts timed out.
+
+.. _kernel commit f19c29e3e391: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=f19c29e3e391a66a273e9afebaf01917245148cd
+
+* TcpExtListenOverflows and TcpExtListenDrops
+When kernel receives a SYN from a client, and if the TCP accept queue
+is full, kernel will drop the SYN and add 1 to TcpExtListenOverflows.
+At the same time kernel will also add 1 to TcpExtListenDrops. When a
+TCP socket is in LISTEN state, and kernel need to drop a packet,
+kernel would always add 1 to TcpExtListenDrops. So increase
+TcpExtListenOverflows would let TcpExtListenDrops increasing at the
+same time, but TcpExtListenDrops would also increase without
+TcpExtListenOverflows increasing, e.g. a memory allocation fail would
+also let TcpExtListenDrops increase.
+
+Note: The above explanation is based on kernel 4.10 or above version, on
+an old kernel, the TCP stack has different behavior when TCP accept
+queue is full. On the old kernel, TCP stack won't drop the SYN, it
+would complete the 3-way handshake. As the accept queue is full, TCP
+stack will keep the socket in the TCP half-open queue. As it is in the
+half open queue, TCP stack will send SYN+ACK on an exponential backoff
+timer, after client replies ACK, TCP stack checks whether the accept
+queue is still full, if it is not full, moves the socket to the accept
+queue, if it is full, keeps the socket in the half-open queue, at next
+time client replies ACK, this socket will get another chance to move
+to the accept queue.
+
+
 TCP Fast Open
 ============
 When kernel receives a TCP packet, it has two paths to handler the
@@ -331,6 +393,38 @@ TcpExtTCPAbortFailed will be increased.
 
 .. _RFC2525 2.17 section: https://tools.ietf.org/html/rfc2525#page-50
 
+TCP Hybrid Slow Start
+====================
+The Hybrid Slow Start algorithm is an enhancement of the traditional
+TCP congestion window Slow Start algorithm. It uses two pieces of
+information to detect whether the max bandwidth of the TCP path is
+approached. The two pieces of information are ACK train length and
+increase in packet delay. For detail information, please refer the
+`Hybrid Slow Start paper`_. Either ACK train length or packet delay
+hits a specific threshold, the congestion control algorithm will come
+into the Congestion Avoidance state. Until v4.20, two congestion
+control algorithms are using Hybrid Slow Start, they are cubic (the
+default congestion control algorithm) and cdg. Four snmp counters
+relate with the Hybrid Slow Start algorithm.
+
+.. _Hybrid Slow Start paper: https://pdfs.semanticscholar.org/25e9/ef3f03315782c7f1cbcd31b587857adae7d1.pdf
+
+* TcpExtTCPHystartTrainDetect
+How many times the ACK train length threshold is detected
+
+* TcpExtTCPHystartTrainCwnd
+The sum of CWND detected by ACK train length. Dividing this value by
+TcpExtTCPHystartTrainDetect is the average CWND which detected by the
+ACK train length.
+
+* TcpExtTCPHystartDelayDetect
+How many times the packet delay threshold is detected.
+
+* TcpExtTCPHystartDelayCwnd
+The sum of CWND detected by packet delay. Dividing this value by
+TcpExtTCPHystartDelayDetect is the average CWND which detected by the
+packet delay.
+
 examples
 =======
 
@@ -743,3 +837,111 @@ After run client_linger.py, check the output of nstat::
 
   nstatuser@nstat-a:~$ nstat | grep -i abort
   TcpExtTCPAbortOnLinger          1                  0.0
+
+TcpExtTCPRcvCoalesce
+-------------------
+On the server, we run a program which listen on TCP port 9000, but
+doesn't read any data::
+
+  import socket
+  import time
+  port = 9000
+  s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+  s.bind(('0.0.0.0', port))
+  s.listen(1)
+  sock, addr = s.accept()
+  while True:
+      time.sleep(9999999)
+
+Save the above code as server_coalesce.py, and run::
+
+  python3 server_coalesce.py
+
+On the client, save below code as client_coalesce.py::
+
+  import socket
+  server = 'nstat-b'
+  port = 9000
+  s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+  s.connect((server, port))
+
+Run::
+
+  nstatuser@nstat-a:~$ python3 -i client_coalesce.py
+
+We use '-i' to come into the interactive mode, then a packet::
+
+  >>> s.send(b'foo')
+  3
+
+Send a packet again::
+
+  >>> s.send(b'bar')
+  3
+
+On the server, run nstat::
+
+  ubuntu@nstat-b:~$ nstat
+  #kernel
+  IpInReceives                    2                  0.0
+  IpInDelivers                    2                  0.0
+  IpOutRequests                   2                  0.0
+  TcpInSegs                       2                  0.0
+  TcpOutSegs                      2                  0.0
+  TcpExtTCPRcvCoalesce            1                  0.0
+  IpExtInOctets                   110                0.0
+  IpExtOutOctets                  104                0.0
+  IpExtInNoECTPkts                2                  0.0
+
+The client sent two packets, server didn't read any data. When
+the second packet arrived at server, the first packet was still in
+the receiving queue. So the TCP layer merged the two packets, and we
+could find the TcpExtTCPRcvCoalesce increased 1.
+
+TcpExtListenOverflows and TcpExtListenDrops
+----------------------------------------
+On server, run the nc command, listen on port 9000::
+
+  nstatuser@nstat-b:~$ nc -lkv 0.0.0.0 9000
+  Listening on [0.0.0.0] (family 0, port 9000)
+
+On client, run 3 nc commands in different terminals::
+
+  nstatuser@nstat-a:~$ nc -v nstat-b 9000
+  Connection to nstat-b 9000 port [tcp/*] succeeded!
+
+The nc command only accepts 1 connection, and the accept queue length
+is 1. On current linux implementation, set queue length to n means the
+actual queue length is n+1. Now we create 3 connections, 1 is accepted
+by nc, 2 in accepted queue, so the accept queue is full.
+
+Before running the 4th nc, we clean the nstat history on the server::
+
+  nstatuser@nstat-b:~$ nstat -n
+
+Run the 4th nc on the client::
+
+  nstatuser@nstat-a:~$ nc -v nstat-b 9000
+
+If the nc server is running on kernel 4.10 or higher version, you
+won't see the "Connection to ... succeeded!" string, because kernel
+will drop the SYN if the accept queue is full. If the nc client is running
+on an old kernel, you would see that the connection is succeeded,
+because kernel would complete the 3 way handshake and keep the socket
+on half open queue. I did the test on kernel 4.15. Below is the nstat
+on the server::
+
+  nstatuser@nstat-b:~$ nstat
+  #kernel
+  IpInReceives                    4                  0.0
+  IpInDelivers                    4                  0.0
+  TcpInSegs                       4                  0.0
+  TcpExtListenOverflows           4                  0.0
+  TcpExtListenDrops               4                  0.0
+  IpExtInOctets                   240                0.0
+  IpExtInNoECTPkts                4                  0.0
+
+Both TcpExtListenOverflows and TcpExtListenDrops were 4. If the time
+between the 4th nc and the nstat was longer, the value of
+TcpExtListenOverflows and TcpExtListenDrops would be larger, because
+the SYN of the 4th nc was dropped, the client was retrying.
-- 
cgit v1.2.3


From 17364b805f5b9016bb528241ba91481e3497e5e1 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:32:59 +0000
Subject: net: usb: aqc111: Driver skeleton for Aquantia AQtion USB to 5GbE

Initialize usb_driver structure skeleton

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/Kconfig  | 12 ++++++++++++
 drivers/net/usb/Makefile |  1 +
 drivers/net/usb/aqc111.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 61 insertions(+)
 create mode 100644 drivers/net/usb/aqc111.c

diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 418b0904cecb..e5fb8ef2d815 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -613,4 +613,16 @@ config USB_NET_CH9200
 	  To compile this driver as a module, choose M here: the
 	  module will be called ch9200.
 
+config USB_NET_AQC111
+	tristate "Aquantia AQtion USB to 5/2.5GbE Controllers support"
+	depends on USB_USBNET
+	select CRC32
+	default y
+	help
+	  This option adds support for Aquantia AQtion USB
+	  Ethernet adapters based on AQC111U/AQC112 chips.
+
+	  This driver should work with at least the following devices:
+	  * Aquantia AQtion USB to 5GbE
+
 endif # USB_NET_DRIVERS
diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile
index 27307a4ab003..99fd12be2111 100644
--- a/drivers/net/usb/Makefile
+++ b/drivers/net/usb/Makefile
@@ -40,3 +40,4 @@ obj-$(CONFIG_USB_VL600)		+= lg-vl600.o
 obj-$(CONFIG_USB_NET_QMI_WWAN)	+= qmi_wwan.o
 obj-$(CONFIG_USB_NET_CDC_MBIM)	+= cdc_mbim.o
 obj-$(CONFIG_USB_NET_CH9200)	+= ch9200.o
+obj-$(CONFIG_USB_NET_AQC111)	+= aqc111.o
diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
new file mode 100644
index 000000000000..96aca929b570
--- /dev/null
+++ b/drivers/net/usb/aqc111.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Aquantia Corp. Aquantia AQtion USB to 5GbE Controller
+ * Copyright (C) 2003-2005 David Hollis <dhollis@davehollis.com>
+ * Copyright (C) 2005 Phil Chang <pchang23@sbcglobal.net>
+ * Copyright (C) 2002-2003 TiVo Inc.
+ * Copyright (C) 2017-2018 ASIX
+ * Copyright (C) 2018 Aquantia Corp.
+ */
+
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/usb/cdc.h>
+#include <linux/usb/usbnet.h>
+
+static const struct driver_info aqc111_info = {
+	.description	= "Aquantia AQtion USB to 5GbE Controller",
+};
+
+#define AQC111_USB_ETH_DEV(vid, pid, table) \
+	USB_DEVICE_INTERFACE_CLASS((vid), (pid), USB_CLASS_VENDOR_SPEC), \
+	.driver_info = (unsigned long)&(table) \
+}, \
+{ \
+	USB_DEVICE_AND_INTERFACE_INFO((vid), (pid), \
+				      USB_CLASS_COMM, \
+				      USB_CDC_SUBCLASS_ETHERNET, \
+				      USB_CDC_PROTO_NONE), \
+	.driver_info = (unsigned long)&(table),
+
+static const struct usb_device_id products[] = {
+	{AQC111_USB_ETH_DEV(0x2eca, 0xc101, aqc111_info)},
+	{ },/* END */
+};
+MODULE_DEVICE_TABLE(usb, products);
+
+static struct usb_driver aq_driver = {
+	.name		= "aqc111",
+	.id_table	= products,
+	.probe		= usbnet_probe,
+	.disconnect	= usbnet_disconnect,
+};
+
+module_usb_driver(aq_driver);
+
+MODULE_DESCRIPTION("Aquantia AQtion USB to 5/2.5GbE Controllers");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 7cea2d40afd05375d521a0f8e17dec1c1b5806b2 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:02 +0000
Subject: net: usb: aqc111: Add bind and empty unbind callbacks

Initialize net_device_ops structure

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 96aca929b570..a2628856c580 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -14,8 +14,43 @@
 #include <linux/usb/cdc.h>
 #include <linux/usb/usbnet.h>
 
+static const struct net_device_ops aqc111_netdev_ops = {
+	.ndo_open		= usbnet_open,
+	.ndo_stop		= usbnet_stop,
+};
+
+static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+	struct usb_device *udev = interface_to_usbdev(intf);
+	int ret;
+
+	/* Check if vendor configuration */
+	if (udev->actconfig->desc.bConfigurationValue != 1) {
+		usb_driver_set_configuration(udev, 1);
+		return -ENODEV;
+	}
+
+	usb_reset_configuration(dev->udev);
+
+	ret = usbnet_get_endpoints(dev, intf);
+	if (ret < 0) {
+		netdev_dbg(dev->net, "usbnet_get_endpoints failed");
+		return ret;
+	}
+
+	dev->net->netdev_ops = &aqc111_netdev_ops;
+
+	return 0;
+}
+
+static void aqc111_unbind(struct usbnet *dev, struct usb_interface *intf)
+{
+}
+
 static const struct driver_info aqc111_info = {
 	.description	= "Aquantia AQtion USB to 5GbE Controller",
+	.bind		= aqc111_bind,
+	.unbind		= aqc111_unbind,
 };
 
 #define AQC111_USB_ETH_DEV(vid, pid, table) \
-- 
cgit v1.2.3


From 619fcb4487959ad5238af1adb13c331dc6945072 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:04 +0000
Subject: net: usb: aqc111: Add implementation of read and write commands

Read/write command register defines and functions

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/usb/aqc111.h | 18 ++++++++++
 2 files changed, 110 insertions(+)
 create mode 100644 drivers/net/usb/aqc111.h

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index a2628856c580..fbd48b8a6944 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -14,6 +14,98 @@
 #include <linux/usb/cdc.h>
 #include <linux/usb/usbnet.h>
 
+#include "aqc111.h"
+
+static int aqc111_read_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value,
+				u16 index, u16 size, void *data)
+{
+	int ret;
+
+	ret = usbnet_read_cmd_nopm(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR |
+				   USB_RECIP_DEVICE, value, index, data, size);
+
+	if (unlikely(ret < 0))
+		netdev_warn(dev->net,
+			    "Failed to read(0x%x) reg index 0x%04x: %d\n",
+			    cmd, index, ret);
+
+	return ret;
+}
+
+static int aqc111_read_cmd(struct usbnet *dev, u8 cmd, u16 value,
+			   u16 index, u16 size, void *data)
+{
+	int ret;
+
+	ret = usbnet_read_cmd(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR |
+			      USB_RECIP_DEVICE, value, index, data, size);
+
+	if (unlikely(ret < 0))
+		netdev_warn(dev->net,
+			    "Failed to read(0x%x) reg index 0x%04x: %d\n",
+			    cmd, index, ret);
+
+	return ret;
+}
+
+static int __aqc111_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
+			      u16 value, u16 index, u16 size, const void *data)
+{
+	int err = -ENOMEM;
+	void *buf = NULL;
+
+	netdev_dbg(dev->net,
+		   "%s cmd=%#x reqtype=%#x value=%#x index=%#x size=%d\n",
+		   __func__, cmd, reqtype, value, index, size);
+
+	if (data) {
+		buf = kmemdup(data, size, GFP_KERNEL);
+		if (!buf)
+			goto out;
+	}
+
+	err = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
+			      cmd, reqtype, value, index, buf, size,
+			      (cmd == AQ_PHY_POWER) ? AQ_USB_PHY_SET_TIMEOUT :
+			      AQ_USB_SET_TIMEOUT);
+
+	if (unlikely(err < 0))
+		netdev_warn(dev->net,
+			    "Failed to write(0x%x) reg index 0x%04x: %d\n",
+			    cmd, index, err);
+	kfree(buf);
+
+out:
+	return err;
+}
+
+static int aqc111_write_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value,
+				 u16 index, u16 size, void *data)
+{
+	int ret;
+
+	ret = __aqc111_write_cmd(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR |
+				 USB_RECIP_DEVICE, value, index, size, data);
+
+	return ret;
+}
+
+static int aqc111_write_cmd(struct usbnet *dev, u8 cmd, u16 value,
+			    u16 index, u16 size, void *data)
+{
+	int ret;
+
+	if (usb_autopm_get_interface(dev->intf) < 0)
+		return -ENODEV;
+
+	ret = __aqc111_write_cmd(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR |
+				 USB_RECIP_DEVICE, value, index, size, data);
+
+	usb_autopm_put_interface(dev->intf);
+
+	return ret;
+}
+
 static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_open		= usbnet_open,
 	.ndo_stop		= usbnet_stop,
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
new file mode 100644
index 000000000000..f4302f7f0cc3
--- /dev/null
+++ b/drivers/net/usb/aqc111.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later
+ * Aquantia Corp. Aquantia AQtion USB to 5GbE Controller
+ * Copyright (C) 2003-2005 David Hollis <dhollis@davehollis.com>
+ * Copyright (C) 2005 Phil Chang <pchang23@sbcglobal.net>
+ * Copyright (C) 2002-2003 TiVo Inc.
+ * Copyright (C) 2017-2018 ASIX
+ * Copyright (C) 2018 Aquantia Corp.
+ */
+
+#ifndef __LINUX_USBNET_AQC111_H
+#define __LINUX_USBNET_AQC111_H
+
+#define AQ_PHY_POWER			0x31
+
+#define AQ_USB_PHY_SET_TIMEOUT		10000
+#define AQ_USB_SET_TIMEOUT		4000
+
+#endif /* __LINUX_USBNET_AQC111_H */
-- 
cgit v1.2.3


From f3aa095ac7ba2ef35ab7cfae52a7ee476723c155 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:07 +0000
Subject: net: usb: aqc111: Various callbacks implementation

Reset, stop callbacks, driver unbind callback.
More register defines required for these callbacks.
Add helpers to read/write 16bit values

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c |  76 +++++++++++++++++++++++++++++++++++
 drivers/net/usb/aqc111.h | 101 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 177 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index fbd48b8a6944..75849714abfa 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -48,6 +48,17 @@ static int aqc111_read_cmd(struct usbnet *dev, u8 cmd, u16 value,
 	return ret;
 }
 
+static int aqc111_read16_cmd(struct usbnet *dev, u8 cmd, u16 value,
+			     u16 index, u16 *data)
+{
+	int ret = 0;
+
+	ret = aqc111_read_cmd(dev, cmd, value, index, sizeof(*data), data);
+	le16_to_cpus(data);
+
+	return ret;
+}
+
 static int __aqc111_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 			      u16 value, u16 index, u16 size, const void *data)
 {
@@ -106,6 +117,26 @@ static int aqc111_write_cmd(struct usbnet *dev, u8 cmd, u16 value,
 	return ret;
 }
 
+static int aqc111_write16_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value,
+				   u16 index, u16 *data)
+{
+	u16 tmp = *data;
+
+	cpu_to_le16s(&tmp);
+
+	return aqc111_write_cmd_nopm(dev, cmd, value, index, sizeof(tmp), &tmp);
+}
+
+static int aqc111_write16_cmd(struct usbnet *dev, u8 cmd, u16 value,
+			      u16 index, u16 *data)
+{
+	u16 tmp = *data;
+
+	cpu_to_le16s(&tmp);
+
+	return aqc111_write_cmd(dev, cmd, value, index, sizeof(tmp), &tmp);
+}
+
 static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_open		= usbnet_open,
 	.ndo_stop		= usbnet_stop,
@@ -137,12 +168,57 @@ static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 
 static void aqc111_unbind(struct usbnet *dev, struct usb_interface *intf)
 {
+	u16 reg16;
+
+	/* Force bz */
+	reg16 = SFR_PHYPWR_RSTCTL_BZ;
+	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_PHYPWR_RSTCTL,
+				2, &reg16);
+	reg16 = 0;
+	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_PHYPWR_RSTCTL,
+				2, &reg16);
+}
+
+static int aqc111_reset(struct usbnet *dev)
+{
+	u8 reg8 = 0;
+
+	reg8 = 0xFF;
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_BM_INT_MASK, 1, 1, &reg8);
+
+	reg8 = 0x0;
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_SWP_CTRL, 1, 1, &reg8);
+
+	aqc111_read_cmd(dev, AQ_ACCESS_MAC, SFR_MONITOR_MODE, 1, 1, &reg8);
+	reg8 &= ~(SFR_MONITOR_MODE_EPHYRW | SFR_MONITOR_MODE_RWLC |
+		  SFR_MONITOR_MODE_RWMP | SFR_MONITOR_MODE_RWWF |
+		  SFR_MONITOR_MODE_RW_FLAG);
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_MONITOR_MODE, 1, 1, &reg8);
+
+	return 0;
+}
+
+static int aqc111_stop(struct usbnet *dev)
+{
+	u16 reg16 = 0;
+
+	aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+			  2, &reg16);
+	reg16 &= ~SFR_MEDIUM_RECEIVE_EN;
+	aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+			   2, &reg16);
+	reg16 = 0;
+	aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
+
+	return 0;
 }
 
 static const struct driver_info aqc111_info = {
 	.description	= "Aquantia AQtion USB to 5GbE Controller",
 	.bind		= aqc111_bind,
 	.unbind		= aqc111_unbind,
+	.reset		= aqc111_reset,
+	.stop		= aqc111_stop,
 };
 
 #define AQC111_USB_ETH_DEV(vid, pid, table) \
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index f4302f7f0cc3..a252ccd78559 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -10,9 +10,110 @@
 #ifndef __LINUX_USBNET_AQC111_H
 #define __LINUX_USBNET_AQC111_H
 
+#define AQ_ACCESS_MAC			0x01
 #define AQ_PHY_POWER			0x31
 
 #define AQ_USB_PHY_SET_TIMEOUT		10000
 #define AQ_USB_SET_TIMEOUT		4000
 
+/* SFR Reg. ********************************************/
+
+#define SFR_GENERAL_STATUS		0x03
+#define SFR_CHIP_STATUS			0x05
+#define SFR_RX_CTL			0x0B
+	#define SFR_RX_CTL_TXPADCRC		0x0400
+	#define SFR_RX_CTL_IPE			0x0200
+	#define SFR_RX_CTL_DROPCRCERR		0x0100
+	#define SFR_RX_CTL_START		0x0080
+	#define SFR_RX_CTL_RF_WAK		0x0040
+	#define SFR_RX_CTL_AP			0x0020
+	#define SFR_RX_CTL_AM			0x0010
+	#define SFR_RX_CTL_AB			0x0008
+	#define SFR_RX_CTL_AMALL		0x0002
+	#define SFR_RX_CTL_PRO			0x0001
+	#define SFR_RX_CTL_STOP			0x0000
+#define SFR_INTER_PACKET_GAP_0		0x0D
+#define SFR_NODE_ID			0x10
+#define SFR_MULTI_FILTER_ARRY		0x16
+#define SFR_MEDIUM_STATUS_MODE		0x22
+	#define SFR_MEDIUM_XGMIIMODE		0x0001
+	#define SFR_MEDIUM_FULL_DUPLEX		0x0002
+	#define SFR_MEDIUM_RXFLOW_CTRLEN	0x0010
+	#define SFR_MEDIUM_TXFLOW_CTRLEN	0x0020
+	#define SFR_MEDIUM_JUMBO_EN		0x0040
+	#define SFR_MEDIUM_RECEIVE_EN		0x0100
+#define SFR_MONITOR_MODE		0x24
+	#define SFR_MONITOR_MODE_EPHYRW		0x01
+	#define SFR_MONITOR_MODE_RWLC		0x02
+	#define SFR_MONITOR_MODE_RWMP		0x04
+	#define SFR_MONITOR_MODE_RWWF		0x08
+	#define SFR_MONITOR_MODE_RW_FLAG	0x10
+	#define SFR_MONITOR_MODE_PMEPOL		0x20
+	#define SFR_MONITOR_MODE_PMETYPE	0x40
+#define SFR_PHYPWR_RSTCTL		0x26
+	#define SFR_PHYPWR_RSTCTL_BZ		0x0010
+	#define SFR_PHYPWR_RSTCTL_IPRL		0x0020
+#define SFR_VLAN_ID_ADDRESS		0x2A
+#define SFR_VLAN_ID_CONTROL		0x2B
+	#define SFR_VLAN_CONTROL_WE		0x0001
+	#define SFR_VLAN_CONTROL_RD		0x0002
+	#define SFR_VLAN_CONTROL_VSO		0x0010
+	#define SFR_VLAN_CONTROL_VFE		0x0020
+#define SFR_VLAN_ID_DATA0		0x2C
+#define SFR_VLAN_ID_DATA1		0x2D
+#define SFR_RX_BULKIN_QCTRL		0x2E
+	#define SFR_RX_BULKIN_QCTRL_TIME	0x01
+	#define SFR_RX_BULKIN_QCTRL_IFG		0x02
+	#define SFR_RX_BULKIN_QCTRL_SIZE	0x04
+#define SFR_RX_BULKIN_QTIMR_LOW		0x2F
+#define SFR_RX_BULKIN_QTIMR_HIGH	0x30
+#define SFR_RX_BULKIN_QSIZE		0x31
+#define SFR_RX_BULKIN_QIFG		0x32
+#define SFR_RXCOE_CTL			0x34
+	#define SFR_RXCOE_IP			0x01
+	#define SFR_RXCOE_TCP			0x02
+	#define SFR_RXCOE_UDP			0x04
+	#define SFR_RXCOE_ICMP			0x08
+	#define SFR_RXCOE_IGMP			0x10
+	#define SFR_RXCOE_TCPV6			0x20
+	#define SFR_RXCOE_UDPV6			0x40
+	#define SFR_RXCOE_ICMV6			0x80
+#define SFR_TXCOE_CTL			0x35
+	#define SFR_TXCOE_IP			0x01
+	#define SFR_TXCOE_TCP			0x02
+	#define SFR_TXCOE_UDP			0x04
+	#define SFR_TXCOE_ICMP			0x08
+	#define SFR_TXCOE_IGMP			0x10
+	#define SFR_TXCOE_TCPV6			0x20
+	#define SFR_TXCOE_UDPV6			0x40
+	#define SFR_TXCOE_ICMV6			0x80
+#define SFR_BM_INT_MASK			0x41
+#define SFR_BMRX_DMA_CONTROL		0x43
+	#define SFR_BMRX_DMA_EN			0x80
+#define SFR_BMTX_DMA_CONTROL		0x46
+#define SFR_PAUSE_WATERLVL_LOW		0x54
+#define SFR_PAUSE_WATERLVL_HIGH		0x55
+#define SFR_ARC_CTRL			0x9E
+#define SFR_SWP_CTRL			0xB1
+#define SFR_TX_PAUSE_RESEND_T		0xB2
+#define SFR_ETH_MAC_PATH		0xB7
+	#define SFR_RX_PATH_READY		0x01
+#define SFR_BULK_OUT_CTRL		0xB9
+	#define SFR_BULK_OUT_FLUSH_EN		0x01
+	#define SFR_BULK_OUT_EFF_EN		0x02
+
+static struct {
+	unsigned char ctrl;
+	unsigned char timer_l;
+	unsigned char timer_h;
+	unsigned char size;
+	unsigned char ifg;
+} AQC111_BULKIN_SIZE[] = {
+	/* xHCI & EHCI & OHCI */
+	{7, 0x00, 0x01, 0x1E, 0xFF},/* 10G, 5G, 2.5G, 1G */
+	{7, 0xA0, 0x00, 0x14, 0x00},/* 100M */
+	/* Jumbo packet */
+	{7, 0x00, 0x01, 0x18, 0xFF},
+};
+
 #endif /* __LINUX_USBNET_AQC111_H */
-- 
cgit v1.2.3


From 33cd597fbfe00d80ce9762fdec8a296b0bc2bfe6 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:09 +0000
Subject: net: usb: aqc111: Introduce PHY access

Add helpers to write 32bit values.
Implement PHY power up/down sequences.
AQC111, PHY is being controlled via vendor command interface.

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/usb/aqc111.h | 33 ++++++++++++++++++++++++
 2 files changed, 98 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 75849714abfa..e277209df616 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -137,14 +137,49 @@ static int aqc111_write16_cmd(struct usbnet *dev, u8 cmd, u16 value,
 	return aqc111_write_cmd(dev, cmd, value, index, sizeof(tmp), &tmp);
 }
 
+static int aqc111_write32_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value,
+				   u16 index, u32 *data)
+{
+	u32 tmp = *data;
+
+	cpu_to_le32s(&tmp);
+
+	return aqc111_write_cmd_nopm(dev, cmd, value, index, sizeof(tmp), &tmp);
+}
+
+static int aqc111_write32_cmd(struct usbnet *dev, u8 cmd, u16 value,
+			      u16 index, u32 *data)
+{
+	u32 tmp = *data;
+
+	cpu_to_le32s(&tmp);
+
+	return aqc111_write_cmd(dev, cmd, value, index, sizeof(tmp), &tmp);
+}
+
 static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_open		= usbnet_open,
 	.ndo_stop		= usbnet_stop,
 };
 
+static void aqc111_read_fw_version(struct usbnet *dev,
+				   struct aqc111_data *aqc111_data)
+{
+	aqc111_read_cmd(dev, AQ_ACCESS_MAC, AQ_FW_VER_MAJOR,
+			1, 1, &aqc111_data->fw_ver.major);
+	aqc111_read_cmd(dev, AQ_ACCESS_MAC, AQ_FW_VER_MINOR,
+			1, 1, &aqc111_data->fw_ver.minor);
+	aqc111_read_cmd(dev, AQ_ACCESS_MAC, AQ_FW_VER_REV,
+			1, 1, &aqc111_data->fw_ver.rev);
+
+	if (aqc111_data->fw_ver.major & 0x80)
+		aqc111_data->fw_ver.major &= ~0x80;
+}
+
 static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
+	struct aqc111_data *aqc111_data;
 	int ret;
 
 	/* Check if vendor configuration */
@@ -161,13 +196,23 @@ static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 		return ret;
 	}
 
+	aqc111_data = kzalloc(sizeof(*aqc111_data), GFP_KERNEL);
+	if (!aqc111_data)
+		return -ENOMEM;
+
+	/* store aqc111_data pointer in device data field */
+	dev->driver_priv = aqc111_data;
+
 	dev->net->netdev_ops = &aqc111_netdev_ops;
 
+	aqc111_read_fw_version(dev, aqc111_data);
+
 	return 0;
 }
 
 static void aqc111_unbind(struct usbnet *dev, struct usb_interface *intf)
 {
+	struct aqc111_data *aqc111_data = dev->driver_priv;
 	u16 reg16;
 
 	/* Force bz */
@@ -177,12 +222,26 @@ static void aqc111_unbind(struct usbnet *dev, struct usb_interface *intf)
 	reg16 = 0;
 	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_PHYPWR_RSTCTL,
 				2, &reg16);
+
+	/* Power down ethernet PHY */
+	aqc111_data->phy_cfg |= AQ_LOW_POWER;
+	aqc111_data->phy_cfg &= ~AQ_PHY_POWER_EN;
+	aqc111_write32_cmd_nopm(dev, AQ_PHY_OPS, 0, 0,
+				&aqc111_data->phy_cfg);
+
+	kfree(aqc111_data);
 }
 
 static int aqc111_reset(struct usbnet *dev)
 {
+	struct aqc111_data *aqc111_data = dev->driver_priv;
 	u8 reg8 = 0;
 
+	/* Power up ethernet PHY */
+	aqc111_data->phy_cfg = AQ_PHY_POWER_EN;
+	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
+			   &aqc111_data->phy_cfg);
+
 	reg8 = 0xFF;
 	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_BM_INT_MASK, 1, 1, &reg8);
 
@@ -200,6 +259,7 @@ static int aqc111_reset(struct usbnet *dev)
 
 static int aqc111_stop(struct usbnet *dev)
 {
+	struct aqc111_data *aqc111_data = dev->driver_priv;
 	u16 reg16 = 0;
 
 	aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
@@ -210,6 +270,11 @@ static int aqc111_stop(struct usbnet *dev)
 	reg16 = 0;
 	aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
 
+	/* Put PHY to low power*/
+	aqc111_data->phy_cfg |= AQ_LOW_POWER;
+	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
+			   &aqc111_data->phy_cfg);
+
 	return 0;
 }
 
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index a252ccd78559..a93d34af76b9 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -12,6 +12,7 @@
 
 #define AQ_ACCESS_MAC			0x01
 #define AQ_PHY_POWER			0x31
+#define AQ_PHY_OPS			0x61
 
 #define AQ_USB_PHY_SET_TIMEOUT		10000
 #define AQ_USB_SET_TIMEOUT		4000
@@ -102,6 +103,38 @@
 	#define SFR_BULK_OUT_FLUSH_EN		0x01
 	#define SFR_BULK_OUT_EFF_EN		0x02
 
+#define AQ_FW_VER_MAJOR			0xDA
+#define AQ_FW_VER_MINOR			0xDB
+#define AQ_FW_VER_REV			0xDC
+
+/*PHY_OPS**********************************************************************/
+
+#define AQ_ADV_100M	BIT(0)
+#define AQ_ADV_1G	BIT(1)
+#define AQ_ADV_2G5	BIT(2)
+#define AQ_ADV_5G	BIT(3)
+
+#define AQ_PAUSE	BIT(16)
+#define AQ_ASYM_PAUSE	BIT(17)
+#define AQ_LOW_POWER	BIT(18)
+#define AQ_PHY_POWER_EN	BIT(19)
+#define AQ_WOL		BIT(20)
+#define AQ_DOWNSHIFT	BIT(21)
+
+#define AQ_DSH_RETRIES_SHIFT	0x18
+#define AQ_DSH_RETRIES_MASK	0xF000000
+
+/******************************************************************************/
+
+struct aqc111_data {
+	struct {
+		u8 major;
+		u8 minor;
+		u8 rev;
+	} fw_ver;
+	u32 phy_cfg;
+};
+
 static struct {
 	unsigned char ctrl;
 	unsigned char timer_l;
-- 
cgit v1.2.3


From 7b8b06544ab03553022ea77736203d3502de6415 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:12 +0000
Subject: net: usb: aqc111: Introduce link management

Add full hardware initialization sequence and link configuration logic

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 235 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/usb/aqc111.h |  13 +++
 2 files changed, 248 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index e277209df616..e33be16b506c 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -157,6 +157,53 @@ static int aqc111_write32_cmd(struct usbnet *dev, u8 cmd, u16 value,
 	return aqc111_write_cmd(dev, cmd, value, index, sizeof(tmp), &tmp);
 }
 
+static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
+{
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+
+	aqc111_data->phy_cfg &= ~AQ_ADV_MASK;
+	aqc111_data->phy_cfg |= AQ_PAUSE;
+	aqc111_data->phy_cfg |= AQ_ASYM_PAUSE;
+	aqc111_data->phy_cfg |= AQ_DOWNSHIFT;
+	aqc111_data->phy_cfg &= ~AQ_DSH_RETRIES_MASK;
+	aqc111_data->phy_cfg |= (3 << AQ_DSH_RETRIES_SHIFT) &
+				AQ_DSH_RETRIES_MASK;
+
+	if (autoneg == AUTONEG_ENABLE) {
+		switch (speed) {
+		case SPEED_5000:
+			aqc111_data->phy_cfg |= AQ_ADV_5G;
+			/* fall-through */
+		case SPEED_2500:
+			aqc111_data->phy_cfg |= AQ_ADV_2G5;
+			/* fall-through */
+		case SPEED_1000:
+			aqc111_data->phy_cfg |= AQ_ADV_1G;
+			/* fall-through */
+		case SPEED_100:
+			aqc111_data->phy_cfg |= AQ_ADV_100M;
+			/* fall-through */
+		}
+	} else {
+		switch (speed) {
+		case SPEED_5000:
+			aqc111_data->phy_cfg |= AQ_ADV_5G;
+			break;
+		case SPEED_2500:
+			aqc111_data->phy_cfg |= AQ_ADV_2G5;
+			break;
+		case SPEED_1000:
+			aqc111_data->phy_cfg |= AQ_ADV_1G;
+			break;
+		case SPEED_100:
+			aqc111_data->phy_cfg |= AQ_ADV_100M;
+			break;
+		}
+	}
+
+	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0, &aqc111_data->phy_cfg);
+}
+
 static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_open		= usbnet_open,
 	.ndo_stop		= usbnet_stop,
@@ -179,6 +226,7 @@ static void aqc111_read_fw_version(struct usbnet *dev,
 static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
+	enum usb_device_speed usb_speed = udev->speed;
 	struct aqc111_data *aqc111_data;
 	int ret;
 
@@ -206,6 +254,9 @@ static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->netdev_ops = &aqc111_netdev_ops;
 
 	aqc111_read_fw_version(dev, aqc111_data);
+	aqc111_data->autoneg = AUTONEG_ENABLE;
+	aqc111_data->advertised_speed = (usb_speed == USB_SPEED_SUPER) ?
+					 SPEED_5000 : SPEED_1000;
 
 	return 0;
 }
@@ -224,6 +275,7 @@ static void aqc111_unbind(struct usbnet *dev, struct usb_interface *intf)
 				2, &reg16);
 
 	/* Power down ethernet PHY */
+	aqc111_data->phy_cfg &= ~AQ_ADV_MASK;
 	aqc111_data->phy_cfg |= AQ_LOW_POWER;
 	aqc111_data->phy_cfg &= ~AQ_PHY_POWER_EN;
 	aqc111_write32_cmd_nopm(dev, AQ_PHY_OPS, 0, 0,
@@ -232,6 +284,179 @@ static void aqc111_unbind(struct usbnet *dev, struct usb_interface *intf)
 	kfree(aqc111_data);
 }
 
+static void aqc111_status(struct usbnet *dev, struct urb *urb)
+{
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+	u64 *event_data = NULL;
+	int link = 0;
+
+	if (urb->actual_length < sizeof(*event_data))
+		return;
+
+	event_data = urb->transfer_buffer;
+	le64_to_cpus(event_data);
+
+	if (*event_data & AQ_LS_MASK)
+		link = 1;
+	else
+		link = 0;
+
+	aqc111_data->link_speed = (*event_data & AQ_SPEED_MASK) >>
+				  AQ_SPEED_SHIFT;
+	aqc111_data->link = link;
+
+	if (netif_carrier_ok(dev->net) != link)
+		usbnet_defer_kevent(dev, EVENT_LINK_RESET);
+}
+
+static void aqc111_configure_rx(struct usbnet *dev,
+				struct aqc111_data *aqc111_data)
+{
+	enum usb_device_speed usb_speed = dev->udev->speed;
+	u16 link_speed = 0, usb_host = 0;
+	u8 buf[5] = { 0 };
+	u8 queue_num = 0;
+	u16 reg16 = 0;
+	u8 reg8 = 0;
+
+	buf[0] = 0x00;
+	buf[1] = 0xF8;
+	buf[2] = 0x07;
+	switch (aqc111_data->link_speed) {
+	case AQ_INT_SPEED_5G:
+		link_speed = 5000;
+		reg8 = 0x05;
+		reg16 = 0x001F;
+		break;
+	case AQ_INT_SPEED_2_5G:
+		link_speed = 2500;
+		reg16 = 0x003F;
+		break;
+	case AQ_INT_SPEED_1G:
+		link_speed = 1000;
+		reg16 = 0x009F;
+		break;
+	case AQ_INT_SPEED_100M:
+		link_speed = 100;
+		queue_num = 1;
+		reg16 = 0x063F;
+		buf[1] = 0xFB;
+		buf[2] = 0x4;
+		break;
+	}
+
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_INTER_PACKET_GAP_0,
+			 1, 1, &reg8);
+
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_TX_PAUSE_RESEND_T, 3, 3, buf);
+
+	switch (usb_speed) {
+	case USB_SPEED_SUPER:
+		usb_host = 3;
+		break;
+	case USB_SPEED_HIGH:
+		usb_host = 2;
+		break;
+	case USB_SPEED_FULL:
+	case USB_SPEED_LOW:
+		usb_host = 1;
+		queue_num = 0;
+		break;
+	default:
+		usb_host = 0;
+		break;
+	}
+
+	memcpy(buf, &AQC111_BULKIN_SIZE[queue_num], 5);
+	/* RX bulk configuration */
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_RX_BULKIN_QCTRL, 5, 5, buf);
+
+	/* Set high low water level */
+	reg16 = 0x0810;
+
+	aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_PAUSE_WATERLVL_LOW,
+			   2, &reg16);
+	netdev_info(dev->net, "Link Speed %d, USB %d", link_speed, usb_host);
+}
+
+static int aqc111_link_reset(struct usbnet *dev)
+{
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+	u16 reg16 = 0;
+	u8 reg8 = 0;
+
+	if (aqc111_data->link == 1) { /* Link up */
+		aqc111_configure_rx(dev, aqc111_data);
+
+		/* Vlan Tag Filter */
+		reg8 = SFR_VLAN_CONTROL_VSO;
+
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_CONTROL,
+				 1, 1, &reg8);
+
+		reg8 = 0x0;
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_BMRX_DMA_CONTROL,
+				 1, 1, &reg8);
+
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_BMTX_DMA_CONTROL,
+				 1, 1, &reg8);
+
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_ARC_CTRL, 1, 1, &reg8);
+
+		reg16 = SFR_RX_CTL_IPE | SFR_RX_CTL_AB;
+		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
+
+		reg8 = SFR_RX_PATH_READY;
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_ETH_MAC_PATH,
+				 1, 1, &reg8);
+
+		reg8 = SFR_BULK_OUT_EFF_EN;
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_BULK_OUT_CTRL,
+				 1, 1, &reg8);
+
+		reg16 = 0;
+		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+				   2, &reg16);
+
+		reg16 = SFR_MEDIUM_XGMIIMODE | SFR_MEDIUM_FULL_DUPLEX;
+		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+				   2, &reg16);
+
+		aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+				  2, &reg16);
+
+		reg16 |= SFR_MEDIUM_RECEIVE_EN | SFR_MEDIUM_RXFLOW_CTRLEN |
+			 SFR_MEDIUM_TXFLOW_CTRLEN;
+		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+				   2, &reg16);
+
+		reg16 = SFR_RX_CTL_IPE | SFR_RX_CTL_AB | SFR_RX_CTL_START;
+		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
+
+		netif_carrier_on(dev->net);
+	} else {
+		aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+				  2, &reg16);
+		reg16 &= ~SFR_MEDIUM_RECEIVE_EN;
+		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+				   2, &reg16);
+
+		aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
+		reg16 &= ~SFR_RX_CTL_START;
+		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
+
+		reg8 = SFR_BULK_OUT_FLUSH_EN | SFR_BULK_OUT_EFF_EN;
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_BULK_OUT_CTRL,
+				 1, 1, &reg8);
+		reg8 = SFR_BULK_OUT_EFF_EN;
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_BULK_OUT_CTRL,
+				 1, 1, &reg8);
+
+		netif_carrier_off(dev->net);
+	}
+	return 0;
+}
+
 static int aqc111_reset(struct usbnet *dev)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
@@ -254,6 +479,12 @@ static int aqc111_reset(struct usbnet *dev)
 		  SFR_MONITOR_MODE_RW_FLAG);
 	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_MONITOR_MODE, 1, 1, &reg8);
 
+	netif_carrier_off(dev->net);
+
+	/* Phy advertise */
+	aqc111_set_phy_speed(dev, aqc111_data->autoneg,
+			     aqc111_data->advertised_speed);
+
 	return 0;
 }
 
@@ -275,6 +506,8 @@ static int aqc111_stop(struct usbnet *dev)
 	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
 			   &aqc111_data->phy_cfg);
 
+	netif_carrier_off(dev->net);
+
 	return 0;
 }
 
@@ -282,6 +515,8 @@ static const struct driver_info aqc111_info = {
 	.description	= "Aquantia AQtion USB to 5GbE Controller",
 	.bind		= aqc111_bind,
 	.unbind		= aqc111_unbind,
+	.status		= aqc111_status,
+	.link_reset	= aqc111_link_reset,
 	.reset		= aqc111_reset,
 	.stop		= aqc111_stop,
 };
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index a93d34af76b9..f3b45d8ca4e3 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -113,6 +113,7 @@
 #define AQ_ADV_1G	BIT(1)
 #define AQ_ADV_2G5	BIT(2)
 #define AQ_ADV_5G	BIT(3)
+#define AQ_ADV_MASK	0x0F
 
 #define AQ_PAUSE	BIT(16)
 #define AQ_ASYM_PAUSE	BIT(17)
@@ -127,6 +128,10 @@
 /******************************************************************************/
 
 struct aqc111_data {
+	u8 link_speed;
+	u8 link;
+	u8 autoneg;
+	u32 advertised_speed;
 	struct {
 		u8 major;
 		u8 minor;
@@ -135,6 +140,14 @@ struct aqc111_data {
 	u32 phy_cfg;
 };
 
+#define AQ_LS_MASK		0x8000
+#define AQ_SPEED_MASK		0x7F00
+#define AQ_SPEED_SHIFT		0x0008
+#define AQ_INT_SPEED_5G		0x000F
+#define AQ_INT_SPEED_2_5G	0x0010
+#define AQ_INT_SPEED_1G		0x0011
+#define AQ_INT_SPEED_100M	0x0013
+
 static struct {
 	unsigned char ctrl;
 	unsigned char timer_l;
-- 
cgit v1.2.3


From df2d59a2ab6c9ceac2c4104272fce03493b8f62f Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:14 +0000
Subject: net: usb: aqc111: Add support for getting and setting of MAC address

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/usb/aqc111.h |  1 +
 2 files changed, 48 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index e33be16b506c..390ed6cbc3fd 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <linux/mii.h>
 #include <linux/usb.h>
+#include <linux/if_vlan.h>
 #include <linux/usb/cdc.h>
 #include <linux/usb/usbnet.h>
 
@@ -204,11 +205,43 @@ static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0, &aqc111_data->phy_cfg);
 }
 
+static int aqc111_set_mac_addr(struct net_device *net, void *p)
+{
+	struct usbnet *dev = netdev_priv(net);
+	int ret = 0;
+
+	ret = eth_mac_addr(net, p);
+	if (ret < 0)
+		return ret;
+
+	/* Set the MAC address */
+	return aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_NODE_ID, ETH_ALEN,
+				ETH_ALEN, net->dev_addr);
+}
+
 static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_open		= usbnet_open,
 	.ndo_stop		= usbnet_stop,
+	.ndo_set_mac_address	= aqc111_set_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
 };
 
+static int aqc111_read_perm_mac(struct usbnet *dev)
+{
+	u8 buf[ETH_ALEN];
+	int ret;
+
+	ret = aqc111_read_cmd(dev, AQ_FLASH_PARAMETERS, 0, 0, ETH_ALEN, buf);
+	if (ret < 0)
+		goto out;
+
+	ether_addr_copy(dev->net->perm_addr, buf);
+
+	return 0;
+out:
+	return ret;
+}
+
 static void aqc111_read_fw_version(struct usbnet *dev,
 				   struct aqc111_data *aqc111_data)
 {
@@ -251,6 +284,12 @@ static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 	/* store aqc111_data pointer in device data field */
 	dev->driver_priv = aqc111_data;
 
+	/* Init the MAC address */
+	ret = aqc111_read_perm_mac(dev);
+	if (ret)
+		goto out;
+
+	ether_addr_copy(dev->net->dev_addr, dev->net->perm_addr);
 	dev->net->netdev_ops = &aqc111_netdev_ops;
 
 	aqc111_read_fw_version(dev, aqc111_data);
@@ -259,6 +298,10 @@ static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 					 SPEED_5000 : SPEED_1000;
 
 	return 0;
+
+out:
+	kfree(aqc111_data);
+	return ret;
 }
 
 static void aqc111_unbind(struct usbnet *dev, struct usb_interface *intf)
@@ -467,6 +510,10 @@ static int aqc111_reset(struct usbnet *dev)
 	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
 			   &aqc111_data->phy_cfg);
 
+	/* Set the MAC address */
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_NODE_ID, ETH_ALEN,
+			 ETH_ALEN, dev->net->dev_addr);
+
 	reg8 = 0xFF;
 	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_BM_INT_MASK, 1, 1, &reg8);
 
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index f3b45d8ca4e3..0c8e1ee29893 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -11,6 +11,7 @@
 #define __LINUX_USBNET_AQC111_H
 
 #define AQ_ACCESS_MAC			0x01
+#define AQ_FLASH_PARAMETERS		0x20
 #define AQ_PHY_POWER			0x31
 #define AQ_PHY_OPS			0x61
 
-- 
cgit v1.2.3


From 4a3576d2bcc755475890e2db717cab0effb1f140 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:16 +0000
Subject: net: usb: aqc111: Implement TX data path

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/usb/aqc111.h |  8 ++++++
 2 files changed, 80 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 390ed6cbc3fd..32a2de74ef3f 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -222,6 +222,9 @@ static int aqc111_set_mac_addr(struct net_device *net, void *p)
 static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_open		= usbnet_open,
 	.ndo_stop		= usbnet_stop,
+	.ndo_start_xmit		= usbnet_start_xmit,
+	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address	= aqc111_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
@@ -290,8 +293,19 @@ static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 		goto out;
 
 	ether_addr_copy(dev->net->dev_addr, dev->net->perm_addr);
+
+	/* Set TX needed headroom & tailroom */
+	dev->net->needed_headroom += sizeof(u64);
+	dev->net->needed_tailroom += sizeof(u64);
+
 	dev->net->netdev_ops = &aqc111_netdev_ops;
 
+	if (usb_device_no_sg_constraint(dev->udev))
+		dev->can_dma_sg = 1;
+
+	dev->net->hw_features |= AQ_SUPPORT_HW_FEATURE;
+	dev->net->features |= AQ_SUPPORT_FEATURE;
+
 	aqc111_read_fw_version(dev, aqc111_data);
 	aqc111_data->autoneg = AUTONEG_ENABLE;
 	aqc111_data->advertised_speed = (usb_speed == USB_SPEED_SUPER) ?
@@ -505,6 +519,12 @@ static int aqc111_reset(struct usbnet *dev)
 	struct aqc111_data *aqc111_data = dev->driver_priv;
 	u8 reg8 = 0;
 
+	if (usb_device_no_sg_constraint(dev->udev))
+		dev->can_dma_sg = 1;
+
+	dev->net->hw_features |= AQ_SUPPORT_HW_FEATURE;
+	dev->net->features |= AQ_SUPPORT_FEATURE;
+
 	/* Power up ethernet PHY */
 	aqc111_data->phy_cfg = AQ_PHY_POWER_EN;
 	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
@@ -558,6 +578,55 @@ static int aqc111_stop(struct usbnet *dev)
 	return 0;
 }
 
+static struct sk_buff *aqc111_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
+				       gfp_t flags)
+{
+	int frame_size = dev->maxpacket;
+	struct sk_buff *new_skb = NULL;
+	u64 *tx_desc_ptr = NULL;
+	int padding_size = 0;
+	int headroom = 0;
+	int tailroom = 0;
+	u64 tx_desc = 0;
+
+	/*Length of actual data*/
+	tx_desc |= skb->len & AQ_TX_DESC_LEN_MASK;
+
+	headroom = (skb->len + sizeof(tx_desc)) % 8;
+	if (headroom != 0)
+		padding_size = 8 - headroom;
+
+	if (((skb->len + sizeof(tx_desc) + padding_size) % frame_size) == 0) {
+		padding_size += 8;
+		tx_desc |= AQ_TX_DESC_DROP_PADD;
+	}
+
+	if (!dev->can_dma_sg && (dev->net->features & NETIF_F_SG) &&
+	    skb_linearize(skb))
+		return NULL;
+
+	headroom = skb_headroom(skb);
+	tailroom = skb_tailroom(skb);
+
+	if (!(headroom >= sizeof(tx_desc) && tailroom >= padding_size)) {
+		new_skb = skb_copy_expand(skb, sizeof(tx_desc),
+					  padding_size, flags);
+		dev_kfree_skb_any(skb);
+		skb = new_skb;
+		if (!skb)
+			return NULL;
+	}
+	if (padding_size != 0)
+		skb_put_zero(skb, padding_size);
+	/* Copy TX header */
+	tx_desc_ptr = skb_push(skb, sizeof(tx_desc));
+	*tx_desc_ptr = cpu_to_le64(tx_desc);
+
+	usbnet_set_skb_tx_stats(skb, 1, 0);
+
+	return skb;
+}
+
 static const struct driver_info aqc111_info = {
 	.description	= "Aquantia AQtion USB to 5GbE Controller",
 	.bind		= aqc111_bind,
@@ -566,6 +635,9 @@ static const struct driver_info aqc111_info = {
 	.link_reset	= aqc111_link_reset,
 	.reset		= aqc111_reset,
 	.stop		= aqc111_stop,
+	.flags		= FLAG_ETHER | FLAG_FRAMING_AX |
+			  FLAG_AVOID_UNLINK_URBS | FLAG_MULTI_PACKET,
+	.tx_fixup	= aqc111_tx_fixup,
 };
 
 #define AQC111_USB_ETH_DEV(vid, pid, table) \
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index 0c8e1ee29893..c09f188b9f3d 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -18,6 +18,10 @@
 #define AQ_USB_PHY_SET_TIMEOUT		10000
 #define AQ_USB_SET_TIMEOUT		4000
 
+/* Feature. ********************************************/
+#define AQ_SUPPORT_FEATURE	(NETIF_F_SG)
+#define AQ_SUPPORT_HW_FEATURE	(NETIF_F_SG)
+
 /* SFR Reg. ********************************************/
 
 #define SFR_GENERAL_STATUS		0x03
@@ -149,6 +153,10 @@ struct aqc111_data {
 #define AQ_INT_SPEED_1G		0x0011
 #define AQ_INT_SPEED_100M	0x0013
 
+/* TX Descriptor */
+#define AQ_TX_DESC_LEN_MASK	0x1FFFFF
+#define AQ_TX_DESC_DROP_PADD	BIT(28)
+
 static struct {
 	unsigned char ctrl;
 	unsigned char timer_l;
-- 
cgit v1.2.3


From 361459cd9642631f048719169da9ef14cbf4a932 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:19 +0000
Subject: net: usb: aqc111: Implement RX data path

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/usb/aqc111.h |  15 +++++++
 2 files changed, 117 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 32a2de74ef3f..7a1976ecf294 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -294,6 +294,9 @@ static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 
 	ether_addr_copy(dev->net->dev_addr, dev->net->perm_addr);
 
+	/* Set Rx urb size */
+	dev->rx_urb_size = URB_SIZE;
+
 	/* Set TX needed headroom & tailroom */
 	dev->net->needed_headroom += sizeof(u64);
 	dev->net->needed_tailroom += sizeof(u64);
@@ -519,6 +522,8 @@ static int aqc111_reset(struct usbnet *dev)
 	struct aqc111_data *aqc111_data = dev->driver_priv;
 	u8 reg8 = 0;
 
+	dev->rx_urb_size = URB_SIZE;
+
 	if (usb_device_no_sg_constraint(dev->udev))
 		dev->can_dma_sg = 1;
 
@@ -578,6 +583,102 @@ static int aqc111_stop(struct usbnet *dev)
 	return 0;
 }
 
+static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+{
+	struct sk_buff *new_skb = NULL;
+	u32 pkt_total_offset = 0;
+	u64 *pkt_desc_ptr = NULL;
+	u32 start_of_descs = 0;
+	u32 desc_offset = 0; /*RX Header Offset*/
+	u16 pkt_count = 0;
+	u64 desc_hdr = 0;
+	u32 skb_len = 0;
+
+	if (!skb)
+		goto err;
+
+	if (skb->len == 0)
+		goto err;
+
+	skb_len = skb->len;
+	/* RX Descriptor Header */
+	skb_trim(skb, skb->len - sizeof(desc_hdr));
+	desc_hdr = le64_to_cpup((u64 *)skb_tail_pointer(skb));
+
+	/* Check these packets */
+	desc_offset = (desc_hdr & AQ_RX_DH_DESC_OFFSET_MASK) >>
+		      AQ_RX_DH_DESC_OFFSET_SHIFT;
+	pkt_count = desc_hdr & AQ_RX_DH_PKT_CNT_MASK;
+	start_of_descs = skb_len - ((pkt_count + 1) *  sizeof(desc_hdr));
+
+	/* self check descs position */
+	if (start_of_descs != desc_offset)
+		goto err;
+
+	/* self check desc_offset from header*/
+	if (desc_offset >= skb_len)
+		goto err;
+
+	if (pkt_count == 0)
+		goto err;
+
+	/* Get the first RX packet descriptor */
+	pkt_desc_ptr = (u64 *)(skb->data + desc_offset);
+
+	while (pkt_count--) {
+		u64 pkt_desc = le64_to_cpup(pkt_desc_ptr);
+		u32 pkt_len_with_padd = 0;
+		u32 pkt_len = 0;
+
+		pkt_len = (u32)((pkt_desc & AQ_RX_PD_LEN_MASK) >>
+			  AQ_RX_PD_LEN_SHIFT);
+		pkt_len_with_padd = ((pkt_len + 7) & 0x7FFF8);
+
+		pkt_total_offset += pkt_len_with_padd;
+		if (pkt_total_offset > desc_offset ||
+		    (pkt_count == 0 && pkt_total_offset != desc_offset)) {
+			goto err;
+		}
+
+		if (pkt_desc & AQ_RX_PD_DROP ||
+		    !(pkt_desc & AQ_RX_PD_RX_OK) ||
+		    pkt_len > (dev->hard_mtu + AQ_RX_HW_PAD)) {
+			skb_pull(skb, pkt_len_with_padd);
+			/* Next RX Packet Descriptor */
+			pkt_desc_ptr++;
+			continue;
+		}
+
+		/* Clone SKB */
+		new_skb = skb_clone(skb, GFP_ATOMIC);
+
+		if (!new_skb)
+			goto err;
+
+		new_skb->len = pkt_len;
+		skb_pull(new_skb, AQ_RX_HW_PAD);
+		skb_set_tail_pointer(new_skb, new_skb->len);
+
+		new_skb->truesize = SKB_TRUESIZE(new_skb->len);
+
+		usbnet_skb_return(dev, new_skb);
+		if (pkt_count == 0)
+			break;
+
+		skb_pull(skb, pkt_len_with_padd);
+
+		/* Next RX Packet Header */
+		pkt_desc_ptr++;
+
+		new_skb = NULL;
+	}
+
+	return 1;
+
+err:
+	return 0;
+}
+
 static struct sk_buff *aqc111_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 				       gfp_t flags)
 {
@@ -637,6 +738,7 @@ static const struct driver_info aqc111_info = {
 	.stop		= aqc111_stop,
 	.flags		= FLAG_ETHER | FLAG_FRAMING_AX |
 			  FLAG_AVOID_UNLINK_URBS | FLAG_MULTI_PACKET,
+	.rx_fixup	= aqc111_rx_fixup,
 	.tx_fixup	= aqc111_tx_fixup,
 };
 
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index c09f188b9f3d..c5785f890022 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -10,6 +10,8 @@
 #ifndef __LINUX_USBNET_AQC111_H
 #define __LINUX_USBNET_AQC111_H
 
+#define URB_SIZE	(1024 * 62)
+
 #define AQ_ACCESS_MAC			0x01
 #define AQ_FLASH_PARAMETERS		0x20
 #define AQ_PHY_POWER			0x31
@@ -157,6 +159,19 @@ struct aqc111_data {
 #define AQ_TX_DESC_LEN_MASK	0x1FFFFF
 #define AQ_TX_DESC_DROP_PADD	BIT(28)
 
+#define AQ_RX_HW_PAD			0x02
+
+/* RX Packet Descriptor */
+#define AQ_RX_PD_RX_OK		BIT(11)
+#define AQ_RX_PD_DROP		BIT(31)
+#define AQ_RX_PD_LEN_MASK	0x7FFF0000
+#define AQ_RX_PD_LEN_SHIFT	0x10
+
+/* RX Descriptor header */
+#define AQ_RX_DH_PKT_CNT_MASK		0x1FFF
+#define AQ_RX_DH_DESC_OFFSET_MASK	0xFFFFE000
+#define AQ_RX_DH_DESC_OFFSET_SHIFT	0x0D
+
 static struct {
 	unsigned char ctrl;
 	unsigned char timer_l;
-- 
cgit v1.2.3


From 0203146646be831de832e7fd2dc4ef1f32958f51 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:21 +0000
Subject: net: usb: aqc111: Add checksum offload support

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 38 ++++++++++++++++++++++++++++++++++++++
 drivers/net/usb/aqc111.h | 16 ++++++++++++++--
 2 files changed, 52 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 7a1976ecf294..1c8812e082bf 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -439,6 +439,26 @@ static void aqc111_configure_rx(struct usbnet *dev,
 	netdev_info(dev->net, "Link Speed %d, USB %d", link_speed, usb_host);
 }
 
+static void aqc111_configure_csum_offload(struct usbnet *dev)
+{
+	u8 reg8 = 0;
+
+	if (dev->net->features & NETIF_F_RXCSUM) {
+		reg8 |= SFR_RXCOE_IP | SFR_RXCOE_TCP | SFR_RXCOE_UDP |
+			SFR_RXCOE_TCPV6 | SFR_RXCOE_UDPV6;
+	}
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_RXCOE_CTL, 1, 1, &reg8);
+
+	reg8 = 0;
+	if (dev->net->features & NETIF_F_IP_CSUM)
+		reg8 |= SFR_TXCOE_IP | SFR_TXCOE_TCP | SFR_TXCOE_UDP;
+
+	if (dev->net->features & NETIF_F_IPV6_CSUM)
+		reg8 |= SFR_TXCOE_TCPV6 | SFR_TXCOE_UDPV6;
+
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_TXCOE_CTL, 1, 1, &reg8);
+}
+
 static int aqc111_link_reset(struct usbnet *dev)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
@@ -482,6 +502,8 @@ static int aqc111_link_reset(struct usbnet *dev)
 		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
 				   2, &reg16);
 
+		aqc111_configure_csum_offload(dev);
+
 		aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
 				  2, &reg16);
 
@@ -583,6 +605,21 @@ static int aqc111_stop(struct usbnet *dev)
 	return 0;
 }
 
+static void aqc111_rx_checksum(struct sk_buff *skb, u64 pkt_desc)
+{
+	u32 pkt_type = 0;
+
+	skb->ip_summed = CHECKSUM_NONE;
+	/* checksum error bit is set */
+	if (pkt_desc & AQ_RX_PD_L4_ERR || pkt_desc & AQ_RX_PD_L3_ERR)
+		return;
+
+	pkt_type = pkt_desc & AQ_RX_PD_L4_TYPE_MASK;
+	/* It must be a TCP or UDP packet with a valid checksum */
+	if (pkt_type == AQ_RX_PD_L4_TCP || pkt_type == AQ_RX_PD_L4_UDP)
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+}
+
 static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
 	struct sk_buff *new_skb = NULL;
@@ -660,6 +697,7 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		skb_set_tail_pointer(new_skb, new_skb->len);
 
 		new_skb->truesize = SKB_TRUESIZE(new_skb->len);
+		aqc111_rx_checksum(new_skb, pkt_desc);
 
 		usbnet_skb_return(dev, new_skb);
 		if (pkt_count == 0)
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index c5785f890022..ff43443bfd72 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -21,8 +21,11 @@
 #define AQ_USB_SET_TIMEOUT		4000
 
 /* Feature. ********************************************/
-#define AQ_SUPPORT_FEATURE	(NETIF_F_SG)
-#define AQ_SUPPORT_HW_FEATURE	(NETIF_F_SG)
+#define AQ_SUPPORT_FEATURE	(NETIF_F_SG | NETIF_F_IP_CSUM |\
+				 NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM)
+
+#define AQ_SUPPORT_HW_FEATURE	(NETIF_F_SG | NETIF_F_IP_CSUM |\
+				 NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM)
 
 /* SFR Reg. ********************************************/
 
@@ -162,6 +165,15 @@ struct aqc111_data {
 #define AQ_RX_HW_PAD			0x02
 
 /* RX Packet Descriptor */
+#define AQ_RX_PD_L4_ERR		BIT(0)
+#define AQ_RX_PD_L3_ERR		BIT(1)
+#define AQ_RX_PD_L4_TYPE_MASK	0x1C
+#define AQ_RX_PD_L4_UDP		0x04
+#define AQ_RX_PD_L4_TCP		0x10
+#define AQ_RX_PD_L3_TYPE_MASK	0x60
+#define AQ_RX_PD_L3_IP		0x20
+#define AQ_RX_PD_L3_IP6		0x40
+
 #define AQ_RX_PD_RX_OK		BIT(11)
 #define AQ_RX_PD_DROP		BIT(31)
 #define AQ_RX_PD_LEN_MASK	0x7FFF0000
-- 
cgit v1.2.3


From a4017cc264c66b368218ece00f1b8a1a1de31731 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:23 +0000
Subject: net: usb: aqc111: Add support for changing MTU

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 59 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 1c8812e082bf..641e68ee017a 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -205,6 +205,48 @@ static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0, &aqc111_data->phy_cfg);
 }
 
+static int aqc111_change_mtu(struct net_device *net, int new_mtu)
+{
+	struct usbnet *dev = netdev_priv(net);
+	u16 reg16 = 0;
+	u8 buf[5];
+
+	net->mtu = new_mtu;
+	dev->hard_mtu = net->mtu + net->hard_header_len;
+
+	aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+			  2, &reg16);
+	if (net->mtu > 1500)
+		reg16 |= SFR_MEDIUM_JUMBO_EN;
+	else
+		reg16 &= ~SFR_MEDIUM_JUMBO_EN;
+
+	aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+			   2, &reg16);
+
+	if (dev->net->mtu > 12500 && dev->net->mtu <= 16334) {
+		memcpy(buf, &AQC111_BULKIN_SIZE[2], 5);
+		/* RX bulk configuration */
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_RX_BULKIN_QCTRL,
+				 5, 5, buf);
+	}
+
+	/* Set high low water level */
+	if (dev->net->mtu <= 4500)
+		reg16 = 0x0810;
+	else if (dev->net->mtu <= 9500)
+		reg16 = 0x1020;
+	else if (dev->net->mtu <= 12500)
+		reg16 = 0x1420;
+	else if (dev->net->mtu <= 16334)
+		reg16 = 0x1A20;
+
+	aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_PAUSE_WATERLVL_LOW,
+			   2, &reg16);
+
+	return 0;
+}
+
 static int aqc111_set_mac_addr(struct net_device *net, void *p)
 {
 	struct usbnet *dev = netdev_priv(net);
@@ -225,6 +267,7 @@ static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_change_mtu		= aqc111_change_mtu,
 	.ndo_set_mac_address	= aqc111_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
@@ -301,6 +344,8 @@ static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->needed_headroom += sizeof(u64);
 	dev->net->needed_tailroom += sizeof(u64);
 
+	dev->net->max_mtu = 16334;
+
 	dev->net->netdev_ops = &aqc111_netdev_ops;
 
 	if (usb_device_no_sg_constraint(dev->udev))
@@ -427,12 +472,22 @@ static void aqc111_configure_rx(struct usbnet *dev,
 		break;
 	}
 
+	if (dev->net->mtu > 12500 && dev->net->mtu <= 16334)
+		queue_num = 2; /* For Jumbo packet 16KB */
+
 	memcpy(buf, &AQC111_BULKIN_SIZE[queue_num], 5);
 	/* RX bulk configuration */
 	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_RX_BULKIN_QCTRL, 5, 5, buf);
 
 	/* Set high low water level */
-	reg16 = 0x0810;
+	if (dev->net->mtu <= 4500)
+		reg16 = 0x0810;
+	else if (dev->net->mtu <= 9500)
+		reg16 = 0x1020;
+	else if (dev->net->mtu <= 12500)
+		reg16 = 0x1420;
+	else if (dev->net->mtu <= 16334)
+		reg16 = 0x1A20;
 
 	aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_PAUSE_WATERLVL_LOW,
 			   2, &reg16);
@@ -507,6 +562,9 @@ static int aqc111_link_reset(struct usbnet *dev)
 		aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
 				  2, &reg16);
 
+		if (dev->net->mtu > 1500)
+			reg16 |= SFR_MEDIUM_JUMBO_EN;
+
 		reg16 |= SFR_MEDIUM_RECEIVE_EN | SFR_MEDIUM_RXFLOW_CTRLEN |
 			 SFR_MEDIUM_TXFLOW_CTRLEN;
 		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
-- 
cgit v1.2.3


From 6649d2a6c43298552db5aa09e522f821cda0b5e0 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:26 +0000
Subject: net: usb: aqc111: Add support for enable/disable checksum offload

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 45 ++++++++++++++++++++++++++++++++++++++++++++-
 drivers/net/usb/aqc111.h |  1 +
 2 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 641e68ee017a..7b69d0a5fc4c 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -261,6 +261,46 @@ static int aqc111_set_mac_addr(struct net_device *net, void *p)
 				ETH_ALEN, net->dev_addr);
 }
 
+static int aqc111_set_features(struct net_device *net,
+			       netdev_features_t features)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+	netdev_features_t changed = net->features ^ features;
+	u8 reg8 = 0;
+
+	if (changed & NETIF_F_IP_CSUM) {
+		aqc111_read_cmd(dev, AQ_ACCESS_MAC, SFR_TXCOE_CTL, 1, 1, &reg8);
+		reg8 ^= SFR_TXCOE_TCP | SFR_TXCOE_UDP;
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_TXCOE_CTL,
+				 1, 1, &reg8);
+	}
+
+	if (changed & NETIF_F_IPV6_CSUM) {
+		aqc111_read_cmd(dev, AQ_ACCESS_MAC, SFR_TXCOE_CTL, 1, 1, &reg8);
+		reg8 ^= SFR_TXCOE_TCPV6 | SFR_TXCOE_UDPV6;
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_TXCOE_CTL,
+				 1, 1, &reg8);
+	}
+
+	if (changed & NETIF_F_RXCSUM) {
+		aqc111_read_cmd(dev, AQ_ACCESS_MAC, SFR_RXCOE_CTL, 1, 1, &reg8);
+		if (features & NETIF_F_RXCSUM) {
+			aqc111_data->rx_checksum = 1;
+			reg8 &= ~(SFR_RXCOE_IP | SFR_RXCOE_TCP | SFR_RXCOE_UDP |
+				  SFR_RXCOE_TCPV6 | SFR_RXCOE_UDPV6);
+		} else {
+			aqc111_data->rx_checksum = 0;
+			reg8 |= SFR_RXCOE_IP | SFR_RXCOE_TCP | SFR_RXCOE_UDP |
+				SFR_RXCOE_TCPV6 | SFR_RXCOE_UDPV6;
+		}
+
+		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_RXCOE_CTL,
+				 1, 1, &reg8);
+	}
+	return 0;
+}
+
 static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_open		= usbnet_open,
 	.ndo_stop		= usbnet_stop,
@@ -270,6 +310,7 @@ static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_change_mtu		= aqc111_change_mtu,
 	.ndo_set_mac_address	= aqc111_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_set_features	= aqc111_set_features,
 };
 
 static int aqc111_read_perm_mac(struct usbnet *dev)
@@ -680,6 +721,7 @@ static void aqc111_rx_checksum(struct sk_buff *skb, u64 pkt_desc)
 
 static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
+	struct aqc111_data *aqc111_data = dev->driver_priv;
 	struct sk_buff *new_skb = NULL;
 	u32 pkt_total_offset = 0;
 	u64 *pkt_desc_ptr = NULL;
@@ -755,7 +797,8 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		skb_set_tail_pointer(new_skb, new_skb->len);
 
 		new_skb->truesize = SKB_TRUESIZE(new_skb->len);
-		aqc111_rx_checksum(new_skb, pkt_desc);
+		if (aqc111_data->rx_checksum)
+			aqc111_rx_checksum(new_skb, pkt_desc);
 
 		usbnet_skb_return(dev, new_skb);
 		if (pkt_count == 0)
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index ff43443bfd72..165cdb8b022c 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -138,6 +138,7 @@
 /******************************************************************************/
 
 struct aqc111_data {
+	u8 rx_checksum;
 	u8 link_speed;
 	u8 link;
 	u8 autoneg;
-- 
cgit v1.2.3


From de074e7a7e20f04023c8fdcb0ed6e356f699ec4b Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:28 +0000
Subject: net: usb: aqc111: Add support for TSO

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 6 ++++++
 drivers/net/usb/aqc111.h | 8 ++++++--
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 7b69d0a5fc4c..fce2a4f65122 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -395,6 +395,8 @@ static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->hw_features |= AQ_SUPPORT_HW_FEATURE;
 	dev->net->features |= AQ_SUPPORT_FEATURE;
 
+	netif_set_gso_max_size(dev->net, 65535);
+
 	aqc111_read_fw_version(dev, aqc111_data);
 	aqc111_data->autoneg = AUTONEG_ENABLE;
 	aqc111_data->advertised_speed = (usb_speed == USB_SPEED_SUPER) ?
@@ -832,6 +834,10 @@ static struct sk_buff *aqc111_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 	/*Length of actual data*/
 	tx_desc |= skb->len & AQ_TX_DESC_LEN_MASK;
 
+	/* TSO MSS */
+	tx_desc |= ((u64)(skb_shinfo(skb)->gso_size & AQ_TX_DESC_MSS_MASK)) <<
+		   AQ_TX_DESC_MSS_SHIFT;
+
 	headroom = (skb->len + sizeof(tx_desc)) % 8;
 	if (headroom != 0)
 		padding_size = 8 - headroom;
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index 165cdb8b022c..a7a333914461 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -22,10 +22,12 @@
 
 /* Feature. ********************************************/
 #define AQ_SUPPORT_FEATURE	(NETIF_F_SG | NETIF_F_IP_CSUM |\
-				 NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM)
+				 NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |\
+				 NETIF_F_TSO)
 
 #define AQ_SUPPORT_HW_FEATURE	(NETIF_F_SG | NETIF_F_IP_CSUM |\
-				 NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM)
+				 NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |\
+				 NETIF_F_TSO)
 
 /* SFR Reg. ********************************************/
 
@@ -162,6 +164,8 @@ struct aqc111_data {
 /* TX Descriptor */
 #define AQ_TX_DESC_LEN_MASK	0x1FFFFF
 #define AQ_TX_DESC_DROP_PADD	BIT(28)
+#define AQ_TX_DESC_MSS_MASK	0x7FFF
+#define AQ_TX_DESC_MSS_SHIFT	0x20
 
 #define AQ_RX_HW_PAD			0x02
 
-- 
cgit v1.2.3


From 59b04eeaf294704f29052216344ce52294d7d4e1 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:31 +0000
Subject: net: usb: aqc111: Implement set_rx_mode callback

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 72 ++++++++++++++++++++++++++++++++++++++++++++----
 drivers/net/usb/aqc111.h |  4 +++
 2 files changed, 71 insertions(+), 5 deletions(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index fce2a4f65122..29131b1e0eec 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <linux/mii.h>
 #include <linux/usb.h>
+#include <linux/crc32.h>
 #include <linux/if_vlan.h>
 #include <linux/usb/cdc.h>
 #include <linux/usb/usbnet.h>
@@ -158,6 +159,25 @@ static int aqc111_write32_cmd(struct usbnet *dev, u8 cmd, u16 value,
 	return aqc111_write_cmd(dev, cmd, value, index, sizeof(tmp), &tmp);
 }
 
+static int aqc111_write_cmd_async(struct usbnet *dev, u8 cmd, u16 value,
+				  u16 index, u16 size, void *data)
+{
+	return usbnet_write_cmd_async(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR |
+				      USB_RECIP_DEVICE, value, index, data,
+				      size);
+}
+
+static int aqc111_write16_cmd_async(struct usbnet *dev, u8 cmd, u16 value,
+				    u16 index, u16 *data)
+{
+	u16 tmp = *data;
+
+	cpu_to_le16s(&tmp);
+
+	return aqc111_write_cmd_async(dev, cmd, value, index,
+				      sizeof(tmp), &tmp);
+}
+
 static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
@@ -261,6 +281,43 @@ static int aqc111_set_mac_addr(struct net_device *net, void *p)
 				ETH_ALEN, net->dev_addr);
 }
 
+static void aqc111_set_rx_mode(struct net_device *net)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+	int mc_count = 0;
+
+	mc_count = netdev_mc_count(net);
+
+	aqc111_data->rxctl &= ~(SFR_RX_CTL_PRO | SFR_RX_CTL_AMALL |
+				SFR_RX_CTL_AM);
+
+	if (net->flags & IFF_PROMISC) {
+		aqc111_data->rxctl |= SFR_RX_CTL_PRO;
+	} else if ((net->flags & IFF_ALLMULTI) || mc_count > AQ_MAX_MCAST) {
+		aqc111_data->rxctl |= SFR_RX_CTL_AMALL;
+	} else if (!netdev_mc_empty(net)) {
+		u8 m_filter[AQ_MCAST_FILTER_SIZE] = { 0 };
+		struct netdev_hw_addr *ha = NULL;
+		u32 crc_bits = 0;
+
+		netdev_for_each_mc_addr(ha, net) {
+			crc_bits = ether_crc(ETH_ALEN, ha->addr) >> 26;
+			m_filter[crc_bits >> 3] |= BIT(crc_bits & 7);
+		}
+
+		aqc111_write_cmd_async(dev, AQ_ACCESS_MAC,
+				       SFR_MULTI_FILTER_ARRY,
+				       AQ_MCAST_FILTER_SIZE,
+				       AQ_MCAST_FILTER_SIZE, m_filter);
+
+		aqc111_data->rxctl |= SFR_RX_CTL_AM;
+	}
+
+	aqc111_write16_cmd_async(dev, AQ_ACCESS_MAC, SFR_RX_CTL,
+				 2, &aqc111_data->rxctl);
+}
+
 static int aqc111_set_features(struct net_device *net,
 			       netdev_features_t features)
 {
@@ -310,6 +367,7 @@ static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_change_mtu		= aqc111_change_mtu,
 	.ndo_set_mac_address	= aqc111_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_set_rx_mode	= aqc111_set_rx_mode,
 	.ndo_set_features	= aqc111_set_features,
 };
 
@@ -582,6 +640,7 @@ static int aqc111_link_reset(struct usbnet *dev)
 		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_ARC_CTRL, 1, 1, &reg8);
 
 		reg16 = SFR_RX_CTL_IPE | SFR_RX_CTL_AB;
+		aqc111_data->rxctl = reg16;
 		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
 
 		reg8 = SFR_RX_PATH_READY;
@@ -602,6 +661,8 @@ static int aqc111_link_reset(struct usbnet *dev)
 
 		aqc111_configure_csum_offload(dev);
 
+		aqc111_set_rx_mode(dev->net);
+
 		aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
 				  2, &reg16);
 
@@ -613,8 +674,9 @@ static int aqc111_link_reset(struct usbnet *dev)
 		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
 				   2, &reg16);
 
-		reg16 = SFR_RX_CTL_IPE | SFR_RX_CTL_AB | SFR_RX_CTL_START;
-		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
+		aqc111_data->rxctl |= SFR_RX_CTL_START;
+		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL,
+				   2, &aqc111_data->rxctl);
 
 		netif_carrier_on(dev->net);
 	} else {
@@ -624,9 +686,9 @@ static int aqc111_link_reset(struct usbnet *dev)
 		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
 				   2, &reg16);
 
-		aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
-		reg16 &= ~SFR_RX_CTL_START;
-		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
+		aqc111_data->rxctl &= ~SFR_RX_CTL_START;
+		aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_RX_CTL,
+				   2, &aqc111_data->rxctl);
 
 		reg8 = SFR_BULK_OUT_FLUSH_EN | SFR_BULK_OUT_EFF_EN;
 		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_BULK_OUT_CTRL,
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index a7a333914461..a57c1184c422 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -12,6 +12,9 @@
 
 #define URB_SIZE	(1024 * 62)
 
+#define AQ_MCAST_FILTER_SIZE		8
+#define AQ_MAX_MCAST			64
+
 #define AQ_ACCESS_MAC			0x01
 #define AQ_FLASH_PARAMETERS		0x20
 #define AQ_PHY_POWER			0x31
@@ -140,6 +143,7 @@
 /******************************************************************************/
 
 struct aqc111_data {
+	u16 rxctl;
 	u8 rx_checksum;
 	u8 link_speed;
 	u8 link;
-- 
cgit v1.2.3


From 7afa6c9803eac43b205c9e33a5ea543b2c51d026 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:33 +0000
Subject: net: usb: aqc111: Add support for VLAN_CTAG_TX/RX offload

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 17 +++++++++++++++++
 drivers/net/usb/aqc111.h | 12 +++++++++++-
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 29131b1e0eec..3590d18ac44d 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -452,6 +452,7 @@ static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 
 	dev->net->hw_features |= AQ_SUPPORT_HW_FEATURE;
 	dev->net->features |= AQ_SUPPORT_FEATURE;
+	dev->net->vlan_features |= AQ_SUPPORT_VLAN_FEATURE;
 
 	netif_set_gso_max_size(dev->net, 65535);
 
@@ -714,6 +715,7 @@ static int aqc111_reset(struct usbnet *dev)
 
 	dev->net->hw_features |= AQ_SUPPORT_HW_FEATURE;
 	dev->net->features |= AQ_SUPPORT_FEATURE;
+	dev->net->vlan_features |= AQ_SUPPORT_VLAN_FEATURE;
 
 	/* Power up ethernet PHY */
 	aqc111_data->phy_cfg = AQ_PHY_POWER_EN;
@@ -793,6 +795,7 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	u32 desc_offset = 0; /*RX Header Offset*/
 	u16 pkt_count = 0;
 	u64 desc_hdr = 0;
+	u16 vlan_tag = 0;
 	u32 skb_len = 0;
 
 	if (!skb)
@@ -864,6 +867,12 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		if (aqc111_data->rx_checksum)
 			aqc111_rx_checksum(new_skb, pkt_desc);
 
+		if (pkt_desc & AQ_RX_PD_VLAN) {
+			vlan_tag = pkt_desc >> AQ_RX_PD_VLAN_SHIFT;
+			__vlan_hwaccel_put_tag(new_skb, htons(ETH_P_8021Q),
+					       vlan_tag & VLAN_VID_MASK);
+		}
+
 		usbnet_skb_return(dev, new_skb);
 		if (pkt_count == 0)
 			break;
@@ -892,6 +901,7 @@ static struct sk_buff *aqc111_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 	int headroom = 0;
 	int tailroom = 0;
 	u64 tx_desc = 0;
+	u16 tci = 0;
 
 	/*Length of actual data*/
 	tx_desc |= skb->len & AQ_TX_DESC_LEN_MASK;
@@ -909,6 +919,13 @@ static struct sk_buff *aqc111_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 		tx_desc |= AQ_TX_DESC_DROP_PADD;
 	}
 
+	/* Vlan Tag */
+	if (vlan_get_tag(skb, &tci) >= 0) {
+		tx_desc |= AQ_TX_DESC_VLAN;
+		tx_desc |= ((u64)tci & AQ_TX_DESC_VLAN_MASK) <<
+			   AQ_TX_DESC_VLAN_SHIFT;
+	}
+
 	if (!dev->can_dma_sg && (dev->net->features & NETIF_F_SG) &&
 	    skb_linearize(skb))
 		return NULL;
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index a57c1184c422..d09326d46273 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -26,12 +26,17 @@
 /* Feature. ********************************************/
 #define AQ_SUPPORT_FEATURE	(NETIF_F_SG | NETIF_F_IP_CSUM |\
 				 NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |\
-				 NETIF_F_TSO)
+				 NETIF_F_TSO | NETIF_F_HW_VLAN_CTAG_TX |\
+				 NETIF_F_HW_VLAN_CTAG_RX)
 
 #define AQ_SUPPORT_HW_FEATURE	(NETIF_F_SG | NETIF_F_IP_CSUM |\
 				 NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |\
 				 NETIF_F_TSO)
 
+#define AQ_SUPPORT_VLAN_FEATURE (NETIF_F_SG | NETIF_F_IP_CSUM |\
+				 NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |\
+				 NETIF_F_TSO)
+
 /* SFR Reg. ********************************************/
 
 #define SFR_GENERAL_STATUS		0x03
@@ -168,8 +173,11 @@ struct aqc111_data {
 /* TX Descriptor */
 #define AQ_TX_DESC_LEN_MASK	0x1FFFFF
 #define AQ_TX_DESC_DROP_PADD	BIT(28)
+#define AQ_TX_DESC_VLAN		BIT(29)
 #define AQ_TX_DESC_MSS_MASK	0x7FFF
 #define AQ_TX_DESC_MSS_SHIFT	0x20
+#define AQ_TX_DESC_VLAN_MASK	0xFFFF
+#define AQ_TX_DESC_VLAN_SHIFT	0x30
 
 #define AQ_RX_HW_PAD			0x02
 
@@ -183,10 +191,12 @@ struct aqc111_data {
 #define AQ_RX_PD_L3_IP		0x20
 #define AQ_RX_PD_L3_IP6		0x40
 
+#define AQ_RX_PD_VLAN		BIT(10)
 #define AQ_RX_PD_RX_OK		BIT(11)
 #define AQ_RX_PD_DROP		BIT(31)
 #define AQ_RX_PD_LEN_MASK	0x7FFF0000
 #define AQ_RX_PD_LEN_SHIFT	0x10
+#define AQ_RX_PD_VLAN_SHIFT	0x20
 
 /* RX Descriptor header */
 #define AQ_RX_DH_PKT_CNT_MASK		0x1FFF
-- 
cgit v1.2.3


From 4189673a2e60e45edb5cc74df96c4a738907e63e Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:35 +0000
Subject: net: usb: aqc111: Add RX VLAN filtering support

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 89 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/usb/aqc111.h |  2 +-
 2 files changed, 90 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 3590d18ac44d..3b42843d7017 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -281,6 +281,57 @@ static int aqc111_set_mac_addr(struct net_device *net, void *p)
 				ETH_ALEN, net->dev_addr);
 }
 
+static int aqc111_vlan_rx_kill_vid(struct net_device *net,
+				   __be16 proto, u16 vid)
+{
+	struct usbnet *dev = netdev_priv(net);
+	u8 vlan_ctrl = 0;
+	u16 reg16 = 0;
+	u8 reg8 = 0;
+
+	aqc111_read_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_CONTROL, 1, 1, &reg8);
+	vlan_ctrl = reg8;
+
+	/* Address */
+	reg8 = (vid / 16);
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_ADDRESS, 1, 1, &reg8);
+	/* Data */
+	reg8 = vlan_ctrl | SFR_VLAN_CONTROL_RD;
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_CONTROL, 1, 1, &reg8);
+	aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_DATA0, 2, &reg16);
+	reg16 &= ~(1 << (vid % 16));
+	aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_DATA0, 2, &reg16);
+	reg8 = vlan_ctrl | SFR_VLAN_CONTROL_WE;
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_CONTROL, 1, 1, &reg8);
+
+	return 0;
+}
+
+static int aqc111_vlan_rx_add_vid(struct net_device *net, __be16 proto, u16 vid)
+{
+	struct usbnet *dev = netdev_priv(net);
+	u8 vlan_ctrl = 0;
+	u16 reg16 = 0;
+	u8 reg8 = 0;
+
+	aqc111_read_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_CONTROL, 1, 1, &reg8);
+	vlan_ctrl = reg8;
+
+	/* Address */
+	reg8 = (vid / 16);
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_ADDRESS, 1, 1, &reg8);
+	/* Data */
+	reg8 = vlan_ctrl | SFR_VLAN_CONTROL_RD;
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_CONTROL, 1, 1, &reg8);
+	aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_DATA0, 2, &reg16);
+	reg16 |= (1 << (vid % 16));
+	aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_DATA0, 2, &reg16);
+	reg8 = vlan_ctrl | SFR_VLAN_CONTROL_WE;
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_CONTROL, 1, 1, &reg8);
+
+	return 0;
+}
+
 static void aqc111_set_rx_mode(struct net_device *net)
 {
 	struct usbnet *dev = netdev_priv(net);
@@ -324,6 +375,7 @@ static int aqc111_set_features(struct net_device *net,
 	struct usbnet *dev = netdev_priv(net);
 	struct aqc111_data *aqc111_data = dev->driver_priv;
 	netdev_features_t changed = net->features ^ features;
+	u16 reg16 = 0;
 	u8 reg8 = 0;
 
 	if (changed & NETIF_F_IP_CSUM) {
@@ -355,6 +407,39 @@ static int aqc111_set_features(struct net_device *net,
 		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_RXCOE_CTL,
 				 1, 1, &reg8);
 	}
+	if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		if (features & NETIF_F_HW_VLAN_CTAG_FILTER) {
+			u16 i = 0;
+
+			for (i = 0; i < 256; i++) {
+				/* Address */
+				reg8 = i;
+				aqc111_write_cmd(dev, AQ_ACCESS_MAC,
+						 SFR_VLAN_ID_ADDRESS,
+						 1, 1, &reg8);
+				/* Data */
+				aqc111_write16_cmd(dev, AQ_ACCESS_MAC,
+						   SFR_VLAN_ID_DATA0,
+						   2, &reg16);
+				reg8 = SFR_VLAN_CONTROL_WE;
+				aqc111_write_cmd(dev, AQ_ACCESS_MAC,
+						 SFR_VLAN_ID_CONTROL,
+						 1, 1, &reg8);
+			}
+			aqc111_read_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_CONTROL,
+					1, 1, &reg8);
+			reg8 |= SFR_VLAN_CONTROL_VFE;
+			aqc111_write_cmd(dev, AQ_ACCESS_MAC,
+					 SFR_VLAN_ID_CONTROL, 1, 1, &reg8);
+		} else {
+			aqc111_read_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_CONTROL,
+					1, 1, &reg8);
+			reg8 &= ~SFR_VLAN_CONTROL_VFE;
+			aqc111_write_cmd(dev, AQ_ACCESS_MAC,
+					 SFR_VLAN_ID_CONTROL, 1, 1, &reg8);
+		}
+	}
+
 	return 0;
 }
 
@@ -367,6 +452,8 @@ static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_change_mtu		= aqc111_change_mtu,
 	.ndo_set_mac_address	= aqc111_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_vlan_rx_add_vid	= aqc111_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= aqc111_vlan_rx_kill_vid,
 	.ndo_set_rx_mode	= aqc111_set_rx_mode,
 	.ndo_set_features	= aqc111_set_features,
 };
@@ -627,6 +714,8 @@ static int aqc111_link_reset(struct usbnet *dev)
 
 		/* Vlan Tag Filter */
 		reg8 = SFR_VLAN_CONTROL_VSO;
+		if (dev->net->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+			reg8 |= SFR_VLAN_CONTROL_VFE;
 
 		aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_VLAN_ID_CONTROL,
 				 1, 1, &reg8);
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index d09326d46273..0ce23a741211 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -31,7 +31,7 @@
 
 #define AQ_SUPPORT_HW_FEATURE	(NETIF_F_SG | NETIF_F_IP_CSUM |\
 				 NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |\
-				 NETIF_F_TSO)
+				 NETIF_F_TSO | NETIF_F_HW_VLAN_CTAG_FILTER)
 
 #define AQ_SUPPORT_VLAN_FEATURE (NETIF_F_SG | NETIF_F_IP_CSUM |\
 				 NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |\
-- 
cgit v1.2.3


From 027e6f7800e5ff2b66afced2f3a0f0029c98ecf3 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:38 +0000
Subject: net: usb: aqc111: Initialize ethtool_ops structure

Implement get_drvinfo, set/get_msglevel, get_link callbacks

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 3b42843d7017..9fc036d5354b 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -9,6 +9,7 @@
 
 #include <linux/module.h>
 #include <linux/netdevice.h>
+#include <linux/ethtool.h>
 #include <linux/mii.h>
 #include <linux/usb.h>
 #include <linux/crc32.h>
@@ -18,6 +19,8 @@
 
 #include "aqc111.h"
 
+#define DRIVER_NAME "aqc111"
+
 static int aqc111_read_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value,
 				u16 index, u16 size, void *data)
 {
@@ -178,6 +181,23 @@ static int aqc111_write16_cmd_async(struct usbnet *dev, u8 cmd, u16 value,
 				      sizeof(tmp), &tmp);
 }
 
+static void aqc111_get_drvinfo(struct net_device *net,
+			       struct ethtool_drvinfo *info)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+
+	/* Inherit standard device info */
+	usbnet_get_drvinfo(net, info);
+	strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver));
+	snprintf(info->fw_version, sizeof(info->fw_version), "%u.%u.%u",
+		 aqc111_data->fw_ver.major,
+		 aqc111_data->fw_ver.minor,
+		 aqc111_data->fw_ver.rev);
+	info->eedump_len = 0x00;
+	info->regdump_len = 0x00;
+}
+
 static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
@@ -225,6 +245,13 @@ static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0, &aqc111_data->phy_cfg);
 }
 
+static const struct ethtool_ops aqc111_ethtool_ops = {
+	.get_drvinfo = aqc111_get_drvinfo,
+	.get_msglevel = usbnet_get_msglevel,
+	.set_msglevel = usbnet_set_msglevel,
+	.get_link = ethtool_op_get_link,
+};
+
 static int aqc111_change_mtu(struct net_device *net, int new_mtu)
 {
 	struct usbnet *dev = netdev_priv(net);
@@ -533,6 +560,7 @@ static int aqc111_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->max_mtu = 16334;
 
 	dev->net->netdev_ops = &aqc111_netdev_ops;
+	dev->net->ethtool_ops = &aqc111_ethtool_ops;
 
 	if (usb_device_no_sg_constraint(dev->udev))
 		dev->can_dma_sg = 1;
-- 
cgit v1.2.3


From abbd8e7d6d108d34405159fc898b0717cfd3e6de Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:42 +0000
Subject: net: usb: aqc111: Implement get/set_link_ksettings callbacks

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 124 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 124 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 9fc036d5354b..650cea33f1a3 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -16,6 +16,7 @@
 #include <linux/if_vlan.h>
 #include <linux/usb/cdc.h>
 #include <linux/usb/usbnet.h>
+#include <linux/linkmode.h>
 
 #include "aqc111.h"
 
@@ -198,6 +199,84 @@ static void aqc111_get_drvinfo(struct net_device *net,
 	info->regdump_len = 0x00;
 }
 
+static void aqc111_speed_to_link_mode(u32 speed,
+				      struct ethtool_link_ksettings *elk)
+{
+	switch (speed) {
+	case SPEED_5000:
+		ethtool_link_ksettings_add_link_mode(elk, advertising,
+						     5000baseT_Full);
+		break;
+	case SPEED_2500:
+		ethtool_link_ksettings_add_link_mode(elk, advertising,
+						     2500baseT_Full);
+		break;
+	case SPEED_1000:
+		ethtool_link_ksettings_add_link_mode(elk, advertising,
+						     1000baseT_Full);
+		break;
+	case SPEED_100:
+		ethtool_link_ksettings_add_link_mode(elk, advertising,
+						     100baseT_Full);
+		break;
+	}
+}
+
+static int aqc111_get_link_ksettings(struct net_device *net,
+				     struct ethtool_link_ksettings *elk)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+	enum usb_device_speed usb_speed = dev->udev->speed;
+	u32 speed = SPEED_UNKNOWN;
+
+	ethtool_link_ksettings_zero_link_mode(elk, supported);
+	ethtool_link_ksettings_add_link_mode(elk, supported,
+					     100baseT_Full);
+	ethtool_link_ksettings_add_link_mode(elk, supported,
+					     1000baseT_Full);
+	if (usb_speed == USB_SPEED_SUPER) {
+		ethtool_link_ksettings_add_link_mode(elk, supported,
+						     2500baseT_Full);
+		ethtool_link_ksettings_add_link_mode(elk, supported,
+						     5000baseT_Full);
+	}
+	ethtool_link_ksettings_add_link_mode(elk, supported, TP);
+	ethtool_link_ksettings_add_link_mode(elk, supported, Autoneg);
+
+	elk->base.port = PORT_TP;
+	elk->base.transceiver = XCVR_INTERNAL;
+
+	elk->base.mdio_support = 0x00; /*Not supported*/
+
+	if (aqc111_data->autoneg)
+		linkmode_copy(elk->link_modes.advertising,
+			      elk->link_modes.supported);
+	else
+		aqc111_speed_to_link_mode(aqc111_data->advertised_speed, elk);
+
+	elk->base.autoneg = aqc111_data->autoneg;
+
+	switch (aqc111_data->link_speed) {
+	case AQ_INT_SPEED_5G:
+		speed = SPEED_5000;
+		break;
+	case AQ_INT_SPEED_2_5G:
+		speed = SPEED_2500;
+		break;
+	case AQ_INT_SPEED_1G:
+		speed = SPEED_1000;
+		break;
+	case AQ_INT_SPEED_100M:
+		speed = SPEED_100;
+		break;
+	}
+	elk->base.duplex = DUPLEX_FULL;
+	elk->base.speed = speed;
+
+	return 0;
+}
+
 static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
@@ -245,11 +324,56 @@ static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0, &aqc111_data->phy_cfg);
 }
 
+static int aqc111_set_link_ksettings(struct net_device *net,
+				     const struct ethtool_link_ksettings *elk)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+	enum usb_device_speed usb_speed = dev->udev->speed;
+	u8 autoneg = elk->base.autoneg;
+	u32 speed = elk->base.speed;
+
+	if (autoneg == AUTONEG_ENABLE) {
+		if (aqc111_data->autoneg != AUTONEG_ENABLE) {
+			aqc111_data->autoneg = AUTONEG_ENABLE;
+			aqc111_data->advertised_speed =
+					(usb_speed == USB_SPEED_SUPER) ?
+					 SPEED_5000 : SPEED_1000;
+			aqc111_set_phy_speed(dev, aqc111_data->autoneg,
+					     aqc111_data->advertised_speed);
+		}
+	} else {
+		if (speed != SPEED_100 &&
+		    speed != SPEED_1000 &&
+		    speed != SPEED_2500 &&
+		    speed != SPEED_5000 &&
+		    speed != SPEED_UNKNOWN)
+			return -EINVAL;
+
+		if (elk->base.duplex != DUPLEX_FULL)
+			return -EINVAL;
+
+		if (usb_speed != USB_SPEED_SUPER && speed > SPEED_1000)
+			return -EINVAL;
+
+		aqc111_data->autoneg = AUTONEG_DISABLE;
+		if (speed != SPEED_UNKNOWN)
+			aqc111_data->advertised_speed = speed;
+
+		aqc111_set_phy_speed(dev, aqc111_data->autoneg,
+				     aqc111_data->advertised_speed);
+	}
+
+	return 0;
+}
+
 static const struct ethtool_ops aqc111_ethtool_ops = {
 	.get_drvinfo = aqc111_get_drvinfo,
 	.get_msglevel = usbnet_get_msglevel,
 	.set_msglevel = usbnet_set_msglevel,
 	.get_link = ethtool_op_get_link,
+	.get_link_ksettings = aqc111_get_link_ksettings,
+	.set_link_ksettings = aqc111_set_link_ksettings
 };
 
 static int aqc111_change_mtu(struct net_device *net, int new_mtu)
-- 
cgit v1.2.3


From e58ba4544c7771591d1e3157bc01b4a8e4d1c3fc Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:45 +0000
Subject: net: usb: aqc111: Add support for wake on LAN by MAGIC packet

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 180 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/usb/aqc111.h |  12 ++++
 2 files changed, 192 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 650cea33f1a3..7c859b9417f1 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -54,6 +54,17 @@ static int aqc111_read_cmd(struct usbnet *dev, u8 cmd, u16 value,
 	return ret;
 }
 
+static int aqc111_read16_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value,
+				  u16 index, u16 *data)
+{
+	int ret = 0;
+
+	ret = aqc111_read_cmd_nopm(dev, cmd, value, index, sizeof(*data), data);
+	le16_to_cpus(data);
+
+	return ret;
+}
+
 static int aqc111_read16_cmd(struct usbnet *dev, u8 cmd, u16 value,
 			     u16 index, u16 *data)
 {
@@ -199,6 +210,35 @@ static void aqc111_get_drvinfo(struct net_device *net,
 	info->regdump_len = 0x00;
 }
 
+static void aqc111_get_wol(struct net_device *net,
+			   struct ethtool_wolinfo *wolinfo)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+
+	wolinfo->supported = WAKE_MAGIC;
+	wolinfo->wolopts = 0;
+
+	if (aqc111_data->wol_flags & AQ_WOL_FLAG_MP)
+		wolinfo->wolopts |= WAKE_MAGIC;
+}
+
+static int aqc111_set_wol(struct net_device *net,
+			  struct ethtool_wolinfo *wolinfo)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+
+	if (wolinfo->wolopts & ~WAKE_MAGIC)
+		return -EINVAL;
+
+	aqc111_data->wol_flags = 0;
+	if (wolinfo->wolopts & WAKE_MAGIC)
+		aqc111_data->wol_flags |= AQ_WOL_FLAG_MP;
+
+	return 0;
+}
+
 static void aqc111_speed_to_link_mode(u32 speed,
 				      struct ethtool_link_ksettings *elk)
 {
@@ -369,6 +409,8 @@ static int aqc111_set_link_ksettings(struct net_device *net,
 
 static const struct ethtool_ops aqc111_ethtool_ops = {
 	.get_drvinfo = aqc111_get_drvinfo,
+	.get_wol = aqc111_get_wol,
+	.set_wol = aqc111_set_wol,
 	.get_msglevel = usbnet_get_msglevel,
 	.set_msglevel = usbnet_set_msglevel,
 	.get_link = ethtool_op_get_link,
@@ -1207,6 +1249,142 @@ static const struct driver_info aqc111_info = {
 	.tx_fixup	= aqc111_tx_fixup,
 };
 
+static int aqc111_suspend(struct usb_interface *intf, pm_message_t message)
+{
+	struct usbnet *dev = usb_get_intfdata(intf);
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+	u16 temp_rx_ctrl = 0x00;
+	u16 reg16;
+	u8 reg8;
+
+	usbnet_suspend(intf, message);
+
+	aqc111_read16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
+	temp_rx_ctrl = reg16;
+	/* Stop RX operations*/
+	reg16 &= ~SFR_RX_CTL_START;
+	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
+	/* Force bz */
+	aqc111_read16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_PHYPWR_RSTCTL,
+			       2, &reg16);
+	reg16 |= SFR_PHYPWR_RSTCTL_BZ;
+	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_PHYPWR_RSTCTL,
+				2, &reg16);
+
+	reg8 = SFR_BULK_OUT_EFF_EN;
+	aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_BULK_OUT_CTRL,
+			      1, 1, &reg8);
+
+	temp_rx_ctrl &= ~(SFR_RX_CTL_START | SFR_RX_CTL_RF_WAK |
+			  SFR_RX_CTL_AP | SFR_RX_CTL_AM);
+	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_CTL,
+				2, &temp_rx_ctrl);
+
+	reg8 = 0x00;
+	aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_ETH_MAC_PATH,
+			      1, 1, &reg8);
+
+	if (aqc111_data->wol_flags) {
+		struct aqc111_wol_cfg wol_cfg = { 0 };
+
+		aqc111_data->phy_cfg |= AQ_WOL;
+		ether_addr_copy(wol_cfg.hw_addr, dev->net->dev_addr);
+		wol_cfg.flags = aqc111_data->wol_flags;
+
+		temp_rx_ctrl |= (SFR_RX_CTL_AB | SFR_RX_CTL_START);
+		aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_CTL,
+					2, &temp_rx_ctrl);
+		reg8 = 0x00;
+		aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_BM_INT_MASK,
+				      1, 1, &reg8);
+		reg8 = SFR_BMRX_DMA_EN;
+		aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_BMRX_DMA_CONTROL,
+				      1, 1, &reg8);
+		reg8 = SFR_RX_PATH_READY;
+		aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_ETH_MAC_PATH,
+				      1, 1, &reg8);
+		reg8 = 0x07;
+		aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_BULKIN_QCTRL,
+				      1, 1, &reg8);
+		reg8 = 0x00;
+		aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC,
+				      SFR_RX_BULKIN_QTIMR_LOW, 1, 1, &reg8);
+		aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC,
+				      SFR_RX_BULKIN_QTIMR_HIGH, 1, 1, &reg8);
+		reg8 = 0xFF;
+		aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_BULKIN_QSIZE,
+				      1, 1, &reg8);
+		aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_BULKIN_QIFG,
+				      1, 1, &reg8);
+
+		aqc111_read16_cmd_nopm(dev, AQ_ACCESS_MAC,
+				       SFR_MEDIUM_STATUS_MODE, 2, &reg16);
+		reg16 |= SFR_MEDIUM_RECEIVE_EN;
+		aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC,
+					SFR_MEDIUM_STATUS_MODE, 2, &reg16);
+
+		aqc111_write_cmd(dev, AQ_WOL_CFG, 0, 0,
+				 WOL_CFG_SIZE, &wol_cfg);
+		aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
+				   &aqc111_data->phy_cfg);
+	} else {
+		aqc111_data->phy_cfg |= AQ_LOW_POWER;
+		aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
+				   &aqc111_data->phy_cfg);
+
+		/* Disable RX path */
+		aqc111_read16_cmd_nopm(dev, AQ_ACCESS_MAC,
+				       SFR_MEDIUM_STATUS_MODE, 2, &reg16);
+		reg16 &= ~SFR_MEDIUM_RECEIVE_EN;
+		aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC,
+					SFR_MEDIUM_STATUS_MODE, 2, &reg16);
+	}
+
+	return 0;
+}
+
+static int aqc111_resume(struct usb_interface *intf)
+{
+	struct usbnet *dev = usb_get_intfdata(intf);
+	struct aqc111_data *aqc111_data = dev->driver_priv;
+	u16 reg16;
+	u8 reg8;
+
+	netif_carrier_off(dev->net);
+
+	/* Power up ethernet PHY */
+	aqc111_data->phy_cfg |= AQ_PHY_POWER_EN;
+	aqc111_data->phy_cfg &= ~AQ_LOW_POWER;
+	aqc111_data->phy_cfg &= ~AQ_WOL;
+
+	reg8 = 0xFF;
+	aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_BM_INT_MASK,
+			      1, 1, &reg8);
+	/* Configure RX control register => start operation */
+	reg16 = aqc111_data->rxctl;
+	reg16 &= ~SFR_RX_CTL_START;
+	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
+
+	reg16 |= SFR_RX_CTL_START;
+	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
+
+	aqc111_set_phy_speed(dev, aqc111_data->autoneg,
+			     aqc111_data->advertised_speed);
+
+	aqc111_read16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+			       2, &reg16);
+	reg16 |= SFR_MEDIUM_RECEIVE_EN;
+	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
+				2, &reg16);
+	reg8 = SFR_RX_PATH_READY;
+	aqc111_write_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_ETH_MAC_PATH,
+			      1, 1, &reg8);
+	reg8 = 0x0;
+	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_BMRX_DMA_CONTROL, 1, 1, &reg8);
+
+	return usbnet_resume(intf);
+}
+
 #define AQC111_USB_ETH_DEV(vid, pid, table) \
 	USB_DEVICE_INTERFACE_CLASS((vid), (pid), USB_CLASS_VENDOR_SPEC), \
 	.driver_info = (unsigned long)&(table) \
@@ -1228,6 +1406,8 @@ static struct usb_driver aq_driver = {
 	.name		= "aqc111",
 	.id_table	= products,
 	.probe		= usbnet_probe,
+	.suspend	= aqc111_suspend,
+	.resume		= aqc111_resume,
 	.disconnect	= usbnet_disconnect,
 };
 
diff --git a/drivers/net/usb/aqc111.h b/drivers/net/usb/aqc111.h
index 0ce23a741211..4d68b3a6067c 100644
--- a/drivers/net/usb/aqc111.h
+++ b/drivers/net/usb/aqc111.h
@@ -18,6 +18,7 @@
 #define AQ_ACCESS_MAC			0x01
 #define AQ_FLASH_PARAMETERS		0x20
 #define AQ_PHY_POWER			0x31
+#define AQ_WOL_CFG			0x60
 #define AQ_PHY_OPS			0x61
 
 #define AQ_USB_PHY_SET_TIMEOUT		10000
@@ -145,8 +146,18 @@
 #define AQ_DSH_RETRIES_SHIFT	0x18
 #define AQ_DSH_RETRIES_MASK	0xF000000
 
+#define AQ_WOL_FLAG_MP			0x2
+
 /******************************************************************************/
 
+struct aqc111_wol_cfg {
+	u8 hw_addr[6];
+	u8 flags;
+	u8 rsvd[283];
+} __packed;
+
+#define WOL_CFG_SIZE sizeof(struct aqc111_wol_cfg)
+
 struct aqc111_data {
 	u16 rxctl;
 	u8 rx_checksum;
@@ -160,6 +171,7 @@ struct aqc111_data {
 		u8 rev;
 	} fw_ver;
 	u32 phy_cfg;
+	u8 wol_flags;
 };
 
 #define AQ_LS_MASK		0x8000
-- 
cgit v1.2.3


From fa61ce4db81c8c939c4d0cf4db83b1d2d9a401ad Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:47 +0000
Subject: net: usb: aqc111: Add ASIX's HW ids

It enables driver for ASIX products which are also based on
aqc111/112U chips.

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 7c859b9417f1..f69d566bd523 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -1249,6 +1249,44 @@ static const struct driver_info aqc111_info = {
 	.tx_fixup	= aqc111_tx_fixup,
 };
 
+#define ASIX111_DESC \
+"ASIX USB 3.1 Gen1 to 5G Multi-Gigabit Ethernet Adapter"
+
+static const struct driver_info asix111_info = {
+	.description	= ASIX111_DESC,
+	.bind		= aqc111_bind,
+	.unbind		= aqc111_unbind,
+	.status		= aqc111_status,
+	.link_reset	= aqc111_link_reset,
+	.reset		= aqc111_reset,
+	.stop		= aqc111_stop,
+	.flags		= FLAG_ETHER | FLAG_FRAMING_AX |
+			  FLAG_AVOID_UNLINK_URBS | FLAG_MULTI_PACKET,
+	.rx_fixup	= aqc111_rx_fixup,
+	.tx_fixup	= aqc111_tx_fixup,
+};
+
+#undef ASIX111_DESC
+
+#define ASIX112_DESC \
+"ASIX USB 3.1 Gen1 to 2.5G Multi-Gigabit Ethernet Adapter"
+
+static const struct driver_info asix112_info = {
+	.description	= ASIX112_DESC,
+	.bind		= aqc111_bind,
+	.unbind		= aqc111_unbind,
+	.status		= aqc111_status,
+	.link_reset	= aqc111_link_reset,
+	.reset		= aqc111_reset,
+	.stop		= aqc111_stop,
+	.flags		= FLAG_ETHER | FLAG_FRAMING_AX |
+			  FLAG_AVOID_UNLINK_URBS | FLAG_MULTI_PACKET,
+	.rx_fixup	= aqc111_rx_fixup,
+	.tx_fixup	= aqc111_tx_fixup,
+};
+
+#undef ASIX112_DESC
+
 static int aqc111_suspend(struct usb_interface *intf, pm_message_t message)
 {
 	struct usbnet *dev = usb_get_intfdata(intf);
@@ -1398,6 +1436,8 @@ static int aqc111_resume(struct usb_interface *intf)
 
 static const struct usb_device_id products[] = {
 	{AQC111_USB_ETH_DEV(0x2eca, 0xc101, aqc111_info)},
+	{AQC111_USB_ETH_DEV(0x0b95, 0x2790, asix111_info)},
+	{AQC111_USB_ETH_DEV(0x0b95, 0x2791, asix112_info)},
 	{ },/* END */
 };
 MODULE_DEVICE_TABLE(usb, products);
-- 
cgit v1.2.3


From d596df3a1421e56ff42508dcc8bae44224f9b231 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Mon, 26 Nov 2018 09:33:50 +0000
Subject: net: usb: aqc111: Extend cdc_ether blacklist

Added Aquantia and ASIX device IDs to prevent loading cdc_ether for
these devices. Our firmware reports CDC configuration simultaneously
with vendor specific.

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 5c42cf81a08b..b3b3c05903a1 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -562,6 +562,8 @@ static const struct driver_info wwan_info = {
 #define MICROSOFT_VENDOR_ID	0x045e
 #define UBLOX_VENDOR_ID		0x1546
 #define TPLINK_VENDOR_ID	0x2357
+#define AQUANTIA_VENDOR_ID	0x2eca
+#define ASIX_VENDOR_ID		0x0b95
 
 static const struct usb_device_id	products[] = {
 /* BLACKLIST !!
@@ -821,6 +823,30 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* Aquantia AQtion USB to 5GbE Controller (based on AQC111U) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(AQUANTIA_VENDOR_ID, 0xc101,
+				      USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
+/* ASIX USB 3.1 Gen1 to 5G Multi-Gigabit Ethernet Adapter(based on AQC111U) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(ASIX_VENDOR_ID, 0x2790, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
+/* ASIX USB 3.1 Gen1 to 2.5G Multi-Gigabit Ethernet Adapter(based on AQC112U) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(ASIX_VENDOR_ID, 0x2791, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* WHITELIST!!!
  *
  * CDC Ether uses two interfaces, not necessarily consecutive.
-- 
cgit v1.2.3


From ec036eb92e34298871c45ae6469cd8f7bb56c30e Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Mon, 26 Nov 2018 02:26:57 -0800
Subject: qed: Display port_id in the UFP debug messages.

MFW sends UFP notifications mostly during the device init phase and PFs
might not be assigned with a name by this time. Hence capturing port-id in
the debug messages would help in finding which PF the ufp notification was
sent to.

Also, fixed a minor scemantic issue in a debug print.

Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_mcp.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index a96364df4320..34ed75744566 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1619,7 +1619,7 @@ static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		qed_sp_pf_update_stag(p_hwfn);
 	}
 
-	DP_VERBOSE(p_hwfn, QED_MSG_SP, "ovlan  = %d hw_mode = 0x%x\n",
+	DP_VERBOSE(p_hwfn, QED_MSG_SP, "ovlan = %d hw_mode = 0x%x\n",
 		   p_hwfn->mcp_info->func_info.ovlan, p_hwfn->hw_info.hw_mode);
 
 	/* Acknowledge the MFW */
@@ -1641,7 +1641,9 @@ void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	val = (port_cfg & OEM_CFG_CHANNEL_TYPE_MASK) >>
 		OEM_CFG_CHANNEL_TYPE_OFFSET;
 	if (val != OEM_CFG_CHANNEL_TYPE_STAGGED)
-		DP_NOTICE(p_hwfn, "Incorrect UFP Channel type  %d\n", val);
+		DP_NOTICE(p_hwfn,
+			  "Incorrect UFP Channel type  %d port_id 0x%02x\n",
+			  val, MFW_PORT(p_hwfn));
 
 	val = (port_cfg & OEM_CFG_SCHED_TYPE_MASK) >> OEM_CFG_SCHED_TYPE_OFFSET;
 	if (val == OEM_CFG_SCHED_TYPE_ETS) {
@@ -1650,7 +1652,9 @@ void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		p_hwfn->ufp_info.mode = QED_UFP_MODE_VNIC_BW;
 	} else {
 		p_hwfn->ufp_info.mode = QED_UFP_MODE_UNKNOWN;
-		DP_NOTICE(p_hwfn, "Unknown UFP scheduling mode %d\n", val);
+		DP_NOTICE(p_hwfn,
+			  "Unknown UFP scheduling mode %d port_id 0x%02x\n",
+			  val, MFW_PORT(p_hwfn));
 	}
 
 	qed_mcp_get_shmem_func(p_hwfn, p_ptt, &shmem_info, MCP_PF_ID(p_hwfn));
@@ -1665,13 +1669,15 @@ void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		p_hwfn->ufp_info.pri_type = QED_UFP_PRI_OS;
 	} else {
 		p_hwfn->ufp_info.pri_type = QED_UFP_PRI_UNKNOWN;
-		DP_NOTICE(p_hwfn, "Unknown Host priority control %d\n", val);
+		DP_NOTICE(p_hwfn,
+			  "Unknown Host priority control %d port_id 0x%02x\n",
+			  val, MFW_PORT(p_hwfn));
 	}
 
 	DP_NOTICE(p_hwfn,
-		  "UFP shmem config: mode = %d tc = %d pri_type = %d\n",
-		  p_hwfn->ufp_info.mode,
-		  p_hwfn->ufp_info.tc, p_hwfn->ufp_info.pri_type);
+		  "UFP shmem config: mode = %d tc = %d pri_type = %d port_id 0x%02x\n",
+		  p_hwfn->ufp_info.mode, p_hwfn->ufp_info.tc,
+		  p_hwfn->ufp_info.pri_type, MFW_PORT(p_hwfn));
 }
 
 static int
-- 
cgit v1.2.3


From 149d3775f108c9b97f3309891f010b65e912c7b7 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Mon, 26 Nov 2018 02:26:58 -0800
Subject: qede: Simplify the usage of qede-flags.

The values represented by qede->flags is being used in mixed ways:
  1. As 'value' at some places e.g., QEDE_FLAGS_IS_VF usage
  2. As bit-mask(value) at some places e.g., QEDE_FLAGS_PTP_TX_IN_PRORGESS
     usage.
This implementation pose problems in future when we want to add more flag
values e.g., overlap of the values, overflow of 64-bit storage.

Updated the implementation to go with approach (2) for qede->flags.

Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede.h      | 11 +++++++----
 drivers/net/ethernet/qlogic/qede/qede_main.c |  2 +-
 drivers/net/ethernet/qlogic/qede/qede_ptp.c  |  6 +++---
 3 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index de98a974673b..f8ced12bfc1a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -168,6 +168,12 @@ struct qede_ptp;
 
 #define QEDE_RFS_MAX_FLTR	256
 
+enum qede_flags_bit {
+	QEDE_FLAGS_IS_VF = 0,
+	QEDE_FLAGS_PTP_TX_IN_PRORGESS,
+	QEDE_FLAGS_TX_TIMESTAMPING_EN
+};
+
 struct qede_dev {
 	struct qed_dev			*cdev;
 	struct net_device		*ndev;
@@ -177,10 +183,7 @@ struct qede_dev {
 	u8				dp_level;
 
 	unsigned long flags;
-#define QEDE_FLAG_IS_VF			BIT(0)
-#define IS_VF(edev)	(!!((edev)->flags & QEDE_FLAG_IS_VF))
-#define QEDE_TX_TIMESTAMPING_EN		BIT(1)
-#define QEDE_FLAGS_PTP_TX_IN_PRORGESS	BIT(2)
+#define IS_VF(edev)	(test_bit(QEDE_FLAGS_IS_VF, &(edev)->flags))
 
 	const struct qed_eth_ops	*ops;
 	struct qede_ptp			*ptp;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 46d0f2eaa0c0..0f1c480759e0 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1086,7 +1086,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 	}
 
 	if (is_vf)
-		edev->flags |= QEDE_FLAG_IS_VF;
+		set_bit(QEDE_FLAGS_IS_VF, &edev->flags);
 
 	qede_init_ndev(edev);
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 013ff567283c..5f3f42a25361 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -223,12 +223,12 @@ static int qede_ptp_cfg_filters(struct qede_dev *edev)
 
 	switch (ptp->tx_type) {
 	case HWTSTAMP_TX_ON:
-		edev->flags |= QEDE_TX_TIMESTAMPING_EN;
+		set_bit(QEDE_FLAGS_TX_TIMESTAMPING_EN, &edev->flags);
 		tx_type = QED_PTP_HWTSTAMP_TX_ON;
 		break;
 
 	case HWTSTAMP_TX_OFF:
-		edev->flags &= ~QEDE_TX_TIMESTAMPING_EN;
+		clear_bit(QEDE_FLAGS_TX_TIMESTAMPING_EN, &edev->flags);
 		tx_type = QED_PTP_HWTSTAMP_TX_OFF;
 		break;
 
@@ -518,7 +518,7 @@ void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb)
 	if (test_and_set_bit_lock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags))
 		return;
 
-	if (unlikely(!(edev->flags & QEDE_TX_TIMESTAMPING_EN))) {
+	if (unlikely(!test_bit(QEDE_FLAGS_TX_TIMESTAMPING_EN, &edev->flags))) {
 		DP_NOTICE(edev,
 			  "Tx timestamping was not enabled, this packet will not be timestamped\n");
 	} else if (unlikely(ptp->tx_skb)) {
-- 
cgit v1.2.3


From f04e48dbfaf732e0a9f926057e8f6fd44d45d1bb Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Mon, 26 Nov 2018 02:26:59 -0800
Subject: qede: Update link status only when interface is ready.

In the case of internal reload (e.g., mtu change), there could be a race
between link-up notification from mfw and the driver unload processing. In
such case kernel assumes the link is up and starts using the queues which
leads to the server crash.

Send link notification to the kernel only when driver has already requested
MFW for the link.

Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede.h      | 1 +
 drivers/net/ethernet/qlogic/qede/qede_main.c | 8 ++++++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index f8ced12bfc1a..8c0fe59eaad5 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -170,6 +170,7 @@ struct qede_ptp;
 
 enum qede_flags_bit {
 	QEDE_FLAGS_IS_VF = 0,
+	QEDE_FLAGS_LINK_REQUESTED,
 	QEDE_FLAGS_PTP_TX_IN_PRORGESS,
 	QEDE_FLAGS_TX_TIMESTAMPING_EN
 };
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 0f1c480759e0..efbb4f3f0f4b 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -2057,6 +2057,8 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 	if (!is_locked)
 		__qede_lock(edev);
 
+	clear_bit(QEDE_FLAGS_LINK_REQUESTED, &edev->flags);
+
 	edev->state = QEDE_STATE_CLOSED;
 
 	qede_rdma_dev_event_close(edev);
@@ -2163,6 +2165,8 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 	/* Program un-configured VLANs */
 	qede_configure_vlan_filters(edev);
 
+	set_bit(QEDE_FLAGS_LINK_REQUESTED, &edev->flags);
+
 	/* Ask for link-up using current configuration */
 	memset(&link_params, 0, sizeof(link_params));
 	link_params.link_up = true;
@@ -2258,8 +2262,8 @@ static void qede_link_update(void *dev, struct qed_link_output *link)
 {
 	struct qede_dev *edev = dev;
 
-	if (!netif_running(edev->ndev)) {
-		DP_VERBOSE(edev, NETIF_MSG_LINK, "Interface is not running\n");
+	if (!test_bit(QEDE_FLAGS_LINK_REQUESTED, &edev->flags)) {
+		DP_VERBOSE(edev, NETIF_MSG_LINK, "Interface is not ready\n");
 		return;
 	}
 
-- 
cgit v1.2.3


From 057d2b192be89df4c78fc8eb5d344d362d75e3c5 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Mon, 26 Nov 2018 02:27:00 -0800
Subject: qed: Add support for MBI upgrade over MFW.

The patch adds driver support for MBI image update through MFW.

Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_hsi.h  |  6 ++++
 drivers/net/ethernet/qlogic/qed/qed_main.c | 13 +++++++--
 drivers/net/ethernet/qlogic/qed/qed_mcp.c  | 45 +++++++++++++++---------------
 drivers/net/ethernet/qlogic/qed/qed_mcp.h  | 10 -------
 4 files changed, 40 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 5c221ebaa7b3..7e120b58ac58 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -12655,6 +12655,7 @@ struct public_drv_mb {
 #define DRV_MB_PARAM_DCBX_NOTIFY_MASK		0x000000FF
 #define DRV_MB_PARAM_DCBX_NOTIFY_SHIFT		3
 
+#define DRV_MB_PARAM_NVM_PUT_FILE_BEGIN_MBI     0x3
 #define DRV_MB_PARAM_NVM_LEN_OFFSET		24
 
 #define DRV_MB_PARAM_CFG_VF_MSIX_VF_ID_SHIFT	0
@@ -12814,6 +12815,11 @@ struct public_drv_mb {
 	union drv_union_data union_data;
 };
 
+#define FW_MB_PARAM_NVM_PUT_FILE_REQ_OFFSET_MASK	0x00ffffff
+#define FW_MB_PARAM_NVM_PUT_FILE_REQ_OFFSET_SHIFT	0
+#define FW_MB_PARAM_NVM_PUT_FILE_REQ_SIZE_MASK		0xff000000
+#define FW_MB_PARAM_NVM_PUT_FILE_REQ_SIZE_SHIFT		24
+
 enum MFW_DRV_MSG_TYPE {
 	MFW_DRV_MSG_LINK_CHANGE,
 	MFW_DRV_MSG_FLR_FW_ACK_FAILED,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index fff7f04d4525..4b3e68217502 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -1939,21 +1939,30 @@ exit:
  * 0B  |                       0x3 [command index]                            |
  * 4B  | b'0: check_response?   | b'1-31  reserved                            |
  * 8B  | File-type |                   reserved                               |
+ * 12B |                    Image length in bytes                             |
  *     \----------------------------------------------------------------------/
  *     Start a new file of the provided type
  */
 static int qed_nvm_flash_image_file_start(struct qed_dev *cdev,
 					  const u8 **data, bool *check_resp)
 {
+	u32 file_type, file_size = 0;
 	int rc;
 
 	*data += 4;
 	*check_resp = !!(**data & BIT(0));
 	*data += 4;
+	file_type = **data;
 
 	DP_VERBOSE(cdev, NETIF_MSG_DRV,
-		   "About to start a new file of type %02x\n", **data);
-	rc = qed_mcp_nvm_put_file_begin(cdev, **data);
+		   "About to start a new file of type %02x\n", file_type);
+	if (file_type == DRV_MB_PARAM_NVM_PUT_FILE_BEGIN_MBI) {
+		*data += 4;
+		file_size = *((u32 *)(*data));
+	}
+
+	rc = qed_mcp_nvm_write(cdev, QED_PUT_FILE_BEGIN, file_type,
+			       (u8 *)(&file_size), 4);
 	*data += 4;
 
 	return rc;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 34ed75744566..e7f18e34ff0d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -2745,24 +2745,6 @@ int qed_mcp_nvm_resp(struct qed_dev *cdev, u8 *p_buf)
 	return 0;
 }
 
-int qed_mcp_nvm_put_file_begin(struct qed_dev *cdev, u32 addr)
-{
-	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
-	struct qed_ptt *p_ptt;
-	u32 resp, param;
-	int rc;
-
-	p_ptt = qed_ptt_acquire(p_hwfn);
-	if (!p_ptt)
-		return -EBUSY;
-	rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_NVM_PUT_FILE_BEGIN, addr,
-			 &resp, &param);
-	cdev->mcp_nvm_resp = resp;
-	qed_ptt_release(p_hwfn, p_ptt);
-
-	return rc;
-}
-
 int qed_mcp_nvm_write(struct qed_dev *cdev,
 		      u32 cmd, u32 addr, u8 *p_buf, u32 len)
 {
@@ -2776,6 +2758,9 @@ int qed_mcp_nvm_write(struct qed_dev *cdev,
 		return -EBUSY;
 
 	switch (cmd) {
+	case QED_PUT_FILE_BEGIN:
+		nvm_cmd = DRV_MSG_CODE_NVM_PUT_FILE_BEGIN;
+		break;
 	case QED_PUT_FILE_DATA:
 		nvm_cmd = DRV_MSG_CODE_NVM_PUT_FILE_DATA;
 		break;
@@ -2788,10 +2773,14 @@ int qed_mcp_nvm_write(struct qed_dev *cdev,
 		goto out;
 	}
 
+	buf_size = min_t(u32, (len - buf_idx), MCP_DRV_NVM_BUF_LEN);
 	while (buf_idx < len) {
-		buf_size = min_t(u32, (len - buf_idx), MCP_DRV_NVM_BUF_LEN);
-		nvm_offset = ((buf_size << DRV_MB_PARAM_NVM_LEN_OFFSET) |
-			      addr) + buf_idx;
+		if (cmd == QED_PUT_FILE_BEGIN)
+			nvm_offset = addr;
+		else
+			nvm_offset = ((buf_size <<
+				       DRV_MB_PARAM_NVM_LEN_OFFSET) | addr) +
+				       buf_idx;
 		rc = qed_mcp_nvm_wr_cmd(p_hwfn, p_ptt, nvm_cmd, nvm_offset,
 					&resp, &param, buf_size,
 					(u32 *)&p_buf[buf_idx]);
@@ -2816,7 +2805,19 @@ int qed_mcp_nvm_write(struct qed_dev *cdev,
 		if (buf_idx % 0x1000 > (buf_idx + buf_size) % 0x1000)
 			usleep_range(1000, 2000);
 
-		buf_idx += buf_size;
+		/* For MBI upgrade, MFW response includes the next buffer offset
+		 * to be delivered to MFW.
+		 */
+		if (param && cmd == QED_PUT_FILE_DATA) {
+			buf_idx = QED_MFW_GET_FIELD(param,
+					FW_MB_PARAM_NVM_PUT_FILE_REQ_OFFSET);
+			buf_size = QED_MFW_GET_FIELD(param,
+					 FW_MB_PARAM_NVM_PUT_FILE_REQ_SIZE);
+		} else {
+			buf_idx += buf_size;
+			buf_size = min_t(u32, (len - buf_idx),
+					 MCP_DRV_NVM_BUF_LEN);
+		}
 	}
 
 	cdev->mcp_nvm_resp = resp;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 1adfe52b3905..eddf67798d6f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -542,16 +542,6 @@ int qed_mcp_nvm_read(struct qed_dev *cdev, u32 addr, u8 *p_buf, u32 len);
 int qed_mcp_nvm_write(struct qed_dev *cdev,
 		      u32 cmd, u32 addr, u8 *p_buf, u32 len);
 
-/**
- * @brief Put file begin
- *
- *  @param cdev
- *  @param addr - nvm offset
- *
- * @return int - 0 - operation was successful.
- */
-int qed_mcp_nvm_put_file_begin(struct qed_dev *cdev, u32 addr);
-
 /**
  * @brief Check latest response
  *
-- 
cgit v1.2.3


From 74be39ebba36e98a973ddb914fb41dc9e5129e36 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 26 Nov 2018 15:42:02 +0100
Subject: netns: remove net arg from rtnl_net_fill()

This argument is not used anymore.

Fixes: cab3c8ec8d57 ("netns: always provide the id to rtnl_net_fill()")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index fefe72774aeb..52b9620e3457 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -739,7 +739,7 @@ static int rtnl_net_get_size(void)
 }
 
 static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags,
-			 int cmd, struct net *net, int nsid)
+			 int cmd, int nsid)
 {
 	struct nlmsghdr *nlh;
 	struct rtgenmsg *rth;
@@ -801,7 +801,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	id = peernet2id(net, peer);
 	err = rtnl_net_fill(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
-			    RTM_NEWNSID, net, id);
+			    RTM_NEWNSID, id);
 	if (err < 0)
 		goto err_out;
 
@@ -816,7 +816,6 @@ out:
 }
 
 struct rtnl_net_dump_cb {
-	struct net *net;
 	struct sk_buff *skb;
 	struct netlink_callback *cb;
 	int idx;
@@ -833,7 +832,7 @@ static int rtnl_net_dumpid_one(int id, void *peer, void *data)
 
 	ret = rtnl_net_fill(net_cb->skb, NETLINK_CB(net_cb->cb->skb).portid,
 			    net_cb->cb->nlh->nlmsg_seq, NLM_F_MULTI,
-			    RTM_NEWNSID, net_cb->net, id);
+			    RTM_NEWNSID, id);
 	if (ret < 0)
 		return ret;
 
@@ -846,7 +845,6 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
 	struct rtnl_net_dump_cb net_cb = {
-		.net = net,
 		.skb = skb,
 		.cb = cb,
 		.idx = 0,
@@ -876,7 +874,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id)
 	if (!msg)
 		goto out;
 
-	err = rtnl_net_fill(msg, 0, 0, 0, cmd, net, id);
+	err = rtnl_net_fill(msg, 0, 0, 0, cmd, id);
 	if (err < 0)
 		goto err_out;
 
-- 
cgit v1.2.3


From a0732ad14d40ee7562c8c6e04b01af6134c82831 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 26 Nov 2018 15:42:03 +0100
Subject: netns: introduce 'struct net_fill_args'

This is a preparatory work. To avoid having to much arguments for the
function rtnl_net_fill(), a new structure is defined.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 48 ++++++++++++++++++++++++++++++++++--------------
 1 file changed, 34 insertions(+), 14 deletions(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 52b9620e3457..f8a5966b086c 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -738,20 +738,28 @@ static int rtnl_net_get_size(void)
 	       ;
 }
 
-static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags,
-			 int cmd, int nsid)
+struct net_fill_args {
+	u32 portid;
+	u32 seq;
+	int flags;
+	int cmd;
+	int nsid;
+};
+
+static int rtnl_net_fill(struct sk_buff *skb, struct net_fill_args *args)
 {
 	struct nlmsghdr *nlh;
 	struct rtgenmsg *rth;
 
-	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rth), flags);
+	nlh = nlmsg_put(skb, args->portid, args->seq, args->cmd, sizeof(*rth),
+			args->flags);
 	if (!nlh)
 		return -EMSGSIZE;
 
 	rth = nlmsg_data(nlh);
 	rth->rtgen_family = AF_UNSPEC;
 
-	if (nla_put_s32(skb, NETNSA_NSID, nsid))
+	if (nla_put_s32(skb, NETNSA_NSID, args->nsid))
 		goto nla_put_failure;
 
 	nlmsg_end(skb, nlh);
@@ -767,10 +775,15 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[NETNSA_MAX + 1];
+	struct net_fill_args fillargs = {
+		.portid = NETLINK_CB(skb).portid,
+		.seq = nlh->nlmsg_seq,
+		.cmd = RTM_NEWNSID,
+	};
 	struct nlattr *nla;
 	struct sk_buff *msg;
 	struct net *peer;
-	int err, id;
+	int err;
 
 	err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
 			  rtnl_net_policy, extack);
@@ -799,9 +812,8 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 	}
 
-	id = peernet2id(net, peer);
-	err = rtnl_net_fill(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
-			    RTM_NEWNSID, id);
+	fillargs.nsid = peernet2id(net, peer);
+	err = rtnl_net_fill(msg, &fillargs);
 	if (err < 0)
 		goto err_out;
 
@@ -817,7 +829,7 @@ out:
 
 struct rtnl_net_dump_cb {
 	struct sk_buff *skb;
-	struct netlink_callback *cb;
+	struct net_fill_args fillargs;
 	int idx;
 	int s_idx;
 };
@@ -830,9 +842,8 @@ static int rtnl_net_dumpid_one(int id, void *peer, void *data)
 	if (net_cb->idx < net_cb->s_idx)
 		goto cont;
 
-	ret = rtnl_net_fill(net_cb->skb, NETLINK_CB(net_cb->cb->skb).portid,
-			    net_cb->cb->nlh->nlmsg_seq, NLM_F_MULTI,
-			    RTM_NEWNSID, id);
+	net_cb->fillargs.nsid = id;
+	ret = rtnl_net_fill(net_cb->skb, &net_cb->fillargs);
 	if (ret < 0)
 		return ret;
 
@@ -846,7 +857,12 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
 	struct net *net = sock_net(skb->sk);
 	struct rtnl_net_dump_cb net_cb = {
 		.skb = skb,
-		.cb = cb,
+		.fillargs = {
+			.portid = NETLINK_CB(cb->skb).portid,
+			.seq = cb->nlh->nlmsg_seq,
+			.flags = NLM_F_MULTI,
+			.cmd = RTM_NEWNSID,
+		},
 		.idx = 0,
 		.s_idx = cb->args[0],
 	};
@@ -867,6 +883,10 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
 
 static void rtnl_net_notifyid(struct net *net, int cmd, int id)
 {
+	struct net_fill_args fillargs = {
+		.cmd = cmd,
+		.nsid = id,
+	};
 	struct sk_buff *msg;
 	int err = -ENOMEM;
 
@@ -874,7 +894,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id)
 	if (!msg)
 		goto out;
 
-	err = rtnl_net_fill(msg, 0, 0, 0, cmd, id);
+	err = rtnl_net_fill(msg, &fillargs);
 	if (err < 0)
 		goto err_out;
 
-- 
cgit v1.2.3


From cff478b9d9ccaee0de0e02700c63addf007b5d3c Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 26 Nov 2018 15:42:04 +0100
Subject: netns: add support of NETNSA_TARGET_NSID

Like it was done for link and address, add the ability to perform get/dump
in another netns by specifying a target nsid attribute.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/net_namespace.h |  1 +
 net/core/net_namespace.c           | 86 +++++++++++++++++++++++++++++++++-----
 2 files changed, 76 insertions(+), 11 deletions(-)

diff --git a/include/uapi/linux/net_namespace.h b/include/uapi/linux/net_namespace.h
index 0187c74d8889..0ed9dd61d32a 100644
--- a/include/uapi/linux/net_namespace.h
+++ b/include/uapi/linux/net_namespace.h
@@ -16,6 +16,7 @@ enum {
 	NETNSA_NSID,
 	NETNSA_PID,
 	NETNSA_FD,
+	NETNSA_TARGET_NSID,
 	__NETNSA_MAX,
 };
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index f8a5966b086c..885c54197e31 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -669,6 +669,7 @@ static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = {
 	[NETNSA_NSID]		= { .type = NLA_S32 },
 	[NETNSA_PID]		= { .type = NLA_U32 },
 	[NETNSA_FD]		= { .type = NLA_U32 },
+	[NETNSA_TARGET_NSID]	= { .type = NLA_S32 },
 };
 
 static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -780,9 +781,10 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
 		.seq = nlh->nlmsg_seq,
 		.cmd = RTM_NEWNSID,
 	};
+	struct net *peer, *target = net;
+	bool put_target = false;
 	struct nlattr *nla;
 	struct sk_buff *msg;
-	struct net *peer;
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
@@ -806,13 +808,27 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return PTR_ERR(peer);
 	}
 
+	if (tb[NETNSA_TARGET_NSID]) {
+		int id = nla_get_s32(tb[NETNSA_TARGET_NSID]);
+
+		target = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, id);
+		if (IS_ERR(target)) {
+			NL_SET_BAD_ATTR(extack, tb[NETNSA_TARGET_NSID]);
+			NL_SET_ERR_MSG(extack,
+				       "Target netns reference is invalid");
+			err = PTR_ERR(target);
+			goto out;
+		}
+		put_target = true;
+	}
+
 	msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
 	if (!msg) {
 		err = -ENOMEM;
 		goto out;
 	}
 
-	fillargs.nsid = peernet2id(net, peer);
+	fillargs.nsid = peernet2id(target, peer);
 	err = rtnl_net_fill(msg, &fillargs);
 	if (err < 0)
 		goto err_out;
@@ -823,15 +839,19 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
 err_out:
 	nlmsg_free(msg);
 out:
+	if (put_target)
+		put_net(target);
 	put_net(peer);
 	return err;
 }
 
 struct rtnl_net_dump_cb {
+	struct net *tgt_net;
 	struct sk_buff *skb;
 	struct net_fill_args fillargs;
 	int idx;
 	int s_idx;
+	bool put_tgt_net;
 };
 
 static int rtnl_net_dumpid_one(int id, void *peer, void *data)
@@ -852,10 +872,50 @@ cont:
 	return 0;
 }
 
+static int rtnl_valid_dump_net_req(const struct nlmsghdr *nlh, struct sock *sk,
+				   struct rtnl_net_dump_cb *net_cb,
+				   struct netlink_callback *cb)
+{
+	struct netlink_ext_ack *extack = cb->extack;
+	struct nlattr *tb[NETNSA_MAX + 1];
+	int err, i;
+
+	err = nlmsg_parse_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
+				 rtnl_net_policy, extack);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i <= NETNSA_MAX; i++) {
+		if (!tb[i])
+			continue;
+
+		if (i == NETNSA_TARGET_NSID) {
+			struct net *net;
+
+			net = rtnl_get_net_ns_capable(sk, nla_get_s32(tb[i]));
+			if (IS_ERR(net)) {
+				NL_SET_BAD_ATTR(extack, tb[i]);
+				NL_SET_ERR_MSG(extack,
+					       "Invalid target network namespace id");
+				return PTR_ERR(net);
+			}
+			net_cb->tgt_net = net;
+			net_cb->put_tgt_net = true;
+		} else {
+			NL_SET_BAD_ATTR(extack, tb[i]);
+			NL_SET_ERR_MSG(extack,
+				       "Unsupported attribute in dump request");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	struct net *net = sock_net(skb->sk);
 	struct rtnl_net_dump_cb net_cb = {
+		.tgt_net = sock_net(skb->sk),
 		.skb = skb,
 		.fillargs = {
 			.portid = NETLINK_CB(cb->skb).portid,
@@ -866,19 +926,23 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
 		.idx = 0,
 		.s_idx = cb->args[0],
 	};
+	int err = 0;
 
-	if (cb->strict_check &&
-	    nlmsg_attrlen(cb->nlh, sizeof(struct rtgenmsg))) {
-			NL_SET_ERR_MSG(cb->extack, "Unknown data in network namespace id dump request");
-			return -EINVAL;
+	if (cb->strict_check) {
+		err = rtnl_valid_dump_net_req(cb->nlh, skb->sk, &net_cb, cb);
+		if (err < 0)
+			goto end;
 	}
 
-	spin_lock_bh(&net->nsid_lock);
-	idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb);
-	spin_unlock_bh(&net->nsid_lock);
+	spin_lock_bh(&net_cb.tgt_net->nsid_lock);
+	idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb);
+	spin_unlock_bh(&net_cb.tgt_net->nsid_lock);
 
 	cb->args[0] = net_cb.idx;
-	return skb->len;
+end:
+	if (net_cb.put_tgt_net)
+		put_net(net_cb.tgt_net);
+	return err < 0 ? err : skb->len;
 }
 
 static void rtnl_net_notifyid(struct net *net, int cmd, int id)
-- 
cgit v1.2.3


From 3a4f68bf660414801781fd06506a9c75c2d936e5 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 26 Nov 2018 15:42:05 +0100
Subject: netns: enable to specify a nsid for a get request

Combined with NETNSA_TARGET_NSID, it enables to "translate" a nsid from one
netns to a nsid of another netns.
This is useful when using NETLINK_F_LISTEN_ALL_NSID because it helps the
user to interpret a nsid received from an other netns.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 885c54197e31..dd25fb22ad45 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -797,6 +797,11 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
 	} else if (tb[NETNSA_FD]) {
 		peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD]));
 		nla = tb[NETNSA_FD];
+	} else if (tb[NETNSA_NSID]) {
+		peer = get_net_ns_by_id(net, nla_get_u32(tb[NETNSA_NSID]));
+		if (!peer)
+			peer = ERR_PTR(-ENOENT);
+		nla = tb[NETNSA_NSID];
 	} else {
 		NL_SET_ERR_MSG(extack, "Peer netns reference is missing");
 		return -EINVAL;
-- 
cgit v1.2.3


From 288f06a001eb6265122c620295b68a0dd53d1482 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 26 Nov 2018 15:42:06 +0100
Subject: netns: enable to dump full nsid translation table

Like the previous patch, the goal is to ease to convert nsids from one
netns to another netns.
A new attribute (NETNSA_CURRENT_NSID) is added to the kernel answer when
NETNSA_TARGET_NSID is provided, thus the user can easily convert nsids.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/net_namespace.h |  1 +
 net/core/net_namespace.c           | 32 ++++++++++++++++++++++++++------
 2 files changed, 27 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/net_namespace.h b/include/uapi/linux/net_namespace.h
index 0ed9dd61d32a..9f9956809565 100644
--- a/include/uapi/linux/net_namespace.h
+++ b/include/uapi/linux/net_namespace.h
@@ -17,6 +17,7 @@ enum {
 	NETNSA_PID,
 	NETNSA_FD,
 	NETNSA_TARGET_NSID,
+	NETNSA_CURRENT_NSID,
 	__NETNSA_MAX,
 };
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index dd25fb22ad45..05b23b285058 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -736,6 +736,7 @@ static int rtnl_net_get_size(void)
 {
 	return NLMSG_ALIGN(sizeof(struct rtgenmsg))
 	       + nla_total_size(sizeof(s32)) /* NETNSA_NSID */
+	       + nla_total_size(sizeof(s32)) /* NETNSA_CURRENT_NSID */
 	       ;
 }
 
@@ -745,6 +746,8 @@ struct net_fill_args {
 	int flags;
 	int cmd;
 	int nsid;
+	bool add_ref;
+	int ref_nsid;
 };
 
 static int rtnl_net_fill(struct sk_buff *skb, struct net_fill_args *args)
@@ -763,6 +766,10 @@ static int rtnl_net_fill(struct sk_buff *skb, struct net_fill_args *args)
 	if (nla_put_s32(skb, NETNSA_NSID, args->nsid))
 		goto nla_put_failure;
 
+	if (args->add_ref &&
+	    nla_put_s32(skb, NETNSA_CURRENT_NSID, args->ref_nsid))
+		goto nla_put_failure;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -782,7 +789,6 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
 		.cmd = RTM_NEWNSID,
 	};
 	struct net *peer, *target = net;
-	bool put_target = false;
 	struct nlattr *nla;
 	struct sk_buff *msg;
 	int err;
@@ -824,7 +830,8 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
 			err = PTR_ERR(target);
 			goto out;
 		}
-		put_target = true;
+		fillargs.add_ref = true;
+		fillargs.ref_nsid = peernet2id(net, peer);
 	}
 
 	msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
@@ -844,7 +851,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh,
 err_out:
 	nlmsg_free(msg);
 out:
-	if (put_target)
+	if (fillargs.add_ref)
 		put_net(target);
 	put_net(peer);
 	return err;
@@ -852,11 +859,11 @@ out:
 
 struct rtnl_net_dump_cb {
 	struct net *tgt_net;
+	struct net *ref_net;
 	struct sk_buff *skb;
 	struct net_fill_args fillargs;
 	int idx;
 	int s_idx;
-	bool put_tgt_net;
 };
 
 static int rtnl_net_dumpid_one(int id, void *peer, void *data)
@@ -868,6 +875,8 @@ static int rtnl_net_dumpid_one(int id, void *peer, void *data)
 		goto cont;
 
 	net_cb->fillargs.nsid = id;
+	if (net_cb->fillargs.add_ref)
+		net_cb->fillargs.ref_nsid = __peernet2id(net_cb->ref_net, peer);
 	ret = rtnl_net_fill(net_cb->skb, &net_cb->fillargs);
 	if (ret < 0)
 		return ret;
@@ -904,8 +913,9 @@ static int rtnl_valid_dump_net_req(const struct nlmsghdr *nlh, struct sock *sk,
 					       "Invalid target network namespace id");
 				return PTR_ERR(net);
 			}
+			net_cb->fillargs.add_ref = true;
+			net_cb->ref_net = net_cb->tgt_net;
 			net_cb->tgt_net = net;
-			net_cb->put_tgt_net = true;
 		} else {
 			NL_SET_BAD_ATTR(extack, tb[i]);
 			NL_SET_ERR_MSG(extack,
@@ -940,12 +950,22 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 
 	spin_lock_bh(&net_cb.tgt_net->nsid_lock);
+	if (net_cb.fillargs.add_ref &&
+	    !net_eq(net_cb.ref_net, net_cb.tgt_net) &&
+	    !spin_trylock_bh(&net_cb.ref_net->nsid_lock)) {
+		spin_unlock_bh(&net_cb.tgt_net->nsid_lock);
+		err = -EAGAIN;
+		goto end;
+	}
 	idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb);
+	if (net_cb.fillargs.add_ref &&
+	    !net_eq(net_cb.ref_net, net_cb.tgt_net))
+		spin_unlock_bh(&net_cb.ref_net->nsid_lock);
 	spin_unlock_bh(&net_cb.tgt_net->nsid_lock);
 
 	cb->args[0] = net_cb.idx;
 end:
-	if (net_cb.put_tgt_net)
+	if (net_cb.fillargs.add_ref)
 		put_net(net_cb.tgt_net);
 	return err < 0 ? err : skb->len;
 }
-- 
cgit v1.2.3


From 5d497936756fa2a917643ca688585d721dc6d31e Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Mon, 26 Nov 2018 18:43:00 +0000
Subject: net: hns3: Config NIC port speed same as that of optical module

Port 0/1 of HiP08 supports 10G and 25G. This patch adds a
change to configure NIC port speed same as that of  optical
module(SFP/QFSP). Driver gets the optical module speed and
sets NIC port speed accordingly.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 23 +++---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 84 ++++++++++------------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  2 +
 3 files changed, 49 insertions(+), 60 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 2b90410eeac2..e1805b972628 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -90,7 +90,6 @@ enum hclge_opcode_type {
 	/* MAC command */
 	HCLGE_OPC_CONFIG_MAC_MODE	= 0x0301,
 	HCLGE_OPC_CONFIG_AN_MODE	= 0x0304,
-	HCLGE_OPC_QUERY_AN_RESULT	= 0x0306,
 	HCLGE_OPC_QUERY_LINK_STATUS	= 0x0307,
 	HCLGE_OPC_CONFIG_MAX_FRM_SIZE	= 0x0308,
 	HCLGE_OPC_CONFIG_SPEED_DUP	= 0x0309,
@@ -212,6 +211,9 @@ enum hclge_opcode_type {
 	/* Led command */
 	HCLGE_OPC_LED_STATUS_CFG	= 0xB000,
 
+	/* SFP command */
+	HCLGE_OPC_SFP_GET_SPEED		= 0x7104,
+
 	/* Error INT commands */
 	HCLGE_TM_SCH_ECC_INT_EN		= 0x0829,
 	HCLGE_TM_SCH_ECC_ERR_RINT_CMD	= 0x082d,
@@ -544,20 +546,6 @@ struct hclge_config_mac_speed_dup_cmd {
 	u8 rsv[22];
 };
 
-#define HCLGE_QUERY_SPEED_S		3
-#define HCLGE_QUERY_AN_B		0
-#define HCLGE_QUERY_DUPLEX_B		2
-
-#define HCLGE_QUERY_SPEED_M		GENMASK(4, 0)
-#define HCLGE_QUERY_AN_M		BIT(HCLGE_QUERY_AN_B)
-#define HCLGE_QUERY_DUPLEX_M		BIT(HCLGE_QUERY_DUPLEX_B)
-
-struct hclge_query_an_speed_dup_cmd {
-	u8 an_syn_dup_speed;
-	u8 pause;
-	u8 rsv[23];
-};
-
 #define HCLGE_RING_ID_MASK		GENMASK(9, 0)
 #define HCLGE_TQP_ENABLE_B		0
 
@@ -574,6 +562,11 @@ struct hclge_config_auto_neg_cmd {
 	u8      rsv[20];
 };
 
+struct hclge_sfp_speed_cmd {
+	__le32	sfp_speed;
+	u32	rsv[5];
+};
+
 #define HCLGE_MAC_UPLINK_PORT		0x100
 
 struct hclge_config_max_frm_size_cmd {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 696cb53013bc..1c8cf840dff8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1896,37 +1896,6 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed,
 	return hclge_cfg_mac_speed_dup(hdev, speed, duplex);
 }
 
-static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed,
-					u8 *duplex)
-{
-	struct hclge_query_an_speed_dup_cmd *req;
-	struct hclge_desc desc;
-	int speed_tmp;
-	int ret;
-
-	req = (struct hclge_query_an_speed_dup_cmd *)desc.data;
-
-	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_AN_RESULT, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"mac speed/autoneg/duplex query cmd failed %d\n",
-			ret);
-		return ret;
-	}
-
-	*duplex = hnae3_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_DUPLEX_B);
-	speed_tmp = hnae3_get_field(req->an_syn_dup_speed, HCLGE_QUERY_SPEED_M,
-				    HCLGE_QUERY_SPEED_S);
-
-	ret = hclge_parse_speed(speed_tmp, speed);
-	if (ret)
-		dev_err(&hdev->pdev->dev,
-			"could not parse speed(=%d), %d\n", speed_tmp, ret);
-
-	return ret;
-}
-
 static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable)
 {
 	struct hclge_config_auto_neg_cmd *req;
@@ -1973,6 +1942,7 @@ static int hclge_mac_init(struct hclge_dev *hdev)
 	struct hclge_mac *mac = &hdev->hw.mac;
 	int ret;
 
+	hdev->support_sfp_query = true;
 	hdev->hw.mac.duplex = HCLGE_MAC_FULL;
 	ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed,
 					 hdev->hw.mac.duplex);
@@ -2082,34 +2052,58 @@ static void hclge_update_link_status(struct hclge_dev *hdev)
 	}
 }
 
+static int hclge_get_sfp_speed(struct hclge_dev *hdev, u32 *speed)
+{
+	struct hclge_sfp_speed_cmd *resp = NULL;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SFP_GET_SPEED, true);
+	resp = (struct hclge_sfp_speed_cmd *)desc.data;
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret == -EOPNOTSUPP) {
+		dev_warn(&hdev->pdev->dev,
+			 "IMP do not support get SFP speed %d\n", ret);
+		return ret;
+	} else if (ret) {
+		dev_err(&hdev->pdev->dev, "get sfp speed failed %d\n", ret);
+		return ret;
+	}
+
+	*speed = resp->sfp_speed;
+
+	return 0;
+}
+
 static int hclge_update_speed_duplex(struct hclge_dev *hdev)
 {
 	struct hclge_mac mac = hdev->hw.mac;
-	u8 duplex;
 	int speed;
 	int ret;
 
-	/* get the speed and duplex as autoneg'result from mac cmd when phy
+	/* get the speed from SFP cmd when phy
 	 * doesn't exit.
 	 */
-	if (mac.phydev || !mac.autoneg)
+	if (mac.phydev)
 		return 0;
 
-	ret = hclge_query_mac_an_speed_dup(hdev, &speed, &duplex);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"mac autoneg/speed/duplex query failed %d\n", ret);
-		return ret;
-	}
+	/* if IMP does not support get SFP/qSFP speed, return directly */
+	if (!hdev->support_sfp_query)
+		return 0;
 
-	ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"mac speed/duplex config failed %d\n", ret);
+	ret = hclge_get_sfp_speed(hdev, &speed);
+	if (ret == -EOPNOTSUPP) {
+		hdev->support_sfp_query = false;
+		return ret;
+	} else if (ret) {
 		return ret;
 	}
 
-	return 0;
+	if (speed == HCLGE_MAC_SPEED_UNKNOWN)
+		return 0; /* do nothing if no SFP */
+
+	/* must config full duplex for SFP */
+	return hclge_cfg_mac_speed_dup(hdev, speed, HCLGE_MAC_FULL);
 }
 
 static int hclge_update_speed_duplex_h(struct hnae3_handle *handle)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 4122ad1aab1f..0dd23a1d81ea 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -155,6 +155,7 @@ enum hclge_evt_cause {
 #define HCLGE_MPF_ENBALE 1
 
 enum HCLGE_MAC_SPEED {
+	HCLGE_MAC_SPEED_UNKNOWN = 0,		/* unknown */
 	HCLGE_MAC_SPEED_10M	= 10,		/* 10 Mbps */
 	HCLGE_MAC_SPEED_100M	= 100,		/* 100 Mbps */
 	HCLGE_MAC_SPEED_1G	= 1000,		/* 1000 Mbps   = 1 Gbps */
@@ -624,6 +625,7 @@ struct hclge_dev {
 	u8 hw_tc_map;
 	u8 tc_num_last_time;
 	enum hclge_fc_mode fc_mode_last_time;
+	u8 support_sfp_query;
 
 #define HCLGE_FLAG_TC_BASE_SCH_MODE		1
 #define HCLGE_FLAG_VNET_BASE_SCH_MODE		2
-- 
cgit v1.2.3


From bd7153bd83b806bfcc2e79b7a6f43aa653d06ef3 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 26 Nov 2018 20:24:16 +0100
Subject: r8169: remove unneeded mmiowb barriers

writex() has implicit barriers, that's what makes it different from
writex_relaxed(). Therefore these calls to mmiowb() can be removed.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 3624e67aef72..e26c48bd54a2 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1283,13 +1283,11 @@ static u16 rtl_get_events(struct rtl8169_private *tp)
 static void rtl_ack_events(struct rtl8169_private *tp, u16 bits)
 {
 	RTL_W16(tp, IntrStatus, bits);
-	mmiowb();
 }
 
 static void rtl_irq_disable(struct rtl8169_private *tp)
 {
 	RTL_W16(tp, IntrMask, 0);
-	mmiowb();
 }
 
 #define RTL_EVENT_NAPI_RX	(RxOK | RxErr)
@@ -6127,10 +6125,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	if (unlikely(stop_queue))
 		netif_stop_queue(dev);
 
-	if (__netdev_sent_queue(dev, skb->len, skb->xmit_more)) {
+	if (__netdev_sent_queue(dev, skb->len, skb->xmit_more))
 		RTL_W8(tp, TxPoll, NPQ);
-		mmiowb();
-	}
 
 	if (unlikely(stop_queue)) {
 		/* Sync with rtl_tx:
@@ -6481,9 +6477,7 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
 
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
-
 		rtl_irq_enable(tp);
-		mmiowb();
 	}
 
 	return work_done;
-- 
cgit v1.2.3


From 16e8c4ca21a238cdf0355475bf15bd72e92feb8f Mon Sep 17 00:00:00 2001
From: Vijay Khemka <vijaykhemka@fb.com>
Date: Mon, 26 Nov 2018 13:49:04 -0800
Subject: net/ncsi: Add NCSI Mellanox OEM command

This patch adds OEM Mellanox commands and response handling. It also
defines OEM Get MAC Address handler to get and configure the device.

ncsi_oem_gma_handler_mlx: This handler send NCSI mellanox command for
getting mac address.
ncsi_rsp_handler_oem_mlx: This handles response received for all
mellanox OEM commands.
ncsi_rsp_handler_oem_mlx_gma: This handles get mac address response and
set it to device.

Signed-off-by: Vijay Khemka <vijaykhemka@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ncsi/internal.h    |  5 +++++
 net/ncsi/ncsi-manage.c | 28 +++++++++++++++++++++++++++-
 net/ncsi/ncsi-pkt.h    |  9 +++++++++
 net/ncsi/ncsi-rsp.c    | 41 ++++++++++++++++++++++++++++++++++++++++-
 4 files changed, 81 insertions(+), 2 deletions(-)

diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index 9e3642b802c4..87505600dbb2 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -73,10 +73,15 @@ enum {
 #define NCSI_OEM_MFR_BCM_ID             0x113d
 /* Broadcom specific OEM Command */
 #define NCSI_OEM_BCM_CMD_GMA            0x01   /* CMD ID for Get MAC */
+/* Mellanox specific OEM Command */
+#define NCSI_OEM_MLX_CMD_GMA            0x00   /* CMD ID for Get MAC */
+#define NCSI_OEM_MLX_CMD_GMA_PARAM      0x1b   /* Parameter for GMA  */
 /* OEM Command payload lengths*/
 #define NCSI_OEM_BCM_CMD_GMA_LEN        12
+#define NCSI_OEM_MLX_CMD_GMA_LEN        8
 /* Mac address offset in OEM response */
 #define BCM_MAC_ADDR_OFFSET             28
+#define MLX_MAC_ADDR_OFFSET             8
 
 
 struct ncsi_channel_version {
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 92e59f07f9a7..31359d5e14ad 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -710,12 +710,38 @@ static int ncsi_oem_gma_handler_bcm(struct ncsi_cmd_arg *nca)
 	return ret;
 }
 
+static int ncsi_oem_gma_handler_mlx(struct ncsi_cmd_arg *nca)
+{
+	union {
+		u8 data_u8[NCSI_OEM_MLX_CMD_GMA_LEN];
+		u32 data_u32[NCSI_OEM_MLX_CMD_GMA_LEN / sizeof(u32)];
+	} u;
+	int ret = 0;
+
+	nca->payload = NCSI_OEM_MLX_CMD_GMA_LEN;
+
+	memset(&u, 0, sizeof(u));
+	u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID);
+	u.data_u8[5] = NCSI_OEM_MLX_CMD_GMA;
+	u.data_u8[6] = NCSI_OEM_MLX_CMD_GMA_PARAM;
+
+	nca->data = u.data_u8;
+
+	ret = ncsi_xmit_cmd(nca);
+	if (ret)
+		netdev_err(nca->ndp->ndev.dev,
+			   "NCSI: Failed to transmit cmd 0x%x during configure\n",
+			   nca->type);
+	return ret;
+}
+
 /* OEM Command handlers initialization */
 static struct ncsi_oem_gma_handler {
 	unsigned int	mfr_id;
 	int		(*handler)(struct ncsi_cmd_arg *nca);
 } ncsi_oem_gma_handlers[] = {
-	{ NCSI_OEM_MFR_BCM_ID, ncsi_oem_gma_handler_bcm }
+	{ NCSI_OEM_MFR_BCM_ID, ncsi_oem_gma_handler_bcm },
+	{ NCSI_OEM_MFR_MLX_ID, ncsi_oem_gma_handler_mlx }
 };
 
 static int ncsi_gma_handler(struct ncsi_cmd_arg *nca, unsigned int mf_id)
diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h
index 4d3f06be38bd..2a6d83a596c9 100644
--- a/net/ncsi/ncsi-pkt.h
+++ b/net/ncsi/ncsi-pkt.h
@@ -165,6 +165,15 @@ struct ncsi_rsp_oem_pkt {
 	unsigned char           data[];      /* Payload data      */
 };
 
+/* Mellanox Response Data */
+struct ncsi_rsp_oem_mlx_pkt {
+	unsigned char           cmd_rev;     /* Command Revision  */
+	unsigned char           cmd;         /* Command ID        */
+	unsigned char           param;       /* Parameter         */
+	unsigned char           optional;    /* Optional data     */
+	unsigned char           data[];      /* Data              */
+};
+
 /* Broadcom Response Data */
 struct ncsi_rsp_oem_bcm_pkt {
 	unsigned char           ver;         /* Payload Version   */
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index de7737a27889..dc07fcc7938e 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -611,6 +611,45 @@ static int ncsi_rsp_handler_snfc(struct ncsi_request *nr)
 	return 0;
 }
 
+/* Response handler for Mellanox command Get Mac Address */
+static int ncsi_rsp_handler_oem_mlx_gma(struct ncsi_request *nr)
+{
+	struct ncsi_dev_priv *ndp = nr->ndp;
+	struct net_device *ndev = ndp->ndev.dev;
+	const struct net_device_ops *ops = ndev->netdev_ops;
+	struct ncsi_rsp_oem_pkt *rsp;
+	struct sockaddr saddr;
+	int ret = 0;
+
+	/* Get the response header */
+	rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp);
+
+	saddr.sa_family = ndev->type;
+	ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	memcpy(saddr.sa_data, &rsp->data[MLX_MAC_ADDR_OFFSET], ETH_ALEN);
+	ret = ops->ndo_set_mac_address(ndev, &saddr);
+	if (ret < 0)
+		netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n");
+
+	return ret;
+}
+
+/* Response handler for Mellanox card */
+static int ncsi_rsp_handler_oem_mlx(struct ncsi_request *nr)
+{
+	struct ncsi_rsp_oem_mlx_pkt *mlx;
+	struct ncsi_rsp_oem_pkt *rsp;
+
+	/* Get the response header */
+	rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp);
+	mlx = (struct ncsi_rsp_oem_mlx_pkt *)(rsp->data);
+
+	if (mlx->cmd == NCSI_OEM_MLX_CMD_GMA &&
+	    mlx->param == NCSI_OEM_MLX_CMD_GMA_PARAM)
+		return ncsi_rsp_handler_oem_mlx_gma(nr);
+	return 0;
+}
+
 /* Response handler for Broadcom command Get Mac Address */
 static int ncsi_rsp_handler_oem_bcm_gma(struct ncsi_request *nr)
 {
@@ -655,7 +694,7 @@ static struct ncsi_rsp_oem_handler {
 	unsigned int	mfr_id;
 	int		(*handler)(struct ncsi_request *nr);
 } ncsi_rsp_oem_handlers[] = {
-	{ NCSI_OEM_MFR_MLX_ID, NULL },
+	{ NCSI_OEM_MFR_MLX_ID, ncsi_rsp_handler_oem_mlx },
 	{ NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm }
 };
 
-- 
cgit v1.2.3


From e7395f1f4ba24dc4116b0b87b4ed0664109b450a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 26 Nov 2018 14:49:12 -0800
Subject: tcp: remove hdrlen argument from tcp_queue_rcv()

Only one caller needs to pull TCP headers, so lets
move __skb_pull() to the caller side.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 568dbf3b711a..f32397890b6d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4603,13 +4603,12 @@ end:
 	}
 }
 
-static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen,
-		  bool *fragstolen)
+static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
+				      bool *fragstolen)
 {
 	int eaten;
 	struct sk_buff *tail = skb_peek_tail(&sk->sk_receive_queue);
 
-	__skb_pull(skb, hdrlen);
 	eaten = (tail &&
 		 tcp_try_coalesce(sk, tail,
 				  skb, fragstolen)) ? 1 : 0;
@@ -4660,7 +4659,7 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size;
 	TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1;
 
-	if (tcp_queue_rcv(sk, skb, 0, &fragstolen)) {
+	if (tcp_queue_rcv(sk, skb, &fragstolen)) {
 		WARN_ON_ONCE(fragstolen); /* should not happen */
 		__kfree_skb(skb);
 	}
@@ -4720,7 +4719,7 @@ queue_and_out:
 			goto drop;
 		}
 
-		eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
+		eaten = tcp_queue_rcv(sk, skb, &fragstolen);
 		if (skb->len)
 			tcp_event_data_recv(sk, skb);
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
@@ -5596,8 +5595,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS);
 
 			/* Bulk data transfer: receiver */
-			eaten = tcp_queue_rcv(sk, skb, tcp_header_len,
-					      &fragstolen);
+			__skb_pull(skb, tcp_header_len);
+			eaten = tcp_queue_rcv(sk, skb, &fragstolen);
 
 			tcp_event_data_recv(sk, skb);
 
-- 
cgit v1.2.3


From a1bcaf023120d44c3500cbcf5769bb3cf034c9ca Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Mon, 26 Nov 2018 22:25:56 -0800
Subject: bnx2x: Add MBI version to ethtool driver query output.

The patch populates the MBI version in the ethtool driver query data.
Adding 'extended_dev_info_shared_cfg' structure describing the nvram
structure, this is required to access the mbi version string.

Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c    | 24 +++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h    |  5 +++++
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index a4a90b6cdb46..68aae3ee31ea 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1105,11 +1105,33 @@ static void bnx2x_get_drvinfo(struct net_device *dev,
 			      struct ethtool_drvinfo *info)
 {
 	struct bnx2x *bp = netdev_priv(dev);
+	char version[ETHTOOL_FWVERS_LEN];
+	int ext_dev_info_offset;
+	u32 mbi;
 
 	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
 	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
 
-	bnx2x_fill_fw_str(bp, info->fw_version, sizeof(info->fw_version));
+	if (SHMEM2_HAS(bp, extended_dev_info_shared_addr)) {
+		ext_dev_info_offset = SHMEM2_RD(bp,
+						extended_dev_info_shared_addr);
+		mbi = REG_RD(bp, ext_dev_info_offset +
+			     offsetof(struct extended_dev_info_shared_cfg,
+				      mbi_version));
+		if (mbi) {
+			memset(version, 0, sizeof(version));
+			snprintf(version, ETHTOOL_FWVERS_LEN, "mbi %d.%d.%d ",
+				 (mbi & 0xff000000) >> 24,
+				 (mbi & 0x00ff0000) >> 16,
+				 (mbi & 0x0000ff00) >> 8);
+			strlcpy(info->fw_version, version,
+				sizeof(info->fw_version));
+		}
+	}
+
+	memset(version, 0, sizeof(version));
+	bnx2x_fill_fw_str(bp, version, ETHTOOL_FWVERS_LEN);
+	strlcat(info->fw_version, version, sizeof(info->fw_version));
 
 	strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
index f8b810313094..d9057c8bbeef 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
@@ -1140,6 +1140,11 @@ struct shm_dev_info {				/* size */
 
 };
 
+struct extended_dev_info_shared_cfg {
+	u32 reserved[18];
+	u32 mbi_version;
+	u32 mbi_date;
+};
 
 #if !defined(__LITTLE_ENDIAN) && !defined(__BIG_ENDIAN)
 	#error "Missing either LITTLE_ENDIAN or BIG_ENDIAN definition."
-- 
cgit v1.2.3


From 96a60ae886a479196e84b6f56f217c9c23b7cb2b Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Mon, 26 Nov 2018 22:25:57 -0800
Subject: bnx2x: Add storm FW version to ethtool driver query output.

The patch populates the Storm FW version in the ethtool driver query data.

Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 68aae3ee31ea..749d0ef44371 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1112,6 +1112,12 @@ static void bnx2x_get_drvinfo(struct net_device *dev,
 	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
 	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
 
+	memset(version, 0, sizeof(version));
+	snprintf(version, ETHTOOL_FWVERS_LEN, " storm %d.%d.%d.%d",
+		 BCM_5710_FW_MAJOR_VERSION, BCM_5710_FW_MINOR_VERSION,
+		 BCM_5710_FW_REVISION_VERSION, BCM_5710_FW_ENGINEERING_VERSION);
+	strlcat(info->version, version, sizeof(info->version));
+
 	if (SHMEM2_HAS(bp, extended_dev_info_shared_addr)) {
 		ext_dev_info_offset = SHMEM2_RD(bp,
 						extended_dev_info_shared_addr);
-- 
cgit v1.2.3


From 86d1d8b72caf648e5b14ac274f9afeaab58bbae1 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 27 Nov 2018 20:52:24 -0800
Subject: net/ipv4: Fix missing raw_init when CONFIG_PROC_FS is disabled

Randy reported when CONFIG_PROC_FS is not enabled:
    ld: net/ipv4/af_inet.o: in function `inet_init':
    af_inet.c:(.init.text+0x42d): undefined reference to `raw_init'

Fix by moving the endif up to the end of the proc entries

Fixes: 6897445fb194c ("net: provide a sysctl raw_l3mdev_accept for raw socket lookup with VRFs")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Mike Manning <mmanning@vyatta.att-mail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/raw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index fb1f02015a15..076f51646d26 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -1132,6 +1132,7 @@ void __init raw_proc_exit(void)
 {
 	unregister_pernet_subsys(&raw_net_ops);
 }
+#endif /* CONFIG_PROC_FS */
 
 static void raw_sysctl_init_net(struct net *net)
 {
@@ -1156,4 +1157,3 @@ void __init raw_init(void)
 	if (register_pernet_subsys(&raw_sysctl_ops))
 		panic("RAW: failed to init sysctl parameters.\n");
 }
-#endif /* CONFIG_PROC_FS */
-- 
cgit v1.2.3


From 88584c30e31967db2ad03c7015a9aea3460deb2c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 27 Nov 2018 13:28:54 +0100
Subject: xfrm: policy: fix policy hash rebuild

Dan Carpenter reports following static checker warning:
 net/xfrm/xfrm_policy.c:1316 xfrm_hash_rebuild()
 warn: 'dir' is out of bounds '3' vs '2'

 |  1280          /* reset the bydst and inexact table in all directions */
 |  1281          xfrm_hash_reset_inexact_table(net);
 |  1282
 |  1283          for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 |                              ^^^^^^^^^^^^^^^^^^^^^
 |dir == XFRM_POLICY_MAX at the end of this loop.
 |  1304          /* re-insert all policies by order of creation */
 |  1305          list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
 [..]
 |  1314                                            xfrm_policy_id2dir(policy->index));
 |  1315                  if (!chain) {
 |  1316                          void *p = xfrm_policy_inexact_insert(policy, dir, 0);

Fix this by updating 'dir' based on current policy.  Otherwise, the
inexact policies won't be found anymore during lookup, as they get
hashed to a bogus bin.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: cc1bb845adc9 ("xfrm: policy: return NULL when inexact search needed")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index ddc3335dd552..be04091eb7db 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1303,15 +1303,16 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 
 	/* re-insert all policies by order of creation */
 	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
-		if (policy->walk.dead ||
-		    xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) {
+		if (policy->walk.dead)
+			continue;
+		dir = xfrm_policy_id2dir(policy->index);
+		if (dir >= XFRM_POLICY_MAX) {
 			/* skip socket policies */
 			continue;
 		}
 		newpos = NULL;
 		chain = policy_hash_bysel(net, &policy->selector,
-					  policy->family,
-					  xfrm_policy_id2dir(policy->index));
+					  policy->family, dir);
 		if (!chain) {
 			void *p = xfrm_policy_inexact_insert(policy, dir, 0);
 
-- 
cgit v1.2.3


From 3b17d4175414baefaaf59948b5e0bc030cc3d943 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 30 Jul 2018 14:40:37 +0100
Subject: can: ucan: fix spelling mistake: "resumbmitting" -> "resubmitting"

Trivial fix to spelling mistake in netdev_dbg error message

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/ucan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
index f3d5bda012a1..04aac3bb54ef 100644
--- a/drivers/net/can/usb/ucan.c
+++ b/drivers/net/can/usb/ucan.c
@@ -715,7 +715,7 @@ static void ucan_read_bulk_callback(struct urb *urb)
 				  up->in_ep_size,
 				  urb->transfer_buffer,
 				  urb->transfer_dma);
-		netdev_dbg(up->netdev, "not resumbmitting urb; status: %d\n",
+		netdev_dbg(up->netdev, "not resubmitting urb; status: %d\n",
 			   urb->status);
 		return;
 	default:
-- 
cgit v1.2.3


From 81de0cd60fd492575b24d97667f38b8b833fb058 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 26 Sep 2018 18:32:29 +0800
Subject: can: xilinx: fix return type of ndo_start_xmit function

The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.

Found by coccinelle.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/xilinx_can.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 045f0845e665..6de5004b453e 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -612,7 +612,7 @@ static int xcan_start_xmit_mailbox(struct sk_buff *skb, struct net_device *ndev)
  *
  * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY when the tx queue is full
  */
-static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
 	int ret;
-- 
cgit v1.2.3


From c5435adc3d2981bbf608a5fa8de1cf2d0d2f2ef9 Mon Sep 17 00:00:00 2001
From: Shubhrajyoti Datta <shubhrajyoti.datta@xilinx.com>
Date: Fri, 12 Oct 2018 09:55:09 +0530
Subject: dt-bindings: can: xilinx_can: add Xilinx CAN FD 2.0 bindings

Add compatible string and new attributes to support the Xilinx CAN
FD 2.0.

Signed-off-by: Shubhrajyoti Datta <shubhrajyoti.datta@xilinx.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/devicetree/bindings/net/can/xilinx_can.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/net/can/xilinx_can.txt b/Documentation/devicetree/bindings/net/can/xilinx_can.txt
index 060e2d46bad9..100cc40b8510 100644
--- a/Documentation/devicetree/bindings/net/can/xilinx_can.txt
+++ b/Documentation/devicetree/bindings/net/can/xilinx_can.txt
@@ -6,6 +6,7 @@ Required properties:
 			  - "xlnx,zynq-can-1.0" for Zynq CAN controllers
 			  - "xlnx,axi-can-1.00.a" for Axi CAN controllers
 			  - "xlnx,canfd-1.0" for CAN FD controllers
+			  - "xlnx,canfd-2.0" for CAN FD 2.0 controllers
 - reg			: Physical base address and size of the controller
 			  registers map.
 - interrupts		: Property with a value describing the interrupt
-- 
cgit v1.2.3


From 0db9071353a0ac1ffb49537bf2be0729e1020645 Mon Sep 17 00:00:00 2001
From: Shubhrajyoti Datta <shubhrajyoti.datta@xilinx.com>
Date: Fri, 12 Oct 2018 09:55:08 +0530
Subject: can: xilinx: add can 2.0 support

Add support for can 2.0.

Signed-off-by: Shubhrajyoti Datta <shubhrajyoti.datta@xilinx.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/xilinx_can.c | 34 +++++++++++++++++++++++++++++++++-
 1 file changed, 33 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 6de5004b453e..97d0933d9bd9 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -63,6 +63,7 @@ enum xcan_reg {
 	XCAN_FSR_OFFSET		= 0x00E8, /* RX FIFO Status */
 	XCAN_TXMSG_BASE_OFFSET	= 0x0100, /* TX Message Space */
 	XCAN_RXMSG_BASE_OFFSET	= 0x1100, /* RX Message Space */
+	XCAN_RXMSG_2_BASE_OFFSET	= 0x2100, /* RX Message Space */
 };
 
 #define XCAN_FRAME_ID_OFFSET(frame_base)	((frame_base) + 0x00)
@@ -75,6 +76,8 @@ enum xcan_reg {
 					 XCAN_CANFD_FRAME_SIZE * (n))
 #define XCAN_RXMSG_FRAME_OFFSET(n)	(XCAN_RXMSG_BASE_OFFSET + \
 					 XCAN_CANFD_FRAME_SIZE * (n))
+#define XCAN_RXMSG_2_FRAME_OFFSET(n)	(XCAN_RXMSG_2_BASE_OFFSET + \
+					 XCAN_CANFD_FRAME_SIZE * (n))
 
 /* the single TX mailbox used by this driver on CAN FD HW */
 #define XCAN_TX_MAILBOX_IDX		0
@@ -152,6 +155,7 @@ enum xcan_reg {
  * instead of the regular FIFO at 0x50
  */
 #define XCAN_FLAG_RX_FIFO_MULTI	0x0010
+#define XCAN_FLAG_CANFD_2	0x0020
 
 struct xcan_devtype_data {
 	unsigned int flags;
@@ -221,6 +225,18 @@ static const struct can_bittiming_const xcan_bittiming_const_canfd = {
 	.brp_inc = 1,
 };
 
+static const struct can_bittiming_const xcan_bittiming_const_canfd2 = {
+	.name = DRIVER_NAME,
+	.tseg1_min = 1,
+	.tseg1_max = 256,
+	.tseg2_min = 1,
+	.tseg2_max = 128,
+	.sjw_max = 128,
+	.brp_min = 1,
+	.brp_max = 256,
+	.brp_inc = 1,
+};
+
 /**
  * xcan_write_reg_le - Write a value to the device register little endian
  * @priv:	Driver private data structure
@@ -973,7 +989,10 @@ static int xcan_rx_fifo_get_next_frame(struct xcan_priv *priv)
 		if (!(fsr & XCAN_FSR_FL_MASK))
 			return -ENOENT;
 
-		offset = XCAN_RXMSG_FRAME_OFFSET(fsr & XCAN_FSR_RI_MASK);
+		if (priv->devtype.flags & XCAN_FLAG_CANFD_2)
+			offset = XCAN_RXMSG_2_FRAME_OFFSET(fsr & XCAN_FSR_RI_MASK);
+		else
+			offset = XCAN_RXMSG_FRAME_OFFSET(fsr & XCAN_FSR_RI_MASK);
 
 	} else {
 		/* check if RX FIFO is empty */
@@ -1430,11 +1449,24 @@ static const struct xcan_devtype_data xcan_canfd_data = {
 	.bus_clk_name = "s_axi_aclk",
 };
 
+static const struct xcan_devtype_data xcan_canfd2_data = {
+	.flags = XCAN_FLAG_EXT_FILTERS |
+		 XCAN_FLAG_RXMNF |
+		 XCAN_FLAG_TX_MAILBOXES |
+		 XCAN_FLAG_CANFD_2 |
+		 XCAN_FLAG_RX_FIFO_MULTI,
+	.bittiming_const = &xcan_bittiming_const_canfd2,
+	.btr_ts2_shift = XCAN_BTR_TS2_SHIFT_CANFD,
+	.btr_sjw_shift = XCAN_BTR_SJW_SHIFT_CANFD,
+	.bus_clk_name = "s_axi_aclk",
+};
+
 /* Match table for OF platform binding */
 static const struct of_device_id xcan_of_match[] = {
 	{ .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data },
 	{ .compatible = "xlnx,axi-can-1.00.a", .data = &xcan_axi_data },
 	{ .compatible = "xlnx,canfd-1.0", .data = &xcan_canfd_data },
+	{ .compatible = "xlnx,canfd-2.0", .data = &xcan_canfd2_data },
 	{ /* end of list */ },
 };
 MODULE_DEVICE_TABLE(of, xcan_of_match);
-- 
cgit v1.2.3


From 06a3f31ae22b4dda56b8512694e029e98779c475 Mon Sep 17 00:00:00 2001
From: Flavio Suligoi <f.suligoi@asem.it>
Date: Tue, 7 Aug 2018 09:17:19 +0200
Subject: can: sja1000: plx_pci: add support for ASEM CAN raw device

This patch adds support for ASEM opto-isolated dual channels
CAN raw device (http://www.asem.it)

Signed-off-by: Flavio Suligoi <f.suligoi@asem.it>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/sja1000/Kconfig   |  1 +
 drivers/net/can/sja1000/plx_pci.c | 65 ++++++++++++++++++++++++++++++++++++++-
 2 files changed, 65 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/sja1000/Kconfig b/drivers/net/can/sja1000/Kconfig
index 1e65cb6c2591..f6dc89927ece 100644
--- a/drivers/net/can/sja1000/Kconfig
+++ b/drivers/net/can/sja1000/Kconfig
@@ -88,6 +88,7 @@ config CAN_PLX_PCI
 	   - TEWS TECHNOLOGIES TPMC810 card (http://www.tews.com/)
 	   - IXXAT Automation PC-I 04/PCI card (http://www.ixxat.com/)
 	   - Connect Tech Inc. CANpro/104-Plus Opto (CRG001) card (http://www.connecttech.com)
+	   - ASEM CAN raw - 2 isolated CAN channels (www.asem.it)
 
 config CAN_TSCAN1
 	tristate "TS-CAN1 PC104 boards"
diff --git a/drivers/net/can/sja1000/plx_pci.c b/drivers/net/can/sja1000/plx_pci.c
index f8ff25c8ee2e..9bcdefea138a 100644
--- a/drivers/net/can/sja1000/plx_pci.c
+++ b/drivers/net/can/sja1000/plx_pci.c
@@ -46,7 +46,8 @@ MODULE_SUPPORTED_DEVICE("Adlink PCI-7841/cPCI-7841, "
 			"esd CAN-PCIe/2000, "
 			"Connect Tech Inc. CANpro/104-Plus Opto (CRG001), "
 			"IXXAT PC-I 04/PCI, "
-			"ELCUS CAN-200-PCI")
+			"ELCUS CAN-200-PCI, "
+			"ASEM DUAL CAN-RAW")
 MODULE_LICENSE("GPL v2");
 
 #define PLX_PCI_MAX_CHAN 2
@@ -70,7 +71,9 @@ struct plx_pci_card {
 					 */
 
 #define PLX_LINT1_EN	0x1		/* Local interrupt 1 enable */
+#define PLX_LINT1_POL	(1 << 1)	/* Local interrupt 1 polarity */
 #define PLX_LINT2_EN	(1 << 3)	/* Local interrupt 2 enable */
+#define PLX_LINT2_POL	(1 << 4)	/* Local interrupt 2 polarity */
 #define PLX_PCI_INT_EN	(1 << 6)	/* PCI Interrupt Enable */
 #define PLX_PCI_RESET	(1 << 30)	/* PCI Adapter Software Reset */
 
@@ -92,6 +95,9 @@ struct plx_pci_card {
  */
 #define PLX_PCI_OCR	(OCR_TX0_PUSHPULL | OCR_TX1_PUSHPULL)
 
+/* OCR setting for ASEM Dual CAN raw */
+#define ASEM_PCI_OCR	0xfe
+
 /*
  * In the CDR register, you should set CBP to 1.
  * You will probably also want to set the clock divider value to 7
@@ -145,10 +151,20 @@ struct plx_pci_card {
 #define MOXA_PCI_VENDOR_ID		0x1393
 #define MOXA_PCI_DEVICE_ID		0x0100
 
+#define ASEM_RAW_CAN_VENDOR_ID		0x10b5
+#define ASEM_RAW_CAN_DEVICE_ID		0x9030
+#define ASEM_RAW_CAN_SUB_VENDOR_ID	0x3000
+#define ASEM_RAW_CAN_SUB_DEVICE_ID	0x1001
+#define ASEM_RAW_CAN_SUB_DEVICE_ID_BIS	0x1002
+#define ASEM_RAW_CAN_RST_REGISTER	0x54
+#define ASEM_RAW_CAN_RST_MASK_CAN1	0x20
+#define ASEM_RAW_CAN_RST_MASK_CAN2	0x04
+
 static void plx_pci_reset_common(struct pci_dev *pdev);
 static void plx9056_pci_reset_common(struct pci_dev *pdev);
 static void plx_pci_reset_marathon_pci(struct pci_dev *pdev);
 static void plx_pci_reset_marathon_pcie(struct pci_dev *pdev);
+static void plx_pci_reset_asem_dual_can_raw(struct pci_dev *pdev);
 
 struct plx_pci_channel_map {
 	u32 bar;
@@ -269,6 +285,14 @@ static struct plx_pci_card_info plx_pci_card_info_moxa = {
 	 /* based on PLX9052 */
 };
 
+static struct plx_pci_card_info plx_pci_card_info_asem_dual_can = {
+	"ASEM Dual CAN raw PCI", 2,
+	PLX_PCI_CAN_CLOCK, ASEM_PCI_OCR, PLX_PCI_CDR,
+	{0, 0x00, 0x00}, { {2, 0x00, 0x00}, {4, 0x00, 0x00} },
+	&plx_pci_reset_asem_dual_can_raw
+	/* based on PLX9030 */
+};
+
 static const struct pci_device_id plx_pci_tbl[] = {
 	{
 		/* Adlink PCI-7841/cPCI-7841 */
@@ -375,6 +399,20 @@ static const struct pci_device_id plx_pci_tbl[] = {
 		0, 0,
 		(kernel_ulong_t)&plx_pci_card_info_moxa
 	},
+	{
+		/* ASEM Dual CAN raw */
+		ASEM_RAW_CAN_VENDOR_ID, ASEM_RAW_CAN_DEVICE_ID,
+		ASEM_RAW_CAN_SUB_VENDOR_ID, ASEM_RAW_CAN_SUB_DEVICE_ID,
+		0, 0,
+		(kernel_ulong_t)&plx_pci_card_info_asem_dual_can
+	},
+	{
+		/* ASEM Dual CAN raw -new model */
+		ASEM_RAW_CAN_VENDOR_ID, ASEM_RAW_CAN_DEVICE_ID,
+		ASEM_RAW_CAN_SUB_VENDOR_ID, ASEM_RAW_CAN_SUB_DEVICE_ID_BIS,
+		0, 0,
+		(kernel_ulong_t)&plx_pci_card_info_asem_dual_can
+	},
 	{ 0,}
 };
 MODULE_DEVICE_TABLE(pci, plx_pci_tbl);
@@ -524,6 +562,31 @@ static void plx_pci_reset_marathon_pcie(struct pci_dev *pdev)
 	}
 }
 
+/* Special reset function for ASEM Dual CAN raw card */
+static void plx_pci_reset_asem_dual_can_raw(struct pci_dev *pdev)
+{
+	void __iomem *bar0_addr;
+	u8 tmpval;
+
+	plx_pci_reset_common(pdev);
+
+	bar0_addr = pci_iomap(pdev, 0, 0);
+	if (!bar0_addr) {
+		dev_err(&pdev->dev, "Failed to remap reset space 0 (BAR0)\n");
+		return;
+	}
+
+	/* reset the two SJA1000 chips */
+	tmpval = ioread8(bar0_addr + ASEM_RAW_CAN_RST_REGISTER);
+	tmpval &= ~(ASEM_RAW_CAN_RST_MASK_CAN1 | ASEM_RAW_CAN_RST_MASK_CAN2);
+	iowrite8(tmpval, bar0_addr + ASEM_RAW_CAN_RST_REGISTER);
+	usleep_range(300, 400);
+	tmpval |= ASEM_RAW_CAN_RST_MASK_CAN1 | ASEM_RAW_CAN_RST_MASK_CAN2;
+	iowrite8(tmpval, bar0_addr + ASEM_RAW_CAN_RST_REGISTER);
+	usleep_range(300, 400);
+	pci_iounmap(pdev, bar0_addr);
+}
+
 static void plx_pci_del_card(struct pci_dev *pdev)
 {
 	struct plx_pci_card *card = pci_get_drvdata(pdev);
-- 
cgit v1.2.3


From 7af42e50f67a4e6f42ca377d7150f5bee93135e3 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 23 Aug 2018 15:34:55 +0200
Subject: can: rcar: use SPDX identifier for Renesas drivers

Adopt the SPDX license identifier headers to ease license compliance
management.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rcar/rcar_can.c   | 6 +-----
 drivers/net/can/rcar/rcar_canfd.c | 6 +-----
 2 files changed, 2 insertions(+), 10 deletions(-)

diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index 771a46083739..13e66297b65f 100644
--- a/drivers/net/can/rcar/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0+
 /* Renesas R-Car CAN device driver
  *
  * Copyright (C) 2013 Cogent Embedded, Inc. <source@cogentembedded.com>
  * Copyright (C) 2013 Renesas Solutions Corp.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index 602c19e23f05..05410008aa6b 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
 /* Renesas R-Car CAN FD device driver
  *
  * Copyright (C) 2015 Renesas Electronics Corp.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /* The R-Car CAN FD controller can operate in either one of the below two modes
-- 
cgit v1.2.3


From e3dfddbf0d63d4503bd502d45d6e41961151b786 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Wed, 26 Sep 2018 01:41:53 +0000
Subject: can: rcar: add SPDX identifiers to Kconfig and Makefile

This patch adds SPDX-License-Identifier to Kconfig and Makefile.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Ramesh Shanmugasundaram <ramesh.shanmugasundaram@bp.renesas.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rcar/Kconfig  | 1 +
 drivers/net/can/rcar/Makefile | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/can/rcar/Kconfig b/drivers/net/can/rcar/Kconfig
index 7b03a3a37db7..bd5a8fcd83e1 100644
--- a/drivers/net/can/rcar/Kconfig
+++ b/drivers/net/can/rcar/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 config CAN_RCAR
 	tristate "Renesas R-Car CAN controller"
 	depends on ARCH_RENESAS || ARM
diff --git a/drivers/net/can/rcar/Makefile b/drivers/net/can/rcar/Makefile
index 08de36a4cfcc..c9185b0c04a8 100644
--- a/drivers/net/can/rcar/Makefile
+++ b/drivers/net/can/rcar/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 #  Makefile for the Renesas R-Car CAN & CAN FD controller drivers
 #
-- 
cgit v1.2.3


From 0f8af56f74cda146c279c6b8e7e590f778a96cc1 Mon Sep 17 00:00:00 2001
From: Pankaj Bansal <pankaj.bansal@nxp.com>
Date: Wed, 1 Aug 2018 19:36:45 +0530
Subject: can: flexcan: enable flexcan for all architectures

flexcan is an IP module independent of the SOC architecture.
Therefore, enable it for all architectures.

Signed-off-by: Pankaj Bansal <pankaj.bansal@nxp.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 7cdd0cead693..e0f0ad7a550a 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -96,7 +96,7 @@ config CAN_AT91
 
 config CAN_FLEXCAN
 	tristate "Support for Freescale FLEXCAN based chips"
-	depends on ARM || PPC
+	depends on OF && HAS_IOMEM
 	---help---
 	  Say Y here if you want to support for Freescale FlexCAN.
 
-- 
cgit v1.2.3


From 9dc1ee1184b4177f98001885387c0e268db06c2a Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Mon, 12 Nov 2018 15:33:57 +0100
Subject: can: flexcan: flexcan_start_xmit(): fix indention

This patch fixes the indentio nin flexcan_start_xmit() by alligning the
code to the opening parenthesis.

Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 75ce11395ee8..f4614a787ca6 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -551,9 +551,9 @@ static netdev_tx_t flexcan_start_xmit(struct sk_buff *skb, struct net_device *de
 	 * Write twice INACTIVE(0x8) code to first MB.
 	 */
 	priv->write(FLEXCAN_MB_CODE_TX_INACTIVE,
-		      &priv->tx_mb_reserved->can_ctrl);
+		    &priv->tx_mb_reserved->can_ctrl);
 	priv->write(FLEXCAN_MB_CODE_TX_INACTIVE,
-		      &priv->tx_mb_reserved->can_ctrl);
+		    &priv->tx_mb_reserved->can_ctrl);
 
 	return NETDEV_TX_OK;
 }
-- 
cgit v1.2.3


From bc8ad651516df40bd013ba787ad19f60dac61523 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 28 Nov 2018 15:45:27 +0100
Subject: can: flexcan: flexcan_irq(): fix indention

The patch fixes the indention by replacing space by tabs, as noted by
checkpatch:

| ERROR: code indent should use tabs where possible
| #980: FILE: drivers/net/can/flexcan.c:980:

Fixes: da49a8075c00 ("can: flexcan: implement error passive state quirk")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index f4614a787ca6..9dc14bc37b40 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -821,7 +821,7 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id)
 	/* state change interrupt or broken error state quirk fix is enabled */
 	if ((reg_esr & FLEXCAN_ESR_ERR_STATE) ||
 	    (priv->devtype_data->quirks & (FLEXCAN_QUIRK_BROKEN_WERR_STATE |
-	                                   FLEXCAN_QUIRK_BROKEN_PERR_STATE)))
+					   FLEXCAN_QUIRK_BROKEN_PERR_STATE)))
 		flexcan_irq_state(dev, reg_esr);
 
 	/* bus error IRQ - handle if bus error reporting is activated */
-- 
cgit v1.2.3


From 22233f7bf2c99ef52ec19d30876a12d2f725972e Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 28 Nov 2018 15:31:37 +0100
Subject: can: flexcan: FLEXCAN_IFLAG_MB: add () around macro argument

This patch fixes the following checkpatch warning:

| Macro argument 'x' may be better as '(x)' to avoid precedence issues

Fixes: cbffaf7aa09e ("can: flexcan: Always use last mailbox for TX")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 9dc14bc37b40..7085eb329cf8 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -140,7 +140,7 @@
 #define FLEXCAN_TX_MB				63
 #define FLEXCAN_RX_MB_OFF_TIMESTAMP_FIRST	(FLEXCAN_TX_MB_RESERVED_OFF_TIMESTAMP + 1)
 #define FLEXCAN_RX_MB_OFF_TIMESTAMP_LAST	(FLEXCAN_TX_MB - 1)
-#define FLEXCAN_IFLAG_MB(x)		BIT(x & 0x1f)
+#define FLEXCAN_IFLAG_MB(x)		BIT((x) & 0x1f)
 #define FLEXCAN_IFLAG_RX_FIFO_OVERFLOW	BIT(7)
 #define FLEXCAN_IFLAG_RX_FIFO_WARN	BIT(6)
 #define FLEXCAN_IFLAG_RX_FIFO_AVAILABLE	BIT(5)
-- 
cgit v1.2.3


From c982a3ca49e330aeb5d8b8446e7bc60c9191080d Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Fri, 17 Aug 2018 14:52:58 +0200
Subject: can: flexcan: flexcan_chip_start(): adjust comment to match the code

With the conversion of the flexcan driver to support both timestamp and
FIFO mode the setup of the MCR register ("enable fifo") has been moved.

This patch moves the comment too, in order to match the code again.

Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 7085eb329cf8..e57a152266d7 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -935,7 +935,6 @@ static int flexcan_chip_start(struct net_device *dev)
 	/* MCR
 	 *
 	 * enable freeze
-	 * enable fifo
 	 * halt now
 	 * only supervisor access
 	 * enable warning int
@@ -950,6 +949,12 @@ static int flexcan_chip_start(struct net_device *dev)
 		FLEXCAN_MCR_WRN_EN | FLEXCAN_MCR_SRX_DIS | FLEXCAN_MCR_IRMQ |
 		FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_MAXMB(FLEXCAN_TX_MB);
 
+	/* MCR
+	 *
+	 * FIFO:
+	 * - disable for timestamp mode
+	 * - enable for FIFO mode
+	 */
 	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP)
 		reg_mcr &= ~FLEXCAN_MCR_FEN;
 	else
-- 
cgit v1.2.3


From b9c9c39e3d20666c80f64e931ccf4c5684c525ba Mon Sep 17 00:00:00 2001
From: Aisheng Dong <aisheng.dong@nxp.com>
Date: Fri, 23 Nov 2018 08:35:29 +0000
Subject: dt-bindings: can: flexcan: add stop mode property to device tree

The FlexCAN controller can parse the stop mode property to enable CAN
self wakeup feature.

Signed-off-by: Aisheng Dong <aisheng.dong@nxp.com>
Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/devicetree/bindings/net/can/fsl-flexcan.txt | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
index bfc0c433654f..bc77477c6878 100644
--- a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
+++ b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
@@ -24,6 +24,14 @@ Optional properties:
               if this property is present then controller is assumed to be big
               endian.
 
+- fsl,stop-mode: register bits of stop mode control, the format is
+		 <&gpr req_gpr req_bit ack_gpr ack_bit>.
+		 gpr is the phandle to general purpose register node.
+		 req_gpr is the gpr register offset of CAN stop request.
+		 req_bit is the bit offset of CAN stop request.
+		 ack_gpr is the gpr register offset of CAN stop acknowledge.
+		 ack_bit is the bit offset of CAN stop acknowledge.
+
 Example:
 
 	can@1c000 {
-- 
cgit v1.2.3


From de3578c198c6d846448c8c989bd0ee7a05f3b601 Mon Sep 17 00:00:00 2001
From: Aisheng Dong <aisheng.dong@nxp.com>
Date: Fri, 23 Nov 2018 08:35:33 +0000
Subject: can: flexcan: add self wakeup support

If wakeup is enabled, enter stop mode, else enter disabled mode. Self wake
can only work on stop mode.

Starting from IMX6, the flexcan stop mode control bits is SoC specific,
move it out of IP driver and parse it from devicetree.

Signed-off-by: Aisheng Dong <aisheng.dong@nxp.com>
Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Reviewed-by: Dong Aisheng <aisheng.dong@nxp.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 173 +++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 164 insertions(+), 9 deletions(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index e57a152266d7..cfdeb5bc77b7 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -19,11 +19,13 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
+#include <linux/regmap.h>
 
 #define DRV_NAME			"flexcan"
 
@@ -131,7 +133,8 @@
 	(FLEXCAN_ESR_ERR_BUS | FLEXCAN_ESR_ERR_STATE)
 #define FLEXCAN_ESR_ALL_INT \
 	(FLEXCAN_ESR_TWRN_INT | FLEXCAN_ESR_RWRN_INT | \
-	 FLEXCAN_ESR_BOFF_INT | FLEXCAN_ESR_ERR_INT)
+	 FLEXCAN_ESR_BOFF_INT | FLEXCAN_ESR_ERR_INT | \
+	 FLEXCAN_ESR_WAK_INT)
 
 /* FLEXCAN interrupt flag register (IFLAG) bits */
 /* Errata ERR005829 step7: Reserve first valid MB */
@@ -189,6 +192,7 @@
 #define FLEXCAN_QUIRK_USE_OFF_TIMESTAMP	BIT(5) /* Use timestamp based offloading */
 #define FLEXCAN_QUIRK_BROKEN_PERR_STATE	BIT(6) /* No interrupt for error passive */
 #define FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN	BIT(7) /* default to BE register access */
+#define FLEXCAN_QUIRK_SETUP_STOP_MODE		BIT(8) /* Setup stop mode to support wakeup */
 
 /* Structure of the message buffer */
 struct flexcan_mb {
@@ -253,6 +257,14 @@ struct flexcan_devtype_data {
 	u32 quirks;		/* quirks needed for different IP cores */
 };
 
+struct flexcan_stop_mode {
+	struct regmap *gpr;
+	u8 req_gpr;
+	u8 req_bit;
+	u8 ack_gpr;
+	u8 ack_bit;
+};
+
 struct flexcan_priv {
 	struct can_priv can;
 	struct can_rx_offload offload;
@@ -267,6 +279,7 @@ struct flexcan_priv {
 	struct clk *clk_per;
 	const struct flexcan_devtype_data *devtype_data;
 	struct regulator *reg_xceiver;
+	struct flexcan_stop_mode stm;
 
 	/* Read and Write APIs */
 	u32 (*read)(void __iomem *addr);
@@ -290,7 +303,8 @@ static const struct flexcan_devtype_data fsl_imx28_devtype_data = {
 
 static const struct flexcan_devtype_data fsl_imx6q_devtype_data = {
 	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
-		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_BROKEN_PERR_STATE,
+		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
+		FLEXCAN_QUIRK_SETUP_STOP_MODE,
 };
 
 static const struct flexcan_devtype_data fsl_vf610_devtype_data = {
@@ -350,6 +364,49 @@ static inline void flexcan_write_le(u32 val, void __iomem *addr)
 	iowrite32(val, addr);
 }
 
+static void flexcan_enable_wakeup_irq(struct flexcan_priv *priv, bool enable)
+{
+	struct flexcan_regs __iomem *regs = priv->regs;
+	u32 reg_mcr;
+
+	reg_mcr = priv->read(&regs->mcr);
+
+	if (enable)
+		reg_mcr |= FLEXCAN_MCR_WAK_MSK;
+	else
+		reg_mcr &= ~FLEXCAN_MCR_WAK_MSK;
+
+	priv->write(reg_mcr, &regs->mcr);
+}
+
+static inline void flexcan_enter_stop_mode(struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->regs;
+	u32 reg_mcr;
+
+	reg_mcr = priv->read(&regs->mcr);
+	reg_mcr |= FLEXCAN_MCR_SLF_WAK;
+	priv->write(reg_mcr, &regs->mcr);
+
+	/* enable stop request */
+	regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr,
+			   1 << priv->stm.req_bit, 1 << priv->stm.req_bit);
+}
+
+static inline void flexcan_exit_stop_mode(struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->regs;
+	u32 reg_mcr;
+
+	/* remove stop request */
+	regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr,
+			   1 << priv->stm.req_bit, 0);
+
+	reg_mcr = priv->read(&regs->mcr);
+	reg_mcr &= ~FLEXCAN_MCR_SLF_WAK;
+	priv->write(reg_mcr, &regs->mcr);
+}
+
 static inline void flexcan_error_irq_enable(const struct flexcan_priv *priv)
 {
 	struct flexcan_regs __iomem *regs = priv->regs;
@@ -1265,6 +1322,59 @@ static void unregister_flexcandev(struct net_device *dev)
 	unregister_candev(dev);
 }
 
+static int flexcan_setup_stop_mode(struct platform_device *pdev)
+{
+	struct net_device *dev = platform_get_drvdata(pdev);
+	struct device_node *np = pdev->dev.of_node;
+	struct device_node *gpr_np;
+	struct flexcan_priv *priv;
+	phandle phandle;
+	u32 out_val[5];
+	int ret;
+
+	if (!np)
+		return -EINVAL;
+
+	/* stop mode property format is:
+	 * <&gpr req_gpr req_bit ack_gpr ack_bit>.
+	 */
+	ret = of_property_read_u32_array(np, "fsl,stop-mode", out_val,
+					 ARRAY_SIZE(out_val));
+	if (ret) {
+		dev_dbg(&pdev->dev, "no stop-mode property\n");
+		return ret;
+	}
+	phandle = *out_val;
+
+	gpr_np = of_find_node_by_phandle(phandle);
+	if (!gpr_np) {
+		dev_dbg(&pdev->dev, "could not find gpr node by phandle\n");
+		return PTR_ERR(gpr_np);
+	}
+
+	priv = netdev_priv(dev);
+	priv->stm.gpr = syscon_node_to_regmap(gpr_np);
+	of_node_put(gpr_np);
+	if (IS_ERR(priv->stm.gpr)) {
+		dev_dbg(&pdev->dev, "could not find gpr regmap\n");
+		return PTR_ERR(priv->stm.gpr);
+	}
+
+	priv->stm.req_gpr = out_val[1];
+	priv->stm.req_bit = out_val[2];
+	priv->stm.ack_gpr = out_val[3];
+	priv->stm.ack_bit = out_val[4];
+
+	dev_dbg(&pdev->dev,
+		"gpr %s req_gpr=0x02%x req_bit=%u ack_gpr=0x02%x ack_bit=%u\n",
+		gpr_np->full_name, priv->stm.req_gpr, priv->stm.req_bit,
+		priv->stm.ack_gpr, priv->stm.ack_bit);
+
+	device_set_wakeup_capable(&pdev->dev, true);
+
+	return 0;
+}
+
 static const struct of_device_id flexcan_of_match[] = {
 	{ .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, },
 	{ .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, },
@@ -1413,6 +1523,12 @@ static int flexcan_probe(struct platform_device *pdev)
 
 	devm_can_led_init(dev);
 
+	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE) {
+		err = flexcan_setup_stop_mode(pdev);
+		if (err)
+			dev_dbg(&pdev->dev, "failed to setup stop-mode\n");
+	}
+
 	dev_info(&pdev->dev, "device registered (reg_base=%p, irq=%d)\n",
 		 priv->regs, dev->irq);
 
@@ -1443,9 +1559,17 @@ static int __maybe_unused flexcan_suspend(struct device *device)
 	int err;
 
 	if (netif_running(dev)) {
-		err = flexcan_chip_disable(priv);
-		if (err)
-			return err;
+		/* if wakeup is enabled, enter stop mode
+		 * else enter disabled mode.
+		 */
+		if (device_may_wakeup(device)) {
+			enable_irq_wake(dev->irq);
+			flexcan_enter_stop_mode(priv);
+		} else {
+			err = flexcan_chip_disable(priv);
+			if (err)
+				return err;
+		}
 		netif_stop_queue(dev);
 		netif_device_detach(dev);
 	}
@@ -1464,14 +1588,45 @@ static int __maybe_unused flexcan_resume(struct device *device)
 	if (netif_running(dev)) {
 		netif_device_attach(dev);
 		netif_start_queue(dev);
-		err = flexcan_chip_enable(priv);
-		if (err)
-			return err;
+		if (device_may_wakeup(device)) {
+			disable_irq_wake(dev->irq);
+		} else {
+			err = flexcan_chip_enable(priv);
+			if (err)
+				return err;
+		}
 	}
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(flexcan_pm_ops, flexcan_suspend, flexcan_resume);
+static int __maybe_unused flexcan_noirq_suspend(struct device *device)
+{
+	struct net_device *dev = dev_get_drvdata(device);
+	struct flexcan_priv *priv = netdev_priv(dev);
+
+	if (netif_running(dev) && device_may_wakeup(device))
+		flexcan_enable_wakeup_irq(priv, true);
+
+	return 0;
+}
+
+static int __maybe_unused flexcan_noirq_resume(struct device *device)
+{
+	struct net_device *dev = dev_get_drvdata(device);
+	struct flexcan_priv *priv = netdev_priv(dev);
+
+	if (netif_running(dev) && device_may_wakeup(device)) {
+		flexcan_enable_wakeup_irq(priv, false);
+		flexcan_exit_stop_mode(priv);
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops flexcan_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(flexcan_suspend, flexcan_resume)
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(flexcan_noirq_suspend, flexcan_noirq_resume)
+};
 
 static struct platform_driver flexcan_driver = {
 	.driver = {
-- 
cgit v1.2.3


From 7ad0f53a394ba829e45682c2e21175791e36b649 Mon Sep 17 00:00:00 2001
From: Pankaj Bansal <pankaj.bansal@nxp.com>
Date: Mon, 13 Aug 2018 23:50:48 +0530
Subject: can: flexcan: flexcan_chip_start(): enable loopback mode in flexcan

Self reception disable bit needs to be cleared for loopback mode to work
in flexcan.

Signed-off-by: Pankaj Bansal <pankaj.bansal@nxp.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index cfdeb5bc77b7..f16668b8dd61 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -995,7 +995,6 @@ static int flexcan_chip_start(struct net_device *dev)
 	 * halt now
 	 * only supervisor access
 	 * enable warning int
-	 * disable local echo
 	 * enable individual RX masking
 	 * choose format C
 	 * set max mailbox number
@@ -1003,8 +1002,8 @@ static int flexcan_chip_start(struct net_device *dev)
 	reg_mcr = priv->read(&regs->mcr);
 	reg_mcr &= ~FLEXCAN_MCR_MAXMB(0xff);
 	reg_mcr |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT | FLEXCAN_MCR_SUPV |
-		FLEXCAN_MCR_WRN_EN | FLEXCAN_MCR_SRX_DIS | FLEXCAN_MCR_IRMQ |
-		FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_MAXMB(FLEXCAN_TX_MB);
+		FLEXCAN_MCR_WRN_EN | FLEXCAN_MCR_IRMQ | FLEXCAN_MCR_IDAM_C |
+		FLEXCAN_MCR_MAXMB(FLEXCAN_TX_MB);
 
 	/* MCR
 	 *
@@ -1017,6 +1016,23 @@ static int flexcan_chip_start(struct net_device *dev)
 	else
 		reg_mcr |= FLEXCAN_MCR_FEN;
 
+	/* MCR
+	 *
+	 * NOTE: In loopback mode, the CAN_MCR[SRXDIS] cannot be
+	 *       asserted because this will impede the self reception
+	 *       of a transmitted message. This is not documented in
+	 *       earlier versions of flexcan block guide.
+	 *
+	 * Self Reception:
+	 * - enable Self Reception for loopback mode
+	 *   (by clearing "Self Reception Disable" bit)
+	 * - disable for normal operation
+	 */
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
+		reg_mcr &= ~FLEXCAN_MCR_SRX_DIS;
+	else
+		reg_mcr |= FLEXCAN_MCR_SRX_DIS;
+
 	netdev_dbg(dev, "%s: writing mcr=0x%08x", __func__, reg_mcr);
 	priv->write(reg_mcr, &regs->mcr);
 
-- 
cgit v1.2.3


From 5156c7b11f35bf305b809dd381d7842f7e078a37 Mon Sep 17 00:00:00 2001
From: Pankaj Bansal <pankaj.bansal@nxp.com>
Date: Mon, 13 Aug 2018 23:50:49 +0530
Subject: can: flexcan: move rx_offload_add() from flexcan_probe() to
 flexcan_open()

rx offload depends on number of message buffers, which in turn depends
on messgae buffer size. with the upcoming LX2160A SOC the message buffer
size can be configured to 72 bytes if it were to be used in CAN FD mode.

The current mode in which the flexcan is being operated is known at the
time of flexcan_open() but not at the time of flexcan_probe().

Therefore, move the rx_offload_add() from flexcan_probe() to
flexcan_open(). correspondingly, move rx_offload_delete() from
flexcan_remove() to flexcan_close().

Signed-off-by: Pankaj Bansal <pankaj.bansal@nxp.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 69 ++++++++++++++++++++++++-----------------------
 1 file changed, 36 insertions(+), 33 deletions(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index f16668b8dd61..b5b9045b86ba 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -1188,6 +1188,7 @@ static void flexcan_chip_stop(struct net_device *dev)
 static int flexcan_open(struct net_device *dev)
 {
 	struct flexcan_priv *priv = netdev_priv(dev);
+	struct flexcan_regs __iomem *regs = priv->regs;
 	int err;
 
 	err = clk_prepare_enable(priv->clk_ipg);
@@ -1206,10 +1207,41 @@ static int flexcan_open(struct net_device *dev)
 	if (err)
 		goto out_close;
 
+	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP)
+		priv->tx_mb_reserved = &regs->mb[FLEXCAN_TX_MB_RESERVED_OFF_TIMESTAMP];
+	else
+		priv->tx_mb_reserved = &regs->mb[FLEXCAN_TX_MB_RESERVED_OFF_FIFO];
+
+	priv->reg_imask1_default = 0;
+	priv->reg_imask2_default = FLEXCAN_IFLAG_MB(FLEXCAN_TX_MB);
+
+	priv->offload.mailbox_read = flexcan_mailbox_read;
+
+	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) {
+		u64 imask;
+
+		priv->offload.mb_first = FLEXCAN_RX_MB_OFF_TIMESTAMP_FIRST;
+		priv->offload.mb_last = FLEXCAN_RX_MB_OFF_TIMESTAMP_LAST;
+
+		imask = GENMASK_ULL(priv->offload.mb_last,
+				    priv->offload.mb_first);
+		priv->reg_imask1_default |= imask;
+		priv->reg_imask2_default |= imask >> 32;
+
+		err = can_rx_offload_add_timestamp(dev, &priv->offload);
+	} else {
+		priv->reg_imask1_default |= FLEXCAN_IFLAG_RX_FIFO_OVERFLOW |
+			FLEXCAN_IFLAG_RX_FIFO_AVAILABLE;
+		err = can_rx_offload_add_fifo(dev, &priv->offload,
+					      FLEXCAN_NAPI_WEIGHT);
+	}
+	if (err)
+		goto out_free_irq;
+
 	/* start chip and queuing */
 	err = flexcan_chip_start(dev);
 	if (err)
-		goto out_free_irq;
+		goto out_offload_del;
 
 	can_led_event(dev, CAN_LED_EVENT_OPEN);
 
@@ -1218,6 +1250,8 @@ static int flexcan_open(struct net_device *dev)
 
 	return 0;
 
+ out_offload_del:
+	can_rx_offload_del(&priv->offload);
  out_free_irq:
 	free_irq(dev->irq, dev);
  out_close:
@@ -1238,6 +1272,7 @@ static int flexcan_close(struct net_device *dev)
 	can_rx_offload_disable(&priv->offload);
 	flexcan_chip_stop(dev);
 
+	can_rx_offload_del(&priv->offload);
 	free_irq(dev->irq, dev);
 	clk_disable_unprepare(priv->clk_per);
 	clk_disable_unprepare(priv->clk_ipg);
@@ -1502,35 +1537,6 @@ static int flexcan_probe(struct platform_device *pdev)
 	priv->devtype_data = devtype_data;
 	priv->reg_xceiver = reg_xceiver;
 
-	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP)
-		priv->tx_mb_reserved = &regs->mb[FLEXCAN_TX_MB_RESERVED_OFF_TIMESTAMP];
-	else
-		priv->tx_mb_reserved = &regs->mb[FLEXCAN_TX_MB_RESERVED_OFF_FIFO];
-
-	priv->reg_imask1_default = 0;
-	priv->reg_imask2_default = FLEXCAN_IFLAG_MB(FLEXCAN_TX_MB);
-
-	priv->offload.mailbox_read = flexcan_mailbox_read;
-
-	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) {
-		u64 imask;
-
-		priv->offload.mb_first = FLEXCAN_RX_MB_OFF_TIMESTAMP_FIRST;
-		priv->offload.mb_last = FLEXCAN_RX_MB_OFF_TIMESTAMP_LAST;
-
-		imask = GENMASK_ULL(priv->offload.mb_last, priv->offload.mb_first);
-		priv->reg_imask1_default |= imask;
-		priv->reg_imask2_default |= imask >> 32;
-
-		err = can_rx_offload_add_timestamp(dev, &priv->offload);
-	} else {
-		priv->reg_imask1_default |= FLEXCAN_IFLAG_RX_FIFO_OVERFLOW |
-			FLEXCAN_IFLAG_RX_FIFO_AVAILABLE;
-		err = can_rx_offload_add_fifo(dev, &priv->offload, FLEXCAN_NAPI_WEIGHT);
-	}
-	if (err)
-		goto failed_offload;
-
 	err = register_flexcandev(dev);
 	if (err) {
 		dev_err(&pdev->dev, "registering netdev failed\n");
@@ -1550,7 +1556,6 @@ static int flexcan_probe(struct platform_device *pdev)
 
 	return 0;
 
- failed_offload:
  failed_register:
 	free_candev(dev);
 	return err;
@@ -1559,10 +1564,8 @@ static int flexcan_probe(struct platform_device *pdev)
 static int flexcan_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
-	struct flexcan_priv *priv = netdev_priv(dev);
 
 	unregister_flexcandev(dev);
-	can_rx_offload_del(&priv->offload);
 	free_candev(dev);
 
 	return 0;
-- 
cgit v1.2.3


From 0517961ccdf190a7f25da9ab17982a6d496e5d1d Mon Sep 17 00:00:00 2001
From: Pankaj Bansal <pankaj.bansal@nxp.com>
Date: Fri, 23 Nov 2018 22:18:44 +0100
Subject: can: flexcan: Add provision for variable payload size

Till now the flexcan module supported 8 byte payload size as per CAN 2.0
specifications. But now upcoming flexcan module in NXP LX2160A SOC
supports CAN FD protocol too. The Message buffers need to be configured
to have payload size 64 bytes.

Therefore, added provision in the driver for payload size to be 64 bytes.

Signed-off-by: Pankaj Bansal <pankaj.bansal@nxp.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 88 +++++++++++++++++++++++++++++------------------
 1 file changed, 55 insertions(+), 33 deletions(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index b5b9045b86ba..ecb50b1bd849 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -140,9 +140,7 @@
 /* Errata ERR005829 step7: Reserve first valid MB */
 #define FLEXCAN_TX_MB_RESERVED_OFF_FIFO		8
 #define FLEXCAN_TX_MB_RESERVED_OFF_TIMESTAMP	0
-#define FLEXCAN_TX_MB				63
 #define FLEXCAN_RX_MB_OFF_TIMESTAMP_FIRST	(FLEXCAN_TX_MB_RESERVED_OFF_TIMESTAMP + 1)
-#define FLEXCAN_RX_MB_OFF_TIMESTAMP_LAST	(FLEXCAN_TX_MB - 1)
 #define FLEXCAN_IFLAG_MB(x)		BIT((x) & 0x1f)
 #define FLEXCAN_IFLAG_RX_FIFO_OVERFLOW	BIT(7)
 #define FLEXCAN_IFLAG_RX_FIFO_WARN	BIT(6)
@@ -198,7 +196,7 @@
 struct flexcan_mb {
 	u32 can_ctrl;
 	u32 can_id;
-	u32 data[2];
+	u32 data[];
 };
 
 /* Structure of the hardware registers */
@@ -227,7 +225,7 @@ struct flexcan_regs {
 	u32 rxfgmask;		/* 0x48 */
 	u32 rxfir;		/* 0x4c */
 	u32 _reserved3[12];	/* 0x50 */
-	struct flexcan_mb mb[64];	/* 0x80 */
+	u8 mb[1024];		/* 0x80 */
 	/* FIFO-mode:
 	 *			MB
 	 * 0x080...0x08f	0	RX message buffer
@@ -270,7 +268,11 @@ struct flexcan_priv {
 	struct can_rx_offload offload;
 
 	struct flexcan_regs __iomem *regs;
+	struct flexcan_mb __iomem *tx_mb;
 	struct flexcan_mb __iomem *tx_mb_reserved;
+	u8 tx_mb_idx;
+	u8 mb_count;
+	u8 mb_size;
 	u32 reg_ctrl_default;
 	u32 reg_imask1_default;
 	u32 reg_imask2_default;
@@ -364,6 +366,16 @@ static inline void flexcan_write_le(u32 val, void __iomem *addr)
 	iowrite32(val, addr);
 }
 
+static struct flexcan_mb __iomem *flexcan_get_mb(const struct flexcan_priv *priv,
+						 u8 mb_index)
+{
+	if (WARN_ON(mb_index >= priv->mb_count))
+		return NULL;
+
+	return (struct flexcan_mb __iomem *)
+		(&priv->regs->mb[priv->mb_size * mb_index]);
+}
+
 static void flexcan_enable_wakeup_irq(struct flexcan_priv *priv, bool enable)
 {
 	struct flexcan_regs __iomem *regs = priv->regs;
@@ -569,11 +581,11 @@ static int flexcan_get_berr_counter(const struct net_device *dev,
 static netdev_tx_t flexcan_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	const struct flexcan_priv *priv = netdev_priv(dev);
-	struct flexcan_regs __iomem *regs = priv->regs;
 	struct can_frame *cf = (struct can_frame *)skb->data;
 	u32 can_id;
 	u32 data;
 	u32 ctrl = FLEXCAN_MB_CODE_TX_DATA | (cf->can_dlc << 16);
+	int i;
 
 	if (can_dropped_invalid_skb(dev, skb))
 		return NETDEV_TX_OK;
@@ -590,19 +602,15 @@ static netdev_tx_t flexcan_start_xmit(struct sk_buff *skb, struct net_device *de
 	if (cf->can_id & CAN_RTR_FLAG)
 		ctrl |= FLEXCAN_MB_CNT_RTR;
 
-	if (cf->can_dlc > 0) {
-		data = be32_to_cpup((__be32 *)&cf->data[0]);
-		priv->write(data, &regs->mb[FLEXCAN_TX_MB].data[0]);
-	}
-	if (cf->can_dlc > 4) {
-		data = be32_to_cpup((__be32 *)&cf->data[4]);
-		priv->write(data, &regs->mb[FLEXCAN_TX_MB].data[1]);
+	for (i = 0; i < cf->can_dlc; i += sizeof(u32)) {
+		data = be32_to_cpup((__be32 *)&cf->data[i]);
+		priv->write(data, &priv->tx_mb->data[i / sizeof(u32)]);
 	}
 
 	can_put_echo_skb(skb, dev, 0);
 
-	priv->write(can_id, &regs->mb[FLEXCAN_TX_MB].can_id);
-	priv->write(ctrl, &regs->mb[FLEXCAN_TX_MB].can_ctrl);
+	priv->write(can_id, &priv->tx_mb->can_id);
+	priv->write(ctrl, &priv->tx_mb->can_ctrl);
 
 	/* Errata ERR005829 step8:
 	 * Write twice INACTIVE(0x8) code to first MB.
@@ -729,8 +737,11 @@ static unsigned int flexcan_mailbox_read(struct can_rx_offload *offload,
 {
 	struct flexcan_priv *priv = rx_offload_to_priv(offload);
 	struct flexcan_regs __iomem *regs = priv->regs;
-	struct flexcan_mb __iomem *mb = &regs->mb[n];
+	struct flexcan_mb __iomem *mb;
 	u32 reg_ctrl, reg_id, reg_iflag1;
+	int i;
+
+	mb = flexcan_get_mb(priv, n);
 
 	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) {
 		u32 code;
@@ -771,8 +782,10 @@ static unsigned int flexcan_mailbox_read(struct can_rx_offload *offload,
 		cf->can_id |= CAN_RTR_FLAG;
 	cf->can_dlc = get_can_dlc((reg_ctrl >> 16) & 0xf);
 
-	*(__be32 *)(cf->data + 0) = cpu_to_be32(priv->read(&mb->data[0]));
-	*(__be32 *)(cf->data + 4) = cpu_to_be32(priv->read(&mb->data[1]));
+	for (i = 0; i < cf->can_dlc; i += sizeof(u32)) {
+		__be32 data = cpu_to_be32(priv->read(&mb->data[i / sizeof(u32)]));
+		*(__be32 *)(cf->data + i) = data;
+	}
 
 	/* mark as read */
 	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) {
@@ -801,7 +814,7 @@ static inline u64 flexcan_read_reg_iflag_rx(struct flexcan_priv *priv)
 	u32 iflag1, iflag2;
 
 	iflag2 = priv->read(&regs->iflag2) & priv->reg_imask2_default &
-		~FLEXCAN_IFLAG_MB(FLEXCAN_TX_MB);
+		~FLEXCAN_IFLAG_MB(priv->tx_mb_idx);
 	iflag1 = priv->read(&regs->iflag1) & priv->reg_imask1_default;
 
 	return (u64)iflag2 << 32 | iflag1;
@@ -851,8 +864,8 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id)
 	reg_iflag2 = priv->read(&regs->iflag2);
 
 	/* transmission complete interrupt */
-	if (reg_iflag2 & FLEXCAN_IFLAG_MB(FLEXCAN_TX_MB)) {
-		u32 reg_ctrl = priv->read(&regs->mb[FLEXCAN_TX_MB].can_ctrl);
+	if (reg_iflag2 & FLEXCAN_IFLAG_MB(priv->tx_mb_idx)) {
+		u32 reg_ctrl = priv->read(&priv->tx_mb->can_ctrl);
 
 		handled = IRQ_HANDLED;
 		stats->tx_bytes += can_rx_offload_get_echo_skb(&priv->offload,
@@ -862,8 +875,8 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id)
 
 		/* after sending a RTR frame MB is in RX mode */
 		priv->write(FLEXCAN_MB_CODE_TX_INACTIVE,
-			    &regs->mb[FLEXCAN_TX_MB].can_ctrl);
-		priv->write(FLEXCAN_IFLAG_MB(FLEXCAN_TX_MB), &regs->iflag2);
+			    &priv->tx_mb->can_ctrl);
+		priv->write(FLEXCAN_IFLAG_MB(priv->tx_mb_idx), &regs->iflag2);
 		netif_wake_queue(dev);
 	}
 
@@ -976,6 +989,7 @@ static int flexcan_chip_start(struct net_device *dev)
 	struct flexcan_regs __iomem *regs = priv->regs;
 	u32 reg_mcr, reg_ctrl, reg_ctrl2, reg_mecr;
 	int err, i;
+	struct flexcan_mb __iomem *mb;
 
 	/* enable module */
 	err = flexcan_chip_enable(priv);
@@ -1003,7 +1017,7 @@ static int flexcan_chip_start(struct net_device *dev)
 	reg_mcr &= ~FLEXCAN_MCR_MAXMB(0xff);
 	reg_mcr |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT | FLEXCAN_MCR_SUPV |
 		FLEXCAN_MCR_WRN_EN | FLEXCAN_MCR_IRMQ | FLEXCAN_MCR_IDAM_C |
-		FLEXCAN_MCR_MAXMB(FLEXCAN_TX_MB);
+		FLEXCAN_MCR_MAXMB(priv->tx_mb_idx);
 
 	/* MCR
 	 *
@@ -1077,14 +1091,16 @@ static int flexcan_chip_start(struct net_device *dev)
 
 	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) {
 		for (i = priv->offload.mb_first; i <= priv->offload.mb_last; i++) {
+			mb = flexcan_get_mb(priv, i);
 			priv->write(FLEXCAN_MB_CODE_RX_EMPTY,
-				    &regs->mb[i].can_ctrl);
+				    &mb->can_ctrl);
 		}
 	} else {
 		/* clear and invalidate unused mailboxes first */
-		for (i = FLEXCAN_TX_MB_RESERVED_OFF_FIFO; i <= ARRAY_SIZE(regs->mb); i++) {
+		for (i = FLEXCAN_TX_MB_RESERVED_OFF_FIFO; i <= priv->mb_count; i++) {
+			mb = flexcan_get_mb(priv, i);
 			priv->write(FLEXCAN_MB_CODE_RX_INACTIVE,
-				    &regs->mb[i].can_ctrl);
+				    &mb->can_ctrl);
 		}
 	}
 
@@ -1094,7 +1110,7 @@ static int flexcan_chip_start(struct net_device *dev)
 
 	/* mark TX mailbox as INACTIVE */
 	priv->write(FLEXCAN_MB_CODE_TX_INACTIVE,
-		    &regs->mb[FLEXCAN_TX_MB].can_ctrl);
+		    &priv->tx_mb->can_ctrl);
 
 	/* acceptance mask/acceptance code (accept everything) */
 	priv->write(0x0, &regs->rxgmask);
@@ -1105,7 +1121,7 @@ static int flexcan_chip_start(struct net_device *dev)
 		priv->write(0x0, &regs->rxfgmask);
 
 	/* clear acceptance filters */
-	for (i = 0; i < ARRAY_SIZE(regs->mb); i++)
+	for (i = 0; i < priv->mb_count; i++)
 		priv->write(0, &regs->rximr[i]);
 
 	/* On Vybrid, disable memory error detection interrupts
@@ -1188,7 +1204,6 @@ static void flexcan_chip_stop(struct net_device *dev)
 static int flexcan_open(struct net_device *dev)
 {
 	struct flexcan_priv *priv = netdev_priv(dev);
-	struct flexcan_regs __iomem *regs = priv->regs;
 	int err;
 
 	err = clk_prepare_enable(priv->clk_ipg);
@@ -1207,13 +1222,20 @@ static int flexcan_open(struct net_device *dev)
 	if (err)
 		goto out_close;
 
+	priv->mb_size = sizeof(struct flexcan_mb) + CAN_MAX_DLEN;
+	priv->mb_count = sizeof(priv->regs->mb) / priv->mb_size;
+
 	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP)
-		priv->tx_mb_reserved = &regs->mb[FLEXCAN_TX_MB_RESERVED_OFF_TIMESTAMP];
+		priv->tx_mb_reserved =
+			flexcan_get_mb(priv, FLEXCAN_TX_MB_RESERVED_OFF_TIMESTAMP);
 	else
-		priv->tx_mb_reserved = &regs->mb[FLEXCAN_TX_MB_RESERVED_OFF_FIFO];
+		priv->tx_mb_reserved =
+			flexcan_get_mb(priv, FLEXCAN_TX_MB_RESERVED_OFF_FIFO);
+	priv->tx_mb_idx = priv->mb_count - 1;
+	priv->tx_mb = flexcan_get_mb(priv, priv->tx_mb_idx);
 
 	priv->reg_imask1_default = 0;
-	priv->reg_imask2_default = FLEXCAN_IFLAG_MB(FLEXCAN_TX_MB);
+	priv->reg_imask2_default = FLEXCAN_IFLAG_MB(priv->tx_mb_idx);
 
 	priv->offload.mailbox_read = flexcan_mailbox_read;
 
@@ -1221,7 +1243,7 @@ static int flexcan_open(struct net_device *dev)
 		u64 imask;
 
 		priv->offload.mb_first = FLEXCAN_RX_MB_OFF_TIMESTAMP_FIRST;
-		priv->offload.mb_last = FLEXCAN_RX_MB_OFF_TIMESTAMP_LAST;
+		priv->offload.mb_last = priv->mb_count - 2;
 
 		imask = GENMASK_ULL(priv->offload.mb_last,
 				    priv->offload.mb_first);
-- 
cgit v1.2.3


From 6cbf76028dcac01129211828d62314285231f79e Mon Sep 17 00:00:00 2001
From: Pankaj Bansal <pankaj.bansal@nxp.com>
Date: Tue, 28 Aug 2018 23:19:12 +0530
Subject: can: flexcan: split the Message Buffer RAM area

The message buffer RAM area is not a contiguous 1KB area but 2 partitions
of 512 bytes each. Till now, we used Message buffers with payload size 8
bytes, which translates to 32 MBs per partition and no spare space is left
in any partition.
However, in upcoming SOC LX2160A the message buffers can have payload size
64 bytes. This results in less than 32 MBs per partition and some empty
area is left at the end of each partition.This empty area should not be
accessed.
Therefore, split the Message Buffer RAM area into two partitions.

Signed-off-by: Pankaj Bansal <pankaj.bansal@nxp.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index ecb50b1bd849..0f36eafe3ac1 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -225,7 +225,7 @@ struct flexcan_regs {
 	u32 rxfgmask;		/* 0x48 */
 	u32 rxfir;		/* 0x4c */
 	u32 _reserved3[12];	/* 0x50 */
-	u8 mb[1024];		/* 0x80 */
+	u8 mb[2][512];		/* 0x80 */
 	/* FIFO-mode:
 	 *			MB
 	 * 0x080...0x08f	0	RX message buffer
@@ -369,11 +369,20 @@ static inline void flexcan_write_le(u32 val, void __iomem *addr)
 static struct flexcan_mb __iomem *flexcan_get_mb(const struct flexcan_priv *priv,
 						 u8 mb_index)
 {
+	u8 bank_size;
+	bool bank;
+
 	if (WARN_ON(mb_index >= priv->mb_count))
 		return NULL;
 
+	bank_size = sizeof(priv->regs->mb[0]) / priv->mb_size;
+
+	bank = mb_index >= bank_size;
+	if (bank)
+		mb_index -= bank_size;
+
 	return (struct flexcan_mb __iomem *)
-		(&priv->regs->mb[priv->mb_size * mb_index]);
+		(&priv->regs->mb[bank][priv->mb_size * mb_index]);
 }
 
 static void flexcan_enable_wakeup_irq(struct flexcan_priv *priv, bool enable)
@@ -1223,7 +1232,8 @@ static int flexcan_open(struct net_device *dev)
 		goto out_close;
 
 	priv->mb_size = sizeof(struct flexcan_mb) + CAN_MAX_DLEN;
-	priv->mb_count = sizeof(priv->regs->mb) / priv->mb_size;
+	priv->mb_count = (sizeof(priv->regs->mb[0]) / priv->mb_size) +
+			 (sizeof(priv->regs->mb[1]) / priv->mb_size);
 
 	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP)
 		priv->tx_mb_reserved =
-- 
cgit v1.2.3


From 7e273a8ebdd3b83f94eb8b49fc8ee61464f47cc2 Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Mon, 26 Nov 2018 16:27:29 +0000
Subject: dpaa2-eth: Add basic XDP support

We keep one XDP program reference per channel. The only actions
supported for now are XDP_DROP and XDP_PASS.

Until now we didn't enforce a maximum size for Rx frames based
on MTU value. Change that, since for XDP mode we must ensure no
scatter-gather frames can be received.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Acked-by: Camelia Groza <camelia.groza@nxp.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 189 ++++++++++++++++++++++-
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h |   6 +
 2 files changed, 194 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 640967a4d50d..d3cfed4a54b3 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -13,7 +13,8 @@
 #include <linux/iommu.h>
 #include <linux/net_tstamp.h>
 #include <linux/fsl/mc.h>
-
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
 #include <net/sock.h>
 
 #include "dpaa2-eth.h"
@@ -199,6 +200,45 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 	return skb;
 }
 
+static u32 run_xdp(struct dpaa2_eth_priv *priv,
+		   struct dpaa2_eth_channel *ch,
+		   struct dpaa2_fd *fd, void *vaddr)
+{
+	struct bpf_prog *xdp_prog;
+	struct xdp_buff xdp;
+	u32 xdp_act = XDP_PASS;
+
+	rcu_read_lock();
+
+	xdp_prog = READ_ONCE(ch->xdp.prog);
+	if (!xdp_prog)
+		goto out;
+
+	xdp.data = vaddr + dpaa2_fd_get_offset(fd);
+	xdp.data_end = xdp.data + dpaa2_fd_get_len(fd);
+	xdp.data_hard_start = xdp.data;
+	xdp_set_data_meta_invalid(&xdp);
+
+	xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+	switch (xdp_act) {
+	case XDP_PASS:
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(xdp_act);
+	case XDP_ABORTED:
+		trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act);
+	case XDP_DROP:
+		ch->buf_count--;
+		free_rx_fd(priv, fd, vaddr);
+		break;
+	}
+
+out:
+	rcu_read_unlock();
+	return xdp_act;
+}
+
 /* Main Rx frame processing routine */
 static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			 struct dpaa2_eth_channel *ch,
@@ -215,6 +255,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	struct dpaa2_fas *fas;
 	void *buf_data;
 	u32 status = 0;
+	u32 xdp_act;
 
 	/* Tracing point */
 	trace_dpaa2_rx_fd(priv->net_dev, fd);
@@ -231,8 +272,17 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	percpu_extras = this_cpu_ptr(priv->percpu_extras);
 
 	if (fd_format == dpaa2_fd_single) {
+		xdp_act = run_xdp(priv, ch, (struct dpaa2_fd *)fd, vaddr);
+		if (xdp_act != XDP_PASS) {
+			percpu_stats->rx_packets++;
+			percpu_stats->rx_bytes += dpaa2_fd_get_len(fd);
+			return;
+		}
+
 		skb = build_linear_skb(ch, fd, vaddr);
 	} else if (fd_format == dpaa2_fd_sg) {
+		WARN_ON(priv->xdp_prog);
+
 		skb = build_frag_skb(priv, ch, buf_data);
 		skb_free_frag(vaddr);
 		percpu_extras->rx_sg_frames++;
@@ -1427,6 +1477,141 @@ static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	return -EINVAL;
 }
 
+static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu)
+{
+	int mfl, linear_mfl;
+
+	mfl = DPAA2_ETH_L2_MAX_FRM(mtu);
+	linear_mfl = DPAA2_ETH_RX_BUF_SIZE - DPAA2_ETH_RX_HWA_SIZE -
+		     dpaa2_eth_rx_head_room(priv);
+
+	if (mfl > linear_mfl) {
+		netdev_warn(priv->net_dev, "Maximum MTU for XDP is %d\n",
+			    linear_mfl - VLAN_ETH_HLEN);
+		return false;
+	}
+
+	return true;
+}
+
+static int set_rx_mfl(struct dpaa2_eth_priv *priv, int mtu, bool has_xdp)
+{
+	int mfl, err;
+
+	/* We enforce a maximum Rx frame length based on MTU only if we have
+	 * an XDP program attached (in order to avoid Rx S/G frames).
+	 * Otherwise, we accept all incoming frames as long as they are not
+	 * larger than maximum size supported in hardware
+	 */
+	if (has_xdp)
+		mfl = DPAA2_ETH_L2_MAX_FRM(mtu);
+	else
+		mfl = DPAA2_ETH_MFL;
+
+	err = dpni_set_max_frame_length(priv->mc_io, 0, priv->mc_token, mfl);
+	if (err) {
+		netdev_err(priv->net_dev, "dpni_set_max_frame_length failed\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int dpaa2_eth_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+	int err;
+
+	if (!priv->xdp_prog)
+		goto out;
+
+	if (!xdp_mtu_valid(priv, new_mtu))
+		return -EINVAL;
+
+	err = set_rx_mfl(priv, new_mtu, true);
+	if (err)
+		return err;
+
+out:
+	dev->mtu = new_mtu;
+	return 0;
+}
+
+static int setup_xdp(struct net_device *dev, struct bpf_prog *prog)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+	struct dpaa2_eth_channel *ch;
+	struct bpf_prog *old;
+	bool up, need_update;
+	int i, err;
+
+	if (prog && !xdp_mtu_valid(priv, dev->mtu))
+		return -EINVAL;
+
+	if (prog) {
+		prog = bpf_prog_add(prog, priv->num_channels);
+		if (IS_ERR(prog))
+			return PTR_ERR(prog);
+	}
+
+	up = netif_running(dev);
+	need_update = (!!priv->xdp_prog != !!prog);
+
+	if (up)
+		dpaa2_eth_stop(dev);
+
+	/* While in xdp mode, enforce a maximum Rx frame size based on MTU */
+	if (need_update) {
+		err = set_rx_mfl(priv, dev->mtu, !!prog);
+		if (err)
+			goto out_err;
+	}
+
+	old = xchg(&priv->xdp_prog, prog);
+	if (old)
+		bpf_prog_put(old);
+
+	for (i = 0; i < priv->num_channels; i++) {
+		ch = priv->channel[i];
+		old = xchg(&ch->xdp.prog, prog);
+		if (old)
+			bpf_prog_put(old);
+	}
+
+	if (up) {
+		err = dpaa2_eth_open(dev);
+		if (err)
+			return err;
+	}
+
+	return 0;
+
+out_err:
+	if (prog)
+		bpf_prog_sub(prog, priv->num_channels);
+	if (up)
+		dpaa2_eth_open(dev);
+
+	return err;
+}
+
+static int dpaa2_eth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return setup_xdp(dev, xdp->prog);
+	case XDP_QUERY_PROG:
+		xdp->prog_id = priv->xdp_prog ? priv->xdp_prog->aux->id : 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_open = dpaa2_eth_open,
 	.ndo_start_xmit = dpaa2_eth_tx,
@@ -1436,6 +1621,8 @@ static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_set_rx_mode = dpaa2_eth_set_rx_mode,
 	.ndo_set_features = dpaa2_eth_set_features,
 	.ndo_do_ioctl = dpaa2_eth_ioctl,
+	.ndo_change_mtu = dpaa2_eth_change_mtu,
+	.ndo_bpf = dpaa2_eth_xdp,
 };
 
 static void cdan_cb(struct dpaa2_io_notification_ctx *ctx)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 16545e9386cd..2873a15b6b28 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -283,6 +283,10 @@ struct dpaa2_eth_fq {
 	struct dpaa2_eth_fq_stats stats;
 };
 
+struct dpaa2_eth_ch_xdp {
+	struct bpf_prog *prog;
+};
+
 struct dpaa2_eth_channel {
 	struct dpaa2_io_notification_ctx nctx;
 	struct fsl_mc_device *dpcon;
@@ -294,6 +298,7 @@ struct dpaa2_eth_channel {
 	struct dpaa2_eth_priv *priv;
 	int buf_count;
 	struct dpaa2_eth_ch_stats stats;
+	struct dpaa2_eth_ch_xdp xdp;
 };
 
 struct dpaa2_eth_dist_fields {
@@ -353,6 +358,7 @@ struct dpaa2_eth_priv {
 	u64 rx_hash_fields;
 	struct dpaa2_eth_cls_rule *cls_rules;
 	u8 rx_cls_enabled;
+	struct bpf_prog *xdp_prog;
 };
 
 #define DPAA2_RXH_SUPPORTED	(RXH_L2DA | RXH_VLAN | RXH_L3_PROTO \
-- 
cgit v1.2.3


From 7b1eea1a747574612d9ec1aeeb4ade9817abfbba Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Mon, 26 Nov 2018 16:27:30 +0000
Subject: dpaa2-eth: Allow XDP header adjustments

Reserve XDP_PACKET_HEADROOM bytes in Rx buffers to allow XDP
programs to increase frame header size.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 43 ++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index d3cfed4a54b3..008cdf8c40be 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -216,11 +216,15 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 
 	xdp.data = vaddr + dpaa2_fd_get_offset(fd);
 	xdp.data_end = xdp.data + dpaa2_fd_get_len(fd);
-	xdp.data_hard_start = xdp.data;
+	xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
 	xdp_set_data_meta_invalid(&xdp);
 
 	xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
+	/* xdp.data pointer may have changed */
+	dpaa2_fd_set_offset(fd, xdp.data - vaddr);
+	dpaa2_fd_set_len(fd, xdp.data_end - xdp.data);
+
 	switch (xdp_act) {
 	case XDP_PASS:
 		break;
@@ -1483,7 +1487,7 @@ static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu)
 
 	mfl = DPAA2_ETH_L2_MAX_FRM(mtu);
 	linear_mfl = DPAA2_ETH_RX_BUF_SIZE - DPAA2_ETH_RX_HWA_SIZE -
-		     dpaa2_eth_rx_head_room(priv);
+		     dpaa2_eth_rx_head_room(priv) - XDP_PACKET_HEADROOM;
 
 	if (mfl > linear_mfl) {
 		netdev_warn(priv->net_dev, "Maximum MTU for XDP is %d\n",
@@ -1537,6 +1541,32 @@ out:
 	return 0;
 }
 
+static int update_rx_buffer_headroom(struct dpaa2_eth_priv *priv, bool has_xdp)
+{
+	struct dpni_buffer_layout buf_layout = {0};
+	int err;
+
+	err = dpni_get_buffer_layout(priv->mc_io, 0, priv->mc_token,
+				     DPNI_QUEUE_RX, &buf_layout);
+	if (err) {
+		netdev_err(priv->net_dev, "dpni_get_buffer_layout failed\n");
+		return err;
+	}
+
+	/* Reserve extra headroom for XDP header size changes */
+	buf_layout.data_head_room = dpaa2_eth_rx_head_room(priv) +
+				    (has_xdp ? XDP_PACKET_HEADROOM : 0);
+	buf_layout.options = DPNI_BUF_LAYOUT_OPT_DATA_HEAD_ROOM;
+	err = dpni_set_buffer_layout(priv->mc_io, 0, priv->mc_token,
+				     DPNI_QUEUE_RX, &buf_layout);
+	if (err) {
+		netdev_err(priv->net_dev, "dpni_set_buffer_layout failed\n");
+		return err;
+	}
+
+	return 0;
+}
+
 static int setup_xdp(struct net_device *dev, struct bpf_prog *prog)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(dev);
@@ -1560,11 +1590,18 @@ static int setup_xdp(struct net_device *dev, struct bpf_prog *prog)
 	if (up)
 		dpaa2_eth_stop(dev);
 
-	/* While in xdp mode, enforce a maximum Rx frame size based on MTU */
+	/* While in xdp mode, enforce a maximum Rx frame size based on MTU.
+	 * Also, when switching between xdp/non-xdp modes we need to reconfigure
+	 * our Rx buffer layout. Buffer pool was drained on dpaa2_eth_stop,
+	 * so we are sure no old format buffers will be used from now on.
+	 */
 	if (need_update) {
 		err = set_rx_mfl(priv, dev->mtu, !!prog);
 		if (err)
 			goto out_err;
+		err = update_rx_buffer_headroom(priv, !!prog);
+		if (err)
+			goto out_err;
 	}
 
 	old = xchg(&priv->xdp_prog, prog);
-- 
cgit v1.2.3


From 569375fb5732b7d7bb5be126c6243acf658697e4 Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Mon, 26 Nov 2018 16:27:31 +0000
Subject: dpaa2-eth: Move function

We'll use function free_bufs() on the XDP path as well, so move
it higher in order to avoid a forward declaration.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 34 ++++++++++++------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 008cdf8c40be..174c960dd62d 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -200,6 +200,23 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 	return skb;
 }
 
+/* Free buffers acquired from the buffer pool or which were meant to
+ * be released in the pool
+ */
+static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
+{
+	struct device *dev = priv->net_dev->dev.parent;
+	void *vaddr;
+	int i;
+
+	for (i = 0; i < count; i++) {
+		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
+		dma_unmap_single(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
+				 DMA_FROM_DEVICE);
+		skb_free_frag(vaddr);
+	}
+}
+
 static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		   struct dpaa2_eth_channel *ch,
 		   struct dpaa2_fd *fd, void *vaddr)
@@ -797,23 +814,6 @@ static int set_tx_csum(struct dpaa2_eth_priv *priv, bool enable)
 	return 0;
 }
 
-/* Free buffers acquired from the buffer pool or which were meant to
- * be released in the pool
- */
-static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
-{
-	struct device *dev = priv->net_dev->dev.parent;
-	void *vaddr;
-	int i;
-
-	for (i = 0; i < count; i++) {
-		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
-		dma_unmap_single(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_FROM_DEVICE);
-		skb_free_frag(vaddr);
-	}
-}
-
 /* Perform a single release command to add buffers
  * to the specified buffer pool
  */
-- 
cgit v1.2.3


From 5d39dc21482aad384d0a34f44cd06cb841a9ee29 Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Mon, 26 Nov 2018 16:27:31 +0000
Subject: dpaa2-eth: Release buffers back to pool on XDP_DROP

Instead of freeing the RX buffers, release them back into the pool.
We wait for the maximum number of buffers supported by a single
release command to accumulate before issuing the command.

Also, don't unmap the Rx buffers at the beginning of the Rx routine
anymore, since that would require remapping them before release.
Instead, just do a DMA sync at first and only unmap if the frame is
meant for the stack.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 34 +++++++++++++++++++++---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h |  2 ++
 2 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 174c960dd62d..ac4cb817ee9a 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -217,10 +217,34 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
 	}
 }
 
+static void xdp_release_buf(struct dpaa2_eth_priv *priv,
+			    struct dpaa2_eth_channel *ch,
+			    dma_addr_t addr)
+{
+	int err;
+
+	ch->xdp.drop_bufs[ch->xdp.drop_cnt++] = addr;
+	if (ch->xdp.drop_cnt < DPAA2_ETH_BUFS_PER_CMD)
+		return;
+
+	while ((err = dpaa2_io_service_release(ch->dpio, priv->bpid,
+					       ch->xdp.drop_bufs,
+					       ch->xdp.drop_cnt)) == -EBUSY)
+		cpu_relax();
+
+	if (err) {
+		free_bufs(priv, ch->xdp.drop_bufs, ch->xdp.drop_cnt);
+		ch->buf_count -= ch->xdp.drop_cnt;
+	}
+
+	ch->xdp.drop_cnt = 0;
+}
+
 static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		   struct dpaa2_eth_channel *ch,
 		   struct dpaa2_fd *fd, void *vaddr)
 {
+	dma_addr_t addr = dpaa2_fd_get_addr(fd);
 	struct bpf_prog *xdp_prog;
 	struct xdp_buff xdp;
 	u32 xdp_act = XDP_PASS;
@@ -250,8 +274,7 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 	case XDP_ABORTED:
 		trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act);
 	case XDP_DROP:
-		ch->buf_count--;
-		free_rx_fd(priv, fd, vaddr);
+		xdp_release_buf(priv, ch, addr);
 		break;
 	}
 
@@ -282,7 +305,8 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	trace_dpaa2_rx_fd(priv->net_dev, fd);
 
 	vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-	dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE, DMA_FROM_DEVICE);
+	dma_sync_single_for_cpu(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+				DMA_FROM_DEVICE);
 
 	fas = dpaa2_get_fas(vaddr, false);
 	prefetch(fas);
@@ -300,10 +324,14 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			return;
 		}
 
+		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+				 DMA_FROM_DEVICE);
 		skb = build_linear_skb(ch, fd, vaddr);
 	} else if (fd_format == dpaa2_fd_sg) {
 		WARN_ON(priv->xdp_prog);
 
+		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+				 DMA_FROM_DEVICE);
 		skb = build_frag_skb(priv, ch, buf_data);
 		skb_free_frag(vaddr);
 		percpu_extras->rx_sg_frames++;
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 2873a15b6b28..23cf9d94f233 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -285,6 +285,8 @@ struct dpaa2_eth_fq {
 
 struct dpaa2_eth_ch_xdp {
 	struct bpf_prog *prog;
+	u64 drop_bufs[DPAA2_ETH_BUFS_PER_CMD];
+	int drop_cnt;
 };
 
 struct dpaa2_eth_channel {
-- 
cgit v1.2.3


From 18c2e770e65180c0cfbc70965c2421ac2a1e8fbb Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Mon, 26 Nov 2018 16:27:32 +0000
Subject: dpaa2-eth: Map Rx buffers as bidirectional

In order to support enqueueing Rx FDs back to hardware, we need to
DMA map Rx buffers as bidirectional.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index ac4cb817ee9a..c2e880bb4015 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -87,7 +87,7 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv,
 		addr = dpaa2_sg_get_addr(&sgt[i]);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
 		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_FROM_DEVICE);
+				 DMA_BIDIRECTIONAL);
 
 		skb_free_frag(sg_vaddr);
 		if (dpaa2_sg_is_final(&sgt[i]))
@@ -145,7 +145,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 		sg_addr = dpaa2_sg_get_addr(sge);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr);
 		dma_unmap_single(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_FROM_DEVICE);
+				 DMA_BIDIRECTIONAL);
 
 		sg_length = dpaa2_sg_get_len(sge);
 
@@ -212,7 +212,7 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
 	for (i = 0; i < count; i++) {
 		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
 		dma_unmap_single(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_FROM_DEVICE);
+				 DMA_BIDIRECTIONAL);
 		skb_free_frag(vaddr);
 	}
 }
@@ -306,7 +306,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 
 	vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
 	dma_sync_single_for_cpu(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
-				DMA_FROM_DEVICE);
+				DMA_BIDIRECTIONAL);
 
 	fas = dpaa2_get_fas(vaddr, false);
 	prefetch(fas);
@@ -325,13 +325,13 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 		}
 
 		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_FROM_DEVICE);
+				 DMA_BIDIRECTIONAL);
 		skb = build_linear_skb(ch, fd, vaddr);
 	} else if (fd_format == dpaa2_fd_sg) {
 		WARN_ON(priv->xdp_prog);
 
 		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_FROM_DEVICE);
+				 DMA_BIDIRECTIONAL);
 		skb = build_frag_skb(priv, ch, buf_data);
 		skb_free_frag(vaddr);
 		percpu_extras->rx_sg_frames++;
@@ -865,7 +865,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		buf = PTR_ALIGN(buf, priv->rx_buf_align);
 
 		addr = dma_map_single(dev, buf, DPAA2_ETH_RX_BUF_SIZE,
-				      DMA_FROM_DEVICE);
+				      DMA_BIDIRECTIONAL);
 		if (unlikely(dma_mapping_error(dev, addr)))
 			goto err_map;
 
-- 
cgit v1.2.3


From 99e43521a06906b6936f0c7b547a2bef856b7d64 Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Mon, 26 Nov 2018 16:27:33 +0000
Subject: dpaa2-eth: Add support for XDP_TX

Send frames back on the same port for XDP_TX action.
Since the frame buffers have been allocated by us, we can recycle
them directly into the Rx buffer pool instead of requesting a
confirmation frame upon transmission complete.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 51 +++++++++++++++++++++++-
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h |  2 +
 2 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index c2e880bb4015..bc582c4bc0c0 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -240,14 +240,53 @@ static void xdp_release_buf(struct dpaa2_eth_priv *priv,
 	ch->xdp.drop_cnt = 0;
 }
 
+static int xdp_enqueue(struct dpaa2_eth_priv *priv, struct dpaa2_fd *fd,
+		       void *buf_start, u16 queue_id)
+{
+	struct dpaa2_eth_fq *fq;
+	struct dpaa2_faead *faead;
+	u32 ctrl, frc;
+	int i, err;
+
+	/* Mark the egress frame hardware annotation area as valid */
+	frc = dpaa2_fd_get_frc(fd);
+	dpaa2_fd_set_frc(fd, frc | DPAA2_FD_FRC_FAEADV);
+	dpaa2_fd_set_ctrl(fd, DPAA2_FD_CTRL_ASAL);
+
+	/* Instruct hardware to release the FD buffer directly into
+	 * the buffer pool once transmission is completed, instead of
+	 * sending a Tx confirmation frame to us
+	 */
+	ctrl = DPAA2_FAEAD_A4V | DPAA2_FAEAD_A2V | DPAA2_FAEAD_EBDDV;
+	faead = dpaa2_get_faead(buf_start, false);
+	faead->ctrl = cpu_to_le32(ctrl);
+	faead->conf_fqid = 0;
+
+	fq = &priv->fq[queue_id];
+	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
+		err = dpaa2_io_service_enqueue_qd(fq->channel->dpio,
+						  priv->tx_qdid, 0,
+						  fq->tx_qdbin, fd);
+		if (err != -EBUSY)
+			break;
+	}
+
+	return err;
+}
+
 static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		   struct dpaa2_eth_channel *ch,
+		   struct dpaa2_eth_fq *rx_fq,
 		   struct dpaa2_fd *fd, void *vaddr)
 {
 	dma_addr_t addr = dpaa2_fd_get_addr(fd);
+	struct rtnl_link_stats64 *percpu_stats;
 	struct bpf_prog *xdp_prog;
 	struct xdp_buff xdp;
 	u32 xdp_act = XDP_PASS;
+	int err;
+
+	percpu_stats = this_cpu_ptr(priv->percpu_stats);
 
 	rcu_read_lock();
 
@@ -269,6 +308,16 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 	switch (xdp_act) {
 	case XDP_PASS:
 		break;
+	case XDP_TX:
+		err = xdp_enqueue(priv, fd, vaddr, rx_fq->flowid);
+		if (err) {
+			xdp_release_buf(priv, ch, addr);
+			percpu_stats->tx_errors++;
+		} else {
+			percpu_stats->tx_packets++;
+			percpu_stats->tx_bytes += dpaa2_fd_get_len(fd);
+		}
+		break;
 	default:
 		bpf_warn_invalid_xdp_action(xdp_act);
 	case XDP_ABORTED:
@@ -317,7 +366,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	percpu_extras = this_cpu_ptr(priv->percpu_extras);
 
 	if (fd_format == dpaa2_fd_single) {
-		xdp_act = run_xdp(priv, ch, (struct dpaa2_fd *)fd, vaddr);
+		xdp_act = run_xdp(priv, ch, fq, (struct dpaa2_fd *)fd, vaddr);
 		if (xdp_act != XDP_PASS) {
 			percpu_stats->rx_packets++;
 			percpu_stats->rx_bytes += dpaa2_fd_get_len(fd);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 23cf9d94f233..5530a0ea8620 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -139,7 +139,9 @@ struct dpaa2_faead {
 };
 
 #define DPAA2_FAEAD_A2V			0x20000000
+#define DPAA2_FAEAD_A4V			0x08000000
 #define DPAA2_FAEAD_UPDV		0x00001000
+#define DPAA2_FAEAD_EBDDV		0x00002000
 #define DPAA2_FAEAD_UPD			0x00000010
 
 /* Accessors for the hardware annotation fields that we use */
-- 
cgit v1.2.3


From 0ff8f0aab49bb1383d848e44aedac6cfc1329f4f Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Mon, 26 Nov 2018 16:27:33 +0000
Subject: dpaa2-eth: Cleanup channel stats

Remove unused counter. Reorder fields in channel stats structure
to match the ethtool strings order and make it easier to print them
with ethtool -S.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c     |  1 -
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h     |  6 ++----
 drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c | 16 +++++-----------
 3 files changed, 7 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index bc582c4bc0c0..d2bc5da05805 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -467,7 +467,6 @@ static int consume_frames(struct dpaa2_eth_channel *ch,
 		return 0;
 
 	fq->stats.frames += cleaned;
-	ch->stats.frames += cleaned;
 
 	/* A dequeue operation only pulls frames from a single queue
 	 * into the store. Return the frame queue as an out param.
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 5530a0ea8620..41a2a0dcef8e 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -245,12 +245,10 @@ struct dpaa2_eth_fq_stats {
 struct dpaa2_eth_ch_stats {
 	/* Volatile dequeues retried due to portal busy */
 	__u64 dequeue_portal_busy;
-	/* Number of CDANs; useful to estimate avg NAPI len */
-	__u64 cdan;
-	/* Number of frames received on queues from this channel */
-	__u64 frames;
 	/* Pull errors */
 	__u64 pull_err;
+	/* Number of CDANs; useful to estimate avg NAPI len */
+	__u64 cdan;
 };
 
 /* Maximum number of queues associated with a DPNI */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 26bd5a2bd8ed..79eeebeb1ffe 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -174,8 +174,6 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 	int j, k, err;
 	int num_cnt;
 	union dpni_statistics dpni_stats;
-	u64 cdan = 0;
-	u64 portal_busy = 0, pull_err = 0;
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	struct dpaa2_eth_drv_stats *extras;
 	struct dpaa2_eth_ch_stats *ch_stats;
@@ -212,16 +210,12 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 	}
 	i += j;
 
-	for (j = 0; j < priv->num_channels; j++) {
-		ch_stats = &priv->channel[j]->stats;
-		cdan += ch_stats->cdan;
-		portal_busy += ch_stats->dequeue_portal_busy;
-		pull_err += ch_stats->pull_err;
+	/* Per-channel stats */
+	for (k = 0; k < priv->num_channels; k++) {
+		ch_stats = &priv->channel[k]->stats;
+		for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64); j++)
+			*((__u64 *)data + i + j) += *((__u64 *)ch_stats + j);
 	}
-
-	*(data + i++) = portal_busy;
-	*(data + i++) = pull_err;
-	*(data + i++) = cdan;
 }
 
 static int prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask,
-- 
cgit v1.2.3


From a4a7b762eb21755bce190de1b75ba7e32bfab4e0 Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Mon, 26 Nov 2018 16:27:34 +0000
Subject: dpaa2-eth: Add xdp counters

Add counters for xdp processed frames to the channel statistics.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c     | 3 +++
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h     | 4 ++++
 drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c | 3 +++
 3 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index d2bc5da05805..be841718eb49 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -313,9 +313,11 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		if (err) {
 			xdp_release_buf(priv, ch, addr);
 			percpu_stats->tx_errors++;
+			ch->stats.xdp_tx_err++;
 		} else {
 			percpu_stats->tx_packets++;
 			percpu_stats->tx_bytes += dpaa2_fd_get_len(fd);
+			ch->stats.xdp_tx++;
 		}
 		break;
 	default:
@@ -324,6 +326,7 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act);
 	case XDP_DROP:
 		xdp_release_buf(priv, ch, addr);
+		ch->stats.xdp_drop++;
 		break;
 	}
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 41a2a0dcef8e..69c965de192b 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -249,6 +249,10 @@ struct dpaa2_eth_ch_stats {
 	__u64 pull_err;
 	/* Number of CDANs; useful to estimate avg NAPI len */
 	__u64 cdan;
+	/* XDP counters */
+	__u64 xdp_drop;
+	__u64 xdp_tx;
+	__u64 xdp_tx_err;
 };
 
 /* Maximum number of queues associated with a DPNI */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 79eeebeb1ffe..0c831bffeb92 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -45,6 +45,9 @@ static char dpaa2_ethtool_extras[][ETH_GSTRING_LEN] = {
 	"[drv] dequeue portal busy",
 	"[drv] channel pull errors",
 	"[drv] cdan",
+	"[drv] xdp drop",
+	"[drv] xdp tx",
+	"[drv] xdp tx errors",
 };
 
 #define DPAA2_ETH_NUM_EXTRA_STATS	ARRAY_SIZE(dpaa2_ethtool_extras)
-- 
cgit v1.2.3


From 9cc549e4a7300a4b09da1429ed8c9c8f5759246f Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 28 Nov 2018 20:24:41 +0800
Subject: net: neterion: vxge: remove set but not used variables 'max_frags'
 and 'txdl_priv'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/neterion/vxge/vxge-traffic.c:1698:35:
 warning: variable 'txdl_priv' set but not used [-Wunused-but-set-variable]
drivers/net/ethernet/neterion/vxge/vxge-traffic.c:1699:6:
 warning: variable 'max_frags' set but not used [-Wunused-but-set-variable]

It never used since introduction in
commit 113241321dcd ("Neterion: New driver: Traffic & alarm handler")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/neterion/vxge/vxge-traffic.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
index f7a0d1d5885e..59e77e3086bb 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
@@ -1695,17 +1695,10 @@ exit:
  */
 void vxge_hw_fifo_txdl_free(struct __vxge_hw_fifo *fifo, void *txdlh)
 {
-	struct __vxge_hw_fifo_txdl_priv *txdl_priv;
-	u32 max_frags;
 	struct __vxge_hw_channel *channel;
 
 	channel = &fifo->channel;
 
-	txdl_priv = __vxge_hw_fifo_txdl_priv(fifo,
-			(struct vxge_hw_fifo_txd *)txdlh);
-
-	max_frags = fifo->config->max_frags;
-
 	vxge_hw_channel_dtr_free(channel, txdlh);
 }
 
-- 
cgit v1.2.3


From 8eb08cf8a35a525dc40b9fedd33833a4a7aecfb2 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 28 Nov 2018 20:29:39 +0800
Subject: qlcnic: remove set but not used variables 'cur_rings, max_hw_rings,
 tx_desc_info'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c:4011:5:
 warning: variable 'max_hw_rings' set but not used [-Wunused-but-set-variable]
drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c:4013:6:
 warning: variable 'cur_rings' set but not used [-Wunused-but-set-variable]
drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c:2996:25:
 warning: variable 'tx_desc_info' set but not used [-Wunused-but-set-variable]

'cur_rings, max_hw_rings' never used since introduction in commit
34e8c406fda5 ("qlcnic: refactor Tx/SDS ring calculation and validation in driver.")
'tx_desc_info' never used since commit
95b3890ae39f ("qlcnic: Enhance Tx timeout debugging.")
Also 'queue_type' only can be QLCNIC_RX_QUEUE/QLCNIC_TX_QUEUE,
so make a trival cleanup on if statement.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Shahed Shaikh <shahed.shaikh@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index d42ba2293d8c..16d0479f6891 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -2993,10 +2993,8 @@ int qlcnic_check_temp(struct qlcnic_adapter *adapter)
 static inline void dump_tx_ring_desc(struct qlcnic_host_tx_ring *tx_ring)
 {
 	int i;
-	struct cmd_desc_type0 *tx_desc_info;
 
 	for (i = 0; i < tx_ring->num_desc; i++) {
-		tx_desc_info = &tx_ring->desc_head[i];
 		pr_info("TX Desc: %d\n", i);
 		print_hex_dump(KERN_INFO, "TX: ", DUMP_PREFIX_OFFSET, 16, 1,
 			       &tx_ring->desc_head[i],
@@ -4008,19 +4006,12 @@ int qlcnic_validate_rings(struct qlcnic_adapter *adapter, __u32 ring_cnt,
 			  int queue_type)
 {
 	struct net_device *netdev = adapter->netdev;
-	u8 max_hw_rings = 0;
 	char buf[8];
-	int cur_rings;
 
-	if (queue_type == QLCNIC_RX_QUEUE) {
-		max_hw_rings = adapter->max_sds_rings;
-		cur_rings = adapter->drv_sds_rings;
+	if (queue_type == QLCNIC_RX_QUEUE)
 		strcpy(buf, "SDS");
-	} else if (queue_type == QLCNIC_TX_QUEUE) {
-		max_hw_rings = adapter->max_tx_rings;
-		cur_rings = adapter->drv_tx_rings;
+	else
 		strcpy(buf, "Tx");
-	}
 
 	if (!is_power_of_2(ring_cnt)) {
 		netdev_err(netdev, "%s rings value should be a power of 2\n",
-- 
cgit v1.2.3


From 62e3a931788223048120357ab3f29dcb55c5ef79 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 28 Nov 2018 20:31:42 +0800
Subject: net: qualcomm: rmnet: remove set but not used variables 'ip_family,
 fc_seq, qos_id'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c:26:6:
 warning: variable 'ip_family' set but not used [-Wunused-but-set-variable]
drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c:27:6:
 warning: variable 'fc_seq' set but not used [-Wunused-but-set-variable]
drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c:28:6:
 warning: variable 'qos_id' set but not used [-Wunused-but-set-variable]

It never used since introduction in commit
ceed73a2cf4a ("drivers: net: ethernet: qualcomm: rmnet: Initial implementation")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
index 3ee8ae9b6838..8990307e5475 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
@@ -23,9 +23,6 @@ static u8 rmnet_map_do_flow_control(struct sk_buff *skb,
 	struct rmnet_map_control_command *cmd;
 	struct rmnet_endpoint *ep;
 	struct net_device *vnd;
-	u16 ip_family;
-	u16 fc_seq;
-	u32 qos_id;
 	u8 mux_id;
 	int r;
 
@@ -45,10 +42,6 @@ static u8 rmnet_map_do_flow_control(struct sk_buff *skb,
 
 	vnd = ep->egress_dev;
 
-	ip_family = cmd->flow_control.ip_family;
-	fc_seq = ntohs(cmd->flow_control.flow_control_seq_num);
-	qos_id = ntohl(cmd->flow_control.qos_id);
-
 	/* Ignore the ip family and pass the sequence number for both v4 and v6
 	 * sequence. User space does not support creating dedicated flows for
 	 * the 2 protocols
-- 
cgit v1.2.3


From 7246d8ed4dcce23f7509949a77be15fa9f0e3d28 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Mon, 26 Nov 2018 14:16:17 -0800
Subject: bpf: helper to pop data from messages

This adds a BPF SK_MSG program helper so that we can pop data from a
msg. We use this to pop metadata from a previous push data call.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h |  16 ++++-
 net/core/filter.c        | 171 +++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/tcp_bpf.c       |  17 ++++-
 net/tls/tls_sw.c         |  11 ++-
 4 files changed, 209 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 23e2031a43d4..597afdbc1ab9 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2268,6 +2268,19 @@ union bpf_attr {
  *
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags)
+ *	 Description
+ *		Will remove *pop* bytes from a *msg* starting at byte *start*.
+ *		This may result in **ENOMEM** errors under certain situations if
+ *		an allocation and copy are required due to a full ring buffer.
+ *		However, the helper will try to avoid doing the allocation
+ *		if possible. Other errors can occur if input parameters are
+ *		invalid either due to *start* byte not being valid part of msg
+ *		payload and/or *pop* value being to large.
+ *
+ *	Return
+ *		0 on success, or a negative erro in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2360,7 +2373,8 @@ union bpf_attr {
 	FN(map_push_elem),		\
 	FN(map_pop_elem),		\
 	FN(map_peek_elem),		\
-	FN(msg_push_data),
+	FN(msg_push_data),		\
+	FN(msg_pop_data),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/net/core/filter.c b/net/core/filter.c
index f50ea971f7a9..bd0df75dc7b6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2425,6 +2425,174 @@ static const struct bpf_func_proto bpf_msg_push_data_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+static void sk_msg_shift_left(struct sk_msg *msg, int i)
+{
+	int prev;
+
+	do {
+		prev = i;
+		sk_msg_iter_var_next(i);
+		msg->sg.data[prev] = msg->sg.data[i];
+	} while (i != msg->sg.end);
+
+	sk_msg_iter_prev(msg, end);
+}
+
+static void sk_msg_shift_right(struct sk_msg *msg, int i)
+{
+	struct scatterlist tmp, sge;
+
+	sk_msg_iter_next(msg, end);
+	sge = sk_msg_elem_cpy(msg, i);
+	sk_msg_iter_var_next(i);
+	tmp = sk_msg_elem_cpy(msg, i);
+
+	while (i != msg->sg.end) {
+		msg->sg.data[i] = sge;
+		sk_msg_iter_var_next(i);
+		sge = tmp;
+		tmp = sk_msg_elem_cpy(msg, i);
+	}
+}
+
+BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
+	   u32, len, u64, flags)
+{
+	u32 i = 0, l, space, offset = 0;
+	u64 last = start + len;
+	int pop;
+
+	if (unlikely(flags))
+		return -EINVAL;
+
+	/* First find the starting scatterlist element */
+	i = msg->sg.start;
+	do {
+		l = sk_msg_elem(msg, i)->length;
+
+		if (start < offset + l)
+			break;
+		offset += l;
+		sk_msg_iter_var_next(i);
+	} while (i != msg->sg.end);
+
+	/* Bounds checks: start and pop must be inside message */
+	if (start >= offset + l || last >= msg->sg.size)
+		return -EINVAL;
+
+	space = MAX_MSG_FRAGS - sk_msg_elem_used(msg);
+
+	pop = len;
+	/* --------------| offset
+	 * -| start      |-------- len -------|
+	 *
+	 *  |----- a ----|-------- pop -------|----- b ----|
+	 *  |______________________________________________| length
+	 *
+	 *
+	 * a:   region at front of scatter element to save
+	 * b:   region at back of scatter element to save when length > A + pop
+	 * pop: region to pop from element, same as input 'pop' here will be
+	 *      decremented below per iteration.
+	 *
+	 * Two top-level cases to handle when start != offset, first B is non
+	 * zero and second B is zero corresponding to when a pop includes more
+	 * than one element.
+	 *
+	 * Then if B is non-zero AND there is no space allocate space and
+	 * compact A, B regions into page. If there is space shift ring to
+	 * the rigth free'ing the next element in ring to place B, leaving
+	 * A untouched except to reduce length.
+	 */
+	if (start != offset) {
+		struct scatterlist *nsge, *sge = sk_msg_elem(msg, i);
+		int a = start;
+		int b = sge->length - pop - a;
+
+		sk_msg_iter_var_next(i);
+
+		if (pop < sge->length - a) {
+			if (space) {
+				sge->length = a;
+				sk_msg_shift_right(msg, i);
+				nsge = sk_msg_elem(msg, i);
+				get_page(sg_page(sge));
+				sg_set_page(nsge,
+					    sg_page(sge),
+					    b, sge->offset + pop + a);
+			} else {
+				struct page *page, *orig;
+				u8 *to, *from;
+
+				page = alloc_pages(__GFP_NOWARN |
+						   __GFP_COMP   | GFP_ATOMIC,
+						   get_order(a + b));
+				if (unlikely(!page))
+					return -ENOMEM;
+
+				sge->length = a;
+				orig = sg_page(sge);
+				from = sg_virt(sge);
+				to = page_address(page);
+				memcpy(to, from, a);
+				memcpy(to + a, from + a + pop, b);
+				sg_set_page(sge, page, a + b, 0);
+				put_page(orig);
+			}
+			pop = 0;
+		} else if (pop >= sge->length - a) {
+			sge->length = a;
+			pop -= (sge->length - a);
+		}
+	}
+
+	/* From above the current layout _must_ be as follows,
+	 *
+	 * -| offset
+	 * -| start
+	 *
+	 *  |---- pop ---|---------------- b ------------|
+	 *  |____________________________________________| length
+	 *
+	 * Offset and start of the current msg elem are equal because in the
+	 * previous case we handled offset != start and either consumed the
+	 * entire element and advanced to the next element OR pop == 0.
+	 *
+	 * Two cases to handle here are first pop is less than the length
+	 * leaving some remainder b above. Simply adjust the element's layout
+	 * in this case. Or pop >= length of the element so that b = 0. In this
+	 * case advance to next element decrementing pop.
+	 */
+	while (pop) {
+		struct scatterlist *sge = sk_msg_elem(msg, i);
+
+		if (pop < sge->length) {
+			sge->length -= pop;
+			sge->offset += pop;
+			pop = 0;
+		} else {
+			pop -= sge->length;
+			sk_msg_shift_left(msg, i);
+		}
+		sk_msg_iter_var_next(i);
+	}
+
+	sk_mem_uncharge(msg->sk, len - pop);
+	msg->sg.size -= (len - pop);
+	sk_msg_compute_data_pointers(msg);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_msg_pop_data_proto = {
+	.func		= bpf_msg_pop_data,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
 {
 	return task_get_classid(skb);
@@ -5098,6 +5266,7 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_xdp_adjust_meta ||
 	    func == bpf_msg_pull_data ||
 	    func == bpf_msg_push_data ||
+	    func == bpf_msg_pop_data ||
 	    func == bpf_xdp_adjust_tail ||
 #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	    func == bpf_lwt_seg6_store_bytes ||
@@ -5394,6 +5563,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_msg_pull_data_proto;
 	case BPF_FUNC_msg_push_data:
 		return &bpf_msg_push_data_proto;
+	case BPF_FUNC_msg_pop_data:
+		return &bpf_msg_pop_data_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 3b45fe530f91..a47c1cdf90fc 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -289,12 +289,23 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 {
 	bool cork = false, enospc = msg->sg.start == msg->sg.end;
 	struct sock *sk_redir;
-	u32 tosend;
+	u32 tosend, delta = 0;
 	int ret;
 
 more_data:
-	if (psock->eval == __SK_NONE)
+	if (psock->eval == __SK_NONE) {
+		/* Track delta in msg size to add/subtract it on SK_DROP from
+		 * returned to user copied size. This ensures user doesn't
+		 * get a positive return code with msg_cut_data and SK_DROP
+		 * verdict.
+		 */
+		delta = msg->sg.size;
 		psock->eval = sk_psock_msg_verdict(sk, psock, msg);
+		if (msg->sg.size < delta)
+			delta -= msg->sg.size;
+		else
+			delta = 0;
+	}
 
 	if (msg->cork_bytes &&
 	    msg->cork_bytes > msg->sg.size && !enospc) {
@@ -350,7 +361,7 @@ more_data:
 	default:
 		sk_msg_free_partial(sk, msg, tosend);
 		sk_msg_apply_bytes(psock, tosend);
-		*copied -= tosend;
+		*copied -= (tosend + delta);
 		return -EACCES;
 	}
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 7b1af8b59cd2..d4ecc66464e6 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -687,6 +687,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 	struct sock *sk_redir;
 	struct tls_rec *rec;
 	int err = 0, send;
+	u32 delta = 0;
 	bool enospc;
 
 	psock = sk_psock_get(sk);
@@ -694,8 +695,14 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 		return tls_push_record(sk, flags, record_type);
 more_data:
 	enospc = sk_msg_full(msg);
-	if (psock->eval == __SK_NONE)
+	if (psock->eval == __SK_NONE) {
+		delta = msg->sg.size;
 		psock->eval = sk_psock_msg_verdict(sk, psock, msg);
+		if (delta < msg->sg.size)
+			delta -= msg->sg.size;
+		else
+			delta = 0;
+	}
 	if (msg->cork_bytes && msg->cork_bytes > msg->sg.size &&
 	    !enospc && !full_record) {
 		err = -ENOSPC;
@@ -743,7 +750,7 @@ more_data:
 			msg->apply_bytes -= send;
 		if (msg->sg.size == 0)
 			tls_free_open_rec(sk);
-		*copied -= send;
+		*copied -= (send + delta);
 		err = -EACCES;
 	}
 
-- 
cgit v1.2.3


From d913a2273a8988cd810a031bfa08249ca7dd5f7c Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Mon, 26 Nov 2018 14:16:18 -0800
Subject: bpf: add msg_pop_data helper to tools

Add the necessary header definitions to tools for new
msg_pop_data_helper.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h            | 16 +++++++++++++++-
 tools/testing/selftests/bpf/bpf_helpers.h |  2 ++
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 23e2031a43d4..597afdbc1ab9 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2268,6 +2268,19 @@ union bpf_attr {
  *
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags)
+ *	 Description
+ *		Will remove *pop* bytes from a *msg* starting at byte *start*.
+ *		This may result in **ENOMEM** errors under certain situations if
+ *		an allocation and copy are required due to a full ring buffer.
+ *		However, the helper will try to avoid doing the allocation
+ *		if possible. Other errors can occur if input parameters are
+ *		invalid either due to *start* byte not being valid part of msg
+ *		payload and/or *pop* value being to large.
+ *
+ *	Return
+ *		0 on success, or a negative erro in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2360,7 +2373,8 @@ union bpf_attr {
 	FN(map_push_elem),		\
 	FN(map_pop_elem),		\
 	FN(map_peek_elem),		\
-	FN(msg_push_data),
+	FN(msg_push_data),		\
+	FN(msg_pop_data),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 686e57ce40f4..7b69519a09b1 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -113,6 +113,8 @@ static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) =
 	(void *) BPF_FUNC_msg_pull_data;
 static int (*bpf_msg_push_data)(void *ctx, int start, int end, int flags) =
 	(void *) BPF_FUNC_msg_push_data;
+static int (*bpf_msg_pop_data)(void *ctx, int start, int cut, int flags) =
+	(void *) BPF_FUNC_msg_pop_data;
 static int (*bpf_bind)(void *ctx, void *addr, int addr_len) =
 	(void *) BPF_FUNC_bind;
 static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
-- 
cgit v1.2.3


From 1ade9abadfca0250c8256bb222a1cd5cc5fa8bbc Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Mon, 26 Nov 2018 14:16:19 -0800
Subject: bpf: test_sockmap, add options for msg_pop_data() helper

Similar to msg_pull_data and msg_push_data add a set of options to
have msg_pop_data() exercised.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_sockmap.c      | 127 +++++++++++++++++++++++-
 tools/testing/selftests/bpf/test_sockmap_kern.h |  70 ++++++++++---
 2 files changed, 180 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 622ade0a0957..e85a771f607b 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -79,6 +79,8 @@ int txmsg_start;
 int txmsg_end;
 int txmsg_start_push;
 int txmsg_end_push;
+int txmsg_start_pop;
+int txmsg_pop;
 int txmsg_ingress;
 int txmsg_skb;
 int ktls;
@@ -104,6 +106,8 @@ static const struct option long_options[] = {
 	{"txmsg_end",	required_argument,	NULL, 'e'},
 	{"txmsg_start_push", required_argument,	NULL, 'p'},
 	{"txmsg_end_push",   required_argument,	NULL, 'q'},
+	{"txmsg_start_pop",  required_argument,	NULL, 'w'},
+	{"txmsg_pop",	     required_argument,	NULL, 'x'},
 	{"txmsg_ingress", no_argument,		&txmsg_ingress, 1 },
 	{"txmsg_skb", no_argument,		&txmsg_skb, 1 },
 	{"ktls", no_argument,			&ktls, 1 },
@@ -473,13 +477,27 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	} else {
 		int slct, recvp = 0, recv, max_fd = fd;
+		float total_bytes, txmsg_pop_total;
 		int fd_flags = O_NONBLOCK;
 		struct timeval timeout;
-		float total_bytes;
 		fd_set w;
 
 		fcntl(fd, fd_flags);
+		/* Account for pop bytes noting each iteration of apply will
+		 * call msg_pop_data helper so we need to account for this
+		 * by calculating the number of apply iterations. Note user
+		 * of the tool can create cases where no data is sent by
+		 * manipulating pop/push/pull/etc. For example txmsg_apply 1
+		 * with txmsg_pop 1 will try to apply 1B at a time but each
+		 * iteration will then pop 1B so no data will ever be sent.
+		 * This is really only useful for testing edge cases in code
+		 * paths.
+		 */
 		total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
+		txmsg_pop_total = txmsg_pop;
+		if (txmsg_apply)
+			txmsg_pop_total *= (total_bytes / txmsg_apply);
+		total_bytes -= txmsg_pop_total;
 		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
 		if (err < 0)
 			perror("recv start time: ");
@@ -488,7 +506,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 				timeout.tv_sec = 0;
 				timeout.tv_usec = 300000;
 			} else {
-				timeout.tv_sec = 1;
+				timeout.tv_sec = 3;
 				timeout.tv_usec = 0;
 			}
 
@@ -503,7 +521,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 				goto out_errno;
 			} else if (!slct) {
 				if (opt->verbose)
-					fprintf(stderr, "unexpected timeout\n");
+					fprintf(stderr, "unexpected timeout: recved %zu/%f pop_total %f\n", s->bytes_recvd, total_bytes, txmsg_pop_total);
 				errno = -EIO;
 				clock_gettime(CLOCK_MONOTONIC, &s->end);
 				goto out_errno;
@@ -619,7 +637,7 @@ static int sendmsg_test(struct sockmap_options *opt)
 			iov_count = 1;
 		err = msg_loop(rx_fd, iov_count, iov_buf,
 			       cnt, &s, false, opt);
-		if (err && opt->verbose)
+		if (opt->verbose)
 			fprintf(stderr,
 				"msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
 				iov_count, iov_buf, cnt, err);
@@ -931,6 +949,39 @@ run:
 			}
 		}
 
+		if (txmsg_start_pop) {
+			i = 4;
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_start_pop, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem %i@%i (txmsg_start_pop):  %d (%s)\n",
+					txmsg_start_pop, i, err, strerror(errno));
+				goto out;
+			}
+		} else {
+			i = 4;
+			bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_start_pop, BPF_ANY);
+		}
+
+		if (txmsg_pop) {
+			i = 5;
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_pop, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem %i@%i (txmsg_pop):  %d (%s)\n",
+					txmsg_pop, i, err, strerror(errno));
+				goto out;
+			}
+		} else {
+			i = 5;
+			bpf_map_update_elem(map_fd[5],
+					    &i, &txmsg_pop, BPF_ANY);
+
+		}
+
 		if (txmsg_ingress) {
 			int in = BPF_F_INGRESS;
 
@@ -1082,6 +1133,11 @@ static void test_options(char *options)
 		snprintf(tstr, OPTSTRING, "end %d,", txmsg_end);
 		strncat(options, tstr, OPTSTRING);
 	}
+	if (txmsg_start_pop) {
+		snprintf(tstr, OPTSTRING, "pop (%d,%d),",
+			 txmsg_start_pop, txmsg_start_pop + txmsg_pop);
+		strncat(options, tstr, OPTSTRING);
+	}
 	if (txmsg_ingress)
 		strncat(options, "ingress,", OPTSTRING);
 	if (txmsg_skb)
@@ -1264,6 +1320,7 @@ static int test_mixed(int cgrp)
 	txmsg_apply = txmsg_cork = 0;
 	txmsg_start = txmsg_end = 0;
 	txmsg_start_push = txmsg_end_push = 0;
+	txmsg_start_pop = txmsg_pop = 0;
 
 	/* Test small and large iov_count values with pass/redir/apply/cork */
 	txmsg_pass = 1;
@@ -1383,6 +1440,19 @@ static int test_start_end(int cgrp)
 	txmsg_end = 2;
 	txmsg_start_push = 1;
 	txmsg_end_push = 2;
+	txmsg_start_pop = 1;
+	txmsg_pop = 1;
+	err = test_txmsg(cgrp);
+	if (err)
+		goto out;
+
+	/* Cut a byte of pushed data but leave reamining in place */
+	txmsg_start = 1;
+	txmsg_end = 2;
+	txmsg_start_push = 1;
+	txmsg_end_push = 3;
+	txmsg_start_pop = 1;
+	txmsg_pop = 1;
 	err = test_txmsg(cgrp);
 	if (err)
 		goto out;
@@ -1393,6 +1463,9 @@ static int test_start_end(int cgrp)
 	opt.iov_length = 100;
 	txmsg_cork = 1600;
 
+	txmsg_start_pop = 0;
+	txmsg_pop = 0;
+
 	for (i = 99; i <= 1600; i += 500) {
 		txmsg_start = 0;
 		txmsg_end = i;
@@ -1403,6 +1476,17 @@ static int test_start_end(int cgrp)
 			goto out;
 	}
 
+	/* Test pop data in middle of cork */
+	for (i = 99; i <= 1600; i += 500) {
+		txmsg_start_pop = 10;
+		txmsg_pop = i;
+		err = test_exec(cgrp, &opt);
+		if (err)
+			goto out;
+	}
+	txmsg_start_pop = 0;
+	txmsg_pop = 0;
+
 	/* Test start/end with cork but pull data in middle */
 	for (i = 199; i <= 1600; i += 500) {
 		txmsg_start = 100;
@@ -1423,6 +1507,15 @@ static int test_start_end(int cgrp)
 	if (err)
 		goto out;
 
+	/* Test pop with cork pulling last sg entry */
+	txmsg_start_pop = 1500;
+	txmsg_pop = 1600;
+	err = test_exec(cgrp, &opt);
+	if (err)
+		goto out;
+	txmsg_start_pop = 0;
+	txmsg_pop = 0;
+
 	/* Test start/end pull of single byte in last page */
 	txmsg_start = 1111;
 	txmsg_end = 1112;
@@ -1432,6 +1525,13 @@ static int test_start_end(int cgrp)
 	if (err)
 		goto out;
 
+	/* Test pop of single byte in last page */
+	txmsg_start_pop = 1111;
+	txmsg_pop = 1112;
+	err = test_exec(cgrp, &opt);
+	if (err)
+		goto out;
+
 	/* Test start/end with end < start */
 	txmsg_start = 1111;
 	txmsg_end = 0;
@@ -1456,7 +1556,20 @@ static int test_start_end(int cgrp)
 	txmsg_start_push = 1601;
 	txmsg_end_push = 1600;
 	err = test_exec(cgrp, &opt);
+	if (err)
+		goto out;
+
+	/* Test pop with start > data */
+	txmsg_start_pop = 1601;
+	txmsg_pop = 1;
+	err = test_exec(cgrp, &opt);
+	if (err)
+		goto out;
 
+	/* Test pop with pop range > data */
+	txmsg_start_pop = 1599;
+	txmsg_pop = 10;
+	err = test_exec(cgrp, &opt);
 out:
 	txmsg_start = 0;
 	txmsg_end = 0;
@@ -1641,6 +1754,12 @@ int main(int argc, char **argv)
 		case 'q':
 			txmsg_end_push = atoi(optarg);
 			break;
+		case 'w':
+			txmsg_start_pop = atoi(optarg);
+			break;
+		case 'x':
+			txmsg_pop = atoi(optarg);
+			break;
 		case 'a':
 			txmsg_apply = atoi(optarg);
 			break;
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h
index 14b8bbac004f..e7639f66a941 100644
--- a/tools/testing/selftests/bpf/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/test_sockmap_kern.h
@@ -74,7 +74,7 @@ struct bpf_map_def SEC("maps") sock_bytes = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(int),
 	.value_size = sizeof(int),
-	.max_entries = 4
+	.max_entries = 6
 };
 
 struct bpf_map_def SEC("maps") sock_redir_flags = {
@@ -181,8 +181,8 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
 SEC("sk_msg1")
 int bpf_prog4(struct sk_msg_md *msg)
 {
-	int *bytes, zero = 0, one = 1, two = 2, three = 3;
-	int *start, *end, *start_push, *end_push;
+	int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
+	int *start, *end, *start_push, *end_push, *start_pop, *pop;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
@@ -198,15 +198,19 @@ int bpf_prog4(struct sk_msg_md *msg)
 	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
 	if (start_push && end_push)
 		bpf_msg_push_data(msg, *start_push, *end_push, 0);
+	start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
+	pop = bpf_map_lookup_elem(&sock_bytes, &five);
+	if (start_pop && pop)
+		bpf_msg_pop_data(msg, *start_pop, *pop, 0);
 	return SK_PASS;
 }
 
 SEC("sk_msg2")
 int bpf_prog5(struct sk_msg_md *msg)
 {
-	int zero = 0, one = 1, two = 2, three = 3;
-	int *start, *end, *start_push, *end_push;
-	int *bytes, len1, len2 = 0, len3;
+	int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
+	int *start, *end, *start_push, *end_push, *start_pop, *pop;
+	int *bytes, len1, len2 = 0, len3, len4;
 	int err1 = -1, err2 = -1;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
@@ -247,6 +251,20 @@ int bpf_prog5(struct sk_msg_md *msg)
 		bpf_printk("sk_msg2: length push_update %i->%i\n",
 			   len2 ? len2 : len1, len3);
 	}
+	start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
+	pop = bpf_map_lookup_elem(&sock_bytes, &five);
+	if (start_pop && pop) {
+		int err;
+
+		bpf_printk("sk_msg2: pop(%i@%i)\n",
+			   start_pop, pop);
+		err = bpf_msg_pop_data(msg, *start_pop, *pop, 0);
+		if (err)
+			bpf_printk("sk_msg2: pop_data err %i\n", err);
+		len4 = (__u64)msg->data_end - (__u64)msg->data;
+		bpf_printk("sk_msg2: length pop_data %i->%i\n",
+			   len1 ? len1 : 0,  len4);
+	}
 
 	bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
 		   len1, err1, err2);
@@ -256,8 +274,8 @@ int bpf_prog5(struct sk_msg_md *msg)
 SEC("sk_msg3")
 int bpf_prog6(struct sk_msg_md *msg)
 {
-	int *bytes, *start, *end, *start_push, *end_push, *f;
-	int zero = 0, one = 1, two = 2, three = 3, key = 0;
+	int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0;
+	int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f;
 	__u64 flags = 0;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
@@ -277,6 +295,11 @@ int bpf_prog6(struct sk_msg_md *msg)
 	if (start_push && end_push)
 		bpf_msg_push_data(msg, *start_push, *end_push, 0);
 
+	start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
+	pop = bpf_map_lookup_elem(&sock_bytes, &five);
+	if (start_pop && pop)
+		bpf_msg_pop_data(msg, *start_pop, *pop, 0);
+
 	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
 	if (f && *f) {
 		key = 2;
@@ -292,8 +315,9 @@ int bpf_prog6(struct sk_msg_md *msg)
 SEC("sk_msg4")
 int bpf_prog7(struct sk_msg_md *msg)
 {
-	int zero = 0, one = 1, two = 2, three = 3, len1, len2 = 0, len3;
-	int *bytes, *start, *end, *start_push, *end_push, *f;
+	int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f;
+	int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
+	int len1, len2 = 0, len3, len4;
 	int err1 = 0, err2 = 0, key = 0;
 	__u64 flags = 0;
 
@@ -335,6 +359,22 @@ int bpf_prog7(struct sk_msg_md *msg)
 			   len2 ? len2 : len1, len3);
 	}
 
+	start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
+	pop = bpf_map_lookup_elem(&sock_bytes, &five);
+	if (start_pop && pop) {
+		int err;
+
+		bpf_printk("sk_msg4: pop(%i@%i)\n",
+			   start_pop, pop);
+		err = bpf_msg_pop_data(msg, *start_pop, *pop, 0);
+		if (err)
+			bpf_printk("sk_msg4: pop_data err %i\n", err);
+		len4 = (__u64)msg->data_end - (__u64)msg->data;
+		bpf_printk("sk_msg4: length pop_data %i->%i\n",
+			   len1 ? len1 : 0,  len4);
+	}
+
+
 	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
 	if (f && *f) {
 		key = 2;
@@ -389,8 +429,8 @@ int bpf_prog9(struct sk_msg_md *msg)
 SEC("sk_msg7")
 int bpf_prog10(struct sk_msg_md *msg)
 {
-	int *bytes, *start, *end, *start_push, *end_push;
-	int zero = 0, one = 1, two = 2, three = 3;
+	int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop;
+	int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
@@ -406,7 +446,11 @@ int bpf_prog10(struct sk_msg_md *msg)
 	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
 	if (start_push && end_push)
 		bpf_msg_push_data(msg, *start_push, *end_push, 0);
-
+	start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
+	pop = bpf_map_lookup_elem(&sock_bytes, &five);
+	if (start_pop && pop)
+		bpf_msg_pop_data(msg, *start_pop, *pop, 0);
+	bpf_printk("return sk drop\n");
 	return SK_DROP;
 }
 
-- 
cgit v1.2.3


From 295daee4ba108a025b9ac66231b0700e18ff5315 Mon Sep 17 00:00:00 2001
From: Naresh Kamboju <naresh.kamboju@linaro.org>
Date: Tue, 27 Nov 2018 20:54:44 +0530
Subject: selftests/bpf: add config fragment CONFIG_FTRACE_SYSCALLS

CONFIG_FTRACE_SYSCALLS=y is required for get_cgroup_id_user test case
this test reads a file from debug trace path
/sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id

Signed-off-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 7f90d3645af8..37f947ec44ed 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -22,3 +22,4 @@ CONFIG_NET_CLS_FLOWER=m
 CONFIG_LWTUNNEL=y
 CONFIG_BPF_STREAM_PARSER=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_FTRACE_SYSCALLS=y
-- 
cgit v1.2.3


From 1ad93ab10e24856ea1ae9f0fd3352992afa67e1b Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Wed, 28 Nov 2018 12:56:10 -0800
Subject: bpf: Fix various lib and testsuite build failures on 32-bit.

Cannot cast a u64 to a pointer on 32-bit without an intervening (long)
cast otherwise GCC warns.

Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/btf.c                      |  2 +-
 tools/testing/selftests/bpf/test_progs.c | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index eadcf8dfd295..c2d641f3e16e 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -466,7 +466,7 @@ int btf__get_from_id(__u32 id, struct btf **btf)
 		goto exit_free;
 	}
 
-	*btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL);
+	*btf = btf__new((__u8 *)(long)btf_info.btf, btf_info.btf_size, NULL);
 	if (IS_ERR(*btf)) {
 		err = PTR_ERR(*btf);
 		*btf = NULL;
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index c1e688f61061..1c57abbe0945 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -524,7 +524,7 @@ static void test_bpf_obj_id(void)
 			  load_time < now - 60 || load_time > now + 60 ||
 			  prog_infos[i].created_by_uid != my_uid ||
 			  prog_infos[i].nr_map_ids != 1 ||
-			  *(int *)prog_infos[i].map_ids != map_infos[i].id ||
+			  *(int *)(long)prog_infos[i].map_ids != map_infos[i].id ||
 			  strcmp((char *)prog_infos[i].name, expected_prog_name),
 			  "get-prog-info(fd)",
 			  "err %d errno %d i %d type %d(%d) info_len %u(%Zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
@@ -539,7 +539,7 @@ static void test_bpf_obj_id(void)
 			  load_time, now,
 			  prog_infos[i].created_by_uid, my_uid,
 			  prog_infos[i].nr_map_ids, 1,
-			  *(int *)prog_infos[i].map_ids, map_infos[i].id,
+			  *(int *)(long)prog_infos[i].map_ids, map_infos[i].id,
 			  prog_infos[i].name, expected_prog_name))
 			goto done;
 	}
@@ -585,7 +585,7 @@ static void test_bpf_obj_id(void)
 		bzero(&prog_info, sizeof(prog_info));
 		info_len = sizeof(prog_info);
 
-		saved_map_id = *(int *)(prog_infos[i].map_ids);
+		saved_map_id = *(int *)((long)prog_infos[i].map_ids);
 		prog_info.map_ids = prog_infos[i].map_ids;
 		prog_info.nr_map_ids = 2;
 		err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
@@ -593,12 +593,12 @@ static void test_bpf_obj_id(void)
 		prog_infos[i].xlated_prog_insns = 0;
 		CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
 		      memcmp(&prog_info, &prog_infos[i], info_len) ||
-		      *(int *)prog_info.map_ids != saved_map_id,
+		      *(int *)(long)prog_info.map_ids != saved_map_id,
 		      "get-prog-info(next_id->fd)",
 		      "err %d errno %d info_len %u(%Zu) memcmp %d map_id %u(%u)\n",
 		      err, errno, info_len, sizeof(struct bpf_prog_info),
 		      memcmp(&prog_info, &prog_infos[i], info_len),
-		      *(int *)prog_info.map_ids, saved_map_id);
+		      *(int *)(long)prog_info.map_ids, saved_map_id);
 		close(prog_fd);
 	}
 	CHECK(nr_id_found != nr_iters,
-- 
cgit v1.2.3


From 58d81d64e06ffaea6bddc85ae2b7295c371bcc55 Mon Sep 17 00:00:00 2001
From: Priit Laes <plaes@plaes.org>
Date: Mon, 19 Nov 2018 20:01:22 +0200
Subject: lib: cordic: Move cordic macros and defines to header file

Now that these macros are in header file, we can eventually
clean up the duplicate macros present in the drivers that
utilize the same cordic algorithm implementation.

Also add CORDIC_ prefix to nonprefixed macros.

Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Priit Laes <plaes@plaes.org>
Acked-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 include/linux/cordic.h |  9 +++++++++
 lib/cordic.c           | 23 +++++++----------------
 2 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/include/linux/cordic.h b/include/linux/cordic.h
index cf68ca4a508c..3d656f54d64f 100644
--- a/include/linux/cordic.h
+++ b/include/linux/cordic.h
@@ -18,6 +18,15 @@
 
 #include <linux/types.h>
 
+#define CORDIC_ANGLE_GEN	39797
+#define CORDIC_PRECISION_SHIFT	16
+#define CORDIC_NUM_ITER	(CORDIC_PRECISION_SHIFT + 2)
+
+#define CORDIC_FIXED(X)	((s32)((X) << CORDIC_PRECISION_SHIFT))
+#define CORDIC_FLOAT(X)	(((X) >= 0) \
+		? ((((X) >> (CORDIC_PRECISION_SHIFT - 1)) + 1) >> 1) \
+		: -((((-(X)) >> (CORDIC_PRECISION_SHIFT - 1)) + 1) >> 1))
+
 /**
  * struct cordic_iq - i/q coordinate.
  *
diff --git a/lib/cordic.c b/lib/cordic.c
index 6cf477839ebd..8ef27c12956f 100644
--- a/lib/cordic.c
+++ b/lib/cordic.c
@@ -16,15 +16,6 @@
 #include <linux/module.h>
 #include <linux/cordic.h>
 
-#define CORDIC_ANGLE_GEN	39797
-#define CORDIC_PRECISION_SHIFT	16
-#define	CORDIC_NUM_ITER		(CORDIC_PRECISION_SHIFT + 2)
-
-#define	FIXED(X)	((s32)((X) << CORDIC_PRECISION_SHIFT))
-#define	FLOAT(X)	(((X) >= 0) \
-		? ((((X) >> (CORDIC_PRECISION_SHIFT - 1)) + 1) >> 1) \
-		: -((((-(X)) >> (CORDIC_PRECISION_SHIFT - 1)) + 1) >> 1))
-
 static const s32 arctan_table[] = {
 	2949120,
 	1740967,
@@ -64,16 +55,16 @@ struct cordic_iq cordic_calc_iq(s32 theta)
 	coord.q = 0;
 	angle = 0;
 
-	theta = FIXED(theta);
+	theta = CORDIC_FIXED(theta);
 	signtheta = (theta < 0) ? -1 : 1;
-	theta = ((theta + FIXED(180) * signtheta) % FIXED(360)) -
-		FIXED(180) * signtheta;
+	theta = ((theta + CORDIC_FIXED(180) * signtheta) % CORDIC_FIXED(360)) -
+		CORDIC_FIXED(180) * signtheta;
 
-	if (FLOAT(theta) > 90) {
-		theta -= FIXED(180);
+	if (CORDIC_FLOAT(theta) > 90) {
+		theta -= CORDIC_FIXED(180);
 		signx = -1;
-	} else if (FLOAT(theta) < -90) {
-		theta += FIXED(180);
+	} else if (CORDIC_FLOAT(theta) < -90) {
+		theta += CORDIC_FIXED(180);
 		signx = -1;
 	}
 
-- 
cgit v1.2.3


From ea3edda9ddba634b9bcb8fcdcd95fe6b0a031a47 Mon Sep 17 00:00:00 2001
From: Priit Laes <plaes@plaes.org>
Date: Mon, 19 Nov 2018 20:01:23 +0200
Subject: brcmsmac: Use cordic-related macros from common cordic library

Current driver includes macro that is available from general cordic
library. Use that and drop unused duplicate and unneeded internal
definitions.

Signed-off-by: Priit Laes <plaes@plaes.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_int.h | 7 -------
 drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c | 4 ++--
 drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c   | 4 ++--
 3 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_int.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_int.h
index 4960f7d26804..e9e8337f386c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_int.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_int.h
@@ -220,13 +220,6 @@ enum phy_cal_mode {
 #define BB_MULT_MASK		0x0000ffff
 #define BB_MULT_VALID_MASK	0x80000000
 
-#define CORDIC_AG	39797
-#define	CORDIC_NI	18
-#define	FIXED(X)	((s32)((X) << 16))
-
-#define	FLOAT(X) \
-	(((X) >= 0) ? ((((X) >> 15) + 1) >> 1) : -((((-(X)) >> 15) + 1) >> 1))
-
 #define PHY_CHAIN_TX_DISABLE_TEMP	115
 #define PHY_HYSTERESIS_DELTATEMP	5
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
index 9fb0d9fbd939..e78a93a45741 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
@@ -3447,8 +3447,8 @@ wlc_lcnphy_start_tx_tone(struct brcms_phy *pi, s32 f_kHz, u16 max_val,
 
 		theta += rot;
 
-		i_samp = (u16) (FLOAT(tone_samp.i * max_val) & 0x3ff);
-		q_samp = (u16) (FLOAT(tone_samp.q * max_val) & 0x3ff);
+		i_samp = (u16)(CORDIC_FLOAT(tone_samp.i * max_val) & 0x3ff);
+		q_samp = (u16)(CORDIC_FLOAT(tone_samp.q * max_val) & 0x3ff);
 		data_buf[t] = (i_samp << 10) | q_samp;
 	}
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
index a57f2711f3c0..f4f5e9044152 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
@@ -23089,8 +23089,8 @@ wlc_phy_gen_load_samples_nphy(struct brcms_phy *pi, u32 f_kHz, u16 max_val,
 
 		theta += rot;
 
-		tone_buf[t].q = (s32) FLOAT(tone_buf[t].q * max_val);
-		tone_buf[t].i = (s32) FLOAT(tone_buf[t].i * max_val);
+		tone_buf[t].q = (s32)CORDIC_FLOAT(tone_buf[t].q * max_val);
+		tone_buf[t].i = (s32)CORDIC_FLOAT(tone_buf[t].i * max_val);
 	}
 
 	wlc_phy_loadsampletable_nphy(pi, tone_buf, num_samps);
-- 
cgit v1.2.3


From 8ea3819c0bbef57a51d8abe579e211033e861677 Mon Sep 17 00:00:00 2001
From: Larry Finger <Larry.Finger@lwfinger.net>
Date: Mon, 19 Nov 2018 20:01:24 +0200
Subject: b43: Fix error in cordic routine
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The cordic routine for calculating sines and cosines that was added in
commit 6f98e62a9f1b ("b43: update cordic code to match current specs")
contains an error whereby a quantity declared u32 can in fact go negative.

This problem was detected by Priit Laes who is switching b43 to use the
routine in the library functions of the kernel.

Fixes: 986504540306 ("b43: make cordic common (LP-PHY and N-PHY need it)")
Reported-by: Priit Laes <plaes@plaes.org>
Cc: Rafał Miłecki <zajec5@gmail.com>
Cc: Stable <stable@vger.kernel.org> # 2.6.34
Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Priit Laes <plaes@plaes.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/b43/phy_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/b43/phy_common.c b/drivers/net/wireless/broadcom/b43/phy_common.c
index 85f2ca989565..ef3ffa5ad466 100644
--- a/drivers/net/wireless/broadcom/b43/phy_common.c
+++ b/drivers/net/wireless/broadcom/b43/phy_common.c
@@ -616,7 +616,7 @@ struct b43_c32 b43_cordic(int theta)
 	u8 i;
 	s32 tmp;
 	s8 signx = 1;
-	u32 angle = 0;
+	s32 angle = 0;
 	struct b43_c32 ret = { .i = 39797, .q = 0, };
 
 	while (theta > (180 << 16))
-- 
cgit v1.2.3


From d5a433556d096d8e5b2526695aadbc7fd6ff48c9 Mon Sep 17 00:00:00 2001
From: Priit Laes <plaes@plaes.org>
Date: Mon, 19 Nov 2018 20:01:25 +0200
Subject: b43: Use cordic algorithm from kernel library

Kernel library has a common cordic algorithm which is identical
to internally implemented one, so use it and drop the duplicate
implementation.

Acked-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Priit Laes <plaes@plaes.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/b43/Kconfig      |  1 +
 drivers/net/wireless/broadcom/b43/phy_common.c | 47 --------------------------
 drivers/net/wireless/broadcom/b43/phy_common.h |  9 -----
 drivers/net/wireless/broadcom/b43/phy_lp.c     | 13 +++----
 drivers/net/wireless/broadcom/b43/phy_n.c      | 13 +++----
 5 files changed, 15 insertions(+), 68 deletions(-)

diff --git a/drivers/net/wireless/broadcom/b43/Kconfig b/drivers/net/wireless/broadcom/b43/Kconfig
index fba856032ca5..3e4145747b20 100644
--- a/drivers/net/wireless/broadcom/b43/Kconfig
+++ b/drivers/net/wireless/broadcom/b43/Kconfig
@@ -4,6 +4,7 @@ config B43
 	select BCMA if B43_BCMA
 	select SSB if B43_SSB
 	select FW_LOADER
+	select CORDIC
 	---help---
 	  b43 is a driver for the Broadcom 43xx series wireless devices.
 
diff --git a/drivers/net/wireless/broadcom/b43/phy_common.c b/drivers/net/wireless/broadcom/b43/phy_common.c
index ef3ffa5ad466..98c4fa5b919c 100644
--- a/drivers/net/wireless/broadcom/b43/phy_common.c
+++ b/drivers/net/wireless/broadcom/b43/phy_common.c
@@ -604,50 +604,3 @@ void b43_phy_force_clock(struct b43_wldev *dev, bool force)
 #endif
 	}
 }
-
-/* http://bcm-v4.sipsolutions.net/802.11/PHY/Cordic */
-struct b43_c32 b43_cordic(int theta)
-{
-	static const u32 arctg[] = {
-		2949120, 1740967, 919879, 466945, 234379, 117304,
-		  58666,   29335,  14668,   7334,   3667,   1833,
-		    917,     458,    229,    115,     57,     29,
-	};
-	u8 i;
-	s32 tmp;
-	s8 signx = 1;
-	s32 angle = 0;
-	struct b43_c32 ret = { .i = 39797, .q = 0, };
-
-	while (theta > (180 << 16))
-		theta -= (360 << 16);
-	while (theta < -(180 << 16))
-		theta += (360 << 16);
-
-	if (theta > (90 << 16)) {
-		theta -= (180 << 16);
-		signx = -1;
-	} else if (theta < -(90 << 16)) {
-		theta += (180 << 16);
-		signx = -1;
-	}
-
-	for (i = 0; i <= 17; i++) {
-		if (theta > angle) {
-			tmp = ret.i - (ret.q >> i);
-			ret.q += ret.i >> i;
-			ret.i = tmp;
-			angle += arctg[i];
-		} else {
-			tmp = ret.i + (ret.q >> i);
-			ret.q -= ret.i >> i;
-			ret.i = tmp;
-			angle -= arctg[i];
-		}
-	}
-
-	ret.i *= signx;
-	ret.q *= signx;
-
-	return ret;
-}
diff --git a/drivers/net/wireless/broadcom/b43/phy_common.h b/drivers/net/wireless/broadcom/b43/phy_common.h
index 57a1ad8afa08..4213caca9117 100644
--- a/drivers/net/wireless/broadcom/b43/phy_common.h
+++ b/drivers/net/wireless/broadcom/b43/phy_common.h
@@ -7,13 +7,6 @@
 
 struct b43_wldev;
 
-/* Complex number using 2 32-bit signed integers */
-struct b43_c32 { s32 i, q; };
-
-#define CORDIC_CONVERT(value)	(((value) >= 0) ? \
-				 ((((value) >> 15) + 1) >> 1) : \
-				 -((((-(value)) >> 15) + 1) >> 1))
-
 /* PHY register routing bits */
 #define B43_PHYROUTE			0x0C00 /* PHY register routing bits mask */
 #define  B43_PHYROUTE_BASE		0x0000 /* Base registers */
@@ -450,6 +443,4 @@ bool b43_is_40mhz(struct b43_wldev *dev);
 
 void b43_phy_force_clock(struct b43_wldev *dev, bool force);
 
-struct b43_c32 b43_cordic(int theta);
-
 #endif /* LINUX_B43_PHY_COMMON_H_ */
diff --git a/drivers/net/wireless/broadcom/b43/phy_lp.c b/drivers/net/wireless/broadcom/b43/phy_lp.c
index 6922cbb99a04..46408a560814 100644
--- a/drivers/net/wireless/broadcom/b43/phy_lp.c
+++ b/drivers/net/wireless/broadcom/b43/phy_lp.c
@@ -23,6 +23,7 @@
 
 */
 
+#include <linux/cordic.h>
 #include <linux/slab.h>
 
 #include "b43.h"
@@ -1780,9 +1781,9 @@ static void lpphy_start_tx_tone(struct b43_wldev *dev, s32 freq, u16 max)
 {
 	struct b43_phy_lp *lpphy = dev->phy.lp;
 	u16 buf[64];
-	int i, samples = 0, angle = 0;
+	int i, samples = 0, theta = 0;
 	int rotation = (((36 * freq) / 20) << 16) / 100;
-	struct b43_c32 sample;
+	struct cordic_iq sample;
 
 	lpphy->tx_tone_freq = freq;
 
@@ -1798,10 +1799,10 @@ static void lpphy_start_tx_tone(struct b43_wldev *dev, s32 freq, u16 max)
 	}
 
 	for (i = 0; i < samples; i++) {
-		sample = b43_cordic(angle);
-		angle += rotation;
-		buf[i] = CORDIC_CONVERT((sample.i * max) & 0xFF) << 8;
-		buf[i] |= CORDIC_CONVERT((sample.q * max) & 0xFF);
+		sample = cordic_calc_iq(CORDIC_FIXED(theta));
+		theta += rotation;
+		buf[i] = CORDIC_FLOAT((sample.i * max) & 0xFF) << 8;
+		buf[i] |= CORDIC_FLOAT((sample.q * max) & 0xFF);
 	}
 
 	b43_lptab_write_bulk(dev, B43_LPTAB16(5, 0), samples, buf);
diff --git a/drivers/net/wireless/broadcom/b43/phy_n.c b/drivers/net/wireless/broadcom/b43/phy_n.c
index 44ab080d6518..7d300362b933 100644
--- a/drivers/net/wireless/broadcom/b43/phy_n.c
+++ b/drivers/net/wireless/broadcom/b43/phy_n.c
@@ -23,6 +23,7 @@
 
 */
 
+#include <linux/cordic.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -1513,7 +1514,7 @@ static void b43_radio_init2055(struct b43_wldev *dev)
 
 /* http://bcm-v4.sipsolutions.net/802.11/PHY/N/LoadSampleTable */
 static int b43_nphy_load_samples(struct b43_wldev *dev,
-					struct b43_c32 *samples, u16 len) {
+					struct cordic_iq *samples, u16 len) {
 	struct b43_phy_n *nphy = dev->phy.n;
 	u16 i;
 	u32 *data;
@@ -1544,7 +1545,7 @@ static u16 b43_nphy_gen_load_samples(struct b43_wldev *dev, u32 freq, u16 max,
 {
 	int i;
 	u16 bw, len, rot, angle;
-	struct b43_c32 *samples;
+	struct cordic_iq *samples;
 
 	bw = b43_is_40mhz(dev) ? 40 : 20;
 	len = bw << 3;
@@ -1561,7 +1562,7 @@ static u16 b43_nphy_gen_load_samples(struct b43_wldev *dev, u32 freq, u16 max,
 		len = bw << 1;
 	}
 
-	samples = kcalloc(len, sizeof(struct b43_c32), GFP_KERNEL);
+	samples = kcalloc(len, sizeof(struct cordic_iq), GFP_KERNEL);
 	if (!samples) {
 		b43err(dev->wl, "allocation for samples generation failed\n");
 		return 0;
@@ -1570,10 +1571,10 @@ static u16 b43_nphy_gen_load_samples(struct b43_wldev *dev, u32 freq, u16 max,
 	angle = 0;
 
 	for (i = 0; i < len; i++) {
-		samples[i] = b43_cordic(angle);
+		samples[i] = cordic_calc_iq(CORDIC_FIXED(angle));
 		angle += rot;
-		samples[i].q = CORDIC_CONVERT(samples[i].q * max);
-		samples[i].i = CORDIC_CONVERT(samples[i].i * max);
+		samples[i].q = CORDIC_FLOAT(samples[i].q * max);
+		samples[i].i = CORDIC_FLOAT(samples[i].i * max);
 	}
 
 	i = b43_nphy_load_samples(dev, samples, len);
-- 
cgit v1.2.3


From 4282ff17e557d319e1b988fa4f582792cfaf6fff Mon Sep 17 00:00:00 2001
From: Dan Haab <riproute@gmail.com>
Date: Fri, 9 Nov 2018 09:38:55 -0700
Subject: brcmfmac: support STA info struct v7
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The newest firmwares provide STA info using v7 of the struct. As v7
isn't backward compatible, a union is needed.

Even though brcmfmac does not use any of the new info it's important to
provide the proper struct buffer. Without this change new firmwares will
fallback to the very limited v3 instead of something in between such as
v4.

Signed-off-by: Dan Haab <dan.haab@luxul.com>
Reviewed-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../broadcom/brcm80211/brcmfmac/fwil_types.h       | 40 ++++++++++++++++++----
 1 file changed, 33 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
index d5bb81e88762..39ac1bbb6cc0 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
@@ -176,6 +176,8 @@
 
 #define BRCMF_VHT_CAP_MCS_MAP_NSS_MAX	8
 
+#define BRCMF_HE_CAP_MCS_MAP_NSS_MAX	8
+
 /* MAX_CHUNK_LEN is the maximum length for data passing to firmware in each
  * ioctl. It is relatively small because firmware has small maximum size input
  * playload restriction for ioctls.
@@ -601,13 +603,37 @@ struct brcmf_sta_info_le {
 	__le32 rx_pkts_retried;        /* # rx with retry bit set */
 	__le32 tx_rate_fallback;       /* lowest fallback TX rate */
 
-	/* Fields valid for ver >= 5 */
-	struct {
-		__le32 count;					/* # rates in this set */
-		u8 rates[BRCMF_MAXRATES_IN_SET];		/* rates in 500kbps units w/hi bit set if basic */
-		u8 mcs[BRCMF_MCSSET_LEN];			/* supported mcs index bit map */
-		__le16 vht_mcs[BRCMF_VHT_CAP_MCS_MAP_NSS_MAX];	/* supported mcs index bit map per nss */
-	} rateset_adv;
+	union {
+		struct {
+			struct {
+				__le32 count;					/* # rates in this set */
+				u8 rates[BRCMF_MAXRATES_IN_SET];		/* rates in 500kbps units w/hi bit set if basic */
+				u8 mcs[BRCMF_MCSSET_LEN];			/* supported mcs index bit map */
+				__le16 vht_mcs[BRCMF_VHT_CAP_MCS_MAP_NSS_MAX];	/* supported mcs index bit map per nss */
+			} rateset_adv;
+		} v5;
+
+		struct {
+			__le32 rx_dur_total;	/* total user RX duration (estimated) */
+			__le16 chanspec;	/** chanspec this sta is on */
+			__le16 pad_1;
+			struct {
+				__le16 version;					/* version */
+				__le16 len;					/* length */
+				__le32 count;					/* # rates in this set */
+				u8 rates[BRCMF_MAXRATES_IN_SET];		/* rates in 500kbps units w/hi bit set if basic */
+				u8 mcs[BRCMF_MCSSET_LEN];			/* supported mcs index bit map */
+				__le16 vht_mcs[BRCMF_VHT_CAP_MCS_MAP_NSS_MAX];	/* supported mcs index bit map per nss */
+				__le16 he_mcs[BRCMF_HE_CAP_MCS_MAP_NSS_MAX];	/* supported he mcs index bit map per nss */
+			} rateset_adv;		/* rateset along with mcs index bitmap */
+			__le16 wpauth;		/* authentication type */
+			u8 algo;		/* crypto algorithm */
+			u8 pad_2;
+			__le32 tx_rspec;	/* Rate of last successful tx frame */
+			__le32 rx_rspec;	/* Rate of last successful rx frame */
+			__le32 wnm_cap;		/* wnm capabilities */
+		} v7;
+	};
 };
 
 struct brcmf_chanspec_list {
-- 
cgit v1.2.3


From 554da3868eb1d7174710c18b4ddd6ff01f6d612c Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 23 Nov 2018 10:11:48 +0100
Subject: brcmfmac: Call brcmf_dmi_probe before brcmf_of_probe

ARM systems with UEFI may have both devicetree (of) and DMI data in this
case we end up setting brcmf_mp_device.board_type twice.

In this case we should prefer the devicetree data, because:
1) The devicerree data is more reliable
2) Some ARM systems (e.g. the Raspberry Pi 3 models) support both UEFI and
   classic uboot booting, the devicetree data is always there, so using it
   makes sure we ask for the same nvram file independent of how we booted.

This commit moves the brcmf_dmi_probe call to before the brcmf_of_probe
call, so that the latter can override the value of the first if both are
set.

Fixes: bd1e82bb420a ("brcmfmac: Set board_type from DMI on x86 based ...")
Cc: Peter Robinson <pbrobinson@gmail.com>
Tested-and-reported-by: Peter Robinson <pbrobinson@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
index e738112ed87c..1f1e95a15a17 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
@@ -449,8 +449,8 @@ struct brcmf_mp_device *brcmf_get_module_param(struct device *dev,
 	}
 	if (!found) {
 		/* No platform data for this device, try OF and DMI data */
-		brcmf_of_probe(dev, bus_type, settings);
 		brcmf_dmi_probe(settings, chip, chiprev);
+		brcmf_of_probe(dev, bus_type, settings);
 	}
 	return settings;
 }
-- 
cgit v1.2.3


From b72c51a58e6d63ef673ac96b8ab5bc98799c5f7b Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Sat, 24 Nov 2018 17:57:05 -0500
Subject: brcmfmac: Fix out of bounds memory access during fw load

I ended up tracking down some rather nasty issues with f2fs (and other
filesystem modules) constantly crashing on my kernel down to a
combination of out of bounds memory accesses, one of which was coming
from brcmfmac during module load:

[   30.891382] brcmfmac: brcmf_fw_alloc_request: using brcm/brcmfmac4356-sdio for chip BCM4356/2
[   30.894437] ==================================================================
[   30.901581] BUG: KASAN: global-out-of-bounds in brcmf_fw_alloc_request+0x42c/0x480 [brcmfmac]
[   30.909935] Read of size 1 at addr ffff2000024865df by task kworker/6:2/387
[   30.916805]
[   30.918261] CPU: 6 PID: 387 Comm: kworker/6:2 Tainted: G           O      4.20.0-rc3Lyude-Test+ #19
[   30.927251] Hardware name: amlogic khadas-vim2/khadas-vim2, BIOS 2018.07-rc2-armbian 09/11/2018
[   30.935964] Workqueue: events brcmf_driver_register [brcmfmac]
[   30.941641] Call trace:
[   30.944058]  dump_backtrace+0x0/0x3e8
[   30.947676]  show_stack+0x14/0x20
[   30.950968]  dump_stack+0x130/0x1c4
[   30.954406]  print_address_description+0x60/0x25c
[   30.959066]  kasan_report+0x1b4/0x368
[   30.962683]  __asan_report_load1_noabort+0x18/0x20
[   30.967547]  brcmf_fw_alloc_request+0x42c/0x480 [brcmfmac]
[   30.967639]  brcmf_sdio_probe+0x163c/0x2050 [brcmfmac]
[   30.978035]  brcmf_ops_sdio_probe+0x598/0xa08 [brcmfmac]
[   30.983254]  sdio_bus_probe+0x190/0x398
[   30.983270]  really_probe+0x2a0/0xa70
[   30.983296]  driver_probe_device+0x1b4/0x2d8
[   30.994901]  __driver_attach+0x200/0x280
[   30.994914]  bus_for_each_dev+0x10c/0x1a8
[   30.994925]  driver_attach+0x38/0x50
[   30.994935]  bus_add_driver+0x330/0x608
[   30.994953]  driver_register+0x140/0x388
[   31.013965]  sdio_register_driver+0x74/0xa0
[   31.014076]  brcmf_sdio_register+0x14/0x60 [brcmfmac]
[   31.023177]  brcmf_driver_register+0xc/0x18 [brcmfmac]
[   31.023209]  process_one_work+0x654/0x1080
[   31.032266]  worker_thread+0x4f0/0x1308
[   31.032286]  kthread+0x2a8/0x320
[   31.039254]  ret_from_fork+0x10/0x1c
[   31.039269]
[   31.044226] The buggy address belongs to the variable:
[   31.044351]  brcmf_firmware_path+0x11f/0xfffffffffffd3b40 [brcmfmac]
[   31.055601]
[   31.057031] Memory state around the buggy address:
[   31.061800]  ffff200002486480: 04 fa fa fa fa fa fa fa 00 00 00 00 00 00 00 00
[   31.068983]  ffff200002486500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[   31.068993] >ffff200002486580: 00 00 00 00 00 00 00 00 fa fa fa fa 00 00 00 00
[   31.068999]                                                     ^
[   31.069017]  ffff200002486600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[   31.096521]  ffff200002486680: 00 00 00 00 00 00 00 00 00 00 00 00 fa fa fa fa
[   31.096528] ==================================================================
[   31.096533] Disabling lock debugging due to kernel taint

It appears that when trying to determine the length of the string in the
alternate firmware path, we make the mistake of not handling the case
where the firmware path is empty correctly. Since strlen(mp_path) can
return 0, we'll end up accessing mp_path[-1] when the firmware_path
isn't provided through the module arguments.

So, fix this by just setting the end char to '\0' by default, and only
changing it if we have a non-zero length. Additionally, use strnlen()
with BRCMF_FW_ALTPATH_LEN instead of strlen() just to be extra safe.

Fixes: 2baa3aaee27f ("brcmfmac: introduce brcmf_fw_alloc_request() function")
Cc: Hante Meuleman <hante.meuleman@broadcom.com>
Cc: Pieter-Paul Giesberts <pieter-paul.giesberts@broadcom.com>
Cc: Franky Lin <franky.lin@broadcom.com>
Cc: Arend van Spriel <arend.vanspriel@broadcom.com>
Cc: Kalle Valo <kvalo@codeaurora.org>
Cc: Arend Van Spriel <arend.vanspriel@broadcom.com>
Cc: Himanshu Jha <himanshujha199640@gmail.com>
Cc: Dan Haab <dhaab@luxul.com>
Cc: Jia-Shyr Chuang <saint.chuang@cypress.com>
Cc: Ian Molton <ian@mnementh.co.uk>
Cc: <stable@vger.kernel.org> # v4.17+
Signed-off-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
index 72d8c0c3c3a1..dad3c1c79038 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
@@ -708,8 +708,9 @@ brcmf_fw_alloc_request(u32 chip, u32 chiprev,
 	struct brcmf_fw_request *fwreq;
 	char chipname[12];
 	const char *mp_path;
+	size_t mp_path_len;
 	u32 i, j;
-	char end;
+	char end = '\0';
 	size_t reqsz;
 
 	for (i = 0; i < table_size; i++) {
@@ -734,7 +735,10 @@ brcmf_fw_alloc_request(u32 chip, u32 chiprev,
 		   mapping_table[i].fw_base, chipname);
 
 	mp_path = brcmf_mp_global.firmware_path;
-	end = mp_path[strlen(mp_path) - 1];
+	mp_path_len = strnlen(mp_path, BRCMF_FW_ALTPATH_LEN);
+	if (mp_path_len)
+		end = mp_path[mp_path_len - 1];
+
 	fwreq->n_items = n_fwnames;
 
 	for (j = 0; j < n_fwnames; j++) {
-- 
cgit v1.2.3


From 0ba78b4a4989de294dd0f17e243f1f91f07d97b3 Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Thu, 29 Nov 2018 17:06:31 +0900
Subject: net: ethernet: ave: Add suspend/resume support

This patch introduces suspend and resume functions to ave driver.

Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/sni_ave.c | 44 ++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 9e7391faa1dc..0933c13cc82a 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -1734,6 +1734,49 @@ static int ave_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int ave_suspend(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct ave_private *priv = netdev_priv(ndev);
+	int ret = 0;
+
+	if (netif_running(ndev)) {
+		ret = ave_stop(ndev);
+		netif_device_detach(ndev);
+	}
+
+	return ret;
+}
+
+static int ave_resume(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct ave_private *priv = netdev_priv(ndev);
+	int ret = 0;
+
+	ave_global_reset(ndev);
+
+	if (ndev->phydev) {
+		ret = phy_resume(ndev->phydev);
+		if (ret)
+			return ret;
+	}
+
+	if (netif_running(ndev)) {
+		ret = ave_open(ndev);
+		netif_device_attach(ndev);
+	}
+
+	return ret;
+}
+
+static SIMPLE_DEV_PM_OPS(ave_pm_ops, ave_suspend, ave_resume);
+#define AVE_PM_OPS	(&ave_pm_ops)
+#else
+#define AVE_PM_OPS	NULL
+#endif
+
 static int ave_pro4_get_pinmode(struct ave_private *priv,
 				phy_interface_t phy_mode, u32 arg)
 {
@@ -1908,6 +1951,7 @@ static struct platform_driver ave_driver = {
 	.remove = ave_remove,
 	.driver	= {
 		.name = "ave",
+		.pm   = AVE_PM_OPS,
 		.of_match_table	= of_ave_match,
 	},
 };
-- 
cgit v1.2.3


From 7200f2e3c9e267d29e2bfa075794339032e0b98e Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Thu, 29 Nov 2018 17:06:32 +0900
Subject: net: ethernet: ave: Set initial wol state to disabled

If wol state of phy hardware is enabled after reset, phy_ethtool_get_wol()
returns that wol.wolopts is true.

However, since net_device.wol_enabled is zero and this doesn't apply wol
state until calling ethtool_set_wol(), so mdio_bus_phy_may_suspend()
returns true, that is, it's in a state where phy can suspend even though
wol state is enabled.

In this inconsistency, phy_suspend() returns -EBUSY, and at last,
suspend sequence fails with the following message:

    dpm_run_callback(): mdio_bus_phy_suspend+0x0/0x58 returns -16
    PM: Device 65000000.ethernet-ffffffff:01 failed to suspend: error -16
    PM: Some devices failed to suspend, or early wake event detected

In order to fix the above issue, this patch forces to set initial wol state
to disabled as default.

Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/sni_ave.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 0933c13cc82a..96b80309e36d 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -1208,9 +1208,13 @@ static int ave_init(struct net_device *ndev)
 
 	priv->phydev = phydev;
 
-	phy_ethtool_get_wol(phydev, &wol);
+	ave_ethtool_get_wol(ndev, &wol);
 	device_set_wakeup_capable(&ndev->dev, !!wol.supported);
 
+	/* set wol initial state disabled */
+	wol.wolopts = 0;
+	ave_ethtool_set_wol(ndev, &wol);
+
 	if (!phy_interface_is_rgmii(phydev))
 		phy_set_max_speed(phydev, SPEED_100);
 
-- 
cgit v1.2.3


From 8d1283b1d6afe9c67ad8d8053f6202ef6fcb038a Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Thu, 29 Nov 2018 17:06:33 +0900
Subject: net: ethernet: ave: Preserve wol state in suspend/resume sequence

Since the wol state forces to be initialized after reset, the state should
be preserved in suspend/resume sequence.

Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/sni_ave.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 96b80309e36d..1f9ef68d91ee 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -261,6 +261,7 @@ struct ave_private {
 	struct regmap		*regmap;
 	unsigned int		pinmode_mask;
 	unsigned int		pinmode_val;
+	u32			wolopts;
 
 	/* stats */
 	struct ave_stats	stats_rx;
@@ -1741,6 +1742,7 @@ static int ave_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM_SLEEP
 static int ave_suspend(struct device *dev)
 {
+	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct ave_private *priv = netdev_priv(ndev);
 	int ret = 0;
@@ -1750,17 +1752,25 @@ static int ave_suspend(struct device *dev)
 		netif_device_detach(ndev);
 	}
 
+	ave_ethtool_get_wol(ndev, &wol);
+	priv->wolopts = wol.wolopts;
+
 	return ret;
 }
 
 static int ave_resume(struct device *dev)
 {
+	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct ave_private *priv = netdev_priv(ndev);
 	int ret = 0;
 
 	ave_global_reset(ndev);
 
+	ave_ethtool_get_wol(ndev, &wol);
+	wol.wolopts = priv->wolopts;
+	ave_ethtool_set_wol(ndev, &wol);
+
 	if (ndev->phydev) {
 		ret = phy_resume(ndev->phydev);
 		if (ret)
-- 
cgit v1.2.3


From c1cb11bcbd09f5f027cbc7fadddab169714948df Mon Sep 17 00:00:00 2001
From: Ioana Ciocoi Radulescu <ruxandra.radulescu@nxp.com>
Date: Thu, 29 Nov 2018 08:43:40 +0000
Subject: dpaa2-eth: Add "fall through" comments

Add comments in the switch statement for XDP action to indicate
fallthrough is intended.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index be841718eb49..1ca9a18139ec 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -322,8 +322,10 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(xdp_act);
+		/* fall through */
 	case XDP_ABORTED:
 		trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act);
+		/* fall through */
 	case XDP_DROP:
 		xdp_release_buf(priv, ch, addr);
 		ch->stats.xdp_drop++;
-- 
cgit v1.2.3


From dcc6abae0f473a67543ce651fbfb6b15452876f6 Mon Sep 17 00:00:00 2001
From: Michael Shteinbok <michael.shteinbok@cavium.com>
Date: Thu, 29 Nov 2018 10:50:19 +0200
Subject: qede - Add a statistic for a case where driver drops tx packet due to
 memory allocation failure.

skb_linearization can fail due to memory allocation failure.
In such a case, the driver will drop the packet. In such a case
The driver used to print an error message.
This patch replaces this error message by a dedicated statistic.

Signed-off-by: Michael Shteinbok <michael.shteinbok@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede.h         | 1 +
 drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 1 +
 drivers/net/ethernet/qlogic/qede/qede_fp.c      | 4 ++--
 3 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 8c0fe59eaad5..613249d1e967 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -381,6 +381,7 @@ struct qede_tx_queue {
 
 	u64 xmit_pkts;
 	u64 stopped_cnt;
+	u64 tx_mem_alloc_err;
 
 	__le16 *hw_cons_ptr;
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 8cbbd628fd73..16331c6c6fa7 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -73,6 +73,7 @@ static const struct {
 } qede_tqstats_arr[] = {
 	QEDE_TQSTAT(xmit_pkts),
 	QEDE_TQSTAT(stopped_cnt),
+	QEDE_TQSTAT(tx_mem_alloc_err),
 };
 
 #define QEDE_STAT_OFFSET(stat_name, type, base) \
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 1a78027de071..bdf816fe5a16 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1466,8 +1466,8 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 #if ((MAX_SKB_FRAGS + 2) > ETH_TX_MAX_BDS_PER_NON_LSO_PACKET)
 	if (qede_pkt_req_lin(skb, xmit_type)) {
 		if (skb_linearize(skb)) {
-			DP_NOTICE(edev,
-				  "SKB linearization failed - silently dropping this SKB\n");
+			txq->tx_mem_alloc_err++;
+
 			dev_kfree_skb_any(skb);
 			return NETDEV_TX_OK;
 		}
-- 
cgit v1.2.3


From 19bf62613a800ef4ffa26cbae6b723d9f46740ed Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 29 Nov 2018 07:56:20 -0800
Subject: tcp: remove loop to compute wscale

We can remove the loop and conditional branches
and compute wscale efficiently thanks to ilog2()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c5dc4c4fdadd..e4c1e51b18c1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -233,16 +233,14 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	if (init_rcv_wnd)
 		*rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
 
-	(*rcv_wscale) = 0;
+	*rcv_wscale = 0;
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
 		space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
 		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
-		while (space > U16_MAX && (*rcv_wscale) < TCP_MAX_WSCALE) {
-			space >>= 1;
-			(*rcv_wscale)++;
-		}
+		*rcv_wscale = clamp_t(int, ilog2(space) - 15,
+				      0, TCP_MAX_WSCALE);
 	}
 	/* Set the clamp no higher than max representable value */
 	(*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp);
-- 
cgit v1.2.3


From 1464193107da8041e05341388964733bbba3be27 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 26 Nov 2018 09:31:26 -0800
Subject: net: explain __skb_checksum_complete() with comments

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c    |  1 +
 net/core/skbuff.c | 18 +++++++++++++++++-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index f69b2fcdee40..abe50c424b29 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5791,6 +5791,7 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb)
 
 	/* NAPI_GRO_CB(skb)->csum holds pseudo checksum */
 	sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum));
+	/* See comments in __skb_checksum_complete(). */
 	if (likely(!sum)) {
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
 		    !skb->csum_complete_sw)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 02cd7ae3d0fb..3c814565ed7c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2635,6 +2635,7 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 	__sum16 sum;
 
 	sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
+	/* See comments in __skb_checksum_complete(). */
 	if (likely(!sum)) {
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
 		    !skb->csum_complete_sw)
@@ -2646,6 +2647,15 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 }
 EXPORT_SYMBOL(__skb_checksum_complete_head);
 
+/* This function assumes skb->csum already holds pseudo header's checksum,
+ * which has been changed from the hardware checksum, for example, by
+ * __skb_checksum_validate_complete(). And, the original skb->csum must
+ * have been validated unsuccessfully for CHECKSUM_COMPLETE case.
+ *
+ * It returns non-zero if the recomputed checksum is still invalid, otherwise
+ * zero. The new checksum is stored back into skb->csum unless the skb is
+ * shared.
+ */
 __sum16 __skb_checksum_complete(struct sk_buff *skb)
 {
 	__wsum csum;
@@ -2653,8 +2663,14 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
 
 	csum = skb_checksum(skb, 0, skb->len, 0);
 
-	/* skb->csum holds pseudo checksum */
 	sum = csum_fold(csum_add(skb->csum, csum));
+	/* This check is inverted, because we already knew the hardware
+	 * checksum is invalid before calling this function. So, if the
+	 * re-computed checksum is valid instead, then we have a mismatch
+	 * between the original skb->csum and skb_checksum(). This means either
+	 * the original hardware checksum is incorrect or we screw up skb->csum
+	 * when moving skb->data around.
+	 */
 	if (likely(!sum)) {
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
 		    !skb->csum_complete_sw)
-- 
cgit v1.2.3


From 3d58c9c9f735c8c9960e8bf8dd796dbfe2585a6a Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 29 Nov 2018 16:01:34 -0800
Subject: net: Don't default Aquantia USB driver to 'y'

Reported-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index e5fb8ef2d815..860352a525fb 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -617,7 +617,6 @@ config USB_NET_AQC111
 	tristate "Aquantia AQtion USB to 5/2.5GbE Controllers support"
 	depends on USB_USBNET
 	select CRC32
-	default y
 	help
 	  This option adds support for Aquantia AQtion USB
 	  Ethernet adapters based on AQC111U/AQC112 chips.
-- 
cgit v1.2.3


From 20902be46c4da59b1891d238801146134e0e06b5 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:38:56 -0800
Subject: net/mlx5: Driver events notifier API

Use atomic notifier chain to fire events to mlx5 core driver
consumers (mlx5e/mlx5_ib) and provide mlx5 register/unregister notifier
API.

This API will replace the current mlx5_interface->event callback and all
the logic around it, especially the delayed events logic introduced by
commit 97834eba7c19 ("net/mlx5: Delay events till ib registration ends")

Which is not needed anymore with this new API where the mlx5 interface
can dynamically register/unregister its notifier.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c   | 25 +++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h |  1 +
 include/linux/mlx5/driver.h                        |  4 ++++
 3 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 3ad004af37d7..560cc14c55f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -35,7 +35,8 @@ static struct mlx5_nb events_nbs_ref[] = {
 struct mlx5_events {
 	struct mlx5_core_dev *dev;
 	struct mlx5_event_nb  notifiers[ARRAY_SIZE(events_nbs_ref)];
-
+	/* driver notifier chain */
+	struct atomic_notifier_head nh;
 	/* port module events stats */
 	struct mlx5_pme_stats pme_stats;
 };
@@ -300,6 +301,7 @@ int mlx5_events_init(struct mlx5_core_dev *dev)
 	if (!events)
 		return -ENOMEM;
 
+	ATOMIC_INIT_NOTIFIER_HEAD(&events->nh);
 	events->dev = dev;
 	dev->priv.events = events;
 	return 0;
@@ -330,3 +332,24 @@ void mlx5_events_stop(struct mlx5_core_dev *dev)
 	for (i = ARRAY_SIZE(events_nbs_ref) - 1; i >= 0 ; i--)
 		mlx5_eq_notifier_unregister(dev, &events->notifiers[i].nb);
 }
+
+int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb)
+{
+	struct mlx5_events *events = dev->priv.events;
+
+	return atomic_notifier_chain_register(&events->nh, nb);
+}
+EXPORT_SYMBOL(mlx5_notifier_register);
+
+int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb)
+{
+	struct mlx5_events *events = dev->priv.events;
+
+	return atomic_notifier_chain_unregister(&events->nh, nb);
+}
+EXPORT_SYMBOL(mlx5_notifier_unregister);
+
+int mlx5_notifier_call_chain(struct mlx5_events *events, unsigned int event, void *data)
+{
+	return atomic_notifier_call_chain(&events->nh, event, data);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 23317e328b0b..4d78a459676e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -73,5 +73,6 @@ struct mlx5_pme_stats {
 };
 
 void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats);
+int mlx5_notifier_call_chain(struct mlx5_events *events, unsigned int event, void *data);
 
 #endif
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index ba64ecf72478..b96929d0cc9c 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -46,6 +46,7 @@
 #include <linux/mempool.h>
 #include <linux/interrupt.h>
 #include <linux/idr.h>
+#include <linux/notifier.h>
 
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/doorbell.h>
@@ -1062,6 +1063,9 @@ struct mlx5_interface {
 void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol);
 int mlx5_register_interface(struct mlx5_interface *intf);
 void mlx5_unregister_interface(struct mlx5_interface *intf);
+int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb);
+int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb);
+
 int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id);
 
 int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev);
-- 
cgit v1.2.3


From 7a1795553074f90d59b3250b4a9b8aaf6ca2831e Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:38:57 -0800
Subject: net/mlx5: Allow port change event to be forwarded to driver notifiers
 chain

The idea is to allow mlx5 core interfaces (mlx5e/mlx5_ib) to be able to
receive some allowed FW events as is via the new notifier API.

In this patch we allow forwarding port change event to mlx5 core interfaces
(mlx5e/mlx5_ib) as it was received from FW.
Once mlx5e and mlx5_ib start using this event we can safely remove the
redundant software version of it and its translation logic.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 560cc14c55f7..adab66eb726c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -24,12 +24,18 @@ static int general_event(struct notifier_block *, unsigned long, void *);
 static int temp_warn(struct notifier_block *, unsigned long, void *);
 static int port_module(struct notifier_block *, unsigned long, void *);
 
+/* handler which forwards the event to events->nh, driver notifiers */
+static int forward_event(struct notifier_block *, unsigned long, void *);
+
 static struct mlx5_nb events_nbs_ref[] = {
 	{.nb.notifier_call = any_notifier,  .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY },
 	{.nb.notifier_call = port_change,   .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
 	{.nb.notifier_call = general_event, .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT },
 	{.nb.notifier_call = temp_warn,     .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT },
 	{.nb.notifier_call = port_module,   .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT },
+
+	/* Events to be forwarded (as is) to mlx5 core interfaces (mlx5e/mlx5_ib) */
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
 };
 
 struct mlx5_events {
@@ -294,6 +300,16 @@ void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats)
 	*stats = dev->priv.events->pme_stats;
 }
 
+/* forward event as is to registered interfaces (mlx5e/mlx5_ib) */
+static int forward_event(struct notifier_block *nb, unsigned long event, void *data)
+{
+	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+	struct mlx5_events   *events   = event_nb->ctx;
+
+	atomic_notifier_call_chain(&events->nh, event, data);
+	return NOTIFY_OK;
+}
+
 int mlx5_events_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_events *events = kzalloc(sizeof(*events), GFP_KERNEL);
-- 
cgit v1.2.3


From 7cffaddd39b438fab49863ea4602d6294a9d657f Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:38:58 -0800
Subject: net/mlx5e: Use the new mlx5 core notifier API

Remove the deprecated mlx5_interface->event mlx5e callback and use new
mlx5 notifier API to subscribe for mlx5 events, handle port change event
as received from FW rather than handling the mlx5 core processed port
change software version event.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 27 ++++++++++++-----------
 2 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index aea74856c702..13d8a74d3db5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -631,7 +631,6 @@ struct mlx5e_channel_stats {
 } ____cacheline_aligned_in_smp;
 
 enum {
-	MLX5E_STATE_ASYNC_EVENTS_ENABLED,
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
 };
@@ -690,6 +689,8 @@ struct mlx5e_priv {
 	struct hwtstamp_config     tstamp;
 	u16                        q_counter;
 	u16                        drop_rq_q_counter;
+	struct notifier_block      events_nb;
+
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	struct mlx5e_dcbx          dcbx;
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0d495a6b3949..56bc41b1c31f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -294,33 +294,35 @@ void mlx5e_queue_update_stats(struct mlx5e_priv *priv)
 	queue_work(priv->wq, &priv->update_stats_work);
 }
 
-static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
-			      enum mlx5_dev_event event, unsigned long param)
+static int async_event(struct notifier_block *nb, unsigned long event, void *data)
 {
-	struct mlx5e_priv *priv = vpriv;
+	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
+	struct mlx5_eqe   *eqe = data;
 
-	if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state))
-		return;
+	if (event != MLX5_EVENT_TYPE_PORT_CHANGE)
+		return NOTIFY_DONE;
 
-	switch (event) {
-	case MLX5_DEV_EVENT_PORT_UP:
-	case MLX5_DEV_EVENT_PORT_DOWN:
+	switch (eqe->sub_type) {
+	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
 		queue_work(priv->wq, &priv->update_carrier_work);
 		break;
 	default:
-		break;
+		return NOTIFY_DONE;
 	}
+
+	return NOTIFY_OK;
 }
 
 static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
 {
-	set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
+	priv->events_nb.notifier_call = async_event;
+	mlx5_notifier_register(priv->mdev, &priv->events_nb);
 }
 
 static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
 {
-	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
-	mlx5_eq_synchronize_async_irq(priv->mdev);
+	mlx5_notifier_unregister(priv->mdev, &priv->events_nb);
 }
 
 static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
@@ -5170,7 +5172,6 @@ static struct mlx5_interface mlx5e_interface = {
 	.remove    = mlx5e_remove,
 	.attach    = mlx5e_attach,
 	.detach    = mlx5e_detach,
-	.event     = mlx5e_async_event,
 	.protocol  = MLX5_INTERFACE_PROTOCOL_ETH,
 	.get_dev   = mlx5e_get_netdev,
 };
-- 
cgit v1.2.3


From 58d180b34e98698fec178a469b700f1bb5a32c1f Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:38:59 -0800
Subject: net/mlx5: Forward all mlx5 events to mlx5 notifiers chain

This to allow seamless migration to the new notifier chain API, and to
eventually deprecate interfaces dev->event callback.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c | 3 +++
 include/linux/mlx5/driver.h                   | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 7eedbea38a78..d63ba8813829 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -32,6 +32,7 @@
 
 #include <linux/mlx5/driver.h>
 #include "mlx5_core.h"
+#include "lib/mlx5.h"
 
 static LIST_HEAD(intf_list);
 static LIST_HEAD(mlx5_dev_list);
@@ -425,6 +426,8 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 			dev_ctx->intf->event(dev, dev_ctx->context, event, param);
 
 	spin_unlock_irqrestore(&priv->ctx_lock, flags);
+
+	mlx5_notifier_call_chain(dev->priv.events, event, (void *)param);
 }
 
 void mlx5_dev_list_lock(void)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index b96929d0cc9c..14ca74707275 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -195,7 +195,7 @@ struct mlx5_rsc_debug {
 };
 
 enum mlx5_dev_event {
-	MLX5_DEV_EVENT_SYS_ERROR,
+	MLX5_DEV_EVENT_SYS_ERROR = 128, /* 0 - 127 are FW events */
 	MLX5_DEV_EVENT_PORT_UP,
 	MLX5_DEV_EVENT_PORT_DOWN,
 	MLX5_DEV_EVENT_PORT_INITIALIZED,
-- 
cgit v1.2.3


From df097a278c7592873d88571a8c78f987f6ae511b Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:39:00 -0800
Subject: IB/mlx5: Use the new mlx5 core notifier API

Remove the deprecated mlx5_interface->event mlx5_ib callback and use new
mlx5 notifier API to subscribe for mlx5 events.

For native mlx5_ib devices profiles pf_profile/nic_rep_profile register
the notifier callback mlx5_ib_handle_event which treats the notifier
context as mlx5_ib_dev.

For vport repesentors, don't register any notifier, same as before, they
didn't receive any mlx5 events.

For slave port (mlx5_ib_multiport_info) register a different notifier
callback mlx5_ib_event_slave_port, which knows that the event is coming
for mlx5_ib_multiport_info and prepares the event job accordingly.
Before this on the event handler work we had to ask mlx5_core if this is
a slave port mlx5_core_is_mp_slave(work->dev), now it is not needed
anymore.
mlx5_ib_multiport_info notifier registration is done on
mlx5_ib_bind_slave_port and de-registration is done on
mlx5_ib_unbind_slave_port.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c    | 77 +++++++++++++++++++++++++++++-------
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  3 ++
 2 files changed, 66 insertions(+), 14 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index fcf4a0328a90..549c766cf309 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -82,10 +82,13 @@ static char mlx5_version[] =
 
 struct mlx5_ib_event_work {
 	struct work_struct	work;
-	struct mlx5_core_dev	*dev;
-	void			*context;
+	union {
+		struct mlx5_ib_dev	      *dev;
+		struct mlx5_ib_multiport_info *mpi;
+	};
+	bool			is_slave;
 	enum mlx5_dev_event	event;
-	unsigned long		param;
+	void			*param;
 };
 
 enum {
@@ -4240,14 +4243,14 @@ static void mlx5_ib_handle_event(struct work_struct *_work)
 	struct mlx5_ib_dev *ibdev;
 	struct ib_event ibev;
 	bool fatal = false;
-	u8 port = (u8)work->param;
+	u8 port = (u8)(unsigned long)work->param;
 
-	if (mlx5_core_is_mp_slave(work->dev)) {
-		ibdev = mlx5_ib_get_ibdev_from_mpi(work->context);
+	if (work->is_slave) {
+		ibdev = mlx5_ib_get_ibdev_from_mpi(work->mpi);
 		if (!ibdev)
 			goto out;
 	} else {
-		ibdev = work->context;
+		ibdev = work->dev;
 	}
 
 	switch (work->event) {
@@ -4256,7 +4259,6 @@ static void mlx5_ib_handle_event(struct work_struct *_work)
 		mlx5_ib_handle_internal_error(ibdev);
 		fatal = true;
 		break;
-
 	case MLX5_DEV_EVENT_PORT_UP:
 	case MLX5_DEV_EVENT_PORT_DOWN:
 	case MLX5_DEV_EVENT_PORT_INITIALIZED:
@@ -4311,22 +4313,43 @@ out:
 	kfree(work);
 }
 
-static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
-			  enum mlx5_dev_event event, unsigned long param)
+static int mlx5_ib_event(struct notifier_block *nb,
+			 unsigned long event, void *param)
 {
 	struct mlx5_ib_event_work *work;
 
 	work = kmalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work)
-		return;
+		return NOTIFY_DONE;
 
 	INIT_WORK(&work->work, mlx5_ib_handle_event);
-	work->dev = dev;
+	work->dev = container_of(nb, struct mlx5_ib_dev, mdev_events);
+	work->is_slave = false;
 	work->param = param;
-	work->context = context;
 	work->event = event;
 
 	queue_work(mlx5_ib_event_wq, &work->work);
+
+	return NOTIFY_OK;
+}
+
+static int mlx5_ib_event_slave_port(struct notifier_block *nb,
+				    unsigned long event, void *param)
+{
+	struct mlx5_ib_event_work *work;
+
+	work = kmalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return NOTIFY_DONE;
+
+	INIT_WORK(&work->work, mlx5_ib_handle_event);
+	work->mpi = container_of(nb, struct mlx5_ib_multiport_info, mdev_events);
+	work->is_slave = true;
+	work->param = param;
+	work->event = event;
+	queue_work(mlx5_ib_event_wq, &work->work);
+
+	return NOTIFY_OK;
 }
 
 static int set_has_smi_cap(struct mlx5_ib_dev *dev)
@@ -5357,6 +5380,11 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
 		spin_unlock(&port->mp.mpi_lock);
 		return;
 	}
+
+	if (mpi->mdev_events.notifier_call)
+		mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events);
+	mpi->mdev_events.notifier_call = NULL;
+
 	mpi->ibdev = NULL;
 
 	spin_unlock(&port->mp.mpi_lock);
@@ -5412,6 +5440,7 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev,
 
 	ibdev->port[port_num].mp.mpi = mpi;
 	mpi->ibdev = ibdev;
+	mpi->mdev_events.notifier_call = NULL;
 	spin_unlock(&ibdev->port[port_num].mp.mpi_lock);
 
 	err = mlx5_nic_vport_affiliate_multiport(ibdev->mdev, mpi->mdev);
@@ -5429,6 +5458,9 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev,
 		goto unbind;
 	}
 
+	mpi->mdev_events.notifier_call = mlx5_ib_event_slave_port;
+	mlx5_notifier_register(mpi->mdev, &mpi->mdev_events);
+
 	err = mlx5_ib_init_cong_debugfs(ibdev, port_num);
 	if (err)
 		goto unbind;
@@ -6163,6 +6195,18 @@ static void mlx5_ib_stage_rep_reg_cleanup(struct mlx5_ib_dev *dev)
 	mlx5_ib_unregister_vport_reps(dev);
 }
 
+static int mlx5_ib_stage_dev_notifier_init(struct mlx5_ib_dev *dev)
+{
+	dev->mdev_events.notifier_call = mlx5_ib_event;
+	mlx5_notifier_register(dev->mdev, &dev->mdev_events);
+	return 0;
+}
+
+static void mlx5_ib_stage_dev_notifier_cleanup(struct mlx5_ib_dev *dev)
+{
+	mlx5_notifier_unregister(dev->mdev, &dev->mdev_events);
+}
+
 void __mlx5_ib_remove(struct mlx5_ib_dev *dev,
 		      const struct mlx5_ib_profile *profile,
 		      int stage)
@@ -6228,6 +6272,9 @@ static const struct mlx5_ib_profile pf_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES,
 		     mlx5_ib_stage_dev_res_init,
 		     mlx5_ib_stage_dev_res_cleanup),
+	STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER,
+		     mlx5_ib_stage_dev_notifier_init,
+		     mlx5_ib_stage_dev_notifier_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_ODP,
 		     mlx5_ib_stage_odp_init,
 		     mlx5_ib_stage_odp_cleanup),
@@ -6279,6 +6326,9 @@ static const struct mlx5_ib_profile nic_rep_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES,
 		     mlx5_ib_stage_dev_res_init,
 		     mlx5_ib_stage_dev_res_cleanup),
+	STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER,
+		     mlx5_ib_stage_dev_notifier_init,
+		     mlx5_ib_stage_dev_notifier_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_COUNTERS,
 		     mlx5_ib_stage_counters_init,
 		     mlx5_ib_stage_counters_cleanup),
@@ -6399,7 +6449,6 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 static struct mlx5_interface mlx5_ib_interface = {
 	.add            = mlx5_ib_add,
 	.remove         = mlx5_ib_remove,
-	.event          = mlx5_ib_event,
 	.protocol	= MLX5_INTERFACE_PROTOCOL_IB,
 };
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 27999fd32356..7326fb8710e0 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -775,6 +775,7 @@ enum mlx5_ib_stages {
 	MLX5_IB_STAGE_NON_DEFAULT_CB,
 	MLX5_IB_STAGE_ROCE,
 	MLX5_IB_STAGE_DEVICE_RESOURCES,
+	MLX5_IB_STAGE_DEVICE_NOTIFIER,
 	MLX5_IB_STAGE_ODP,
 	MLX5_IB_STAGE_COUNTERS,
 	MLX5_IB_STAGE_CONG_DEBUGFS,
@@ -806,6 +807,7 @@ struct mlx5_ib_multiport_info {
 	struct list_head list;
 	struct mlx5_ib_dev *ibdev;
 	struct mlx5_core_dev *mdev;
+	struct notifier_block mdev_events;
 	struct completion unref_comp;
 	u64 sys_image_guid;
 	u32 mdev_refcnt;
@@ -893,6 +895,7 @@ struct mlx5_ib_dev {
 	struct ib_device		ib_dev;
 	const struct uverbs_object_tree_def *driver_trees[7];
 	struct mlx5_core_dev		*mdev;
+	struct notifier_block		mdev_events;
 	struct mlx5_roce		roce[MLX5_MAX_PORTS];
 	int				num_ports;
 	/* serialize update of capability mask
-- 
cgit v1.2.3


From 02039fb659b366011f55b15890136754f3d82e2d Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:39:01 -0800
Subject: net/mlx5: Remove unused events callback and logic

The mlx5_interface->event callback is not used by mlx5e/mlx5_ib anymore.

We totally remove the delayed events logic work around, since with
the dynamic notifier registration API it is not needed anymore, mlx5_ib
can register its notifier and start receiving events exactly at the moment
it is ready to handle them.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c      | 109 +--------------------
 drivers/net/ethernet/mellanox/mlx5/core/events.c   |   8 +-
 drivers/net/ethernet/mellanox/mlx5/core/health.c   |   3 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  10 --
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |   3 -
 include/linux/mlx5/driver.h                        |  10 +-
 6 files changed, 11 insertions(+), 132 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index d63ba8813829..d2ed14bc37c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -32,7 +32,6 @@
 
 #include <linux/mlx5/driver.h>
 #include "mlx5_core.h"
-#include "lib/mlx5.h"
 
 static LIST_HEAD(intf_list);
 static LIST_HEAD(mlx5_dev_list);
@@ -46,75 +45,11 @@ struct mlx5_device_context {
 	unsigned long		state;
 };
 
-struct mlx5_delayed_event {
-	struct list_head	list;
-	struct mlx5_core_dev	*dev;
-	enum mlx5_dev_event	event;
-	unsigned long		param;
-};
-
 enum {
 	MLX5_INTERFACE_ADDED,
 	MLX5_INTERFACE_ATTACHED,
 };
 
-static void add_delayed_event(struct mlx5_priv *priv,
-			      struct mlx5_core_dev *dev,
-			      enum mlx5_dev_event event,
-			      unsigned long param)
-{
-	struct mlx5_delayed_event *delayed_event;
-
-	delayed_event = kzalloc(sizeof(*delayed_event), GFP_ATOMIC);
-	if (!delayed_event) {
-		mlx5_core_err(dev, "event %d is missed\n", event);
-		return;
-	}
-
-	mlx5_core_dbg(dev, "Accumulating event %d\n", event);
-	delayed_event->dev = dev;
-	delayed_event->event = event;
-	delayed_event->param = param;
-	list_add_tail(&delayed_event->list, &priv->waiting_events_list);
-}
-
-static void delayed_event_release(struct mlx5_device_context *dev_ctx,
-				  struct mlx5_priv *priv)
-{
-	struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv);
-	struct mlx5_delayed_event *de;
-	struct mlx5_delayed_event *n;
-	struct list_head temp;
-
-	INIT_LIST_HEAD(&temp);
-
-	spin_lock_irq(&priv->ctx_lock);
-
-	priv->is_accum_events = false;
-	list_splice_init(&priv->waiting_events_list, &temp);
-	if (!dev_ctx->context)
-		goto out;
-	list_for_each_entry_safe(de, n, &temp, list)
-		dev_ctx->intf->event(dev, dev_ctx->context, de->event, de->param);
-
-out:
-	spin_unlock_irq(&priv->ctx_lock);
-
-	list_for_each_entry_safe(de, n, &temp, list) {
-		list_del(&de->list);
-		kfree(de);
-	}
-}
-
-/* accumulating events that can come after mlx5_ib calls to
- * ib_register_device, till adding that interface to the events list.
- */
-static void delayed_event_start(struct mlx5_priv *priv)
-{
-	spin_lock_irq(&priv->ctx_lock);
-	priv->is_accum_events = true;
-	spin_unlock_irq(&priv->ctx_lock);
-}
 
 void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 {
@@ -130,8 +65,6 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 
 	dev_ctx->intf = intf;
 
-	delayed_event_start(priv);
-
 	dev_ctx->context = intf->add(dev);
 	if (dev_ctx->context) {
 		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
@@ -143,8 +76,6 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 		spin_unlock_irq(&priv->ctx_lock);
 	}
 
-	delayed_event_release(dev_ctx, priv);
-
 	if (!dev_ctx->context)
 		kfree(dev_ctx);
 }
@@ -188,26 +119,20 @@ static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv
 	if (!dev_ctx)
 		return;
 
-	delayed_event_start(priv);
 	if (intf->attach) {
 		if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state))
-			goto out;
+			return;
 		if (intf->attach(dev, dev_ctx->context))
-			goto out;
-
+			return;
 		set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
 	} else {
 		if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
-			goto out;
+			return;
 		dev_ctx->context = intf->add(dev);
 		if (!dev_ctx->context)
-			goto out;
-
+			return;
 		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
 	}
-
-out:
-	delayed_event_release(dev_ctx, priv);
 }
 
 void mlx5_attach_device(struct mlx5_core_dev *dev)
@@ -403,32 +328,6 @@ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
 	return res;
 }
 
-void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
-		     unsigned long param)
-{
-	struct mlx5_priv *priv = &dev->priv;
-	struct mlx5_device_context *dev_ctx;
-	unsigned long flags;
-
-	spin_lock_irqsave(&priv->ctx_lock, flags);
-
-	if (priv->is_accum_events)
-		add_delayed_event(priv, dev, event, param);
-
-	/* After mlx5_detach_device, the dev_ctx->intf is still set and dev_ctx is
-	 * still in priv->ctx_list. In this case, only notify the dev_ctx if its
-	 * ADDED or ATTACHED bit are set.
-	 */
-	list_for_each_entry(dev_ctx, &priv->ctx_list, list)
-		if (dev_ctx->intf->event &&
-		    (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state) ||
-		     test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)))
-			dev_ctx->intf->event(dev, dev_ctx->context, event, param);
-
-	spin_unlock_irqrestore(&priv->ctx_lock, flags);
-
-	mlx5_notifier_call_chain(dev->priv.events, event, (void *)param);
-}
 
 void mlx5_dev_list_lock(void)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index adab66eb726c..ab66f5d65a04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -178,8 +178,8 @@ static int port_change(struct notifier_block *nb,
 			       port, eqe->sub_type);
 	}
 
-	if (dev->event && dev_event_dispatch)
-		dev->event(dev, dev_event, dev_event_data);
+	if (dev_event_dispatch)
+		mlx5_notifier_call_chain(events, dev_event, (void *)dev_event_data);
 
 	return NOTIFY_OK;
 }
@@ -207,8 +207,8 @@ static int general_event(struct notifier_block *nb, unsigned long type, void *da
 			      eqe->sub_type);
 	}
 
-	if (dev->event && dev_event_dispatch)
-		dev->event(dev, dev_event, dev_event_data);
+	if (dev_event_dispatch)
+		mlx5_notifier_call_chain(events, dev_event, (void *)dev_event_data);
 
 	return NOTIFY_OK;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 4e42bd290959..196c07383082 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -39,6 +39,7 @@
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 #include "lib/eq.h"
+#include "lib/mlx5.h"
 
 enum {
 	MLX5_HEALTH_POLL_INTERVAL	= 2 * HZ,
@@ -105,7 +106,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 		mlx5_cmd_trigger_completions(dev);
 	}
 
-	mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 1);
+	mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_SYS_ERROR, (void *)1);
 	mlx5_core_err(dev, "end\n");
 
 unlock:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index e56278ead4eb..4bc27a073dc4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1125,12 +1125,6 @@ out:
 	return err;
 }
 
-struct mlx5_core_event_handler {
-	void (*event)(struct mlx5_core_dev *dev,
-		      enum mlx5_dev_event event,
-		      void *data);
-};
-
 static const struct devlink_ops mlx5_devlink_ops = {
 #ifdef CONFIG_MLX5_ESWITCH
 	.eswitch_mode_set = mlx5_devlink_eswitch_mode_set,
@@ -1164,7 +1158,6 @@ static int init_one(struct pci_dev *pdev,
 	pci_set_drvdata(pdev, dev);
 
 	dev->pdev = pdev;
-	dev->event = mlx5_core_event;
 	dev->profile = &profile[prof_sel];
 
 	INIT_LIST_HEAD(&priv->ctx_list);
@@ -1172,9 +1165,6 @@ static int init_one(struct pci_dev *pdev,
 	mutex_init(&dev->pci_status_mutex);
 	mutex_init(&dev->intf_state_mutex);
 
-	INIT_LIST_HEAD(&priv->waiting_events_list);
-	priv->is_accum_events = false;
-
 	mutex_init(&priv->bfregs.reg_head.lock);
 	mutex_init(&priv->bfregs.wc_head.lock);
 	INIT_LIST_HEAD(&priv->bfregs.reg_head.list);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index c70bd94e18d6..fd3141a4b3f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -102,9 +102,6 @@ int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id);
 int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev);
-
-void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
-		     unsigned long param);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
 void mlx5_recover_device(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 14ca74707275..d3ffc64f9a75 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -588,10 +588,7 @@ struct mlx5_priv {
 	struct list_head        dev_list;
 	struct list_head        ctx_list;
 	spinlock_t              ctx_lock;
-
-	struct list_head	waiting_events_list;
-	bool			is_accum_events;
-	struct mlx5_events     *events;
+	struct mlx5_events      *events;
 
 	struct mlx5_flow_steering *steering;
 	struct mlx5_mpfs        *mpfs;
@@ -696,9 +693,6 @@ struct mlx5_core_dev {
 	/* sync interface state */
 	struct mutex		intf_state_mutex;
 	unsigned long		intf_state;
-	void			(*event) (struct mlx5_core_dev *dev,
-					  enum mlx5_dev_event event,
-					  unsigned long param);
 	struct mlx5_priv	priv;
 	struct mlx5_profile	*profile;
 	atomic_t		num_qps;
@@ -1053,8 +1047,6 @@ struct mlx5_interface {
 	void			(*remove)(struct mlx5_core_dev *dev, void *context);
 	int			(*attach)(struct mlx5_core_dev *dev, void *context);
 	void			(*detach)(struct mlx5_core_dev *dev, void *context);
-	void			(*event)(struct mlx5_core_dev *dev, void *context,
-					 enum mlx5_dev_event event, unsigned long param);
 	void *                  (*get_dev)(void *context);
 	int			protocol;
 	struct list_head	list;
-- 
cgit v1.2.3


From 134e9349ecf0e23c954e205a31f5b665ce25e5f6 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:39:02 -0800
Subject: IB/mlx5: Handle raw port change event rather than the software
 version

Use the FW version of the port change event as forwarded via new mlx5
notifiers API.

After this patch, processed software version of the port change event
will become deprecated and will be totally removed in downstream
patches.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c | 86 +++++++++++++++++++++++----------------
 1 file changed, 52 insertions(+), 34 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 549c766cf309..a0668b923f78 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -87,7 +87,7 @@ struct mlx5_ib_event_work {
 		struct mlx5_ib_multiport_info *mpi;
 	};
 	bool			is_slave;
-	enum mlx5_dev_event	event;
+	unsigned int		event;
 	void			*param;
 };
 
@@ -4236,6 +4236,51 @@ static void delay_drop_handler(struct work_struct *work)
 	mutex_unlock(&delay_drop->lock);
 }
 
+static int handle_port_change(struct mlx5_ib_dev *ibdev, struct mlx5_eqe *eqe,
+			      struct ib_event *ibev)
+{
+	u8 port = (eqe->data.port.port >> 4) & 0xf;
+
+	ibev->element.port_num = port;
+
+	switch (eqe->sub_type) {
+	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+	case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
+		/* In RoCE, port up/down events are handled in
+		 * mlx5_netdev_event().
+		 */
+		if (mlx5_ib_port_link_layer(&ibdev->ib_dev, port) ==
+					    IB_LINK_LAYER_ETHERNET)
+			return -EINVAL;
+
+		ibev->event = (eqe->sub_type == MLX5_PORT_CHANGE_SUBTYPE_ACTIVE) ?
+				IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR;
+		break;
+
+	case MLX5_PORT_CHANGE_SUBTYPE_LID:
+		ibev->event = IB_EVENT_LID_CHANGE;
+		break;
+
+	case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
+		ibev->event = IB_EVENT_PKEY_CHANGE;
+		schedule_work(&ibdev->devr.ports[port - 1].pkey_change_work);
+		break;
+
+	case MLX5_PORT_CHANGE_SUBTYPE_GUID:
+		ibev->event = IB_EVENT_GID_CHANGE;
+		break;
+
+	case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
+		ibev->event = IB_EVENT_CLIENT_REREGISTER;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static void mlx5_ib_handle_event(struct work_struct *_work)
 {
 	struct mlx5_ib_event_work *work =
@@ -4243,7 +4288,6 @@ static void mlx5_ib_handle_event(struct work_struct *_work)
 	struct mlx5_ib_dev *ibdev;
 	struct ib_event ibev;
 	bool fatal = false;
-	u8 port = (u8)(unsigned long)work->param;
 
 	if (work->is_slave) {
 		ibdev = mlx5_ib_get_ibdev_from_mpi(work->mpi);
@@ -4257,37 +4301,12 @@ static void mlx5_ib_handle_event(struct work_struct *_work)
 	case MLX5_DEV_EVENT_SYS_ERROR:
 		ibev.event = IB_EVENT_DEVICE_FATAL;
 		mlx5_ib_handle_internal_error(ibdev);
+		ibev.element.port_num  = (u8)(unsigned long)work->param;
 		fatal = true;
 		break;
-	case MLX5_DEV_EVENT_PORT_UP:
-	case MLX5_DEV_EVENT_PORT_DOWN:
-	case MLX5_DEV_EVENT_PORT_INITIALIZED:
-		/* In RoCE, port up/down events are handled in
-		 * mlx5_netdev_event().
-		 */
-		if (mlx5_ib_port_link_layer(&ibdev->ib_dev, port) ==
-			IB_LINK_LAYER_ETHERNET)
+	case MLX5_EVENT_TYPE_PORT_CHANGE:
+		if (handle_port_change(ibdev, work->param, &ibev))
 			goto out;
-
-		ibev.event = (work->event == MLX5_DEV_EVENT_PORT_UP) ?
-			     IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR;
-		break;
-
-	case MLX5_DEV_EVENT_LID_CHANGE:
-		ibev.event = IB_EVENT_LID_CHANGE;
-		break;
-
-	case MLX5_DEV_EVENT_PKEY_CHANGE:
-		ibev.event = IB_EVENT_PKEY_CHANGE;
-		schedule_work(&ibdev->devr.ports[port - 1].pkey_change_work);
-		break;
-
-	case MLX5_DEV_EVENT_GUID_CHANGE:
-		ibev.event = IB_EVENT_GID_CHANGE;
-		break;
-
-	case MLX5_DEV_EVENT_CLIENT_REREG:
-		ibev.event = IB_EVENT_CLIENT_REREGISTER;
 		break;
 	case MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT:
 		schedule_work(&ibdev->delay_drop.delay_drop_work);
@@ -4296,11 +4315,10 @@ static void mlx5_ib_handle_event(struct work_struct *_work)
 		goto out;
 	}
 
-	ibev.device	      = &ibdev->ib_dev;
-	ibev.element.port_num = port;
+	ibev.device = &ibdev->ib_dev;
 
-	if (!rdma_is_port_valid(&ibdev->ib_dev, port)) {
-		mlx5_ib_warn(ibdev, "warning: event on port %d\n", port);
+	if (!rdma_is_port_valid(&ibdev->ib_dev, ibev.element.port_num)) {
+		mlx5_ib_warn(ibdev, "warning: event on port %d\n",  ibev.element.port_num);
 		goto out;
 	}
 
-- 
cgit v1.2.3


From cb6191bf25f755f47593fc40b8fd39d3eedde884 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:39:03 -0800
Subject: net/mlx5: Allow forwarding event type general event as is

FW general event is used by mlx5_ib for RQ delay drop timeout event
handling, in this patch we allow to forward FW general event type to mlx5
notifiers chain so mlx5_ib can handle it and to deprecate the software
version of it.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index ab66f5d65a04..735a9b038a73 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -36,6 +36,7 @@ static struct mlx5_nb events_nbs_ref[] = {
 
 	/* Events to be forwarded (as is) to mlx5 core interfaces (mlx5e/mlx5_ib) */
 	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT },
 };
 
 struct mlx5_events {
-- 
cgit v1.2.3


From 09e574fa76d6a47e283a7eb18ec1b0cb34174532 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:39:04 -0800
Subject: IB/mlx5: Handle raw delay drop general event

Handle FW general event rq delay drop as it was received from FW via mlx5
notifiers API, instead of handling the processed software version of that
event. After this patch we can safely remove all software processed FW
events types and definitions.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index a0668b923f78..7e6af18e7d82 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4236,6 +4236,18 @@ static void delay_drop_handler(struct work_struct *work)
 	mutex_unlock(&delay_drop->lock);
 }
 
+static void handle_general_event(struct mlx5_ib_dev *ibdev, struct mlx5_eqe *eqe,
+				 struct ib_event *ibev)
+{
+	switch (eqe->sub_type) {
+	case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT:
+		schedule_work(&ibdev->delay_drop.delay_drop_work);
+		break;
+	default: /* do nothing */
+		return;
+	}
+}
+
 static int handle_port_change(struct mlx5_ib_dev *ibdev, struct mlx5_eqe *eqe,
 			      struct ib_event *ibev)
 {
@@ -4308,9 +4320,9 @@ static void mlx5_ib_handle_event(struct work_struct *_work)
 		if (handle_port_change(ibdev, work->param, &ibev))
 			goto out;
 		break;
-	case MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT:
-		schedule_work(&ibdev->delay_drop.delay_drop_work);
-		goto out;
+	case MLX5_EVENT_TYPE_GENERAL_EVENT:
+		handle_general_event(ibdev, work->param, &ibev);
+		/* fall through */
 	default:
 		goto out;
 	}
-- 
cgit v1.2.3


From b8267cd765b333673e05696b517d38a1a7eb5b2e Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:39:05 -0800
Subject: net/mlx5: Remove all deprecated software versions of FW events

Before the new mlx5 event notification infrastructure and API,
mlx5_core used to process all events before forwarding them to mlx5
interfaces (mlx5e/mlx5_ib) and used to translate the event type enum
to a software defined enum, this is not needed anymore since it is ok
for mlx5e and mlx5_ib to receive FW events as is, at least the few ones
mlx5 core allows.

mlx5e and mlx5_ib already moved to use the new API and they only handle FW
events types, it is now safe to remove all equivalent software defined
events and the logic around them.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 92 +-----------------------
 include/linux/mlx5/driver.h                      |  9 ---
 2 files changed, 1 insertion(+), 100 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 735a9b038a73..3708b42c1d6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -19,8 +19,6 @@ struct mlx5_event_nb {
  * separate notifiers callbacks, specifically by those mlx5 components.
  */
 static int any_notifier(struct notifier_block *, unsigned long, void *);
-static int port_change(struct notifier_block *, unsigned long, void *);
-static int general_event(struct notifier_block *, unsigned long, void *);
 static int temp_warn(struct notifier_block *, unsigned long, void *);
 static int port_module(struct notifier_block *, unsigned long, void *);
 
@@ -28,9 +26,8 @@ static int port_module(struct notifier_block *, unsigned long, void *);
 static int forward_event(struct notifier_block *, unsigned long, void *);
 
 static struct mlx5_nb events_nbs_ref[] = {
+	/* Events to be proccessed by mlx5_core */
 	{.nb.notifier_call = any_notifier,  .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY },
-	{.nb.notifier_call = port_change,   .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
-	{.nb.notifier_call = general_event, .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT },
 	{.nb.notifier_call = temp_warn,     .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT },
 	{.nb.notifier_call = port_module,   .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT },
 
@@ -127,93 +124,6 @@ static int any_notifier(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-static enum mlx5_dev_event port_subtype2dev(u8 subtype)
-{
-	switch (subtype) {
-	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
-		return MLX5_DEV_EVENT_PORT_DOWN;
-	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-		return MLX5_DEV_EVENT_PORT_UP;
-	case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
-		return MLX5_DEV_EVENT_PORT_INITIALIZED;
-	case MLX5_PORT_CHANGE_SUBTYPE_LID:
-		return MLX5_DEV_EVENT_LID_CHANGE;
-	case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
-		return MLX5_DEV_EVENT_PKEY_CHANGE;
-	case MLX5_PORT_CHANGE_SUBTYPE_GUID:
-		return MLX5_DEV_EVENT_GUID_CHANGE;
-	case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
-		return MLX5_DEV_EVENT_CLIENT_REREG;
-	}
-	return -1;
-}
-
-/* type == MLX5_EVENT_TYPE_PORT_CHANGE */
-static int port_change(struct notifier_block *nb,
-		       unsigned long type, void *data)
-{
-	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
-	struct mlx5_events   *events   = event_nb->ctx;
-	struct mlx5_core_dev *dev      = events->dev;
-
-	bool dev_event_dispatch = false;
-	enum mlx5_dev_event dev_event;
-	unsigned long dev_event_data;
-	struct mlx5_eqe *eqe = data;
-	u8 port = (eqe->data.port.port >> 4) & 0xf;
-
-	switch (eqe->sub_type) {
-	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
-	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-	case MLX5_PORT_CHANGE_SUBTYPE_LID:
-	case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
-	case MLX5_PORT_CHANGE_SUBTYPE_GUID:
-	case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
-	case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
-		dev_event = port_subtype2dev(eqe->sub_type);
-		dev_event_data = (unsigned long)port;
-		dev_event_dispatch = true;
-		break;
-	default:
-		mlx5_core_warn(dev, "Port event with unrecognized subtype: port %d, sub_type %d\n",
-			       port, eqe->sub_type);
-	}
-
-	if (dev_event_dispatch)
-		mlx5_notifier_call_chain(events, dev_event, (void *)dev_event_data);
-
-	return NOTIFY_OK;
-}
-
-/* type == MLX5_EVENT_TYPE_GENERAL_EVENT */
-static int general_event(struct notifier_block *nb, unsigned long type, void *data)
-{
-	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
-	struct mlx5_events   *events   = event_nb->ctx;
-	struct mlx5_core_dev *dev      = events->dev;
-
-	bool dev_event_dispatch = false;
-	enum mlx5_dev_event dev_event;
-	unsigned long dev_event_data;
-	struct mlx5_eqe *eqe = data;
-
-	switch (eqe->sub_type) {
-	case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT:
-		dev_event = MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT;
-		dev_event_data = 0;
-		dev_event_dispatch = true;
-		break;
-	default:
-		mlx5_core_dbg(dev, "General event with unrecognized subtype: sub_type %d\n",
-			      eqe->sub_type);
-	}
-
-	if (dev_event_dispatch)
-		mlx5_notifier_call_chain(events, dev_event, (void *)dev_event_data);
-
-	return NOTIFY_OK;
-}
-
 /* type == MLX5_EVENT_TYPE_TEMP_WARN_EVENT */
 static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
 {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d3ffc64f9a75..a77bedb8a556 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -196,15 +196,6 @@ struct mlx5_rsc_debug {
 
 enum mlx5_dev_event {
 	MLX5_DEV_EVENT_SYS_ERROR = 128, /* 0 - 127 are FW events */
-	MLX5_DEV_EVENT_PORT_UP,
-	MLX5_DEV_EVENT_PORT_DOWN,
-	MLX5_DEV_EVENT_PORT_INITIALIZED,
-	MLX5_DEV_EVENT_LID_CHANGE,
-	MLX5_DEV_EVENT_PKEY_CHANGE,
-	MLX5_DEV_EVENT_GUID_CHANGE,
-	MLX5_DEV_EVENT_CLIENT_REREG,
-	MLX5_DEV_EVENT_PPS,
-	MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT,
 };
 
 enum mlx5_port_status {
-- 
cgit v1.2.3


From 451be51c0b474f790e9833cd575fd9a6fbd679df Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:39:06 -0800
Subject: net/mlx5: Forward QP/WorkQueues resource events

Allow forwarding QP and WQ events to mlx5_core interfaces, e.g. mlx5_ib

Use mlx5_notifier_register/unregister in qp.c in order to allow seamless
transition of qp.c to infiniband subsystem.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 10 ++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/qp.c     |  8 ++++----
 include/linux/mlx5/driver.h                      |  2 +-
 3 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 3708b42c1d6b..201c5f6091ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -34,6 +34,16 @@ static struct mlx5_nb events_nbs_ref[] = {
 	/* Events to be forwarded (as is) to mlx5 core interfaces (mlx5e/mlx5_ib) */
 	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
 	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT },
+	/* QP/WQ resource events to forward */
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_DCT_DRAINED },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PATH_MIG },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_COMM_EST },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_SQ_DRAINED },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_SRQ_LAST_WQE },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_WQ_CATAS_ERROR },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PATH_MIG_FAILED },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_WQ_ACCESS_ERROR },
 };
 
 struct mlx5_events {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 28726c63101f..388f205a497f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -150,7 +150,7 @@ static int rsc_event_notifier(struct notifier_block *nb,
 		return NOTIFY_DONE;
 	}
 
-	table = mlx5_nb_cof(nb, struct mlx5_qp_table, nb);
+	table = container_of(nb, struct mlx5_qp_table, nb);
 	priv  = container_of(table, struct mlx5_priv, qp_table);
 	dev   = container_of(priv, struct mlx5_core_dev, priv);
 
@@ -523,15 +523,15 @@ void mlx5_init_qp_table(struct mlx5_core_dev *dev)
 	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
 	mlx5_qp_debugfs_init(dev);
 
-	MLX5_NB_INIT(&table->nb, rsc_event_notifier, NOTIFY_ANY);
-	mlx5_eq_notifier_register(dev, &table->nb);
+	table->nb.notifier_call = rsc_event_notifier;
+	mlx5_notifier_register(dev, &table->nb);
 }
 
 void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev)
 {
 	struct mlx5_qp_table *table = &dev->priv.qp_table;
 
-	mlx5_eq_notifier_unregister(dev, &table->nb);
+	mlx5_notifier_unregister(dev, &table->nb);
 	mlx5_qp_debugfs_cleanup(dev);
 }
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index a77bedb8a556..4f078b7f6620 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -456,7 +456,7 @@ struct mlx5_core_health {
 };
 
 struct mlx5_qp_table {
-	struct mlx5_nb          nb;
+	struct notifier_block   nb;
 
 	/* protect radix tree
 	 */
-- 
cgit v1.2.3


From 4e2df04ad25ab8e627878817e56d6a27645ca4a8 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:39:07 -0800
Subject: net/mlx5: Forward SRQ resource events

Allow forwarding of SRQ events to mlx5_core interfaces, e.g. mlx5_ib.
Use mlx5_notifier_register/unregister in srq.c in order to allow seamless
transition of srq.c to infiniband subsystem.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c |  3 ++
 drivers/net/ethernet/mellanox/mlx5/core/srq.c    | 38 +++++++-----------------
 include/linux/mlx5/driver.h                      |  3 +-
 3 files changed, 14 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 201c5f6091ea..9e6e216faac3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -44,6 +44,9 @@ static struct mlx5_nb events_nbs_ref[] = {
 	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PATH_MIG_FAILED },
 	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR },
 	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_WQ_ACCESS_ERROR },
+	/* SRQ events */
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_SRQ_CATAS_ERROR },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_SRQ_RQ_LIMIT },
 };
 
 struct mlx5_events {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
index 0563866c13f2..79c5f0d57956 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
@@ -40,15 +40,21 @@
 #include "mlx5_core.h"
 #include "lib/eq.h"
 
-static int srq_event_notifier(struct mlx5_srq_table *table,
+static int srq_event_notifier(struct notifier_block *nb,
 			      unsigned long type, void *data)
 {
+	struct mlx5_srq_table *table;
 	struct mlx5_core_dev *dev;
 	struct mlx5_core_srq *srq;
 	struct mlx5_priv *priv;
 	struct mlx5_eqe *eqe;
 	u32 srqn;
 
+	if (type != MLX5_EVENT_TYPE_SRQ_CATAS_ERROR &&
+	    type != MLX5_EVENT_TYPE_SRQ_RQ_LIMIT)
+		return NOTIFY_DONE;
+
+	table = container_of(nb, struct mlx5_srq_table, nb);
 	priv  = container_of(table, struct mlx5_priv, srq_table);
 	dev   = container_of(priv, struct mlx5_core_dev, priv);
 
@@ -77,26 +83,6 @@ static int srq_event_notifier(struct mlx5_srq_table *table,
 	return NOTIFY_OK;
 }
 
-static int catas_err_notifier(struct notifier_block *nb,
-			      unsigned long type, void *data)
-{
-	struct mlx5_srq_table *table;
-
-	table = mlx5_nb_cof(nb, struct mlx5_srq_table, catas_err_nb);
-	/* type == MLX5_EVENT_TYPE_SRQ_CATAS_ERROR */
-	return srq_event_notifier(table, type, data);
-}
-
-static int rq_limit_notifier(struct notifier_block *nb,
-			     unsigned long type, void *data)
-{
-	struct mlx5_srq_table *table;
-
-	table = mlx5_nb_cof(nb, struct mlx5_srq_table, rq_limit_nb);
-	/* type == MLX5_EVENT_TYPE_SRQ_RQ_LIMIT */
-	return srq_event_notifier(table, type, data);
-}
-
 static int get_pas_size(struct mlx5_srq_attr *in)
 {
 	u32 log_page_size = in->log_page_size + 12;
@@ -743,17 +729,13 @@ void mlx5_init_srq_table(struct mlx5_core_dev *dev)
 	spin_lock_init(&table->lock);
 	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
 
-	MLX5_NB_INIT(&table->catas_err_nb, catas_err_notifier, SRQ_CATAS_ERROR);
-	mlx5_eq_notifier_register(dev, &table->catas_err_nb);
-
-	MLX5_NB_INIT(&table->rq_limit_nb, rq_limit_notifier, SRQ_RQ_LIMIT);
-	mlx5_eq_notifier_register(dev, &table->rq_limit_nb);
+	table->nb.notifier_call = srq_event_notifier;
+	mlx5_notifier_register(dev, &table->nb);
 }
 
 void mlx5_cleanup_srq_table(struct mlx5_core_dev *dev)
 {
 	struct mlx5_srq_table *table = &dev->priv.srq_table;
 
-	mlx5_eq_notifier_unregister(dev, &table->rq_limit_nb);
-	mlx5_eq_notifier_unregister(dev, &table->catas_err_nb);
+	mlx5_notifier_unregister(dev, &table->nb);
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 4f078b7f6620..27a481b159ed 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -465,8 +465,7 @@ struct mlx5_qp_table {
 };
 
 struct mlx5_srq_table {
-	struct mlx5_nb          catas_err_nb;
-	struct mlx5_nb          rq_limit_nb;
+	struct notifier_block   nb;
 	/* protect radix tree
 	 */
 	spinlock_t		lock;
-- 
cgit v1.2.3


From 93631211c9c07dd3e60ca8462281ff475d3b87a6 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 26 Nov 2018 14:39:08 -0800
Subject: net/mlx5: Debug print for forwarded async events

Print a debug message for every async FW event forwarded to mlx5
interfaces (mlx5e netdev and mlx5_ib rdma module).

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 9e6e216faac3..e92df7020a26 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -229,7 +229,10 @@ static int forward_event(struct notifier_block *nb, unsigned long event, void *d
 {
 	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
 	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_eqe      *eqe      = data;
 
+	mlx5_core_dbg(events->dev, "Async eqe type %s, subtype (%d) forward to interfaces\n",
+		      eqe_type_str(eqe->type), eqe->sub_type);
 	atomic_notifier_call_chain(&events->nh, event, data);
 	return NOTIFY_OK;
 }
-- 
cgit v1.2.3


From b42699547fc9fb1057795bccc21a6445743a7fde Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 29 Nov 2018 15:31:45 -0800
Subject: tools/bpf: make libbpf _GNU_SOURCE friendly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During porting libbpf to bcc, I got some warnings like below:
  ...
  [  2%] Building C object src/cc/CMakeFiles/bpf-shared.dir/libbpf/src/libbpf.c.o
  /home/yhs/work/bcc2/src/cc/libbpf/src/libbpf.c:12:0:
  warning: "_GNU_SOURCE" redefined [enabled by default]
   #define _GNU_SOURCE
  ...
  [  3%] Building C object src/cc/CMakeFiles/bpf-shared.dir/libbpf/src/libbpf_errno.c.o
  /home/yhs/work/bcc2/src/cc/libbpf/src/libbpf_errno.c: In function ‘libbpf_strerror’:
  /home/yhs/work/bcc2/src/cc/libbpf/src/libbpf_errno.c:45:7:
  warning: assignment makes integer from pointer without a cast [enabled by default]
     ret = strerror_r(err, buf, size);
  ...

bcc is built with _GNU_SOURCE defined and this caused the above warning.
This patch intends to make libpf _GNU_SOURCE friendly by
  . define _GNU_SOURCE in libbpf.c unless it is not defined
  . undefine _GNU_SOURCE as non-gnu version of strerror_r is expected.

Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c       | 2 ++
 tools/lib/bpf/libbpf_errno.c | 1 +
 2 files changed, 3 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ed4212a4c5f9..59b748ebd15f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -9,7 +9,9 @@
  * Copyright (C) 2017 Nicira, Inc.
  */
 
+#ifndef _GNU_SOURCE
 #define _GNU_SOURCE
+#endif
 #include <stdlib.h>
 #include <stdio.h>
 #include <stdarg.h>
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index d83b17f8435c..4343e40588c6 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2017 Nicira, Inc.
  */
 
+#undef _GNU_SOURCE
 #include <stdio.h>
 #include <string.h>
 
-- 
cgit v1.2.3


From cc2b8ed1369592fb84609e920f99a5659a6445f7 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 23 Nov 2018 18:29:02 +0100
Subject: arm64/bpf: use movn/movk/movk sequence to generate kernel addresses

On arm64, all executable code is guaranteed to reside in the vmalloc
space (or the module space), and so jump targets will only use 48
bits at most, and the remaining bits are guaranteed to be 0x1.

This means we can generate an immediate jump address using a sequence
of one MOVN (move wide negated) and two MOVK instructions, where the
first one sets the lower 16 bits but also sets all top bits to 0x1.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm64/net/bpf_jit_comp.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 89198017e8e6..b87285924023 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -134,10 +134,9 @@ static inline void emit_a64_mov_i64(const int reg, const u64 val,
 }
 
 /*
- * This is an unoptimized 64 immediate emission used for BPF to BPF call
- * addresses. It will always do a full 64 bit decomposition as otherwise
- * more complexity in the last extra pass is required since we previously
- * reserved 4 instructions for the address.
+ * Kernel addresses in the vmalloc space use at most 48 bits, and the
+ * remaining bits are guaranteed to be 0x1. So we can compose the address
+ * with a fixed length movn/movk/movk sequence.
  */
 static inline void emit_addr_mov_i64(const int reg, const u64 val,
 				     struct jit_ctx *ctx)
@@ -145,8 +144,8 @@ static inline void emit_addr_mov_i64(const int reg, const u64 val,
 	u64 tmp = val;
 	int shift = 0;
 
-	emit(A64_MOVZ(1, reg, tmp & 0xffff, shift), ctx);
-	for (;shift < 48;) {
+	emit(A64_MOVN(1, reg, ~tmp & 0xffff, shift), ctx);
+	while (shift < 32) {
 		tmp >>= 16;
 		shift += 16;
 		emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx);
@@ -634,11 +633,7 @@ emit_cond_jmp:
 					    &func_addr, &func_addr_fixed);
 		if (ret < 0)
 			return ret;
-		if (func_addr_fixed)
-			/* We can use optimized emission here. */
-			emit_a64_mov_i64(tmp, func_addr, ctx);
-		else
-			emit_addr_mov_i64(tmp, func_addr, ctx);
+		emit_addr_mov_i64(tmp, func_addr, ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
 		break;
-- 
cgit v1.2.3


From cac97ed681db9891c74be91b54e6b550dc6afb03 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sun, 14 Oct 2018 18:38:05 +0200
Subject: mt76x2: align mt76x2 and mt76x2u firmware

Unify firmware version used on mt76x2e and mt76x2u drivers

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h  | 3 ---
 drivers/net/wireless/mediatek/mt76/mt76x2/usb.c     | 4 ++--
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c | 4 ++--
 3 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index ab93125f46de..b546fe83a40d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -31,9 +31,6 @@
 #define MT7662_ROM_PATCH	"mt7662_rom_patch.bin"
 #define MT7662_EEPROM_SIZE	512
 
-#define MT7662U_FIRMWARE	"mediatek/mt7662u.bin"
-#define MT7662U_ROM_PATCH	"mediatek/mt7662u_rom_patch.bin"
-
 #define MT_CALIBRATE_INTERVAL	HZ
 
 #include "../mt76x02.h"
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index 57baf8d1c830..4d1788eb3812 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -131,8 +131,8 @@ err:
 }
 
 MODULE_DEVICE_TABLE(usb, mt76x2u_device_table);
-MODULE_FIRMWARE(MT7662U_FIRMWARE);
-MODULE_FIRMWARE(MT7662U_ROM_PATCH);
+MODULE_FIRMWARE(MT7662_FIRMWARE);
+MODULE_FIRMWARE(MT7662_ROM_PATCH);
 
 static struct usb_driver mt76x2u_driver = {
 	.name		= KBUILD_MODNAME,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
index 3f1e558e5e6d..a40aa838b6b2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
@@ -117,7 +117,7 @@ static int mt76x2u_mcu_load_rom_patch(struct mt76x02_dev *dev)
 		return 0;
 	}
 
-	err = request_firmware(&fw, MT7662U_ROM_PATCH, dev->mt76.dev);
+	err = request_firmware(&fw, MT7662_ROM_PATCH, dev->mt76.dev);
 	if (err < 0)
 		return err;
 
@@ -183,7 +183,7 @@ static int mt76x2u_mcu_load_firmware(struct mt76x02_dev *dev)
 	int err, len, ilm_len, dlm_len;
 	const struct firmware *fw;
 
-	err = request_firmware(&fw, MT7662U_FIRMWARE, dev->mt76.dev);
+	err = request_firmware(&fw, MT7662_FIRMWARE, dev->mt76.dev);
 	if (err < 0)
 		return err;
 
-- 
cgit v1.2.3


From 989582e50cbfd248707c0c3160f408dd4bd0c4bc Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sun, 14 Oct 2018 20:27:28 +0200
Subject: mt76x2u: align channel gain logic to mt76x2 one

Update vga tuning algorithm to the one used in mt76x2 driver

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x2/dfs.h    |   1 -
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h |   1 +
 .../net/wireless/mediatek/mt76/mt76x2/mt76x2u.h    |   2 -
 .../net/wireless/mediatek/mt76/mt76x2/pci_dfs.c    |  21 ----
 .../net/wireless/mediatek/mt76/mt76x2/pci_phy.c    |  90 -----------------
 drivers/net/wireless/mediatek/mt76/mt76x2/phy.c    | 111 +++++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt76x2/usb_mcu.c    |  24 -----
 .../net/wireless/mediatek/mt76/mt76x2/usb_phy.c    |  41 +-------
 8 files changed, 114 insertions(+), 177 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/dfs.h b/drivers/net/wireless/mediatek/mt76/mt76x2/dfs.h
index 3cb9d1864286..a11babbf292d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/dfs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/dfs.h
@@ -19,7 +19,6 @@
 
 void mt76x2_dfs_init_params(struct mt76x02_dev *dev);
 void mt76x2_dfs_init_detector(struct mt76x02_dev *dev);
-void mt76x2_dfs_adjust_agc(struct mt76x02_dev *dev);
 void mt76x2_dfs_set_domain(struct mt76x02_dev *dev,
 			   enum nl80211_dfs_regions region);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index b546fe83a40d..be0ae24d310a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -98,5 +98,6 @@ void mt76x2_phy_set_txpower_regs(struct mt76x02_dev *dev,
 void mt76x2_configure_tx_delay(struct mt76x02_dev *dev,
 			       enum nl80211_band band, u8 bw);
 void mt76x2_apply_gain_adj(struct mt76x02_dev *dev);
+void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev);
 
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2u.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2u.h
index 6e932b5010ef..833974de5c80 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2u.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2u.h
@@ -46,8 +46,6 @@ void mt76x2u_phy_calibrate(struct work_struct *work);
 void mt76x2u_phy_channel_calibrate(struct mt76x02_dev *dev);
 
 void mt76x2u_mcu_complete_urb(struct urb *urb);
-int mt76x2u_mcu_set_dynamic_vga(struct mt76x02_dev *dev, u8 channel, bool ap,
-				bool ext, int rssi, u32 false_cca);
 int mt76x2u_mcu_init(struct mt76x02_dev *dev);
 int mt76x2u_mcu_fw_init(struct mt76x02_dev *dev);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_dfs.c
index b56febae8945..8d66952400a8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_dfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_dfs.c
@@ -803,27 +803,6 @@ static void mt76x2_dfs_set_bbp_params(struct mt76x02_dev *dev)
 	mt76_wr(dev, 0x212c, 0x0c350001);
 }
 
-void mt76x2_dfs_adjust_agc(struct mt76x02_dev *dev)
-{
-	u32 agc_r8, agc_r4, val_r8, val_r4, dfs_r31;
-
-	agc_r8 = mt76_rr(dev, MT_BBP(AGC, 8));
-	agc_r4 = mt76_rr(dev, MT_BBP(AGC, 4));
-
-	val_r8 = (agc_r8 & 0x00007e00) >> 9;
-	val_r4 = agc_r4 & ~0x1f000000;
-	val_r4 += (((val_r8 + 1) >> 1) << 24);
-	mt76_wr(dev, MT_BBP(AGC, 4), val_r4);
-
-	dfs_r31 = FIELD_GET(MT_BBP_AGC_LNA_HIGH_GAIN, val_r4);
-	dfs_r31 += val_r8;
-	dfs_r31 -= (agc_r8 & 0x00000038) >> 3;
-	dfs_r31 = (dfs_r31 << 16) | 0x00000307;
-	mt76_wr(dev, MT_BBP(DFS, 31), dfs_r31);
-
-	mt76_wr(dev, MT_BBP(DFS, 32), 0x00040071);
-}
-
 void mt76x2_dfs_init_params(struct mt76x02_dev *dev)
 {
 	struct cfg80211_chan_def *chandef = &dev->mt76.chandef;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c
index 5bda44540225..16ff6c376373 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c
@@ -124,96 +124,6 @@ void mt76x2_phy_set_antenna(struct mt76x02_dev *dev)
 	mt76_wr(dev, MT_BBP(AGC, 0), val);
 }
 
-static void
-mt76x2_phy_set_gain_val(struct mt76x02_dev *dev)
-{
-	u32 val;
-	u8 gain_val[2];
-
-	gain_val[0] = dev->cal.agc_gain_cur[0] - dev->cal.agc_gain_adjust;
-	gain_val[1] = dev->cal.agc_gain_cur[1] - dev->cal.agc_gain_adjust;
-
-	if (dev->mt76.chandef.width >= NL80211_CHAN_WIDTH_40)
-		val = 0x1e42 << 16;
-	else
-		val = 0x1836 << 16;
-
-	val |= 0xf8;
-
-	mt76_wr(dev, MT_BBP(AGC, 8),
-		val | FIELD_PREP(MT_BBP_AGC_GAIN, gain_val[0]));
-	mt76_wr(dev, MT_BBP(AGC, 9),
-		val | FIELD_PREP(MT_BBP_AGC_GAIN, gain_val[1]));
-
-	if (dev->mt76.chandef.chan->flags & IEEE80211_CHAN_RADAR)
-		mt76x2_dfs_adjust_agc(dev);
-}
-
-static void
-mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev)
-{
-	u8 *gain = dev->cal.agc_gain_init;
-	u8 low_gain_delta, gain_delta;
-	bool gain_change;
-	int low_gain;
-	u32 val;
-
-	dev->cal.avg_rssi_all = mt76x02_phy_get_min_avg_rssi(dev);
-
-	low_gain = (dev->cal.avg_rssi_all > mt76x02_get_rssi_gain_thresh(dev)) +
-		   (dev->cal.avg_rssi_all > mt76x02_get_low_rssi_gain_thresh(dev));
-
-	gain_change = (dev->cal.low_gain & 2) ^ (low_gain & 2);
-	dev->cal.low_gain = low_gain;
-
-	if (!gain_change) {
-		if (mt76x02_phy_adjust_vga_gain(dev))
-			mt76x2_phy_set_gain_val(dev);
-		return;
-	}
-
-	if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80) {
-		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560211);
-		val = mt76_rr(dev, MT_BBP(AGC, 26)) & ~0xf;
-		if (low_gain == 2)
-			val |= 0x3;
-		else
-			val |= 0x5;
-		mt76_wr(dev, MT_BBP(AGC, 26), val);
-	} else {
-		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560423);
-	}
-
-	if (mt76x2_has_ext_lna(dev))
-		low_gain_delta = 10;
-	else
-		low_gain_delta = 14;
-
-	if (low_gain == 2) {
-		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a990);
-		mt76_wr(dev, MT_BBP(AGC, 35), 0x08080808);
-		mt76_wr(dev, MT_BBP(AGC, 37), 0x08080808);
-		gain_delta = low_gain_delta;
-		dev->cal.agc_gain_adjust = 0;
-	} else {
-		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a991);
-		if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80)
-			mt76_wr(dev, MT_BBP(AGC, 35), 0x10101014);
-		else
-			mt76_wr(dev, MT_BBP(AGC, 35), 0x11111116);
-		mt76_wr(dev, MT_BBP(AGC, 37), 0x2121262C);
-		gain_delta = 0;
-		dev->cal.agc_gain_adjust = low_gain_delta;
-	}
-
-	dev->cal.agc_gain_cur[0] = gain[0] - gain_delta;
-	dev->cal.agc_gain_cur[1] = gain[1] - gain_delta;
-	mt76x2_phy_set_gain_val(dev);
-
-	/* clear false CCA counters */
-	mt76_rr(dev, MT_RX_STAT_1);
-}
-
 int mt76x2_phy_set_channel(struct mt76x02_dev *dev,
 			   struct cfg80211_chan_def *chandef)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
index e9fff5b7f125..0f9f54569147 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
@@ -250,3 +250,114 @@ void mt76x2_phy_tssi_compensate(struct mt76x02_dev *dev, bool wait)
 	}
 }
 EXPORT_SYMBOL_GPL(mt76x2_phy_tssi_compensate);
+
+static void mt76x2_phy_dfs_adjust_agc(struct mt76x02_dev *dev)
+{
+	u32 agc_r8, agc_r4, val_r8, val_r4, dfs_r31;
+
+	agc_r8 = mt76_rr(dev, MT_BBP(AGC, 8));
+	agc_r4 = mt76_rr(dev, MT_BBP(AGC, 4));
+
+	val_r8 = (agc_r8 & 0x00007e00) >> 9;
+	val_r4 = agc_r4 & ~0x1f000000;
+	val_r4 += (((val_r8 + 1) >> 1) << 24);
+	mt76_wr(dev, MT_BBP(AGC, 4), val_r4);
+
+	dfs_r31 = FIELD_GET(MT_BBP_AGC_LNA_HIGH_GAIN, val_r4);
+	dfs_r31 += val_r8;
+	dfs_r31 -= (agc_r8 & 0x00000038) >> 3;
+	dfs_r31 = (dfs_r31 << 16) | 0x00000307;
+	mt76_wr(dev, MT_BBP(DFS, 31), dfs_r31);
+
+	mt76_wr(dev, MT_BBP(DFS, 32), 0x00040071);
+}
+
+static void
+mt76x2_phy_set_gain_val(struct mt76x02_dev *dev)
+{
+	u32 val;
+	u8 gain_val[2];
+
+	gain_val[0] = dev->cal.agc_gain_cur[0] - dev->cal.agc_gain_adjust;
+	gain_val[1] = dev->cal.agc_gain_cur[1] - dev->cal.agc_gain_adjust;
+
+	if (dev->mt76.chandef.width >= NL80211_CHAN_WIDTH_40)
+		val = 0x1e42 << 16;
+	else
+		val = 0x1836 << 16;
+
+	val |= 0xf8;
+
+	mt76_wr(dev, MT_BBP(AGC, 8),
+		val | FIELD_PREP(MT_BBP_AGC_GAIN, gain_val[0]));
+	mt76_wr(dev, MT_BBP(AGC, 9),
+		val | FIELD_PREP(MT_BBP_AGC_GAIN, gain_val[1]));
+
+	if (dev->mt76.chandef.chan->flags & IEEE80211_CHAN_RADAR)
+		mt76x2_phy_dfs_adjust_agc(dev);
+}
+
+void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev)
+{
+	u8 *gain = dev->cal.agc_gain_init;
+	u8 low_gain_delta, gain_delta;
+	bool gain_change;
+	int low_gain;
+	u32 val;
+
+	dev->cal.avg_rssi_all = mt76x02_phy_get_min_avg_rssi(dev);
+
+	low_gain = (dev->cal.avg_rssi_all > mt76x02_get_rssi_gain_thresh(dev)) +
+		   (dev->cal.avg_rssi_all > mt76x02_get_low_rssi_gain_thresh(dev));
+
+	gain_change = (dev->cal.low_gain & 2) ^ (low_gain & 2);
+	dev->cal.low_gain = low_gain;
+
+	if (!gain_change) {
+		if (mt76x02_phy_adjust_vga_gain(dev))
+			mt76x2_phy_set_gain_val(dev);
+		return;
+	}
+
+	if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80) {
+		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560211);
+		val = mt76_rr(dev, MT_BBP(AGC, 26)) & ~0xf;
+		if (low_gain == 2)
+			val |= 0x3;
+		else
+			val |= 0x5;
+		mt76_wr(dev, MT_BBP(AGC, 26), val);
+	} else {
+		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560423);
+	}
+
+	if (mt76x2_has_ext_lna(dev))
+		low_gain_delta = 10;
+	else
+		low_gain_delta = 14;
+
+	if (low_gain == 2) {
+		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a990);
+		mt76_wr(dev, MT_BBP(AGC, 35), 0x08080808);
+		mt76_wr(dev, MT_BBP(AGC, 37), 0x08080808);
+		gain_delta = low_gain_delta;
+		dev->cal.agc_gain_adjust = 0;
+	} else {
+		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a991);
+		if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80)
+			mt76_wr(dev, MT_BBP(AGC, 35), 0x10101014);
+		else
+			mt76_wr(dev, MT_BBP(AGC, 35), 0x11111116);
+		mt76_wr(dev, MT_BBP(AGC, 37), 0x2121262C);
+		gain_delta = 0;
+		dev->cal.agc_gain_adjust = low_gain_delta;
+	}
+
+	dev->cal.agc_gain_cur[0] = gain[0] - gain_delta;
+	dev->cal.agc_gain_cur[1] = gain[1] - gain_delta;
+	mt76x2_phy_set_gain_val(dev);
+
+	/* clear false CCA counters */
+	mt76_rr(dev, MT_RX_STAT_1);
+}
+EXPORT_SYMBOL_GPL(mt76x2_phy_update_channel_gain);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
index a40aa838b6b2..d6e3e663dd8a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
@@ -29,30 +29,6 @@
 #define MT76U_MCU_DLM_OFFSET		0x110000
 #define MT76U_MCU_ROM_PATCH_OFFSET	0x90000
 
-int mt76x2u_mcu_set_dynamic_vga(struct mt76x02_dev *dev, u8 channel, bool ap,
-				bool ext, int rssi, u32 false_cca)
-{
-	struct {
-		__le32 channel;
-		__le32 rssi_val;
-		__le32 false_cca_val;
-	} __packed __aligned(4) msg = {
-		.rssi_val = cpu_to_le32(rssi),
-		.false_cca_val = cpu_to_le32(false_cca),
-	};
-	struct sk_buff *skb;
-	u32 val = channel;
-
-	if (ap)
-		val |= BIT(31);
-	if (ext)
-		val |= BIT(30);
-	msg.channel = cpu_to_le32(val);
-
-	skb = mt76_mcu_msg_alloc(dev, &msg, sizeof(msg));
-	return mt76_mcu_send_msg(dev, skb, CMD_DYNC_VGA_OP, true);
-}
-
 static void mt76x2u_mcu_load_ivb(struct mt76x02_dev *dev)
 {
 	mt76u_vendor_request(&dev->mt76, MT_VEND_DEV_MODE,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
index ca96ba60510e..8011c261c658 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
@@ -39,51 +39,13 @@ void mt76x2u_phy_channel_calibrate(struct mt76x02_dev *dev)
 	mt76x2u_mac_resume(dev);
 }
 
-static void
-mt76x2u_phy_update_channel_gain(struct mt76x02_dev *dev)
-{
-	u8 channel = dev->mt76.chandef.chan->hw_value;
-	int freq, freq1;
-	u32 false_cca;
-
-	freq = dev->mt76.chandef.chan->center_freq;
-	freq1 = dev->mt76.chandef.center_freq1;
-
-	switch (dev->mt76.chandef.width) {
-	case NL80211_CHAN_WIDTH_80: {
-		int ch_group_index;
-
-		ch_group_index = (freq - freq1 + 30) / 20;
-		if (WARN_ON(ch_group_index < 0 || ch_group_index > 3))
-			ch_group_index = 0;
-		channel += 6 - ch_group_index * 4;
-		break;
-	}
-	case NL80211_CHAN_WIDTH_40:
-		if (freq1 > freq)
-			channel += 2;
-		else
-			channel -= 2;
-		break;
-	default:
-		break;
-	}
-
-	dev->cal.avg_rssi_all = mt76x02_phy_get_min_avg_rssi(dev);
-	false_cca = FIELD_GET(MT_RX_STAT_1_CCA_ERRORS,
-			      mt76_rr(dev, MT_RX_STAT_1));
-
-	mt76x2u_mcu_set_dynamic_vga(dev, channel, false, false,
-				    dev->cal.avg_rssi_all, false_cca);
-}
-
 void mt76x2u_phy_calibrate(struct work_struct *work)
 {
 	struct mt76x02_dev *dev;
 
 	dev = container_of(work, struct mt76x02_dev, cal_work.work);
 	mt76x2_phy_tssi_compensate(dev, false);
-	mt76x2u_phy_update_channel_gain(dev);
+	mt76x2_phy_update_channel_gain(dev);
 
 	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->cal_work,
 				     MT_CALIBRATE_INTERVAL);
@@ -202,6 +164,7 @@ int mt76x2u_phy_set_channel(struct mt76x02_dev *dev,
 	if (scan)
 		return 0;
 
+	mt76x02_init_agc_gain(dev);
 	if (mt76x2_tssi_enabled(dev)) {
 		/* init default values for temp compensation */
 		mt76_rmw_field(dev, MT_TX_ALC_CFG_1, MT_TX_ALC_CFG_1_TEMP_COMP,
-- 
cgit v1.2.3


From 9c410782472e37539dff93688d205d31ad7c78ec Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sun, 14 Oct 2018 18:55:18 +0200
Subject: mt76x0: phy: use proper name convention

Use mt76x0_phy as prefix for routines in mt76x0/phy.c
Moreover use mt76x0_rf_set to enable vco calibration in
mt76x0_phy_vco_cal

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c   |   2 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |   2 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    | 222 ++++++++++-----------
 3 files changed, 113 insertions(+), 113 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index 4a9408801260..d7d4dfbbd04d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -113,7 +113,7 @@ static int mt76x0_init_bbp(struct mt76x02_dev *dev)
 {
 	int ret, i;
 
-	ret = mt76x0_wait_bbp_ready(dev);
+	ret = mt76x0_phy_wait_bbp_ready(dev);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 2187bafaf2e9..f27335ccb582 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -65,7 +65,7 @@ int mt76x0_set_rts_threshold(struct ieee80211_hw *hw, u32 value);
 
 /* PHY */
 void mt76x0_phy_init(struct mt76x02_dev *dev);
-int mt76x0_wait_bbp_ready(struct mt76x02_dev *dev);
+int mt76x0_phy_wait_bbp_ready(struct mt76x02_dev *dev);
 int mt76x0_phy_set_channel(struct mt76x02_dev *dev,
 			    struct cfg80211_chan_def *chandef);
 void mt76x0_phy_recalibrate_after_assoc(struct mt76x02_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index cf024950e0ed..b1bf990148d4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -110,7 +110,7 @@ out:
 }
 
 static int
-rf_wr(struct mt76x02_dev *dev, u32 offset, u8 val)
+mt76x0_rf_wr(struct mt76x02_dev *dev, u32 offset, u8 val)
 {
 	if (mt76_is_usb(dev)) {
 		struct mt76_reg_pair pair = {
@@ -126,8 +126,7 @@ rf_wr(struct mt76x02_dev *dev, u32 offset, u8 val)
 	}
 }
 
-static int
-rf_rr(struct mt76x02_dev *dev, u32 offset)
+static int mt76x0_rf_rr(struct mt76x02_dev *dev, u32 offset)
 {
 	int ret;
 	u32 val;
@@ -149,38 +148,38 @@ rf_rr(struct mt76x02_dev *dev, u32 offset)
 }
 
 static int
-rf_rmw(struct mt76x02_dev *dev, u32 offset, u8 mask, u8 val)
+mt76x0_rf_rmw(struct mt76x02_dev *dev, u32 offset, u8 mask, u8 val)
 {
 	int ret;
 
-	ret = rf_rr(dev, offset);
+	ret = mt76x0_rf_rr(dev, offset);
 	if (ret < 0)
 		return ret;
+
 	val |= ret & ~mask;
-	ret = rf_wr(dev, offset, val);
-	if (ret)
-		return ret;
 
-	return val;
+	ret = mt76x0_rf_wr(dev, offset, val);
+	return ret ? ret : val;
 }
 
 static int
-rf_set(struct mt76x02_dev *dev, u32 offset, u8 val)
+mt76x0_rf_set(struct mt76x02_dev *dev, u32 offset, u8 val)
 {
-	return rf_rmw(dev, offset, 0, val);
+	return mt76x0_rf_rmw(dev, offset, 0, val);
 }
 
 #if 0
 static int
 rf_clear(struct mt76x02_dev *dev, u32 offset, u8 mask)
 {
-	return rf_rmw(dev, offset, mask, 0);
+	return mt76x0_rf_rmw(dev, offset, mask, 0);
 }
 #endif
 
 static void
-mt76x0_rf_csr_wr_rp(struct mt76x02_dev *dev, const struct mt76_reg_pair *data,
-		    int n)
+mt76x0_phy_rf_csr_wr_rp(struct mt76x02_dev *dev,
+			const struct mt76_reg_pair *data,
+			int n)
 {
 	while (n-- > 0) {
 		mt76x0_rf_csr_wr(dev, data->reg, data->value);
@@ -190,12 +189,12 @@ mt76x0_rf_csr_wr_rp(struct mt76x02_dev *dev, const struct mt76_reg_pair *data,
 
 #define RF_RANDOM_WRITE(dev, tab) do {					\
 	if (mt76_is_mmio(dev))						\
-		mt76x0_rf_csr_wr_rp(dev, tab, ARRAY_SIZE(tab));		\
+		mt76x0_phy_rf_csr_wr_rp(dev, tab, ARRAY_SIZE(tab));	\
 	else								\
 		mt76_wr_rp(dev, MT_MCU_MEMMAP_RF, tab, ARRAY_SIZE(tab));\
 } while (0)
 
-int mt76x0_wait_bbp_ready(struct mt76x02_dev *dev)
+int mt76x0_phy_wait_bbp_ready(struct mt76x02_dev *dev)
 {
 	int i = 20;
 	u32 val;
@@ -215,11 +214,11 @@ int mt76x0_wait_bbp_ready(struct mt76x02_dev *dev)
 	return 0;
 }
 
-static void mt76x0_vco_cal(struct mt76x02_dev *dev, u8 channel)
+static void mt76x0_phy_vco_cal(struct mt76x02_dev *dev, u8 channel)
 {
 	u8 val;
 
-	val = rf_rr(dev, MT_RF(0, 4));
+	val = mt76x0_rf_rr(dev, MT_RF(0, 4));
 	if ((val & 0x70) != 0x30)
 		return;
 
@@ -235,20 +234,20 @@ static void mt76x0_vco_cal(struct mt76x02_dev *dev, u8 channel)
 	 *  40MHz channel: 101
 	 *  20MHz channel: 100
 	 */
-	val = rf_rr(dev, MT_RF(0, 6));
+	val = mt76x0_rf_rr(dev, MT_RF(0, 6));
 	val &= ~0xf;
 	val |= 0x09;
-	rf_wr(dev, MT_RF(0, 6), val);
+	mt76x0_rf_wr(dev, MT_RF(0, 6), val);
 
-	val = rf_rr(dev, MT_RF(0, 5));
+	val = mt76x0_rf_rr(dev, MT_RF(0, 5));
 	if (val != 0)
-		rf_wr(dev, MT_RF(0, 5), 0x0);
+		mt76x0_rf_wr(dev, MT_RF(0, 5), 0x0);
 
-	val = rf_rr(dev, MT_RF(0, 4));
+	val = mt76x0_rf_rr(dev, MT_RF(0, 4));
 	val &= ~0x07;
-	rf_wr(dev, MT_RF(0, 4), val);
+	mt76x0_rf_wr(dev, MT_RF(0, 4), val);
 
-	val = rf_rr(dev, MT_RF(0, 3));
+	val = mt76x0_rf_rr(dev, MT_RF(0, 3));
 	val &= ~0x77;
 	if (channel == 1 || channel == 7 || channel == 9 || channel >= 13) {
 		val |= 0x63;
@@ -261,12 +260,9 @@ static void mt76x0_vco_cal(struct mt76x02_dev *dev, u8 channel)
 		WARN(1, "Unknown channel %u\n", channel);
 		return;
 	}
-	rf_wr(dev, MT_RF(0, 3), val);
+	mt76x0_rf_wr(dev, MT_RF(0, 3), val);
 
-	/* TODO replace by mt76x0_rf_set(dev, MT_RF(0, 4), BIT(7)); */
-	val = rf_rr(dev, MT_RF(0, 4));
-	val = ((val & ~(0x80)) | 0x80);
-	rf_wr(dev, MT_RF(0, 4), val);
+	mt76x0_rf_set(dev, MT_RF(0, 4), BIT(7));
 
 	msleep(2);
 }
@@ -278,8 +274,8 @@ mt76x0_phy_set_band(struct mt76x02_dev *dev, enum nl80211_band band)
 	case NL80211_BAND_2GHZ:
 		RF_RANDOM_WRITE(dev, mt76x0_rf_2g_channel_0_tab);
 
-		rf_wr(dev, MT_RF(5, 0), 0x45);
-		rf_wr(dev, MT_RF(6, 0), 0x44);
+		mt76x0_rf_wr(dev, MT_RF(5, 0), 0x45);
+		mt76x0_rf_wr(dev, MT_RF(6, 0), 0x44);
 
 		mt76_wr(dev, MT_TX_ALC_VGA3, 0x00050007);
 		mt76_wr(dev, MT_TX0_RF_GAIN_CORR, 0x003E0002);
@@ -287,8 +283,8 @@ mt76x0_phy_set_band(struct mt76x02_dev *dev, enum nl80211_band band)
 	case NL80211_BAND_5GHZ:
 		RF_RANDOM_WRITE(dev, mt76x0_rf_5g_channel_0_tab);
 
-		rf_wr(dev, MT_RF(5, 0), 0x44);
-		rf_wr(dev, MT_RF(6, 0), 0x45);
+		mt76x0_rf_wr(dev, MT_RF(5, 0), 0x44);
+		mt76x0_rf_wr(dev, MT_RF(6, 0), 0x45);
 
 		mt76_wr(dev, MT_TX_ALC_VGA3, 0x00000005);
 		mt76_wr(dev, MT_TX0_RF_GAIN_CORR, 0x01010102);
@@ -326,103 +322,103 @@ mt76x0_phy_set_chan_rf_params(struct mt76x02_dev *dev, u8 channel, u16 rf_bw_ban
 			else
 				freq_item = &(mt76x0_frequency_plan[i]);
 
-			rf_wr(dev, MT_RF(0, 37), freq_item->pllR37);
-			rf_wr(dev, MT_RF(0, 36), freq_item->pllR36);
-			rf_wr(dev, MT_RF(0, 35), freq_item->pllR35);
-			rf_wr(dev, MT_RF(0, 34), freq_item->pllR34);
-			rf_wr(dev, MT_RF(0, 33), freq_item->pllR33);
+			mt76x0_rf_wr(dev, MT_RF(0, 37), freq_item->pllR37);
+			mt76x0_rf_wr(dev, MT_RF(0, 36), freq_item->pllR36);
+			mt76x0_rf_wr(dev, MT_RF(0, 35), freq_item->pllR35);
+			mt76x0_rf_wr(dev, MT_RF(0, 34), freq_item->pllR34);
+			mt76x0_rf_wr(dev, MT_RF(0, 33), freq_item->pllR33);
 
-			rf_val = rf_rr(dev, MT_RF(0, 32));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 32));
 			rf_val &= ~0xE0;
 			rf_val |= freq_item->pllR32_b7b5;
-			rf_wr(dev, MT_RF(0, 32), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 32), rf_val);
 
 			/* R32<4:0> pll_den: (Denomina - 8) */
-			rf_val = rf_rr(dev, MT_RF(0, 32));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 32));
 			rf_val &= ~0x1F;
 			rf_val |= freq_item->pllR32_b4b0;
-			rf_wr(dev, MT_RF(0, 32), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 32), rf_val);
 
 			/* R31<7:5> */
-			rf_val = rf_rr(dev, MT_RF(0, 31));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 31));
 			rf_val &= ~0xE0;
 			rf_val |= freq_item->pllR31_b7b5;
-			rf_wr(dev, MT_RF(0, 31), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 31), rf_val);
 
 			/* R31<4:0> pll_k(Nominator) */
-			rf_val = rf_rr(dev, MT_RF(0, 31));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 31));
 			rf_val &= ~0x1F;
 			rf_val |= freq_item->pllR31_b4b0;
-			rf_wr(dev, MT_RF(0, 31), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 31), rf_val);
 
 			/* R30<7> sdm_reset_n */
-			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 30));
 			rf_val &= ~0x80;
 			if (bSDM) {
-				rf_wr(dev, MT_RF(0, 30), rf_val);
+				mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
 				rf_val |= 0x80;
-				rf_wr(dev, MT_RF(0, 30), rf_val);
+				mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
 			} else {
 				rf_val |= freq_item->pllR30_b7;
-				rf_wr(dev, MT_RF(0, 30), rf_val);
+				mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
 			}
 
 			/* R30<6:2> sdmmash_prbs,sin */
-			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 30));
 			rf_val &= ~0x7C;
 			rf_val |= freq_item->pllR30_b6b2;
-			rf_wr(dev, MT_RF(0, 30), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
 
 			/* R30<1> sdm_bp */
-			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 30));
 			rf_val &= ~0x02;
 			rf_val |= (freq_item->pllR30_b1 << 1);
-			rf_wr(dev, MT_RF(0, 30), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
 
 			/* R30<0> R29<7:0> (hex) pll_n */
 			rf_val = freq_item->pll_n & 0x00FF;
-			rf_wr(dev, MT_RF(0, 29), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 29), rf_val);
 
-			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 30));
 			rf_val &= ~0x1;
 			rf_val |= ((freq_item->pll_n >> 8) & 0x0001);
-			rf_wr(dev, MT_RF(0, 30), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
 
 			/* R28<7:6> isi_iso */
-			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 28));
 			rf_val &= ~0xC0;
 			rf_val |= freq_item->pllR28_b7b6;
-			rf_wr(dev, MT_RF(0, 28), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 28), rf_val);
 
 			/* R28<5:4> pfd_dly */
-			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 28));
 			rf_val &= ~0x30;
 			rf_val |= freq_item->pllR28_b5b4;
-			rf_wr(dev, MT_RF(0, 28), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 28), rf_val);
 
 			/* R28<3:2> clksel option */
-			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 28));
 			rf_val &= ~0x0C;
 			rf_val |= freq_item->pllR28_b3b2;
-			rf_wr(dev, MT_RF(0, 28), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 28), rf_val);
 
 			/* R28<1:0> R27<7:0> R26<7:0> (hex) sdm_k */
 			rf_val = freq_item->pll_sdm_k & 0x000000FF;
-			rf_wr(dev, MT_RF(0, 26), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 26), rf_val);
 
 			rf_val = ((freq_item->pll_sdm_k >> 8) & 0x000000FF);
-			rf_wr(dev, MT_RF(0, 27), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 27), rf_val);
 
-			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 28));
 			rf_val &= ~0x3;
 			rf_val |= ((freq_item->pll_sdm_k >> 16) & 0x0003);
-			rf_wr(dev, MT_RF(0, 28), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 28), rf_val);
 
 			/* R24<1:0> xo_div */
-			rf_val = rf_rr(dev, MT_RF(0, 24));
+			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 24));
 			rf_val &= ~0x3;
 			rf_val |= freq_item->pllR24_b1b0;
-			rf_wr(dev, MT_RF(0, 24), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 24), rf_val);
 
 			break;
 		}
@@ -430,19 +426,22 @@ mt76x0_phy_set_chan_rf_params(struct mt76x02_dev *dev, u8 channel, u16 rf_bw_ban
 
 	for (i = 0; i < ARRAY_SIZE(mt76x0_rf_bw_switch_tab); i++) {
 		if (rf_bw == mt76x0_rf_bw_switch_tab[i].bw_band) {
-			rf_wr(dev, mt76x0_rf_bw_switch_tab[i].rf_bank_reg,
-				   mt76x0_rf_bw_switch_tab[i].value);
+			mt76x0_rf_wr(dev,
+				     mt76x0_rf_bw_switch_tab[i].rf_bank_reg,
+				     mt76x0_rf_bw_switch_tab[i].value);
 		} else if ((rf_bw == (mt76x0_rf_bw_switch_tab[i].bw_band & 0xFF)) &&
 			   (rf_band & mt76x0_rf_bw_switch_tab[i].bw_band)) {
-			rf_wr(dev, mt76x0_rf_bw_switch_tab[i].rf_bank_reg,
-				   mt76x0_rf_bw_switch_tab[i].value);
+			mt76x0_rf_wr(dev,
+				     mt76x0_rf_bw_switch_tab[i].rf_bank_reg,
+				     mt76x0_rf_bw_switch_tab[i].value);
 		}
 	}
 
 	for (i = 0; i < ARRAY_SIZE(mt76x0_rf_band_switch_tab); i++) {
 		if (mt76x0_rf_band_switch_tab[i].bw_band & rf_band) {
-			rf_wr(dev, mt76x0_rf_band_switch_tab[i].rf_bank_reg,
-				   mt76x0_rf_band_switch_tab[i].value);
+			mt76x0_rf_wr(dev,
+				     mt76x0_rf_band_switch_tab[i].rf_bank_reg,
+				     mt76x0_rf_band_switch_tab[i].value);
 		}
 	}
 
@@ -470,8 +469,9 @@ mt76x0_phy_set_chan_rf_params(struct mt76x02_dev *dev, u8 channel, u16 rf_bw_ban
 		/* External PA */
 		for (i = 0; i < ARRAY_SIZE(mt76x0_rf_ext_pa_tab); i++)
 			if (mt76x0_rf_ext_pa_tab[i].bw_band & rf_band)
-				rf_wr(dev, mt76x0_rf_ext_pa_tab[i].rf_bank_reg,
-					   mt76x0_rf_ext_pa_tab[i].value);
+				mt76x0_rf_wr(dev,
+					mt76x0_rf_ext_pa_tab[i].rf_bank_reg,
+					mt76x0_rf_ext_pa_tab[i].value);
 	}
 
 	if (rf_band & RF_G_BAND) {
@@ -516,7 +516,7 @@ mt76x0_phy_set_chan_bbp_params(struct mt76x02_dev *dev, u16 rf_bw_band)
 	}
 }
 
-static void mt76x0_ant_select(struct mt76x02_dev *dev)
+static void mt76x0_phy_ant_select(struct mt76x02_dev *dev)
 {
 	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
 
@@ -536,7 +536,7 @@ static void mt76x0_ant_select(struct mt76x02_dev *dev)
 }
 
 static void
-mt76x0_bbp_set_bw(struct mt76x02_dev *dev, enum nl80211_chan_width width)
+mt76x0_phy_bbp_set_bw(struct mt76x02_dev *dev, enum nl80211_chan_width width)
 {
 	enum { BW_20 = 0, BW_40 = 1, BW_80 = 2, BW_10 = 4};
 	int bw;
@@ -684,7 +684,7 @@ int mt76x0_phy_set_channel(struct mt76x02_dev *dev,
 	}
 
 	if (mt76_is_usb(dev)) {
-		mt76x0_bbp_set_bw(dev, chandef->width);
+		mt76x0_phy_bbp_set_bw(dev, chandef->width);
 	} else {
 		if (chandef->width == NL80211_CHAN_WIDTH_80 ||
 		    chandef->width == NL80211_CHAN_WIDTH_40)
@@ -696,7 +696,7 @@ int mt76x0_phy_set_channel(struct mt76x02_dev *dev,
 	mt76x02_phy_set_bw(dev, chandef->width, ch_group_index);
 	mt76x02_phy_set_band(dev, chandef->chan->band,
 			     ch_group_index & 1);
-	mt76x0_ant_select(dev);
+	mt76x0_phy_ant_select(dev);
 
 	mt76_rmw(dev, MT_EXT_CCA_CFG,
 		 (MT_EXT_CCA_CFG_CCA0 |
@@ -722,10 +722,10 @@ int mt76x0_phy_set_channel(struct mt76x02_dev *dev,
 	mt76x02_init_agc_gain(dev);
 
 	if (mt76_is_usb(dev)) {
-		mt76x0_vco_cal(dev, channel);
+		mt76x0_phy_vco_cal(dev, channel);
 	} else {
 		/* enable vco */
-		rf_set(dev, MT_RF(0, 4), BIT(7));
+		mt76x0_rf_set(dev, MT_RF(0, 4), BIT(7));
 	}
 
 	if (scan)
@@ -749,7 +749,7 @@ void mt76x0_phy_recalibrate_after_assoc(struct mt76x02_dev *dev)
 
 	mt76x02_mcu_calibrate(dev, MCU_CAL_R, 0, false);
 
-	mt76x0_vco_cal(dev, channel);
+	mt76x0_phy_vco_cal(dev, channel);
 
 	tx_alc = mt76_rr(dev, MT_TX_ALC_CFG_0);
 	mt76_wr(dev, MT_TX_ALC_CFG_0, 0);
@@ -774,18 +774,18 @@ void mt76x0_phy_recalibrate_after_assoc(struct mt76x02_dev *dev)
 	mt76x02_mcu_calibrate(dev, MCU_CAL_RXDCOC, 1, false);
 }
 
-static void mt76x0_temp_sensor(struct mt76x02_dev *dev)
+static void mt76x0_phy_temp_sensor(struct mt76x02_dev *dev)
 {
 	u8 rf_b7_73, rf_b0_66, rf_b0_67;
 	s8 val;
 
-	rf_b7_73 = rf_rr(dev, MT_RF(7, 73));
-	rf_b0_66 = rf_rr(dev, MT_RF(0, 66));
-	rf_b0_67 = rf_rr(dev, MT_RF(0, 67));
+	rf_b7_73 = mt76x0_rf_rr(dev, MT_RF(7, 73));
+	rf_b0_66 = mt76x0_rf_rr(dev, MT_RF(0, 66));
+	rf_b0_67 = mt76x0_rf_rr(dev, MT_RF(0, 67));
 
-	rf_wr(dev, MT_RF(7, 73), 0x02);
-	rf_wr(dev, MT_RF(0, 66), 0x23);
-	rf_wr(dev, MT_RF(0, 67), 0x01);
+	mt76x0_rf_wr(dev, MT_RF(7, 73), 0x02);
+	mt76x0_rf_wr(dev, MT_RF(0, 66), 0x23);
+	mt76x0_rf_wr(dev, MT_RF(0, 67), 0x01);
 
 	mt76_wr(dev, MT_BBP(CORE, 34), 0x00080055);
 
@@ -809,9 +809,9 @@ static void mt76x0_temp_sensor(struct mt76x02_dev *dev)
 	}
 
 done:
-	rf_wr(dev, MT_RF(7, 73), rf_b7_73);
-	rf_wr(dev, MT_RF(0, 66), rf_b0_66);
-	rf_wr(dev, MT_RF(0, 67), rf_b0_67);
+	mt76x0_rf_wr(dev, MT_RF(7, 73), rf_b7_73);
+	mt76x0_rf_wr(dev, MT_RF(0, 66), rf_b0_66);
+	mt76x0_rf_wr(dev, MT_RF(0, 67), rf_b0_67);
 }
 
 static void mt76x0_phy_set_gain_val(struct mt76x02_dev *dev)
@@ -861,13 +861,13 @@ static void mt76x0_phy_calibration_work(struct work_struct *work)
 
 	mt76x0_phy_update_channel_gain(dev);
 	if (!mt76x0_tssi_enabled(dev))
-		mt76x0_temp_sensor(dev);
+		mt76x0_phy_temp_sensor(dev);
 
 	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->cal_work,
 				     MT_CALIBRATE_INTERVAL);
 }
 
-static void mt76x0_rf_init(struct mt76x02_dev *dev)
+static void mt76x0_phy_rf_init(struct mt76x02_dev *dev)
 {
 	int i;
 	u8 val;
@@ -881,16 +881,16 @@ static void mt76x0_rf_init(struct mt76x02_dev *dev)
 		const struct mt76x0_rf_switch_item *item = &mt76x0_rf_bw_switch_tab[i];
 
 		if (item->bw_band == RF_BW_20)
-			rf_wr(dev, item->rf_bank_reg, item->value);
+			mt76x0_rf_wr(dev, item->rf_bank_reg, item->value);
 		else if (((RF_G_BAND | RF_BW_20) & item->bw_band) == (RF_G_BAND | RF_BW_20))
-			rf_wr(dev, item->rf_bank_reg, item->value);
+			mt76x0_rf_wr(dev, item->rf_bank_reg, item->value);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(mt76x0_rf_band_switch_tab); i++) {
 		if (mt76x0_rf_band_switch_tab[i].bw_band & RF_G_BAND) {
-			rf_wr(dev,
-			      mt76x0_rf_band_switch_tab[i].rf_bank_reg,
-			      mt76x0_rf_band_switch_tab[i].value);
+			mt76x0_rf_wr(dev,
+				     mt76x0_rf_band_switch_tab[i].rf_bank_reg,
+				     mt76x0_rf_band_switch_tab[i].value);
 		}
 	}
 
@@ -899,32 +899,32 @@ static void mt76x0_rf_init(struct mt76x02_dev *dev)
 	   E1: B0.R22<6:0>: xo_cxo<6:0>
 	   E2: B0.R21<0>: xo_cxo<0>, B0.R22<7:0>: xo_cxo<8:1>
 	 */
-	rf_wr(dev, MT_RF(0, 22),
-	      min_t(u8, dev->cal.rx.freq_offset, 0xbf));
-	val = rf_rr(dev, MT_RF(0, 22));
+	mt76x0_rf_wr(dev, MT_RF(0, 22),
+		     min_t(u8, dev->cal.rx.freq_offset, 0xbf));
+	val = mt76x0_rf_rr(dev, MT_RF(0, 22));
 
 	/*
 	   Reset the DAC (Set B0.R73<7>=1, then set B0.R73<7>=0, and then set B0.R73<7>) during power up.
 	 */
-	val = rf_rr(dev, MT_RF(0, 73));
+	val = mt76x0_rf_rr(dev, MT_RF(0, 73));
 	val |= 0x80;
-	rf_wr(dev, MT_RF(0, 73), val);
+	mt76x0_rf_wr(dev, MT_RF(0, 73), val);
 	val &= ~0x80;
-	rf_wr(dev, MT_RF(0, 73), val);
+	mt76x0_rf_wr(dev, MT_RF(0, 73), val);
 	val |= 0x80;
-	rf_wr(dev, MT_RF(0, 73), val);
+	mt76x0_rf_wr(dev, MT_RF(0, 73), val);
 
 	/*
 	   vcocal_en (initiate VCO calibration (reset after completion)) - It should be at the end of RF configuration.
 	 */
-	rf_set(dev, MT_RF(0, 4), 0x80);
+	mt76x0_rf_set(dev, MT_RF(0, 4), 0x80);
 }
 
 void mt76x0_phy_init(struct mt76x02_dev *dev)
 {
 	INIT_DELAYED_WORK(&dev->cal_work, mt76x0_phy_calibration_work);
 
-	mt76x0_rf_init(dev);
+	mt76x0_phy_rf_init(dev);
 	mt76x02_phy_set_rxpath(dev);
 	mt76x02_phy_set_txdac(dev);
 }
-- 
cgit v1.2.3


From d3caa060e1718928d1514caf81a6312d2f2a9369 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sun, 14 Oct 2018 18:55:19 +0200
Subject: mt76x0: phy: simplify rf configuration routines

Simplify mt76x0_phy_vco_cal and mt76x0_phy_set_chan_rf_params
routines using mt76x0_rf_wr, mt76x0_rf_set and mt76x0_rf_clear
helper routines. Moreover over get rid of magic numbers

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c | 233 +++++++++---------------
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.h |  17 ++
 2 files changed, 106 insertions(+), 144 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index b1bf990148d4..53927547cf12 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -49,11 +49,11 @@ mt76x0_rf_csr_wr(struct mt76x02_dev *dev, u32 offset, u8 value)
 	}
 
 	mt76_wr(dev, MT_RF_CSR_CFG,
-		   FIELD_PREP(MT_RF_CSR_CFG_DATA, value) |
-		   FIELD_PREP(MT_RF_CSR_CFG_REG_BANK, bank) |
-		   FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
-		   MT_RF_CSR_CFG_WR |
-		   MT_RF_CSR_CFG_KICK);
+		FIELD_PREP(MT_RF_CSR_CFG_DATA, value) |
+		FIELD_PREP(MT_RF_CSR_CFG_REG_BANK, bank) |
+		FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
+		MT_RF_CSR_CFG_WR |
+		MT_RF_CSR_CFG_KICK);
 	trace_mt76x0_rf_write(&dev->mt76, bank, offset, value);
 out:
 	mutex_unlock(&dev->phy_mutex);
@@ -86,9 +86,9 @@ static int mt76x0_rf_csr_rr(struct mt76x02_dev *dev, u32 offset)
 		goto out;
 
 	mt76_wr(dev, MT_RF_CSR_CFG,
-		   FIELD_PREP(MT_RF_CSR_CFG_REG_BANK, bank) |
-		   FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
-		   MT_RF_CSR_CFG_KICK);
+		FIELD_PREP(MT_RF_CSR_CFG_REG_BANK, bank) |
+		FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
+		MT_RF_CSR_CFG_KICK);
 
 	if (!mt76_poll(dev, MT_RF_CSR_CFG, MT_RF_CSR_CFG_KICK, 0, 100))
 		goto out;
@@ -168,13 +168,11 @@ mt76x0_rf_set(struct mt76x02_dev *dev, u32 offset, u8 val)
 	return mt76x0_rf_rmw(dev, offset, 0, val);
 }
 
-#if 0
 static int
-rf_clear(struct mt76x02_dev *dev, u32 offset, u8 mask)
+mt76x0_rf_clear(struct mt76x02_dev *dev, u32 offset, u8 mask)
 {
 	return mt76x0_rf_rmw(dev, offset, mask, 0);
 }
-#endif
 
 static void
 mt76x0_phy_rf_csr_wr_rp(struct mt76x02_dev *dev,
@@ -222,46 +220,31 @@ static void mt76x0_phy_vco_cal(struct mt76x02_dev *dev, u8 channel)
 	if ((val & 0x70) != 0x30)
 		return;
 
-	/*
-	 * Calibration Mode - Open loop, closed loop, and amplitude:
-	 * B0.R06.[0]: 1
-	 * B0.R06.[3:1] bp_close_code: 100
-	 * B0.R05.[7:0] bp_open_code: 0x0
-	 * B0.R04.[2:0] cal_bits: 000
-	 * B0.R03.[2:0] startup_time: 011
-	 * B0.R03.[6:4] settle_time:
-	 *  80MHz channel: 110
-	 *  40MHz channel: 101
-	 *  20MHz channel: 100
-	 */
-	val = mt76x0_rf_rr(dev, MT_RF(0, 6));
-	val &= ~0xf;
-	val |= 0x09;
-	mt76x0_rf_wr(dev, MT_RF(0, 6), val);
+	/* closed loop calibarion - B0.R06.[3:0]: 1001 */
+	mt76x0_rf_rmw(dev, MT_RF(0, 6), MT_RF_VCO_BP_CLOSE_LOOP_MASK,
+		      MT_RF_VCO_BP_CLOSE_LOOP | BIT(0));
 
-	val = mt76x0_rf_rr(dev, MT_RF(0, 5));
-	if (val != 0)
-		mt76x0_rf_wr(dev, MT_RF(0, 5), 0x0);
+	/* open loop calibration - B0.R05.[7:0]: 0x0 */
+	mt76x0_rf_wr(dev, MT_RF(0, 5), 0x0);
 
-	val = mt76x0_rf_rr(dev, MT_RF(0, 4));
-	val &= ~0x07;
-	mt76x0_rf_wr(dev, MT_RF(0, 4), val);
-
-	val = mt76x0_rf_rr(dev, MT_RF(0, 3));
-	val &= ~0x77;
-	if (channel == 1 || channel == 7 || channel == 9 || channel >= 13) {
-		val |= 0x63;
-	} else if (channel == 3 || channel == 4 || channel == 10) {
-		val |= 0x53;
-	} else if (channel == 2 || channel == 5 || channel == 6 ||
-		   channel == 8 || channel == 11 || channel == 12) {
-		val |= 0x43;
-	} else {
-		WARN(1, "Unknown channel %u\n", channel);
-		return;
-	}
-	mt76x0_rf_wr(dev, MT_RF(0, 3), val);
+	/* caliration mask - B0.R04.[2:0]: 000 */
+	mt76x0_rf_clear(dev, MT_RF(0, 4), MT_RF_VCO_CAL_MASK);
+
+	/* startup time - B0.R03.[2:0] startup_time: 011 */
+	mt76x0_rf_rmw(dev, MT_RF(0, 3), MT_RF_START_TIME_MASK,
+		      MT_RF_START_TIME);
+
+	/* settle_time - B0.R03.[6:4] */
+	if (channel == 3 || channel == 4 || channel == 10)
+		val = 0x50;
+	else if (channel == 2 || channel == 5 || channel == 6 ||
+		 channel == 8 || channel == 11 || channel == 12)
+		val = 0x40;
+	else
+		val = 0x60;
+	mt76x0_rf_rmw(dev, MT_RF(0, 3), MT_RF_SETTLE_TIME_MASK, val);
 
+	/* enable vco */
 	mt76x0_rf_set(dev, MT_RF(0, 4), BIT(7));
 
 	msleep(2);
@@ -297,18 +280,17 @@ mt76x0_phy_set_band(struct mt76x02_dev *dev, enum nl80211_band band)
 static void
 mt76x0_phy_set_chan_rf_params(struct mt76x02_dev *dev, u8 channel, u16 rf_bw_band)
 {
+	const struct mt76x0_freq_item *freq_item;
 	u16 rf_band = rf_bw_band & 0xff00;
 	u16 rf_bw = rf_bw_band & 0x00ff;
 	enum nl80211_band band;
+	bool b_sdm = false;
 	u32 mac_reg;
-	u8 rf_val;
 	int i;
-	bool bSDM = false;
-	const struct mt76x0_freq_item *freq_item;
 
 	for (i = 0; i < ARRAY_SIZE(mt76x0_sdm_channel); i++) {
 		if (channel == mt76x0_sdm_channel[i]) {
-			bSDM = true;
+			b_sdm = true;
 			break;
 		}
 	}
@@ -317,7 +299,7 @@ mt76x0_phy_set_chan_rf_params(struct mt76x02_dev *dev, u8 channel, u16 rf_bw_ban
 		if (channel == mt76x0_frequency_plan[i].channel) {
 			rf_band = mt76x0_frequency_plan[i].band;
 
-			if (bSDM)
+			if (b_sdm)
 				freq_item = &(mt76x0_sdm_frequency_plan[i]);
 			else
 				freq_item = &(mt76x0_frequency_plan[i]);
@@ -328,97 +310,73 @@ mt76x0_phy_set_chan_rf_params(struct mt76x02_dev *dev, u8 channel, u16 rf_bw_ban
 			mt76x0_rf_wr(dev, MT_RF(0, 34), freq_item->pllR34);
 			mt76x0_rf_wr(dev, MT_RF(0, 33), freq_item->pllR33);
 
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 32));
-			rf_val &= ~0xE0;
-			rf_val |= freq_item->pllR32_b7b5;
-			mt76x0_rf_wr(dev, MT_RF(0, 32), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 32), 0xe0,
+				      freq_item->pllR32_b7b5);
 
 			/* R32<4:0> pll_den: (Denomina - 8) */
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 32));
-			rf_val &= ~0x1F;
-			rf_val |= freq_item->pllR32_b4b0;
-			mt76x0_rf_wr(dev, MT_RF(0, 32), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 32), MT_RF_PLL_DEN_MASK,
+				      freq_item->pllR32_b4b0);
 
 			/* R31<7:5> */
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 31));
-			rf_val &= ~0xE0;
-			rf_val |= freq_item->pllR31_b7b5;
-			mt76x0_rf_wr(dev, MT_RF(0, 31), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 31), 0xe0,
+				      freq_item->pllR31_b7b5);
 
 			/* R31<4:0> pll_k(Nominator) */
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 31));
-			rf_val &= ~0x1F;
-			rf_val |= freq_item->pllR31_b4b0;
-			mt76x0_rf_wr(dev, MT_RF(0, 31), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 31), MT_RF_PLL_K_MASK,
+				      freq_item->pllR31_b4b0);
 
 			/* R30<7> sdm_reset_n */
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 30));
-			rf_val &= ~0x80;
-			if (bSDM) {
-				mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
-				rf_val |= 0x80;
-				mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
+			if (b_sdm) {
+				mt76x0_rf_clear(dev, MT_RF(0, 30),
+						MT_RF_SDM_RESET_MASK);
+				mt76x0_rf_set(dev, MT_RF(0, 30),
+					      MT_RF_SDM_RESET_MASK);
 			} else {
-				rf_val |= freq_item->pllR30_b7;
-				mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
+				mt76x0_rf_rmw(dev, MT_RF(0, 30),
+					      MT_RF_SDM_RESET_MASK,
+					      freq_item->pllR30_b7);
 			}
 
 			/* R30<6:2> sdmmash_prbs,sin */
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 30));
-			rf_val &= ~0x7C;
-			rf_val |= freq_item->pllR30_b6b2;
-			mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 30),
+				      MT_RF_SDM_MASH_PRBS_MASK,
+				      freq_item->pllR30_b6b2);
 
 			/* R30<1> sdm_bp */
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 30));
-			rf_val &= ~0x02;
-			rf_val |= (freq_item->pllR30_b1 << 1);
-			mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 30), MT_RF_SDM_BP_MASK,
+				      freq_item->pllR30_b1 << 1);
 
 			/* R30<0> R29<7:0> (hex) pll_n */
-			rf_val = freq_item->pll_n & 0x00FF;
-			mt76x0_rf_wr(dev, MT_RF(0, 29), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 29),
+				     freq_item->pll_n & 0xff);
 
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 30));
-			rf_val &= ~0x1;
-			rf_val |= ((freq_item->pll_n >> 8) & 0x0001);
-			mt76x0_rf_wr(dev, MT_RF(0, 30), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 30), 0x1,
+				      (freq_item->pll_n >> 8) & 0x1);
 
 			/* R28<7:6> isi_iso */
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 28));
-			rf_val &= ~0xC0;
-			rf_val |= freq_item->pllR28_b7b6;
-			mt76x0_rf_wr(dev, MT_RF(0, 28), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 28), MT_RF_ISI_ISO_MASK,
+				      freq_item->pllR28_b7b6);
 
 			/* R28<5:4> pfd_dly */
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 28));
-			rf_val &= ~0x30;
-			rf_val |= freq_item->pllR28_b5b4;
-			mt76x0_rf_wr(dev, MT_RF(0, 28), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 28), MT_RF_PFD_DLY_MASK,
+				      freq_item->pllR28_b5b4);
 
 			/* R28<3:2> clksel option */
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 28));
-			rf_val &= ~0x0C;
-			rf_val |= freq_item->pllR28_b3b2;
-			mt76x0_rf_wr(dev, MT_RF(0, 28), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 28), MT_RF_CLK_SEL_MASK,
+				      freq_item->pllR28_b3b2);
 
 			/* R28<1:0> R27<7:0> R26<7:0> (hex) sdm_k */
-			rf_val = freq_item->pll_sdm_k & 0x000000FF;
-			mt76x0_rf_wr(dev, MT_RF(0, 26), rf_val);
-
-			rf_val = ((freq_item->pll_sdm_k >> 8) & 0x000000FF);
-			mt76x0_rf_wr(dev, MT_RF(0, 27), rf_val);
+			mt76x0_rf_wr(dev, MT_RF(0, 26),
+				     freq_item->pll_sdm_k & 0xff);
+			mt76x0_rf_wr(dev, MT_RF(0, 27),
+				     (freq_item->pll_sdm_k >> 8) & 0xff);
 
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 28));
-			rf_val &= ~0x3;
-			rf_val |= ((freq_item->pll_sdm_k >> 16) & 0x0003);
-			mt76x0_rf_wr(dev, MT_RF(0, 28), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 28), 0x3,
+				      (freq_item->pll_sdm_k >> 16) & 0x3);
 
 			/* R24<1:0> xo_div */
-			rf_val = mt76x0_rf_rr(dev, MT_RF(0, 24));
-			rf_val &= ~0x3;
-			rf_val |= freq_item->pllR24_b1b0;
-			mt76x0_rf_wr(dev, MT_RF(0, 24), rf_val);
+			mt76x0_rf_rmw(dev, MT_RF(0, 24), MT_RF_XO_DIV_MASK,
+				      freq_item->pllR24_b1b0);
 
 			break;
 		}
@@ -445,9 +403,7 @@ mt76x0_phy_set_chan_rf_params(struct mt76x02_dev *dev, u8 channel, u16 rf_bw_ban
 		}
 	}
 
-	mac_reg = mt76_rr(dev, MT_RF_MISC);
-	mac_reg &= ~0xC; /* Clear 0x518[3:2] */
-	mt76_wr(dev, MT_RF_MISC, mac_reg);
+	mt76_clear(dev, MT_RF_MISC, 0xc);
 
 	band = (rf_band & RF_G_BAND) ? NL80211_BAND_2GHZ : NL80211_BAND_5GHZ;
 	if (mt76x02_ext_pa_enabled(dev, band)) {
@@ -456,15 +412,10 @@ mt76x0_phy_set_chan_rf_params(struct mt76x02_dev *dev, u8 channel, u16 rf_bw_ban
 			[2]1'b1: enable external A band PA, 1'b0: disable external A band PA
 			[3]1'b1: enable external G band PA, 1'b0: disable external G band PA
 		*/
-		if (rf_band & RF_A_BAND) {
-			mac_reg = mt76_rr(dev, MT_RF_MISC);
-			mac_reg |= 0x4;
-			mt76_wr(dev, MT_RF_MISC, mac_reg);
-		} else {
-			mac_reg = mt76_rr(dev, MT_RF_MISC);
-			mac_reg |= 0x8;
-			mt76_wr(dev, MT_RF_MISC, mac_reg);
-		}
+		if (rf_band & RF_A_BAND)
+			mt76_set(dev, MT_RF_MISC, BIT(2));
+		else
+			mt76_set(dev, MT_RF_MISC, BIT(3));
 
 		/* External PA */
 		for (i = 0; i < ARRAY_SIZE(mt76x0_rf_ext_pa_tab); i++)
@@ -710,12 +661,10 @@ int mt76x0_phy_set_channel(struct mt76x02_dev *dev,
 	mt76x0_phy_set_chan_rf_params(dev, channel, rf_bw_band);
 
 	/* set Japan Tx filter at channel 14 */
-	val = mt76_rr(dev, MT_BBP(CORE, 1));
 	if (channel == 14)
-		val |= 0x20;
+		mt76_set(dev, MT_BBP(CORE, 1), 0x20);
 	else
-		val &= ~0x20;
-	mt76_wr(dev, MT_BBP(CORE, 1), val);
+		mt76_clear(dev, MT_BBP(CORE, 1), 0x20);
 
 	mt76x0_read_rx_gain(dev);
 	mt76x0_phy_set_chan_bbp_params(dev, rf_bw_band);
@@ -903,20 +852,16 @@ static void mt76x0_phy_rf_init(struct mt76x02_dev *dev)
 		     min_t(u8, dev->cal.rx.freq_offset, 0xbf));
 	val = mt76x0_rf_rr(dev, MT_RF(0, 22));
 
-	/*
-	   Reset the DAC (Set B0.R73<7>=1, then set B0.R73<7>=0, and then set B0.R73<7>) during power up.
+	/* Reset procedure DAC during power-up:
+	 * - set B0.R73<7>
+	 * - clear B0.R73<7>
+	 * - set B0.R73<7>
 	 */
-	val = mt76x0_rf_rr(dev, MT_RF(0, 73));
-	val |= 0x80;
-	mt76x0_rf_wr(dev, MT_RF(0, 73), val);
-	val &= ~0x80;
-	mt76x0_rf_wr(dev, MT_RF(0, 73), val);
-	val |= 0x80;
-	mt76x0_rf_wr(dev, MT_RF(0, 73), val);
+	mt76x0_rf_set(dev, MT_RF(0, 73), BIT(7));
+	mt76x0_rf_clear(dev, MT_RF(0, 73), BIT(7));
+	mt76x0_rf_set(dev, MT_RF(0, 73), BIT(7));
 
-	/*
-	   vcocal_en (initiate VCO calibration (reset after completion)) - It should be at the end of RF configuration.
-	 */
+	/* vcocal_en: initiate VCO calibration (reset after completion)) */
 	mt76x0_rf_set(dev, MT_RF(0, 4), 0x80);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.h b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.h
index 2880a43c3cb0..9889132b768a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.h
@@ -30,6 +30,23 @@
 #define MT_RF_BANK(offset) (offset >> 16)
 #define MT_RF_REG(offset) (offset & 0xff)
 
+#define MT_RF_VCO_BP_CLOSE_LOOP		BIT(3)
+#define MT_RF_VCO_BP_CLOSE_LOOP_MASK	GENMASK(3, 0)
+#define MT_RF_VCO_CAL_MASK		GENMASK(2, 0)
+#define MT_RF_START_TIME		0x3
+#define MT_RF_START_TIME_MASK		GENMASK(2, 0)
+#define MT_RF_SETTLE_TIME_MASK		GENMASK(6, 4)
+
+#define MT_RF_PLL_DEN_MASK		GENMASK(4, 0)
+#define MT_RF_PLL_K_MASK		GENMASK(4, 0)
+#define MT_RF_SDM_RESET_MASK		BIT(7)
+#define MT_RF_SDM_MASH_PRBS_MASK	GENMASK(6, 2)
+#define MT_RF_SDM_BP_MASK		BIT(1)
+#define MT_RF_ISI_ISO_MASK		GENMASK(7, 6)
+#define MT_RF_PFD_DLY_MASK		GENMASK(5, 4)
+#define MT_RF_CLK_SEL_MASK		GENMASK(3, 2)
+#define MT_RF_XO_DIV_MASK		GENMASK(1, 0)
+
 struct mt76x0_bbp_switch_item {
 	u16 bw_band;
 	struct mt76_reg_pair reg_pair;
-- 
cgit v1.2.3


From b8defea4b2ee82cdb1e11c44f5ff401c45cf5748 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sun, 14 Oct 2018 18:55:20 +0200
Subject: mt76x0: phy: improve code readability in initvals_phy.h

Improve initvals_phy.h code readability (there are no actual changes
of original values)

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt76x0/initvals_phy.h   | 1313 +++++++++-----------
 1 file changed, 591 insertions(+), 722 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_phy.h b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_phy.h
index 95d43efc1f3d..56c6fa73daf5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_phy.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_phy.h
@@ -16,757 +16,626 @@
 #ifndef __MT76X0U_PHY_INITVALS_H
 #define __MT76X0U_PHY_INITVALS_H
 
-#define RF_REG_PAIR(bank, reg, value)				\
-	{ (bank) << 16 | (reg), value }
-
-
 static const struct mt76_reg_pair mt76x0_rf_central_tab[] = {
-/*
-	Bank 0 - For central blocks: BG, PLL, XTAL, LO, ADC/DAC
-*/
-	{ MT_RF(0, 1), 0x01},
-	{ MT_RF(0, 2), 0x11},
-
-	/*
-		R3 ~ R7: VCO Cal.
-	*/
-	{ MT_RF(0, 3), 0x73}, /* VCO Freq Cal - No Bypass, VCO Amp Cal - No Bypass */
-	{ MT_RF(0, 4), 0x30}, /* R4 b<7>=1, VCO cal */
-	{ MT_RF(0, 5), 0x00},
-	{ MT_RF(0, 6), 0x41}, /* Set the open loop amplitude to middle since bypassing amplitude calibration */
-	{ MT_RF(0, 7), 0x00},
-
-	/*
-		XO
-	*/
-	{ MT_RF(0,  8), 0x00},
-	{ MT_RF(0,  9), 0x00},
-	{ MT_RF(0, 10), 0x0C},
-	{ MT_RF(0, 11), 0x00},
-	{ MT_RF(0, 12), 0x00},
-
-	/*
-		BG
-	*/
-	{ MT_RF(0, 13), 0x00},
-	{ MT_RF(0, 14), 0x00},
-	{ MT_RF(0, 15), 0x00},
-
-	/*
-		LDO
-	*/
-	{ MT_RF(0, 19), 0x20},
-	/*
-		XO
-	*/
-	{ MT_RF(0, 20), 0x22},
-	{ MT_RF(0, 21), 0x12},
-	{ MT_RF(0, 23), 0x00},
-	{ MT_RF(0, 24), 0x33}, /* See band selection for R24<1:0> */
-	{ MT_RF(0, 25), 0x00},
-
-	/*
-		PLL, See Freq Selection
-	*/
-	{ MT_RF(0, 26), 0x00},
-	{ MT_RF(0, 27), 0x00},
-	{ MT_RF(0, 28), 0x00},
-	{ MT_RF(0, 29), 0x00},
-	{ MT_RF(0, 30), 0x00},
-	{ MT_RF(0, 31), 0x00},
-	{ MT_RF(0, 32), 0x00},
-	{ MT_RF(0, 33), 0x00},
-	{ MT_RF(0, 34), 0x00},
-	{ MT_RF(0, 35), 0x00},
-	{ MT_RF(0, 36), 0x00},
-	{ MT_RF(0, 37), 0x00},
-
-	/*
-		LO Buffer
-	*/
-	{ MT_RF(0, 38), 0x2F},
-
-	/*
-		Test Ports
-	*/
-	{ MT_RF(0, 64), 0x00},
-	{ MT_RF(0, 65), 0x80},
-	{ MT_RF(0, 66), 0x01},
-	{ MT_RF(0, 67), 0x04},
-
-	/*
-		ADC/DAC
-	*/
-	{ MT_RF(0, 68), 0x00},
-	{ MT_RF(0, 69), 0x08},
-	{ MT_RF(0, 70), 0x08},
-	{ MT_RF(0, 71), 0x40},
-	{ MT_RF(0, 72), 0xD0},
-	{ MT_RF(0, 73), 0x93},
+	{ MT_RF(0,  1), 0x01 },
+	{ MT_RF(0,  2), 0x11 },
+	/* R3 ~ R7: VCO Cal */
+	{ MT_RF(0,  3), 0x73 }, /* VCO Freq Cal */
+	{ MT_RF(0,  4), 0x30 }, /* R4 b<7>=1, VCO cal */
+	{ MT_RF(0,  5), 0x00 },
+	{ MT_RF(0,  6), 0x41 },
+	{ MT_RF(0,  7), 0x00 },
+	{ MT_RF(0,  8), 0x00 },
+	{ MT_RF(0,  9), 0x00 },
+	{ MT_RF(0, 10), 0x0C },
+	{ MT_RF(0, 11), 0x00 },
+	{ MT_RF(0, 12), 0x00 },
+	/* BG */
+	{ MT_RF(0, 13), 0x00 },
+	{ MT_RF(0, 14), 0x00 },
+	{ MT_RF(0, 15), 0x00 },
+	/* LDO */
+	{ MT_RF(0, 19), 0x20 },
+	{ MT_RF(0, 20), 0x22 },
+	{ MT_RF(0, 21), 0x12 },
+	{ MT_RF(0, 23), 0x00 },
+	{ MT_RF(0, 24), 0x33 },
+	{ MT_RF(0, 25), 0x00 },
+	/* PLL */
+	{ MT_RF(0, 26), 0x00 },
+	{ MT_RF(0, 27), 0x00 },
+	{ MT_RF(0, 28), 0x00 },
+	{ MT_RF(0, 29), 0x00 },
+	{ MT_RF(0, 30), 0x00 },
+	{ MT_RF(0, 31), 0x00 },
+	{ MT_RF(0, 32), 0x00 },
+	{ MT_RF(0, 33), 0x00 },
+	{ MT_RF(0, 34), 0x00 },
+	{ MT_RF(0, 35), 0x00 },
+	{ MT_RF(0, 36), 0x00 },
+	{ MT_RF(0, 37), 0x00 },
+	/* LO Buffer */
+	{ MT_RF(0, 38), 0x2F },
+	/* Test Ports */
+	{ MT_RF(0, 64), 0x00 },
+	{ MT_RF(0, 65), 0x80 },
+	{ MT_RF(0, 66), 0x01 },
+	{ MT_RF(0, 67), 0x04 },
+	/* ADC-DAC */
+	{ MT_RF(0, 68), 0x00 },
+	{ MT_RF(0, 69), 0x08 },
+	{ MT_RF(0, 70), 0x08 },
+	{ MT_RF(0, 71), 0x40 },
+	{ MT_RF(0, 72), 0xD0 },
+	{ MT_RF(0, 73), 0x93 },
 };
 
 static const struct mt76_reg_pair mt76x0_rf_2g_channel_0_tab[] = {
-/*
-	Bank 5 - Channel 0 2G RF registers
-*/
-	/*
-		RX logic operation
-	*/
-	/* RF_R00 Change in SelectBand6590 */
-
-	{ MT_RF(5, 2), 0x0C}, /* 5G+2G (MT7610U) */
-	{ MT_RF(5, 3), 0x00},
-
-	/*
-		TX logic operation
-	*/
-	{ MT_RF(5, 4), 0x00},
-	{ MT_RF(5, 5), 0x84},
-	{ MT_RF(5, 6), 0x02},
-
-	/*
-		LDO
-	*/
-	{ MT_RF(5, 7), 0x00},
-	{ MT_RF(5, 8), 0x00},
-	{ MT_RF(5, 9), 0x00},
-
-	/*
-		RX
-	*/
-	{ MT_RF(5, 10), 0x51},
-	{ MT_RF(5, 11), 0x22},
-	{ MT_RF(5, 12), 0x22},
-	{ MT_RF(5, 13), 0x0F},
-	{ MT_RF(5, 14), 0x47}, /* Increase mixer current for more gain */
-	{ MT_RF(5, 15), 0x25},
-	{ MT_RF(5, 16), 0xC7}, /* Tune LNA2 tank */
-	{ MT_RF(5, 17), 0x00},
-	{ MT_RF(5, 18), 0x00},
-	{ MT_RF(5, 19), 0x30}, /* Improve max Pin */
-	{ MT_RF(5, 20), 0x33},
-	{ MT_RF(5, 21), 0x02},
-	{ MT_RF(5, 22), 0x32}, /* Tune LNA1 tank */
-	{ MT_RF(5, 23), 0x00},
-	{ MT_RF(5, 24), 0x25},
-	{ MT_RF(5, 26), 0x00},
-	{ MT_RF(5, 27), 0x12},
-	{ MT_RF(5, 28), 0x0F},
-	{ MT_RF(5, 29), 0x00},
-
-	/*
-		LOGEN
-	*/
-	{ MT_RF(5, 30), 0x51}, /* Tune LOGEN tank */
-	{ MT_RF(5, 31), 0x35},
-	{ MT_RF(5, 32), 0x31},
-	{ MT_RF(5, 33), 0x31},
-	{ MT_RF(5, 34), 0x34},
-	{ MT_RF(5, 35), 0x03},
-	{ MT_RF(5, 36), 0x00},
-
-	/*
-		TX
-	*/
-	{ MT_RF(5, 37), 0xDD}, /* Improve 3.2GHz spur */
-	{ MT_RF(5, 38), 0xB3},
-	{ MT_RF(5, 39), 0x33},
-	{ MT_RF(5, 40), 0xB1},
-	{ MT_RF(5, 41), 0x71},
-	{ MT_RF(5, 42), 0xF2},
-	{ MT_RF(5, 43), 0x47},
-	{ MT_RF(5, 44), 0x77},
-	{ MT_RF(5, 45), 0x0E},
-	{ MT_RF(5, 46), 0x10},
-	{ MT_RF(5, 47), 0x00},
-	{ MT_RF(5, 48), 0x53},
-	{ MT_RF(5, 49), 0x03},
-	{ MT_RF(5, 50), 0xEF},
-	{ MT_RF(5, 51), 0xC7},
-	{ MT_RF(5, 52), 0x62},
-	{ MT_RF(5, 53), 0x62},
-	{ MT_RF(5, 54), 0x00},
-	{ MT_RF(5, 55), 0x00},
-	{ MT_RF(5, 56), 0x0F},
-	{ MT_RF(5, 57), 0x0F},
-	{ MT_RF(5, 58), 0x16},
-	{ MT_RF(5, 59), 0x16},
-	{ MT_RF(5, 60), 0x10},
-	{ MT_RF(5, 61), 0x10},
-	{ MT_RF(5, 62), 0xD0},
-	{ MT_RF(5, 63), 0x6C},
-	{ MT_RF(5, 64), 0x58},
-	{ MT_RF(5, 65), 0x58},
-	{ MT_RF(5, 66), 0xF2},
-	{ MT_RF(5, 67), 0xE8},
-	{ MT_RF(5, 68), 0xF0},
-	{ MT_RF(5, 69), 0xF0},
-	{ MT_RF(5, 127), 0x04},
+	/* RX logic operation */
+	{ MT_RF(5,  2), 0x0C }, /* 5G+2G */
+	{ MT_RF(5,  3), 0x00 },
+	/* TX logic operation */
+	{ MT_RF(5,  4), 0x00 },
+	{ MT_RF(5,  5), 0x84 },
+	{ MT_RF(5,  6), 0x02 },
+	/* LDO */
+	{ MT_RF(5,  7), 0x00 },
+	{ MT_RF(5,  8), 0x00 },
+	{ MT_RF(5,  9), 0x00 },
+	/* RX */
+	{ MT_RF(5, 10), 0x51 },
+	{ MT_RF(5, 11), 0x22 },
+	{ MT_RF(5, 12), 0x22 },
+	{ MT_RF(5, 13), 0x0F },
+	{ MT_RF(5, 14), 0x47 },
+	{ MT_RF(5, 15), 0x25 },
+	{ MT_RF(5, 16), 0xC7 },
+	{ MT_RF(5, 17), 0x00 },
+	{ MT_RF(5, 18), 0x00 },
+	{ MT_RF(5, 19), 0x30 },
+	{ MT_RF(5, 20), 0x33 },
+	{ MT_RF(5, 21), 0x02 },
+	{ MT_RF(5, 22), 0x32 },
+	{ MT_RF(5, 23), 0x00 },
+	{ MT_RF(5, 24), 0x25 },
+	{ MT_RF(5, 26), 0x00 },
+	{ MT_RF(5, 27), 0x12 },
+	{ MT_RF(5, 28), 0x0F },
+	{ MT_RF(5, 29), 0x00 },
+	/* LOGEN */
+	{ MT_RF(5, 30), 0x51 },
+	{ MT_RF(5, 31), 0x35 },
+	{ MT_RF(5, 32), 0x31 },
+	{ MT_RF(5, 33), 0x31 },
+	{ MT_RF(5, 34), 0x34 },
+	{ MT_RF(5, 35), 0x03 },
+	{ MT_RF(5, 36), 0x00 },
+	/* TX */
+	{ MT_RF(5, 37), 0xDD },
+	{ MT_RF(5, 38), 0xB3 },
+	{ MT_RF(5, 39), 0x33 },
+	{ MT_RF(5, 40), 0xB1 },
+	{ MT_RF(5, 41), 0x71 },
+	{ MT_RF(5, 42), 0xF2 },
+	{ MT_RF(5, 43), 0x47 },
+	{ MT_RF(5, 44), 0x77 },
+	{ MT_RF(5, 45), 0x0E },
+	{ MT_RF(5, 46), 0x10 },
+	{ MT_RF(5, 47), 0x00 },
+	{ MT_RF(5, 48), 0x53 },
+	{ MT_RF(5, 49), 0x03 },
+	{ MT_RF(5, 50), 0xEF },
+	{ MT_RF(5, 51), 0xC7 },
+	{ MT_RF(5, 52), 0x62 },
+	{ MT_RF(5, 53), 0x62 },
+	{ MT_RF(5, 54), 0x00 },
+	{ MT_RF(5, 55), 0x00 },
+	{ MT_RF(5, 56), 0x0F },
+	{ MT_RF(5, 57), 0x0F },
+	{ MT_RF(5, 58), 0x16 },
+	{ MT_RF(5, 59), 0x16 },
+	{ MT_RF(5, 60), 0x10 },
+	{ MT_RF(5, 61), 0x10 },
+	{ MT_RF(5, 62), 0xD0 },
+	{ MT_RF(5, 63), 0x6C },
+	{ MT_RF(5, 64), 0x58 },
+	{ MT_RF(5, 65), 0x58 },
+	{ MT_RF(5, 66), 0xF2 },
+	{ MT_RF(5, 67), 0xE8 },
+	{ MT_RF(5, 68), 0xF0 },
+	{ MT_RF(5, 69), 0xF0 },
+	{ MT_RF(5, 127), 0x04 },
 };
 
 static const struct mt76_reg_pair mt76x0_rf_5g_channel_0_tab[] = {
-/*
-	Bank 6 - Channel 0 5G RF registers
-*/
-	/*
-		RX logic operation
-	*/
-	/* RF_R00 Change in SelectBandmt76x0 */
-
-	{ MT_RF(6, 2), 0x0C},
-	{ MT_RF(6, 3), 0x00},
-
-	/*
-		TX logic operation
-	*/
-	{ MT_RF(6, 4), 0x00},
-	{ MT_RF(6, 5), 0x84},
-	{ MT_RF(6, 6), 0x02},
-
-	/*
-		LDO
-	*/
-	{ MT_RF(6, 7), 0x00},
-	{ MT_RF(6, 8), 0x00},
-	{ MT_RF(6, 9), 0x00},
-
-	/*
-		RX
-	*/
-	{ MT_RF(6, 10), 0x00},
-	{ MT_RF(6, 11), 0x01},
-
-	{ MT_RF(6, 13), 0x23},
-	{ MT_RF(6, 14), 0x00},
-	{ MT_RF(6, 15), 0x04},
-	{ MT_RF(6, 16), 0x22},
-
-	{ MT_RF(6, 18), 0x08},
-	{ MT_RF(6, 19), 0x00},
-	{ MT_RF(6, 20), 0x00},
-	{ MT_RF(6, 21), 0x00},
-	{ MT_RF(6, 22), 0xFB},
-
-	/*
-		LOGEN5G
-	*/
-	{ MT_RF(6, 25), 0x76},
-	{ MT_RF(6, 26), 0x24},
-	{ MT_RF(6, 27), 0x04},
-	{ MT_RF(6, 28), 0x00},
-	{ MT_RF(6, 29), 0x00},
-
-	/*
-		TX
-	*/
-	{ MT_RF(6, 37), 0xBB},
-	{ MT_RF(6, 38), 0xB3},
-
-	{ MT_RF(6, 40), 0x33},
-	{ MT_RF(6, 41), 0x33},
-
-	{ MT_RF(6, 43), 0x03},
-	{ MT_RF(6, 44), 0xB3},
-
-	{ MT_RF(6, 46), 0x17},
-	{ MT_RF(6, 47), 0x0E},
-	{ MT_RF(6, 48), 0x10},
-	{ MT_RF(6, 49), 0x07},
-
-	{ MT_RF(6, 62), 0x00},
-	{ MT_RF(6, 63), 0x00},
-	{ MT_RF(6, 64), 0xF1},
-	{ MT_RF(6, 65), 0x0F},
+	/* RX logic operation */
+	{ MT_RF(6, 2), 0x0C },
+	{ MT_RF(6, 3), 0x00 },
+	/* TX logic operation */
+	{ MT_RF(6, 4), 0x00 },
+	{ MT_RF(6, 5), 0x84 },
+	{ MT_RF(6, 6), 0x02 },
+	/* LDO */
+	{ MT_RF(6, 7), 0x00 },
+	{ MT_RF(6, 8), 0x00 },
+	{ MT_RF(6, 9), 0x00 },
+	/* RX */
+	{ MT_RF(6, 10), 0x00 },
+	{ MT_RF(6, 11), 0x01 },
+	{ MT_RF(6, 13), 0x23 },
+	{ MT_RF(6, 14), 0x00 },
+	{ MT_RF(6, 15), 0x04 },
+	{ MT_RF(6, 16), 0x22 },
+	{ MT_RF(6, 18), 0x08 },
+	{ MT_RF(6, 19), 0x00 },
+	{ MT_RF(6, 20), 0x00 },
+	{ MT_RF(6, 21), 0x00 },
+	{ MT_RF(6, 22), 0xFB },
+	/* LOGEN5G */
+	{ MT_RF(6, 25), 0x76 },
+	{ MT_RF(6, 26), 0x24 },
+	{ MT_RF(6, 27), 0x04 },
+	{ MT_RF(6, 28), 0x00 },
+	{ MT_RF(6, 29), 0x00 },
+	/* TX */
+	{ MT_RF(6, 37), 0xBB },
+	{ MT_RF(6, 38), 0xB3 },
+	{ MT_RF(6, 40), 0x33 },
+	{ MT_RF(6, 41), 0x33 },
+	{ MT_RF(6, 43), 0x03 },
+	{ MT_RF(6, 44), 0xB3 },
+	{ MT_RF(6, 46), 0x17 },
+	{ MT_RF(6, 47), 0x0E },
+	{ MT_RF(6, 48), 0x10 },
+	{ MT_RF(6, 49), 0x07 },
+	{ MT_RF(6, 62), 0x00 },
+	{ MT_RF(6, 63), 0x00 },
+	{ MT_RF(6, 64), 0xF1 },
+	{ MT_RF(6, 65), 0x0F },
 };
 
 static const struct mt76_reg_pair mt76x0_rf_vga_channel_0_tab[] = {
-/*
-	Bank 7 - Channel 0 VGA RF registers
-*/
 	/* E3 CR */
-	{ MT_RF(7, 0), 0x47}, /* Allow BBP/MAC to do calibration */
-	{ MT_RF(7, 1), 0x00},
-	{ MT_RF(7, 2), 0x00},
-	{ MT_RF(7, 3), 0x00},
-	{ MT_RF(7, 4), 0x00},
-
-	{ MT_RF(7, 10), 0x13},
-	{ MT_RF(7, 11), 0x0F},
-	{ MT_RF(7, 12), 0x13}, /* For dcoc */
-	{ MT_RF(7, 13), 0x13}, /* For dcoc */
-	{ MT_RF(7, 14), 0x13}, /* For dcoc */
-	{ MT_RF(7, 15), 0x20}, /* For dcoc */
-	{ MT_RF(7, 16), 0x22}, /* For dcoc */
-
-	{ MT_RF(7, 17), 0x7C},
-
-	{ MT_RF(7, 18), 0x00},
-	{ MT_RF(7, 19), 0x00},
-	{ MT_RF(7, 20), 0x00},
-	{ MT_RF(7, 21), 0xF1},
-	{ MT_RF(7, 22), 0x11},
-	{ MT_RF(7, 23), 0xC2},
-	{ MT_RF(7, 24), 0x41},
-	{ MT_RF(7, 25), 0x20},
-	{ MT_RF(7, 26), 0x40},
-	{ MT_RF(7, 27), 0xD7},
-	{ MT_RF(7, 28), 0xA2},
-	{ MT_RF(7, 29), 0x60},
-	{ MT_RF(7, 30), 0x49},
-	{ MT_RF(7, 31), 0x20},
-	{ MT_RF(7, 32), 0x44},
-	{ MT_RF(7, 33), 0xC1},
-	{ MT_RF(7, 34), 0x60},
-	{ MT_RF(7, 35), 0xC0},
-
-	{ MT_RF(7, 61), 0x01},
-
-	{ MT_RF(7, 72), 0x3C},
-	{ MT_RF(7, 73), 0x34},
-	{ MT_RF(7, 74), 0x00},
+	{ MT_RF(7,  0), 0x47 },
+	{ MT_RF(7,  1), 0x00 },
+	{ MT_RF(7,  2), 0x00 },
+	{ MT_RF(7,  3), 0x00 },
+	{ MT_RF(7,  4), 0x00 },
+	{ MT_RF(7, 10), 0x13 },
+	{ MT_RF(7, 11), 0x0F },
+	{ MT_RF(7, 12), 0x13 },
+	{ MT_RF(7, 13), 0x13 },
+	{ MT_RF(7, 14), 0x13 },
+	{ MT_RF(7, 15), 0x20 },
+	{ MT_RF(7, 16), 0x22 },
+	{ MT_RF(7, 17), 0x7C },
+	{ MT_RF(7, 18), 0x00 },
+	{ MT_RF(7, 19), 0x00 },
+	{ MT_RF(7, 20), 0x00 },
+	{ MT_RF(7, 21), 0xF1 },
+	{ MT_RF(7, 22), 0x11 },
+	{ MT_RF(7, 23), 0xC2 },
+	{ MT_RF(7, 24), 0x41 },
+	{ MT_RF(7, 25), 0x20 },
+	{ MT_RF(7, 26), 0x40 },
+	{ MT_RF(7, 27), 0xD7 },
+	{ MT_RF(7, 28), 0xA2 },
+	{ MT_RF(7, 29), 0x60 },
+	{ MT_RF(7, 30), 0x49 },
+	{ MT_RF(7, 31), 0x20 },
+	{ MT_RF(7, 32), 0x44 },
+	{ MT_RF(7, 33), 0xC1 },
+	{ MT_RF(7, 34), 0x60 },
+	{ MT_RF(7, 35), 0xC0 },
+	{ MT_RF(7, 61), 0x01 },
+	{ MT_RF(7, 72), 0x3C },
+	{ MT_RF(7, 73), 0x34 },
+	{ MT_RF(7, 74), 0x00 },
 };
 
 static const struct mt76x0_rf_switch_item mt76x0_rf_bw_switch_tab[] = {
-	/*   Bank, 		Register,	Bw/Band, 	Value */
-	{ MT_RF(0, 17),		RF_G_BAND | RF_BW_20,	0x00},
-	{ MT_RF(0, 17),		RF_G_BAND | RF_BW_40,	0x00},
-	{ MT_RF(0, 17),		RF_A_BAND | RF_BW_20,	0x00},
-	{ MT_RF(0, 17),		RF_A_BAND | RF_BW_40,	0x00},
-	{ MT_RF(0, 17),		RF_A_BAND | RF_BW_80,	0x00},
-
-	/* TODO: need to check B7.R6 & B7.R7 setting for 2.4G again @20121112 */
-	{ MT_RF(7,  6),		RF_G_BAND | RF_BW_20,	0x40},
-	{ MT_RF(7,  6),		RF_G_BAND | RF_BW_40,	0x1C},
-	{ MT_RF(7,  6),		RF_A_BAND | RF_BW_20,	0x40},
-	{ MT_RF(7,  6),		RF_A_BAND | RF_BW_40,	0x20},
-	{ MT_RF(7,  6),		RF_A_BAND | RF_BW_80,	0x10},
-
-	{ MT_RF(7,  7),		RF_G_BAND | RF_BW_20,	0x40},
-	{ MT_RF(7,  7),		RF_G_BAND | RF_BW_40,	0x20},
-	{ MT_RF(7,  7),		RF_A_BAND | RF_BW_20,	0x40},
-	{ MT_RF(7,  7),		RF_A_BAND | RF_BW_40,	0x20},
-	{ MT_RF(7,  7),		RF_A_BAND | RF_BW_80,	0x10},
-
-	{ MT_RF(7,  8),		RF_G_BAND | RF_BW_20,	0x03},
-	{ MT_RF(7,  8),		RF_G_BAND | RF_BW_40,	0x01},
-	{ MT_RF(7,  8),		RF_A_BAND | RF_BW_20,	0x03},
-	{ MT_RF(7,  8),		RF_A_BAND | RF_BW_40,	0x01},
-	{ MT_RF(7,  8),		RF_A_BAND | RF_BW_80,	0x00},
-
-	/* TODO: need to check B7.R58 & B7.R59 setting for 2.4G again @20121112 */
-	{ MT_RF(7, 58),		RF_G_BAND | RF_BW_20,	0x40},
-	{ MT_RF(7, 58),		RF_G_BAND | RF_BW_40,	0x40},
-	{ MT_RF(7, 58),		RF_A_BAND | RF_BW_20,	0x40},
-	{ MT_RF(7, 58),		RF_A_BAND | RF_BW_40,	0x40},
-	{ MT_RF(7, 58),		RF_A_BAND | RF_BW_80,	0x10},
-
-	{ MT_RF(7, 59),		RF_G_BAND | RF_BW_20,	0x40},
-	{ MT_RF(7, 59),		RF_G_BAND | RF_BW_40,	0x40},
-	{ MT_RF(7, 59),		RF_A_BAND | RF_BW_20,	0x40},
-	{ MT_RF(7, 59),		RF_A_BAND | RF_BW_40,	0x40},
-	{ MT_RF(7, 59),		RF_A_BAND | RF_BW_80,	0x10},
-
-	{ MT_RF(7, 60),		RF_G_BAND | RF_BW_20,	0xAA},
-	{ MT_RF(7, 60),		RF_G_BAND | RF_BW_40,	0xAA},
-	{ MT_RF(7, 60),		RF_A_BAND | RF_BW_20,	0xAA},
-	{ MT_RF(7, 60),		RF_A_BAND | RF_BW_40,	0xAA},
-	{ MT_RF(7, 60),		RF_A_BAND | RF_BW_80,	0xAA},
-
-	{ MT_RF(7, 76),		RF_BW_20,	0x40},
-	{ MT_RF(7, 76),		RF_BW_40,	0x40},
-	{ MT_RF(7, 76),		RF_BW_80,	0x10},
-
-	{ MT_RF(7, 77),		RF_BW_20,	0x40},
-	{ MT_RF(7, 77),		RF_BW_40,	0x40},
-	{ MT_RF(7, 77),		RF_BW_80,	0x10},
+	/* bank, reg	bw/band			value */
+	{ MT_RF(0, 17),	RF_G_BAND | RF_BW_20,	0x00 },
+	{ MT_RF(0, 17),	RF_G_BAND | RF_BW_40,	0x00 },
+	{ MT_RF(0, 17),	RF_A_BAND | RF_BW_20,	0x00 },
+	{ MT_RF(0, 17),	RF_A_BAND | RF_BW_40,	0x00 },
+	{ MT_RF(0, 17),	RF_A_BAND | RF_BW_80,	0x00 },
+	{ MT_RF(7,  6),	RF_G_BAND | RF_BW_20,	0x40 },
+	{ MT_RF(7,  6),	RF_G_BAND | RF_BW_40,	0x1C },
+	{ MT_RF(7,  6),	RF_A_BAND | RF_BW_20,	0x40 },
+	{ MT_RF(7,  6),	RF_A_BAND | RF_BW_40,	0x20 },
+	{ MT_RF(7,  6),	RF_A_BAND | RF_BW_80,	0x10 },
+	{ MT_RF(7,  7),	RF_G_BAND | RF_BW_20,	0x40 },
+	{ MT_RF(7,  7),	RF_G_BAND | RF_BW_40,	0x20 },
+	{ MT_RF(7,  7),	RF_A_BAND | RF_BW_20,	0x40 },
+	{ MT_RF(7,  7),	RF_A_BAND | RF_BW_40,	0x20 },
+	{ MT_RF(7,  7),	RF_A_BAND | RF_BW_80,	0x10 },
+	{ MT_RF(7,  8),	RF_G_BAND | RF_BW_20,	0x03 },
+	{ MT_RF(7,  8),	RF_G_BAND | RF_BW_40,	0x01 },
+	{ MT_RF(7,  8),	RF_A_BAND | RF_BW_20,	0x03 },
+	{ MT_RF(7,  8),	RF_A_BAND | RF_BW_40,	0x01 },
+	{ MT_RF(7,  8),	RF_A_BAND | RF_BW_80,	0x00 },
+	{ MT_RF(7, 58),	RF_G_BAND | RF_BW_20,	0x40 },
+	{ MT_RF(7, 58),	RF_G_BAND | RF_BW_40,	0x40 },
+	{ MT_RF(7, 58),	RF_A_BAND | RF_BW_20,	0x40 },
+	{ MT_RF(7, 58),	RF_A_BAND | RF_BW_40,	0x40 },
+	{ MT_RF(7, 58),	RF_A_BAND | RF_BW_80,	0x10 },
+	{ MT_RF(7, 59),	RF_G_BAND | RF_BW_20,	0x40 },
+	{ MT_RF(7, 59),	RF_G_BAND | RF_BW_40,	0x40 },
+	{ MT_RF(7, 59),	RF_A_BAND | RF_BW_20,	0x40 },
+	{ MT_RF(7, 59),	RF_A_BAND | RF_BW_40,	0x40 },
+	{ MT_RF(7, 59),	RF_A_BAND | RF_BW_80,	0x10 },
+	{ MT_RF(7, 60),	RF_G_BAND | RF_BW_20,	0xAA },
+	{ MT_RF(7, 60),	RF_G_BAND | RF_BW_40,	0xAA },
+	{ MT_RF(7, 60),	RF_A_BAND | RF_BW_20,	0xAA },
+	{ MT_RF(7, 60),	RF_A_BAND | RF_BW_40,	0xAA },
+	{ MT_RF(7, 60),	RF_A_BAND | RF_BW_80,	0xAA },
+	{ MT_RF(7, 76),	RF_BW_20,		0x40 },
+	{ MT_RF(7, 76),	RF_BW_40,		0x40 },
+	{ MT_RF(7, 76),	RF_BW_80,		0x10 },
+	{ MT_RF(7, 77),	RF_BW_20,		0x40 },
+	{ MT_RF(7, 77),	RF_BW_40,		0x40 },
+	{ MT_RF(7, 77),	RF_BW_80,		0x10 },
 };
 
 static const struct mt76x0_rf_switch_item mt76x0_rf_band_switch_tab[] = {
-	/*   Bank, 		Register,	Bw/Band, 		Value */
-	{ MT_RF(0, 16),		RF_G_BAND,		0x20},
-	{ MT_RF(0, 16),		RF_A_BAND,		0x20},
-
-	{ MT_RF(0, 18),		RF_G_BAND,		0x00},
-	{ MT_RF(0, 18),		RF_A_BAND,		0x00},
-
-	{ MT_RF(0, 39),		RF_G_BAND,		0x36},
-	{ MT_RF(0, 39),		RF_A_BAND_LB,	0x34},
-	{ MT_RF(0, 39),		RF_A_BAND_MB,	0x33},
-	{ MT_RF(0, 39),		RF_A_BAND_HB,	0x31},
-	{ MT_RF(0, 39),		RF_A_BAND_11J,	0x36},
-
-	{ MT_RF(6, 12),		RF_A_BAND_LB,	0x44},
-	{ MT_RF(6, 12),		RF_A_BAND_MB,	0x44},
-	{ MT_RF(6, 12),		RF_A_BAND_HB,	0x55},
-	{ MT_RF(6, 12),		RF_A_BAND_11J,	0x44},
-
-	{ MT_RF(6, 17),		RF_A_BAND_LB,	0x02},
-	{ MT_RF(6, 17),		RF_A_BAND_MB,	0x00},
-	{ MT_RF(6, 17),		RF_A_BAND_HB,	0x00},
-	{ MT_RF(6, 17),		RF_A_BAND_11J,	0x05},
-
-	{ MT_RF(6, 24),		RF_A_BAND_LB,	0xA1},
-	{ MT_RF(6, 24),		RF_A_BAND_MB,	0x41},
-	{ MT_RF(6, 24),		RF_A_BAND_HB,	0x21},
-	{ MT_RF(6, 24),		RF_A_BAND_11J,	0xE1},
-
-	{ MT_RF(6, 39),		RF_A_BAND_LB,	0x36},
-	{ MT_RF(6, 39),		RF_A_BAND_MB,	0x34},
-	{ MT_RF(6, 39),		RF_A_BAND_HB,	0x32},
-	{ MT_RF(6, 39),		RF_A_BAND_11J,	0x37},
-
-	{ MT_RF(6, 42),		RF_A_BAND_LB,	0xFB},
-	{ MT_RF(6, 42),		RF_A_BAND_MB,	0xF3},
-	{ MT_RF(6, 42),		RF_A_BAND_HB,	0xEB},
-	{ MT_RF(6, 42),		RF_A_BAND_11J,	0xEB},
-
-	/* Move R6-R45, R50~R59 to mt76x0_RF_INT_PA_5G_Channel_0_RegTb/mt76x0_RF_EXT_PA_5G_Channel_0_RegTb */
-
-	{ MT_RF(6, 127),	RF_G_BAND,		0x84},
-	{ MT_RF(6, 127),	RF_A_BAND,		0x04},
-
-	{ MT_RF(7, 5),		RF_G_BAND,		0x40},
-	{ MT_RF(7, 5),		RF_A_BAND,		0x00},
-
-	{ MT_RF(7, 9),		RF_G_BAND,		0x00},
-	{ MT_RF(7, 9),		RF_A_BAND,		0x00},
-
-	{ MT_RF(7, 70),		RF_G_BAND,		0x00},
-	{ MT_RF(7, 70),		RF_A_BAND,		0x6D},
-
-	{ MT_RF(7, 71),		RF_G_BAND,		0x00},
-	{ MT_RF(7, 71),		RF_A_BAND,		0xB0},
-
-	{ MT_RF(7, 78),		RF_G_BAND,		0x00},
-	{ MT_RF(7, 78),		RF_A_BAND,		0x55},
-
-	{ MT_RF(7, 79),		RF_G_BAND,		0x00},
-	{ MT_RF(7, 79),		RF_A_BAND,		0x55},
+	/* bank, reg		bw/band		value */
+	{ MT_RF(0,  16),	RF_G_BAND,	0x20 },
+	{ MT_RF(0,  16),	RF_A_BAND,	0x20 },
+	{ MT_RF(0,  18),	RF_G_BAND,	0x00 },
+	{ MT_RF(0,  18),	RF_A_BAND,	0x00 },
+	{ MT_RF(0,  39),	RF_G_BAND,	0x36 },
+	{ MT_RF(0,  39),	RF_A_BAND_LB,	0x34 },
+	{ MT_RF(0,  39),	RF_A_BAND_MB,	0x33 },
+	{ MT_RF(0,  39),	RF_A_BAND_HB,	0x31 },
+	{ MT_RF(0,  39),	RF_A_BAND_11J,	0x36 },
+	{ MT_RF(6,  12),	RF_A_BAND_LB,	0x44 },
+	{ MT_RF(6,  12),	RF_A_BAND_MB,	0x44 },
+	{ MT_RF(6,  12),	RF_A_BAND_HB,	0x55 },
+	{ MT_RF(6,  12),	RF_A_BAND_11J,	0x44 },
+	{ MT_RF(6,  17),	RF_A_BAND_LB,	0x02 },
+	{ MT_RF(6,  17),	RF_A_BAND_MB,	0x00 },
+	{ MT_RF(6,  17),	RF_A_BAND_HB,	0x00 },
+	{ MT_RF(6,  17),	RF_A_BAND_11J,	0x05 },
+	{ MT_RF(6,  24),	RF_A_BAND_LB,	0xA1 },
+	{ MT_RF(6,  24),	RF_A_BAND_MB,	0x41 },
+	{ MT_RF(6,  24),	RF_A_BAND_HB,	0x21 },
+	{ MT_RF(6,  24),	RF_A_BAND_11J,	0xE1 },
+	{ MT_RF(6,  39),	RF_A_BAND_LB,	0x36 },
+	{ MT_RF(6,  39),	RF_A_BAND_MB,	0x34 },
+	{ MT_RF(6,  39),	RF_A_BAND_HB,	0x32 },
+	{ MT_RF(6,  39),	RF_A_BAND_11J,	0x37 },
+	{ MT_RF(6,  42),	RF_A_BAND_LB,	0xFB },
+	{ MT_RF(6,  42),	RF_A_BAND_MB,	0xF3 },
+	{ MT_RF(6,  42),	RF_A_BAND_HB,	0xEB },
+	{ MT_RF(6,  42),	RF_A_BAND_11J,	0xEB },
+	{ MT_RF(6, 127),	RF_G_BAND,	0x84 },
+	{ MT_RF(6, 127),	RF_A_BAND,	0x04 },
+	{ MT_RF(7,   5),	RF_G_BAND,	0x40 },
+	{ MT_RF(7,   5),	RF_A_BAND,	0x00 },
+	{ MT_RF(7,   9),	RF_G_BAND,	0x00 },
+	{ MT_RF(7,   9),	RF_A_BAND,	0x00 },
+	{ MT_RF(7,  70),	RF_G_BAND,	0x00 },
+	{ MT_RF(7,  70),	RF_A_BAND,	0x6D },
+	{ MT_RF(7,  71),	RF_G_BAND,	0x00 },
+	{ MT_RF(7,  71),	RF_A_BAND,	0xB0 },
+	{ MT_RF(7,  78),	RF_G_BAND,	0x00 },
+	{ MT_RF(7,  78),	RF_A_BAND,	0x55 },
+	{ MT_RF(7,  79),	RF_G_BAND,	0x00 },
+	{ MT_RF(7,  79),	RF_A_BAND,	0x55 },
 };
 
 static const struct mt76x0_freq_item mt76x0_frequency_plan[] = {
-	{1,	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xE2, 0x40, 0x02, 0x40, 0x02, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 2412 */
-	{2, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xE4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA1, 0, 0x30, 0, 0, 0x1}, /* Freq 2417 */
-	{3, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xE2, 0x40, 0x07, 0x40, 0x0B, 0, 0, 1, 0x50, 0, 0x30, 0, 0, 0x0}, /* Freq 2422 */
-	{4, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xD4, 0x40, 0x02, 0x40, 0x09, 0, 0, 1, 0x50, 0, 0x30, 0, 0, 0x0}, /* Freq 2427 */
-	{5, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA2, 0, 0x30, 0, 0, 0x1}, /* Freq 2432 */
-	{6, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x07, 0, 0, 1, 0xA2, 0, 0x30, 0, 0, 0x1}, /* Freq 2437 */
-	{7, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xE2, 0x40, 0x02, 0x40, 0x07, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 2442 */
-	{8, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA3, 0, 0x30, 0, 0, 0x1}, /* Freq 2447 */
-	{9, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xF2, 0x40, 0x07, 0x40, 0x0D, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 2452 */
-	{10, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xD4, 0x40, 0x02, 0x40, 0x09, 0, 0, 1, 0x51, 0, 0x30, 0, 0, 0x0}, /* Freq 2457 */
-	{11, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA4, 0, 0x30, 0, 0, 0x1}, /* Freq 2462 */
-	{12, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x07, 0, 0, 1, 0xA4, 0, 0x30, 0, 0, 0x1}, /* Freq 2467 */
-	{13, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xF2, 0x40, 0x02, 0x40, 0x02, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 2472 */
-	{14, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xF2, 0x40, 0x02, 0x40, 0x04, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 2484 */
-
-	{183, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 4915 */
-	{184, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x00, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4920 */
-	{185, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4925 */
-	{187, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4935 */
-	{188, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4940 */
-	{189, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4945 */
-	{192, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4960 */
-	{196, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4980 */
-
-	{36, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5180 */
-	{37, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5185 */
-	{38, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5190 */
-	{39, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5195 */
-	{40, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5200 */
-	{41, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5205 */
-	{42, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5210 */
-	{43, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5215 */
-	{44, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5220 */
-	{45, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5225 */
-	{46, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5230 */
-	{47, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5235 */
-	{48, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5240 */
-	{49, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5245 */
-	{50, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5250 */
-	{51, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5255 */
-	{52, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5260 */
-	{53, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5265 */
-	{54, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5270 */
-	{55, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5275 */
-	{56, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5280 */
-	{57, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5285 */
-	{58, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5290 */
-	{59, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5295 */
-	{60, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5300 */
-	{61, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5305 */
-	{62, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5310 */
-	{63, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5315 */
-	{64, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5320 */
-
-	{100, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5500 */
-	{101, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5505 */
-	{102, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5510 */
-	{103, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5515 */
-	{104, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5520 */
-	{105, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5525 */
-	{106, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5530 */
-	{107, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5535 */
-	{108, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5540 */
-	{109, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5545 */
-	{110, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5550 */
-	{111, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5555 */
-	{112, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5560 */
-	{113, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5565 */
-	{114, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5570 */
-	{115, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5575 */
-	{116, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5580 */
-	{117, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5585 */
-	{118, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5590 */
-	{119, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5595 */
-	{120, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5600 */
-	{121, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5605 */
-	{122, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5610 */
-	{123, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5615 */
-	{124, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5620 */
-	{125, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5625 */
-	{126, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5630 */
-	{127, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5635 */
-	{128, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5640 */
-	{129, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5645 */
-	{130, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5650 */
-	{131, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5655 */
-	{132, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5660 */
-	{133, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5665 */
-	{134, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5670 */
-	{135, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5675 */
-	{136, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5680 */
-
-	{137, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5685 */
-	{138, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5690 */
-	{139, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5695 */
-	{140, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5700 */
-	{141, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5705 */
-	{142, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5710 */
-	{143, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5715 */
-	{144, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5720 */
-	{145, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5725 */
-	{146, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5730 */
-	{147, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5735 */
-	{148, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5740 */
-	{149, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5745 */
-	{150, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5750 */
-	{151, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5755 */
-	{152, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5760 */
-	{153, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5765 */
-	{154, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5770 */
-	{155, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5775 */
-	{156, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5780 */
-	{157, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5785 */
-	{158, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5790 */
-	{159, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5795 */
-	{160, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5800 */
-	{161, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5805 */
-	{162, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5810 */
-	{163, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5815 */
-	{164, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5820 */
-	{165, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5825 */
-	{166, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5830 */
-	{167, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5835 */
-	{168, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5840 */
-	{169, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5845 */
-	{170, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5850 */
-	{171, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5855 */
-	{172, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5860 */
-	{173, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5865 */
+	{   1,	RF_G_BAND,			0x02, 0x3F, 0x28, 0xDD, 0xE2, 0x40, 0x02, 0x40, 0x02, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3 }, /* Freq 2412 */
+	{   2, 	RF_G_BAND,			0x02, 0x3F, 0x3C, 0xDD, 0xE4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA1, 0, 0x30, 0, 0, 0x1 }, /* Freq 2417 */
+	{   3, 	RF_G_BAND,			0x02, 0x3F, 0x3C, 0xDD, 0xE2, 0x40, 0x07, 0x40, 0x0B, 0, 0, 1, 0x50, 0, 0x30, 0, 0, 0x0 }, /* Freq 2422 */
+	{   4, 	RF_G_BAND,			0x02, 0x3F, 0x28, 0xDD, 0xD4, 0x40, 0x02, 0x40, 0x09, 0, 0, 1, 0x50, 0, 0x30, 0, 0, 0x0 }, /* Freq 2427 */
+	{   5, 	RF_G_BAND,			0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA2, 0, 0x30, 0, 0, 0x1 }, /* Freq 2432 */
+	{   6, 	RF_G_BAND,			0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x07, 0, 0, 1, 0xA2, 0, 0x30, 0, 0, 0x1 }, /* Freq 2437 */
+	{   7, 	RF_G_BAND,			0x02, 0x3F, 0x28, 0xDD, 0xE2, 0x40, 0x02, 0x40, 0x07, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3 }, /* Freq 2442 */
+	{   8, 	RF_G_BAND,			0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA3, 0, 0x30, 0, 0, 0x1 }, /* Freq 2447 */
+	{   9, 	RF_G_BAND,			0x02, 0x3F, 0x3C, 0xDD, 0xF2, 0x40, 0x07, 0x40, 0x0D, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3 }, /* Freq 2452 */
+	{  10, 	RF_G_BAND,			0x02, 0x3F, 0x28, 0xDD, 0xD4, 0x40, 0x02, 0x40, 0x09, 0, 0, 1, 0x51, 0, 0x30, 0, 0, 0x0 }, /* Freq 2457 */
+	{  11, 	RF_G_BAND,			0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA4, 0, 0x30, 0, 0, 0x1 }, /* Freq 2462 */
+	{  12, 	RF_G_BAND,			0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x07, 0, 0, 1, 0xA4, 0, 0x30, 0, 0, 0x1 }, /* Freq 2467 */
+	{  13, 	RF_G_BAND,			0x02, 0x3F, 0x28, 0xDD, 0xF2, 0x40, 0x02, 0x40, 0x02, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3 }, /* Freq 2472 */
+	{  14, 	RF_G_BAND,			0x02, 0x3F, 0x28, 0xDD, 0xF2, 0x40, 0x02, 0x40, 0x04, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3 }, /* Freq 2484 */
+	{ 183, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3 }, /* Freq 4915 */
+	{ 184, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x00, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3 }, /* Freq 4920 */
+	{ 185, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3 }, /* Freq 4925 */
+	{ 187, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3 }, /* Freq 4935 */
+	{ 188, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3 }, /* Freq 4940 */
+	{ 189, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3 }, /* Freq 4945 */
+	{ 192, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3 }, /* Freq 4960 */
+	{ 196, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3 }, /* Freq 4980 */
+	{  36, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5180 */
+	{  37, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5185 */
+	{  38, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5190 */
+	{  39, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5195 */
+	{  40, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5200 */
+	{  41, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5205 */
+	{  42, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5210 */
+	{  43, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5215 */
+	{  44, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5220 */
+	{  45, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5225 */
+	{  46, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5230 */
+	{  47, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5235 */
+	{  48, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5240 */
+	{  49, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5245 */
+	{  50, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5250 */
+	{  51, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5255 */
+	{  52, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5260 */
+	{  53, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5265 */
+	{  54, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5270 */
+	{  55, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3 }, /* Freq 5275 */
+	{  56, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3 }, /* Freq 5280 */
+	{  57, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3 }, /* Freq 5285 */
+	{  58, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3 }, /* Freq 5290 */
+	{  59, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3 }, /* Freq 5295 */
+	{  60, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3 }, /* Freq 5300 */
+	{  61, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3 }, /* Freq 5305 */
+	{  62, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3 }, /* Freq 5310 */
+	{  63, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3 }, /* Freq 5315 */
+	{  64, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3 }, /* Freq 5320 */
+	{ 100, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3 }, /* Freq 5500 */
+	{ 101, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3 }, /* Freq 5505 */
+	{ 102, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3 }, /* Freq 5510 */
+	{ 103, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3 }, /* Freq 5515 */
+	{ 104, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5520 */
+	{ 105, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5525 */
+	{ 106, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5530 */
+	{ 107, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5535 */
+	{ 108, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5540 */
+	{ 109, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5545 */
+	{ 110, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5550 */
+	{ 111, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5555 */
+	{ 112, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5560 */
+	{ 113, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5565 */
+	{ 114, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5570 */
+	{ 115, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5575 */
+	{ 116, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5580 */
+	{ 117, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5585 */
+	{ 118, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5590 */
+	{ 119, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5595 */
+	{ 120, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5600 */
+	{ 121, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5605 */
+	{ 122, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5610 */
+	{ 123, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5615 */
+	{ 124, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5620 */
+	{ 125, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5625 */
+	{ 126, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5630 */
+	{ 127, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3 }, /* Freq 5635 */
+	{ 128, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5640 */
+	{ 129, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5645 */
+	{ 130, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5650 */
+	{ 131, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5655 */
+	{ 132, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5660 */
+	{ 133, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5665 */
+	{ 134, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5670 */
+	{ 135, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5675 */
+	{ 136, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5680 */
+	{ 137, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5685 */
+	{ 138, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5690 */
+	{ 139, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5695 */
+	{ 140, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5700 */
+	{ 141, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5705 */
+	{ 142, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5710 */
+	{ 143, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5715 */
+	{ 144, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5720 */
+	{ 145, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5725 */
+	{ 146, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5730 */
+	{ 147, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5735 */
+	{ 148, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5740 */
+	{ 149, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5745 */
+	{ 150, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5750 */
+	{ 151, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3 }, /* Freq 5755 */
+	{ 152, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5760 */
+	{ 153, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5765 */
+	{ 154, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5770 */
+	{ 155, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5775 */
+	{ 156, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5780 */
+	{ 157, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5785 */
+	{ 158, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5790 */
+	{ 159, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5795 */
+	{ 160, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5800 */
+	{ 161, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5805 */
+	{ 162, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5810 */
+	{ 163, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5815 */
+	{ 164, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5820 */
+	{ 165, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5825 */
+	{ 166, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5830 */
+	{ 167, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5835 */
+	{ 168, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5840 */
+	{ 169, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5845 */
+	{ 170, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5850 */
+	{ 171, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5855 */
+	{ 172, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5860 */
+	{ 173, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3 }, /* Freq 5865 */
 };
 
 static const struct mt76x0_freq_item mt76x0_sdm_frequency_plan[] = {
-	{1,	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0xCCCC,  0x3}, /* Freq 2412 */
-	{2, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x12222, 0x3}, /* Freq 2417 */
-	{3, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x17777, 0x3}, /* Freq 2422 */
-	{4, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x1CCCC, 0x3}, /* Freq 2427 */
-	{5, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x22222, 0x3}, /* Freq 2432 */
-	{6, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x27777, 0x3}, /* Freq 2437 */
-	{7, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x2CCCC, 0x3}, /* Freq 2442 */
-	{8, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x32222, 0x3}, /* Freq 2447 */
-	{9, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x37777, 0x3}, /* Freq 2452 */
-	{10, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x3CCCC, 0x3}, /* Freq 2457 */
-	{11, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x2222, 0x3}, /* Freq 2462 */
-	{12, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x7777, 0x3}, /* Freq 2467 */
-	{13, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0xCCCC, 0x3}, /* Freq 2472 */
-	{14, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x19999, 0x3}, /* Freq 2484 */
-
-	{183, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 4915 */
-	{184, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x0,     0x3}, /* Freq 4920 */
-	{185, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x2AAA,  0x3}, /* Freq 4925 */
-	{187, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x8000,  0x3}, /* Freq 4935 */
-	{188, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0xAAAA,  0x3}, /* Freq 4940 */
-	{189, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0xD555,  0x3}, /* Freq 4945 */
-	{192, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 4960 */
-	{196, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 4980 */
-
-	{36, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0xAAAA,  0x3}, /* Freq 5180 */
-	{37, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0xD555,  0x3}, /* Freq 5185 */
-	{38, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5190 */
-	{39, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5195 */
-	{40, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5200 */
-	{41, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5205 */
-	{42, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5210 */
-	{43, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5215 */
-	{44, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5220 */
-	{45, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5225 */
-	{46, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5230 */
-	{47, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5235 */
-	{48, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5240 */
-	{49, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5245 */
-	{50, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5250 */
-	{51, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5255 */
-	{52, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5260 */
-	{53, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5265 */
-	{54, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5270 */
-	{55, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5275 */
-	{56, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5280 */
-	{57, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5285 */
-	{58, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5290 */
-	{59, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5295 */
-	{60, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5300 */
-	{61, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5305 */
-	{62, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5310 */
-	{63, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5315 */
-	{64, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5320 */
-
-	{100, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5500 */
-	{101, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5505 */
-	{102, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5510 */
-	{103, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5515 */
-	{104, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5520 */
-	{105, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5525 */
-	{106, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5530 */
-	{107, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5535 */
-	{108, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5540 */
-	{109, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5545 */
-	{110, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5550 */
-	{111, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5555 */
-	{112, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5560 */
-	{113, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5565 */
-	{114, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5570 */
-	{115, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5575 */
-	{116, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5580 */
-	{117, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5585 */
-	{118, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5590 */
-	{119, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5595 */
-	{120, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5600 */
-	{121, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5605 */
-	{122, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5610 */
-	{123, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5615 */
-	{124, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5620 */
-	{125, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5625 */
-	{126, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5630 */
-	{127, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5635 */
-	{128, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5640 */
-	{129, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5645 */
-	{130, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5650 */
-	{131, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5655 */
-	{132, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5660 */
-	{133, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5665 */
-	{134, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5670 */
-	{135, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5675 */
-	{136, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5680 */
-
-	{137, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5685 */
-	{138, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5690 */
-	{139, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5695 */
-	{140, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5700 */
-	{141, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5705 */
-	{142, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5710 */
-	{143, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5715 */
-	{144, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5720 */
-	{145, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5725 */
-	{146, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5730 */
-	{147, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5735 */
-	{148, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5740 */
-	{149, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5745 */
-	{150, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5750 */
-	{151, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5755 */
-	{152, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5760 */
-	{153, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5765 */
-	{154, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5770 */
-	{155, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5775 */
-	{156, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5780 */
-	{157, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5785 */
-	{158, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5790 */
-	{159, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5795 */
-	{160, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5800 */
-	{161, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5805 */
-	{162, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5810 */
-	{163, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5815 */
-	{164, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5820 */
-	{165, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5825 */
-	{166, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5830 */
-	{167, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5835 */
-	{168, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5840 */
-	{169, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5845 */
-	{170, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5850 */
-	{171, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5855 */
-	{172, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5860 */
-	{173, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5865 */
+	{   1,	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x28, 0, 0x0, 0x8, 0x0CCCC, 0x3 }, /* Freq 2412 */
+	{   2, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x28, 0, 0x0, 0x8, 0x12222, 0x3 }, /* Freq 2417 */
+	{   3, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x28, 0, 0x0, 0x8, 0x17777, 0x3 }, /* Freq 2422 */
+	{   4, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x28, 0, 0x0, 0x8, 0x1CCCC, 0x3 }, /* Freq 2427 */
+	{   5, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x28, 0, 0x0, 0x8, 0x22222, 0x3 }, /* Freq 2432 */
+	{   6, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x28, 0, 0x0, 0x8, 0x27777, 0x3 }, /* Freq 2437 */
+	{   7, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x28, 0, 0x0, 0x8, 0x2CCCC, 0x3 }, /* Freq 2442 */
+	{   8, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x28, 0, 0x0, 0x8, 0x32222, 0x3 }, /* Freq 2447 */
+	{   9, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x28, 0, 0x0, 0x8, 0x37777, 0x3 }, /* Freq 2452 */
+	{  10, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x28, 0, 0x0, 0x8, 0x3CCCC, 0x3 }, /* Freq 2457 */
+	{  11, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x29, 0, 0x0, 0x8, 0x02222, 0x3 }, /* Freq 2462 */
+	{  12, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x29, 0, 0x0, 0x8, 0x07777, 0x3 }, /* Freq 2467 */
+	{  13, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x29, 0, 0x0, 0x8, 0x0CCCC, 0x3 }, /* Freq 2472 */
+	{  14, 	RF_G_BAND,			0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x29, 0, 0x0, 0x8, 0x19999, 0x3 }, /* Freq 2484 */
+	{ 183, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x28, 0, 0x0, 0x8, 0x3D555, 0x3 }, /* Freq 4915 */
+	{ 184, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x29, 0, 0x0, 0x8, 0x00000, 0x3 }, /* Freq 4920 */
+	{ 185, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x29, 0, 0x0, 0x8, 0x02AAA, 0x3 }, /* Freq 4925 */
+	{ 187, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x29, 0, 0x0, 0x8, 0x08000, 0x3 }, /* Freq 4935 */
+	{ 188, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x29, 0, 0x0, 0x8, 0x0AAAA, 0x3 }, /* Freq 4940 */
+	{ 189, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x29, 0, 0x0, 0x8, 0x0D555, 0x3 }, /* Freq 4945 */
+	{ 192, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x29, 0, 0x0, 0x8, 0x15555, 0x3 }, /* Freq 4960 */
+	{ 196, 	(RF_A_BAND | RF_A_BAND_11J),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x29, 0, 0x0, 0x8, 0x20000, 0x3 }, /* Freq 4980 */
+	{  36, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x0AAAA, 0x3 }, /* Freq 5180 */
+	{  37, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x0D555, 0x3 }, /* Freq 5185 */
+	{  38, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x10000, 0x3 }, /* Freq 5190 */
+	{  39, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x12AAA, 0x3 }, /* Freq 5195 */
+	{  40, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x15555, 0x3 }, /* Freq 5200 */
+	{  41, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x18000, 0x3 }, /* Freq 5205 */
+	{  42, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x1AAAA, 0x3 }, /* Freq 5210 */
+	{  43, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x1D555, 0x3 }, /* Freq 5215 */
+	{  44, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x20000, 0x3 }, /* Freq 5220 */
+	{  45, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x22AAA, 0x3 }, /* Freq 5225 */
+	{  46, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x25555, 0x3 }, /* Freq 5230 */
+	{  47, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x28000, 0x3 }, /* Freq 5235 */
+	{  48, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x2AAAA, 0x3 }, /* Freq 5240 */
+	{  49, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x2D555, 0x3 }, /* Freq 5245 */
+	{  50, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x30000, 0x3 }, /* Freq 5250 */
+	{  51, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x32AAA, 0x3 }, /* Freq 5255 */
+	{  52, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x35555, 0x3 }, /* Freq 5260 */
+	{  53, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x38000, 0x3 }, /* Freq 5265 */
+	{  54, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x3AAAA, 0x3 }, /* Freq 5270 */
+	{  55, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2B, 0, 0x0, 0x8, 0x3D555, 0x3 }, /* Freq 5275 */
+	{  56, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2C, 0, 0x0, 0x8, 0x00000, 0x3 }, /* Freq 5280 */
+	{  57, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2C, 0, 0x0, 0x8, 0x02AAA, 0x3 }, /* Freq 5285 */
+	{  58, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2C, 0, 0x0, 0x8, 0x05555, 0x3 }, /* Freq 5290 */
+	{  59, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2C, 0, 0x0, 0x8, 0x08000, 0x3 }, /* Freq 5295 */
+	{  60, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2C, 0, 0x0, 0x8, 0x0AAAA, 0x3 }, /* Freq 5300 */
+	{  61, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2C, 0, 0x0, 0x8, 0x0D555, 0x3 }, /* Freq 5305 */
+	{  62, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2C, 0, 0x0, 0x8, 0x10000, 0x3 }, /* Freq 5310 */
+	{  63, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2C, 0, 0x0, 0x8, 0x12AAA, 0x3 }, /* Freq 5315 */
+	{  64, 	(RF_A_BAND | RF_A_BAND_LB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2C, 0, 0x0, 0x8, 0x15555, 0x3 }, /* Freq 5320 */
+	{ 100, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2D, 0, 0x0, 0x8, 0x35555, 0x3 }, /* Freq 5500 */
+	{ 101, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2D, 0, 0x0, 0x8, 0x38000, 0x3 }, /* Freq 5505 */
+	{ 102, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2D, 0, 0x0, 0x8, 0x3AAAA, 0x3 }, /* Freq 5510 */
+	{ 103, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2D, 0, 0x0, 0x8, 0x3D555, 0x3 }, /* Freq 5515 */
+	{ 104, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x00000, 0x3 }, /* Freq 5520 */
+	{ 105, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x02AAA, 0x3 }, /* Freq 5525 */
+	{ 106, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x05555, 0x3 }, /* Freq 5530 */
+	{ 107, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x08000, 0x3 }, /* Freq 5535 */
+	{ 108, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x0AAAA, 0x3 }, /* Freq 5540 */
+	{ 109, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x0D555, 0x3 }, /* Freq 5545 */
+	{ 110, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x10000, 0x3 }, /* Freq 5550 */
+	{ 111, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x12AAA, 0x3 }, /* Freq 5555 */
+	{ 112, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x15555, 0x3 }, /* Freq 5560 */
+	{ 113, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x18000, 0x3 }, /* Freq 5565 */
+	{ 114, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x1AAAA, 0x3 }, /* Freq 5570 */
+	{ 115, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x1D555, 0x3 }, /* Freq 5575 */
+	{ 116, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x20000, 0x3 }, /* Freq 5580 */
+	{ 117, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x22AAA, 0x3 }, /* Freq 5585 */
+	{ 118, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x25555, 0x3 }, /* Freq 5590 */
+	{ 119, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x28000, 0x3 }, /* Freq 5595 */
+	{ 120, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x2AAAA, 0x3 }, /* Freq 5600 */
+	{ 121, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x2D555, 0x3 }, /* Freq 5605 */
+	{ 122, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x30000, 0x3 }, /* Freq 5610 */
+	{ 123, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x32AAA, 0x3 }, /* Freq 5615 */
+	{ 124, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x35555, 0x3 }, /* Freq 5620 */
+	{ 125, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x38000, 0x3 }, /* Freq 5625 */
+	{ 126, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x3AAAA, 0x3 }, /* Freq 5630 */
+	{ 127, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2E, 0, 0x0, 0x8, 0x3D555, 0x3 }, /* Freq 5635 */
+	{ 128, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x00000, 0x3 }, /* Freq 5640 */
+	{ 129, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x02AAA, 0x3 }, /* Freq 5645 */
+	{ 130, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x05555, 0x3 }, /* Freq 5650 */
+	{ 131, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x08000, 0x3 }, /* Freq 5655 */
+	{ 132, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x0AAAA, 0x3 }, /* Freq 5660 */
+	{ 133, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x0D555, 0x3 }, /* Freq 5665 */
+	{ 134, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x10000, 0x3 }, /* Freq 5670 */
+	{ 135, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x12AAA, 0x3 }, /* Freq 5675 */
+	{ 136, 	(RF_A_BAND | RF_A_BAND_MB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x15555, 0x3 }, /* Freq 5680 */
+	{ 137, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x18000, 0x3 }, /* Freq 5685 */
+	{ 138, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x1AAAA, 0x3 }, /* Freq 5690 */
+	{ 139, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x1D555, 0x3 }, /* Freq 5695 */
+	{ 140, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x20000, 0x3 }, /* Freq 5700 */
+	{ 141, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x22AAA, 0x3 }, /* Freq 5705 */
+	{ 142, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x25555, 0x3 }, /* Freq 5710 */
+	{ 143, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x28000, 0x3 }, /* Freq 5715 */
+	{ 144, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x2AAAA, 0x3 }, /* Freq 5720 */
+	{ 145, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x2D555, 0x3 }, /* Freq 5725 */
+	{ 146, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x30000, 0x3 }, /* Freq 5730 */
+	{ 147, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x32AAA, 0x3 }, /* Freq 5735 */
+	{ 148, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x35555, 0x3 }, /* Freq 5740 */
+	{ 149, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x38000, 0x3 }, /* Freq 5745 */
+	{ 150, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x3AAAA, 0x3 }, /* Freq 5750 */
+	{ 151, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x2F, 0, 0x0, 0x8, 0x3D555, 0x3 }, /* Freq 5755 */
+	{ 152, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x00000, 0x3 }, /* Freq 5760 */
+	{ 153, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x02AAA, 0x3 }, /* Freq 5765 */
+	{ 154, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x05555, 0x3 }, /* Freq 5770 */
+	{ 155, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x08000, 0x3 }, /* Freq 5775 */
+	{ 156, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x0AAAA, 0x3 }, /* Freq 5780 */
+	{ 157, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x0D555, 0x3 }, /* Freq 5785 */
+	{ 158, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x10000, 0x3 }, /* Freq 5790 */
+	{ 159, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x12AAA, 0x3 }, /* Freq 5795 */
+	{ 160, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x15555, 0x3 }, /* Freq 5800 */
+	{ 161, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x18000, 0x3 }, /* Freq 5805 */
+	{ 162, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x1AAAA, 0x3 }, /* Freq 5810 */
+	{ 163, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x1D555, 0x3 }, /* Freq 5815 */
+	{ 164, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x20000, 0x3 }, /* Freq 5820 */
+	{ 165, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x22AAA, 0x3 }, /* Freq 5825 */
+	{ 166, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x25555, 0x3 }, /* Freq 5830 */
+	{ 167, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x28000, 0x3 }, /* Freq 5835 */
+	{ 168, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x2AAAA, 0x3 }, /* Freq 5840 */
+	{ 169, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x2D555, 0x3 }, /* Freq 5845 */
+	{ 170, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x30000, 0x3 }, /* Freq 5850 */
+	{ 171, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x32AAA, 0x3 }, /* Freq 5855 */
+	{ 172, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x35555, 0x3 }, /* Freq 5860 */
+	{ 173, 	(RF_A_BAND | RF_A_BAND_HB),	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0, 0, 0, 0x30, 0, 0x0, 0x8, 0x38000, 0x3 }, /* Freq 5865 */
 };
 
 static const u8 mt76x0_sdm_channel[] = {
-	183, 185, 43, 45, 54, 55, 57, 58, 102, 103, 105, 106, 115, 117, 126, 127, 129, 130, 139, 141, 150, 151, 153, 154, 163, 165
+	183, 185,  43,  45,
+	54,   55,  57,  58,
+	102, 103, 105, 106,
+	115, 117, 126, 127,
+	129, 130, 139, 141,
+	150, 151, 153, 154,
+	163, 165
 };
 
 static const struct mt76x0_rf_switch_item mt76x0_rf_ext_pa_tab[] = {
-	{ MT_RF(6, 45),		RF_A_BAND_LB,	0x63},
-	{ MT_RF(6, 45),		RF_A_BAND_MB,	0x43},
-	{ MT_RF(6, 45),		RF_A_BAND_HB,	0x33},
-	{ MT_RF(6, 45),		RF_A_BAND_11J,	0x73},
-
-	{ MT_RF(6, 50),		RF_A_BAND_LB,	0x02},
-	{ MT_RF(6, 50),		RF_A_BAND_MB,	0x02},
-	{ MT_RF(6, 50),		RF_A_BAND_HB,	0x02},
-	{ MT_RF(6, 50),		RF_A_BAND_11J,	0x02},
-
-	{ MT_RF(6, 51),		RF_A_BAND_LB,	0x02},
-	{ MT_RF(6, 51),		RF_A_BAND_MB,	0x02},
-	{ MT_RF(6, 51),		RF_A_BAND_HB,	0x02},
-	{ MT_RF(6, 51),		RF_A_BAND_11J,	0x02},
-
-	{ MT_RF(6, 52),		RF_A_BAND_LB,	0x08},
-	{ MT_RF(6, 52),		RF_A_BAND_MB,	0x08},
-	{ MT_RF(6, 52),		RF_A_BAND_HB,	0x08},
-	{ MT_RF(6, 52),		RF_A_BAND_11J,	0x08},
-
-	{ MT_RF(6, 53),		RF_A_BAND_LB,	0x08},
-	{ MT_RF(6, 53),		RF_A_BAND_MB,	0x08},
-	{ MT_RF(6, 53),		RF_A_BAND_HB,	0x08},
-	{ MT_RF(6, 53),		RF_A_BAND_11J,	0x08},
-
-	{ MT_RF(6, 54),		RF_A_BAND_LB,	0x0A},
-	{ MT_RF(6, 54),		RF_A_BAND_MB,	0x0A},
-	{ MT_RF(6, 54),		RF_A_BAND_HB,	0x0A},
-	{ MT_RF(6, 54),		RF_A_BAND_11J,	0x0A},
-
-	{ MT_RF(6, 55),		RF_A_BAND_LB,	0x0A},
-	{ MT_RF(6, 55),		RF_A_BAND_MB,	0x0A},
-	{ MT_RF(6, 55),		RF_A_BAND_HB,	0x0A},
-	{ MT_RF(6, 55),		RF_A_BAND_11J,	0x0A},
-
-	{ MT_RF(6, 56),		RF_A_BAND_LB,	0x05},
-	{ MT_RF(6, 56),		RF_A_BAND_MB,	0x05},
-	{ MT_RF(6, 56),		RF_A_BAND_HB,	0x05},
-	{ MT_RF(6, 56),		RF_A_BAND_11J,	0x05},
-
-	{ MT_RF(6, 57),		RF_A_BAND_LB,	0x05},
-	{ MT_RF(6, 57),		RF_A_BAND_MB,	0x05},
-	{ MT_RF(6, 57),		RF_A_BAND_HB,	0x05},
-	{ MT_RF(6, 57),		RF_A_BAND_11J,	0x05},
-
-	{ MT_RF(6, 58),		RF_A_BAND_LB,	0x05},
-	{ MT_RF(6, 58),		RF_A_BAND_MB,	0x03},
-	{ MT_RF(6, 58),		RF_A_BAND_HB,	0x02},
-	{ MT_RF(6, 58),		RF_A_BAND_11J,	0x07},
-
-	{ MT_RF(6, 59),		RF_A_BAND_LB,	0x05},
-	{ MT_RF(6, 59),		RF_A_BAND_MB,	0x03},
-	{ MT_RF(6, 59),		RF_A_BAND_HB,	0x02},
-	{ MT_RF(6, 59),		RF_A_BAND_11J,	0x07},
+	{ MT_RF(6, 45),	RF_A_BAND_LB,	0x63 },
+	{ MT_RF(6, 45),	RF_A_BAND_MB,	0x43 },
+	{ MT_RF(6, 45),	RF_A_BAND_HB,	0x33 },
+	{ MT_RF(6, 45),	RF_A_BAND_11J,	0x73 },
+	{ MT_RF(6, 50),	RF_A_BAND_LB,	0x02 },
+	{ MT_RF(6, 50),	RF_A_BAND_MB,	0x02 },
+	{ MT_RF(6, 50),	RF_A_BAND_HB,	0x02 },
+	{ MT_RF(6, 50),	RF_A_BAND_11J,	0x02 },
+	{ MT_RF(6, 51),	RF_A_BAND_LB,	0x02 },
+	{ MT_RF(6, 51),	RF_A_BAND_MB,	0x02 },
+	{ MT_RF(6, 51),	RF_A_BAND_HB,	0x02 },
+	{ MT_RF(6, 51),	RF_A_BAND_11J,	0x02 },
+	{ MT_RF(6, 52),	RF_A_BAND_LB,	0x08 },
+	{ MT_RF(6, 52),	RF_A_BAND_MB,	0x08 },
+	{ MT_RF(6, 52),	RF_A_BAND_HB,	0x08 },
+	{ MT_RF(6, 52),	RF_A_BAND_11J,	0x08 },
+	{ MT_RF(6, 53),	RF_A_BAND_LB,	0x08 },
+	{ MT_RF(6, 53),	RF_A_BAND_MB,	0x08 },
+	{ MT_RF(6, 53),	RF_A_BAND_HB,	0x08 },
+	{ MT_RF(6, 53),	RF_A_BAND_11J,	0x08 },
+	{ MT_RF(6, 54),	RF_A_BAND_LB,	0x0A },
+	{ MT_RF(6, 54),	RF_A_BAND_MB,	0x0A },
+	{ MT_RF(6, 54),	RF_A_BAND_HB,	0x0A },
+	{ MT_RF(6, 54),	RF_A_BAND_11J,	0x0A },
+	{ MT_RF(6, 55),	RF_A_BAND_LB,	0x0A },
+	{ MT_RF(6, 55),	RF_A_BAND_MB,	0x0A },
+	{ MT_RF(6, 55),	RF_A_BAND_HB,	0x0A },
+	{ MT_RF(6, 55),	RF_A_BAND_11J,	0x0A },
+	{ MT_RF(6, 56),	RF_A_BAND_LB,	0x05 },
+	{ MT_RF(6, 56),	RF_A_BAND_MB,	0x05 },
+	{ MT_RF(6, 56),	RF_A_BAND_HB,	0x05 },
+	{ MT_RF(6, 56),	RF_A_BAND_11J,	0x05 },
+	{ MT_RF(6, 57),	RF_A_BAND_LB,	0x05 },
+	{ MT_RF(6, 57),	RF_A_BAND_MB,	0x05 },
+	{ MT_RF(6, 57),	RF_A_BAND_HB,	0x05 },
+	{ MT_RF(6, 57),	RF_A_BAND_11J,	0x05 },
+	{ MT_RF(6, 58),	RF_A_BAND_LB,	0x05 },
+	{ MT_RF(6, 58),	RF_A_BAND_MB,	0x03 },
+	{ MT_RF(6, 58),	RF_A_BAND_HB,	0x02 },
+	{ MT_RF(6, 58),	RF_A_BAND_11J,	0x07 },
+	{ MT_RF(6, 59),	RF_A_BAND_LB,	0x05 },
+	{ MT_RF(6, 59),	RF_A_BAND_MB,	0x03 },
+	{ MT_RF(6, 59),	RF_A_BAND_HB,	0x02 },
+	{ MT_RF(6, 59),	RF_A_BAND_11J,	0x07 },
 };
 
 #endif
-- 
cgit v1.2.3


From 6250318694cad72f3dd6e5ead2bd612126383bb4 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 15 Oct 2018 11:33:11 +0200
Subject: mt76x0: pci: add get_survey support

Move mt76x02_update_channel routine in mt76x02-lib module in
order to be reused by mt76x0 driver adding get_survey support

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c      |  2 ++
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c     |  5 +++++
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c      |  2 ++
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c     | 18 ++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.h     |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h   |  2 --
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c  | 19 +------------------
 8 files changed, 30 insertions(+), 21 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
index 7a422c590211..9cabe8ebf5da 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
@@ -137,6 +137,8 @@ void mt76x0_mac_work(struct work_struct *work)
 	u32 sum, n;
 	int i, j, k;
 
+	mt76x02_update_channel(&dev->mt76);
+
 	/* Note: using MCU_RANDOM_READ is actually slower then reading all the
 	 *	 registers by hand.  MCU takes ca. 20ms to complete read of 24
 	 *	 registers while reading them one by one will takes roughly
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index 9273d2d2764a..e9fbbabbe7e0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -25,6 +25,11 @@ mt76x0_set_channel(struct mt76x02_dev *dev, struct cfg80211_chan_def *chandef)
 
 	mt76_set_channel(&dev->mt76);
 	ret = mt76x0_phy_set_channel(dev, chandef);
+
+	/* channel cycle counters read-and-clear */
+	mt76_rr(dev, MT_CH_IDLE);
+	mt76_rr(dev, MT_CH_BUSY);
+
 	mt76_txq_schedule_all(&dev->mt76);
 
 	return ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 522c86059bcb..3277e6b07a46 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -85,6 +85,7 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.ampdu_action = mt76x02_ampdu_action,
 	.sta_rate_tbl_update = mt76x02_sta_rate_tbl_update,
 	.wake_tx_queue = mt76_wake_tx_queue,
+	.get_survey = mt76_get_survey,
 };
 
 static int mt76x0e_register_device(struct mt76x02_dev *dev)
@@ -135,6 +136,7 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	static const struct mt76_driver_ops drv_ops = {
 		.txwi_size = sizeof(struct mt76x02_txwi),
+		.update_survey = mt76x02_update_channel,
 		.tx_prepare_skb = mt76x02_tx_prepare_skb,
 		.tx_complete_skb = mt76x02_tx_complete_skb,
 		.rx_skb = mt76x02_queue_rx_skb,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index 10578e4cb269..e6d6ddaa5a07 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -735,3 +735,21 @@ void mt76x02_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
 		dev_kfree_skb_any(e->skb);
 }
 EXPORT_SYMBOL_GPL(mt76x02_tx_complete_skb);
+
+void mt76x02_update_channel(struct mt76_dev *mdev)
+{
+	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
+	struct mt76_channel_state *state;
+	u32 active, busy;
+
+	state = mt76_channel_state(&dev->mt76, dev->mt76.chandef.chan);
+
+	busy = mt76_rr(dev, MT_CH_BUSY);
+	active = busy + mt76_rr(dev, MT_CH_IDLE);
+
+	spin_lock_bh(&dev->mt76.cc_lock);
+	state->cc_busy += busy;
+	state->cc_active += active;
+	spin_unlock_bh(&dev->mt76.cc_lock);
+}
+EXPORT_SYMBOL_GPL(mt76x02_update_channel);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index d99c18743969..6bce18bcbf36 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -226,4 +226,5 @@ void mt76x02_mac_write_txwi(struct mt76x02_dev *dev, struct mt76x02_txwi *txwi,
 void mt76x02_mac_poll_tx_status(struct mt76x02_dev *dev, bool irq);
 void mt76x02_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
 			     struct mt76_queue_entry *e, bool flush);
+void mt76x02_update_channel(struct mt76_dev *mdev);
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index be0ae24d310a..72c365040be1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -85,8 +85,6 @@ void mt76x2_pre_tbtt_tasklet(unsigned long arg);
 
 void mt76x2_sta_ps(struct mt76_dev *dev, struct ieee80211_sta *sta, bool ps);
 
-void mt76x2_update_channel(struct mt76_dev *mdev);
-
 void mt76x2_reset_wlan(struct mt76x02_dev *dev, bool enable);
 void mt76x2_init_txpower(struct mt76x02_dev *dev,
 			 struct ieee80211_supported_band *sband);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 3824290b219d..279edc612119 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -354,7 +354,7 @@ struct mt76x02_dev *mt76x2_alloc_device(struct device *pdev)
 {
 	static const struct mt76_driver_ops drv_ops = {
 		.txwi_size = sizeof(struct mt76x02_txwi),
-		.update_survey = mt76x2_update_channel,
+		.update_survey = mt76x02_update_channel,
 		.tx_prepare_skb = mt76x02_tx_prepare_skb,
 		.tx_complete_skb = mt76x02_tx_complete_skb,
 		.rx_skb = mt76x02_queue_rx_skb,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c
index 4b331ed14bb2..15620d4d425e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c
@@ -137,30 +137,13 @@ void mt76x2_mac_set_beacon_enable(struct mt76x02_dev *dev,
 		mt76x02_irq_disable(dev, MT_INT_PRE_TBTT | MT_INT_TBTT);
 }
 
-void mt76x2_update_channel(struct mt76_dev *mdev)
-{
-	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
-	struct mt76_channel_state *state;
-	u32 active, busy;
-
-	state = mt76_channel_state(&dev->mt76, dev->mt76.chandef.chan);
-
-	busy = mt76_rr(dev, MT_CH_BUSY);
-	active = busy + mt76_rr(dev, MT_CH_IDLE);
-
-	spin_lock_bh(&dev->mt76.cc_lock);
-	state->cc_busy += busy;
-	state->cc_active += active;
-	spin_unlock_bh(&dev->mt76.cc_lock);
-}
-
 void mt76x2_mac_work(struct work_struct *work)
 {
 	struct mt76x02_dev *dev = container_of(work, struct mt76x02_dev,
 					       mac_work.work);
 	int i, idx;
 
-	mt76x2_update_channel(&dev->mt76);
+	mt76x02_update_channel(&dev->mt76);
 	for (i = 0, idx = 0; i < 16; i++) {
 		u32 val = mt76_rr(dev, MT_TX_AGG_CNT(i));
 
-- 
cgit v1.2.3


From 7dd735883dec1c0e8d64e22b56dda3848c0d48e3 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 15 Oct 2018 11:33:12 +0200
Subject: mt76: move mt76x02_mac_work routine in mt76x02-lib module

Move mt76x02_mac_work routine in mt76x02_mac.c in order to be reused by
mt76x0 driver to read device statistics

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h   |  2 --
 drivers/net/wireless/mediatek/mt76/mt76x02.h         |  2 ++
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c     | 19 +++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.h     |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x2/mac.h      |  2 --
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h   |  2 --
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c  | 18 ------------------
 8 files changed, 23 insertions(+), 25 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index f27335ccb582..17fc7206c55d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -28,8 +28,6 @@
 #include "../mt76x02.h"
 #include "eeprom.h"
 
-#define MT_CALIBRATE_INTERVAL		(4 * HZ)
-
 #define MT_USB_AGGR_SIZE_LIMIT		21 /* * 1024B */
 #define MT_USB_AGGR_TIMEOUT		0x80 /* * 33ns */
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 47c42c607964..189c697973bd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -26,6 +26,8 @@
 #include "mt76x02_dfs.h"
 #include "mt76x02_dma.h"
 
+#define MT_CALIBRATE_INTERVAL	HZ
+
 struct mt76x02_mac_stats {
 	u64 rx_stat[6];
 	u64 tx_stat[6];
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index e6d6ddaa5a07..c7666f4c432f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -753,3 +753,22 @@ void mt76x02_update_channel(struct mt76_dev *mdev)
 	spin_unlock_bh(&dev->mt76.cc_lock);
 }
 EXPORT_SYMBOL_GPL(mt76x02_update_channel);
+
+void mt76x02_mac_work(struct work_struct *work)
+{
+	struct mt76x02_dev *dev = container_of(work, struct mt76x02_dev,
+					       mac_work.work);
+	int i, idx;
+
+	mt76x02_update_channel(&dev->mt76);
+	for (i = 0, idx = 0; i < 16; i++) {
+		u32 val = mt76_rr(dev, MT_TX_AGG_CNT(i));
+
+		dev->aggr_stats[idx++] += val & 0xffff;
+		dev->aggr_stats[idx++] += val >> 16;
+	}
+
+	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mac_work,
+				     MT_CALIBRATE_INTERVAL);
+}
+EXPORT_SYMBOL_GPL(mt76x02_mac_work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index 6bce18bcbf36..c1936e2277d1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -227,4 +227,5 @@ void mt76x02_mac_poll_tx_status(struct mt76x02_dev *dev, bool irq);
 void mt76x02_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
 			     struct mt76_queue_entry *e, bool flush);
 void mt76x02_update_channel(struct mt76_dev *mdev);
+void mt76x02_mac_work(struct work_struct *work);
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mac.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mac.h
index a31bd49ae6cb..2dc2b9d5dc8f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mac.h
@@ -32,6 +32,4 @@ int mt76x2_mac_set_beacon(struct mt76x02_dev *dev, u8 vif_idx,
 			  struct sk_buff *skb);
 void mt76x2_mac_set_beacon_enable(struct mt76x02_dev *dev, u8 vif_idx, bool val);
 
-void mt76x2_mac_work(struct work_struct *work);
-
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index 72c365040be1..eca142ac656d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -31,8 +31,6 @@
 #define MT7662_ROM_PATCH	"mt7662_rom_patch.bin"
 #define MT7662_EEPROM_SIZE	512
 
-#define MT_CALIBRATE_INTERVAL	HZ
-
 #include "../mt76x02.h"
 #include "mac.h"
 #include "dfs.h"
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 279edc612119..0dea7d7b17a3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -467,7 +467,7 @@ int mt76x2_register_device(struct mt76x02_dev *dev)
 	int i, ret;
 
 	INIT_DELAYED_WORK(&dev->cal_work, mt76x2_phy_calibrate);
-	INIT_DELAYED_WORK(&dev->mac_work, mt76x2_mac_work);
+	INIT_DELAYED_WORK(&dev->mac_work, mt76x02_mac_work);
 
 	mt76x2_init_device(dev);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c
index 15620d4d425e..97128ea6bd7a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c
@@ -137,24 +137,6 @@ void mt76x2_mac_set_beacon_enable(struct mt76x02_dev *dev,
 		mt76x02_irq_disable(dev, MT_INT_PRE_TBTT | MT_INT_TBTT);
 }
 
-void mt76x2_mac_work(struct work_struct *work)
-{
-	struct mt76x02_dev *dev = container_of(work, struct mt76x02_dev,
-					       mac_work.work);
-	int i, idx;
-
-	mt76x02_update_channel(&dev->mt76);
-	for (i = 0, idx = 0; i < 16; i++) {
-		u32 val = mt76_rr(dev, MT_TX_AGG_CNT(i));
-
-		dev->aggr_stats[idx++] += val & 0xffff;
-		dev->aggr_stats[idx++] += val >> 16;
-	}
-
-	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mac_work,
-				     MT_CALIBRATE_INTERVAL);
-}
-
 void mt76x2_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val)
 {
 	u32 data = 0;
-- 
cgit v1.2.3


From 760554130852f6ab0d9fabb3f9f40b191b849787 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 15 Oct 2018 11:33:13 +0200
Subject: mt76: move mt76x02_debugfs in mt76x02-lib module

Move mt76x02_debugfs in mt76x02-lib module in order to
be reused by mt76x0 driver and remove duplicated code

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/Makefile        |   2 +-
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |   2 +
 .../net/wireless/mediatek/mt76/mt76x02_debugfs.c   | 137 +++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2/Makefile |   2 +-
 .../net/wireless/mediatek/mt76/mt76x2/debugfs.c    | 137 ---------------------
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h |   1 -
 .../net/wireless/mediatek/mt76/mt76x2/pci_init.c   |   2 +-
 .../net/wireless/mediatek/mt76/mt76x2/usb_init.c   |   2 +-
 8 files changed, 143 insertions(+), 142 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2/debugfs.c

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index 9b8d7488c545..a737a518802f 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -14,7 +14,7 @@ CFLAGS_mt76x02_trace.o := -I$(src)
 
 mt76x02-lib-y := mt76x02_util.o mt76x02_mac.o mt76x02_mcu.o \
 		 mt76x02_eeprom.o mt76x02_phy.o mt76x02_mmio.o \
-		 mt76x02_txrx.o mt76x02_trace.o
+		 mt76x02_txrx.o mt76x02_trace.o mt76x02_debugfs.o
 
 mt76x02-usb-y := mt76x02_usb_mcu.o mt76x02_usb_core.o
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 189c697973bd..58721307d917 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -162,6 +162,8 @@ void mt76x02_set_beacon_offsets(struct mt76x02_dev *dev);
 void mt76x02_set_irq_mask(struct mt76x02_dev *dev, u32 clear, u32 set);
 void mt76x02_mac_start(struct mt76x02_dev *dev);
 
+void mt76x02_init_debugfs(struct mt76x02_dev *dev);
+
 static inline bool is_mt76x2(struct mt76x02_dev *dev)
 {
 	return mt76_chip(&dev->mt76) == 0x7612 ||
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c
new file mode 100644
index 000000000000..a9d52ba1e270
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c
@@ -0,0 +1,137 @@
+/*
+ * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/debugfs.h>
+#include "mt76x02.h"
+
+static int
+mt76x02_ampdu_stat_read(struct seq_file *file, void *data)
+{
+	struct mt76x02_dev *dev = file->private;
+	int i, j;
+
+	for (i = 0; i < 4; i++) {
+		seq_puts(file, "Length: ");
+		for (j = 0; j < 8; j++)
+			seq_printf(file, "%8d | ", i * 8 + j + 1);
+		seq_puts(file, "\n");
+		seq_puts(file, "Count:  ");
+		for (j = 0; j < 8; j++)
+			seq_printf(file, "%8d | ", dev->aggr_stats[i * 8 + j]);
+		seq_puts(file, "\n");
+		seq_puts(file, "--------");
+		for (j = 0; j < 8; j++)
+			seq_puts(file, "-----------");
+		seq_puts(file, "\n");
+	}
+
+	return 0;
+}
+
+static int
+mt76x02_ampdu_stat_open(struct inode *inode, struct file *f)
+{
+	return single_open(f, mt76x02_ampdu_stat_read, inode->i_private);
+}
+
+static int read_txpower(struct seq_file *file, void *data)
+{
+	struct mt76x02_dev *dev = dev_get_drvdata(file->private);
+
+	seq_printf(file, "Target power: %d\n", dev->target_power);
+
+	mt76_seq_puts_array(file, "Delta", dev->target_power_delta,
+			    ARRAY_SIZE(dev->target_power_delta));
+	return 0;
+}
+
+static const struct file_operations fops_ampdu_stat = {
+	.open = mt76x02_ampdu_stat_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int
+mt76x02_dfs_stat_read(struct seq_file *file, void *data)
+{
+	struct mt76x02_dev *dev = file->private;
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	int i;
+
+	seq_printf(file, "allocated sequences:\t%d\n",
+		   dfs_pd->seq_stats.seq_pool_len);
+	seq_printf(file, "used sequences:\t\t%d\n",
+		   dfs_pd->seq_stats.seq_len);
+	seq_puts(file, "\n");
+
+	for (i = 0; i < MT_DFS_NUM_ENGINES; i++) {
+		seq_printf(file, "engine: %d\n", i);
+		seq_printf(file, "  hw pattern detected:\t%d\n",
+			   dfs_pd->stats[i].hw_pattern);
+		seq_printf(file, "  hw pulse discarded:\t%d\n",
+			   dfs_pd->stats[i].hw_pulse_discarded);
+		seq_printf(file, "  sw pattern detected:\t%d\n",
+			   dfs_pd->stats[i].sw_pattern);
+	}
+
+	return 0;
+}
+
+static int
+mt76x02_dfs_stat_open(struct inode *inode, struct file *f)
+{
+	return single_open(f, mt76x02_dfs_stat_read, inode->i_private);
+}
+
+static const struct file_operations fops_dfs_stat = {
+	.open = mt76x02_dfs_stat_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int read_agc(struct seq_file *file, void *data)
+{
+	struct mt76x02_dev *dev = dev_get_drvdata(file->private);
+
+	seq_printf(file, "avg_rssi: %d\n", dev->cal.avg_rssi_all);
+	seq_printf(file, "low_gain: %d\n", dev->cal.low_gain);
+	seq_printf(file, "false_cca: %d\n", dev->cal.false_cca);
+	seq_printf(file, "agc_gain_adjust: %d\n", dev->cal.agc_gain_adjust);
+
+	return 0;
+}
+
+void mt76x02_init_debugfs(struct mt76x02_dev *dev)
+{
+	struct dentry *dir;
+
+	dir = mt76_register_debugfs(&dev->mt76);
+	if (!dir)
+		return;
+
+	debugfs_create_u8("temperature", 0400, dir, &dev->cal.temp);
+	debugfs_create_bool("tpc", 0600, dir, &dev->enable_tpc);
+
+	debugfs_create_file("ampdu_stat", 0400, dir, dev, &fops_ampdu_stat);
+	debugfs_create_file("dfs_stats", 0400, dir, dev, &fops_dfs_stat);
+	debugfs_create_devm_seqfile(dev->mt76.dev, "txpower", dir,
+				    read_txpower);
+
+	debugfs_create_devm_seqfile(dev->mt76.dev, "agc", dir, read_agc);
+}
+EXPORT_SYMBOL_GPL(mt76x02_init_debugfs);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile b/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
index b71bb1049170..696f071f47f8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
@@ -3,7 +3,7 @@ obj-$(CONFIG_MT76x2E) += mt76x2e.o
 obj-$(CONFIG_MT76x2U) += mt76x2u.o
 
 mt76x2-common-y := \
-	eeprom.o mac.o init.o phy.o debugfs.o mcu.o
+	eeprom.o mac.o init.o phy.o mcu.o
 
 mt76x2e-y := \
 	pci.o pci_main.o pci_init.o pci_tx.o \
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x2/debugfs.c
deleted file mode 100644
index e8f8ccc0a5ed..000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/debugfs.c
+++ /dev/null
@@ -1,137 +0,0 @@
-/*
- * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- */
-
-#include <linux/debugfs.h>
-#include "mt76x2.h"
-
-static int
-mt76x2_ampdu_stat_read(struct seq_file *file, void *data)
-{
-	struct mt76x02_dev *dev = file->private;
-	int i, j;
-
-	for (i = 0; i < 4; i++) {
-		seq_puts(file, "Length: ");
-		for (j = 0; j < 8; j++)
-			seq_printf(file, "%8d | ", i * 8 + j + 1);
-		seq_puts(file, "\n");
-		seq_puts(file, "Count:  ");
-		for (j = 0; j < 8; j++)
-			seq_printf(file, "%8d | ", dev->aggr_stats[i * 8 + j]);
-		seq_puts(file, "\n");
-		seq_puts(file, "--------");
-		for (j = 0; j < 8; j++)
-			seq_puts(file, "-----------");
-		seq_puts(file, "\n");
-	}
-
-	return 0;
-}
-
-static int
-mt76x2_ampdu_stat_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, mt76x2_ampdu_stat_read, inode->i_private);
-}
-
-static int read_txpower(struct seq_file *file, void *data)
-{
-	struct mt76x02_dev *dev = dev_get_drvdata(file->private);
-
-	seq_printf(file, "Target power: %d\n", dev->target_power);
-
-	mt76_seq_puts_array(file, "Delta", dev->target_power_delta,
-			    ARRAY_SIZE(dev->target_power_delta));
-	return 0;
-}
-
-static const struct file_operations fops_ampdu_stat = {
-	.open = mt76x2_ampdu_stat_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-static int
-mt76x2_dfs_stat_read(struct seq_file *file, void *data)
-{
-	struct mt76x02_dev *dev = file->private;
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-	int i;
-
-	seq_printf(file, "allocated sequences:\t%d\n",
-		   dfs_pd->seq_stats.seq_pool_len);
-	seq_printf(file, "used sequences:\t\t%d\n",
-		   dfs_pd->seq_stats.seq_len);
-	seq_puts(file, "\n");
-
-	for (i = 0; i < MT_DFS_NUM_ENGINES; i++) {
-		seq_printf(file, "engine: %d\n", i);
-		seq_printf(file, "  hw pattern detected:\t%d\n",
-			   dfs_pd->stats[i].hw_pattern);
-		seq_printf(file, "  hw pulse discarded:\t%d\n",
-			   dfs_pd->stats[i].hw_pulse_discarded);
-		seq_printf(file, "  sw pattern detected:\t%d\n",
-			   dfs_pd->stats[i].sw_pattern);
-	}
-
-	return 0;
-}
-
-static int
-mt76x2_dfs_stat_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, mt76x2_dfs_stat_read, inode->i_private);
-}
-
-static const struct file_operations fops_dfs_stat = {
-	.open = mt76x2_dfs_stat_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-static int read_agc(struct seq_file *file, void *data)
-{
-	struct mt76x02_dev *dev = dev_get_drvdata(file->private);
-
-	seq_printf(file, "avg_rssi: %d\n", dev->cal.avg_rssi_all);
-	seq_printf(file, "low_gain: %d\n", dev->cal.low_gain);
-	seq_printf(file, "false_cca: %d\n", dev->cal.false_cca);
-	seq_printf(file, "agc_gain_adjust: %d\n", dev->cal.agc_gain_adjust);
-
-	return 0;
-}
-
-void mt76x2_init_debugfs(struct mt76x02_dev *dev)
-{
-	struct dentry *dir;
-
-	dir = mt76_register_debugfs(&dev->mt76);
-	if (!dir)
-		return;
-
-	debugfs_create_u8("temperature", 0400, dir, &dev->cal.temp);
-	debugfs_create_bool("tpc", 0600, dir, &dev->enable_tpc);
-
-	debugfs_create_file("ampdu_stat", 0400, dir, dev, &fops_ampdu_stat);
-	debugfs_create_file("dfs_stats", 0400, dir, dev, &fops_dfs_stat);
-	debugfs_create_devm_seqfile(dev->mt76.dev, "txpower", dir,
-				    read_txpower);
-
-	debugfs_create_devm_seqfile(dev->mt76.dev, "agc", dir, read_agc);
-}
-EXPORT_SYMBOL_GPL(mt76x2_init_debugfs);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index eca142ac656d..7408db788409 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -52,7 +52,6 @@ extern const struct ieee80211_ops mt76x2_ops;
 
 struct mt76x02_dev *mt76x2_alloc_device(struct device *pdev);
 int mt76x2_register_device(struct mt76x02_dev *dev);
-void mt76x2_init_debugfs(struct mt76x02_dev *dev);
 void mt76x2_init_device(struct mt76x02_dev *dev);
 
 void mt76x2_phy_power_on(struct mt76x02_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 0dea7d7b17a3..5b167aaaf7f7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -515,7 +515,7 @@ int mt76x2_register_device(struct mt76x02_dev *dev)
 	if (ret)
 		goto fail;
 
-	mt76x2_init_debugfs(dev);
+	mt76x02_init_debugfs(dev);
 	mt76x2_init_txpower(dev, &dev->mt76.sband_2g.sband);
 	mt76x2_init_txpower(dev, &dev->mt76.sband_5g.sband);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
index 13cce2937573..dfc80ecfde92 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
@@ -282,7 +282,7 @@ int mt76x2u_register_device(struct mt76x02_dev *dev)
 
 	set_bit(MT76_STATE_INITIALIZED, &dev->mt76.state);
 
-	mt76x2_init_debugfs(dev);
+	mt76x02_init_debugfs(dev);
 	mt76x2_init_txpower(dev, &dev->mt76.sband_2g.sband);
 	mt76x2_init_txpower(dev, &dev->mt76.sband_5g.sband);
 
-- 
cgit v1.2.3


From 63f15d9459db54491001437499647dc0aa74260e Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 15 Oct 2018 11:33:14 +0200
Subject: mt76x0: use shared debugfs implementation

Use mt76x02 debugfs implementation and remove duplicated code

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/Makefile |  4 +-
 .../net/wireless/mediatek/mt76/mt76x0/debugfs.c    | 87 ----------------------
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c   |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  2 -
 4 files changed, 3 insertions(+), 92 deletions(-)
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/debugfs.c

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile b/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
index 20672978dceb..e49cbf6be945 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
@@ -3,8 +3,8 @@ obj-$(CONFIG_MT76x0E) += mt76x0e.o
 obj-$(CONFIG_MT76x0_COMMON) += mt76x0-common.o
 
 mt76x0-common-y := \
-	init.o main.o trace.o eeprom.o phy.o \
-	mac.o debugfs.o
+	init.o main.o trace.o eeprom.o phy.o mac.o
+
 mt76x0u-y := usb.o usb_mcu.o
 mt76x0e-y := pci.o pci_mcu.o
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x0/debugfs.c
deleted file mode 100644
index 3224e5b1a1e5..000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/debugfs.c
+++ /dev/null
@@ -1,87 +0,0 @@
-/*
- * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
- * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/debugfs.h>
-
-#include "mt76x0.h"
-#include "eeprom.h"
-
-static int
-mt76x0_ampdu_stat_read(struct seq_file *file, void *data)
-{
-	struct mt76x02_dev *dev = file->private;
-	int i, j;
-
-#define stat_printf(grp, off, name)					\
-	seq_printf(file, #name ":\t%llu\n", dev->stats.grp[off])
-
-	stat_printf(rx_stat, 0, rx_crc_err);
-	stat_printf(rx_stat, 1, rx_phy_err);
-	stat_printf(rx_stat, 2, rx_false_cca);
-	stat_printf(rx_stat, 3, rx_plcp_err);
-	stat_printf(rx_stat, 4, rx_fifo_overflow);
-	stat_printf(rx_stat, 5, rx_duplicate);
-
-	stat_printf(tx_stat, 0, tx_fail_cnt);
-	stat_printf(tx_stat, 1, tx_bcn_cnt);
-	stat_printf(tx_stat, 2, tx_success);
-	stat_printf(tx_stat, 3, tx_retransmit);
-	stat_printf(tx_stat, 4, tx_zero_len);
-	stat_printf(tx_stat, 5, tx_underflow);
-
-	stat_printf(aggr_stat, 0, non_aggr_tx);
-	stat_printf(aggr_stat, 1, aggr_tx);
-
-	stat_printf(zero_len_del, 0, tx_zero_len_del);
-	stat_printf(zero_len_del, 1, rx_zero_len_del);
-#undef stat_printf
-
-	seq_puts(file, "Aggregations stats:\n");
-	for (i = 0; i < 4; i++) {
-		for (j = 0; j < 8; j++)
-			seq_printf(file, "%08llx ",
-				   dev->stats.aggr_n[i * 8 + j]);
-		seq_putc(file, '\n');
-	}
-
-	seq_printf(file, "recent average AMPDU len: %d\n",
-		   atomic_read(&dev->avg_ampdu_len));
-
-	return 0;
-}
-
-static int
-mt76x0_ampdu_stat_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, mt76x0_ampdu_stat_read, inode->i_private);
-}
-
-static const struct file_operations fops_ampdu_stat = {
-	.open = mt76x0_ampdu_stat_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-void mt76x0_init_debugfs(struct mt76x02_dev *dev)
-{
-	struct dentry *dir;
-
-	dir = mt76_register_debugfs(&dev->mt76);
-	if (!dir)
-		return;
-
-	debugfs_create_file("ampdu_stat", S_IRUSR, dir, dev, &fops_ampdu_stat);
-}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index d7d4dfbbd04d..f90ef4d803d5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -389,7 +389,7 @@ int mt76x0_register_device(struct mt76x02_dev *dev)
 	if (mdev->cap.has_5ghz)
 		mt76x0_vht_cap_mask(&dev->mt76.sband_5g.sband);
 
-	mt76x0_init_debugfs(dev);
+	mt76x02_init_debugfs(dev);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 17fc7206c55d..b9743b575099 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -37,8 +37,6 @@ static inline bool is_mt7610e(struct mt76x02_dev *dev)
 	return false;
 }
 
-void mt76x0_init_debugfs(struct mt76x02_dev *dev);
-
 /* Init */
 struct mt76x02_dev *
 mt76x0_alloc_device(struct device *pdev,
-- 
cgit v1.2.3


From 73556561ab9f5e7ff14c0d4d248c53f0162b4090 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 15 Oct 2018 11:33:15 +0200
Subject: mt76x0: use mt76x02_mac_work as stats handler

Use mt76x02_mac_work utility routine as stats workqueue handler
and remove duplicated code. Moreover run mac stuck check in
mt76x02_mac_work for client interfaces.
Remove no longer used avg_ampdu_len and mt76x02_mac_stats data
structure in mt76x02_dev

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c   |  3 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c    | 68 ----------------------
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  1 -
 drivers/net/wireless/mediatek/mt76/mt76x02.h       | 10 ----
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c   | 19 ++++++
 5 files changed, 20 insertions(+), 81 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index f90ef4d803d5..f5c7db9ca02a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -339,7 +339,6 @@ mt76x0_alloc_device(struct device *pdev,
 
 	dev = container_of(mdev, struct mt76x02_dev, mt76);
 	mutex_init(&dev->phy_mutex);
-	atomic_set(&dev->avg_ampdu_len, 1);
 
 	return dev;
 }
@@ -378,7 +377,7 @@ int mt76x0_register_device(struct mt76x02_dev *dev)
 
 	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
 
-	INIT_DELAYED_WORK(&dev->mac_work, mt76x0_mac_work);
+	INIT_DELAYED_WORK(&dev->mac_work, mt76x02_mac_work);
 
 	ret = mt76_register_device(mdev, true, mt76x02_rates,
 				   ARRAY_SIZE(mt76x02_rates));
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
index 9cabe8ebf5da..98d4a97f0a72 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
@@ -105,74 +105,6 @@ void mt76x0_mac_config_tsf(struct mt76x02_dev *dev, bool enable, int interval)
 		MT_BEACON_TIME_CFG_TBTT_EN;
 }
 
-static void mt76x0_check_mac_err(struct mt76x02_dev *dev)
-{
-	u32 val = mt76_rr(dev, 0x10f4);
-
-	if (!(val & BIT(29)) || !(val & (BIT(7) | BIT(5))))
-		return;
-
-	dev_err(dev->mt76.dev, "Error: MAC specific condition occurred\n");
-
-	mt76_set(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_RESET_CSR);
-	udelay(10);
-	mt76_clear(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_RESET_CSR);
-}
-void mt76x0_mac_work(struct work_struct *work)
-{
-	struct mt76x02_dev *dev = container_of(work, struct mt76x02_dev,
-					       mac_work.work);
-	struct {
-		u32 addr_base;
-		u32 span;
-		u64 *stat_base;
-	} spans[] = {
-		{ MT_RX_STAT_0,	3,	dev->stats.rx_stat },
-		{ MT_TX_STA_0,	3,	dev->stats.tx_stat },
-		{ MT_TX_AGG_STAT,	1,	dev->stats.aggr_stat },
-		{ MT_MPDU_DENSITY_CNT,	1,	dev->stats.zero_len_del },
-		{ MT_TX_AGG_CNT_BASE0,	8,	&dev->stats.aggr_n[0] },
-		{ MT_TX_AGG_CNT_BASE1,	8,	&dev->stats.aggr_n[16] },
-	};
-	u32 sum, n;
-	int i, j, k;
-
-	mt76x02_update_channel(&dev->mt76);
-
-	/* Note: using MCU_RANDOM_READ is actually slower then reading all the
-	 *	 registers by hand.  MCU takes ca. 20ms to complete read of 24
-	 *	 registers while reading them one by one will takes roughly
-	 *	 24*200us =~ 5ms.
-	 */
-
-	k = 0;
-	n = 0;
-	sum = 0;
-	for (i = 0; i < ARRAY_SIZE(spans); i++)
-		for (j = 0; j < spans[i].span; j++) {
-			u32 val = mt76_rr(dev, spans[i].addr_base + j * 4);
-
-			spans[i].stat_base[j * 2] += val & 0xffff;
-			spans[i].stat_base[j * 2 + 1] += val >> 16;
-
-			/* Calculate average AMPDU length */
-			if (spans[i].addr_base != MT_TX_AGG_CNT_BASE0 &&
-			    spans[i].addr_base != MT_TX_AGG_CNT_BASE1)
-				continue;
-
-			n += (val >> 16) + (val & 0xffff);
-			sum += (val & 0xffff) * (1 + k * 2) +
-				(val >> 16) * (2 + k * 2);
-			k++;
-		}
-
-	atomic_set(&dev->avg_ampdu_len, n ? DIV_ROUND_CLOSEST(sum, n) : 1);
-
-	mt76x0_check_mac_err(dev);
-
-	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->mac_work, 10 * HZ);
-}
-
 void mt76x0_mac_set_ampdu_factor(struct mt76x02_dev *dev)
 {
 	struct ieee80211_sta *sta;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index b9743b575099..85de821483cd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -69,7 +69,6 @@ void mt76x0_phy_set_txpower(struct mt76x02_dev *dev);
 void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on);
 
 /* MAC */
-void mt76x0_mac_work(struct work_struct *work);
 void mt76x0_mac_set_protection(struct mt76x02_dev *dev, bool legacy_prot,
 				int ht_mode);
 void mt76x0_mac_set_short_preamble(struct mt76x02_dev *dev, bool short_preamb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 58721307d917..bdbe4bbf7a59 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -28,14 +28,6 @@
 
 #define MT_CALIBRATE_INTERVAL	HZ
 
-struct mt76x02_mac_stats {
-	u64 rx_stat[6];
-	u64 tx_stat[6];
-	u64 aggr_stat[2];
-	u64 aggr_n[32];
-	u64 zero_len_del[2];
-};
-
 #define MT_MAX_CHAINS		2
 struct mt76x02_rx_freq_cal {
 	s8 high_gain[MT_MAX_CHAINS];
@@ -85,8 +77,6 @@ struct mt76x02_dev {
 	struct delayed_work cal_work;
 	struct delayed_work mac_work;
 
-	struct mt76x02_mac_stats stats;
-	atomic_t avg_ampdu_len;
 	u32 aggr_stats[32];
 
 	struct sk_buff *beacons[8];
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index c7666f4c432f..3896da690b83 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -754,6 +754,21 @@ void mt76x02_update_channel(struct mt76_dev *mdev)
 }
 EXPORT_SYMBOL_GPL(mt76x02_update_channel);
 
+static void mt76x02_check_mac_err(struct mt76x02_dev *dev)
+{
+	u32 val = mt76_rr(dev, 0x10f4);
+
+	if (!(val & BIT(29)) || !(val & (BIT(7) | BIT(5))))
+		return;
+
+	dev_err(dev->mt76.dev, "mac specific condition occurred\n");
+
+	mt76_set(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_RESET_CSR);
+	udelay(10);
+	mt76_clear(dev, MT_MAC_SYS_CTRL,
+		   MT_MAC_SYS_CTRL_ENABLE_TX | MT_MAC_SYS_CTRL_ENABLE_RX);
+}
+
 void mt76x02_mac_work(struct work_struct *work)
 {
 	struct mt76x02_dev *dev = container_of(work, struct mt76x02_dev,
@@ -768,6 +783,10 @@ void mt76x02_mac_work(struct work_struct *work)
 		dev->aggr_stats[idx++] += val >> 16;
 	}
 
+	/* XXX: check beacon stuck for ap mode */
+	if (!dev->beacon_mask)
+		mt76x02_check_mac_err(dev);
+
 	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mac_work,
 				     MT_CALIBRATE_INTERVAL);
 }
-- 
cgit v1.2.3


From 70289adc6af61efc6bce737c9b86bf42779829d3 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 15 Oct 2018 11:33:16 +0200
Subject: mt76x2u: introduce mac workqueue support

Add mac workqueue support to mt76x2u driver in order
to compute device statistics and add mac stuck routine

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x2/init.c     | 2 ++
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c | 1 -
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c | 2 ++
 4 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/init.c
index 3c73fdeaf30f..04790f84d7d4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/init.c
@@ -162,6 +162,8 @@ void mt76x2_init_device(struct mt76x02_dev *dev)
 {
 	struct ieee80211_hw *hw = mt76_hw(dev);
 
+	INIT_DELAYED_WORK(&dev->mac_work, mt76x02_mac_work);
+
 	hw->queues = 4;
 	hw->max_rates = 1;
 	hw->max_report_rates = 7;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 5b167aaaf7f7..b15c97e1dfb3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -467,7 +467,6 @@ int mt76x2_register_device(struct mt76x02_dev *dev)
 	int i, ret;
 
 	INIT_DELAYED_WORK(&dev->cal_work, mt76x2_phy_calibrate);
-	INIT_DELAYED_WORK(&dev->mac_work, mt76x02_mac_work);
 
 	mt76x2_init_device(dev);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
index dfc80ecfde92..b2388f506505 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
@@ -297,6 +297,7 @@ void mt76x2u_stop_hw(struct mt76x02_dev *dev)
 {
 	mt76u_stop_stat_wk(&dev->mt76);
 	cancel_delayed_work_sync(&dev->cal_work);
+	cancel_delayed_work_sync(&dev->mac_work);
 	mt76x2u_mac_stop(dev);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
index 1971a1b00038..25c43175e6e5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
@@ -27,6 +27,8 @@ static int mt76x2u_start(struct ieee80211_hw *hw)
 	if (ret)
 		goto out;
 
+	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mac_work,
+				     MT_CALIBRATE_INTERVAL);
 	set_bit(MT76_STATE_RUNNING, &dev->mt76.state);
 
 out:
-- 
cgit v1.2.3


From 1163bdb636a118b9d7c3c03b9e67e7e799425a9c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 15 Oct 2018 14:18:05 +0200
Subject: mt76x0: phy: unify calibration between mt76x0u and mt76x0e

Align phy calibration logic between mt76x0u and mt76x0e drivers
This patch improves connection stability with low SNR

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c   |  3 -
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  1 -
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    | 83 +---------------------
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c    |  1 +
 4 files changed, 4 insertions(+), 84 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index e9fbbabbe7e0..fdffbdf90e59 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -121,9 +121,6 @@ void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
 			       MT_BKOFF_SLOT_CFG_SLOTTIME, slottime);
 	}
 
-	if (changed & BSS_CHANGED_ASSOC)
-		mt76x0_phy_recalibrate_after_assoc(dev);
-
 	mutex_unlock(&dev->mt76.mutex);
 }
 EXPORT_SYMBOL_GPL(mt76x0_bss_info_changed);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 85de821483cd..17ad3fa0858b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -64,7 +64,6 @@ void mt76x0_phy_init(struct mt76x02_dev *dev);
 int mt76x0_phy_wait_bbp_ready(struct mt76x02_dev *dev);
 int mt76x0_phy_set_channel(struct mt76x02_dev *dev,
 			    struct cfg80211_chan_def *chandef);
-void mt76x0_phy_recalibrate_after_assoc(struct mt76x02_dev *dev);
 void mt76x0_phy_set_txpower(struct mt76x02_dev *dev);
 void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index 53927547cf12..dbb92586b6e1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -212,44 +212,6 @@ int mt76x0_phy_wait_bbp_ready(struct mt76x02_dev *dev)
 	return 0;
 }
 
-static void mt76x0_phy_vco_cal(struct mt76x02_dev *dev, u8 channel)
-{
-	u8 val;
-
-	val = mt76x0_rf_rr(dev, MT_RF(0, 4));
-	if ((val & 0x70) != 0x30)
-		return;
-
-	/* closed loop calibarion - B0.R06.[3:0]: 1001 */
-	mt76x0_rf_rmw(dev, MT_RF(0, 6), MT_RF_VCO_BP_CLOSE_LOOP_MASK,
-		      MT_RF_VCO_BP_CLOSE_LOOP | BIT(0));
-
-	/* open loop calibration - B0.R05.[7:0]: 0x0 */
-	mt76x0_rf_wr(dev, MT_RF(0, 5), 0x0);
-
-	/* caliration mask - B0.R04.[2:0]: 000 */
-	mt76x0_rf_clear(dev, MT_RF(0, 4), MT_RF_VCO_CAL_MASK);
-
-	/* startup time - B0.R03.[2:0] startup_time: 011 */
-	mt76x0_rf_rmw(dev, MT_RF(0, 3), MT_RF_START_TIME_MASK,
-		      MT_RF_START_TIME);
-
-	/* settle_time - B0.R03.[6:4] */
-	if (channel == 3 || channel == 4 || channel == 10)
-		val = 0x50;
-	else if (channel == 2 || channel == 5 || channel == 6 ||
-		 channel == 8 || channel == 11 || channel == 12)
-		val = 0x40;
-	else
-		val = 0x60;
-	mt76x0_rf_rmw(dev, MT_RF(0, 3), MT_RF_SETTLE_TIME_MASK, val);
-
-	/* enable vco */
-	mt76x0_rf_set(dev, MT_RF(0, 4), BIT(7));
-
-	msleep(2);
-}
-
 static void
 mt76x0_phy_set_band(struct mt76x02_dev *dev, enum nl80211_band band)
 {
@@ -670,18 +632,12 @@ int mt76x0_phy_set_channel(struct mt76x02_dev *dev,
 	mt76x0_phy_set_chan_bbp_params(dev, rf_bw_band);
 	mt76x02_init_agc_gain(dev);
 
-	if (mt76_is_usb(dev)) {
-		mt76x0_phy_vco_cal(dev, channel);
-	} else {
-		/* enable vco */
-		mt76x0_rf_set(dev, MT_RF(0, 4), BIT(7));
-	}
-
+	/* enable vco */
+	mt76x0_rf_set(dev, MT_RF(0, 4), BIT(7));
 	if (scan)
 		return 0;
 
-	if (mt76_is_mmio(dev))
-		mt76x0_phy_calibrate(dev, false);
+	mt76x0_phy_calibrate(dev, false);
 	mt76x0_phy_set_txpower(dev);
 
 	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->cal_work,
@@ -690,39 +646,6 @@ int mt76x0_phy_set_channel(struct mt76x02_dev *dev,
 	return 0;
 }
 
-void mt76x0_phy_recalibrate_after_assoc(struct mt76x02_dev *dev)
-{
-	u32 tx_alc, reg_val;
-	u8 channel = dev->mt76.chandef.chan->hw_value;
-	int is_5ghz = (dev->mt76.chandef.chan->band == NL80211_BAND_5GHZ) ? 1 : 0;
-
-	mt76x02_mcu_calibrate(dev, MCU_CAL_R, 0, false);
-
-	mt76x0_phy_vco_cal(dev, channel);
-
-	tx_alc = mt76_rr(dev, MT_TX_ALC_CFG_0);
-	mt76_wr(dev, MT_TX_ALC_CFG_0, 0);
-	usleep_range(500, 700);
-
-	reg_val = mt76_rr(dev, MT_BBP(IBI, 9));
-	mt76_wr(dev, MT_BBP(IBI, 9), 0xffffff7e);
-
-	mt76x02_mcu_calibrate(dev, MCU_CAL_RXDCOC, 0, false);
-
-	mt76x02_mcu_calibrate(dev, MCU_CAL_LC, is_5ghz, false);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_LOFT, is_5ghz, false);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_TXIQ, is_5ghz, false);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_TX_GROUP_DELAY, is_5ghz, false);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_RXIQ, is_5ghz, false);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_RX_GROUP_DELAY, is_5ghz, false);
-
-	mt76_wr(dev, MT_BBP(IBI, 9), reg_val);
-	mt76_wr(dev, MT_TX_ALC_CFG_0, tx_alc);
-	msleep(100);
-
-	mt76x02_mcu_calibrate(dev, MCU_CAL_RXDCOC, 1, false);
-}
-
 static void mt76x0_phy_temp_sensor(struct mt76x02_dev *dev)
 {
 	u8 rf_b7_73, rf_b0_66, rf_b0_67;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index a7fd36c2f633..ea517864186b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -117,6 +117,7 @@ static int mt76x0u_start(struct ieee80211_hw *hw)
 	if (ret)
 		goto out;
 
+	mt76x0_phy_calibrate(dev, true);
 	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->mac_work,
 				     MT_CALIBRATE_INTERVAL);
 	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->cal_work,
-- 
cgit v1.2.3


From a83150eaad42769e4d08b6e07956a489e40214ae Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 16 Oct 2018 09:58:43 +0200
Subject: mt76x0: do not perform MCU calibration for MT7630

Driver works better for MT7630 without MCU calibration, which
looks like it can hangs the firmware. Vendor driver do not
perform it for MT7630 as well.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h | 5 +++++
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    | 3 +++
 2 files changed, 8 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 17ad3fa0858b..33475788bc26 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -37,6 +37,11 @@ static inline bool is_mt7610e(struct mt76x02_dev *dev)
 	return false;
 }
 
+static inline bool is_mt7630(struct mt76x02_dev *dev)
+{
+	return mt76_chip(&dev->mt76) == 0x7630;
+}
+
 /* Init */
 struct mt76x02_dev *
 mt76x0_alloc_device(struct device *pdev,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index dbb92586b6e1..37e1ead1dc85 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -500,6 +500,9 @@ void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on)
 	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
 	u32 val, tx_alc, reg_val;
 
+	if (is_mt7630(dev))
+		return;
+
 	if (power_on) {
 		mt76x02_mcu_calibrate(dev, MCU_CAL_R, 0, false);
 		mt76x02_mcu_calibrate(dev, MCU_CAL_VCO, chan->hw_value,
-- 
cgit v1.2.3


From 5567b37359919d2f678de04e9d6e83571b3140ff Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 17 Oct 2018 13:10:16 +0200
Subject: mt76: clean up unused leftover EXPORT_SYMBOLs

Make previously exported functions static where possible

Acked-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h         | 2 --
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c  | 8 +-------
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.h  | 2 --
 drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c | 1 -
 drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c | 2 --
 drivers/net/wireless/mediatek/mt76/usb.c          | 6 ++----
 6 files changed, 3 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 3bfa7f5e3513..53ddc4fa5884 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -668,8 +668,6 @@ int mt76u_vendor_request(struct mt76_dev *dev, u8 req,
 			 void *buf, size_t len);
 void mt76u_single_wr(struct mt76_dev *dev, const u8 req,
 		     const u16 offset, const u32 val);
-u32 mt76u_rr(struct mt76_dev *dev, u32 addr);
-void mt76u_wr(struct mt76_dev *dev, u32 addr, u32 val);
 int mt76u_init(struct mt76_dev *dev, struct usb_interface *intf);
 void mt76u_deinit(struct mt76_dev *dev);
 int mt76u_buf_alloc(struct mt76_dev *dev, struct mt76u_buf *buf,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index 3896da690b83..899ffd026e62 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -18,7 +18,7 @@
 #include "mt76x02.h"
 #include "mt76x02_trace.h"
 
-enum mt76x02_cipher_type
+static enum mt76x02_cipher_type
 mt76x02_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data)
 {
 	memset(key_data, 0, 32);
@@ -43,7 +43,6 @@ mt76x02_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data)
 		return MT_CIPHER_NONE;
 	}
 }
-EXPORT_SYMBOL_GPL(mt76x02_mac_get_key_info);
 
 int mt76x02_mac_shared_key_setup(struct mt76x02_dev *dev, u8 vif_idx,
 				 u8 key_idx, struct ieee80211_key_conf *key)
@@ -95,7 +94,6 @@ int mt76x02_mac_wcid_set_key(struct mt76x02_dev *dev, u8 idx,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mt76x02_mac_wcid_set_key);
 
 void mt76x02_mac_wcid_setup(struct mt76x02_dev *dev, u8 idx,
 			    u8 vif_idx, u8 *mac)
@@ -154,7 +152,6 @@ void mt76x02_txq_init(struct mt76x02_dev *dev, struct ieee80211_txq *txq)
 
 	mt76_txq_init(&dev->mt76, txq);
 }
-EXPORT_SYMBOL_GPL(mt76x02_txq_init);
 
 static __le16
 mt76x02_mac_tx_rate_val(struct mt76x02_dev *dev,
@@ -239,7 +236,6 @@ bool mt76x02_mac_load_tx_status(struct mt76x02_dev *dev,
 
 	return true;
 }
-EXPORT_SYMBOL_GPL(mt76x02_mac_load_tx_status);
 
 static int
 mt76x02_mac_process_tx_rate(struct ieee80211_tx_rate *txrate, u16 rate,
@@ -483,7 +479,6 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 out:
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL_GPL(mt76x02_send_tx_status);
 
 int
 mt76x02_mac_process_rate(struct mt76_rx_status *status, u16 rate)
@@ -705,7 +700,6 @@ void mt76x02_mac_poll_tx_status(struct mt76x02_dev *dev, bool irq)
 		kfifo_put(&dev->txstatus_fifo, stat);
 	}
 }
-EXPORT_SYMBOL_GPL(mt76x02_mac_poll_tx_status);
 
 static void
 mt76x02_mac_queue_txdone(struct mt76x02_dev *dev, struct sk_buff *skb,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index c1936e2277d1..81c16aef6a94 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -199,8 +199,6 @@ mt76x02_skb_tx_info(struct sk_buff *skb)
 }
 
 void mt76x02_txq_init(struct mt76x02_dev *dev, struct ieee80211_txq *txq);
-enum mt76x02_cipher_type
-mt76x02_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data);
 
 int mt76x02_mac_shared_key_setup(struct mt76x02_dev *dev, u8 vif_idx,
 				 u8 key_idx, struct ieee80211_key_conf *key);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
index 39f092034240..784b76e08382 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
@@ -225,7 +225,6 @@ static void mt76x02_dma_enable(struct mt76x02_dev *dev)
 	mt76_clear(dev, MT_WPDMA_GLO_CFG,
 		   MT_WPDMA_GLO_CFG_TX_WRITEBACK_DONE);
 }
-EXPORT_SYMBOL_GPL(mt76x02_dma_enable);
 
 void mt76x02_dma_cleanup(struct mt76x02_dev *dev)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c b/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c
index d3de08872d6e..7ec3f8f5f228 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c
@@ -110,7 +110,6 @@ s8 mt76x02_tx_get_max_txpwr_adj(struct mt76x02_dev *dev,
 
 	return max_txpwr;
 }
-EXPORT_SYMBOL_GPL(mt76x02_tx_get_max_txpwr_adj);
 
 s8 mt76x02_tx_get_txpwr_adj(struct mt76x02_dev *dev, s8 txpwr, s8 max_txpwr_adj)
 {
@@ -125,7 +124,6 @@ s8 mt76x02_tx_get_txpwr_adj(struct mt76x02_dev *dev, s8 txpwr, s8 max_txpwr_adj)
 	else
 		return (txpwr < -16) ? 8 : (txpwr + 32) / 2;
 }
-EXPORT_SYMBOL_GPL(mt76x02_tx_get_txpwr_adj);
 
 void mt76x02_tx_set_txpwr_auto(struct mt76x02_dev *dev, s8 txpwr)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index 5f0faf07c346..4ef61d64fc36 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -100,7 +100,7 @@ static u32 __mt76u_rr(struct mt76_dev *dev, u32 addr)
 	return data;
 }
 
-u32 mt76u_rr(struct mt76_dev *dev, u32 addr)
+static u32 mt76u_rr(struct mt76_dev *dev, u32 addr)
 {
 	u32 ret;
 
@@ -110,7 +110,6 @@ u32 mt76u_rr(struct mt76_dev *dev, u32 addr)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(mt76u_rr);
 
 /* should be called with usb_ctrl_mtx locked */
 static void __mt76u_wr(struct mt76_dev *dev, u32 addr, u32 val)
@@ -136,13 +135,12 @@ static void __mt76u_wr(struct mt76_dev *dev, u32 addr, u32 val)
 	trace_usb_reg_wr(dev, addr, val);
 }
 
-void mt76u_wr(struct mt76_dev *dev, u32 addr, u32 val)
+static void mt76u_wr(struct mt76_dev *dev, u32 addr, u32 val)
 {
 	mutex_lock(&dev->usb.usb_ctrl_mtx);
 	__mt76u_wr(dev, addr, val);
 	mutex_unlock(&dev->usb.usb_ctrl_mtx);
 }
-EXPORT_SYMBOL_GPL(mt76u_wr);
 
 static u32 mt76u_rmw(struct mt76_dev *dev, u32 addr,
 		     u32 mask, u32 val)
-- 
cgit v1.2.3


From cadc83efce65fe505ec7736cec6ff5f26cbce52a Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 18 Oct 2018 16:09:07 +0200
Subject: mt76: mt76x0: handle chip specific initval differences

Some RF registers need different values for various chips.
For at least mt76x0_rf_central_tab registers, overwriting them later does
not work, as the wrong values can cause the entire system to hang on some
devices with MT7610E

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  6 ++-
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    | 47 +++++++++++++++++++++-
 2 files changed, 49 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 33475788bc26..989ed00c0b7a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -33,8 +33,10 @@
 
 static inline bool is_mt7610e(struct mt76x02_dev *dev)
 {
-	/* TODO */
-	return false;
+	if (!mt76_is_mmio(dev))
+		return false;
+
+	return mt76_chip(&dev->mt76) == 0x7610;
 }
 
 static inline bool is_mt7630(struct mt76x02_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index 37e1ead1dc85..29689318c4d6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -742,13 +742,56 @@ static void mt76x0_phy_calibration_work(struct work_struct *work)
 				     MT_CALIBRATE_INTERVAL);
 }
 
+static void mt76x0_rf_patch_reg_array(struct mt76x02_dev *dev,
+				      const struct mt76_reg_pair *rp, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++) {
+		u32 reg = rp[i].reg;
+		u8 val = rp[i].value;
+
+		switch (reg) {
+		case MT_RF(0, 3):
+			if (mt76_is_mmio(dev)) {
+				if (is_mt7630(dev))
+					val = 0x70;
+				else
+					val = 0x63;
+			} else {
+				val = 0x73;
+			}
+			break;
+		case MT_RF(0, 21):
+			if (is_mt7610e(dev))
+				val = 0x10;
+			else
+				val = 0x12;
+			break;
+		case MT_RF(5, 2):
+			if (is_mt7630(dev))
+				val = 0x1d;
+			else if (is_mt7610e(dev))
+				val = 0x00;
+			else
+				val = 0x0c;
+			break;
+		default:
+			break;
+		}
+		mt76x0_rf_wr(dev, reg, val);
+	}
+}
+
 static void mt76x0_phy_rf_init(struct mt76x02_dev *dev)
 {
 	int i;
 	u8 val;
 
-	RF_RANDOM_WRITE(dev, mt76x0_rf_central_tab);
-	RF_RANDOM_WRITE(dev, mt76x0_rf_2g_channel_0_tab);
+	mt76x0_rf_patch_reg_array(dev, mt76x0_rf_central_tab,
+				  ARRAY_SIZE(mt76x0_rf_central_tab));
+	mt76x0_rf_patch_reg_array(dev, mt76x0_rf_2g_channel_0_tab,
+				  ARRAY_SIZE(mt76x0_rf_2g_channel_0_tab));
 	RF_RANDOM_WRITE(dev, mt76x0_rf_5g_channel_0_tab);
 	RF_RANDOM_WRITE(dev, mt76x0_rf_vga_channel_0_tab);
 
-- 
cgit v1.2.3


From e0168dc675e2b5fd36b2f3792966963c4feb0423 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Thu, 18 Oct 2018 00:35:32 +0200
Subject: mt76: usb: fix static tracepoints

Add submit_urb and rx_urb static tracepoints in mt76-usb module.
Move trace_mac_txstat_fetch in mt76x02_mac_load_tx_status routine
in order to be available to usb drivers. Moreover remove
no longer used mt76x0/trace.{c,h}

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/Makefile |   3 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c   |   1 -
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c    |   1 -
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    |   8 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/trace.c  |  21 --
 drivers/net/wireless/mediatek/mt76/mt76x0/trace.h  | 312 ---------------------
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c    |   1 -
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c   |   4 +-
 drivers/net/wireless/mediatek/mt76/usb.c           |   5 +
 drivers/net/wireless/mediatek/mt76/usb_trace.h     |  29 +-
 10 files changed, 38 insertions(+), 347 deletions(-)
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/trace.c
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/trace.h

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile b/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
index e49cbf6be945..1b4f2fa99317 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
@@ -3,10 +3,9 @@ obj-$(CONFIG_MT76x0E) += mt76x0e.o
 obj-$(CONFIG_MT76x0_COMMON) += mt76x0-common.o
 
 mt76x0-common-y := \
-	init.o main.o trace.o eeprom.o phy.o mac.o
+	init.o main.o eeprom.o phy.o mac.o
 
 mt76x0u-y := usb.o usb_mcu.o
 mt76x0e-y := pci.o pci_mcu.o
 
 # ccflags-y := -DDEBUG
-CFLAGS_trace.o := -I$(src)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index f5c7db9ca02a..74c007c44a8f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -16,7 +16,6 @@
 
 #include "mt76x0.h"
 #include "eeprom.h"
-#include "trace.h"
 #include "mcu.h"
 #include "initvals.h"
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
index 98d4a97f0a72..8cbdeb6d3dbe 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
@@ -16,7 +16,6 @@
 #include <linux/etherdevice.h>
 
 #include "mt76x0.h"
-#include "trace.h"
 
 void mt76x0_mac_set_protection(struct mt76x02_dev *dev, bool legacy_prot,
 			       int ht_mode)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index 29689318c4d6..2a96f8cc0b20 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -20,7 +20,6 @@
 #include "mt76x0.h"
 #include "mcu.h"
 #include "eeprom.h"
-#include "trace.h"
 #include "phy.h"
 #include "initvals.h"
 #include "initvals_phy.h"
@@ -54,7 +53,7 @@ mt76x0_rf_csr_wr(struct mt76x02_dev *dev, u32 offset, u8 value)
 		FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
 		MT_RF_CSR_CFG_WR |
 		MT_RF_CSR_CFG_KICK);
-	trace_mt76x0_rf_write(&dev->mt76, bank, offset, value);
+
 out:
 	mutex_unlock(&dev->phy_mutex);
 
@@ -95,10 +94,9 @@ static int mt76x0_rf_csr_rr(struct mt76x02_dev *dev, u32 offset)
 
 	val = mt76_rr(dev, MT_RF_CSR_CFG);
 	if (FIELD_GET(MT_RF_CSR_CFG_REG_ID, val) == reg &&
-	    FIELD_GET(MT_RF_CSR_CFG_REG_BANK, val) == bank) {
+	    FIELD_GET(MT_RF_CSR_CFG_REG_BANK, val) == bank)
 		ret = FIELD_GET(MT_RF_CSR_CFG_DATA, val);
-		trace_mt76x0_rf_read(&dev->mt76, bank, offset, ret);
-	}
+
 out:
 	mutex_unlock(&dev->phy_mutex);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/trace.c b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.c
deleted file mode 100644
index 8abdd3cd546d..000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/trace.c
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/module.h>
-
-#ifndef __CHECKER__
-#define CREATE_TRACE_POINTS
-#include "trace.h"
-
-#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h
deleted file mode 100644
index 75d1d6738c34..000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h
+++ /dev/null
@@ -1,312 +0,0 @@
-/*
- * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#if !defined(__MT76X0U_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
-#define __MT76X0U_TRACE_H
-
-#include <linux/tracepoint.h>
-#include "mt76x0.h"
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM mt76x0
-
-#define MAXNAME		32
-#define DEV_ENTRY	__array(char, wiphy_name, 32)
-#define DEV_ASSIGN	strlcpy(__entry->wiphy_name,			\
-				wiphy_name(dev->hw->wiphy), MAXNAME)
-#define DEV_PR_FMT	"%s "
-#define DEV_PR_ARG	__entry->wiphy_name
-
-#define REG_ENTRY	__field(u32, reg) __field(u32, val)
-#define REG_ASSIGN	__entry->reg = reg; __entry->val = val
-#define REG_PR_FMT	"%04x=%08x"
-#define REG_PR_ARG	__entry->reg, __entry->val
-
-DECLARE_EVENT_CLASS(dev_reg_evt,
-	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
-	TP_ARGS(dev, reg, val),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		REG_ENTRY
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		REG_ASSIGN;
-	),
-	TP_printk(
-		DEV_PR_FMT REG_PR_FMT,
-		DEV_PR_ARG, REG_PR_ARG
-	)
-);
-
-DEFINE_EVENT(dev_reg_evt, mt76x0_reg_read,
-	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
-	TP_ARGS(dev, reg, val)
-);
-
-DEFINE_EVENT(dev_reg_evt, mt76x0_reg_write,
-	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
-	TP_ARGS(dev, reg, val)
-);
-
-TRACE_EVENT(mt76x0_submit_urb,
-	TP_PROTO(struct mt76_dev *dev, struct urb *u),
-	TP_ARGS(dev, u),
-	TP_STRUCT__entry(
-		DEV_ENTRY __field(unsigned, pipe) __field(u32, len)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->pipe = u->pipe;
-		__entry->len = u->transfer_buffer_length;
-	),
-	TP_printk(DEV_PR_FMT "p:%08x len:%u",
-		  DEV_PR_ARG, __entry->pipe, __entry->len)
-);
-
-#define trace_mt76x0_submit_urb_sync(__dev, __pipe, __len) ({	\
-	struct urb u;					\
-	u.pipe = __pipe;				\
-	u.transfer_buffer_length = __len;		\
-	trace_mt76x0_submit_urb(__dev, &u);			\
-})
-
-TRACE_EVENT(mt76x0_mcu_msg_send,
-	TP_PROTO(struct mt76_dev *dev,
-		 struct sk_buff *skb, u32 csum, bool resp),
-	TP_ARGS(dev, skb, csum, resp),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field(u32, info)
-		__field(u32, csum)
-		__field(bool, resp)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->info = *(u32 *)skb->data;
-		__entry->csum = csum;
-		__entry->resp = resp;
-	),
-	TP_printk(DEV_PR_FMT "i:%08x c:%08x r:%d",
-		  DEV_PR_ARG, __entry->info, __entry->csum, __entry->resp)
-);
-
-TRACE_EVENT(mt76x0_vend_req,
-	TP_PROTO(struct mt76_dev *dev, unsigned pipe, u8 req, u8 req_type,
-		 u16 val, u16 offset, void *buf, size_t buflen, int ret),
-	TP_ARGS(dev, pipe, req, req_type, val, offset, buf, buflen, ret),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field(unsigned, pipe) __field(u8, req) __field(u8, req_type)
-		__field(u16, val) __field(u16, offset) __field(void*, buf)
-		__field(int, buflen) __field(int, ret)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->pipe = pipe;
-		__entry->req = req;
-		__entry->req_type = req_type;
-		__entry->val = val;
-		__entry->offset = offset;
-		__entry->buf = buf;
-		__entry->buflen = buflen;
-		__entry->ret = ret;
-	),
-	TP_printk(DEV_PR_FMT
-		  "%d p:%08x req:%02hhx %02hhx val:%04hx %04hx buf:%d %d",
-		  DEV_PR_ARG, __entry->ret, __entry->pipe, __entry->req,
-		  __entry->req_type, __entry->val, __entry->offset,
-		  !!__entry->buf, __entry->buflen)
-);
-
-DECLARE_EVENT_CLASS(dev_rf_reg_evt,
-	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
-	TP_ARGS(dev, bank, reg, val),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field(u8, bank)
-		__field(u8, reg)
-		__field(u8, val)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		REG_ASSIGN;
-		__entry->bank = bank;
-	),
-	TP_printk(
-		DEV_PR_FMT "%02hhx:%02hhx=%02hhx",
-		DEV_PR_ARG, __entry->bank, __entry->reg, __entry->val
-	)
-);
-
-DEFINE_EVENT(dev_rf_reg_evt, mt76x0_rf_read,
-	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
-	TP_ARGS(dev, bank, reg, val)
-);
-
-DEFINE_EVENT(dev_rf_reg_evt, mt76x0_rf_write,
-	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
-	TP_ARGS(dev, bank, reg, val)
-);
-
-DECLARE_EVENT_CLASS(dev_simple_evt,
-	TP_PROTO(struct mt76_dev *dev, u8 val),
-	TP_ARGS(dev, val),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field(u8, val)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->val = val;
-	),
-	TP_printk(
-		DEV_PR_FMT "%02hhx", DEV_PR_ARG, __entry->val
-	)
-);
-
-TRACE_EVENT(mt76x0_rx,
-	TP_PROTO(struct mt76_dev *dev, struct mt76x02_rxwi *rxwi, u32 f),
-	TP_ARGS(dev, rxwi, f),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field_struct(struct mt76x02_rxwi, rxwi)
-		__field(u32, fce_info)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->rxwi = *rxwi;
-		__entry->fce_info = f;
-	),
-	TP_printk(DEV_PR_FMT "rxi:%08x ctl:%08x", DEV_PR_ARG,
-		  le32_to_cpu(__entry->rxwi.rxinfo),
-		  le32_to_cpu(__entry->rxwi.ctl))
-);
-
-TRACE_EVENT(mt76x0_tx,
-	TP_PROTO(struct mt76_dev *dev, struct sk_buff *skb,
-		 struct mt76x02_sta *sta, struct mt76x02_txwi *h),
-	TP_ARGS(dev, skb, sta, h),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field_struct(struct mt76x02_txwi, h)
-		__field(struct sk_buff *, skb)
-		__field(struct mt76x02_sta *, sta)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->h = *h;
-		__entry->skb = skb;
-		__entry->sta = sta;
-	),
-	TP_printk(DEV_PR_FMT "skb:%p sta:%p  flg:%04hx rate:%04hx "
-		  "ack:%02hhx wcid:%02hhx len_ctl:%05hx", DEV_PR_ARG,
-		  __entry->skb, __entry->sta,
-		  le16_to_cpu(__entry->h.flags),
-		  le16_to_cpu(__entry->h.rate),
-		  __entry->h.ack_ctl, __entry->h.wcid,
-		  le16_to_cpu(__entry->h.len_ctl))
-);
-
-TRACE_EVENT(mt76x0_tx_dma_done,
-	TP_PROTO(struct mt76_dev *dev, struct sk_buff *skb),
-	TP_ARGS(dev, skb),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field(struct sk_buff *, skb)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->skb = skb;
-	),
-	TP_printk(DEV_PR_FMT "%p", DEV_PR_ARG, __entry->skb)
-);
-
-TRACE_EVENT(mt76x0_tx_status_cleaned,
-	TP_PROTO(struct mt76_dev *dev, int cleaned),
-	TP_ARGS(dev, cleaned),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field(int, cleaned)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->cleaned = cleaned;
-	),
-	TP_printk(DEV_PR_FMT "%d", DEV_PR_ARG, __entry->cleaned)
-);
-
-TRACE_EVENT(mt76x0_tx_status,
-	TP_PROTO(struct mt76_dev *dev, u32 stat1, u32 stat2),
-	TP_ARGS(dev, stat1, stat2),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field(u32, stat1)	__field(u32, stat2)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->stat1 = stat1;
-		__entry->stat2 = stat2;
-	),
-	TP_printk(DEV_PR_FMT "%08x %08x",
-		  DEV_PR_ARG, __entry->stat1, __entry->stat2)
-);
-
-TRACE_EVENT(mt76x0_rx_dma_aggr,
-	TP_PROTO(struct mt76_dev *dev, int cnt, bool paged),
-	TP_ARGS(dev, cnt, paged),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field(u8, cnt)
-		__field(bool, paged)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->cnt = cnt;
-		__entry->paged = paged;
-	),
-	TP_printk(DEV_PR_FMT "cnt:%d paged:%d",
-		  DEV_PR_ARG, __entry->cnt, __entry->paged)
-);
-
-DEFINE_EVENT(dev_simple_evt, mt76x0_set_key,
-	TP_PROTO(struct mt76_dev *dev, u8 val),
-	TP_ARGS(dev, val)
-);
-
-TRACE_EVENT(mt76x0_set_shared_key,
-	TP_PROTO(struct mt76_dev *dev, u8 vid, u8 key),
-	TP_ARGS(dev, vid, key),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field(u8, vid)
-		__field(u8, key)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->vid = vid;
-		__entry->key = key;
-	),
-	TP_printk(DEV_PR_FMT "phy:%02hhx off:%02hhx",
-		  DEV_PR_ARG, __entry->vid, __entry->key)
-);
-
-#endif
-
-#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH .
-#undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_FILE trace
-
-#include <trace/define_trace.h>
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index ea517864186b..cdbb8a6db608 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -17,7 +17,6 @@
 
 #include "mt76x0.h"
 #include "mcu.h"
-#include "trace.h"
 #include "../mt76x02_usb.h"
 
 static struct usb_device_id mt76x0_device_table[] = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index 899ffd026e62..ccc7f532ceba 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -234,6 +234,8 @@ bool mt76x02_mac_load_tx_status(struct mt76x02_dev *dev,
 	stat->retry = FIELD_GET(MT_TX_STAT_FIFO_EXT_RETRY, stat2);
 	stat->pktid = FIELD_GET(MT_TX_STAT_FIFO_EXT_PKTID, stat2);
 
+	trace_mac_txstat_fetch(dev, stat);
+
 	return true;
 }
 
@@ -690,8 +692,6 @@ void mt76x02_mac_poll_tx_status(struct mt76x02_dev *dev, bool irq)
 		if (!ret)
 			break;
 
-		trace_mac_txstat_fetch(dev, &stat);
-
 		if (!irq) {
 			mt76x02_send_tx_status(dev, &stat, &update);
 			continue;
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index 4ef61d64fc36..24d41288ea59 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -354,6 +354,7 @@ int mt76u_submit_buf(struct mt76_dev *dev, int dir, int index,
 
 	usb_fill_bulk_urb(buf->urb, udev, pipe, NULL, buf->len,
 			  complete_fn, context);
+	trace_submit_urb(dev, buf->urb);
 
 	return usb_submit_urb(buf->urb, gfp);
 }
@@ -440,6 +441,8 @@ static void mt76u_complete_rx(struct urb *urb)
 	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
 	unsigned long flags;
 
+	trace_rx_urb(dev, urb);
+
 	switch (urb->status) {
 	case -ECONNRESET:
 	case -ESHUTDOWN:
@@ -726,6 +729,8 @@ static void mt76u_tx_kick(struct mt76_dev *dev, struct mt76_queue *q)
 
 	while (q->first != q->tail) {
 		buf = &q->entry[q->first].ubuf;
+
+		trace_submit_urb(dev, buf->urb);
 		err = usb_submit_urb(buf->urb, GFP_ATOMIC);
 		if (err < 0) {
 			if (err == -ENODEV)
diff --git a/drivers/net/wireless/mediatek/mt76/usb_trace.h b/drivers/net/wireless/mediatek/mt76/usb_trace.h
index 52db7012304a..b56c32343eb1 100644
--- a/drivers/net/wireless/mediatek/mt76/usb_trace.h
+++ b/drivers/net/wireless/mediatek/mt76/usb_trace.h
@@ -26,12 +26,12 @@
 #define MAXNAME		32
 #define DEV_ENTRY   __array(char, wiphy_name, 32)
 #define DEV_ASSIGN  strlcpy(__entry->wiphy_name, wiphy_name(dev->hw->wiphy), MAXNAME)
-#define DEV_PR_FMT  "%s"
+#define DEV_PR_FMT  "%s "
 #define DEV_PR_ARG  __entry->wiphy_name
 
 #define REG_ENTRY	__field(u32, reg) __field(u32, val)
 #define REG_ASSIGN	__entry->reg = reg; __entry->val = val
-#define REG_PR_FMT	" %04x=%08x"
+#define REG_PR_FMT	"reg:0x%04x=0x%08x"
 #define REG_PR_ARG	__entry->reg, __entry->val
 
 DECLARE_EVENT_CLASS(dev_reg_evt,
@@ -61,6 +61,31 @@ DEFINE_EVENT(dev_reg_evt, usb_reg_wr,
 	TP_ARGS(dev, reg, val)
 );
 
+DECLARE_EVENT_CLASS(urb_transfer,
+	TP_PROTO(struct mt76_dev *dev, struct urb *u),
+	TP_ARGS(dev, u),
+	TP_STRUCT__entry(
+		DEV_ENTRY __field(unsigned, pipe) __field(u32, len)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->pipe = u->pipe;
+		__entry->len = u->transfer_buffer_length;
+	),
+	TP_printk(DEV_PR_FMT "p:%08x len:%u",
+		  DEV_PR_ARG, __entry->pipe, __entry->len)
+);
+
+DEFINE_EVENT(urb_transfer, submit_urb,
+	TP_PROTO(struct mt76_dev *dev, struct urb *u),
+	TP_ARGS(dev, u)
+);
+
+DEFINE_EVENT(urb_transfer, rx_urb,
+	TP_PROTO(struct mt76_dev *dev, struct urb *u),
+	TP_ARGS(dev, u)
+);
+
 #endif
 
 #undef TRACE_INCLUDE_PATH
-- 
cgit v1.2.3


From ef442b73b6bc36b5499e1983611abb46e6337975 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Thu, 18 Oct 2018 12:15:31 +0200
Subject: mt76x0: antenna select corrections

Update mt76x0_phy_ant_select() to conform vendor driver, most notably
add dual antenna mode support, read configuration from EEPROM and
move ant select out of channel config to init phase. Plus small MT7630E
quirk for MT_CMB_CTRL register which vendor driver dedicated to this
chip do.

This make MT7630E workable with mt76x0e driver and do not cause any
problems on MT7610U for me.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Acked-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    | 52 ++++++++++++++++------
 .../net/wireless/mediatek/mt76/mt76x02_eeprom.h    | 10 ++---
 2 files changed, 44 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index 2a96f8cc0b20..b33074b783dc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -429,21 +429,47 @@ mt76x0_phy_set_chan_bbp_params(struct mt76x02_dev *dev, u16 rf_bw_band)
 
 static void mt76x0_phy_ant_select(struct mt76x02_dev *dev)
 {
-	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
-
-	/* single antenna mode */
-	if (chan->band == NL80211_BAND_2GHZ) {
-		mt76_rmw(dev, MT_COEXCFG3,
-			 BIT(5) | BIT(4) | BIT(3) | BIT(2), BIT(1));
-		mt76_rmw(dev, MT_WLAN_FUN_CTRL, BIT(5), BIT(6));
+	u16 ee_ant = mt76x02_eeprom_get(dev, MT_EE_ANTENNA);
+	u16 nic_conf2 = mt76x02_eeprom_get(dev, MT_EE_NIC_CONF_2);
+	u32 wlan, coex3, cmb;
+	bool ant_div;
+
+	wlan = mt76_rr(dev, MT_WLAN_FUN_CTRL);
+	cmb = mt76_rr(dev, MT_CMB_CTRL);
+	coex3 = mt76_rr(dev, MT_COEXCFG3);
+
+	cmb   &= ~(BIT(14) | BIT(12));
+	wlan  &= ~(BIT(6) | BIT(5));
+	coex3 &= ~GENMASK(5, 2);
+
+	if (ee_ant & MT_EE_ANTENNA_DUAL) {
+		/* dual antenna mode */
+		ant_div = !(nic_conf2 & MT_EE_NIC_CONF_2_ANT_OPT) &&
+			  (nic_conf2 & MT_EE_NIC_CONF_2_ANT_DIV);
+		if (ant_div)
+			cmb |= BIT(12);
+		else
+			coex3 |= BIT(4);
+		coex3 |= BIT(3);
+		if (dev->mt76.cap.has_2ghz)
+			wlan |= BIT(6);
 	} else {
-		mt76_rmw(dev, MT_COEXCFG3, BIT(5) | BIT(2),
-			 BIT(4) | BIT(3));
-		mt76_clear(dev, MT_WLAN_FUN_CTRL,
-			   BIT(6) | BIT(5));
+		/* sigle antenna mode */
+		if (dev->mt76.cap.has_5ghz) {
+			coex3 |= BIT(3) | BIT(4);
+		} else {
+			wlan |= BIT(6);
+			coex3 |= BIT(1);
+		}
 	}
-	mt76_clear(dev, MT_CMB_CTRL, BIT(14) | BIT(12));
+
+	if (is_mt7630(dev))
+		cmb |= BIT(14) | BIT(11);
+
+	mt76_wr(dev, MT_WLAN_FUN_CTRL, wlan);
+	mt76_wr(dev, MT_CMB_CTRL, cmb);
 	mt76_clear(dev, MT_COEXCFG0, BIT(2));
+	mt76_wr(dev, MT_COEXCFG3, coex3);
 }
 
 static void
@@ -610,7 +636,6 @@ int mt76x0_phy_set_channel(struct mt76x02_dev *dev,
 	mt76x02_phy_set_bw(dev, chandef->width, ch_group_index);
 	mt76x02_phy_set_band(dev, chandef->chan->band,
 			     ch_group_index & 1);
-	mt76x0_phy_ant_select(dev);
 
 	mt76_rmw(dev, MT_EXT_CCA_CFG,
 		 (MT_EXT_CCA_CFG_CCA0 |
@@ -836,6 +861,7 @@ void mt76x0_phy_init(struct mt76x02_dev *dev)
 {
 	INIT_DELAYED_WORK(&dev->cal_work, mt76x0_phy_calibration_work);
 
+	mt76x0_phy_ant_select(dev);
 	mt76x0_phy_rf_init(dev);
 	mt76x02_phy_set_rxpath(dev);
 	mt76x02_phy_set_txdac(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h
index b3ec74835d10..1de041590050 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h
@@ -25,6 +25,7 @@ enum mt76x02_eeprom_field {
 	MT_EE_VERSION =				0x002,
 	MT_EE_MAC_ADDR =			0x004,
 	MT_EE_PCI_ID =				0x00A,
+	MT_EE_ANTENNA =				0x022,
 	MT_EE_NIC_CONF_0 =			0x034,
 	MT_EE_NIC_CONF_1 =			0x036,
 	MT_EE_COUNTRY_REGION_5GHZ =		0x038,
@@ -104,6 +105,8 @@ enum mt76x02_eeprom_field {
 	__MT_EE_MAX
 };
 
+#define MT_EE_ANTENNA_DUAL			BIT(15)
+
 #define MT_EE_NIC_CONF_0_RX_PATH		GENMASK(3, 0)
 #define MT_EE_NIC_CONF_0_TX_PATH		GENMASK(7, 4)
 #define MT_EE_NIC_CONF_0_PA_TYPE		GENMASK(9, 8)
@@ -118,12 +121,9 @@ enum mt76x02_eeprom_field {
 #define MT_EE_NIC_CONF_1_LNA_EXT_5G		BIT(3)
 #define MT_EE_NIC_CONF_1_TX_ALC_EN		BIT(13)
 
-#define MT_EE_NIC_CONF_2_RX_STREAM		GENMASK(3, 0)
-#define MT_EE_NIC_CONF_2_TX_STREAM		GENMASK(7, 4)
-#define MT_EE_NIC_CONF_2_HW_ANTDIV		BIT(8)
+#define MT_EE_NIC_CONF_2_ANT_OPT		BIT(3)
+#define MT_EE_NIC_CONF_2_ANT_DIV		BIT(4)
 #define MT_EE_NIC_CONF_2_XTAL_OPTION		GENMASK(10, 9)
-#define MT_EE_NIC_CONF_2_TEMP_DISABLE		BIT(11)
-#define MT_EE_NIC_CONF_2_COEX_METHOD		GENMASK(15, 13)
 
 #define MT_EFUSE_USAGE_MAP_SIZE			(MT_EE_USAGE_MAP_END - \
 						 MT_EE_USAGE_MAP_START + 1)
-- 
cgit v1.2.3


From 00eccdd622078b319d789da4914715e68f42f3b5 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 16 Oct 2018 11:42:32 +0200
Subject: mt76x0: init: simplify mt76x0_init_mac_registers

Simplify mt76x0_init_mac_registers routine using mt76_set, mt76_clear
and mt76_rmw utility routines

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c | 27 +++++++++---------------
 1 file changed, 10 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index 74c007c44a8f..263d5e8df945 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -133,8 +133,6 @@ static int mt76x0_init_bbp(struct mt76x02_dev *dev)
 
 static void mt76x0_init_mac_registers(struct mt76x02_dev *dev)
 {
-	u32 reg;
-
 	RANDOM_WRITE(dev, common_mac_reg_table);
 
 	mt76x02_set_beacon_offsets(dev);
@@ -143,27 +141,22 @@ static void mt76x0_init_mac_registers(struct mt76x02_dev *dev)
 	RANDOM_WRITE(dev, mt76x0_mac_reg_table);
 
 	/* Release BBP and MAC reset MAC_SYS_CTRL[1:0] = 0x0 */
-	reg = mt76_rr(dev, MT_MAC_SYS_CTRL);
-	reg &= ~0x3;
-	mt76_wr(dev, MT_MAC_SYS_CTRL, reg);
+	mt76_clear(dev, MT_MAC_SYS_CTRL, 0x3);
 
 	/* Set 0x141C[15:12]=0xF */
-	reg = mt76_rr(dev, MT_EXT_CCA_CFG);
-	reg |= 0x0000F000;
-	mt76_wr(dev, MT_EXT_CCA_CFG, reg);
+	mt76_set(dev, MT_EXT_CCA_CFG, 0xf000);
 
 	mt76_clear(dev, MT_FCE_L2_STUFF, MT_FCE_L2_STUFF_WR_MPDU_LEN_EN);
 
 	/*
-		TxRing 9 is for Mgmt frame.
-		TxRing 8 is for In-band command frame.
-		WMM_RG0_TXQMA: This register setting is for FCE to define the rule of TxRing 9.
-		WMM_RG1_TXQMA: This register setting is for FCE to define the rule of TxRing 8.
-	*/
-	reg = mt76_rr(dev, MT_WMM_CTRL);
-	reg &= ~0x000003FF;
-	reg |= 0x00000201;
-	mt76_wr(dev, MT_WMM_CTRL, reg);
+	 * tx_ring 9 is for mgmt frame
+	 * tx_ring 8 is for in-band command frame.
+	 * WMM_RG0_TXQMA: this register setting is for FCE to
+	 *		  define the rule of tx_ring 9
+	 * WMM_RG1_TXQMA: this register setting is for FCE to
+	 *		  define the rule of tx_ring 8
+	 */
+	mt76_rmw(dev, MT_WMM_CTRL, 0x3ff, 0x201);
 }
 
 static int mt76x0_init_wcid_mem(struct mt76x02_dev *dev)
-- 
cgit v1.2.3


From b13dc8a8da093a49219d54bb55981ef23e912da7 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 19 Oct 2018 00:57:32 +0200
Subject: mt76x0: pci: add missing MODULE_FIRMWARE macro

Add missing firmware declaration for mt76x0e driver

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h  | 3 +++
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c     | 2 ++
 drivers/net/wireless/mediatek/mt76/mt76x0/pci_mcu.c | 3 ---
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 989ed00c0b7a..24e817bda500 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -28,6 +28,9 @@
 #include "../mt76x02.h"
 #include "eeprom.h"
 
+#define MT7610E_FIRMWARE		"mediatek/mt7610e.bin"
+#define MT7650E_FIRMWARE		"mediatek/mt7650e.bin"
+
 #define MT_USB_AGGR_SIZE_LIMIT		21 /* * 1024B */
 #define MT_USB_AGGR_TIMEOUT		0x80 /* * 33ns */
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 3277e6b07a46..6e11b8c8e495 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -211,6 +211,8 @@ static const struct pci_device_id mt76x0e_device_table[] = {
 };
 
 MODULE_DEVICE_TABLE(pci, mt76x0e_device_table);
+MODULE_FIRMWARE(MT7610E_FIRMWARE);
+MODULE_FIRMWARE(MT7650E_FIRMWARE);
 MODULE_LICENSE("Dual BSD/GPL");
 
 static struct pci_driver mt76x0e_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci_mcu.c
index 569861289aa5..aca0ea318dce 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci_mcu.c
@@ -19,9 +19,6 @@
 #include "mt76x0.h"
 #include "mcu.h"
 
-#define MT7610E_FIRMWARE	"mediatek/mt7610e.bin"
-#define MT7650E_FIRMWARE	"mediatek/mt7650e.bin"
-
 #define MT_MCU_IVB_ADDR		(MT_MCU_ILM_ADDR + 0x54000 - MT_MCU_IVB_SIZE)
 
 static int mt76x0e_load_firmware(struct mt76x02_dev *dev)
-- 
cgit v1.2.3


From 64c6a54a5a7c0ce9f88aab718cc76e6fd2485150 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 19 Oct 2018 12:47:35 +0200
Subject: mt76x0: mac: remove mt76x0_mac_set_ampdu_factor

Remove no longer used mt76x0_mac_set_ampdu_factor routine

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c    | 25 ----------------------
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  1 -
 2 files changed, 26 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
index 8cbdeb6d3dbe..57e15c8ced7e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
@@ -103,28 +103,3 @@ void mt76x0_mac_config_tsf(struct mt76x02_dev *dev, bool enable, int interval)
 		MT_BEACON_TIME_CFG_SYNC_MODE |
 		MT_BEACON_TIME_CFG_TBTT_EN;
 }
-
-void mt76x0_mac_set_ampdu_factor(struct mt76x02_dev *dev)
-{
-	struct ieee80211_sta *sta;
-	struct mt76_wcid *wcid;
-	void *msta;
-	u8 min_factor = 3;
-	int i;
-
-	rcu_read_lock();
-	for (i = 0; i < ARRAY_SIZE(dev->mt76.wcid); i++) {
-		wcid = rcu_dereference(dev->mt76.wcid[i]);
-		if (!wcid)
-			continue;
-
-		msta = container_of(wcid, struct mt76x02_sta, wcid);
-		sta = container_of(msta, struct ieee80211_sta, drv_priv);
-
-		min_factor = min(min_factor, sta->ht_cap.ampdu_factor);
-	}
-	rcu_read_unlock();
-
-	mt76_wr(dev, MT_MAX_LEN_CFG, 0xa0fff |
-		   FIELD_PREP(MT_MAX_LEN_CFG_AMPDU, min_factor));
-}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 24e817bda500..0f11815b93fa 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -82,6 +82,5 @@ void mt76x0_mac_set_protection(struct mt76x02_dev *dev, bool legacy_prot,
 				int ht_mode);
 void mt76x0_mac_set_short_preamble(struct mt76x02_dev *dev, bool short_preamb);
 void mt76x0_mac_config_tsf(struct mt76x02_dev *dev, bool enable, int interval);
-void mt76x0_mac_set_ampdu_factor(struct mt76x02_dev *dev);
 
 #endif
-- 
cgit v1.2.3


From f47301403f112cfc681abb644a4c4e382503773c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 19 Oct 2018 11:40:48 +0200
Subject: mt76x0: align mt76x0u and mt76x0e fw version

Unify firmware version used on mt76x0e and mt76x0u drivers.
Fallback to mt7610u fw if mt7610e one is not available

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  2 ++
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c    |  2 ++
 .../net/wireless/mediatek/mt76/mt76x0/usb_mcu.c    | 23 ++++++++++++++++++----
 3 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 0f11815b93fa..282814cbcc12 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -31,6 +31,8 @@
 #define MT7610E_FIRMWARE		"mediatek/mt7610e.bin"
 #define MT7650E_FIRMWARE		"mediatek/mt7650e.bin"
 
+#define MT7610U_FIRMWARE		"mediatek/mt7610u.bin"
+
 #define MT_USB_AGGR_SIZE_LIMIT		21 /* * 1024B */
 #define MT_USB_AGGR_TIMEOUT		0x80 /* * 33ns */
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index cdbb8a6db608..245eb4aa9764 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -337,6 +337,8 @@ err:
 }
 
 MODULE_DEVICE_TABLE(usb, mt76x0_device_table);
+MODULE_FIRMWARE(MT7610E_FIRMWARE);
+MODULE_FIRMWARE(MT7610U_FIRMWARE);
 MODULE_LICENSE("GPL");
 
 static struct usb_driver mt76x0_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb_mcu.c
index a9f14d5149d1..9d7585029df9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb_mcu.c
@@ -22,7 +22,6 @@
 
 #define MCU_FW_URB_MAX_PAYLOAD		0x38f8
 #define MCU_FW_URB_SIZE			(MCU_FW_URB_MAX_PAYLOAD + 12)
-#define MT7610U_FIRMWARE		"mediatek/mt7610u.bin"
 
 static int
 mt76x0u_upload_firmware(struct mt76x02_dev *dev,
@@ -75,6 +74,24 @@ out:
 	return err;
 }
 
+static int mt76x0_get_firmware(struct mt76x02_dev *dev,
+			       const struct firmware **fw)
+{
+	int err;
+
+	/* try to load mt7610e fw if available
+	 * otherwise fall back to mt7610u one
+	 */
+	err = firmware_request_nowarn(fw, MT7610E_FIRMWARE, dev->mt76.dev);
+	if (err) {
+		dev_info(dev->mt76.dev, "%s not found, switching to %s",
+			 MT7610E_FIRMWARE, MT7610U_FIRMWARE);
+		return request_firmware(fw, MT7610U_FIRMWARE,
+					dev->mt76.dev);
+	}
+	return 0;
+}
+
 static int mt76x0u_load_firmware(struct mt76x02_dev *dev)
 {
 	const struct firmware *fw;
@@ -88,7 +105,7 @@ static int mt76x0u_load_firmware(struct mt76x02_dev *dev)
 	if (mt76x0_firmware_running(dev))
 		return 0;
 
-	ret = request_firmware(&fw, MT7610U_FIRMWARE, dev->mt76.dev);
+	ret = mt76x0_get_firmware(dev, &fw);
 	if (ret)
 		return ret;
 
@@ -171,5 +188,3 @@ int mt76x0u_mcu_init(struct mt76x02_dev *dev)
 
 	return 0;
 }
-
-MODULE_FIRMWARE(MT7610U_FIRMWARE);
-- 
cgit v1.2.3


From dd61100db4acb374a1d93f7bfa966d9c07cecfa8 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 19 Oct 2018 14:56:24 +0200
Subject: mt76: move mt76x02_mac_set_short_preamble in mt76x02_mac.c

Move mt76x02_mac_set_short_preamble routine in mt76x02-lib module
since it is shared between mt76x0 and mt76x2 drivers

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c    | 8 --------
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c   | 2 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h | 1 -
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c   | 9 +++++++++
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.h   | 1 +
 5 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
index 57e15c8ced7e..ded0ad623723 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
@@ -76,14 +76,6 @@ void mt76x0_mac_set_protection(struct mt76x02_dev *dev, bool legacy_prot,
 		mt76_wr(dev, MT_CCK_PROT_CFG + i * 4, prot[i]);
 }
 
-void mt76x0_mac_set_short_preamble(struct mt76x02_dev *dev, bool short_preamb)
-{
-	if (short_preamb)
-		mt76_set(dev, MT_AUTO_RSP_CFG, MT_AUTO_RSP_PREAMB_SHORT);
-	else
-		mt76_clear(dev, MT_AUTO_RSP_CFG, MT_AUTO_RSP_PREAMB_SHORT);
-}
-
 void mt76x0_mac_config_tsf(struct mt76x02_dev *dev, bool enable, int interval)
 {
 	u32 val = mt76_rr(dev, MT_BEACON_TIME_CFG);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index fdffbdf90e59..a61b23239cb2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -112,7 +112,7 @@ void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
 					   info->ht_operation_mode);
 
 	if (changed & BSS_CHANGED_ERP_PREAMBLE)
-		mt76x0_mac_set_short_preamble(dev, info->use_short_preamble);
+		mt76x02_mac_set_short_preamble(dev, info->use_short_preamble);
 
 	if (changed & BSS_CHANGED_ERP_SLOT) {
 		int slottime = info->use_short_slot ? 9 : 20;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 282814cbcc12..9cdecb9bfc64 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -82,7 +82,6 @@ void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on);
 /* MAC */
 void mt76x0_mac_set_protection(struct mt76x02_dev *dev, bool legacy_prot,
 				int ht_mode);
-void mt76x0_mac_set_short_preamble(struct mt76x02_dev *dev, bool short_preamb);
 void mt76x0_mac_config_tsf(struct mt76x02_dev *dev, bool enable, int interval);
 
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index ccc7f532ceba..f21bf0af8937 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -213,6 +213,15 @@ void mt76x02_mac_wcid_set_rate(struct mt76x02_dev *dev, struct mt76_wcid *wcid,
 	spin_unlock_bh(&dev->mt76.lock);
 }
 
+void mt76x02_mac_set_short_preamble(struct mt76x02_dev *dev, bool enable)
+{
+	if (enable)
+		mt76_set(dev, MT_AUTO_RSP_CFG, MT_AUTO_RSP_PREAMB_SHORT);
+	else
+		mt76_clear(dev, MT_AUTO_RSP_CFG, MT_AUTO_RSP_PREAMB_SHORT);
+}
+EXPORT_SYMBOL_GPL(mt76x02_mac_set_short_preamble);
+
 bool mt76x02_mac_load_tx_status(struct mt76x02_dev *dev,
 				struct mt76x02_tx_status *stat)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index 81c16aef6a94..55b3a49ba77a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -200,6 +200,7 @@ mt76x02_skb_tx_info(struct sk_buff *skb)
 
 void mt76x02_txq_init(struct mt76x02_dev *dev, struct ieee80211_txq *txq);
 
+void mt76x02_mac_set_short_preamble(struct mt76x02_dev *dev, bool enable);
 int mt76x02_mac_shared_key_setup(struct mt76x02_dev *dev, u8 vif_idx,
 				 u8 key_idx, struct ieee80211_key_conf *key);
 int mt76x02_mac_wcid_set_key(struct mt76x02_dev *dev, u8 idx,
-- 
cgit v1.2.3


From 5cbace02d842b62cf276ef97555a5f296d3dc59e Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:13:24 +0200
Subject: mt76: move mt76x02_init_device in mt76x02-lib module

Move mt76x02_init_device routine in mt76x02_util.c in order to be
reused by mt76x0 driver and remove duplicated code. Move interface
combo definition supported by the driver in mt76x02_init_device routine

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c |  2 -
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c   | 36 +---------
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c  | 81 ++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2/init.c   | 34 ---------
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h |  1 -
 .../net/wireless/mediatek/mt76/mt76x2/pci_init.c   | 41 +----------
 .../net/wireless/mediatek/mt76/mt76x2/usb_init.c   |  5 +-
 8 files changed, 87 insertions(+), 114 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
index ab4fd6e0f23a..275d77c90624 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
@@ -340,8 +340,6 @@ int mt76x0_eeprom_init(struct mt76x02_dev *dev)
 	mt76x0_set_freq_offset(dev);
 	mt76x0_set_temp_offset(dev);
 
-	dev->mt76.chainmask = 0x0101;
-
 	return 0;
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index 263d5e8df945..95a015281697 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -338,46 +338,16 @@ EXPORT_SYMBOL_GPL(mt76x0_alloc_device);
 
 int mt76x0_register_device(struct mt76x02_dev *dev)
 {
-	struct mt76_dev *mdev = &dev->mt76;
-	struct ieee80211_hw *hw = mdev->hw;
-	struct wiphy *wiphy = hw->wiphy;
 	int ret;
 
-	/* Reserve WCID 0 for mcast - thanks to this APs WCID will go to
-	 * entry no. 1 like it does in the vendor driver.
-	 */
-	mdev->wcid_mask[0] |= 1;
-
-	/* init fake wcid for monitor interfaces */
-	mdev->global_wcid.idx = 0xff;
-	mdev->global_wcid.hw_key_idx = -1;
-
-	/* init antenna configuration */
-	mdev->antenna_mask = 1;
-
-	hw->queues = 4;
-	hw->max_rates = 1;
-	hw->max_report_rates = 7;
-	hw->max_rate_tries = 1;
-	hw->extra_tx_headroom = 2;
-	if (mt76_is_usb(dev))
-		hw->extra_tx_headroom += sizeof(struct mt76x02_txwi) +
-					 MT_DMA_HDR_LEN;
-
-	hw->sta_data_size = sizeof(struct mt76x02_sta);
-	hw->vif_data_size = sizeof(struct mt76x02_vif);
-
-	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
-
-	INIT_DELAYED_WORK(&dev->mac_work, mt76x02_mac_work);
-
-	ret = mt76_register_device(mdev, true, mt76x02_rates,
+	mt76x02_init_device(dev);
+	ret = mt76_register_device(&dev->mt76, true, mt76x02_rates,
 				   ARRAY_SIZE(mt76x02_rates));
 	if (ret)
 		return ret;
 
 	/* overwrite unsupported features */
-	if (mdev->cap.has_5ghz)
+	if (dev->mt76.cap.has_5ghz)
 		mt76x0_vht_cap_mask(&dev->mt76.sband_5g.sband);
 
 	mt76x02_init_debugfs(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index bdbe4bbf7a59..1cd0f758587d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -102,6 +102,7 @@ struct mt76x02_dev {
 
 extern struct ieee80211_rate mt76x02_rates[12];
 
+void mt76x02_init_device(struct mt76x02_dev *dev);
 void mt76x02_configure_filter(struct ieee80211_hw *hw,
 			     unsigned int changed_flags,
 			     unsigned int *total_flags, u64 multicast);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index ca05332f81fc..208c76d40afa 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -47,6 +47,87 @@ struct ieee80211_rate mt76x02_rates[] = {
 };
 EXPORT_SYMBOL_GPL(mt76x02_rates);
 
+static const struct ieee80211_iface_limit mt76x02_if_limits[] = {
+	{
+		.max = 1,
+		.types = BIT(NL80211_IFTYPE_ADHOC)
+	}, {
+		.max = 8,
+		.types = BIT(NL80211_IFTYPE_STATION) |
+#ifdef CONFIG_MAC80211_MESH
+			 BIT(NL80211_IFTYPE_MESH_POINT) |
+#endif
+			 BIT(NL80211_IFTYPE_AP)
+	 },
+};
+
+static const struct ieee80211_iface_combination mt76x02_if_comb[] = {
+	{
+		.limits = mt76x02_if_limits,
+		.n_limits = ARRAY_SIZE(mt76x02_if_limits),
+		.max_interfaces = 8,
+		.num_different_channels = 1,
+		.beacon_int_infra_match = true,
+		.radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) |
+				       BIT(NL80211_CHAN_WIDTH_20) |
+				       BIT(NL80211_CHAN_WIDTH_40) |
+				       BIT(NL80211_CHAN_WIDTH_80),
+	}
+};
+
+void mt76x02_init_device(struct mt76x02_dev *dev)
+{
+	struct ieee80211_hw *hw = mt76_hw(dev);
+	struct wiphy *wiphy = hw->wiphy;
+
+	INIT_DELAYED_WORK(&dev->mac_work, mt76x02_mac_work);
+
+	hw->queues = 4;
+	hw->max_rates = 1;
+	hw->max_report_rates = 7;
+	hw->max_rate_tries = 1;
+	hw->extra_tx_headroom = 2;
+
+	if (mt76_is_usb(dev)) {
+		hw->extra_tx_headroom += sizeof(struct mt76x02_txwi) +
+					 MT_DMA_HDR_LEN;
+		wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
+	} else {
+		wiphy->iface_combinations = mt76x02_if_comb;
+		wiphy->n_iface_combinations = ARRAY_SIZE(mt76x02_if_comb);
+		wiphy->interface_modes =
+			BIT(NL80211_IFTYPE_STATION) |
+			BIT(NL80211_IFTYPE_AP) |
+#ifdef CONFIG_MAC80211_MESH
+			BIT(NL80211_IFTYPE_MESH_POINT) |
+#endif
+			BIT(NL80211_IFTYPE_ADHOC);
+	}
+
+	hw->sta_data_size = sizeof(struct mt76x02_sta);
+	hw->vif_data_size = sizeof(struct mt76x02_vif);
+
+	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
+	ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
+
+	dev->mt76.global_wcid.idx = 255;
+	dev->mt76.global_wcid.hw_key_idx = -1;
+	dev->slottime = 9;
+
+	if (is_mt76x2(dev)) {
+		dev->mt76.sband_2g.sband.ht_cap.cap |=
+				IEEE80211_HT_CAP_LDPC_CODING;
+		dev->mt76.sband_5g.sband.ht_cap.cap |=
+				IEEE80211_HT_CAP_LDPC_CODING;
+		dev->mt76.chainmask = 0x202;
+		dev->mt76.antenna_mask = 3;
+	} else {
+		dev->mt76.chainmask = 0x101;
+		dev->mt76.antenna_mask = 1;
+	}
+}
+EXPORT_SYMBOL_GPL(mt76x02_init_device);
+
 void mt76x02_configure_filter(struct ieee80211_hw *hw,
 			      unsigned int changed_flags,
 			      unsigned int *total_flags, u64 multicast)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/init.c
index 04790f84d7d4..54a9b5fac787 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/init.c
@@ -158,40 +158,6 @@ void mt76_write_mac_initvals(struct mt76x02_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76_write_mac_initvals);
 
-void mt76x2_init_device(struct mt76x02_dev *dev)
-{
-	struct ieee80211_hw *hw = mt76_hw(dev);
-
-	INIT_DELAYED_WORK(&dev->mac_work, mt76x02_mac_work);
-
-	hw->queues = 4;
-	hw->max_rates = 1;
-	hw->max_report_rates = 7;
-	hw->max_rate_tries = 1;
-	hw->extra_tx_headroom = 2;
-	if (mt76_is_usb(dev))
-		hw->extra_tx_headroom += sizeof(struct mt76x02_txwi) +
-					 MT_DMA_HDR_LEN;
-
-	hw->sta_data_size = sizeof(struct mt76x02_sta);
-	hw->vif_data_size = sizeof(struct mt76x02_vif);
-
-	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
-	ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
-
-	dev->mt76.sband_2g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
-	dev->mt76.sband_5g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
-
-	dev->mt76.chainmask = 0x202;
-	dev->mt76.global_wcid.idx = 255;
-	dev->mt76.global_wcid.hw_key_idx = -1;
-	dev->slottime = 9;
-
-	/* init antenna configuration */
-	dev->mt76.antenna_mask = 3;
-}
-EXPORT_SYMBOL_GPL(mt76x2_init_device);
-
 void mt76x2_init_txpower(struct mt76x02_dev *dev,
 			 struct ieee80211_supported_band *sband)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index 7408db788409..eaa44de14826 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -52,7 +52,6 @@ extern const struct ieee80211_ops mt76x2_ops;
 
 struct mt76x02_dev *mt76x2_alloc_device(struct device *pdev);
 int mt76x2_register_device(struct mt76x02_dev *dev);
-void mt76x2_init_device(struct mt76x02_dev *dev);
 
 void mt76x2_phy_power_on(struct mt76x02_dev *dev);
 int mt76x2_init_hardware(struct mt76x02_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index b15c97e1dfb3..d0dbf6936c92 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -384,34 +384,6 @@ static void mt76x2_regd_notifier(struct wiphy *wiphy,
 	mt76x2_dfs_set_domain(dev, request->dfs_region);
 }
 
-static const struct ieee80211_iface_limit if_limits[] = {
-	{
-		.max = 1,
-		.types = BIT(NL80211_IFTYPE_ADHOC)
-	}, {
-		.max = 8,
-		.types = BIT(NL80211_IFTYPE_STATION) |
-#ifdef CONFIG_MAC80211_MESH
-			 BIT(NL80211_IFTYPE_MESH_POINT) |
-#endif
-			 BIT(NL80211_IFTYPE_AP)
-	 },
-};
-
-static const struct ieee80211_iface_combination if_comb[] = {
-	{
-		.limits = if_limits,
-		.n_limits = ARRAY_SIZE(if_limits),
-		.max_interfaces = 8,
-		.num_different_channels = 1,
-		.beacon_int_infra_match = true,
-		.radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) |
-				       BIT(NL80211_CHAN_WIDTH_20) |
-				       BIT(NL80211_CHAN_WIDTH_40) |
-				       BIT(NL80211_CHAN_WIDTH_80),
-	}
-};
-
 static void mt76x2_led_set_config(struct mt76_dev *mt76, u8 delay_on,
 				  u8 delay_off)
 {
@@ -468,7 +440,7 @@ int mt76x2_register_device(struct mt76x02_dev *dev)
 
 	INIT_DELAYED_WORK(&dev->cal_work, mt76x2_phy_calibrate);
 
-	mt76x2_init_device(dev);
+	mt76x02_init_device(dev);
 
 	ret = mt76x2_init_hardware(dev);
 	if (ret)
@@ -488,19 +460,8 @@ int mt76x2_register_device(struct mt76x02_dev *dev)
 	wiphy->addresses = dev->macaddr_list;
 	wiphy->n_addresses = ARRAY_SIZE(dev->macaddr_list);
 
-	wiphy->iface_combinations = if_comb;
-	wiphy->n_iface_combinations = ARRAY_SIZE(if_comb);
-
 	wiphy->reg_notifier = mt76x2_regd_notifier;
 
-	wiphy->interface_modes =
-		BIT(NL80211_IFTYPE_STATION) |
-		BIT(NL80211_IFTYPE_AP) |
-#ifdef CONFIG_MAC80211_MESH
-		BIT(NL80211_IFTYPE_MESH_POINT) |
-#endif
-		BIT(NL80211_IFTYPE_ADHOC);
-
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 
 	mt76x2_dfs_init_detector(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
index b2388f506505..a7d591610f16 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
@@ -245,11 +245,10 @@ int mt76x2u_init_hardware(struct mt76x02_dev *dev)
 int mt76x2u_register_device(struct mt76x02_dev *dev)
 {
 	struct ieee80211_hw *hw = mt76_hw(dev);
-	struct wiphy *wiphy = hw->wiphy;
 	int err;
 
 	INIT_DELAYED_WORK(&dev->cal_work, mt76x2u_phy_calibrate);
-	mt76x2_init_device(dev);
+	mt76x02_init_device(dev);
 
 	err = mt76x2u_init_eeprom(dev);
 	if (err < 0)
@@ -267,8 +266,6 @@ int mt76x2u_register_device(struct mt76x02_dev *dev)
 	if (err < 0)
 		goto fail;
 
-	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
-
 	err = mt76_register_device(&dev->mt76, true, mt76x02_rates,
 				   ARRAY_SIZE(mt76x02_rates));
 	if (err)
-- 
cgit v1.2.3


From dc33b2512d9237ce80cf5f404d91ebb2ca9142b9 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:13:25 +0200
Subject: mt76: move mac beacon routines in mt76x02-lib module

Move mt76x02_beacon mac routines in mt76x02_mac.c in
order to be reused by mt76x0 driver adding AP support

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c   | 123 +++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.h   |   6 +
 drivers/net/wireless/mediatek/mt76/mt76x2/mac.h    |   5 -
 .../net/wireless/mediatek/mt76/mt76x2/pci_init.c   |   4 +-
 .../net/wireless/mediatek/mt76/mt76x2/pci_mac.c    | 118 --------------------
 .../net/wireless/mediatek/mt76/mt76x2/pci_main.c   |   6 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_tx.c |   2 +-
 7 files changed, 135 insertions(+), 129 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index f21bf0af8937..d9d7f3e609fc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -794,3 +794,126 @@ void mt76x02_mac_work(struct work_struct *work)
 				     MT_CALIBRATE_INTERVAL);
 }
 EXPORT_SYMBOL_GPL(mt76x02_mac_work);
+
+void mt76x02_mac_set_bssid(struct mt76x02_dev *dev, u8 idx, const u8 *addr)
+{
+	idx &= 7;
+	mt76_wr(dev, MT_MAC_APC_BSSID_L(idx), get_unaligned_le32(addr));
+	mt76_rmw_field(dev, MT_MAC_APC_BSSID_H(idx), MT_MAC_APC_BSSID_H_ADDR,
+		       get_unaligned_le16(addr + 4));
+}
+EXPORT_SYMBOL_GPL(mt76x02_mac_set_bssid);
+
+static int
+mt76x02_write_beacon(struct mt76x02_dev *dev, int offset, struct sk_buff *skb)
+{
+	int beacon_len = mt76x02_beacon_offsets[1] - mt76x02_beacon_offsets[0];
+	struct mt76x02_txwi txwi;
+
+	if (WARN_ON_ONCE(beacon_len < skb->len + sizeof(struct mt76x02_txwi)))
+		return -ENOSPC;
+
+	mt76x02_mac_write_txwi(dev, &txwi, skb, NULL, NULL, skb->len);
+
+	mt76_wr_copy(dev, offset, &txwi, sizeof(txwi));
+	offset += sizeof(txwi);
+
+	mt76_wr_copy(dev, offset, skb->data, skb->len);
+	return 0;
+}
+
+static int
+__mt76x02_mac_set_beacon(struct mt76x02_dev *dev, u8 bcn_idx,
+			 struct sk_buff *skb)
+{
+	int beacon_len = mt76x02_beacon_offsets[1] - mt76x02_beacon_offsets[0];
+	int beacon_addr = mt76x02_beacon_offsets[bcn_idx];
+	int ret = 0;
+	int i;
+
+	/* Prevent corrupt transmissions during update */
+	mt76_set(dev, MT_BCN_BYPASS_MASK, BIT(bcn_idx));
+
+	if (skb) {
+		ret = mt76x02_write_beacon(dev, beacon_addr, skb);
+		if (!ret)
+			dev->beacon_data_mask |= BIT(bcn_idx);
+	} else {
+		dev->beacon_data_mask &= ~BIT(bcn_idx);
+		for (i = 0; i < beacon_len; i += 4)
+			mt76_wr(dev, beacon_addr + i, 0);
+	}
+
+	mt76_wr(dev, MT_BCN_BYPASS_MASK, 0xff00 | ~dev->beacon_data_mask);
+
+	return ret;
+}
+
+int mt76x02_mac_set_beacon(struct mt76x02_dev *dev, u8 vif_idx,
+			   struct sk_buff *skb)
+{
+	bool force_update = false;
+	int bcn_idx = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dev->beacons); i++) {
+		if (vif_idx == i) {
+			force_update = !!dev->beacons[i] ^ !!skb;
+
+			if (dev->beacons[i])
+				dev_kfree_skb(dev->beacons[i]);
+
+			dev->beacons[i] = skb;
+			__mt76x02_mac_set_beacon(dev, bcn_idx, skb);
+		} else if (force_update && dev->beacons[i]) {
+			__mt76x02_mac_set_beacon(dev, bcn_idx,
+						 dev->beacons[i]);
+		}
+
+		bcn_idx += !!dev->beacons[i];
+	}
+
+	for (i = bcn_idx; i < ARRAY_SIZE(dev->beacons); i++) {
+		if (!(dev->beacon_data_mask & BIT(i)))
+			break;
+
+		__mt76x02_mac_set_beacon(dev, i, NULL);
+	}
+
+	mt76_rmw_field(dev, MT_MAC_BSSID_DW1, MT_MAC_BSSID_DW1_MBEACON_N,
+		       bcn_idx - 1);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x02_mac_set_beacon);
+
+void mt76x02_mac_set_beacon_enable(struct mt76x02_dev *dev,
+				   u8 vif_idx, bool val)
+{
+	u8 old_mask = dev->beacon_mask;
+	bool en;
+	u32 reg;
+
+	if (val) {
+		dev->beacon_mask |= BIT(vif_idx);
+	} else {
+		dev->beacon_mask &= ~BIT(vif_idx);
+		mt76x02_mac_set_beacon(dev, vif_idx, NULL);
+	}
+
+	if (!!old_mask == !!dev->beacon_mask)
+		return;
+
+	en = dev->beacon_mask;
+
+	mt76_rmw_field(dev, MT_INT_TIMER_EN, MT_INT_TIMER_EN_PRE_TBTT_EN, en);
+	reg = MT_BEACON_TIME_CFG_BEACON_TX |
+	      MT_BEACON_TIME_CFG_TBTT_EN |
+	      MT_BEACON_TIME_CFG_TIMER_EN;
+	mt76_rmw(dev, MT_BEACON_TIME_CFG, reg, reg * en);
+
+	if (en)
+		mt76x02_irq_enable(dev, MT_INT_PRE_TBTT | MT_INT_TBTT);
+	else
+		mt76x02_irq_disable(dev, MT_INT_PRE_TBTT | MT_INT_TBTT);
+}
+EXPORT_SYMBOL_GPL(mt76x02_mac_set_beacon_enable);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index 55b3a49ba77a..350cb0fed980 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -227,4 +227,10 @@ void mt76x02_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
 			     struct mt76_queue_entry *e, bool flush);
 void mt76x02_update_channel(struct mt76_dev *mdev);
 void mt76x02_mac_work(struct work_struct *work);
+
+void mt76x02_mac_set_bssid(struct mt76x02_dev *dev, u8 idx, const u8 *addr);
+int mt76x02_mac_set_beacon(struct mt76x02_dev *dev, u8 vif_idx,
+			   struct sk_buff *skb);
+void mt76x02_mac_set_beacon_enable(struct mt76x02_dev *dev, u8 vif_idx,
+				   bool val);
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mac.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mac.h
index 2dc2b9d5dc8f..4c8e20bce920 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mac.h
@@ -26,10 +26,5 @@ struct mt76x02_vif;
 int mt76x2_mac_start(struct mt76x02_dev *dev);
 void mt76x2_mac_stop(struct mt76x02_dev *dev, bool force);
 void mt76x2_mac_resume(struct mt76x02_dev *dev);
-void mt76x2_mac_set_bssid(struct mt76x02_dev *dev, u8 idx, const u8 *addr);
-
-int mt76x2_mac_set_beacon(struct mt76x02_dev *dev, u8 vif_idx,
-			  struct sk_buff *skb);
-void mt76x2_mac_set_beacon_enable(struct mt76x02_dev *dev, u8 vif_idx, bool val);
 
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index d0dbf6936c92..5c1531ae8b93 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -153,8 +153,8 @@ static int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard)
 			mt76x02_mac_shared_key_setup(dev, i, k, NULL);
 
 	for (i = 0; i < 8; i++) {
-		mt76x2_mac_set_bssid(dev, i, null_addr);
-		mt76x2_mac_set_beacon(dev, i, NULL);
+		mt76x02_mac_set_bssid(dev, i, null_addr);
+		mt76x02_mac_set_beacon(dev, i, NULL);
 	}
 
 	for (i = 0; i < 16; i++)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c
index 97128ea6bd7a..31e1f5bd9050 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c
@@ -19,124 +19,6 @@
 #include "mcu.h"
 #include "eeprom.h"
 
-void mt76x2_mac_set_bssid(struct mt76x02_dev *dev, u8 idx, const u8 *addr)
-{
-	idx &= 7;
-	mt76_wr(dev, MT_MAC_APC_BSSID_L(idx), get_unaligned_le32(addr));
-	mt76_rmw_field(dev, MT_MAC_APC_BSSID_H(idx), MT_MAC_APC_BSSID_H_ADDR,
-		       get_unaligned_le16(addr + 4));
-}
-
-static int
-mt76_write_beacon(struct mt76x02_dev *dev, int offset, struct sk_buff *skb)
-{
-	int beacon_len = mt76x02_beacon_offsets[1] - mt76x02_beacon_offsets[0];
-	struct mt76x02_txwi txwi;
-
-	if (WARN_ON_ONCE(beacon_len < skb->len + sizeof(struct mt76x02_txwi)))
-		return -ENOSPC;
-
-	mt76x02_mac_write_txwi(dev, &txwi, skb, NULL, NULL, skb->len);
-
-	mt76_wr_copy(dev, offset, &txwi, sizeof(txwi));
-	offset += sizeof(txwi);
-
-	mt76_wr_copy(dev, offset, skb->data, skb->len);
-	return 0;
-}
-
-static int
-__mt76x2_mac_set_beacon(struct mt76x02_dev *dev, u8 bcn_idx, struct sk_buff *skb)
-{
-	int beacon_len = mt76x02_beacon_offsets[1] - mt76x02_beacon_offsets[0];
-	int beacon_addr = mt76x02_beacon_offsets[bcn_idx];
-	int ret = 0;
-	int i;
-
-	/* Prevent corrupt transmissions during update */
-	mt76_set(dev, MT_BCN_BYPASS_MASK, BIT(bcn_idx));
-
-	if (skb) {
-		ret = mt76_write_beacon(dev, beacon_addr, skb);
-		if (!ret)
-			dev->beacon_data_mask |= BIT(bcn_idx);
-	} else {
-		dev->beacon_data_mask &= ~BIT(bcn_idx);
-		for (i = 0; i < beacon_len; i += 4)
-			mt76_wr(dev, beacon_addr + i, 0);
-	}
-
-	mt76_wr(dev, MT_BCN_BYPASS_MASK, 0xff00 | ~dev->beacon_data_mask);
-
-	return ret;
-}
-
-int mt76x2_mac_set_beacon(struct mt76x02_dev *dev, u8 vif_idx,
-			  struct sk_buff *skb)
-{
-	bool force_update = false;
-	int bcn_idx = 0;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(dev->beacons); i++) {
-		if (vif_idx == i) {
-			force_update = !!dev->beacons[i] ^ !!skb;
-
-			if (dev->beacons[i])
-				dev_kfree_skb(dev->beacons[i]);
-
-			dev->beacons[i] = skb;
-			__mt76x2_mac_set_beacon(dev, bcn_idx, skb);
-		} else if (force_update && dev->beacons[i]) {
-			__mt76x2_mac_set_beacon(dev, bcn_idx, dev->beacons[i]);
-		}
-
-		bcn_idx += !!dev->beacons[i];
-	}
-
-	for (i = bcn_idx; i < ARRAY_SIZE(dev->beacons); i++) {
-		if (!(dev->beacon_data_mask & BIT(i)))
-			break;
-
-		__mt76x2_mac_set_beacon(dev, i, NULL);
-	}
-
-	mt76_rmw_field(dev, MT_MAC_BSSID_DW1, MT_MAC_BSSID_DW1_MBEACON_N,
-		       bcn_idx - 1);
-	return 0;
-}
-
-void mt76x2_mac_set_beacon_enable(struct mt76x02_dev *dev,
-				  u8 vif_idx, bool val)
-{
-	u8 old_mask = dev->beacon_mask;
-	bool en;
-	u32 reg;
-
-	if (val) {
-		dev->beacon_mask |= BIT(vif_idx);
-	} else {
-		dev->beacon_mask &= ~BIT(vif_idx);
-		mt76x2_mac_set_beacon(dev, vif_idx, NULL);
-	}
-
-	if (!!old_mask == !!dev->beacon_mask)
-		return;
-
-	en = dev->beacon_mask;
-
-	mt76_rmw_field(dev, MT_INT_TIMER_EN, MT_INT_TIMER_EN_PRE_TBTT_EN, en);
-	reg = MT_BEACON_TIME_CFG_BEACON_TX |
-	      MT_BEACON_TIME_CFG_TBTT_EN |
-	      MT_BEACON_TIME_CFG_TIMER_EN;
-	mt76_rmw(dev, MT_BEACON_TIME_CFG, reg, reg * en);
-
-	if (en)
-		mt76x02_irq_enable(dev, MT_INT_PRE_TBTT | MT_INT_TBTT);
-	else
-		mt76x02_irq_disable(dev, MT_INT_PRE_TBTT | MT_INT_TBTT);
-}
-
 void mt76x2_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val)
 {
 	u32 data = 0;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
index 034a06295668..1b3b9594c2a2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
@@ -137,7 +137,7 @@ mt76x2_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	mutex_lock(&dev->mt76.mutex);
 
 	if (changed & BSS_CHANGED_BSSID)
-		mt76x2_mac_set_bssid(dev, mvif->idx, info->bssid);
+		mt76x02_mac_set_bssid(dev, mvif->idx, info->bssid);
 
 	if (changed & BSS_CHANGED_BEACON_INT) {
 		mt76_rmw_field(dev, MT_BEACON_TIME_CFG,
@@ -149,8 +149,8 @@ mt76x2_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	if (changed & BSS_CHANGED_BEACON_ENABLED) {
 		tasklet_disable(&dev->pre_tbtt_tasklet);
-		mt76x2_mac_set_beacon_enable(dev, mvif->idx,
-					     info->enable_beacon);
+		mt76x02_mac_set_beacon_enable(dev, mvif->idx,
+					      info->enable_beacon);
 		tasklet_enable(&dev->pre_tbtt_tasklet);
 	}
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_tx.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_tx.c
index 3a2ec86d3e88..fac38cbaa41b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_tx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_tx.c
@@ -36,7 +36,7 @@ mt76x2_update_beacon_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
 	if (!skb)
 		return;
 
-	mt76x2_mac_set_beacon(dev, mvif->idx, skb);
+	mt76x02_mac_set_beacon(dev, mvif->idx, skb);
 }
 
 static void
-- 
cgit v1.2.3


From dfe6c80c92248e0c196fdb396b281d7c68f07458 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:13:26 +0200
Subject: mt76: move tx beacon routines in mt76x02-lib module

Move mt76x02_tx beacon utility routines in mt76x02_mmio.c
in order to be reused by mt76x0 driver adding AP support

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |   2 +
 drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c  | 125 ++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2/Makefile |   4 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h |   2 -
 .../net/wireless/mediatek/mt76/mt76x2/pci_init.c   |   2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_tx.c | 142 ---------------------
 6 files changed, 130 insertions(+), 147 deletions(-)
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2/pci_tx.c

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 1cd0f758587d..72343d329f81 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -148,6 +148,8 @@ int mt76x02_tx_prepare_skb(struct mt76_dev *mdev, void *txwi,
 			   struct mt76_wcid *wcid, struct ieee80211_sta *sta,
 			   u32 *tx_info);
 
+void mt76x02_pre_tbtt_tasklet(unsigned long arg);
+
 extern const u16 mt76x02_beacon_offsets[16];
 void mt76x02_set_beacon_offsets(struct mt76x02_dev *dev);
 void mt76x02_set_irq_mask(struct mt76x02_dev *dev, u32 clear, u32 set);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
index 784b76e08382..ab1c8c8ef15b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
@@ -21,6 +21,131 @@
 #include "mt76x02.h"
 #include "mt76x02_trace.h"
 
+struct beacon_bc_data {
+	struct mt76x02_dev *dev;
+	struct sk_buff_head q;
+	struct sk_buff *tail[8];
+};
+
+static void
+mt76x02_update_beacon_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
+{
+	struct mt76x02_dev *dev = (struct mt76x02_dev *)priv;
+	struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
+	struct sk_buff *skb = NULL;
+
+	if (!(dev->beacon_mask & BIT(mvif->idx)))
+		return;
+
+	skb = ieee80211_beacon_get(mt76_hw(dev), vif);
+	if (!skb)
+		return;
+
+	mt76x02_mac_set_beacon(dev, mvif->idx, skb);
+}
+
+static void
+mt76x02_add_buffered_bc(void *priv, u8 *mac, struct ieee80211_vif *vif)
+{
+	struct beacon_bc_data *data = priv;
+	struct mt76x02_dev *dev = data->dev;
+	struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
+	struct ieee80211_tx_info *info;
+	struct sk_buff *skb;
+
+	if (!(dev->beacon_mask & BIT(mvif->idx)))
+		return;
+
+	skb = ieee80211_get_buffered_bc(mt76_hw(dev), vif);
+	if (!skb)
+		return;
+
+	info = IEEE80211_SKB_CB(skb);
+	info->control.vif = vif;
+	info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ;
+	mt76_skb_set_moredata(skb, true);
+	__skb_queue_tail(&data->q, skb);
+	data->tail[mvif->idx] = skb;
+}
+
+static void
+mt76x02_resync_beacon_timer(struct mt76x02_dev *dev)
+{
+	u32 timer_val = dev->beacon_int << 4;
+
+	dev->tbtt_count++;
+
+	/*
+	 * Beacon timer drifts by 1us every tick, the timer is configured
+	 * in 1/16 TU (64us) units.
+	 */
+	if (dev->tbtt_count < 62)
+		return;
+
+	if (dev->tbtt_count >= 64) {
+		dev->tbtt_count = 0;
+		return;
+	}
+
+	/*
+	 * The updated beacon interval takes effect after two TBTT, because
+	 * at this point the original interval has already been loaded into
+	 * the next TBTT_TIMER value
+	 */
+	if (dev->tbtt_count == 62)
+		timer_val -= 1;
+
+	mt76_rmw_field(dev, MT_BEACON_TIME_CFG,
+		       MT_BEACON_TIME_CFG_INTVAL, timer_val);
+}
+
+void mt76x02_pre_tbtt_tasklet(unsigned long arg)
+{
+	struct mt76x02_dev *dev = (struct mt76x02_dev *)arg;
+	struct mt76_queue *q = &dev->mt76.q_tx[MT_TXQ_PSD];
+	struct beacon_bc_data data = {};
+	struct sk_buff *skb;
+	int i, nframes;
+
+	mt76x02_resync_beacon_timer(dev);
+
+	data.dev = dev;
+	__skb_queue_head_init(&data.q);
+
+	ieee80211_iterate_active_interfaces_atomic(mt76_hw(dev),
+		IEEE80211_IFACE_ITER_RESUME_ALL,
+		mt76x02_update_beacon_iter, dev);
+
+	do {
+		nframes = skb_queue_len(&data.q);
+		ieee80211_iterate_active_interfaces_atomic(mt76_hw(dev),
+			IEEE80211_IFACE_ITER_RESUME_ALL,
+			mt76x02_add_buffered_bc, &data);
+	} while (nframes != skb_queue_len(&data.q));
+
+	if (!nframes)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(data.tail); i++) {
+		if (!data.tail[i])
+			continue;
+
+		mt76_skb_set_moredata(data.tail[i], false);
+	}
+
+	spin_lock_bh(&q->lock);
+	while ((skb = __skb_dequeue(&data.q)) != NULL) {
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+		struct ieee80211_vif *vif = info->control.vif;
+		struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
+
+		mt76_dma_tx_queue_skb(&dev->mt76, q, skb, &mvif->group_wcid,
+				      NULL);
+	}
+	spin_unlock_bh(&q->lock);
+}
+EXPORT_SYMBOL_GPL(mt76x02_pre_tbtt_tasklet);
+
 static int
 mt76x02_init_tx_queue(struct mt76x02_dev *dev, struct mt76_queue *q,
 		      int idx, int n_desc)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile b/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
index 696f071f47f8..cf8ef1a2f261 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
@@ -6,8 +6,8 @@ mt76x2-common-y := \
 	eeprom.o mac.o init.o phy.o mcu.o
 
 mt76x2e-y := \
-	pci.o pci_main.o pci_init.o pci_tx.o \
-	pci_mac.o pci_mcu.o pci_phy.o pci_dfs.o
+	pci.o pci_main.o pci_init.o pci_mac.o \
+	pci_mcu.o pci_phy.o pci_dfs.o
 
 mt76x2u-y := \
 	usb.o usb_init.o usb_main.o usb_mac.o usb_mcu.o \
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index eaa44de14826..2bae70c63ab0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -77,8 +77,6 @@ void mt76x2_cleanup(struct mt76x02_dev *dev);
 
 void mt76x2_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val);
 
-void mt76x2_pre_tbtt_tasklet(unsigned long arg);
-
 void mt76x2_sta_ps(struct mt76_dev *dev, struct ieee80211_sta *sta, bool ps);
 
 void mt76x2_reset_wlan(struct mt76x02_dev *dev, bool enable);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 5c1531ae8b93..bc1dbdf5af20 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -298,7 +298,7 @@ int mt76x2_init_hardware(struct mt76x02_dev *dev)
 {
 	int ret;
 
-	tasklet_init(&dev->pre_tbtt_tasklet, mt76x2_pre_tbtt_tasklet,
+	tasklet_init(&dev->pre_tbtt_tasklet, mt76x02_pre_tbtt_tasklet,
 		     (unsigned long) dev);
 
 	mt76x02_dma_disable(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_tx.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_tx.c
deleted file mode 100644
index fac38cbaa41b..000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_tx.c
+++ /dev/null
@@ -1,142 +0,0 @@
-/*
- * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- */
-
-#include "mt76x2.h"
-
-struct beacon_bc_data {
-	struct mt76x02_dev *dev;
-	struct sk_buff_head q;
-	struct sk_buff *tail[8];
-};
-
-static void
-mt76x2_update_beacon_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
-{
-	struct mt76x02_dev *dev = (struct mt76x02_dev *) priv;
-	struct mt76x02_vif *mvif = (struct mt76x02_vif *) vif->drv_priv;
-	struct sk_buff *skb = NULL;
-
-	if (!(dev->beacon_mask & BIT(mvif->idx)))
-		return;
-
-	skb = ieee80211_beacon_get(mt76_hw(dev), vif);
-	if (!skb)
-		return;
-
-	mt76x02_mac_set_beacon(dev, mvif->idx, skb);
-}
-
-static void
-mt76x2_add_buffered_bc(void *priv, u8 *mac, struct ieee80211_vif *vif)
-{
-	struct beacon_bc_data *data = priv;
-	struct mt76x02_dev *dev = data->dev;
-	struct mt76x02_vif *mvif = (struct mt76x02_vif *) vif->drv_priv;
-	struct ieee80211_tx_info *info;
-	struct sk_buff *skb;
-
-	if (!(dev->beacon_mask & BIT(mvif->idx)))
-		return;
-
-	skb = ieee80211_get_buffered_bc(mt76_hw(dev), vif);
-	if (!skb)
-		return;
-
-	info = IEEE80211_SKB_CB(skb);
-	info->control.vif = vif;
-	info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ;
-	mt76_skb_set_moredata(skb, true);
-	__skb_queue_tail(&data->q, skb);
-	data->tail[mvif->idx] = skb;
-}
-
-static void
-mt76x2_resync_beacon_timer(struct mt76x02_dev *dev)
-{
-	u32 timer_val = dev->beacon_int << 4;
-
-	dev->tbtt_count++;
-
-	/*
-	 * Beacon timer drifts by 1us every tick, the timer is configured
-	 * in 1/16 TU (64us) units.
-	 */
-	if (dev->tbtt_count < 62)
-		return;
-
-	if (dev->tbtt_count >= 64) {
-		dev->tbtt_count = 0;
-		return;
-	}
-
-	/*
-	 * The updated beacon interval takes effect after two TBTT, because
-	 * at this point the original interval has already been loaded into
-	 * the next TBTT_TIMER value
-	 */
-	if (dev->tbtt_count == 62)
-		timer_val -= 1;
-
-	mt76_rmw_field(dev, MT_BEACON_TIME_CFG,
-		       MT_BEACON_TIME_CFG_INTVAL, timer_val);
-}
-
-void mt76x2_pre_tbtt_tasklet(unsigned long arg)
-{
-	struct mt76x02_dev *dev = (struct mt76x02_dev *) arg;
-	struct mt76_queue *q = &dev->mt76.q_tx[MT_TXQ_PSD];
-	struct beacon_bc_data data = {};
-	struct sk_buff *skb;
-	int i, nframes;
-
-	mt76x2_resync_beacon_timer(dev);
-
-	data.dev = dev;
-	__skb_queue_head_init(&data.q);
-
-	ieee80211_iterate_active_interfaces_atomic(mt76_hw(dev),
-		IEEE80211_IFACE_ITER_RESUME_ALL,
-		mt76x2_update_beacon_iter, dev);
-
-	do {
-		nframes = skb_queue_len(&data.q);
-		ieee80211_iterate_active_interfaces_atomic(mt76_hw(dev),
-			IEEE80211_IFACE_ITER_RESUME_ALL,
-			mt76x2_add_buffered_bc, &data);
-	} while (nframes != skb_queue_len(&data.q));
-
-	if (!nframes)
-		return;
-
-	for (i = 0; i < ARRAY_SIZE(data.tail); i++) {
-		if (!data.tail[i])
-			continue;
-
-		mt76_skb_set_moredata(data.tail[i], false);
-	}
-
-	spin_lock_bh(&q->lock);
-	while ((skb = __skb_dequeue(&data.q)) != NULL) {
-		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-		struct ieee80211_vif *vif = info->control.vif;
-		struct mt76x02_vif *mvif = (struct mt76x02_vif *) vif->drv_priv;
-
-		mt76_dma_tx_queue_skb(&dev->mt76, q, skb, &mvif->group_wcid,
-				      NULL);
-	}
-	spin_unlock_bh(&q->lock);
-}
-
-- 
cgit v1.2.3


From 82b5c239417a4abe16c46f5bb25383f6f2363921 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:13:27 +0200
Subject: mt76x0: pci: add pre_tbtt_tasklet support

Enable/disable pre_tbtt_tasklet in mt76x0 driver in order
to add AP support

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c     | 2 ++
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c      | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x02.h         | 2 --
 drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c    | 6 ++++--
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c | 3 ---
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index a61b23239cb2..da98382bdb5a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -22,6 +22,7 @@ mt76x0_set_channel(struct mt76x02_dev *dev, struct cfg80211_chan_def *chandef)
 	int ret;
 
 	cancel_delayed_work_sync(&dev->cal_work);
+	tasklet_disable(&dev->pre_tbtt_tasklet);
 
 	mt76_set_channel(&dev->mt76);
 	ret = mt76x0_phy_set_channel(dev, chandef);
@@ -30,6 +31,7 @@ mt76x0_set_channel(struct mt76x02_dev *dev, struct cfg80211_chan_def *chandef)
 	mt76_rr(dev, MT_CH_IDLE);
 	mt76_rr(dev, MT_CH_BUSY);
 
+	tasklet_enable(&dev->pre_tbtt_tasklet);
 	mt76_txq_schedule_all(&dev->mt76);
 
 	return ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 6e11b8c8e495..f15f9bf14900 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -187,6 +187,7 @@ error:
 static void mt76x0e_cleanup(struct mt76x02_dev *dev)
 {
 	clear_bit(MT76_STATE_INITIALIZED, &dev->mt76.state);
+	tasklet_disable(&dev->pre_tbtt_tasklet);
 	mt76x0_chip_onoff(dev, false, false);
 	mt76x0e_stop_hw(dev);
 	mt76x02_dma_cleanup(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 72343d329f81..1cd0f758587d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -148,8 +148,6 @@ int mt76x02_tx_prepare_skb(struct mt76_dev *mdev, void *txwi,
 			   struct mt76_wcid *wcid, struct ieee80211_sta *sta,
 			   u32 *tx_info);
 
-void mt76x02_pre_tbtt_tasklet(unsigned long arg);
-
 extern const u16 mt76x02_beacon_offsets[16];
 void mt76x02_set_beacon_offsets(struct mt76x02_dev *dev);
 void mt76x02_set_irq_mask(struct mt76x02_dev *dev, u32 clear, u32 set);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
index ab1c8c8ef15b..66315410aebe 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
@@ -99,7 +99,7 @@ mt76x02_resync_beacon_timer(struct mt76x02_dev *dev)
 		       MT_BEACON_TIME_CFG_INTVAL, timer_val);
 }
 
-void mt76x02_pre_tbtt_tasklet(unsigned long arg)
+static void mt76x02_pre_tbtt_tasklet(unsigned long arg)
 {
 	struct mt76x02_dev *dev = (struct mt76x02_dev *)arg;
 	struct mt76_queue *q = &dev->mt76.q_tx[MT_TXQ_PSD];
@@ -144,7 +144,6 @@ void mt76x02_pre_tbtt_tasklet(unsigned long arg)
 	}
 	spin_unlock_bh(&q->lock);
 }
-EXPORT_SYMBOL_GPL(mt76x02_pre_tbtt_tasklet);
 
 static int
 mt76x02_init_tx_queue(struct mt76x02_dev *dev, struct mt76_queue *q,
@@ -223,6 +222,9 @@ int mt76x02_dma_init(struct mt76x02_dev *dev)
 		return -ENOMEM;
 
 	tasklet_init(&dev->tx_tasklet, mt76x02_tx_tasklet, (unsigned long) dev);
+	tasklet_init(&dev->pre_tbtt_tasklet, mt76x02_pre_tbtt_tasklet,
+		     (unsigned long)dev);
+
 	kfifo_init(&dev->txstatus_fifo, status_fifo, fifo_size);
 
 	mt76_dma_attach(&dev->mt76);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index bc1dbdf5af20..c5d5fcbd9a55 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -298,9 +298,6 @@ int mt76x2_init_hardware(struct mt76x02_dev *dev)
 {
 	int ret;
 
-	tasklet_init(&dev->pre_tbtt_tasklet, mt76x02_pre_tbtt_tasklet,
-		     (unsigned long) dev);
-
 	mt76x02_dma_disable(dev);
 	mt76x2_reset_wlan(dev, true);
 	mt76x2_power_on(dev);
-- 
cgit v1.2.3


From c2756a1c41e4d6433e9e994d97bae88a0b6033cf Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:13:28 +0200
Subject: mt76: move mt76x02_sw_scan and mt76x02_sw_scan_complete in
 mt76x02-lib module

Move mt76x02_sw_scan and mt76x02_sw_scan_complete utility routines
in mt76x02_util.c in order to be reused by mt76x0 and mt76x2u drivers
and remove duplicated code

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c   | 18 -----------------
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  4 ----
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c    |  4 ++--
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c    |  4 ++--
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |  4 ++++
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c  | 22 +++++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt76x2/pci_main.c   | 23 ++--------------------
 .../net/wireless/mediatek/mt76/mt76x2/usb_main.c   | 21 ++------------------
 8 files changed, 34 insertions(+), 66 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index da98382bdb5a..5747d72bd13a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -127,24 +127,6 @@ void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL_GPL(mt76x0_bss_info_changed);
 
-void mt76x0_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		    const u8 *mac_addr)
-{
-	struct mt76x02_dev *dev = hw->priv;
-
-	set_bit(MT76_SCANNING, &dev->mt76.state);
-}
-EXPORT_SYMBOL_GPL(mt76x0_sw_scan);
-
-void mt76x0_sw_scan_complete(struct ieee80211_hw *hw,
-			     struct ieee80211_vif *vif)
-{
-	struct mt76x02_dev *dev = hw->priv;
-
-	clear_bit(MT76_SCANNING, &dev->mt76.state);
-}
-EXPORT_SYMBOL_GPL(mt76x0_sw_scan_complete);
-
 int mt76x0_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 {
 	struct mt76x02_dev *dev = hw->priv;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 9cdecb9bfc64..2f3abbe491c5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -65,10 +65,6 @@ int mt76x0_config(struct ieee80211_hw *hw, u32 changed);
 void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif,
 			     struct ieee80211_bss_conf *info, u32 changed);
-void mt76x0_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		    const u8 *mac_addr);
-void mt76x0_sw_scan_complete(struct ieee80211_hw *hw,
-			     struct ieee80211_vif *vif);
 int mt76x0_set_rts_threshold(struct ieee80211_hw *hw, u32 value);
 
 /* PHY */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index f15f9bf14900..7f506975c9b9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -80,8 +80,8 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.sta_remove = mt76x02_sta_remove,
 	.set_key = mt76x02_set_key,
 	.conf_tx = mt76x02_conf_tx,
-	.sw_scan_start = mt76x0_sw_scan,
-	.sw_scan_complete = mt76x0_sw_scan_complete,
+	.sw_scan_start = mt76x02_sw_scan,
+	.sw_scan_complete = mt76x02_sw_scan_complete,
 	.ampdu_action = mt76x02_ampdu_action,
 	.sta_rate_tbl_update = mt76x02_sta_rate_tbl_update,
 	.wake_tx_queue = mt76_wake_tx_queue,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 245eb4aa9764..8640ddf0e594 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -150,8 +150,8 @@ static const struct ieee80211_ops mt76x0u_ops = {
 	.sta_remove = mt76x02_sta_remove,
 	.set_key = mt76x02_set_key,
 	.conf_tx = mt76x02_conf_tx,
-	.sw_scan_start = mt76x0_sw_scan,
-	.sw_scan_complete = mt76x0_sw_scan_complete,
+	.sw_scan_start = mt76x02_sw_scan,
+	.sw_scan_complete = mt76x02_sw_scan_complete,
 	.ampdu_action = mt76x02_ampdu_action,
 	.sta_rate_tbl_update = mt76x02_sta_rate_tbl_update,
 	.set_rts_threshold = mt76x0_set_rts_threshold,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 1cd0f758587d..0890794c92d7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -147,6 +147,10 @@ int mt76x02_tx_prepare_skb(struct mt76_dev *mdev, void *txwi,
 			   struct sk_buff *skb, struct mt76_queue *q,
 			   struct mt76_wcid *wcid, struct ieee80211_sta *sta,
 			   u32 *tx_info);
+void mt76x02_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		     const u8 *mac);
+void mt76x02_sw_scan_complete(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif);
 
 extern const u16 mt76x02_beacon_offsets[16];
 void mt76x02_set_beacon_offsets(struct mt76x02_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 208c76d40afa..bbc2cab4ffdc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -486,6 +486,28 @@ void mt76x02_remove_hdr_pad(struct sk_buff *skb, int len)
 }
 EXPORT_SYMBOL_GPL(mt76x02_remove_hdr_pad);
 
+void mt76x02_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		     const u8 *mac)
+{
+	struct mt76x02_dev *dev = hw->priv;
+
+	if (mt76_is_mmio(dev))
+		tasklet_disable(&dev->pre_tbtt_tasklet);
+	set_bit(MT76_SCANNING, &dev->mt76.state);
+}
+EXPORT_SYMBOL_GPL(mt76x02_sw_scan);
+
+void mt76x02_sw_scan_complete(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif)
+{
+	struct mt76x02_dev *dev = hw->priv;
+
+	clear_bit(MT76_SCANNING, &dev->mt76.state);
+	if (mt76_is_mmio(dev))
+		tasklet_enable(&dev->pre_tbtt_tasklet);
+}
+EXPORT_SYMBOL_GPL(mt76x02_sw_scan_complete);
+
 const u16 mt76x02_beacon_offsets[16] = {
 	/* 1024 byte per beacon */
 	0xc000,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
index 1b3b9594c2a2..36042331e4b2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
@@ -175,25 +175,6 @@ mt76x2_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps)
 	mt76x02_mac_wcid_set_drop(dev, idx, ps);
 }
 
-static void
-mt76x2_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-	       const u8 *mac)
-{
-	struct mt76x02_dev *dev = hw->priv;
-
-	tasklet_disable(&dev->pre_tbtt_tasklet);
-	set_bit(MT76_SCANNING, &dev->mt76.state);
-}
-
-static void
-mt76x2_sw_scan_complete(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
-{
-	struct mt76x02_dev *dev = hw->priv;
-
-	clear_bit(MT76_SCANNING, &dev->mt76.state);
-	tasklet_enable(&dev->pre_tbtt_tasklet);
-}
-
 static void
 mt76x2_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	     u32 queues, bool drop)
@@ -292,8 +273,8 @@ const struct ieee80211_ops mt76x2_ops = {
 	.sta_remove = mt76x02_sta_remove,
 	.set_key = mt76x02_set_key,
 	.conf_tx = mt76x02_conf_tx,
-	.sw_scan_start = mt76x2_sw_scan,
-	.sw_scan_complete = mt76x2_sw_scan_complete,
+	.sw_scan_start = mt76x02_sw_scan,
+	.sw_scan_complete = mt76x02_sw_scan_complete,
 	.flush = mt76x2_flush,
 	.ampdu_action = mt76x02_ampdu_action,
 	.get_txpower = mt76x2_get_txpower,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
index 25c43175e6e5..5187a5f4832a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
@@ -143,23 +143,6 @@ mt76x2u_config(struct ieee80211_hw *hw, u32 changed)
 	return err;
 }
 
-static void
-mt76x2u_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		const u8 *mac)
-{
-	struct mt76x02_dev *dev = hw->priv;
-
-	set_bit(MT76_SCANNING, &dev->mt76.state);
-}
-
-static void
-mt76x2u_sw_scan_complete(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
-{
-	struct mt76x02_dev *dev = hw->priv;
-
-	clear_bit(MT76_SCANNING, &dev->mt76.state);
-}
-
 const struct ieee80211_ops mt76x2u_ops = {
 	.tx = mt76x02_tx,
 	.start = mt76x2u_start,
@@ -175,7 +158,7 @@ const struct ieee80211_ops mt76x2u_ops = {
 	.bss_info_changed = mt76x2u_bss_info_changed,
 	.configure_filter = mt76x02_configure_filter,
 	.conf_tx = mt76x02_conf_tx,
-	.sw_scan_start = mt76x2u_sw_scan,
-	.sw_scan_complete = mt76x2u_sw_scan_complete,
+	.sw_scan_start = mt76x02_sw_scan,
+	.sw_scan_complete = mt76x02_sw_scan_complete,
 	.sta_rate_tbl_update = mt76x02_sta_rate_tbl_update,
 };
-- 
cgit v1.2.3


From 1da0a411bece6f63e2110f6a69862db70aadcc5e Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:13:29 +0200
Subject: mt76: move mt76x02_get_txpower in mt76x02_util.c

Move mt76x02_get_txpower utility routine in mt76x02-lib module
in order to be reused by mt76x0 and mt76x2u drivers

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c      |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c      |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x02.h         |  2 ++
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c    | 18 ++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c | 15 +--------------
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c |  1 +
 6 files changed, 24 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 7f506975c9b9..4d4800d09da6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -86,6 +86,7 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.sta_rate_tbl_update = mt76x02_sta_rate_tbl_update,
 	.wake_tx_queue = mt76_wake_tx_queue,
 	.get_survey = mt76_get_survey,
+	.get_txpower = mt76x02_get_txpower,
 };
 
 static int mt76x0e_register_device(struct mt76x02_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 8640ddf0e594..2105e966f745 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -156,6 +156,7 @@ static const struct ieee80211_ops mt76x0u_ops = {
 	.sta_rate_tbl_update = mt76x02_sta_rate_tbl_update,
 	.set_rts_threshold = mt76x0_set_rts_threshold,
 	.wake_tx_queue = mt76_wake_tx_queue,
+	.get_txpower = mt76x02_get_txpower,
 };
 
 static int mt76x0u_register_device(struct mt76x02_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 0890794c92d7..f830e39b58e7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -151,6 +151,8 @@ void mt76x02_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		     const u8 *mac);
 void mt76x02_sw_scan_complete(struct ieee80211_hw *hw,
 			      struct ieee80211_vif *vif);
+int mt76x02_get_txpower(struct ieee80211_hw *hw,
+			struct ieee80211_vif *vif, int *dbm);
 
 extern const u16 mt76x02_beacon_offsets[16];
 void mt76x02_set_beacon_offsets(struct mt76x02_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index bbc2cab4ffdc..25f36e333b9b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -508,6 +508,24 @@ void mt76x02_sw_scan_complete(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL_GPL(mt76x02_sw_scan_complete);
 
+int mt76x02_get_txpower(struct ieee80211_hw *hw,
+			struct ieee80211_vif *vif, int *dbm)
+{
+	struct mt76x02_dev *dev = hw->priv;
+	u8 nstreams = dev->mt76.chainmask & 0xf;
+
+	*dbm = dev->mt76.txpower_cur / 2;
+
+	/* convert from per-chain power to combined
+	 * output on 2x2 devices
+	 */
+	if (nstreams > 1)
+		*dbm += 3;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x02_get_txpower);
+
 const u16 mt76x02_beacon_offsets[16] = {
 	/* 1024 byte per beacon */
 	0xc000,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
index 36042331e4b2..5dfd06e56636 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
@@ -181,19 +181,6 @@ mt76x2_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 }
 
-static int
-mt76x2_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int *dbm)
-{
-	struct mt76x02_dev *dev = hw->priv;
-
-	*dbm = dev->mt76.txpower_cur / 2;
-
-	/* convert from per-chain power to combined output on 2x2 devices */
-	*dbm += 3;
-
-	return 0;
-}
-
 static void mt76x2_set_coverage_class(struct ieee80211_hw *hw,
 				      s16 coverage_class)
 {
@@ -277,7 +264,7 @@ const struct ieee80211_ops mt76x2_ops = {
 	.sw_scan_complete = mt76x02_sw_scan_complete,
 	.flush = mt76x2_flush,
 	.ampdu_action = mt76x02_ampdu_action,
-	.get_txpower = mt76x2_get_txpower,
+	.get_txpower = mt76x02_get_txpower,
 	.wake_tx_queue = mt76_wake_tx_queue,
 	.sta_rate_tbl_update = mt76x02_sta_rate_tbl_update,
 	.release_buffered_frames = mt76_release_buffered_frames,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
index 5187a5f4832a..c2e0a43082e5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
@@ -161,4 +161,5 @@ const struct ieee80211_ops mt76x2u_ops = {
 	.sw_scan_start = mt76x02_sw_scan,
 	.sw_scan_complete = mt76x02_sw_scan_complete,
 	.sta_rate_tbl_update = mt76x02_sta_rate_tbl_update,
+	.get_txpower = mt76x02_get_txpower,
 };
-- 
cgit v1.2.3


From f7c8a0f2da379dae08075d6023d24b9accf2d1f9 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:13:30 +0200
Subject: mt76: move mt76x02_sta_ps in mt76x02-lib module

Move mt76x02_sta_ps utility routine in mt76x02_util.c
in order to be reused by mt76x0 driver adding AP support

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c      |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x02.h         |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c    | 12 ++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h   |  2 --
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c | 11 -----------
 6 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 4d4800d09da6..4deaf7f7c4f7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -142,6 +142,7 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		.tx_complete_skb = mt76x02_tx_complete_skb,
 		.rx_skb = mt76x02_queue_rx_skb,
 		.rx_poll_complete = mt76x02_rx_poll_complete,
+		.sta_ps = mt76x02_sta_ps,
 	};
 	struct mt76x02_dev *dev;
 	int ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index f830e39b58e7..1733226b657d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -153,6 +153,7 @@ void mt76x02_sw_scan_complete(struct ieee80211_hw *hw,
 			      struct ieee80211_vif *vif);
 int mt76x02_get_txpower(struct ieee80211_hw *hw,
 			struct ieee80211_vif *vif, int *dbm);
+void mt76x02_sta_ps(struct mt76_dev *dev, struct ieee80211_sta *sta, bool ps);
 
 extern const u16 mt76x02_beacon_offsets[16];
 void mt76x02_set_beacon_offsets(struct mt76x02_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 25f36e333b9b..4e358066bf9b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -526,6 +526,18 @@ int mt76x02_get_txpower(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL_GPL(mt76x02_get_txpower);
 
+void mt76x02_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta,
+		    bool ps)
+{
+	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
+	struct mt76x02_sta *msta = (struct mt76x02_sta *)sta->drv_priv;
+	int idx = msta->wcid.idx;
+
+	mt76_stop_tx_queues(&dev->mt76, sta, true);
+	mt76x02_mac_wcid_set_drop(dev, idx, ps);
+}
+EXPORT_SYMBOL_GPL(mt76x02_sta_ps);
+
 const u16 mt76x02_beacon_offsets[16] = {
 	/* 1024 byte per beacon */
 	0xc000,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index 2bae70c63ab0..0c323a0762e8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -77,8 +77,6 @@ void mt76x2_cleanup(struct mt76x02_dev *dev);
 
 void mt76x2_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val);
 
-void mt76x2_sta_ps(struct mt76_dev *dev, struct ieee80211_sta *sta, bool ps);
-
 void mt76x2_reset_wlan(struct mt76x02_dev *dev, bool enable);
 void mt76x2_init_txpower(struct mt76x02_dev *dev,
 			 struct ieee80211_supported_band *sband);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index c5d5fcbd9a55..c3c2f4441777 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -356,7 +356,7 @@ struct mt76x02_dev *mt76x2_alloc_device(struct device *pdev)
 		.tx_complete_skb = mt76x02_tx_complete_skb,
 		.rx_skb = mt76x02_queue_rx_skb,
 		.rx_poll_complete = mt76x02_rx_poll_complete,
-		.sta_ps = mt76x2_sta_ps,
+		.sta_ps = mt76x02_sta_ps,
 	};
 	struct mt76x02_dev *dev;
 	struct mt76_dev *mdev;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
index 5dfd06e56636..b2c599d4d670 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
@@ -164,17 +164,6 @@ mt76x2_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	mutex_unlock(&dev->mt76.mutex);
 }
 
-void
-mt76x2_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps)
-{
-	struct mt76x02_sta *msta = (struct mt76x02_sta *) sta->drv_priv;
-	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
-	int idx = msta->wcid.idx;
-
-	mt76_stop_tx_queues(&dev->mt76, sta, true);
-	mt76x02_mac_wcid_set_drop(dev, idx, ps);
-}
-
 static void
 mt76x2_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	     u32 queues, bool drop)
-- 
cgit v1.2.3


From fc245983a8a8cc82046cfb83e327b991aefabaf7 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:13:31 +0200
Subject: mt76: introduce mt76x02_init_beacon_config routine

Add mt76x02_init_beacon_config utility routine in mt76x02-lib
module in order to be reused by mt76x0 driver configuring
BSSID registers and remove duplicated code

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c   |  8 +-----
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c  | 30 ++++++++++++++++++++--
 .../net/wireless/mediatek/mt76/mt76x2/pci_init.c   | 19 +-------------
 4 files changed, 31 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index 95a015281697..64eb6f451541 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -135,8 +135,6 @@ static void mt76x0_init_mac_registers(struct mt76x02_dev *dev)
 {
 	RANDOM_WRITE(dev, common_mac_reg_table);
 
-	mt76x02_set_beacon_offsets(dev);
-
 	/* Enable PBF and MAC clock SYS_CTRL[11:10] = 0x3 */
 	RANDOM_WRITE(dev, mt76x0_mac_reg_table);
 
@@ -297,11 +295,6 @@ int mt76x0_init_hardware(struct mt76x02_dev *dev)
 	if (ret)
 		return ret;
 
-	mt76_clear(dev, MT_BEACON_TIME_CFG, (MT_BEACON_TIME_CFG_TIMER_EN |
-					     MT_BEACON_TIME_CFG_SYNC_MODE |
-					     MT_BEACON_TIME_CFG_TBTT_EN |
-					     MT_BEACON_TIME_CFG_BEACON_TX));
-
 	mt76x0_reset_counters(dev);
 
 	ret = mt76x0_eeprom_init(dev);
@@ -309,6 +302,7 @@ int mt76x0_init_hardware(struct mt76x02_dev *dev)
 		return ret;
 
 	mt76x0_phy_init(dev);
+	mt76x02_init_beacon_config(dev);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 1733226b657d..a4141265d7a9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -156,7 +156,7 @@ int mt76x02_get_txpower(struct ieee80211_hw *hw,
 void mt76x02_sta_ps(struct mt76_dev *dev, struct ieee80211_sta *sta, bool ps);
 
 extern const u16 mt76x02_beacon_offsets[16];
-void mt76x02_set_beacon_offsets(struct mt76x02_dev *dev);
+void mt76x02_init_beacon_config(struct mt76x02_dev *dev);
 void mt76x02_set_irq_mask(struct mt76x02_dev *dev, u32 clear, u32 set);
 void mt76x02_mac_start(struct mt76x02_dev *dev);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 4e358066bf9b..2a81d2fc5d4d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -560,7 +560,7 @@ const u16 mt76x02_beacon_offsets[16] = {
 };
 EXPORT_SYMBOL_GPL(mt76x02_beacon_offsets);
 
-void mt76x02_set_beacon_offsets(struct mt76x02_dev *dev)
+static void mt76x02_set_beacon_offsets(struct mt76x02_dev *dev)
 {
 	u16 val, base = MT_BEACON_BASE;
 	u32 regs[4] = {};
@@ -574,6 +574,32 @@ void mt76x02_set_beacon_offsets(struct mt76x02_dev *dev)
 	for (i = 0; i < 4; i++)
 		mt76_wr(dev, MT_BCN_OFFSET(i), regs[i]);
 }
-EXPORT_SYMBOL_GPL(mt76x02_set_beacon_offsets);
+
+void mt76x02_init_beacon_config(struct mt76x02_dev *dev)
+{
+	static const u8 null_addr[ETH_ALEN] = {};
+	int i;
+
+	mt76_wr(dev, MT_MAC_BSSID_DW0,
+		get_unaligned_le32(dev->mt76.macaddr));
+	mt76_wr(dev, MT_MAC_BSSID_DW1,
+		get_unaligned_le16(dev->mt76.macaddr + 4) |
+		FIELD_PREP(MT_MAC_BSSID_DW1_MBSS_MODE, 3) | /* 8 beacons */
+		MT_MAC_BSSID_DW1_MBSS_LOCAL_BIT);
+
+	/* Fire a pre-TBTT interrupt 8 ms before TBTT */
+	mt76_rmw_field(dev, MT_INT_TIMER_CFG, MT_INT_TIMER_CFG_PRE_TBTT,
+		       8 << 4);
+	mt76_wr(dev, MT_INT_TIMER_EN, 0);
+
+	mt76_wr(dev, MT_BCN_BYPASS_MASK, 0xffff);
+
+	for (i = 0; i < 8; i++) {
+		mt76x02_mac_set_bssid(dev, i, null_addr);
+		mt76x02_mac_set_beacon(dev, i, NULL);
+	}
+	mt76x02_set_beacon_offsets(dev);
+}
+EXPORT_SYMBOL_GPL(mt76x02_init_beacon_config);
 
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index c3c2f4441777..f561f5916625 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -79,7 +79,6 @@ mt76x2_fixup_xtal(struct mt76x02_dev *dev)
 
 static int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard)
 {
-	static const u8 null_addr[ETH_ALEN] = {};
 	const u8 *macaddr = dev->mt76.macaddr;
 	u32 val;
 	int i, k;
@@ -123,19 +122,10 @@ static int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard)
 	mt76_wr(dev, MT_MAC_ADDR_DW0, get_unaligned_le32(macaddr));
 	mt76_wr(dev, MT_MAC_ADDR_DW1, get_unaligned_le16(macaddr + 4));
 
-	mt76_wr(dev, MT_MAC_BSSID_DW0, get_unaligned_le32(macaddr));
-	mt76_wr(dev, MT_MAC_BSSID_DW1, get_unaligned_le16(macaddr + 4) |
-		FIELD_PREP(MT_MAC_BSSID_DW1_MBSS_MODE, 3) | /* 8 beacons */
-		MT_MAC_BSSID_DW1_MBSS_LOCAL_BIT);
-
-	/* Fire a pre-TBTT interrupt 8 ms before TBTT */
-	mt76_rmw_field(dev, MT_INT_TIMER_CFG, MT_INT_TIMER_CFG_PRE_TBTT,
-		       8 << 4);
 	mt76_rmw_field(dev, MT_INT_TIMER_CFG, MT_INT_TIMER_CFG_GP_TIMER,
 		       MT_DFS_GP_INTERVAL);
-	mt76_wr(dev, MT_INT_TIMER_EN, 0);
 
-	mt76_wr(dev, MT_BCN_BYPASS_MASK, 0xffff);
+	mt76x02_init_beacon_config(dev);
 	if (!hard)
 		return 0;
 
@@ -152,11 +142,6 @@ static int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard)
 		for (k = 0; k < 4; k++)
 			mt76x02_mac_shared_key_setup(dev, i, k, NULL);
 
-	for (i = 0; i < 8; i++) {
-		mt76x02_mac_set_bssid(dev, i, null_addr);
-		mt76x02_mac_set_beacon(dev, i, NULL);
-	}
-
 	for (i = 0; i < 16; i++)
 		mt76_rr(dev, MT_TX_STAT_FIFO);
 
@@ -168,8 +153,6 @@ static int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard)
 		MT_CH_TIME_CFG_EIFS_AS_BUSY |
 		FIELD_PREP(MT_CH_TIME_CFG_CH_TIMER_CLR, 1));
 
-	mt76x02_set_beacon_offsets(dev);
-
 	mt76x2_set_tx_ackto(dev);
 
 	return 0;
-- 
cgit v1.2.3


From 4cb23b650a59b042f647d09d16d527d026b2d2f2 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:13:32 +0200
Subject: mt76x0: pci: enable AP support

Add missing mac80211 callbacks to mt76x0e_ops data structure
and add mt76x02_beacon utility routines in mt76x0_bss_info_changed
in order to enable/disable beacon transmission

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c    | 20 --------------
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c   | 32 ++++++++++------------
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  2 --
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c    | 17 ++++++++++++
 4 files changed, 32 insertions(+), 39 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
index ded0ad623723..78d15cb006e0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
@@ -75,23 +75,3 @@ void mt76x0_mac_set_protection(struct mt76x02_dev *dev, bool legacy_prot,
 	for (i = 0; i < 6; i++)
 		mt76_wr(dev, MT_CCK_PROT_CFG + i * 4, prot[i]);
 }
-
-void mt76x0_mac_config_tsf(struct mt76x02_dev *dev, bool enable, int interval)
-{
-	u32 val = mt76_rr(dev, MT_BEACON_TIME_CFG);
-
-	val &= ~(MT_BEACON_TIME_CFG_TIMER_EN |
-		 MT_BEACON_TIME_CFG_SYNC_MODE |
-		 MT_BEACON_TIME_CFG_TBTT_EN);
-
-	if (!enable) {
-		mt76_wr(dev, MT_BEACON_TIME_CFG, val);
-		return;
-	}
-
-	val &= ~MT_BEACON_TIME_CFG_INTVAL;
-	val |= FIELD_PREP(MT_BEACON_TIME_CFG_INTVAL, interval << 4) |
-		MT_BEACON_TIME_CFG_TIMER_EN |
-		MT_BEACON_TIME_CFG_SYNC_MODE |
-		MT_BEACON_TIME_CFG_TBTT_EN;
-}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index 5747d72bd13a..3dff198bbccd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -72,30 +72,23 @@ int mt76x0_config(struct ieee80211_hw *hw, u32 changed)
 }
 EXPORT_SYMBOL_GPL(mt76x0_config);
 
-static void
-mt76x0_addr_wr(struct mt76x02_dev *dev, const u32 offset, const u8 *addr)
-{
-	mt76_wr(dev, offset, get_unaligned_le32(addr));
-	mt76_wr(dev, offset + 4, addr[4] | addr[5] << 8);
-}
-
 void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif,
 			     struct ieee80211_bss_conf *info, u32 changed)
 {
+	struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
 	struct mt76x02_dev *dev = hw->priv;
 
 	mutex_lock(&dev->mt76.mutex);
 
-	if (changed & BSS_CHANGED_BSSID) {
-		mt76x0_addr_wr(dev, MT_MAC_BSSID_DW0, info->bssid);
+	if (changed & BSS_CHANGED_BSSID)
+		mt76x02_mac_set_bssid(dev, mvif->idx, info->bssid);
 
-		/* Note: this is a hack because beacon_int is not changed
-		 *	 on leave nor is any more appropriate event generated.
-		 *	 rt2x00 doesn't seem to be bothered though.
-		 */
-		if (is_zero_ether_addr(info->bssid))
-			mt76x0_mac_config_tsf(dev, false, 0);
+	if (changed & BSS_CHANGED_BEACON_ENABLED) {
+		tasklet_disable(&dev->pre_tbtt_tasklet);
+		mt76x02_mac_set_beacon_enable(dev, mvif->idx,
+					      info->enable_beacon);
+		tasklet_enable(&dev->pre_tbtt_tasklet);
 	}
 
 	if (changed & BSS_CHANGED_BASIC_RATES) {
@@ -106,8 +99,13 @@ void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
 		mt76_wr(dev, MT_LG_FBK_CFG1, 0x00002100);
 	}
 
-	if (changed & BSS_CHANGED_BEACON_INT)
-		mt76x0_mac_config_tsf(dev, true, info->beacon_int);
+	if (changed & BSS_CHANGED_BEACON_INT) {
+		mt76_rmw_field(dev, MT_BEACON_TIME_CFG,
+			       MT_BEACON_TIME_CFG_INTVAL,
+			       info->beacon_int << 4);
+		dev->beacon_int = info->beacon_int;
+		dev->tbtt_count = 0;
+	}
 
 	if (changed & BSS_CHANGED_HT || changed & BSS_CHANGED_ERP_CTS_PROT)
 		mt76x0_mac_set_protection(dev, info->use_cts_prot,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 2f3abbe491c5..5b4f30225dc1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -78,6 +78,4 @@ void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on);
 /* MAC */
 void mt76x0_mac_set_protection(struct mt76x02_dev *dev, bool legacy_prot,
 				int ht_mode);
-void mt76x0_mac_config_tsf(struct mt76x02_dev *dev, bool enable, int interval);
-
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 4deaf7f7c4f7..08412bbf7dcb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -68,6 +68,19 @@ static void mt76x0e_stop(struct ieee80211_hw *hw)
 	mutex_unlock(&dev->mt76.mutex);
 }
 
+static void
+mt76x0e_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+	      u32 queues, bool drop)
+{
+}
+
+static int
+mt76x0e_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
+		bool set)
+{
+	return 0;
+}
+
 static const struct ieee80211_ops mt76x0e_ops = {
 	.tx = mt76x02_tx,
 	.start = mt76x0e_start,
@@ -76,6 +89,7 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.remove_interface = mt76x02_remove_interface,
 	.config = mt76x0_config,
 	.configure_filter = mt76x02_configure_filter,
+	.bss_info_changed = mt76x0_bss_info_changed,
 	.sta_add = mt76x02_sta_add,
 	.sta_remove = mt76x02_sta_remove,
 	.set_key = mt76x02_set_key,
@@ -87,6 +101,9 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.wake_tx_queue = mt76_wake_tx_queue,
 	.get_survey = mt76_get_survey,
 	.get_txpower = mt76x02_get_txpower,
+	.flush = mt76x0e_flush,
+	.set_tim = mt76x0e_set_tim,
+	.release_buffered_frames = mt76_release_buffered_frames,
 };
 
 static int mt76x0e_register_device(struct mt76x02_dev *dev)
-- 
cgit v1.2.3


From 3670405193e2e7c1834244f44a3008149fca5059 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:40:52 +0200
Subject: mt76: move mt76x02_set_tx_ackto in mt76x02-lib module

Move mt76x02_set_tx_ackto and mt76x02_set_coverage_class routines
in mt76x02-lib module in order to be reused by mt76x0 driver.
This is a preliminary patch to unify drv_bss_info_changed mac80211
callback between mt76x0 and mt76x2 drivers

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c   |  4 +--
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c    |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |  3 +++
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c  | 30 ++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h |  1 -
 .../net/wireless/mediatek/mt76/mt76x2/pci_init.c   | 19 +-------------
 .../net/wireless/mediatek/mt76/mt76x2/pci_main.c   | 15 ++---------
 7 files changed, 39 insertions(+), 34 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index 3dff198bbccd..8de19fe534a3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -117,8 +117,8 @@ void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
 	if (changed & BSS_CHANGED_ERP_SLOT) {
 		int slottime = info->use_short_slot ? 9 : 20;
 
-		mt76_rmw_field(dev, MT_BKOFF_SLOT_CFG,
-			       MT_BKOFF_SLOT_CFG_SLOTTIME, slottime);
+		dev->slottime = slottime;
+		mt76x02_set_tx_ackto(dev);
 	}
 
 	mutex_unlock(&dev->mt76.mutex);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 08412bbf7dcb..b16227fdbdc4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -104,6 +104,7 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.flush = mt76x0e_flush,
 	.set_tim = mt76x0e_set_tim,
 	.release_buffered_frames = mt76_release_buffered_frames,
+	.set_coverage_class = mt76x02_set_coverage_class,
 };
 
 static int mt76x0e_register_device(struct mt76x02_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index a4141265d7a9..95af2b1c7eed 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -133,6 +133,9 @@ s8 mt76x02_tx_get_max_txpwr_adj(struct mt76x02_dev *dev,
 s8 mt76x02_tx_get_txpwr_adj(struct mt76x02_dev *dev, s8 txpwr,
 			    s8 max_txpwr_adj);
 void mt76x02_tx_set_txpwr_auto(struct mt76x02_dev *dev, s8 txpwr);
+void mt76x02_set_tx_ackto(struct mt76x02_dev *dev);
+void mt76x02_set_coverage_class(struct ieee80211_hw *hw,
+				s16 coverage_class);
 int mt76x02_insert_hdr_pad(struct sk_buff *skb);
 void mt76x02_remove_hdr_pad(struct sk_buff *skb, int len);
 void mt76x02_tx_complete(struct mt76_dev *dev, struct sk_buff *skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 2a81d2fc5d4d..c485f6600ae9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -438,6 +438,36 @@ int mt76x02_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 }
 EXPORT_SYMBOL_GPL(mt76x02_conf_tx);
 
+void mt76x02_set_tx_ackto(struct mt76x02_dev *dev)
+{
+	u8 ackto, sifs, slottime = dev->slottime;
+
+	/* As defined by IEEE 802.11-2007 17.3.8.6 */
+	slottime += 3 * dev->coverage_class;
+	mt76_rmw_field(dev, MT_BKOFF_SLOT_CFG,
+		       MT_BKOFF_SLOT_CFG_SLOTTIME, slottime);
+
+	sifs = mt76_get_field(dev, MT_XIFS_TIME_CFG,
+			      MT_XIFS_TIME_CFG_OFDM_SIFS);
+
+	ackto = slottime + sifs;
+	mt76_rmw_field(dev, MT_TX_TIMEOUT_CFG,
+		       MT_TX_TIMEOUT_CFG_ACKTO, ackto);
+}
+EXPORT_SYMBOL_GPL(mt76x02_set_tx_ackto);
+
+void mt76x02_set_coverage_class(struct ieee80211_hw *hw,
+				s16 coverage_class)
+{
+	struct mt76x02_dev *dev = hw->priv;
+
+	mutex_lock(&dev->mt76.mutex);
+	dev->coverage_class = coverage_class;
+	mt76x02_set_tx_ackto(dev);
+	mutex_unlock(&dev->mt76.mutex);
+}
+EXPORT_SYMBOL_GPL(mt76x02_set_coverage_class);
+
 void mt76x02_sta_rate_tbl_update(struct ieee80211_hw *hw,
 				struct ieee80211_vif *vif,
 				struct ieee80211_sta *sta)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index 0c323a0762e8..3f0b9c78625d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -58,7 +58,6 @@ int mt76x2_init_hardware(struct mt76x02_dev *dev);
 void mt76x2_stop_hardware(struct mt76x02_dev *dev);
 int mt76x2_eeprom_init(struct mt76x02_dev *dev);
 int mt76x2_apply_calibration_data(struct mt76x02_dev *dev, int channel);
-void mt76x2_set_tx_ackto(struct mt76x02_dev *dev);
 
 void mt76x2_phy_set_antenna(struct mt76x02_dev *dev);
 int mt76x2_phy_start(struct mt76x02_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index f561f5916625..41c0cb62a919 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -153,7 +153,7 @@ static int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard)
 		MT_CH_TIME_CFG_EIFS_AS_BUSY |
 		FIELD_PREP(MT_CH_TIME_CFG_CH_TIMER_CLR, 1));
 
-	mt76x2_set_tx_ackto(dev);
+	mt76x02_set_tx_ackto(dev);
 
 	return 0;
 }
@@ -260,23 +260,6 @@ mt76x2_power_on(struct mt76x02_dev *dev)
 	mt76x2_power_on_rf(dev, 1);
 }
 
-void mt76x2_set_tx_ackto(struct mt76x02_dev *dev)
-{
-	u8 ackto, sifs, slottime = dev->slottime;
-
-	/* As defined by IEEE 802.11-2007 17.3.8.6 */
-	slottime += 3 * dev->coverage_class;
-	mt76_rmw_field(dev, MT_BKOFF_SLOT_CFG,
-		       MT_BKOFF_SLOT_CFG_SLOTTIME, slottime);
-
-	sifs = mt76_get_field(dev, MT_XIFS_TIME_CFG,
-			      MT_XIFS_TIME_CFG_OFDM_SIFS);
-
-	ackto = slottime + sifs;
-	mt76_rmw_field(dev, MT_TX_TIMEOUT_CFG,
-		       MT_TX_TIMEOUT_CFG_ACKTO, ackto);
-}
-
 int mt76x2_init_hardware(struct mt76x02_dev *dev)
 {
 	int ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
index b2c599d4d670..f984bb0f9aa1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
@@ -158,7 +158,7 @@ mt76x2_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		int slottime = info->use_short_slot ? 9 : 20;
 
 		dev->slottime = slottime;
-		mt76x2_set_tx_ackto(dev);
+		mt76x02_set_tx_ackto(dev);
 	}
 
 	mutex_unlock(&dev->mt76.mutex);
@@ -170,17 +170,6 @@ mt76x2_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 }
 
-static void mt76x2_set_coverage_class(struct ieee80211_hw *hw,
-				      s16 coverage_class)
-{
-	struct mt76x02_dev *dev = hw->priv;
-
-	mutex_lock(&dev->mt76.mutex);
-	dev->coverage_class = coverage_class;
-	mt76x2_set_tx_ackto(dev);
-	mutex_unlock(&dev->mt76.mutex);
-}
-
 static int
 mt76x2_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta, bool set)
 {
@@ -257,7 +246,7 @@ const struct ieee80211_ops mt76x2_ops = {
 	.wake_tx_queue = mt76_wake_tx_queue,
 	.sta_rate_tbl_update = mt76x02_sta_rate_tbl_update,
 	.release_buffered_frames = mt76_release_buffered_frames,
-	.set_coverage_class = mt76x2_set_coverage_class,
+	.set_coverage_class = mt76x02_set_coverage_class,
 	.get_survey = mt76_get_survey,
 	.set_tim = mt76x2_set_tim,
 	.set_antenna = mt76x2_set_antenna,
-- 
cgit v1.2.3


From 13ed9d4ae5b3dc5775bba41d228e3bded0b84dec Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:40:53 +0200
Subject: mt76x0: update init vals for MT_TX_PROT registers

Add missing VHT MT_TX_PROT register init values

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
index 236dce6860b4..a1657922758e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
@@ -37,14 +37,14 @@ static const struct mt76_reg_pair common_mac_reg_table[] = {
 	{ MT_PBF_RX_MAX_PCNT,		0x0000fe9f },
 	{ MT_TX_RETRY_CFG,		0x47d01f0f },
 	{ MT_AUTO_RSP_CFG,		0x00000013 },
-	{ MT_CCK_PROT_CFG,		0x05740003 },
-	{ MT_OFDM_PROT_CFG,		0x05740003 },
+	{ MT_CCK_PROT_CFG,		0x07f40003 },
+	{ MT_OFDM_PROT_CFG,		0x07f42004 },
 	{ MT_PBF_CFG,			0x00f40006 },
 	{ MT_WPDMA_GLO_CFG,		0x00000030 },
-	{ MT_GF20_PROT_CFG,		0x01744004 },
-	{ MT_GF40_PROT_CFG,		0x03f44084 },
-	{ MT_MM20_PROT_CFG,		0x01744004 },
-	{ MT_MM40_PROT_CFG,		0x03f54084 },
+	{ MT_GF20_PROT_CFG,		0x01742004 },
+	{ MT_GF40_PROT_CFG,		0x03f42084 },
+	{ MT_MM20_PROT_CFG,		0x01742004 },
+	{ MT_MM40_PROT_CFG,		0x03f42084 },
 	{ MT_TXOP_CTRL_CFG,		0x0000583f },
 	{ MT_TX_RTS_CFG,		0x00092b20 },
 	{ MT_EXP_ACK_TIME,		0x002400ca },
@@ -85,6 +85,9 @@ static const struct mt76_reg_pair mt76x0_mac_reg_table[] = {
 	{ MT_HT_CTRL_CFG,		0x000001FF },
 	{ MT_TXOP_HLDR_ET,		0x00000000 },
 	{ MT_PN_PAD_MODE,		0x00000003 },
+	{ MT_TX_PROT_CFG6,		0xe3f42004 },
+	{ MT_TX_PROT_CFG7,		0xe3f42084 },
+	{ MT_TX_PROT_CFG8,		0xe3f42104 },
 };
 
 static const struct mt76_reg_pair mt76x0_bbp_init_tab[] = {
-- 
cgit v1.2.3


From 317ed42b701b088013fb8c909c10ca7f44bdf2b3 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:40:54 +0200
Subject: mt76: move tx protection routines in mt76x02-lib module

Move mt76x02_set_rts_threshold and mt76x02_mac_set_tx_protection
routines in mt76x02-lib module and remove duplicated code in mt76x0
and mt76x2 drivers. Remove pci_mac.c and mt76x0/mac.c since now are
empty files

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/Makefile |  3 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c    | 77 ----------------------
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c   | 14 ----
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  5 --
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c    |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c   | 30 +++++++++
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.h   |  4 +-
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c  | 15 +++++
 drivers/net/wireless/mediatek/mt76/mt76x2/Makefile |  4 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h |  2 -
 .../net/wireless/mediatek/mt76/mt76x2/pci_mac.c    | 50 --------------
 .../net/wireless/mediatek/mt76/mt76x2/pci_main.c   | 17 +----
 14 files changed, 54 insertions(+), 171 deletions(-)
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile b/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
index 1b4f2fa99317..aa22ba954716 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
@@ -2,8 +2,7 @@ obj-$(CONFIG_MT76x0U) += mt76x0u.o
 obj-$(CONFIG_MT76x0E) += mt76x0e.o
 obj-$(CONFIG_MT76x0_COMMON) += mt76x0-common.o
 
-mt76x0-common-y := \
-	init.o main.o eeprom.o phy.o mac.o
+mt76x0-common-y := init.o main.o eeprom.o phy.o
 
 mt76x0u-y := usb.o usb_mcu.o
 mt76x0e-y := pci.o pci_mcu.o
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
deleted file mode 100644
index 78d15cb006e0..000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
- * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/etherdevice.h>
-
-#include "mt76x0.h"
-
-void mt76x0_mac_set_protection(struct mt76x02_dev *dev, bool legacy_prot,
-			       int ht_mode)
-{
-	int mode = ht_mode & IEEE80211_HT_OP_MODE_PROTECTION;
-	bool non_gf = !!(ht_mode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT);
-	u32 prot[6];
-	bool ht_rts[4] = {};
-	int i;
-
-	prot[0] = MT_PROT_NAV_SHORT |
-		  MT_PROT_TXOP_ALLOW_ALL |
-		  MT_PROT_RTS_THR_EN;
-	prot[1] = prot[0];
-	if (legacy_prot)
-		prot[1] |= MT_PROT_CTRL_CTS2SELF;
-
-	prot[2] = prot[4] = MT_PROT_NAV_SHORT | MT_PROT_TXOP_ALLOW_BW20;
-	prot[3] = prot[5] = MT_PROT_NAV_SHORT | MT_PROT_TXOP_ALLOW_ALL;
-
-	if (legacy_prot) {
-		prot[2] |= MT_PROT_RATE_CCK_11;
-		prot[3] |= MT_PROT_RATE_CCK_11;
-		prot[4] |= MT_PROT_RATE_CCK_11;
-		prot[5] |= MT_PROT_RATE_CCK_11;
-	} else {
-		prot[2] |= MT_PROT_RATE_OFDM_24;
-		prot[3] |= MT_PROT_RATE_DUP_OFDM_24;
-		prot[4] |= MT_PROT_RATE_OFDM_24;
-		prot[5] |= MT_PROT_RATE_DUP_OFDM_24;
-	}
-
-	switch (mode) {
-	case IEEE80211_HT_OP_MODE_PROTECTION_NONE:
-		break;
-
-	case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER:
-		ht_rts[0] = ht_rts[1] = ht_rts[2] = ht_rts[3] = true;
-		break;
-
-	case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ:
-		ht_rts[1] = ht_rts[3] = true;
-		break;
-
-	case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED:
-		ht_rts[0] = ht_rts[1] = ht_rts[2] = ht_rts[3] = true;
-		break;
-	}
-
-	if (non_gf)
-		ht_rts[2] = ht_rts[3] = true;
-
-	for (i = 0; i < 4; i++)
-		if (ht_rts[i])
-			prot[i + 2] |= MT_PROT_CTRL_RTS_CTS;
-
-	for (i = 0; i < 6; i++)
-		mt76_wr(dev, MT_CCK_PROT_CFG + i * 4, prot[i]);
-}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index 8de19fe534a3..b8eba511d0f3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -107,10 +107,6 @@ void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
 		dev->tbtt_count = 0;
 	}
 
-	if (changed & BSS_CHANGED_HT || changed & BSS_CHANGED_ERP_CTS_PROT)
-		mt76x0_mac_set_protection(dev, info->use_cts_prot,
-					   info->ht_operation_mode);
-
 	if (changed & BSS_CHANGED_ERP_PREAMBLE)
 		mt76x02_mac_set_short_preamble(dev, info->use_short_preamble);
 
@@ -124,13 +120,3 @@ void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
 	mutex_unlock(&dev->mt76.mutex);
 }
 EXPORT_SYMBOL_GPL(mt76x0_bss_info_changed);
-
-int mt76x0_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
-{
-	struct mt76x02_dev *dev = hw->priv;
-
-	mt76_rmw_field(dev, MT_TX_RTS_CFG, MT_TX_RTS_CFG_THRESH, value);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mt76x0_set_rts_threshold);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 5b4f30225dc1..14ca5937ed97 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -65,7 +65,6 @@ int mt76x0_config(struct ieee80211_hw *hw, u32 changed);
 void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif,
 			     struct ieee80211_bss_conf *info, u32 changed);
-int mt76x0_set_rts_threshold(struct ieee80211_hw *hw, u32 value);
 
 /* PHY */
 void mt76x0_phy_init(struct mt76x02_dev *dev);
@@ -74,8 +73,4 @@ int mt76x0_phy_set_channel(struct mt76x02_dev *dev,
 			    struct cfg80211_chan_def *chandef);
 void mt76x0_phy_set_txpower(struct mt76x02_dev *dev);
 void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on);
-
-/* MAC */
-void mt76x0_mac_set_protection(struct mt76x02_dev *dev, bool legacy_prot,
-				int ht_mode);
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index b16227fdbdc4..0a5b499061e9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -105,6 +105,7 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.set_tim = mt76x0e_set_tim,
 	.release_buffered_frames = mt76_release_buffered_frames,
 	.set_coverage_class = mt76x02_set_coverage_class,
+	.set_rts_threshold = mt76x02_set_rts_threshold,
 };
 
 static int mt76x0e_register_device(struct mt76x02_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 2105e966f745..690c2e6abaeb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -154,7 +154,7 @@ static const struct ieee80211_ops mt76x0u_ops = {
 	.sw_scan_complete = mt76x02_sw_scan_complete,
 	.ampdu_action = mt76x02_ampdu_action,
 	.sta_rate_tbl_update = mt76x02_sta_rate_tbl_update,
-	.set_rts_threshold = mt76x0_set_rts_threshold,
+	.set_rts_threshold = mt76x02_set_rts_threshold,
 	.wake_tx_queue = mt76_wake_tx_queue,
 	.get_txpower = mt76x02_get_txpower,
 };
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 95af2b1c7eed..3b698f0e8b28 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -136,6 +136,7 @@ void mt76x02_tx_set_txpwr_auto(struct mt76x02_dev *dev, s8 txpwr);
 void mt76x02_set_tx_ackto(struct mt76x02_dev *dev);
 void mt76x02_set_coverage_class(struct ieee80211_hw *hw,
 				s16 coverage_class);
+int mt76x02_set_rts_threshold(struct ieee80211_hw *hw, u32 val);
 int mt76x02_insert_hdr_pad(struct sk_buff *skb);
 void mt76x02_remove_hdr_pad(struct sk_buff *skb, int len);
 void mt76x02_tx_complete(struct mt76_dev *dev, struct sk_buff *skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index d9d7f3e609fc..4fb9f095ffec 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -739,6 +739,36 @@ void mt76x02_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
 }
 EXPORT_SYMBOL_GPL(mt76x02_tx_complete_skb);
 
+void mt76x02_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val)
+{
+	u32 data = 0;
+
+	if (val != ~0)
+		data = FIELD_PREP(MT_PROT_CFG_CTRL, 1) |
+		       MT_PROT_CFG_RTS_THRESH;
+
+	mt76_rmw_field(dev, MT_TX_RTS_CFG, MT_TX_RTS_CFG_THRESH, val);
+
+	mt76_rmw(dev, MT_CCK_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_OFDM_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_MM20_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_MM40_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_GF20_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_GF40_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_TX_PROT_CFG6,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_TX_PROT_CFG7,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_TX_PROT_CFG8,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+}
+
 void mt76x02_update_channel(struct mt76_dev *mdev)
 {
 	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index 350cb0fed980..f65157600779 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -216,8 +216,8 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 			    struct mt76x02_tx_status *stat, u8 *update);
 int mt76x02_mac_process_rx(struct mt76x02_dev *dev, struct sk_buff *skb,
 			   void *rxi);
-int
-mt76x02_mac_process_rate(struct mt76_rx_status *status, u16 rate);
+int mt76x02_mac_process_rate(struct mt76_rx_status *status, u16 rate);
+void mt76x02_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val);
 void mt76x02_mac_setaddr(struct mt76x02_dev *dev, u8 *addr);
 void mt76x02_mac_write_txwi(struct mt76x02_dev *dev, struct mt76x02_txwi *txwi,
 			    struct sk_buff *skb, struct mt76_wcid *wcid,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index c485f6600ae9..65eed824d9c8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -468,6 +468,21 @@ void mt76x02_set_coverage_class(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL_GPL(mt76x02_set_coverage_class);
 
+int mt76x02_set_rts_threshold(struct ieee80211_hw *hw, u32 val)
+{
+	struct mt76x02_dev *dev = hw->priv;
+
+	if (val != ~0 && val > 0xffff)
+		return -EINVAL;
+
+	mutex_lock(&dev->mutex);
+	mt76x02_mac_set_tx_protection(dev, val);
+	mutex_unlock(&dev->mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x02_set_rts_threshold);
+
 void mt76x02_sta_rate_tbl_update(struct ieee80211_hw *hw,
 				struct ieee80211_vif *vif,
 				struct ieee80211_sta *sta)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile b/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
index cf8ef1a2f261..eec18e293407 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
@@ -6,8 +6,8 @@ mt76x2-common-y := \
 	eeprom.o mac.o init.o phy.o mcu.o
 
 mt76x2e-y := \
-	pci.o pci_main.o pci_init.o pci_mac.o \
-	pci_mcu.o pci_phy.o pci_dfs.o
+	pci.o pci_main.o pci_init.o pci_mcu.o \
+	pci_phy.o pci_dfs.o
 
 mt76x2u-y := \
 	usb.o usb_init.o usb_main.o usb_mac.o usb_mcu.o \
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index 3f0b9c78625d..4dfd49190735 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -74,8 +74,6 @@ int mt76x2_mcu_load_cr(struct mt76x02_dev *dev, u8 type, u8 temp_level,
 
 void mt76x2_cleanup(struct mt76x02_dev *dev);
 
-void mt76x2_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val);
-
 void mt76x2_reset_wlan(struct mt76x02_dev *dev, bool enable);
 void mt76x2_init_txpower(struct mt76x02_dev *dev,
 			 struct ieee80211_supported_band *sband);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c
deleted file mode 100644
index 31e1f5bd9050..000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mac.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- */
-
-#include <linux/delay.h>
-#include "mt76x2.h"
-#include "mcu.h"
-#include "eeprom.h"
-
-void mt76x2_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val)
-{
-	u32 data = 0;
-
-	if (val != ~0)
-		data = FIELD_PREP(MT_PROT_CFG_CTRL, 1) |
-		       MT_PROT_CFG_RTS_THRESH;
-
-	mt76_rmw_field(dev, MT_TX_RTS_CFG, MT_TX_RTS_CFG_THRESH, val);
-
-	mt76_rmw(dev, MT_CCK_PROT_CFG,
-		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
-	mt76_rmw(dev, MT_OFDM_PROT_CFG,
-		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
-	mt76_rmw(dev, MT_MM20_PROT_CFG,
-		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
-	mt76_rmw(dev, MT_MM40_PROT_CFG,
-		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
-	mt76_rmw(dev, MT_GF20_PROT_CFG,
-		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
-	mt76_rmw(dev, MT_GF40_PROT_CFG,
-		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
-	mt76_rmw(dev, MT_TX_PROT_CFG6,
-		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
-	mt76_rmw(dev, MT_TX_PROT_CFG7,
-		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
-	mt76_rmw(dev, MT_TX_PROT_CFG8,
-		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
-}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
index f984bb0f9aa1..f1bd36c46036 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
@@ -210,21 +210,6 @@ static int mt76x2_get_antenna(struct ieee80211_hw *hw, u32 *tx_ant,
 	return 0;
 }
 
-static int
-mt76x2_set_rts_threshold(struct ieee80211_hw *hw, u32 val)
-{
-	struct mt76x02_dev *dev = hw->priv;
-
-	if (val != ~0 && val > 0xffff)
-		return -EINVAL;
-
-	mutex_lock(&dev->mutex);
-	mt76x2_mac_set_tx_protection(dev, val);
-	mutex_unlock(&dev->mutex);
-
-	return 0;
-}
-
 const struct ieee80211_ops mt76x2_ops = {
 	.tx = mt76x02_tx,
 	.start = mt76x2_start,
@@ -251,6 +236,6 @@ const struct ieee80211_ops mt76x2_ops = {
 	.set_tim = mt76x2_set_tim,
 	.set_antenna = mt76x2_set_antenna,
 	.get_antenna = mt76x2_get_antenna,
-	.set_rts_threshold = mt76x2_set_rts_threshold,
+	.set_rts_threshold = mt76x02_set_rts_threshold,
 };
 
-- 
cgit v1.2.3


From cc726268e4dcec33c6ed65d664d70b9e13cb4760 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 20 Oct 2018 12:40:55 +0200
Subject: mt76: move mt76x02_bss_info_changed in mt76x02-lib module

Unify drv_bss_info_changed mac80211 callback and remove duplicated
code in mt76x0 and mt76x2 drivers

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c   | 49 ----------------------
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  3 --
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |  3 ++
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c  | 42 +++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt76x2/pci_main.c   | 39 +----------------
 7 files changed, 48 insertions(+), 92 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index b8eba511d0f3..cd1a1225ad8b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -71,52 +71,3 @@ int mt76x0_config(struct ieee80211_hw *hw, u32 changed)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mt76x0_config);
-
-void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
-			     struct ieee80211_vif *vif,
-			     struct ieee80211_bss_conf *info, u32 changed)
-{
-	struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
-	struct mt76x02_dev *dev = hw->priv;
-
-	mutex_lock(&dev->mt76.mutex);
-
-	if (changed & BSS_CHANGED_BSSID)
-		mt76x02_mac_set_bssid(dev, mvif->idx, info->bssid);
-
-	if (changed & BSS_CHANGED_BEACON_ENABLED) {
-		tasklet_disable(&dev->pre_tbtt_tasklet);
-		mt76x02_mac_set_beacon_enable(dev, mvif->idx,
-					      info->enable_beacon);
-		tasklet_enable(&dev->pre_tbtt_tasklet);
-	}
-
-	if (changed & BSS_CHANGED_BASIC_RATES) {
-		mt76_wr(dev, MT_LEGACY_BASIC_RATE, info->basic_rates);
-		mt76_wr(dev, MT_VHT_HT_FBK_CFG0, 0x65432100);
-		mt76_wr(dev, MT_VHT_HT_FBK_CFG1, 0xedcba980);
-		mt76_wr(dev, MT_LG_FBK_CFG0, 0xedcba988);
-		mt76_wr(dev, MT_LG_FBK_CFG1, 0x00002100);
-	}
-
-	if (changed & BSS_CHANGED_BEACON_INT) {
-		mt76_rmw_field(dev, MT_BEACON_TIME_CFG,
-			       MT_BEACON_TIME_CFG_INTVAL,
-			       info->beacon_int << 4);
-		dev->beacon_int = info->beacon_int;
-		dev->tbtt_count = 0;
-	}
-
-	if (changed & BSS_CHANGED_ERP_PREAMBLE)
-		mt76x02_mac_set_short_preamble(dev, info->use_short_preamble);
-
-	if (changed & BSS_CHANGED_ERP_SLOT) {
-		int slottime = info->use_short_slot ? 9 : 20;
-
-		dev->slottime = slottime;
-		mt76x02_set_tx_ackto(dev);
-	}
-
-	mutex_unlock(&dev->mt76.mutex);
-}
-EXPORT_SYMBOL_GPL(mt76x0_bss_info_changed);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 14ca5937ed97..46629f61673b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -62,9 +62,6 @@ int mt76x0_mac_start(struct mt76x02_dev *dev);
 void mt76x0_mac_stop(struct mt76x02_dev *dev);
 
 int mt76x0_config(struct ieee80211_hw *hw, u32 changed);
-void mt76x0_bss_info_changed(struct ieee80211_hw *hw,
-			     struct ieee80211_vif *vif,
-			     struct ieee80211_bss_conf *info, u32 changed);
 
 /* PHY */
 void mt76x0_phy_init(struct mt76x02_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 0a5b499061e9..757816d2b1ab 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -89,7 +89,7 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.remove_interface = mt76x02_remove_interface,
 	.config = mt76x0_config,
 	.configure_filter = mt76x02_configure_filter,
-	.bss_info_changed = mt76x0_bss_info_changed,
+	.bss_info_changed = mt76x02_bss_info_changed,
 	.sta_add = mt76x02_sta_add,
 	.sta_remove = mt76x02_sta_remove,
 	.set_key = mt76x02_set_key,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 690c2e6abaeb..35b98661632a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -145,7 +145,7 @@ static const struct ieee80211_ops mt76x0u_ops = {
 	.remove_interface = mt76x02_remove_interface,
 	.config = mt76x0_config,
 	.configure_filter = mt76x02_configure_filter,
-	.bss_info_changed = mt76x0_bss_info_changed,
+	.bss_info_changed = mt76x02_bss_info_changed,
 	.sta_add = mt76x02_sta_add,
 	.sta_remove = mt76x02_sta_remove,
 	.set_key = mt76x02_set_key,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 3b698f0e8b28..d599b7dddac7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -158,6 +158,9 @@ void mt76x02_sw_scan_complete(struct ieee80211_hw *hw,
 int mt76x02_get_txpower(struct ieee80211_hw *hw,
 			struct ieee80211_vif *vif, int *dbm);
 void mt76x02_sta_ps(struct mt76_dev *dev, struct ieee80211_sta *sta, bool ps);
+void mt76x02_bss_info_changed(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_bss_conf *info, u32 changed);
 
 extern const u16 mt76x02_beacon_offsets[16];
 void mt76x02_init_beacon_config(struct mt76x02_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 65eed824d9c8..4c3b8392b2b7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -647,4 +647,46 @@ void mt76x02_init_beacon_config(struct mt76x02_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76x02_init_beacon_config);
 
+void mt76x02_bss_info_changed(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_bss_conf *info,
+			      u32 changed)
+{
+	struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
+	struct mt76x02_dev *dev = hw->priv;
+
+	mutex_lock(&dev->mt76.mutex);
+
+	if (changed & BSS_CHANGED_BSSID)
+		mt76x02_mac_set_bssid(dev, mvif->idx, info->bssid);
+
+	if (changed & BSS_CHANGED_BEACON_ENABLED) {
+		tasklet_disable(&dev->pre_tbtt_tasklet);
+		mt76x02_mac_set_beacon_enable(dev, mvif->idx,
+					      info->enable_beacon);
+		tasklet_enable(&dev->pre_tbtt_tasklet);
+	}
+
+	if (changed & BSS_CHANGED_BEACON_INT) {
+		mt76_rmw_field(dev, MT_BEACON_TIME_CFG,
+			       MT_BEACON_TIME_CFG_INTVAL,
+			       info->beacon_int << 4);
+		dev->beacon_int = info->beacon_int;
+		dev->tbtt_count = 0;
+	}
+
+	if (changed & BSS_CHANGED_ERP_PREAMBLE)
+		mt76x02_mac_set_short_preamble(dev, info->use_short_preamble);
+
+	if (changed & BSS_CHANGED_ERP_SLOT) {
+		int slottime = info->use_short_slot ? 9 : 20;
+
+		dev->slottime = slottime;
+		mt76x02_set_tx_ackto(dev);
+	}
+
+	mutex_unlock(&dev->mt76.mutex);
+}
+EXPORT_SYMBOL_GPL(mt76x02_bss_info_changed);
+
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
index f1bd36c46036..ec585b92d6c0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
@@ -127,43 +127,6 @@ mt76x2_config(struct ieee80211_hw *hw, u32 changed)
 	return ret;
 }
 
-static void
-mt76x2_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			struct ieee80211_bss_conf *info, u32 changed)
-{
-	struct mt76x02_dev *dev = hw->priv;
-	struct mt76x02_vif *mvif = (struct mt76x02_vif *) vif->drv_priv;
-
-	mutex_lock(&dev->mt76.mutex);
-
-	if (changed & BSS_CHANGED_BSSID)
-		mt76x02_mac_set_bssid(dev, mvif->idx, info->bssid);
-
-	if (changed & BSS_CHANGED_BEACON_INT) {
-		mt76_rmw_field(dev, MT_BEACON_TIME_CFG,
-			       MT_BEACON_TIME_CFG_INTVAL,
-			       info->beacon_int << 4);
-		dev->beacon_int = info->beacon_int;
-		dev->tbtt_count = 0;
-	}
-
-	if (changed & BSS_CHANGED_BEACON_ENABLED) {
-		tasklet_disable(&dev->pre_tbtt_tasklet);
-		mt76x02_mac_set_beacon_enable(dev, mvif->idx,
-					      info->enable_beacon);
-		tasklet_enable(&dev->pre_tbtt_tasklet);
-	}
-
-	if (changed & BSS_CHANGED_ERP_SLOT) {
-		int slottime = info->use_short_slot ? 9 : 20;
-
-		dev->slottime = slottime;
-		mt76x02_set_tx_ackto(dev);
-	}
-
-	mutex_unlock(&dev->mt76.mutex);
-}
-
 static void
 mt76x2_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	     u32 queues, bool drop)
@@ -218,7 +181,7 @@ const struct ieee80211_ops mt76x2_ops = {
 	.remove_interface = mt76x02_remove_interface,
 	.config = mt76x2_config,
 	.configure_filter = mt76x02_configure_filter,
-	.bss_info_changed = mt76x2_bss_info_changed,
+	.bss_info_changed = mt76x02_bss_info_changed,
 	.sta_add = mt76x02_sta_add,
 	.sta_remove = mt76x02_sta_remove,
 	.set_key = mt76x02_set_key,
-- 
cgit v1.2.3


From e6cb3291053fdf21e5caba68137b4bab112815fc Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 22 Oct 2018 23:42:12 +0200
Subject: mt76: move dfs support in mt76x02-lib module

Move mt76x2 DFS support in mt76x02-lib module in order to
be reused by mt76x0 driver and unlock DFS frequencies

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/Makefile        |   3 +-
 drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c   | 868 +++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x02_dfs.h   |   4 +
 drivers/net/wireless/mediatek/mt76/mt76x2/Makefile |   2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/dfs.h    |  25 -
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h |   1 -
 .../net/wireless/mediatek/mt76/mt76x2/pci_dfs.c    | 857 --------------------
 .../net/wireless/mediatek/mt76/mt76x2/pci_init.c   |  13 +-
 .../net/wireless/mediatek/mt76/mt76x2/pci_main.c   |   2 +-
 9 files changed, 878 insertions(+), 897 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2/dfs.h
 delete mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2/pci_dfs.c

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index a737a518802f..1a45cb30f39f 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -14,7 +14,8 @@ CFLAGS_mt76x02_trace.o := -I$(src)
 
 mt76x02-lib-y := mt76x02_util.o mt76x02_mac.o mt76x02_mcu.o \
 		 mt76x02_eeprom.o mt76x02_phy.o mt76x02_mmio.o \
-		 mt76x02_txrx.o mt76x02_trace.o mt76x02_debugfs.o
+		 mt76x02_txrx.o mt76x02_trace.o mt76x02_debugfs.o \
+		 mt76x02_dfs.o
 
 mt76x02-usb-y := mt76x02_usb_mcu.o mt76x02_usb_core.o
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
new file mode 100644
index 000000000000..21e7b8c9f824
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
@@ -0,0 +1,868 @@
+/*
+ * Copyright (C) 2016 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x02.h"
+
+#define RADAR_SPEC(m, len, el, eh, wl, wh,		\
+		   w_tolerance, tl, th, t_tolerance,	\
+		   bl, bh, event_exp, power_jmp)	\
+{							\
+	.mode = m,					\
+	.avg_len = len,					\
+	.e_low = el,					\
+	.e_high = eh,					\
+	.w_low = wl,					\
+	.w_high = wh,					\
+	.w_margin = w_tolerance,			\
+	.t_low = tl,					\
+	.t_high = th,					\
+	.t_margin = t_tolerance,			\
+	.b_low = bl,					\
+	.b_high = bh,					\
+	.event_expiration = event_exp,			\
+	.pwr_jmp = power_jmp				\
+}
+
+static const struct mt76x02_radar_specs etsi_radar_specs[] = {
+	/* 20MHz */
+	RADAR_SPEC(0, 8, 2, 15, 106, 150, 10, 4900, 100096, 10, 0,
+		   0x7fffffff, 0x155cc0, 0x19cc),
+	RADAR_SPEC(0, 40, 4, 59, 96, 380, 150, 4900, 100096, 40, 0,
+		   0x7fffffff, 0x155cc0, 0x19cc),
+	RADAR_SPEC(3, 60, 20, 46, 300, 640, 80, 4900, 10100, 80, 0,
+		   0x7fffffff, 0x155cc0, 0x19dd),
+	RADAR_SPEC(8, 8, 2, 9, 106, 150, 32, 4900, 296704, 32, 0,
+		   0x7fffffff, 0x2191c0, 0x15cc),
+	/* 40MHz */
+	RADAR_SPEC(0, 8, 2, 15, 106, 150, 10, 4900, 100096, 10, 0,
+		   0x7fffffff, 0x155cc0, 0x19cc),
+	RADAR_SPEC(0, 40, 4, 59, 96, 380, 150, 4900, 100096, 40, 0,
+		   0x7fffffff, 0x155cc0, 0x19cc),
+	RADAR_SPEC(3, 60, 20, 46, 300, 640, 80, 4900, 10100, 80, 0,
+		   0x7fffffff, 0x155cc0, 0x19dd),
+	RADAR_SPEC(8, 8, 2, 9, 106, 150, 32, 4900, 296704, 32, 0,
+		   0x7fffffff, 0x2191c0, 0x15cc),
+	/* 80MHz */
+	RADAR_SPEC(0, 8, 2, 15, 106, 150, 10, 4900, 100096, 10, 0,
+		   0x7fffffff, 0x155cc0, 0x19cc),
+	RADAR_SPEC(0, 40, 4, 59, 96, 380, 150, 4900, 100096, 40, 0,
+		   0x7fffffff, 0x155cc0, 0x19cc),
+	RADAR_SPEC(3, 60, 20, 46, 300, 640, 80, 4900, 10100, 80, 0,
+		   0x7fffffff, 0x155cc0, 0x19dd),
+	RADAR_SPEC(8, 8, 2, 9, 106, 150, 32, 4900, 296704, 32, 0,
+		   0x7fffffff, 0x2191c0, 0x15cc)
+};
+
+static const struct mt76x02_radar_specs fcc_radar_specs[] = {
+	/* 20MHz */
+	RADAR_SPEC(0, 8, 2, 12, 106, 150, 5, 2900, 80100, 5, 0,
+		   0x7fffffff, 0xfe808, 0x13dc),
+	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
+		   0x7fffffff, 0xfe808, 0x19dd),
+	RADAR_SPEC(0, 40, 4, 54, 96, 480, 150, 2900, 80100, 40, 0,
+		   0x7fffffff, 0xfe808, 0x12cc),
+	RADAR_SPEC(2, 60, 15, 63, 640, 2080, 32, 19600, 40200, 32, 0,
+		   0x3938700, 0x57bcf00, 0x1289),
+	/* 40MHz */
+	RADAR_SPEC(0, 8, 2, 12, 106, 150, 5, 2900, 80100, 5, 0,
+		   0x7fffffff, 0xfe808, 0x13dc),
+	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
+		   0x7fffffff, 0xfe808, 0x19dd),
+	RADAR_SPEC(0, 40, 4, 54, 96, 480, 150, 2900, 80100, 40, 0,
+		   0x7fffffff, 0xfe808, 0x12cc),
+	RADAR_SPEC(2, 60, 15, 63, 640, 2080, 32, 19600, 40200, 32, 0,
+		   0x3938700, 0x57bcf00, 0x1289),
+	/* 80MHz */
+	RADAR_SPEC(0, 8, 2, 14, 106, 150, 15, 2900, 80100, 15, 0,
+		   0x7fffffff, 0xfe808, 0x16cc),
+	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
+		   0x7fffffff, 0xfe808, 0x19dd),
+	RADAR_SPEC(0, 40, 4, 54, 96, 480, 150, 2900, 80100, 40, 0,
+		   0x7fffffff, 0xfe808, 0x12cc),
+	RADAR_SPEC(2, 60, 15, 63, 640, 2080, 32, 19600, 40200, 32, 0,
+		   0x3938700, 0x57bcf00, 0x1289)
+};
+
+static const struct mt76x02_radar_specs jp_w56_radar_specs[] = {
+	/* 20MHz */
+	RADAR_SPEC(0, 8, 2, 7, 106, 150, 5, 2900, 80100, 5, 0,
+		   0x7fffffff, 0x14c080, 0x13dc),
+	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
+		   0x7fffffff, 0x14c080, 0x19dd),
+	RADAR_SPEC(0, 40, 4, 44, 96, 480, 150, 2900, 80100, 40, 0,
+		   0x7fffffff, 0x14c080, 0x12cc),
+	RADAR_SPEC(2, 60, 15, 48, 940, 2080, 32, 19600, 40200, 32, 0,
+		   0x3938700, 0X57bcf00, 0x1289),
+	/* 40MHz */
+	RADAR_SPEC(0, 8, 2, 7, 106, 150, 5, 2900, 80100, 5, 0,
+		   0x7fffffff, 0x14c080, 0x13dc),
+	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
+		   0x7fffffff, 0x14c080, 0x19dd),
+	RADAR_SPEC(0, 40, 4, 44, 96, 480, 150, 2900, 80100, 40, 0,
+		   0x7fffffff, 0x14c080, 0x12cc),
+	RADAR_SPEC(2, 60, 15, 48, 940, 2080, 32, 19600, 40200, 32, 0,
+		   0x3938700, 0X57bcf00, 0x1289),
+	/* 80MHz */
+	RADAR_SPEC(0, 8, 2, 9, 106, 150, 15, 2900, 80100, 15, 0,
+		   0x7fffffff, 0x14c080, 0x16cc),
+	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
+		   0x7fffffff, 0x14c080, 0x19dd),
+	RADAR_SPEC(0, 40, 4, 44, 96, 480, 150, 2900, 80100, 40, 0,
+		   0x7fffffff, 0x14c080, 0x12cc),
+	RADAR_SPEC(2, 60, 15, 48, 940, 2080, 32, 19600, 40200, 32, 0,
+		   0x3938700, 0X57bcf00, 0x1289)
+};
+
+static const struct mt76x02_radar_specs jp_w53_radar_specs[] = {
+	/* 20MHz */
+	RADAR_SPEC(0, 8, 2, 9, 106, 150, 20, 28400, 77000, 20, 0,
+		   0x7fffffff, 0x14c080, 0x16cc),
+	{ 0 },
+	RADAR_SPEC(0, 40, 4, 44, 96, 200, 150, 28400, 77000, 60, 0,
+		   0x7fffffff, 0x14c080, 0x16cc),
+	{ 0 },
+	/* 40MHz */
+	RADAR_SPEC(0, 8, 2, 9, 106, 150, 20, 28400, 77000, 20, 0,
+		   0x7fffffff, 0x14c080, 0x16cc),
+	{ 0 },
+	RADAR_SPEC(0, 40, 4, 44, 96, 200, 150, 28400, 77000, 60, 0,
+		   0x7fffffff, 0x14c080, 0x16cc),
+	{ 0 },
+	/* 80MHz */
+	RADAR_SPEC(0, 8, 2, 9, 106, 150, 20, 28400, 77000, 20, 0,
+		   0x7fffffff, 0x14c080, 0x16cc),
+	{ 0 },
+	RADAR_SPEC(0, 40, 4, 44, 96, 200, 150, 28400, 77000, 60, 0,
+		   0x7fffffff, 0x14c080, 0x16cc),
+	{ 0 }
+};
+
+static void
+mt76x02_dfs_set_capture_mode_ctrl(struct mt76x02_dev *dev, u8 enable)
+{
+	u32 data;
+
+	data = (1 << 1) | enable;
+	mt76_wr(dev, MT_BBP(DFS, 36), data);
+}
+
+static void mt76x02_dfs_seq_pool_put(struct mt76x02_dev *dev,
+				     struct mt76x02_dfs_sequence *seq)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+
+	list_add(&seq->head, &dfs_pd->seq_pool);
+
+	dfs_pd->seq_stats.seq_pool_len++;
+	dfs_pd->seq_stats.seq_len--;
+}
+
+static struct mt76x02_dfs_sequence *
+mt76x02_dfs_seq_pool_get(struct mt76x02_dev *dev)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x02_dfs_sequence *seq;
+
+	if (list_empty(&dfs_pd->seq_pool)) {
+		seq = devm_kzalloc(dev->mt76.dev, sizeof(*seq), GFP_ATOMIC);
+	} else {
+		seq = list_first_entry(&dfs_pd->seq_pool,
+				       struct mt76x02_dfs_sequence,
+				       head);
+		list_del(&seq->head);
+		dfs_pd->seq_stats.seq_pool_len--;
+	}
+	if (seq)
+		dfs_pd->seq_stats.seq_len++;
+
+	return seq;
+}
+
+static int mt76x02_dfs_get_multiple(int val, int frac, int margin)
+{
+	int remainder, factor;
+
+	if (!frac)
+		return 0;
+
+	if (abs(val - frac) <= margin)
+		return 1;
+
+	factor = val / frac;
+	remainder = val % frac;
+
+	if (remainder > margin) {
+		if ((frac - remainder) <= margin)
+			factor++;
+		else
+			factor = 0;
+	}
+	return factor;
+}
+
+static void mt76x02_dfs_detector_reset(struct mt76x02_dev *dev)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x02_dfs_sequence *seq, *tmp_seq;
+	int i;
+
+	/* reset hw detector */
+	mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
+
+	/* reset sw detector */
+	for (i = 0; i < ARRAY_SIZE(dfs_pd->event_rb); i++) {
+		dfs_pd->event_rb[i].h_rb = 0;
+		dfs_pd->event_rb[i].t_rb = 0;
+	}
+
+	list_for_each_entry_safe(seq, tmp_seq, &dfs_pd->sequences, head) {
+		list_del_init(&seq->head);
+		mt76x02_dfs_seq_pool_put(dev, seq);
+	}
+}
+
+static bool mt76x02_dfs_check_chirp(struct mt76x02_dev *dev)
+{
+	bool ret = false;
+	u32 current_ts, delta_ts;
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+
+	current_ts = mt76_rr(dev, MT_PBF_LIFE_TIMER);
+	delta_ts = current_ts - dfs_pd->chirp_pulse_ts;
+	dfs_pd->chirp_pulse_ts = current_ts;
+
+	/* 12 sec */
+	if (delta_ts <= (12 * (1 << 20))) {
+		if (++dfs_pd->chirp_pulse_cnt > 8)
+			ret = true;
+	} else {
+		dfs_pd->chirp_pulse_cnt = 1;
+	}
+
+	return ret;
+}
+
+static void mt76x02_dfs_get_hw_pulse(struct mt76x02_dev *dev,
+				     struct mt76x02_dfs_hw_pulse *pulse)
+{
+	u32 data;
+
+	/* select channel */
+	data = (MT_DFS_CH_EN << 16) | pulse->engine;
+	mt76_wr(dev, MT_BBP(DFS, 0), data);
+
+	/* reported period */
+	pulse->period = mt76_rr(dev, MT_BBP(DFS, 19));
+
+	/* reported width */
+	pulse->w1 = mt76_rr(dev, MT_BBP(DFS, 20));
+	pulse->w2 = mt76_rr(dev, MT_BBP(DFS, 23));
+
+	/* reported burst number */
+	pulse->burst = mt76_rr(dev, MT_BBP(DFS, 22));
+}
+
+static bool mt76x02_dfs_check_hw_pulse(struct mt76x02_dev *dev,
+				       struct mt76x02_dfs_hw_pulse *pulse)
+{
+	bool ret = false;
+
+	if (!pulse->period || !pulse->w1)
+		return false;
+
+	switch (dev->dfs_pd.region) {
+	case NL80211_DFS_FCC:
+		if (pulse->engine > 3)
+			break;
+
+		if (pulse->engine == 3) {
+			ret = mt76x02_dfs_check_chirp(dev);
+			break;
+		}
+
+		/* check short pulse*/
+		if (pulse->w1 < 120)
+			ret = (pulse->period >= 2900 &&
+			       (pulse->period <= 4700 ||
+				pulse->period >= 6400) &&
+			       (pulse->period <= 6800 ||
+				pulse->period >= 10200) &&
+			       pulse->period <= 61600);
+		else if (pulse->w1 < 130) /* 120 - 130 */
+			ret = (pulse->period >= 2900 &&
+			       pulse->period <= 61600);
+		else
+			ret = (pulse->period >= 3500 &&
+			       pulse->period <= 10100);
+		break;
+	case NL80211_DFS_ETSI:
+		if (pulse->engine >= 3)
+			break;
+
+		ret = (pulse->period >= 4900 &&
+		       (pulse->period <= 10200 ||
+			pulse->period >= 12400) &&
+		       pulse->period <= 100100);
+		break;
+	case NL80211_DFS_JP:
+		if (dev->mt76.chandef.chan->center_freq >= 5250 &&
+		    dev->mt76.chandef.chan->center_freq <= 5350) {
+			/* JPW53 */
+			if (pulse->w1 <= 130)
+				ret = (pulse->period >= 28360 &&
+				       (pulse->period <= 28700 ||
+					pulse->period >= 76900) &&
+				       pulse->period <= 76940);
+			break;
+		}
+
+		if (pulse->engine > 3)
+			break;
+
+		if (pulse->engine == 3) {
+			ret = mt76x02_dfs_check_chirp(dev);
+			break;
+		}
+
+		/* check short pulse*/
+		if (pulse->w1 < 120)
+			ret = (pulse->period >= 2900 &&
+			       (pulse->period <= 4700 ||
+				pulse->period >= 6400) &&
+			       (pulse->period <= 6800 ||
+				pulse->period >= 27560) &&
+			       (pulse->period <= 27960 ||
+				pulse->period >= 28360) &&
+			       (pulse->period <= 28700 ||
+				pulse->period >= 79900) &&
+			       pulse->period <= 80100);
+		else if (pulse->w1 < 130) /* 120 - 130 */
+			ret = (pulse->period >= 2900 &&
+			       (pulse->period <= 10100 ||
+				pulse->period >= 27560) &&
+			       (pulse->period <= 27960 ||
+				pulse->period >= 28360) &&
+			       (pulse->period <= 28700 ||
+				pulse->period >= 79900) &&
+			       pulse->period <= 80100);
+		else
+			ret = (pulse->period >= 3900 &&
+			       pulse->period <= 10100);
+		break;
+	case NL80211_DFS_UNSET:
+	default:
+		return false;
+	}
+
+	return ret;
+}
+
+static bool mt76x02_dfs_fetch_event(struct mt76x02_dev *dev,
+				    struct mt76x02_dfs_event *event)
+{
+	u32 data;
+
+	/* 1st: DFS_R37[31]: 0 (engine 0) - 1 (engine 2)
+	 * 2nd: DFS_R37[21:0]: pulse time
+	 * 3rd: DFS_R37[11:0]: pulse width
+	 * 3rd: DFS_R37[25:16]: phase
+	 * 4th: DFS_R37[12:0]: current pwr
+	 * 4th: DFS_R37[21:16]: pwr stable counter
+	 *
+	 * 1st: DFS_R37[31:0] set to 0xffffffff means no event detected
+	 */
+	data = mt76_rr(dev, MT_BBP(DFS, 37));
+	if (!MT_DFS_CHECK_EVENT(data))
+		return false;
+
+	event->engine = MT_DFS_EVENT_ENGINE(data);
+	data = mt76_rr(dev, MT_BBP(DFS, 37));
+	event->ts = MT_DFS_EVENT_TIMESTAMP(data);
+	data = mt76_rr(dev, MT_BBP(DFS, 37));
+	event->width = MT_DFS_EVENT_WIDTH(data);
+
+	return true;
+}
+
+static bool mt76x02_dfs_check_event(struct mt76x02_dev *dev,
+				    struct mt76x02_dfs_event *event)
+{
+	if (event->engine == 2) {
+		struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+		struct mt76x02_dfs_event_rb *event_buff = &dfs_pd->event_rb[1];
+		u16 last_event_idx;
+		u32 delta_ts;
+
+		last_event_idx = mt76_decr(event_buff->t_rb,
+					   MT_DFS_EVENT_BUFLEN);
+		delta_ts = event->ts - event_buff->data[last_event_idx].ts;
+		if (delta_ts < MT_DFS_EVENT_TIME_MARGIN &&
+		    event_buff->data[last_event_idx].width >= 200)
+			return false;
+	}
+	return true;
+}
+
+static void mt76x02_dfs_queue_event(struct mt76x02_dev *dev,
+				    struct mt76x02_dfs_event *event)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x02_dfs_event_rb *event_buff;
+
+	/* add radar event to ring buffer */
+	event_buff = event->engine == 2 ? &dfs_pd->event_rb[1]
+					: &dfs_pd->event_rb[0];
+	event_buff->data[event_buff->t_rb] = *event;
+	event_buff->data[event_buff->t_rb].fetch_ts = jiffies;
+
+	event_buff->t_rb = mt76_incr(event_buff->t_rb, MT_DFS_EVENT_BUFLEN);
+	if (event_buff->t_rb == event_buff->h_rb)
+		event_buff->h_rb = mt76_incr(event_buff->h_rb,
+					     MT_DFS_EVENT_BUFLEN);
+}
+
+static int mt76x02_dfs_create_sequence(struct mt76x02_dev *dev,
+				       struct mt76x02_dfs_event *event,
+				       u16 cur_len)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x02_dfs_sw_detector_params *sw_params;
+	u32 width_delta, with_sum, factor, cur_pri;
+	struct mt76x02_dfs_sequence seq, *seq_p;
+	struct mt76x02_dfs_event_rb *event_rb;
+	struct mt76x02_dfs_event *cur_event;
+	int i, j, end, pri;
+
+	event_rb = event->engine == 2 ? &dfs_pd->event_rb[1]
+				      : &dfs_pd->event_rb[0];
+
+	i = mt76_decr(event_rb->t_rb, MT_DFS_EVENT_BUFLEN);
+	end = mt76_decr(event_rb->h_rb, MT_DFS_EVENT_BUFLEN);
+
+	while (i != end) {
+		cur_event = &event_rb->data[i];
+		with_sum = event->width + cur_event->width;
+
+		sw_params = &dfs_pd->sw_dpd_params;
+		switch (dev->dfs_pd.region) {
+		case NL80211_DFS_FCC:
+		case NL80211_DFS_JP:
+			if (with_sum < 600)
+				width_delta = 8;
+			else
+				width_delta = with_sum >> 3;
+			break;
+		case NL80211_DFS_ETSI:
+			if (event->engine == 2)
+				width_delta = with_sum >> 6;
+			else if (with_sum < 620)
+				width_delta = 24;
+			else
+				width_delta = 8;
+			break;
+		case NL80211_DFS_UNSET:
+		default:
+			return -EINVAL;
+		}
+
+		pri = event->ts - cur_event->ts;
+		if (abs(event->width - cur_event->width) > width_delta ||
+		    pri < sw_params->min_pri)
+			goto next;
+
+		if (pri > sw_params->max_pri)
+			break;
+
+		seq.pri = event->ts - cur_event->ts;
+		seq.first_ts = cur_event->ts;
+		seq.last_ts = event->ts;
+		seq.engine = event->engine;
+		seq.count = 2;
+
+		j = mt76_decr(i, MT_DFS_EVENT_BUFLEN);
+		while (j != end) {
+			cur_event = &event_rb->data[j];
+			cur_pri = event->ts - cur_event->ts;
+			factor = mt76x02_dfs_get_multiple(cur_pri, seq.pri,
+						sw_params->pri_margin);
+			if (factor > 0) {
+				seq.first_ts = cur_event->ts;
+				seq.count++;
+			}
+
+			j = mt76_decr(j, MT_DFS_EVENT_BUFLEN);
+		}
+		if (seq.count <= cur_len)
+			goto next;
+
+		seq_p = mt76x02_dfs_seq_pool_get(dev);
+		if (!seq_p)
+			return -ENOMEM;
+
+		*seq_p = seq;
+		INIT_LIST_HEAD(&seq_p->head);
+		list_add(&seq_p->head, &dfs_pd->sequences);
+next:
+		i = mt76_decr(i, MT_DFS_EVENT_BUFLEN);
+	}
+	return 0;
+}
+
+static u16 mt76x02_dfs_add_event_to_sequence(struct mt76x02_dev *dev,
+					     struct mt76x02_dfs_event *event)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x02_dfs_sw_detector_params *sw_params;
+	struct mt76x02_dfs_sequence *seq, *tmp_seq;
+	u16 max_seq_len = 0;
+	u32 factor, pri;
+
+	sw_params = &dfs_pd->sw_dpd_params;
+	list_for_each_entry_safe(seq, tmp_seq, &dfs_pd->sequences, head) {
+		if (event->ts > seq->first_ts + MT_DFS_SEQUENCE_WINDOW) {
+			list_del_init(&seq->head);
+			mt76x02_dfs_seq_pool_put(dev, seq);
+			continue;
+		}
+
+		if (event->engine != seq->engine)
+			continue;
+
+		pri = event->ts - seq->last_ts;
+		factor = mt76x02_dfs_get_multiple(pri, seq->pri,
+						  sw_params->pri_margin);
+		if (factor > 0) {
+			seq->last_ts = event->ts;
+			seq->count++;
+			max_seq_len = max_t(u16, max_seq_len, seq->count);
+		}
+	}
+	return max_seq_len;
+}
+
+static bool mt76x02_dfs_check_detection(struct mt76x02_dev *dev)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x02_dfs_sequence *seq;
+
+	if (list_empty(&dfs_pd->sequences))
+		return false;
+
+	list_for_each_entry(seq, &dfs_pd->sequences, head) {
+		if (seq->count > MT_DFS_SEQUENCE_TH) {
+			dfs_pd->stats[seq->engine].sw_pattern++;
+			return true;
+		}
+	}
+	return false;
+}
+
+static void mt76x02_dfs_add_events(struct mt76x02_dev *dev)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x02_dfs_event event;
+	int i, seq_len;
+
+	/* disable debug mode */
+	mt76x02_dfs_set_capture_mode_ctrl(dev, false);
+	for (i = 0; i < MT_DFS_EVENT_LOOP; i++) {
+		if (!mt76x02_dfs_fetch_event(dev, &event))
+			break;
+
+		if (dfs_pd->last_event_ts > event.ts)
+			mt76x02_dfs_detector_reset(dev);
+		dfs_pd->last_event_ts = event.ts;
+
+		if (!mt76x02_dfs_check_event(dev, &event))
+			continue;
+
+		seq_len = mt76x02_dfs_add_event_to_sequence(dev, &event);
+		mt76x02_dfs_create_sequence(dev, &event, seq_len);
+
+		mt76x02_dfs_queue_event(dev, &event);
+	}
+	mt76x02_dfs_set_capture_mode_ctrl(dev, true);
+}
+
+static void mt76x02_dfs_check_event_window(struct mt76x02_dev *dev)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x02_dfs_event_rb *event_buff;
+	struct mt76x02_dfs_event *event;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dfs_pd->event_rb); i++) {
+		event_buff = &dfs_pd->event_rb[i];
+
+		while (event_buff->h_rb != event_buff->t_rb) {
+			event = &event_buff->data[event_buff->h_rb];
+
+			/* sorted list */
+			if (time_is_after_jiffies(event->fetch_ts +
+						  MT_DFS_EVENT_WINDOW))
+				break;
+			event_buff->h_rb = mt76_incr(event_buff->h_rb,
+						     MT_DFS_EVENT_BUFLEN);
+		}
+	}
+}
+
+static void mt76x02_dfs_tasklet(unsigned long arg)
+{
+	struct mt76x02_dev *dev = (struct mt76x02_dev *)arg;
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	u32 engine_mask;
+	int i;
+
+	if (test_bit(MT76_SCANNING, &dev->mt76.state))
+		goto out;
+
+	if (time_is_before_jiffies(dfs_pd->last_sw_check +
+				   MT_DFS_SW_TIMEOUT)) {
+		bool radar_detected;
+
+		dfs_pd->last_sw_check = jiffies;
+
+		mt76x02_dfs_add_events(dev);
+		radar_detected = mt76x02_dfs_check_detection(dev);
+		if (radar_detected) {
+			/* sw detector rx radar pattern */
+			ieee80211_radar_detected(dev->mt76.hw);
+			mt76x02_dfs_detector_reset(dev);
+
+			return;
+		}
+		mt76x02_dfs_check_event_window(dev);
+	}
+
+	engine_mask = mt76_rr(dev, MT_BBP(DFS, 1));
+	if (!(engine_mask & 0xf))
+		goto out;
+
+	for (i = 0; i < MT_DFS_NUM_ENGINES; i++) {
+		struct mt76x02_dfs_hw_pulse pulse;
+
+		if (!(engine_mask & (1 << i)))
+			continue;
+
+		pulse.engine = i;
+		mt76x02_dfs_get_hw_pulse(dev, &pulse);
+
+		if (!mt76x02_dfs_check_hw_pulse(dev, &pulse)) {
+			dfs_pd->stats[i].hw_pulse_discarded++;
+			continue;
+		}
+
+		/* hw detector rx radar pattern */
+		dfs_pd->stats[i].hw_pattern++;
+		ieee80211_radar_detected(dev->mt76.hw);
+		mt76x02_dfs_detector_reset(dev);
+
+		return;
+	}
+
+	/* reset hw detector */
+	mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
+
+out:
+	mt76x02_irq_enable(dev, MT_INT_GPTIMER);
+}
+
+static void mt76x02_dfs_init_sw_detector(struct mt76x02_dev *dev)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+
+	switch (dev->dfs_pd.region) {
+	case NL80211_DFS_FCC:
+		dfs_pd->sw_dpd_params.max_pri = MT_DFS_FCC_MAX_PRI;
+		dfs_pd->sw_dpd_params.min_pri = MT_DFS_FCC_MIN_PRI;
+		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN;
+		break;
+	case NL80211_DFS_ETSI:
+		dfs_pd->sw_dpd_params.max_pri = MT_DFS_ETSI_MAX_PRI;
+		dfs_pd->sw_dpd_params.min_pri = MT_DFS_ETSI_MIN_PRI;
+		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN << 2;
+		break;
+	case NL80211_DFS_JP:
+		dfs_pd->sw_dpd_params.max_pri = MT_DFS_JP_MAX_PRI;
+		dfs_pd->sw_dpd_params.min_pri = MT_DFS_JP_MIN_PRI;
+		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN;
+		break;
+	case NL80211_DFS_UNSET:
+	default:
+		break;
+	}
+}
+
+static void mt76x02_dfs_set_bbp_params(struct mt76x02_dev *dev)
+{
+	const struct mt76x02_radar_specs *radar_specs;
+	u8 i, shift;
+	u32 data;
+
+	switch (dev->mt76.chandef.width) {
+	case NL80211_CHAN_WIDTH_40:
+		shift = MT_DFS_NUM_ENGINES;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		shift = 2 * MT_DFS_NUM_ENGINES;
+		break;
+	default:
+		shift = 0;
+		break;
+	}
+
+	switch (dev->dfs_pd.region) {
+	case NL80211_DFS_FCC:
+		radar_specs = &fcc_radar_specs[shift];
+		break;
+	case NL80211_DFS_ETSI:
+		radar_specs = &etsi_radar_specs[shift];
+		break;
+	case NL80211_DFS_JP:
+		if (dev->mt76.chandef.chan->center_freq >= 5250 &&
+		    dev->mt76.chandef.chan->center_freq <= 5350)
+			radar_specs = &jp_w53_radar_specs[shift];
+		else
+			radar_specs = &jp_w56_radar_specs[shift];
+		break;
+	case NL80211_DFS_UNSET:
+	default:
+		return;
+	}
+
+	data = (MT_DFS_VGA_MASK << 16) |
+	       (MT_DFS_PWR_GAIN_OFFSET << 12) |
+	       (MT_DFS_PWR_DOWN_TIME << 8) |
+	       (MT_DFS_SYM_ROUND << 4) |
+	       (MT_DFS_DELTA_DELAY & 0xf);
+	mt76_wr(dev, MT_BBP(DFS, 2), data);
+
+	data = (MT_DFS_RX_PE_MASK << 16) | MT_DFS_PKT_END_MASK;
+	mt76_wr(dev, MT_BBP(DFS, 3), data);
+
+	for (i = 0; i < MT_DFS_NUM_ENGINES; i++) {
+		/* configure engine */
+		mt76_wr(dev, MT_BBP(DFS, 0), i);
+
+		/* detection mode + avg_len */
+		data = ((radar_specs[i].avg_len & 0x1ff) << 16) |
+		       (radar_specs[i].mode & 0xf);
+		mt76_wr(dev, MT_BBP(DFS, 4), data);
+
+		/* dfs energy */
+		data = ((radar_specs[i].e_high & 0x0fff) << 16) |
+		       (radar_specs[i].e_low & 0x0fff);
+		mt76_wr(dev, MT_BBP(DFS, 5), data);
+
+		/* dfs period */
+		mt76_wr(dev, MT_BBP(DFS, 7), radar_specs[i].t_low);
+		mt76_wr(dev, MT_BBP(DFS, 9), radar_specs[i].t_high);
+
+		/* dfs burst */
+		mt76_wr(dev, MT_BBP(DFS, 11), radar_specs[i].b_low);
+		mt76_wr(dev, MT_BBP(DFS, 13), radar_specs[i].b_high);
+
+		/* dfs width */
+		data = ((radar_specs[i].w_high & 0x0fff) << 16) |
+		       (radar_specs[i].w_low & 0x0fff);
+		mt76_wr(dev, MT_BBP(DFS, 14), data);
+
+		/* dfs margins */
+		data = (radar_specs[i].w_margin << 16) |
+		       radar_specs[i].t_margin;
+		mt76_wr(dev, MT_BBP(DFS, 15), data);
+
+		/* dfs event expiration */
+		mt76_wr(dev, MT_BBP(DFS, 17), radar_specs[i].event_expiration);
+
+		/* dfs pwr adj */
+		mt76_wr(dev, MT_BBP(DFS, 30), radar_specs[i].pwr_jmp);
+	}
+
+	/* reset status */
+	mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
+	mt76_wr(dev, MT_BBP(DFS, 36), 0x3);
+
+	/* enable detection*/
+	mt76_wr(dev, MT_BBP(DFS, 0), MT_DFS_CH_EN << 16);
+	mt76_wr(dev, 0x212c, 0x0c350001);
+}
+
+void mt76x02_dfs_init_params(struct mt76x02_dev *dev)
+{
+	struct cfg80211_chan_def *chandef = &dev->mt76.chandef;
+
+	if ((chandef->chan->flags & IEEE80211_CHAN_RADAR) &&
+	    dev->dfs_pd.region != NL80211_DFS_UNSET) {
+		mt76x02_dfs_init_sw_detector(dev);
+		mt76x02_dfs_set_bbp_params(dev);
+		/* enable debug mode */
+		mt76x02_dfs_set_capture_mode_ctrl(dev, true);
+
+		mt76x02_irq_enable(dev, MT_INT_GPTIMER);
+		mt76_rmw_field(dev, MT_INT_TIMER_EN,
+			       MT_INT_TIMER_EN_GP_TIMER_EN, 1);
+	} else {
+		/* disable hw detector */
+		mt76_wr(dev, MT_BBP(DFS, 0), 0);
+		/* clear detector status */
+		mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
+		mt76_wr(dev, 0x212c, 0);
+
+		mt76x02_irq_disable(dev, MT_INT_GPTIMER);
+		mt76_rmw_field(dev, MT_INT_TIMER_EN,
+			       MT_INT_TIMER_EN_GP_TIMER_EN, 0);
+	}
+}
+EXPORT_SYMBOL_GPL(mt76x02_dfs_init_params);
+
+void mt76x02_dfs_init_detector(struct mt76x02_dev *dev)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+
+	INIT_LIST_HEAD(&dfs_pd->sequences);
+	INIT_LIST_HEAD(&dfs_pd->seq_pool);
+	dfs_pd->region = NL80211_DFS_UNSET;
+	dfs_pd->last_sw_check = jiffies;
+	tasklet_init(&dfs_pd->dfs_tasklet, mt76x02_dfs_tasklet,
+		     (unsigned long)dev);
+}
+EXPORT_SYMBOL_GPL(mt76x02_dfs_init_detector);
+
+static void
+mt76x02_dfs_set_domain(struct mt76x02_dev *dev,
+		       enum nl80211_dfs_regions region)
+{
+	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+
+	if (dfs_pd->region != region) {
+		tasklet_disable(&dfs_pd->dfs_tasklet);
+		dfs_pd->region = region;
+		mt76x02_dfs_init_params(dev);
+		tasklet_enable(&dfs_pd->dfs_tasklet);
+	}
+}
+
+void mt76x02_regd_notifier(struct wiphy *wiphy,
+			   struct regulatory_request *request)
+{
+	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
+	struct mt76x02_dev *dev = hw->priv;
+
+	mt76x02_dfs_set_domain(dev, request->dfs_region);
+}
+EXPORT_SYMBOL_GPL(mt76x02_regd_notifier);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.h b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.h
index 7e177c934592..59e1524ff98b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.h
@@ -137,4 +137,8 @@ struct mt76x02_dfs_pattern_detector {
 	struct tasklet_struct dfs_tasklet;
 };
 
+void mt76x02_dfs_init_params(struct mt76x02_dev *dev);
+void mt76x02_dfs_init_detector(struct mt76x02_dev *dev);
+void mt76x02_regd_notifier(struct wiphy *wiphy,
+			   struct regulatory_request *request);
 #endif /* __MT76x02_DFS_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile b/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
index eec18e293407..9297b850bbba 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/Makefile
@@ -7,7 +7,7 @@ mt76x2-common-y := \
 
 mt76x2e-y := \
 	pci.o pci_main.o pci_init.o pci_mcu.o \
-	pci_phy.o pci_dfs.o
+	pci_phy.o
 
 mt76x2u-y := \
 	usb.o usb_init.o usb_main.o usb_mac.o usb_mcu.o \
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/dfs.h b/drivers/net/wireless/mediatek/mt76/mt76x2/dfs.h
deleted file mode 100644
index a11babbf292d..000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/dfs.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * Copyright (C) 2016 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- */
-
-#ifndef __DFS_H
-#define __DFS_H
-
-void mt76x2_dfs_init_params(struct mt76x02_dev *dev);
-void mt76x2_dfs_init_detector(struct mt76x02_dev *dev);
-void mt76x2_dfs_set_domain(struct mt76x02_dev *dev,
-			   enum nl80211_dfs_regions region);
-
-#endif /* __DFS_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index 4dfd49190735..e5846a85d6ab 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -33,7 +33,6 @@
 
 #include "../mt76x02.h"
 #include "mac.h"
-#include "dfs.h"
 
 static inline bool is_mt7612(struct mt76x02_dev *dev)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_dfs.c
deleted file mode 100644
index 8d66952400a8..000000000000
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_dfs.c
+++ /dev/null
@@ -1,857 +0,0 @@
-/*
- * Copyright (C) 2016 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- */
-
-#include "mt76x2.h"
-
-#define RADAR_SPEC(m, len, el, eh, wl, wh,		\
-		   w_tolerance, tl, th, t_tolerance,	\
-		   bl, bh, event_exp, power_jmp)	\
-{							\
-	.mode = m,					\
-	.avg_len = len,					\
-	.e_low = el,					\
-	.e_high = eh,					\
-	.w_low = wl,					\
-	.w_high = wh,					\
-	.w_margin = w_tolerance,			\
-	.t_low = tl,					\
-	.t_high = th,					\
-	.t_margin = t_tolerance,			\
-	.b_low = bl,					\
-	.b_high = bh,					\
-	.event_expiration = event_exp,			\
-	.pwr_jmp = power_jmp				\
-}
-
-static const struct mt76x02_radar_specs etsi_radar_specs[] = {
-	/* 20MHz */
-	RADAR_SPEC(0, 8, 2, 15, 106, 150, 10, 4900, 100096, 10, 0,
-		   0x7fffffff, 0x155cc0, 0x19cc),
-	RADAR_SPEC(0, 40, 4, 59, 96, 380, 150, 4900, 100096, 40, 0,
-		   0x7fffffff, 0x155cc0, 0x19cc),
-	RADAR_SPEC(3, 60, 20, 46, 300, 640, 80, 4900, 10100, 80, 0,
-		   0x7fffffff, 0x155cc0, 0x19dd),
-	RADAR_SPEC(8, 8, 2, 9, 106, 150, 32, 4900, 296704, 32, 0,
-		   0x7fffffff, 0x2191c0, 0x15cc),
-	/* 40MHz */
-	RADAR_SPEC(0, 8, 2, 15, 106, 150, 10, 4900, 100096, 10, 0,
-		   0x7fffffff, 0x155cc0, 0x19cc),
-	RADAR_SPEC(0, 40, 4, 59, 96, 380, 150, 4900, 100096, 40, 0,
-		   0x7fffffff, 0x155cc0, 0x19cc),
-	RADAR_SPEC(3, 60, 20, 46, 300, 640, 80, 4900, 10100, 80, 0,
-		   0x7fffffff, 0x155cc0, 0x19dd),
-	RADAR_SPEC(8, 8, 2, 9, 106, 150, 32, 4900, 296704, 32, 0,
-		   0x7fffffff, 0x2191c0, 0x15cc),
-	/* 80MHz */
-	RADAR_SPEC(0, 8, 2, 15, 106, 150, 10, 4900, 100096, 10, 0,
-		   0x7fffffff, 0x155cc0, 0x19cc),
-	RADAR_SPEC(0, 40, 4, 59, 96, 380, 150, 4900, 100096, 40, 0,
-		   0x7fffffff, 0x155cc0, 0x19cc),
-	RADAR_SPEC(3, 60, 20, 46, 300, 640, 80, 4900, 10100, 80, 0,
-		   0x7fffffff, 0x155cc0, 0x19dd),
-	RADAR_SPEC(8, 8, 2, 9, 106, 150, 32, 4900, 296704, 32, 0,
-		   0x7fffffff, 0x2191c0, 0x15cc)
-};
-
-static const struct mt76x02_radar_specs fcc_radar_specs[] = {
-	/* 20MHz */
-	RADAR_SPEC(0, 8, 2, 12, 106, 150, 5, 2900, 80100, 5, 0,
-		   0x7fffffff, 0xfe808, 0x13dc),
-	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
-		   0x7fffffff, 0xfe808, 0x19dd),
-	RADAR_SPEC(0, 40, 4, 54, 96, 480, 150, 2900, 80100, 40, 0,
-		   0x7fffffff, 0xfe808, 0x12cc),
-	RADAR_SPEC(2, 60, 15, 63, 640, 2080, 32, 19600, 40200, 32, 0,
-		   0x3938700, 0x57bcf00, 0x1289),
-	/* 40MHz */
-	RADAR_SPEC(0, 8, 2, 12, 106, 150, 5, 2900, 80100, 5, 0,
-		   0x7fffffff, 0xfe808, 0x13dc),
-	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
-		   0x7fffffff, 0xfe808, 0x19dd),
-	RADAR_SPEC(0, 40, 4, 54, 96, 480, 150, 2900, 80100, 40, 0,
-		   0x7fffffff, 0xfe808, 0x12cc),
-	RADAR_SPEC(2, 60, 15, 63, 640, 2080, 32, 19600, 40200, 32, 0,
-		   0x3938700, 0x57bcf00, 0x1289),
-	/* 80MHz */
-	RADAR_SPEC(0, 8, 2, 14, 106, 150, 15, 2900, 80100, 15, 0,
-		   0x7fffffff, 0xfe808, 0x16cc),
-	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
-		   0x7fffffff, 0xfe808, 0x19dd),
-	RADAR_SPEC(0, 40, 4, 54, 96, 480, 150, 2900, 80100, 40, 0,
-		   0x7fffffff, 0xfe808, 0x12cc),
-	RADAR_SPEC(2, 60, 15, 63, 640, 2080, 32, 19600, 40200, 32, 0,
-		   0x3938700, 0x57bcf00, 0x1289)
-};
-
-static const struct mt76x02_radar_specs jp_w56_radar_specs[] = {
-	/* 20MHz */
-	RADAR_SPEC(0, 8, 2, 7, 106, 150, 5, 2900, 80100, 5, 0,
-		   0x7fffffff, 0x14c080, 0x13dc),
-	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
-		   0x7fffffff, 0x14c080, 0x19dd),
-	RADAR_SPEC(0, 40, 4, 44, 96, 480, 150, 2900, 80100, 40, 0,
-		   0x7fffffff, 0x14c080, 0x12cc),
-	RADAR_SPEC(2, 60, 15, 48, 940, 2080, 32, 19600, 40200, 32, 0,
-		   0x3938700, 0X57bcf00, 0x1289),
-	/* 40MHz */
-	RADAR_SPEC(0, 8, 2, 7, 106, 150, 5, 2900, 80100, 5, 0,
-		   0x7fffffff, 0x14c080, 0x13dc),
-	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
-		   0x7fffffff, 0x14c080, 0x19dd),
-	RADAR_SPEC(0, 40, 4, 44, 96, 480, 150, 2900, 80100, 40, 0,
-		   0x7fffffff, 0x14c080, 0x12cc),
-	RADAR_SPEC(2, 60, 15, 48, 940, 2080, 32, 19600, 40200, 32, 0,
-		   0x3938700, 0X57bcf00, 0x1289),
-	/* 80MHz */
-	RADAR_SPEC(0, 8, 2, 9, 106, 150, 15, 2900, 80100, 15, 0,
-		   0x7fffffff, 0x14c080, 0x16cc),
-	RADAR_SPEC(0, 8, 2, 7, 106, 140, 5, 27600, 27900, 5, 0,
-		   0x7fffffff, 0x14c080, 0x19dd),
-	RADAR_SPEC(0, 40, 4, 44, 96, 480, 150, 2900, 80100, 40, 0,
-		   0x7fffffff, 0x14c080, 0x12cc),
-	RADAR_SPEC(2, 60, 15, 48, 940, 2080, 32, 19600, 40200, 32, 0,
-		   0x3938700, 0X57bcf00, 0x1289)
-};
-
-static const struct mt76x02_radar_specs jp_w53_radar_specs[] = {
-	/* 20MHz */
-	RADAR_SPEC(0, 8, 2, 9, 106, 150, 20, 28400, 77000, 20, 0,
-		   0x7fffffff, 0x14c080, 0x16cc),
-	{ 0 },
-	RADAR_SPEC(0, 40, 4, 44, 96, 200, 150, 28400, 77000, 60, 0,
-		   0x7fffffff, 0x14c080, 0x16cc),
-	{ 0 },
-	/* 40MHz */
-	RADAR_SPEC(0, 8, 2, 9, 106, 150, 20, 28400, 77000, 20, 0,
-		   0x7fffffff, 0x14c080, 0x16cc),
-	{ 0 },
-	RADAR_SPEC(0, 40, 4, 44, 96, 200, 150, 28400, 77000, 60, 0,
-		   0x7fffffff, 0x14c080, 0x16cc),
-	{ 0 },
-	/* 80MHz */
-	RADAR_SPEC(0, 8, 2, 9, 106, 150, 20, 28400, 77000, 20, 0,
-		   0x7fffffff, 0x14c080, 0x16cc),
-	{ 0 },
-	RADAR_SPEC(0, 40, 4, 44, 96, 200, 150, 28400, 77000, 60, 0,
-		   0x7fffffff, 0x14c080, 0x16cc),
-	{ 0 }
-};
-
-static void
-mt76x2_dfs_set_capture_mode_ctrl(struct mt76x02_dev *dev,
-				 u8 enable)
-{
-	u32 data;
-
-	data = (1 << 1) | enable;
-	mt76_wr(dev, MT_BBP(DFS, 36), data);
-}
-
-static void mt76x2_dfs_seq_pool_put(struct mt76x02_dev *dev,
-				    struct mt76x02_dfs_sequence *seq)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-
-	list_add(&seq->head, &dfs_pd->seq_pool);
-
-	dfs_pd->seq_stats.seq_pool_len++;
-	dfs_pd->seq_stats.seq_len--;
-}
-
-static struct mt76x02_dfs_sequence *
-mt76x2_dfs_seq_pool_get(struct mt76x02_dev *dev)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-	struct mt76x02_dfs_sequence *seq;
-
-	if (list_empty(&dfs_pd->seq_pool)) {
-		seq = devm_kzalloc(dev->mt76.dev, sizeof(*seq), GFP_ATOMIC);
-	} else {
-		seq = list_first_entry(&dfs_pd->seq_pool,
-				       struct mt76x02_dfs_sequence,
-				       head);
-		list_del(&seq->head);
-		dfs_pd->seq_stats.seq_pool_len--;
-	}
-	if (seq)
-		dfs_pd->seq_stats.seq_len++;
-
-	return seq;
-}
-
-static int mt76x2_dfs_get_multiple(int val, int frac, int margin)
-{
-	int remainder, factor;
-
-	if (!frac)
-		return 0;
-
-	if (abs(val - frac) <= margin)
-		return 1;
-
-	factor = val / frac;
-	remainder = val % frac;
-
-	if (remainder > margin) {
-		if ((frac - remainder) <= margin)
-			factor++;
-		else
-			factor = 0;
-	}
-	return factor;
-}
-
-static void mt76x2_dfs_detector_reset(struct mt76x02_dev *dev)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-	struct mt76x02_dfs_sequence *seq, *tmp_seq;
-	int i;
-
-	/* reset hw detector */
-	mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
-
-	/* reset sw detector */
-	for (i = 0; i < ARRAY_SIZE(dfs_pd->event_rb); i++) {
-		dfs_pd->event_rb[i].h_rb = 0;
-		dfs_pd->event_rb[i].t_rb = 0;
-	}
-
-	list_for_each_entry_safe(seq, tmp_seq, &dfs_pd->sequences, head) {
-		list_del_init(&seq->head);
-		mt76x2_dfs_seq_pool_put(dev, seq);
-	}
-}
-
-static bool mt76x2_dfs_check_chirp(struct mt76x02_dev *dev)
-{
-	bool ret = false;
-	u32 current_ts, delta_ts;
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-
-	current_ts = mt76_rr(dev, MT_PBF_LIFE_TIMER);
-	delta_ts = current_ts - dfs_pd->chirp_pulse_ts;
-	dfs_pd->chirp_pulse_ts = current_ts;
-
-	/* 12 sec */
-	if (delta_ts <= (12 * (1 << 20))) {
-		if (++dfs_pd->chirp_pulse_cnt > 8)
-			ret = true;
-	} else {
-		dfs_pd->chirp_pulse_cnt = 1;
-	}
-
-	return ret;
-}
-
-static void mt76x2_dfs_get_hw_pulse(struct mt76x02_dev *dev,
-				    struct mt76x02_dfs_hw_pulse *pulse)
-{
-	u32 data;
-
-	/* select channel */
-	data = (MT_DFS_CH_EN << 16) | pulse->engine;
-	mt76_wr(dev, MT_BBP(DFS, 0), data);
-
-	/* reported period */
-	pulse->period = mt76_rr(dev, MT_BBP(DFS, 19));
-
-	/* reported width */
-	pulse->w1 = mt76_rr(dev, MT_BBP(DFS, 20));
-	pulse->w2 = mt76_rr(dev, MT_BBP(DFS, 23));
-
-	/* reported burst number */
-	pulse->burst = mt76_rr(dev, MT_BBP(DFS, 22));
-}
-
-static bool mt76x2_dfs_check_hw_pulse(struct mt76x02_dev *dev,
-				      struct mt76x02_dfs_hw_pulse *pulse)
-{
-	bool ret = false;
-
-	if (!pulse->period || !pulse->w1)
-		return false;
-
-	switch (dev->dfs_pd.region) {
-	case NL80211_DFS_FCC:
-		if (pulse->engine > 3)
-			break;
-
-		if (pulse->engine == 3) {
-			ret = mt76x2_dfs_check_chirp(dev);
-			break;
-		}
-
-		/* check short pulse*/
-		if (pulse->w1 < 120)
-			ret = (pulse->period >= 2900 &&
-			       (pulse->period <= 4700 ||
-				pulse->period >= 6400) &&
-			       (pulse->period <= 6800 ||
-				pulse->period >= 10200) &&
-			       pulse->period <= 61600);
-		else if (pulse->w1 < 130) /* 120 - 130 */
-			ret = (pulse->period >= 2900 &&
-			       pulse->period <= 61600);
-		else
-			ret = (pulse->period >= 3500 &&
-			       pulse->period <= 10100);
-		break;
-	case NL80211_DFS_ETSI:
-		if (pulse->engine >= 3)
-			break;
-
-		ret = (pulse->period >= 4900 &&
-		       (pulse->period <= 10200 ||
-			pulse->period >= 12400) &&
-		       pulse->period <= 100100);
-		break;
-	case NL80211_DFS_JP:
-		if (dev->mt76.chandef.chan->center_freq >= 5250 &&
-		    dev->mt76.chandef.chan->center_freq <= 5350) {
-			/* JPW53 */
-			if (pulse->w1 <= 130)
-				ret = (pulse->period >= 28360 &&
-				       (pulse->period <= 28700 ||
-					pulse->period >= 76900) &&
-				       pulse->period <= 76940);
-			break;
-		}
-
-		if (pulse->engine > 3)
-			break;
-
-		if (pulse->engine == 3) {
-			ret = mt76x2_dfs_check_chirp(dev);
-			break;
-		}
-
-		/* check short pulse*/
-		if (pulse->w1 < 120)
-			ret = (pulse->period >= 2900 &&
-			       (pulse->period <= 4700 ||
-				pulse->period >= 6400) &&
-			       (pulse->period <= 6800 ||
-				pulse->period >= 27560) &&
-			       (pulse->period <= 27960 ||
-				pulse->period >= 28360) &&
-			       (pulse->period <= 28700 ||
-				pulse->period >= 79900) &&
-			       pulse->period <= 80100);
-		else if (pulse->w1 < 130) /* 120 - 130 */
-			ret = (pulse->period >= 2900 &&
-			       (pulse->period <= 10100 ||
-				pulse->period >= 27560) &&
-			       (pulse->period <= 27960 ||
-				pulse->period >= 28360) &&
-			       (pulse->period <= 28700 ||
-				pulse->period >= 79900) &&
-			       pulse->period <= 80100);
-		else
-			ret = (pulse->period >= 3900 &&
-			       pulse->period <= 10100);
-		break;
-	case NL80211_DFS_UNSET:
-	default:
-		return false;
-	}
-
-	return ret;
-}
-
-static bool mt76x2_dfs_fetch_event(struct mt76x02_dev *dev,
-				   struct mt76x02_dfs_event *event)
-{
-	u32 data;
-
-	/* 1st: DFS_R37[31]: 0 (engine 0) - 1 (engine 2)
-	 * 2nd: DFS_R37[21:0]: pulse time
-	 * 3rd: DFS_R37[11:0]: pulse width
-	 * 3rd: DFS_R37[25:16]: phase
-	 * 4th: DFS_R37[12:0]: current pwr
-	 * 4th: DFS_R37[21:16]: pwr stable counter
-	 *
-	 * 1st: DFS_R37[31:0] set to 0xffffffff means no event detected
-	 */
-	data = mt76_rr(dev, MT_BBP(DFS, 37));
-	if (!MT_DFS_CHECK_EVENT(data))
-		return false;
-
-	event->engine = MT_DFS_EVENT_ENGINE(data);
-	data = mt76_rr(dev, MT_BBP(DFS, 37));
-	event->ts = MT_DFS_EVENT_TIMESTAMP(data);
-	data = mt76_rr(dev, MT_BBP(DFS, 37));
-	event->width = MT_DFS_EVENT_WIDTH(data);
-
-	return true;
-}
-
-static bool mt76x2_dfs_check_event(struct mt76x02_dev *dev,
-				   struct mt76x02_dfs_event *event)
-{
-	if (event->engine == 2) {
-		struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-		struct mt76x02_dfs_event_rb *event_buff = &dfs_pd->event_rb[1];
-		u16 last_event_idx;
-		u32 delta_ts;
-
-		last_event_idx = mt76_decr(event_buff->t_rb,
-					   MT_DFS_EVENT_BUFLEN);
-		delta_ts = event->ts - event_buff->data[last_event_idx].ts;
-		if (delta_ts < MT_DFS_EVENT_TIME_MARGIN &&
-		    event_buff->data[last_event_idx].width >= 200)
-			return false;
-	}
-	return true;
-}
-
-static void mt76x2_dfs_queue_event(struct mt76x02_dev *dev,
-				   struct mt76x02_dfs_event *event)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-	struct mt76x02_dfs_event_rb *event_buff;
-
-	/* add radar event to ring buffer */
-	event_buff = event->engine == 2 ? &dfs_pd->event_rb[1]
-					: &dfs_pd->event_rb[0];
-	event_buff->data[event_buff->t_rb] = *event;
-	event_buff->data[event_buff->t_rb].fetch_ts = jiffies;
-
-	event_buff->t_rb = mt76_incr(event_buff->t_rb, MT_DFS_EVENT_BUFLEN);
-	if (event_buff->t_rb == event_buff->h_rb)
-		event_buff->h_rb = mt76_incr(event_buff->h_rb,
-					     MT_DFS_EVENT_BUFLEN);
-}
-
-static int mt76x2_dfs_create_sequence(struct mt76x02_dev *dev,
-				      struct mt76x02_dfs_event *event,
-				      u16 cur_len)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-	struct mt76x02_dfs_sw_detector_params *sw_params;
-	u32 width_delta, with_sum, factor, cur_pri;
-	struct mt76x02_dfs_sequence seq, *seq_p;
-	struct mt76x02_dfs_event_rb *event_rb;
-	struct mt76x02_dfs_event *cur_event;
-	int i, j, end, pri;
-
-	event_rb = event->engine == 2 ? &dfs_pd->event_rb[1]
-				      : &dfs_pd->event_rb[0];
-
-	i = mt76_decr(event_rb->t_rb, MT_DFS_EVENT_BUFLEN);
-	end = mt76_decr(event_rb->h_rb, MT_DFS_EVENT_BUFLEN);
-
-	while (i != end) {
-		cur_event = &event_rb->data[i];
-		with_sum = event->width + cur_event->width;
-
-		sw_params = &dfs_pd->sw_dpd_params;
-		switch (dev->dfs_pd.region) {
-		case NL80211_DFS_FCC:
-		case NL80211_DFS_JP:
-			if (with_sum < 600)
-				width_delta = 8;
-			else
-				width_delta = with_sum >> 3;
-			break;
-		case NL80211_DFS_ETSI:
-			if (event->engine == 2)
-				width_delta = with_sum >> 6;
-			else if (with_sum < 620)
-				width_delta = 24;
-			else
-				width_delta = 8;
-			break;
-		case NL80211_DFS_UNSET:
-		default:
-			return -EINVAL;
-		}
-
-		pri = event->ts - cur_event->ts;
-		if (abs(event->width - cur_event->width) > width_delta ||
-		    pri < sw_params->min_pri)
-			goto next;
-
-		if (pri > sw_params->max_pri)
-			break;
-
-		seq.pri = event->ts - cur_event->ts;
-		seq.first_ts = cur_event->ts;
-		seq.last_ts = event->ts;
-		seq.engine = event->engine;
-		seq.count = 2;
-
-		j = mt76_decr(i, MT_DFS_EVENT_BUFLEN);
-		while (j != end) {
-			cur_event = &event_rb->data[j];
-			cur_pri = event->ts - cur_event->ts;
-			factor = mt76x2_dfs_get_multiple(cur_pri, seq.pri,
-						sw_params->pri_margin);
-			if (factor > 0) {
-				seq.first_ts = cur_event->ts;
-				seq.count++;
-			}
-
-			j = mt76_decr(j, MT_DFS_EVENT_BUFLEN);
-		}
-		if (seq.count <= cur_len)
-			goto next;
-
-		seq_p = mt76x2_dfs_seq_pool_get(dev);
-		if (!seq_p)
-			return -ENOMEM;
-
-		*seq_p = seq;
-		INIT_LIST_HEAD(&seq_p->head);
-		list_add(&seq_p->head, &dfs_pd->sequences);
-next:
-		i = mt76_decr(i, MT_DFS_EVENT_BUFLEN);
-	}
-	return 0;
-}
-
-static u16 mt76x2_dfs_add_event_to_sequence(struct mt76x02_dev *dev,
-					    struct mt76x02_dfs_event *event)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-	struct mt76x02_dfs_sw_detector_params *sw_params;
-	struct mt76x02_dfs_sequence *seq, *tmp_seq;
-	u16 max_seq_len = 0;
-	u32 factor, pri;
-
-	sw_params = &dfs_pd->sw_dpd_params;
-	list_for_each_entry_safe(seq, tmp_seq, &dfs_pd->sequences, head) {
-		if (event->ts > seq->first_ts + MT_DFS_SEQUENCE_WINDOW) {
-			list_del_init(&seq->head);
-			mt76x2_dfs_seq_pool_put(dev, seq);
-			continue;
-		}
-
-		if (event->engine != seq->engine)
-			continue;
-
-		pri = event->ts - seq->last_ts;
-		factor = mt76x2_dfs_get_multiple(pri, seq->pri,
-						 sw_params->pri_margin);
-		if (factor > 0) {
-			seq->last_ts = event->ts;
-			seq->count++;
-			max_seq_len = max_t(u16, max_seq_len, seq->count);
-		}
-	}
-	return max_seq_len;
-}
-
-static bool mt76x2_dfs_check_detection(struct mt76x02_dev *dev)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-	struct mt76x02_dfs_sequence *seq;
-
-	if (list_empty(&dfs_pd->sequences))
-		return false;
-
-	list_for_each_entry(seq, &dfs_pd->sequences, head) {
-		if (seq->count > MT_DFS_SEQUENCE_TH) {
-			dfs_pd->stats[seq->engine].sw_pattern++;
-			return true;
-		}
-	}
-	return false;
-}
-
-static void mt76x2_dfs_add_events(struct mt76x02_dev *dev)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-	struct mt76x02_dfs_event event;
-	int i, seq_len;
-
-	/* disable debug mode */
-	mt76x2_dfs_set_capture_mode_ctrl(dev, false);
-	for (i = 0; i < MT_DFS_EVENT_LOOP; i++) {
-		if (!mt76x2_dfs_fetch_event(dev, &event))
-			break;
-
-		if (dfs_pd->last_event_ts > event.ts)
-			mt76x2_dfs_detector_reset(dev);
-		dfs_pd->last_event_ts = event.ts;
-
-		if (!mt76x2_dfs_check_event(dev, &event))
-			continue;
-
-		seq_len = mt76x2_dfs_add_event_to_sequence(dev, &event);
-		mt76x2_dfs_create_sequence(dev, &event, seq_len);
-
-		mt76x2_dfs_queue_event(dev, &event);
-	}
-	mt76x2_dfs_set_capture_mode_ctrl(dev, true);
-}
-
-static void mt76x2_dfs_check_event_window(struct mt76x02_dev *dev)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-	struct mt76x02_dfs_event_rb *event_buff;
-	struct mt76x02_dfs_event *event;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(dfs_pd->event_rb); i++) {
-		event_buff = &dfs_pd->event_rb[i];
-
-		while (event_buff->h_rb != event_buff->t_rb) {
-			event = &event_buff->data[event_buff->h_rb];
-
-			/* sorted list */
-			if (time_is_after_jiffies(event->fetch_ts +
-						  MT_DFS_EVENT_WINDOW))
-				break;
-			event_buff->h_rb = mt76_incr(event_buff->h_rb,
-						     MT_DFS_EVENT_BUFLEN);
-		}
-	}
-}
-
-static void mt76x2_dfs_tasklet(unsigned long arg)
-{
-	struct mt76x02_dev *dev = (struct mt76x02_dev *)arg;
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-	u32 engine_mask;
-	int i;
-
-	if (test_bit(MT76_SCANNING, &dev->mt76.state))
-		goto out;
-
-	if (time_is_before_jiffies(dfs_pd->last_sw_check +
-				   MT_DFS_SW_TIMEOUT)) {
-		bool radar_detected;
-
-		dfs_pd->last_sw_check = jiffies;
-
-		mt76x2_dfs_add_events(dev);
-		radar_detected = mt76x2_dfs_check_detection(dev);
-		if (radar_detected) {
-			/* sw detector rx radar pattern */
-			ieee80211_radar_detected(dev->mt76.hw);
-			mt76x2_dfs_detector_reset(dev);
-
-			return;
-		}
-		mt76x2_dfs_check_event_window(dev);
-	}
-
-	engine_mask = mt76_rr(dev, MT_BBP(DFS, 1));
-	if (!(engine_mask & 0xf))
-		goto out;
-
-	for (i = 0; i < MT_DFS_NUM_ENGINES; i++) {
-		struct mt76x02_dfs_hw_pulse pulse;
-
-		if (!(engine_mask & (1 << i)))
-			continue;
-
-		pulse.engine = i;
-		mt76x2_dfs_get_hw_pulse(dev, &pulse);
-
-		if (!mt76x2_dfs_check_hw_pulse(dev, &pulse)) {
-			dfs_pd->stats[i].hw_pulse_discarded++;
-			continue;
-		}
-
-		/* hw detector rx radar pattern */
-		dfs_pd->stats[i].hw_pattern++;
-		ieee80211_radar_detected(dev->mt76.hw);
-		mt76x2_dfs_detector_reset(dev);
-
-		return;
-	}
-
-	/* reset hw detector */
-	mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
-
-out:
-	mt76x02_irq_enable(dev, MT_INT_GPTIMER);
-}
-
-static void mt76x2_dfs_init_sw_detector(struct mt76x02_dev *dev)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-
-	switch (dev->dfs_pd.region) {
-	case NL80211_DFS_FCC:
-		dfs_pd->sw_dpd_params.max_pri = MT_DFS_FCC_MAX_PRI;
-		dfs_pd->sw_dpd_params.min_pri = MT_DFS_FCC_MIN_PRI;
-		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN;
-		break;
-	case NL80211_DFS_ETSI:
-		dfs_pd->sw_dpd_params.max_pri = MT_DFS_ETSI_MAX_PRI;
-		dfs_pd->sw_dpd_params.min_pri = MT_DFS_ETSI_MIN_PRI;
-		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN << 2;
-		break;
-	case NL80211_DFS_JP:
-		dfs_pd->sw_dpd_params.max_pri = MT_DFS_JP_MAX_PRI;
-		dfs_pd->sw_dpd_params.min_pri = MT_DFS_JP_MIN_PRI;
-		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN;
-		break;
-	case NL80211_DFS_UNSET:
-	default:
-		break;
-	}
-}
-
-static void mt76x2_dfs_set_bbp_params(struct mt76x02_dev *dev)
-{
-	const struct mt76x02_radar_specs *radar_specs;
-	u8 i, shift;
-	u32 data;
-
-	switch (dev->mt76.chandef.width) {
-	case NL80211_CHAN_WIDTH_40:
-		shift = MT_DFS_NUM_ENGINES;
-		break;
-	case NL80211_CHAN_WIDTH_80:
-		shift = 2 * MT_DFS_NUM_ENGINES;
-		break;
-	default:
-		shift = 0;
-		break;
-	}
-
-	switch (dev->dfs_pd.region) {
-	case NL80211_DFS_FCC:
-		radar_specs = &fcc_radar_specs[shift];
-		break;
-	case NL80211_DFS_ETSI:
-		radar_specs = &etsi_radar_specs[shift];
-		break;
-	case NL80211_DFS_JP:
-		if (dev->mt76.chandef.chan->center_freq >= 5250 &&
-		    dev->mt76.chandef.chan->center_freq <= 5350)
-			radar_specs = &jp_w53_radar_specs[shift];
-		else
-			radar_specs = &jp_w56_radar_specs[shift];
-		break;
-	case NL80211_DFS_UNSET:
-	default:
-		return;
-	}
-
-	data = (MT_DFS_VGA_MASK << 16) |
-	       (MT_DFS_PWR_GAIN_OFFSET << 12) |
-	       (MT_DFS_PWR_DOWN_TIME << 8) |
-	       (MT_DFS_SYM_ROUND << 4) |
-	       (MT_DFS_DELTA_DELAY & 0xf);
-	mt76_wr(dev, MT_BBP(DFS, 2), data);
-
-	data = (MT_DFS_RX_PE_MASK << 16) | MT_DFS_PKT_END_MASK;
-	mt76_wr(dev, MT_BBP(DFS, 3), data);
-
-	for (i = 0; i < MT_DFS_NUM_ENGINES; i++) {
-		/* configure engine */
-		mt76_wr(dev, MT_BBP(DFS, 0), i);
-
-		/* detection mode + avg_len */
-		data = ((radar_specs[i].avg_len & 0x1ff) << 16) |
-		       (radar_specs[i].mode & 0xf);
-		mt76_wr(dev, MT_BBP(DFS, 4), data);
-
-		/* dfs energy */
-		data = ((radar_specs[i].e_high & 0x0fff) << 16) |
-		       (radar_specs[i].e_low & 0x0fff);
-		mt76_wr(dev, MT_BBP(DFS, 5), data);
-
-		/* dfs period */
-		mt76_wr(dev, MT_BBP(DFS, 7), radar_specs[i].t_low);
-		mt76_wr(dev, MT_BBP(DFS, 9), radar_specs[i].t_high);
-
-		/* dfs burst */
-		mt76_wr(dev, MT_BBP(DFS, 11), radar_specs[i].b_low);
-		mt76_wr(dev, MT_BBP(DFS, 13), radar_specs[i].b_high);
-
-		/* dfs width */
-		data = ((radar_specs[i].w_high & 0x0fff) << 16) |
-		       (radar_specs[i].w_low & 0x0fff);
-		mt76_wr(dev, MT_BBP(DFS, 14), data);
-
-		/* dfs margins */
-		data = (radar_specs[i].w_margin << 16) |
-		       radar_specs[i].t_margin;
-		mt76_wr(dev, MT_BBP(DFS, 15), data);
-
-		/* dfs event expiration */
-		mt76_wr(dev, MT_BBP(DFS, 17), radar_specs[i].event_expiration);
-
-		/* dfs pwr adj */
-		mt76_wr(dev, MT_BBP(DFS, 30), radar_specs[i].pwr_jmp);
-	}
-
-	/* reset status */
-	mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
-	mt76_wr(dev, MT_BBP(DFS, 36), 0x3);
-
-	/* enable detection*/
-	mt76_wr(dev, MT_BBP(DFS, 0), MT_DFS_CH_EN << 16);
-	mt76_wr(dev, 0x212c, 0x0c350001);
-}
-
-void mt76x2_dfs_init_params(struct mt76x02_dev *dev)
-{
-	struct cfg80211_chan_def *chandef = &dev->mt76.chandef;
-
-	if ((chandef->chan->flags & IEEE80211_CHAN_RADAR) &&
-	    dev->dfs_pd.region != NL80211_DFS_UNSET) {
-		mt76x2_dfs_init_sw_detector(dev);
-		mt76x2_dfs_set_bbp_params(dev);
-		/* enable debug mode */
-		mt76x2_dfs_set_capture_mode_ctrl(dev, true);
-
-		mt76x02_irq_enable(dev, MT_INT_GPTIMER);
-		mt76_rmw_field(dev, MT_INT_TIMER_EN,
-			       MT_INT_TIMER_EN_GP_TIMER_EN, 1);
-	} else {
-		/* disable hw detector */
-		mt76_wr(dev, MT_BBP(DFS, 0), 0);
-		/* clear detector status */
-		mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
-		mt76_wr(dev, 0x212c, 0);
-
-		mt76x02_irq_disable(dev, MT_INT_GPTIMER);
-		mt76_rmw_field(dev, MT_INT_TIMER_EN,
-			       MT_INT_TIMER_EN_GP_TIMER_EN, 0);
-	}
-}
-
-void mt76x2_dfs_init_detector(struct mt76x02_dev *dev)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-
-	INIT_LIST_HEAD(&dfs_pd->sequences);
-	INIT_LIST_HEAD(&dfs_pd->seq_pool);
-	dfs_pd->region = NL80211_DFS_UNSET;
-	dfs_pd->last_sw_check = jiffies;
-	tasklet_init(&dfs_pd->dfs_tasklet, mt76x2_dfs_tasklet,
-		     (unsigned long)dev);
-}
-
-void mt76x2_dfs_set_domain(struct mt76x02_dev *dev,
-			   enum nl80211_dfs_regions region)
-{
-	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
-
-	if (dfs_pd->region != region) {
-		tasklet_disable(&dfs_pd->dfs_tasklet);
-		dfs_pd->region = region;
-		mt76x2_dfs_init_params(dev);
-		tasklet_enable(&dfs_pd->dfs_tasklet);
-	}
-}
-
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 41c0cb62a919..b6144e03047f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -338,15 +338,6 @@ struct mt76x02_dev *mt76x2_alloc_device(struct device *pdev)
 	return dev;
 }
 
-static void mt76x2_regd_notifier(struct wiphy *wiphy,
-				 struct regulatory_request *request)
-{
-	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
-	struct mt76x02_dev *dev = hw->priv;
-
-	mt76x2_dfs_set_domain(dev, request->dfs_region);
-}
-
 static void mt76x2_led_set_config(struct mt76_dev *mt76, u8 delay_on,
 				  u8 delay_off)
 {
@@ -423,11 +414,11 @@ int mt76x2_register_device(struct mt76x02_dev *dev)
 	wiphy->addresses = dev->macaddr_list;
 	wiphy->n_addresses = ARRAY_SIZE(dev->macaddr_list);
 
-	wiphy->reg_notifier = mt76x2_regd_notifier;
+	wiphy->reg_notifier = mt76x02_regd_notifier;
 
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 
-	mt76x2_dfs_init_detector(dev);
+	mt76x02_dfs_init_detector(dev);
 
 	/* init led callbacks */
 	dev->mt76.led_cdev.brightness_set = mt76x2_led_set_brightness;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
index ec585b92d6c0..3d73926837bf 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
@@ -74,7 +74,7 @@ mt76x2_set_channel(struct mt76x02_dev *dev, struct cfg80211_chan_def *chandef)
 	mt76_rr(dev, MT_CH_IDLE);
 	mt76_rr(dev, MT_CH_BUSY);
 
-	mt76x2_dfs_init_params(dev);
+	mt76x02_dfs_init_params(dev);
 
 	mt76x2_mac_resume(dev);
 	tasklet_enable(&dev->dfs_pd.dfs_tasklet);
-- 
cgit v1.2.3


From 801ccc8a60381f76810b5da9b22f9fe47076a6e9 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 22 Oct 2018 23:42:13 +0200
Subject: mt76x0: pci: add DFS support

Introduce dfs support in mt76x0e driver and unlock radar channels

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c   | 11 ++++++--
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    |  4 +++
 drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c   | 31 ++++++++++++++++++++--
 drivers/net/wireless/mediatek/mt76/mt76x02_dfs.h   |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c  |  5 ++++
 .../net/wireless/mediatek/mt76/mt76x2/pci_init.c   |  7 -----
 drivers/net/wireless/mediatek/mt76/mt76x2/phy.c    | 23 +---------------
 7 files changed, 49 insertions(+), 33 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index cd1a1225ad8b..a803a9b6a4c5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -22,7 +22,10 @@ mt76x0_set_channel(struct mt76x02_dev *dev, struct cfg80211_chan_def *chandef)
 	int ret;
 
 	cancel_delayed_work_sync(&dev->cal_work);
-	tasklet_disable(&dev->pre_tbtt_tasklet);
+	if (mt76_is_mmio(dev)) {
+		tasklet_disable(&dev->pre_tbtt_tasklet);
+		tasklet_disable(&dev->dfs_pd.dfs_tasklet);
+	}
 
 	mt76_set_channel(&dev->mt76);
 	ret = mt76x0_phy_set_channel(dev, chandef);
@@ -31,7 +34,11 @@ mt76x0_set_channel(struct mt76x02_dev *dev, struct cfg80211_chan_def *chandef)
 	mt76_rr(dev, MT_CH_IDLE);
 	mt76_rr(dev, MT_CH_BUSY);
 
-	tasklet_enable(&dev->pre_tbtt_tasklet);
+	if (mt76_is_mmio(dev)) {
+		mt76x02_dfs_init_params(dev);
+		tasklet_enable(&dev->pre_tbtt_tasklet);
+		tasklet_enable(&dev->dfs_pd.dfs_tasklet);
+	}
 	mt76_txq_schedule_all(&dev->mt76);
 
 	return ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index b33074b783dc..c734987a344c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -719,6 +719,10 @@ static void mt76x0_phy_set_gain_val(struct mt76x02_dev *dev)
 
 	mt76_wr(dev, MT_BBP(AGC, 8),
 		val | FIELD_PREP(MT_BBP_AGC_GAIN, gain));
+
+	if ((dev->mt76.chandef.chan->flags & IEEE80211_CHAN_RADAR) &&
+	    !is_mt7630(dev))
+		mt76x02_phy_dfs_adjust_agc(dev);
 }
 
 static void
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
index 21e7b8c9f824..527e530d480a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
@@ -802,6 +802,35 @@ static void mt76x02_dfs_set_bbp_params(struct mt76x02_dev *dev)
 	mt76_wr(dev, 0x212c, 0x0c350001);
 }
 
+void mt76x02_phy_dfs_adjust_agc(struct mt76x02_dev *dev)
+{
+	u32 agc_r8, agc_r4, val_r8, val_r4, dfs_r31;
+
+	agc_r8 = mt76_rr(dev, MT_BBP(AGC, 8));
+	agc_r4 = mt76_rr(dev, MT_BBP(AGC, 4));
+
+	val_r8 = (agc_r8 & 0x00007e00) >> 9;
+	val_r4 = agc_r4 & ~0x1f000000;
+	val_r4 += (((val_r8 + 1) >> 1) << 24);
+	mt76_wr(dev, MT_BBP(AGC, 4), val_r4);
+
+	dfs_r31 = FIELD_GET(MT_BBP_AGC_LNA_HIGH_GAIN, val_r4);
+	dfs_r31 += val_r8;
+	dfs_r31 -= (agc_r8 & 0x00000038) >> 3;
+	dfs_r31 = (dfs_r31 << 16) | 0x00000307;
+	mt76_wr(dev, MT_BBP(DFS, 31), dfs_r31);
+
+	if (is_mt76x2(dev)) {
+		mt76_wr(dev, MT_BBP(DFS, 32), 0x00040071);
+	} else {
+		/* disable hw detector */
+		mt76_wr(dev, MT_BBP(DFS, 0), 0);
+		/* enable hw detector */
+		mt76_wr(dev, MT_BBP(DFS, 0), MT_DFS_CH_EN << 16);
+	}
+}
+EXPORT_SYMBOL_GPL(mt76x02_phy_dfs_adjust_agc);
+
 void mt76x02_dfs_init_params(struct mt76x02_dev *dev)
 {
 	struct cfg80211_chan_def *chandef = &dev->mt76.chandef;
@@ -841,7 +870,6 @@ void mt76x02_dfs_init_detector(struct mt76x02_dev *dev)
 	tasklet_init(&dfs_pd->dfs_tasklet, mt76x02_dfs_tasklet,
 		     (unsigned long)dev);
 }
-EXPORT_SYMBOL_GPL(mt76x02_dfs_init_detector);
 
 static void
 mt76x02_dfs_set_domain(struct mt76x02_dev *dev,
@@ -865,4 +893,3 @@ void mt76x02_regd_notifier(struct wiphy *wiphy,
 
 	mt76x02_dfs_set_domain(dev, request->dfs_region);
 }
-EXPORT_SYMBOL_GPL(mt76x02_regd_notifier);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.h b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.h
index 59e1524ff98b..70b394e17340 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.h
@@ -141,4 +141,5 @@ void mt76x02_dfs_init_params(struct mt76x02_dev *dev);
 void mt76x02_dfs_init_detector(struct mt76x02_dev *dev);
 void mt76x02_regd_notifier(struct wiphy *wiphy,
 			   struct regulatory_request *request);
+void mt76x02_phy_dfs_adjust_agc(struct mt76x02_dev *dev);
 #endif /* __MT76x02_DFS_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 4c3b8392b2b7..9f083008dbd4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -93,6 +93,9 @@ void mt76x02_init_device(struct mt76x02_dev *dev)
 					 MT_DMA_HDR_LEN;
 		wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
 	} else {
+		mt76x02_dfs_init_detector(dev);
+
+		wiphy->reg_notifier = mt76x02_regd_notifier;
 		wiphy->iface_combinations = mt76x02_if_comb;
 		wiphy->n_iface_combinations = ARRAY_SIZE(mt76x02_if_comb);
 		wiphy->interface_modes =
@@ -635,6 +638,8 @@ void mt76x02_init_beacon_config(struct mt76x02_dev *dev)
 	/* Fire a pre-TBTT interrupt 8 ms before TBTT */
 	mt76_rmw_field(dev, MT_INT_TIMER_CFG, MT_INT_TIMER_CFG_PRE_TBTT,
 		       8 << 4);
+	mt76_rmw_field(dev, MT_INT_TIMER_CFG, MT_INT_TIMER_CFG_GP_TIMER,
+		       MT_DFS_GP_INTERVAL);
 	mt76_wr(dev, MT_INT_TIMER_EN, 0);
 
 	mt76_wr(dev, MT_BCN_BYPASS_MASK, 0xffff);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index b6144e03047f..f6e8af6432c1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -122,9 +122,6 @@ static int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard)
 	mt76_wr(dev, MT_MAC_ADDR_DW0, get_unaligned_le32(macaddr));
 	mt76_wr(dev, MT_MAC_ADDR_DW1, get_unaligned_le16(macaddr + 4));
 
-	mt76_rmw_field(dev, MT_INT_TIMER_CFG, MT_INT_TIMER_CFG_GP_TIMER,
-		       MT_DFS_GP_INTERVAL);
-
 	mt76x02_init_beacon_config(dev);
 	if (!hard)
 		return 0;
@@ -414,12 +411,8 @@ int mt76x2_register_device(struct mt76x02_dev *dev)
 	wiphy->addresses = dev->macaddr_list;
 	wiphy->n_addresses = ARRAY_SIZE(dev->macaddr_list);
 
-	wiphy->reg_notifier = mt76x02_regd_notifier;
-
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 
-	mt76x02_dfs_init_detector(dev);
-
 	/* init led callbacks */
 	dev->mt76.led_cdev.brightness_set = mt76x2_led_set_brightness;
 	dev->mt76.led_cdev.blink_set = mt76x2_led_set_blink;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
index 0f9f54569147..bbeff9c19997 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
@@ -251,27 +251,6 @@ void mt76x2_phy_tssi_compensate(struct mt76x02_dev *dev, bool wait)
 }
 EXPORT_SYMBOL_GPL(mt76x2_phy_tssi_compensate);
 
-static void mt76x2_phy_dfs_adjust_agc(struct mt76x02_dev *dev)
-{
-	u32 agc_r8, agc_r4, val_r8, val_r4, dfs_r31;
-
-	agc_r8 = mt76_rr(dev, MT_BBP(AGC, 8));
-	agc_r4 = mt76_rr(dev, MT_BBP(AGC, 4));
-
-	val_r8 = (agc_r8 & 0x00007e00) >> 9;
-	val_r4 = agc_r4 & ~0x1f000000;
-	val_r4 += (((val_r8 + 1) >> 1) << 24);
-	mt76_wr(dev, MT_BBP(AGC, 4), val_r4);
-
-	dfs_r31 = FIELD_GET(MT_BBP_AGC_LNA_HIGH_GAIN, val_r4);
-	dfs_r31 += val_r8;
-	dfs_r31 -= (agc_r8 & 0x00000038) >> 3;
-	dfs_r31 = (dfs_r31 << 16) | 0x00000307;
-	mt76_wr(dev, MT_BBP(DFS, 31), dfs_r31);
-
-	mt76_wr(dev, MT_BBP(DFS, 32), 0x00040071);
-}
-
 static void
 mt76x2_phy_set_gain_val(struct mt76x02_dev *dev)
 {
@@ -294,7 +273,7 @@ mt76x2_phy_set_gain_val(struct mt76x02_dev *dev)
 		val | FIELD_PREP(MT_BBP_AGC_GAIN, gain_val[1]));
 
 	if (dev->mt76.chandef.chan->flags & IEEE80211_CHAN_RADAR)
-		mt76x2_phy_dfs_adjust_agc(dev);
+		mt76x02_phy_dfs_adjust_agc(dev);
 }
 
 void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev)
-- 
cgit v1.2.3


From 1a4846fcfed6d7cf902719ad0cd1fe8eaf7b3f91 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 24 Oct 2018 17:57:10 +0200
Subject: mt76: clean up more unused EXPORT_SYMBOLs

Make functions static where possible

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c  | 9 +--------
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.h  | 1 -
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c | 1 -
 3 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index 4fb9f095ffec..34fc9f2eb51f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -128,7 +128,6 @@ void mt76x02_mac_wcid_set_drop(struct mt76x02_dev *dev, u8 idx, bool drop)
 	if ((val & bit) != (bit * drop))
 		mt76_wr(dev, MT_WCID_DROP(idx), (val & ~bit) | (bit * drop));
 }
-EXPORT_SYMBOL_GPL(mt76x02_mac_wcid_set_drop);
 
 void mt76x02_txq_init(struct mt76x02_dev *dev, struct ieee80211_txq *txq)
 {
@@ -220,7 +219,6 @@ void mt76x02_mac_set_short_preamble(struct mt76x02_dev *dev, bool enable)
 	else
 		mt76_clear(dev, MT_AUTO_RSP_CFG, MT_AUTO_RSP_PREAMB_SHORT);
 }
-EXPORT_SYMBOL_GPL(mt76x02_mac_set_short_preamble);
 
 bool mt76x02_mac_load_tx_status(struct mt76x02_dev *dev,
 				struct mt76x02_tx_status *stat)
@@ -491,7 +489,7 @@ out:
 	rcu_read_unlock();
 }
 
-int
+static int
 mt76x02_mac_process_rate(struct mt76_rx_status *status, u16 rate)
 {
 	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
@@ -557,7 +555,6 @@ mt76x02_mac_process_rate(struct mt76_rx_status *status, u16 rate)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mt76x02_mac_process_rate);
 
 void mt76x02_mac_setaddr(struct mt76x02_dev *dev, u8 *addr)
 {
@@ -823,7 +820,6 @@ void mt76x02_mac_work(struct work_struct *work)
 	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mac_work,
 				     MT_CALIBRATE_INTERVAL);
 }
-EXPORT_SYMBOL_GPL(mt76x02_mac_work);
 
 void mt76x02_mac_set_bssid(struct mt76x02_dev *dev, u8 idx, const u8 *addr)
 {
@@ -832,7 +828,6 @@ void mt76x02_mac_set_bssid(struct mt76x02_dev *dev, u8 idx, const u8 *addr)
 	mt76_rmw_field(dev, MT_MAC_APC_BSSID_H(idx), MT_MAC_APC_BSSID_H_ADDR,
 		       get_unaligned_le16(addr + 4));
 }
-EXPORT_SYMBOL_GPL(mt76x02_mac_set_bssid);
 
 static int
 mt76x02_write_beacon(struct mt76x02_dev *dev, int offset, struct sk_buff *skb)
@@ -914,7 +909,6 @@ int mt76x02_mac_set_beacon(struct mt76x02_dev *dev, u8 vif_idx,
 		       bcn_idx - 1);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mt76x02_mac_set_beacon);
 
 void mt76x02_mac_set_beacon_enable(struct mt76x02_dev *dev,
 				   u8 vif_idx, bool val)
@@ -946,4 +940,3 @@ void mt76x02_mac_set_beacon_enable(struct mt76x02_dev *dev,
 	else
 		mt76x02_irq_disable(dev, MT_INT_PRE_TBTT | MT_INT_TBTT);
 }
-EXPORT_SYMBOL_GPL(mt76x02_mac_set_beacon_enable);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index f65157600779..e2c47ca18d85 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -216,7 +216,6 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 			    struct mt76x02_tx_status *stat, u8 *update);
 int mt76x02_mac_process_rx(struct mt76x02_dev *dev, struct sk_buff *skb,
 			   void *rxi);
-int mt76x02_mac_process_rate(struct mt76_rx_status *status, u16 rate);
 void mt76x02_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val);
 void mt76x02_mac_setaddr(struct mt76x02_dev *dev, u8 *addr);
 void mt76x02_mac_write_txwi(struct mt76x02_dev *dev, struct mt76x02_txwi *txwi,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 9f083008dbd4..c0f923942edc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -606,7 +606,6 @@ const u16 mt76x02_beacon_offsets[16] = {
 	0xc000,
 	0xc000,
 };
-EXPORT_SYMBOL_GPL(mt76x02_beacon_offsets);
 
 static void mt76x02_set_beacon_offsets(struct mt76x02_dev *dev)
 {
-- 
cgit v1.2.3


From 65b526a108264aeac769ec82cf33e5f966c9a1df Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 25 Oct 2018 14:23:13 +0200
Subject: mt76: mt76x02: skip station tx status for non-sta wcid entries

Fixes a crash that could occur if a frame is sent to a station, but the
station's wcid was not used (e.g. for software encrypted mgmt tx)

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index 34fc9f2eb51f..ad8df680c6a5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -450,7 +450,7 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 	if (stat->wcid < ARRAY_SIZE(dev->mt76.wcid))
 		wcid = rcu_dereference(dev->mt76.wcid[stat->wcid]);
 
-	if (wcid) {
+	if (wcid && wcid->sta) {
 		void *priv;
 
 		priv = msta = container_of(wcid, struct mt76x02_sta, wcid);
-- 
cgit v1.2.3


From 59b55d066ff625f8613c563bd2ed705bce412fa8 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 25 Oct 2018 17:40:06 +0200
Subject: mt76: mt76x02: only override control->sta on sw-encrypted tx

control->sta is set to NULL early when encryption is turned on for the
station and info->control.hw_key is not set.
This code is missing a check for the 802.11 header protected flag, otherwise
it resets the station for other frames, e.g. client probing frames.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c b/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c
index 7ec3f8f5f228..c008e08602f3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c
@@ -22,6 +22,7 @@
 void mt76x02_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
 		struct sk_buff *skb)
 {
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct mt76x02_dev *dev = hw->priv;
 	struct ieee80211_vif *vif = info->control.vif;
@@ -33,7 +34,8 @@ void mt76x02_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
 		msta = (struct mt76x02_sta *)control->sta->drv_priv;
 		wcid = &msta->wcid;
 		/* sw encrypted frames */
-		if (!info->control.hw_key && wcid->hw_key_idx != 0xff)
+		if (!info->control.hw_key && wcid->hw_key_idx != 0xff &&
+		    ieee80211_has_protected(hdr->frame_control))
 			control->sta = NULL;
 	}
 
-- 
cgit v1.2.3


From 88046b2c9f6d8b91cc8b3ada547f49f6dd45469b Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 25 Oct 2018 16:11:34 +0200
Subject: mt76: add support for reporting tx status with skb

MT76x2/MT76x0 has somewhat unreliable tx status reporting, and for that
reason the driver currently does not report per-skb tx ack status at all.
This breaks things like client idle polling, which relies on the tx ack
status of a transmitted nullfunc frame.

This patch adds code to report skb-attached tx status if requested by
mac80211 or the rate control module. Since tx status is polled from a
simple FIFO register, the code needs to account for the possibility of
tx status events getting lost.

The code keeps a list of skbs for which tx status is required and passes
them to mac80211 once tx status has been filled in and the DMA queue is
done with it.
If a tx status event is not received after one second, the status rates
are cleared, and a succesful ACK is indicated to avoid spurious disassoc
during assoc or client polling.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/dma.c           |   1 +
 drivers/net/wireless/mediatek/mt76/mac80211.c      |   3 +
 drivers/net/wireless/mediatek/mt76/mt76.h          |  48 +++++++++
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |   1 -
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c   |  74 +++++++-------
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.h   |  19 ----
 drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c  |  25 ++---
 .../net/wireless/mediatek/mt76/mt76x02_usb_core.c  |  42 ++++----
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c  |   1 +
 drivers/net/wireless/mediatek/mt76/tx.c            | 111 +++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/usb.c           |   1 +
 11 files changed, 231 insertions(+), 95 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index f7fbd7016403..2d7bd26875c6 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -258,6 +258,7 @@ int mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
 		return -ENOMEM;
 	}
 
+	skb->prev = skb->next = NULL;
 	dma_sync_single_for_cpu(dev->dev, t->dma_addr, sizeof(t->txwi),
 				DMA_TO_DEVICE);
 	ret = dev->drv->tx_prepare_skb(dev, &t->txwi, skb, q, wcid, sta,
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 2a699e8b79bf..85e05a825b5d 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -285,6 +285,7 @@ mt76_alloc_device(unsigned int size, const struct ieee80211_ops *ops)
 	spin_lock_init(&dev->cc_lock);
 	mutex_init(&dev->mutex);
 	init_waitqueue_head(&dev->tx_wait);
+	skb_queue_head_init(&dev->status_list);
 
 	return dev;
 }
@@ -326,6 +327,7 @@ int mt76_register_device(struct mt76_dev *dev, bool vht,
 	ieee80211_hw_set(hw, TX_FRAG_LIST);
 	ieee80211_hw_set(hw, MFP_CAPABLE);
 	ieee80211_hw_set(hw, AP_LINK_PS);
+	ieee80211_hw_set(hw, REPORTS_TX_ACK_STATUS);
 
 	wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
 
@@ -357,6 +359,7 @@ void mt76_unregister_device(struct mt76_dev *dev)
 {
 	struct ieee80211_hw *hw = dev->hw;
 
+	mt76_tx_status_flush(dev, NULL);
 	ieee80211_unregister_hw(hw);
 	mt76_tx_free(dev);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 53ddc4fa5884..94ab00b549af 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -195,6 +195,8 @@ struct mt76_wcid {
 	u8 tx_rate_nss;
 	s8 max_txpwr_adj;
 	bool sw_iv;
+
+	u8 packet_id;
 };
 
 struct mt76_txq {
@@ -233,6 +235,22 @@ struct mt76_rx_tid {
 	struct sk_buff *reorder_buf[];
 };
 
+#define MT_TX_CB_DMA_DONE		BIT(0)
+#define MT_TX_CB_TXS_DONE		BIT(1)
+#define MT_TX_CB_TXS_FAILED		BIT(2)
+
+#define MT_PACKET_ID_MASK		GENMASK(7, 0)
+#define MT_PACKET_ID_NO_ACK		MT_PACKET_ID_MASK
+
+#define MT_TX_STATUS_SKB_TIMEOUT	HZ
+
+struct mt76_tx_cb {
+	unsigned long jiffies;
+	u8 wcid;
+	u8 pktid;
+	u8 flags;
+};
+
 enum {
 	MT76_STATE_INITIALIZED,
 	MT76_STATE_RUNNING,
@@ -400,6 +418,7 @@ struct mt76_dev {
 	const struct mt76_queue_ops *queue_ops;
 
 	wait_queue_head_t tx_wait;
+	struct sk_buff_head status_list;
 
 	unsigned long wcid_mask[MT76_N_WCIDS / BITS_PER_LONG];
 
@@ -594,6 +613,13 @@ wcid_to_sta(struct mt76_wcid *wcid)
 	return container_of(ptr, struct ieee80211_sta, drv_priv);
 }
 
+static inline struct mt76_tx_cb *mt76_tx_skb_cb(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(struct mt76_tx_cb) >
+		     sizeof(IEEE80211_SKB_CB(skb)->status.status_driver_data));
+	return ((void *) IEEE80211_SKB_CB(skb)->status.status_driver_data);
+}
+
 int mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
 			  struct sk_buff *skb, struct mt76_wcid *wcid,
 			  struct ieee80211_sta *sta);
@@ -624,6 +650,28 @@ void mt76_rx_aggr_stop(struct mt76_dev *dev, struct mt76_wcid *wcid, u8 tid);
 
 void mt76_wcid_key_setup(struct mt76_dev *dev, struct mt76_wcid *wcid,
 			 struct ieee80211_key_conf *key);
+int mt76_tx_status_skb_add(struct mt76_dev *dev, struct mt76_wcid *wcid,
+			   struct sk_buff *skb);
+struct sk_buff *mt76_tx_status_skb_get(struct mt76_dev *dev,
+				       struct mt76_wcid *wcid, int pktid);
+void mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb);
+void mt76_tx_complete_skb(struct mt76_dev *dev, struct sk_buff *skb);
+
+static inline void
+mt76_tx_status_check(struct mt76_dev *dev)
+{
+	spin_lock_bh(&dev->status_list.lock);
+	mt76_tx_status_skb_get(dev, NULL, 0);
+	spin_unlock_bh(&dev->status_list.lock);
+}
+
+static inline void
+mt76_tx_status_flush(struct mt76_dev *dev, struct mt76_wcid *wcid)
+{
+	spin_lock_bh(&dev->status_list.lock);
+	mt76_tx_status_skb_get(dev, wcid, -1);
+	spin_unlock_bh(&dev->status_list.lock);
+}
 
 struct ieee80211_sta *mt76_rx_convert(struct sk_buff *skb);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index d599b7dddac7..19489a72fc2b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -139,7 +139,6 @@ void mt76x02_set_coverage_class(struct ieee80211_hw *hw,
 int mt76x02_set_rts_threshold(struct ieee80211_hw *hw, u32 val);
 int mt76x02_insert_hdr_pad(struct sk_buff *skb);
 void mt76x02_remove_hdr_pad(struct sk_buff *skb, int len);
-void mt76x02_tx_complete(struct mt76_dev *dev, struct sk_buff *skb);
 bool mt76x02_tx_status_data(struct mt76_dev *mdev, u8 *update);
 void mt76x02_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			  struct sk_buff *skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index ad8df680c6a5..90d24af7f6c8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -324,8 +324,6 @@ void mt76x02_mac_write_txwi(struct mt76x02_dev *dev, struct mt76x02_txwi *txwi,
 	else
 		txwi->wcid = 0xff;
 
-	txwi->pktid = 1;
-
 	if (wcid && wcid->sw_iv && key) {
 		u64 pn = atomic64_inc_return(&key->tx_pn);
 		ccmp_pn[0] = pn;
@@ -371,8 +369,6 @@ void mt76x02_mac_write_txwi(struct mt76x02_dev *dev, struct mt76x02_txwi *txwi,
 		txwi->ack_ctl |= MT_TXWI_ACK_CTL_REQ;
 	if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)
 		txwi->ack_ctl |= MT_TXWI_ACK_CTL_NSEQ;
-	if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
-		txwi->pktid |= MT_TXWI_PKTID_PROBE;
 	if ((info->flags & IEEE80211_TX_CTL_AMPDU) && sta) {
 		u8 ba_size = IEEE80211_MIN_AMPDU_BUF;
 
@@ -425,9 +421,6 @@ mt76x02_mac_fill_tx_status(struct mt76x02_dev *dev,
 	info->status.ampdu_len = n_frames;
 	info->status.ampdu_ack_len = st->success ? n_frames : 0;
 
-	if (st->pktid & MT_TXWI_PKTID_PROBE)
-		info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
-
 	if (st->aggr)
 		info->flags |= IEEE80211_TX_CTL_AMPDU |
 			       IEEE80211_TX_STAT_AMPDU;
@@ -442,11 +435,19 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 			    struct mt76x02_tx_status *stat, u8 *update)
 {
 	struct ieee80211_tx_info info = {};
-	struct ieee80211_sta *sta = NULL;
+	struct ieee80211_tx_status status = {
+		.info = &info
+	};
 	struct mt76_wcid *wcid = NULL;
 	struct mt76x02_sta *msta = NULL;
+	struct mt76_dev *mdev = &dev->mt76;
+
+	if (stat->pktid == MT_PACKET_ID_NO_ACK)
+		return;
 
 	rcu_read_lock();
+	spin_lock_bh(&mdev->status_list.lock);
+
 	if (stat->wcid < ARRAY_SIZE(dev->mt76.wcid))
 		wcid = rcu_dereference(dev->mt76.wcid[stat->wcid]);
 
@@ -454,11 +455,19 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 		void *priv;
 
 		priv = msta = container_of(wcid, struct mt76x02_sta, wcid);
-		sta = container_of(priv, struct ieee80211_sta,
-				   drv_priv);
+		status.sta = container_of(priv, struct ieee80211_sta,
+					  drv_priv);
+	}
+
+	if (wcid) {
+		if (stat->pktid)
+			status.skb = mt76_tx_status_skb_get(mdev, wcid,
+							    stat->pktid);
+		if (status.skb)
+			status.info = IEEE80211_SKB_CB(status.skb);
 	}
 
-	if (msta && stat->aggr) {
+	if (msta && stat->aggr && !status.skb) {
 		u32 stat_val, stat_cache;
 
 		stat_val = stat->rate;
@@ -472,20 +481,24 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 			goto out;
 		}
 
-		mt76x02_mac_fill_tx_status(dev, &info, &msta->status,
+		mt76x02_mac_fill_tx_status(dev, status.info, &msta->status,
 					   msta->n_frames);
 
 		msta->status = *stat;
 		msta->n_frames = 1;
 		*update = 0;
 	} else {
-		mt76x02_mac_fill_tx_status(dev, &info, stat, 1);
+		mt76x02_mac_fill_tx_status(dev, status.info, stat, 1);
 		*update = 1;
 	}
 
-	ieee80211_tx_status_noskb(dev->mt76.hw, sta, &info);
+	if (status.skb)
+		mt76_tx_status_skb_done(mdev, status.skb);
+	else
+		ieee80211_tx_status_ext(mt76_hw(dev), &status);
 
 out:
+	spin_unlock_bh(&mdev->status_list.lock);
 	rcu_read_unlock();
 }
 
@@ -707,32 +720,23 @@ void mt76x02_mac_poll_tx_status(struct mt76x02_dev *dev, bool irq)
 	}
 }
 
-static void
-mt76x02_mac_queue_txdone(struct mt76x02_dev *dev, struct sk_buff *skb,
-			 void *txwi_ptr)
-{
-	struct mt76x02_tx_info *txi = mt76x02_skb_tx_info(skb);
-	struct mt76x02_txwi *txwi = txwi_ptr;
-
-	mt76x02_mac_poll_tx_status(dev, false);
-
-	txi->tries = 0;
-	txi->jiffies = jiffies;
-	txi->wcid = txwi->wcid;
-	txi->pktid = txwi->pktid;
-	trace_mac_txdone_add(dev, txwi->wcid, txwi->pktid);
-	mt76x02_tx_complete(&dev->mt76, skb);
-}
-
 void mt76x02_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
 			     struct mt76_queue_entry *e, bool flush)
 {
 	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
+	struct mt76x02_txwi *txwi;
 
-	if (e->txwi)
-		mt76x02_mac_queue_txdone(dev, e->skb, &e->txwi->txwi);
-	else
+	if (!e->txwi) {
 		dev_kfree_skb_any(e->skb);
+		return;
+	}
+
+	mt76x02_mac_poll_tx_status(dev, false);
+
+	txwi = (struct mt76x02_txwi *) &e->txwi->txwi;
+	trace_mac_txdone_add(dev, txwi->wcid, txwi->pktid);
+
+	mt76_tx_complete_skb(mdev, e->skb);
 }
 EXPORT_SYMBOL_GPL(mt76x02_tx_complete_skb);
 
@@ -817,6 +821,8 @@ void mt76x02_mac_work(struct work_struct *work)
 	if (!dev->beacon_mask)
 		mt76x02_check_mac_err(dev);
 
+	mt76_tx_status_check(&dev->mt76);
+
 	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mac_work,
 				     MT_CALIBRATE_INTERVAL);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index e2c47ca18d85..b076c4305585 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -42,15 +42,6 @@ struct mt76x02_vif {
 	struct mt76_wcid group_wcid;
 };
 
-struct mt76x02_tx_info {
-	unsigned long jiffies;
-	u8 tries;
-
-	u8 wcid;
-	u8 pktid;
-	u8 retry;
-};
-
 DECLARE_EWMA(signal, 10, 8);
 
 struct mt76x02_sta {
@@ -153,8 +144,6 @@ enum mt76x2_phy_bandwidth {
 #define MT_TXWI_ACK_CTL_NSEQ		BIT(1)
 #define MT_TXWI_ACK_CTL_BA_WINDOW	GENMASK(7, 2)
 
-#define MT_TXWI_PKTID_PROBE		BIT(7)
-
 struct mt76x02_txwi {
 	__le16 flags;
 	__le16 rate;
@@ -190,14 +179,6 @@ static inline bool mt76x02_wait_for_mac(struct mt76_dev *dev)
 	return false;
 }
 
-static inline struct mt76x02_tx_info *
-mt76x02_skb_tx_info(struct sk_buff *skb)
-{
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-
-	return (void *)info->status.status_driver_data;
-}
-
 void mt76x02_txq_init(struct mt76x02_dev *dev, struct ieee80211_txq *txq);
 
 void mt76x02_mac_set_short_preamble(struct mt76x02_dev *dev, bool enable);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c b/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c
index c008e08602f3..4598cb2cc3ff 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c
@@ -140,21 +140,6 @@ void mt76x02_tx_set_txpwr_auto(struct mt76x02_dev *dev, s8 txpwr)
 }
 EXPORT_SYMBOL_GPL(mt76x02_tx_set_txpwr_auto);
 
-void mt76x02_tx_complete(struct mt76_dev *dev, struct sk_buff *skb)
-{
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-
-	if (info->flags & IEEE80211_TX_CTL_AMPDU) {
-		ieee80211_free_txskb(dev->hw, skb);
-	} else {
-		ieee80211_tx_info_clear_status(info);
-		info->status.rates[0].idx = -1;
-		info->flags |= IEEE80211_TX_STAT_ACK;
-		ieee80211_tx_status(dev->hw, skb);
-	}
-}
-EXPORT_SYMBOL_GPL(mt76x02_tx_complete);
-
 bool mt76x02_tx_status_data(struct mt76_dev *mdev, u8 *update)
 {
 	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
@@ -169,14 +154,15 @@ bool mt76x02_tx_status_data(struct mt76_dev *mdev, u8 *update)
 }
 EXPORT_SYMBOL_GPL(mt76x02_tx_status_data);
 
-int mt76x02_tx_prepare_skb(struct mt76_dev *mdev, void *txwi,
+int mt76x02_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			   struct sk_buff *skb, struct mt76_queue *q,
 			   struct mt76_wcid *wcid, struct ieee80211_sta *sta,
 			   u32 *tx_info)
 {
 	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct mt76x02_txwi *txwi = txwi_ptr;
 	int qsel = MT_QSEL_EDCA;
+	int pid;
 	int ret;
 
 	if (q == &dev->mt76.q_tx[MT_TXQ_PSD] && wcid && wcid->idx < 128)
@@ -184,11 +170,14 @@ int mt76x02_tx_prepare_skb(struct mt76_dev *mdev, void *txwi,
 
 	mt76x02_mac_write_txwi(dev, txwi, skb, wcid, sta, skb->len);
 
+	pid = mt76_tx_status_skb_add(mdev, wcid, skb);
+	txwi->pktid = pid;
+
 	ret = mt76x02_insert_hdr_pad(skb);
 	if (ret < 0)
 		return ret;
 
-	if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
+	if (pid && pid != MT_PACKET_ID_NO_ACK)
 		qsel = MT_QSEL_MGMT;
 
 	*tx_info = FIELD_PREP(MT_TXD_INFO_QSEL, qsel) |
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
index dc2226c722dd..81970cf777c0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
@@ -30,7 +30,7 @@ void mt76x02u_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
 			      struct mt76_queue_entry *e, bool flush)
 {
 	mt76x02u_remove_dma_hdr(e->skb);
-	mt76x02_tx_complete(mdev, e->skb);
+	mt76_tx_complete_skb(mdev, e->skb);
 }
 EXPORT_SYMBOL_GPL(mt76x02u_tx_complete_skb);
 
@@ -67,27 +67,6 @@ int mt76x02u_skb_dma_info(struct sk_buff *skb, int port, u32 flags)
 	return 0;
 }
 
-static int
-mt76x02u_set_txinfo(struct sk_buff *skb, struct mt76_wcid *wcid, u8 ep)
-{
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	enum mt76_qsel qsel;
-	u32 flags;
-
-	if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) ||
-	    ep == MT_EP_OUT_HCCA)
-		qsel = MT_QSEL_MGMT;
-	else
-		qsel = MT_QSEL_EDCA;
-
-	flags = FIELD_PREP(MT_TXD_INFO_QSEL, qsel) |
-		MT_TXD_INFO_80211;
-	if (!wcid || wcid->hw_key_idx == 0xff || wcid->sw_iv)
-		flags |= MT_TXD_INFO_WIV;
-
-	return mt76x02u_skb_dma_info(skb, WLAN_PORT, flags);
-}
-
 int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
 			    struct sk_buff *skb, struct mt76_queue *q,
 			    struct mt76_wcid *wcid, struct ieee80211_sta *sta,
@@ -95,13 +74,30 @@ int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
 {
 	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
 	struct mt76x02_txwi *txwi;
+	enum mt76_qsel qsel;
 	int len = skb->len;
+	u32 flags;
+	int pid;
 
 	mt76x02_insert_hdr_pad(skb);
 
 	txwi = skb_push(skb, sizeof(struct mt76x02_txwi));
 	mt76x02_mac_write_txwi(dev, txwi, skb, wcid, sta, len);
 
-	return mt76x02u_set_txinfo(skb, wcid, q2ep(q->hw_idx));
+	pid = mt76_tx_status_skb_add(mdev, wcid, skb);
+	txwi->pktid = pid;
+
+	if ((pid && pid != MT_PACKET_ID_NO_ACK) ||
+	    q2ep(q->hw_idx) == MT_EP_OUT_HCCA)
+		qsel = MT_QSEL_MGMT;
+	else
+		qsel = MT_QSEL_EDCA;
+
+	flags = FIELD_PREP(MT_TXD_INFO_QSEL, qsel) |
+		MT_TXD_INFO_80211;
+	if (!wcid || wcid->hw_key_idx == 0xff || wcid->sw_iv)
+		flags |= MT_TXD_INFO_WIV;
+
+	return mt76x02u_skb_dma_info(skb, WLAN_PORT, flags);
 }
 EXPORT_SYMBOL_GPL(mt76x02u_tx_prepare_skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index c0f923942edc..adfc46419b6b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -215,6 +215,7 @@ int mt76x02_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	int i;
 
 	mutex_lock(&dev->mt76.mutex);
+	mt76_tx_status_flush(&dev->mt76, &msta->wcid);
 	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
 	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
 		mt76_txq_remove(&dev->mt76, sta->txq[i]);
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index 7cbce03aa65b..e6cd583aafd3 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -103,6 +103,117 @@ mt76_check_agg_ssn(struct mt76_txq *mtxq, struct sk_buff *skb)
 	mtxq->agg_ssn = le16_to_cpu(hdr->seq_ctrl) + 0x10;
 }
 
+static void
+__mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb, u8 flags)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct mt76_tx_cb *cb = mt76_tx_skb_cb(skb);
+	u8 done = MT_TX_CB_DMA_DONE | MT_TX_CB_TXS_DONE;
+
+	flags |= cb->flags;
+	cb->flags = flags;
+
+	if ((flags & done) != done)
+		return;
+
+	__skb_unlink(skb, &dev->status_list);
+
+	/* Tx status can be unreliable. if it fails, mark the frame as ACKed */
+	if (flags & MT_TX_CB_TXS_FAILED) {
+		ieee80211_tx_info_clear_status(info);
+		info->status.rates[0].idx = -1;
+		info->flags |= IEEE80211_TX_STAT_ACK;
+	}
+
+	ieee80211_tx_status(dev->hw, skb);
+}
+
+void
+mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb)
+{
+	__mt76_tx_status_skb_done(dev, skb, MT_TX_CB_TXS_DONE);
+}
+EXPORT_SYMBOL_GPL(mt76_tx_status_skb_done);
+
+int
+mt76_tx_status_skb_add(struct mt76_dev *dev, struct mt76_wcid *wcid,
+		       struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct mt76_tx_cb *cb = mt76_tx_skb_cb(skb);
+	int pid;
+
+	if (!wcid)
+		return 0;
+
+	if (info->flags & IEEE80211_TX_CTL_NO_ACK)
+		return MT_PACKET_ID_NO_ACK;
+
+	if (!(info->flags & (IEEE80211_TX_CTL_REQ_TX_STATUS |
+			     IEEE80211_TX_CTL_RATE_CTRL_PROBE)))
+		return 0;
+
+	spin_lock_bh(&dev->status_list.lock);
+
+	memset(cb, 0, sizeof(*cb));
+	wcid->packet_id = (wcid->packet_id + 1) & MT_PACKET_ID_MASK;
+	if (!wcid->packet_id || wcid->packet_id == MT_PACKET_ID_NO_ACK)
+		wcid->packet_id = 1;
+
+	pid = wcid->packet_id;
+	cb->wcid = wcid->idx;
+	cb->pktid = pid;
+	cb->jiffies = jiffies;
+
+	__skb_queue_tail(&dev->status_list, skb);
+	spin_unlock_bh(&dev->status_list.lock);
+
+	return pid;
+}
+EXPORT_SYMBOL_GPL(mt76_tx_status_skb_add);
+
+struct sk_buff *
+mt76_tx_status_skb_get(struct mt76_dev *dev, struct mt76_wcid *wcid, int pktid)
+{
+	struct sk_buff *skb, *tmp;
+
+	if (pktid == MT_PACKET_ID_NO_ACK)
+		return NULL;
+
+	skb_queue_walk_safe(&dev->status_list, skb, tmp) {
+		struct mt76_tx_cb *cb = mt76_tx_skb_cb(skb);
+
+		if (wcid && cb->wcid != wcid->idx)
+			continue;
+
+		if (cb->pktid == pktid)
+			return skb;
+
+		if (!pktid &&
+		    !time_after(jiffies, cb->jiffies + MT_TX_STATUS_SKB_TIMEOUT))
+			continue;
+
+		__mt76_tx_status_skb_done(dev, skb, MT_TX_CB_TXS_FAILED |
+						    MT_TX_CB_TXS_DONE);
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(mt76_tx_status_skb_get);
+
+void mt76_tx_complete_skb(struct mt76_dev *dev, struct sk_buff *skb)
+{
+	if (!skb->prev) {
+		ieee80211_free_txskb(dev->hw, skb);
+		return;
+	}
+
+	spin_lock_bh(&dev->status_list.lock);
+	__mt76_tx_status_skb_done(dev, skb, MT_TX_CB_DMA_DONE);
+	spin_unlock_bh(&dev->status_list.lock);
+}
+EXPORT_SYMBOL_GPL(mt76_tx_complete_skb);
+
 void
 mt76_tx(struct mt76_dev *dev, struct ieee80211_sta *sta,
 	struct mt76_wcid *wcid, struct sk_buff *skb)
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index 24d41288ea59..b061263453d4 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -700,6 +700,7 @@ mt76u_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
 	if (q->queued == q->ndesc)
 		return -ENOSPC;
 
+	skb->prev = skb->next = NULL;
 	err = dev->drv->tx_prepare_skb(dev, NULL, skb, q, wcid, sta, NULL);
 	if (err < 0)
 		return err;
-- 
cgit v1.2.3


From b983a5b900627faa49cf37e101d65b56e941c740 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Wed, 31 Oct 2018 08:32:58 +0100
Subject: mt76x0: do not overwrite other MT_BBP(AGC, 8) fields

MT_BBP(AGC, 8) register has values depend on band in
mt76x0_bbp_switch_tab, so we should not overwrite other fields
than MT_BBP_AGC_GAIN when setting gain.

This can fix performance issues when connecting to 2.4GHz AP.

Fixes: 4636a2544c3b ("mt76x0: phy: align channel gain logic to mt76x2 one")
Acked-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index c734987a344c..ec9b2a2a403f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -715,10 +715,8 @@ done:
 static void mt76x0_phy_set_gain_val(struct mt76x02_dev *dev)
 {
 	u8 gain = dev->cal.agc_gain_cur[0] - dev->cal.agc_gain_adjust;
-	u32 val = 0x122c << 16 | 0xf2;
 
-	mt76_wr(dev, MT_BBP(AGC, 8),
-		val | FIELD_PREP(MT_BBP_AGC_GAIN, gain));
+	mt76_rmw_field(dev, MT_BBP(AGC, 8), MT_BBP_AGC_GAIN, gain);
 
 	if ((dev->mt76.chandef.chan->flags & IEEE80211_CHAN_RADAR) &&
 	    !is_mt7630(dev))
-- 
cgit v1.2.3


From 0464cbfc36ac35700d572925769d7c73b3744798 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 27 Oct 2018 21:06:25 +0200
Subject: mt76x0: phy: use mt76_poll_msec in mt76x0_phy_temp_sensor

Use mt76_poll_msec utility routine for CORE_R34 register polling
instead of mt76_poll in order to allow the hw to complete requested
calibration since on slow devices (e.g. mt7620 based boards) calibration
takes longer than 2ms

Fixes: 66a34c66e0cb ("mt76x0: phy: add phy/vco temperature compensation")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index ec9b2a2a403f..563f1cbbeab4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -686,8 +686,7 @@ static void mt76x0_phy_temp_sensor(struct mt76x02_dev *dev)
 	mt76x0_rf_wr(dev, MT_RF(0, 67), 0x01);
 
 	mt76_wr(dev, MT_BBP(CORE, 34), 0x00080055);
-
-	if (!mt76_poll(dev, MT_BBP(CORE, 34), BIT(4), 0, 2000)) {
+	if (!mt76_poll_msec(dev, MT_BBP(CORE, 34), BIT(4), 0, 200)) {
 		mt76_clear(dev, MT_BBP(CORE, 34), BIT(4));
 		goto done;
 	}
-- 
cgit v1.2.3


From 48c76588221b49e7d46e6f3c26bce0318fbea97a Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sun, 28 Oct 2018 23:54:36 +0100
Subject: mt76x0: init: use mt76x02_mac_shared_key_setup in
 mt76x0_init_hardware

Use mt76x02_mac_shared_key_setup utility routine for shared key
initialization and remove duplicated code

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index 64eb6f451541..23ff29990ff7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -176,13 +176,6 @@ static int mt76x0_init_wcid_mem(struct mt76x02_dev *dev)
 	return 0;
 }
 
-static void mt76x0_init_key_mem(struct mt76x02_dev *dev)
-{
-	u32 vals[4] = {};
-
-	mt76_wr_copy(dev, MT_SKEY_MODE_BASE_0, vals, ARRAY_SIZE(vals));
-}
-
 static int mt76x0_init_wcid_attr_mem(struct mt76x02_dev *dev)
 {
 	u32 *vals;
@@ -260,7 +253,7 @@ EXPORT_SYMBOL_GPL(mt76x0_mac_stop);
 
 int mt76x0_init_hardware(struct mt76x02_dev *dev)
 {
-	int ret;
+	int ret, i, k;
 
 	if (!mt76x02_wait_for_wpdma(&dev->mt76, 1000))
 		return -EIO;
@@ -289,7 +282,9 @@ int mt76x0_init_hardware(struct mt76x02_dev *dev)
 	if (ret)
 		return ret;
 
-	mt76x0_init_key_mem(dev);
+	for (i = 0; i < 16; i++)
+		for (k = 0; k < 4; k++)
+			mt76x02_mac_shared_key_setup(dev, i, k, NULL);
 
 	ret = mt76x0_init_wcid_attr_mem(dev);
 	if (ret)
-- 
cgit v1.2.3


From 544f9a532f0ac3236dec903e1d0c3c5cc8bed919 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 29 Oct 2018 01:36:59 +0100
Subject: mt76x2: move wcid_tx_rate conf at bootstrap

Move WCID tx rate configuration at device bootstrap since
the related register are always set to 0

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c     | 3 ---
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c | 5 ++++-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index 90d24af7f6c8..59b336e34cb5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -106,9 +106,6 @@ void mt76x02_mac_wcid_setup(struct mt76x02_dev *dev, u8 idx,
 
 	mt76_wr(dev, MT_WCID_ATTR(idx), attr);
 
-	mt76_wr(dev, MT_WCID_TX_RATE(idx), 0);
-	mt76_wr(dev, MT_WCID_TX_RATE(idx) + 4, 0);
-
 	if (idx >= 128)
 		return;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index f6e8af6432c1..7b53b2be28c2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -129,8 +129,11 @@ static int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard)
 	for (i = 0; i < 256 / 32; i++)
 		mt76_wr(dev, MT_WCID_DROP_BASE + i * 4, 0);
 
-	for (i = 0; i < 256; i++)
+	for (i = 0; i < 256; i++) {
 		mt76x02_mac_wcid_setup(dev, i, 0, NULL);
+		mt76_wr(dev, MT_WCID_TX_RATE(i), 0);
+		mt76_wr(dev, MT_WCID_TX_RATE(i) + 4, 0);
+	}
 
 	for (i = 0; i < MT_MAX_VIFS; i++)
 		mt76x02_mac_wcid_setup(dev, MT_VIF_WCID(i), i, NULL);
-- 
cgit v1.2.3


From 24702cdb5f49c4e09dd89cfc248ae4e43275b2bd Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 29 Oct 2018 01:37:00 +0100
Subject: mt76x0: init: use mt76x02_mac_wcid_setup for wcid configuration

Use mt76x02_mac_wcid_setup utility routine for wcid init configuration
and remove duplicated code. This patch fixes a mt76x0 AP issue since
hw key table selection was set to pairwise by default

Fixes: dbad2adcb2c7 ("mt76x0: pci: enable AP support")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c | 45 ++----------------------
 1 file changed, 2 insertions(+), 43 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index 23ff29990ff7..55db5a15410e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -157,42 +157,6 @@ static void mt76x0_init_mac_registers(struct mt76x02_dev *dev)
 	mt76_rmw(dev, MT_WMM_CTRL, 0x3ff, 0x201);
 }
 
-static int mt76x0_init_wcid_mem(struct mt76x02_dev *dev)
-{
-	u32 *vals;
-	int i;
-
-	vals = kmalloc(sizeof(*vals) * MT76_N_WCIDS * 2, GFP_KERNEL);
-	if (!vals)
-		return -ENOMEM;
-
-	for (i = 0; i < MT76_N_WCIDS; i++)  {
-		vals[i * 2] = 0xffffffff;
-		vals[i * 2 + 1] = 0x00ffffff;
-	}
-
-	mt76_wr_copy(dev, MT_WCID_ADDR_BASE, vals, MT76_N_WCIDS * 2);
-	kfree(vals);
-	return 0;
-}
-
-static int mt76x0_init_wcid_attr_mem(struct mt76x02_dev *dev)
-{
-	u32 *vals;
-	int i;
-
-	vals = kmalloc(sizeof(*vals) * MT76_N_WCIDS * 2, GFP_KERNEL);
-	if (!vals)
-		return -ENOMEM;
-
-	for (i = 0; i < MT76_N_WCIDS * 2; i++)
-		vals[i] = 1;
-
-	mt76_wr_copy(dev, MT_WCID_ATTR_BASE, vals, MT76_N_WCIDS * 2);
-	kfree(vals);
-	return 0;
-}
-
 static void mt76x0_reset_counters(struct mt76x02_dev *dev)
 {
 	mt76_rr(dev, MT_RX_STAT_0);
@@ -278,17 +242,12 @@ int mt76x0_init_hardware(struct mt76x02_dev *dev)
 
 	dev->mt76.rxfilter = mt76_rr(dev, MT_RX_FILTR_CFG);
 
-	ret = mt76x0_init_wcid_mem(dev);
-	if (ret)
-		return ret;
-
 	for (i = 0; i < 16; i++)
 		for (k = 0; k < 4; k++)
 			mt76x02_mac_shared_key_setup(dev, i, k, NULL);
 
-	ret = mt76x0_init_wcid_attr_mem(dev);
-	if (ret)
-		return ret;
+	for (i = 0; i < 256; i++)
+		mt76x02_mac_wcid_setup(dev, i, 0, NULL);
 
 	mt76x0_reset_counters(dev);
 
-- 
cgit v1.2.3


From 40b63348030a080e6438d19d354b8e29165fa67a Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 29 Oct 2018 15:12:22 +0100
Subject: mt76x2u: init: remove not useful configuration

Remove MT_TSO_CTRL and MT_HEADER_TRANS_CTRL_REG initialization since
it is already done in mt76_write_mac_initvals routine

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
index a7d591610f16..c338ac0433ad 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
@@ -191,9 +191,6 @@ int mt76x2u_init_hardware(struct mt76x02_dev *dev)
 	if (!mt76x02_wait_for_mac(&dev->mt76))
 		return -ETIMEDOUT;
 
-	mt76_wr(dev, MT_HEADER_TRANS_CTRL_REG, 0);
-	mt76_wr(dev, MT_TSO_CTRL, 0);
-
 	mt76x2u_init_dma(dev);
 
 	err = mt76x2u_mcu_init(dev);
-- 
cgit v1.2.3


From 016ebffba18f6f792ad346c5b62941970f0e5b45 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 29 Oct 2018 22:16:50 +0100
Subject: mt76x2u: init: use common routines for wcid/key initialization

Use mt76x02_mac_wcid_setup and mt76x02_mac_shared_key_setup for
shared keys and wcid table initialization and remove duplicated
code

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
index c338ac0433ad..94a4b58fddc1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
@@ -166,11 +166,7 @@ static void mt76x2u_init_beacon_offsets(struct mt76x02_dev *dev)
 
 int mt76x2u_init_hardware(struct mt76x02_dev *dev)
 {
-	const struct mt76_wcid_addr addr = {
-		.macaddr = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff},
-		.ba_mask = 0,
-	};
-	int i, err;
+	int i, k, err;
 
 	mt76x2_reset_wlan(dev, true);
 	mt76x2u_power_on(dev);
@@ -210,15 +206,14 @@ int mt76x2u_init_hardware(struct mt76x02_dev *dev)
 		return -ETIMEDOUT;
 
 	/* reset wcid table */
-	for (i = 0; i < 254; i++)
-		mt76_wr_copy(dev, MT_WCID_ADDR(i), &addr,
-			     sizeof(struct mt76_wcid_addr));
+	for (i = 0; i < 256; i++)
+		mt76x02_mac_wcid_setup(dev, i, 0, NULL);
 
 	/* reset shared key table and pairwise key table */
-	for (i = 0; i < 4; i++)
-		mt76_wr(dev, MT_SKEY_MODE_BASE_0 + 4 * i, 0);
-	for (i = 0; i < 256; i++)
-		mt76_wr(dev, MT_WCID_ATTR(i), 1);
+	for (i = 0; i < 16; i++) {
+		for (k = 0; k < 4; k++)
+			mt76x02_mac_shared_key_setup(dev, i, k, NULL);
+	}
 
 	mt76_clear(dev, MT_BEACON_TIME_CFG,
 		   MT_BEACON_TIME_CFG_TIMER_EN |
-- 
cgit v1.2.3


From 693792ec55d5d87d6d9f704f40cc77f6932820ad Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 29 Oct 2018 22:31:23 +0100
Subject: mt76: move mt76x02_eeprom_copy in mt76x02-lib module

Move mt76x02_eeprom_copy utility routine in mt76x02-lib module
in order to be reused by mt76x0 driver adding tssi calibration
support

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c | 12 ++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h |  3 +++
 drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c  | 15 ++-------------
 3 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c
index 9390de2a323e..07f0496d828a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c
@@ -53,6 +53,18 @@ mt76x02_efuse_read(struct mt76x02_dev *dev, u16 addr, u8 *data,
 	return 0;
 }
 
+int mt76x02_eeprom_copy(struct mt76x02_dev *dev,
+			enum mt76x02_eeprom_field field,
+			void *dest, int len)
+{
+	if (field + len > dev->mt76.eeprom.size)
+		return -1;
+
+	memcpy(dest, dev->mt76.eeprom.data + field, len);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x02_eeprom_copy);
+
 int mt76x02_get_efuse_data(struct mt76x02_dev *dev, u16 base, void *buf,
 			   int len, enum mt76x02_eeprom_modes mode)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h
index 1de041590050..5db01bda64b5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h
@@ -188,5 +188,8 @@ u8 mt76x02_get_lna_gain(struct mt76x02_dev *dev,
 			s8 *lna_2g, s8 *lna_5g,
 			struct ieee80211_channel *chan);
 void mt76x02_eeprom_parse_hw_cap(struct mt76x02_dev *dev);
+int mt76x02_eeprom_copy(struct mt76x02_dev *dev,
+			enum mt76x02_eeprom_field field,
+			void *dest, int len);
 
 #endif /* __MT76x02_EEPROM_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
index f39b622d03f4..6f6998561d9d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
@@ -21,17 +21,6 @@
 
 #define EE_FIELD(_name, _value) [MT_EE_##_name] = (_value) | 1
 
-static int
-mt76x2_eeprom_copy(struct mt76x02_dev *dev, enum mt76x02_eeprom_field field,
-		   void *dest, int len)
-{
-	if (field + len > dev->mt76.eeprom.size)
-		return -1;
-
-	memcpy(dest, dev->mt76.eeprom.data + field, len);
-	return 0;
-}
-
 static int
 mt76x2_eeprom_get_macaddr(struct mt76x02_dev *dev)
 {
@@ -378,7 +367,7 @@ mt76x2_get_power_info_2g(struct mt76x02_dev *dev,
 	else
 		delta_idx = 5;
 
-	mt76x2_eeprom_copy(dev, offset, data, sizeof(data));
+	mt76x02_eeprom_copy(dev, offset, data, sizeof(data));
 
 	t->chain[chain].tssi_slope = data[0];
 	t->chain[chain].tssi_offset = data[1];
@@ -429,7 +418,7 @@ mt76x2_get_power_info_5g(struct mt76x02_dev *dev,
 	else
 		delta_idx = 4;
 
-	mt76x2_eeprom_copy(dev, offset, data, sizeof(data));
+	mt76x02_eeprom_copy(dev, offset, data, sizeof(data));
 
 	t->chain[chain].tssi_slope = data[0];
 	t->chain[chain].tssi_offset = data[1];
-- 
cgit v1.2.3


From 3548a9dd2def69d92952baa23c5baf2037f818dd Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 29 Oct 2018 22:31:24 +0100
Subject: mt76x0: phy: introduce tssi calibration support

Run mt76x0 tssi calibration process if enabled in eeprom data.
Perform calibration procedure every 4s

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    | 355 ++++++++++++++++++++-
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |   3 +
 .../net/wireless/mediatek/mt76/mt76x02_eeprom.h    |   2 +
 3 files changed, 357 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index 563f1cbbeab4..e2cedf9ded4d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -503,6 +503,345 @@ mt76x0_phy_bbp_set_bw(struct mt76x02_dev *dev, enum nl80211_chan_width width)
 	mt76x02_mcu_function_select(dev, BW_SETTING, bw, false);
 }
 
+static void mt76x0_phy_tssi_dc_calibrate(struct mt76x02_dev *dev)
+{
+	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+	u32 val;
+
+	if (chan->band == NL80211_BAND_5GHZ)
+		mt76x0_rf_clear(dev, MT_RF(0, 67), 0xf);
+
+	/* bypass ADDA control */
+	mt76_wr(dev, MT_RF_SETTING_0, 0x60002237);
+	mt76_wr(dev, MT_RF_BYPASS_0, 0xffffffff);
+
+	/* bbp sw reset */
+	mt76_set(dev, MT_BBP(CORE, 4), BIT(0));
+	usleep_range(500, 1000);
+	mt76_clear(dev, MT_BBP(CORE, 4), BIT(0));
+
+	val = (chan->band == NL80211_BAND_5GHZ) ? 0x80055 : 0x80050;
+	mt76_wr(dev, MT_BBP(CORE, 34), val);
+
+	/* enable TX with DAC0 input */
+	mt76_wr(dev, MT_BBP(TXBE, 6), BIT(31));
+
+	mt76_poll_msec(dev, MT_BBP(CORE, 34), BIT(4), 0, 200);
+	dev->cal.tssi_dc = mt76_rr(dev, MT_BBP(CORE, 35)) & 0xff;
+
+	/* stop bypass ADDA */
+	mt76_wr(dev, MT_RF_BYPASS_0, 0);
+	/* stop TX */
+	mt76_wr(dev, MT_BBP(TXBE, 6), 0);
+	/* bbp sw reset */
+	mt76_set(dev, MT_BBP(CORE, 4), BIT(0));
+	usleep_range(500, 1000);
+	mt76_clear(dev, MT_BBP(CORE, 4), BIT(0));
+
+	if (chan->band == NL80211_BAND_5GHZ)
+		mt76x0_rf_rmw(dev, MT_RF(0, 67), 0xf, 0x4);
+}
+
+static int
+mt76x0_phy_tssi_adc_calibrate(struct mt76x02_dev *dev, s16 *ltssi,
+			      u8 *info)
+{
+	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+	u32 val;
+
+	val = (chan->band == NL80211_BAND_5GHZ) ? 0x80055 : 0x80050;
+	mt76_wr(dev, MT_BBP(CORE, 34), val);
+
+	if (!mt76_poll_msec(dev, MT_BBP(CORE, 34), BIT(4), 0, 200)) {
+		mt76_clear(dev, MT_BBP(CORE, 34), BIT(4));
+		return -ETIMEDOUT;
+	}
+
+	*ltssi = mt76_rr(dev, MT_BBP(CORE, 35)) & 0xff;
+	if (chan->band == NL80211_BAND_5GHZ)
+		*ltssi += 128;
+
+	/* set packet info#1 mode */
+	mt76_wr(dev, MT_BBP(CORE, 34), 0x80041);
+	info[0] = mt76_rr(dev, MT_BBP(CORE, 35)) & 0xff;
+
+	/* set packet info#2 mode */
+	mt76_wr(dev, MT_BBP(CORE, 34), 0x80042);
+	info[1] = mt76_rr(dev, MT_BBP(CORE, 35)) & 0xff;
+
+	/* set packet info#3 mode */
+	mt76_wr(dev, MT_BBP(CORE, 34), 0x80043);
+	info[2] = mt76_rr(dev, MT_BBP(CORE, 35)) & 0xff;
+
+	return 0;
+}
+
+static u8 mt76x0_phy_get_rf_pa_mode(struct mt76x02_dev *dev,
+				    int index, u8 tx_rate)
+{
+	u32 val, reg;
+
+	reg = (index == 1) ? MT_RF_PA_MODE_CFG1 : MT_RF_PA_MODE_CFG0;
+	val = mt76_rr(dev, reg);
+	return (val & (3 << (tx_rate * 2))) >> (tx_rate * 2);
+}
+
+static int
+mt76x0_phy_get_target_power(struct mt76x02_dev *dev, u8 tx_mode,
+			    u8 *info, s8 *target_power,
+			    s8 *target_pa_power)
+{
+	u8 tx_rate, cur_power;
+
+	cur_power = mt76_rr(dev, MT_TX_ALC_CFG_0) & MT_TX_ALC_CFG_0_CH_INIT_0;
+	switch (tx_mode) {
+	case 0:
+		/* cck rates */
+		tx_rate = (info[0] & 0x60) >> 5;
+		if (tx_rate > 3)
+			return -EINVAL;
+
+		*target_power = cur_power + dev->mt76.rate_power.cck[tx_rate];
+		*target_pa_power = mt76x0_phy_get_rf_pa_mode(dev, 0, tx_rate);
+		break;
+	case 1: {
+		u8 index;
+
+		/* ofdm rates */
+		tx_rate = (info[0] & 0xf0) >> 4;
+		switch (tx_rate) {
+		case 0xb:
+			index = 0;
+			break;
+		case 0xf:
+			index = 1;
+			break;
+		case 0xa:
+			index = 2;
+			break;
+		case 0xe:
+			index = 3;
+			break;
+		case 0x9:
+			index = 4;
+			break;
+		case 0xd:
+			index = 5;
+			break;
+		case 0x8:
+			index = 6;
+			break;
+		case 0xc:
+			index = 7;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		*target_power = cur_power + dev->mt76.rate_power.ofdm[index];
+		*target_pa_power = mt76x0_phy_get_rf_pa_mode(dev, 0, index + 4);
+		break;
+	}
+	case 4:
+		/* vht rates */
+		tx_rate = info[1] & 0xf;
+		if (tx_rate > 9)
+			return -EINVAL;
+
+		*target_power = cur_power + dev->mt76.rate_power.vht[tx_rate];
+		*target_pa_power = mt76x0_phy_get_rf_pa_mode(dev, 1, tx_rate);
+		break;
+	default:
+		/* ht rates */
+		tx_rate = info[1] & 0x7f;
+		if (tx_rate > 9)
+			return -EINVAL;
+
+		*target_power = cur_power + dev->mt76.rate_power.ht[tx_rate];
+		*target_pa_power = mt76x0_phy_get_rf_pa_mode(dev, 1, tx_rate);
+		break;
+	}
+
+	return 0;
+}
+
+static s16 mt76x0_phy_lin2db(u16 val)
+{
+	u32 mantissa = val << 4;
+	int ret, data;
+	s16 exp = -4;
+
+	while (mantissa < BIT(15)) {
+		mantissa <<= 1;
+		if (--exp < -20)
+			return -10000;
+	}
+	while (mantissa > 0xffff) {
+		mantissa >>= 1;
+		if (++exp > 20)
+			return -10000;
+	}
+
+	/* s(15,0) */
+	if (mantissa <= 47104)
+		data = mantissa + (mantissa >> 3) + (mantissa >> 4) - 38400;
+	else
+		data = mantissa - (mantissa >> 3) - (mantissa >> 6) - 23040;
+	data = max_t(int, 0, data);
+
+	ret = ((15 + exp) << 15) + data;
+	ret = (ret << 2) + (ret << 1) + (ret >> 6) + (ret >> 7);
+	return ret >> 10;
+}
+
+static int
+mt76x0_phy_get_delta_power(struct mt76x02_dev *dev, u8 tx_mode,
+			   s8 target_power, s8 target_pa_power,
+			   s16 ltssi)
+{
+	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+	int tssi_target = target_power << 12, tssi_slope;
+	int tssi_offset, tssi_db, ret;
+	u32 data;
+	u16 val;
+
+	if (chan->band == NL80211_BAND_5GHZ) {
+		u8 bound[7];
+		int i, err;
+
+		err = mt76x02_eeprom_copy(dev, MT_EE_TSSI_BOUND1, bound,
+					  sizeof(bound));
+		if (err < 0)
+			return err;
+
+		for (i = 0; i < ARRAY_SIZE(bound); i++) {
+			if (chan->hw_value <= bound[i] || !bound[i])
+				break;
+		}
+		val = mt76x02_eeprom_get(dev, MT_EE_TSSI_SLOPE_5G + i * 2);
+
+		tssi_offset = val >> 8;
+		if ((tssi_offset >= 64 && tssi_offset <= 127) ||
+		    (tssi_offset & BIT(7)))
+			tssi_offset -= BIT(8);
+	} else {
+		val = mt76x02_eeprom_get(dev, MT_EE_TSSI_SLOPE_2G);
+
+		tssi_offset = val >> 8;
+		if (tssi_offset & BIT(7))
+			tssi_offset -= BIT(8);
+	}
+	tssi_slope = val & 0xff;
+
+	switch (target_pa_power) {
+	case 1:
+		if (chan->band == NL80211_BAND_2GHZ)
+			tssi_target += 29491; /* 3.6 * 8192 */
+		/* fall through */
+	case 0:
+		break;
+	default:
+		tssi_target += 4424; /* 0.54 * 8192 */
+		break;
+	}
+
+	if (!tx_mode) {
+		data = mt76_rr(dev, MT_BBP(CORE, 1));
+		if (is_mt7630(dev) && mt76_is_mmio(dev)) {
+			int offset;
+
+			/* 2.3 * 8192 or 1.5 * 8192 */
+			offset = (data & BIT(5)) ? 18841 : 12288;
+			tssi_target += offset;
+		} else if (data & BIT(5)) {
+			/* 0.8 * 8192 */
+			tssi_target += 6554;
+		}
+	}
+
+	data = mt76_rr(dev, MT_BBP(TXBE, 4));
+	switch (data & 0x3) {
+	case 1:
+		tssi_target -= 49152; /* -6db * 8192 */
+		break;
+	case 2:
+		tssi_target -= 98304; /* -12db * 8192 */
+		break;
+	case 3:
+		tssi_target += 49152; /* 6db * 8192 */
+		break;
+	default:
+		break;
+	}
+
+	tssi_db = mt76x0_phy_lin2db(ltssi - dev->cal.tssi_dc) * tssi_slope;
+	if (chan->band == NL80211_BAND_5GHZ) {
+		tssi_db += ((tssi_offset - 50) << 10); /* offset s4.3 */
+		tssi_target -= tssi_db;
+		if (ltssi > 254 && tssi_target > 0) {
+			/* upper saturate */
+			tssi_target = 0;
+		}
+	} else {
+		tssi_db += (tssi_offset << 9); /* offset s3.4 */
+		tssi_target -= tssi_db;
+		/* upper-lower saturate */
+		if ((ltssi > 126 && tssi_target > 0) ||
+		    ((ltssi - dev->cal.tssi_dc) < 1 && tssi_target < 0)) {
+			tssi_target = 0;
+		}
+	}
+
+	if ((dev->cal.tssi_target ^ tssi_target) < 0 &&
+	    dev->cal.tssi_target > -4096 && dev->cal.tssi_target < 4096 &&
+	    tssi_target > -4096 && tssi_target < 4096) {
+		if ((tssi_target < 0 &&
+		     tssi_target + dev->cal.tssi_target > 0) ||
+		    (tssi_target > 0 &&
+		     tssi_target + dev->cal.tssi_target <= 0))
+			tssi_target = 0;
+		else
+			dev->cal.tssi_target = tssi_target;
+	} else {
+		dev->cal.tssi_target = tssi_target;
+	}
+
+	/* make the compensate value to the nearest compensate code */
+	if (tssi_target > 0)
+		tssi_target += 2048;
+	else
+		tssi_target -= 2048;
+	tssi_target >>= 12;
+
+	ret = mt76_get_field(dev, MT_TX_ALC_CFG_1, MT_TX_ALC_CFG_1_TEMP_COMP);
+	if (ret & BIT(5))
+		ret -= BIT(6);
+	ret += tssi_target;
+
+	ret = min_t(int, 31, ret);
+	return max_t(int, -32, ret);
+}
+
+static void mt76x0_phy_tssi_calibrate(struct mt76x02_dev *dev)
+{
+	s8 target_power, target_pa_power;
+	u8 tssi_info[3], tx_mode;
+	s16 ltssi;
+	s8 val;
+
+	if (mt76x0_phy_tssi_adc_calibrate(dev, &ltssi, tssi_info) < 0)
+		return;
+
+	tx_mode = tssi_info[0] & 0x7;
+	if (mt76x0_phy_get_target_power(dev, tx_mode, tssi_info,
+					&target_power, &target_pa_power) < 0)
+		return;
+
+	val = mt76x0_phy_get_delta_power(dev, tx_mode, target_power,
+					 target_pa_power, ltssi);
+	mt76_rmw_field(dev, MT_TX_ALC_CFG_1, MT_TX_ALC_CFG_1_TEMP_COMP, val);
+}
+
 void mt76x0_phy_set_txpower(struct mt76x02_dev *dev)
 {
 	struct mt76_rate_power *t = &dev->mt76.rate_power;
@@ -532,7 +871,15 @@ void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on)
 		mt76x02_mcu_calibrate(dev, MCU_CAL_VCO, chan->hw_value,
 				      false);
 		usleep_range(10, 20);
-		/* XXX: tssi */
+
+		if (mt76x0_tssi_enabled(dev)) {
+			mt76_wr(dev, MT_MAC_SYS_CTRL,
+				MT_MAC_SYS_CTRL_ENABLE_RX);
+			mt76x0_phy_tssi_dc_calibrate(dev);
+			mt76_wr(dev, MT_MAC_SYS_CTRL,
+				MT_MAC_SYS_CTRL_ENABLE_TX |
+				MT_MAC_SYS_CTRL_ENABLE_RX);
+		}
 	}
 
 	tx_alc = mt76_rr(dev, MT_TX_ALC_CFG_0);
@@ -759,11 +1106,13 @@ static void mt76x0_phy_calibration_work(struct work_struct *work)
 					       cal_work.work);
 
 	mt76x0_phy_update_channel_gain(dev);
-	if (!mt76x0_tssi_enabled(dev))
+	if (mt76x0_tssi_enabled(dev))
+		mt76x0_phy_tssi_calibrate(dev);
+	else
 		mt76x0_phy_temp_sensor(dev);
 
 	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->cal_work,
-				     MT_CALIBRATE_INTERVAL);
+				     4 * MT_CALIBRATE_INTERVAL);
 }
 
 static void mt76x0_rf_patch_reg_array(struct mt76x02_dev *dev,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 19489a72fc2b..b92293c4c322 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -57,6 +57,9 @@ struct mt76x02_calibration {
 	bool tssi_comp_pending;
 	bool dpd_cal_done;
 	bool channel_cal_done;
+
+	int tssi_target;
+	s8 tssi_dc;
 };
 
 struct mt76x02_dev {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h
index 5db01bda64b5..e3442bc4e0a4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.h
@@ -56,6 +56,7 @@ enum mt76x02_eeprom_field {
 #define MT_TX_POWER_GROUP_SIZE_5G		5
 #define MT_TX_POWER_GROUPS_5G			6
 	MT_EE_TX_POWER_0_START_5G =		0x062,
+	MT_EE_TSSI_SLOPE_2G =			0x06e,
 
 	MT_EE_TX_POWER_0_GRP3_TX_POWER_DELTA =	0x074,
 	MT_EE_TX_POWER_0_GRP4_TSSI_SLOPE =	0x076,
@@ -86,6 +87,7 @@ enum mt76x02_eeprom_field {
 	MT_EE_TSSI_BOUND5 =			0x0dc,
 	MT_EE_TX_POWER_BYRATE_BASE =		0x0de,
 
+	MT_EE_TSSI_SLOPE_5G =			0x0f0,
 	MT_EE_RF_TEMP_COMP_SLOPE_5G =		0x0f2,
 	MT_EE_RF_TEMP_COMP_SLOPE_2G =		0x0f4,
 
-- 
cgit v1.2.3


From 07e548521274729c4af71e28a67b51dbd2361c0d Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 29 Oct 2018 22:31:25 +0100
Subject: mt76x0: phy: use tssi reported value to configure tx power if
 available

Use tssi calibrated value to configure tx power gain if tssi is enabled
in eeprom data

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c | 20 ++++++++++++++++----
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    |  2 +-
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
index 275d77c90624..497e762978cc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
@@ -135,9 +135,6 @@ static s8 mt76x0_get_delta(struct mt76x02_dev *dev)
 	struct cfg80211_chan_def *chandef = &dev->mt76.chandef;
 	u8 val;
 
-	if (mt76x0_tssi_enabled(dev))
-		return 0;
-
 	if (chandef->width == NL80211_CHAN_WIDTH_80) {
 		val = mt76x02_eeprom_get(dev, MT_EE_5G_TARGET_POWER) >> 8;
 	} else if (chandef->width == NL80211_CHAN_WIDTH_40) {
@@ -160,8 +157,8 @@ void mt76x0_get_tx_power_per_rate(struct mt76x02_dev *dev)
 	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
 	bool is_2ghz = chan->band == NL80211_BAND_2GHZ;
 	struct mt76_rate_power *t = &dev->mt76.rate_power;
-	s8 delta = mt76x0_get_delta(dev);
 	u16 val, addr;
+	s8 delta;
 
 	memset(t, 0, sizeof(*t));
 
@@ -211,6 +208,7 @@ void mt76x0_get_tx_power_per_rate(struct mt76x02_dev *dev)
 	t->vht[7] = s6_to_s8(val);
 	t->vht[8] = s6_to_s8(val >> 8);
 
+	delta = mt76x0_tssi_enabled(dev) ? 0 : mt76x0_get_delta(dev);
 	mt76x02_add_rate_power_offset(t, delta);
 }
 
@@ -233,6 +231,20 @@ void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info)
 	u16 data;
 	int i;
 
+	if (mt76x0_tssi_enabled(dev)) {
+		s8 target_power;
+
+		if (chan->band == NL80211_BAND_5GHZ)
+			data = mt76x02_eeprom_get(dev, MT_EE_5G_TARGET_POWER);
+		else
+			data = mt76x02_eeprom_get(dev, MT_EE_2G_TARGET_POWER);
+		target_power = (data & 0xff) - dev->mt76.rate_power.ofdm[7];
+		info[0] = target_power + mt76x0_get_delta(dev);
+		info[1] = 0;
+
+		return;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(chan_map); i++) {
 		if (chan_map[i].chan <= chan->hw_value) {
 			offset = chan_map[i].offset;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index e2cedf9ded4d..7a46a4d09294 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -847,8 +847,8 @@ void mt76x0_phy_set_txpower(struct mt76x02_dev *dev)
 	struct mt76_rate_power *t = &dev->mt76.rate_power;
 	u8 info[2];
 
-	mt76x0_get_power_info(dev, info);
 	mt76x0_get_tx_power_per_rate(dev);
+	mt76x0_get_power_info(dev, info);
 
 	mt76x02_add_rate_power_offset(t, info[0]);
 	mt76x02_limit_rate_power(t, dev->mt76.txpower_conf);
-- 
cgit v1.2.3


From ad3f993a0857ad3b792e7463828eb0d90cdd6f4d Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Thu, 25 Oct 2018 18:18:33 +0200
Subject: mt76x0: use band parameter for LC calibration

We use always 1 as band parameter for MCU_CAL_LC, this break 2GHz,
we should use 0 for this band instead.

Patch fixes problems happened sometimes when try to associate with 2GHz
AP and manifest by errors like below:

[14680.920823] wlan0: authenticate with 18:31:bf:c0:51:b0
[14681.109506] wlan0: send auth to 18:31:bf:c0:51:b0 (try 1/3)
[14681.310454] wlan0: send auth to 18:31:bf:c0:51:b0 (try 2/3)
[14681.518469] wlan0: send auth to 18:31:bf:c0:51:b0 (try 3/3)
[14681.726499] wlan0: authentication with 18:31:bf:c0:51:b0 timed out

Fixes: 9aec146d0f6b ("mt76x0: pci: introduce mt76x0_phy_calirate routine")
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index 7a46a4d09294..1450ba5c84ba 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -861,6 +861,7 @@ void mt76x0_phy_set_txpower(struct mt76x02_dev *dev)
 void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on)
 {
 	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+	int is_5ghz = (chan->band == NL80211_BAND_5GHZ) ? 1 : 0;
 	u32 val, tx_alc, reg_val;
 
 	if (is_mt7630(dev))
@@ -889,7 +890,7 @@ void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on)
 	reg_val = mt76_rr(dev, MT_BBP(IBI, 9));
 	mt76_wr(dev, MT_BBP(IBI, 9), 0xffffff7e);
 
-	if (chan->band == NL80211_BAND_5GHZ) {
+	if (is_5ghz) {
 		if (chan->hw_value < 100)
 			val = 0x701;
 		else if (chan->hw_value < 140)
@@ -902,7 +903,7 @@ void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on)
 
 	mt76x02_mcu_calibrate(dev, MCU_CAL_FULL, val, false);
 	msleep(350);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_LC, 1, false);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_LC, is_5ghz, false);
 	usleep_range(15000, 20000);
 
 	mt76_wr(dev, MT_BBP(IBI, 9), reg_val);
-- 
cgit v1.2.3


From a74d6336092c954ddf07e0e0a31466befdef6ed7 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Fri, 26 Oct 2018 14:00:26 +0200
Subject: mt76: remove mcu_msg_alloc

We almost always use patter like this:

       skb = mt76_mcu_msg_alloc(dev, &msg, sizeof(msg));
       return mt76_mcu_send_msg(dev, skb, CMD_FUN_SET_OP, wait_resp);

This is not needed, we can allocate skb in mcu_send_msg routine.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h          |  6 ++---
 .../net/wireless/mediatek/mt76/mt76x0/pci_mcu.c    |  1 -
 drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c   | 26 ++++++++++------------
 drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h   |  5 ++---
 .../net/wireless/mediatek/mt76/mt76x02_usb_mcu.c   | 18 +++++++++------
 drivers/net/wireless/mediatek/mt76/mt76x2/mcu.c    | 22 +++++++-----------
 .../net/wireless/mediatek/mt76/mt76x2/pci_mcu.c    |  1 -
 7 files changed, 35 insertions(+), 44 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 94ab00b549af..e1d89163ee6b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -135,9 +135,8 @@ struct mt76_queue {
 };
 
 struct mt76_mcu_ops {
-	struct sk_buff *(*mcu_msg_alloc)(const void *data, int len);
-	int (*mcu_send_msg)(struct mt76_dev *dev, struct sk_buff *skb,
-			    int cmd, bool wait_resp);
+	int (*mcu_send_msg)(struct mt76_dev *dev, int cmd, const void *data,
+			    int len, bool wait_resp);
 	int (*mcu_wr_rp)(struct mt76_dev *dev, u32 base,
 			 const struct mt76_reg_pair *rp, int len);
 	int (*mcu_rd_rp)(struct mt76_dev *dev, u32 base,
@@ -503,7 +502,6 @@ struct mt76_rx_status {
 #define mt76_wr_rp(dev, ...)	(dev)->mt76.bus->wr_rp(&((dev)->mt76), __VA_ARGS__)
 #define mt76_rd_rp(dev, ...)	(dev)->mt76.bus->rd_rp(&((dev)->mt76), __VA_ARGS__)
 
-#define mt76_mcu_msg_alloc(dev, ...)	(dev)->mt76.mcu_ops->mcu_msg_alloc(__VA_ARGS__)
 #define mt76_mcu_send_msg(dev, ...)	(dev)->mt76.mcu_ops->mcu_send_msg(&((dev)->mt76), __VA_ARGS__)
 
 #define mt76_set(dev, offset, val)	mt76_rmw(dev, offset, 0, val)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci_mcu.c
index aca0ea318dce..490c1869f2c4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci_mcu.c
@@ -127,7 +127,6 @@ out:
 int mt76x0e_mcu_init(struct mt76x02_dev *dev)
 {
 	static const struct mt76_mcu_ops mt76x0e_mcu_ops = {
-		.mcu_msg_alloc = mt76x02_mcu_msg_alloc,
 		.mcu_send_msg = mt76x02_mcu_msg_send,
 	};
 	int err;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
index 1b853bb723fb..550e73f81438 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
@@ -21,7 +21,7 @@
 
 #include "mt76x02_mcu.h"
 
-struct sk_buff *mt76x02_mcu_msg_alloc(const void *data, int len)
+static struct sk_buff *mt76x02_mcu_msg_alloc(const void *data, int len)
 {
 	struct sk_buff *skb;
 
@@ -32,7 +32,6 @@ struct sk_buff *mt76x02_mcu_msg_alloc(const void *data, int len)
 
 	return skb;
 }
-EXPORT_SYMBOL_GPL(mt76x02_mcu_msg_alloc);
 
 static struct sk_buff *
 mt76x02_mcu_get_response(struct mt76x02_dev *dev, unsigned long expires)
@@ -80,16 +79,18 @@ mt76x02_tx_queue_mcu(struct mt76x02_dev *dev, enum mt76_txq_id qid,
 	return 0;
 }
 
-int mt76x02_mcu_msg_send(struct mt76_dev *mdev, struct sk_buff *skb,
-			 int cmd, bool wait_resp)
+int mt76x02_mcu_msg_send(struct mt76_dev *mdev, int cmd, const void *data,
+			 int len, bool wait_resp)
 {
 	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
 	unsigned long expires = jiffies + HZ;
+	struct sk_buff *skb;
 	int ret;
 	u8 seq;
 
+	skb = mt76x02_mcu_msg_alloc(data, len);
 	if (!skb)
-		return -EINVAL;
+		return -ENOMEM;
 
 	mutex_lock(&mdev->mmio.mcu.mutex);
 
@@ -135,7 +136,6 @@ int mt76x02_mcu_function_select(struct mt76x02_dev *dev,
 				enum mcu_function func,
 				u32 val, bool wait_resp)
 {
-	struct sk_buff *skb;
 	struct {
 	    __le32 id;
 	    __le32 value;
@@ -144,15 +144,14 @@ int mt76x02_mcu_function_select(struct mt76x02_dev *dev,
 	    .value = cpu_to_le32(val),
 	};
 
-	skb = mt76_mcu_msg_alloc(dev, &msg, sizeof(msg));
-	return mt76_mcu_send_msg(dev, skb, CMD_FUN_SET_OP, wait_resp);
+	return mt76_mcu_send_msg(dev, CMD_FUN_SET_OP, &msg, sizeof(msg),
+				 wait_resp);
 }
 EXPORT_SYMBOL_GPL(mt76x02_mcu_function_select);
 
 int mt76x02_mcu_set_radio_state(struct mt76x02_dev *dev, bool on,
 				bool wait_resp)
 {
-	struct sk_buff *skb;
 	struct {
 		__le32 mode;
 		__le32 level;
@@ -161,15 +160,14 @@ int mt76x02_mcu_set_radio_state(struct mt76x02_dev *dev, bool on,
 		.level = cpu_to_le32(0),
 	};
 
-	skb = mt76_mcu_msg_alloc(dev, &msg, sizeof(msg));
-	return mt76_mcu_send_msg(dev, skb, CMD_POWER_SAVING_OP, wait_resp);
+	return mt76_mcu_send_msg(dev, CMD_POWER_SAVING_OP, &msg, sizeof(msg),
+				 wait_resp);
 }
 EXPORT_SYMBOL_GPL(mt76x02_mcu_set_radio_state);
 
 int mt76x02_mcu_calibrate(struct mt76x02_dev *dev, int type,
 			  u32 param, bool wait)
 {
-	struct sk_buff *skb;
 	struct {
 		__le32 id;
 		__le32 value;
@@ -182,8 +180,8 @@ int mt76x02_mcu_calibrate(struct mt76x02_dev *dev, int type,
 	if (wait)
 		mt76_rmw(dev, MT_MCU_COM_REG0, BIT(31), 0);
 
-	skb = mt76_mcu_msg_alloc(dev, &msg, sizeof(msg));
-	ret = mt76_mcu_send_msg(dev, skb, CMD_CALIBRATION_OP, true);
+	ret = mt76_mcu_send_msg(dev, CMD_CALIBRATION_OP, &msg, sizeof(msg),
+				true);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
index 2d8fd2514570..a3aee579d42c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
@@ -99,9 +99,8 @@ struct mt76x02_patch_header {
 int mt76x02_mcu_cleanup(struct mt76x02_dev *dev);
 int mt76x02_mcu_calibrate(struct mt76x02_dev *dev, int type,
 			  u32 param, bool wait);
-struct sk_buff *mt76x02_mcu_msg_alloc(const void *data, int len);
-int mt76x02_mcu_msg_send(struct mt76_dev *mdev, struct sk_buff *skb,
-			 int cmd, bool wait_resp);
+int mt76x02_mcu_msg_send(struct mt76_dev *mdev, int cmd, const void *data,
+			 int len, bool wait_resp);
 int mt76x02_mcu_function_select(struct mt76x02_dev *dev,
 				enum mcu_function func,
 				u32 val, bool wait_resp);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
index da299b8a1334..6db789f90269 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
@@ -129,9 +129,6 @@ __mt76x02u_mcu_send_msg(struct mt76_dev *dev, struct sk_buff *skb,
 	u8 seq = 0;
 	u32 info;
 
-	if (!skb)
-		return -EINVAL;
-
 	if (test_bit(MT76_REMOVED, &dev->state))
 		return 0;
 
@@ -162,12 +159,17 @@ __mt76x02u_mcu_send_msg(struct mt76_dev *dev, struct sk_buff *skb,
 }
 
 static int
-mt76x02u_mcu_send_msg(struct mt76_dev *dev, struct sk_buff *skb,
-		      int cmd, bool wait_resp)
+mt76x02u_mcu_send_msg(struct mt76_dev *dev, int cmd, const void *data,
+		      int len, bool wait_resp)
 {
 	struct mt76_usb *usb = &dev->usb;
+	struct sk_buff *skb;
 	int err;
 
+	skb = mt76x02u_mcu_msg_alloc(data, len);
+	if (!skb)
+		return -ENOMEM;
+
 	mutex_lock(&usb->mcu.mutex);
 	err = __mt76x02u_mcu_send_msg(dev, skb, cmd, wait_resp);
 	mutex_unlock(&usb->mcu.mutex);
@@ -186,6 +188,7 @@ mt76x02u_mcu_wr_rp(struct mt76_dev *dev, u32 base,
 {
 	const int CMD_RANDOM_WRITE = 12;
 	const int max_vals_per_cmd = MT_INBAND_PACKET_MAX_LEN / 8;
+	struct mt76_usb *usb = &dev->usb;
 	struct sk_buff *skb;
 	int cnt, i, ret;
 
@@ -204,7 +207,9 @@ mt76x02u_mcu_wr_rp(struct mt76_dev *dev, u32 base,
 		skb_put_le32(skb, data[i].value);
 	}
 
-	ret = mt76x02u_mcu_send_msg(dev, skb, CMD_RANDOM_WRITE, cnt == n);
+	mutex_lock(&usb->mcu.mutex);
+	ret = __mt76x02u_mcu_send_msg(dev, skb, CMD_RANDOM_WRITE, cnt == n);
+	mutex_unlock(&usb->mcu.mutex);
 	if (ret)
 		return ret;
 
@@ -345,7 +350,6 @@ EXPORT_SYMBOL_GPL(mt76x02u_mcu_fw_send_data);
 void mt76x02u_init_mcu(struct mt76_dev *dev)
 {
 	static const struct mt76_mcu_ops mt76x02u_mcu_ops = {
-		.mcu_msg_alloc = mt76x02u_mcu_msg_alloc,
 		.mcu_send_msg = mt76x02u_mcu_send_msg,
 		.mcu_wr_rp = mt76x02u_mcu_wr_rp,
 		.mcu_rd_rp = mt76x02u_mcu_rd_rp,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2/mcu.c
index 88bd62cfbdf9..cd3e082f486c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mcu.c
@@ -26,7 +26,6 @@
 int mt76x2_mcu_set_channel(struct mt76x02_dev *dev, u8 channel, u8 bw,
 			   u8 bw_index, bool scan)
 {
-	struct sk_buff *skb;
 	struct {
 		u8 idx;
 		u8 scan;
@@ -45,21 +44,19 @@ int mt76x2_mcu_set_channel(struct mt76x02_dev *dev, u8 channel, u8 bw,
 	};
 
 	/* first set the channel without the extension channel info */
-	skb = mt76_mcu_msg_alloc(dev, &msg, sizeof(msg));
-	mt76_mcu_send_msg(dev, skb, CMD_SWITCH_CHANNEL_OP, true);
+	mt76_mcu_send_msg(dev, CMD_SWITCH_CHANNEL_OP, &msg, sizeof(msg), true);
 
 	usleep_range(5000, 10000);
 
 	msg.ext_chan = 0xe0 + bw_index;
-	skb = mt76_mcu_msg_alloc(dev, &msg, sizeof(msg));
-	return mt76_mcu_send_msg(dev, skb, CMD_SWITCH_CHANNEL_OP, true);
+	return mt76_mcu_send_msg(dev, CMD_SWITCH_CHANNEL_OP, &msg, sizeof(msg),
+				 true);
 }
 EXPORT_SYMBOL_GPL(mt76x2_mcu_set_channel);
 
 int mt76x2_mcu_load_cr(struct mt76x02_dev *dev, u8 type, u8 temp_level,
 		       u8 channel)
 {
-	struct sk_buff *skb;
 	struct {
 		u8 cr_mode;
 		u8 temp;
@@ -80,15 +77,13 @@ int mt76x2_mcu_load_cr(struct mt76x02_dev *dev, u8 type, u8 temp_level,
 	msg.cfg = cpu_to_le32(val);
 
 	/* first set the channel without the extension channel info */
-	skb = mt76_mcu_msg_alloc(dev, &msg, sizeof(msg));
-	return mt76_mcu_send_msg(dev, skb, CMD_LOAD_CR, true);
+	return mt76_mcu_send_msg(dev, CMD_LOAD_CR, &msg, sizeof(msg), true);
 }
 EXPORT_SYMBOL_GPL(mt76x2_mcu_load_cr);
 
 int mt76x2_mcu_init_gain(struct mt76x02_dev *dev, u8 channel, u32 gain,
 			 bool force)
 {
-	struct sk_buff *skb;
 	struct {
 		__le32 channel;
 		__le32 gain_val;
@@ -100,15 +95,14 @@ int mt76x2_mcu_init_gain(struct mt76x02_dev *dev, u8 channel, u32 gain,
 	if (force)
 		msg.channel |= cpu_to_le32(BIT(31));
 
-	skb = mt76_mcu_msg_alloc(dev, &msg, sizeof(msg));
-	return mt76_mcu_send_msg(dev, skb, CMD_INIT_GAIN_OP, true);
+	return mt76_mcu_send_msg(dev, CMD_INIT_GAIN_OP, &msg, sizeof(msg),
+				 true);
 }
 EXPORT_SYMBOL_GPL(mt76x2_mcu_init_gain);
 
 int mt76x2_mcu_tssi_comp(struct mt76x02_dev *dev,
 			 struct mt76x2_tssi_comp *tssi_data)
 {
-	struct sk_buff *skb;
 	struct {
 		__le32 id;
 		struct mt76x2_tssi_comp data;
@@ -117,7 +111,7 @@ int mt76x2_mcu_tssi_comp(struct mt76x02_dev *dev,
 		.data = *tssi_data,
 	};
 
-	skb = mt76_mcu_msg_alloc(dev, &msg, sizeof(msg));
-	return mt76_mcu_send_msg(dev, skb, CMD_CALIBRATION_OP, true);
+	return mt76_mcu_send_msg(dev, CMD_CALIBRATION_OP, &msg, sizeof(msg),
+				 true);
 }
 EXPORT_SYMBOL_GPL(mt76x2_mcu_tssi_comp);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c
index d8fa9ba56437..b5067ee0b001 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c
@@ -168,7 +168,6 @@ error:
 int mt76x2_mcu_init(struct mt76x02_dev *dev)
 {
 	static const struct mt76_mcu_ops mt76x2_mcu_ops = {
-		.mcu_msg_alloc = mt76x02_mcu_msg_alloc,
 		.mcu_send_msg = mt76x02_mcu_msg_send,
 	};
 	int ret;
-- 
cgit v1.2.3


From 3d2d61b5f7a52936e8ec01fa55ace709d52eacc2 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Fri, 26 Oct 2018 14:00:28 +0200
Subject: mt76: remove wait argument from mt76x02_mcu_function_select

Remove wait argument from mt76x02_mcu_function_select and wait for
response when function is not Q_SELECT, what is the same behaviour
like in vendor driver.

Note this change behaviour for PCIe devices for Q_SELECT function
form wait to no-wait, and for mt76x0u BW_SETTING from no-wait to wait.
But the change is in align with vendor driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c     |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c    | 12 +++++++-----
 drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h    |  5 ++---
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c |  2 +-
 6 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index 55db5a15410e..e74d476eca24 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -227,7 +227,7 @@ int mt76x0_init_hardware(struct mt76x02_dev *dev)
 		return -ETIMEDOUT;
 
 	mt76x0_reset_csr_bbp(dev);
-	ret = mt76x02_mcu_function_select(dev, Q_SELECT, 1, false);
+	ret = mt76x02_mcu_function_select(dev, Q_SELECT, 1);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index 1450ba5c84ba..e9e6d33d3463 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -500,7 +500,7 @@ mt76x0_phy_bbp_set_bw(struct mt76x02_dev *dev, enum nl80211_chan_width width)
 		return ;
 	}
 
-	mt76x02_mcu_function_select(dev, BW_SETTING, bw, false);
+	mt76x02_mcu_function_select(dev, BW_SETTING, bw);
 }
 
 static void mt76x0_phy_tssi_dc_calibrate(struct mt76x02_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
index 550e73f81438..cd906b48d013 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
@@ -132,9 +132,8 @@ out:
 }
 EXPORT_SYMBOL_GPL(mt76x02_mcu_msg_send);
 
-int mt76x02_mcu_function_select(struct mt76x02_dev *dev,
-				enum mcu_function func,
-				u32 val, bool wait_resp)
+int mt76x02_mcu_function_select(struct mt76x02_dev *dev, enum mcu_function func,
+				u32 val)
 {
 	struct {
 	    __le32 id;
@@ -143,9 +142,12 @@ int mt76x02_mcu_function_select(struct mt76x02_dev *dev,
 	    .id = cpu_to_le32(func),
 	    .value = cpu_to_le32(val),
 	};
+	bool wait = false;
 
-	return mt76_mcu_send_msg(dev, CMD_FUN_SET_OP, &msg, sizeof(msg),
-				 wait_resp);
+	if (func != Q_SELECT)
+		wait = true;
+
+	return mt76_mcu_send_msg(dev, CMD_FUN_SET_OP, &msg, sizeof(msg), wait);
 }
 EXPORT_SYMBOL_GPL(mt76x02_mcu_function_select);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
index a3aee579d42c..f34d55bc056e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
@@ -101,9 +101,8 @@ int mt76x02_mcu_calibrate(struct mt76x02_dev *dev, int type,
 			  u32 param, bool wait);
 int mt76x02_mcu_msg_send(struct mt76_dev *mdev, int cmd, const void *data,
 			 int len, bool wait_resp);
-int mt76x02_mcu_function_select(struct mt76x02_dev *dev,
-				enum mcu_function func,
-				u32 val, bool wait_resp);
+int mt76x02_mcu_function_select(struct mt76x02_dev *dev, enum mcu_function func,
+				u32 val);
 int mt76x02_mcu_set_radio_state(struct mt76x02_dev *dev, bool on,
 				bool wait_resp);
 void mt76x02_set_ethtool_fwver(struct mt76x02_dev *dev,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c
index b5067ee0b001..03e24ae7f66c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c
@@ -182,6 +182,6 @@ int mt76x2_mcu_init(struct mt76x02_dev *dev)
 	if (ret)
 		return ret;
 
-	mt76x02_mcu_function_select(dev, Q_SELECT, 1, true);
+	mt76x02_mcu_function_select(dev, Q_SELECT, 1);
 	return 0;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
index d6e3e663dd8a..ca9037af804c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
@@ -258,7 +258,7 @@ int mt76x2u_mcu_init(struct mt76x02_dev *dev)
 {
 	int err;
 
-	err = mt76x02_mcu_function_select(dev, Q_SELECT, 1, false);
+	err = mt76x02_mcu_function_select(dev, Q_SELECT, 1);
 	if (err < 0)
 		return err;
 
-- 
cgit v1.2.3


From c69505367c2a81683a35b0ff263485f41fe19c89 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Fri, 26 Oct 2018 14:00:29 +0200
Subject: mt76: remove wait argument from mt76x02_mcu_set_radio_state

Remove wait argument from mt76x02_mcu_set_radio_state and newer wait
for response when sending CMD_POWER_SAVING_OP mcu command.
Note this change behaviour for PCIe devices, but the change is in
align with vendor driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c     | 6 ++----
 drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h     | 3 +--
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c | 2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c  | 2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c | 2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c  | 2 +-
 6 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
index cd906b48d013..6015ba9ffdac 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
@@ -151,8 +151,7 @@ int mt76x02_mcu_function_select(struct mt76x02_dev *dev, enum mcu_function func,
 }
 EXPORT_SYMBOL_GPL(mt76x02_mcu_function_select);
 
-int mt76x02_mcu_set_radio_state(struct mt76x02_dev *dev, bool on,
-				bool wait_resp)
+int mt76x02_mcu_set_radio_state(struct mt76x02_dev *dev, bool on)
 {
 	struct {
 		__le32 mode;
@@ -162,8 +161,7 @@ int mt76x02_mcu_set_radio_state(struct mt76x02_dev *dev, bool on,
 		.level = cpu_to_le32(0),
 	};
 
-	return mt76_mcu_send_msg(dev, CMD_POWER_SAVING_OP, &msg, sizeof(msg),
-				 wait_resp);
+	return mt76_mcu_send_msg(dev, CMD_POWER_SAVING_OP, &msg, sizeof(msg), false);
 }
 EXPORT_SYMBOL_GPL(mt76x02_mcu_set_radio_state);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
index f34d55bc056e..97025c31a986 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
@@ -103,8 +103,7 @@ int mt76x02_mcu_msg_send(struct mt76_dev *mdev, int cmd, const void *data,
 			 int len, bool wait_resp);
 int mt76x02_mcu_function_select(struct mt76x02_dev *dev, enum mcu_function func,
 				u32 val);
-int mt76x02_mcu_set_radio_state(struct mt76x02_dev *dev, bool on,
-				bool wait_resp);
+int mt76x02_mcu_set_radio_state(struct mt76x02_dev *dev, bool on);
 void mt76x02_set_ethtool_fwver(struct mt76x02_dev *dev,
 			       const struct mt76x02_fw_header *h);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 7b53b2be28c2..076b7479ba99 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -300,7 +300,7 @@ void mt76x2_stop_hardware(struct mt76x02_dev *dev)
 {
 	cancel_delayed_work_sync(&dev->cal_work);
 	cancel_delayed_work_sync(&dev->mac_work);
-	mt76x02_mcu_set_radio_state(dev, false, true);
+	mt76x02_mcu_set_radio_state(dev, false);
 	mt76x2_mac_stop(dev, false);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c
index 16ff6c376373..63866b2fec64 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c
@@ -305,7 +305,7 @@ int mt76x2_phy_start(struct mt76x02_dev *dev)
 {
 	int ret;
 
-	ret = mt76x02_mcu_set_radio_state(dev, true, true);
+	ret = mt76x02_mcu_set_radio_state(dev, true);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
index 94a4b58fddc1..8b280a4ea792 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
@@ -292,7 +292,7 @@ void mt76x2u_stop_hw(struct mt76x02_dev *dev)
 
 void mt76x2u_cleanup(struct mt76x02_dev *dev)
 {
-	mt76x02_mcu_set_radio_state(dev, false, false);
+	mt76x02_mcu_set_radio_state(dev, false);
 	mt76x2u_stop_hw(dev);
 	mt76u_queues_deinit(&dev->mt76);
 	mt76u_mcu_deinit(&dev->mt76);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
index ca9037af804c..45a95ee3a415 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c
@@ -262,5 +262,5 @@ int mt76x2u_mcu_init(struct mt76x02_dev *dev)
 	if (err < 0)
 		return err;
 
-	return mt76x02_mcu_set_radio_state(dev, true, false);
+	return mt76x02_mcu_set_radio_state(dev, true);
 }
-- 
cgit v1.2.3


From f1b8ee35fec4a070b7760a99709fc98f237c2b86 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Thu, 1 Nov 2018 16:35:01 +0100
Subject: mt76x02: run calibration after scanning

If we are associated and scanning is performed, sw_scan_complete callback
is done after we get back to operating channel, so we do not perform
queue cal work. Fix this queue cal work from sw_scan_complete().

On mt76x0 we have to restore gain in MT_BBP(AGC, 8) register after
scanning, as it was multiple times modified by channel switch code.
So queue cal work without any delay to set AGC gain value.

Similar like in mt76x2 init AGC gain only when set operating channel
and just check before queuing cal work in sw_scan_complete() if
initialization was already done.

Fixes: bbd10586f0df ("mt76x0: phy: do not run calibration during channel switch")
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c   | 2 +-
 drivers/net/wireless/mediatek/mt76/mt76x02.h      | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x02_phy.c  | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c | 3 +++
 4 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index e9e6d33d3463..272a68884269 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -1004,13 +1004,13 @@ int mt76x0_phy_set_channel(struct mt76x02_dev *dev,
 
 	mt76x0_read_rx_gain(dev);
 	mt76x0_phy_set_chan_bbp_params(dev, rf_bw_band);
-	mt76x02_init_agc_gain(dev);
 
 	/* enable vco */
 	mt76x0_rf_set(dev, MT_RF(0, 4), BIT(7));
 	if (scan)
 		return 0;
 
+	mt76x02_init_agc_gain(dev);
 	mt76x0_phy_calibrate(dev, false);
 	mt76x0_phy_set_txpower(dev);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index b92293c4c322..a8c5fdd903b9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -57,6 +57,7 @@ struct mt76x02_calibration {
 	bool tssi_comp_pending;
 	bool dpd_cal_done;
 	bool channel_cal_done;
+	bool gain_init_done;
 
 	int tssi_target;
 	s8 tssi_dc;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c
index 0f1d7b5c9f68..977a8e7e26df 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c
@@ -254,5 +254,6 @@ void mt76x02_init_agc_gain(struct mt76x02_dev *dev)
 	memcpy(dev->cal.agc_gain_cur, dev->cal.agc_gain_init,
 	       sizeof(dev->cal.agc_gain_cur));
 	dev->cal.low_gain = -1;
+	dev->cal.gain_init_done = true;
 }
 EXPORT_SYMBOL_GPL(mt76x02_init_agc_gain);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index adfc46419b6b..8a250224fcd7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -554,6 +554,9 @@ void mt76x02_sw_scan_complete(struct ieee80211_hw *hw,
 	clear_bit(MT76_SCANNING, &dev->mt76.state);
 	if (mt76_is_mmio(dev))
 		tasklet_enable(&dev->pre_tbtt_tasklet);
+
+	if (dev->cal.gain_init_done)
+		ieee80211_queue_delayed_work(hw, &dev->cal_work, 0);
 }
 EXPORT_SYMBOL_GPL(mt76x02_sw_scan_complete);
 
-- 
cgit v1.2.3


From 4784a3cc3fffd0ba5ef6c7a23980ae0318fc1369 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Thu, 1 Nov 2018 16:35:02 +0100
Subject: mt76x02: assure we update gain after scan

Assure that after we initialize dev->cal.low_gain to -1 this
will cause update gain calibration. Otherwise this might or
might not happen depending on value of second bit of low_gain
and values read from registers in mt76x02_phy_adjust_vga_gain().

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c   | 3 ++-
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c | 5 ++++-
 drivers/net/wireless/mediatek/mt76/mt76x2/phy.c   | 3 ++-
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index 272a68884269..275458891ce4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -1082,7 +1082,8 @@ mt76x0_phy_update_channel_gain(struct mt76x02_dev *dev)
 	low_gain = (dev->cal.avg_rssi_all > mt76x02_get_rssi_gain_thresh(dev)) +
 		   (dev->cal.avg_rssi_all > mt76x02_get_low_rssi_gain_thresh(dev));
 
-	gain_change = (dev->cal.low_gain & 2) ^ (low_gain & 2);
+	gain_change = dev->cal.low_gain < 0 ||
+		      (dev->cal.low_gain & 2) ^ (low_gain & 2);
 	dev->cal.low_gain = low_gain;
 
 	if (!gain_change) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 8a250224fcd7..87ce6a51fb05 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -555,8 +555,11 @@ void mt76x02_sw_scan_complete(struct ieee80211_hw *hw,
 	if (mt76_is_mmio(dev))
 		tasklet_enable(&dev->pre_tbtt_tasklet);
 
-	if (dev->cal.gain_init_done)
+	if (dev->cal.gain_init_done) {
+		/* Restore AGC gain and resume calibration after scanning. */
+		dev->cal.low_gain = -1;
 		ieee80211_queue_delayed_work(hw, &dev->cal_work, 0);
+	}
 }
 EXPORT_SYMBOL_GPL(mt76x02_sw_scan_complete);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
index bbeff9c19997..1b85fb415548 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
@@ -289,7 +289,8 @@ void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev)
 	low_gain = (dev->cal.avg_rssi_all > mt76x02_get_rssi_gain_thresh(dev)) +
 		   (dev->cal.avg_rssi_all > mt76x02_get_low_rssi_gain_thresh(dev));
 
-	gain_change = (dev->cal.low_gain & 2) ^ (low_gain & 2);
+	gain_change = dev->cal.low_gain < 0 ||
+		      (dev->cal.low_gain & 2) ^ (low_gain & 2);
 	dev->cal.low_gain = low_gain;
 
 	if (!gain_change) {
-- 
cgit v1.2.3


From 6bf4a8e902aad7df55d7f2b10b850cfa3f880996 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 5 Nov 2018 00:18:26 +0100
Subject: mt76x0: dfs: fix IBI_R11 configuration on non-radar channels

Fix IBI_R11 configuration on non-radar channels for mt76x0e
driver. This patch improve system stability under heavy load.
Moreover use IBI_R11 name and remove magic numbers for
0x212c register

Fixes: 0c3b3abc9251 ("mt76x0: pci: add DFS support")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
index 527e530d480a..054609c634a2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
@@ -799,7 +799,7 @@ static void mt76x02_dfs_set_bbp_params(struct mt76x02_dev *dev)
 
 	/* enable detection*/
 	mt76_wr(dev, MT_BBP(DFS, 0), MT_DFS_CH_EN << 16);
-	mt76_wr(dev, 0x212c, 0x0c350001);
+	mt76_wr(dev, MT_BBP(IBI, 11), 0x0c350001);
 }
 
 void mt76x02_phy_dfs_adjust_agc(struct mt76x02_dev *dev)
@@ -850,7 +850,11 @@ void mt76x02_dfs_init_params(struct mt76x02_dev *dev)
 		mt76_wr(dev, MT_BBP(DFS, 0), 0);
 		/* clear detector status */
 		mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
-		mt76_wr(dev, 0x212c, 0);
+		if (mt76_chip(&dev->mt76) == 0x7610 ||
+		    mt76_chip(&dev->mt76) == 0x7630)
+			mt76_wr(dev, MT_BBP(IBI, 11), 0xfde8081);
+		else
+			mt76_wr(dev, MT_BBP(IBI, 11), 0);
 
 		mt76x02_irq_disable(dev, MT_INT_GPTIMER);
 		mt76_rmw_field(dev, MT_INT_TIMER_EN,
-- 
cgit v1.2.3


From 269906ac82fb22d41e1f95111ec2bf2546c80ce8 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 6 Nov 2018 23:49:12 +0100
Subject: mt76: introduce mt76x02_config_mac_addr_list routine

Add mt76x02_config_mac_addr_list routine in order to set
the mac address list supported by the driver. Initialize
wiphy->addresses/n_addresses for mt76x0e driver

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c   |  2 ++
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c  | 22 ++++++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt76x2/pci_init.c   | 17 ++---------------
 4 files changed, 27 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index e74d476eca24..87b575fe1c74 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -289,6 +289,8 @@ int mt76x0_register_device(struct mt76x02_dev *dev)
 	int ret;
 
 	mt76x02_init_device(dev);
+	mt76x02_config_mac_addr_list(dev);
+
 	ret = mt76_register_device(&dev->mt76, true, mt76x02_rates,
 				   ARRAY_SIZE(mt76x02_rates));
 	if (ret)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index a8c5fdd903b9..65daa3d3c289 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -115,6 +115,7 @@ int mt76x02_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 int mt76x02_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		      struct ieee80211_sta *sta);
 
+void mt76x02_config_mac_addr_list(struct mt76x02_dev *dev);
 void mt76x02_vif_init(struct mt76x02_dev *dev, struct ieee80211_vif *vif,
 		      unsigned int idx);
 int mt76x02_add_interface(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 87ce6a51fb05..a52db63c3c68 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -700,4 +700,26 @@ void mt76x02_bss_info_changed(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL_GPL(mt76x02_bss_info_changed);
 
+void mt76x02_config_mac_addr_list(struct mt76x02_dev *dev)
+{
+	struct ieee80211_hw *hw = mt76_hw(dev);
+	struct wiphy *wiphy = hw->wiphy;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dev->macaddr_list); i++) {
+		u8 *addr = dev->macaddr_list[i].addr;
+
+		memcpy(addr, dev->mt76.macaddr, ETH_ALEN);
+
+		if (!i)
+			continue;
+
+		addr[0] |= BIT(1);
+		addr[0] ^= ((i - 1) << 2);
+	}
+	wiphy->addresses = dev->macaddr_list;
+	wiphy->n_addresses = ARRAY_SIZE(dev->macaddr_list);
+}
+EXPORT_SYMBOL_GPL(mt76x02_config_mac_addr_list);
+
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 076b7479ba99..80b4e11ea28e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -390,7 +390,7 @@ int mt76x2_register_device(struct mt76x02_dev *dev)
 {
 	struct ieee80211_hw *hw = mt76_hw(dev);
 	struct wiphy *wiphy = hw->wiphy;
-	int i, ret;
+	int ret;
 
 	INIT_DELAYED_WORK(&dev->cal_work, mt76x2_phy_calibrate);
 
@@ -400,20 +400,7 @@ int mt76x2_register_device(struct mt76x02_dev *dev)
 	if (ret)
 		return ret;
 
-	for (i = 0; i < ARRAY_SIZE(dev->macaddr_list); i++) {
-		u8 *addr = dev->macaddr_list[i].addr;
-
-		memcpy(addr, dev->mt76.macaddr, ETH_ALEN);
-
-		if (!i)
-			continue;
-
-		addr[0] |= BIT(1);
-		addr[0] ^= ((i - 1) << 2);
-	}
-	wiphy->addresses = dev->macaddr_list;
-	wiphy->n_addresses = ARRAY_SIZE(dev->macaddr_list);
-
+	mt76x02_config_mac_addr_list(dev);
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 
 	/* init led callbacks */
-- 
cgit v1.2.3


From 8f2fbff574a9bc3ee0d34a080873e2dbec39f488 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 6 Nov 2018 23:54:49 +0100
Subject: mt76x0: pci: enable VHT rates in IBSS mode

Enable VHT tx rates in ad-hoc mode for mt76x0e driver.

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c    | 2 ++
 drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c | 3 ---
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index a52db63c3c68..48f2f5382b57 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -105,6 +105,8 @@ void mt76x02_init_device(struct mt76x02_dev *dev)
 			BIT(NL80211_IFTYPE_MESH_POINT) |
 #endif
 			BIT(NL80211_IFTYPE_ADHOC);
+
+		wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 	}
 
 	hw->sta_data_size = sizeof(struct mt76x02_sta);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 80b4e11ea28e..843dda261cf8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -388,8 +388,6 @@ static void mt76x2_led_set_brightness(struct led_classdev *led_cdev,
 
 int mt76x2_register_device(struct mt76x02_dev *dev)
 {
-	struct ieee80211_hw *hw = mt76_hw(dev);
-	struct wiphy *wiphy = hw->wiphy;
 	int ret;
 
 	INIT_DELAYED_WORK(&dev->cal_work, mt76x2_phy_calibrate);
@@ -401,7 +399,6 @@ int mt76x2_register_device(struct mt76x02_dev *dev)
 		return ret;
 
 	mt76x02_config_mac_addr_list(dev);
-	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 
 	/* init led callbacks */
 	dev->mt76.led_cdev.brightness_set = mt76x2_led_set_brightness;
-- 
cgit v1.2.3


From 4f833fadc99cb19cd1bf74134e199dd4b1fad34c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 6 Nov 2018 17:59:45 +0100
Subject: mt76x2u: phy: add TX_SHAPING calibration

Add MCU_CAL_TX_SHAPING calibration in mt76x2u_phy_channel_calibrate
routine since now mt76x2 and mt76x2u driver run the same firmware

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
index 8011c261c658..24e292e895b6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
@@ -35,6 +35,7 @@ void mt76x2u_phy_channel_calibrate(struct mt76x02_dev *dev)
 	mt76x02_mcu_calibrate(dev, MCU_CAL_TXIQ, is_5ghz, false);
 	mt76x02_mcu_calibrate(dev, MCU_CAL_RXIQC_FI, is_5ghz, false);
 	mt76x02_mcu_calibrate(dev, MCU_CAL_TEMP_SENSOR, 0, false);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_TX_SHAPING, 0, false);
 
 	mt76x2u_mac_resume(dev);
 }
-- 
cgit v1.2.3


From 04289783cec4cf942a9d7498624bde5287806399 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 6 Nov 2018 17:59:46 +0100
Subject: mt76x2u: phy: run phy_channel_calibrate after channel switch

Perform channel calibration after each channel switch and not only after
connection establishment since NetworkManager perform multiple frequency
scanning if RSSI in lower a given threshold

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2u.h  |  1 -
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c |  5 -----
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c  | 18 +++++++++++++++---
 3 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2u.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2u.h
index 833974de5c80..0b0075411b34 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2u.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2u.h
@@ -43,7 +43,6 @@ int mt76x2u_mac_stop(struct mt76x02_dev *dev);
 int mt76x2u_phy_set_channel(struct mt76x02_dev *dev,
 			    struct cfg80211_chan_def *chandef);
 void mt76x2u_phy_calibrate(struct work_struct *work);
-void mt76x2u_phy_channel_calibrate(struct mt76x02_dev *dev);
 
 void mt76x2u_mcu_complete_urb(struct urb *urb);
 int mt76x2u_mcu_init(struct mt76x02_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
index c2e0a43082e5..cad99715997e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
@@ -91,11 +91,6 @@ mt76x2u_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	mutex_lock(&dev->mt76.mutex);
 
-	if (changed & BSS_CHANGED_ASSOC) {
-		mt76x2u_phy_channel_calibrate(dev);
-		mt76x2_apply_gain_adj(dev);
-	}
-
 	if (changed & BSS_CHANGED_BSSID) {
 		mt76_wr(dev, MT_MAC_BSSID_DW0,
 			get_unaligned_le32(info->bssid));
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
index 24e292e895b6..a64268e8db42 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
@@ -18,15 +18,20 @@
 #include "eeprom.h"
 #include "../mt76x02_phy.h"
 
-void mt76x2u_phy_channel_calibrate(struct mt76x02_dev *dev)
+static void
+mt76x2u_phy_channel_calibrate(struct mt76x02_dev *dev, bool mac_stopped)
 {
 	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
 	bool is_5ghz = chan->band == NL80211_BAND_5GHZ;
 
+	if (dev->cal.channel_cal_done)
+		return;
+
 	if (mt76x2_channel_silent(dev))
 		return;
 
-	mt76x2u_mac_stop(dev);
+	if (!mac_stopped)
+		mt76x2u_mac_stop(dev);
 
 	if (is_5ghz)
 		mt76x02_mcu_calibrate(dev, MCU_CAL_LC, 0, false);
@@ -37,7 +42,11 @@ void mt76x2u_phy_channel_calibrate(struct mt76x02_dev *dev)
 	mt76x02_mcu_calibrate(dev, MCU_CAL_TEMP_SENSOR, 0, false);
 	mt76x02_mcu_calibrate(dev, MCU_CAL_TX_SHAPING, 0, false);
 
-	mt76x2u_mac_resume(dev);
+	if (!mac_stopped)
+		mt76x2u_mac_resume(dev);
+	mt76x2_apply_gain_adj(dev);
+
+	dev->cal.channel_cal_done = true;
 }
 
 void mt76x2u_phy_calibrate(struct work_struct *work)
@@ -45,6 +54,7 @@ void mt76x2u_phy_calibrate(struct work_struct *work)
 	struct mt76x02_dev *dev;
 
 	dev = container_of(work, struct mt76x02_dev, cal_work.work);
+	mt76x2u_phy_channel_calibrate(dev, false);
 	mt76x2_phy_tssi_compensate(dev, false);
 	mt76x2_phy_update_channel_gain(dev);
 
@@ -165,7 +175,9 @@ int mt76x2u_phy_set_channel(struct mt76x02_dev *dev,
 	if (scan)
 		return 0;
 
+	mt76x2u_phy_channel_calibrate(dev, true);
 	mt76x02_init_agc_gain(dev);
+
 	if (mt76x2_tssi_enabled(dev)) {
 		/* init default values for temp compensation */
 		mt76_rmw_field(dev, MT_TX_ALC_CFG_1, MT_TX_ALC_CFG_1_TEMP_COMP,
-- 
cgit v1.2.3


From 9446a928e1478f27838dc57608a1ac3b5f203ddd Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 6 Nov 2018 17:59:47 +0100
Subject: mt76x2u: main: use mt76x02_bss_info_changed utility routine

Initialize bss_info_changed mac80211 callback to
mt76x02_bss_info_changed utility routine and remove duplicated code.
Use 8 as WCID index for sta interface

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt76x2/usb_main.c   | 23 +++-------------------
 1 file changed, 3 insertions(+), 20 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
index cad99715997e..a9ecc92875ae 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
@@ -50,11 +50,12 @@ static int mt76x2u_add_interface(struct ieee80211_hw *hw,
 				 struct ieee80211_vif *vif)
 {
 	struct mt76x02_dev *dev = hw->priv;
+	unsigned int idx = 8;
 
 	if (!ether_addr_equal(dev->mt76.macaddr, vif->addr))
 		mt76x02_mac_setaddr(dev, vif->addr);
 
-	mt76x02_vif_init(dev, vif, 0);
+	mt76x02_vif_init(dev, vif, idx);
 	return 0;
 }
 
@@ -83,24 +84,6 @@ mt76x2u_set_channel(struct mt76x02_dev *dev,
 	return err;
 }
 
-static void
-mt76x2u_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			 struct ieee80211_bss_conf *info, u32 changed)
-{
-	struct mt76x02_dev *dev = hw->priv;
-
-	mutex_lock(&dev->mt76.mutex);
-
-	if (changed & BSS_CHANGED_BSSID) {
-		mt76_wr(dev, MT_MAC_BSSID_DW0,
-			get_unaligned_le32(info->bssid));
-		mt76_wr(dev, MT_MAC_BSSID_DW1,
-			get_unaligned_le16(info->bssid + 4));
-	}
-
-	mutex_unlock(&dev->mt76.mutex);
-}
-
 static int
 mt76x2u_config(struct ieee80211_hw *hw, u32 changed)
 {
@@ -150,7 +133,7 @@ const struct ieee80211_ops mt76x2u_ops = {
 	.ampdu_action = mt76x02_ampdu_action,
 	.config = mt76x2u_config,
 	.wake_tx_queue = mt76_wake_tx_queue,
-	.bss_info_changed = mt76x2u_bss_info_changed,
+	.bss_info_changed = mt76x02_bss_info_changed,
 	.configure_filter = mt76x02_configure_filter,
 	.conf_tx = mt76x02_conf_tx,
 	.sw_scan_start = mt76x02_sw_scan,
-- 
cgit v1.2.3


From 93ac31680e57eb45723948102680b03d83e2684e Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 6 Nov 2018 17:59:48 +0100
Subject: mt76x2u: init: remove mt76x2u_init_beacon_offsets routine

Remove mt76x2u_init_beacon_offsets routine since the driver supports
just STA mode

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
index 8b280a4ea792..de0fbdb02c4d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
@@ -156,14 +156,6 @@ struct mt76x02_dev *mt76x2u_alloc_device(struct device *pdev)
 	return dev;
 }
 
-static void mt76x2u_init_beacon_offsets(struct mt76x02_dev *dev)
-{
-	mt76_wr(dev, MT_BCN_OFFSET(0), 0x18100800);
-	mt76_wr(dev, MT_BCN_OFFSET(1), 0x38302820);
-	mt76_wr(dev, MT_BCN_OFFSET(2), 0x58504840);
-	mt76_wr(dev, MT_BCN_OFFSET(3), 0x78706860);
-}
-
 int mt76x2u_init_hardware(struct mt76x02_dev *dev)
 {
 	int i, k, err;
@@ -200,8 +192,6 @@ int mt76x2u_init_hardware(struct mt76x02_dev *dev)
 	mt76x02_mac_setaddr(dev, dev->mt76.eeprom.data + MT_EE_MAC_ADDR);
 	dev->mt76.rxfilter = mt76_rr(dev, MT_RX_FILTR_CFG);
 
-	mt76x2u_init_beacon_offsets(dev);
-
 	if (!mt76x02_wait_for_txrx_idle(&dev->mt76))
 		return -ETIMEDOUT;
 
-- 
cgit v1.2.3


From 4ece1e0a86b35bbb43d8d3e5268e68c6b4c6294e Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Fri, 9 Nov 2018 11:56:10 +0100
Subject: mt76: remove wait argument from mt76x02_mcu_calibrate

We always wait for CMD_CALIBRATION_OP mcu message, but wait argument is used
for do additional MT_MCU_COM_REG0 register operations, which are needed
for mt76x2e devices and we can use appropriate check instead of wait argument.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    | 14 ++++++--------
 drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c   |  8 ++++----
 drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h   |  3 +--
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h |  2 +-
 .../net/wireless/mediatek/mt76/mt76x2/pci_phy.c    | 22 +++++++++++-----------
 drivers/net/wireless/mediatek/mt76/mt76x2/phy.c    |  4 ++--
 .../net/wireless/mediatek/mt76/mt76x2/usb_phy.c    | 22 +++++++++++-----------
 7 files changed, 36 insertions(+), 39 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index 275458891ce4..1eb1a802ed20 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -868,9 +868,8 @@ void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on)
 		return;
 
 	if (power_on) {
-		mt76x02_mcu_calibrate(dev, MCU_CAL_R, 0, false);
-		mt76x02_mcu_calibrate(dev, MCU_CAL_VCO, chan->hw_value,
-				      false);
+		mt76x02_mcu_calibrate(dev, MCU_CAL_R, 0);
+		mt76x02_mcu_calibrate(dev, MCU_CAL_VCO, chan->hw_value);
 		usleep_range(10, 20);
 
 		if (mt76x0_tssi_enabled(dev)) {
@@ -901,14 +900,14 @@ void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on)
 		val = 0x600;
 	}
 
-	mt76x02_mcu_calibrate(dev, MCU_CAL_FULL, val, false);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_FULL, val);
 	msleep(350);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_LC, is_5ghz, false);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_LC, is_5ghz);
 	usleep_range(15000, 20000);
 
 	mt76_wr(dev, MT_BBP(IBI, 9), reg_val);
 	mt76_wr(dev, MT_TX_ALC_CFG_0, tx_alc);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_RXDCOC, 1, false);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_RXDCOC, 1);
 }
 EXPORT_SYMBOL_GPL(mt76x0_phy_calibrate);
 
@@ -1044,8 +1043,7 @@ static void mt76x0_phy_temp_sensor(struct mt76x02_dev *dev)
 
 	if (abs(val - dev->cal.temp_vco) > 20) {
 		mt76x02_mcu_calibrate(dev, MCU_CAL_VCO,
-				      dev->mt76.chandef.chan->hw_value,
-				      false);
+				      dev->mt76.chandef.chan->hw_value);
 		dev->cal.temp_vco = val;
 	}
 	if (abs(val - dev->cal.temp) > 30) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
index 6015ba9ffdac..b7f4edb729e3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.c
@@ -165,8 +165,7 @@ int mt76x02_mcu_set_radio_state(struct mt76x02_dev *dev, bool on)
 }
 EXPORT_SYMBOL_GPL(mt76x02_mcu_set_radio_state);
 
-int mt76x02_mcu_calibrate(struct mt76x02_dev *dev, int type,
-			  u32 param, bool wait)
+int mt76x02_mcu_calibrate(struct mt76x02_dev *dev, int type, u32 param)
 {
 	struct {
 		__le32 id;
@@ -175,9 +174,10 @@ int mt76x02_mcu_calibrate(struct mt76x02_dev *dev, int type,
 		.id = cpu_to_le32(type),
 		.value = cpu_to_le32(param),
 	};
+	bool is_mt76x2e = mt76_is_mmio(dev) && is_mt76x2(dev);
 	int ret;
 
-	if (wait)
+	if (is_mt76x2e)
 		mt76_rmw(dev, MT_MCU_COM_REG0, BIT(31), 0);
 
 	ret = mt76_mcu_send_msg(dev, CMD_CALIBRATION_OP, &msg, sizeof(msg),
@@ -185,7 +185,7 @@ int mt76x02_mcu_calibrate(struct mt76x02_dev *dev, int type,
 	if (ret)
 		return ret;
 
-	if (wait &&
+	if (is_mt76x2e &&
 	    WARN_ON(!mt76_poll_msec(dev, MT_MCU_COM_REG0,
 				    BIT(31), BIT(31), 100)))
 		return -ETIMEDOUT;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
index 97025c31a986..7e4004120102 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mcu.h
@@ -97,8 +97,7 @@ struct mt76x02_patch_header {
 };
 
 int mt76x02_mcu_cleanup(struct mt76x02_dev *dev);
-int mt76x02_mcu_calibrate(struct mt76x02_dev *dev, int type,
-			  u32 param, bool wait);
+int mt76x02_mcu_calibrate(struct mt76x02_dev *dev, int type, u32 param);
 int mt76x02_mcu_msg_send(struct mt76_dev *mdev, int cmd, const void *data,
 			 int len, bool wait_resp);
 int mt76x02_mcu_function_select(struct mt76x02_dev *dev, enum mcu_function func,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index e5846a85d6ab..b259e4b50f1e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -78,7 +78,7 @@ void mt76x2_init_txpower(struct mt76x02_dev *dev,
 			 struct ieee80211_supported_band *sband);
 void mt76_write_mac_initvals(struct mt76x02_dev *dev);
 
-void mt76x2_phy_tssi_compensate(struct mt76x02_dev *dev, bool wait);
+void mt76x2_phy_tssi_compensate(struct mt76x02_dev *dev);
 void mt76x2_phy_set_txpower_regs(struct mt76x02_dev *dev,
 				 enum nl80211_band band);
 void mt76x2_configure_tx_delay(struct mt76x02_dev *dev,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c
index 63866b2fec64..da7cd40f56ff 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c
@@ -38,7 +38,7 @@ mt76x2_phy_tssi_init_cal(struct mt76x02_dev *dev)
 	if (mt76x02_ext_pa_enabled(dev, chan->band))
 		flag |= BIT(8);
 
-	mt76x02_mcu_calibrate(dev, MCU_CAL_TSSI, flag, true);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_TSSI, flag);
 	dev->cal.tssi_cal_done = true;
 	return true;
 }
@@ -62,13 +62,13 @@ mt76x2_phy_channel_calibrate(struct mt76x02_dev *dev, bool mac_stopped)
 		mt76x2_mac_stop(dev, false);
 
 	if (is_5ghz)
-		mt76x02_mcu_calibrate(dev, MCU_CAL_LC, 0, true);
+		mt76x02_mcu_calibrate(dev, MCU_CAL_LC, 0);
 
-	mt76x02_mcu_calibrate(dev, MCU_CAL_TX_LOFT, is_5ghz, true);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_TXIQ, is_5ghz, true);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_RXIQC_FI, is_5ghz, true);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_TEMP_SENSOR, 0, true);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_TX_SHAPING, 0, true);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_TX_LOFT, is_5ghz);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_TXIQ, is_5ghz);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_RXIQC_FI, is_5ghz);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_TEMP_SENSOR, 0);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_TX_SHAPING, 0);
 
 	if (!mac_stopped)
 		mt76x2_mac_resume(dev);
@@ -223,14 +223,14 @@ int mt76x2_phy_set_channel(struct mt76x02_dev *dev,
 		u8 val = mt76x02_eeprom_get(dev, MT_EE_BT_RCAL_RESULT);
 
 		if (val != 0xff)
-			mt76x02_mcu_calibrate(dev, MCU_CAL_R, 0, true);
+			mt76x02_mcu_calibrate(dev, MCU_CAL_R, 0);
 	}
 
-	mt76x02_mcu_calibrate(dev, MCU_CAL_RXDCOC, channel, true);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_RXDCOC, channel);
 
 	/* Rx LPF calibration */
 	if (!dev->cal.init_cal_done)
-		mt76x02_mcu_calibrate(dev, MCU_CAL_RC, 0, true);
+		mt76x02_mcu_calibrate(dev, MCU_CAL_RC, 0);
 
 	dev->cal.init_cal_done = true;
 
@@ -294,7 +294,7 @@ void mt76x2_phy_calibrate(struct work_struct *work)
 
 	dev = container_of(work, struct mt76x02_dev, cal_work.work);
 	mt76x2_phy_channel_calibrate(dev, false);
-	mt76x2_phy_tssi_compensate(dev, true);
+	mt76x2_phy_tssi_compensate(dev);
 	mt76x2_phy_temp_compensate(dev);
 	mt76x2_phy_update_channel_gain(dev);
 	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->cal_work,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
index 1b85fb415548..c9634a774705 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
@@ -210,7 +210,7 @@ void mt76x2_configure_tx_delay(struct mt76x02_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mt76x2_configure_tx_delay);
 
-void mt76x2_phy_tssi_compensate(struct mt76x02_dev *dev, bool wait)
+void mt76x2_phy_tssi_compensate(struct mt76x02_dev *dev)
 {
 	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
 	struct mt76x2_tx_power_info txp;
@@ -245,7 +245,7 @@ void mt76x2_phy_tssi_compensate(struct mt76x02_dev *dev, bool wait)
 			return;
 
 		usleep_range(10000, 20000);
-		mt76x02_mcu_calibrate(dev, MCU_CAL_DPD, chan->hw_value, wait);
+		mt76x02_mcu_calibrate(dev, MCU_CAL_DPD, chan->hw_value);
 		dev->cal.dpd_cal_done = true;
 	}
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
index a64268e8db42..11d414d86c68 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_phy.c
@@ -34,13 +34,13 @@ mt76x2u_phy_channel_calibrate(struct mt76x02_dev *dev, bool mac_stopped)
 		mt76x2u_mac_stop(dev);
 
 	if (is_5ghz)
-		mt76x02_mcu_calibrate(dev, MCU_CAL_LC, 0, false);
+		mt76x02_mcu_calibrate(dev, MCU_CAL_LC, 0);
 
-	mt76x02_mcu_calibrate(dev, MCU_CAL_TX_LOFT, is_5ghz, false);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_TXIQ, is_5ghz, false);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_RXIQC_FI, is_5ghz, false);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_TEMP_SENSOR, 0, false);
-	mt76x02_mcu_calibrate(dev, MCU_CAL_TX_SHAPING, 0, false);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_TX_LOFT, is_5ghz);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_TXIQ, is_5ghz);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_RXIQC_FI, is_5ghz);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_TEMP_SENSOR, 0);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_TX_SHAPING, 0);
 
 	if (!mac_stopped)
 		mt76x2u_mac_resume(dev);
@@ -55,7 +55,7 @@ void mt76x2u_phy_calibrate(struct work_struct *work)
 
 	dev = container_of(work, struct mt76x02_dev, cal_work.work);
 	mt76x2u_phy_channel_calibrate(dev, false);
-	mt76x2_phy_tssi_compensate(dev, false);
+	mt76x2_phy_tssi_compensate(dev);
 	mt76x2_phy_update_channel_gain(dev);
 
 	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->cal_work,
@@ -153,14 +153,14 @@ int mt76x2u_phy_set_channel(struct mt76x02_dev *dev,
 		u8 val = mt76x02_eeprom_get(dev, MT_EE_BT_RCAL_RESULT);
 
 		if (val != 0xff)
-			mt76x02_mcu_calibrate(dev, MCU_CAL_R, 0, false);
+			mt76x02_mcu_calibrate(dev, MCU_CAL_R, 0);
 	}
 
-	mt76x02_mcu_calibrate(dev, MCU_CAL_RXDCOC, channel, false);
+	mt76x02_mcu_calibrate(dev, MCU_CAL_RXDCOC, channel);
 
 	/* Rx LPF calibration */
 	if (!dev->cal.init_cal_done)
-		mt76x02_mcu_calibrate(dev, MCU_CAL_RC, 0, false);
+		mt76x02_mcu_calibrate(dev, MCU_CAL_RC, 0);
 	dev->cal.init_cal_done = true;
 
 	mt76_wr(dev, MT_BBP(AGC, 61), 0xff64a4e2);
@@ -195,7 +195,7 @@ int mt76x2u_phy_set_channel(struct mt76x02_dev *dev,
 				flag |= BIT(0);
 			if (mt76x02_ext_pa_enabled(dev, chan->band))
 				flag |= BIT(8);
-			mt76x02_mcu_calibrate(dev, MCU_CAL_TSSI, flag, false);
+			mt76x02_mcu_calibrate(dev, MCU_CAL_TSSI, flag);
 			dev->cal.tssi_cal_done = true;
 		}
 	}
-- 
cgit v1.2.3


From 79d1c94c9c78ea2f90a7218e16946a1dde2527a0 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 5 Nov 2018 21:11:39 +0100
Subject: mt76: avoid queue/status spinlocks while passing tx status to
 mac80211

There is some code in the mac80211 tx status processing code that could
potentially call back into the tx codepath.
To avoid deadlocks, make sure that no tx related spinlocks are taken
during the ieee80211_tx_status call.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/dma.c          | 11 +++--
 drivers/net/wireless/mediatek/mt76/mac80211.c     |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76.h         | 30 +++++-------
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c  | 11 +++--
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c |  2 +-
 drivers/net/wireless/mediatek/mt76/tx.c           | 58 +++++++++++++++++++----
 6 files changed, 76 insertions(+), 38 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 2d7bd26875c6..d62f8d9f2ea1 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -157,17 +157,20 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, enum mt76_txq_id qid, bool flush)
 		if (entry.schedule)
 			q->swq_queued--;
 
-		if (entry.skb)
+		q->tail = (q->tail + 1) % q->ndesc;
+		q->queued--;
+
+		if (entry.skb) {
+			spin_unlock_bh(&q->lock);
 			dev->drv->tx_complete_skb(dev, q, &entry, flush);
+			spin_lock_bh(&q->lock);
+		}
 
 		if (entry.txwi) {
 			mt76_put_txwi(dev, entry.txwi);
 			wake = true;
 		}
 
-		q->tail = (q->tail + 1) % q->ndesc;
-		q->queued--;
-
 		if (!flush && q->tail == last)
 			last = ioread32(&q->regs->dma_idx);
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 85e05a825b5d..3be73b021d27 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -359,7 +359,7 @@ void mt76_unregister_device(struct mt76_dev *dev)
 {
 	struct ieee80211_hw *hw = dev->hw;
 
-	mt76_tx_status_flush(dev, NULL);
+	mt76_tx_status_check(dev, NULL, true);
 	ieee80211_unregister_hw(hw);
 	mt76_tx_free(dev);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index e1d89163ee6b..ea74ba00aebc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -648,28 +648,22 @@ void mt76_rx_aggr_stop(struct mt76_dev *dev, struct mt76_wcid *wcid, u8 tid);
 
 void mt76_wcid_key_setup(struct mt76_dev *dev, struct mt76_wcid *wcid,
 			 struct ieee80211_key_conf *key);
+
+void mt76_tx_status_lock(struct mt76_dev *dev, struct sk_buff_head *list)
+			 __acquires(&dev->status_list.lock);
+void mt76_tx_status_unlock(struct mt76_dev *dev, struct sk_buff_head *list)
+			   __releases(&dev->status_list.lock);
+
 int mt76_tx_status_skb_add(struct mt76_dev *dev, struct mt76_wcid *wcid,
 			   struct sk_buff *skb);
 struct sk_buff *mt76_tx_status_skb_get(struct mt76_dev *dev,
-				       struct mt76_wcid *wcid, int pktid);
-void mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb);
+				       struct mt76_wcid *wcid, int pktid,
+				       struct sk_buff_head *list);
+void mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb,
+			     struct sk_buff_head *list);
 void mt76_tx_complete_skb(struct mt76_dev *dev, struct sk_buff *skb);
-
-static inline void
-mt76_tx_status_check(struct mt76_dev *dev)
-{
-	spin_lock_bh(&dev->status_list.lock);
-	mt76_tx_status_skb_get(dev, NULL, 0);
-	spin_unlock_bh(&dev->status_list.lock);
-}
-
-static inline void
-mt76_tx_status_flush(struct mt76_dev *dev, struct mt76_wcid *wcid)
-{
-	spin_lock_bh(&dev->status_list.lock);
-	mt76_tx_status_skb_get(dev, wcid, -1);
-	spin_unlock_bh(&dev->status_list.lock);
-}
+void mt76_tx_status_check(struct mt76_dev *dev, struct mt76_wcid *wcid,
+			  bool flush);
 
 struct ieee80211_sta *mt76_rx_convert(struct sk_buff *skb);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index 59b336e34cb5..4c35d3f7fb15 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -438,12 +438,13 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 	struct mt76_wcid *wcid = NULL;
 	struct mt76x02_sta *msta = NULL;
 	struct mt76_dev *mdev = &dev->mt76;
+	struct sk_buff_head list;
 
 	if (stat->pktid == MT_PACKET_ID_NO_ACK)
 		return;
 
 	rcu_read_lock();
-	spin_lock_bh(&mdev->status_list.lock);
+	mt76_tx_status_lock(mdev, &list);
 
 	if (stat->wcid < ARRAY_SIZE(dev->mt76.wcid))
 		wcid = rcu_dereference(dev->mt76.wcid[stat->wcid]);
@@ -459,7 +460,7 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 	if (wcid) {
 		if (stat->pktid)
 			status.skb = mt76_tx_status_skb_get(mdev, wcid,
-							    stat->pktid);
+							    stat->pktid, &list);
 		if (status.skb)
 			status.info = IEEE80211_SKB_CB(status.skb);
 	}
@@ -490,12 +491,12 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 	}
 
 	if (status.skb)
-		mt76_tx_status_skb_done(mdev, status.skb);
+		mt76_tx_status_skb_done(mdev, status.skb, &list);
 	else
 		ieee80211_tx_status_ext(mt76_hw(dev), &status);
 
 out:
-	spin_unlock_bh(&mdev->status_list.lock);
+	mt76_tx_status_unlock(mdev, &list);
 	rcu_read_unlock();
 }
 
@@ -818,7 +819,7 @@ void mt76x02_mac_work(struct work_struct *work)
 	if (!dev->beacon_mask)
 		mt76x02_check_mac_err(dev);
 
-	mt76_tx_status_check(&dev->mt76);
+	mt76_tx_status_check(&dev->mt76, NULL, false);
 
 	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mac_work,
 				     MT_CALIBRATE_INTERVAL);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 48f2f5382b57..d2ac1a84668c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -217,7 +217,7 @@ int mt76x02_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	int i;
 
 	mutex_lock(&dev->mt76.mutex);
-	mt76_tx_status_flush(&dev->mt76, &msta->wcid);
+	mt76_tx_status_check(&dev->mt76, &msta->wcid, true);
 	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
 	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
 		mt76_txq_remove(&dev->mt76, sta->txq[i]);
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index e6cd583aafd3..e42a24628e4f 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -103,8 +103,33 @@ mt76_check_agg_ssn(struct mt76_txq *mtxq, struct sk_buff *skb)
 	mtxq->agg_ssn = le16_to_cpu(hdr->seq_ctrl) + 0x10;
 }
 
+void
+mt76_tx_status_lock(struct mt76_dev *dev, struct sk_buff_head *list)
+		   __acquires(&dev->status_list.lock)
+{
+	__skb_queue_head_init(list);
+	spin_lock_bh(&dev->status_list.lock);
+	__acquire(&dev->status_list.lock);
+}
+EXPORT_SYMBOL_GPL(mt76_tx_status_lock);
+
+void
+mt76_tx_status_unlock(struct mt76_dev *dev, struct sk_buff_head *list)
+		      __releases(&dev->status_list.unlock)
+{
+	struct sk_buff *skb;
+
+	spin_unlock_bh(&dev->status_list.lock);
+	__release(&dev->status_list.unlock);
+
+	while ((skb = __skb_dequeue(list)) != NULL)
+		ieee80211_tx_status(dev->hw, skb);
+}
+EXPORT_SYMBOL_GPL(mt76_tx_status_unlock);
+
 static void
-__mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb, u8 flags)
+__mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb, u8 flags,
+			  struct sk_buff_head *list)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct mt76_tx_cb *cb = mt76_tx_skb_cb(skb);
@@ -125,13 +150,14 @@ __mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb, u8 flags)
 		info->flags |= IEEE80211_TX_STAT_ACK;
 	}
 
-	ieee80211_tx_status(dev->hw, skb);
+	__skb_queue_tail(list, skb);
 }
 
 void
-mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb)
+mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb,
+			struct sk_buff_head *list)
 {
-	__mt76_tx_status_skb_done(dev, skb, MT_TX_CB_TXS_DONE);
+	__mt76_tx_status_skb_done(dev, skb, MT_TX_CB_TXS_DONE, list);
 }
 EXPORT_SYMBOL_GPL(mt76_tx_status_skb_done);
 
@@ -173,7 +199,8 @@ mt76_tx_status_skb_add(struct mt76_dev *dev, struct mt76_wcid *wcid,
 EXPORT_SYMBOL_GPL(mt76_tx_status_skb_add);
 
 struct sk_buff *
-mt76_tx_status_skb_get(struct mt76_dev *dev, struct mt76_wcid *wcid, int pktid)
+mt76_tx_status_skb_get(struct mt76_dev *dev, struct mt76_wcid *wcid, int pktid,
+		       struct sk_buff_head *list)
 {
 	struct sk_buff *skb, *tmp;
 
@@ -194,23 +221,36 @@ mt76_tx_status_skb_get(struct mt76_dev *dev, struct mt76_wcid *wcid, int pktid)
 			continue;
 
 		__mt76_tx_status_skb_done(dev, skb, MT_TX_CB_TXS_FAILED |
-						    MT_TX_CB_TXS_DONE);
+						    MT_TX_CB_TXS_DONE, list);
 	}
 
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(mt76_tx_status_skb_get);
 
+void
+mt76_tx_status_check(struct mt76_dev *dev, struct mt76_wcid *wcid, bool flush)
+{
+	struct sk_buff_head list;
+
+	mt76_tx_status_lock(dev, &list);
+	mt76_tx_status_skb_get(dev, wcid, flush ? -1 : 0, &list);
+	mt76_tx_status_unlock(dev, &list);
+}
+EXPORT_SYMBOL_GPL(mt76_tx_status_check);
+
 void mt76_tx_complete_skb(struct mt76_dev *dev, struct sk_buff *skb)
 {
+	struct sk_buff_head list;
+
 	if (!skb->prev) {
 		ieee80211_free_txskb(dev->hw, skb);
 		return;
 	}
 
-	spin_lock_bh(&dev->status_list.lock);
-	__mt76_tx_status_skb_done(dev, skb, MT_TX_CB_DMA_DONE);
-	spin_unlock_bh(&dev->status_list.lock);
+	mt76_tx_status_lock(dev, &list);
+	__mt76_tx_status_skb_done(dev, skb, MT_TX_CB_DMA_DONE, &list);
+	mt76_tx_status_unlock(dev, &list);
 }
 EXPORT_SYMBOL_GPL(mt76_tx_complete_skb);
 
-- 
cgit v1.2.3


From 13c6d5f8370a55f556443e32c314f8b3abf842ad Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Fri, 9 Nov 2018 13:43:58 +0100
Subject: mt76: do not wake tx queues during flush

While the queue is being cleaned up, the stack must not attempt to add
any extra packets

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/dma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index d62f8d9f2ea1..e2ba26378575 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -168,7 +168,7 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, enum mt76_txq_id qid, bool flush)
 
 		if (entry.txwi) {
 			mt76_put_txwi(dev, entry.txwi);
-			wake = true;
+			wake = !flush;
 		}
 
 		if (!flush && q->tail == last)
-- 
cgit v1.2.3


From c2a1a5e13684cafb866f15af2394119f62c423a9 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 13 Nov 2018 11:25:47 +0100
Subject: mt76: fix race condition in station removal

If there are still pending packets in the tx queue when removing a station,
it could possibly lead to a call to further attempts to pull packets from
the mac80211 tx queue after it has already been removed from the scheduling
list.
Prevent this from happening by calling synchronize_rcu after deleting the
wcid pointer before further cleaning up the tx queues.
To be extra careful, ensure that mtxq->list is always initialized properly.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c | 4 +++-
 drivers/net/wireless/mediatek/mt76/tx.c           | 2 +-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index d2ac1a84668c..1a51193d5d59 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -216,9 +216,11 @@ int mt76x02_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	int idx = msta->wcid.idx;
 	int i;
 
+	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
+	synchronize_rcu();
+
 	mutex_lock(&dev->mt76.mutex);
 	mt76_tx_status_check(&dev->mt76, &msta->wcid, true);
-	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
 	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
 		mt76_txq_remove(&dev->mt76, sta->txq[i]);
 	mt76x02_mac_wcid_set_drop(dev, idx, true);
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index e42a24628e4f..f4093dc0e174 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -590,7 +590,7 @@ void mt76_txq_remove(struct mt76_dev *dev, struct ieee80211_txq *txq)
 
 	spin_lock_bh(&hwq->lock);
 	if (!list_empty(&mtxq->list))
-		list_del(&mtxq->list);
+		list_del_init(&mtxq->list);
 	spin_unlock_bh(&hwq->lock);
 
 	while ((skb = skb_dequeue(&mtxq->retry_q)) != NULL)
-- 
cgit v1.2.3


From 723b90dc7d39e5f867cefc6a75468f9425fc9855 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 13 Nov 2018 11:33:46 +0100
Subject: mt76: add mt76_sta_remove helper

This allows station removal code to be used by mt7603 later

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c     | 19 +++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76.h         |  2 ++
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c | 12 +++---------
 3 files changed, 24 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 3be73b021d27..1098919f5498 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -630,3 +630,22 @@ void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q,
 	mt76_rx_complete(dev, &frames, napi);
 }
 EXPORT_SYMBOL_GPL(mt76_rx_poll_complete);
+
+void mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
+		     struct ieee80211_sta *sta)
+{
+	struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv;
+	int idx = wcid->idx;
+	int i;
+
+	rcu_assign_pointer(dev->wcid[idx], NULL);
+	synchronize_rcu();
+
+	mutex_lock(&dev->mutex);
+	mt76_tx_status_check(dev, wcid, true);
+	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
+		mt76_txq_remove(dev, sta->txq[i]);
+	mt76_wcid_free(dev->wcid_mask, idx);
+	mutex_unlock(&dev->mutex);
+}
+EXPORT_SYMBOL_GPL(mt76_sta_remove);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index ea74ba00aebc..878836fe80d3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -664,6 +664,8 @@ void mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb,
 void mt76_tx_complete_skb(struct mt76_dev *dev, struct sk_buff *skb);
 void mt76_tx_status_check(struct mt76_dev *dev, struct mt76_wcid *wcid,
 			  bool flush);
+void mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
+		     struct ieee80211_sta *sta);
 
 struct ieee80211_sta *mt76_rx_convert(struct sk_buff *skb);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 1a51193d5d59..0ea7ab9cf0c6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -212,19 +212,13 @@ int mt76x02_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta)
 {
 	struct mt76x02_dev *dev = hw->priv;
-	struct mt76x02_sta *msta = (struct mt76x02_sta *)sta->drv_priv;
-	int idx = msta->wcid.idx;
-	int i;
+	struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv;
+	int idx = wcid->idx;
 
-	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
-	synchronize_rcu();
+	mt76_sta_remove(&dev->mt76, vif, sta);
 
 	mutex_lock(&dev->mt76.mutex);
-	mt76_tx_status_check(&dev->mt76, &msta->wcid, true);
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
-		mt76_txq_remove(&dev->mt76, sta->txq[i]);
 	mt76x02_mac_wcid_set_drop(dev, idx, true);
-	mt76_wcid_free(dev->mt76.wcid_mask, idx);
 	mt76x02_mac_wcid_setup(dev, idx, 0, NULL);
 	mutex_unlock(&dev->mt76.mutex);
 
-- 
cgit v1.2.3


From c30bdfea80cca1348ef6e0c611d75793e533e4c7 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 15 Nov 2018 18:44:37 +0100
Subject: mt76: mt76x02: make group_wcid the first member in struct mt76x02_vif

Allows mt76 core to cast vif->drv_priv to struct mt76_wcid

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index b076c4305585..cf5c06a0a58a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -37,9 +37,8 @@ struct mt76x02_tx_status {
 #define MT_MAX_VIFS		8
 
 struct mt76x02_vif {
+	struct mt76_wcid group_wcid; /* must be first */
 	u8 idx;
-
-	struct mt76_wcid group_wcid;
 };
 
 DECLARE_EWMA(signal, 10, 8);
-- 
cgit v1.2.3


From 54f1bf8a9fddf6e9af5b037a47be3074b1aabe96 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 15 Nov 2018 19:01:21 +0100
Subject: mt76: mt76x02: remove mt76x02_txq_init

Open-coding it simplifies the code

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c  | 23 -----------------------
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.h  |  2 --
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c | 18 +++++++++++++++---
 3 files changed, 15 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index 4c35d3f7fb15..c08bf371e527 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -126,29 +126,6 @@ void mt76x02_mac_wcid_set_drop(struct mt76x02_dev *dev, u8 idx, bool drop)
 		mt76_wr(dev, MT_WCID_DROP(idx), (val & ~bit) | (bit * drop));
 }
 
-void mt76x02_txq_init(struct mt76x02_dev *dev, struct ieee80211_txq *txq)
-{
-	struct mt76_txq *mtxq;
-
-	if (!txq)
-		return;
-
-	mtxq = (struct mt76_txq *) txq->drv_priv;
-	if (txq->sta) {
-		struct mt76x02_sta *sta;
-
-		sta = (struct mt76x02_sta *) txq->sta->drv_priv;
-		mtxq->wcid = &sta->wcid;
-	} else {
-		struct mt76x02_vif *mvif;
-
-		mvif = (struct mt76x02_vif *) txq->vif->drv_priv;
-		mtxq->wcid = &mvif->group_wcid;
-	}
-
-	mt76_txq_init(&dev->mt76, txq);
-}
-
 static __le16
 mt76x02_mac_tx_rate_val(struct mt76x02_dev *dev,
 			const struct ieee80211_tx_rate *rate, u8 *nss_val)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index cf5c06a0a58a..4e597004c445 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -178,8 +178,6 @@ static inline bool mt76x02_wait_for_mac(struct mt76_dev *dev)
 	return false;
 }
 
-void mt76x02_txq_init(struct mt76x02_dev *dev, struct ieee80211_txq *txq);
-
 void mt76x02_mac_set_short_preamble(struct mt76x02_dev *dev, bool enable);
 int mt76x02_mac_shared_key_setup(struct mt76x02_dev *dev, u8 vif_idx,
 				 u8 key_idx, struct ieee80211_key_conf *key);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 0ea7ab9cf0c6..6eb892d6b676 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -191,8 +191,16 @@ int mt76x02_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	msta->wcid.hw_key_idx = -1;
 	mt76x02_mac_wcid_setup(dev, idx, mvif->idx, sta->addr);
 	mt76x02_mac_wcid_set_drop(dev, idx, false);
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
-		mt76x02_txq_init(dev, sta->txq[i]);
+	for (i = 0; i < ARRAY_SIZE(sta->txq); i++) {
+		struct mt76_txq *mtxq;
+
+		if (!sta->txq[i])
+			continue;
+
+		mtxq = (struct mt76_txq *) sta->txq[i]->drv_priv;
+		mtxq->wcid = &msta->wcid;
+		mt76_txq_init(&dev->mt76, sta->txq[i]);
+	}
 
 	if (vif->type == NL80211_IFTYPE_AP)
 		set_bit(MT_WCID_FLAG_CHECK_PS, &msta->wcid.flags);
@@ -230,11 +238,15 @@ void mt76x02_vif_init(struct mt76x02_dev *dev, struct ieee80211_vif *vif,
 		      unsigned int idx)
 {
 	struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
+	struct mt76_txq *mtxq;
 
 	mvif->idx = idx;
 	mvif->group_wcid.idx = MT_VIF_WCID(idx);
 	mvif->group_wcid.hw_key_idx = -1;
-	mt76x02_txq_init(dev, vif->txq);
+	mtxq = (struct mt76_txq *) vif->txq->drv_priv;
+	mtxq->wcid = &mvif->group_wcid;
+
+	mt76_txq_init(&dev->mt76, vif->txq);
 }
 EXPORT_SYMBOL_GPL(mt76x02_vif_init);
 
-- 
cgit v1.2.3


From e28487ea84a9c081c6d8d7da319427f7fcc32ff5 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Fri, 16 Nov 2018 10:49:14 +0100
Subject: mt76: replace sta_add/remove ops with common sta_state function

Allows adding unassociated stations from mac80211

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c      | 64 +++++++++++++++++++++-
 drivers/net/wireless/mediatek/mt76/mt76.h          | 12 +++-
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c    |  5 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c    |  5 +-
 drivers/net/wireless/mediatek/mt76/mt76x02.h       |  8 +--
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c  | 43 +++------------
 .../net/wireless/mediatek/mt76/mt76x2/pci_init.c   |  2 +
 .../net/wireless/mediatek/mt76/mt76x2/pci_main.c   |  3 +-
 .../net/wireless/mediatek/mt76/mt76x2/usb_init.c   |  2 +
 .../net/wireless/mediatek/mt76/mt76x2/usb_main.c   |  3 +-
 10 files changed, 95 insertions(+), 52 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 1098919f5498..b33074cf7e00 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -631,8 +631,43 @@ void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q,
 }
 EXPORT_SYMBOL_GPL(mt76_rx_poll_complete);
 
-void mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
-		     struct ieee80211_sta *sta)
+static int
+mt76_sta_add(struct mt76_dev *dev, struct ieee80211_vif *vif,
+	     struct ieee80211_sta *sta)
+{
+	struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv;
+	int ret;
+	int i;
+
+	mutex_lock(&dev->mutex);
+
+	ret = dev->drv->sta_add(dev, vif, sta);
+	if (ret)
+		goto out;
+
+	for (i = 0; i < ARRAY_SIZE(sta->txq); i++) {
+		struct mt76_txq *mtxq;
+
+		if (!sta->txq[i])
+			continue;
+
+		mtxq = (struct mt76_txq *)sta->txq[i]->drv_priv;
+		mtxq->wcid = wcid;
+
+		mt76_txq_init(dev, sta->txq[i]);
+	}
+
+	rcu_assign_pointer(dev->wcid[wcid->idx], wcid);
+
+out:
+	mutex_unlock(&dev->mutex);
+
+	return ret;
+}
+
+static void
+mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
+	        struct ieee80211_sta *sta)
 {
 	struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv;
 	int idx = wcid->idx;
@@ -642,10 +677,33 @@ void mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
 	synchronize_rcu();
 
 	mutex_lock(&dev->mutex);
+
+	if (dev->drv->sta_remove)
+		dev->drv->sta_remove(dev, vif, sta);
+
 	mt76_tx_status_check(dev, wcid, true);
 	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
 		mt76_txq_remove(dev, sta->txq[i]);
 	mt76_wcid_free(dev->wcid_mask, idx);
+
 	mutex_unlock(&dev->mutex);
 }
-EXPORT_SYMBOL_GPL(mt76_sta_remove);
+
+int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   struct ieee80211_sta *sta,
+		   enum ieee80211_sta_state old_state,
+		   enum ieee80211_sta_state new_state)
+{
+	struct mt76_dev *dev = hw->priv;
+
+	if (old_state == IEEE80211_STA_NOTEXIST &&
+	    new_state == IEEE80211_STA_NONE)
+		return mt76_sta_add(dev, vif, sta);
+
+	if (old_state == IEEE80211_STA_NONE &&
+		 new_state == IEEE80211_STA_NOTEXIST)
+		mt76_sta_remove(dev, vif, sta);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76_sta_state);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 878836fe80d3..5cd508a68609 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -288,6 +288,12 @@ struct mt76_driver_ops {
 
 	void (*sta_ps)(struct mt76_dev *dev, struct ieee80211_sta *sta,
 		       bool ps);
+
+	int (*sta_add)(struct mt76_dev *dev, struct ieee80211_vif *vif,
+		       struct ieee80211_sta *sta);
+
+	void (*sta_remove)(struct mt76_dev *dev, struct ieee80211_vif *vif,
+			   struct ieee80211_sta *sta);
 };
 
 struct mt76_channel_state {
@@ -664,8 +670,10 @@ void mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb,
 void mt76_tx_complete_skb(struct mt76_dev *dev, struct sk_buff *skb);
 void mt76_tx_status_check(struct mt76_dev *dev, struct mt76_wcid *wcid,
 			  bool flush);
-void mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
-		     struct ieee80211_sta *sta);
+int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   struct ieee80211_sta *sta,
+		   enum ieee80211_sta_state old_state,
+		   enum ieee80211_sta_state new_state);
 
 struct ieee80211_sta *mt76_rx_convert(struct sk_buff *skb);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 757816d2b1ab..d895b6f3dc44 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -90,8 +90,7 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.config = mt76x0_config,
 	.configure_filter = mt76x02_configure_filter,
 	.bss_info_changed = mt76x02_bss_info_changed,
-	.sta_add = mt76x02_sta_add,
-	.sta_remove = mt76x02_sta_remove,
+	.sta_state = mt76_sta_state,
 	.set_key = mt76x02_set_key,
 	.conf_tx = mt76x02_conf_tx,
 	.sw_scan_start = mt76x02_sw_scan,
@@ -162,6 +161,8 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		.rx_skb = mt76x02_queue_rx_skb,
 		.rx_poll_complete = mt76x02_rx_poll_complete,
 		.sta_ps = mt76x02_sta_ps,
+		.sta_add = mt76x02_sta_add,
+		.sta_remove = mt76x02_sta_remove,
 	};
 	struct mt76x02_dev *dev;
 	int ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 35b98661632a..0e6b43bb4678 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -146,8 +146,7 @@ static const struct ieee80211_ops mt76x0u_ops = {
 	.config = mt76x0_config,
 	.configure_filter = mt76x02_configure_filter,
 	.bss_info_changed = mt76x02_bss_info_changed,
-	.sta_add = mt76x02_sta_add,
-	.sta_remove = mt76x02_sta_remove,
+	.sta_state = mt76_sta_state,
 	.set_key = mt76x02_set_key,
 	.conf_tx = mt76x02_conf_tx,
 	.sw_scan_start = mt76x02_sw_scan,
@@ -219,6 +218,8 @@ static int mt76x0u_probe(struct usb_interface *usb_intf,
 		.tx_complete_skb = mt76x02u_tx_complete_skb,
 		.tx_status_data = mt76x02_tx_status_data,
 		.rx_skb = mt76x02_queue_rx_skb,
+		.sta_add = mt76x02_sta_add,
+		.sta_remove = mt76x02_sta_remove,
 	};
 	struct usb_device *usb_dev = interface_to_usbdev(usb_intf);
 	struct mt76x02_dev *dev;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 65daa3d3c289..b1d83dd34204 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -110,10 +110,10 @@ void mt76x02_init_device(struct mt76x02_dev *dev);
 void mt76x02_configure_filter(struct ieee80211_hw *hw,
 			     unsigned int changed_flags,
 			     unsigned int *total_flags, u64 multicast);
-int mt76x02_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		   struct ieee80211_sta *sta);
-int mt76x02_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		      struct ieee80211_sta *sta);
+int mt76x02_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
+		    struct ieee80211_sta *sta);
+void mt76x02_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
+			struct ieee80211_sta *sta);
 
 void mt76x02_config_mac_addr_list(struct mt76x02_dev *dev);
 void mt76x02_vif_init(struct mt76x02_dev *dev, struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 6eb892d6b676..3a70e5bf7d42 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -167,23 +167,17 @@ void mt76x02_configure_filter(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL_GPL(mt76x02_configure_filter);
 
-int mt76x02_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+int mt76x02_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		    struct ieee80211_sta *sta)
 {
-	struct mt76x02_dev *dev = hw->priv;
+	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
 	struct mt76x02_sta *msta = (struct mt76x02_sta *)sta->drv_priv;
 	struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
-	int ret = 0;
 	int idx = 0;
-	int i;
-
-	mutex_lock(&dev->mt76.mutex);
 
 	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, ARRAY_SIZE(dev->mt76.wcid));
-	if (idx < 0) {
-		ret = -ENOSPC;
-		goto out;
-	}
+	if (idx < 0)
+		return -ENOSPC;
 
 	msta->vif = mvif;
 	msta->wcid.sta = 1;
@@ -191,46 +185,25 @@ int mt76x02_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	msta->wcid.hw_key_idx = -1;
 	mt76x02_mac_wcid_setup(dev, idx, mvif->idx, sta->addr);
 	mt76x02_mac_wcid_set_drop(dev, idx, false);
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++) {
-		struct mt76_txq *mtxq;
-
-		if (!sta->txq[i])
-			continue;
-
-		mtxq = (struct mt76_txq *) sta->txq[i]->drv_priv;
-		mtxq->wcid = &msta->wcid;
-		mt76_txq_init(&dev->mt76, sta->txq[i]);
-	}
 
 	if (vif->type == NL80211_IFTYPE_AP)
 		set_bit(MT_WCID_FLAG_CHECK_PS, &msta->wcid.flags);
 
 	ewma_signal_init(&msta->rssi);
 
-	rcu_assign_pointer(dev->mt76.wcid[idx], &msta->wcid);
-
-out:
-	mutex_unlock(&dev->mt76.mutex);
-
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(mt76x02_sta_add);
 
-int mt76x02_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		       struct ieee80211_sta *sta)
+void mt76x02_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
+			struct ieee80211_sta *sta)
 {
-	struct mt76x02_dev *dev = hw->priv;
+	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
 	struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv;
 	int idx = wcid->idx;
 
-	mt76_sta_remove(&dev->mt76, vif, sta);
-
-	mutex_lock(&dev->mt76.mutex);
 	mt76x02_mac_wcid_set_drop(dev, idx, true);
 	mt76x02_mac_wcid_setup(dev, idx, 0, NULL);
-	mutex_unlock(&dev->mt76.mutex);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(mt76x02_sta_remove);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 843dda261cf8..6eaab156387a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -323,6 +323,8 @@ struct mt76x02_dev *mt76x2_alloc_device(struct device *pdev)
 		.rx_skb = mt76x02_queue_rx_skb,
 		.rx_poll_complete = mt76x02_rx_poll_complete,
 		.sta_ps = mt76x02_sta_ps,
+		.sta_add = mt76x02_sta_add,
+		.sta_remove = mt76x02_sta_remove,
 	};
 	struct mt76x02_dev *dev;
 	struct mt76_dev *mdev;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
index 3d73926837bf..b54a32397486 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
@@ -182,8 +182,7 @@ const struct ieee80211_ops mt76x2_ops = {
 	.config = mt76x2_config,
 	.configure_filter = mt76x02_configure_filter,
 	.bss_info_changed = mt76x02_bss_info_changed,
-	.sta_add = mt76x02_sta_add,
-	.sta_remove = mt76x02_sta_remove,
+	.sta_state = mt76_sta_state,
 	.set_key = mt76x02_set_key,
 	.conf_tx = mt76x02_conf_tx,
 	.sw_scan_start = mt76x02_sw_scan,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
index de0fbdb02c4d..0be3784f44fb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
@@ -141,6 +141,8 @@ struct mt76x02_dev *mt76x2u_alloc_device(struct device *pdev)
 		.tx_complete_skb = mt76x02u_tx_complete_skb,
 		.tx_status_data = mt76x02_tx_status_data,
 		.rx_skb = mt76x02_queue_rx_skb,
+		.sta_add = mt76x02_sta_add,
+		.sta_remove = mt76x02_sta_remove,
 	};
 	struct mt76x02_dev *dev;
 	struct mt76_dev *mdev;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
index a9ecc92875ae..2b48cc51a30d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
@@ -127,8 +127,7 @@ const struct ieee80211_ops mt76x2u_ops = {
 	.stop = mt76x2u_stop,
 	.add_interface = mt76x2u_add_interface,
 	.remove_interface = mt76x02_remove_interface,
-	.sta_add = mt76x02_sta_add,
-	.sta_remove = mt76x02_sta_remove,
+	.sta_state = mt76_sta_state,
 	.set_key = mt76x02_set_key,
 	.ampdu_action = mt76x02_ampdu_action,
 	.config = mt76x2u_config,
-- 
cgit v1.2.3


From 1b974aa43ae22b4626721d11dd755a8541bb32de Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Tue, 27 Nov 2018 14:59:06 +0530
Subject: cxgb4: number of VFs supported is not always 16

Total number of VFs supported by PF is used to determine the last
byte of VF's mac address. Number of VFs supported is not always
16, use the variable nvfs to get the number of VFs supported
rather than hard coding it to 16.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 7f76ad9e1ad6..6ba9099ca7fe 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2646,7 +2646,7 @@ static void cxgb4_mgmt_fill_vf_station_mac_addr(struct adapter *adap)
 
 	for (vf = 0, nvfs = pci_sriov_get_totalvfs(adap->pdev);
 		vf < nvfs; vf++) {
-		macaddr[5] = adap->pf * 16 + vf;
+		macaddr[5] = adap->pf * nvfs + vf;
 		ether_addr_copy(adap->vfinfo[vf].vf_mac_addr, macaddr);
 	}
 }
-- 
cgit v1.2.3


From 91c459561bfdc67eb3cb4a5d149e9cbfa4400d7f Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Tue, 27 Nov 2018 15:40:59 +0000
Subject: net/flow_dissector: correct comments on enum flow_dissector_key_id

There are no such structs flow_dissector_key_flow_vlan or
 flow_dissector_key_flow_tags, the actual structs used are struct
 flow_dissector_key_vlan and struct flow_dissector_key_tags.  So correct the
 comments against FLOW_DISSECTOR_KEY_VLAN, FLOW_DISSECTOR_KEY_FLOW_LABEL and
 FLOW_DISSECTOR_KEY_CVLAN to refer to those.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_dissector.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 6a4586dcdede..2b26979efb48 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -209,8 +209,8 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */
 	FLOW_DISSECTOR_KEY_TIPC, /* struct flow_dissector_key_tipc */
 	FLOW_DISSECTOR_KEY_ARP, /* struct flow_dissector_key_arp */
-	FLOW_DISSECTOR_KEY_VLAN, /* struct flow_dissector_key_flow_vlan */
-	FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_flow_tags */
+	FLOW_DISSECTOR_KEY_VLAN, /* struct flow_dissector_key_vlan */
+	FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_tags */
 	FLOW_DISSECTOR_KEY_GRE_KEYID, /* struct flow_dissector_key_keyid */
 	FLOW_DISSECTOR_KEY_MPLS_ENTROPY, /* struct flow_dissector_key_keyid */
 	FLOW_DISSECTOR_KEY_ENC_KEYID, /* struct flow_dissector_key_keyid */
@@ -221,7 +221,7 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */
 	FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */
 	FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */
-	FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_flow_vlan */
+	FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_vlan */
 	FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */
 	FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */
 
-- 
cgit v1.2.3


From b0e3f1bdf9e7140fd1151af575f468b5827a61e1 Mon Sep 17 00:00:00 2001
From: Geneviève Bastien <gbastien@versatic.net>
Date: Tue, 27 Nov 2018 12:52:39 -0500
Subject: net: Add trace events for all receive exit points
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Trace events are already present for the receive entry points, to indicate
how the reception entered the stack.

This patch adds the corresponding exit trace events that will bound the
reception such that all events occurring between the entry and the exit
can be considered as part of the reception context. This greatly helps
for dependency and root cause analyses.

Without this, it is not possible with tracepoint instrumentation to
determine whether a sched_wakeup event following a netif_receive_skb
event is the result of the packet reception or a simple coincidence after
further processing by the thread. It is possible using other mechanisms
like kretprobes, but considering the "entry" points are already present,
it would be good to add the matching exit events.

In addition to linking packets with wakeups, the entry/exit event pair
can also be used to perform network stack latency analyses.

Signed-off-by: Geneviève Bastien <gbastien@versatic.net>
CC: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Ingo Molnar <mingo@redhat.com>
CC: David S. Miller <davem@davemloft.net>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> (tracing side)
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/net.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++
 net/core/dev.c             | 35 ++++++++++++++++++++++-----
 2 files changed, 88 insertions(+), 6 deletions(-)

diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 00aa72ce0e7c..1efd7d9b25fe 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -244,6 +244,65 @@ DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_ni_entry,
 	TP_ARGS(skb)
 );
 
+DECLARE_EVENT_CLASS(net_dev_rx_exit_template,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret),
+
+	TP_STRUCT__entry(
+		__field(int,	ret)
+	),
+
+	TP_fast_assign(
+		__entry->ret = ret;
+	),
+
+	TP_printk("ret=%d", __entry->ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_frags_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_receive_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_ni_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
+DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit,
+
+	TP_PROTO(int ret),
+
+	TP_ARGS(ret)
+);
+
 #endif /* _TRACE_NET_H */
 
 /* This part must be outside protection */
diff --git a/net/core/dev.c b/net/core/dev.c
index abe50c424b29..04a6b7100aac 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4527,9 +4527,14 @@ static int netif_rx_internal(struct sk_buff *skb)
 
 int netif_rx(struct sk_buff *skb)
 {
+	int ret;
+
 	trace_netif_rx_entry(skb);
 
-	return netif_rx_internal(skb);
+	ret = netif_rx_internal(skb);
+	trace_netif_rx_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(netif_rx);
 
@@ -4544,6 +4549,7 @@ int netif_rx_ni(struct sk_buff *skb)
 	if (local_softirq_pending())
 		do_softirq();
 	preempt_enable();
+	trace_netif_rx_ni_exit(err);
 
 	return err;
 }
@@ -5229,9 +5235,14 @@ static void netif_receive_skb_list_internal(struct list_head *head)
  */
 int netif_receive_skb(struct sk_buff *skb)
 {
+	int ret;
+
 	trace_netif_receive_skb_entry(skb);
 
-	return netif_receive_skb_internal(skb);
+	ret = netif_receive_skb_internal(skb);
+	trace_netif_receive_skb_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(netif_receive_skb);
 
@@ -5251,9 +5262,12 @@ void netif_receive_skb_list(struct list_head *head)
 
 	if (list_empty(head))
 		return;
-	list_for_each_entry(skb, head, list)
-		trace_netif_receive_skb_list_entry(skb);
+	if (trace_netif_receive_skb_list_entry_enabled()) {
+		list_for_each_entry(skb, head, list)
+			trace_netif_receive_skb_list_entry(skb);
+	}
 	netif_receive_skb_list_internal(head);
+	trace_netif_receive_skb_list_exit(0);
 }
 EXPORT_SYMBOL(netif_receive_skb_list);
 
@@ -5645,12 +5659,17 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
+	gro_result_t ret;
+
 	skb_mark_napi_id(skb, napi);
 	trace_napi_gro_receive_entry(skb);
 
 	skb_gro_reset_offset(skb);
 
-	return napi_skb_finish(dev_gro_receive(napi, skb), skb);
+	ret = napi_skb_finish(dev_gro_receive(napi, skb), skb);
+	trace_napi_gro_receive_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(napi_gro_receive);
 
@@ -5768,6 +5787,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 
 gro_result_t napi_gro_frags(struct napi_struct *napi)
 {
+	gro_result_t ret;
 	struct sk_buff *skb = napi_frags_skb(napi);
 
 	if (!skb)
@@ -5775,7 +5795,10 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
 
 	trace_napi_gro_frags_entry(skb);
 
-	return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
+	ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
+	trace_napi_gro_frags_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(napi_gro_frags);
 
-- 
cgit v1.2.3


From ebeef4bcccf4681ba3de04fbf3a005f6054f7999 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 27 Nov 2018 14:42:00 -0800
Subject: tcp: hint compiler about sack flows

Tell the compiler that most TCP flows are using SACK these days.

There is no need to add the unlikely() clause in tcp_is_reno(),
the compiler is able to infer it.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 63e37dd1c274..0c61bf0a06da 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1124,7 +1124,7 @@ void tcp_rate_check_app_limited(struct sock *sk);
  */
 static inline int tcp_is_sack(const struct tcp_sock *tp)
 {
-	return tp->rx_opt.sack_ok;
+	return likely(tp->rx_opt.sack_ok);
 }
 
 static inline bool tcp_is_reno(const struct tcp_sock *tp)
-- 
cgit v1.2.3


From 19119f298bb1f2af3bb1093f5f2a1fed8da94e37 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 27 Nov 2018 14:42:01 -0800
Subject: tcp: take care of compressed acks in tcp_add_reno_sack()

Neal pointed out that non sack flows might suffer from ACK compression
added in the following patch ("tcp: implement coalescing on backlog queue")

Instead of tweaking tcp_add_backlog() we can take into
account how many ACK were coalesced, this information
will be available in skb_shinfo(skb)->gso_segs

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 58 ++++++++++++++++++++++++++++++----------------------
 1 file changed, 33 insertions(+), 25 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 78752746a6e2..76858b14ebe9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1865,16 +1865,20 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend)
 
 /* Emulate SACKs for SACKless connection: account for a new dupack. */
 
-static void tcp_add_reno_sack(struct sock *sk)
+static void tcp_add_reno_sack(struct sock *sk, int num_dupack)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
-	u32 prior_sacked = tp->sacked_out;
+	if (num_dupack) {
+		struct tcp_sock *tp = tcp_sk(sk);
+		u32 prior_sacked = tp->sacked_out;
+		s32 delivered;
 
-	tp->sacked_out++;
-	tcp_check_reno_reordering(sk, 0);
-	if (tp->sacked_out > prior_sacked)
-		tp->delivered++; /* Some out-of-order packet is delivered */
-	tcp_verify_left_out(tp);
+		tp->sacked_out += num_dupack;
+		tcp_check_reno_reordering(sk, 0);
+		delivered = tp->sacked_out - prior_sacked;
+		if (delivered > 0)
+			tp->delivered += delivered;
+		tcp_verify_left_out(tp);
+	}
 }
 
 /* Account for ACK, ACKing some data in Reno Recovery phase. */
@@ -2636,7 +2640,7 @@ void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 /* Process an ACK in CA_Loss state. Move to CA_Open if lost data are
  * recovered or spurious. Otherwise retransmits more on partial ACKs.
  */
-static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
+static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
 			     int *rexmit)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -2655,7 +2659,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
 			return;
 
 		if (after(tp->snd_nxt, tp->high_seq)) {
-			if (flag & FLAG_DATA_SACKED || is_dupack)
+			if (flag & FLAG_DATA_SACKED || num_dupack)
 				tp->frto = 0; /* Step 3.a. loss was real */
 		} else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
 			tp->high_seq = tp->snd_nxt;
@@ -2681,8 +2685,8 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
 		/* A Reno DUPACK means new data in F-RTO step 2.b above are
 		 * delivered. Lower inflight to clock out (re)tranmissions.
 		 */
-		if (after(tp->snd_nxt, tp->high_seq) && is_dupack)
-			tcp_add_reno_sack(sk);
+		if (after(tp->snd_nxt, tp->high_seq) && num_dupack)
+			tcp_add_reno_sack(sk, num_dupack);
 		else if (flag & FLAG_SND_UNA_ADVANCED)
 			tcp_reset_reno_sack(tp);
 	}
@@ -2759,13 +2763,13 @@ static bool tcp_force_fast_retransmit(struct sock *sk)
  * tcp_xmit_retransmit_queue().
  */
 static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
-				  bool is_dupack, int *ack_flag, int *rexmit)
+				  int num_dupack, int *ack_flag, int *rexmit)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int fast_rexmit = 0, flag = *ack_flag;
-	bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
-				     tcp_force_fast_retransmit(sk));
+	bool do_lost = num_dupack || ((flag & FLAG_DATA_SACKED) &&
+				      tcp_force_fast_retransmit(sk));
 
 	if (!tp->packets_out && tp->sacked_out)
 		tp->sacked_out = 0;
@@ -2812,8 +2816,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 	switch (icsk->icsk_ca_state) {
 	case TCP_CA_Recovery:
 		if (!(flag & FLAG_SND_UNA_ADVANCED)) {
-			if (tcp_is_reno(tp) && is_dupack)
-				tcp_add_reno_sack(sk);
+			if (tcp_is_reno(tp))
+				tcp_add_reno_sack(sk, num_dupack);
 		} else {
 			if (tcp_try_undo_partial(sk, prior_snd_una))
 				return;
@@ -2828,7 +2832,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		tcp_identify_packet_loss(sk, ack_flag);
 		break;
 	case TCP_CA_Loss:
-		tcp_process_loss(sk, flag, is_dupack, rexmit);
+		tcp_process_loss(sk, flag, num_dupack, rexmit);
 		tcp_identify_packet_loss(sk, ack_flag);
 		if (!(icsk->icsk_ca_state == TCP_CA_Open ||
 		      (*ack_flag & FLAG_LOST_RETRANS)))
@@ -2839,8 +2843,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		if (tcp_is_reno(tp)) {
 			if (flag & FLAG_SND_UNA_ADVANCED)
 				tcp_reset_reno_sack(tp);
-			if (is_dupack)
-				tcp_add_reno_sack(sk);
+			tcp_add_reno_sack(sk, num_dupack);
 		}
 
 		if (icsk->icsk_ca_state <= TCP_CA_Disorder)
@@ -3562,7 +3565,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	bool is_sack_reneg = tp->is_sack_reneg;
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
-	bool is_dupack = false;
+	int num_dupack = 0;
 	int prior_packets = tp->packets_out;
 	u32 delivered = tp->delivered;
 	u32 lost = tp->lost;
@@ -3673,8 +3676,13 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		tcp_set_xmit_timer(sk);
 
 	if (tcp_ack_is_dubious(sk, flag)) {
-		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
-		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+		if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) {
+			num_dupack = 1;
+			/* Consider if pure acks were aggregated in tcp_add_backlog() */
+			if (!(flag & FLAG_DATA))
+				num_dupack = max_t(u16, 1, skb_shinfo(skb)->gso_segs);
+		}
+		tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
 				      &rexmit);
 	}
 
@@ -3692,7 +3700,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 no_queue:
 	/* If data was DSACKed, see if we can undo a cwnd reduction. */
 	if (flag & FLAG_DSACKING_ACK) {
-		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+		tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
 				      &rexmit);
 		tcp_newly_delivered(sk, delivered, flag);
 	}
@@ -3717,7 +3725,7 @@ old_ack:
 	if (TCP_SKB_CB(skb)->sacked) {
 		flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
 						&sack_state);
-		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+		tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
 				      &rexmit);
 		tcp_newly_delivered(sk, delivered, flag);
 		tcp_xmit_recovery(sk, rexmit);
-- 
cgit v1.2.3


From 85bdf7db5b53cdcc7a901db12bcb3d0063e3866d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 27 Nov 2018 14:42:02 -0800
Subject: tcp: make tcp_space() aware of socket backlog

Jean-Louis Dupond reported poor iscsi TCP receive performance
that we tracked to backlog drops.

Apparently we fail to send window updates reflecting the
fact that we are under stress.

Note that we might lack a proper window increase when
backlog is fully processed, since __release_sock() clears
sk->sk_backlog.len _after_ all skbs have been processed.

This should not matter in practice. If we had a significant
load through socket backlog, we are in a dangerous
situation.

Reported-by: Jean-Louis Dupond <jean-louis@dupond.be>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Tested-by: Jean-Louis Dupond<jean-louis@dupond.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0c61bf0a06da..3b522259da7d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1368,7 +1368,7 @@ static inline int tcp_win_from_space(const struct sock *sk, int space)
 /* Note: caller must be prepared to deal with negative returns */
 static inline int tcp_space(const struct sock *sk)
 {
-	return tcp_win_from_space(sk, sk->sk_rcvbuf -
+	return tcp_win_from_space(sk, sk->sk_rcvbuf - sk->sk_backlog.len -
 				  atomic_read(&sk->sk_rmem_alloc));
 }
 
-- 
cgit v1.2.3


From 4f693b55c3d2d2239b8a0094b518a1e533cf75d5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 27 Nov 2018 14:42:03 -0800
Subject: tcp: implement coalescing on backlog queue

In case GRO is not as efficient as it should be or disabled,
we might have a user thread trapped in __release_sock() while
softirq handler flood packets up to the point we have to drop.

This patch balances work done from user thread and softirq,
to give more chances to __release_sock() to complete its work
before new packets are added the the backlog.

This also helps if we receive many ACK packets, since GRO
does not aggregate them.

This patch brings ~60% throughput increase on a receiver
without GRO, but the spectacular gain is really on
1000x release_sock() latency reduction I have measured.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/snmp.h |  1 +
 net/ipv4/proc.c           |  1 +
 net/ipv4/tcp_ipv4.c       | 92 +++++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 88 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index f80135e5feaa..86dc24a96c90 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -243,6 +243,7 @@ enum
 	LINUX_MIB_TCPREQQFULLDROP,		/* TCPReqQFullDrop */
 	LINUX_MIB_TCPRETRANSFAIL,		/* TCPRetransFail */
 	LINUX_MIB_TCPRCVCOALESCE,		/* TCPRcvCoalesce */
+	LINUX_MIB_TCPBACKLOGCOALESCE,		/* TCPBacklogCoalesce */
 	LINUX_MIB_TCPOFOQUEUE,			/* TCPOFOQueue */
 	LINUX_MIB_TCPOFODROP,			/* TCPOFODrop */
 	LINUX_MIB_TCPOFOMERGE,			/* TCPOFOMerge */
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 70289682a670..c3610b37bb4c 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -219,6 +219,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPRenoRecoveryFail", LINUX_MIB_TCPRENORECOVERYFAIL),
 	SNMP_MIB_ITEM("TCPSackRecoveryFail", LINUX_MIB_TCPSACKRECOVERYFAIL),
 	SNMP_MIB_ITEM("TCPRcvCollapsed", LINUX_MIB_TCPRCVCOLLAPSED),
+	SNMP_MIB_ITEM("TCPBacklogCoalesce", LINUX_MIB_TCPBACKLOGCOALESCE),
 	SNMP_MIB_ITEM("TCPDSACKOldSent", LINUX_MIB_TCPDSACKOLDSENT),
 	SNMP_MIB_ITEM("TCPDSACKOfoSent", LINUX_MIB_TCPDSACKOFOSENT),
 	SNMP_MIB_ITEM("TCPDSACKRecv", LINUX_MIB_TCPDSACKRECV),
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 795605a23275..4904250a9aac 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1619,12 +1619,14 @@ int tcp_v4_early_demux(struct sk_buff *skb)
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
 	u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf;
-
-	/* Only socket owner can try to collapse/prune rx queues
-	 * to reduce memory overhead, so add a little headroom here.
-	 * Few sockets backlog are possibly concurrently non empty.
-	 */
-	limit += 64*1024;
+	struct skb_shared_info *shinfo;
+	const struct tcphdr *th;
+	struct tcphdr *thtail;
+	struct sk_buff *tail;
+	unsigned int hdrlen;
+	bool fragstolen;
+	u32 gso_segs;
+	int delta;
 
 	/* In case all data was pulled from skb frags (in __pskb_pull_tail()),
 	 * we can fix skb->truesize to its real value to avoid future drops.
@@ -1636,6 +1638,84 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 
 	skb_dst_drop(skb);
 
+	if (unlikely(tcp_checksum_complete(skb))) {
+		bh_unlock_sock(sk);
+		__TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
+		__TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
+		return true;
+	}
+
+	/* Attempt coalescing to last skb in backlog, even if we are
+	 * above the limits.
+	 * This is okay because skb capacity is limited to MAX_SKB_FRAGS.
+	 */
+	th = (const struct tcphdr *)skb->data;
+	hdrlen = th->doff * 4;
+	shinfo = skb_shinfo(skb);
+
+	if (!shinfo->gso_size)
+		shinfo->gso_size = skb->len - hdrlen;
+
+	if (!shinfo->gso_segs)
+		shinfo->gso_segs = 1;
+
+	tail = sk->sk_backlog.tail;
+	if (!tail)
+		goto no_coalesce;
+	thtail = (struct tcphdr *)tail->data;
+
+	if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq ||
+	    TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield ||
+	    ((TCP_SKB_CB(tail)->tcp_flags |
+	      TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_URG) ||
+	    ((TCP_SKB_CB(tail)->tcp_flags ^
+	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
+#ifdef CONFIG_TLS_DEVICE
+	    tail->decrypted != skb->decrypted ||
+#endif
+	    thtail->doff != th->doff ||
+	    memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)))
+		goto no_coalesce;
+
+	__skb_pull(skb, hdrlen);
+	if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) {
+		thtail->window = th->window;
+
+		TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq;
+
+		if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))
+			TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq;
+
+		TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+
+		if (TCP_SKB_CB(skb)->has_rxtstamp) {
+			TCP_SKB_CB(tail)->has_rxtstamp = true;
+			tail->tstamp = skb->tstamp;
+			skb_hwtstamps(tail)->hwtstamp = skb_hwtstamps(skb)->hwtstamp;
+		}
+
+		/* Not as strict as GRO. We only need to carry mss max value */
+		skb_shinfo(tail)->gso_size = max(shinfo->gso_size,
+						 skb_shinfo(tail)->gso_size);
+
+		gso_segs = skb_shinfo(tail)->gso_segs + shinfo->gso_segs;
+		skb_shinfo(tail)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+
+		sk->sk_backlog.len += delta;
+		__NET_INC_STATS(sock_net(sk),
+				LINUX_MIB_TCPBACKLOGCOALESCE);
+		kfree_skb_partial(skb, fragstolen);
+		return false;
+	}
+	__skb_push(skb, hdrlen);
+
+no_coalesce:
+	/* Only socket owner can try to collapse/prune rx queues
+	 * to reduce memory overhead, so add a little headroom here.
+	 * Few sockets backlog are possibly concurrently non empty.
+	 */
+	limit += 64*1024;
+
 	if (unlikely(sk_add_backlog(sk, skb, limit))) {
 		bh_unlock_sock(sk);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP);
-- 
cgit v1.2.3


From 6015c71e656bb6895b416c31a8b7db457e45cecf Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 27 Nov 2018 15:03:21 -0800
Subject: tcp: md5: add tcp_md5_needed jump label

Most linux hosts never setup TCP MD5 keys. We can avoid a
cache line miss (accessing tp->md5ig_info) on RX and TX
using a jump label.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 18 +++++++++++++++---
 net/ipv4/tcp.c        |  5 ++++-
 net/ipv4/tcp_ipv4.c   | 11 +++++++----
 net/ipv4/tcp_output.c |  6 ++++--
 4 files changed, 30 insertions(+), 10 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3b522259da7d..0681afc62354 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1555,9 +1555,21 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
 					 const struct sock *addr_sk);
 
 #ifdef CONFIG_TCP_MD5SIG
-struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk,
-					 const union tcp_md5_addr *addr,
-					 int family);
+#include <linux/jump_label.h>
+extern struct static_key tcp_md5_needed;
+struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk,
+					   const union tcp_md5_addr *addr,
+					   int family);
+static inline struct tcp_md5sig_key *
+tcp_md5_do_lookup(const struct sock *sk,
+		  const union tcp_md5_addr *addr,
+		  int family)
+{
+	if (!static_key_false(&tcp_md5_needed))
+		return NULL;
+	return __tcp_md5_do_lookup(sk, addr, family);
+}
+
 #define tcp_twsk_md5_key(twsk)	((twsk)->tw_md5_key)
 #else
 static inline struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 252048776dbb..215e4d3b3616 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3656,8 +3656,11 @@ bool tcp_alloc_md5sig_pool(void)
 	if (unlikely(!tcp_md5sig_pool_populated)) {
 		mutex_lock(&tcp_md5sig_mutex);
 
-		if (!tcp_md5sig_pool_populated)
+		if (!tcp_md5sig_pool_populated) {
 			__tcp_alloc_md5sig_pool();
+			if (tcp_md5sig_pool_populated)
+				static_key_slow_inc(&tcp_md5_needed);
+		}
 
 		mutex_unlock(&tcp_md5sig_mutex);
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4904250a9aac..efc6fef692ff 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -970,10 +970,13 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req)
  * We need to maintain these in the sk structure.
  */
 
+struct static_key tcp_md5_needed __read_mostly;
+EXPORT_SYMBOL(tcp_md5_needed);
+
 /* Find the Key structure for an address.  */
-struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk,
-					 const union tcp_md5_addr *addr,
-					 int family)
+struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk,
+					   const union tcp_md5_addr *addr,
+					   int family)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *key;
@@ -1011,7 +1014,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk,
 	}
 	return best_match;
 }
-EXPORT_SYMBOL(tcp_md5_do_lookup);
+EXPORT_SYMBOL(__tcp_md5_do_lookup);
 
 static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk,
 						      const union tcp_md5_addr *addr,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e4c1e51b18c1..d3b691f3a9e8 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -594,7 +594,8 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 
 	*md5 = NULL;
 #ifdef CONFIG_TCP_MD5SIG
-	if (unlikely(rcu_access_pointer(tp->md5sig_info))) {
+	if (static_key_false(&tcp_md5_needed) &&
+	    rcu_access_pointer(tp->md5sig_info)) {
 		*md5 = tp->af_specific->md5_lookup(sk, sk);
 		if (*md5) {
 			opts->options |= OPTION_MD5;
@@ -730,7 +731,8 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 
 	*md5 = NULL;
 #ifdef CONFIG_TCP_MD5SIG
-	if (unlikely(rcu_access_pointer(tp->md5sig_info))) {
+	if (static_key_false(&tcp_md5_needed) &&
+	    rcu_access_pointer(tp->md5sig_info)) {
 		*md5 = tp->af_specific->md5_lookup(sk, sk);
 		if (*md5) {
 			opts->options |= OPTION_MD5;
-- 
cgit v1.2.3


From 95862749674f598e979cb3ef2d18aec2e5d8bd29 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:24:48 -0800
Subject: nfp: copy only the relevant part of the TX descriptor for frags

Chained descriptors for fragments need to duplicate all the descriptor
fields of the skb head, so we copy the descriptor and then modify the
relevant fields.  This is wasteful, because the top half of the descriptor
will get overwritten entirely while the bottom half is not modified at all.
Copy only the bottom half.  This saves us 0.3% of CPU in a GSO test.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net.h        |  1 +
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 12 +++++++-----
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index bb3dbd74583b..5a9a6178cf26 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -158,6 +158,7 @@ struct nfp_net_tx_desc {
 			__le16 data_len; /* Length of frame + meta data */
 		} __packed;
 		__le32 vals[4];
+		__le64 vals8[2];
 	};
 };
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 9aa6265bf4de..b54c6e481229 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -786,11 +786,11 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	const struct skb_frag_struct *frag;
-	struct nfp_net_tx_desc *txd, txdg;
 	int f, nr_frags, wr_idx, md_bytes;
 	struct nfp_net_tx_ring *tx_ring;
 	struct nfp_net_r_vector *r_vec;
 	struct nfp_net_tx_buf *txbuf;
+	struct nfp_net_tx_desc *txd;
 	struct netdev_queue *nd_q;
 	struct nfp_net_dp *dp;
 	dma_addr_t dma_addr;
@@ -860,8 +860,10 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 
 	/* Gather DMA */
 	if (nr_frags > 0) {
+		__le64 second_half;
+
 		/* all descs must match except for in addr, length and eop */
-		txdg = *txd;
+		second_half = txd->vals8[1];
 
 		for (f = 0; f < nr_frags; f++) {
 			frag = &skb_shinfo(skb)->frags[f];
@@ -878,11 +880,11 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 			tx_ring->txbufs[wr_idx].fidx = f;
 
 			txd = &tx_ring->txds[wr_idx];
-			*txd = txdg;
 			txd->dma_len = cpu_to_le16(fsize);
 			nfp_desc_set_dma_addr(txd, dma_addr);
-			txd->offset_eop |=
-				(f == nr_frags - 1) ? PCIE_DESC_TX_EOP : 0;
+			txd->offset_eop = md_bytes |
+				((f == nr_frags - 1) ? PCIE_DESC_TX_EOP : 0);
+			txd->vals8[1] = second_half;
 		}
 
 		u64_stats_update_begin(&r_vec->tx_sync);
-- 
cgit v1.2.3


From de31049a48bb75bc458e9f8a0fae037fcbf1241f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:24:49 -0800
Subject: nfp: move temporary variables in nfp_net_tx_complete()

Move temporary variables in scope of the loop in nfp_net_tx_complete(),
and add a temp for txbuf software structure.  This saves us 0.2% of CPU.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 31 ++++++++++++----------
 1 file changed, 17 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index b54c6e481229..78c651f9f774 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -940,14 +940,10 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
 	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
-	const struct skb_frag_struct *frag;
 	struct netdev_queue *nd_q;
 	u32 done_pkts = 0, done_bytes = 0;
-	struct sk_buff *skb;
-	int todo, nr_frags;
 	u32 qcp_rd_p;
-	int fidx;
-	int idx;
+	int todo;
 
 	if (tx_ring->wr_p == tx_ring->rd_p)
 		return;
@@ -961,26 +957,33 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget)
 	todo = D_IDX(tx_ring, qcp_rd_p - tx_ring->qcp_rd_p);
 
 	while (todo--) {
+		const struct skb_frag_struct *frag;
+		struct nfp_net_tx_buf *tx_buf;
+		struct sk_buff *skb;
+		int fidx, nr_frags;
+		int idx;
+
 		idx = D_IDX(tx_ring, tx_ring->rd_p++);
+		tx_buf = &tx_ring->txbufs[idx];
 
-		skb = tx_ring->txbufs[idx].skb;
+		skb = tx_buf->skb;
 		if (!skb)
 			continue;
 
 		nr_frags = skb_shinfo(skb)->nr_frags;
-		fidx = tx_ring->txbufs[idx].fidx;
+		fidx = tx_buf->fidx;
 
 		if (fidx == -1) {
 			/* unmap head */
-			dma_unmap_single(dp->dev, tx_ring->txbufs[idx].dma_addr,
+			dma_unmap_single(dp->dev, tx_buf->dma_addr,
 					 skb_headlen(skb), DMA_TO_DEVICE);
 
-			done_pkts += tx_ring->txbufs[idx].pkt_cnt;
-			done_bytes += tx_ring->txbufs[idx].real_len;
+			done_pkts += tx_buf->pkt_cnt;
+			done_bytes += tx_buf->real_len;
 		} else {
 			/* unmap fragment */
 			frag = &skb_shinfo(skb)->frags[fidx];
-			dma_unmap_page(dp->dev, tx_ring->txbufs[idx].dma_addr,
+			dma_unmap_page(dp->dev, tx_buf->dma_addr,
 				       skb_frag_size(frag), DMA_TO_DEVICE);
 		}
 
@@ -988,9 +991,9 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget)
 		if (fidx == nr_frags - 1)
 			napi_consume_skb(skb, budget);
 
-		tx_ring->txbufs[idx].dma_addr = 0;
-		tx_ring->txbufs[idx].skb = NULL;
-		tx_ring->txbufs[idx].fidx = -2;
+		tx_buf->dma_addr = 0;
+		tx_buf->skb = NULL;
+		tx_buf->fidx = -2;
 	}
 
 	tx_ring->qcp_rd_p = qcp_rd_p;
-- 
cgit v1.2.3


From 8b5ddf1e51818d2446f0ca997beb82a850718d2e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:24:50 -0800
Subject: nfp: move queue variable init

nd_q is only used at the very end of nfp_net_tx(), there is no need
to initialize it early.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 78c651f9f774..0302a38149b6 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -801,13 +801,13 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	qidx = skb_get_queue_mapping(skb);
 	tx_ring = &dp->tx_rings[qidx];
 	r_vec = tx_ring->r_vec;
-	nd_q = netdev_get_tx_queue(dp->netdev, qidx);
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 
 	if (unlikely(nfp_net_tx_full(tx_ring, nr_frags + 1))) {
 		nn_dp_warn(dp, "TX ring %d busy. wrp=%u rdp=%u\n",
 			   qidx, tx_ring->wr_p, tx_ring->rd_p);
+		nd_q = netdev_get_tx_queue(dp->netdev, qidx);
 		netif_tx_stop_queue(nd_q);
 		nfp_net_tx_xmit_more_flush(tx_ring);
 		u64_stats_update_begin(&r_vec->tx_sync);
@@ -894,6 +894,8 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 
 	skb_tx_timestamp(skb);
 
+	nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
+
 	tx_ring->wr_p += nr_frags + 1;
 	if (nfp_net_tx_ring_should_stop(tx_ring))
 		nfp_net_tx_ring_stop(nd_q, tx_ring);
-- 
cgit v1.2.3


From b54ad0eaad8e5defcc48b224a7c7deb3f162cb99 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:24:51 -0800
Subject: nfp: correct descriptor offsets in presence of metadata

The TSO-related offsets in the descriptor should not include
the length of the prepended metadata.  Adjust them.  Note that
this could not have caused issues in the past as we don't
support TSO with metadata prepend as of this patch.

Signed-off-by: Michael Rapson <michael.rapson@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 0302a38149b6..9cc2c204baa3 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -647,27 +647,29 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q,
  * @txbuf: Pointer to driver soft TX descriptor
  * @txd: Pointer to HW TX descriptor
  * @skb: Pointer to SKB
+ * @md_bytes: Prepend length
  *
  * Set up Tx descriptor for LSO, do nothing for non-LSO skbs.
  * Return error on packet header greater than maximum supported LSO header size.
  */
 static void nfp_net_tx_tso(struct nfp_net_r_vector *r_vec,
 			   struct nfp_net_tx_buf *txbuf,
-			   struct nfp_net_tx_desc *txd, struct sk_buff *skb)
+			   struct nfp_net_tx_desc *txd, struct sk_buff *skb,
+			   u32 md_bytes)
 {
-	u32 hdrlen;
+	u32 l3_offset, l4_offset, hdrlen;
 	u16 mss;
 
 	if (!skb_is_gso(skb))
 		return;
 
 	if (!skb->encapsulation) {
-		txd->l3_offset = skb_network_offset(skb);
-		txd->l4_offset = skb_transport_offset(skb);
+		l3_offset = skb_network_offset(skb);
+		l4_offset = skb_transport_offset(skb);
 		hdrlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
 	} else {
-		txd->l3_offset = skb_inner_network_offset(skb);
-		txd->l4_offset = skb_inner_transport_offset(skb);
+		l3_offset = skb_inner_network_offset(skb);
+		l4_offset = skb_inner_transport_offset(skb);
 		hdrlen = skb_inner_transport_header(skb) - skb->data +
 			inner_tcp_hdrlen(skb);
 	}
@@ -676,7 +678,9 @@ static void nfp_net_tx_tso(struct nfp_net_r_vector *r_vec,
 	txbuf->real_len += hdrlen * (txbuf->pkt_cnt - 1);
 
 	mss = skb_shinfo(skb)->gso_size & PCIE_DESC_TX_MSS_MASK;
-	txd->lso_hdrlen = hdrlen;
+	txd->l3_offset = l3_offset - md_bytes;
+	txd->l4_offset = l4_offset - md_bytes;
+	txd->lso_hdrlen = hdrlen - md_bytes;
 	txd->mss = cpu_to_le16(mss);
 	txd->flags |= PCIE_DESC_TX_LSO;
 
@@ -851,7 +855,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	txd->lso_hdrlen = 0;
 
 	/* Do not reorder - tso may adjust pkt cnt, vlan may override fields */
-	nfp_net_tx_tso(r_vec, txbuf, txd, skb);
+	nfp_net_tx_tso(r_vec, txbuf, txd, skb, md_bytes);
 	nfp_net_tx_csum(dp, r_vec, txbuf, txd, skb);
 	if (skb_vlan_tag_present(skb) && dp->ctrl & NFP_NET_CFG_CTRL_TXVLAN) {
 		txd->flags |= PCIE_DESC_TX_VLAN;
-- 
cgit v1.2.3


From d7cc8252252f9e5b72975a3d498ba2ee08245740 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:24:52 -0800
Subject: nfp: avoid oversized TSO headers with metadata prepend

In preparation for TSO over representors make sure the port id
prepend will always fit in the frame.  The current max header
length is 255, which is ample, so assume worst case scenario
of 8 byte prepend and save ourselves the conditionals.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 9cc2c204baa3..3cb7dceca2d9 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3284,7 +3284,10 @@ nfp_net_features_check(struct sk_buff *skb, struct net_device *dev,
 		hdrlen = skb_inner_transport_header(skb) - skb->data +
 			inner_tcp_hdrlen(skb);
 
-		if (unlikely(hdrlen > NFP_NET_LSO_MAX_HDR_SZ))
+		/* Assume worst case scenario of having longest possible
+		 * metadata prepend - 8B
+		 */
+		if (unlikely(hdrlen > NFP_NET_LSO_MAX_HDR_SZ - 8))
 			features &= ~NETIF_F_GSO_MASK;
 	}
 
-- 
cgit v1.2.3


From 9db8bbcb9bc68e7f58e13d30eec87905e2b8825d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:24:53 -0800
Subject: nfp: run representor TX locklessly

Our representors are software devices built on top of the PF
vNIC, the only state they have are per-cpu stats, so make
the TX run locklessly.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index c09b893c30dd..769fb5210aaf 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -299,6 +299,8 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 
 	SWITCHDEV_SET_OPS(netdev, &nfp_port_switchdev_ops);
 
+	netdev->features |= NETIF_F_LLTX;
+
 	if (nfp_app_has_tc(app)) {
 		netdev->features |= NETIF_F_HW_TC;
 		netdev->hw_features |= NETIF_F_HW_TC;
-- 
cgit v1.2.3


From fbf60e377d5b9623abae599f947f3013c07842c4 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:24:54 -0800
Subject: nfp: run don't require Qdiscs on representor netdevs

Our representors are software devices built on top of the PF
vNIC, the queuing should only happen at the vNIC netdevice.
Allow representors to run qdisc-less.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index 769fb5210aaf..b9904f6b41f8 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -299,6 +299,7 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 
 	SWITCHDEV_SET_OPS(netdev, &nfp_port_switchdev_ops);
 
+	netdev->priv_flags |= IFF_NO_QUEUE;
 	netdev->features |= NETIF_F_LLTX;
 
 	if (nfp_app_has_tc(app)) {
-- 
cgit v1.2.3


From 71844fac1ed459024dd2a448d63d5b28b8c87daa Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:24:55 -0800
Subject: nfp: add locking around representor changes

Up until now we never needed to keep a networking locks around
representors accesses, we only accessed them when device was
reconfigured (under nfp pf->lock) or on fast path (under RCU).
Now we want to be able to iterate over all representors during
notifications, so make sure representor assignment is done
under RTNL lock.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.c     | 4 ++++
 drivers/net/ethernet/netronome/nfp/nfp_app.c      | 2 ++
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 2 ++
 3 files changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 7a4d55f794c2..80e79447b644 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -126,7 +126,9 @@ nfp_abm_spawn_repr(struct nfp_app *app, struct nfp_abm_link *alink,
 
 	reprs = nfp_reprs_get_locked(app, rtype);
 	WARN(nfp_repr_get_locked(app, reprs, alink->id), "duplicate repr");
+	rtnl_lock();
 	rcu_assign_pointer(reprs->reprs[alink->id], netdev);
+	rtnl_unlock();
 
 	nfp_info(app->cpp, "%s Port %d Representor(%s) created\n",
 		 ptype == NFP_PORT_PF_PORT ? "PCIe" : "Phys",
@@ -152,7 +154,9 @@ nfp_abm_kill_repr(struct nfp_app *app, struct nfp_abm_link *alink,
 	netdev = nfp_repr_get_locked(app, reprs, alink->id);
 	if (!netdev)
 		return;
+	rtnl_lock();
 	rcu_assign_pointer(reprs->reprs[alink->id], NULL);
+	rtnl_unlock();
 	synchronize_rcu();
 	/* Cast to make sure nfp_repr_clean_and_free() takes a nfp_repr */
 	nfp_repr_clean_and_free((struct nfp_repr *)netdev_priv(netdev));
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c
index 4a1b8f79e731..117553914342 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c
@@ -131,7 +131,9 @@ nfp_app_reprs_set(struct nfp_app *app, enum nfp_repr_type type,
 	struct nfp_reprs *old;
 
 	old = nfp_reprs_get_locked(app, type);
+	rtnl_lock();
 	rcu_assign_pointer(app->reprs[type], reprs);
+	rtnl_unlock();
 
 	return old;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index b9904f6b41f8..0a1d761c6692 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -445,7 +445,9 @@ int nfp_reprs_resync_phys_ports(struct nfp_app *app)
 			continue;
 
 		nfp_app_repr_preclean(app, netdev);
+		rtnl_lock();
 		rcu_assign_pointer(reprs->reprs[i], NULL);
+		rtnl_unlock();
 		synchronize_rcu();
 		nfp_repr_clean(repr);
 	}
-- 
cgit v1.2.3


From 51a6588e8c08a108ca7daa899a28b3219fc47e46 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:24:56 -0800
Subject: nfp: add offloads on representors

FW/HW can generally support the standard networking offloads
on representors without any trouble.  Add the ability for FW
to advertise which features should be available on representors.

Because representors are muxed on top of the vNIC we need to listen
on feature changes of their lower devices, and update their features
appropriately.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_app.c      | 40 +++++++++++
 drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c |  9 +++
 drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h |  7 ++
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 85 +++++++++++++++++++++++
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.h |  2 +
 5 files changed, 143 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c
index 117553914342..3a973282b2bb 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c
@@ -138,6 +138,38 @@ nfp_app_reprs_set(struct nfp_app *app, enum nfp_repr_type type,
 	return old;
 }
 
+static void
+nfp_app_netdev_feat_change(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_net *nn;
+	unsigned int type;
+
+	if (!nfp_netdev_is_nfp_net(netdev))
+		return;
+	nn = netdev_priv(netdev);
+	if (nn->app != app)
+		return;
+
+	for (type = 0; type < __NFP_REPR_TYPE_MAX; type++) {
+		struct nfp_reprs *reprs;
+		unsigned int i;
+
+		reprs = rtnl_dereference(app->reprs[type]);
+		if (!reprs)
+			continue;
+
+		for (i = 0; i < reprs->num_reprs; i++) {
+			struct net_device *repr;
+
+			repr = rtnl_dereference(reprs->reprs[i]);
+			if (!repr)
+				continue;
+
+			nfp_repr_transfer_features(repr, netdev);
+		}
+	}
+}
+
 static int
 nfp_app_netdev_event(struct notifier_block *nb, unsigned long event, void *ptr)
 {
@@ -147,6 +179,14 @@ nfp_app_netdev_event(struct notifier_block *nb, unsigned long event, void *ptr)
 	netdev = netdev_notifier_info_to_dev(ptr);
 	app = container_of(nb, struct nfp_app, netdev_nb);
 
+	/* Handle events common code is interested in */
+	switch (event) {
+	case NETDEV_FEAT_CHANGE:
+		nfp_app_netdev_feat_change(app, netdev);
+		break;
+	}
+
+	/* Call offload specific handlers */
 	if (app->type->netdev_event)
 		return app->type->netdev_event(app, netdev, event, ptr);
 	return NOTIFY_DONE;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
index f2aaef976c7d..d26ea32df8d9 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
@@ -90,6 +90,15 @@ int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
 				 FIELD_GET(NFP_NET_CFG_TLV_HEADER_TYPE, hdr),
 				 offset, length);
 			break;
+		case NFP_NET_CFG_TLV_TYPE_REPR_CAP:
+			if (length < 4) {
+				dev_err(dev, "REPR CAP TLV short %dB < 4B\n",
+					length);
+				return -EINVAL;
+			}
+
+			caps->repr_cap = readl(data);
+			break;
 		default:
 			if (!FIELD_GET(NFP_NET_CFG_TLV_HEADER_REQUIRED, hdr))
 				break;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index ccec69944de5..166d7f71442e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -466,6 +466,10 @@
  * Variable, experimental IDs.  IDs designated for internal development and
  * experiments before a stable TLV ID has been allocated to a feature.  Should
  * never be present in production firmware.
+ *
+ * %NFP_NET_CFG_TLV_TYPE_REPR_CAP:
+ * Single word, equivalent of %NFP_NET_CFG_CAP for representors, features which
+ * can be used on representors.
  */
 #define NFP_NET_CFG_TLV_TYPE_UNKNOWN		0
 #define NFP_NET_CFG_TLV_TYPE_RESERVED		1
@@ -474,6 +478,7 @@
 #define NFP_NET_CFG_TLV_TYPE_MBOX		4
 #define NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL0	5
 #define NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL1	6
+#define NFP_NET_CFG_TLV_TYPE_REPR_CAP		7
 
 struct device;
 
@@ -482,11 +487,13 @@ struct device;
  * @me_freq_mhz:	ME clock_freq (MHz)
  * @mbox_off:		vNIC mailbox area offset
  * @mbox_len:		vNIC mailbox area length
+ * @repr_cap:		capabilities for representors
  */
 struct nfp_net_tlv_caps {
 	u32 me_freq_mhz;
 	unsigned int mbox_off;
 	unsigned int mbox_len;
+	u32 repr_cap;
 };
 
 int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index 0a1d761c6692..69d7aebda09b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -11,6 +11,7 @@
 #include "nfpcore/nfp_nsp.h"
 #include "nfp_app.h"
 #include "nfp_main.h"
+#include "nfp_net.h"
 #include "nfp_net_ctrl.h"
 #include "nfp_net_repr.h"
 #include "nfp_net_sriov.h"
@@ -231,6 +232,27 @@ err_port_disable:
 	return err;
 }
 
+static netdev_features_t
+nfp_repr_fix_features(struct net_device *netdev, netdev_features_t features)
+{
+	struct nfp_repr *repr = netdev_priv(netdev);
+	netdev_features_t old_features = features;
+	netdev_features_t lower_features;
+	struct net_device *lower_dev;
+
+	lower_dev = repr->dst->u.port_info.lower_dev;
+
+	lower_features = lower_dev->features;
+	if (lower_features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))
+		lower_features |= NETIF_F_HW_CSUM;
+
+	features = netdev_intersect_features(features, lower_features);
+	features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_HW_TC);
+	features |= NETIF_F_LLTX;
+
+	return features;
+}
+
 const struct net_device_ops nfp_repr_netdev_ops = {
 	.ndo_init		= nfp_app_ndo_init,
 	.ndo_uninit		= nfp_app_ndo_uninit,
@@ -248,10 +270,25 @@ const struct net_device_ops nfp_repr_netdev_ops = {
 	.ndo_set_vf_spoofchk	= nfp_app_set_vf_spoofchk,
 	.ndo_get_vf_config	= nfp_app_get_vf_config,
 	.ndo_set_vf_link_state	= nfp_app_set_vf_link_state,
+	.ndo_fix_features	= nfp_repr_fix_features,
 	.ndo_set_features	= nfp_port_set_features,
 	.ndo_set_mac_address    = eth_mac_addr,
 };
 
+void
+nfp_repr_transfer_features(struct net_device *netdev, struct net_device *lower)
+{
+	struct nfp_repr *repr = netdev_priv(netdev);
+
+	if (repr->dst->u.port_info.lower_dev != lower)
+		return;
+
+	netdev->gso_max_size = lower->gso_max_size;
+	netdev->gso_max_segs = lower->gso_max_segs;
+
+	netdev_update_features(netdev);
+}
+
 static void nfp_repr_clean(struct nfp_repr *repr)
 {
 	unregister_netdev(repr->netdev);
@@ -281,6 +318,8 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 		  struct net_device *pf_netdev)
 {
 	struct nfp_repr *repr = netdev_priv(netdev);
+	struct nfp_net *nn = netdev_priv(pf_netdev);
+	u32 repr_cap = nn->tlv_caps.repr_cap;
 	int err;
 
 	nfp_repr_set_lockdep_class(netdev);
@@ -299,6 +338,52 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 
 	SWITCHDEV_SET_OPS(netdev, &nfp_port_switchdev_ops);
 
+	/* Set features the lower device can support with representors */
+	if (repr_cap & NFP_NET_CFG_CTRL_LIVE_ADDR)
+		netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+
+	netdev->hw_features = NETIF_F_HIGHDMA;
+	if (repr_cap & NFP_NET_CFG_CTRL_RXCSUM_ANY)
+		netdev->hw_features |= NETIF_F_RXCSUM;
+	if (repr_cap & NFP_NET_CFG_CTRL_TXCSUM)
+		netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	if (repr_cap & NFP_NET_CFG_CTRL_GATHER)
+		netdev->hw_features |= NETIF_F_SG;
+	if ((repr_cap & NFP_NET_CFG_CTRL_LSO && nn->fw_ver.major > 2) ||
+	    repr_cap & NFP_NET_CFG_CTRL_LSO2)
+		netdev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;
+	if (repr_cap & NFP_NET_CFG_CTRL_RSS_ANY)
+		netdev->hw_features |= NETIF_F_RXHASH;
+	if (repr_cap & NFP_NET_CFG_CTRL_VXLAN) {
+		if (repr_cap & NFP_NET_CFG_CTRL_LSO)
+			netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+	}
+	if (repr_cap & NFP_NET_CFG_CTRL_NVGRE) {
+		if (repr_cap & NFP_NET_CFG_CTRL_LSO)
+			netdev->hw_features |= NETIF_F_GSO_GRE;
+	}
+	if (repr_cap & (NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE))
+		netdev->hw_enc_features = netdev->hw_features;
+
+	netdev->vlan_features = netdev->hw_features;
+
+	if (repr_cap & NFP_NET_CFG_CTRL_RXVLAN)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
+	if (repr_cap & NFP_NET_CFG_CTRL_TXVLAN) {
+		if (repr_cap & NFP_NET_CFG_CTRL_LSO2)
+			netdev_warn(netdev, "Device advertises both TSO2 and TXVLAN. Refusing to enable TXVLAN.\n");
+		else
+			netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
+	}
+	if (repr_cap & NFP_NET_CFG_CTRL_CTAG_FILTER)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	netdev->features = netdev->hw_features;
+
+	/* Advertise but disable TSO by default. */
+	netdev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
+	netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS;
+
 	netdev->priv_flags |= IFF_NO_QUEUE;
 	netdev->features |= NETIF_F_LLTX;
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h
index c412b94bfb97..e0f13dfe1f39 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h
@@ -92,6 +92,8 @@ nfp_repr_get_locked(struct nfp_app *app, struct nfp_reprs *set,
 		    unsigned int id);
 
 void nfp_repr_inc_rx_stats(struct net_device *netdev, unsigned int len);
+void
+nfp_repr_transfer_features(struct net_device *netdev, struct net_device *lower);
 int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 		  u32 cmsg_port_id, struct nfp_port *port,
 		  struct net_device *pf_netdev);
-- 
cgit v1.2.3


From 9571d9877546434682b653e8a81a5a177cd4529e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:24:57 -0800
Subject: nfp: add offset to all TLV parsing errors

When troubleshooting incorrect FW capabilities it's useful to know
where the faulty TLV is located.  Add offset to all errors messages.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
index d26ea32df8d9..6d5213b5bcb0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
@@ -41,8 +41,8 @@ int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
 		data += 4;
 
 		if (length % NFP_NET_CFG_TLV_LENGTH_INC) {
-			dev_err(dev, "TLV size not multiple of %u len:%u\n",
-				NFP_NET_CFG_TLV_LENGTH_INC, length);
+			dev_err(dev, "TLV size not multiple of %u offset:%u len:%u\n",
+				NFP_NET_CFG_TLV_LENGTH_INC, offset, length);
 			return -EINVAL;
 		}
 		if (data + length > end) {
@@ -61,14 +61,14 @@ int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
 			if (!length)
 				return 0;
 
-			dev_err(dev, "END TLV should be empty, has len:%d\n",
-				length);
+			dev_err(dev, "END TLV should be empty, has offset:%u len:%d\n",
+				offset, length);
 			return -EINVAL;
 		case NFP_NET_CFG_TLV_TYPE_ME_FREQ:
 			if (length != 4) {
 				dev_err(dev,
-					"ME FREQ TLV should be 4B, is %dB\n",
-					length);
+					"ME FREQ TLV should be 4B, is %dB offset:%u\n",
+					length, offset);
 				return -EINVAL;
 			}
 
@@ -92,8 +92,8 @@ int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
 			break;
 		case NFP_NET_CFG_TLV_TYPE_REPR_CAP:
 			if (length < 4) {
-				dev_err(dev, "REPR CAP TLV short %dB < 4B\n",
-					length);
+				dev_err(dev, "REPR CAP TLV short %dB < 4B offset:%u\n",
+					length, offset);
 				return -EINVAL;
 			}
 
-- 
cgit v1.2.3


From 6db3a9dcf0b99cf478c9b1421c83a81345ffbb15 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:24:58 -0800
Subject: nfp: report more info when reconfiguration fails

FW reconfiguration timeouts are a common indicator of FW trouble.
To make debugging easier print requested update and control word
when reconfiguration fails.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net.h        | 2 ++
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 9 +++++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 5a9a6178cf26..be37c2d6151c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -544,6 +544,7 @@ struct nfp_net_dp {
  * @reconfig_timer_active:  Timer for reading reconfiguration results is pending
  * @reconfig_sync_present:  Some thread is performing synchronous reconfig
  * @reconfig_timer:	Timer for async reading of reconfig results
+ * @reconfig_in_progress_update:	Update FW is processing now (debug only)
  * @link_up:            Is the link up?
  * @link_status_lock:	Protects @link_* and ensures atomicity with BAR reading
  * @rx_coalesce_usecs:      RX interrupt moderation usecs delay parameter
@@ -612,6 +613,7 @@ struct nfp_net {
 	bool reconfig_timer_active;
 	bool reconfig_sync_present;
 	struct timer_list reconfig_timer;
+	u32 reconfig_in_progress_update;
 
 	u32 rx_coalesce_usecs;
 	u32 rx_coalesce_max_frames;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 3cb7dceca2d9..e97636d2e6ee 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -101,6 +101,7 @@ static void nfp_net_reconfig_start(struct nfp_net *nn, u32 update)
 	/* ensure update is written before pinging HW */
 	nn_pci_flush(nn);
 	nfp_qcp_wr_ptr_add(nn->qcp_cfg, 1);
+	nn->reconfig_in_progress_update = update;
 }
 
 /* Pass 0 as update to run posted reconfigs. */
@@ -123,10 +124,14 @@ static bool nfp_net_reconfig_check_done(struct nfp_net *nn, bool last_check)
 	if (reg == 0)
 		return true;
 	if (reg & NFP_NET_CFG_UPDATE_ERR) {
-		nn_err(nn, "Reconfig error: 0x%08x\n", reg);
+		nn_err(nn, "Reconfig error (status: 0x%08x update: 0x%08x ctrl: 0x%08x)\n",
+		       reg, nn->reconfig_in_progress_update,
+		       nn_readl(nn, NFP_NET_CFG_CTRL));
 		return true;
 	} else if (last_check) {
-		nn_err(nn, "Reconfig timeout: 0x%08x\n", reg);
+		nn_err(nn, "Reconfig timeout (status: 0x%08x update: 0x%08x ctrl: 0x%08x)\n",
+		       reg, nn->reconfig_in_progress_update,
+		       nn_readl(nn, NFP_NET_CFG_CTRL));
 		return true;
 	}
 
-- 
cgit v1.2.3


From 420d031822737ef570df6834c0eae26f33988f20 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:32:30 -0800
Subject: rtnetlink: remove a level of indentation in rtnl_newlink()

rtnl_newlink() used to create VLAs based on link kind.  Since
commit ccf8dbcd062a ("rtnetlink: Remove VLA usage") statically
sized array is created on the stack, so there is no more use
for a separate code block that used to be the VLA's live range.

While at it christmas tree the variables.  Note that there is
a goto-based retry so to be on the safe side the variables can
no longer be initialized in place.  It doesn't seem to matter,
logically, but why make the code harder to read..

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 313 +++++++++++++++++++++++++--------------------------
 1 file changed, 154 insertions(+), 159 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a498bb41c9aa..ee2caa2fd940 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2974,17 +2974,22 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
 static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct netlink_ext_ack *extack)
 {
+	struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
+	unsigned char name_assign_type = NET_NAME_USER;
+	struct nlattr *linkinfo[IFLA_INFO_MAX + 1];
+	const struct rtnl_link_ops *m_ops = NULL;
+	struct nlattr *attr[RTNL_MAX_TYPE + 1];
+	struct net_device *master_dev = NULL;
 	struct net *net = sock_net(skb->sk);
 	const struct rtnl_link_ops *ops;
-	const struct rtnl_link_ops *m_ops = NULL;
+	struct nlattr *tb[IFLA_MAX + 1];
+	struct net *dest_net, *link_net;
+	struct nlattr **slave_data;
+	char kind[MODULE_NAME_LEN];
 	struct net_device *dev;
-	struct net_device *master_dev = NULL;
 	struct ifinfomsg *ifm;
-	char kind[MODULE_NAME_LEN];
 	char ifname[IFNAMSIZ];
-	struct nlattr *tb[IFLA_MAX+1];
-	struct nlattr *linkinfo[IFLA_INFO_MAX+1];
-	unsigned char name_assign_type = NET_NAME_USER;
+	struct nlattr **data;
 	int err;
 
 #ifdef CONFIG_MODULES
@@ -3040,195 +3045,185 @@ replay:
 		ops = NULL;
 	}
 
-	if (1) {
-		struct nlattr *attr[RTNL_MAX_TYPE + 1];
-		struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
-		struct nlattr **data = NULL;
-		struct nlattr **slave_data = NULL;
-		struct net *dest_net, *link_net = NULL;
-
-		if (ops) {
-			if (ops->maxtype > RTNL_MAX_TYPE)
-				return -EINVAL;
+	data = NULL;
+	if (ops) {
+		if (ops->maxtype > RTNL_MAX_TYPE)
+			return -EINVAL;
 
-			if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
-				err = nla_parse_nested(attr, ops->maxtype,
-						       linkinfo[IFLA_INFO_DATA],
-						       ops->policy, extack);
-				if (err < 0)
-					return err;
-				data = attr;
-			}
-			if (ops->validate) {
-				err = ops->validate(tb, data, extack);
-				if (err < 0)
-					return err;
-			}
+		if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
+			err = nla_parse_nested(attr, ops->maxtype,
+					       linkinfo[IFLA_INFO_DATA],
+					       ops->policy, extack);
+			if (err < 0)
+				return err;
+			data = attr;
+		}
+		if (ops->validate) {
+			err = ops->validate(tb, data, extack);
+			if (err < 0)
+				return err;
 		}
+	}
 
-		if (m_ops) {
-			if (m_ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE)
-				return -EINVAL;
+	slave_data = NULL;
+	if (m_ops) {
+		if (m_ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE)
+			return -EINVAL;
 
-			if (m_ops->slave_maxtype &&
-			    linkinfo[IFLA_INFO_SLAVE_DATA]) {
-				err = nla_parse_nested(slave_attr,
-						       m_ops->slave_maxtype,
-						       linkinfo[IFLA_INFO_SLAVE_DATA],
-						       m_ops->slave_policy,
-						       extack);
-				if (err < 0)
-					return err;
-				slave_data = slave_attr;
-			}
+		if (m_ops->slave_maxtype &&
+		    linkinfo[IFLA_INFO_SLAVE_DATA]) {
+			err = nla_parse_nested(slave_attr, m_ops->slave_maxtype,
+					       linkinfo[IFLA_INFO_SLAVE_DATA],
+					       m_ops->slave_policy, extack);
+			if (err < 0)
+				return err;
+			slave_data = slave_attr;
 		}
+	}
 
-		if (dev) {
-			int status = 0;
-
-			if (nlh->nlmsg_flags & NLM_F_EXCL)
-				return -EEXIST;
-			if (nlh->nlmsg_flags & NLM_F_REPLACE)
-				return -EOPNOTSUPP;
+	if (dev) {
+		int status = 0;
 
-			if (linkinfo[IFLA_INFO_DATA]) {
-				if (!ops || ops != dev->rtnl_link_ops ||
-				    !ops->changelink)
-					return -EOPNOTSUPP;
+		if (nlh->nlmsg_flags & NLM_F_EXCL)
+			return -EEXIST;
+		if (nlh->nlmsg_flags & NLM_F_REPLACE)
+			return -EOPNOTSUPP;
 
-				err = ops->changelink(dev, tb, data, extack);
-				if (err < 0)
-					return err;
-				status |= DO_SETLINK_NOTIFY;
-			}
+		if (linkinfo[IFLA_INFO_DATA]) {
+			if (!ops || ops != dev->rtnl_link_ops ||
+			    !ops->changelink)
+				return -EOPNOTSUPP;
 
-			if (linkinfo[IFLA_INFO_SLAVE_DATA]) {
-				if (!m_ops || !m_ops->slave_changelink)
-					return -EOPNOTSUPP;
+			err = ops->changelink(dev, tb, data, extack);
+			if (err < 0)
+				return err;
+			status |= DO_SETLINK_NOTIFY;
+		}
 
-				err = m_ops->slave_changelink(master_dev, dev,
-							      tb, slave_data,
-							      extack);
-				if (err < 0)
-					return err;
-				status |= DO_SETLINK_NOTIFY;
-			}
+		if (linkinfo[IFLA_INFO_SLAVE_DATA]) {
+			if (!m_ops || !m_ops->slave_changelink)
+				return -EOPNOTSUPP;
 
-			return do_setlink(skb, dev, ifm, extack, tb, ifname,
-					  status);
+			err = m_ops->slave_changelink(master_dev, dev, tb,
+						      slave_data, extack);
+			if (err < 0)
+				return err;
+			status |= DO_SETLINK_NOTIFY;
 		}
 
-		if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
-			if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
-				return rtnl_group_changelink(skb, net,
+		return do_setlink(skb, dev, ifm, extack, tb, ifname, status);
+	}
+
+	if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
+		if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
+			return rtnl_group_changelink(skb, net,
 						nla_get_u32(tb[IFLA_GROUP]),
 						ifm, extack, tb);
-			return -ENODEV;
-		}
+		return -ENODEV;
+	}
 
-		if (tb[IFLA_MAP] || tb[IFLA_PROTINFO])
-			return -EOPNOTSUPP;
+	if (tb[IFLA_MAP] || tb[IFLA_PROTINFO])
+		return -EOPNOTSUPP;
 
-		if (!ops) {
+	if (!ops) {
 #ifdef CONFIG_MODULES
-			if (kind[0]) {
-				__rtnl_unlock();
-				request_module("rtnl-link-%s", kind);
-				rtnl_lock();
-				ops = rtnl_link_ops_get(kind);
-				if (ops)
-					goto replay;
-			}
-#endif
-			NL_SET_ERR_MSG(extack, "Unknown device type");
-			return -EOPNOTSUPP;
+		if (kind[0]) {
+			__rtnl_unlock();
+			request_module("rtnl-link-%s", kind);
+			rtnl_lock();
+			ops = rtnl_link_ops_get(kind);
+			if (ops)
+				goto replay;
 		}
+#endif
+		NL_SET_ERR_MSG(extack, "Unknown device type");
+		return -EOPNOTSUPP;
+	}
 
-		if (!ops->setup)
-			return -EOPNOTSUPP;
-
-		if (!ifname[0]) {
-			snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind);
-			name_assign_type = NET_NAME_ENUM;
-		}
+	if (!ops->setup)
+		return -EOPNOTSUPP;
 
-		dest_net = rtnl_link_get_net_capable(skb, net, tb, CAP_NET_ADMIN);
-		if (IS_ERR(dest_net))
-			return PTR_ERR(dest_net);
+	if (!ifname[0]) {
+		snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind);
+		name_assign_type = NET_NAME_ENUM;
+	}
 
-		if (tb[IFLA_LINK_NETNSID]) {
-			int id = nla_get_s32(tb[IFLA_LINK_NETNSID]);
+	dest_net = rtnl_link_get_net_capable(skb, net, tb, CAP_NET_ADMIN);
+	if (IS_ERR(dest_net))
+		return PTR_ERR(dest_net);
 
-			link_net = get_net_ns_by_id(dest_net, id);
-			if (!link_net) {
-				NL_SET_ERR_MSG(extack, "Unknown network namespace id");
-				err =  -EINVAL;
-				goto out;
-			}
-			err = -EPERM;
-			if (!netlink_ns_capable(skb, link_net->user_ns, CAP_NET_ADMIN))
-				goto out;
-		}
+	if (tb[IFLA_LINK_NETNSID]) {
+		int id = nla_get_s32(tb[IFLA_LINK_NETNSID]);
 
-		dev = rtnl_create_link(link_net ? : dest_net, ifname,
-				       name_assign_type, ops, tb, extack);
-		if (IS_ERR(dev)) {
-			err = PTR_ERR(dev);
+		link_net = get_net_ns_by_id(dest_net, id);
+		if (!link_net) {
+			NL_SET_ERR_MSG(extack, "Unknown network namespace id");
+			err =  -EINVAL;
 			goto out;
 		}
+		err = -EPERM;
+		if (!netlink_ns_capable(skb, link_net->user_ns, CAP_NET_ADMIN))
+			goto out;
+	} else {
+		link_net = NULL;
+	}
 
-		dev->ifindex = ifm->ifi_index;
+	dev = rtnl_create_link(link_net ? : dest_net, ifname,
+			       name_assign_type, ops, tb, extack);
+	if (IS_ERR(dev)) {
+		err = PTR_ERR(dev);
+		goto out;
+	}
 
-		if (ops->newlink) {
-			err = ops->newlink(link_net ? : net, dev, tb, data,
-					   extack);
-			/* Drivers should call free_netdev() in ->destructor
-			 * and unregister it on failure after registration
-			 * so that device could be finally freed in rtnl_unlock.
-			 */
-			if (err < 0) {
-				/* If device is not registered at all, free it now */
-				if (dev->reg_state == NETREG_UNINITIALIZED)
-					free_netdev(dev);
-				goto out;
-			}
-		} else {
-			err = register_netdevice(dev);
-			if (err < 0) {
+	dev->ifindex = ifm->ifi_index;
+
+	if (ops->newlink) {
+		err = ops->newlink(link_net ? : net, dev, tb, data, extack);
+		/* Drivers should call free_netdev() in ->destructor
+		 * and unregister it on failure after registration
+		 * so that device could be finally freed in rtnl_unlock.
+		 */
+		if (err < 0) {
+			/* If device is not registered at all, free it now */
+			if (dev->reg_state == NETREG_UNINITIALIZED)
 				free_netdev(dev);
-				goto out;
-			}
+			goto out;
+		}
+	} else {
+		err = register_netdevice(dev);
+		if (err < 0) {
+			free_netdev(dev);
+			goto out;
 		}
-		err = rtnl_configure_link(dev, ifm);
+	}
+	err = rtnl_configure_link(dev, ifm);
+	if (err < 0)
+		goto out_unregister;
+	if (link_net) {
+		err = dev_change_net_namespace(dev, dest_net, ifname);
 		if (err < 0)
 			goto out_unregister;
-		if (link_net) {
-			err = dev_change_net_namespace(dev, dest_net, ifname);
-			if (err < 0)
-				goto out_unregister;
-		}
-		if (tb[IFLA_MASTER]) {
-			err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]),
-					    extack);
-			if (err)
-				goto out_unregister;
-		}
+	}
+	if (tb[IFLA_MASTER]) {
+		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
+		if (err)
+			goto out_unregister;
+	}
 out:
-		if (link_net)
-			put_net(link_net);
-		put_net(dest_net);
-		return err;
+	if (link_net)
+		put_net(link_net);
+	put_net(dest_net);
+	return err;
 out_unregister:
-		if (ops->newlink) {
-			LIST_HEAD(list_kill);
+	if (ops->newlink) {
+		LIST_HEAD(list_kill);
 
-			ops->dellink(dev, &list_kill);
-			unregister_netdevice_many(&list_kill);
-		} else {
-			unregister_netdevice(dev);
-		}
-		goto out;
+		ops->dellink(dev, &list_kill);
+		unregister_netdevice_many(&list_kill);
+	} else {
+		unregister_netdevice(dev);
 	}
+	goto out;
 }
 
 static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
-- 
cgit v1.2.3


From a293974590cfdc2d59c559a54d62a5ecb648104b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 27 Nov 2018 22:32:31 -0800
Subject: rtnetlink: avoid frame size warning in rtnl_newlink()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Standard kernel compilation produces the following warning:

net/core/rtnetlink.c: In function ‘rtnl_newlink’:
net/core/rtnetlink.c:3232:1: warning: the frame size of 1288 bytes is larger than 1024 bytes [-Wframe-larger-than=]
 }
  ^

This should not really be an issue, as rtnl_newlink() stack is
generally quite shallow.

Fix the warning by allocating attributes with kmalloc() in a wrapper
and passing it down to rtnl_newlink(), avoiding complexities on error
paths.

Alternatively we could kmalloc() some structure within rtnl_newlink(),
slave attributes look like a good candidate.  In practice it adds to
already rather high complexity and length of the function.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index ee2caa2fd940..98876cd1e36c 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2971,14 +2971,13 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
 	return 0;
 }
 
-static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
-			struct netlink_ext_ack *extack)
+static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct nlattr **attr, struct netlink_ext_ack *extack)
 {
 	struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
 	unsigned char name_assign_type = NET_NAME_USER;
 	struct nlattr *linkinfo[IFLA_INFO_MAX + 1];
 	const struct rtnl_link_ops *m_ops = NULL;
-	struct nlattr *attr[RTNL_MAX_TYPE + 1];
 	struct net_device *master_dev = NULL;
 	struct net *net = sock_net(skb->sk);
 	const struct rtnl_link_ops *ops;
@@ -3226,6 +3225,21 @@ out_unregister:
 	goto out;
 }
 
+static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
+{
+	struct nlattr **attr;
+	int ret;
+
+	attr = kmalloc_array(RTNL_MAX_TYPE + 1, sizeof(*attr), GFP_KERNEL);
+	if (!attr)
+		return -ENOMEM;
+
+	ret = __rtnl_newlink(skb, nlh, attr, extack);
+	kfree(attr);
+	return ret;
+}
+
 static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct netlink_ext_ack *extack)
 {
-- 
cgit v1.2.3


From 36907cd5cd720c5a6d36670b49eba3b1f7f4d8fe Mon Sep 17 00:00:00 2001
From: Ariel Elior <Ariel.Elior@cavium.com>
Date: Wed, 28 Nov 2018 18:16:02 +0200
Subject: qed: Add doorbell overflow recovery mechanism

Add the database used to register doorbelling entities, and APIs for adding
and deleting entries, and logic for traversing the database and doorbelling
once on behalf of all entities.

Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Tomer Tayar <Tomer.Tayar@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed.h         |  17 ++
 drivers/net/ethernet/qlogic/qed/qed_dev.c     | 320 ++++++++++++++++++++++++++
 drivers/net/ethernet/qlogic/qed/qed_dev_api.h |  28 +++
 include/linux/qed/qed_if.h                    |  14 ++
 4 files changed, 379 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index d9a03aba0e02..fb399ee681d3 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -296,6 +296,12 @@ enum qed_wol_support {
 	QED_WOL_SUPPORT_PME,
 };
 
+enum qed_db_rec_exec {
+	DB_REC_DRY_RUN,
+	DB_REC_REAL_DEAL,
+	DB_REC_ONCE,
+};
+
 struct qed_hw_info {
 	/* PCI personality */
 	enum qed_pci_personality personality;
@@ -425,6 +431,14 @@ struct qed_qm_info {
 	u8 num_pf_rls;
 };
 
+struct qed_db_recovery_info {
+	struct list_head list;
+
+	/* Lock to protect the doorbell recovery mechanism list */
+	spinlock_t lock;
+	u32 db_recovery_counter;
+};
+
 struct storm_stats {
 	u32     address;
 	u32     len;
@@ -640,6 +654,9 @@ struct qed_hwfn {
 	/* L2-related */
 	struct qed_l2_info *p_l2_info;
 
+	/* Mechanism for recovering from doorbell drop */
+	struct qed_db_recovery_info db_recovery_info;
+
 	/* Nvm images number and attributes */
 	struct qed_nvm_image_info nvm_info;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 88a8576ca9ce..19b8a6d72832 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -66,6 +66,318 @@
 
 static DEFINE_SPINLOCK(qm_lock);
 
+/******************** Doorbell Recovery *******************/
+/* The doorbell recovery mechanism consists of a list of entries which represent
+ * doorbelling entities (l2 queues, roce sq/rq/cqs, the slowpath spq, etc). Each
+ * entity needs to register with the mechanism and provide the parameters
+ * describing it's doorbell, including a location where last used doorbell data
+ * can be found. The doorbell execute function will traverse the list and
+ * doorbell all of the registered entries.
+ */
+struct qed_db_recovery_entry {
+	struct list_head list_entry;
+	void __iomem *db_addr;
+	void *db_data;
+	enum qed_db_rec_width db_width;
+	enum qed_db_rec_space db_space;
+	u8 hwfn_idx;
+};
+
+/* Display a single doorbell recovery entry */
+static void qed_db_recovery_dp_entry(struct qed_hwfn *p_hwfn,
+				     struct qed_db_recovery_entry *db_entry,
+				     char *action)
+{
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_SPQ,
+		   "(%s: db_entry %p, addr %p, data %p, width %s, %s space, hwfn %d)\n",
+		   action,
+		   db_entry,
+		   db_entry->db_addr,
+		   db_entry->db_data,
+		   db_entry->db_width == DB_REC_WIDTH_32B ? "32b" : "64b",
+		   db_entry->db_space == DB_REC_USER ? "user" : "kernel",
+		   db_entry->hwfn_idx);
+}
+
+/* Doorbell address sanity (address within doorbell bar range) */
+static bool qed_db_rec_sanity(struct qed_dev *cdev,
+			      void __iomem *db_addr, void *db_data)
+{
+	/* Make sure doorbell address is within the doorbell bar */
+	if (db_addr < cdev->doorbells ||
+	    (u8 __iomem *)db_addr >
+	    (u8 __iomem *)cdev->doorbells + cdev->db_size) {
+		WARN(true,
+		     "Illegal doorbell address: %p. Legal range for doorbell addresses is [%p..%p]\n",
+		     db_addr,
+		     cdev->doorbells,
+		     (u8 __iomem *)cdev->doorbells + cdev->db_size);
+		return false;
+	}
+
+	/* ake sure doorbell data pointer is not null */
+	if (!db_data) {
+		WARN(true, "Illegal doorbell data pointer: %p", db_data);
+		return false;
+	}
+
+	return true;
+}
+
+/* Find hwfn according to the doorbell address */
+static struct qed_hwfn *qed_db_rec_find_hwfn(struct qed_dev *cdev,
+					     void __iomem *db_addr)
+{
+	struct qed_hwfn *p_hwfn;
+
+	/* In CMT doorbell bar is split down the middle between engine 0 and enigne 1 */
+	if (cdev->num_hwfns > 1)
+		p_hwfn = db_addr < cdev->hwfns[1].doorbells ?
+		    &cdev->hwfns[0] : &cdev->hwfns[1];
+	else
+		p_hwfn = QED_LEADING_HWFN(cdev);
+
+	return p_hwfn;
+}
+
+/* Add a new entry to the doorbell recovery mechanism */
+int qed_db_recovery_add(struct qed_dev *cdev,
+			void __iomem *db_addr,
+			void *db_data,
+			enum qed_db_rec_width db_width,
+			enum qed_db_rec_space db_space)
+{
+	struct qed_db_recovery_entry *db_entry;
+	struct qed_hwfn *p_hwfn;
+
+	/* Shortcircuit VFs, for now */
+	if (IS_VF(cdev)) {
+		DP_VERBOSE(cdev,
+			   QED_MSG_IOV, "db recovery - skipping VF doorbell\n");
+		return 0;
+	}
+
+	/* Sanitize doorbell address */
+	if (!qed_db_rec_sanity(cdev, db_addr, db_data))
+		return -EINVAL;
+
+	/* Obtain hwfn from doorbell address */
+	p_hwfn = qed_db_rec_find_hwfn(cdev, db_addr);
+
+	/* Create entry */
+	db_entry = kzalloc(sizeof(*db_entry), GFP_KERNEL);
+	if (!db_entry) {
+		DP_NOTICE(cdev, "Failed to allocate a db recovery entry\n");
+		return -ENOMEM;
+	}
+
+	/* Populate entry */
+	db_entry->db_addr = db_addr;
+	db_entry->db_data = db_data;
+	db_entry->db_width = db_width;
+	db_entry->db_space = db_space;
+	db_entry->hwfn_idx = p_hwfn->my_id;
+
+	/* Display */
+	qed_db_recovery_dp_entry(p_hwfn, db_entry, "Adding");
+
+	/* Protect the list */
+	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
+	list_add_tail(&db_entry->list_entry, &p_hwfn->db_recovery_info.list);
+	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
+
+	return 0;
+}
+
+/* Remove an entry from the doorbell recovery mechanism */
+int qed_db_recovery_del(struct qed_dev *cdev,
+			void __iomem *db_addr, void *db_data)
+{
+	struct qed_db_recovery_entry *db_entry = NULL;
+	struct qed_hwfn *p_hwfn;
+	int rc = -EINVAL;
+
+	/* Shortcircuit VFs, for now */
+	if (IS_VF(cdev)) {
+		DP_VERBOSE(cdev,
+			   QED_MSG_IOV, "db recovery - skipping VF doorbell\n");
+		return 0;
+	}
+
+	/* Sanitize doorbell address */
+	if (!qed_db_rec_sanity(cdev, db_addr, db_data))
+		return -EINVAL;
+
+	/* Obtain hwfn from doorbell address */
+	p_hwfn = qed_db_rec_find_hwfn(cdev, db_addr);
+
+	/* Protect the list */
+	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
+	list_for_each_entry(db_entry,
+			    &p_hwfn->db_recovery_info.list, list_entry) {
+		/* search according to db_data addr since db_addr is not unique (roce) */
+		if (db_entry->db_data == db_data) {
+			qed_db_recovery_dp_entry(p_hwfn, db_entry, "Deleting");
+			list_del(&db_entry->list_entry);
+			rc = 0;
+			break;
+		}
+	}
+
+	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
+
+	if (rc == -EINVAL)
+
+		DP_NOTICE(p_hwfn,
+			  "Failed to find element in list. Key (db_data addr) was %p. db_addr was %p\n",
+			  db_data, db_addr);
+	else
+		kfree(db_entry);
+
+	return rc;
+}
+
+/* Initialize the doorbell recovery mechanism */
+static int qed_db_recovery_setup(struct qed_hwfn *p_hwfn)
+{
+	DP_VERBOSE(p_hwfn, QED_MSG_SPQ, "Setting up db recovery\n");
+
+	/* Make sure db_size was set in cdev */
+	if (!p_hwfn->cdev->db_size) {
+		DP_ERR(p_hwfn->cdev, "db_size not set\n");
+		return -EINVAL;
+	}
+
+	INIT_LIST_HEAD(&p_hwfn->db_recovery_info.list);
+	spin_lock_init(&p_hwfn->db_recovery_info.lock);
+	p_hwfn->db_recovery_info.db_recovery_counter = 0;
+
+	return 0;
+}
+
+/* Destroy the doorbell recovery mechanism */
+static void qed_db_recovery_teardown(struct qed_hwfn *p_hwfn)
+{
+	struct qed_db_recovery_entry *db_entry = NULL;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SPQ, "Tearing down db recovery\n");
+	if (!list_empty(&p_hwfn->db_recovery_info.list)) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_SPQ,
+			   "Doorbell Recovery teardown found the doorbell recovery list was not empty (Expected in disorderly driver unload (e.g. recovery) otherwise this probably means some flow forgot to db_recovery_del). Prepare to purge doorbell recovery list...\n");
+		while (!list_empty(&p_hwfn->db_recovery_info.list)) {
+			db_entry =
+			    list_first_entry(&p_hwfn->db_recovery_info.list,
+					     struct qed_db_recovery_entry,
+					     list_entry);
+			qed_db_recovery_dp_entry(p_hwfn, db_entry, "Purging");
+			list_del(&db_entry->list_entry);
+			kfree(db_entry);
+		}
+	}
+	p_hwfn->db_recovery_info.db_recovery_counter = 0;
+}
+
+/* Print the content of the doorbell recovery mechanism */
+void qed_db_recovery_dp(struct qed_hwfn *p_hwfn)
+{
+	struct qed_db_recovery_entry *db_entry = NULL;
+
+	DP_NOTICE(p_hwfn,
+		  "Dispalying doorbell recovery database. Counter was %d\n",
+		  p_hwfn->db_recovery_info.db_recovery_counter);
+
+	/* Protect the list */
+	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
+	list_for_each_entry(db_entry,
+			    &p_hwfn->db_recovery_info.list, list_entry) {
+		qed_db_recovery_dp_entry(p_hwfn, db_entry, "Printing");
+	}
+
+	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
+}
+
+/* Ring the doorbell of a single doorbell recovery entry */
+static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
+				 struct qed_db_recovery_entry *db_entry,
+				 enum qed_db_rec_exec db_exec)
+{
+	if (db_exec != DB_REC_ONCE) {
+		/* Print according to width */
+		if (db_entry->db_width == DB_REC_WIDTH_32B) {
+			DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+				   "%s doorbell address %p data %x\n",
+				   db_exec == DB_REC_DRY_RUN ?
+				   "would have rung" : "ringing",
+				   db_entry->db_addr,
+				   *(u32 *)db_entry->db_data);
+		} else {
+			DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+				   "%s doorbell address %p data %llx\n",
+				   db_exec == DB_REC_DRY_RUN ?
+				   "would have rung" : "ringing",
+				   db_entry->db_addr,
+				   *(u64 *)(db_entry->db_data));
+		}
+	}
+
+	/* Sanity */
+	if (!qed_db_rec_sanity(p_hwfn->cdev, db_entry->db_addr,
+			       db_entry->db_data))
+		return;
+
+	/* Flush the write combined buffer. Since there are multiple doorbelling
+	 * entities using the same address, if we don't flush, a transaction
+	 * could be lost.
+	 */
+	wmb();
+
+	/* Ring the doorbell */
+	if (db_exec == DB_REC_REAL_DEAL || db_exec == DB_REC_ONCE) {
+		if (db_entry->db_width == DB_REC_WIDTH_32B)
+			DIRECT_REG_WR(db_entry->db_addr,
+				      *(u32 *)(db_entry->db_data));
+		else
+			DIRECT_REG_WR64(db_entry->db_addr,
+					*(u64 *)(db_entry->db_data));
+	}
+
+	/* Flush the write combined buffer. Next doorbell may come from a
+	 * different entity to the same address...
+	 */
+	wmb();
+}
+
+/* Traverse the doorbell recovery entry list and ring all the doorbells */
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn,
+			     enum qed_db_rec_exec db_exec)
+{
+	struct qed_db_recovery_entry *db_entry = NULL;
+
+	if (db_exec != DB_REC_ONCE) {
+		DP_NOTICE(p_hwfn,
+			  "Executing doorbell recovery. Counter was %d\n",
+			  p_hwfn->db_recovery_info.db_recovery_counter);
+
+		/* Track amount of times recovery was executed */
+		p_hwfn->db_recovery_info.db_recovery_counter++;
+	}
+
+	/* Protect the list */
+	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
+	list_for_each_entry(db_entry,
+			    &p_hwfn->db_recovery_info.list, list_entry) {
+		qed_db_recovery_ring(p_hwfn, db_entry, db_exec);
+		if (db_exec == DB_REC_ONCE)
+			break;
+	}
+
+	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
+}
+
+/******************** Doorbell Recovery end ****************/
+
 #define QED_MIN_DPIS            (4)
 #define QED_MIN_PWM_REGION      (QED_WID_SIZE * QED_MIN_DPIS)
 
@@ -194,6 +506,9 @@ void qed_resc_free(struct qed_dev *cdev)
 		qed_dmae_info_free(p_hwfn);
 		qed_dcbx_info_free(p_hwfn);
 		qed_dbg_user_data_free(p_hwfn);
+
+		/* Destroy doorbell recovery mechanism */
+		qed_db_recovery_teardown(p_hwfn);
 	}
 }
 
@@ -969,6 +1284,11 @@ int qed_resc_alloc(struct qed_dev *cdev)
 		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
 		u32 n_eqes, num_cons;
 
+		/* Initialize the doorbell recovery mechanism */
+		rc = qed_db_recovery_setup(p_hwfn);
+		if (rc)
+			goto alloc_err;
+
 		/* First allocate the context manager structure */
 		rc = qed_cxt_mngr_alloc(p_hwfn);
 		if (rc)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
index defdda1ffaa2..acccd85170aa 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
@@ -472,6 +472,34 @@ int qed_get_queue_coalesce(struct qed_hwfn *p_hwfn, u16 *coal, void *handle);
 int
 qed_set_queue_coalesce(u16 rx_coal, u16 tx_coal, void *p_handle);
 
+/**
+ * @brief db_recovery_add - add doorbell information to the doorbell
+ * recovery mechanism.
+ *
+ * @param cdev
+ * @param db_addr - doorbell address
+ * @param db_data - address of where db_data is stored
+ * @param db_width - doorbell is 32b pr 64b
+ * @param db_space - doorbell recovery addresses are user or kernel space
+ */
+int qed_db_recovery_add(struct qed_dev *cdev,
+			void __iomem *db_addr,
+			void *db_data,
+			enum qed_db_rec_width db_width,
+			enum qed_db_rec_space db_space);
+
+/**
+ * @brief db_recovery_del - remove doorbell information from the doorbell
+ * recovery mechanism. db_data serves as key (db_addr is not unique).
+ *
+ * @param cdev
+ * @param db_addr - doorbell address
+ * @param db_data - address where db_data is stored. Serves as key for the
+ *                  entry to delete.
+ */
+int qed_db_recovery_del(struct qed_dev *cdev,
+			void __iomem *db_addr, void *db_data);
+
 
 const char *qed_hw_get_resc_name(enum qed_resources res_id);
 #endif
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index a47321a0d572..eb851f89f417 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -47,6 +47,7 @@
 #include <linux/slab.h>
 #include <linux/qed/common_hsi.h>
 #include <linux/qed/qed_chain.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 
 enum dcbx_protocol_type {
 	DCBX_PROTOCOL_ISCSI,
@@ -448,11 +449,24 @@ struct qed_mfw_tlv_iscsi {
 	bool tx_bytes_set;
 };
 
+enum qed_db_rec_width {
+	DB_REC_WIDTH_32B,
+	DB_REC_WIDTH_64B,
+};
+
+enum qed_db_rec_space {
+	DB_REC_KERNEL,
+	DB_REC_USER,
+};
+
 #define DIRECT_REG_WR(reg_addr, val) writel((u32)val, \
 					    (void __iomem *)(reg_addr))
 
 #define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr))
 
+#define DIRECT_REG_WR64(reg_addr, val) writeq((u32)val,	\
+					      (void __iomem *)(reg_addr))
+
 #define QED_COALESCE_MAX 0x1FF
 #define QED_DEFAULT_RX_USECS 12
 #define QED_DEFAULT_TX_USECS 48
-- 
cgit v1.2.3


From a1b469b8b17f1573741eb0272349eca47d32462a Mon Sep 17 00:00:00 2001
From: Ariel Elior <Ariel.Elior@cavium.com>
Date: Wed, 28 Nov 2018 18:16:03 +0200
Subject: qed: Use the doorbell overflow recovery mechanism in case of doorbell
 overflow

In case of an attention from the doorbell queue block, analyze the HW
indications. In case of a doorbell overflow, execute a doorbell recovery.
Since there can be spurious indications (race conditions between multiple PFs),
schedule a periodic task for checking whether a doorbell overflow may have been
missed. After a set time with no indications, terminate the periodic task.

Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Tomer Tayar <Tomer.Tayar@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed.h          |  14 ++-
 drivers/net/ethernet/qlogic/qed/qed_dev.c      |  14 ++-
 drivers/net/ethernet/qlogic/qed/qed_int.c      | 152 ++++++++++++++++++++++---
 drivers/net/ethernet/qlogic/qed/qed_int.h      |  10 ++
 drivers/net/ethernet/qlogic/qed/qed_main.c     |  64 ++++++++++-
 drivers/net/ethernet/qlogic/qed/qed_reg_addr.h |  50 ++++++++
 6 files changed, 280 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index fb399ee681d3..24a90163775e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -536,6 +536,7 @@ struct qed_simd_fp_handler {
 
 enum qed_slowpath_wq_flag {
 	QED_SLOWPATH_MFW_TLV_REQ,
+	QED_SLOWPATH_PERIODIC_DB_REC,
 };
 
 struct qed_hwfn {
@@ -669,11 +670,12 @@ struct qed_hwfn {
 	struct delayed_work iov_task;
 	unsigned long iov_task_flags;
 #endif
-
-	struct z_stream_s		*stream;
+	struct z_stream_s *stream;
+	bool slowpath_wq_active;
 	struct workqueue_struct *slowpath_wq;
 	struct delayed_work slowpath_task;
 	unsigned long slowpath_task_flags;
+	u32 periodic_db_rec_count;
 };
 
 struct pci_params {
@@ -914,6 +916,12 @@ u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 
 #define QED_LEADING_HWFN(dev)   (&dev->hwfns[0])
 
+/* doorbell recovery mechanism */
+void qed_db_recovery_dp(struct qed_hwfn *p_hwfn);
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn,
+			     enum qed_db_rec_exec db_exec);
+bool qed_edpm_enabled(struct qed_hwfn *p_hwfn);
+
 /* Other Linux specific common definitions */
 #define DP_NAME(cdev) ((cdev)->name)
 
@@ -948,4 +956,6 @@ int qed_mfw_fill_tlv_data(struct qed_hwfn *hwfn,
 			  union qed_mfw_tlv_data *tlv_data);
 
 void qed_hw_info_set_offload_tc(struct qed_hw_info *p_info, u8 tc);
+
+void qed_periodic_db_rec_start(struct qed_hwfn *p_hwfn);
 #endif /* _QED_H */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 19b8a6d72832..a817b6632eb2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -1788,6 +1788,14 @@ enum QED_ROCE_EDPM_MODE {
 	QED_ROCE_EDPM_MODE_DISABLE = 2,
 };
 
+bool qed_edpm_enabled(struct qed_hwfn *p_hwfn)
+{
+	if (p_hwfn->dcbx_no_edpm || p_hwfn->db_bar_no_edpm)
+		return false;
+
+	return true;
+}
+
 static int
 qed_hw_init_pf_doorbell_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
@@ -1857,13 +1865,13 @@ qed_hw_init_pf_doorbell_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	p_hwfn->wid_count = (u16) n_cpus;
 
 	DP_INFO(p_hwfn,
-		"doorbell bar: normal_region_size=%d, pwm_region_size=%d, dpi_size=%d, dpi_count=%d, roce_edpm=%s\n",
+		"doorbell bar: normal_region_size=%d, pwm_region_size=%d, dpi_size=%d, dpi_count=%d, roce_edpm=%s, page_size=%lu\n",
 		norm_regsize,
 		pwm_regsize,
 		p_hwfn->dpi_size,
 		p_hwfn->dpi_count,
-		((p_hwfn->dcbx_no_edpm) || (p_hwfn->db_bar_no_edpm)) ?
-		"disabled" : "enabled");
+		(!qed_edpm_enabled(p_hwfn)) ?
+		"disabled" : "enabled", PAGE_SIZE);
 
 	if (rc) {
 		DP_ERR(p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index b22f464ea3fa..92340919d852 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -361,29 +361,147 @@ static int qed_pglub_rbc_attn_cb(struct qed_hwfn *p_hwfn)
 	return 0;
 }
 
-#define QED_DORQ_ATTENTION_REASON_MASK	(0xfffff)
-#define QED_DORQ_ATTENTION_OPAQUE_MASK (0xffff)
-#define QED_DORQ_ATTENTION_SIZE_MASK	(0x7f)
-#define QED_DORQ_ATTENTION_SIZE_SHIFT	(16)
+#define QED_DORQ_ATTENTION_REASON_MASK  (0xfffff)
+#define QED_DORQ_ATTENTION_OPAQUE_MASK  (0xffff)
+#define QED_DORQ_ATTENTION_OPAQUE_SHIFT (0x0)
+#define QED_DORQ_ATTENTION_SIZE_MASK            (0x7f)
+#define QED_DORQ_ATTENTION_SIZE_SHIFT           (16)
+
+#define QED_DB_REC_COUNT                        1000
+#define QED_DB_REC_INTERVAL                     100
+
+static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn,
+				  struct qed_ptt *p_ptt)
+{
+	u32 count = QED_DB_REC_COUNT;
+	u32 usage = 1;
+
+	/* wait for usage to zero or count to run out. This is necessary since
+	 * EDPM doorbell transactions can take multiple 64b cycles, and as such
+	 * can "split" over the pci. Possibly, the doorbell drop can happen with
+	 * half an EDPM in the queue and other half dropped. Another EDPM
+	 * doorbell to the same address (from doorbell recovery mechanism or
+	 * from the doorbelling entity) could have first half dropped and second
+	 * half interpreted as continuation of the first. To prevent such
+	 * malformed doorbells from reaching the device, flush the queue before
+	 * releasing the overflow sticky indication.
+	 */
+	while (count-- && usage) {
+		usage = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_USAGE_CNT);
+		udelay(QED_DB_REC_INTERVAL);
+	}
+
+	/* should have been depleted by now */
+	if (usage) {
+		DP_NOTICE(p_hwfn->cdev,
+			  "DB recovery: doorbell usage failed to zero after %d usec. usage was %x\n",
+			  QED_DB_REC_INTERVAL * QED_DB_REC_COUNT, usage);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	u32 overflow;
+	int rc;
+
+	overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+	DP_NOTICE(p_hwfn, "PF Overflow sticky 0x%x\n", overflow);
+	if (!overflow) {
+		qed_db_recovery_execute(p_hwfn, DB_REC_ONCE);
+		return 0;
+	}
+
+	if (qed_edpm_enabled(p_hwfn)) {
+		rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
+		if (rc)
+			return rc;
+	}
+
+	/* Flush any pending (e)dpm as they may never arrive */
+	qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
+
+	/* Release overflow sticky indication (stop silently dropping everything) */
+	qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
+
+	/* Repeat all last doorbells (doorbell drop recovery) */
+	qed_db_recovery_execute(p_hwfn, DB_REC_REAL_DEAL);
+
+	return 0;
+}
+
 static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
 {
-	u32 reason;
+	u32 int_sts, first_drop_reason, details, address, all_drops_reason;
+	struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
+	int rc;
 
-	reason = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt, DORQ_REG_DB_DROP_REASON) &
-			QED_DORQ_ATTENTION_REASON_MASK;
-	if (reason) {
-		u32 details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-				     DORQ_REG_DB_DROP_DETAILS);
+	int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
+	DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
 
-		DP_INFO(p_hwfn->cdev,
-			"DORQ db_drop: address 0x%08x Opaque FID 0x%04x Size [bytes] 0x%08x Reason: 0x%08x\n",
-			qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-			       DORQ_REG_DB_DROP_DETAILS_ADDRESS),
-			(u16)(details & QED_DORQ_ATTENTION_OPAQUE_MASK),
-			GET_FIELD(details, QED_DORQ_ATTENTION_SIZE) * 4,
-			reason);
+	/* int_sts may be zero since all PFs were interrupted for doorbell
+	 * overflow but another one already handled it. Can abort here. If
+	 * This PF also requires overflow recovery we will be interrupted again.
+	 * The masked almost full indication may also be set. Ignoring.
+	 */
+	if (!(int_sts & ~DORQ_REG_INT_STS_DORQ_FIFO_AFULL))
+		return 0;
+
+	/* check if db_drop or overflow happened */
+	if (int_sts & (DORQ_REG_INT_STS_DB_DROP |
+		       DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR)) {
+		/* Obtain data about db drop/overflow */
+		first_drop_reason = qed_rd(p_hwfn, p_ptt,
+					   DORQ_REG_DB_DROP_REASON) &
+		    QED_DORQ_ATTENTION_REASON_MASK;
+		details = qed_rd(p_hwfn, p_ptt, DORQ_REG_DB_DROP_DETAILS);
+		address = qed_rd(p_hwfn, p_ptt,
+				 DORQ_REG_DB_DROP_DETAILS_ADDRESS);
+		all_drops_reason = qed_rd(p_hwfn, p_ptt,
+					  DORQ_REG_DB_DROP_DETAILS_REASON);
+
+		/* Log info */
+		DP_NOTICE(p_hwfn->cdev,
+			  "Doorbell drop occurred\n"
+			  "Address\t\t0x%08x\t(second BAR address)\n"
+			  "FID\t\t0x%04x\t\t(Opaque FID)\n"
+			  "Size\t\t0x%04x\t\t(in bytes)\n"
+			  "1st drop reason\t0x%08x\t(details on first drop since last handling)\n"
+			  "Sticky reasons\t0x%08x\t(all drop reasons since last handling)\n",
+			  address,
+			  GET_FIELD(details, QED_DORQ_ATTENTION_OPAQUE),
+			  GET_FIELD(details, QED_DORQ_ATTENTION_SIZE) * 4,
+			  first_drop_reason, all_drops_reason);
+
+		rc = qed_db_rec_handler(p_hwfn, p_ptt);
+		qed_periodic_db_rec_start(p_hwfn);
+		if (rc)
+			return rc;
+
+		/* Clear the doorbell drop details and prepare for next drop */
+		qed_wr(p_hwfn, p_ptt, DORQ_REG_DB_DROP_DETAILS_REL, 0);
+
+		/* Mark interrupt as handled (note: even if drop was due to a different
+		 * reason than overflow we mark as handled)
+		 */
+		qed_wr(p_hwfn,
+		       p_ptt,
+		       DORQ_REG_INT_STS_WR,
+		       DORQ_REG_INT_STS_DB_DROP |
+		       DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR);
+
+		/* If there are no indications other than drop indications, success */
+		if ((int_sts & ~(DORQ_REG_INT_STS_DB_DROP |
+				 DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR |
+				 DORQ_REG_INT_STS_DORQ_FIFO_AFULL)) == 0)
+			return 0;
 	}
 
+	/* Some other indication was present - non recoverable */
+	DP_INFO(p_hwfn, "DORQ fatal attention\n");
+
 	return -EINVAL;
 }
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h
index 54b4ee0acfd7..d81a62ebd524 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.h
@@ -190,6 +190,16 @@ void qed_int_get_num_sbs(struct qed_hwfn	*p_hwfn,
  */
 void qed_int_disable_post_isr_release(struct qed_dev *cdev);
 
+/**
+ * @brief - Doorbell Recovery handler.
+ *          Run DB_REAL_DEAL doorbell recovery in case of PF overflow
+ *          (and flush DORQ if needed), otherwise run DB_REC_ONCE.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ */
+int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
 #define QED_CAU_DEF_RX_TIMER_RES 0
 #define QED_CAU_DEF_TX_TIMER_RES 0
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 4b3e68217502..5ec3f5d1d6b2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -966,9 +966,47 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 	}
 }
 
+#define QED_PERIODIC_DB_REC_COUNT		100
+#define QED_PERIODIC_DB_REC_INTERVAL_MS		100
+#define QED_PERIODIC_DB_REC_INTERVAL \
+	msecs_to_jiffies(QED_PERIODIC_DB_REC_INTERVAL_MS)
+#define QED_PERIODIC_DB_REC_WAIT_COUNT		10
+#define QED_PERIODIC_DB_REC_WAIT_INTERVAL \
+	(QED_PERIODIC_DB_REC_INTERVAL_MS / QED_PERIODIC_DB_REC_WAIT_COUNT)
+
+static int qed_slowpath_delayed_work(struct qed_hwfn *hwfn,
+				     enum qed_slowpath_wq_flag wq_flag,
+				     unsigned long delay)
+{
+	if (!hwfn->slowpath_wq_active)
+		return -EINVAL;
+
+	/* Memory barrier for setting atomic bit */
+	smp_mb__before_atomic();
+	set_bit(wq_flag, &hwfn->slowpath_task_flags);
+	smp_mb__after_atomic();
+	queue_delayed_work(hwfn->slowpath_wq, &hwfn->slowpath_task, delay);
+
+	return 0;
+}
+
+void qed_periodic_db_rec_start(struct qed_hwfn *p_hwfn)
+{
+	/* Reset periodic Doorbell Recovery counter */
+	p_hwfn->periodic_db_rec_count = QED_PERIODIC_DB_REC_COUNT;
+
+	/* Don't schedule periodic Doorbell Recovery if already scheduled */
+	if (test_bit(QED_SLOWPATH_PERIODIC_DB_REC,
+		     &p_hwfn->slowpath_task_flags))
+		return;
+
+	qed_slowpath_delayed_work(p_hwfn, QED_SLOWPATH_PERIODIC_DB_REC,
+				  QED_PERIODIC_DB_REC_INTERVAL);
+}
+
 static void qed_slowpath_wq_stop(struct qed_dev *cdev)
 {
-	int i;
+	int i, sleep_count = QED_PERIODIC_DB_REC_WAIT_COUNT;
 
 	if (IS_VF(cdev))
 		return;
@@ -977,6 +1015,15 @@ static void qed_slowpath_wq_stop(struct qed_dev *cdev)
 		if (!cdev->hwfns[i].slowpath_wq)
 			continue;
 
+		/* Stop queuing new delayed works */
+		cdev->hwfns[i].slowpath_wq_active = false;
+
+		/* Wait until the last periodic doorbell recovery is executed */
+		while (test_bit(QED_SLOWPATH_PERIODIC_DB_REC,
+				&cdev->hwfns[i].slowpath_task_flags) &&
+		       sleep_count--)
+			msleep(QED_PERIODIC_DB_REC_WAIT_INTERVAL);
+
 		flush_workqueue(cdev->hwfns[i].slowpath_wq);
 		destroy_workqueue(cdev->hwfns[i].slowpath_wq);
 	}
@@ -989,7 +1036,10 @@ static void qed_slowpath_task(struct work_struct *work)
 	struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
 
 	if (!ptt) {
-		queue_delayed_work(hwfn->slowpath_wq, &hwfn->slowpath_task, 0);
+		if (hwfn->slowpath_wq_active)
+			queue_delayed_work(hwfn->slowpath_wq,
+					   &hwfn->slowpath_task, 0);
+
 		return;
 	}
 
@@ -997,6 +1047,15 @@ static void qed_slowpath_task(struct work_struct *work)
 			       &hwfn->slowpath_task_flags))
 		qed_mfw_process_tlv_req(hwfn, ptt);
 
+	if (test_and_clear_bit(QED_SLOWPATH_PERIODIC_DB_REC,
+			       &hwfn->slowpath_task_flags)) {
+		qed_db_rec_handler(hwfn, ptt);
+		if (hwfn->periodic_db_rec_count--)
+			qed_slowpath_delayed_work(hwfn,
+						  QED_SLOWPATH_PERIODIC_DB_REC,
+						  QED_PERIODIC_DB_REC_INTERVAL);
+	}
+
 	qed_ptt_release(hwfn, ptt);
 }
 
@@ -1023,6 +1082,7 @@ static int qed_slowpath_wq_start(struct qed_dev *cdev)
 		}
 
 		INIT_DELAYED_WORK(&hwfn->slowpath_task, qed_slowpath_task);
+		hwfn->slowpath_wq_active = true;
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
index 2440970882c4..8939ed6e08b7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
@@ -1243,6 +1243,56 @@
 	0x1701534UL
 #define TSEM_REG_DBG_FORCE_FRAME \
 	0x1701538UL
+#define DORQ_REG_PF_USAGE_CNT \
+	0x1009c0UL
+#define DORQ_REG_PF_OVFL_STICKY	\
+	0x1009d0UL
+#define DORQ_REG_DPM_FORCE_ABORT \
+	0x1009d8UL
+#define DORQ_REG_INT_STS \
+	0x100180UL
+#define DORQ_REG_INT_STS_ADDRESS_ERROR \
+	(0x1UL << 0)
+#define DORQ_REG_INT_STS_WR \
+	0x100188UL
+#define DORQ_REG_DB_DROP_DETAILS_REL \
+	0x100a28UL
+#define DORQ_REG_INT_STS_ADDRESS_ERROR_SHIFT \
+	0
+#define DORQ_REG_INT_STS_DB_DROP \
+		(0x1UL << 1)
+#define DORQ_REG_INT_STS_DB_DROP_SHIFT \
+	1
+#define DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR \
+		(0x1UL << 2)
+#define DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR_SHIFT \
+	2
+#define DORQ_REG_INT_STS_DORQ_FIFO_AFULL\
+		(0x1UL << 3)
+#define DORQ_REG_INT_STS_DORQ_FIFO_AFULL_SHIFT \
+	3
+#define DORQ_REG_INT_STS_CFC_BYP_VALIDATION_ERR \
+		(0x1UL << 4)
+#define DORQ_REG_INT_STS_CFC_BYP_VALIDATION_ERR_SHIFT \
+	4
+#define DORQ_REG_INT_STS_CFC_LD_RESP_ERR \
+		(0x1UL << 5)
+#define DORQ_REG_INT_STS_CFC_LD_RESP_ERR_SHIFT \
+	5
+#define DORQ_REG_INT_STS_XCM_DONE_CNT_ERR \
+		(0x1UL << 6)
+#define DORQ_REG_INT_STS_XCM_DONE_CNT_ERR_SHIFT	\
+	6
+#define DORQ_REG_INT_STS_CFC_LD_REQ_FIFO_OVFL_ERR \
+		(0x1UL << 7)
+#define DORQ_REG_INT_STS_CFC_LD_REQ_FIFO_OVFL_ERR_SHIFT	\
+	7
+#define DORQ_REG_INT_STS_CFC_LD_REQ_FIFO_UNDER_ERR \
+		(0x1UL << 8)
+#define DORQ_REG_INT_STS_CFC_LD_REQ_FIFO_UNDER_ERR_SHIFT \
+	8
+#define DORQ_REG_DB_DROP_DETAILS_REASON	\
+	0x100a20UL
 #define MSEM_REG_DBG_SELECT \
 	0x1801528UL
 #define MSEM_REG_DBG_DWORD_ENABLE \
-- 
cgit v1.2.3


From 9ecd8c3feaa53405508499495d06a6f1e7dc8e7b Mon Sep 17 00:00:00 2001
From: Ariel Elior <Ariel.Elior@cavium.com>
Date: Wed, 28 Nov 2018 18:16:04 +0200
Subject: qed: Register slowpath queue doorbell with doorbell overflow recovery
 mechanism

Slow path queue is a doorbelling entity. Register it with the overflow mechanism.

Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Tomer Tayar <Tomer.Tayar@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_sp.h  |  4 ++-
 drivers/net/ethernet/qlogic/qed/qed_spq.c | 47 +++++++++++++++++++++++--------
 2 files changed, 38 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index 3157c0d99441..4179c9013fc6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -227,7 +227,9 @@ struct qed_spq {
 	u32			comp_count;
 
 	u32			cid;
-	qed_spq_async_comp_cb async_comp_cb[MAX_PROTOCOL_TYPE];
+	u32			db_addr_offset;
+	struct core_db_data	db_data;
+	qed_spq_async_comp_cb	async_comp_cb[MAX_PROTOCOL_TYPE];
 };
 
 /**
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 0a9c5bb0fa48..eb88bbc6b193 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -252,9 +252,9 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn,
 			   struct qed_spq *p_spq, struct qed_spq_entry *p_ent)
 {
 	struct qed_chain *p_chain = &p_hwfn->p_spq->chain;
+	struct core_db_data *p_db_data = &p_spq->db_data;
 	u16 echo = qed_chain_get_prod_idx(p_chain);
 	struct slow_path_element	*elem;
-	struct core_db_data		db;
 
 	p_ent->elem.hdr.echo	= cpu_to_le16(echo);
 	elem = qed_chain_produce(p_chain);
@@ -266,27 +266,22 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn,
 	*elem = p_ent->elem; /* struct assignment */
 
 	/* send a doorbell on the slow hwfn session */
-	memset(&db, 0, sizeof(db));
-	SET_FIELD(db.params, CORE_DB_DATA_DEST, DB_DEST_XCM);
-	SET_FIELD(db.params, CORE_DB_DATA_AGG_CMD, DB_AGG_CMD_SET);
-	SET_FIELD(db.params, CORE_DB_DATA_AGG_VAL_SEL,
-		  DQ_XCM_CORE_SPQ_PROD_CMD);
-	db.agg_flags = DQ_XCM_CORE_DQ_CF_CMD;
-	db.spq_prod = cpu_to_le16(qed_chain_get_prod_idx(p_chain));
+	p_db_data->spq_prod = cpu_to_le16(qed_chain_get_prod_idx(p_chain));
 
 	/* make sure the SPQE is updated before the doorbell */
 	wmb();
 
-	DOORBELL(p_hwfn, qed_db_addr(p_spq->cid, DQ_DEMS_LEGACY), *(u32 *)&db);
+	DOORBELL(p_hwfn, p_spq->db_addr_offset, *(u32 *)p_db_data);
 
 	/* make sure doorbell is rang */
 	wmb();
 
 	DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
 		   "Doorbelled [0x%08x, CID 0x%08x] with Flags: %02x agg_params: %02x, prod: %04x\n",
-		   qed_db_addr(p_spq->cid, DQ_DEMS_LEGACY),
-		   p_spq->cid, db.params, db.agg_flags,
-		   qed_chain_get_prod_idx(p_chain));
+		   p_spq->db_addr_offset,
+		   p_spq->cid,
+		   p_db_data->params,
+		   p_db_data->agg_flags, qed_chain_get_prod_idx(p_chain));
 
 	return 0;
 }
@@ -490,8 +485,11 @@ void qed_spq_setup(struct qed_hwfn *p_hwfn)
 {
 	struct qed_spq *p_spq = p_hwfn->p_spq;
 	struct qed_spq_entry *p_virt = NULL;
+	struct core_db_data *p_db_data;
+	void __iomem *db_addr;
 	dma_addr_t p_phys = 0;
 	u32 i, capacity;
+	int rc;
 
 	INIT_LIST_HEAD(&p_spq->pending);
 	INIT_LIST_HEAD(&p_spq->completion_pending);
@@ -528,6 +526,25 @@ void qed_spq_setup(struct qed_hwfn *p_hwfn)
 
 	/* reset the chain itself */
 	qed_chain_reset(&p_spq->chain);
+
+	/* Initialize the address/data of the SPQ doorbell */
+	p_spq->db_addr_offset = qed_db_addr(p_spq->cid, DQ_DEMS_LEGACY);
+	p_db_data = &p_spq->db_data;
+	memset(p_db_data, 0, sizeof(*p_db_data));
+	SET_FIELD(p_db_data->params, CORE_DB_DATA_DEST, DB_DEST_XCM);
+	SET_FIELD(p_db_data->params, CORE_DB_DATA_AGG_CMD, DB_AGG_CMD_MAX);
+	SET_FIELD(p_db_data->params, CORE_DB_DATA_AGG_VAL_SEL,
+		  DQ_XCM_CORE_SPQ_PROD_CMD);
+	p_db_data->agg_flags = DQ_XCM_CORE_DQ_CF_CMD;
+
+	/* Register the SPQ doorbell with the doorbell recovery mechanism */
+	db_addr = (void __iomem *)((u8 __iomem *)p_hwfn->doorbells +
+				   p_spq->db_addr_offset);
+	rc = qed_db_recovery_add(p_hwfn->cdev, db_addr, &p_spq->db_data,
+				 DB_REC_WIDTH_32B, DB_REC_KERNEL);
+	if (rc)
+		DP_INFO(p_hwfn,
+			"Failed to register the SPQ doorbell with the doorbell recovery mechanism\n");
 }
 
 int qed_spq_alloc(struct qed_hwfn *p_hwfn)
@@ -575,11 +592,17 @@ spq_allocate_fail:
 void qed_spq_free(struct qed_hwfn *p_hwfn)
 {
 	struct qed_spq *p_spq = p_hwfn->p_spq;
+	void __iomem *db_addr;
 	u32 capacity;
 
 	if (!p_spq)
 		return;
 
+	/* Delete the SPQ doorbell from the doorbell recovery mechanism */
+	db_addr = (void __iomem *)((u8 __iomem *)p_hwfn->doorbells +
+				   p_spq->db_addr_offset);
+	qed_db_recovery_del(p_hwfn->cdev, db_addr, &p_spq->db_data);
+
 	if (p_spq->p_virt) {
 		capacity = qed_chain_get_capacity(&p_spq->chain);
 		dma_free_coherent(&p_hwfn->cdev->pdev->dev,
-- 
cgit v1.2.3


From b78d5400bda4e7c49ffdb001df83e4ffcb93d63b Mon Sep 17 00:00:00 2001
From: Ariel Elior <Ariel.Elior@cavium.com>
Date: Wed, 28 Nov 2018 18:16:05 +0200
Subject: qed: Register light L2 queues with doorbell overflow recovery
 mechanism

Light L2 queues are doorbelling entities. Modify the implementation
to keep the doorbell data necessary for doorbelling in well known
location instead of recomputing every time. Register the LL2 queue
with doorbell recovery mechanism.

Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Tomer Tayar <Tomer.Tayar@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_ll2.c | 30 ++++++++++++++++++++----------
 drivers/net/ethernet/qlogic/qed/qed_ll2.h |  1 +
 2 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index aa633381aa47..504c8f71b61d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -1085,7 +1085,14 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 
 	p_ramrod->gsi_offload_flag = p_ll2_conn->input.gsi_enable;
 
-	return qed_spq_post(p_hwfn, p_ent, NULL);
+	rc = qed_spq_post(p_hwfn, p_ent, NULL);
+	if (rc)
+		return rc;
+
+	rc = qed_db_recovery_add(p_hwfn->cdev, p_tx->doorbell_addr,
+				 &p_tx->db_msg, DB_REC_WIDTH_32B,
+				 DB_REC_KERNEL);
+	return rc;
 }
 
 static int qed_sp_ll2_rx_queue_stop(struct qed_hwfn *p_hwfn,
@@ -1119,9 +1126,11 @@ static int qed_sp_ll2_rx_queue_stop(struct qed_hwfn *p_hwfn,
 static int qed_sp_ll2_tx_queue_stop(struct qed_hwfn *p_hwfn,
 				    struct qed_ll2_info *p_ll2_conn)
 {
+	struct qed_ll2_tx_queue *p_tx = &p_ll2_conn->tx_queue;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
 	int rc = -EINVAL;
+	qed_db_recovery_del(p_hwfn->cdev, p_tx->doorbell_addr, &p_tx->db_msg);
 
 	/* Get SPQ entry */
 	memset(&init_data, 0, sizeof(init_data));
@@ -1542,6 +1551,13 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle)
 	p_tx->doorbell_addr = (u8 __iomem *)p_hwfn->doorbells +
 					    qed_db_addr(p_ll2_conn->cid,
 							DQ_DEMS_LEGACY);
+	/* prepare db data */
+	SET_FIELD(p_tx->db_msg.params, CORE_DB_DATA_DEST, DB_DEST_XCM);
+	SET_FIELD(p_tx->db_msg.params, CORE_DB_DATA_AGG_CMD, DB_AGG_CMD_SET);
+	SET_FIELD(p_tx->db_msg.params, CORE_DB_DATA_AGG_VAL_SEL,
+		  DQ_XCM_CORE_TX_BD_PROD_CMD);
+	p_tx->db_msg.agg_flags = DQ_XCM_CORE_DQ_CF_CMD;
+
 
 	rc = qed_ll2_establish_connection_rx(p_hwfn, p_ll2_conn);
 	if (rc)
@@ -1780,7 +1796,6 @@ static void qed_ll2_tx_packet_notify(struct qed_hwfn *p_hwfn,
 	bool b_notify = p_ll2_conn->tx_queue.cur_send_packet->notify_fw;
 	struct qed_ll2_tx_queue *p_tx = &p_ll2_conn->tx_queue;
 	struct qed_ll2_tx_packet *p_pkt = NULL;
-	struct core_db_data db_msg = { 0, 0, 0 };
 	u16 bd_prod;
 
 	/* If there are missing BDs, don't do anything now */
@@ -1809,24 +1824,19 @@ static void qed_ll2_tx_packet_notify(struct qed_hwfn *p_hwfn,
 		list_move_tail(&p_pkt->list_entry, &p_tx->active_descq);
 	}
 
-	SET_FIELD(db_msg.params, CORE_DB_DATA_DEST, DB_DEST_XCM);
-	SET_FIELD(db_msg.params, CORE_DB_DATA_AGG_CMD, DB_AGG_CMD_SET);
-	SET_FIELD(db_msg.params, CORE_DB_DATA_AGG_VAL_SEL,
-		  DQ_XCM_CORE_TX_BD_PROD_CMD);
-	db_msg.agg_flags = DQ_XCM_CORE_DQ_CF_CMD;
-	db_msg.spq_prod = cpu_to_le16(bd_prod);
+	p_tx->db_msg.spq_prod = cpu_to_le16(bd_prod);
 
 	/* Make sure the BDs data is updated before ringing the doorbell */
 	wmb();
 
-	DIRECT_REG_WR(p_tx->doorbell_addr, *((u32 *)&db_msg));
+	DIRECT_REG_WR(p_tx->doorbell_addr, *((u32 *)&p_tx->db_msg));
 
 	DP_VERBOSE(p_hwfn,
 		   (NETIF_MSG_TX_QUEUED | QED_MSG_LL2),
 		   "LL2 [q 0x%02x cid 0x%08x type 0x%08x] Doorbelled [producer 0x%04x]\n",
 		   p_ll2_conn->queue_id,
 		   p_ll2_conn->cid,
-		   p_ll2_conn->input.conn_type, db_msg.spq_prod);
+		   p_ll2_conn->input.conn_type, p_tx->db_msg.spq_prod);
 }
 
 int qed_ll2_prepare_tx_packet(void *cxt,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
index 1a5c1ae01474..5f01fbd3c073 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
@@ -103,6 +103,7 @@ struct qed_ll2_tx_queue {
 	struct qed_ll2_tx_packet cur_completing_packet;
 	u16 cur_completing_bd_idx;
 	void __iomem *doorbell_addr;
+	struct core_db_data db_msg;
 	u16 bds_idx;
 	u16 cur_send_frag_num;
 	u16 cur_completing_frag_num;
-- 
cgit v1.2.3


From 0e1f10447e2aa79ba7d8960e5d0ed3cf2ea8356e Mon Sep 17 00:00:00 2001
From: Ariel Elior <Ariel.Elior@cavium.com>
Date: Wed, 28 Nov 2018 18:16:06 +0200
Subject: qed: Expose the doorbell overflow recovery mechanism to the protocol
 drivers

Most of the doorbelling entities are outside of the core module.
L2 queues, Roce queues, iscsi and fcoe all need to register.
Make the APIs available for these drivers.

Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Tomer Tayar <Tomer.Tayar@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_main.c |  2 ++
 include/linux/qed/qed_if.h                 | 27 +++++++++++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 5ec3f5d1d6b2..6adf5bda9811 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -2384,6 +2384,8 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.update_mac = &qed_update_mac,
 	.update_mtu = &qed_update_mtu,
 	.update_wol = &qed_update_wol,
+	.db_recovery_add = &qed_db_recovery_add,
+	.db_recovery_del = &qed_db_recovery_del,
 	.read_module_eeprom = &qed_read_module_eeprom,
 };
 
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index eb851f89f417..91c536a01b56 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -1029,6 +1029,33 @@ struct qed_common_ops {
  */
 	int (*set_led)(struct qed_dev *cdev,
 		       enum qed_led_mode mode);
+/**
+ * @brief db_recovery_add - add doorbell information to the doorbell
+ * recovery mechanism.
+ *
+ * @param cdev
+ * @param db_addr - doorbell address
+ * @param db_data - address of where db_data is stored
+ * @param db_is_32b - doorbell is 32b pr 64b
+ * @param db_is_user - doorbell recovery addresses are user or kernel space
+ */
+	int (*db_recovery_add)(struct qed_dev *cdev,
+			       void __iomem *db_addr,
+			       void *db_data,
+			       enum qed_db_rec_width db_width,
+			       enum qed_db_rec_space db_space);
+
+/**
+ * @brief db_recovery_del - remove doorbell information from the doorbell
+ * recovery mechanism. db_data serves as key (db_addr is not unique).
+ *
+ * @param cdev
+ * @param db_addr - doorbell address
+ * @param db_data - address where db_data is stored. Serves as key for the
+ *		    entry to delete.
+ */
+	int (*db_recovery_del)(struct qed_dev *cdev,
+			       void __iomem *db_addr, void *db_data);
 
 /**
  * @brief update_drv_state - API to inform the change in the driver state.
-- 
cgit v1.2.3


From bd4db888ab848ac6f9a2a5f8e66bd4d5a99dce6f Mon Sep 17 00:00:00 2001
From: Ariel Elior <Ariel.Elior@cavium.com>
Date: Wed, 28 Nov 2018 18:16:07 +0200
Subject: qede: Register l2 queues with doorbell overflow recovery mechanism

All L2 queues funnel through this flow, so this would cover the
regular RSS queues, as well queues created for VFs, mqos queues,
xdp queues, etc.

Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Tomer Tayar <Tomer.Tayar@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index efbb4f3f0f4b..5a74fcbdbc2b 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1774,6 +1774,10 @@ static int qede_drain_txq(struct qede_dev *edev,
 static int qede_stop_txq(struct qede_dev *edev,
 			 struct qede_tx_queue *txq, int rss_id)
 {
+	/* delete doorbell from doorbell recovery mechanism */
+	edev->ops->common->db_recovery_del(edev->cdev, txq->doorbell_addr,
+					   &txq->tx_db);
+
 	return edev->ops->q_tx_stop(edev->cdev, rss_id, txq->handle);
 }
 
@@ -1910,6 +1914,11 @@ static int qede_start_txq(struct qede_dev *edev,
 		  DQ_XCM_ETH_TX_BD_PROD_CMD);
 	txq->tx_db.data.agg_flags = DQ_XCM_ETH_DQ_CF_CMD;
 
+	/* register doorbell with doorbell recovery mechanism */
+	rc = edev->ops->common->db_recovery_add(edev->cdev, txq->doorbell_addr,
+						&txq->tx_db, DB_REC_WIDTH_32B,
+						DB_REC_KERNEL);
+
 	return rc;
 }
 
-- 
cgit v1.2.3


From 327e5dab6dd8559ba28739ec8873350d7b5bb080 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 30 Nov 2018 16:25:44 +0000
Subject: tools: bpftool: use "/proc/self/" i.o. crafting links with getpid()

The getpid() function is called in a couple of places in bpftool to
craft links of the shape "/proc/<pid>/...". Instead, it is possible to
use the "/proc/self/" shortcut, which makes things a bit easier, in
particular in jit_disasm.c.

Do the replacement, and remove the includes of <sys/types.h> from the
relevant files, now we do not use getpid() anymore.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/common.c     |  5 ++---
 tools/bpf/bpftool/jit_disasm.c | 11 +----------
 2 files changed, 3 insertions(+), 13 deletions(-)

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 4e217d57118e..4349b6683ca8 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -48,7 +48,6 @@
 #include <sys/mount.h>
 #include <sys/resource.h>
 #include <sys/stat.h>
-#include <sys/types.h>
 #include <sys/vfs.h>
 
 #include <bpf.h>
@@ -276,7 +275,7 @@ int get_fd_type(int fd)
 	char buf[512];
 	ssize_t n;
 
-	snprintf(path, sizeof(path), "/proc/%d/fd/%d", getpid(), fd);
+	snprintf(path, sizeof(path), "/proc/self/fd/%d", fd);
 
 	n = readlink(path, buf, sizeof(buf));
 	if (n < 0) {
@@ -304,7 +303,7 @@ char *get_fdinfo(int fd, const char *key)
 	ssize_t n;
 	FILE *fdi;
 
-	snprintf(path, sizeof(path), "/proc/%d/fdinfo/%d", getpid(), fd);
+	snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", fd);
 
 	fdi = fopen(path, "r");
 	if (!fdi) {
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index b2ed5ee1af5f..545a92471c33 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -19,7 +19,6 @@
 #include <string.h>
 #include <bfd.h>
 #include <dis-asm.h>
-#include <sys/types.h>
 #include <sys/stat.h>
 #include <limits.h>
 
@@ -28,20 +27,12 @@
 
 static void get_exec_path(char *tpath, size_t size)
 {
+	const char *path = "/proc/self/exe";
 	ssize_t len;
-	char *path;
-
-	snprintf(tpath, size, "/proc/%d/exe", (int) getpid());
-	tpath[size - 1] = 0;
-
-	path = strdup(tpath);
-	assert(path);
 
 	len = readlink(path, tpath, size - 1);
 	assert(len > 0);
 	tpath[len] = 0;
-
-	free(path);
 }
 
 static int oper_count;
-- 
cgit v1.2.3


From cad4977344b35ea116ec5fefe91a76b1dfa113f5 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 30 Nov 2018 16:25:45 +0000
Subject: tools: bpftool: fix bash completion for bpftool prog (attach|detach)

Fix bash completion for "bpftool prog (attach|detach) PROG TYPE MAP" so
that the list of indices proposed for MAP are map indices, and not PROG
indices. Also use variables for map and prog reference types ("id",
"pinned", and "tag" for programs).

Fixes: b7d3826c2ed6 ("bpf: bpftool, add support for attaching programs to maps")
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/bash-completion/bpftool | 73 +++++++++++++++++++++----------
 1 file changed, 49 insertions(+), 24 deletions(-)

diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 45c2db257d2b..b7e6c4f25ad1 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -243,16 +243,20 @@ _bpftool()
     # Completion depends on object and command in use
     case $object in
         prog)
-            if [[ $command != "load" && $command != "loadall" ]]; then
-                case $prev in
-                    id)
-                        _bpftool_get_prog_ids
-                        return 0
-                        ;;
-                esac
-            fi
+            # Complete id, only for subcommands that use prog (but no map) ids
+            case $command in
+                show|list|dump|pin)
+                    case $prev in
+                        id)
+                            _bpftool_get_prog_ids
+                            return 0
+                            ;;
+                    esac
+                    ;;
+            esac
 
             local PROG_TYPE='id pinned tag'
+            local MAP_TYPE='id pinned'
             case $command in
                 show|list)
                     [[ $prev != "$command" ]] && return 0
@@ -293,22 +297,43 @@ _bpftool()
                     return 0
                     ;;
                 attach|detach)
-                    if [[ ${#words[@]} == 7 ]]; then
-                        COMPREPLY=( $( compgen -W "id pinned" -- "$cur" ) )
-                        return 0
-                    fi
-
-                    if [[ ${#words[@]} == 6 ]]; then
-                        COMPREPLY=( $( compgen -W "msg_verdict skb_verdict \
-                            skb_parse flow_dissector" -- "$cur" ) )
-                        return 0
-                    fi
-
-                    if [[ $prev == "$command" ]]; then
-                        COMPREPLY=( $( compgen -W "id pinned" -- "$cur" ) )
-                        return 0
-                    fi
-                    return 0
+                    case $cword in
+                        3)
+                            COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        4)
+                            case $prev in
+                                id)
+                                    _bpftool_get_prog_ids
+                                    ;;
+                                pinned)
+                                    _filedir
+                                    ;;
+                            esac
+                            return 0
+                            ;;
+                        5)
+                            COMPREPLY=( $( compgen -W 'msg_verdict skb_verdict \
+                                skb_parse flow_dissector' -- "$cur" ) )
+                            return 0
+                            ;;
+                        6)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        7)
+                            case $prev in
+                                id)
+                                    _bpftool_get_map_ids
+                                    ;;
+                                pinned)
+                                    _filedir
+                                    ;;
+                            esac
+                            return 0
+                            ;;
+                    esac
                     ;;
                 load|loadall)
                     local obj
-- 
cgit v1.2.3


From 4f0fc6f571d29837bc09aa8c51591f330f17bbf0 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 30 Nov 2018 16:25:46 +0000
Subject: tools: bpftool: fix bash completion for new map types (queue and
 stack)

Commit 197c2dac74e4 ("bpf: Add BPF_MAP_TYPE_QUEUE and BPF_MAP_TYPE_STACK
to bpftool-map") added support for queue and stack eBPF map types in
bpftool map handling. Let's update the bash completion accordingly.

Fixes: 197c2dac74e4 ("bpf: Add BPF_MAP_TYPE_QUEUE and BPF_MAP_TYPE_STACK to bpftool-map")
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/bash-completion/bpftool | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index b7e6c4f25ad1..9a60080f085f 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -436,7 +436,7 @@ _bpftool()
                                 lru_percpu_hash lpm_trie array_of_maps \
                                 hash_of_maps devmap sockmap cpumap xskmap \
                                 sockhash cgroup_storage reuseport_sockarray \
-                                percpu_cgroup_storage' -- \
+                                percpu_cgroup_storage queue stack' -- \
                                                    "$cur" ) )
                             return 0
                             ;;
-- 
cgit v1.2.3


From 73f0b9db53836a68c40691fad1467ed44a3123e8 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 30 Nov 2018 16:25:47 +0000
Subject: tools: bpftool: mark offloaded programs more explicitly in plain
 output

In bpftool (plain) output for "bpftool prog show" or "bpftool map show",
an offloaded BPF object is simply denoted with "dev ifname", which is
not really explicit. Change it with something that clearly shows the
program is offloaded.

While at it also add an additional space, as done between other
information fields.

Example output, before:

    # bpftool prog show
    1337: xdp  tag a04f5eef06a7f555 dev foo
            loaded_at 2018-10-19T16:40:36+0100  uid 0
            xlated 16B  not jited  memlock 4096B

After:

    # bpftool prog show
    1337: xdp  tag a04f5eef06a7f555  offloaded_to foo
            loaded_at 2018-10-19T16:40:36+0100  uid 0
            xlated 16B  not jited  memlock 4096B

Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 4349b6683ca8..172d3761d9ab 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -604,7 +604,7 @@ void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode)
 	if (!ifindex)
 		return;
 
-	printf(" dev ");
+	printf("  offloaded_to ");
 	if (ifindex_to_name_ns(ifindex, ns_dev, ns_inode, name))
 		printf("%s", name);
 	else
-- 
cgit v1.2.3


From 99a44bef587082fbbaddf6aaa1e823ebbb629339 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 30 Nov 2018 16:25:48 +0000
Subject: tools: bpftool: add owner_prog_type and owner_jited to bpftool output

For prog array maps, the type of the owner program, and the JIT-ed state
of that program, are available from the file descriptor information
under /proc. Add them to "bpftool map show" output. Example output:

    # bpftool map show
    158225: prog_array  name jmp_table  flags 0x0
        key 4B  value 4B  max_entries 8  memlock 4096B
        owner_prog_type flow_dissector  owner jited
    # bpftool --json --pretty map show
    [{
            "id": 1337,
            "type": "prog_array",
            "name": "jmp_table",
            "flags": 0,
            "bytes_key": 4,
            "bytes_value": 4,
            "max_entries": 8,
            "bytes_memlock": 4096,
            "owner_prog_type": "flow_dissector",
            "owner_jited": true
        }
    ]

As we move the table used for associating names to program types,
complete it with the missing types (lwt_seg6local and sk_reuseport).
Also add missing types to the help message for "bpftool prog"
(sk_reuseport and flow_dissector).

Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/main.h | 26 +++++++++++++++++++++++++
 tools/bpf/bpftool/map.c  | 50 ++++++++++++++++++++++++++++++++++++++++++++++--
 tools/bpf/bpftool/prog.c | 25 +-----------------------
 3 files changed, 75 insertions(+), 26 deletions(-)

diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 7431669fae0a..2761981669c8 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -78,6 +78,32 @@
 #define HELP_SPEC_MAP							\
 	"MAP := { id MAP_ID | pinned FILE }"
 
+static const char * const prog_type_name[] = {
+	[BPF_PROG_TYPE_UNSPEC]			= "unspec",
+	[BPF_PROG_TYPE_SOCKET_FILTER]		= "socket_filter",
+	[BPF_PROG_TYPE_KPROBE]			= "kprobe",
+	[BPF_PROG_TYPE_SCHED_CLS]		= "sched_cls",
+	[BPF_PROG_TYPE_SCHED_ACT]		= "sched_act",
+	[BPF_PROG_TYPE_TRACEPOINT]		= "tracepoint",
+	[BPF_PROG_TYPE_XDP]			= "xdp",
+	[BPF_PROG_TYPE_PERF_EVENT]		= "perf_event",
+	[BPF_PROG_TYPE_CGROUP_SKB]		= "cgroup_skb",
+	[BPF_PROG_TYPE_CGROUP_SOCK]		= "cgroup_sock",
+	[BPF_PROG_TYPE_LWT_IN]			= "lwt_in",
+	[BPF_PROG_TYPE_LWT_OUT]			= "lwt_out",
+	[BPF_PROG_TYPE_LWT_XMIT]		= "lwt_xmit",
+	[BPF_PROG_TYPE_SOCK_OPS]		= "sock_ops",
+	[BPF_PROG_TYPE_SK_SKB]			= "sk_skb",
+	[BPF_PROG_TYPE_CGROUP_DEVICE]		= "cgroup_device",
+	[BPF_PROG_TYPE_SK_MSG]			= "sk_msg",
+	[BPF_PROG_TYPE_RAW_TRACEPOINT]		= "raw_tracepoint",
+	[BPF_PROG_TYPE_CGROUP_SOCK_ADDR]	= "cgroup_sock_addr",
+	[BPF_PROG_TYPE_LWT_SEG6LOCAL]		= "lwt_seg6local",
+	[BPF_PROG_TYPE_LIRC_MODE2]		= "lirc_mode2",
+	[BPF_PROG_TYPE_SK_REUSEPORT]		= "sk_reuseport",
+	[BPF_PROG_TYPE_FLOW_DISSECTOR]		= "flow_dissector",
+};
+
 enum bpf_obj_type {
 	BPF_OBJ_UNKNOWN,
 	BPF_OBJ_PROG,
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 3850f8d65703..8469ea6cf1c8 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -487,7 +487,6 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
 	char *memlock;
 
 	memlock = get_fdinfo(fd, "memlock");
-	close(fd);
 
 	jsonw_start_object(json_wtr);
 
@@ -514,6 +513,30 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
 		jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
 	free(memlock);
 
+	if (info->type == BPF_MAP_TYPE_PROG_ARRAY) {
+		char *owner_prog_type = get_fdinfo(fd, "owner_prog_type");
+		char *owner_jited = get_fdinfo(fd, "owner_jited");
+
+		if (owner_prog_type) {
+			unsigned int prog_type = atoi(owner_prog_type);
+
+			if (prog_type < ARRAY_SIZE(prog_type_name))
+				jsonw_string_field(json_wtr, "owner_prog_type",
+						   prog_type_name[prog_type]);
+			else
+				jsonw_uint_field(json_wtr, "owner_prog_type",
+						 prog_type);
+		}
+		if (atoi(owner_jited))
+			jsonw_bool_field(json_wtr, "owner_jited", true);
+		else
+			jsonw_bool_field(json_wtr, "owner_jited", false);
+
+		free(owner_prog_type);
+		free(owner_jited);
+	}
+	close(fd);
+
 	if (!hash_empty(map_table.table)) {
 		struct pinned_obj *obj;
 
@@ -536,7 +559,6 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
 	char *memlock;
 
 	memlock = get_fdinfo(fd, "memlock");
-	close(fd);
 
 	printf("%u: ", info->id);
 	if (info->type < ARRAY_SIZE(map_type_name))
@@ -557,6 +579,30 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
 		printf("  memlock %sB", memlock);
 	free(memlock);
 
+	if (info->type == BPF_MAP_TYPE_PROG_ARRAY) {
+		char *owner_prog_type = get_fdinfo(fd, "owner_prog_type");
+		char *owner_jited = get_fdinfo(fd, "owner_jited");
+
+		printf("\n\t");
+		if (owner_prog_type) {
+			unsigned int prog_type = atoi(owner_prog_type);
+
+			if (prog_type < ARRAY_SIZE(prog_type_name))
+				printf("owner_prog_type %s  ",
+				       prog_type_name[prog_type]);
+			else
+				printf("owner_prog_type %d  ", prog_type);
+		}
+		if (atoi(owner_jited))
+			printf("owner jited");
+		else
+			printf("owner not jited");
+
+		free(owner_prog_type);
+		free(owner_jited);
+	}
+	close(fd);
+
 	printf("\n");
 	if (!hash_empty(map_table.table)) {
 		struct pinned_obj *obj;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 4e04699a2350..56db61c5a91f 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -54,30 +54,6 @@
 #include "main.h"
 #include "xlated_dumper.h"
 
-static const char * const prog_type_name[] = {
-	[BPF_PROG_TYPE_UNSPEC]		= "unspec",
-	[BPF_PROG_TYPE_SOCKET_FILTER]	= "socket_filter",
-	[BPF_PROG_TYPE_KPROBE]		= "kprobe",
-	[BPF_PROG_TYPE_SCHED_CLS]	= "sched_cls",
-	[BPF_PROG_TYPE_SCHED_ACT]	= "sched_act",
-	[BPF_PROG_TYPE_TRACEPOINT]	= "tracepoint",
-	[BPF_PROG_TYPE_XDP]		= "xdp",
-	[BPF_PROG_TYPE_PERF_EVENT]	= "perf_event",
-	[BPF_PROG_TYPE_CGROUP_SKB]	= "cgroup_skb",
-	[BPF_PROG_TYPE_CGROUP_SOCK]	= "cgroup_sock",
-	[BPF_PROG_TYPE_LWT_IN]		= "lwt_in",
-	[BPF_PROG_TYPE_LWT_OUT]		= "lwt_out",
-	[BPF_PROG_TYPE_LWT_XMIT]	= "lwt_xmit",
-	[BPF_PROG_TYPE_SOCK_OPS]	= "sock_ops",
-	[BPF_PROG_TYPE_SK_SKB]		= "sk_skb",
-	[BPF_PROG_TYPE_CGROUP_DEVICE]	= "cgroup_device",
-	[BPF_PROG_TYPE_SK_MSG]		= "sk_msg",
-	[BPF_PROG_TYPE_RAW_TRACEPOINT]	= "raw_tracepoint",
-	[BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr",
-	[BPF_PROG_TYPE_LIRC_MODE2]	= "lirc_mode2",
-	[BPF_PROG_TYPE_FLOW_DISSECTOR]	= "flow_dissector",
-};
-
 static const char * const attach_type_strings[] = {
 	[BPF_SK_SKB_STREAM_PARSER] = "stream_parser",
 	[BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict",
@@ -1172,6 +1148,7 @@ static int do_help(int argc, char **argv)
 		"                 tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n"
 		"                 cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n"
 		"                 lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n"
+		"                 sk_reuseport | flow_dissector |\n"
 		"                 cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
 		"                 cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
 		"                 cgroup/sendmsg4 | cgroup/sendmsg6 }\n"
-- 
cgit v1.2.3


From 5a6db04ca8d44c873d6dd6bc3d2328aaa4c86a87 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 28 Nov 2018 20:06:58 +0000
Subject: net: bridge: Extend br_vlan_get_pvid() for bridge ports

Currently, the function only works for the bridge device itself, but
subsequent patches will need to be able to query the PVID of a given
bridge port, so extend the function.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index b21838b51220..48f50d7ac624 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -1217,9 +1217,13 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v,
 int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
 {
 	struct net_bridge_vlan_group *vg;
+	struct net_bridge_port *p;
 
 	ASSERT_RTNL();
-	if (netif_is_bridge_master(dev))
+	p = br_port_get_check_rtnl(dev);
+	if (p)
+		vg = nbp_vlan_group(p);
+	else if (netif_is_bridge_master(dev))
 		vg = br_vlan_group(netdev_priv(dev));
 	else
 		return -EINVAL;
-- 
cgit v1.2.3


From 5a8fb370bef8222c497130fc9aa100fe5ca78308 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 28 Nov 2018 20:06:59 +0000
Subject: mlxsw: spectrum_fid: Add API to lookup 802.1Q FIDs without creating
 them

In a similar fashion to commit 564c6d727aca ("mlxsw: spectrum_fid: Add
APIs to lookup FID without creating it"), add a corresponding API to
lookup 802.1Q FIDs.

This is a prerequisite to VxLAN support with VLAN-aware bridges and will
allow us to resolve a 802.1Q FID by its VLAN when an FDB entry is added
on the bridge port of the VxLAN device.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           | 2 ++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c       | 6 ++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 5 +++--
 3 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 244972bf8b0a..55ed69038796 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -753,6 +753,8 @@ u16 mlxsw_sp_fid_8021q_vid(const struct mlxsw_sp_fid *fid);
 struct mlxsw_sp_fid *mlxsw_sp_fid_8021q_get(struct mlxsw_sp *mlxsw_sp, u16 vid);
 struct mlxsw_sp_fid *mlxsw_sp_fid_8021d_get(struct mlxsw_sp *mlxsw_sp,
 					    int br_ifindex);
+struct mlxsw_sp_fid *mlxsw_sp_fid_8021q_lookup(struct mlxsw_sp *mlxsw_sp,
+					       u16 vid);
 struct mlxsw_sp_fid *mlxsw_sp_fid_8021d_lookup(struct mlxsw_sp *mlxsw_sp,
 					       int br_ifindex);
 struct mlxsw_sp_fid *mlxsw_sp_fid_rfid_get(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index 6830e79aed93..f9af68230455 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -1068,6 +1068,12 @@ struct mlxsw_sp_fid *mlxsw_sp_fid_8021d_get(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_sp_fid_get(mlxsw_sp, MLXSW_SP_FID_TYPE_8021D, &br_ifindex);
 }
 
+struct mlxsw_sp_fid *mlxsw_sp_fid_8021q_lookup(struct mlxsw_sp *mlxsw_sp,
+					       u16 vid)
+{
+	return mlxsw_sp_fid_lookup(mlxsw_sp, MLXSW_SP_FID_TYPE_8021Q, &vid);
+}
+
 struct mlxsw_sp_fid *mlxsw_sp_fid_8021d_lookup(struct mlxsw_sp *mlxsw_sp,
 					       int br_ifindex)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 3c2428404b2e..108dbb764c77 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2031,8 +2031,9 @@ static struct mlxsw_sp_fid *
 mlxsw_sp_bridge_8021q_fid_lookup(struct mlxsw_sp_bridge_device *bridge_device,
 				 u16 vid)
 {
-	WARN_ON(1);
-	return NULL;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
+
+	return mlxsw_sp_fid_8021q_lookup(mlxsw_sp, vid);
 }
 
 static u16
-- 
cgit v1.2.3


From b03fa9e7e0cfe9ae5f3d294bbb60b5acd02dbfde Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 28 Nov 2018 20:07:01 +0000
Subject: mlxsw: spectrum_switchdev: Unify VxLAN leave function

The function mlxsw_sp_bridge_vxlan_leave() is currently split between
VLAN-aware and VLAN-unaware bridges, but actually both types can use the
same function.

The function needs to resolve the FID that corresponds to the VxLAN
device and disable NVE encapsulation on it. Instead of looking up the
FID differently for VLAN-aware and VLAN-unaware bridges, we can always
use the VxLAN's device VNI.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  4 +--
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  1 -
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 42 ++++------------------
 3 files changed, 9 insertions(+), 38 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 93378d507962..9cc063af6f7b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -5174,7 +5174,7 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 			return mlxsw_sp_bridge_vxlan_join(mlxsw_sp, upper_dev,
 							  dev, extack);
 		} else {
-			mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, upper_dev, dev);
+			mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, dev);
 		}
 		break;
 	case NETDEV_PRE_UP:
@@ -5195,7 +5195,7 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 			return 0;
 		if (!mlxsw_sp_lower_get(upper_dev))
 			return 0;
-		mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, upper_dev, dev);
+		mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, dev);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 55ed69038796..696c2360fbb4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -361,7 +361,6 @@ int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 			       const struct net_device *vxlan_dev,
 			       struct netlink_ext_ack *extack);
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-				 const struct net_device *br_dev,
 				 const struct net_device *vxlan_dev);
 
 /* spectrum.c */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 108dbb764c77..801c1af81916 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -87,8 +87,6 @@ struct mlxsw_sp_bridge_ops {
 	int (*vxlan_join)(struct mlxsw_sp_bridge_device *bridge_device,
 			  const struct net_device *vxlan_dev,
 			  struct netlink_ext_ack *extack);
-	void (*vxlan_leave)(struct mlxsw_sp_bridge_device *bridge_device,
-			    const struct net_device *vxlan_dev);
 	struct mlxsw_sp_fid *
 		(*fid_get)(struct mlxsw_sp_bridge_device *bridge_device,
 			   u16 vid);
@@ -2012,12 +2010,6 @@ mlxsw_sp_bridge_8021q_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device,
 	return -EINVAL;
 }
 
-static void
-mlxsw_sp_bridge_8021q_vxlan_leave(struct mlxsw_sp_bridge_device *bridge_device,
-				  const struct net_device *vxlan_dev)
-{
-}
-
 static struct mlxsw_sp_fid *
 mlxsw_sp_bridge_8021q_fid_get(struct mlxsw_sp_bridge_device *bridge_device,
 			      u16 vid)
@@ -2047,7 +2039,6 @@ static const struct mlxsw_sp_bridge_ops mlxsw_sp_bridge_8021q_ops = {
 	.port_join	= mlxsw_sp_bridge_8021q_port_join,
 	.port_leave	= mlxsw_sp_bridge_8021q_port_leave,
 	.vxlan_join	= mlxsw_sp_bridge_8021q_vxlan_join,
-	.vxlan_leave	= mlxsw_sp_bridge_8021q_vxlan_leave,
 	.fid_get	= mlxsw_sp_bridge_8021q_fid_get,
 	.fid_lookup	= mlxsw_sp_bridge_8021q_fid_lookup,
 	.fid_vid	= mlxsw_sp_bridge_8021q_fid_vid,
@@ -2152,26 +2143,6 @@ err_nve_fid_enable:
 	return err;
 }
 
-static void
-mlxsw_sp_bridge_8021d_vxlan_leave(struct mlxsw_sp_bridge_device *bridge_device,
-				  const struct net_device *vxlan_dev)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
-	struct mlxsw_sp_fid *fid;
-
-	fid = mlxsw_sp_fid_8021d_lookup(mlxsw_sp, bridge_device->dev->ifindex);
-	if (WARN_ON(!fid))
-		return;
-
-	/* If the VxLAN device is down, then the FID does not have a VNI */
-	if (!mlxsw_sp_fid_vni_is_set(fid))
-		goto out;
-
-	mlxsw_sp_nve_fid_disable(mlxsw_sp, fid);
-out:
-	mlxsw_sp_fid_put(fid);
-}
-
 static struct mlxsw_sp_fid *
 mlxsw_sp_bridge_8021d_fid_get(struct mlxsw_sp_bridge_device *bridge_device,
 			      u16 vid)
@@ -2230,7 +2201,6 @@ static const struct mlxsw_sp_bridge_ops mlxsw_sp_bridge_8021d_ops = {
 	.port_join	= mlxsw_sp_bridge_8021d_port_join,
 	.port_leave	= mlxsw_sp_bridge_8021d_port_leave,
 	.vxlan_join	= mlxsw_sp_bridge_8021d_vxlan_join,
-	.vxlan_leave	= mlxsw_sp_bridge_8021d_vxlan_leave,
 	.fid_get	= mlxsw_sp_bridge_8021d_fid_get,
 	.fid_lookup	= mlxsw_sp_bridge_8021d_fid_lookup,
 	.fid_vid	= mlxsw_sp_bridge_8021d_fid_vid,
@@ -2298,16 +2268,18 @@ int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 }
 
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-				 const struct net_device *br_dev,
 				 const struct net_device *vxlan_dev)
 {
-	struct mlxsw_sp_bridge_device *bridge_device;
+	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
+	struct mlxsw_sp_fid *fid;
 
-	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
-	if (WARN_ON(!bridge_device))
+	/* If the VxLAN device is down, then the FID does not have a VNI */
+	fid = mlxsw_sp_fid_lookup_by_vni(mlxsw_sp, vxlan->cfg.vni);
+	if (!fid)
 		return;
 
-	bridge_device->ops->vxlan_leave(bridge_device, vxlan_dev);
+	mlxsw_sp_nve_fid_disable(mlxsw_sp, fid);
+	mlxsw_sp_fid_put(fid);
 }
 
 static void
-- 
cgit v1.2.3


From 48fde4660654d5bbaa09c2a38fa9ca7c72f1a95e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 28 Nov 2018 20:07:02 +0000
Subject: mlxsw: spectrum_switchdev: Prepare function for VLAN-aware bridges

The vxlan_join() function resolves the FID on which the VNI should be
set and then sets the VNI. Currently, the FID is simply resolved
according to the ifindex of the bridge device to which the VxLAN device
is enslaved. This works because only VLAN-unaware bridges are supported.

With VLAN-aware bridges the FID would need to be resolved based on the
VLAN to which the VNI is mapped to.

Add the VLAN ID to the argument list of the function.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c           |  4 ++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 14 ++++++++------
 3 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 9cc063af6f7b..d215e3270376 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -5172,7 +5172,7 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 			if (!netif_running(dev))
 				return 0;
 			return mlxsw_sp_bridge_vxlan_join(mlxsw_sp, upper_dev,
-							  dev, extack);
+							  dev, 0, extack);
 		} else {
 			mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, dev);
 		}
@@ -5185,7 +5185,7 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 			return 0;
 		if (!mlxsw_sp_lower_get(upper_dev))
 			return 0;
-		return mlxsw_sp_bridge_vxlan_join(mlxsw_sp, upper_dev, dev,
+		return mlxsw_sp_bridge_vxlan_join(mlxsw_sp, upper_dev, dev, 0,
 						  extack);
 	case NETDEV_DOWN:
 		upper_dev = netdev_master_upper_dev_get(dev);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 696c2360fbb4..0361d0d1b1e2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -358,7 +358,7 @@ bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp,
 					 const struct net_device *br_dev);
 int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 			       const struct net_device *br_dev,
-			       const struct net_device *vxlan_dev,
+			       const struct net_device *vxlan_dev, u16 vid,
 			       struct netlink_ext_ack *extack);
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 				 const struct net_device *vxlan_dev);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 801c1af81916..30c861129c8d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -85,7 +85,7 @@ struct mlxsw_sp_bridge_ops {
 			   struct mlxsw_sp_bridge_port *bridge_port,
 			   struct mlxsw_sp_port *mlxsw_sp_port);
 	int (*vxlan_join)(struct mlxsw_sp_bridge_device *bridge_device,
-			  const struct net_device *vxlan_dev,
+			  const struct net_device *vxlan_dev, u16 vid,
 			  struct netlink_ext_ack *extack);
 	struct mlxsw_sp_fid *
 		(*fid_get)(struct mlxsw_sp_bridge_device *bridge_device,
@@ -2003,7 +2003,7 @@ mlxsw_sp_bridge_8021q_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
 
 static int
 mlxsw_sp_bridge_8021q_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device,
-				 const struct net_device *vxlan_dev,
+				 const struct net_device *vxlan_dev, u16 vid,
 				 struct netlink_ext_ack *extack)
 {
 	WARN_ON(1);
@@ -2107,7 +2107,7 @@ mlxsw_sp_bridge_8021d_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
 
 static int
 mlxsw_sp_bridge_8021d_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device,
-				 const struct net_device *vxlan_dev,
+				 const struct net_device *vxlan_dev, u16 vid,
 				 struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
@@ -2166,7 +2166,8 @@ mlxsw_sp_bridge_8021d_fid_get(struct mlxsw_sp_bridge_device *bridge_device,
 	if (!netif_running(vxlan_dev))
 		return fid;
 
-	err = mlxsw_sp_bridge_8021d_vxlan_join(bridge_device, vxlan_dev, NULL);
+	err = mlxsw_sp_bridge_8021d_vxlan_join(bridge_device, vxlan_dev, 0,
+					       NULL);
 	if (err)
 		goto err_vxlan_join;
 
@@ -2255,7 +2256,7 @@ void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 
 int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 			       const struct net_device *br_dev,
-			       const struct net_device *vxlan_dev,
+			       const struct net_device *vxlan_dev, u16 vid,
 			       struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_bridge_device *bridge_device;
@@ -2264,7 +2265,8 @@ int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 	if (WARN_ON(!bridge_device))
 		return -EINVAL;
 
-	return bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, extack);
+	return bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, vid,
+					      extack);
 }
 
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-- 
cgit v1.2.3


From d70e42b22dd40a56ee44f451fb5a661ab88e4691 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 28 Nov 2018 20:07:04 +0000
Subject: mlxsw: spectrum: Enable VxLAN enslavement to VLAN-aware bridges

Commit 1c30d1836aeb ("mlxsw: spectrum: Enable VxLAN enslavement to
bridges") enabled the enslavement of VxLAN devices to bridges that have
mlxsw ports (or their upper) as slaves. This patch extends mlxsw to also
support VLAN-aware bridges.

The patch is similar in nature to mentioned commit, but there is one
major difference. With VLAN-aware bridges, the VxLAN device's VNI is
mapped to the VLAN that is configured as PVID and egress untagged on the
bridge port.

Therefore, the driver is extended to listen to VLAN configuration on
VxLAN devices of interest and enable / disable NVE encapsulation on the
corresponding 802.1Q FIDs.

To prevent ambiguity, the driver makes sure that a given VLAN is not
configured as PVID and egress untagged on multiple VxLAN devices. This
sanitization takes place both when a port is enslaved to a bridge with
existing VxLAN devices and when a VLAN is added to / removed from a
VxLAN device of interest.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  45 ++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  21 ++
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 352 ++++++++++++++++++++-
 3 files changed, 404 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index d215e3270376..3b3b59314125 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4782,6 +4782,30 @@ static bool mlxsw_sp_bridge_has_multiple_vxlans(struct net_device *br_dev)
 	return num_vxlans > 1;
 }
 
+static bool mlxsw_sp_bridge_vxlan_vlan_is_valid(struct net_device *br_dev)
+{
+	DECLARE_BITMAP(vlans, VLAN_N_VID) = {0};
+	struct net_device *dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(br_dev, dev, iter) {
+		u16 pvid;
+		int err;
+
+		if (!netif_is_vxlan(dev))
+			continue;
+
+		err = mlxsw_sp_vxlan_mapped_vid(dev, &pvid);
+		if (err || !pvid)
+			continue;
+
+		if (test_and_set_bit(pvid, vlans))
+			return false;
+	}
+
+	return true;
+}
+
 static bool mlxsw_sp_bridge_vxlan_is_valid(struct net_device *br_dev,
 					   struct netlink_ext_ack *extack)
 {
@@ -4790,13 +4814,15 @@ static bool mlxsw_sp_bridge_vxlan_is_valid(struct net_device *br_dev,
 		return false;
 	}
 
-	if (br_vlan_enabled(br_dev)) {
-		NL_SET_ERR_MSG_MOD(extack, "VLAN filtering can not be enabled on a bridge with a VxLAN device");
+	if (!br_vlan_enabled(br_dev) &&
+	    mlxsw_sp_bridge_has_multiple_vxlans(br_dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Multiple VxLAN devices are not supported in a VLAN-unaware bridge");
 		return false;
 	}
 
-	if (mlxsw_sp_bridge_has_multiple_vxlans(br_dev)) {
-		NL_SET_ERR_MSG_MOD(extack, "Multiple VxLAN devices are not supported in a VLAN-unaware bridge");
+	if (br_vlan_enabled(br_dev) &&
+	    !mlxsw_sp_bridge_vxlan_vlan_is_valid(br_dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Multiple VxLAN devices cannot have the same VLAN as PVID and egress untagged");
 		return false;
 	}
 
@@ -5171,9 +5197,20 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 		if (cu_info->linking) {
 			if (!netif_running(dev))
 				return 0;
+			/* When the bridge is VLAN-aware, the VNI of the VxLAN
+			 * device needs to be mapped to a VLAN, but at this
+			 * point no VLANs are configured on the VxLAN device
+			 */
+			if (br_vlan_enabled(upper_dev))
+				return 0;
 			return mlxsw_sp_bridge_vxlan_join(mlxsw_sp, upper_dev,
 							  dev, 0, extack);
 		} else {
+			/* VLANs were already flushed, which triggered the
+			 * necessary cleanup
+			 */
+			if (br_vlan_enabled(upper_dev))
+				return 0;
 			mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, dev);
 		}
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 0361d0d1b1e2..a3e564e0da39 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -8,6 +8,7 @@
 #include <linux/netdevice.h>
 #include <linux/rhashtable.h>
 #include <linux/bitops.h>
+#include <linux/if_bridge.h>
 #include <linux/if_vlan.h>
 #include <linux/list.h>
 #include <linux/dcbnl.h>
@@ -261,6 +262,26 @@ static inline bool mlxsw_sp_bridge_has_vxlan(struct net_device *br_dev)
 	return !!mlxsw_sp_bridge_vxlan_dev_find(br_dev);
 }
 
+static inline int
+mlxsw_sp_vxlan_mapped_vid(const struct net_device *vxlan_dev, u16 *p_vid)
+{
+	struct bridge_vlan_info vinfo;
+	u16 vid = 0;
+	int err;
+
+	err = br_vlan_get_pvid(vxlan_dev, &vid);
+	if (err || !vid)
+		goto out;
+
+	err = br_vlan_get_info(vxlan_dev, vid, &vinfo);
+	if (err || !(vinfo.flags & BRIDGE_VLAN_INFO_UNTAGGED))
+		vid = 0;
+
+out:
+	*p_vid = vid;
+	return err;
+}
+
 static inline bool
 mlxsw_sp_port_is_pause_en(const struct mlxsw_sp_port *mlxsw_sp_port)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 30c861129c8d..7c38231bbd89 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2006,8 +2006,76 @@ mlxsw_sp_bridge_8021q_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device,
 				 const struct net_device *vxlan_dev, u16 vid,
 				 struct netlink_ext_ack *extack)
 {
-	WARN_ON(1);
-	return -EINVAL;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
+	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
+	struct mlxsw_sp_nve_params params = {
+		.type = MLXSW_SP_NVE_TYPE_VXLAN,
+		.vni = vxlan->cfg.vni,
+		.dev = vxlan_dev,
+	};
+	struct mlxsw_sp_fid *fid;
+	int err;
+
+	/* If the VLAN is 0, we need to find the VLAN that is configured as
+	 * PVID and egress untagged on the bridge port of the VxLAN device.
+	 * It is possible no such VLAN exists
+	 */
+	if (!vid) {
+		err = mlxsw_sp_vxlan_mapped_vid(vxlan_dev, &vid);
+		if (err || !vid)
+			return err;
+	}
+
+	/* If no other port is member in the VLAN, then the FID does not exist.
+	 * NVE will be enabled on the FID once a port joins the VLAN
+	 */
+	fid = mlxsw_sp_fid_8021q_lookup(mlxsw_sp, vid);
+	if (!fid)
+		return 0;
+
+	if (mlxsw_sp_fid_vni_is_set(fid)) {
+		err = -EINVAL;
+		goto err_vni_exists;
+	}
+
+	err = mlxsw_sp_nve_fid_enable(mlxsw_sp, fid, &params, extack);
+	if (err)
+		goto err_nve_fid_enable;
+
+	/* The tunnel port does not hold a reference on the FID. Only
+	 * local ports and the router port
+	 */
+	mlxsw_sp_fid_put(fid);
+
+	return 0;
+
+err_nve_fid_enable:
+err_vni_exists:
+	mlxsw_sp_fid_put(fid);
+	return err;
+}
+
+static struct net_device *
+mlxsw_sp_bridge_8021q_vxlan_dev_find(struct net_device *br_dev, u16 vid)
+{
+	struct net_device *dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(br_dev, dev, iter) {
+		u16 pvid;
+		int err;
+
+		if (!netif_is_vxlan(dev))
+			continue;
+
+		err = mlxsw_sp_vxlan_mapped_vid(dev, &pvid);
+		if (err || pvid != vid)
+			continue;
+
+		return dev;
+	}
+
+	return NULL;
 }
 
 static struct mlxsw_sp_fid *
@@ -2015,8 +2083,38 @@ mlxsw_sp_bridge_8021q_fid_get(struct mlxsw_sp_bridge_device *bridge_device,
 			      u16 vid)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
+	struct net_device *vxlan_dev;
+	struct mlxsw_sp_fid *fid;
+	int err;
 
-	return mlxsw_sp_fid_8021q_get(mlxsw_sp, vid);
+	fid = mlxsw_sp_fid_8021q_get(mlxsw_sp, vid);
+	if (IS_ERR(fid))
+		return fid;
+
+	if (mlxsw_sp_fid_vni_is_set(fid))
+		return fid;
+
+	/* Find the VxLAN device that has the specified VLAN configured as
+	 * PVID and egress untagged. There can be at most one such device
+	 */
+	vxlan_dev = mlxsw_sp_bridge_8021q_vxlan_dev_find(bridge_device->dev,
+							 vid);
+	if (!vxlan_dev)
+		return fid;
+
+	if (!netif_running(vxlan_dev))
+		return fid;
+
+	err = mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, vxlan_dev, vid,
+					       NULL);
+	if (err)
+		goto err_vxlan_join;
+
+	return fid;
+
+err_vxlan_join:
+	mlxsw_sp_fid_put(fid);
+	return ERR_PTR(err);
 }
 
 static struct mlxsw_sp_fid *
@@ -3092,22 +3190,256 @@ static struct notifier_block mlxsw_sp_switchdev_notifier = {
 	.notifier_call = mlxsw_sp_switchdev_event,
 };
 
+static int
+mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_bridge_device *bridge_device,
+				  const struct net_device *vxlan_dev, u16 vid,
+				  bool flag_untagged, bool flag_pvid,
+				  struct switchdev_trans *trans)
+{
+	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
+	__be32 vni = vxlan->cfg.vni;
+	struct mlxsw_sp_fid *fid;
+	u16 old_vid;
+	int err;
+
+	/* We cannot have the same VLAN as PVID and egress untagged on multiple
+	 * VxLAN devices. Note that we get this notification before the VLAN is
+	 * actually added to the bridge's database, so it is not possible for
+	 * the lookup function to return 'vxlan_dev'
+	 */
+	if (flag_untagged && flag_pvid &&
+	    mlxsw_sp_bridge_8021q_vxlan_dev_find(bridge_device->dev, vid))
+		return -EINVAL;
+
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
+	if (!netif_running(vxlan_dev))
+		return 0;
+
+	/* First case: FID is not associated with this VNI, but the new VLAN
+	 * is both PVID and egress untagged. Need to enable NVE on the FID, if
+	 * it exists
+	 */
+	fid = mlxsw_sp_fid_lookup_by_vni(mlxsw_sp, vni);
+	if (!fid) {
+		if (!flag_untagged || !flag_pvid)
+			return 0;
+		return mlxsw_sp_bridge_8021q_vxlan_join(bridge_device,
+							vxlan_dev, vid, NULL);
+	}
+
+	/* Second case: FID is associated with the VNI and the VLAN associated
+	 * with the FID is the same as the notified VLAN. This means the flags
+	 * (PVID / egress untagged) were toggled and that NVE should be
+	 * disabled on the FID
+	 */
+	old_vid = mlxsw_sp_fid_8021q_vid(fid);
+	if (vid == old_vid) {
+		if (WARN_ON(flag_untagged && flag_pvid)) {
+			mlxsw_sp_fid_put(fid);
+			return -EINVAL;
+		}
+		mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+		mlxsw_sp_fid_put(fid);
+		return 0;
+	}
+
+	/* Third case: A new VLAN was configured on the VxLAN device, but this
+	 * VLAN is not PVID, so there is nothing to do.
+	 */
+	if (!flag_pvid) {
+		mlxsw_sp_fid_put(fid);
+		return 0;
+	}
+
+	/* Fourth case: Thew new VLAN is PVID, which means the VLAN currently
+	 * mapped to the VNI should be unmapped
+	 */
+	mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+	mlxsw_sp_fid_put(fid);
+
+	/* Fifth case: The new VLAN is also egress untagged, which means the
+	 * VLAN needs to be mapped to the VNI
+	 */
+	if (!flag_untagged)
+		return 0;
+
+	err = mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, vxlan_dev, vid,
+					       NULL);
+	if (err)
+		goto err_vxlan_join;
+
+	return 0;
+
+err_vxlan_join:
+	mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, vxlan_dev, old_vid,
+					 NULL);
+	return err;
+}
+
+static void
+mlxsw_sp_switchdev_vxlan_vlan_del(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_bridge_device *bridge_device,
+				  const struct net_device *vxlan_dev, u16 vid)
+{
+	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
+	__be32 vni = vxlan->cfg.vni;
+	struct mlxsw_sp_fid *fid;
+
+	if (!netif_running(vxlan_dev))
+		return;
+
+	fid = mlxsw_sp_fid_lookup_by_vni(mlxsw_sp, vni);
+	if (!fid)
+		return;
+
+	/* A different VLAN than the one mapped to the VNI is deleted */
+	if (mlxsw_sp_fid_8021q_vid(fid) != vid)
+		goto out;
+
+	mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+
+out:
+	mlxsw_sp_fid_put(fid);
+}
+
+static int
+mlxsw_sp_switchdev_vxlan_vlans_add(struct net_device *vxlan_dev,
+				   struct switchdev_notifier_port_obj_info *
+				   port_obj_info)
+{
+	struct switchdev_obj_port_vlan *vlan =
+		SWITCHDEV_OBJ_PORT_VLAN(port_obj_info->obj);
+	bool flag_untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool flag_pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+	struct switchdev_trans *trans = port_obj_info->trans;
+	struct mlxsw_sp_bridge_device *bridge_device;
+	struct mlxsw_sp *mlxsw_sp;
+	struct net_device *br_dev;
+	u16 vid;
+
+	br_dev = netdev_master_upper_dev_get(vxlan_dev);
+	if (!br_dev)
+		return 0;
+
+	mlxsw_sp = mlxsw_sp_lower_get(br_dev);
+	if (!mlxsw_sp)
+		return 0;
+
+	port_obj_info->handled = true;
+
+	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
+	if (!bridge_device)
+		return -EINVAL;
+
+	if (!bridge_device->vlan_enabled)
+		return 0;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		int err;
+
+		err = mlxsw_sp_switchdev_vxlan_vlan_add(mlxsw_sp, bridge_device,
+							vxlan_dev, vid,
+							flag_untagged,
+							flag_pvid, trans);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void
+mlxsw_sp_switchdev_vxlan_vlans_del(struct net_device *vxlan_dev,
+				   struct switchdev_notifier_port_obj_info *
+				   port_obj_info)
+{
+	struct switchdev_obj_port_vlan *vlan =
+		SWITCHDEV_OBJ_PORT_VLAN(port_obj_info->obj);
+	struct mlxsw_sp_bridge_device *bridge_device;
+	struct mlxsw_sp *mlxsw_sp;
+	struct net_device *br_dev;
+	u16 vid;
+
+	br_dev = netdev_master_upper_dev_get(vxlan_dev);
+	if (!br_dev)
+		return;
+
+	mlxsw_sp = mlxsw_sp_lower_get(br_dev);
+	if (!mlxsw_sp)
+		return;
+
+	port_obj_info->handled = true;
+
+	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
+	if (!bridge_device)
+		return;
+
+	if (!bridge_device->vlan_enabled)
+		return;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++)
+		mlxsw_sp_switchdev_vxlan_vlan_del(mlxsw_sp, bridge_device,
+						  vxlan_dev, vid);
+}
+
+static int
+mlxsw_sp_switchdev_handle_vxlan_obj_add(struct net_device *vxlan_dev,
+					struct switchdev_notifier_port_obj_info *
+					port_obj_info)
+{
+	int err = 0;
+
+	switch (port_obj_info->obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		err = mlxsw_sp_switchdev_vxlan_vlans_add(vxlan_dev,
+							 port_obj_info);
+		break;
+	default:
+		break;
+	}
+
+	return err;
+}
+
+static void
+mlxsw_sp_switchdev_handle_vxlan_obj_del(struct net_device *vxlan_dev,
+					struct switchdev_notifier_port_obj_info *
+					port_obj_info)
+{
+	switch (port_obj_info->obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		mlxsw_sp_switchdev_vxlan_vlans_del(vxlan_dev, port_obj_info);
+		break;
+	default:
+		break;
+	}
+}
+
 static int mlxsw_sp_switchdev_blocking_event(struct notifier_block *unused,
 					     unsigned long event, void *ptr)
 {
 	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
-	int err;
+	int err = 0;
 
 	switch (event) {
 	case SWITCHDEV_PORT_OBJ_ADD:
-		err = switchdev_handle_port_obj_add(dev, ptr,
-						    mlxsw_sp_port_dev_check,
-						    mlxsw_sp_port_obj_add);
+		if (netif_is_vxlan(dev))
+			err = mlxsw_sp_switchdev_handle_vxlan_obj_add(dev, ptr);
+		else
+			err = switchdev_handle_port_obj_add(dev, ptr,
+							mlxsw_sp_port_dev_check,
+							mlxsw_sp_port_obj_add);
 		return notifier_from_errno(err);
 	case SWITCHDEV_PORT_OBJ_DEL:
-		err = switchdev_handle_port_obj_del(dev, ptr,
-						    mlxsw_sp_port_dev_check,
-						    mlxsw_sp_port_obj_del);
+		if (netif_is_vxlan(dev))
+			mlxsw_sp_switchdev_handle_vxlan_obj_del(dev, ptr);
+		else
+			err = switchdev_handle_port_obj_del(dev, ptr,
+							mlxsw_sp_port_dev_check,
+							mlxsw_sp_port_obj_del);
 		return notifier_from_errno(err);
 	}
 
-- 
cgit v1.2.3


From bbe210615dc1fa7ec88516adb7dfccb47bccba21 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 28 Nov 2018 20:07:05 +0000
Subject: selftests: mlxsw: Consider VLAN-aware bridges as valid

Previous patches add the ability to work with VLAN-aware bridges and
VxLAN devices, so make sure such configuration no longer fails.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/vxlan.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
index ffa79b738f2a..d00d4665c807 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
@@ -81,7 +81,7 @@ sanitization_single_dev_vlan_aware_test()
 	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
 		ttl 20 tos inherit local 198.51.100.1 dstport 4789
 
-	sanitization_single_dev_test_fail
+	sanitization_single_dev_test_pass
 
 	ip link del dev vxlan0
 	ip link del dev br0
-- 
cgit v1.2.3


From f07232375d7f9384ec971d55343bf44ea1881fc4 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 28 Nov 2018 20:07:06 +0000
Subject: selftests: mlxsw: Add a test for VxLAN configuration with a
 VLAN-aware bridge

Extend the existing VLAN-unaware tests with their VLAN-aware
counterparts. This includes sanitization of invalid configuration and
offload indication on the local route performing decapsulation and the
FDB entries perform encapsulation.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/vxlan.sh | 204 ++++++++++++++++++++-
 1 file changed, 203 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
index d00d4665c807..90b4998a3b70 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
@@ -6,7 +6,8 @@
 
 lib_dir=$(dirname $0)/../../../net/forwarding
 
-ALL_TESTS="sanitization_test offload_indication_test"
+ALL_TESTS="sanitization_test offload_indication_test \
+	sanitization_vlan_aware_test offload_indication_vlan_aware_test"
 NUM_NETIFS=2
 source $lib_dir/lib.sh
 
@@ -654,6 +655,207 @@ offload_indication_test()
 	offload_indication_setup_destroy
 }
 
+sanitization_vlan_aware_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0 vlan_filtering 1
+
+	ip link add name vxlan10 up master br0 type vxlan id 10 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	ip link add name vxlan20 up master br0 type vxlan id 20 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	# Test that when each VNI is mapped to a different VLAN we can enslave
+	# a port to the bridge
+	bridge vlan add vid 10 dev vxlan10 pvid untagged
+	bridge vlan add vid 20 dev vxlan20 pvid untagged
+
+	ip link set dev $swp1 master br0
+	check_err $?
+
+	log_test "vlan-aware - enslavement to vlan-aware bridge"
+
+	# Try to map both VNIs to the same VLAN and make sure configuration
+	# fails
+	RET=0
+
+	bridge vlan add vid 10 dev vxlan20 pvid untagged &> /dev/null
+	check_fail $?
+
+	log_test "vlan-aware - two vnis mapped to the same vlan"
+
+	# Test that enslavement of a port to a bridge fails when two VNIs
+	# are mapped to the same VLAN
+	RET=0
+
+	ip link set dev $swp1 nomaster
+
+	bridge vlan del vid 20 dev vxlan20 pvid untagged
+	bridge vlan add vid 10 dev vxlan20 pvid untagged
+
+	ip link set dev $swp1 master br0 &> /dev/null
+	check_fail $?
+
+	log_test "vlan-aware - failed enslavement to vlan-aware bridge"
+
+	ip link del dev vxlan20
+	ip link del dev vxlan10
+	ip link del dev br0
+}
+
+offload_indication_vlan_aware_setup_create()
+{
+	# Create a simple setup with two VxLAN devices and a single VLAN-aware
+	# bridge
+	ip link add name br0 up type bridge mcast_snooping 0 vlan_filtering 1 \
+		vlan_default_pvid 0
+
+	ip link set dev $swp1 master br0
+
+	bridge vlan add vid 10 dev $swp1
+	bridge vlan add vid 20 dev $swp1
+
+	ip address add 198.51.100.1/32 dev lo
+
+	ip link add name vxlan10 up master br0 type vxlan id 10 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan20 up master br0 type vxlan id 20 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	bridge vlan add vid 10 dev vxlan10 pvid untagged
+	bridge vlan add vid 20 dev vxlan20 pvid untagged
+}
+
+offload_indication_vlan_aware_setup_destroy()
+{
+	bridge vlan del vid 20 dev vxlan20
+	bridge vlan del vid 10 dev vxlan10
+
+	ip link del dev vxlan20
+	ip link del dev vxlan10
+
+	ip address del 198.51.100.1/32 dev lo
+
+	bridge vlan del vid 20 dev $swp1
+	bridge vlan del vid 10 dev $swp1
+
+	ip link set dev $swp1 nomaster
+
+	ip link del dev br0
+}
+
+offload_indication_vlan_aware_fdb_test()
+{
+	RET=0
+
+	log_info "vxlan entry offload indication - vlan-aware"
+
+	bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self master static \
+		dst 198.51.100.2 vlan 10
+
+	bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_err $?
+	bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_err $?
+
+	log_test "vxlan entry offload indication - initial state"
+
+	# Remove FDB entry from the bridge driver and check that corresponding
+	# entry in the VxLAN driver is not marked as offloaded
+	RET=0
+
+	bridge fdb del de:ad:be:ef:13:37 dev vxlan10 master vlan 10
+	bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_fail $?
+
+	log_test "vxlan entry offload indication - after removal from bridge"
+
+	# Add the FDB entry back to the bridge driver and make sure it is
+	# marked as offloaded in both drivers
+	RET=0
+
+	bridge fdb add de:ad:be:ef:13:37 dev vxlan10 master static vlan 10
+	bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_err $?
+	bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_err $?
+
+	log_test "vxlan entry offload indication - after re-add to bridge"
+
+	# Remove FDB entry from the VxLAN driver and check that corresponding
+	# entry in the bridge driver is not marked as offloaded
+	RET=0
+
+	bridge fdb del de:ad:be:ef:13:37 dev vxlan10 self
+	bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_fail $?
+
+	log_test "vxlan entry offload indication - after removal from vxlan"
+
+	# Add the FDB entry back to the VxLAN driver and make sure it is
+	# marked as offloaded in both drivers
+	RET=0
+
+	bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self dst 198.51.100.2
+	bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_err $?
+	bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_err $?
+
+	log_test "vxlan entry offload indication - after re-add to vxlan"
+
+	bridge fdb del de:ad:be:ef:13:37 dev vxlan10 self master vlan 10
+}
+
+offload_indication_vlan_aware_decap_route_test()
+{
+	RET=0
+
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	# Toggle PVID flag on one VxLAN device and make sure route is still
+	# marked as offloaded
+	bridge vlan add vid 10 dev vxlan10 untagged
+
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	# Toggle PVID flag on second VxLAN device and make sure route is no
+	# longer marked as offloaded
+	bridge vlan add vid 20 dev vxlan20 untagged
+
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_fail $?
+
+	# Toggle PVID flag back and make sure route is marked as offloaded
+	bridge vlan add vid 10 dev vxlan10 pvid untagged
+	bridge vlan add vid 20 dev vxlan20 pvid untagged
+
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	log_test "vxlan decap route - vni map/unmap"
+}
+
+offload_indication_vlan_aware_test()
+{
+	offload_indication_vlan_aware_setup_create
+	offload_indication_vlan_aware_fdb_test
+	offload_indication_vlan_aware_decap_route_test
+	offload_indication_vlan_aware_setup_destroy
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
cgit v1.2.3


From b5166d7a92398e3bd7fc44f8705c07fdfbfc0c17 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 28 Nov 2018 20:07:08 +0000
Subject: selftests: forwarding: Add VxLAN test with a VLAN-aware bridge

The test is very similar to its VLAN-unaware counterpart
(vxlan_bridge_1d.sh), but instead of using multiple VLAN-unaware
bridges, a single VLAN-aware bridge is used with multiple VLANs.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1q.sh    | 790 +++++++++++++++++++++
 .../net/forwarding/vxlan_bridge_1q_port_8472.sh    |  10 +
 2 files changed, 800 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
 create mode 100755 tools/testing/selftests/net/forwarding/vxlan_bridge_1q_port_8472.sh

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
new file mode 100755
index 000000000000..bac2e568d22c
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
@@ -0,0 +1,790 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +-----------------------+                          +------------------------+
+# | H1 (vrf)              |                          | H2 (vrf)               |
+# |  + $h1.10             |                          |  + $h2.10              |
+# |  | 192.0.2.1/28       |                          |  | 192.0.2.2/28        |
+# |  |                    |                          |  |                     |
+# |  | + $h1.20           |                          |  | + $h2.20            |
+# |  \ | 198.51.100.1/24  |                          |  \ | 198.51.100.2/24   |
+# |   \|                  |                          |   \|                   |
+# |    + $h1              |                          |    + $h2               |
+# +----|------------------+                          +----|-------------------+
+#      |                                                  |
+# +----|--------------------------------------------------|-------------------+
+# | SW |                                                  |                   |
+# | +--|--------------------------------------------------|-----------------+ |
+# | |  + $swp1                   BR1 (802.1q)             + $swp2           | |
+# | |     vid 10                                             vid 10         | |
+# | |     vid 20                                             vid 20         | |
+# | |                                                                       | |
+# | |  + vx10 (vxlan)                        + vx20 (vxlan)                 | |
+# | |    local 192.0.2.17                      local 192.0.2.17             | |
+# | |    remote 192.0.2.34 192.0.2.50          remote 192.0.2.34 192.0.2.50 | |
+# | |    id 1000 dstport $VXPORT               id 2000 dstport $VXPORT      | |
+# | |    vid 10 pvid untagged                  vid 20 pvid untagged         | |
+# | +-----------------------------------------------------------------------+ |
+# |                                                                           |
+# |  192.0.2.32/28 via 192.0.2.18                                             |
+# |  192.0.2.48/28 via 192.0.2.18                                             |
+# |                                                                           |
+# |    + $rp1                                                                 |
+# |    | 192.0.2.17/28                                                        |
+# +----|----------------------------------------------------------------------+
+#      |
+# +----|--------------------------------------------------------+
+# |    |                                             VRP2 (vrf) |
+# |    + $rp2                                                   |
+# |      192.0.2.18/28                                          |
+# |                                                             |   (maybe) HW
+# =============================================================================
+# |                                                             |  (likely) SW
+# |    + v1 (veth)                             + v3 (veth)      |
+# |    | 192.0.2.33/28                         | 192.0.2.49/28  |
+# +----|---------------------------------------|----------------+
+#      |                                       |
+# +----|------------------------------+   +----|------------------------------+
+# |    + v2 (veth)        NS1 (netns) |   |    + v4 (veth)        NS2 (netns) |
+# |      192.0.2.34/28                |   |      192.0.2.50/28                |
+# |                                   |   |                                   |
+# |   192.0.2.16/28 via 192.0.2.33    |   |   192.0.2.16/28 via 192.0.2.49    |
+# |   192.0.2.50/32 via 192.0.2.33    |   |   192.0.2.34/32 via 192.0.2.49    |
+# |                                   |   |                                   |
+# | +-------------------------------+ |   | +-------------------------------+ |
+# | |                  BR2 (802.1q) | |   | |                  BR2 (802.1q) | |
+# | |  + vx10 (vxlan)               | |   | |  + vx10 (vxlan)               | |
+# | |    local 192.0.2.34           | |   | |    local 192.0.2.50           | |
+# | |    remote 192.0.2.17          | |   | |    remote 192.0.2.17          | |
+# | |    remote 192.0.2.50          | |   | |    remote 192.0.2.34          | |
+# | |    id 1000 dstport $VXPORT    | |   | |    id 1000 dstport $VXPORT    | |
+# | |    vid 10 pvid untagged       | |   | |    vid 10 pvid untagged       | |
+# | |                               | |   | |                               | |
+# | |  + vx20 (vxlan)               | |   | |  + vx20 (vxlan)               | |
+# | |    local 192.0.2.34           | |   | |    local 192.0.2.50           | |
+# | |    remote 192.0.2.17          | |   | |    remote 192.0.2.17          | |
+# | |    remote 192.0.2.50          | |   | |    remote 192.0.2.34          | |
+# | |    id 2000 dstport $VXPORT    | |   | |    id 2000 dstport $VXPORT    | |
+# | |    vid 20 pvid untagged       | |   | |    vid 20 pvid untagged       | |
+# | |                               | |   | |                               | |
+# | |  + w1 (veth)                  | |   | |  + w1 (veth)                  | |
+# | |  | vid 10                     | |   | |  | vid 10                     | |
+# | |  | vid 20                     | |   | |  | vid 20                     | |
+# | +--|----------------------------+ |   | +--|----------------------------+ |
+# |    |                              |   |    |                              |
+# | +--|----------------------------+ |   | +--|----------------------------+ |
+# | |  + w2 (veth)        VW2 (vrf) | |   | |  + w2 (veth)        VW2 (vrf) | |
+# | |  |\                           | |   | |  |\                           | |
+# | |  | + w2.10                    | |   | |  | + w2.10                    | |
+# | |  |   192.0.2.3/28             | |   | |  |   192.0.2.4/28             | |
+# | |  |                            | |   | |  |                            | |
+# | |  + w2.20                      | |   | |  + w2.20                      | |
+# | |    198.51.100.3/24            | |   | |    198.51.100.4/24            | |
+# | +-------------------------------+ |   | +-------------------------------+ |
+# +-----------------------------------+   +-----------------------------------+
+
+: ${VXPORT:=4789}
+export VXPORT
+
+: ${ALL_TESTS:="
+	ping_ipv4
+	test_flood
+	test_unicast
+	reapply_config
+	ping_ipv4
+	test_flood
+	test_unicast
+	test_learning
+    "}
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+	tc qdisc add dev $h1 clsact
+	vlan_create $h1 10 v$h1 192.0.2.1/28
+	vlan_create $h1 20 v$h1 198.51.100.1/24
+}
+
+h1_destroy()
+{
+	vlan_destroy $h1 20
+	vlan_destroy $h1 10
+	tc qdisc del dev $h1 clsact
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2
+	tc qdisc add dev $h2 clsact
+	vlan_create $h2 10 v$h2 192.0.2.2/28
+	vlan_create $h2 20 v$h2 198.51.100.2/24
+}
+
+h2_destroy()
+{
+	vlan_destroy $h2 20
+	vlan_destroy $h2 10
+	tc qdisc del dev $h2 clsact
+	simple_if_fini $h2
+}
+
+rp1_set_addr()
+{
+	ip address add dev $rp1 192.0.2.17/28
+
+	ip route add 192.0.2.32/28 nexthop via 192.0.2.18
+	ip route add 192.0.2.48/28 nexthop via 192.0.2.18
+}
+
+rp1_unset_addr()
+{
+	ip route del 192.0.2.48/28 nexthop via 192.0.2.18
+	ip route del 192.0.2.32/28 nexthop via 192.0.2.18
+
+	ip address del dev $rp1 192.0.2.17/28
+}
+
+switch_create()
+{
+	ip link add name br1 type bridge vlan_filtering 1 vlan_default_pvid 0 \
+		mcast_snooping 0
+	# Make sure the bridge uses the MAC address of the local port and not
+	# that of the VxLAN's device.
+	ip link set dev br1 address $(mac_get $swp1)
+	ip link set dev br1 up
+
+	ip link set dev $rp1 up
+	rp1_set_addr
+
+	ip link add name vx10 type vxlan id 1000	\
+		local 192.0.2.17 dstport "$VXPORT"	\
+		nolearning noudpcsum tos inherit ttl 100
+	ip link set dev vx10 up
+
+	ip link set dev vx10 master br1
+	bridge vlan add vid 10 dev vx10 pvid untagged
+
+	ip link add name vx20 type vxlan id 2000	\
+		local 192.0.2.17 dstport "$VXPORT"	\
+		nolearning noudpcsum tos inherit ttl 100
+	ip link set dev vx20 up
+
+	ip link set dev vx20 master br1
+	bridge vlan add vid 20 dev vx20 pvid untagged
+
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+	bridge vlan add vid 10 dev $swp1
+	bridge vlan add vid 20 dev $swp1
+
+	ip link set dev $swp2 master br1
+	ip link set dev $swp2 up
+	bridge vlan add vid 10 dev $swp2
+	bridge vlan add vid 20 dev $swp2
+
+	bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self
+	bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self
+
+	bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self
+	bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self
+}
+
+switch_destroy()
+{
+	bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self
+	bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self
+
+	bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self
+	bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self
+
+	bridge vlan del vid 20 dev $swp2
+	bridge vlan del vid 10 dev $swp2
+	ip link set dev $swp2 down
+	ip link set dev $swp2 nomaster
+
+	bridge vlan del vid 20 dev $swp1
+	bridge vlan del vid 10 dev $swp1
+	ip link set dev $swp1 down
+	ip link set dev $swp1 nomaster
+
+	bridge vlan del vid 20 dev vx20
+	ip link set dev vx20 nomaster
+
+	ip link set dev vx20 down
+	ip link del dev vx20
+
+	bridge vlan del vid 10 dev vx10
+	ip link set dev vx10 nomaster
+
+	ip link set dev vx10 down
+	ip link del dev vx10
+
+	rp1_unset_addr
+	ip link set dev $rp1 down
+
+	ip link set dev br1 down
+	ip link del dev br1
+}
+
+vrp2_create()
+{
+	simple_if_init $rp2 192.0.2.18/28
+	__simple_if_init v1 v$rp2 192.0.2.33/28
+	__simple_if_init v3 v$rp2 192.0.2.49/28
+	tc qdisc add dev v1 clsact
+}
+
+vrp2_destroy()
+{
+	tc qdisc del dev v1 clsact
+	__simple_if_fini v3 192.0.2.49/28
+	__simple_if_fini v1 192.0.2.33/28
+	simple_if_fini $rp2 192.0.2.18/28
+}
+
+ns_init_common()
+{
+	local in_if=$1; shift
+	local in_addr=$1; shift
+	local other_in_addr=$1; shift
+	local nh_addr=$1; shift
+	local host_addr1=$1; shift
+	local host_addr2=$1; shift
+
+	ip link set dev $in_if up
+	ip address add dev $in_if $in_addr/28
+	tc qdisc add dev $in_if clsact
+
+	ip link add name br2 type bridge vlan_filtering 1 vlan_default_pvid 0
+	ip link set dev br2 up
+
+	ip link add name w1 type veth peer name w2
+
+	ip link set dev w1 master br2
+	ip link set dev w1 up
+
+	bridge vlan add vid 10 dev w1
+	bridge vlan add vid 20 dev w1
+
+	ip link add name vx10 type vxlan id 1000 local $in_addr \
+		dstport "$VXPORT"
+	ip link set dev vx10 up
+	bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.17 self
+	bridge fdb append dev vx10 00:00:00:00:00:00 dst $other_in_addr self
+
+	ip link set dev vx10 master br2
+	tc qdisc add dev vx10 clsact
+
+	bridge vlan add vid 10 dev vx10 pvid untagged
+
+	ip link add name vx20 type vxlan id 2000 local $in_addr \
+		dstport "$VXPORT"
+	ip link set dev vx20 up
+	bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.17 self
+	bridge fdb append dev vx20 00:00:00:00:00:00 dst $other_in_addr self
+
+	ip link set dev vx20 master br2
+	tc qdisc add dev vx20 clsact
+
+	bridge vlan add vid 20 dev vx20 pvid untagged
+
+	simple_if_init w2
+        vlan_create w2 10 vw2 $host_addr1/28
+        vlan_create w2 20 vw2 $host_addr2/24
+
+	ip route add 192.0.2.16/28 nexthop via $nh_addr
+	ip route add $other_in_addr/32 nexthop via $nh_addr
+}
+export -f ns_init_common
+
+ns1_create()
+{
+	ip netns add ns1
+	ip link set dev v2 netns ns1
+	in_ns ns1 \
+	      ns_init_common v2 192.0.2.34 192.0.2.50 192.0.2.33 192.0.2.3 \
+	      198.51.100.3
+}
+
+ns1_destroy()
+{
+	ip netns exec ns1 ip link set dev v2 netns 1
+	ip netns del ns1
+}
+
+ns2_create()
+{
+	ip netns add ns2
+	ip link set dev v4 netns ns2
+	in_ns ns2 \
+	      ns_init_common v4 192.0.2.50 192.0.2.34 192.0.2.49 192.0.2.4 \
+	      198.51.100.4
+}
+
+ns2_destroy()
+{
+	ip netns exec ns2 ip link set dev v4 netns 1
+	ip netns del ns2
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp1=${NETIFS[p5]}
+	rp2=${NETIFS[p6]}
+
+	vrf_prepare
+	forwarding_enable
+
+	h1_create
+	h2_create
+	switch_create
+
+	ip link add name v1 type veth peer name v2
+	ip link add name v3 type veth peer name v4
+	vrp2_create
+	ns1_create
+	ns2_create
+
+	r1_mac=$(in_ns ns1 mac_get w2)
+	r2_mac=$(in_ns ns2 mac_get w2)
+	h2_mac=$(mac_get $h2)
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ns2_destroy
+	ns1_destroy
+	vrp2_destroy
+	ip link del dev v3
+	ip link del dev v1
+
+	switch_destroy
+	h2_destroy
+	h1_destroy
+
+	forwarding_restore
+	vrf_cleanup
+}
+
+# For the first round of tests, vx10 and vx20 were the first devices to get
+# attached to the bridge, and that at the point that the local IP is already
+# configured. Try the other scenario of attaching these devices to a bridge
+# that already has local ports members, and only then assign the local IP.
+reapply_config()
+{
+	log_info "Reapplying configuration"
+
+	bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self
+	bridge fdb del dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self
+
+	bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self
+	bridge fdb del dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self
+
+	ip link set dev vx20 nomaster
+	ip link set dev vx10 nomaster
+
+	rp1_unset_addr
+	sleep 5
+
+	ip link set dev vx10 master br1
+	bridge vlan add vid 10 dev vx10 pvid untagged
+
+	ip link set dev vx20 master br1
+	bridge vlan add vid 20 dev vx20 pvid untagged
+
+	bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.34 self
+	bridge fdb append dev vx10 00:00:00:00:00:00 dst 192.0.2.50 self
+
+	bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.34 self
+	bridge fdb append dev vx20 00:00:00:00:00:00 dst 192.0.2.50 self
+
+	rp1_set_addr
+	sleep 5
+}
+
+ping_ipv4()
+{
+	ping_test $h1.10 192.0.2.2 ": local->local vid 10"
+	ping_test $h1.20 198.51.100.2 ": local->local vid 20"
+	ping_test $h1.10 192.0.2.3 ": local->remote 1 vid 10"
+	ping_test $h1.10 192.0.2.4 ": local->remote 2 vid 10"
+	ping_test $h1.20 198.51.100.3 ": local->remote 1 vid 20"
+	ping_test $h1.20 198.51.100.4 ": local->remote 2 vid 20"
+}
+
+maybe_in_ns()
+{
+	echo ${1:+in_ns} $1
+}
+
+__flood_counter_add_del()
+{
+	local add_del=$1; shift
+	local dev=$1; shift
+	local ns=$1; shift
+
+	# Putting the ICMP capture both to HW and to SW will end up
+	# double-counting the packets that are trapped to slow path, such as for
+	# the unicast test. Adding either skip_hw or skip_sw fixes this problem,
+	# but with skip_hw, the flooded packets are not counted at all, because
+	# those are dropped due to MAC address mismatch; and skip_sw is a no-go
+	# for veth-based topologies.
+	#
+	# So try to install with skip_sw and fall back to skip_sw if that fails.
+
+	$(maybe_in_ns $ns) __icmp_capture_add_del          \
+			   $add_del 100 "" $dev skip_sw 2>/dev/null || \
+	$(maybe_in_ns $ns) __icmp_capture_add_del          \
+			   $add_del 100 "" $dev skip_hw
+}
+
+flood_counter_install()
+{
+	__flood_counter_add_del add "$@"
+}
+
+flood_counter_uninstall()
+{
+	__flood_counter_add_del del "$@"
+}
+
+flood_fetch_stat()
+{
+	local dev=$1; shift
+	local ns=$1; shift
+
+	$(maybe_in_ns $ns) tc_rule_stats_get $dev 100 ingress
+}
+
+flood_fetch_stats()
+{
+	local counters=("${@}")
+	local counter
+
+	for counter in "${counters[@]}"; do
+		flood_fetch_stat $counter
+	done
+}
+
+vxlan_flood_test()
+{
+	local mac=$1; shift
+	local dst=$1; shift
+	local vid=$1; shift
+	local -a expects=("${@}")
+
+	local -a counters=($h2 "vx10 ns1" "vx20 ns1" "vx10 ns2" "vx20 ns2")
+	local counter
+	local key
+
+	# Packets reach the local host tagged whereas they reach the VxLAN
+	# devices untagged. In order to be able to use the same filter for
+	# all counters, make sure the packets also reach the local host
+	# untagged
+	bridge vlan add vid $vid dev $swp2 untagged
+	for counter in "${counters[@]}"; do
+		flood_counter_install $counter
+	done
+
+	local -a t0s=($(flood_fetch_stats "${counters[@]}"))
+	$MZ $h1 -Q $vid -c 10 -d 100msec -p 64 -b $mac -B $dst -t icmp -q
+	sleep 1
+	local -a t1s=($(flood_fetch_stats "${counters[@]}"))
+
+	for key in ${!t0s[@]}; do
+		local delta=$((t1s[$key] - t0s[$key]))
+		local expect=${expects[$key]}
+
+		((expect == delta))
+		check_err $? "${counters[$key]}: Expected to capture $expect packets, got $delta."
+	done
+
+	for counter in "${counters[@]}"; do
+		flood_counter_uninstall $counter
+	done
+	bridge vlan add vid $vid dev $swp2
+}
+
+__test_flood()
+{
+	local mac=$1; shift
+	local dst=$1; shift
+	local vid=$1; shift
+	local what=$1; shift
+	local -a expects=("${@}")
+
+	RET=0
+
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	log_test "VXLAN: $what"
+}
+
+test_flood()
+{
+	__test_flood de:ad:be:ef:13:37 192.0.2.100 10 "flood vlan 10" \
+		10 10 0 10 0
+	__test_flood ca:fe:be:ef:13:37 198.51.100.100 20 "flood vlan 20" \
+		10 0 10 0 10
+}
+
+vxlan_fdb_add_del()
+{
+	local add_del=$1; shift
+	local vid=$1; shift
+	local mac=$1; shift
+	local dev=$1; shift
+	local dst=$1; shift
+
+	bridge fdb $add_del dev $dev $mac self static permanent \
+		${dst:+dst} $dst 2>/dev/null
+	bridge fdb $add_del dev $dev $mac master static vlan $vid 2>/dev/null
+}
+
+__test_unicast()
+{
+	local mac=$1; shift
+	local dst=$1; shift
+	local hit_idx=$1; shift
+	local vid=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	local -a expects=(0 0 0 0 0)
+	expects[$hit_idx]=10
+
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	log_test "VXLAN: $what"
+}
+
+test_unicast()
+{
+	local -a targets=("$h2_mac $h2"
+			  "$r1_mac vx10 192.0.2.34"
+			  "$r2_mac vx10 192.0.2.50")
+	local target
+
+	log_info "unicast vlan 10"
+
+	for target in "${targets[@]}"; do
+		vxlan_fdb_add_del add 10 $target
+	done
+
+	__test_unicast $h2_mac 192.0.2.2 0 10 "local MAC unicast"
+	__test_unicast $r1_mac 192.0.2.3 1 10 "remote MAC 1 unicast"
+	__test_unicast $r2_mac 192.0.2.4 3 10 "remote MAC 2 unicast"
+
+	for target in "${targets[@]}"; do
+		vxlan_fdb_add_del del 10 $target
+	done
+
+	log_info "unicast vlan 20"
+
+	targets=("$h2_mac $h2" "$r1_mac vx20 192.0.2.34" \
+		 "$r2_mac vx20 192.0.2.50")
+
+	for target in "${targets[@]}"; do
+		vxlan_fdb_add_del add 20 $target
+	done
+
+	__test_unicast $h2_mac 198.51.100.2 0 20 "local MAC unicast"
+	__test_unicast $r1_mac 198.51.100.3 2 20 "remote MAC 1 unicast"
+	__test_unicast $r2_mac 198.51.100.4 4 20 "remote MAC 2 unicast"
+
+	for target in "${targets[@]}"; do
+		vxlan_fdb_add_del del 20 $target
+	done
+}
+
+vxlan_ping_test()
+{
+	local ping_dev=$1; shift
+	local ping_dip=$1; shift
+	local ping_args=$1; shift
+	local capture_dev=$1; shift
+	local capture_dir=$1; shift
+	local capture_pref=$1; shift
+	local expect=$1; shift
+
+	local t0=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir)
+	ping_do $ping_dev $ping_dip "$ping_args"
+	local t1=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir)
+	local delta=$((t1 - t0))
+
+	# Tolerate a couple stray extra packets.
+	((expect <= delta && delta <= expect + 2))
+	check_err $? "$capture_dev: Expected to capture $expect packets, got $delta."
+}
+
+__test_learning()
+{
+	local -a expects=(0 0 0 0 0)
+	local mac=$1; shift
+	local dst=$1; shift
+	local vid=$1; shift
+	local idx1=$1; shift
+	local idx2=$1; shift
+	local vx=vx$vid
+
+	# Check that flooding works
+	RET=0
+
+	expects[0]=10; expects[$idx1]=10; expects[$idx2]=10
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	log_test "VXLAN: flood before learning"
+
+	# Send a packet with source mac set to $mac from host w2 and check that
+	# a corresponding entry is created in the VxLAN device
+	RET=0
+
+	in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \
+		-B $dst -t icmp -q
+	sleep 1
+
+	bridge fdb show brport $vx | grep $mac | grep -q self
+	check_err $?
+	bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \
+		| grep -q -v self
+	check_err $?
+
+	log_test "VXLAN: show learned FDB entry"
+
+	# Repeat first test and check that packets only reach host w2 in ns1
+	RET=0
+
+	expects[0]=0; expects[$idx1]=10; expects[$idx2]=0
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	log_test "VXLAN: learned FDB entry"
+
+	# Delete the learned FDB entry from the VxLAN and bridge devices and
+	# check that packets are flooded
+	RET=0
+
+	bridge fdb del dev $vx $mac master self vlan $vid
+	sleep 1
+
+	expects[0]=10; expects[$idx1]=10; expects[$idx2]=10
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	log_test "VXLAN: deletion of learned FDB entry"
+
+	# Re-learn the first FDB entry and check that it is correctly aged-out
+	RET=0
+
+	in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \
+		-B $dst -t icmp -q
+	sleep 1
+
+	bridge fdb show brport $vx | grep $mac | grep -q self
+	check_err $?
+	bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \
+		| grep -q -v self
+	check_err $?
+
+	expects[0]=0; expects[$idx1]=10; expects[$idx2]=0
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	sleep 20
+
+	bridge fdb show brport $vx | grep $mac | grep -q self
+	check_fail $?
+	bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \
+		| grep -q -v self
+	check_fail $?
+
+	expects[0]=10; expects[$idx1]=10; expects[$idx2]=10
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	log_test "VXLAN: Ageing of learned FDB entry"
+
+	# Toggle learning on the bridge port and check that the bridge's FDB
+	# is populated only when it should
+	RET=0
+
+	ip link set dev $vx type bridge_slave learning off
+
+	in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \
+		-B $dst -t icmp -q
+	sleep 1
+
+	bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \
+		| grep -q -v self
+	check_fail $?
+
+	ip link set dev $vx type bridge_slave learning on
+
+	in_ns ns1 $MZ w2 -Q $vid -c 1 -p 64 -a $mac -b ff:ff:ff:ff:ff:ff \
+		-B $dst -t icmp -q
+	sleep 1
+
+	bridge fdb show brport $vx | grep $mac | grep "vlan $vid" \
+		| grep -q -v self
+	check_err $?
+
+	log_test "VXLAN: learning toggling on bridge port"
+}
+
+test_learning()
+{
+	local mac=de:ad:be:ef:13:37
+	local dst=192.0.2.100
+	local vid=10
+
+	# Enable learning on the VxLAN devices and set ageing time to 10 seconds
+	ip link set dev br1 type bridge ageing_time 1000
+	ip link set dev vx10 type vxlan ageing 10
+	ip link set dev vx10 type vxlan learning
+	ip link set dev vx20 type vxlan ageing 10
+	ip link set dev vx20 type vxlan learning
+	reapply_config
+
+	log_info "learning vlan 10"
+
+	__test_learning $mac $dst $vid 1 3
+
+	log_info "learning vlan 20"
+
+	mac=ca:fe:be:ef:13:37
+	dst=198.51.100.100
+	vid=20
+
+	__test_learning $mac $dst $vid 2 4
+
+	# Restore previous settings
+	ip link set dev vx20 type vxlan nolearning
+	ip link set dev vx20 type vxlan ageing 300
+	ip link set dev vx10 type vxlan nolearning
+	ip link set dev vx10 type vxlan ageing 300
+	ip link set dev br1 type bridge ageing_time 30000
+	reapply_config
+}
+
+test_all()
+{
+	log_info "Running tests with UDP port $VXPORT"
+	tests_run
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+test_all
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_port_8472.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_port_8472.sh
new file mode 100755
index 000000000000..b1b2d1a3164f
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_port_8472.sh
@@ -0,0 +1,10 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# A wrapper to run VXLAN tests with an unusual port number.
+
+VXPORT=8472
+ALL_TESTS="
+	ping_ipv4
+"
+source vxlan_bridge_1q.sh
-- 
cgit v1.2.3


From bf1c3ab8d3571db8a973b0c46c5aa963b30d9a82 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 28 Nov 2018 17:37:53 +0100
Subject: net: reorder flowi_common fields to avoid holes

the flowi* structures are used and memsetted by server functions
in critical path. Currently flowi_common has a couple of holes that
we can eliminate reordering the struct fields. As a side effect,
both flowi4 and flowi6 shrink by 8 bytes.

Before:
pahole -EC flowi_common
struct flowi_common {
// ...
	/* size: 40, cachelines: 1, members: 10 */
	/* sum members: 32, holes: 1, sum holes: 4 */
	/* padding: 4 */
	/* last cacheline: 40 bytes */
};
pahole -EC flowi6
struct flowi6 {
// ...
        /* size: 88, cachelines: 2, members: 6 */
        /* padding: 4 */
        /* last cacheline: 24 bytes */
};
pahole -EC flowi4
struct flowi4 {
// ...
        /* size: 56, cachelines: 1, members: 4 */
        /* padding: 4 */
        /* last cacheline: 56 bytes */
};

After:
struct flowi_common {
// ...
	/* size: 32, cachelines: 1, members: 10 */
	/* last cacheline: 32 bytes */
};
struct flowi6 {
// ...
        /* size: 80, cachelines: 2, members: 6 */
        /* padding: 4 */
        /* last cacheline: 16 bytes */
};
struct flowi4 {
// ...
        /* size: 48, cachelines: 1, members: 4 */
        /* padding: 4 */
        /* last cacheline: 48 bytes */
};

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/flow.h b/include/net/flow.h
index 8ce21793094e..93f2c9a0f098 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -38,8 +38,8 @@ struct flowi_common {
 #define FLOWI_FLAG_KNOWN_NH		0x02
 #define FLOWI_FLAG_SKIP_NH_OIF		0x04
 	__u32	flowic_secid;
-	struct flowi_tunnel flowic_tun_key;
 	kuid_t  flowic_uid;
+	struct flowi_tunnel flowic_tun_key;
 };
 
 union flowi_uli {
-- 
cgit v1.2.3


From 26d31925cd5ea4b5b168ed538b0326d63ccbb384 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 28 Nov 2018 19:12:56 +0100
Subject: tun: implement carrier change

The userspace may need to control the carrier state.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: Didier Pallard <didier.pallard@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c           | 27 ++++++++++++++++++++++++++-
 include/uapi/linux/if_tun.h |  1 +
 2 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 56575f88d1fd..835c73f42ae7 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1254,6 +1254,21 @@ static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
+static int tun_net_change_carrier(struct net_device *dev, bool new_carrier)
+{
+	if (new_carrier) {
+		struct tun_struct *tun = netdev_priv(dev);
+
+		if (!tun->numqueues)
+			return -EPERM;
+
+		netif_carrier_on(dev);
+	} else {
+		netif_carrier_off(dev);
+	}
+	return 0;
+}
+
 static const struct net_device_ops tun_netdev_ops = {
 	.ndo_uninit		= tun_net_uninit,
 	.ndo_open		= tun_net_open,
@@ -1263,6 +1278,7 @@ static const struct net_device_ops tun_netdev_ops = {
 	.ndo_select_queue	= tun_select_queue,
 	.ndo_set_rx_headroom	= tun_set_headroom,
 	.ndo_get_stats64	= tun_net_get_stats64,
+	.ndo_change_carrier	= tun_net_change_carrier,
 };
 
 static void __tun_xdp_flush_tfile(struct tun_file *tfile)
@@ -1345,6 +1361,7 @@ static const struct net_device_ops tap_netdev_ops = {
 	.ndo_get_stats64	= tun_net_get_stats64,
 	.ndo_bpf		= tun_xdp,
 	.ndo_xdp_xmit		= tun_xdp_xmit,
+	.ndo_change_carrier	= tun_net_change_carrier,
 };
 
 static void tun_flow_init(struct tun_struct *tun)
@@ -3002,12 +3019,12 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	struct net *net = sock_net(&tfile->sk);
 	struct tun_struct *tun;
 	void __user* argp = (void __user*)arg;
+	unsigned int ifindex, carrier;
 	struct ifreq ifr;
 	kuid_t owner;
 	kgid_t group;
 	int sndbuf;
 	int vnet_hdr_sz;
-	unsigned int ifindex;
 	int le;
 	int ret;
 	bool do_notify = false;
@@ -3291,6 +3308,14 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		ret = tun_set_ebpf(tun, &tun->filter_prog, argp);
 		break;
 
+	case TUNSETCARRIER:
+		ret = -EFAULT;
+		if (copy_from_user(&carrier, argp, sizeof(carrier)))
+			goto unlock;
+
+		ret = tun_net_change_carrier(tun->dev, (bool)carrier);
+		break;
+
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index ee432cd3018c..23a6753b37df 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -59,6 +59,7 @@
 #define TUNGETVNETBE _IOR('T', 223, int)
 #define TUNSETSTEERINGEBPF _IOR('T', 224, int)
 #define TUNSETFILTEREBPF _IOR('T', 225, int)
+#define TUNSETCARRIER _IOW('T', 226, int)
 
 /* TUNSETIFF ifr flags */
 #define IFF_TUN		0x0001
-- 
cgit v1.2.3


From 315c9e83010d63370fb0de160e52a21c3f3fa687 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 29 Nov 2018 02:36:32 +0000
Subject: net: qualcomm: rmnet: Remove set but not used variable 'cmd'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c: In function 'rmnet_map_do_flow_control':
drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c:23:36: warning:
 variable 'cmd' set but not used [-Wunused-but-set-variable]
  struct rmnet_map_control_command *cmd;

'cmd' not used anymore now, should also be removed.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
index 8990307e5475..f6cf59aee212 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
@@ -20,14 +20,12 @@ static u8 rmnet_map_do_flow_control(struct sk_buff *skb,
 				    struct rmnet_port *port,
 				    int enable)
 {
-	struct rmnet_map_control_command *cmd;
 	struct rmnet_endpoint *ep;
 	struct net_device *vnd;
 	u8 mux_id;
 	int r;
 
 	mux_id = RMNET_MAP_GET_MUX_ID(skb);
-	cmd = RMNET_MAP_GET_CMD_START(skb);
 
 	if (mux_id >= RMNET_MAX_LOGICAL_EP) {
 		kfree_skb(skb);
-- 
cgit v1.2.3


From 97e6c858a26ee8a31719a08ae896ca682eb8978e Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Wed, 28 Nov 2018 23:01:05 -0700
Subject: net: usb: aqc111: Initialize wol_cfg with memset in aqc111_suspend

Clang warns:

drivers/net/usb/aqc111.c:1326:37: warning: suggest braces around
initialization of subobject [-Wmissing-braces]
                struct aqc111_wol_cfg wol_cfg = { 0 };
                                                  ^
                                                  {}
1 warning generated.

Use memset to initialize the object to take compiler instrumentation out
of the equation.

Fixes: e58ba4544c77 ("net: usb: aqc111: Add support for wake on LAN by MAGIC packet")
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index f69d566bd523..57f1c94fca0b 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -1323,7 +1323,9 @@ static int aqc111_suspend(struct usb_interface *intf, pm_message_t message)
 			      1, 1, &reg8);
 
 	if (aqc111_data->wol_flags) {
-		struct aqc111_wol_cfg wol_cfg = { 0 };
+		struct aqc111_wol_cfg wol_cfg;
+
+		memset(&wol_cfg, 0, sizeof(struct aqc111_wol_cfg));
 
 		aqc111_data->phy_cfg |= AQ_WOL;
 		ether_addr_copy(wol_cfg.hw_addr, dev->net->dev_addr);
-- 
cgit v1.2.3


From 88945f460603ad8909b556c67a9229bb23188d41 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Wed, 28 Nov 2018 22:33:53 -0800
Subject: bpf: Fix verifier log string check for bad alignment.

The message got changed a lot time ago.

This was responsible for 36 test case failures on sparc64.

Fixes: f1174f77b50c ("bpf/verifier: rework value tracking")
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 17021d2b6bfe..5eace1f606fb 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -14287,7 +14287,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 
 	reject_from_alignment = fd_prog < 0 &&
 				(test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
-				strstr(bpf_vlog, "Unknown alignment.");
+				strstr(bpf_vlog, "misaligned");
 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 	if (reject_from_alignment) {
 		printf("FAIL\nFailed due to alignment despite having efficient unaligned access: '%s'!\n",
-- 
cgit v1.2.3


From e9ee9efc0d176512cdce9d27ff8549d7ffa2bfcd Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Fri, 30 Nov 2018 21:08:14 -0800
Subject: bpf: Add BPF_F_ANY_ALIGNMENT.

Often we want to write tests cases that check things like bad context
offset accesses.  And one way to do this is to use an odd offset on,
for example, a 32-bit load.

This unfortunately triggers the alignment checks first on platforms
that do not set CONFIG_EFFICIENT_UNALIGNED_ACCESS.  So the test
case see the alignment failure rather than what it was testing for.

It is often not completely possible to respect the original intention
of the test, or even test the same exact thing, while solving the
alignment issue.

Another option could have been to check the alignment after the
context and other validations are performed by the verifier, but
that is a non-trivial change to the verifier.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h                    | 14 ++++++++++++++
 kernel/bpf/syscall.c                        |  7 ++++++-
 kernel/bpf/verifier.c                       |  2 ++
 tools/include/uapi/linux/bpf.h              | 14 ++++++++++++++
 tools/lib/bpf/bpf.c                         |  8 ++++----
 tools/lib/bpf/bpf.h                         |  2 +-
 tools/testing/selftests/bpf/test_align.c    |  4 ++--
 tools/testing/selftests/bpf/test_verifier.c |  3 ++-
 8 files changed, 45 insertions(+), 9 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 597afdbc1ab9..8050caea7495 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -232,6 +232,20 @@ enum bpf_attach_type {
  */
 #define BPF_F_STRICT_ALIGNMENT	(1U << 0)
 
+/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the
+ * verifier will allow any alignment whatsoever.  On platforms
+ * with strict alignment requirements for loads ands stores (such
+ * as sparc and mips) the verifier validates that all loads and
+ * stores provably follow this requirement.  This flag turns that
+ * checking and enforcement off.
+ *
+ * It is mostly used for testing when we want to validate the
+ * context and memory access aspects of the verifier, but because
+ * of an unaligned access the alignment check would trigger before
+ * the one we are interested in.
+ */
+#define BPF_F_ANY_ALIGNMENT	(1U << 1)
+
 /* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
 #define BPF_PSEUDO_MAP_FD	1
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 85cbeec06e50..f9554d9a14e1 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1452,9 +1452,14 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	if (CHECK_ATTR(BPF_PROG_LOAD))
 		return -EINVAL;
 
-	if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT)
+	if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT))
 		return -EINVAL;
 
+	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
+	    (attr->prog_flags & BPF_F_ANY_ALIGNMENT) &&
+	    !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	/* copy eBPF program license from user space */
 	if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
 			      sizeof(license) - 1) < 0)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9584438fa2cc..71988337ac14 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6505,6 +6505,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
 		env->strict_alignment = true;
+	if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
+		env->strict_alignment = false;
 
 	ret = replace_map_fd_with_map_ptr(env);
 	if (ret < 0)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 597afdbc1ab9..8050caea7495 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -232,6 +232,20 @@ enum bpf_attach_type {
  */
 #define BPF_F_STRICT_ALIGNMENT	(1U << 0)
 
+/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the
+ * verifier will allow any alignment whatsoever.  On platforms
+ * with strict alignment requirements for loads ands stores (such
+ * as sparc and mips) the verifier validates that all loads and
+ * stores provably follow this requirement.  This flag turns that
+ * checking and enforcement off.
+ *
+ * It is mostly used for testing when we want to validate the
+ * context and memory access aspects of the verifier, but because
+ * of an unaligned access the alignment check would trigger before
+ * the one we are interested in.
+ */
+#define BPF_F_ANY_ALIGNMENT	(1U << 1)
+
 /* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
 #define BPF_PSEUDO_MAP_FD	1
 
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index ce1822194590..c19226cccf39 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -279,9 +279,9 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 }
 
 int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
-		       size_t insns_cnt, int strict_alignment,
-		       const char *license, __u32 kern_version,
-		       char *log_buf, size_t log_buf_sz, int log_level)
+		       size_t insns_cnt, __u32 prog_flags, const char *license,
+		       __u32 kern_version, char *log_buf, size_t log_buf_sz,
+		       int log_level)
 {
 	union bpf_attr attr;
 
@@ -295,7 +295,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	attr.log_level = log_level;
 	log_buf[0] = 0;
 	attr.kern_version = kern_version;
-	attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0;
+	attr.prog_flags = prog_flags;
 
 	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 }
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 09e8bbe111d4..60392b70587c 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -98,7 +98,7 @@ LIBBPF_API int bpf_load_program(enum bpf_prog_type type,
 				char *log_buf, size_t log_buf_sz);
 LIBBPF_API int bpf_verify_program(enum bpf_prog_type type,
 				  const struct bpf_insn *insns,
-				  size_t insns_cnt, int strict_alignment,
+				  size_t insns_cnt, __u32 prog_flags,
 				  const char *license, __u32 kern_version,
 				  char *log_buf, size_t log_buf_sz,
 				  int log_level);
diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c
index 5f377ec53f2f..3c789d03b629 100644
--- a/tools/testing/selftests/bpf/test_align.c
+++ b/tools/testing/selftests/bpf/test_align.c
@@ -620,8 +620,8 @@ static int do_test_single(struct bpf_align_test *test)
 
 	prog_len = probe_filter_length(prog);
 	fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
-				     prog, prog_len, 1, "GPL", 0,
-				     bpf_vlog, sizeof(bpf_vlog), 2);
+				     prog, prog_len, BPF_F_STRICT_ALIGNMENT,
+				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 2);
 	if (fd_prog < 0 && test->result != REJECT) {
 		printf("Failed to load program.\n");
 		printf("%s", bpf_vlog);
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 5eace1f606fb..78e779c35869 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -14275,7 +14275,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	prog_len = probe_filter_length(prog);
 
 	fd_prog = bpf_verify_program(prog_type, prog, prog_len,
-				     test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
+				     test->flags & F_LOAD_WITH_STRICT_ALIGNMENT ?
+				     BPF_F_STRICT_ALIGNMENT : 0,
 				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1);
 
 	expected_ret = unpriv && test->result_unpriv != UNDEF ?
-- 
cgit v1.2.3


From c7665702d3208b77b8e00f0699b6b88241b04360 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Fri, 30 Nov 2018 21:08:26 -0800
Subject: bpf: Adjust F_NEEDS_EFFICIENT_UNALIGNED_ACCESS handling in
 test_verifier.c

Make it set the flag argument to bpf_verify_program() which will relax
the alignment restrictions.

Now all such test cases will go properly through the verifier even on
inefficient unaligned access architectures.

On inefficient unaligned access architectures do not try to run such
programs, instead mark the test case as passing but annotate the
result similarly to how it is done now in the presence of this flag.

So, we get complete full coverage for all REJECT test cases, and at
least verifier level coverage for ACCEPT test cases.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 42 ++++++++++++++++-------------
 1 file changed, 24 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 78e779c35869..1d1775faaf14 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -14257,13 +14257,14 @@ out:
 static void do_test_single(struct bpf_test *test, bool unpriv,
 			   int *passes, int *errors)
 {
-	int fd_prog, expected_ret, reject_from_alignment;
+	int fd_prog, expected_ret, alignment_prevented_execution;
 	int prog_len, prog_type = test->prog_type;
 	struct bpf_insn *prog = test->insns;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
 	uint32_t expected_val;
 	uint32_t retval;
+	__u32 pflags;
 	int i, err;
 
 	for (i = 0; i < MAX_NR_MAPS; i++)
@@ -14274,9 +14275,12 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	do_test_fixup(test, prog_type, prog, map_fds);
 	prog_len = probe_filter_length(prog);
 
-	fd_prog = bpf_verify_program(prog_type, prog, prog_len,
-				     test->flags & F_LOAD_WITH_STRICT_ALIGNMENT ?
-				     BPF_F_STRICT_ALIGNMENT : 0,
+	pflags = 0;
+	if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT)
+		pflags |= BPF_F_STRICT_ALIGNMENT;
+	if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
+		pflags |= BPF_F_ANY_ALIGNMENT;
+	fd_prog = bpf_verify_program(prog_type, prog, prog_len, pflags,
 				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1);
 
 	expected_ret = unpriv && test->result_unpriv != UNDEF ?
@@ -14286,28 +14290,27 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	expected_val = unpriv && test->retval_unpriv ?
 		       test->retval_unpriv : test->retval;
 
-	reject_from_alignment = fd_prog < 0 &&
-				(test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
-				strstr(bpf_vlog, "misaligned");
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-	if (reject_from_alignment) {
-		printf("FAIL\nFailed due to alignment despite having efficient unaligned access: '%s'!\n",
-		       strerror(errno));
-		goto fail_log;
-	}
-#endif
+	alignment_prevented_execution = 0;
+
 	if (expected_ret == ACCEPT) {
-		if (fd_prog < 0 && !reject_from_alignment) {
+		if (fd_prog < 0) {
 			printf("FAIL\nFailed to load prog '%s'!\n",
 			       strerror(errno));
 			goto fail_log;
 		}
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+		if (fd_prog >= 0 &&
+		    (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)) {
+			alignment_prevented_execution = 1;
+			goto test_ok;
+		}
+#endif
 	} else {
 		if (fd_prog >= 0) {
 			printf("FAIL\nUnexpected success to load!\n");
 			goto fail_log;
 		}
-		if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) {
+		if (!strstr(bpf_vlog, expected_err)) {
 			printf("FAIL\nUnexpected error message!\n\tEXP: %s\n\tRES: %s\n",
 			      expected_err, bpf_vlog);
 			goto fail_log;
@@ -14335,9 +14338,12 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 			goto fail_log;
 		}
 	}
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+test_ok:
+#endif
 	(*passes)++;
-	printf("OK%s\n", reject_from_alignment ?
-	       " (NOTE: reject due to unknown alignment)" : "");
+	printf("OK%s\n", alignment_prevented_execution ?
+	       " (NOTE: not executed due to unknown alignment)" : "");
 close_fds:
 	close(fd_prog);
 	for (i = 0; i < MAX_NR_MAPS; i++)
-- 
cgit v1.2.3


From 2acc5fd5b8c25df0de7f3c8b8e385f5c6f8202ec Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Fri, 30 Nov 2018 21:08:39 -0800
Subject: bpf: Make more use of 'any' alignment in test_verifier.c

Use F_NEEDS_EFFICIENT_UNALIGNED_ACCESS in more tests where the
expected result is REJECT.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 44 +++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 1d1775faaf14..6bfd3242ea43 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1823,6 +1823,7 @@ static struct bpf_test tests[] = {
 		.errstr = "invalid bpf_context access",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SK_MSG,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"direct packet read for SK_MSG",
@@ -2215,6 +2216,8 @@ static struct bpf_test tests[] = {
 		},
 		.errstr = "invalid bpf_context access",
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"check cb access: half, wrong type",
@@ -3281,6 +3284,7 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.errstr = "R0 invalid mem access 'inv'",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"raw_stack: skb_load_bytes, spilled regs corruption 2",
@@ -3311,6 +3315,7 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.errstr = "R3 invalid mem access 'inv'",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"raw_stack: skb_load_bytes, spilled regs + data",
@@ -3810,6 +3815,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R2 invalid mem access 'inv'",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"direct packet access: test16 (arith on data_end)",
@@ -3993,6 +3999,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = REJECT,
 		.errstr = "invalid access to packet, off=0 size=8, R5(id=1,off=0,r=0)",
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"direct packet access: test24 (x += pkt_ptr, 5)",
@@ -5149,6 +5156,7 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=64 off=-2 size=4",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"invalid cgroup storage access 5",
@@ -5265,6 +5273,7 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=64 off=-2 size=4",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"invalid per-cpu cgroup storage access 5",
@@ -7206,6 +7215,7 @@ static struct bpf_test tests[] = {
 		.errstr = "invalid mem access 'inv'",
 		.result = REJECT,
 		.result_unpriv = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"map element value illegal alu op, 5",
@@ -7228,6 +7238,7 @@ static struct bpf_test tests[] = {
 		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 invalid mem access 'inv'",
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"map element value is preserved across register spilling",
@@ -9720,6 +9731,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_end > pkt_data', good access",
@@ -9758,6 +9770,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_end > pkt_data', bad access 2",
@@ -9776,6 +9789,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data' < pkt_end, good access",
@@ -9814,6 +9828,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data' < pkt_end, bad access 2",
@@ -9832,6 +9847,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_end < pkt_data', good access",
@@ -9886,6 +9902,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data' >= pkt_end, good access",
@@ -9922,6 +9939,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data' >= pkt_end, bad access 2",
@@ -9997,6 +10015,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data' <= pkt_end, good access",
@@ -10053,6 +10072,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_end <= pkt_data', good access",
@@ -10089,6 +10109,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_end <= pkt_data', bad access 2",
@@ -10162,6 +10183,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data > pkt_meta', good access",
@@ -10200,6 +10222,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data > pkt_meta', bad access 2",
@@ -10218,6 +10241,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_meta' < pkt_data, good access",
@@ -10256,6 +10280,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_meta' < pkt_data, bad access 2",
@@ -10274,6 +10299,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data < pkt_meta', good access",
@@ -10328,6 +10354,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_meta' >= pkt_data, good access",
@@ -10364,6 +10391,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_meta' >= pkt_data, bad access 2",
@@ -10439,6 +10467,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_meta' <= pkt_data, good access",
@@ -10495,6 +10524,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data <= pkt_meta', good access",
@@ -10531,6 +10561,7 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 offset is outside of the packet",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data <= pkt_meta', bad access 2",
@@ -10635,6 +10666,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = REJECT,
 		.errstr = "dereference of modified ctx ptr",
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"check deducing bounds from const, 8",
@@ -10648,6 +10680,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = REJECT,
 		.errstr = "dereference of modified ctx ptr",
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"check deducing bounds from const, 9",
@@ -11122,6 +11155,7 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.errstr = "R6 invalid mem access 'inv'",
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: two calls with args",
@@ -11987,6 +12021,7 @@ static struct bpf_test tests[] = {
 		.fixup_map_hash_8b = { 12, 22 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=8 off=2 size=8",
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: two calls that receive map_value via arg=ptr_stack_of_caller. test2",
@@ -12130,6 +12165,7 @@ static struct bpf_test tests[] = {
 		.fixup_map_hash_8b = { 12, 22 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=8 off=2 size=8",
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: two calls that receive map_value_ptr_or_null via arg. test1",
@@ -12301,6 +12337,7 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.retval = POINTER_VALUE,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: pkt_ptr spill into caller stack 2",
@@ -12332,6 +12369,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.errstr = "invalid access to packet",
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: pkt_ptr spill into caller stack 3",
@@ -12434,6 +12472,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.errstr = "same insn cannot be used with different",
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: pkt_ptr spill into caller stack 6",
@@ -12469,6 +12508,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.errstr = "R4 invalid mem access",
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: pkt_ptr spill into caller stack 7",
@@ -12503,6 +12543,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.errstr = "R4 invalid mem access",
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: pkt_ptr spill into caller stack 8",
@@ -12584,6 +12625,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.errstr = "invalid access to packet",
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: caller stack init to zero or map_value_or_null",
@@ -12949,6 +12991,7 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.errstr = "BPF_XADD stores into R2 pkt is not allowed",
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"xadd/w check whether src/dst got mangled, 1",
@@ -13435,6 +13478,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.errstr = "Unreleased reference",
 		.result = REJECT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"reference tracking: alloc, check, free in both subbranches",
-- 
cgit v1.2.3


From 0a68632488aa0129ed530af9ae9e8573f5650812 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Fri, 30 Nov 2018 21:08:50 -0800
Subject: bpf: Apply F_NEEDS_EFFICIENT_UNALIGNED_ACCESS to more ACCEPT test
 cases.

If a testcase has alignment problems but is expected to be ACCEPT,
verify it using F_NEEDS_EFFICIENT_UNALIGNED_ACCESS too.

Maybe in the future if we add some architecture specific code to elide
the unaligned memory access warnings during the test, we can execute
these as well.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 6bfd3242ea43..c3b038f26ece 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3918,6 +3918,7 @@ static struct bpf_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"direct packet access: test21 (x += pkt_ptr, 2)",
@@ -3943,6 +3944,7 @@ static struct bpf_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"direct packet access: test22 (x += pkt_ptr, 3)",
@@ -3973,6 +3975,7 @@ static struct bpf_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"direct packet access: test23 (x += pkt_ptr, 4)",
@@ -4025,6 +4028,7 @@ static struct bpf_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"direct packet access: test25 (marking on <, good access)",
@@ -7732,6 +7736,7 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.retval = 0 /* csum_diff of 64-byte packet */,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"helper access to variable memory: size = 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)",
@@ -9694,6 +9699,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data' > pkt_end, bad access 1",
@@ -9865,6 +9871,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_end < pkt_data', bad access 1",
@@ -9977,6 +9984,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_end >= pkt_data', bad access 1",
@@ -10034,6 +10042,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data' <= pkt_end, bad access 1",
@@ -10146,6 +10155,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_meta' > pkt_data, bad access 1",
@@ -10317,6 +10327,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data < pkt_meta', bad access 1",
@@ -10429,6 +10440,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_data >= pkt_meta', bad access 1",
@@ -10486,6 +10498,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"XDP pkt read, pkt_meta' <= pkt_data, bad access 1",
@@ -12405,6 +12418,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 		.retval = 1,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: pkt_ptr spill into caller stack 4",
@@ -12439,6 +12453,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 		.retval = 1,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: pkt_ptr spill into caller stack 5",
@@ -12584,6 +12599,7 @@ static struct bpf_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"calls: pkt_ptr spill into caller stack 9",
@@ -13507,6 +13523,7 @@ static struct bpf_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
 	{
 		"reference tracking in call: free reference in subprog",
-- 
cgit v1.2.3


From d606ee5c1d9a9bc4d1bba3c36fae615447f9851c Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Sat, 1 Dec 2018 01:23:05 +0100
Subject: samples: bpf: improve xdp1 example

Store only the total packet count for every protocol, instead of the
whole per-cpu array.
Use bpf_map_get_next_key() to iterate the map, instead of looking up
all the protocols.

Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/xdp1_user.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index b02c531510ed..4f3d824fc044 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -34,26 +34,24 @@ static void int_exit(int sig)
 static void poll_stats(int map_fd, int interval)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
-	const unsigned int nr_keys = 256;
-	__u64 values[nr_cpus], prev[nr_keys][nr_cpus];
-	__u32 key;
+	__u64 values[nr_cpus], prev[UINT8_MAX] = { 0 };
 	int i;
 
-	memset(prev, 0, sizeof(prev));
-
 	while (1) {
+		__u32 key = UINT32_MAX;
+
 		sleep(interval);
 
-		for (key = 0; key < nr_keys; key++) {
+		while (bpf_map_get_next_key(map_fd, &key, &key) != -1) {
 			__u64 sum = 0;
 
 			assert(bpf_map_lookup_elem(map_fd, &key, values) == 0);
 			for (i = 0; i < nr_cpus; i++)
-				sum += (values[i] - prev[key][i]);
-			if (sum)
+				sum += values[i];
+			if (sum > prev[key])
 				printf("proto %u: %10llu pkt/s\n",
-				       key, sum / interval);
-			memcpy(prev[key], values, sizeof(values));
+				       key, (sum - prev[key]) / interval);
+			prev[key] = sum;
 		}
 	}
 }
-- 
cgit v1.2.3


From dc378a1ab5b6009629a3f8410f8b3030ac6b14c9 Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Sat, 1 Dec 2018 01:23:06 +0100
Subject: samples: bpf: get ifindex from ifname

Find the ifindex with if_nametoindex() instead of requiring the
numeric ifindex.

Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/xdp1_user.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index 4f3d824fc044..0a197f86ac43 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -15,6 +15,7 @@
 #include <unistd.h>
 #include <libgen.h>
 #include <sys/resource.h>
+#include <net/if.h>
 
 #include "bpf_util.h"
 #include "bpf/bpf.h"
@@ -59,7 +60,7 @@ static void poll_stats(int map_fd, int interval)
 static void usage(const char *prog)
 {
 	fprintf(stderr,
-		"usage: %s [OPTS] IFINDEX\n\n"
+		"usage: %s [OPTS] IFACE\n\n"
 		"OPTS:\n"
 		"    -S    use skb-mode\n"
 		"    -N    enforce native mode\n",
@@ -102,7 +103,11 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	ifindex = strtoul(argv[optind], NULL, 0);
+	ifindex = if_nametoindex(argv[1]);
+	if (!ifindex) {
+		perror("if_nametoindex");
+		return 1;
+	}
 
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
 	prog_load_attr.file = filename;
-- 
cgit v1.2.3


From c8d1da4000b0b95bf95d3e13b7450eec5428da1e Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.ibm.com>
Date: Sun, 11 Nov 2018 11:43:59 -0800
Subject: netfilter: Replace call_rcu_bh(), rcu_barrier_bh(), and
 synchronize_rcu_bh()

Now that call_rcu()'s callback is not invoked until after bh-disable
regions of code have completed (in addition to explicitly marked
RCU read-side critical sections), call_rcu() can be used in place
of call_rcu_bh().  Similarly, rcu_barrier() can be used in place of
rcu_barrier_bh() and synchronize_rcu() in place of synchronize_rcu_bh().
This commit therefore makes these changes.

Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/ipt_CLUSTERIP.c    | 6 +++---
 net/netfilter/ipset/ip_set_hash_gen.h | 4 ++--
 net/netfilter/nfnetlink_log.c         | 2 +-
 net/netfilter/xt_hashlimit.c          | 4 ++--
 4 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 2c8d313ae216..5b0c1ee6ae26 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -94,7 +94,7 @@ static inline void
 clusterip_config_put(struct clusterip_config *c)
 {
 	if (refcount_dec_and_test(&c->refcount))
-		call_rcu_bh(&c->rcu, clusterip_config_rcu_free);
+		call_rcu(&c->rcu, clusterip_config_rcu_free);
 }
 
 /* decrease the count of entries using/referencing this config.  If last
@@ -876,8 +876,8 @@ static void __exit clusterip_tg_exit(void)
 	xt_unregister_target(&clusterip_tg_reg);
 	unregister_pernet_subsys(&clusterip_net_ops);
 
-	/* Wait for completion of call_rcu_bh()'s (clusterip_config_rcu_free) */
-	rcu_barrier_bh();
+	/* Wait for completion of call_rcu()'s (clusterip_config_rcu_free) */
+	rcu_barrier();
 }
 
 module_init(clusterip_tg_init);
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index e287da68d5fa..2c9609929c71 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -67,7 +67,7 @@ tune_ahash_max(u8 curr, u32 multi)
 
 /* A hash bucket */
 struct hbucket {
-	struct rcu_head rcu;	/* for call_rcu_bh */
+	struct rcu_head rcu;	/* for call_rcu */
 	/* Which positions are used in the array */
 	DECLARE_BITMAP(used, AHASH_MAX_TUNED);
 	u8 size;		/* size of the array */
@@ -664,7 +664,7 @@ retry:
 	spin_unlock_bh(&set->lock);
 
 	/* Give time to other readers of the set */
-	synchronize_rcu_bh();
+	synchronize_rcu();
 
 	pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name,
 		 orig->htable_bits, orig, t->htable_bits, t);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 332c69d27b47..b1f9c5303f02 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -148,7 +148,7 @@ static void
 instance_put(struct nfulnl_instance *inst)
 {
 	if (inst && refcount_dec_and_test(&inst->use))
-		call_rcu_bh(&inst->rcu, nfulnl_instance_free_rcu);
+		call_rcu(&inst->rcu, nfulnl_instance_free_rcu);
 }
 
 static void nfulnl_timer(struct timer_list *t);
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 3e7d259e5d8d..8138b68a9a44 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -260,7 +260,7 @@ static inline void
 dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent)
 {
 	hlist_del_rcu(&ent->node);
-	call_rcu_bh(&ent->rcu, dsthash_free_rcu);
+	call_rcu(&ent->rcu, dsthash_free_rcu);
 	ht->count--;
 }
 static void htable_gc(struct work_struct *work);
@@ -1329,7 +1329,7 @@ static void __exit hashlimit_mt_exit(void)
 	xt_unregister_matches(hashlimit_mt_reg, ARRAY_SIZE(hashlimit_mt_reg));
 	unregister_pernet_subsys(&hashlimit_net_ops);
 
-	rcu_barrier_bh();
+	rcu_barrier();
 	kmem_cache_destroy(hashlimit_cachep);
 }
 
-- 
cgit v1.2.3


From c3e9305983597a61083482581e83f0bd77ba306a Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 12 Nov 2018 16:26:44 +0100
Subject: netfilter: remove NFC_* cache bits

These are very very (for long time unused) caching infrastructure
definition, remove then. They have nothing to do with the NFC subsystem.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter.h        |  4 ----
 include/uapi/linux/netfilter_decnet.h | 10 ----------
 include/uapi/linux/netfilter_ipv4.h   | 28 ----------------------------
 include/uapi/linux/netfilter_ipv6.h   | 29 -----------------------------
 4 files changed, 71 deletions(-)

diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h
index cca10e767cd8..ca9e63d6e0e4 100644
--- a/include/uapi/linux/netfilter.h
+++ b/include/uapi/linux/netfilter.h
@@ -34,10 +34,6 @@
 
 /* only for userspace compatibility */
 #ifndef __KERNEL__
-/* Generic cache responses from hook functions.
-   <= 0x2000 is used for protocol-flags. */
-#define NFC_UNKNOWN 0x4000
-#define NFC_ALTERED 0x8000
 
 /* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */
 #define NF_VERDICT_BITS 16
diff --git a/include/uapi/linux/netfilter_decnet.h b/include/uapi/linux/netfilter_decnet.h
index 61f1c7dfd033..3c77f54560f2 100644
--- a/include/uapi/linux/netfilter_decnet.h
+++ b/include/uapi/linux/netfilter_decnet.h
@@ -15,16 +15,6 @@
 
 #include <limits.h> /* for INT_MIN, INT_MAX */
 
-/* IP Cache bits. */
-/* Src IP address. */
-#define NFC_DN_SRC		0x0001
-/* Dest IP address. */
-#define NFC_DN_DST		0x0002
-/* Input device. */
-#define NFC_DN_IF_IN		0x0004
-/* Output device. */
-#define NFC_DN_IF_OUT		0x0008
-
 /* kernel define is in netfilter_defs.h */
 #define NF_DN_NUMHOOKS		7
 #endif /* ! __KERNEL__ */
diff --git a/include/uapi/linux/netfilter_ipv4.h b/include/uapi/linux/netfilter_ipv4.h
index c3b060775e13..155e77d6a42d 100644
--- a/include/uapi/linux/netfilter_ipv4.h
+++ b/include/uapi/linux/netfilter_ipv4.h
@@ -13,34 +13,6 @@
 
 #include <limits.h> /* for INT_MIN, INT_MAX */
 
-/* IP Cache bits. */
-/* Src IP address. */
-#define NFC_IP_SRC		0x0001
-/* Dest IP address. */
-#define NFC_IP_DST		0x0002
-/* Input device. */
-#define NFC_IP_IF_IN		0x0004
-/* Output device. */
-#define NFC_IP_IF_OUT		0x0008
-/* TOS. */
-#define NFC_IP_TOS		0x0010
-/* Protocol. */
-#define NFC_IP_PROTO		0x0020
-/* IP options. */
-#define NFC_IP_OPTIONS		0x0040
-/* Frag & flags. */
-#define NFC_IP_FRAG		0x0080
-
-/* Per-protocol information: only matters if proto match. */
-/* TCP flags. */
-#define NFC_IP_TCPFLAGS		0x0100
-/* Source port. */
-#define NFC_IP_SRC_PT		0x0200
-/* Dest port. */
-#define NFC_IP_DST_PT		0x0400
-/* Something else about the proto */
-#define NFC_IP_PROTO_UNKNOWN	0x2000
-
 /* IP Hooks */
 /* After promisc drops, checksum checks. */
 #define NF_IP_PRE_ROUTING	0
diff --git a/include/uapi/linux/netfilter_ipv6.h b/include/uapi/linux/netfilter_ipv6.h
index dc624fd24d25..80aa9b0799af 100644
--- a/include/uapi/linux/netfilter_ipv6.h
+++ b/include/uapi/linux/netfilter_ipv6.h
@@ -16,35 +16,6 @@
 
 #include <limits.h> /* for INT_MIN, INT_MAX */
 
-/* IP Cache bits. */
-/* Src IP address. */
-#define NFC_IP6_SRC              0x0001
-/* Dest IP address. */
-#define NFC_IP6_DST              0x0002
-/* Input device. */
-#define NFC_IP6_IF_IN            0x0004
-/* Output device. */
-#define NFC_IP6_IF_OUT           0x0008
-/* TOS. */
-#define NFC_IP6_TOS              0x0010
-/* Protocol. */
-#define NFC_IP6_PROTO            0x0020
-/* IP options. */
-#define NFC_IP6_OPTIONS          0x0040
-/* Frag & flags. */
-#define NFC_IP6_FRAG             0x0080
-
-
-/* Per-protocol information: only matters if proto match. */
-/* TCP flags. */
-#define NFC_IP6_TCPFLAGS         0x0100
-/* Source port. */
-#define NFC_IP6_SRC_PT           0x0200
-/* Dest port. */
-#define NFC_IP6_DST_PT           0x0400
-/* Something else about the proto */
-#define NFC_IP6_PROTO_UNKNOWN    0x2000
-
 /* IP6 Hooks */
 /* After promisc drops, checksum checks. */
 #define NF_IP6_PRE_ROUTING	0
-- 
cgit v1.2.3


From 6ed5943f8735e2b778d92ea4d9805c0a1d89bc2b Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 15 Nov 2018 10:22:59 +0100
Subject: netfilter: nat: remove l4 protocol port rovers

This is a leftover from days where single-cpu systems were common:
Store last port used to resolve a clash to use it as a starting point when
the next conflict needs to be resolved.

When we have parallel attempt to connect to same address:port pair,
its likely that both cores end up computing the same "available" port,
as both use same starting port, and newly used ports won't become
visible to other cores until the conntrack gets confirmed later.

One of the cores then has to drop the packet at insertion time because
the chosen new tuple turns out to be in use after all.

Lets simplify this: remove port rover and use a pseudo-random starting
point.

Note that this doesn't make netfilter default to 'fully random' mode;
the 'rover' was only used if NAT could not reuse source port as-is.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l4proto.h |  2 +-
 net/netfilter/nf_nat_proto_common.c    |  8 ++------
 net/netfilter/nf_nat_proto_dccp.c      |  5 +----
 net/netfilter/nf_nat_proto_sctp.c      |  5 +----
 net/netfilter/nf_nat_proto_tcp.c       |  5 +----
 net/netfilter/nf_nat_proto_udp.c       | 10 ++--------
 6 files changed, 8 insertions(+), 27 deletions(-)

diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h
index b4d6b29bca62..7ecac2cd1020 100644
--- a/include/net/netfilter/nf_nat_l4proto.h
+++ b/include/net/netfilter/nf_nat_l4proto.h
@@ -74,7 +74,7 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
 				 struct nf_conntrack_tuple *tuple,
 				 const struct nf_nat_range2 *range,
 				 enum nf_nat_manip_type maniptype,
-				 const struct nf_conn *ct, u16 *rover);
+				 const struct nf_conn *ct);
 
 int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
 				   struct nf_nat_range2 *range);
diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c
index 5d849d835561..a7de939fa5a9 100644
--- a/net/netfilter/nf_nat_proto_common.c
+++ b/net/netfilter/nf_nat_proto_common.c
@@ -38,8 +38,7 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
 				 struct nf_conntrack_tuple *tuple,
 				 const struct nf_nat_range2 *range,
 				 enum nf_nat_manip_type maniptype,
-				 const struct nf_conn *ct,
-				 u16 *rover)
+				 const struct nf_conn *ct)
 {
 	unsigned int range_size, min, max, i;
 	__be16 *portptr;
@@ -86,16 +85,13 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
 	} else if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) {
 		off = (ntohs(*portptr) - ntohs(range->base_proto.all));
 	} else {
-		off = *rover;
+		off = prandom_u32();
 	}
 
 	for (i = 0; ; ++off) {
 		*portptr = htons(min + off % range_size);
 		if (++i != range_size && nf_nat_used_tuple(tuple, ct))
 			continue;
-		if (!(range->flags & (NF_NAT_RANGE_PROTO_RANDOM_ALL|
-					NF_NAT_RANGE_PROTO_OFFSET)))
-			*rover = off;
 		return;
 	}
 }
diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c
index 67ea0d83aa5a..7d4d2c124990 100644
--- a/net/netfilter/nf_nat_proto_dccp.c
+++ b/net/netfilter/nf_nat_proto_dccp.c
@@ -18,8 +18,6 @@
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static u_int16_t dccp_port_rover;
-
 static void
 dccp_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		  struct nf_conntrack_tuple *tuple,
@@ -27,8 +25,7 @@ dccp_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		  enum nf_nat_manip_type maniptype,
 		  const struct nf_conn *ct)
 {
-	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct,
-				    &dccp_port_rover);
+	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct);
 }
 
 static bool
diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c
index 1c5d9b65fbba..f05ad8fa7b20 100644
--- a/net/netfilter/nf_nat_proto_sctp.c
+++ b/net/netfilter/nf_nat_proto_sctp.c
@@ -12,8 +12,6 @@
 
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static u_int16_t nf_sctp_port_rover;
-
 static void
 sctp_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		  struct nf_conntrack_tuple *tuple,
@@ -21,8 +19,7 @@ sctp_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		  enum nf_nat_manip_type maniptype,
 		  const struct nf_conn *ct)
 {
-	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct,
-				    &nf_sctp_port_rover);
+	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct);
 }
 
 static bool
diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c
index f15fcd475f98..c312e6b3e2ea 100644
--- a/net/netfilter/nf_nat_proto_tcp.c
+++ b/net/netfilter/nf_nat_proto_tcp.c
@@ -18,8 +18,6 @@
 #include <net/netfilter/nf_nat_l4proto.h>
 #include <net/netfilter/nf_nat_core.h>
 
-static u16 tcp_port_rover;
-
 static void
 tcp_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		 struct nf_conntrack_tuple *tuple,
@@ -27,8 +25,7 @@ tcp_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		 enum nf_nat_manip_type maniptype,
 		 const struct nf_conn *ct)
 {
-	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct,
-				    &tcp_port_rover);
+	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct);
 }
 
 static bool
diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c
index 5790f70a83b2..208c14316359 100644
--- a/net/netfilter/nf_nat_proto_udp.c
+++ b/net/netfilter/nf_nat_proto_udp.c
@@ -17,8 +17,6 @@
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static u16 udp_port_rover;
-
 static void
 udp_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		 struct nf_conntrack_tuple *tuple,
@@ -26,8 +24,7 @@ udp_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		 enum nf_nat_manip_type maniptype,
 		 const struct nf_conn *ct)
 {
-	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct,
-				    &udp_port_rover);
+	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct);
 }
 
 static void
@@ -79,8 +76,6 @@ static bool udp_manip_pkt(struct sk_buff *skb,
 }
 
 #ifdef CONFIG_NF_NAT_PROTO_UDPLITE
-static u16 udplite_port_rover;
-
 static bool udplite_manip_pkt(struct sk_buff *skb,
 			      const struct nf_nat_l3proto *l3proto,
 			      unsigned int iphdroff, unsigned int hdroff,
@@ -104,8 +99,7 @@ udplite_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		     enum nf_nat_manip_type maniptype,
 		     const struct nf_conn *ct)
 {
-	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct,
-				    &udplite_port_rover);
+	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct);
 }
 
 const struct nf_nat_l4proto nf_nat_l4proto_udplite = {
-- 
cgit v1.2.3


From 5482e9a93c83839f94e75db712e6837e6a39962c Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Sat, 1 Dec 2018 17:08:44 -0800
Subject: bpf: Fix memleak in aux->func_info and aux->btf

The aux->func_info and aux->btf are leaked in the error out cases
during bpf_prog_load().  This patch fixes it.

Fixes: ba64e7d85252 ("bpf: btf: support proper non-jit func info")
Cc: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/syscall.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f9554d9a14e1..4445d0d084d8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1560,6 +1560,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	return err;
 
 free_used_maps:
+	kvfree(prog->aux->func_info);
+	btf_put(prog->aux->btf);
 	bpf_prog_kallsyms_del_subprogs(prog);
 	free_used_maps(prog->aux);
 free_prog:
-- 
cgit v1.2.3


From de94b651eef38b44adc20057ab5eb6d4ca672169 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Sun, 2 Dec 2018 13:02:15 -0800
Subject: libbpf: Fix license in README.rst

The whole libbpf is licensed as (LGPL-2.1 OR BSD-2-Clause). I missed it
while adding README.rst. Fix it and use same license as all other files
in libbpf do. Since I'm the only author of README.rst so far, no others'
permissions should be needed.

Fixes: 76d1b894c515 ("libbpf: Document API and ABI conventions")
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/README.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst
index 2ced9e061c4b..056f38310722 100644
--- a/tools/lib/bpf/README.rst
+++ b/tools/lib/bpf/README.rst
@@ -1,4 +1,4 @@
-.. SPDX-License-Identifier: GPL-2.0
+.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 libbpf API naming convention
 ============================
-- 
cgit v1.2.3


From e3da08d057002f9d0831949d51666c3e15dc6b29 Mon Sep 17 00:00:00 2001
From: Petar Penkov <ppenkov@google.com>
Date: Sun, 2 Dec 2018 20:18:19 -0500
Subject: bpf: allow BPF read access to qdisc pkt_len

The pkt_len field in qdisc_skb_cb stores the skb length as it will
appear on the wire after segmentation. For byte accounting, this value
is more accurate than skb->len. It is computed on entry to the TC
layer, so only valid there.

Allow read access to this field from BPF tc classifier and action
programs. The implementation is analogous to tc_classid, aside from
restricting to read access.

To distinguish it from skb->len and self-describe export as wire_len.

Changes v1->v2
  - Rename pkt_len to wire_len

Signed-off-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: Vlad Dumitrescu <vladum@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h                    |  1 +
 net/core/filter.c                           | 16 +++++++++++++++
 tools/include/uapi/linux/bpf.h              |  1 +
 tools/testing/selftests/bpf/test_verifier.c | 32 +++++++++++++++++++++++++++++
 4 files changed, 50 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8050caea7495..0183b8e70a9e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2497,6 +2497,7 @@ struct __sk_buff {
 	__u32 data_meta;
 	struct bpf_flow_keys *flow_keys;
 	__u64 tstamp;
+	__u32 wire_len;
 };
 
 struct bpf_tunnel_key {
diff --git a/net/core/filter.c b/net/core/filter.c
index bd0df75dc7b6..3d54af4c363d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5773,6 +5773,7 @@ static bool sk_filter_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, flow_keys):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 	case bpf_ctx_range(struct __sk_buff, tstamp):
+	case bpf_ctx_range(struct __sk_buff, wire_len):
 		return false;
 	}
 
@@ -5797,6 +5798,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, flow_keys):
+	case bpf_ctx_range(struct __sk_buff, wire_len):
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
 	case bpf_ctx_range(struct __sk_buff, data_end):
@@ -5843,6 +5845,7 @@ static bool lwt_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, flow_keys):
 	case bpf_ctx_range(struct __sk_buff, tstamp):
+	case bpf_ctx_range(struct __sk_buff, wire_len):
 		return false;
 	}
 
@@ -6273,6 +6276,7 @@ static bool sk_skb_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, flow_keys):
 	case bpf_ctx_range(struct __sk_buff, tstamp):
+	case bpf_ctx_range(struct __sk_buff, wire_len):
 		return false;
 	}
 
@@ -6360,6 +6364,7 @@ static bool flow_dissector_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 	case bpf_ctx_range(struct __sk_buff, tstamp):
+	case bpf_ctx_range(struct __sk_buff, wire_len):
 		return false;
 	}
 
@@ -6685,6 +6690,17 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 					      bpf_target_off(struct sk_buff,
 							     tstamp, 8,
 							     target_size));
+		break;
+
+	case offsetof(struct __sk_buff, wire_len):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, pkt_len) != 4);
+
+		off = si->off;
+		off -= offsetof(struct __sk_buff, wire_len);
+		off += offsetof(struct sk_buff, cb);
+		off += offsetof(struct qdisc_skb_cb, pkt_len);
+		*target_size = 4;
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off);
 	}
 
 	return insn - insn_buf;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 8050caea7495..0183b8e70a9e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2497,6 +2497,7 @@ struct __sk_buff {
 	__u32 data_meta;
 	struct bpf_flow_keys *flow_keys;
 	__u64 tstamp;
+	__u32 wire_len;
 };
 
 struct bpf_tunnel_key {
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index c3b038f26ece..b4b4a3f93639 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -14033,6 +14033,38 @@ static struct bpf_test tests[] = {
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
 	},
+	{
+		"check wire_len is not readable by sockets",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, wire_len)),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_context access",
+		.result = REJECT,
+	},
+	{
+		"check wire_len is readable by tc classifier",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, wire_len)),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"check wire_len is not writable by tc classifier",
+		.insns = {
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, wire_len)),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "invalid bpf_context access",
+		.errstr_unpriv = "R1 leaks addr",
+		.result = REJECT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
-- 
cgit v1.2.3


From 90b1023f68c78b9b85e364250155776c8e421176 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Mon, 3 Dec 2018 12:13:35 +0000
Subject: bpf: fix documentation for eBPF helpers

The missing indentation on the "Return" sections for bpf_map_pop_elem()
and bpf_map_peek_elem() helpers break RST and man pages generation. This
patch fixes them, and moves the description of those two helpers towards
the end of the list (even though they are somehow related to the three
first helpers for maps, the man page explicitly states that the helpers
are sorted in chronological order).

While at it, bring other minor formatting edits for eBPF helpers
documentation: mostly blank lines removal, RST formatting, or other
small nits for consistency.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h | 90 ++++++++++++++++++++++++------------------------
 1 file changed, 45 insertions(+), 45 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0183b8e70a9e..572eb2d42768 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -496,18 +496,6 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_map_pop_elem(struct bpf_map *map, void *value)
- * 	Description
- * 		Pop an element from *map*.
- * Return
- * 		0 on success, or a negative error in case of failure.
- *
- * int bpf_map_peek_elem(struct bpf_map *map, void *value)
- * 	Description
- * 		Get an element from *map* without removing it.
- * Return
- * 		0 on success, or a negative error in case of failure.
- *
  * int bpf_probe_read(void *dst, u32 size, const void *src)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
@@ -1931,9 +1919,9 @@ union bpf_attr {
  *		is set to metric from route (IPv4/IPv6 only), and ifindex
  *		is set to the device index of the nexthop from the FIB lookup.
  *
- *             *plen* argument is the size of the passed in struct.
- *             *flags* argument can be a combination of one or more of the
- *             following values:
+ *		*plen* argument is the size of the passed in struct.
+ *		*flags* argument can be a combination of one or more of the
+ *		following values:
  *
  *		**BPF_FIB_LOOKUP_DIRECT**
  *			Do a direct table lookup vs full lookup using FIB
@@ -1942,9 +1930,9 @@ union bpf_attr {
  *			Perform lookup from an egress perspective (default is
  *			ingress).
  *
- *             *ctx* is either **struct xdp_md** for XDP programs or
- *             **struct sk_buff** tc cls_act programs.
- *     Return
+ *		*ctx* is either **struct xdp_md** for XDP programs or
+ *		**struct sk_buff** tc cls_act programs.
+ *	Return
  *		* < 0 if any input argument is invalid
  *		*   0 on success (packet is forwarded, nexthop neighbor exists)
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
@@ -2089,8 +2077,8 @@ union bpf_attr {
  *		translated to a keycode using the rc keymap, and reported as
  *		an input key down event. After a period a key up event is
  *		generated. This period can be extended by calling either
- *		**bpf_rc_keydown** () again with the same values, or calling
- *		**bpf_rc_repeat** ().
+ *		**bpf_rc_keydown**\ () again with the same values, or calling
+ *		**bpf_rc_repeat**\ ().
  *
  *		Some protocols include a toggle bit, in case the button	was
  *		released and pressed again between consecutive scancodes.
@@ -2173,21 +2161,22 @@ union bpf_attr {
  *		The *flags* meaning is specific for each map type,
  *		and has to be 0 for cgroup local storage.
  *
- *		Depending on the bpf program type, a local storage area
- *		can be shared between multiple instances of the bpf program,
+ *		Depending on the BPF program type, a local storage area
+ *		can be shared between multiple instances of the BPF program,
  *		running simultaneously.
  *
  *		A user should care about the synchronization by himself.
- *		For example, by using the BPF_STX_XADD instruction to alter
+ *		For example, by using the **BPF_STX_XADD** instruction to alter
  *		the shared data.
  *	Return
- *		Pointer to the local storage area.
+ *		A pointer to the local storage area.
  *
  * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
  *	Description
- *		Select a SO_REUSEPORT sk from a	BPF_MAP_TYPE_REUSEPORT_ARRAY map
- *		It checks the selected sk is matching the incoming
- *		request in the skb.
+ *		Select a **SO_REUSEPORT** socket from a
+ *		**BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*.
+ *		It checks the selected socket is matching the incoming
+ *		request in the socket buffer.
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
@@ -2195,7 +2184,7 @@ union bpf_attr {
  *	Description
  *		Look for TCP socket matching *tuple*, optionally in a child
  *		network namespace *netns*. The return value must be checked,
- *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *		and if non-**NULL**, released via **bpf_sk_release**\ ().
  *
  *		The *ctx* should point to the context of the program, such as
  *		the skb or socket (depending on the hook in use). This is used
@@ -2221,15 +2210,15 @@ union bpf_attr {
  *		This helper is available only if the kernel was compiled with
  *		**CONFIG_NET** configuration option.
  *	Return
- *		Pointer to *struct bpf_sock*, or NULL in case of failure.
- *		For sockets with reuseport option, *struct bpf_sock*
- *		return is from reuse->socks[] using hash of the packet.
+ *		A pointer to *struct bpf_sock*, or **NULL** in case of failure.
+ *		For sockets with reuseport option, **struct bpf_sock**
+ *		return is from **reuse->socks**\ [] using hash of the packet.
  *
  * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
  *	Description
  *		Look for UDP socket matching *tuple*, optionally in a child
  *		network namespace *netns*. The return value must be checked,
- *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *		and if non-**NULL**, released via **bpf_sk_release**\ ().
  *
  *		The *ctx* should point to the context of the program, such as
  *		the skb or socket (depending on the hook in use). This is used
@@ -2255,46 +2244,57 @@ union bpf_attr {
  *		This helper is available only if the kernel was compiled with
  *		**CONFIG_NET** configuration option.
  *	Return
- *		Pointer to *struct bpf_sock*, or NULL in case of failure.
- *		For sockets with reuseport option, *struct bpf_sock*
- *		return is from reuse->socks[] using hash of the packet.
+ *		A pointer to **struct bpf_sock**, or **NULL** in case of
+ *		failure. For sockets with reuseport option, **struct bpf_sock**
+ *		return is from **reuse->socks**\ [] using hash of the packet.
  *
- * int bpf_sk_release(struct bpf_sock *sk)
+ * int bpf_sk_release(struct bpf_sock *sock)
  *	Description
- *		Release the reference held by *sock*. *sock* must be a non-NULL
- *		pointer that was returned from bpf_sk_lookup_xxx\ ().
+ *		Release the reference held by *sock*. *sock* must be a
+ *		non-**NULL** pointer that was returned from
+ *		**bpf_sk_lookup_xxx**\ ().
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
+ * int bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Pop an element from *map*.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Get an element from *map* without removing it.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
  *	Description
- *		For socket policies, insert *len* bytes into msg at offset
+ *		For socket policies, insert *len* bytes into *msg* at offset
  *		*start*.
  *
  *		If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
- *		*msg* it may want to insert metadata or options into the msg.
+ *		*msg* it may want to insert metadata or options into the *msg*.
  *		This can later be read and used by any of the lower layer BPF
  *		hooks.
  *
  *		This helper may fail if under memory pressure (a malloc
  *		fails) in these cases BPF programs will get an appropriate
  *		error and BPF programs will need to handle them.
- *
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
  * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags)
- *	 Description
+ *	Description
  *		Will remove *pop* bytes from a *msg* starting at byte *start*.
  *		This may result in **ENOMEM** errors under certain situations if
  *		an allocation and copy are required due to a full ring buffer.
  *		However, the helper will try to avoid doing the allocation
  *		if possible. Other errors can occur if input parameters are
- *		invalid either due to *start* byte not being valid part of msg
+ *		invalid either due to *start* byte not being valid part of *msg*
  *		payload and/or *pop* value being to large.
- *
  *	Return
- *		0 on success, or a negative erro in case of failure.
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
-- 
cgit v1.2.3


From 6915bf3b002bba76cbbb928a983795fdd93af49b Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Dec 2018 08:04:57 +0100
Subject: net: phy: don't allow __set_phy_supported to add unsupported modes

Currently __set_phy_supported allows to add modes w/o checking whether
the PHY supports them. This is wrong, it should never add modes but
only remove modes we don't want to support.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 42 ++++++++++++++----------------------------
 1 file changed, 14 insertions(+), 28 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 0904002b19a2..40404a8f5f5e 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1898,37 +1898,23 @@ EXPORT_SYMBOL(genphy_loopback);
 
 static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(speeds) = { 0, };
-
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       speeds);
-	linkmode_set_bit_array(phy_gbit_features_array,
-			       ARRAY_SIZE(phy_gbit_features_array),
-			       speeds);
-
-	linkmode_andnot(phydev->supported, phydev->supported, speeds);
-
 	switch (max_speed) {
-	default:
-		return -ENOTSUPP;
-	case SPEED_1000:
-		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
-				 phydev->supported);
-		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
-				 phydev->supported);
+	case SPEED_10:
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+				   phydev->supported);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+				   phydev->supported);
 		/* fall through */
 	case SPEED_100:
-		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
-				 phydev->supported);
-		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
-				 phydev->supported);
-		/* fall through */
-	case SPEED_10:
-		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
-				 phydev->supported);
-		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
-				 phydev->supported);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+				   phydev->supported);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				   phydev->supported);
+		break;
+	case SPEED_1000:
+		break;
+	default:
+		return -ENOTSUPP;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 846e980a87fc30075517d6d979548294d5461bdb Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Mon, 3 Dec 2018 07:58:59 +0000
Subject: devlink: Add 'fw_load_policy' generic parameter

Many drivers load the device's firmware image during the initialization
flow either from the flash or from the disk. Currently this option is not
controlled by the user and the driver decides from where to load the
firmware image.

'fw_load_policy' gives the ability to control this option which allows the
user to choose between different loading policies supported by the driver.

This parameter can be useful while testing and/or debugging the device. For
example, testing a firmware bug fix.

Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/devlink-params.txt | 9 +++++++++
 include/net/devlink.h                       | 4 ++++
 include/uapi/linux/devlink.h                | 5 +++++
 net/core/devlink.c                          | 5 +++++
 4 files changed, 23 insertions(+)

diff --git a/Documentation/networking/devlink-params.txt b/Documentation/networking/devlink-params.txt
index ae444ffe73ac..2d26434ddcf8 100644
--- a/Documentation/networking/devlink-params.txt
+++ b/Documentation/networking/devlink-params.txt
@@ -40,3 +40,12 @@ msix_vec_per_pf_min	[DEVICE, GENERIC]
 			for the device initialization. Value is same across all
 			physical functions (PFs) in the device.
 			Type: u32
+
+fw_load_policy		[DEVICE, GENERIC]
+			Controls the device's firmware loading policy.
+			Valid values:
+			* DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER (0)
+			  Load firmware version preferred by the driver.
+			* DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH (1)
+			  Load firmware currently stored in flash.
+			Type: u8
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 45db0c79462d..67f4293bc970 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -365,6 +365,7 @@ enum devlink_param_generic_id {
 	DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI,
 	DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
 	DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
+	DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
 
 	/* add new param generic ids above here*/
 	__DEVLINK_PARAM_GENERIC_ID_MAX,
@@ -392,6 +393,9 @@ enum devlink_param_generic_id {
 #define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME "msix_vec_per_pf_min"
 #define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE DEVLINK_PARAM_TYPE_U32
 
+#define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME "fw_load_policy"
+#define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE DEVLINK_PARAM_TYPE_U8
+
 #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate)	\
 {									\
 	.id = DEVLINK_PARAM_GENERIC_ID_##_id,				\
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 79407bbd296d..6e52d3660654 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -163,6 +163,11 @@ enum devlink_param_cmode {
 	DEVLINK_PARAM_CMODE_MAX = __DEVLINK_PARAM_CMODE_MAX - 1
 };
 
+enum devlink_param_fw_load_policy_value {
+	DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER,
+	DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH,
+};
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 3a4b29a13d31..abb0da9d7b4b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2692,6 +2692,11 @@ static const struct devlink_param devlink_param_generic[] = {
 		.name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME,
 		.type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE,
 	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
+		.name = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME,
+		.type = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE,
+	},
 };
 
 static int devlink_param_generic_verify(const struct devlink_param *param)
-- 
cgit v1.2.3


From 03bffcad491fa824eba21b68e4ed710f9eca49d8 Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Mon, 3 Dec 2018 07:59:01 +0000
Subject: mlxsw: core: Reset firmware after flash during driver initialization

After flashing new firmware during the driver initialization flow (reload
or not), the driver should do a firmware reset when it gets -EAGAIN in
order to load the new one.

Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c | 32 ++++++++++++++++++++++++++----
 drivers/net/ethernet/mellanox/mlxsw/pci.c  | 11 +---------
 2 files changed, 29 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 30f751e69698..b2e1b83525db 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -965,10 +965,11 @@ static const struct devlink_ops mlxsw_devlink_ops = {
 	.sb_occ_tc_port_bind_get	= mlxsw_devlink_sb_occ_tc_port_bind_get,
 };
 
-int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
-				   const struct mlxsw_bus *mlxsw_bus,
-				   void *bus_priv, bool reload,
-				   struct devlink *devlink)
+static int
+__mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
+				 const struct mlxsw_bus *mlxsw_bus,
+				 void *bus_priv, bool reload,
+				 struct devlink *devlink)
 {
 	const char *device_kind = mlxsw_bus_info->device_kind;
 	struct mlxsw_core *mlxsw_core;
@@ -1076,6 +1077,29 @@ err_bus_init:
 err_devlink_alloc:
 	return err;
 }
+
+int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
+				   const struct mlxsw_bus *mlxsw_bus,
+				   void *bus_priv, bool reload,
+				   struct devlink *devlink)
+{
+	bool called_again = false;
+	int err;
+
+again:
+	err = __mlxsw_core_bus_device_register(mlxsw_bus_info, mlxsw_bus,
+					       bus_priv, reload, devlink);
+	/* -EAGAIN is returned in case the FW was updated. FW needs
+	 * a reset, so lets try to call __mlxsw_core_bus_device_register()
+	 * again.
+	 */
+	if (err == -EAGAIN && !called_again) {
+		called_again = true;
+		goto again;
+	}
+
+	return err;
+}
 EXPORT_SYMBOL(mlxsw_core_bus_device_register);
 
 void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 5890fdfd62c3..66b8098c6fd2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1720,7 +1720,6 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	const char *driver_name = pdev->driver->name;
 	struct mlxsw_pci *mlxsw_pci;
-	bool called_again = false;
 	int err;
 
 	mlxsw_pci = kzalloc(sizeof(*mlxsw_pci), GFP_KERNEL);
@@ -1777,18 +1776,10 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mlxsw_pci->bus_info.dev = &pdev->dev;
 	mlxsw_pci->id = id;
 
-again:
 	err = mlxsw_core_bus_device_register(&mlxsw_pci->bus_info,
 					     &mlxsw_pci_bus, mlxsw_pci, false,
 					     NULL);
-	/* -EAGAIN is returned in case the FW was updated. FW needs
-	 * a reset, so lets try to call mlxsw_core_bus_device_register()
-	 * again.
-	 */
-	if (err == -EAGAIN && !called_again) {
-		called_again = true;
-		goto again;
-	} else if (err) {
+	if (err) {
 		dev_err(&pdev->dev, "cannot register bus device\n");
 		goto err_bus_device_register;
 	}
-- 
cgit v1.2.3


From 064501c5b6fd344cc2770194f23d620c65f2bd2c Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Mon, 3 Dec 2018 07:59:02 +0000
Subject: mlxsw: spectrum: Load firmware version based on devlink parameter

Load firmware version based on 'fw_load_policy' devlink parameter. The
driver supports these two options:
    * DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER (0)
      Default, load firmware version preferred by the driver
    * DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH (1)
      Load firmware currently stored in flash

The second option, 'flash', allow the device to run with different firmware
version than preferred by the driver for testing and/or debugging purposes.
For example, testing a firmware bug fix.

Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c     | 13 ++++++
 drivers/net/ethernet/mellanox/mlxsw/core.h     |  2 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 60 ++++++++++++++++++++++++++
 3 files changed, 75 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index b2e1b83525db..281aeb1c2386 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1036,6 +1036,12 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 			goto err_devlink_register;
 	}
 
+	if (mlxsw_driver->params_register && !reload) {
+		err = mlxsw_driver->params_register(mlxsw_core);
+		if (err)
+			goto err_register_params;
+	}
+
 	err = mlxsw_hwmon_init(mlxsw_core, mlxsw_bus_info, &mlxsw_core->hwmon);
 	if (err)
 		goto err_hwmon_init;
@@ -1058,6 +1064,9 @@ err_driver_init:
 err_thermal_init:
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
 err_hwmon_init:
+	if (mlxsw_driver->params_unregister && !reload)
+		mlxsw_driver->params_unregister(mlxsw_core);
+err_register_params:
 	if (!reload)
 		devlink_unregister(devlink);
 err_devlink_register:
@@ -1121,6 +1130,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 		mlxsw_core->driver->fini(mlxsw_core);
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
+	if (mlxsw_core->driver->params_unregister && !reload)
+		mlxsw_core->driver->params_unregister(mlxsw_core);
 	if (!reload)
 		devlink_unregister(devlink);
 	mlxsw_emad_fini(mlxsw_core);
@@ -1133,6 +1144,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 	return;
 
 reload_fail_deinit:
+	if (mlxsw_core->driver->params_unregister)
+		mlxsw_core->driver->params_unregister(mlxsw_core);
 	devlink_unregister(devlink);
 	devlink_resources_unregister(devlink, NULL);
 	devlink_free(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index c35be477856f..d811be8989b0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -282,6 +282,8 @@ struct mlxsw_driver {
 			     const struct mlxsw_config_profile *profile,
 			     u64 *p_single_size, u64 *p_double_size,
 			     u64 *p_linear_size);
+	int (*params_register)(struct mlxsw_core *mlxsw_core);
+	void (*params_unregister)(struct mlxsw_core *mlxsw_core);
 	u8 txhdr_len;
 	const struct mlxsw_config_profile *profile;
 	bool res_query_enabled;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3b3b59314125..c293ff1eed63 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -318,6 +318,7 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
 	const struct mlxsw_fw_rev *rev = &mlxsw_sp->bus_info->fw_rev;
 	const struct mlxsw_fw_rev *req_rev = mlxsw_sp->req_rev;
 	const char *fw_filename = mlxsw_sp->fw_filename;
+	union devlink_param_value value;
 	const struct firmware *firmware;
 	int err;
 
@@ -325,6 +326,15 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
 	if (!req_rev || !fw_filename)
 		return 0;
 
+	/* Don't check if devlink 'fw_load_policy' param is 'flash' */
+	err = devlink_param_driverinit_value_get(priv_to_devlink(mlxsw_sp->core),
+						 DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
+						 &value);
+	if (err)
+		return err;
+	if (value.vu8 == DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH)
+		return 0;
+
 	/* Validate driver & FW are compatible */
 	if (rev->major != req_rev->major) {
 		WARN(1, "Mismatch in major FW version [%d:%d] is never expected; Please contact support\n",
@@ -4328,6 +4338,52 @@ static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
 	return 0;
 }
 
+static int
+mlxsw_sp_devlink_param_fw_load_policy_validate(struct devlink *devlink, u32 id,
+					       union devlink_param_value val,
+					       struct netlink_ext_ack *extack)
+{
+	if ((val.vu8 != DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER) &&
+	    (val.vu8 != DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH)) {
+		NL_SET_ERR_MSG_MOD(extack, "'fw_load_policy' must be 'driver' or 'flash'");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct devlink_param mlxsw_sp_devlink_params[] = {
+	DEVLINK_PARAM_GENERIC(FW_LOAD_POLICY,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL,
+			      mlxsw_sp_devlink_param_fw_load_policy_validate),
+};
+
+static int mlxsw_sp_params_register(struct mlxsw_core *mlxsw_core)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_core);
+	union devlink_param_value value;
+	int err;
+
+	err = devlink_params_register(devlink, mlxsw_sp_devlink_params,
+				      ARRAY_SIZE(mlxsw_sp_devlink_params));
+	if (err)
+		return err;
+
+	value.vu8 = DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER;
+	devlink_param_driverinit_value_set(devlink,
+					   DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
+					   value);
+	return 0;
+}
+
+static void mlxsw_sp_params_unregister(struct mlxsw_core *mlxsw_core)
+{
+	devlink_params_unregister(priv_to_devlink(mlxsw_core),
+				  mlxsw_sp_devlink_params,
+				  ARRAY_SIZE(mlxsw_sp_devlink_params));
+}
+
 static struct mlxsw_driver mlxsw_sp1_driver = {
 	.kind				= mlxsw_sp1_driver_name,
 	.priv_size			= sizeof(struct mlxsw_sp),
@@ -4349,6 +4405,8 @@ static struct mlxsw_driver mlxsw_sp1_driver = {
 	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp1_resources_register,
 	.kvd_sizes_get			= mlxsw_sp_kvd_sizes_get,
+	.params_register		= mlxsw_sp_params_register,
+	.params_unregister		= mlxsw_sp_params_unregister,
 	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp1_config_profile,
 	.res_query_enabled		= true,
@@ -4374,6 +4432,8 @@ static struct mlxsw_driver mlxsw_sp2_driver = {
 	.sb_occ_tc_port_bind_get	= mlxsw_sp_sb_occ_tc_port_bind_get,
 	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp2_resources_register,
+	.params_register		= mlxsw_sp_params_register,
+	.params_unregister		= mlxsw_sp_params_unregister,
 	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp2_config_profile,
 	.res_query_enabled		= true,
-- 
cgit v1.2.3


From da5095d052860baa7fe2932fb1209628dd3e3813 Mon Sep 17 00:00:00 2001
From: Alexis Bauvin <abauvin@scaleway.com>
Date: Mon, 3 Dec 2018 10:54:38 +0100
Subject: udp_tunnel: add config option to bind to a device

UDP tunnel sockets are always opened unbound to a specific device. This
patch allow the socket to be bound on a custom device, which
incidentally makes UDP tunnels VRF-aware if binding to an l3mdev.

Signed-off-by: Alexis Bauvin <abauvin@scaleway.com>
Reviewed-by: Amine Kherbouche <akherbouche@scaleway.com>
Tested-by: Amine Kherbouche <akherbouche@scaleway.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp_tunnel.h  |  1 +
 net/ipv4/udp_tunnel.c     | 17 +++++++++++++++++
 net/ipv6/ip6_udp_tunnel.c | 16 ++++++++++++++++
 3 files changed, 34 insertions(+)

diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index dc8d804af3b4..b8137953fea3 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -30,6 +30,7 @@ struct udp_port_cfg {
 
 	__be16			local_udp_port;
 	__be16			peer_udp_port;
+	int			bind_ifindex;
 	unsigned int		use_udp_checksums:1,
 				use_udp6_tx_checksums:1,
 				use_udp6_rx_checksums:1,
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index d0c412fc56ad..be8b5b2157d8 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -20,6 +20,23 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
 	if (err < 0)
 		goto error;
 
+	if (cfg->bind_ifindex) {
+		struct net_device *dev;
+
+		dev = dev_get_by_index(net, cfg->bind_ifindex);
+		if (!dev) {
+			err = -ENODEV;
+			goto error;
+		}
+
+		err = kernel_setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE,
+					dev->name, strlen(dev->name) + 1);
+		dev_put(dev);
+
+		if (err < 0)
+			goto error;
+	}
+
 	udp_addr.sin_family = AF_INET;
 	udp_addr.sin_addr = cfg->local_ip;
 	udp_addr.sin_port = cfg->local_udp_port;
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index b283f293ee4a..3965d5396b0a 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -31,6 +31,22 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
 		if (err < 0)
 			goto error;
 	}
+	if (cfg->bind_ifindex) {
+		struct net_device *dev;
+
+		dev = dev_get_by_index(net, cfg->bind_ifindex);
+		if (!dev) {
+			err = -ENODEV;
+			goto error;
+		}
+
+		err = kernel_setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE,
+					dev->name, strlen(dev->name) + 1);
+		dev_put(dev);
+
+		if (err < 0)
+			goto error;
+	}
 
 	udp6_addr.sin6_family = AF_INET6;
 	memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6,
-- 
cgit v1.2.3


From 6a6d6681ac1add9655b7ab5dd0b46b54aeb1b44f Mon Sep 17 00:00:00 2001
From: Alexis Bauvin <abauvin@scaleway.com>
Date: Mon, 3 Dec 2018 10:54:39 +0100
Subject: l3mdev: add function to retreive upper master

Existing functions to retreive the l3mdev of a device did not walk the
master chain to find the upper master. This patch adds a function to
find the l3mdev, even indirect through e.g. a bridge:

+----------+
|          |
| vrf-blue |
|          |
+----+-----+
     |
     |
+----+-----+
|          |
| br-blue  |
|          |
+----+-----+
     |
     |
+----+-----+
|          |
|   eth0   |
|          |
+----------+

This will properly resolve the l3mdev of eth0 to vrf-blue.

Signed-off-by: Alexis Bauvin <abauvin@scaleway.com>
Reviewed-by: Amine Kherbouche <akherbouche@scaleway.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: Amine Kherbouche <akherbouche@scaleway.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/l3mdev.h | 22 ++++++++++++++++++++++
 net/l3mdev/l3mdev.c  | 18 ++++++++++++++++++
 2 files changed, 40 insertions(+)

diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index 3832099289c5..78fa0ac4613c 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -101,6 +101,17 @@ struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev)
 	return master;
 }
 
+int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex);
+static inline
+int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex)
+{
+	rcu_read_lock();
+	ifindex = l3mdev_master_upper_ifindex_by_index_rcu(net, ifindex);
+	rcu_read_unlock();
+
+	return ifindex;
+}
+
 u32 l3mdev_fib_table_rcu(const struct net_device *dev);
 u32 l3mdev_fib_table_by_index(struct net *net, int ifindex);
 static inline u32 l3mdev_fib_table(const struct net_device *dev)
@@ -207,6 +218,17 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex)
 	return 0;
 }
 
+static inline
+int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex)
+{
+	return 0;
+}
+static inline
+int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex)
+{
+	return 0;
+}
+
 static inline
 struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev)
 {
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index 8da86ceca33d..309dee76724e 100644
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -46,6 +46,24 @@ int l3mdev_master_ifindex_rcu(const struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(l3mdev_master_ifindex_rcu);
 
+/**
+ *	l3mdev_master_upper_ifindex_by_index - get index of upper l3 master
+ *					       device
+ *	@net: network namespace for device index lookup
+ *	@ifindex: targeted interface
+ */
+int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex)
+{
+	struct net_device *dev;
+
+	dev = dev_get_by_index_rcu(net, ifindex);
+	while (dev && !netif_is_l3_master(dev))
+		dev = netdev_master_upper_dev_get(dev);
+
+	return dev ? dev->ifindex : 0;
+}
+EXPORT_SYMBOL_GPL(l3mdev_master_upper_ifindex_by_index_rcu);
+
 /**
  *	l3mdev_fib_table - get FIB table id associated with an L3
  *                             master interface
-- 
cgit v1.2.3


From aab8cc3630e325065a70740438dc0a47035fcdc8 Mon Sep 17 00:00:00 2001
From: Alexis Bauvin <abauvin@scaleway.com>
Date: Mon, 3 Dec 2018 10:54:40 +0100
Subject: vxlan: add support for underlay in non-default VRF

Creating a VXLAN device with is underlay in the non-default VRF makes
egress route lookup fail or incorrect since it will resolve in the
default VRF, and ingress fail because the socket listens in the default
VRF.

This patch binds the underlying UDP tunnel socket to the l3mdev of the
lower device of the VXLAN device. This will listen in the proper VRF and
output traffic from said l3mdev, matching l3mdev routing rules and
looking up the correct routing table.

When the VXLAN device does not have a lower device, or the lower device
is in the default VRF, the socket will not be bound to any interface,
keeping the previous behaviour.

The underlay l3mdev is deduced from the VXLAN lower device
(IFLA_VXLAN_LINK).

+----------+                         +---------+
|          |                         |         |
| vrf-blue |                         | vrf-red |
|          |                         |         |
+----+-----+                         +----+----+
     |                                    |
     |                                    |
+----+-----+                         +----+----+
|          |                         |         |
| br-blue  |                         | br-red  |
|          |                         |         |
+----+-----+                         +---+-+---+
     |                                   | |
     |                             +-----+ +-----+
     |                             |             |
+----+-----+                +------+----+   +----+----+
|          |  lower device  |           |   |         |
|   eth0   | <- - - - - - - | vxlan-red |   | tap-red | (... more taps)
|          |                |           |   |         |
+----------+                +-----------+   +---------+

Signed-off-by: Alexis Bauvin <abauvin@scaleway.com>
Reviewed-by: Amine Kherbouche <akherbouche@scaleway.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: Amine Kherbouche <akherbouche@scaleway.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 911066299a83..901eef428280 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -188,7 +188,7 @@ static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb)
  * and enabled unshareable flags.
  */
 static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
-					  __be16 port, u32 flags)
+					  __be16 port, u32 flags, int ifindex)
 {
 	struct vxlan_sock *vs;
 
@@ -197,7 +197,8 @@ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
 	hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
 		if (inet_sk(vs->sock->sk)->inet_sport == port &&
 		    vxlan_get_sk_family(vs) == family &&
-		    vs->flags == flags)
+		    vs->flags == flags &&
+		    vs->sock->sk->sk_bound_dev_if == ifindex)
 			return vs;
 	}
 	return NULL;
@@ -237,7 +238,7 @@ static struct vxlan_dev *vxlan_find_vni(struct net *net, int ifindex,
 {
 	struct vxlan_sock *vs;
 
-	vs = vxlan_find_sock(net, family, port, flags);
+	vs = vxlan_find_sock(net, family, port, flags, ifindex);
 	if (!vs)
 		return NULL;
 
@@ -2288,6 +2289,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		struct rtable *rt;
 		__be16 df = 0;
 
+		if (!ifindex)
+			ifindex = sock4->sock->sk->sk_bound_dev_if;
+
 		rt = vxlan_get_route(vxlan, dev, sock4, skb, ifindex, tos,
 				     dst->sin.sin_addr.s_addr,
 				     &local_ip.sin.sin_addr.s_addr,
@@ -2337,6 +2341,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	} else {
 		struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
 
+		if (!ifindex)
+			ifindex = sock6->sock->sk->sk_bound_dev_if;
+
 		ndst = vxlan6_get_route(vxlan, dev, sock6, skb, ifindex, tos,
 					label, &dst->sin6.sin6_addr,
 					&local_ip.sin6.sin6_addr,
@@ -2951,7 +2958,7 @@ static const struct ethtool_ops vxlan_ethtool_ops = {
 };
 
 static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
-					__be16 port, u32 flags)
+					__be16 port, u32 flags, int ifindex)
 {
 	struct socket *sock;
 	struct udp_port_cfg udp_conf;
@@ -2969,6 +2976,7 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
 	}
 
 	udp_conf.local_udp_port = port;
+	udp_conf.bind_ifindex = ifindex;
 
 	/* Open UDP socket */
 	err = udp_sock_create(net, &udp_conf, &sock);
@@ -2980,7 +2988,8 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
 
 /* Create new listen socket if needed */
 static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
-					      __be16 port, u32 flags)
+					      __be16 port, u32 flags,
+					      int ifindex)
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_sock *vs;
@@ -2995,7 +3004,7 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
 	for (h = 0; h < VNI_HASH_SIZE; ++h)
 		INIT_HLIST_HEAD(&vs->vni_list[h]);
 
-	sock = vxlan_create_sock(net, ipv6, port, flags);
+	sock = vxlan_create_sock(net, ipv6, port, flags, ifindex);
 	if (IS_ERR(sock)) {
 		kfree(vs);
 		return ERR_CAST(sock);
@@ -3033,11 +3042,17 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	struct vxlan_sock *vs = NULL;
 	struct vxlan_dev_node *node;
+	int l3mdev_index = 0;
+
+	if (vxlan->cfg.remote_ifindex)
+		l3mdev_index = l3mdev_master_upper_ifindex_by_index(
+			vxlan->net, vxlan->cfg.remote_ifindex);
 
 	if (!vxlan->cfg.no_share) {
 		spin_lock(&vn->sock_lock);
 		vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET,
-				     vxlan->cfg.dst_port, vxlan->cfg.flags);
+				     vxlan->cfg.dst_port, vxlan->cfg.flags,
+				     l3mdev_index);
 		if (vs && !refcount_inc_not_zero(&vs->refcnt)) {
 			spin_unlock(&vn->sock_lock);
 			return -EBUSY;
@@ -3046,7 +3061,8 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 	}
 	if (!vs)
 		vs = vxlan_socket_create(vxlan->net, ipv6,
-					 vxlan->cfg.dst_port, vxlan->cfg.flags);
+					 vxlan->cfg.dst_port, vxlan->cfg.flags,
+					 l3mdev_index);
 	if (IS_ERR(vs))
 		return PTR_ERR(vs);
 #if IS_ENABLED(CONFIG_IPV6)
-- 
cgit v1.2.3


From 03f1c26b1c56936fa29675b5556c3bb08185585a Mon Sep 17 00:00:00 2001
From: Alexis Bauvin <abauvin@scaleway.com>
Date: Mon, 3 Dec 2018 10:54:41 +0100
Subject: test/net: Add script for VXLAN underlay in a VRF

This script tests the support of a VXLAN underlay in a non-default VRF.

It does so by simulating two hypervisors and two VMs, an extended L2
between the VMs with the hypervisors as VTEPs with the underlay in a
VRF, and finally by pinging the two VMs.

It also tests that moving the underlay from a VRF to another works when
down/up the VXLAN interface.

Signed-off-by: Alexis Bauvin <abauvin@scaleway.com>
Reviewed-by: Amine Kherbouche <akherbouche@scaleway.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: Amine Kherbouche <akherbouche@scaleway.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile               |   2 +-
 .../testing/selftests/net/test_vxlan_under_vrf.sh  | 129 +++++++++++++++++++++
 2 files changed, 130 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/test_vxlan_under_vrf.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 7aebbcaa91bf..ee2e27b1cd0d 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -7,7 +7,7 @@ CFLAGS += -I../../../../usr/include/
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
-TEST_PROGS += udpgro_bench.sh udpgro.sh
+TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
diff --git a/tools/testing/selftests/net/test_vxlan_under_vrf.sh b/tools/testing/selftests/net/test_vxlan_under_vrf.sh
new file mode 100755
index 000000000000..09f9ed92cbe4
--- /dev/null
+++ b/tools/testing/selftests/net/test_vxlan_under_vrf.sh
@@ -0,0 +1,129 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test is for checking VXLAN underlay in a non-default VRF.
+#
+# It simulates two hypervisors running a VM each using four network namespaces:
+# two for the HVs, two for the VMs.
+# A small VXLAN tunnel is made between the two hypervisors to have the two vms
+# in the same virtual L2:
+#
+# +-------------------+                                    +-------------------+
+# |                   |                                    |                   |
+# |    vm-1 netns     |                                    |    vm-2 netns     |
+# |                   |                                    |                   |
+# |  +-------------+  |                                    |  +-------------+  |
+# |  |   veth-hv   |  |                                    |  |   veth-hv   |  |
+# |  | 10.0.0.1/24 |  |                                    |  | 10.0.0.2/24 |  |
+# |  +-------------+  |                                    |  +-------------+  |
+# |        .          |                                    |         .         |
+# +-------------------+                                    +-------------------+
+#          .                                                         .
+#          .                                                         .
+#          .                                                         .
+# +-----------------------------------+   +------------------------------------+
+# |        .                          |   |                          .         |
+# |  +----------+                     |   |                     +----------+   |
+# |  | veth-tap |                     |   |                     | veth-tap |   |
+# |  +----+-----+                     |   |                     +----+-----+   |
+# |       |                           |   |                          |         |
+# |    +--+--+      +--------------+  |   |  +--------------+     +--+--+      |
+# |    | br0 |      | vrf-underlay |  |   |  | vrf-underlay |     | br0 |      |
+# |    +--+--+      +-------+------+  |   |  +------+-------+     +--+--+      |
+# |       |                 |         |   |         |                |         |
+# |   +---+----+    +-------+-------+ |   | +-------+-------+    +---+----+    |
+# |   | vxlan0 |....|     veth0     |.|...|.|     veth0     |....| vxlan0 |    |
+# |   +--------+    | 172.16.0.1/24 | |   | | 172.16.0.2/24 |    +--------+    |
+# |                 +---------------+ |   | +---------------+                  |
+# |                                   |   |                                    |
+# |             hv-1 netns            |   |           hv-2 netns               |
+# |                                   |   |                                    |
+# +-----------------------------------+   +------------------------------------+
+#
+# This tests both the connectivity between vm-1 and vm-2, and that the underlay
+# can be moved in and out of the vrf by unsetting and setting veth0's master.
+
+set -e
+
+cleanup() {
+    ip link del veth-hv-1 2>/dev/null || true
+    ip link del veth-tap 2>/dev/null || true
+
+    for ns in hv-1 hv-2 vm-1 vm-2; do
+        ip netns del $ns || true
+    done
+}
+
+# Clean start
+cleanup &> /dev/null
+
+[[ $1 == "clean" ]] && exit 0
+
+trap cleanup EXIT
+
+# Setup "Hypervisors" simulated with netns
+ip link add veth-hv-1 type veth peer name veth-hv-2
+setup-hv-networking() {
+    hv=$1
+
+    ip netns add hv-$hv
+    ip link set veth-hv-$hv netns hv-$hv
+    ip -netns hv-$hv link set veth-hv-$hv name veth0
+
+    ip -netns hv-$hv link add vrf-underlay type vrf table 1
+    ip -netns hv-$hv link set vrf-underlay up
+    ip -netns hv-$hv addr add 172.16.0.$hv/24 dev veth0
+    ip -netns hv-$hv link set veth0 up
+
+    ip -netns hv-$hv link add br0 type bridge
+    ip -netns hv-$hv link set br0 up
+
+    ip -netns hv-$hv link add vxlan0 type vxlan id 10 local 172.16.0.$hv dev veth0 dstport 4789
+    ip -netns hv-$hv link set vxlan0 master br0
+    ip -netns hv-$hv link set vxlan0 up
+}
+setup-hv-networking 1
+setup-hv-networking 2
+
+# Check connectivity between HVs by pinging hv-2 from hv-1
+echo -n "Checking HV connectivity                                           "
+ip netns exec hv-1 ping -c 1 -W 1 172.16.0.2 &> /dev/null || (echo "[FAIL]"; false)
+echo "[ OK ]"
+
+# Setups a "VM" simulated by a netns an a veth pair
+setup-vm() {
+    id=$1
+
+    ip netns add vm-$id
+    ip link add veth-tap type veth peer name veth-hv
+
+    ip link set veth-tap netns hv-$id
+    ip -netns hv-$id link set veth-tap master br0
+    ip -netns hv-$id link set veth-tap up
+
+    ip link set veth-hv netns vm-$id
+    ip -netns vm-$id addr add 10.0.0.$id/24 dev veth-hv
+    ip -netns vm-$id link set veth-hv up
+}
+setup-vm 1
+setup-vm 2
+
+# Setup VTEP routes to make ARP work
+bridge -netns hv-1 fdb add 00:00:00:00:00:00 dev vxlan0 dst 172.16.0.2 self permanent
+bridge -netns hv-2 fdb add 00:00:00:00:00:00 dev vxlan0 dst 172.16.0.1 self permanent
+
+echo -n "Check VM connectivity through VXLAN (underlay in the default VRF)  "
+ip netns exec vm-1 ping -c 1 -W 1 10.0.0.2 &> /dev/null || (echo "[FAIL]"; false)
+echo "[ OK ]"
+
+# Move the underlay to a non-default VRF
+ip -netns hv-1 link set veth0 vrf vrf-underlay
+ip -netns hv-1 link set veth0 down
+ip -netns hv-1 link set veth0 up
+ip -netns hv-2 link set veth0 vrf vrf-underlay
+ip -netns hv-2 link set veth0 down
+ip -netns hv-2 link set veth0 up
+
+echo -n "Check VM connectivity through VXLAN (underlay in a VRF)            "
+ip netns exec vm-1 ping -c 1 -W 1 10.0.0.2 &> /dev/null || (echo "[FAIL]"; false)
+echo "[ OK ]"
-- 
cgit v1.2.3


From d59dd69d5576d699d7d3f5da0b4738c3a36d0133 Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Mon, 3 Dec 2018 19:39:30 +0900
Subject: samples: bpf: fix: seg fault with NULL pointer arg

When NULL pointer accidentally passed to write_kprobe_events,
due to strlen(NULL), segmentation fault happens.
Changed code returns -1 to deal with this situation.

Bug issued with Smatch, static analysis.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/bpf_load.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 434ea34a5954..eae7b635343d 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -58,7 +58,9 @@ static int write_kprobe_events(const char *val)
 {
 	int fd, ret, flags;
 
-	if ((val != NULL) && (val[0] == '\0'))
+	if (val == NULL)
+		return -1;
+	else if (val[0] == '\0')
 		flags = O_WRONLY | O_TRUNC;
 	else
 		flags = O_WRONLY | O_APPEND;
-- 
cgit v1.2.3


From d1420bb9951592c6de4148de7441bfa93ce4eed5 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 27 Nov 2018 22:30:14 +0100
Subject: net: phy: improve generic EEE ethtool functions

So far the two functions consider neither member eee_enabled nor
eee_active. Therefore network drivers have to do this in some kind
of glue code. I think this can be avoided.

Getting EEE parameters:
When not advertising any EEE mode, we can't consider EEE to be enabled.
Therefore interpret "EEE enabled" as "we advertise at least one EEE
mode". It's similar with "EEE active": interpret it as "EEE modes
advertised by both link partner have at least one mode in common".

Setting EEE parameters:
If eee_enabled isn't set, don't advertise any EEE mode and restart
aneg if needed to switch off EEE. If eee_enabled is set and
data->advertised is empty (e.g. because EEE was disabled), advertise
everything we support as default. This way EEE can easily switched
on/off by doing ethtool --set-eee <if> eee on/off, w/o any additional
parameters.

The changes to both functions shouldn't break any existing user.
Once the changes have been applied, at least some users can be
simplified.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 376a0d8a2b61..e1a1e54baac2 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1144,6 +1144,7 @@ int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data)
 	if (val < 0)
 		return val;
 	data->advertised = mmd_eee_adv_to_ethtool_adv_t(val);
+	data->eee_enabled = !!data->advertised;
 
 	/* Get LP advertisement EEE */
 	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE);
@@ -1151,6 +1152,8 @@ int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data)
 		return val;
 	data->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(val);
 
+	data->eee_active = !!(data->advertised & data->lp_advertised);
+
 	return 0;
 }
 EXPORT_SYMBOL(phy_ethtool_get_eee);
@@ -1164,7 +1167,7 @@ EXPORT_SYMBOL(phy_ethtool_get_eee);
  */
 int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 {
-	int cap, old_adv, adv, ret;
+	int cap, old_adv, adv = 0, ret;
 
 	if (!phydev->drv)
 		return -EIO;
@@ -1178,10 +1181,12 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 	if (old_adv < 0)
 		return old_adv;
 
-	adv = ethtool_adv_to_mmd_eee_adv_t(data->advertised) & cap;
-
-	/* Mask prohibited EEE modes */
-	adv &= ~phydev->eee_broken_modes;
+	if (data->eee_enabled) {
+		adv = !data->advertised ? cap :
+		      ethtool_adv_to_mmd_eee_adv_t(data->advertised) & cap;
+		/* Mask prohibited EEE modes */
+		adv &= ~phydev->eee_broken_modes;
+	}
 
 	if (old_adv != adv) {
 		ret = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, adv);
-- 
cgit v1.2.3


From 1600c3e5f23e39c0ecdad237838e6366713656b7 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 29 Nov 2018 16:40:58 +0000
Subject: net: hns3: Support "ethtool -d" for HNS3 VF driver

This patch adds "ethtool -d" support for HNS3 VF Driver.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 120 +++++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  54 ++++++++++
 2 files changed, 174 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index efec1b7a6a64..417e078eac62 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -23,6 +23,58 @@ static const struct pci_device_id ae_algovf_pci_tbl[] = {
 
 MODULE_DEVICE_TABLE(pci, ae_algovf_pci_tbl);
 
+static const u32 cmdq_reg_addr_list[] = {HCLGEVF_CMDQ_TX_ADDR_L_REG,
+					 HCLGEVF_CMDQ_TX_ADDR_H_REG,
+					 HCLGEVF_CMDQ_TX_DEPTH_REG,
+					 HCLGEVF_CMDQ_TX_TAIL_REG,
+					 HCLGEVF_CMDQ_TX_HEAD_REG,
+					 HCLGEVF_CMDQ_RX_ADDR_L_REG,
+					 HCLGEVF_CMDQ_RX_ADDR_H_REG,
+					 HCLGEVF_CMDQ_RX_DEPTH_REG,
+					 HCLGEVF_CMDQ_RX_TAIL_REG,
+					 HCLGEVF_CMDQ_RX_HEAD_REG,
+					 HCLGEVF_VECTOR0_CMDQ_SRC_REG,
+					 HCLGEVF_CMDQ_INTR_STS_REG,
+					 HCLGEVF_CMDQ_INTR_EN_REG,
+					 HCLGEVF_CMDQ_INTR_GEN_REG};
+
+static const u32 common_reg_addr_list[] = {HCLGEVF_MISC_VECTOR_REG_BASE,
+					   HCLGEVF_RST_ING,
+					   HCLGEVF_GRO_EN_REG};
+
+static const u32 ring_reg_addr_list[] = {HCLGEVF_RING_RX_ADDR_L_REG,
+					 HCLGEVF_RING_RX_ADDR_H_REG,
+					 HCLGEVF_RING_RX_BD_NUM_REG,
+					 HCLGEVF_RING_RX_BD_LENGTH_REG,
+					 HCLGEVF_RING_RX_MERGE_EN_REG,
+					 HCLGEVF_RING_RX_TAIL_REG,
+					 HCLGEVF_RING_RX_HEAD_REG,
+					 HCLGEVF_RING_RX_FBD_NUM_REG,
+					 HCLGEVF_RING_RX_OFFSET_REG,
+					 HCLGEVF_RING_RX_FBD_OFFSET_REG,
+					 HCLGEVF_RING_RX_STASH_REG,
+					 HCLGEVF_RING_RX_BD_ERR_REG,
+					 HCLGEVF_RING_TX_ADDR_L_REG,
+					 HCLGEVF_RING_TX_ADDR_H_REG,
+					 HCLGEVF_RING_TX_BD_NUM_REG,
+					 HCLGEVF_RING_TX_PRIORITY_REG,
+					 HCLGEVF_RING_TX_TC_REG,
+					 HCLGEVF_RING_TX_MERGE_EN_REG,
+					 HCLGEVF_RING_TX_TAIL_REG,
+					 HCLGEVF_RING_TX_HEAD_REG,
+					 HCLGEVF_RING_TX_FBD_NUM_REG,
+					 HCLGEVF_RING_TX_OFFSET_REG,
+					 HCLGEVF_RING_TX_EBD_NUM_REG,
+					 HCLGEVF_RING_TX_EBD_OFFSET_REG,
+					 HCLGEVF_RING_TX_BD_ERR_REG,
+					 HCLGEVF_RING_EN_REG};
+
+static const u32 tqp_intr_reg_addr_list[] = {HCLGEVF_TQP_INTR_CTRL_REG,
+					     HCLGEVF_TQP_INTR_GL0_REG,
+					     HCLGEVF_TQP_INTR_GL1_REG,
+					     HCLGEVF_TQP_INTR_GL2_REG,
+					     HCLGEVF_TQP_INTR_RL_REG};
+
 static inline struct hclgevf_dev *hclgevf_ae_get_hdev(
 	struct hnae3_handle *handle)
 {
@@ -2473,6 +2525,72 @@ static unsigned long hclgevf_ae_dev_reset_cnt(struct hnae3_handle *handle)
 	return hdev->reset_count;
 }
 
+#define MAX_SEPARATE_NUM	4
+#define SEPARATOR_VALUE		0xFFFFFFFF
+#define REG_NUM_PER_LINE	4
+#define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
+
+static int hclgevf_get_regs_len(struct hnae3_handle *handle)
+{
+	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1;
+
+	return (cmdq_lines + common_lines + ring_lines * hdev->num_tqps +
+		tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE;
+}
+
+static void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
+			     void *data)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int i, j, reg_um, separator_num;
+	u32 *reg = data;
+
+	*version = hdev->fw_version;
+
+	/* fetching per-VF registers values from VF PCIe register space */
+	reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (i = 0; i < reg_um; i++)
+		*reg++ = hclgevf_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	reg_um = sizeof(common_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (i = 0; i < reg_um; i++)
+		*reg++ = hclgevf_read_dev(&hdev->hw, common_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	reg_um = sizeof(ring_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (j = 0; j < hdev->num_tqps; j++) {
+		for (i = 0; i < reg_um; i++)
+			*reg++ = hclgevf_read_dev(&hdev->hw,
+						  ring_reg_addr_list[i] +
+						  0x200 * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+
+	reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (j = 0; j < hdev->num_msi_used - 1; j++) {
+		for (i = 0; i < reg_um; i++)
+			*reg++ = hclgevf_read_dev(&hdev->hw,
+						  tqp_intr_reg_addr_list[i] +
+						  4 * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+}
+
 static const struct hnae3_ae_ops hclgevf_ops = {
 	.init_ae_dev = hclgevf_init_ae_dev,
 	.uninit_ae_dev = hclgevf_uninit_ae_dev,
@@ -2514,6 +2632,8 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.set_default_reset_request = hclgevf_set_def_reset_request,
 	.get_channels = hclgevf_get_channels,
 	.get_tqps_and_rss_info = hclgevf_get_tqps_and_rss_info,
+	.get_regs_len = hclgevf_get_regs_len,
+	.get_regs = hclgevf_get_regs,
 	.get_status = hclgevf_get_status,
 	.get_ksettings_an_result = hclgevf_get_ksettings_an_result,
 	.get_media_type = hclgevf_get_media_type,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 4517b7ea5817..787bc06944e5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -27,6 +27,60 @@
 #define HCLGEVF_VECTOR_REG_OFFSET	0x4
 #define HCLGEVF_VECTOR_VF_OFFSET		0x100000
 
+/* bar registers for cmdq */
+#define HCLGEVF_CMDQ_TX_ADDR_L_REG		0x27000
+#define HCLGEVF_CMDQ_TX_ADDR_H_REG		0x27004
+#define HCLGEVF_CMDQ_TX_DEPTH_REG		0x27008
+#define HCLGEVF_CMDQ_TX_TAIL_REG		0x27010
+#define HCLGEVF_CMDQ_TX_HEAD_REG		0x27014
+#define HCLGEVF_CMDQ_RX_ADDR_L_REG		0x27018
+#define HCLGEVF_CMDQ_RX_ADDR_H_REG		0x2701C
+#define HCLGEVF_CMDQ_RX_DEPTH_REG		0x27020
+#define HCLGEVF_CMDQ_RX_TAIL_REG		0x27024
+#define HCLGEVF_CMDQ_RX_HEAD_REG		0x27028
+#define HCLGEVF_CMDQ_INTR_SRC_REG		0x27100
+#define HCLGEVF_CMDQ_INTR_STS_REG		0x27104
+#define HCLGEVF_CMDQ_INTR_EN_REG		0x27108
+#define HCLGEVF_CMDQ_INTR_GEN_REG		0x2710C
+
+/* bar registers for common func */
+#define HCLGEVF_GRO_EN_REG			0x28000
+
+/* bar registers for rcb */
+#define HCLGEVF_RING_RX_ADDR_L_REG		0x80000
+#define HCLGEVF_RING_RX_ADDR_H_REG		0x80004
+#define HCLGEVF_RING_RX_BD_NUM_REG		0x80008
+#define HCLGEVF_RING_RX_BD_LENGTH_REG		0x8000C
+#define HCLGEVF_RING_RX_MERGE_EN_REG		0x80014
+#define HCLGEVF_RING_RX_TAIL_REG		0x80018
+#define HCLGEVF_RING_RX_HEAD_REG		0x8001C
+#define HCLGEVF_RING_RX_FBD_NUM_REG		0x80020
+#define HCLGEVF_RING_RX_OFFSET_REG		0x80024
+#define HCLGEVF_RING_RX_FBD_OFFSET_REG		0x80028
+#define HCLGEVF_RING_RX_STASH_REG		0x80030
+#define HCLGEVF_RING_RX_BD_ERR_REG		0x80034
+#define HCLGEVF_RING_TX_ADDR_L_REG		0x80040
+#define HCLGEVF_RING_TX_ADDR_H_REG		0x80044
+#define HCLGEVF_RING_TX_BD_NUM_REG		0x80048
+#define HCLGEVF_RING_TX_PRIORITY_REG		0x8004C
+#define HCLGEVF_RING_TX_TC_REG			0x80050
+#define HCLGEVF_RING_TX_MERGE_EN_REG		0x80054
+#define HCLGEVF_RING_TX_TAIL_REG		0x80058
+#define HCLGEVF_RING_TX_HEAD_REG		0x8005C
+#define HCLGEVF_RING_TX_FBD_NUM_REG		0x80060
+#define HCLGEVF_RING_TX_OFFSET_REG		0x80064
+#define HCLGEVF_RING_TX_EBD_NUM_REG		0x80068
+#define HCLGEVF_RING_TX_EBD_OFFSET_REG		0x80070
+#define HCLGEVF_RING_TX_BD_ERR_REG		0x80074
+#define HCLGEVF_RING_EN_REG			0x80090
+
+/* bar registers for tqp interrupt */
+#define HCLGEVF_TQP_INTR_CTRL_REG		0x20000
+#define HCLGEVF_TQP_INTR_GL0_REG		0x20100
+#define HCLGEVF_TQP_INTR_GL1_REG		0x20200
+#define HCLGEVF_TQP_INTR_GL2_REG		0x20300
+#define HCLGEVF_TQP_INTR_RL_REG			0x20900
+
 /* Vector0 interrupt CMDQ event source register(RW) */
 #define HCLGEVF_VECTOR0_CMDQ_SRC_REG	0x27100
 /* CMDQ register bits for RX event(=MBX event) */
-- 
cgit v1.2.3


From ea4750caa0567879ec622a0999eb58479989ad2f Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 29 Nov 2018 16:40:59 +0000
Subject: net: hns3: Adds support to dump(using ethool-d) PCIe regs in HNS3 PF
 driver

This patch adds support to dump PF PCIe registers using ethtool -d
for HNS3 PF Driver.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 120 ++++++++++++++++++++-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  56 ++++++++++
 2 files changed, 171 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 1c8cf840dff8..8432c841aa4f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -48,6 +48,62 @@ static const struct pci_device_id ae_algo_pci_tbl[] = {
 
 MODULE_DEVICE_TABLE(pci, ae_algo_pci_tbl);
 
+static const u32 cmdq_reg_addr_list[] = {HCLGE_CMDQ_TX_ADDR_L_REG,
+					 HCLGE_CMDQ_TX_ADDR_H_REG,
+					 HCLGE_CMDQ_TX_DEPTH_REG,
+					 HCLGE_CMDQ_TX_TAIL_REG,
+					 HCLGE_CMDQ_TX_HEAD_REG,
+					 HCLGE_CMDQ_RX_ADDR_L_REG,
+					 HCLGE_CMDQ_RX_ADDR_H_REG,
+					 HCLGE_CMDQ_RX_DEPTH_REG,
+					 HCLGE_CMDQ_RX_TAIL_REG,
+					 HCLGE_CMDQ_RX_HEAD_REG,
+					 HCLGE_VECTOR0_CMDQ_SRC_REG,
+					 HCLGE_CMDQ_INTR_STS_REG,
+					 HCLGE_CMDQ_INTR_EN_REG,
+					 HCLGE_CMDQ_INTR_GEN_REG};
+
+static const u32 common_reg_addr_list[] = {HCLGE_MISC_VECTOR_REG_BASE,
+					   HCLGE_VECTOR0_OTER_EN_REG,
+					   HCLGE_MISC_RESET_STS_REG,
+					   HCLGE_MISC_VECTOR_INT_STS,
+					   HCLGE_GLOBAL_RESET_REG,
+					   HCLGE_FUN_RST_ING,
+					   HCLGE_GRO_EN_REG};
+
+static const u32 ring_reg_addr_list[] = {HCLGE_RING_RX_ADDR_L_REG,
+					 HCLGE_RING_RX_ADDR_H_REG,
+					 HCLGE_RING_RX_BD_NUM_REG,
+					 HCLGE_RING_RX_BD_LENGTH_REG,
+					 HCLGE_RING_RX_MERGE_EN_REG,
+					 HCLGE_RING_RX_TAIL_REG,
+					 HCLGE_RING_RX_HEAD_REG,
+					 HCLGE_RING_RX_FBD_NUM_REG,
+					 HCLGE_RING_RX_OFFSET_REG,
+					 HCLGE_RING_RX_FBD_OFFSET_REG,
+					 HCLGE_RING_RX_STASH_REG,
+					 HCLGE_RING_RX_BD_ERR_REG,
+					 HCLGE_RING_TX_ADDR_L_REG,
+					 HCLGE_RING_TX_ADDR_H_REG,
+					 HCLGE_RING_TX_BD_NUM_REG,
+					 HCLGE_RING_TX_PRIORITY_REG,
+					 HCLGE_RING_TX_TC_REG,
+					 HCLGE_RING_TX_MERGE_EN_REG,
+					 HCLGE_RING_TX_TAIL_REG,
+					 HCLGE_RING_TX_HEAD_REG,
+					 HCLGE_RING_TX_FBD_NUM_REG,
+					 HCLGE_RING_TX_OFFSET_REG,
+					 HCLGE_RING_TX_EBD_NUM_REG,
+					 HCLGE_RING_TX_EBD_OFFSET_REG,
+					 HCLGE_RING_TX_BD_ERR_REG,
+					 HCLGE_RING_EN_REG};
+
+static const u32 tqp_intr_reg_addr_list[] = {HCLGE_TQP_INTR_CTRL_REG,
+					     HCLGE_TQP_INTR_GL0_REG,
+					     HCLGE_TQP_INTR_GL1_REG,
+					     HCLGE_TQP_INTR_GL2_REG,
+					     HCLGE_TQP_INTR_RL_REG};
+
 static const char hns3_nic_test_strs[][ETH_GSTRING_LEN] = {
 	"App    Loopback test",
 	"Serdes serial Loopback test",
@@ -7637,8 +7693,15 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 	return 0;
 }
 
+#define MAX_SEPARATE_NUM	4
+#define SEPARATOR_VALUE		0xFFFFFFFF
+#define REG_NUM_PER_LINE	4
+#define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
+
 static int hclge_get_regs_len(struct hnae3_handle *handle)
 {
+	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 	u32 regs_num_32_bit, regs_num_64_bit;
@@ -7651,15 +7714,25 @@ static int hclge_get_regs_len(struct hnae3_handle *handle)
 		return -EOPNOTSUPP;
 	}
 
-	return regs_num_32_bit * sizeof(u32) + regs_num_64_bit * sizeof(u64);
+	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1;
+
+	return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps +
+		tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE +
+		regs_num_32_bit * sizeof(u32) + regs_num_64_bit * sizeof(u64);
 }
 
 static void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
 			   void *data)
 {
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 	u32 regs_num_32_bit, regs_num_64_bit;
+	int i, j, reg_um, separator_num;
+	u32 *reg = data;
 	int ret;
 
 	*version = hdev->fw_version;
@@ -7671,16 +7744,53 @@ static void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
 		return;
 	}
 
-	ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, data);
+	/* fetching per-PF registers valus from PF PCIe register space */
+	reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (i = 0; i < reg_um; i++)
+		*reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	reg_um = sizeof(common_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (i = 0; i < reg_um; i++)
+		*reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	reg_um = sizeof(ring_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (j = 0; j < kinfo->num_tqps; j++) {
+		for (i = 0; i < reg_um; i++)
+			*reg++ = hclge_read_dev(&hdev->hw,
+						ring_reg_addr_list[i] +
+						0x200 * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+
+	reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (j = 0; j < hdev->num_msi_used - 1; j++) {
+		for (i = 0; i < reg_um; i++)
+			*reg++ = hclge_read_dev(&hdev->hw,
+						tqp_intr_reg_addr_list[i] +
+						4 * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+
+	/* fetching PF common registers values from firmware */
+	ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Get 32 bit register failed, ret = %d.\n", ret);
 		return;
 	}
 
-	data = (u32 *)data + regs_num_32_bit;
-	ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit,
-				    data);
+	reg += regs_num_32_bit;
+	ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg);
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Get 64 bit register failed, ret = %d.\n", ret);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 0dd23a1d81ea..ee6024270d5a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -28,6 +28,62 @@
 #define HCLGE_VECTOR_REG_OFFSET		0x4
 #define HCLGE_VECTOR_VF_OFFSET		0x100000
 
+#define HCLGE_CMDQ_TX_ADDR_L_REG	0x27000
+#define HCLGE_CMDQ_TX_ADDR_H_REG	0x27004
+#define HCLGE_CMDQ_TX_DEPTH_REG		0x27008
+#define HCLGE_CMDQ_TX_TAIL_REG		0x27010
+#define HCLGE_CMDQ_TX_HEAD_REG		0x27014
+#define HCLGE_CMDQ_RX_ADDR_L_REG	0x27018
+#define HCLGE_CMDQ_RX_ADDR_H_REG	0x2701C
+#define HCLGE_CMDQ_RX_DEPTH_REG		0x27020
+#define HCLGE_CMDQ_RX_TAIL_REG		0x27024
+#define HCLGE_CMDQ_RX_HEAD_REG		0x27028
+#define HCLGE_CMDQ_INTR_SRC_REG		0x27100
+#define HCLGE_CMDQ_INTR_STS_REG		0x27104
+#define HCLGE_CMDQ_INTR_EN_REG		0x27108
+#define HCLGE_CMDQ_INTR_GEN_REG		0x2710C
+
+/* bar registers for common func */
+#define HCLGE_VECTOR0_OTER_EN_REG	0x20600
+#define HCLGE_RAS_OTHER_STS_REG		0x20B00
+#define HCLGE_FUNC_RESET_STS_REG	0x20C00
+#define HCLGE_GRO_EN_REG		0x28000
+
+/* bar registers for rcb */
+#define HCLGE_RING_RX_ADDR_L_REG	0x80000
+#define HCLGE_RING_RX_ADDR_H_REG	0x80004
+#define HCLGE_RING_RX_BD_NUM_REG	0x80008
+#define HCLGE_RING_RX_BD_LENGTH_REG	0x8000C
+#define HCLGE_RING_RX_MERGE_EN_REG	0x80014
+#define HCLGE_RING_RX_TAIL_REG		0x80018
+#define HCLGE_RING_RX_HEAD_REG		0x8001C
+#define HCLGE_RING_RX_FBD_NUM_REG	0x80020
+#define HCLGE_RING_RX_OFFSET_REG	0x80024
+#define HCLGE_RING_RX_FBD_OFFSET_REG	0x80028
+#define HCLGE_RING_RX_STASH_REG		0x80030
+#define HCLGE_RING_RX_BD_ERR_REG	0x80034
+#define HCLGE_RING_TX_ADDR_L_REG	0x80040
+#define HCLGE_RING_TX_ADDR_H_REG	0x80044
+#define HCLGE_RING_TX_BD_NUM_REG	0x80048
+#define HCLGE_RING_TX_PRIORITY_REG	0x8004C
+#define HCLGE_RING_TX_TC_REG		0x80050
+#define HCLGE_RING_TX_MERGE_EN_REG	0x80054
+#define HCLGE_RING_TX_TAIL_REG		0x80058
+#define HCLGE_RING_TX_HEAD_REG		0x8005C
+#define HCLGE_RING_TX_FBD_NUM_REG	0x80060
+#define HCLGE_RING_TX_OFFSET_REG	0x80064
+#define HCLGE_RING_TX_EBD_NUM_REG	0x80068
+#define HCLGE_RING_TX_EBD_OFFSET_REG	0x80070
+#define HCLGE_RING_TX_BD_ERR_REG	0x80074
+#define HCLGE_RING_EN_REG		0x80090
+
+/* bar registers for tqp interrupt */
+#define HCLGE_TQP_INTR_CTRL_REG		0x20000
+#define HCLGE_TQP_INTR_GL0_REG		0x20100
+#define HCLGE_TQP_INTR_GL1_REG		0x20200
+#define HCLGE_TQP_INTR_GL2_REG		0x20300
+#define HCLGE_TQP_INTR_RL_REG		0x20900
+
 #define HCLGE_RSS_IND_TBL_SIZE		512
 #define HCLGE_RSS_SET_BITMAP_MSK	GENMASK(15, 0)
 #define HCLGE_RSS_KEY_SIZE		40
-- 
cgit v1.2.3


From 82208d0d54ab85d8fedbb1c9a1960bd401a4ca1a Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Fri, 30 Nov 2018 10:26:50 +1100
Subject: rhashtable: detect when object movement between tables might have
 invalidated a lookup

Some users of rhashtables might need to move an object from one table
to another -  this appears to be the reason for the incomplete usage
of NULLS markers.

To support these, we store a unique NULLS_MARKER at the end of
each chain, and when a search fails to find a match, we check
if the NULLS marker found was the expected one.  If not, the search
may not have examined all objects in the target bucket, so it is
repeated.

The unique NULLS_MARKER is derived from the address of the
head of the chain.  As this cannot be derived at load-time the
static rhnull in rht_bucket_nested() needs to be initialised
at run time.

Any caller of a lookup function must still be prepared for the
possibility that the object returned is in a different table - it
might have been there for some time.

Note that this does NOT provide support for other uses of
NULLS_MARKERs such as allocating with SLAB_TYPESAFE_BY_RCU or changing
the key of an object and re-inserting it in the same table.
These could only be done safely if new objects were inserted
at the *start* of a hash chain, and that is not currently the case.

Signed-off-by: NeilBrown <neilb@suse.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 34 ++++++++++++++++++++++++++--------
 lib/rhashtable.c           |  8 +++++---
 2 files changed, 31 insertions(+), 11 deletions(-)

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index eb7111039247..20f9c6af7473 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -75,8 +75,19 @@ struct bucket_table {
 	struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp;
 };
 
+/*
+ * NULLS_MARKER() expects a hash value with the low
+ * bits mostly likely to be significant, and it discards
+ * the msb.
+ * We git it an address, in which the bottom 2 bits are
+ * always 0, and the msb might be significant.
+ * So we shift the address down one bit to align with
+ * expectations and avoid losing a significant bit.
+ */
+#define	RHT_NULLS_MARKER(ptr)	\
+	((void *)NULLS_MARKER(((unsigned long) (ptr)) >> 1))
 #define INIT_RHT_NULLS_HEAD(ptr)	\
-	((ptr) = (typeof(ptr)) NULLS_MARKER(0))
+	((ptr) = RHT_NULLS_MARKER(&(ptr)))
 
 static inline bool rht_is_a_nulls(const struct rhash_head *ptr)
 {
@@ -471,6 +482,7 @@ static inline struct rhash_head *__rhashtable_lookup(
 		.ht = ht,
 		.key = key,
 	};
+	struct rhash_head __rcu * const *head;
 	struct bucket_table *tbl;
 	struct rhash_head *he;
 	unsigned int hash;
@@ -478,13 +490,19 @@ static inline struct rhash_head *__rhashtable_lookup(
 	tbl = rht_dereference_rcu(ht->tbl, ht);
 restart:
 	hash = rht_key_hashfn(ht, tbl, key, params);
-	rht_for_each_rcu(he, tbl, hash) {
-		if (params.obj_cmpfn ?
-		    params.obj_cmpfn(&arg, rht_obj(ht, he)) :
-		    rhashtable_compare(&arg, rht_obj(ht, he)))
-			continue;
-		return he;
-	}
+	head = rht_bucket(tbl, hash);
+	do {
+		rht_for_each_rcu_continue(he, *head, tbl, hash) {
+			if (params.obj_cmpfn ?
+			    params.obj_cmpfn(&arg, rht_obj(ht, he)) :
+			    rhashtable_compare(&arg, rht_obj(ht, he)))
+				continue;
+			return he;
+		}
+		/* An object might have been moved to a different hash chain,
+		 * while we walk along it - better check and retry.
+		 */
+	} while (he != RHT_NULLS_MARKER(head));
 
 	/* Ensure we see any new tables. */
 	smp_rmb();
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 30526afa8343..852ffa5160f1 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -1179,8 +1179,7 @@ struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
 					    unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
-	static struct rhash_head __rcu *rhnull =
-		(struct rhash_head __rcu *)NULLS_MARKER(0);
+	static struct rhash_head __rcu *rhnull;
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
 	unsigned int size = tbl->size >> tbl->nest;
 	unsigned int subhash = hash;
@@ -1198,8 +1197,11 @@ struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
 		subhash >>= shift;
 	}
 
-	if (!ntbl)
+	if (!ntbl) {
+		if (!rhnull)
+			INIT_RHT_NULLS_HEAD(rhnull);
 		return &rhnull;
+	}
 
 	return &ntbl[subhash].bucket;
 
-- 
cgit v1.2.3


From 0e839df92cf37be4adef7e661813206cd2b32d66 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Fri, 30 Nov 2018 09:20:57 +0100
Subject: net: ethernet: provide nvmem_get_mac_address()

We already have of_get_nvmem_mac_address() but some non-DT systems want
to read the MAC address from NVMEM too. Implement a generalized routine
that takes struct device as argument.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/etherdevice.h |  1 +
 net/ethernet/eth.c          | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 572e11bb8696..2c0af7b00715 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -32,6 +32,7 @@
 struct device;
 int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr);
 unsigned char *arch_get_platform_mac_address(void);
+int nvmem_get_mac_address(struct device *dev, void *addrbuf);
 u32 eth_get_headlen(void *data, unsigned int max_len);
 __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
 extern const struct header_ops eth_header_ops;
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 58933fa50bb5..4c520110b04f 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -47,6 +47,7 @@
 #include <linux/inet.h>
 #include <linux/ip.h>
 #include <linux/netdevice.h>
+#include <linux/nvmem-consumer.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
 #include <linux/errno.h>
@@ -550,3 +551,40 @@ int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr)
 	return 0;
 }
 EXPORT_SYMBOL(eth_platform_get_mac_address);
+
+/**
+ * Obtain the MAC address from an nvmem cell named 'mac-address' associated
+ * with given device.
+ *
+ * @dev:	Device with which the mac-address cell is associated.
+ * @addrbuf:	Buffer to which the MAC address will be copied on success.
+ *
+ * Returns 0 on success or a negative error number on failure.
+ */
+int nvmem_get_mac_address(struct device *dev, void *addrbuf)
+{
+	struct nvmem_cell *cell;
+	const void *mac;
+	size_t len;
+
+	cell = nvmem_cell_get(dev, "mac-address");
+	if (IS_ERR(cell))
+		return PTR_ERR(cell);
+
+	mac = nvmem_cell_read(cell, &len);
+	nvmem_cell_put(cell);
+
+	if (IS_ERR(mac))
+		return PTR_ERR(mac);
+
+	if (len != ETH_ALEN || !is_valid_ether_addr(mac)) {
+		kfree(mac);
+		return -EINVAL;
+	}
+
+	ether_addr_copy(addrbuf, mac);
+	kfree(mac);
+
+	return 0;
+}
+EXPORT_SYMBOL(nvmem_get_mac_address);
-- 
cgit v1.2.3


From cce41b8ffa4b3978dfbcbf3fd2e7397253346245 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Fri, 30 Nov 2018 09:20:58 +0100
Subject: net: cadence: switch to using nvmem_get_mac_address()

We now have a generalized helper routine to read the MAC address from
nvmem which takes struct device as argument. The nvmem subsystem will
then try device tree first before all other potential providers.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 1d86b4d5645a..d9a208f7bb40 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -4055,7 +4055,7 @@ static int macb_probe(struct platform_device *pdev)
 	if (mac) {
 		ether_addr_copy(bp->dev->dev_addr, mac);
 	} else {
-		err = of_get_nvmem_mac_address(np, bp->dev->dev_addr);
+		err = nvmem_get_mac_address(&pdev->dev, bp->dev->dev_addr);
 		if (err) {
 			if (err == -EPROBE_DEFER)
 				goto err_out_free_netdev;
-- 
cgit v1.2.3


From afa64a72b862a7a9d04f8d07fba632eaf06b23f8 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Fri, 30 Nov 2018 09:20:59 +0100
Subject: of: net: kill of_get_nvmem_mac_address()

We've switched all users to nvmem_get_mac_address(). Remove the now
dead code.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/of/of_net.c    | 39 ---------------------------------------
 include/linux/of_net.h |  6 ------
 2 files changed, 45 deletions(-)

diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c
index 53189d4022a6..810ab0fbcccb 100644
--- a/drivers/of/of_net.c
+++ b/drivers/of/of_net.c
@@ -81,42 +81,3 @@ const void *of_get_mac_address(struct device_node *np)
 	return of_get_mac_addr(np, "address");
 }
 EXPORT_SYMBOL(of_get_mac_address);
-
-/**
- * Obtain the MAC address from an nvmem provider named 'mac-address' through
- * device tree.
- * On success, copies the new address into memory pointed to by addr and
- * returns 0. Returns a negative error code otherwise.
- * @np:		Device tree node containing the nvmem-cells phandle
- * @addr:	Pointer to receive the MAC address using ether_addr_copy()
- */
-int of_get_nvmem_mac_address(struct device_node *np, void *addr)
-{
-	struct nvmem_cell *cell;
-	const void *mac;
-	size_t len;
-	int ret;
-
-	cell = of_nvmem_cell_get(np, "mac-address");
-	if (IS_ERR(cell))
-		return PTR_ERR(cell);
-
-	mac = nvmem_cell_read(cell, &len);
-
-	nvmem_cell_put(cell);
-
-	if (IS_ERR(mac))
-		return PTR_ERR(mac);
-
-	if (len < ETH_ALEN || !is_valid_ether_addr(mac)) {
-		ret = -EINVAL;
-	} else {
-		ether_addr_copy(addr, mac);
-		ret = 0;
-	}
-
-	kfree(mac);
-
-	return ret;
-}
-EXPORT_SYMBOL(of_get_nvmem_mac_address);
diff --git a/include/linux/of_net.h b/include/linux/of_net.h
index 90d81ee9e6a0..9cd72aab76fe 100644
--- a/include/linux/of_net.h
+++ b/include/linux/of_net.h
@@ -13,7 +13,6 @@
 struct net_device;
 extern int of_get_phy_mode(struct device_node *np);
 extern const void *of_get_mac_address(struct device_node *np);
-extern int of_get_nvmem_mac_address(struct device_node *np, void *addr);
 extern struct net_device *of_find_net_device_by_node(struct device_node *np);
 #else
 static inline int of_get_phy_mode(struct device_node *np)
@@ -26,11 +25,6 @@ static inline const void *of_get_mac_address(struct device_node *np)
 	return NULL;
 }
 
-static inline int of_get_nvmem_mac_address(struct device_node *np, void *addr)
-{
-	return -ENODEV;
-}
-
 static inline struct net_device *of_find_net_device_by_node(struct device_node *np)
 {
 	return NULL;
-- 
cgit v1.2.3


From 18dbfc81de708409ed82e95b418ef7092e91c2fb Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Fri, 30 Nov 2018 09:21:00 +0100
Subject: net: davinci_emac: use nvmem_get_mac_address()

All DaVinci boards still supported in board files now define nvmem
cells containing the MAC address. We want to stop using the setup
callback from at24 so the MAC address for those users will no longer
be provided over platform data. If we didn't get a valid MAC in pdata,
try nvmem before resorting to a random MAC.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/davinci_emac.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index 9153db120352..840820402cd0 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1912,11 +1912,15 @@ static int davinci_emac_probe(struct platform_device *pdev)
 		ether_addr_copy(ndev->dev_addr, priv->mac_addr);
 
 	if (!is_valid_ether_addr(priv->mac_addr)) {
-		/* Use random MAC if none passed */
-		eth_hw_addr_random(ndev);
-		memcpy(priv->mac_addr, ndev->dev_addr, ndev->addr_len);
-		dev_warn(&pdev->dev, "using random MAC addr: %pM\n",
-							priv->mac_addr);
+		/* Try nvmem if MAC wasn't passed over pdata or DT. */
+		rc = nvmem_get_mac_address(&pdev->dev, priv->mac_addr);
+		if (rc) {
+			/* Use random MAC if still none obtained. */
+			eth_hw_addr_random(ndev);
+			memcpy(priv->mac_addr, ndev->dev_addr, ndev->addr_len);
+			dev_warn(&pdev->dev, "using random MAC addr: %pM\n",
+				 priv->mac_addr);
+		}
 	}
 
 	ndev->netdev_ops = &emac_netdev_ops;
-- 
cgit v1.2.3


From b5947e5d1e710c35ea281247bd27e6975250285c Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 30 Nov 2018 15:32:39 -0500
Subject: udp: msg_zerocopy

Extend zerocopy to udp sockets. Allow setting sockopt SO_ZEROCOPY and
interpret flag MSG_ZEROCOPY.

This patch was previously part of the zerocopy RFC patchsets. Zerocopy
is not effective at small MTU. With segmentation offload building
larger datagrams, the benefit of page flipping outweights the cost of
generating a completion notification.

tools/testing/selftests/net/msg_zerocopy.sh after applying follow-on
test patch and making skb_orphan_frags_rx same as skb_orphan_frags:

    ipv4 udp -t 1
    tx=191312 (11938 MB) txc=0 zc=n
    rx=191312 (11938 MB)
    ipv4 udp -z -t 1
    tx=304507 (19002 MB) txc=304507 zc=y
    rx=304507 (19002 MB)
    ok
    ipv6 udp -t 1
    tx=174485 (10888 MB) txc=0 zc=n
    rx=174485 (10888 MB)
    ipv6 udp -z -t 1
    tx=294801 (18396 MB) txc=294801 zc=y
    rx=294801 (18396 MB)
    ok

Changes
  v1 -> v2
    - Fixup reverse christmas tree violation
  v2 -> v3
    - Split refcount avoidance optimization into separate patch
      - Fix refcount leak on error in fragmented case
        (thanks to Paolo Abeni for pointing this one out!)
      - Fix refcount inc on zero
      - Test sock_flag SOCK_ZEROCOPY directly in __ip_append_data.
        This is needed since commit 5cf4a8532c99 ("tcp: really ignore
	MSG_ZEROCOPY if no SO_ZEROCOPY") did the same for tcp.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  1 +
 net/core/skbuff.c      |  6 ++++++
 net/core/sock.c        |  5 ++++-
 net/ipv4/ip_output.c   | 23 ++++++++++++++++++++++-
 net/ipv6/ip6_output.c  | 23 ++++++++++++++++++++++-
 5 files changed, 55 insertions(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 73902acf2b71..04f52e719571 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -485,6 +485,7 @@ void sock_zerocopy_put_abort(struct ubuf_info *uarg);
 
 void sock_zerocopy_callback(struct ubuf_info *uarg, bool success);
 
+int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len);
 int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 			     struct msghdr *msg, int len,
 			     struct ubuf_info *uarg);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3c814565ed7c..1350901c5cb8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1105,6 +1105,12 @@ EXPORT_SYMBOL_GPL(sock_zerocopy_put_abort);
 extern int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 				   struct iov_iter *from, size_t length);
 
+int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len)
+{
+	return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len);
+}
+EXPORT_SYMBOL_GPL(skb_zerocopy_iter_dgram);
+
 int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 			     struct msghdr *msg, int len,
 			     struct ubuf_info *uarg)
diff --git a/net/core/sock.c b/net/core/sock.c
index 6d7e189e3cd9..f5bb89785e47 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1018,7 +1018,10 @@ set_rcvbuf:
 
 	case SO_ZEROCOPY:
 		if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) {
-			if (sk->sk_protocol != IPPROTO_TCP)
+			if (!((sk->sk_type == SOCK_STREAM &&
+			       sk->sk_protocol == IPPROTO_TCP) ||
+			      (sk->sk_type == SOCK_DGRAM &&
+			       sk->sk_protocol == IPPROTO_UDP)))
 				ret = -ENOTSUPP;
 		} else if (sk->sk_family != PF_RDS) {
 			ret = -ENOTSUPP;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 5dbec21856f4..6f843aff628c 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -867,6 +867,7 @@ static int __ip_append_data(struct sock *sk,
 			    unsigned int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
+	struct ubuf_info *uarg = NULL;
 	struct sk_buff *skb;
 
 	struct ip_options *opt = cork->opt;
@@ -916,6 +917,19 @@ static int __ip_append_data(struct sock *sk,
 	    (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM)))
 		csummode = CHECKSUM_PARTIAL;
 
+	if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) {
+		uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
+		if (!uarg)
+			return -ENOBUFS;
+		if (rt->dst.dev->features & NETIF_F_SG &&
+		    csummode == CHECKSUM_PARTIAL) {
+			paged = true;
+		} else {
+			uarg->zerocopy = 0;
+			skb_zcopy_set(skb, uarg);
+		}
+	}
+
 	cork->length += length;
 
 	/* So, what's going on in the loop below?
@@ -1006,6 +1020,7 @@ alloc_new_skb:
 			cork->tx_flags = 0;
 			skb_shinfo(skb)->tskey = tskey;
 			tskey = 0;
+			skb_zcopy_set(skb, uarg);
 
 			/*
 			 *	Find where to start putting bytes.
@@ -1068,7 +1083,7 @@ alloc_new_skb:
 				err = -EFAULT;
 				goto error;
 			}
-		} else {
+		} else if (!uarg || !uarg->zerocopy) {
 			int i = skb_shinfo(skb)->nr_frags;
 
 			err = -ENOMEM;
@@ -1098,6 +1113,10 @@ alloc_new_skb:
 			skb->data_len += copy;
 			skb->truesize += copy;
 			wmem_alloc_delta += copy;
+		} else {
+			err = skb_zerocopy_iter_dgram(skb, from, copy);
+			if (err < 0)
+				goto error;
 		}
 		offset += copy;
 		length -= copy;
@@ -1105,11 +1124,13 @@ alloc_new_skb:
 
 	if (wmem_alloc_delta)
 		refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
+	sock_zerocopy_put(uarg);
 	return 0;
 
 error_efault:
 	err = -EFAULT;
 error:
+	sock_zerocopy_put_abort(uarg);
 	cork->length -= length;
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 827a3f5ff3bb..7df04d20a91f 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1245,6 +1245,7 @@ static int __ip6_append_data(struct sock *sk,
 {
 	struct sk_buff *skb, *skb_prev = NULL;
 	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
+	struct ubuf_info *uarg = NULL;
 	int exthdrlen = 0;
 	int dst_exthdrlen = 0;
 	int hh_len;
@@ -1322,6 +1323,19 @@ emsgsize:
 	    rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
 		csummode = CHECKSUM_PARTIAL;
 
+	if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) {
+		uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
+		if (!uarg)
+			return -ENOBUFS;
+		if (rt->dst.dev->features & NETIF_F_SG &&
+		    csummode == CHECKSUM_PARTIAL) {
+			paged = true;
+		} else {
+			uarg->zerocopy = 0;
+			skb_zcopy_set(skb, uarg);
+		}
+	}
+
 	/*
 	 * Let's try using as much space as possible.
 	 * Use MTU if total length of the message fits into the MTU.
@@ -1445,6 +1459,7 @@ alloc_new_skb:
 			cork->tx_flags = 0;
 			skb_shinfo(skb)->tskey = tskey;
 			tskey = 0;
+			skb_zcopy_set(skb, uarg);
 
 			/*
 			 *	Find where to start putting bytes
@@ -1506,7 +1521,7 @@ alloc_new_skb:
 				err = -EFAULT;
 				goto error;
 			}
-		} else {
+		} else if (!uarg || !uarg->zerocopy) {
 			int i = skb_shinfo(skb)->nr_frags;
 
 			err = -ENOMEM;
@@ -1536,6 +1551,10 @@ alloc_new_skb:
 			skb->data_len += copy;
 			skb->truesize += copy;
 			wmem_alloc_delta += copy;
+		} else {
+			err = skb_zerocopy_iter_dgram(skb, from, copy);
+			if (err < 0)
+				goto error;
 		}
 		offset += copy;
 		length -= copy;
@@ -1543,11 +1562,13 @@ alloc_new_skb:
 
 	if (wmem_alloc_delta)
 		refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
+	sock_zerocopy_put(uarg);
 	return 0;
 
 error_efault:
 	err = -EFAULT;
 error:
+	sock_zerocopy_put_abort(uarg);
 	cork->length -= length;
 	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
-- 
cgit v1.2.3


From 52900d22288e7d45846037e1db277c665bbc40db Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 30 Nov 2018 15:32:40 -0500
Subject: udp: elide zerocopy operation in hot path

With MSG_ZEROCOPY, each skb holds a reference to a struct ubuf_info.
Release of its last reference triggers a completion notification.

The TCP stack in tcp_sendmsg_locked holds an extra ref independent of
the skbs, because it can build, send and free skbs within its loop,
possibly reaching refcount zero and freeing the ubuf_info too soon.

The UDP stack currently also takes this extra ref, but does not need
it as all skbs are sent after return from __ip(6)_append_data.

Avoid the extra refcount_inc and refcount_dec_and_test, and generally
the sock_zerocopy_put in the common path, by passing the initial
reference to the first skb.

This approach is taken instead of initializing the refcount to 0, as
that would generate error "refcount_t: increment on 0" on the
next skb_zcopy_set.

Changes
  v3 -> v4
    - Move skb_zcopy_set below the only kfree_skb that might cause
      a premature uarg destroy before skb_zerocopy_put_abort
      - Move the entire skb_shinfo assignment block, to keep that
        cacheline access in one place

Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 12 ++++++++----
 net/core/skbuff.c      |  9 +++++----
 net/ipv4/ip_output.c   | 22 +++++++++++-----------
 net/ipv4/tcp.c         |  2 +-
 net/ipv6/ip6_output.c  | 22 +++++++++++-----------
 5 files changed, 36 insertions(+), 31 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 04f52e719571..75d50ab7997c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -481,7 +481,7 @@ static inline void sock_zerocopy_get(struct ubuf_info *uarg)
 }
 
 void sock_zerocopy_put(struct ubuf_info *uarg);
-void sock_zerocopy_put_abort(struct ubuf_info *uarg);
+void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
 
 void sock_zerocopy_callback(struct ubuf_info *uarg, bool success);
 
@@ -1326,10 +1326,14 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb)
 	return is_zcopy ? skb_uarg(skb) : NULL;
 }
 
-static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg)
+static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg,
+				 bool *have_ref)
 {
 	if (skb && uarg && !skb_zcopy(skb)) {
-		sock_zerocopy_get(uarg);
+		if (unlikely(have_ref && *have_ref))
+			*have_ref = false;
+		else
+			sock_zerocopy_get(uarg);
 		skb_shinfo(skb)->destructor_arg = uarg;
 		skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG;
 	}
@@ -1374,7 +1378,7 @@ static inline void skb_zcopy_abort(struct sk_buff *skb)
 	struct ubuf_info *uarg = skb_zcopy(skb);
 
 	if (uarg) {
-		sock_zerocopy_put_abort(uarg);
+		sock_zerocopy_put_abort(uarg, false);
 		skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG;
 	}
 }
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1350901c5cb8..c78ce114537e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1089,7 +1089,7 @@ void sock_zerocopy_put(struct ubuf_info *uarg)
 }
 EXPORT_SYMBOL_GPL(sock_zerocopy_put);
 
-void sock_zerocopy_put_abort(struct ubuf_info *uarg)
+void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref)
 {
 	if (uarg) {
 		struct sock *sk = skb_from_uarg(uarg)->sk;
@@ -1097,7 +1097,8 @@ void sock_zerocopy_put_abort(struct ubuf_info *uarg)
 		atomic_dec(&sk->sk_zckey);
 		uarg->len--;
 
-		sock_zerocopy_put(uarg);
+		if (have_uref)
+			sock_zerocopy_put(uarg);
 	}
 }
 EXPORT_SYMBOL_GPL(sock_zerocopy_put_abort);
@@ -1137,7 +1138,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 		return err;
 	}
 
-	skb_zcopy_set(skb, uarg);
+	skb_zcopy_set(skb, uarg, NULL);
 	return skb->len - orig_len;
 }
 EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream);
@@ -1157,7 +1158,7 @@ static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig,
 			if (skb_copy_ubufs(nskb, GFP_ATOMIC))
 				return -EIO;
 		}
-		skb_zcopy_set(nskb, skb_uarg(orig));
+		skb_zcopy_set(nskb, skb_uarg(orig), NULL);
 	}
 	return 0;
 }
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 6f843aff628c..78f028bdad30 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -881,8 +881,8 @@ static int __ip_append_data(struct sock *sk,
 	int csummode = CHECKSUM_NONE;
 	struct rtable *rt = (struct rtable *)cork->dst;
 	unsigned int wmem_alloc_delta = 0;
+	bool paged, extra_uref;
 	u32 tskey = 0;
-	bool paged;
 
 	skb = skb_peek_tail(queue);
 
@@ -921,12 +921,13 @@ static int __ip_append_data(struct sock *sk,
 		uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
 		if (!uarg)
 			return -ENOBUFS;
+		extra_uref = true;
 		if (rt->dst.dev->features & NETIF_F_SG &&
 		    csummode == CHECKSUM_PARTIAL) {
 			paged = true;
 		} else {
 			uarg->zerocopy = 0;
-			skb_zcopy_set(skb, uarg);
+			skb_zcopy_set(skb, uarg, &extra_uref);
 		}
 	}
 
@@ -1015,13 +1016,6 @@ alloc_new_skb:
 			skb->csum = 0;
 			skb_reserve(skb, hh_len);
 
-			/* only the initial fragment is time stamped */
-			skb_shinfo(skb)->tx_flags = cork->tx_flags;
-			cork->tx_flags = 0;
-			skb_shinfo(skb)->tskey = tskey;
-			tskey = 0;
-			skb_zcopy_set(skb, uarg);
-
 			/*
 			 *	Find where to start putting bytes.
 			 */
@@ -1054,6 +1048,13 @@ alloc_new_skb:
 			exthdrlen = 0;
 			csummode = CHECKSUM_NONE;
 
+			/* only the initial fragment is time stamped */
+			skb_shinfo(skb)->tx_flags = cork->tx_flags;
+			cork->tx_flags = 0;
+			skb_shinfo(skb)->tskey = tskey;
+			tskey = 0;
+			skb_zcopy_set(skb, uarg, &extra_uref);
+
 			if ((flags & MSG_CONFIRM) && !skb_prev)
 				skb_set_dst_pending_confirm(skb, 1);
 
@@ -1124,13 +1125,12 @@ alloc_new_skb:
 
 	if (wmem_alloc_delta)
 		refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
-	sock_zerocopy_put(uarg);
 	return 0;
 
 error_efault:
 	err = -EFAULT;
 error:
-	sock_zerocopy_put_abort(uarg);
+	sock_zerocopy_put_abort(uarg, extra_uref);
 	cork->length -= length;
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 215e4d3b3616..dc68c408bba0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1423,7 +1423,7 @@ do_error:
 	if (copied + copied_syn)
 		goto out;
 out_err:
-	sock_zerocopy_put_abort(uarg);
+	sock_zerocopy_put_abort(uarg, true);
 	err = sk_stream_error(sk, flags, err);
 	/* make sure we wake any epoll edge trigger waiter */
 	if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7df04d20a91f..ec8c235ea891 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1258,7 +1258,7 @@ static int __ip6_append_data(struct sock *sk,
 	int csummode = CHECKSUM_NONE;
 	unsigned int maxnonfragsize, headersize;
 	unsigned int wmem_alloc_delta = 0;
-	bool paged;
+	bool paged, extra_uref;
 
 	skb = skb_peek_tail(queue);
 	if (!skb) {
@@ -1327,12 +1327,13 @@ emsgsize:
 		uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
 		if (!uarg)
 			return -ENOBUFS;
+		extra_uref = true;
 		if (rt->dst.dev->features & NETIF_F_SG &&
 		    csummode == CHECKSUM_PARTIAL) {
 			paged = true;
 		} else {
 			uarg->zerocopy = 0;
-			skb_zcopy_set(skb, uarg);
+			skb_zcopy_set(skb, uarg, &extra_uref);
 		}
 	}
 
@@ -1454,13 +1455,6 @@ alloc_new_skb:
 			skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
 				    dst_exthdrlen);
 
-			/* Only the initial fragment is time stamped */
-			skb_shinfo(skb)->tx_flags = cork->tx_flags;
-			cork->tx_flags = 0;
-			skb_shinfo(skb)->tskey = tskey;
-			tskey = 0;
-			skb_zcopy_set(skb, uarg);
-
 			/*
 			 *	Find where to start putting bytes
 			 */
@@ -1492,6 +1486,13 @@ alloc_new_skb:
 			exthdrlen = 0;
 			dst_exthdrlen = 0;
 
+			/* Only the initial fragment is time stamped */
+			skb_shinfo(skb)->tx_flags = cork->tx_flags;
+			cork->tx_flags = 0;
+			skb_shinfo(skb)->tskey = tskey;
+			tskey = 0;
+			skb_zcopy_set(skb, uarg, &extra_uref);
+
 			if ((flags & MSG_CONFIRM) && !skb_prev)
 				skb_set_dst_pending_confirm(skb, 1);
 
@@ -1562,13 +1563,12 @@ alloc_new_skb:
 
 	if (wmem_alloc_delta)
 		refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
-	sock_zerocopy_put(uarg);
 	return 0;
 
 error_efault:
 	err = -EFAULT;
 error:
-	sock_zerocopy_put_abort(uarg);
+	sock_zerocopy_put_abort(uarg, extra_uref);
 	cork->length -= length;
 	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
-- 
cgit v1.2.3


From db63e489c7aa03bab86960d6bcb6bf1fad8eea4e Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 30 Nov 2018 15:32:41 -0500
Subject: selftests: extend zerocopy tests to udp

Both msg_zerocopy and udpgso_bench have udp zerocopy variants.
Exercise these as part of the standard kselftest run.

With udp, msg_zerocopy has no control channel. Ensure that the
receiver exits after the sender by accounting for the initial
delay in starting them (in msg_zerocopy.sh).

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/msg_zerocopy.c  | 3 ++-
 tools/testing/selftests/net/msg_zerocopy.sh | 2 ++
 tools/testing/selftests/net/udpgso_bench.sh | 3 +++
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
index 406cc70c571d..4b02933cab8a 100644
--- a/tools/testing/selftests/net/msg_zerocopy.c
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -651,12 +651,13 @@ static void do_flush_datagram(int fd, int type)
 
 static void do_rx(int domain, int type, int protocol)
 {
+	const int cfg_receiver_wait_ms = 400;
 	uint64_t tstop;
 	int fd;
 
 	fd = do_setup_rx(domain, type, protocol);
 
-	tstop = gettimeofday_ms() + cfg_runtime_ms;
+	tstop = gettimeofday_ms() + cfg_runtime_ms + cfg_receiver_wait_ms;
 	do {
 		if (type == SOCK_STREAM)
 			do_flush_tcp(fd);
diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh
index c43c6debda06..825ffec85cea 100755
--- a/tools/testing/selftests/net/msg_zerocopy.sh
+++ b/tools/testing/selftests/net/msg_zerocopy.sh
@@ -25,6 +25,8 @@ readonly path_sysctl_mem="net.core.optmem_max"
 if [[ "$#" -eq "0" ]]; then
 	$0 4 tcp -t 1
 	$0 6 tcp -t 1
+	$0 4 udp -t 1
+	$0 6 udp -t 1
 	echo "OK. All tests passed"
 	exit 0
 fi
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 0f0628613f81..5670a9ffd8eb 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -35,6 +35,9 @@ run_udp() {
 
 	echo "udp gso"
 	run_in_netns ${args} -S 0
+
+	echo "udp gso zerocopy"
+	run_in_netns ${args} -S 0 -z
 }
 
 run_tcp() {
-- 
cgit v1.2.3


From c5e4e4d1060b9b6937db54829c66f5f2429ad2fc Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@marvell.com>
Date: Sun, 2 Dec 2018 18:17:36 +0530
Subject: octeontx2-af: Skip NIXLF check for bcast MCE entry

At the time of initial broadcast packet replication table init,
NIXLFs are not yet attached to PF_FUNCs. Hence skipped checking
NIXLF while submitting MCE entry init instruction to NIX admin queue.

Also did a minor cleanup while installing bcast match entry in
packet parser unit i.e NPC.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c | 14 +++++++++-----
 drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c |  2 +-
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 962a82f7d141..183331448cf0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -431,9 +431,8 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
 	bool ena;
 	u64 cfg;
 
-	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
-	if (!pfvf->nixlf || blkaddr < 0)
+	if (blkaddr < 0)
 		return NIX_AF_ERR_AF_LF_INVALID;
 
 	block = &hw->block[blkaddr];
@@ -443,9 +442,14 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
 		return NIX_AF_ERR_AQ_ENQUEUE;
 	}
 
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	nixlf = rvu_get_lf(rvu, block, pcifunc, 0);
-	if (nixlf < 0)
-		return NIX_AF_ERR_AF_LF_INVALID;
+
+	/* Skip NIXLF check for broadcast MCE entry init */
+	if (!(!rsp && req->ctype == NIX_AQ_CTYPE_MCE)) {
+		if (!pfvf->nixlf || nixlf < 0)
+			return NIX_AF_ERR_AF_LF_INVALID;
+	}
 
 	switch (req->ctype) {
 	case NIX_AQ_CTYPE_RQ:
@@ -1295,7 +1299,7 @@ static int nix_setup_mce(struct rvu *rvu, int mce, u8 op,
 	struct nix_aq_enq_req aq_req;
 	int err;
 
-	aq_req.hdr.pcifunc = pcifunc;
+	aq_req.hdr.pcifunc = 0;
 	aq_req.ctype = NIX_AQ_CTYPE_MCE;
 	aq_req.op = op;
 	aq_req.qidx = mce;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 6ea2b0e2df42..ee2600d93d54 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -476,7 +476,7 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 	 *
 	 */
 	entry.kw[0] = BIT_ULL(13) | chan;
-	entry.kw_mask[0] = ~entry.kw[0] & (BIT_ULL(13) | 0xFFFULL);
+	entry.kw_mask[0] = BIT_ULL(13) | 0xFFFULL;
 
 	*(u64 *)&action = 0x00;
 #ifdef MCAST_MCE
-- 
cgit v1.2.3


From bd522d68704deda0f10e02ded55935469485f77a Mon Sep 17 00:00:00 2001
From: Jerin Jacob <jerinjacobk@gmail.com>
Date: Sun, 2 Dec 2018 18:17:37 +0530
Subject: octeontx2-af: Add response for RSS flow key cfg message

Added response for nix_rss_flowkey_cfg message to return
selected RSS algorithm index.

The FLOW_KEY_TYPE* definition is part of the mbox message and
it will be used by the other consumers of AF driver hence moving to mbox.h.

Also renamed FLOW_* definitions to NIX_FLOW_* to avoid global
name space collisions, as we have various coming from
include/uapi/linux/pkt_cls.h for example.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/common.h |  28 ++---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  14 ++-
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |   2 +-
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 115 +++++++++++----------
 4 files changed, 86 insertions(+), 73 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index 9bddb032dd7e..ceb3f1dbede5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -193,26 +193,18 @@ enum nix_scheduler {
 #define DEFAULT_RSS_CONTEXT_GROUP	0
 #define MAX_RSS_INDIR_TBL_SIZE		256 /* 1 << Max adder bits */
 
-/* NIX flow tag, key type flags */
-#define FLOW_KEY_TYPE_PORT	BIT(0)
-#define FLOW_KEY_TYPE_IPV4	BIT(1)
-#define FLOW_KEY_TYPE_IPV6	BIT(2)
-#define FLOW_KEY_TYPE_TCP	BIT(3)
-#define FLOW_KEY_TYPE_UDP	BIT(4)
-#define FLOW_KEY_TYPE_SCTP	BIT(5)
-
 /* NIX flow tag algorithm indices, max is 31 */
 enum {
-	FLOW_KEY_ALG_PORT,
-	FLOW_KEY_ALG_IP,
-	FLOW_KEY_ALG_TCP,
-	FLOW_KEY_ALG_UDP,
-	FLOW_KEY_ALG_SCTP,
-	FLOW_KEY_ALG_TCP_UDP,
-	FLOW_KEY_ALG_TCP_SCTP,
-	FLOW_KEY_ALG_UDP_SCTP,
-	FLOW_KEY_ALG_TCP_UDP_SCTP,
-	FLOW_KEY_ALG_MAX,
+	NIX_FLOW_KEY_ALG_PORT,
+	NIX_FLOW_KEY_ALG_IP,
+	NIX_FLOW_KEY_ALG_TCP,
+	NIX_FLOW_KEY_ALG_UDP,
+	NIX_FLOW_KEY_ALG_SCTP,
+	NIX_FLOW_KEY_ALG_TCP_UDP,
+	NIX_FLOW_KEY_ALG_TCP_SCTP,
+	NIX_FLOW_KEY_ALG_UDP_SCTP,
+	NIX_FLOW_KEY_ALG_TCP_UDP_SCTP,
+	NIX_FLOW_KEY_ALG_MAX,
 };
 
 #endif /* COMMON_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 292c13a901df..76081ac8af48 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -193,7 +193,8 @@ M(NIX_TXSCHQ_CFG,	0x8006, nix_txschq_cfg, nix_txschq_config, msg_rsp)  \
 M(NIX_STATS_RST,	0x8007, nix_stats_rst, msg_req, msg_rsp)	\
 M(NIX_VTAG_CFG,		0x8008, nix_vtag_cfg, nix_vtag_config, msg_rsp)	\
 M(NIX_RSS_FLOWKEY_CFG,  0x8009, nix_rss_flowkey_cfg,			\
-				 nix_rss_flowkey_cfg, msg_rsp)		\
+				 nix_rss_flowkey_cfg,			\
+				 nix_rss_flowkey_cfg_rsp)		\
 M(NIX_SET_MAC_ADDR,	0x800a, nix_set_mac_addr, nix_set_mac_addr, msg_rsp) \
 M(NIX_SET_RX_MODE,	0x800b, nix_set_rx_mode, nix_rx_mode, msg_rsp)	\
 M(NIX_SET_HW_FRS,	0x800c, nix_set_hw_frs, nix_frs_cfg, msg_rsp)	\
@@ -560,10 +561,21 @@ struct nix_vtag_config {
 struct nix_rss_flowkey_cfg {
 	struct mbox_msghdr hdr;
 	int	mcam_index;  /* MCAM entry index to modify */
+#define NIX_FLOW_KEY_TYPE_PORT	BIT(0)
+#define NIX_FLOW_KEY_TYPE_IPV4	BIT(1)
+#define NIX_FLOW_KEY_TYPE_IPV6	BIT(2)
+#define NIX_FLOW_KEY_TYPE_TCP	BIT(3)
+#define NIX_FLOW_KEY_TYPE_UDP	BIT(4)
+#define NIX_FLOW_KEY_TYPE_SCTP	BIT(5)
 	u32	flowkey_cfg; /* Flowkey types selected */
 	u8	group;       /* RSS context or group */
 };
 
+struct nix_rss_flowkey_cfg_rsp {
+	struct mbox_msghdr hdr;
+	u8	alg_idx; /* Selected algo index */
+};
+
 struct nix_set_mac_addr {
 	struct mbox_msghdr hdr;
 	u8 mac_addr[ETH_ALEN]; /* MAC address to be set for this pcifunc */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index ae8e2e206c87..48dbbaa9dd4d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -398,7 +398,7 @@ int rvu_mbox_handler_nix_rxvlan_alloc(struct rvu *rvu, struct msg_req *req,
 				      struct msg_rsp *rsp);
 int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
 					 struct nix_rss_flowkey_cfg *req,
-					 struct msg_rsp *rsp);
+					 struct nix_rss_flowkey_cfg_rsp *rsp);
 int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu,
 				      struct nix_set_mac_addr *req,
 				      struct msg_rsp *rsp);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 183331448cf0..f23e095b8a95 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -1601,32 +1601,35 @@ static int get_flowkey_alg_idx(u32 flow_cfg)
 {
 	u32 ip_cfg;
 
-	flow_cfg &= ~FLOW_KEY_TYPE_PORT;
-	ip_cfg = FLOW_KEY_TYPE_IPV4 | FLOW_KEY_TYPE_IPV6;
+	flow_cfg &= ~NIX_FLOW_KEY_TYPE_PORT;
+	ip_cfg = NIX_FLOW_KEY_TYPE_IPV4 | NIX_FLOW_KEY_TYPE_IPV6;
 	if (flow_cfg == ip_cfg)
-		return FLOW_KEY_ALG_IP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_TCP))
-		return FLOW_KEY_ALG_TCP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_UDP))
-		return FLOW_KEY_ALG_UDP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_SCTP))
-		return FLOW_KEY_ALG_SCTP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_TCP | FLOW_KEY_TYPE_UDP))
-		return FLOW_KEY_ALG_TCP_UDP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_TCP | FLOW_KEY_TYPE_SCTP))
-		return FLOW_KEY_ALG_TCP_SCTP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_UDP | FLOW_KEY_TYPE_SCTP))
-		return FLOW_KEY_ALG_UDP_SCTP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_TCP |
-			      FLOW_KEY_TYPE_UDP | FLOW_KEY_TYPE_SCTP))
-		return FLOW_KEY_ALG_TCP_UDP_SCTP;
-
-	return FLOW_KEY_ALG_PORT;
+		return NIX_FLOW_KEY_ALG_IP;
+	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_TCP))
+		return NIX_FLOW_KEY_ALG_TCP;
+	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_UDP))
+		return NIX_FLOW_KEY_ALG_UDP;
+	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_SCTP))
+		return NIX_FLOW_KEY_ALG_SCTP;
+	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_TCP |
+			      NIX_FLOW_KEY_TYPE_UDP))
+		return NIX_FLOW_KEY_ALG_TCP_UDP;
+	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_TCP |
+			      NIX_FLOW_KEY_TYPE_SCTP))
+		return NIX_FLOW_KEY_ALG_TCP_SCTP;
+	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_UDP |
+			      NIX_FLOW_KEY_TYPE_SCTP))
+		return NIX_FLOW_KEY_ALG_UDP_SCTP;
+	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_TCP |
+			      NIX_FLOW_KEY_TYPE_UDP | NIX_FLOW_KEY_TYPE_SCTP))
+		return NIX_FLOW_KEY_ALG_TCP_UDP_SCTP;
+
+	return NIX_FLOW_KEY_ALG_PORT;
 }
 
 int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
 					 struct nix_rss_flowkey_cfg *req,
-					 struct msg_rsp *rsp)
+					 struct nix_rss_flowkey_cfg_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
 	u16 pcifunc = req->hdr.pcifunc;
@@ -1641,7 +1644,7 @@ int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
 		return NIX_AF_ERR_AF_LF_INVALID;
 
 	alg_idx = get_flowkey_alg_idx(req->flowkey_cfg);
-
+	rsp->alg_idx = alg_idx;
 	rvu_npc_update_flowkey_alg_idx(rvu, pcifunc, nixlf, req->group,
 				       alg_idx, req->mcam_index);
 	return 0;
@@ -1674,13 +1677,13 @@ static void set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
 		if (!key_type)
 			continue;
 		switch (key_type) {
-		case FLOW_KEY_TYPE_PORT:
+		case NIX_FLOW_KEY_TYPE_PORT:
 			field = &alg[0];
 			field->sel_chan = true;
 			/* This should be set to 1, when SEL_CHAN is set */
 			field->bytesm1 = 1;
 			break;
-		case FLOW_KEY_TYPE_IPV4:
+		case NIX_FLOW_KEY_TYPE_IPV4:
 			field = &alg[0];
 			field->lid = NPC_LID_LC;
 			field->ltype_match = NPC_LT_LC_IP;
@@ -1688,7 +1691,7 @@ static void set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
 			field->bytesm1 = 7; /* SIP + DIP, 8 bytes */
 			field->ltype_mask = 0xF; /* Match only IPv4 */
 			break;
-		case FLOW_KEY_TYPE_IPV6:
+		case NIX_FLOW_KEY_TYPE_IPV6:
 			field = &alg[1];
 			field->lid = NPC_LID_LC;
 			field->ltype_match = NPC_LT_LC_IP6;
@@ -1696,17 +1699,17 @@ static void set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
 			field->bytesm1 = 31; /* SIP + DIP, 32 bytes */
 			field->ltype_mask = 0xF; /* Match only IPv6 */
 			break;
-		case FLOW_KEY_TYPE_TCP:
-		case FLOW_KEY_TYPE_UDP:
-		case FLOW_KEY_TYPE_SCTP:
+		case NIX_FLOW_KEY_TYPE_TCP:
+		case NIX_FLOW_KEY_TYPE_UDP:
+		case NIX_FLOW_KEY_TYPE_SCTP:
 			field = &alg[2];
 			field->lid = NPC_LID_LD;
 			field->bytesm1 = 3; /* Sport + Dport, 4 bytes */
-			if (key_type == FLOW_KEY_TYPE_TCP)
+			if (key_type == NIX_FLOW_KEY_TYPE_TCP)
 				field->ltype_match |= NPC_LT_LD_TCP;
-			else if (key_type == FLOW_KEY_TYPE_UDP)
+			else if (key_type == NIX_FLOW_KEY_TYPE_UDP)
 				field->ltype_match |= NPC_LT_LD_UDP;
-			else if (key_type == FLOW_KEY_TYPE_SCTP)
+			else if (key_type == NIX_FLOW_KEY_TYPE_SCTP)
 				field->ltype_match |= NPC_LT_LD_SCTP;
 			field->key_offset = 32; /* After IPv4/v6 SIP, DIP */
 			field->ltype_mask = ~field->ltype_match;
@@ -1721,15 +1724,15 @@ static void set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
 static void nix_rx_flowkey_alg_cfg(struct rvu *rvu, int blkaddr)
 {
 #define FIELDS_PER_ALG	5
-	u64 field[FLOW_KEY_ALG_MAX][FIELDS_PER_ALG];
+	u64 field[NIX_FLOW_KEY_ALG_MAX][FIELDS_PER_ALG];
 	u32 flowkey_cfg, minkey_cfg;
 	int alg, fid;
 
-	memset(&field, 0, sizeof(u64) * FLOW_KEY_ALG_MAX * FIELDS_PER_ALG);
+	memset(&field, 0, sizeof(u64) * NIX_FLOW_KEY_ALG_MAX * FIELDS_PER_ALG);
 
 	/* Only incoming channel number */
-	flowkey_cfg = FLOW_KEY_TYPE_PORT;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_PORT], flowkey_cfg);
+	flowkey_cfg = NIX_FLOW_KEY_TYPE_PORT;
+	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_PORT], flowkey_cfg);
 
 	/* For a incoming pkt if none of the fields match then flowkey
 	 * will be zero, hence tag generated will also be zero.
@@ -1738,41 +1741,47 @@ static void nix_rx_flowkey_alg_cfg(struct rvu *rvu, int blkaddr)
 	 */
 
 	/* IPv4/IPv6 SIP/DIPs */
-	flowkey_cfg = FLOW_KEY_TYPE_IPV4 | FLOW_KEY_TYPE_IPV6;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_IP], flowkey_cfg);
+	flowkey_cfg = NIX_FLOW_KEY_TYPE_IPV4 | NIX_FLOW_KEY_TYPE_IPV6;
+	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_IP], flowkey_cfg);
 
 	/* TCPv4/v6 4-tuple, SIP, DIP, Sport, Dport */
 	minkey_cfg = flowkey_cfg;
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_TCP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_TCP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP;
+	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_TCP], flowkey_cfg);
 
 	/* UDPv4/v6 4-tuple, SIP, DIP, Sport, Dport */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_UDP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_UDP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_UDP;
+	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_UDP], flowkey_cfg);
 
 	/* SCTPv4/v6 4-tuple, SIP, DIP, Sport, Dport */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_SCTP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_SCTP;
+	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_SCTP], flowkey_cfg);
 
 	/* TCP/UDP v4/v6 4-tuple, rest IP pkts 2-tuple */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_TCP | FLOW_KEY_TYPE_UDP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_TCP_UDP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP |
+			NIX_FLOW_KEY_TYPE_UDP;
+	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_TCP_UDP],
+			   flowkey_cfg);
 
 	/* TCP/SCTP v4/v6 4-tuple, rest IP pkts 2-tuple */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_TCP | FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_TCP_SCTP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP |
+			NIX_FLOW_KEY_TYPE_SCTP;
+	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_TCP_SCTP],
+			   flowkey_cfg);
 
 	/* UDP/SCTP v4/v6 4-tuple, rest IP pkts 2-tuple */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_UDP | FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_UDP_SCTP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_UDP |
+			NIX_FLOW_KEY_TYPE_SCTP;
+	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_UDP_SCTP],
+			   flowkey_cfg);
 
 	/* TCP/UDP/SCTP v4/v6 4-tuple, rest IP pkts 2-tuple */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_TCP |
-		      FLOW_KEY_TYPE_UDP | FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_TCP_UDP_SCTP],
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP |
+		      NIX_FLOW_KEY_TYPE_UDP | NIX_FLOW_KEY_TYPE_SCTP;
+	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_TCP_UDP_SCTP],
 			   flowkey_cfg);
 
-	for (alg = 0; alg < FLOW_KEY_ALG_MAX; alg++) {
+	for (alg = 0; alg < NIX_FLOW_KEY_ALG_MAX; alg++) {
 		for (fid = 0; fid < FIELDS_PER_ALG; fid++)
 			rvu_write64(rvu, blkaddr,
 				    NIX_AF_RX_FLOW_KEY_ALGX_FIELDX(alg, fid),
-- 
cgit v1.2.3


From b648366c2c256645a4cd1da6efd7b91e7c253ecb Mon Sep 17 00:00:00 2001
From: Jerin Jacob <jerinjacobk@gmail.com>
Date: Sun, 2 Dec 2018 18:17:38 +0530
Subject: octeontx2-af: Add support for dynamic flow cfg to RSS field
 generation

Introduce state-based algorithm to convert the flow_key value
to RSS algo field used by NIX_AF_RX_FLOW_KEY_ALGX_FIELDX register.

The outer `for loop` goes over _all_ protocol field and the following
variables depict the state machine forward progress logic.

a) keyoff_marker - Enabled when hash byte length needs to be accounted
in field->key_offset update.
b) field_marker - Enabled when a new field needs to be selected.
c) group_member - Enabled when a protocol is part of a group.

This would remove the existing hard coding and enable to add
new protocol support seamlessly.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |   1 +
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 113 ++++++++++++++++-----
 2 files changed, 87 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 76081ac8af48..a293091cb414 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -414,6 +414,7 @@ enum nix_af_status {
 	NIX_AF_INVAL_TXSCHQ_CFG     = -412,
 	NIX_AF_SMQ_FLUSH_FAILED     = -413,
 	NIX_AF_ERR_LF_RESET         = -414,
+	NIX_AF_ERR_RSS_NOSPC_FIELD  = -415,
 	NIX_AF_INVAL_NPA_PF_FUNC    = -419,
 	NIX_AF_INVAL_SSO_PF_FUNC    = -420,
 };
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index f23e095b8a95..c9f51ab4d875 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -1650,80 +1650,139 @@ int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
 	return 0;
 }
 
-static void set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
+static int set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
 {
-	struct nix_rx_flowkey_alg *field = NULL;
-	int idx, key_type;
+	int idx, nr_field, key_off, field_marker, keyoff_marker;
+	int max_key_off, max_bit_pos, group_member;
+	struct nix_rx_flowkey_alg *field;
+	struct nix_rx_flowkey_alg tmp;
+	u32 key_type, valid_key;
 
 	if (!alg)
-		return;
+		return -EINVAL;
 
-	/* FIELD0: IPv4
-	 * FIELD1: IPv6
-	 * FIELD2: TCP/UDP/SCTP/ALL
-	 * FIELD3: Unused
-	 * FIELD4: Unused
-	 *
-	 * Each of the 32 possible flow key algorithm definitions should
+#define FIELDS_PER_ALG  5
+#define MAX_KEY_OFF	40
+	/* Clear all fields */
+	memset(alg, 0, sizeof(uint64_t) * FIELDS_PER_ALG);
+
+	/* Each of the 32 possible flow key algorithm definitions should
 	 * fall into above incremental config (except ALG0). Otherwise a
 	 * single NPC MCAM entry is not sufficient for supporting RSS.
 	 *
 	 * If a different definition or combination needed then NPC MCAM
 	 * has to be programmed to filter such pkts and it's action should
 	 * point to this definition to calculate flowtag or hash.
+	 *
+	 * The `for loop` goes over _all_ protocol field and the following
+	 * variables depicts the state machine forward progress logic.
+	 *
+	 * keyoff_marker - Enabled when hash byte length needs to be accounted
+	 * in field->key_offset update.
+	 * field_marker - Enabled when a new field needs to be selected.
+	 * group_member - Enabled when protocol is part of a group.
 	 */
-	for (idx = 0; idx < 32; idx++) {
-		key_type = flow_cfg & BIT_ULL(idx);
-		if (!key_type)
-			continue;
+
+	keyoff_marker = 0; max_key_off = 0; group_member = 0;
+	nr_field = 0; key_off = 0; field_marker = 1;
+	field = &tmp; max_bit_pos = fls(flow_cfg);
+	for (idx = 0;
+	     idx < max_bit_pos && nr_field < FIELDS_PER_ALG &&
+	     key_off < MAX_KEY_OFF; idx++) {
+		key_type = BIT(idx);
+		valid_key = flow_cfg & key_type;
+		/* Found a field marker, reset the field values */
+		if (field_marker)
+			memset(&tmp, 0, sizeof(tmp));
+
 		switch (key_type) {
 		case NIX_FLOW_KEY_TYPE_PORT:
-			field = &alg[0];
 			field->sel_chan = true;
 			/* This should be set to 1, when SEL_CHAN is set */
 			field->bytesm1 = 1;
+			field_marker = true;
+			keyoff_marker = true;
 			break;
 		case NIX_FLOW_KEY_TYPE_IPV4:
-			field = &alg[0];
 			field->lid = NPC_LID_LC;
 			field->ltype_match = NPC_LT_LC_IP;
 			field->hdr_offset = 12; /* SIP offset */
 			field->bytesm1 = 7; /* SIP + DIP, 8 bytes */
 			field->ltype_mask = 0xF; /* Match only IPv4 */
+			field_marker = true;
+			keyoff_marker = false;
 			break;
 		case NIX_FLOW_KEY_TYPE_IPV6:
-			field = &alg[1];
 			field->lid = NPC_LID_LC;
 			field->ltype_match = NPC_LT_LC_IP6;
 			field->hdr_offset = 8; /* SIP offset */
 			field->bytesm1 = 31; /* SIP + DIP, 32 bytes */
 			field->ltype_mask = 0xF; /* Match only IPv6 */
+			field_marker = true;
+			keyoff_marker = true;
 			break;
 		case NIX_FLOW_KEY_TYPE_TCP:
 		case NIX_FLOW_KEY_TYPE_UDP:
 		case NIX_FLOW_KEY_TYPE_SCTP:
-			field = &alg[2];
 			field->lid = NPC_LID_LD;
 			field->bytesm1 = 3; /* Sport + Dport, 4 bytes */
-			if (key_type == NIX_FLOW_KEY_TYPE_TCP)
+			if (key_type == NIX_FLOW_KEY_TYPE_TCP && valid_key) {
 				field->ltype_match |= NPC_LT_LD_TCP;
-			else if (key_type == NIX_FLOW_KEY_TYPE_UDP)
+				group_member = true;
+			} else if (key_type == NIX_FLOW_KEY_TYPE_UDP &&
+				   valid_key) {
 				field->ltype_match |= NPC_LT_LD_UDP;
-			else if (key_type == NIX_FLOW_KEY_TYPE_SCTP)
+				group_member = true;
+			} else if (key_type == NIX_FLOW_KEY_TYPE_SCTP &&
+				   valid_key) {
 				field->ltype_match |= NPC_LT_LD_SCTP;
-			field->key_offset = 32; /* After IPv4/v6 SIP, DIP */
+				group_member = true;
+			}
 			field->ltype_mask = ~field->ltype_match;
+			if (key_type == NIX_FLOW_KEY_TYPE_SCTP) {
+				/* Handle the case where any of the group item
+				 * is enabled in the group but not the final one
+				 */
+				if (group_member) {
+					valid_key = true;
+					group_member = false;
+				}
+				field_marker = true;
+				keyoff_marker = true;
+			} else {
+				field_marker = false;
+				keyoff_marker = false;
+			}
 			break;
 		}
-		if (field)
-			field->ena = 1;
-		field = NULL;
+		field->ena = 1;
+
+		/* Found a valid flow key type */
+		if (valid_key) {
+			field->key_offset = key_off;
+			memcpy(&alg[nr_field], field, sizeof(*field));
+			max_key_off = max(max_key_off, field->bytesm1 + 1);
+
+			/* Found a field marker, get the next field */
+			if (field_marker)
+				nr_field++;
+		}
+
+		/* Found a keyoff marker, update the new key_off */
+		if (keyoff_marker) {
+			key_off += max_key_off;
+			max_key_off = 0;
+		}
 	}
+	/* Processed all the flow key types */
+	if (idx == max_bit_pos && key_off <= MAX_KEY_OFF)
+		return 0;
+	else
+		return NIX_AF_ERR_RSS_NOSPC_FIELD;
 }
 
 static void nix_rx_flowkey_alg_cfg(struct rvu *rvu, int blkaddr)
 {
-#define FIELDS_PER_ALG	5
 	u64 field[NIX_FLOW_KEY_ALG_MAX][FIELDS_PER_ALG];
 	u32 flowkey_cfg, minkey_cfg;
 	int alg, fid;
-- 
cgit v1.2.3


From 7ee74697e557ab9638d7fdcc091c5d25fc78af3d Mon Sep 17 00:00:00 2001
From: Jerin Jacob <jerinjacobk@gmail.com>
Date: Sun, 2 Dec 2018 18:17:39 +0530
Subject: octeontx2-af: Add support for runtime RSS algo index reservation

Introduced reserve_flowkey_alg_idx()to reserve RSS algorithm index,
it would internally use set_flowkey_fields() to generate fields
based on the flow key dynamically.

On AF driver init, it would reserve a predefined set RSS algo indexes,
which will be available all the time for all the AF driver consumers.
The leftover algo indexes can be reserved at runtime through
exiting nix_rss_flowkey_cfg mailbox message.

The NIX_FLOW_KEY_TYPE_PORT is removed from predefined a set of RSS flow
type as it is not used by any consumer.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/common.h |  14 --
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |   1 +
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |   7 +
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 191 ++++++++++++---------
 4 files changed, 119 insertions(+), 94 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index ceb3f1dbede5..72ad04eb8769 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -193,18 +193,4 @@ enum nix_scheduler {
 #define DEFAULT_RSS_CONTEXT_GROUP	0
 #define MAX_RSS_INDIR_TBL_SIZE		256 /* 1 << Max adder bits */
 
-/* NIX flow tag algorithm indices, max is 31 */
-enum {
-	NIX_FLOW_KEY_ALG_PORT,
-	NIX_FLOW_KEY_ALG_IP,
-	NIX_FLOW_KEY_ALG_TCP,
-	NIX_FLOW_KEY_ALG_UDP,
-	NIX_FLOW_KEY_ALG_SCTP,
-	NIX_FLOW_KEY_ALG_TCP_UDP,
-	NIX_FLOW_KEY_ALG_TCP_SCTP,
-	NIX_FLOW_KEY_ALG_UDP_SCTP,
-	NIX_FLOW_KEY_ALG_TCP_UDP_SCTP,
-	NIX_FLOW_KEY_ALG_MAX,
-};
-
 #endif /* COMMON_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index a293091cb414..640a230c43a2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -415,6 +415,7 @@ enum nix_af_status {
 	NIX_AF_SMQ_FLUSH_FAILED     = -413,
 	NIX_AF_ERR_LF_RESET         = -414,
 	NIX_AF_ERR_RSS_NOSPC_FIELD  = -415,
+	NIX_AF_ERR_RSS_NOSPC_ALGO   = -416,
 	NIX_AF_INVAL_NPA_PF_FUNC    = -419,
 	NIX_AF_INVAL_SSO_PF_FUNC    = -420,
 };
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 48dbbaa9dd4d..a0e445d8eb2d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -164,9 +164,16 @@ struct npc_pkind {
 	u32	*pfchan_map;
 };
 
+struct nix_flowkey {
+#define NIX_FLOW_KEY_ALG_MAX 32
+	u32 flowkey[NIX_FLOW_KEY_ALG_MAX];
+	int in_use;
+};
+
 struct nix_hw {
 	struct nix_txsch txsch[NIX_TXSCH_LVL_CNT]; /* Tx schedulers */
 	struct nix_mcast mcast;
+	struct nix_flowkey flowkey;
 };
 
 struct rvu_hwinfo {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index c9f51ab4d875..a1f268652b04 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -1597,57 +1597,16 @@ int rvu_mbox_handler_nix_stats_rst(struct rvu *rvu, struct msg_req *req,
 }
 
 /* Returns the ALG index to be set into NPC_RX_ACTION */
-static int get_flowkey_alg_idx(u32 flow_cfg)
+static int get_flowkey_alg_idx(struct nix_hw *nix_hw, u32 flow_cfg)
 {
-	u32 ip_cfg;
-
-	flow_cfg &= ~NIX_FLOW_KEY_TYPE_PORT;
-	ip_cfg = NIX_FLOW_KEY_TYPE_IPV4 | NIX_FLOW_KEY_TYPE_IPV6;
-	if (flow_cfg == ip_cfg)
-		return NIX_FLOW_KEY_ALG_IP;
-	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_TCP))
-		return NIX_FLOW_KEY_ALG_TCP;
-	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_UDP))
-		return NIX_FLOW_KEY_ALG_UDP;
-	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_SCTP))
-		return NIX_FLOW_KEY_ALG_SCTP;
-	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_TCP |
-			      NIX_FLOW_KEY_TYPE_UDP))
-		return NIX_FLOW_KEY_ALG_TCP_UDP;
-	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_TCP |
-			      NIX_FLOW_KEY_TYPE_SCTP))
-		return NIX_FLOW_KEY_ALG_TCP_SCTP;
-	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_UDP |
-			      NIX_FLOW_KEY_TYPE_SCTP))
-		return NIX_FLOW_KEY_ALG_UDP_SCTP;
-	else if (flow_cfg == (ip_cfg | NIX_FLOW_KEY_TYPE_TCP |
-			      NIX_FLOW_KEY_TYPE_UDP | NIX_FLOW_KEY_TYPE_SCTP))
-		return NIX_FLOW_KEY_ALG_TCP_UDP_SCTP;
-
-	return NIX_FLOW_KEY_ALG_PORT;
-}
+	int i;
 
-int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
-					 struct nix_rss_flowkey_cfg *req,
-					 struct nix_rss_flowkey_cfg_rsp *rsp)
-{
-	struct rvu_hwinfo *hw = rvu->hw;
-	u16 pcifunc = req->hdr.pcifunc;
-	int alg_idx, nixlf, blkaddr;
+	/* Scan over exiting algo entries to find a match */
+	for (i = 0; i < nix_hw->flowkey.in_use; i++)
+		if (nix_hw->flowkey.flowkey[i] == flow_cfg)
+			return i;
 
-	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
-	if (blkaddr < 0)
-		return NIX_AF_ERR_AF_LF_INVALID;
-
-	nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
-	if (nixlf < 0)
-		return NIX_AF_ERR_AF_LF_INVALID;
-
-	alg_idx = get_flowkey_alg_idx(req->flowkey_cfg);
-	rsp->alg_idx = alg_idx;
-	rvu_npc_update_flowkey_alg_idx(rvu, pcifunc, nixlf, req->group,
-				       alg_idx, req->mcam_index);
-	return 0;
+	return -ERANGE;
 }
 
 static int set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
@@ -1781,71 +1740,141 @@ static int set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
 		return NIX_AF_ERR_RSS_NOSPC_FIELD;
 }
 
-static void nix_rx_flowkey_alg_cfg(struct rvu *rvu, int blkaddr)
+static int reserve_flowkey_alg_idx(struct rvu *rvu, int blkaddr, u32 flow_cfg)
 {
-	u64 field[NIX_FLOW_KEY_ALG_MAX][FIELDS_PER_ALG];
-	u32 flowkey_cfg, minkey_cfg;
-	int alg, fid;
+	u64 field[FIELDS_PER_ALG];
+	struct nix_hw *hw;
+	int fid, rc;
 
-	memset(&field, 0, sizeof(u64) * NIX_FLOW_KEY_ALG_MAX * FIELDS_PER_ALG);
+	hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!hw)
+		return -EINVAL;
 
-	/* Only incoming channel number */
-	flowkey_cfg = NIX_FLOW_KEY_TYPE_PORT;
-	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_PORT], flowkey_cfg);
+	/* No room to add new flow hash algoritham */
+	if (hw->flowkey.in_use >= NIX_FLOW_KEY_ALG_MAX)
+		return NIX_AF_ERR_RSS_NOSPC_ALGO;
 
-	/* For a incoming pkt if none of the fields match then flowkey
-	 * will be zero, hence tag generated will also be zero.
-	 * RSS entry at rsse_index = NIX_AF_LF()_RSS_GRP()[OFFSET] will
-	 * be used to queue the packet.
-	 */
+	/* Generate algo fields for the given flow_cfg */
+	rc = set_flowkey_fields((struct nix_rx_flowkey_alg *)field, flow_cfg);
+	if (rc)
+		return rc;
+
+	/* Update ALGX_FIELDX register with generated fields */
+	for (fid = 0; fid < FIELDS_PER_ALG; fid++)
+		rvu_write64(rvu, blkaddr,
+			    NIX_AF_RX_FLOW_KEY_ALGX_FIELDX(hw->flowkey.in_use,
+							   fid), field[fid]);
+
+	/* Store the flow_cfg for futher lookup */
+	rc = hw->flowkey.in_use;
+	hw->flowkey.flowkey[rc] = flow_cfg;
+	hw->flowkey.in_use++;
+
+	return rc;
+}
+
+int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
+					 struct nix_rss_flowkey_cfg *req,
+					 struct nix_rss_flowkey_cfg_rsp *rsp)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	u16 pcifunc = req->hdr.pcifunc;
+	int alg_idx, nixlf, blkaddr;
+	struct nix_hw *nix_hw;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
+	if (nixlf < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	alg_idx = get_flowkey_alg_idx(nix_hw, req->flowkey_cfg);
+	/* Failed to get algo index from the exiting list, reserve new  */
+	if (alg_idx < 0) {
+		alg_idx = reserve_flowkey_alg_idx(rvu, blkaddr,
+						  req->flowkey_cfg);
+		if (alg_idx < 0)
+			return alg_idx;
+	}
+	rsp->alg_idx = alg_idx;
+	rvu_npc_update_flowkey_alg_idx(rvu, pcifunc, nixlf, req->group,
+				       alg_idx, req->mcam_index);
+	return 0;
+}
+
+static int nix_rx_flowkey_alg_cfg(struct rvu *rvu, int blkaddr)
+{
+	u32 flowkey_cfg, minkey_cfg;
+	int alg, fid, rc;
+
+	/* Disable all flow key algx fieldx */
+	for (alg = 0; alg < NIX_FLOW_KEY_ALG_MAX; alg++) {
+		for (fid = 0; fid < FIELDS_PER_ALG; fid++)
+			rvu_write64(rvu, blkaddr,
+				    NIX_AF_RX_FLOW_KEY_ALGX_FIELDX(alg, fid),
+				    0);
+	}
 
 	/* IPv4/IPv6 SIP/DIPs */
 	flowkey_cfg = NIX_FLOW_KEY_TYPE_IPV4 | NIX_FLOW_KEY_TYPE_IPV6;
-	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_IP], flowkey_cfg);
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* TCPv4/v6 4-tuple, SIP, DIP, Sport, Dport */
 	minkey_cfg = flowkey_cfg;
 	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP;
-	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_TCP], flowkey_cfg);
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* UDPv4/v6 4-tuple, SIP, DIP, Sport, Dport */
 	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_UDP;
-	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_UDP], flowkey_cfg);
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* SCTPv4/v6 4-tuple, SIP, DIP, Sport, Dport */
 	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_SCTP], flowkey_cfg);
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* TCP/UDP v4/v6 4-tuple, rest IP pkts 2-tuple */
 	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP |
 			NIX_FLOW_KEY_TYPE_UDP;
-	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_TCP_UDP],
-			   flowkey_cfg);
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* TCP/SCTP v4/v6 4-tuple, rest IP pkts 2-tuple */
 	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP |
 			NIX_FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_TCP_SCTP],
-			   flowkey_cfg);
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* UDP/SCTP v4/v6 4-tuple, rest IP pkts 2-tuple */
 	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_UDP |
 			NIX_FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_UDP_SCTP],
-			   flowkey_cfg);
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* TCP/UDP/SCTP v4/v6 4-tuple, rest IP pkts 2-tuple */
 	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP |
 		      NIX_FLOW_KEY_TYPE_UDP | NIX_FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[NIX_FLOW_KEY_ALG_TCP_UDP_SCTP],
-			   flowkey_cfg);
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
-	for (alg = 0; alg < NIX_FLOW_KEY_ALG_MAX; alg++) {
-		for (fid = 0; fid < FIELDS_PER_ALG; fid++)
-			rvu_write64(rvu, blkaddr,
-				    NIX_AF_RX_FLOW_KEY_ALGX_FIELDX(alg, fid),
-				    field[alg][fid]);
-	}
+	return 0;
 }
 
 int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu,
@@ -2314,7 +2343,9 @@ int rvu_nix_init(struct rvu *rvu)
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OIP4,
 			    (NPC_LID_LC << 8) | (NPC_LT_LC_IP << 4) | 0x0F);
 
-		nix_rx_flowkey_alg_cfg(rvu, blkaddr);
+		err = nix_rx_flowkey_alg_cfg(rvu, blkaddr);
+		if (err)
+			return err;
 
 		/* Initialize CGX/LBK/SDP link credits, min/max pkt lengths */
 		nix_link_config(rvu, blkaddr);
-- 
cgit v1.2.3


From 26dda7da8ed33b8541053daaf1a2a08389bc0fe0 Mon Sep 17 00:00:00 2001
From: Nithin Dabilpuram <ndabilpuram@marvell.com>
Date: Sun, 2 Dec 2018 18:17:40 +0530
Subject: octeontx2-af: Restrict TL1 allocation and configuration

TL1 is the root node in the scheduling hierarchy and
it is a global resource with a limited number.

This patch introduces restriction and validation on
the allocation of the TL1 nodes for the effective resource
sharing across the AF consumers.

- Limit TL1 allocation to 2 per lmac.
  One could be for the normal link and one for IEEE802.3br
  express link (Express Send DMA).
  Effectively all the VF's of an RVU PF(lmac) share the two TL1 schqs.
- TL1 cannot be freed once allocated.
- Allow VF's to only apply default config to TL1 if not
  already applied. PF's can always overwrite the TL1 config.
- Consider NIX_AQ_INSTOP_WRITE while validating txschq
  when sq.ena is set.

Signed-off-by: Krzysztof Kanas <kkanas@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/common.h |   3 +
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |   6 +-
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 227 +++++++++++++++++++--
 3 files changed, 218 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index 72ad04eb8769..ec50a21c5aaf 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -143,6 +143,9 @@ enum nix_scheduler {
 	NIX_TXSCH_LVL_CNT = 0x5,
 };
 
+#define TXSCH_TL1_DFLT_RR_QTM      ((1 << 24) - 1)
+#define TXSCH_TL1_DFLT_RR_PRIO     (0x1ull)
+
 /* Min/Max packet sizes, excluding FCS */
 #define	NIC_HW_MIN_FRS			40
 #define	NIC_HW_MAX_FRS			9212
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index a0e445d8eb2d..b1841725af5b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -156,7 +156,11 @@ struct rvu_pfvf {
 struct nix_txsch {
 	struct rsrc_bmap schq;
 	u8   lvl;
-	u16  *pfvf_map;
+#define NIX_TXSCHQ_TL1_CFG_DONE       BIT_ULL(0)
+#define TXSCH_MAP_FUNC(__pfvf_map)    ((__pfvf_map) & 0xFFFF)
+#define TXSCH_MAP_FLAGS(__pfvf_map)   ((__pfvf_map) >> 16)
+#define TXSCH_MAP(__func, __flags)    (((__func) & 0xFFFF) | ((__flags) << 16))
+	u32  *pfvf_map;
 };
 
 struct npc_pkind {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index a1f268652b04..0d4929bd3a95 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -127,6 +127,7 @@ static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
 {
 	struct nix_txsch *txsch;
 	struct nix_hw *nix_hw;
+	u16 map_func;
 
 	nix_hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
@@ -138,11 +139,18 @@ static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
 		return false;
 
 	mutex_lock(&rvu->rsrc_lock);
-	if (txsch->pfvf_map[schq] != pcifunc) {
-		mutex_unlock(&rvu->rsrc_lock);
-		return false;
-	}
+	map_func = TXSCH_MAP_FUNC(txsch->pfvf_map[schq]);
 	mutex_unlock(&rvu->rsrc_lock);
+
+	/* For TL1 schq, sharing across VF's of same PF is ok */
+	if (lvl == NIX_TXSCH_LVL_TL1 &&
+	    rvu_get_pf(map_func) != rvu_get_pf(pcifunc))
+		return false;
+
+	if (lvl != NIX_TXSCH_LVL_TL1 &&
+	    map_func != pcifunc)
+		return false;
+
 	return true;
 }
 
@@ -494,7 +502,9 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
 
 	/* Check if SQ pointed SMQ belongs to this PF/VF or not */
 	if (req->ctype == NIX_AQ_CTYPE_SQ &&
-	    req->op != NIX_AQ_INSTOP_WRITE) {
+	    ((req->op == NIX_AQ_INSTOP_INIT && req->sq.ena) ||
+	     (req->op == NIX_AQ_INSTOP_WRITE &&
+	      req->sq_mask.ena && req->sq_mask.smq && req->sq.ena))) {
 		if (!is_valid_txschq(rvu, blkaddr, NIX_TXSCH_LVL_SMQ,
 				     pcifunc, req->sq.smq))
 			return NIX_AF_ERR_AQ_ENQUEUE;
@@ -987,6 +997,73 @@ static void nix_reset_tx_linkcfg(struct rvu *rvu, int blkaddr,
 			    NIX_AF_TL3_TL2X_LINKX_CFG(schq, link), 0x00);
 }
 
+static int
+rvu_get_tl1_schqs(struct rvu *rvu, int blkaddr, u16 pcifunc,
+		  u16 *schq_list, u16 *schq_cnt)
+{
+	struct nix_txsch *txsch;
+	struct nix_hw *nix_hw;
+	struct rvu_pfvf *pfvf;
+	u8 cgx_id, lmac_id;
+	u16 schq_base;
+	u32 *pfvf_map;
+	int pf, intf;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -ENODEV;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL1];
+	pfvf_map = txsch->pfvf_map;
+	pf = rvu_get_pf(pcifunc);
+
+	/* static allocation as two TL1's per link */
+	intf = is_afvf(pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
+
+	switch (intf) {
+	case NIX_INTF_TYPE_CGX:
+		rvu_get_cgx_lmac_id(pfvf->cgx_lmac, &cgx_id, &lmac_id);
+		schq_base = (cgx_id * MAX_LMAC_PER_CGX + lmac_id) * 2;
+		break;
+	case NIX_INTF_TYPE_LBK:
+		schq_base = rvu->cgx_cnt_max * MAX_LMAC_PER_CGX * 2;
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	if (schq_base + 1 > txsch->schq.max)
+		return -ENODEV;
+
+	/* init pfvf_map as we store flags */
+	if (pfvf_map[schq_base] == U32_MAX) {
+		pfvf_map[schq_base] =
+			TXSCH_MAP((pf << RVU_PFVF_PF_SHIFT), 0);
+		pfvf_map[schq_base + 1] =
+			TXSCH_MAP((pf << RVU_PFVF_PF_SHIFT), 0);
+
+		/* Onetime reset for TL1 */
+		nix_reset_tx_linkcfg(rvu, blkaddr,
+				     NIX_TXSCH_LVL_TL1, schq_base);
+		nix_reset_tx_shaping(rvu, blkaddr,
+				     NIX_TXSCH_LVL_TL1, schq_base);
+
+		nix_reset_tx_linkcfg(rvu, blkaddr,
+				     NIX_TXSCH_LVL_TL1, schq_base + 1);
+		nix_reset_tx_shaping(rvu, blkaddr,
+				     NIX_TXSCH_LVL_TL1, schq_base + 1);
+	}
+
+	if (schq_list && schq_cnt) {
+		schq_list[0] = schq_base;
+		schq_list[1] = schq_base + 1;
+		*schq_cnt = 2;
+	}
+
+	return 0;
+}
+
 int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 				     struct nix_txsch_alloc_req *req,
 				     struct nix_txsch_alloc_rsp *rsp)
@@ -997,6 +1074,7 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 	struct rvu_pfvf *pfvf;
 	struct nix_hw *nix_hw;
 	int blkaddr, rc = 0;
+	u32 *pfvf_map;
 	u16 schq;
 
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
@@ -1012,13 +1090,23 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 	for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
 		txsch = &nix_hw->txsch[lvl];
 		req_schq = req->schq_contig[lvl] + req->schq[lvl];
+		pfvf_map = txsch->pfvf_map;
+
+		if (!req_schq)
+			continue;
 
 		/* There are only 28 TL1s */
-		if (lvl == NIX_TXSCH_LVL_TL1 && req_schq > txsch->schq.max)
-			goto err;
+		if (lvl == NIX_TXSCH_LVL_TL1) {
+			if (req->schq_contig[lvl] ||
+			    req->schq[lvl] > 2 ||
+			    rvu_get_tl1_schqs(rvu, blkaddr,
+					      pcifunc, NULL, NULL))
+				goto err;
+			continue;
+		}
 
 		/* Check if request is valid */
-		if (!req_schq || req_schq > MAX_TXSCHQ_PER_FUNC)
+		if (req_schq > MAX_TXSCHQ_PER_FUNC)
 			goto err;
 
 		/* If contiguous queues are needed, check for availability */
@@ -1034,16 +1122,32 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 	for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
 		txsch = &nix_hw->txsch[lvl];
 		rsp->schq_contig[lvl] = req->schq_contig[lvl];
+		pfvf_map = txsch->pfvf_map;
 		rsp->schq[lvl] = req->schq[lvl];
 
-		schq = 0;
+		if (!req->schq[lvl] && !req->schq_contig[lvl])
+			continue;
+
+		/* Handle TL1 specially as it is
+		 * allocation is restricted to 2 TL1's
+		 * per link
+		 */
+
+		if (lvl == NIX_TXSCH_LVL_TL1) {
+			rsp->schq_contig[lvl] = 0;
+			rvu_get_tl1_schqs(rvu, blkaddr, pcifunc,
+					  &rsp->schq_list[lvl][0],
+					  &rsp->schq[lvl]);
+			continue;
+		}
+
 		/* Alloc contiguous queues first */
 		if (req->schq_contig[lvl]) {
 			schq = rvu_alloc_rsrc_contig(&txsch->schq,
 						     req->schq_contig[lvl]);
 
 			for (idx = 0; idx < req->schq_contig[lvl]; idx++) {
-				txsch->pfvf_map[schq] = pcifunc;
+				pfvf_map[schq] = TXSCH_MAP(pcifunc, 0);
 				nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq);
 				nix_reset_tx_shaping(rvu, blkaddr, lvl, schq);
 				rsp->schq_contig_list[lvl][idx] = schq;
@@ -1054,7 +1158,7 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 		/* Alloc non-contiguous queues */
 		for (idx = 0; idx < req->schq[lvl]; idx++) {
 			schq = rvu_alloc_rsrc(&txsch->schq);
-			txsch->pfvf_map[schq] = pcifunc;
+			pfvf_map[schq] = TXSCH_MAP(pcifunc, 0);
 			nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq);
 			nix_reset_tx_shaping(rvu, blkaddr, lvl, schq);
 			rsp->schq_list[lvl][idx] = schq;
@@ -1096,7 +1200,7 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 
 		txsch = &nix_hw->txsch[lvl];
 		for (schq = 0; schq < txsch->schq.max; schq++) {
-			if (txsch->pfvf_map[schq] != pcifunc)
+			if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
 				continue;
 			nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq);
 		}
@@ -1105,7 +1209,7 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 	/* Flush SMQs */
 	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ];
 	for (schq = 0; schq < txsch->schq.max; schq++) {
-		if (txsch->pfvf_map[schq] != pcifunc)
+		if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
 			continue;
 		cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq));
 		/* Do SMQ flush and set enqueue xoff */
@@ -1123,9 +1227,15 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 
 	/* Now free scheduler queues to free pool */
 	for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
+		/* Free all SCHQ's except TL1 as
+		 * TL1 is shared across all VF's for a RVU PF
+		 */
+		if (lvl == NIX_TXSCH_LVL_TL1)
+			continue;
+
 		txsch = &nix_hw->txsch[lvl];
 		for (schq = 0; schq < txsch->schq.max; schq++) {
-			if (txsch->pfvf_map[schq] != pcifunc)
+			if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
 				continue;
 			rvu_free_rsrc(&txsch->schq, schq);
 			txsch->pfvf_map[schq] = 0;
@@ -1187,16 +1297,73 @@ static bool is_txschq_config_valid(struct rvu *rvu, u16 pcifunc, int blkaddr,
 	return true;
 }
 
+static int
+nix_tl1_default_cfg(struct rvu *rvu, u16 pcifunc)
+{
+	u16 schq_list[2], schq_cnt, schq;
+	int blkaddr, idx, err = 0;
+	u16 map_func, map_flags;
+	struct nix_hw *nix_hw;
+	u64 reg, regval;
+	u32 *pfvf_map;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	pfvf_map = nix_hw->txsch[NIX_TXSCH_LVL_TL1].pfvf_map;
+
+	mutex_lock(&rvu->rsrc_lock);
+
+	err = rvu_get_tl1_schqs(rvu, blkaddr,
+				pcifunc, schq_list, &schq_cnt);
+	if (err)
+		goto unlock;
+
+	for (idx = 0; idx < schq_cnt; idx++) {
+		schq = schq_list[idx];
+		map_func = TXSCH_MAP_FUNC(pfvf_map[schq]);
+		map_flags = TXSCH_MAP_FLAGS(pfvf_map[schq]);
+
+		/* check if config is already done or this is pf */
+		if (map_flags & NIX_TXSCHQ_TL1_CFG_DONE)
+			continue;
+
+		/* default configuration */
+		reg = NIX_AF_TL1X_TOPOLOGY(schq);
+		regval = (TXSCH_TL1_DFLT_RR_PRIO << 1);
+		rvu_write64(rvu, blkaddr, reg, regval);
+		reg = NIX_AF_TL1X_SCHEDULE(schq);
+		regval = TXSCH_TL1_DFLT_RR_QTM;
+		rvu_write64(rvu, blkaddr, reg, regval);
+		reg = NIX_AF_TL1X_CIR(schq);
+		regval = 0;
+		rvu_write64(rvu, blkaddr, reg, regval);
+
+		map_flags |= NIX_TXSCHQ_TL1_CFG_DONE;
+		pfvf_map[schq] = TXSCH_MAP(map_func, map_flags);
+	}
+unlock:
+	mutex_unlock(&rvu->rsrc_lock);
+	return err;
+}
+
 int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 				    struct nix_txschq_config *req,
 				    struct msg_rsp *rsp)
 {
+	u16 schq, pcifunc = req->hdr.pcifunc;
 	struct rvu_hwinfo *hw = rvu->hw;
-	u16 pcifunc = req->hdr.pcifunc;
 	u64 reg, regval, schq_regbase;
 	struct nix_txsch *txsch;
+	u16 map_func, map_flags;
 	struct nix_hw *nix_hw;
 	int blkaddr, idx, err;
+	u32 *pfvf_map;
 	int nixlf;
 
 	if (req->lvl >= NIX_TXSCH_LVL_CNT ||
@@ -1216,6 +1383,16 @@ int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 		return NIX_AF_ERR_AF_LF_INVALID;
 
 	txsch = &nix_hw->txsch[req->lvl];
+	pfvf_map = txsch->pfvf_map;
+
+	/* VF is only allowed to trigger
+	 * setting default cfg on TL1
+	 */
+	if (pcifunc & RVU_PFVF_FUNC_MASK &&
+	    req->lvl == NIX_TXSCH_LVL_TL1) {
+		return nix_tl1_default_cfg(rvu, pcifunc);
+	}
+
 	for (idx = 0; idx < req->num_regs; idx++) {
 		reg = req->reg[idx];
 		regval = req->regval[idx];
@@ -1233,6 +1410,21 @@ int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 			regval |= ((u64)nixlf << 24);
 		}
 
+		/* Mark config as done for TL1 by PF */
+		if (schq_regbase >= NIX_AF_TL1X_SCHEDULE(0) &&
+		    schq_regbase <= NIX_AF_TL1X_GREEN_BYTES(0)) {
+			schq = TXSCHQ_IDX(reg, TXSCHQ_IDX_SHIFT);
+
+			mutex_lock(&rvu->rsrc_lock);
+
+			map_func = TXSCH_MAP_FUNC(pfvf_map[schq]);
+			map_flags = TXSCH_MAP_FLAGS(pfvf_map[schq]);
+
+			map_flags |= NIX_TXSCHQ_TL1_CFG_DONE;
+			pfvf_map[schq] = TXSCH_MAP(map_func, map_flags);
+			mutex_unlock(&rvu->rsrc_lock);
+		}
+
 		rvu_write64(rvu, blkaddr, reg, regval);
 
 		/* Check for SMQ flush, if so, poll for its completion */
@@ -1559,9 +1751,10 @@ static int nix_setup_txschq(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 		 * PF/VF pcifunc mapping info.
 		 */
 		txsch->pfvf_map = devm_kcalloc(rvu->dev, txsch->schq.max,
-					       sizeof(u16), GFP_KERNEL);
+					       sizeof(u32), GFP_KERNEL);
 		if (!txsch->pfvf_map)
 			return -ENOMEM;
+		memset(txsch->pfvf_map, U8_MAX, txsch->schq.max * sizeof(u32));
 	}
 	return 0;
 }
@@ -2020,7 +2213,7 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
 	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ];
 	mutex_lock(&rvu->rsrc_lock);
 	for (schq = 0; schq < txsch->schq.max; schq++) {
-		if (txsch->pfvf_map[schq] != pcifunc)
+		if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
 			continue;
 		cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq));
 		cfg = (cfg & ~(0xFFFFULL << 8)) | ((u64)req->maxlen << 8);
-- 
cgit v1.2.3


From e2703c5f581a8d970c46251914e837db192b80d4 Mon Sep 17 00:00:00 2001
From: Nithin Dabilpuram <ndabilpuram@marvell.com>
Date: Sun, 2 Dec 2018 18:17:41 +0530
Subject: octeontx2-af: Allow freeing single TLx Tx schedule queue

The default behavior was to free all the TLx Tx schedule
queues. This patch adds support for freeing a single Tx
schedule queue if TXSCHQ_FREE_ALL flag is not set.

Signed-off-by: Krzysztof Kanas <kkanas@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 72 +++++++++++++++++++++-
 1 file changed, 71 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 0d4929bd3a95..741728c3d597 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -1252,11 +1252,81 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 	return 0;
 }
 
+static int nix_txschq_free_one(struct rvu *rvu,
+			       struct nix_txsch_free_req *req)
+{
+	int lvl, schq, nixlf, blkaddr, rc;
+	struct rvu_hwinfo *hw = rvu->hw;
+	u16 pcifunc = req->hdr.pcifunc;
+	struct nix_txsch *txsch;
+	struct nix_hw *nix_hw;
+	u32 *pfvf_map;
+	u64 cfg;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
+	if (nixlf < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	lvl = req->schq_lvl;
+	schq = req->schq;
+	txsch = &nix_hw->txsch[lvl];
+
+	/* Don't allow freeing TL1 */
+	if (lvl > NIX_TXSCH_LVL_TL2 ||
+	    schq >= txsch->schq.max)
+		goto err;
+
+	pfvf_map = txsch->pfvf_map;
+	mutex_lock(&rvu->rsrc_lock);
+
+	if (TXSCH_MAP_FUNC(pfvf_map[schq]) != pcifunc) {
+		mutex_unlock(&rvu->rsrc_lock);
+		goto err;
+	}
+
+	/* Flush if it is a SMQ. Onus of disabling
+	 * TL2/3 queue links before SMQ flush is on user
+	 */
+	if (lvl == NIX_TXSCH_LVL_SMQ) {
+		cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq));
+		/* Do SMQ flush and set enqueue xoff */
+		cfg |= BIT_ULL(50) | BIT_ULL(49);
+		rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq), cfg);
+
+		/* Wait for flush to complete */
+		rc = rvu_poll_reg(rvu, blkaddr,
+				  NIX_AF_SMQX_CFG(schq), BIT_ULL(49), true);
+		if (rc) {
+			dev_err(rvu->dev,
+				"NIXLF%d: SMQ%d flush failed\n", nixlf, schq);
+		}
+	}
+
+	/* Free the resource */
+	rvu_free_rsrc(&txsch->schq, schq);
+	txsch->pfvf_map[schq] = 0;
+	mutex_unlock(&rvu->rsrc_lock);
+	return 0;
+err:
+	return NIX_AF_ERR_TLX_INVALID;
+}
+
 int rvu_mbox_handler_nix_txsch_free(struct rvu *rvu,
 				    struct nix_txsch_free_req *req,
 				    struct msg_rsp *rsp)
 {
-	return nix_txschq_free(rvu, req->hdr.pcifunc);
+	if (req->flags & TXSCHQ_FREE_ALL)
+		return nix_txschq_free(rvu, req->hdr.pcifunc);
+	else
+		return nix_txschq_free_one(rvu, req);
 }
 
 static bool is_txschq_config_valid(struct rvu *rvu, u16 pcifunc, int blkaddr,
-- 
cgit v1.2.3


From 962e1bd6b74d6c1725761d1974698e1437565fb6 Mon Sep 17 00:00:00 2001
From: Jerin Jacob <jerinjacobk@gmail.com>
Date: Sun, 2 Dec 2018 18:17:42 +0530
Subject: octeontx2-af: Enable inner IPv4 checksum and its error code

This patch enables the inner IPv4 checksum and
defines the error code for Rx inner and outer checksum errors.
Setting ERRCODE as 1 so that CQE descriptor can be embedded
valid checksum error code and the driver can interpret
checksum error as ERRLEV = LID + 1 and ERRCODE = 1.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index ee2600d93d54..c203d3fddde9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -1008,13 +1008,20 @@ int rvu_npc_init(struct rvu *rvu)
 	rvu_write64(rvu, blkaddr, NPC_AF_PCK_DEF_OIP4,
 		    (NPC_LID_LC << 8) | (NPC_LT_LC_IP << 4) | 0x0F);
 
+	/* Config Inner IPV4 NPC layer info */
+	rvu_write64(rvu, blkaddr, NPC_AF_PCK_DEF_IIP4,
+		    (NPC_LID_LF << 8) | (NPC_LT_LF_TU_IP << 4) | 0x0F);
+
 	/* Enable below for Rx pkts.
 	 * - Outer IPv4 header checksum validation.
 	 * - Detect outer L2 broadcast address and set NPC_RESULT_S[L2M].
+	 * - Inner IPv4 header checksum validation.
+	 * - Set non zero checksum error code value
 	 */
 	rvu_write64(rvu, blkaddr, NPC_AF_PCK_CFG,
 		    rvu_read64(rvu, blkaddr, NPC_AF_PCK_CFG) |
-		    BIT_ULL(6) | BIT_ULL(2));
+		    BIT_ULL(32) | BIT_ULL(24) | BIT_ULL(6) |
+		    BIT_ULL(2) | BIT_ULL(1));
 
 	/* Set RX and TX side MCAM search key size.
 	 * LA..LD (ltype only) + Channel
-- 
cgit v1.2.3


From 7c91a92efc3db6dc721fae1cfbe1630f3d940fff Mon Sep 17 00:00:00 2001
From: Jerin Jacob <jerinjacobk@gmail.com>
Date: Sun, 2 Dec 2018 18:17:43 +0530
Subject: octeontx2-af: Define all NIX_AF_RX_DEF_* registers

In order to support all NIX specific valid length errors and
checksum errors on Rx, Update all NIX_AF_RX_DEF_* registers.

Also sorted all registers in HRM definition order.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 25 +++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 741728c3d597..2a7229809247 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -2593,18 +2593,33 @@ int rvu_nix_init(struct rvu *rvu)
 		if (err)
 			return err;
 
-		/* Config Outer L2, IP, TCP and UDP's NPC layer info.
+		/* Config Outer/Inner L2, IP, TCP, UDP and SCTP NPC layer info.
 		 * This helps HW protocol checker to identify headers
 		 * and validate length and checksums.
 		 */
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OL2,
 			    (NPC_LID_LA << 8) | (NPC_LT_LA_ETHER << 4) | 0x0F);
-		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OUDP,
-			    (NPC_LID_LD << 8) | (NPC_LT_LD_UDP << 4) | 0x0F);
-		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OTCP,
-			    (NPC_LID_LD << 8) | (NPC_LT_LD_TCP << 4) | 0x0F);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OIP4,
 			    (NPC_LID_LC << 8) | (NPC_LT_LC_IP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IIP4,
+			    (NPC_LID_LF << 8) | (NPC_LT_LF_TU_IP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OIP6,
+			    (NPC_LID_LC << 8) | (NPC_LT_LC_IP6 << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IIP6,
+			    (NPC_LID_LF << 8) | (NPC_LT_LF_TU_IP6 << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OTCP,
+			    (NPC_LID_LD << 8) | (NPC_LT_LD_TCP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_ITCP,
+			    (NPC_LID_LG << 8) | (NPC_LT_LG_TU_TCP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OUDP,
+			    (NPC_LID_LD << 8) | (NPC_LT_LD_UDP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IUDP,
+			    (NPC_LID_LG << 8) | (NPC_LT_LG_TU_UDP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OSCTP,
+			    (NPC_LID_LD << 8) | (NPC_LT_LD_SCTP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_ISCTP,
+			    (NPC_LID_LG << 8) | (NPC_LT_LG_TU_SCTP << 4) |
+			    0x0F);
 
 		err = nix_rx_flowkey_alg_cfg(rvu, blkaddr);
 		if (err)
-- 
cgit v1.2.3


From f9f2da46c03d5e998f92134126e9be9822a473ec Mon Sep 17 00:00:00 2001
From: Vamsi Attunuru <vamsi.attunuru@marvell.com>
Date: Sun, 2 Dec 2018 18:17:44 +0530
Subject: octeontx2-af: Enable RSS with promiscuous mode

This patch adds support for enabling RSS in promiscuous mode
if RSS is already requested by the AF client.

Signed-off-by: Vamsi Attunuru <vamsi.attunuru@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 35 +++++++++++++++++++---
 1 file changed, 31 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index c203d3fddde9..bf81031f0fdd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -368,9 +368,9 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 				   int nixlf, u64 chan, bool allmulti)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr, ucast_idx, index, kwi;
 	struct mcam_entry entry = { {0} };
 	struct nix_rx_action action = { };
-	int blkaddr, index, kwi;
 
 	/* Only PF or AF VF can add a promiscuous entry */
 	if ((pcifunc & RVU_PFVF_FUNC_MASK) && !is_afvf(pcifunc))
@@ -392,9 +392,21 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 		entry.kw_mask[kwi] = BIT_ULL(40);
 	}
 
-	*(u64 *)&action = 0x00;
-	action.op = NIX_RX_ACTIONOP_UCAST;
-	action.pf_func = pcifunc;
+	ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					     nixlf, NIXLF_UCAST_ENTRY);
+
+	/* If the corresponding PF's ucast action is RSS,
+	 * use the same action for promisc also
+	 */
+	if (is_mcam_entry_enabled(rvu, mcam, blkaddr, ucast_idx))
+		*(u64 *)&action = npc_get_mcam_action(rvu, mcam,
+							blkaddr, ucast_idx);
+
+	if (action.op != NIX_RX_ACTIONOP_RSS) {
+		*(u64 *)&action = 0x00;
+		action.op = NIX_RX_ACTIONOP_UCAST;
+		action.pf_func = pcifunc;
+	}
 
 	entry.action = *(u64 *)&action;
 	npc_config_mcam_entry(rvu, mcam, blkaddr, index,
@@ -539,6 +551,21 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 	rvu_write64(rvu, blkaddr,
 		    NPC_AF_MCAMEX_BANKX_ACTION(index, bank), *(u64 *)&action);
 
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					 nixlf, NIXLF_PROMISC_ENTRY);
+
+	/* If PF's promiscuous entry is enabled,
+	 * Set RSS action for that entry as well
+	 */
+	if (is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) {
+		bank = npc_get_bank(mcam, index);
+		index &= (mcam->banksize - 1);
+
+		rvu_write64(rvu, blkaddr,
+			    NPC_AF_MCAMEX_BANKX_ACTION(index, bank),
+			    *(u64 *)&action);
+	}
+
 	rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
 }
 
-- 
cgit v1.2.3


From a27d765916bd97d879887337fff26759e5d3279b Mon Sep 17 00:00:00 2001
From: Krzysztof Kanas <kkanas@marvell.com>
Date: Sun, 2 Dec 2018 18:17:45 +0530
Subject: octeontx2-af: Add support for Tx packet marking

NIX_AF_MARK_FORMAT(0..127)_CTL register enables an SW defined
means to mark/insert various data in the packet based on
final packet color from traffic shaping HW.

0..127 works as an index to choose the algorithm. On success,
the mailbox returns the index to the client.

Add NIX_MARK_FORMAT_CFG mailbox which reserves mark format based on
tuple (offset, y_mask, y_val, r_mask, r_val)

If the tuple is requested again for mark format that was already
reserved, then it will be reused. If not it will reserve a new entry
if space is available.

Also on AF init commonly used marker format such as VLAN DEI, IPv4
ECN, IPv4 DSCP are reserved for AF consumers.

Signed-off-by: Krzysztof Kanas <kkanas@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  18 ++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  12 +++
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 103 +++++++++++++++++++++
 3 files changed, 133 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 640a230c43a2..146f8f9656ba 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -200,6 +200,9 @@ M(NIX_SET_RX_MODE,	0x800b, nix_set_rx_mode, nix_rx_mode, msg_rsp)	\
 M(NIX_SET_HW_FRS,	0x800c, nix_set_hw_frs, nix_frs_cfg, msg_rsp)	\
 M(NIX_LF_START_RX,	0x800d, nix_lf_start_rx, msg_req, msg_rsp)	\
 M(NIX_LF_STOP_RX,	0x800e, nix_lf_stop_rx, msg_req, msg_rsp)	\
+M(NIX_MARK_FORMAT_CFG,	0x800f, nix_mark_format_cfg,			\
+				 nix_mark_format_cfg,			\
+				 nix_mark_format_cfg_rsp)		\
 M(NIX_RXVLAN_ALLOC,	0x8012, nix_rxvlan_alloc, msg_req, msg_rsp)
 
 /* Messages initiated by AF (range 0xC00 - 0xDFF) */
@@ -416,6 +419,7 @@ enum nix_af_status {
 	NIX_AF_ERR_LF_RESET         = -414,
 	NIX_AF_ERR_RSS_NOSPC_FIELD  = -415,
 	NIX_AF_ERR_RSS_NOSPC_ALGO   = -416,
+	NIX_AF_ERR_MARK_CFG_FAIL    = -417,
 	NIX_AF_INVAL_NPA_PF_FUNC    = -419,
 	NIX_AF_INVAL_SSO_PF_FUNC    = -420,
 };
@@ -583,6 +587,20 @@ struct nix_set_mac_addr {
 	u8 mac_addr[ETH_ALEN]; /* MAC address to be set for this pcifunc */
 };
 
+struct nix_mark_format_cfg {
+	struct mbox_msghdr hdr;
+	u8 offset;
+	u8 y_mask;
+	u8 y_val;
+	u8 r_mask;
+	u8 r_val;
+};
+
+struct nix_mark_format_cfg_rsp {
+	struct mbox_msghdr hdr;
+	u8 mark_format_idx;
+};
+
 struct nix_rx_mode {
 	struct mbox_msghdr hdr;
 #define NIX_RX_MODE_UCAST	BIT(0)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index b1841725af5b..563e3bfb89a5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -163,6 +163,12 @@ struct nix_txsch {
 	u32  *pfvf_map;
 };
 
+struct nix_mark_format {
+	u8 total;
+	u8 in_use;
+	u32 *cfg;
+};
+
 struct npc_pkind {
 	struct rsrc_bmap rsrc;
 	u32	*pfchan_map;
@@ -178,6 +184,7 @@ struct nix_hw {
 	struct nix_txsch txsch[NIX_TXSCH_LVL_CNT]; /* Tx schedulers */
 	struct nix_mcast mcast;
 	struct nix_flowkey flowkey;
+	struct nix_mark_format mark_format;
 };
 
 struct rvu_hwinfo {
@@ -377,6 +384,8 @@ int rvu_mbox_handler_npa_lf_free(struct rvu *rvu, struct msg_req *req,
 /* NIX APIs */
 bool is_nixlf_attached(struct rvu *rvu, u16 pcifunc);
 int rvu_nix_init(struct rvu *rvu);
+int rvu_nix_reserve_mark_format(struct rvu *rvu, struct nix_hw *nix_hw,
+				int blkaddr, u32 cfg);
 void rvu_nix_freemem(struct rvu *rvu);
 int rvu_get_nixlf_count(struct rvu *rvu);
 void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf);
@@ -421,6 +430,9 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
 				     struct msg_rsp *rsp);
 int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
 				    struct msg_rsp *rsp);
+int rvu_mbox_handler_nix_mark_format_cfg(struct rvu *rvu,
+					 struct nix_mark_format_cfg  *req,
+					 struct nix_mark_format_cfg_rsp *rsp);
 
 /* NPC APIs */
 int rvu_npc_init(struct rvu *rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 2a7229809247..43639665e737 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -43,6 +43,19 @@ enum mc_buf_cnt {
 	MC_BUF_CNT_2048,
 };
 
+enum nix_makr_fmt_indexes {
+	NIX_MARK_CFG_IP_DSCP_RED,
+	NIX_MARK_CFG_IP_DSCP_YELLOW,
+	NIX_MARK_CFG_IP_DSCP_YELLOW_RED,
+	NIX_MARK_CFG_IP_ECN_RED,
+	NIX_MARK_CFG_IP_ECN_YELLOW,
+	NIX_MARK_CFG_IP_ECN_YELLOW_RED,
+	NIX_MARK_CFG_VLAN_DEI_RED,
+	NIX_MARK_CFG_VLAN_DEI_YELLOW,
+	NIX_MARK_CFG_VLAN_DEI_YELLOW_RED,
+	NIX_MARK_CFG_MAX,
+};
+
 /* For now considering MC resources needed for broadcast
  * pkt replication only. i.e 256 HWVFs + 12 PFs.
  */
@@ -939,6 +952,41 @@ int rvu_mbox_handler_nix_lf_free(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
+int rvu_mbox_handler_nix_mark_format_cfg(struct rvu *rvu,
+					 struct nix_mark_format_cfg  *req,
+					 struct nix_mark_format_cfg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	struct nix_hw *nix_hw;
+	struct rvu_pfvf *pfvf;
+	int blkaddr, rc;
+	u32 cfg;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (!pfvf->nixlf || blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	cfg = (((u32)req->offset & 0x7) << 16) |
+	      (((u32)req->y_mask & 0xF) << 12) |
+	      (((u32)req->y_val & 0xF) << 8) |
+	      (((u32)req->r_mask & 0xF) << 4) | ((u32)req->r_val & 0xF);
+
+	rc = rvu_nix_reserve_mark_format(rvu, nix_hw, blkaddr, cfg);
+	if (rc < 0) {
+		dev_err(rvu->dev, "No mark_format_ctl for (pf:%d, vf:%d)",
+			rvu_get_pf(pcifunc), pcifunc & RVU_PFVF_FUNC_MASK);
+		return NIX_AF_ERR_MARK_CFG_FAIL;
+	}
+
+	rsp->mark_format_idx = rc;
+	return 0;
+}
+
 /* Disable shaping of pkts by a scheduler queue
  * at a given scheduler level.
  */
@@ -1829,6 +1877,57 @@ static int nix_setup_txschq(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 	return 0;
 }
 
+int rvu_nix_reserve_mark_format(struct rvu *rvu, struct nix_hw *nix_hw,
+				int blkaddr, u32 cfg)
+{
+	int fmt_idx;
+
+	for (fmt_idx = 0; fmt_idx < nix_hw->mark_format.in_use; fmt_idx++) {
+		if (nix_hw->mark_format.cfg[fmt_idx] == cfg)
+			return fmt_idx;
+	}
+	if (fmt_idx >= nix_hw->mark_format.total)
+		return -ERANGE;
+
+	rvu_write64(rvu, blkaddr, NIX_AF_MARK_FORMATX_CTL(fmt_idx), cfg);
+	nix_hw->mark_format.cfg[fmt_idx] = cfg;
+	nix_hw->mark_format.in_use++;
+	return fmt_idx;
+}
+
+static int nix_af_mark_format_setup(struct rvu *rvu, struct nix_hw *nix_hw,
+				    int blkaddr)
+{
+	u64 cfgs[] = {
+		[NIX_MARK_CFG_IP_DSCP_RED]         = 0x10003,
+		[NIX_MARK_CFG_IP_DSCP_YELLOW]      = 0x11200,
+		[NIX_MARK_CFG_IP_DSCP_YELLOW_RED]  = 0x11203,
+		[NIX_MARK_CFG_IP_ECN_RED]          = 0x6000c,
+		[NIX_MARK_CFG_IP_ECN_YELLOW]       = 0x60c00,
+		[NIX_MARK_CFG_IP_ECN_YELLOW_RED]   = 0x60c0c,
+		[NIX_MARK_CFG_VLAN_DEI_RED]        = 0x30008,
+		[NIX_MARK_CFG_VLAN_DEI_YELLOW]     = 0x30800,
+		[NIX_MARK_CFG_VLAN_DEI_YELLOW_RED] = 0x30808,
+	};
+	int i, rc;
+	u64 total;
+
+	total = (rvu_read64(rvu, blkaddr, NIX_AF_PSE_CONST) & 0xFF00) >> 8;
+	nix_hw->mark_format.total = (u8)total;
+	nix_hw->mark_format.cfg = devm_kcalloc(rvu->dev, total, sizeof(u32),
+					       GFP_KERNEL);
+	if (!nix_hw->mark_format.cfg)
+		return -ENOMEM;
+	for (i = 0; i < NIX_MARK_CFG_MAX; i++) {
+		rc = rvu_nix_reserve_mark_format(rvu, nix_hw, blkaddr, cfgs[i]);
+		if (rc < 0)
+			dev_err(rvu->dev, "Err %d in setup mark format %d\n",
+				i, rc);
+	}
+
+	return 0;
+}
+
 int rvu_mbox_handler_nix_stats_rst(struct rvu *rvu, struct msg_req *req,
 				   struct msg_rsp *rsp)
 {
@@ -2589,6 +2688,10 @@ int rvu_nix_init(struct rvu *rvu)
 		if (err)
 			return err;
 
+		err = nix_af_mark_format_setup(rvu, hw->nix0, blkaddr);
+		if (err)
+			return err;
+
 		err = nix_setup_mcast(rvu, hw->nix0, blkaddr);
 		if (err)
 			return err;
-- 
cgit v1.2.3


From a253933e6a8609ef40bf296b8ad60892133636c8 Mon Sep 17 00:00:00 2001
From: Nithin Dabilpuram <ndabilpuram@marvell.com>
Date: Sun, 2 Dec 2018 18:17:46 +0530
Subject: octeontx2-af: Configure VLAN TPIDs

Setup TPID's for vlan0 and vlan1 for Tx VLAN insertion offloads.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 43639665e737..88875ebbe10a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -865,6 +865,13 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 		    (u64)pfvf->nix_qints_ctx->iova);
 	rvu_write64(rvu, blkaddr, NIX_AF_LFX_QINTS_CFG(nixlf), BIT_ULL(36));
 
+	/* Setup VLANX TPID's.
+	 * Use VLAN1 for 802.1Q
+	 * and VLAN0 for 802.1AD.
+	 */
+	cfg = (0x8100ULL << 16) | 0x88A8ULL;
+	rvu_write64(rvu, blkaddr, NIX_AF_LFX_TX_CFG(nixlf), cfg);
+
 	/* Enable LMTST for this NIX LF */
 	rvu_write64(rvu, blkaddr, NIX_AF_LFX_TX_CFG2(nixlf), BIT_ULL(0));
 
-- 
cgit v1.2.3


From 159a8a6734da0462314d54c7701518a6fbe2bef6 Mon Sep 17 00:00:00 2001
From: Vidhya Raman <vraman@marvell.com>
Date: Sun, 2 Dec 2018 18:17:47 +0530
Subject: octeontx2-af: Add L3 and L4 packet verification mailbox

Adds mailbox support for L4 checksum verification
and L3 and L4 length verification configuration.

Signed-off-by: Vidhya Raman <vraman@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   | 10 ++++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |  3 ++
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 42 ++++++++++++++++++++++
 3 files changed, 55 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 146f8f9656ba..0707a5aa6b1f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -203,6 +203,7 @@ M(NIX_LF_STOP_RX,	0x800e, nix_lf_stop_rx, msg_req, msg_rsp)	\
 M(NIX_MARK_FORMAT_CFG,	0x800f, nix_mark_format_cfg,			\
 				 nix_mark_format_cfg,			\
 				 nix_mark_format_cfg_rsp)		\
+M(NIX_SET_RX_CFG,	0x8010, nix_set_rx_cfg, nix_rx_cfg, msg_rsp)	\
 M(NIX_RXVLAN_ALLOC,	0x8012, nix_rxvlan_alloc, msg_req, msg_rsp)
 
 /* Messages initiated by AF (range 0xC00 - 0xDFF) */
@@ -609,6 +610,15 @@ struct nix_rx_mode {
 	u16	mode;
 };
 
+struct nix_rx_cfg {
+	struct mbox_msghdr hdr;
+#define NIX_RX_OL3_VERIFY   BIT(0)
+#define NIX_RX_OL4_VERIFY   BIT(1)
+	u8 len_verify; /* Outer L3/L4 len check */
+#define NIX_RX_CSUM_OL4_VERIFY  BIT(0)
+	u8 csum_verify; /* Outer L4 checksum verification */
+};
+
 struct nix_frs_cfg {
 	struct mbox_msghdr hdr;
 	u8	update_smq;    /* Update SMQ's min/max lens */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 563e3bfb89a5..c6d61a3a5729 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -433,6 +433,9 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
 int rvu_mbox_handler_nix_mark_format_cfg(struct rvu *rvu,
 					 struct nix_mark_format_cfg  *req,
 					 struct nix_mark_format_cfg_rsp *rsp);
+int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req,
+				    struct msg_rsp *rsp);
+
 
 /* NPC APIs */
 int rvu_npc_init(struct rvu *rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 88875ebbe10a..f1bd9de54cb7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -2504,6 +2504,48 @@ free_entry:
 	return err;
 }
 
+int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req,
+				    struct msg_rsp *rsp)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	u16 pcifunc = req->hdr.pcifunc;
+	struct rvu_block *block;
+	struct rvu_pfvf *pfvf;
+	int nixlf, blkaddr;
+	u64 cfg;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (!pfvf->nixlf || blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	block = &hw->block[blkaddr];
+	nixlf = rvu_get_lf(rvu, block, pcifunc, 0);
+	if (nixlf < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_LFX_RX_CFG(nixlf));
+	/* Set the interface configuration */
+	if (req->len_verify & BIT(0))
+		cfg |= BIT_ULL(41);
+	else
+		cfg &= ~BIT_ULL(41);
+
+	if (req->len_verify & BIT(1))
+		cfg |= BIT_ULL(40);
+	else
+		cfg &= ~BIT_ULL(40);
+
+	if (req->csum_verify & BIT(0))
+		cfg |= BIT_ULL(37);
+	else
+		cfg &= ~BIT_ULL(37);
+
+	rvu_write64(rvu, blkaddr, NIX_AF_LFX_RX_CFG(nixlf), cfg);
+
+	return 0;
+}
+
 static void nix_link_config(struct rvu *rvu, int blkaddr)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
-- 
cgit v1.2.3


From da5d32e1ab855f8d70f8c28d18b22d43f06f6d20 Mon Sep 17 00:00:00 2001
From: Nithin Dabilpuram <ndabilpuram@marvell.com>
Date: Sun, 2 Dec 2018 18:17:48 +0530
Subject: octeontx2-af: Add LSO format configuration mailbox

NIX_AF_LSO_FORMAT(0..31)_FIELD(0..7) register enables an SW defined
means to define LSO packet modification formats.

0..31 works as an index to choose the algorithm, On success, the mailbox
returns the index to the client of chosen LSO algorithm selection.
This index will be used in configuring the transmit descriptors.

Add mailbox interface to dynamically reserve and configure LSO format.

This commit also fixes 'sizem1' for NIX_LSOALG_TCP_FLAGS
to '1' i.e 2 Bytes.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   | 16 +++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    | 10 ++-
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 72 ++++++++++++++++++++--
 3 files changed, 91 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 0707a5aa6b1f..f8c332b1acec 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -204,6 +204,9 @@ M(NIX_MARK_FORMAT_CFG,	0x800f, nix_mark_format_cfg,			\
 				 nix_mark_format_cfg,			\
 				 nix_mark_format_cfg_rsp)		\
 M(NIX_SET_RX_CFG,	0x8010, nix_set_rx_cfg, nix_rx_cfg, msg_rsp)	\
+M(NIX_LSO_FORMAT_CFG,	0x8011, nix_lso_format_cfg,			\
+				 nix_lso_format_cfg,			\
+				 nix_lso_format_cfg_rsp)		\
 M(NIX_RXVLAN_ALLOC,	0x8012, nix_rxvlan_alloc, msg_req, msg_rsp)
 
 /* Messages initiated by AF (range 0xC00 - 0xDFF) */
@@ -421,6 +424,7 @@ enum nix_af_status {
 	NIX_AF_ERR_RSS_NOSPC_FIELD  = -415,
 	NIX_AF_ERR_RSS_NOSPC_ALGO   = -416,
 	NIX_AF_ERR_MARK_CFG_FAIL    = -417,
+	NIX_AF_ERR_LSO_CFG_FAIL     = -418,
 	NIX_AF_INVAL_NPA_PF_FUNC    = -419,
 	NIX_AF_INVAL_SSO_PF_FUNC    = -420,
 };
@@ -628,6 +632,18 @@ struct nix_frs_cfg {
 	u16	minlen;
 };
 
+struct nix_lso_format_cfg {
+	struct mbox_msghdr hdr;
+	u64 field_mask;
+#define NIX_LSO_FIELD_MAX	8
+	u64 fields[NIX_LSO_FIELD_MAX];
+};
+
+struct nix_lso_format_cfg_rsp {
+	struct mbox_msghdr hdr;
+	u8 lso_format_idx;
+};
+
 /* NPC mbox message structs */
 
 #define NPC_MCAM_ENTRY_INVALID	0xFFFF
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index c6d61a3a5729..3abdb98fb348 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -180,11 +180,17 @@ struct nix_flowkey {
 	int in_use;
 };
 
+struct nix_lso {
+	u8 total;
+	u8 in_use;
+};
+
 struct nix_hw {
 	struct nix_txsch txsch[NIX_TXSCH_LVL_CNT]; /* Tx schedulers */
 	struct nix_mcast mcast;
 	struct nix_flowkey flowkey;
 	struct nix_mark_format mark_format;
+	struct nix_lso lso;
 };
 
 struct rvu_hwinfo {
@@ -435,7 +441,9 @@ int rvu_mbox_handler_nix_mark_format_cfg(struct rvu *rvu,
 					 struct nix_mark_format_cfg_rsp *rsp);
 int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req,
 				    struct msg_rsp *rsp);
-
+int rvu_mbox_handler_nix_lso_format_cfg(struct rvu *rvu,
+					struct nix_lso_format_cfg *req,
+					struct nix_lso_format_cfg_rsp *rsp);
 
 /* NPC APIs */
 int rvu_npc_init(struct rvu *rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index f1bd9de54cb7..4a7609fd6dd0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -298,17 +298,21 @@ static void nix_setup_lso_tso_l4(struct rvu *rvu, int blkaddr,
 	/* TCP's flags field */
 	field.layer = NIX_TXLAYER_OL4;
 	field.offset = 12;
-	field.sizem1 = 0; /* not needed */
+	field.sizem1 = 1; /* 2 bytes */
 	field.alg = NIX_LSOALG_TCP_FLAGS;
 	rvu_write64(rvu, blkaddr,
 		    NIX_AF_LSO_FORMATX_FIELDX(format, (*fidx)++),
 		    *(u64 *)&field);
 }
 
-static void nix_setup_lso(struct rvu *rvu, int blkaddr)
+static void nix_setup_lso(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 {
 	u64 cfg, idx, fidx = 0;
 
+	/* Get max HW supported format indices */
+	cfg = (rvu_read64(rvu, blkaddr, NIX_AF_CONST1) >> 48) & 0xFF;
+	nix_hw->lso.total = cfg;
+
 	/* Enable LSO */
 	cfg = rvu_read64(rvu, blkaddr, NIX_AF_LSO_CFG);
 	/* For TSO, set first and middle segment flags to
@@ -318,7 +322,10 @@ static void nix_setup_lso(struct rvu *rvu, int blkaddr)
 	cfg |= (0xFFF2ULL << 32) | (0xFFF2ULL << 16);
 	rvu_write64(rvu, blkaddr, NIX_AF_LSO_CFG, cfg | BIT_ULL(63));
 
-	/* Configure format fields for TCPv4 segmentation offload */
+	/* Setup default static LSO formats
+	 *
+	 * Configure format fields for TCPv4 segmentation offload
+	 */
 	idx = NIX_LSO_FORMAT_IDX_TSOV4;
 	nix_setup_lso_tso_l3(rvu, blkaddr, idx, true, &fidx);
 	nix_setup_lso_tso_l4(rvu, blkaddr, idx, &fidx);
@@ -328,6 +335,7 @@ static void nix_setup_lso(struct rvu *rvu, int blkaddr)
 		rvu_write64(rvu, blkaddr,
 			    NIX_AF_LSO_FORMATX_FIELDX(idx, fidx), 0x0ULL);
 	}
+	nix_hw->lso.in_use++;
 
 	/* Configure format fields for TCPv6 segmentation offload */
 	idx = NIX_LSO_FORMAT_IDX_TSOV6;
@@ -340,6 +348,7 @@ static void nix_setup_lso(struct rvu *rvu, int blkaddr)
 		rvu_write64(rvu, blkaddr,
 			    NIX_AF_LSO_FORMATX_FIELDX(idx, fidx), 0x0ULL);
 	}
+	nix_hw->lso.in_use++;
 }
 
 static void nix_ctx_free(struct rvu *rvu, struct rvu_pfvf *pfvf)
@@ -2724,9 +2733,6 @@ int rvu_nix_init(struct rvu *rvu)
 	/* Restore CINT timer delay to HW reset values */
 	rvu_write64(rvu, blkaddr, NIX_AF_CINT_DELAY, 0x0ULL);
 
-	/* Configure segmentation offload formats */
-	nix_setup_lso(rvu, blkaddr);
-
 	if (blkaddr == BLKADDR_NIX0) {
 		hw->nix0 = devm_kzalloc(rvu->dev,
 					sizeof(struct nix_hw), GFP_KERNEL);
@@ -2745,6 +2751,9 @@ int rvu_nix_init(struct rvu *rvu)
 		if (err)
 			return err;
 
+		/* Configure segmentation offload formats */
+		nix_setup_lso(rvu, hw->nix0, blkaddr);
+
 		/* Config Outer/Inner L2, IP, TCP, UDP and SCTP NPC layer info.
 		 * This helps HW protocol checker to identify headers
 		 * and validate length and checksums.
@@ -2897,3 +2906,54 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf)
 
 	nix_ctx_free(rvu, pfvf);
 }
+
+int rvu_mbox_handler_nix_lso_format_cfg(struct rvu *rvu,
+					struct nix_lso_format_cfg *req,
+					struct nix_lso_format_cfg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	struct nix_hw *nix_hw;
+	struct rvu_pfvf *pfvf;
+	int blkaddr, idx, f;
+	u64 reg;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (!pfvf->nixlf || blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	/* Find existing matching LSO format, if any */
+	for (idx = 0; idx < nix_hw->lso.in_use; idx++) {
+		for (f = 0; f < NIX_LSO_FIELD_MAX; f++) {
+			reg = rvu_read64(rvu, blkaddr,
+					 NIX_AF_LSO_FORMATX_FIELDX(idx, f));
+			if (req->fields[f] != (reg & req->field_mask))
+				break;
+		}
+
+		if (f == NIX_LSO_FIELD_MAX)
+			break;
+	}
+
+	if (idx < nix_hw->lso.in_use) {
+		/* Match found */
+		rsp->lso_format_idx = idx;
+		return 0;
+	}
+
+	if (nix_hw->lso.in_use == nix_hw->lso.total)
+		return NIX_AF_ERR_LSO_CFG_FAIL;
+
+	rsp->lso_format_idx = nix_hw->lso.in_use++;
+
+	for (f = 0; f < NIX_LSO_FIELD_MAX; f++)
+		rvu_write64(rvu, blkaddr,
+			    NIX_AF_LSO_FORMATX_FIELDX(rsp->lso_format_idx, f),
+			    req->fields[f]);
+
+	return 0;
+}
-- 
cgit v1.2.3


From 23705adb2c6319c8ea3cf21b99c8b3eb85fa9734 Mon Sep 17 00:00:00 2001
From: Vamsi Attunuru <vamsi.attunuru@marvell.com>
Date: Sun, 2 Dec 2018 18:17:49 +0530
Subject: octeontx2-af: Enable mkex profile

The following set of NPC registers allow the driver to configure NPC
to generate different key value schemes to compare against packet
payload in MCAM search.

NPC_AF_INTF(0..1)_KEX_CFG
NPC_AF_KEX_LDATA(0..1)_FLAGS_CFG
NPC_AF_INTF(0..1)_LID(0..7)_LT(0..15)_LD(0..1)_CFG
NPC_AF_INTF(0..1)_LDATA(0..1)_FLAGS(0..15)_CFG

Currently, the AF driver populates these registers to
configure the default values to address the most common
use cases such as key generation for channel number + DMAC.

The secure firmware stores different configuration
value of these registers to enable different NPC use case
along with the name for the lookup.

Patch loads profile binary from secure firmware over
the exiting CGX mailbox interface and apply the profile.

AF driver shall fall back to the default configuration
in case of any errors.

The AF consumer driver can know the selected profile
on response to NPC_GET_KEX_CFG mailbox by introducing
mkex_pfl_name in the struct npc_get_kex_cfg_rsp.

Signed-off-by: Vamsi Attunuru <vamsi.attunuru@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c    |  54 ++++++++++
 drivers/net/ethernet/marvell/octeontx2/af/cgx.h    |   1 +
 .../net/ethernet/marvell/octeontx2/af/cgx_fw_if.h  |  12 +++
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |   2 +
 drivers/net/ethernet/marvell/octeontx2/af/npc.h    |  18 ++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c    |  15 +++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    |   2 +
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 111 ++++++++++++++++++++-
 8 files changed, 213 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 4c94571e03eb..742f0c1f60df 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -498,6 +498,60 @@ static inline bool cgx_event_is_linkevent(u64 event)
 		return false;
 }
 
+static inline int cgx_fwi_get_mkex_prfl_sz(u64 *prfl_sz,
+					   struct cgx *cgx)
+{
+	u64 req = 0;
+	u64 resp;
+	int err;
+
+	req = FIELD_SET(CMDREG_ID, CGX_CMD_GET_MKEX_PRFL_SIZE, req);
+	err = cgx_fwi_cmd_generic(req, &resp, cgx, 0);
+	if (!err)
+		*prfl_sz = FIELD_GET(RESP_MKEX_PRFL_SIZE, resp);
+
+	return err;
+}
+
+static inline int cgx_fwi_get_mkex_prfl_addr(u64 *prfl_addr,
+					     struct cgx *cgx)
+{
+	u64 req = 0;
+	u64 resp;
+	int err;
+
+	req = FIELD_SET(CMDREG_ID, CGX_CMD_GET_MKEX_PRFL_ADDR, req);
+	err = cgx_fwi_cmd_generic(req, &resp, cgx, 0);
+	if (!err)
+		*prfl_addr = FIELD_GET(RESP_MKEX_PRFL_ADDR, resp);
+
+	return err;
+}
+
+int cgx_get_mkex_prfl_info(u64 *addr, u64 *size)
+{
+	struct cgx *cgx_dev;
+	int err;
+
+	if (!addr || !size)
+		return -EINVAL;
+
+	cgx_dev = list_first_entry(&cgx_list, struct cgx, cgx_list);
+	if (!cgx_dev)
+		return -ENXIO;
+
+	err = cgx_fwi_get_mkex_prfl_sz(size, cgx_dev);
+	if (err)
+		return -EIO;
+
+	err = cgx_fwi_get_mkex_prfl_addr(addr, cgx_dev);
+	if (err)
+		return -EIO;
+
+	return 0;
+}
+EXPORT_SYMBOL(cgx_get_mkex_prfl_info);
+
 static irqreturn_t cgx_fwi_event_handler(int irq, void *data)
 {
 	struct lmac *lmac = data;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index 8c2be8493321..206dc5dc1df8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -111,4 +111,5 @@ int cgx_lmac_internal_loopback(void *cgxd, int lmac_id, bool enable);
 int cgx_get_link_info(void *cgxd, int lmac_id,
 		      struct cgx_link_user_info *linfo);
 int cgx_lmac_linkup_start(void *cgxd);
+int cgx_get_mkex_prfl_info(u64 *addr, u64 *size);
 #endif /* CGX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
index 2d9fe51c6616..fb3ba4968a9b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
@@ -78,6 +78,8 @@ enum cgx_cmd_id {
 	CGX_CMD_LINK_STATE_CHANGE,
 	CGX_CMD_MODE_CHANGE,		/* hot plug support */
 	CGX_CMD_INTF_SHUTDOWN,
+	CGX_CMD_GET_MKEX_PRFL_SIZE,
+	CGX_CMD_GET_MKEX_PRFL_ADDR
 };
 
 /* async event ids */
@@ -137,6 +139,16 @@ enum cgx_cmd_own {
  */
 #define RESP_MAC_ADDR		GENMASK_ULL(56, 9)
 
+/* Response to cmd ID as CGX_CMD_GET_MKEX_PRFL_SIZE with cmd status as
+ * CGX_STAT_SUCCESS
+ */
+#define RESP_MKEX_PRFL_SIZE		GENMASK_ULL(63, 9)
+
+/* Response to cmd ID as CGX_CMD_GET_MKEX_PRFL_ADDR with cmd status as
+ * CGX_STAT_SUCCESS
+ */
+#define RESP_MKEX_PRFL_ADDR		GENMASK_ULL(63, 9)
+
 /* Response to cmd ID - CGX_CMD_LINK_BRING_UP/DOWN, event ID CGX_EVT_LINK_CHANGE
  * status can be either CGX_STAT_FAIL or CGX_STAT_SUCCESS
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index f8c332b1acec..76a4575d18ff 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -788,6 +788,8 @@ struct npc_get_kex_cfg_rsp {
 	u64 intf_lid_lt_ld[NPC_MAX_INTF][NPC_MAX_LID][NPC_MAX_LT][NPC_MAX_LD];
 	/* NPC_AF_INTF(0..1)_LDATA(0..1)_FLAGS(0..15)_CFG */
 	u64 intf_ld_flags[NPC_MAX_INTF][NPC_MAX_LD][NPC_MAX_LFL];
+#define MKEX_NAME_LEN 128
+	u8 mkex_pfl_name[MKEX_NAME_LEN];
 };
 
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index a7a20afb3ba0..8d6d90fdfb73 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -265,4 +265,22 @@ struct nix_rx_action {
 #define VTAG0_LID_MASK		GENMASK_ULL(10, 8)
 #define VTAG0_RELPTR_MASK	GENMASK_ULL(7, 0)
 
+struct npc_mcam_kex {
+	/* MKEX Profle Header */
+	u64 mkex_sign; /* "mcam-kex-profile" (8 bytes/ASCII characters) */
+	u8 name[MKEX_NAME_LEN];   /* MKEX Profile name */
+	u64 cpu_model;   /* Format as profiled by CPU hardware */
+	u64 kpu_version; /* KPU firmware/profile version */
+	u64 reserved; /* Reserved for extension */
+
+	/* MKEX Profle Data */
+	u64 keyx_cfg[NPC_MAX_INTF]; /* NPC_AF_INTF(0..1)_KEX_CFG */
+	/* NPC_AF_KEX_LDATA(0..1)_FLAGS_CFG */
+	u64 kex_ld_flags[NPC_MAX_LD];
+	/* NPC_AF_INTF(0..1)_LID(0..7)_LT(0..15)_LD(0..1)_CFG */
+	u64 intf_lid_lt_ld[NPC_MAX_INTF][NPC_MAX_LID][NPC_MAX_LT][NPC_MAX_LD];
+	/* NPC_AF_INTF(0..1)_LDATA(0..1)_FLAGS(0..15)_CFG */
+	u64 intf_ld_flags[NPC_MAX_INTF][NPC_MAX_LD][NPC_MAX_LFL];
+} __packed;
+
 #endif /* NPC_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 4d061d971956..e581091c09c4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -52,6 +52,10 @@ MODULE_LICENSE("GPL v2");
 MODULE_VERSION(DRV_VERSION);
 MODULE_DEVICE_TABLE(pci, rvu_id_table);
 
+static char *mkex_profile; /* MKEX profile name */
+module_param(mkex_profile, charp, 0000);
+MODULE_PARM_DESC(mkex_profile, "MKEX profile name string");
+
 /* Poll a RVU block's register 'offset', for a 'zero'
  * or 'nonzero' at bits specified by 'mask'
  */
@@ -2359,6 +2363,14 @@ static void rvu_disable_sriov(struct rvu *rvu)
 	pci_disable_sriov(rvu->pdev);
 }
 
+static void rvu_update_module_params(struct rvu *rvu)
+{
+	const char *default_pfl_name = "default";
+
+	strscpy(rvu->mkex_pfl_name,
+		mkex_profile ? mkex_profile : default_pfl_name, MKEX_NAME_LEN);
+}
+
 static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct device *dev = &pdev->dev;
@@ -2412,6 +2424,9 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_release_regions;
 	}
 
+	/* Store module params in rvu structure */
+	rvu_update_module_params(rvu);
+
 	/* Check which blocks the HW supports */
 	rvu_check_block_implemented(rvu);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 3abdb98fb348..c9d60b0554c0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -261,6 +261,8 @@ struct rvu {
 	struct			workqueue_struct *cgx_evh_wq;
 	spinlock_t		cgx_evq_lock; /* cgx event queue lock */
 	struct list_head	cgx_evq_head; /* cgx event queue head */
+
+	char mkex_pfl_name[MKEX_NAME_LEN]; /* Configured MKEX profile name */
 };
 
 static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index bf81031f0fdd..15f70273e29c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -16,6 +16,7 @@
 #include "rvu_reg.h"
 #include "rvu.h"
 #include "npc.h"
+#include "cgx.h"
 #include "npc_profile.h"
 
 #define RSVD_MCAM_ENTRIES_PER_PF	2 /* Bcast & Promisc */
@@ -731,6 +732,111 @@ static void npc_config_ldata_extract(struct rvu *rvu, int blkaddr)
 	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_TCP, 1, cfg);
 }
 
+static void npc_program_mkex_profile(struct rvu *rvu, int blkaddr,
+				     struct npc_mcam_kex *mkex)
+{
+	int lid, lt, ld, fl;
+
+	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX),
+		    mkex->keyx_cfg[NIX_INTF_RX]);
+	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX),
+		    mkex->keyx_cfg[NIX_INTF_TX]);
+
+	for (ld = 0; ld < NPC_MAX_LD; ld++)
+		rvu_write64(rvu, blkaddr, NPC_AF_KEX_LDATAX_FLAGS_CFG(ld),
+			    mkex->kex_ld_flags[ld]);
+
+	for (lid = 0; lid < NPC_MAX_LID; lid++) {
+		for (lt = 0; lt < NPC_MAX_LT; lt++) {
+			for (ld = 0; ld < NPC_MAX_LD; ld++) {
+				SET_KEX_LD(NIX_INTF_RX, lid, lt, ld,
+					   mkex->intf_lid_lt_ld[NIX_INTF_RX]
+					   [lid][lt][ld]);
+
+				SET_KEX_LD(NIX_INTF_TX, lid, lt, ld,
+					   mkex->intf_lid_lt_ld[NIX_INTF_TX]
+					   [lid][lt][ld]);
+			}
+		}
+	}
+
+	for (ld = 0; ld < NPC_MAX_LD; ld++) {
+		for (fl = 0; fl < NPC_MAX_LFL; fl++) {
+			SET_KEX_LDFLAGS(NIX_INTF_RX, ld, fl,
+					mkex->intf_ld_flags[NIX_INTF_RX]
+					[ld][fl]);
+
+			SET_KEX_LDFLAGS(NIX_INTF_TX, ld, fl,
+					mkex->intf_ld_flags[NIX_INTF_TX]
+					[ld][fl]);
+		}
+	}
+}
+
+/* strtoull of "mkexprof" with base:36 */
+#define MKEX_SIGN      0x19bbfdbd15f
+#define MKEX_END_SIGN  0xdeadbeef
+
+static void npc_load_mkex_profile(struct rvu *rvu, int blkaddr)
+{
+	const char *mkex_profile = rvu->mkex_pfl_name;
+	struct device *dev = &rvu->pdev->dev;
+	void __iomem *mkex_prfl_addr = NULL;
+	struct npc_mcam_kex *mcam_kex;
+	u64 prfl_addr;
+	u64 prfl_sz;
+
+	/* If user not selected mkex profile */
+	if (!strncmp(mkex_profile, "default", MKEX_NAME_LEN))
+		goto load_default;
+
+	if (cgx_get_mkex_prfl_info(&prfl_addr, &prfl_sz))
+		goto load_default;
+
+	if (!prfl_addr || !prfl_sz)
+		goto load_default;
+
+	mkex_prfl_addr = ioremap_wc(prfl_addr, prfl_sz);
+	if (!mkex_prfl_addr)
+		goto load_default;
+
+	mcam_kex = (struct npc_mcam_kex *)mkex_prfl_addr;
+
+	while (((s64)prfl_sz > 0) && (mcam_kex->mkex_sign != MKEX_END_SIGN)) {
+		/* Compare with mkex mod_param name string */
+		if (mcam_kex->mkex_sign == MKEX_SIGN &&
+		    !strncmp(mcam_kex->name, mkex_profile, MKEX_NAME_LEN)) {
+			/* Due to an errata (35786) in A0 pass silicon,
+			 * parse nibble enable configuration has to be
+			 * identical for both Rx and Tx interfaces.
+			 */
+			if (is_rvu_9xxx_A0(rvu) &&
+			    mcam_kex->keyx_cfg[NIX_INTF_RX] !=
+			    mcam_kex->keyx_cfg[NIX_INTF_TX])
+				goto load_default;
+
+			/* Program selected mkex profile */
+			npc_program_mkex_profile(rvu, blkaddr, mcam_kex);
+
+			goto unmap;
+		}
+
+		mcam_kex++;
+		prfl_sz -= sizeof(struct npc_mcam_kex);
+	}
+	dev_warn(dev, "Failed to load requested profile: %s\n",
+		 rvu->mkex_pfl_name);
+
+load_default:
+	dev_info(rvu->dev, "Using default mkex profile\n");
+	/* Config packet data and flags extraction into PARSE result */
+	npc_config_ldata_extract(rvu, blkaddr);
+
+unmap:
+	if (mkex_prfl_addr)
+		iounmap(mkex_prfl_addr);
+}
+
 static void npc_config_kpuaction(struct rvu *rvu, int blkaddr,
 				 struct npc_kpu_profile_action *kpuaction,
 				 int kpu, int entry, bool pkind)
@@ -1068,8 +1174,8 @@ int rvu_npc_init(struct rvu *rvu)
 	if (err)
 		return err;
 
-	/* Config packet data and flags extraction into PARSE result */
-	npc_config_ldata_extract(rvu, blkaddr);
+	/* Configure MKEX profile */
+	npc_load_mkex_profile(rvu, blkaddr);
 
 	/* Set TX miss action to UCAST_DEFAULT i.e
 	 * transmit the packet on NIX LF SQ's default channel.
@@ -2077,6 +2183,7 @@ int rvu_mbox_handler_npc_get_kex_cfg(struct rvu *rvu, struct msg_req *req,
 					GET_KEX_LDFLAGS(NIX_INTF_TX, ld, fl);
 		}
 	}
+	memcpy(rsp->mkex_pfl_name, rvu->mkex_pfl_name, MKEX_NAME_LEN);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 30fcd6a9edf1a169a07c3558f3a6e6a0007760fb Mon Sep 17 00:00:00 2001
From: Jose Abreu <jose.abreu@synopsys.com>
Date: Sun, 2 Dec 2018 16:33:14 +0100
Subject: net: phy: Also request modules for C45 IDs

Logic of phy_device_create() requests PHY modules according to PHY ID
but for C45 PHYs we use different field for the IDs.

Let's also request the modules for these IDs.

Changes from v1:
- Only request C22 modules if C45 are not present (Andrew)

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Joao Pinto <joao.pinto@synopsys.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 40404a8f5f5e..e6720e2a2da6 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -605,7 +605,21 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
 	 * driver will get bored and give up as soon as it finds that
 	 * there's no driver _already_ loaded.
 	 */
-	request_module(MDIO_MODULE_PREFIX MDIO_ID_FMT, MDIO_ID_ARGS(phy_id));
+	if (is_c45 && c45_ids) {
+		const int num_ids = ARRAY_SIZE(c45_ids->device_ids);
+		int i;
+
+		for (i = 1; i < num_ids; i++) {
+			if (!(c45_ids->devices_in_package & (1 << i)))
+				continue;
+
+			request_module(MDIO_MODULE_PREFIX MDIO_ID_FMT,
+				       MDIO_ID_ARGS(c45_ids->device_ids[i]));
+		}
+	} else {
+		request_module(MDIO_MODULE_PREFIX MDIO_ID_FMT,
+			       MDIO_ID_ARGS(phy_id));
+	}
 
 	device_initialize(&mdiodev->dev);
 
-- 
cgit v1.2.3


From 95aac2cdafd8c8298c9b2589c52f44db0d824e0e Mon Sep 17 00:00:00 2001
From: Erez Alfasi <ereza@mellanox.com>
Date: Sun, 2 Dec 2018 17:40:25 +0200
Subject: net/mlx4_core: Fix return codes of unsupported operations

Functions __set_port_type and mlx4_check_port_params returned
-EINVAL while the proper return code is -EOPNOTSUPP as a
result of an unsupported operation. All drivers should generate
this and all users should check for it when detecting an
unsupported functionality.

Signed-off-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 6a046030e873..4afe56a6eedf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -313,7 +313,7 @@ int mlx4_check_port_params(struct mlx4_dev *dev,
 		for (i = 0; i < dev->caps.num_ports - 1; i++) {
 			if (port_type[i] != port_type[i + 1]) {
 				mlx4_err(dev, "Only same port types supported on this HCA, aborting\n");
-				return -EINVAL;
+				return -EOPNOTSUPP;
 			}
 		}
 	}
@@ -322,7 +322,7 @@ int mlx4_check_port_params(struct mlx4_dev *dev,
 		if (!(port_type[i] & dev->caps.supported_type[i+1])) {
 			mlx4_err(dev, "Requested port type for port %d is not supported on this HCA\n",
 				 i + 1);
-			return -EINVAL;
+			return -EOPNOTSUPP;
 		}
 	}
 	return 0;
@@ -1188,8 +1188,7 @@ static int __set_port_type(struct mlx4_port_info *info,
 		mlx4_err(mdev,
 			 "Requested port type for port %d is not supported on this HCA\n",
 			 info->port);
-		err = -EINVAL;
-		goto err_sup;
+		return -EOPNOTSUPP;
 	}
 
 	mlx4_stop_sense(mdev);
@@ -1211,7 +1210,7 @@ static int __set_port_type(struct mlx4_port_info *info,
 		for (i = 1; i <= mdev->caps.num_ports; i++) {
 			if (mdev->caps.possible_type[i] == MLX4_PORT_TYPE_AUTO) {
 				mdev->caps.possible_type[i] = mdev->caps.port_type[i];
-				err = -EINVAL;
+				err = -EOPNOTSUPP;
 			}
 		}
 	}
@@ -1237,7 +1236,7 @@ static int __set_port_type(struct mlx4_port_info *info,
 out:
 	mlx4_start_sense(mdev);
 	mutex_unlock(&priv->port_mutex);
-err_sup:
+
 	return err;
 }
 
-- 
cgit v1.2.3


From 92a59ad040e339da838c0a9fc681bbae619a39e3 Mon Sep 17 00:00:00 2001
From: Erez Alfasi <ereza@mellanox.com>
Date: Sun, 2 Dec 2018 17:40:26 +0200
Subject: net/mlx4_core: Fix several coding style errors

Fix 3 checkpatch errors within mlx4/main.c:
- Unnecessary mlx4_debug_level global variable initialization to 0.
- Prohibited space before comma.
- Whitespaces instead of tab.

Signed-off-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 4afe56a6eedf..bdb8dd161923 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -63,7 +63,7 @@ struct workqueue_struct *mlx4_wq;
 
 #ifdef CONFIG_MLX4_DEBUG
 
-int mlx4_debug_level = 0;
+int mlx4_debug_level; /* 0 by default */
 module_param_named(debug_level, mlx4_debug_level, int, 0644);
 MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0");
 
@@ -83,7 +83,7 @@ MODULE_PARM_DESC(msi_x, "0 - don't use MSI-X, 1 - use MSI-X, >1 - limit number o
 
 static uint8_t num_vfs[3] = {0, 0, 0};
 static int num_vfs_argc;
-module_param_array(num_vfs, byte , &num_vfs_argc, 0444);
+module_param_array(num_vfs, byte, &num_vfs_argc, 0444);
 MODULE_PARM_DESC(num_vfs, "enable #num_vfs functions if num_vfs > 0\n"
 			  "num_vfs=port1,port2,port1+2");
 
@@ -3251,7 +3251,7 @@ disable_sriov:
 free_mem:
 	dev->persist->num_vfs = 0;
 	kfree(dev->dev_vfs);
-        dev->dev_vfs = NULL;
+	dev->dev_vfs = NULL;
 	return dev_flags & ~MLX4_FLAG_MASTER;
 }
 
-- 
cgit v1.2.3


From 6f6c74fad8655b1227f659de2e10d6b812acc276 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Mon, 3 Dec 2018 09:13:35 -0500
Subject: nfp: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/netronome/nfp/nfp_net_debugfs.c   | 42 +++++-----------------
 1 file changed, 8 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
index 69b1c9b62e3d..ab7f2498e1c4 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
@@ -8,7 +8,7 @@
 
 static struct dentry *nfp_dir;
 
-static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
+static int nfp_rx_q_show(struct seq_file *file, void *data)
 {
 	struct nfp_net_r_vector *r_vec = file->private;
 	struct nfp_net_rx_ring *rx_ring;
@@ -65,31 +65,12 @@ out:
 	rtnl_unlock();
 	return 0;
 }
+DEFINE_SHOW_ATTRIBUTE(nfp_rx_q);
 
-static int nfp_net_debugfs_rx_q_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, nfp_net_debugfs_rx_q_read, inode->i_private);
-}
+static int nfp_tx_q_show(struct seq_file *file, void *data);
+DEFINE_SHOW_ATTRIBUTE(nfp_tx_q);
 
-static const struct file_operations nfp_rx_q_fops = {
-	.owner = THIS_MODULE,
-	.open = nfp_net_debugfs_rx_q_open,
-	.release = single_release,
-	.read = seq_read,
-	.llseek = seq_lseek
-};
-
-static int nfp_net_debugfs_tx_q_open(struct inode *inode, struct file *f);
-
-static const struct file_operations nfp_tx_q_fops = {
-	.owner = THIS_MODULE,
-	.open = nfp_net_debugfs_tx_q_open,
-	.release = single_release,
-	.read = seq_read,
-	.llseek = seq_lseek
-};
-
-static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
+static int nfp_tx_q_show(struct seq_file *file, void *data)
 {
 	struct nfp_net_r_vector *r_vec = file->private;
 	struct nfp_net_tx_ring *tx_ring;
@@ -158,18 +139,11 @@ out:
 	return 0;
 }
 
-static int nfp_net_debugfs_tx_q_open(struct inode *inode, struct file *f)
+static int nfp_xdp_q_show(struct seq_file *file, void *data)
 {
-	return single_open(f, nfp_net_debugfs_tx_q_read, inode->i_private);
+	return nfp_tx_q_show(file, data);
 }
-
-static const struct file_operations nfp_xdp_q_fops = {
-	.owner = THIS_MODULE,
-	.open = nfp_net_debugfs_tx_q_open,
-	.release = single_release,
-	.read = seq_read,
-	.llseek = seq_lseek
-};
+DEFINE_SHOW_ATTRIBUTE(nfp_xdp_q);
 
 void nfp_net_debugfs_vnic_add(struct nfp_net *nn, struct dentry *ddir)
 {
-- 
cgit v1.2.3


From fb0d9c6339e0d8d1eb09414a09df8513499bbf79 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Mon, 3 Dec 2018 09:22:09 -0500
Subject: net: stmmac: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 34 +++--------------------
 1 file changed, 4 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 076a8be18d67..c728ed1375b2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3891,7 +3891,7 @@ static void sysfs_display_ring(void *head, int size, int extend_desc,
 	}
 }
 
-static int stmmac_sysfs_ring_read(struct seq_file *seq, void *v)
+static int stmmac_rings_status_show(struct seq_file *seq, void *v)
 {
 	struct net_device *dev = seq->private;
 	struct stmmac_priv *priv = netdev_priv(dev);
@@ -3933,23 +3933,9 @@ static int stmmac_sysfs_ring_read(struct seq_file *seq, void *v)
 
 	return 0;
 }
+DEFINE_SHOW_ATTRIBUTE(stmmac_rings_status);
 
-static int stmmac_sysfs_ring_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, stmmac_sysfs_ring_read, inode->i_private);
-}
-
-/* Debugfs files, should appear in /sys/kernel/debug/stmmaceth/eth0 */
-
-static const struct file_operations stmmac_rings_status_fops = {
-	.owner = THIS_MODULE,
-	.open = stmmac_sysfs_ring_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-static int stmmac_sysfs_dma_cap_read(struct seq_file *seq, void *v)
+static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
 {
 	struct net_device *dev = seq->private;
 	struct stmmac_priv *priv = netdev_priv(dev);
@@ -4012,19 +3998,7 @@ static int stmmac_sysfs_dma_cap_read(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-static int stmmac_sysfs_dma_cap_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, stmmac_sysfs_dma_cap_read, inode->i_private);
-}
-
-static const struct file_operations stmmac_dma_cap_fops = {
-	.owner = THIS_MODULE,
-	.open = stmmac_sysfs_dma_cap_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(stmmac_dma_cap);
 
 static int stmmac_init_fs(struct net_device *dev)
 {
-- 
cgit v1.2.3


From 25079154f71170f615f67c33d47af1188117668b Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Mon, 3 Dec 2018 09:26:38 -0500
Subject: net: qca_spi: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Acked-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_debug.c | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c
index 1450f386bc65..bcb890b18a94 100644
--- a/drivers/net/ethernet/qualcomm/qca_debug.c
+++ b/drivers/net/ethernet/qualcomm/qca_debug.c
@@ -126,19 +126,7 @@ qcaspi_info_show(struct seq_file *s, void *what)
 
 	return 0;
 }
-
-static int
-qcaspi_info_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, qcaspi_info_show, inode->i_private);
-}
-
-static const struct file_operations qcaspi_info_ops = {
-	.open = qcaspi_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(qcaspi_info);
 
 void
 qcaspi_init_device_debugfs(struct qcaspi *qca)
@@ -154,7 +142,7 @@ qcaspi_init_device_debugfs(struct qcaspi *qca)
 		return;
 	}
 	debugfs_create_file("info", S_IFREG | 0444, device_root, qca,
-			    &qcaspi_info_ops);
+			    &qcaspi_info_fops);
 }
 
 void
-- 
cgit v1.2.3


From d9bbd6a1a56eccb2b1198b8f2008d622982df0a1 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Mon, 3 Dec 2018 09:34:11 -0500
Subject: net: marvell: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/skge.c | 14 +-------------
 drivers/net/ethernet/marvell/sky2.c | 14 +-------------
 2 files changed, 2 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 9c08c3650c02..04fd1f135011 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -3732,19 +3732,7 @@ static int skge_debug_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-static int skge_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, skge_debug_show, inode->i_private);
-}
-
-static const struct file_operations skge_debug_fops = {
-	.owner		= THIS_MODULE,
-	.open		= skge_debug_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(skge_debug);
 
 /*
  * Use network device events to create/remove/rename
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index c7cd0081058e..f3a5fa84860f 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -4621,19 +4621,7 @@ static int sky2_debug_show(struct seq_file *seq, void *v)
 	napi_enable(&hw->napi);
 	return 0;
 }
-
-static int sky2_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, sky2_debug_show, inode->i_private);
-}
-
-static const struct file_operations sky2_debug_fops = {
-	.owner		= THIS_MODULE,
-	.open		= sky2_debug_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(sky2_debug);
 
 /*
  * Use network device events to create/remove/rename
-- 
cgit v1.2.3


From 6cd0014ab90f6959fa1f8cc8b3f38d302457c919 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Nov 2018 20:53:33 +0200
Subject: net/mlx5: Align SRQ licenses and copyright information

Ensure that both RDMA and netdev parts of SRQ implementation
has same copyright and license information annotated by SPDX
tags.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/srq.c              | 31 ++-------------------------
 drivers/net/ethernet/mellanox/mlx5/core/srq.c | 31 ++-------------------------
 include/linux/mlx5/srq.h                      | 31 ++-------------------------
 3 files changed, 6 insertions(+), 87 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index d012e7dbcc38..28794780062e 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /*
- * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
+ * Copyright (c) 2013-2018, Mellanox Technologies inc.  All rights reserved.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
index 79c5f0d57956..10036aaa200a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /*
- * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
+ * Copyright (c) 2013-2018, Mellanox Technologies inc.  All rights reserved.
  */
 
 #include <linux/kernel.h>
diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h
index 1b1f3c20c6a3..77bc4264066d 100644
--- a/include/linux/mlx5/srq.h
+++ b/include/linux/mlx5/srq.h
@@ -1,33 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
 /*
- * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
+ * Copyright (c) 2013-2018, Mellanox Technologies. All rights reserved.
  */
 
 #ifndef MLX5_SRQ_H
-- 
cgit v1.2.3


From 5b5f0f16276021794038f12adc56df70cec42b4f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Nov 2018 20:53:34 +0200
Subject: net/mlx5: Remove dead transobj code

Delete functions which are not called and not needed.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/transobj.c | 66 ----------------------
 include/linux/mlx5/transobj.h                      |  5 --
 2 files changed, 71 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index a1ee9a8a769e..ab482124e901 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -301,72 +301,6 @@ int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out)
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
 }
 
-int mlx5_core_arm_rmp(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm)
-{
-	void *in;
-	void *rmpc;
-	void *wq;
-	void *bitmask;
-	int  err;
-
-	in = kvzalloc(MLX5_ST_SZ_BYTES(modify_rmp_in), GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
-	rmpc    = MLX5_ADDR_OF(modify_rmp_in,   in,   ctx);
-	bitmask = MLX5_ADDR_OF(modify_rmp_in,   in,   bitmask);
-	wq      = MLX5_ADDR_OF(rmpc,	        rmpc, wq);
-
-	MLX5_SET(modify_rmp_in, in,	 rmp_state, MLX5_RMPC_STATE_RDY);
-	MLX5_SET(modify_rmp_in, in,	 rmpn,      rmpn);
-	MLX5_SET(wq,		wq,	 lwm,	    lwm);
-	MLX5_SET(rmp_bitmask,	bitmask, lwm,	    1);
-	MLX5_SET(rmpc,		rmpc,	 state,	    MLX5_RMPC_STATE_RDY);
-
-	err =  mlx5_core_modify_rmp(dev, in, MLX5_ST_SZ_BYTES(modify_rmp_in));
-
-	kvfree(in);
-
-	return err;
-}
-
-int mlx5_core_create_xsrq(struct mlx5_core_dev *dev, u32 *in, int inlen,
-			  u32 *xsrqn)
-{
-	u32 out[MLX5_ST_SZ_DW(create_xrc_srq_out)] = {0};
-	int err;
-
-	MLX5_SET(create_xrc_srq_in, in, opcode,     MLX5_CMD_OP_CREATE_XRC_SRQ);
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
-	if (!err)
-		*xsrqn = MLX5_GET(create_xrc_srq_out, out, xrc_srqn);
-
-	return err;
-}
-
-int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 xsrqn)
-{
-	u32 in[MLX5_ST_SZ_DW(destroy_xrc_srq_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_xrc_srq_out)] = {0};
-
-	MLX5_SET(destroy_xrc_srq_in, in, opcode,   MLX5_CMD_OP_DESTROY_XRC_SRQ);
-	MLX5_SET(destroy_xrc_srq_in, in, xrc_srqn, xsrqn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 xsrqn, u16 lwm)
-{
-	u32 in[MLX5_ST_SZ_DW(arm_xrc_srq_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(arm_xrc_srq_out)] = {0};
-
-	MLX5_SET(arm_xrc_srq_in, in, opcode,   MLX5_CMD_OP_ARM_XRC_SRQ);
-	MLX5_SET(arm_xrc_srq_in, in, xrc_srqn, xsrqn);
-	MLX5_SET(arm_xrc_srq_in, in, lwm,      lwm);
-	MLX5_SET(arm_xrc_srq_in, in, op_mod,
-		 MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
 int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *rqtn)
 {
diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h
index 7f5ca2cd3a32..39ebb699875b 100644
--- a/include/linux/mlx5/transobj.h
+++ b/include/linux/mlx5/transobj.h
@@ -63,11 +63,6 @@ int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen,
 int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen);
 int mlx5_core_destroy_rmp(struct mlx5_core_dev *dev, u32 rmpn);
 int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out);
-int mlx5_core_arm_rmp(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm);
-int mlx5_core_create_xsrq(struct mlx5_core_dev *dev, u32 *in, int inlen,
-			  u32 *rmpn);
-int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 rmpn);
-int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm);
 
 int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *rqtn);
-- 
cgit v1.2.3


From 26d1164dff81096c38d955f00b84a0075563d8c7 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Nov 2018 20:53:35 +0200
Subject: net/mlx5: Remove not-used lib/eq.h header file

lib/eq.h is needed for EQ manipulation which are not performed in SRQ.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/srq.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
index 10036aaa200a..248f1c8dd5d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
@@ -11,7 +11,6 @@
 #include <rdma/ib_verbs.h>
 #include <linux/mlx5/transobj.h>
 #include "mlx5_core.h"
-#include "lib/eq.h"
 
 static int srq_event_notifier(struct notifier_block *nb,
 			      unsigned long type, void *data)
-- 
cgit v1.2.3


From c23f88cb575fe4a0b49603d7f9e5c3782886269f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Nov 2018 20:53:36 +0200
Subject: net/mlx5: Remove references to local mlx5_core functions

As a preparation to move SRQ functionality to RDMA, drop all references
to mlx5_core logic and make SRQ be dependent on shared code only.

Most of the time, we are interested to know if events are working/not
working and it is possible with previous commit ("net/mlx5: Debug print
for forwarded async events").

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/srq.c | 22 +++-------------------
 1 file changed, 3 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
index 248f1c8dd5d3..690815234838 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
@@ -10,15 +10,12 @@
 #include <linux/mlx5/srq.h>
 #include <rdma/ib_verbs.h>
 #include <linux/mlx5/transobj.h>
-#include "mlx5_core.h"
 
 static int srq_event_notifier(struct notifier_block *nb,
 			      unsigned long type, void *data)
 {
 	struct mlx5_srq_table *table;
-	struct mlx5_core_dev *dev;
 	struct mlx5_core_srq *srq;
-	struct mlx5_priv *priv;
 	struct mlx5_eqe *eqe;
 	u32 srqn;
 
@@ -27,12 +24,9 @@ static int srq_event_notifier(struct notifier_block *nb,
 		return NOTIFY_DONE;
 
 	table = container_of(nb, struct mlx5_srq_table, nb);
-	priv  = container_of(table, struct mlx5_priv, srq_table);
-	dev   = container_of(priv, struct mlx5_core_dev, priv);
 
 	eqe = data;
 	srqn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
-	mlx5_core_dbg(dev, "SRQ event (%d): srqn 0x%x\n", eqe->type, srqn);
 
 	spin_lock(&table->lock);
 
@@ -42,10 +36,8 @@ static int srq_event_notifier(struct notifier_block *nb,
 
 	spin_unlock(&table->lock);
 
-	if (!srq) {
-		mlx5_core_warn(dev, "Async event for bogus SRQ 0x%08x\n", srqn);
+	if (!srq)
 		return NOTIFY_OK;
-	}
 
 	srq->event(srq, eqe->type);
 
@@ -617,10 +609,8 @@ int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	spin_lock_irq(&table->lock);
 	err = radix_tree_insert(&table->tree, srq->srqn, srq);
 	spin_unlock_irq(&table->lock);
-	if (err) {
-		mlx5_core_warn(dev, "err %d, srqn 0x%x\n", err, srq->srqn);
+	if (err)
 		goto err_destroy_srq_split;
-	}
 
 	return 0;
 
@@ -640,14 +630,8 @@ int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
 	spin_lock_irq(&table->lock);
 	tmp = radix_tree_delete(&table->tree, srq->srqn);
 	spin_unlock_irq(&table->lock);
-	if (!tmp) {
-		mlx5_core_warn(dev, "srq 0x%x not found in tree\n", srq->srqn);
+	if (!tmp || tmp != srq)
 		return -EINVAL;
-	}
-	if (tmp != srq) {
-		mlx5_core_warn(dev, "corruption on srqn 0x%x\n", srq->srqn);
-		return -EINVAL;
-	}
 
 	err = destroy_srq_split(dev, srq);
 	if (err)
-- 
cgit v1.2.3


From f02d0d6e53ac2c8a75b6cc87dc86675a9351d84d Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Nov 2018 20:53:37 +0200
Subject: net/mlx5: Move SRQ functions to RDMA part

There is no need to keep SRQ which is RDMA object in mlx5_core.
In this patch, we partially move the execution code, while next patches
will move table initialization/release logic too.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/Makefile                |   4 +-
 drivers/infiniband/hw/mlx5/cq.c                    |   1 +
 drivers/infiniband/hw/mlx5/srq.c                   |   2 +-
 drivers/infiniband/hw/mlx5/srq.h                   |  46 ++
 drivers/infiniband/hw/mlx5/srq_cmd.c               | 666 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/srq.c      | 634 --------------------
 drivers/net/ethernet/mellanox/mlx5/core/transobj.c |  43 --
 include/linux/mlx5/driver.h                        |   8 -
 include/linux/mlx5/srq.h                           |  31 -
 include/linux/mlx5/transobj.h                      |   6 -
 10 files changed, 717 insertions(+), 724 deletions(-)
 create mode 100644 drivers/infiniband/hw/mlx5/srq.h
 create mode 100644 drivers/infiniband/hw/mlx5/srq_cmd.c

diff --git a/drivers/infiniband/hw/mlx5/Makefile b/drivers/infiniband/hw/mlx5/Makefile
index b8e4b15e2674..33f5adb14e4e 100644
--- a/drivers/infiniband/hw/mlx5/Makefile
+++ b/drivers/infiniband/hw/mlx5/Makefile
@@ -1,6 +1,8 @@
 obj-$(CONFIG_MLX5_INFINIBAND)	+= mlx5_ib.o
 
-mlx5_ib-y :=	main.o cq.o doorbell.o qp.o mem.o srq.o mr.o ah.o mad.o gsi.o ib_virt.o cmd.o cong.o
+mlx5_ib-y :=	main.o cq.o doorbell.o qp.o mem.o srq_cmd.o \
+		srq.o mr.o ah.o mad.o gsi.o ib_virt.o cmd.o \
+		cong.o
 mlx5_ib-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += odp.o
 mlx5_ib-$(CONFIG_MLX5_ESWITCH) += ib_rep.o
 mlx5_ib-$(CONFIG_INFINIBAND_USER_ACCESS) += devx.o
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 7d769b5538b4..c5d2824ada59 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -35,6 +35,7 @@
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_cache.h>
 #include "mlx5_ib.h"
+#include "srq.h"
 
 static void mlx5_ib_cq_comp(struct mlx5_core_cq *cq)
 {
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 28794780062e..a86d9f153805 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -9,8 +9,8 @@
 #include <linux/slab.h>
 #include <rdma/ib_umem.h>
 #include <rdma/ib_user_verbs.h>
-
 #include "mlx5_ib.h"
+#include "srq.h"
 
 /* not supported currently */
 static int srq_signature;
diff --git a/drivers/infiniband/hw/mlx5/srq.h b/drivers/infiniband/hw/mlx5/srq.h
new file mode 100644
index 000000000000..f23d5de12973
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/srq.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright (c) 2013-2018, Mellanox Technologies. All rights reserved.
+ */
+
+#ifndef MLX5_IB_SRQ_H
+#define MLX5_IB_SRQ_H
+
+enum {
+	MLX5_SRQ_FLAG_ERR    = (1 << 0),
+	MLX5_SRQ_FLAG_WQ_SIG = (1 << 1),
+	MLX5_SRQ_FLAG_RNDV   = (1 << 2),
+};
+
+struct mlx5_srq_attr {
+	u32 type;
+	u32 flags;
+	u32 log_size;
+	u32 wqe_shift;
+	u32 log_page_size;
+	u32 wqe_cnt;
+	u32 srqn;
+	u32 xrcd;
+	u32 page_offset;
+	u32 cqn;
+	u32 pd;
+	u32 lwm;
+	u32 user_index;
+	u64 db_record;
+	__be64 *pas;
+	u32 tm_log_list_size;
+	u32 tm_next_tag;
+	u32 tm_hw_phase_cnt;
+	u32 tm_sw_phase_cnt;
+	u16 uid;
+};
+
+int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			 struct mlx5_srq_attr *in);
+int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq);
+int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			struct mlx5_srq_attr *out);
+int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+		      u16 lwm, int is_srq);
+struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
+#endif /* MLX5_IB_SRQ_H */
diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c
new file mode 100644
index 000000000000..4a64ad4c9b25
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/srq_cmd.c
@@ -0,0 +1,666 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2013-2018, Mellanox Technologies inc.  All rights reserved.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/cmd.h>
+#include "srq.h"
+
+static int get_pas_size(struct mlx5_srq_attr *in)
+{
+	u32 log_page_size = in->log_page_size + 12;
+	u32 log_srq_size  = in->log_size;
+	u32 log_rq_stride = in->wqe_shift;
+	u32 page_offset   = in->page_offset;
+	u32 po_quanta	  = 1 << (log_page_size - 6);
+	u32 rq_sz	  = 1 << (log_srq_size + 4 + log_rq_stride);
+	u32 page_size	  = 1 << log_page_size;
+	u32 rq_sz_po      = rq_sz + (page_offset * po_quanta);
+	u32 rq_num_pas    = DIV_ROUND_UP(rq_sz_po, page_size);
+
+	return rq_num_pas * sizeof(u64);
+}
+
+static void set_wq(void *wq, struct mlx5_srq_attr *in)
+{
+	MLX5_SET(wq,   wq, wq_signature,  !!(in->flags
+		 & MLX5_SRQ_FLAG_WQ_SIG));
+	MLX5_SET(wq,   wq, log_wq_pg_sz,  in->log_page_size);
+	MLX5_SET(wq,   wq, log_wq_stride, in->wqe_shift + 4);
+	MLX5_SET(wq,   wq, log_wq_sz,     in->log_size);
+	MLX5_SET(wq,   wq, page_offset,   in->page_offset);
+	MLX5_SET(wq,   wq, lwm,		  in->lwm);
+	MLX5_SET(wq,   wq, pd,		  in->pd);
+	MLX5_SET64(wq, wq, dbr_addr,	  in->db_record);
+}
+
+static void set_srqc(void *srqc, struct mlx5_srq_attr *in)
+{
+	MLX5_SET(srqc,   srqc, wq_signature,  !!(in->flags
+		 & MLX5_SRQ_FLAG_WQ_SIG));
+	MLX5_SET(srqc,   srqc, log_page_size, in->log_page_size);
+	MLX5_SET(srqc,   srqc, log_rq_stride, in->wqe_shift);
+	MLX5_SET(srqc,   srqc, log_srq_size,  in->log_size);
+	MLX5_SET(srqc,   srqc, page_offset,   in->page_offset);
+	MLX5_SET(srqc,	 srqc, lwm,	      in->lwm);
+	MLX5_SET(srqc,	 srqc, pd,	      in->pd);
+	MLX5_SET64(srqc, srqc, dbr_addr,      in->db_record);
+	MLX5_SET(srqc,	 srqc, xrcd,	      in->xrcd);
+	MLX5_SET(srqc,	 srqc, cqn,	      in->cqn);
+}
+
+static void get_wq(void *wq, struct mlx5_srq_attr *in)
+{
+	if (MLX5_GET(wq, wq, wq_signature))
+		in->flags &= MLX5_SRQ_FLAG_WQ_SIG;
+	in->log_page_size = MLX5_GET(wq,   wq, log_wq_pg_sz);
+	in->wqe_shift	  = MLX5_GET(wq,   wq, log_wq_stride) - 4;
+	in->log_size	  = MLX5_GET(wq,   wq, log_wq_sz);
+	in->page_offset   = MLX5_GET(wq,   wq, page_offset);
+	in->lwm		  = MLX5_GET(wq,   wq, lwm);
+	in->pd		  = MLX5_GET(wq,   wq, pd);
+	in->db_record	  = MLX5_GET64(wq, wq, dbr_addr);
+}
+
+static void get_srqc(void *srqc, struct mlx5_srq_attr *in)
+{
+	if (MLX5_GET(srqc, srqc, wq_signature))
+		in->flags &= MLX5_SRQ_FLAG_WQ_SIG;
+	in->log_page_size = MLX5_GET(srqc,   srqc, log_page_size);
+	in->wqe_shift	  = MLX5_GET(srqc,   srqc, log_rq_stride);
+	in->log_size	  = MLX5_GET(srqc,   srqc, log_srq_size);
+	in->page_offset   = MLX5_GET(srqc,   srqc, page_offset);
+	in->lwm		  = MLX5_GET(srqc,   srqc, lwm);
+	in->pd		  = MLX5_GET(srqc,   srqc, pd);
+	in->db_record	  = MLX5_GET64(srqc, srqc, dbr_addr);
+}
+
+struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn)
+{
+	struct mlx5_srq_table *table = &dev->priv.srq_table;
+	struct mlx5_core_srq *srq;
+
+	spin_lock(&table->lock);
+
+	srq = radix_tree_lookup(&table->tree, srqn);
+	if (srq)
+		atomic_inc(&srq->refcount);
+
+	spin_unlock(&table->lock);
+
+	return srq;
+}
+
+static int create_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			  struct mlx5_srq_attr *in)
+{
+	u32 create_out[MLX5_ST_SZ_DW(create_srq_out)] = {0};
+	void *create_in;
+	void *srqc;
+	void *pas;
+	int pas_size;
+	int inlen;
+	int err;
+
+	pas_size  = get_pas_size(in);
+	inlen	  = MLX5_ST_SZ_BYTES(create_srq_in) + pas_size;
+	create_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!create_in)
+		return -ENOMEM;
+
+	MLX5_SET(create_srq_in, create_in, uid, in->uid);
+	srqc = MLX5_ADDR_OF(create_srq_in, create_in, srq_context_entry);
+	pas = MLX5_ADDR_OF(create_srq_in, create_in, pas);
+
+	set_srqc(srqc, in);
+	memcpy(pas, in->pas, pas_size);
+
+	MLX5_SET(create_srq_in, create_in, opcode,
+		 MLX5_CMD_OP_CREATE_SRQ);
+
+	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
+			    sizeof(create_out));
+	kvfree(create_in);
+	if (!err) {
+		srq->srqn = MLX5_GET(create_srq_out, create_out, srqn);
+		srq->uid = in->uid;
+	}
+
+	return err;
+}
+
+static int destroy_srq_cmd(struct mlx5_core_dev *dev,
+			   struct mlx5_core_srq *srq)
+{
+	u32 srq_in[MLX5_ST_SZ_DW(destroy_srq_in)] = {0};
+	u32 srq_out[MLX5_ST_SZ_DW(destroy_srq_out)] = {0};
+
+	MLX5_SET(destroy_srq_in, srq_in, opcode,
+		 MLX5_CMD_OP_DESTROY_SRQ);
+	MLX5_SET(destroy_srq_in, srq_in, srqn, srq->srqn);
+	MLX5_SET(destroy_srq_in, srq_in, uid, srq->uid);
+
+	return mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
+			     srq_out, sizeof(srq_out));
+}
+
+static int arm_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+		       u16 lwm, int is_srq)
+{
+	u32 srq_in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
+	u32 srq_out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
+
+	MLX5_SET(arm_rq_in, srq_in, opcode, MLX5_CMD_OP_ARM_RQ);
+	MLX5_SET(arm_rq_in, srq_in, op_mod, MLX5_ARM_RQ_IN_OP_MOD_SRQ);
+	MLX5_SET(arm_rq_in, srq_in, srq_number, srq->srqn);
+	MLX5_SET(arm_rq_in, srq_in, lwm,      lwm);
+	MLX5_SET(arm_rq_in, srq_in, uid, srq->uid);
+
+	return  mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
+			      srq_out, sizeof(srq_out));
+}
+
+static int query_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			 struct mlx5_srq_attr *out)
+{
+	u32 srq_in[MLX5_ST_SZ_DW(query_srq_in)] = {0};
+	u32 *srq_out;
+	void *srqc;
+	int err;
+
+	srq_out = kvzalloc(MLX5_ST_SZ_BYTES(query_srq_out), GFP_KERNEL);
+	if (!srq_out)
+		return -ENOMEM;
+
+	MLX5_SET(query_srq_in, srq_in, opcode,
+		 MLX5_CMD_OP_QUERY_SRQ);
+	MLX5_SET(query_srq_in, srq_in, srqn, srq->srqn);
+	err =  mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
+			     srq_out, MLX5_ST_SZ_BYTES(query_srq_out));
+	if (err)
+		goto out;
+
+	srqc = MLX5_ADDR_OF(query_srq_out, srq_out, srq_context_entry);
+	get_srqc(srqc, out);
+	if (MLX5_GET(srqc, srqc, state) != MLX5_SRQC_STATE_GOOD)
+		out->flags |= MLX5_SRQ_FLAG_ERR;
+out:
+	kvfree(srq_out);
+	return err;
+}
+
+static int create_xrc_srq_cmd(struct mlx5_core_dev *dev,
+			      struct mlx5_core_srq *srq,
+			      struct mlx5_srq_attr *in)
+{
+	u32 create_out[MLX5_ST_SZ_DW(create_xrc_srq_out)];
+	void *create_in;
+	void *xrc_srqc;
+	void *pas;
+	int pas_size;
+	int inlen;
+	int err;
+
+	pas_size  = get_pas_size(in);
+	inlen	  = MLX5_ST_SZ_BYTES(create_xrc_srq_in) + pas_size;
+	create_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!create_in)
+		return -ENOMEM;
+
+	MLX5_SET(create_xrc_srq_in, create_in, uid, in->uid);
+	xrc_srqc = MLX5_ADDR_OF(create_xrc_srq_in, create_in,
+				xrc_srq_context_entry);
+	pas	 = MLX5_ADDR_OF(create_xrc_srq_in, create_in, pas);
+
+	set_srqc(xrc_srqc, in);
+	MLX5_SET(xrc_srqc, xrc_srqc, user_index, in->user_index);
+	memcpy(pas, in->pas, pas_size);
+	MLX5_SET(create_xrc_srq_in, create_in, opcode,
+		 MLX5_CMD_OP_CREATE_XRC_SRQ);
+
+	memset(create_out, 0, sizeof(create_out));
+	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
+			    sizeof(create_out));
+	if (err)
+		goto out;
+
+	srq->srqn = MLX5_GET(create_xrc_srq_out, create_out, xrc_srqn);
+	srq->uid = in->uid;
+out:
+	kvfree(create_in);
+	return err;
+}
+
+static int destroy_xrc_srq_cmd(struct mlx5_core_dev *dev,
+			       struct mlx5_core_srq *srq)
+{
+	u32 xrcsrq_in[MLX5_ST_SZ_DW(destroy_xrc_srq_in)]   = {0};
+	u32 xrcsrq_out[MLX5_ST_SZ_DW(destroy_xrc_srq_out)] = {0};
+
+	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, opcode,
+		 MLX5_CMD_OP_DESTROY_XRC_SRQ);
+	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
+	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, uid, srq->uid);
+
+	return mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in),
+			     xrcsrq_out, sizeof(xrcsrq_out));
+}
+
+static int arm_xrc_srq_cmd(struct mlx5_core_dev *dev,
+			   struct mlx5_core_srq *srq, u16 lwm)
+{
+	u32 xrcsrq_in[MLX5_ST_SZ_DW(arm_xrc_srq_in)]   = {0};
+	u32 xrcsrq_out[MLX5_ST_SZ_DW(arm_xrc_srq_out)] = {0};
+
+	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, opcode,   MLX5_CMD_OP_ARM_XRC_SRQ);
+	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, op_mod,   MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ);
+	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
+	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, lwm,      lwm);
+	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, uid, srq->uid);
+
+	return  mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in),
+			      xrcsrq_out, sizeof(xrcsrq_out));
+}
+
+static int query_xrc_srq_cmd(struct mlx5_core_dev *dev,
+			     struct mlx5_core_srq *srq,
+			     struct mlx5_srq_attr *out)
+{
+	u32 xrcsrq_in[MLX5_ST_SZ_DW(query_xrc_srq_in)];
+	u32 *xrcsrq_out;
+	void *xrc_srqc;
+	int err;
+
+	xrcsrq_out = kvzalloc(MLX5_ST_SZ_BYTES(query_xrc_srq_out), GFP_KERNEL);
+	if (!xrcsrq_out)
+		return -ENOMEM;
+	memset(xrcsrq_in, 0, sizeof(xrcsrq_in));
+
+	MLX5_SET(query_xrc_srq_in, xrcsrq_in, opcode,
+		 MLX5_CMD_OP_QUERY_XRC_SRQ);
+	MLX5_SET(query_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
+
+	err =  mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in), xrcsrq_out,
+			     MLX5_ST_SZ_BYTES(query_xrc_srq_out));
+	if (err)
+		goto out;
+
+	xrc_srqc = MLX5_ADDR_OF(query_xrc_srq_out, xrcsrq_out,
+				xrc_srq_context_entry);
+	get_srqc(xrc_srqc, out);
+	if (MLX5_GET(xrc_srqc, xrc_srqc, state) != MLX5_XRC_SRQC_STATE_GOOD)
+		out->flags |= MLX5_SRQ_FLAG_ERR;
+
+out:
+	kvfree(xrcsrq_out);
+	return err;
+}
+
+static int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen,
+				u32 *rmpn)
+{
+	u32 out[MLX5_ST_SZ_DW(create_rmp_out)] = { 0 };
+	int err;
+
+	MLX5_SET(create_rmp_in, in, opcode, MLX5_CMD_OP_CREATE_RMP);
+	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	if (!err)
+		*rmpn = MLX5_GET(create_rmp_out, out, rmpn);
+
+	return err;
+}
+
+static int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen)
+{
+	u32 out[MLX5_ST_SZ_DW(modify_rmp_out)] = {0};
+
+	MLX5_SET(modify_rmp_in, in, opcode, MLX5_CMD_OP_MODIFY_RMP);
+	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+}
+
+static int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out)
+{
+	u32 in[MLX5_ST_SZ_DW(query_rmp_in)] = {0};
+	int outlen = MLX5_ST_SZ_BYTES(query_rmp_out);
+
+	MLX5_SET(query_rmp_in, in, opcode, MLX5_CMD_OP_QUERY_RMP);
+	MLX5_SET(query_rmp_in, in, rmpn,   rmpn);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
+static int create_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			  struct mlx5_srq_attr *in)
+{
+	void *create_in;
+	void *rmpc;
+	void *wq;
+	int pas_size;
+	int inlen;
+	int err;
+
+	pas_size = get_pas_size(in);
+	inlen = MLX5_ST_SZ_BYTES(create_rmp_in) + pas_size;
+	create_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!create_in)
+		return -ENOMEM;
+
+	rmpc = MLX5_ADDR_OF(create_rmp_in, create_in, ctx);
+	wq = MLX5_ADDR_OF(rmpc, rmpc, wq);
+
+	MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
+	MLX5_SET(create_rmp_in, create_in, uid, in->uid);
+	set_wq(wq, in);
+	memcpy(MLX5_ADDR_OF(rmpc, rmpc, wq.pas), in->pas, pas_size);
+
+	err = mlx5_core_create_rmp(dev, create_in, inlen, &srq->srqn);
+	if (!err)
+		srq->uid = in->uid;
+
+	kvfree(create_in);
+	return err;
+}
+
+static int destroy_rmp_cmd(struct mlx5_core_dev *dev,
+			   struct mlx5_core_srq *srq)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_rmp_in)]   = {};
+	u32 out[MLX5_ST_SZ_DW(destroy_rmp_out)] = {};
+
+	MLX5_SET(destroy_rmp_in, in, opcode, MLX5_CMD_OP_DESTROY_RMP);
+	MLX5_SET(destroy_rmp_in, in, rmpn, srq->srqn);
+	MLX5_SET(destroy_rmp_in, in, uid, srq->uid);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int arm_rmp_cmd(struct mlx5_core_dev *dev,
+		       struct mlx5_core_srq *srq,
+		       u16 lwm)
+{
+	void *in;
+	void *rmpc;
+	void *wq;
+	void *bitmask;
+	int err;
+
+	in = kvzalloc(MLX5_ST_SZ_BYTES(modify_rmp_in), GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	rmpc =	  MLX5_ADDR_OF(modify_rmp_in,   in,   ctx);
+	bitmask = MLX5_ADDR_OF(modify_rmp_in,   in,   bitmask);
+	wq   =	  MLX5_ADDR_OF(rmpc,	        rmpc, wq);
+
+	MLX5_SET(modify_rmp_in, in,	 rmp_state, MLX5_RMPC_STATE_RDY);
+	MLX5_SET(modify_rmp_in, in,	 rmpn,      srq->srqn);
+	MLX5_SET(modify_rmp_in, in, uid, srq->uid);
+	MLX5_SET(wq,		wq,	 lwm,	    lwm);
+	MLX5_SET(rmp_bitmask,	bitmask, lwm,	    1);
+	MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
+
+	err = mlx5_core_modify_rmp(dev, in, MLX5_ST_SZ_BYTES(modify_rmp_in));
+
+	kvfree(in);
+	return err;
+}
+
+static int query_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			 struct mlx5_srq_attr *out)
+{
+	u32 *rmp_out;
+	void *rmpc;
+	int err;
+
+	rmp_out =  kvzalloc(MLX5_ST_SZ_BYTES(query_rmp_out), GFP_KERNEL);
+	if (!rmp_out)
+		return -ENOMEM;
+
+	err = mlx5_core_query_rmp(dev, srq->srqn, rmp_out);
+	if (err)
+		goto out;
+
+	rmpc = MLX5_ADDR_OF(query_rmp_out, rmp_out, rmp_context);
+	get_wq(MLX5_ADDR_OF(rmpc, rmpc, wq), out);
+	if (MLX5_GET(rmpc, rmpc, state) != MLX5_RMPC_STATE_RDY)
+		out->flags |= MLX5_SRQ_FLAG_ERR;
+
+out:
+	kvfree(rmp_out);
+	return err;
+}
+
+static int create_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			  struct mlx5_srq_attr *in)
+{
+	u32 create_out[MLX5_ST_SZ_DW(create_xrq_out)] = {0};
+	void *create_in;
+	void *xrqc;
+	void *wq;
+	int pas_size;
+	int inlen;
+	int err;
+
+	pas_size = get_pas_size(in);
+	inlen = MLX5_ST_SZ_BYTES(create_xrq_in) + pas_size;
+	create_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!create_in)
+		return -ENOMEM;
+
+	xrqc = MLX5_ADDR_OF(create_xrq_in, create_in, xrq_context);
+	wq = MLX5_ADDR_OF(xrqc, xrqc, wq);
+
+	set_wq(wq, in);
+	memcpy(MLX5_ADDR_OF(xrqc, xrqc, wq.pas), in->pas, pas_size);
+
+	if (in->type == IB_SRQT_TM) {
+		MLX5_SET(xrqc, xrqc, topology, MLX5_XRQC_TOPOLOGY_TAG_MATCHING);
+		if (in->flags & MLX5_SRQ_FLAG_RNDV)
+			MLX5_SET(xrqc, xrqc, offload, MLX5_XRQC_OFFLOAD_RNDV);
+		MLX5_SET(xrqc, xrqc,
+			 tag_matching_topology_context.log_matching_list_sz,
+			 in->tm_log_list_size);
+	}
+	MLX5_SET(xrqc, xrqc, user_index, in->user_index);
+	MLX5_SET(xrqc, xrqc, cqn, in->cqn);
+	MLX5_SET(create_xrq_in, create_in, opcode, MLX5_CMD_OP_CREATE_XRQ);
+	MLX5_SET(create_xrq_in, create_in, uid, in->uid);
+	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
+			    sizeof(create_out));
+	kvfree(create_in);
+	if (!err) {
+		srq->srqn = MLX5_GET(create_xrq_out, create_out, xrqn);
+		srq->uid = in->uid;
+	}
+
+	return err;
+}
+
+static int destroy_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_xrq_in)] = {0};
+	u32 out[MLX5_ST_SZ_DW(destroy_xrq_out)] = {0};
+
+	MLX5_SET(destroy_xrq_in, in, opcode, MLX5_CMD_OP_DESTROY_XRQ);
+	MLX5_SET(destroy_xrq_in, in, xrqn,   srq->srqn);
+	MLX5_SET(destroy_xrq_in, in, uid, srq->uid);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int arm_xrq_cmd(struct mlx5_core_dev *dev,
+		       struct mlx5_core_srq *srq,
+		       u16 lwm)
+{
+	u32 out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
+
+	MLX5_SET(arm_rq_in, in, opcode,     MLX5_CMD_OP_ARM_RQ);
+	MLX5_SET(arm_rq_in, in, op_mod,     MLX5_ARM_RQ_IN_OP_MOD_XRQ);
+	MLX5_SET(arm_rq_in, in, srq_number, srq->srqn);
+	MLX5_SET(arm_rq_in, in, lwm,	    lwm);
+	MLX5_SET(arm_rq_in, in, uid, srq->uid);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int query_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			 struct mlx5_srq_attr *out)
+{
+	u32 in[MLX5_ST_SZ_DW(query_xrq_in)] = {0};
+	u32 *xrq_out;
+	int outlen = MLX5_ST_SZ_BYTES(query_xrq_out);
+	void *xrqc;
+	int err;
+
+	xrq_out = kvzalloc(outlen, GFP_KERNEL);
+	if (!xrq_out)
+		return -ENOMEM;
+
+	MLX5_SET(query_xrq_in, in, opcode, MLX5_CMD_OP_QUERY_XRQ);
+	MLX5_SET(query_xrq_in, in, xrqn, srq->srqn);
+
+	err = mlx5_cmd_exec(dev, in, sizeof(in), xrq_out, outlen);
+	if (err)
+		goto out;
+
+	xrqc = MLX5_ADDR_OF(query_xrq_out, xrq_out, xrq_context);
+	get_wq(MLX5_ADDR_OF(xrqc, xrqc, wq), out);
+	if (MLX5_GET(xrqc, xrqc, state) != MLX5_XRQC_STATE_GOOD)
+		out->flags |= MLX5_SRQ_FLAG_ERR;
+	out->tm_next_tag =
+		MLX5_GET(xrqc, xrqc,
+			 tag_matching_topology_context.append_next_index);
+	out->tm_hw_phase_cnt =
+		MLX5_GET(xrqc, xrqc,
+			 tag_matching_topology_context.hw_phase_cnt);
+	out->tm_sw_phase_cnt =
+		MLX5_GET(xrqc, xrqc,
+			 tag_matching_topology_context.sw_phase_cnt);
+
+out:
+	kvfree(xrq_out);
+	return err;
+}
+
+static int create_srq_split(struct mlx5_core_dev *dev,
+			    struct mlx5_core_srq *srq,
+			    struct mlx5_srq_attr *in)
+{
+	if (!dev->issi)
+		return create_srq_cmd(dev, srq, in);
+	switch (srq->common.res) {
+	case MLX5_RES_XSRQ:
+		return create_xrc_srq_cmd(dev, srq, in);
+	case MLX5_RES_XRQ:
+		return create_xrq_cmd(dev, srq, in);
+	default:
+		return create_rmp_cmd(dev, srq, in);
+	}
+}
+
+static int destroy_srq_split(struct mlx5_core_dev *dev,
+			     struct mlx5_core_srq *srq)
+{
+	if (!dev->issi)
+		return destroy_srq_cmd(dev, srq);
+	switch (srq->common.res) {
+	case MLX5_RES_XSRQ:
+		return destroy_xrc_srq_cmd(dev, srq);
+	case MLX5_RES_XRQ:
+		return destroy_xrq_cmd(dev, srq);
+	default:
+		return destroy_rmp_cmd(dev, srq);
+	}
+}
+
+int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			 struct mlx5_srq_attr *in)
+{
+	int err;
+	struct mlx5_srq_table *table = &dev->priv.srq_table;
+
+	switch (in->type) {
+	case IB_SRQT_XRC:
+		srq->common.res = MLX5_RES_XSRQ;
+		break;
+	case IB_SRQT_TM:
+		srq->common.res = MLX5_RES_XRQ;
+		break;
+	default:
+		srq->common.res = MLX5_RES_SRQ;
+	}
+
+	err = create_srq_split(dev, srq, in);
+	if (err)
+		return err;
+
+	atomic_set(&srq->refcount, 1);
+	init_completion(&srq->free);
+
+	spin_lock_irq(&table->lock);
+	err = radix_tree_insert(&table->tree, srq->srqn, srq);
+	spin_unlock_irq(&table->lock);
+	if (err)
+		goto err_destroy_srq_split;
+
+	return 0;
+
+err_destroy_srq_split:
+	destroy_srq_split(dev, srq);
+
+	return err;
+}
+
+int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
+{
+	struct mlx5_srq_table *table = &dev->priv.srq_table;
+	struct mlx5_core_srq *tmp;
+	int err;
+
+	spin_lock_irq(&table->lock);
+	tmp = radix_tree_delete(&table->tree, srq->srqn);
+	spin_unlock_irq(&table->lock);
+	if (!tmp || tmp != srq)
+		return -EINVAL;
+
+	err = destroy_srq_split(dev, srq);
+	if (err)
+		return err;
+
+	if (atomic_dec_and_test(&srq->refcount))
+		complete(&srq->free);
+	wait_for_completion(&srq->free);
+
+	return 0;
+}
+
+int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			struct mlx5_srq_attr *out)
+{
+	if (!dev->issi)
+		return query_srq_cmd(dev, srq, out);
+	switch (srq->common.res) {
+	case MLX5_RES_XSRQ:
+		return query_xrc_srq_cmd(dev, srq, out);
+	case MLX5_RES_XRQ:
+		return query_xrq_cmd(dev, srq, out);
+	default:
+		return query_rmp_cmd(dev, srq, out);
+	}
+}
+
+int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+		      u16 lwm, int is_srq)
+{
+	if (!dev->issi)
+		return arm_srq_cmd(dev, srq, lwm, is_srq);
+	switch (srq->common.res) {
+	case MLX5_RES_XSRQ:
+		return arm_xrc_srq_cmd(dev, srq, lwm);
+	case MLX5_RES_XRQ:
+		return arm_xrq_cmd(dev, srq, lwm);
+	default:
+		return arm_rmp_cmd(dev, srq, lwm);
+	}
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
index 690815234838..0e80ddbe2510 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
@@ -4,12 +4,8 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
 #include <linux/mlx5/srq.h>
-#include <rdma/ib_verbs.h>
-#include <linux/mlx5/transobj.h>
 
 static int srq_event_notifier(struct notifier_block *nb,
 			      unsigned long type, void *data)
@@ -47,636 +43,6 @@ static int srq_event_notifier(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-static int get_pas_size(struct mlx5_srq_attr *in)
-{
-	u32 log_page_size = in->log_page_size + 12;
-	u32 log_srq_size  = in->log_size;
-	u32 log_rq_stride = in->wqe_shift;
-	u32 page_offset   = in->page_offset;
-	u32 po_quanta	  = 1 << (log_page_size - 6);
-	u32 rq_sz	  = 1 << (log_srq_size + 4 + log_rq_stride);
-	u32 page_size	  = 1 << log_page_size;
-	u32 rq_sz_po      = rq_sz + (page_offset * po_quanta);
-	u32 rq_num_pas    = DIV_ROUND_UP(rq_sz_po, page_size);
-
-	return rq_num_pas * sizeof(u64);
-}
-
-static void set_wq(void *wq, struct mlx5_srq_attr *in)
-{
-	MLX5_SET(wq,   wq, wq_signature,  !!(in->flags
-		 & MLX5_SRQ_FLAG_WQ_SIG));
-	MLX5_SET(wq,   wq, log_wq_pg_sz,  in->log_page_size);
-	MLX5_SET(wq,   wq, log_wq_stride, in->wqe_shift + 4);
-	MLX5_SET(wq,   wq, log_wq_sz,     in->log_size);
-	MLX5_SET(wq,   wq, page_offset,   in->page_offset);
-	MLX5_SET(wq,   wq, lwm,		  in->lwm);
-	MLX5_SET(wq,   wq, pd,		  in->pd);
-	MLX5_SET64(wq, wq, dbr_addr,	  in->db_record);
-}
-
-static void set_srqc(void *srqc, struct mlx5_srq_attr *in)
-{
-	MLX5_SET(srqc,   srqc, wq_signature,  !!(in->flags
-		 & MLX5_SRQ_FLAG_WQ_SIG));
-	MLX5_SET(srqc,   srqc, log_page_size, in->log_page_size);
-	MLX5_SET(srqc,   srqc, log_rq_stride, in->wqe_shift);
-	MLX5_SET(srqc,   srqc, log_srq_size,  in->log_size);
-	MLX5_SET(srqc,   srqc, page_offset,   in->page_offset);
-	MLX5_SET(srqc,	 srqc, lwm,	      in->lwm);
-	MLX5_SET(srqc,	 srqc, pd,	      in->pd);
-	MLX5_SET64(srqc, srqc, dbr_addr,      in->db_record);
-	MLX5_SET(srqc,	 srqc, xrcd,	      in->xrcd);
-	MLX5_SET(srqc,	 srqc, cqn,	      in->cqn);
-}
-
-static void get_wq(void *wq, struct mlx5_srq_attr *in)
-{
-	if (MLX5_GET(wq, wq, wq_signature))
-		in->flags &= MLX5_SRQ_FLAG_WQ_SIG;
-	in->log_page_size = MLX5_GET(wq,   wq, log_wq_pg_sz);
-	in->wqe_shift	  = MLX5_GET(wq,   wq, log_wq_stride) - 4;
-	in->log_size	  = MLX5_GET(wq,   wq, log_wq_sz);
-	in->page_offset   = MLX5_GET(wq,   wq, page_offset);
-	in->lwm		  = MLX5_GET(wq,   wq, lwm);
-	in->pd		  = MLX5_GET(wq,   wq, pd);
-	in->db_record	  = MLX5_GET64(wq, wq, dbr_addr);
-}
-
-static void get_srqc(void *srqc, struct mlx5_srq_attr *in)
-{
-	if (MLX5_GET(srqc, srqc, wq_signature))
-		in->flags &= MLX5_SRQ_FLAG_WQ_SIG;
-	in->log_page_size = MLX5_GET(srqc,   srqc, log_page_size);
-	in->wqe_shift	  = MLX5_GET(srqc,   srqc, log_rq_stride);
-	in->log_size	  = MLX5_GET(srqc,   srqc, log_srq_size);
-	in->page_offset   = MLX5_GET(srqc,   srqc, page_offset);
-	in->lwm		  = MLX5_GET(srqc,   srqc, lwm);
-	in->pd		  = MLX5_GET(srqc,   srqc, pd);
-	in->db_record	  = MLX5_GET64(srqc, srqc, dbr_addr);
-}
-
-struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn)
-{
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
-	struct mlx5_core_srq *srq;
-
-	spin_lock(&table->lock);
-
-	srq = radix_tree_lookup(&table->tree, srqn);
-	if (srq)
-		atomic_inc(&srq->refcount);
-
-	spin_unlock(&table->lock);
-
-	return srq;
-}
-EXPORT_SYMBOL(mlx5_core_get_srq);
-
-static int create_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			  struct mlx5_srq_attr *in)
-{
-	u32 create_out[MLX5_ST_SZ_DW(create_srq_out)] = {0};
-	void *create_in;
-	void *srqc;
-	void *pas;
-	int pas_size;
-	int inlen;
-	int err;
-
-	pas_size  = get_pas_size(in);
-	inlen	  = MLX5_ST_SZ_BYTES(create_srq_in) + pas_size;
-	create_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!create_in)
-		return -ENOMEM;
-
-	MLX5_SET(create_srq_in, create_in, uid, in->uid);
-	srqc = MLX5_ADDR_OF(create_srq_in, create_in, srq_context_entry);
-	pas = MLX5_ADDR_OF(create_srq_in, create_in, pas);
-
-	set_srqc(srqc, in);
-	memcpy(pas, in->pas, pas_size);
-
-	MLX5_SET(create_srq_in, create_in, opcode,
-		 MLX5_CMD_OP_CREATE_SRQ);
-
-	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
-			    sizeof(create_out));
-	kvfree(create_in);
-	if (!err) {
-		srq->srqn = MLX5_GET(create_srq_out, create_out, srqn);
-		srq->uid = in->uid;
-	}
-
-	return err;
-}
-
-static int destroy_srq_cmd(struct mlx5_core_dev *dev,
-			   struct mlx5_core_srq *srq)
-{
-	u32 srq_in[MLX5_ST_SZ_DW(destroy_srq_in)] = {0};
-	u32 srq_out[MLX5_ST_SZ_DW(destroy_srq_out)] = {0};
-
-	MLX5_SET(destroy_srq_in, srq_in, opcode,
-		 MLX5_CMD_OP_DESTROY_SRQ);
-	MLX5_SET(destroy_srq_in, srq_in, srqn, srq->srqn);
-	MLX5_SET(destroy_srq_in, srq_in, uid, srq->uid);
-
-	return mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
-			     srq_out, sizeof(srq_out));
-}
-
-static int arm_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-		       u16 lwm, int is_srq)
-{
-	u32 srq_in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
-	u32 srq_out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
-
-	MLX5_SET(arm_rq_in, srq_in, opcode, MLX5_CMD_OP_ARM_RQ);
-	MLX5_SET(arm_rq_in, srq_in, op_mod, MLX5_ARM_RQ_IN_OP_MOD_SRQ);
-	MLX5_SET(arm_rq_in, srq_in, srq_number, srq->srqn);
-	MLX5_SET(arm_rq_in, srq_in, lwm,      lwm);
-	MLX5_SET(arm_rq_in, srq_in, uid, srq->uid);
-
-	return  mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
-			      srq_out, sizeof(srq_out));
-}
-
-static int query_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_srq_attr *out)
-{
-	u32 srq_in[MLX5_ST_SZ_DW(query_srq_in)] = {0};
-	u32 *srq_out;
-	void *srqc;
-	int err;
-
-	srq_out = kvzalloc(MLX5_ST_SZ_BYTES(query_srq_out), GFP_KERNEL);
-	if (!srq_out)
-		return -ENOMEM;
-
-	MLX5_SET(query_srq_in, srq_in, opcode,
-		 MLX5_CMD_OP_QUERY_SRQ);
-	MLX5_SET(query_srq_in, srq_in, srqn, srq->srqn);
-	err =  mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
-			     srq_out, MLX5_ST_SZ_BYTES(query_srq_out));
-	if (err)
-		goto out;
-
-	srqc = MLX5_ADDR_OF(query_srq_out, srq_out, srq_context_entry);
-	get_srqc(srqc, out);
-	if (MLX5_GET(srqc, srqc, state) != MLX5_SRQC_STATE_GOOD)
-		out->flags |= MLX5_SRQ_FLAG_ERR;
-out:
-	kvfree(srq_out);
-	return err;
-}
-
-static int create_xrc_srq_cmd(struct mlx5_core_dev *dev,
-			      struct mlx5_core_srq *srq,
-			      struct mlx5_srq_attr *in)
-{
-	u32 create_out[MLX5_ST_SZ_DW(create_xrc_srq_out)];
-	void *create_in;
-	void *xrc_srqc;
-	void *pas;
-	int pas_size;
-	int inlen;
-	int err;
-
-	pas_size  = get_pas_size(in);
-	inlen	  = MLX5_ST_SZ_BYTES(create_xrc_srq_in) + pas_size;
-	create_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!create_in)
-		return -ENOMEM;
-
-	MLX5_SET(create_xrc_srq_in, create_in, uid, in->uid);
-	xrc_srqc = MLX5_ADDR_OF(create_xrc_srq_in, create_in,
-				xrc_srq_context_entry);
-	pas	 = MLX5_ADDR_OF(create_xrc_srq_in, create_in, pas);
-
-	set_srqc(xrc_srqc, in);
-	MLX5_SET(xrc_srqc, xrc_srqc, user_index, in->user_index);
-	memcpy(pas, in->pas, pas_size);
-	MLX5_SET(create_xrc_srq_in, create_in, opcode,
-		 MLX5_CMD_OP_CREATE_XRC_SRQ);
-
-	memset(create_out, 0, sizeof(create_out));
-	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
-			    sizeof(create_out));
-	if (err)
-		goto out;
-
-	srq->srqn = MLX5_GET(create_xrc_srq_out, create_out, xrc_srqn);
-	srq->uid = in->uid;
-out:
-	kvfree(create_in);
-	return err;
-}
-
-static int destroy_xrc_srq_cmd(struct mlx5_core_dev *dev,
-			       struct mlx5_core_srq *srq)
-{
-	u32 xrcsrq_in[MLX5_ST_SZ_DW(destroy_xrc_srq_in)]   = {0};
-	u32 xrcsrq_out[MLX5_ST_SZ_DW(destroy_xrc_srq_out)] = {0};
-
-	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, opcode,
-		 MLX5_CMD_OP_DESTROY_XRC_SRQ);
-	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
-	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, uid, srq->uid);
-
-	return mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in),
-			     xrcsrq_out, sizeof(xrcsrq_out));
-}
-
-static int arm_xrc_srq_cmd(struct mlx5_core_dev *dev,
-			   struct mlx5_core_srq *srq, u16 lwm)
-{
-	u32 xrcsrq_in[MLX5_ST_SZ_DW(arm_xrc_srq_in)]   = {0};
-	u32 xrcsrq_out[MLX5_ST_SZ_DW(arm_xrc_srq_out)] = {0};
-
-	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, opcode,   MLX5_CMD_OP_ARM_XRC_SRQ);
-	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, op_mod,   MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ);
-	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
-	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, lwm,      lwm);
-	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, uid, srq->uid);
-
-	return  mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in),
-			      xrcsrq_out, sizeof(xrcsrq_out));
-}
-
-static int query_xrc_srq_cmd(struct mlx5_core_dev *dev,
-			     struct mlx5_core_srq *srq,
-			     struct mlx5_srq_attr *out)
-{
-	u32 xrcsrq_in[MLX5_ST_SZ_DW(query_xrc_srq_in)];
-	u32 *xrcsrq_out;
-	void *xrc_srqc;
-	int err;
-
-	xrcsrq_out = kvzalloc(MLX5_ST_SZ_BYTES(query_xrc_srq_out), GFP_KERNEL);
-	if (!xrcsrq_out)
-		return -ENOMEM;
-	memset(xrcsrq_in, 0, sizeof(xrcsrq_in));
-
-	MLX5_SET(query_xrc_srq_in, xrcsrq_in, opcode,
-		 MLX5_CMD_OP_QUERY_XRC_SRQ);
-	MLX5_SET(query_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
-
-	err =  mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in), xrcsrq_out,
-			     MLX5_ST_SZ_BYTES(query_xrc_srq_out));
-	if (err)
-		goto out;
-
-	xrc_srqc = MLX5_ADDR_OF(query_xrc_srq_out, xrcsrq_out,
-				xrc_srq_context_entry);
-	get_srqc(xrc_srqc, out);
-	if (MLX5_GET(xrc_srqc, xrc_srqc, state) != MLX5_XRC_SRQC_STATE_GOOD)
-		out->flags |= MLX5_SRQ_FLAG_ERR;
-
-out:
-	kvfree(xrcsrq_out);
-	return err;
-}
-
-static int create_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			  struct mlx5_srq_attr *in)
-{
-	void *create_in;
-	void *rmpc;
-	void *wq;
-	int pas_size;
-	int inlen;
-	int err;
-
-	pas_size = get_pas_size(in);
-	inlen = MLX5_ST_SZ_BYTES(create_rmp_in) + pas_size;
-	create_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!create_in)
-		return -ENOMEM;
-
-	rmpc = MLX5_ADDR_OF(create_rmp_in, create_in, ctx);
-	wq = MLX5_ADDR_OF(rmpc, rmpc, wq);
-
-	MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
-	MLX5_SET(create_rmp_in, create_in, uid, in->uid);
-	set_wq(wq, in);
-	memcpy(MLX5_ADDR_OF(rmpc, rmpc, wq.pas), in->pas, pas_size);
-
-	err = mlx5_core_create_rmp(dev, create_in, inlen, &srq->srqn);
-	if (!err)
-		srq->uid = in->uid;
-
-	kvfree(create_in);
-	return err;
-}
-
-static int destroy_rmp_cmd(struct mlx5_core_dev *dev,
-			   struct mlx5_core_srq *srq)
-{
-	u32 in[MLX5_ST_SZ_DW(destroy_rmp_in)]   = {};
-	u32 out[MLX5_ST_SZ_DW(destroy_rmp_out)] = {};
-
-	MLX5_SET(destroy_rmp_in, in, opcode, MLX5_CMD_OP_DESTROY_RMP);
-	MLX5_SET(destroy_rmp_in, in, rmpn, srq->srqn);
-	MLX5_SET(destroy_rmp_in, in, uid, srq->uid);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-static int arm_rmp_cmd(struct mlx5_core_dev *dev,
-		       struct mlx5_core_srq *srq,
-		       u16 lwm)
-{
-	void *in;
-	void *rmpc;
-	void *wq;
-	void *bitmask;
-	int err;
-
-	in = kvzalloc(MLX5_ST_SZ_BYTES(modify_rmp_in), GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
-	rmpc =	  MLX5_ADDR_OF(modify_rmp_in,   in,   ctx);
-	bitmask = MLX5_ADDR_OF(modify_rmp_in,   in,   bitmask);
-	wq   =	  MLX5_ADDR_OF(rmpc,	        rmpc, wq);
-
-	MLX5_SET(modify_rmp_in, in,	 rmp_state, MLX5_RMPC_STATE_RDY);
-	MLX5_SET(modify_rmp_in, in,	 rmpn,      srq->srqn);
-	MLX5_SET(modify_rmp_in, in, uid, srq->uid);
-	MLX5_SET(wq,		wq,	 lwm,	    lwm);
-	MLX5_SET(rmp_bitmask,	bitmask, lwm,	    1);
-	MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
-
-	err = mlx5_core_modify_rmp(dev, in, MLX5_ST_SZ_BYTES(modify_rmp_in));
-
-	kvfree(in);
-	return err;
-}
-
-static int query_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_srq_attr *out)
-{
-	u32 *rmp_out;
-	void *rmpc;
-	int err;
-
-	rmp_out =  kvzalloc(MLX5_ST_SZ_BYTES(query_rmp_out), GFP_KERNEL);
-	if (!rmp_out)
-		return -ENOMEM;
-
-	err = mlx5_core_query_rmp(dev, srq->srqn, rmp_out);
-	if (err)
-		goto out;
-
-	rmpc = MLX5_ADDR_OF(query_rmp_out, rmp_out, rmp_context);
-	get_wq(MLX5_ADDR_OF(rmpc, rmpc, wq), out);
-	if (MLX5_GET(rmpc, rmpc, state) != MLX5_RMPC_STATE_RDY)
-		out->flags |= MLX5_SRQ_FLAG_ERR;
-
-out:
-	kvfree(rmp_out);
-	return err;
-}
-
-static int create_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			  struct mlx5_srq_attr *in)
-{
-	u32 create_out[MLX5_ST_SZ_DW(create_xrq_out)] = {0};
-	void *create_in;
-	void *xrqc;
-	void *wq;
-	int pas_size;
-	int inlen;
-	int err;
-
-	pas_size = get_pas_size(in);
-	inlen = MLX5_ST_SZ_BYTES(create_xrq_in) + pas_size;
-	create_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!create_in)
-		return -ENOMEM;
-
-	xrqc = MLX5_ADDR_OF(create_xrq_in, create_in, xrq_context);
-	wq = MLX5_ADDR_OF(xrqc, xrqc, wq);
-
-	set_wq(wq, in);
-	memcpy(MLX5_ADDR_OF(xrqc, xrqc, wq.pas), in->pas, pas_size);
-
-	if (in->type == IB_SRQT_TM) {
-		MLX5_SET(xrqc, xrqc, topology, MLX5_XRQC_TOPOLOGY_TAG_MATCHING);
-		if (in->flags & MLX5_SRQ_FLAG_RNDV)
-			MLX5_SET(xrqc, xrqc, offload, MLX5_XRQC_OFFLOAD_RNDV);
-		MLX5_SET(xrqc, xrqc,
-			 tag_matching_topology_context.log_matching_list_sz,
-			 in->tm_log_list_size);
-	}
-	MLX5_SET(xrqc, xrqc, user_index, in->user_index);
-	MLX5_SET(xrqc, xrqc, cqn, in->cqn);
-	MLX5_SET(create_xrq_in, create_in, opcode, MLX5_CMD_OP_CREATE_XRQ);
-	MLX5_SET(create_xrq_in, create_in, uid, in->uid);
-	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
-			    sizeof(create_out));
-	kvfree(create_in);
-	if (!err) {
-		srq->srqn = MLX5_GET(create_xrq_out, create_out, xrqn);
-		srq->uid = in->uid;
-	}
-
-	return err;
-}
-
-static int destroy_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
-{
-	u32 in[MLX5_ST_SZ_DW(destroy_xrq_in)] = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_xrq_out)] = {0};
-
-	MLX5_SET(destroy_xrq_in, in, opcode, MLX5_CMD_OP_DESTROY_XRQ);
-	MLX5_SET(destroy_xrq_in, in, xrqn,   srq->srqn);
-	MLX5_SET(destroy_xrq_in, in, uid, srq->uid);
-
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-static int arm_xrq_cmd(struct mlx5_core_dev *dev,
-		       struct mlx5_core_srq *srq,
-		       u16 lwm)
-{
-	u32 out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
-
-	MLX5_SET(arm_rq_in, in, opcode,     MLX5_CMD_OP_ARM_RQ);
-	MLX5_SET(arm_rq_in, in, op_mod,     MLX5_ARM_RQ_IN_OP_MOD_XRQ);
-	MLX5_SET(arm_rq_in, in, srq_number, srq->srqn);
-	MLX5_SET(arm_rq_in, in, lwm,	    lwm);
-	MLX5_SET(arm_rq_in, in, uid, srq->uid);
-
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-static int query_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_srq_attr *out)
-{
-	u32 in[MLX5_ST_SZ_DW(query_xrq_in)] = {0};
-	u32 *xrq_out;
-	int outlen = MLX5_ST_SZ_BYTES(query_xrq_out);
-	void *xrqc;
-	int err;
-
-	xrq_out = kvzalloc(outlen, GFP_KERNEL);
-	if (!xrq_out)
-		return -ENOMEM;
-
-	MLX5_SET(query_xrq_in, in, opcode, MLX5_CMD_OP_QUERY_XRQ);
-	MLX5_SET(query_xrq_in, in, xrqn, srq->srqn);
-
-	err = mlx5_cmd_exec(dev, in, sizeof(in), xrq_out, outlen);
-	if (err)
-		goto out;
-
-	xrqc = MLX5_ADDR_OF(query_xrq_out, xrq_out, xrq_context);
-	get_wq(MLX5_ADDR_OF(xrqc, xrqc, wq), out);
-	if (MLX5_GET(xrqc, xrqc, state) != MLX5_XRQC_STATE_GOOD)
-		out->flags |= MLX5_SRQ_FLAG_ERR;
-	out->tm_next_tag =
-		MLX5_GET(xrqc, xrqc,
-			 tag_matching_topology_context.append_next_index);
-	out->tm_hw_phase_cnt =
-		MLX5_GET(xrqc, xrqc,
-			 tag_matching_topology_context.hw_phase_cnt);
-	out->tm_sw_phase_cnt =
-		MLX5_GET(xrqc, xrqc,
-			 tag_matching_topology_context.sw_phase_cnt);
-
-out:
-	kvfree(xrq_out);
-	return err;
-}
-
-static int create_srq_split(struct mlx5_core_dev *dev,
-			    struct mlx5_core_srq *srq,
-			    struct mlx5_srq_attr *in)
-{
-	if (!dev->issi)
-		return create_srq_cmd(dev, srq, in);
-	switch (srq->common.res) {
-	case MLX5_RES_XSRQ:
-		return create_xrc_srq_cmd(dev, srq, in);
-	case MLX5_RES_XRQ:
-		return create_xrq_cmd(dev, srq, in);
-	default:
-		return create_rmp_cmd(dev, srq, in);
-	}
-}
-
-static int destroy_srq_split(struct mlx5_core_dev *dev,
-			     struct mlx5_core_srq *srq)
-{
-	if (!dev->issi)
-		return destroy_srq_cmd(dev, srq);
-	switch (srq->common.res) {
-	case MLX5_RES_XSRQ:
-		return destroy_xrc_srq_cmd(dev, srq);
-	case MLX5_RES_XRQ:
-		return destroy_xrq_cmd(dev, srq);
-	default:
-		return destroy_rmp_cmd(dev, srq);
-	}
-}
-
-int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_srq_attr *in)
-{
-	int err;
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
-
-	switch (in->type) {
-	case IB_SRQT_XRC:
-		srq->common.res = MLX5_RES_XSRQ;
-		break;
-	case IB_SRQT_TM:
-		srq->common.res = MLX5_RES_XRQ;
-		break;
-	default:
-		srq->common.res = MLX5_RES_SRQ;
-	}
-
-	err = create_srq_split(dev, srq, in);
-	if (err)
-		return err;
-
-	atomic_set(&srq->refcount, 1);
-	init_completion(&srq->free);
-
-	spin_lock_irq(&table->lock);
-	err = radix_tree_insert(&table->tree, srq->srqn, srq);
-	spin_unlock_irq(&table->lock);
-	if (err)
-		goto err_destroy_srq_split;
-
-	return 0;
-
-err_destroy_srq_split:
-	destroy_srq_split(dev, srq);
-
-	return err;
-}
-EXPORT_SYMBOL(mlx5_core_create_srq);
-
-int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
-{
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
-	struct mlx5_core_srq *tmp;
-	int err;
-
-	spin_lock_irq(&table->lock);
-	tmp = radix_tree_delete(&table->tree, srq->srqn);
-	spin_unlock_irq(&table->lock);
-	if (!tmp || tmp != srq)
-		return -EINVAL;
-
-	err = destroy_srq_split(dev, srq);
-	if (err)
-		return err;
-
-	if (atomic_dec_and_test(&srq->refcount))
-		complete(&srq->free);
-	wait_for_completion(&srq->free);
-
-	return 0;
-}
-EXPORT_SYMBOL(mlx5_core_destroy_srq);
-
-int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			struct mlx5_srq_attr *out)
-{
-	if (!dev->issi)
-		return query_srq_cmd(dev, srq, out);
-	switch (srq->common.res) {
-	case MLX5_RES_XSRQ:
-		return query_xrc_srq_cmd(dev, srq, out);
-	case MLX5_RES_XRQ:
-		return query_xrq_cmd(dev, srq, out);
-	default:
-		return query_rmp_cmd(dev, srq, out);
-	}
-}
-EXPORT_SYMBOL(mlx5_core_query_srq);
-
-int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-		      u16 lwm, int is_srq)
-{
-	if (!dev->issi)
-		return arm_srq_cmd(dev, srq, lwm, is_srq);
-	switch (srq->common.res) {
-	case MLX5_RES_XSRQ:
-		return arm_xrc_srq_cmd(dev, srq, lwm);
-	case MLX5_RES_XRQ:
-		return arm_xrq_cmd(dev, srq, lwm);
-	default:
-		return arm_rmp_cmd(dev, srq, lwm);
-	}
-}
-EXPORT_SYMBOL(mlx5_core_arm_srq);
-
 void mlx5_init_srq_table(struct mlx5_core_dev *dev)
 {
 	struct mlx5_srq_table *table = &dev->priv.srq_table;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index ab482124e901..c4d4b76096dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -258,49 +258,6 @@ void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn)
 }
 EXPORT_SYMBOL(mlx5_core_destroy_tis);
 
-int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen,
-			 u32 *rmpn)
-{
-	u32 out[MLX5_ST_SZ_DW(create_rmp_out)] = {0};
-	int err;
-
-	MLX5_SET(create_rmp_in, in, opcode, MLX5_CMD_OP_CREATE_RMP);
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
-	if (!err)
-		*rmpn = MLX5_GET(create_rmp_out, out, rmpn);
-
-	return err;
-}
-
-int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen)
-{
-	u32 out[MLX5_ST_SZ_DW(modify_rmp_out)] = {0};
-
-	MLX5_SET(modify_rmp_in, in, opcode, MLX5_CMD_OP_MODIFY_RMP);
-	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
-}
-
-int mlx5_core_destroy_rmp(struct mlx5_core_dev *dev, u32 rmpn)
-{
-	u32 in[MLX5_ST_SZ_DW(destroy_rmp_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_rmp_out)] = {0};
-
-	MLX5_SET(destroy_rmp_in, in, opcode, MLX5_CMD_OP_DESTROY_RMP);
-	MLX5_SET(destroy_rmp_in, in, rmpn, rmpn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out,
-					  sizeof(out));
-}
-
-int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out)
-{
-	u32 in[MLX5_ST_SZ_DW(query_rmp_in)] = {0};
-	int outlen = MLX5_ST_SZ_BYTES(query_rmp_out);
-
-	MLX5_SET(query_rmp_in, in, opcode, MLX5_CMD_OP_QUERY_RMP);
-	MLX5_SET(query_rmp_in, in, rmpn,   rmpn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
-}
-
 int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *rqtn)
 {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 27a481b159ed..1096da4fb368 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -904,13 +904,6 @@ struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev,
 						      gfp_t flags, int npages);
 void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev,
 				 struct mlx5_cmd_mailbox *head);
-int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_srq_attr *in);
-int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq);
-int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			struct mlx5_srq_attr *out);
-int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-		      u16 lwm, int is_srq);
 void mlx5_init_mkey_table(struct mlx5_core_dev *dev);
 void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev);
 int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
@@ -942,7 +935,6 @@ void mlx5_unregister_debugfs(void);
 
 void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas);
 void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas);
-struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 		    unsigned int *irqn);
 int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h
index 77bc4264066d..9343306cd188 100644
--- a/include/linux/mlx5/srq.h
+++ b/include/linux/mlx5/srq.h
@@ -6,37 +6,6 @@
 #ifndef MLX5_SRQ_H
 #define MLX5_SRQ_H
 
-#include <linux/mlx5/driver.h>
-
-enum {
-	MLX5_SRQ_FLAG_ERR    = (1 << 0),
-	MLX5_SRQ_FLAG_WQ_SIG = (1 << 1),
-	MLX5_SRQ_FLAG_RNDV   = (1 << 2),
-};
-
-struct mlx5_srq_attr {
-	u32 type;
-	u32 flags;
-	u32 log_size;
-	u32 wqe_shift;
-	u32 log_page_size;
-	u32 wqe_cnt;
-	u32 srqn;
-	u32 xrcd;
-	u32 page_offset;
-	u32 cqn;
-	u32 pd;
-	u32 lwm;
-	u32 user_index;
-	u64 db_record;
-	__be64 *pas;
-	u32 tm_log_list_size;
-	u32 tm_next_tag;
-	u32 tm_hw_phase_cnt;
-	u32 tm_sw_phase_cnt;
-	u16 uid;
-};
-
 struct mlx5_core_dev;
 
 void mlx5_init_srq_table(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h
index 39ebb699875b..a261d5528ff7 100644
--- a/include/linux/mlx5/transobj.h
+++ b/include/linux/mlx5/transobj.h
@@ -58,12 +58,6 @@ int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen,
 int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in,
 			 int inlen);
 void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn);
-int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen,
-			 u32 *rmpn);
-int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen);
-int mlx5_core_destroy_rmp(struct mlx5_core_dev *dev, u32 rmpn);
-int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out);
-
 int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *rqtn);
 int mlx5_core_modify_rqt(struct mlx5_core_dev *dev, u32 rqtn, u32 *in,
-- 
cgit v1.2.3


From c48d386b2bbb5b7546a409afb611346ba9520f73 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Nov 2018 20:53:38 +0200
Subject: RDMA/mlx5: Remove SRQ signature global flag

SRQ signature is not supported, hence no need for special static
global variable to announce it.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/srq.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index a86d9f153805..154fd0d3718e 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -12,9 +12,6 @@
 #include "mlx5_ib.h"
 #include "srq.h"
 
-/* not supported currently */
-static int srq_signature;
-
 static void *get_wqe(struct mlx5_ib_srq *srq, int n)
 {
 	return mlx5_buf_offset(&srq->buf, n << srq->msrq.wqe_shift);
@@ -175,7 +172,7 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 		err = -ENOMEM;
 		goto err_in;
 	}
-	srq->wq_sig = !!srq_signature;
+	srq->wq_sig = 0;
 
 	in->log_page_size = srq->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT;
 	if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1 &&
-- 
cgit v1.2.3


From 81773ce5f07fd4c3acd4bb7e918ce03a4e652a5f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Nov 2018 20:53:39 +0200
Subject: RDMA/mlx5: Use stages for callback to setup and release DEVX

Reuse existing infrastructure to initialize and release DEVX uid.
The DevX interface is intended for user space access, so it is supposed
to be initialized before ib_register_device(). Also it isn't supported
in switchdev mode and don't need to initialize it in that mode.

Fixes: 76dc5a8406bf ("IB/mlx5: Manage device uid for DEVX white list commands")
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c    | 26 +++++++++++++++++++-------
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  1 +
 2 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 7e6af18e7d82..56472fa3e18b 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -6237,6 +6237,22 @@ static void mlx5_ib_stage_dev_notifier_cleanup(struct mlx5_ib_dev *dev)
 	mlx5_notifier_unregister(dev->mdev, &dev->mdev_events);
 }
 
+static int mlx5_ib_stage_devx_init(struct mlx5_ib_dev *dev)
+{
+	int uid;
+
+	uid = mlx5_ib_devx_create(dev);
+	if (uid > 0)
+		dev->devx_whitelist_uid = uid;
+
+	return 0;
+}
+static void mlx5_ib_stage_devx_cleanup(struct mlx5_ib_dev *dev)
+{
+	if (dev->devx_whitelist_uid)
+		mlx5_ib_devx_destroy(dev, dev->devx_whitelist_uid);
+}
+
 void __mlx5_ib_remove(struct mlx5_ib_dev *dev,
 		      const struct mlx5_ib_profile *profile,
 		      int stage)
@@ -6248,8 +6264,6 @@ void __mlx5_ib_remove(struct mlx5_ib_dev *dev,
 			profile->stage[stage].cleanup(dev);
 	}
 
-	if (dev->devx_whitelist_uid)
-		mlx5_ib_devx_destroy(dev, dev->devx_whitelist_uid);
 	ib_dealloc_device((struct ib_device *)dev);
 }
 
@@ -6258,7 +6272,6 @@ void *__mlx5_ib_add(struct mlx5_ib_dev *dev,
 {
 	int err;
 	int i;
-	int uid;
 
 	for (i = 0; i < MLX5_IB_STAGE_MAX; i++) {
 		if (profile->stage[i].init) {
@@ -6268,10 +6281,6 @@ void *__mlx5_ib_add(struct mlx5_ib_dev *dev,
 		}
 	}
 
-	uid = mlx5_ib_devx_create(dev);
-	if (uid > 0)
-		dev->devx_whitelist_uid = uid;
-
 	dev->profile = profile;
 	dev->ib_active = true;
 
@@ -6326,6 +6335,9 @@ static const struct mlx5_ib_profile pf_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_SPECS,
 		     mlx5_ib_stage_populate_specs,
 		     NULL),
+	STAGE_CREATE(MLX5_IB_STAGE_WHITELIST_UID,
+		     mlx5_ib_stage_devx_init,
+		     mlx5_ib_stage_devx_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_IB_REG,
 		     mlx5_ib_stage_ib_reg_init,
 		     mlx5_ib_stage_ib_reg_cleanup),
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 7326fb8710e0..332d5c4d8ab3 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -783,6 +783,7 @@ enum mlx5_ib_stages {
 	MLX5_IB_STAGE_BFREG,
 	MLX5_IB_STAGE_PRE_IB_REG_UMR,
 	MLX5_IB_STAGE_SPECS,
+	MLX5_IB_STAGE_WHITELIST_UID,
 	MLX5_IB_STAGE_IB_REG,
 	MLX5_IB_STAGE_POST_IB_REG_UMR,
 	MLX5_IB_STAGE_DELAY_DROP,
-- 
cgit v1.2.3


From b4990804e1a46321806df6b56e3f04f1803a03d9 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Nov 2018 20:53:40 +0200
Subject: RDMA/mlx5: Update SRQ functions signatures to mlx5_ib format

Reflect the change of moving SRQ code from mlx5_core to mlx5_ib by
updating function signatures do not require mlx5_core_dev as an input,
because all operations in mlx5_ib are supposed to use mlx5_ib_dev.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/cq.c      |   3 +-
 drivers/infiniband/hw/mlx5/srq.c     |  10 +--
 drivers/infiniband/hw/mlx5/srq.h     |  18 ++---
 drivers/infiniband/hw/mlx5/srq_cmd.c | 129 ++++++++++++++++++-----------------
 4 files changed, 83 insertions(+), 77 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index c5d2824ada59..0b99f7d0630d 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -178,8 +178,7 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
 		struct mlx5_core_srq *msrq = NULL;
 
 		if (qp->ibqp.xrcd) {
-			msrq = mlx5_core_get_srq(dev->mdev,
-						 be32_to_cpu(cqe->srqn));
+			msrq = mlx5_cmd_get_srq(dev, be32_to_cpu(cqe->srqn));
 			srq = to_mibsrq(msrq);
 		} else {
 			srq = to_msrq(qp->ibqp.srq);
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 154fd0d3718e..2b184c7f531a 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -297,7 +297,7 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 
 	in.pd = to_mpd(pd)->pdn;
 	in.db_record = srq->db.dma;
-	err = mlx5_core_create_srq(dev->mdev, &srq->msrq, &in);
+	err = mlx5_cmd_create_srq(dev, &srq->msrq, &in);
 	kvfree(in.pas);
 	if (err) {
 		mlx5_ib_dbg(dev, "create SRQ failed, err %d\n", err);
@@ -321,7 +321,7 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 	return &srq->ibsrq;
 
 err_core:
-	mlx5_core_destroy_srq(dev->mdev, &srq->msrq);
+	mlx5_cmd_destroy_srq(dev, &srq->msrq);
 
 err_usr_kern_srq:
 	if (pd->uobject)
@@ -351,7 +351,7 @@ int mlx5_ib_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 			return -EINVAL;
 
 		mutex_lock(&srq->mutex);
-		ret = mlx5_core_arm_srq(dev->mdev, &srq->msrq, attr->srq_limit, 1);
+		ret = mlx5_cmd_arm_srq(dev, &srq->msrq, attr->srq_limit, 1);
 		mutex_unlock(&srq->mutex);
 
 		if (ret)
@@ -372,7 +372,7 @@ int mlx5_ib_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr)
 	if (!out)
 		return -ENOMEM;
 
-	ret = mlx5_core_query_srq(dev->mdev, &srq->msrq, out);
+	ret = mlx5_cmd_query_srq(dev, &srq->msrq, out);
 	if (ret)
 		goto out_box;
 
@@ -390,7 +390,7 @@ int mlx5_ib_destroy_srq(struct ib_srq *srq)
 	struct mlx5_ib_dev *dev = to_mdev(srq->device);
 	struct mlx5_ib_srq *msrq = to_msrq(srq);
 
-	mlx5_core_destroy_srq(dev->mdev, &msrq->msrq);
+	mlx5_cmd_destroy_srq(dev, &msrq->msrq);
 
 	if (srq->uobject) {
 		mlx5_ib_db_unmap_user(to_mucontext(srq->uobject->context), &msrq->db);
diff --git a/drivers/infiniband/hw/mlx5/srq.h b/drivers/infiniband/hw/mlx5/srq.h
index f23d5de12973..1110aeaa775e 100644
--- a/drivers/infiniband/hw/mlx5/srq.h
+++ b/drivers/infiniband/hw/mlx5/srq.h
@@ -35,12 +35,14 @@ struct mlx5_srq_attr {
 	u16 uid;
 };
 
-int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_srq_attr *in);
-int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq);
-int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			struct mlx5_srq_attr *out);
-int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-		      u16 lwm, int is_srq);
-struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
+struct mlx5_ib_dev;
+
+int mlx5_cmd_create_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+			struct mlx5_srq_attr *in);
+int mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq);
+int mlx5_cmd_query_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+		       struct mlx5_srq_attr *out);
+int mlx5_cmd_arm_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+		     u16 lwm, int is_srq);
+struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn);
 #endif /* MLX5_IB_SRQ_H */
diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c
index 4a64ad4c9b25..fdb9443f49f0 100644
--- a/drivers/infiniband/hw/mlx5/srq_cmd.c
+++ b/drivers/infiniband/hw/mlx5/srq_cmd.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cmd.h>
+#include "mlx5_ib.h"
 #include "srq.h"
 
 static int get_pas_size(struct mlx5_srq_attr *in)
@@ -77,11 +78,14 @@ static void get_srqc(void *srqc, struct mlx5_srq_attr *in)
 	in->db_record	  = MLX5_GET64(srqc, srqc, dbr_addr);
 }
 
-struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn)
+struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn)
 {
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
+	struct mlx5_core_dev *mdev = dev->mdev;
+	struct mlx5_srq_table *table;
 	struct mlx5_core_srq *srq;
 
+	table = &mdev->priv.srq_table;
+
 	spin_lock(&table->lock);
 
 	srq = radix_tree_lookup(&table->tree, srqn);
@@ -93,7 +97,7 @@ struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn)
 	return srq;
 }
 
-static int create_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+static int create_srq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			  struct mlx5_srq_attr *in)
 {
 	u32 create_out[MLX5_ST_SZ_DW(create_srq_out)] = {0};
@@ -120,7 +124,7 @@ static int create_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	MLX5_SET(create_srq_in, create_in, opcode,
 		 MLX5_CMD_OP_CREATE_SRQ);
 
-	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
+	err = mlx5_cmd_exec(dev->mdev, create_in, inlen, create_out,
 			    sizeof(create_out));
 	kvfree(create_in);
 	if (!err) {
@@ -131,8 +135,7 @@ static int create_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	return err;
 }
 
-static int destroy_srq_cmd(struct mlx5_core_dev *dev,
-			   struct mlx5_core_srq *srq)
+static int destroy_srq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
 {
 	u32 srq_in[MLX5_ST_SZ_DW(destroy_srq_in)] = {0};
 	u32 srq_out[MLX5_ST_SZ_DW(destroy_srq_out)] = {0};
@@ -142,11 +145,11 @@ static int destroy_srq_cmd(struct mlx5_core_dev *dev,
 	MLX5_SET(destroy_srq_in, srq_in, srqn, srq->srqn);
 	MLX5_SET(destroy_srq_in, srq_in, uid, srq->uid);
 
-	return mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
-			     srq_out, sizeof(srq_out));
+	return mlx5_cmd_exec(dev->mdev, srq_in, sizeof(srq_in), srq_out,
+			     sizeof(srq_out));
 }
 
-static int arm_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+static int arm_srq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 		       u16 lwm, int is_srq)
 {
 	u32 srq_in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
@@ -158,11 +161,11 @@ static int arm_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	MLX5_SET(arm_rq_in, srq_in, lwm,      lwm);
 	MLX5_SET(arm_rq_in, srq_in, uid, srq->uid);
 
-	return  mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
-			      srq_out, sizeof(srq_out));
+	return mlx5_cmd_exec(dev->mdev, srq_in, sizeof(srq_in), srq_out,
+			     sizeof(srq_out));
 }
 
-static int query_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+static int query_srq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			 struct mlx5_srq_attr *out)
 {
 	u32 srq_in[MLX5_ST_SZ_DW(query_srq_in)] = {0};
@@ -177,8 +180,8 @@ static int query_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	MLX5_SET(query_srq_in, srq_in, opcode,
 		 MLX5_CMD_OP_QUERY_SRQ);
 	MLX5_SET(query_srq_in, srq_in, srqn, srq->srqn);
-	err =  mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
-			     srq_out, MLX5_ST_SZ_BYTES(query_srq_out));
+	err = mlx5_cmd_exec(dev->mdev, srq_in, sizeof(srq_in), srq_out,
+			    MLX5_ST_SZ_BYTES(query_srq_out));
 	if (err)
 		goto out;
 
@@ -191,7 +194,7 @@ out:
 	return err;
 }
 
-static int create_xrc_srq_cmd(struct mlx5_core_dev *dev,
+static int create_xrc_srq_cmd(struct mlx5_ib_dev *dev,
 			      struct mlx5_core_srq *srq,
 			      struct mlx5_srq_attr *in)
 {
@@ -221,7 +224,7 @@ static int create_xrc_srq_cmd(struct mlx5_core_dev *dev,
 		 MLX5_CMD_OP_CREATE_XRC_SRQ);
 
 	memset(create_out, 0, sizeof(create_out));
-	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
+	err = mlx5_cmd_exec(dev->mdev, create_in, inlen, create_out,
 			    sizeof(create_out));
 	if (err)
 		goto out;
@@ -233,7 +236,7 @@ out:
 	return err;
 }
 
-static int destroy_xrc_srq_cmd(struct mlx5_core_dev *dev,
+static int destroy_xrc_srq_cmd(struct mlx5_ib_dev *dev,
 			       struct mlx5_core_srq *srq)
 {
 	u32 xrcsrq_in[MLX5_ST_SZ_DW(destroy_xrc_srq_in)]   = {0};
@@ -244,12 +247,12 @@ static int destroy_xrc_srq_cmd(struct mlx5_core_dev *dev,
 	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
 	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, uid, srq->uid);
 
-	return mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in),
+	return mlx5_cmd_exec(dev->mdev, xrcsrq_in, sizeof(xrcsrq_in),
 			     xrcsrq_out, sizeof(xrcsrq_out));
 }
 
-static int arm_xrc_srq_cmd(struct mlx5_core_dev *dev,
-			   struct mlx5_core_srq *srq, u16 lwm)
+static int arm_xrc_srq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+			   u16 lwm)
 {
 	u32 xrcsrq_in[MLX5_ST_SZ_DW(arm_xrc_srq_in)]   = {0};
 	u32 xrcsrq_out[MLX5_ST_SZ_DW(arm_xrc_srq_out)] = {0};
@@ -260,11 +263,11 @@ static int arm_xrc_srq_cmd(struct mlx5_core_dev *dev,
 	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, lwm,      lwm);
 	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, uid, srq->uid);
 
-	return  mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in),
+	return  mlx5_cmd_exec(dev->mdev, xrcsrq_in, sizeof(xrcsrq_in),
 			      xrcsrq_out, sizeof(xrcsrq_out));
 }
 
-static int query_xrc_srq_cmd(struct mlx5_core_dev *dev,
+static int query_xrc_srq_cmd(struct mlx5_ib_dev *dev,
 			     struct mlx5_core_srq *srq,
 			     struct mlx5_srq_attr *out)
 {
@@ -282,8 +285,8 @@ static int query_xrc_srq_cmd(struct mlx5_core_dev *dev,
 		 MLX5_CMD_OP_QUERY_XRC_SRQ);
 	MLX5_SET(query_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
 
-	err =  mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in), xrcsrq_out,
-			     MLX5_ST_SZ_BYTES(query_xrc_srq_out));
+	err = mlx5_cmd_exec(dev->mdev, xrcsrq_in, sizeof(xrcsrq_in),
+			    xrcsrq_out, MLX5_ST_SZ_BYTES(query_xrc_srq_out));
 	if (err)
 		goto out;
 
@@ -298,39 +301,39 @@ out:
 	return err;
 }
 
-static int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen,
+static int mlx5_core_create_rmp(struct mlx5_ib_dev *dev, u32 *in, int inlen,
 				u32 *rmpn)
 {
 	u32 out[MLX5_ST_SZ_DW(create_rmp_out)] = { 0 };
 	int err;
 
 	MLX5_SET(create_rmp_in, in, opcode, MLX5_CMD_OP_CREATE_RMP);
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	err = mlx5_cmd_exec(dev->mdev, in, inlen, out, sizeof(out));
 	if (!err)
 		*rmpn = MLX5_GET(create_rmp_out, out, rmpn);
 
 	return err;
 }
 
-static int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen)
+static int mlx5_core_modify_rmp(struct mlx5_ib_dev *dev, u32 *in, int inlen)
 {
 	u32 out[MLX5_ST_SZ_DW(modify_rmp_out)] = {0};
 
 	MLX5_SET(modify_rmp_in, in, opcode, MLX5_CMD_OP_MODIFY_RMP);
-	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	return mlx5_cmd_exec(dev->mdev, in, inlen, out, sizeof(out));
 }
 
-static int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out)
+static int mlx5_core_query_rmp(struct mlx5_ib_dev *dev, u32 rmpn, u32 *out)
 {
 	u32 in[MLX5_ST_SZ_DW(query_rmp_in)] = {0};
 	int outlen = MLX5_ST_SZ_BYTES(query_rmp_out);
 
 	MLX5_SET(query_rmp_in, in, opcode, MLX5_CMD_OP_QUERY_RMP);
 	MLX5_SET(query_rmp_in, in, rmpn,   rmpn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+	return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, outlen);
 }
 
-static int create_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+static int create_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			  struct mlx5_srq_attr *in)
 {
 	void *create_in;
@@ -362,8 +365,7 @@ static int create_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	return err;
 }
 
-static int destroy_rmp_cmd(struct mlx5_core_dev *dev,
-			   struct mlx5_core_srq *srq)
+static int destroy_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
 {
 	u32 in[MLX5_ST_SZ_DW(destroy_rmp_in)]   = {};
 	u32 out[MLX5_ST_SZ_DW(destroy_rmp_out)] = {};
@@ -371,11 +373,10 @@ static int destroy_rmp_cmd(struct mlx5_core_dev *dev,
 	MLX5_SET(destroy_rmp_in, in, opcode, MLX5_CMD_OP_DESTROY_RMP);
 	MLX5_SET(destroy_rmp_in, in, rmpn, srq->srqn);
 	MLX5_SET(destroy_rmp_in, in, uid, srq->uid);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
 }
 
-static int arm_rmp_cmd(struct mlx5_core_dev *dev,
-		       struct mlx5_core_srq *srq,
+static int arm_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 		       u16 lwm)
 {
 	void *in;
@@ -405,7 +406,7 @@ static int arm_rmp_cmd(struct mlx5_core_dev *dev,
 	return err;
 }
 
-static int query_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+static int query_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			 struct mlx5_srq_attr *out)
 {
 	u32 *rmp_out;
@@ -430,7 +431,7 @@ out:
 	return err;
 }
 
-static int create_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+static int create_xrq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			  struct mlx5_srq_attr *in)
 {
 	u32 create_out[MLX5_ST_SZ_DW(create_xrq_out)] = {0};
@@ -465,7 +466,7 @@ static int create_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	MLX5_SET(xrqc, xrqc, cqn, in->cqn);
 	MLX5_SET(create_xrq_in, create_in, opcode, MLX5_CMD_OP_CREATE_XRQ);
 	MLX5_SET(create_xrq_in, create_in, uid, in->uid);
-	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
+	err = mlx5_cmd_exec(dev->mdev, create_in, inlen, create_out,
 			    sizeof(create_out));
 	kvfree(create_in);
 	if (!err) {
@@ -476,7 +477,7 @@ static int create_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	return err;
 }
 
-static int destroy_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
+static int destroy_xrq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
 {
 	u32 in[MLX5_ST_SZ_DW(destroy_xrq_in)] = {0};
 	u32 out[MLX5_ST_SZ_DW(destroy_xrq_out)] = {0};
@@ -485,10 +486,10 @@ static int destroy_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
 	MLX5_SET(destroy_xrq_in, in, xrqn,   srq->srqn);
 	MLX5_SET(destroy_xrq_in, in, uid, srq->uid);
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
 }
 
-static int arm_xrq_cmd(struct mlx5_core_dev *dev,
+static int arm_xrq_cmd(struct mlx5_ib_dev *dev,
 		       struct mlx5_core_srq *srq,
 		       u16 lwm)
 {
@@ -501,10 +502,10 @@ static int arm_xrq_cmd(struct mlx5_core_dev *dev,
 	MLX5_SET(arm_rq_in, in, lwm,	    lwm);
 	MLX5_SET(arm_rq_in, in, uid, srq->uid);
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
 }
 
-static int query_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+static int query_xrq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			 struct mlx5_srq_attr *out)
 {
 	u32 in[MLX5_ST_SZ_DW(query_xrq_in)] = {0};
@@ -520,7 +521,7 @@ static int query_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	MLX5_SET(query_xrq_in, in, opcode, MLX5_CMD_OP_QUERY_XRQ);
 	MLX5_SET(query_xrq_in, in, xrqn, srq->srqn);
 
-	err = mlx5_cmd_exec(dev, in, sizeof(in), xrq_out, outlen);
+	err = mlx5_cmd_exec(dev->mdev, in, sizeof(in), xrq_out, outlen);
 	if (err)
 		goto out;
 
@@ -543,11 +544,10 @@ out:
 	return err;
 }
 
-static int create_srq_split(struct mlx5_core_dev *dev,
-			    struct mlx5_core_srq *srq,
+static int create_srq_split(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			    struct mlx5_srq_attr *in)
 {
-	if (!dev->issi)
+	if (!dev->mdev->issi)
 		return create_srq_cmd(dev, srq, in);
 	switch (srq->common.res) {
 	case MLX5_RES_XSRQ:
@@ -559,10 +559,9 @@ static int create_srq_split(struct mlx5_core_dev *dev,
 	}
 }
 
-static int destroy_srq_split(struct mlx5_core_dev *dev,
-			     struct mlx5_core_srq *srq)
+static int destroy_srq_split(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
 {
-	if (!dev->issi)
+	if (!dev->mdev->issi)
 		return destroy_srq_cmd(dev, srq);
 	switch (srq->common.res) {
 	case MLX5_RES_XSRQ:
@@ -574,11 +573,14 @@ static int destroy_srq_split(struct mlx5_core_dev *dev,
 	}
 }
 
-int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_srq_attr *in)
+int mlx5_cmd_create_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+			struct mlx5_srq_attr *in)
 {
+	struct mlx5_core_dev *mdev = dev->mdev;
+	struct mlx5_srq_table *table;
 	int err;
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
+
+	table = &mdev->priv.srq_table;
 
 	switch (in->type) {
 	case IB_SRQT_XRC:
@@ -612,12 +614,15 @@ err_destroy_srq_split:
 	return err;
 }
 
-int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
+int mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
 {
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
+	struct mlx5_core_dev *mdev = dev->mdev;
+	struct mlx5_srq_table *table;
 	struct mlx5_core_srq *tmp;
 	int err;
 
+	table = &mdev->priv.srq_table;
+
 	spin_lock_irq(&table->lock);
 	tmp = radix_tree_delete(&table->tree, srq->srqn);
 	spin_unlock_irq(&table->lock);
@@ -635,10 +640,10 @@ int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
 	return 0;
 }
 
-int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			struct mlx5_srq_attr *out)
+int mlx5_cmd_query_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+		       struct mlx5_srq_attr *out)
 {
-	if (!dev->issi)
+	if (!dev->mdev->issi)
 		return query_srq_cmd(dev, srq, out);
 	switch (srq->common.res) {
 	case MLX5_RES_XSRQ:
@@ -650,10 +655,10 @@ int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	}
 }
 
-int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-		      u16 lwm, int is_srq)
+int mlx5_cmd_arm_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+		     u16 lwm, int is_srq)
 {
-	if (!dev->issi)
+	if (!dev->mdev->issi)
 		return arm_srq_cmd(dev, srq, lwm, is_srq);
 	switch (srq->common.res) {
 	case MLX5_RES_XSRQ:
-- 
cgit v1.2.3


From f3da6577da67a3cd44610ca54e308c6838c92157 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Nov 2018 20:53:41 +0200
Subject: RDMA/mlx5: Initialize SRQ tables on mlx5_ib

Transfer initialization and cleanup from mlx5_priv struct of
mlx5_core_dev to be part of mlx5_ib_dev. This completes removal
of SRQ from mlx5_core.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/ib_rep.c              |  4 ++
 drivers/infiniband/hw/mlx5/main.c                |  7 +++
 drivers/infiniband/hw/mlx5/mlx5_ib.h             |  5 +-
 drivers/infiniband/hw/mlx5/srq.c                 |  1 -
 drivers/infiniband/hw/mlx5/srq.h                 | 25 ++++++++
 drivers/infiniband/hw/mlx5/srq_cmd.c             | 72 ++++++++++++++++++++----
 drivers/net/ethernet/mellanox/mlx5/core/Makefile |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c   |  5 --
 drivers/net/ethernet/mellanox/mlx5/core/srq.c    | 63 ---------------------
 include/linux/mlx5/driver.h                      | 25 --------
 include/linux/mlx5/srq.h                         | 14 -----
 11 files changed, 101 insertions(+), 122 deletions(-)
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/srq.c
 delete mode 100644 include/linux/mlx5/srq.h

diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index 584ff2ea7810..8a682d86d634 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -4,6 +4,7 @@
  */
 
 #include "ib_rep.h"
+#include "srq.h"
 
 static const struct mlx5_ib_profile rep_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_INIT,
@@ -21,6 +22,9 @@ static const struct mlx5_ib_profile rep_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_ROCE,
 		     mlx5_ib_stage_rep_roce_init,
 		     mlx5_ib_stage_rep_roce_cleanup),
+	STAGE_CREATE(MLX5_IB_STAGE_SRQ,
+		     mlx5_init_srq_table,
+		     mlx5_cleanup_srq_table),
 	STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES,
 		     mlx5_ib_stage_dev_res_init,
 		     mlx5_ib_stage_dev_res_cleanup),
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 56472fa3e18b..96515a8c9d2c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -60,6 +60,7 @@
 #include "mlx5_ib.h"
 #include "ib_rep.h"
 #include "cmd.h"
+#include "srq.h"
 #include <linux/mlx5/fs_helpers.h>
 #include <linux/mlx5/accel.h>
 #include <rdma/uverbs_std_types.h>
@@ -6308,6 +6309,9 @@ static const struct mlx5_ib_profile pf_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_ROCE,
 		     mlx5_ib_stage_roce_init,
 		     mlx5_ib_stage_roce_cleanup),
+	STAGE_CREATE(MLX5_IB_STAGE_SRQ,
+		     mlx5_init_srq_table,
+		     mlx5_cleanup_srq_table),
 	STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES,
 		     mlx5_ib_stage_dev_res_init,
 		     mlx5_ib_stage_dev_res_cleanup),
@@ -6365,6 +6369,9 @@ static const struct mlx5_ib_profile nic_rep_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_ROCE,
 		     mlx5_ib_stage_rep_roce_init,
 		     mlx5_ib_stage_rep_roce_cleanup),
+	STAGE_CREATE(MLX5_IB_STAGE_SRQ,
+		     mlx5_init_srq_table,
+		     mlx5_cleanup_srq_table),
 	STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES,
 		     mlx5_ib_stage_dev_res_init,
 		     mlx5_ib_stage_dev_res_cleanup),
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 332d5c4d8ab3..861b68f2e330 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -41,7 +41,6 @@
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/fs.h>
 #include <linux/mlx5/qp.h>
-#include <linux/mlx5/srq.h>
 #include <linux/mlx5/fs.h>
 #include <linux/types.h>
 #include <linux/mlx5/transobj.h>
@@ -50,6 +49,8 @@
 #include <rdma/uverbs_ioctl.h>
 #include <rdma/mlx5_user_ioctl_cmds.h>
 
+#include "srq.h"
+
 #define mlx5_ib_dbg(_dev, format, arg...)                                      \
 	dev_dbg(&(_dev)->ib_dev.dev, "%s:%d:(pid %d): " format, __func__,      \
 		__LINE__, current->pid, ##arg)
@@ -774,6 +775,7 @@ enum mlx5_ib_stages {
 	MLX5_IB_STAGE_CAPS,
 	MLX5_IB_STAGE_NON_DEFAULT_CB,
 	MLX5_IB_STAGE_ROCE,
+	MLX5_IB_STAGE_SRQ,
 	MLX5_IB_STAGE_DEVICE_RESOURCES,
 	MLX5_IB_STAGE_DEVICE_NOTIFIER,
 	MLX5_IB_STAGE_ODP,
@@ -942,6 +944,7 @@ struct mlx5_ib_dev {
 	u64			sys_image_guid;
 	struct mlx5_memic	memic;
 	u16			devx_whitelist_uid;
+	struct mlx5_srq_table   srq_table;
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 2b184c7f531a..91dcd3918d96 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -5,7 +5,6 @@
 
 #include <linux/module.h>
 #include <linux/mlx5/qp.h>
-#include <linux/mlx5/srq.h>
 #include <linux/slab.h>
 #include <rdma/ib_umem.h>
 #include <rdma/ib_user_verbs.h>
diff --git a/drivers/infiniband/hw/mlx5/srq.h b/drivers/infiniband/hw/mlx5/srq.h
index 1110aeaa775e..75eb5839ae95 100644
--- a/drivers/infiniband/hw/mlx5/srq.h
+++ b/drivers/infiniband/hw/mlx5/srq.h
@@ -37,6 +37,28 @@ struct mlx5_srq_attr {
 
 struct mlx5_ib_dev;
 
+struct mlx5_core_srq {
+	struct mlx5_core_rsc_common common; /* must be first */
+	u32 srqn;
+	int max;
+	size_t max_gs;
+	size_t max_avail_gather;
+	int wqe_shift;
+	void (*event)(struct mlx5_core_srq *srq, enum mlx5_event e);
+
+	atomic_t refcount;
+	struct completion free;
+	u16 uid;
+};
+
+struct mlx5_srq_table {
+	struct notifier_block nb;
+	/* protect radix tree
+	 */
+	spinlock_t lock;
+	struct radix_tree_root tree;
+};
+
 int mlx5_cmd_create_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			struct mlx5_srq_attr *in);
 int mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq);
@@ -45,4 +67,7 @@ int mlx5_cmd_query_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 int mlx5_cmd_arm_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 		     u16 lwm, int is_srq);
 struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn);
+
+int mlx5_init_srq_table(struct mlx5_ib_dev *dev);
+void mlx5_cleanup_srq_table(struct mlx5_ib_dev *dev);
 #endif /* MLX5_IB_SRQ_H */
diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c
index fdb9443f49f0..6be89c6be40f 100644
--- a/drivers/infiniband/hw/mlx5/srq_cmd.c
+++ b/drivers/infiniband/hw/mlx5/srq_cmd.c
@@ -80,12 +80,9 @@ static void get_srqc(void *srqc, struct mlx5_srq_attr *in)
 
 struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn)
 {
-	struct mlx5_core_dev *mdev = dev->mdev;
-	struct mlx5_srq_table *table;
+	struct mlx5_srq_table *table = &dev->srq_table;
 	struct mlx5_core_srq *srq;
 
-	table = &mdev->priv.srq_table;
-
 	spin_lock(&table->lock);
 
 	srq = radix_tree_lookup(&table->tree, srqn);
@@ -576,12 +573,9 @@ static int destroy_srq_split(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
 int mlx5_cmd_create_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			struct mlx5_srq_attr *in)
 {
-	struct mlx5_core_dev *mdev = dev->mdev;
-	struct mlx5_srq_table *table;
+	struct mlx5_srq_table *table = &dev->srq_table;
 	int err;
 
-	table = &mdev->priv.srq_table;
-
 	switch (in->type) {
 	case IB_SRQT_XRC:
 		srq->common.res = MLX5_RES_XSRQ;
@@ -616,13 +610,10 @@ err_destroy_srq_split:
 
 int mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
 {
-	struct mlx5_core_dev *mdev = dev->mdev;
-	struct mlx5_srq_table *table;
+	struct mlx5_srq_table *table = &dev->srq_table;
 	struct mlx5_core_srq *tmp;
 	int err;
 
-	table = &mdev->priv.srq_table;
-
 	spin_lock_irq(&table->lock);
 	tmp = radix_tree_delete(&table->tree, srq->srqn);
 	spin_unlock_irq(&table->lock);
@@ -669,3 +660,60 @@ int mlx5_cmd_arm_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 		return arm_rmp_cmd(dev, srq, lwm);
 	}
 }
+
+static int srq_event_notifier(struct notifier_block *nb,
+			      unsigned long type, void *data)
+{
+	struct mlx5_srq_table *table;
+	struct mlx5_core_srq *srq;
+	struct mlx5_eqe *eqe;
+	u32 srqn;
+
+	if (type != MLX5_EVENT_TYPE_SRQ_CATAS_ERROR &&
+	    type != MLX5_EVENT_TYPE_SRQ_RQ_LIMIT)
+		return NOTIFY_DONE;
+
+	table = container_of(nb, struct mlx5_srq_table, nb);
+
+	eqe = data;
+	srqn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
+
+	spin_lock(&table->lock);
+
+	srq = radix_tree_lookup(&table->tree, srqn);
+	if (srq)
+		atomic_inc(&srq->refcount);
+
+	spin_unlock(&table->lock);
+
+	if (!srq)
+		return NOTIFY_OK;
+
+	srq->event(srq, eqe->type);
+
+	if (atomic_dec_and_test(&srq->refcount))
+		complete(&srq->free);
+
+	return NOTIFY_OK;
+}
+
+int mlx5_init_srq_table(struct mlx5_ib_dev *dev)
+{
+	struct mlx5_srq_table *table = &dev->srq_table;
+
+	memset(table, 0, sizeof(*table));
+	spin_lock_init(&table->lock);
+	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
+
+	table->nb.notifier_call = srq_event_notifier;
+	mlx5_notifier_register(dev->mdev, &table->nb);
+
+	return 0;
+}
+
+void mlx5_cleanup_srq_table(struct mlx5_ib_dev *dev)
+{
+	struct mlx5_srq_table *table = &dev->srq_table;
+
+	mlx5_notifier_unregister(dev->mdev, &table->nb);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 26afe0779a0c..d499b3d00348 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 # mlx5 core basic
 #
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
-		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
+		health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \
 		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
 		fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
 		diag/fs_tracepoint.o diag/fw_tracer.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 4bc27a073dc4..778995573812 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -43,7 +43,6 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/qp.h>
-#include <linux/mlx5/srq.h>
 #include <linux/debugfs.h>
 #include <linux/kmod.h>
 #include <linux/mlx5/mlx5_ifc.h>
@@ -749,8 +748,6 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 
 	mlx5_init_qp_table(dev);
 
-	mlx5_init_srq_table(dev);
-
 	mlx5_init_mkey_table(dev);
 
 	mlx5_init_reserved_gids(dev);
@@ -804,7 +801,6 @@ err_rl_cleanup:
 err_tables_cleanup:
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_mkey_table(dev);
-	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 err_events_cleanup:
@@ -828,7 +824,6 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cleanup_clock(dev);
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cleanup_mkey_table(dev);
-	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_events_cleanup(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
deleted file mode 100644
index 0e80ddbe2510..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c
+++ /dev/null
@@ -1,63 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
-/*
- * Copyright (c) 2013-2018, Mellanox Technologies inc.  All rights reserved.
- */
-
-#include <linux/kernel.h>
-#include <linux/mlx5/driver.h>
-#include <linux/mlx5/srq.h>
-
-static int srq_event_notifier(struct notifier_block *nb,
-			      unsigned long type, void *data)
-{
-	struct mlx5_srq_table *table;
-	struct mlx5_core_srq *srq;
-	struct mlx5_eqe *eqe;
-	u32 srqn;
-
-	if (type != MLX5_EVENT_TYPE_SRQ_CATAS_ERROR &&
-	    type != MLX5_EVENT_TYPE_SRQ_RQ_LIMIT)
-		return NOTIFY_DONE;
-
-	table = container_of(nb, struct mlx5_srq_table, nb);
-
-	eqe = data;
-	srqn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
-
-	spin_lock(&table->lock);
-
-	srq = radix_tree_lookup(&table->tree, srqn);
-	if (srq)
-		atomic_inc(&srq->refcount);
-
-	spin_unlock(&table->lock);
-
-	if (!srq)
-		return NOTIFY_OK;
-
-	srq->event(srq, eqe->type);
-
-	if (atomic_dec_and_test(&srq->refcount))
-		complete(&srq->free);
-
-	return NOTIFY_OK;
-}
-
-void mlx5_init_srq_table(struct mlx5_core_dev *dev)
-{
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
-
-	memset(table, 0, sizeof(*table));
-	spin_lock_init(&table->lock);
-	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
-
-	table->nb.notifier_call = srq_event_notifier;
-	mlx5_notifier_register(dev, &table->nb);
-}
-
-void mlx5_cleanup_srq_table(struct mlx5_core_dev *dev)
-{
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
-
-	mlx5_notifier_unregister(dev, &table->nb);
-}
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 1096da4fb368..584d8a5df7eb 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -50,7 +50,6 @@
 
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/doorbell.h>
-#include <linux/mlx5/srq.h>
 #include <linux/mlx5/eq.h>
 #include <linux/timecounter.h>
 #include <linux/ptp_clock_kernel.h>
@@ -393,20 +392,6 @@ struct mlx5_core_rsc_common {
 	struct completion	free;
 };
 
-struct mlx5_core_srq {
-	struct mlx5_core_rsc_common	common; /* must be first */
-	u32		srqn;
-	int		max;
-	size_t		max_gs;
-	size_t		max_avail_gather;
-	int		wqe_shift;
-	void (*event)	(struct mlx5_core_srq *, enum mlx5_event);
-
-	atomic_t		refcount;
-	struct completion	free;
-	u16		uid;
-};
-
 struct mlx5_uars_page {
 	void __iomem	       *map;
 	bool			wc;
@@ -464,14 +449,6 @@ struct mlx5_qp_table {
 	struct radix_tree_root	tree;
 };
 
-struct mlx5_srq_table {
-	struct notifier_block   nb;
-	/* protect radix tree
-	 */
-	spinlock_t		lock;
-	struct radix_tree_root	tree;
-};
-
 struct mlx5_mkey_table {
 	/* protect radix tree
 	 */
@@ -547,8 +524,6 @@ struct mlx5_priv {
 
 	struct mlx5_core_health health;
 
-	struct mlx5_srq_table	srq_table;
-
 	/* start: qp staff */
 	struct mlx5_qp_table	qp_table;
 	struct dentry	       *qp_debugfs;
diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h
deleted file mode 100644
index 9343306cd188..000000000000
--- a/include/linux/mlx5/srq.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
-/*
- * Copyright (c) 2013-2018, Mellanox Technologies. All rights reserved.
- */
-
-#ifndef MLX5_SRQ_H
-#define MLX5_SRQ_H
-
-struct mlx5_core_dev;
-
-void mlx5_init_srq_table(struct mlx5_core_dev *dev);
-void mlx5_cleanup_srq_table(struct mlx5_core_dev *dev);
-
-#endif /* MLX5_SRQ_H */
-- 
cgit v1.2.3


From a1eb180238a71797d84bd91acfb1de1d632623c5 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Nov 2018 20:53:42 +0200
Subject: RDMA/mlx5: Unfold create RMP function

There is no need to perform create_rmp in two separate function, while
one of them uses stack as a placeholder for data while other allocates
it dynamically. Combine those two functions to one instead of two.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/srq_cmd.c | 35 ++++++++++++++++-------------------
 1 file changed, 16 insertions(+), 19 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c
index 6be89c6be40f..955df638b416 100644
--- a/drivers/infiniband/hw/mlx5/srq_cmd.c
+++ b/drivers/infiniband/hw/mlx5/srq_cmd.c
@@ -298,20 +298,6 @@ out:
 	return err;
 }
 
-static int mlx5_core_create_rmp(struct mlx5_ib_dev *dev, u32 *in, int inlen,
-				u32 *rmpn)
-{
-	u32 out[MLX5_ST_SZ_DW(create_rmp_out)] = { 0 };
-	int err;
-
-	MLX5_SET(create_rmp_in, in, opcode, MLX5_CMD_OP_CREATE_RMP);
-	err = mlx5_cmd_exec(dev->mdev, in, inlen, out, sizeof(out));
-	if (!err)
-		*rmpn = MLX5_GET(create_rmp_out, out, rmpn);
-
-	return err;
-}
-
 static int mlx5_core_modify_rmp(struct mlx5_ib_dev *dev, u32 *in, int inlen)
 {
 	u32 out[MLX5_ST_SZ_DW(modify_rmp_out)] = {0};
@@ -333,18 +319,24 @@ static int mlx5_core_query_rmp(struct mlx5_ib_dev *dev, u32 rmpn, u32 *out)
 static int create_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			  struct mlx5_srq_attr *in)
 {
-	void *create_in;
+	void *create_out = NULL;
+	void *create_in = NULL;
 	void *rmpc;
 	void *wq;
 	int pas_size;
+	int outlen;
 	int inlen;
 	int err;
 
 	pas_size = get_pas_size(in);
 	inlen = MLX5_ST_SZ_BYTES(create_rmp_in) + pas_size;
+	outlen = MLX5_ST_SZ_BYTES(create_rmp_out);
 	create_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!create_in)
-		return -ENOMEM;
+	create_out = kvzalloc(outlen, GFP_KERNEL);
+	if (!create_in || !create_out) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	rmpc = MLX5_ADDR_OF(create_rmp_in, create_in, ctx);
 	wq = MLX5_ADDR_OF(rmpc, rmpc, wq);
@@ -354,11 +346,16 @@ static int create_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 	set_wq(wq, in);
 	memcpy(MLX5_ADDR_OF(rmpc, rmpc, wq.pas), in->pas, pas_size);
 
-	err = mlx5_core_create_rmp(dev, create_in, inlen, &srq->srqn);
-	if (!err)
+	MLX5_SET(create_rmp_in, create_in, opcode, MLX5_CMD_OP_CREATE_RMP);
+	err = mlx5_cmd_exec(dev->mdev, create_in, inlen, create_out, outlen);
+	if (!err) {
+		srq->srqn = MLX5_GET(create_rmp_out, create_out, rmpn);
 		srq->uid = in->uid;
+	}
 
+out:
 	kvfree(create_in);
+	kvfree(create_out);
 	return err;
 }
 
-- 
cgit v1.2.3


From 36ff48805ae457d79886147913ad07056780dca0 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Nov 2018 20:53:43 +0200
Subject: RDMA/mlx5: Unfold modify RMP function

There is no need to perform modify_rmp in two separate function,
while one of them uses stack as a placeholder for data while other
allocates it dynamically. Combine those two functions to one call
instead of two.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/srq_cmd.c | 62 ++++++++++++++++++++----------------
 1 file changed, 34 insertions(+), 28 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c
index 955df638b416..7aaaffbd4afa 100644
--- a/drivers/infiniband/hw/mlx5/srq_cmd.c
+++ b/drivers/infiniband/hw/mlx5/srq_cmd.c
@@ -298,24 +298,6 @@ out:
 	return err;
 }
 
-static int mlx5_core_modify_rmp(struct mlx5_ib_dev *dev, u32 *in, int inlen)
-{
-	u32 out[MLX5_ST_SZ_DW(modify_rmp_out)] = {0};
-
-	MLX5_SET(modify_rmp_in, in, opcode, MLX5_CMD_OP_MODIFY_RMP);
-	return mlx5_cmd_exec(dev->mdev, in, inlen, out, sizeof(out));
-}
-
-static int mlx5_core_query_rmp(struct mlx5_ib_dev *dev, u32 rmpn, u32 *out)
-{
-	u32 in[MLX5_ST_SZ_DW(query_rmp_in)] = {0};
-	int outlen = MLX5_ST_SZ_BYTES(query_rmp_out);
-
-	MLX5_SET(query_rmp_in, in, opcode, MLX5_CMD_OP_QUERY_RMP);
-	MLX5_SET(query_rmp_in, in, rmpn,   rmpn);
-	return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, outlen);
-}
-
 static int create_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			  struct mlx5_srq_attr *in)
 {
@@ -373,15 +355,24 @@ static int destroy_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
 static int arm_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 		       u16 lwm)
 {
-	void *in;
+	void *out = NULL;
+	void *in = NULL;
 	void *rmpc;
 	void *wq;
 	void *bitmask;
+	int outlen;
+	int inlen;
 	int err;
 
-	in = kvzalloc(MLX5_ST_SZ_BYTES(modify_rmp_in), GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
+	inlen = MLX5_ST_SZ_BYTES(modify_rmp_in);
+	outlen = MLX5_ST_SZ_BYTES(modify_rmp_out);
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!in || !out) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	rmpc =	  MLX5_ADDR_OF(modify_rmp_in,   in,   ctx);
 	bitmask = MLX5_ADDR_OF(modify_rmp_in,   in,   bitmask);
@@ -393,25 +384,39 @@ static int arm_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 	MLX5_SET(wq,		wq,	 lwm,	    lwm);
 	MLX5_SET(rmp_bitmask,	bitmask, lwm,	    1);
 	MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
+	MLX5_SET(modify_rmp_in, in, opcode, MLX5_CMD_OP_MODIFY_RMP);
 
-	err = mlx5_core_modify_rmp(dev, in, MLX5_ST_SZ_BYTES(modify_rmp_in));
+	err = mlx5_cmd_exec(dev->mdev, in, inlen, out, outlen);
 
+out:
 	kvfree(in);
+	kvfree(out);
 	return err;
 }
 
 static int query_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			 struct mlx5_srq_attr *out)
 {
-	u32 *rmp_out;
+	u32 *rmp_out = NULL;
+	u32 *rmp_in = NULL;
 	void *rmpc;
+	int outlen;
+	int inlen;
 	int err;
 
-	rmp_out =  kvzalloc(MLX5_ST_SZ_BYTES(query_rmp_out), GFP_KERNEL);
-	if (!rmp_out)
-		return -ENOMEM;
+	outlen = MLX5_ST_SZ_BYTES(query_rmp_out);
+	inlen = MLX5_ST_SZ_BYTES(query_rmp_in);
+
+	rmp_out = kvzalloc(outlen, GFP_KERNEL);
+	rmp_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!rmp_out || !rmp_in) {
+		err = -ENOMEM;
+		goto out;
+	}
 
-	err = mlx5_core_query_rmp(dev, srq->srqn, rmp_out);
+	MLX5_SET(query_rmp_in, rmp_in, opcode, MLX5_CMD_OP_QUERY_RMP);
+	MLX5_SET(query_rmp_in, rmp_in, rmpn,   srq->srqn);
+	err = mlx5_cmd_exec(dev->mdev, rmp_in, inlen, rmp_out, outlen);
 	if (err)
 		goto out;
 
@@ -422,6 +427,7 @@ static int query_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 
 out:
 	kvfree(rmp_out);
+	kvfree(rmp_in);
 	return err;
 }
 
-- 
cgit v1.2.3


From 9d43faac02e3a4a26171f96f4de69fa650d3b6f6 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Mon, 26 Nov 2018 08:28:32 +0200
Subject: net/mlx5: Update mlx5_ifc with DEVX UCTX capabilities bits

Expose device capabilities for DEVX user context, it includes which caps
the device is supported and a matching bit to set as part of user
context creation.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6f64e814cc10..ece1b606c909 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -883,6 +883,10 @@ enum {
 	MLX5_CAP_UMR_FENCE_NONE		= 0x2,
 };
 
+enum {
+	MLX5_UCTX_CAP_RAW_TX = 1UL << 0,
+};
+
 struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_0[0x30];
 	u8         vhca_id[0x10];
@@ -1193,7 +1197,13 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   num_vhca_ports[0x8];
 	u8	   reserved_at_618[0x6];
 	u8	   sw_owner_id[0x1];
-	u8	   reserved_at_61f[0x1e1];
+	u8         reserved_at_61f[0x1];
+
+	u8         reserved_at_620[0x80];
+
+	u8         uctx_cap[0x20];
+
+	u8	   reserved_at_6c0[0x140];
 };
 
 enum mlx5_flow_destination_type {
@@ -9276,7 +9286,9 @@ struct mlx5_ifc_umem_bits {
 struct mlx5_ifc_uctx_bits {
 	u8         modify_field_select[0x40];
 
-	u8         reserved_at_40[0x1c0];
+	u8         cap[0x20];
+
+	u8         reserved_at_60[0x1a0];
 };
 
 struct mlx5_ifc_create_umem_in_bits {
-- 
cgit v1.2.3


From b5a36b1e1b138285ea0df34bf96c759e1e30fafd Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 3 Dec 2018 11:31:23 +0000
Subject: bpf: respect size hint to BPF_PROG_TEST_RUN if present

Use data_size_out as a size hint when copying test output to user space.
ENOSPC is returned if the output buffer is too small.
Callers which so far did not set data_size_out are not affected.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h |  7 +++++--
 net/bpf/test_run.c       | 15 +++++++++++++--
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 572eb2d42768..c8e1eeee2c5f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -374,8 +374,11 @@ union bpf_attr {
 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
 		__u32		prog_fd;
 		__u32		retval;
-		__u32		data_size_in;
-		__u32		data_size_out;
+		__u32		data_size_in;	/* input: len of data_in */
+		__u32		data_size_out;	/* input/output: len of data_out
+						 *   returns ENOSPC if data_out
+						 *   is too small.
+						 */
 		__aligned_u64	data_in;
 		__aligned_u64	data_out;
 		__u32		repeat;
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index c89c22c49015..7663e6a57280 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -74,8 +74,18 @@ static int bpf_test_finish(const union bpf_attr *kattr,
 {
 	void __user *data_out = u64_to_user_ptr(kattr->test.data_out);
 	int err = -EFAULT;
+	u32 copy_size = size;
+
+	/* Clamp copy if the user has provided a size hint, but copy the full
+	 * buffer if not to retain old behaviour.
+	 */
+	if (kattr->test.data_size_out &&
+	    copy_size > kattr->test.data_size_out) {
+		copy_size = kattr->test.data_size_out;
+		err = -ENOSPC;
+	}
 
-	if (data_out && copy_to_user(data_out, data, size))
+	if (data_out && copy_to_user(data_out, data, copy_size))
 		goto out;
 	if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size)))
 		goto out;
@@ -83,7 +93,8 @@ static int bpf_test_finish(const union bpf_attr *kattr,
 		goto out;
 	if (copy_to_user(&uattr->test.duration, &duration, sizeof(duration)))
 		goto out;
-	err = 0;
+	if (err != -ENOSPC)
+		err = 0;
 out:
 	return err;
 }
-- 
cgit v1.2.3


From 2587a974f184ff1cd8103de25b6354a3a4da7132 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 3 Dec 2018 11:31:24 +0000
Subject: tools: sync uapi/linux/bpf.h

Pull changes from "bpf: respect size hint to BPF_PROG_TEST_RUN if present".

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0183b8e70a9e..64262890feb2 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -374,8 +374,11 @@ union bpf_attr {
 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
 		__u32		prog_fd;
 		__u32		retval;
-		__u32		data_size_in;
-		__u32		data_size_out;
+		__u32		data_size_in;	/* input: len of data_in */
+		__u32		data_size_out;	/* input/output: len of data_out
+						 *   returns ENOSPC if data_out
+						 *   is too small.
+						 */
 		__aligned_u64	data_in;
 		__aligned_u64	data_out;
 		__u32		repeat;
-- 
cgit v1.2.3


From 64a975913b311e5192a76cd10721d4565c9addd1 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 3 Dec 2018 11:31:25 +0000
Subject: libbpf: add bpf_prog_test_run_xattr

Add a new function, which encourages safe usage of the test interface.
bpf_prog_test_run continues to work as before, but should be considered
unsafe.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c      | 23 +++++++++++++++++++++++
 tools/lib/bpf/bpf.h      | 19 +++++++++++++++++++
 tools/lib/bpf/libbpf.map |  1 +
 3 files changed, 43 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index c19226cccf39..5c3be06bf0dd 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -463,6 +463,29 @@ int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 	return ret;
 }
 
+int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
+{
+	union bpf_attr attr;
+	int ret;
+
+	if (!test_attr->data_out && test_attr->data_size_out > 0)
+		return -EINVAL;
+
+	bzero(&attr, sizeof(attr));
+	attr.test.prog_fd = test_attr->prog_fd;
+	attr.test.data_in = ptr_to_u64(test_attr->data_in);
+	attr.test.data_out = ptr_to_u64(test_attr->data_out);
+	attr.test.data_size_in = test_attr->data_size_in;
+	attr.test.data_size_out = test_attr->data_size_out;
+	attr.test.repeat = test_attr->repeat;
+
+	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+	test_attr->data_size_out = attr.test.data_size_out;
+	test_attr->retval = attr.test.retval;
+	test_attr->duration = attr.test.duration;
+	return ret;
+}
+
 int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
 {
 	union bpf_attr attr;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 60392b70587c..098e6f793b76 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -118,6 +118,25 @@ LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
 LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
 				enum bpf_attach_type type);
+
+struct bpf_prog_test_run_attr {
+	int prog_fd;
+	int repeat;
+	const void *data_in;
+	__u32 data_size_in;
+	void *data_out;      /* optional */
+	__u32 data_size_out; /* in: max length of data_out
+			      * out: length of data_out */
+	__u32 retval;        /* out: return code of the BPF program */
+	__u32 duration;      /* out: average per repetition in ns */
+};
+
+LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr);
+
+/*
+ * bpf_prog_test_run does not check that data_out is large enough. Consider
+ * using bpf_prog_test_run_xattr instead.
+ */
 LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data,
 				 __u32 size, void *data_out, __u32 *size_out,
 				 __u32 *retval, __u32 *duration);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 4fb29f6d7a80..8deff22d61bb 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -65,6 +65,7 @@ LIBBPF_0.0.1 {
 		bpf_prog_load_xattr;
 		bpf_prog_query;
 		bpf_prog_test_run;
+		bpf_prog_test_run_xattr;
 		bpf_program__fd;
 		bpf_program__is_kprobe;
 		bpf_program__is_perf_event;
-- 
cgit v1.2.3


From df47fc376df8338fdc9b27a5c9162a08f6e6157c Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 3 Dec 2018 11:31:26 +0000
Subject: selftests: add a test for bpf_prog_test_run_xattr

Make sure that bpf_prog_test_run_xattr returns the correct length
and that the kernel respects the output size hint. Also check
that errno indicates ENOSPC if there is a short output buffer given.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_progs.c | 55 +++++++++++++++++++++++++++++++-
 1 file changed, 54 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 1c57abbe0945..26f1fdf3e2bf 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -70,7 +70,7 @@ static struct {
 	.tcp.urg_ptr = 123,
 };
 
-#define CHECK(condition, tag, format...) ({				\
+#define _CHECK(condition, tag, duration, format...) ({			\
 	int __ret = !!(condition);					\
 	if (__ret) {							\
 		error_cnt++;						\
@@ -83,6 +83,11 @@ static struct {
 	__ret;								\
 })
 
+#define CHECK(condition, tag, format...) \
+	_CHECK(condition, tag, duration, format)
+#define CHECK_ATTR(condition, tag, format...) \
+	_CHECK(condition, tag, tattr.duration, format)
+
 static int bpf_find_map(const char *test, struct bpf_object *obj,
 			const char *name)
 {
@@ -124,6 +129,53 @@ static void test_pkt_access(void)
 	bpf_object__close(obj);
 }
 
+static void test_prog_run_xattr(void)
+{
+	const char *file = "./test_pkt_access.o";
+	struct bpf_object *obj;
+	char buf[10];
+	int err;
+	struct bpf_prog_test_run_attr tattr = {
+		.repeat = 1,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.data_out = buf,
+		.data_size_out = 5,
+	};
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj,
+			    &tattr.prog_fd);
+	if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno))
+		return;
+
+	memset(buf, 0, sizeof(buf));
+
+	err = bpf_prog_test_run_xattr(&tattr);
+	CHECK_ATTR(err != -1 || errno != ENOSPC || tattr.retval, "run",
+	      "err %d errno %d retval %d\n", err, errno, tattr.retval);
+
+	CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out",
+	      "incorrect output size, want %lu have %u\n",
+	      sizeof(pkt_v4), tattr.data_size_out);
+
+	CHECK_ATTR(buf[5] != 0, "overflow",
+	      "BPF_PROG_TEST_RUN ignored size hint\n");
+
+	tattr.data_out = NULL;
+	tattr.data_size_out = 0;
+	errno = 0;
+
+	err = bpf_prog_test_run_xattr(&tattr);
+	CHECK_ATTR(err || errno || tattr.retval, "run_no_output",
+	      "err %d errno %d retval %d\n", err, errno, tattr.retval);
+
+	tattr.data_size_out = 1;
+	err = bpf_prog_test_run_xattr(&tattr);
+	CHECK_ATTR(err != -EINVAL, "run_wrong_size_out", "err %d\n", err);
+
+	bpf_object__close(obj);
+}
+
 static void test_xdp(void)
 {
 	struct vip key4 = {.protocol = 6, .family = AF_INET};
@@ -1837,6 +1889,7 @@ int main(void)
 	jit_enabled = is_jit_enabled();
 
 	test_pkt_access();
+	test_prog_run_xattr();
 	test_xdp();
 	test_xdp_adjust_tail();
 	test_l4lb_all();
-- 
cgit v1.2.3


From 875e8939953483d856de226b72d14c6a000f9457 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 4 Dec 2018 08:15:10 +0000
Subject: skbuff: Rename 'offload_mr_fwd_mark' to 'offload_l3_fwd_mark'

Commit abf4bb6b63d0 ("skbuff: Add the offload_mr_fwd_mark field") added
the 'offload_mr_fwd_mark' field to indicate that a packet has already
undergone L3 multicast routing by a capable device. The field is used to
prevent the kernel from forwarding a packet through a netdev through
which the device has already forwarded the packet.

Currently, no unicast packet is routed by both the device and the
kernel, but this is about to change by subsequent patches and we need to
be able to mark such packets, so that they will no be forwarded twice.

Instead of adding yet another field to 'struct sk_buff', we can just
rename 'offload_mr_fwd_mark' to 'offload_l3_fwd_mark', as a packet
either has a multicast or a unicast destination IP.

While at it, add a comment about both 'offload_fwd_mark' and
'offload_l3_fwd_mark'.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 10 +++++-----
 include/linux/skbuff.h                         |  4 +++-
 net/core/skbuff.c                              |  2 +-
 net/ipv4/ipmr.c                                |  2 +-
 4 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index c293ff1eed63..920085fbbf2a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3554,10 +3554,10 @@ static void mlxsw_sp_rx_listener_mark_func(struct sk_buff *skb, u8 local_port,
 	return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv);
 }
 
-static void mlxsw_sp_rx_listener_mr_mark_func(struct sk_buff *skb,
+static void mlxsw_sp_rx_listener_l3_mark_func(struct sk_buff *skb,
 					      u8 local_port, void *priv)
 {
-	skb->offload_mr_fwd_mark = 1;
+	skb->offload_l3_fwd_mark = 1;
 	skb->offload_fwd_mark = 1;
 	return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv);
 }
@@ -3605,8 +3605,8 @@ out:
 	MLXSW_RXL(mlxsw_sp_rx_listener_mark_func, _trap_id, _action,	\
 		_is_ctrl, SP_##_trap_group, DISCARD)
 
-#define MLXSW_SP_RXL_MR_MARK(_trap_id, _action, _trap_group, _is_ctrl)	\
-	MLXSW_RXL(mlxsw_sp_rx_listener_mr_mark_func, _trap_id, _action,	\
+#define MLXSW_SP_RXL_L3_MARK(_trap_id, _action, _trap_group, _is_ctrl)	\
+	MLXSW_RXL(mlxsw_sp_rx_listener_l3_mark_func, _trap_id, _action,	\
 		_is_ctrl, SP_##_trap_group, DISCARD)
 
 #define MLXSW_SP_EVENTL(_func, _trap_id)		\
@@ -3683,7 +3683,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(IPV6_PIM, TRAP_TO_CPU, PIM, false),
 	MLXSW_SP_RXL_MARK(RPF, TRAP_TO_CPU, RPF, false),
 	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
-	MLXSW_SP_RXL_MR_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
+	MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
 	/* NVE traps */
 	MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, ARP, false),
 };
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 75d50ab7997c..b1831a5ca173 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -616,6 +616,8 @@ typedef unsigned char *sk_buff_data_t;
  *	@pkt_type: Packet class
  *	@fclone: skbuff clone status
  *	@ipvs_property: skbuff is owned by ipvs
+ *	@offload_fwd_mark: Packet was L2-forwarded in hardware
+ *	@offload_l3_fwd_mark: Packet was L3-forwarded in hardware
  *	@tc_skip_classify: do not classify packet. set by IFB device
  *	@tc_at_ingress: used within tc_classify to distinguish in/egress
  *	@tc_redirected: packet was redirected by a tc action
@@ -799,7 +801,7 @@ struct sk_buff {
 	__u8			remcsum_offload:1;
 #ifdef CONFIG_NET_SWITCHDEV
 	__u8			offload_fwd_mark:1;
-	__u8			offload_mr_fwd_mark:1;
+	__u8			offload_l3_fwd_mark:1;
 #endif
 #ifdef CONFIG_NET_CLS_ACT
 	__u8			tc_skip_classify:1;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c78ce114537e..40552547c69a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4885,7 +4885,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 
 #ifdef CONFIG_NET_SWITCHDEV
 	skb->offload_fwd_mark = 0;
-	skb->offload_mr_fwd_mark = 0;
+	skb->offload_l3_fwd_mark = 0;
 #endif
 
 	if (!xnet)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index a6defbec4f1b..5cbc749a50aa 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1802,7 +1802,7 @@ static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt,
 	struct vif_device *out_vif = &mrt->vif_table[out_vifi];
 	struct vif_device *in_vif = &mrt->vif_table[in_vifi];
 
-	if (!skb->offload_mr_fwd_mark)
+	if (!skb->offload_l3_fwd_mark)
 		return false;
 	if (!out_vif->dev_parent_id.id_len || !in_vif->dev_parent_id.id_len)
 		return false;
-- 
cgit v1.2.3


From f839a6c92504cff92a10f522cf686b51ff18dd35 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 4 Dec 2018 08:15:11 +0000
Subject: net: Do not route unicast IP packets twice

Packets marked with 'offload_l3_fwd_mark' were already forwarded by a
capable device and should not be forwarded again by the kernel.
Therefore, have the kernel consume them.

The check is performed in ip{,6}_forward_finish() in order to allow the
kernel to process such packets in ip{,6}_forward() and generate required
exceptions. For example, ICMP redirects.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_forward.c | 7 +++++++
 net/ipv6/ip6_output.c | 7 +++++++
 2 files changed, 14 insertions(+)

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 32662e9e5d21..06ee4696703c 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -69,6 +69,13 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s
 	__IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS);
 	__IP_ADD_STATS(net, IPSTATS_MIB_OUTOCTETS, skb->len);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	if (skb->offload_l3_fwd_mark) {
+		consume_skb(skb);
+		return 0;
+	}
+#endif
+
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ec8c235ea891..6592a39e5ec1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -378,6 +378,13 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk,
 	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
 	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	if (skb->offload_l3_fwd_mark) {
+		consume_skb(skb);
+		return 0;
+	}
+#endif
+
 	return dst_output(net, sk, skb);
 }
 
-- 
cgit v1.2.3


From 2f4f44946b748918de6345dd12d0c418c0206002 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 4 Dec 2018 08:15:12 +0000
Subject: mlxsw: spectrum: Mirror loopbacked packets instead of trapping them

When the ASIC detects that a unicast packet is routed through the same
router interface (RIF) from which it ingressed (iRIF == eRIF), it raises
a trap called loopback error (LBERROR).

Thus far, this trap was configured to send a sole copy of the packet to
the CPU so that ICMP redirect packets could be potentially generated by
the kernel.

This is problematic as the CPU cannot forward packets at 3.2Tb/s and
there are scenarios (e.g., "one-armed router") where iRIF == eRIF is not
an exception.

Solve this by changing the trap to send a copy of the packet to the CPU.
To prevent the kernel from forwarding the packet again, it is marked
with 'offload_l3_fwd_mark'.

The trap is configured in a trap group of its own with a dedicated
policer in order not to prevent packets trapped by other traps from
reaching the CPU.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 5c8a38f61a93..b9c37b0bb175 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5072,6 +5072,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR,
 };
 
 /* reg_htgt_trap_group
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 920085fbbf2a..0f37b203103a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3639,7 +3639,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	/* L3 traps */
 	MLXSW_SP_RXL_MARK(MTUERROR, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(TTLERROR, TRAP_TO_CPU, ROUTER_EXP, false),
-	MLXSW_SP_RXL_MARK(LBERROR, TRAP_TO_CPU, ROUTER_EXP, false),
+	MLXSW_SP_RXL_L3_MARK(LBERROR, MIRROR_TO_CPU, LBERROR, false),
 	MLXSW_SP_RXL_MARK(IP2ME, TRAP_TO_CPU, IP2ME, false),
 	MLXSW_SP_RXL_MARK(IPV6_UNSPECIFIED_ADDRESS, TRAP_TO_CPU, ROUTER_EXP,
 			  false),
@@ -3713,6 +3713,7 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_RPF:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:
 			rate = 128;
 			burst_size = 7;
 			break;
@@ -3798,6 +3799,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:
 			priority = 1;
 			tc = 1;
 			break;
-- 
cgit v1.2.3


From b6f153d3e5a5bfbda17b997bd9e258143aa11809 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 4 Dec 2018 08:15:14 +0000
Subject: selftests: mlxsw: Add one-armed router test

Construct a "one-armed router" topology and test that packets are
forwarded by the ASIC and that a copy of the packet is sent to the
kernel, which does not forward the packet again.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/one_armed_router.sh          | 259 +++++++++++++++++++++
 1 file changed, 259 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh b/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh
new file mode 100755
index 000000000000..f02d83e94576
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh
@@ -0,0 +1,259 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test a "one-armed router" [1] scenario. Packets forwarded between H1 and H2
+# should be forwarded by the ASIC, but also trapped so that ICMP redirect
+# packets could be potentially generated.
+#
+# 1. https://en.wikipedia.org/wiki/One-armed_router
+#
+# +---------------------------------+
+# | H1 (vrf)                        |
+# |    + $h1                        |
+# |    | 192.0.2.1/24               |
+# |    | 2001:db8:1::1/64           |
+# |    |                            |
+# |    |  default via 192.0.2.2     |
+# |    |  default via 2001:db8:1::2 |
+# +----|----------------------------+
+#      |
+# +----|----------------------------------------------------------------------+
+# | SW |                                                                      |
+# | +--|--------------------------------------------------------------------+ |
+# | |  + $swp1                   BR0 (802.1d)                               | |
+# | |                                                                       | |
+# | |                            192.0.2.2/24                               | |
+# | |                          2001:db8:1::2/64                             | |
+# | |                           198.51.100.2/24                             | |
+# | |                          2001:db8:2::2/64                             | |
+# | |                                                                       | |
+# | |  + $swp2                                                              | |
+# | +--|--------------------------------------------------------------------+ |
+# |    |                                                                      |
+# +----|----------------------------------------------------------------------+
+#      |
+# +----|----------------------------+
+# |    |  default via 198.51.100.2  |
+# |    |  default via 2001:db8:2::2 |
+# |    |                            |
+# |    | 2001:db8:2::1/64           |
+# |    | 198.51.100.1/24            |
+# |    + $h2                        |
+# | H2 (vrf)                        |
+# +---------------------------------+
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="ping_ipv4 ping_ipv6 fwd_mark_ipv4 fwd_mark_ipv6"
+NUM_NETIFS=4
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64
+
+	ip -4 route add default vrf v$h1 nexthop via 192.0.2.2
+	ip -6 route add default vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip -6 route del default vrf v$h1 nexthop via 2001:db8:1::2
+	ip -4 route del default vrf v$h1 nexthop via 192.0.2.2
+
+	simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 198.51.100.1/24 2001:db8:2::1/64
+
+	ip -4 route add default vrf v$h2 nexthop via 198.51.100.2
+	ip -6 route add default vrf v$h2 nexthop via 2001:db8:2::2
+}
+
+h2_destroy()
+{
+	ip -6 route del default vrf v$h2 nexthop via 2001:db8:2::2
+	ip -4 route del default vrf v$h2 nexthop via 198.51.100.2
+
+	simple_if_fini $h2 198.51.100.1/24 2001:db8:2::1/64
+}
+
+switch_create()
+{
+	ip link add name br0 type bridge mcast_snooping 0
+	ip link set dev br0 up
+
+	ip link set dev $swp1 master br0
+	ip link set dev $swp1 up
+	ip link set dev $swp2 master br0
+	ip link set dev $swp2 up
+
+	tc qdisc add dev $swp1 clsact
+	tc qdisc add dev $swp2 clsact
+
+	__addr_add_del br0 add 192.0.2.2/24 2001:db8:1::2/64
+	__addr_add_del br0 add 198.51.100.2/24 2001:db8:2::2/64
+}
+
+switch_destroy()
+{
+	__addr_add_del br0 del 198.51.100.2/24 2001:db8:2::2/64
+	__addr_add_del br0 del 192.0.2.2/24 2001:db8:1::2/64
+
+	tc qdisc del dev $swp2 clsact
+	tc qdisc del dev $swp1 clsact
+
+	ip link set dev $swp2 down
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 down
+	ip link set dev $swp1 nomaster
+
+	ip link set dev br0 down
+	ip link del dev br0
+}
+
+ping_ipv4()
+{
+	ping_test $h1 198.51.100.1 ": h1->h2"
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::1 ": h1->h2"
+}
+
+fwd_mark_ipv4()
+{
+	# Transmit packets from H1 to H2 and make sure they are trapped at
+	# swp1 due to loopback error, but only forwarded by the ASIC through
+	# swp2
+
+	tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \
+		skip_hw dst_ip 198.51.100.1 ip_proto udp dst_port 52768 \
+		action pass
+
+	tc filter add dev $swp2 egress protocol ip pref 1 handle 101 flower \
+		skip_hw dst_ip 198.51.100.1 ip_proto udp dst_port 52768 \
+		action pass
+
+	tc filter add dev $swp2 egress protocol ip pref 2 handle 102 flower \
+		skip_sw dst_ip 198.51.100.1 ip_proto udp dst_port 52768 \
+		action pass
+
+	ip vrf exec v$h1 $MZ $h1 -c 10 -d 100msec -p 64 -A 192.0.2.1 \
+		-B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+	RET=0
+
+	tc_check_packets "dev $swp1 ingress" 101 10
+	check_err $?
+
+	log_test "fwd mark: trapping IPv4 packets due to LBERROR"
+
+	RET=0
+
+	tc_check_packets "dev $swp2 egress" 101 0
+	check_err $?
+
+	log_test "fwd mark: forwarding IPv4 packets in software"
+
+	RET=0
+
+	tc_check_packets "dev $swp2 egress" 102 10
+	check_err $?
+
+	log_test "fwd mark: forwarding IPv4 packets in hardware"
+
+	tc filter del dev $swp2 egress protocol ip pref 2 handle 102 flower
+	tc filter del dev $swp2 egress protocol ip pref 1 handle 101 flower
+	tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
+}
+
+fwd_mark_ipv6()
+{
+	tc filter add dev $swp1 ingress protocol ipv6 pref 1 handle 101 flower \
+		skip_hw dst_ip 2001:db8:2::1 ip_proto udp dst_port 52768 \
+		action pass
+
+	tc filter add dev $swp2 egress protocol ipv6 pref 1 handle 101 flower \
+		skip_hw dst_ip 2001:db8:2::1 ip_proto udp dst_port 52768 \
+		action pass
+
+	tc filter add dev $swp2 egress protocol ipv6 pref 2 handle 102 flower \
+		skip_sw dst_ip 2001:db8:2::1 ip_proto udp dst_port 52768 \
+		action pass
+
+	ip vrf exec v$h1 $MZ $h1 -6 -c 10 -d 100msec -p 64 -A 2001:db8:1::1 \
+		-B 2001:db8:2::1 -t udp dp=52768,sp=42768 -q
+
+	RET=0
+
+	tc_check_packets "dev $swp1 ingress" 101 10
+	check_err $?
+
+	log_test "fwd mark: trapping IPv6 packets due to LBERROR"
+
+	RET=0
+
+	tc_check_packets "dev $swp2 egress" 101 0
+	check_err $?
+
+	log_test "fwd mark: forwarding IPv6 packets in software"
+
+	RET=0
+
+	tc_check_packets "dev $swp2 egress" 102 10
+	check_err $?
+
+	log_test "fwd mark: forwarding IPv6 packets in hardware"
+
+	tc filter del dev $swp2 egress protocol ipv6 pref 2 handle 102 flower
+	tc filter del dev $swp2 egress protocol ipv6 pref 1 handle 101 flower
+	tc filter del dev $swp1 ingress protocol ipv6 pref 1 handle 101 flower
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+	forwarding_enable
+
+	sysctl_set net.ipv4.conf.all.accept_redirects 0
+	sysctl_set net.ipv6.conf.all.accept_redirects 0
+
+	h1_create
+	h2_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h2_destroy
+	h1_destroy
+
+	sysctl_restore net.ipv6.conf.all.accept_redirects
+	sysctl_restore net.ipv4.conf.all.accept_redirects
+
+	forwarding_restore
+	vrf_cleanup
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 8742c7eb3d134cced700f4ec6d7fc0c663de1e28 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 5 Nov 2018 11:26:32 -0800
Subject: net/mlx5e: Remove trailing space of tx_pause ethtool counter name

tx_pause_storm_warning_events ethtool counter name has a trailing
space, remove it.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 3e99d0728b2f..40b60e958cfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -936,7 +936,7 @@ static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
 };
 
 static const struct counter_desc pport_pfc_stall_stats_desc[] = {
-	{ "tx_pause_storm_warning_events ", PPORT_PER_PRIO_OFF(device_stall_minor_watermark_cnt) },
+	{ "tx_pause_storm_warning_events", PPORT_PER_PRIO_OFF(device_stall_minor_watermark_cnt) },
 	{ "tx_pause_storm_error_events", PPORT_PER_PRIO_OFF(device_stall_critical_watermark_cnt) },
 };
 
-- 
cgit v1.2.3


From 305438310938e9163f9366aa261336f93d2622f6 Mon Sep 17 00:00:00 2001
From: Gal Pressman <pressmangal@gmail.com>
Date: Wed, 7 Nov 2018 20:31:36 +0200
Subject: net/mlx5e: Cleanup unused defines

Remove couple of defines that are no longer used.

Signed-off-by: Gal Pressman <pressmangal@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 118324802926..2af43465ba2c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -147,9 +147,6 @@ struct page_pool;
 	       MLX5_UMR_MTT_ALIGNMENT))
 #define MLX5E_UMR_WQEBBS \
 	(DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_BB))
-#define MLX5E_ICOSQ_MAX_WQEBBS MLX5E_UMR_WQEBBS
-
-#define MLX5E_NUM_MAIN_GROUPS 9
 
 #define MLX5E_MSG_LEVEL			NETIF_MSG_LINK
 
-- 
cgit v1.2.3


From 080d1b17fbc51789287cd8b2044a8cc9ec600e81 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Tue, 23 Oct 2018 10:02:08 +0300
Subject: net/mlx5e: Move modify tirs hash functionality

Move modify tirs hash functionality (mlx5e_modify_tirs_hash) from
en_ethtool.c to en_main.c. This allows future use of this fuctionality
from en_fs_ethtool.c, while keeping current convention: en_ethtool.c
doesn't have an API.  There is no functional change here.

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  1 +
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   | 25 -------------------
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 28 ++++++++++++++++++++++
 3 files changed, 29 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 2af43465ba2c..86d60222b3cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -799,6 +799,7 @@ int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
 void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
 				    enum mlx5e_traffic_types tt,
 				    void *tirc, bool inner);
+void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 25c1c4f96841..2d5b00751a6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -972,31 +972,6 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	return 0;
 }
 
-static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
-{
-	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
-	struct mlx5_core_dev *mdev = priv->mdev;
-	int ctxlen = MLX5_ST_SZ_BYTES(tirc);
-	int tt;
-
-	MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
-
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, false);
-		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
-	}
-
-	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
-		return;
-
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, true);
-		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in, inlen);
-	}
-}
-
 static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 			  const u8 *key, const u8 hfunc)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 871313d6b34d..85a4633454d0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2735,6 +2735,34 @@ void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
 	}
 }
 
+void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
+{
+	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int ctxlen = MLX5_ST_SZ_BYTES(tirc);
+	int tt;
+
+	MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
+
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		memset(tirc, 0, ctxlen);
+		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc,
+					       false);
+		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
+	}
+
+	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+		return;
+
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		memset(tirc, 0, ctxlen);
+		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc,
+					       true);
+		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in,
+				     inlen);
+	}
+}
+
 static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-- 
cgit v1.2.3


From d1ecf8a660fafd023f2e5792107381de6fb34357 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 3 Dec 2018 17:13:31 +0000
Subject: qed: fix spelling mistake "Dispalying" -> "Displaying"

There is a spelling mistake in a DP_NOTICE message, fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index a817b6632eb2..8f6551421945 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -285,7 +285,7 @@ void qed_db_recovery_dp(struct qed_hwfn *p_hwfn)
 	struct qed_db_recovery_entry *db_entry = NULL;
 
 	DP_NOTICE(p_hwfn,
-		  "Dispalying doorbell recovery database. Counter was %d\n",
+		  "Displaying doorbell recovery database. Counter was %d\n",
 		  p_hwfn->db_recovery_info.db_recovery_counter);
 
 	/* Protect the list */
-- 
cgit v1.2.3


From 80ef0f22ceda1804cc572836722df7a33dec71c9 Mon Sep 17 00:00:00 2001
From: Adi Nissim <adin@mellanox.com>
Date: Sun, 2 Dec 2018 14:55:20 +0200
Subject: net/sched: act_tunnel_key: Allow key-less tunnels

Allow setting a tunnel without a tunnel key. This is required for
tunneling protocols, such as GRE, that define the key as an optional
field.

Signed-off-by: Adi Nissim <adin@mellanox.com>
Acked-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 4cca8f274662..fad438c0f7a7 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -210,9 +210,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	struct tcf_tunnel_key *t;
 	bool exists = false;
 	__be16 dst_port = 0;
+	__be64 key_id = 0;
 	int opts_len = 0;
-	__be64 key_id;
-	__be16 flags;
+	__be16 flags = 0;
 	u8 tos, ttl;
 	int ret = 0;
 	int err;
@@ -246,15 +246,15 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	case TCA_TUNNEL_KEY_ACT_RELEASE:
 		break;
 	case TCA_TUNNEL_KEY_ACT_SET:
-		if (!tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) {
-			NL_SET_ERR_MSG(extack, "Missing tunnel key id");
-			ret = -EINVAL;
-			goto err_out;
-		}
+		if (tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) {
+			__be32 key32;
 
-		key_id = key32_to_tunnel_id(nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]));
+			key32 = nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]);
+			key_id = key32_to_tunnel_id(key32);
+			flags = TUNNEL_KEY;
+		}
 
-		flags = TUNNEL_KEY | TUNNEL_CSUM;
+		flags |= TUNNEL_CSUM;
 		if (tb[TCA_TUNNEL_KEY_NO_CSUM] &&
 		    nla_get_u8(tb[TCA_TUNNEL_KEY_NO_CSUM]))
 			flags &= ~TUNNEL_CSUM;
@@ -508,7 +508,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
 		struct ip_tunnel_key *key = &info->key;
 		__be32 key_id = tunnel_id_to_key32(key->tun_id);
 
-		if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) ||
+		if (((key->tun_flags & TUNNEL_KEY) &&
+		     nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id)) ||
 		    tunnel_key_dump_addresses(skb,
 					      &params->tcft_enc_metadata->u.tun_info) ||
 		    nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst) ||
-- 
cgit v1.2.3


From 1c25324caf8292573b2b519fa4957baefd0c9657 Mon Sep 17 00:00:00 2001
From: Adi Nissim <adin@mellanox.com>
Date: Sun, 2 Dec 2018 14:55:21 +0200
Subject: net/sched: act_tunnel_key: Don't dump dst port if it wasn't set

It's possible to set a tunnel without a destination port. However,
on dump(), a zero dst port is returned to user space even if it was not
set, fix that.

Note that so far it wasn't required, b/c key less tunnels were not
supported and the UDP tunnels do require destination port.

Signed-off-by: Adi Nissim <adin@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index fad438c0f7a7..c3b90fadaff6 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -512,7 +512,9 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
 		     nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id)) ||
 		    tunnel_key_dump_addresses(skb,
 					      &params->tcft_enc_metadata->u.tun_info) ||
-		    nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst) ||
+		    (key->tp_dst &&
+		      nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT,
+				   key->tp_dst)) ||
 		    nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM,
 			       !(key->tun_flags & TUNNEL_CSUM)) ||
 		    tunnel_key_opts_dump(skb, info))
-- 
cgit v1.2.3


From a74f0fa082b76c6a76cba5672f36218518bfdc09 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 4 Dec 2018 07:58:17 -0800
Subject: tcp: reduce POLLOUT events caused by TCP_NOTSENT_LOWAT

TCP_NOTSENT_LOWAT socket option or sysctl was added in linux-3.12
as a step to enable bigger tcp sndbuf limits.

It works reasonably well, but the following happens :

Once the limit is reached, TCP stack generates
an [E]POLLOUT event for every incoming ACK packet.

This causes a high number of context switches.

This patch implements the strategy David Miller added
in sock_def_write_space() :

 - If TCP socket has a notsent_lowat constraint of X bytes,
   allow sendmsg() to fill up to X bytes, but send [E]POLLOUT
   only if number of notsent bytes is below X/2

This considerably reduces TCP_NOTSENT_LOWAT overhead,
while allowing to keep the pipe full.

Tested:
 100 ms RTT netem testbed between A and B, 100 concurrent TCP_STREAM

A:/# cat /proc/sys/net/ipv4/tcp_wmem
4096	262144	64000000
A:/# super_netperf 100 -H B -l 1000 -- -K bbr &

A:/# grep TCP /proc/net/sockstat
TCP: inuse 203 orphan 0 tw 19 alloc 414 mem 1364904 # This is about 54 MB of memory per flow :/

A:/# vmstat 5 5
procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu-----
 r  b   swpd   free   buff  cache   si   so    bi    bo   in   cs us sy id wa st
 0  0      0 256220672  13532 694976    0    0    10     0   28   14  0  1 99  0  0
 2  0      0 256320016  13532 698480    0    0   512     0 715901 5927  0 10 90  0  0
 0  0      0 256197232  13532 700992    0    0   735    13 771161 5849  0 11 89  0  0
 1  0      0 256233824  13532 703320    0    0   512    23 719650 6635  0 11 89  0  0
 2  0      0 256226880  13532 705780    0    0   642     4 775650 6009  0 12 88  0  0

A:/# echo 2097152 >/proc/sys/net/ipv4/tcp_notsent_lowat

A:/# grep TCP /proc/net/sockstat
TCP: inuse 203 orphan 0 tw 19 alloc 414 mem 86411 # 3.5 MB per flow

A:/# vmstat 5 5  # check that context switches have not inflated too much.
procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu-----
 r  b   swpd   free   buff  cache   si   so    bi    bo   in   cs us sy id wa st
 2  0      0 260386512  13592 662148    0    0    10     0   17   14  0  1 99  0  0
 0  0      0 260519680  13592 604184    0    0   512    13 726843 12424  0 10 90  0  0
 1  1      0 260435424  13592 598360    0    0   512    25 764645 12925  0 10 90  0  0
 1  0      0 260855392  13592 578380    0    0   512     7 722943 13624  0 11 88  0  0
 1  0      0 260445008  13592 601176    0    0   614    34 772288 14317  0 10 90  0  0

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 20 +++++++++++++++-----
 include/net/tcp.h  |  8 ++++++--
 net/core/stream.c  |  2 +-
 3 files changed, 22 insertions(+), 8 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index f665d74ae509..df390a3e23fe 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1110,7 +1110,7 @@ struct proto {
 	unsigned int		inuse_idx;
 #endif
 
-	bool			(*stream_memory_free)(const struct sock *sk);
+	bool			(*stream_memory_free)(const struct sock *sk, int wake);
 	bool			(*stream_memory_read)(const struct sock *sk);
 	/* Memory pressure */
 	void			(*enter_memory_pressure)(struct sock *sk);
@@ -1192,19 +1192,29 @@ static inline void sk_refcnt_debug_release(const struct sock *sk)
 #define sk_refcnt_debug_release(sk) do { } while (0)
 #endif /* SOCK_REFCNT_DEBUG */
 
-static inline bool sk_stream_memory_free(const struct sock *sk)
+static inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
 {
 	if (sk->sk_wmem_queued >= sk->sk_sndbuf)
 		return false;
 
 	return sk->sk_prot->stream_memory_free ?
-		sk->sk_prot->stream_memory_free(sk) : true;
+		sk->sk_prot->stream_memory_free(sk, wake) : true;
 }
 
-static inline bool sk_stream_is_writeable(const struct sock *sk)
+static inline bool sk_stream_memory_free(const struct sock *sk)
+{
+	return __sk_stream_memory_free(sk, 0);
+}
+
+static inline bool __sk_stream_is_writeable(const struct sock *sk, int wake)
 {
 	return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) &&
-	       sk_stream_memory_free(sk);
+	       __sk_stream_memory_free(sk, wake);
+}
+
+static inline bool sk_stream_is_writeable(const struct sock *sk)
+{
+	return __sk_stream_is_writeable(sk, 0);
 }
 
 static inline int sk_under_cgroup_hierarchy(struct sock *sk,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0681afc62354..e0a65c067662 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1870,12 +1870,16 @@ static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
 	return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat;
 }
 
-static inline bool tcp_stream_memory_free(const struct sock *sk)
+/* @wake is one when sk_stream_write_space() calls us.
+ * This sends EPOLLOUT only if notsent_bytes is half the limit.
+ * This mimics the strategy used in sock_def_write_space().
+ */
+static inline bool tcp_stream_memory_free(const struct sock *sk, int wake)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	u32 notsent_bytes = tp->write_seq - tp->snd_nxt;
 
-	return notsent_bytes < tcp_notsent_lowat(tp);
+	return (notsent_bytes << wake) < tcp_notsent_lowat(tp);
 }
 
 #ifdef CONFIG_PROC_FS
diff --git a/net/core/stream.c b/net/core/stream.c
index 7d329fb1f553..e94bb02a5629 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -32,7 +32,7 @@ void sk_stream_write_space(struct sock *sk)
 	struct socket *sock = sk->sk_socket;
 	struct socket_wq *wq;
 
-	if (sk_stream_is_writeable(sk) && sock) {
+	if (__sk_stream_is_writeable(sk, 1) && sock) {
 		clear_bit(SOCK_NOSPACE, &sock->flags);
 
 		rcu_read_lock();
-- 
cgit v1.2.3


From 082b12d4e541b260e5527aeac48b5ab2ce3a7f94 Mon Sep 17 00:00:00 2001
From: James Prestwood <james.prestwood@linux.intel.com>
Date: Tue, 13 Nov 2018 11:26:42 -0800
Subject: mac80211_hwsim: fixes kernel crash during mac80211_hwsim init

Creating radios during startup follows a different code path than
HWSIM_CMD_NEW_RADIO. The problem was that param.iftypes was not
being set to the deafult before calling mac80211_hwsim_new_radio

Signed-off-by: James Prestwood <james.prestwood@linux.intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 4033a800b209..2a5a133f23cf 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -3884,6 +3884,7 @@ static int __init init_mac80211_hwsim(void)
 
 		param.p2p_device = support_p2p_device;
 		param.use_chanctx = channels > 1;
+		param.iftypes = HWSIM_IFTYPE_SUPPORT_MASK;
 
 		err = mac80211_hwsim_new_radio(NULL, &param);
 		if (err < 0)
-- 
cgit v1.2.3


From cc1068eb6ad21a6cf54aa5f9ae25bf50fd5c9d4b Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Thu, 15 Nov 2018 15:25:04 -0800
Subject: uapi/nl80211: fix spelling errors

Spelling errors found by codespell

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 51bd85b7d839..2b53c0e949c7 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1734,7 +1734,7 @@ enum nl80211_commands {
  *	the values passed in @NL80211_ATTR_SCAN_SSIDS (eg. if an SSID
  *	is included in the probe request, but the match attributes
  *	will never let it go through), -EINVAL may be returned.
- *	If ommited, no filtering is done.
+ *	If omitted, no filtering is done.
  *
  * @NL80211_ATTR_INTERFACE_COMBINATIONS: Nested attribute listing the supported
  *	interface combinations. In each nested item, it contains attributes
@@ -1839,7 +1839,7 @@ enum nl80211_commands {
  *
  * @NL80211_ATTR_INACTIVITY_TIMEOUT: timeout value in seconds, this can be
  *	used by the drivers which has MLME in firmware and does not have support
- *	to report per station tx/rx activity to free up the staion entry from
+ *	to report per station tx/rx activity to free up the station entry from
  *	the list. This needs to be used when the driver advertises the
  *	capability to timeout the stations.
  *
@@ -2200,7 +2200,7 @@ enum nl80211_commands {
  *
  * @NL80211_ATTR_SCHED_SCAN_RSSI_ADJUST: When present the RSSI level for BSSs in
  *	the specified band is to be adjusted before doing
- *	%NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI based comparision to figure out
+ *	%NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI based comparison to figure out
  *	better BSSs. The attribute value is a packed structure
  *	value as specified by &struct nl80211_bss_select_rssi_adjust.
  *
@@ -4910,7 +4910,7 @@ enum nl80211_iface_limit_attrs {
  *	numbers = [ #{STA} <= 1, #{P2P-client,P2P-GO} <= 3 ], max = 4
  *	=> allows a STA plus three P2P interfaces
  *
- * The list of these four possiblities could completely be contained
+ * The list of these four possibilities could completely be contained
  * within the %NL80211_ATTR_INTERFACE_COMBINATIONS attribute to indicate
  * that any of these groups must match.
  *
@@ -4940,7 +4940,7 @@ enum nl80211_if_combination_attrs {
  * enum nl80211_plink_state - state of a mesh peer link finite state machine
  *
  * @NL80211_PLINK_LISTEN: initial state, considered the implicit
- *	state of non existant mesh peer links
+ *	state of non existent mesh peer links
  * @NL80211_PLINK_OPN_SNT: mesh plink open frame has been sent to
  *	this mesh peer
  * @NL80211_PLINK_OPN_RCVD: mesh plink open frame has been received
@@ -5432,7 +5432,7 @@ enum nl80211_timeout_reason {
  *	request parameters IE in the probe request
  * @NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP: accept broadcast probe responses
  * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE: send probe request frames at
- *	rate of at least 5.5M. In case non OCE AP is dicovered in the channel,
+ *	rate of at least 5.5M. In case non OCE AP is discovered in the channel,
  *	only the first probe req in the channel will be sent in high rate.
  * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: allow probe request
  *	tx deferral (dot11FILSProbeDelay shall be set to 15ms)
-- 
cgit v1.2.3


From c7cdba31ed8b87526db978976392802d3f93110c Mon Sep 17 00:00:00 2001
From: Cody Schuffelen <schuffelen@google.com>
Date: Tue, 20 Nov 2018 19:14:49 -0800
Subject: mac80211-next: rtnetlink wifi simulation device

This device takes over an existing network device and produces a
new one that appears like a wireless connection, returning enough canned
responses to nl80211 to satisfy a standard connection manager. If
necessary, it can also be set up one step removed from an existing
network device, such as through a vlan/80211Q or macvlan connection to
not disrupt the existing network interface.

To use it to wrap a bare ethernet connection:

ip link add link eth0 name wlan0 type virt_wifi

You may have to rename or otherwise hide the eth0 from your connection
manager, as the original network link will become unusuable and only
the wireless wrapper will be functional. This can also be combined with
vlan or macvlan links on top of eth0 to share the network between
distinct links, but that requires support outside the machine for
accepting vlan-tagged packets or packets from multiple MAC addresses.

This is being used for Google's Remote Android Virtual Device project,
which runs Android devices in virtual machines. The standard network
interfaces provided inside the virtual machines are all ethernet.
However, Android is not interested in ethernet devices and would rather
connect to a wireless interface. This patch allows the virtual machine
guest to treat one of its network connections as wireless rather than
ethernet, satisfying Android's network connection requirements.

We believe this is a generally useful driver for simulating wireless
network connections in other environments where a wireless connection is
desired by some userspace process but is not available.

This is distinct from other testing efforts such as mac80211_hwsim by
being a cfg80211 device instead of mac80211 device, allowing straight
pass-through on the data plane instead of forcing packaging of ethernet
data into mac80211 frames.

Signed-off-by: A. Cody Schuffelen <schuffelen@google.com>
Acked-by: Alistair Strachan <astrachan@google.com>
Acked-by: Greg Hartman <ghartman@google.com>
Acked-by: Tristan Muntsinger <muntsinger@google.com>
[make it a tristate]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/Kconfig     |   7 +
 drivers/net/wireless/Makefile    |   2 +
 drivers/net/wireless/virt_wifi.c | 632 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 641 insertions(+)
 create mode 100644 drivers/net/wireless/virt_wifi.c

diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig
index 166920ae23f8..8c456a66ac3b 100644
--- a/drivers/net/wireless/Kconfig
+++ b/drivers/net/wireless/Kconfig
@@ -114,4 +114,11 @@ config USB_NET_RNDIS_WLAN
 
 	  If you choose to build a module, it'll be called rndis_wlan.
 
+config VIRT_WIFI
+	tristate "Wifi wrapper for ethernet drivers"
+	depends on CFG80211
+	---help---
+	  This option adds support for ethernet connections to appear as if they
+	  are wifi connections through a special rtnetlink device.
+
 endif # WLAN
diff --git a/drivers/net/wireless/Makefile b/drivers/net/wireless/Makefile
index 7fc96306712a..6cfe74515c95 100644
--- a/drivers/net/wireless/Makefile
+++ b/drivers/net/wireless/Makefile
@@ -27,3 +27,5 @@ obj-$(CONFIG_PCMCIA_WL3501)	+= wl3501_cs.o
 obj-$(CONFIG_USB_NET_RNDIS_WLAN)	+= rndis_wlan.o
 
 obj-$(CONFIG_MAC80211_HWSIM)	+= mac80211_hwsim.o
+
+obj-$(CONFIG_VIRT_WIFI)	+= virt_wifi.o
diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c
new file mode 100644
index 000000000000..64b218699656
--- /dev/null
+++ b/drivers/net/wireless/virt_wifi.c
@@ -0,0 +1,632 @@
+// SPDX-License-Identifier: GPL-2.0
+/* drivers/net/wireless/virt_wifi.c
+ *
+ * A fake implementation of cfg80211_ops that can be tacked on to an ethernet
+ * net_device to make it appear as a wireless connection.
+ *
+ * Copyright (C) 2018 Google, Inc.
+ *
+ * Author: schuffelen@google.com
+ */
+
+#include <net/cfg80211.h>
+#include <net/rtnetlink.h>
+#include <linux/etherdevice.h>
+#include <linux/module.h>
+
+#include <net/cfg80211.h>
+#include <net/rtnetlink.h>
+#include <linux/etherdevice.h>
+#include <linux/module.h>
+
+static struct wiphy *common_wiphy;
+
+struct virt_wifi_wiphy_priv {
+	struct delayed_work scan_result;
+	struct cfg80211_scan_request *scan_request;
+	bool being_deleted;
+};
+
+static struct ieee80211_channel channel_2ghz = {
+	.band = NL80211_BAND_2GHZ,
+	.center_freq = 2432,
+	.hw_value = 2432,
+	.max_power = 20,
+};
+
+static struct ieee80211_rate bitrates_2ghz[] = {
+	{ .bitrate = 10 },
+	{ .bitrate = 20 },
+	{ .bitrate = 55 },
+	{ .bitrate = 110 },
+	{ .bitrate = 60 },
+	{ .bitrate = 120 },
+	{ .bitrate = 240 },
+};
+
+static struct ieee80211_supported_band band_2ghz = {
+	.channels = &channel_2ghz,
+	.bitrates = bitrates_2ghz,
+	.band = NL80211_BAND_2GHZ,
+	.n_channels = 1,
+	.n_bitrates = ARRAY_SIZE(bitrates_2ghz),
+	.ht_cap = {
+		.ht_supported = true,
+		.cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 |
+		       IEEE80211_HT_CAP_GRN_FLD |
+		       IEEE80211_HT_CAP_SGI_20 |
+		       IEEE80211_HT_CAP_SGI_40 |
+		       IEEE80211_HT_CAP_DSSSCCK40,
+		.ampdu_factor = 0x3,
+		.ampdu_density = 0x6,
+		.mcs = {
+			.rx_mask = {0xff, 0xff},
+			.tx_params = IEEE80211_HT_MCS_TX_DEFINED,
+		},
+	},
+};
+
+static struct ieee80211_channel channel_5ghz = {
+	.band = NL80211_BAND_5GHZ,
+	.center_freq = 5240,
+	.hw_value = 5240,
+	.max_power = 20,
+};
+
+static struct ieee80211_rate bitrates_5ghz[] = {
+	{ .bitrate = 60 },
+	{ .bitrate = 120 },
+	{ .bitrate = 240 },
+};
+
+#define RX_MCS_MAP (IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 2 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 4 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 6 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 8 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 10 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 12 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 14)
+
+#define TX_MCS_MAP (IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 2 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 4 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 6 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 8 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 10 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 12 | \
+		    IEEE80211_VHT_MCS_SUPPORT_0_9 << 14)
+
+static struct ieee80211_supported_band band_5ghz = {
+	.channels = &channel_5ghz,
+	.bitrates = bitrates_5ghz,
+	.band = NL80211_BAND_5GHZ,
+	.n_channels = 1,
+	.n_bitrates = ARRAY_SIZE(bitrates_5ghz),
+	.ht_cap = {
+		.ht_supported = true,
+		.cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 |
+		       IEEE80211_HT_CAP_GRN_FLD |
+		       IEEE80211_HT_CAP_SGI_20 |
+		       IEEE80211_HT_CAP_SGI_40 |
+		       IEEE80211_HT_CAP_DSSSCCK40,
+		.ampdu_factor = 0x3,
+		.ampdu_density = 0x6,
+		.mcs = {
+			.rx_mask = {0xff, 0xff},
+			.tx_params = IEEE80211_HT_MCS_TX_DEFINED,
+		},
+	},
+	.vht_cap = {
+		.vht_supported = true,
+		.cap = IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 |
+		       IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ |
+		       IEEE80211_VHT_CAP_RXLDPC |
+		       IEEE80211_VHT_CAP_SHORT_GI_80 |
+		       IEEE80211_VHT_CAP_SHORT_GI_160 |
+		       IEEE80211_VHT_CAP_TXSTBC |
+		       IEEE80211_VHT_CAP_RXSTBC_1 |
+		       IEEE80211_VHT_CAP_RXSTBC_2 |
+		       IEEE80211_VHT_CAP_RXSTBC_3 |
+		       IEEE80211_VHT_CAP_RXSTBC_4 |
+		       IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK,
+		.vht_mcs = {
+			.rx_mcs_map = cpu_to_le16(RX_MCS_MAP),
+			.tx_mcs_map = cpu_to_le16(TX_MCS_MAP),
+		}
+	},
+};
+
+/* Assigned at module init. Guaranteed locally-administered and unicast. */
+static u8 fake_router_bssid[ETH_ALEN] __ro_after_init = {};
+
+/* Called with the rtnl lock held. */
+static int virt_wifi_scan(struct wiphy *wiphy,
+			  struct cfg80211_scan_request *request)
+{
+	struct virt_wifi_wiphy_priv *priv = wiphy_priv(wiphy);
+
+	wiphy_debug(wiphy, "scan\n");
+
+	if (priv->scan_request || priv->being_deleted)
+		return -EBUSY;
+
+	priv->scan_request = request;
+	schedule_delayed_work(&priv->scan_result, HZ * 2);
+
+	return 0;
+}
+
+/* Acquires and releases the rdev BSS lock. */
+static void virt_wifi_scan_result(struct work_struct *work)
+{
+	struct {
+		u8 tag;
+		u8 len;
+		u8 ssid[8];
+	} __packed ssid = {
+		.tag = WLAN_EID_SSID, .len = 8, .ssid = "VirtWifi",
+	};
+	struct cfg80211_bss *informed_bss;
+	struct virt_wifi_wiphy_priv *priv =
+		container_of(work, struct virt_wifi_wiphy_priv,
+			     scan_result.work);
+	struct wiphy *wiphy = priv_to_wiphy(priv);
+	struct cfg80211_scan_info scan_info = { .aborted = false };
+
+	informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz,
+					   CFG80211_BSS_FTYPE_PRESP,
+					   fake_router_bssid,
+					   ktime_get_boot_ns(),
+					   WLAN_CAPABILITY_ESS, 0,
+					   (void *)&ssid, sizeof(ssid),
+					   DBM_TO_MBM(-50), GFP_KERNEL);
+	cfg80211_put_bss(wiphy, informed_bss);
+
+	/* Schedules work which acquires and releases the rtnl lock. */
+	cfg80211_scan_done(priv->scan_request, &scan_info);
+	priv->scan_request = NULL;
+}
+
+/* May acquire and release the rdev BSS lock. */
+static void virt_wifi_cancel_scan(struct wiphy *wiphy)
+{
+	struct virt_wifi_wiphy_priv *priv = wiphy_priv(wiphy);
+
+	cancel_delayed_work_sync(&priv->scan_result);
+	/* Clean up dangling callbacks if necessary. */
+	if (priv->scan_request) {
+		struct cfg80211_scan_info scan_info = { .aborted = true };
+		/* Schedules work which acquires and releases the rtnl lock. */
+		cfg80211_scan_done(priv->scan_request, &scan_info);
+		priv->scan_request = NULL;
+	}
+}
+
+struct virt_wifi_netdev_priv {
+	struct delayed_work connect;
+	struct net_device *lowerdev;
+	struct net_device *upperdev;
+	u32 tx_packets;
+	u32 tx_failed;
+	u8 connect_requested_bss[ETH_ALEN];
+	bool is_up;
+	bool is_connected;
+	bool being_deleted;
+};
+
+/* Called with the rtnl lock held. */
+static int virt_wifi_connect(struct wiphy *wiphy, struct net_device *netdev,
+			     struct cfg80211_connect_params *sme)
+{
+	struct virt_wifi_netdev_priv *priv = netdev_priv(netdev);
+	bool could_schedule;
+
+	if (priv->being_deleted || !priv->is_up)
+		return -EBUSY;
+
+	could_schedule = schedule_delayed_work(&priv->connect, HZ * 2);
+	if (!could_schedule)
+		return -EBUSY;
+
+	if (sme->bssid)
+		ether_addr_copy(priv->connect_requested_bss, sme->bssid);
+	else
+		eth_zero_addr(priv->connect_requested_bss);
+
+	wiphy_debug(wiphy, "connect\n");
+
+	return 0;
+}
+
+/* Acquires and releases the rdev event lock. */
+static void virt_wifi_connect_complete(struct work_struct *work)
+{
+	struct virt_wifi_netdev_priv *priv =
+		container_of(work, struct virt_wifi_netdev_priv, connect.work);
+	u8 *requested_bss = priv->connect_requested_bss;
+	bool has_addr = !is_zero_ether_addr(requested_bss);
+	bool right_addr = ether_addr_equal(requested_bss, fake_router_bssid);
+	u16 status = WLAN_STATUS_SUCCESS;
+
+	if (!priv->is_up || (has_addr && !right_addr))
+		status = WLAN_STATUS_UNSPECIFIED_FAILURE;
+	else
+		priv->is_connected = true;
+
+	/* Schedules an event that acquires the rtnl lock. */
+	cfg80211_connect_result(priv->upperdev, requested_bss, NULL, 0, NULL, 0,
+				status, GFP_KERNEL);
+	netif_carrier_on(priv->upperdev);
+}
+
+/* May acquire and release the rdev event lock. */
+static void virt_wifi_cancel_connect(struct net_device *netdev)
+{
+	struct virt_wifi_netdev_priv *priv = netdev_priv(netdev);
+
+	/* If there is work pending, clean up dangling callbacks. */
+	if (cancel_delayed_work_sync(&priv->connect)) {
+		/* Schedules an event that acquires the rtnl lock. */
+		cfg80211_connect_result(priv->upperdev,
+					priv->connect_requested_bss, NULL, 0,
+					NULL, 0,
+					WLAN_STATUS_UNSPECIFIED_FAILURE,
+					GFP_KERNEL);
+	}
+}
+
+/* Called with the rtnl lock held. Acquires the rdev event lock. */
+static int virt_wifi_disconnect(struct wiphy *wiphy, struct net_device *netdev,
+				u16 reason_code)
+{
+	struct virt_wifi_netdev_priv *priv = netdev_priv(netdev);
+
+	if (priv->being_deleted)
+		return -EBUSY;
+
+	wiphy_debug(wiphy, "disconnect\n");
+	virt_wifi_cancel_connect(netdev);
+
+	cfg80211_disconnected(netdev, reason_code, NULL, 0, true, GFP_KERNEL);
+	priv->is_connected = false;
+	netif_carrier_off(netdev);
+
+	return 0;
+}
+
+/* Called with the rtnl lock held. */
+static int virt_wifi_get_station(struct wiphy *wiphy, struct net_device *dev,
+				 const u8 *mac, struct station_info *sinfo)
+{
+	struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+
+	wiphy_debug(wiphy, "get_station\n");
+
+	if (!priv->is_connected || !ether_addr_equal(mac, fake_router_bssid))
+		return -ENOENT;
+
+	sinfo->filled = BIT_ULL(NL80211_STA_INFO_TX_PACKETS) |
+		BIT_ULL(NL80211_STA_INFO_TX_FAILED) |
+		BIT_ULL(NL80211_STA_INFO_SIGNAL) |
+		BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
+	sinfo->tx_packets = priv->tx_packets;
+	sinfo->tx_failed = priv->tx_failed;
+	/* For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_ */
+	sinfo->signal = -50;
+	sinfo->txrate = (struct rate_info) {
+		.legacy = 10, /* units are 100kbit/s */
+	};
+	return 0;
+}
+
+/* Called with the rtnl lock held. */
+static int virt_wifi_dump_station(struct wiphy *wiphy, struct net_device *dev,
+				  int idx, u8 *mac, struct station_info *sinfo)
+{
+	struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+
+	wiphy_debug(wiphy, "dump_station\n");
+
+	if (idx != 0 || !priv->is_connected)
+		return -ENOENT;
+
+	ether_addr_copy(mac, fake_router_bssid);
+	return virt_wifi_get_station(wiphy, dev, fake_router_bssid, sinfo);
+}
+
+static const struct cfg80211_ops virt_wifi_cfg80211_ops = {
+	.scan = virt_wifi_scan,
+
+	.connect = virt_wifi_connect,
+	.disconnect = virt_wifi_disconnect,
+
+	.get_station = virt_wifi_get_station,
+	.dump_station = virt_wifi_dump_station,
+};
+
+/* Acquires and releases the rtnl lock. */
+static struct wiphy *virt_wifi_make_wiphy(void)
+{
+	struct wiphy *wiphy;
+	struct virt_wifi_wiphy_priv *priv;
+	int err;
+
+	wiphy = wiphy_new(&virt_wifi_cfg80211_ops, sizeof(*priv));
+
+	if (!wiphy)
+		return NULL;
+
+	wiphy->max_scan_ssids = 4;
+	wiphy->max_scan_ie_len = 1000;
+	wiphy->signal_type = CFG80211_SIGNAL_TYPE_MBM;
+
+	wiphy->bands[NL80211_BAND_2GHZ] = &band_2ghz;
+	wiphy->bands[NL80211_BAND_5GHZ] = &band_5ghz;
+	wiphy->bands[NL80211_BAND_60GHZ] = NULL;
+
+	wiphy->regulatory_flags = REGULATORY_WIPHY_SELF_MANAGED;
+	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
+
+	priv = wiphy_priv(wiphy);
+	priv->being_deleted = false;
+	priv->scan_request = NULL;
+	INIT_DELAYED_WORK(&priv->scan_result, virt_wifi_scan_result);
+
+	err = wiphy_register(wiphy);
+	if (err < 0) {
+		wiphy_free(wiphy);
+		return NULL;
+	}
+
+	return wiphy;
+}
+
+/* Acquires and releases the rtnl lock. */
+static void virt_wifi_destroy_wiphy(struct wiphy *wiphy)
+{
+	struct virt_wifi_wiphy_priv *priv;
+
+	WARN(!wiphy, "%s called with null wiphy", __func__);
+	if (!wiphy)
+		return;
+
+	priv = wiphy_priv(wiphy);
+	priv->being_deleted = true;
+	virt_wifi_cancel_scan(wiphy);
+
+	if (wiphy->registered)
+		wiphy_unregister(wiphy);
+	wiphy_free(wiphy);
+}
+
+/* Enters and exits a RCU-bh critical section. */
+static netdev_tx_t virt_wifi_start_xmit(struct sk_buff *skb,
+					struct net_device *dev)
+{
+	struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+
+	priv->tx_packets++;
+	if (!priv->is_connected) {
+		priv->tx_failed++;
+		return NET_XMIT_DROP;
+	}
+
+	skb->dev = priv->lowerdev;
+	return dev_queue_xmit(skb);
+}
+
+/* Called with rtnl lock held. */
+static int virt_wifi_net_device_open(struct net_device *dev)
+{
+	struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+
+	priv->is_up = true;
+	return 0;
+}
+
+/* Called with rtnl lock held. */
+static int virt_wifi_net_device_stop(struct net_device *dev)
+{
+	struct virt_wifi_netdev_priv *n_priv = netdev_priv(dev);
+	struct virt_wifi_wiphy_priv *w_priv;
+
+	n_priv->is_up = false;
+
+	if (!dev->ieee80211_ptr)
+		return 0;
+	w_priv = wiphy_priv(dev->ieee80211_ptr->wiphy);
+
+	virt_wifi_cancel_scan(dev->ieee80211_ptr->wiphy);
+	virt_wifi_cancel_connect(dev);
+	netif_carrier_off(dev);
+
+	return 0;
+}
+
+static const struct net_device_ops virt_wifi_ops = {
+	.ndo_start_xmit = virt_wifi_start_xmit,
+	.ndo_open = virt_wifi_net_device_open,
+	.ndo_stop = virt_wifi_net_device_stop,
+};
+
+/* Invoked as part of rtnl lock release. */
+static void virt_wifi_net_device_destructor(struct net_device *dev)
+{
+	/* Delayed past dellink to allow nl80211 to react to the device being
+	 * deleted.
+	 */
+	kfree(dev->ieee80211_ptr);
+	dev->ieee80211_ptr = NULL;
+	free_netdev(dev);
+}
+
+/* No lock interaction. */
+static void virt_wifi_setup(struct net_device *dev)
+{
+	ether_setup(dev);
+	dev->netdev_ops = &virt_wifi_ops;
+	dev->priv_destructor = virt_wifi_net_device_destructor;
+}
+
+/* Called in a RCU read critical section from netif_receive_skb */
+static rx_handler_result_t virt_wifi_rx_handler(struct sk_buff **pskb)
+{
+	struct sk_buff *skb = *pskb;
+	struct virt_wifi_netdev_priv *priv =
+		rcu_dereference(skb->dev->rx_handler_data);
+
+	if (!priv->is_connected)
+		return RX_HANDLER_PASS;
+
+	/* GFP_ATOMIC because this is a packet interrupt handler. */
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb) {
+		dev_err(&priv->upperdev->dev, "can't skb_share_check\n");
+		return RX_HANDLER_CONSUMED;
+	}
+
+	*pskb = skb;
+	skb->dev = priv->upperdev;
+	skb->pkt_type = PACKET_HOST;
+	return RX_HANDLER_ANOTHER;
+}
+
+/* Called with rtnl lock held. */
+static int virt_wifi_newlink(struct net *src_net, struct net_device *dev,
+			     struct nlattr *tb[], struct nlattr *data[],
+			     struct netlink_ext_ack *extack)
+{
+	struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+	int err;
+
+	if (!tb[IFLA_LINK])
+		return -EINVAL;
+
+	netif_carrier_off(dev);
+
+	priv->upperdev = dev;
+	priv->lowerdev = __dev_get_by_index(src_net,
+					    nla_get_u32(tb[IFLA_LINK]));
+
+	if (!priv->lowerdev)
+		return -ENODEV;
+	if (!tb[IFLA_MTU])
+		dev->mtu = priv->lowerdev->mtu;
+	else if (dev->mtu > priv->lowerdev->mtu)
+		return -EINVAL;
+
+	err = netdev_rx_handler_register(priv->lowerdev, virt_wifi_rx_handler,
+					 priv);
+	if (err) {
+		dev_err(&priv->lowerdev->dev,
+			"can't netdev_rx_handler_register: %d\n", err);
+		return err;
+	}
+
+	eth_hw_addr_inherit(dev, priv->lowerdev);
+	netif_stacked_transfer_operstate(priv->lowerdev, dev);
+
+	SET_NETDEV_DEV(dev, &priv->lowerdev->dev);
+	dev->ieee80211_ptr = kzalloc(sizeof(*dev->ieee80211_ptr), GFP_KERNEL);
+
+	if (!dev->ieee80211_ptr)
+		goto remove_handler;
+
+	dev->ieee80211_ptr->iftype = NL80211_IFTYPE_STATION;
+	dev->ieee80211_ptr->wiphy = common_wiphy;
+
+	err = register_netdevice(dev);
+	if (err) {
+		dev_err(&priv->lowerdev->dev, "can't register_netdevice: %d\n",
+			err);
+		goto free_wireless_dev;
+	}
+
+	err = netdev_upper_dev_link(priv->lowerdev, dev, extack);
+	if (err) {
+		dev_err(&priv->lowerdev->dev, "can't netdev_upper_dev_link: %d\n",
+			err);
+		goto unregister_netdev;
+	}
+
+	priv->being_deleted = false;
+	priv->is_connected = false;
+	priv->is_up = false;
+	INIT_DELAYED_WORK(&priv->connect, virt_wifi_connect_complete);
+
+	return 0;
+unregister_netdev:
+	unregister_netdevice(dev);
+free_wireless_dev:
+	kfree(dev->ieee80211_ptr);
+	dev->ieee80211_ptr = NULL;
+remove_handler:
+	netdev_rx_handler_unregister(priv->lowerdev);
+
+	return err;
+}
+
+/* Called with rtnl lock held. */
+static void virt_wifi_dellink(struct net_device *dev,
+			      struct list_head *head)
+{
+	struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+
+	if (dev->ieee80211_ptr)
+		virt_wifi_cancel_scan(dev->ieee80211_ptr->wiphy);
+
+	priv->being_deleted = true;
+	virt_wifi_cancel_connect(dev);
+	netif_carrier_off(dev);
+
+	netdev_rx_handler_unregister(priv->lowerdev);
+	netdev_upper_dev_unlink(priv->lowerdev, dev);
+
+	unregister_netdevice_queue(dev, head);
+
+	/* Deleting the wiphy is handled in the module destructor. */
+}
+
+static struct rtnl_link_ops virt_wifi_link_ops = {
+	.kind		= "virt_wifi",
+	.setup		= virt_wifi_setup,
+	.newlink	= virt_wifi_newlink,
+	.dellink	= virt_wifi_dellink,
+	.priv_size	= sizeof(struct virt_wifi_netdev_priv),
+};
+
+/* Acquires and releases the rtnl lock. */
+static int __init virt_wifi_init_module(void)
+{
+	int err;
+
+	/* Guaranteed to be locallly-administered and not multicast. */
+	eth_random_addr(fake_router_bssid);
+
+	common_wiphy = virt_wifi_make_wiphy();
+	if (!common_wiphy)
+		return -ENOMEM;
+
+	err = rtnl_link_register(&virt_wifi_link_ops);
+	if (err)
+		virt_wifi_destroy_wiphy(common_wiphy);
+
+	return err;
+}
+
+/* Acquires and releases the rtnl lock. */
+static void __exit virt_wifi_cleanup_module(void)
+{
+	/* Will delete any devices that depend on the wiphy. */
+	rtnl_link_unregister(&virt_wifi_link_ops);
+	virt_wifi_destroy_wiphy(common_wiphy);
+}
+
+module_init(virt_wifi_init_module);
+module_exit(virt_wifi_cleanup_module);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Cody Schuffelen <schuffelen@google.com>");
+MODULE_DESCRIPTION("Driver for a wireless wrapper of ethernet devices");
+MODULE_ALIAS_RTNL_LINK("virt_wifi");
-- 
cgit v1.2.3


From c8d10cbda12f14c312dcf7c5a1748625f2c308c1 Mon Sep 17 00:00:00 2001
From: Bob Copeland <me@bobcopeland.com>
Date: Tue, 4 Dec 2018 10:22:00 -0500
Subject: mac80211: rewrite Kconfig text for mesh

Lubomir Rintel recently pointed out a dead link for o11s.org, and
repointed it to a still live, but also stale website.  As far as I
know, no one is updating the content at open80211s.org.

Since this Kconfig text was originally written, though, the 802.11s
mesh drafts were approved and ultimately rolled into 802.11 proper.
Meanwhile, the implementation has converged on the final standard,
so we can lose all of the text here and provide something that's a
little more helpful and accurate.

Signed-off-by: Bob Copeland <bobcopeland@fb.com>
Reviewed-by: Lubomir Rintel <lkundrak@v3.sk>
Reviewed-by: Steve deRosier <derosier@cal-sierra.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/Kconfig | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index f869e35d0974..be471fe95048 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -57,14 +57,13 @@ comment "Some wireless drivers require a rate control algorithm"
 	depends on MAC80211 && MAC80211_HAS_RC=n
 
 config MAC80211_MESH
-	bool "Enable mac80211 mesh networking (pre-802.11s) support"
+	bool "Enable mac80211 mesh networking support"
 	depends on MAC80211
 	---help---
-	 This options enables support of Draft 802.11s mesh networking.
-	 The implementation is based on Draft 2.08 of the Mesh Networking
-	 amendment.  However, no compliance with that draft is claimed or even
-	 possible, as drafts leave a number of identifiers to be defined after
-	 ratification.  For more information visit http://o11s.org/.
+	  Select this option to enable 802.11 mesh operation in mac80211
+	  drivers that support it.  802.11 mesh connects multiple stations
+	  over (possibly multi-hop) wireless links to form a single logical
+	  LAN.
 
 config MAC80211_LEDS
 	bool "Enable LED triggers"
-- 
cgit v1.2.3


From f6c7f03f69f7422bc237bc79599e152d390b74e0 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 3 Dec 2018 21:15:49 +0200
Subject: mac80211: fix deauth TX when we disconnect

The iTXQs stop/wake queue mechanism involves a whole bunch
of locks and this is probably why the call to
ieee80211_wake_txqs is deferred to a tasklet when called from
__ieee80211_wake_queue.

Another advantage of that is that ieee80211_wake_txqs might
call the wake_tx_queue() callback and then the driver may
call mac80211 which will call it back in the same context.

The bug I saw is that when we send a deauth frame as a
station we do:

flush(drop=1)
tx deauth
flush(drop=0)

While we flush we stop the queues and wake them up
immediately after we finished flushing. The problem here is
that the tasklet that de-facto enables the queue may not have
run until we send the deauth. Then the deauth frame is sent
to the driver (which is surprising by itself), but the driver
won't get anything useful from ieee80211_tx_dequeue because
the queue is stopped (or more precisely because
vif->txqs_stopped[0] is true).
Then the deauth is not sent. Later on, the tasklet will run,
but that'll be too late. We'll already have removed all the
vif etc...

Fix this by calling ieee80211_wake_txqs synchronously if we
are not waking up the queues from the driver (we check the
reason to determine that). This makes the code really
convoluted because we may call ieee80211_wake_txqs from
__ieee80211_wake_queue. The latter assumes that
queue_stop_reason_lock has been taken by the caller and
ieee80211_wake_txqs may release the lock to send the frames.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/util.c | 49 +++++++++++++++++++++++++++++++++++--------------
 1 file changed, 35 insertions(+), 14 deletions(-)

diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index bec424316ea4..dddfff7cf44f 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -299,16 +299,16 @@ out:
 	spin_unlock_bh(&fq->lock);
 }
 
-void ieee80211_wake_txqs(unsigned long data)
+static void
+__releases(&local->queue_stop_reason_lock)
+__acquires(&local->queue_stop_reason_lock)
+_ieee80211_wake_txqs(struct ieee80211_local *local, unsigned long *flags)
 {
-	struct ieee80211_local *local = (struct ieee80211_local *)data;
 	struct ieee80211_sub_if_data *sdata;
 	int n_acs = IEEE80211_NUM_ACS;
-	unsigned long flags;
 	int i;
 
 	rcu_read_lock();
-	spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
 
 	if (local->hw.queues < IEEE80211_NUM_ACS)
 		n_acs = 1;
@@ -317,7 +317,7 @@ void ieee80211_wake_txqs(unsigned long data)
 		if (local->queue_stop_reasons[i])
 			continue;
 
-		spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
+		spin_unlock_irqrestore(&local->queue_stop_reason_lock, *flags);
 		list_for_each_entry_rcu(sdata, &local->interfaces, list) {
 			int ac;
 
@@ -329,13 +329,22 @@ void ieee80211_wake_txqs(unsigned long data)
 					__ieee80211_wake_txqs(sdata, ac);
 			}
 		}
-		spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
+		spin_lock_irqsave(&local->queue_stop_reason_lock, *flags);
 	}
 
-	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 	rcu_read_unlock();
 }
 
+void ieee80211_wake_txqs(unsigned long data)
+{
+	struct ieee80211_local *local = (struct ieee80211_local *)data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
+	_ieee80211_wake_txqs(local, &flags);
+	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
+}
+
 void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue)
 {
 	struct ieee80211_sub_if_data *sdata;
@@ -371,7 +380,8 @@ void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue)
 
 static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue,
 				   enum queue_stop_reason reason,
-				   bool refcounted)
+				   bool refcounted,
+				   unsigned long *flags)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
 
@@ -405,8 +415,19 @@ static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue,
 	} else
 		tasklet_schedule(&local->tx_pending_tasklet);
 
-	if (local->ops->wake_tx_queue)
-		tasklet_schedule(&local->wake_txqs_tasklet);
+	/*
+	 * Calling _ieee80211_wake_txqs here can be a problem because it may
+	 * release queue_stop_reason_lock which has been taken by
+	 * __ieee80211_wake_queue's caller. It is certainly not very nice to
+	 * release someone's lock, but it is fine because all the callers of
+	 * __ieee80211_wake_queue call it right before releasing the lock.
+	 */
+	if (local->ops->wake_tx_queue) {
+		if (reason == IEEE80211_QUEUE_STOP_REASON_DRIVER)
+			tasklet_schedule(&local->wake_txqs_tasklet);
+		else
+			_ieee80211_wake_txqs(local, flags);
+	}
 }
 
 void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue,
@@ -417,7 +438,7 @@ void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue,
 	unsigned long flags;
 
 	spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
-	__ieee80211_wake_queue(hw, queue, reason, refcounted);
+	__ieee80211_wake_queue(hw, queue, reason, refcounted, &flags);
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 }
 
@@ -514,7 +535,7 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local,
 			       false);
 	__skb_queue_tail(&local->pending[queue], skb);
 	__ieee80211_wake_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD,
-			       false);
+			       false, &flags);
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 }
 
@@ -547,7 +568,7 @@ void ieee80211_add_pending_skbs(struct ieee80211_local *local,
 	for (i = 0; i < hw->queues; i++)
 		__ieee80211_wake_queue(hw, i,
 			IEEE80211_QUEUE_STOP_REASON_SKB_ADD,
-			false);
+			false, &flags);
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 }
 
@@ -605,7 +626,7 @@ void ieee80211_wake_queues_by_reason(struct ieee80211_hw *hw,
 	spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
 
 	for_each_set_bit(i, &queues, hw->queues)
-		__ieee80211_wake_queue(hw, i, reason, refcounted);
+		__ieee80211_wake_queue(hw, i, reason, refcounted, &flags);
 
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 }
-- 
cgit v1.2.3


From dc002bb62f10c5905420f8b8a7d5ec0da567fc82 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 23 Nov 2018 23:18:03 +0100
Subject: bpf: add __weak hook for allocating executable memory

By default, BPF uses module_alloc() to allocate executable memory,
but this is not necessary on all arches and potentially undesirable
on some of them.

So break out the module_alloc() and module_memfree() calls into __weak
functions to allow them to be overridden in arch code.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/core.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f93ed667546f..86817ab204e8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -623,6 +623,16 @@ static void bpf_jit_uncharge_modmem(u32 pages)
 	atomic_long_sub(pages, &bpf_jit_current);
 }
 
+void *__weak bpf_jit_alloc_exec(unsigned long size)
+{
+	return module_alloc(size);
+}
+
+void __weak bpf_jit_free_exec(void *addr)
+{
+	module_memfree(addr);
+}
+
 struct bpf_binary_header *
 bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
 		     unsigned int alignment,
@@ -640,7 +650,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
 
 	if (bpf_jit_charge_modmem(pages))
 		return NULL;
-	hdr = module_alloc(size);
+	hdr = bpf_jit_alloc_exec(size);
 	if (!hdr) {
 		bpf_jit_uncharge_modmem(pages);
 		return NULL;
@@ -664,7 +674,7 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr)
 {
 	u32 pages = hdr->pages;
 
-	module_memfree(hdr);
+	bpf_jit_free_exec(hdr);
 	bpf_jit_uncharge_modmem(pages);
 }
 
-- 
cgit v1.2.3


From 91fc957c9b1d6c55168df15a397cbd1af16bc00f Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 23 Nov 2018 23:18:04 +0100
Subject: arm64/bpf: don't allocate BPF JIT programs in module memory

The arm64 module region is a 128 MB region that is kept close to
the core kernel, in order to ensure that relative branches are
always in range. So using the same region for programs that do
not have this restriction is wasteful, and preferably avoided.

Now that the core BPF JIT code permits the alloc/free routines to
be overridden, implement them by vmalloc()/vfree() calls from a
dedicated 128 MB region set aside for BPF programs. This ensures
that BPF programs are still in branching range of each other, which
is something the JIT currently depends upon (and is not guaranteed
when using module_alloc() on KASLR kernels like we do currently).
It also ensures that placement of BPF programs does not correlate
with the placement of the core kernel or modules, making it less
likely that leaking the former will reveal the latter.

This also solves an issue under KASAN, where shadow memory is
needlessly allocated for all BPF programs (which don't require KASAN
shadow pages since they are not KASAN instrumented)

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm64/include/asm/memory.h |  5 ++++-
 arch/arm64/net/bpf_jit_comp.c   | 13 +++++++++++++
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index b96442960aea..ee20fc63899c 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -62,8 +62,11 @@
 #define PAGE_OFFSET		(UL(0xffffffffffffffff) - \
 	(UL(1) << (VA_BITS - 1)) + 1)
 #define KIMAGE_VADDR		(MODULES_END)
+#define BPF_JIT_REGION_START	(VA_START + KASAN_SHADOW_SIZE)
+#define BPF_JIT_REGION_SIZE	(SZ_128M)
+#define BPF_JIT_REGION_END	(BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE)
 #define MODULES_END		(MODULES_VADDR + MODULES_VSIZE)
-#define MODULES_VADDR		(VA_START + KASAN_SHADOW_SIZE)
+#define MODULES_VADDR		(BPF_JIT_REGION_END)
 #define MODULES_VSIZE		(SZ_128M)
 #define VMEMMAP_START		(PAGE_OFFSET - VMEMMAP_SIZE)
 #define PCI_IO_END		(VMEMMAP_START - SZ_2M)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index b87285924023..0a7371a86139 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -943,3 +943,16 @@ out:
 					   tmp : orig_prog);
 	return prog;
 }
+
+void *bpf_jit_alloc_exec(unsigned long size)
+{
+	return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
+				    BPF_JIT_REGION_END, GFP_KERNEL,
+				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				    __builtin_return_address(0));
+}
+
+void bpf_jit_free_exec(void *addr)
+{
+	return vfree(addr);
+}
-- 
cgit v1.2.3


From 30da46b5dc3a9a14db11706d841440e28b12bb53 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Wed, 5 Dec 2018 10:28:24 +0000
Subject: tools: bpftool: add a command to dump the trace pipe

BPF programs can use the bpf_trace_printk() helper to print debug
information into the trace pipe. Add a subcommand
"bpftool prog tracelog" to simply dump this pipe to the console.

This is for a good part copied from iproute2, where the feature is
available with "tc exec bpf dbg". Changes include dumping pipe content
to stdout instead of stderr and adding JSON support (content is dumped
as an array of strings, one per line read from the pipe). This version
is dual-licensed, with Daniel's permission.

Cc: Daniel Borkmann <daniel@iogearbox.net>
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst |  13 +-
 tools/bpf/bpftool/bash-completion/bpftool        |   5 +-
 tools/bpf/bpftool/main.h                         |   1 +
 tools/bpf/bpftool/prog.c                         |   4 +-
 tools/bpf/bpftool/tracelog.c                     | 157 +++++++++++++++++++++++
 5 files changed, 176 insertions(+), 4 deletions(-)
 create mode 100644 tools/bpf/bpftool/tracelog.c

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index ab36e920e552..5524b6dccd85 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -26,8 +26,9 @@ MAP COMMANDS
 |	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
 |	**bpftool** **prog pin** *PROG* *FILE*
 |	**bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
-|       **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*]
-|       **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*]
+|	**bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*]
+|	**bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*]
+|	**bpftool** **prog tracelog**
 |	**bpftool** **prog help**
 |
 |	*MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
@@ -117,6 +118,14 @@ DESCRIPTION
 		  parameter, with the exception of *flow_dissector* which is
 		  detached from the current networking name space.
 
+	**bpftool prog tracelog**
+		  Dump the trace pipe of the system to the console (stdout).
+		  Hit <Ctrl+C> to stop printing. BPF programs can write to this
+		  trace pipe at runtime with the **bpf_trace_printk()** helper.
+		  This should be used only for debugging purposes. For
+		  streaming data from BPF programs to user space, one can use
+		  perf events (see also **bpftool-map**\ (8)).
+
 	**bpftool prog help**
 		  Print short help message.
 
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 9a60080f085f..44c189ba072a 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -398,10 +398,13 @@ _bpftool()
                             ;;
                     esac
                     ;;
+                tracelog)
+                    return 0
+                    ;;
                 *)
                     [[ $prev == $object ]] && \
                         COMPREPLY=( $( compgen -W 'dump help pin attach detach load \
-                            show list' -- "$cur" ) )
+                            show list tracelog' -- "$cur" ) )
                     ;;
             esac
             ;;
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 2761981669c8..0be0dd8f467f 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -167,6 +167,7 @@ int do_event_pipe(int argc, char **argv);
 int do_cgroup(int argc, char **arg);
 int do_perf(int argc, char **arg);
 int do_net(int argc, char **arg);
+int do_tracelog(int argc, char **arg);
 
 int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what);
 int prog_parse_fd(int *argc, char ***argv);
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 56db61c5a91f..54c8dbf05c9c 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -1140,6 +1140,7 @@ static int do_help(int argc, char **argv)
 		"                         [pinmaps MAP_DIR]\n"
 		"       %s %s attach PROG ATTACH_TYPE [MAP]\n"
 		"       %s %s detach PROG ATTACH_TYPE [MAP]\n"
+		"       %s %s tracelog\n"
 		"       %s %s help\n"
 		"\n"
 		"       " HELP_SPEC_MAP "\n"
@@ -1158,7 +1159,7 @@ static int do_help(int argc, char **argv)
 		"",
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
-		bin_name, argv[-2], bin_name, argv[-2]);
+		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]);
 
 	return 0;
 }
@@ -1173,6 +1174,7 @@ static const struct cmd cmds[] = {
 	{ "loadall",	do_loadall },
 	{ "attach",	do_attach },
 	{ "detach",	do_detach },
+	{ "tracelog",	do_tracelog },
 	{ 0 }
 };
 
diff --git a/tools/bpf/bpftool/tracelog.c b/tools/bpf/bpftool/tracelog.c
new file mode 100644
index 000000000000..1fa8e513f590
--- /dev/null
+++ b/tools/bpf/bpftool/tracelog.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (c) 2015-2017 Daniel Borkmann */
+/* Copyright (c) 2018 Netronome Systems, Inc. */
+
+#include <errno.h>
+#include <limits.h>
+#include <signal.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/magic.h>
+#include <sys/fcntl.h>
+#include <sys/vfs.h>
+
+#include "main.h"
+
+#ifndef TRACEFS_MAGIC
+# define TRACEFS_MAGIC	0x74726163
+#endif
+
+#define _textify(x)	#x
+#define textify(x)	_textify(x)
+
+FILE *trace_pipe_fd;
+char *buff;
+
+static int validate_tracefs_mnt(const char *mnt, unsigned long magic)
+{
+	struct statfs st_fs;
+
+	if (statfs(mnt, &st_fs) < 0)
+		return -ENOENT;
+	if ((unsigned long)st_fs.f_type != magic)
+		return -ENOENT;
+
+	return 0;
+}
+
+static bool
+find_tracefs_mnt_single(unsigned long magic, char *mnt, const char *mntpt)
+{
+	size_t src_len;
+
+	if (validate_tracefs_mnt(mntpt, magic))
+		return false;
+
+	src_len = strlen(mntpt);
+	if (src_len + 1 >= PATH_MAX) {
+		p_err("tracefs mount point name too long");
+		return false;
+	}
+
+	strcpy(mnt, mntpt);
+	return true;
+}
+
+static bool find_tracefs_pipe(char *mnt)
+{
+	static const char * const known_mnts[] = {
+		"/sys/kernel/debug/tracing",
+		"/sys/kernel/tracing",
+		"/tracing",
+		"/trace",
+	};
+	const char *pipe_name = "/trace_pipe";
+	const char *fstype = "tracefs";
+	char type[100], format[32];
+	const char * const *ptr;
+	bool found = false;
+	FILE *fp;
+
+	for (ptr = known_mnts; ptr < known_mnts + ARRAY_SIZE(known_mnts); ptr++)
+		if (find_tracefs_mnt_single(TRACEFS_MAGIC, mnt, *ptr))
+			goto exit_found;
+
+	fp = fopen("/proc/mounts", "r");
+	if (!fp)
+		return false;
+
+	/* Allow room for NULL terminating byte and pipe file name */
+	snprintf(format, sizeof(format), "%%*s %%%zds %%99s %%*s %%*d %%*d\\n",
+		 PATH_MAX - strlen(pipe_name) - 1);
+	while (fscanf(fp, format, mnt, type) == 2)
+		if (strcmp(type, fstype) == 0) {
+			found = true;
+			break;
+		}
+	fclose(fp);
+
+	/* The string from fscanf() might be truncated, check mnt is valid */
+	if (!found || validate_tracefs_mnt(mnt, TRACEFS_MAGIC))
+		return false;
+
+exit_found:
+	strcat(mnt, pipe_name);
+	return true;
+}
+
+static void exit_tracelog(int signum)
+{
+	fclose(trace_pipe_fd);
+	free(buff);
+
+	if (json_output) {
+		jsonw_end_array(json_wtr);
+		jsonw_destroy(&json_wtr);
+	}
+
+	exit(0);
+}
+
+int do_tracelog(int argc, char **argv)
+{
+	const struct sigaction act = {
+		.sa_handler = exit_tracelog
+	};
+	char trace_pipe[PATH_MAX];
+	bool found_trace_pipe;
+	size_t buff_len = 0;
+
+	if (json_output)
+		jsonw_start_array(json_wtr);
+
+	found_trace_pipe = find_tracefs_pipe(trace_pipe);
+	if (!found_trace_pipe) {
+		p_err("could not find trace pipe, tracefs not mounted?");
+		return -1;
+	}
+
+	trace_pipe_fd = fopen(trace_pipe, "r");
+	if (!trace_pipe_fd) {
+		p_err("could not open trace pipe: %s", strerror(errno));
+		return -1;
+	}
+
+	sigaction(SIGHUP, &act, NULL);
+	sigaction(SIGINT, &act, NULL);
+	sigaction(SIGTERM, &act, NULL);
+	while (1) {
+		ssize_t ret;
+
+		ret = getline(&buff, &buff_len, trace_pipe_fd);
+		if (ret <= 0) {
+			p_err("failed to read content from trace pipe: %s",
+			      strerror(errno));
+			break;
+		}
+		if (json_output)
+			jsonw_string(json_wtr, buff);
+		else
+			printf("%s", buff);
+	}
+
+	fclose(trace_pipe_fd);
+	free(buff);
+	return -1;
+}
-- 
cgit v1.2.3


From b255e500c8dc111dd9efac1442a85a0dac913feb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 3 Dec 2018 17:43:28 -0800
Subject: net: documentation: build a directory structure for drivers

Documentation/networking/ is full of cryptically named files with
driver documentation.  This makes finding interesting information
at a glance really hard.  Move all those files into a directory
called device_drivers (since not all drivers are for device) and
fix up references.

RFC v0.1 -> RFC v1:
 - also add .txt suffix to the files which are missing it (Quentin)

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: David Ahern <dsahern@gmail.com>
Acked-by: Henrik Austad <henrik@austad.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../devicetree/bindings/misc/fsl,qoriq-mc.txt      |   2 +-
 Documentation/networking/3c509.txt                 | 213 ------
 Documentation/networking/LICENSE.qla3xxx           |  46 --
 Documentation/networking/LICENSE.qlcnic            | 288 --------
 Documentation/networking/LICENSE.qlge              | 288 --------
 Documentation/networking/README.ipw2100            | 293 --------
 Documentation/networking/README.ipw2200            | 472 -------------
 Documentation/networking/README.sb1000             | 207 ------
 Documentation/networking/cs89x0.txt                | 624 -----------------
 Documentation/networking/cxgb.txt                  | 352 ----------
 Documentation/networking/de4x5.txt                 | 178 -----
 .../networking/device_drivers/3com/3c509.txt       | 213 ++++++
 .../networking/device_drivers/3com/vortex.txt      | 448 ++++++++++++
 .../networking/device_drivers/amazon/ena.txt       | 305 ++++++++
 .../networking/device_drivers/chelsio/cxgb.txt     | 352 ++++++++++
 .../networking/device_drivers/cirrus/cs89x0.txt    | 624 +++++++++++++++++
 .../networking/device_drivers/davicom/dm9000.txt   | 167 +++++
 .../networking/device_drivers/dec/de4x5.txt        | 178 +++++
 .../networking/device_drivers/dec/dmfe.txt         |  66 ++
 .../networking/device_drivers/dlink/dl2k.txt       | 282 ++++++++
 .../networking/device_drivers/freescale/dpaa.txt   | 260 +++++++
 .../device_drivers/freescale/dpaa2/dpio-driver.rst | 158 +++++
 .../freescale/dpaa2/ethernet-driver.rst            | 185 +++++
 .../device_drivers/freescale/dpaa2/index.rst       |  10 +
 .../device_drivers/freescale/dpaa2/overview.rst    | 405 +++++++++++
 .../device_drivers/freescale/gianfar.txt           |  42 ++
 .../networking/device_drivers/intel/e100.rst       | 187 +++++
 .../networking/device_drivers/intel/e1000.rst      | 462 +++++++++++++
 .../networking/device_drivers/intel/e1000e.rst     | 382 ++++++++++
 .../networking/device_drivers/intel/fm10k.rst      | 141 ++++
 .../networking/device_drivers/intel/i40e.rst       | 770 +++++++++++++++++++++
 .../networking/device_drivers/intel/iavf.rst       | 281 ++++++++
 .../networking/device_drivers/intel/ice.rst        |  45 ++
 .../networking/device_drivers/intel/igb.rst        | 193 ++++++
 .../networking/device_drivers/intel/igbvf.rst      |  64 ++
 .../networking/device_drivers/intel/ipw2100.txt    | 293 ++++++++
 .../networking/device_drivers/intel/ipw2200.txt    | 472 +++++++++++++
 .../networking/device_drivers/intel/ixgb.rst       | 467 +++++++++++++
 .../networking/device_drivers/intel/ixgbe.rst      | 540 +++++++++++++++
 .../networking/device_drivers/intel/ixgbevf.rst    |  66 ++
 .../networking/device_drivers/microsoft/netvsc.txt |  84 +++
 .../networking/device_drivers/neterion/s2io.txt    | 141 ++++
 .../networking/device_drivers/neterion/vxge.txt    |  93 +++
 .../device_drivers/qlogic/LICENSE.qla3xxx          |  46 ++
 .../device_drivers/qlogic/LICENSE.qlcnic           | 288 ++++++++
 .../networking/device_drivers/qlogic/LICENSE.qlge  | 288 ++++++++
 .../networking/device_drivers/qualcomm/rmnet.txt   |  82 +++
 Documentation/networking/device_drivers/sb1000.txt | 207 ++++++
 .../networking/device_drivers/smsc/smc9.txt        |  42 ++
 .../networking/device_drivers/stmicro/stmmac.txt   | 401 +++++++++++
 .../networking/device_drivers/ti/cpsw.txt          | 541 +++++++++++++++
 .../networking/device_drivers/ti/tlan.txt          | 117 ++++
 .../device_drivers/toshiba/spider_net.txt          | 204 ++++++
 Documentation/networking/dl2k.txt                  | 282 --------
 Documentation/networking/dm9000.txt                | 167 -----
 Documentation/networking/dmfe.txt                  |  66 --
 Documentation/networking/dpaa.txt                  | 260 -------
 Documentation/networking/dpaa2/dpio-driver.rst     | 158 -----
 Documentation/networking/dpaa2/ethernet-driver.rst | 185 -----
 Documentation/networking/dpaa2/index.rst           |  10 -
 Documentation/networking/dpaa2/overview.rst        | 405 -----------
 Documentation/networking/e100.rst                  | 187 -----
 Documentation/networking/e1000.rst                 | 462 -------------
 Documentation/networking/e1000e.rst                | 382 ----------
 Documentation/networking/ena.txt                   | 305 --------
 Documentation/networking/fm10k.rst                 | 141 ----
 Documentation/networking/gianfar.txt               |  42 --
 Documentation/networking/i40e.rst                  | 770 ---------------------
 Documentation/networking/iavf.rst                  | 281 --------
 Documentation/networking/ice.rst                   |  45 --
 Documentation/networking/igb.rst                   | 193 ------
 Documentation/networking/igbvf.rst                 |  64 --
 Documentation/networking/ixgb.rst                  | 467 -------------
 Documentation/networking/ixgbe.rst                 | 540 ---------------
 Documentation/networking/ixgbevf.rst               |  66 --
 Documentation/networking/netvsc.txt                |  84 ---
 Documentation/networking/rmnet.txt                 |  82 ---
 Documentation/networking/s2io.txt                  | 141 ----
 Documentation/networking/smc9.txt                  |  42 --
 Documentation/networking/spider_net.txt            | 204 ------
 Documentation/networking/stmmac.txt                | 401 -----------
 Documentation/networking/ti-cpsw.txt               | 541 ---------------
 Documentation/networking/tlan.txt                  | 117 ----
 Documentation/networking/vortex.txt                | 448 ------------
 Documentation/networking/vxge.txt                  |  93 ---
 MAINTAINERS                                        |  48 +-
 drivers/net/Kconfig                                |   8 +-
 drivers/net/ethernet/3com/3c59x.c                  |   4 +-
 drivers/net/ethernet/3com/Kconfig                  |   5 +-
 drivers/net/ethernet/chelsio/Kconfig               |   3 +-
 drivers/net/ethernet/cirrus/Kconfig                |   2 +-
 drivers/net/ethernet/dec/tulip/Kconfig             |   4 +-
 drivers/net/ethernet/dlink/dl2k.c                  |   2 +-
 drivers/net/ethernet/intel/Kconfig                 |  24 +-
 drivers/net/ethernet/neterion/Kconfig              |   4 +-
 drivers/net/ethernet/smsc/Kconfig                  |   4 +-
 drivers/net/ethernet/ti/Kconfig                    |   3 +-
 drivers/net/ethernet/ti/tlan.c                     |   4 +-
 drivers/net/wireless/intel/ipw2x00/Kconfig         |  10 +-
 drivers/net/wireless/intel/ipw2x00/ipw2100.c       |   2 +-
 100 files changed, 10659 insertions(+), 10654 deletions(-)
 delete mode 100644 Documentation/networking/3c509.txt
 delete mode 100644 Documentation/networking/LICENSE.qla3xxx
 delete mode 100644 Documentation/networking/LICENSE.qlcnic
 delete mode 100644 Documentation/networking/LICENSE.qlge
 delete mode 100644 Documentation/networking/README.ipw2100
 delete mode 100644 Documentation/networking/README.ipw2200
 delete mode 100644 Documentation/networking/README.sb1000
 delete mode 100644 Documentation/networking/cs89x0.txt
 delete mode 100644 Documentation/networking/cxgb.txt
 delete mode 100644 Documentation/networking/de4x5.txt
 create mode 100644 Documentation/networking/device_drivers/3com/3c509.txt
 create mode 100644 Documentation/networking/device_drivers/3com/vortex.txt
 create mode 100644 Documentation/networking/device_drivers/amazon/ena.txt
 create mode 100644 Documentation/networking/device_drivers/chelsio/cxgb.txt
 create mode 100644 Documentation/networking/device_drivers/cirrus/cs89x0.txt
 create mode 100644 Documentation/networking/device_drivers/davicom/dm9000.txt
 create mode 100644 Documentation/networking/device_drivers/dec/de4x5.txt
 create mode 100644 Documentation/networking/device_drivers/dec/dmfe.txt
 create mode 100644 Documentation/networking/device_drivers/dlink/dl2k.txt
 create mode 100644 Documentation/networking/device_drivers/freescale/dpaa.txt
 create mode 100644 Documentation/networking/device_drivers/freescale/dpaa2/dpio-driver.rst
 create mode 100644 Documentation/networking/device_drivers/freescale/dpaa2/ethernet-driver.rst
 create mode 100644 Documentation/networking/device_drivers/freescale/dpaa2/index.rst
 create mode 100644 Documentation/networking/device_drivers/freescale/dpaa2/overview.rst
 create mode 100644 Documentation/networking/device_drivers/freescale/gianfar.txt
 create mode 100644 Documentation/networking/device_drivers/intel/e100.rst
 create mode 100644 Documentation/networking/device_drivers/intel/e1000.rst
 create mode 100644 Documentation/networking/device_drivers/intel/e1000e.rst
 create mode 100644 Documentation/networking/device_drivers/intel/fm10k.rst
 create mode 100644 Documentation/networking/device_drivers/intel/i40e.rst
 create mode 100644 Documentation/networking/device_drivers/intel/iavf.rst
 create mode 100644 Documentation/networking/device_drivers/intel/ice.rst
 create mode 100644 Documentation/networking/device_drivers/intel/igb.rst
 create mode 100644 Documentation/networking/device_drivers/intel/igbvf.rst
 create mode 100644 Documentation/networking/device_drivers/intel/ipw2100.txt
 create mode 100644 Documentation/networking/device_drivers/intel/ipw2200.txt
 create mode 100644 Documentation/networking/device_drivers/intel/ixgb.rst
 create mode 100644 Documentation/networking/device_drivers/intel/ixgbe.rst
 create mode 100644 Documentation/networking/device_drivers/intel/ixgbevf.rst
 create mode 100644 Documentation/networking/device_drivers/microsoft/netvsc.txt
 create mode 100644 Documentation/networking/device_drivers/neterion/s2io.txt
 create mode 100644 Documentation/networking/device_drivers/neterion/vxge.txt
 create mode 100644 Documentation/networking/device_drivers/qlogic/LICENSE.qla3xxx
 create mode 100644 Documentation/networking/device_drivers/qlogic/LICENSE.qlcnic
 create mode 100644 Documentation/networking/device_drivers/qlogic/LICENSE.qlge
 create mode 100644 Documentation/networking/device_drivers/qualcomm/rmnet.txt
 create mode 100644 Documentation/networking/device_drivers/sb1000.txt
 create mode 100644 Documentation/networking/device_drivers/smsc/smc9.txt
 create mode 100644 Documentation/networking/device_drivers/stmicro/stmmac.txt
 create mode 100644 Documentation/networking/device_drivers/ti/cpsw.txt
 create mode 100644 Documentation/networking/device_drivers/ti/tlan.txt
 create mode 100644 Documentation/networking/device_drivers/toshiba/spider_net.txt
 delete mode 100644 Documentation/networking/dl2k.txt
 delete mode 100644 Documentation/networking/dm9000.txt
 delete mode 100644 Documentation/networking/dmfe.txt
 delete mode 100644 Documentation/networking/dpaa.txt
 delete mode 100644 Documentation/networking/dpaa2/dpio-driver.rst
 delete mode 100644 Documentation/networking/dpaa2/ethernet-driver.rst
 delete mode 100644 Documentation/networking/dpaa2/index.rst
 delete mode 100644 Documentation/networking/dpaa2/overview.rst
 delete mode 100644 Documentation/networking/e100.rst
 delete mode 100644 Documentation/networking/e1000.rst
 delete mode 100644 Documentation/networking/e1000e.rst
 delete mode 100644 Documentation/networking/ena.txt
 delete mode 100644 Documentation/networking/fm10k.rst
 delete mode 100644 Documentation/networking/gianfar.txt
 delete mode 100644 Documentation/networking/i40e.rst
 delete mode 100644 Documentation/networking/iavf.rst
 delete mode 100644 Documentation/networking/ice.rst
 delete mode 100644 Documentation/networking/igb.rst
 delete mode 100644 Documentation/networking/igbvf.rst
 delete mode 100644 Documentation/networking/ixgb.rst
 delete mode 100644 Documentation/networking/ixgbe.rst
 delete mode 100644 Documentation/networking/ixgbevf.rst
 delete mode 100644 Documentation/networking/netvsc.txt
 delete mode 100644 Documentation/networking/rmnet.txt
 delete mode 100644 Documentation/networking/s2io.txt
 delete mode 100644 Documentation/networking/smc9.txt
 delete mode 100644 Documentation/networking/spider_net.txt
 delete mode 100644 Documentation/networking/stmmac.txt
 delete mode 100644 Documentation/networking/ti-cpsw.txt
 delete mode 100644 Documentation/networking/tlan.txt
 delete mode 100644 Documentation/networking/vortex.txt
 delete mode 100644 Documentation/networking/vxge.txt

diff --git a/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt b/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt
index 01fdc33a41d0..bb7e896cb644 100644
--- a/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt
+++ b/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt
@@ -10,7 +10,7 @@ such as network interfaces, crypto accelerator instances, L2 switches,
 etc.
 
 For an overview of the DPAA2 architecture and fsl-mc bus see:
-Documentation/networking/dpaa2/overview.rst
+Documentation/networking/device_drivers/freescale/dpaa2/overview.rst
 
 As described in the above overview, all DPAA2 objects in a DPRC share the
 same hardware "isolation context" and a 10-bit value called an ICID
diff --git a/Documentation/networking/3c509.txt b/Documentation/networking/3c509.txt
deleted file mode 100644
index fbf722e15ac3..000000000000
--- a/Documentation/networking/3c509.txt
+++ /dev/null
@@ -1,213 +0,0 @@
-Linux and the 3Com EtherLink III Series Ethercards (driver v1.18c and higher)
-----------------------------------------------------------------------------
-
-This file contains the instructions and caveats for v1.18c and higher versions
-of the 3c509 driver. You should not use the driver without reading this file.
-
-release 1.0
-28 February 2002
-Current maintainer (corrections to):
-  David Ruggiero <jdr@farfalle.com>
-
-----------------------------------------------------------------------------
-
-(0) Introduction
-
-The following are notes and information on using the 3Com EtherLink III series
-ethercards in Linux. These cards are commonly known by the most widely-used
-card's 3Com model number, 3c509. They are all 10mb/s ISA-bus cards and shouldn't
-be (but sometimes are) confused with the similarly-numbered PCI-bus "3c905"
-(aka "Vortex" or "Boomerang") series.  Kernel support for the 3c509 family is
-provided by the module 3c509.c, which has code to support all of the following
-models:
-
-  3c509 (original ISA card)
-  3c509B (later revision of the ISA card; supports full-duplex)
-  3c589 (PCMCIA)
-  3c589B (later revision of the 3c589; supports full-duplex)
-  3c579 (EISA)
-
-Large portions of this documentation were heavily borrowed from the guide
-written the original author of the 3c509 driver, Donald Becker. The master
-copy of that document, which contains notes on older versions of the driver,
-currently resides on Scyld web server: http://www.scyld.com/.
-
-
-(1) Special Driver Features
-
-Overriding card settings
-
-The driver allows boot- or load-time overriding of the card's detected IOADDR,
-IRQ, and transceiver settings, although this capability shouldn't generally be
-needed except to enable full-duplex mode (see below). An example of the syntax
-for LILO parameters for doing this:
-
-    ether=10,0x310,3,0x3c509,eth0 
-
-This configures the first found 3c509 card for IRQ 10, base I/O 0x310, and
-transceiver type 3 (10base2). The flag "0x3c509" must be set to avoid conflicts
-with other card types when overriding the I/O address. When the driver is
-loaded as a module, only the IRQ may be overridden. For example,
-setting two cards to IRQ10 and IRQ11 is done by using the irq module
-option:
-
-   options 3c509 irq=10,11
-
-
-(2) Full-duplex mode
-
-The v1.18c driver added support for the 3c509B's full-duplex capabilities.
-In order to enable and successfully use full-duplex mode, three conditions
-must be met: 
-
-(a) You must have a Etherlink III card model whose hardware supports full-
-duplex operations. Currently, the only members of the 3c509 family that are
-positively known to support full-duplex are the 3c509B (ISA bus) and 3c589B
-(PCMCIA) cards. Cards without the "B" model designation do *not* support
-full-duplex mode; these include the original 3c509 (no "B"), the original
-3c589, the 3c529 (MCA bus), and the 3c579 (EISA bus).
-
-(b) You must be using your card's 10baseT transceiver (i.e., the RJ-45
-connector), not its AUI (thick-net) or 10base2 (thin-net/coax) interfaces.
-AUI and 10base2 network cabling is physically incapable of full-duplex
-operation.
-
-(c) Most importantly, your 3c509B must be connected to a link partner that is
-itself full-duplex capable. This is almost certainly one of two things: a full-
-duplex-capable  Ethernet switch (*not* a hub), or a full-duplex-capable NIC on
-another system that's connected directly to the 3c509B via a crossover cable.
-
-Full-duplex mode can be enabled using 'ethtool'.
- 
-/////Extremely important caution concerning full-duplex mode/////
-Understand that the 3c509B's hardware's full-duplex support is much more
-limited than that provide by more modern network interface cards. Although
-at the physical layer of the network it fully supports full-duplex operation,
-the card was designed before the current Ethernet auto-negotiation (N-way)
-spec was written. This means that the 3c509B family ***cannot and will not
-auto-negotiate a full-duplex connection with its link partner under any
-circumstances, no matter how it is initialized***. If the full-duplex mode
-of the 3c509B is enabled, its link partner will very likely need to be
-independently _forced_ into full-duplex mode as well; otherwise various nasty
-failures will occur - at the very least, you'll see massive numbers of packet
-collisions. This is one of very rare circumstances where disabling auto-
-negotiation and forcing the duplex mode of a network interface card or switch
-would ever be necessary or desirable.
-
-
-(3) Available Transceiver Types
-
-For versions of the driver v1.18c and above, the available transceiver types are:
- 
-0  transceiver type from EEPROM config (normally 10baseT); force half-duplex
-1  AUI (thick-net / DB15 connector)
-2  (undefined)
-3  10base2 (thin-net == coax / BNC connector)
-4  10baseT (RJ-45 connector); force half-duplex mode
-8  transceiver type and duplex mode taken from card's EEPROM config settings
-12 10baseT (RJ-45 connector); force full-duplex mode
-
-Prior to driver version 1.18c, only transceiver codes 0-4 were supported. Note
-that the new transceiver codes 8 and 12 are the *only* ones that will enable
-full-duplex mode, no matter what the card's detected EEPROM settings might be.
-This insured that merely upgrading the driver from an earlier version would
-never automatically enable full-duplex mode in an existing installation;
-it must always be explicitly enabled via one of these code in order to be
-activated.
-
-The transceiver type can be changed using 'ethtool'.
-  
-
-(4a) Interpretation of error messages and common problems
-
-Error Messages
-
-eth0: Infinite loop in interrupt, status 2011. 
-These are "mostly harmless" message indicating that the driver had too much
-work during that interrupt cycle. With a status of 0x2011 you are receiving
-packets faster than they can be removed from the card. This should be rare
-or impossible in normal operation. Possible causes of this error report are:
- 
-   - a "green" mode enabled that slows the processor down when there is no
-     keyboard activity. 
-
-   - some other device or device driver hogging the bus or disabling interrupts.
-     Check /proc/interrupts for excessive interrupt counts. The timer tick
-     interrupt should always be incrementing faster than the others. 
-
-No received packets 
-If a 3c509, 3c562 or 3c589 can successfully transmit packets, but never
-receives packets (as reported by /proc/net/dev or 'ifconfig') you likely
-have an interrupt line problem. Check /proc/interrupts to verify that the
-card is actually generating interrupts. If the interrupt count is not
-increasing you likely have a physical conflict with two devices trying to
-use the same ISA IRQ line. The common conflict is with a sound card on IRQ10
-or IRQ5, and the easiest solution is to move the 3c509 to a different
-interrupt line. If the device is receiving packets but 'ping' doesn't work,
-you have a routing problem.
-
-Tx Carrier Errors Reported in /proc/net/dev 
-If an EtherLink III appears to transmit packets, but the "Tx carrier errors"
-field in /proc/net/dev increments as quickly as the Tx packet count, you
-likely have an unterminated network or the incorrect media transceiver selected. 
-
-3c509B card is not detected on machines with an ISA PnP BIOS. 
-While the updated driver works with most PnP BIOS programs, it does not work
-with all. This can be fixed by disabling PnP support using the 3Com-supplied
-setup program. 
-
-3c509 card is not detected on overclocked machines 
-Increase the delay time in id_read_eeprom() from the current value, 500,
-to an absurdly high value, such as 5000. 
-
-
-(4b) Decoding Status and Error Messages
-
-The bits in the main status register are: 
-
-value 	description
-0x01 	Interrupt latch
-0x02 	Tx overrun, or Rx underrun
-0x04 	Tx complete
-0x08 	Tx FIFO room available
-0x10 	A complete Rx packet has arrived
-0x20 	A Rx packet has started to arrive
-0x40 	The driver has requested an interrupt
-0x80 	Statistics counter nearly full
-
-The bits in the transmit (Tx) status word are: 
-
-value 	description
-0x02 	Out-of-window collision.
-0x04 	Status stack overflow (normally impossible).
-0x08 	16 collisions.
-0x10 	Tx underrun (not enough PCI bus bandwidth).
-0x20 	Tx jabber.
-0x40 	Tx interrupt requested.
-0x80 	Status is valid (this should always be set).
-
-
-When a transmit error occurs the driver produces a status message such as 
-
-   eth0: Transmit error, Tx status register 82
-
-The two values typically seen here are:
-
-0x82 
-Out of window collision. This typically occurs when some other Ethernet
-host is incorrectly set to full duplex on a half duplex network. 
-
-0x88 
-16 collisions. This typically occurs when the network is exceptionally busy
-or when another host doesn't correctly back off after a collision. If this
-error is mixed with 0x82 errors it is the result of a host incorrectly set
-to full duplex (see above).
-
-Both of these errors are the result of network problems that should be
-corrected. They do not represent driver malfunction.
-
-
-(5) Revision history (this file)
-
-28Feb02 v1.0  DR   New; major portions based on Becker original 3c509 docs
-
diff --git a/Documentation/networking/LICENSE.qla3xxx b/Documentation/networking/LICENSE.qla3xxx
deleted file mode 100644
index 2f2077e34d81..000000000000
--- a/Documentation/networking/LICENSE.qla3xxx
+++ /dev/null
@@ -1,46 +0,0 @@
-Copyright (c)  2003-2006 QLogic Corporation
-QLogic Linux Networking HBA Driver
-
-This program includes a device driver for Linux 2.6 that may be
-distributed with QLogic hardware specific firmware binary file.
-You may modify and redistribute the device driver code under the
-GNU General Public License as published by the Free Software
-Foundation (version 2 or a later version).
-
-You may redistribute the hardware specific firmware binary file
-under the following terms:
-
-	1. Redistribution of source code (only if applicable),
-	   must retain the above copyright notice, this list of
-	   conditions and the following disclaimer.
-
-	2. Redistribution in binary form must reproduce the above
-	   copyright notice, this list of conditions and the
-	   following disclaimer in the documentation and/or other
-	   materials provided with the distribution.
-
-	3. The name of QLogic Corporation may not be used to
-	   endorse or promote products derived from this software
-	   without specific prior written permission
-
-REGARDLESS OF WHAT LICENSING MECHANISM IS USED OR APPLICABLE,
-THIS PROGRAM IS PROVIDED BY QLOGIC CORPORATION "AS IS'' AND ANY
-EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
-PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR
-BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
-EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
-TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
-ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
-OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
-
-USER ACKNOWLEDGES AND AGREES THAT USE OF THIS PROGRAM WILL NOT
-CREATE OR GIVE GROUNDS FOR A LICENSE BY IMPLICATION, ESTOPPEL, OR
-OTHERWISE IN ANY INTELLECTUAL PROPERTY RIGHTS (PATENT, COPYRIGHT,
-TRADE SECRET, MASK WORK, OR OTHER PROPRIETARY RIGHT) EMBODIED IN
-ANY OTHER QLOGIC HARDWARE OR SOFTWARE EITHER SOLELY OR IN
-COMBINATION WITH THIS PROGRAM.
-
diff --git a/Documentation/networking/LICENSE.qlcnic b/Documentation/networking/LICENSE.qlcnic
deleted file mode 100644
index 2ae3b64983ab..000000000000
--- a/Documentation/networking/LICENSE.qlcnic
+++ /dev/null
@@ -1,288 +0,0 @@
-Copyright (c) 2009-2013 QLogic Corporation
-QLogic Linux qlcnic NIC Driver
-
-You may modify and redistribute the device driver code under the
-GNU General Public License (a copy of which is attached hereto as
-Exhibit A) published by the Free Software Foundation (version 2).
-
-
-EXHIBIT A
-
-		    GNU GENERAL PUBLIC LICENSE
-		       Version 2, June 1991
-
- Copyright (C) 1989, 1991 Free Software Foundation, Inc.
- 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
- Everyone is permitted to copy and distribute verbatim copies
- of this license document, but changing it is not allowed.
-
-			    Preamble
-
-  The licenses for most software are designed to take away your
-freedom to share and change it.  By contrast, the GNU General Public
-License is intended to guarantee your freedom to share and change free
-software--to make sure the software is free for all its users.  This
-General Public License applies to most of the Free Software
-Foundation's software and to any other program whose authors commit to
-using it.  (Some other Free Software Foundation software is covered by
-the GNU Lesser General Public License instead.)  You can apply it to
-your programs, too.
-
-  When we speak of free software, we are referring to freedom, not
-price.  Our General Public Licenses are designed to make sure that you
-have the freedom to distribute copies of free software (and charge for
-this service if you wish), that you receive source code or can get it
-if you want it, that you can change the software or use pieces of it
-in new free programs; and that you know you can do these things.
-
-  To protect your rights, we need to make restrictions that forbid
-anyone to deny you these rights or to ask you to surrender the rights.
-These restrictions translate to certain responsibilities for you if you
-distribute copies of the software, or if you modify it.
-
-  For example, if you distribute copies of such a program, whether
-gratis or for a fee, you must give the recipients all the rights that
-you have.  You must make sure that they, too, receive or can get the
-source code.  And you must show them these terms so they know their
-rights.
-
-  We protect your rights with two steps: (1) copyright the software, and
-(2) offer you this license which gives you legal permission to copy,
-distribute and/or modify the software.
-
-  Also, for each author's protection and ours, we want to make certain
-that everyone understands that there is no warranty for this free
-software.  If the software is modified by someone else and passed on, we
-want its recipients to know that what they have is not the original, so
-that any problems introduced by others will not reflect on the original
-authors' reputations.
-
-  Finally, any free program is threatened constantly by software
-patents.  We wish to avoid the danger that redistributors of a free
-program will individually obtain patent licenses, in effect making the
-program proprietary.  To prevent this, we have made it clear that any
-patent must be licensed for everyone's free use or not licensed at all.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.
-
-		    GNU GENERAL PUBLIC LICENSE
-   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
-
-  0. This License applies to any program or other work which contains
-a notice placed by the copyright holder saying it may be distributed
-under the terms of this General Public License.  The "Program", below,
-refers to any such program or work, and a "work based on the Program"
-means either the Program or any derivative work under copyright law:
-that is to say, a work containing the Program or a portion of it,
-either verbatim or with modifications and/or translated into another
-language.  (Hereinafter, translation is included without limitation in
-the term "modification".)  Each licensee is addressed as "you".
-
-Activities other than copying, distribution and modification are not
-covered by this License; they are outside its scope.  The act of
-running the Program is not restricted, and the output from the Program
-is covered only if its contents constitute a work based on the
-Program (independent of having been made by running the Program).
-Whether that is true depends on what the Program does.
-
-  1. You may copy and distribute verbatim copies of the Program's
-source code as you receive it, in any medium, provided that you
-conspicuously and appropriately publish on each copy an appropriate
-copyright notice and disclaimer of warranty; keep intact all the
-notices that refer to this License and to the absence of any warranty;
-and give any other recipients of the Program a copy of this License
-along with the Program.
-
-You may charge a fee for the physical act of transferring a copy, and
-you may at your option offer warranty protection in exchange for a fee.
-
-  2. You may modify your copy or copies of the Program or any portion
-of it, thus forming a work based on the Program, and copy and
-distribute such modifications or work under the terms of Section 1
-above, provided that you also meet all of these conditions:
-
-    a) You must cause the modified files to carry prominent notices
-    stating that you changed the files and the date of any change.
-
-    b) You must cause any work that you distribute or publish, that in
-    whole or in part contains or is derived from the Program or any
-    part thereof, to be licensed as a whole at no charge to all third
-    parties under the terms of this License.
-
-    c) If the modified program normally reads commands interactively
-    when run, you must cause it, when started running for such
-    interactive use in the most ordinary way, to print or display an
-    announcement including an appropriate copyright notice and a
-    notice that there is no warranty (or else, saying that you provide
-    a warranty) and that users may redistribute the program under
-    these conditions, and telling the user how to view a copy of this
-    License.  (Exception: if the Program itself is interactive but
-    does not normally print such an announcement, your work based on
-    the Program is not required to print an announcement.)
-
-These requirements apply to the modified work as a whole.  If
-identifiable sections of that work are not derived from the Program,
-and can be reasonably considered independent and separate works in
-themselves, then this License, and its terms, do not apply to those
-sections when you distribute them as separate works.  But when you
-distribute the same sections as part of a whole which is a work based
-on the Program, the distribution of the whole must be on the terms of
-this License, whose permissions for other licensees extend to the
-entire whole, and thus to each and every part regardless of who wrote it.
-
-Thus, it is not the intent of this section to claim rights or contest
-your rights to work written entirely by you; rather, the intent is to
-exercise the right to control the distribution of derivative or
-collective works based on the Program.
-
-In addition, mere aggregation of another work not based on the Program
-with the Program (or with a work based on the Program) on a volume of
-a storage or distribution medium does not bring the other work under
-the scope of this License.
-
-  3. You may copy and distribute the Program (or a work based on it,
-under Section 2) in object code or executable form under the terms of
-Sections 1 and 2 above provided that you also do one of the following:
-
-    a) Accompany it with the complete corresponding machine-readable
-    source code, which must be distributed under the terms of Sections
-    1 and 2 above on a medium customarily used for software interchange; or,
-
-    b) Accompany it with a written offer, valid for at least three
-    years, to give any third party, for a charge no more than your
-    cost of physically performing source distribution, a complete
-    machine-readable copy of the corresponding source code, to be
-    distributed under the terms of Sections 1 and 2 above on a medium
-    customarily used for software interchange; or,
-
-    c) Accompany it with the information you received as to the offer
-    to distribute corresponding source code.  (This alternative is
-    allowed only for noncommercial distribution and only if you
-    received the program in object code or executable form with such
-    an offer, in accord with Subsection b above.)
-
-The source code for a work means the preferred form of the work for
-making modifications to it.  For an executable work, complete source
-code means all the source code for all modules it contains, plus any
-associated interface definition files, plus the scripts used to
-control compilation and installation of the executable.  However, as a
-special exception, the source code distributed need not include
-anything that is normally distributed (in either source or binary
-form) with the major components (compiler, kernel, and so on) of the
-operating system on which the executable runs, unless that component
-itself accompanies the executable.
-
-If distribution of executable or object code is made by offering
-access to copy from a designated place, then offering equivalent
-access to copy the source code from the same place counts as
-distribution of the source code, even though third parties are not
-compelled to copy the source along with the object code.
-
-  4. You may not copy, modify, sublicense, or distribute the Program
-except as expressly provided under this License.  Any attempt
-otherwise to copy, modify, sublicense or distribute the Program is
-void, and will automatically terminate your rights under this License.
-However, parties who have received copies, or rights, from you under
-this License will not have their licenses terminated so long as such
-parties remain in full compliance.
-
-  5. You are not required to accept this License, since you have not
-signed it.  However, nothing else grants you permission to modify or
-distribute the Program or its derivative works.  These actions are
-prohibited by law if you do not accept this License.  Therefore, by
-modifying or distributing the Program (or any work based on the
-Program), you indicate your acceptance of this License to do so, and
-all its terms and conditions for copying, distributing or modifying
-the Program or works based on it.
-
-  6. Each time you redistribute the Program (or any work based on the
-Program), the recipient automatically receives a license from the
-original licensor to copy, distribute or modify the Program subject to
-these terms and conditions.  You may not impose any further
-restrictions on the recipients' exercise of the rights granted herein.
-You are not responsible for enforcing compliance by third parties to
-this License.
-
-  7. If, as a consequence of a court judgment or allegation of patent
-infringement or for any other reason (not limited to patent issues),
-conditions are imposed on you (whether by court order, agreement or
-otherwise) that contradict the conditions of this License, they do not
-excuse you from the conditions of this License.  If you cannot
-distribute so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you
-may not distribute the Program at all.  For example, if a patent
-license would not permit royalty-free redistribution of the Program by
-all those who receive copies directly or indirectly through you, then
-the only way you could satisfy both it and this License would be to
-refrain entirely from distribution of the Program.
-
-If any portion of this section is held invalid or unenforceable under
-any particular circumstance, the balance of the section is intended to
-apply and the section as a whole is intended to apply in other
-circumstances.
-
-It is not the purpose of this section to induce you to infringe any
-patents or other property right claims or to contest validity of any
-such claims; this section has the sole purpose of protecting the
-integrity of the free software distribution system, which is
-implemented by public license practices.  Many people have made
-generous contributions to the wide range of software distributed
-through that system in reliance on consistent application of that
-system; it is up to the author/donor to decide if he or she is willing
-to distribute software through any other system and a licensee cannot
-impose that choice.
-
-This section is intended to make thoroughly clear what is believed to
-be a consequence of the rest of this License.
-
-  8. If the distribution and/or use of the Program is restricted in
-certain countries either by patents or by copyrighted interfaces, the
-original copyright holder who places the Program under this License
-may add an explicit geographical distribution limitation excluding
-those countries, so that distribution is permitted only in or among
-countries not thus excluded.  In such case, this License incorporates
-the limitation as if written in the body of this License.
-
-  9. The Free Software Foundation may publish revised and/or new versions
-of the General Public License from time to time.  Such new versions will
-be similar in spirit to the present version, but may differ in detail to
-address new problems or concerns.
-
-Each version is given a distinguishing version number.  If the Program
-specifies a version number of this License which applies to it and "any
-later version", you have the option of following the terms and conditions
-either of that version or of any later version published by the Free
-Software Foundation.  If the Program does not specify a version number of
-this License, you may choose any version ever published by the Free Software
-Foundation.
-
-  10. If you wish to incorporate parts of the Program into other free
-programs whose distribution conditions are different, write to the author
-to ask for permission.  For software which is copyrighted by the Free
-Software Foundation, write to the Free Software Foundation; we sometimes
-make exceptions for this.  Our decision will be guided by the two goals
-of preserving the free status of all derivatives of our free software and
-of promoting the sharing and reuse of software generally.
-
-			    NO WARRANTY
-
-  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
-FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
-OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
-PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
-OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
-MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
-TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
-PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
-REPAIR OR CORRECTION.
-
-  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
-WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
-REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
-INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
-OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
-TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
-YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
-PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGES.
diff --git a/Documentation/networking/LICENSE.qlge b/Documentation/networking/LICENSE.qlge
deleted file mode 100644
index ce64e4d15b21..000000000000
--- a/Documentation/networking/LICENSE.qlge
+++ /dev/null
@@ -1,288 +0,0 @@
-Copyright (c) 2003-2011 QLogic Corporation
-QLogic Linux qlge NIC Driver
-
-You may modify and redistribute the device driver code under the
-GNU General Public License (a copy of which is attached hereto as
-Exhibit A) published by the Free Software Foundation (version 2).
-
-
-EXHIBIT A
-
-		    GNU GENERAL PUBLIC LICENSE
-		       Version 2, June 1991
-
- Copyright (C) 1989, 1991 Free Software Foundation, Inc.
- 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
- Everyone is permitted to copy and distribute verbatim copies
- of this license document, but changing it is not allowed.
-
-			    Preamble
-
-  The licenses for most software are designed to take away your
-freedom to share and change it.  By contrast, the GNU General Public
-License is intended to guarantee your freedom to share and change free
-software--to make sure the software is free for all its users.  This
-General Public License applies to most of the Free Software
-Foundation's software and to any other program whose authors commit to
-using it.  (Some other Free Software Foundation software is covered by
-the GNU Lesser General Public License instead.)  You can apply it to
-your programs, too.
-
-  When we speak of free software, we are referring to freedom, not
-price.  Our General Public Licenses are designed to make sure that you
-have the freedom to distribute copies of free software (and charge for
-this service if you wish), that you receive source code or can get it
-if you want it, that you can change the software or use pieces of it
-in new free programs; and that you know you can do these things.
-
-  To protect your rights, we need to make restrictions that forbid
-anyone to deny you these rights or to ask you to surrender the rights.
-These restrictions translate to certain responsibilities for you if you
-distribute copies of the software, or if you modify it.
-
-  For example, if you distribute copies of such a program, whether
-gratis or for a fee, you must give the recipients all the rights that
-you have.  You must make sure that they, too, receive or can get the
-source code.  And you must show them these terms so they know their
-rights.
-
-  We protect your rights with two steps: (1) copyright the software, and
-(2) offer you this license which gives you legal permission to copy,
-distribute and/or modify the software.
-
-  Also, for each author's protection and ours, we want to make certain
-that everyone understands that there is no warranty for this free
-software.  If the software is modified by someone else and passed on, we
-want its recipients to know that what they have is not the original, so
-that any problems introduced by others will not reflect on the original
-authors' reputations.
-
-  Finally, any free program is threatened constantly by software
-patents.  We wish to avoid the danger that redistributors of a free
-program will individually obtain patent licenses, in effect making the
-program proprietary.  To prevent this, we have made it clear that any
-patent must be licensed for everyone's free use or not licensed at all.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.
-
-		    GNU GENERAL PUBLIC LICENSE
-   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
-
-  0. This License applies to any program or other work which contains
-a notice placed by the copyright holder saying it may be distributed
-under the terms of this General Public License.  The "Program", below,
-refers to any such program or work, and a "work based on the Program"
-means either the Program or any derivative work under copyright law:
-that is to say, a work containing the Program or a portion of it,
-either verbatim or with modifications and/or translated into another
-language.  (Hereinafter, translation is included without limitation in
-the term "modification".)  Each licensee is addressed as "you".
-
-Activities other than copying, distribution and modification are not
-covered by this License; they are outside its scope.  The act of
-running the Program is not restricted, and the output from the Program
-is covered only if its contents constitute a work based on the
-Program (independent of having been made by running the Program).
-Whether that is true depends on what the Program does.
-
-  1. You may copy and distribute verbatim copies of the Program's
-source code as you receive it, in any medium, provided that you
-conspicuously and appropriately publish on each copy an appropriate
-copyright notice and disclaimer of warranty; keep intact all the
-notices that refer to this License and to the absence of any warranty;
-and give any other recipients of the Program a copy of this License
-along with the Program.
-
-You may charge a fee for the physical act of transferring a copy, and
-you may at your option offer warranty protection in exchange for a fee.
-
-  2. You may modify your copy or copies of the Program or any portion
-of it, thus forming a work based on the Program, and copy and
-distribute such modifications or work under the terms of Section 1
-above, provided that you also meet all of these conditions:
-
-    a) You must cause the modified files to carry prominent notices
-    stating that you changed the files and the date of any change.
-
-    b) You must cause any work that you distribute or publish, that in
-    whole or in part contains or is derived from the Program or any
-    part thereof, to be licensed as a whole at no charge to all third
-    parties under the terms of this License.
-
-    c) If the modified program normally reads commands interactively
-    when run, you must cause it, when started running for such
-    interactive use in the most ordinary way, to print or display an
-    announcement including an appropriate copyright notice and a
-    notice that there is no warranty (or else, saying that you provide
-    a warranty) and that users may redistribute the program under
-    these conditions, and telling the user how to view a copy of this
-    License.  (Exception: if the Program itself is interactive but
-    does not normally print such an announcement, your work based on
-    the Program is not required to print an announcement.)
-
-These requirements apply to the modified work as a whole.  If
-identifiable sections of that work are not derived from the Program,
-and can be reasonably considered independent and separate works in
-themselves, then this License, and its terms, do not apply to those
-sections when you distribute them as separate works.  But when you
-distribute the same sections as part of a whole which is a work based
-on the Program, the distribution of the whole must be on the terms of
-this License, whose permissions for other licensees extend to the
-entire whole, and thus to each and every part regardless of who wrote it.
-
-Thus, it is not the intent of this section to claim rights or contest
-your rights to work written entirely by you; rather, the intent is to
-exercise the right to control the distribution of derivative or
-collective works based on the Program.
-
-In addition, mere aggregation of another work not based on the Program
-with the Program (or with a work based on the Program) on a volume of
-a storage or distribution medium does not bring the other work under
-the scope of this License.
-
-  3. You may copy and distribute the Program (or a work based on it,
-under Section 2) in object code or executable form under the terms of
-Sections 1 and 2 above provided that you also do one of the following:
-
-    a) Accompany it with the complete corresponding machine-readable
-    source code, which must be distributed under the terms of Sections
-    1 and 2 above on a medium customarily used for software interchange; or,
-
-    b) Accompany it with a written offer, valid for at least three
-    years, to give any third party, for a charge no more than your
-    cost of physically performing source distribution, a complete
-    machine-readable copy of the corresponding source code, to be
-    distributed under the terms of Sections 1 and 2 above on a medium
-    customarily used for software interchange; or,
-
-    c) Accompany it with the information you received as to the offer
-    to distribute corresponding source code.  (This alternative is
-    allowed only for noncommercial distribution and only if you
-    received the program in object code or executable form with such
-    an offer, in accord with Subsection b above.)
-
-The source code for a work means the preferred form of the work for
-making modifications to it.  For an executable work, complete source
-code means all the source code for all modules it contains, plus any
-associated interface definition files, plus the scripts used to
-control compilation and installation of the executable.  However, as a
-special exception, the source code distributed need not include
-anything that is normally distributed (in either source or binary
-form) with the major components (compiler, kernel, and so on) of the
-operating system on which the executable runs, unless that component
-itself accompanies the executable.
-
-If distribution of executable or object code is made by offering
-access to copy from a designated place, then offering equivalent
-access to copy the source code from the same place counts as
-distribution of the source code, even though third parties are not
-compelled to copy the source along with the object code.
-
-  4. You may not copy, modify, sublicense, or distribute the Program
-except as expressly provided under this License.  Any attempt
-otherwise to copy, modify, sublicense or distribute the Program is
-void, and will automatically terminate your rights under this License.
-However, parties who have received copies, or rights, from you under
-this License will not have their licenses terminated so long as such
-parties remain in full compliance.
-
-  5. You are not required to accept this License, since you have not
-signed it.  However, nothing else grants you permission to modify or
-distribute the Program or its derivative works.  These actions are
-prohibited by law if you do not accept this License.  Therefore, by
-modifying or distributing the Program (or any work based on the
-Program), you indicate your acceptance of this License to do so, and
-all its terms and conditions for copying, distributing or modifying
-the Program or works based on it.
-
-  6. Each time you redistribute the Program (or any work based on the
-Program), the recipient automatically receives a license from the
-original licensor to copy, distribute or modify the Program subject to
-these terms and conditions.  You may not impose any further
-restrictions on the recipients' exercise of the rights granted herein.
-You are not responsible for enforcing compliance by third parties to
-this License.
-
-  7. If, as a consequence of a court judgment or allegation of patent
-infringement or for any other reason (not limited to patent issues),
-conditions are imposed on you (whether by court order, agreement or
-otherwise) that contradict the conditions of this License, they do not
-excuse you from the conditions of this License.  If you cannot
-distribute so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you
-may not distribute the Program at all.  For example, if a patent
-license would not permit royalty-free redistribution of the Program by
-all those who receive copies directly or indirectly through you, then
-the only way you could satisfy both it and this License would be to
-refrain entirely from distribution of the Program.
-
-If any portion of this section is held invalid or unenforceable under
-any particular circumstance, the balance of the section is intended to
-apply and the section as a whole is intended to apply in other
-circumstances.
-
-It is not the purpose of this section to induce you to infringe any
-patents or other property right claims or to contest validity of any
-such claims; this section has the sole purpose of protecting the
-integrity of the free software distribution system, which is
-implemented by public license practices.  Many people have made
-generous contributions to the wide range of software distributed
-through that system in reliance on consistent application of that
-system; it is up to the author/donor to decide if he or she is willing
-to distribute software through any other system and a licensee cannot
-impose that choice.
-
-This section is intended to make thoroughly clear what is believed to
-be a consequence of the rest of this License.
-
-  8. If the distribution and/or use of the Program is restricted in
-certain countries either by patents or by copyrighted interfaces, the
-original copyright holder who places the Program under this License
-may add an explicit geographical distribution limitation excluding
-those countries, so that distribution is permitted only in or among
-countries not thus excluded.  In such case, this License incorporates
-the limitation as if written in the body of this License.
-
-  9. The Free Software Foundation may publish revised and/or new versions
-of the General Public License from time to time.  Such new versions will
-be similar in spirit to the present version, but may differ in detail to
-address new problems or concerns.
-
-Each version is given a distinguishing version number.  If the Program
-specifies a version number of this License which applies to it and "any
-later version", you have the option of following the terms and conditions
-either of that version or of any later version published by the Free
-Software Foundation.  If the Program does not specify a version number of
-this License, you may choose any version ever published by the Free Software
-Foundation.
-
-  10. If you wish to incorporate parts of the Program into other free
-programs whose distribution conditions are different, write to the author
-to ask for permission.  For software which is copyrighted by the Free
-Software Foundation, write to the Free Software Foundation; we sometimes
-make exceptions for this.  Our decision will be guided by the two goals
-of preserving the free status of all derivatives of our free software and
-of promoting the sharing and reuse of software generally.
-
-			    NO WARRANTY
-
-  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
-FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
-OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
-PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
-OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
-MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
-TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
-PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
-REPAIR OR CORRECTION.
-
-  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
-WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
-REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
-INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
-OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
-TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
-YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
-PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGES.
diff --git a/Documentation/networking/README.ipw2100 b/Documentation/networking/README.ipw2100
deleted file mode 100644
index 6f85e1d06031..000000000000
--- a/Documentation/networking/README.ipw2100
+++ /dev/null
@@ -1,293 +0,0 @@
-
-Intel(R) PRO/Wireless 2100 Driver for Linux in support of:
-
-Intel(R) PRO/Wireless 2100 Network Connection
-
-Copyright (C) 2003-2006, Intel Corporation
-
-README.ipw2100
-
-Version: git-1.1.5
-Date   : January 25, 2006
-
-Index
------------------------------------------------
-0. IMPORTANT INFORMATION BEFORE USING THIS DRIVER
-1. Introduction
-2. Release git-1.1.5 Current Features
-3. Command Line Parameters
-4. Sysfs Helper Files
-5. Radio Kill Switch
-6. Dynamic Firmware
-7. Power Management
-8. Support
-9. License
-
-
-0.   IMPORTANT INFORMATION BEFORE USING THIS DRIVER
------------------------------------------------
-
-Important Notice FOR ALL USERS OR DISTRIBUTORS!!!!
-
-Intel wireless LAN adapters are engineered, manufactured, tested, and
-quality checked to ensure that they meet all necessary local and
-governmental regulatory agency requirements for the regions that they
-are designated and/or marked to ship into. Since wireless LANs are
-generally unlicensed devices that share spectrum with radars,
-satellites, and other licensed and unlicensed devices, it is sometimes
-necessary to dynamically detect, avoid, and limit usage to avoid
-interference with these devices. In many instances Intel is required to
-provide test data to prove regional and local compliance to regional and
-governmental regulations before certification or approval to use the
-product is granted. Intel's wireless LAN's EEPROM, firmware, and
-software driver are designed to carefully control parameters that affect
-radio operation and to ensure electromagnetic compliance (EMC). These
-parameters include, without limitation, RF power, spectrum usage,
-channel scanning, and human exposure.
-
-For these reasons Intel cannot permit any manipulation by third parties
-of the software provided in binary format with the wireless WLAN
-adapters (e.g., the EEPROM and firmware). Furthermore, if you use any
-patches, utilities, or code with the Intel wireless LAN adapters that
-have been manipulated by an unauthorized party (i.e., patches,
-utilities, or code (including open source code modifications) which have
-not been validated by Intel), (i) you will be solely responsible for
-ensuring the regulatory compliance of the products, (ii) Intel will bear
-no liability, under any theory of liability for any issues associated
-with the modified products, including without limitation, claims under
-the warranty and/or issues arising from regulatory non-compliance, and
-(iii) Intel will not provide or be required to assist in providing
-support to any third parties for such modified products.
-
-Note: Many regulatory agencies consider Wireless LAN adapters to be
-modules, and accordingly, condition system-level regulatory approval
-upon receipt and review of test data documenting that the antennas and
-system configuration do not cause the EMC and radio operation to be
-non-compliant.
-
-The drivers available for download from SourceForge are provided as a
-part of a development project.  Conformance to local regulatory
-requirements is the responsibility of the individual developer.  As
-such, if you are interested in deploying or shipping a driver as part of
-solution intended to be used for purposes other than development, please
-obtain a tested driver from Intel Customer Support at:
-
-http://www.intel.com/support/wireless/sb/CS-006408.htm
-
-1. Introduction
------------------------------------------------
-
-This document provides a brief overview of the features supported by the 
-IPW2100 driver project.  The main project website, where the latest 
-development version of the driver can be found, is:
-
-	http://ipw2100.sourceforge.net
-
-There you can find the not only the latest releases, but also information about
-potential fixes and patches, as well as links to the development mailing list
-for the driver project.
-
-
-2. Release git-1.1.5 Current Supported Features
------------------------------------------------
-- Managed (BSS) and Ad-Hoc (IBSS)
-- WEP (shared key and open)
-- Wireless Tools support 
-- 802.1x (tested with XSupplicant 1.0.1)
-
-Enabled (but not supported) features:
-- Monitor/RFMon mode
-- WPA/WPA2
-
-The distinction between officially supported and enabled is a reflection
-on the amount of validation and interoperability testing that has been
-performed on a given feature.
-
-
-3. Command Line Parameters
------------------------------------------------
-
-If the driver is built as a module, the following optional parameters are used
-by entering them on the command line with the modprobe command using this
-syntax:
-
-	modprobe ipw2100 [<option>=<VAL1><,VAL2>...]
-
-For example, to disable the radio on driver loading, enter:
-
-	modprobe ipw2100 disable=1
-
-The ipw2100 driver supports the following module parameters:
-
-Name		Value		Example:
-debug		0x0-0xffffffff	debug=1024
-mode		0,1,2		mode=1   /* AdHoc */
-channel		int		channel=3 /* Only valid in AdHoc or Monitor */
-associate	boolean		associate=0 /* Do NOT auto associate */
-disable		boolean		disable=1 /* Do not power the HW */
-
-
-4. Sysfs Helper Files
----------------------------     
------------------------------------------------
-
-There are several ways to control the behavior of the driver.  Many of the 
-general capabilities are exposed through the Wireless Tools (iwconfig).  There
-are a few capabilities that are exposed through entries in the Linux Sysfs.
-
-
------ Driver Level ------
-For the driver level files, look in /sys/bus/pci/drivers/ipw2100/
-
-  debug_level  
-	
-	This controls the same global as the 'debug' module parameter.  For 
-        information on the various debugging levels available, run the 'dvals'
-	script found in the driver source directory.
-
-	NOTE:  'debug_level' is only enabled if CONFIG_IPW2100_DEBUG is turn
-	       on.
-
------ Device Level ------
-For the device level files look in
-	
-	/sys/bus/pci/drivers/ipw2100/{PCI-ID}/
-
-For example:
-	/sys/bus/pci/drivers/ipw2100/0000:02:01.0
-
-For the device level files, see /sys/bus/pci/drivers/ipw2100:
-
-  rf_kill
-	read - 
-	0 = RF kill not enabled (radio on)
-	1 = SW based RF kill active (radio off)
-	2 = HW based RF kill active (radio off)
-	3 = Both HW and SW RF kill active (radio off)
-	write -
-	0 = If SW based RF kill active, turn the radio back on
-	1 = If radio is on, activate SW based RF kill
-
-	NOTE: If you enable the SW based RF kill and then toggle the HW
-  	based RF kill from ON -> OFF -> ON, the radio will NOT come back on
-
-
-5. Radio Kill Switch
------------------------------------------------
-Most laptops provide the ability for the user to physically disable the radio.
-Some vendors have implemented this as a physical switch that requires no
-software to turn the radio off and on.  On other laptops, however, the switch
-is controlled through a button being pressed and a software driver then making
-calls to turn the radio off and on.  This is referred to as a "software based
-RF kill switch"
-
-See the Sysfs helper file 'rf_kill' for determining the state of the RF switch
-on your system.
-
-
-6. Dynamic Firmware
------------------------------------------------
-As the firmware is licensed under a restricted use license, it can not be 
-included within the kernel sources.  To enable the IPW2100 you will need a 
-firmware image to load into the wireless NIC's processors.
-
-You can obtain these images from <http://ipw2100.sf.net/firmware.php>.
-
-See INSTALL for instructions on installing the firmware.
-
-
-7. Power Management
------------------------------------------------
-The IPW2100 supports the configuration of the Power Save Protocol 
-through a private wireless extension interface.  The IPW2100 supports 
-the following different modes:
-
-	off	No power management.  Radio is always on.
-	on	Automatic power management
-	1-5	Different levels of power management.  The higher the 
-		number the greater the power savings, but with an impact to 
-		packet latencies. 
-
-Power management works by powering down the radio after a certain 
-interval of time has passed where no packets are passed through the 
-radio.  Once powered down, the radio remains in that state for a given 
-period of time.  For higher power savings, the interval between last 
-packet processed to sleep is shorter and the sleep period is longer.
-
-When the radio is asleep, the access point sending data to the station 
-must buffer packets at the AP until the station wakes up and requests 
-any buffered packets.  If you have an AP that does not correctly support 
-the PSP protocol you may experience packet loss or very poor performance 
-while power management is enabled.  If this is the case, you will need 
-to try and find a firmware update for your AP, or disable power 
-management (via `iwconfig eth1 power off`)
-
-To configure the power level on the IPW2100 you use a combination of 
-iwconfig and iwpriv.  iwconfig is used to turn power management on, off, 
-and set it to auto.
-
-	iwconfig eth1 power off    Disables radio power down
-	iwconfig eth1 power on     Enables radio power management to 
-				   last set level (defaults to AUTO)
-	iwpriv eth1 set_power 0    Sets power level to AUTO and enables 
-				   power management if not previously 
-				   enabled.
-	iwpriv eth1 set_power 1-5  Set the power level as specified, 
-				   enabling power management if not 
-				   previously enabled.
-
-You can view the current power level setting via:
-	
-	iwpriv eth1 get_power
-
-It will return the current period or timeout that is configured as a string
-in the form of xxxx/yyyy (z) where xxxx is the timeout interval (amount of
-time after packet processing), yyyy is the period to sleep (amount of time to 
-wait before powering the radio and querying the access point for buffered
-packets), and z is the 'power level'.  If power management is turned off the
-xxxx/yyyy will be replaced with 'off' -- the level reported will be the active
-level if `iwconfig eth1 power on` is invoked.
-
-
-8. Support
------------------------------------------------
-
-For general development information and support,
-go to:
-	
-    http://ipw2100.sf.net/
-
-The ipw2100 1.1.0 driver and firmware can be downloaded from:  
-
-    http://support.intel.com
-
-For installation support on the ipw2100 1.1.0 driver on Linux kernels 
-2.6.8 or greater, email support is available from:  
-
-    http://supportmail.intel.com
-
-9. License
------------------------------------------------
-
-  Copyright(c) 2003 - 2006 Intel Corporation. All rights reserved.
-
-  This program is free software; you can redistribute it and/or modify it 
-  under the terms of the GNU General Public License (version 2) as 
-  published by the Free Software Foundation.
-  
-  This program is distributed in the hope that it will be useful, but WITHOUT 
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for 
-  more details.
-  
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, write to the Free Software Foundation, Inc., 59 
-  Temple Place - Suite 330, Boston, MA  02111-1307, USA.
-  
-  The full GNU General Public License is included in this distribution in the
-  file called LICENSE.
-  
-  License Contact Information:
-  James P. Ketrenos <ipw2100-admin@linux.intel.com>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
diff --git a/Documentation/networking/README.ipw2200 b/Documentation/networking/README.ipw2200
deleted file mode 100644
index b7658bed4906..000000000000
--- a/Documentation/networking/README.ipw2200
+++ /dev/null
@@ -1,472 +0,0 @@
-
-Intel(R) PRO/Wireless 2915ABG Driver for Linux in support of:
-
-Intel(R) PRO/Wireless 2200BG Network Connection
-Intel(R) PRO/Wireless 2915ABG Network Connection
-
-Note: The Intel(R) PRO/Wireless 2915ABG Driver for Linux and Intel(R)
-PRO/Wireless 2200BG Driver for Linux is a unified driver that works on
-both hardware adapters listed above. In this document the Intel(R)
-PRO/Wireless 2915ABG Driver for Linux will be used to reference the
-unified driver.
-
-Copyright (C) 2004-2006, Intel Corporation
-
-README.ipw2200
-
-Version: 1.1.2
-Date   : March 30, 2006
-
-
-Index
------------------------------------------------
-0.   IMPORTANT INFORMATION BEFORE USING THIS DRIVER
-1.   Introduction
-1.1. Overview of features
-1.2. Module parameters
-1.3. Wireless Extension Private Methods
-1.4. Sysfs Helper Files
-1.5. Supported channels
-2.   Ad-Hoc Networking
-3.   Interacting with Wireless Tools
-3.1. iwconfig mode
-3.2. iwconfig sens
-4.   About the Version Numbers
-5.   Firmware installation
-6.   Support
-7.   License
-
-
-0.   IMPORTANT INFORMATION BEFORE USING THIS DRIVER
------------------------------------------------
-
-Important Notice FOR ALL USERS OR DISTRIBUTORS!!!! 
-
-Intel wireless LAN adapters are engineered, manufactured, tested, and
-quality checked to ensure that they meet all necessary local and
-governmental regulatory agency requirements for the regions that they
-are designated and/or marked to ship into. Since wireless LANs are
-generally unlicensed devices that share spectrum with radars,
-satellites, and other licensed and unlicensed devices, it is sometimes
-necessary to dynamically detect, avoid, and limit usage to avoid
-interference with these devices. In many instances Intel is required to
-provide test data to prove regional and local compliance to regional and
-governmental regulations before certification or approval to use the
-product is granted. Intel's wireless LAN's EEPROM, firmware, and
-software driver are designed to carefully control parameters that affect
-radio operation and to ensure electromagnetic compliance (EMC). These
-parameters include, without limitation, RF power, spectrum usage,
-channel scanning, and human exposure. 
-
-For these reasons Intel cannot permit any manipulation by third parties
-of the software provided in binary format with the wireless WLAN
-adapters (e.g., the EEPROM and firmware). Furthermore, if you use any
-patches, utilities, or code with the Intel wireless LAN adapters that
-have been manipulated by an unauthorized party (i.e., patches,
-utilities, or code (including open source code modifications) which have
-not been validated by Intel), (i) you will be solely responsible for
-ensuring the regulatory compliance of the products, (ii) Intel will bear
-no liability, under any theory of liability for any issues associated
-with the modified products, including without limitation, claims under
-the warranty and/or issues arising from regulatory non-compliance, and
-(iii) Intel will not provide or be required to assist in providing
-support to any third parties for such modified products.  
-
-Note: Many regulatory agencies consider Wireless LAN adapters to be
-modules, and accordingly, condition system-level regulatory approval
-upon receipt and review of test data documenting that the antennas and
-system configuration do not cause the EMC and radio operation to be
-non-compliant.
-
-The drivers available for download from SourceForge are provided as a 
-part of a development project.  Conformance to local regulatory 
-requirements is the responsibility of the individual developer.  As 
-such, if you are interested in deploying or shipping a driver as part of 
-solution intended to be used for purposes other than development, please 
-obtain a tested driver from Intel Customer Support at:
-
-http://support.intel.com
-
-
-1.   Introduction
------------------------------------------------
-The following sections attempt to provide a brief introduction to using 
-the Intel(R) PRO/Wireless 2915ABG Driver for Linux.
-
-This document is not meant to be a comprehensive manual on 
-understanding or using wireless technologies, but should be sufficient 
-to get you moving without wires on Linux.
-
-For information on building and installing the driver, see the INSTALL
-file.
-
-
-1.1. Overview of Features
------------------------------------------------
-The current release (1.1.2) supports the following features:
-
-+ BSS mode (Infrastructure, Managed)
-+ IBSS mode (Ad-Hoc)
-+ WEP (OPEN and SHARED KEY mode)
-+ 802.1x EAP via wpa_supplicant and xsupplicant
-+ Wireless Extension support 
-+ Full B and G rate support (2200 and 2915)
-+ Full A rate support (2915 only)
-+ Transmit power control
-+ S state support (ACPI suspend/resume)
-
-The following features are currently enabled, but not officially
-supported:
-
-+ WPA
-+ long/short preamble support
-+ Monitor mode (aka RFMon)
-
-The distinction between officially supported and enabled is a reflection 
-on the amount of validation and interoperability testing that has been
-performed on a given feature. 
-
-
-
-1.2. Command Line Parameters
------------------------------------------------
-
-Like many modules used in the Linux kernel, the Intel(R) PRO/Wireless
-2915ABG Driver for Linux allows configuration options to be provided 
-as module parameters.  The most common way to specify a module parameter 
-is via the command line.  
-
-The general form is:
-
-% modprobe ipw2200 parameter=value
-
-Where the supported parameter are:
-
-  associate
-	Set to 0 to disable the auto scan-and-associate functionality of the
-	driver.  If disabled, the driver will not attempt to scan 
-	for and associate to a network until it has been configured with 
-	one or more properties for the target network, for example configuring 
-	the network SSID.  Default is 0 (do not auto-associate)
-	
-	Example: % modprobe ipw2200 associate=0
-
-  auto_create
-	Set to 0 to disable the auto creation of an Ad-Hoc network 
-	matching the channel and network name parameters provided.  
-	Default is 1.
-
-  channel
-	channel number for association.  The normal method for setting
-        the channel would be to use the standard wireless tools
-        (i.e. `iwconfig eth1 channel 10`), but it is useful sometimes
-	to set this while debugging.  Channel 0 means 'ANY'
-
-  debug
-	If using a debug build, this is used to control the amount of debug
-	info is logged.  See the 'dvals' and 'load' script for more info on
-	how to use this (the dvals and load scripts are provided as part 
-	of the ipw2200 development snapshot releases available from the 
-	SourceForge project at http://ipw2200.sf.net)
-  
-  led
-	Can be used to turn on experimental LED code.
-	0 = Off, 1 = On.  Default is 1.
-
-  mode
-	Can be used to set the default mode of the adapter.  
-	0 = Managed, 1 = Ad-Hoc, 2 = Monitor
-
-
-1.3. Wireless Extension Private Methods
------------------------------------------------
-
-As an interface designed to handle generic hardware, there are certain 
-capabilities not exposed through the normal Wireless Tool interface.  As 
-such, a provision is provided for a driver to declare custom, or 
-private, methods.  The Intel(R) PRO/Wireless 2915ABG Driver for Linux 
-defines several of these to configure various settings.
-
-The general form of using the private wireless methods is:
-
-	% iwpriv $IFNAME method parameters
-
-Where $IFNAME is the interface name the device is registered with 
-(typically eth1, customized via one of the various network interface
-name managers, such as ifrename)
-
-The supported private methods are:
-
-  get_mode
-	Can be used to report out which IEEE mode the driver is 
-	configured to support.  Example:
-	
-	% iwpriv eth1 get_mode
-	eth1	get_mode:802.11bg (6)
-
-  set_mode
-	Can be used to configure which IEEE mode the driver will 
-	support.  
-
-	Usage:
-	% iwpriv eth1 set_mode {mode}
-	Where {mode} is a number in the range 1-7:
-	1	802.11a (2915 only)
-	2	802.11b
-	3	802.11ab (2915 only)
-	4	802.11g 
-	5	802.11ag (2915 only)
-	6	802.11bg
-	7	802.11abg (2915 only)
-
-  get_preamble
-	Can be used to report configuration of preamble length.
-
-  set_preamble
-	Can be used to set the configuration of preamble length:
-
-	Usage:
-	% iwpriv eth1 set_preamble {mode}
-	Where {mode} is one of:
-	1	Long preamble only
-	0	Auto (long or short based on connection)
-	
-
-1.4. Sysfs Helper Files:
------------------------------------------------
-
-The Linux kernel provides a pseudo file system that can be used to 
-access various components of the operating system.  The Intel(R)
-PRO/Wireless 2915ABG Driver for Linux exposes several configuration
-parameters through this mechanism.
-
-An entry in the sysfs can support reading and/or writing.  You can 
-typically query the contents of a sysfs entry through the use of cat, 
-and can set the contents via echo.  For example:
-
-% cat /sys/bus/pci/drivers/ipw2200/debug_level
-
-Will report the current debug level of the driver's logging subsystem 
-(only available if CONFIG_IPW2200_DEBUG was configured when the driver
-was built).
-
-You can set the debug level via:
-
-% echo $VALUE > /sys/bus/pci/drivers/ipw2200/debug_level
-
-Where $VALUE would be a number in the case of this sysfs entry.  The 
-input to sysfs files does not have to be a number.  For example, the 
-firmware loader used by hotplug utilizes sysfs entries for transferring 
-the firmware image from user space into the driver.
-
-The Intel(R) PRO/Wireless 2915ABG Driver for Linux exposes sysfs entries 
-at two levels -- driver level, which apply to all instances of the driver 
-(in the event that there are more than one device installed) and device 
-level, which applies only to the single specific instance.
-
-
-1.4.1 Driver Level Sysfs Helper Files
------------------------------------------------
-
-For the driver level files, look in /sys/bus/pci/drivers/ipw2200/
-
-  debug_level  
-	
-	This controls the same global as the 'debug' module parameter
-
-
-
-1.4.2 Device Level Sysfs Helper Files
------------------------------------------------
-
-For the device level files, look in
-	
-	/sys/bus/pci/drivers/ipw2200/{PCI-ID}/
-
-For example:
-	/sys/bus/pci/drivers/ipw2200/0000:02:01.0
-
-For the device level files, see /sys/bus/pci/drivers/ipw2200:
-
-  rf_kill
-	read - 
-	0 = RF kill not enabled (radio on)
-	1 = SW based RF kill active (radio off)
-	2 = HW based RF kill active (radio off)
-	3 = Both HW and SW RF kill active (radio off)
-	write -
-	0 = If SW based RF kill active, turn the radio back on
-	1 = If radio is on, activate SW based RF kill
-
-	NOTE: If you enable the SW based RF kill and then toggle the HW
-  	based RF kill from ON -> OFF -> ON, the radio will NOT come back on
-	
-  ucode 
-	read-only access to the ucode version number
-
-  led
-	read -
-	0 = LED code disabled
-	1 = LED code enabled
-	write -
-	0 = Disable LED code
-	1 = Enable LED code
-
-	NOTE: The LED code has been reported to hang some systems when 
-	running ifconfig and is therefore disabled by default.
-
-
-1.5. Supported channels
------------------------------------------------
-
-Upon loading the Intel(R) PRO/Wireless 2915ABG Driver for Linux, a
-message stating the detected geography code and the number of 802.11
-channels supported by the card will be displayed in the log.
-
-The geography code corresponds to a regulatory domain as shown in the
-table below.
-
-					  Supported channels
-Code	Geography			802.11bg	802.11a
-
----	Restricted			11 	 	 0
-ZZF	Custom US/Canada		11	 	 8
-ZZD	Rest of World			13	 	 0
-ZZA	Custom USA & Europe & High	11		13
-ZZB	Custom NA & Europe    		11		13
-ZZC	Custom Japan			11	 	 4
-ZZM	Custom 				11	 	 0
-ZZE	Europe				13		19
-ZZJ	Custom Japan			14	 	 4
-ZZR	Rest of World			14	 	 0
-ZZH	High Band			13	 	 4
-ZZG	Custom Europe			13	 	 4
-ZZK	Europe 				13		24
-ZZL	Europe				11		13
-
-
-2.   Ad-Hoc Networking
------------------------------------------------
-
-When using a device in an Ad-Hoc network, it is useful to understand the 
-sequence and requirements for the driver to be able to create, join, or 
-merge networks.
-
-The following attempts to provide enough information so that you can 
-have a consistent experience while using the driver as a member of an 
-Ad-Hoc network.
-
-2.1. Joining an Ad-Hoc Network
------------------------------------------------
-
-The easiest way to get onto an Ad-Hoc network is to join one that 
-already exists.
-
-2.2. Creating an Ad-Hoc Network
------------------------------------------------
-
-An Ad-Hoc networks is created using the syntax of the Wireless tool.
-
-For Example:
-iwconfig eth1 mode ad-hoc essid testing channel 2
-
-2.3. Merging Ad-Hoc Networks
------------------------------------------------
-
-
-3.  Interaction with Wireless Tools
------------------------------------------------
-
-3.1 iwconfig mode
------------------------------------------------
-
-When configuring the mode of the adapter, all run-time configured parameters
-are reset to the value used when the module was loaded.  This includes
-channels, rates, ESSID, etc.
-
-3.2 iwconfig sens
------------------------------------------------
-
-The 'iwconfig ethX sens XX' command will not set the signal sensitivity
-threshold, as described in iwconfig documentation, but rather the number
-of consecutive missed beacons that will trigger handover, i.e. roaming
-to another access point. At the same time, it will set the disassociation
-threshold to 3 times the given value.
-
-
-4.   About the Version Numbers
------------------------------------------------
-
-Due to the nature of open source development projects, there are 
-frequently changes being incorporated that have not gone through 
-a complete validation process.  These changes are incorporated into 
-development snapshot releases.
-
-Releases are numbered with a three level scheme: 
-
-	major.minor.development
-
-Any version where the 'development' portion is 0 (for example
-1.0.0, 1.1.0, etc.) indicates a stable version that will be made 
-available for kernel inclusion.
-
-Any version where the 'development' portion is not a 0 (for
-example 1.0.1, 1.1.5, etc.) indicates a development version that is
-being made available for testing and cutting edge users.  The stability 
-and functionality of the development releases are not know.  We make
-efforts to try and keep all snapshots reasonably stable, but due to the
-frequency of their release, and the desire to get those releases 
-available as quickly as possible, unknown anomalies should be expected.
-
-The major version number will be incremented when significant changes
-are made to the driver.  Currently, there are no major changes planned.
-
-5.  Firmware installation
-----------------------------------------------
-
-The driver requires a firmware image, download it and extract the
-files under /lib/firmware (or wherever your hotplug's firmware.agent
-will look for firmware files)
-
-The firmware can be downloaded from the following URL:
-
-    http://ipw2200.sf.net/
-
-
-6.  Support
------------------------------------------------
-
-For direct support of the 1.0.0 version, you can contact 
-http://supportmail.intel.com, or you can use the open source project
-support.
-
-For general information and support, go to:
-	
-    http://ipw2200.sf.net/
-
-
-7.  License
------------------------------------------------
-
-  Copyright(c) 2003 - 2006 Intel Corporation. All rights reserved.
-
-  This program is free software; you can redistribute it and/or modify it 
-  under the terms of the GNU General Public License version 2 as 
-  published by the Free Software Foundation.
-  
-  This program is distributed in the hope that it will be useful, but WITHOUT 
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for 
-  more details.
-  
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, write to the Free Software Foundation, Inc., 59 
-  Temple Place - Suite 330, Boston, MA  02111-1307, USA.
-  
-  The full GNU General Public License is included in this distribution in the
-  file called LICENSE.
-  
-  Contact Information:
-  James P. Ketrenos <ipw2100-admin@linux.intel.com>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
diff --git a/Documentation/networking/README.sb1000 b/Documentation/networking/README.sb1000
deleted file mode 100644
index f92c2aac56a9..000000000000
--- a/Documentation/networking/README.sb1000
+++ /dev/null
@@ -1,207 +0,0 @@
-sb1000 is a module network device driver for the General Instrument (also known
-as NextLevel) SURFboard1000 internal cable modem board.  This is an ISA card
-which is used by a number of cable TV companies to provide cable modem access.
-It's a one-way downstream-only cable modem, meaning that your upstream net link
-is provided by your regular phone modem.
-
-This driver was written by Franco Venturi <fventuri@mediaone.net>.  He deserves
-a great deal of thanks for this wonderful piece of code!
-
------------------------------------------------------------------------------
-
-Support for this device is now a part of the standard Linux kernel.  The
-driver source code file is drivers/net/sb1000.c.  In addition to this
-you will need:
-
-1.) The "cmconfig" program.  This is a utility which supplements "ifconfig"
-to configure the cable modem and network interface (usually called "cm0");
-and
-
-2.) Several PPP scripts which live in /etc/ppp to make connecting via your
-cable modem easy.
-
-   These utilities can be obtained from:
-
-      http://www.jacksonville.net/~fventuri/
-
-   in Franco's original source code distribution .tar.gz file.  Support for
-   the sb1000 driver can be found at:
-
-      http://web.archive.org/web/*/http://home.adelphia.net/~siglercm/sb1000.html
-      http://web.archive.org/web/*/http://linuxpower.cx/~cable/
-
-   along with these utilities.
-
-3.) The standard isapnp tools.  These are necessary to configure your SB1000
-card at boot time (or afterwards by hand) since it's a PnP card.
-
-   If you don't have these installed as a standard part of your Linux
-   distribution, you can find them at:
-
-      http://www.roestock.demon.co.uk/isapnptools/
-
-   or check your Linux distribution binary CD or their web site.  For help with
-   isapnp, pnpdump, or /etc/isapnp.conf, go to:
-
-      http://www.roestock.demon.co.uk/isapnptools/isapnpfaq.html
-
------------------------------------------------------------------------------
-
-To make the SB1000 card work, follow these steps:
-
-1.) Run `make config', or `make menuconfig', or `make xconfig', whichever
-you prefer, in the top kernel tree directory to set up your kernel
-configuration.  Make sure to say "Y" to "Prompt for development drivers"
-and to say "M" to the sb1000 driver.  Also say "Y" or "M" to all the standard
-networking questions to get TCP/IP and PPP networking support.
-
-2.) *BEFORE* you build the kernel, edit drivers/net/sb1000.c.  Make sure
-to redefine the value of READ_DATA_PORT to match the I/O address used
-by isapnp to access your PnP cards.  This is the value of READPORT in
-/etc/isapnp.conf or given by the output of pnpdump.
-
-3.) Build and install the kernel and modules as usual.
-
-4.) Boot your new kernel following the usual procedures.
-
-5.) Set up to configure the new SB1000 PnP card by capturing the output
-of "pnpdump" to a file and editing this file to set the correct I/O ports,
-IRQ, and DMA settings for all your PnP cards.  Make sure none of the settings
-conflict with one another.  Then test this configuration by running the
-"isapnp" command with your new config file as the input.  Check for
-errors and fix as necessary.  (As an aside, I use I/O ports 0x110 and
-0x310 and IRQ 11 for my SB1000 card and these work well for me.  YMMV.)
-Then save the finished config file as /etc/isapnp.conf for proper configuration
-on subsequent reboots.
-
-6.) Download the original file sb1000-1.1.2.tar.gz from Franco's site or one of
-the others referenced above.  As root, unpack it into a temporary directory and
-do a `make cmconfig' and then `install -c cmconfig /usr/local/sbin'.  Don't do
-`make install' because it expects to find all the utilities built and ready for
-installation, not just cmconfig.
-
-7.) As root, copy all the files under the ppp/ subdirectory in Franco's
-tar file into /etc/ppp, being careful not to overwrite any files that are
-already in there.  Then modify ppp@gi-on to set the correct login name,
-phone number, and frequency for the cable modem.  Also edit pap-secrets
-to specify your login name and password and any site-specific information
-you need.
-
-8.) Be sure to modify /etc/ppp/firewall to use ipchains instead of
-the older ipfwadm commands from the 2.0.x kernels.  There's a neat utility to
-convert ipfwadm commands to ipchains commands:
-
-   http://users.dhp.com/~whisper/ipfwadm2ipchains/
-
-You may also wish to modify the firewall script to implement a different
-firewalling scheme.
-
-9.) Start the PPP connection via the script /etc/ppp/ppp@gi-on.  You must be
-root to do this.  It's better to use a utility like sudo to execute
-frequently used commands like this with root permissions if possible.  If you
-connect successfully the cable modem interface will come up and you'll see a
-driver message like this at the console:
-
-         cm0: sb1000 at (0x110,0x310), csn 1, S/N 0x2a0d16d8, IRQ 11.
-         sb1000.c:v1.1.2 6/01/98 (fventuri@mediaone.net)
-
-The "ifconfig" command should show two new interfaces, ppp0 and cm0.
-The command "cmconfig cm0" will give you information about the cable modem
-interface.
-
-10.) Try pinging a site via `ping -c 5 www.yahoo.com', for example.  You should
-see packets received.
-
-11.) If you can't get site names (like www.yahoo.com) to resolve into
-IP addresses (like 204.71.200.67), be sure your /etc/resolv.conf file
-has no syntax errors and has the right nameserver IP addresses in it.
-If this doesn't help, try something like `ping -c 5 204.71.200.67' to
-see if the networking is running but the DNS resolution is where the
-problem lies.
-
-12.) If you still have problems, go to the support web sites mentioned above
-and read the information and documentation there.
-
------------------------------------------------------------------------------
-
-Common problems:
-
-1.) Packets go out on the ppp0 interface but don't come back on the cm0
-interface.  It looks like I'm connected but I can't even ping any
-numerical IP addresses.  (This happens predominantly on Debian systems due
-to a default boot-time configuration script.)
-
-Solution -- As root `echo 0 > /proc/sys/net/ipv4/conf/cm0/rp_filter' so it
-can share the same IP address as the ppp0 interface.  Note that this
-command should probably be added to the /etc/ppp/cablemodem script
-*right*between* the "/sbin/ifconfig" and "/sbin/cmconfig" commands.
-You may need to do this to /proc/sys/net/ipv4/conf/ppp0/rp_filter as well.
-If you do this to /proc/sys/net/ipv4/conf/default/rp_filter on each reboot
-(in rc.local or some such) then any interfaces can share the same IP
-addresses.
-
-2.) I get "unresolved symbol" error messages on executing `insmod sb1000.o'.
-
-Solution -- You probably have a non-matching kernel source tree and
-/usr/include/linux and /usr/include/asm header files.  Make sure you
-install the correct versions of the header files in these two directories.
-Then rebuild and reinstall the kernel.
-
-3.) When isapnp runs it reports an error, and my SB1000 card isn't working.
-
-Solution -- There's a problem with later versions of isapnp using the "(CHECK)"
-option in the lines that allocate the two I/O addresses for the SB1000 card.
-This first popped up on RH 6.0.  Delete "(CHECK)" for the SB1000 I/O addresses.
-Make sure they don't conflict with any other pieces of hardware first!  Then
-rerun isapnp and go from there.
-
-4.) I can't execute the /etc/ppp/ppp@gi-on file.
-
-Solution -- As root do `chmod ug+x /etc/ppp/ppp@gi-on'.
-
-5.) The firewall script isn't working (with 2.2.x and higher kernels).
-
-Solution -- Use the ipfwadm2ipchains script referenced above to convert the
-/etc/ppp/firewall script from the deprecated ipfwadm commands to ipchains.
-
-6.) I'm getting *tons* of firewall deny messages in the /var/kern.log,
-/var/messages, and/or /var/syslog files, and they're filling up my /var
-partition!!!
-
-Solution -- First, tell your ISP that you're receiving DoS (Denial of Service)
-and/or portscanning (UDP connection attempts) attacks!  Look over the deny
-messages to figure out what the attack is and where it's coming from.  Next,
-edit /etc/ppp/cablemodem and make sure the ",nobroadcast" option is turned on
-to the "cmconfig" command (uncomment that line).  If you're not receiving these
-denied packets on your broadcast interface (IP address xxx.yyy.zzz.255
-typically), then someone is attacking your machine in particular.  Be careful
-out there....
-
-7.) Everything seems to work fine but my computer locks up after a while
-(and typically during a lengthy download through the cable modem)!
-
-Solution -- You may need to add a short delay in the driver to 'slow down' the
-SURFboard because your PC might not be able to keep up with the transfer rate
-of the SB1000. To do this, it's probably best to download Franco's
-sb1000-1.1.2.tar.gz archive and build and install sb1000.o manually.  You'll
-want to edit the 'Makefile' and look for the 'SB1000_DELAY'
-define.  Uncomment those 'CFLAGS' lines (and comment out the default ones)
-and try setting the delay to something like 60 microseconds with:
-'-DSB1000_DELAY=60'.  Then do `make' and as root `make install' and try
-it out.  If it still doesn't work or you like playing with the driver, you may
-try other numbers.  Remember though that the higher the delay, the slower the
-driver (which slows down the rest of the PC too when it is actively
-used). Thanks to Ed Daiga for this tip!
-
------------------------------------------------------------------------------
-
-Credits:  This README came from Franco Venturi's original README file which is
-still supplied with his driver .tar.gz archive.  I and all other sb1000 users
-owe Franco a tremendous "Thank you!"  Additional thanks goes to Carl Patten
-and Ralph Bonnell who are now managing the Linux SB1000 web site, and to
-the SB1000 users who reported and helped debug the common problems listed
-above.
-
-
-					Clemmitt Sigler
-					csigler@vt.edu
diff --git a/Documentation/networking/cs89x0.txt b/Documentation/networking/cs89x0.txt
deleted file mode 100644
index 0e190180eec8..000000000000
--- a/Documentation/networking/cs89x0.txt
+++ /dev/null
@@ -1,624 +0,0 @@
-
-NOTE
-----
-
-This document was contributed by Cirrus Logic for kernel 2.2.5.  This version
-has been updated for 2.3.48 by Andrew Morton.
-
-Cirrus make a copy of this driver available at their website, as
-described below.  In general, you should use the driver version which
-comes with your Linux distribution.
-
-
-
-CIRRUS LOGIC LAN CS8900/CS8920 ETHERNET ADAPTERS
-Linux Network Interface Driver ver. 2.00 <kernel 2.3.48>
-===============================================================================
- 
-
-TABLE OF CONTENTS
-
-1.0 CIRRUS LOGIC LAN CS8900/CS8920 ETHERNET ADAPTERS
-    1.1 Product Overview 
-    1.2 Driver Description
-	1.2.1 Driver Name
-	1.2.2 File in the Driver Package
-    1.3 System Requirements
-    1.4 Licensing Information
-
-2.0 ADAPTER INSTALLATION and CONFIGURATION
-    2.1 CS8900-based Adapter Configuration
-    2.2 CS8920-based Adapter Configuration 
-
-3.0 LOADING THE DRIVER AS A MODULE
-
-4.0 COMPILING THE DRIVER
-    4.1 Compiling the Driver as a Loadable Module
-    4.2 Compiling the driver to support memory mode
-    4.3 Compiling the driver to support Rx DMA 
-
-5.0 TESTING AND TROUBLESHOOTING
-    5.1 Known Defects and Limitations
-    5.2 Testing the Adapter
-        5.2.1 Diagnostic Self-Test
-        5.2.2 Diagnostic Network Test
-    5.3 Using the Adapter's LEDs
-    5.4 Resolving I/O Conflicts
-
-6.0 TECHNICAL SUPPORT
-    6.1 Contacting Cirrus Logic's Technical Support
-    6.2 Information Required Before Contacting Technical Support
-    6.3 Obtaining the Latest Driver Version
-    6.4 Current maintainer
-    6.5 Kernel boot parameters
-
-
-1.0 CIRRUS LOGIC LAN CS8900/CS8920 ETHERNET ADAPTERS
-===============================================================================
-
-
-1.1 PRODUCT OVERVIEW
-
-The CS8900-based ISA Ethernet Adapters from Cirrus Logic follow 
-IEEE 802.3 standards and support half or full-duplex operation in ISA bus 
-computers on 10 Mbps Ethernet networks.  The adapters are designed for operation 
-in 16-bit ISA or EISA bus expansion slots and are available in 
-10BaseT-only or 3-media configurations (10BaseT, 10Base2, and AUI for 10Base-5 
-or fiber networks).  
-
-CS8920-based adapters are similar to the CS8900-based adapter with additional 
-features for Plug and Play (PnP) support and Wakeup Frame recognition.  As 
-such, the configuration procedures differ somewhat between the two types of 
-adapters.  Refer to the "Adapter Configuration" section for details on 
-configuring both types of adapters.
-
-
-1.2 DRIVER DESCRIPTION
-
-The CS8900/CS8920 Ethernet Adapter driver for Linux supports the Linux
-v2.3.48 or greater kernel.  It can be compiled directly into the kernel
-or loaded at run-time as a device driver module.
-
-1.2.1 Driver Name: cs89x0
-
-1.2.2 Files in the Driver Archive:
-
-The files in the driver at Cirrus' website include:
-
-  readme.txt         - this file
-  build              - batch file to compile cs89x0.c.
-  cs89x0.c           - driver C code
-  cs89x0.h           - driver header file
-  cs89x0.o           - pre-compiled module (for v2.2.5 kernel)
-  config/Config.in   - sample file to include cs89x0 driver in the kernel.
-  config/Makefile    - sample file to include cs89x0 driver in the kernel.
-  config/Space.c     - sample file to include cs89x0 driver in the kernel.
-
-
-
-1.3 SYSTEM REQUIREMENTS
-
-The following hardware is required:
-
-   * Cirrus Logic LAN (CS8900/20-based) Ethernet ISA Adapter   
-
-   * IBM or IBM-compatible PC with:
-     * An 80386 or higher processor
-     * 16 bytes of contiguous IO space available between 210h - 370h
-     * One available IRQ (5,10,11,or 12 for the CS8900, 3-7,9-15 for CS8920).
-
-   * Appropriate cable (and connector for AUI, 10BASE-2) for your network
-     topology.
-
-The following software is required:
-
-* LINUX kernel version 2.3.48 or higher
-
-   * CS8900/20 Setup Utility (DOS-based)
-
-   * LINUX kernel sources for your kernel (if compiling into kernel)
-
-   * GNU Toolkit (gcc and make) v2.6 or above (if compiling into kernel 
-     or a module)   
-
-
-
-1.4 LICENSING INFORMATION
-
-This program is free software; you can redistribute it and/or modify it under
-the terms of the GNU General Public License as published by the Free Software
-Foundation, version 1.
-
-This program is distributed in the hope that it will be useful, but WITHOUT
-ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 
-FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for 
-more details.
-
-For a full copy of the GNU General Public License, write to the Free Software
-Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-
-
-
-2.0 ADAPTER INSTALLATION and CONFIGURATION
-===============================================================================
-
-Both the CS8900 and CS8920-based adapters can be configured using parameters 
-stored in an on-board EEPROM. You must use the DOS-based CS8900/20 Setup 
-Utility if you want to change the adapter's configuration in EEPROM.  
-
-When loading the driver as a module, you can specify many of the adapter's 
-configuration parameters on the command-line to override the EEPROM's settings 
-or for interface configuration when an EEPROM is not used. (CS8920-based 
-adapters must use an EEPROM.) See Section 3.0 LOADING THE DRIVER AS A MODULE.
-
-Since the CS8900/20 Setup Utility is a DOS-based application, you must install 
-and configure the adapter in a DOS-based system using the CS8900/20 Setup 
-Utility before installation in the target LINUX system.  (Not required if 
-installing a CS8900-based adapter and the default configuration is acceptable.)
-     
-
-2.1 CS8900-BASED ADAPTER CONFIGURATION
-
-CS8900-based adapters shipped from Cirrus Logic have been configured 
-with the following "default" settings:
-
-  Operation Mode:      Memory Mode
-  IRQ:                 10
-  Base I/O Address:    300
-  Memory Base Address: D0000
-  Optimization:	       DOS Client
-  Transmission Mode:   Half-duplex
-  BootProm:            None
-  Media Type:	       Autodetect (3-media cards) or 
-                       10BASE-T (10BASE-T only adapter)
-
-You should only change the default configuration settings if conflicts with 
-another adapter exists. To change the adapter's configuration, run the 
-CS8900/20 Setup Utility. 
-
-
-2.2 CS8920-BASED ADAPTER CONFIGURATION
-
-CS8920-based adapters are shipped from Cirrus Logic configured as Plug
-and Play (PnP) enabled.  However, since the cs89x0 driver does NOT
-support PnP, you must install the CS8920 adapter in a DOS-based PC and
-run the CS8900/20 Setup Utility to disable PnP and configure the
-adapter before installation in the target Linux system.  Failure to do
-this will leave the adapter inactive and the driver will be unable to
-communicate with the adapter.  
-
-
-        **************************************************************** 
-        *                    CS8920-BASED ADAPTERS:                    *
-        *                                                              * 
-        * CS8920-BASED ADAPTERS ARE PLUG and PLAY ENABLED BY DEFAULT.  * 
-        * THE CS89X0 DRIVER DOES NOT SUPPORT PnP. THEREFORE, YOU MUST  *
-        * RUN THE CS8900/20 SETUP UTILITY TO DISABLE PnP SUPPORT AND   *
-        * TO ACTIVATE THE ADAPTER.                                     *
-        ****************************************************************
-
-
-
-
-3.0 LOADING THE DRIVER AS A MODULE
-===============================================================================
-
-If the driver is compiled as a loadable module, you can load the driver module
-with the 'modprobe' command.  Many of the adapter's configuration parameters can 
-be specified as command-line arguments to the load command.  This facility 
-provides a means to override the EEPROM's settings or for interface 
-configuration when an EEPROM is not used.
-
-Example:
-
-    insmod cs89x0.o io=0x200 irq=0xA media=aui
-
-This example loads the module and configures the adapter to use an IO port base
-address of 200h, interrupt 10, and use the AUI media connection.  The following
-configuration options are available on the command line:
-
-* io=###               - specify IO address (200h-360h)
-* irq=##               - specify interrupt level
-* use_dma=1            - Enable DMA
-* dma=#                - specify dma channel (Driver is compiled to support
-                         Rx DMA only)
-* dmasize=# (16 or 64) - DMA size 16K or 64K.  Default value is set to 16.
-* media=rj45           - specify media type
-   or media=bnc
-   or media=aui
-   or media=auto
-* duplex=full          - specify forced half/full/autonegotiate duplex
-   or duplex=half
-   or duplex=auto
-* debug=#              - debug level (only available if the driver was compiled
-                         for debugging)
-
-NOTES:
-
-a) If an EEPROM is present, any specified command-line parameter
-   will override the corresponding configuration value stored in
-   EEPROM.
-
-b) The "io" parameter must be specified on the command-line.  
-
-c) The driver's hardware probe routine is designed to avoid
-   writing to I/O space until it knows that there is a cs89x0
-   card at the written addresses.  This could cause problems
-   with device probing.  To avoid this behaviour, add one
-   to the `io=' module parameter.  This doesn't actually change
-   the I/O address, but it is a flag to tell the driver
-   to partially initialise the hardware before trying to
-   identify the card.  This could be dangerous if you are
-   not sure that there is a cs89x0 card at the provided address.
-
-   For example, to scan for an adapter located at IO base 0x300,
-   specify an IO address of 0x301.  
-
-d) The "duplex=auto" parameter is only supported for the CS8920.
-
-e) The minimum command-line configuration required if an EEPROM is
-   not present is:
-
-   io 
-   irq 
-   media type (no autodetect)
-
-f) The following additional parameters are CS89XX defaults (values
-   used with no EEPROM or command-line argument).
-
-   * DMA Burst = enabled
-   * IOCHRDY Enabled = enabled
-   * UseSA = enabled
-   * CS8900 defaults to half-duplex if not specified on command-line
-   * CS8920 defaults to autoneg if not specified on command-line
-   * Use reset defaults for other config parameters
-   * dma_mode = 0
-
-g) You can use ifconfig to set the adapter's Ethernet address.
-
-h) Many Linux distributions use the 'modprobe' command to load
-   modules.  This program uses the '/etc/conf.modules' file to
-   determine configuration information which is passed to a driver
-   module when it is loaded.  All the configuration options which are
-   described above may be placed within /etc/conf.modules.
-
-   For example:
-
-   > cat /etc/conf.modules
-   ...
-   alias eth0 cs89x0
-   options cs89x0 io=0x0200 dma=5 use_dma=1
-   ...
-
-   In this example we are telling the module system that the
-   ethernet driver for this machine should use the cs89x0 driver.  We
-   are asking 'modprobe' to pass the 'io', 'dma' and 'use_dma'
-   arguments to the driver when it is loaded.
-
-i) Cirrus recommend that the cs89x0 use the ISA DMA channels 5, 6 or
-   7.  You will probably find that other DMA channels will not work.
-
-j) The cs89x0 supports DMA for receiving only.  DMA mode is
-   significantly more efficient.  Flooding a 400 MHz Celeron machine
-   with large ping packets consumes 82% of its CPU capacity in non-DMA
-   mode.  With DMA this is reduced to 45%.
-
-k) If your Linux kernel was compiled with inbuilt plug-and-play
-   support you will be able to find information about the cs89x0 card
-   with the command
-
-   cat /proc/isapnp
-
-l) If during DMA operation you find erratic behavior or network data
-   corruption you should use your PC's BIOS to slow the EISA bus clock.
-
-m) If the cs89x0 driver is compiled directly into the kernel
-   (non-modular) then its I/O address is automatically determined by
-   ISA bus probing.  The IRQ number, media options, etc are determined
-   from the card's EEPROM.
-
-n) If the cs89x0 driver is compiled directly into the kernel, DMA
-   mode may be selected by providing the kernel with a boot option
-   'cs89x0_dma=N' where 'N' is the desired DMA channel number (5, 6 or 7).
-
-   Kernel boot options may be provided on the LILO command line:
-
-	LILO boot: linux cs89x0_dma=5
-
-   or they may be placed in /etc/lilo.conf:
-
-	image=/boot/bzImage-2.3.48
-	  append="cs89x0_dma=5"
-	  label=linux
-	  root=/dev/hda5
-	  read-only
-
-   The DMA Rx buffer size is hardwired to 16 kbytes in this mode.
-   (64k mode is not available).
-
-
-4.0 COMPILING THE DRIVER
-===============================================================================
-
-The cs89x0 driver can be compiled directly into the kernel or compiled into
-a loadable device driver module.
-
-
-4.1 COMPILING THE DRIVER AS A LOADABLE MODULE
-
-To compile the driver into a loadable module, use the following command 
-(single command line, without quotes):
-
-"gcc -D__KERNEL__ -I/usr/src/linux/include -I/usr/src/linux/net/inet -Wall 
--Wstrict-prototypes -O2 -fomit-frame-pointer -DMODULE -DCONFIG_MODVERSIONS 
--c cs89x0.c"
-
-4.2 COMPILING THE DRIVER TO SUPPORT MEMORY MODE
-
-Support for memory mode was not carried over into the 2.3 series kernels.
-
-4.3 COMPILING THE DRIVER TO SUPPORT Rx DMA
-
-The compile-time optionality for DMA was removed in the 2.3 kernel
-series.  DMA support is now unconditionally part of the driver.  It is
-enabled by the 'use_dma=1' module option.
-
-
-5.0 TESTING AND TROUBLESHOOTING
-===============================================================================
-
-5.1 KNOWN DEFECTS and LIMITATIONS
-
-Refer to the RELEASE.TXT file distributed as part of this archive for a list of 
-known defects, driver limitations, and work arounds.
-
-
-5.2 TESTING THE ADAPTER
-
-Once the adapter has been installed and configured, the diagnostic option of 
-the CS8900/20 Setup Utility can be used to test the functionality of the 
-adapter and its network connection.  Use the diagnostics 'Self Test' option to
-test the functionality of the adapter with the hardware configuration you have
-assigned. You can use the diagnostics 'Network Test' to test the ability of the
-adapter to communicate across the Ethernet with another PC equipped with a 
-CS8900/20-based adapter card (it must also be running the CS8900/20 Setup 
-Utility).
-
-         NOTE: The Setup Utility's diagnostics are designed to run in a
-         DOS-only operating system environment.  DO NOT run the diagnostics 
-         from a DOS or command prompt session under Windows 95, Windows NT, 
-         OS/2, or other operating system.
-
-To run the diagnostics tests on the CS8900/20 adapter:
-
-   1.) Boot DOS on the PC and start the CS8900/20 Setup Utility.
-
-   2.) The adapter's current configuration is displayed.  Hit the ENTER key to
-       get to the main menu.
-
-   4.) Select 'Diagnostics' (ALT-G) from the main menu.  
-       * Select 'Self-Test' to test the adapter's basic functionality.
-       * Select 'Network Test' to test the network connection and cabling.
-
-
-5.2.1 DIAGNOSTIC SELF-TEST
-
-The diagnostic self-test checks the adapter's basic functionality as well as 
-its ability to communicate across the ISA bus based on the system resources 
-assigned during hardware configuration.  The following tests are performed:
-
-   * IO Register Read/Write Test
-     The IO Register Read/Write test insures that the CS8900/20 can be 
-     accessed in IO mode, and that the IO base address is correct.
-
-   * Shared Memory Test
-     The Shared Memory test insures the CS8900/20 can be accessed in memory 
-     mode and that the range of memory addresses assigned does not conflict 
-     with other devices in the system.
-
-   * Interrupt Test
-     The Interrupt test insures there are no conflicts with the assigned IRQ
-     signal.
-
-   * EEPROM Test
-     The EEPROM test insures the EEPROM can be read.
-
-   * Chip RAM Test
-     The Chip RAM test insures the 4K of memory internal to the CS8900/20 is
-     working properly.
-
-   * Internal Loop-back Test
-     The Internal Loop Back test insures the adapter's transmitter and 
-     receiver are operating properly.  If this test fails, make sure the 
-     adapter's cable is connected to the network (check for LED activity for 
-     example).
-
-   * Boot PROM Test
-     The Boot PROM  test insures the Boot PROM is present, and can be read.
-     Failure indicates the Boot PROM  was not successfully read due to a
-     hardware problem or due to a conflicts on the Boot PROM address
-     assignment. (Test only applies if the adapter is configured to use the
-     Boot PROM option.)
-
-Failure of a test item indicates a possible system resource conflict with 
-another device on the ISA bus.  In this case, you should use the Manual Setup 
-option to reconfigure the adapter by selecting a different value for the system
-resource that failed.
-
-
-5.2.2 DIAGNOSTIC NETWORK TEST
-
-The Diagnostic Network Test verifies a working network connection by 
-transferring data between two CS8900/20 adapters installed in different PCs 
-on the same network. (Note: the diagnostic network test should not be run 
-between two nodes across a router.) 
-
-This test requires that each of the two PCs have a CS8900/20-based adapter
-installed and have the CS8900/20 Setup Utility running.  The first PC is 
-configured as a Responder and the other PC is configured as an Initiator.  
-Once the Initiator is started, it sends data frames to the Responder which 
-returns the frames to the Initiator.
-
-The total number of frames received and transmitted are displayed on the 
-Initiator's display, along with a count of the number of frames received and 
-transmitted OK or in error.  The test can be terminated anytime by the user at 
-either PC.
-
-To setup the Diagnostic Network Test:
-
-    1.) Select a PC with a CS8900/20-based adapter and a known working network
-        connection to act as the Responder.  Run the CS8900/20 Setup Utility 
-        and select 'Diagnostics -> Network Test -> Responder' from the main 
-        menu.  Hit ENTER to start the Responder.
-
-    2.) Return to the PC with the CS8900/20-based adapter you want to test and
-        start the CS8900/20 Setup Utility. 
-
-    3.) From the main menu, Select 'Diagnostic -> Network Test -> Initiator'.
-        Hit ENTER to start the test.
- 
-You may stop the test on the Initiator at any time while allowing the Responder
-to continue running.  In this manner, you can move to additional PCs and test 
-them by starting the Initiator on another PC without having to stop/start the 
-Responder.
- 
-
-
-5.3 USING THE ADAPTER'S LEDs
-
-The 2 and 3-media adapters have two LEDs visible on the back end of the board 
-located near the 10Base-T connector.  
-
-Link Integrity LED: A "steady" ON of the green LED indicates a valid 10Base-T 
-connection.  (Only applies to 10Base-T.  The green LED has no significance for
-a 10Base-2 or AUI connection.)
-
-TX/RX LED: The yellow LED lights briefly each time the adapter transmits or 
-receives data. (The yellow LED will appear to "flicker" on a typical network.)
-
-
-5.4 RESOLVING I/O CONFLICTS
-
-An IO conflict occurs when two or more adapter use the same ISA resource (IO 
-address, memory address or IRQ).  You can usually detect an IO conflict in one 
-of four ways after installing and or configuring the CS8900/20-based adapter:
-
-    1.) The system does not boot properly (or at all).
-
-    2.) The driver cannot communicate with the adapter, reporting an "Adapter
-        not found" error message.
-
-    3.) You cannot connect to the network or the driver will not load.
-
-    4.) If you have configured the adapter to run in memory mode but the driver
-        reports it is using IO mode when loading, this is an indication of a
-        memory address conflict.
-
-If an IO conflict occurs, run the CS8900/20 Setup Utility and perform a 
-diagnostic self-test.  Normally, the ISA resource in conflict will fail the 
-self-test.  If so, reconfigure the adapter selecting another choice for the 
-resource in conflict.  Run the diagnostics again to check for further IO 
-conflicts.
-
-In some cases, such as when the PC will not boot, it may be necessary to remove
-the adapter and reconfigure it by installing it in another PC to run the 
-CS8900/20 Setup Utility.  Once reinstalled in the target system, run the 
-diagnostics self-test to ensure the new configuration is free of conflicts 
-before loading the driver again.
-
-When manually configuring the adapter, keep in mind the typical ISA system 
-resource usage as indicated in the tables below.
-
-I/O Address    	Device                        IRQ      Device
------------    	--------                      ---      --------
- 200-20F       	Game I/O adapter               3       COM2, Bus Mouse
- 230-23F       	Bus Mouse                      4       COM1
- 270-27F       	LPT3: third parallel port      5       LPT2
- 2F0-2FF       	COM2: second serial port       6       Floppy Disk controller
- 320-32F       	Fixed disk controller          7       LPT1
-                                      	       8       Real-time Clock
-                                                 9       EGA/VGA display adapter    
-                                                12       Mouse (PS/2)                              
-Memory Address  Device                          13       Math Coprocessor
---------------  ---------------------           14       Hard Disk controller
-A000-BFFF	EGA Graphics Adapter
-A000-C7FF	VGA Graphics Adapter
-B000-BFFF	Mono Graphics Adapter
-B800-BFFF	Color Graphics Adapter
-E000-FFFF	AT BIOS
-
-
-
-
-6.0 TECHNICAL SUPPORT
-===============================================================================
-
-6.1 CONTACTING CIRRUS LOGIC'S TECHNICAL SUPPORT
-
-Cirrus Logic's CS89XX Technical Application Support can be reached at:
-
-Telephone  :(800) 888-5016 (from inside U.S. and Canada)
-           :(512) 442-7555 (from outside the U.S. and Canada)
-Fax        :(512) 912-3871
-Email      :ethernet@crystal.cirrus.com
-WWW        :http://www.cirrus.com
-
-
-6.2 INFORMATION REQUIRED BEFORE CONTACTING TECHNICAL SUPPORT
-
-Before contacting Cirrus Logic for technical support, be prepared to provide as 
-Much of the following information as possible. 
-
-1.) Adapter type (CRD8900, CDB8900, CDB8920, etc.)
-
-2.) Adapter configuration
-
-    * IO Base, Memory Base, IO or memory mode enabled, IRQ, DMA channel
-    * Plug and Play enabled/disabled (CS8920-based adapters only)
-    * Configured for media auto-detect or specific media type (which type).    
-
-3.) PC System's Configuration
-
-    * Plug and Play system (yes/no)
-    * BIOS (make and version)
-    * System make and model
-    * CPU (type and speed)
-    * System RAM
-    * SCSI Adapter
-
-4.) Software
-
-    * CS89XX driver and version
-    * Your network operating system and version
-    * Your system's OS version 
-    * Version of all protocol support files
-
-5.) Any Error Message displayed.
-
-
-
-6.3 OBTAINING THE LATEST DRIVER VERSION
-
-You can obtain the latest CS89XX drivers and support software from Cirrus Logic's 
-Web site.  You can also contact Cirrus Logic's Technical Support (email:
-ethernet@crystal.cirrus.com) and request that you be registered for automatic 
-software-update notification.
-
-Cirrus Logic maintains a web page at http://www.cirrus.com with the
-latest drivers and technical publications.
-
-
-6.4 Current maintainer
-
-In February 2000 the maintenance of this driver was assumed by Andrew
-Morton.
-
-6.5 Kernel module parameters
-
-For use in embedded environments with no cs89x0 EEPROM, the kernel boot
-parameter `cs89x0_media=' has been implemented.  Usage is:
-
-	cs89x0_media=rj45    or
-	cs89x0_media=aui     or
-	cs89x0_media=bnc
-
diff --git a/Documentation/networking/cxgb.txt b/Documentation/networking/cxgb.txt
deleted file mode 100644
index 20a887615c4a..000000000000
--- a/Documentation/networking/cxgb.txt
+++ /dev/null
@@ -1,352 +0,0 @@
-                 Chelsio N210 10Gb Ethernet Network Controller
-
-                         Driver Release Notes for Linux
-
-                                 Version 2.1.1
-
-                                 June 20, 2005
-
-CONTENTS
-========
- INTRODUCTION
- FEATURES
- PERFORMANCE
- DRIVER MESSAGES
- KNOWN ISSUES
- SUPPORT
-
-
-INTRODUCTION
-============
-
- This document describes the Linux driver for Chelsio 10Gb Ethernet Network
- Controller. This driver supports the Chelsio N210 NIC and is backward
- compatible with the Chelsio N110 model 10Gb NICs.
-
-
-FEATURES
-========
-
- Adaptive Interrupts (adaptive-rx)
- ---------------------------------
-
-  This feature provides an adaptive algorithm that adjusts the interrupt
-  coalescing parameters, allowing the driver to dynamically adapt the latency
-  settings to achieve the highest performance during various types of network
-  load.
-
-  The interface used to control this feature is ethtool. Please see the
-  ethtool manpage for additional usage information.
-
-  By default, adaptive-rx is disabled.
-  To enable adaptive-rx:
-
-      ethtool -C <interface> adaptive-rx on
-
-  To disable adaptive-rx, use ethtool:
-
-      ethtool -C <interface> adaptive-rx off
-
-  After disabling adaptive-rx, the timer latency value will be set to 50us.
-  You may set the timer latency after disabling adaptive-rx:
-
-      ethtool -C <interface> rx-usecs <microseconds>
-
-  An example to set the timer latency value to 100us on eth0:
-
-      ethtool -C eth0 rx-usecs 100
-
-  You may also provide a timer latency value while disabling adaptive-rx:
-
-      ethtool -C <interface> adaptive-rx off rx-usecs <microseconds>
-
-  If adaptive-rx is disabled and a timer latency value is specified, the timer
-  will be set to the specified value until changed by the user or until
-  adaptive-rx is enabled.
-
-  To view the status of the adaptive-rx and timer latency values:
-
-      ethtool -c <interface>
-
-
- TCP Segmentation Offloading (TSO) Support
- -----------------------------------------
-
-  This feature, also known as "large send", enables a system's protocol stack
-  to offload portions of outbound TCP processing to a network interface card
-  thereby reducing system CPU utilization and enhancing performance.
-
-  The interface used to control this feature is ethtool version 1.8 or higher.
-  Please see the ethtool manpage for additional usage information.
-
-  By default, TSO is enabled.
-  To disable TSO:
-
-      ethtool -K <interface> tso off
-
-  To enable TSO:
-
-      ethtool -K <interface> tso on
-
-  To view the status of TSO:
-
-      ethtool -k <interface>
-
-
-PERFORMANCE
-===========
-
- The following information is provided as an example of how to change system
- parameters for "performance tuning" an what value to use. You may or may not
- want to change these system parameters, depending on your server/workstation
- application. Doing so is not warranted in any way by Chelsio Communications,
- and is done at "YOUR OWN RISK". Chelsio will not be held responsible for loss
- of data or damage to equipment.
-
- Your distribution may have a different way of doing things, or you may prefer
- a different method. These commands are shown only to provide an example of
- what to do and are by no means definitive.
-
- Making any of the following system changes will only last until you reboot
- your system. You may want to write a script that runs at boot-up which
- includes the optimal settings for your system.
-
-  Setting PCI Latency Timer:
-      setpci -d 1425:* 0x0c.l=0x0000F800
-
-  Disabling TCP timestamp:
-      sysctl -w net.ipv4.tcp_timestamps=0
-
-  Disabling SACK:
-      sysctl -w net.ipv4.tcp_sack=0
-
-  Setting large number of incoming connection requests:
-      sysctl -w net.ipv4.tcp_max_syn_backlog=3000
-
-  Setting maximum receive socket buffer size:
-      sysctl -w net.core.rmem_max=1024000
-
-  Setting maximum send socket buffer size:
-      sysctl -w net.core.wmem_max=1024000
-
-  Set smp_affinity (on a multiprocessor system) to a single CPU:
-      echo 1 > /proc/irq/<interrupt_number>/smp_affinity
-
-  Setting default receive socket buffer size:
-      sysctl -w net.core.rmem_default=524287
-
-  Setting default send socket buffer size:
-      sysctl -w net.core.wmem_default=524287
-
-  Setting maximum option memory buffers:
-      sysctl -w net.core.optmem_max=524287
-
-  Setting maximum backlog (# of unprocessed packets before kernel drops):
-      sysctl -w net.core.netdev_max_backlog=300000
-
-  Setting TCP read buffers (min/default/max):
-      sysctl -w net.ipv4.tcp_rmem="10000000 10000000 10000000"
-
-  Setting TCP write buffers (min/pressure/max):
-      sysctl -w net.ipv4.tcp_wmem="10000000 10000000 10000000"
-
-  Setting TCP buffer space (min/pressure/max):
-      sysctl -w net.ipv4.tcp_mem="10000000 10000000 10000000"
-
-  TCP window size for single connections:
-   The receive buffer (RX_WINDOW) size must be at least as large as the
-   Bandwidth-Delay Product of the communication link between the sender and
-   receiver. Due to the variations of RTT, you may want to increase the buffer
-   size up to 2 times the Bandwidth-Delay Product. Reference page 289 of
-   "TCP/IP Illustrated, Volume 1, The Protocols" by W. Richard Stevens.
-   At 10Gb speeds, use the following formula:
-       RX_WINDOW >= 1.25MBytes * RTT(in milliseconds)
-       Example for RTT with 100us: RX_WINDOW = (1,250,000 * 0.1) = 125,000
-   RX_WINDOW sizes of 256KB - 512KB should be sufficient.
-   Setting the min, max, and default receive buffer (RX_WINDOW) size:
-       sysctl -w net.ipv4.tcp_rmem="<min> <default> <max>"
-
-  TCP window size for multiple connections:
-   The receive buffer (RX_WINDOW) size may be calculated the same as single
-   connections, but should be divided by the number of connections. The
-   smaller window prevents congestion and facilitates better pacing,
-   especially if/when MAC level flow control does not work well or when it is
-   not supported on the machine. Experimentation may be necessary to attain
-   the correct value. This method is provided as a starting point for the
-   correct receive buffer size.
-   Setting the min, max, and default receive buffer (RX_WINDOW) size is
-   performed in the same manner as single connection.
-
-
-DRIVER MESSAGES
-===============
-
- The following messages are the most common messages logged by syslog. These
- may be found in /var/log/messages.
-
-  Driver up:
-     Chelsio Network Driver - version 2.1.1
-
-  NIC detected:
-     eth#: Chelsio N210 1x10GBaseX NIC (rev #), PCIX 133MHz/64-bit
-
-  Link up:
-     eth#: link is up at 10 Gbps, full duplex
-
-  Link down:
-     eth#: link is down
-
-
-KNOWN ISSUES
-============
-
- These issues have been identified during testing. The following information
- is provided as a workaround to the problem. In some cases, this problem is
- inherent to Linux or to a particular Linux Distribution and/or hardware
- platform.
-
-  1. Large number of TCP retransmits on a multiprocessor (SMP) system.
-
-      On a system with multiple CPUs, the interrupt (IRQ) for the network
-      controller may be bound to more than one CPU. This will cause TCP
-      retransmits if the packet data were to be split across different CPUs
-      and re-assembled in a different order than expected.
-
-      To eliminate the TCP retransmits, set smp_affinity on the particular
-      interrupt to a single CPU. You can locate the interrupt (IRQ) used on
-      the N110/N210 by using ifconfig:
-          ifconfig <dev_name> | grep Interrupt
-      Set the smp_affinity to a single CPU:
-          echo 1 > /proc/irq/<interrupt_number>/smp_affinity
-
-      It is highly suggested that you do not run the irqbalance daemon on your
-      system, as this will change any smp_affinity setting you have applied.
-      The irqbalance daemon runs on a 10 second interval and binds interrupts
-      to the least loaded CPU determined by the daemon. To disable this daemon:
-          chkconfig --level 2345 irqbalance off
-
-      By default, some Linux distributions enable the kernel feature,
-      irqbalance, which performs the same function as the daemon. To disable
-      this feature, add the following line to your bootloader:
-          noirqbalance
-
-          Example using the Grub bootloader:
-              title Red Hat Enterprise Linux AS (2.4.21-27.ELsmp)
-              root (hd0,0)
-              kernel /vmlinuz-2.4.21-27.ELsmp ro root=/dev/hda3 noirqbalance
-              initrd /initrd-2.4.21-27.ELsmp.img
-
-  2. After running insmod, the driver is loaded and the incorrect network
-     interface is brought up without running ifup.
-
-      When using 2.4.x kernels, including RHEL kernels, the Linux kernel
-      invokes a script named "hotplug". This script is primarily used to
-      automatically bring up USB devices when they are plugged in, however,
-      the script also attempts to automatically bring up a network interface
-      after loading the kernel module. The hotplug script does this by scanning
-      the ifcfg-eth# config files in /etc/sysconfig/network-scripts, looking
-      for HWADDR=<mac_address>.
-
-      If the hotplug script does not find the HWADDRR within any of the
-      ifcfg-eth# files, it will bring up the device with the next available
-      interface name. If this interface is already configured for a different
-      network card, your new interface will have incorrect IP address and
-      network settings.
-
-      To solve this issue, you can add the HWADDR=<mac_address> key to the
-      interface config file of your network controller.
-
-      To disable this "hotplug" feature, you may add the driver (module name)
-      to the "blacklist" file located in /etc/hotplug. It has been noted that
-      this does not work for network devices because the net.agent script
-      does not use the blacklist file. Simply remove, or rename, the net.agent
-      script located in /etc/hotplug to disable this feature.
-
-  3. Transport Protocol (TP) hangs when running heavy multi-connection traffic
-     on an AMD Opteron system with HyperTransport PCI-X Tunnel chipset.
-
-      If your AMD Opteron system uses the AMD-8131 HyperTransport PCI-X Tunnel
-      chipset, you may experience the "133-Mhz Mode Split Completion Data
-      Corruption" bug identified by AMD while using a 133Mhz PCI-X card on the
-      bus PCI-X bus.
-
-      AMD states, "Under highly specific conditions, the AMD-8131 PCI-X Tunnel
-      can provide stale data via split completion cycles to a PCI-X card that
-      is operating at 133 Mhz", causing data corruption.
-
-      AMD's provides three workarounds for this problem, however, Chelsio
-      recommends the first option for best performance with this bug:
-
-        For 133Mhz secondary bus operation, limit the transaction length and
-        the number of outstanding transactions, via BIOS configuration
-        programming of the PCI-X card, to the following:
-
-           Data Length (bytes): 1k
-           Total allowed outstanding transactions: 2
-
-      Please refer to AMD 8131-HT/PCI-X Errata 26310 Rev 3.08 August 2004,
-      section 56, "133-MHz Mode Split Completion Data Corruption" for more
-      details with this bug and workarounds suggested by AMD.
-
-      It may be possible to work outside AMD's recommended PCI-X settings, try
-      increasing the Data Length to 2k bytes for increased performance. If you
-      have issues with these settings, please revert to the "safe" settings
-      and duplicate the problem before submitting a bug or asking for support.
-
-      NOTE: The default setting on most systems is 8 outstanding transactions
-            and 2k bytes data length.
-
-  4. On multiprocessor systems, it has been noted that an application which
-     is handling 10Gb networking can switch between CPUs causing degraded
-     and/or unstable performance.
-
-      If running on an SMP system and taking performance measurements, it
-      is suggested you either run the latest netperf-2.4.0+ or use a binding
-      tool such as Tim Hockin's procstate utilities (runon)
-      <http://www.hockin.org/~thockin/procstate/>.
-
-      Binding netserver and netperf (or other applications) to particular
-      CPUs will have a significant difference in performance measurements.
-      You may need to experiment which CPU to bind the application to in
-      order to achieve the best performance for your system.
-
-      If you are developing an application designed for 10Gb networking,
-      please keep in mind you may want to look at kernel functions
-      sched_setaffinity & sched_getaffinity to bind your application.
-
-      If you are just running user-space applications such as ftp, telnet,
-      etc., you may want to try the runon tool provided by Tim Hockin's
-      procstate utility. You could also try binding the interface to a
-      particular CPU: runon 0 ifup eth0
-
-
-SUPPORT
-=======
-
- If you have problems with the software or hardware, please contact our
- customer support team via email at support@chelsio.com or check our website
- at http://www.chelsio.com
-
-===============================================================================
-
- Chelsio Communications
- 370 San Aleso Ave.
- Suite 100
- Sunnyvale, CA 94085
- http://www.chelsio.com
-
-This program is free software; you can redistribute it and/or modify
-it under the terms of the GNU General Public License, version 2, as
-published by the Free Software Foundation.
-
-You should have received a copy of the GNU General Public License along
-with this program; if not, write to the Free Software Foundation, Inc.,
-59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
-
-THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
-WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
-MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
-
- Copyright (c) 2003-2005 Chelsio Communications. All rights reserved.
-
-===============================================================================
diff --git a/Documentation/networking/de4x5.txt b/Documentation/networking/de4x5.txt
deleted file mode 100644
index c8e4ca9b2c3e..000000000000
--- a/Documentation/networking/de4x5.txt
+++ /dev/null
@@ -1,178 +0,0 @@
-    Originally,   this  driver  was    written  for the  Digital   Equipment
-    Corporation series of EtherWORKS Ethernet cards:
-
-        DE425 TP/COAX EISA
-	DE434 TP PCI
-	DE435 TP/COAX/AUI PCI
-	DE450 TP/COAX/AUI PCI
-	DE500 10/100 PCI Fasternet
-
-    but it  will  now attempt  to  support all  cards which   conform to the
-    Digital Semiconductor   SROM   Specification.    The  driver   currently
-    recognises the following chips:
-
-        DC21040  (no SROM) 
-	DC21041[A]  
-	DC21140[A] 
-	DC21142 
-	DC21143 
-
-    So far the driver is known to work with the following cards:
-
-        KINGSTON
-	Linksys
-	ZNYX342
-	SMC8432
-	SMC9332 (w/new SROM)
-	ZNYX31[45]
-	ZNYX346 10/100 4 port (can act as a 10/100 bridge!) 
-
-    The driver has been tested on a relatively busy network using the DE425,
-    DE434, DE435 and DE500 cards and benchmarked with 'ttcp': it transferred
-    16M of data to a DECstation 5000/200 as follows:
-
-                TCP           UDP
-             TX     RX     TX     RX
-    DE425   1030k  997k   1170k  1128k
-    DE434   1063k  995k   1170k  1125k
-    DE435   1063k  995k   1170k  1125k
-    DE500   1063k  998k   1170k  1125k  in 10Mb/s mode
-
-    All  values are typical (in   kBytes/sec) from a  sample  of 4 for  each
-    measurement. Their error is +/-20k on a quiet (private) network and also
-    depend on what load the CPU has.
-
-    =========================================================================
-
-    The ability to load this  driver as a loadable  module has been included
-    and used extensively  during the driver development  (to save those long
-    reboot sequences).  Loadable module support  under PCI and EISA has been
-    achieved by letting the driver autoprobe as if it were compiled into the
-    kernel. Do make sure  you're not sharing  interrupts with anything  that
-    cannot accommodate  interrupt  sharing!
-
-    To utilise this ability, you have to do 8 things:
-
-    0) have a copy of the loadable modules code installed on your system.
-    1) copy de4x5.c from the  /linux/drivers/net directory to your favourite
-    temporary directory.
-    2) for fixed  autoprobes (not  recommended),  edit the source code  near
-    line 5594 to reflect the I/O address  you're using, or assign these when
-    loading by:
-
-                   insmod de4x5 io=0xghh           where g = bus number
-		                                        hh = device number   
-
-       NB: autoprobing for modules is now supported by default. You may just
-           use:
-
-                   insmod de4x5
-
-           to load all available boards. For a specific board, still use
-	   the 'io=?' above.
-    3) compile  de4x5.c, but include -DMODULE in  the command line to ensure
-    that the correct bits are compiled (see end of source code).
-    4) if you are wanting to add a new  card, goto 5. Otherwise, recompile a
-    kernel with the de4x5 configuration turned off and reboot.
-    5) insmod de4x5 [io=0xghh]
-    6) run the net startup bits for your new eth?? interface(s) manually 
-    (usually /etc/rc.inet[12] at boot time). 
-    7) enjoy!
-
-    To unload a module, turn off the associated interface(s) 
-    'ifconfig eth?? down' then 'rmmod de4x5'.
-
-    Automedia detection is included so that in  principle you can disconnect
-    from, e.g.  TP, reconnect  to BNC  and  things will still work  (after a
-    pause whilst the   driver figures out   where its media went).  My tests
-    using ping showed that it appears to work....
-
-    By  default,  the driver will  now   autodetect any  DECchip based card.
-    Should you have a need to restrict the driver to DIGITAL only cards, you
-    can compile with a  DEC_ONLY define, or if  loading as a module, use the
-    'dec_only=1'  parameter. 
-
-    I've changed the timing routines to  use the kernel timer and scheduling
-    functions  so that the  hangs  and other assorted problems that occurred
-    while autosensing the  media  should be gone.  A  bonus  for the DC21040
-    auto  media sense algorithm is  that it can now  use one that is more in
-    line with the  rest (the DC21040  chip doesn't  have a hardware  timer).
-    The downside is the 1 'jiffies' (10ms) resolution.
-
-    IEEE 802.3u MII interface code has  been added in anticipation that some
-    products may use it in the future.
-
-    The SMC9332 card  has a non-compliant SROM  which needs fixing -  I have
-    patched this  driver to detect it  because the SROM format used complies
-    to a previous DEC-STD format.
-
-    I have removed the buffer copies needed for receive on Intels.  I cannot
-    remove them for   Alphas since  the  Tulip hardware   only does longword
-    aligned  DMA transfers  and  the  Alphas get   alignment traps with  non
-    longword aligned data copies (which makes them really slow). No comment.
-
-    I  have added SROM decoding  routines to make this  driver work with any
-    card that  supports the Digital  Semiconductor SROM spec. This will help
-    all  cards running the dc2114x  series chips in particular.  Cards using
-    the dc2104x  chips should run correctly with  the basic  driver.  I'm in
-    debt to <mjacob@feral.com> for the  testing and feedback that helped get
-    this feature working.  So far we have  tested KINGSTON, SMC8432, SMC9332
-    (with the latest SROM complying  with the SROM spec  V3: their first was
-    broken), ZNYX342  and  LinkSys. ZNYX314 (dual  21041  MAC) and  ZNYX 315
-    (quad 21041 MAC)  cards also  appear  to work despite their  incorrectly
-    wired IRQs.
-
-    I have added a temporary fix for interrupt problems when some SCSI cards
-    share the same interrupt as the DECchip based  cards. The problem occurs
-    because  the SCSI card wants to  grab the interrupt  as a fast interrupt
-    (runs the   service routine with interrupts turned   off) vs.  this card
-    which really needs to run the service routine with interrupts turned on.
-    This driver will  now   add the interrupt service   routine  as  a  fast
-    interrupt if it   is bounced from the   slow interrupt.  THIS IS NOT   A
-    RECOMMENDED WAY TO RUN THE DRIVER  and has been done  for a limited time
-    until  people   sort  out their  compatibility    issues and the  kernel
-    interrupt  service code  is  fixed.   YOU  SHOULD SEPARATE OUT  THE FAST
-    INTERRUPT CARDS FROM THE SLOW INTERRUPT CARDS to ensure that they do not
-    run on the same interrupt. PCMCIA/CardBus is another can of worms...
-
-    Finally, I think  I have really  fixed  the module  loading problem with
-    more than one DECchip based  card.  As a  side effect, I don't mess with
-    the  device structure any  more which means that  if more than 1 card in
-    2.0.x is    installed (4  in   2.1.x),  the  user   will have   to  edit
-    linux/drivers/net/Space.c  to make room for  them. Hence, module loading
-    is  the preferred way to use   this driver, since  it  doesn't have this
-    limitation.
-
-    Where SROM media  detection is used and  full duplex is specified in the
-    SROM,  the feature is  ignored unless  lp->params.fdx  is set at compile
-    time  OR during  a   module load  (insmod  de4x5   args='eth??:fdx' [see
-    below]).  This is because there  is no way  to automatically detect full
-    duplex   links  except through   autonegotiation.    When I  include the
-    autonegotiation feature in  the SROM autoconf  code, this detection will
-    occur automatically for that case.
-
-    Command line  arguments are  now allowed, similar to  passing  arguments
-    through LILO. This will allow a per adapter board set  up of full duplex
-    and media. The only lexical constraints are:  the board name (dev->name)
-    appears in  the list before its parameters.  The list of parameters ends
-    either at the end of the parameter list or with another board name.  The
-    following parameters are allowed:
-
-            fdx        for full duplex
-	    autosense  to set the media/speed; with the following 
-	               sub-parameters:
-		       TP, TP_NW, BNC, AUI, BNC_AUI, 100Mb, 10Mb, AUTO
-
-    Case sensitivity is important  for  the sub-parameters. They *must*   be
-    upper case. Examples:
-
-        insmod de4x5 args='eth1:fdx autosense=BNC eth0:autosense=100Mb'.
-
-    For a compiled in driver, in linux/drivers/net/CONFIG, place e.g.
-	DE4X5_OPTS = -DDE4X5_PARM='"eth0:fdx autosense=AUI eth2:autosense=TP"' 
-
-    Yes,  I know full duplex  isn't permissible on BNC  or AUI; they're just
-    examples. By default, full duplex is turned  off and AUTO is the default
-    autosense setting. In  reality, I expect only the  full duplex option to
-    be used. Note the use of single quotes in the two examples above and the
-    lack of commas to separate items.
diff --git a/Documentation/networking/device_drivers/3com/3c509.txt b/Documentation/networking/device_drivers/3com/3c509.txt
new file mode 100644
index 000000000000..fbf722e15ac3
--- /dev/null
+++ b/Documentation/networking/device_drivers/3com/3c509.txt
@@ -0,0 +1,213 @@
+Linux and the 3Com EtherLink III Series Ethercards (driver v1.18c and higher)
+----------------------------------------------------------------------------
+
+This file contains the instructions and caveats for v1.18c and higher versions
+of the 3c509 driver. You should not use the driver without reading this file.
+
+release 1.0
+28 February 2002
+Current maintainer (corrections to):
+  David Ruggiero <jdr@farfalle.com>
+
+----------------------------------------------------------------------------
+
+(0) Introduction
+
+The following are notes and information on using the 3Com EtherLink III series
+ethercards in Linux. These cards are commonly known by the most widely-used
+card's 3Com model number, 3c509. They are all 10mb/s ISA-bus cards and shouldn't
+be (but sometimes are) confused with the similarly-numbered PCI-bus "3c905"
+(aka "Vortex" or "Boomerang") series.  Kernel support for the 3c509 family is
+provided by the module 3c509.c, which has code to support all of the following
+models:
+
+  3c509 (original ISA card)
+  3c509B (later revision of the ISA card; supports full-duplex)
+  3c589 (PCMCIA)
+  3c589B (later revision of the 3c589; supports full-duplex)
+  3c579 (EISA)
+
+Large portions of this documentation were heavily borrowed from the guide
+written the original author of the 3c509 driver, Donald Becker. The master
+copy of that document, which contains notes on older versions of the driver,
+currently resides on Scyld web server: http://www.scyld.com/.
+
+
+(1) Special Driver Features
+
+Overriding card settings
+
+The driver allows boot- or load-time overriding of the card's detected IOADDR,
+IRQ, and transceiver settings, although this capability shouldn't generally be
+needed except to enable full-duplex mode (see below). An example of the syntax
+for LILO parameters for doing this:
+
+    ether=10,0x310,3,0x3c509,eth0 
+
+This configures the first found 3c509 card for IRQ 10, base I/O 0x310, and
+transceiver type 3 (10base2). The flag "0x3c509" must be set to avoid conflicts
+with other card types when overriding the I/O address. When the driver is
+loaded as a module, only the IRQ may be overridden. For example,
+setting two cards to IRQ10 and IRQ11 is done by using the irq module
+option:
+
+   options 3c509 irq=10,11
+
+
+(2) Full-duplex mode
+
+The v1.18c driver added support for the 3c509B's full-duplex capabilities.
+In order to enable and successfully use full-duplex mode, three conditions
+must be met: 
+
+(a) You must have a Etherlink III card model whose hardware supports full-
+duplex operations. Currently, the only members of the 3c509 family that are
+positively known to support full-duplex are the 3c509B (ISA bus) and 3c589B
+(PCMCIA) cards. Cards without the "B" model designation do *not* support
+full-duplex mode; these include the original 3c509 (no "B"), the original
+3c589, the 3c529 (MCA bus), and the 3c579 (EISA bus).
+
+(b) You must be using your card's 10baseT transceiver (i.e., the RJ-45
+connector), not its AUI (thick-net) or 10base2 (thin-net/coax) interfaces.
+AUI and 10base2 network cabling is physically incapable of full-duplex
+operation.
+
+(c) Most importantly, your 3c509B must be connected to a link partner that is
+itself full-duplex capable. This is almost certainly one of two things: a full-
+duplex-capable  Ethernet switch (*not* a hub), or a full-duplex-capable NIC on
+another system that's connected directly to the 3c509B via a crossover cable.
+
+Full-duplex mode can be enabled using 'ethtool'.
+ 
+/////Extremely important caution concerning full-duplex mode/////
+Understand that the 3c509B's hardware's full-duplex support is much more
+limited than that provide by more modern network interface cards. Although
+at the physical layer of the network it fully supports full-duplex operation,
+the card was designed before the current Ethernet auto-negotiation (N-way)
+spec was written. This means that the 3c509B family ***cannot and will not
+auto-negotiate a full-duplex connection with its link partner under any
+circumstances, no matter how it is initialized***. If the full-duplex mode
+of the 3c509B is enabled, its link partner will very likely need to be
+independently _forced_ into full-duplex mode as well; otherwise various nasty
+failures will occur - at the very least, you'll see massive numbers of packet
+collisions. This is one of very rare circumstances where disabling auto-
+negotiation and forcing the duplex mode of a network interface card or switch
+would ever be necessary or desirable.
+
+
+(3) Available Transceiver Types
+
+For versions of the driver v1.18c and above, the available transceiver types are:
+ 
+0  transceiver type from EEPROM config (normally 10baseT); force half-duplex
+1  AUI (thick-net / DB15 connector)
+2  (undefined)
+3  10base2 (thin-net == coax / BNC connector)
+4  10baseT (RJ-45 connector); force half-duplex mode
+8  transceiver type and duplex mode taken from card's EEPROM config settings
+12 10baseT (RJ-45 connector); force full-duplex mode
+
+Prior to driver version 1.18c, only transceiver codes 0-4 were supported. Note
+that the new transceiver codes 8 and 12 are the *only* ones that will enable
+full-duplex mode, no matter what the card's detected EEPROM settings might be.
+This insured that merely upgrading the driver from an earlier version would
+never automatically enable full-duplex mode in an existing installation;
+it must always be explicitly enabled via one of these code in order to be
+activated.
+
+The transceiver type can be changed using 'ethtool'.
+  
+
+(4a) Interpretation of error messages and common problems
+
+Error Messages
+
+eth0: Infinite loop in interrupt, status 2011. 
+These are "mostly harmless" message indicating that the driver had too much
+work during that interrupt cycle. With a status of 0x2011 you are receiving
+packets faster than they can be removed from the card. This should be rare
+or impossible in normal operation. Possible causes of this error report are:
+ 
+   - a "green" mode enabled that slows the processor down when there is no
+     keyboard activity. 
+
+   - some other device or device driver hogging the bus or disabling interrupts.
+     Check /proc/interrupts for excessive interrupt counts. The timer tick
+     interrupt should always be incrementing faster than the others. 
+
+No received packets 
+If a 3c509, 3c562 or 3c589 can successfully transmit packets, but never
+receives packets (as reported by /proc/net/dev or 'ifconfig') you likely
+have an interrupt line problem. Check /proc/interrupts to verify that the
+card is actually generating interrupts. If the interrupt count is not
+increasing you likely have a physical conflict with two devices trying to
+use the same ISA IRQ line. The common conflict is with a sound card on IRQ10
+or IRQ5, and the easiest solution is to move the 3c509 to a different
+interrupt line. If the device is receiving packets but 'ping' doesn't work,
+you have a routing problem.
+
+Tx Carrier Errors Reported in /proc/net/dev 
+If an EtherLink III appears to transmit packets, but the "Tx carrier errors"
+field in /proc/net/dev increments as quickly as the Tx packet count, you
+likely have an unterminated network or the incorrect media transceiver selected. 
+
+3c509B card is not detected on machines with an ISA PnP BIOS. 
+While the updated driver works with most PnP BIOS programs, it does not work
+with all. This can be fixed by disabling PnP support using the 3Com-supplied
+setup program. 
+
+3c509 card is not detected on overclocked machines 
+Increase the delay time in id_read_eeprom() from the current value, 500,
+to an absurdly high value, such as 5000. 
+
+
+(4b) Decoding Status and Error Messages
+
+The bits in the main status register are: 
+
+value 	description
+0x01 	Interrupt latch
+0x02 	Tx overrun, or Rx underrun
+0x04 	Tx complete
+0x08 	Tx FIFO room available
+0x10 	A complete Rx packet has arrived
+0x20 	A Rx packet has started to arrive
+0x40 	The driver has requested an interrupt
+0x80 	Statistics counter nearly full
+
+The bits in the transmit (Tx) status word are: 
+
+value 	description
+0x02 	Out-of-window collision.
+0x04 	Status stack overflow (normally impossible).
+0x08 	16 collisions.
+0x10 	Tx underrun (not enough PCI bus bandwidth).
+0x20 	Tx jabber.
+0x40 	Tx interrupt requested.
+0x80 	Status is valid (this should always be set).
+
+
+When a transmit error occurs the driver produces a status message such as 
+
+   eth0: Transmit error, Tx status register 82
+
+The two values typically seen here are:
+
+0x82 
+Out of window collision. This typically occurs when some other Ethernet
+host is incorrectly set to full duplex on a half duplex network. 
+
+0x88 
+16 collisions. This typically occurs when the network is exceptionally busy
+or when another host doesn't correctly back off after a collision. If this
+error is mixed with 0x82 errors it is the result of a host incorrectly set
+to full duplex (see above).
+
+Both of these errors are the result of network problems that should be
+corrected. They do not represent driver malfunction.
+
+
+(5) Revision history (this file)
+
+28Feb02 v1.0  DR   New; major portions based on Becker original 3c509 docs
+
diff --git a/Documentation/networking/device_drivers/3com/vortex.txt b/Documentation/networking/device_drivers/3com/vortex.txt
new file mode 100644
index 000000000000..587f3fcfbcae
--- /dev/null
+++ b/Documentation/networking/device_drivers/3com/vortex.txt
@@ -0,0 +1,448 @@
+Documentation/networking/device_drivers/3com/vortex.txt
+Andrew Morton
+30 April 2000
+
+
+This document describes the usage and errata of the 3Com "Vortex" device
+driver for Linux, 3c59x.c.
+
+The driver was written by Donald Becker <becker@scyld.com>
+
+Don is no longer the prime maintainer of this version of the driver. 
+Please report problems to one or more of:
+
+  Andrew Morton
+  Netdev mailing list <netdev@vger.kernel.org>
+  Linux kernel mailing list <linux-kernel@vger.kernel.org>
+
+Please note the 'Reporting and Diagnosing Problems' section at the end
+of this file.
+
+
+Since kernel 2.3.99-pre6, this driver incorporates the support for the
+3c575-series Cardbus cards which used to be handled by 3c575_cb.c.
+
+This driver supports the following hardware:
+
+	3c590 Vortex 10Mbps
+	3c592 EISA 10Mbps Demon/Vortex
+	3c597 EISA Fast Demon/Vortex
+	3c595 Vortex 100baseTx
+	3c595 Vortex 100baseT4
+	3c595 Vortex 100base-MII
+	3c900 Boomerang 10baseT
+	3c900 Boomerang 10Mbps Combo
+	3c900 Cyclone 10Mbps TPO
+	3c900 Cyclone 10Mbps Combo
+	3c900 Cyclone 10Mbps TPC
+	3c900B-FL Cyclone 10base-FL
+	3c905 Boomerang 100baseTx
+	3c905 Boomerang 100baseT4
+	3c905B Cyclone 100baseTx
+	3c905B Cyclone 10/100/BNC
+	3c905B-FX Cyclone 100baseFx
+	3c905C Tornado
+	3c920B-EMB-WNM (ATI Radeon 9100 IGP)
+	3c980 Cyclone
+	3c980C Python-T
+	3cSOHO100-TX Hurricane
+	3c555 Laptop Hurricane
+	3c556 Laptop Tornado
+	3c556B Laptop Hurricane
+	3c575 [Megahertz] 10/100 LAN  CardBus
+	3c575 Boomerang CardBus
+	3CCFE575BT Cyclone CardBus
+	3CCFE575CT Tornado CardBus
+	3CCFE656 Cyclone CardBus
+	3CCFEM656B Cyclone+Winmodem CardBus
+	3CXFEM656C Tornado+Winmodem CardBus
+	3c450 HomePNA Tornado
+	3c920 Tornado
+	3c982 Hydra Dual Port A
+	3c982 Hydra Dual Port B
+	3c905B-T4
+	3c920B-EMB-WNM Tornado
+
+Module parameters
+=================
+
+There are several parameters which may be provided to the driver when
+its module is loaded.  These are usually placed in /etc/modprobe.d/*.conf
+configuration files.  Example:
+
+options 3c59x debug=3 rx_copybreak=300
+
+If you are using the PCMCIA tools (cardmgr) then the options may be
+placed in /etc/pcmcia/config.opts:
+
+module "3c59x" opts "debug=3 rx_copybreak=300"
+
+
+The supported parameters are:
+
+debug=N
+
+  Where N is a number from 0 to 7.  Anything above 3 produces a lot
+  of output in your system logs.  debug=1 is default.
+
+options=N1,N2,N3,...
+
+  Each number in the list provides an option to the corresponding
+  network card.  So if you have two 3c905's and you wish to provide
+  them with option 0x204 you would use:
+
+    options=0x204,0x204
+
+  The individual options are composed of a number of bitfields which
+  have the following meanings:
+
+  Possible media type settings
+	0	10baseT
+	1	10Mbs AUI
+	2	undefined
+	3	10base2 (BNC)
+	4	100base-TX
+	5	100base-FX
+	6	MII (Media Independent Interface)
+	7	Use default setting from EEPROM
+	8       Autonegotiate
+	9       External MII
+	10      Use default setting from EEPROM
+
+  When generating a value for the 'options' setting, the above media
+  selection values may be OR'ed (or added to) the following:
+
+  0x8000  Set driver debugging level to 7
+  0x4000  Set driver debugging level to 2
+  0x0400  Enable Wake-on-LAN
+  0x0200  Force full duplex mode.
+  0x0010  Bus-master enable bit (Old Vortex cards only)
+
+  For example:
+
+    insmod 3c59x options=0x204
+
+  will force full-duplex 100base-TX, rather than allowing the usual
+  autonegotiation.
+
+global_options=N
+
+  Sets the `options' parameter for all 3c59x NICs in the machine. 
+  Entries in the `options' array above will override any setting of
+  this.
+
+full_duplex=N1,N2,N3...
+
+  Similar to bit 9 of 'options'.  Forces the corresponding card into
+  full-duplex mode.  Please use this in preference to the `options'
+  parameter.
+
+  In fact, please don't use this at all! You're better off getting
+  autonegotiation working properly.
+
+global_full_duplex=N1
+
+  Sets full duplex mode for all 3c59x NICs in the machine.  Entries
+  in the `full_duplex' array above will override any setting of this.
+
+flow_ctrl=N1,N2,N3...
+
+  Use 802.3x MAC-layer flow control.  The 3com cards only support the
+  PAUSE command, which means that they will stop sending packets for a
+  short period if they receive a PAUSE frame from the link partner. 
+
+  The driver only allows flow control on a link which is operating in
+  full duplex mode.
+
+  This feature does not appear to work on the 3c905 - only 3c905B and
+  3c905C have been tested.
+
+  The 3com cards appear to only respond to PAUSE frames which are
+  sent to the reserved destination address of 01:80:c2:00:00:01.  They
+  do not honour PAUSE frames which are sent to the station MAC address.
+
+rx_copybreak=M
+
+  The driver preallocates 32 full-sized (1536 byte) network buffers
+  for receiving.  When a packet arrives, the driver has to decide
+  whether to leave the packet in its full-sized buffer, or to allocate
+  a smaller buffer and copy the packet across into it.
+
+  This is a speed/space tradeoff.
+
+  The value of rx_copybreak is used to decide when to make the copy. 
+  If the packet size is less than rx_copybreak, the packet is copied. 
+  The default value for rx_copybreak is 200 bytes.
+
+max_interrupt_work=N
+
+  The driver's interrupt service routine can handle many receive and
+  transmit packets in a single invocation.  It does this in a loop. 
+  The value of max_interrupt_work governs how many times the interrupt
+  service routine will loop.  The default value is 32 loops.  If this
+  is exceeded the interrupt service routine gives up and generates a
+  warning message "eth0: Too much work in interrupt".
+
+hw_checksums=N1,N2,N3,...
+
+  Recent 3com NICs are able to generate IPv4, TCP and UDP checksums
+  in hardware.  Linux has used the Rx checksumming for a long time. 
+  The "zero copy" patch which is planned for the 2.4 kernel series
+  allows you to make use of the NIC's DMA scatter/gather and transmit
+  checksumming as well.
+
+  The driver is set up so that, when the zerocopy patch is applied,
+  all Tornado and Cyclone devices will use S/G and Tx checksums.
+
+  This module parameter has been provided so you can override this
+  decision.  If you think that Tx checksums are causing a problem, you
+  may disable the feature with `hw_checksums=0'.
+
+  If you think your NIC should be performing Tx checksumming and the
+  driver isn't enabling it, you can force the use of hardware Tx
+  checksumming with `hw_checksums=1'.
+
+  The driver drops a message in the logfiles to indicate whether or
+  not it is using hardware scatter/gather and hardware Tx checksums.
+
+  Scatter/gather and hardware checksums provide considerable
+  performance improvement for the sendfile() system call, but a small
+  decrease in throughput for send().  There is no effect upon receive
+  efficiency.
+
+compaq_ioaddr=N
+compaq_irq=N
+compaq_device_id=N
+
+  "Variables to work-around the Compaq PCI BIOS32 problem"....
+
+watchdog=N
+
+  Sets the time duration (in milliseconds) after which the kernel
+  decides that the transmitter has become stuck and needs to be reset. 
+  This is mainly for debugging purposes, although it may be advantageous
+  to increase this value on LANs which have very high collision rates.
+  The default value is 5000 (5.0 seconds).
+
+enable_wol=N1,N2,N3,...
+
+  Enable Wake-on-LAN support for the relevant interface.  Donald
+  Becker's `ether-wake' application may be used to wake suspended
+  machines.
+
+  Also enables the NIC's power management support.
+
+global_enable_wol=N
+
+  Sets enable_wol mode for all 3c59x NICs in the machine.  Entries in
+  the `enable_wol' array above will override any setting of this.
+
+Media selection
+---------------
+
+A number of the older NICs such as the 3c590 and 3c900 series have
+10base2 and AUI interfaces.
+
+Prior to January, 2001 this driver would autoeselect the 10base2 or AUI
+port if it didn't detect activity on the 10baseT port.  It would then
+get stuck on the 10base2 port and a driver reload was necessary to
+switch back to 10baseT.  This behaviour could not be prevented with a
+module option override.
+
+Later (current) versions of the driver _do_ support locking of the
+media type.  So if you load the driver module with
+
+	modprobe 3c59x options=0
+
+it will permanently select the 10baseT port.  Automatic selection of
+other media types does not occur.
+
+
+Transmit error, Tx status register 82
+-------------------------------------
+
+This is a common error which is almost always caused by another host on
+the same network being in full-duplex mode, while this host is in
+half-duplex mode.  You need to find that other host and make it run in
+half-duplex mode or fix this host to run in full-duplex mode.
+
+As a last resort, you can force the 3c59x driver into full-duplex mode
+with
+
+	options 3c59x full_duplex=1
+
+but this has to be viewed as a workaround for broken network gear and
+should only really be used for equipment which cannot autonegotiate.
+
+
+Additional resources
+--------------------
+
+Details of the device driver implementation are at the top of the source file.
+
+Additional documentation is available at Don Becker's Linux Drivers site:
+
+     http://www.scyld.com/vortex.html
+
+Donald Becker's driver development site:
+
+     http://www.scyld.com/network.html
+
+Donald's vortex-diag program is useful for inspecting the NIC's state:
+
+     http://www.scyld.com/ethercard_diag.html
+
+Donald's mii-diag program may be used for inspecting and manipulating
+the NIC's Media Independent Interface subsystem:
+
+     http://www.scyld.com/ethercard_diag.html#mii-diag
+
+Donald's wake-on-LAN page:
+
+     http://www.scyld.com/wakeonlan.html
+
+3Com's DOS-based application for setting up the NICs EEPROMs:
+
+	ftp://ftp.3com.com/pub/nic/3c90x/3c90xx2.exe
+
+
+Autonegotiation notes
+---------------------
+
+  The driver uses a one-minute heartbeat for adapting to changes in
+  the external LAN environment if link is up and 5 seconds if link is down.
+  This means that when, for example, a machine is unplugged from a hubbed
+  10baseT LAN plugged into a  switched 100baseT LAN, the throughput
+  will be quite dreadful for up to sixty seconds.  Be patient.
+
+  Cisco interoperability note from Walter Wong <wcw+@CMU.EDU>:
+
+  On a side note, adding HAS_NWAY seems to share a problem with the
+  Cisco 6509 switch.  Specifically, you need to change the spanning
+  tree parameter for the port the machine is plugged into to 'portfast'
+  mode.  Otherwise, the negotiation fails.  This has been an issue
+  we've noticed for a while but haven't had the time to track down.
+
+  Cisco switches    (Jeff Busch <jbusch@deja.com>)
+
+    My "standard config" for ports to which PC's/servers connect directly:
+
+        interface FastEthernet0/N
+        description machinename
+        load-interval 30
+        spanning-tree portfast
+
+    If autonegotiation is a problem, you may need to specify "speed
+    100" and "duplex full" as well (or "speed 10" and "duplex half").
+
+    WARNING: DO NOT hook up hubs/switches/bridges to these
+    specially-configured ports! The switch will become very confused.
+
+
+Reporting and diagnosing problems
+---------------------------------
+
+Maintainers find that accurate and complete problem reports are
+invaluable in resolving driver problems.  We are frequently not able to
+reproduce problems and must rely on your patience and efforts to get to
+the bottom of the problem.
+
+If you believe you have a driver problem here are some of the
+steps you should take:
+
+- Is it really a driver problem?
+
+   Eliminate some variables: try different cards, different
+   computers, different cables, different ports on the switch/hub,
+   different versions of the kernel or of the driver, etc.
+
+- OK, it's a driver problem.
+
+   You need to generate a report.  Typically this is an email to the
+   maintainer and/or netdev@vger.kernel.org.  The maintainer's
+   email address will be in the driver source or in the MAINTAINERS file.
+
+- The contents of your report will vary a lot depending upon the
+  problem.  If it's a kernel crash then you should refer to the
+  admin-guide/reporting-bugs.rst file.
+
+  But for most problems it is useful to provide the following:
+
+   o Kernel version, driver version
+
+   o A copy of the banner message which the driver generates when
+     it is initialised.  For example:
+
+     eth0: 3Com PCI 3c905C Tornado at 0xa400,  00:50:da:6a:88:f0, IRQ 19
+     8K byte-wide RAM 5:3 Rx:Tx split, autoselect/Autonegotiate interface.
+     MII transceiver found at address 24, status 782d.
+     Enabling bus-master transmits and whole-frame receives.
+
+     NOTE: You must provide the `debug=2' modprobe option to generate
+     a full detection message.  Please do this:
+
+	modprobe 3c59x debug=2
+
+   o If it is a PCI device, the relevant output from 'lspci -vx', eg:
+
+     00:09.0 Ethernet controller: 3Com Corporation 3c905C-TX [Fast Etherlink] (rev 74)
+             Subsystem: 3Com Corporation: Unknown device 9200
+             Flags: bus master, medium devsel, latency 32, IRQ 19
+             I/O ports at a400 [size=128]
+             Memory at db000000 (32-bit, non-prefetchable) [size=128]
+             Expansion ROM at <unassigned> [disabled] [size=128K]
+             Capabilities: [dc] Power Management version 2
+     00: b7 10 00 92 07 00 10 02 74 00 00 02 08 20 00 00
+     10: 01 a4 00 00 00 00 00 db 00 00 00 00 00 00 00 00
+     20: 00 00 00 00 00 00 00 00 00 00 00 00 b7 10 00 10
+     30: 00 00 00 00 dc 00 00 00 00 00 00 00 05 01 0a 0a
+
+   o A description of the environment: 10baseT? 100baseT?
+     full/half duplex? switched or hubbed?
+
+   o Any additional module parameters which you may be providing to the driver.
+
+   o Any kernel logs which are produced.  The more the merrier. 
+     If this is a large file and you are sending your report to a
+     mailing list, mention that you have the logfile, but don't send
+     it.  If you're reporting direct to the maintainer then just send
+     it.
+
+     To ensure that all kernel logs are available, add the
+     following line to /etc/syslog.conf:
+
+         kern.* /var/log/messages
+
+     Then restart syslogd with:
+
+         /etc/rc.d/init.d/syslog restart
+
+     (The above may vary, depending upon which Linux distribution you use).
+
+    o If your problem is reproducible then that's great.  Try the
+      following:
+
+      1) Increase the debug level.  Usually this is done via:
+
+         a) modprobe driver debug=7
+         b) In /etc/modprobe.d/driver.conf:
+            options driver debug=7
+
+      2) Recreate the problem with the higher debug level,
+         send all logs to the maintainer.
+
+      3) Download you card's diagnostic tool from Donald
+         Becker's website <http://www.scyld.com/ethercard_diag.html>.
+         Download mii-diag.c as well.  Build these.
+
+         a) Run 'vortex-diag -aaee' and 'mii-diag -v' when the card is
+            working correctly.  Save the output.
+
+         b) Run the above commands when the card is malfunctioning.  Send
+            both sets of output.
+
+Finally, please be patient and be prepared to do some work.  You may
+end up working on this problem for a week or more as the maintainer
+asks more questions, asks for more tests, asks for patches to be
+applied, etc.  At the end of it all, the problem may even remain
+unresolved.
diff --git a/Documentation/networking/device_drivers/amazon/ena.txt b/Documentation/networking/device_drivers/amazon/ena.txt
new file mode 100644
index 000000000000..2b4b6f57e549
--- /dev/null
+++ b/Documentation/networking/device_drivers/amazon/ena.txt
@@ -0,0 +1,305 @@
+Linux kernel driver for Elastic Network Adapter (ENA) family:
+=============================================================
+
+Overview:
+=========
+ENA is a networking interface designed to make good use of modern CPU
+features and system architectures.
+
+The ENA device exposes a lightweight management interface with a
+minimal set of memory mapped registers and extendable command set
+through an Admin Queue.
+
+The driver supports a range of ENA devices, is link-speed independent
+(i.e., the same driver is used for 10GbE, 25GbE, 40GbE, etc.), and has
+a negotiated and extendable feature set.
+
+Some ENA devices support SR-IOV. This driver is used for both the
+SR-IOV Physical Function (PF) and Virtual Function (VF) devices.
+
+ENA devices enable high speed and low overhead network traffic
+processing by providing multiple Tx/Rx queue pairs (the maximum number
+is advertised by the device via the Admin Queue), a dedicated MSI-X
+interrupt vector per Tx/Rx queue pair, adaptive interrupt moderation,
+and CPU cacheline optimized data placement.
+
+The ENA driver supports industry standard TCP/IP offload features such
+as checksum offload and TCP transmit segmentation offload (TSO).
+Receive-side scaling (RSS) is supported for multi-core scaling.
+
+The ENA driver and its corresponding devices implement health
+monitoring mechanisms such as watchdog, enabling the device and driver
+to recover in a manner transparent to the application, as well as
+debug logs.
+
+Some of the ENA devices support a working mode called Low-latency
+Queue (LLQ), which saves several more microseconds.
+
+Supported PCI vendor ID/device IDs:
+===================================
+1d0f:0ec2 - ENA PF
+1d0f:1ec2 - ENA PF with LLQ support
+1d0f:ec20 - ENA VF
+1d0f:ec21 - ENA VF with LLQ support
+
+ENA Source Code Directory Structure:
+====================================
+ena_com.[ch]      - Management communication layer. This layer is
+                    responsible for the handling all the management
+                    (admin) communication between the device and the
+                    driver.
+ena_eth_com.[ch]  - Tx/Rx data path.
+ena_admin_defs.h  - Definition of ENA management interface.
+ena_eth_io_defs.h - Definition of ENA data path interface.
+ena_common_defs.h - Common definitions for ena_com layer.
+ena_regs_defs.h   - Definition of ENA PCI memory-mapped (MMIO) registers.
+ena_netdev.[ch]   - Main Linux kernel driver.
+ena_syfsfs.[ch]   - Sysfs files.
+ena_ethtool.c     - ethtool callbacks.
+ena_pci_id_tbl.h  - Supported device IDs.
+
+Management Interface:
+=====================
+ENA management interface is exposed by means of:
+- PCIe Configuration Space
+- Device Registers
+- Admin Queue (AQ) and Admin Completion Queue (ACQ)
+- Asynchronous Event Notification Queue (AENQ)
+
+ENA device MMIO Registers are accessed only during driver
+initialization and are not involved in further normal device
+operation.
+
+AQ is used for submitting management commands, and the
+results/responses are reported asynchronously through ACQ.
+
+ENA introduces a very small set of management commands with room for
+vendor-specific extensions. Most of the management operations are
+framed in a generic Get/Set feature command.
+
+The following admin queue commands are supported:
+- Create I/O submission queue
+- Create I/O completion queue
+- Destroy I/O submission queue
+- Destroy I/O completion queue
+- Get feature
+- Set feature
+- Configure AENQ
+- Get statistics
+
+Refer to ena_admin_defs.h for the list of supported Get/Set Feature
+properties.
+
+The Asynchronous Event Notification Queue (AENQ) is a uni-directional
+queue used by the ENA device to send to the driver events that cannot
+be reported using ACQ. AENQ events are subdivided into groups. Each
+group may have multiple syndromes, as shown below
+
+The events are:
+	Group			Syndrome
+	Link state change	- X -
+	Fatal error		- X -
+	Notification		Suspend traffic
+	Notification		Resume traffic
+	Keep-Alive		- X -
+
+ACQ and AENQ share the same MSI-X vector.
+
+Keep-Alive is a special mechanism that allows monitoring of the
+device's health. The driver maintains a watchdog (WD) handler which,
+if fired, logs the current state and statistics then resets and
+restarts the ENA device and driver. A Keep-Alive event is delivered by
+the device every second. The driver re-arms the WD upon reception of a
+Keep-Alive event. A missed Keep-Alive event causes the WD handler to
+fire.
+
+Data Path Interface:
+====================
+I/O operations are based on Tx and Rx Submission Queues (Tx SQ and Rx
+SQ correspondingly). Each SQ has a completion queue (CQ) associated
+with it.
+
+The SQs and CQs are implemented as descriptor rings in contiguous
+physical memory.
+
+The ENA driver supports two Queue Operation modes for Tx SQs:
+- Regular mode
+  * In this mode the Tx SQs reside in the host's memory. The ENA
+    device fetches the ENA Tx descriptors and packet data from host
+    memory.
+- Low Latency Queue (LLQ) mode or "push-mode".
+  * In this mode the driver pushes the transmit descriptors and the
+    first 128 bytes of the packet directly to the ENA device memory
+    space. The rest of the packet payload is fetched by the
+    device. For this operation mode, the driver uses a dedicated PCI
+    device memory BAR, which is mapped with write-combine capability.
+
+The Rx SQs support only the regular mode.
+
+Note: Not all ENA devices support LLQ, and this feature is negotiated
+      with the device upon initialization. If the ENA device does not
+      support LLQ mode, the driver falls back to the regular mode.
+
+The driver supports multi-queue for both Tx and Rx. This has various
+benefits:
+- Reduced CPU/thread/process contention on a given Ethernet interface.
+- Cache miss rate on completion is reduced, particularly for data
+  cache lines that hold the sk_buff structures.
+- Increased process-level parallelism when handling received packets.
+- Increased data cache hit rate, by steering kernel processing of
+  packets to the CPU, where the application thread consuming the
+  packet is running.
+- In hardware interrupt re-direction.
+
+Interrupt Modes:
+================
+The driver assigns a single MSI-X vector per queue pair (for both Tx
+and Rx directions). The driver assigns an additional dedicated MSI-X vector
+for management (for ACQ and AENQ).
+
+Management interrupt registration is performed when the Linux kernel
+probes the adapter, and it is de-registered when the adapter is
+removed. I/O queue interrupt registration is performed when the Linux
+interface of the adapter is opened, and it is de-registered when the
+interface is closed.
+
+The management interrupt is named:
+   ena-mgmnt@pci:<PCI domain:bus:slot.function>
+and for each queue pair, an interrupt is named:
+   <interface name>-Tx-Rx-<queue index>
+
+The ENA device operates in auto-mask and auto-clear interrupt
+modes. That is, once MSI-X is delivered to the host, its Cause bit is
+automatically cleared and the interrupt is masked. The interrupt is
+unmasked by the driver after NAPI processing is complete.
+
+Interrupt Moderation:
+=====================
+ENA driver and device can operate in conventional or adaptive interrupt
+moderation mode.
+
+In conventional mode the driver instructs device to postpone interrupt
+posting according to static interrupt delay value. The interrupt delay
+value can be configured through ethtool(8). The following ethtool
+parameters are supported by the driver: tx-usecs, rx-usecs
+
+In adaptive interrupt moderation mode the interrupt delay value is
+updated by the driver dynamically and adjusted every NAPI cycle
+according to the traffic nature.
+
+By default ENA driver applies adaptive coalescing on Rx traffic and
+conventional coalescing on Tx traffic.
+
+Adaptive coalescing can be switched on/off through ethtool(8)
+adaptive_rx on|off parameter.
+
+The driver chooses interrupt delay value according to the number of
+bytes and packets received between interrupt unmasking and interrupt
+posting. The driver uses interrupt delay table that subdivides the
+range of received bytes/packets into 5 levels and assigns interrupt
+delay value to each level.
+
+The user can enable/disable adaptive moderation, modify the interrupt
+delay table and restore its default values through sysfs.
+
+The rx_copybreak is initialized by default to ENA_DEFAULT_RX_COPYBREAK
+and can be configured by the ETHTOOL_STUNABLE command of the
+SIOCETHTOOL ioctl.
+
+SKB:
+The driver-allocated SKB for frames received from Rx handling using
+NAPI context. The allocation method depends on the size of the packet.
+If the frame length is larger than rx_copybreak, napi_get_frags()
+is used, otherwise netdev_alloc_skb_ip_align() is used, the buffer
+content is copied (by CPU) to the SKB, and the buffer is recycled.
+
+Statistics:
+===========
+The user can obtain ENA device and driver statistics using ethtool.
+The driver can collect regular or extended statistics (including
+per-queue stats) from the device.
+
+In addition the driver logs the stats to syslog upon device reset.
+
+MTU:
+====
+The driver supports an arbitrarily large MTU with a maximum that is
+negotiated with the device. The driver configures MTU using the
+SetFeature command (ENA_ADMIN_MTU property). The user can change MTU
+via ip(8) and similar legacy tools.
+
+Stateless Offloads:
+===================
+The ENA driver supports:
+- TSO over IPv4/IPv6
+- TSO with ECN
+- IPv4 header checksum offload
+- TCP/UDP over IPv4/IPv6 checksum offloads
+
+RSS:
+====
+- The ENA device supports RSS that allows flexible Rx traffic
+  steering.
+- Toeplitz and CRC32 hash functions are supported.
+- Different combinations of L2/L3/L4 fields can be configured as
+  inputs for hash functions.
+- The driver configures RSS settings using the AQ SetFeature command
+  (ENA_ADMIN_RSS_HASH_FUNCTION, ENA_ADMIN_RSS_HASH_INPUT and
+  ENA_ADMIN_RSS_REDIRECTION_TABLE_CONFIG properties).
+- If the NETIF_F_RXHASH flag is set, the 32-bit result of the hash
+  function delivered in the Rx CQ descriptor is set in the received
+  SKB.
+- The user can provide a hash key, hash function, and configure the
+  indirection table through ethtool(8).
+
+DATA PATH:
+==========
+Tx:
+---
+end_start_xmit() is called by the stack. This function does the following:
+- Maps data buffers (skb->data and frags).
+- Populates ena_buf for the push buffer (if the driver and device are
+  in push mode.)
+- Prepares ENA bufs for the remaining frags.
+- Allocates a new request ID from the empty req_id ring. The request
+  ID is the index of the packet in the Tx info. This is used for
+  out-of-order TX completions.
+- Adds the packet to the proper place in the Tx ring.
+- Calls ena_com_prepare_tx(), an ENA communication layer that converts
+  the ena_bufs to ENA descriptors (and adds meta ENA descriptors as
+  needed.)
+  * This function also copies the ENA descriptors and the push buffer
+    to the Device memory space (if in push mode.)
+- Writes doorbell to the ENA device.
+- When the ENA device finishes sending the packet, a completion
+  interrupt is raised.
+- The interrupt handler schedules NAPI.
+- The ena_clean_tx_irq() function is called. This function handles the
+  completion descriptors generated by the ENA, with a single
+  completion descriptor per completed packet.
+  * req_id is retrieved from the completion descriptor. The tx_info of
+    the packet is retrieved via the req_id. The data buffers are
+    unmapped and req_id is returned to the empty req_id ring.
+  * The function stops when the completion descriptors are completed or
+    the budget is reached.
+
+Rx:
+---
+- When a packet is received from the ENA device.
+- The interrupt handler schedules NAPI.
+- The ena_clean_rx_irq() function is called. This function calls
+  ena_rx_pkt(), an ENA communication layer function, which returns the
+  number of descriptors used for a new unhandled packet, and zero if
+  no new packet is found.
+- Then it calls the ena_clean_rx_irq() function.
+- ena_eth_rx_skb() checks packet length:
+  * If the packet is small (len < rx_copybreak), the driver allocates
+    a SKB for the new packet, and copies the packet payload into the
+    SKB data buffer.
+    - In this way the original data buffer is not passed to the stack
+      and is reused for future Rx packets.
+  * Otherwise the function unmaps the Rx buffer, then allocates the
+    new SKB structure and hooks the Rx buffer to the SKB frags.
+- The new SKB is updated with the necessary information (protocol,
+  checksum hw verify result, etc.), and then passed to the network
+  stack, using the NAPI interface function napi_gro_receive().
diff --git a/Documentation/networking/device_drivers/chelsio/cxgb.txt b/Documentation/networking/device_drivers/chelsio/cxgb.txt
new file mode 100644
index 000000000000..20a887615c4a
--- /dev/null
+++ b/Documentation/networking/device_drivers/chelsio/cxgb.txt
@@ -0,0 +1,352 @@
+                 Chelsio N210 10Gb Ethernet Network Controller
+
+                         Driver Release Notes for Linux
+
+                                 Version 2.1.1
+
+                                 June 20, 2005
+
+CONTENTS
+========
+ INTRODUCTION
+ FEATURES
+ PERFORMANCE
+ DRIVER MESSAGES
+ KNOWN ISSUES
+ SUPPORT
+
+
+INTRODUCTION
+============
+
+ This document describes the Linux driver for Chelsio 10Gb Ethernet Network
+ Controller. This driver supports the Chelsio N210 NIC and is backward
+ compatible with the Chelsio N110 model 10Gb NICs.
+
+
+FEATURES
+========
+
+ Adaptive Interrupts (adaptive-rx)
+ ---------------------------------
+
+  This feature provides an adaptive algorithm that adjusts the interrupt
+  coalescing parameters, allowing the driver to dynamically adapt the latency
+  settings to achieve the highest performance during various types of network
+  load.
+
+  The interface used to control this feature is ethtool. Please see the
+  ethtool manpage for additional usage information.
+
+  By default, adaptive-rx is disabled.
+  To enable adaptive-rx:
+
+      ethtool -C <interface> adaptive-rx on
+
+  To disable adaptive-rx, use ethtool:
+
+      ethtool -C <interface> adaptive-rx off
+
+  After disabling adaptive-rx, the timer latency value will be set to 50us.
+  You may set the timer latency after disabling adaptive-rx:
+
+      ethtool -C <interface> rx-usecs <microseconds>
+
+  An example to set the timer latency value to 100us on eth0:
+
+      ethtool -C eth0 rx-usecs 100
+
+  You may also provide a timer latency value while disabling adaptive-rx:
+
+      ethtool -C <interface> adaptive-rx off rx-usecs <microseconds>
+
+  If adaptive-rx is disabled and a timer latency value is specified, the timer
+  will be set to the specified value until changed by the user or until
+  adaptive-rx is enabled.
+
+  To view the status of the adaptive-rx and timer latency values:
+
+      ethtool -c <interface>
+
+
+ TCP Segmentation Offloading (TSO) Support
+ -----------------------------------------
+
+  This feature, also known as "large send", enables a system's protocol stack
+  to offload portions of outbound TCP processing to a network interface card
+  thereby reducing system CPU utilization and enhancing performance.
+
+  The interface used to control this feature is ethtool version 1.8 or higher.
+  Please see the ethtool manpage for additional usage information.
+
+  By default, TSO is enabled.
+  To disable TSO:
+
+      ethtool -K <interface> tso off
+
+  To enable TSO:
+
+      ethtool -K <interface> tso on
+
+  To view the status of TSO:
+
+      ethtool -k <interface>
+
+
+PERFORMANCE
+===========
+
+ The following information is provided as an example of how to change system
+ parameters for "performance tuning" an what value to use. You may or may not
+ want to change these system parameters, depending on your server/workstation
+ application. Doing so is not warranted in any way by Chelsio Communications,
+ and is done at "YOUR OWN RISK". Chelsio will not be held responsible for loss
+ of data or damage to equipment.
+
+ Your distribution may have a different way of doing things, or you may prefer
+ a different method. These commands are shown only to provide an example of
+ what to do and are by no means definitive.
+
+ Making any of the following system changes will only last until you reboot
+ your system. You may want to write a script that runs at boot-up which
+ includes the optimal settings for your system.
+
+  Setting PCI Latency Timer:
+      setpci -d 1425:* 0x0c.l=0x0000F800
+
+  Disabling TCP timestamp:
+      sysctl -w net.ipv4.tcp_timestamps=0
+
+  Disabling SACK:
+      sysctl -w net.ipv4.tcp_sack=0
+
+  Setting large number of incoming connection requests:
+      sysctl -w net.ipv4.tcp_max_syn_backlog=3000
+
+  Setting maximum receive socket buffer size:
+      sysctl -w net.core.rmem_max=1024000
+
+  Setting maximum send socket buffer size:
+      sysctl -w net.core.wmem_max=1024000
+
+  Set smp_affinity (on a multiprocessor system) to a single CPU:
+      echo 1 > /proc/irq/<interrupt_number>/smp_affinity
+
+  Setting default receive socket buffer size:
+      sysctl -w net.core.rmem_default=524287
+
+  Setting default send socket buffer size:
+      sysctl -w net.core.wmem_default=524287
+
+  Setting maximum option memory buffers:
+      sysctl -w net.core.optmem_max=524287
+
+  Setting maximum backlog (# of unprocessed packets before kernel drops):
+      sysctl -w net.core.netdev_max_backlog=300000
+
+  Setting TCP read buffers (min/default/max):
+      sysctl -w net.ipv4.tcp_rmem="10000000 10000000 10000000"
+
+  Setting TCP write buffers (min/pressure/max):
+      sysctl -w net.ipv4.tcp_wmem="10000000 10000000 10000000"
+
+  Setting TCP buffer space (min/pressure/max):
+      sysctl -w net.ipv4.tcp_mem="10000000 10000000 10000000"
+
+  TCP window size for single connections:
+   The receive buffer (RX_WINDOW) size must be at least as large as the
+   Bandwidth-Delay Product of the communication link between the sender and
+   receiver. Due to the variations of RTT, you may want to increase the buffer
+   size up to 2 times the Bandwidth-Delay Product. Reference page 289 of
+   "TCP/IP Illustrated, Volume 1, The Protocols" by W. Richard Stevens.
+   At 10Gb speeds, use the following formula:
+       RX_WINDOW >= 1.25MBytes * RTT(in milliseconds)
+       Example for RTT with 100us: RX_WINDOW = (1,250,000 * 0.1) = 125,000
+   RX_WINDOW sizes of 256KB - 512KB should be sufficient.
+   Setting the min, max, and default receive buffer (RX_WINDOW) size:
+       sysctl -w net.ipv4.tcp_rmem="<min> <default> <max>"
+
+  TCP window size for multiple connections:
+   The receive buffer (RX_WINDOW) size may be calculated the same as single
+   connections, but should be divided by the number of connections. The
+   smaller window prevents congestion and facilitates better pacing,
+   especially if/when MAC level flow control does not work well or when it is
+   not supported on the machine. Experimentation may be necessary to attain
+   the correct value. This method is provided as a starting point for the
+   correct receive buffer size.
+   Setting the min, max, and default receive buffer (RX_WINDOW) size is
+   performed in the same manner as single connection.
+
+
+DRIVER MESSAGES
+===============
+
+ The following messages are the most common messages logged by syslog. These
+ may be found in /var/log/messages.
+
+  Driver up:
+     Chelsio Network Driver - version 2.1.1
+
+  NIC detected:
+     eth#: Chelsio N210 1x10GBaseX NIC (rev #), PCIX 133MHz/64-bit
+
+  Link up:
+     eth#: link is up at 10 Gbps, full duplex
+
+  Link down:
+     eth#: link is down
+
+
+KNOWN ISSUES
+============
+
+ These issues have been identified during testing. The following information
+ is provided as a workaround to the problem. In some cases, this problem is
+ inherent to Linux or to a particular Linux Distribution and/or hardware
+ platform.
+
+  1. Large number of TCP retransmits on a multiprocessor (SMP) system.
+
+      On a system with multiple CPUs, the interrupt (IRQ) for the network
+      controller may be bound to more than one CPU. This will cause TCP
+      retransmits if the packet data were to be split across different CPUs
+      and re-assembled in a different order than expected.
+
+      To eliminate the TCP retransmits, set smp_affinity on the particular
+      interrupt to a single CPU. You can locate the interrupt (IRQ) used on
+      the N110/N210 by using ifconfig:
+          ifconfig <dev_name> | grep Interrupt
+      Set the smp_affinity to a single CPU:
+          echo 1 > /proc/irq/<interrupt_number>/smp_affinity
+
+      It is highly suggested that you do not run the irqbalance daemon on your
+      system, as this will change any smp_affinity setting you have applied.
+      The irqbalance daemon runs on a 10 second interval and binds interrupts
+      to the least loaded CPU determined by the daemon. To disable this daemon:
+          chkconfig --level 2345 irqbalance off
+
+      By default, some Linux distributions enable the kernel feature,
+      irqbalance, which performs the same function as the daemon. To disable
+      this feature, add the following line to your bootloader:
+          noirqbalance
+
+          Example using the Grub bootloader:
+              title Red Hat Enterprise Linux AS (2.4.21-27.ELsmp)
+              root (hd0,0)
+              kernel /vmlinuz-2.4.21-27.ELsmp ro root=/dev/hda3 noirqbalance
+              initrd /initrd-2.4.21-27.ELsmp.img
+
+  2. After running insmod, the driver is loaded and the incorrect network
+     interface is brought up without running ifup.
+
+      When using 2.4.x kernels, including RHEL kernels, the Linux kernel
+      invokes a script named "hotplug". This script is primarily used to
+      automatically bring up USB devices when they are plugged in, however,
+      the script also attempts to automatically bring up a network interface
+      after loading the kernel module. The hotplug script does this by scanning
+      the ifcfg-eth# config files in /etc/sysconfig/network-scripts, looking
+      for HWADDR=<mac_address>.
+
+      If the hotplug script does not find the HWADDRR within any of the
+      ifcfg-eth# files, it will bring up the device with the next available
+      interface name. If this interface is already configured for a different
+      network card, your new interface will have incorrect IP address and
+      network settings.
+
+      To solve this issue, you can add the HWADDR=<mac_address> key to the
+      interface config file of your network controller.
+
+      To disable this "hotplug" feature, you may add the driver (module name)
+      to the "blacklist" file located in /etc/hotplug. It has been noted that
+      this does not work for network devices because the net.agent script
+      does not use the blacklist file. Simply remove, or rename, the net.agent
+      script located in /etc/hotplug to disable this feature.
+
+  3. Transport Protocol (TP) hangs when running heavy multi-connection traffic
+     on an AMD Opteron system with HyperTransport PCI-X Tunnel chipset.
+
+      If your AMD Opteron system uses the AMD-8131 HyperTransport PCI-X Tunnel
+      chipset, you may experience the "133-Mhz Mode Split Completion Data
+      Corruption" bug identified by AMD while using a 133Mhz PCI-X card on the
+      bus PCI-X bus.
+
+      AMD states, "Under highly specific conditions, the AMD-8131 PCI-X Tunnel
+      can provide stale data via split completion cycles to a PCI-X card that
+      is operating at 133 Mhz", causing data corruption.
+
+      AMD's provides three workarounds for this problem, however, Chelsio
+      recommends the first option for best performance with this bug:
+
+        For 133Mhz secondary bus operation, limit the transaction length and
+        the number of outstanding transactions, via BIOS configuration
+        programming of the PCI-X card, to the following:
+
+           Data Length (bytes): 1k
+           Total allowed outstanding transactions: 2
+
+      Please refer to AMD 8131-HT/PCI-X Errata 26310 Rev 3.08 August 2004,
+      section 56, "133-MHz Mode Split Completion Data Corruption" for more
+      details with this bug and workarounds suggested by AMD.
+
+      It may be possible to work outside AMD's recommended PCI-X settings, try
+      increasing the Data Length to 2k bytes for increased performance. If you
+      have issues with these settings, please revert to the "safe" settings
+      and duplicate the problem before submitting a bug or asking for support.
+
+      NOTE: The default setting on most systems is 8 outstanding transactions
+            and 2k bytes data length.
+
+  4. On multiprocessor systems, it has been noted that an application which
+     is handling 10Gb networking can switch between CPUs causing degraded
+     and/or unstable performance.
+
+      If running on an SMP system and taking performance measurements, it
+      is suggested you either run the latest netperf-2.4.0+ or use a binding
+      tool such as Tim Hockin's procstate utilities (runon)
+      <http://www.hockin.org/~thockin/procstate/>.
+
+      Binding netserver and netperf (or other applications) to particular
+      CPUs will have a significant difference in performance measurements.
+      You may need to experiment which CPU to bind the application to in
+      order to achieve the best performance for your system.
+
+      If you are developing an application designed for 10Gb networking,
+      please keep in mind you may want to look at kernel functions
+      sched_setaffinity & sched_getaffinity to bind your application.
+
+      If you are just running user-space applications such as ftp, telnet,
+      etc., you may want to try the runon tool provided by Tim Hockin's
+      procstate utility. You could also try binding the interface to a
+      particular CPU: runon 0 ifup eth0
+
+
+SUPPORT
+=======
+
+ If you have problems with the software or hardware, please contact our
+ customer support team via email at support@chelsio.com or check our website
+ at http://www.chelsio.com
+
+===============================================================================
+
+ Chelsio Communications
+ 370 San Aleso Ave.
+ Suite 100
+ Sunnyvale, CA 94085
+ http://www.chelsio.com
+
+This program is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License, version 2, as
+published by the Free Software Foundation.
+
+You should have received a copy of the GNU General Public License along
+with this program; if not, write to the Free Software Foundation, Inc.,
+59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+
+THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+
+ Copyright (c) 2003-2005 Chelsio Communications. All rights reserved.
+
+===============================================================================
diff --git a/Documentation/networking/device_drivers/cirrus/cs89x0.txt b/Documentation/networking/device_drivers/cirrus/cs89x0.txt
new file mode 100644
index 000000000000..0e190180eec8
--- /dev/null
+++ b/Documentation/networking/device_drivers/cirrus/cs89x0.txt
@@ -0,0 +1,624 @@
+
+NOTE
+----
+
+This document was contributed by Cirrus Logic for kernel 2.2.5.  This version
+has been updated for 2.3.48 by Andrew Morton.
+
+Cirrus make a copy of this driver available at their website, as
+described below.  In general, you should use the driver version which
+comes with your Linux distribution.
+
+
+
+CIRRUS LOGIC LAN CS8900/CS8920 ETHERNET ADAPTERS
+Linux Network Interface Driver ver. 2.00 <kernel 2.3.48>
+===============================================================================
+ 
+
+TABLE OF CONTENTS
+
+1.0 CIRRUS LOGIC LAN CS8900/CS8920 ETHERNET ADAPTERS
+    1.1 Product Overview 
+    1.2 Driver Description
+	1.2.1 Driver Name
+	1.2.2 File in the Driver Package
+    1.3 System Requirements
+    1.4 Licensing Information
+
+2.0 ADAPTER INSTALLATION and CONFIGURATION
+    2.1 CS8900-based Adapter Configuration
+    2.2 CS8920-based Adapter Configuration 
+
+3.0 LOADING THE DRIVER AS A MODULE
+
+4.0 COMPILING THE DRIVER
+    4.1 Compiling the Driver as a Loadable Module
+    4.2 Compiling the driver to support memory mode
+    4.3 Compiling the driver to support Rx DMA 
+
+5.0 TESTING AND TROUBLESHOOTING
+    5.1 Known Defects and Limitations
+    5.2 Testing the Adapter
+        5.2.1 Diagnostic Self-Test
+        5.2.2 Diagnostic Network Test
+    5.3 Using the Adapter's LEDs
+    5.4 Resolving I/O Conflicts
+
+6.0 TECHNICAL SUPPORT
+    6.1 Contacting Cirrus Logic's Technical Support
+    6.2 Information Required Before Contacting Technical Support
+    6.3 Obtaining the Latest Driver Version
+    6.4 Current maintainer
+    6.5 Kernel boot parameters
+
+
+1.0 CIRRUS LOGIC LAN CS8900/CS8920 ETHERNET ADAPTERS
+===============================================================================
+
+
+1.1 PRODUCT OVERVIEW
+
+The CS8900-based ISA Ethernet Adapters from Cirrus Logic follow 
+IEEE 802.3 standards and support half or full-duplex operation in ISA bus 
+computers on 10 Mbps Ethernet networks.  The adapters are designed for operation 
+in 16-bit ISA or EISA bus expansion slots and are available in 
+10BaseT-only or 3-media configurations (10BaseT, 10Base2, and AUI for 10Base-5 
+or fiber networks).  
+
+CS8920-based adapters are similar to the CS8900-based adapter with additional 
+features for Plug and Play (PnP) support and Wakeup Frame recognition.  As 
+such, the configuration procedures differ somewhat between the two types of 
+adapters.  Refer to the "Adapter Configuration" section for details on 
+configuring both types of adapters.
+
+
+1.2 DRIVER DESCRIPTION
+
+The CS8900/CS8920 Ethernet Adapter driver for Linux supports the Linux
+v2.3.48 or greater kernel.  It can be compiled directly into the kernel
+or loaded at run-time as a device driver module.
+
+1.2.1 Driver Name: cs89x0
+
+1.2.2 Files in the Driver Archive:
+
+The files in the driver at Cirrus' website include:
+
+  readme.txt         - this file
+  build              - batch file to compile cs89x0.c.
+  cs89x0.c           - driver C code
+  cs89x0.h           - driver header file
+  cs89x0.o           - pre-compiled module (for v2.2.5 kernel)
+  config/Config.in   - sample file to include cs89x0 driver in the kernel.
+  config/Makefile    - sample file to include cs89x0 driver in the kernel.
+  config/Space.c     - sample file to include cs89x0 driver in the kernel.
+
+
+
+1.3 SYSTEM REQUIREMENTS
+
+The following hardware is required:
+
+   * Cirrus Logic LAN (CS8900/20-based) Ethernet ISA Adapter   
+
+   * IBM or IBM-compatible PC with:
+     * An 80386 or higher processor
+     * 16 bytes of contiguous IO space available between 210h - 370h
+     * One available IRQ (5,10,11,or 12 for the CS8900, 3-7,9-15 for CS8920).
+
+   * Appropriate cable (and connector for AUI, 10BASE-2) for your network
+     topology.
+
+The following software is required:
+
+* LINUX kernel version 2.3.48 or higher
+
+   * CS8900/20 Setup Utility (DOS-based)
+
+   * LINUX kernel sources for your kernel (if compiling into kernel)
+
+   * GNU Toolkit (gcc and make) v2.6 or above (if compiling into kernel 
+     or a module)   
+
+
+
+1.4 LICENSING INFORMATION
+
+This program is free software; you can redistribute it and/or modify it under
+the terms of the GNU General Public License as published by the Free Software
+Foundation, version 1.
+
+This program is distributed in the hope that it will be useful, but WITHOUT
+ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 
+FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for 
+more details.
+
+For a full copy of the GNU General Public License, write to the Free Software
+Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+
+
+2.0 ADAPTER INSTALLATION and CONFIGURATION
+===============================================================================
+
+Both the CS8900 and CS8920-based adapters can be configured using parameters 
+stored in an on-board EEPROM. You must use the DOS-based CS8900/20 Setup 
+Utility if you want to change the adapter's configuration in EEPROM.  
+
+When loading the driver as a module, you can specify many of the adapter's 
+configuration parameters on the command-line to override the EEPROM's settings 
+or for interface configuration when an EEPROM is not used. (CS8920-based 
+adapters must use an EEPROM.) See Section 3.0 LOADING THE DRIVER AS A MODULE.
+
+Since the CS8900/20 Setup Utility is a DOS-based application, you must install 
+and configure the adapter in a DOS-based system using the CS8900/20 Setup 
+Utility before installation in the target LINUX system.  (Not required if 
+installing a CS8900-based adapter and the default configuration is acceptable.)
+     
+
+2.1 CS8900-BASED ADAPTER CONFIGURATION
+
+CS8900-based adapters shipped from Cirrus Logic have been configured 
+with the following "default" settings:
+
+  Operation Mode:      Memory Mode
+  IRQ:                 10
+  Base I/O Address:    300
+  Memory Base Address: D0000
+  Optimization:	       DOS Client
+  Transmission Mode:   Half-duplex
+  BootProm:            None
+  Media Type:	       Autodetect (3-media cards) or 
+                       10BASE-T (10BASE-T only adapter)
+
+You should only change the default configuration settings if conflicts with 
+another adapter exists. To change the adapter's configuration, run the 
+CS8900/20 Setup Utility. 
+
+
+2.2 CS8920-BASED ADAPTER CONFIGURATION
+
+CS8920-based adapters are shipped from Cirrus Logic configured as Plug
+and Play (PnP) enabled.  However, since the cs89x0 driver does NOT
+support PnP, you must install the CS8920 adapter in a DOS-based PC and
+run the CS8900/20 Setup Utility to disable PnP and configure the
+adapter before installation in the target Linux system.  Failure to do
+this will leave the adapter inactive and the driver will be unable to
+communicate with the adapter.  
+
+
+        **************************************************************** 
+        *                    CS8920-BASED ADAPTERS:                    *
+        *                                                              * 
+        * CS8920-BASED ADAPTERS ARE PLUG and PLAY ENABLED BY DEFAULT.  * 
+        * THE CS89X0 DRIVER DOES NOT SUPPORT PnP. THEREFORE, YOU MUST  *
+        * RUN THE CS8900/20 SETUP UTILITY TO DISABLE PnP SUPPORT AND   *
+        * TO ACTIVATE THE ADAPTER.                                     *
+        ****************************************************************
+
+
+
+
+3.0 LOADING THE DRIVER AS A MODULE
+===============================================================================
+
+If the driver is compiled as a loadable module, you can load the driver module
+with the 'modprobe' command.  Many of the adapter's configuration parameters can 
+be specified as command-line arguments to the load command.  This facility 
+provides a means to override the EEPROM's settings or for interface 
+configuration when an EEPROM is not used.
+
+Example:
+
+    insmod cs89x0.o io=0x200 irq=0xA media=aui
+
+This example loads the module and configures the adapter to use an IO port base
+address of 200h, interrupt 10, and use the AUI media connection.  The following
+configuration options are available on the command line:
+
+* io=###               - specify IO address (200h-360h)
+* irq=##               - specify interrupt level
+* use_dma=1            - Enable DMA
+* dma=#                - specify dma channel (Driver is compiled to support
+                         Rx DMA only)
+* dmasize=# (16 or 64) - DMA size 16K or 64K.  Default value is set to 16.
+* media=rj45           - specify media type
+   or media=bnc
+   or media=aui
+   or media=auto
+* duplex=full          - specify forced half/full/autonegotiate duplex
+   or duplex=half
+   or duplex=auto
+* debug=#              - debug level (only available if the driver was compiled
+                         for debugging)
+
+NOTES:
+
+a) If an EEPROM is present, any specified command-line parameter
+   will override the corresponding configuration value stored in
+   EEPROM.
+
+b) The "io" parameter must be specified on the command-line.  
+
+c) The driver's hardware probe routine is designed to avoid
+   writing to I/O space until it knows that there is a cs89x0
+   card at the written addresses.  This could cause problems
+   with device probing.  To avoid this behaviour, add one
+   to the `io=' module parameter.  This doesn't actually change
+   the I/O address, but it is a flag to tell the driver
+   to partially initialise the hardware before trying to
+   identify the card.  This could be dangerous if you are
+   not sure that there is a cs89x0 card at the provided address.
+
+   For example, to scan for an adapter located at IO base 0x300,
+   specify an IO address of 0x301.  
+
+d) The "duplex=auto" parameter is only supported for the CS8920.
+
+e) The minimum command-line configuration required if an EEPROM is
+   not present is:
+
+   io 
+   irq 
+   media type (no autodetect)
+
+f) The following additional parameters are CS89XX defaults (values
+   used with no EEPROM or command-line argument).
+
+   * DMA Burst = enabled
+   * IOCHRDY Enabled = enabled
+   * UseSA = enabled
+   * CS8900 defaults to half-duplex if not specified on command-line
+   * CS8920 defaults to autoneg if not specified on command-line
+   * Use reset defaults for other config parameters
+   * dma_mode = 0
+
+g) You can use ifconfig to set the adapter's Ethernet address.
+
+h) Many Linux distributions use the 'modprobe' command to load
+   modules.  This program uses the '/etc/conf.modules' file to
+   determine configuration information which is passed to a driver
+   module when it is loaded.  All the configuration options which are
+   described above may be placed within /etc/conf.modules.
+
+   For example:
+
+   > cat /etc/conf.modules
+   ...
+   alias eth0 cs89x0
+   options cs89x0 io=0x0200 dma=5 use_dma=1
+   ...
+
+   In this example we are telling the module system that the
+   ethernet driver for this machine should use the cs89x0 driver.  We
+   are asking 'modprobe' to pass the 'io', 'dma' and 'use_dma'
+   arguments to the driver when it is loaded.
+
+i) Cirrus recommend that the cs89x0 use the ISA DMA channels 5, 6 or
+   7.  You will probably find that other DMA channels will not work.
+
+j) The cs89x0 supports DMA for receiving only.  DMA mode is
+   significantly more efficient.  Flooding a 400 MHz Celeron machine
+   with large ping packets consumes 82% of its CPU capacity in non-DMA
+   mode.  With DMA this is reduced to 45%.
+
+k) If your Linux kernel was compiled with inbuilt plug-and-play
+   support you will be able to find information about the cs89x0 card
+   with the command
+
+   cat /proc/isapnp
+
+l) If during DMA operation you find erratic behavior or network data
+   corruption you should use your PC's BIOS to slow the EISA bus clock.
+
+m) If the cs89x0 driver is compiled directly into the kernel
+   (non-modular) then its I/O address is automatically determined by
+   ISA bus probing.  The IRQ number, media options, etc are determined
+   from the card's EEPROM.
+
+n) If the cs89x0 driver is compiled directly into the kernel, DMA
+   mode may be selected by providing the kernel with a boot option
+   'cs89x0_dma=N' where 'N' is the desired DMA channel number (5, 6 or 7).
+
+   Kernel boot options may be provided on the LILO command line:
+
+	LILO boot: linux cs89x0_dma=5
+
+   or they may be placed in /etc/lilo.conf:
+
+	image=/boot/bzImage-2.3.48
+	  append="cs89x0_dma=5"
+	  label=linux
+	  root=/dev/hda5
+	  read-only
+
+   The DMA Rx buffer size is hardwired to 16 kbytes in this mode.
+   (64k mode is not available).
+
+
+4.0 COMPILING THE DRIVER
+===============================================================================
+
+The cs89x0 driver can be compiled directly into the kernel or compiled into
+a loadable device driver module.
+
+
+4.1 COMPILING THE DRIVER AS A LOADABLE MODULE
+
+To compile the driver into a loadable module, use the following command 
+(single command line, without quotes):
+
+"gcc -D__KERNEL__ -I/usr/src/linux/include -I/usr/src/linux/net/inet -Wall 
+-Wstrict-prototypes -O2 -fomit-frame-pointer -DMODULE -DCONFIG_MODVERSIONS 
+-c cs89x0.c"
+
+4.2 COMPILING THE DRIVER TO SUPPORT MEMORY MODE
+
+Support for memory mode was not carried over into the 2.3 series kernels.
+
+4.3 COMPILING THE DRIVER TO SUPPORT Rx DMA
+
+The compile-time optionality for DMA was removed in the 2.3 kernel
+series.  DMA support is now unconditionally part of the driver.  It is
+enabled by the 'use_dma=1' module option.
+
+
+5.0 TESTING AND TROUBLESHOOTING
+===============================================================================
+
+5.1 KNOWN DEFECTS and LIMITATIONS
+
+Refer to the RELEASE.TXT file distributed as part of this archive for a list of 
+known defects, driver limitations, and work arounds.
+
+
+5.2 TESTING THE ADAPTER
+
+Once the adapter has been installed and configured, the diagnostic option of 
+the CS8900/20 Setup Utility can be used to test the functionality of the 
+adapter and its network connection.  Use the diagnostics 'Self Test' option to
+test the functionality of the adapter with the hardware configuration you have
+assigned. You can use the diagnostics 'Network Test' to test the ability of the
+adapter to communicate across the Ethernet with another PC equipped with a 
+CS8900/20-based adapter card (it must also be running the CS8900/20 Setup 
+Utility).
+
+         NOTE: The Setup Utility's diagnostics are designed to run in a
+         DOS-only operating system environment.  DO NOT run the diagnostics 
+         from a DOS or command prompt session under Windows 95, Windows NT, 
+         OS/2, or other operating system.
+
+To run the diagnostics tests on the CS8900/20 adapter:
+
+   1.) Boot DOS on the PC and start the CS8900/20 Setup Utility.
+
+   2.) The adapter's current configuration is displayed.  Hit the ENTER key to
+       get to the main menu.
+
+   4.) Select 'Diagnostics' (ALT-G) from the main menu.  
+       * Select 'Self-Test' to test the adapter's basic functionality.
+       * Select 'Network Test' to test the network connection and cabling.
+
+
+5.2.1 DIAGNOSTIC SELF-TEST
+
+The diagnostic self-test checks the adapter's basic functionality as well as 
+its ability to communicate across the ISA bus based on the system resources 
+assigned during hardware configuration.  The following tests are performed:
+
+   * IO Register Read/Write Test
+     The IO Register Read/Write test insures that the CS8900/20 can be 
+     accessed in IO mode, and that the IO base address is correct.
+
+   * Shared Memory Test
+     The Shared Memory test insures the CS8900/20 can be accessed in memory 
+     mode and that the range of memory addresses assigned does not conflict 
+     with other devices in the system.
+
+   * Interrupt Test
+     The Interrupt test insures there are no conflicts with the assigned IRQ
+     signal.
+
+   * EEPROM Test
+     The EEPROM test insures the EEPROM can be read.
+
+   * Chip RAM Test
+     The Chip RAM test insures the 4K of memory internal to the CS8900/20 is
+     working properly.
+
+   * Internal Loop-back Test
+     The Internal Loop Back test insures the adapter's transmitter and 
+     receiver are operating properly.  If this test fails, make sure the 
+     adapter's cable is connected to the network (check for LED activity for 
+     example).
+
+   * Boot PROM Test
+     The Boot PROM  test insures the Boot PROM is present, and can be read.
+     Failure indicates the Boot PROM  was not successfully read due to a
+     hardware problem or due to a conflicts on the Boot PROM address
+     assignment. (Test only applies if the adapter is configured to use the
+     Boot PROM option.)
+
+Failure of a test item indicates a possible system resource conflict with 
+another device on the ISA bus.  In this case, you should use the Manual Setup 
+option to reconfigure the adapter by selecting a different value for the system
+resource that failed.
+
+
+5.2.2 DIAGNOSTIC NETWORK TEST
+
+The Diagnostic Network Test verifies a working network connection by 
+transferring data between two CS8900/20 adapters installed in different PCs 
+on the same network. (Note: the diagnostic network test should not be run 
+between two nodes across a router.) 
+
+This test requires that each of the two PCs have a CS8900/20-based adapter
+installed and have the CS8900/20 Setup Utility running.  The first PC is 
+configured as a Responder and the other PC is configured as an Initiator.  
+Once the Initiator is started, it sends data frames to the Responder which 
+returns the frames to the Initiator.
+
+The total number of frames received and transmitted are displayed on the 
+Initiator's display, along with a count of the number of frames received and 
+transmitted OK or in error.  The test can be terminated anytime by the user at 
+either PC.
+
+To setup the Diagnostic Network Test:
+
+    1.) Select a PC with a CS8900/20-based adapter and a known working network
+        connection to act as the Responder.  Run the CS8900/20 Setup Utility 
+        and select 'Diagnostics -> Network Test -> Responder' from the main 
+        menu.  Hit ENTER to start the Responder.
+
+    2.) Return to the PC with the CS8900/20-based adapter you want to test and
+        start the CS8900/20 Setup Utility. 
+
+    3.) From the main menu, Select 'Diagnostic -> Network Test -> Initiator'.
+        Hit ENTER to start the test.
+ 
+You may stop the test on the Initiator at any time while allowing the Responder
+to continue running.  In this manner, you can move to additional PCs and test 
+them by starting the Initiator on another PC without having to stop/start the 
+Responder.
+ 
+
+
+5.3 USING THE ADAPTER'S LEDs
+
+The 2 and 3-media adapters have two LEDs visible on the back end of the board 
+located near the 10Base-T connector.  
+
+Link Integrity LED: A "steady" ON of the green LED indicates a valid 10Base-T 
+connection.  (Only applies to 10Base-T.  The green LED has no significance for
+a 10Base-2 or AUI connection.)
+
+TX/RX LED: The yellow LED lights briefly each time the adapter transmits or 
+receives data. (The yellow LED will appear to "flicker" on a typical network.)
+
+
+5.4 RESOLVING I/O CONFLICTS
+
+An IO conflict occurs when two or more adapter use the same ISA resource (IO 
+address, memory address or IRQ).  You can usually detect an IO conflict in one 
+of four ways after installing and or configuring the CS8900/20-based adapter:
+
+    1.) The system does not boot properly (or at all).
+
+    2.) The driver cannot communicate with the adapter, reporting an "Adapter
+        not found" error message.
+
+    3.) You cannot connect to the network or the driver will not load.
+
+    4.) If you have configured the adapter to run in memory mode but the driver
+        reports it is using IO mode when loading, this is an indication of a
+        memory address conflict.
+
+If an IO conflict occurs, run the CS8900/20 Setup Utility and perform a 
+diagnostic self-test.  Normally, the ISA resource in conflict will fail the 
+self-test.  If so, reconfigure the adapter selecting another choice for the 
+resource in conflict.  Run the diagnostics again to check for further IO 
+conflicts.
+
+In some cases, such as when the PC will not boot, it may be necessary to remove
+the adapter and reconfigure it by installing it in another PC to run the 
+CS8900/20 Setup Utility.  Once reinstalled in the target system, run the 
+diagnostics self-test to ensure the new configuration is free of conflicts 
+before loading the driver again.
+
+When manually configuring the adapter, keep in mind the typical ISA system 
+resource usage as indicated in the tables below.
+
+I/O Address    	Device                        IRQ      Device
+-----------    	--------                      ---      --------
+ 200-20F       	Game I/O adapter               3       COM2, Bus Mouse
+ 230-23F       	Bus Mouse                      4       COM1
+ 270-27F       	LPT3: third parallel port      5       LPT2
+ 2F0-2FF       	COM2: second serial port       6       Floppy Disk controller
+ 320-32F       	Fixed disk controller          7       LPT1
+                                      	       8       Real-time Clock
+                                                 9       EGA/VGA display adapter    
+                                                12       Mouse (PS/2)                              
+Memory Address  Device                          13       Math Coprocessor
+--------------  ---------------------           14       Hard Disk controller
+A000-BFFF	EGA Graphics Adapter
+A000-C7FF	VGA Graphics Adapter
+B000-BFFF	Mono Graphics Adapter
+B800-BFFF	Color Graphics Adapter
+E000-FFFF	AT BIOS
+
+
+
+
+6.0 TECHNICAL SUPPORT
+===============================================================================
+
+6.1 CONTACTING CIRRUS LOGIC'S TECHNICAL SUPPORT
+
+Cirrus Logic's CS89XX Technical Application Support can be reached at:
+
+Telephone  :(800) 888-5016 (from inside U.S. and Canada)
+           :(512) 442-7555 (from outside the U.S. and Canada)
+Fax        :(512) 912-3871
+Email      :ethernet@crystal.cirrus.com
+WWW        :http://www.cirrus.com
+
+
+6.2 INFORMATION REQUIRED BEFORE CONTACTING TECHNICAL SUPPORT
+
+Before contacting Cirrus Logic for technical support, be prepared to provide as 
+Much of the following information as possible. 
+
+1.) Adapter type (CRD8900, CDB8900, CDB8920, etc.)
+
+2.) Adapter configuration
+
+    * IO Base, Memory Base, IO or memory mode enabled, IRQ, DMA channel
+    * Plug and Play enabled/disabled (CS8920-based adapters only)
+    * Configured for media auto-detect or specific media type (which type).    
+
+3.) PC System's Configuration
+
+    * Plug and Play system (yes/no)
+    * BIOS (make and version)
+    * System make and model
+    * CPU (type and speed)
+    * System RAM
+    * SCSI Adapter
+
+4.) Software
+
+    * CS89XX driver and version
+    * Your network operating system and version
+    * Your system's OS version 
+    * Version of all protocol support files
+
+5.) Any Error Message displayed.
+
+
+
+6.3 OBTAINING THE LATEST DRIVER VERSION
+
+You can obtain the latest CS89XX drivers and support software from Cirrus Logic's 
+Web site.  You can also contact Cirrus Logic's Technical Support (email:
+ethernet@crystal.cirrus.com) and request that you be registered for automatic 
+software-update notification.
+
+Cirrus Logic maintains a web page at http://www.cirrus.com with the
+latest drivers and technical publications.
+
+
+6.4 Current maintainer
+
+In February 2000 the maintenance of this driver was assumed by Andrew
+Morton.
+
+6.5 Kernel module parameters
+
+For use in embedded environments with no cs89x0 EEPROM, the kernel boot
+parameter `cs89x0_media=' has been implemented.  Usage is:
+
+	cs89x0_media=rj45    or
+	cs89x0_media=aui     or
+	cs89x0_media=bnc
+
diff --git a/Documentation/networking/device_drivers/davicom/dm9000.txt b/Documentation/networking/device_drivers/davicom/dm9000.txt
new file mode 100644
index 000000000000..5552e2e575c5
--- /dev/null
+++ b/Documentation/networking/device_drivers/davicom/dm9000.txt
@@ -0,0 +1,167 @@
+DM9000 Network driver
+=====================
+
+Copyright 2008 Simtec Electronics,
+	  Ben Dooks <ben@simtec.co.uk> <ben-linux@fluff.org>
+
+
+Introduction
+------------
+
+This file describes how to use the DM9000 platform-device based network driver
+that is contained in the files drivers/net/dm9000.c and drivers/net/dm9000.h.
+
+The driver supports three DM9000 variants, the DM9000E which is the first chip
+supported as well as the newer DM9000A and DM9000B devices. It is currently
+maintained and tested by Ben Dooks, who should be CC: to any patches for this
+driver.
+
+
+Defining the platform device
+----------------------------
+
+The minimum set of resources attached to the platform device are as follows:
+
+    1) The physical address of the address register
+    2) The physical address of the data register
+    3) The IRQ line the device's interrupt pin is connected to.
+
+These resources should be specified in that order, as the ordering of the
+two address regions is important (the driver expects these to be address
+and then data).
+
+An example from arch/arm/mach-s3c2410/mach-bast.c is:
+
+static struct resource bast_dm9k_resource[] = {
+	[0] = {
+		.start = S3C2410_CS5 + BAST_PA_DM9000,
+		.end   = S3C2410_CS5 + BAST_PA_DM9000 + 3,
+		.flags = IORESOURCE_MEM,
+	},
+	[1] = {
+		.start = S3C2410_CS5 + BAST_PA_DM9000 + 0x40,
+		.end   = S3C2410_CS5 + BAST_PA_DM9000 + 0x40 + 0x3f,
+		.flags = IORESOURCE_MEM,
+	},
+	[2] = {
+		.start = IRQ_DM9000,
+		.end   = IRQ_DM9000,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
+	}
+};
+
+static struct platform_device bast_device_dm9k = {
+	.name		= "dm9000",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(bast_dm9k_resource),
+	.resource	= bast_dm9k_resource,
+};
+
+Note the setting of the IRQ trigger flag in bast_dm9k_resource[2].flags,
+as this will generate a warning if it is not present. The trigger from
+the flags field will be passed to request_irq() when registering the IRQ
+handler to ensure that the IRQ is setup correctly.
+
+This shows a typical platform device, without the optional configuration
+platform data supplied. The next example uses the same resources, but adds
+the optional platform data to pass extra configuration data:
+
+static struct dm9000_plat_data bast_dm9k_platdata = {
+	.flags		= DM9000_PLATF_16BITONLY,
+};
+
+static struct platform_device bast_device_dm9k = {
+	.name		= "dm9000",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(bast_dm9k_resource),
+	.resource	= bast_dm9k_resource,
+	.dev		= {
+		.platform_data = &bast_dm9k_platdata,
+	}
+};
+
+The platform data is defined in include/linux/dm9000.h and described below.
+
+
+Platform data
+-------------
+
+Extra platform data for the DM9000 can describe the IO bus width to the
+device, whether or not an external PHY is attached to the device and
+the availability of an external configuration EEPROM.
+
+The flags for the platform data .flags field are as follows:
+
+DM9000_PLATF_8BITONLY
+
+	The IO should be done with 8bit operations.
+
+DM9000_PLATF_16BITONLY
+
+	The IO should be done with 16bit operations.
+
+DM9000_PLATF_32BITONLY
+
+	The IO should be done with 32bit operations.
+
+DM9000_PLATF_EXT_PHY
+
+	The chip is connected to an external PHY.
+
+DM9000_PLATF_NO_EEPROM
+
+	This can be used to signify that the board does not have an
+	EEPROM, or that the EEPROM should be hidden from the user.
+
+DM9000_PLATF_SIMPLE_PHY
+
+	Switch to using the simpler PHY polling method which does not
+	try and read the MII PHY state regularly. This is only available
+	when using the internal PHY. See the section on link state polling
+	for more information.
+
+	The config symbol DM9000_FORCE_SIMPLE_PHY_POLL, Kconfig entry
+	"Force simple NSR based PHY polling" allows this flag to be
+	forced on at build time.
+
+
+PHY Link state polling
+----------------------
+
+The driver keeps track of the link state and informs the network core
+about link (carrier) availability. This is managed by several methods
+depending on the version of the chip and on which PHY is being used.
+
+For the internal PHY, the original (and currently default) method is
+to read the MII state, either when the status changes if we have the
+necessary interrupt support in the chip or every two seconds via a
+periodic timer.
+
+To reduce the overhead for the internal PHY, there is now the option
+of using the DM9000_FORCE_SIMPLE_PHY_POLL config, or DM9000_PLATF_SIMPLE_PHY
+platform data option to read the summary information without the
+expensive MII accesses. This method is faster, but does not print
+as much information.
+
+When using an external PHY, the driver currently has to poll the MII
+link status as there is no method for getting an interrupt on link change.
+
+
+DM9000A / DM9000B
+-----------------
+
+These chips are functionally similar to the DM9000E and are supported easily
+by the same driver. The features are:
+
+   1) Interrupt on internal PHY state change. This means that the periodic
+      polling of the PHY status may be disabled on these devices when using
+      the internal PHY.
+
+   2) TCP/UDP checksum offloading, which the driver does not currently support.
+
+
+ethtool
+-------
+
+The driver supports the ethtool interface for access to the driver
+state information, the PHY state and the EEPROM.
diff --git a/Documentation/networking/device_drivers/dec/de4x5.txt b/Documentation/networking/device_drivers/dec/de4x5.txt
new file mode 100644
index 000000000000..c8e4ca9b2c3e
--- /dev/null
+++ b/Documentation/networking/device_drivers/dec/de4x5.txt
@@ -0,0 +1,178 @@
+    Originally,   this  driver  was    written  for the  Digital   Equipment
+    Corporation series of EtherWORKS Ethernet cards:
+
+        DE425 TP/COAX EISA
+	DE434 TP PCI
+	DE435 TP/COAX/AUI PCI
+	DE450 TP/COAX/AUI PCI
+	DE500 10/100 PCI Fasternet
+
+    but it  will  now attempt  to  support all  cards which   conform to the
+    Digital Semiconductor   SROM   Specification.    The  driver   currently
+    recognises the following chips:
+
+        DC21040  (no SROM) 
+	DC21041[A]  
+	DC21140[A] 
+	DC21142 
+	DC21143 
+
+    So far the driver is known to work with the following cards:
+
+        KINGSTON
+	Linksys
+	ZNYX342
+	SMC8432
+	SMC9332 (w/new SROM)
+	ZNYX31[45]
+	ZNYX346 10/100 4 port (can act as a 10/100 bridge!) 
+
+    The driver has been tested on a relatively busy network using the DE425,
+    DE434, DE435 and DE500 cards and benchmarked with 'ttcp': it transferred
+    16M of data to a DECstation 5000/200 as follows:
+
+                TCP           UDP
+             TX     RX     TX     RX
+    DE425   1030k  997k   1170k  1128k
+    DE434   1063k  995k   1170k  1125k
+    DE435   1063k  995k   1170k  1125k
+    DE500   1063k  998k   1170k  1125k  in 10Mb/s mode
+
+    All  values are typical (in   kBytes/sec) from a  sample  of 4 for  each
+    measurement. Their error is +/-20k on a quiet (private) network and also
+    depend on what load the CPU has.
+
+    =========================================================================
+
+    The ability to load this  driver as a loadable  module has been included
+    and used extensively  during the driver development  (to save those long
+    reboot sequences).  Loadable module support  under PCI and EISA has been
+    achieved by letting the driver autoprobe as if it were compiled into the
+    kernel. Do make sure  you're not sharing  interrupts with anything  that
+    cannot accommodate  interrupt  sharing!
+
+    To utilise this ability, you have to do 8 things:
+
+    0) have a copy of the loadable modules code installed on your system.
+    1) copy de4x5.c from the  /linux/drivers/net directory to your favourite
+    temporary directory.
+    2) for fixed  autoprobes (not  recommended),  edit the source code  near
+    line 5594 to reflect the I/O address  you're using, or assign these when
+    loading by:
+
+                   insmod de4x5 io=0xghh           where g = bus number
+		                                        hh = device number   
+
+       NB: autoprobing for modules is now supported by default. You may just
+           use:
+
+                   insmod de4x5
+
+           to load all available boards. For a specific board, still use
+	   the 'io=?' above.
+    3) compile  de4x5.c, but include -DMODULE in  the command line to ensure
+    that the correct bits are compiled (see end of source code).
+    4) if you are wanting to add a new  card, goto 5. Otherwise, recompile a
+    kernel with the de4x5 configuration turned off and reboot.
+    5) insmod de4x5 [io=0xghh]
+    6) run the net startup bits for your new eth?? interface(s) manually 
+    (usually /etc/rc.inet[12] at boot time). 
+    7) enjoy!
+
+    To unload a module, turn off the associated interface(s) 
+    'ifconfig eth?? down' then 'rmmod de4x5'.
+
+    Automedia detection is included so that in  principle you can disconnect
+    from, e.g.  TP, reconnect  to BNC  and  things will still work  (after a
+    pause whilst the   driver figures out   where its media went).  My tests
+    using ping showed that it appears to work....
+
+    By  default,  the driver will  now   autodetect any  DECchip based card.
+    Should you have a need to restrict the driver to DIGITAL only cards, you
+    can compile with a  DEC_ONLY define, or if  loading as a module, use the
+    'dec_only=1'  parameter. 
+
+    I've changed the timing routines to  use the kernel timer and scheduling
+    functions  so that the  hangs  and other assorted problems that occurred
+    while autosensing the  media  should be gone.  A  bonus  for the DC21040
+    auto  media sense algorithm is  that it can now  use one that is more in
+    line with the  rest (the DC21040  chip doesn't  have a hardware  timer).
+    The downside is the 1 'jiffies' (10ms) resolution.
+
+    IEEE 802.3u MII interface code has  been added in anticipation that some
+    products may use it in the future.
+
+    The SMC9332 card  has a non-compliant SROM  which needs fixing -  I have
+    patched this  driver to detect it  because the SROM format used complies
+    to a previous DEC-STD format.
+
+    I have removed the buffer copies needed for receive on Intels.  I cannot
+    remove them for   Alphas since  the  Tulip hardware   only does longword
+    aligned  DMA transfers  and  the  Alphas get   alignment traps with  non
+    longword aligned data copies (which makes them really slow). No comment.
+
+    I  have added SROM decoding  routines to make this  driver work with any
+    card that  supports the Digital  Semiconductor SROM spec. This will help
+    all  cards running the dc2114x  series chips in particular.  Cards using
+    the dc2104x  chips should run correctly with  the basic  driver.  I'm in
+    debt to <mjacob@feral.com> for the  testing and feedback that helped get
+    this feature working.  So far we have  tested KINGSTON, SMC8432, SMC9332
+    (with the latest SROM complying  with the SROM spec  V3: their first was
+    broken), ZNYX342  and  LinkSys. ZNYX314 (dual  21041  MAC) and  ZNYX 315
+    (quad 21041 MAC)  cards also  appear  to work despite their  incorrectly
+    wired IRQs.
+
+    I have added a temporary fix for interrupt problems when some SCSI cards
+    share the same interrupt as the DECchip based  cards. The problem occurs
+    because  the SCSI card wants to  grab the interrupt  as a fast interrupt
+    (runs the   service routine with interrupts turned   off) vs.  this card
+    which really needs to run the service routine with interrupts turned on.
+    This driver will  now   add the interrupt service   routine  as  a  fast
+    interrupt if it   is bounced from the   slow interrupt.  THIS IS NOT   A
+    RECOMMENDED WAY TO RUN THE DRIVER  and has been done  for a limited time
+    until  people   sort  out their  compatibility    issues and the  kernel
+    interrupt  service code  is  fixed.   YOU  SHOULD SEPARATE OUT  THE FAST
+    INTERRUPT CARDS FROM THE SLOW INTERRUPT CARDS to ensure that they do not
+    run on the same interrupt. PCMCIA/CardBus is another can of worms...
+
+    Finally, I think  I have really  fixed  the module  loading problem with
+    more than one DECchip based  card.  As a  side effect, I don't mess with
+    the  device structure any  more which means that  if more than 1 card in
+    2.0.x is    installed (4  in   2.1.x),  the  user   will have   to  edit
+    linux/drivers/net/Space.c  to make room for  them. Hence, module loading
+    is  the preferred way to use   this driver, since  it  doesn't have this
+    limitation.
+
+    Where SROM media  detection is used and  full duplex is specified in the
+    SROM,  the feature is  ignored unless  lp->params.fdx  is set at compile
+    time  OR during  a   module load  (insmod  de4x5   args='eth??:fdx' [see
+    below]).  This is because there  is no way  to automatically detect full
+    duplex   links  except through   autonegotiation.    When I  include the
+    autonegotiation feature in  the SROM autoconf  code, this detection will
+    occur automatically for that case.
+
+    Command line  arguments are  now allowed, similar to  passing  arguments
+    through LILO. This will allow a per adapter board set  up of full duplex
+    and media. The only lexical constraints are:  the board name (dev->name)
+    appears in  the list before its parameters.  The list of parameters ends
+    either at the end of the parameter list or with another board name.  The
+    following parameters are allowed:
+
+            fdx        for full duplex
+	    autosense  to set the media/speed; with the following 
+	               sub-parameters:
+		       TP, TP_NW, BNC, AUI, BNC_AUI, 100Mb, 10Mb, AUTO
+
+    Case sensitivity is important  for  the sub-parameters. They *must*   be
+    upper case. Examples:
+
+        insmod de4x5 args='eth1:fdx autosense=BNC eth0:autosense=100Mb'.
+
+    For a compiled in driver, in linux/drivers/net/CONFIG, place e.g.
+	DE4X5_OPTS = -DDE4X5_PARM='"eth0:fdx autosense=AUI eth2:autosense=TP"' 
+
+    Yes,  I know full duplex  isn't permissible on BNC  or AUI; they're just
+    examples. By default, full duplex is turned  off and AUTO is the default
+    autosense setting. In  reality, I expect only the  full duplex option to
+    be used. Note the use of single quotes in the two examples above and the
+    lack of commas to separate items.
diff --git a/Documentation/networking/device_drivers/dec/dmfe.txt b/Documentation/networking/device_drivers/dec/dmfe.txt
new file mode 100644
index 000000000000..25320bf19c86
--- /dev/null
+++ b/Documentation/networking/device_drivers/dec/dmfe.txt
@@ -0,0 +1,66 @@
+Note: This driver doesn't have a maintainer.
+
+Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver for Linux.
+
+This program is free software; you can redistribute it and/or
+modify it under the terms of the GNU General   Public License
+as published by the Free Software Foundation; either version 2
+of the License, or (at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+
+This driver provides kernel support for Davicom DM9102(A)/DM9132/DM9801 ethernet cards ( CNET
+10/100 ethernet cards uses Davicom chipset too, so this driver supports CNET cards too ).If you
+didn't compile this driver as a module, it will automatically load itself on boot and print a
+line similar to :
+
+	dmfe: Davicom DM9xxx net driver, version 1.36.4 (2002-01-17)
+
+If you compiled this driver as a module, you have to load it on boot.You can load it with command :
+
+	insmod dmfe
+
+This way it will autodetect the device mode.This is the suggested way to load the module.Or you can pass
+a mode= setting to module while loading, like :
+
+	insmod dmfe mode=0 # Force 10M Half Duplex
+	insmod dmfe mode=1 # Force 100M Half Duplex
+	insmod dmfe mode=4 # Force 10M Full Duplex
+	insmod dmfe mode=5 # Force 100M Full Duplex
+
+Next you should configure your network interface with a command similar to :
+
+	ifconfig eth0 172.22.3.18
+                      ^^^^^^^^^^^
+		     Your IP Address
+
+Then you may have to modify the default routing table with command :
+
+	route add default eth0
+
+
+Now your ethernet card should be up and running.
+
+
+TODO:
+
+Implement pci_driver::suspend() and pci_driver::resume() power management methods.
+Check on 64 bit boxes.
+Check and fix on big endian boxes.
+Test and make sure PCI latency is now correct for all cases.
+
+
+Authors:
+
+Sten Wang <sten_wang@davicom.com.tw >   : Original Author
+
+Contributors:
+
+Marcelo Tosatti <marcelo@conectiva.com.br>
+Alan Cox <alan@lxorguk.ukuu.org.uk>
+Jeff Garzik <jgarzik@pobox.com>
+Vojtech Pavlik <vojtech@suse.cz>
diff --git a/Documentation/networking/device_drivers/dlink/dl2k.txt b/Documentation/networking/device_drivers/dlink/dl2k.txt
new file mode 100644
index 000000000000..cba74f7a3abc
--- /dev/null
+++ b/Documentation/networking/device_drivers/dlink/dl2k.txt
@@ -0,0 +1,282 @@
+
+    D-Link DL2000-based Gigabit Ethernet Adapter Installation
+    for Linux
+    May 23, 2002
+
+Contents
+========
+ - Compatibility List
+ - Quick Install
+ - Compiling the Driver
+ - Installing the Driver
+ - Option parameter
+ - Configuration Script Sample
+ - Troubleshooting
+
+
+Compatibility List
+=================
+Adapter Support:
+
+D-Link DGE-550T Gigabit Ethernet Adapter.
+D-Link DGE-550SX Gigabit Ethernet Adapter.
+D-Link DL2000-based Gigabit Ethernet Adapter.
+
+
+The driver support Linux kernel 2.4.7 later. We had tested it
+on the environments below.
+
+ . Red Hat v6.2 (update kernel to 2.4.7)
+ . Red Hat v7.0 (update kernel to 2.4.7)
+ . Red Hat v7.1 (kernel 2.4.7)
+ . Red Hat v7.2 (kernel 2.4.7-10)
+
+
+Quick Install
+=============
+Install linux driver as following command:
+
+1. make all
+2. insmod dl2k.ko
+3. ifconfig eth0 up 10.xxx.xxx.xxx netmask 255.0.0.0
+		    ^^^^^^^^^^^^^^^\	    ^^^^^^^^\
+				    IP		     NETMASK
+Now eth0 should active, you can test it by "ping" or get more information by
+"ifconfig". If tested ok, continue the next step.
+
+4. cp dl2k.ko /lib/modules/`uname -r`/kernel/drivers/net
+5. Add the following line to /etc/modprobe.d/dl2k.conf:
+	alias eth0 dl2k
+6. Run depmod to updated module indexes.
+7. Run "netconfig" or "netconf" to create configuration script ifcfg-eth0
+   located at /etc/sysconfig/network-scripts or create it manually.
+   [see - Configuration Script Sample]
+8. Driver will automatically load and configure at next boot time.
+
+Compiling the Driver
+====================
+  In Linux, NIC drivers are most commonly configured as loadable modules.
+The approach of building a monolithic kernel has become obsolete. The driver
+can be compiled as part of a monolithic kernel, but is strongly discouraged.
+The remainder of this section assumes the driver is built as a loadable module.
+In the Linux environment, it is a good idea to rebuild the driver from the
+source instead of relying on a precompiled version. This approach provides
+better reliability since a precompiled driver might depend on libraries or
+kernel features that are not present in a given Linux installation.
+
+The 3 files necessary to build Linux device driver are dl2k.c, dl2k.h and
+Makefile. To compile, the Linux installation must include the gcc compiler,
+the kernel source, and the kernel headers. The Linux driver supports Linux
+Kernels 2.4.7. Copy the files to a directory and enter the following command
+to compile and link the driver:
+
+CD-ROM drive
+------------
+
+[root@XXX /] mkdir cdrom
+[root@XXX /] mount -r -t iso9660 -o conv=auto /dev/cdrom /cdrom
+[root@XXX /] cd root
+[root@XXX /root] mkdir dl2k
+[root@XXX /root] cd dl2k
+[root@XXX dl2k] cp /cdrom/linux/dl2k.tgz /root/dl2k
+[root@XXX dl2k] tar xfvz dl2k.tgz
+[root@XXX dl2k] make all
+
+Floppy disc drive
+-----------------
+
+[root@XXX /] cd root
+[root@XXX /root] mkdir dl2k
+[root@XXX /root] cd dl2k
+[root@XXX dl2k] mcopy a:/linux/dl2k.tgz /root/dl2k
+[root@XXX dl2k] tar xfvz dl2k.tgz
+[root@XXX dl2k] make all
+
+Installing the Driver
+=====================
+
+  Manual Installation
+  -------------------
+  Once the driver has been compiled, it must be loaded, enabled, and bound
+  to a protocol stack in order to establish network connectivity. To load a
+  module enter the command:
+
+  insmod dl2k.o
+
+  or
+
+  insmod dl2k.o <optional parameter>	; add parameter
+
+  ===============================================================
+   example: insmod dl2k.o media=100mbps_hd
+   or	    insmod dl2k.o media=3
+   or	    insmod dl2k.o media=3,2	; for 2 cards
+  ===============================================================
+
+  Please reference the list of the command line parameters supported by
+  the Linux device driver below.
+
+  The insmod command only loads the driver and gives it a name of the form
+  eth0, eth1, etc. To bring the NIC into an operational state,
+  it is necessary to issue the following command:
+
+  ifconfig eth0 up
+
+  Finally, to bind the driver to the active protocol (e.g., TCP/IP with
+  Linux), enter the following command:
+
+  ifup eth0
+
+  Note that this is meaningful only if the system can find a configuration
+  script that contains the necessary network information. A sample will be
+  given in the next paragraph.
+
+  The commands to unload a driver are as follows:
+
+  ifdown eth0
+  ifconfig eth0 down
+  rmmod dl2k.o
+
+  The following are the commands to list the currently loaded modules and
+  to see the current network configuration.
+
+  lsmod
+  ifconfig
+
+
+  Automated Installation
+  ----------------------
+  This section describes how to install the driver such that it is
+  automatically loaded and configured at boot time. The following description
+  is based on a Red Hat 6.0/7.0 distribution, but it can easily be ported to
+  other distributions as well.
+
+  Red Hat v6.x/v7.x
+  -----------------
+  1. Copy dl2k.o to the network modules directory, typically
+     /lib/modules/2.x.x-xx/net or /lib/modules/2.x.x/kernel/drivers/net.
+  2. Locate the boot module configuration file, most commonly in the
+     /etc/modprobe.d/ directory. Add the following lines:
+
+     alias ethx dl2k
+     options dl2k <optional parameters>
+
+     where ethx will be eth0 if the NIC is the only ethernet adapter, eth1 if
+     one other ethernet adapter is installed, etc. Refer to the table in the
+     previous section for the list of optional parameters.
+  3. Locate the network configuration scripts, normally the
+     /etc/sysconfig/network-scripts directory, and create a configuration
+     script named ifcfg-ethx that contains network information.
+  4. Note that for most Linux distributions, Red Hat included, a configuration
+     utility with a graphical user interface is provided to perform steps 2
+     and 3 above.
+
+
+Parameter Description
+=====================
+You can install this driver without any additional parameter. However, if you
+are going to have extensive functions then it is necessary to set extra
+parameter. Below is a list of the command line parameters supported by the
+Linux device
+driver.
+
+mtu=packet_size			- Specifies the maximum packet size. default
+				  is 1500.
+
+media=media_type		- Specifies the media type the NIC operates at.
+				  autosense	Autosensing active media.
+				  10mbps_hd	10Mbps half duplex.
+				  10mbps_fd	10Mbps full duplex.
+				  100mbps_hd	100Mbps half duplex.
+				  100mbps_fd	100Mbps full duplex.
+				  1000mbps_fd	1000Mbps full duplex.
+				  1000mbps_hd	1000Mbps half duplex.
+				  0		Autosensing active media.
+				  1		10Mbps half duplex.
+				  2		10Mbps full duplex.
+				  3		100Mbps half duplex.
+				  4		100Mbps full duplex.
+				  5          	1000Mbps half duplex.
+				  6          	1000Mbps full duplex.
+
+				  By default, the NIC operates at autosense.
+				  1000mbps_fd and 1000mbps_hd types are only
+				  available for fiber adapter.
+
+vlan=n				- Specifies the VLAN ID. If vlan=0, the
+				  Virtual Local Area Network (VLAN) function is
+				  disable.
+
+jumbo=[0|1]			- Specifies the jumbo frame support. If jumbo=1,
+				  the NIC accept jumbo frames. By default, this
+				  function is disabled.
+				  Jumbo frame usually improve the performance
+				  int gigabit.
+				  This feature need jumbo frame compatible 
+				  remote.
+				  
+rx_coalesce=m			- Number of rx frame handled each interrupt.
+rx_timeout=n			- Rx DMA wait time for an interrupt. 
+				  If set rx_coalesce > 0, hardware only assert 
+				  an interrupt for m frames. Hardware won't 
+				  assert rx interrupt until m frames received or
+				  reach timeout of n * 640 nano seconds. 
+				  Set proper rx_coalesce and rx_timeout can 
+				  reduce congestion collapse and overload which
+				  has been a bottleneck for high speed network.
+				  
+				  For example, rx_coalesce=10 rx_timeout=800.
+				  that is, hardware assert only 1 interrupt 
+				  for 10 frames received or timeout of 512 us. 
+
+tx_coalesce=n			- Number of tx frame handled each interrupt.
+				  Set n > 1 can reduce the interrupts 
+				  congestion usually lower performance of
+				  high speed network card. Default is 16.
+				  
+tx_flow=[1|0]			- Specifies the Tx flow control. If tx_flow=0, 
+				  the Tx flow control disable else driver
+				  autodetect.
+rx_flow=[1|0]			- Specifies the Rx flow control. If rx_flow=0, 
+				  the Rx flow control enable else driver
+				  autodetect.
+
+
+Configuration Script Sample
+===========================
+Here is a sample of a simple configuration script:
+
+DEVICE=eth0
+USERCTL=no
+ONBOOT=yes
+POOTPROTO=none
+BROADCAST=207.200.5.255
+NETWORK=207.200.5.0
+NETMASK=255.255.255.0
+IPADDR=207.200.5.2
+
+
+Troubleshooting
+===============
+Q1. Source files contain ^ M behind every line.
+	Make sure all files are Unix file format (no LF). Try the following
+    shell command to convert files.
+
+	cat dl2k.c | col -b > dl2k.tmp
+	mv dl2k.tmp dl2k.c
+
+	OR
+
+	cat dl2k.c | tr -d "\r" > dl2k.tmp
+	mv dl2k.tmp dl2k.c
+
+Q2: Could not find header files (*.h) ?
+	To compile the driver, you need kernel header files. After
+    installing the kernel source, the header files are usually located in
+    /usr/src/linux/include, which is the default include directory configured
+    in Makefile. For some distributions, there is a copy of header files in
+    /usr/src/include/linux and /usr/src/include/asm, that you can change the
+    INCLUDEDIR in Makefile to /usr/include without installing kernel source.
+	Note that RH 7.0 didn't provide correct header files in /usr/include,
+    including those files will make a wrong version driver.
+
diff --git a/Documentation/networking/device_drivers/freescale/dpaa.txt b/Documentation/networking/device_drivers/freescale/dpaa.txt
new file mode 100644
index 000000000000..f88194f71c54
--- /dev/null
+++ b/Documentation/networking/device_drivers/freescale/dpaa.txt
@@ -0,0 +1,260 @@
+The QorIQ DPAA Ethernet Driver
+==============================
+
+Authors:
+Madalin Bucur <madalin.bucur@nxp.com>
+Camelia Groza <camelia.groza@nxp.com>
+
+Contents
+========
+
+	- DPAA Ethernet Overview
+	- DPAA Ethernet Supported SoCs
+	- Configuring DPAA Ethernet in your kernel
+	- DPAA Ethernet Frame Processing
+	- DPAA Ethernet Features
+	- DPAA IRQ Affinity and Receive Side Scaling
+	- Debugging
+
+DPAA Ethernet Overview
+======================
+
+DPAA stands for Data Path Acceleration Architecture and it is a
+set of networking acceleration IPs that are available on several
+generations of SoCs, both on PowerPC and ARM64.
+
+The Freescale DPAA architecture consists of a series of hardware blocks
+that support Ethernet connectivity. The Ethernet driver depends upon the
+following drivers in the Linux kernel:
+
+ - Peripheral Access Memory Unit (PAMU) (* needed only for PPC platforms)
+    drivers/iommu/fsl_*
+ - Frame Manager (FMan)
+    drivers/net/ethernet/freescale/fman
+ - Queue Manager (QMan), Buffer Manager (BMan)
+    drivers/soc/fsl/qbman
+
+A simplified view of the dpaa_eth interfaces mapped to FMan MACs:
+
+  dpaa_eth       /eth0\     ...       /ethN\
+  driver        |      |             |      |
+  -------------   ----   -----------   ----   -------------
+       -Ports  / Tx  Rx \    ...    / Tx  Rx \
+  FMan        |          |         |          |
+       -MACs  |   MAC0   |         |   MACN   |
+             /   dtsec0   \  ...  /   dtsecN   \ (or tgec)
+            /              \     /              \(or memac)
+  ---------  --------------  ---  --------------  ---------
+      FMan, FMan Port, FMan SP, FMan MURAM drivers
+  ---------------------------------------------------------
+      FMan HW blocks: MURAM, MACs, Ports, SP
+  ---------------------------------------------------------
+
+The dpaa_eth relation to the QMan, BMan and FMan:
+              ________________________________
+  dpaa_eth   /            eth0                \
+  driver    /                                  \
+  ---------   -^-   -^-   -^-   ---    ---------
+  QMan driver / \   / \   / \  \   /  | BMan    |
+             |Rx | |Rx | |Tx | |Tx |  | driver  |
+  ---------  |Dfl| |Err| |Cnf| |FQs|  |         |
+  QMan HW    |FQ | |FQ | |FQs| |   |  |         |
+             /   \ /   \ /   \  \ /   |         |
+  ---------   ---   ---   ---   -v-    ---------
+            |        FMan QMI         |         |
+            | FMan HW       FMan BMI  | BMan HW |
+              -----------------------   --------
+
+where the acronyms used above (and in the code) are:
+DPAA = Data Path Acceleration Architecture
+FMan = DPAA Frame Manager
+QMan = DPAA Queue Manager
+BMan = DPAA Buffers Manager
+QMI = QMan interface in FMan
+BMI = BMan interface in FMan
+FMan SP = FMan Storage Profiles
+MURAM = Multi-user RAM in FMan
+FQ = QMan Frame Queue
+Rx Dfl FQ = default reception FQ
+Rx Err FQ = Rx error frames FQ
+Tx Cnf FQ = Tx confirmation FQs
+Tx FQs = transmission frame queues
+dtsec = datapath three speed Ethernet controller (10/100/1000 Mbps)
+tgec = ten gigabit Ethernet controller (10 Gbps)
+memac = multirate Ethernet MAC (10/100/1000/10000)
+
+DPAA Ethernet Supported SoCs
+============================
+
+The DPAA drivers enable the Ethernet controllers present on the following SoCs:
+
+# PPC
+P1023
+P2041
+P3041
+P4080
+P5020
+P5040
+T1023
+T1024
+T1040
+T1042
+T2080
+T4240
+B4860
+
+# ARM
+LS1043A
+LS1046A
+
+Configuring DPAA Ethernet in your kernel
+========================================
+
+To enable the DPAA Ethernet driver, the following Kconfig options are required:
+
+# common for arch/arm64 and arch/powerpc platforms
+CONFIG_FSL_DPAA=y
+CONFIG_FSL_FMAN=y
+CONFIG_FSL_DPAA_ETH=y
+CONFIG_FSL_XGMAC_MDIO=y
+
+# for arch/powerpc only
+CONFIG_FSL_PAMU=y
+
+# common options needed for the PHYs used on the RDBs
+CONFIG_VITESSE_PHY=y
+CONFIG_REALTEK_PHY=y
+CONFIG_AQUANTIA_PHY=y
+
+DPAA Ethernet Frame Processing
+==============================
+
+On Rx, buffers for the incoming frames are retrieved from one of the three
+existing buffers pools. The driver initializes and seeds these, each with
+buffers of different sizes: 1KB, 2KB and 4KB.
+
+On Tx, all transmitted frames are returned to the driver through Tx
+confirmation frame queues. The driver is then responsible for freeing the
+buffers. In order to do this properly, a backpointer is added to the buffer
+before transmission that points to the skb. When the buffer returns to the
+driver on a confirmation FQ, the skb can be correctly consumed.
+
+DPAA Ethernet Features
+======================
+
+Currently the DPAA Ethernet driver enables the basic features required for
+a Linux Ethernet driver. The support for advanced features will be added
+gradually.
+
+The driver has Rx and Tx checksum offloading for UDP and TCP. Currently the Rx
+checksum offload feature is enabled by default and cannot be controlled through
+ethtool. Also, rx-flow-hash and rx-hashing was added. The addition of RSS
+provides a big performance boost for the forwarding scenarios, allowing
+different traffic flows received by one interface to be processed by different
+CPUs in parallel.
+
+The driver has support for multiple prioritized Tx traffic classes. Priorities
+range from 0 (lowest) to 3 (highest). These are mapped to HW workqueues with
+strict priority levels. Each traffic class contains NR_CPU TX queues. By
+default, only one traffic class is enabled and the lowest priority Tx queues
+are used. Higher priority traffic classes can be enabled with the mqprio
+qdisc. For example, all four traffic classes are enabled on an interface with
+the following command. Furthermore, skb priority levels are mapped to traffic
+classes as follows:
+
+	* priorities 0 to 3 - traffic class 0 (low priority)
+	* priorities 4 to 7 - traffic class 1 (medium-low priority)
+	* priorities 8 to 11 - traffic class 2 (medium-high priority)
+	* priorities 12 to 15 - traffic class 3 (high priority)
+
+tc qdisc add dev <int> root handle 1: \
+	 mqprio num_tc 4 map 0 0 0 0 1 1 1 1 2 2 2 2 3 3 3 3 hw 1
+
+DPAA IRQ Affinity and Receive Side Scaling
+==========================================
+
+Traffic coming on the DPAA Rx queues or on the DPAA Tx confirmation
+queues is seen by the CPU as ingress traffic on a certain portal.
+The DPAA QMan portal interrupts are affined each to a certain CPU.
+The same portal interrupt services all the QMan portal consumers.
+
+By default the DPAA Ethernet driver enables RSS, making use of the
+DPAA FMan Parser and Keygen blocks to distribute traffic on 128
+hardware frame queues using a hash on IP v4/v6 source and destination
+and L4 source and destination ports, in present in the received frame.
+When RSS is disabled, all traffic received by a certain interface is
+received on the default Rx frame queue. The default DPAA Rx frame
+queues are configured to put the received traffic into a pool channel
+that allows any available CPU portal to dequeue the ingress traffic.
+The default frame queues have the HOLDACTIVE option set, ensuring that
+traffic bursts from a certain queue are serviced by the same CPU.
+This ensures a very low rate of frame reordering. A drawback of this
+is that only one CPU at a time can service the traffic received by a
+certain interface when RSS is not enabled.
+
+To implement RSS, the DPAA Ethernet driver allocates an extra set of
+128 Rx frame queues that are configured to dedicated channels, in a
+round-robin manner. The mapping of the frame queues to CPUs is now
+hardcoded, there is no indirection table to move traffic for a certain
+FQ (hash result) to another CPU. The ingress traffic arriving on one
+of these frame queues will arrive at the same portal and will always
+be processed by the same CPU. This ensures intra-flow order preservation
+and workload distribution for multiple traffic flows.
+
+RSS can be turned off for a certain interface using ethtool, i.e.
+
+	# ethtool -N fm1-mac9 rx-flow-hash tcp4 ""
+
+To turn it back on, one needs to set rx-flow-hash for tcp4/6 or udp4/6:
+
+	# ethtool -N fm1-mac9 rx-flow-hash udp4 sfdn
+
+There is no independent control for individual protocols, any command
+run for one of tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6 is
+going to control the rx-flow-hashing for all protocols on that interface.
+
+Besides using the FMan Keygen computed hash for spreading traffic on the
+128 Rx FQs, the DPAA Ethernet driver also sets the skb hash value when
+the NETIF_F_RXHASH feature is on (active by default). This can be turned
+on or off through ethtool, i.e.:
+
+	# ethtool -K fm1-mac9 rx-hashing off
+	# ethtool -k fm1-mac9 | grep hash
+	receive-hashing: off
+	# ethtool -K fm1-mac9 rx-hashing on
+	Actual changes:
+	receive-hashing: on
+	# ethtool -k fm1-mac9 | grep hash
+	receive-hashing: on
+
+Please note that Rx hashing depends upon the rx-flow-hashing being on
+for that interface - turning off rx-flow-hashing will also disable the
+rx-hashing (without ethtool reporting it as off as that depends on the
+NETIF_F_RXHASH feature flag).
+
+Debugging
+=========
+
+The following statistics are exported for each interface through ethtool:
+
+	- interrupt count per CPU
+	- Rx packets count per CPU
+	- Tx packets count per CPU
+	- Tx confirmed packets count per CPU
+	- Tx S/G frames count per CPU
+	- Tx error count per CPU
+	- Rx error count per CPU
+	- Rx error count per type
+	- congestion related statistics:
+		- congestion status
+		- time spent in congestion
+		- number of time the device entered congestion
+		- dropped packets count per cause
+
+The driver also exports the following information in sysfs:
+
+	- the FQ IDs for each FQ type
+	/sys/devices/platform/dpaa-ethernet.0/net/<int>/fqids
+
+	- the IDs of the buffer pools in use
+	/sys/devices/platform/dpaa-ethernet.0/net/<int>/bpids
diff --git a/Documentation/networking/device_drivers/freescale/dpaa2/dpio-driver.rst b/Documentation/networking/device_drivers/freescale/dpaa2/dpio-driver.rst
new file mode 100644
index 000000000000..a188466b6698
--- /dev/null
+++ b/Documentation/networking/device_drivers/freescale/dpaa2/dpio-driver.rst
@@ -0,0 +1,158 @@
+.. include:: <isonum.txt>
+
+DPAA2 DPIO (Data Path I/O) Overview
+===================================
+
+:Copyright: |copy| 2016-2018 NXP
+
+This document provides an overview of the Freescale DPAA2 DPIO
+drivers
+
+Introduction
+============
+
+A DPAA2 DPIO (Data Path I/O) is a hardware object that provides
+interfaces to enqueue and dequeue frames to/from network interfaces
+and other accelerators.  A DPIO also provides hardware buffer
+pool management for network interfaces.
+
+This document provides an overview the Linux DPIO driver, its
+subcomponents, and its APIs.
+
+See Documentation/networking/device_drivers/freescale/dpaa2/overview.rst for
+a general overview of DPAA2 and the general DPAA2 driver architecture in Linux.
+
+Driver Overview
+---------------
+
+The DPIO driver is bound to DPIO objects discovered on the fsl-mc bus and
+provides services that:
+  A) allow other drivers, such as the Ethernet driver, to enqueue and dequeue
+     frames for their respective objects
+  B) allow drivers to register callbacks for data availability notifications
+     when data becomes available on a queue or channel
+  C) allow drivers to manage hardware buffer pools
+
+The Linux DPIO driver consists of 3 primary components--
+   DPIO object driver-- fsl-mc driver that manages the DPIO object
+
+   DPIO service-- provides APIs to other Linux drivers for services
+
+   QBman portal interface-- sends portal commands, gets responses
+::
+
+          fsl-mc          other
+           bus           drivers
+            |               |
+        +---+----+   +------+-----+
+        |DPIO obj|   |DPIO service|
+        | driver |---|  (DPIO)    |
+        +--------+   +------+-----+
+                            |
+                     +------+-----+
+                     |    QBman   |
+                     | portal i/f |
+                     +------------+
+                            |
+                         hardware
+
+
+The diagram below shows how the DPIO driver components fit with the other
+DPAA2 Linux driver components::
+                                                   +------------+
+                                                   | OS Network |
+                                                   |   Stack    |
+                 +------------+                    +------------+
+                 | Allocator  |. . . . . . .       |  Ethernet  |
+                 |(DPMCP,DPBP)|                    |   (DPNI)   |
+                 +-.----------+                    +---+---+----+
+                  .          .                         ^   |
+                 .            .           <data avail, |   |<enqueue,
+                .              .           tx confirm> |   | dequeue>
+    +-------------+             .                      |   |
+    | DPRC driver |              .    +--------+ +------------+
+    |   (DPRC)    |               . . |DPIO obj| |DPIO service|
+    +----------+--+                   | driver |-|  (DPIO)    |
+               |                      +--------+ +------+-----+
+               |<dev add/remove>                 +------|-----+
+               |                                 |   QBman    |
+          +----+--------------+                  | portal i/f |
+          |   MC-bus driver   |                  +------------+
+          |                   |                     |
+          | /soc/fsl-mc       |                     |
+          +-------------------+                     |
+                                                    |
+ =========================================|=========|========================
+                                        +-+--DPIO---|-----------+
+                                        |           |           |
+                                        |        QBman Portal   |
+                                        +-----------------------+
+
+ ============================================================================
+
+
+DPIO Object Driver (dpio-driver.c)
+----------------------------------
+
+   The dpio-driver component registers with the fsl-mc bus to handle objects of
+   type "dpio".  The implementation of probe() handles basic initialization
+   of the DPIO including mapping of the DPIO regions (the QBman SW portal)
+   and initializing interrupts and registering irq handlers.  The dpio-driver
+   registers the probed DPIO with dpio-service.
+
+DPIO service  (dpio-service.c, dpaa2-io.h)
+------------------------------------------
+
+   The dpio service component provides queuing, notification, and buffers
+   management services to DPAA2 drivers, such as the Ethernet driver.  A system
+   will typically allocate 1 DPIO object per CPU to allow queuing operations
+   to happen simultaneously across all CPUs.
+
+   Notification handling
+      dpaa2_io_service_register()
+
+      dpaa2_io_service_deregister()
+
+      dpaa2_io_service_rearm()
+
+   Queuing
+      dpaa2_io_service_pull_fq()
+
+      dpaa2_io_service_pull_channel()
+
+      dpaa2_io_service_enqueue_fq()
+
+      dpaa2_io_service_enqueue_qd()
+
+      dpaa2_io_store_create()
+
+      dpaa2_io_store_destroy()
+
+      dpaa2_io_store_next()
+
+   Buffer pool management
+      dpaa2_io_service_release()
+
+      dpaa2_io_service_acquire()
+
+QBman portal interface (qbman-portal.c)
+---------------------------------------
+
+   The qbman-portal component provides APIs to do the low level hardware
+   bit twiddling for operations such as:
+      -initializing Qman software portals
+
+      -building and sending portal commands
+
+      -portal interrupt configuration and processing
+
+   The qbman-portal APIs are not public to other drivers, and are
+   only used by dpio-service.
+
+Other (dpaa2-fd.h, dpaa2-global.h)
+----------------------------------
+
+   Frame descriptor and scatter-gather definitions and the APIs used to
+   manipulate them are defined in dpaa2-fd.h.
+
+   Dequeue result struct and parsing APIs are defined in dpaa2-global.h.
diff --git a/Documentation/networking/device_drivers/freescale/dpaa2/ethernet-driver.rst b/Documentation/networking/device_drivers/freescale/dpaa2/ethernet-driver.rst
new file mode 100644
index 000000000000..cb4c9a0c5a17
--- /dev/null
+++ b/Documentation/networking/device_drivers/freescale/dpaa2/ethernet-driver.rst
@@ -0,0 +1,185 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+===============================
+DPAA2 Ethernet driver
+===============================
+
+:Copyright: |copy| 2017-2018 NXP
+
+This file provides documentation for the Freescale DPAA2 Ethernet driver.
+
+Supported Platforms
+===================
+This driver provides networking support for Freescale DPAA2 SoCs, e.g.
+LS2080A, LS2088A, LS1088A.
+
+
+Architecture Overview
+=====================
+Unlike regular NICs, in the DPAA2 architecture there is no single hardware block
+representing network interfaces; instead, several separate hardware resources
+concur to provide the networking functionality:
+
+- network interfaces
+- queues, channels
+- buffer pools
+- MAC/PHY
+
+All hardware resources are allocated and configured through the Management
+Complex (MC) portals. MC abstracts most of these resources as DPAA2 objects
+and exposes ABIs through which they can be configured and controlled. A few
+hardware resources, like queues, do not have a corresponding MC object and
+are treated as internal resources of other objects.
+
+For a more detailed description of the DPAA2 architecture and its object
+abstractions see *Documentation/networking/device_drivers/freescale/dpaa2/overview.rst*.
+
+Each Linux net device is built on top of a Datapath Network Interface (DPNI)
+object and uses Buffer Pools (DPBPs), I/O Portals (DPIOs) and Concentrators
+(DPCONs).
+
+Configuration interface::
+
+                 -----------------------
+                | DPAA2 Ethernet Driver |
+                 -----------------------
+                     .      .      .
+                     .      .      .
+             . . . . .      .      . . . . . .
+             .              .                .
+             .              .                .
+         ----------     ----------      -----------
+        | DPBP API |   | DPNI API |    | DPCON API |
+         ----------     ----------      -----------
+             .              .                .             software
+    =======  .  ==========  .  ============  .  ===================
+             .              .                .             hardware
+         ------------------------------------------
+        |            MC hardware portals           |
+         ------------------------------------------
+             .              .                .
+             .              .                .
+          ------         ------            -------
+         | DPBP |       | DPNI |          | DPCON |
+          ------         ------            -------
+
+The DPNIs are network interfaces without a direct one-on-one mapping to PHYs.
+DPBPs represent hardware buffer pools. Packet I/O is performed in the context
+of DPCON objects, using DPIO portals for managing and communicating with the
+hardware resources.
+
+Datapath (I/O) interface::
+
+         -----------------------------------------------
+        |           DPAA2 Ethernet Driver               |
+         -----------------------------------------------
+          |          ^        ^         |            |
+          |          |        |         |            |
+   enqueue|   dequeue|   data |  dequeue|       seed |
+    (Tx)  | (Rx, TxC)|  avail.|  request|     buffers|
+          |          |  notify|         |            |
+          |          |        |         |            |
+          V          |        |         V            V
+         -----------------------------------------------
+        |                 DPIO Driver                   |
+         -----------------------------------------------
+          |          |        |         |            |          software
+          |          |        |         |            |  ================
+          |          |        |         |            |          hardware
+         -----------------------------------------------
+        |               I/O hardware portals            |
+         -----------------------------------------------
+          |          ^        ^         |            |
+          |          |        |         |            |
+          |          |        |         V            |
+          V          |    ================           V
+        ----------------------           |      -------------
+ queues  ----------------------          |     | Buffer pool |
+          ----------------------         |      -------------
+                   =======================
+                                Channel
+
+Datapath I/O (DPIO) portals provide enqueue and dequeue services, data
+availability notifications and buffer pool management. DPIOs are shared between
+all DPAA2 objects (and implicitly all DPAA2 kernel drivers) that work with data
+frames, but must be affine to the CPUs for the purpose of traffic distribution.
+
+Frames are transmitted and received through hardware frame queues, which can be
+grouped in channels for the purpose of hardware scheduling. The Ethernet driver
+enqueues TX frames on egress queues and after transmission is complete a TX
+confirmation frame is sent back to the CPU.
+
+When frames are available on ingress queues, a data availability notification
+is sent to the CPU; notifications are raised per channel, so even if multiple
+queues in the same channel have available frames, only one notification is sent.
+After a channel fires a notification, is must be explicitly rearmed.
+
+Each network interface can have multiple Rx, Tx and confirmation queues affined
+to CPUs, and one channel (DPCON) for each CPU that services at least one queue.
+DPCONs are used to distribute ingress traffic to different CPUs via the cores'
+affine DPIOs.
+
+The role of hardware buffer pools is storage of ingress frame data. Each network
+interface has a privately owned buffer pool which it seeds with kernel allocated
+buffers.
+
+
+DPNIs are decoupled from PHYs; a DPNI can be connected to a PHY through a DPMAC
+object or to another DPNI through an internal link, but the connection is
+managed by MC and completely transparent to the Ethernet driver.
+
+::
+
+     ---------     ---------     ---------
+    | eth if1 |   | eth if2 |   | eth ifn |
+     ---------     ---------     ---------
+          .           .          .
+          .           .          .
+          .           .          .
+         ---------------------------
+        |   DPAA2 Ethernet Driver   |
+         ---------------------------
+          .           .          .
+          .           .          .
+          .           .          .
+       ------      ------      ------            -------
+      | DPNI |    | DPNI |    | DPNI |          | DPMAC |----+
+       ------      ------      ------            -------     |
+         |           |           |                  |        |
+         |           |           |                  |      -----
+          ===========             ==================      | PHY |
+                                                           -----
+
+Creating a Network Interface
+============================
+A net device is created for each DPNI object probed on the MC bus. Each DPNI has
+a number of properties which determine the network interface configuration
+options and associated hardware resources.
+
+DPNI objects (and the other DPAA2 objects needed for a network interface) can be
+added to a container on the MC bus in one of two ways: statically, through a
+Datapath Layout Binary file (DPL) that is parsed by MC at boot time; or created
+dynamically at runtime, via the DPAA2 objects APIs.
+
+
+Features & Offloads
+===================
+Hardware checksum offloading is supported for TCP and UDP over IPv4/6 frames.
+The checksum offloads can be independently configured on RX and TX through
+ethtool.
+
+Hardware offload of unicast and multicast MAC filtering is supported on the
+ingress path and permanently enabled.
+
+Scatter-gather frames are supported on both RX and TX paths. On TX, SG support
+is configurable via ethtool; on RX it is always enabled.
+
+The DPAA2 hardware can process jumbo Ethernet frames of up to 10K bytes.
+
+The Ethernet driver defines a static flow hashing scheme that distributes
+traffic based on a 5-tuple key: src IP, dst IP, IP proto, L4 src port,
+L4 dst port. No user configuration is supported for now.
+
+Hardware specific statistics for the network interface as well as some
+non-standard driver stats can be consulted through ethtool -S option.
diff --git a/Documentation/networking/device_drivers/freescale/dpaa2/index.rst b/Documentation/networking/device_drivers/freescale/dpaa2/index.rst
new file mode 100644
index 000000000000..67bd87fe6c53
--- /dev/null
+++ b/Documentation/networking/device_drivers/freescale/dpaa2/index.rst
@@ -0,0 +1,10 @@
+===================
+DPAA2 Documentation
+===================
+
+.. toctree::
+   :maxdepth: 1
+
+   overview
+   dpio-driver
+   ethernet-driver
diff --git a/Documentation/networking/device_drivers/freescale/dpaa2/overview.rst b/Documentation/networking/device_drivers/freescale/dpaa2/overview.rst
new file mode 100644
index 000000000000..d638b5a8aadd
--- /dev/null
+++ b/Documentation/networking/device_drivers/freescale/dpaa2/overview.rst
@@ -0,0 +1,405 @@
+.. include:: <isonum.txt>
+
+=========================================================
+DPAA2 (Data Path Acceleration Architecture Gen2) Overview
+=========================================================
+
+:Copyright: |copy| 2015 Freescale Semiconductor Inc.
+:Copyright: |copy| 2018 NXP
+
+This document provides an overview of the Freescale DPAA2 architecture
+and how it is integrated into the Linux kernel.
+
+Introduction
+============
+
+DPAA2 is a hardware architecture designed for high-speeed network
+packet processing.  DPAA2 consists of sophisticated mechanisms for
+processing Ethernet packets, queue management, buffer management,
+autonomous L2 switching, virtual Ethernet bridging, and accelerator
+(e.g. crypto) sharing.
+
+A DPAA2 hardware component called the Management Complex (or MC) manages the
+DPAA2 hardware resources.  The MC provides an object-based abstraction for
+software drivers to use the DPAA2 hardware.
+The MC uses DPAA2 hardware resources such as queues, buffer pools, and
+network ports to create functional objects/devices such as network
+interfaces, an L2 switch, or accelerator instances.
+The MC provides memory-mapped I/O command interfaces (MC portals)
+which DPAA2 software drivers use to operate on DPAA2 objects.
+
+The diagram below shows an overview of the DPAA2 resource management
+architecture::
+
+	+--------------------------------------+
+	|                  OS                  |
+	|                        DPAA2 drivers |
+	|                             |        |
+	+-----------------------------|--------+
+	                              |
+	                              | (create,discover,connect
+	                              |  config,use,destroy)
+	                              |
+	                 DPAA2        |
+	+------------------------| mc portal |-+
+	|                             |        |
+	|   +- - - - - - - - - - - - -V- - -+  |
+	|   |                               |  |
+	|   |   Management Complex (MC)     |  |
+	|   |                               |  |
+	|   +- - - - - - - - - - - - - - - -+  |
+	|                                      |
+	| Hardware                  Hardware   |
+	| Resources                 Objects    |
+	| ---------                 -------    |
+	| -queues                   -DPRC      |
+	| -buffer pools             -DPMCP     |
+	| -Eth MACs/ports           -DPIO      |
+	| -network interface        -DPNI      |
+	|  profiles                 -DPMAC     |
+	| -queue portals            -DPBP      |
+	| -MC portals                ...       |
+	|  ...                                 |
+	|                                      |
+	+--------------------------------------+
+
+
+The MC mediates operations such as create, discover,
+connect, configuration, and destroy.  Fast-path operations
+on data, such as packet transmit/receive, are not mediated by
+the MC and are done directly using memory mapped regions in
+DPIO objects.
+
+Overview of DPAA2 Objects
+=========================
+
+The section provides a brief overview of some key DPAA2 objects.
+A simple scenario is described illustrating the objects involved
+in creating a network interfaces.
+
+DPRC (Datapath Resource Container)
+----------------------------------
+
+A DPRC is a container object that holds all the other
+types of DPAA2 objects.  In the example diagram below there
+are 8 objects of 5 types (DPMCP, DPIO, DPBP, DPNI, and DPMAC)
+in the container.
+
+::
+
+	+---------------------------------------------------------+
+	| DPRC                                                    |
+	|                                                         |
+	|  +-------+  +-------+  +-------+  +-------+  +-------+  |
+	|  | DPMCP |  | DPIO  |  | DPBP  |  | DPNI  |  | DPMAC |  |
+	|  +-------+  +-------+  +-------+  +---+---+  +---+---+  |
+	|  | DPMCP |  | DPIO  |                                   |
+	|  +-------+  +-------+                                   |
+	|  | DPMCP |                                              |
+	|  +-------+                                              |
+	|                                                         |
+	+---------------------------------------------------------+
+
+From the point of view of an OS, a DPRC behaves similar to a plug and
+play bus, like PCI.  DPRC commands can be used to enumerate the contents
+of the DPRC, discover the hardware objects present (including mappable
+regions and interrupts).
+
+::
+
+	DPRC.1 (bus)
+	   |
+	   +--+--------+-------+-------+-------+
+	      |        |       |       |       |
+	    DPMCP.1  DPIO.1  DPBP.1  DPNI.1  DPMAC.1
+	    DPMCP.2  DPIO.2
+	    DPMCP.3
+
+Hardware objects can be created and destroyed dynamically, providing
+the ability to hot plug/unplug objects in and out of the DPRC.
+
+A DPRC has a mappable MMIO region (an MC portal) that can be used
+to send MC commands.  It has an interrupt for status events (like
+hotplug).
+All objects in a container share the same hardware "isolation context".
+This means that with respect to an IOMMU the isolation granularity
+is at the DPRC (container) level, not at the individual object
+level.
+
+DPRCs can be defined statically and populated with objects
+via a config file passed to the MC when firmware starts it.
+
+DPAA2 Objects for an Ethernet Network Interface
+-----------------------------------------------
+
+A typical Ethernet NIC is monolithic-- the NIC device contains TX/RX
+queuing mechanisms, configuration mechanisms, buffer management,
+physical ports, and interrupts.  DPAA2 uses a more granular approach
+utilizing multiple hardware objects.  Each object provides specialized
+functions. Groups of these objects are used by software to provide
+Ethernet network interface functionality.  This approach provides
+efficient use of finite hardware resources, flexibility, and
+performance advantages.
+
+The diagram below shows the objects needed for a simple
+network interface configuration on a system with 2 CPUs.
+
+::
+
+	+---+---+ +---+---+
+	   CPU0     CPU1
+	+---+---+ +---+---+
+	    |         |
+	+---+---+ +---+---+
+	   DPIO     DPIO
+	+---+---+ +---+---+
+	    \     /
+	     \   /
+	      \ /
+	   +---+---+
+	      DPNI  --- DPBP,DPMCP
+	   +---+---+
+	       |
+	       |
+	   +---+---+
+	     DPMAC
+	   +---+---+
+	       |
+	   port/PHY
+
+Below the objects are described.  For each object a brief description
+is provided along with a summary of the kinds of operations the object
+supports and a summary of key resources of the object (MMIO regions
+and IRQs).
+
+DPMAC (Datapath Ethernet MAC)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Represents an Ethernet MAC, a hardware device that connects to an Ethernet
+PHY and allows physical transmission and reception of Ethernet frames.
+
+- MMIO regions: none
+- IRQs: DPNI link change
+- commands: set link up/down, link config, get stats,
+  IRQ config, enable, reset
+
+DPNI (Datapath Network Interface)
+Contains TX/RX queues, network interface configuration, and RX buffer pool
+configuration mechanisms.  The TX/RX queues are in memory and are identified
+by queue number.
+
+- MMIO regions: none
+- IRQs: link state
+- commands: port config, offload config, queue config,
+  parse/classify config, IRQ config, enable, reset
+
+DPIO (Datapath I/O)
+~~~~~~~~~~~~~~~~~~~
+Provides interfaces to enqueue and dequeue
+packets and do hardware buffer pool management operations.  The DPAA2
+architecture separates the mechanism to access queues (the DPIO object)
+from the queues themselves.  The DPIO provides an MMIO interface to
+enqueue/dequeue packets.  To enqueue something a descriptor is written
+to the DPIO MMIO region, which includes the target queue number.
+There will typically be one DPIO assigned to each CPU.  This allows all
+CPUs to simultaneously perform enqueue/dequeued operations.  DPIOs are
+expected to be shared by different DPAA2 drivers.
+
+- MMIO regions: queue operations, buffer management
+- IRQs: data availability, congestion notification, buffer
+  pool depletion
+- commands: IRQ config, enable, reset
+
+DPBP (Datapath Buffer Pool)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Represents a hardware buffer pool.
+
+- MMIO regions: none
+- IRQs: none
+- commands: enable, reset
+
+DPMCP (Datapath MC Portal)
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+Provides an MC command portal.
+Used by drivers to send commands to the MC to manage
+objects.
+
+- MMIO regions: MC command portal
+- IRQs: command completion
+- commands: IRQ config, enable, reset
+
+Object Connections
+==================
+Some objects have explicit relationships that must
+be configured:
+
+- DPNI <--> DPMAC
+- DPNI <--> DPNI
+- DPNI <--> L2-switch-port
+
+    A DPNI must be connected to something such as a DPMAC,
+    another DPNI, or L2 switch port.  The DPNI connection
+    is made via a DPRC command.
+
+::
+
+              +-------+  +-------+
+              | DPNI  |  | DPMAC |
+              +---+---+  +---+---+
+                  |          |
+                  +==========+
+
+- DPNI <--> DPBP
+
+    A network interface requires a 'buffer pool' (DPBP
+    object) which provides a list of pointers to memory
+    where received Ethernet data is to be copied.  The
+    Ethernet driver configures the DPBPs associated with
+    the network interface.
+
+Interrupts
+==========
+All interrupts generated by DPAA2 objects are message
+interrupts.  At the hardware level message interrupts
+generated by devices will normally have 3 components--
+1) a non-spoofable 'device-id' expressed on the hardware
+bus, 2) an address, 3) a data value.
+
+In the case of DPAA2 devices/objects, all objects in the
+same container/DPRC share the same 'device-id'.
+For ARM-based SoC this is the same as the stream ID.
+
+
+DPAA2 Linux Drivers Overview
+============================
+
+This section provides an overview of the Linux kernel drivers for
+DPAA2-- 1) the bus driver and associated "DPAA2 infrastructure"
+drivers and 2) functional object drivers (such as Ethernet).
+
+As described previously, a DPRC is a container that holds the other
+types of DPAA2 objects.  It is functionally similar to a plug-and-play
+bus controller.
+Each object in the DPRC is a Linux "device" and is bound to a driver.
+The diagram below shows the Linux drivers involved in a networking
+scenario and the objects bound to each driver.  A brief description
+of each driver follows.
+
+::
+
+	                                     +------------+
+	                                     | OS Network |
+	                                     |   Stack    |
+	         +------------+              +------------+
+	         | Allocator  |. . . . . . . |  Ethernet  |
+	         |(DPMCP,DPBP)|              |   (DPNI)   |
+	         +-.----------+              +---+---+----+
+	          .          .                   ^   |
+	         .            .     <data avail, |   | <enqueue,
+	        .              .     tx confirm> |   | dequeue>
+	+-------------+         .                |   |
+	| DPRC driver |          .           +---+---V----+     +---------+
+	|   (DPRC)    |           . . . . . .| DPIO driver|     |   MAC   |
+	+----------+--+                      |  (DPIO)    |     | (DPMAC) |
+	           |                         +------+-----+     +-----+---+
+	           |<dev add/remove>                |                 |
+	           |                                |                 |
+	  +--------+----------+                     |              +--+---+
+	  |   MC-bus driver   |                     |              | PHY  |
+	  |                   |                     |              |driver|
+	  |   /bus/fsl-mc     |                     |              +--+---+
+	  +-------------------+                     |                 |
+	                                            |                 |
+	========================= HARDWARE =========|=================|======
+	                                          DPIO                |
+	                                            |                 |
+	                                          DPNI---DPBP         |
+	                                            |                 |
+	                                          DPMAC               |
+	                                            |                 |
+	                                           PHY ---------------+
+	============================================|========================
+
+A brief description of each driver is provided below.
+
+MC-bus driver
+-------------
+The MC-bus driver is a platform driver and is probed from a
+node in the device tree (compatible "fsl,qoriq-mc") passed in by boot
+firmware.  It is responsible for bootstrapping the DPAA2 kernel
+infrastructure.
+Key functions include:
+
+- registering a new bus type named "fsl-mc" with the kernel,
+  and implementing bus call-backs (e.g. match/uevent/dev_groups)
+- implementing APIs for DPAA2 driver registration and for device
+  add/remove
+- creates an MSI IRQ domain
+- doing a 'device add' to expose the 'root' DPRC, in turn triggering
+  a bind of the root DPRC to the DPRC driver
+
+The binding for the MC-bus device-tree node can be consulted at
+*Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt*.
+The sysfs bind/unbind interfaces for the MC-bus can be consulted at
+*Documentation/ABI/testing/sysfs-bus-fsl-mc*.
+
+DPRC driver
+-----------
+The DPRC driver is bound to DPRC objects and does runtime management
+of a bus instance.  It performs the initial bus scan of the DPRC
+and handles interrupts for container events such as hot plug by
+re-scanning the DPRC.
+
+Allocator
+---------
+Certain objects such as DPMCP and DPBP are generic and fungible,
+and are intended to be used by other drivers.  For example,
+the DPAA2 Ethernet driver needs:
+
+- DPMCPs to send MC commands, to configure network interfaces
+- DPBPs for network buffer pools
+
+The allocator driver registers for these allocatable object types
+and those objects are bound to the allocator when the bus is probed.
+The allocator maintains a pool of objects that are available for
+allocation by other DPAA2 drivers.
+
+DPIO driver
+-----------
+The DPIO driver is bound to DPIO objects and provides services that allow
+other drivers such as the Ethernet driver to enqueue and dequeue data for
+their respective objects.
+Key services include:
+
+- data availability notifications
+- hardware queuing operations (enqueue and dequeue of data)
+- hardware buffer pool management
+
+To transmit a packet the Ethernet driver puts data on a queue and
+invokes a DPIO API.  For receive, the Ethernet driver registers
+a data availability notification callback.  To dequeue a packet
+a DPIO API is used.
+There is typically one DPIO object per physical CPU for optimum
+performance, allowing different CPUs to simultaneously enqueue
+and dequeue data.
+
+The DPIO driver operates on behalf of all DPAA2 drivers
+active in the kernel--  Ethernet, crypto, compression,
+etc.
+
+Ethernet driver
+---------------
+The Ethernet driver is bound to a DPNI and implements the kernel
+interfaces needed to connect the DPAA2 network interface to
+the network stack.
+Each DPNI corresponds to a Linux network interface.
+
+MAC driver
+----------
+An Ethernet PHY is an off-chip, board specific component and is managed
+by the appropriate PHY driver via an mdio bus.  The MAC driver
+plays a role of being a proxy between the PHY driver and the
+MC.  It does this proxy via the MC commands to a DPMAC object.
+If the PHY driver signals a link change, the MAC driver notifies
+the MC via a DPMAC command.  If a network interface is brought
+up or down, the MC notifies the DPMAC driver via an interrupt and
+the driver can take appropriate action.
diff --git a/Documentation/networking/device_drivers/freescale/gianfar.txt b/Documentation/networking/device_drivers/freescale/gianfar.txt
new file mode 100644
index 000000000000..ba1daea7f2e4
--- /dev/null
+++ b/Documentation/networking/device_drivers/freescale/gianfar.txt
@@ -0,0 +1,42 @@
+The Gianfar Ethernet Driver
+
+Author: Andy Fleming <afleming@freescale.com>
+Updated: 2005-07-28
+
+
+CHECKSUM OFFLOADING
+
+The eTSEC controller (first included in parts from late 2005 like
+the 8548) has the ability to perform TCP, UDP, and IP checksums
+in hardware.  The Linux kernel only offloads the TCP and UDP
+checksums (and always performs the pseudo header checksums), so
+the driver only supports checksumming for TCP/IP and UDP/IP
+packets.  Use ethtool to enable or disable this feature for RX
+and TX.
+
+VLAN
+
+In order to use VLAN, please consult Linux documentation on
+configuring VLANs.  The gianfar driver supports hardware insertion and
+extraction of VLAN headers, but not filtering.  Filtering will be
+done by the kernel.
+
+MULTICASTING
+
+The gianfar driver supports using the group hash table on the
+TSEC (and the extended hash table on the eTSEC) for multicast
+filtering.  On the eTSEC, the exact-match MAC registers are used
+before the hash tables.  See Linux documentation on how to join
+multicast groups.
+
+PADDING
+
+The gianfar driver supports padding received frames with 2 bytes
+to align the IP header to a 16-byte boundary, when supported by
+hardware.
+
+ETHTOOL
+
+The gianfar driver supports the use of ethtool for many
+configuration options.  You must run ethtool only on currently
+open interfaces.  See ethtool documentation for details.
diff --git a/Documentation/networking/device_drivers/intel/e100.rst b/Documentation/networking/device_drivers/intel/e100.rst
new file mode 100644
index 000000000000..5e2839b4ec92
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/e100.rst
@@ -0,0 +1,187 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters
+==============================================================
+
+June 1, 2018
+
+Contents
+========
+
+- In This Release
+- Identifying Your Adapter
+- Building and Installation
+- Driver Configuration Parameters
+- Additional Configurations
+- Known Issues
+- Support
+
+
+In This Release
+===============
+
+This file describes the Linux* Base Driver for the Intel(R) PRO/100 Family of
+Adapters. This driver includes support for Itanium(R)2-based systems.
+
+For questions related to hardware requirements, refer to the documentation
+supplied with your Intel PRO/100 adapter.
+
+The following features are now available in supported kernels:
+ - Native VLANs
+ - Channel Bonding (teaming)
+ - SNMP
+
+Channel Bonding documentation can be found in the Linux kernel source:
+/Documentation/networking/bonding.txt
+
+
+Identifying Your Adapter
+========================
+
+For information on how to identify your adapter, and for the latest Intel
+network drivers, refer to the Intel Support website:
+http://www.intel.com/support
+
+Driver Configuration Parameters
+===============================
+
+The default value for each parameter is generally the recommended setting,
+unless otherwise noted.
+
+Rx Descriptors:
+   Number of receive descriptors. A receive descriptor is a data
+   structure that describes a receive buffer and its attributes to the network
+   controller. The data in the descriptor is used by the controller to write
+   data from the controller to host memory. In the 3.x.x driver the valid range
+   for this parameter is 64-256. The default value is 256. This parameter can be
+   changed using the command::
+
+     ethtool -G eth? rx n
+
+   Where n is the number of desired Rx descriptors.
+
+Tx Descriptors:
+   Number of transmit descriptors. A transmit descriptor is a data
+   structure that describes a transmit buffer and its attributes to the network
+   controller. The data in the descriptor is used by the controller to read
+   data from the host memory to the controller. In the 3.x.x driver the valid
+   range for this parameter is 64-256. The default value is 128. This parameter
+   can be changed using the command::
+
+     ethtool -G eth? tx n
+
+   Where n is the number of desired Tx descriptors.
+
+Speed/Duplex:
+   The driver auto-negotiates the link speed and duplex settings by
+   default. The ethtool utility can be used as follows to force speed/duplex.::
+
+     ethtool -s eth?  autoneg off speed {10|100} duplex {full|half}
+
+   NOTE: setting the speed/duplex to incorrect values will cause the link to
+   fail.
+
+Event Log Message Level:
+   The driver uses the message level flag to log events
+   to syslog. The message level can be set at driver load time. It can also be
+   set using the command::
+
+     ethtool -s eth? msglvl n
+
+
+Additional Configurations
+=========================
+
+Configuring the Driver on Different Distributions
+-------------------------------------------------
+
+Configuring a network driver to load properly when the system is started
+is distribution dependent.  Typically, the configuration process involves
+adding an alias line to `/etc/modprobe.d/*.conf` as well as editing other
+system startup scripts and/or configuration files.  Many popular Linux
+distributions ship with tools to make these changes for you.  To learn
+the proper way to configure a network device for your system, refer to
+your distribution documentation.  If during this process you are asked
+for the driver or module name, the name for the Linux Base Driver for
+the Intel PRO/100 Family of Adapters is e100.
+
+As an example, if you install the e100 driver for two PRO/100 adapters
+(eth0 and eth1), add the following to a configuration file in
+/etc/modprobe.d/::
+
+       alias eth0 e100
+       alias eth1 e100
+
+Viewing Link Messages
+---------------------
+
+In order to see link messages and other Intel driver information on your
+console, you must set the dmesg level up to six.  This can be done by
+entering the following on the command line before loading the e100
+driver::
+
+       dmesg -n 6
+
+If you wish to see all messages issued by the driver, including debug
+messages, set the dmesg level to eight.
+
+NOTE: This setting is not saved across reboots.
+
+ethtool
+-------
+
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information.  The ethtool
+version 1.6 or later is required for this functionality.
+
+The latest release of ethtool can be found from
+https://www.kernel.org/pub/software/network/ethtool/
+
+Enabling Wake on LAN* (WoL)
+---------------------------
+WoL is provided through the ethtool* utility.  For instructions on
+enabling WoL with ethtool, refer to the ethtool man page.  WoL will be
+enabled on the system during the next shut down or reboot.  For this
+driver version, in order to enable WoL, the e100 driver must be loaded
+when shutting down or rebooting the system.
+
+NAPI
+----
+
+NAPI (Rx polling mode) is supported in the e100 driver.
+
+See https://wiki.linuxfoundation.org/networking/napi for more
+information on NAPI.
+
+Multiple Interfaces on Same Ethernet Broadcast Network
+------------------------------------------------------
+
+Due to the default ARP behavior on Linux, it is not possible to have one
+system on two IP networks in the same Ethernet broadcast domain
+(non-partitioned switch) behave as expected.  All Ethernet interfaces
+will respond to IP traffic for any IP address assigned to the system.
+This results in unbalanced receive traffic.
+
+If you have multiple interfaces in a server, either turn on ARP
+filtering by
+
+(1) entering::
+
+	echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
+
+    (this only works if your kernel's version is higher than 2.4.5), or
+
+(2) installing the interfaces in separate broadcast domains (either
+    in different switches or in a switch partitioned to VLANs).
+
+
+Support
+=======
+For general information, go to the Intel support website at:
+http://www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+http://sourceforge.net/projects/e1000
+If an issue is identified with the released source code on a supported kernel
+with a supported adapter, email the specific information related to the issue
+to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/device_drivers/intel/e1000.rst b/Documentation/networking/device_drivers/intel/e1000.rst
new file mode 100644
index 000000000000..6379d4d20771
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/e1000.rst
@@ -0,0 +1,462 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux* Base Driver for Intel(R) Ethernet Network Connection
+===========================================================
+
+Intel Gigabit Linux driver.
+Copyright(c) 1999 - 2013 Intel Corporation.
+
+Contents
+========
+
+- Identifying Your Adapter
+- Command Line Parameters
+- Speed and Duplex Configuration
+- Additional Configurations
+- Support
+
+Identifying Your Adapter
+========================
+
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+
+    http://support.intel.com/support/go/network/adapter/idguide.htm
+
+For the latest Intel network drivers for Linux, refer to the following
+website.  In the search field, enter your adapter name or type, or use the
+networking link on the left to search for your adapter:
+
+    http://support.intel.com/support/go/network/adapter/home.htm
+
+Command Line Parameters
+=======================
+
+The default value for each parameter is generally the recommended setting,
+unless otherwise noted.
+
+NOTES:
+	For more information about the AutoNeg, Duplex, and Speed
+        parameters, see the "Speed and Duplex Configuration" section in
+        this document.
+
+        For more information about the InterruptThrottleRate,
+        RxIntDelay, TxIntDelay, RxAbsIntDelay, and TxAbsIntDelay
+        parameters, see the application note at:
+        http://www.intel.com/design/network/applnots/ap450.htm
+
+AutoNeg
+-------
+
+(Supported only on adapters with copper connections)
+
+:Valid Range:   0x01-0x0F, 0x20-0x2F
+:Default Value: 0x2F
+
+This parameter is a bit-mask that specifies the speed and duplex settings
+advertised by the adapter.  When this parameter is used, the Speed and
+Duplex parameters must not be specified.
+
+NOTE:
+       Refer to the Speed and Duplex section of this readme for more
+       information on the AutoNeg parameter.
+
+Duplex
+------
+
+(Supported only on adapters with copper connections)
+
+:Valid Range:   0-2 (0=auto-negotiate, 1=half, 2=full)
+:Default Value: 0
+
+This defines the direction in which data is allowed to flow.  Can be
+either one or two-directional.  If both Duplex and the link partner are
+set to auto-negotiate, the board auto-detects the correct duplex.  If the
+link partner is forced (either full or half), Duplex defaults to half-
+duplex.
+
+FlowControl
+-----------
+
+:Valid Range:   0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
+:Default Value: Reads flow control settings from the EEPROM
+
+This parameter controls the automatic generation(Tx) and response(Rx)
+to Ethernet PAUSE frames.
+
+InterruptThrottleRate
+---------------------
+
+(not supported on Intel(R) 82542, 82543 or 82544-based adapters)
+
+:Valid Range:
+   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
+   4=simplified balancing)
+:Default Value: 3
+
+The driver can limit the amount of interrupts per second that the adapter
+will generate for incoming packets. It does this by writing a value to the
+adapter that is based on the maximum amount of interrupts that the adapter
+will generate per second.
+
+Setting InterruptThrottleRate to a value greater or equal to 100
+will program the adapter to send out a maximum of that many interrupts
+per second, even if more packets have come in. This reduces interrupt
+load on the system and can lower CPU utilization under heavy load,
+but will increase latency as packets are not processed as quickly.
+
+The default behaviour of the driver previously assumed a static
+InterruptThrottleRate value of 8000, providing a good fallback value for
+all traffic types,but lacking in small packet performance and latency.
+The hardware can handle many more small packets per second however, and
+for this reason an adaptive interrupt moderation algorithm was implemented.
+
+Since 7.3.x, the driver has two adaptive modes (setting 1 or 3) in which
+it dynamically adjusts the InterruptThrottleRate value based on the traffic
+that it receives. After determining the type of incoming traffic in the last
+timeframe, it will adjust the InterruptThrottleRate to an appropriate value
+for that traffic.
+
+The algorithm classifies the incoming traffic every interval into
+classes.  Once the class is determined, the InterruptThrottleRate value is
+adjusted to suit that traffic type the best. There are three classes defined:
+"Bulk traffic", for large amounts of packets of normal size; "Low latency",
+for small amounts of traffic and/or a significant percentage of small
+packets; and "Lowest latency", for almost completely small packets or
+minimal traffic.
+
+In dynamic conservative mode, the InterruptThrottleRate value is set to 4000
+for traffic that falls in class "Bulk traffic". If traffic falls in the "Low
+latency" or "Lowest latency" class, the InterruptThrottleRate is increased
+stepwise to 20000. This default mode is suitable for most applications.
+
+For situations where low latency is vital such as cluster or
+grid computing, the algorithm can reduce latency even more when
+InterruptThrottleRate is set to mode 1. In this mode, which operates
+the same as mode 3, the InterruptThrottleRate will be increased stepwise to
+70000 for traffic in class "Lowest latency".
+
+In simplified mode the interrupt rate is based on the ratio of TX and
+RX traffic.  If the bytes per second rate is approximately equal, the
+interrupt rate will drop as low as 2000 interrupts per second.  If the
+traffic is mostly transmit or mostly receive, the interrupt rate could
+be as high as 8000.
+
+Setting InterruptThrottleRate to 0 turns off any interrupt moderation
+and may improve small packet latency, but is generally not suitable
+for bulk throughput traffic.
+
+NOTE:
+       InterruptThrottleRate takes precedence over the TxAbsIntDelay and
+       RxAbsIntDelay parameters.  In other words, minimizing the receive
+       and/or transmit absolute delays does not force the controller to
+       generate more interrupts than what the Interrupt Throttle Rate
+       allows.
+
+CAUTION:
+          If you are using the Intel(R) PRO/1000 CT Network Connection
+          (controller 82547), setting InterruptThrottleRate to a value
+          greater than 75,000, may hang (stop transmitting) adapters
+          under certain network conditions.  If this occurs a NETDEV
+          WATCHDOG message is logged in the system event log.  In
+          addition, the controller is automatically reset, restoring
+          the network connection.  To eliminate the potential for the
+          hang, ensure that InterruptThrottleRate is set no greater
+          than 75,000 and is not set to 0.
+
+NOTE:
+       When e1000 is loaded with default settings and multiple adapters
+       are in use simultaneously, the CPU utilization may increase non-
+       linearly.  In order to limit the CPU utilization without impacting
+       the overall throughput, we recommend that you load the driver as
+       follows::
+
+           modprobe e1000 InterruptThrottleRate=3000,3000,3000
+
+       This sets the InterruptThrottleRate to 3000 interrupts/sec for
+       the first, second, and third instances of the driver.  The range
+       of 2000 to 3000 interrupts per second works on a majority of
+       systems and is a good starting point, but the optimal value will
+       be platform-specific.  If CPU utilization is not a concern, use
+       RX_POLLING (NAPI) and default driver settings.
+
+RxDescriptors
+-------------
+
+:Valid Range:
+ - 48-256 for 82542 and 82543-based adapters
+ - 48-4096 for all other supported adapters
+:Default Value: 256
+
+This value specifies the number of receive buffer descriptors allocated
+by the driver.  Increasing this value allows the driver to buffer more
+incoming packets, at the expense of increased system memory utilization.
+
+Each descriptor is 16 bytes.  A receive buffer is also allocated for each
+descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending
+on the MTU setting. The maximum MTU size is 16110.
+
+NOTE:
+       MTU designates the frame size.  It only needs to be set for Jumbo
+       Frames.  Depending on the available system resources, the request
+       for a higher number of receive descriptors may be denied.  In this
+       case, use a lower number.
+
+RxIntDelay
+----------
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 0
+
+This value delays the generation of receive interrupts in units of 1.024
+microseconds.  Receive interrupt reduction can improve CPU efficiency if
+properly tuned for specific network traffic.  Increasing this value adds
+extra latency to frame reception and can end up decreasing the throughput
+of TCP traffic.  If the system is reporting dropped receives, this value
+may be set too high, causing the driver to run out of available receive
+descriptors.
+
+CAUTION:
+          When setting RxIntDelay to a value other than 0, adapters may
+          hang (stop transmitting) under certain network conditions.  If
+          this occurs a NETDEV WATCHDOG message is logged in the system
+          event log.  In addition, the controller is automatically reset,
+          restoring the network connection.  To eliminate the potential
+          for the hang ensure that RxIntDelay is set to 0.
+
+RxAbsIntDelay
+-------------
+
+(This parameter is supported only on 82540, 82545 and later adapters.)
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 128
+
+This value, in units of 1.024 microseconds, limits the delay in which a
+receive interrupt is generated.  Useful only if RxIntDelay is non-zero,
+this value ensures that an interrupt is generated after the initial
+packet is received within the set amount of time.  Proper tuning,
+along with RxIntDelay, may improve traffic throughput in specific network
+conditions.
+
+Speed
+-----
+
+(This parameter is supported only on adapters with copper connections.)
+
+:Valid Settings: 0, 10, 100, 1000
+:Default Value:  0 (auto-negotiate at all supported speeds)
+
+Speed forces the line speed to the specified value in megabits per second
+(Mbps).  If this parameter is not specified or is set to 0 and the link
+partner is set to auto-negotiate, the board will auto-detect the correct
+speed.  Duplex should also be set when Speed is set to either 10 or 100.
+
+TxDescriptors
+-------------
+
+:Valid Range:
+  - 48-256 for 82542 and 82543-based adapters
+  - 48-4096 for all other supported adapters
+:Default Value: 256
+
+This value is the number of transmit descriptors allocated by the driver.
+Increasing this value allows the driver to queue more transmits.  Each
+descriptor is 16 bytes.
+
+NOTE:
+       Depending on the available system resources, the request for a
+       higher number of transmit descriptors may be denied.  In this case,
+       use a lower number.
+
+TxIntDelay
+----------
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 8
+
+This value delays the generation of transmit interrupts in units of
+1.024 microseconds.  Transmit interrupt reduction can improve CPU
+efficiency if properly tuned for specific network traffic.  If the
+system is reporting dropped transmits, this value may be set too high
+causing the driver to run out of available transmit descriptors.
+
+TxAbsIntDelay
+-------------
+
+(This parameter is supported only on 82540, 82545 and later adapters.)
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 32
+
+This value, in units of 1.024 microseconds, limits the delay in which a
+transmit interrupt is generated.  Useful only if TxIntDelay is non-zero,
+this value ensures that an interrupt is generated after the initial
+packet is sent on the wire within the set amount of time.  Proper tuning,
+along with TxIntDelay, may improve traffic throughput in specific
+network conditions.
+
+XsumRX
+------
+
+(This parameter is NOT supported on the 82542-based adapter.)
+
+:Valid Range:   0-1
+:Default Value: 1
+
+A value of '1' indicates that the driver should enable IP checksum
+offload for received packets (both UDP and TCP) to the adapter hardware.
+
+Copybreak
+---------
+
+:Valid Range:   0-xxxxxxx (0=off)
+:Default Value: 256
+:Usage: modprobe e1000.ko copybreak=128
+
+Driver copies all packets below or equaling this size to a fresh RX
+buffer before handing it up the stack.
+
+This parameter is different than other parameters, in that it is a
+single (not 1,1,1 etc.) parameter applied to all driver instances and
+it is also available during runtime at
+/sys/module/e1000/parameters/copybreak
+
+SmartPowerDownEnable
+--------------------
+
+:Valid Range: 0-1
+:Default Value:  0 (disabled)
+
+Allows PHY to turn off in lower power states. The user can turn off
+this parameter in supported chipsets.
+
+Speed and Duplex Configuration
+==============================
+
+Three keywords are used to control the speed and duplex configuration.
+These keywords are Speed, Duplex, and AutoNeg.
+
+If the board uses a fiber interface, these keywords are ignored, and the
+fiber interface board only links at 1000 Mbps full-duplex.
+
+For copper-based boards, the keywords interact as follows:
+
+- The default operation is auto-negotiate.  The board advertises all
+  supported speed and duplex combinations, and it links at the highest
+  common speed and duplex mode IF the link partner is set to auto-negotiate.
+
+- If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps
+  is advertised (The 1000BaseT spec requires auto-negotiation.)
+
+- If Speed = 10 or 100, then both Speed and Duplex should be set.  Auto-
+  negotiation is disabled, and the AutoNeg parameter is ignored.  Partner
+  SHOULD also be forced.
+
+The AutoNeg parameter is used when more control is required over the
+auto-negotiation process.  It should be used when you wish to control which
+speed and duplex combinations are advertised during the auto-negotiation
+process.
+
+The parameter may be specified as either a decimal or hexadecimal value as
+determined by the bitmap below.
+
+============== ====== ====== ======= ======= ====== ====== ======= ======
+Bit position   7      6      5       4       3      2      1       0
+Decimal Value  128    64     32      16      8      4      2       1
+Hex value      80     40     20      10      8      4      2       1
+Speed (Mbps)   N/A    N/A    1000    N/A     100    100    10      10
+Duplex                       Full            Full   Half   Full    Half
+============== ====== ====== ======= ======= ====== ====== ======= ======
+
+Some examples of using AutoNeg::
+
+  modprobe e1000 AutoNeg=0x01 (Restricts autonegotiation to 10 Half)
+  modprobe e1000 AutoNeg=1 (Same as above)
+  modprobe e1000 AutoNeg=0x02 (Restricts autonegotiation to 10 Full)
+  modprobe e1000 AutoNeg=0x03 (Restricts autonegotiation to 10 Half or 10 Full)
+  modprobe e1000 AutoNeg=0x04 (Restricts autonegotiation to 100 Half)
+  modprobe e1000 AutoNeg=0x05 (Restricts autonegotiation to 10 Half or 100
+  Half)
+  modprobe e1000 AutoNeg=0x020 (Restricts autonegotiation to 1000 Full)
+  modprobe e1000 AutoNeg=32 (Same as above)
+
+Note that when this parameter is used, Speed and Duplex must not be specified.
+
+If the link partner is forced to a specific speed and duplex, then this
+parameter should not be used.  Instead, use the Speed and Duplex parameters
+previously mentioned to force the adapter to the same speed and duplex.
+
+Additional Configurations
+=========================
+
+Jumbo Frames
+------------
+
+  Jumbo Frames support is enabled by changing the MTU to a value larger than
+  the default of 1500.  Use the ifconfig command to increase the MTU size.
+  For example::
+
+       ifconfig eth<x> mtu 9000 up
+
+  This setting is not saved across reboots.  It can be made permanent if
+  you add::
+
+       MTU=9000
+
+  to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>.  This example
+  applies to the Red Hat distributions; other distributions may store this
+  setting in a different location.
+
+Notes:
+  Degradation in throughput performance may be observed in some Jumbo frames
+  environments. If this is observed, increasing the application's socket buffer
+  size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
+  See the specific application manual and /usr/src/linux*/Documentation/
+  networking/ip-sysctl.txt for more details.
+
+  - The maximum MTU setting for Jumbo Frames is 16110.  This value coincides
+    with the maximum Jumbo Frames size of 16128.
+
+  - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
+    poor performance or loss of link.
+
+  - Adapters based on the Intel(R) 82542 and 82573V/E controller do not
+    support Jumbo Frames. These correspond to the following product names::
+
+     Intel(R) PRO/1000 Gigabit Server Adapter
+     Intel(R) PRO/1000 PM Network Connection
+
+ethtool
+-------
+
+  The driver utilizes the ethtool interface for driver configuration and
+  diagnostics, as well as displaying statistical information.  The ethtool
+  version 1.6 or later is required for this functionality.
+
+  The latest release of ethtool can be found from
+  https://www.kernel.org/pub/software/network/ethtool/
+
+Enabling Wake on LAN* (WoL)
+---------------------------
+
+  WoL is configured through the ethtool* utility.
+
+  WoL will be enabled on the system during the next shut down or reboot.
+  For this driver version, in order to enable WoL, the e1000 driver must be
+  loaded when shutting down or rebooting the system.
+
+Support
+=======
+
+For general information, go to the Intel support website at:
+
+    http://support.intel.com
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+    http://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on the supported
+kernel with a supported adapter, email the specific information related
+to the issue to e1000-devel@lists.sf.net
diff --git a/Documentation/networking/device_drivers/intel/e1000e.rst b/Documentation/networking/device_drivers/intel/e1000e.rst
new file mode 100644
index 000000000000..33554e5416c5
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/e1000e.rst
@@ -0,0 +1,382 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux* Driver for Intel(R) Ethernet Network Connection
+======================================================
+
+Intel Gigabit Linux driver.
+Copyright(c) 2008-2018 Intel Corporation.
+
+Contents
+========
+
+- Identifying Your Adapter
+- Command Line Parameters
+- Additional Configurations
+- Support
+
+
+Identifying Your Adapter
+========================
+For information on how to identify your adapter, and for the latest Intel
+network drivers, refer to the Intel Support website:
+https://www.intel.com/support
+
+
+Command Line Parameters
+=======================
+If the driver is built as a module, the following optional parameters are used
+by entering them on the command line with the modprobe command using this
+syntax::
+
+    modprobe e1000e [<option>=<VAL1>,<VAL2>,...]
+
+There needs to be a <VAL#> for each network port in the system supported by
+this driver. The values will be applied to each instance, in function order.
+For example::
+
+    modprobe e1000e InterruptThrottleRate=16000,16000
+
+In this case, there are two network ports supported by e1000e in the system.
+The default value for each parameter is generally the recommended setting,
+unless otherwise noted.
+
+NOTE: A descriptor describes a data buffer and attributes related to the data
+buffer. This information is accessed by the hardware.
+
+InterruptThrottleRate
+---------------------
+:Valid Range: 0,1,3,4,100-100000
+:Default Value: 3
+
+Interrupt Throttle Rate controls the number of interrupts each interrupt
+vector can generate per second. Increasing ITR lowers latency at the cost of
+increased CPU utilization, though it may help throughput in some circumstances.
+
+Setting InterruptThrottleRate to a value greater or equal to 100
+will program the adapter to send out a maximum of that many interrupts
+per second, even if more packets have come in. This reduces interrupt
+load on the system and can lower CPU utilization under heavy load,
+but will increase latency as packets are not processed as quickly.
+
+The default behaviour of the driver previously assumed a static
+InterruptThrottleRate value of 8000, providing a good fallback value for
+all traffic types, but lacking in small packet performance and latency.
+The hardware can handle many more small packets per second however, and
+for this reason an adaptive interrupt moderation algorithm was implemented.
+
+The driver has two adaptive modes (setting 1 or 3) in which
+it dynamically adjusts the InterruptThrottleRate value based on the traffic
+that it receives. After determining the type of incoming traffic in the last
+timeframe, it will adjust the InterruptThrottleRate to an appropriate value
+for that traffic.
+
+The algorithm classifies the incoming traffic every interval into
+classes.  Once the class is determined, the InterruptThrottleRate value is
+adjusted to suit that traffic type the best. There are three classes defined:
+"Bulk traffic", for large amounts of packets of normal size; "Low latency",
+for small amounts of traffic and/or a significant percentage of small
+packets; and "Lowest latency", for almost completely small packets or
+minimal traffic.
+
+ - 0: Off
+      Turns off any interrupt moderation and may improve small packet latency.
+      However, this is generally not suitable for bulk throughput traffic due
+      to the increased CPU utilization of the higher interrupt rate.
+ - 1: Dynamic mode
+      This mode attempts to moderate interrupts per vector while maintaining
+      very low latency. This can sometimes cause extra CPU utilization. If
+      planning on deploying e1000e in a latency sensitive environment, this
+      parameter should be considered.
+ - 3: Dynamic Conservative mode (default)
+      In dynamic conservative mode, the InterruptThrottleRate value is set to
+      4000 for traffic that falls in class "Bulk traffic". If traffic falls in
+      the "Low latency" or "Lowest latency" class, the InterruptThrottleRate is
+      increased stepwise to 20000. This default mode is suitable for most
+      applications.
+ - 4: Simplified Balancing mode
+      In simplified mode the interrupt rate is based on the ratio of TX and
+      RX traffic.  If the bytes per second rate is approximately equal, the
+      interrupt rate will drop as low as 2000 interrupts per second.  If the
+      traffic is mostly transmit or mostly receive, the interrupt rate could
+      be as high as 8000.
+ - 100-100000:
+      Setting InterruptThrottleRate to a value greater or equal to 100
+      will program the adapter to send at most that many interrupts per second,
+      even if more packets have come in. This reduces interrupt load on the
+      system and can lower CPU utilization under heavy load, but will increase
+      latency as packets are not processed as quickly.
+
+NOTE: InterruptThrottleRate takes precedence over the TxAbsIntDelay and
+RxAbsIntDelay parameters. In other words, minimizing the receive and/or
+transmit absolute delays does not force the controller to generate more
+interrupts than what the Interrupt Throttle Rate allows.
+
+RxIntDelay
+----------
+:Valid Range: 0-65535 (0=off)
+:Default Value: 0
+
+This value delays the generation of receive interrupts in units of 1.024
+microseconds. Receive interrupt reduction can improve CPU efficiency if
+properly tuned for specific network traffic. Increasing this value adds extra
+latency to frame reception and can end up decreasing the throughput of TCP
+traffic. If the system is reporting dropped receives, this value may be set
+too high, causing the driver to run out of available receive descriptors.
+
+CAUTION: When setting RxIntDelay to a value other than 0, adapters may hang
+(stop transmitting) under certain network conditions. If this occurs a NETDEV
+WATCHDOG message is logged in the system event log. In addition, the
+controller is automatically reset, restoring the network connection. To
+eliminate the potential for the hang ensure that RxIntDelay is set to 0.
+
+RxAbsIntDelay
+-------------
+:Valid Range: 0-65535 (0=off)
+:Default Value: 8
+
+This value, in units of 1.024 microseconds, limits the delay in which a
+receive interrupt is generated. This value ensures that an interrupt is
+generated after the initial packet is received within the set amount of time,
+which is useful only if RxIntDelay is non-zero. Proper tuning, along with
+RxIntDelay, may improve traffic throughput in specific network conditions.
+
+TxIntDelay
+----------
+:Valid Range: 0-65535 (0=off)
+:Default Value: 8
+
+This value delays the generation of transmit interrupts in units of 1.024
+microseconds. Transmit interrupt reduction can improve CPU efficiency if
+properly tuned for specific network traffic. If the system is reporting
+dropped transmits, this value may be set too high causing the driver to run
+out of available transmit descriptors.
+
+TxAbsIntDelay
+-------------
+:Valid Range: 0-65535 (0=off)
+:Default Value: 32
+
+This value, in units of 1.024 microseconds, limits the delay in which a
+transmit interrupt is generated. It is useful only if TxIntDelay is non-zero.
+It ensures that an interrupt is generated after the initial Packet is sent on
+the wire within the set amount of time. Proper tuning, along with TxIntDelay,
+may improve traffic throughput in specific network conditions.
+
+copybreak
+---------
+:Valid Range: 0-xxxxxxx (0=off)
+:Default Value: 256
+
+The driver copies all packets below or equaling this size to a fresh receive
+buffer before handing it up the stack.
+This parameter differs from other parameters because it is a single (not 1,1,1
+etc.) parameter applied to all driver instances and it is also available
+during runtime at /sys/module/e1000e/parameters/copybreak.
+
+To use copybreak, type::
+
+    modprobe e1000e.ko copybreak=128
+
+SmartPowerDownEnable
+--------------------
+:Valid Range: 0,1
+:Default Value: 0 (disabled)
+
+Allows the PHY to turn off in lower power states. The user can turn off this
+parameter in supported chipsets.
+
+KumeranLockLoss
+---------------
+:Valid Range: 0,1
+:Default Value: 1 (enabled)
+
+This workaround skips resetting the PHY at shutdown for the initial silicon
+releases of ICH8 systems.
+
+IntMode
+-------
+:Valid Range: 0-2
+:Default Value: 0
+
+   +-------+----------------+
+   | Value | Interrupt Mode |
+   +=======+================+
+   |   0   |     Legacy     |
+   +-------+----------------+
+   |   1   |       MSI      |
+   +-------+----------------+
+   |   2   |      MSI-X     |
+   +-------+----------------+
+
+IntMode allows load time control over the type of interrupt registered for by
+the driver. MSI-X is required for multiple queue support, and some kernels and
+combinations of kernel .config options will force a lower level of interrupt
+support.
+
+This command will show different values for each type of interrupt::
+
+  cat /proc/interrupts
+
+CrcStripping
+------------
+:Valid Range: 0,1
+:Default Value: 1 (enabled)
+
+Strip the CRC from received packets before sending up the network stack. If
+you have a machine with a BMC enabled but cannot receive IPMI traffic after
+loading or enabling the driver, try disabling this feature.
+
+WriteProtectNVM
+---------------
+:Valid Range: 0,1
+:Default Value: 1 (enabled)
+
+If set to 1, configure the hardware to ignore all write/erase cycles to the
+GbE region in the ICHx NVM (in order to prevent accidental corruption of the
+NVM). This feature can be disabled by setting the parameter to 0 during initial
+driver load.
+
+NOTE: The machine must be power cycled (full off/on) when enabling NVM writes
+via setting the parameter to zero. Once the NVM has been locked (via the
+parameter at 1 when the driver loads) it cannot be unlocked except via power
+cycle.
+
+Debug
+-----
+:Valid Range: 0-16 (0=none,...,16=all)
+:Default Value: 0
+
+This parameter adjusts the level of debug messages displayed in the system logs.
+
+
+Additional Features and Configurations
+======================================
+
+Jumbo Frames
+------------
+Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU)
+to a value larger than the default value of 1500.
+
+Use the ifconfig command to increase the MTU size. For example, enter the
+following where <x> is the interface number::
+
+    ifconfig eth<x> mtu 9000 up
+
+Alternatively, you can use the ip command as follows::
+
+    ip link set mtu 9000 dev eth<x>
+    ip link set up dev eth<x>
+
+This setting is not saved across reboots. The setting change can be made
+permanent by adding 'MTU=9000' to the file:
+
+- For RHEL: /etc/sysconfig/network-scripts/ifcfg-eth<x>
+- For SLES: /etc/sysconfig/network/<config_file>
+
+NOTE: The maximum MTU setting for Jumbo Frames is 8996. This value coincides
+with the maximum Jumbo Frames size of 9018 bytes.
+
+NOTE: Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
+poor performance or loss of link.
+
+NOTE: The following adapters limit Jumbo Frames sized packets to a maximum of
+4088 bytes:
+
+  - Intel(R) 82578DM Gigabit Network Connection
+  - Intel(R) 82577LM Gigabit Network Connection
+
+The following adapters do not support Jumbo Frames:
+
+  - Intel(R) PRO/1000 Gigabit Server Adapter
+  - Intel(R) PRO/1000 PM Network Connection
+  - Intel(R) 82562G 10/100 Network Connection
+  - Intel(R) 82562G-2 10/100 Network Connection
+  - Intel(R) 82562GT 10/100 Network Connection
+  - Intel(R) 82562GT-2 10/100 Network Connection
+  - Intel(R) 82562V 10/100 Network Connection
+  - Intel(R) 82562V-2 10/100 Network Connection
+  - Intel(R) 82566DC Gigabit Network Connection
+  - Intel(R) 82566DC-2 Gigabit Network Connection
+  - Intel(R) 82566DM Gigabit Network Connection
+  - Intel(R) 82566MC Gigabit Network Connection
+  - Intel(R) 82566MM Gigabit Network Connection
+  - Intel(R) 82567V-3 Gigabit Network Connection
+  - Intel(R) 82577LC Gigabit Network Connection
+  - Intel(R) 82578DC Gigabit Network Connection
+
+NOTE: Jumbo Frames cannot be configured on an 82579-based Network device if
+MACSec is enabled on the system.
+
+
+ethtool
+-------
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information. The latest ethtool
+version is required for this functionality. Download it at:
+
+https://www.kernel.org/pub/software/network/ethtool/
+
+NOTE: When validating enable/disable tests on some parts (for example, 82578),
+it is necessary to add a few seconds between tests when working with ethtool.
+
+
+Speed and Duplex Configuration
+------------------------------
+In addressing speed and duplex configuration issues, you need to distinguish
+between copper-based adapters and fiber-based adapters.
+
+In the default mode, an Intel(R) Ethernet Network Adapter using copper
+connections will attempt to auto-negotiate with its link partner to determine
+the best setting. If the adapter cannot establish link with the link partner
+using auto-negotiation, you may need to manually configure the adapter and link
+partner to identical settings to establish link and pass packets. This should
+only be needed when attempting to link with an older switch that does not
+support auto-negotiation or one that has been forced to a specific speed or
+duplex mode. Your link partner must match the setting you choose. 1 Gbps speeds
+and higher cannot be forced. Use the autonegotiation advertising setting to
+manually set devices for 1 Gbps and higher.
+
+Speed, duplex, and autonegotiation advertising are configured through the
+ethtool* utility.
+
+Caution: Only experienced network administrators should force speed and duplex
+or change autonegotiation advertising manually. The settings at the switch must
+always match the adapter settings. Adapter performance may suffer or your
+adapter may not operate if you configure the adapter differently from your
+switch.
+
+An Intel(R) Ethernet Network Adapter using fiber-based connections, however,
+will not attempt to auto-negotiate with its link partner since those adapters
+operate only in full duplex and only at their native speed.
+
+
+Enabling Wake on LAN* (WoL)
+---------------------------
+WoL is configured through the ethtool* utility.
+
+WoL will be enabled on the system during the next shut down or reboot. For
+this driver version, in order to enable WoL, the e1000e driver must be loaded
+prior to shutting down or suspending the system.
+
+NOTE: Wake on LAN is only supported on port A for the following devices:
+- Intel(R) PRO/1000 PT Dual Port Network Connection
+- Intel(R) PRO/1000 PT Dual Port Server Connection
+- Intel(R) PRO/1000 PT Dual Port Server Adapter
+- Intel(R) PRO/1000 PF Dual Port Server Adapter
+- Intel(R) PRO/1000 PT Quad Port Server Adapter
+- Intel(R) Gigabit PT Quad Port Server ExpressModule
+
+
+Support
+=======
+For general information, go to the Intel support website at:
+
+https://www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+https://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on a supported kernel
+with a supported adapter, email the specific information related to the issue
+to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/device_drivers/intel/fm10k.rst b/Documentation/networking/device_drivers/intel/fm10k.rst
new file mode 100644
index 000000000000..bf5e5942f28d
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/fm10k.rst
@@ -0,0 +1,141 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux* Base Driver for Intel(R) Ethernet Multi-host Controller
+==============================================================
+
+August 20, 2018
+Copyright(c) 2015-2018 Intel Corporation.
+
+Contents
+========
+- Identifying Your Adapter
+- Additional Configurations
+- Performance Tuning
+- Known Issues
+- Support
+
+Identifying Your Adapter
+========================
+The driver in this release is compatible with devices based on the Intel(R)
+Ethernet Multi-host Controller.
+
+For information on how to identify your adapter, and for the latest Intel
+network drivers, refer to the Intel Support website:
+http://www.intel.com/support
+
+
+Flow Control
+------------
+The Intel(R) Ethernet Switch Host Interface Driver does not support Flow
+Control. It will not send pause frames. This may result in dropped frames.
+
+
+Virtual Functions (VFs)
+-----------------------
+Use sysfs to enable VFs.
+Valid Range: 0-64
+
+For example::
+
+    echo $num_vf_enabled > /sys/class/net/$dev/device/sriov_numvfs //enable VFs
+    echo 0 > /sys/class/net/$dev/device/sriov_numvfs //disable VFs
+
+NOTE: Neither the device nor the driver control how VFs are mapped into config
+space. Bus layout will vary by operating system. On operating systems that
+support it, you can check sysfs to find the mapping.
+
+NOTE: When SR-IOV mode is enabled, hardware VLAN filtering and VLAN tag
+stripping/insertion will remain enabled. Please remove the old VLAN filter
+before the new VLAN filter is added. For example::
+
+    ip link set eth0 vf 0 vlan 100	// set vlan 100 for VF 0
+    ip link set eth0 vf 0 vlan 0	// Delete vlan 100
+    ip link set eth0 vf 0 vlan 200	// set a new vlan 200 for VF 0
+
+
+Additional Features and Configurations
+======================================
+
+Jumbo Frames
+------------
+Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU)
+to a value larger than the default value of 1500.
+
+Use the ifconfig command to increase the MTU size. For example, enter the
+following where <x> is the interface number::
+
+    ifconfig eth<x> mtu 9000 up
+
+Alternatively, you can use the ip command as follows::
+
+    ip link set mtu 9000 dev eth<x>
+    ip link set up dev eth<x>
+
+This setting is not saved across reboots. The setting change can be made
+permanent by adding 'MTU=9000' to the file:
+
+- For RHEL: /etc/sysconfig/network-scripts/ifcfg-eth<x>
+- For SLES: /etc/sysconfig/network/<config_file>
+
+NOTE: The maximum MTU setting for Jumbo Frames is 15342. This value coincides
+with the maximum Jumbo Frames size of 15364 bytes.
+
+NOTE: This driver will attempt to use multiple page sized buffers to receive
+each jumbo packet. This should help to avoid buffer starvation issues when
+allocating receive packets.
+
+
+Generic Receive Offload, aka GRO
+--------------------------------
+The driver supports the in-kernel software implementation of GRO. GRO has
+shown that by coalescing Rx traffic into larger chunks of data, CPU
+utilization can be significantly reduced when under large Rx load. GRO is an
+evolution of the previously-used LRO interface. GRO is able to coalesce
+other protocols besides TCP. It's also safe to use with configurations that
+are problematic for LRO, namely bridging and iSCSI.
+
+
+
+Supported ethtool Commands and Options for Filtering
+----------------------------------------------------
+-n --show-nfc
+  Retrieves the receive network flow classification configurations.
+
+rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6
+  Retrieves the hash options for the specified network traffic type.
+
+-N --config-nfc
+  Configures the receive network flow classification.
+
+rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6 m|v|t|s|d|f|n|r
+  Configures the hash options for the specified network traffic type.
+
+- udp4: UDP over IPv4
+- udp6: UDP over IPv6
+- f Hash on bytes 0 and 1 of the Layer 4 header of the rx packet.
+- n Hash on bytes 2 and 3 of the Layer 4 header of the rx packet.
+
+
+Known Issues/Troubleshooting
+============================
+
+Enabling SR-IOV in a 64-bit Microsoft* Windows Server* 2012/R2 guest OS under Linux KVM
+---------------------------------------------------------------------------------------
+KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM. This
+includes traditional PCIe devices, as well as SR-IOV-capable devices based on
+the Intel Ethernet Controller XL710.
+
+
+Support
+=======
+For general information, go to the Intel support website at:
+
+https://www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+https://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on a supported kernel
+with a supported adapter, email the specific information related to the issue
+to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/device_drivers/intel/i40e.rst b/Documentation/networking/device_drivers/intel/i40e.rst
new file mode 100644
index 000000000000..0cc16c525d10
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/i40e.rst
@@ -0,0 +1,770 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux* Base Driver for the Intel(R) Ethernet Controller 700 Series
+==================================================================
+
+Intel 40 Gigabit Linux driver.
+Copyright(c) 1999-2018 Intel Corporation.
+
+Contents
+========
+
+- Overview
+- Identifying Your Adapter
+- Intel(R) Ethernet Flow Director
+- Additional Configurations
+- Known Issues
+- Support
+
+
+Driver information can be obtained using ethtool, lspci, and ifconfig.
+Instructions on updating ethtool can be found in the section Additional
+Configurations later in this document.
+
+For questions related to hardware requirements, refer to the documentation
+supplied with your Intel adapter. All hardware requirements listed apply to use
+with Linux.
+
+
+Identifying Your Adapter
+========================
+The driver is compatible with devices based on the following:
+
+ * Intel(R) Ethernet Controller X710
+ * Intel(R) Ethernet Controller XL710
+ * Intel(R) Ethernet Network Connection X722
+ * Intel(R) Ethernet Controller XXV710
+
+For the best performance, make sure the latest NVM/FW is installed on your
+device.
+
+For information on how to identify your adapter, and for the latest NVM/FW
+images and Intel network drivers, refer to the Intel Support website:
+https://www.intel.com/support
+
+SFP+ and QSFP+ Devices
+----------------------
+For information about supported media, refer to this document:
+https://www.intel.com/content/dam/www/public/us/en/documents/release-notes/xl710-ethernet-controller-feature-matrix.pdf
+
+NOTE: Some adapters based on the Intel(R) Ethernet Controller 700 Series only
+support Intel Ethernet Optics modules. On these adapters, other modules are not
+supported and will not function.  In all cases Intel recommends using Intel
+Ethernet Optics; other modules may function but are not validated by Intel.
+Contact Intel for supported media types.
+
+NOTE: For connections based on Intel(R) Ethernet Controller 700 Series, support
+is dependent on your system board. Please see your vendor for details.
+
+NOTE: In systems that do not have adequate airflow to cool the adapter and
+optical modules, you must use high temperature optical modules.
+
+Virtual Functions (VFs)
+-----------------------
+Use sysfs to enable VFs. For example::
+
+  #echo $num_vf_enabled > /sys/class/net/$dev/device/sriov_numvfs #enable VFs
+  #echo 0 > /sys/class/net/$dev/device/sriov_numvfs #disable VFs
+
+For example, the following instructions will configure PF eth0 and the first VF
+on VLAN 10::
+
+  $ ip link set dev eth0 vf 0 vlan 10
+
+VLAN Tag Packet Steering
+------------------------
+Allows you to send all packets with a specific VLAN tag to a particular SR-IOV
+virtual function (VF). Further, this feature allows you to designate a
+particular VF as trusted, and allows that trusted VF to request selective
+promiscuous mode on the Physical Function (PF).
+
+To set a VF as trusted or untrusted, enter the following command in the
+Hypervisor::
+
+  # ip link set dev eth0 vf 1 trust [on|off]
+
+Once the VF is designated as trusted, use the following commands in the VM to
+set the VF to promiscuous mode.
+
+::
+
+  For promiscuous all:
+  #ip link set eth2 promisc on
+  Where eth2 is a VF interface in the VM
+
+  For promiscuous Multicast:
+  #ip link set eth2 allmulticast on
+  Where eth2 is a VF interface in the VM
+
+NOTE: By default, the ethtool priv-flag vf-true-promisc-support is set to
+"off",meaning that promiscuous mode for the VF will be limited. To set the
+promiscuous mode for the VF to true promiscuous and allow the VF to see all
+ingress traffic, use the following command::
+
+  #ethtool -set-priv-flags p261p1 vf-true-promisc-support on
+
+The vf-true-promisc-support priv-flag does not enable promiscuous mode; rather,
+it designates which type of promiscuous mode (limited or true) you will get
+when you enable promiscuous mode using the ip link commands above. Note that
+this is a global setting that affects the entire device. However,the
+vf-true-promisc-support priv-flag is only exposed to the first PF of the
+device. The PF remains in limited promiscuous mode (unless it is in MFP mode)
+regardless of the vf-true-promisc-support setting.
+
+Now add a VLAN interface on the VF interface::
+
+  #ip link add link eth2 name eth2.100 type vlan id 100
+
+Note that the order in which you set the VF to promiscuous mode and add the
+VLAN interface does not matter (you can do either first). The end result in
+this example is that the VF will get all traffic that is tagged with VLAN 100.
+
+Intel(R) Ethernet Flow Director
+-------------------------------
+The Intel Ethernet Flow Director performs the following tasks:
+
+- Directs receive packets according to their flows to different queues.
+- Enables tight control on routing a flow in the platform.
+- Matches flows and CPU cores for flow affinity.
+- Supports multiple parameters for flexible flow classification and load
+  balancing (in SFP mode only).
+
+NOTE: The Linux i40e driver supports the following flow types: IPv4, TCPv4, and
+UDPv4. For a given flow type, it supports valid combinations of IP addresses
+(source or destination) and UDP/TCP ports (source and destination). For
+example, you can supply only a source IP address, a source IP address and a
+destination port, or any combination of one or more of these four parameters.
+
+NOTE: The Linux i40e driver allows you to filter traffic based on a
+user-defined flexible two-byte pattern and offset by using the ethtool user-def
+and mask fields. Only L3 and L4 flow types are supported for user-defined
+flexible filters. For a given flow type, you must clear all Intel Ethernet Flow
+Director filters before changing the input set (for that flow type).
+
+To enable or disable the Intel Ethernet Flow Director::
+
+  # ethtool -K ethX ntuple <on|off>
+
+When disabling ntuple filters, all the user programmed filters are flushed from
+the driver cache and hardware. All needed filters must be re-added when ntuple
+is re-enabled.
+
+To add a filter that directs packet to queue 2, use -U or -N switch::
+
+  # ethtool -N ethX flow-type tcp4 src-ip 192.168.10.1 dst-ip \
+  192.168.10.2 src-port 2000 dst-port 2001 action 2 [loc 1]
+
+To set a filter using only the source and destination IP address::
+
+  # ethtool -N ethX flow-type tcp4 src-ip 192.168.10.1 dst-ip \
+  192.168.10.2 action 2 [loc 1]
+
+To see the list of filters currently present::
+
+  # ethtool <-u|-n> ethX
+
+Application Targeted Routing (ATR) Perfect Filters
+--------------------------------------------------
+ATR is enabled by default when the kernel is in multiple transmit queue mode.
+An ATR Intel Ethernet Flow Director filter rule is added when a TCP-IP flow
+starts and is deleted when the flow ends. When a TCP-IP Intel Ethernet Flow
+Director rule is added from ethtool (Sideband filter), ATR is turned off by the
+driver. To re-enable ATR, the sideband can be disabled with the ethtool -K
+option. For example::
+
+  ethtool –K [adapter] ntuple [off|on]
+
+If sideband is re-enabled after ATR is re-enabled, ATR remains enabled until a
+TCP-IP flow is added. When all TCP-IP sideband rules are deleted, ATR is
+automatically re-enabled.
+
+Packets that match the ATR rules are counted in fdir_atr_match stats in
+ethtool, which also can be used to verify whether ATR rules still exist.
+
+Sideband Perfect Filters
+------------------------
+Sideband Perfect Filters are used to direct traffic that matches specified
+characteristics. They are enabled through ethtool's ntuple interface. To add a
+new filter use the following command::
+
+  ethtool -U <device> flow-type <type> src-ip <ip> dst-ip <ip> src-port <port> \
+  dst-port <port> action <queue>
+
+Where:
+  <device> - the ethernet device to program
+  <type> - can be ip4, tcp4, udp4, or sctp4
+  <ip> - the ip address to match on
+  <port> - the port number to match on
+  <queue> - the queue to direct traffic towards (-1 discards matching traffic)
+
+Use the following command to display all of the active filters::
+
+  ethtool -u <device>
+
+Use the following command to delete a filter::
+
+  ethtool -U <device> delete <N>
+
+Where <N> is the filter id displayed when printing all the active filters, and
+may also have been specified using "loc <N>" when adding the filter.
+
+The following example matches TCP traffic sent from 192.168.0.1, port 5300,
+directed to 192.168.0.5, port 80, and sends it to queue 7::
+
+  ethtool -U enp130s0 flow-type tcp4 src-ip 192.168.0.1 dst-ip 192.168.0.5 \
+  src-port 5300 dst-port 80 action 7
+
+For each flow-type, the programmed filters must all have the same matching
+input set. For example, issuing the following two commands is acceptable::
+
+  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.1 src-port 5300 action 7
+  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.5 src-port 55 action 10
+
+Issuing the next two commands, however, is not acceptable, since the first
+specifies src-ip and the second specifies dst-ip::
+
+  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.1 src-port 5300 action 7
+  ethtool -U enp130s0 flow-type ip4 dst-ip 192.168.0.5 src-port 55 action 10
+
+The second command will fail with an error. You may program multiple filters
+with the same fields, using different values, but, on one device, you may not
+program two tcp4 filters with different matching fields.
+
+Matching on a sub-portion of a field is not supported by the i40e driver, thus
+partial mask fields are not supported.
+
+The driver also supports matching user-defined data within the packet payload.
+This flexible data is specified using the "user-def" field of the ethtool
+command in the following way:
+
++----------------------------+--------------------------+
+| 31    28    24    20    16 | 15    12    8    4    0  |
++----------------------------+--------------------------+
+| offset into packet payload | 2 bytes of flexible data |
++----------------------------+--------------------------+
+
+For example,
+
+::
+
+  ... user-def 0x4FFFF ...
+
+tells the filter to look 4 bytes into the payload and match that value against
+0xFFFF. The offset is based on the beginning of the payload, and not the
+beginning of the packet. Thus
+
+::
+
+  flow-type tcp4 ... user-def 0x8BEAF ...
+
+would match TCP/IPv4 packets which have the value 0xBEAF 8 bytes into the
+TCP/IPv4 payload.
+
+Note that ICMP headers are parsed as 4 bytes of header and 4 bytes of payload.
+Thus to match the first byte of the payload, you must actually add 4 bytes to
+the offset. Also note that ip4 filters match both ICMP frames as well as raw
+(unknown) ip4 frames, where the payload will be the L3 payload of the IP4 frame.
+
+The maximum offset is 64. The hardware will only read up to 64 bytes of data
+from the payload. The offset must be even because the flexible data is 2 bytes
+long and must be aligned to byte 0 of the packet payload.
+
+The user-defined flexible offset is also considered part of the input set and
+cannot be programmed separately for multiple filters of the same type. However,
+the flexible data is not part of the input set and multiple filters may use the
+same offset but match against different data.
+
+To create filters that direct traffic to a specific Virtual Function, use the
+"action" parameter. Specify the action as a 64 bit value, where the lower 32
+bits represents the queue number, while the next 8 bits represent which VF.
+Note that 0 is the PF, so the VF identifier is offset by 1. For example::
+
+  ... action 0x800000002 ...
+
+specifies to direct traffic to Virtual Function 7 (8 minus 1) into queue 2 of
+that VF.
+
+Note that these filters will not break internal routing rules, and will not
+route traffic that otherwise would not have been sent to the specified Virtual
+Function.
+
+Setting the link-down-on-close Private Flag
+-------------------------------------------
+When the link-down-on-close private flag is set to "on", the port's link will
+go down when the interface is brought down using the ifconfig ethX down command.
+
+Use ethtool to view and set link-down-on-close, as follows::
+
+  ethtool --show-priv-flags ethX
+  ethtool --set-priv-flags ethX link-down-on-close [on|off]
+
+Viewing Link Messages
+---------------------
+Link messages will not be displayed to the console if the distribution is
+restricting system messages. In order to see network driver link messages on
+your console, set dmesg to eight by entering the following::
+
+  dmesg -n 8
+
+NOTE: This setting is not saved across reboots.
+
+Jumbo Frames
+------------
+Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU)
+to a value larger than the default value of 1500.
+
+Use the ifconfig command to increase the MTU size. For example, enter the
+following where <x> is the interface number::
+
+  ifconfig eth<x> mtu 9000 up
+
+Alternatively, you can use the ip command as follows::
+
+  ip link set mtu 9000 dev eth<x>
+  ip link set up dev eth<x>
+
+This setting is not saved across reboots. The setting change can be made
+permanent by adding 'MTU=9000' to the file::
+
+  /etc/sysconfig/network-scripts/ifcfg-eth<x> // for RHEL
+  /etc/sysconfig/network/<config_file> // for SLES
+
+NOTE: The maximum MTU setting for Jumbo Frames is 9702. This value coincides
+with the maximum Jumbo Frames size of 9728 bytes.
+
+NOTE: This driver will attempt to use multiple page sized buffers to receive
+each jumbo packet. This should help to avoid buffer starvation issues when
+allocating receive packets.
+
+ethtool
+-------
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information. The latest ethtool
+version is required for this functionality. Download it at:
+https://www.kernel.org/pub/software/network/ethtool/
+
+Supported ethtool Commands and Options for Filtering
+----------------------------------------------------
+-n --show-nfc
+  Retrieves the receive network flow classification configurations.
+
+rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6
+  Retrieves the hash options for the specified network traffic type.
+
+-N --config-nfc
+  Configures the receive network flow classification.
+
+rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6 m|v|t|s|d|f|n|r...
+  Configures the hash options for the specified network traffic type.
+
+udp4 UDP over IPv4
+udp6 UDP over IPv6
+
+f Hash on bytes 0 and 1 of the Layer 4 header of the Rx packet.
+n Hash on bytes 2 and 3 of the Layer 4 header of the Rx packet.
+
+Speed and Duplex Configuration
+------------------------------
+In addressing speed and duplex configuration issues, you need to distinguish
+between copper-based adapters and fiber-based adapters.
+
+In the default mode, an Intel(R) Ethernet Network Adapter using copper
+connections will attempt to auto-negotiate with its link partner to determine
+the best setting. If the adapter cannot establish link with the link partner
+using auto-negotiation, you may need to manually configure the adapter and link
+partner to identical settings to establish link and pass packets. This should
+only be needed when attempting to link with an older switch that does not
+support auto-negotiation or one that has been forced to a specific speed or
+duplex mode. Your link partner must match the setting you choose. 1 Gbps speeds
+and higher cannot be forced. Use the autonegotiation advertising setting to
+manually set devices for 1 Gbps and higher.
+
+NOTE: You cannot set the speed for devices based on the Intel(R) Ethernet
+Network Adapter XXV710 based devices.
+
+Speed, duplex, and autonegotiation advertising are configured through the
+ethtool* utility.
+
+Caution: Only experienced network administrators should force speed and duplex
+or change autonegotiation advertising manually. The settings at the switch must
+always match the adapter settings. Adapter performance may suffer or your
+adapter may not operate if you configure the adapter differently from your
+switch.
+
+An Intel(R) Ethernet Network Adapter using fiber-based connections, however,
+will not attempt to auto-negotiate with its link partner since those adapters
+operate only in full duplex and only at their native speed.
+
+NAPI
+----
+NAPI (Rx polling mode) is supported in the i40e driver.
+For more information on NAPI, see
+https://wiki.linuxfoundation.org/networking/napi
+
+Flow Control
+------------
+Ethernet Flow Control (IEEE 802.3x) can be configured with ethtool to enable
+receiving and transmitting pause frames for i40e. When transmit is enabled,
+pause frames are generated when the receive packet buffer crosses a predefined
+threshold. When receive is enabled, the transmit unit will halt for the time
+delay specified when a pause frame is received.
+
+NOTE: You must have a flow control capable link partner.
+
+Flow Control is on by default.
+
+Use ethtool to change the flow control settings.
+
+To enable or disable Rx or Tx Flow Control::
+
+  ethtool -A eth? rx <on|off> tx <on|off>
+
+Note: This command only enables or disables Flow Control if auto-negotiation is
+disabled. If auto-negotiation is enabled, this command changes the parameters
+used for auto-negotiation with the link partner.
+
+To enable or disable auto-negotiation::
+
+  ethtool -s eth? autoneg <on|off>
+
+Note: Flow Control auto-negotiation is part of link auto-negotiation. Depending
+on your device, you may not be able to change the auto-negotiation setting.
+
+RSS Hash Flow
+-------------
+Allows you to set the hash bytes per flow type and any combination of one or
+more options for Receive Side Scaling (RSS) hash byte configuration.
+
+::
+
+  # ethtool -N <dev> rx-flow-hash <type> <option>
+
+Where <type> is:
+  tcp4	signifying TCP over IPv4
+  udp4	signifying UDP over IPv4
+  tcp6	signifying TCP over IPv6
+  udp6	signifying UDP over IPv6
+And <option> is one or more of:
+  s	Hash on the IP source address of the Rx packet.
+  d	Hash on the IP destination address of the Rx packet.
+  f	Hash on bytes 0 and 1 of the Layer 4 header of the Rx packet.
+  n	Hash on bytes 2 and 3 of the Layer 4 header of the Rx packet.
+
+MAC and VLAN anti-spoofing feature
+----------------------------------
+When a malicious driver attempts to send a spoofed packet, it is dropped by the
+hardware and not transmitted.
+NOTE: This feature can be disabled for a specific Virtual Function (VF)::
+
+  ip link set <pf dev> vf <vf id> spoofchk {off|on}
+
+IEEE 1588 Precision Time Protocol (PTP) Hardware Clock (PHC)
+------------------------------------------------------------
+Precision Time Protocol (PTP) is used to synchronize clocks in a computer
+network. PTP support varies among Intel devices that support this driver. Use
+"ethtool -T <netdev name>" to get a definitive list of PTP capabilities
+supported by the device.
+
+IEEE 802.1ad (QinQ) Support
+---------------------------
+The IEEE 802.1ad standard, informally known as QinQ, allows for multiple VLAN
+IDs within a single Ethernet frame. VLAN IDs are sometimes referred to as
+"tags," and multiple VLAN IDs are thus referred to as a "tag stack." Tag stacks
+allow L2 tunneling and the ability to segregate traffic within a particular
+VLAN ID, among other uses.
+
+The following are examples of how to configure 802.1ad (QinQ)::
+
+  ip link add link eth0 eth0.24 type vlan proto 802.1ad id 24
+  ip link add link eth0.24 eth0.24.371 type vlan proto 802.1Q id 371
+
+Where "24" and "371" are example VLAN IDs.
+
+NOTES:
+  Receive checksum offloads, cloud filters, and VLAN acceleration are not
+  supported for 802.1ad (QinQ) packets.
+
+VXLAN and GENEVE Overlay HW Offloading
+--------------------------------------
+Virtual Extensible LAN (VXLAN) allows you to extend an L2 network over an L3
+network, which may be useful in a virtualized or cloud environment. Some
+Intel(R) Ethernet Network devices perform VXLAN processing, offloading it from
+the operating system. This reduces CPU utilization.
+
+VXLAN offloading is controlled by the Tx and Rx checksum offload options
+provided by ethtool. That is, if Tx checksum offload is enabled, and the
+adapter has the capability, VXLAN offloading is also enabled.
+
+Support for VXLAN and GENEVE HW offloading is dependent on kernel support of
+the HW offloading features.
+
+Multiple Functions per Port
+---------------------------
+Some adapters based on the Intel Ethernet Controller X710/XL710 support
+multiple functions on a single physical port. Configure these functions through
+the System Setup/BIOS.
+
+Minimum TX Bandwidth is the guaranteed minimum data transmission bandwidth, as
+a percentage of the full physical port link speed, that the partition will
+receive. The bandwidth the partition is awarded will never fall below the level
+you specify.
+
+The range for the minimum bandwidth values is:
+1 to ((100 minus # of partitions on the physical port) plus 1)
+For example, if a physical port has 4 partitions, the range would be:
+1 to ((100 - 4) + 1 = 97)
+
+The Maximum Bandwidth percentage represents the maximum transmit bandwidth
+allocated to the partition as a percentage of the full physical port link
+speed. The accepted range of values is 1-100. The value is used as a limiter,
+should you chose that any one particular function not be able to consume 100%
+of a port's bandwidth (should it be available). The sum of all the values for
+Maximum Bandwidth is not restricted, because no more than 100% of a port's
+bandwidth can ever be used.
+
+NOTE: X710/XXV710 devices fail to enable Max VFs (64) when Multiple Functions
+per Port (MFP) and SR-IOV are enabled. An error from i40e is logged that says
+"add vsi failed for VF N, aq_err 16". To workaround the issue, enable less than
+64 virtual functions (VFs).
+
+Data Center Bridging (DCB)
+--------------------------
+DCB is a configuration Quality of Service implementation in hardware. It uses
+the VLAN priority tag (802.1p) to filter traffic. That means that there are 8
+different priorities that traffic can be filtered into. It also enables
+priority flow control (802.1Qbb) which can limit or eliminate the number of
+dropped packets during network stress. Bandwidth can be allocated to each of
+these priorities, which is enforced at the hardware level (802.1Qaz).
+
+Adapter firmware implements LLDP and DCBX protocol agents as per 802.1AB and
+802.1Qaz respectively. The firmware based DCBX agent runs in willing mode only
+and can accept settings from a DCBX capable peer. Software configuration of
+DCBX parameters via dcbtool/lldptool are not supported.
+
+NOTE: Firmware LLDP can be disabled by setting the private flag disable-fw-lldp.
+
+The i40e driver implements the DCB netlink interface layer to allow user-space
+to communicate with the driver and query DCB configuration for the port.
+
+NOTE:
+The kernel assumes that TC0 is available, and will disable Priority Flow
+Control (PFC) on the device if TC0 is not available. To fix this, ensure TC0 is
+enabled when setting up DCB on your switch.
+
+Interrupt Rate Limiting
+-----------------------
+:Valid Range: 0-235 (0=no limit)
+
+The Intel(R) Ethernet Controller XL710 family supports an interrupt rate
+limiting mechanism. The user can control, via ethtool, the number of
+microseconds between interrupts.
+
+Syntax::
+
+  # ethtool -C ethX rx-usecs-high N
+
+The range of 0-235 microseconds provides an effective range of 4,310 to 250,000
+interrupts per second. The value of rx-usecs-high can be set independently of
+rx-usecs and tx-usecs in the same ethtool command, and is also independent of
+the adaptive interrupt moderation algorithm. The underlying hardware supports
+granularity in 4-microsecond intervals, so adjacent values may result in the
+same interrupt rate.
+
+One possible use case is the following::
+
+  # ethtool -C ethX adaptive-rx off adaptive-tx off rx-usecs-high 20 rx-usecs \
+    5 tx-usecs 5
+
+The above command would disable adaptive interrupt moderation, and allow a
+maximum of 5 microseconds before indicating a receive or transmit was complete.
+However, instead of resulting in as many as 200,000 interrupts per second, it
+limits total interrupts per second to 50,000 via the rx-usecs-high parameter.
+
+Performance Optimization
+========================
+Driver defaults are meant to fit a wide variety of workloads, but if further
+optimization is required we recommend experimenting with the following settings.
+
+NOTE: For better performance when processing small (64B) frame sizes, try
+enabling Hyper threading in the BIOS in order to increase the number of logical
+cores in the system and subsequently increase the number of queues available to
+the adapter.
+
+Virtualized Environments
+------------------------
+1. Disable XPS on both ends by using the included virt_perf_default script
+or by running the following command as root::
+
+  for file in `ls /sys/class/net/<ethX>/queues/tx-*/xps_cpus`;
+  do echo 0 > $file; done
+
+2. Using the appropriate mechanism (vcpupin) in the vm, pin the cpu's to
+individual lcpu's, making sure to use a set of cpu's included in the
+device's local_cpulist: /sys/class/net/<ethX>/device/local_cpulist.
+
+3. Configure as many Rx/Tx queues in the VM as available. Do not rely on
+the default setting of 1.
+
+
+Non-virtualized Environments
+----------------------------
+Pin the adapter's IRQs to specific cores by disabling the irqbalance service
+and using the included set_irq_affinity script. Please see the script's help
+text for further options.
+
+- The following settings will distribute the IRQs across all the cores evenly::
+
+  # scripts/set_irq_affinity -x all <interface1> , [ <interface2>, ... ]
+
+- The following settings will distribute the IRQs across all the cores that are
+  local to the adapter (same NUMA node)::
+
+  # scripts/set_irq_affinity -x local <interface1> ,[ <interface2>, ... ]
+
+For very CPU intensive workloads, we recommend pinning the IRQs to all cores.
+
+For IP Forwarding: Disable Adaptive ITR and lower Rx and Tx interrupts per
+queue using ethtool.
+
+- Setting rx-usecs and tx-usecs to 125 will limit interrupts to about 8000
+  interrupts per second per queue.
+
+::
+
+  # ethtool -C <interface> adaptive-rx off adaptive-tx off rx-usecs 125 \
+    tx-usecs 125
+
+For lower CPU utilization: Disable Adaptive ITR and lower Rx and Tx interrupts
+per queue using ethtool.
+
+- Setting rx-usecs and tx-usecs to 250 will limit interrupts to about 4000
+  interrupts per second per queue.
+
+::
+
+  # ethtool -C <interface> adaptive-rx off adaptive-tx off rx-usecs 250 \
+    tx-usecs 250
+
+For lower latency: Disable Adaptive ITR and ITR by setting Rx and Tx to 0 using
+ethtool.
+
+::
+
+  # ethtool -C <interface> adaptive-rx off adaptive-tx off rx-usecs 0 \
+    tx-usecs 0
+
+Application Device Queues (ADq)
+-------------------------------
+Application Device Queues (ADq) allows you to dedicate one or more queues to a
+specific application. This can reduce latency for the specified application,
+and allow Tx traffic to be rate limited per application. Follow the steps below
+to set ADq.
+
+1. Create traffic classes (TCs). Maximum of 8 TCs can be created per interface.
+The shaper bw_rlimit parameter is optional.
+
+Example: Sets up two tcs, tc0 and tc1, with 16 queues each and max tx rate set
+to 1Gbit for tc0 and 3Gbit for tc1.
+
+::
+
+  # tc qdisc add dev <interface> root mqprio num_tc 2 map 0 0 0 0 1 1 1 1
+  queues 16@0 16@16 hw 1 mode channel shaper bw_rlimit min_rate 1Gbit 2Gbit
+  max_rate 1Gbit 3Gbit
+
+map: priority mapping for up to 16 priorities to tcs (e.g. map 0 0 0 0 1 1 1 1
+sets priorities 0-3 to use tc0 and 4-7 to use tc1)
+
+queues: for each tc, <num queues>@<offset> (e.g. queues 16@0 16@16 assigns
+16 queues to tc0 at offset 0 and 16 queues to tc1 at offset 16. Max total
+number of queues for all tcs is 64 or number of cores, whichever is lower.)
+
+hw 1 mode channel: ‘channel’ with ‘hw’ set to 1 is a new new hardware
+offload mode in mqprio that makes full use of the mqprio options, the
+TCs, the queue configurations, and the QoS parameters.
+
+shaper bw_rlimit: for each tc, sets minimum and maximum bandwidth rates.
+Totals must be equal or less than port speed.
+
+For example: min_rate 1Gbit 3Gbit: Verify bandwidth limit using network
+monitoring tools such as ifstat or sar –n DEV [interval] [number of samples]
+
+2. Enable HW TC offload on interface::
+
+    # ethtool -K <interface> hw-tc-offload on
+
+3. Apply TCs to ingress (RX) flow of interface::
+
+    # tc qdisc add dev <interface> ingress
+
+NOTES:
+ - Run all tc commands from the iproute2 <pathtoiproute2>/tc/ directory.
+ - ADq is not compatible with cloud filters.
+ - Setting up channels via ethtool (ethtool -L) is not supported when the
+   TCs are configured using mqprio.
+ - You must have iproute2 latest version
+ - NVM version 6.01 or later is required.
+ - ADq cannot be enabled when any the following features are enabled: Data
+   Center Bridging (DCB), Multiple Functions per Port (MFP), or Sideband
+   Filters.
+ - If another driver (for example, DPDK) has set cloud filters, you cannot
+   enable ADq.
+ - Tunnel filters are not supported in ADq. If encapsulated packets do
+   arrive in non-tunnel mode, filtering will be done on the inner headers.
+   For example, for VXLAN traffic in non-tunnel mode, PCTYPE is identified
+   as a VXLAN encapsulated packet, outer headers are ignored. Therefore,
+   inner headers are matched.
+ - If a TC filter on a PF matches traffic over a VF (on the PF), that
+   traffic will be routed to the appropriate queue of the PF, and will
+   not be passed on the VF. Such traffic will end up getting dropped higher
+   up in the TCP/IP stack as it does not match PF address data.
+ - If traffic matches multiple TC filters that point to different TCs,
+   that traffic will be duplicated and sent to all matching TC queues.
+   The hardware switch mirrors the packet to a VSI list when multiple
+   filters are matched.
+
+
+Known Issues/Troubleshooting
+============================
+
+NOTE: 1 Gb devices based on the Intel(R) Ethernet Network Connection X722 do
+not support the following features:
+
+  * Data Center Bridging (DCB)
+  * QOS
+  * VMQ
+  * SR-IOV
+  * Task Encapsulation offload (VXLAN, NVGRE)
+  * Energy Efficient Ethernet (EEE)
+  * Auto-media detect
+
+Unexpected Issues when the device driver and DPDK share a device
+----------------------------------------------------------------
+Unexpected issues may result when an i40e device is in multi driver mode and
+the kernel driver and DPDK driver are sharing the device. This is because
+access to the global NIC resources is not synchronized between multiple
+drivers. Any change to the global NIC configuration (writing to a global
+register, setting global configuration by AQ, or changing switch modes) will
+affect all ports and drivers on the device. Loading DPDK with the
+"multi-driver" module parameter may mitigate some of the issues.
+
+TC0 must be enabled when setting up DCB on a switch
+---------------------------------------------------
+The kernel assumes that TC0 is available, and will disable Priority Flow
+Control (PFC) on the device if TC0 is not available. To fix this, ensure TC0 is
+enabled when setting up DCB on your switch.
+
+
+Support
+=======
+For general information, go to the Intel support website at:
+
+https://www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+https://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on a supported kernel
+with a supported adapter, email the specific information related to the issue
+to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/device_drivers/intel/iavf.rst b/Documentation/networking/device_drivers/intel/iavf.rst
new file mode 100644
index 000000000000..f8b42b64eb28
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/iavf.rst
@@ -0,0 +1,281 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux* Base Driver for Intel(R) Ethernet Adaptive Virtual Function
+==================================================================
+
+Intel Ethernet Adaptive Virtual Function Linux driver.
+Copyright(c) 2013-2018 Intel Corporation.
+
+Contents
+========
+
+- Identifying Your Adapter
+- Additional Configurations
+- Known Issues/Troubleshooting
+- Support
+
+This file describes the iavf Linux* Base Driver. This driver was formerly
+called i40evf.
+
+The iavf driver supports the below mentioned virtual function devices and
+can only be activated on kernels running the i40e or newer Physical Function
+(PF) driver compiled with CONFIG_PCI_IOV.  The iavf driver requires
+CONFIG_PCI_MSI to be enabled.
+
+The guest OS loading the iavf driver must support MSI-X interrupts.
+
+Identifying Your Adapter
+========================
+The driver in this kernel is compatible with devices based on the following:
+ * Intel(R) XL710 X710 Virtual Function
+ * Intel(R) X722 Virtual Function
+ * Intel(R) XXV710 Virtual Function
+ * Intel(R) Ethernet Adaptive Virtual Function
+
+For the best performance, make sure the latest NVM/FW is installed on your
+device.
+
+For information on how to identify your adapter, and for the latest NVM/FW
+images and Intel network drivers, refer to the Intel Support website:
+http://www.intel.com/support
+
+
+Additional Features and Configurations
+======================================
+
+Viewing Link Messages
+---------------------
+Link messages will not be displayed to the console if the distribution is
+restricting system messages. In order to see network driver link messages on
+your console, set dmesg to eight by entering the following::
+
+  dmesg -n 8
+
+NOTE: This setting is not saved across reboots.
+
+ethtool
+-------
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information. The latest ethtool
+version is required for this functionality. Download it at:
+https://www.kernel.org/pub/software/network/ethtool/
+
+Setting VLAN Tag Stripping
+--------------------------
+If you have applications that require Virtual Functions (VFs) to receive
+packets with VLAN tags, you can disable VLAN tag stripping for the VF. The
+Physical Function (PF) processes requests issued from the VF to enable or
+disable VLAN tag stripping. Note that if the PF has assigned a VLAN to a VF,
+then requests from that VF to set VLAN tag stripping will be ignored.
+
+To enable/disable VLAN tag stripping for a VF, issue the following command
+from inside the VM in which you are running the VF::
+
+  ethtool -K <if_name> rxvlan on/off
+
+or alternatively::
+
+  ethtool --offload <if_name> rxvlan on/off
+
+Adaptive Virtual Function
+-------------------------
+Adaptive Virtual Function (AVF) allows the virtual function driver, or VF, to
+adapt to changing feature sets of the physical function driver (PF) with which
+it is associated. This allows system administrators to update a PF without
+having to update all the VFs associated with it. All AVFs have a single common
+device ID and branding string.
+
+AVFs have a minimum set of features known as "base mode," but may provide
+additional features depending on what features are available in the PF with
+which the AVF is associated. The following are base mode features:
+
+- 4 Queue Pairs (QP) and associated Configuration Status Registers (CSRs)
+  for Tx/Rx.
+- i40e descriptors and ring format.
+- Descriptor write-back completion.
+- 1 control queue, with i40e descriptors, CSRs and ring format.
+- 5 MSI-X interrupt vectors and corresponding i40e CSRs.
+- 1 Interrupt Throttle Rate (ITR) index.
+- 1 Virtual Station Interface (VSI) per VF.
+- 1 Traffic Class (TC), TC0
+- Receive Side Scaling (RSS) with 64 entry indirection table and key,
+  configured through the PF.
+- 1 unicast MAC address reserved per VF.
+- 16 MAC address filters for each VF.
+- Stateless offloads - non-tunneled checksums.
+- AVF device ID.
+- HW mailbox is used for VF to PF communications (including on Windows).
+
+IEEE 802.1ad (QinQ) Support
+---------------------------
+The IEEE 802.1ad standard, informally known as QinQ, allows for multiple VLAN
+IDs within a single Ethernet frame. VLAN IDs are sometimes referred to as
+"tags," and multiple VLAN IDs are thus referred to as a "tag stack." Tag stacks
+allow L2 tunneling and the ability to segregate traffic within a particular
+VLAN ID, among other uses.
+
+The following are examples of how to configure 802.1ad (QinQ)::
+
+  ip link add link eth0 eth0.24 type vlan proto 802.1ad id 24
+  ip link add link eth0.24 eth0.24.371 type vlan proto 802.1Q id 371
+
+Where "24" and "371" are example VLAN IDs.
+
+NOTES:
+  Receive checksum offloads, cloud filters, and VLAN acceleration are not
+  supported for 802.1ad (QinQ) packets.
+
+Application Device Queues (ADq)
+-------------------------------
+Application Device Queues (ADq) allows you to dedicate one or more queues to a
+specific application. This can reduce latency for the specified application,
+and allow Tx traffic to be rate limited per application. Follow the steps below
+to set ADq.
+
+1. Create traffic classes (TCs). Maximum of 8 TCs can be created per interface.
+The shaper bw_rlimit parameter is optional.
+
+Example: Sets up two tcs, tc0 and tc1, with 16 queues each and max tx rate set
+to 1Gbit for tc0 and 3Gbit for tc1.
+
+::
+
+  # tc qdisc add dev <interface> root mqprio num_tc 2 map 0 0 0 0 1 1 1 1
+  queues 16@0 16@16 hw 1 mode channel shaper bw_rlimit min_rate 1Gbit 2Gbit
+  max_rate 1Gbit 3Gbit
+
+map: priority mapping for up to 16 priorities to tcs (e.g. map 0 0 0 0 1 1 1 1
+sets priorities 0-3 to use tc0 and 4-7 to use tc1)
+
+queues: for each tc, <num queues>@<offset> (e.g. queues 16@0 16@16 assigns
+16 queues to tc0 at offset 0 and 16 queues to tc1 at offset 16. Max total
+number of queues for all tcs is 64 or number of cores, whichever is lower.)
+
+hw 1 mode channel: ‘channel’ with ‘hw’ set to 1 is a new new hardware
+offload mode in mqprio that makes full use of the mqprio options, the
+TCs, the queue configurations, and the QoS parameters.
+
+shaper bw_rlimit: for each tc, sets minimum and maximum bandwidth rates.
+Totals must be equal or less than port speed.
+
+For example: min_rate 1Gbit 3Gbit: Verify bandwidth limit using network
+monitoring tools such as ifstat or sar –n DEV [interval] [number of samples]
+
+2. Enable HW TC offload on interface::
+
+    # ethtool -K <interface> hw-tc-offload on
+
+3. Apply TCs to ingress (RX) flow of interface::
+
+    # tc qdisc add dev <interface> ingress
+
+NOTES:
+ - Run all tc commands from the iproute2 <pathtoiproute2>/tc/ directory.
+ - ADq is not compatible with cloud filters.
+ - Setting up channels via ethtool (ethtool -L) is not supported when the TCs
+   are configured using mqprio.
+ - You must have iproute2 latest version
+ - NVM version 6.01 or later is required.
+ - ADq cannot be enabled when any the following features are enabled: Data
+   Center Bridging (DCB), Multiple Functions per Port (MFP), or Sideband Filters.
+ - If another driver (for example, DPDK) has set cloud filters, you cannot
+   enable ADq.
+ - Tunnel filters are not supported in ADq. If encapsulated packets do arrive
+   in non-tunnel mode, filtering will be done on the inner headers.  For example,
+   for VXLAN traffic in non-tunnel mode, PCTYPE is identified as a VXLAN
+   encapsulated packet, outer headers are ignored. Therefore, inner headers are
+   matched.
+ - If a TC filter on a PF matches traffic over a VF (on the PF), that traffic
+   will be routed to the appropriate queue of the PF, and will not be passed on
+   the VF. Such traffic will end up getting dropped higher up in the TCP/IP
+   stack as it does not match PF address data.
+ - If traffic matches multiple TC filters that point to different TCs, that
+   traffic will be duplicated and sent to all matching TC queues.  The hardware
+   switch mirrors the packet to a VSI list when multiple filters are matched.
+
+
+Known Issues/Troubleshooting
+============================
+
+Traffic Is Not Being Passed Between VM and Client
+-------------------------------------------------
+You may not be able to pass traffic between a client system and a
+Virtual Machine (VM) running on a separate host if the Virtual Function
+(VF, or Virtual NIC) is not in trusted mode and spoof checking is enabled
+on the VF. Note that this situation can occur in any combination of client,
+host, and guest operating system. For information on how to set the VF to
+trusted mode, refer to the section "VLAN Tag Packet Steering" in this
+readme document. For information on setting spoof checking, refer to the
+section "MAC and VLAN anti-spoofing feature" in this readme document.
+
+Do not unload port driver if VF with active VM is bound to it
+-------------------------------------------------------------
+Do not unload a port's driver if a Virtual Function (VF) with an active Virtual
+Machine (VM) is bound to it. Doing so will cause the port to appear to hang.
+Once the VM shuts down, or otherwise releases the VF, the command will complete.
+
+Virtual machine does not get link
+---------------------------------
+If the virtual machine has more than one virtual port assigned to it, and those
+virtual ports are bound to different physical ports, you may not get link on
+all of the virtual ports. The following command may work around the issue::
+
+  ethtool -r <PF>
+
+Where <PF> is the PF interface in the host, for example: p5p1. You may need to
+run the command more than once to get link on all virtual ports.
+
+MAC address of Virtual Function changes unexpectedly
+----------------------------------------------------
+If a Virtual Function's MAC address is not assigned in the host, then the VF
+(virtual function) driver will use a random MAC address. This random MAC
+address may change each time the VF driver is reloaded. You can assign a static
+MAC address in the host machine. This static MAC address will survive
+a VF driver reload.
+
+Driver Buffer Overflow Fix
+--------------------------
+The fix to resolve CVE-2016-8105, referenced in Intel SA-00069
+https://www.intel.com/content/www/us/en/security-center/advisory/intel-sa-00069.html
+is included in this and future versions of the driver.
+
+Multiple Interfaces on Same Ethernet Broadcast Network
+------------------------------------------------------
+Due to the default ARP behavior on Linux, it is not possible to have one system
+on two IP networks in the same Ethernet broadcast domain (non-partitioned
+switch) behave as expected. All Ethernet interfaces will respond to IP traffic
+for any IP address assigned to the system. This results in unbalanced receive
+traffic.
+
+If you have multiple interfaces in a server, either turn on ARP filtering by
+entering::
+
+  echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
+
+NOTE: This setting is not saved across reboots. The configuration change can be
+made permanent by adding the following line to the file /etc/sysctl.conf::
+
+  net.ipv4.conf.all.arp_filter = 1
+
+Another alternative is to install the interfaces in separate broadcast domains
+(either in different switches or in a switch partitioned to VLANs).
+
+Rx Page Allocation Errors
+-------------------------
+'Page allocation failure. order:0' errors may occur under stress.
+This is caused by the way the Linux kernel reports this stressed condition.
+
+
+Support
+=======
+For general information, go to the Intel support website at:
+
+https://support.intel.com
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+https://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on the supported kernel
+with a supported adapter, email the specific information related to the issue
+to e1000-devel@lists.sf.net
diff --git a/Documentation/networking/device_drivers/intel/ice.rst b/Documentation/networking/device_drivers/intel/ice.rst
new file mode 100644
index 000000000000..4d118b827bbb
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/ice.rst
@@ -0,0 +1,45 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux* Base Driver for the Intel(R) Ethernet Connection E800 Series
+===================================================================
+
+Intel ice Linux driver.
+Copyright(c) 2018 Intel Corporation.
+
+Contents
+========
+
+- Enabling the driver
+- Support
+
+The driver in this release supports Intel's E800 Series of products. For
+more information, visit Intel's support page at https://support.intel.com.
+
+Enabling the driver
+===================
+The driver is enabled via the standard kernel configuration system,
+using the make command::
+
+  make oldconfig/menuconfig/etc.
+
+The driver is located in the menu structure at:
+
+  -> Device Drivers
+    -> Network device support (NETDEVICES [=y])
+      -> Ethernet driver support
+        -> Intel devices
+          -> Intel(R) Ethernet Connection E800 Series Support
+
+Support
+=======
+For general information, go to the Intel support website at:
+
+https://www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+https://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on a supported kernel
+with a supported adapter, email the specific information related to the issue
+to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/device_drivers/intel/igb.rst b/Documentation/networking/device_drivers/intel/igb.rst
new file mode 100644
index 000000000000..ba16b86d5593
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/igb.rst
@@ -0,0 +1,193 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux* Base Driver for Intel(R) Ethernet Network Connection
+===========================================================
+
+Intel Gigabit Linux driver.
+Copyright(c) 1999-2018 Intel Corporation.
+
+Contents
+========
+
+- Identifying Your Adapter
+- Command Line Parameters
+- Additional Configurations
+- Support
+
+
+Identifying Your Adapter
+========================
+For information on how to identify your adapter, and for the latest Intel
+network drivers, refer to the Intel Support website:
+http://www.intel.com/support
+
+
+Command Line Parameters
+========================
+If the driver is built as a module, the following optional parameters are used
+by entering them on the command line with the modprobe command using this
+syntax::
+
+    modprobe igb [<option>=<VAL1>,<VAL2>,...]
+
+There needs to be a <VAL#> for each network port in the system supported by
+this driver. The values will be applied to each instance, in function order.
+For example::
+
+    modprobe igb max_vfs=2,4
+
+In this case, there are two network ports supported by igb in the system.
+
+NOTE: A descriptor describes a data buffer and attributes related to the data
+buffer. This information is accessed by the hardware.
+
+max_vfs
+-------
+:Valid Range: 0-7
+
+This parameter adds support for SR-IOV. It causes the driver to spawn up to
+max_vfs worth of virtual functions.  If the value is greater than 0 it will
+also force the VMDq parameter to be 1 or more.
+
+The parameters for the driver are referenced by position. Thus, if you have a
+dual port adapter, or more than one adapter in your system, and want N virtual
+functions per port, you must specify a number for each port with each parameter
+separated by a comma. For example::
+
+    modprobe igb max_vfs=4
+
+This will spawn 4 VFs on the first port.
+
+::
+
+    modprobe igb max_vfs=2,4
+
+This will spawn 2 VFs on the first port and 4 VFs on the second port.
+
+NOTE: Caution must be used in loading the driver with these parameters.
+Depending on your system configuration, number of slots, etc., it is impossible
+to predict in all cases where the positions would be on the command line.
+
+NOTE: Neither the device nor the driver control how VFs are mapped into config
+space. Bus layout will vary by operating system. On operating systems that
+support it, you can check sysfs to find the mapping.
+
+NOTE: When either SR-IOV mode or VMDq mode is enabled, hardware VLAN filtering
+and VLAN tag stripping/insertion will remain enabled. Please remove the old
+VLAN filter before the new VLAN filter is added. For example::
+
+    ip link set eth0 vf 0 vlan 100	// set vlan 100 for VF 0
+    ip link set eth0 vf 0 vlan 0	// Delete vlan 100
+    ip link set eth0 vf 0 vlan 200	// set a new vlan 200 for VF 0
+
+Debug
+-----
+:Valid Range: 0-16 (0=none,...,16=all)
+:Default Value: 0
+
+This parameter adjusts the level debug messages displayed in the system logs.
+
+
+Additional Features and Configurations
+======================================
+
+Jumbo Frames
+------------
+Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU)
+to a value larger than the default value of 1500.
+
+Use the ifconfig command to increase the MTU size. For example, enter the
+following where <x> is the interface number::
+
+    ifconfig eth<x> mtu 9000 up
+
+Alternatively, you can use the ip command as follows::
+
+    ip link set mtu 9000 dev eth<x>
+    ip link set up dev eth<x>
+
+This setting is not saved across reboots. The setting change can be made
+permanent by adding 'MTU=9000' to the file:
+
+- For RHEL: /etc/sysconfig/network-scripts/ifcfg-eth<x>
+- For SLES: /etc/sysconfig/network/<config_file>
+
+NOTE: The maximum MTU setting for Jumbo Frames is 9216. This value coincides
+with the maximum Jumbo Frames size of 9234 bytes.
+
+NOTE: Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
+poor performance or loss of link.
+
+
+ethtool
+-------
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information. The latest ethtool
+version is required for this functionality. Download it at:
+
+https://www.kernel.org/pub/software/network/ethtool/
+
+
+Enabling Wake on LAN* (WoL)
+---------------------------
+WoL is configured through the ethtool* utility.
+
+WoL will be enabled on the system during the next shut down or reboot. For
+this driver version, in order to enable WoL, the igb driver must be loaded
+prior to shutting down or suspending the system.
+
+NOTE: Wake on LAN is only supported on port A of multi-port devices.  Also
+Wake On LAN is not supported for the following device:
+- Intel(R) Gigabit VT Quad Port Server Adapter
+
+
+Multiqueue
+----------
+In this mode, a separate MSI-X vector is allocated for each queue and one for
+"other" interrupts such as link status change and errors. All interrupts are
+throttled via interrupt moderation. Interrupt moderation must be used to avoid
+interrupt storms while the driver is processing one interrupt. The moderation
+value should be at least as large as the expected time for the driver to
+process an interrupt. Multiqueue is off by default.
+
+REQUIREMENTS: MSI-X support is required for Multiqueue. If MSI-X is not found,
+the system will fallback to MSI or to Legacy interrupts. This driver supports
+receive multiqueue on all kernels that support MSI-X.
+
+NOTE: On some kernels a reboot is required to switch between single queue mode
+and multiqueue mode or vice-versa.
+
+
+MAC and VLAN anti-spoofing feature
+----------------------------------
+When a malicious driver attempts to send a spoofed packet, it is dropped by the
+hardware and not transmitted.
+
+An interrupt is sent to the PF driver notifying it of the spoof attempt. When a
+spoofed packet is detected, the PF driver will send the following message to
+the system log (displayed by the "dmesg" command):
+Spoof event(s) detected on VF(n), where n = the VF that attempted to do the
+spoofing
+
+
+Setting MAC Address, VLAN and Rate Limit Using IProute2 Tool
+------------------------------------------------------------
+You can set a MAC address of a Virtual Function (VF), a default VLAN and the
+rate limit using the IProute2 tool. Download the latest version of the
+IProute2 tool from Sourceforge if your version does not have all the features
+you require.
+
+
+Support
+=======
+For general information, go to the Intel support website at:
+
+https://www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+https://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on a supported kernel
+with a supported adapter, email the specific information related to the issue
+to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/device_drivers/intel/igbvf.rst b/Documentation/networking/device_drivers/intel/igbvf.rst
new file mode 100644
index 000000000000..a8a9ffa4f8d3
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/igbvf.rst
@@ -0,0 +1,64 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux* Base Virtual Function Driver for Intel(R) 1G Ethernet
+============================================================
+
+Intel Gigabit Virtual Function Linux driver.
+Copyright(c) 1999-2018 Intel Corporation.
+
+Contents
+========
+- Identifying Your Adapter
+- Additional Configurations
+- Support
+
+This driver supports Intel 82576-based virtual function devices-based virtual
+function devices that can only be activated on kernels that support SR-IOV.
+
+SR-IOV requires the correct platform and OS support.
+
+The guest OS loading this driver must support MSI-X interrupts.
+
+For questions related to hardware requirements, refer to the documentation
+supplied with your Intel adapter. All hardware requirements listed apply to use
+with Linux.
+
+Driver information can be obtained using ethtool, lspci, and ifconfig.
+Instructions on updating ethtool can be found in the section Additional
+Configurations later in this document.
+
+NOTE: There is a limit of a total of 32 shared VLANs to 1 or more VFs.
+
+
+Identifying Your Adapter
+========================
+For information on how to identify your adapter, and for the latest Intel
+network drivers, refer to the Intel Support website:
+http://www.intel.com/support
+
+
+Additional Features and Configurations
+======================================
+
+ethtool
+-------
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information. The latest ethtool
+version is required for this functionality. Download it at:
+
+https://www.kernel.org/pub/software/network/ethtool/
+
+
+Support
+=======
+For general information, go to the Intel support website at:
+
+https://www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+https://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on a supported kernel
+with a supported adapter, email the specific information related to the issue
+to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/device_drivers/intel/ipw2100.txt b/Documentation/networking/device_drivers/intel/ipw2100.txt
new file mode 100644
index 000000000000..6f85e1d06031
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/ipw2100.txt
@@ -0,0 +1,293 @@
+
+Intel(R) PRO/Wireless 2100 Driver for Linux in support of:
+
+Intel(R) PRO/Wireless 2100 Network Connection
+
+Copyright (C) 2003-2006, Intel Corporation
+
+README.ipw2100
+
+Version: git-1.1.5
+Date   : January 25, 2006
+
+Index
+-----------------------------------------------
+0. IMPORTANT INFORMATION BEFORE USING THIS DRIVER
+1. Introduction
+2. Release git-1.1.5 Current Features
+3. Command Line Parameters
+4. Sysfs Helper Files
+5. Radio Kill Switch
+6. Dynamic Firmware
+7. Power Management
+8. Support
+9. License
+
+
+0.   IMPORTANT INFORMATION BEFORE USING THIS DRIVER
+-----------------------------------------------
+
+Important Notice FOR ALL USERS OR DISTRIBUTORS!!!!
+
+Intel wireless LAN adapters are engineered, manufactured, tested, and
+quality checked to ensure that they meet all necessary local and
+governmental regulatory agency requirements for the regions that they
+are designated and/or marked to ship into. Since wireless LANs are
+generally unlicensed devices that share spectrum with radars,
+satellites, and other licensed and unlicensed devices, it is sometimes
+necessary to dynamically detect, avoid, and limit usage to avoid
+interference with these devices. In many instances Intel is required to
+provide test data to prove regional and local compliance to regional and
+governmental regulations before certification or approval to use the
+product is granted. Intel's wireless LAN's EEPROM, firmware, and
+software driver are designed to carefully control parameters that affect
+radio operation and to ensure electromagnetic compliance (EMC). These
+parameters include, without limitation, RF power, spectrum usage,
+channel scanning, and human exposure.
+
+For these reasons Intel cannot permit any manipulation by third parties
+of the software provided in binary format with the wireless WLAN
+adapters (e.g., the EEPROM and firmware). Furthermore, if you use any
+patches, utilities, or code with the Intel wireless LAN adapters that
+have been manipulated by an unauthorized party (i.e., patches,
+utilities, or code (including open source code modifications) which have
+not been validated by Intel), (i) you will be solely responsible for
+ensuring the regulatory compliance of the products, (ii) Intel will bear
+no liability, under any theory of liability for any issues associated
+with the modified products, including without limitation, claims under
+the warranty and/or issues arising from regulatory non-compliance, and
+(iii) Intel will not provide or be required to assist in providing
+support to any third parties for such modified products.
+
+Note: Many regulatory agencies consider Wireless LAN adapters to be
+modules, and accordingly, condition system-level regulatory approval
+upon receipt and review of test data documenting that the antennas and
+system configuration do not cause the EMC and radio operation to be
+non-compliant.
+
+The drivers available for download from SourceForge are provided as a
+part of a development project.  Conformance to local regulatory
+requirements is the responsibility of the individual developer.  As
+such, if you are interested in deploying or shipping a driver as part of
+solution intended to be used for purposes other than development, please
+obtain a tested driver from Intel Customer Support at:
+
+http://www.intel.com/support/wireless/sb/CS-006408.htm
+
+1. Introduction
+-----------------------------------------------
+
+This document provides a brief overview of the features supported by the 
+IPW2100 driver project.  The main project website, where the latest 
+development version of the driver can be found, is:
+
+	http://ipw2100.sourceforge.net
+
+There you can find the not only the latest releases, but also information about
+potential fixes and patches, as well as links to the development mailing list
+for the driver project.
+
+
+2. Release git-1.1.5 Current Supported Features
+-----------------------------------------------
+- Managed (BSS) and Ad-Hoc (IBSS)
+- WEP (shared key and open)
+- Wireless Tools support 
+- 802.1x (tested with XSupplicant 1.0.1)
+
+Enabled (but not supported) features:
+- Monitor/RFMon mode
+- WPA/WPA2
+
+The distinction between officially supported and enabled is a reflection
+on the amount of validation and interoperability testing that has been
+performed on a given feature.
+
+
+3. Command Line Parameters
+-----------------------------------------------
+
+If the driver is built as a module, the following optional parameters are used
+by entering them on the command line with the modprobe command using this
+syntax:
+
+	modprobe ipw2100 [<option>=<VAL1><,VAL2>...]
+
+For example, to disable the radio on driver loading, enter:
+
+	modprobe ipw2100 disable=1
+
+The ipw2100 driver supports the following module parameters:
+
+Name		Value		Example:
+debug		0x0-0xffffffff	debug=1024
+mode		0,1,2		mode=1   /* AdHoc */
+channel		int		channel=3 /* Only valid in AdHoc or Monitor */
+associate	boolean		associate=0 /* Do NOT auto associate */
+disable		boolean		disable=1 /* Do not power the HW */
+
+
+4. Sysfs Helper Files
+---------------------------     
+-----------------------------------------------
+
+There are several ways to control the behavior of the driver.  Many of the 
+general capabilities are exposed through the Wireless Tools (iwconfig).  There
+are a few capabilities that are exposed through entries in the Linux Sysfs.
+
+
+----- Driver Level ------
+For the driver level files, look in /sys/bus/pci/drivers/ipw2100/
+
+  debug_level  
+	
+	This controls the same global as the 'debug' module parameter.  For 
+        information on the various debugging levels available, run the 'dvals'
+	script found in the driver source directory.
+
+	NOTE:  'debug_level' is only enabled if CONFIG_IPW2100_DEBUG is turn
+	       on.
+
+----- Device Level ------
+For the device level files look in
+	
+	/sys/bus/pci/drivers/ipw2100/{PCI-ID}/
+
+For example:
+	/sys/bus/pci/drivers/ipw2100/0000:02:01.0
+
+For the device level files, see /sys/bus/pci/drivers/ipw2100:
+
+  rf_kill
+	read - 
+	0 = RF kill not enabled (radio on)
+	1 = SW based RF kill active (radio off)
+	2 = HW based RF kill active (radio off)
+	3 = Both HW and SW RF kill active (radio off)
+	write -
+	0 = If SW based RF kill active, turn the radio back on
+	1 = If radio is on, activate SW based RF kill
+
+	NOTE: If you enable the SW based RF kill and then toggle the HW
+  	based RF kill from ON -> OFF -> ON, the radio will NOT come back on
+
+
+5. Radio Kill Switch
+-----------------------------------------------
+Most laptops provide the ability for the user to physically disable the radio.
+Some vendors have implemented this as a physical switch that requires no
+software to turn the radio off and on.  On other laptops, however, the switch
+is controlled through a button being pressed and a software driver then making
+calls to turn the radio off and on.  This is referred to as a "software based
+RF kill switch"
+
+See the Sysfs helper file 'rf_kill' for determining the state of the RF switch
+on your system.
+
+
+6. Dynamic Firmware
+-----------------------------------------------
+As the firmware is licensed under a restricted use license, it can not be 
+included within the kernel sources.  To enable the IPW2100 you will need a 
+firmware image to load into the wireless NIC's processors.
+
+You can obtain these images from <http://ipw2100.sf.net/firmware.php>.
+
+See INSTALL for instructions on installing the firmware.
+
+
+7. Power Management
+-----------------------------------------------
+The IPW2100 supports the configuration of the Power Save Protocol 
+through a private wireless extension interface.  The IPW2100 supports 
+the following different modes:
+
+	off	No power management.  Radio is always on.
+	on	Automatic power management
+	1-5	Different levels of power management.  The higher the 
+		number the greater the power savings, but with an impact to 
+		packet latencies. 
+
+Power management works by powering down the radio after a certain 
+interval of time has passed where no packets are passed through the 
+radio.  Once powered down, the radio remains in that state for a given 
+period of time.  For higher power savings, the interval between last 
+packet processed to sleep is shorter and the sleep period is longer.
+
+When the radio is asleep, the access point sending data to the station 
+must buffer packets at the AP until the station wakes up and requests 
+any buffered packets.  If you have an AP that does not correctly support 
+the PSP protocol you may experience packet loss or very poor performance 
+while power management is enabled.  If this is the case, you will need 
+to try and find a firmware update for your AP, or disable power 
+management (via `iwconfig eth1 power off`)
+
+To configure the power level on the IPW2100 you use a combination of 
+iwconfig and iwpriv.  iwconfig is used to turn power management on, off, 
+and set it to auto.
+
+	iwconfig eth1 power off    Disables radio power down
+	iwconfig eth1 power on     Enables radio power management to 
+				   last set level (defaults to AUTO)
+	iwpriv eth1 set_power 0    Sets power level to AUTO and enables 
+				   power management if not previously 
+				   enabled.
+	iwpriv eth1 set_power 1-5  Set the power level as specified, 
+				   enabling power management if not 
+				   previously enabled.
+
+You can view the current power level setting via:
+	
+	iwpriv eth1 get_power
+
+It will return the current period or timeout that is configured as a string
+in the form of xxxx/yyyy (z) where xxxx is the timeout interval (amount of
+time after packet processing), yyyy is the period to sleep (amount of time to 
+wait before powering the radio and querying the access point for buffered
+packets), and z is the 'power level'.  If power management is turned off the
+xxxx/yyyy will be replaced with 'off' -- the level reported will be the active
+level if `iwconfig eth1 power on` is invoked.
+
+
+8. Support
+-----------------------------------------------
+
+For general development information and support,
+go to:
+	
+    http://ipw2100.sf.net/
+
+The ipw2100 1.1.0 driver and firmware can be downloaded from:  
+
+    http://support.intel.com
+
+For installation support on the ipw2100 1.1.0 driver on Linux kernels 
+2.6.8 or greater, email support is available from:  
+
+    http://supportmail.intel.com
+
+9. License
+-----------------------------------------------
+
+  Copyright(c) 2003 - 2006 Intel Corporation. All rights reserved.
+
+  This program is free software; you can redistribute it and/or modify it 
+  under the terms of the GNU General Public License (version 2) as 
+  published by the Free Software Foundation.
+  
+  This program is distributed in the hope that it will be useful, but WITHOUT 
+  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 
+  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for 
+  more details.
+  
+  You should have received a copy of the GNU General Public License along with
+  this program; if not, write to the Free Software Foundation, Inc., 59 
+  Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+  
+  The full GNU General Public License is included in this distribution in the
+  file called LICENSE.
+  
+  License Contact Information:
+  James P. Ketrenos <ipw2100-admin@linux.intel.com>
+  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+
diff --git a/Documentation/networking/device_drivers/intel/ipw2200.txt b/Documentation/networking/device_drivers/intel/ipw2200.txt
new file mode 100644
index 000000000000..b7658bed4906
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/ipw2200.txt
@@ -0,0 +1,472 @@
+
+Intel(R) PRO/Wireless 2915ABG Driver for Linux in support of:
+
+Intel(R) PRO/Wireless 2200BG Network Connection
+Intel(R) PRO/Wireless 2915ABG Network Connection
+
+Note: The Intel(R) PRO/Wireless 2915ABG Driver for Linux and Intel(R)
+PRO/Wireless 2200BG Driver for Linux is a unified driver that works on
+both hardware adapters listed above. In this document the Intel(R)
+PRO/Wireless 2915ABG Driver for Linux will be used to reference the
+unified driver.
+
+Copyright (C) 2004-2006, Intel Corporation
+
+README.ipw2200
+
+Version: 1.1.2
+Date   : March 30, 2006
+
+
+Index
+-----------------------------------------------
+0.   IMPORTANT INFORMATION BEFORE USING THIS DRIVER
+1.   Introduction
+1.1. Overview of features
+1.2. Module parameters
+1.3. Wireless Extension Private Methods
+1.4. Sysfs Helper Files
+1.5. Supported channels
+2.   Ad-Hoc Networking
+3.   Interacting with Wireless Tools
+3.1. iwconfig mode
+3.2. iwconfig sens
+4.   About the Version Numbers
+5.   Firmware installation
+6.   Support
+7.   License
+
+
+0.   IMPORTANT INFORMATION BEFORE USING THIS DRIVER
+-----------------------------------------------
+
+Important Notice FOR ALL USERS OR DISTRIBUTORS!!!! 
+
+Intel wireless LAN adapters are engineered, manufactured, tested, and
+quality checked to ensure that they meet all necessary local and
+governmental regulatory agency requirements for the regions that they
+are designated and/or marked to ship into. Since wireless LANs are
+generally unlicensed devices that share spectrum with radars,
+satellites, and other licensed and unlicensed devices, it is sometimes
+necessary to dynamically detect, avoid, and limit usage to avoid
+interference with these devices. In many instances Intel is required to
+provide test data to prove regional and local compliance to regional and
+governmental regulations before certification or approval to use the
+product is granted. Intel's wireless LAN's EEPROM, firmware, and
+software driver are designed to carefully control parameters that affect
+radio operation and to ensure electromagnetic compliance (EMC). These
+parameters include, without limitation, RF power, spectrum usage,
+channel scanning, and human exposure. 
+
+For these reasons Intel cannot permit any manipulation by third parties
+of the software provided in binary format with the wireless WLAN
+adapters (e.g., the EEPROM and firmware). Furthermore, if you use any
+patches, utilities, or code with the Intel wireless LAN adapters that
+have been manipulated by an unauthorized party (i.e., patches,
+utilities, or code (including open source code modifications) which have
+not been validated by Intel), (i) you will be solely responsible for
+ensuring the regulatory compliance of the products, (ii) Intel will bear
+no liability, under any theory of liability for any issues associated
+with the modified products, including without limitation, claims under
+the warranty and/or issues arising from regulatory non-compliance, and
+(iii) Intel will not provide or be required to assist in providing
+support to any third parties for such modified products.  
+
+Note: Many regulatory agencies consider Wireless LAN adapters to be
+modules, and accordingly, condition system-level regulatory approval
+upon receipt and review of test data documenting that the antennas and
+system configuration do not cause the EMC and radio operation to be
+non-compliant.
+
+The drivers available for download from SourceForge are provided as a 
+part of a development project.  Conformance to local regulatory 
+requirements is the responsibility of the individual developer.  As 
+such, if you are interested in deploying or shipping a driver as part of 
+solution intended to be used for purposes other than development, please 
+obtain a tested driver from Intel Customer Support at:
+
+http://support.intel.com
+
+
+1.   Introduction
+-----------------------------------------------
+The following sections attempt to provide a brief introduction to using 
+the Intel(R) PRO/Wireless 2915ABG Driver for Linux.
+
+This document is not meant to be a comprehensive manual on 
+understanding or using wireless technologies, but should be sufficient 
+to get you moving without wires on Linux.
+
+For information on building and installing the driver, see the INSTALL
+file.
+
+
+1.1. Overview of Features
+-----------------------------------------------
+The current release (1.1.2) supports the following features:
+
++ BSS mode (Infrastructure, Managed)
++ IBSS mode (Ad-Hoc)
++ WEP (OPEN and SHARED KEY mode)
++ 802.1x EAP via wpa_supplicant and xsupplicant
++ Wireless Extension support 
++ Full B and G rate support (2200 and 2915)
++ Full A rate support (2915 only)
++ Transmit power control
++ S state support (ACPI suspend/resume)
+
+The following features are currently enabled, but not officially
+supported:
+
++ WPA
++ long/short preamble support
++ Monitor mode (aka RFMon)
+
+The distinction between officially supported and enabled is a reflection 
+on the amount of validation and interoperability testing that has been
+performed on a given feature. 
+
+
+
+1.2. Command Line Parameters
+-----------------------------------------------
+
+Like many modules used in the Linux kernel, the Intel(R) PRO/Wireless
+2915ABG Driver for Linux allows configuration options to be provided 
+as module parameters.  The most common way to specify a module parameter 
+is via the command line.  
+
+The general form is:
+
+% modprobe ipw2200 parameter=value
+
+Where the supported parameter are:
+
+  associate
+	Set to 0 to disable the auto scan-and-associate functionality of the
+	driver.  If disabled, the driver will not attempt to scan 
+	for and associate to a network until it has been configured with 
+	one or more properties for the target network, for example configuring 
+	the network SSID.  Default is 0 (do not auto-associate)
+	
+	Example: % modprobe ipw2200 associate=0
+
+  auto_create
+	Set to 0 to disable the auto creation of an Ad-Hoc network 
+	matching the channel and network name parameters provided.  
+	Default is 1.
+
+  channel
+	channel number for association.  The normal method for setting
+        the channel would be to use the standard wireless tools
+        (i.e. `iwconfig eth1 channel 10`), but it is useful sometimes
+	to set this while debugging.  Channel 0 means 'ANY'
+
+  debug
+	If using a debug build, this is used to control the amount of debug
+	info is logged.  See the 'dvals' and 'load' script for more info on
+	how to use this (the dvals and load scripts are provided as part 
+	of the ipw2200 development snapshot releases available from the 
+	SourceForge project at http://ipw2200.sf.net)
+  
+  led
+	Can be used to turn on experimental LED code.
+	0 = Off, 1 = On.  Default is 1.
+
+  mode
+	Can be used to set the default mode of the adapter.  
+	0 = Managed, 1 = Ad-Hoc, 2 = Monitor
+
+
+1.3. Wireless Extension Private Methods
+-----------------------------------------------
+
+As an interface designed to handle generic hardware, there are certain 
+capabilities not exposed through the normal Wireless Tool interface.  As 
+such, a provision is provided for a driver to declare custom, or 
+private, methods.  The Intel(R) PRO/Wireless 2915ABG Driver for Linux 
+defines several of these to configure various settings.
+
+The general form of using the private wireless methods is:
+
+	% iwpriv $IFNAME method parameters
+
+Where $IFNAME is the interface name the device is registered with 
+(typically eth1, customized via one of the various network interface
+name managers, such as ifrename)
+
+The supported private methods are:
+
+  get_mode
+	Can be used to report out which IEEE mode the driver is 
+	configured to support.  Example:
+	
+	% iwpriv eth1 get_mode
+	eth1	get_mode:802.11bg (6)
+
+  set_mode
+	Can be used to configure which IEEE mode the driver will 
+	support.  
+
+	Usage:
+	% iwpriv eth1 set_mode {mode}
+	Where {mode} is a number in the range 1-7:
+	1	802.11a (2915 only)
+	2	802.11b
+	3	802.11ab (2915 only)
+	4	802.11g 
+	5	802.11ag (2915 only)
+	6	802.11bg
+	7	802.11abg (2915 only)
+
+  get_preamble
+	Can be used to report configuration of preamble length.
+
+  set_preamble
+	Can be used to set the configuration of preamble length:
+
+	Usage:
+	% iwpriv eth1 set_preamble {mode}
+	Where {mode} is one of:
+	1	Long preamble only
+	0	Auto (long or short based on connection)
+	
+
+1.4. Sysfs Helper Files:
+-----------------------------------------------
+
+The Linux kernel provides a pseudo file system that can be used to 
+access various components of the operating system.  The Intel(R)
+PRO/Wireless 2915ABG Driver for Linux exposes several configuration
+parameters through this mechanism.
+
+An entry in the sysfs can support reading and/or writing.  You can 
+typically query the contents of a sysfs entry through the use of cat, 
+and can set the contents via echo.  For example:
+
+% cat /sys/bus/pci/drivers/ipw2200/debug_level
+
+Will report the current debug level of the driver's logging subsystem 
+(only available if CONFIG_IPW2200_DEBUG was configured when the driver
+was built).
+
+You can set the debug level via:
+
+% echo $VALUE > /sys/bus/pci/drivers/ipw2200/debug_level
+
+Where $VALUE would be a number in the case of this sysfs entry.  The 
+input to sysfs files does not have to be a number.  For example, the 
+firmware loader used by hotplug utilizes sysfs entries for transferring 
+the firmware image from user space into the driver.
+
+The Intel(R) PRO/Wireless 2915ABG Driver for Linux exposes sysfs entries 
+at two levels -- driver level, which apply to all instances of the driver 
+(in the event that there are more than one device installed) and device 
+level, which applies only to the single specific instance.
+
+
+1.4.1 Driver Level Sysfs Helper Files
+-----------------------------------------------
+
+For the driver level files, look in /sys/bus/pci/drivers/ipw2200/
+
+  debug_level  
+	
+	This controls the same global as the 'debug' module parameter
+
+
+
+1.4.2 Device Level Sysfs Helper Files
+-----------------------------------------------
+
+For the device level files, look in
+	
+	/sys/bus/pci/drivers/ipw2200/{PCI-ID}/
+
+For example:
+	/sys/bus/pci/drivers/ipw2200/0000:02:01.0
+
+For the device level files, see /sys/bus/pci/drivers/ipw2200:
+
+  rf_kill
+	read - 
+	0 = RF kill not enabled (radio on)
+	1 = SW based RF kill active (radio off)
+	2 = HW based RF kill active (radio off)
+	3 = Both HW and SW RF kill active (radio off)
+	write -
+	0 = If SW based RF kill active, turn the radio back on
+	1 = If radio is on, activate SW based RF kill
+
+	NOTE: If you enable the SW based RF kill and then toggle the HW
+  	based RF kill from ON -> OFF -> ON, the radio will NOT come back on
+	
+  ucode 
+	read-only access to the ucode version number
+
+  led
+	read -
+	0 = LED code disabled
+	1 = LED code enabled
+	write -
+	0 = Disable LED code
+	1 = Enable LED code
+
+	NOTE: The LED code has been reported to hang some systems when 
+	running ifconfig and is therefore disabled by default.
+
+
+1.5. Supported channels
+-----------------------------------------------
+
+Upon loading the Intel(R) PRO/Wireless 2915ABG Driver for Linux, a
+message stating the detected geography code and the number of 802.11
+channels supported by the card will be displayed in the log.
+
+The geography code corresponds to a regulatory domain as shown in the
+table below.
+
+					  Supported channels
+Code	Geography			802.11bg	802.11a
+
+---	Restricted			11 	 	 0
+ZZF	Custom US/Canada		11	 	 8
+ZZD	Rest of World			13	 	 0
+ZZA	Custom USA & Europe & High	11		13
+ZZB	Custom NA & Europe    		11		13
+ZZC	Custom Japan			11	 	 4
+ZZM	Custom 				11	 	 0
+ZZE	Europe				13		19
+ZZJ	Custom Japan			14	 	 4
+ZZR	Rest of World			14	 	 0
+ZZH	High Band			13	 	 4
+ZZG	Custom Europe			13	 	 4
+ZZK	Europe 				13		24
+ZZL	Europe				11		13
+
+
+2.   Ad-Hoc Networking
+-----------------------------------------------
+
+When using a device in an Ad-Hoc network, it is useful to understand the 
+sequence and requirements for the driver to be able to create, join, or 
+merge networks.
+
+The following attempts to provide enough information so that you can 
+have a consistent experience while using the driver as a member of an 
+Ad-Hoc network.
+
+2.1. Joining an Ad-Hoc Network
+-----------------------------------------------
+
+The easiest way to get onto an Ad-Hoc network is to join one that 
+already exists.
+
+2.2. Creating an Ad-Hoc Network
+-----------------------------------------------
+
+An Ad-Hoc networks is created using the syntax of the Wireless tool.
+
+For Example:
+iwconfig eth1 mode ad-hoc essid testing channel 2
+
+2.3. Merging Ad-Hoc Networks
+-----------------------------------------------
+
+
+3.  Interaction with Wireless Tools
+-----------------------------------------------
+
+3.1 iwconfig mode
+-----------------------------------------------
+
+When configuring the mode of the adapter, all run-time configured parameters
+are reset to the value used when the module was loaded.  This includes
+channels, rates, ESSID, etc.
+
+3.2 iwconfig sens
+-----------------------------------------------
+
+The 'iwconfig ethX sens XX' command will not set the signal sensitivity
+threshold, as described in iwconfig documentation, but rather the number
+of consecutive missed beacons that will trigger handover, i.e. roaming
+to another access point. At the same time, it will set the disassociation
+threshold to 3 times the given value.
+
+
+4.   About the Version Numbers
+-----------------------------------------------
+
+Due to the nature of open source development projects, there are 
+frequently changes being incorporated that have not gone through 
+a complete validation process.  These changes are incorporated into 
+development snapshot releases.
+
+Releases are numbered with a three level scheme: 
+
+	major.minor.development
+
+Any version where the 'development' portion is 0 (for example
+1.0.0, 1.1.0, etc.) indicates a stable version that will be made 
+available for kernel inclusion.
+
+Any version where the 'development' portion is not a 0 (for
+example 1.0.1, 1.1.5, etc.) indicates a development version that is
+being made available for testing and cutting edge users.  The stability 
+and functionality of the development releases are not know.  We make
+efforts to try and keep all snapshots reasonably stable, but due to the
+frequency of their release, and the desire to get those releases 
+available as quickly as possible, unknown anomalies should be expected.
+
+The major version number will be incremented when significant changes
+are made to the driver.  Currently, there are no major changes planned.
+
+5.  Firmware installation
+----------------------------------------------
+
+The driver requires a firmware image, download it and extract the
+files under /lib/firmware (or wherever your hotplug's firmware.agent
+will look for firmware files)
+
+The firmware can be downloaded from the following URL:
+
+    http://ipw2200.sf.net/
+
+
+6.  Support
+-----------------------------------------------
+
+For direct support of the 1.0.0 version, you can contact 
+http://supportmail.intel.com, or you can use the open source project
+support.
+
+For general information and support, go to:
+	
+    http://ipw2200.sf.net/
+
+
+7.  License
+-----------------------------------------------
+
+  Copyright(c) 2003 - 2006 Intel Corporation. All rights reserved.
+
+  This program is free software; you can redistribute it and/or modify it 
+  under the terms of the GNU General Public License version 2 as 
+  published by the Free Software Foundation.
+  
+  This program is distributed in the hope that it will be useful, but WITHOUT 
+  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 
+  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for 
+  more details.
+  
+  You should have received a copy of the GNU General Public License along with
+  this program; if not, write to the Free Software Foundation, Inc., 59 
+  Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+  
+  The full GNU General Public License is included in this distribution in the
+  file called LICENSE.
+  
+  Contact Information:
+  James P. Ketrenos <ipw2100-admin@linux.intel.com>
+  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+
diff --git a/Documentation/networking/device_drivers/intel/ixgb.rst b/Documentation/networking/device_drivers/intel/ixgb.rst
new file mode 100644
index 000000000000..8bd80e27843d
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/ixgb.rst
@@ -0,0 +1,467 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux Base Driver for 10 Gigabit Intel(R) Ethernet Network Connection
+=====================================================================
+
+October 1, 2018
+
+
+Contents
+========
+
+- In This Release
+- Identifying Your Adapter
+- Command Line Parameters
+- Improving Performance
+- Additional Configurations
+- Known Issues/Troubleshooting
+- Support
+
+
+
+In This Release
+===============
+
+This file describes the ixgb Linux Base Driver for the 10 Gigabit Intel(R)
+Network Connection.  This driver includes support for Itanium(R)2-based
+systems.
+
+For questions related to hardware requirements, refer to the documentation
+supplied with your 10 Gigabit adapter.  All hardware requirements listed apply
+to use with Linux.
+
+The following features are available in this kernel:
+ - Native VLANs
+ - Channel Bonding (teaming)
+ - SNMP
+
+Channel Bonding documentation can be found in the Linux kernel source:
+/Documentation/networking/bonding.txt
+
+The driver information previously displayed in the /proc filesystem is not
+supported in this release.  Alternatively, you can use ethtool (version 1.6
+or later), lspci, and iproute2 to obtain the same information.
+
+Instructions on updating ethtool can be found in the section "Additional
+Configurations" later in this document.
+
+
+Identifying Your Adapter
+========================
+
+The following Intel network adapters are compatible with the drivers in this
+release:
+
++------------+------------------------------+----------------------------------+
+| Controller | Adapter Name                 | Physical Layer                   |
++============+==============================+==================================+
+| 82597EX    | Intel(R) PRO/10GbE LR/SR/CX4 | - 10G Base-LR (fiber)            |
+|            | Server Adapters              | - 10G Base-SR (fiber)            |
+|            |                              | - 10G Base-CX4 (copper)          |
++------------+------------------------------+----------------------------------+
+
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+
+    https://support.intel.com
+
+
+Command Line Parameters
+=======================
+
+If the driver is built as a module, the  following optional parameters are
+used by entering them on the command line with the modprobe command using
+this syntax::
+
+    modprobe ixgb [<option>=<VAL1>,<VAL2>,...]
+
+For example, with two 10GbE PCI adapters, entering::
+
+    modprobe ixgb TxDescriptors=80,128
+
+loads the ixgb driver with 80 TX resources for the first adapter and 128 TX
+resources for the second adapter.
+
+The default value for each parameter is generally the recommended setting,
+unless otherwise noted.
+
+Copybreak
+---------
+:Valid Range: 0-XXXX
+:Default Value: 256
+
+    This is the maximum size of packet that is copied to a new buffer on
+    receive.
+
+Debug
+-----
+:Valid Range: 0-16 (0=none,...,16=all)
+:Default Value: 0
+
+    This parameter adjusts the level of debug messages displayed in the
+    system logs.
+
+FlowControl
+-----------
+:Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
+:Default Value: 1 if no EEPROM, otherwise read from EEPROM
+
+    This parameter controls the automatic generation(Tx) and response(Rx) to
+    Ethernet PAUSE frames.  There are hardware bugs associated with enabling
+    Tx flow control so beware.
+
+RxDescriptors
+-------------
+:Valid Range: 64-4096
+:Default Value: 1024
+
+    This value is the number of receive descriptors allocated by the driver.
+    Increasing this value allows the driver to buffer more incoming packets.
+    Each descriptor is 16 bytes.  A receive buffer is also allocated for
+    each descriptor and can be either 2048, 4056, 8192, or 16384 bytes,
+    depending on the MTU setting.  When the MTU size is 1500 or less, the
+    receive buffer size is 2048 bytes. When the MTU is greater than 1500 the
+    receive buffer size will be either 4056, 8192, or 16384 bytes.  The
+    maximum MTU size is 16114.
+
+TxDescriptors
+-------------
+:Valid Range: 64-4096
+:Default Value: 256
+
+    This value is the number of transmit descriptors allocated by the driver.
+    Increasing this value allows the driver to queue more transmits.  Each
+    descriptor is 16 bytes.
+
+RxIntDelay
+----------
+:Valid Range: 0-65535 (0=off)
+:Default Value: 72
+
+    This value delays the generation of receive interrupts in units of
+    0.8192 microseconds.  Receive interrupt reduction can improve CPU
+    efficiency if properly tuned for specific network traffic.  Increasing
+    this value adds extra latency to frame reception and can end up
+    decreasing the throughput of TCP traffic.  If the system is reporting
+    dropped receives, this value may be set too high, causing the driver to
+    run out of available receive descriptors.
+
+TxIntDelay
+----------
+:Valid Range: 0-65535 (0=off)
+:Default Value: 32
+
+    This value delays the generation of transmit interrupts in units of
+    0.8192 microseconds.  Transmit interrupt reduction can improve CPU
+    efficiency if properly tuned for specific network traffic.  Increasing
+    this value adds extra latency to frame transmission and can end up
+    decreasing the throughput of TCP traffic.  If this value is set too high,
+    it will cause the driver to run out of available transmit descriptors.
+
+XsumRX
+------
+:Valid Range: 0-1
+:Default Value: 1
+
+    A value of '1' indicates that the driver should enable IP checksum
+    offload for received packets (both UDP and TCP) to the adapter hardware.
+
+RxFCHighThresh
+--------------
+:Valid Range: 1,536-262,136 (0x600 - 0x3FFF8, 8 byte granularity)
+:Default Value: 196,608 (0x30000)
+
+    Receive Flow control high threshold (when we send a pause frame)
+
+RxFCLowThresh
+-------------
+:Valid Range: 64-262,136 (0x40 - 0x3FFF8, 8 byte granularity)
+:Default Value: 163,840 (0x28000)
+
+    Receive Flow control low threshold (when we send a resume frame)
+
+FCReqTimeout
+------------
+:Valid Range: 1-65535
+:Default Value: 65535
+
+    Flow control request timeout (how long to pause the link partner's tx)
+
+IntDelayEnable
+--------------
+:Value Range: 0,1
+:Default Value: 1
+
+    Interrupt Delay, 0 disables transmit interrupt delay and 1 enables it.
+
+
+Improving Performance
+=====================
+
+With the 10 Gigabit server adapters, the default Linux configuration will
+very likely limit the total available throughput artificially.  There is a set
+of configuration changes that, when applied together, will increase the ability
+of Linux to transmit and receive data.  The following enhancements were
+originally acquired from settings published at http://www.spec.org/web99/ for
+various submitted results using Linux.
+
+NOTE:
+  These changes are only suggestions, and serve as a starting point for
+  tuning your network performance.
+
+The changes are made in three major ways, listed in order of greatest effect:
+
+- Use ip link to modify the mtu (maximum transmission unit) and the txqueuelen
+  parameter.
+- Use sysctl to modify /proc parameters (essentially kernel tuning)
+- Use setpci to modify the MMRBC field in PCI-X configuration space to increase
+  transmit burst lengths on the bus.
+
+NOTE:
+  setpci modifies the adapter's configuration registers to allow it to read
+  up to 4k bytes at a time (for transmits).  However, for some systems the
+  behavior after modifying this register may be undefined (possibly errors of
+  some kind).  A power-cycle, hard reset or explicitly setting the e6 register
+  back to 22 (setpci -d 8086:1a48 e6.b=22) may be required to get back to a
+  stable configuration.
+
+- COPY these lines and paste them into ixgb_perf.sh:
+
+::
+
+  #!/bin/bash
+  echo "configuring network performance , edit this file to change the interface
+  or device ID of 10GbE card"
+  # set mmrbc to 4k reads, modify only Intel 10GbE device IDs
+  # replace 1a48 with appropriate 10GbE device's ID installed on the system,
+  # if needed.
+  setpci -d 8086:1a48 e6.b=2e
+  # set the MTU (max transmission unit) - it requires your switch and clients
+  # to change as well.
+  # set the txqueuelen
+  # your ixgb adapter should be loaded as eth1 for this to work, change if needed
+  ip li set dev eth1 mtu 9000 txqueuelen 1000 up
+  # call the sysctl utility to modify /proc/sys entries
+  sysctl -p ./sysctl_ixgb.conf
+
+- COPY these lines and paste them into sysctl_ixgb.conf:
+
+::
+
+  # some of the defaults may be different for your kernel
+  # call this file with sysctl -p <this file>
+  # these are just suggested values that worked well to increase throughput in
+  # several network benchmark tests, your mileage may vary
+
+  ### IPV4 specific settings
+  # turn TCP timestamp support off, default 1, reduces CPU use
+  net.ipv4.tcp_timestamps = 0
+  # turn SACK support off, default on
+  # on systems with a VERY fast bus -> memory interface this is the big gainer
+  net.ipv4.tcp_sack = 0
+  # set min/default/max TCP read buffer, default 4096 87380 174760
+  net.ipv4.tcp_rmem = 10000000 10000000 10000000
+  # set min/pressure/max TCP write buffer, default 4096 16384 131072
+  net.ipv4.tcp_wmem = 10000000 10000000 10000000
+  # set min/pressure/max TCP buffer space, default 31744 32256 32768
+  net.ipv4.tcp_mem = 10000000 10000000 10000000
+
+  ### CORE settings (mostly for socket and UDP effect)
+  # set maximum receive socket buffer size, default 131071
+  net.core.rmem_max = 524287
+  # set maximum send socket buffer size, default 131071
+  net.core.wmem_max = 524287
+  # set default receive socket buffer size, default 65535
+  net.core.rmem_default = 524287
+  # set default send socket buffer size, default 65535
+  net.core.wmem_default = 524287
+  # set maximum amount of option memory buffers, default 10240
+  net.core.optmem_max = 524287
+  # set number of unprocessed input packets before kernel starts dropping them; default 300
+  net.core.netdev_max_backlog = 300000
+
+Edit the ixgb_perf.sh script if necessary to change eth1 to whatever interface
+your ixgb driver is using and/or replace '1a48' with appropriate 10GbE device's
+ID installed on the system.
+
+NOTE:
+  Unless these scripts are added to the boot process, these changes will
+  only last only until the next system reboot.
+
+
+Resolving Slow UDP Traffic
+--------------------------
+If your server does not seem to be able to receive UDP traffic as fast as it
+can receive TCP traffic, it could be because Linux, by default, does not set
+the network stack buffers as large as they need to be to support high UDP
+transfer rates.  One way to alleviate this problem is to allow more memory to
+be used by the IP stack to store incoming data.
+
+For instance, use the commands::
+
+    sysctl -w net.core.rmem_max=262143
+
+and::
+
+    sysctl -w net.core.rmem_default=262143
+
+to increase the read buffer memory max and default to 262143 (256k - 1) from
+defaults of max=131071 (128k - 1) and default=65535 (64k - 1).  These variables
+will increase the amount of memory used by the network stack for receives, and
+can be increased significantly more if necessary for your application.
+
+
+Additional Configurations
+=========================
+
+Configuring the Driver on Different Distributions
+-------------------------------------------------
+Configuring a network driver to load properly when the system is started is
+distribution dependent. Typically, the configuration process involves adding
+an alias line to /etc/modprobe.conf as well as editing other system startup
+scripts and/or configuration files.  Many popular Linux distributions ship
+with tools to make these changes for you.  To learn the proper way to
+configure a network device for your system, refer to your distribution
+documentation.  If during this process you are asked for the driver or module
+name, the name for the Linux Base Driver for the Intel 10GbE Family of
+Adapters is ixgb.
+
+Viewing Link Messages
+---------------------
+Link messages will not be displayed to the console if the distribution is
+restricting system messages. In order to see network driver link messages on
+your console, set dmesg to eight by entering the following::
+
+    dmesg -n 8
+
+NOTE: This setting is not saved across reboots.
+
+Jumbo Frames
+------------
+The driver supports Jumbo Frames for all adapters. Jumbo Frames support is
+enabled by changing the MTU to a value larger than the default of 1500.
+The maximum value for the MTU is 16114.  Use the ip command to
+increase the MTU size.  For example::
+
+    ip li set dev ethx mtu 9000
+
+The maximum MTU setting for Jumbo Frames is 16114.  This value coincides
+with the maximum Jumbo Frames size of 16128.
+
+Ethtool
+-------
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information.  The ethtool
+version 1.6 or later is required for this functionality.
+
+The latest release of ethtool can be found from
+https://www.kernel.org/pub/software/network/ethtool/
+
+NOTE:
+  The ethtool version 1.6 only supports a limited set of ethtool options.
+  Support for a more complete ethtool feature set can be enabled by
+  upgrading to the latest version.
+
+NAPI
+----
+NAPI (Rx polling mode) is supported in the ixgb driver.
+
+See https://wiki.linuxfoundation.org/networking/napi for more information on
+NAPI.
+
+
+Known Issues/Troubleshooting
+============================
+
+NOTE:
+  After installing the driver, if your Intel Network Connection is not
+  working, verify in the "In This Release" section of the readme that you have
+  installed the correct driver.
+
+Cable Interoperability Issue with Fujitsu XENPAK Module in SmartBits Chassis
+----------------------------------------------------------------------------
+Excessive CRC errors may be observed if the Intel(R) PRO/10GbE CX4
+Server adapter is connected to a Fujitsu XENPAK CX4 module in a SmartBits
+chassis using 15 m/24AWG cable assemblies manufactured by Fujitsu or Leoni.
+The CRC errors may be received either by the Intel(R) PRO/10GbE CX4
+Server adapter or the SmartBits. If this situation occurs using a different
+cable assembly may resolve the issue.
+
+Cable Interoperability Issues with HP Procurve 3400cl Switch Port
+-----------------------------------------------------------------
+Excessive CRC errors may be observed if the Intel(R) PRO/10GbE CX4 Server
+adapter is connected to an HP Procurve 3400cl switch port using short cables
+(1 m or shorter). If this situation occurs, using a longer cable may resolve
+the issue.
+
+Excessive CRC errors may be observed using Fujitsu 24AWG cable assemblies that
+Are 10 m or longer or where using a Leoni 15 m/24AWG cable assembly. The CRC
+errors may be received either by the CX4 Server adapter or at the switch. If
+this situation occurs, using a different cable assembly may resolve the issue.
+
+Jumbo Frames System Requirement
+-------------------------------
+Memory allocation failures have been observed on Linux systems with 64 MB
+of RAM or less that are running Jumbo Frames.  If you are using Jumbo
+Frames, your system may require more than the advertised minimum
+requirement of 64 MB of system memory.
+
+Performance Degradation with Jumbo Frames
+-----------------------------------------
+Degradation in throughput performance may be observed in some Jumbo frames
+environments.  If this is observed, increasing the application's socket buffer
+size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
+See the specific application manual and /usr/src/linux*/Documentation/
+networking/ip-sysctl.txt for more details.
+
+Allocating Rx Buffers when Using Jumbo Frames
+---------------------------------------------
+Allocating Rx buffers when using Jumbo Frames on 2.6.x kernels may fail if
+the available memory is heavily fragmented. This issue may be seen with PCI-X
+adapters or with packet split disabled. This can be reduced or eliminated
+by changing the amount of available memory for receive buffer allocation, by
+increasing /proc/sys/vm/min_free_kbytes.
+
+Multiple Interfaces on Same Ethernet Broadcast Network
+------------------------------------------------------
+Due to the default ARP behavior on Linux, it is not possible to have
+one system on two IP networks in the same Ethernet broadcast domain
+(non-partitioned switch) behave as expected.  All Ethernet interfaces
+will respond to IP traffic for any IP address assigned to the system.
+This results in unbalanced receive traffic.
+
+If you have multiple interfaces in a server, do either of the following:
+
+  - Turn on ARP filtering by entering::
+
+      echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
+
+  - Install the interfaces in separate broadcast domains - either in
+    different switches or in a switch partitioned to VLANs.
+
+UDP Stress Test Dropped Packet Issue
+--------------------------------------
+Under small packets UDP stress test with 10GbE driver, the Linux system
+may drop UDP packets due to the fullness of socket buffers. You may want
+to change the driver's Flow Control variables to the minimum value for
+controlling packet reception.
+
+Tx Hangs Possible Under Stress
+------------------------------
+Under stress conditions, if TX hangs occur, turning off TSO
+"ethtool -K eth0 tso off" may resolve the problem.
+
+
+Support
+=======
+For general information, go to the Intel support website at:
+
+https://www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+https://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on a supported kernel
+with a supported adapter, email the specific information related to the issue
+to e1000-devel@lists.sf.net
diff --git a/Documentation/networking/device_drivers/intel/ixgbe.rst b/Documentation/networking/device_drivers/intel/ixgbe.rst
new file mode 100644
index 000000000000..86d887a63606
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/ixgbe.rst
@@ -0,0 +1,540 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux* Base Driver for the Intel(R) Ethernet 10 Gigabit PCI Express Adapters
+=============================================================================
+
+Intel 10 Gigabit Linux driver.
+Copyright(c) 1999-2018 Intel Corporation.
+
+Contents
+========
+
+- Identifying Your Adapter
+- Command Line Parameters
+- Additional Configurations
+- Known Issues
+- Support
+
+Identifying Your Adapter
+========================
+The driver is compatible with devices based on the following:
+
+ * Intel(R) Ethernet Controller 82598
+ * Intel(R) Ethernet Controller 82599
+ * Intel(R) Ethernet Controller X520
+ * Intel(R) Ethernet Controller X540
+ * Intel(R) Ethernet Controller x550
+ * Intel(R) Ethernet Controller X552
+ * Intel(R) Ethernet Controller X553
+
+For information on how to identify your adapter, and for the latest Intel
+network drivers, refer to the Intel Support website:
+https://www.intel.com/support
+
+SFP+ Devices with Pluggable Optics
+----------------------------------
+
+82599-BASED ADAPTERS
+~~~~~~~~~~~~~~~~~~~~
+NOTES:
+- If your 82599-based Intel(R) Network Adapter came with Intel optics or is an
+Intel(R) Ethernet Server Adapter X520-2, then it only supports Intel optics
+and/or the direct attach cables listed below.
+- When 82599-based SFP+ devices are connected back to back, they should be set
+to the same Speed setting via ethtool. Results may vary if you mix speed
+settings.
+
++---------------+---------------------------------------+------------------+
+| Supplier      | Type                                  | Part Numbers     |
++===============+=======================================+==================+
+| SR Modules                                                               |
++---------------+---------------------------------------+------------------+
+| Intel         | DUAL RATE 1G/10G SFP+ SR (bailed)     | FTLX8571D3BCV-IT |
++---------------+---------------------------------------+------------------+
+| Intel         | DUAL RATE 1G/10G SFP+ SR (bailed)     | AFBR-703SDZ-IN2  |
++---------------+---------------------------------------+------------------+
+| Intel         | DUAL RATE 1G/10G SFP+ SR (bailed)     | AFBR-703SDDZ-IN1 |
++---------------+---------------------------------------+------------------+
+| LR Modules                                                               |
++---------------+---------------------------------------+------------------+
+| Intel         | DUAL RATE 1G/10G SFP+ LR (bailed)     | FTLX1471D3BCV-IT |
++---------------+---------------------------------------+------------------+
+| Intel         | DUAL RATE 1G/10G SFP+ LR (bailed)     | AFCT-701SDZ-IN2  |
++---------------+---------------------------------------+------------------+
+| Intel         | DUAL RATE 1G/10G SFP+ LR (bailed)     | AFCT-701SDDZ-IN1 |
++---------------+---------------------------------------+------------------+
+
+The following is a list of 3rd party SFP+ modules that have received some
+testing. Not all modules are applicable to all devices.
+
++---------------+---------------------------------------+------------------+
+| Supplier      | Type                                  | Part Numbers     |
++===============+=======================================+==================+
+| Finisar       | SFP+ SR bailed, 10g single rate       | FTLX8571D3BCL    |
++---------------+---------------------------------------+------------------+
+| Avago         | SFP+ SR bailed, 10g single rate       | AFBR-700SDZ      |
++---------------+---------------------------------------+------------------+
+| Finisar       | SFP+ LR bailed, 10g single rate       | FTLX1471D3BCL    |
++---------------+---------------------------------------+------------------+
+| Finisar       | DUAL RATE 1G/10G SFP+ SR (No Bail)    | FTLX8571D3QCV-IT |
++---------------+---------------------------------------+------------------+
+| Avago         | DUAL RATE 1G/10G SFP+ SR (No Bail)    | AFBR-703SDZ-IN1  |
++---------------+---------------------------------------+------------------+
+| Finisar       | DUAL RATE 1G/10G SFP+ LR (No Bail)    | FTLX1471D3QCV-IT |
++---------------+---------------------------------------+------------------+
+| Avago         | DUAL RATE 1G/10G SFP+ LR (No Bail)    | AFCT-701SDZ-IN1  |
++---------------+---------------------------------------+------------------+
+| Finisar       | 1000BASE-T SFP                        | FCLF8522P2BTL    |
++---------------+---------------------------------------+------------------+
+| Avago         | 1000BASE-T                            | ABCU-5710RZ      |
++---------------+---------------------------------------+------------------+
+| HP            | 1000BASE-SX SFP                       | 453153-001       |
++---------------+---------------------------------------+------------------+
+
+82599-based adapters support all passive and active limiting direct attach
+cables that comply with SFF-8431 v4.1 and SFF-8472 v10.4 specifications.
+
+Laser turns off for SFP+ when ifconfig ethX down
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+"ifconfig ethX down" turns off the laser for 82599-based SFP+ fiber adapters.
+"ifconfig ethX up" turns on the laser.
+Alternatively, you can use "ip link set [down/up] dev ethX" to turn the
+laser off and on.
+
+
+82599-based QSFP+ Adapters
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+NOTES:
+- If your 82599-based Intel(R) Network Adapter came with Intel optics, it only
+supports Intel optics.
+- 82599-based QSFP+ adapters only support 4x10 Gbps connections.  1x40 Gbps
+connections are not supported. QSFP+ link partners must be configured for
+4x10 Gbps.
+- 82599-based QSFP+ adapters do not support automatic link speed detection.
+The link speed must be configured to either 10 Gbps or 1 Gbps to match the link
+partners speed capabilities. Incorrect speed configurations will result in
+failure to link.
+- Intel(R) Ethernet Converged Network Adapter X520-Q1 only supports the optics
+and direct attach cables listed below.
+
++---------------+---------------------------------------+------------------+
+| Supplier      | Type                                  | Part Numbers     |
++===============+=======================================+==================+
+| Intel         | DUAL RATE 1G/10G QSFP+ SRL (bailed)   | E10GQSFPSR       |
++---------------+---------------------------------------+------------------+
+
+82599-based QSFP+ adapters support all passive and active limiting QSFP+
+direct attach cables that comply with SFF-8436 v4.1 specifications.
+
+82598-BASED ADAPTERS
+~~~~~~~~~~~~~~~~~~~~
+NOTES:
+- Intel(r) Ethernet Network Adapters that support removable optical modules
+only support their original module type (for example, the Intel(R) 10 Gigabit
+SR Dual Port Express Module only supports SR optical modules). If you plug in
+a different type of module, the driver will not load.
+- Hot Swapping/hot plugging optical modules is not supported.
+- Only single speed, 10 gigabit modules are supported.
+- LAN on Motherboard (LOMs) may support DA, SR, or LR modules. Other module
+types are not supported. Please see your system documentation for details.
+
+The following is a list of SFP+ modules and direct attach cables that have
+received some testing. Not all modules are applicable to all devices.
+
++---------------+---------------------------------------+------------------+
+| Supplier      | Type                                  | Part Numbers     |
++===============+=======================================+==================+
+| Finisar       | SFP+ SR bailed, 10g single rate       | FTLX8571D3BCL    |
++---------------+---------------------------------------+------------------+
+| Avago         | SFP+ SR bailed, 10g single rate       | AFBR-700SDZ      |
++---------------+---------------------------------------+------------------+
+| Finisar       | SFP+ LR bailed, 10g single rate       | FTLX1471D3BCL    |
++---------------+---------------------------------------+------------------+
+
+82598-based adapters support all passive direct attach cables that comply with
+SFF-8431 v4.1 and SFF-8472 v10.4 specifications. Active direct attach cables
+are not supported.
+
+Third party optic modules and cables referred to above are listed only for the
+purpose of highlighting third party specifications and potential
+compatibility, and are not recommendations or endorsements or sponsorship of
+any third party's product by Intel. Intel is not endorsing or promoting
+products made by any third party and the third party reference is provided
+only to share information regarding certain optic modules and cables with the
+above specifications. There may be other manufacturers or suppliers, producing
+or supplying optic modules and cables with similar or matching descriptions.
+Customers must use their own discretion and diligence to purchase optic
+modules and cables from any third party of their choice. Customers are solely
+responsible for assessing the suitability of the product and/or devices and
+for the selection of the vendor for purchasing any product. THE OPTIC MODULES
+AND CABLES REFERRED TO ABOVE ARE NOT WARRANTED OR SUPPORTED BY INTEL. INTEL
+ASSUMES NO LIABILITY WHATSOEVER, AND INTEL DISCLAIMS ANY EXPRESS OR IMPLIED
+WARRANTY, RELATING TO SALE AND/OR USE OF SUCH THIRD PARTY PRODUCTS OR
+SELECTION OF VENDOR BY CUSTOMERS.
+
+Command Line Parameters
+=======================
+
+max_vfs
+-------
+:Valid Range: 1-63
+
+This parameter adds support for SR-IOV. It causes the driver to spawn up to
+max_vfs worth of virtual functions.
+If the value is greater than 0 it will also force the VMDq parameter to be 1 or
+more.
+
+NOTE: This parameter is only used on kernel 3.7.x and below. On kernel 3.8.x
+and above, use sysfs to enable VFs. Also, for Red Hat distributions, this
+parameter is only used on version 6.6 and older. For version 6.7 and newer, use
+sysfs. For example::
+
+  #echo $num_vf_enabled > /sys/class/net/$dev/device/sriov_numvfs // enable VFs
+  #echo 0 > /sys/class/net/$dev/device/sriov_numvfs               //disable VFs
+
+The parameters for the driver are referenced by position. Thus, if you have a
+dual port adapter, or more than one adapter in your system, and want N virtual
+functions per port, you must specify a number for each port with each parameter
+separated by a comma. For example::
+
+  modprobe ixgbe max_vfs=4
+
+This will spawn 4 VFs on the first port.
+
+::
+
+  modprobe ixgbe max_vfs=2,4
+
+This will spawn 2 VFs on the first port and 4 VFs on the second port.
+
+NOTE: Caution must be used in loading the driver with these parameters.
+Depending on your system configuration, number of slots, etc., it is impossible
+to predict in all cases where the positions would be on the command line.
+
+NOTE: Neither the device nor the driver control how VFs are mapped into config
+space. Bus layout will vary by operating system. On operating systems that
+support it, you can check sysfs to find the mapping.
+
+NOTE: When either SR-IOV mode or VMDq mode is enabled, hardware VLAN filtering
+and VLAN tag stripping/insertion will remain enabled. Please remove the old
+VLAN filter before the new VLAN filter is added. For example,
+
+::
+
+  ip link set eth0 vf 0 vlan 100 // set VLAN 100 for VF 0
+  ip link set eth0 vf 0 vlan 0   // Delete VLAN 100
+  ip link set eth0 vf 0 vlan 200 // set a new VLAN 200 for VF 0
+
+With kernel 3.6, the driver supports the simultaneous usage of max_vfs and DCB
+features, subject to the constraints described below. Prior to kernel 3.6, the
+driver did not support the simultaneous operation of max_vfs greater than 0 and
+the DCB features (multiple traffic classes utilizing Priority Flow Control and
+Extended Transmission Selection).
+
+When DCB is enabled, network traffic is transmitted and received through
+multiple traffic classes (packet buffers in the NIC). The traffic is associated
+with a specific class based on priority, which has a value of 0 through 7 used
+in the VLAN tag. When SR-IOV is not enabled, each traffic class is associated
+with a set of receive/transmit descriptor queue pairs. The number of queue
+pairs for a given traffic class depends on the hardware configuration. When
+SR-IOV is enabled, the descriptor queue pairs are grouped into pools. The
+Physical Function (PF) and each Virtual Function (VF) is allocated a pool of
+receive/transmit descriptor queue pairs. When multiple traffic classes are
+configured (for example, DCB is enabled), each pool contains a queue pair from
+each traffic class. When a single traffic class is configured in the hardware,
+the pools contain multiple queue pairs from the single traffic class.
+
+The number of VFs that can be allocated depends on the number of traffic
+classes that can be enabled. The configurable number of traffic classes for
+each enabled VF is as follows:
+0 - 15 VFs = Up to 8 traffic classes, depending on device support
+16 - 31 VFs = Up to 4 traffic classes
+32 - 63 VFs = 1 traffic class
+
+When VFs are configured, the PF is allocated one pool as well. The PF supports
+the DCB features with the constraint that each traffic class will only use a
+single queue pair. When zero VFs are configured, the PF can support multiple
+queue pairs per traffic class.
+
+allow_unsupported_sfp
+---------------------
+:Valid Range: 0,1
+:Default Value: 0 (disabled)
+
+This parameter allows unsupported and untested SFP+ modules on 82599-based
+adapters, as long as the type of module is known to the driver.
+
+debug
+-----
+:Valid Range: 0-16 (0=none,...,16=all)
+:Default Value: 0
+
+This parameter adjusts the level of debug messages displayed in the system
+logs.
+
+
+Additional Features and Configurations
+======================================
+
+Flow Control
+------------
+Ethernet Flow Control (IEEE 802.3x) can be configured with ethtool to enable
+receiving and transmitting pause frames for ixgbe. When transmit is enabled,
+pause frames are generated when the receive packet buffer crosses a predefined
+threshold. When receive is enabled, the transmit unit will halt for the time
+delay specified when a pause frame is received.
+
+NOTE: You must have a flow control capable link partner.
+
+Flow Control is enabled by default.
+
+Use ethtool to change the flow control settings. To enable or disable Rx or
+Tx Flow Control::
+
+  ethtool -A eth? rx <on|off> tx <on|off>
+
+Note: This command only enables or disables Flow Control if auto-negotiation is
+disabled. If auto-negotiation is enabled, this command changes the parameters
+used for auto-negotiation with the link partner.
+
+To enable or disable auto-negotiation::
+
+  ethtool -s eth? autoneg <on|off>
+
+Note: Flow Control auto-negotiation is part of link auto-negotiation. Depending
+on your device, you may not be able to change the auto-negotiation setting.
+
+NOTE: For 82598 backplane cards entering 1 gigabit mode, flow control default
+behavior is changed to off. Flow control in 1 gigabit mode on these devices can
+lead to transmit hangs.
+
+Intel(R) Ethernet Flow Director
+-------------------------------
+The Intel Ethernet Flow Director performs the following tasks:
+
+- Directs receive packets according to their flows to different queues.
+- Enables tight control on routing a flow in the platform.
+- Matches flows and CPU cores for flow affinity.
+- Supports multiple parameters for flexible flow classification and load
+  balancing (in SFP mode only).
+
+NOTE: Intel Ethernet Flow Director masking works in the opposite manner from
+subnet masking. In the following command::
+
+  #ethtool -N eth11 flow-type ip4 src-ip 172.4.1.2 m 255.0.0.0 dst-ip \
+  172.21.1.1 m 255.128.0.0 action 31
+
+The src-ip value that is written to the filter will be 0.4.1.2, not 172.0.0.0
+as might be expected. Similarly, the dst-ip value written to the filter will be
+0.21.1.1, not 172.0.0.0.
+
+To enable or disable the Intel Ethernet Flow Director::
+
+  # ethtool -K ethX ntuple <on|off>
+
+When disabling ntuple filters, all the user programmed filters are flushed from
+the driver cache and hardware. All needed filters must be re-added when ntuple
+is re-enabled.
+
+To add a filter that directs packet to queue 2, use -U or -N switch::
+
+  # ethtool -N ethX flow-type tcp4 src-ip 192.168.10.1 dst-ip \
+  192.168.10.2 src-port 2000 dst-port 2001 action 2 [loc 1]
+
+To see the list of filters currently present::
+
+  # ethtool <-u|-n> ethX
+
+Sideband Perfect Filters
+------------------------
+Sideband Perfect Filters are used to direct traffic that matches specified
+characteristics. They are enabled through ethtool's ntuple interface. To add a
+new filter use the following command::
+
+  ethtool -U <device> flow-type <type> src-ip <ip> dst-ip <ip> src-port <port> \
+  dst-port <port> action <queue>
+
+Where:
+  <device> - the ethernet device to program
+  <type> - can be ip4, tcp4, udp4, or sctp4
+  <ip> - the IP address to match on
+  <port> - the port number to match on
+  <queue> - the queue to direct traffic towards (-1 discards the matched traffic)
+
+Use the following command to delete a filter::
+
+  ethtool -U <device> delete <N>
+
+Where <N> is the filter id displayed when printing all the active filters, and
+may also have been specified using "loc <N>" when adding the filter.
+
+The following example matches TCP traffic sent from 192.168.0.1, port 5300,
+directed to 192.168.0.5, port 80, and sends it to queue 7::
+
+  ethtool -U enp130s0 flow-type tcp4 src-ip 192.168.0.1 dst-ip 192.168.0.5 \
+  src-port 5300 dst-port 80 action 7
+
+For each flow-type, the programmed filters must all have the same matching
+input set. For example, issuing the following two commands is acceptable::
+
+  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.1 src-port 5300 action 7
+  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.5 src-port 55 action 10
+
+Issuing the next two commands, however, is not acceptable, since the first
+specifies src-ip and the second specifies dst-ip::
+
+  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.1 src-port 5300 action 7
+  ethtool -U enp130s0 flow-type ip4 dst-ip 192.168.0.5 src-port 55 action 10
+
+The second command will fail with an error. You may program multiple filters
+with the same fields, using different values, but, on one device, you may not
+program two TCP4 filters with different matching fields.
+
+Matching on a sub-portion of a field is not supported by the ixgbe driver, thus
+partial mask fields are not supported.
+
+To create filters that direct traffic to a specific Virtual Function, use the
+"user-def" parameter. Specify the user-def as a 64 bit value, where the lower 32
+bits represents the queue number, while the next 8 bits represent which VF.
+Note that 0 is the PF, so the VF identifier is offset by 1. For example::
+
+  ... user-def 0x800000002 ...
+
+specifies to direct traffic to Virtual Function 7 (8 minus 1) into queue 2 of
+that VF.
+
+Note that these filters will not break internal routing rules, and will not
+route traffic that otherwise would not have been sent to the specified Virtual
+Function.
+
+Jumbo Frames
+------------
+Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU)
+to a value larger than the default value of 1500.
+
+Use the ifconfig command to increase the MTU size. For example, enter the
+following where <x> is the interface number::
+
+  ifconfig eth<x> mtu 9000 up
+
+Alternatively, you can use the ip command as follows::
+
+  ip link set mtu 9000 dev eth<x>
+  ip link set up dev eth<x>
+
+This setting is not saved across reboots. The setting change can be made
+permanent by adding 'MTU=9000' to the file::
+
+  /etc/sysconfig/network-scripts/ifcfg-eth<x> // for RHEL
+  /etc/sysconfig/network/<config_file> // for SLES
+
+NOTE: The maximum MTU setting for Jumbo Frames is 9710. This value coincides
+with the maximum Jumbo Frames size of 9728 bytes.
+
+NOTE: This driver will attempt to use multiple page sized buffers to receive
+each jumbo packet. This should help to avoid buffer starvation issues when
+allocating receive packets.
+
+NOTE: For 82599-based network connections, if you are enabling jumbo frames in
+a virtual function (VF), jumbo frames must first be enabled in the physical
+function (PF). The VF MTU setting cannot be larger than the PF MTU.
+
+Generic Receive Offload, aka GRO
+--------------------------------
+The driver supports the in-kernel software implementation of GRO. GRO has
+shown that by coalescing Rx traffic into larger chunks of data, CPU
+utilization can be significantly reduced when under large Rx load. GRO is an
+evolution of the previously-used LRO interface. GRO is able to coalesce
+other protocols besides TCP. It's also safe to use with configurations that
+are problematic for LRO, namely bridging and iSCSI.
+
+Data Center Bridging (DCB)
+--------------------------
+NOTE:
+The kernel assumes that TC0 is available, and will disable Priority Flow
+Control (PFC) on the device if TC0 is not available. To fix this, ensure TC0 is
+enabled when setting up DCB on your switch.
+
+DCB is a configuration Quality of Service implementation in hardware. It uses
+the VLAN priority tag (802.1p) to filter traffic. That means that there are 8
+different priorities that traffic can be filtered into. It also enables
+priority flow control (802.1Qbb) which can limit or eliminate the number of
+dropped packets during network stress. Bandwidth can be allocated to each of
+these priorities, which is enforced at the hardware level (802.1Qaz).
+
+Adapter firmware implements LLDP and DCBX protocol agents as per 802.1AB and
+802.1Qaz respectively. The firmware based DCBX agent runs in willing mode only
+and can accept settings from a DCBX capable peer. Software configuration of
+DCBX parameters via dcbtool/lldptool are not supported.
+
+The ixgbe driver implements the DCB netlink interface layer to allow user-space
+to communicate with the driver and query DCB configuration for the port.
+
+ethtool
+-------
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information. The latest ethtool
+version is required for this functionality. Download it at:
+https://www.kernel.org/pub/software/network/ethtool/
+
+FCoE
+----
+The ixgbe driver supports Fiber Channel over Ethernet (FCoE) and Data Center
+Bridging (DCB). This code has no default effect on the regular driver
+operation. Configuring DCB and FCoE is outside the scope of this README. Refer
+to http://www.open-fcoe.org/ for FCoE project information and contact
+ixgbe-eedc@lists.sourceforge.net for DCB information.
+
+MAC and VLAN anti-spoofing feature
+----------------------------------
+When a malicious driver attempts to send a spoofed packet, it is dropped by the
+hardware and not transmitted.
+
+An interrupt is sent to the PF driver notifying it of the spoof attempt. When a
+spoofed packet is detected, the PF driver will send the following message to
+the system log (displayed by the "dmesg" command)::
+
+  ixgbe ethX: ixgbe_spoof_check: n spoofed packets detected
+
+where "x" is the PF interface number; and "n" is number of spoofed packets.
+NOTE: This feature can be disabled for a specific Virtual Function (VF)::
+
+  ip link set <pf dev> vf <vf id> spoofchk {off|on}
+
+IPsec Offload
+-------------
+The ixgbe driver supports IPsec Hardware Offload.  When creating Security
+Associations with "ip xfrm ..." the 'offload' tag option can be used to
+register the IPsec SA with the driver in order to get higher throughput in
+the secure communications.
+
+The offload is also supported for ixgbe's VFs, but the VF must be set as
+'trusted' and the support must be enabled with::
+
+  ethtool --set-priv-flags eth<x> vf-ipsec on
+  ip link set eth<x> vf <y> trust on
+
+
+Known Issues/Troubleshooting
+============================
+
+Enabling SR-IOV in a 64-bit Microsoft* Windows Server* 2012/R2 guest OS
+-----------------------------------------------------------------------
+Linux KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM.
+This includes traditional PCIe devices, as well as SR-IOV-capable devices based
+on the Intel Ethernet Controller XL710.
+
+
+Support
+=======
+For general information, go to the Intel support website at:
+
+https://www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+https://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on a supported kernel
+with a supported adapter, email the specific information related to the issue
+to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/device_drivers/intel/ixgbevf.rst b/Documentation/networking/device_drivers/intel/ixgbevf.rst
new file mode 100644
index 000000000000..56cde6366c2f
--- /dev/null
+++ b/Documentation/networking/device_drivers/intel/ixgbevf.rst
@@ -0,0 +1,66 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Linux* Base Virtual Function Driver for Intel(R) 10G Ethernet
+=============================================================
+
+Intel 10 Gigabit Virtual Function Linux driver.
+Copyright(c) 1999-2018 Intel Corporation.
+
+Contents
+========
+
+- Identifying Your Adapter
+- Known Issues
+- Support
+
+This driver supports 82599, X540, X550, and X552-based virtual function devices
+that can only be activated on kernels that support SR-IOV.
+
+For questions related to hardware requirements, refer to the documentation
+supplied with your Intel adapter. All hardware requirements listed apply to use
+with Linux.
+
+
+Identifying Your Adapter
+========================
+The driver is compatible with devices based on the following:
+
+  * Intel(R) Ethernet Controller 82598
+  * Intel(R) Ethernet Controller 82599
+  * Intel(R) Ethernet Controller X520
+  * Intel(R) Ethernet Controller X540
+  * Intel(R) Ethernet Controller x550
+  * Intel(R) Ethernet Controller X552
+  * Intel(R) Ethernet Controller X553
+
+For information on how to identify your adapter, and for the latest Intel
+network drivers, refer to the Intel Support website:
+https://www.intel.com/support
+
+Known Issues/Troubleshooting
+============================
+
+SR-IOV requires the correct platform and OS support.
+
+The guest OS loading this driver must support MSI-X interrupts.
+
+This driver is only supported as a loadable module at this time. Intel is not
+supplying patches against the kernel source to allow for static linking of the
+drivers.
+
+VLANs: There is a limit of a total of 64 shared VLANs to 1 or more VFs.
+
+
+Support
+=======
+For general information, go to the Intel support website at:
+
+https://www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+https://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on a supported kernel
+with a supported adapter, email the specific information related to the issue
+to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/device_drivers/microsoft/netvsc.txt b/Documentation/networking/device_drivers/microsoft/netvsc.txt
new file mode 100644
index 000000000000..3bfa635bbbd5
--- /dev/null
+++ b/Documentation/networking/device_drivers/microsoft/netvsc.txt
@@ -0,0 +1,84 @@
+Hyper-V network driver
+======================
+
+Compatibility
+=============
+
+This driver is compatible with Windows Server 2012 R2, 2016 and
+Windows 10.
+
+Features
+========
+
+  Checksum offload
+  ----------------
+  The netvsc driver supports checksum offload as long as the
+  Hyper-V host version does. Windows Server 2016 and Azure
+  support checksum offload for TCP and UDP for both IPv4 and
+  IPv6. Windows Server 2012 only supports checksum offload for TCP.
+
+  Receive Side Scaling
+  --------------------
+  Hyper-V supports receive side scaling. For TCP & UDP, packets can
+  be distributed among available queues based on IP address and port
+  number.
+
+  For TCP & UDP, we can switch hash level between L3 and L4 by ethtool
+  command. TCP/UDP over IPv4 and v6 can be set differently. The default
+  hash level is L4. We currently only allow switching TX hash level
+  from within the guests.
+
+  On Azure, fragmented UDP packets have high loss rate with L4
+  hashing. Using L3 hashing is recommended in this case.
+
+  For example, for UDP over IPv4 on eth0:
+  To include UDP port numbers in hashing:
+        ethtool -N eth0 rx-flow-hash udp4 sdfn
+  To exclude UDP port numbers in hashing:
+        ethtool -N eth0 rx-flow-hash udp4 sd
+  To show UDP hash level:
+        ethtool -n eth0 rx-flow-hash udp4
+
+  Generic Receive Offload, aka GRO
+  --------------------------------
+  The driver supports GRO and it is enabled by default. GRO coalesces
+  like packets and significantly reduces CPU usage under heavy Rx
+  load.
+
+  Large Receive Offload (LRO), or Receive Side Coalescing (RSC)
+  -------------------------------------------------------------
+  The driver supports LRO/RSC in the vSwitch feature. It reduces the per packet
+  processing overhead by coalescing multiple TCP segments when possible. The
+  feature is enabled by default on VMs running on Windows Server 2019 and
+  later. It may be changed by ethtool command:
+	ethtool -K eth0 lro on
+	ethtool -K eth0 lro off
+
+  SR-IOV support
+  --------------
+  Hyper-V supports SR-IOV as a hardware acceleration option. If SR-IOV
+  is enabled in both the vSwitch and the guest configuration, then the
+  Virtual Function (VF) device is passed to the guest as a PCI
+  device. In this case, both a synthetic (netvsc) and VF device are
+  visible in the guest OS and both NIC's have the same MAC address.
+
+  The VF is enslaved by netvsc device.  The netvsc driver will transparently
+  switch the data path to the VF when it is available and up.
+  Network state (addresses, firewall, etc) should be applied only to the
+  netvsc device; the slave device should not be accessed directly in
+  most cases.  The exceptions are if some special queue discipline or
+  flow direction is desired, these should be applied directly to the
+  VF slave device.
+
+  Receive Buffer
+  --------------
+  Packets are received into a receive area which is created when device
+  is probed. The receive area is broken into MTU sized chunks and each may
+  contain one or more packets. The number of receive sections may be changed
+  via ethtool Rx ring parameters.
+
+  There is a similar send buffer which is used to aggregate packets for sending.
+  The send area is broken into chunks of 6144 bytes, each of section may
+  contain one or more packets. The send buffer is an optimization, the driver
+  will use slower method to handle very large packets or if the send buffer
+  area is exhausted.
diff --git a/Documentation/networking/device_drivers/neterion/s2io.txt b/Documentation/networking/device_drivers/neterion/s2io.txt
new file mode 100644
index 000000000000..0362a42f7cf4
--- /dev/null
+++ b/Documentation/networking/device_drivers/neterion/s2io.txt
@@ -0,0 +1,141 @@
+Release notes for Neterion's (Formerly S2io) Xframe I/II PCI-X 10GbE driver.
+
+Contents
+=======
+- 1.  Introduction
+- 2.  Identifying the adapter/interface
+- 3.  Features supported
+- 4.  Command line parameters
+- 5.  Performance suggestions
+- 6.  Available Downloads 
+
+
+1.	Introduction:
+This Linux driver supports Neterion's Xframe I PCI-X 1.0 and
+Xframe II PCI-X 2.0 adapters. It supports several features 
+such as jumbo frames, MSI/MSI-X, checksum offloads, TSO, UFO and so on.
+See below for complete list of features.
+All features are supported for both IPv4 and IPv6.
+
+2.	Identifying the adapter/interface:
+a. Insert the adapter(s) in your system.
+b. Build and load driver 
+# insmod s2io.ko
+c. View log messages
+# dmesg | tail -40
+You will see messages similar to:
+eth3: Neterion Xframe I 10GbE adapter (rev 3), Version 2.0.9.1, Intr type INTA
+eth4: Neterion Xframe II 10GbE adapter (rev 2), Version 2.0.9.1, Intr type INTA
+eth4: Device is on 64 bit 133MHz PCIX(M1) bus
+
+The above messages identify the adapter type(Xframe I/II), adapter revision,
+driver version, interface name(eth3, eth4), Interrupt type(INTA, MSI, MSI-X).
+In case of Xframe II, the PCI/PCI-X bus width and frequency are displayed
+as well.
+
+To associate an interface with a physical adapter use "ethtool -p <ethX>".
+The corresponding adapter's LED will blink multiple times.
+
+3.	Features supported:
+a. Jumbo frames. Xframe I/II supports MTU up to 9600 bytes,
+modifiable using ip command.
+
+b. Offloads. Supports checksum offload(TCP/UDP/IP) on transmit
+and receive, TSO.
+
+c. Multi-buffer receive mode. Scattering of packet across multiple
+buffers. Currently driver supports 2-buffer mode which yields
+significant performance improvement on certain platforms(SGI Altix,
+IBM xSeries).
+
+d. MSI/MSI-X. Can be enabled on platforms which support this feature
+(IA64, Xeon) resulting in noticeable performance improvement(up to 7%
+on certain platforms).
+
+e. Statistics. Comprehensive MAC-level and software statistics displayed
+using "ethtool -S" option.
+
+f. Multi-FIFO/Ring. Supports up to 8 transmit queues and receive rings,
+with multiple steering options.
+
+4.  Command line parameters
+a. tx_fifo_num
+Number of transmit queues
+Valid range: 1-8
+Default: 1
+
+b. rx_ring_num
+Number of receive rings
+Valid range: 1-8
+Default: 1
+
+c. tx_fifo_len
+Size of each transmit queue
+Valid range: Total length of all queues should not exceed 8192
+Default: 4096
+
+d. rx_ring_sz 
+Size of each receive ring(in 4K blocks)
+Valid range: Limited by memory on system
+Default: 30 
+
+e. intr_type
+Specifies interrupt type. Possible values 0(INTA), 2(MSI-X)
+Valid values: 0, 2
+Default: 2
+
+5.  Performance suggestions
+General:
+a. Set MTU to maximum(9000 for switch setup, 9600 in back-to-back configuration)
+b. Set TCP windows size to optimal value. 
+For instance, for MTU=1500 a value of 210K has been observed to result in 
+good performance.
+# sysctl -w net.ipv4.tcp_rmem="210000 210000 210000"
+# sysctl -w net.ipv4.tcp_wmem="210000 210000 210000"
+For MTU=9000, TCP window size of 10 MB is recommended.
+# sysctl -w net.ipv4.tcp_rmem="10000000 10000000 10000000"
+# sysctl -w net.ipv4.tcp_wmem="10000000 10000000 10000000"
+
+Transmit performance:
+a. By default, the driver respects BIOS settings for PCI bus parameters. 
+However, you may want to experiment with PCI bus parameters 
+max-split-transactions(MOST) and MMRBC (use setpci command). 
+A MOST value of 2 has been found optimal for Opterons and 3 for Itanium.  
+It could be different for your hardware.  
+Set MMRBC to 4K**.
+
+For example you can set 
+For opteron
+#setpci -d 17d5:* 62=1d 
+For Itanium
+#setpci -d 17d5:* 62=3d 
+
+For detailed description of the PCI registers, please see Xframe User Guide.
+
+b. Ensure Transmit Checksum offload is enabled. Use ethtool to set/verify this 
+parameter.
+c. Turn on TSO(using "ethtool -K")
+# ethtool -K <ethX> tso on
+
+Receive performance:
+a. By default, the driver respects BIOS settings for PCI bus parameters. 
+However, you may want to set PCI latency timer to 248.
+#setpci -d 17d5:* LATENCY_TIMER=f8
+For detailed description of the PCI registers, please see Xframe User Guide.
+b. Use 2-buffer mode. This results in large performance boost on
+certain platforms(eg. SGI Altix, IBM xSeries).
+c. Ensure Receive Checksum offload is enabled. Use "ethtool -K ethX" command to 
+set/verify this option.
+d. Enable NAPI feature(in kernel configuration Device Drivers ---> Network 
+device support --->  Ethernet (10000 Mbit) ---> S2IO 10Gbe Xframe NIC) to 
+bring down CPU utilization.
+
+** For AMD opteron platforms with 8131 chipset, MMRBC=1 and MOST=1 are 
+recommended as safe parameters.
+For more information, please review the AMD8131 errata at
+http://vip.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/
+26310_AMD-8131_HyperTransport_PCI-X_Tunnel_Revision_Guide_rev_3_18.pdf
+
+6. Support
+For further support please contact either your 10GbE Xframe NIC vendor (IBM, 
+HP, SGI etc.)
diff --git a/Documentation/networking/device_drivers/neterion/vxge.txt b/Documentation/networking/device_drivers/neterion/vxge.txt
new file mode 100644
index 000000000000..abfec245f97c
--- /dev/null
+++ b/Documentation/networking/device_drivers/neterion/vxge.txt
@@ -0,0 +1,93 @@
+Neterion's (Formerly S2io) X3100 Series 10GbE PCIe Server Adapter Linux driver
+==============================================================================
+
+Contents
+--------
+
+1) Introduction
+2) Features supported
+3) Configurable driver parameters
+4) Troubleshooting
+
+1) Introduction:
+----------------
+This Linux driver supports all Neterion's X3100 series 10 GbE PCIe I/O
+Virtualized Server adapters.
+The X3100 series supports four modes of operation, configurable via
+firmware -
+	Single function mode
+	Multi function mode
+	SRIOV mode
+	MRIOV mode
+The functions share a 10GbE link and the pci-e bus, but hardly anything else
+inside the ASIC. Features like independent hw reset, statistics, bandwidth/
+priority allocation and guarantees, GRO, TSO, interrupt moderation etc are
+supported independently on each function.
+
+(See below for a complete list of features supported for both IPv4 and IPv6)
+
+2) Features supported:
+----------------------
+
+i)   Single function mode (up to 17 queues)
+
+ii)  Multi function mode (up to 17 functions)
+
+iii) PCI-SIG's I/O Virtualization
+       - Single Root mode: v1.0 (up to 17 functions)
+       - Multi-Root mode: v1.0 (up to 17 functions)
+
+iv)  Jumbo frames
+       X3100 Series supports MTU up to 9600 bytes, modifiable using
+       ip command.
+
+v)   Offloads supported: (Enabled by default)
+       Checksum offload (TCP/UDP/IP) on transmit and receive paths
+       TCP Segmentation Offload (TSO) on transmit path
+       Generic Receive Offload (GRO) on receive path
+
+vi)  MSI-X: (Enabled by default)
+       Resulting in noticeable performance improvement (up to 7% on certain
+       platforms).
+
+vii) NAPI: (Enabled by default)
+       For better Rx interrupt moderation.
+
+viii)RTH (Receive Traffic Hash): (Enabled by default)
+       Receive side steering for better scaling.
+
+ix)  Statistics
+       Comprehensive MAC-level and software statistics displayed using
+       "ethtool -S" option.
+
+x)   Multiple hardware queues: (Enabled by default)
+       Up to 17 hardware based transmit and receive data channels, with
+       multiple steering options (transmit multiqueue enabled by default).
+
+3) Configurable driver parameters:
+----------------------------------
+
+i)  max_config_dev
+       Specifies maximum device functions to be enabled.
+       Valid range: 1-8
+
+ii) max_config_port
+       Specifies number of ports to be enabled.
+       Valid range: 1,2
+       Default: 1
+
+iii)max_config_vpath
+       Specifies maximum VPATH(s) configured for each device function.
+       Valid range: 1-17
+
+iv) vlan_tag_strip
+       Enables/disables vlan tag stripping from all received tagged frames that
+       are not replicated at the internal L2 switch.
+       Valid range: 0,1 (disabled, enabled respectively)
+       Default: 1
+
+v)  addr_learn_en
+       Enable learning the mac address of the guest OS interface in
+       virtualization environment.
+       Valid range: 0,1 (disabled, enabled respectively)
+       Default: 0
diff --git a/Documentation/networking/device_drivers/qlogic/LICENSE.qla3xxx b/Documentation/networking/device_drivers/qlogic/LICENSE.qla3xxx
new file mode 100644
index 000000000000..2f2077e34d81
--- /dev/null
+++ b/Documentation/networking/device_drivers/qlogic/LICENSE.qla3xxx
@@ -0,0 +1,46 @@
+Copyright (c)  2003-2006 QLogic Corporation
+QLogic Linux Networking HBA Driver
+
+This program includes a device driver for Linux 2.6 that may be
+distributed with QLogic hardware specific firmware binary file.
+You may modify and redistribute the device driver code under the
+GNU General Public License as published by the Free Software
+Foundation (version 2 or a later version).
+
+You may redistribute the hardware specific firmware binary file
+under the following terms:
+
+	1. Redistribution of source code (only if applicable),
+	   must retain the above copyright notice, this list of
+	   conditions and the following disclaimer.
+
+	2. Redistribution in binary form must reproduce the above
+	   copyright notice, this list of conditions and the
+	   following disclaimer in the documentation and/or other
+	   materials provided with the distribution.
+
+	3. The name of QLogic Corporation may not be used to
+	   endorse or promote products derived from this software
+	   without specific prior written permission
+
+REGARDLESS OF WHAT LICENSING MECHANISM IS USED OR APPLICABLE,
+THIS PROGRAM IS PROVIDED BY QLOGIC CORPORATION "AS IS'' AND ANY
+EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR
+BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
+TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+
+USER ACKNOWLEDGES AND AGREES THAT USE OF THIS PROGRAM WILL NOT
+CREATE OR GIVE GROUNDS FOR A LICENSE BY IMPLICATION, ESTOPPEL, OR
+OTHERWISE IN ANY INTELLECTUAL PROPERTY RIGHTS (PATENT, COPYRIGHT,
+TRADE SECRET, MASK WORK, OR OTHER PROPRIETARY RIGHT) EMBODIED IN
+ANY OTHER QLOGIC HARDWARE OR SOFTWARE EITHER SOLELY OR IN
+COMBINATION WITH THIS PROGRAM.
+
diff --git a/Documentation/networking/device_drivers/qlogic/LICENSE.qlcnic b/Documentation/networking/device_drivers/qlogic/LICENSE.qlcnic
new file mode 100644
index 000000000000..2ae3b64983ab
--- /dev/null
+++ b/Documentation/networking/device_drivers/qlogic/LICENSE.qlcnic
@@ -0,0 +1,288 @@
+Copyright (c) 2009-2013 QLogic Corporation
+QLogic Linux qlcnic NIC Driver
+
+You may modify and redistribute the device driver code under the
+GNU General Public License (a copy of which is attached hereto as
+Exhibit A) published by the Free Software Foundation (version 2).
+
+
+EXHIBIT A
+
+		    GNU GENERAL PUBLIC LICENSE
+		       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+ 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+			    Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+		    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+			    NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
diff --git a/Documentation/networking/device_drivers/qlogic/LICENSE.qlge b/Documentation/networking/device_drivers/qlogic/LICENSE.qlge
new file mode 100644
index 000000000000..ce64e4d15b21
--- /dev/null
+++ b/Documentation/networking/device_drivers/qlogic/LICENSE.qlge
@@ -0,0 +1,288 @@
+Copyright (c) 2003-2011 QLogic Corporation
+QLogic Linux qlge NIC Driver
+
+You may modify and redistribute the device driver code under the
+GNU General Public License (a copy of which is attached hereto as
+Exhibit A) published by the Free Software Foundation (version 2).
+
+
+EXHIBIT A
+
+		    GNU GENERAL PUBLIC LICENSE
+		       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+ 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+			    Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+		    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+			    NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
diff --git a/Documentation/networking/device_drivers/qualcomm/rmnet.txt b/Documentation/networking/device_drivers/qualcomm/rmnet.txt
new file mode 100644
index 000000000000..6b341eaf2062
--- /dev/null
+++ b/Documentation/networking/device_drivers/qualcomm/rmnet.txt
@@ -0,0 +1,82 @@
+1. Introduction
+
+rmnet driver is used for supporting the Multiplexing and aggregation
+Protocol (MAP). This protocol is used by all recent chipsets using Qualcomm
+Technologies, Inc. modems.
+
+This driver can be used to register onto any physical network device in
+IP mode. Physical transports include USB, HSIC, PCIe and IP accelerator.
+
+Multiplexing allows for creation of logical netdevices (rmnet devices) to
+handle multiple private data networks (PDN) like a default internet, tethering,
+multimedia messaging service (MMS) or IP media subsystem (IMS). Hardware sends
+packets with MAP headers to rmnet. Based on the multiplexer id, rmnet
+routes to the appropriate PDN after removing the MAP header.
+
+Aggregation is required to achieve high data rates. This involves hardware
+sending aggregated bunch of MAP frames. rmnet driver will de-aggregate
+these MAP frames and send them to appropriate PDN's.
+
+2. Packet format
+
+a. MAP packet (data / control)
+
+MAP header has the same endianness of the IP packet.
+
+Packet format -
+
+Bit             0             1           2-7      8 - 15           16 - 31
+Function   Command / Data   Reserved     Pad   Multiplexer ID    Payload length
+Bit            32 - x
+Function     Raw  Bytes
+
+Command (1)/ Data (0) bit value is to indicate if the packet is a MAP command
+or data packet. Control packet is used for transport level flow control. Data
+packets are standard IP packets.
+
+Reserved bits are usually zeroed out and to be ignored by receiver.
+
+Padding is number of bytes to be added for 4 byte alignment if required by
+hardware.
+
+Multiplexer ID is to indicate the PDN on which data has to be sent.
+
+Payload length includes the padding length but does not include MAP header
+length.
+
+b. MAP packet (command specific)
+
+Bit             0             1           2-7      8 - 15           16 - 31
+Function   Command         Reserved     Pad   Multiplexer ID    Payload length
+Bit          32 - 39        40 - 45    46 - 47       48 - 63
+Function   Command name    Reserved   Command Type   Reserved
+Bit          64 - 95
+Function   Transaction ID
+Bit          96 - 127
+Function   Command data
+
+Command 1 indicates disabling flow while 2 is enabling flow
+
+Command types -
+0 for MAP command request
+1 is to acknowledge the receipt of a command
+2 is for unsupported commands
+3 is for error during processing of commands
+
+c. Aggregation
+
+Aggregation is multiple MAP packets (can be data or command) delivered to
+rmnet in a single linear skb. rmnet will process the individual
+packets and either ACK the MAP command or deliver the IP packet to the
+network stack as needed
+
+MAP header|IP Packet|Optional padding|MAP header|IP Packet|Optional padding....
+MAP header|IP Packet|Optional padding|MAP header|Command Packet|Optional pad...
+
+3. Userspace configuration
+
+rmnet userspace configuration is done through netlink library librmnetctl
+and command line utility rmnetcli. Utility is hosted in codeaurora forum git.
+The driver uses rtnl_link_ops for communication.
+
+https://source.codeaurora.org/quic/la/platform/vendor/qcom-opensource/dataservices/tree/rmnetctl
diff --git a/Documentation/networking/device_drivers/sb1000.txt b/Documentation/networking/device_drivers/sb1000.txt
new file mode 100644
index 000000000000..f92c2aac56a9
--- /dev/null
+++ b/Documentation/networking/device_drivers/sb1000.txt
@@ -0,0 +1,207 @@
+sb1000 is a module network device driver for the General Instrument (also known
+as NextLevel) SURFboard1000 internal cable modem board.  This is an ISA card
+which is used by a number of cable TV companies to provide cable modem access.
+It's a one-way downstream-only cable modem, meaning that your upstream net link
+is provided by your regular phone modem.
+
+This driver was written by Franco Venturi <fventuri@mediaone.net>.  He deserves
+a great deal of thanks for this wonderful piece of code!
+
+-----------------------------------------------------------------------------
+
+Support for this device is now a part of the standard Linux kernel.  The
+driver source code file is drivers/net/sb1000.c.  In addition to this
+you will need:
+
+1.) The "cmconfig" program.  This is a utility which supplements "ifconfig"
+to configure the cable modem and network interface (usually called "cm0");
+and
+
+2.) Several PPP scripts which live in /etc/ppp to make connecting via your
+cable modem easy.
+
+   These utilities can be obtained from:
+
+      http://www.jacksonville.net/~fventuri/
+
+   in Franco's original source code distribution .tar.gz file.  Support for
+   the sb1000 driver can be found at:
+
+      http://web.archive.org/web/*/http://home.adelphia.net/~siglercm/sb1000.html
+      http://web.archive.org/web/*/http://linuxpower.cx/~cable/
+
+   along with these utilities.
+
+3.) The standard isapnp tools.  These are necessary to configure your SB1000
+card at boot time (or afterwards by hand) since it's a PnP card.
+
+   If you don't have these installed as a standard part of your Linux
+   distribution, you can find them at:
+
+      http://www.roestock.demon.co.uk/isapnptools/
+
+   or check your Linux distribution binary CD or their web site.  For help with
+   isapnp, pnpdump, or /etc/isapnp.conf, go to:
+
+      http://www.roestock.demon.co.uk/isapnptools/isapnpfaq.html
+
+-----------------------------------------------------------------------------
+
+To make the SB1000 card work, follow these steps:
+
+1.) Run `make config', or `make menuconfig', or `make xconfig', whichever
+you prefer, in the top kernel tree directory to set up your kernel
+configuration.  Make sure to say "Y" to "Prompt for development drivers"
+and to say "M" to the sb1000 driver.  Also say "Y" or "M" to all the standard
+networking questions to get TCP/IP and PPP networking support.
+
+2.) *BEFORE* you build the kernel, edit drivers/net/sb1000.c.  Make sure
+to redefine the value of READ_DATA_PORT to match the I/O address used
+by isapnp to access your PnP cards.  This is the value of READPORT in
+/etc/isapnp.conf or given by the output of pnpdump.
+
+3.) Build and install the kernel and modules as usual.
+
+4.) Boot your new kernel following the usual procedures.
+
+5.) Set up to configure the new SB1000 PnP card by capturing the output
+of "pnpdump" to a file and editing this file to set the correct I/O ports,
+IRQ, and DMA settings for all your PnP cards.  Make sure none of the settings
+conflict with one another.  Then test this configuration by running the
+"isapnp" command with your new config file as the input.  Check for
+errors and fix as necessary.  (As an aside, I use I/O ports 0x110 and
+0x310 and IRQ 11 for my SB1000 card and these work well for me.  YMMV.)
+Then save the finished config file as /etc/isapnp.conf for proper configuration
+on subsequent reboots.
+
+6.) Download the original file sb1000-1.1.2.tar.gz from Franco's site or one of
+the others referenced above.  As root, unpack it into a temporary directory and
+do a `make cmconfig' and then `install -c cmconfig /usr/local/sbin'.  Don't do
+`make install' because it expects to find all the utilities built and ready for
+installation, not just cmconfig.
+
+7.) As root, copy all the files under the ppp/ subdirectory in Franco's
+tar file into /etc/ppp, being careful not to overwrite any files that are
+already in there.  Then modify ppp@gi-on to set the correct login name,
+phone number, and frequency for the cable modem.  Also edit pap-secrets
+to specify your login name and password and any site-specific information
+you need.
+
+8.) Be sure to modify /etc/ppp/firewall to use ipchains instead of
+the older ipfwadm commands from the 2.0.x kernels.  There's a neat utility to
+convert ipfwadm commands to ipchains commands:
+
+   http://users.dhp.com/~whisper/ipfwadm2ipchains/
+
+You may also wish to modify the firewall script to implement a different
+firewalling scheme.
+
+9.) Start the PPP connection via the script /etc/ppp/ppp@gi-on.  You must be
+root to do this.  It's better to use a utility like sudo to execute
+frequently used commands like this with root permissions if possible.  If you
+connect successfully the cable modem interface will come up and you'll see a
+driver message like this at the console:
+
+         cm0: sb1000 at (0x110,0x310), csn 1, S/N 0x2a0d16d8, IRQ 11.
+         sb1000.c:v1.1.2 6/01/98 (fventuri@mediaone.net)
+
+The "ifconfig" command should show two new interfaces, ppp0 and cm0.
+The command "cmconfig cm0" will give you information about the cable modem
+interface.
+
+10.) Try pinging a site via `ping -c 5 www.yahoo.com', for example.  You should
+see packets received.
+
+11.) If you can't get site names (like www.yahoo.com) to resolve into
+IP addresses (like 204.71.200.67), be sure your /etc/resolv.conf file
+has no syntax errors and has the right nameserver IP addresses in it.
+If this doesn't help, try something like `ping -c 5 204.71.200.67' to
+see if the networking is running but the DNS resolution is where the
+problem lies.
+
+12.) If you still have problems, go to the support web sites mentioned above
+and read the information and documentation there.
+
+-----------------------------------------------------------------------------
+
+Common problems:
+
+1.) Packets go out on the ppp0 interface but don't come back on the cm0
+interface.  It looks like I'm connected but I can't even ping any
+numerical IP addresses.  (This happens predominantly on Debian systems due
+to a default boot-time configuration script.)
+
+Solution -- As root `echo 0 > /proc/sys/net/ipv4/conf/cm0/rp_filter' so it
+can share the same IP address as the ppp0 interface.  Note that this
+command should probably be added to the /etc/ppp/cablemodem script
+*right*between* the "/sbin/ifconfig" and "/sbin/cmconfig" commands.
+You may need to do this to /proc/sys/net/ipv4/conf/ppp0/rp_filter as well.
+If you do this to /proc/sys/net/ipv4/conf/default/rp_filter on each reboot
+(in rc.local or some such) then any interfaces can share the same IP
+addresses.
+
+2.) I get "unresolved symbol" error messages on executing `insmod sb1000.o'.
+
+Solution -- You probably have a non-matching kernel source tree and
+/usr/include/linux and /usr/include/asm header files.  Make sure you
+install the correct versions of the header files in these two directories.
+Then rebuild and reinstall the kernel.
+
+3.) When isapnp runs it reports an error, and my SB1000 card isn't working.
+
+Solution -- There's a problem with later versions of isapnp using the "(CHECK)"
+option in the lines that allocate the two I/O addresses for the SB1000 card.
+This first popped up on RH 6.0.  Delete "(CHECK)" for the SB1000 I/O addresses.
+Make sure they don't conflict with any other pieces of hardware first!  Then
+rerun isapnp and go from there.
+
+4.) I can't execute the /etc/ppp/ppp@gi-on file.
+
+Solution -- As root do `chmod ug+x /etc/ppp/ppp@gi-on'.
+
+5.) The firewall script isn't working (with 2.2.x and higher kernels).
+
+Solution -- Use the ipfwadm2ipchains script referenced above to convert the
+/etc/ppp/firewall script from the deprecated ipfwadm commands to ipchains.
+
+6.) I'm getting *tons* of firewall deny messages in the /var/kern.log,
+/var/messages, and/or /var/syslog files, and they're filling up my /var
+partition!!!
+
+Solution -- First, tell your ISP that you're receiving DoS (Denial of Service)
+and/or portscanning (UDP connection attempts) attacks!  Look over the deny
+messages to figure out what the attack is and where it's coming from.  Next,
+edit /etc/ppp/cablemodem and make sure the ",nobroadcast" option is turned on
+to the "cmconfig" command (uncomment that line).  If you're not receiving these
+denied packets on your broadcast interface (IP address xxx.yyy.zzz.255
+typically), then someone is attacking your machine in particular.  Be careful
+out there....
+
+7.) Everything seems to work fine but my computer locks up after a while
+(and typically during a lengthy download through the cable modem)!
+
+Solution -- You may need to add a short delay in the driver to 'slow down' the
+SURFboard because your PC might not be able to keep up with the transfer rate
+of the SB1000. To do this, it's probably best to download Franco's
+sb1000-1.1.2.tar.gz archive and build and install sb1000.o manually.  You'll
+want to edit the 'Makefile' and look for the 'SB1000_DELAY'
+define.  Uncomment those 'CFLAGS' lines (and comment out the default ones)
+and try setting the delay to something like 60 microseconds with:
+'-DSB1000_DELAY=60'.  Then do `make' and as root `make install' and try
+it out.  If it still doesn't work or you like playing with the driver, you may
+try other numbers.  Remember though that the higher the delay, the slower the
+driver (which slows down the rest of the PC too when it is actively
+used). Thanks to Ed Daiga for this tip!
+
+-----------------------------------------------------------------------------
+
+Credits:  This README came from Franco Venturi's original README file which is
+still supplied with his driver .tar.gz archive.  I and all other sb1000 users
+owe Franco a tremendous "Thank you!"  Additional thanks goes to Carl Patten
+and Ralph Bonnell who are now managing the Linux SB1000 web site, and to
+the SB1000 users who reported and helped debug the common problems listed
+above.
+
+
+					Clemmitt Sigler
+					csigler@vt.edu
diff --git a/Documentation/networking/device_drivers/smsc/smc9.txt b/Documentation/networking/device_drivers/smsc/smc9.txt
new file mode 100644
index 000000000000..d1e15074e43d
--- /dev/null
+++ b/Documentation/networking/device_drivers/smsc/smc9.txt
@@ -0,0 +1,42 @@
+
+SMC 9xxxx Driver 
+Revision 0.12 
+3/5/96
+Copyright 1996  Erik Stahlman 
+Released under terms of the GNU General Public License. 
+
+This file contains the instructions and caveats for my SMC9xxx driver.  You
+should not be using the driver without reading this file.  
+
+Things to note about installation:
+
+  1. The driver should work on all kernels from 1.2.13 until 1.3.71.
+	(A kernel patch is supplied for 1.3.71 )
+
+  2. If you include this into the kernel, you might need to change some
+	options, such as for forcing IRQ.   
+
+ 
+  3.  To compile as a module, run 'make' .   
+	Make will give you the appropriate options for various kernel support.
+ 
+  4.  Loading the driver as a module :
+
+	use:   insmod smc9194.o 
+	optional parameters:
+		io=xxxx    : your base address
+		irq=xx	   : your irq 
+		ifport=x   :	0 for whatever is default
+				1 for twisted pair
+				2 for AUI  ( or BNC on some cards )
+
+How to obtain the latest version? 
+	
+FTP:  
+	ftp://fenris.campus.vt.edu/smc9/smc9-12.tar.gz
+	ftp://sfbox.vt.edu/filebox/F/fenris/smc9/smc9-12.tar.gz 
+   
+
+Contacting me:
+    erik@mail.vt.edu
+ 
diff --git a/Documentation/networking/device_drivers/stmicro/stmmac.txt b/Documentation/networking/device_drivers/stmicro/stmmac.txt
new file mode 100644
index 000000000000..2bb07078f535
--- /dev/null
+++ b/Documentation/networking/device_drivers/stmicro/stmmac.txt
@@ -0,0 +1,401 @@
+       STMicroelectronics 10/100/1000 Synopsys Ethernet driver
+
+Copyright (C) 2007-2015  STMicroelectronics Ltd
+Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
+
+This is the driver for the MAC 10/100/1000 on-chip Ethernet controllers
+(Synopsys IP blocks).
+
+Currently this network device driver is for all STi embedded MAC/GMAC
+(i.e. 7xxx/5xxx SoCs), SPEAr (arm), Loongson1B (mips) and XLINX XC2V3000
+FF1152AMT0221 D1215994A VIRTEX FPGA board.
+
+DWC Ether MAC 10/100/1000 Universal version 3.70a (and older) and DWC Ether
+MAC 10/100 Universal version 4.0 have been used for developing this driver.
+
+This driver supports both the platform bus and PCI.
+
+Please, for more information also visit: www.stlinux.com
+
+1) Kernel Configuration
+The kernel configuration option is STMMAC_ETH:
+ Device Drivers ---> Network device support ---> Ethernet (1000 Mbit) --->
+ STMicroelectronics 10/100/1000 Ethernet driver (STMMAC_ETH)
+
+CONFIG_STMMAC_PLATFORM: is to enable the platform driver.
+CONFIG_STMMAC_PCI: is to enable the pci driver.
+
+2) Driver parameters list:
+	debug: message level (0: no output, 16: all);
+	phyaddr: to manually provide the physical address to the PHY device;
+	buf_sz: DMA buffer size;
+	tc: control the HW FIFO threshold;
+	watchdog: transmit timeout (in milliseconds);
+	flow_ctrl: Flow control ability [on/off];
+	pause: Flow Control Pause Time;
+	eee_timer: tx EEE timer;
+	chain_mode: select chain mode instead of ring.
+
+3) Command line options
+Driver parameters can be also passed in command line by using:
+	stmmaceth=watchdog:100,chain_mode=1
+
+4) Driver information and notes
+
+4.1) Transmit process
+The xmit method is invoked when the kernel needs to transmit a packet; it sets
+the descriptors in the ring and informs the DMA engine, that there is a packet
+ready to be transmitted.
+By default, the driver sets the NETIF_F_SG bit in the features field of the
+net_device structure, enabling the scatter-gather feature. This is true on
+chips and configurations where the checksum can be done in hardware.
+Once the controller has finished transmitting the packet, timer will be
+scheduled to release the transmit resources.
+
+4.2) Receive process
+When one or more packets are received, an interrupt happens. The interrupts
+are not queued, so the driver has to scan all the descriptors in the ring during
+the receive process.
+This is based on NAPI, so the interrupt handler signals only if there is work
+to be done, and it exits.
+Then the poll method will be scheduled at some future point.
+The incoming packets are stored, by the DMA, in a list of pre-allocated socket
+buffers in order to avoid the memcpy (zero-copy).
+
+4.3) Interrupt mitigation
+The driver is able to mitigate the number of its DMA interrupts
+using NAPI for the reception on chips older than the 3.50.
+New chips have an HW RX-Watchdog used for this mitigation.
+Mitigation parameters can be tuned by ethtool.
+
+4.4) WOL
+Wake up on Lan feature through Magic and Unicast frames are supported for the
+GMAC core.
+
+4.5) DMA descriptors
+Driver handles both normal and alternate descriptors. The latter has been only
+tested on DWC Ether MAC 10/100/1000 Universal version 3.41a and later.
+
+STMMAC supports DMA descriptor to operate both in dual buffer (RING)
+and linked-list(CHAINED) mode. In RING each descriptor points to two
+data buffer pointers whereas in CHAINED mode they point to only one data
+buffer pointer. RING mode is the default.
+
+In CHAINED mode each descriptor will have pointer to next descriptor in
+the list, hence creating the explicit chaining in the descriptor itself,
+whereas such explicit chaining is not possible in RING mode.
+
+4.5.1) Extended descriptors
+The extended descriptors give us information about the Ethernet payload
+when it is carrying PTP packets or TCP/UDP/ICMP over IP.
+These are not available on GMAC Synopsys chips older than the 3.50.
+At probe time the driver will decide if these can be actually used.
+This support also is mandatory for PTPv2 because the extra descriptors
+are used for saving the hardware timestamps and Extended Status.
+
+4.6) Ethtool support
+Ethtool is supported.
+
+For example, driver statistics (including RMON), internal errors can be taken
+using:
+  # ethtool -S ethX
+command
+
+4.7) Jumbo and Segmentation Offloading
+Jumbo frames are supported and tested for the GMAC.
+The GSO has been also added but it's performed in software.
+LRO is not supported.
+
+4.8) Physical
+The driver is compatible with Physical Abstraction Layer to be connected with
+PHY and GPHY devices.
+
+4.9) Platform information
+Several information can be passed through the platform and device-tree.
+
+struct plat_stmmacenet_data {
+	char *phy_bus_name;
+	int bus_id;
+	int phy_addr;
+	int interface;
+	struct stmmac_mdio_bus_data *mdio_bus_data;
+	struct stmmac_dma_cfg *dma_cfg;
+	int clk_csr;
+	int has_gmac;
+	int enh_desc;
+	int tx_coe;
+	int rx_coe;
+	int bugged_jumbo;
+	int pmt;
+	int force_sf_dma_mode;
+	int force_thresh_dma_mode;
+	int riwt_off;
+	int max_speed;
+	int maxmtu;
+	void (*fix_mac_speed)(void *priv, unsigned int speed);
+	void (*bus_setup)(void __iomem *ioaddr);
+	int (*init)(struct platform_device *pdev, void *priv);
+	void (*exit)(struct platform_device *pdev, void *priv);
+	void *bsp_priv;
+	int has_gmac4;
+	bool tso_en;
+};
+
+Where:
+ o phy_bus_name: phy bus name to attach to the stmmac.
+ o bus_id: bus identifier.
+ o phy_addr: the physical address can be passed from the platform.
+	    If it is set to -1 the driver will automatically
+	    detect it at run-time by probing all the 32 addresses.
+ o interface: PHY device's interface.
+ o mdio_bus_data: specific platform fields for the MDIO bus.
+ o dma_cfg: internal DMA parameters
+   o pbl: the Programmable Burst Length is maximum number of beats to
+       be transferred in one DMA transaction.
+       GMAC also enables the 4xPBL by default. (8xPBL for GMAC 3.50 and newer)
+   o txpbl/rxpbl: GMAC and newer supports independent DMA pbl for tx/rx.
+   o pblx8: Enable 8xPBL (4xPBL for core rev < 3.50). Enabled by default.
+   o fixed_burst/mixed_burst/aal
+ o clk_csr: fixed CSR Clock range selection.
+ o has_gmac: uses the GMAC core.
+ o enh_desc: if sets the MAC will use the enhanced descriptor structure.
+ o tx_coe: core is able to perform the tx csum in HW.
+ o rx_coe: the supports three check sum offloading engine types:
+	   type_1, type_2 (full csum) and no RX coe.
+ o bugged_jumbo: some HWs are not able to perform the csum in HW for
+		over-sized frames due to limited buffer sizes.
+		Setting this flag the csum will be done in SW on
+		JUMBO frames.
+ o pmt: core has the embedded power module (optional).
+ o force_sf_dma_mode: force DMA to use the Store and Forward mode
+		     instead of the Threshold.
+ o force_thresh_dma_mode: force DMA to use the Threshold mode other than
+		     the Store and Forward mode.
+ o riwt_off: force to disable the RX watchdog feature and switch to NAPI mode.
+ o fix_mac_speed: this callback is used for modifying some syscfg registers
+		 (on ST SoCs) according to the link speed negotiated by the
+		 physical layer .
+ o bus_setup: perform HW setup of the bus. For example, on some ST platforms
+	     this field is used to configure the AMBA  bridge to generate more
+	     efficient STBus traffic.
+ o init/exit: callbacks used for calling a custom initialization;
+	     this is sometime necessary on some platforms (e.g. ST boxes)
+	     where the HW needs to have set some PIO lines or system cfg
+	     registers.  init/exit callbacks should not use or modify
+	     platform data.
+ o bsp_priv: another private pointer.
+ o has_gmac4: uses GMAC4 core.
+ o tso_en: Enables TSO (TCP Segmentation Offload) feature.
+
+For MDIO bus The we have:
+
+ struct stmmac_mdio_bus_data {
+	int (*phy_reset)(void *priv);
+	unsigned int phy_mask;
+	int *irqs;
+	int probed_phy_irq;
+ };
+
+Where:
+ o phy_reset: hook to reset the phy device attached to the bus.
+ o phy_mask: phy mask passed when register the MDIO bus within the driver.
+ o irqs: list of IRQs, one per PHY.
+ o probed_phy_irq: if irqs is NULL, use this for probed PHY.
+
+For DMA engine we have the following internal fields that should be
+tuned according to the HW capabilities.
+
+struct stmmac_dma_cfg {
+	int pbl;
+	int txpbl;
+	int rxpbl;
+	bool pblx8;
+	int fixed_burst;
+	int mixed_burst;
+	bool aal;
+};
+
+Where:
+ o pbl: Programmable Burst Length (tx and rx)
+ o txpbl: Transmit Programmable Burst Length. Only for GMAC and newer.
+	 If set, DMA tx will use this value rather than pbl.
+ o rxpbl: Receive Programmable Burst Length. Only for GMAC and newer.
+	 If set, DMA rx will use this value rather than pbl.
+ o pblx8: Enable 8xPBL (4xPBL for core rev < 3.50). Enabled by default.
+ o fixed_burst: program the DMA to use the fixed burst mode
+ o mixed_burst: program the DMA to use the mixed burst mode
+ o aal: Address-Aligned Beats
+
+---
+
+Below an example how the structures above are using on ST platforms.
+
+ static struct plat_stmmacenet_data stxYYY_ethernet_platform_data = {
+	.has_gmac = 0,
+	.enh_desc = 0,
+	.fix_mac_speed = stxYYY_ethernet_fix_mac_speed,
+				|
+				|-> to write an internal syscfg
+				|   on this platform when the
+				|   link speed changes from 10 to
+				|   100 and viceversa
+	.init = &stmmac_claim_resource,
+				|
+				|-> On ST SoC this calls own "PAD"
+				|   manager framework to claim
+				|   all the resources necessary
+				|   (GPIO ...). The .custom_cfg field
+				|   is used to pass a custom config.
+};
+
+Below the usage of the stmmac_mdio_bus_data: on this SoC, in fact,
+there are two MAC cores: one MAC is for MDIO Bus/PHY emulation
+with fixed_link support.
+
+static struct stmmac_mdio_bus_data stmmac1_mdio_bus = {
+	.phy_reset = phy_reset;
+		|
+		|-> function to provide the phy_reset on this board
+	.phy_mask = 0,
+};
+
+static struct fixed_phy_status stmmac0_fixed_phy_status = {
+	.link = 1,
+	.speed = 100,
+	.duplex = 1,
+};
+
+During the board's device_init we can configure the first
+MAC for fixed_link by calling:
+  fixed_phy_add(PHY_POLL, 1, &stmmac0_fixed_phy_status, -1);
+and the second one, with a real PHY device attached to the bus,
+by using the stmmac_mdio_bus_data structure (to provide the id, the
+reset procedure etc).
+
+Note that, starting from new chips, where it is available the HW capability
+register, many configurations are discovered at run-time for example to
+understand if EEE, HW csum, PTP, enhanced descriptor etc are actually
+available. As strategy adopted in this driver, the information from the HW
+capability register can replace what has been passed from the platform.
+
+4.10) Device-tree support.
+
+Please see the following document:
+	Documentation/devicetree/bindings/net/stmmac.txt
+
+4.11) This is a summary of the content of some relevant files:
+ o stmmac_main.c: implements the main network device driver;
+ o stmmac_mdio.c: provides MDIO functions;
+ o stmmac_pci: this is the PCI driver;
+ o stmmac_platform.c: this the platform driver (OF supported);
+ o stmmac_ethtool.c: implements the ethtool support;
+ o stmmac.h: private driver structure;
+ o common.h: common definitions and VFTs;
+ o mmc_core.c/mmc.h: Management MAC Counters;
+ o stmmac_hwtstamp.c: HW timestamp support for PTP;
+ o stmmac_ptp.c: PTP 1588 clock;
+ o stmmac_pcs.h: Physical Coding Sublayer common implementation;
+ o dwmac-<XXX>.c: these are for the platform glue-logic file; e.g. dwmac-sti.c
+   for STMicroelectronics SoCs.
+
+- GMAC 3.x
+ o descs.h: descriptor structure definitions;
+ o dwmac1000_core.c: dwmac GiGa core functions;
+ o dwmac1000_dma.c: dma functions for the GMAC chip;
+ o dwmac1000.h: specific header file for the dwmac GiGa;
+ o dwmac100_core: dwmac 100 core code;
+ o dwmac100_dma.c: dma functions for the dwmac 100 chip;
+ o dwmac1000.h: specific header file for the MAC;
+ o dwmac_lib.c: generic DMA functions;
+ o enh_desc.c: functions for handling enhanced descriptors;
+ o norm_desc.c: functions for handling normal descriptors;
+ o chain_mode.c/ring_mode.c:: functions to manage RING/CHAINED modes;
+
+- GMAC4.x generation
+ o dwmac4_core.c: dwmac GMAC4.x core functions;
+ o dwmac4_desc.c: functions for handling GMAC4.x descriptors;
+ o dwmac4_descs.h: descriptor definitions;
+ o dwmac4_dma.c: dma functions for the GMAC4.x chip;
+ o dwmac4_dma.h: dma definitions for the GMAC4.x chip;
+ o dwmac4.h: core definitions for the GMAC4.x chip;
+ o dwmac4_lib.c: generic GMAC4.x functions;
+
+4.12) TSO support (GMAC4.x)
+
+TSO (Tcp Segmentation Offload) feature is supported by GMAC 4.x chip family.
+When a packet is sent through TCP protocol, the TCP stack ensures that
+the SKB provided to the low level driver (stmmac in our case) matches with
+the maximum frame len (IP header + TCP header + payload <= 1500 bytes (for
+MTU set to 1500)). It means that if an application using TCP want to send a
+packet which will have a length (after adding headers) > 1514 the packet
+will be split in several TCP packets: The data payload is split and headers
+(TCP/IP ..) are added. It is done by software.
+
+When TSO is enabled, the TCP stack doesn't care about the maximum frame
+length and provide SKB packet to stmmac as it is. The GMAC IP will have to
+perform the segmentation by it self to match with maximum frame length.
+
+This feature can be enabled in device tree through "snps,tso" entry.
+
+5) Debug Information
+
+The driver exports many information i.e. internal statistics,
+debug information, MAC and DMA registers etc.
+
+These can be read in several ways depending on the
+type of the information actually needed.
+
+For example a user can be use the ethtool support
+to get statistics: e.g. using: ethtool -S ethX
+(that shows the Management counters (MMC) if supported)
+or sees the MAC/DMA registers: e.g. using: ethtool -d ethX
+
+Compiling the Kernel with CONFIG_DEBUG_FS the driver will export the following
+debugfs entries:
+
+/sys/kernel/debug/stmmaceth/descriptors_status
+  To show the DMA TX/RX descriptor rings
+
+Developer can also use the "debug" module parameter to get further debug
+information (please see: NETIF Msg Level).
+
+6) Energy Efficient Ethernet
+
+Energy Efficient Ethernet(EEE) enables IEEE 802.3 MAC sublayer along
+with a family of Physical layer to operate in the Low power Idle(LPI)
+mode. The EEE mode supports the IEEE 802.3 MAC operation at 100Mbps,
+1000Mbps & 10Gbps.
+
+The LPI mode allows power saving by switching off parts of the
+communication device functionality when there is no data to be
+transmitted & received. The system on both the side of the link can
+disable some functionalities & save power during the period of low-link
+utilization. The MAC controls whether the system should enter or exit
+the LPI mode & communicate this to PHY.
+
+As soon as the interface is opened, the driver verifies if the EEE can
+be supported. This is done by looking at both the DMA HW capability
+register and the PHY devices MCD registers.
+To enter in Tx LPI mode the driver needs to have a software timer
+that enable and disable the LPI mode when there is nothing to be
+transmitted.
+
+7) Precision Time Protocol (PTP)
+The driver supports the IEEE 1588-2002, Precision Time Protocol (PTP),
+which enables precise synchronization of clocks in measurement and
+control systems implemented with technologies such as network
+communication.
+
+In addition to the basic timestamp features mentioned in IEEE 1588-2002
+Timestamps, new GMAC cores support the advanced timestamp features.
+IEEE 1588-2008 that can be enabled when configure the Kernel.
+
+8) SGMII/RGMII support
+New GMAC devices provide own way to manage RGMII/SGMII.
+This information is available at run-time by looking at the
+HW capability register. This means that the stmmac can manage
+auto-negotiation and link status w/o using the PHYLIB stuff.
+In fact, the HW provides a subset of extended registers to
+restart the ANE, verify Full/Half duplex mode and Speed.
+Thanks to these registers, it is possible to look at the
+Auto-negotiated Link Parter Ability.
diff --git a/Documentation/networking/device_drivers/ti/cpsw.txt b/Documentation/networking/device_drivers/ti/cpsw.txt
new file mode 100644
index 000000000000..d4d4c0751a09
--- /dev/null
+++ b/Documentation/networking/device_drivers/ti/cpsw.txt
@@ -0,0 +1,541 @@
+* Texas Instruments CPSW ethernet driver
+
+Multiqueue & CBS & MQPRIO
+=====================================================================
+=====================================================================
+
+The cpsw has 3 CBS shapers for each external ports. This document
+describes MQPRIO and CBS Qdisc offload configuration for cpsw driver
+based on examples. It potentially can be used in audio video bridging
+(AVB) and time sensitive networking (TSN).
+
+The following examples were tested on AM572x EVM and BBB boards.
+
+Test setup
+==========
+
+Under consideration two examples with AM572x EVM running cpsw driver
+in dual_emac mode.
+
+Several prerequisites:
+- TX queues must be rated starting from txq0 that has highest priority
+- Traffic classes are used starting from 0, that has highest priority
+- CBS shapers should be used with rated queues
+- The bandwidth for CBS shapers has to be set a little bit more then
+  potential incoming rate, thus, rate of all incoming tx queues has
+  to be a little less
+- Real rates can differ, due to discreetness
+- Map skb-priority to txq is not enough, also skb-priority to l2 prio
+  map has to be created with ip or vconfig tool
+- Any l2/socket prio (0 - 7) for classes can be used, but for
+  simplicity default values are used: 3 and 2
+- only 2 classes tested: A and B, but checked and can work with more,
+  maximum allowed 4, but only for 3 rate can be set.
+
+Test setup for examples
+=======================
+                                    +-------------------------------+
+                                    |--+                            |
+                                    |  |      Workstation0          |
+                                    |E |  MAC 18:03:73:66:87:42     |
++-----------------------------+  +--|t |                            |
+|                    | 1  | E |  |  |h |./tsn_listener -d \         |
+|  Target board:     | 0  | t |--+  |0 | 18:03:73:66:87:42 -i eth0 \|
+|  AM572x EVM        | 0  | h |     |  | -s 1500                    |
+|                    | 0  | 0 |     |--+                            |
+|  Only 2 classes:   |Mb  +---|     +-------------------------------+
+|  class A, class B  |        |
+|                    |    +---|     +-------------------------------+
+|                    | 1  | E |     |--+                            |
+|                    | 0  | t |     |  |      Workstation1          |
+|                    | 0  | h |--+  |E |  MAC 20:cf:30:85:7d:fd     |
+|                    |Mb  | 1 |  +--|t |                            |
++-----------------------------+     |h |./tsn_listener -d \         |
+                                    |0 | 20:cf:30:85:7d:fd -i eth0 \|
+                                    |  | -s 1500                    |
+                                    |--+                            |
+                                    +-------------------------------+
+
+*********************************************************************
+*********************************************************************
+*********************************************************************
+Example 1: One port tx AVB configuration scheme for target board
+----------------------------------------------------------------------
+(prints and scheme for AM572x evm, applicable for single port boards)
+
+tc - traffic class
+txq - transmit queue
+p - priority
+f - fifo (cpsw fifo)
+S - shaper configured
+
++------------------------------------------------------------------+ u
+| +---------------+  +---------------+  +------+ +------+          | s
+| |               |  |               |  |      | |      |          | e
+| | App 1         |  | App 2         |  | Apps | | Apps |          | r
+| | Class A       |  | Class B       |  | Rest | | Rest |          |
+| | Eth0          |  | Eth0          |  | Eth0 | | Eth1 |          | s
+| | VLAN100       |  | VLAN100       |  |   |  | |   |  |          | p
+| | 40 Mb/s       |  | 20 Mb/s       |  |   |  | |   |  |          | a
+| | SO_PRIORITY=3 |  | SO_PRIORITY=2 |  |   |  | |   |  |          | c
+| |   |           |  |   |           |  |   |  | |   |  |          | e
+| +---|-----------+  +---|-----------+  +---|--+ +---|--+          |
++-----|------------------|------------------|--------|-------------+
+    +-+     +------------+                  |        |
+    |       |             +-----------------+     +--+
+    |       |             |                       |
++---|-------|-------------|-----------------------|----------------+
+| +----+ +----+ +----+ +----+                   +----+             |
+| | p3 | | p2 | | p1 | | p0 |                   | p0 |             | k
+| \    / \    / \    / \    /                   \    /             | e
+|  \  /   \  /   \  /   \  /                     \  /              | r
+|   \/     \/     \/     \/                       \/               | n
+|    |     |             |                        |                | e
+|    |     |       +-----+                        |                | l
+|    |     |       |                              |                |
+| +----+ +----+ +----+                          +----+             | s
+| |tc0 | |tc1 | |tc2 |                          |tc0 |             | p
+| \    / \    / \    /                          \    /             | a
+|  \  /   \  /   \  /                            \  /              | c
+|   \/     \/     \/                              \/               | e
+|   |      |       +-----+                        |                |
+|   |      |       |     |                        |                |
+|   |      |       |     |                        |                |
+|   |      |       |     |                        |                |
+| +----+ +----+ +----+ +----+                   +----+             |
+| |txq0| |txq1| |txq2| |txq3|                   |txq4|             |
+| \    / \    / \    / \    /                   \    /             |
+|  \  /   \  /   \  /   \  /                     \  /              |
+|   \/     \/     \/     \/                       \/               |
+| +-|------|------|------|--+                  +--|--------------+ |
+| | |      |      |      |  | Eth0.100         |  |     Eth1     | |
++---|------|------|------|------------------------|----------------+
+    |      |      |      |                        |
+    p      p      p      p                        |
+    3      2      0-1, 4-7  <- L2 priority        |
+    |      |      |      |                        |
+    |      |      |      |                        |
++---|------|------|------|------------------------|----------------+
+|   |      |      |      |             |----------+                |
+| +----+ +----+ +----+ +----+       +----+                         |
+| |dma7| |dma6| |dma5| |dma4|       |dma3|                         |
+| \    / \    / \    / \    /       \    /                         | c
+|  \S /   \S /   \  /   \  /         \  /                          | p
+|   \/     \/     \/     \/           \/                           | s
+|   |      |      | +-----            |                            | w
+|   |      |      | |                 |                            |
+|   |      |      | |                 |                            | d
+| +----+ +----+ +----+p            p+----+                         | r
+| |    | |    | |    |o            o|    |                         | i
+| | f3 | | f2 | | f0 |r            r| f0 |                         | v
+| |tc0 | |tc1 | |tc2 |t            t|tc0 |                         | e
+| \CBS / \CBS / \CBS /1            2\CBS /                         | r
+|  \S /   \S /   \  /                \  /                          |
+|   \/     \/     \/                  \/                           |
++------------------------------------------------------------------+
+========================================Eth==========================>
+
+1)
+// Add 4 tx queues, for interface Eth0, and 1 tx queue for Eth1
+$ ethtool -L eth0 rx 1 tx 5
+rx unmodified, ignoring
+
+2)
+// Check if num of queues is set correctly:
+$ ethtool -l eth0
+Channel parameters for eth0:
+Pre-set maximums:
+RX:             8
+TX:             8
+Other:          0
+Combined:       0
+Current hardware settings:
+RX:             1
+TX:             5
+Other:          0
+Combined:       0
+
+3)
+// TX queues must be rated starting from 0, so set bws for tx0 and tx1
+// Set rates 40 and 20 Mb/s appropriately.
+// Pay attention, real speed can differ a bit due to discreetness.
+// Leave last 2 tx queues not rated.
+$ echo 40 > /sys/class/net/eth0/queues/tx-0/tx_maxrate
+$ echo 20 > /sys/class/net/eth0/queues/tx-1/tx_maxrate
+
+4)
+// Check maximum rate of tx (cpdma) queues:
+$ cat /sys/class/net/eth0/queues/tx-*/tx_maxrate
+40
+20
+0
+0
+0
+
+5)
+// Map skb->priority to traffic class:
+// 3pri -> tc0, 2pri -> tc1, (0,1,4-7)pri -> tc2
+// Map traffic class to transmit queue:
+// tc0 -> txq0, tc1 -> txq1, tc2 -> (txq2, txq3)
+$ tc qdisc replace dev eth0 handle 100: parent root mqprio num_tc 3 \
+map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 1
+
+5a)
+// As two interface sharing same set of tx queues, assign all traffic
+// coming to interface Eth1 to separate queue in order to not mix it
+// with traffic from interface Eth0, so use separate txq to send
+// packets to Eth1, so all prio -> tc0 and tc0 -> txq4
+// Here hw 0, so here still default configuration for eth1 in hw
+$ tc qdisc replace dev eth1 handle 100: parent root mqprio num_tc 1 \
+map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@4 hw 0
+
+6)
+// Check classes settings
+$ tc -g class show dev eth0
++---(100:ffe2) mqprio
+|    +---(100:3) mqprio
+|    +---(100:4) mqprio
+|
++---(100:ffe1) mqprio
+|    +---(100:2) mqprio
+|
++---(100:ffe0) mqprio
+     +---(100:1) mqprio
+
+$ tc -g class show dev eth1
++---(100:ffe0) mqprio
+     +---(100:5) mqprio
+
+7)
+// Set rate for class A - 41 Mbit (tc0, txq0) using CBS Qdisc
+// Set it +1 Mb for reserve (important!)
+// here only idle slope is important, others arg are ignored
+// Pay attention, real speed can differ a bit due to discreetness
+$ tc qdisc add dev eth0 parent 100:1 cbs locredit -1438 \
+hicredit 62 sendslope -959000 idleslope 41000 offload 1
+net eth0: set FIFO3 bw = 50
+
+8)
+// Set rate for class B - 21 Mbit (tc1, txq1) using CBS Qdisc:
+// Set it +1 Mb for reserve (important!)
+$ tc qdisc add dev eth0 parent 100:2 cbs locredit -1468 \
+hicredit 65 sendslope -979000 idleslope 21000 offload 1
+net eth0: set FIFO2 bw = 30
+
+9)
+// Create vlan 100 to map sk->priority to vlan qos
+$ ip link add link eth0 name eth0.100 type vlan id 100
+8021q: 802.1Q VLAN Support v1.8
+8021q: adding VLAN 0 to HW filter on device eth0
+8021q: adding VLAN 0 to HW filter on device eth1
+net eth0: Adding vlanid 100 to vlan filter
+
+10)
+// Map skb->priority to L2 prio, 1 to 1
+$ ip link set eth0.100 type vlan \
+egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+11)
+// Check egress map for vlan 100
+$ cat /proc/net/vlan/eth0.100
+[...]
+INGRESS priority mappings: 0:0  1:0  2:0  3:0  4:0  5:0  6:0 7:0
+EGRESS priority mappings: 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+12)
+// Run your appropriate tools with socket option "SO_PRIORITY"
+// to 3 for class A and/or to 2 for class B
+// (I took at https://www.spinics.net/lists/netdev/msg460869.html)
+./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p3 -s 1500&
+./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p2 -s 1500&
+
+13)
+// run your listener on workstation (should be in same vlan)
+// (I took at https://www.spinics.net/lists/netdev/msg460869.html)
+./tsn_listener -d 18:03:73:66:87:42 -i enp5s0 -s 1500
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39000 kbps
+
+14)
+// Restore default configuration if needed
+$ ip link del eth0.100
+$ tc qdisc del dev eth1 root
+$ tc qdisc del dev eth0 root
+net eth0: Prev FIFO2 is shaped
+net eth0: set FIFO3 bw = 0
+net eth0: set FIFO2 bw = 0
+$ ethtool -L eth0 rx 1 tx 1
+
+*********************************************************************
+*********************************************************************
+*********************************************************************
+Example 2: Two port tx AVB configuration scheme for target board
+----------------------------------------------------------------------
+(prints and scheme for AM572x evm, for dual emac boards only)
+
++------------------------------------------------------------------+ u
+| +----------+  +----------+  +------+  +----------+  +----------+ | s
+| |          |  |          |  |      |  |          |  |          | | e
+| | App 1    |  | App 2    |  | Apps |  | App 3    |  | App 4    | | r
+| | Class A  |  | Class B  |  | Rest |  | Class B  |  | Class A  | |
+| | Eth0     |  | Eth0     |  |   |  |  | Eth1     |  | Eth1     | | s
+| | VLAN100  |  | VLAN100  |  |   |  |  | VLAN100  |  | VLAN100  | | p
+| | 40 Mb/s  |  | 20 Mb/s  |  |   |  |  | 10 Mb/s  |  | 30 Mb/s  | | a
+| | SO_PRI=3 |  | SO_PRI=2 |  |   |  |  | SO_PRI=3 |  | SO_PRI=2 | | c
+| |   |      |  |   |      |  |   |  |  |   |      |  |   |      | | e
+| +---|------+  +---|------+  +---|--+  +---|------+  +---|------+ |
++-----|-------------|-------------|---------|-------------|--------+
+    +-+     +-------+             |         +----------+  +----+
+    |       |             +-------+------+             |       |
+    |       |             |              |             |       |
++---|-------|-------------|--------------|-------------|-------|---+
+| +----+ +----+ +----+ +----+          +----+ +----+ +----+ +----+ |
+| | p3 | | p2 | | p1 | | p0 |          | p0 | | p1 | | p2 | | p3 | | k
+| \    / \    / \    / \    /          \    / \    / \    / \    / | e
+|  \  /   \  /   \  /   \  /            \  /   \  /   \  /   \  /  | r
+|   \/     \/     \/     \/              \/     \/     \/     \/   | n
+|   |      |             |                |             |      |   | e
+|   |      |        +----+                +----+        |      |   | l
+|   |      |        |                          |        |      |   |
+| +----+ +----+ +----+                        +----+ +----+ +----+ | s
+| |tc0 | |tc1 | |tc2 |                        |tc2 | |tc1 | |tc0 | | p
+| \    / \    / \    /                        \    / \    / \    / | a
+|  \  /   \  /   \  /                          \  /   \  /   \  /  | c
+|   \/     \/     \/                            \/     \/     \/   | e
+|   |      |       +-----+                +-----+      |       |   |
+|   |      |       |     |                |     |      |       |   |
+|   |      |       |     |                |     |      |       |   |
+|   |      |       |     |    E      E    |     |      |       |   |
+| +----+ +----+ +----+ +----+ t      t +----+ +----+ +----+ +----+ |
+| |txq0| |txq1| |txq4| |txq5| h      h |txq6| |txq7| |txq3| |txq2| |
+| \    / \    / \    / \    / 0      1 \    / \    / \    / \    / |
+|  \  /   \  /   \  /   \  /  .      .  \  /   \  /   \  /   \  /  |
+|   \/     \/     \/     \/   1      1   \/     \/     \/     \/   |
+| +-|------|------|------|--+ 0      0 +-|------|------|------|--+ |
+| | |      |      |      |  | 0      0 | |      |      |      |  | |
++---|------|------|------|---------------|------|------|------|----+
+    |      |      |      |               |      |      |      |
+    p      p      p      p               p      p      p      p
+    3      2      0-1, 4-7   <-L2 pri->  0-1, 4-7      2      3
+    |      |      |      |               |      |      |      |
+    |      |      |      |               |      |      |      |
++---|------|------|------|---------------|------|------|------|----+
+|   |      |      |      |               |      |      |      |    |
+| +----+ +----+ +----+ +----+          +----+ +----+ +----+ +----+ |
+| |dma7| |dma6| |dma3| |dma2|          |dma1| |dma0| |dma4| |dma5| |
+| \    / \    / \    / \    /          \    / \    / \    / \    / | c
+|  \S /   \S /   \  /   \  /            \  /   \  /   \S /   \S /  | p
+|   \/     \/     \/     \/              \/     \/     \/     \/   | s
+|   |      |      | +-----                |      |      |      |   | w
+|   |      |      | |                     +----+ |      |      |   |
+|   |      |      | |                          | |      |      |   | d
+| +----+ +----+ +----+p                      p+----+ +----+ +----+ | r
+| |    | |    | |    |o                      o|    | |    | |    | | i
+| | f3 | | f2 | | f0 |r        CPSW          r| f3 | | f2 | | f0 | | v
+| |tc0 | |tc1 | |tc2 |t                      t|tc0 | |tc1 | |tc2 | | e
+| \CBS / \CBS / \CBS /1                      2\CBS / \CBS / \CBS / | r
+|  \S /   \S /   \  /                          \S /   \S /   \  /  |
+|   \/     \/     \/                            \/     \/     \/   |
++------------------------------------------------------------------+
+========================================Eth==========================>
+
+1)
+// Add 8 tx queues, for interface Eth0, but they are common, so are accessed
+// by two interfaces Eth0 and Eth1.
+$ ethtool -L eth1 rx 1 tx 8
+rx unmodified, ignoring
+
+2)
+// Check if num of queues is set correctly:
+$ ethtool -l eth0
+Channel parameters for eth0:
+Pre-set maximums:
+RX:             8
+TX:             8
+Other:          0
+Combined:       0
+Current hardware settings:
+RX:             1
+TX:             8
+Other:          0
+Combined:       0
+
+3)
+// TX queues must be rated starting from 0, so set bws for tx0 and tx1 for Eth0
+// and for tx2 and tx3 for Eth1. That is, rates 40 and 20 Mb/s appropriately
+// for Eth0 and 30 and 10 Mb/s for Eth1.
+// Real speed can differ a bit due to discreetness
+// Leave last 4 tx queues as not rated
+$ echo 40 > /sys/class/net/eth0/queues/tx-0/tx_maxrate
+$ echo 20 > /sys/class/net/eth0/queues/tx-1/tx_maxrate
+$ echo 30 > /sys/class/net/eth1/queues/tx-2/tx_maxrate
+$ echo 10 > /sys/class/net/eth1/queues/tx-3/tx_maxrate
+
+4)
+// Check maximum rate of tx (cpdma) queues:
+$ cat /sys/class/net/eth0/queues/tx-*/tx_maxrate
+40
+20
+30
+10
+0
+0
+0
+0
+
+5)
+// Map skb->priority to traffic class for Eth0:
+// 3pri -> tc0, 2pri -> tc1, (0,1,4-7)pri -> tc2
+// Map traffic class to transmit queue:
+// tc0 -> txq0, tc1 -> txq1, tc2 -> (txq4, txq5)
+$ tc qdisc replace dev eth0 handle 100: parent root mqprio num_tc 3 \
+map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@4 hw 1
+
+6)
+// Check classes settings
+$ tc -g class show dev eth0
++---(100:ffe2) mqprio
+|    +---(100:5) mqprio
+|    +---(100:6) mqprio
+|
++---(100:ffe1) mqprio
+|    +---(100:2) mqprio
+|
++---(100:ffe0) mqprio
+     +---(100:1) mqprio
+
+7)
+// Set rate for class A - 41 Mbit (tc0, txq0) using CBS Qdisc for Eth0
+// here only idle slope is important, others ignored
+// Real speed can differ a bit due to discreetness
+$ tc qdisc add dev eth0 parent 100:1 cbs locredit -1470 \
+hicredit 62 sendslope -959000 idleslope 41000 offload 1
+net eth0: set FIFO3 bw = 50
+
+8)
+// Set rate for class B - 21 Mbit (tc1, txq1) using CBS Qdisc for Eth0
+$ tc qdisc add dev eth0 parent 100:2 cbs locredit -1470 \
+hicredit 65 sendslope -979000 idleslope 21000 offload 1
+net eth0: set FIFO2 bw = 30
+
+9)
+// Create vlan 100 to map sk->priority to vlan qos for Eth0
+$ ip link add link eth0 name eth0.100 type vlan id 100
+net eth0: Adding vlanid 100 to vlan filter
+
+10)
+// Map skb->priority to L2 prio for Eth0.100, one to one
+$ ip link set eth0.100 type vlan \
+egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+11)
+// Check egress map for vlan 100
+$ cat /proc/net/vlan/eth0.100
+[...]
+INGRESS priority mappings: 0:0  1:0  2:0  3:0  4:0  5:0  6:0 7:0
+EGRESS priority mappings: 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+12)
+// Map skb->priority to traffic class for Eth1:
+// 3pri -> tc0, 2pri -> tc1, (0,1,4-7)pri -> tc2
+// Map traffic class to transmit queue:
+// tc0 -> txq2, tc1 -> txq3, tc2 -> (txq6, txq7)
+$ tc qdisc replace dev eth1 handle 100: parent root mqprio num_tc 3 \
+map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@2 1@3 2@6 hw 1
+
+13)
+// Check classes settings
+$ tc -g class show dev eth1
++---(100:ffe2) mqprio
+|    +---(100:7) mqprio
+|    +---(100:8) mqprio
+|
++---(100:ffe1) mqprio
+|    +---(100:4) mqprio
+|
++---(100:ffe0) mqprio
+     +---(100:3) mqprio
+
+14)
+// Set rate for class A - 31 Mbit (tc0, txq2) using CBS Qdisc for Eth1
+// here only idle slope is important, others ignored, but calculated
+// for interface speed - 100Mb for eth1 port.
+// Set it +1 Mb for reserve (important!)
+$ tc qdisc add dev eth1 parent 100:3 cbs locredit -1035 \
+hicredit 465 sendslope -69000 idleslope 31000 offload 1
+net eth1: set FIFO3 bw = 31
+
+15)
+// Set rate for class B - 11 Mbit (tc1, txq3) using CBS Qdisc for Eth1
+// Set it +1 Mb for reserve (important!)
+$ tc qdisc add dev eth1 parent 100:4 cbs locredit -1335 \
+hicredit 405 sendslope -89000 idleslope 11000 offload 1
+net eth1: set FIFO2 bw = 11
+
+16)
+// Create vlan 100 to map sk->priority to vlan qos for Eth1
+$ ip link add link eth1 name eth1.100 type vlan id 100
+net eth1: Adding vlanid 100 to vlan filter
+
+17)
+// Map skb->priority to L2 prio for Eth1.100, one to one
+$ ip link set eth1.100 type vlan \
+egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+18)
+// Check egress map for vlan 100
+$ cat /proc/net/vlan/eth1.100
+[...]
+INGRESS priority mappings: 0:0  1:0  2:0  3:0  4:0  5:0  6:0 7:0
+EGRESS priority mappings: 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+19)
+// Run appropriate tools with socket option "SO_PRIORITY" to 3
+// for class A and to 2 for class B. For both interfaces
+./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p2 -s 1500&
+./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p3 -s 1500&
+./tsn_talker -d 20:cf:30:85:7d:fd -i eth1.100 -p2 -s 1500&
+./tsn_talker -d 20:cf:30:85:7d:fd -i eth1.100 -p3 -s 1500&
+
+20)
+// run your listener on workstation (should be in same vlan)
+// (I took at https://www.spinics.net/lists/netdev/msg460869.html)
+./tsn_listener -d 18:03:73:66:87:42 -i enp5s0 -s 1500
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39000 kbps
+
+21)
+// Restore default configuration if needed
+$ ip link del eth1.100
+$ ip link del eth0.100
+$ tc qdisc del dev eth1 root
+net eth1: Prev FIFO2 is shaped
+net eth1: set FIFO3 bw = 0
+net eth1: set FIFO2 bw = 0
+$ tc qdisc del dev eth0 root
+net eth0: Prev FIFO2 is shaped
+net eth0: set FIFO3 bw = 0
+net eth0: set FIFO2 bw = 0
+$ ethtool -L eth0 rx 1 tx 1
diff --git a/Documentation/networking/device_drivers/ti/tlan.txt b/Documentation/networking/device_drivers/ti/tlan.txt
new file mode 100644
index 000000000000..34550dfcef74
--- /dev/null
+++ b/Documentation/networking/device_drivers/ti/tlan.txt
@@ -0,0 +1,117 @@
+(C) 1997-1998 Caldera, Inc.
+(C) 1998 James Banks
+(C) 1999-2001 Torben Mathiasen <tmm@image.dk, torben.mathiasen@compaq.com>
+
+For driver information/updates visit http://www.compaq.com
+
+
+TLAN driver for Linux, version 1.14a
+README
+
+
+I.  Supported Devices.
+
+    Only PCI devices will work with this driver.
+
+    Supported:
+    Vendor ID	Device ID	Name
+    0e11	ae32		Compaq Netelligent 10/100 TX PCI UTP
+    0e11	ae34		Compaq Netelligent 10 T PCI UTP
+    0e11	ae35		Compaq Integrated NetFlex 3/P
+    0e11	ae40		Compaq Netelligent Dual 10/100 TX PCI UTP
+    0e11	ae43		Compaq Netelligent Integrated 10/100 TX UTP
+    0e11	b011		Compaq Netelligent 10/100 TX Embedded UTP
+    0e11	b012		Compaq Netelligent 10 T/2 PCI UTP/Coax
+    0e11	b030		Compaq Netelligent 10/100 TX UTP
+    0e11	f130		Compaq NetFlex 3/P
+    0e11	f150		Compaq NetFlex 3/P
+    108d	0012		Olicom OC-2325	
+    108d	0013		Olicom OC-2183
+    108d	0014		Olicom OC-2326	
+
+
+    Caveats:
+    
+    I am not sure if 100BaseTX daughterboards (for those cards which
+    support such things) will work.  I haven't had any solid evidence
+    either way.
+
+    However, if a card supports 100BaseTx without requiring an add
+    on daughterboard, it should work with 100BaseTx.
+
+    The "Netelligent 10 T/2 PCI UTP/Coax" (b012) device is untested,
+    but I do not expect any problems.
+    
+
+II.   Driver Options
+	1. You can append debug=x to the end of the insmod line to get
+           debug messages, where x is a bit field where the bits mean
+	   the following:
+	   
+	   0x01		Turn on general debugging messages.
+	   0x02		Turn on receive debugging messages.
+	   0x04		Turn on transmit debugging messages.
+	   0x08		Turn on list debugging messages.
+
+	2. You can append aui=1 to the end of the insmod line to cause
+           the adapter to use the AUI interface instead of the 10 Base T
+           interface.  This is also what to do if you want to use the BNC
+	   connector on a TLAN based device.  (Setting this option on a
+	   device that does not have an AUI/BNC connector will probably
+	   cause it to not function correctly.)
+
+	3. You can set duplex=1 to force half duplex, and duplex=2 to
+	   force full duplex.
+
+	4. You can set speed=10 to force 10Mbs operation, and speed=100
+	   to force 100Mbs operation. (I'm not sure what will happen
+	   if a card which only supports 10Mbs is forced into 100Mbs
+	   mode.)
+
+	5. You have to use speed=X duplex=Y together now. If you just
+	   do "insmod tlan.o speed=100" the driver will do Auto-Neg.
+	   To force a 10Mbps Half-Duplex link do "insmod tlan.o speed=10 
+	   duplex=1".
+
+	6. If the driver is built into the kernel, you can use the 3rd
+	   and 4th parameters to set aui and debug respectively.  For
+	   example:
+
+	   ether=0,0,0x1,0x7,eth0
+
+	   This sets aui to 0x1 and debug to 0x7, assuming eth0 is a
+	   supported TLAN device.
+
+	   The bits in the third byte are assigned as follows:
+
+		0x01 = aui
+		0x02 = use half duplex
+		0x04 = use full duplex
+		0x08 = use 10BaseT
+		0x10 = use 100BaseTx
+
+	   You also need to set both speed and duplex settings when forcing
+	   speeds with kernel-parameters. 
+	   ether=0,0,0x12,0,eth0 will force link to 100Mbps Half-Duplex.
+
+	7. If you have more than one tlan adapter in your system, you can
+	   use the above options on a per adapter basis. To force a 100Mbit/HD
+	   link with your eth1 adapter use:
+	   
+	   insmod tlan speed=0,100 duplex=0,1
+
+	   Now eth0 will use auto-neg and eth1 will be forced to 100Mbit/HD.
+	   Note that the tlan driver supports a maximum of 8 adapters.
+
+
+III.  Things to try if you have problems.
+	1. Make sure your card's PCI id is among those listed in
+	   section I, above.
+	2. Make sure routing is correct.
+	3. Try forcing different speed/duplex settings
+
+
+There is also a tlan mailing list which you can join by sending "subscribe tlan"
+in the body of an email to majordomo@vuser.vu.union.edu.
+There is also a tlan website at http://www.compaq.com
+
diff --git a/Documentation/networking/device_drivers/toshiba/spider_net.txt b/Documentation/networking/device_drivers/toshiba/spider_net.txt
new file mode 100644
index 000000000000..b0b75f8463b3
--- /dev/null
+++ b/Documentation/networking/device_drivers/toshiba/spider_net.txt
@@ -0,0 +1,204 @@
+
+            The Spidernet Device Driver
+            ===========================
+
+Written by Linas Vepstas <linas@austin.ibm.com>
+
+Version of 7 June 2007
+
+Abstract
+========
+This document sketches the structure of portions of the spidernet
+device driver in the Linux kernel tree. The spidernet is a gigabit
+ethernet device built into the Toshiba southbridge commonly used
+in the SONY Playstation 3 and the IBM QS20 Cell blade.
+
+The Structure of the RX Ring.
+=============================
+The receive (RX) ring is a circular linked list of RX descriptors,
+together with three pointers into the ring that are used to manage its
+contents.
+
+The elements of the ring are called "descriptors" or "descrs"; they
+describe the received data. This includes a pointer to a buffer
+containing the received data, the buffer size, and various status bits.
+
+There are three primary states that a descriptor can be in: "empty",
+"full" and "not-in-use".  An "empty" or "ready" descriptor is ready
+to receive data from the hardware. A "full" descriptor has data in it,
+and is waiting to be emptied and processed by the OS. A "not-in-use"
+descriptor is neither empty or full; it is simply not ready. It may
+not even have a data buffer in it, or is otherwise unusable.
+
+During normal operation, on device startup, the OS (specifically, the
+spidernet device driver) allocates a set of RX descriptors and RX
+buffers. These are all marked "empty", ready to receive data. This
+ring is handed off to the hardware, which sequentially fills in the
+buffers, and marks them "full". The OS follows up, taking the full
+buffers, processing them, and re-marking them empty.
+
+This filling and emptying is managed by three pointers, the "head"
+and "tail" pointers, managed by the OS, and a hardware current
+descriptor pointer (GDACTDPA). The GDACTDPA points at the descr
+currently being filled. When this descr is filled, the hardware
+marks it full, and advances the GDACTDPA by one.  Thus, when there is
+flowing RX traffic, every descr behind it should be marked "full",
+and everything in front of it should be "empty".  If the hardware
+discovers that the current descr is not empty, it will signal an
+interrupt, and halt processing.
+
+The tail pointer tails or trails the hardware pointer. When the
+hardware is ahead, the tail pointer will be pointing at a "full"
+descr. The OS will process this descr, and then mark it "not-in-use",
+and advance the tail pointer.  Thus, when there is flowing RX traffic,
+all of the descrs in front of the tail pointer should be "full", and
+all of those behind it should be "not-in-use". When RX traffic is not
+flowing, then the tail pointer can catch up to the hardware pointer.
+The OS will then note that the current tail is "empty", and halt
+processing.
+
+The head pointer (somewhat mis-named) follows after the tail pointer.
+When traffic is flowing, then the head pointer will be pointing at
+a "not-in-use" descr. The OS will perform various housekeeping duties
+on this descr. This includes allocating a new data buffer and
+dma-mapping it so as to make it visible to the hardware. The OS will
+then mark the descr as "empty", ready to receive data. Thus, when there
+is flowing RX traffic, everything in front of the head pointer should
+be "not-in-use", and everything behind it should be "empty". If no
+RX traffic is flowing, then the head pointer can catch up to the tail
+pointer, at which point the OS will notice that the head descr is
+"empty", and it will halt processing.
+
+Thus, in an idle system, the GDACTDPA, tail and head pointers will
+all be pointing at the same descr, which should be "empty". All of the
+other descrs in the ring should be "empty" as well.
+
+The show_rx_chain() routine will print out the locations of the
+GDACTDPA, tail and head pointers. It will also summarize the contents
+of the ring, starting at the tail pointer, and listing the status
+of the descrs that follow.
+
+A typical example of the output, for a nearly idle system, might be
+
+net eth1: Total number of descrs=256
+net eth1: Chain tail located at descr=20
+net eth1: Chain head is at 20
+net eth1: HW curr desc (GDACTDPA) is at 21
+net eth1: Have 1 descrs with stat=x40800101
+net eth1: HW next desc (GDACNEXTDA) is at 22
+net eth1: Last 255 descrs with stat=xa0800000
+
+In the above, the hardware has filled in one descr, number 20. Both
+head and tail are pointing at 20, because it has not yet been emptied.
+Meanwhile, hw is pointing at 21, which is free.
+
+The "Have nnn decrs" refers to the descr starting at the tail: in this
+case, nnn=1 descr, starting at descr 20. The "Last nnn descrs" refers
+to all of the rest of the descrs, from the last status change. The "nnn"
+is a count of how many descrs have exactly the same status.
+
+The status x4... corresponds to "full" and status xa... corresponds
+to "empty". The actual value printed is RXCOMST_A.
+
+In the device driver source code, a different set of names are
+used for these same concepts, so that
+
+"empty" == SPIDER_NET_DESCR_CARDOWNED == 0xa
+"full"  == SPIDER_NET_DESCR_FRAME_END == 0x4
+"not in use" == SPIDER_NET_DESCR_NOT_IN_USE == 0xf
+
+
+The RX RAM full bug/feature
+===========================
+
+As long as the OS can empty out the RX buffers at a rate faster than
+the hardware can fill them, there is no problem. If, for some reason,
+the OS fails to empty the RX ring fast enough, the hardware GDACTDPA
+pointer will catch up to the head, notice the not-empty condition,
+ad stop. However, RX packets may still continue arriving on the wire.
+The spidernet chip can save some limited number of these in local RAM.
+When this local ram fills up, the spider chip will issue an interrupt
+indicating this (GHIINT0STS will show ERRINT, and the GRMFLLINT bit
+will be set in GHIINT1STS).  When the RX ram full condition occurs,
+a certain bug/feature is triggered that has to be specially handled.
+This section describes the special handling for this condition.
+
+When the OS finally has a chance to run, it will empty out the RX ring.
+In particular, it will clear the descriptor on which the hardware had
+stopped. However, once the hardware has decided that a certain
+descriptor is invalid, it will not restart at that descriptor; instead
+it will restart at the next descr. This potentially will lead to a
+deadlock condition, as the tail pointer will be pointing at this descr,
+which, from the OS point of view, is empty; the OS will be waiting for
+this descr to be filled. However, the hardware has skipped this descr,
+and is filling the next descrs. Since the OS doesn't see this, there
+is a potential deadlock, with the OS waiting for one descr to fill,
+while the hardware is waiting for a different set of descrs to become
+empty.
+
+A call to show_rx_chain() at this point indicates the nature of the
+problem. A typical print when the network is hung shows the following:
+
+net eth1: Spider RX RAM full, incoming packets might be discarded!
+net eth1: Total number of descrs=256
+net eth1: Chain tail located at descr=255
+net eth1: Chain head is at 255
+net eth1: HW curr desc (GDACTDPA) is at 0
+net eth1: Have 1 descrs with stat=xa0800000
+net eth1: HW next desc (GDACNEXTDA) is at 1
+net eth1: Have 127 descrs with stat=x40800101
+net eth1: Have 1 descrs with stat=x40800001
+net eth1: Have 126 descrs with stat=x40800101
+net eth1: Last 1 descrs with stat=xa0800000
+
+Both the tail and head pointers are pointing at descr 255, which is
+marked xa... which is "empty". Thus, from the OS point of view, there
+is nothing to be done. In particular, there is the implicit assumption
+that everything in front of the "empty" descr must surely also be empty,
+as explained in the last section. The OS is waiting for descr 255 to
+become non-empty, which, in this case, will never happen.
+
+The HW pointer is at descr 0. This descr is marked 0x4.. or "full".
+Since its already full, the hardware can do nothing more, and thus has
+halted processing. Notice that descrs 0 through 254 are all marked
+"full", while descr 254 and 255 are empty. (The "Last 1 descrs" is
+descr 254, since tail was at 255.) Thus, the system is deadlocked,
+and there can be no forward progress; the OS thinks there's nothing
+to do, and the hardware has nowhere to put incoming data.
+
+This bug/feature is worked around with the spider_net_resync_head_ptr()
+routine. When the driver receives RX interrupts, but an examination
+of the RX chain seems to show it is empty, then it is probable that
+the hardware has skipped a descr or two (sometimes dozens under heavy
+network conditions). The spider_net_resync_head_ptr() subroutine will
+search the ring for the next full descr, and the driver will resume
+operations there.  Since this will leave "holes" in the ring, there
+is also a spider_net_resync_tail_ptr() that will skip over such holes.
+
+As of this writing, the spider_net_resync() strategy seems to work very
+well, even under heavy network loads.
+
+
+The TX ring
+===========
+The TX ring uses a low-watermark interrupt scheme to make sure that
+the TX queue is appropriately serviced for large packet sizes.
+
+For packet sizes greater than about 1KBytes, the kernel can fill
+the TX ring quicker than the device can drain it. Once the ring
+is full, the netdev is stopped. When there is room in the ring,
+the netdev needs to be reawakened, so that more TX packets are placed
+in the ring. The hardware can empty the ring about four times per jiffy,
+so its not appropriate to wait for the poll routine to refill, since
+the poll routine runs only once per jiffy.  The low-watermark mechanism
+marks a descr about 1/4th of the way from the bottom of the queue, so
+that an interrupt is generated when the descr is processed. This
+interrupt wakes up the netdev, which can then refill the queue.
+For large packets, this mechanism generates a relatively small number
+of interrupts, about 1K/sec. For smaller packets, this will drop to zero
+interrupts, as the hardware can empty the queue faster than the kernel
+can fill it.
+
+
+ ======= END OF DOCUMENT ========
+
diff --git a/Documentation/networking/dl2k.txt b/Documentation/networking/dl2k.txt
deleted file mode 100644
index cba74f7a3abc..000000000000
--- a/Documentation/networking/dl2k.txt
+++ /dev/null
@@ -1,282 +0,0 @@
-
-    D-Link DL2000-based Gigabit Ethernet Adapter Installation
-    for Linux
-    May 23, 2002
-
-Contents
-========
- - Compatibility List
- - Quick Install
- - Compiling the Driver
- - Installing the Driver
- - Option parameter
- - Configuration Script Sample
- - Troubleshooting
-
-
-Compatibility List
-=================
-Adapter Support:
-
-D-Link DGE-550T Gigabit Ethernet Adapter.
-D-Link DGE-550SX Gigabit Ethernet Adapter.
-D-Link DL2000-based Gigabit Ethernet Adapter.
-
-
-The driver support Linux kernel 2.4.7 later. We had tested it
-on the environments below.
-
- . Red Hat v6.2 (update kernel to 2.4.7)
- . Red Hat v7.0 (update kernel to 2.4.7)
- . Red Hat v7.1 (kernel 2.4.7)
- . Red Hat v7.2 (kernel 2.4.7-10)
-
-
-Quick Install
-=============
-Install linux driver as following command:
-
-1. make all
-2. insmod dl2k.ko
-3. ifconfig eth0 up 10.xxx.xxx.xxx netmask 255.0.0.0
-		    ^^^^^^^^^^^^^^^\	    ^^^^^^^^\
-				    IP		     NETMASK
-Now eth0 should active, you can test it by "ping" or get more information by
-"ifconfig". If tested ok, continue the next step.
-
-4. cp dl2k.ko /lib/modules/`uname -r`/kernel/drivers/net
-5. Add the following line to /etc/modprobe.d/dl2k.conf:
-	alias eth0 dl2k
-6. Run depmod to updated module indexes.
-7. Run "netconfig" or "netconf" to create configuration script ifcfg-eth0
-   located at /etc/sysconfig/network-scripts or create it manually.
-   [see - Configuration Script Sample]
-8. Driver will automatically load and configure at next boot time.
-
-Compiling the Driver
-====================
-  In Linux, NIC drivers are most commonly configured as loadable modules.
-The approach of building a monolithic kernel has become obsolete. The driver
-can be compiled as part of a monolithic kernel, but is strongly discouraged.
-The remainder of this section assumes the driver is built as a loadable module.
-In the Linux environment, it is a good idea to rebuild the driver from the
-source instead of relying on a precompiled version. This approach provides
-better reliability since a precompiled driver might depend on libraries or
-kernel features that are not present in a given Linux installation.
-
-The 3 files necessary to build Linux device driver are dl2k.c, dl2k.h and
-Makefile. To compile, the Linux installation must include the gcc compiler,
-the kernel source, and the kernel headers. The Linux driver supports Linux
-Kernels 2.4.7. Copy the files to a directory and enter the following command
-to compile and link the driver:
-
-CD-ROM drive
-------------
-
-[root@XXX /] mkdir cdrom
-[root@XXX /] mount -r -t iso9660 -o conv=auto /dev/cdrom /cdrom
-[root@XXX /] cd root
-[root@XXX /root] mkdir dl2k
-[root@XXX /root] cd dl2k
-[root@XXX dl2k] cp /cdrom/linux/dl2k.tgz /root/dl2k
-[root@XXX dl2k] tar xfvz dl2k.tgz
-[root@XXX dl2k] make all
-
-Floppy disc drive
------------------
-
-[root@XXX /] cd root
-[root@XXX /root] mkdir dl2k
-[root@XXX /root] cd dl2k
-[root@XXX dl2k] mcopy a:/linux/dl2k.tgz /root/dl2k
-[root@XXX dl2k] tar xfvz dl2k.tgz
-[root@XXX dl2k] make all
-
-Installing the Driver
-=====================
-
-  Manual Installation
-  -------------------
-  Once the driver has been compiled, it must be loaded, enabled, and bound
-  to a protocol stack in order to establish network connectivity. To load a
-  module enter the command:
-
-  insmod dl2k.o
-
-  or
-
-  insmod dl2k.o <optional parameter>	; add parameter
-
-  ===============================================================
-   example: insmod dl2k.o media=100mbps_hd
-   or	    insmod dl2k.o media=3
-   or	    insmod dl2k.o media=3,2	; for 2 cards
-  ===============================================================
-
-  Please reference the list of the command line parameters supported by
-  the Linux device driver below.
-
-  The insmod command only loads the driver and gives it a name of the form
-  eth0, eth1, etc. To bring the NIC into an operational state,
-  it is necessary to issue the following command:
-
-  ifconfig eth0 up
-
-  Finally, to bind the driver to the active protocol (e.g., TCP/IP with
-  Linux), enter the following command:
-
-  ifup eth0
-
-  Note that this is meaningful only if the system can find a configuration
-  script that contains the necessary network information. A sample will be
-  given in the next paragraph.
-
-  The commands to unload a driver are as follows:
-
-  ifdown eth0
-  ifconfig eth0 down
-  rmmod dl2k.o
-
-  The following are the commands to list the currently loaded modules and
-  to see the current network configuration.
-
-  lsmod
-  ifconfig
-
-
-  Automated Installation
-  ----------------------
-  This section describes how to install the driver such that it is
-  automatically loaded and configured at boot time. The following description
-  is based on a Red Hat 6.0/7.0 distribution, but it can easily be ported to
-  other distributions as well.
-
-  Red Hat v6.x/v7.x
-  -----------------
-  1. Copy dl2k.o to the network modules directory, typically
-     /lib/modules/2.x.x-xx/net or /lib/modules/2.x.x/kernel/drivers/net.
-  2. Locate the boot module configuration file, most commonly in the
-     /etc/modprobe.d/ directory. Add the following lines:
-
-     alias ethx dl2k
-     options dl2k <optional parameters>
-
-     where ethx will be eth0 if the NIC is the only ethernet adapter, eth1 if
-     one other ethernet adapter is installed, etc. Refer to the table in the
-     previous section for the list of optional parameters.
-  3. Locate the network configuration scripts, normally the
-     /etc/sysconfig/network-scripts directory, and create a configuration
-     script named ifcfg-ethx that contains network information.
-  4. Note that for most Linux distributions, Red Hat included, a configuration
-     utility with a graphical user interface is provided to perform steps 2
-     and 3 above.
-
-
-Parameter Description
-=====================
-You can install this driver without any additional parameter. However, if you
-are going to have extensive functions then it is necessary to set extra
-parameter. Below is a list of the command line parameters supported by the
-Linux device
-driver.
-
-mtu=packet_size			- Specifies the maximum packet size. default
-				  is 1500.
-
-media=media_type		- Specifies the media type the NIC operates at.
-				  autosense	Autosensing active media.
-				  10mbps_hd	10Mbps half duplex.
-				  10mbps_fd	10Mbps full duplex.
-				  100mbps_hd	100Mbps half duplex.
-				  100mbps_fd	100Mbps full duplex.
-				  1000mbps_fd	1000Mbps full duplex.
-				  1000mbps_hd	1000Mbps half duplex.
-				  0		Autosensing active media.
-				  1		10Mbps half duplex.
-				  2		10Mbps full duplex.
-				  3		100Mbps half duplex.
-				  4		100Mbps full duplex.
-				  5          	1000Mbps half duplex.
-				  6          	1000Mbps full duplex.
-
-				  By default, the NIC operates at autosense.
-				  1000mbps_fd and 1000mbps_hd types are only
-				  available for fiber adapter.
-
-vlan=n				- Specifies the VLAN ID. If vlan=0, the
-				  Virtual Local Area Network (VLAN) function is
-				  disable.
-
-jumbo=[0|1]			- Specifies the jumbo frame support. If jumbo=1,
-				  the NIC accept jumbo frames. By default, this
-				  function is disabled.
-				  Jumbo frame usually improve the performance
-				  int gigabit.
-				  This feature need jumbo frame compatible 
-				  remote.
-				  
-rx_coalesce=m			- Number of rx frame handled each interrupt.
-rx_timeout=n			- Rx DMA wait time for an interrupt. 
-				  If set rx_coalesce > 0, hardware only assert 
-				  an interrupt for m frames. Hardware won't 
-				  assert rx interrupt until m frames received or
-				  reach timeout of n * 640 nano seconds. 
-				  Set proper rx_coalesce and rx_timeout can 
-				  reduce congestion collapse and overload which
-				  has been a bottleneck for high speed network.
-				  
-				  For example, rx_coalesce=10 rx_timeout=800.
-				  that is, hardware assert only 1 interrupt 
-				  for 10 frames received or timeout of 512 us. 
-
-tx_coalesce=n			- Number of tx frame handled each interrupt.
-				  Set n > 1 can reduce the interrupts 
-				  congestion usually lower performance of
-				  high speed network card. Default is 16.
-				  
-tx_flow=[1|0]			- Specifies the Tx flow control. If tx_flow=0, 
-				  the Tx flow control disable else driver
-				  autodetect.
-rx_flow=[1|0]			- Specifies the Rx flow control. If rx_flow=0, 
-				  the Rx flow control enable else driver
-				  autodetect.
-
-
-Configuration Script Sample
-===========================
-Here is a sample of a simple configuration script:
-
-DEVICE=eth0
-USERCTL=no
-ONBOOT=yes
-POOTPROTO=none
-BROADCAST=207.200.5.255
-NETWORK=207.200.5.0
-NETMASK=255.255.255.0
-IPADDR=207.200.5.2
-
-
-Troubleshooting
-===============
-Q1. Source files contain ^ M behind every line.
-	Make sure all files are Unix file format (no LF). Try the following
-    shell command to convert files.
-
-	cat dl2k.c | col -b > dl2k.tmp
-	mv dl2k.tmp dl2k.c
-
-	OR
-
-	cat dl2k.c | tr -d "\r" > dl2k.tmp
-	mv dl2k.tmp dl2k.c
-
-Q2: Could not find header files (*.h) ?
-	To compile the driver, you need kernel header files. After
-    installing the kernel source, the header files are usually located in
-    /usr/src/linux/include, which is the default include directory configured
-    in Makefile. For some distributions, there is a copy of header files in
-    /usr/src/include/linux and /usr/src/include/asm, that you can change the
-    INCLUDEDIR in Makefile to /usr/include without installing kernel source.
-	Note that RH 7.0 didn't provide correct header files in /usr/include,
-    including those files will make a wrong version driver.
-
diff --git a/Documentation/networking/dm9000.txt b/Documentation/networking/dm9000.txt
deleted file mode 100644
index 5552e2e575c5..000000000000
--- a/Documentation/networking/dm9000.txt
+++ /dev/null
@@ -1,167 +0,0 @@
-DM9000 Network driver
-=====================
-
-Copyright 2008 Simtec Electronics,
-	  Ben Dooks <ben@simtec.co.uk> <ben-linux@fluff.org>
-
-
-Introduction
-------------
-
-This file describes how to use the DM9000 platform-device based network driver
-that is contained in the files drivers/net/dm9000.c and drivers/net/dm9000.h.
-
-The driver supports three DM9000 variants, the DM9000E which is the first chip
-supported as well as the newer DM9000A and DM9000B devices. It is currently
-maintained and tested by Ben Dooks, who should be CC: to any patches for this
-driver.
-
-
-Defining the platform device
-----------------------------
-
-The minimum set of resources attached to the platform device are as follows:
-
-    1) The physical address of the address register
-    2) The physical address of the data register
-    3) The IRQ line the device's interrupt pin is connected to.
-
-These resources should be specified in that order, as the ordering of the
-two address regions is important (the driver expects these to be address
-and then data).
-
-An example from arch/arm/mach-s3c2410/mach-bast.c is:
-
-static struct resource bast_dm9k_resource[] = {
-	[0] = {
-		.start = S3C2410_CS5 + BAST_PA_DM9000,
-		.end   = S3C2410_CS5 + BAST_PA_DM9000 + 3,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = S3C2410_CS5 + BAST_PA_DM9000 + 0x40,
-		.end   = S3C2410_CS5 + BAST_PA_DM9000 + 0x40 + 0x3f,
-		.flags = IORESOURCE_MEM,
-	},
-	[2] = {
-		.start = IRQ_DM9000,
-		.end   = IRQ_DM9000,
-		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
-	}
-};
-
-static struct platform_device bast_device_dm9k = {
-	.name		= "dm9000",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(bast_dm9k_resource),
-	.resource	= bast_dm9k_resource,
-};
-
-Note the setting of the IRQ trigger flag in bast_dm9k_resource[2].flags,
-as this will generate a warning if it is not present. The trigger from
-the flags field will be passed to request_irq() when registering the IRQ
-handler to ensure that the IRQ is setup correctly.
-
-This shows a typical platform device, without the optional configuration
-platform data supplied. The next example uses the same resources, but adds
-the optional platform data to pass extra configuration data:
-
-static struct dm9000_plat_data bast_dm9k_platdata = {
-	.flags		= DM9000_PLATF_16BITONLY,
-};
-
-static struct platform_device bast_device_dm9k = {
-	.name		= "dm9000",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(bast_dm9k_resource),
-	.resource	= bast_dm9k_resource,
-	.dev		= {
-		.platform_data = &bast_dm9k_platdata,
-	}
-};
-
-The platform data is defined in include/linux/dm9000.h and described below.
-
-
-Platform data
--------------
-
-Extra platform data for the DM9000 can describe the IO bus width to the
-device, whether or not an external PHY is attached to the device and
-the availability of an external configuration EEPROM.
-
-The flags for the platform data .flags field are as follows:
-
-DM9000_PLATF_8BITONLY
-
-	The IO should be done with 8bit operations.
-
-DM9000_PLATF_16BITONLY
-
-	The IO should be done with 16bit operations.
-
-DM9000_PLATF_32BITONLY
-
-	The IO should be done with 32bit operations.
-
-DM9000_PLATF_EXT_PHY
-
-	The chip is connected to an external PHY.
-
-DM9000_PLATF_NO_EEPROM
-
-	This can be used to signify that the board does not have an
-	EEPROM, or that the EEPROM should be hidden from the user.
-
-DM9000_PLATF_SIMPLE_PHY
-
-	Switch to using the simpler PHY polling method which does not
-	try and read the MII PHY state regularly. This is only available
-	when using the internal PHY. See the section on link state polling
-	for more information.
-
-	The config symbol DM9000_FORCE_SIMPLE_PHY_POLL, Kconfig entry
-	"Force simple NSR based PHY polling" allows this flag to be
-	forced on at build time.
-
-
-PHY Link state polling
-----------------------
-
-The driver keeps track of the link state and informs the network core
-about link (carrier) availability. This is managed by several methods
-depending on the version of the chip and on which PHY is being used.
-
-For the internal PHY, the original (and currently default) method is
-to read the MII state, either when the status changes if we have the
-necessary interrupt support in the chip or every two seconds via a
-periodic timer.
-
-To reduce the overhead for the internal PHY, there is now the option
-of using the DM9000_FORCE_SIMPLE_PHY_POLL config, or DM9000_PLATF_SIMPLE_PHY
-platform data option to read the summary information without the
-expensive MII accesses. This method is faster, but does not print
-as much information.
-
-When using an external PHY, the driver currently has to poll the MII
-link status as there is no method for getting an interrupt on link change.
-
-
-DM9000A / DM9000B
------------------
-
-These chips are functionally similar to the DM9000E and are supported easily
-by the same driver. The features are:
-
-   1) Interrupt on internal PHY state change. This means that the periodic
-      polling of the PHY status may be disabled on these devices when using
-      the internal PHY.
-
-   2) TCP/UDP checksum offloading, which the driver does not currently support.
-
-
-ethtool
--------
-
-The driver supports the ethtool interface for access to the driver
-state information, the PHY state and the EEPROM.
diff --git a/Documentation/networking/dmfe.txt b/Documentation/networking/dmfe.txt
deleted file mode 100644
index 25320bf19c86..000000000000
--- a/Documentation/networking/dmfe.txt
+++ /dev/null
@@ -1,66 +0,0 @@
-Note: This driver doesn't have a maintainer.
-
-Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver for Linux.
-
-This program is free software; you can redistribute it and/or
-modify it under the terms of the GNU General   Public License
-as published by the Free Software Foundation; either version 2
-of the License, or (at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-
-This driver provides kernel support for Davicom DM9102(A)/DM9132/DM9801 ethernet cards ( CNET
-10/100 ethernet cards uses Davicom chipset too, so this driver supports CNET cards too ).If you
-didn't compile this driver as a module, it will automatically load itself on boot and print a
-line similar to :
-
-	dmfe: Davicom DM9xxx net driver, version 1.36.4 (2002-01-17)
-
-If you compiled this driver as a module, you have to load it on boot.You can load it with command :
-
-	insmod dmfe
-
-This way it will autodetect the device mode.This is the suggested way to load the module.Or you can pass
-a mode= setting to module while loading, like :
-
-	insmod dmfe mode=0 # Force 10M Half Duplex
-	insmod dmfe mode=1 # Force 100M Half Duplex
-	insmod dmfe mode=4 # Force 10M Full Duplex
-	insmod dmfe mode=5 # Force 100M Full Duplex
-
-Next you should configure your network interface with a command similar to :
-
-	ifconfig eth0 172.22.3.18
-                      ^^^^^^^^^^^
-		     Your IP Address
-
-Then you may have to modify the default routing table with command :
-
-	route add default eth0
-
-
-Now your ethernet card should be up and running.
-
-
-TODO:
-
-Implement pci_driver::suspend() and pci_driver::resume() power management methods.
-Check on 64 bit boxes.
-Check and fix on big endian boxes.
-Test and make sure PCI latency is now correct for all cases.
-
-
-Authors:
-
-Sten Wang <sten_wang@davicom.com.tw >   : Original Author
-
-Contributors:
-
-Marcelo Tosatti <marcelo@conectiva.com.br>
-Alan Cox <alan@lxorguk.ukuu.org.uk>
-Jeff Garzik <jgarzik@pobox.com>
-Vojtech Pavlik <vojtech@suse.cz>
diff --git a/Documentation/networking/dpaa.txt b/Documentation/networking/dpaa.txt
deleted file mode 100644
index f88194f71c54..000000000000
--- a/Documentation/networking/dpaa.txt
+++ /dev/null
@@ -1,260 +0,0 @@
-The QorIQ DPAA Ethernet Driver
-==============================
-
-Authors:
-Madalin Bucur <madalin.bucur@nxp.com>
-Camelia Groza <camelia.groza@nxp.com>
-
-Contents
-========
-
-	- DPAA Ethernet Overview
-	- DPAA Ethernet Supported SoCs
-	- Configuring DPAA Ethernet in your kernel
-	- DPAA Ethernet Frame Processing
-	- DPAA Ethernet Features
-	- DPAA IRQ Affinity and Receive Side Scaling
-	- Debugging
-
-DPAA Ethernet Overview
-======================
-
-DPAA stands for Data Path Acceleration Architecture and it is a
-set of networking acceleration IPs that are available on several
-generations of SoCs, both on PowerPC and ARM64.
-
-The Freescale DPAA architecture consists of a series of hardware blocks
-that support Ethernet connectivity. The Ethernet driver depends upon the
-following drivers in the Linux kernel:
-
- - Peripheral Access Memory Unit (PAMU) (* needed only for PPC platforms)
-    drivers/iommu/fsl_*
- - Frame Manager (FMan)
-    drivers/net/ethernet/freescale/fman
- - Queue Manager (QMan), Buffer Manager (BMan)
-    drivers/soc/fsl/qbman
-
-A simplified view of the dpaa_eth interfaces mapped to FMan MACs:
-
-  dpaa_eth       /eth0\     ...       /ethN\
-  driver        |      |             |      |
-  -------------   ----   -----------   ----   -------------
-       -Ports  / Tx  Rx \    ...    / Tx  Rx \
-  FMan        |          |         |          |
-       -MACs  |   MAC0   |         |   MACN   |
-             /   dtsec0   \  ...  /   dtsecN   \ (or tgec)
-            /              \     /              \(or memac)
-  ---------  --------------  ---  --------------  ---------
-      FMan, FMan Port, FMan SP, FMan MURAM drivers
-  ---------------------------------------------------------
-      FMan HW blocks: MURAM, MACs, Ports, SP
-  ---------------------------------------------------------
-
-The dpaa_eth relation to the QMan, BMan and FMan:
-              ________________________________
-  dpaa_eth   /            eth0                \
-  driver    /                                  \
-  ---------   -^-   -^-   -^-   ---    ---------
-  QMan driver / \   / \   / \  \   /  | BMan    |
-             |Rx | |Rx | |Tx | |Tx |  | driver  |
-  ---------  |Dfl| |Err| |Cnf| |FQs|  |         |
-  QMan HW    |FQ | |FQ | |FQs| |   |  |         |
-             /   \ /   \ /   \  \ /   |         |
-  ---------   ---   ---   ---   -v-    ---------
-            |        FMan QMI         |         |
-            | FMan HW       FMan BMI  | BMan HW |
-              -----------------------   --------
-
-where the acronyms used above (and in the code) are:
-DPAA = Data Path Acceleration Architecture
-FMan = DPAA Frame Manager
-QMan = DPAA Queue Manager
-BMan = DPAA Buffers Manager
-QMI = QMan interface in FMan
-BMI = BMan interface in FMan
-FMan SP = FMan Storage Profiles
-MURAM = Multi-user RAM in FMan
-FQ = QMan Frame Queue
-Rx Dfl FQ = default reception FQ
-Rx Err FQ = Rx error frames FQ
-Tx Cnf FQ = Tx confirmation FQs
-Tx FQs = transmission frame queues
-dtsec = datapath three speed Ethernet controller (10/100/1000 Mbps)
-tgec = ten gigabit Ethernet controller (10 Gbps)
-memac = multirate Ethernet MAC (10/100/1000/10000)
-
-DPAA Ethernet Supported SoCs
-============================
-
-The DPAA drivers enable the Ethernet controllers present on the following SoCs:
-
-# PPC
-P1023
-P2041
-P3041
-P4080
-P5020
-P5040
-T1023
-T1024
-T1040
-T1042
-T2080
-T4240
-B4860
-
-# ARM
-LS1043A
-LS1046A
-
-Configuring DPAA Ethernet in your kernel
-========================================
-
-To enable the DPAA Ethernet driver, the following Kconfig options are required:
-
-# common for arch/arm64 and arch/powerpc platforms
-CONFIG_FSL_DPAA=y
-CONFIG_FSL_FMAN=y
-CONFIG_FSL_DPAA_ETH=y
-CONFIG_FSL_XGMAC_MDIO=y
-
-# for arch/powerpc only
-CONFIG_FSL_PAMU=y
-
-# common options needed for the PHYs used on the RDBs
-CONFIG_VITESSE_PHY=y
-CONFIG_REALTEK_PHY=y
-CONFIG_AQUANTIA_PHY=y
-
-DPAA Ethernet Frame Processing
-==============================
-
-On Rx, buffers for the incoming frames are retrieved from one of the three
-existing buffers pools. The driver initializes and seeds these, each with
-buffers of different sizes: 1KB, 2KB and 4KB.
-
-On Tx, all transmitted frames are returned to the driver through Tx
-confirmation frame queues. The driver is then responsible for freeing the
-buffers. In order to do this properly, a backpointer is added to the buffer
-before transmission that points to the skb. When the buffer returns to the
-driver on a confirmation FQ, the skb can be correctly consumed.
-
-DPAA Ethernet Features
-======================
-
-Currently the DPAA Ethernet driver enables the basic features required for
-a Linux Ethernet driver. The support for advanced features will be added
-gradually.
-
-The driver has Rx and Tx checksum offloading for UDP and TCP. Currently the Rx
-checksum offload feature is enabled by default and cannot be controlled through
-ethtool. Also, rx-flow-hash and rx-hashing was added. The addition of RSS
-provides a big performance boost for the forwarding scenarios, allowing
-different traffic flows received by one interface to be processed by different
-CPUs in parallel.
-
-The driver has support for multiple prioritized Tx traffic classes. Priorities
-range from 0 (lowest) to 3 (highest). These are mapped to HW workqueues with
-strict priority levels. Each traffic class contains NR_CPU TX queues. By
-default, only one traffic class is enabled and the lowest priority Tx queues
-are used. Higher priority traffic classes can be enabled with the mqprio
-qdisc. For example, all four traffic classes are enabled on an interface with
-the following command. Furthermore, skb priority levels are mapped to traffic
-classes as follows:
-
-	* priorities 0 to 3 - traffic class 0 (low priority)
-	* priorities 4 to 7 - traffic class 1 (medium-low priority)
-	* priorities 8 to 11 - traffic class 2 (medium-high priority)
-	* priorities 12 to 15 - traffic class 3 (high priority)
-
-tc qdisc add dev <int> root handle 1: \
-	 mqprio num_tc 4 map 0 0 0 0 1 1 1 1 2 2 2 2 3 3 3 3 hw 1
-
-DPAA IRQ Affinity and Receive Side Scaling
-==========================================
-
-Traffic coming on the DPAA Rx queues or on the DPAA Tx confirmation
-queues is seen by the CPU as ingress traffic on a certain portal.
-The DPAA QMan portal interrupts are affined each to a certain CPU.
-The same portal interrupt services all the QMan portal consumers.
-
-By default the DPAA Ethernet driver enables RSS, making use of the
-DPAA FMan Parser and Keygen blocks to distribute traffic on 128
-hardware frame queues using a hash on IP v4/v6 source and destination
-and L4 source and destination ports, in present in the received frame.
-When RSS is disabled, all traffic received by a certain interface is
-received on the default Rx frame queue. The default DPAA Rx frame
-queues are configured to put the received traffic into a pool channel
-that allows any available CPU portal to dequeue the ingress traffic.
-The default frame queues have the HOLDACTIVE option set, ensuring that
-traffic bursts from a certain queue are serviced by the same CPU.
-This ensures a very low rate of frame reordering. A drawback of this
-is that only one CPU at a time can service the traffic received by a
-certain interface when RSS is not enabled.
-
-To implement RSS, the DPAA Ethernet driver allocates an extra set of
-128 Rx frame queues that are configured to dedicated channels, in a
-round-robin manner. The mapping of the frame queues to CPUs is now
-hardcoded, there is no indirection table to move traffic for a certain
-FQ (hash result) to another CPU. The ingress traffic arriving on one
-of these frame queues will arrive at the same portal and will always
-be processed by the same CPU. This ensures intra-flow order preservation
-and workload distribution for multiple traffic flows.
-
-RSS can be turned off for a certain interface using ethtool, i.e.
-
-	# ethtool -N fm1-mac9 rx-flow-hash tcp4 ""
-
-To turn it back on, one needs to set rx-flow-hash for tcp4/6 or udp4/6:
-
-	# ethtool -N fm1-mac9 rx-flow-hash udp4 sfdn
-
-There is no independent control for individual protocols, any command
-run for one of tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6 is
-going to control the rx-flow-hashing for all protocols on that interface.
-
-Besides using the FMan Keygen computed hash for spreading traffic on the
-128 Rx FQs, the DPAA Ethernet driver also sets the skb hash value when
-the NETIF_F_RXHASH feature is on (active by default). This can be turned
-on or off through ethtool, i.e.:
-
-	# ethtool -K fm1-mac9 rx-hashing off
-	# ethtool -k fm1-mac9 | grep hash
-	receive-hashing: off
-	# ethtool -K fm1-mac9 rx-hashing on
-	Actual changes:
-	receive-hashing: on
-	# ethtool -k fm1-mac9 | grep hash
-	receive-hashing: on
-
-Please note that Rx hashing depends upon the rx-flow-hashing being on
-for that interface - turning off rx-flow-hashing will also disable the
-rx-hashing (without ethtool reporting it as off as that depends on the
-NETIF_F_RXHASH feature flag).
-
-Debugging
-=========
-
-The following statistics are exported for each interface through ethtool:
-
-	- interrupt count per CPU
-	- Rx packets count per CPU
-	- Tx packets count per CPU
-	- Tx confirmed packets count per CPU
-	- Tx S/G frames count per CPU
-	- Tx error count per CPU
-	- Rx error count per CPU
-	- Rx error count per type
-	- congestion related statistics:
-		- congestion status
-		- time spent in congestion
-		- number of time the device entered congestion
-		- dropped packets count per cause
-
-The driver also exports the following information in sysfs:
-
-	- the FQ IDs for each FQ type
-	/sys/devices/platform/dpaa-ethernet.0/net/<int>/fqids
-
-	- the IDs of the buffer pools in use
-	/sys/devices/platform/dpaa-ethernet.0/net/<int>/bpids
diff --git a/Documentation/networking/dpaa2/dpio-driver.rst b/Documentation/networking/dpaa2/dpio-driver.rst
deleted file mode 100644
index 13588104161b..000000000000
--- a/Documentation/networking/dpaa2/dpio-driver.rst
+++ /dev/null
@@ -1,158 +0,0 @@
-.. include:: <isonum.txt>
-
-DPAA2 DPIO (Data Path I/O) Overview
-===================================
-
-:Copyright: |copy| 2016-2018 NXP
-
-This document provides an overview of the Freescale DPAA2 DPIO
-drivers
-
-Introduction
-============
-
-A DPAA2 DPIO (Data Path I/O) is a hardware object that provides
-interfaces to enqueue and dequeue frames to/from network interfaces
-and other accelerators.  A DPIO also provides hardware buffer
-pool management for network interfaces.
-
-This document provides an overview the Linux DPIO driver, its
-subcomponents, and its APIs.
-
-See Documentation/networking/dpaa2/overview.rst for a general overview of DPAA2
-and the general DPAA2 driver architecture in Linux.
-
-Driver Overview
----------------
-
-The DPIO driver is bound to DPIO objects discovered on the fsl-mc bus and
-provides services that:
-  A) allow other drivers, such as the Ethernet driver, to enqueue and dequeue
-     frames for their respective objects
-  B) allow drivers to register callbacks for data availability notifications
-     when data becomes available on a queue or channel
-  C) allow drivers to manage hardware buffer pools
-
-The Linux DPIO driver consists of 3 primary components--
-   DPIO object driver-- fsl-mc driver that manages the DPIO object
-
-   DPIO service-- provides APIs to other Linux drivers for services
-
-   QBman portal interface-- sends portal commands, gets responses
-::
-
-          fsl-mc          other
-           bus           drivers
-            |               |
-        +---+----+   +------+-----+
-        |DPIO obj|   |DPIO service|
-        | driver |---|  (DPIO)    |
-        +--------+   +------+-----+
-                            |
-                     +------+-----+
-                     |    QBman   |
-                     | portal i/f |
-                     +------------+
-                            |
-                         hardware
-
-
-The diagram below shows how the DPIO driver components fit with the other
-DPAA2 Linux driver components::
-                                                   +------------+
-                                                   | OS Network |
-                                                   |   Stack    |
-                 +------------+                    +------------+
-                 | Allocator  |. . . . . . .       |  Ethernet  |
-                 |(DPMCP,DPBP)|                    |   (DPNI)   |
-                 +-.----------+                    +---+---+----+
-                  .          .                         ^   |
-                 .            .           <data avail, |   |<enqueue,
-                .              .           tx confirm> |   | dequeue>
-    +-------------+             .                      |   |
-    | DPRC driver |              .    +--------+ +------------+
-    |   (DPRC)    |               . . |DPIO obj| |DPIO service|
-    +----------+--+                   | driver |-|  (DPIO)    |
-               |                      +--------+ +------+-----+
-               |<dev add/remove>                 +------|-----+
-               |                                 |   QBman    |
-          +----+--------------+                  | portal i/f |
-          |   MC-bus driver   |                  +------------+
-          |                   |                     |
-          | /soc/fsl-mc       |                     |
-          +-------------------+                     |
-                                                    |
- =========================================|=========|========================
-                                        +-+--DPIO---|-----------+
-                                        |           |           |
-                                        |        QBman Portal   |
-                                        +-----------------------+
-
- ============================================================================
-
-
-DPIO Object Driver (dpio-driver.c)
-----------------------------------
-
-   The dpio-driver component registers with the fsl-mc bus to handle objects of
-   type "dpio".  The implementation of probe() handles basic initialization
-   of the DPIO including mapping of the DPIO regions (the QBman SW portal)
-   and initializing interrupts and registering irq handlers.  The dpio-driver
-   registers the probed DPIO with dpio-service.
-
-DPIO service  (dpio-service.c, dpaa2-io.h)
-------------------------------------------
-
-   The dpio service component provides queuing, notification, and buffers
-   management services to DPAA2 drivers, such as the Ethernet driver.  A system
-   will typically allocate 1 DPIO object per CPU to allow queuing operations
-   to happen simultaneously across all CPUs.
-
-   Notification handling
-      dpaa2_io_service_register()
-
-      dpaa2_io_service_deregister()
-
-      dpaa2_io_service_rearm()
-
-   Queuing
-      dpaa2_io_service_pull_fq()
-
-      dpaa2_io_service_pull_channel()
-
-      dpaa2_io_service_enqueue_fq()
-
-      dpaa2_io_service_enqueue_qd()
-
-      dpaa2_io_store_create()
-
-      dpaa2_io_store_destroy()
-
-      dpaa2_io_store_next()
-
-   Buffer pool management
-      dpaa2_io_service_release()
-
-      dpaa2_io_service_acquire()
-
-QBman portal interface (qbman-portal.c)
----------------------------------------
-
-   The qbman-portal component provides APIs to do the low level hardware
-   bit twiddling for operations such as:
-      -initializing Qman software portals
-
-      -building and sending portal commands
-
-      -portal interrupt configuration and processing
-
-   The qbman-portal APIs are not public to other drivers, and are
-   only used by dpio-service.
-
-Other (dpaa2-fd.h, dpaa2-global.h)
-----------------------------------
-
-   Frame descriptor and scatter-gather definitions and the APIs used to
-   manipulate them are defined in dpaa2-fd.h.
-
-   Dequeue result struct and parsing APIs are defined in dpaa2-global.h.
diff --git a/Documentation/networking/dpaa2/ethernet-driver.rst b/Documentation/networking/dpaa2/ethernet-driver.rst
deleted file mode 100644
index 90ec940749e8..000000000000
--- a/Documentation/networking/dpaa2/ethernet-driver.rst
+++ /dev/null
@@ -1,185 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-.. include:: <isonum.txt>
-
-===============================
-DPAA2 Ethernet driver
-===============================
-
-:Copyright: |copy| 2017-2018 NXP
-
-This file provides documentation for the Freescale DPAA2 Ethernet driver.
-
-Supported Platforms
-===================
-This driver provides networking support for Freescale DPAA2 SoCs, e.g.
-LS2080A, LS2088A, LS1088A.
-
-
-Architecture Overview
-=====================
-Unlike regular NICs, in the DPAA2 architecture there is no single hardware block
-representing network interfaces; instead, several separate hardware resources
-concur to provide the networking functionality:
-
-- network interfaces
-- queues, channels
-- buffer pools
-- MAC/PHY
-
-All hardware resources are allocated and configured through the Management
-Complex (MC) portals. MC abstracts most of these resources as DPAA2 objects
-and exposes ABIs through which they can be configured and controlled. A few
-hardware resources, like queues, do not have a corresponding MC object and
-are treated as internal resources of other objects.
-
-For a more detailed description of the DPAA2 architecture and its object
-abstractions see *Documentation/networking/dpaa2/overview.rst*.
-
-Each Linux net device is built on top of a Datapath Network Interface (DPNI)
-object and uses Buffer Pools (DPBPs), I/O Portals (DPIOs) and Concentrators
-(DPCONs).
-
-Configuration interface::
-
-                 -----------------------
-                | DPAA2 Ethernet Driver |
-                 -----------------------
-                     .      .      .
-                     .      .      .
-             . . . . .      .      . . . . . .
-             .              .                .
-             .              .                .
-         ----------     ----------      -----------
-        | DPBP API |   | DPNI API |    | DPCON API |
-         ----------     ----------      -----------
-             .              .                .             software
-    =======  .  ==========  .  ============  .  ===================
-             .              .                .             hardware
-         ------------------------------------------
-        |            MC hardware portals           |
-         ------------------------------------------
-             .              .                .
-             .              .                .
-          ------         ------            -------
-         | DPBP |       | DPNI |          | DPCON |
-          ------         ------            -------
-
-The DPNIs are network interfaces without a direct one-on-one mapping to PHYs.
-DPBPs represent hardware buffer pools. Packet I/O is performed in the context
-of DPCON objects, using DPIO portals for managing and communicating with the
-hardware resources.
-
-Datapath (I/O) interface::
-
-         -----------------------------------------------
-        |           DPAA2 Ethernet Driver               |
-         -----------------------------------------------
-          |          ^        ^         |            |
-          |          |        |         |            |
-   enqueue|   dequeue|   data |  dequeue|       seed |
-    (Tx)  | (Rx, TxC)|  avail.|  request|     buffers|
-          |          |  notify|         |            |
-          |          |        |         |            |
-          V          |        |         V            V
-         -----------------------------------------------
-        |                 DPIO Driver                   |
-         -----------------------------------------------
-          |          |        |         |            |          software
-          |          |        |         |            |  ================
-          |          |        |         |            |          hardware
-         -----------------------------------------------
-        |               I/O hardware portals            |
-         -----------------------------------------------
-          |          ^        ^         |            |
-          |          |        |         |            |
-          |          |        |         V            |
-          V          |    ================           V
-        ----------------------           |      -------------
- queues  ----------------------          |     | Buffer pool |
-          ----------------------         |      -------------
-                   =======================
-                                Channel
-
-Datapath I/O (DPIO) portals provide enqueue and dequeue services, data
-availability notifications and buffer pool management. DPIOs are shared between
-all DPAA2 objects (and implicitly all DPAA2 kernel drivers) that work with data
-frames, but must be affine to the CPUs for the purpose of traffic distribution.
-
-Frames are transmitted and received through hardware frame queues, which can be
-grouped in channels for the purpose of hardware scheduling. The Ethernet driver
-enqueues TX frames on egress queues and after transmission is complete a TX
-confirmation frame is sent back to the CPU.
-
-When frames are available on ingress queues, a data availability notification
-is sent to the CPU; notifications are raised per channel, so even if multiple
-queues in the same channel have available frames, only one notification is sent.
-After a channel fires a notification, is must be explicitly rearmed.
-
-Each network interface can have multiple Rx, Tx and confirmation queues affined
-to CPUs, and one channel (DPCON) for each CPU that services at least one queue.
-DPCONs are used to distribute ingress traffic to different CPUs via the cores'
-affine DPIOs.
-
-The role of hardware buffer pools is storage of ingress frame data. Each network
-interface has a privately owned buffer pool which it seeds with kernel allocated
-buffers.
-
-
-DPNIs are decoupled from PHYs; a DPNI can be connected to a PHY through a DPMAC
-object or to another DPNI through an internal link, but the connection is
-managed by MC and completely transparent to the Ethernet driver.
-
-::
-
-     ---------     ---------     ---------
-    | eth if1 |   | eth if2 |   | eth ifn |
-     ---------     ---------     ---------
-          .           .          .
-          .           .          .
-          .           .          .
-         ---------------------------
-        |   DPAA2 Ethernet Driver   |
-         ---------------------------
-          .           .          .
-          .           .          .
-          .           .          .
-       ------      ------      ------            -------
-      | DPNI |    | DPNI |    | DPNI |          | DPMAC |----+
-       ------      ------      ------            -------     |
-         |           |           |                  |        |
-         |           |           |                  |      -----
-          ===========             ==================      | PHY |
-                                                           -----
-
-Creating a Network Interface
-============================
-A net device is created for each DPNI object probed on the MC bus. Each DPNI has
-a number of properties which determine the network interface configuration
-options and associated hardware resources.
-
-DPNI objects (and the other DPAA2 objects needed for a network interface) can be
-added to a container on the MC bus in one of two ways: statically, through a
-Datapath Layout Binary file (DPL) that is parsed by MC at boot time; or created
-dynamically at runtime, via the DPAA2 objects APIs.
-
-
-Features & Offloads
-===================
-Hardware checksum offloading is supported for TCP and UDP over IPv4/6 frames.
-The checksum offloads can be independently configured on RX and TX through
-ethtool.
-
-Hardware offload of unicast and multicast MAC filtering is supported on the
-ingress path and permanently enabled.
-
-Scatter-gather frames are supported on both RX and TX paths. On TX, SG support
-is configurable via ethtool; on RX it is always enabled.
-
-The DPAA2 hardware can process jumbo Ethernet frames of up to 10K bytes.
-
-The Ethernet driver defines a static flow hashing scheme that distributes
-traffic based on a 5-tuple key: src IP, dst IP, IP proto, L4 src port,
-L4 dst port. No user configuration is supported for now.
-
-Hardware specific statistics for the network interface as well as some
-non-standard driver stats can be consulted through ethtool -S option.
diff --git a/Documentation/networking/dpaa2/index.rst b/Documentation/networking/dpaa2/index.rst
deleted file mode 100644
index 67bd87fe6c53..000000000000
--- a/Documentation/networking/dpaa2/index.rst
+++ /dev/null
@@ -1,10 +0,0 @@
-===================
-DPAA2 Documentation
-===================
-
-.. toctree::
-   :maxdepth: 1
-
-   overview
-   dpio-driver
-   ethernet-driver
diff --git a/Documentation/networking/dpaa2/overview.rst b/Documentation/networking/dpaa2/overview.rst
deleted file mode 100644
index d638b5a8aadd..000000000000
--- a/Documentation/networking/dpaa2/overview.rst
+++ /dev/null
@@ -1,405 +0,0 @@
-.. include:: <isonum.txt>
-
-=========================================================
-DPAA2 (Data Path Acceleration Architecture Gen2) Overview
-=========================================================
-
-:Copyright: |copy| 2015 Freescale Semiconductor Inc.
-:Copyright: |copy| 2018 NXP
-
-This document provides an overview of the Freescale DPAA2 architecture
-and how it is integrated into the Linux kernel.
-
-Introduction
-============
-
-DPAA2 is a hardware architecture designed for high-speeed network
-packet processing.  DPAA2 consists of sophisticated mechanisms for
-processing Ethernet packets, queue management, buffer management,
-autonomous L2 switching, virtual Ethernet bridging, and accelerator
-(e.g. crypto) sharing.
-
-A DPAA2 hardware component called the Management Complex (or MC) manages the
-DPAA2 hardware resources.  The MC provides an object-based abstraction for
-software drivers to use the DPAA2 hardware.
-The MC uses DPAA2 hardware resources such as queues, buffer pools, and
-network ports to create functional objects/devices such as network
-interfaces, an L2 switch, or accelerator instances.
-The MC provides memory-mapped I/O command interfaces (MC portals)
-which DPAA2 software drivers use to operate on DPAA2 objects.
-
-The diagram below shows an overview of the DPAA2 resource management
-architecture::
-
-	+--------------------------------------+
-	|                  OS                  |
-	|                        DPAA2 drivers |
-	|                             |        |
-	+-----------------------------|--------+
-	                              |
-	                              | (create,discover,connect
-	                              |  config,use,destroy)
-	                              |
-	                 DPAA2        |
-	+------------------------| mc portal |-+
-	|                             |        |
-	|   +- - - - - - - - - - - - -V- - -+  |
-	|   |                               |  |
-	|   |   Management Complex (MC)     |  |
-	|   |                               |  |
-	|   +- - - - - - - - - - - - - - - -+  |
-	|                                      |
-	| Hardware                  Hardware   |
-	| Resources                 Objects    |
-	| ---------                 -------    |
-	| -queues                   -DPRC      |
-	| -buffer pools             -DPMCP     |
-	| -Eth MACs/ports           -DPIO      |
-	| -network interface        -DPNI      |
-	|  profiles                 -DPMAC     |
-	| -queue portals            -DPBP      |
-	| -MC portals                ...       |
-	|  ...                                 |
-	|                                      |
-	+--------------------------------------+
-
-
-The MC mediates operations such as create, discover,
-connect, configuration, and destroy.  Fast-path operations
-on data, such as packet transmit/receive, are not mediated by
-the MC and are done directly using memory mapped regions in
-DPIO objects.
-
-Overview of DPAA2 Objects
-=========================
-
-The section provides a brief overview of some key DPAA2 objects.
-A simple scenario is described illustrating the objects involved
-in creating a network interfaces.
-
-DPRC (Datapath Resource Container)
-----------------------------------
-
-A DPRC is a container object that holds all the other
-types of DPAA2 objects.  In the example diagram below there
-are 8 objects of 5 types (DPMCP, DPIO, DPBP, DPNI, and DPMAC)
-in the container.
-
-::
-
-	+---------------------------------------------------------+
-	| DPRC                                                    |
-	|                                                         |
-	|  +-------+  +-------+  +-------+  +-------+  +-------+  |
-	|  | DPMCP |  | DPIO  |  | DPBP  |  | DPNI  |  | DPMAC |  |
-	|  +-------+  +-------+  +-------+  +---+---+  +---+---+  |
-	|  | DPMCP |  | DPIO  |                                   |
-	|  +-------+  +-------+                                   |
-	|  | DPMCP |                                              |
-	|  +-------+                                              |
-	|                                                         |
-	+---------------------------------------------------------+
-
-From the point of view of an OS, a DPRC behaves similar to a plug and
-play bus, like PCI.  DPRC commands can be used to enumerate the contents
-of the DPRC, discover the hardware objects present (including mappable
-regions and interrupts).
-
-::
-
-	DPRC.1 (bus)
-	   |
-	   +--+--------+-------+-------+-------+
-	      |        |       |       |       |
-	    DPMCP.1  DPIO.1  DPBP.1  DPNI.1  DPMAC.1
-	    DPMCP.2  DPIO.2
-	    DPMCP.3
-
-Hardware objects can be created and destroyed dynamically, providing
-the ability to hot plug/unplug objects in and out of the DPRC.
-
-A DPRC has a mappable MMIO region (an MC portal) that can be used
-to send MC commands.  It has an interrupt for status events (like
-hotplug).
-All objects in a container share the same hardware "isolation context".
-This means that with respect to an IOMMU the isolation granularity
-is at the DPRC (container) level, not at the individual object
-level.
-
-DPRCs can be defined statically and populated with objects
-via a config file passed to the MC when firmware starts it.
-
-DPAA2 Objects for an Ethernet Network Interface
------------------------------------------------
-
-A typical Ethernet NIC is monolithic-- the NIC device contains TX/RX
-queuing mechanisms, configuration mechanisms, buffer management,
-physical ports, and interrupts.  DPAA2 uses a more granular approach
-utilizing multiple hardware objects.  Each object provides specialized
-functions. Groups of these objects are used by software to provide
-Ethernet network interface functionality.  This approach provides
-efficient use of finite hardware resources, flexibility, and
-performance advantages.
-
-The diagram below shows the objects needed for a simple
-network interface configuration on a system with 2 CPUs.
-
-::
-
-	+---+---+ +---+---+
-	   CPU0     CPU1
-	+---+---+ +---+---+
-	    |         |
-	+---+---+ +---+---+
-	   DPIO     DPIO
-	+---+---+ +---+---+
-	    \     /
-	     \   /
-	      \ /
-	   +---+---+
-	      DPNI  --- DPBP,DPMCP
-	   +---+---+
-	       |
-	       |
-	   +---+---+
-	     DPMAC
-	   +---+---+
-	       |
-	   port/PHY
-
-Below the objects are described.  For each object a brief description
-is provided along with a summary of the kinds of operations the object
-supports and a summary of key resources of the object (MMIO regions
-and IRQs).
-
-DPMAC (Datapath Ethernet MAC)
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-Represents an Ethernet MAC, a hardware device that connects to an Ethernet
-PHY and allows physical transmission and reception of Ethernet frames.
-
-- MMIO regions: none
-- IRQs: DPNI link change
-- commands: set link up/down, link config, get stats,
-  IRQ config, enable, reset
-
-DPNI (Datapath Network Interface)
-Contains TX/RX queues, network interface configuration, and RX buffer pool
-configuration mechanisms.  The TX/RX queues are in memory and are identified
-by queue number.
-
-- MMIO regions: none
-- IRQs: link state
-- commands: port config, offload config, queue config,
-  parse/classify config, IRQ config, enable, reset
-
-DPIO (Datapath I/O)
-~~~~~~~~~~~~~~~~~~~
-Provides interfaces to enqueue and dequeue
-packets and do hardware buffer pool management operations.  The DPAA2
-architecture separates the mechanism to access queues (the DPIO object)
-from the queues themselves.  The DPIO provides an MMIO interface to
-enqueue/dequeue packets.  To enqueue something a descriptor is written
-to the DPIO MMIO region, which includes the target queue number.
-There will typically be one DPIO assigned to each CPU.  This allows all
-CPUs to simultaneously perform enqueue/dequeued operations.  DPIOs are
-expected to be shared by different DPAA2 drivers.
-
-- MMIO regions: queue operations, buffer management
-- IRQs: data availability, congestion notification, buffer
-  pool depletion
-- commands: IRQ config, enable, reset
-
-DPBP (Datapath Buffer Pool)
-~~~~~~~~~~~~~~~~~~~~~~~~~~~
-Represents a hardware buffer pool.
-
-- MMIO regions: none
-- IRQs: none
-- commands: enable, reset
-
-DPMCP (Datapath MC Portal)
-~~~~~~~~~~~~~~~~~~~~~~~~~~
-Provides an MC command portal.
-Used by drivers to send commands to the MC to manage
-objects.
-
-- MMIO regions: MC command portal
-- IRQs: command completion
-- commands: IRQ config, enable, reset
-
-Object Connections
-==================
-Some objects have explicit relationships that must
-be configured:
-
-- DPNI <--> DPMAC
-- DPNI <--> DPNI
-- DPNI <--> L2-switch-port
-
-    A DPNI must be connected to something such as a DPMAC,
-    another DPNI, or L2 switch port.  The DPNI connection
-    is made via a DPRC command.
-
-::
-
-              +-------+  +-------+
-              | DPNI  |  | DPMAC |
-              +---+---+  +---+---+
-                  |          |
-                  +==========+
-
-- DPNI <--> DPBP
-
-    A network interface requires a 'buffer pool' (DPBP
-    object) which provides a list of pointers to memory
-    where received Ethernet data is to be copied.  The
-    Ethernet driver configures the DPBPs associated with
-    the network interface.
-
-Interrupts
-==========
-All interrupts generated by DPAA2 objects are message
-interrupts.  At the hardware level message interrupts
-generated by devices will normally have 3 components--
-1) a non-spoofable 'device-id' expressed on the hardware
-bus, 2) an address, 3) a data value.
-
-In the case of DPAA2 devices/objects, all objects in the
-same container/DPRC share the same 'device-id'.
-For ARM-based SoC this is the same as the stream ID.
-
-
-DPAA2 Linux Drivers Overview
-============================
-
-This section provides an overview of the Linux kernel drivers for
-DPAA2-- 1) the bus driver and associated "DPAA2 infrastructure"
-drivers and 2) functional object drivers (such as Ethernet).
-
-As described previously, a DPRC is a container that holds the other
-types of DPAA2 objects.  It is functionally similar to a plug-and-play
-bus controller.
-Each object in the DPRC is a Linux "device" and is bound to a driver.
-The diagram below shows the Linux drivers involved in a networking
-scenario and the objects bound to each driver.  A brief description
-of each driver follows.
-
-::
-
-	                                     +------------+
-	                                     | OS Network |
-	                                     |   Stack    |
-	         +------------+              +------------+
-	         | Allocator  |. . . . . . . |  Ethernet  |
-	         |(DPMCP,DPBP)|              |   (DPNI)   |
-	         +-.----------+              +---+---+----+
-	          .          .                   ^   |
-	         .            .     <data avail, |   | <enqueue,
-	        .              .     tx confirm> |   | dequeue>
-	+-------------+         .                |   |
-	| DPRC driver |          .           +---+---V----+     +---------+
-	|   (DPRC)    |           . . . . . .| DPIO driver|     |   MAC   |
-	+----------+--+                      |  (DPIO)    |     | (DPMAC) |
-	           |                         +------+-----+     +-----+---+
-	           |<dev add/remove>                |                 |
-	           |                                |                 |
-	  +--------+----------+                     |              +--+---+
-	  |   MC-bus driver   |                     |              | PHY  |
-	  |                   |                     |              |driver|
-	  |   /bus/fsl-mc     |                     |              +--+---+
-	  +-------------------+                     |                 |
-	                                            |                 |
-	========================= HARDWARE =========|=================|======
-	                                          DPIO                |
-	                                            |                 |
-	                                          DPNI---DPBP         |
-	                                            |                 |
-	                                          DPMAC               |
-	                                            |                 |
-	                                           PHY ---------------+
-	============================================|========================
-
-A brief description of each driver is provided below.
-
-MC-bus driver
--------------
-The MC-bus driver is a platform driver and is probed from a
-node in the device tree (compatible "fsl,qoriq-mc") passed in by boot
-firmware.  It is responsible for bootstrapping the DPAA2 kernel
-infrastructure.
-Key functions include:
-
-- registering a new bus type named "fsl-mc" with the kernel,
-  and implementing bus call-backs (e.g. match/uevent/dev_groups)
-- implementing APIs for DPAA2 driver registration and for device
-  add/remove
-- creates an MSI IRQ domain
-- doing a 'device add' to expose the 'root' DPRC, in turn triggering
-  a bind of the root DPRC to the DPRC driver
-
-The binding for the MC-bus device-tree node can be consulted at
-*Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt*.
-The sysfs bind/unbind interfaces for the MC-bus can be consulted at
-*Documentation/ABI/testing/sysfs-bus-fsl-mc*.
-
-DPRC driver
------------
-The DPRC driver is bound to DPRC objects and does runtime management
-of a bus instance.  It performs the initial bus scan of the DPRC
-and handles interrupts for container events such as hot plug by
-re-scanning the DPRC.
-
-Allocator
----------
-Certain objects such as DPMCP and DPBP are generic and fungible,
-and are intended to be used by other drivers.  For example,
-the DPAA2 Ethernet driver needs:
-
-- DPMCPs to send MC commands, to configure network interfaces
-- DPBPs for network buffer pools
-
-The allocator driver registers for these allocatable object types
-and those objects are bound to the allocator when the bus is probed.
-The allocator maintains a pool of objects that are available for
-allocation by other DPAA2 drivers.
-
-DPIO driver
------------
-The DPIO driver is bound to DPIO objects and provides services that allow
-other drivers such as the Ethernet driver to enqueue and dequeue data for
-their respective objects.
-Key services include:
-
-- data availability notifications
-- hardware queuing operations (enqueue and dequeue of data)
-- hardware buffer pool management
-
-To transmit a packet the Ethernet driver puts data on a queue and
-invokes a DPIO API.  For receive, the Ethernet driver registers
-a data availability notification callback.  To dequeue a packet
-a DPIO API is used.
-There is typically one DPIO object per physical CPU for optimum
-performance, allowing different CPUs to simultaneously enqueue
-and dequeue data.
-
-The DPIO driver operates on behalf of all DPAA2 drivers
-active in the kernel--  Ethernet, crypto, compression,
-etc.
-
-Ethernet driver
----------------
-The Ethernet driver is bound to a DPNI and implements the kernel
-interfaces needed to connect the DPAA2 network interface to
-the network stack.
-Each DPNI corresponds to a Linux network interface.
-
-MAC driver
-----------
-An Ethernet PHY is an off-chip, board specific component and is managed
-by the appropriate PHY driver via an mdio bus.  The MAC driver
-plays a role of being a proxy between the PHY driver and the
-MC.  It does this proxy via the MC commands to a DPMAC object.
-If the PHY driver signals a link change, the MAC driver notifies
-the MC via a DPMAC command.  If a network interface is brought
-up or down, the MC notifies the DPMAC driver via an interrupt and
-the driver can take appropriate action.
diff --git a/Documentation/networking/e100.rst b/Documentation/networking/e100.rst
deleted file mode 100644
index 5e2839b4ec92..000000000000
--- a/Documentation/networking/e100.rst
+++ /dev/null
@@ -1,187 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters
-==============================================================
-
-June 1, 2018
-
-Contents
-========
-
-- In This Release
-- Identifying Your Adapter
-- Building and Installation
-- Driver Configuration Parameters
-- Additional Configurations
-- Known Issues
-- Support
-
-
-In This Release
-===============
-
-This file describes the Linux* Base Driver for the Intel(R) PRO/100 Family of
-Adapters. This driver includes support for Itanium(R)2-based systems.
-
-For questions related to hardware requirements, refer to the documentation
-supplied with your Intel PRO/100 adapter.
-
-The following features are now available in supported kernels:
- - Native VLANs
- - Channel Bonding (teaming)
- - SNMP
-
-Channel Bonding documentation can be found in the Linux kernel source:
-/Documentation/networking/bonding.txt
-
-
-Identifying Your Adapter
-========================
-
-For information on how to identify your adapter, and for the latest Intel
-network drivers, refer to the Intel Support website:
-http://www.intel.com/support
-
-Driver Configuration Parameters
-===============================
-
-The default value for each parameter is generally the recommended setting,
-unless otherwise noted.
-
-Rx Descriptors:
-   Number of receive descriptors. A receive descriptor is a data
-   structure that describes a receive buffer and its attributes to the network
-   controller. The data in the descriptor is used by the controller to write
-   data from the controller to host memory. In the 3.x.x driver the valid range
-   for this parameter is 64-256. The default value is 256. This parameter can be
-   changed using the command::
-
-     ethtool -G eth? rx n
-
-   Where n is the number of desired Rx descriptors.
-
-Tx Descriptors:
-   Number of transmit descriptors. A transmit descriptor is a data
-   structure that describes a transmit buffer and its attributes to the network
-   controller. The data in the descriptor is used by the controller to read
-   data from the host memory to the controller. In the 3.x.x driver the valid
-   range for this parameter is 64-256. The default value is 128. This parameter
-   can be changed using the command::
-
-     ethtool -G eth? tx n
-
-   Where n is the number of desired Tx descriptors.
-
-Speed/Duplex:
-   The driver auto-negotiates the link speed and duplex settings by
-   default. The ethtool utility can be used as follows to force speed/duplex.::
-
-     ethtool -s eth?  autoneg off speed {10|100} duplex {full|half}
-
-   NOTE: setting the speed/duplex to incorrect values will cause the link to
-   fail.
-
-Event Log Message Level:
-   The driver uses the message level flag to log events
-   to syslog. The message level can be set at driver load time. It can also be
-   set using the command::
-
-     ethtool -s eth? msglvl n
-
-
-Additional Configurations
-=========================
-
-Configuring the Driver on Different Distributions
--------------------------------------------------
-
-Configuring a network driver to load properly when the system is started
-is distribution dependent.  Typically, the configuration process involves
-adding an alias line to `/etc/modprobe.d/*.conf` as well as editing other
-system startup scripts and/or configuration files.  Many popular Linux
-distributions ship with tools to make these changes for you.  To learn
-the proper way to configure a network device for your system, refer to
-your distribution documentation.  If during this process you are asked
-for the driver or module name, the name for the Linux Base Driver for
-the Intel PRO/100 Family of Adapters is e100.
-
-As an example, if you install the e100 driver for two PRO/100 adapters
-(eth0 and eth1), add the following to a configuration file in
-/etc/modprobe.d/::
-
-       alias eth0 e100
-       alias eth1 e100
-
-Viewing Link Messages
----------------------
-
-In order to see link messages and other Intel driver information on your
-console, you must set the dmesg level up to six.  This can be done by
-entering the following on the command line before loading the e100
-driver::
-
-       dmesg -n 6
-
-If you wish to see all messages issued by the driver, including debug
-messages, set the dmesg level to eight.
-
-NOTE: This setting is not saved across reboots.
-
-ethtool
--------
-
-The driver utilizes the ethtool interface for driver configuration and
-diagnostics, as well as displaying statistical information.  The ethtool
-version 1.6 or later is required for this functionality.
-
-The latest release of ethtool can be found from
-https://www.kernel.org/pub/software/network/ethtool/
-
-Enabling Wake on LAN* (WoL)
----------------------------
-WoL is provided through the ethtool* utility.  For instructions on
-enabling WoL with ethtool, refer to the ethtool man page.  WoL will be
-enabled on the system during the next shut down or reboot.  For this
-driver version, in order to enable WoL, the e100 driver must be loaded
-when shutting down or rebooting the system.
-
-NAPI
-----
-
-NAPI (Rx polling mode) is supported in the e100 driver.
-
-See https://wiki.linuxfoundation.org/networking/napi for more
-information on NAPI.
-
-Multiple Interfaces on Same Ethernet Broadcast Network
-------------------------------------------------------
-
-Due to the default ARP behavior on Linux, it is not possible to have one
-system on two IP networks in the same Ethernet broadcast domain
-(non-partitioned switch) behave as expected.  All Ethernet interfaces
-will respond to IP traffic for any IP address assigned to the system.
-This results in unbalanced receive traffic.
-
-If you have multiple interfaces in a server, either turn on ARP
-filtering by
-
-(1) entering::
-
-	echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
-
-    (this only works if your kernel's version is higher than 2.4.5), or
-
-(2) installing the interfaces in separate broadcast domains (either
-    in different switches or in a switch partitioned to VLANs).
-
-
-Support
-=======
-For general information, go to the Intel support website at:
-http://www.intel.com/support/
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-http://sourceforge.net/projects/e1000
-If an issue is identified with the released source code on a supported kernel
-with a supported adapter, email the specific information related to the issue
-to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/e1000.rst b/Documentation/networking/e1000.rst
deleted file mode 100644
index 6379d4d20771..000000000000
--- a/Documentation/networking/e1000.rst
+++ /dev/null
@@ -1,462 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux* Base Driver for Intel(R) Ethernet Network Connection
-===========================================================
-
-Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2013 Intel Corporation.
-
-Contents
-========
-
-- Identifying Your Adapter
-- Command Line Parameters
-- Speed and Duplex Configuration
-- Additional Configurations
-- Support
-
-Identifying Your Adapter
-========================
-
-For more information on how to identify your adapter, go to the Adapter &
-Driver ID Guide at:
-
-    http://support.intel.com/support/go/network/adapter/idguide.htm
-
-For the latest Intel network drivers for Linux, refer to the following
-website.  In the search field, enter your adapter name or type, or use the
-networking link on the left to search for your adapter:
-
-    http://support.intel.com/support/go/network/adapter/home.htm
-
-Command Line Parameters
-=======================
-
-The default value for each parameter is generally the recommended setting,
-unless otherwise noted.
-
-NOTES:
-	For more information about the AutoNeg, Duplex, and Speed
-        parameters, see the "Speed and Duplex Configuration" section in
-        this document.
-
-        For more information about the InterruptThrottleRate,
-        RxIntDelay, TxIntDelay, RxAbsIntDelay, and TxAbsIntDelay
-        parameters, see the application note at:
-        http://www.intel.com/design/network/applnots/ap450.htm
-
-AutoNeg
--------
-
-(Supported only on adapters with copper connections)
-
-:Valid Range:   0x01-0x0F, 0x20-0x2F
-:Default Value: 0x2F
-
-This parameter is a bit-mask that specifies the speed and duplex settings
-advertised by the adapter.  When this parameter is used, the Speed and
-Duplex parameters must not be specified.
-
-NOTE:
-       Refer to the Speed and Duplex section of this readme for more
-       information on the AutoNeg parameter.
-
-Duplex
-------
-
-(Supported only on adapters with copper connections)
-
-:Valid Range:   0-2 (0=auto-negotiate, 1=half, 2=full)
-:Default Value: 0
-
-This defines the direction in which data is allowed to flow.  Can be
-either one or two-directional.  If both Duplex and the link partner are
-set to auto-negotiate, the board auto-detects the correct duplex.  If the
-link partner is forced (either full or half), Duplex defaults to half-
-duplex.
-
-FlowControl
------------
-
-:Valid Range:   0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
-:Default Value: Reads flow control settings from the EEPROM
-
-This parameter controls the automatic generation(Tx) and response(Rx)
-to Ethernet PAUSE frames.
-
-InterruptThrottleRate
----------------------
-
-(not supported on Intel(R) 82542, 82543 or 82544-based adapters)
-
-:Valid Range:
-   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
-   4=simplified balancing)
-:Default Value: 3
-
-The driver can limit the amount of interrupts per second that the adapter
-will generate for incoming packets. It does this by writing a value to the
-adapter that is based on the maximum amount of interrupts that the adapter
-will generate per second.
-
-Setting InterruptThrottleRate to a value greater or equal to 100
-will program the adapter to send out a maximum of that many interrupts
-per second, even if more packets have come in. This reduces interrupt
-load on the system and can lower CPU utilization under heavy load,
-but will increase latency as packets are not processed as quickly.
-
-The default behaviour of the driver previously assumed a static
-InterruptThrottleRate value of 8000, providing a good fallback value for
-all traffic types,but lacking in small packet performance and latency.
-The hardware can handle many more small packets per second however, and
-for this reason an adaptive interrupt moderation algorithm was implemented.
-
-Since 7.3.x, the driver has two adaptive modes (setting 1 or 3) in which
-it dynamically adjusts the InterruptThrottleRate value based on the traffic
-that it receives. After determining the type of incoming traffic in the last
-timeframe, it will adjust the InterruptThrottleRate to an appropriate value
-for that traffic.
-
-The algorithm classifies the incoming traffic every interval into
-classes.  Once the class is determined, the InterruptThrottleRate value is
-adjusted to suit that traffic type the best. There are three classes defined:
-"Bulk traffic", for large amounts of packets of normal size; "Low latency",
-for small amounts of traffic and/or a significant percentage of small
-packets; and "Lowest latency", for almost completely small packets or
-minimal traffic.
-
-In dynamic conservative mode, the InterruptThrottleRate value is set to 4000
-for traffic that falls in class "Bulk traffic". If traffic falls in the "Low
-latency" or "Lowest latency" class, the InterruptThrottleRate is increased
-stepwise to 20000. This default mode is suitable for most applications.
-
-For situations where low latency is vital such as cluster or
-grid computing, the algorithm can reduce latency even more when
-InterruptThrottleRate is set to mode 1. In this mode, which operates
-the same as mode 3, the InterruptThrottleRate will be increased stepwise to
-70000 for traffic in class "Lowest latency".
-
-In simplified mode the interrupt rate is based on the ratio of TX and
-RX traffic.  If the bytes per second rate is approximately equal, the
-interrupt rate will drop as low as 2000 interrupts per second.  If the
-traffic is mostly transmit or mostly receive, the interrupt rate could
-be as high as 8000.
-
-Setting InterruptThrottleRate to 0 turns off any interrupt moderation
-and may improve small packet latency, but is generally not suitable
-for bulk throughput traffic.
-
-NOTE:
-       InterruptThrottleRate takes precedence over the TxAbsIntDelay and
-       RxAbsIntDelay parameters.  In other words, minimizing the receive
-       and/or transmit absolute delays does not force the controller to
-       generate more interrupts than what the Interrupt Throttle Rate
-       allows.
-
-CAUTION:
-          If you are using the Intel(R) PRO/1000 CT Network Connection
-          (controller 82547), setting InterruptThrottleRate to a value
-          greater than 75,000, may hang (stop transmitting) adapters
-          under certain network conditions.  If this occurs a NETDEV
-          WATCHDOG message is logged in the system event log.  In
-          addition, the controller is automatically reset, restoring
-          the network connection.  To eliminate the potential for the
-          hang, ensure that InterruptThrottleRate is set no greater
-          than 75,000 and is not set to 0.
-
-NOTE:
-       When e1000 is loaded with default settings and multiple adapters
-       are in use simultaneously, the CPU utilization may increase non-
-       linearly.  In order to limit the CPU utilization without impacting
-       the overall throughput, we recommend that you load the driver as
-       follows::
-
-           modprobe e1000 InterruptThrottleRate=3000,3000,3000
-
-       This sets the InterruptThrottleRate to 3000 interrupts/sec for
-       the first, second, and third instances of the driver.  The range
-       of 2000 to 3000 interrupts per second works on a majority of
-       systems and is a good starting point, but the optimal value will
-       be platform-specific.  If CPU utilization is not a concern, use
-       RX_POLLING (NAPI) and default driver settings.
-
-RxDescriptors
--------------
-
-:Valid Range:
- - 48-256 for 82542 and 82543-based adapters
- - 48-4096 for all other supported adapters
-:Default Value: 256
-
-This value specifies the number of receive buffer descriptors allocated
-by the driver.  Increasing this value allows the driver to buffer more
-incoming packets, at the expense of increased system memory utilization.
-
-Each descriptor is 16 bytes.  A receive buffer is also allocated for each
-descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending
-on the MTU setting. The maximum MTU size is 16110.
-
-NOTE:
-       MTU designates the frame size.  It only needs to be set for Jumbo
-       Frames.  Depending on the available system resources, the request
-       for a higher number of receive descriptors may be denied.  In this
-       case, use a lower number.
-
-RxIntDelay
-----------
-
-:Valid Range:   0-65535 (0=off)
-:Default Value: 0
-
-This value delays the generation of receive interrupts in units of 1.024
-microseconds.  Receive interrupt reduction can improve CPU efficiency if
-properly tuned for specific network traffic.  Increasing this value adds
-extra latency to frame reception and can end up decreasing the throughput
-of TCP traffic.  If the system is reporting dropped receives, this value
-may be set too high, causing the driver to run out of available receive
-descriptors.
-
-CAUTION:
-          When setting RxIntDelay to a value other than 0, adapters may
-          hang (stop transmitting) under certain network conditions.  If
-          this occurs a NETDEV WATCHDOG message is logged in the system
-          event log.  In addition, the controller is automatically reset,
-          restoring the network connection.  To eliminate the potential
-          for the hang ensure that RxIntDelay is set to 0.
-
-RxAbsIntDelay
--------------
-
-(This parameter is supported only on 82540, 82545 and later adapters.)
-
-:Valid Range:   0-65535 (0=off)
-:Default Value: 128
-
-This value, in units of 1.024 microseconds, limits the delay in which a
-receive interrupt is generated.  Useful only if RxIntDelay is non-zero,
-this value ensures that an interrupt is generated after the initial
-packet is received within the set amount of time.  Proper tuning,
-along with RxIntDelay, may improve traffic throughput in specific network
-conditions.
-
-Speed
------
-
-(This parameter is supported only on adapters with copper connections.)
-
-:Valid Settings: 0, 10, 100, 1000
-:Default Value:  0 (auto-negotiate at all supported speeds)
-
-Speed forces the line speed to the specified value in megabits per second
-(Mbps).  If this parameter is not specified or is set to 0 and the link
-partner is set to auto-negotiate, the board will auto-detect the correct
-speed.  Duplex should also be set when Speed is set to either 10 or 100.
-
-TxDescriptors
--------------
-
-:Valid Range:
-  - 48-256 for 82542 and 82543-based adapters
-  - 48-4096 for all other supported adapters
-:Default Value: 256
-
-This value is the number of transmit descriptors allocated by the driver.
-Increasing this value allows the driver to queue more transmits.  Each
-descriptor is 16 bytes.
-
-NOTE:
-       Depending on the available system resources, the request for a
-       higher number of transmit descriptors may be denied.  In this case,
-       use a lower number.
-
-TxIntDelay
-----------
-
-:Valid Range:   0-65535 (0=off)
-:Default Value: 8
-
-This value delays the generation of transmit interrupts in units of
-1.024 microseconds.  Transmit interrupt reduction can improve CPU
-efficiency if properly tuned for specific network traffic.  If the
-system is reporting dropped transmits, this value may be set too high
-causing the driver to run out of available transmit descriptors.
-
-TxAbsIntDelay
--------------
-
-(This parameter is supported only on 82540, 82545 and later adapters.)
-
-:Valid Range:   0-65535 (0=off)
-:Default Value: 32
-
-This value, in units of 1.024 microseconds, limits the delay in which a
-transmit interrupt is generated.  Useful only if TxIntDelay is non-zero,
-this value ensures that an interrupt is generated after the initial
-packet is sent on the wire within the set amount of time.  Proper tuning,
-along with TxIntDelay, may improve traffic throughput in specific
-network conditions.
-
-XsumRX
-------
-
-(This parameter is NOT supported on the 82542-based adapter.)
-
-:Valid Range:   0-1
-:Default Value: 1
-
-A value of '1' indicates that the driver should enable IP checksum
-offload for received packets (both UDP and TCP) to the adapter hardware.
-
-Copybreak
----------
-
-:Valid Range:   0-xxxxxxx (0=off)
-:Default Value: 256
-:Usage: modprobe e1000.ko copybreak=128
-
-Driver copies all packets below or equaling this size to a fresh RX
-buffer before handing it up the stack.
-
-This parameter is different than other parameters, in that it is a
-single (not 1,1,1 etc.) parameter applied to all driver instances and
-it is also available during runtime at
-/sys/module/e1000/parameters/copybreak
-
-SmartPowerDownEnable
---------------------
-
-:Valid Range: 0-1
-:Default Value:  0 (disabled)
-
-Allows PHY to turn off in lower power states. The user can turn off
-this parameter in supported chipsets.
-
-Speed and Duplex Configuration
-==============================
-
-Three keywords are used to control the speed and duplex configuration.
-These keywords are Speed, Duplex, and AutoNeg.
-
-If the board uses a fiber interface, these keywords are ignored, and the
-fiber interface board only links at 1000 Mbps full-duplex.
-
-For copper-based boards, the keywords interact as follows:
-
-- The default operation is auto-negotiate.  The board advertises all
-  supported speed and duplex combinations, and it links at the highest
-  common speed and duplex mode IF the link partner is set to auto-negotiate.
-
-- If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps
-  is advertised (The 1000BaseT spec requires auto-negotiation.)
-
-- If Speed = 10 or 100, then both Speed and Duplex should be set.  Auto-
-  negotiation is disabled, and the AutoNeg parameter is ignored.  Partner
-  SHOULD also be forced.
-
-The AutoNeg parameter is used when more control is required over the
-auto-negotiation process.  It should be used when you wish to control which
-speed and duplex combinations are advertised during the auto-negotiation
-process.
-
-The parameter may be specified as either a decimal or hexadecimal value as
-determined by the bitmap below.
-
-============== ====== ====== ======= ======= ====== ====== ======= ======
-Bit position   7      6      5       4       3      2      1       0
-Decimal Value  128    64     32      16      8      4      2       1
-Hex value      80     40     20      10      8      4      2       1
-Speed (Mbps)   N/A    N/A    1000    N/A     100    100    10      10
-Duplex                       Full            Full   Half   Full    Half
-============== ====== ====== ======= ======= ====== ====== ======= ======
-
-Some examples of using AutoNeg::
-
-  modprobe e1000 AutoNeg=0x01 (Restricts autonegotiation to 10 Half)
-  modprobe e1000 AutoNeg=1 (Same as above)
-  modprobe e1000 AutoNeg=0x02 (Restricts autonegotiation to 10 Full)
-  modprobe e1000 AutoNeg=0x03 (Restricts autonegotiation to 10 Half or 10 Full)
-  modprobe e1000 AutoNeg=0x04 (Restricts autonegotiation to 100 Half)
-  modprobe e1000 AutoNeg=0x05 (Restricts autonegotiation to 10 Half or 100
-  Half)
-  modprobe e1000 AutoNeg=0x020 (Restricts autonegotiation to 1000 Full)
-  modprobe e1000 AutoNeg=32 (Same as above)
-
-Note that when this parameter is used, Speed and Duplex must not be specified.
-
-If the link partner is forced to a specific speed and duplex, then this
-parameter should not be used.  Instead, use the Speed and Duplex parameters
-previously mentioned to force the adapter to the same speed and duplex.
-
-Additional Configurations
-=========================
-
-Jumbo Frames
-------------
-
-  Jumbo Frames support is enabled by changing the MTU to a value larger than
-  the default of 1500.  Use the ifconfig command to increase the MTU size.
-  For example::
-
-       ifconfig eth<x> mtu 9000 up
-
-  This setting is not saved across reboots.  It can be made permanent if
-  you add::
-
-       MTU=9000
-
-  to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>.  This example
-  applies to the Red Hat distributions; other distributions may store this
-  setting in a different location.
-
-Notes:
-  Degradation in throughput performance may be observed in some Jumbo frames
-  environments. If this is observed, increasing the application's socket buffer
-  size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
-  See the specific application manual and /usr/src/linux*/Documentation/
-  networking/ip-sysctl.txt for more details.
-
-  - The maximum MTU setting for Jumbo Frames is 16110.  This value coincides
-    with the maximum Jumbo Frames size of 16128.
-
-  - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
-    poor performance or loss of link.
-
-  - Adapters based on the Intel(R) 82542 and 82573V/E controller do not
-    support Jumbo Frames. These correspond to the following product names::
-
-     Intel(R) PRO/1000 Gigabit Server Adapter
-     Intel(R) PRO/1000 PM Network Connection
-
-ethtool
--------
-
-  The driver utilizes the ethtool interface for driver configuration and
-  diagnostics, as well as displaying statistical information.  The ethtool
-  version 1.6 or later is required for this functionality.
-
-  The latest release of ethtool can be found from
-  https://www.kernel.org/pub/software/network/ethtool/
-
-Enabling Wake on LAN* (WoL)
----------------------------
-
-  WoL is configured through the ethtool* utility.
-
-  WoL will be enabled on the system during the next shut down or reboot.
-  For this driver version, in order to enable WoL, the e1000 driver must be
-  loaded when shutting down or rebooting the system.
-
-Support
-=======
-
-For general information, go to the Intel support website at:
-
-    http://support.intel.com
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-
-    http://sourceforge.net/projects/e1000
-
-If an issue is identified with the released source code on the supported
-kernel with a supported adapter, email the specific information related
-to the issue to e1000-devel@lists.sf.net
diff --git a/Documentation/networking/e1000e.rst b/Documentation/networking/e1000e.rst
deleted file mode 100644
index 33554e5416c5..000000000000
--- a/Documentation/networking/e1000e.rst
+++ /dev/null
@@ -1,382 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux* Driver for Intel(R) Ethernet Network Connection
-======================================================
-
-Intel Gigabit Linux driver.
-Copyright(c) 2008-2018 Intel Corporation.
-
-Contents
-========
-
-- Identifying Your Adapter
-- Command Line Parameters
-- Additional Configurations
-- Support
-
-
-Identifying Your Adapter
-========================
-For information on how to identify your adapter, and for the latest Intel
-network drivers, refer to the Intel Support website:
-https://www.intel.com/support
-
-
-Command Line Parameters
-=======================
-If the driver is built as a module, the following optional parameters are used
-by entering them on the command line with the modprobe command using this
-syntax::
-
-    modprobe e1000e [<option>=<VAL1>,<VAL2>,...]
-
-There needs to be a <VAL#> for each network port in the system supported by
-this driver. The values will be applied to each instance, in function order.
-For example::
-
-    modprobe e1000e InterruptThrottleRate=16000,16000
-
-In this case, there are two network ports supported by e1000e in the system.
-The default value for each parameter is generally the recommended setting,
-unless otherwise noted.
-
-NOTE: A descriptor describes a data buffer and attributes related to the data
-buffer. This information is accessed by the hardware.
-
-InterruptThrottleRate
----------------------
-:Valid Range: 0,1,3,4,100-100000
-:Default Value: 3
-
-Interrupt Throttle Rate controls the number of interrupts each interrupt
-vector can generate per second. Increasing ITR lowers latency at the cost of
-increased CPU utilization, though it may help throughput in some circumstances.
-
-Setting InterruptThrottleRate to a value greater or equal to 100
-will program the adapter to send out a maximum of that many interrupts
-per second, even if more packets have come in. This reduces interrupt
-load on the system and can lower CPU utilization under heavy load,
-but will increase latency as packets are not processed as quickly.
-
-The default behaviour of the driver previously assumed a static
-InterruptThrottleRate value of 8000, providing a good fallback value for
-all traffic types, but lacking in small packet performance and latency.
-The hardware can handle many more small packets per second however, and
-for this reason an adaptive interrupt moderation algorithm was implemented.
-
-The driver has two adaptive modes (setting 1 or 3) in which
-it dynamically adjusts the InterruptThrottleRate value based on the traffic
-that it receives. After determining the type of incoming traffic in the last
-timeframe, it will adjust the InterruptThrottleRate to an appropriate value
-for that traffic.
-
-The algorithm classifies the incoming traffic every interval into
-classes.  Once the class is determined, the InterruptThrottleRate value is
-adjusted to suit that traffic type the best. There are three classes defined:
-"Bulk traffic", for large amounts of packets of normal size; "Low latency",
-for small amounts of traffic and/or a significant percentage of small
-packets; and "Lowest latency", for almost completely small packets or
-minimal traffic.
-
- - 0: Off
-      Turns off any interrupt moderation and may improve small packet latency.
-      However, this is generally not suitable for bulk throughput traffic due
-      to the increased CPU utilization of the higher interrupt rate.
- - 1: Dynamic mode
-      This mode attempts to moderate interrupts per vector while maintaining
-      very low latency. This can sometimes cause extra CPU utilization. If
-      planning on deploying e1000e in a latency sensitive environment, this
-      parameter should be considered.
- - 3: Dynamic Conservative mode (default)
-      In dynamic conservative mode, the InterruptThrottleRate value is set to
-      4000 for traffic that falls in class "Bulk traffic". If traffic falls in
-      the "Low latency" or "Lowest latency" class, the InterruptThrottleRate is
-      increased stepwise to 20000. This default mode is suitable for most
-      applications.
- - 4: Simplified Balancing mode
-      In simplified mode the interrupt rate is based on the ratio of TX and
-      RX traffic.  If the bytes per second rate is approximately equal, the
-      interrupt rate will drop as low as 2000 interrupts per second.  If the
-      traffic is mostly transmit or mostly receive, the interrupt rate could
-      be as high as 8000.
- - 100-100000:
-      Setting InterruptThrottleRate to a value greater or equal to 100
-      will program the adapter to send at most that many interrupts per second,
-      even if more packets have come in. This reduces interrupt load on the
-      system and can lower CPU utilization under heavy load, but will increase
-      latency as packets are not processed as quickly.
-
-NOTE: InterruptThrottleRate takes precedence over the TxAbsIntDelay and
-RxAbsIntDelay parameters. In other words, minimizing the receive and/or
-transmit absolute delays does not force the controller to generate more
-interrupts than what the Interrupt Throttle Rate allows.
-
-RxIntDelay
-----------
-:Valid Range: 0-65535 (0=off)
-:Default Value: 0
-
-This value delays the generation of receive interrupts in units of 1.024
-microseconds. Receive interrupt reduction can improve CPU efficiency if
-properly tuned for specific network traffic. Increasing this value adds extra
-latency to frame reception and can end up decreasing the throughput of TCP
-traffic. If the system is reporting dropped receives, this value may be set
-too high, causing the driver to run out of available receive descriptors.
-
-CAUTION: When setting RxIntDelay to a value other than 0, adapters may hang
-(stop transmitting) under certain network conditions. If this occurs a NETDEV
-WATCHDOG message is logged in the system event log. In addition, the
-controller is automatically reset, restoring the network connection. To
-eliminate the potential for the hang ensure that RxIntDelay is set to 0.
-
-RxAbsIntDelay
--------------
-:Valid Range: 0-65535 (0=off)
-:Default Value: 8
-
-This value, in units of 1.024 microseconds, limits the delay in which a
-receive interrupt is generated. This value ensures that an interrupt is
-generated after the initial packet is received within the set amount of time,
-which is useful only if RxIntDelay is non-zero. Proper tuning, along with
-RxIntDelay, may improve traffic throughput in specific network conditions.
-
-TxIntDelay
-----------
-:Valid Range: 0-65535 (0=off)
-:Default Value: 8
-
-This value delays the generation of transmit interrupts in units of 1.024
-microseconds. Transmit interrupt reduction can improve CPU efficiency if
-properly tuned for specific network traffic. If the system is reporting
-dropped transmits, this value may be set too high causing the driver to run
-out of available transmit descriptors.
-
-TxAbsIntDelay
--------------
-:Valid Range: 0-65535 (0=off)
-:Default Value: 32
-
-This value, in units of 1.024 microseconds, limits the delay in which a
-transmit interrupt is generated. It is useful only if TxIntDelay is non-zero.
-It ensures that an interrupt is generated after the initial Packet is sent on
-the wire within the set amount of time. Proper tuning, along with TxIntDelay,
-may improve traffic throughput in specific network conditions.
-
-copybreak
----------
-:Valid Range: 0-xxxxxxx (0=off)
-:Default Value: 256
-
-The driver copies all packets below or equaling this size to a fresh receive
-buffer before handing it up the stack.
-This parameter differs from other parameters because it is a single (not 1,1,1
-etc.) parameter applied to all driver instances and it is also available
-during runtime at /sys/module/e1000e/parameters/copybreak.
-
-To use copybreak, type::
-
-    modprobe e1000e.ko copybreak=128
-
-SmartPowerDownEnable
---------------------
-:Valid Range: 0,1
-:Default Value: 0 (disabled)
-
-Allows the PHY to turn off in lower power states. The user can turn off this
-parameter in supported chipsets.
-
-KumeranLockLoss
----------------
-:Valid Range: 0,1
-:Default Value: 1 (enabled)
-
-This workaround skips resetting the PHY at shutdown for the initial silicon
-releases of ICH8 systems.
-
-IntMode
--------
-:Valid Range: 0-2
-:Default Value: 0
-
-   +-------+----------------+
-   | Value | Interrupt Mode |
-   +=======+================+
-   |   0   |     Legacy     |
-   +-------+----------------+
-   |   1   |       MSI      |
-   +-------+----------------+
-   |   2   |      MSI-X     |
-   +-------+----------------+
-
-IntMode allows load time control over the type of interrupt registered for by
-the driver. MSI-X is required for multiple queue support, and some kernels and
-combinations of kernel .config options will force a lower level of interrupt
-support.
-
-This command will show different values for each type of interrupt::
-
-  cat /proc/interrupts
-
-CrcStripping
-------------
-:Valid Range: 0,1
-:Default Value: 1 (enabled)
-
-Strip the CRC from received packets before sending up the network stack. If
-you have a machine with a BMC enabled but cannot receive IPMI traffic after
-loading or enabling the driver, try disabling this feature.
-
-WriteProtectNVM
----------------
-:Valid Range: 0,1
-:Default Value: 1 (enabled)
-
-If set to 1, configure the hardware to ignore all write/erase cycles to the
-GbE region in the ICHx NVM (in order to prevent accidental corruption of the
-NVM). This feature can be disabled by setting the parameter to 0 during initial
-driver load.
-
-NOTE: The machine must be power cycled (full off/on) when enabling NVM writes
-via setting the parameter to zero. Once the NVM has been locked (via the
-parameter at 1 when the driver loads) it cannot be unlocked except via power
-cycle.
-
-Debug
------
-:Valid Range: 0-16 (0=none,...,16=all)
-:Default Value: 0
-
-This parameter adjusts the level of debug messages displayed in the system logs.
-
-
-Additional Features and Configurations
-======================================
-
-Jumbo Frames
-------------
-Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU)
-to a value larger than the default value of 1500.
-
-Use the ifconfig command to increase the MTU size. For example, enter the
-following where <x> is the interface number::
-
-    ifconfig eth<x> mtu 9000 up
-
-Alternatively, you can use the ip command as follows::
-
-    ip link set mtu 9000 dev eth<x>
-    ip link set up dev eth<x>
-
-This setting is not saved across reboots. The setting change can be made
-permanent by adding 'MTU=9000' to the file:
-
-- For RHEL: /etc/sysconfig/network-scripts/ifcfg-eth<x>
-- For SLES: /etc/sysconfig/network/<config_file>
-
-NOTE: The maximum MTU setting for Jumbo Frames is 8996. This value coincides
-with the maximum Jumbo Frames size of 9018 bytes.
-
-NOTE: Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
-poor performance or loss of link.
-
-NOTE: The following adapters limit Jumbo Frames sized packets to a maximum of
-4088 bytes:
-
-  - Intel(R) 82578DM Gigabit Network Connection
-  - Intel(R) 82577LM Gigabit Network Connection
-
-The following adapters do not support Jumbo Frames:
-
-  - Intel(R) PRO/1000 Gigabit Server Adapter
-  - Intel(R) PRO/1000 PM Network Connection
-  - Intel(R) 82562G 10/100 Network Connection
-  - Intel(R) 82562G-2 10/100 Network Connection
-  - Intel(R) 82562GT 10/100 Network Connection
-  - Intel(R) 82562GT-2 10/100 Network Connection
-  - Intel(R) 82562V 10/100 Network Connection
-  - Intel(R) 82562V-2 10/100 Network Connection
-  - Intel(R) 82566DC Gigabit Network Connection
-  - Intel(R) 82566DC-2 Gigabit Network Connection
-  - Intel(R) 82566DM Gigabit Network Connection
-  - Intel(R) 82566MC Gigabit Network Connection
-  - Intel(R) 82566MM Gigabit Network Connection
-  - Intel(R) 82567V-3 Gigabit Network Connection
-  - Intel(R) 82577LC Gigabit Network Connection
-  - Intel(R) 82578DC Gigabit Network Connection
-
-NOTE: Jumbo Frames cannot be configured on an 82579-based Network device if
-MACSec is enabled on the system.
-
-
-ethtool
--------
-The driver utilizes the ethtool interface for driver configuration and
-diagnostics, as well as displaying statistical information. The latest ethtool
-version is required for this functionality. Download it at:
-
-https://www.kernel.org/pub/software/network/ethtool/
-
-NOTE: When validating enable/disable tests on some parts (for example, 82578),
-it is necessary to add a few seconds between tests when working with ethtool.
-
-
-Speed and Duplex Configuration
-------------------------------
-In addressing speed and duplex configuration issues, you need to distinguish
-between copper-based adapters and fiber-based adapters.
-
-In the default mode, an Intel(R) Ethernet Network Adapter using copper
-connections will attempt to auto-negotiate with its link partner to determine
-the best setting. If the adapter cannot establish link with the link partner
-using auto-negotiation, you may need to manually configure the adapter and link
-partner to identical settings to establish link and pass packets. This should
-only be needed when attempting to link with an older switch that does not
-support auto-negotiation or one that has been forced to a specific speed or
-duplex mode. Your link partner must match the setting you choose. 1 Gbps speeds
-and higher cannot be forced. Use the autonegotiation advertising setting to
-manually set devices for 1 Gbps and higher.
-
-Speed, duplex, and autonegotiation advertising are configured through the
-ethtool* utility.
-
-Caution: Only experienced network administrators should force speed and duplex
-or change autonegotiation advertising manually. The settings at the switch must
-always match the adapter settings. Adapter performance may suffer or your
-adapter may not operate if you configure the adapter differently from your
-switch.
-
-An Intel(R) Ethernet Network Adapter using fiber-based connections, however,
-will not attempt to auto-negotiate with its link partner since those adapters
-operate only in full duplex and only at their native speed.
-
-
-Enabling Wake on LAN* (WoL)
----------------------------
-WoL is configured through the ethtool* utility.
-
-WoL will be enabled on the system during the next shut down or reboot. For
-this driver version, in order to enable WoL, the e1000e driver must be loaded
-prior to shutting down or suspending the system.
-
-NOTE: Wake on LAN is only supported on port A for the following devices:
-- Intel(R) PRO/1000 PT Dual Port Network Connection
-- Intel(R) PRO/1000 PT Dual Port Server Connection
-- Intel(R) PRO/1000 PT Dual Port Server Adapter
-- Intel(R) PRO/1000 PF Dual Port Server Adapter
-- Intel(R) PRO/1000 PT Quad Port Server Adapter
-- Intel(R) Gigabit PT Quad Port Server ExpressModule
-
-
-Support
-=======
-For general information, go to the Intel support website at:
-
-https://www.intel.com/support/
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-
-https://sourceforge.net/projects/e1000
-
-If an issue is identified with the released source code on a supported kernel
-with a supported adapter, email the specific information related to the issue
-to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/ena.txt b/Documentation/networking/ena.txt
deleted file mode 100644
index 2b4b6f57e549..000000000000
--- a/Documentation/networking/ena.txt
+++ /dev/null
@@ -1,305 +0,0 @@
-Linux kernel driver for Elastic Network Adapter (ENA) family:
-=============================================================
-
-Overview:
-=========
-ENA is a networking interface designed to make good use of modern CPU
-features and system architectures.
-
-The ENA device exposes a lightweight management interface with a
-minimal set of memory mapped registers and extendable command set
-through an Admin Queue.
-
-The driver supports a range of ENA devices, is link-speed independent
-(i.e., the same driver is used for 10GbE, 25GbE, 40GbE, etc.), and has
-a negotiated and extendable feature set.
-
-Some ENA devices support SR-IOV. This driver is used for both the
-SR-IOV Physical Function (PF) and Virtual Function (VF) devices.
-
-ENA devices enable high speed and low overhead network traffic
-processing by providing multiple Tx/Rx queue pairs (the maximum number
-is advertised by the device via the Admin Queue), a dedicated MSI-X
-interrupt vector per Tx/Rx queue pair, adaptive interrupt moderation,
-and CPU cacheline optimized data placement.
-
-The ENA driver supports industry standard TCP/IP offload features such
-as checksum offload and TCP transmit segmentation offload (TSO).
-Receive-side scaling (RSS) is supported for multi-core scaling.
-
-The ENA driver and its corresponding devices implement health
-monitoring mechanisms such as watchdog, enabling the device and driver
-to recover in a manner transparent to the application, as well as
-debug logs.
-
-Some of the ENA devices support a working mode called Low-latency
-Queue (LLQ), which saves several more microseconds.
-
-Supported PCI vendor ID/device IDs:
-===================================
-1d0f:0ec2 - ENA PF
-1d0f:1ec2 - ENA PF with LLQ support
-1d0f:ec20 - ENA VF
-1d0f:ec21 - ENA VF with LLQ support
-
-ENA Source Code Directory Structure:
-====================================
-ena_com.[ch]      - Management communication layer. This layer is
-                    responsible for the handling all the management
-                    (admin) communication between the device and the
-                    driver.
-ena_eth_com.[ch]  - Tx/Rx data path.
-ena_admin_defs.h  - Definition of ENA management interface.
-ena_eth_io_defs.h - Definition of ENA data path interface.
-ena_common_defs.h - Common definitions for ena_com layer.
-ena_regs_defs.h   - Definition of ENA PCI memory-mapped (MMIO) registers.
-ena_netdev.[ch]   - Main Linux kernel driver.
-ena_syfsfs.[ch]   - Sysfs files.
-ena_ethtool.c     - ethtool callbacks.
-ena_pci_id_tbl.h  - Supported device IDs.
-
-Management Interface:
-=====================
-ENA management interface is exposed by means of:
-- PCIe Configuration Space
-- Device Registers
-- Admin Queue (AQ) and Admin Completion Queue (ACQ)
-- Asynchronous Event Notification Queue (AENQ)
-
-ENA device MMIO Registers are accessed only during driver
-initialization and are not involved in further normal device
-operation.
-
-AQ is used for submitting management commands, and the
-results/responses are reported asynchronously through ACQ.
-
-ENA introduces a very small set of management commands with room for
-vendor-specific extensions. Most of the management operations are
-framed in a generic Get/Set feature command.
-
-The following admin queue commands are supported:
-- Create I/O submission queue
-- Create I/O completion queue
-- Destroy I/O submission queue
-- Destroy I/O completion queue
-- Get feature
-- Set feature
-- Configure AENQ
-- Get statistics
-
-Refer to ena_admin_defs.h for the list of supported Get/Set Feature
-properties.
-
-The Asynchronous Event Notification Queue (AENQ) is a uni-directional
-queue used by the ENA device to send to the driver events that cannot
-be reported using ACQ. AENQ events are subdivided into groups. Each
-group may have multiple syndromes, as shown below
-
-The events are:
-	Group			Syndrome
-	Link state change	- X -
-	Fatal error		- X -
-	Notification		Suspend traffic
-	Notification		Resume traffic
-	Keep-Alive		- X -
-
-ACQ and AENQ share the same MSI-X vector.
-
-Keep-Alive is a special mechanism that allows monitoring of the
-device's health. The driver maintains a watchdog (WD) handler which,
-if fired, logs the current state and statistics then resets and
-restarts the ENA device and driver. A Keep-Alive event is delivered by
-the device every second. The driver re-arms the WD upon reception of a
-Keep-Alive event. A missed Keep-Alive event causes the WD handler to
-fire.
-
-Data Path Interface:
-====================
-I/O operations are based on Tx and Rx Submission Queues (Tx SQ and Rx
-SQ correspondingly). Each SQ has a completion queue (CQ) associated
-with it.
-
-The SQs and CQs are implemented as descriptor rings in contiguous
-physical memory.
-
-The ENA driver supports two Queue Operation modes for Tx SQs:
-- Regular mode
-  * In this mode the Tx SQs reside in the host's memory. The ENA
-    device fetches the ENA Tx descriptors and packet data from host
-    memory.
-- Low Latency Queue (LLQ) mode or "push-mode".
-  * In this mode the driver pushes the transmit descriptors and the
-    first 128 bytes of the packet directly to the ENA device memory
-    space. The rest of the packet payload is fetched by the
-    device. For this operation mode, the driver uses a dedicated PCI
-    device memory BAR, which is mapped with write-combine capability.
-
-The Rx SQs support only the regular mode.
-
-Note: Not all ENA devices support LLQ, and this feature is negotiated
-      with the device upon initialization. If the ENA device does not
-      support LLQ mode, the driver falls back to the regular mode.
-
-The driver supports multi-queue for both Tx and Rx. This has various
-benefits:
-- Reduced CPU/thread/process contention on a given Ethernet interface.
-- Cache miss rate on completion is reduced, particularly for data
-  cache lines that hold the sk_buff structures.
-- Increased process-level parallelism when handling received packets.
-- Increased data cache hit rate, by steering kernel processing of
-  packets to the CPU, where the application thread consuming the
-  packet is running.
-- In hardware interrupt re-direction.
-
-Interrupt Modes:
-================
-The driver assigns a single MSI-X vector per queue pair (for both Tx
-and Rx directions). The driver assigns an additional dedicated MSI-X vector
-for management (for ACQ and AENQ).
-
-Management interrupt registration is performed when the Linux kernel
-probes the adapter, and it is de-registered when the adapter is
-removed. I/O queue interrupt registration is performed when the Linux
-interface of the adapter is opened, and it is de-registered when the
-interface is closed.
-
-The management interrupt is named:
-   ena-mgmnt@pci:<PCI domain:bus:slot.function>
-and for each queue pair, an interrupt is named:
-   <interface name>-Tx-Rx-<queue index>
-
-The ENA device operates in auto-mask and auto-clear interrupt
-modes. That is, once MSI-X is delivered to the host, its Cause bit is
-automatically cleared and the interrupt is masked. The interrupt is
-unmasked by the driver after NAPI processing is complete.
-
-Interrupt Moderation:
-=====================
-ENA driver and device can operate in conventional or adaptive interrupt
-moderation mode.
-
-In conventional mode the driver instructs device to postpone interrupt
-posting according to static interrupt delay value. The interrupt delay
-value can be configured through ethtool(8). The following ethtool
-parameters are supported by the driver: tx-usecs, rx-usecs
-
-In adaptive interrupt moderation mode the interrupt delay value is
-updated by the driver dynamically and adjusted every NAPI cycle
-according to the traffic nature.
-
-By default ENA driver applies adaptive coalescing on Rx traffic and
-conventional coalescing on Tx traffic.
-
-Adaptive coalescing can be switched on/off through ethtool(8)
-adaptive_rx on|off parameter.
-
-The driver chooses interrupt delay value according to the number of
-bytes and packets received between interrupt unmasking and interrupt
-posting. The driver uses interrupt delay table that subdivides the
-range of received bytes/packets into 5 levels and assigns interrupt
-delay value to each level.
-
-The user can enable/disable adaptive moderation, modify the interrupt
-delay table and restore its default values through sysfs.
-
-The rx_copybreak is initialized by default to ENA_DEFAULT_RX_COPYBREAK
-and can be configured by the ETHTOOL_STUNABLE command of the
-SIOCETHTOOL ioctl.
-
-SKB:
-The driver-allocated SKB for frames received from Rx handling using
-NAPI context. The allocation method depends on the size of the packet.
-If the frame length is larger than rx_copybreak, napi_get_frags()
-is used, otherwise netdev_alloc_skb_ip_align() is used, the buffer
-content is copied (by CPU) to the SKB, and the buffer is recycled.
-
-Statistics:
-===========
-The user can obtain ENA device and driver statistics using ethtool.
-The driver can collect regular or extended statistics (including
-per-queue stats) from the device.
-
-In addition the driver logs the stats to syslog upon device reset.
-
-MTU:
-====
-The driver supports an arbitrarily large MTU with a maximum that is
-negotiated with the device. The driver configures MTU using the
-SetFeature command (ENA_ADMIN_MTU property). The user can change MTU
-via ip(8) and similar legacy tools.
-
-Stateless Offloads:
-===================
-The ENA driver supports:
-- TSO over IPv4/IPv6
-- TSO with ECN
-- IPv4 header checksum offload
-- TCP/UDP over IPv4/IPv6 checksum offloads
-
-RSS:
-====
-- The ENA device supports RSS that allows flexible Rx traffic
-  steering.
-- Toeplitz and CRC32 hash functions are supported.
-- Different combinations of L2/L3/L4 fields can be configured as
-  inputs for hash functions.
-- The driver configures RSS settings using the AQ SetFeature command
-  (ENA_ADMIN_RSS_HASH_FUNCTION, ENA_ADMIN_RSS_HASH_INPUT and
-  ENA_ADMIN_RSS_REDIRECTION_TABLE_CONFIG properties).
-- If the NETIF_F_RXHASH flag is set, the 32-bit result of the hash
-  function delivered in the Rx CQ descriptor is set in the received
-  SKB.
-- The user can provide a hash key, hash function, and configure the
-  indirection table through ethtool(8).
-
-DATA PATH:
-==========
-Tx:
----
-end_start_xmit() is called by the stack. This function does the following:
-- Maps data buffers (skb->data and frags).
-- Populates ena_buf for the push buffer (if the driver and device are
-  in push mode.)
-- Prepares ENA bufs for the remaining frags.
-- Allocates a new request ID from the empty req_id ring. The request
-  ID is the index of the packet in the Tx info. This is used for
-  out-of-order TX completions.
-- Adds the packet to the proper place in the Tx ring.
-- Calls ena_com_prepare_tx(), an ENA communication layer that converts
-  the ena_bufs to ENA descriptors (and adds meta ENA descriptors as
-  needed.)
-  * This function also copies the ENA descriptors and the push buffer
-    to the Device memory space (if in push mode.)
-- Writes doorbell to the ENA device.
-- When the ENA device finishes sending the packet, a completion
-  interrupt is raised.
-- The interrupt handler schedules NAPI.
-- The ena_clean_tx_irq() function is called. This function handles the
-  completion descriptors generated by the ENA, with a single
-  completion descriptor per completed packet.
-  * req_id is retrieved from the completion descriptor. The tx_info of
-    the packet is retrieved via the req_id. The data buffers are
-    unmapped and req_id is returned to the empty req_id ring.
-  * The function stops when the completion descriptors are completed or
-    the budget is reached.
-
-Rx:
----
-- When a packet is received from the ENA device.
-- The interrupt handler schedules NAPI.
-- The ena_clean_rx_irq() function is called. This function calls
-  ena_rx_pkt(), an ENA communication layer function, which returns the
-  number of descriptors used for a new unhandled packet, and zero if
-  no new packet is found.
-- Then it calls the ena_clean_rx_irq() function.
-- ena_eth_rx_skb() checks packet length:
-  * If the packet is small (len < rx_copybreak), the driver allocates
-    a SKB for the new packet, and copies the packet payload into the
-    SKB data buffer.
-    - In this way the original data buffer is not passed to the stack
-      and is reused for future Rx packets.
-  * Otherwise the function unmaps the Rx buffer, then allocates the
-    new SKB structure and hooks the Rx buffer to the SKB frags.
-- The new SKB is updated with the necessary information (protocol,
-  checksum hw verify result, etc.), and then passed to the network
-  stack, using the NAPI interface function napi_gro_receive().
diff --git a/Documentation/networking/fm10k.rst b/Documentation/networking/fm10k.rst
deleted file mode 100644
index bf5e5942f28d..000000000000
--- a/Documentation/networking/fm10k.rst
+++ /dev/null
@@ -1,141 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux* Base Driver for Intel(R) Ethernet Multi-host Controller
-==============================================================
-
-August 20, 2018
-Copyright(c) 2015-2018 Intel Corporation.
-
-Contents
-========
-- Identifying Your Adapter
-- Additional Configurations
-- Performance Tuning
-- Known Issues
-- Support
-
-Identifying Your Adapter
-========================
-The driver in this release is compatible with devices based on the Intel(R)
-Ethernet Multi-host Controller.
-
-For information on how to identify your adapter, and for the latest Intel
-network drivers, refer to the Intel Support website:
-http://www.intel.com/support
-
-
-Flow Control
-------------
-The Intel(R) Ethernet Switch Host Interface Driver does not support Flow
-Control. It will not send pause frames. This may result in dropped frames.
-
-
-Virtual Functions (VFs)
------------------------
-Use sysfs to enable VFs.
-Valid Range: 0-64
-
-For example::
-
-    echo $num_vf_enabled > /sys/class/net/$dev/device/sriov_numvfs //enable VFs
-    echo 0 > /sys/class/net/$dev/device/sriov_numvfs //disable VFs
-
-NOTE: Neither the device nor the driver control how VFs are mapped into config
-space. Bus layout will vary by operating system. On operating systems that
-support it, you can check sysfs to find the mapping.
-
-NOTE: When SR-IOV mode is enabled, hardware VLAN filtering and VLAN tag
-stripping/insertion will remain enabled. Please remove the old VLAN filter
-before the new VLAN filter is added. For example::
-
-    ip link set eth0 vf 0 vlan 100	// set vlan 100 for VF 0
-    ip link set eth0 vf 0 vlan 0	// Delete vlan 100
-    ip link set eth0 vf 0 vlan 200	// set a new vlan 200 for VF 0
-
-
-Additional Features and Configurations
-======================================
-
-Jumbo Frames
-------------
-Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU)
-to a value larger than the default value of 1500.
-
-Use the ifconfig command to increase the MTU size. For example, enter the
-following where <x> is the interface number::
-
-    ifconfig eth<x> mtu 9000 up
-
-Alternatively, you can use the ip command as follows::
-
-    ip link set mtu 9000 dev eth<x>
-    ip link set up dev eth<x>
-
-This setting is not saved across reboots. The setting change can be made
-permanent by adding 'MTU=9000' to the file:
-
-- For RHEL: /etc/sysconfig/network-scripts/ifcfg-eth<x>
-- For SLES: /etc/sysconfig/network/<config_file>
-
-NOTE: The maximum MTU setting for Jumbo Frames is 15342. This value coincides
-with the maximum Jumbo Frames size of 15364 bytes.
-
-NOTE: This driver will attempt to use multiple page sized buffers to receive
-each jumbo packet. This should help to avoid buffer starvation issues when
-allocating receive packets.
-
-
-Generic Receive Offload, aka GRO
---------------------------------
-The driver supports the in-kernel software implementation of GRO. GRO has
-shown that by coalescing Rx traffic into larger chunks of data, CPU
-utilization can be significantly reduced when under large Rx load. GRO is an
-evolution of the previously-used LRO interface. GRO is able to coalesce
-other protocols besides TCP. It's also safe to use with configurations that
-are problematic for LRO, namely bridging and iSCSI.
-
-
-
-Supported ethtool Commands and Options for Filtering
-----------------------------------------------------
--n --show-nfc
-  Retrieves the receive network flow classification configurations.
-
-rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6
-  Retrieves the hash options for the specified network traffic type.
-
--N --config-nfc
-  Configures the receive network flow classification.
-
-rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6 m|v|t|s|d|f|n|r
-  Configures the hash options for the specified network traffic type.
-
-- udp4: UDP over IPv4
-- udp6: UDP over IPv6
-- f Hash on bytes 0 and 1 of the Layer 4 header of the rx packet.
-- n Hash on bytes 2 and 3 of the Layer 4 header of the rx packet.
-
-
-Known Issues/Troubleshooting
-============================
-
-Enabling SR-IOV in a 64-bit Microsoft* Windows Server* 2012/R2 guest OS under Linux KVM
----------------------------------------------------------------------------------------
-KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM. This
-includes traditional PCIe devices, as well as SR-IOV-capable devices based on
-the Intel Ethernet Controller XL710.
-
-
-Support
-=======
-For general information, go to the Intel support website at:
-
-https://www.intel.com/support/
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-
-https://sourceforge.net/projects/e1000
-
-If an issue is identified with the released source code on a supported kernel
-with a supported adapter, email the specific information related to the issue
-to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/gianfar.txt b/Documentation/networking/gianfar.txt
deleted file mode 100644
index ba1daea7f2e4..000000000000
--- a/Documentation/networking/gianfar.txt
+++ /dev/null
@@ -1,42 +0,0 @@
-The Gianfar Ethernet Driver
-
-Author: Andy Fleming <afleming@freescale.com>
-Updated: 2005-07-28
-
-
-CHECKSUM OFFLOADING
-
-The eTSEC controller (first included in parts from late 2005 like
-the 8548) has the ability to perform TCP, UDP, and IP checksums
-in hardware.  The Linux kernel only offloads the TCP and UDP
-checksums (and always performs the pseudo header checksums), so
-the driver only supports checksumming for TCP/IP and UDP/IP
-packets.  Use ethtool to enable or disable this feature for RX
-and TX.
-
-VLAN
-
-In order to use VLAN, please consult Linux documentation on
-configuring VLANs.  The gianfar driver supports hardware insertion and
-extraction of VLAN headers, but not filtering.  Filtering will be
-done by the kernel.
-
-MULTICASTING
-
-The gianfar driver supports using the group hash table on the
-TSEC (and the extended hash table on the eTSEC) for multicast
-filtering.  On the eTSEC, the exact-match MAC registers are used
-before the hash tables.  See Linux documentation on how to join
-multicast groups.
-
-PADDING
-
-The gianfar driver supports padding received frames with 2 bytes
-to align the IP header to a 16-byte boundary, when supported by
-hardware.
-
-ETHTOOL
-
-The gianfar driver supports the use of ethtool for many
-configuration options.  You must run ethtool only on currently
-open interfaces.  See ethtool documentation for details.
diff --git a/Documentation/networking/i40e.rst b/Documentation/networking/i40e.rst
deleted file mode 100644
index 0cc16c525d10..000000000000
--- a/Documentation/networking/i40e.rst
+++ /dev/null
@@ -1,770 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux* Base Driver for the Intel(R) Ethernet Controller 700 Series
-==================================================================
-
-Intel 40 Gigabit Linux driver.
-Copyright(c) 1999-2018 Intel Corporation.
-
-Contents
-========
-
-- Overview
-- Identifying Your Adapter
-- Intel(R) Ethernet Flow Director
-- Additional Configurations
-- Known Issues
-- Support
-
-
-Driver information can be obtained using ethtool, lspci, and ifconfig.
-Instructions on updating ethtool can be found in the section Additional
-Configurations later in this document.
-
-For questions related to hardware requirements, refer to the documentation
-supplied with your Intel adapter. All hardware requirements listed apply to use
-with Linux.
-
-
-Identifying Your Adapter
-========================
-The driver is compatible with devices based on the following:
-
- * Intel(R) Ethernet Controller X710
- * Intel(R) Ethernet Controller XL710
- * Intel(R) Ethernet Network Connection X722
- * Intel(R) Ethernet Controller XXV710
-
-For the best performance, make sure the latest NVM/FW is installed on your
-device.
-
-For information on how to identify your adapter, and for the latest NVM/FW
-images and Intel network drivers, refer to the Intel Support website:
-https://www.intel.com/support
-
-SFP+ and QSFP+ Devices
-----------------------
-For information about supported media, refer to this document:
-https://www.intel.com/content/dam/www/public/us/en/documents/release-notes/xl710-ethernet-controller-feature-matrix.pdf
-
-NOTE: Some adapters based on the Intel(R) Ethernet Controller 700 Series only
-support Intel Ethernet Optics modules. On these adapters, other modules are not
-supported and will not function.  In all cases Intel recommends using Intel
-Ethernet Optics; other modules may function but are not validated by Intel.
-Contact Intel for supported media types.
-
-NOTE: For connections based on Intel(R) Ethernet Controller 700 Series, support
-is dependent on your system board. Please see your vendor for details.
-
-NOTE: In systems that do not have adequate airflow to cool the adapter and
-optical modules, you must use high temperature optical modules.
-
-Virtual Functions (VFs)
------------------------
-Use sysfs to enable VFs. For example::
-
-  #echo $num_vf_enabled > /sys/class/net/$dev/device/sriov_numvfs #enable VFs
-  #echo 0 > /sys/class/net/$dev/device/sriov_numvfs #disable VFs
-
-For example, the following instructions will configure PF eth0 and the first VF
-on VLAN 10::
-
-  $ ip link set dev eth0 vf 0 vlan 10
-
-VLAN Tag Packet Steering
-------------------------
-Allows you to send all packets with a specific VLAN tag to a particular SR-IOV
-virtual function (VF). Further, this feature allows you to designate a
-particular VF as trusted, and allows that trusted VF to request selective
-promiscuous mode on the Physical Function (PF).
-
-To set a VF as trusted or untrusted, enter the following command in the
-Hypervisor::
-
-  # ip link set dev eth0 vf 1 trust [on|off]
-
-Once the VF is designated as trusted, use the following commands in the VM to
-set the VF to promiscuous mode.
-
-::
-
-  For promiscuous all:
-  #ip link set eth2 promisc on
-  Where eth2 is a VF interface in the VM
-
-  For promiscuous Multicast:
-  #ip link set eth2 allmulticast on
-  Where eth2 is a VF interface in the VM
-
-NOTE: By default, the ethtool priv-flag vf-true-promisc-support is set to
-"off",meaning that promiscuous mode for the VF will be limited. To set the
-promiscuous mode for the VF to true promiscuous and allow the VF to see all
-ingress traffic, use the following command::
-
-  #ethtool -set-priv-flags p261p1 vf-true-promisc-support on
-
-The vf-true-promisc-support priv-flag does not enable promiscuous mode; rather,
-it designates which type of promiscuous mode (limited or true) you will get
-when you enable promiscuous mode using the ip link commands above. Note that
-this is a global setting that affects the entire device. However,the
-vf-true-promisc-support priv-flag is only exposed to the first PF of the
-device. The PF remains in limited promiscuous mode (unless it is in MFP mode)
-regardless of the vf-true-promisc-support setting.
-
-Now add a VLAN interface on the VF interface::
-
-  #ip link add link eth2 name eth2.100 type vlan id 100
-
-Note that the order in which you set the VF to promiscuous mode and add the
-VLAN interface does not matter (you can do either first). The end result in
-this example is that the VF will get all traffic that is tagged with VLAN 100.
-
-Intel(R) Ethernet Flow Director
--------------------------------
-The Intel Ethernet Flow Director performs the following tasks:
-
-- Directs receive packets according to their flows to different queues.
-- Enables tight control on routing a flow in the platform.
-- Matches flows and CPU cores for flow affinity.
-- Supports multiple parameters for flexible flow classification and load
-  balancing (in SFP mode only).
-
-NOTE: The Linux i40e driver supports the following flow types: IPv4, TCPv4, and
-UDPv4. For a given flow type, it supports valid combinations of IP addresses
-(source or destination) and UDP/TCP ports (source and destination). For
-example, you can supply only a source IP address, a source IP address and a
-destination port, or any combination of one or more of these four parameters.
-
-NOTE: The Linux i40e driver allows you to filter traffic based on a
-user-defined flexible two-byte pattern and offset by using the ethtool user-def
-and mask fields. Only L3 and L4 flow types are supported for user-defined
-flexible filters. For a given flow type, you must clear all Intel Ethernet Flow
-Director filters before changing the input set (for that flow type).
-
-To enable or disable the Intel Ethernet Flow Director::
-
-  # ethtool -K ethX ntuple <on|off>
-
-When disabling ntuple filters, all the user programmed filters are flushed from
-the driver cache and hardware. All needed filters must be re-added when ntuple
-is re-enabled.
-
-To add a filter that directs packet to queue 2, use -U or -N switch::
-
-  # ethtool -N ethX flow-type tcp4 src-ip 192.168.10.1 dst-ip \
-  192.168.10.2 src-port 2000 dst-port 2001 action 2 [loc 1]
-
-To set a filter using only the source and destination IP address::
-
-  # ethtool -N ethX flow-type tcp4 src-ip 192.168.10.1 dst-ip \
-  192.168.10.2 action 2 [loc 1]
-
-To see the list of filters currently present::
-
-  # ethtool <-u|-n> ethX
-
-Application Targeted Routing (ATR) Perfect Filters
---------------------------------------------------
-ATR is enabled by default when the kernel is in multiple transmit queue mode.
-An ATR Intel Ethernet Flow Director filter rule is added when a TCP-IP flow
-starts and is deleted when the flow ends. When a TCP-IP Intel Ethernet Flow
-Director rule is added from ethtool (Sideband filter), ATR is turned off by the
-driver. To re-enable ATR, the sideband can be disabled with the ethtool -K
-option. For example::
-
-  ethtool –K [adapter] ntuple [off|on]
-
-If sideband is re-enabled after ATR is re-enabled, ATR remains enabled until a
-TCP-IP flow is added. When all TCP-IP sideband rules are deleted, ATR is
-automatically re-enabled.
-
-Packets that match the ATR rules are counted in fdir_atr_match stats in
-ethtool, which also can be used to verify whether ATR rules still exist.
-
-Sideband Perfect Filters
-------------------------
-Sideband Perfect Filters are used to direct traffic that matches specified
-characteristics. They are enabled through ethtool's ntuple interface. To add a
-new filter use the following command::
-
-  ethtool -U <device> flow-type <type> src-ip <ip> dst-ip <ip> src-port <port> \
-  dst-port <port> action <queue>
-
-Where:
-  <device> - the ethernet device to program
-  <type> - can be ip4, tcp4, udp4, or sctp4
-  <ip> - the ip address to match on
-  <port> - the port number to match on
-  <queue> - the queue to direct traffic towards (-1 discards matching traffic)
-
-Use the following command to display all of the active filters::
-
-  ethtool -u <device>
-
-Use the following command to delete a filter::
-
-  ethtool -U <device> delete <N>
-
-Where <N> is the filter id displayed when printing all the active filters, and
-may also have been specified using "loc <N>" when adding the filter.
-
-The following example matches TCP traffic sent from 192.168.0.1, port 5300,
-directed to 192.168.0.5, port 80, and sends it to queue 7::
-
-  ethtool -U enp130s0 flow-type tcp4 src-ip 192.168.0.1 dst-ip 192.168.0.5 \
-  src-port 5300 dst-port 80 action 7
-
-For each flow-type, the programmed filters must all have the same matching
-input set. For example, issuing the following two commands is acceptable::
-
-  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.1 src-port 5300 action 7
-  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.5 src-port 55 action 10
-
-Issuing the next two commands, however, is not acceptable, since the first
-specifies src-ip and the second specifies dst-ip::
-
-  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.1 src-port 5300 action 7
-  ethtool -U enp130s0 flow-type ip4 dst-ip 192.168.0.5 src-port 55 action 10
-
-The second command will fail with an error. You may program multiple filters
-with the same fields, using different values, but, on one device, you may not
-program two tcp4 filters with different matching fields.
-
-Matching on a sub-portion of a field is not supported by the i40e driver, thus
-partial mask fields are not supported.
-
-The driver also supports matching user-defined data within the packet payload.
-This flexible data is specified using the "user-def" field of the ethtool
-command in the following way:
-
-+----------------------------+--------------------------+
-| 31    28    24    20    16 | 15    12    8    4    0  |
-+----------------------------+--------------------------+
-| offset into packet payload | 2 bytes of flexible data |
-+----------------------------+--------------------------+
-
-For example,
-
-::
-
-  ... user-def 0x4FFFF ...
-
-tells the filter to look 4 bytes into the payload and match that value against
-0xFFFF. The offset is based on the beginning of the payload, and not the
-beginning of the packet. Thus
-
-::
-
-  flow-type tcp4 ... user-def 0x8BEAF ...
-
-would match TCP/IPv4 packets which have the value 0xBEAF 8 bytes into the
-TCP/IPv4 payload.
-
-Note that ICMP headers are parsed as 4 bytes of header and 4 bytes of payload.
-Thus to match the first byte of the payload, you must actually add 4 bytes to
-the offset. Also note that ip4 filters match both ICMP frames as well as raw
-(unknown) ip4 frames, where the payload will be the L3 payload of the IP4 frame.
-
-The maximum offset is 64. The hardware will only read up to 64 bytes of data
-from the payload. The offset must be even because the flexible data is 2 bytes
-long and must be aligned to byte 0 of the packet payload.
-
-The user-defined flexible offset is also considered part of the input set and
-cannot be programmed separately for multiple filters of the same type. However,
-the flexible data is not part of the input set and multiple filters may use the
-same offset but match against different data.
-
-To create filters that direct traffic to a specific Virtual Function, use the
-"action" parameter. Specify the action as a 64 bit value, where the lower 32
-bits represents the queue number, while the next 8 bits represent which VF.
-Note that 0 is the PF, so the VF identifier is offset by 1. For example::
-
-  ... action 0x800000002 ...
-
-specifies to direct traffic to Virtual Function 7 (8 minus 1) into queue 2 of
-that VF.
-
-Note that these filters will not break internal routing rules, and will not
-route traffic that otherwise would not have been sent to the specified Virtual
-Function.
-
-Setting the link-down-on-close Private Flag
--------------------------------------------
-When the link-down-on-close private flag is set to "on", the port's link will
-go down when the interface is brought down using the ifconfig ethX down command.
-
-Use ethtool to view and set link-down-on-close, as follows::
-
-  ethtool --show-priv-flags ethX
-  ethtool --set-priv-flags ethX link-down-on-close [on|off]
-
-Viewing Link Messages
----------------------
-Link messages will not be displayed to the console if the distribution is
-restricting system messages. In order to see network driver link messages on
-your console, set dmesg to eight by entering the following::
-
-  dmesg -n 8
-
-NOTE: This setting is not saved across reboots.
-
-Jumbo Frames
-------------
-Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU)
-to a value larger than the default value of 1500.
-
-Use the ifconfig command to increase the MTU size. For example, enter the
-following where <x> is the interface number::
-
-  ifconfig eth<x> mtu 9000 up
-
-Alternatively, you can use the ip command as follows::
-
-  ip link set mtu 9000 dev eth<x>
-  ip link set up dev eth<x>
-
-This setting is not saved across reboots. The setting change can be made
-permanent by adding 'MTU=9000' to the file::
-
-  /etc/sysconfig/network-scripts/ifcfg-eth<x> // for RHEL
-  /etc/sysconfig/network/<config_file> // for SLES
-
-NOTE: The maximum MTU setting for Jumbo Frames is 9702. This value coincides
-with the maximum Jumbo Frames size of 9728 bytes.
-
-NOTE: This driver will attempt to use multiple page sized buffers to receive
-each jumbo packet. This should help to avoid buffer starvation issues when
-allocating receive packets.
-
-ethtool
--------
-The driver utilizes the ethtool interface for driver configuration and
-diagnostics, as well as displaying statistical information. The latest ethtool
-version is required for this functionality. Download it at:
-https://www.kernel.org/pub/software/network/ethtool/
-
-Supported ethtool Commands and Options for Filtering
-----------------------------------------------------
--n --show-nfc
-  Retrieves the receive network flow classification configurations.
-
-rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6
-  Retrieves the hash options for the specified network traffic type.
-
--N --config-nfc
-  Configures the receive network flow classification.
-
-rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6 m|v|t|s|d|f|n|r...
-  Configures the hash options for the specified network traffic type.
-
-udp4 UDP over IPv4
-udp6 UDP over IPv6
-
-f Hash on bytes 0 and 1 of the Layer 4 header of the Rx packet.
-n Hash on bytes 2 and 3 of the Layer 4 header of the Rx packet.
-
-Speed and Duplex Configuration
-------------------------------
-In addressing speed and duplex configuration issues, you need to distinguish
-between copper-based adapters and fiber-based adapters.
-
-In the default mode, an Intel(R) Ethernet Network Adapter using copper
-connections will attempt to auto-negotiate with its link partner to determine
-the best setting. If the adapter cannot establish link with the link partner
-using auto-negotiation, you may need to manually configure the adapter and link
-partner to identical settings to establish link and pass packets. This should
-only be needed when attempting to link with an older switch that does not
-support auto-negotiation or one that has been forced to a specific speed or
-duplex mode. Your link partner must match the setting you choose. 1 Gbps speeds
-and higher cannot be forced. Use the autonegotiation advertising setting to
-manually set devices for 1 Gbps and higher.
-
-NOTE: You cannot set the speed for devices based on the Intel(R) Ethernet
-Network Adapter XXV710 based devices.
-
-Speed, duplex, and autonegotiation advertising are configured through the
-ethtool* utility.
-
-Caution: Only experienced network administrators should force speed and duplex
-or change autonegotiation advertising manually. The settings at the switch must
-always match the adapter settings. Adapter performance may suffer or your
-adapter may not operate if you configure the adapter differently from your
-switch.
-
-An Intel(R) Ethernet Network Adapter using fiber-based connections, however,
-will not attempt to auto-negotiate with its link partner since those adapters
-operate only in full duplex and only at their native speed.
-
-NAPI
-----
-NAPI (Rx polling mode) is supported in the i40e driver.
-For more information on NAPI, see
-https://wiki.linuxfoundation.org/networking/napi
-
-Flow Control
-------------
-Ethernet Flow Control (IEEE 802.3x) can be configured with ethtool to enable
-receiving and transmitting pause frames for i40e. When transmit is enabled,
-pause frames are generated when the receive packet buffer crosses a predefined
-threshold. When receive is enabled, the transmit unit will halt for the time
-delay specified when a pause frame is received.
-
-NOTE: You must have a flow control capable link partner.
-
-Flow Control is on by default.
-
-Use ethtool to change the flow control settings.
-
-To enable or disable Rx or Tx Flow Control::
-
-  ethtool -A eth? rx <on|off> tx <on|off>
-
-Note: This command only enables or disables Flow Control if auto-negotiation is
-disabled. If auto-negotiation is enabled, this command changes the parameters
-used for auto-negotiation with the link partner.
-
-To enable or disable auto-negotiation::
-
-  ethtool -s eth? autoneg <on|off>
-
-Note: Flow Control auto-negotiation is part of link auto-negotiation. Depending
-on your device, you may not be able to change the auto-negotiation setting.
-
-RSS Hash Flow
--------------
-Allows you to set the hash bytes per flow type and any combination of one or
-more options for Receive Side Scaling (RSS) hash byte configuration.
-
-::
-
-  # ethtool -N <dev> rx-flow-hash <type> <option>
-
-Where <type> is:
-  tcp4	signifying TCP over IPv4
-  udp4	signifying UDP over IPv4
-  tcp6	signifying TCP over IPv6
-  udp6	signifying UDP over IPv6
-And <option> is one or more of:
-  s	Hash on the IP source address of the Rx packet.
-  d	Hash on the IP destination address of the Rx packet.
-  f	Hash on bytes 0 and 1 of the Layer 4 header of the Rx packet.
-  n	Hash on bytes 2 and 3 of the Layer 4 header of the Rx packet.
-
-MAC and VLAN anti-spoofing feature
-----------------------------------
-When a malicious driver attempts to send a spoofed packet, it is dropped by the
-hardware and not transmitted.
-NOTE: This feature can be disabled for a specific Virtual Function (VF)::
-
-  ip link set <pf dev> vf <vf id> spoofchk {off|on}
-
-IEEE 1588 Precision Time Protocol (PTP) Hardware Clock (PHC)
-------------------------------------------------------------
-Precision Time Protocol (PTP) is used to synchronize clocks in a computer
-network. PTP support varies among Intel devices that support this driver. Use
-"ethtool -T <netdev name>" to get a definitive list of PTP capabilities
-supported by the device.
-
-IEEE 802.1ad (QinQ) Support
----------------------------
-The IEEE 802.1ad standard, informally known as QinQ, allows for multiple VLAN
-IDs within a single Ethernet frame. VLAN IDs are sometimes referred to as
-"tags," and multiple VLAN IDs are thus referred to as a "tag stack." Tag stacks
-allow L2 tunneling and the ability to segregate traffic within a particular
-VLAN ID, among other uses.
-
-The following are examples of how to configure 802.1ad (QinQ)::
-
-  ip link add link eth0 eth0.24 type vlan proto 802.1ad id 24
-  ip link add link eth0.24 eth0.24.371 type vlan proto 802.1Q id 371
-
-Where "24" and "371" are example VLAN IDs.
-
-NOTES:
-  Receive checksum offloads, cloud filters, and VLAN acceleration are not
-  supported for 802.1ad (QinQ) packets.
-
-VXLAN and GENEVE Overlay HW Offloading
---------------------------------------
-Virtual Extensible LAN (VXLAN) allows you to extend an L2 network over an L3
-network, which may be useful in a virtualized or cloud environment. Some
-Intel(R) Ethernet Network devices perform VXLAN processing, offloading it from
-the operating system. This reduces CPU utilization.
-
-VXLAN offloading is controlled by the Tx and Rx checksum offload options
-provided by ethtool. That is, if Tx checksum offload is enabled, and the
-adapter has the capability, VXLAN offloading is also enabled.
-
-Support for VXLAN and GENEVE HW offloading is dependent on kernel support of
-the HW offloading features.
-
-Multiple Functions per Port
----------------------------
-Some adapters based on the Intel Ethernet Controller X710/XL710 support
-multiple functions on a single physical port. Configure these functions through
-the System Setup/BIOS.
-
-Minimum TX Bandwidth is the guaranteed minimum data transmission bandwidth, as
-a percentage of the full physical port link speed, that the partition will
-receive. The bandwidth the partition is awarded will never fall below the level
-you specify.
-
-The range for the minimum bandwidth values is:
-1 to ((100 minus # of partitions on the physical port) plus 1)
-For example, if a physical port has 4 partitions, the range would be:
-1 to ((100 - 4) + 1 = 97)
-
-The Maximum Bandwidth percentage represents the maximum transmit bandwidth
-allocated to the partition as a percentage of the full physical port link
-speed. The accepted range of values is 1-100. The value is used as a limiter,
-should you chose that any one particular function not be able to consume 100%
-of a port's bandwidth (should it be available). The sum of all the values for
-Maximum Bandwidth is not restricted, because no more than 100% of a port's
-bandwidth can ever be used.
-
-NOTE: X710/XXV710 devices fail to enable Max VFs (64) when Multiple Functions
-per Port (MFP) and SR-IOV are enabled. An error from i40e is logged that says
-"add vsi failed for VF N, aq_err 16". To workaround the issue, enable less than
-64 virtual functions (VFs).
-
-Data Center Bridging (DCB)
---------------------------
-DCB is a configuration Quality of Service implementation in hardware. It uses
-the VLAN priority tag (802.1p) to filter traffic. That means that there are 8
-different priorities that traffic can be filtered into. It also enables
-priority flow control (802.1Qbb) which can limit or eliminate the number of
-dropped packets during network stress. Bandwidth can be allocated to each of
-these priorities, which is enforced at the hardware level (802.1Qaz).
-
-Adapter firmware implements LLDP and DCBX protocol agents as per 802.1AB and
-802.1Qaz respectively. The firmware based DCBX agent runs in willing mode only
-and can accept settings from a DCBX capable peer. Software configuration of
-DCBX parameters via dcbtool/lldptool are not supported.
-
-NOTE: Firmware LLDP can be disabled by setting the private flag disable-fw-lldp.
-
-The i40e driver implements the DCB netlink interface layer to allow user-space
-to communicate with the driver and query DCB configuration for the port.
-
-NOTE:
-The kernel assumes that TC0 is available, and will disable Priority Flow
-Control (PFC) on the device if TC0 is not available. To fix this, ensure TC0 is
-enabled when setting up DCB on your switch.
-
-Interrupt Rate Limiting
------------------------
-:Valid Range: 0-235 (0=no limit)
-
-The Intel(R) Ethernet Controller XL710 family supports an interrupt rate
-limiting mechanism. The user can control, via ethtool, the number of
-microseconds between interrupts.
-
-Syntax::
-
-  # ethtool -C ethX rx-usecs-high N
-
-The range of 0-235 microseconds provides an effective range of 4,310 to 250,000
-interrupts per second. The value of rx-usecs-high can be set independently of
-rx-usecs and tx-usecs in the same ethtool command, and is also independent of
-the adaptive interrupt moderation algorithm. The underlying hardware supports
-granularity in 4-microsecond intervals, so adjacent values may result in the
-same interrupt rate.
-
-One possible use case is the following::
-
-  # ethtool -C ethX adaptive-rx off adaptive-tx off rx-usecs-high 20 rx-usecs \
-    5 tx-usecs 5
-
-The above command would disable adaptive interrupt moderation, and allow a
-maximum of 5 microseconds before indicating a receive or transmit was complete.
-However, instead of resulting in as many as 200,000 interrupts per second, it
-limits total interrupts per second to 50,000 via the rx-usecs-high parameter.
-
-Performance Optimization
-========================
-Driver defaults are meant to fit a wide variety of workloads, but if further
-optimization is required we recommend experimenting with the following settings.
-
-NOTE: For better performance when processing small (64B) frame sizes, try
-enabling Hyper threading in the BIOS in order to increase the number of logical
-cores in the system and subsequently increase the number of queues available to
-the adapter.
-
-Virtualized Environments
-------------------------
-1. Disable XPS on both ends by using the included virt_perf_default script
-or by running the following command as root::
-
-  for file in `ls /sys/class/net/<ethX>/queues/tx-*/xps_cpus`;
-  do echo 0 > $file; done
-
-2. Using the appropriate mechanism (vcpupin) in the vm, pin the cpu's to
-individual lcpu's, making sure to use a set of cpu's included in the
-device's local_cpulist: /sys/class/net/<ethX>/device/local_cpulist.
-
-3. Configure as many Rx/Tx queues in the VM as available. Do not rely on
-the default setting of 1.
-
-
-Non-virtualized Environments
-----------------------------
-Pin the adapter's IRQs to specific cores by disabling the irqbalance service
-and using the included set_irq_affinity script. Please see the script's help
-text for further options.
-
-- The following settings will distribute the IRQs across all the cores evenly::
-
-  # scripts/set_irq_affinity -x all <interface1> , [ <interface2>, ... ]
-
-- The following settings will distribute the IRQs across all the cores that are
-  local to the adapter (same NUMA node)::
-
-  # scripts/set_irq_affinity -x local <interface1> ,[ <interface2>, ... ]
-
-For very CPU intensive workloads, we recommend pinning the IRQs to all cores.
-
-For IP Forwarding: Disable Adaptive ITR and lower Rx and Tx interrupts per
-queue using ethtool.
-
-- Setting rx-usecs and tx-usecs to 125 will limit interrupts to about 8000
-  interrupts per second per queue.
-
-::
-
-  # ethtool -C <interface> adaptive-rx off adaptive-tx off rx-usecs 125 \
-    tx-usecs 125
-
-For lower CPU utilization: Disable Adaptive ITR and lower Rx and Tx interrupts
-per queue using ethtool.
-
-- Setting rx-usecs and tx-usecs to 250 will limit interrupts to about 4000
-  interrupts per second per queue.
-
-::
-
-  # ethtool -C <interface> adaptive-rx off adaptive-tx off rx-usecs 250 \
-    tx-usecs 250
-
-For lower latency: Disable Adaptive ITR and ITR by setting Rx and Tx to 0 using
-ethtool.
-
-::
-
-  # ethtool -C <interface> adaptive-rx off adaptive-tx off rx-usecs 0 \
-    tx-usecs 0
-
-Application Device Queues (ADq)
--------------------------------
-Application Device Queues (ADq) allows you to dedicate one or more queues to a
-specific application. This can reduce latency for the specified application,
-and allow Tx traffic to be rate limited per application. Follow the steps below
-to set ADq.
-
-1. Create traffic classes (TCs). Maximum of 8 TCs can be created per interface.
-The shaper bw_rlimit parameter is optional.
-
-Example: Sets up two tcs, tc0 and tc1, with 16 queues each and max tx rate set
-to 1Gbit for tc0 and 3Gbit for tc1.
-
-::
-
-  # tc qdisc add dev <interface> root mqprio num_tc 2 map 0 0 0 0 1 1 1 1
-  queues 16@0 16@16 hw 1 mode channel shaper bw_rlimit min_rate 1Gbit 2Gbit
-  max_rate 1Gbit 3Gbit
-
-map: priority mapping for up to 16 priorities to tcs (e.g. map 0 0 0 0 1 1 1 1
-sets priorities 0-3 to use tc0 and 4-7 to use tc1)
-
-queues: for each tc, <num queues>@<offset> (e.g. queues 16@0 16@16 assigns
-16 queues to tc0 at offset 0 and 16 queues to tc1 at offset 16. Max total
-number of queues for all tcs is 64 or number of cores, whichever is lower.)
-
-hw 1 mode channel: ‘channel’ with ‘hw’ set to 1 is a new new hardware
-offload mode in mqprio that makes full use of the mqprio options, the
-TCs, the queue configurations, and the QoS parameters.
-
-shaper bw_rlimit: for each tc, sets minimum and maximum bandwidth rates.
-Totals must be equal or less than port speed.
-
-For example: min_rate 1Gbit 3Gbit: Verify bandwidth limit using network
-monitoring tools such as ifstat or sar –n DEV [interval] [number of samples]
-
-2. Enable HW TC offload on interface::
-
-    # ethtool -K <interface> hw-tc-offload on
-
-3. Apply TCs to ingress (RX) flow of interface::
-
-    # tc qdisc add dev <interface> ingress
-
-NOTES:
- - Run all tc commands from the iproute2 <pathtoiproute2>/tc/ directory.
- - ADq is not compatible with cloud filters.
- - Setting up channels via ethtool (ethtool -L) is not supported when the
-   TCs are configured using mqprio.
- - You must have iproute2 latest version
- - NVM version 6.01 or later is required.
- - ADq cannot be enabled when any the following features are enabled: Data
-   Center Bridging (DCB), Multiple Functions per Port (MFP), or Sideband
-   Filters.
- - If another driver (for example, DPDK) has set cloud filters, you cannot
-   enable ADq.
- - Tunnel filters are not supported in ADq. If encapsulated packets do
-   arrive in non-tunnel mode, filtering will be done on the inner headers.
-   For example, for VXLAN traffic in non-tunnel mode, PCTYPE is identified
-   as a VXLAN encapsulated packet, outer headers are ignored. Therefore,
-   inner headers are matched.
- - If a TC filter on a PF matches traffic over a VF (on the PF), that
-   traffic will be routed to the appropriate queue of the PF, and will
-   not be passed on the VF. Such traffic will end up getting dropped higher
-   up in the TCP/IP stack as it does not match PF address data.
- - If traffic matches multiple TC filters that point to different TCs,
-   that traffic will be duplicated and sent to all matching TC queues.
-   The hardware switch mirrors the packet to a VSI list when multiple
-   filters are matched.
-
-
-Known Issues/Troubleshooting
-============================
-
-NOTE: 1 Gb devices based on the Intel(R) Ethernet Network Connection X722 do
-not support the following features:
-
-  * Data Center Bridging (DCB)
-  * QOS
-  * VMQ
-  * SR-IOV
-  * Task Encapsulation offload (VXLAN, NVGRE)
-  * Energy Efficient Ethernet (EEE)
-  * Auto-media detect
-
-Unexpected Issues when the device driver and DPDK share a device
-----------------------------------------------------------------
-Unexpected issues may result when an i40e device is in multi driver mode and
-the kernel driver and DPDK driver are sharing the device. This is because
-access to the global NIC resources is not synchronized between multiple
-drivers. Any change to the global NIC configuration (writing to a global
-register, setting global configuration by AQ, or changing switch modes) will
-affect all ports and drivers on the device. Loading DPDK with the
-"multi-driver" module parameter may mitigate some of the issues.
-
-TC0 must be enabled when setting up DCB on a switch
----------------------------------------------------
-The kernel assumes that TC0 is available, and will disable Priority Flow
-Control (PFC) on the device if TC0 is not available. To fix this, ensure TC0 is
-enabled when setting up DCB on your switch.
-
-
-Support
-=======
-For general information, go to the Intel support website at:
-
-https://www.intel.com/support/
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-
-https://sourceforge.net/projects/e1000
-
-If an issue is identified with the released source code on a supported kernel
-with a supported adapter, email the specific information related to the issue
-to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/iavf.rst b/Documentation/networking/iavf.rst
deleted file mode 100644
index f8b42b64eb28..000000000000
--- a/Documentation/networking/iavf.rst
+++ /dev/null
@@ -1,281 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux* Base Driver for Intel(R) Ethernet Adaptive Virtual Function
-==================================================================
-
-Intel Ethernet Adaptive Virtual Function Linux driver.
-Copyright(c) 2013-2018 Intel Corporation.
-
-Contents
-========
-
-- Identifying Your Adapter
-- Additional Configurations
-- Known Issues/Troubleshooting
-- Support
-
-This file describes the iavf Linux* Base Driver. This driver was formerly
-called i40evf.
-
-The iavf driver supports the below mentioned virtual function devices and
-can only be activated on kernels running the i40e or newer Physical Function
-(PF) driver compiled with CONFIG_PCI_IOV.  The iavf driver requires
-CONFIG_PCI_MSI to be enabled.
-
-The guest OS loading the iavf driver must support MSI-X interrupts.
-
-Identifying Your Adapter
-========================
-The driver in this kernel is compatible with devices based on the following:
- * Intel(R) XL710 X710 Virtual Function
- * Intel(R) X722 Virtual Function
- * Intel(R) XXV710 Virtual Function
- * Intel(R) Ethernet Adaptive Virtual Function
-
-For the best performance, make sure the latest NVM/FW is installed on your
-device.
-
-For information on how to identify your adapter, and for the latest NVM/FW
-images and Intel network drivers, refer to the Intel Support website:
-http://www.intel.com/support
-
-
-Additional Features and Configurations
-======================================
-
-Viewing Link Messages
----------------------
-Link messages will not be displayed to the console if the distribution is
-restricting system messages. In order to see network driver link messages on
-your console, set dmesg to eight by entering the following::
-
-  dmesg -n 8
-
-NOTE: This setting is not saved across reboots.
-
-ethtool
--------
-The driver utilizes the ethtool interface for driver configuration and
-diagnostics, as well as displaying statistical information. The latest ethtool
-version is required for this functionality. Download it at:
-https://www.kernel.org/pub/software/network/ethtool/
-
-Setting VLAN Tag Stripping
---------------------------
-If you have applications that require Virtual Functions (VFs) to receive
-packets with VLAN tags, you can disable VLAN tag stripping for the VF. The
-Physical Function (PF) processes requests issued from the VF to enable or
-disable VLAN tag stripping. Note that if the PF has assigned a VLAN to a VF,
-then requests from that VF to set VLAN tag stripping will be ignored.
-
-To enable/disable VLAN tag stripping for a VF, issue the following command
-from inside the VM in which you are running the VF::
-
-  ethtool -K <if_name> rxvlan on/off
-
-or alternatively::
-
-  ethtool --offload <if_name> rxvlan on/off
-
-Adaptive Virtual Function
--------------------------
-Adaptive Virtual Function (AVF) allows the virtual function driver, or VF, to
-adapt to changing feature sets of the physical function driver (PF) with which
-it is associated. This allows system administrators to update a PF without
-having to update all the VFs associated with it. All AVFs have a single common
-device ID and branding string.
-
-AVFs have a minimum set of features known as "base mode," but may provide
-additional features depending on what features are available in the PF with
-which the AVF is associated. The following are base mode features:
-
-- 4 Queue Pairs (QP) and associated Configuration Status Registers (CSRs)
-  for Tx/Rx.
-- i40e descriptors and ring format.
-- Descriptor write-back completion.
-- 1 control queue, with i40e descriptors, CSRs and ring format.
-- 5 MSI-X interrupt vectors and corresponding i40e CSRs.
-- 1 Interrupt Throttle Rate (ITR) index.
-- 1 Virtual Station Interface (VSI) per VF.
-- 1 Traffic Class (TC), TC0
-- Receive Side Scaling (RSS) with 64 entry indirection table and key,
-  configured through the PF.
-- 1 unicast MAC address reserved per VF.
-- 16 MAC address filters for each VF.
-- Stateless offloads - non-tunneled checksums.
-- AVF device ID.
-- HW mailbox is used for VF to PF communications (including on Windows).
-
-IEEE 802.1ad (QinQ) Support
----------------------------
-The IEEE 802.1ad standard, informally known as QinQ, allows for multiple VLAN
-IDs within a single Ethernet frame. VLAN IDs are sometimes referred to as
-"tags," and multiple VLAN IDs are thus referred to as a "tag stack." Tag stacks
-allow L2 tunneling and the ability to segregate traffic within a particular
-VLAN ID, among other uses.
-
-The following are examples of how to configure 802.1ad (QinQ)::
-
-  ip link add link eth0 eth0.24 type vlan proto 802.1ad id 24
-  ip link add link eth0.24 eth0.24.371 type vlan proto 802.1Q id 371
-
-Where "24" and "371" are example VLAN IDs.
-
-NOTES:
-  Receive checksum offloads, cloud filters, and VLAN acceleration are not
-  supported for 802.1ad (QinQ) packets.
-
-Application Device Queues (ADq)
--------------------------------
-Application Device Queues (ADq) allows you to dedicate one or more queues to a
-specific application. This can reduce latency for the specified application,
-and allow Tx traffic to be rate limited per application. Follow the steps below
-to set ADq.
-
-1. Create traffic classes (TCs). Maximum of 8 TCs can be created per interface.
-The shaper bw_rlimit parameter is optional.
-
-Example: Sets up two tcs, tc0 and tc1, with 16 queues each and max tx rate set
-to 1Gbit for tc0 and 3Gbit for tc1.
-
-::
-
-  # tc qdisc add dev <interface> root mqprio num_tc 2 map 0 0 0 0 1 1 1 1
-  queues 16@0 16@16 hw 1 mode channel shaper bw_rlimit min_rate 1Gbit 2Gbit
-  max_rate 1Gbit 3Gbit
-
-map: priority mapping for up to 16 priorities to tcs (e.g. map 0 0 0 0 1 1 1 1
-sets priorities 0-3 to use tc0 and 4-7 to use tc1)
-
-queues: for each tc, <num queues>@<offset> (e.g. queues 16@0 16@16 assigns
-16 queues to tc0 at offset 0 and 16 queues to tc1 at offset 16. Max total
-number of queues for all tcs is 64 or number of cores, whichever is lower.)
-
-hw 1 mode channel: ‘channel’ with ‘hw’ set to 1 is a new new hardware
-offload mode in mqprio that makes full use of the mqprio options, the
-TCs, the queue configurations, and the QoS parameters.
-
-shaper bw_rlimit: for each tc, sets minimum and maximum bandwidth rates.
-Totals must be equal or less than port speed.
-
-For example: min_rate 1Gbit 3Gbit: Verify bandwidth limit using network
-monitoring tools such as ifstat or sar –n DEV [interval] [number of samples]
-
-2. Enable HW TC offload on interface::
-
-    # ethtool -K <interface> hw-tc-offload on
-
-3. Apply TCs to ingress (RX) flow of interface::
-
-    # tc qdisc add dev <interface> ingress
-
-NOTES:
- - Run all tc commands from the iproute2 <pathtoiproute2>/tc/ directory.
- - ADq is not compatible with cloud filters.
- - Setting up channels via ethtool (ethtool -L) is not supported when the TCs
-   are configured using mqprio.
- - You must have iproute2 latest version
- - NVM version 6.01 or later is required.
- - ADq cannot be enabled when any the following features are enabled: Data
-   Center Bridging (DCB), Multiple Functions per Port (MFP), or Sideband Filters.
- - If another driver (for example, DPDK) has set cloud filters, you cannot
-   enable ADq.
- - Tunnel filters are not supported in ADq. If encapsulated packets do arrive
-   in non-tunnel mode, filtering will be done on the inner headers.  For example,
-   for VXLAN traffic in non-tunnel mode, PCTYPE is identified as a VXLAN
-   encapsulated packet, outer headers are ignored. Therefore, inner headers are
-   matched.
- - If a TC filter on a PF matches traffic over a VF (on the PF), that traffic
-   will be routed to the appropriate queue of the PF, and will not be passed on
-   the VF. Such traffic will end up getting dropped higher up in the TCP/IP
-   stack as it does not match PF address data.
- - If traffic matches multiple TC filters that point to different TCs, that
-   traffic will be duplicated and sent to all matching TC queues.  The hardware
-   switch mirrors the packet to a VSI list when multiple filters are matched.
-
-
-Known Issues/Troubleshooting
-============================
-
-Traffic Is Not Being Passed Between VM and Client
--------------------------------------------------
-You may not be able to pass traffic between a client system and a
-Virtual Machine (VM) running on a separate host if the Virtual Function
-(VF, or Virtual NIC) is not in trusted mode and spoof checking is enabled
-on the VF. Note that this situation can occur in any combination of client,
-host, and guest operating system. For information on how to set the VF to
-trusted mode, refer to the section "VLAN Tag Packet Steering" in this
-readme document. For information on setting spoof checking, refer to the
-section "MAC and VLAN anti-spoofing feature" in this readme document.
-
-Do not unload port driver if VF with active VM is bound to it
--------------------------------------------------------------
-Do not unload a port's driver if a Virtual Function (VF) with an active Virtual
-Machine (VM) is bound to it. Doing so will cause the port to appear to hang.
-Once the VM shuts down, or otherwise releases the VF, the command will complete.
-
-Virtual machine does not get link
----------------------------------
-If the virtual machine has more than one virtual port assigned to it, and those
-virtual ports are bound to different physical ports, you may not get link on
-all of the virtual ports. The following command may work around the issue::
-
-  ethtool -r <PF>
-
-Where <PF> is the PF interface in the host, for example: p5p1. You may need to
-run the command more than once to get link on all virtual ports.
-
-MAC address of Virtual Function changes unexpectedly
-----------------------------------------------------
-If a Virtual Function's MAC address is not assigned in the host, then the VF
-(virtual function) driver will use a random MAC address. This random MAC
-address may change each time the VF driver is reloaded. You can assign a static
-MAC address in the host machine. This static MAC address will survive
-a VF driver reload.
-
-Driver Buffer Overflow Fix
---------------------------
-The fix to resolve CVE-2016-8105, referenced in Intel SA-00069
-https://www.intel.com/content/www/us/en/security-center/advisory/intel-sa-00069.html
-is included in this and future versions of the driver.
-
-Multiple Interfaces on Same Ethernet Broadcast Network
-------------------------------------------------------
-Due to the default ARP behavior on Linux, it is not possible to have one system
-on two IP networks in the same Ethernet broadcast domain (non-partitioned
-switch) behave as expected. All Ethernet interfaces will respond to IP traffic
-for any IP address assigned to the system. This results in unbalanced receive
-traffic.
-
-If you have multiple interfaces in a server, either turn on ARP filtering by
-entering::
-
-  echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
-
-NOTE: This setting is not saved across reboots. The configuration change can be
-made permanent by adding the following line to the file /etc/sysctl.conf::
-
-  net.ipv4.conf.all.arp_filter = 1
-
-Another alternative is to install the interfaces in separate broadcast domains
-(either in different switches or in a switch partitioned to VLANs).
-
-Rx Page Allocation Errors
--------------------------
-'Page allocation failure. order:0' errors may occur under stress.
-This is caused by the way the Linux kernel reports this stressed condition.
-
-
-Support
-=======
-For general information, go to the Intel support website at:
-
-https://support.intel.com
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-
-https://sourceforge.net/projects/e1000
-
-If an issue is identified with the released source code on the supported kernel
-with a supported adapter, email the specific information related to the issue
-to e1000-devel@lists.sf.net
diff --git a/Documentation/networking/ice.rst b/Documentation/networking/ice.rst
deleted file mode 100644
index 4d118b827bbb..000000000000
--- a/Documentation/networking/ice.rst
+++ /dev/null
@@ -1,45 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux* Base Driver for the Intel(R) Ethernet Connection E800 Series
-===================================================================
-
-Intel ice Linux driver.
-Copyright(c) 2018 Intel Corporation.
-
-Contents
-========
-
-- Enabling the driver
-- Support
-
-The driver in this release supports Intel's E800 Series of products. For
-more information, visit Intel's support page at https://support.intel.com.
-
-Enabling the driver
-===================
-The driver is enabled via the standard kernel configuration system,
-using the make command::
-
-  make oldconfig/menuconfig/etc.
-
-The driver is located in the menu structure at:
-
-  -> Device Drivers
-    -> Network device support (NETDEVICES [=y])
-      -> Ethernet driver support
-        -> Intel devices
-          -> Intel(R) Ethernet Connection E800 Series Support
-
-Support
-=======
-For general information, go to the Intel support website at:
-
-https://www.intel.com/support/
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-
-https://sourceforge.net/projects/e1000
-
-If an issue is identified with the released source code on a supported kernel
-with a supported adapter, email the specific information related to the issue
-to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/igb.rst b/Documentation/networking/igb.rst
deleted file mode 100644
index ba16b86d5593..000000000000
--- a/Documentation/networking/igb.rst
+++ /dev/null
@@ -1,193 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux* Base Driver for Intel(R) Ethernet Network Connection
-===========================================================
-
-Intel Gigabit Linux driver.
-Copyright(c) 1999-2018 Intel Corporation.
-
-Contents
-========
-
-- Identifying Your Adapter
-- Command Line Parameters
-- Additional Configurations
-- Support
-
-
-Identifying Your Adapter
-========================
-For information on how to identify your adapter, and for the latest Intel
-network drivers, refer to the Intel Support website:
-http://www.intel.com/support
-
-
-Command Line Parameters
-========================
-If the driver is built as a module, the following optional parameters are used
-by entering them on the command line with the modprobe command using this
-syntax::
-
-    modprobe igb [<option>=<VAL1>,<VAL2>,...]
-
-There needs to be a <VAL#> for each network port in the system supported by
-this driver. The values will be applied to each instance, in function order.
-For example::
-
-    modprobe igb max_vfs=2,4
-
-In this case, there are two network ports supported by igb in the system.
-
-NOTE: A descriptor describes a data buffer and attributes related to the data
-buffer. This information is accessed by the hardware.
-
-max_vfs
--------
-:Valid Range: 0-7
-
-This parameter adds support for SR-IOV. It causes the driver to spawn up to
-max_vfs worth of virtual functions.  If the value is greater than 0 it will
-also force the VMDq parameter to be 1 or more.
-
-The parameters for the driver are referenced by position. Thus, if you have a
-dual port adapter, or more than one adapter in your system, and want N virtual
-functions per port, you must specify a number for each port with each parameter
-separated by a comma. For example::
-
-    modprobe igb max_vfs=4
-
-This will spawn 4 VFs on the first port.
-
-::
-
-    modprobe igb max_vfs=2,4
-
-This will spawn 2 VFs on the first port and 4 VFs on the second port.
-
-NOTE: Caution must be used in loading the driver with these parameters.
-Depending on your system configuration, number of slots, etc., it is impossible
-to predict in all cases where the positions would be on the command line.
-
-NOTE: Neither the device nor the driver control how VFs are mapped into config
-space. Bus layout will vary by operating system. On operating systems that
-support it, you can check sysfs to find the mapping.
-
-NOTE: When either SR-IOV mode or VMDq mode is enabled, hardware VLAN filtering
-and VLAN tag stripping/insertion will remain enabled. Please remove the old
-VLAN filter before the new VLAN filter is added. For example::
-
-    ip link set eth0 vf 0 vlan 100	// set vlan 100 for VF 0
-    ip link set eth0 vf 0 vlan 0	// Delete vlan 100
-    ip link set eth0 vf 0 vlan 200	// set a new vlan 200 for VF 0
-
-Debug
------
-:Valid Range: 0-16 (0=none,...,16=all)
-:Default Value: 0
-
-This parameter adjusts the level debug messages displayed in the system logs.
-
-
-Additional Features and Configurations
-======================================
-
-Jumbo Frames
-------------
-Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU)
-to a value larger than the default value of 1500.
-
-Use the ifconfig command to increase the MTU size. For example, enter the
-following where <x> is the interface number::
-
-    ifconfig eth<x> mtu 9000 up
-
-Alternatively, you can use the ip command as follows::
-
-    ip link set mtu 9000 dev eth<x>
-    ip link set up dev eth<x>
-
-This setting is not saved across reboots. The setting change can be made
-permanent by adding 'MTU=9000' to the file:
-
-- For RHEL: /etc/sysconfig/network-scripts/ifcfg-eth<x>
-- For SLES: /etc/sysconfig/network/<config_file>
-
-NOTE: The maximum MTU setting for Jumbo Frames is 9216. This value coincides
-with the maximum Jumbo Frames size of 9234 bytes.
-
-NOTE: Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
-poor performance or loss of link.
-
-
-ethtool
--------
-The driver utilizes the ethtool interface for driver configuration and
-diagnostics, as well as displaying statistical information. The latest ethtool
-version is required for this functionality. Download it at:
-
-https://www.kernel.org/pub/software/network/ethtool/
-
-
-Enabling Wake on LAN* (WoL)
----------------------------
-WoL is configured through the ethtool* utility.
-
-WoL will be enabled on the system during the next shut down or reboot. For
-this driver version, in order to enable WoL, the igb driver must be loaded
-prior to shutting down or suspending the system.
-
-NOTE: Wake on LAN is only supported on port A of multi-port devices.  Also
-Wake On LAN is not supported for the following device:
-- Intel(R) Gigabit VT Quad Port Server Adapter
-
-
-Multiqueue
-----------
-In this mode, a separate MSI-X vector is allocated for each queue and one for
-"other" interrupts such as link status change and errors. All interrupts are
-throttled via interrupt moderation. Interrupt moderation must be used to avoid
-interrupt storms while the driver is processing one interrupt. The moderation
-value should be at least as large as the expected time for the driver to
-process an interrupt. Multiqueue is off by default.
-
-REQUIREMENTS: MSI-X support is required for Multiqueue. If MSI-X is not found,
-the system will fallback to MSI or to Legacy interrupts. This driver supports
-receive multiqueue on all kernels that support MSI-X.
-
-NOTE: On some kernels a reboot is required to switch between single queue mode
-and multiqueue mode or vice-versa.
-
-
-MAC and VLAN anti-spoofing feature
-----------------------------------
-When a malicious driver attempts to send a spoofed packet, it is dropped by the
-hardware and not transmitted.
-
-An interrupt is sent to the PF driver notifying it of the spoof attempt. When a
-spoofed packet is detected, the PF driver will send the following message to
-the system log (displayed by the "dmesg" command):
-Spoof event(s) detected on VF(n), where n = the VF that attempted to do the
-spoofing
-
-
-Setting MAC Address, VLAN and Rate Limit Using IProute2 Tool
-------------------------------------------------------------
-You can set a MAC address of a Virtual Function (VF), a default VLAN and the
-rate limit using the IProute2 tool. Download the latest version of the
-IProute2 tool from Sourceforge if your version does not have all the features
-you require.
-
-
-Support
-=======
-For general information, go to the Intel support website at:
-
-https://www.intel.com/support/
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-
-https://sourceforge.net/projects/e1000
-
-If an issue is identified with the released source code on a supported kernel
-with a supported adapter, email the specific information related to the issue
-to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/igbvf.rst b/Documentation/networking/igbvf.rst
deleted file mode 100644
index a8a9ffa4f8d3..000000000000
--- a/Documentation/networking/igbvf.rst
+++ /dev/null
@@ -1,64 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux* Base Virtual Function Driver for Intel(R) 1G Ethernet
-============================================================
-
-Intel Gigabit Virtual Function Linux driver.
-Copyright(c) 1999-2018 Intel Corporation.
-
-Contents
-========
-- Identifying Your Adapter
-- Additional Configurations
-- Support
-
-This driver supports Intel 82576-based virtual function devices-based virtual
-function devices that can only be activated on kernels that support SR-IOV.
-
-SR-IOV requires the correct platform and OS support.
-
-The guest OS loading this driver must support MSI-X interrupts.
-
-For questions related to hardware requirements, refer to the documentation
-supplied with your Intel adapter. All hardware requirements listed apply to use
-with Linux.
-
-Driver information can be obtained using ethtool, lspci, and ifconfig.
-Instructions on updating ethtool can be found in the section Additional
-Configurations later in this document.
-
-NOTE: There is a limit of a total of 32 shared VLANs to 1 or more VFs.
-
-
-Identifying Your Adapter
-========================
-For information on how to identify your adapter, and for the latest Intel
-network drivers, refer to the Intel Support website:
-http://www.intel.com/support
-
-
-Additional Features and Configurations
-======================================
-
-ethtool
--------
-The driver utilizes the ethtool interface for driver configuration and
-diagnostics, as well as displaying statistical information. The latest ethtool
-version is required for this functionality. Download it at:
-
-https://www.kernel.org/pub/software/network/ethtool/
-
-
-Support
-=======
-For general information, go to the Intel support website at:
-
-https://www.intel.com/support/
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-
-https://sourceforge.net/projects/e1000
-
-If an issue is identified with the released source code on a supported kernel
-with a supported adapter, email the specific information related to the issue
-to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/ixgb.rst b/Documentation/networking/ixgb.rst
deleted file mode 100644
index 8bd80e27843d..000000000000
--- a/Documentation/networking/ixgb.rst
+++ /dev/null
@@ -1,467 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux Base Driver for 10 Gigabit Intel(R) Ethernet Network Connection
-=====================================================================
-
-October 1, 2018
-
-
-Contents
-========
-
-- In This Release
-- Identifying Your Adapter
-- Command Line Parameters
-- Improving Performance
-- Additional Configurations
-- Known Issues/Troubleshooting
-- Support
-
-
-
-In This Release
-===============
-
-This file describes the ixgb Linux Base Driver for the 10 Gigabit Intel(R)
-Network Connection.  This driver includes support for Itanium(R)2-based
-systems.
-
-For questions related to hardware requirements, refer to the documentation
-supplied with your 10 Gigabit adapter.  All hardware requirements listed apply
-to use with Linux.
-
-The following features are available in this kernel:
- - Native VLANs
- - Channel Bonding (teaming)
- - SNMP
-
-Channel Bonding documentation can be found in the Linux kernel source:
-/Documentation/networking/bonding.txt
-
-The driver information previously displayed in the /proc filesystem is not
-supported in this release.  Alternatively, you can use ethtool (version 1.6
-or later), lspci, and iproute2 to obtain the same information.
-
-Instructions on updating ethtool can be found in the section "Additional
-Configurations" later in this document.
-
-
-Identifying Your Adapter
-========================
-
-The following Intel network adapters are compatible with the drivers in this
-release:
-
-+------------+------------------------------+----------------------------------+
-| Controller | Adapter Name                 | Physical Layer                   |
-+============+==============================+==================================+
-| 82597EX    | Intel(R) PRO/10GbE LR/SR/CX4 | - 10G Base-LR (fiber)            |
-|            | Server Adapters              | - 10G Base-SR (fiber)            |
-|            |                              | - 10G Base-CX4 (copper)          |
-+------------+------------------------------+----------------------------------+
-
-For more information on how to identify your adapter, go to the Adapter &
-Driver ID Guide at:
-
-    https://support.intel.com
-
-
-Command Line Parameters
-=======================
-
-If the driver is built as a module, the  following optional parameters are
-used by entering them on the command line with the modprobe command using
-this syntax::
-
-    modprobe ixgb [<option>=<VAL1>,<VAL2>,...]
-
-For example, with two 10GbE PCI adapters, entering::
-
-    modprobe ixgb TxDescriptors=80,128
-
-loads the ixgb driver with 80 TX resources for the first adapter and 128 TX
-resources for the second adapter.
-
-The default value for each parameter is generally the recommended setting,
-unless otherwise noted.
-
-Copybreak
----------
-:Valid Range: 0-XXXX
-:Default Value: 256
-
-    This is the maximum size of packet that is copied to a new buffer on
-    receive.
-
-Debug
------
-:Valid Range: 0-16 (0=none,...,16=all)
-:Default Value: 0
-
-    This parameter adjusts the level of debug messages displayed in the
-    system logs.
-
-FlowControl
------------
-:Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
-:Default Value: 1 if no EEPROM, otherwise read from EEPROM
-
-    This parameter controls the automatic generation(Tx) and response(Rx) to
-    Ethernet PAUSE frames.  There are hardware bugs associated with enabling
-    Tx flow control so beware.
-
-RxDescriptors
--------------
-:Valid Range: 64-4096
-:Default Value: 1024
-
-    This value is the number of receive descriptors allocated by the driver.
-    Increasing this value allows the driver to buffer more incoming packets.
-    Each descriptor is 16 bytes.  A receive buffer is also allocated for
-    each descriptor and can be either 2048, 4056, 8192, or 16384 bytes,
-    depending on the MTU setting.  When the MTU size is 1500 or less, the
-    receive buffer size is 2048 bytes. When the MTU is greater than 1500 the
-    receive buffer size will be either 4056, 8192, or 16384 bytes.  The
-    maximum MTU size is 16114.
-
-TxDescriptors
--------------
-:Valid Range: 64-4096
-:Default Value: 256
-
-    This value is the number of transmit descriptors allocated by the driver.
-    Increasing this value allows the driver to queue more transmits.  Each
-    descriptor is 16 bytes.
-
-RxIntDelay
-----------
-:Valid Range: 0-65535 (0=off)
-:Default Value: 72
-
-    This value delays the generation of receive interrupts in units of
-    0.8192 microseconds.  Receive interrupt reduction can improve CPU
-    efficiency if properly tuned for specific network traffic.  Increasing
-    this value adds extra latency to frame reception and can end up
-    decreasing the throughput of TCP traffic.  If the system is reporting
-    dropped receives, this value may be set too high, causing the driver to
-    run out of available receive descriptors.
-
-TxIntDelay
-----------
-:Valid Range: 0-65535 (0=off)
-:Default Value: 32
-
-    This value delays the generation of transmit interrupts in units of
-    0.8192 microseconds.  Transmit interrupt reduction can improve CPU
-    efficiency if properly tuned for specific network traffic.  Increasing
-    this value adds extra latency to frame transmission and can end up
-    decreasing the throughput of TCP traffic.  If this value is set too high,
-    it will cause the driver to run out of available transmit descriptors.
-
-XsumRX
-------
-:Valid Range: 0-1
-:Default Value: 1
-
-    A value of '1' indicates that the driver should enable IP checksum
-    offload for received packets (both UDP and TCP) to the adapter hardware.
-
-RxFCHighThresh
---------------
-:Valid Range: 1,536-262,136 (0x600 - 0x3FFF8, 8 byte granularity)
-:Default Value: 196,608 (0x30000)
-
-    Receive Flow control high threshold (when we send a pause frame)
-
-RxFCLowThresh
--------------
-:Valid Range: 64-262,136 (0x40 - 0x3FFF8, 8 byte granularity)
-:Default Value: 163,840 (0x28000)
-
-    Receive Flow control low threshold (when we send a resume frame)
-
-FCReqTimeout
-------------
-:Valid Range: 1-65535
-:Default Value: 65535
-
-    Flow control request timeout (how long to pause the link partner's tx)
-
-IntDelayEnable
---------------
-:Value Range: 0,1
-:Default Value: 1
-
-    Interrupt Delay, 0 disables transmit interrupt delay and 1 enables it.
-
-
-Improving Performance
-=====================
-
-With the 10 Gigabit server adapters, the default Linux configuration will
-very likely limit the total available throughput artificially.  There is a set
-of configuration changes that, when applied together, will increase the ability
-of Linux to transmit and receive data.  The following enhancements were
-originally acquired from settings published at http://www.spec.org/web99/ for
-various submitted results using Linux.
-
-NOTE:
-  These changes are only suggestions, and serve as a starting point for
-  tuning your network performance.
-
-The changes are made in three major ways, listed in order of greatest effect:
-
-- Use ip link to modify the mtu (maximum transmission unit) and the txqueuelen
-  parameter.
-- Use sysctl to modify /proc parameters (essentially kernel tuning)
-- Use setpci to modify the MMRBC field in PCI-X configuration space to increase
-  transmit burst lengths on the bus.
-
-NOTE:
-  setpci modifies the adapter's configuration registers to allow it to read
-  up to 4k bytes at a time (for transmits).  However, for some systems the
-  behavior after modifying this register may be undefined (possibly errors of
-  some kind).  A power-cycle, hard reset or explicitly setting the e6 register
-  back to 22 (setpci -d 8086:1a48 e6.b=22) may be required to get back to a
-  stable configuration.
-
-- COPY these lines and paste them into ixgb_perf.sh:
-
-::
-
-  #!/bin/bash
-  echo "configuring network performance , edit this file to change the interface
-  or device ID of 10GbE card"
-  # set mmrbc to 4k reads, modify only Intel 10GbE device IDs
-  # replace 1a48 with appropriate 10GbE device's ID installed on the system,
-  # if needed.
-  setpci -d 8086:1a48 e6.b=2e
-  # set the MTU (max transmission unit) - it requires your switch and clients
-  # to change as well.
-  # set the txqueuelen
-  # your ixgb adapter should be loaded as eth1 for this to work, change if needed
-  ip li set dev eth1 mtu 9000 txqueuelen 1000 up
-  # call the sysctl utility to modify /proc/sys entries
-  sysctl -p ./sysctl_ixgb.conf
-
-- COPY these lines and paste them into sysctl_ixgb.conf:
-
-::
-
-  # some of the defaults may be different for your kernel
-  # call this file with sysctl -p <this file>
-  # these are just suggested values that worked well to increase throughput in
-  # several network benchmark tests, your mileage may vary
-
-  ### IPV4 specific settings
-  # turn TCP timestamp support off, default 1, reduces CPU use
-  net.ipv4.tcp_timestamps = 0
-  # turn SACK support off, default on
-  # on systems with a VERY fast bus -> memory interface this is the big gainer
-  net.ipv4.tcp_sack = 0
-  # set min/default/max TCP read buffer, default 4096 87380 174760
-  net.ipv4.tcp_rmem = 10000000 10000000 10000000
-  # set min/pressure/max TCP write buffer, default 4096 16384 131072
-  net.ipv4.tcp_wmem = 10000000 10000000 10000000
-  # set min/pressure/max TCP buffer space, default 31744 32256 32768
-  net.ipv4.tcp_mem = 10000000 10000000 10000000
-
-  ### CORE settings (mostly for socket and UDP effect)
-  # set maximum receive socket buffer size, default 131071
-  net.core.rmem_max = 524287
-  # set maximum send socket buffer size, default 131071
-  net.core.wmem_max = 524287
-  # set default receive socket buffer size, default 65535
-  net.core.rmem_default = 524287
-  # set default send socket buffer size, default 65535
-  net.core.wmem_default = 524287
-  # set maximum amount of option memory buffers, default 10240
-  net.core.optmem_max = 524287
-  # set number of unprocessed input packets before kernel starts dropping them; default 300
-  net.core.netdev_max_backlog = 300000
-
-Edit the ixgb_perf.sh script if necessary to change eth1 to whatever interface
-your ixgb driver is using and/or replace '1a48' with appropriate 10GbE device's
-ID installed on the system.
-
-NOTE:
-  Unless these scripts are added to the boot process, these changes will
-  only last only until the next system reboot.
-
-
-Resolving Slow UDP Traffic
---------------------------
-If your server does not seem to be able to receive UDP traffic as fast as it
-can receive TCP traffic, it could be because Linux, by default, does not set
-the network stack buffers as large as they need to be to support high UDP
-transfer rates.  One way to alleviate this problem is to allow more memory to
-be used by the IP stack to store incoming data.
-
-For instance, use the commands::
-
-    sysctl -w net.core.rmem_max=262143
-
-and::
-
-    sysctl -w net.core.rmem_default=262143
-
-to increase the read buffer memory max and default to 262143 (256k - 1) from
-defaults of max=131071 (128k - 1) and default=65535 (64k - 1).  These variables
-will increase the amount of memory used by the network stack for receives, and
-can be increased significantly more if necessary for your application.
-
-
-Additional Configurations
-=========================
-
-Configuring the Driver on Different Distributions
--------------------------------------------------
-Configuring a network driver to load properly when the system is started is
-distribution dependent. Typically, the configuration process involves adding
-an alias line to /etc/modprobe.conf as well as editing other system startup
-scripts and/or configuration files.  Many popular Linux distributions ship
-with tools to make these changes for you.  To learn the proper way to
-configure a network device for your system, refer to your distribution
-documentation.  If during this process you are asked for the driver or module
-name, the name for the Linux Base Driver for the Intel 10GbE Family of
-Adapters is ixgb.
-
-Viewing Link Messages
----------------------
-Link messages will not be displayed to the console if the distribution is
-restricting system messages. In order to see network driver link messages on
-your console, set dmesg to eight by entering the following::
-
-    dmesg -n 8
-
-NOTE: This setting is not saved across reboots.
-
-Jumbo Frames
-------------
-The driver supports Jumbo Frames for all adapters. Jumbo Frames support is
-enabled by changing the MTU to a value larger than the default of 1500.
-The maximum value for the MTU is 16114.  Use the ip command to
-increase the MTU size.  For example::
-
-    ip li set dev ethx mtu 9000
-
-The maximum MTU setting for Jumbo Frames is 16114.  This value coincides
-with the maximum Jumbo Frames size of 16128.
-
-Ethtool
--------
-The driver utilizes the ethtool interface for driver configuration and
-diagnostics, as well as displaying statistical information.  The ethtool
-version 1.6 or later is required for this functionality.
-
-The latest release of ethtool can be found from
-https://www.kernel.org/pub/software/network/ethtool/
-
-NOTE:
-  The ethtool version 1.6 only supports a limited set of ethtool options.
-  Support for a more complete ethtool feature set can be enabled by
-  upgrading to the latest version.
-
-NAPI
-----
-NAPI (Rx polling mode) is supported in the ixgb driver.
-
-See https://wiki.linuxfoundation.org/networking/napi for more information on
-NAPI.
-
-
-Known Issues/Troubleshooting
-============================
-
-NOTE:
-  After installing the driver, if your Intel Network Connection is not
-  working, verify in the "In This Release" section of the readme that you have
-  installed the correct driver.
-
-Cable Interoperability Issue with Fujitsu XENPAK Module in SmartBits Chassis
-----------------------------------------------------------------------------
-Excessive CRC errors may be observed if the Intel(R) PRO/10GbE CX4
-Server adapter is connected to a Fujitsu XENPAK CX4 module in a SmartBits
-chassis using 15 m/24AWG cable assemblies manufactured by Fujitsu or Leoni.
-The CRC errors may be received either by the Intel(R) PRO/10GbE CX4
-Server adapter or the SmartBits. If this situation occurs using a different
-cable assembly may resolve the issue.
-
-Cable Interoperability Issues with HP Procurve 3400cl Switch Port
------------------------------------------------------------------
-Excessive CRC errors may be observed if the Intel(R) PRO/10GbE CX4 Server
-adapter is connected to an HP Procurve 3400cl switch port using short cables
-(1 m or shorter). If this situation occurs, using a longer cable may resolve
-the issue.
-
-Excessive CRC errors may be observed using Fujitsu 24AWG cable assemblies that
-Are 10 m or longer or where using a Leoni 15 m/24AWG cable assembly. The CRC
-errors may be received either by the CX4 Server adapter or at the switch. If
-this situation occurs, using a different cable assembly may resolve the issue.
-
-Jumbo Frames System Requirement
--------------------------------
-Memory allocation failures have been observed on Linux systems with 64 MB
-of RAM or less that are running Jumbo Frames.  If you are using Jumbo
-Frames, your system may require more than the advertised minimum
-requirement of 64 MB of system memory.
-
-Performance Degradation with Jumbo Frames
------------------------------------------
-Degradation in throughput performance may be observed in some Jumbo frames
-environments.  If this is observed, increasing the application's socket buffer
-size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
-See the specific application manual and /usr/src/linux*/Documentation/
-networking/ip-sysctl.txt for more details.
-
-Allocating Rx Buffers when Using Jumbo Frames
----------------------------------------------
-Allocating Rx buffers when using Jumbo Frames on 2.6.x kernels may fail if
-the available memory is heavily fragmented. This issue may be seen with PCI-X
-adapters or with packet split disabled. This can be reduced or eliminated
-by changing the amount of available memory for receive buffer allocation, by
-increasing /proc/sys/vm/min_free_kbytes.
-
-Multiple Interfaces on Same Ethernet Broadcast Network
-------------------------------------------------------
-Due to the default ARP behavior on Linux, it is not possible to have
-one system on two IP networks in the same Ethernet broadcast domain
-(non-partitioned switch) behave as expected.  All Ethernet interfaces
-will respond to IP traffic for any IP address assigned to the system.
-This results in unbalanced receive traffic.
-
-If you have multiple interfaces in a server, do either of the following:
-
-  - Turn on ARP filtering by entering::
-
-      echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
-
-  - Install the interfaces in separate broadcast domains - either in
-    different switches or in a switch partitioned to VLANs.
-
-UDP Stress Test Dropped Packet Issue
---------------------------------------
-Under small packets UDP stress test with 10GbE driver, the Linux system
-may drop UDP packets due to the fullness of socket buffers. You may want
-to change the driver's Flow Control variables to the minimum value for
-controlling packet reception.
-
-Tx Hangs Possible Under Stress
-------------------------------
-Under stress conditions, if TX hangs occur, turning off TSO
-"ethtool -K eth0 tso off" may resolve the problem.
-
-
-Support
-=======
-For general information, go to the Intel support website at:
-
-https://www.intel.com/support/
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-
-https://sourceforge.net/projects/e1000
-
-If an issue is identified with the released source code on a supported kernel
-with a supported adapter, email the specific information related to the issue
-to e1000-devel@lists.sf.net
diff --git a/Documentation/networking/ixgbe.rst b/Documentation/networking/ixgbe.rst
deleted file mode 100644
index 86d887a63606..000000000000
--- a/Documentation/networking/ixgbe.rst
+++ /dev/null
@@ -1,540 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux* Base Driver for the Intel(R) Ethernet 10 Gigabit PCI Express Adapters
-=============================================================================
-
-Intel 10 Gigabit Linux driver.
-Copyright(c) 1999-2018 Intel Corporation.
-
-Contents
-========
-
-- Identifying Your Adapter
-- Command Line Parameters
-- Additional Configurations
-- Known Issues
-- Support
-
-Identifying Your Adapter
-========================
-The driver is compatible with devices based on the following:
-
- * Intel(R) Ethernet Controller 82598
- * Intel(R) Ethernet Controller 82599
- * Intel(R) Ethernet Controller X520
- * Intel(R) Ethernet Controller X540
- * Intel(R) Ethernet Controller x550
- * Intel(R) Ethernet Controller X552
- * Intel(R) Ethernet Controller X553
-
-For information on how to identify your adapter, and for the latest Intel
-network drivers, refer to the Intel Support website:
-https://www.intel.com/support
-
-SFP+ Devices with Pluggable Optics
-----------------------------------
-
-82599-BASED ADAPTERS
-~~~~~~~~~~~~~~~~~~~~
-NOTES:
-- If your 82599-based Intel(R) Network Adapter came with Intel optics or is an
-Intel(R) Ethernet Server Adapter X520-2, then it only supports Intel optics
-and/or the direct attach cables listed below.
-- When 82599-based SFP+ devices are connected back to back, they should be set
-to the same Speed setting via ethtool. Results may vary if you mix speed
-settings.
-
-+---------------+---------------------------------------+------------------+
-| Supplier      | Type                                  | Part Numbers     |
-+===============+=======================================+==================+
-| SR Modules                                                               |
-+---------------+---------------------------------------+------------------+
-| Intel         | DUAL RATE 1G/10G SFP+ SR (bailed)     | FTLX8571D3BCV-IT |
-+---------------+---------------------------------------+------------------+
-| Intel         | DUAL RATE 1G/10G SFP+ SR (bailed)     | AFBR-703SDZ-IN2  |
-+---------------+---------------------------------------+------------------+
-| Intel         | DUAL RATE 1G/10G SFP+ SR (bailed)     | AFBR-703SDDZ-IN1 |
-+---------------+---------------------------------------+------------------+
-| LR Modules                                                               |
-+---------------+---------------------------------------+------------------+
-| Intel         | DUAL RATE 1G/10G SFP+ LR (bailed)     | FTLX1471D3BCV-IT |
-+---------------+---------------------------------------+------------------+
-| Intel         | DUAL RATE 1G/10G SFP+ LR (bailed)     | AFCT-701SDZ-IN2  |
-+---------------+---------------------------------------+------------------+
-| Intel         | DUAL RATE 1G/10G SFP+ LR (bailed)     | AFCT-701SDDZ-IN1 |
-+---------------+---------------------------------------+------------------+
-
-The following is a list of 3rd party SFP+ modules that have received some
-testing. Not all modules are applicable to all devices.
-
-+---------------+---------------------------------------+------------------+
-| Supplier      | Type                                  | Part Numbers     |
-+===============+=======================================+==================+
-| Finisar       | SFP+ SR bailed, 10g single rate       | FTLX8571D3BCL    |
-+---------------+---------------------------------------+------------------+
-| Avago         | SFP+ SR bailed, 10g single rate       | AFBR-700SDZ      |
-+---------------+---------------------------------------+------------------+
-| Finisar       | SFP+ LR bailed, 10g single rate       | FTLX1471D3BCL    |
-+---------------+---------------------------------------+------------------+
-| Finisar       | DUAL RATE 1G/10G SFP+ SR (No Bail)    | FTLX8571D3QCV-IT |
-+---------------+---------------------------------------+------------------+
-| Avago         | DUAL RATE 1G/10G SFP+ SR (No Bail)    | AFBR-703SDZ-IN1  |
-+---------------+---------------------------------------+------------------+
-| Finisar       | DUAL RATE 1G/10G SFP+ LR (No Bail)    | FTLX1471D3QCV-IT |
-+---------------+---------------------------------------+------------------+
-| Avago         | DUAL RATE 1G/10G SFP+ LR (No Bail)    | AFCT-701SDZ-IN1  |
-+---------------+---------------------------------------+------------------+
-| Finisar       | 1000BASE-T SFP                        | FCLF8522P2BTL    |
-+---------------+---------------------------------------+------------------+
-| Avago         | 1000BASE-T                            | ABCU-5710RZ      |
-+---------------+---------------------------------------+------------------+
-| HP            | 1000BASE-SX SFP                       | 453153-001       |
-+---------------+---------------------------------------+------------------+
-
-82599-based adapters support all passive and active limiting direct attach
-cables that comply with SFF-8431 v4.1 and SFF-8472 v10.4 specifications.
-
-Laser turns off for SFP+ when ifconfig ethX down
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-"ifconfig ethX down" turns off the laser for 82599-based SFP+ fiber adapters.
-"ifconfig ethX up" turns on the laser.
-Alternatively, you can use "ip link set [down/up] dev ethX" to turn the
-laser off and on.
-
-
-82599-based QSFP+ Adapters
-~~~~~~~~~~~~~~~~~~~~~~~~~~
-NOTES:
-- If your 82599-based Intel(R) Network Adapter came with Intel optics, it only
-supports Intel optics.
-- 82599-based QSFP+ adapters only support 4x10 Gbps connections.  1x40 Gbps
-connections are not supported. QSFP+ link partners must be configured for
-4x10 Gbps.
-- 82599-based QSFP+ adapters do not support automatic link speed detection.
-The link speed must be configured to either 10 Gbps or 1 Gbps to match the link
-partners speed capabilities. Incorrect speed configurations will result in
-failure to link.
-- Intel(R) Ethernet Converged Network Adapter X520-Q1 only supports the optics
-and direct attach cables listed below.
-
-+---------------+---------------------------------------+------------------+
-| Supplier      | Type                                  | Part Numbers     |
-+===============+=======================================+==================+
-| Intel         | DUAL RATE 1G/10G QSFP+ SRL (bailed)   | E10GQSFPSR       |
-+---------------+---------------------------------------+------------------+
-
-82599-based QSFP+ adapters support all passive and active limiting QSFP+
-direct attach cables that comply with SFF-8436 v4.1 specifications.
-
-82598-BASED ADAPTERS
-~~~~~~~~~~~~~~~~~~~~
-NOTES:
-- Intel(r) Ethernet Network Adapters that support removable optical modules
-only support their original module type (for example, the Intel(R) 10 Gigabit
-SR Dual Port Express Module only supports SR optical modules). If you plug in
-a different type of module, the driver will not load.
-- Hot Swapping/hot plugging optical modules is not supported.
-- Only single speed, 10 gigabit modules are supported.
-- LAN on Motherboard (LOMs) may support DA, SR, or LR modules. Other module
-types are not supported. Please see your system documentation for details.
-
-The following is a list of SFP+ modules and direct attach cables that have
-received some testing. Not all modules are applicable to all devices.
-
-+---------------+---------------------------------------+------------------+
-| Supplier      | Type                                  | Part Numbers     |
-+===============+=======================================+==================+
-| Finisar       | SFP+ SR bailed, 10g single rate       | FTLX8571D3BCL    |
-+---------------+---------------------------------------+------------------+
-| Avago         | SFP+ SR bailed, 10g single rate       | AFBR-700SDZ      |
-+---------------+---------------------------------------+------------------+
-| Finisar       | SFP+ LR bailed, 10g single rate       | FTLX1471D3BCL    |
-+---------------+---------------------------------------+------------------+
-
-82598-based adapters support all passive direct attach cables that comply with
-SFF-8431 v4.1 and SFF-8472 v10.4 specifications. Active direct attach cables
-are not supported.
-
-Third party optic modules and cables referred to above are listed only for the
-purpose of highlighting third party specifications and potential
-compatibility, and are not recommendations or endorsements or sponsorship of
-any third party's product by Intel. Intel is not endorsing or promoting
-products made by any third party and the third party reference is provided
-only to share information regarding certain optic modules and cables with the
-above specifications. There may be other manufacturers or suppliers, producing
-or supplying optic modules and cables with similar or matching descriptions.
-Customers must use their own discretion and diligence to purchase optic
-modules and cables from any third party of their choice. Customers are solely
-responsible for assessing the suitability of the product and/or devices and
-for the selection of the vendor for purchasing any product. THE OPTIC MODULES
-AND CABLES REFERRED TO ABOVE ARE NOT WARRANTED OR SUPPORTED BY INTEL. INTEL
-ASSUMES NO LIABILITY WHATSOEVER, AND INTEL DISCLAIMS ANY EXPRESS OR IMPLIED
-WARRANTY, RELATING TO SALE AND/OR USE OF SUCH THIRD PARTY PRODUCTS OR
-SELECTION OF VENDOR BY CUSTOMERS.
-
-Command Line Parameters
-=======================
-
-max_vfs
--------
-:Valid Range: 1-63
-
-This parameter adds support for SR-IOV. It causes the driver to spawn up to
-max_vfs worth of virtual functions.
-If the value is greater than 0 it will also force the VMDq parameter to be 1 or
-more.
-
-NOTE: This parameter is only used on kernel 3.7.x and below. On kernel 3.8.x
-and above, use sysfs to enable VFs. Also, for Red Hat distributions, this
-parameter is only used on version 6.6 and older. For version 6.7 and newer, use
-sysfs. For example::
-
-  #echo $num_vf_enabled > /sys/class/net/$dev/device/sriov_numvfs // enable VFs
-  #echo 0 > /sys/class/net/$dev/device/sriov_numvfs               //disable VFs
-
-The parameters for the driver are referenced by position. Thus, if you have a
-dual port adapter, or more than one adapter in your system, and want N virtual
-functions per port, you must specify a number for each port with each parameter
-separated by a comma. For example::
-
-  modprobe ixgbe max_vfs=4
-
-This will spawn 4 VFs on the first port.
-
-::
-
-  modprobe ixgbe max_vfs=2,4
-
-This will spawn 2 VFs on the first port and 4 VFs on the second port.
-
-NOTE: Caution must be used in loading the driver with these parameters.
-Depending on your system configuration, number of slots, etc., it is impossible
-to predict in all cases where the positions would be on the command line.
-
-NOTE: Neither the device nor the driver control how VFs are mapped into config
-space. Bus layout will vary by operating system. On operating systems that
-support it, you can check sysfs to find the mapping.
-
-NOTE: When either SR-IOV mode or VMDq mode is enabled, hardware VLAN filtering
-and VLAN tag stripping/insertion will remain enabled. Please remove the old
-VLAN filter before the new VLAN filter is added. For example,
-
-::
-
-  ip link set eth0 vf 0 vlan 100 // set VLAN 100 for VF 0
-  ip link set eth0 vf 0 vlan 0   // Delete VLAN 100
-  ip link set eth0 vf 0 vlan 200 // set a new VLAN 200 for VF 0
-
-With kernel 3.6, the driver supports the simultaneous usage of max_vfs and DCB
-features, subject to the constraints described below. Prior to kernel 3.6, the
-driver did not support the simultaneous operation of max_vfs greater than 0 and
-the DCB features (multiple traffic classes utilizing Priority Flow Control and
-Extended Transmission Selection).
-
-When DCB is enabled, network traffic is transmitted and received through
-multiple traffic classes (packet buffers in the NIC). The traffic is associated
-with a specific class based on priority, which has a value of 0 through 7 used
-in the VLAN tag. When SR-IOV is not enabled, each traffic class is associated
-with a set of receive/transmit descriptor queue pairs. The number of queue
-pairs for a given traffic class depends on the hardware configuration. When
-SR-IOV is enabled, the descriptor queue pairs are grouped into pools. The
-Physical Function (PF) and each Virtual Function (VF) is allocated a pool of
-receive/transmit descriptor queue pairs. When multiple traffic classes are
-configured (for example, DCB is enabled), each pool contains a queue pair from
-each traffic class. When a single traffic class is configured in the hardware,
-the pools contain multiple queue pairs from the single traffic class.
-
-The number of VFs that can be allocated depends on the number of traffic
-classes that can be enabled. The configurable number of traffic classes for
-each enabled VF is as follows:
-0 - 15 VFs = Up to 8 traffic classes, depending on device support
-16 - 31 VFs = Up to 4 traffic classes
-32 - 63 VFs = 1 traffic class
-
-When VFs are configured, the PF is allocated one pool as well. The PF supports
-the DCB features with the constraint that each traffic class will only use a
-single queue pair. When zero VFs are configured, the PF can support multiple
-queue pairs per traffic class.
-
-allow_unsupported_sfp
----------------------
-:Valid Range: 0,1
-:Default Value: 0 (disabled)
-
-This parameter allows unsupported and untested SFP+ modules on 82599-based
-adapters, as long as the type of module is known to the driver.
-
-debug
------
-:Valid Range: 0-16 (0=none,...,16=all)
-:Default Value: 0
-
-This parameter adjusts the level of debug messages displayed in the system
-logs.
-
-
-Additional Features and Configurations
-======================================
-
-Flow Control
-------------
-Ethernet Flow Control (IEEE 802.3x) can be configured with ethtool to enable
-receiving and transmitting pause frames for ixgbe. When transmit is enabled,
-pause frames are generated when the receive packet buffer crosses a predefined
-threshold. When receive is enabled, the transmit unit will halt for the time
-delay specified when a pause frame is received.
-
-NOTE: You must have a flow control capable link partner.
-
-Flow Control is enabled by default.
-
-Use ethtool to change the flow control settings. To enable or disable Rx or
-Tx Flow Control::
-
-  ethtool -A eth? rx <on|off> tx <on|off>
-
-Note: This command only enables or disables Flow Control if auto-negotiation is
-disabled. If auto-negotiation is enabled, this command changes the parameters
-used for auto-negotiation with the link partner.
-
-To enable or disable auto-negotiation::
-
-  ethtool -s eth? autoneg <on|off>
-
-Note: Flow Control auto-negotiation is part of link auto-negotiation. Depending
-on your device, you may not be able to change the auto-negotiation setting.
-
-NOTE: For 82598 backplane cards entering 1 gigabit mode, flow control default
-behavior is changed to off. Flow control in 1 gigabit mode on these devices can
-lead to transmit hangs.
-
-Intel(R) Ethernet Flow Director
--------------------------------
-The Intel Ethernet Flow Director performs the following tasks:
-
-- Directs receive packets according to their flows to different queues.
-- Enables tight control on routing a flow in the platform.
-- Matches flows and CPU cores for flow affinity.
-- Supports multiple parameters for flexible flow classification and load
-  balancing (in SFP mode only).
-
-NOTE: Intel Ethernet Flow Director masking works in the opposite manner from
-subnet masking. In the following command::
-
-  #ethtool -N eth11 flow-type ip4 src-ip 172.4.1.2 m 255.0.0.0 dst-ip \
-  172.21.1.1 m 255.128.0.0 action 31
-
-The src-ip value that is written to the filter will be 0.4.1.2, not 172.0.0.0
-as might be expected. Similarly, the dst-ip value written to the filter will be
-0.21.1.1, not 172.0.0.0.
-
-To enable or disable the Intel Ethernet Flow Director::
-
-  # ethtool -K ethX ntuple <on|off>
-
-When disabling ntuple filters, all the user programmed filters are flushed from
-the driver cache and hardware. All needed filters must be re-added when ntuple
-is re-enabled.
-
-To add a filter that directs packet to queue 2, use -U or -N switch::
-
-  # ethtool -N ethX flow-type tcp4 src-ip 192.168.10.1 dst-ip \
-  192.168.10.2 src-port 2000 dst-port 2001 action 2 [loc 1]
-
-To see the list of filters currently present::
-
-  # ethtool <-u|-n> ethX
-
-Sideband Perfect Filters
-------------------------
-Sideband Perfect Filters are used to direct traffic that matches specified
-characteristics. They are enabled through ethtool's ntuple interface. To add a
-new filter use the following command::
-
-  ethtool -U <device> flow-type <type> src-ip <ip> dst-ip <ip> src-port <port> \
-  dst-port <port> action <queue>
-
-Where:
-  <device> - the ethernet device to program
-  <type> - can be ip4, tcp4, udp4, or sctp4
-  <ip> - the IP address to match on
-  <port> - the port number to match on
-  <queue> - the queue to direct traffic towards (-1 discards the matched traffic)
-
-Use the following command to delete a filter::
-
-  ethtool -U <device> delete <N>
-
-Where <N> is the filter id displayed when printing all the active filters, and
-may also have been specified using "loc <N>" when adding the filter.
-
-The following example matches TCP traffic sent from 192.168.0.1, port 5300,
-directed to 192.168.0.5, port 80, and sends it to queue 7::
-
-  ethtool -U enp130s0 flow-type tcp4 src-ip 192.168.0.1 dst-ip 192.168.0.5 \
-  src-port 5300 dst-port 80 action 7
-
-For each flow-type, the programmed filters must all have the same matching
-input set. For example, issuing the following two commands is acceptable::
-
-  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.1 src-port 5300 action 7
-  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.5 src-port 55 action 10
-
-Issuing the next two commands, however, is not acceptable, since the first
-specifies src-ip and the second specifies dst-ip::
-
-  ethtool -U enp130s0 flow-type ip4 src-ip 192.168.0.1 src-port 5300 action 7
-  ethtool -U enp130s0 flow-type ip4 dst-ip 192.168.0.5 src-port 55 action 10
-
-The second command will fail with an error. You may program multiple filters
-with the same fields, using different values, but, on one device, you may not
-program two TCP4 filters with different matching fields.
-
-Matching on a sub-portion of a field is not supported by the ixgbe driver, thus
-partial mask fields are not supported.
-
-To create filters that direct traffic to a specific Virtual Function, use the
-"user-def" parameter. Specify the user-def as a 64 bit value, where the lower 32
-bits represents the queue number, while the next 8 bits represent which VF.
-Note that 0 is the PF, so the VF identifier is offset by 1. For example::
-
-  ... user-def 0x800000002 ...
-
-specifies to direct traffic to Virtual Function 7 (8 minus 1) into queue 2 of
-that VF.
-
-Note that these filters will not break internal routing rules, and will not
-route traffic that otherwise would not have been sent to the specified Virtual
-Function.
-
-Jumbo Frames
-------------
-Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU)
-to a value larger than the default value of 1500.
-
-Use the ifconfig command to increase the MTU size. For example, enter the
-following where <x> is the interface number::
-
-  ifconfig eth<x> mtu 9000 up
-
-Alternatively, you can use the ip command as follows::
-
-  ip link set mtu 9000 dev eth<x>
-  ip link set up dev eth<x>
-
-This setting is not saved across reboots. The setting change can be made
-permanent by adding 'MTU=9000' to the file::
-
-  /etc/sysconfig/network-scripts/ifcfg-eth<x> // for RHEL
-  /etc/sysconfig/network/<config_file> // for SLES
-
-NOTE: The maximum MTU setting for Jumbo Frames is 9710. This value coincides
-with the maximum Jumbo Frames size of 9728 bytes.
-
-NOTE: This driver will attempt to use multiple page sized buffers to receive
-each jumbo packet. This should help to avoid buffer starvation issues when
-allocating receive packets.
-
-NOTE: For 82599-based network connections, if you are enabling jumbo frames in
-a virtual function (VF), jumbo frames must first be enabled in the physical
-function (PF). The VF MTU setting cannot be larger than the PF MTU.
-
-Generic Receive Offload, aka GRO
---------------------------------
-The driver supports the in-kernel software implementation of GRO. GRO has
-shown that by coalescing Rx traffic into larger chunks of data, CPU
-utilization can be significantly reduced when under large Rx load. GRO is an
-evolution of the previously-used LRO interface. GRO is able to coalesce
-other protocols besides TCP. It's also safe to use with configurations that
-are problematic for LRO, namely bridging and iSCSI.
-
-Data Center Bridging (DCB)
---------------------------
-NOTE:
-The kernel assumes that TC0 is available, and will disable Priority Flow
-Control (PFC) on the device if TC0 is not available. To fix this, ensure TC0 is
-enabled when setting up DCB on your switch.
-
-DCB is a configuration Quality of Service implementation in hardware. It uses
-the VLAN priority tag (802.1p) to filter traffic. That means that there are 8
-different priorities that traffic can be filtered into. It also enables
-priority flow control (802.1Qbb) which can limit or eliminate the number of
-dropped packets during network stress. Bandwidth can be allocated to each of
-these priorities, which is enforced at the hardware level (802.1Qaz).
-
-Adapter firmware implements LLDP and DCBX protocol agents as per 802.1AB and
-802.1Qaz respectively. The firmware based DCBX agent runs in willing mode only
-and can accept settings from a DCBX capable peer. Software configuration of
-DCBX parameters via dcbtool/lldptool are not supported.
-
-The ixgbe driver implements the DCB netlink interface layer to allow user-space
-to communicate with the driver and query DCB configuration for the port.
-
-ethtool
--------
-The driver utilizes the ethtool interface for driver configuration and
-diagnostics, as well as displaying statistical information. The latest ethtool
-version is required for this functionality. Download it at:
-https://www.kernel.org/pub/software/network/ethtool/
-
-FCoE
-----
-The ixgbe driver supports Fiber Channel over Ethernet (FCoE) and Data Center
-Bridging (DCB). This code has no default effect on the regular driver
-operation. Configuring DCB and FCoE is outside the scope of this README. Refer
-to http://www.open-fcoe.org/ for FCoE project information and contact
-ixgbe-eedc@lists.sourceforge.net for DCB information.
-
-MAC and VLAN anti-spoofing feature
-----------------------------------
-When a malicious driver attempts to send a spoofed packet, it is dropped by the
-hardware and not transmitted.
-
-An interrupt is sent to the PF driver notifying it of the spoof attempt. When a
-spoofed packet is detected, the PF driver will send the following message to
-the system log (displayed by the "dmesg" command)::
-
-  ixgbe ethX: ixgbe_spoof_check: n spoofed packets detected
-
-where "x" is the PF interface number; and "n" is number of spoofed packets.
-NOTE: This feature can be disabled for a specific Virtual Function (VF)::
-
-  ip link set <pf dev> vf <vf id> spoofchk {off|on}
-
-IPsec Offload
--------------
-The ixgbe driver supports IPsec Hardware Offload.  When creating Security
-Associations with "ip xfrm ..." the 'offload' tag option can be used to
-register the IPsec SA with the driver in order to get higher throughput in
-the secure communications.
-
-The offload is also supported for ixgbe's VFs, but the VF must be set as
-'trusted' and the support must be enabled with::
-
-  ethtool --set-priv-flags eth<x> vf-ipsec on
-  ip link set eth<x> vf <y> trust on
-
-
-Known Issues/Troubleshooting
-============================
-
-Enabling SR-IOV in a 64-bit Microsoft* Windows Server* 2012/R2 guest OS
------------------------------------------------------------------------
-Linux KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM.
-This includes traditional PCIe devices, as well as SR-IOV-capable devices based
-on the Intel Ethernet Controller XL710.
-
-
-Support
-=======
-For general information, go to the Intel support website at:
-
-https://www.intel.com/support/
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-
-https://sourceforge.net/projects/e1000
-
-If an issue is identified with the released source code on a supported kernel
-with a supported adapter, email the specific information related to the issue
-to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/ixgbevf.rst b/Documentation/networking/ixgbevf.rst
deleted file mode 100644
index 56cde6366c2f..000000000000
--- a/Documentation/networking/ixgbevf.rst
+++ /dev/null
@@ -1,66 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0+
-
-Linux* Base Virtual Function Driver for Intel(R) 10G Ethernet
-=============================================================
-
-Intel 10 Gigabit Virtual Function Linux driver.
-Copyright(c) 1999-2018 Intel Corporation.
-
-Contents
-========
-
-- Identifying Your Adapter
-- Known Issues
-- Support
-
-This driver supports 82599, X540, X550, and X552-based virtual function devices
-that can only be activated on kernels that support SR-IOV.
-
-For questions related to hardware requirements, refer to the documentation
-supplied with your Intel adapter. All hardware requirements listed apply to use
-with Linux.
-
-
-Identifying Your Adapter
-========================
-The driver is compatible with devices based on the following:
-
-  * Intel(R) Ethernet Controller 82598
-  * Intel(R) Ethernet Controller 82599
-  * Intel(R) Ethernet Controller X520
-  * Intel(R) Ethernet Controller X540
-  * Intel(R) Ethernet Controller x550
-  * Intel(R) Ethernet Controller X552
-  * Intel(R) Ethernet Controller X553
-
-For information on how to identify your adapter, and for the latest Intel
-network drivers, refer to the Intel Support website:
-https://www.intel.com/support
-
-Known Issues/Troubleshooting
-============================
-
-SR-IOV requires the correct platform and OS support.
-
-The guest OS loading this driver must support MSI-X interrupts.
-
-This driver is only supported as a loadable module at this time. Intel is not
-supplying patches against the kernel source to allow for static linking of the
-drivers.
-
-VLANs: There is a limit of a total of 64 shared VLANs to 1 or more VFs.
-
-
-Support
-=======
-For general information, go to the Intel support website at:
-
-https://www.intel.com/support/
-
-or the Intel Wired Networking project hosted by Sourceforge at:
-
-https://sourceforge.net/projects/e1000
-
-If an issue is identified with the released source code on a supported kernel
-with a supported adapter, email the specific information related to the issue
-to e1000-devel@lists.sf.net.
diff --git a/Documentation/networking/netvsc.txt b/Documentation/networking/netvsc.txt
deleted file mode 100644
index 3bfa635bbbd5..000000000000
--- a/Documentation/networking/netvsc.txt
+++ /dev/null
@@ -1,84 +0,0 @@
-Hyper-V network driver
-======================
-
-Compatibility
-=============
-
-This driver is compatible with Windows Server 2012 R2, 2016 and
-Windows 10.
-
-Features
-========
-
-  Checksum offload
-  ----------------
-  The netvsc driver supports checksum offload as long as the
-  Hyper-V host version does. Windows Server 2016 and Azure
-  support checksum offload for TCP and UDP for both IPv4 and
-  IPv6. Windows Server 2012 only supports checksum offload for TCP.
-
-  Receive Side Scaling
-  --------------------
-  Hyper-V supports receive side scaling. For TCP & UDP, packets can
-  be distributed among available queues based on IP address and port
-  number.
-
-  For TCP & UDP, we can switch hash level between L3 and L4 by ethtool
-  command. TCP/UDP over IPv4 and v6 can be set differently. The default
-  hash level is L4. We currently only allow switching TX hash level
-  from within the guests.
-
-  On Azure, fragmented UDP packets have high loss rate with L4
-  hashing. Using L3 hashing is recommended in this case.
-
-  For example, for UDP over IPv4 on eth0:
-  To include UDP port numbers in hashing:
-        ethtool -N eth0 rx-flow-hash udp4 sdfn
-  To exclude UDP port numbers in hashing:
-        ethtool -N eth0 rx-flow-hash udp4 sd
-  To show UDP hash level:
-        ethtool -n eth0 rx-flow-hash udp4
-
-  Generic Receive Offload, aka GRO
-  --------------------------------
-  The driver supports GRO and it is enabled by default. GRO coalesces
-  like packets and significantly reduces CPU usage under heavy Rx
-  load.
-
-  Large Receive Offload (LRO), or Receive Side Coalescing (RSC)
-  -------------------------------------------------------------
-  The driver supports LRO/RSC in the vSwitch feature. It reduces the per packet
-  processing overhead by coalescing multiple TCP segments when possible. The
-  feature is enabled by default on VMs running on Windows Server 2019 and
-  later. It may be changed by ethtool command:
-	ethtool -K eth0 lro on
-	ethtool -K eth0 lro off
-
-  SR-IOV support
-  --------------
-  Hyper-V supports SR-IOV as a hardware acceleration option. If SR-IOV
-  is enabled in both the vSwitch and the guest configuration, then the
-  Virtual Function (VF) device is passed to the guest as a PCI
-  device. In this case, both a synthetic (netvsc) and VF device are
-  visible in the guest OS and both NIC's have the same MAC address.
-
-  The VF is enslaved by netvsc device.  The netvsc driver will transparently
-  switch the data path to the VF when it is available and up.
-  Network state (addresses, firewall, etc) should be applied only to the
-  netvsc device; the slave device should not be accessed directly in
-  most cases.  The exceptions are if some special queue discipline or
-  flow direction is desired, these should be applied directly to the
-  VF slave device.
-
-  Receive Buffer
-  --------------
-  Packets are received into a receive area which is created when device
-  is probed. The receive area is broken into MTU sized chunks and each may
-  contain one or more packets. The number of receive sections may be changed
-  via ethtool Rx ring parameters.
-
-  There is a similar send buffer which is used to aggregate packets for sending.
-  The send area is broken into chunks of 6144 bytes, each of section may
-  contain one or more packets. The send buffer is an optimization, the driver
-  will use slower method to handle very large packets or if the send buffer
-  area is exhausted.
diff --git a/Documentation/networking/rmnet.txt b/Documentation/networking/rmnet.txt
deleted file mode 100644
index 6b341eaf2062..000000000000
--- a/Documentation/networking/rmnet.txt
+++ /dev/null
@@ -1,82 +0,0 @@
-1. Introduction
-
-rmnet driver is used for supporting the Multiplexing and aggregation
-Protocol (MAP). This protocol is used by all recent chipsets using Qualcomm
-Technologies, Inc. modems.
-
-This driver can be used to register onto any physical network device in
-IP mode. Physical transports include USB, HSIC, PCIe and IP accelerator.
-
-Multiplexing allows for creation of logical netdevices (rmnet devices) to
-handle multiple private data networks (PDN) like a default internet, tethering,
-multimedia messaging service (MMS) or IP media subsystem (IMS). Hardware sends
-packets with MAP headers to rmnet. Based on the multiplexer id, rmnet
-routes to the appropriate PDN after removing the MAP header.
-
-Aggregation is required to achieve high data rates. This involves hardware
-sending aggregated bunch of MAP frames. rmnet driver will de-aggregate
-these MAP frames and send them to appropriate PDN's.
-
-2. Packet format
-
-a. MAP packet (data / control)
-
-MAP header has the same endianness of the IP packet.
-
-Packet format -
-
-Bit             0             1           2-7      8 - 15           16 - 31
-Function   Command / Data   Reserved     Pad   Multiplexer ID    Payload length
-Bit            32 - x
-Function     Raw  Bytes
-
-Command (1)/ Data (0) bit value is to indicate if the packet is a MAP command
-or data packet. Control packet is used for transport level flow control. Data
-packets are standard IP packets.
-
-Reserved bits are usually zeroed out and to be ignored by receiver.
-
-Padding is number of bytes to be added for 4 byte alignment if required by
-hardware.
-
-Multiplexer ID is to indicate the PDN on which data has to be sent.
-
-Payload length includes the padding length but does not include MAP header
-length.
-
-b. MAP packet (command specific)
-
-Bit             0             1           2-7      8 - 15           16 - 31
-Function   Command         Reserved     Pad   Multiplexer ID    Payload length
-Bit          32 - 39        40 - 45    46 - 47       48 - 63
-Function   Command name    Reserved   Command Type   Reserved
-Bit          64 - 95
-Function   Transaction ID
-Bit          96 - 127
-Function   Command data
-
-Command 1 indicates disabling flow while 2 is enabling flow
-
-Command types -
-0 for MAP command request
-1 is to acknowledge the receipt of a command
-2 is for unsupported commands
-3 is for error during processing of commands
-
-c. Aggregation
-
-Aggregation is multiple MAP packets (can be data or command) delivered to
-rmnet in a single linear skb. rmnet will process the individual
-packets and either ACK the MAP command or deliver the IP packet to the
-network stack as needed
-
-MAP header|IP Packet|Optional padding|MAP header|IP Packet|Optional padding....
-MAP header|IP Packet|Optional padding|MAP header|Command Packet|Optional pad...
-
-3. Userspace configuration
-
-rmnet userspace configuration is done through netlink library librmnetctl
-and command line utility rmnetcli. Utility is hosted in codeaurora forum git.
-The driver uses rtnl_link_ops for communication.
-
-https://source.codeaurora.org/quic/la/platform/vendor/qcom-opensource/dataservices/tree/rmnetctl
diff --git a/Documentation/networking/s2io.txt b/Documentation/networking/s2io.txt
deleted file mode 100644
index 0362a42f7cf4..000000000000
--- a/Documentation/networking/s2io.txt
+++ /dev/null
@@ -1,141 +0,0 @@
-Release notes for Neterion's (Formerly S2io) Xframe I/II PCI-X 10GbE driver.
-
-Contents
-=======
-- 1.  Introduction
-- 2.  Identifying the adapter/interface
-- 3.  Features supported
-- 4.  Command line parameters
-- 5.  Performance suggestions
-- 6.  Available Downloads 
-
-
-1.	Introduction:
-This Linux driver supports Neterion's Xframe I PCI-X 1.0 and
-Xframe II PCI-X 2.0 adapters. It supports several features 
-such as jumbo frames, MSI/MSI-X, checksum offloads, TSO, UFO and so on.
-See below for complete list of features.
-All features are supported for both IPv4 and IPv6.
-
-2.	Identifying the adapter/interface:
-a. Insert the adapter(s) in your system.
-b. Build and load driver 
-# insmod s2io.ko
-c. View log messages
-# dmesg | tail -40
-You will see messages similar to:
-eth3: Neterion Xframe I 10GbE adapter (rev 3), Version 2.0.9.1, Intr type INTA
-eth4: Neterion Xframe II 10GbE adapter (rev 2), Version 2.0.9.1, Intr type INTA
-eth4: Device is on 64 bit 133MHz PCIX(M1) bus
-
-The above messages identify the adapter type(Xframe I/II), adapter revision,
-driver version, interface name(eth3, eth4), Interrupt type(INTA, MSI, MSI-X).
-In case of Xframe II, the PCI/PCI-X bus width and frequency are displayed
-as well.
-
-To associate an interface with a physical adapter use "ethtool -p <ethX>".
-The corresponding adapter's LED will blink multiple times.
-
-3.	Features supported:
-a. Jumbo frames. Xframe I/II supports MTU up to 9600 bytes,
-modifiable using ip command.
-
-b. Offloads. Supports checksum offload(TCP/UDP/IP) on transmit
-and receive, TSO.
-
-c. Multi-buffer receive mode. Scattering of packet across multiple
-buffers. Currently driver supports 2-buffer mode which yields
-significant performance improvement on certain platforms(SGI Altix,
-IBM xSeries).
-
-d. MSI/MSI-X. Can be enabled on platforms which support this feature
-(IA64, Xeon) resulting in noticeable performance improvement(up to 7%
-on certain platforms).
-
-e. Statistics. Comprehensive MAC-level and software statistics displayed
-using "ethtool -S" option.
-
-f. Multi-FIFO/Ring. Supports up to 8 transmit queues and receive rings,
-with multiple steering options.
-
-4.  Command line parameters
-a. tx_fifo_num
-Number of transmit queues
-Valid range: 1-8
-Default: 1
-
-b. rx_ring_num
-Number of receive rings
-Valid range: 1-8
-Default: 1
-
-c. tx_fifo_len
-Size of each transmit queue
-Valid range: Total length of all queues should not exceed 8192
-Default: 4096
-
-d. rx_ring_sz 
-Size of each receive ring(in 4K blocks)
-Valid range: Limited by memory on system
-Default: 30 
-
-e. intr_type
-Specifies interrupt type. Possible values 0(INTA), 2(MSI-X)
-Valid values: 0, 2
-Default: 2
-
-5.  Performance suggestions
-General:
-a. Set MTU to maximum(9000 for switch setup, 9600 in back-to-back configuration)
-b. Set TCP windows size to optimal value. 
-For instance, for MTU=1500 a value of 210K has been observed to result in 
-good performance.
-# sysctl -w net.ipv4.tcp_rmem="210000 210000 210000"
-# sysctl -w net.ipv4.tcp_wmem="210000 210000 210000"
-For MTU=9000, TCP window size of 10 MB is recommended.
-# sysctl -w net.ipv4.tcp_rmem="10000000 10000000 10000000"
-# sysctl -w net.ipv4.tcp_wmem="10000000 10000000 10000000"
-
-Transmit performance:
-a. By default, the driver respects BIOS settings for PCI bus parameters. 
-However, you may want to experiment with PCI bus parameters 
-max-split-transactions(MOST) and MMRBC (use setpci command). 
-A MOST value of 2 has been found optimal for Opterons and 3 for Itanium.  
-It could be different for your hardware.  
-Set MMRBC to 4K**.
-
-For example you can set 
-For opteron
-#setpci -d 17d5:* 62=1d 
-For Itanium
-#setpci -d 17d5:* 62=3d 
-
-For detailed description of the PCI registers, please see Xframe User Guide.
-
-b. Ensure Transmit Checksum offload is enabled. Use ethtool to set/verify this 
-parameter.
-c. Turn on TSO(using "ethtool -K")
-# ethtool -K <ethX> tso on
-
-Receive performance:
-a. By default, the driver respects BIOS settings for PCI bus parameters. 
-However, you may want to set PCI latency timer to 248.
-#setpci -d 17d5:* LATENCY_TIMER=f8
-For detailed description of the PCI registers, please see Xframe User Guide.
-b. Use 2-buffer mode. This results in large performance boost on
-certain platforms(eg. SGI Altix, IBM xSeries).
-c. Ensure Receive Checksum offload is enabled. Use "ethtool -K ethX" command to 
-set/verify this option.
-d. Enable NAPI feature(in kernel configuration Device Drivers ---> Network 
-device support --->  Ethernet (10000 Mbit) ---> S2IO 10Gbe Xframe NIC) to 
-bring down CPU utilization.
-
-** For AMD opteron platforms with 8131 chipset, MMRBC=1 and MOST=1 are 
-recommended as safe parameters.
-For more information, please review the AMD8131 errata at
-http://vip.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/
-26310_AMD-8131_HyperTransport_PCI-X_Tunnel_Revision_Guide_rev_3_18.pdf
-
-6. Support
-For further support please contact either your 10GbE Xframe NIC vendor (IBM, 
-HP, SGI etc.)
diff --git a/Documentation/networking/smc9.txt b/Documentation/networking/smc9.txt
deleted file mode 100644
index d1e15074e43d..000000000000
--- a/Documentation/networking/smc9.txt
+++ /dev/null
@@ -1,42 +0,0 @@
-
-SMC 9xxxx Driver 
-Revision 0.12 
-3/5/96
-Copyright 1996  Erik Stahlman 
-Released under terms of the GNU General Public License. 
-
-This file contains the instructions and caveats for my SMC9xxx driver.  You
-should not be using the driver without reading this file.  
-
-Things to note about installation:
-
-  1. The driver should work on all kernels from 1.2.13 until 1.3.71.
-	(A kernel patch is supplied for 1.3.71 )
-
-  2. If you include this into the kernel, you might need to change some
-	options, such as for forcing IRQ.   
-
- 
-  3.  To compile as a module, run 'make' .   
-	Make will give you the appropriate options for various kernel support.
- 
-  4.  Loading the driver as a module :
-
-	use:   insmod smc9194.o 
-	optional parameters:
-		io=xxxx    : your base address
-		irq=xx	   : your irq 
-		ifport=x   :	0 for whatever is default
-				1 for twisted pair
-				2 for AUI  ( or BNC on some cards )
-
-How to obtain the latest version? 
-	
-FTP:  
-	ftp://fenris.campus.vt.edu/smc9/smc9-12.tar.gz
-	ftp://sfbox.vt.edu/filebox/F/fenris/smc9/smc9-12.tar.gz 
-   
-
-Contacting me:
-    erik@mail.vt.edu
- 
diff --git a/Documentation/networking/spider_net.txt b/Documentation/networking/spider_net.txt
deleted file mode 100644
index b0b75f8463b3..000000000000
--- a/Documentation/networking/spider_net.txt
+++ /dev/null
@@ -1,204 +0,0 @@
-
-            The Spidernet Device Driver
-            ===========================
-
-Written by Linas Vepstas <linas@austin.ibm.com>
-
-Version of 7 June 2007
-
-Abstract
-========
-This document sketches the structure of portions of the spidernet
-device driver in the Linux kernel tree. The spidernet is a gigabit
-ethernet device built into the Toshiba southbridge commonly used
-in the SONY Playstation 3 and the IBM QS20 Cell blade.
-
-The Structure of the RX Ring.
-=============================
-The receive (RX) ring is a circular linked list of RX descriptors,
-together with three pointers into the ring that are used to manage its
-contents.
-
-The elements of the ring are called "descriptors" or "descrs"; they
-describe the received data. This includes a pointer to a buffer
-containing the received data, the buffer size, and various status bits.
-
-There are three primary states that a descriptor can be in: "empty",
-"full" and "not-in-use".  An "empty" or "ready" descriptor is ready
-to receive data from the hardware. A "full" descriptor has data in it,
-and is waiting to be emptied and processed by the OS. A "not-in-use"
-descriptor is neither empty or full; it is simply not ready. It may
-not even have a data buffer in it, or is otherwise unusable.
-
-During normal operation, on device startup, the OS (specifically, the
-spidernet device driver) allocates a set of RX descriptors and RX
-buffers. These are all marked "empty", ready to receive data. This
-ring is handed off to the hardware, which sequentially fills in the
-buffers, and marks them "full". The OS follows up, taking the full
-buffers, processing them, and re-marking them empty.
-
-This filling and emptying is managed by three pointers, the "head"
-and "tail" pointers, managed by the OS, and a hardware current
-descriptor pointer (GDACTDPA). The GDACTDPA points at the descr
-currently being filled. When this descr is filled, the hardware
-marks it full, and advances the GDACTDPA by one.  Thus, when there is
-flowing RX traffic, every descr behind it should be marked "full",
-and everything in front of it should be "empty".  If the hardware
-discovers that the current descr is not empty, it will signal an
-interrupt, and halt processing.
-
-The tail pointer tails or trails the hardware pointer. When the
-hardware is ahead, the tail pointer will be pointing at a "full"
-descr. The OS will process this descr, and then mark it "not-in-use",
-and advance the tail pointer.  Thus, when there is flowing RX traffic,
-all of the descrs in front of the tail pointer should be "full", and
-all of those behind it should be "not-in-use". When RX traffic is not
-flowing, then the tail pointer can catch up to the hardware pointer.
-The OS will then note that the current tail is "empty", and halt
-processing.
-
-The head pointer (somewhat mis-named) follows after the tail pointer.
-When traffic is flowing, then the head pointer will be pointing at
-a "not-in-use" descr. The OS will perform various housekeeping duties
-on this descr. This includes allocating a new data buffer and
-dma-mapping it so as to make it visible to the hardware. The OS will
-then mark the descr as "empty", ready to receive data. Thus, when there
-is flowing RX traffic, everything in front of the head pointer should
-be "not-in-use", and everything behind it should be "empty". If no
-RX traffic is flowing, then the head pointer can catch up to the tail
-pointer, at which point the OS will notice that the head descr is
-"empty", and it will halt processing.
-
-Thus, in an idle system, the GDACTDPA, tail and head pointers will
-all be pointing at the same descr, which should be "empty". All of the
-other descrs in the ring should be "empty" as well.
-
-The show_rx_chain() routine will print out the locations of the
-GDACTDPA, tail and head pointers. It will also summarize the contents
-of the ring, starting at the tail pointer, and listing the status
-of the descrs that follow.
-
-A typical example of the output, for a nearly idle system, might be
-
-net eth1: Total number of descrs=256
-net eth1: Chain tail located at descr=20
-net eth1: Chain head is at 20
-net eth1: HW curr desc (GDACTDPA) is at 21
-net eth1: Have 1 descrs with stat=x40800101
-net eth1: HW next desc (GDACNEXTDA) is at 22
-net eth1: Last 255 descrs with stat=xa0800000
-
-In the above, the hardware has filled in one descr, number 20. Both
-head and tail are pointing at 20, because it has not yet been emptied.
-Meanwhile, hw is pointing at 21, which is free.
-
-The "Have nnn decrs" refers to the descr starting at the tail: in this
-case, nnn=1 descr, starting at descr 20. The "Last nnn descrs" refers
-to all of the rest of the descrs, from the last status change. The "nnn"
-is a count of how many descrs have exactly the same status.
-
-The status x4... corresponds to "full" and status xa... corresponds
-to "empty". The actual value printed is RXCOMST_A.
-
-In the device driver source code, a different set of names are
-used for these same concepts, so that
-
-"empty" == SPIDER_NET_DESCR_CARDOWNED == 0xa
-"full"  == SPIDER_NET_DESCR_FRAME_END == 0x4
-"not in use" == SPIDER_NET_DESCR_NOT_IN_USE == 0xf
-
-
-The RX RAM full bug/feature
-===========================
-
-As long as the OS can empty out the RX buffers at a rate faster than
-the hardware can fill them, there is no problem. If, for some reason,
-the OS fails to empty the RX ring fast enough, the hardware GDACTDPA
-pointer will catch up to the head, notice the not-empty condition,
-ad stop. However, RX packets may still continue arriving on the wire.
-The spidernet chip can save some limited number of these in local RAM.
-When this local ram fills up, the spider chip will issue an interrupt
-indicating this (GHIINT0STS will show ERRINT, and the GRMFLLINT bit
-will be set in GHIINT1STS).  When the RX ram full condition occurs,
-a certain bug/feature is triggered that has to be specially handled.
-This section describes the special handling for this condition.
-
-When the OS finally has a chance to run, it will empty out the RX ring.
-In particular, it will clear the descriptor on which the hardware had
-stopped. However, once the hardware has decided that a certain
-descriptor is invalid, it will not restart at that descriptor; instead
-it will restart at the next descr. This potentially will lead to a
-deadlock condition, as the tail pointer will be pointing at this descr,
-which, from the OS point of view, is empty; the OS will be waiting for
-this descr to be filled. However, the hardware has skipped this descr,
-and is filling the next descrs. Since the OS doesn't see this, there
-is a potential deadlock, with the OS waiting for one descr to fill,
-while the hardware is waiting for a different set of descrs to become
-empty.
-
-A call to show_rx_chain() at this point indicates the nature of the
-problem. A typical print when the network is hung shows the following:
-
-net eth1: Spider RX RAM full, incoming packets might be discarded!
-net eth1: Total number of descrs=256
-net eth1: Chain tail located at descr=255
-net eth1: Chain head is at 255
-net eth1: HW curr desc (GDACTDPA) is at 0
-net eth1: Have 1 descrs with stat=xa0800000
-net eth1: HW next desc (GDACNEXTDA) is at 1
-net eth1: Have 127 descrs with stat=x40800101
-net eth1: Have 1 descrs with stat=x40800001
-net eth1: Have 126 descrs with stat=x40800101
-net eth1: Last 1 descrs with stat=xa0800000
-
-Both the tail and head pointers are pointing at descr 255, which is
-marked xa... which is "empty". Thus, from the OS point of view, there
-is nothing to be done. In particular, there is the implicit assumption
-that everything in front of the "empty" descr must surely also be empty,
-as explained in the last section. The OS is waiting for descr 255 to
-become non-empty, which, in this case, will never happen.
-
-The HW pointer is at descr 0. This descr is marked 0x4.. or "full".
-Since its already full, the hardware can do nothing more, and thus has
-halted processing. Notice that descrs 0 through 254 are all marked
-"full", while descr 254 and 255 are empty. (The "Last 1 descrs" is
-descr 254, since tail was at 255.) Thus, the system is deadlocked,
-and there can be no forward progress; the OS thinks there's nothing
-to do, and the hardware has nowhere to put incoming data.
-
-This bug/feature is worked around with the spider_net_resync_head_ptr()
-routine. When the driver receives RX interrupts, but an examination
-of the RX chain seems to show it is empty, then it is probable that
-the hardware has skipped a descr or two (sometimes dozens under heavy
-network conditions). The spider_net_resync_head_ptr() subroutine will
-search the ring for the next full descr, and the driver will resume
-operations there.  Since this will leave "holes" in the ring, there
-is also a spider_net_resync_tail_ptr() that will skip over such holes.
-
-As of this writing, the spider_net_resync() strategy seems to work very
-well, even under heavy network loads.
-
-
-The TX ring
-===========
-The TX ring uses a low-watermark interrupt scheme to make sure that
-the TX queue is appropriately serviced for large packet sizes.
-
-For packet sizes greater than about 1KBytes, the kernel can fill
-the TX ring quicker than the device can drain it. Once the ring
-is full, the netdev is stopped. When there is room in the ring,
-the netdev needs to be reawakened, so that more TX packets are placed
-in the ring. The hardware can empty the ring about four times per jiffy,
-so its not appropriate to wait for the poll routine to refill, since
-the poll routine runs only once per jiffy.  The low-watermark mechanism
-marks a descr about 1/4th of the way from the bottom of the queue, so
-that an interrupt is generated when the descr is processed. This
-interrupt wakes up the netdev, which can then refill the queue.
-For large packets, this mechanism generates a relatively small number
-of interrupts, about 1K/sec. For smaller packets, this will drop to zero
-interrupts, as the hardware can empty the queue faster than the kernel
-can fill it.
-
-
- ======= END OF DOCUMENT ========
-
diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt
deleted file mode 100644
index 2bb07078f535..000000000000
--- a/Documentation/networking/stmmac.txt
+++ /dev/null
@@ -1,401 +0,0 @@
-       STMicroelectronics 10/100/1000 Synopsys Ethernet driver
-
-Copyright (C) 2007-2015  STMicroelectronics Ltd
-Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
-
-This is the driver for the MAC 10/100/1000 on-chip Ethernet controllers
-(Synopsys IP blocks).
-
-Currently this network device driver is for all STi embedded MAC/GMAC
-(i.e. 7xxx/5xxx SoCs), SPEAr (arm), Loongson1B (mips) and XLINX XC2V3000
-FF1152AMT0221 D1215994A VIRTEX FPGA board.
-
-DWC Ether MAC 10/100/1000 Universal version 3.70a (and older) and DWC Ether
-MAC 10/100 Universal version 4.0 have been used for developing this driver.
-
-This driver supports both the platform bus and PCI.
-
-Please, for more information also visit: www.stlinux.com
-
-1) Kernel Configuration
-The kernel configuration option is STMMAC_ETH:
- Device Drivers ---> Network device support ---> Ethernet (1000 Mbit) --->
- STMicroelectronics 10/100/1000 Ethernet driver (STMMAC_ETH)
-
-CONFIG_STMMAC_PLATFORM: is to enable the platform driver.
-CONFIG_STMMAC_PCI: is to enable the pci driver.
-
-2) Driver parameters list:
-	debug: message level (0: no output, 16: all);
-	phyaddr: to manually provide the physical address to the PHY device;
-	buf_sz: DMA buffer size;
-	tc: control the HW FIFO threshold;
-	watchdog: transmit timeout (in milliseconds);
-	flow_ctrl: Flow control ability [on/off];
-	pause: Flow Control Pause Time;
-	eee_timer: tx EEE timer;
-	chain_mode: select chain mode instead of ring.
-
-3) Command line options
-Driver parameters can be also passed in command line by using:
-	stmmaceth=watchdog:100,chain_mode=1
-
-4) Driver information and notes
-
-4.1) Transmit process
-The xmit method is invoked when the kernel needs to transmit a packet; it sets
-the descriptors in the ring and informs the DMA engine, that there is a packet
-ready to be transmitted.
-By default, the driver sets the NETIF_F_SG bit in the features field of the
-net_device structure, enabling the scatter-gather feature. This is true on
-chips and configurations where the checksum can be done in hardware.
-Once the controller has finished transmitting the packet, timer will be
-scheduled to release the transmit resources.
-
-4.2) Receive process
-When one or more packets are received, an interrupt happens. The interrupts
-are not queued, so the driver has to scan all the descriptors in the ring during
-the receive process.
-This is based on NAPI, so the interrupt handler signals only if there is work
-to be done, and it exits.
-Then the poll method will be scheduled at some future point.
-The incoming packets are stored, by the DMA, in a list of pre-allocated socket
-buffers in order to avoid the memcpy (zero-copy).
-
-4.3) Interrupt mitigation
-The driver is able to mitigate the number of its DMA interrupts
-using NAPI for the reception on chips older than the 3.50.
-New chips have an HW RX-Watchdog used for this mitigation.
-Mitigation parameters can be tuned by ethtool.
-
-4.4) WOL
-Wake up on Lan feature through Magic and Unicast frames are supported for the
-GMAC core.
-
-4.5) DMA descriptors
-Driver handles both normal and alternate descriptors. The latter has been only
-tested on DWC Ether MAC 10/100/1000 Universal version 3.41a and later.
-
-STMMAC supports DMA descriptor to operate both in dual buffer (RING)
-and linked-list(CHAINED) mode. In RING each descriptor points to two
-data buffer pointers whereas in CHAINED mode they point to only one data
-buffer pointer. RING mode is the default.
-
-In CHAINED mode each descriptor will have pointer to next descriptor in
-the list, hence creating the explicit chaining in the descriptor itself,
-whereas such explicit chaining is not possible in RING mode.
-
-4.5.1) Extended descriptors
-The extended descriptors give us information about the Ethernet payload
-when it is carrying PTP packets or TCP/UDP/ICMP over IP.
-These are not available on GMAC Synopsys chips older than the 3.50.
-At probe time the driver will decide if these can be actually used.
-This support also is mandatory for PTPv2 because the extra descriptors
-are used for saving the hardware timestamps and Extended Status.
-
-4.6) Ethtool support
-Ethtool is supported.
-
-For example, driver statistics (including RMON), internal errors can be taken
-using:
-  # ethtool -S ethX
-command
-
-4.7) Jumbo and Segmentation Offloading
-Jumbo frames are supported and tested for the GMAC.
-The GSO has been also added but it's performed in software.
-LRO is not supported.
-
-4.8) Physical
-The driver is compatible with Physical Abstraction Layer to be connected with
-PHY and GPHY devices.
-
-4.9) Platform information
-Several information can be passed through the platform and device-tree.
-
-struct plat_stmmacenet_data {
-	char *phy_bus_name;
-	int bus_id;
-	int phy_addr;
-	int interface;
-	struct stmmac_mdio_bus_data *mdio_bus_data;
-	struct stmmac_dma_cfg *dma_cfg;
-	int clk_csr;
-	int has_gmac;
-	int enh_desc;
-	int tx_coe;
-	int rx_coe;
-	int bugged_jumbo;
-	int pmt;
-	int force_sf_dma_mode;
-	int force_thresh_dma_mode;
-	int riwt_off;
-	int max_speed;
-	int maxmtu;
-	void (*fix_mac_speed)(void *priv, unsigned int speed);
-	void (*bus_setup)(void __iomem *ioaddr);
-	int (*init)(struct platform_device *pdev, void *priv);
-	void (*exit)(struct platform_device *pdev, void *priv);
-	void *bsp_priv;
-	int has_gmac4;
-	bool tso_en;
-};
-
-Where:
- o phy_bus_name: phy bus name to attach to the stmmac.
- o bus_id: bus identifier.
- o phy_addr: the physical address can be passed from the platform.
-	    If it is set to -1 the driver will automatically
-	    detect it at run-time by probing all the 32 addresses.
- o interface: PHY device's interface.
- o mdio_bus_data: specific platform fields for the MDIO bus.
- o dma_cfg: internal DMA parameters
-   o pbl: the Programmable Burst Length is maximum number of beats to
-       be transferred in one DMA transaction.
-       GMAC also enables the 4xPBL by default. (8xPBL for GMAC 3.50 and newer)
-   o txpbl/rxpbl: GMAC and newer supports independent DMA pbl for tx/rx.
-   o pblx8: Enable 8xPBL (4xPBL for core rev < 3.50). Enabled by default.
-   o fixed_burst/mixed_burst/aal
- o clk_csr: fixed CSR Clock range selection.
- o has_gmac: uses the GMAC core.
- o enh_desc: if sets the MAC will use the enhanced descriptor structure.
- o tx_coe: core is able to perform the tx csum in HW.
- o rx_coe: the supports three check sum offloading engine types:
-	   type_1, type_2 (full csum) and no RX coe.
- o bugged_jumbo: some HWs are not able to perform the csum in HW for
-		over-sized frames due to limited buffer sizes.
-		Setting this flag the csum will be done in SW on
-		JUMBO frames.
- o pmt: core has the embedded power module (optional).
- o force_sf_dma_mode: force DMA to use the Store and Forward mode
-		     instead of the Threshold.
- o force_thresh_dma_mode: force DMA to use the Threshold mode other than
-		     the Store and Forward mode.
- o riwt_off: force to disable the RX watchdog feature and switch to NAPI mode.
- o fix_mac_speed: this callback is used for modifying some syscfg registers
-		 (on ST SoCs) according to the link speed negotiated by the
-		 physical layer .
- o bus_setup: perform HW setup of the bus. For example, on some ST platforms
-	     this field is used to configure the AMBA  bridge to generate more
-	     efficient STBus traffic.
- o init/exit: callbacks used for calling a custom initialization;
-	     this is sometime necessary on some platforms (e.g. ST boxes)
-	     where the HW needs to have set some PIO lines or system cfg
-	     registers.  init/exit callbacks should not use or modify
-	     platform data.
- o bsp_priv: another private pointer.
- o has_gmac4: uses GMAC4 core.
- o tso_en: Enables TSO (TCP Segmentation Offload) feature.
-
-For MDIO bus The we have:
-
- struct stmmac_mdio_bus_data {
-	int (*phy_reset)(void *priv);
-	unsigned int phy_mask;
-	int *irqs;
-	int probed_phy_irq;
- };
-
-Where:
- o phy_reset: hook to reset the phy device attached to the bus.
- o phy_mask: phy mask passed when register the MDIO bus within the driver.
- o irqs: list of IRQs, one per PHY.
- o probed_phy_irq: if irqs is NULL, use this for probed PHY.
-
-For DMA engine we have the following internal fields that should be
-tuned according to the HW capabilities.
-
-struct stmmac_dma_cfg {
-	int pbl;
-	int txpbl;
-	int rxpbl;
-	bool pblx8;
-	int fixed_burst;
-	int mixed_burst;
-	bool aal;
-};
-
-Where:
- o pbl: Programmable Burst Length (tx and rx)
- o txpbl: Transmit Programmable Burst Length. Only for GMAC and newer.
-	 If set, DMA tx will use this value rather than pbl.
- o rxpbl: Receive Programmable Burst Length. Only for GMAC and newer.
-	 If set, DMA rx will use this value rather than pbl.
- o pblx8: Enable 8xPBL (4xPBL for core rev < 3.50). Enabled by default.
- o fixed_burst: program the DMA to use the fixed burst mode
- o mixed_burst: program the DMA to use the mixed burst mode
- o aal: Address-Aligned Beats
-
----
-
-Below an example how the structures above are using on ST platforms.
-
- static struct plat_stmmacenet_data stxYYY_ethernet_platform_data = {
-	.has_gmac = 0,
-	.enh_desc = 0,
-	.fix_mac_speed = stxYYY_ethernet_fix_mac_speed,
-				|
-				|-> to write an internal syscfg
-				|   on this platform when the
-				|   link speed changes from 10 to
-				|   100 and viceversa
-	.init = &stmmac_claim_resource,
-				|
-				|-> On ST SoC this calls own "PAD"
-				|   manager framework to claim
-				|   all the resources necessary
-				|   (GPIO ...). The .custom_cfg field
-				|   is used to pass a custom config.
-};
-
-Below the usage of the stmmac_mdio_bus_data: on this SoC, in fact,
-there are two MAC cores: one MAC is for MDIO Bus/PHY emulation
-with fixed_link support.
-
-static struct stmmac_mdio_bus_data stmmac1_mdio_bus = {
-	.phy_reset = phy_reset;
-		|
-		|-> function to provide the phy_reset on this board
-	.phy_mask = 0,
-};
-
-static struct fixed_phy_status stmmac0_fixed_phy_status = {
-	.link = 1,
-	.speed = 100,
-	.duplex = 1,
-};
-
-During the board's device_init we can configure the first
-MAC for fixed_link by calling:
-  fixed_phy_add(PHY_POLL, 1, &stmmac0_fixed_phy_status, -1);
-and the second one, with a real PHY device attached to the bus,
-by using the stmmac_mdio_bus_data structure (to provide the id, the
-reset procedure etc).
-
-Note that, starting from new chips, where it is available the HW capability
-register, many configurations are discovered at run-time for example to
-understand if EEE, HW csum, PTP, enhanced descriptor etc are actually
-available. As strategy adopted in this driver, the information from the HW
-capability register can replace what has been passed from the platform.
-
-4.10) Device-tree support.
-
-Please see the following document:
-	Documentation/devicetree/bindings/net/stmmac.txt
-
-4.11) This is a summary of the content of some relevant files:
- o stmmac_main.c: implements the main network device driver;
- o stmmac_mdio.c: provides MDIO functions;
- o stmmac_pci: this is the PCI driver;
- o stmmac_platform.c: this the platform driver (OF supported);
- o stmmac_ethtool.c: implements the ethtool support;
- o stmmac.h: private driver structure;
- o common.h: common definitions and VFTs;
- o mmc_core.c/mmc.h: Management MAC Counters;
- o stmmac_hwtstamp.c: HW timestamp support for PTP;
- o stmmac_ptp.c: PTP 1588 clock;
- o stmmac_pcs.h: Physical Coding Sublayer common implementation;
- o dwmac-<XXX>.c: these are for the platform glue-logic file; e.g. dwmac-sti.c
-   for STMicroelectronics SoCs.
-
-- GMAC 3.x
- o descs.h: descriptor structure definitions;
- o dwmac1000_core.c: dwmac GiGa core functions;
- o dwmac1000_dma.c: dma functions for the GMAC chip;
- o dwmac1000.h: specific header file for the dwmac GiGa;
- o dwmac100_core: dwmac 100 core code;
- o dwmac100_dma.c: dma functions for the dwmac 100 chip;
- o dwmac1000.h: specific header file for the MAC;
- o dwmac_lib.c: generic DMA functions;
- o enh_desc.c: functions for handling enhanced descriptors;
- o norm_desc.c: functions for handling normal descriptors;
- o chain_mode.c/ring_mode.c:: functions to manage RING/CHAINED modes;
-
-- GMAC4.x generation
- o dwmac4_core.c: dwmac GMAC4.x core functions;
- o dwmac4_desc.c: functions for handling GMAC4.x descriptors;
- o dwmac4_descs.h: descriptor definitions;
- o dwmac4_dma.c: dma functions for the GMAC4.x chip;
- o dwmac4_dma.h: dma definitions for the GMAC4.x chip;
- o dwmac4.h: core definitions for the GMAC4.x chip;
- o dwmac4_lib.c: generic GMAC4.x functions;
-
-4.12) TSO support (GMAC4.x)
-
-TSO (Tcp Segmentation Offload) feature is supported by GMAC 4.x chip family.
-When a packet is sent through TCP protocol, the TCP stack ensures that
-the SKB provided to the low level driver (stmmac in our case) matches with
-the maximum frame len (IP header + TCP header + payload <= 1500 bytes (for
-MTU set to 1500)). It means that if an application using TCP want to send a
-packet which will have a length (after adding headers) > 1514 the packet
-will be split in several TCP packets: The data payload is split and headers
-(TCP/IP ..) are added. It is done by software.
-
-When TSO is enabled, the TCP stack doesn't care about the maximum frame
-length and provide SKB packet to stmmac as it is. The GMAC IP will have to
-perform the segmentation by it self to match with maximum frame length.
-
-This feature can be enabled in device tree through "snps,tso" entry.
-
-5) Debug Information
-
-The driver exports many information i.e. internal statistics,
-debug information, MAC and DMA registers etc.
-
-These can be read in several ways depending on the
-type of the information actually needed.
-
-For example a user can be use the ethtool support
-to get statistics: e.g. using: ethtool -S ethX
-(that shows the Management counters (MMC) if supported)
-or sees the MAC/DMA registers: e.g. using: ethtool -d ethX
-
-Compiling the Kernel with CONFIG_DEBUG_FS the driver will export the following
-debugfs entries:
-
-/sys/kernel/debug/stmmaceth/descriptors_status
-  To show the DMA TX/RX descriptor rings
-
-Developer can also use the "debug" module parameter to get further debug
-information (please see: NETIF Msg Level).
-
-6) Energy Efficient Ethernet
-
-Energy Efficient Ethernet(EEE) enables IEEE 802.3 MAC sublayer along
-with a family of Physical layer to operate in the Low power Idle(LPI)
-mode. The EEE mode supports the IEEE 802.3 MAC operation at 100Mbps,
-1000Mbps & 10Gbps.
-
-The LPI mode allows power saving by switching off parts of the
-communication device functionality when there is no data to be
-transmitted & received. The system on both the side of the link can
-disable some functionalities & save power during the period of low-link
-utilization. The MAC controls whether the system should enter or exit
-the LPI mode & communicate this to PHY.
-
-As soon as the interface is opened, the driver verifies if the EEE can
-be supported. This is done by looking at both the DMA HW capability
-register and the PHY devices MCD registers.
-To enter in Tx LPI mode the driver needs to have a software timer
-that enable and disable the LPI mode when there is nothing to be
-transmitted.
-
-7) Precision Time Protocol (PTP)
-The driver supports the IEEE 1588-2002, Precision Time Protocol (PTP),
-which enables precise synchronization of clocks in measurement and
-control systems implemented with technologies such as network
-communication.
-
-In addition to the basic timestamp features mentioned in IEEE 1588-2002
-Timestamps, new GMAC cores support the advanced timestamp features.
-IEEE 1588-2008 that can be enabled when configure the Kernel.
-
-8) SGMII/RGMII support
-New GMAC devices provide own way to manage RGMII/SGMII.
-This information is available at run-time by looking at the
-HW capability register. This means that the stmmac can manage
-auto-negotiation and link status w/o using the PHYLIB stuff.
-In fact, the HW provides a subset of extended registers to
-restart the ANE, verify Full/Half duplex mode and Speed.
-Thanks to these registers, it is possible to look at the
-Auto-negotiated Link Parter Ability.
diff --git a/Documentation/networking/ti-cpsw.txt b/Documentation/networking/ti-cpsw.txt
deleted file mode 100644
index d4d4c0751a09..000000000000
--- a/Documentation/networking/ti-cpsw.txt
+++ /dev/null
@@ -1,541 +0,0 @@
-* Texas Instruments CPSW ethernet driver
-
-Multiqueue & CBS & MQPRIO
-=====================================================================
-=====================================================================
-
-The cpsw has 3 CBS shapers for each external ports. This document
-describes MQPRIO and CBS Qdisc offload configuration for cpsw driver
-based on examples. It potentially can be used in audio video bridging
-(AVB) and time sensitive networking (TSN).
-
-The following examples were tested on AM572x EVM and BBB boards.
-
-Test setup
-==========
-
-Under consideration two examples with AM572x EVM running cpsw driver
-in dual_emac mode.
-
-Several prerequisites:
-- TX queues must be rated starting from txq0 that has highest priority
-- Traffic classes are used starting from 0, that has highest priority
-- CBS shapers should be used with rated queues
-- The bandwidth for CBS shapers has to be set a little bit more then
-  potential incoming rate, thus, rate of all incoming tx queues has
-  to be a little less
-- Real rates can differ, due to discreetness
-- Map skb-priority to txq is not enough, also skb-priority to l2 prio
-  map has to be created with ip or vconfig tool
-- Any l2/socket prio (0 - 7) for classes can be used, but for
-  simplicity default values are used: 3 and 2
-- only 2 classes tested: A and B, but checked and can work with more,
-  maximum allowed 4, but only for 3 rate can be set.
-
-Test setup for examples
-=======================
-                                    +-------------------------------+
-                                    |--+                            |
-                                    |  |      Workstation0          |
-                                    |E |  MAC 18:03:73:66:87:42     |
-+-----------------------------+  +--|t |                            |
-|                    | 1  | E |  |  |h |./tsn_listener -d \         |
-|  Target board:     | 0  | t |--+  |0 | 18:03:73:66:87:42 -i eth0 \|
-|  AM572x EVM        | 0  | h |     |  | -s 1500                    |
-|                    | 0  | 0 |     |--+                            |
-|  Only 2 classes:   |Mb  +---|     +-------------------------------+
-|  class A, class B  |        |
-|                    |    +---|     +-------------------------------+
-|                    | 1  | E |     |--+                            |
-|                    | 0  | t |     |  |      Workstation1          |
-|                    | 0  | h |--+  |E |  MAC 20:cf:30:85:7d:fd     |
-|                    |Mb  | 1 |  +--|t |                            |
-+-----------------------------+     |h |./tsn_listener -d \         |
-                                    |0 | 20:cf:30:85:7d:fd -i eth0 \|
-                                    |  | -s 1500                    |
-                                    |--+                            |
-                                    +-------------------------------+
-
-*********************************************************************
-*********************************************************************
-*********************************************************************
-Example 1: One port tx AVB configuration scheme for target board
-----------------------------------------------------------------------
-(prints and scheme for AM572x evm, applicable for single port boards)
-
-tc - traffic class
-txq - transmit queue
-p - priority
-f - fifo (cpsw fifo)
-S - shaper configured
-
-+------------------------------------------------------------------+ u
-| +---------------+  +---------------+  +------+ +------+          | s
-| |               |  |               |  |      | |      |          | e
-| | App 1         |  | App 2         |  | Apps | | Apps |          | r
-| | Class A       |  | Class B       |  | Rest | | Rest |          |
-| | Eth0          |  | Eth0          |  | Eth0 | | Eth1 |          | s
-| | VLAN100       |  | VLAN100       |  |   |  | |   |  |          | p
-| | 40 Mb/s       |  | 20 Mb/s       |  |   |  | |   |  |          | a
-| | SO_PRIORITY=3 |  | SO_PRIORITY=2 |  |   |  | |   |  |          | c
-| |   |           |  |   |           |  |   |  | |   |  |          | e
-| +---|-----------+  +---|-----------+  +---|--+ +---|--+          |
-+-----|------------------|------------------|--------|-------------+
-    +-+     +------------+                  |        |
-    |       |             +-----------------+     +--+
-    |       |             |                       |
-+---|-------|-------------|-----------------------|----------------+
-| +----+ +----+ +----+ +----+                   +----+             |
-| | p3 | | p2 | | p1 | | p0 |                   | p0 |             | k
-| \    / \    / \    / \    /                   \    /             | e
-|  \  /   \  /   \  /   \  /                     \  /              | r
-|   \/     \/     \/     \/                       \/               | n
-|    |     |             |                        |                | e
-|    |     |       +-----+                        |                | l
-|    |     |       |                              |                |
-| +----+ +----+ +----+                          +----+             | s
-| |tc0 | |tc1 | |tc2 |                          |tc0 |             | p
-| \    / \    / \    /                          \    /             | a
-|  \  /   \  /   \  /                            \  /              | c
-|   \/     \/     \/                              \/               | e
-|   |      |       +-----+                        |                |
-|   |      |       |     |                        |                |
-|   |      |       |     |                        |                |
-|   |      |       |     |                        |                |
-| +----+ +----+ +----+ +----+                   +----+             |
-| |txq0| |txq1| |txq2| |txq3|                   |txq4|             |
-| \    / \    / \    / \    /                   \    /             |
-|  \  /   \  /   \  /   \  /                     \  /              |
-|   \/     \/     \/     \/                       \/               |
-| +-|------|------|------|--+                  +--|--------------+ |
-| | |      |      |      |  | Eth0.100         |  |     Eth1     | |
-+---|------|------|------|------------------------|----------------+
-    |      |      |      |                        |
-    p      p      p      p                        |
-    3      2      0-1, 4-7  <- L2 priority        |
-    |      |      |      |                        |
-    |      |      |      |                        |
-+---|------|------|------|------------------------|----------------+
-|   |      |      |      |             |----------+                |
-| +----+ +----+ +----+ +----+       +----+                         |
-| |dma7| |dma6| |dma5| |dma4|       |dma3|                         |
-| \    / \    / \    / \    /       \    /                         | c
-|  \S /   \S /   \  /   \  /         \  /                          | p
-|   \/     \/     \/     \/           \/                           | s
-|   |      |      | +-----            |                            | w
-|   |      |      | |                 |                            |
-|   |      |      | |                 |                            | d
-| +----+ +----+ +----+p            p+----+                         | r
-| |    | |    | |    |o            o|    |                         | i
-| | f3 | | f2 | | f0 |r            r| f0 |                         | v
-| |tc0 | |tc1 | |tc2 |t            t|tc0 |                         | e
-| \CBS / \CBS / \CBS /1            2\CBS /                         | r
-|  \S /   \S /   \  /                \  /                          |
-|   \/     \/     \/                  \/                           |
-+------------------------------------------------------------------+
-========================================Eth==========================>
-
-1)
-// Add 4 tx queues, for interface Eth0, and 1 tx queue for Eth1
-$ ethtool -L eth0 rx 1 tx 5
-rx unmodified, ignoring
-
-2)
-// Check if num of queues is set correctly:
-$ ethtool -l eth0
-Channel parameters for eth0:
-Pre-set maximums:
-RX:             8
-TX:             8
-Other:          0
-Combined:       0
-Current hardware settings:
-RX:             1
-TX:             5
-Other:          0
-Combined:       0
-
-3)
-// TX queues must be rated starting from 0, so set bws for tx0 and tx1
-// Set rates 40 and 20 Mb/s appropriately.
-// Pay attention, real speed can differ a bit due to discreetness.
-// Leave last 2 tx queues not rated.
-$ echo 40 > /sys/class/net/eth0/queues/tx-0/tx_maxrate
-$ echo 20 > /sys/class/net/eth0/queues/tx-1/tx_maxrate
-
-4)
-// Check maximum rate of tx (cpdma) queues:
-$ cat /sys/class/net/eth0/queues/tx-*/tx_maxrate
-40
-20
-0
-0
-0
-
-5)
-// Map skb->priority to traffic class:
-// 3pri -> tc0, 2pri -> tc1, (0,1,4-7)pri -> tc2
-// Map traffic class to transmit queue:
-// tc0 -> txq0, tc1 -> txq1, tc2 -> (txq2, txq3)
-$ tc qdisc replace dev eth0 handle 100: parent root mqprio num_tc 3 \
-map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 1
-
-5a)
-// As two interface sharing same set of tx queues, assign all traffic
-// coming to interface Eth1 to separate queue in order to not mix it
-// with traffic from interface Eth0, so use separate txq to send
-// packets to Eth1, so all prio -> tc0 and tc0 -> txq4
-// Here hw 0, so here still default configuration for eth1 in hw
-$ tc qdisc replace dev eth1 handle 100: parent root mqprio num_tc 1 \
-map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@4 hw 0
-
-6)
-// Check classes settings
-$ tc -g class show dev eth0
-+---(100:ffe2) mqprio
-|    +---(100:3) mqprio
-|    +---(100:4) mqprio
-|
-+---(100:ffe1) mqprio
-|    +---(100:2) mqprio
-|
-+---(100:ffe0) mqprio
-     +---(100:1) mqprio
-
-$ tc -g class show dev eth1
-+---(100:ffe0) mqprio
-     +---(100:5) mqprio
-
-7)
-// Set rate for class A - 41 Mbit (tc0, txq0) using CBS Qdisc
-// Set it +1 Mb for reserve (important!)
-// here only idle slope is important, others arg are ignored
-// Pay attention, real speed can differ a bit due to discreetness
-$ tc qdisc add dev eth0 parent 100:1 cbs locredit -1438 \
-hicredit 62 sendslope -959000 idleslope 41000 offload 1
-net eth0: set FIFO3 bw = 50
-
-8)
-// Set rate for class B - 21 Mbit (tc1, txq1) using CBS Qdisc:
-// Set it +1 Mb for reserve (important!)
-$ tc qdisc add dev eth0 parent 100:2 cbs locredit -1468 \
-hicredit 65 sendslope -979000 idleslope 21000 offload 1
-net eth0: set FIFO2 bw = 30
-
-9)
-// Create vlan 100 to map sk->priority to vlan qos
-$ ip link add link eth0 name eth0.100 type vlan id 100
-8021q: 802.1Q VLAN Support v1.8
-8021q: adding VLAN 0 to HW filter on device eth0
-8021q: adding VLAN 0 to HW filter on device eth1
-net eth0: Adding vlanid 100 to vlan filter
-
-10)
-// Map skb->priority to L2 prio, 1 to 1
-$ ip link set eth0.100 type vlan \
-egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
-
-11)
-// Check egress map for vlan 100
-$ cat /proc/net/vlan/eth0.100
-[...]
-INGRESS priority mappings: 0:0  1:0  2:0  3:0  4:0  5:0  6:0 7:0
-EGRESS priority mappings: 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
-
-12)
-// Run your appropriate tools with socket option "SO_PRIORITY"
-// to 3 for class A and/or to 2 for class B
-// (I took at https://www.spinics.net/lists/netdev/msg460869.html)
-./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p3 -s 1500&
-./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p2 -s 1500&
-
-13)
-// run your listener on workstation (should be in same vlan)
-// (I took at https://www.spinics.net/lists/netdev/msg460869.html)
-./tsn_listener -d 18:03:73:66:87:42 -i enp5s0 -s 1500
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39000 kbps
-
-14)
-// Restore default configuration if needed
-$ ip link del eth0.100
-$ tc qdisc del dev eth1 root
-$ tc qdisc del dev eth0 root
-net eth0: Prev FIFO2 is shaped
-net eth0: set FIFO3 bw = 0
-net eth0: set FIFO2 bw = 0
-$ ethtool -L eth0 rx 1 tx 1
-
-*********************************************************************
-*********************************************************************
-*********************************************************************
-Example 2: Two port tx AVB configuration scheme for target board
-----------------------------------------------------------------------
-(prints and scheme for AM572x evm, for dual emac boards only)
-
-+------------------------------------------------------------------+ u
-| +----------+  +----------+  +------+  +----------+  +----------+ | s
-| |          |  |          |  |      |  |          |  |          | | e
-| | App 1    |  | App 2    |  | Apps |  | App 3    |  | App 4    | | r
-| | Class A  |  | Class B  |  | Rest |  | Class B  |  | Class A  | |
-| | Eth0     |  | Eth0     |  |   |  |  | Eth1     |  | Eth1     | | s
-| | VLAN100  |  | VLAN100  |  |   |  |  | VLAN100  |  | VLAN100  | | p
-| | 40 Mb/s  |  | 20 Mb/s  |  |   |  |  | 10 Mb/s  |  | 30 Mb/s  | | a
-| | SO_PRI=3 |  | SO_PRI=2 |  |   |  |  | SO_PRI=3 |  | SO_PRI=2 | | c
-| |   |      |  |   |      |  |   |  |  |   |      |  |   |      | | e
-| +---|------+  +---|------+  +---|--+  +---|------+  +---|------+ |
-+-----|-------------|-------------|---------|-------------|--------+
-    +-+     +-------+             |         +----------+  +----+
-    |       |             +-------+------+             |       |
-    |       |             |              |             |       |
-+---|-------|-------------|--------------|-------------|-------|---+
-| +----+ +----+ +----+ +----+          +----+ +----+ +----+ +----+ |
-| | p3 | | p2 | | p1 | | p0 |          | p0 | | p1 | | p2 | | p3 | | k
-| \    / \    / \    / \    /          \    / \    / \    / \    / | e
-|  \  /   \  /   \  /   \  /            \  /   \  /   \  /   \  /  | r
-|   \/     \/     \/     \/              \/     \/     \/     \/   | n
-|   |      |             |                |             |      |   | e
-|   |      |        +----+                +----+        |      |   | l
-|   |      |        |                          |        |      |   |
-| +----+ +----+ +----+                        +----+ +----+ +----+ | s
-| |tc0 | |tc1 | |tc2 |                        |tc2 | |tc1 | |tc0 | | p
-| \    / \    / \    /                        \    / \    / \    / | a
-|  \  /   \  /   \  /                          \  /   \  /   \  /  | c
-|   \/     \/     \/                            \/     \/     \/   | e
-|   |      |       +-----+                +-----+      |       |   |
-|   |      |       |     |                |     |      |       |   |
-|   |      |       |     |                |     |      |       |   |
-|   |      |       |     |    E      E    |     |      |       |   |
-| +----+ +----+ +----+ +----+ t      t +----+ +----+ +----+ +----+ |
-| |txq0| |txq1| |txq4| |txq5| h      h |txq6| |txq7| |txq3| |txq2| |
-| \    / \    / \    / \    / 0      1 \    / \    / \    / \    / |
-|  \  /   \  /   \  /   \  /  .      .  \  /   \  /   \  /   \  /  |
-|   \/     \/     \/     \/   1      1   \/     \/     \/     \/   |
-| +-|------|------|------|--+ 0      0 +-|------|------|------|--+ |
-| | |      |      |      |  | 0      0 | |      |      |      |  | |
-+---|------|------|------|---------------|------|------|------|----+
-    |      |      |      |               |      |      |      |
-    p      p      p      p               p      p      p      p
-    3      2      0-1, 4-7   <-L2 pri->  0-1, 4-7      2      3
-    |      |      |      |               |      |      |      |
-    |      |      |      |               |      |      |      |
-+---|------|------|------|---------------|------|------|------|----+
-|   |      |      |      |               |      |      |      |    |
-| +----+ +----+ +----+ +----+          +----+ +----+ +----+ +----+ |
-| |dma7| |dma6| |dma3| |dma2|          |dma1| |dma0| |dma4| |dma5| |
-| \    / \    / \    / \    /          \    / \    / \    / \    / | c
-|  \S /   \S /   \  /   \  /            \  /   \  /   \S /   \S /  | p
-|   \/     \/     \/     \/              \/     \/     \/     \/   | s
-|   |      |      | +-----                |      |      |      |   | w
-|   |      |      | |                     +----+ |      |      |   |
-|   |      |      | |                          | |      |      |   | d
-| +----+ +----+ +----+p                      p+----+ +----+ +----+ | r
-| |    | |    | |    |o                      o|    | |    | |    | | i
-| | f3 | | f2 | | f0 |r        CPSW          r| f3 | | f2 | | f0 | | v
-| |tc0 | |tc1 | |tc2 |t                      t|tc0 | |tc1 | |tc2 | | e
-| \CBS / \CBS / \CBS /1                      2\CBS / \CBS / \CBS / | r
-|  \S /   \S /   \  /                          \S /   \S /   \  /  |
-|   \/     \/     \/                            \/     \/     \/   |
-+------------------------------------------------------------------+
-========================================Eth==========================>
-
-1)
-// Add 8 tx queues, for interface Eth0, but they are common, so are accessed
-// by two interfaces Eth0 and Eth1.
-$ ethtool -L eth1 rx 1 tx 8
-rx unmodified, ignoring
-
-2)
-// Check if num of queues is set correctly:
-$ ethtool -l eth0
-Channel parameters for eth0:
-Pre-set maximums:
-RX:             8
-TX:             8
-Other:          0
-Combined:       0
-Current hardware settings:
-RX:             1
-TX:             8
-Other:          0
-Combined:       0
-
-3)
-// TX queues must be rated starting from 0, so set bws for tx0 and tx1 for Eth0
-// and for tx2 and tx3 for Eth1. That is, rates 40 and 20 Mb/s appropriately
-// for Eth0 and 30 and 10 Mb/s for Eth1.
-// Real speed can differ a bit due to discreetness
-// Leave last 4 tx queues as not rated
-$ echo 40 > /sys/class/net/eth0/queues/tx-0/tx_maxrate
-$ echo 20 > /sys/class/net/eth0/queues/tx-1/tx_maxrate
-$ echo 30 > /sys/class/net/eth1/queues/tx-2/tx_maxrate
-$ echo 10 > /sys/class/net/eth1/queues/tx-3/tx_maxrate
-
-4)
-// Check maximum rate of tx (cpdma) queues:
-$ cat /sys/class/net/eth0/queues/tx-*/tx_maxrate
-40
-20
-30
-10
-0
-0
-0
-0
-
-5)
-// Map skb->priority to traffic class for Eth0:
-// 3pri -> tc0, 2pri -> tc1, (0,1,4-7)pri -> tc2
-// Map traffic class to transmit queue:
-// tc0 -> txq0, tc1 -> txq1, tc2 -> (txq4, txq5)
-$ tc qdisc replace dev eth0 handle 100: parent root mqprio num_tc 3 \
-map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@4 hw 1
-
-6)
-// Check classes settings
-$ tc -g class show dev eth0
-+---(100:ffe2) mqprio
-|    +---(100:5) mqprio
-|    +---(100:6) mqprio
-|
-+---(100:ffe1) mqprio
-|    +---(100:2) mqprio
-|
-+---(100:ffe0) mqprio
-     +---(100:1) mqprio
-
-7)
-// Set rate for class A - 41 Mbit (tc0, txq0) using CBS Qdisc for Eth0
-// here only idle slope is important, others ignored
-// Real speed can differ a bit due to discreetness
-$ tc qdisc add dev eth0 parent 100:1 cbs locredit -1470 \
-hicredit 62 sendslope -959000 idleslope 41000 offload 1
-net eth0: set FIFO3 bw = 50
-
-8)
-// Set rate for class B - 21 Mbit (tc1, txq1) using CBS Qdisc for Eth0
-$ tc qdisc add dev eth0 parent 100:2 cbs locredit -1470 \
-hicredit 65 sendslope -979000 idleslope 21000 offload 1
-net eth0: set FIFO2 bw = 30
-
-9)
-// Create vlan 100 to map sk->priority to vlan qos for Eth0
-$ ip link add link eth0 name eth0.100 type vlan id 100
-net eth0: Adding vlanid 100 to vlan filter
-
-10)
-// Map skb->priority to L2 prio for Eth0.100, one to one
-$ ip link set eth0.100 type vlan \
-egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
-
-11)
-// Check egress map for vlan 100
-$ cat /proc/net/vlan/eth0.100
-[...]
-INGRESS priority mappings: 0:0  1:0  2:0  3:0  4:0  5:0  6:0 7:0
-EGRESS priority mappings: 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
-
-12)
-// Map skb->priority to traffic class for Eth1:
-// 3pri -> tc0, 2pri -> tc1, (0,1,4-7)pri -> tc2
-// Map traffic class to transmit queue:
-// tc0 -> txq2, tc1 -> txq3, tc2 -> (txq6, txq7)
-$ tc qdisc replace dev eth1 handle 100: parent root mqprio num_tc 3 \
-map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@2 1@3 2@6 hw 1
-
-13)
-// Check classes settings
-$ tc -g class show dev eth1
-+---(100:ffe2) mqprio
-|    +---(100:7) mqprio
-|    +---(100:8) mqprio
-|
-+---(100:ffe1) mqprio
-|    +---(100:4) mqprio
-|
-+---(100:ffe0) mqprio
-     +---(100:3) mqprio
-
-14)
-// Set rate for class A - 31 Mbit (tc0, txq2) using CBS Qdisc for Eth1
-// here only idle slope is important, others ignored, but calculated
-// for interface speed - 100Mb for eth1 port.
-// Set it +1 Mb for reserve (important!)
-$ tc qdisc add dev eth1 parent 100:3 cbs locredit -1035 \
-hicredit 465 sendslope -69000 idleslope 31000 offload 1
-net eth1: set FIFO3 bw = 31
-
-15)
-// Set rate for class B - 11 Mbit (tc1, txq3) using CBS Qdisc for Eth1
-// Set it +1 Mb for reserve (important!)
-$ tc qdisc add dev eth1 parent 100:4 cbs locredit -1335 \
-hicredit 405 sendslope -89000 idleslope 11000 offload 1
-net eth1: set FIFO2 bw = 11
-
-16)
-// Create vlan 100 to map sk->priority to vlan qos for Eth1
-$ ip link add link eth1 name eth1.100 type vlan id 100
-net eth1: Adding vlanid 100 to vlan filter
-
-17)
-// Map skb->priority to L2 prio for Eth1.100, one to one
-$ ip link set eth1.100 type vlan \
-egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
-
-18)
-// Check egress map for vlan 100
-$ cat /proc/net/vlan/eth1.100
-[...]
-INGRESS priority mappings: 0:0  1:0  2:0  3:0  4:0  5:0  6:0 7:0
-EGRESS priority mappings: 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
-
-19)
-// Run appropriate tools with socket option "SO_PRIORITY" to 3
-// for class A and to 2 for class B. For both interfaces
-./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p2 -s 1500&
-./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p3 -s 1500&
-./tsn_talker -d 20:cf:30:85:7d:fd -i eth1.100 -p2 -s 1500&
-./tsn_talker -d 20:cf:30:85:7d:fd -i eth1.100 -p3 -s 1500&
-
-20)
-// run your listener on workstation (should be in same vlan)
-// (I took at https://www.spinics.net/lists/netdev/msg460869.html)
-./tsn_listener -d 18:03:73:66:87:42 -i enp5s0 -s 1500
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39012 kbps
-Receiving data rate: 39000 kbps
-
-21)
-// Restore default configuration if needed
-$ ip link del eth1.100
-$ ip link del eth0.100
-$ tc qdisc del dev eth1 root
-net eth1: Prev FIFO2 is shaped
-net eth1: set FIFO3 bw = 0
-net eth1: set FIFO2 bw = 0
-$ tc qdisc del dev eth0 root
-net eth0: Prev FIFO2 is shaped
-net eth0: set FIFO3 bw = 0
-net eth0: set FIFO2 bw = 0
-$ ethtool -L eth0 rx 1 tx 1
diff --git a/Documentation/networking/tlan.txt b/Documentation/networking/tlan.txt
deleted file mode 100644
index 34550dfcef74..000000000000
--- a/Documentation/networking/tlan.txt
+++ /dev/null
@@ -1,117 +0,0 @@
-(C) 1997-1998 Caldera, Inc.
-(C) 1998 James Banks
-(C) 1999-2001 Torben Mathiasen <tmm@image.dk, torben.mathiasen@compaq.com>
-
-For driver information/updates visit http://www.compaq.com
-
-
-TLAN driver for Linux, version 1.14a
-README
-
-
-I.  Supported Devices.
-
-    Only PCI devices will work with this driver.
-
-    Supported:
-    Vendor ID	Device ID	Name
-    0e11	ae32		Compaq Netelligent 10/100 TX PCI UTP
-    0e11	ae34		Compaq Netelligent 10 T PCI UTP
-    0e11	ae35		Compaq Integrated NetFlex 3/P
-    0e11	ae40		Compaq Netelligent Dual 10/100 TX PCI UTP
-    0e11	ae43		Compaq Netelligent Integrated 10/100 TX UTP
-    0e11	b011		Compaq Netelligent 10/100 TX Embedded UTP
-    0e11	b012		Compaq Netelligent 10 T/2 PCI UTP/Coax
-    0e11	b030		Compaq Netelligent 10/100 TX UTP
-    0e11	f130		Compaq NetFlex 3/P
-    0e11	f150		Compaq NetFlex 3/P
-    108d	0012		Olicom OC-2325	
-    108d	0013		Olicom OC-2183
-    108d	0014		Olicom OC-2326	
-
-
-    Caveats:
-    
-    I am not sure if 100BaseTX daughterboards (for those cards which
-    support such things) will work.  I haven't had any solid evidence
-    either way.
-
-    However, if a card supports 100BaseTx without requiring an add
-    on daughterboard, it should work with 100BaseTx.
-
-    The "Netelligent 10 T/2 PCI UTP/Coax" (b012) device is untested,
-    but I do not expect any problems.
-    
-
-II.   Driver Options
-	1. You can append debug=x to the end of the insmod line to get
-           debug messages, where x is a bit field where the bits mean
-	   the following:
-	   
-	   0x01		Turn on general debugging messages.
-	   0x02		Turn on receive debugging messages.
-	   0x04		Turn on transmit debugging messages.
-	   0x08		Turn on list debugging messages.
-
-	2. You can append aui=1 to the end of the insmod line to cause
-           the adapter to use the AUI interface instead of the 10 Base T
-           interface.  This is also what to do if you want to use the BNC
-	   connector on a TLAN based device.  (Setting this option on a
-	   device that does not have an AUI/BNC connector will probably
-	   cause it to not function correctly.)
-
-	3. You can set duplex=1 to force half duplex, and duplex=2 to
-	   force full duplex.
-
-	4. You can set speed=10 to force 10Mbs operation, and speed=100
-	   to force 100Mbs operation. (I'm not sure what will happen
-	   if a card which only supports 10Mbs is forced into 100Mbs
-	   mode.)
-
-	5. You have to use speed=X duplex=Y together now. If you just
-	   do "insmod tlan.o speed=100" the driver will do Auto-Neg.
-	   To force a 10Mbps Half-Duplex link do "insmod tlan.o speed=10 
-	   duplex=1".
-
-	6. If the driver is built into the kernel, you can use the 3rd
-	   and 4th parameters to set aui and debug respectively.  For
-	   example:
-
-	   ether=0,0,0x1,0x7,eth0
-
-	   This sets aui to 0x1 and debug to 0x7, assuming eth0 is a
-	   supported TLAN device.
-
-	   The bits in the third byte are assigned as follows:
-
-		0x01 = aui
-		0x02 = use half duplex
-		0x04 = use full duplex
-		0x08 = use 10BaseT
-		0x10 = use 100BaseTx
-
-	   You also need to set both speed and duplex settings when forcing
-	   speeds with kernel-parameters. 
-	   ether=0,0,0x12,0,eth0 will force link to 100Mbps Half-Duplex.
-
-	7. If you have more than one tlan adapter in your system, you can
-	   use the above options on a per adapter basis. To force a 100Mbit/HD
-	   link with your eth1 adapter use:
-	   
-	   insmod tlan speed=0,100 duplex=0,1
-
-	   Now eth0 will use auto-neg and eth1 will be forced to 100Mbit/HD.
-	   Note that the tlan driver supports a maximum of 8 adapters.
-
-
-III.  Things to try if you have problems.
-	1. Make sure your card's PCI id is among those listed in
-	   section I, above.
-	2. Make sure routing is correct.
-	3. Try forcing different speed/duplex settings
-
-
-There is also a tlan mailing list which you can join by sending "subscribe tlan"
-in the body of an email to majordomo@vuser.vu.union.edu.
-There is also a tlan website at http://www.compaq.com
-
diff --git a/Documentation/networking/vortex.txt b/Documentation/networking/vortex.txt
deleted file mode 100644
index ad3dead052a4..000000000000
--- a/Documentation/networking/vortex.txt
+++ /dev/null
@@ -1,448 +0,0 @@
-Documentation/networking/vortex.txt
-Andrew Morton
-30 April 2000
-
-
-This document describes the usage and errata of the 3Com "Vortex" device
-driver for Linux, 3c59x.c.
-
-The driver was written by Donald Becker <becker@scyld.com>
-
-Don is no longer the prime maintainer of this version of the driver. 
-Please report problems to one or more of:
-
-  Andrew Morton
-  Netdev mailing list <netdev@vger.kernel.org>
-  Linux kernel mailing list <linux-kernel@vger.kernel.org>
-
-Please note the 'Reporting and Diagnosing Problems' section at the end
-of this file.
-
-
-Since kernel 2.3.99-pre6, this driver incorporates the support for the
-3c575-series Cardbus cards which used to be handled by 3c575_cb.c.
-
-This driver supports the following hardware:
-
-	3c590 Vortex 10Mbps
-	3c592 EISA 10Mbps Demon/Vortex
-	3c597 EISA Fast Demon/Vortex
-	3c595 Vortex 100baseTx
-	3c595 Vortex 100baseT4
-	3c595 Vortex 100base-MII
-	3c900 Boomerang 10baseT
-	3c900 Boomerang 10Mbps Combo
-	3c900 Cyclone 10Mbps TPO
-	3c900 Cyclone 10Mbps Combo
-	3c900 Cyclone 10Mbps TPC
-	3c900B-FL Cyclone 10base-FL
-	3c905 Boomerang 100baseTx
-	3c905 Boomerang 100baseT4
-	3c905B Cyclone 100baseTx
-	3c905B Cyclone 10/100/BNC
-	3c905B-FX Cyclone 100baseFx
-	3c905C Tornado
-	3c920B-EMB-WNM (ATI Radeon 9100 IGP)
-	3c980 Cyclone
-	3c980C Python-T
-	3cSOHO100-TX Hurricane
-	3c555 Laptop Hurricane
-	3c556 Laptop Tornado
-	3c556B Laptop Hurricane
-	3c575 [Megahertz] 10/100 LAN  CardBus
-	3c575 Boomerang CardBus
-	3CCFE575BT Cyclone CardBus
-	3CCFE575CT Tornado CardBus
-	3CCFE656 Cyclone CardBus
-	3CCFEM656B Cyclone+Winmodem CardBus
-	3CXFEM656C Tornado+Winmodem CardBus
-	3c450 HomePNA Tornado
-	3c920 Tornado
-	3c982 Hydra Dual Port A
-	3c982 Hydra Dual Port B
-	3c905B-T4
-	3c920B-EMB-WNM Tornado
-
-Module parameters
-=================
-
-There are several parameters which may be provided to the driver when
-its module is loaded.  These are usually placed in /etc/modprobe.d/*.conf
-configuration files.  Example:
-
-options 3c59x debug=3 rx_copybreak=300
-
-If you are using the PCMCIA tools (cardmgr) then the options may be
-placed in /etc/pcmcia/config.opts:
-
-module "3c59x" opts "debug=3 rx_copybreak=300"
-
-
-The supported parameters are:
-
-debug=N
-
-  Where N is a number from 0 to 7.  Anything above 3 produces a lot
-  of output in your system logs.  debug=1 is default.
-
-options=N1,N2,N3,...
-
-  Each number in the list provides an option to the corresponding
-  network card.  So if you have two 3c905's and you wish to provide
-  them with option 0x204 you would use:
-
-    options=0x204,0x204
-
-  The individual options are composed of a number of bitfields which
-  have the following meanings:
-
-  Possible media type settings
-	0	10baseT
-	1	10Mbs AUI
-	2	undefined
-	3	10base2 (BNC)
-	4	100base-TX
-	5	100base-FX
-	6	MII (Media Independent Interface)
-	7	Use default setting from EEPROM
-	8       Autonegotiate
-	9       External MII
-	10      Use default setting from EEPROM
-
-  When generating a value for the 'options' setting, the above media
-  selection values may be OR'ed (or added to) the following:
-
-  0x8000  Set driver debugging level to 7
-  0x4000  Set driver debugging level to 2
-  0x0400  Enable Wake-on-LAN
-  0x0200  Force full duplex mode.
-  0x0010  Bus-master enable bit (Old Vortex cards only)
-
-  For example:
-
-    insmod 3c59x options=0x204
-
-  will force full-duplex 100base-TX, rather than allowing the usual
-  autonegotiation.
-
-global_options=N
-
-  Sets the `options' parameter for all 3c59x NICs in the machine. 
-  Entries in the `options' array above will override any setting of
-  this.
-
-full_duplex=N1,N2,N3...
-
-  Similar to bit 9 of 'options'.  Forces the corresponding card into
-  full-duplex mode.  Please use this in preference to the `options'
-  parameter.
-
-  In fact, please don't use this at all! You're better off getting
-  autonegotiation working properly.
-
-global_full_duplex=N1
-
-  Sets full duplex mode for all 3c59x NICs in the machine.  Entries
-  in the `full_duplex' array above will override any setting of this.
-
-flow_ctrl=N1,N2,N3...
-
-  Use 802.3x MAC-layer flow control.  The 3com cards only support the
-  PAUSE command, which means that they will stop sending packets for a
-  short period if they receive a PAUSE frame from the link partner. 
-
-  The driver only allows flow control on a link which is operating in
-  full duplex mode.
-
-  This feature does not appear to work on the 3c905 - only 3c905B and
-  3c905C have been tested.
-
-  The 3com cards appear to only respond to PAUSE frames which are
-  sent to the reserved destination address of 01:80:c2:00:00:01.  They
-  do not honour PAUSE frames which are sent to the station MAC address.
-
-rx_copybreak=M
-
-  The driver preallocates 32 full-sized (1536 byte) network buffers
-  for receiving.  When a packet arrives, the driver has to decide
-  whether to leave the packet in its full-sized buffer, or to allocate
-  a smaller buffer and copy the packet across into it.
-
-  This is a speed/space tradeoff.
-
-  The value of rx_copybreak is used to decide when to make the copy. 
-  If the packet size is less than rx_copybreak, the packet is copied. 
-  The default value for rx_copybreak is 200 bytes.
-
-max_interrupt_work=N
-
-  The driver's interrupt service routine can handle many receive and
-  transmit packets in a single invocation.  It does this in a loop. 
-  The value of max_interrupt_work governs how many times the interrupt
-  service routine will loop.  The default value is 32 loops.  If this
-  is exceeded the interrupt service routine gives up and generates a
-  warning message "eth0: Too much work in interrupt".
-
-hw_checksums=N1,N2,N3,...
-
-  Recent 3com NICs are able to generate IPv4, TCP and UDP checksums
-  in hardware.  Linux has used the Rx checksumming for a long time. 
-  The "zero copy" patch which is planned for the 2.4 kernel series
-  allows you to make use of the NIC's DMA scatter/gather and transmit
-  checksumming as well.
-
-  The driver is set up so that, when the zerocopy patch is applied,
-  all Tornado and Cyclone devices will use S/G and Tx checksums.
-
-  This module parameter has been provided so you can override this
-  decision.  If you think that Tx checksums are causing a problem, you
-  may disable the feature with `hw_checksums=0'.
-
-  If you think your NIC should be performing Tx checksumming and the
-  driver isn't enabling it, you can force the use of hardware Tx
-  checksumming with `hw_checksums=1'.
-
-  The driver drops a message in the logfiles to indicate whether or
-  not it is using hardware scatter/gather and hardware Tx checksums.
-
-  Scatter/gather and hardware checksums provide considerable
-  performance improvement for the sendfile() system call, but a small
-  decrease in throughput for send().  There is no effect upon receive
-  efficiency.
-
-compaq_ioaddr=N
-compaq_irq=N
-compaq_device_id=N
-
-  "Variables to work-around the Compaq PCI BIOS32 problem"....
-
-watchdog=N
-
-  Sets the time duration (in milliseconds) after which the kernel
-  decides that the transmitter has become stuck and needs to be reset. 
-  This is mainly for debugging purposes, although it may be advantageous
-  to increase this value on LANs which have very high collision rates.
-  The default value is 5000 (5.0 seconds).
-
-enable_wol=N1,N2,N3,...
-
-  Enable Wake-on-LAN support for the relevant interface.  Donald
-  Becker's `ether-wake' application may be used to wake suspended
-  machines.
-
-  Also enables the NIC's power management support.
-
-global_enable_wol=N
-
-  Sets enable_wol mode for all 3c59x NICs in the machine.  Entries in
-  the `enable_wol' array above will override any setting of this.
-
-Media selection
----------------
-
-A number of the older NICs such as the 3c590 and 3c900 series have
-10base2 and AUI interfaces.
-
-Prior to January, 2001 this driver would autoeselect the 10base2 or AUI
-port if it didn't detect activity on the 10baseT port.  It would then
-get stuck on the 10base2 port and a driver reload was necessary to
-switch back to 10baseT.  This behaviour could not be prevented with a
-module option override.
-
-Later (current) versions of the driver _do_ support locking of the
-media type.  So if you load the driver module with
-
-	modprobe 3c59x options=0
-
-it will permanently select the 10baseT port.  Automatic selection of
-other media types does not occur.
-
-
-Transmit error, Tx status register 82
--------------------------------------
-
-This is a common error which is almost always caused by another host on
-the same network being in full-duplex mode, while this host is in
-half-duplex mode.  You need to find that other host and make it run in
-half-duplex mode or fix this host to run in full-duplex mode.
-
-As a last resort, you can force the 3c59x driver into full-duplex mode
-with
-
-	options 3c59x full_duplex=1
-
-but this has to be viewed as a workaround for broken network gear and
-should only really be used for equipment which cannot autonegotiate.
-
-
-Additional resources
---------------------
-
-Details of the device driver implementation are at the top of the source file.
-
-Additional documentation is available at Don Becker's Linux Drivers site:
-
-     http://www.scyld.com/vortex.html
-
-Donald Becker's driver development site:
-
-     http://www.scyld.com/network.html
-
-Donald's vortex-diag program is useful for inspecting the NIC's state:
-
-     http://www.scyld.com/ethercard_diag.html
-
-Donald's mii-diag program may be used for inspecting and manipulating
-the NIC's Media Independent Interface subsystem:
-
-     http://www.scyld.com/ethercard_diag.html#mii-diag
-
-Donald's wake-on-LAN page:
-
-     http://www.scyld.com/wakeonlan.html
-
-3Com's DOS-based application for setting up the NICs EEPROMs:
-
-	ftp://ftp.3com.com/pub/nic/3c90x/3c90xx2.exe
-
-
-Autonegotiation notes
----------------------
-
-  The driver uses a one-minute heartbeat for adapting to changes in
-  the external LAN environment if link is up and 5 seconds if link is down.
-  This means that when, for example, a machine is unplugged from a hubbed
-  10baseT LAN plugged into a  switched 100baseT LAN, the throughput
-  will be quite dreadful for up to sixty seconds.  Be patient.
-
-  Cisco interoperability note from Walter Wong <wcw+@CMU.EDU>:
-
-  On a side note, adding HAS_NWAY seems to share a problem with the
-  Cisco 6509 switch.  Specifically, you need to change the spanning
-  tree parameter for the port the machine is plugged into to 'portfast'
-  mode.  Otherwise, the negotiation fails.  This has been an issue
-  we've noticed for a while but haven't had the time to track down.
-
-  Cisco switches    (Jeff Busch <jbusch@deja.com>)
-
-    My "standard config" for ports to which PC's/servers connect directly:
-
-        interface FastEthernet0/N
-        description machinename
-        load-interval 30
-        spanning-tree portfast
-
-    If autonegotiation is a problem, you may need to specify "speed
-    100" and "duplex full" as well (or "speed 10" and "duplex half").
-
-    WARNING: DO NOT hook up hubs/switches/bridges to these
-    specially-configured ports! The switch will become very confused.
-
-
-Reporting and diagnosing problems
----------------------------------
-
-Maintainers find that accurate and complete problem reports are
-invaluable in resolving driver problems.  We are frequently not able to
-reproduce problems and must rely on your patience and efforts to get to
-the bottom of the problem.
-
-If you believe you have a driver problem here are some of the
-steps you should take:
-
-- Is it really a driver problem?
-
-   Eliminate some variables: try different cards, different
-   computers, different cables, different ports on the switch/hub,
-   different versions of the kernel or of the driver, etc.
-
-- OK, it's a driver problem.
-
-   You need to generate a report.  Typically this is an email to the
-   maintainer and/or netdev@vger.kernel.org.  The maintainer's
-   email address will be in the driver source or in the MAINTAINERS file.
-
-- The contents of your report will vary a lot depending upon the
-  problem.  If it's a kernel crash then you should refer to the
-  admin-guide/reporting-bugs.rst file.
-
-  But for most problems it is useful to provide the following:
-
-   o Kernel version, driver version
-
-   o A copy of the banner message which the driver generates when
-     it is initialised.  For example:
-
-     eth0: 3Com PCI 3c905C Tornado at 0xa400,  00:50:da:6a:88:f0, IRQ 19
-     8K byte-wide RAM 5:3 Rx:Tx split, autoselect/Autonegotiate interface.
-     MII transceiver found at address 24, status 782d.
-     Enabling bus-master transmits and whole-frame receives.
-
-     NOTE: You must provide the `debug=2' modprobe option to generate
-     a full detection message.  Please do this:
-
-	modprobe 3c59x debug=2
-
-   o If it is a PCI device, the relevant output from 'lspci -vx', eg:
-
-     00:09.0 Ethernet controller: 3Com Corporation 3c905C-TX [Fast Etherlink] (rev 74)
-             Subsystem: 3Com Corporation: Unknown device 9200
-             Flags: bus master, medium devsel, latency 32, IRQ 19
-             I/O ports at a400 [size=128]
-             Memory at db000000 (32-bit, non-prefetchable) [size=128]
-             Expansion ROM at <unassigned> [disabled] [size=128K]
-             Capabilities: [dc] Power Management version 2
-     00: b7 10 00 92 07 00 10 02 74 00 00 02 08 20 00 00
-     10: 01 a4 00 00 00 00 00 db 00 00 00 00 00 00 00 00
-     20: 00 00 00 00 00 00 00 00 00 00 00 00 b7 10 00 10
-     30: 00 00 00 00 dc 00 00 00 00 00 00 00 05 01 0a 0a
-
-   o A description of the environment: 10baseT? 100baseT?
-     full/half duplex? switched or hubbed?
-
-   o Any additional module parameters which you may be providing to the driver.
-
-   o Any kernel logs which are produced.  The more the merrier. 
-     If this is a large file and you are sending your report to a
-     mailing list, mention that you have the logfile, but don't send
-     it.  If you're reporting direct to the maintainer then just send
-     it.
-
-     To ensure that all kernel logs are available, add the
-     following line to /etc/syslog.conf:
-
-         kern.* /var/log/messages
-
-     Then restart syslogd with:
-
-         /etc/rc.d/init.d/syslog restart
-
-     (The above may vary, depending upon which Linux distribution you use).
-
-    o If your problem is reproducible then that's great.  Try the
-      following:
-
-      1) Increase the debug level.  Usually this is done via:
-
-         a) modprobe driver debug=7
-         b) In /etc/modprobe.d/driver.conf:
-            options driver debug=7
-
-      2) Recreate the problem with the higher debug level,
-         send all logs to the maintainer.
-
-      3) Download you card's diagnostic tool from Donald
-         Becker's website <http://www.scyld.com/ethercard_diag.html>.
-         Download mii-diag.c as well.  Build these.
-
-         a) Run 'vortex-diag -aaee' and 'mii-diag -v' when the card is
-            working correctly.  Save the output.
-
-         b) Run the above commands when the card is malfunctioning.  Send
-            both sets of output.
-
-Finally, please be patient and be prepared to do some work.  You may
-end up working on this problem for a week or more as the maintainer
-asks more questions, asks for more tests, asks for patches to be
-applied, etc.  At the end of it all, the problem may even remain
-unresolved.
diff --git a/Documentation/networking/vxge.txt b/Documentation/networking/vxge.txt
deleted file mode 100644
index abfec245f97c..000000000000
--- a/Documentation/networking/vxge.txt
+++ /dev/null
@@ -1,93 +0,0 @@
-Neterion's (Formerly S2io) X3100 Series 10GbE PCIe Server Adapter Linux driver
-==============================================================================
-
-Contents
---------
-
-1) Introduction
-2) Features supported
-3) Configurable driver parameters
-4) Troubleshooting
-
-1) Introduction:
-----------------
-This Linux driver supports all Neterion's X3100 series 10 GbE PCIe I/O
-Virtualized Server adapters.
-The X3100 series supports four modes of operation, configurable via
-firmware -
-	Single function mode
-	Multi function mode
-	SRIOV mode
-	MRIOV mode
-The functions share a 10GbE link and the pci-e bus, but hardly anything else
-inside the ASIC. Features like independent hw reset, statistics, bandwidth/
-priority allocation and guarantees, GRO, TSO, interrupt moderation etc are
-supported independently on each function.
-
-(See below for a complete list of features supported for both IPv4 and IPv6)
-
-2) Features supported:
-----------------------
-
-i)   Single function mode (up to 17 queues)
-
-ii)  Multi function mode (up to 17 functions)
-
-iii) PCI-SIG's I/O Virtualization
-       - Single Root mode: v1.0 (up to 17 functions)
-       - Multi-Root mode: v1.0 (up to 17 functions)
-
-iv)  Jumbo frames
-       X3100 Series supports MTU up to 9600 bytes, modifiable using
-       ip command.
-
-v)   Offloads supported: (Enabled by default)
-       Checksum offload (TCP/UDP/IP) on transmit and receive paths
-       TCP Segmentation Offload (TSO) on transmit path
-       Generic Receive Offload (GRO) on receive path
-
-vi)  MSI-X: (Enabled by default)
-       Resulting in noticeable performance improvement (up to 7% on certain
-       platforms).
-
-vii) NAPI: (Enabled by default)
-       For better Rx interrupt moderation.
-
-viii)RTH (Receive Traffic Hash): (Enabled by default)
-       Receive side steering for better scaling.
-
-ix)  Statistics
-       Comprehensive MAC-level and software statistics displayed using
-       "ethtool -S" option.
-
-x)   Multiple hardware queues: (Enabled by default)
-       Up to 17 hardware based transmit and receive data channels, with
-       multiple steering options (transmit multiqueue enabled by default).
-
-3) Configurable driver parameters:
-----------------------------------
-
-i)  max_config_dev
-       Specifies maximum device functions to be enabled.
-       Valid range: 1-8
-
-ii) max_config_port
-       Specifies number of ports to be enabled.
-       Valid range: 1,2
-       Default: 1
-
-iii)max_config_vpath
-       Specifies maximum VPATH(s) configured for each device function.
-       Valid range: 1-17
-
-iv) vlan_tag_strip
-       Enables/disables vlan tag stripping from all received tagged frames that
-       are not replicated at the internal L2 switch.
-       Valid range: 0,1 (disabled, enabled respectively)
-       Default: 1
-
-v)  addr_learn_en
-       Enable learning the mac address of the guest OS interface in
-       virtualization environment.
-       Valid range: 0,1 (disabled, enabled respectively)
-       Default: 0
diff --git a/MAINTAINERS b/MAINTAINERS
index fb88b6863d10..6db870b9d681 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -140,7 +140,7 @@ Maintainers List (try to look for most precise areas first)
 M:	Steffen Klassert <klassert@kernel.org>
 L:	netdev@vger.kernel.org
 S:	Odd Fixes
-F:	Documentation/networking/vortex.txt
+F:	Documentation/networking/device_drivers/3com/vortex.txt
 F:	drivers/net/ethernet/3com/3c59x.c
 
 3CR990 NETWORK DRIVER
@@ -740,7 +740,7 @@ R:	Saeed Bishara <saeedb@amazon.com>
 R:	Zorik Machulsky <zorik@amazon.com>
 L:	netdev@vger.kernel.org
 S:	Supported
-F:	Documentation/networking/ena.txt
+F:	Documentation/networking/device_drivers/amazon/ena.txt
 F:	drivers/net/ethernet/amazon/
 
 AMD CRYPTOGRAPHIC COPROCESSOR (CCP) DRIVER
@@ -4187,7 +4187,7 @@ F:	net/ax25/sysctl_net_ax25.c
 DAVICOM FAST ETHERNET (DMFE) NETWORK DRIVER
 L:	netdev@vger.kernel.org
 S:	Orphan
-F:	Documentation/networking/dmfe.txt
+F:	Documentation/networking/device_drivers/dec/dmfe.txt
 F:	drivers/net/ethernet/dec/tulip/dmfe.c
 
 DC390/AM53C974 SCSI driver
@@ -6899,7 +6899,7 @@ M:	Haiyang Zhang <haiyangz@microsoft.com>
 M:	Stephen Hemminger <sthemmin@microsoft.com>
 L:	devel@linuxdriverproject.org
 S:	Maintained
-F:	Documentation/networking/netvsc.txt
+F:	Documentation/networking/device_drivers/microsoft/netvsc.txt
 F:	arch/x86/include/asm/mshyperv.h
 F:	arch/x86/include/asm/trace/hyperv.h
 F:	arch/x86/include/asm/hyperv-tlfs.h
@@ -7483,18 +7483,18 @@ Q:	http://patchwork.ozlabs.org/project/intel-wired-lan/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git
 S:	Supported
-F:	Documentation/networking/e100.rst
-F:	Documentation/networking/e1000.rst
-F:	Documentation/networking/e1000e.rst
-F:	Documentation/networking/fm10k.rst
-F:	Documentation/networking/igb.rst
-F:	Documentation/networking/igbvf.rst
-F:	Documentation/networking/ixgb.rst
-F:	Documentation/networking/ixgbe.rst
-F:	Documentation/networking/ixgbevf.rst
-F:	Documentation/networking/i40e.rst
-F:	Documentation/networking/iavf.rst
-F:	Documentation/networking/ice.rst
+F:	Documentation/networking/device_drivers/intel/e100.rst
+F:	Documentation/networking/device_drivers/intel/e1000.rst
+F:	Documentation/networking/device_drivers/intel/e1000e.rst
+F:	Documentation/networking/device_drivers/intel/fm10k.rst
+F:	Documentation/networking/device_drivers/intel/igb.rst
+F:	Documentation/networking/device_drivers/intel/igbvf.rst
+F:	Documentation/networking/device_drivers/intel/ixgb.rst
+F:	Documentation/networking/device_drivers/intel/ixgbe.rst
+F:	Documentation/networking/device_drivers/intel/ixgbevf.rst
+F:	Documentation/networking/device_drivers/intel/i40e.rst
+F:	Documentation/networking/device_drivers/intel/iavf.rst
+F:	Documentation/networking/device_drivers/intel/ice.rst
 F:	drivers/net/ethernet/intel/
 F:	drivers/net/ethernet/intel/*/
 F:	include/linux/avf/virtchnl.h
@@ -7668,8 +7668,8 @@ INTEL PRO/WIRELESS 2100, 2200BG, 2915ABG NETWORK CONNECTION SUPPORT
 M:	Stanislav Yakovlev <stas.yakovlev@gmail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-F:	Documentation/networking/README.ipw2100
-F:	Documentation/networking/README.ipw2200
+F:	Documentation/networking/device_drivers/intel/ipw2100.txt
+F:	Documentation/networking/device_drivers/intel/ipw2200.txt
 F:	drivers/net/wireless/intel/ipw2x00/
 
 INTEL PSTATE DRIVER
@@ -10315,8 +10315,8 @@ NETERION 10GbE DRIVERS (s2io/vxge)
 M:	Jon Mason <jdmason@kudzu.us>
 L:	netdev@vger.kernel.org
 S:	Supported
-F:	Documentation/networking/s2io.txt
-F:	Documentation/networking/vxge.txt
+F:	Documentation/networking/device_drivers/neterion/s2io.txt
+F:	Documentation/networking/device_drivers/neterion/vxge.txt
 F:	drivers/net/ethernet/neterion/
 
 NETFILTER
@@ -12325,7 +12325,7 @@ QLOGIC QLA3XXX NETWORK DRIVER
 M:	Dept-GELinuxNICDev@cavium.com
 L:	netdev@vger.kernel.org
 S:	Supported
-F:	Documentation/networking/LICENSE.qla3xxx
+F:	Documentation/networking/device_drivers/qlogic/LICENSE.qla3xxx
 F:	drivers/net/ethernet/qlogic/qla3xxx.*
 
 QLOGIC QLA4XXX iSCSI DRIVER
@@ -12377,7 +12377,7 @@ L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	drivers/bus/fsl-mc/
 F:	Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt
-F:	Documentation/networking/dpaa2/overview.rst
+F:	Documentation/networking/device_drivers/freescale/dpaa2/overview.rst
 
 QT1010 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
@@ -14109,7 +14109,7 @@ SPIDERNET NETWORK DRIVER for CELL
 M:	Ishizaki Kou <kou.ishizaki@toshiba.co.jp>
 L:	netdev@vger.kernel.org
 S:	Supported
-F:	Documentation/networking/spider_net.txt
+F:	Documentation/networking/device_drivers/toshiba/spider_net.txt
 F:	drivers/net/ethernet/toshiba/spider_net*
 
 SPMI SUBSYSTEM
@@ -15099,7 +15099,7 @@ M:	Samuel Chessman <chessman@tux.org>
 L:	tlan-devel@lists.sourceforge.net (subscribers-only)
 W:	http://sourceforge.net/projects/tlan/
 S:	Maintained
-F:	Documentation/networking/tlan.txt
+F:	Documentation/networking/device_drivers/ti/tlan.txt
 F:	drivers/net/ethernet/ti/tlan.*
 
 TM6000 VIDEO4LINUX DRIVER
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index d03775100f7d..6371958dd170 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -397,10 +397,10 @@ config NET_SB1000
 
 	  At present this driver only compiles as a module, so say M here if
 	  you have this card. The module will be called sb1000. Then read
-	  <file:Documentation/networking/README.sb1000> for information on how
-	  to use this module, as it needs special ppp scripts for establishing
-	  a connection. Further documentation and the necessary scripts can be
-	  found at:
+	  <file:Documentation/networking/device_drivers/sb1000.txt> for
+	  information on how to use this module, as it needs special ppp
+	  scripts for establishing a connection. Further documentation
+	  and the necessary scripts can be found at:
 
 	  <http://www.jacksonville.net/~fventuri/>
 	  <http://home.adelphia.net/~siglercm/sb1000.html>
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 5bc168314ea2..40f421dbdf57 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1151,7 +1151,7 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq,
 
 	print_info = (vortex_debug > 1);
 	if (print_info)
-		pr_info("See Documentation/networking/vortex.txt\n");
+		pr_info("See Documentation/networking/device_drivers/3com/vortex.txt\n");
 
 	pr_info("%s: 3Com %s %s at %p.\n",
 	       print_name,
@@ -1956,7 +1956,7 @@ vortex_error(struct net_device *dev, int status)
 				   dev->name, tx_status);
 			if (tx_status == 0x82) {
 				pr_err("Probably a duplex mismatch.  See "
-						"Documentation/networking/vortex.txt\n");
+						"Documentation/networking/device_drivers/3com/vortex.txt\n");
 			}
 			dump_tx_ring(dev);
 		}
diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig
index 5c3ef9fc8207..0ac44ef1f7a9 100644
--- a/drivers/net/ethernet/3com/Kconfig
+++ b/drivers/net/ethernet/3com/Kconfig
@@ -75,8 +75,9 @@ config VORTEX
 	  "Hurricane" (3c555/3cSOHO)                           PCI
 
 	  If you have such a card, say Y here.  More specific information is in
-	  <file:Documentation/networking/vortex.txt> and in the comments at
-	  the beginning of <file:drivers/net/ethernet/3com/3c59x.c>.
+	  <file:Documentation/networking/device_drivers/3com/vortex.txt> and
+	  in the comments at the beginning of
+	  <file:drivers/net/ethernet/3com/3c59x.c>.
 
 	  To compile this support as a module, choose M here.
 
diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig
index e2cdfa75673f..e8001e974411 100644
--- a/drivers/net/ethernet/chelsio/Kconfig
+++ b/drivers/net/ethernet/chelsio/Kconfig
@@ -24,7 +24,8 @@ config CHELSIO_T1
 	---help---
 	  This driver supports Chelsio gigabit and 10-gigabit
 	  Ethernet cards. More information about adapter features and
-	  performance tuning is in <file:Documentation/networking/cxgb.txt>.
+	  performance tuning is in
+	  <file:Documentation/networking/device_drivers/chelsio/cxgb.txt>.
 
 	  For general information about Chelsio and our products, visit
 	  our website at <http://www.chelsio.com>.
diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig
index ec0b545197e2..e9a0213b08c4 100644
--- a/drivers/net/ethernet/cirrus/Kconfig
+++ b/drivers/net/ethernet/cirrus/Kconfig
@@ -23,7 +23,7 @@ config CS89x0
 	---help---
 	  Support for CS89x0 chipset based Ethernet cards. If you have a
 	  network (Ethernet) card of this type, say Y and read the file
-	  <file:Documentation/networking/cs89x0.txt>.
+	  <file:Documentation/networking/device_drivers/cirrus/cs89x0.txt>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called cs89x0.
diff --git a/drivers/net/ethernet/dec/tulip/Kconfig b/drivers/net/ethernet/dec/tulip/Kconfig
index 1003201b5d80..264e9b413e94 100644
--- a/drivers/net/ethernet/dec/tulip/Kconfig
+++ b/drivers/net/ethernet/dec/tulip/Kconfig
@@ -113,7 +113,7 @@ config DE4X5
 	  These include the DE425, DE434, DE435, DE450 and DE500 models.  If
 	  you have a network card of this type, say Y.  More specific
 	  information is contained in
-	  <file:Documentation/networking/de4x5.txt>.
+	  <file:Documentation/networking/device_drivers/dec/de4x5.txt>.
 
 	  To compile this driver as a module, choose M here. The module will
 	  be called de4x5.
@@ -137,7 +137,7 @@ config DM9102
 	  This driver is for DM9102(A)/DM9132/DM9801 compatible PCI cards from
 	  Davicom (<http://www.davicom.com.tw/>).  If you have such a network
 	  (Ethernet) card, say Y.  Some information is contained in the file
-	  <file:Documentation/networking/dmfe.txt>.
+	  <file:Documentation/networking/device_drivers/dec/dmfe.txt>.
 
 	  To compile this driver as a module, choose M here. The module will
 	  be called dmfe.
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index f0536b16b3c3..d8d423f22c4f 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -1881,7 +1881,7 @@ Compile command:
 
 gcc -D__KERNEL__ -DMODULE -I/usr/src/linux/include -Wall -Wstrict-prototypes -O2 -c dl2k.c
 
-Read Documentation/networking/dl2k.txt for details.
+Read Documentation/networking/device_drivers/dlink/dl2k.txt for details.
 
 */
 
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 59e1bc0f609e..f05c91d4c469 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -33,7 +33,7 @@ config E100
 	  to identify the adapter.
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/e100.rst>.
+	  <file:Documentation/networking/device_drivers/intel/e100.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called e100.
@@ -49,7 +49,7 @@ config E1000
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/e1000.rst>.
+	  <file:Documentation/networking/device_drivers/intel/e1000.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called e1000.
@@ -69,7 +69,7 @@ config E1000E
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/e1000e.rst>.
+	  <file:Documentation/networking/device_drivers/intel/e1000e.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called e1000e.
@@ -97,7 +97,7 @@ config IGB
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/igb.rst>.
+	  <file:Documentation/networking/device_drivers/intel/igb.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called igb.
@@ -133,7 +133,7 @@ config IGBVF
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/igbvf.rst>.
+	  <file:Documentation/networking/device_drivers/intel/igbvf.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called igbvf.
@@ -150,7 +150,7 @@ config IXGB
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/ixgb.rst>.
+	  <file:Documentation/networking/device_drivers/intel/ixgb.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called ixgb.
@@ -168,7 +168,7 @@ config IXGBE
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/ixgbe.rst>.
+	  <file:Documentation/networking/device_drivers/intel/ixgbe.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called ixgbe.
@@ -220,7 +220,7 @@ config IXGBEVF
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/ixgbevf.rst>.
+	  <file:Documentation/networking/device_drivers/intel/ixgbevf.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called ixgbevf.  MSI-X interrupt support is required
@@ -247,7 +247,7 @@ config I40E
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/i40e.rst>.
+	  <file:Documentation/networking/device_drivers/intel/i40e.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called i40e.
@@ -282,7 +282,7 @@ config I40EVF
 	  This driver was formerly named i40evf.
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/iavf.rst>.
+	  <file:Documentation/networking/device_drivers/intel/iavf.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called iavf.  MSI-X interrupt support is required
@@ -300,7 +300,7 @@ config ICE
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/ice.rst>.
+	  <file:Documentation/networking/device_drivers/intel/ice.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called ice.
@@ -318,7 +318,7 @@ config FM10K
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/fm10k.rst>.
+	  <file:Documentation/networking/device_drivers/intel/fm10k.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called fm10k.  MSI-X interrupt support is required
diff --git a/drivers/net/ethernet/neterion/Kconfig b/drivers/net/ethernet/neterion/Kconfig
index c26e0f70c494..7df20561e3fa 100644
--- a/drivers/net/ethernet/neterion/Kconfig
+++ b/drivers/net/ethernet/neterion/Kconfig
@@ -26,7 +26,7 @@ config S2IO
 	  on its age.
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/s2io.txt>.
+	  <file:Documentation/networking/device_drivers/neterion/s2io.txt>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called s2io.
@@ -41,7 +41,7 @@ config VXGE
 	  labeled as either one, depending on its age.
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/vxge.txt>.
+	  <file:Documentation/networking/device_drivers/neterion/vxge.txt>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called vxge.
diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig
index 358820282ef0..79612060d0ba 100644
--- a/drivers/net/ethernet/smsc/Kconfig
+++ b/drivers/net/ethernet/smsc/Kconfig
@@ -27,7 +27,7 @@ config SMC9194
 	  option if you have a DELL laptop with the docking station, or
 	  another SMC9192/9194 based chipset.  Say Y if you want it compiled
 	  into the kernel, and read the file
-	  <file:Documentation/networking/smc9.txt>.
+	  <file:Documentation/networking/device_drivers/smsc/smc9.txt>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called smc9194.
@@ -43,7 +43,7 @@ config SMC91X
 	  This is a driver for SMC's 91x series of Ethernet chipsets,
 	  including the SMC91C94 and the SMC91C111. Say Y if you want it
 	  compiled into the kernel, and read the file
-	  <file:Documentation/networking/smc9.txt>.
+	  <file:Documentation/networking/device_drivers/smsc/smc9.txt>.
 
 	  This driver is also available as a module ( = code which can be
 	  inserted in and removed from the running kernel whenever you want).
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index f932923f7d56..bb126be1eb72 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -121,7 +121,8 @@ config TLAN
 
 	  Devices currently supported by this driver are Compaq Netelligent,
 	  Compaq NetFlex and Olicom cards.  Please read the file
-	  <file:Documentation/networking/tlan.txt> for more details.
+	  <file:Documentation/networking/device_drivers/ti/tlan.txt>
+	  for more details.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called tlan.
diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index 93d142867c2a..b4ab1a5f6cd0 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -69,7 +69,9 @@ MODULE_AUTHOR("Maintainer: Samuel Chessman <chessman@tux.org>");
 MODULE_DESCRIPTION("Driver for TI ThunderLAN based ethernet PCI adapters");
 MODULE_LICENSE("GPL");
 
-/* Turn on debugging. See Documentation/networking/tlan.txt for details */
+/* Turn on debugging.
+ * See Documentation/networking/device_drivers/ti/tlan.txt for details
+ */
 static  int		debug;
 module_param(debug, int, 0);
 MODULE_PARM_DESC(debug, "ThunderLAN debug mask");
diff --git a/drivers/net/wireless/intel/ipw2x00/Kconfig b/drivers/net/wireless/intel/ipw2x00/Kconfig
index d6ec44d7a391..562395517e6c 100644
--- a/drivers/net/wireless/intel/ipw2x00/Kconfig
+++ b/drivers/net/wireless/intel/ipw2x00/Kconfig
@@ -15,9 +15,9 @@ config IPW2100
           A driver for the Intel PRO/Wireless 2100 Network 
 	  Connection 802.11b wireless network adapter.
 
-          See <file:Documentation/networking/README.ipw2100> for information on
-          the capabilities currently enabled in this driver and for tips
-          for debugging issues and problems.
+          See <file:Documentation/networking/device_drivers/intel/ipw2100.txt>
+	  for information on the capabilities currently enabled in this driver
+	  and for tips for debugging issues and problems.
 
 	  In order to use this driver, you will need a firmware image for it.
           You can obtain the firmware from
@@ -77,8 +77,8 @@ config IPW2200
           A driver for the Intel PRO/Wireless 2200BG and 2915ABG Network
 	  Connection adapters. 
 
-          See <file:Documentation/networking/README.ipw2200> for 
-	  information on the capabilities currently enabled in this 
+          See <file:Documentation/networking/device_drivers/intel/ipw2200.txt>
+	  for information on the capabilities currently enabled in this
 	  driver and for tips for debugging issues and problems.
 
 	  In order to use this driver, you will need a firmware image for it.
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index 910db46db6a1..6e31687a9c94 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -8370,7 +8370,7 @@ static int ipw2100_mod_firmware_load(struct ipw2100_fw *fw)
 	if (IPW2100_FW_MAJOR(h->version) != IPW2100_FW_MAJOR_VERSION) {
 		printk(KERN_WARNING DRV_NAME ": Firmware image not compatible "
 		       "(detected version id of %u). "
-		       "See Documentation/networking/README.ipw2100\n",
+		       "See Documentation/networking/device_drivers/intel/ipw2100.txt\n",
 		       h->version);
 		return 1;
 	}
-- 
cgit v1.2.3


From d930ac796fdb3eed62b0053297a728ced8fd58b1 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Sun, 28 Oct 2018 16:22:57 +0200
Subject: net/mlx5e: Refactor TIR configuration function

Refactor mlx5e_build_indir_tir_ctx_hash for better code re-use. TIR
stands for Transport Interface Receive, which is responsible for all
transport related operations on the receive side. Added a
static array with TIR default configuration values. This separates
configuration values from command setting, which is needed for
downstream patch.

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |   3 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/fs.h   |  16 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 167 +++++++++-------------
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c   |   5 +-
 4 files changed, 87 insertions(+), 104 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 86d60222b3cb..8539ea9a67ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -797,9 +797,10 @@ struct mlx5e_redirect_rqt_param {
 int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
 		       struct mlx5e_redirect_rqt_param rrp);
 void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
-				    enum mlx5e_traffic_types tt,
+				    const struct mlx5e_tirc_config *ttconfig,
 				    void *tirc, bool inner);
 void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen);
+struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 1431232c9a09..be5961ff24cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -73,6 +73,22 @@ enum mlx5e_traffic_types {
 	MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
 };
 
+struct mlx5e_tirc_config {
+	u8 l3_prot_type;
+	u8 l4_prot_type;
+	u32 rx_hash_fields;
+};
+
+#define MLX5_HASH_IP		(MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP)
+#define MLX5_HASH_IP_L4PORTS	(MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP   |\
+				 MLX5_HASH_FIELD_SEL_L4_SPORT |\
+				 MLX5_HASH_FIELD_SEL_L4_DPORT)
+#define MLX5_HASH_IP_IPSEC_SPI	(MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP   |\
+				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
+
 enum mlx5e_tunnel_types {
 	MLX5E_TT_IPV4_GRE,
 	MLX5E_TT_IPV6_GRE,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 85a4633454d0..01828efe905d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2607,6 +2607,54 @@ static void mlx5e_redirect_rqts_to_drop(struct mlx5e_priv *priv)
 	mlx5e_redirect_rqts(priv, drop_rrp);
 }
 
+static const struct mlx5e_tirc_config tirc_default_config[MLX5E_NUM_INDIR_TIRS] = {
+	[MLX5E_TT_IPV4_TCP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_TCP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV6_TCP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_TCP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV4_UDP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_UDP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV6_UDP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_UDP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV4_IPSEC_AH] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				     .l4_prot_type = 0,
+				     .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV6_IPSEC_AH] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				     .l4_prot_type = 0,
+				     .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV4_IPSEC_ESP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				      .l4_prot_type = 0,
+				      .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV6_IPSEC_ESP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				      .l4_prot_type = 0,
+				      .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV4] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+			    .l4_prot_type = 0,
+			    .rx_hash_fields = MLX5_HASH_IP,
+	},
+	[MLX5E_TT_IPV6] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+			    .l4_prot_type = 0,
+			    .rx_hash_fields = MLX5_HASH_IP,
+	},
+};
+
+struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt)
+{
+	return tirc_default_config[tt];
+}
+
 static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
 {
 	if (!params->lro_en)
@@ -2623,24 +2671,12 @@ static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
 }
 
 void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
-				    enum mlx5e_traffic_types tt,
+				    const struct mlx5e_tirc_config *ttconfig,
 				    void *tirc, bool inner)
 {
 	void *hfso = inner ? MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner) :
 			     MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
 
-#define MLX5_HASH_IP            (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP)
-
-#define MLX5_HASH_IP_L4PORTS    (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP   |\
-				 MLX5_HASH_FIELD_SEL_L4_SPORT |\
-				 MLX5_HASH_FIELD_SEL_L4_DPORT)
-
-#define MLX5_HASH_IP_IPSEC_SPI  (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP   |\
-				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
-
 	MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(params->rss_hfunc));
 	if (params->rss_hfunc == ETH_RSS_HASH_TOP) {
 		void *rss_key = MLX5_ADDR_OF(tirc, tirc,
@@ -2651,88 +2687,12 @@ void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
 		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
 		memcpy(rss_key, params->toeplitz_hash_key, len);
 	}
-
-	switch (tt) {
-	case MLX5E_TT_IPV4_TCP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_TCP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV6_TCP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_TCP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV4_UDP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_UDP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV6_UDP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_UDP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV4_IPSEC_AH:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV6_IPSEC_AH:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV4_IPSEC_ESP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV6_IPSEC_ESP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV4:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP);
-		break;
-
-	case MLX5E_TT_IPV6:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP);
-		break;
-	default:
-		WARN_ONCE(true, "%s: bad traffic type!\n", __func__);
-	}
+	MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+		 ttconfig->l3_prot_type);
+	MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+		 ttconfig->l4_prot_type);
+	MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+		 ttconfig->rx_hash_fields);
 }
 
 void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
@@ -2746,8 +2706,9 @@ void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc,
-					       false);
+		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params,
+					       &tirc_default_config[tt],
+					       tirc, false);
 		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
 	}
 
@@ -2756,8 +2717,9 @@ void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc,
-					       true);
+		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params,
+					       &tirc_default_config[tt],
+					       tirc, true);
 		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in,
 				     inlen);
 	}
@@ -2816,7 +2778,8 @@ static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv,
 	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
 	MLX5_SET(tirc, tirc, tunneled_offload_en, 0x1);
 
-	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, true);
+	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params,
+				       &tirc_default_config[tt], tirc, true);
 }
 
 static int mlx5e_set_mtu(struct mlx5_core_dev *mdev,
@@ -3208,7 +3171,9 @@ static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv,
 
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
-	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, false);
+
+	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params,
+				       &tirc_default_config[tt], tirc, false);
 }
 
 static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *tirc)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index fca6f4132c91..1025afc80f42 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -360,14 +360,15 @@ static int mlx5e_hairpin_create_indirect_tirs(struct mlx5e_hairpin *hp)
 	void *tirc;
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		struct mlx5e_tirc_config ttconfig = mlx5e_tirc_get_default_config(tt);
+
 		memset(in, 0, MLX5_ST_SZ_BYTES(create_tir_in));
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
 
 		MLX5_SET(tirc, tirc, transport_domain, hp->tdn);
 		MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 		MLX5_SET(tirc, tirc, indirect_table, hp->indir_rqt.rqtn);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, false);
-
+		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, &ttconfig, tirc, false);
 		err = mlx5_core_create_tir(hp->func_mdev, in,
 					   MLX5_ST_SZ_BYTES(create_tir_in), &hp->indir_tirn[tt]);
 		if (err) {
-- 
cgit v1.2.3


From bbeb53b8b2c92fd4e5b51e8fd9ab1c4000e4d350 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Tue, 6 Nov 2018 21:05:29 +0200
Subject: net/mlx5e: Move RSS params to a dedicated struct

Remove RSS params from params struct under channels, and introduce
a new struct with RSS configuration params under priv struct. There is
no functional change here.

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       | 16 +++++---
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   | 34 ++++++++---------
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 43 ++++++++++++----------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  9 +++--
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    |  5 ++-
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c  |  2 +-
 6 files changed, 62 insertions(+), 47 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8539ea9a67ca..330c476c1df2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -244,9 +244,6 @@ struct mlx5e_params {
 	bool lro_en;
 	u32 lro_wqe_sz;
 	u8  tx_min_inline_mode;
-	u8  rss_hfunc;
-	u8  toeplitz_hash_key[40];
-	u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE];
 	bool vlan_strip_disable;
 	bool scatter_fcs_en;
 	bool rx_dim_enabled;
@@ -651,6 +648,12 @@ enum {
 	MLX5E_NIC_PRIO
 };
 
+struct mlx5e_rss_params {
+	u32	indirection_rqt[MLX5E_INDIR_RQT_SIZE];
+	u8	toeplitz_hash_key[40];
+	u8	hfunc;
+};
+
 struct mlx5e_priv {
 	/* priv data path fields - start */
 	struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
@@ -671,6 +674,7 @@ struct mlx5e_priv {
 	struct mlx5e_tir           indir_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_tir           inner_indir_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_tir           direct_tir[MLX5E_MAX_NUM_CHANNELS];
+	struct mlx5e_rss_params    rss_params;
 	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
 
 	struct mlx5e_flow_steering fs;
@@ -796,7 +800,7 @@ struct mlx5e_redirect_rqt_param {
 
 int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
 		       struct mlx5e_redirect_rqt_param rrp);
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
 				    const struct mlx5e_tirc_config *ttconfig,
 				    void *tirc, bool inner);
 void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen);
@@ -982,11 +986,13 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv);
 void mlx5e_detach_netdev(struct mlx5e_priv *priv);
 void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+			    struct mlx5e_rss_params *rss_params,
 			    struct mlx5e_params *params,
 			    u16 max_channels, u16 mtu);
 void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
 			   struct mlx5e_params *params);
-void mlx5e_build_rss_params(struct mlx5e_params *params);
+void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
+			    u16 num_channels);
 u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
 void mlx5e_rx_dim_work(struct work_struct *work);
 void mlx5e_tx_dim_work(struct work_struct *work);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 2d5b00751a6d..e868d42c83cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -353,7 +353,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 	new_channels.params = priv->channels.params;
 	new_channels.params.num_channels = count;
 	if (!netif_is_rxfh_configured(priv->netdev))
-		mlx5e_build_default_indir_rqt(new_channels.params.indirection_rqt,
+		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
 					      MLX5E_INDIR_RQT_SIZE, count);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
@@ -931,7 +931,7 @@ out:
 
 u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv)
 {
-	return sizeof(priv->channels.params.toeplitz_hash_key);
+	return sizeof(priv->rss_params.toeplitz_hash_key);
 }
 
 static u32 mlx5e_get_rxfh_key_size(struct net_device *netdev)
@@ -957,17 +957,18 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 			  u8 *hfunc)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rss_params *rss = &priv->rss_params;
 
 	if (indir)
-		memcpy(indir, priv->channels.params.indirection_rqt,
-		       sizeof(priv->channels.params.indirection_rqt));
+		memcpy(indir, rss->indirection_rqt,
+		       sizeof(rss->indirection_rqt));
 
 	if (key)
-		memcpy(key, priv->channels.params.toeplitz_hash_key,
-		       sizeof(priv->channels.params.toeplitz_hash_key));
+		memcpy(key, rss->toeplitz_hash_key,
+		       sizeof(rss->toeplitz_hash_key));
 
 	if (hfunc)
-		*hfunc = priv->channels.params.rss_hfunc;
+		*hfunc = rss->hfunc;
 
 	return 0;
 }
@@ -976,6 +977,7 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 			  const u8 *key, const u8 hfunc)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_rss_params *rss = &priv->rss_params;
 	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	bool hash_changed = false;
 	void *in;
@@ -991,15 +993,14 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 
 	mutex_lock(&priv->state_lock);
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	    hfunc != priv->channels.params.rss_hfunc) {
-		priv->channels.params.rss_hfunc = hfunc;
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != rss->hfunc) {
+		rss->hfunc = hfunc;
 		hash_changed = true;
 	}
 
 	if (indir) {
-		memcpy(priv->channels.params.indirection_rqt, indir,
-		       sizeof(priv->channels.params.indirection_rqt));
+		memcpy(rss->indirection_rqt, indir,
+		       sizeof(rss->indirection_rqt));
 
 		if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
 			u32 rqtn = priv->indir_rqt.rqtn;
@@ -1007,7 +1008,7 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 				.is_rss = true,
 				{
 					.rss = {
-						.hfunc = priv->channels.params.rss_hfunc,
+						.hfunc = rss->hfunc,
 						.channels  = &priv->channels,
 					},
 				},
@@ -1018,10 +1019,9 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 	}
 
 	if (key) {
-		memcpy(priv->channels.params.toeplitz_hash_key, key,
-		       sizeof(priv->channels.params.toeplitz_hash_key));
-		hash_changed = hash_changed ||
-			       priv->channels.params.rss_hfunc == ETH_RSS_HASH_TOP;
+		memcpy(rss->toeplitz_hash_key, key,
+		       sizeof(rss->toeplitz_hash_key));
+		hash_changed = hash_changed || rss->hfunc == ETH_RSS_HASH_TOP;
 	}
 
 	if (hash_changed)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 01828efe905d..be782c508f3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2504,7 +2504,7 @@ static void mlx5e_fill_rqt_rqns(struct mlx5e_priv *priv, int sz,
 			if (rrp.rss.hfunc == ETH_RSS_HASH_XOR)
 				ix = mlx5e_bits_invert(i, ilog2(sz));
 
-			ix = priv->channels.params.indirection_rqt[ix];
+			ix = priv->rss_params.indirection_rqt[ix];
 			rqn = rrp.rss.channels->c[ix]->rq.rqn;
 		} else {
 			rqn = rrp.rqn;
@@ -2587,7 +2587,7 @@ static void mlx5e_redirect_rqts_to_channels(struct mlx5e_priv *priv,
 		{
 			.rss = {
 				.channels  = chs,
-				.hfunc     = chs->params.rss_hfunc,
+				.hfunc     = priv->rss_params.hfunc,
 			}
 		},
 	};
@@ -2670,22 +2670,22 @@ static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
 	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, params->lro_timeout);
 }
 
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
 				    const struct mlx5e_tirc_config *ttconfig,
 				    void *tirc, bool inner)
 {
 	void *hfso = inner ? MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner) :
 			     MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
 
-	MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(params->rss_hfunc));
-	if (params->rss_hfunc == ETH_RSS_HASH_TOP) {
+	MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(rss_params->hfunc));
+	if (rss_params->hfunc == ETH_RSS_HASH_TOP) {
 		void *rss_key = MLX5_ADDR_OF(tirc, tirc,
 					     rx_hash_toeplitz_key);
 		size_t len = MLX5_FLD_SZ_BYTES(tirc,
 					       rx_hash_toeplitz_key);
 
 		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
-		memcpy(rss_key, params->toeplitz_hash_key, len);
+		memcpy(rss_key, rss_params->toeplitz_hash_key, len);
 	}
 	MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
 		 ttconfig->l3_prot_type);
@@ -2706,7 +2706,7 @@ void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params,
+		mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
 					       &tirc_default_config[tt],
 					       tirc, false);
 		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
@@ -2717,7 +2717,7 @@ void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params,
+		mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
 					       &tirc_default_config[tt],
 					       tirc, true);
 		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in,
@@ -2778,7 +2778,7 @@ static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv,
 	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
 	MLX5_SET(tirc, tirc, tunneled_offload_en, 0x1);
 
-	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params,
+	mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
 				       &tirc_default_config[tt], tirc, true);
 }
 
@@ -3172,7 +3172,7 @@ static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv,
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
 
-	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params,
+	mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
 				       &tirc_default_config[tt], tirc, false);
 }
 
@@ -4511,15 +4511,18 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
 	mlx5e_init_rq_type_params(mdev, params);
 }
 
-void mlx5e_build_rss_params(struct mlx5e_params *params)
+void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
+			    u16 num_channels)
 {
-	params->rss_hfunc = ETH_RSS_HASH_XOR;
-	netdev_rss_key_fill(params->toeplitz_hash_key, sizeof(params->toeplitz_hash_key));
-	mlx5e_build_default_indir_rqt(params->indirection_rqt,
-				      MLX5E_INDIR_RQT_SIZE, params->num_channels);
+	rss_params->hfunc = ETH_RSS_HASH_XOR;
+	netdev_rss_key_fill(rss_params->toeplitz_hash_key,
+			    sizeof(rss_params->toeplitz_hash_key));
+	mlx5e_build_default_indir_rqt(rss_params->indirection_rqt,
+				      MLX5E_INDIR_RQT_SIZE, num_channels);
 }
 
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+			    struct mlx5e_rss_params *rss_params,
 			    struct mlx5e_params *params,
 			    u16 max_channels, u16 mtu)
 {
@@ -4568,7 +4571,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 	params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(mdev);
 
 	/* RSS */
-	mlx5e_build_rss_params(params);
+	mlx5e_build_rss_params(rss_params, params->num_channels);
 }
 
 static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
@@ -4741,14 +4744,16 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 			  void *ppriv)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rss_params *rss = &priv->rss_params;
 	int err;
 
 	err = mlx5e_netdev_init(netdev, priv, mdev, profile, ppriv);
 	if (err)
 		return err;
 
-	mlx5e_build_nic_params(mdev, &priv->channels.params,
-			       mlx5e_get_netdev_max_channels(netdev), netdev->mtu);
+	mlx5e_build_nic_params(mdev, rss, &priv->channels.params,
+			       mlx5e_get_netdev_max_channels(netdev),
+			       netdev->mtu);
 
 	mlx5e_timestamp_init(priv);
 
@@ -5023,7 +5028,7 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 	if (priv->channels.params.num_channels > max_nch) {
 		mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
 		priv->channels.params.num_channels = max_nch;
-		mlx5e_build_default_indir_rqt(priv->channels.params.indirection_rqt,
+		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
 					      MLX5E_INDIR_RQT_SIZE, max_nch);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index c3c657548824..a137540b84bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1012,7 +1012,9 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
 };
 
 static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
-				   struct mlx5e_params *params, u16 mtu)
+				   struct mlx5e_params *params,
+				   struct mlx5e_rss_params *rss_params,
+				   u16 mtu)
 {
 	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
 					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
@@ -1034,7 +1036,7 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
 	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
 
 	/* RSS */
-	mlx5e_build_rss_params(params);
+	mlx5e_build_rss_params(rss_params, params->num_channels);
 }
 
 static void mlx5e_build_rep_netdev(struct net_device *netdev)
@@ -1087,7 +1089,8 @@ static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
 	priv->channels.params.num_channels =
 				mlx5e_get_netdev_max_channels(netdev);
 
-	mlx5e_build_rep_params(mdev, &priv->channels.params, netdev->mtu);
+	mlx5e_build_rep_params(mdev, &priv->channels.params,
+			       &priv->rss_params, netdev->mtu);
 	mlx5e_build_rep_netdev(netdev);
 
 	mlx5e_timestamp_init(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 1025afc80f42..a3ff2492646d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -316,7 +316,7 @@ static void mlx5e_hairpin_fill_rqt_rqns(struct mlx5e_hairpin *hp, void *rqtc)
 
 	for (i = 0; i < sz; i++) {
 		ix = i;
-		if (priv->channels.params.rss_hfunc == ETH_RSS_HASH_XOR)
+		if (priv->rss_params.hfunc == ETH_RSS_HASH_XOR)
 			ix = mlx5e_bits_invert(i, ilog2(sz));
 		ix = indirection_rqt[ix];
 		rqn = hp->pair->rqn[ix];
@@ -368,7 +368,8 @@ static int mlx5e_hairpin_create_indirect_tirs(struct mlx5e_hairpin *hp)
 		MLX5_SET(tirc, tirc, transport_domain, hp->tdn);
 		MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 		MLX5_SET(tirc, tirc, indirect_table, hp->indir_rqt.rqtn);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, &ttconfig, tirc, false);
+		mlx5e_build_indir_tir_ctx_hash(&priv->rss_params, &ttconfig, tirc, false);
+
 		err = mlx5_core_create_tir(hp->func_mdev, in,
 					   MLX5_ST_SZ_BYTES(create_tir_in), &hp->indir_tirn[tt]);
 		if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 11dabd62e2c7..bfc0f6581729 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -87,7 +87,7 @@ int mlx5i_init(struct mlx5_core_dev *mdev,
 	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
 	netdev->mtu = max_mtu;
 
-	mlx5e_build_nic_params(mdev, &priv->channels.params,
+	mlx5e_build_nic_params(mdev, &priv->rss_params, &priv->channels.params,
 			       mlx5e_get_netdev_max_channels(netdev),
 			       netdev->mtu);
 	mlx5i_build_nic_params(mdev, &priv->channels.params);
-- 
cgit v1.2.3


From 756c41603a189e4ae9dca77c3c3d80a926d8bedf Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Tue, 23 Oct 2018 16:03:33 +0300
Subject: net/mlx5e: ethtool, Support user configuration for RX hash fields

Enable user configuration of RX hash fields that are used for traffic
spreading into RX queues. User can change built-in RSS (Receive Side
Scaling) profiles on the following traffic types: UDP4, UDP6, TCP4 and
TCP6.  This configuration effects both outer and inner headers.  Added
support for ethtool commands: ETHTOOL_SRXFH and ETHTOOL_GRXFH.

Command example respectively:
$ethtool -N eth1 rx-flow-hash tcp4 sdfn
$ethtool -n eth1 rx-flow-hash tcpp4
IP SA
IP DA
L4 bytes 0 & 1 [TCP/UDP src port]
L4 bytes 2 & 3 [TCP/UDP dst port]

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   1 +
 .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c    | 112 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  27 +++--
 3 files changed, 134 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 330c476c1df2..c6686256a92a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -650,6 +650,7 @@ enum {
 
 struct mlx5e_rss_params {
 	u32	indirection_rqt[MLX5E_INDIR_RQT_SIZE];
+	u32	rx_hash_fields[MLX5E_NUM_INDIR_TIRS];
 	u8	toeplitz_hash_key[40];
 	u8	hfunc;
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index c18dcebe1462..4421c10f58ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -771,6 +771,112 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)
 	INIT_LIST_HEAD(&priv->fs.ethtool.rules);
 }
 
+static enum mlx5e_traffic_types flow_type_to_traffic_type(u32 flow_type)
+{
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+		return  MLX5E_TT_IPV4_TCP;
+	case TCP_V6_FLOW:
+		return MLX5E_TT_IPV6_TCP;
+	case UDP_V4_FLOW:
+		return MLX5E_TT_IPV4_UDP;
+	case UDP_V6_FLOW:
+		return MLX5E_TT_IPV6_UDP;
+	case AH_V4_FLOW:
+		return MLX5E_TT_IPV4_IPSEC_AH;
+	case AH_V6_FLOW:
+		return MLX5E_TT_IPV6_IPSEC_AH;
+	case ESP_V4_FLOW:
+		return MLX5E_TT_IPV4_IPSEC_ESP;
+	case ESP_V6_FLOW:
+		return MLX5E_TT_IPV6_IPSEC_ESP;
+	case IPV4_FLOW:
+		return MLX5E_TT_IPV4;
+	case IPV6_FLOW:
+		return MLX5E_TT_IPV6;
+	default:
+		return MLX5E_NUM_INDIR_TIRS;
+	}
+}
+
+static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv,
+				  struct ethtool_rxnfc *nfc)
+{
+	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
+	enum mlx5e_traffic_types tt;
+	u8 rx_hash_field = 0;
+	void *in;
+
+	tt = flow_type_to_traffic_type(nfc->flow_type);
+	if (tt == MLX5E_NUM_INDIR_TIRS)
+		return -EINVAL;
+
+	/*  RSS does not support anything other than hashing to queues
+	 *  on src IP, dest IP, TCP/UDP src port and TCP/UDP dest
+	 *  port.
+	 */
+	if (nfc->flow_type != TCP_V4_FLOW &&
+	    nfc->flow_type != TCP_V6_FLOW &&
+	    nfc->flow_type != UDP_V4_FLOW &&
+	    nfc->flow_type != UDP_V6_FLOW)
+		return -EOPNOTSUPP;
+
+	if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST |
+			  RXH_L4_B_0_1 | RXH_L4_B_2_3))
+		return -EOPNOTSUPP;
+
+	if (nfc->data & RXH_IP_SRC)
+		rx_hash_field |= MLX5_HASH_FIELD_SEL_SRC_IP;
+	if (nfc->data & RXH_IP_DST)
+		rx_hash_field |= MLX5_HASH_FIELD_SEL_DST_IP;
+	if (nfc->data & RXH_L4_B_0_1)
+		rx_hash_field |= MLX5_HASH_FIELD_SEL_L4_SPORT;
+	if (nfc->data & RXH_L4_B_2_3)
+		rx_hash_field |= MLX5_HASH_FIELD_SEL_L4_DPORT;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	mutex_lock(&priv->state_lock);
+
+	if (rx_hash_field == priv->rss_params.rx_hash_fields[tt])
+		goto out;
+
+	priv->rss_params.rx_hash_fields[tt] = rx_hash_field;
+	mlx5e_modify_tirs_hash(priv, in, inlen);
+
+out:
+	mutex_unlock(&priv->state_lock);
+	kvfree(in);
+	return 0;
+}
+
+static int mlx5e_get_rss_hash_opt(struct mlx5e_priv *priv,
+				  struct ethtool_rxnfc *nfc)
+{
+	enum mlx5e_traffic_types tt;
+	u32 hash_field = 0;
+
+	tt = flow_type_to_traffic_type(nfc->flow_type);
+	if (tt == MLX5E_NUM_INDIR_TIRS)
+		return -EINVAL;
+
+	hash_field = priv->rss_params.rx_hash_fields[tt];
+	nfc->data = 0;
+
+	if (hash_field & MLX5_HASH_FIELD_SEL_SRC_IP)
+		nfc->data |= RXH_IP_SRC;
+	if (hash_field & MLX5_HASH_FIELD_SEL_DST_IP)
+		nfc->data |= RXH_IP_DST;
+	if (hash_field & MLX5_HASH_FIELD_SEL_L4_SPORT)
+		nfc->data |= RXH_L4_B_0_1;
+	if (hash_field & MLX5_HASH_FIELD_SEL_L4_DPORT)
+		nfc->data |= RXH_L4_B_2_3;
+
+	return 0;
+}
+
 int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 {
 	int err = 0;
@@ -783,6 +889,9 @@ int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	case ETHTOOL_SRXCLSRLDEL:
 		err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
 		break;
+	case ETHTOOL_SRXFH:
+		err = mlx5e_set_rss_hash_opt(priv, cmd);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
@@ -810,6 +919,9 @@ int mlx5e_get_rxnfc(struct net_device *dev,
 	case ETHTOOL_GRXCLSRLALL:
 		err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
 		break;
+	case ETHTOOL_GRXFH:
+		err =  mlx5e_get_rss_hash_opt(priv, info);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index be782c508f3a..544c287c6481 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2695,20 +2695,30 @@ void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
 		 ttconfig->rx_hash_fields);
 }
 
+static void mlx5e_update_rx_hash_fields(struct mlx5e_tirc_config *ttconfig,
+					enum mlx5e_traffic_types tt,
+					u32 rx_hash_fields)
+{
+	*ttconfig                = tirc_default_config[tt];
+	ttconfig->rx_hash_fields = rx_hash_fields;
+}
+
 void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 {
 	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
+	struct mlx5e_rss_params *rss = &priv->rss_params;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int ctxlen = MLX5_ST_SZ_BYTES(tirc);
+	struct mlx5e_tirc_config ttconfig;
 	int tt;
 
 	MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
-					       &tirc_default_config[tt],
-					       tirc, false);
+		mlx5e_update_rx_hash_fields(&ttconfig, tt,
+					    rss->rx_hash_fields[tt]);
+		mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, false);
 		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
 	}
 
@@ -2717,9 +2727,9 @@ void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
-					       &tirc_default_config[tt],
-					       tirc, true);
+		mlx5e_update_rx_hash_fields(&ttconfig, tt,
+					    rss->rx_hash_fields[tt]);
+		mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, true);
 		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in,
 				     inlen);
 	}
@@ -4514,11 +4524,16 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
 void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
 			    u16 num_channels)
 {
+	enum mlx5e_traffic_types tt;
+
 	rss_params->hfunc = ETH_RSS_HASH_XOR;
 	netdev_rss_key_fill(rss_params->toeplitz_hash_key,
 			    sizeof(rss_params->toeplitz_hash_key));
 	mlx5e_build_default_indir_rqt(rss_params->indirection_rqt,
 				      MLX5E_INDIR_RQT_SIZE, num_channels);
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
+		rss_params->rx_hash_fields[tt] =
+			tirc_default_config[tt].rx_hash_fields;
 }
 
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
-- 
cgit v1.2.3


From 8ff57c18e9f6b03722070a372cdcc850b13bcbc8 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 19 Nov 2018 15:07:07 +0200
Subject: net/mlx5e: Improve ethtool private-flags code structure

Refactor the code of private-flags setter.
Replace consecutive calls to mlx5e_handle_pflag with a loop
that uses a preset set of parameters.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       | 18 ++---
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   | 76 +++++++++-------------
 2 files changed, 41 insertions(+), 53 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index c6686256a92a..8760d10ad5a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -49,6 +49,7 @@
 #include <net/switchdev.h>
 #include <net/xdp.h>
 #include <linux/net_dim.h>
+#include <linux/bits.h>
 #include "wq.h"
 #include "mlx5_core.h"
 #include "en_stats.h"
@@ -211,22 +212,23 @@ struct mlx5e_umr_wqe {
 extern const char mlx5e_self_tests[][ETH_GSTRING_LEN];
 
 enum mlx5e_priv_flag {
-	MLX5E_PFLAG_RX_CQE_BASED_MODER = (1 << 0),
-	MLX5E_PFLAG_TX_CQE_BASED_MODER = (1 << 1),
-	MLX5E_PFLAG_RX_CQE_COMPRESS = (1 << 2),
-	MLX5E_PFLAG_RX_STRIDING_RQ = (1 << 3),
-	MLX5E_PFLAG_RX_NO_CSUM_COMPLETE = (1 << 4),
+	MLX5E_PFLAG_RX_CQE_BASED_MODER,
+	MLX5E_PFLAG_TX_CQE_BASED_MODER,
+	MLX5E_PFLAG_RX_CQE_COMPRESS,
+	MLX5E_PFLAG_RX_STRIDING_RQ,
+	MLX5E_PFLAG_RX_NO_CSUM_COMPLETE,
+	MLX5E_NUM_PFLAGS, /* Keep last */
 };
 
 #define MLX5E_SET_PFLAG(params, pflag, enable)			\
 	do {							\
 		if (enable)					\
-			(params)->pflags |= (pflag);		\
+			(params)->pflags |= BIT(pflag);		\
 		else						\
-			(params)->pflags &= ~(pflag);		\
+			(params)->pflags &= ~(BIT(pflag));	\
 	} while (0)
 
-#define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (pflag)))
+#define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (BIT(pflag))))
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index e868d42c83cb..da4bb62ac528 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -135,14 +135,15 @@ void mlx5e_build_ptys2ethtool_map(void)
 				       ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT);
 }
 
-static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = {
-	"rx_cqe_moder",
-	"tx_cqe_moder",
-	"rx_cqe_compress",
-	"rx_striding_rq",
-	"rx_no_csum_complete",
+typedef int (*mlx5e_pflag_handler)(struct net_device *netdev, bool enable);
+
+struct pflag_desc {
+	char name[ETH_GSTRING_LEN];
+	mlx5e_pflag_handler handler;
 };
 
+static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS];
+
 int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset)
 {
 	int i, num_stats = 0;
@@ -153,7 +154,7 @@ int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset)
 			num_stats += mlx5e_stats_grps[i].get_num_stats(priv);
 		return num_stats;
 	case ETH_SS_PRIV_FLAGS:
-		return ARRAY_SIZE(mlx5e_priv_flags);
+		return MLX5E_NUM_PFLAGS;
 	case ETH_SS_TEST:
 		return mlx5e_self_test_num(priv);
 	/* fallthrough */
@@ -183,8 +184,9 @@ void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv, u32 stringset, u8 *data)
 
 	switch (stringset) {
 	case ETH_SS_PRIV_FLAGS:
-		for (i = 0; i < ARRAY_SIZE(mlx5e_priv_flags); i++)
-			strcpy(data + i * ETH_GSTRING_LEN, mlx5e_priv_flags[i]);
+		for (i = 0; i < MLX5E_NUM_PFLAGS; i++)
+			strcpy(data + i * ETH_GSTRING_LEN,
+			       mlx5e_priv_flags[i].name);
 		break;
 
 	case ETH_SS_TEST:
@@ -1485,8 +1487,6 @@ static int mlx5e_get_module_eeprom(struct net_device *netdev,
 	return 0;
 }
 
-typedef int (*mlx5e_pflag_handler)(struct net_device *netdev, bool enable);
-
 static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable,
 				     bool is_rx_cq)
 {
@@ -1649,23 +1649,30 @@ static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
 	return 0;
 }
 
+static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS] = {
+	{ "rx_cqe_moder",        set_pflag_rx_cqe_based_moder },
+	{ "tx_cqe_moder",        set_pflag_tx_cqe_based_moder },
+	{ "rx_cqe_compress",     set_pflag_rx_cqe_compress },
+	{ "rx_striding_rq",      set_pflag_rx_striding_rq },
+	{ "rx_no_csum_complete", set_pflag_rx_no_csum_complete },
+};
+
 static int mlx5e_handle_pflag(struct net_device *netdev,
 			      u32 wanted_flags,
-			      enum mlx5e_priv_flag flag,
-			      mlx5e_pflag_handler pflag_handler)
+			      enum mlx5e_priv_flag flag)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	bool enable = !!(wanted_flags & flag);
+	bool enable = !!(wanted_flags & BIT(flag));
 	u32 changes = wanted_flags ^ priv->channels.params.pflags;
 	int err;
 
-	if (!(changes & flag))
+	if (!(changes & BIT(flag)))
 		return 0;
 
-	err = pflag_handler(netdev, enable);
+	err = mlx5e_priv_flags[flag].handler(netdev, enable);
 	if (err) {
-		netdev_err(netdev, "%s private flag 0x%x failed err %d\n",
-			   enable ? "Enable" : "Disable", flag, err);
+		netdev_err(netdev, "%s private flag '%s' failed err %d\n",
+			   enable ? "Enable" : "Disable", mlx5e_priv_flags[flag].name, err);
 		return err;
 	}
 
@@ -1676,38 +1683,17 @@ static int mlx5e_handle_pflag(struct net_device *netdev,
 static int mlx5e_set_priv_flags(struct net_device *netdev, u32 pflags)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	enum mlx5e_priv_flag pflag;
 	int err;
 
 	mutex_lock(&priv->state_lock);
-	err = mlx5e_handle_pflag(netdev, pflags,
-				 MLX5E_PFLAG_RX_CQE_BASED_MODER,
-				 set_pflag_rx_cqe_based_moder);
-	if (err)
-		goto out;
-
-	err = mlx5e_handle_pflag(netdev, pflags,
-				 MLX5E_PFLAG_TX_CQE_BASED_MODER,
-				 set_pflag_tx_cqe_based_moder);
-	if (err)
-		goto out;
-
-	err = mlx5e_handle_pflag(netdev, pflags,
-				 MLX5E_PFLAG_RX_CQE_COMPRESS,
-				 set_pflag_rx_cqe_compress);
-	if (err)
-		goto out;
 
-	err = mlx5e_handle_pflag(netdev, pflags,
-				 MLX5E_PFLAG_RX_STRIDING_RQ,
-				 set_pflag_rx_striding_rq);
-	if (err)
-		goto out;
-
-	err = mlx5e_handle_pflag(netdev, pflags,
-				 MLX5E_PFLAG_RX_NO_CSUM_COMPLETE,
-				 set_pflag_rx_no_csum_complete);
+	for (pflag = 0; pflag < MLX5E_NUM_PFLAGS; pflag++) {
+		err = mlx5e_handle_pflag(netdev, pflags, pflag);
+		if (err)
+			break;
+	}
 
-out:
 	mutex_unlock(&priv->state_lock);
 
 	/* Need to fix some features.. */
-- 
cgit v1.2.3


From 5f15eed245bc6d7c82d44f0ebcaf62071a9d55bd Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 5 Dec 2018 21:49:40 +0100
Subject: net: mii: Fix autoneg in mii_lpa_to_linkmode_lpa_t()

mii_adv_to_linkmode_adv_t() clears all bits before setting it needs to
set. This means the freshly set Autoneg gets cleared.

Change the order, and add comments about it clearing the old content
of the bitmap.

Fixes: c0ec3c273677 ("net: phy: Convert u32 phydev->lp_advertising to linkmode")
Reported-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mii.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/linux/mii.h b/include/linux/mii.h
index fb7ae4ae8ce3..57365224306c 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -378,7 +378,8 @@ static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa)
  * @adv: value of the MII_ADVERTISE register
  *
  * A small helper function that translates MII_ADVERTISE bits
- * to linkmode advertisement settings.
+ * to linkmode advertisement settings. Clears the old value
+ * of advertising.
  */
 static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising,
 					     u32 adv)
@@ -408,16 +409,18 @@ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising,
  * @adv: value of the MII_LPA register
  *
  * A small helper function that translates MII_LPA bits, when in
- * 1000Base-T mode, to linkmode LP advertisement settings.
+ * 1000Base-T mode, to linkmode LP advertisement settings. Clears the
+ * old value of advertising
  */
 static inline void mii_lpa_to_linkmode_lpa_t(unsigned long *lp_advertising,
 					     u32 lpa)
 {
+	mii_adv_to_linkmode_adv_t(lp_advertising, lpa);
+
 	if (lpa & LPA_LPACK)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
 				 lp_advertising);
 
-	mii_adv_to_linkmode_adv_t(lp_advertising, lpa);
 }
 
 /**
-- 
cgit v1.2.3


From 78a24df370072ea3b7c0a466efd776fc8f87c73a Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 5 Dec 2018 21:49:41 +0100
Subject: net: mii: Rename mii_stat1000_to_linkmode_lpa_t

Rename mii_stat1000_to_linkmode_lpa_t to
mii_stat1000_mod_linkmode_lpa_t to indicate it modifies the passed
linkmode bitmap, without clearing any other bits.

Add a helper to set/clear bits in a linkmode.

Use this helper to ensure bit are clear which the stat1000 indicates
should not be set.

Fixes: c0ec3c273677 ("net: phy: Convert u32 phydev->lp_advertising to linkmode")
Suggested-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c    |  2 +-
 drivers/net/phy/marvell10g.c |  2 +-
 drivers/net/phy/phy_device.c |  4 ++--
 include/linux/linkmode.h     |  9 +++++++++
 include/linux/mii.h          | 20 ++++++++++----------
 5 files changed, 23 insertions(+), 14 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 6a9881942e53..03dafe0e68a2 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1138,7 +1138,7 @@ static int marvell_read_status_page_an(struct phy_device *phydev,
 
 	if (!fiber) {
 		mii_lpa_to_linkmode_lpa_t(phydev->lp_advertising, lpa);
-		mii_stat1000_to_linkmode_lpa_t(phydev->lp_advertising, lpagb);
+		mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, lpagb);
 
 		if (phydev->duplex == DUPLEX_FULL) {
 			phydev->pause = lpa & LPA_PAUSE_CAP ? 1 : 0;
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 6f6e886fc836..82ab6ed3b74e 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -490,7 +490,7 @@ static int mv3310_read_status(struct phy_device *phydev)
 		if (val < 0)
 			return val;
 
-		mii_stat1000_to_linkmode_lpa_t(phydev->lp_advertising, val);
+		mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, val);
 
 		if (phydev->autoneg == AUTONEG_ENABLE)
 			phy_resolve_aneg_linkmode(phydev);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index e6720e2a2da6..c20b5ecc0f4b 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1739,8 +1739,8 @@ int genphy_read_status(struct phy_device *phydev)
 				return -ENOLINK;
 			}
 
-			mii_stat1000_to_linkmode_lpa_t(phydev->lp_advertising,
-						       lpagb);
+			mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising,
+							lpagb);
 			common_adv_gb = lpagb & adv << 2;
 		}
 
diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h
index 22443d7fb5cd..a99c58866860 100644
--- a/include/linux/linkmode.h
+++ b/include/linux/linkmode.h
@@ -57,6 +57,15 @@ static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr)
 	__clear_bit(nr, addr);
 }
 
+static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr,
+				    int set)
+{
+	if (set)
+		linkmode_set_bit(nr, addr);
+	else
+		linkmode_clear_bit(nr, addr);
+}
+
 static inline void linkmode_change_bit(int nr, volatile unsigned long *addr)
 {
 	__change_bit(nr, addr);
diff --git a/include/linux/mii.h b/include/linux/mii.h
index 57365224306c..b915ef6c3692 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -288,22 +288,22 @@ static inline u32 mii_stat1000_to_ethtool_lpa_t(u32 lpa)
 }
 
 /**
- * mii_stat1000_to_linkmode_lpa_t
+ * mii_stat1000_mod_linkmode_lpa_t
  * @advertising: target the linkmode advertisement settings
  * @adv: value of the MII_STAT1000 register
  *
  * A small helper function that translates MII_STAT1000 bits, when in
- * 1000Base-T mode, to linkmode advertisement settings.
+ * 1000Base-T mode, to linkmode advertisement settings. Other bits in
+ * advertising are not changes.
  */
-static inline void mii_stat1000_to_linkmode_lpa_t(unsigned long *advertising,
-						  u32 lpa)
+static inline void mii_stat1000_mod_linkmode_lpa_t(unsigned long *advertising,
+						   u32 lpa)
 {
-	if (lpa & LPA_1000HALF)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
-				 advertising);
-	if (lpa & LPA_1000FULL)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
-				 advertising);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+			 advertising, lpa & LPA_1000HALF);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+			 advertising, lpa & LPA_1000FULL);
 }
 
 /**
-- 
cgit v1.2.3


From ab9cb729ab0d4151f7ba76dd3ff592242a694754 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 5 Dec 2018 21:49:42 +0100
Subject: phy: marvell: Rename mii_lpa_to_linkmode_lpa_t

Rename mii_lpa_to_linkmode_lpa_t to mii_lpa_mod_linkmode_lpa_t to
indicate it modifies the passed linkmode bitmap, without clearing any
other bits.

Also, ensure bit are clear which the lpa indicates should not be set.

Fixes: c0ec3c273677 ("net: phy: Convert u32 phydev->lp_advertising to linkmode")
Suggested-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 03dafe0e68a2..a9c7c7f41b0c 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1047,21 +1047,21 @@ static int m88e1145_config_init(struct phy_device *phydev)
 }
 
 /**
- * fiber_lpa_to_linkmode_lpa_t
+ * fiber_lpa_mod_linkmode_lpa_t
  * @advertising: the linkmode advertisement settings
  * @lpa: value of the MII_LPA register for fiber link
  *
- * A small helper function that translates MII_LPA
- * bits to linkmode LP advertisement settings.
+ * A small helper function that translates MII_LPA bits to linkmode LP
+ * advertisement settings. Other bits in advertising are left
+ * unchanged.
  */
-static void fiber_lpa_to_linkmode_lpa_t(unsigned long *advertising, u32 lpa)
+static void fiber_lpa_mod_linkmode_lpa_t(unsigned long *advertising, u32 lpa)
 {
-	if (lpa & LPA_FIBER_1000HALF)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
-				 advertising);
-	if (lpa & LPA_FIBER_1000FULL)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
-				 advertising);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+			 advertising, lpa & LPA_FIBER_1000HALF);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+			 advertising, lpa & LPA_FIBER_1000FULL);
 }
 
 /**
@@ -1146,7 +1146,7 @@ static int marvell_read_status_page_an(struct phy_device *phydev,
 		}
 	} else {
 		/* The fiber link is only 1000M capable */
-		fiber_lpa_to_linkmode_lpa_t(phydev->lp_advertising, lpa);
+		fiber_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, lpa);
 
 		if (phydev->duplex == DUPLEX_FULL) {
 			if (!(lpa & LPA_PAUSE_FIBER)) {
-- 
cgit v1.2.3


From d3351931a37bdb329b5ea761424579fa91c866ee Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 5 Dec 2018 21:49:43 +0100
Subject: net: mii: Add mii_lpa_mod_linkmode_lpa_t

Add a _mod_ variant of mii_lpa_to_linkmode_lpa_t. Use this to fix the
genphy_read_status() where the 1G link partner features are getting
lost.

Fixes: c0ec3c273677 ("net: phy: Convert u32 phydev->lp_advertising to linkmode")
Reported-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c |  2 +-
 include/linux/mii.h          | 68 +++++++++++++++++++++++++++++++++-----------
 2 files changed, 53 insertions(+), 17 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index c20b5ecc0f4b..7d5d698604aa 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1748,7 +1748,7 @@ int genphy_read_status(struct phy_device *phydev)
 		if (lpa < 0)
 			return lpa;
 
-		mii_lpa_to_linkmode_lpa_t(phydev->lp_advertising, lpa);
+		mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, lpa);
 
 		adv = phy_read(phydev, MII_ADVERTISE);
 		if (adv < 0)
diff --git a/include/linux/mii.h b/include/linux/mii.h
index b915ef6c3692..e72447778a08 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -372,6 +372,36 @@ static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa)
 	return result | mii_adv_to_ethtool_adv_x(lpa);
 }
 
+/**
+ * mii_adv_mod_linkmode_adv_t
+ * @advertising:pointer to destination link mode.
+ * @adv: value of the MII_ADVERTISE register
+ *
+ * A small helper function that translates MII_ADVERTISE bits to
+ * linkmode advertisement settings. Leaves other bits unchanged.
+ */
+static inline void mii_adv_mod_linkmode_adv_t(unsigned long *advertising,
+					      u32 adv)
+{
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
+			 advertising, adv & ADVERTISE_10HALF);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
+			 advertising, adv & ADVERTISE_10FULL);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+			 advertising, adv & ADVERTISE_100HALF);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+			 advertising, adv & ADVERTISE_100FULL);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising,
+			 adv & ADVERTISE_PAUSE_CAP);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+			 advertising, adv & ADVERTISE_PAUSE_ASYM);
+}
+
 /**
  * mii_adv_to_linkmode_adv_t
  * @advertising:pointer to destination link mode.
@@ -386,22 +416,7 @@ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising,
 {
 	linkmode_zero(advertising);
 
-	if (adv & ADVERTISE_10HALF)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
-				 advertising);
-	if (adv & ADVERTISE_10FULL)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
-				 advertising);
-	if (adv & ADVERTISE_100HALF)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
-				 advertising);
-	if (adv & ADVERTISE_100FULL)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
-				 advertising);
-	if (adv & ADVERTISE_PAUSE_CAP)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising);
-	if (adv & ADVERTISE_PAUSE_ASYM)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising);
+	mii_adv_mod_linkmode_adv_t(advertising, adv);
 }
 
 /**
@@ -423,6 +438,27 @@ static inline void mii_lpa_to_linkmode_lpa_t(unsigned long *lp_advertising,
 
 }
 
+/**
+ * mii_lpa_mod_linkmode_lpa_t
+ * @adv: value of the MII_LPA register
+ *
+ * A small helper function that translates MII_LPA bits, when in
+ * 1000Base-T mode, to linkmode LP advertisement settings. Leaves
+ * other bits unchanged.
+ */
+static inline void mii_lpa_mod_linkmode_lpa_t(unsigned long *lp_advertising,
+					      u32 lpa)
+{
+	mii_adv_mod_linkmode_adv_t(lp_advertising, lpa);
+
+	if (lpa & LPA_LPACK)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+				 lp_advertising);
+	else
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+				   lp_advertising);
+}
+
 /**
  * linkmode_adv_to_lcl_adv_t
  * @advertising:pointer to linkmode advertising
-- 
cgit v1.2.3


From 6dbd0090f999c443763c0742b574da1ce189404c Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 5 Dec 2018 21:49:44 +0100
Subject: net: mii: mii_lpa_mod_linkmode_lpa_t: Make use of linkmode_mod_bit
 helper

Replace the if else code structure with a call to the helper
linkmode_mod_bit.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mii.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/include/linux/mii.h b/include/linux/mii.h
index e72447778a08..6fee8b1a4400 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -451,12 +451,8 @@ static inline void mii_lpa_mod_linkmode_lpa_t(unsigned long *lp_advertising,
 {
 	mii_adv_mod_linkmode_adv_t(lp_advertising, lpa);
 
-	if (lpa & LPA_LPACK)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
-				 lp_advertising);
-	else
-		linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
-				   lp_advertising);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+			 lp_advertising, lpa & LPA_LPACK);
 }
 
 /**
-- 
cgit v1.2.3


From 9db299c736eea35ea97dbc9d80a58befc067bcd8 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 5 Dec 2018 21:49:45 +0100
Subject: net: phy: Fix ioctl handler when modifing MII_ADVERTISE

When the MII_ADVERTISE register is modified by the IOCTL handler,
phydev->advertising needs recalculating. Use the _mod_ variant of
mii_adv_to_linkmode_adv_t so that bits outside of the advertise
registers are not cleared.

Fixes: c0ec3c273677 ("net: phy: Convert u32 phydev->lp_advertising to linkmode")
Reported-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index e1a1e54baac2..e24708f1fc16 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -437,8 +437,8 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 				}
 				break;
 			case MII_ADVERTISE:
-				mii_adv_to_linkmode_adv_t(phydev->advertising,
-							  val);
+				mii_adv_mod_linkmode_adv_t(phydev->advertising,
+							   val);
 				change_autoneg = true;
 				break;
 			default:
-- 
cgit v1.2.3


From 19e3a9c90c53479fecaa02307bf2db5ab8b3ffe3 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 5 Dec 2018 15:14:24 +0200
Subject: net: bridge: convert multicast to generic rhashtable

The bridge multicast code currently uses a custom resizable hashtable
which predates the generic rhashtable interface. It has many
shortcomings compared and duplicates functionality that is presently
available via the generic rhashtable, so this patch removes the custom
rhashtable implementation in favor of the kernel's generic rhashtable.
The hash maximum is kept and the rhashtable's size is used to do a loose
check if it's reached in which case we revert to the old behaviour and
disable further bridge multicast processing. Also now we can support any
hash maximum, doesn't need to be a power of 2.

v3: add non-rcu br_mdb_get variant and use it where multicast_lock is
    held to avoid RCU splat, drop hash_max function and just set it
    directly

v2: handle when IGMP snooping is undefined, add br_mdb_init/uninit
    placeholders

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_device.c    |  10 ++
 net/bridge/br_mdb.c       | 120 ++++++--------
 net/bridge/br_multicast.c | 414 ++++++++--------------------------------------
 net/bridge/br_netlink.c   |   9 +-
 net/bridge/br_private.h   |  38 +++--
 net/bridge/br_sysfs_br.c  |   8 +-
 6 files changed, 163 insertions(+), 436 deletions(-)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index c6abf927f0c9..9f41a5d4da3f 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -131,9 +131,17 @@ static int br_dev_init(struct net_device *dev)
 		return err;
 	}
 
+	err = br_mdb_hash_init(br);
+	if (err) {
+		free_percpu(br->stats);
+		br_fdb_hash_fini(br);
+		return err;
+	}
+
 	err = br_vlan_init(br);
 	if (err) {
 		free_percpu(br->stats);
+		br_mdb_hash_fini(br);
 		br_fdb_hash_fini(br);
 		return err;
 	}
@@ -142,6 +150,7 @@ static int br_dev_init(struct net_device *dev)
 	if (err) {
 		free_percpu(br->stats);
 		br_vlan_flush(br);
+		br_mdb_hash_fini(br);
 		br_fdb_hash_fini(br);
 	}
 	br_set_lockdep_class(dev);
@@ -156,6 +165,7 @@ static void br_dev_uninit(struct net_device *dev)
 	br_multicast_dev_del(br);
 	br_multicast_uninit_stats(br);
 	br_vlan_flush(br);
+	br_mdb_hash_fini(br);
 	br_fdb_hash_fini(br);
 	free_percpu(br->stats);
 }
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index a7ea2d431714..ea8abdb56df3 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -78,82 +78,72 @@ static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip)
 static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 			    struct net_device *dev)
 {
+	int idx = 0, s_idx = cb->args[1], err = 0;
 	struct net_bridge *br = netdev_priv(dev);
-	struct net_bridge_mdb_htable *mdb;
+	struct net_bridge_mdb_entry *mp;
 	struct nlattr *nest, *nest2;
-	int i, err = 0;
-	int idx = 0, s_idx = cb->args[1];
 
 	if (!br_opt_get(br, BROPT_MULTICAST_ENABLED))
 		return 0;
 
-	mdb = rcu_dereference(br->mdb);
-	if (!mdb)
-		return 0;
-
 	nest = nla_nest_start(skb, MDBA_MDB);
 	if (nest == NULL)
 		return -EMSGSIZE;
 
-	for (i = 0; i < mdb->max; i++) {
-		struct net_bridge_mdb_entry *mp;
+	hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) {
 		struct net_bridge_port_group *p;
 		struct net_bridge_port_group __rcu **pp;
 		struct net_bridge_port *port;
 
-		hlist_for_each_entry_rcu(mp, &mdb->mhash[i], hlist[mdb->ver]) {
-			if (idx < s_idx)
-				goto skip;
+		if (idx < s_idx)
+			goto skip;
 
-			nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
-			if (nest2 == NULL) {
-				err = -EMSGSIZE;
-				goto out;
-			}
+		nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
+		if (!nest2) {
+			err = -EMSGSIZE;
+			break;
+		}
 
-			for (pp = &mp->ports;
-			     (p = rcu_dereference(*pp)) != NULL;
-			      pp = &p->next) {
-				struct nlattr *nest_ent;
-				struct br_mdb_entry e;
-
-				port = p->port;
-				if (!port)
-					continue;
-
-				memset(&e, 0, sizeof(e));
-				e.ifindex = port->dev->ifindex;
-				e.vid = p->addr.vid;
-				__mdb_entry_fill_flags(&e, p->flags);
-				if (p->addr.proto == htons(ETH_P_IP))
-					e.addr.u.ip4 = p->addr.u.ip4;
+		for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL;
+		      pp = &p->next) {
+			struct nlattr *nest_ent;
+			struct br_mdb_entry e;
+
+			port = p->port;
+			if (!port)
+				continue;
+
+			memset(&e, 0, sizeof(e));
+			e.ifindex = port->dev->ifindex;
+			e.vid = p->addr.vid;
+			__mdb_entry_fill_flags(&e, p->flags);
+			if (p->addr.proto == htons(ETH_P_IP))
+				e.addr.u.ip4 = p->addr.u.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
-				if (p->addr.proto == htons(ETH_P_IPV6))
-					e.addr.u.ip6 = p->addr.u.ip6;
+			if (p->addr.proto == htons(ETH_P_IPV6))
+				e.addr.u.ip6 = p->addr.u.ip6;
 #endif
-				e.addr.proto = p->addr.proto;
-				nest_ent = nla_nest_start(skb,
-							  MDBA_MDB_ENTRY_INFO);
-				if (!nest_ent) {
-					nla_nest_cancel(skb, nest2);
-					err = -EMSGSIZE;
-					goto out;
-				}
-				if (nla_put_nohdr(skb, sizeof(e), &e) ||
-				    nla_put_u32(skb,
-						MDBA_MDB_EATTR_TIMER,
-						br_timer_value(&p->timer))) {
-					nla_nest_cancel(skb, nest_ent);
-					nla_nest_cancel(skb, nest2);
-					err = -EMSGSIZE;
-					goto out;
-				}
-				nla_nest_end(skb, nest_ent);
+			e.addr.proto = p->addr.proto;
+			nest_ent = nla_nest_start(skb, MDBA_MDB_ENTRY_INFO);
+			if (!nest_ent) {
+				nla_nest_cancel(skb, nest2);
+				err = -EMSGSIZE;
+				goto out;
 			}
-			nla_nest_end(skb, nest2);
-		skip:
-			idx++;
+			if (nla_put_nohdr(skb, sizeof(e), &e) ||
+			    nla_put_u32(skb,
+					MDBA_MDB_EATTR_TIMER,
+					br_timer_value(&p->timer))) {
+				nla_nest_cancel(skb, nest_ent);
+				nla_nest_cancel(skb, nest2);
+				err = -EMSGSIZE;
+				goto out;
+			}
+			nla_nest_end(skb, nest_ent);
 		}
+		nla_nest_end(skb, nest2);
+skip:
+		idx++;
 	}
 
 out:
@@ -203,8 +193,7 @@ static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 
-	/* In theory this could be wrapped to 0... */
-	cb->seq = net->dev_base_seq + br_mdb_rehash_seq;
+	cb->seq = net->dev_base_seq;
 
 	for_each_netdev_rcu(net, dev) {
 		if (dev->priv_flags & IFF_EBRIDGE) {
@@ -297,7 +286,6 @@ static void br_mdb_complete(struct net_device *dev, int err, void *priv)
 	struct br_mdb_complete_info *data = priv;
 	struct net_bridge_port_group __rcu **pp;
 	struct net_bridge_port_group *p;
-	struct net_bridge_mdb_htable *mdb;
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port *port = data->port;
 	struct net_bridge *br = port->br;
@@ -306,8 +294,7 @@ static void br_mdb_complete(struct net_device *dev, int err, void *priv)
 		goto err;
 
 	spin_lock_bh(&br->multicast_lock);
-	mdb = mlock_dereference(br->mdb, br);
-	mp = br_mdb_ip_get(mdb, &data->ip);
+	mp = br_mdb_ip_get(br, &data->ip);
 	if (!mp)
 		goto out;
 	for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
@@ -588,14 +575,12 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
-	struct net_bridge_mdb_htable *mdb;
 	unsigned long now = jiffies;
 	int err;
 
-	mdb = mlock_dereference(br->mdb, br);
-	mp = br_mdb_ip_get(mdb, group);
+	mp = br_mdb_ip_get(br, group);
 	if (!mp) {
-		mp = br_multicast_new_group(br, port, group);
+		mp = br_multicast_new_group(br, group);
 		err = PTR_ERR_OR_ZERO(mp);
 		if (err)
 			return err;
@@ -696,7 +681,6 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 {
-	struct net_bridge_mdb_htable *mdb;
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
@@ -709,9 +693,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 	__mdb_entry_to_br_ip(entry, &ip);
 
 	spin_lock_bh(&br->multicast_lock);
-	mdb = mlock_dereference(br->mdb, br);
-
-	mp = br_mdb_ip_get(mdb, &ip);
+	mp = br_mdb_ip_get(br, &ip);
 	if (!mp)
 		goto unlock;
 
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 6bac0d6b7b94..83a5931a7784 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -37,6 +37,14 @@
 
 #include "br_private.h"
 
+static const struct rhashtable_params br_mdb_rht_params = {
+	.head_offset = offsetof(struct net_bridge_mdb_entry, rhnode),
+	.key_offset = offsetof(struct net_bridge_mdb_entry, addr),
+	.key_len = sizeof(struct br_ip),
+	.automatic_shrinking = true,
+	.locks_mul = 1,
+};
+
 static void br_multicast_start_querier(struct net_bridge *br,
 				       struct bridge_mcast_own_query *query);
 static void br_multicast_add_router(struct net_bridge *br,
@@ -54,7 +62,6 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 					 const struct in6_addr *group,
 					 __u16 vid, const unsigned char *src);
 #endif
-unsigned int br_mdb_rehash_seq;
 
 static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
 {
@@ -73,89 +80,58 @@ static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
 	return 0;
 }
 
-static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip,
-				__u16 vid)
-{
-	return jhash_2words((__force u32)ip, vid, mdb->secret) & (mdb->max - 1);
-}
-
-#if IS_ENABLED(CONFIG_IPV6)
-static inline int __br_ip6_hash(struct net_bridge_mdb_htable *mdb,
-				const struct in6_addr *ip,
-				__u16 vid)
+static struct net_bridge_mdb_entry *br_mdb_ip_get_rcu(struct net_bridge *br,
+						      struct br_ip *dst)
 {
-	return jhash_2words(ipv6_addr_hash(ip), vid,
-			    mdb->secret) & (mdb->max - 1);
+	return rhashtable_lookup(&br->mdb_hash_tbl, dst, br_mdb_rht_params);
 }
-#endif
 
-static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb,
-			     struct br_ip *ip)
-{
-	switch (ip->proto) {
-	case htons(ETH_P_IP):
-		return __br_ip4_hash(mdb, ip->u.ip4, ip->vid);
-#if IS_ENABLED(CONFIG_IPV6)
-	case htons(ETH_P_IPV6):
-		return __br_ip6_hash(mdb, &ip->u.ip6, ip->vid);
-#endif
-	}
-	return 0;
-}
-
-static struct net_bridge_mdb_entry *__br_mdb_ip_get(
-	struct net_bridge_mdb_htable *mdb, struct br_ip *dst, int hash)
+struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge *br,
+					   struct br_ip *dst)
 {
-	struct net_bridge_mdb_entry *mp;
-
-	hlist_for_each_entry_rcu(mp, &mdb->mhash[hash], hlist[mdb->ver]) {
-		if (br_ip_equal(&mp->addr, dst))
-			return mp;
-	}
+	struct net_bridge_mdb_entry *ent;
 
-	return NULL;
-}
+	lockdep_assert_held_once(&br->multicast_lock);
 
-struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge_mdb_htable *mdb,
-					   struct br_ip *dst)
-{
-	if (!mdb)
-		return NULL;
+	rcu_read_lock();
+	ent = rhashtable_lookup(&br->mdb_hash_tbl, dst, br_mdb_rht_params);
+	rcu_read_unlock();
 
-	return __br_mdb_ip_get(mdb, dst, br_ip_hash(mdb, dst));
+	return ent;
 }
 
-static struct net_bridge_mdb_entry *br_mdb_ip4_get(
-	struct net_bridge_mdb_htable *mdb, __be32 dst, __u16 vid)
+static struct net_bridge_mdb_entry *br_mdb_ip4_get(struct net_bridge *br,
+						   __be32 dst, __u16 vid)
 {
 	struct br_ip br_dst;
 
+	memset(&br_dst, 0, sizeof(br_dst));
 	br_dst.u.ip4 = dst;
 	br_dst.proto = htons(ETH_P_IP);
 	br_dst.vid = vid;
 
-	return br_mdb_ip_get(mdb, &br_dst);
+	return br_mdb_ip_get(br, &br_dst);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static struct net_bridge_mdb_entry *br_mdb_ip6_get(
-	struct net_bridge_mdb_htable *mdb, const struct in6_addr *dst,
-	__u16 vid)
+static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br,
+						   const struct in6_addr *dst,
+						   __u16 vid)
 {
 	struct br_ip br_dst;
 
+	memset(&br_dst, 0, sizeof(br_dst));
 	br_dst.u.ip6 = *dst;
 	br_dst.proto = htons(ETH_P_IPV6);
 	br_dst.vid = vid;
 
-	return br_mdb_ip_get(mdb, &br_dst);
+	return br_mdb_ip_get(br, &br_dst);
 }
 #endif
 
 struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 					struct sk_buff *skb, u16 vid)
 {
-	struct net_bridge_mdb_htable *mdb = rcu_dereference(br->mdb);
 	struct br_ip ip;
 
 	if (!br_opt_get(br, BROPT_MULTICAST_ENABLED))
@@ -164,6 +140,7 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 	if (BR_INPUT_SKB_CB(skb)->igmp)
 		return NULL;
 
+	memset(&ip, 0, sizeof(ip));
 	ip.proto = skb->protocol;
 	ip.vid = vid;
 
@@ -180,47 +157,7 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 		return NULL;
 	}
 
-	return br_mdb_ip_get(mdb, &ip);
-}
-
-static void br_mdb_free(struct rcu_head *head)
-{
-	struct net_bridge_mdb_htable *mdb =
-		container_of(head, struct net_bridge_mdb_htable, rcu);
-	struct net_bridge_mdb_htable *old = mdb->old;
-
-	mdb->old = NULL;
-	kfree(old->mhash);
-	kfree(old);
-}
-
-static int br_mdb_copy(struct net_bridge_mdb_htable *new,
-		       struct net_bridge_mdb_htable *old,
-		       int elasticity)
-{
-	struct net_bridge_mdb_entry *mp;
-	int maxlen;
-	int len;
-	int i;
-
-	for (i = 0; i < old->max; i++)
-		hlist_for_each_entry(mp, &old->mhash[i], hlist[old->ver])
-			hlist_add_head(&mp->hlist[new->ver],
-				       &new->mhash[br_ip_hash(new, &mp->addr)]);
-
-	if (!elasticity)
-		return 0;
-
-	maxlen = 0;
-	for (i = 0; i < new->max; i++) {
-		len = 0;
-		hlist_for_each_entry(mp, &new->mhash[i], hlist[new->ver])
-			len++;
-		if (len > maxlen)
-			maxlen = len;
-	}
-
-	return maxlen > elasticity ? -EINVAL : 0;
+	return br_mdb_ip_get_rcu(br, &ip);
 }
 
 void br_multicast_free_pg(struct rcu_head *head)
@@ -243,7 +180,6 @@ static void br_multicast_group_expired(struct timer_list *t)
 {
 	struct net_bridge_mdb_entry *mp = from_timer(mp, t, timer);
 	struct net_bridge *br = mp->br;
-	struct net_bridge_mdb_htable *mdb;
 
 	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) || timer_pending(&mp->timer))
@@ -255,10 +191,9 @@ static void br_multicast_group_expired(struct timer_list *t)
 	if (mp->ports)
 		goto out;
 
-	mdb = mlock_dereference(br->mdb, br);
-
-	hlist_del_rcu(&mp->hlist[mdb->ver]);
-	mdb->size--;
+	rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode,
+			       br_mdb_rht_params);
+	hlist_del_rcu(&mp->mdb_node);
 
 	call_rcu_bh(&mp->rcu, br_multicast_free_group);
 
@@ -269,14 +204,11 @@ out:
 static void br_multicast_del_pg(struct net_bridge *br,
 				struct net_bridge_port_group *pg)
 {
-	struct net_bridge_mdb_htable *mdb;
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
 
-	mdb = mlock_dereference(br->mdb, br);
-
-	mp = br_mdb_ip_get(mdb, &pg->addr);
+	mp = br_mdb_ip_get(br, &pg->addr);
 	if (WARN_ON(!mp))
 		return;
 
@@ -319,53 +251,6 @@ out:
 	spin_unlock(&br->multicast_lock);
 }
 
-static int br_mdb_rehash(struct net_bridge_mdb_htable __rcu **mdbp, int max,
-			 int elasticity)
-{
-	struct net_bridge_mdb_htable *old = rcu_dereference_protected(*mdbp, 1);
-	struct net_bridge_mdb_htable *mdb;
-	int err;
-
-	mdb = kmalloc(sizeof(*mdb), GFP_ATOMIC);
-	if (!mdb)
-		return -ENOMEM;
-
-	mdb->max = max;
-	mdb->old = old;
-
-	mdb->mhash = kcalloc(max, sizeof(*mdb->mhash), GFP_ATOMIC);
-	if (!mdb->mhash) {
-		kfree(mdb);
-		return -ENOMEM;
-	}
-
-	mdb->size = old ? old->size : 0;
-	mdb->ver = old ? old->ver ^ 1 : 0;
-
-	if (!old || elasticity)
-		get_random_bytes(&mdb->secret, sizeof(mdb->secret));
-	else
-		mdb->secret = old->secret;
-
-	if (!old)
-		goto out;
-
-	err = br_mdb_copy(mdb, old, elasticity);
-	if (err) {
-		kfree(mdb->mhash);
-		kfree(mdb);
-		return err;
-	}
-
-	br_mdb_rehash_seq++;
-	call_rcu_bh(&mdb->rcu, br_mdb_free);
-
-out:
-	rcu_assign_pointer(*mdbp, mdb);
-
-	return 0;
-}
-
 static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
 						    __be32 group,
 						    u8 *igmp_type)
@@ -589,111 +474,19 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
 	return NULL;
 }
 
-static struct net_bridge_mdb_entry *br_multicast_get_group(
-	struct net_bridge *br, struct net_bridge_port *port,
-	struct br_ip *group, int hash)
-{
-	struct net_bridge_mdb_htable *mdb;
-	struct net_bridge_mdb_entry *mp;
-	unsigned int count = 0;
-	unsigned int max;
-	int elasticity;
-	int err;
-
-	mdb = rcu_dereference_protected(br->mdb, 1);
-	hlist_for_each_entry(mp, &mdb->mhash[hash], hlist[mdb->ver]) {
-		count++;
-		if (unlikely(br_ip_equal(group, &mp->addr)))
-			return mp;
-	}
-
-	elasticity = 0;
-	max = mdb->max;
-
-	if (unlikely(count > br->hash_elasticity && count)) {
-		if (net_ratelimit())
-			br_info(br, "Multicast hash table "
-				"chain limit reached: %s\n",
-				port ? port->dev->name : br->dev->name);
-
-		elasticity = br->hash_elasticity;
-	}
-
-	if (mdb->size >= max) {
-		max *= 2;
-		if (unlikely(max > br->hash_max)) {
-			br_warn(br, "Multicast hash table maximum of %d "
-				"reached, disabling snooping: %s\n",
-				br->hash_max,
-				port ? port->dev->name : br->dev->name);
-			err = -E2BIG;
-disable:
-			br_opt_toggle(br, BROPT_MULTICAST_ENABLED, false);
-			goto err;
-		}
-	}
-
-	if (max > mdb->max || elasticity) {
-		if (mdb->old) {
-			if (net_ratelimit())
-				br_info(br, "Multicast hash table "
-					"on fire: %s\n",
-					port ? port->dev->name : br->dev->name);
-			err = -EEXIST;
-			goto err;
-		}
-
-		err = br_mdb_rehash(&br->mdb, max, elasticity);
-		if (err) {
-			br_warn(br, "Cannot rehash multicast "
-				"hash table, disabling snooping: %s, %d, %d\n",
-				port ? port->dev->name : br->dev->name,
-				mdb->size, err);
-			goto disable;
-		}
-
-		err = -EAGAIN;
-		goto err;
-	}
-
-	return NULL;
-
-err:
-	mp = ERR_PTR(err);
-	return mp;
-}
-
 struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br,
-						    struct net_bridge_port *p,
 						    struct br_ip *group)
 {
-	struct net_bridge_mdb_htable *mdb;
 	struct net_bridge_mdb_entry *mp;
-	int hash;
 	int err;
 
-	mdb = rcu_dereference_protected(br->mdb, 1);
-	if (!mdb) {
-		err = br_mdb_rehash(&br->mdb, BR_HASH_SIZE, 0);
-		if (err)
-			return ERR_PTR(err);
-		goto rehash;
-	}
-
-	hash = br_ip_hash(mdb, group);
-	mp = br_multicast_get_group(br, p, group, hash);
-	switch (PTR_ERR(mp)) {
-	case 0:
-		break;
+	mp = br_mdb_ip_get(br, group);
+	if (mp)
+		return mp;
 
-	case -EAGAIN:
-rehash:
-		mdb = rcu_dereference_protected(br->mdb, 1);
-		hash = br_ip_hash(mdb, group);
-		break;
-
-	default:
-		goto out;
+	if (atomic_read(&br->mdb_hash_tbl.nelems) >= br->hash_max) {
+		br_opt_toggle(br, BROPT_MULTICAST_ENABLED, false);
+		return ERR_PTR(-E2BIG);
 	}
 
 	mp = kzalloc(sizeof(*mp), GFP_ATOMIC);
@@ -703,11 +496,15 @@ rehash:
 	mp->br = br;
 	mp->addr = *group;
 	timer_setup(&mp->timer, br_multicast_group_expired, 0);
+	err = rhashtable_lookup_insert_fast(&br->mdb_hash_tbl, &mp->rhnode,
+					    br_mdb_rht_params);
+	if (err) {
+		kfree(mp);
+		mp = ERR_PTR(err);
+	} else {
+		hlist_add_head_rcu(&mp->mdb_node, &br->mdb_list);
+	}
 
-	hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]);
-	mdb->size++;
-
-out:
 	return mp;
 }
 
@@ -768,7 +565,7 @@ static int br_multicast_add_group(struct net_bridge *br,
 	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
-	mp = br_multicast_new_group(br, port, group);
+	mp = br_multicast_new_group(br, group);
 	err = PTR_ERR(mp);
 	if (IS_ERR(mp))
 		goto err;
@@ -837,6 +634,7 @@ static int br_ip6_multicast_add_group(struct net_bridge *br,
 	if (ipv6_addr_is_ll_all_nodes(group))
 		return 0;
 
+	memset(&br_group, 0, sizeof(br_group));
 	br_group.u.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
@@ -1483,7 +1281,7 @@ static void br_ip4_multicast_query(struct net_bridge *br,
 		goto out;
 	}
 
-	mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group, vid);
+	mp = br_mdb_ip4_get(br, group, vid);
 	if (!mp)
 		goto out;
 
@@ -1567,7 +1365,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 		goto out;
 	}
 
-	mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group, vid);
+	mp = br_mdb_ip6_get(br, group, vid);
 	if (!mp)
 		goto out;
 
@@ -1601,7 +1399,6 @@ br_multicast_leave_group(struct net_bridge *br,
 			 struct bridge_mcast_own_query *own_query,
 			 const unsigned char *src)
 {
-	struct net_bridge_mdb_htable *mdb;
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port_group *p;
 	unsigned long now;
@@ -1612,8 +1409,7 @@ br_multicast_leave_group(struct net_bridge *br,
 	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
-	mdb = mlock_dereference(br->mdb, br);
-	mp = br_mdb_ip_get(mdb, group);
+	mp = br_mdb_ip_get(br, group);
 	if (!mp)
 		goto out;
 
@@ -1999,6 +1795,7 @@ void br_multicast_init(struct net_bridge *br)
 	timer_setup(&br->ip6_own_query.timer,
 		    br_ip6_multicast_query_expired, 0);
 #endif
+	INIT_HLIST_HEAD(&br->mdb_list);
 }
 
 static void __br_multicast_open(struct net_bridge *br,
@@ -2033,40 +1830,20 @@ void br_multicast_stop(struct net_bridge *br)
 
 void br_multicast_dev_del(struct net_bridge *br)
 {
-	struct net_bridge_mdb_htable *mdb;
 	struct net_bridge_mdb_entry *mp;
-	struct hlist_node *n;
-	u32 ver;
-	int i;
+	struct hlist_node *tmp;
 
 	spin_lock_bh(&br->multicast_lock);
-	mdb = mlock_dereference(br->mdb, br);
-	if (!mdb)
-		goto out;
-
-	br->mdb = NULL;
-
-	ver = mdb->ver;
-	for (i = 0; i < mdb->max; i++) {
-		hlist_for_each_entry_safe(mp, n, &mdb->mhash[i],
-					  hlist[ver]) {
-			del_timer(&mp->timer);
-			call_rcu_bh(&mp->rcu, br_multicast_free_group);
-		}
-	}
-
-	if (mdb->old) {
-		spin_unlock_bh(&br->multicast_lock);
-		rcu_barrier_bh();
-		spin_lock_bh(&br->multicast_lock);
-		WARN_ON(mdb->old);
+	hlist_for_each_entry_safe(mp, tmp, &br->mdb_list, mdb_node) {
+		del_timer(&mp->timer);
+		rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode,
+				       br_mdb_rht_params);
+		hlist_del_rcu(&mp->mdb_node);
+		call_rcu_bh(&mp->rcu, br_multicast_free_group);
 	}
-
-	mdb->old = mdb;
-	call_rcu_bh(&mdb->rcu, br_mdb_free);
-
-out:
 	spin_unlock_bh(&br->multicast_lock);
+
+	rcu_barrier_bh();
 }
 
 int br_multicast_set_router(struct net_bridge *br, unsigned long val)
@@ -2176,7 +1953,6 @@ static void br_multicast_start_querier(struct net_bridge *br,
 
 int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 {
-	struct net_bridge_mdb_htable *mdb;
 	struct net_bridge_port *port;
 	int err = 0;
 
@@ -2192,21 +1968,6 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 	if (!netif_running(br->dev))
 		goto unlock;
 
-	mdb = mlock_dereference(br->mdb, br);
-	if (mdb) {
-		if (mdb->old) {
-			err = -EEXIST;
-rollback:
-			br_opt_toggle(br, BROPT_MULTICAST_ENABLED, false);
-			goto unlock;
-		}
-
-		err = br_mdb_rehash(&br->mdb, mdb->max,
-				    br->hash_elasticity);
-		if (err)
-			goto rollback;
-	}
-
 	br_multicast_open(br);
 	list_for_each_entry(port, &br->port_list, list)
 		__br_multicast_enable_port(port);
@@ -2271,45 +2032,6 @@ unlock:
 	return 0;
 }
 
-int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val)
-{
-	int err = -EINVAL;
-	u32 old;
-	struct net_bridge_mdb_htable *mdb;
-
-	spin_lock_bh(&br->multicast_lock);
-	if (!is_power_of_2(val))
-		goto unlock;
-
-	mdb = mlock_dereference(br->mdb, br);
-	if (mdb && val < mdb->size)
-		goto unlock;
-
-	err = 0;
-
-	old = br->hash_max;
-	br->hash_max = val;
-
-	if (mdb) {
-		if (mdb->old) {
-			err = -EEXIST;
-rollback:
-			br->hash_max = old;
-			goto unlock;
-		}
-
-		err = br_mdb_rehash(&br->mdb, br->hash_max,
-				    br->hash_elasticity);
-		if (err)
-			goto rollback;
-	}
-
-unlock:
-	spin_unlock_bh(&br->multicast_lock);
-
-	return err;
-}
-
 int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val)
 {
 	/* Currently we support only version 2 and 3 */
@@ -2646,3 +2368,13 @@ void br_multicast_get_stats(const struct net_bridge *br,
 	}
 	memcpy(dest, &tdst, sizeof(*dest));
 }
+
+int br_mdb_hash_init(struct net_bridge *br)
+{
+	return rhashtable_init(&br->mdb_hash_tbl, &br_mdb_rht_params);
+}
+
+void br_mdb_hash_fini(struct net_bridge *br)
+{
+	rhashtable_destroy(&br->mdb_hash_tbl);
+}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 13cd50326af2..063da636cb82 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1195,13 +1195,8 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 		br->hash_elasticity = val;
 	}
 
-	if (data[IFLA_BR_MCAST_HASH_MAX]) {
-		u32 hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]);
-
-		err = br_multicast_set_hash_max(br, hash_max);
-		if (err)
-			return err;
-	}
+	if (data[IFLA_BR_MCAST_HASH_MAX])
+		br->hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]);
 
 	if (data[IFLA_BR_MCAST_LAST_MEMBER_CNT]) {
 		u32 val = nla_get_u32(data[IFLA_BR_MCAST_LAST_MEMBER_CNT]);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index d29f837cd7a2..a0ce0822921c 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -213,23 +213,14 @@ struct net_bridge_port_group {
 };
 
 struct net_bridge_mdb_entry {
-	struct hlist_node		hlist[2];
+	struct rhash_head		rhnode;
 	struct net_bridge		*br;
 	struct net_bridge_port_group __rcu *ports;
 	struct rcu_head			rcu;
 	struct timer_list		timer;
 	struct br_ip			addr;
 	bool				host_joined;
-};
-
-struct net_bridge_mdb_htable {
-	struct hlist_head		*mhash;
-	struct rcu_head			rcu;
-	struct net_bridge_mdb_htable	*old;
-	u32				size;
-	u32				max;
-	u32				secret;
-	u32				ver;
+	struct hlist_node		mdb_node;
 };
 
 struct net_bridge_port {
@@ -400,7 +391,9 @@ struct net_bridge {
 	unsigned long			multicast_query_response_interval;
 	unsigned long			multicast_startup_query_interval;
 
-	struct net_bridge_mdb_htable __rcu *mdb;
+	struct rhashtable		mdb_hash_tbl;
+
+	struct hlist_head		mdb_list;
 	struct hlist_head		router_list;
 
 	struct timer_list		multicast_router_timer;
@@ -659,7 +652,6 @@ int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd,
 
 /* br_multicast.c */
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
-extern unsigned int br_mdb_rehash_seq;
 int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
 		     struct sk_buff *skb, u16 vid);
 struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
@@ -684,17 +676,16 @@ int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val);
 int br_multicast_set_mld_version(struct net_bridge *br, unsigned long val);
 #endif
 struct net_bridge_mdb_entry *
-br_mdb_ip_get(struct net_bridge_mdb_htable *mdb, struct br_ip *dst);
+br_mdb_ip_get(struct net_bridge *br, struct br_ip *dst);
 struct net_bridge_mdb_entry *
-br_multicast_new_group(struct net_bridge *br, struct net_bridge_port *port,
-		       struct br_ip *group);
+br_multicast_new_group(struct net_bridge *br, struct br_ip *group);
 void br_multicast_free_pg(struct rcu_head *head);
 struct net_bridge_port_group *
 br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group,
 			    struct net_bridge_port_group __rcu *next,
 			    unsigned char flags, const unsigned char *src);
-void br_mdb_init(void);
-void br_mdb_uninit(void);
+int br_mdb_hash_init(struct net_bridge *br);
+void br_mdb_hash_fini(struct net_bridge *br);
 void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
 		   struct br_ip *group, int type, u8 flags);
 void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port,
@@ -706,6 +697,8 @@ void br_multicast_uninit_stats(struct net_bridge *br);
 void br_multicast_get_stats(const struct net_bridge *br,
 			    const struct net_bridge_port *p,
 			    struct br_mcast_stats *dest);
+void br_mdb_init(void);
+void br_mdb_uninit(void);
 
 #define mlock_dereference(X, br) \
 	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
@@ -831,6 +824,15 @@ static inline void br_mdb_uninit(void)
 {
 }
 
+static inline int br_mdb_hash_init(struct net_bridge *br)
+{
+	return 0;
+}
+
+static inline void br_mdb_hash_fini(struct net_bridge *br)
+{
+}
+
 static inline void br_multicast_count(struct net_bridge *br,
 				      const struct net_bridge_port *p,
 				      const struct sk_buff *skb,
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index 6a378a7e16ea..f164cda30fe2 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -449,10 +449,16 @@ static ssize_t hash_max_show(struct device *d, struct device_attribute *attr,
 	return sprintf(buf, "%u\n", br->hash_max);
 }
 
+static int set_hash_max(struct net_bridge *br, unsigned long val)
+{
+	br->hash_max = val;
+	return 0;
+}
+
 static ssize_t hash_max_store(struct device *d, struct device_attribute *attr,
 			      const char *buf, size_t len)
 {
-	return store_bridge_parm(d, buf, len, br_multicast_set_hash_max);
+	return store_bridge_parm(d, buf, len, set_hash_max);
 }
 static DEVICE_ATTR_RW(hash_max);
 
-- 
cgit v1.2.3


From 4329596cb10d23c9e22c78e676a3667ef28ed62f Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 5 Dec 2018 15:14:25 +0200
Subject: net: bridge: multicast: use non-bh rcu flavor

The bridge multicast code has been using a mix of RCU and RCU-bh flavors
sometimes in questionable way. Since we've moved to rhashtable just use
non-bh RCU everywhere. In addition this simplifies freeing of objects
and allows us to remove some unnecessary callback functions.

v3: new patch

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c       |  2 +-
 net/bridge/br_multicast.c | 26 +++++---------------------
 net/bridge/br_private.h   |  1 -
 3 files changed, 6 insertions(+), 23 deletions(-)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index ea8abdb56df3..79d4c9d253e0 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -710,7 +710,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 		rcu_assign_pointer(*pp, p->next);
 		hlist_del_init(&p->mglist);
 		del_timer(&p->timer);
-		call_rcu_bh(&p->rcu, br_multicast_free_pg);
+		kfree_rcu(p, rcu);
 		err = 0;
 
 		if (!mp->ports && !mp->host_joined &&
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 83a5931a7784..5b8cfef8bc4d 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -160,22 +160,6 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 	return br_mdb_ip_get_rcu(br, &ip);
 }
 
-void br_multicast_free_pg(struct rcu_head *head)
-{
-	struct net_bridge_port_group *p =
-		container_of(head, struct net_bridge_port_group, rcu);
-
-	kfree(p);
-}
-
-static void br_multicast_free_group(struct rcu_head *head)
-{
-	struct net_bridge_mdb_entry *mp =
-		container_of(head, struct net_bridge_mdb_entry, rcu);
-
-	kfree(mp);
-}
-
 static void br_multicast_group_expired(struct timer_list *t)
 {
 	struct net_bridge_mdb_entry *mp = from_timer(mp, t, timer);
@@ -195,7 +179,7 @@ static void br_multicast_group_expired(struct timer_list *t)
 			       br_mdb_rht_params);
 	hlist_del_rcu(&mp->mdb_node);
 
-	call_rcu_bh(&mp->rcu, br_multicast_free_group);
+	kfree_rcu(mp, rcu);
 
 out:
 	spin_unlock(&br->multicast_lock);
@@ -223,7 +207,7 @@ static void br_multicast_del_pg(struct net_bridge *br,
 		del_timer(&p->timer);
 		br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB,
 			      p->flags);
-		call_rcu_bh(&p->rcu, br_multicast_free_pg);
+		kfree_rcu(p, rcu);
 
 		if (!mp->ports && !mp->host_joined &&
 		    netif_running(br->dev))
@@ -1425,7 +1409,7 @@ br_multicast_leave_group(struct net_bridge *br,
 			rcu_assign_pointer(*pp, p->next);
 			hlist_del_init(&p->mglist);
 			del_timer(&p->timer);
-			call_rcu_bh(&p->rcu, br_multicast_free_pg);
+			kfree_rcu(p, rcu);
 			br_mdb_notify(br->dev, port, group, RTM_DELMDB,
 				      p->flags);
 
@@ -1839,11 +1823,11 @@ void br_multicast_dev_del(struct net_bridge *br)
 		rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode,
 				       br_mdb_rht_params);
 		hlist_del_rcu(&mp->mdb_node);
-		call_rcu_bh(&mp->rcu, br_multicast_free_group);
+		kfree_rcu(mp, rcu);
 	}
 	spin_unlock_bh(&br->multicast_lock);
 
-	rcu_barrier_bh();
+	rcu_barrier();
 }
 
 int br_multicast_set_router(struct net_bridge *br, unsigned long val)
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index a0ce0822921c..cf1f7365deb3 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -679,7 +679,6 @@ struct net_bridge_mdb_entry *
 br_mdb_ip_get(struct net_bridge *br, struct br_ip *dst);
 struct net_bridge_mdb_entry *
 br_multicast_new_group(struct net_bridge *br, struct br_ip *group);
-void br_multicast_free_pg(struct rcu_head *head);
 struct net_bridge_port_group *
 br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group,
 			    struct net_bridge_port_group __rcu *next,
-- 
cgit v1.2.3


From cf332bca56f4981cad19027f037fb4d661dcb172 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 5 Dec 2018 15:14:26 +0200
Subject: net: bridge: mark hash_elasticity as obsolete

Now that the bridge multicast uses the generic rhashtable interface we
can drop the hash_elasticity option as that is already done for us and
it's hardcoded to a maximum of RHT_ELASTICITY (16 currently). Add a
warning about the obsolete option when the hash_elasticity is set.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c |  1 -
 net/bridge/br_netlink.c   | 11 ++++-------
 net/bridge/br_private.h   |  1 -
 net/bridge/br_sysfs_br.c  |  6 +++---
 4 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 5b8cfef8bc4d..804ee15c45c1 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1741,7 +1741,6 @@ static void br_ip6_multicast_query_expired(struct timer_list *t)
 
 void br_multicast_init(struct net_bridge *br)
 {
-	br->hash_elasticity = 4;
 	br->hash_max = 512;
 
 	br->multicast_router = MDB_RTR_TYPE_TEMP_QUERY;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 063da636cb82..ff2c10d47529 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1189,11 +1189,9 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 			return err;
 	}
 
-	if (data[IFLA_BR_MCAST_HASH_ELASTICITY]) {
-		u32 val = nla_get_u32(data[IFLA_BR_MCAST_HASH_ELASTICITY]);
-
-		br->hash_elasticity = val;
-	}
+	if (data[IFLA_BR_MCAST_HASH_ELASTICITY])
+		br_warn(br, "the hash_elasticity option has been deprecated and is always %u\n",
+			RHT_ELASTICITY);
 
 	if (data[IFLA_BR_MCAST_HASH_MAX])
 		br->hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]);
@@ -1452,8 +1450,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 		       br_opt_get(br, BROPT_MULTICAST_QUERIER)) ||
 	    nla_put_u8(skb, IFLA_BR_MCAST_STATS_ENABLED,
 		       br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)) ||
-	    nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY,
-			br->hash_elasticity) ||
+	    nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, RHT_ELASTICITY) ||
 	    nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) ||
 	    nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT,
 			br->multicast_last_member_count) ||
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index cf1f7365deb3..ba50fa437a94 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -372,7 +372,6 @@ struct net_bridge {
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 
-	u32				hash_elasticity;
 	u32				hash_max;
 
 	u32				multicast_last_member_count;
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index f164cda30fe2..b05b94e9c595 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -424,13 +424,13 @@ static DEVICE_ATTR_RW(multicast_querier);
 static ssize_t hash_elasticity_show(struct device *d,
 				    struct device_attribute *attr, char *buf)
 {
-	struct net_bridge *br = to_bridge(d);
-	return sprintf(buf, "%u\n", br->hash_elasticity);
+	return sprintf(buf, "%u\n", RHT_ELASTICITY);
 }
 
 static int set_elasticity(struct net_bridge *br, unsigned long val)
 {
-	br->hash_elasticity = val;
+	br_warn(br, "the hash_elasticity option has been deprecated and is always %u\n",
+		RHT_ELASTICITY);
 	return 0;
 }
 
-- 
cgit v1.2.3


From d08c6bc08f72f74cd37f6b7954e3f708005518f9 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 5 Dec 2018 15:14:27 +0200
Subject: net: bridge: increase multicast's default maximum number of entries

bridge's default hash_max was 512 which is rather conservative, now that
we're using the generic rhashtable API which autoshrinks let's increase
it to 4096 and move it to a define in br_private.h.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 2 +-
 net/bridge/br_private.h   | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 804ee15c45c1..879cd2315769 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1741,7 +1741,7 @@ static void br_ip6_multicast_query_expired(struct timer_list *t)
 
 void br_multicast_init(struct net_bridge *br)
 {
-	br->hash_max = 512;
+	br->hash_max = BR_MULTICAST_DEFAULT_HASH_MAX;
 
 	br->multicast_router = MDB_RTR_TYPE_TEMP_QUERY;
 	br->multicast_last_member_count = 2;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index ba50fa437a94..5719b4d3e466 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -31,6 +31,8 @@
 #define BR_PORT_BITS	10
 #define BR_MAX_PORTS	(1<<BR_PORT_BITS)
 
+#define BR_MULTICAST_DEFAULT_HASH_MAX 4096
+
 #define BR_VERSION	"2.3"
 
 /* Control of forwarding link local multicast */
-- 
cgit v1.2.3


From 7337224fc150b3b762190425399ac0e8dee380d1 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 5 Dec 2018 17:35:43 -0800
Subject: bpf: Improve the info.func_info and info.func_info_rec_size behavior

1) When bpf_dump_raw_ok() == false and the kernel can provide >=1
   func_info to the userspace, the current behavior is setting
   the info.func_info_cnt to 0 instead of setting info.func_info
   to 0.

   It is different from the behavior in jited_func_lens/nr_jited_func_lens,
   jited_ksyms/nr_jited_ksyms...etc.

   This patch fixes it. (i.e. set func_info to 0 instead of
   func_info_cnt to 0 when bpf_dump_raw_ok() == false).

2) When the userspace passed in info.func_info_cnt == 0, the kernel
   will set the expected func_info size back to the
   info.func_info_rec_size.  It is a way for the userspace to learn
   the kernel expected func_info_rec_size introduced in
   commit 838e96904ff3 ("bpf: Introduce bpf_func_info").

   An exception is the kernel expected size is not set when
   func_info is not available for a bpf_prog.  This makes the
   returned info.func_info_rec_size has different values
   depending on the returned value of info.func_info_cnt.

   This patch sets the kernel expected size to info.func_info_rec_size
   independent of the info.func_info_cnt.

3) The current logic only rejects invalid func_info_rec_size if
   func_info_cnt is non zero.  This patch also rejects invalid
   nonzero info.func_info_rec_size and not equal to the kernel
   expected size.

4) Set info.btf_id as long as prog->aux->btf != NULL.  That will
   setup the later copy_to_user() codes look the same as others
   which then easier to understand and maintain.

   prog->aux->btf is not NULL only if prog->aux->func_info_cnt > 0.

   Breaking up info.btf_id from prog->aux->func_info_cnt is needed
   for the later line info patch anyway.

   A similar change is made to bpf_get_prog_name().

Fixes: 838e96904ff3 ("bpf: Introduce bpf_func_info")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/core.c    |  2 +-
 kernel/bpf/syscall.c | 46 ++++++++++++++++++++--------------------------
 2 files changed, 21 insertions(+), 27 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 86817ab204e8..628b3970a49b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -410,7 +410,7 @@ static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
 	sym  = bin2hex(sym, prog->tag, sizeof(prog->tag));
 
 	/* prog->aux->name will be ignored if full btf name is available */
-	if (prog->aux->btf) {
+	if (prog->aux->func_info_cnt) {
 		type = btf_type_by_id(prog->aux->btf,
 				      prog->aux->func_info[prog->aux->func_idx].type_id);
 		func_name = btf_name_by_offset(prog->aux->btf, type->name_off);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4445d0d084d8..aa05aa38f4a8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2083,6 +2083,12 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 				return -EFAULT;
 	}
 
+	if ((info.func_info_cnt || info.func_info_rec_size) &&
+	    info.func_info_rec_size != sizeof(struct bpf_func_info))
+		return -EINVAL;
+
+	info.func_info_rec_size = sizeof(struct bpf_func_info);
+
 	if (!capable(CAP_SYS_ADMIN)) {
 		info.jited_prog_len = 0;
 		info.xlated_prog_len = 0;
@@ -2226,35 +2232,23 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		}
 	}
 
-	if (prog->aux->btf) {
-		u32 krec_size = sizeof(struct bpf_func_info);
-		u32 ucnt, urec_size;
-
+	if (prog->aux->btf)
 		info.btf_id = btf_id(prog->aux->btf);
 
-		ucnt = info.func_info_cnt;
-		info.func_info_cnt = prog->aux->func_info_cnt;
-		urec_size = info.func_info_rec_size;
-		info.func_info_rec_size = krec_size;
-		if (ucnt) {
-			/* expect passed-in urec_size is what the kernel expects */
-			if (urec_size != info.func_info_rec_size)
-				return -EINVAL;
-
-			if (bpf_dump_raw_ok()) {
-				char __user *user_finfo;
-
-				user_finfo = u64_to_user_ptr(info.func_info);
-				ucnt = min_t(u32, info.func_info_cnt, ucnt);
-				if (copy_to_user(user_finfo, prog->aux->func_info,
-						 krec_size * ucnt))
-					return -EFAULT;
-			} else {
-				info.func_info_cnt = 0;
-			}
+	ulen = info.func_info_cnt;
+	info.func_info_cnt = prog->aux->func_info_cnt;
+	if (info.func_info_cnt && ulen) {
+		if (bpf_dump_raw_ok()) {
+			char __user *user_finfo;
+
+			user_finfo = u64_to_user_ptr(info.func_info);
+			ulen = min_t(u32, info.func_info_cnt, ulen);
+			if (copy_to_user(user_finfo, prog->aux->func_info,
+					 info.func_info_rec_size * ulen))
+				return -EFAULT;
+		} else {
+			info.func_info = 0;
 		}
-	} else {
-		info.func_info_cnt = 0;
 	}
 
 done:
-- 
cgit v1.2.3


From d30d42e08c76cb9323ec6121190eb026b07f773b Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 5 Dec 2018 17:35:44 -0800
Subject: bpf: Change insn_offset to insn_off in bpf_func_info

The later patch will introduce "struct bpf_line_info" which
has member "line_off" and "file_off" referring back to the
string section in btf.  The line_"off" and file_"off"
are more consistent to the naming convention in btf.h that
means "offset" (e.g. name_off in "struct btf_type").

The to-be-added "struct bpf_line_info" also has another
member, "insn_off" which is the same as the "insn_offset"
in "struct bpf_func_info".  Hence, this patch renames "insn_offset"
to "insn_off" for "struct bpf_func_info".

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h |  2 +-
 kernel/bpf/verifier.c    | 18 +++++++++---------
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c8e1eeee2c5f..a84fd232d934 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2991,7 +2991,7 @@ struct bpf_flow_keys {
 };
 
 struct bpf_func_info {
-	__u32	insn_offset;
+	__u32	insn_off;
 	__u32	type_id;
 };
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 71988337ac14..7658c61c1a88 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4707,24 +4707,24 @@ static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
 			goto free_btf;
 		}
 
-		/* check insn_offset */
+		/* check insn_off */
 		if (i == 0) {
-			if (krecord[i].insn_offset) {
+			if (krecord[i].insn_off) {
 				verbose(env,
-					"nonzero insn_offset %u for the first func info record",
-					krecord[i].insn_offset);
+					"nonzero insn_off %u for the first func info record",
+					krecord[i].insn_off);
 				ret = -EINVAL;
 				goto free_btf;
 			}
-		} else if (krecord[i].insn_offset <= prev_offset) {
+		} else if (krecord[i].insn_off <= prev_offset) {
 			verbose(env,
 				"same or smaller insn offset (%u) than previous func info record (%u)",
-				krecord[i].insn_offset, prev_offset);
+				krecord[i].insn_off, prev_offset);
 			ret = -EINVAL;
 			goto free_btf;
 		}
 
-		if (env->subprog_info[i].start != krecord[i].insn_offset) {
+		if (env->subprog_info[i].start != krecord[i].insn_off) {
 			verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
 			ret = -EINVAL;
 			goto free_btf;
@@ -4739,7 +4739,7 @@ static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
 			goto free_btf;
 		}
 
-		prev_offset = krecord[i].insn_offset;
+		prev_offset = krecord[i].insn_off;
 		urecord += urec_size;
 	}
 
@@ -4762,7 +4762,7 @@ static void adjust_btf_func(struct bpf_verifier_env *env)
 		return;
 
 	for (i = 0; i < env->subprog_cnt; i++)
-		env->prog->aux->func_info[i].insn_offset = env->subprog_info[i].start;
+		env->prog->aux->func_info[i].insn_off = env->subprog_info[i].start;
 }
 
 /* check %cur's range satisfies %old's */
-- 
cgit v1.2.3


From 555249df711b146a2898949ac80503be29fe7340 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 5 Dec 2018 17:35:45 -0800
Subject: bpf: tools: Sync uapi bpf.h for the name changes in bpf_func_info

This patch sync the name changes in bpf_func_info to
the tools/.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 64262890feb2..16263e8827fc 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2991,7 +2991,7 @@ struct bpf_flow_keys {
 };
 
 struct bpf_func_info {
-	__u32	insn_offset;
+	__u32	insn_off;
 	__u32	type_id;
 };
 
-- 
cgit v1.2.3


From 84ecc1f98ca7ce28ede9bc5cc70a557fdfa09caa Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 5 Dec 2018 17:35:47 -0800
Subject: bpf: Expect !info.func_info and insn_off name changes in
 test_btf/libbpf/bpftool

Similar to info.jited_*, info.func_info could be 0 if
bpf_dump_raw_ok() == false.

This patch makes changes to test_btf and bpftool to expect info.func_info
could be 0.

This patch also makes the needed changes for s/insn_offset/insn_off/.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/prog.c               |  7 +++++++
 tools/bpf/bpftool/xlated_dumper.c      |  4 ++--
 tools/lib/bpf/btf.c                    | 12 ++++++------
 tools/testing/selftests/bpf/test_btf.c |  8 +++++++-
 4 files changed, 22 insertions(+), 9 deletions(-)

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 54c8dbf05c9c..a9a51123454c 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -589,6 +589,13 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
+	if (func_info && !info.func_info) {
+		/* kernel.kptr_restrict is set.  No func_info available. */
+		free(func_info);
+		func_info = NULL;
+		finfo_cnt = 0;
+	}
+
 	if ((member_len == &info.jited_prog_len &&
 	     info.jited_prog_insns == 0) ||
 	    (member_len == &info.xlated_prog_len &&
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index e06ac0286a75..131ecd175533 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -261,7 +261,7 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len,
 		jsonw_start_object(json_wtr);
 
 		if (btf && record) {
-			if (record->insn_offset == i) {
+			if (record->insn_off == i) {
 				btf_dumper_type_only(btf, record->type_id,
 						     func_sig,
 						     sizeof(func_sig));
@@ -330,7 +330,7 @@ void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len,
 		}
 
 		if (btf && record) {
-			if (record->insn_offset == i) {
+			if (record->insn_off == i) {
 				btf_dumper_type_only(btf, record->type_id,
 						     func_sig,
 						     sizeof(func_sig));
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index c2d641f3e16e..85d6446cf832 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -45,7 +45,7 @@ struct btf_ext {
 
 /* The minimum bpf_func_info checked by the loader */
 struct bpf_func_info_min {
-	__u32   insn_offset;
+	__u32   insn_off;
 	__u32   type_id;
 };
 
@@ -670,7 +670,7 @@ int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext,
 
 		memcpy(data, sinfo->data, records_len);
 
-		/* adjust the insn_offset, the data in .BTF.ext is
+		/* adjust the insn_off, the data in .BTF.ext is
 		 * the actual byte offset, and the kernel expects
 		 * the offset in term of bpf_insn.
 		 *
@@ -681,7 +681,7 @@ int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext,
 			struct bpf_func_info_min *record;
 
 			record = data + i * record_size;
-			record->insn_offset /= sizeof(struct bpf_insn);
+			record->insn_off /= sizeof(struct bpf_insn);
 		}
 
 		*func_info = data;
@@ -722,15 +722,15 @@ int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
 			return -ENOMEM;
 
 		memcpy(data + existing_flen, sinfo->data, records_len);
-		/* adjust insn_offset only, the rest data will be passed
+		/* adjust insn_off only, the rest data will be passed
 		 * to the kernel.
 		 */
 		for (i = 0; i < sinfo->num_func_info; i++) {
 			struct bpf_func_info_min *record;
 
 			record = data + existing_flen + i * record_size;
-			record->insn_offset =
-				record->insn_offset / sizeof(struct bpf_insn) +
+			record->insn_off =
+				record->insn_off / sizeof(struct bpf_insn) +
 				insns_cnt;
 		}
 		*func_info = data;
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index bae7308b7ec5..ff0952ea757a 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -3156,7 +3156,7 @@ static struct btf_func_type_test {
 },
 
 {
-	.descr = "func_type (Incorrect bpf_func_info.insn_offset)",
+	.descr = "func_type (Incorrect bpf_func_info.insn_off)",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),	/* [2] */
@@ -3303,6 +3303,12 @@ static int do_test_func_type(int test_num)
 		goto done;
 	}
 
+	if (CHECK(!info.func_info,
+		  "info.func_info == 0. kernel.kptr_restrict is set?")) {
+		err = -1;
+		goto done;
+	}
+
 	finfo = func_info;
 	for (i = 0; i < 2; i++) {
 		if (CHECK(finfo->type_id != test->func_info[i][1],
-- 
cgit v1.2.3


From d66280b12bd7ad6345df4dee2ee1c20f5902242d Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Tue, 4 Dec 2018 11:55:56 -0800
Subject: net: netem: use a list in addition to rbtree

When testing high-bandwidth TCP streams with large windows,
high latency, and low jitter, netem consumes a lot of CPU cycles
doing rbtree rebalancing.

This patch uses a linear list/queue in addition to the rbtree:
if an incoming packet is past the tail of the linear queue, it is
added there, otherwise it is inserted into the rbtree.

Without this patch, perf shows netem_enqueue, netem_dequeue,
and rb_* functions among the top offenders. With this patch,
only netem_enqueue is noticeable if jitter is low/absent.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_netem.c | 89 +++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 69 insertions(+), 20 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 2c38e3d07924..84658f60a872 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -77,6 +77,10 @@ struct netem_sched_data {
 	/* internal t(ime)fifo qdisc uses t_root and sch->limit */
 	struct rb_root t_root;
 
+	/* a linear queue; reduces rbtree rebalancing when jitter is low */
+	struct sk_buff	*t_head;
+	struct sk_buff	*t_tail;
+
 	/* optional qdisc for classful handling (NULL at netem init) */
 	struct Qdisc	*qdisc;
 
@@ -369,26 +373,39 @@ static void tfifo_reset(struct Qdisc *sch)
 		rb_erase(&skb->rbnode, &q->t_root);
 		rtnl_kfree_skbs(skb, skb);
 	}
+
+	rtnl_kfree_skbs(q->t_head, q->t_tail);
+	q->t_head = NULL;
+	q->t_tail = NULL;
 }
 
 static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 	u64 tnext = netem_skb_cb(nskb)->time_to_send;
-	struct rb_node **p = &q->t_root.rb_node, *parent = NULL;
 
-	while (*p) {
-		struct sk_buff *skb;
-
-		parent = *p;
-		skb = rb_to_skb(parent);
-		if (tnext >= netem_skb_cb(skb)->time_to_send)
-			p = &parent->rb_right;
+	if (!q->t_tail || tnext >= netem_skb_cb(q->t_tail)->time_to_send) {
+		if (q->t_tail)
+			q->t_tail->next = nskb;
 		else
-			p = &parent->rb_left;
+			q->t_head = nskb;
+		q->t_tail = nskb;
+	} else {
+		struct rb_node **p = &q->t_root.rb_node, *parent = NULL;
+
+		while (*p) {
+			struct sk_buff *skb;
+
+			parent = *p;
+			skb = rb_to_skb(parent);
+			if (tnext >= netem_skb_cb(skb)->time_to_send)
+				p = &parent->rb_right;
+			else
+				p = &parent->rb_left;
+		}
+		rb_link_node(&nskb->rbnode, parent, p);
+		rb_insert_color(&nskb->rbnode, &q->t_root);
 	}
-	rb_link_node(&nskb->rbnode, parent, p);
-	rb_insert_color(&nskb->rbnode, &q->t_root);
 	sch->q.qlen++;
 }
 
@@ -530,9 +547,16 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 				t_skb = skb_rb_last(&q->t_root);
 				t_last = netem_skb_cb(t_skb);
 				if (!last ||
-				    t_last->time_to_send > last->time_to_send) {
+				    t_last->time_to_send > last->time_to_send)
+					last = t_last;
+			}
+			if (q->t_tail) {
+				struct netem_skb_cb *t_last =
+					netem_skb_cb(q->t_tail);
+
+				if (!last ||
+				    t_last->time_to_send > last->time_to_send)
 					last = t_last;
-				}
 			}
 
 			if (last) {
@@ -611,11 +635,38 @@ static void get_slot_next(struct netem_sched_data *q, u64 now)
 	q->slot.bytes_left = q->slot_config.max_bytes;
 }
 
+static struct sk_buff *netem_peek(struct netem_sched_data *q)
+{
+	struct sk_buff *skb = skb_rb_first(&q->t_root);
+	u64 t1, t2;
+
+	if (!skb)
+		return q->t_head;
+	if (!q->t_head)
+		return skb;
+
+	t1 = netem_skb_cb(skb)->time_to_send;
+	t2 = netem_skb_cb(q->t_head)->time_to_send;
+	if (t1 < t2)
+		return skb;
+	return q->t_head;
+}
+
+static void netem_erase_head(struct netem_sched_data *q, struct sk_buff *skb)
+{
+	if (skb == q->t_head) {
+		q->t_head = skb->next;
+		if (!q->t_head)
+			q->t_tail = NULL;
+	} else {
+		rb_erase(&skb->rbnode, &q->t_root);
+	}
+}
+
 static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
-	struct rb_node *p;
 
 tfifo_dequeue:
 	skb = __qdisc_dequeue_head(&sch->q);
@@ -625,20 +676,18 @@ deliver:
 		qdisc_bstats_update(sch, skb);
 		return skb;
 	}
-	p = rb_first(&q->t_root);
-	if (p) {
+	skb = netem_peek(q);
+	if (skb) {
 		u64 time_to_send;
 		u64 now = ktime_get_ns();
 
-		skb = rb_to_skb(p);
-
 		/* if more time remaining? */
 		time_to_send = netem_skb_cb(skb)->time_to_send;
 		if (q->slot.slot_next && q->slot.slot_next < time_to_send)
 			get_slot_next(q, now);
 
-		if (time_to_send <= now &&  q->slot.slot_next <= now) {
-			rb_erase(p, &q->t_root);
+		if (time_to_send <= now && q->slot.slot_next <= now) {
+			netem_erase_head(q, skb);
 			sch->q.qlen--;
 			qdisc_qstats_backlog_dec(sch, skb);
 			skb->next = NULL;
-- 
cgit v1.2.3


From bf5849f15a30358e0af55576d93aedefe41e781d Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 5 Dec 2018 13:50:32 -0600
Subject: net: Use of_node_name_eq for node name comparisons

Convert string compares of DT node names to use of_node_name_eq helper
instead. This removes direct access to the node name pointer.

For instances using of_node_cmp, this has the side effect of now using
case sensitive comparisons. This should not matter for any FDT based
system which all of these are.

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Claudiu Manoil <claudiu.manoil@nxp.com>
Cc: Grygorii Strashko <grygorii.strashko@ti.com>
Cc: Wingman Kwok <w-kwok2@ti.com>
Cc: Murali Karicheri <m-karicheri2@ti.com>
Cc: netdev@vger.kernel.org
Cc: linux-omap@vger.kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/sunlance.c      | 4 ++--
 drivers/net/ethernet/freescale/gianfar.c | 4 ++--
 drivers/net/ethernet/sun/sunhme.c        | 2 +-
 drivers/net/ethernet/ti/cpsw.c           | 4 ++--
 drivers/net/ethernet/ti/netcp_ethss.c    | 4 ++--
 5 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c
index 9d4899826823..bd6589de93d9 100644
--- a/drivers/net/ethernet/amd/sunlance.c
+++ b/drivers/net/ethernet/amd/sunlance.c
@@ -1488,9 +1488,9 @@ static int sunlance_sbus_probe(struct platform_device *op)
 	struct device_node *parent_dp = parent->dev.of_node;
 	int err;
 
-	if (!strcmp(parent_dp->name, "ledma")) {
+	if (of_node_name_eq(parent_dp, "ledma")) {
 		err = sparc_lance_probe_one(op, parent, NULL);
-	} else if (!strcmp(parent_dp->name, "lebuffer")) {
+	} else if (of_node_name_eq(parent_dp, "lebuffer")) {
 		err = sparc_lance_probe_one(op, NULL, parent);
 	} else
 		err = sparc_lance_probe_one(op, NULL, NULL);
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 0e102c764b13..a831086601eb 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -720,7 +720,7 @@ static int gfar_of_group_count(struct device_node *np)
 	int num = 0;
 
 	for_each_available_child_of_node(np, child)
-		if (!of_node_cmp(child->name, "queue-group"))
+		if (of_node_name_eq(child, "queue-group"))
 			num++;
 
 	return num;
@@ -838,7 +838,7 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 	/* Parse and initialize group specific information */
 	if (priv->mode == MQ_MG_MODE) {
 		for_each_available_child_of_node(np, child) {
-			if (of_node_cmp(child->name, "queue-group"))
+			if (!of_node_name_eq(child, "queue-group"))
 				continue;
 
 			err = gfar_parse_group(child, priv, model);
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 863fd602fd33..ff641cf30a4e 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -2691,7 +2691,7 @@ static int happy_meal_sbus_probe_one(struct platform_device *op, int is_qfe)
 	sbus_dp = op->dev.parent->of_node;
 
 	/* We can match PCI devices too, do not accept those here. */
-	if (strcmp(sbus_dp->name, "sbus") && strcmp(sbus_dp->name, "sbi"))
+	if (!of_node_name_eq(sbus_dp, "sbus") && !of_node_name_eq(sbus_dp, "sbi"))
 		return err;
 
 	if (is_qfe) {
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index e4aa030f1726..0e8f61a29479 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -3271,7 +3271,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 		const __be32 *parp;
 
 		/* This is no slave child node, continue */
-		if (strcmp(slave_node->name, "slave"))
+		if (!of_node_name_eq(slave_node, "slave"))
 			continue;
 
 		slave_data->phy_node = of_parse_phandle(slave_node,
@@ -3367,7 +3367,7 @@ static void cpsw_remove_dt(struct platform_device *pdev)
 	for_each_available_child_of_node(node, slave_node) {
 		struct cpsw_slave_data *slave_data = &data->slave_data[i];
 
-		if (strcmp(slave_node->name, "slave"))
+		if (!of_node_name_eq(slave_node, "slave"))
 			continue;
 
 		if (of_phy_is_fixed_link(slave_node))
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 20d81e0b1c29..5174d318901e 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -3623,7 +3623,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 		return -EINVAL;
 	}
 
-	if (!strcmp(node->name, "gbe")) {
+	if (of_node_name_eq(node, "gbe")) {
 		ret = get_gbe_resource_version(gbe_dev, node);
 		if (ret)
 			return ret;
@@ -3637,7 +3637,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 		else
 			ret = -ENODEV;
 
-	} else if (!strcmp(node->name, "xgbe")) {
+	} else if (of_node_name_eq(node, "xgbe")) {
 		ret = set_xgbe_ethss10_priv(gbe_dev, node);
 		if (ret)
 			return ret;
-- 
cgit v1.2.3


From f5d6c3e5a359c0507800e7ac68d565c21de9b5a1 Mon Sep 17 00:00:00 2001
From: Hoang Le <hoang.h.le@dektech.com.au>
Date: Thu, 6 Dec 2018 09:00:09 +0700
Subject: tipc: fix node keep alive interval calculation

When setting LINK tolerance, node timer interval will be calculated
base on the LINK with lowest tolerance.

But when calculated, the old node timer interval only updated if current
setting value (tolerance/4) less than old ones regardless of number of
links as well as links' lowest tolerance value.

This caused to two cases missing if tolerance changed as following:
Case 1:
1.1/ There is one link (L1) available in the system
1.2/ Set L1's tolerance from 1500ms => lower (i.e 500ms)
1.3/ Then, fallback to default (1500ms) or higher (i.e 2000ms)

Expected:
    node timer interval is 1500/4=375ms after 1.3

Result:
node timer interval will not being updated after changing tolerance at 1.3
since its value 1500/4=375ms is not less than 500/4=125ms at 1.2.

Case 2:
2.1/ There are two links (L1, L2) available in the system
2.2/ L1 and L2 tolerance value are 2000ms as initial
2.3/ Set L2's tolerance from 2000ms => lower 1500ms
2.4/ Disable link L2 (bring down its bearer)

Expected:
    node timer interval is 2000ms/4=500ms after 2.4

Result:
node timer interval will not being updated after disabling L2 since
its value 2000ms/4=500ms is still not less than 1500/4=375ms at 2.3
although L2 is already not available in the system.

To fix this, we start the node interval calculation by initializing it to
a value larger than any conceivable calculated value. This way, the link
with the lowest tolerance will always determine the calculated value.

Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Hoang Le <hoang.h.le@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 488019766433..32556f480a60 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -624,6 +624,12 @@ static void tipc_node_timeout(struct timer_list *t)
 
 	__skb_queue_head_init(&xmitq);
 
+	/* Initial node interval to value larger (10 seconds), then it will be
+	 * recalculated with link lowest tolerance
+	 */
+	tipc_node_read_lock(n);
+	n->keepalive_intv = 10000;
+	tipc_node_read_unlock(n);
 	for (bearer_id = 0; remains && (bearer_id < MAX_BEARERS); bearer_id++) {
 		tipc_node_read_lock(n);
 		le = &n->links[bearer_id];
-- 
cgit v1.2.3


From 7a35a50df5a34e6eaee1b1f4f913b84879068fee Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 5 Dec 2018 20:02:29 -0800
Subject: neighbor: Add extack messages for add and delete commands

Add extack messages for failures in neigh_add and neigh_delete.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 55 +++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 39 insertions(+), 16 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 41954e42a2de..6d479b5562be 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1137,8 +1137,9 @@ static void neigh_update_hhs(struct neighbour *neigh)
    Caller MUST hold reference count on the entry.
  */
 
-int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
-		 u32 flags, u32 nlmsg_pid)
+static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
+			  u8 new, u32 flags, u32 nlmsg_pid,
+			  struct netlink_ext_ack *extack)
 {
 	u8 old;
 	int err;
@@ -1155,8 +1156,10 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
 	    (old & (NUD_NOARP | NUD_PERMANENT)))
 		goto out;
-	if (neigh->dead)
+	if (neigh->dead) {
+		NL_SET_ERR_MSG(extack, "Neighbor entry is now dead");
 		goto out;
+	}
 
 	neigh_update_ext_learned(neigh, flags, &notify);
 
@@ -1193,8 +1196,10 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 		   use it, otherwise discard the request.
 		 */
 		err = -EINVAL;
-		if (!(old & NUD_VALID))
+		if (!(old & NUD_VALID)) {
+			NL_SET_ERR_MSG(extack, "No link layer address given");
 			goto out;
+		}
 		lladdr = neigh->ha;
 	}
 
@@ -1307,6 +1312,12 @@ out:
 
 	return err;
 }
+
+int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
+		 u32 flags, u32 nlmsg_pid)
+{
+	return __neigh_update(neigh, lladdr, new, flags, nlmsg_pid, NULL);
+}
 EXPORT_SYMBOL(neigh_update);
 
 /* Update the neigh to listen temporarily for probe responses, even if it is
@@ -1678,8 +1689,10 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 
 	dst_attr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_DST);
-	if (dst_attr == NULL)
+	if (!dst_attr) {
+		NL_SET_ERR_MSG(extack, "Network address not specified");
 		goto out;
+	}
 
 	ndm = nlmsg_data(nlh);
 	if (ndm->ndm_ifindex) {
@@ -1694,8 +1707,10 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tbl == NULL)
 		return -EAFNOSUPPORT;
 
-	if (nla_len(dst_attr) < (int)tbl->key_len)
+	if (nla_len(dst_attr) < (int)tbl->key_len) {
+		NL_SET_ERR_MSG(extack, "Invalid network address");
 		goto out;
+	}
 
 	if (ndm->ndm_flags & NTF_PROXY) {
 		err = pneigh_delete(tbl, net, nla_data(dst_attr), dev);
@@ -1711,10 +1726,9 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 	}
 
-	err = neigh_update(neigh, NULL, NUD_FAILED,
-			   NEIGH_UPDATE_F_OVERRIDE |
-			   NEIGH_UPDATE_F_ADMIN,
-			   NETLINK_CB(skb).portid);
+	err = __neigh_update(neigh, NULL, NUD_FAILED,
+			     NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN,
+			     NETLINK_CB(skb).portid, extack);
 	write_lock_bh(&tbl->lock);
 	neigh_release(neigh);
 	neigh_remove_one(neigh, tbl);
@@ -1744,8 +1758,10 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 
 	err = -EINVAL;
-	if (tb[NDA_DST] == NULL)
+	if (!tb[NDA_DST]) {
+		NL_SET_ERR_MSG(extack, "Network address not specified");
 		goto out;
+	}
 
 	ndm = nlmsg_data(nlh);
 	if (ndm->ndm_ifindex) {
@@ -1755,16 +1771,21 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 			goto out;
 		}
 
-		if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len)
+		if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len) {
+			NL_SET_ERR_MSG(extack, "Invalid link address");
 			goto out;
+		}
 	}
 
 	tbl = neigh_find_table(ndm->ndm_family);
 	if (tbl == NULL)
 		return -EAFNOSUPPORT;
 
-	if (nla_len(tb[NDA_DST]) < (int)tbl->key_len)
+	if (nla_len(tb[NDA_DST]) < (int)tbl->key_len) {
+		NL_SET_ERR_MSG(extack, "Invalid network address");
 		goto out;
+	}
+
 	dst = nla_data(tb[NDA_DST]);
 	lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
 
@@ -1780,8 +1801,10 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 	}
 
-	if (dev == NULL)
+	if (!dev) {
+		NL_SET_ERR_MSG(extack, "Device not specified");
 		goto out;
+	}
 
 	neigh = neigh_lookup(tbl, dst, dev);
 	if (neigh == NULL) {
@@ -1817,8 +1840,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		neigh_event_send(neigh, NULL);
 		err = 0;
 	} else
-		err = neigh_update(neigh, lladdr, ndm->ndm_state, flags,
-				   NETLINK_CB(skb).portid);
+		err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags,
+				     NETLINK_CB(skb).portid, extack);
 	neigh_release(neigh);
 
 out:
-- 
cgit v1.2.3


From 83b1bc122cab87547731a154db5feec5b9d4807c Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Thu, 6 Dec 2018 16:08:17 +0800
Subject: tun: align write-heavy flow entry members to a cache line

tun flow entry 'updated' fields are written when receive
every packet. Thus if a flow is receiving packets from a
particular flow entry, it'll cause false-sharing with
all the other who has looked it up, so move it in its own
cache line

and update 'queue_index' and 'update' field only when
they are changed to reduce the cache false-sharing.

Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: Wang Li <wangli39@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 835c73f42ae7..d0745dc81976 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -201,7 +201,7 @@ struct tun_flow_entry {
 	u32 rxhash;
 	u32 rps_rxhash;
 	int queue_index;
-	unsigned long updated;
+	unsigned long updated ____cacheline_aligned_in_smp;
 };
 
 #define TUN_NUM_FLOW_ENTRIES 1024
@@ -539,8 +539,10 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash,
 	e = tun_flow_find(head, rxhash);
 	if (likely(e)) {
 		/* TODO: keep queueing to old queue until it's empty? */
-		e->queue_index = queue_index;
-		e->updated = jiffies;
+		if (e->queue_index != queue_index)
+			e->queue_index = queue_index;
+		if (e->updated != jiffies)
+			e->updated = jiffies;
 		sock_rps_record_flow_hash(e->rps_rxhash);
 	} else {
 		spin_lock_bh(&tun->lock);
-- 
cgit v1.2.3


From 5c327f673d2f134ac01c068b511c6ab816b4b41c Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Thu, 6 Dec 2018 16:28:11 +0800
Subject: tun: remove unnecessary check in tun_flow_update

caller has guaranted that rxhash is not zero

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index d0745dc81976..6760b86547df 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -529,10 +529,7 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash,
 	unsigned long delay = tun->ageing_time;
 	u16 queue_index = tfile->queue_index;
 
-	if (!rxhash)
-		return;
-	else
-		head = &tun->flows[tun_hashfn(rxhash)];
+	head = &tun->flows[tun_hashfn(rxhash)];
 
 	rcu_read_lock();
 
-- 
cgit v1.2.3


From a5dd308778a4e05e7b0b927cf18b89d1ebbff59c Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 6 Dec 2018 11:36:04 +0100
Subject: net: dsa: Add overhead to tag protocol ops.

Each DSA tag protocol needs to add additional headers to the Ethernet
frame in order to direct it towards a specific switch egress port. It
must also remove the head from a frame received from a
switch. Indicate the maximum size of these headers in the tag protocol
ops structure, so the core can take these overheads into account.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h     | 1 +
 net/dsa/tag_brcm.c    | 2 ++
 net/dsa/tag_dsa.c     | 1 +
 net/dsa/tag_edsa.c    | 1 +
 net/dsa/tag_gswip.c   | 1 +
 net/dsa/tag_ksz.c     | 1 +
 net/dsa/tag_lan9303.c | 1 +
 net/dsa/tag_mtk.c     | 1 +
 net/dsa/tag_qca.c     | 1 +
 net/dsa/tag_trailer.c | 1 +
 10 files changed, 11 insertions(+)

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 23690c44e167..6ee2e24e0a6e 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -113,6 +113,7 @@ struct dsa_device_ops {
 			       struct packet_type *pt);
 	int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto,
 			    int *offset);
+	unsigned int overhead;
 };
 
 struct dsa_switch_tree {
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 2b06bb91318b..4aa1d368a5ae 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -174,6 +174,7 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 const struct dsa_device_ops brcm_netdev_ops = {
 	.xmit	= brcm_tag_xmit,
 	.rcv	= brcm_tag_rcv,
+	.overhead = BRCM_TAG_LEN,
 };
 #endif
 
@@ -196,5 +197,6 @@ static struct sk_buff *brcm_tag_rcv_prepend(struct sk_buff *skb,
 const struct dsa_device_ops brcm_prepend_netdev_ops = {
 	.xmit	= brcm_tag_xmit_prepend,
 	.rcv	= brcm_tag_rcv_prepend,
+	.overhead = BRCM_TAG_LEN,
 };
 #endif
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index cd13cfc542ce..8b2f92e3f3a2 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -149,4 +149,5 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
 const struct dsa_device_ops dsa_netdev_ops = {
 	.xmit	= dsa_xmit,
 	.rcv	= dsa_rcv,
+	.overhead = DSA_HLEN,
 };
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 4083326b806e..f5b87ee5c94e 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -168,4 +168,5 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
 const struct dsa_device_ops edsa_netdev_ops = {
 	.xmit	= edsa_xmit,
 	.rcv	= edsa_rcv,
+	.overhead = EDSA_HLEN,
 };
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index 49e9b73f1be3..cb6f82ffe5eb 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -106,4 +106,5 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb,
 const struct dsa_device_ops gswip_netdev_ops = {
 	.xmit = gswip_tag_xmit,
 	.rcv = gswip_tag_rcv,
+	.overhead = GSWIP_RX_HEADER_LEN,
 };
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 0f62effad88f..96411f70ab9f 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -99,4 +99,5 @@ static struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev,
 const struct dsa_device_ops ksz_netdev_ops = {
 	.xmit	= ksz_xmit,
 	.rcv	= ksz_rcv,
+	.overhead = KSZ_INGRESS_TAG_LEN,
 };
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index 548c00254c07..f48889e46ff7 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -140,4 +140,5 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev,
 const struct dsa_device_ops lan9303_netdev_ops = {
 	.xmit = lan9303_xmit,
 	.rcv = lan9303_rcv,
+	.overhead = LAN9303_TAG_LEN,
 };
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index 11535bc70743..f39f4dfeda34 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -109,4 +109,5 @@ const struct dsa_device_ops mtk_netdev_ops = {
 	.xmit		= mtk_tag_xmit,
 	.rcv		= mtk_tag_rcv,
 	.flow_dissect	= mtk_tag_flow_dissect,
+	.overhead	= MTK_HDR_LEN,
 };
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 613f4ee97771..ed4f6dc26365 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -101,4 +101,5 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 const struct dsa_device_ops qca_netdev_ops = {
 	.xmit	= qca_tag_xmit,
 	.rcv	= qca_tag_rcv,
+	.overhead = QCA_HDR_LEN,
 };
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 56197f0d9608..b40756ed6e57 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -84,4 +84,5 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
 const struct dsa_device_ops trailer_netdev_ops = {
 	.xmit	= trailer_xmit,
 	.rcv	= trailer_rcv,
+	.overhead = 4,
 };
-- 
cgit v1.2.3


From dc0fe7d47f9f2256e3aa695bb754625f37291e17 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 6 Dec 2018 11:36:05 +0100
Subject: net: dsa: Set the master device's MTU to account for DSA overheads

DSA tagging of frames sent over the master interface to the switch
increases the size of the frame. Such frames can then be bigger than
the normal MTU of the master interface, and it may drop them. Use the
overhead information from the tagger to set the MTU of the master
device to include this overhead.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/master.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/net/dsa/master.c b/net/dsa/master.c
index c90ee3227dea..42f525bc68e2 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -158,8 +158,24 @@ static void dsa_master_ethtool_teardown(struct net_device *dev)
 	cpu_dp->orig_ethtool_ops = NULL;
 }
 
+void dsa_master_set_mtu(struct net_device *dev, struct dsa_port *cpu_dp)
+{
+	unsigned int mtu = ETH_DATA_LEN + cpu_dp->tag_ops->overhead;
+	int err;
+
+	rtnl_lock();
+	if (mtu <= dev->max_mtu) {
+		err = dev_set_mtu(dev, mtu);
+		if (err)
+			netdev_dbg(dev, "Unable to set MTU to include for DSA overheads\n");
+	}
+	rtnl_unlock();
+}
+
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 {
+	dsa_master_set_mtu(dev,  cpu_dp);
+
 	/* If we use a tagging format that doesn't have an ethertype
 	 * field, make sure that all packets from this point on get
 	 * sent to the tag format's receive function.
-- 
cgit v1.2.3


From fdb8b298676a39b660d10c6dcaaf5b702f811009 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@gmail.com>
Date: Thu, 6 Dec 2018 10:45:28 -0200
Subject: tcp: fix code style in tcp_recvmsg()

2 goto labels are indented with a tab. remove the tabs and
keep the code style consistent.

Signed-off-by: Pedro Tammela <pctammela@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dc68c408bba0..27e2f6837062 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2088,7 +2088,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		}
 		continue;
 
-	found_ok_skb:
+found_ok_skb:
 		/* Ok so how much can we use? */
 		used = skb->len - offset;
 		if (len < used)
@@ -2147,7 +2147,7 @@ skip_copy:
 			sk_eat_skb(sk, skb);
 		continue;
 
-	found_fin_ok:
+found_fin_ok:
 		/* Process the FIN. */
 		++*seq;
 		if (!(flags & MSG_PEEK))
-- 
cgit v1.2.3


From 00f54e68924eaf075f3f24be18557899d347bc4a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 6 Dec 2018 17:05:36 +0000
Subject: net: core: dev: Add extack argument to dev_open()

In order to pass extack together with NETDEV_PRE_UP notifications, it's
necessary to route the extack to __dev_open() from diverse (possibly
indirect) callers. One prominent API through which the notification is
invoked is dev_open().

Therefore extend dev_open() with and extra extack argument and update
all users. Most of the calls end up just encoding NULL, but bond and
team drivers have the extack readily available.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c                     | 2 +-
 drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c | 2 +-
 drivers/net/ethernet/cisco/enic/enic_ethtool.c      | 2 +-
 drivers/net/ethernet/hisilicon/hns/hns_ethtool.c    | 2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c  | 2 +-
 drivers/net/ethernet/sfc/ethtool.c                  | 2 +-
 drivers/net/ethernet/sfc/falcon/ethtool.c           | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c   | 2 +-
 drivers/net/hyperv/netvsc_drv.c                     | 4 ++--
 drivers/net/net_failover.c                          | 8 ++++----
 drivers/net/team/team.c                             | 2 +-
 drivers/net/wireless/intersil/hostap/hostap_main.c  | 2 +-
 drivers/s390/net/qeth_l2_main.c                     | 2 +-
 drivers/s390/net/qeth_l3_main.c                     | 2 +-
 drivers/staging/fsl-dpaa2/ethsw/ethsw.c             | 2 +-
 drivers/staging/unisys/visornic/visornic_main.c     | 2 +-
 include/linux/netdevice.h                           | 2 +-
 net/bluetooth/6lowpan.c                             | 2 +-
 net/core/dev.c                                      | 5 +++--
 net/core/netpoll.c                                  | 2 +-
 net/ipv4/ipmr.c                                     | 4 ++--
 net/ipv6/addrconf.c                                 | 2 +-
 net/ipv6/ip6mr.c                                    | 2 +-
 23 files changed, 30 insertions(+), 29 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 333387f1f1fe..6b34dbefa7dd 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1538,7 +1538,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	slave_dev->flags |= IFF_SLAVE;
 
 	/* open the slave since the application closed it */
-	res = dev_open(slave_dev);
+	res = dev_open(slave_dev, extack);
 	if (res) {
 		netdev_dbg(bond_dev, "Opening slave %s failed\n", slave_dev->name);
 		goto err_restore_mac;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index a5fd71692c8b..43b42615ad84 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -525,7 +525,7 @@ static int aq_set_ringparam(struct net_device *ndev,
 		}
 	}
 	if (ndev_running)
-		err = dev_open(ndev);
+		err = dev_open(ndev, NULL);
 
 err_exit:
 	return err;
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index f42f7a6e1559..ebd5c2cf1efe 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -241,7 +241,7 @@ static int enic_set_ringparam(struct net_device *netdev,
 	}
 	enic_init_vnic_resources(enic);
 	if (running) {
-		err = dev_open(netdev);
+		err = dev_open(netdev, NULL);
 		if (err)
 			goto err_out;
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 774beda040a1..8e9b95871d30 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -624,7 +624,7 @@ static void hns_nic_self_test(struct net_device *ndev,
 		clear_bit(NIC_STATE_TESTING, &priv->state);
 
 		if (if_running)
-			(void)dev_open(ndev);
+			(void)dev_open(ndev, NULL);
 	}
 	/* Online tests aren't run; pass by default */
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 4563638367ac..e678b6939da3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -821,7 +821,7 @@ static int hns3_set_ringparam(struct net_device *ndev,
 	}
 
 	if (if_running)
-		ret = dev_open(ndev);
+		ret = dev_open(ndev, NULL);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 3143588ffd77..600d7b895cf2 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -539,7 +539,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev,
 	/* We need rx buffers and interrupts. */
 	already_up = (efx->net_dev->flags & IFF_UP);
 	if (!already_up) {
-		rc = dev_open(efx->net_dev);
+		rc = dev_open(efx->net_dev, NULL);
 		if (rc) {
 			netif_err(efx, drv, efx->net_dev,
 				  "failed opening device.\n");
diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c
index 1ccdb7a82e2a..72cedec945c1 100644
--- a/drivers/net/ethernet/sfc/falcon/ethtool.c
+++ b/drivers/net/ethernet/sfc/falcon/ethtool.c
@@ -517,7 +517,7 @@ static void ef4_ethtool_self_test(struct net_device *net_dev,
 	/* We need rx buffers and interrupts. */
 	already_up = (efx->net_dev->flags & IFF_UP);
 	if (!already_up) {
-		rc = dev_open(efx->net_dev);
+		rc = dev_open(efx->net_dev, NULL);
 		if (rc) {
 			netif_err(efx, drv, efx->net_dev,
 				  "failed opening device.\n");
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c728ed1375b2..d20496f0ebd0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4082,7 +4082,7 @@ static void stmmac_reset_subtask(struct stmmac_priv *priv)
 
 	set_bit(STMMAC_DOWN, &priv->state);
 	dev_close(priv->dev);
-	dev_open(priv->dev);
+	dev_open(priv->dev, NULL);
 	clear_bit(STMMAC_DOWN, &priv->state);
 	clear_bit(STMMAC_RESETING, &priv->state);
 	rtnl_unlock();
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 85936ed9e952..c65620adab52 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -137,7 +137,7 @@ static int netvsc_open(struct net_device *net)
 		 * slave as up. If open fails, then slave will be
 		 * still be offline (and not used).
 		 */
-		ret = dev_open(vf_netdev);
+		ret = dev_open(vf_netdev, NULL);
 		if (ret)
 			netdev_warn(net,
 				    "unable to open slave: %s: %d\n",
@@ -2002,7 +2002,7 @@ static void __netvsc_vf_setup(struct net_device *ndev,
 	netif_addr_unlock_bh(ndev);
 
 	if (netif_running(ndev)) {
-		ret = dev_open(vf_netdev);
+		ret = dev_open(vf_netdev, NULL);
 		if (ret)
 			netdev_warn(vf_netdev,
 				    "unable to open: %d\n", ret);
diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index e964d312f4ca..ed1166adaa2f 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -40,14 +40,14 @@ static int net_failover_open(struct net_device *dev)
 
 	primary_dev = rtnl_dereference(nfo_info->primary_dev);
 	if (primary_dev) {
-		err = dev_open(primary_dev);
+		err = dev_open(primary_dev, NULL);
 		if (err)
 			goto err_primary_open;
 	}
 
 	standby_dev = rtnl_dereference(nfo_info->standby_dev);
 	if (standby_dev) {
-		err = dev_open(standby_dev);
+		err = dev_open(standby_dev, NULL);
 		if (err)
 			goto err_standby_open;
 	}
@@ -517,7 +517,7 @@ static int net_failover_slave_register(struct net_device *slave_dev,
 	dev_hold(slave_dev);
 
 	if (netif_running(failover_dev)) {
-		err = dev_open(slave_dev);
+		err = dev_open(slave_dev, NULL);
 		if (err && (err != -EBUSY)) {
 			netdev_err(failover_dev, "Opening slave %s failed err:%d\n",
 				   slave_dev->name, err);
@@ -680,7 +680,7 @@ static int net_failover_slave_name_change(struct net_device *slave_dev,
 	/* We need to bring up the slave after the rename by udev in case
 	 * open failed with EBUSY when it was registered.
 	 */
-	dev_open(slave_dev);
+	dev_open(slave_dev, NULL);
 
 	return 0;
 }
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 364f514d56d8..93576e0240dd 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1212,7 +1212,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		goto err_port_enter;
 	}
 
-	err = dev_open(port_dev);
+	err = dev_open(port_dev, extack);
 	if (err) {
 		netdev_dbg(dev, "Device %s opening failed\n",
 			   portname);
diff --git a/drivers/net/wireless/intersil/hostap/hostap_main.c b/drivers/net/wireless/intersil/hostap/hostap_main.c
index 012930d35434..b0e7c0a0617e 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_main.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_main.c
@@ -690,7 +690,7 @@ static int prism2_open(struct net_device *dev)
 		/* Master radio interface is needed for all operation, so open
 		 * it automatically when any virtual net_device is opened. */
 		local->master_dev_auto_open = 1;
-		dev_open(local->dev);
+		dev_open(local->dev, NULL);
 	}
 
 	netif_device_attach(dev);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 2836231c1c5d..f108d4b44605 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1007,7 +1007,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 			qeth_l2_set_rx_mode(card->dev);
 		} else {
 			rtnl_lock();
-			dev_open(card->dev);
+			dev_open(card->dev, NULL);
 			rtnl_unlock();
 		}
 	}
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index eca68da39d05..42a7cdc59b76 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2417,7 +2417,7 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 			__qeth_l3_open(card->dev);
 			qeth_l3_set_rx_mode(card->dev);
 		} else {
-			dev_open(card->dev);
+			dev_open(card->dev, NULL);
 		}
 		rtnl_unlock();
 	}
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index 4fa37d6e598b..daabaceeea52 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -1172,7 +1172,7 @@ static int ethsw_open(struct ethsw_core *ethsw)
 
 	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
 		port_priv = ethsw->ports[i];
-		err = dev_open(port_priv->netdev);
+		err = dev_open(port_priv->netdev, NULL);
 		if (err) {
 			netdev_err(port_priv->netdev, "dev_open err %d\n", err);
 			return err;
diff --git a/drivers/staging/unisys/visornic/visornic_main.c b/drivers/staging/unisys/visornic/visornic_main.c
index 3647b8f1ed28..5eeb4b93b45b 100644
--- a/drivers/staging/unisys/visornic/visornic_main.c
+++ b/drivers/staging/unisys/visornic/visornic_main.c
@@ -2095,7 +2095,7 @@ static int visornic_resume(struct visor_device *dev,
 	mod_timer(&devdata->irq_poll_timer, msecs_to_jiffies(2));
 
 	rtnl_lock();
-	dev_open(netdev);
+	dev_open(netdev, NULL);
 	rtnl_unlock();
 
 	complete_func(dev, 0);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 94fb2e12f117..d79be3055f5f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2605,7 +2605,7 @@ struct net_device *dev_get_by_name(struct net *net, const char *name);
 struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
 struct net_device *__dev_get_by_name(struct net *net, const char *name);
 int dev_alloc_name(struct net_device *dev, const char *name);
-int dev_open(struct net_device *dev);
+int dev_open(struct net_device *dev, struct netlink_ext_ack *extack);
 void dev_close(struct net_device *dev);
 void dev_close_many(struct list_head *head, bool unlink);
 void dev_disable_lro(struct net_device *dev);
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 828e87fe8027..9d79c7de234a 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -607,7 +607,7 @@ static void ifup(struct net_device *netdev)
 	int err;
 
 	rtnl_lock();
-	err = dev_open(netdev);
+	err = dev_open(netdev, NULL);
 	if (err < 0)
 		BT_INFO("iface %s cannot be opened (%d)", netdev->name, err);
 	rtnl_unlock();
diff --git a/net/core/dev.c b/net/core/dev.c
index 04a6b7100aac..b801c1aafd70 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1406,7 +1406,8 @@ static int __dev_open(struct net_device *dev)
 
 /**
  *	dev_open	- prepare an interface for use.
- *	@dev:	device to open
+ *	@dev: device to open
+ *	@extack: netlink extended ack
  *
  *	Takes a device from down to up state. The device's private open
  *	function is invoked and then the multicast lists are loaded. Finally
@@ -1416,7 +1417,7 @@ static int __dev_open(struct net_device *dev)
  *	Calling this function on an active interface is a nop. On a failure
  *	a negative errno code is returned.
  */
-int dev_open(struct net_device *dev)
+int dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 {
 	int ret;
 
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 2b9fdbc43205..36a2b63ffd6d 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -663,7 +663,7 @@ int netpoll_setup(struct netpoll *np)
 
 		np_info(np, "device %s not up yet, forcing it\n", np->dev_name);
 
-		err = dev_open(ndev);
+		err = dev_open(ndev, NULL);
 
 		if (err) {
 			np_err(np, "failed to open %s\n", ndev->name);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5cbc749a50aa..ea04e38f56e9 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -506,7 +506,7 @@ static struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v)
 			dev->flags |= IFF_MULTICAST;
 			if (!ipmr_init_vif_indev(dev))
 				goto failure;
-			if (dev_open(dev))
+			if (dev_open(dev, NULL))
 				goto failure;
 			dev_hold(dev);
 		}
@@ -589,7 +589,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 
 	if (!ipmr_init_vif_indev(dev))
 		goto failure;
-	if (dev_open(dev))
+	if (dev_open(dev, NULL))
 		goto failure;
 
 	dev_hold(dev);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 045597b9a7c0..521e471f1cf9 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2820,7 +2820,7 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg)
 			dev = __dev_get_by_name(net, p.name);
 			if (!dev)
 				goto err_exit;
-			err = dev_open(dev);
+			err = dev_open(dev, NULL);
 		}
 	}
 #endif
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index e2ea691e42c6..8c63494400c4 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -655,7 +655,7 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt)
 		return NULL;
 	}
 
-	if (dev_open(dev))
+	if (dev_open(dev, NULL))
 		goto failure;
 
 	dev_hold(dev);
-- 
cgit v1.2.3


From dc1aea1e08de3fb02c52df6e0e27095a49fb5a41 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 6 Dec 2018 17:05:38 +0000
Subject: net: vrf: cycle_netdev(): Add an extack argument

A follow-up patch will extend dev_change_flags() with an extack
argument. Extend cycle_netdev() to have that argument available for the
conversion.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 21ad4b1d7f03..1e9f2dc0de07 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -747,7 +747,8 @@ static int vrf_rtable_create(struct net_device *dev)
 /**************************** device handling ********************/
 
 /* cycle interface to flush neighbor cache and move routes across tables */
-static void cycle_netdev(struct net_device *dev)
+static void cycle_netdev(struct net_device *dev,
+			 struct netlink_ext_ack *extack)
 {
 	unsigned int flags = dev->flags;
 	int ret;
@@ -785,7 +786,7 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev,
 	if (ret < 0)
 		goto err;
 
-	cycle_netdev(port_dev);
+	cycle_netdev(port_dev, extack);
 
 	return 0;
 
@@ -815,7 +816,7 @@ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev)
 	netdev_upper_dev_unlink(port_dev, dev);
 	port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE;
 
-	cycle_netdev(port_dev);
+	cycle_netdev(port_dev, NULL);
 
 	return 0;
 }
-- 
cgit v1.2.3


From cf7686a01266de84b3b825acc05026d4e55454e1 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 6 Dec 2018 17:05:40 +0000
Subject: net: ipvlan: ipvlan_set_port_mode(): Add an extack argument

A follow-up patch will extend dev_change_flags() with an extack
argument. Extend ipvlan_set_port_mode() to have that argument available
for the conversion.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 4a949569ec4c..14f1cbd3b96f 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -71,7 +71,8 @@ static void ipvlan_unregister_nf_hook(struct net *net)
 					ARRAY_SIZE(ipvl_nfops));
 }
 
-static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
+static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
+				struct netlink_ext_ack *extack)
 {
 	struct ipvl_dev *ipvlan;
 	struct net_device *mdev = port->dev;
@@ -498,7 +499,7 @@ static int ipvlan_nl_changelink(struct net_device *dev,
 	if (data[IFLA_IPVLAN_MODE]) {
 		u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
 
-		err = ipvlan_set_port_mode(port, nmode);
+		err = ipvlan_set_port_mode(port, nmode, extack);
 	}
 
 	if (!err && data[IFLA_IPVLAN_FLAGS]) {
@@ -672,7 +673,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	if (data && data[IFLA_IPVLAN_MODE])
 		mode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
 
-	err = ipvlan_set_port_mode(port, mode);
+	err = ipvlan_set_port_mode(port, mode, extack);
 	if (err)
 		goto unlink_netdev;
 
-- 
cgit v1.2.3


From 567c5e13be5cc74d24f5eb54cf353c2e2277189b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 6 Dec 2018 17:05:42 +0000
Subject: net: core: dev: Add extack argument to dev_change_flags()

In order to pass extack together with NETDEV_PRE_UP notifications, it's
necessary to route the extack to __dev_open() from diverse (possibly
indirect) callers. One prominent API through which the notification is
invoked is dev_change_flags().

Therefore extend dev_change_flags() with and extra extack argument and
update all users. Most of the calls end up just encoding NULL, but
several sites (VLAN, ipvlan, VRF, rtnetlink) do have extack available.

Since the function declaration line is changed anyway, name the other
function arguments to placate checkpatch.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/ulp/ipoib/ipoib_main.c |  6 +++---
 drivers/net/hyperv/netvsc_drv.c           |  2 +-
 drivers/net/ipvlan/ipvlan_main.c          | 12 ++++++++----
 drivers/net/vrf.c                         |  4 ++--
 include/linux/netdevice.h                 |  3 ++-
 net/8021q/vlan.c                          |  4 +++-
 net/core/dev.c                            |  4 +++-
 net/core/dev_ioctl.c                      |  2 +-
 net/core/net-sysfs.c                      |  2 +-
 net/core/rtnetlink.c                      |  3 ++-
 net/ipv4/devinet.c                        |  2 +-
 net/ipv4/ipconfig.c                       |  6 +++---
 net/openvswitch/vport-geneve.c            |  2 +-
 net/openvswitch/vport-gre.c               |  2 +-
 net/openvswitch/vport-vxlan.c             |  2 +-
 15 files changed, 33 insertions(+), 23 deletions(-)

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 8710214594d8..6214d8c0d546 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -167,7 +167,7 @@ int ipoib_open(struct net_device *dev)
 			if (flags & IFF_UP)
 				continue;
 
-			dev_change_flags(cpriv->dev, flags | IFF_UP);
+			dev_change_flags(cpriv->dev, flags | IFF_UP, NULL);
 		}
 		up_read(&priv->vlan_rwsem);
 	}
@@ -207,7 +207,7 @@ static int ipoib_stop(struct net_device *dev)
 			if (!(flags & IFF_UP))
 				continue;
 
-			dev_change_flags(cpriv->dev, flags & ~IFF_UP);
+			dev_change_flags(cpriv->dev, flags & ~IFF_UP, NULL);
 		}
 		up_read(&priv->vlan_rwsem);
 	}
@@ -1823,7 +1823,7 @@ static void ipoib_parent_unregister_pre(struct net_device *ndev)
 	 * running ensures the it will not add more work.
 	 */
 	rtnl_lock();
-	dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP);
+	dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP, NULL);
 	rtnl_unlock();
 
 	/* ipoib_event() cannot be running once this returns */
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index c65620adab52..18b5584d6377 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1993,7 +1993,7 @@ static void __netvsc_vf_setup(struct net_device *ndev,
 			    "unable to change mtu to %u\n", ndev->mtu);
 
 	/* set multicast etc flags on VF */
-	dev_change_flags(vf_netdev, ndev->flags | IFF_SLAVE);
+	dev_change_flags(vf_netdev, ndev->flags | IFF_SLAVE, NULL);
 
 	/* sync address list from ndev to VF */
 	netif_addr_lock_bh(ndev);
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 14f1cbd3b96f..c3d3e458f541 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -85,10 +85,12 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
 			flags = ipvlan->dev->flags;
 			if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) {
 				err = dev_change_flags(ipvlan->dev,
-						       flags | IFF_NOARP);
+						       flags | IFF_NOARP,
+						       extack);
 			} else {
 				err = dev_change_flags(ipvlan->dev,
-						       flags & ~IFF_NOARP);
+						       flags & ~IFF_NOARP,
+						       extack);
 			}
 			if (unlikely(err))
 				goto fail;
@@ -117,9 +119,11 @@ fail:
 		flags = ipvlan->dev->flags;
 		if (port->mode == IPVLAN_MODE_L3 ||
 		    port->mode == IPVLAN_MODE_L3S)
-			dev_change_flags(ipvlan->dev, flags | IFF_NOARP);
+			dev_change_flags(ipvlan->dev, flags | IFF_NOARP,
+					 NULL);
 		else
-			dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP);
+			dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP,
+					 NULL);
 	}
 
 	return err;
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 1e9f2dc0de07..95909e262ba4 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -756,9 +756,9 @@ static void cycle_netdev(struct net_device *dev,
 	if (!netif_running(dev))
 		return;
 
-	ret = dev_change_flags(dev, flags & ~IFF_UP);
+	ret = dev_change_flags(dev, flags & ~IFF_UP, extack);
 	if (ret >= 0)
-		ret = dev_change_flags(dev, flags);
+		ret = dev_change_flags(dev, flags, extack);
 
 	if (ret < 0) {
 		netdev_err(dev,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d79be3055f5f..18cf464450ee 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3612,7 +3612,8 @@ int dev_ifconf(struct net *net, struct ifconf *, int);
 int dev_ethtool(struct net *net, struct ifreq *);
 unsigned int dev_get_flags(const struct net_device *);
 int __dev_change_flags(struct net_device *, unsigned int flags);
-int dev_change_flags(struct net_device *, unsigned int);
+int dev_change_flags(struct net_device *dev, unsigned int flags,
+		     struct netlink_ext_ack *extack);
 void __dev_notify_flags(struct net_device *, unsigned int old_flags,
 			unsigned int gchanges);
 int dev_change_name(struct net_device *, const char *);
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index aef1a977279c..dc4411165e43 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -358,6 +358,7 @@ static int __vlan_device_event(struct net_device *dev, unsigned long event)
 static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			     void *ptr)
 {
+	struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr);
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct vlan_group *grp;
 	struct vlan_info *vlan_info;
@@ -460,7 +461,8 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 
 			vlan = vlan_dev_priv(vlandev);
 			if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
-				dev_change_flags(vlandev, flgs | IFF_UP);
+				dev_change_flags(vlandev, flgs | IFF_UP,
+						 extack);
 			netif_stacked_transfer_operstate(dev, vlandev);
 		}
 		break;
diff --git a/net/core/dev.c b/net/core/dev.c
index b801c1aafd70..8bba6f98b545 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7595,11 +7595,13 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
  *	dev_change_flags - change device settings
  *	@dev: device
  *	@flags: device state flags
+ *	@extack: netlink extended ack
  *
  *	Change settings on device based state flags. The flags are
  *	in the userspace exported format.
  */
-int dev_change_flags(struct net_device *dev, unsigned int flags)
+int dev_change_flags(struct net_device *dev, unsigned int flags,
+		     struct netlink_ext_ack *extack)
 {
 	int ret;
 	unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags;
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 90e8aa36881e..da273ec3cc57 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -234,7 +234,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 
 	switch (cmd) {
 	case SIOCSIFFLAGS:	/* Set interface flags */
-		return dev_change_flags(dev, ifr->ifr_flags);
+		return dev_change_flags(dev, ifr->ifr_flags, NULL);
 
 	case SIOCSIFMETRIC:	/* Set the metric on the interface
 				   (currently unused) */
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index bd67c4d0fcfd..ff9fd2bb4ce4 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -337,7 +337,7 @@ NETDEVICE_SHOW_RW(mtu, fmt_dec);
 
 static int change_flags(struct net_device *dev, unsigned long new_flags)
 {
-	return dev_change_flags(dev, (unsigned int)new_flags);
+	return dev_change_flags(dev, (unsigned int)new_flags, NULL);
 }
 
 static ssize_t flags_store(struct device *dev, struct device_attribute *attr,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 98876cd1e36c..4c9e4e187600 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2489,7 +2489,8 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 
 	if (ifm->ifi_flags || ifm->ifi_change) {
-		err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm));
+		err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
+				       extack);
 		if (err < 0)
 			goto errout;
 	}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index a34602ae27de..5b9b6d497f71 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1100,7 +1100,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr)
 				inet_del_ifa(in_dev, ifap, 1);
 			break;
 		}
-		ret = dev_change_flags(dev, ifr->ifr_flags);
+		ret = dev_change_flags(dev, ifr->ifr_flags, NULL);
 		break;
 
 	case SIOCSIFADDR:	/* Set interface address (and family) */
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 88212615bf4c..55757764c381 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -220,7 +220,7 @@ static int __init ic_open_devs(void)
 	for_each_netdev(&init_net, dev) {
 		if (!(dev->flags & IFF_LOOPBACK) && !netdev_uses_dsa(dev))
 			continue;
-		if (dev_change_flags(dev, dev->flags | IFF_UP) < 0)
+		if (dev_change_flags(dev, dev->flags | IFF_UP, NULL) < 0)
 			pr_err("IP-Config: Failed to open %s\n", dev->name);
 	}
 
@@ -238,7 +238,7 @@ static int __init ic_open_devs(void)
 			if (ic_proto_enabled && !able)
 				continue;
 			oflags = dev->flags;
-			if (dev_change_flags(dev, oflags | IFF_UP) < 0) {
+			if (dev_change_flags(dev, oflags | IFF_UP, NULL) < 0) {
 				pr_err("IP-Config: Failed to open %s\n",
 				       dev->name);
 				continue;
@@ -315,7 +315,7 @@ static void __init ic_close_devs(void)
 		dev = d->dev;
 		if (d != ic_dev && !netdev_uses_dsa(dev)) {
 			pr_debug("IP-Config: Downing %s\n", dev->name);
-			dev_change_flags(dev, d->flags);
+			dev_change_flags(dev, d->flags, NULL);
 		}
 		kfree(d);
 	}
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
index 5aaf3babfc3f..acb6077b7478 100644
--- a/net/openvswitch/vport-geneve.c
+++ b/net/openvswitch/vport-geneve.c
@@ -93,7 +93,7 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms)
 		return ERR_CAST(dev);
 	}
 
-	err = dev_change_flags(dev, dev->flags | IFF_UP);
+	err = dev_change_flags(dev, dev->flags | IFF_UP, NULL);
 	if (err < 0) {
 		rtnl_delete_link(dev);
 		rtnl_unlock();
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index 0e72d95b0e8f..c38a62464b85 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -68,7 +68,7 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms)
 		return ERR_CAST(dev);
 	}
 
-	err = dev_change_flags(dev, dev->flags | IFF_UP);
+	err = dev_change_flags(dev, dev->flags | IFF_UP, NULL);
 	if (err < 0) {
 		rtnl_delete_link(dev);
 		rtnl_unlock();
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 7e6301b2ec4d..8f16f11f7ad3 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -131,7 +131,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
 		return ERR_CAST(dev);
 	}
 
-	err = dev_change_flags(dev, dev->flags | IFF_UP);
+	err = dev_change_flags(dev, dev->flags | IFF_UP, NULL);
 	if (err < 0) {
 		rtnl_delete_link(dev);
 		rtnl_unlock();
-- 
cgit v1.2.3


From 6d0403216d030e5623de3911168fceeaac2e14d6 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 6 Dec 2018 17:05:43 +0000
Subject: net: core: dev: Add extack argument to __dev_change_flags()

In order to pass extack together with NETDEV_PRE_UP notifications, it's
necessary to route the extack to __dev_open() from diverse (possibly
indirect) callers. The last missing API is __dev_change_flags().

Therefore extend __dev_change_flags() with and extra extack argument and
update the two existing users.

Since the function declaration line is changed anyway, name the struct
net_device argument to placate checkpatch.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 3 ++-
 net/core/dev.c            | 5 +++--
 net/core/rtnetlink.c      | 3 ++-
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 18cf464450ee..fc6ba71513be 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3611,7 +3611,8 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr,
 int dev_ifconf(struct net *net, struct ifconf *, int);
 int dev_ethtool(struct net *net, struct ifreq *);
 unsigned int dev_get_flags(const struct net_device *);
-int __dev_change_flags(struct net_device *, unsigned int flags);
+int __dev_change_flags(struct net_device *dev, unsigned int flags,
+		       struct netlink_ext_ack *extack);
 int dev_change_flags(struct net_device *dev, unsigned int flags,
 		     struct netlink_ext_ack *extack);
 void __dev_notify_flags(struct net_device *, unsigned int old_flags,
diff --git a/net/core/dev.c b/net/core/dev.c
index 8bba6f98b545..b37e320def13 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7498,7 +7498,8 @@ unsigned int dev_get_flags(const struct net_device *dev)
 }
 EXPORT_SYMBOL(dev_get_flags);
 
-int __dev_change_flags(struct net_device *dev, unsigned int flags)
+int __dev_change_flags(struct net_device *dev, unsigned int flags,
+		       struct netlink_ext_ack *extack)
 {
 	unsigned int old_flags = dev->flags;
 	int ret;
@@ -7606,7 +7607,7 @@ int dev_change_flags(struct net_device *dev, unsigned int flags,
 	int ret;
 	unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags;
 
-	ret = __dev_change_flags(dev, flags);
+	ret = __dev_change_flags(dev, flags, extack);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4c9e4e187600..91a0f7477f8e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2871,7 +2871,8 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 
 	old_flags = dev->flags;
 	if (ifm && (ifm->ifi_flags || ifm->ifi_change)) {
-		err = __dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm));
+		err = __dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
+					 NULL);
 		if (err < 0)
 			return err;
 	}
-- 
cgit v1.2.3


From 263726053400b9c6671df8e87d3db9728199da13 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 6 Dec 2018 17:05:45 +0000
Subject: net: core: dev: Add call_netdevice_notifiers_extack()

In order to propagate extack through NETDEV_PRE_UP, add a new function
call_netdevice_notifiers_extack() that primes the extack field of the
notifier info. Convert call_netdevice_notifiers() to a simple wrapper
around the new function that passes NULL for extack.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index b37e320def13..4b033af8e6cd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -162,6 +162,9 @@ static struct list_head offload_base __read_mostly;
 static int netif_rx_internal(struct sk_buff *skb);
 static int call_netdevice_notifiers_info(unsigned long val,
 					 struct netdev_notifier_info *info);
+static int call_netdevice_notifiers_extack(unsigned long val,
+					   struct net_device *dev,
+					   struct netlink_ext_ack *extack);
 static struct napi_struct *napi_by_id(unsigned int napi_id);
 
 /*
@@ -1734,6 +1737,18 @@ static int call_netdevice_notifiers_info(unsigned long val,
 	return raw_notifier_call_chain(&netdev_chain, val, info);
 }
 
+static int call_netdevice_notifiers_extack(unsigned long val,
+					   struct net_device *dev,
+					   struct netlink_ext_ack *extack)
+{
+	struct netdev_notifier_info info = {
+		.dev = dev,
+		.extack = extack,
+	};
+
+	return call_netdevice_notifiers_info(val, &info);
+}
+
 /**
  *	call_netdevice_notifiers - call all network notifier blocks
  *      @val: value passed unmodified to notifier function
@@ -1745,11 +1760,7 @@ static int call_netdevice_notifiers_info(unsigned long val,
 
 int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 {
-	struct netdev_notifier_info info = {
-		.dev = dev,
-	};
-
-	return call_netdevice_notifiers_info(val, &info);
+	return call_netdevice_notifiers_extack(val, dev, NULL);
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
-- 
cgit v1.2.3


From 40c900aa1ff580afe941ff77f327f004546f0ce7 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 6 Dec 2018 17:05:47 +0000
Subject: net: core: dev: Attach extack to NETDEV_PRE_UP

Drivers may need to validate configuration of a device that's about to
be upped. Should the validation fail, there's currently no way to
communicate details of the failure to the user, beyond an error number.

To mend that, change __dev_open() to take an extack argument and pass it
from __dev_change_flags() and dev_open(), where it was propagated in the
previous patches.

Change __dev_open() to call call_netdevice_notifiers_extack() so that
the passed-in extack is attached to the NETDEV_PRE_UP notifier.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 4b033af8e6cd..068b60db35ae 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1364,7 +1364,7 @@ void netdev_notify_peers(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_notify_peers);
 
-static int __dev_open(struct net_device *dev)
+static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int ret;
@@ -1380,7 +1380,7 @@ static int __dev_open(struct net_device *dev)
 	 */
 	netpoll_poll_disable(dev);
 
-	ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
+	ret = call_netdevice_notifiers_extack(NETDEV_PRE_UP, dev, extack);
 	ret = notifier_to_errno(ret);
 	if (ret)
 		return ret;
@@ -1427,7 +1427,7 @@ int dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 	if (dev->flags & IFF_UP)
 		return 0;
 
-	ret = __dev_open(dev);
+	ret = __dev_open(dev, extack);
 	if (ret < 0)
 		return ret;
 
@@ -7547,7 +7547,7 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags,
 		if (old_flags & IFF_UP)
 			__dev_close(dev);
 		else
-			ret = __dev_open(dev);
+			ret = __dev_open(dev, extack);
 	}
 
 	if ((flags ^ dev->gflags) & IFF_PROMISC) {
-- 
cgit v1.2.3


From 1ba1daed90e235f297f60443128a3acfc05aac7b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 6 Dec 2018 17:05:48 +0000
Subject: selftests: mlxsw: Add a new test extack.sh

Add a testsuite dedicated to testing extack propagation and related
functionality.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/drivers/net/mlxsw/extack.sh  | 84 ++++++++++++++++++++++
 1 file changed, 84 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/extack.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/extack.sh b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
new file mode 100755
index 000000000000..101a5508bdfd
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
@@ -0,0 +1,84 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test operations that we expect to report extended ack.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	netdev_pre_up_test
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+
+	ip link set dev $swp1 up
+	ip link set dev $swp2 up
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link set dev $swp2 down
+	ip link set dev $swp1 down
+}
+
+netdev_pre_up_test()
+{
+	RET=0
+
+	ip link add name br1 up type bridge vlan_filtering 0 mcast_snooping 0
+	ip link add name vx1 up type vxlan id 1000 \
+		local 192.0.2.17 remote 192.0.2.18 \
+		dstport 4789 nolearning noudpcsum tos inherit ttl 100
+
+	ip link set dev vx1 master br1
+	check_err $?
+
+	ip link set dev $swp1 master br1
+	check_err $?
+
+	ip link add name br2 up type bridge vlan_filtering 0 mcast_snooping 0
+	ip link add name vx2 up type vxlan id 2000 \
+		local 192.0.2.17 remote 192.0.2.18 \
+		dstport 4789 nolearning noudpcsum tos inherit ttl 100
+
+	ip link set dev vx2 master br2
+	check_err $?
+
+	ip link set dev $swp2 master br2
+	check_err $?
+
+	# Unsupported configuration: mlxsw demands that all offloaded VXLAN
+	# devices have the same TTL.
+	ip link set dev vx2 down
+	ip link set dev vx2 type vxlan ttl 200
+
+	ip link set dev vx2 up &>/dev/null
+	check_fail $?
+
+	ip link set dev vx2 up 2>&1 >/dev/null | grep -q mlxsw_spectrum
+	check_err $?
+
+	log_test "extack - NETDEV_PRE_UP"
+
+	ip link del dev vx2
+	ip link del dev br2
+
+	ip link del dev vx1
+	ip link del dev br1
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 3fd3c80acc172fcaab2356c15e5e3c05758a9d51 Mon Sep 17 00:00:00 2001
From: Danit Goldberg <danitg@mellanox.com>
Date: Fri, 30 Nov 2018 13:22:04 +0200
Subject: net/mlx5: Expose packet based credit mode

Packet based credit mode bit determines whether the credit mode
is done per message or packet. Expose the QP creation flag and
the HCA capability.

Signed-off-by: Danit Goldberg <danitg@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ece1b606c909..91d6e85e3cef 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1047,7 +1047,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         vector_calc[0x1];
 	u8         umr_ptr_rlky[0x1];
 	u8	   imaicl[0x1];
-	u8         reserved_at_232[0x4];
+	u8	   qp_packet_based[0x1];
+	u8         reserved_at_233[0x3];
 	u8         qkv[0x1];
 	u8         pkv[0x1];
 	u8         set_deth_sqpn[0x1];
@@ -2259,7 +2260,8 @@ struct mlx5_ifc_qpc_bits {
 	u8         st[0x8];
 	u8         reserved_at_10[0x3];
 	u8         pm_state[0x2];
-	u8         reserved_at_15[0x3];
+	u8         reserved_at_15[0x1];
+	u8         req_e2e_credit_mode[0x2];
 	u8         offload_type[0x4];
 	u8         end_padding_mode[0x2];
 	u8         reserved_at_1e[0x2];
-- 
cgit v1.2.3


From 474fb1150d40780e71f0b569aeac4f375df3af3d Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Fri, 7 Dec 2018 14:00:11 +0000
Subject: net: aquantia: fix RSS table and key sizes

Set RSS indirection table and RSS hash key sizes to their real size.

Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_cfg.h | 4 ++--
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
index 91eb8910b1c9..90a0e1d0d622 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
@@ -42,8 +42,8 @@
 #define AQ_CFG_IS_LRO_DEF           1U
 
 /* RSS */
-#define AQ_CFG_RSS_INDIRECTION_TABLE_MAX  128U
-#define AQ_CFG_RSS_HASHKEY_SIZE           320U
+#define AQ_CFG_RSS_INDIRECTION_TABLE_MAX  64U
+#define AQ_CFG_RSS_HASHKEY_SIZE           40U
 
 #define AQ_CFG_IS_RSS_DEF           1U
 #define AQ_CFG_NUM_RSS_QUEUES_DEF   AQ_CFG_VECS_DEF
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 279ea58f4a9e..d617289d95f7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -44,7 +44,7 @@ static void aq_nic_rss_init(struct aq_nic_s *self, unsigned int num_rss_queues)
 	struct aq_rss_parameters *rss_params = &cfg->aq_rss;
 	int i = 0;
 
-	static u8 rss_key[40] = {
+	static u8 rss_key[AQ_CFG_RSS_HASHKEY_SIZE] = {
 		0x1e, 0xad, 0x71, 0x87, 0x65, 0xfc, 0x26, 0x7d,
 		0x0d, 0x45, 0x67, 0x74, 0xcd, 0x06, 0x1a, 0x18,
 		0xb6, 0xc1, 0xf0, 0xc7, 0xbb, 0x18, 0xbe, 0xf8,
-- 
cgit v1.2.3


From 71a963cfc50b0309ca3192c7258569e0d5477ab0 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Fri, 7 Dec 2018 14:00:15 +0000
Subject: net: aquantia: increase max number of hw queues

Increase the upper limit of the hw queues up to 8.
This makes RSS better on multiheaded cpus.

This is a maximum AQC hardware supports in one traffic class.

The actual value is still limited by a number of available cpu cores.

Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_cfg.h           | 2 +-
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
index 90a0e1d0d622..3944ce7f0870 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
@@ -12,7 +12,7 @@
 #ifndef AQ_CFG_H
 #define AQ_CFG_H
 
-#define AQ_CFG_VECS_DEF   4U
+#define AQ_CFG_VECS_DEF   8U
 #define AQ_CFG_TCS_DEF    1U
 
 #define AQ_CFG_TXDS_DEF    4096U
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 6af7d7f0cdca..08596a7a6486 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -21,7 +21,7 @@
 
 #define DEFAULT_B0_BOARD_BASIC_CAPABILITIES \
 	.is_64_dma = true,		  \
-	.msix_irqs = 4U,		  \
+	.msix_irqs = 8U,		  \
 	.irq_mask = ~0U,		  \
 	.vecs = HW_ATL_B0_RSS_MAX,	  \
 	.tcs = HW_ATL_B0_TC_MAX,	  \
-- 
cgit v1.2.3


From a8c69ca79217c8f1d070e470066cc24d8f866d6e Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Fri, 7 Dec 2018 14:00:17 +0000
Subject: net: aquantia: fix initialization of RSS table

Now RSS indirection table is initialized before setting up the number of
hw queues, consequently the table may be filled by non existing queues.
This patch moves the initialization when the number of hw queues is
known.

Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index d617289d95f7..0147c037ca96 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -84,8 +84,6 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 
 	cfg->is_lro = AQ_CFG_IS_LRO_DEF;
 
-	aq_nic_rss_init(self, cfg->num_rss_queues);
-
 	/*descriptors */
 	cfg->rxds = min(cfg->aq_hw_caps->rxds_max, AQ_CFG_RXDS_DEF);
 	cfg->txds = min(cfg->aq_hw_caps->txds_max, AQ_CFG_TXDS_DEF);
@@ -106,6 +104,8 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 
 	cfg->num_rss_queues = min(cfg->vecs, AQ_CFG_NUM_RSS_QUEUES_DEF);
 
+	aq_nic_rss_init(self, cfg->num_rss_queues);
+
 	cfg->irq_type = aq_pci_func_get_irq_type(self);
 
 	if ((cfg->irq_type == AQ_HW_IRQ_LEGACY) ||
-- 
cgit v1.2.3


From 391637676fc9a2d545e51efbb11dd8dc3faf604f Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Fri, 7 Dec 2018 14:00:22 +0000
Subject: net: aquantia: add support of RSS configuration

Add support of configuration of RSS hash key and RSS indirection table.

Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_ethtool.c    | 36 ++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 43b42615ad84..38e87eed76b9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -202,6 +202,41 @@ static int aq_ethtool_get_rss(struct net_device *ndev, u32 *indir, u8 *key,
 	return 0;
 }
 
+static int aq_ethtool_set_rss(struct net_device *netdev, const u32 *indir,
+			      const u8 *key, const u8 hfunc)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(netdev);
+	struct aq_nic_cfg_s *cfg;
+	unsigned int i = 0U;
+	u32 rss_entries;
+	int err = 0;
+
+	cfg = aq_nic_get_cfg(aq_nic);
+	rss_entries = cfg->aq_rss.indirection_table_size;
+
+	/* We do not allow change in unsupported parameters */
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+	/* Fill out the redirection table */
+	if (indir)
+		for (i = 0; i < rss_entries; i++)
+			cfg->aq_rss.indirection_table[i] = indir[i];
+
+	/* Fill out the rss hash key */
+	if (key) {
+		memcpy(cfg->aq_rss.hash_secret_key, key,
+		       sizeof(cfg->aq_rss.hash_secret_key));
+		err = aq_nic->aq_hw_ops->hw_rss_hash_set(aq_nic->aq_hw,
+			&cfg->aq_rss);
+		if (err)
+			return err;
+	}
+
+	err = aq_nic->aq_hw_ops->hw_rss_set(aq_nic->aq_hw, &cfg->aq_rss);
+
+	return err;
+}
+
 static int aq_ethtool_get_rxnfc(struct net_device *ndev,
 				struct ethtool_rxnfc *cmd,
 				u32 *rule_locs)
@@ -549,6 +584,7 @@ const struct ethtool_ops aq_ethtool_ops = {
 	.set_pauseparam      = aq_ethtool_set_pauseparam,
 	.get_rxfh_key_size   = aq_ethtool_get_rss_key_size,
 	.get_rxfh            = aq_ethtool_get_rss,
+	.set_rxfh            = aq_ethtool_set_rss,
 	.get_rxnfc           = aq_ethtool_get_rxnfc,
 	.set_rxnfc           = aq_ethtool_set_rxnfc,
 	.get_sset_count      = aq_ethtool_get_sset_count,
-- 
cgit v1.2.3


From ff23b91ce1ae686e436e9926de1fda3342ef26f8 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:03 +0000
Subject: vxlan: Add a function to init switchdev_notifier_vxlan_fdb_info

There are currently two places that need to initialize the notifier info
structure, and one more is coming next when vxlan_fdb_replay() is
introduced. These three instances have / will have very similar code
that is easy to abstract away into a named function.

Add such function, vxlan_fdb_switchdev_notifier_info(), and call it from
vxlan_fdb_switchdev_call_notifiers() and vxlan_fdb_find_uc().

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 41 ++++++++++++++++++-----------------------
 1 file changed, 18 insertions(+), 23 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 901eef428280..d3db0313c97e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -358,6 +358,22 @@ errout:
 		rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
 }
 
+static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan,
+			    const struct vxlan_fdb *fdb,
+			    const struct vxlan_rdst *rd,
+			    struct switchdev_notifier_vxlan_fdb_info *fdb_info)
+{
+	fdb_info->info.dev = vxlan->dev;
+	fdb_info->remote_ip = rd->remote_ip;
+	fdb_info->remote_port = rd->remote_port;
+	fdb_info->remote_vni = rd->remote_vni;
+	fdb_info->remote_ifindex = rd->remote_ifindex;
+	memcpy(fdb_info->eth_addr, fdb->eth_addr, ETH_ALEN);
+	fdb_info->vni = fdb->vni;
+	fdb_info->offloaded = rd->offloaded;
+	fdb_info->added_by_user = fdb->flags & NTF_VXLAN_ADDED_BY_USER;
+}
+
 static void vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan,
 					       struct vxlan_fdb *fdb,
 					       struct vxlan_rdst *rd,
@@ -371,18 +387,7 @@ static void vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan,
 
 	notifier_type = adding ? SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE
 			       : SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE;
-
-	info = (struct switchdev_notifier_vxlan_fdb_info){
-		.remote_ip = rd->remote_ip,
-		.remote_port = rd->remote_port,
-		.remote_vni = rd->remote_vni,
-		.remote_ifindex = rd->remote_ifindex,
-		.vni = fdb->vni,
-		.offloaded = rd->offloaded,
-		.added_by_user = fdb->flags & NTF_VXLAN_ADDED_BY_USER,
-	};
-	memcpy(info.eth_addr, fdb->eth_addr, ETH_ALEN);
-
+	vxlan_fdb_switchdev_notifier_info(vxlan, fdb, rd, &info);
 	call_switchdev_notifiers(notifier_type, vxlan->dev,
 				 &info.info);
 }
@@ -539,17 +544,7 @@ int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni,
 	}
 
 	rdst = first_remote_rcu(f);
-
-	memset(fdb_info, 0, sizeof(*fdb_info));
-	fdb_info->info.dev = dev;
-	fdb_info->remote_ip = rdst->remote_ip;
-	fdb_info->remote_port = rdst->remote_port;
-	fdb_info->remote_vni = rdst->remote_vni;
-	fdb_info->remote_ifindex = rdst->remote_ifindex;
-	fdb_info->vni = vni;
-	fdb_info->offloaded = rdst->offloaded;
-	fdb_info->added_by_user = f->flags & NTF_VXLAN_ADDED_BY_USER;
-	ether_addr_copy(fdb_info->eth_addr, mac);
+	vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, fdb_info);
 
 out:
 	rcu_read_unlock();
-- 
cgit v1.2.3


From 4f89f5b5353cae2e056713e823819f24cad92bc3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:04 +0000
Subject: vxlan: Add vxlan_fdb_replay()

When a VXLAN device becomes relevant to a driver (such as when it is
attached to an offloaded bridge), the driver will generally need to walk
the existing FDB entries and offload them.

Add a function vxlan_fdb_replay() to call a given notifier block for
each FDB entry with a given VNI.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 include/net/vxlan.h |  9 +++++++++
 2 files changed, 56 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d3db0313c97e..d9cb0d903283 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -552,6 +552,53 @@ out:
 }
 EXPORT_SYMBOL_GPL(vxlan_fdb_find_uc);
 
+static int vxlan_fdb_notify_one(struct notifier_block *nb,
+				const struct vxlan_dev *vxlan,
+				const struct vxlan_fdb *f,
+				const struct vxlan_rdst *rdst)
+{
+	struct switchdev_notifier_vxlan_fdb_info fdb_info;
+	int rc;
+
+	vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, &fdb_info);
+	rc = nb->notifier_call(nb, SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE,
+			       &fdb_info);
+	return notifier_to_errno(rc);
+}
+
+int vxlan_fdb_replay(const struct net_device *dev, __be32 vni,
+		     struct notifier_block *nb)
+{
+	struct vxlan_dev *vxlan;
+	struct vxlan_rdst *rdst;
+	struct vxlan_fdb *f;
+	unsigned int h;
+	int rc = 0;
+
+	if (!netif_is_vxlan(dev))
+		return -EINVAL;
+	vxlan = netdev_priv(dev);
+
+	spin_lock_bh(&vxlan->hash_lock);
+	for (h = 0; h < FDB_HASH_SIZE; ++h) {
+		hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) {
+			if (f->vni == vni) {
+				list_for_each_entry(rdst, &f->remotes, list) {
+					rc = vxlan_fdb_notify_one(nb, vxlan,
+								  f, rdst);
+					if (rc)
+						goto out;
+				}
+			}
+		}
+	}
+
+out:
+	spin_unlock_bh(&vxlan->hash_lock);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(vxlan_fdb_replay);
+
 /* Replace destination of unicast mac */
 static int vxlan_fdb_replace(struct vxlan_fdb *f,
 			     union vxlan_addr *ip, __be16 port, __be32 vni,
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index b73c670df184..f49aa9afe598 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -427,6 +427,9 @@ struct switchdev_notifier_vxlan_fdb_info {
 #if IS_ENABLED(CONFIG_VXLAN)
 int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni,
 		      struct switchdev_notifier_vxlan_fdb_info *fdb_info);
+int vxlan_fdb_replay(const struct net_device *dev, __be32 vni,
+		     struct notifier_block *nb);
+
 #else
 static inline int
 vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni,
@@ -434,6 +437,12 @@ vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni,
 {
 	return -ENOENT;
 }
+
+static inline int vxlan_fdb_replay(const struct net_device *dev, __be32 vni,
+				   struct notifier_block *nb)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 #endif
-- 
cgit v1.2.3


From e5ff4b1952893fb75aa75067fce31c8567341ed7 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:06 +0000
Subject: vxlan: Add vxlan_fdb_clear_offload()

When a driver unoffloads all FDB entries en bloc, it's inefficient to
send the switchdev notification one by one. Add a helper that walks the
FDB table, unsetting the offload flag on RDST with a given VNI.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 22 ++++++++++++++++++++++
 include/net/vxlan.h |  6 ++++++
 2 files changed, 28 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d9cb0d903283..b56ef684ecac 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -599,6 +599,28 @@ out:
 }
 EXPORT_SYMBOL_GPL(vxlan_fdb_replay);
 
+void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni)
+{
+	struct vxlan_dev *vxlan;
+	struct vxlan_rdst *rdst;
+	struct vxlan_fdb *f;
+	unsigned int h;
+
+	if (!netif_is_vxlan(dev))
+		return;
+	vxlan = netdev_priv(dev);
+
+	spin_lock_bh(&vxlan->hash_lock);
+	for (h = 0; h < FDB_HASH_SIZE; ++h) {
+		hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist)
+			if (f->vni == vni)
+				list_for_each_entry(rdst, &f->remotes, list)
+					rdst->offloaded = false;
+	}
+	spin_unlock_bh(&vxlan->hash_lock);
+}
+EXPORT_SYMBOL_GPL(vxlan_fdb_clear_offload);
+
 /* Replace destination of unicast mac */
 static int vxlan_fdb_replace(struct vxlan_fdb *f,
 			     union vxlan_addr *ip, __be16 port, __be32 vni,
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index f49aa9afe598..236403eb5ba6 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -429,6 +429,7 @@ int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni,
 		      struct switchdev_notifier_vxlan_fdb_info *fdb_info);
 int vxlan_fdb_replay(const struct net_device *dev, __be32 vni,
 		     struct notifier_block *nb);
+void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni);
 
 #else
 static inline int
@@ -443,6 +444,11 @@ static inline int vxlan_fdb_replay(const struct net_device *dev, __be32 vni,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline void
+vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni)
+{
+}
 #endif
 
 #endif
-- 
cgit v1.2.3


From 43920edf3b24b0a3d136019c816e84ffcbef83ab Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:07 +0000
Subject: bridge: Add br_fdb_clear_offload()

When a driver unoffloads all FDB entries en bloc, it's inefficient to
send the switchdev notification one by one. Add a helper that unsets the
offload flag on FDB entries on a given bridge port and VLAN.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h |  6 ++++++
 net/bridge/br_fdb.c       | 20 ++++++++++++++++++++
 2 files changed, 26 insertions(+)

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index ef7c3d376b21..627b788ba0ff 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -119,6 +119,7 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid,
 struct net_device *br_fdb_find_port(const struct net_device *br_dev,
 				    const unsigned char *addr,
 				    __u16 vid);
+void br_fdb_clear_offload(const struct net_device *dev, u16 vid);
 bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag);
 #else
 static inline struct net_device *
@@ -128,6 +129,11 @@ br_fdb_find_port(const struct net_device *br_dev,
 {
 	return NULL;
 }
+
+static inline void br_fdb_clear_offload(const struct net_device *dev, u16 vid)
+{
+}
+
 static inline bool
 br_port_flag_is_set(const struct net_device *dev, unsigned long flag)
 {
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index e56ba3912a90..38b1d0dd0529 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -1164,3 +1164,23 @@ void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p,
 
 	spin_unlock_bh(&br->hash_lock);
 }
+
+void br_fdb_clear_offload(const struct net_device *dev, u16 vid)
+{
+	struct net_bridge_fdb_entry *f;
+	struct net_bridge_port *p;
+
+	ASSERT_RTNL();
+
+	p = br_port_get_rtnl(dev);
+	if (!p)
+		return;
+
+	spin_lock_bh(&p->br->hash_lock);
+	hlist_for_each_entry(f, &p->br->fdb_list, fdb_node) {
+		if (f->dst == p && f->key.vlan_id == vid)
+			f->offloaded = 0;
+	}
+	spin_unlock_bh(&p->br->hash_lock);
+}
+EXPORT_SYMBOL_GPL(br_fdb_clear_offload);
-- 
cgit v1.2.3


From 2a36c12520683b17ce3fff674446313482e5ab5e Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:09 +0000
Subject: mlxsw: spectrum: Track NVE type at FIDs

A follow-up patch will add support for replay and for clearing of
offload marks. These are NVE type-sensitive operations, and to be able
to dispatch them properly, a FID needs to know what NVE type is attached
to it.

Therefore, track the NVE type at struct mlxsw_sp_fid. Extend
mlxsw_sp_fid_vni_set() to take it as an argument, and add
mlxsw_sp_fid_nve_type().

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     | 13 ++++++++-----
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c | 16 +++++++++++++++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c |  3 ++-
 3 files changed, 25 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index a3e564e0da39..00d783136d11 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -81,6 +81,10 @@ enum mlxsw_sp_fid_type {
 	MLXSW_SP_FID_TYPE_MAX,
 };
 
+enum mlxsw_sp_nve_type {
+	MLXSW_SP_NVE_TYPE_VXLAN,
+};
+
 struct mlxsw_sp_mid {
 	struct list_head list;
 	unsigned char addr[ETH_ALEN];
@@ -745,6 +749,8 @@ bool mlxsw_sp_fid_lag_vid_valid(const struct mlxsw_sp_fid *fid);
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp,
 						  u16 fid_index);
 int mlxsw_sp_fid_nve_ifindex(const struct mlxsw_sp_fid *fid, int *nve_ifindex);
+int mlxsw_sp_fid_nve_type(const struct mlxsw_sp_fid *fid,
+			  enum mlxsw_sp_nve_type *p_type);
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_vni(struct mlxsw_sp *mlxsw_sp,
 						__be32 vni);
 int mlxsw_sp_fid_vni(const struct mlxsw_sp_fid *fid, __be32 *vni);
@@ -752,7 +758,8 @@ int mlxsw_sp_fid_nve_flood_index_set(struct mlxsw_sp_fid *fid,
 				     u32 nve_flood_index);
 void mlxsw_sp_fid_nve_flood_index_clear(struct mlxsw_sp_fid *fid);
 bool mlxsw_sp_fid_nve_flood_index_is_set(const struct mlxsw_sp_fid *fid);
-int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, __be32 vni, int nve_ifindex);
+int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, enum mlxsw_sp_nve_type type,
+			 __be32 vni, int nve_ifindex);
 void mlxsw_sp_fid_vni_clear(struct mlxsw_sp_fid *fid);
 bool mlxsw_sp_fid_vni_is_set(const struct mlxsw_sp_fid *fid);
 int mlxsw_sp_fid_flood_set(struct mlxsw_sp_fid *fid,
@@ -823,10 +830,6 @@ extern const struct mlxsw_sp_mr_tcam_ops mlxsw_sp1_mr_tcam_ops;
 extern const struct mlxsw_sp_mr_tcam_ops mlxsw_sp2_mr_tcam_ops;
 
 /* spectrum_nve.c */
-enum mlxsw_sp_nve_type {
-	MLXSW_SP_NVE_TYPE_VXLAN,
-};
-
 struct mlxsw_sp_nve_params {
 	enum mlxsw_sp_nve_type type;
 	__be32 vni;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index f9af68230455..fe16e0be716e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -30,6 +30,7 @@ struct mlxsw_sp_fid {
 	struct rhash_head ht_node;
 
 	struct rhash_head vni_ht_node;
+	enum mlxsw_sp_nve_type nve_type;
 	__be32 vni;
 	u32 nve_flood_index;
 	int nve_ifindex;
@@ -151,6 +152,17 @@ int mlxsw_sp_fid_nve_ifindex(const struct mlxsw_sp_fid *fid, int *nve_ifindex)
 	return 0;
 }
 
+int mlxsw_sp_fid_nve_type(const struct mlxsw_sp_fid *fid,
+			  enum mlxsw_sp_nve_type *p_type)
+{
+	if (!fid->vni_valid)
+		return -EINVAL;
+
+	*p_type = fid->nve_type;
+
+	return 0;
+}
+
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_vni(struct mlxsw_sp *mlxsw_sp,
 						__be32 vni)
 {
@@ -211,7 +223,8 @@ bool mlxsw_sp_fid_nve_flood_index_is_set(const struct mlxsw_sp_fid *fid)
 	return fid->nve_flood_index_valid;
 }
 
-int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, __be32 vni, int nve_ifindex)
+int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, enum mlxsw_sp_nve_type type,
+			 __be32 vni, int nve_ifindex)
 {
 	struct mlxsw_sp_fid_family *fid_family = fid->fid_family;
 	const struct mlxsw_sp_fid_ops *ops = fid_family->ops;
@@ -221,6 +234,7 @@ int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, __be32 vni, int nve_ifindex)
 	if (WARN_ON(!ops->vni_set || fid->vni_valid))
 		return -EINVAL;
 
+	fid->nve_type = type;
 	fid->nve_ifindex = nve_ifindex;
 	fid->vni = vni;
 	err = rhashtable_lookup_insert_fast(&mlxsw_sp->fid_core->vni_ht,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
index c4d5a0865c8f..e8e4cb6dfd38 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
@@ -817,7 +817,8 @@ int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid,
 		return err;
 	}
 
-	err = mlxsw_sp_fid_vni_set(fid, params->vni, params->dev->ifindex);
+	err = mlxsw_sp_fid_vni_set(fid, params->type, params->vni,
+				   params->dev->ifindex);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed to set VNI on FID");
 		goto err_fid_vni_set;
-- 
cgit v1.2.3


From 34139ede051ea8a10643c615076cb9dadc2a0942 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:11 +0000
Subject: mlxsw: spectrum_switchdev: Publish mlxsw_sp_switchdev_notifier

The notifier block will need to be passed to vxlan_fdb_replay() in a
follow-up patch.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 00d783136d11..6b0dc40fa213 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -387,6 +387,7 @@ int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 			       struct netlink_ext_ack *extack);
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 				 const struct net_device *vxlan_dev);
+extern struct notifier_block mlxsw_sp_switchdev_notifier;
 
 /* spectrum.c */
 int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 7c38231bbd89..402f652cbf1b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -3186,7 +3186,7 @@ err_addr_alloc:
 	return NOTIFY_BAD;
 }
 
-static struct notifier_block mlxsw_sp_switchdev_notifier = {
+struct notifier_block mlxsw_sp_switchdev_notifier = {
 	.notifier_call = mlxsw_sp_switchdev_event,
 };
 
-- 
cgit v1.2.3


From a6ef5a48a32fe87af947e22973a409870bc63d0d Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:12 +0000
Subject: mlxsw: spectrum_nve: Add mlxsw_sp_nve_ops.fdb_replay

A replay of FDB needs to be performed so that the FDB entries existing
at the NVE device are offloaded. How the replay is done depends on NVE
device type, and therefore add a per-NVE-type operation.

Implement the operation for the sole NVE device type currently supported
by mlxsw, VXLAN.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h       |  1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c | 10 ++++++++++
 2 files changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
index 4cc3297e13d6..e2f945543433 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
@@ -41,6 +41,7 @@ struct mlxsw_sp_nve_ops {
 	int (*init)(struct mlxsw_sp_nve *nve,
 		    const struct mlxsw_sp_nve_config *config);
 	void (*fini)(struct mlxsw_sp_nve *nve);
+	int (*fdb_replay)(const struct net_device *nve_dev, __be32 vni);
 };
 
 extern const struct mlxsw_sp_nve_ops mlxsw_sp1_nve_vxlan_ops;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
index 4e9cc00a88fd..1651c912ef77 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
@@ -211,12 +211,21 @@ static void mlxsw_sp1_nve_vxlan_fini(struct mlxsw_sp_nve *nve)
 				 config->udp_dport);
 }
 
+static int
+mlxsw_sp_nve_vxlan_fdb_replay(const struct net_device *nve_dev, __be32 vni)
+{
+	if (WARN_ON(!netif_is_vxlan(nve_dev)))
+		return -EINVAL;
+	return vxlan_fdb_replay(nve_dev, vni, &mlxsw_sp_switchdev_notifier);
+}
+
 const struct mlxsw_sp_nve_ops mlxsw_sp1_nve_vxlan_ops = {
 	.type		= MLXSW_SP_NVE_TYPE_VXLAN,
 	.can_offload	= mlxsw_sp1_nve_vxlan_can_offload,
 	.nve_config	= mlxsw_sp_nve_vxlan_config,
 	.init		= mlxsw_sp1_nve_vxlan_init,
 	.fini		= mlxsw_sp1_nve_vxlan_fini,
+	.fdb_replay	= mlxsw_sp_nve_vxlan_fdb_replay,
 };
 
 static bool mlxsw_sp2_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve,
@@ -242,4 +251,5 @@ const struct mlxsw_sp_nve_ops mlxsw_sp2_nve_vxlan_ops = {
 	.nve_config	= mlxsw_sp_nve_vxlan_config,
 	.init		= mlxsw_sp2_nve_vxlan_init,
 	.fini		= mlxsw_sp2_nve_vxlan_fini,
+	.fdb_replay	= mlxsw_sp_nve_vxlan_fdb_replay,
 };
-- 
cgit v1.2.3


From b73ef0e0ee30e14104f1eb19471df462ccaae4b3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:14 +0000
Subject: mlxsw: spectrum_nve: Add mlxsw_sp_nve_ops.fdb_clear_offload

If there are any offloaded FDB entries at an NVE device at the time that
it's un-offloaded, their offloaded marks need to be cleared. How that is
done depends on NVE device type, and therefore add a per-NVE-type
operation.

Implement the operation for the sole NVE device type currently supported
by mlxsw, VXLAN.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h       |  1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c | 10 ++++++++++
 2 files changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
index e2f945543433..02937ea95bc3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
@@ -42,6 +42,7 @@ struct mlxsw_sp_nve_ops {
 		    const struct mlxsw_sp_nve_config *config);
 	void (*fini)(struct mlxsw_sp_nve *nve);
 	int (*fdb_replay)(const struct net_device *nve_dev, __be32 vni);
+	void (*fdb_clear_offload)(const struct net_device *nve_dev, __be32 vni);
 };
 
 extern const struct mlxsw_sp_nve_ops mlxsw_sp1_nve_vxlan_ops;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
index 1651c912ef77..74e564c4ac19 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
@@ -219,6 +219,14 @@ mlxsw_sp_nve_vxlan_fdb_replay(const struct net_device *nve_dev, __be32 vni)
 	return vxlan_fdb_replay(nve_dev, vni, &mlxsw_sp_switchdev_notifier);
 }
 
+static void
+mlxsw_sp_nve_vxlan_clear_offload(const struct net_device *nve_dev, __be32 vni)
+{
+	if (WARN_ON(!netif_is_vxlan(nve_dev)))
+		return;
+	vxlan_fdb_clear_offload(nve_dev, vni);
+}
+
 const struct mlxsw_sp_nve_ops mlxsw_sp1_nve_vxlan_ops = {
 	.type		= MLXSW_SP_NVE_TYPE_VXLAN,
 	.can_offload	= mlxsw_sp1_nve_vxlan_can_offload,
@@ -226,6 +234,7 @@ const struct mlxsw_sp_nve_ops mlxsw_sp1_nve_vxlan_ops = {
 	.init		= mlxsw_sp1_nve_vxlan_init,
 	.fini		= mlxsw_sp1_nve_vxlan_fini,
 	.fdb_replay	= mlxsw_sp_nve_vxlan_fdb_replay,
+	.fdb_clear_offload = mlxsw_sp_nve_vxlan_clear_offload,
 };
 
 static bool mlxsw_sp2_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve,
@@ -252,4 +261,5 @@ const struct mlxsw_sp_nve_ops mlxsw_sp2_nve_vxlan_ops = {
 	.init		= mlxsw_sp2_nve_vxlan_init,
 	.fini		= mlxsw_sp2_nve_vxlan_fini,
 	.fdb_replay	= mlxsw_sp_nve_vxlan_fdb_replay,
+	.fdb_clear_offload = mlxsw_sp_nve_vxlan_clear_offload,
 };
-- 
cgit v1.2.3


From 83de78831b99582c0de13d7d2a5849b6bab962c8 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:15 +0000
Subject: mlxsw: spectrum: Add mlxsw_sp_fid_ops.fdb_clear_offload

If there are any offloaded FDB entries at bridge master of an NVE device
at the time that it's un-offloaded, their offloaded marks need to be
cleared. How that is done depends on whether the bridge in question is
vlan aware. Therefore add a per-FID-type operation.

Implement the operation for the 802.1q and 802.1d bridges.

Add and publish a function mlxsw_sp_fid_fdb_clear_offload() to dispatch
to the new operation according to FID type.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  2 ++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c | 28 ++++++++++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 6b0dc40fa213..2d8f3692a949 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -763,6 +763,8 @@ int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, enum mlxsw_sp_nve_type type,
 			 __be32 vni, int nve_ifindex);
 void mlxsw_sp_fid_vni_clear(struct mlxsw_sp_fid *fid);
 bool mlxsw_sp_fid_vni_is_set(const struct mlxsw_sp_fid *fid);
+void mlxsw_sp_fid_fdb_clear_offload(const struct mlxsw_sp_fid *fid,
+				    const struct net_device *nve_dev);
 int mlxsw_sp_fid_flood_set(struct mlxsw_sp_fid *fid,
 			   enum mlxsw_sp_flood_type packet_type, u8 local_port,
 			   bool member);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index fe16e0be716e..7adb1494ebba 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -85,6 +85,8 @@ struct mlxsw_sp_fid_ops {
 	int (*nve_flood_index_set)(struct mlxsw_sp_fid *fid,
 				   u32 nve_flood_index);
 	void (*nve_flood_index_clear)(struct mlxsw_sp_fid *fid);
+	void (*fdb_clear_offload)(const struct mlxsw_sp_fid *fid,
+				  const struct net_device *nve_dev);
 };
 
 struct mlxsw_sp_fid_family {
@@ -277,6 +279,16 @@ bool mlxsw_sp_fid_vni_is_set(const struct mlxsw_sp_fid *fid)
 	return fid->vni_valid;
 }
 
+void mlxsw_sp_fid_fdb_clear_offload(const struct mlxsw_sp_fid *fid,
+				    const struct net_device *nve_dev)
+{
+	struct mlxsw_sp_fid_family *fid_family = fid->fid_family;
+	const struct mlxsw_sp_fid_ops *ops = fid_family->ops;
+
+	if (ops->fdb_clear_offload)
+		ops->fdb_clear_offload(fid, nve_dev);
+}
+
 static const struct mlxsw_sp_flood_table *
 mlxsw_sp_fid_flood_table_lookup(const struct mlxsw_sp_fid *fid,
 				enum mlxsw_sp_flood_type packet_type)
@@ -766,6 +778,13 @@ static void mlxsw_sp_fid_8021d_nve_flood_index_clear(struct mlxsw_sp_fid *fid)
 			    fid->vni_valid, 0, false);
 }
 
+static void
+mlxsw_sp_fid_8021d_fdb_clear_offload(const struct mlxsw_sp_fid *fid,
+				     const struct net_device *nve_dev)
+{
+	br_fdb_clear_offload(nve_dev, 0);
+}
+
 static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021d_ops = {
 	.setup			= mlxsw_sp_fid_8021d_setup,
 	.configure		= mlxsw_sp_fid_8021d_configure,
@@ -779,6 +798,7 @@ static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021d_ops = {
 	.vni_clear		= mlxsw_sp_fid_8021d_vni_clear,
 	.nve_flood_index_set	= mlxsw_sp_fid_8021d_nve_flood_index_set,
 	.nve_flood_index_clear	= mlxsw_sp_fid_8021d_nve_flood_index_clear,
+	.fdb_clear_offload	= mlxsw_sp_fid_8021d_fdb_clear_offload,
 };
 
 static const struct mlxsw_sp_flood_table mlxsw_sp_fid_8021d_flood_tables[] = {
@@ -815,6 +835,13 @@ static const struct mlxsw_sp_fid_family mlxsw_sp_fid_8021d_family = {
 	.lag_vid_valid		= 1,
 };
 
+static void
+mlxsw_sp_fid_8021q_fdb_clear_offload(const struct mlxsw_sp_fid *fid,
+				     const struct net_device *nve_dev)
+{
+	br_fdb_clear_offload(nve_dev, mlxsw_sp_fid_8021q_vid(fid));
+}
+
 static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021q_emu_ops = {
 	.setup			= mlxsw_sp_fid_8021q_setup,
 	.configure		= mlxsw_sp_fid_8021d_configure,
@@ -828,6 +855,7 @@ static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021q_emu_ops = {
 	.vni_clear		= mlxsw_sp_fid_8021d_vni_clear,
 	.nve_flood_index_set	= mlxsw_sp_fid_8021d_nve_flood_index_set,
 	.nve_flood_index_clear	= mlxsw_sp_fid_8021d_nve_flood_index_clear,
+	.fdb_clear_offload	= mlxsw_sp_fid_8021q_fdb_clear_offload,
 };
 
 /* There are 4K-2 emulated 802.1Q FIDs, starting right after the 802.1D FIDs */
-- 
cgit v1.2.3


From 8a5969d8a83d86f3542355eedcad67d47feafdab Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:17 +0000
Subject: mlxsw: spectrum_nve: Un/offload FDB on nve_fid_disable/enable

Any existing NVE FDB entries need to be offloaded when NVE is enabled
for a given FID. Recent patches have added fdb_replay op for this, so
just invoke it from mlxsw_sp_nve_fid_enable().

When NVE is disabled on a FID, any existing FDB offloaded marks need to
be cleared on NVE device as well as on its bridge master. An op to
handle this, fdb_clear_offload, has been added to FID ops and NVE ops in
previous patches. Add code to resolve the NVE device, NVE type, and
dispatch to both fdb_clear_offload ops.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c | 41 ++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
index e8e4cb6dfd38..9a86a7cde3b9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
@@ -789,6 +789,21 @@ static void mlxsw_sp_nve_fdb_flush_by_fid(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
 }
 
+static void mlxsw_sp_nve_fdb_clear_offload(struct mlxsw_sp *mlxsw_sp,
+					   const struct mlxsw_sp_fid *fid,
+					   const struct net_device *nve_dev,
+					   __be32 vni)
+{
+	const struct mlxsw_sp_nve_ops *ops;
+	enum mlxsw_sp_nve_type type;
+
+	if (WARN_ON(mlxsw_sp_fid_nve_type(fid, &type)))
+		return;
+
+	ops = mlxsw_sp->nve->nve_ops_arr[type];
+	ops->fdb_clear_offload(nve_dev, vni);
+}
+
 int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid,
 			    struct mlxsw_sp_nve_params *params,
 			    struct netlink_ext_ack *extack)
@@ -826,8 +841,16 @@ int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid,
 
 	nve->config = config;
 
+	err = ops->fdb_replay(params->dev, params->vni);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to offload the FDB");
+		goto err_fdb_replay;
+	}
+
 	return 0;
 
+err_fdb_replay:
+	mlxsw_sp_fid_vni_clear(fid);
 err_fid_vni_set:
 	mlxsw_sp_nve_tunnel_fini(mlxsw_sp);
 	return err;
@@ -837,9 +860,27 @@ void mlxsw_sp_nve_fid_disable(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_fid *fid)
 {
 	u16 fid_index = mlxsw_sp_fid_index(fid);
+	struct net_device *nve_dev;
+	int nve_ifindex;
+	__be32 vni;
 
 	mlxsw_sp_nve_flood_ip_flush(mlxsw_sp, fid);
 	mlxsw_sp_nve_fdb_flush_by_fid(mlxsw_sp, fid_index);
+
+	if (WARN_ON(mlxsw_sp_fid_nve_ifindex(fid, &nve_ifindex) ||
+		    mlxsw_sp_fid_vni(fid, &vni)))
+		goto out;
+
+	nve_dev = dev_get_by_index(&init_net, nve_ifindex);
+	if (!nve_dev)
+		goto out;
+
+	mlxsw_sp_nve_fdb_clear_offload(mlxsw_sp, fid, nve_dev, vni);
+	mlxsw_sp_fid_fdb_clear_offload(fid, nve_dev);
+
+	dev_put(nve_dev);
+
+out:
 	mlxsw_sp_fid_vni_clear(fid);
 	mlxsw_sp_nve_tunnel_fini(mlxsw_sp);
 }
-- 
cgit v1.2.3


From 0efe9ed98d15146becded107965b4e2f6b3aa805 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:18 +0000
Subject: selftests: mlxsw: vxlan: Test FDB un/marking on VXLAN join/leave

When a VXLAN device is attached to an offloaded bridge, or when a
front-panel port is attached to a bridge that already has a VXLAN
device, mlxsw should offload the existing offloadable FDB entries.
Similarly when VXLAN device is downed, the FDB entries are unoffloaded,
and the marks thus need to be cleared. Similarly when a front-panel port
device is attached to a bridge with a VXLAN device, or when VLAN flags
are tweaked on a VXLAN port attached to a VLAN-aware bridge.

Test that the replaying / clearing logic works by observing transitions
in presence of offload marks under different scenarios.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/vxlan.sh | 177 +++++++++++++++++++++
 1 file changed, 177 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
index 90b4998a3b70..ea11535f5a6e 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
@@ -647,12 +647,159 @@ offload_indication_decap_route_test()
 		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
 }
 
+check_fdb_offloaded()
+{
+	local mac=00:11:22:33:44:55
+	local zmac=00:00:00:00:00:00
+
+	bridge fdb show dev vxlan0 | grep $mac | grep self | grep -q offload
+	check_err $?
+	bridge fdb show dev vxlan0 | grep $mac | grep master | grep -q offload
+	check_err $?
+
+	bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
+	check_err $?
+}
+
+check_vxlan_fdb_not_offloaded()
+{
+	local mac=00:11:22:33:44:55
+	local zmac=00:00:00:00:00:00
+
+	bridge fdb show dev vxlan0 | grep $mac | grep -q self
+	check_err $?
+	bridge fdb show dev vxlan0 | grep $mac | grep self | grep -q offload
+	check_fail $?
+
+	bridge fdb show dev vxlan0 | grep $zmac | grep -q self
+	check_err $?
+	bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
+	check_fail $?
+}
+
+check_bridge_fdb_not_offloaded()
+{
+	local mac=00:11:22:33:44:55
+	local zmac=00:00:00:00:00:00
+
+	bridge fdb show dev vxlan0 | grep $mac | grep -q master
+	check_err $?
+	bridge fdb show dev vxlan0 | grep $mac | grep master | grep -q offload
+	check_fail $?
+}
+
+__offload_indication_join_vxlan_first()
+{
+	local vid=$1; shift
+
+	local mac=00:11:22:33:44:55
+	local zmac=00:00:00:00:00:00
+
+	bridge fdb append $zmac dev vxlan0 self dst 198.51.100.2
+
+	ip link set dev vxlan0 master br0
+	bridge fdb add dev vxlan0 $mac self master static dst 198.51.100.2
+
+	RET=0
+	check_vxlan_fdb_not_offloaded
+	ip link set dev $swp1 master br0
+	sleep .1
+	check_fdb_offloaded
+	log_test "offload indication - attach vxlan first"
+
+	RET=0
+	ip link set dev vxlan0 down
+	check_vxlan_fdb_not_offloaded
+	check_bridge_fdb_not_offloaded
+	log_test "offload indication - set vxlan down"
+
+	RET=0
+	ip link set dev vxlan0 up
+	sleep .1
+	check_fdb_offloaded
+	log_test "offload indication - set vxlan up"
+
+	if [[ ! -z $vid ]]; then
+		RET=0
+		bridge vlan del dev vxlan0 vid $vid
+		check_vxlan_fdb_not_offloaded
+		check_bridge_fdb_not_offloaded
+		log_test "offload indication - delete VLAN"
+
+		RET=0
+		bridge vlan add dev vxlan0 vid $vid
+		check_vxlan_fdb_not_offloaded
+		check_bridge_fdb_not_offloaded
+		log_test "offload indication - add tagged VLAN"
+
+		RET=0
+		bridge vlan add dev vxlan0 vid $vid pvid untagged
+		sleep .1
+		check_fdb_offloaded
+		log_test "offload indication - add pvid/untagged VLAN"
+	fi
+
+	RET=0
+	ip link set dev $swp1 nomaster
+	check_vxlan_fdb_not_offloaded
+	log_test "offload indication - detach port"
+}
+
+offload_indication_join_vxlan_first()
+{
+	ip link add dev br0 up type bridge mcast_snooping 0
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	__offload_indication_join_vxlan_first
+
+	ip link del dev vxlan0
+	ip link del dev br0
+}
+
+__offload_indication_join_vxlan_last()
+{
+	local zmac=00:00:00:00:00:00
+
+	RET=0
+
+	bridge fdb append $zmac dev vxlan0 self dst 198.51.100.2
+
+	ip link set dev $swp1 master br0
+
+	bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
+	check_fail $?
+
+	ip link set dev vxlan0 master br0
+
+	bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload
+	check_err $?
+
+	log_test "offload indication - attach vxlan last"
+}
+
+offload_indication_join_vxlan_last()
+{
+	ip link add dev br0 up type bridge mcast_snooping 0
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	__offload_indication_join_vxlan_last
+
+	ip link del dev vxlan0
+	ip link del dev br0
+}
+
 offload_indication_test()
 {
 	offload_indication_setup_create
 	offload_indication_fdb_test
 	offload_indication_decap_route_test
 	offload_indication_setup_destroy
+
+	log_info "offload indication - replay & cleanup"
+	offload_indication_join_vxlan_first
+	offload_indication_join_vxlan_last
 }
 
 sanitization_vlan_aware_test()
@@ -848,12 +995,42 @@ offload_indication_vlan_aware_decap_route_test()
 	log_test "vxlan decap route - vni map/unmap"
 }
 
+offload_indication_vlan_aware_join_vxlan_first()
+{
+	ip link add dev br0 up type bridge mcast_snooping 0 \
+		vlan_filtering 1 vlan_default_pvid 1
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	__offload_indication_join_vxlan_first 1
+
+	ip link del dev vxlan0
+	ip link del dev br0
+}
+
+offload_indication_vlan_aware_join_vxlan_last()
+{
+	ip link add dev br0 up type bridge mcast_snooping 0 \
+		vlan_filtering 1 vlan_default_pvid 1
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	__offload_indication_join_vxlan_last
+
+	ip link del dev vxlan0
+	ip link del dev br0
+}
+
 offload_indication_vlan_aware_test()
 {
 	offload_indication_vlan_aware_setup_create
 	offload_indication_vlan_aware_fdb_test
 	offload_indication_vlan_aware_decap_route_test
 	offload_indication_vlan_aware_setup_destroy
+
+	log_info "offload indication - replay & cleanup - vlan aware"
+	offload_indication_vlan_aware_join_vxlan_first
+	offload_indication_vlan_aware_join_vxlan_last
 }
 
 trap cleanup EXIT
-- 
cgit v1.2.3


From 55939b262a61d35d3ccde8a388976b946d654dcf Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 7 Dec 2018 19:55:20 +0000
Subject: selftests: forwarding: Add PVID test case for VXLAN with VLAN-aware
 bridges

When using VLAN-aware bridges with VXLAN, the VLAN that is mapped to the
VNI of the VXLAN device is that which is configured as "pvid untagged"
on the corresponding bridge port.

When these flags are toggled or when the VLAN is deleted entirely,
remote hosts should not be able to receive packets from the VTEP.

Add a test case for above mentioned scenarios.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1q.sh    | 70 ++++++++++++++++++++++
 1 file changed, 70 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
index bac2e568d22c..a5789721ba92 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
@@ -95,6 +95,7 @@ export VXPORT
 	test_flood
 	test_unicast
 	test_learning
+	test_pvid
     "}
 
 NUM_NETIFS=6
@@ -610,6 +611,75 @@ test_unicast()
 	done
 }
 
+test_pvid()
+{
+	local -a expects=(0 0 0 0 0)
+	local mac=de:ad:be:ef:13:37
+	local dst=192.0.2.100
+	local vid=10
+
+	# Check that flooding works
+	RET=0
+
+	expects[0]=10; expects[1]=10; expects[3]=10
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	log_test "VXLAN: flood before pvid off"
+
+	# Toggle PVID off and test that flood to remote hosts does not work
+	RET=0
+
+	bridge vlan add vid 10 dev vx10
+
+	expects[0]=10; expects[1]=0; expects[3]=0
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	log_test "VXLAN: flood after pvid off"
+
+	# Toggle PVID on and test that flood to remote hosts does work
+	RET=0
+
+	bridge vlan add vid 10 dev vx10 pvid untagged
+
+	expects[0]=10; expects[1]=10; expects[3]=10
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	log_test "VXLAN: flood after pvid on"
+
+	# Add a new VLAN and test that it does not affect flooding
+	RET=0
+
+	bridge vlan add vid 30 dev vx10
+
+	expects[0]=10; expects[1]=10; expects[3]=10
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	bridge vlan del vid 30 dev vx10
+
+	log_test "VXLAN: flood after vlan add"
+
+	# Remove currently mapped VLAN and test that flood to remote hosts does
+	# not work
+	RET=0
+
+	bridge vlan del vid 10 dev vx10
+
+	expects[0]=10; expects[1]=0; expects[3]=0
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	log_test "VXLAN: flood after vlan delete"
+
+	# Re-add the VLAN and test that flood to remote hosts does work
+	RET=0
+
+	bridge vlan add vid 10 dev vx10 pvid untagged
+
+	expects[0]=10; expects[1]=10; expects[3]=10
+	vxlan_flood_test $mac $dst $vid "${expects[@]}"
+
+	log_test "VXLAN: flood after vlan re-add"
+}
+
 vxlan_ping_test()
 {
 	local ping_dev=$1; shift
-- 
cgit v1.2.3


From 17f6c83fb5ebf7db4fcc94a5be4c22d5a7bfe428 Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Mon, 3 Dec 2018 17:27:54 -0500
Subject: mips: bpf: fix encoding bug for mm_srlv32_op

For micro-mips, srlv inside POOL32A encoding space should use 0x50
sub-opcode, NOT 0x90.

Some early version ISA doc describes the encoding as 0x90 for both srlv and
srav, this looks to me was a typo. I checked Binutils libopcode
implementation which is using 0x50 for srlv and 0x90 for srav.

v1->v2:
  - Keep mm_srlv32_op sorted by value.

Fixes: f31318fdf324 ("MIPS: uasm: Add srlv uasm instruction")
Cc: Markos Chandras <markos.chandras@imgtec.com>
Cc: Paul Burton <paul.burton@mips.com>
Cc: linux-mips@vger.kernel.org
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/mips/include/uapi/asm/inst.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index c05dcf5ab414..273ef58f4d43 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -369,8 +369,8 @@ enum mm_32a_minor_op {
 	mm_ext_op = 0x02c,
 	mm_pool32axf_op = 0x03c,
 	mm_srl32_op = 0x040,
+	mm_srlv32_op = 0x050,
 	mm_sra_op = 0x080,
-	mm_srlv32_op = 0x090,
 	mm_rotr_op = 0x0c0,
 	mm_lwxs_op = 0x118,
 	mm_addu32_op = 0x150,
-- 
cgit v1.2.3


From ee94b90c8acaa593b627f5f3fe93e076e7779f5c Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Wed, 5 Dec 2018 13:52:30 -0500
Subject: mips: bpf: implement jitting of BPF_ALU | BPF_ARSH | BPF_X

Jitting of BPF_K is supported already, but not BPF_X. This patch complete
the support for the latter on both MIPS and microMIPS.

Cc: Paul Burton <paul.burton@mips.com>
Cc: linux-mips@vger.kernel.org
Acked-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/mips/include/asm/uasm.h      | 1 +
 arch/mips/include/uapi/asm/inst.h | 1 +
 arch/mips/mm/uasm-micromips.c     | 1 +
 arch/mips/mm/uasm-mips.c          | 1 +
 arch/mips/mm/uasm.c               | 9 +++++----
 arch/mips/net/ebpf_jit.c          | 4 ++++
 6 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/arch/mips/include/asm/uasm.h b/arch/mips/include/asm/uasm.h
index 59dae37f6b8d..b1990dd75f27 100644
--- a/arch/mips/include/asm/uasm.h
+++ b/arch/mips/include/asm/uasm.h
@@ -157,6 +157,7 @@ Ip_u2u1s3(_slti);
 Ip_u2u1s3(_sltiu);
 Ip_u3u1u2(_sltu);
 Ip_u2u1u3(_sra);
+Ip_u3u2u1(_srav);
 Ip_u2u1u3(_srl);
 Ip_u3u2u1(_srlv);
 Ip_u3u1u2(_subu);
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index 273ef58f4d43..40fbb5dd66df 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -371,6 +371,7 @@ enum mm_32a_minor_op {
 	mm_srl32_op = 0x040,
 	mm_srlv32_op = 0x050,
 	mm_sra_op = 0x080,
+	mm_srav_op = 0x090,
 	mm_rotr_op = 0x0c0,
 	mm_lwxs_op = 0x118,
 	mm_addu32_op = 0x150,
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index 24e5b0d06899..75ef90486fe6 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -104,6 +104,7 @@ static const struct insn insn_table_MM[insn_invalid] = {
 	[insn_sltiu]	= {M(mm_sltiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
 	[insn_sltu]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_sltu_op), RT | RS | RD},
 	[insn_sra]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_sra_op), RT | RS | RD},
+	[insn_srav]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_srav_op), RT | RS | RD},
 	[insn_srl]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_srl32_op), RT | RS | RD},
 	[insn_srlv]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_srlv32_op), RT | RS | RD},
 	[insn_rotr]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_rotr_op), RT | RS | RD},
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index 60ceb93c71a0..6abe40fc413d 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -171,6 +171,7 @@ static const struct insn insn_table[insn_invalid] = {
 	[insn_sltiu]	= {M(sltiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM},
 	[insn_sltu]	= {M(spec_op, 0, 0, 0, 0, sltu_op), RS | RT | RD},
 	[insn_sra]	= {M(spec_op, 0, 0, 0, 0, sra_op),  RT | RD | RE},
+	[insn_srav]	= {M(spec_op, 0, 0, 0, 0, srav_op), RS | RT | RD},
 	[insn_srl]	= {M(spec_op, 0, 0, 0, 0, srl_op),  RT | RD | RE},
 	[insn_srlv]	= {M(spec_op, 0, 0, 0, 0, srlv_op),  RS | RT | RD},
 	[insn_subu]	= {M(spec_op, 0, 0, 0, 0, subu_op),	RS | RT | RD},
diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c
index 57570c0649b4..45b6264ff308 100644
--- a/arch/mips/mm/uasm.c
+++ b/arch/mips/mm/uasm.c
@@ -61,10 +61,10 @@ enum opcode {
 	insn_mthc0, insn_mthi, insn_mtlo, insn_mul, insn_multu, insn_nor,
 	insn_or, insn_ori, insn_pref, insn_rfe, insn_rotr, insn_sb,
 	insn_sc, insn_scd, insn_sd, insn_sh, insn_sll, insn_sllv,
-	insn_slt, insn_slti, insn_sltiu, insn_sltu, insn_sra, insn_srl,
-	insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall, insn_tlbp,
-	insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh, insn_xor,
-	insn_xori, insn_yield,
+	insn_slt, insn_slti, insn_sltiu, insn_sltu, insn_sra, insn_srav,
+	insn_srl, insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall,
+	insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh,
+	insn_xor, insn_xori, insn_yield,
 	insn_invalid /* insn_invalid must be last */
 };
 
@@ -353,6 +353,7 @@ I_u2u1s3(_slti)
 I_u2u1s3(_sltiu)
 I_u3u1u2(_sltu)
 I_u2u1u3(_sra)
+I_u3u2u1(_srav)
 I_u2u1u3(_srl)
 I_u3u2u1(_srlv)
 I_u2u1u3(_rotr)
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index aeb7b1b0f202..b16710a8a9e7 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -854,6 +854,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	case BPF_ALU | BPF_MOD | BPF_X: /* ALU_REG */
 	case BPF_ALU | BPF_LSH | BPF_X: /* ALU_REG */
 	case BPF_ALU | BPF_RSH | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_ARSH | BPF_X: /* ALU_REG */
 		src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
 		if (src < 0 || dst < 0)
@@ -913,6 +914,9 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		case BPF_RSH:
 			emit_instr(ctx, srlv, dst, dst, src);
 			break;
+		case BPF_ARSH:
+			emit_instr(ctx, srav, dst, dst, src);
+			break;
 		default:
 			pr_err("ALU_REG NOT HANDLED\n");
 			return -EINVAL;
-- 
cgit v1.2.3


From 44cf43c04bb5f7c688608ff4136b13f2a8a7a129 Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Wed, 5 Dec 2018 13:52:31 -0500
Subject: ppc: bpf: implement jitting of BPF_ALU | BPF_ARSH | BPF_*

This patch implements code-gen for BPF_ALU | BPF_ARSH | BPF_*.

Cc: Naveen N. Rao <naveen.n.rao@linux.ibm.com>
Cc: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/powerpc/include/asm/ppc-opcode.h | 2 ++
 arch/powerpc/net/bpf_jit.h            | 4 ++++
 arch/powerpc/net/bpf_jit_comp64.c     | 6 ++++++
 3 files changed, 12 insertions(+)

diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index a6e9e314c707..901459226eca 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -342,6 +342,8 @@
 #define PPC_INST_SLW			0x7c000030
 #define PPC_INST_SLD			0x7c000036
 #define PPC_INST_SRW			0x7c000430
+#define PPC_INST_SRAW			0x7c000630
+#define PPC_INST_SRAWI			0x7c000670
 #define PPC_INST_SRD			0x7c000436
 #define PPC_INST_SRAD			0x7c000634
 #define PPC_INST_SRADI			0x7c000674
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 47fc6660845d..c2d5192ed64f 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -152,6 +152,10 @@
 				     ___PPC_RS(a) | ___PPC_RB(s))
 #define PPC_SRW(d, a, s)	EMIT(PPC_INST_SRW | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_SRAW(d, a, s)	EMIT(PPC_INST_SRAW | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_SRAWI(d, a, i)	EMIT(PPC_INST_SRAWI | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | __PPC_SH(i))
 #define PPC_SRD(d, a, s)	EMIT(PPC_INST_SRD | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(s))
 #define PPC_SRAD(d, a, s)	EMIT(PPC_INST_SRAD | ___PPC_RA(d) |	      \
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 17482f5de3e2..7dc81877057d 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -529,9 +529,15 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			if (imm != 0)
 				PPC_SRDI(dst_reg, dst_reg, imm);
 			break;
+		case BPF_ALU | BPF_ARSH | BPF_X: /* (s32) dst >>= src */
+			PPC_SRAW(dst_reg, dst_reg, src_reg);
+			goto bpf_alu32_trunc;
 		case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */
 			PPC_SRAD(dst_reg, dst_reg, src_reg);
 			break;
+		case BPF_ALU | BPF_ARSH | BPF_K: /* (s32) dst >>= imm */
+			PPC_SRAWI(dst_reg, dst_reg, imm);
+			goto bpf_alu32_trunc;
 		case BPF_ALU64 | BPF_ARSH | BPF_K: /* (s64) dst >>= imm */
 			if (imm != 0)
 				PPC_SRADI(dst_reg, dst_reg, imm);
-- 
cgit v1.2.3


From f860203b010ab11995b3073a96cc0d04e520129e Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Wed, 5 Dec 2018 13:52:32 -0500
Subject: s390: bpf: implement jitting of BPF_ALU | BPF_ARSH | BPF_*

This patch implements code-gen for BPF_ALU | BPF_ARSH | BPF_*.

Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/s390/net/bpf_jit_comp.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index d7052cbe984f..3ff758eeb71d 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -821,10 +821,22 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	/*
 	 * BPF_ARSH
 	 */
+	case BPF_ALU | BPF_ARSH | BPF_X: /* ((s32) dst) >>= src */
+		/* sra %dst,%dst,0(%src) */
+		EMIT4_DISP(0x8a000000, dst_reg, src_reg, 0);
+		EMIT_ZERO(dst_reg);
+		break;
 	case BPF_ALU64 | BPF_ARSH | BPF_X: /* ((s64) dst) >>= src */
 		/* srag %dst,%dst,0(%src) */
 		EMIT6_DISP_LH(0xeb000000, 0x000a, dst_reg, dst_reg, src_reg, 0);
 		break;
+	case BPF_ALU | BPF_ARSH | BPF_K: /* ((s32) dst >> imm */
+		if (imm == 0)
+			break;
+		/* sra %dst,imm(%r0) */
+		EMIT4_DISP(0x8a000000, dst_reg, REG_0, imm);
+		EMIT_ZERO(dst_reg);
+		break;
 	case BPF_ALU64 | BPF_ARSH | BPF_K: /* ((s64) dst) >>= imm */
 		if (imm == 0)
 			break;
-- 
cgit v1.2.3


From 84708c1386770e957347d847522a4aac22ea04dc Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Wed, 5 Dec 2018 13:52:33 -0500
Subject: nfp: bpf: implement jitting of BPF_ALU | BPF_ARSH | BPF_*

BPF_X support needs indirect shift mode, please see code comments for
details.

Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/bpf/jit.c | 45 ++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 97d33bb4d84d..662cbc21d909 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -2382,6 +2382,49 @@ static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int __ashr_imm(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
+{
+	/* Set signedness bit (MSB of result). */
+	emit_alu(nfp_prog, reg_none(), reg_a(dst), ALU_OP_OR, reg_imm(0));
+	emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR, reg_b(dst),
+		 SHF_SC_R_SHF, shift_amt);
+	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+
+	return 0;
+}
+
+static int ashr_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u64 umin, umax;
+	u8 dst, src;
+
+	dst = insn->dst_reg * 2;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
+	if (umin == umax)
+		return __ashr_imm(nfp_prog, dst, umin);
+
+	src = insn->src_reg * 2;
+	/* NOTE: the first insn will set both indirect shift amount (source A)
+	 * and signedness bit (MSB of result).
+	 */
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_b(dst));
+	emit_shf_indir(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR,
+		       reg_b(dst), SHF_SC_R_SHF);
+	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+
+	return 0;
+}
+
+static int ashr_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u8 dst = insn->dst_reg * 2;
+
+	return __ashr_imm(nfp_prog, dst, insn->imm);
+}
+
 static int shl_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
@@ -3286,6 +3329,8 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU | BPF_DIV | BPF_K] =	div_imm,
 	[BPF_ALU | BPF_NEG] =		neg_reg,
 	[BPF_ALU | BPF_LSH | BPF_K] =	shl_imm,
+	[BPF_ALU | BPF_ARSH | BPF_X] =	ashr_reg,
+	[BPF_ALU | BPF_ARSH | BPF_K] =	ashr_imm,
 	[BPF_ALU | BPF_END | BPF_X] =	end_reg32,
 	[BPF_LD | BPF_IMM | BPF_DW] =	imm_ld8,
 	[BPF_LD | BPF_ABS | BPF_B] =	data_ld1,
-- 
cgit v1.2.3


From 2dc6b100f928aac8d7532bf7112d3f8d3f952bad Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Wed, 5 Dec 2018 13:52:34 -0500
Subject: bpf: interpreter support BPF_ALU | BPF_ARSH

This patch implements interpreting BPF_ALU | BPF_ARSH. Do arithmetic right
shift on low 32-bit sub-register, and zero the high 32 bits.

Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/core.c | 52 ++++++++++++++++++++++++++++++----------------------
 1 file changed, 30 insertions(+), 22 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 628b3970a49b..a5b223ef7131 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -933,32 +933,34 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
 #define BPF_INSN_MAP(INSN_2, INSN_3)		\
 	/* 32 bit ALU operations. */		\
 	/*   Register based. */			\
-	INSN_3(ALU, ADD, X),			\
-	INSN_3(ALU, SUB, X),			\
-	INSN_3(ALU, AND, X),			\
-	INSN_3(ALU, OR,  X),			\
-	INSN_3(ALU, LSH, X),			\
-	INSN_3(ALU, RSH, X),			\
-	INSN_3(ALU, XOR, X),			\
-	INSN_3(ALU, MUL, X),			\
-	INSN_3(ALU, MOV, X),			\
-	INSN_3(ALU, DIV, X),			\
-	INSN_3(ALU, MOD, X),			\
+	INSN_3(ALU, ADD,  X),			\
+	INSN_3(ALU, SUB,  X),			\
+	INSN_3(ALU, AND,  X),			\
+	INSN_3(ALU, OR,   X),			\
+	INSN_3(ALU, LSH,  X),			\
+	INSN_3(ALU, RSH,  X),			\
+	INSN_3(ALU, XOR,  X),			\
+	INSN_3(ALU, MUL,  X),			\
+	INSN_3(ALU, MOV,  X),			\
+	INSN_3(ALU, ARSH, X),			\
+	INSN_3(ALU, DIV,  X),			\
+	INSN_3(ALU, MOD,  X),			\
 	INSN_2(ALU, NEG),			\
 	INSN_3(ALU, END, TO_BE),		\
 	INSN_3(ALU, END, TO_LE),		\
 	/*   Immediate based. */		\
-	INSN_3(ALU, ADD, K),			\
-	INSN_3(ALU, SUB, K),			\
-	INSN_3(ALU, AND, K),			\
-	INSN_3(ALU, OR,  K),			\
-	INSN_3(ALU, LSH, K),			\
-	INSN_3(ALU, RSH, K),			\
-	INSN_3(ALU, XOR, K),			\
-	INSN_3(ALU, MUL, K),			\
-	INSN_3(ALU, MOV, K),			\
-	INSN_3(ALU, DIV, K),			\
-	INSN_3(ALU, MOD, K),			\
+	INSN_3(ALU, ADD,  K),			\
+	INSN_3(ALU, SUB,  K),			\
+	INSN_3(ALU, AND,  K),			\
+	INSN_3(ALU, OR,   K),			\
+	INSN_3(ALU, LSH,  K),			\
+	INSN_3(ALU, RSH,  K),			\
+	INSN_3(ALU, XOR,  K),			\
+	INSN_3(ALU, MUL,  K),			\
+	INSN_3(ALU, MOV,  K),			\
+	INSN_3(ALU, ARSH, K),			\
+	INSN_3(ALU, DIV,  K),			\
+	INSN_3(ALU, MOD,  K),			\
 	/* 64 bit ALU operations. */		\
 	/*   Register based. */			\
 	INSN_3(ALU64, ADD,  X),			\
@@ -1137,6 +1139,12 @@ select_insn:
 		DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32;
 		insn++;
 		CONT;
+	ALU_ARSH_X:
+		DST = (u64) (u32) ((*(s32 *) &DST) >> SRC);
+		CONT;
+	ALU_ARSH_K:
+		DST = (u64) (u32) ((*(s32 *) &DST) >> IMM);
+		CONT;
 	ALU64_ARSH_X:
 		(*(s64 *) &DST) >>= SRC;
 		CONT;
-- 
cgit v1.2.3


From c49f7dbd4f9c2c49df7fc0f5b50c1350ee7e01ee Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Wed, 5 Dec 2018 13:52:35 -0500
Subject: bpf: verifier remove the rejection on BPF_ALU | BPF_ARSH

This patch remove the rejection on BPF_ALU | BPF_ARSH as we have supported
them on interpreter and all JIT back-ends

Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7658c61c1a88..2752d35ad073 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3649,11 +3649,6 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			return -EINVAL;
 		}
 
-		if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) {
-			verbose(env, "BPF_ARSH not supported for 32 bit ALU\n");
-			return -EINVAL;
-		}
-
 		if ((opcode == BPF_LSH || opcode == BPF_RSH ||
 		     opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
 			int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
-- 
cgit v1.2.3


From c099f3f413f354ecdd518e4be6a232592e91d5b9 Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Wed, 5 Dec 2018 13:52:36 -0500
Subject: selftests: bpf: update testcases for BPF_ALU | BPF_ARSH

"arsh32 on imm" and "arsh32 on reg" now are accepted. Also added two new
testcases to make sure arsh32 won't be treated as arsh64 during
interpretation or JIT code-gen for which case the high bits will be moved
into low halve that the testcases could catch them.

Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index b4b4a3f93639..36ce58b4933e 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -721,8 +721,18 @@ static struct bpf_test tests[] = {
 			BPF_ALU32_IMM(BPF_ARSH, BPF_REG_0, 5),
 			BPF_EXIT_INSN(),
 		},
-		.result = REJECT,
-		.errstr = "unknown opcode c4",
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"arsh32 on imm 2",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_0, 0x1122334485667788),
+			BPF_ALU32_IMM(BPF_ARSH, BPF_REG_0, 7),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = -16069393,
 	},
 	{
 		"arsh32 on reg",
@@ -732,8 +742,19 @@ static struct bpf_test tests[] = {
 			BPF_ALU32_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1),
 			BPF_EXIT_INSN(),
 		},
-		.result = REJECT,
-		.errstr = "unknown opcode cc",
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"arsh32 on reg 2",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_0, 0xffff55667788),
+			BPF_MOV64_IMM(BPF_REG_1, 15),
+			BPF_ALU32_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 43724,
 	},
 	{
 		"arsh64 on imm",
-- 
cgit v1.2.3


From fe0f7d698d5dce6195b034e1c5f4ea1633d42387 Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:07:58 +0000
Subject: net: hns3: remove existing process error functions and reorder hw_blk
 table

1.The command interface for queryng and clearing hw errors is
  changed, which requires the new process error functions to be added.
  This patch removes all the current process error functions and
  associated definitions. The new functions to handle ras errors
  would be added in this patch set.

2. Fixed order issue of the hw_blk table.

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |  12 -
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 462 +--------------------
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h |  19 -
 3 files changed, 18 insertions(+), 475 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index e1805b972628..d2fb2103c709 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -216,25 +216,13 @@ enum hclge_opcode_type {
 
 	/* Error INT commands */
 	HCLGE_TM_SCH_ECC_INT_EN		= 0x0829,
-	HCLGE_TM_SCH_ECC_ERR_RINT_CMD	= 0x082d,
-	HCLGE_TM_SCH_ECC_ERR_RINT_CE	= 0x082f,
-	HCLGE_TM_SCH_ECC_ERR_RINT_NFE	= 0x0830,
-	HCLGE_TM_SCH_ECC_ERR_RINT_FE	= 0x0831,
-	HCLGE_TM_SCH_MBIT_ECC_INFO_CMD	= 0x0833,
 	HCLGE_COMMON_ECC_INT_CFG	= 0x1505,
-	HCLGE_IGU_EGU_TNL_INT_QUERY	= 0x1802,
 	HCLGE_IGU_EGU_TNL_INT_EN	= 0x1803,
-	HCLGE_IGU_EGU_TNL_INT_CLR	= 0x1804,
-	HCLGE_IGU_COMMON_INT_QUERY	= 0x1805,
 	HCLGE_IGU_COMMON_INT_EN		= 0x1806,
-	HCLGE_IGU_COMMON_INT_CLR	= 0x1807,
 	HCLGE_TM_QCN_MEM_INT_CFG	= 0x1A14,
-	HCLGE_TM_QCN_MEM_INT_INFO_CMD	= 0x1A17,
 	HCLGE_PPP_CMD0_INT_CMD		= 0x2100,
 	HCLGE_PPP_CMD1_INT_CMD		= 0x2101,
-	HCLGE_NCSI_INT_QUERY		= 0x2400,
 	HCLGE_NCSI_INT_EN		= 0x2401,
-	HCLGE_NCSI_INT_CLR		= 0x2402,
 };
 
 #define HCLGE_TQP_REG_OFFSET		0x80000
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 6da9e22d82d0..ac9ab3c3b8a2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -336,25 +336,6 @@ static const struct hclge_hw_error hclge_qcn_ecc_err_int[] = {
 	{ /* sentinel */ }
 };
 
-static void hclge_log_error(struct device *dev,
-			    const struct hclge_hw_error *err_list,
-			    u32 err_sts)
-{
-	const struct hclge_hw_error *err;
-	int i = 0;
-
-	while (err_list[i].msg) {
-		err = &err_list[i];
-		if (!(err->int_msk & err_sts)) {
-			i++;
-			continue;
-		}
-		dev_warn(dev, "%s [error status=0x%x] found\n",
-			 err->msg, err_sts);
-		i++;
-	}
-}
-
 /* hclge_cmd_query_error: read the error information
  * @hdev: pointer to struct hclge_dev
  * @desc: descriptor for describing the command
@@ -391,53 +372,6 @@ static int hclge_cmd_query_error(struct hclge_dev *hdev,
 	return ret;
 }
 
-/* hclge_cmd_clear_error: clear the error status
- * @hdev: pointer to struct hclge_dev
- * @desc: descriptor for describing the command
- * @desc_src: prefilled descriptor from the previous command for reusing
- * @cmd:  command opcode
- * @flag: flag for extended command structure
- *
- * This function clear the error status in the hw register/s using command
- */
-static int hclge_cmd_clear_error(struct hclge_dev *hdev,
-				 struct hclge_desc *desc,
-				 struct hclge_desc *desc_src,
-				 u32 cmd, u16 flag)
-{
-	struct device *dev = &hdev->pdev->dev;
-	int num = 1;
-	int ret, i;
-
-	if (cmd) {
-		hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
-		if (flag) {
-			desc[0].flag |= cpu_to_le16(flag);
-			hclge_cmd_setup_basic_desc(&desc[1], cmd, false);
-			num = 2;
-		}
-		if (desc_src) {
-			for (i = 0; i < 6; i++) {
-				desc[0].data[i] = desc_src[0].data[i];
-				if (flag)
-					desc[1].data[i] = desc_src[1].data[i];
-			}
-		}
-	} else {
-		hclge_cmd_reuse_desc(&desc[0], false);
-		if (flag) {
-			desc[0].flag |= cpu_to_le16(flag);
-			hclge_cmd_reuse_desc(&desc[1], false);
-			num = 2;
-		}
-	}
-	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
-	if (ret)
-		dev_err(dev, "clear error cmd failed (%d)\n", ret);
-
-	return ret;
-}
-
 static int hclge_enable_common_error(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
@@ -665,368 +599,23 @@ int hclge_enable_tm_hw_error(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
-static void hclge_process_common_error(struct hclge_dev *hdev,
-				       enum hclge_err_int_type type)
-{
-	struct device *dev = &hdev->pdev->dev;
-	struct hclge_desc desc[2];
-	u32 err_sts;
-	int ret;
-
-	/* read err sts */
-	ret = hclge_cmd_query_error(hdev, &desc[0],
-				    HCLGE_COMMON_ECC_INT_CFG,
-				    HCLGE_CMD_FLAG_NEXT, 0, 0);
-	if (ret) {
-		dev_err(dev,
-			"failed(=%d) to query COMMON error interrupt status\n",
-			ret);
-		return;
-	}
-
-	/* log err */
-	err_sts = (le32_to_cpu(desc[0].data[0])) & HCLGE_IMP_TCM_ECC_INT_MASK;
-	hclge_log_error(dev, &hclge_imp_tcm_ecc_int[0], err_sts);
-
-	err_sts = (le32_to_cpu(desc[0].data[1])) & HCLGE_CMDQ_ECC_INT_MASK;
-	hclge_log_error(dev, &hclge_cmdq_nic_mem_ecc_int[0], err_sts);
-
-	err_sts = (le32_to_cpu(desc[0].data[1]) >> HCLGE_CMDQ_ROC_ECC_INT_SHIFT)
-		   & HCLGE_CMDQ_ECC_INT_MASK;
-	hclge_log_error(dev, &hclge_cmdq_rocee_mem_ecc_int[0], err_sts);
-
-	if ((le32_to_cpu(desc[0].data[3])) & BIT(0))
-		dev_warn(dev, "imp_rd_data_poison_err found\n");
-
-	err_sts = (le32_to_cpu(desc[0].data[3]) >> HCLGE_TQP_ECC_INT_SHIFT) &
-		   HCLGE_TQP_ECC_INT_MASK;
-	hclge_log_error(dev, &hclge_tqp_int_ecc_int[0], err_sts);
-
-	err_sts = (le32_to_cpu(desc[0].data[5])) &
-		   HCLGE_IMP_ITCM4_ECC_INT_MASK;
-	hclge_log_error(dev, &hclge_imp_itcm4_ecc_int[0], err_sts);
-
-	/* clear error interrupts */
-	desc[1].data[0] = cpu_to_le32(HCLGE_IMP_TCM_ECC_CLR_MASK);
-	desc[1].data[1] = cpu_to_le32(HCLGE_CMDQ_NIC_ECC_CLR_MASK |
-				HCLGE_CMDQ_ROCEE_ECC_CLR_MASK);
-	desc[1].data[3] = cpu_to_le32(HCLGE_TQP_IMP_ERR_CLR_MASK);
-	desc[1].data[5] = cpu_to_le32(HCLGE_IMP_ITCM4_ECC_CLR_MASK);
-
-	ret = hclge_cmd_clear_error(hdev, &desc[0], NULL, 0,
-				    HCLGE_CMD_FLAG_NEXT);
-	if (ret)
-		dev_err(dev,
-			"failed(%d) to clear COMMON error interrupt status\n",
-			ret);
-}
-
-static void hclge_process_ncsi_error(struct hclge_dev *hdev,
-				     enum hclge_err_int_type type)
-{
-	struct device *dev = &hdev->pdev->dev;
-	struct hclge_desc desc_rd;
-	struct hclge_desc desc_wr;
-	u32 err_sts;
-	int ret;
-
-	if (hdev->pdev->revision < 0x21)
-		return;
-
-	/* read NCSI error status */
-	ret = hclge_cmd_query_error(hdev, &desc_rd, HCLGE_NCSI_INT_QUERY,
-				    0, 1, HCLGE_NCSI_ERR_INT_TYPE);
-	if (ret) {
-		dev_err(dev,
-			"failed(=%d) to query NCSI error interrupt status\n",
-			ret);
-		return;
-	}
-
-	/* log err */
-	err_sts = le32_to_cpu(desc_rd.data[0]);
-	hclge_log_error(dev, &hclge_ncsi_err_int[0], err_sts);
-
-	/* clear err int */
-	ret = hclge_cmd_clear_error(hdev, &desc_wr, &desc_rd,
-				    HCLGE_NCSI_INT_CLR, 0);
-	if (ret)
-		dev_err(dev, "failed(=%d) to clear NCSI interrupt status\n",
-			ret);
-}
-
-static void hclge_process_igu_egu_error(struct hclge_dev *hdev,
-					enum hclge_err_int_type int_type)
-{
-	struct device *dev = &hdev->pdev->dev;
-	struct hclge_desc desc_rd;
-	struct hclge_desc desc_wr;
-	u32 err_sts;
-	int ret;
-
-	/* read IGU common err sts */
-	ret = hclge_cmd_query_error(hdev, &desc_rd,
-				    HCLGE_IGU_COMMON_INT_QUERY,
-				    0, 1, int_type);
-	if (ret) {
-		dev_err(dev, "failed(=%d) to query IGU common int status\n",
-			ret);
-		return;
-	}
-
-	/* log err */
-	err_sts = le32_to_cpu(desc_rd.data[0]) &
-				   HCLGE_IGU_COM_INT_MASK;
-	hclge_log_error(dev, &hclge_igu_com_err_int[0], err_sts);
-
-	/* clear err int */
-	ret = hclge_cmd_clear_error(hdev, &desc_wr, &desc_rd,
-				    HCLGE_IGU_COMMON_INT_CLR, 0);
-	if (ret) {
-		dev_err(dev, "failed(=%d) to clear IGU common int status\n",
-			ret);
-		return;
-	}
-
-	/* read IGU-EGU TNL err sts */
-	ret = hclge_cmd_query_error(hdev, &desc_rd,
-				    HCLGE_IGU_EGU_TNL_INT_QUERY,
-				    0, 1, int_type);
-	if (ret) {
-		dev_err(dev, "failed(=%d) to query IGU-EGU TNL int status\n",
-			ret);
-		return;
-	}
-
-	/* log err */
-	err_sts = le32_to_cpu(desc_rd.data[0]) &
-				   HCLGE_IGU_EGU_TNL_INT_MASK;
-	hclge_log_error(dev, &hclge_igu_egu_tnl_err_int[0], err_sts);
-
-	/* clear err int */
-	ret = hclge_cmd_clear_error(hdev, &desc_wr, &desc_rd,
-				    HCLGE_IGU_EGU_TNL_INT_CLR, 0);
-	if (ret) {
-		dev_err(dev, "failed(=%d) to clear IGU-EGU TNL int status\n",
-			ret);
-		return;
-	}
-
-	hclge_process_ncsi_error(hdev, HCLGE_ERR_INT_RAS_NFE);
-}
-
-static int hclge_log_and_clear_ppp_error(struct hclge_dev *hdev, u32 cmd,
-					 enum hclge_err_int_type int_type)
-{
-	struct device *dev = &hdev->pdev->dev;
-	const struct hclge_hw_error *hw_err_lst1, *hw_err_lst2, *hw_err_lst3;
-	struct hclge_desc desc[2];
-	u32 err_sts;
-	int ret;
-
-	/* read PPP INT sts */
-	ret = hclge_cmd_query_error(hdev, &desc[0], cmd,
-				    HCLGE_CMD_FLAG_NEXT, 5, int_type);
-	if (ret) {
-		dev_err(dev, "failed(=%d) to query PPP interrupt status\n",
-			ret);
-		return -EIO;
-	}
-
-	/* log error */
-	if (cmd == HCLGE_PPP_CMD0_INT_CMD) {
-		hw_err_lst1 = &hclge_ppp_mpf_int0[0];
-		hw_err_lst2 = &hclge_ppp_mpf_int1[0];
-		hw_err_lst3 = &hclge_ppp_pf_int[0];
-	} else if (cmd == HCLGE_PPP_CMD1_INT_CMD) {
-		hw_err_lst1 = &hclge_ppp_mpf_int2[0];
-		hw_err_lst2 = &hclge_ppp_mpf_int3[0];
-	} else {
-		dev_err(dev, "invalid command(=%d)\n", cmd);
-		return -EINVAL;
-	}
-
-	err_sts = le32_to_cpu(desc[0].data[2]);
-	if (err_sts)
-		hclge_log_error(dev, hw_err_lst1, err_sts);
-
-	err_sts = le32_to_cpu(desc[0].data[3]);
-	if (err_sts)
-		hclge_log_error(dev, hw_err_lst2, err_sts);
-
-	if (cmd == HCLGE_PPP_CMD0_INT_CMD) {
-		err_sts = (le32_to_cpu(desc[0].data[4]) >> 8) & 0x3;
-		if (err_sts)
-			hclge_log_error(dev, hw_err_lst3, err_sts);
-	}
-
-	/* clear PPP INT */
-	ret = hclge_cmd_clear_error(hdev, &desc[0], NULL, 0,
-				    HCLGE_CMD_FLAG_NEXT);
-	if (ret) {
-		dev_err(dev, "failed(=%d) to clear PPP interrupt status\n",
-			ret);
-		return -EIO;
-	}
-
-	return 0;
-}
-
-static void hclge_process_ppp_error(struct hclge_dev *hdev,
-				    enum hclge_err_int_type int_type)
-{
-	struct device *dev = &hdev->pdev->dev;
-	int ret;
-
-	/* read PPP INT0,1 sts */
-	ret = hclge_log_and_clear_ppp_error(hdev, HCLGE_PPP_CMD0_INT_CMD,
-					    int_type);
-	if (ret < 0) {
-		dev_err(dev, "failed(=%d) to clear PPP interrupt 0,1 status\n",
-			ret);
-		return;
-	}
-
-	/* read err PPP INT2,3 sts */
-	ret = hclge_log_and_clear_ppp_error(hdev, HCLGE_PPP_CMD1_INT_CMD,
-					    int_type);
-	if (ret < 0)
-		dev_err(dev, "failed(=%d) to clear PPP interrupt 2,3 status\n",
-			ret);
-}
-
-static void hclge_process_tm_sch_error(struct hclge_dev *hdev)
-{
-	struct device *dev = &hdev->pdev->dev;
-	const struct hclge_tm_sch_ecc_info *tm_sch_ecc_info;
-	struct hclge_desc desc;
-	u32 ecc_info;
-	u8 module_no;
-	u8 ram_no;
-	int ret;
-
-	/* read TM scheduler errors */
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_SCH_MBIT_ECC_INFO_CMD, 0, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to read SCH mbit ECC err info\n", ret);
-		return;
-	}
-	ecc_info = le32_to_cpu(desc.data[0]);
-
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_SCH_ECC_ERR_RINT_CMD, 0, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to read SCH ECC err status\n", ret);
-		return;
-	}
-
-	/* log TM scheduler errors */
-	if (le32_to_cpu(desc.data[0])) {
-		hclge_log_error(dev, &hclge_tm_sch_err_int[0],
-				le32_to_cpu(desc.data[0]));
-		if (le32_to_cpu(desc.data[0]) & 0x2) {
-			module_no = (ecc_info >> 20) & 0xF;
-			ram_no = (ecc_info >> 16) & 0xF;
-			tm_sch_ecc_info =
-				&hclge_tm_sch_ecc_err[module_no][ram_no];
-			dev_warn(dev, "ecc err module:ram=%s\n",
-				 tm_sch_ecc_info->name);
-			dev_warn(dev, "ecc memory address = 0x%x\n",
-				 ecc_info & 0xFFFF);
-		}
-	}
-
-	/* clear TM scheduler errors */
-	ret = hclge_cmd_clear_error(hdev, &desc, NULL, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to clear TM SCH error status\n", ret);
-		return;
-	}
-
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_SCH_ECC_ERR_RINT_CE, 0, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to read SCH CE status\n", ret);
-		return;
-	}
-
-	ret = hclge_cmd_clear_error(hdev, &desc, NULL, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to clear TM SCH CE status\n", ret);
-		return;
-	}
-
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_SCH_ECC_ERR_RINT_NFE, 0, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to read SCH NFE status\n", ret);
-		return;
-	}
-
-	ret = hclge_cmd_clear_error(hdev, &desc, NULL, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to clear TM SCH NFE status\n", ret);
-		return;
-	}
-
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_SCH_ECC_ERR_RINT_FE, 0, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to read SCH FE status\n", ret);
-		return;
-	}
-
-	ret = hclge_cmd_clear_error(hdev, &desc, NULL, 0, 0);
-	if (ret)
-		dev_err(dev, "failed(%d) to clear TM SCH FE status\n", ret);
-}
-
-static void hclge_process_tm_qcn_error(struct hclge_dev *hdev)
-{
-	struct device *dev = &hdev->pdev->dev;
-	struct hclge_desc desc;
-	int ret;
-
-	/* read QCN errors */
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_QCN_MEM_INT_INFO_CMD, 0, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to read QCN ECC err status\n", ret);
-		return;
-	}
-
-	/* log QCN errors */
-	if (le32_to_cpu(desc.data[0]))
-		hclge_log_error(dev, &hclge_qcn_ecc_err_int[0],
-				le32_to_cpu(desc.data[0]));
-
-	/* clear QCN errors */
-	ret = hclge_cmd_clear_error(hdev, &desc, NULL, 0, 0);
-	if (ret)
-		dev_err(dev, "failed(%d) to clear QCN error status\n", ret);
-}
-
-static void hclge_process_tm_error(struct hclge_dev *hdev,
-				   enum hclge_err_int_type type)
-{
-	hclge_process_tm_sch_error(hdev);
-	hclge_process_tm_qcn_error(hdev);
-}
-
 static const struct hclge_hw_blk hw_blk[] = {
-	{ .msk = BIT(0), .name = "IGU_EGU",
+	{
+	  .msk = BIT(0), .name = "IGU_EGU",
 	  .enable_error = hclge_enable_igu_egu_error,
-	  .process_error = hclge_process_igu_egu_error, },
-	{ .msk = BIT(5), .name = "COMMON",
-	  .enable_error = hclge_enable_common_error,
-	  .process_error = hclge_process_common_error, },
-	{ .msk = BIT(4), .name = "TM",
-	  .enable_error = hclge_enable_tm_hw_error,
-	  .process_error = hclge_process_tm_error, },
-	{ .msk = BIT(1), .name = "PPP",
+	},
+	{
+	  .msk = BIT(1), .name = "PPP",
 	  .enable_error = hclge_enable_ppp_error,
-	  .process_error = hclge_process_ppp_error, },
+	},
+	{
+	  .msk = BIT(4), .name = "TM",
+	  .enable_error = hclge_enable_tm_hw_error,
+	},
+	{
+	  .msk = BIT(5), .name = "COMMON",
+	  .enable_error = hclge_enable_common_error,
+	},
 	{ /* sentinel */ }
 };
 
@@ -1056,28 +645,13 @@ pci_ers_result_t hclge_process_ras_hw_error(struct hnae3_ae_dev *ae_dev)
 {
 	struct hclge_dev *hdev = ae_dev->priv;
 	struct device *dev = &hdev->pdev->dev;
-	u32 sts, val;
-	int i = 0;
+	u32 sts;
 
 	sts = hclge_read_dev(&hdev->hw, HCLGE_RAS_PF_OTHER_INT_STS_REG);
 
-	/* Processing Non-fatal errors */
-	if (sts & HCLGE_RAS_REG_NFE_MASK) {
-		val = (sts >> HCLGE_RAS_REG_NFE_SHIFT) & 0xFF;
-		i = 0;
-		while (hw_blk[i].name) {
-			if (!(hw_blk[i].msk & val)) {
-				i++;
-				continue;
-			}
-			dev_warn(dev, "%s ras non-fatal error identified\n",
-				 hw_blk[i].name);
-			if (hw_blk[i].process_error)
-				hw_blk[i].process_error(hdev,
-							 HCLGE_ERR_INT_RAS_NFE);
-			i++;
-		}
-	}
+	/* Handling Non-fatal RAS errors */
+	if (sts & HCLGE_RAS_REG_NFE_MASK)
+		dev_warn(dev, "HNS Non-Fatal RAS error identified\n");
 
 	return PCI_ERS_RESULT_NEED_RESET;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index e0e3b5861495..1c5514d3e395 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -7,9 +7,7 @@
 #include "hclge_main.h"
 
 #define HCLGE_RAS_PF_OTHER_INT_STS_REG   0x20B00
-#define HCLGE_RAS_REG_FE_MASK    0xFF
 #define HCLGE_RAS_REG_NFE_MASK   0xFF00
-#define HCLGE_RAS_REG_NFE_SHIFT	8
 
 #define HCLGE_IMP_TCM_ECC_ERR_INT_EN	0xFFFF0000
 #define HCLGE_IMP_TCM_ECC_ERR_INT_EN_MASK	0xFFFF0000
@@ -42,21 +40,6 @@
 #define HCLGE_NCSI_ERR_INT_EN	0x3
 #define HCLGE_NCSI_ERR_INT_TYPE	0x9
 
-#define HCLGE_IMP_TCM_ECC_INT_MASK	0xFFFF
-#define HCLGE_IMP_ITCM4_ECC_INT_MASK	0x3
-#define HCLGE_CMDQ_ECC_INT_MASK		0xFFFF
-#define HCLGE_CMDQ_ROC_ECC_INT_SHIFT	16
-#define HCLGE_TQP_ECC_INT_MASK		0xFFF
-#define HCLGE_TQP_ECC_INT_SHIFT		16
-#define HCLGE_IMP_TCM_ECC_CLR_MASK	0xFFFF
-#define HCLGE_IMP_ITCM4_ECC_CLR_MASK	0x3
-#define HCLGE_CMDQ_NIC_ECC_CLR_MASK	0xFFFF
-#define HCLGE_CMDQ_ROCEE_ECC_CLR_MASK	0xFFFF0000
-#define HCLGE_TQP_IMP_ERR_CLR_MASK	0x0FFF0001
-#define HCLGE_IGU_COM_INT_MASK		0xF
-#define HCLGE_IGU_EGU_TNL_INT_MASK	0x3F
-#define HCLGE_PPP_PF_INT_MASK		0x100
-
 enum hclge_err_int_type {
 	HCLGE_ERR_INT_MSIX = 0,
 	HCLGE_ERR_INT_RAS_CE = 1,
@@ -68,8 +51,6 @@ struct hclge_hw_blk {
 	u32 msk;
 	const char *name;
 	int (*enable_error)(struct hclge_dev *hdev, bool en);
-	void (*process_error)(struct hclge_dev *hdev,
-			      enum hclge_err_int_type type);
 };
 
 struct hclge_hw_error {
-- 
cgit v1.2.3


From 98da4027afa626221466adf43e627e8668802884 Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:07:59 +0000
Subject: net: hns3: rename enable error interrupt functions

This patch
- renames the enable error interrupt functions.
  The reason is that these functions
  are used for both enable and disable error interrupts.

- removes redundant logs from the enable error interrupt functions.

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 83 ++++++++--------------
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h |  4 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    |  2 +-
 3 files changed, 34 insertions(+), 55 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index ac9ab3c3b8a2..21437feb554f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -372,18 +372,18 @@ static int hclge_cmd_query_error(struct hclge_dev *hdev,
 	return ret;
 }
 
-static int hclge_enable_common_error(struct hclge_dev *hdev, bool en)
+static int hclge_config_common_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc[2];
 	int ret;
 
+	/* configure common error interrupts */
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_COMMON_ECC_INT_CFG, false);
 	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
 	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_COMMON_ECC_INT_CFG, false);
 
 	if (en) {
-		/* enable COMMON error interrupts */
 		desc[0].data[0] = cpu_to_le32(HCLGE_IMP_TCM_ECC_ERR_INT_EN);
 		desc[0].data[2] = cpu_to_le32(HCLGE_CMDQ_NIC_ECC_ERR_INT_EN |
 					HCLGE_CMDQ_ROCEE_ECC_ERR_INT_EN);
@@ -391,7 +391,6 @@ static int hclge_enable_common_error(struct hclge_dev *hdev, bool en)
 		desc[0].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN);
 		desc[0].data[5] = cpu_to_le32(HCLGE_IMP_ITCM4_ECC_ERR_INT_EN);
 	} else {
-		/* disable COMMON error interrupts */
 		desc[0].data[0] = 0;
 		desc[0].data[2] = 0;
 		desc[0].data[3] = 0;
@@ -408,13 +407,12 @@ static int hclge_enable_common_error(struct hclge_dev *hdev, bool en)
 	ret = hclge_cmd_send(&hdev->hw, &desc[0], 2);
 	if (ret)
 		dev_err(dev,
-			"failed(%d) to enable/disable COMMON err interrupts\n",
-			ret);
+			"fail(%d) to configure common err interrupts\n", ret);
 
 	return ret;
 }
 
-static int hclge_enable_ncsi_error(struct hclge_dev *hdev, bool en)
+static int hclge_config_ncsi_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc;
@@ -423,7 +421,7 @@ static int hclge_enable_ncsi_error(struct hclge_dev *hdev, bool en)
 	if (hdev->pdev->revision < 0x21)
 		return 0;
 
-	/* enable/disable NCSI  error interrupts */
+	/* configure NCSI error interrupts */
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_NCSI_INT_EN, false);
 	if (en)
 		desc.data[0] = cpu_to_le32(HCLGE_NCSI_ERR_INT_EN);
@@ -433,19 +431,18 @@ static int hclge_enable_ncsi_error(struct hclge_dev *hdev, bool en)
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
 		dev_err(dev,
-			"failed(%d) to enable/disable NCSI error interrupts\n",
-			ret);
+			"fail(%d) to configure  NCSI error interrupts\n", ret);
 
 	return ret;
 }
 
-static int hclge_enable_igu_egu_error(struct hclge_dev *hdev, bool en)
+static int hclge_config_igu_egu_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc;
 	int ret;
 
-	/* enable/disable error interrupts */
+	/* configure IGU,EGU error interrupts */
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_IGU_COMMON_INT_EN, false);
 	if (en)
 		desc.data[0] = cpu_to_le32(HCLGE_IGU_ERR_INT_EN);
@@ -456,8 +453,7 @@ static int hclge_enable_igu_egu_error(struct hclge_dev *hdev, bool en)
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
 		dev_err(dev,
-			"failed(%d) to enable/disable IGU common interrupts\n",
-			ret);
+			"fail(%d) to configure IGU common interrupts\n", ret);
 		return ret;
 	}
 
@@ -471,26 +467,23 @@ static int hclge_enable_igu_egu_error(struct hclge_dev *hdev, bool en)
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
 		dev_err(dev,
-			"failed(%d) to enable/disable IGU-EGU TNL interrupts\n",
-			ret);
+			"fail(%d) to configure IGU-EGU TNL interrupts\n", ret);
 		return ret;
 	}
 
-	ret = hclge_enable_ncsi_error(hdev, en);
-	if (ret)
-		dev_err(dev, "fail(%d) to en/disable err int\n", ret);
+	ret = hclge_config_ncsi_hw_err_int(hdev, en);
 
 	return ret;
 }
 
-static int hclge_enable_ppp_error_interrupt(struct hclge_dev *hdev, u32 cmd,
+static int hclge_config_ppp_error_interrupt(struct hclge_dev *hdev, u32 cmd,
 					    bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc[2];
 	int ret;
 
-	/* enable/disable PPP error interrupts */
+	/* configure PPP error interrupts */
 	hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
 	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
 	hclge_cmd_setup_basic_desc(&desc[1], cmd, false);
@@ -527,44 +520,33 @@ static int hclge_enable_ppp_error_interrupt(struct hclge_dev *hdev, u32 cmd,
 
 	ret = hclge_cmd_send(&hdev->hw, &desc[0], 2);
 	if (ret)
-		dev_err(dev,
-			"failed(%d) to enable/disable PPP error interrupts\n",
-			ret);
+		dev_err(dev, "fail(%d) to configure PPP error intr\n", ret);
 
 	return ret;
 }
 
-static int hclge_enable_ppp_error(struct hclge_dev *hdev, bool en)
+static int hclge_config_ppp_hw_err_int(struct hclge_dev *hdev, bool en)
 {
-	struct device *dev = &hdev->pdev->dev;
 	int ret;
 
-	ret = hclge_enable_ppp_error_interrupt(hdev, HCLGE_PPP_CMD0_INT_CMD,
+	ret = hclge_config_ppp_error_interrupt(hdev, HCLGE_PPP_CMD0_INT_CMD,
 					       en);
-	if (ret) {
-		dev_err(dev,
-			"failed(%d) to enable/disable PPP error intr 0,1\n",
-			ret);
+	if (ret)
 		return ret;
-	}
 
-	ret = hclge_enable_ppp_error_interrupt(hdev, HCLGE_PPP_CMD1_INT_CMD,
+	ret = hclge_config_ppp_error_interrupt(hdev, HCLGE_PPP_CMD1_INT_CMD,
 					       en);
-	if (ret)
-		dev_err(dev,
-			"failed(%d) to enable/disable PPP error intr 2,3\n",
-			ret);
 
 	return ret;
 }
 
-int hclge_enable_tm_hw_error(struct hclge_dev *hdev, bool en)
+int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc;
 	int ret;
 
-	/* enable TM SCH hw errors */
+	/* configure TM SCH hw errors */
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_TM_SCH_ECC_INT_EN, false);
 	if (en)
 		desc.data[0] = cpu_to_le32(HCLGE_TM_SCH_ECC_ERR_INT_EN);
@@ -573,15 +555,15 @@ int hclge_enable_tm_hw_error(struct hclge_dev *hdev, bool en)
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
-		dev_err(dev, "failed(%d) to configure TM SCH errors\n", ret);
+		dev_err(dev, "fail(%d) to configure TM SCH errors\n", ret);
 		return ret;
 	}
 
-	/* enable TM QCN hw errors */
+	/* configure TM QCN hw errors */
 	ret = hclge_cmd_query_error(hdev, &desc, HCLGE_TM_QCN_MEM_INT_CFG,
 				    0, 0, 0);
 	if (ret) {
-		dev_err(dev, "failed(%d) to read TM QCN CFG status\n", ret);
+		dev_err(dev, "fail(%d) to read TM QCN CFG status\n", ret);
 		return ret;
 	}
 
@@ -594,7 +576,7 @@ int hclge_enable_tm_hw_error(struct hclge_dev *hdev, bool en)
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
 		dev_err(dev,
-			"failed(%d) to configure TM QCN mem errors\n", ret);
+			"fail(%d) to configure TM QCN mem errors\n", ret);
 
 	return ret;
 }
@@ -602,39 +584,36 @@ int hclge_enable_tm_hw_error(struct hclge_dev *hdev, bool en)
 static const struct hclge_hw_blk hw_blk[] = {
 	{
 	  .msk = BIT(0), .name = "IGU_EGU",
-	  .enable_error = hclge_enable_igu_egu_error,
+	  .config_err_int = hclge_config_igu_egu_hw_err_int,
 	},
 	{
 	  .msk = BIT(1), .name = "PPP",
-	  .enable_error = hclge_enable_ppp_error,
+	  .config_err_int = hclge_config_ppp_hw_err_int,
 	},
 	{
 	  .msk = BIT(4), .name = "TM",
-	  .enable_error = hclge_enable_tm_hw_error,
+	  .config_err_int = hclge_config_tm_hw_err_int,
 	},
 	{
 	  .msk = BIT(5), .name = "COMMON",
-	  .enable_error = hclge_enable_common_error,
+	  .config_err_int = hclge_config_common_hw_err_int,
 	},
 	{ /* sentinel */ }
 };
 
 int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state)
 {
-	struct device *dev = &hdev->pdev->dev;
 	int ret = 0;
 	int i = 0;
 
 	while (hw_blk[i].name) {
-		if (!hw_blk[i].enable_error) {
+		if (!hw_blk[i].config_err_int) {
 			i++;
 			continue;
 		}
-		ret = hw_blk[i].enable_error(hdev, state);
-		if (ret) {
-			dev_err(dev, "fail(%d) to en/disable err int\n", ret);
+		ret = hw_blk[i].config_err_int(hdev, state);
+		if (ret)
 			return ret;
-		}
 		i++;
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 1c5514d3e395..856374c3feef 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -50,7 +50,7 @@ enum hclge_err_int_type {
 struct hclge_hw_blk {
 	u32 msk;
 	const char *name;
-	int (*enable_error)(struct hclge_dev *hdev, bool en);
+	int (*config_err_int)(struct hclge_dev *hdev, bool en);
 };
 
 struct hclge_hw_error {
@@ -59,6 +59,6 @@ struct hclge_hw_error {
 };
 
 int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state);
-int hclge_enable_tm_hw_error(struct hclge_dev *hdev, bool en);
+int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en);
 pci_ers_result_t hclge_process_ras_hw_error(struct hnae3_ae_dev *ae_dev);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 8432c841aa4f..5cea95c4f1a2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7408,7 +7408,7 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 	/* Re-enable the TM hw error interrupts because
 	 * they get disabled on core/global reset.
 	 */
-	if (hclge_enable_tm_hw_error(hdev, true))
+	if (hclge_config_tm_hw_err_int(hdev, true))
 		dev_err(&pdev->dev, "failed to enable TM hw error interrupts\n");
 
 	hclge_reset_vport_state(hdev);
-- 
cgit v1.2.3


From f3fa4a94dbc2f2b6ee05295bc92457e545c95131 Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:08:00 +0000
Subject: net: hns3: re-enable error interrupts on hw reset

This patch adds calling hclge_hw_error_set_state function
to re-enable the error interrupts those will be disabled on
the hw reset.

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c  |  2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h  |  1 -
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 14 +++++++++-----
 3 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 21437feb554f..7e23d3691a2d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -540,7 +540,7 @@ static int hclge_config_ppp_hw_err_int(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
-int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en)
+static int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 856374c3feef..405739bf67e0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -59,6 +59,5 @@ struct hclge_hw_error {
 };
 
 int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state);
-int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en);
 pci_ers_result_t hclge_process_ras_hw_error(struct hnae3_ae_dev *ae_dev);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 5cea95c4f1a2..431d92a0926d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7269,7 +7269,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	ret = hclge_hw_error_set_state(hdev, true);
 	if (ret) {
 		dev_err(&pdev->dev,
-			"hw error interrupts enable failed, ret =%d\n", ret);
+			"fail(%d) to enable hw error interrupts\n", ret);
 		goto err_mdiobus_unreg;
 	}
 
@@ -7405,11 +7405,15 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
-	/* Re-enable the TM hw error interrupts because
-	 * they get disabled on core/global reset.
+	/* Re-enable the hw error interrupts because
+	 * the interrupts get disabled on core/global reset.
 	 */
-	if (hclge_config_tm_hw_err_int(hdev, true))
-		dev_err(&pdev->dev, "failed to enable TM hw error interrupts\n");
+	ret = hclge_hw_error_set_state(hdev, true);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"fail(%d) to re-enable HNS hw error interrupts\n", ret);
+		return ret;
+	}
 
 	hclge_reset_vport_state(hdev);
 
-- 
cgit v1.2.3


From 166b04c3ee31994a133fc27393c99aee7e7164d7 Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:08:01 +0000
Subject: net: hns3: deletes unnecessary settings of the descriptor data

This patch deletes unnecessary setting of the descriptor data
to 0 for disabling error interrupts because
it is already done by the hclge_cmd_setup_basic_desc function.

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 27 ++++------------------
 1 file changed, 5 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 7e23d3691a2d..62fab2332f21 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -390,13 +390,8 @@ static int hclge_config_common_hw_err_int(struct hclge_dev *hdev, bool en)
 		desc[0].data[3] = cpu_to_le32(HCLGE_IMP_RD_POISON_ERR_INT_EN);
 		desc[0].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN);
 		desc[0].data[5] = cpu_to_le32(HCLGE_IMP_ITCM4_ECC_ERR_INT_EN);
-	} else {
-		desc[0].data[0] = 0;
-		desc[0].data[2] = 0;
-		desc[0].data[3] = 0;
-		desc[0].data[4] = 0;
-		desc[0].data[5] = 0;
 	}
+
 	desc[1].data[0] = cpu_to_le32(HCLGE_IMP_TCM_ECC_ERR_INT_EN_MASK);
 	desc[1].data[2] = cpu_to_le32(HCLGE_CMDQ_NIC_ECC_ERR_INT_EN_MASK |
 				HCLGE_CMDQ_ROCEE_ECC_ERR_INT_EN_MASK);
@@ -425,8 +420,6 @@ static int hclge_config_ncsi_hw_err_int(struct hclge_dev *hdev, bool en)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_NCSI_INT_EN, false);
 	if (en)
 		desc.data[0] = cpu_to_le32(HCLGE_NCSI_ERR_INT_EN);
-	else
-		desc.data[0] = 0;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
@@ -446,8 +439,7 @@ static int hclge_config_igu_egu_hw_err_int(struct hclge_dev *hdev, bool en)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_IGU_COMMON_INT_EN, false);
 	if (en)
 		desc.data[0] = cpu_to_le32(HCLGE_IGU_ERR_INT_EN);
-	else
-		desc.data[0] = 0;
+
 	desc.data[1] = cpu_to_le32(HCLGE_IGU_ERR_INT_EN_MASK);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -460,8 +452,7 @@ static int hclge_config_igu_egu_hw_err_int(struct hclge_dev *hdev, bool en)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_IGU_EGU_TNL_INT_EN, false);
 	if (en)
 		desc.data[0] = cpu_to_le32(HCLGE_IGU_TNL_ERR_INT_EN);
-	else
-		desc.data[0] = 0;
+
 	desc.data[1] = cpu_to_le32(HCLGE_IGU_TNL_ERR_INT_EN_MASK);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -494,10 +485,8 @@ static int hclge_config_ppp_error_interrupt(struct hclge_dev *hdev, u32 cmd,
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT0_EN);
 			desc[0].data[1] =
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT1_EN);
-		} else {
-			desc[0].data[0] = 0;
-			desc[0].data[1] = 0;
 		}
+
 		desc[1].data[0] =
 			cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT0_EN_MASK);
 		desc[1].data[1] =
@@ -508,10 +497,8 @@ static int hclge_config_ppp_error_interrupt(struct hclge_dev *hdev, u32 cmd,
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT2_EN);
 			desc[0].data[1] =
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT3_EN);
-		} else {
-			desc[0].data[0] = 0;
-			desc[0].data[1] = 0;
 		}
+
 		desc[1].data[0] =
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT2_EN_MASK);
 		desc[1].data[1] =
@@ -550,8 +537,6 @@ static int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_TM_SCH_ECC_INT_EN, false);
 	if (en)
 		desc.data[0] = cpu_to_le32(HCLGE_TM_SCH_ECC_ERR_INT_EN);
-	else
-		desc.data[0] = 0;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -570,8 +555,6 @@ static int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en)
 	hclge_cmd_reuse_desc(&desc, false);
 	if (en)
 		desc.data[1] = cpu_to_le32(HCLGE_TM_QCN_MEM_ERR_INT_EN);
-	else
-		desc.data[1] = 0;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
-- 
cgit v1.2.3


From 381c356e956627d387b7f0944d7616175057504f Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:08:02 +0000
Subject: net: hns3: rename process_hw_error function

This patch renames process_hw_error function to
handle_hw_ras_error function to match the purpose
of the function. This is because hw errors reported through
ras and msix interrupts will be handled separately.

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h             | 2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c         | 4 ++--
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c  | 2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h  | 2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +-
 5 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index a1707b77c47f..9d9f4f9c873f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -454,7 +454,7 @@ struct hnae3_ae_ops {
 	int (*restore_fd_rules)(struct hnae3_handle *handle);
 	void (*enable_fd)(struct hnae3_handle *handle, bool enable);
 	int (*dbg_run_cmd)(struct hnae3_handle *handle, char *cmd_buf);
-	pci_ers_result_t (*process_hw_error)(struct hnae3_ae_dev *ae_dev);
+	pci_ers_result_t (*handle_hw_ras_error)(struct hnae3_ae_dev *ae_dev);
 	bool (*get_hw_reset_stat)(struct hnae3_handle *handle);
 	bool (*ae_dev_resetting)(struct hnae3_handle *handle);
 	unsigned long (*ae_dev_reset_cnt)(struct hnae3_handle *handle);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index d1b2de2ecc89..69142a381064 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1828,8 +1828,8 @@ static pci_ers_result_t hns3_error_detected(struct pci_dev *pdev,
 		return PCI_ERS_RESULT_NONE;
 	}
 
-	if (ae_dev->ops->process_hw_error)
-		ret = ae_dev->ops->process_hw_error(ae_dev);
+	if (ae_dev->ops->handle_hw_ras_error)
+		ret = ae_dev->ops->handle_hw_ras_error(ae_dev);
 	else
 		return PCI_ERS_RESULT_NONE;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 62fab2332f21..2d07be873a31 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -603,7 +603,7 @@ int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state)
 	return ret;
 }
 
-pci_ers_result_t hclge_process_ras_hw_error(struct hnae3_ae_dev *ae_dev)
+pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev)
 {
 	struct hclge_dev *hdev = ae_dev->priv;
 	struct device *dev = &hdev->pdev->dev;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 405739bf67e0..9fe1c966574e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -59,5 +59,5 @@ struct hclge_hw_error {
 };
 
 int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state);
-pci_ers_result_t hclge_process_ras_hw_error(struct hnae3_ae_dev *ae_dev);
+pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 431d92a0926d..354ac5fa2af2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7935,7 +7935,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.restore_fd_rules = hclge_restore_fd_entries,
 	.enable_fd = hclge_enable_fd,
 	.dbg_run_cmd = hclge_dbg_run_cmd,
-	.process_hw_error = hclge_process_ras_hw_error,
+	.handle_hw_ras_error = hclge_handle_hw_ras_error,
 	.get_hw_reset_stat = hclge_get_hw_reset_stat,
 	.ae_dev_resetting = hclge_ae_dev_resetting,
 	.ae_dev_reset_cnt = hclge_ae_dev_reset_cnt,
-- 
cgit v1.2.3


From 481a626a603d5e234618a19abbaa889405755f46 Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:08:03 +0000
Subject: net: hns3: add optimization in the hclge_hw_error_set_state

1. This patch adds minor loop optimization in the
   hclge_hw_error_set_state function.
2. Adds logging module's name if it fails to configure the
   error interrupts.

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 2d07be873a31..d1c9f7ac9021 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -586,18 +586,16 @@ static const struct hclge_hw_blk hw_blk[] = {
 
 int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state)
 {
+	const struct hclge_hw_blk *module = hw_blk;
 	int ret = 0;
-	int i = 0;
 
-	while (hw_blk[i].name) {
-		if (!hw_blk[i].config_err_int) {
-			i++;
-			continue;
+	while (module->name) {
+		if (module->config_err_int) {
+			ret = module->config_err_int(hdev, state);
+			if (ret)
+				return ret;
 		}
-		ret = hw_blk[i].config_err_int(hdev, state);
-		if (ret)
-			return ret;
-		i++;
+		module++;
 	}
 
 	return ret;
-- 
cgit v1.2.3


From 332fbf576579a78a769209a9e588dae0c8fc0bdb Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:08:04 +0000
Subject: net: hns3: add handling of hw ras errors using new set of commands

1. This patch adds handling of hw ras errors using new set of
   common commands.
2. Updated the error message tables to match the register's name and
   error status returned by the commands.

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |   3 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 489 ++++++++++++++-------
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h |   9 +
 3 files changed, 331 insertions(+), 170 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index d2fb2103c709..0a0eb6c154c5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -217,6 +217,9 @@ enum hclge_opcode_type {
 	/* Error INT commands */
 	HCLGE_TM_SCH_ECC_INT_EN		= 0x0829,
 	HCLGE_COMMON_ECC_INT_CFG	= 0x1505,
+	HCLGE_QUERY_RAS_INT_STS_BD_NUM	= 0x1510,
+	HCLGE_QUERY_CLEAR_MPF_RAS_INT	= 0x1511,
+	HCLGE_QUERY_CLEAR_PF_RAS_INT	= 0x1512,
 	HCLGE_IGU_EGU_TNL_INT_EN	= 0x1803,
 	HCLGE_IGU_COMMON_INT_EN		= 0x1806,
 	HCLGE_TM_QCN_MEM_INT_CFG	= 0x1A14,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index d1c9f7ac9021..22e7c5bb2f7d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -20,12 +20,7 @@ static const struct hclge_hw_error hclge_imp_tcm_ecc_int[] = {
 	{ .int_msk = BIT(13), .msg = "imp_dtcm1_mem0_ecc_mbit_err" },
 	{ .int_msk = BIT(14), .msg = "imp_dtcm1_mem1_ecc_1bit_err" },
 	{ .int_msk = BIT(15), .msg = "imp_dtcm1_mem1_ecc_mbit_err" },
-	{ /* sentinel */ }
-};
-
-static const struct hclge_hw_error hclge_imp_itcm4_ecc_int[] = {
-	{ .int_msk = BIT(0), .msg = "imp_itcm4_ecc_1bit_err" },
-	{ .int_msk = BIT(1), .msg = "imp_itcm4_ecc_mbit_err" },
+	{ .int_msk = BIT(17), .msg = "imp_itcm4_ecc_mbit_err" },
 	{ /* sentinel */ }
 };
 
@@ -46,26 +41,14 @@ static const struct hclge_hw_error hclge_cmdq_nic_mem_ecc_int[] = {
 	{ .int_msk = BIT(13), .msg = "cmdq_nic_rx_addr_ecc_mbit_err" },
 	{ .int_msk = BIT(14), .msg = "cmdq_nic_tx_addr_ecc_1bit_err" },
 	{ .int_msk = BIT(15), .msg = "cmdq_nic_tx_addr_ecc_mbit_err" },
-	{ /* sentinel */ }
-};
-
-static const struct hclge_hw_error hclge_cmdq_rocee_mem_ecc_int[] = {
-	{ .int_msk = BIT(0), .msg = "cmdq_rocee_rx_depth_ecc_1bit_err" },
-	{ .int_msk = BIT(1), .msg = "cmdq_rocee_rx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "cmdq_rocee_tx_depth_ecc_1bit_err" },
-	{ .int_msk = BIT(3), .msg = "cmdq_rocee_tx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(4), .msg = "cmdq_rocee_rx_tail_ecc_1bit_err" },
-	{ .int_msk = BIT(5), .msg = "cmdq_rocee_rx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "cmdq_rocee_tx_tail_ecc_1bit_err" },
-	{ .int_msk = BIT(7), .msg = "cmdq_rocee_tx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(8), .msg = "cmdq_rocee_rx_head_ecc_1bit_err" },
-	{ .int_msk = BIT(9), .msg = "cmdq_rocee_rx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(10), .msg = "cmdq_rocee_tx_head_ecc_1bit_err" },
-	{ .int_msk = BIT(11), .msg = "cmdq_rocee_tx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(12), .msg = "cmdq_rocee_rx_addr_ecc_1bit_err" },
-	{ .int_msk = BIT(13), .msg = "cmdq_rocee_rx_addr_ecc_mbit_err" },
-	{ .int_msk = BIT(14), .msg = "cmdq_rocee_tx_addr_ecc_1bit_err" },
-	{ .int_msk = BIT(15), .msg = "cmdq_rocee_tx_addr_ecc_mbit_err" },
+	{ .int_msk = BIT(17), .msg = "cmdq_rocee_rx_depth_ecc_mbit_err" },
+	{ .int_msk = BIT(19), .msg = "cmdq_rocee_tx_depth_ecc_mbit_err" },
+	{ .int_msk = BIT(21), .msg = "cmdq_rocee_rx_tail_ecc_mbit_err" },
+	{ .int_msk = BIT(23), .msg = "cmdq_rocee_tx_tail_ecc_mbit_err" },
+	{ .int_msk = BIT(25), .msg = "cmdq_rocee_rx_head_ecc_mbit_err" },
+	{ .int_msk = BIT(27), .msg = "cmdq_rocee_tx_head_ecc_mbit_err" },
+	{ .int_msk = BIT(29), .msg = "cmdq_rocee_rx_addr_ecc_mbit_err" },
+	{ .int_msk = BIT(31), .msg = "cmdq_rocee_tx_addr_ecc_mbit_err" },
 	{ /* sentinel */ }
 };
 
@@ -85,7 +68,13 @@ static const struct hclge_hw_error hclge_tqp_int_ecc_int[] = {
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_igu_com_err_int[] = {
+static const struct hclge_hw_error hclge_msix_sram_ecc_int[] = {
+	{ .int_msk = BIT(1), .msg = "msix_nic_ecc_mbit_err" },
+	{ .int_msk = BIT(3), .msg = "msix_rocee_ecc_mbit_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_igu_int[] = {
 	{ .int_msk = BIT(0), .msg = "igu_rx_buf0_ecc_mbit_err" },
 	{ .int_msk = BIT(1), .msg = "igu_rx_buf0_ecc_1bit_err" },
 	{ .int_msk = BIT(2), .msg = "igu_rx_buf1_ecc_mbit_err" },
@@ -93,7 +82,7 @@ static const struct hclge_hw_error hclge_igu_com_err_int[] = {
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_igu_egu_tnl_err_int[] = {
+static const struct hclge_hw_error hclge_igu_egu_tnl_int[] = {
 	{ .int_msk = BIT(0), .msg = "rx_buf_overflow" },
 	{ .int_msk = BIT(1), .msg = "rx_stp_fifo_overflow" },
 	{ .int_msk = BIT(2), .msg = "rx_stp_fifo_undeflow" },
@@ -109,46 +98,7 @@ static const struct hclge_hw_error hclge_ncsi_err_int[] = {
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_ppp_mpf_int0[] = {
-	{ .int_msk = BIT(0), .msg = "vf_vlan_ad_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(1), .msg = "umv_mcast_group_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(2), .msg = "umv_key_mem0_ecc_1bit_err" },
-	{ .int_msk = BIT(3), .msg = "umv_key_mem1_ecc_1bit_err" },
-	{ .int_msk = BIT(4), .msg = "umv_key_mem2_ecc_1bit_err" },
-	{ .int_msk = BIT(5), .msg = "umv_key_mem3_ecc_1bit_err" },
-	{ .int_msk = BIT(6), .msg = "umv_ad_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(7), .msg = "rss_tc_mode_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(8), .msg = "rss_idt_mem0_ecc_1bit_err" },
-	{ .int_msk = BIT(9), .msg = "rss_idt_mem1_ecc_1bit_err" },
-	{ .int_msk = BIT(10), .msg = "rss_idt_mem2_ecc_1bit_err" },
-	{ .int_msk = BIT(11), .msg = "rss_idt_mem3_ecc_1bit_err" },
-	{ .int_msk = BIT(12), .msg = "rss_idt_mem4_ecc_1bit_err" },
-	{ .int_msk = BIT(13), .msg = "rss_idt_mem5_ecc_1bit_err" },
-	{ .int_msk = BIT(14), .msg = "rss_idt_mem6_ecc_1bit_err" },
-	{ .int_msk = BIT(15), .msg = "rss_idt_mem7_ecc_1bit_err" },
-	{ .int_msk = BIT(16), .msg = "rss_idt_mem8_ecc_1bit_err" },
-	{ .int_msk = BIT(17), .msg = "rss_idt_mem9_ecc_1bit_err" },
-	{ .int_msk = BIT(18), .msg = "rss_idt_mem10_ecc_1bit_err" },
-	{ .int_msk = BIT(19), .msg = "rss_idt_mem11_ecc_1bit_err" },
-	{ .int_msk = BIT(20), .msg = "rss_idt_mem12_ecc_1bit_err" },
-	{ .int_msk = BIT(21), .msg = "rss_idt_mem13_ecc_1bit_err" },
-	{ .int_msk = BIT(22), .msg = "rss_idt_mem14_ecc_1bit_err" },
-	{ .int_msk = BIT(23), .msg = "rss_idt_mem15_ecc_1bit_err" },
-	{ .int_msk = BIT(24), .msg = "port_vlan_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(25), .msg = "mcast_linear_table_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(26), .msg = "mcast_result_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(27),
-		.msg = "flow_director_ad_mem0_ecc_1bit_err" },
-	{ .int_msk = BIT(28),
-		.msg = "flow_director_ad_mem1_ecc_1bit_err" },
-	{ .int_msk = BIT(29),
-		.msg = "rx_vlan_tag_memory_ecc_1bit_err" },
-	{ .int_msk = BIT(30),
-		.msg = "Tx_UP_mapping_config_mem_ecc_1bit_err" },
-	{ /* sentinel */ }
-};
-
-static const struct hclge_hw_error hclge_ppp_mpf_int1[] = {
+static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st1[] = {
 	{ .int_msk = BIT(0), .msg = "vf_vlan_ad_mem_ecc_mbit_err" },
 	{ .int_msk = BIT(1), .msg = "umv_mcast_group_mem_ecc_mbit_err" },
 	{ .int_msk = BIT(2), .msg = "umv_key_mem0_ecc_mbit_err" },
@@ -193,17 +143,7 @@ static const struct hclge_hw_error hclge_ppp_pf_int[] = {
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_ppp_mpf_int2[] = {
-	{ .int_msk = BIT(0), .msg = "hfs_fifo_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(1), .msg = "rslt_descr_fifo_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(2), .msg = "tx_vlan_tag_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(3), .msg = "FD_CN0_memory_ecc_1bit_err" },
-	{ .int_msk = BIT(4), .msg = "FD_CN1_memory_ecc_1bit_err" },
-	{ .int_msk = BIT(5), .msg = "GRO_AD_memory_ecc_1bit_err" },
-	{ /* sentinel */ }
-};
-
-static const struct hclge_hw_error hclge_ppp_mpf_int3[] = {
+static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st3[] = {
 	{ .int_msk = BIT(0), .msg = "hfs_fifo_mem_ecc_mbit_err" },
 	{ .int_msk = BIT(1), .msg = "rslt_descr_fifo_mem_ecc_mbit_err" },
 	{ .int_msk = BIT(2), .msg = "tx_vlan_tag_mem_ecc_mbit_err" },
@@ -213,104 +153,75 @@ static const struct hclge_hw_error hclge_ppp_mpf_int3[] = {
 	{ /* sentinel */ }
 };
 
-struct hclge_tm_sch_ecc_info {
-	const char *name;
-};
-
-static const struct hclge_tm_sch_ecc_info hclge_tm_sch_ecc_err[7][15] = {
-	{
-		{ .name = "QSET_QUEUE_CTRL:PRI_LEN TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPA_LEN TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPB_LEN TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRA_LEN TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRB_LEN TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPA_HPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPB_HPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRA_HPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRB_HPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:QS_LINKLIST TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPA_TPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPB_TPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRA_TPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRB_TPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:QS_DEFICITCNT TAB" },
-	},
-	{
-		{ .name = "ROCE_QUEUE_CTRL:QS_LEN TAB" },
-		{ .name = "ROCE_QUEUE_CTRL:QS_TPTR TAB" },
-		{ .name = "ROCE_QUEUE_CTRL:QS_HPTR TAB" },
-		{ .name = "ROCE_QUEUE_CTRL:QLINKLIST TAB" },
-		{ .name = "ROCE_QUEUE_CTRL:QCLEN TAB" },
-	},
-	{
-		{ .name = "NIC_QUEUE_CTRL:QS_LEN TAB" },
-		{ .name = "NIC_QUEUE_CTRL:QS_TPTR TAB" },
-		{ .name = "NIC_QUEUE_CTRL:QS_HPTR TAB" },
-		{ .name = "NIC_QUEUE_CTRL:QLINKLIST TAB" },
-		{ .name = "NIC_QUEUE_CTRL:QCLEN TAB" },
-	},
-	{
-		{ .name = "RAM_CFG_CTRL:CSHAP TAB" },
-		{ .name = "RAM_CFG_CTRL:PSHAP TAB" },
-	},
-	{
-		{ .name = "SHAPER_CTRL:PSHAP TAB" },
-	},
-	{
-		{ .name = "MSCH_CTRL" },
-	},
-	{
-		{ .name = "TOP_CTRL" },
-	},
-};
-
-static const struct hclge_hw_error hclge_tm_sch_err_int[] = {
+static const struct hclge_hw_error hclge_tm_sch_rint[] = {
 	{ .int_msk = BIT(0), .msg = "tm_sch_ecc_1bit_err" },
 	{ .int_msk = BIT(1), .msg = "tm_sch_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "tm_sch_port_shap_sub_fifo_wr_full_err" },
-	{ .int_msk = BIT(3), .msg = "tm_sch_port_shap_sub_fifo_rd_empty_err" },
-	{ .int_msk = BIT(4), .msg = "tm_sch_pg_pshap_sub_fifo_wr_full_err" },
-	{ .int_msk = BIT(5), .msg = "tm_sch_pg_pshap_sub_fifo_rd_empty_err" },
-	{ .int_msk = BIT(6), .msg = "tm_sch_pg_cshap_sub_fifo_wr_full_err" },
-	{ .int_msk = BIT(7), .msg = "tm_sch_pg_cshap_sub_fifo_rd_empty_err" },
-	{ .int_msk = BIT(8), .msg = "tm_sch_pri_pshap_sub_fifo_wr_full_err" },
-	{ .int_msk = BIT(9), .msg = "tm_sch_pri_pshap_sub_fifo_rd_empty_err" },
-	{ .int_msk = BIT(10), .msg = "tm_sch_pri_cshap_sub_fifo_wr_full_err" },
-	{ .int_msk = BIT(11), .msg = "tm_sch_pri_cshap_sub_fifo_rd_empty_err" },
+	{ .int_msk = BIT(2), .msg = "tm_sch_port_shap_sub_fifo_wr_err" },
+	{ .int_msk = BIT(3), .msg = "tm_sch_port_shap_sub_fifo_rd_err" },
+	{ .int_msk = BIT(4), .msg = "tm_sch_pg_pshap_sub_fifo_wr_err" },
+	{ .int_msk = BIT(5), .msg = "tm_sch_pg_pshap_sub_fifo_rd_err" },
+	{ .int_msk = BIT(6), .msg = "tm_sch_pg_cshap_sub_fifo_wr_err" },
+	{ .int_msk = BIT(7), .msg = "tm_sch_pg_cshap_sub_fifo_rd_err" },
+	{ .int_msk = BIT(8), .msg = "tm_sch_pri_pshap_sub_fifo_wr_err" },
+	{ .int_msk = BIT(9), .msg = "tm_sch_pri_pshap_sub_fifo_rd_err" },
+	{ .int_msk = BIT(10), .msg = "tm_sch_pri_cshap_sub_fifo_wr_err" },
+	{ .int_msk = BIT(11), .msg = "tm_sch_pri_cshap_sub_fifo_rd_err" },
 	{ .int_msk = BIT(12),
-	  .msg = "tm_sch_port_shap_offset_fifo_wr_full_err" },
+	  .msg = "tm_sch_port_shap_offset_fifo_wr_err" },
 	{ .int_msk = BIT(13),
-	  .msg = "tm_sch_port_shap_offset_fifo_rd_empty_err" },
+	  .msg = "tm_sch_port_shap_offset_fifo_rd_err" },
 	{ .int_msk = BIT(14),
-	  .msg = "tm_sch_pg_pshap_offset_fifo_wr_full_err" },
+	  .msg = "tm_sch_pg_pshap_offset_fifo_wr_err" },
 	{ .int_msk = BIT(15),
-	  .msg = "tm_sch_pg_pshap_offset_fifo_rd_empty_err" },
+	  .msg = "tm_sch_pg_pshap_offset_fifo_rd_err" },
 	{ .int_msk = BIT(16),
-	  .msg = "tm_sch_pg_cshap_offset_fifo_wr_full_err" },
+	  .msg = "tm_sch_pg_cshap_offset_fifo_wr_err" },
 	{ .int_msk = BIT(17),
-	  .msg = "tm_sch_pg_cshap_offset_fifo_rd_empty_err" },
+	  .msg = "tm_sch_pg_cshap_offset_fifo_rd_err" },
 	{ .int_msk = BIT(18),
-	  .msg = "tm_sch_pri_pshap_offset_fifo_wr_full_err" },
+	  .msg = "tm_sch_pri_pshap_offset_fifo_wr_err" },
 	{ .int_msk = BIT(19),
-	  .msg = "tm_sch_pri_pshap_offset_fifo_rd_empty_err" },
+	  .msg = "tm_sch_pri_pshap_offset_fifo_rd_err" },
 	{ .int_msk = BIT(20),
-	  .msg = "tm_sch_pri_cshap_offset_fifo_wr_full_err" },
+	  .msg = "tm_sch_pri_cshap_offset_fifo_wr_err" },
 	{ .int_msk = BIT(21),
-	  .msg = "tm_sch_pri_cshap_offset_fifo_rd_empty_err" },
-	{ .int_msk = BIT(22), .msg = "tm_sch_rq_fifo_wr_full_err" },
-	{ .int_msk = BIT(23), .msg = "tm_sch_rq_fifo_rd_empty_err" },
-	{ .int_msk = BIT(24), .msg = "tm_sch_nq_fifo_wr_full_err" },
-	{ .int_msk = BIT(25), .msg = "tm_sch_nq_fifo_rd_empty_err" },
-	{ .int_msk = BIT(26), .msg = "tm_sch_roce_up_fifo_wr_full_err" },
-	{ .int_msk = BIT(27), .msg = "tm_sch_roce_up_fifo_rd_empty_err" },
-	{ .int_msk = BIT(28), .msg = "tm_sch_rcb_byte_fifo_wr_full_err" },
-	{ .int_msk = BIT(29), .msg = "tm_sch_rcb_byte_fifo_rd_empty_err" },
-	{ .int_msk = BIT(30), .msg = "tm_sch_ssu_byte_fifo_wr_full_err" },
-	{ .int_msk = BIT(31), .msg = "tm_sch_ssu_byte_fifo_rd_empty_err" },
+	  .msg = "tm_sch_pri_cshap_offset_fifo_rd_err" },
+	{ .int_msk = BIT(22), .msg = "tm_sch_rq_fifo_wr_err" },
+	{ .int_msk = BIT(23), .msg = "tm_sch_rq_fifo_rd_err" },
+	{ .int_msk = BIT(24), .msg = "tm_sch_nq_fifo_wr_err" },
+	{ .int_msk = BIT(25), .msg = "tm_sch_nq_fifo_rd_err" },
+	{ .int_msk = BIT(26), .msg = "tm_sch_roce_up_fifo_wr_err" },
+	{ .int_msk = BIT(27), .msg = "tm_sch_roce_up_fifo_rd_err" },
+	{ .int_msk = BIT(28), .msg = "tm_sch_rcb_byte_fifo_wr_err" },
+	{ .int_msk = BIT(29), .msg = "tm_sch_rcb_byte_fifo_rd_err" },
+	{ .int_msk = BIT(30), .msg = "tm_sch_ssu_byte_fifo_wr_err" },
+	{ .int_msk = BIT(31), .msg = "tm_sch_ssu_byte_fifo_rd_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_qcn_fifo_rint[] = {
+	{ .int_msk = BIT(0), .msg = "qcn_shap_gp0_sch_fifo_rd_err" },
+	{ .int_msk = BIT(1), .msg = "qcn_shap_gp0_sch_fifo_wr_err" },
+	{ .int_msk = BIT(2), .msg = "qcn_shap_gp1_sch_fifo_rd_err" },
+	{ .int_msk = BIT(3), .msg = "qcn_shap_gp1_sch_fifo_wr_err" },
+	{ .int_msk = BIT(4), .msg = "qcn_shap_gp2_sch_fifo_rd_err" },
+	{ .int_msk = BIT(5), .msg = "qcn_shap_gp2_sch_fifo_wr_err" },
+	{ .int_msk = BIT(6), .msg = "qcn_shap_gp3_sch_fifo_rd_err" },
+	{ .int_msk = BIT(7), .msg = "qcn_shap_gp3_sch_fifo_wr_err" },
+	{ .int_msk = BIT(8), .msg = "qcn_shap_gp0_offset_fifo_rd_err" },
+	{ .int_msk = BIT(9), .msg = "qcn_shap_gp0_offser_fifo_wr_err" },
+	{ .int_msk = BIT(10), .msg = "qcn_shap_gp1_offset_fifo_rd_err" },
+	{ .int_msk = BIT(11), .msg = "qcn_shap_gp1_offset_fifo_wr_err" },
+	{ .int_msk = BIT(12), .msg = "qcn_shap_gp2_offset_fifo_rd_err" },
+	{ .int_msk = BIT(13), .msg = "qcn_shap_gp2_offset_fifo_wr_err" },
+	{ .int_msk = BIT(14), .msg = "qcn_shap_gp3_offset_fifo_rd_err" },
+	{ .int_msk = BIT(15), .msg = "qcn_shap_gp3_offset_fifo_wr_err" },
+	{ .int_msk = BIT(16), .msg = "qcn_byte_info_fifo_rd_err" },
+	{ .int_msk = BIT(17), .msg = "qcn_byte_info_fifo_wr_err" },
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_qcn_ecc_err_int[] = {
+static const struct hclge_hw_error hclge_qcn_ecc_rint[] = {
 	{ .int_msk = BIT(0), .msg = "qcn_byte_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(1), .msg = "qcn_byte_mem_ecc_mbit_err" },
 	{ .int_msk = BIT(2), .msg = "qcn_time_mem_ecc_1bit_err" },
@@ -336,6 +247,18 @@ static const struct hclge_hw_error hclge_qcn_ecc_err_int[] = {
 	{ /* sentinel */ }
 };
 
+static void hclge_log_error(struct device *dev, char *reg,
+			    const struct hclge_hw_error *err,
+			    u32 err_sts)
+{
+	while (err->msg) {
+		if (err->int_msk & err_sts)
+			dev_warn(dev, "%s %s found [error status=0x%x]\n",
+				 reg, err->msg, err_sts);
+		err++;
+	}
+}
+
 /* hclge_cmd_query_error: read the error information
  * @hdev: pointer to struct hclge_dev
  * @desc: descriptor for describing the command
@@ -388,7 +311,8 @@ static int hclge_config_common_hw_err_int(struct hclge_dev *hdev, bool en)
 		desc[0].data[2] = cpu_to_le32(HCLGE_CMDQ_NIC_ECC_ERR_INT_EN |
 					HCLGE_CMDQ_ROCEE_ECC_ERR_INT_EN);
 		desc[0].data[3] = cpu_to_le32(HCLGE_IMP_RD_POISON_ERR_INT_EN);
-		desc[0].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN);
+		desc[0].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN |
+					      HCLGE_MSIX_SRAM_ECC_ERR_INT_EN);
 		desc[0].data[5] = cpu_to_le32(HCLGE_IMP_ITCM4_ECC_ERR_INT_EN);
 	}
 
@@ -396,7 +320,8 @@ static int hclge_config_common_hw_err_int(struct hclge_dev *hdev, bool en)
 	desc[1].data[2] = cpu_to_le32(HCLGE_CMDQ_NIC_ECC_ERR_INT_EN_MASK |
 				HCLGE_CMDQ_ROCEE_ECC_ERR_INT_EN_MASK);
 	desc[1].data[3] = cpu_to_le32(HCLGE_IMP_RD_POISON_ERR_INT_EN_MASK);
-	desc[1].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN_MASK);
+	desc[1].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN_MASK |
+				      HCLGE_MSIX_SRAM_ECC_ERR_INT_EN_MASK);
 	desc[1].data[5] = cpu_to_le32(HCLGE_IMP_ITCM4_ECC_ERR_INT_EN_MASK);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc[0], 2);
@@ -564,6 +489,225 @@ static int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
+#define HCLGE_SET_DEFAULT_RESET_REQUEST(reset_type) \
+	do { \
+		if (ae_dev->ops->set_default_reset_request) \
+			ae_dev->ops->set_default_reset_request(ae_dev, \
+							       reset_type); \
+	} while (0)
+
+/* hclge_handle_mpf_ras_error: handle all main PF RAS errors
+ * @hdev: pointer to struct hclge_dev
+ * @desc: descriptor for describing the command
+ * @num:  number of extended command structures
+ *
+ * This function handles all the main PF RAS errors in the
+ * hw register/s using command.
+ */
+static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev,
+				      struct hclge_desc *desc,
+				      int num)
+{
+	struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
+	struct device *dev = &hdev->pdev->dev;
+	__le32 *desc_data;
+	u32 status;
+	int ret;
+
+	/* query all main PF RAS errors */
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_MPF_RAS_INT,
+				   true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+	if (ret) {
+		dev_err(dev, "query all mpf ras int cmd failed (%d)\n", ret);
+		return ret;
+	}
+
+	/* log HNS common errors */
+	status = le32_to_cpu(desc[0].data[0]);
+	if (status) {
+		hclge_log_error(dev, "IMP_TCM_ECC_INT_STS",
+				&hclge_imp_tcm_ecc_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+	}
+
+	status = le32_to_cpu(desc[0].data[1]);
+	if (status) {
+		hclge_log_error(dev, "CMDQ_MEM_ECC_INT_STS",
+				&hclge_cmdq_nic_mem_ecc_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+	}
+
+	if ((le32_to_cpu(desc[0].data[2])) & BIT(0)) {
+		dev_warn(dev, "imp_rd_data_poison_err found\n");
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+	}
+
+	status = le32_to_cpu(desc[0].data[3]);
+	if (status) {
+		hclge_log_error(dev, "TQP_INT_ECC_INT_STS",
+				&hclge_tqp_int_ecc_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	status = le32_to_cpu(desc[0].data[4]);
+	if (status) {
+		hclge_log_error(dev, "MSIX_ECC_INT_STS",
+				&hclge_msix_sram_ecc_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	/* log IGU(Ingress Unit) errors */
+	desc_data = (__le32 *)&desc[3];
+	status = le32_to_cpu(*desc_data) & HCLGE_IGU_INT_MASK;
+	if (status)
+		hclge_log_error(dev, "IGU_INT_STS",
+				&hclge_igu_int[0], status);
+
+	/* log PPP(Programmable Packet Process) errors */
+	desc_data = (__le32 *)&desc[4];
+	status = le32_to_cpu(*(desc_data + 1));
+	if (status)
+		hclge_log_error(dev, "PPP_MPF_ABNORMAL_INT_ST1",
+				&hclge_ppp_mpf_abnormal_int_st1[0], status);
+
+	status = le32_to_cpu(*(desc_data + 3)) & HCLGE_PPP_MPF_INT_ST3_MASK;
+	if (status)
+		hclge_log_error(dev, "PPP_MPF_ABNORMAL_INT_ST3",
+				&hclge_ppp_mpf_abnormal_int_st3[0], status);
+
+	/* log TM(Traffic Manager) errors */
+	desc_data = (__le32 *)&desc[6];
+	status = le32_to_cpu(*desc_data);
+	if (status) {
+		hclge_log_error(dev, "TM_SCH_RINT",
+				&hclge_tm_sch_rint[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	/* log QCN(Quantized Congestion Control) errors */
+	desc_data = (__le32 *)&desc[7];
+	status = le32_to_cpu(*desc_data) & HCLGE_QCN_FIFO_INT_MASK;
+	if (status) {
+		hclge_log_error(dev, "QCN_FIFO_RINT",
+				&hclge_qcn_fifo_rint[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	status = le32_to_cpu(*(desc_data + 1)) & HCLGE_QCN_ECC_INT_MASK;
+	if (status) {
+		hclge_log_error(dev, "QCN_ECC_RINT",
+				&hclge_qcn_ecc_rint[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	/* log NCSI errors */
+	desc_data = (__le32 *)&desc[9];
+	status = le32_to_cpu(*desc_data) & HCLGE_NCSI_ECC_INT_MASK;
+	if (status) {
+		hclge_log_error(dev, "NCSI_ECC_INT_RPT",
+				&hclge_ncsi_err_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	/* clear all main PF RAS errors */
+	hclge_cmd_reuse_desc(&desc[0], false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+	if (ret)
+		dev_err(dev, "clear all mpf ras int cmd failed (%d)\n", ret);
+
+	return ret;
+}
+
+/* hclge_handle_pf_ras_error: handle all PF RAS errors
+ * @hdev: pointer to struct hclge_dev
+ * @desc: descriptor for describing the command
+ * @num:  number of extended command structures
+ *
+ * This function handles all the PF RAS errors in the
+ * hw register/s using command.
+ */
+static int hclge_handle_pf_ras_error(struct hclge_dev *hdev,
+				     struct hclge_desc *desc,
+				     int num)
+{
+	struct device *dev = &hdev->pdev->dev;
+	__le32 *desc_data;
+	u32 status;
+	int ret;
+
+	/* query all PF RAS errors */
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_PF_RAS_INT,
+				   true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+	if (ret) {
+		dev_err(dev, "query all pf ras int cmd failed (%d)\n", ret);
+		return ret;
+	}
+
+	/* log IGU(Ingress Unit) EGU(Egress Unit) TNL errors */
+	desc_data = (__le32 *)&desc[1];
+	status = le32_to_cpu(*desc_data) & HCLGE_IGU_EGU_TNL_INT_MASK;
+	if (status)
+		hclge_log_error(dev, "IGU_EGU_TNL_INT_STS",
+				&hclge_igu_egu_tnl_int[0], status);
+
+	/* clear all PF RAS errors */
+	hclge_cmd_reuse_desc(&desc[0], false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+	if (ret)
+		dev_err(dev, "clear all pf ras int cmd failed (%d)\n", ret);
+
+	return ret;
+}
+
+static int hclge_handle_all_ras_errors(struct hclge_dev *hdev)
+{
+	struct device *dev = &hdev->pdev->dev;
+	u32 mpf_bd_num, pf_bd_num, bd_num;
+	struct hclge_desc desc_bd;
+	struct hclge_desc *desc;
+	int ret;
+
+	/* query the number of registers in the RAS int status */
+	hclge_cmd_setup_basic_desc(&desc_bd, HCLGE_QUERY_RAS_INT_STS_BD_NUM,
+				   true);
+	ret = hclge_cmd_send(&hdev->hw, &desc_bd, 1);
+	if (ret) {
+		dev_err(dev, "fail(%d) to query ras int status bd num\n", ret);
+		return ret;
+	}
+	mpf_bd_num = le32_to_cpu(desc_bd.data[0]);
+	pf_bd_num = le32_to_cpu(desc_bd.data[1]);
+	bd_num = max_t(u32, mpf_bd_num, pf_bd_num);
+
+	desc = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	/* handle all main PF RAS errors */
+	ret = hclge_handle_mpf_ras_error(hdev, desc, mpf_bd_num);
+	if (ret) {
+		kfree(desc);
+		return ret;
+	}
+	memset(desc, 0, bd_num * sizeof(struct hclge_desc));
+
+	/* handle all PF RAS errors */
+	ret = hclge_handle_pf_ras_error(hdev, desc, pf_bd_num);
+	kfree(desc);
+
+	return ret;
+}
+
 static const struct hclge_hw_blk hw_blk[] = {
 	{
 	  .msk = BIT(0), .name = "IGU_EGU",
@@ -605,13 +749,18 @@ pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev)
 {
 	struct hclge_dev *hdev = ae_dev->priv;
 	struct device *dev = &hdev->pdev->dev;
-	u32 sts;
+	u32 status;
 
-	sts = hclge_read_dev(&hdev->hw, HCLGE_RAS_PF_OTHER_INT_STS_REG);
+	status = hclge_read_dev(&hdev->hw, HCLGE_RAS_PF_OTHER_INT_STS_REG);
 
-	/* Handling Non-fatal RAS errors */
-	if (sts & HCLGE_RAS_REG_NFE_MASK)
-		dev_warn(dev, "HNS Non-Fatal RAS error identified\n");
+	/* Handling Non-fatal HNS RAS errors */
+	if (status & HCLGE_RAS_REG_NFE_MASK) {
+		dev_warn(dev,
+			 "HNS Non-Fatal RAS error(status=0x%x) identified\n",
+			 status);
+		hclge_handle_all_ras_errors(hdev);
+		return PCI_ERS_RESULT_NEED_RESET;
+	}
 
-	return PCI_ERS_RESULT_NEED_RESET;
+	return PCI_ERS_RESULT_RECOVERED;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 9fe1c966574e..809e6981aa8b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -21,6 +21,8 @@
 #define HCLGE_IMP_RD_POISON_ERR_INT_EN_MASK	0x0100
 #define HCLGE_TQP_ECC_ERR_INT_EN	0x0FFF
 #define HCLGE_TQP_ECC_ERR_INT_EN_MASK	0x0FFF
+#define HCLGE_MSIX_SRAM_ECC_ERR_INT_EN_MASK	0x0F000000
+#define HCLGE_MSIX_SRAM_ECC_ERR_INT_EN	0x0F000000
 #define HCLGE_IGU_ERR_INT_EN	0x0000066F
 #define HCLGE_IGU_ERR_INT_EN_MASK	0x000F
 #define HCLGE_IGU_TNL_ERR_INT_EN    0x0002AABF
@@ -40,6 +42,13 @@
 #define HCLGE_NCSI_ERR_INT_EN	0x3
 #define HCLGE_NCSI_ERR_INT_TYPE	0x9
 
+#define HCLGE_IGU_INT_MASK		GENMASK(3, 0)
+#define HCLGE_IGU_EGU_TNL_INT_MASK	GENMASK(5, 0)
+#define HCLGE_PPP_MPF_INT_ST3_MASK	GENMASK(5, 0)
+#define HCLGE_QCN_FIFO_INT_MASK		GENMASK(17, 0)
+#define HCLGE_QCN_ECC_INT_MASK		GENMASK(21, 0)
+#define HCLGE_NCSI_ECC_INT_MASK		GENMASK(1, 0)
+
 enum hclge_err_int_type {
 	HCLGE_ERR_INT_MSIX = 0,
 	HCLGE_ERR_INT_RAS_CE = 1,
-- 
cgit v1.2.3


From 8bb147927c7c6caf8a26d9f5022f5744b12ea55a Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:08:05 +0000
Subject: net: hns3: deleted logging 1 bit errors

This patch deletes logging 1 bit errors for the following reasons.
1. AER does not notify 1 bit errors to the device drivers.
   However AER reports 1 bit errors to the userspace through the
   trace_aer_event for logging in the rasdaemon.
2. Firmware clears the status of 1 bit errors in the hw registers.

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 37 ----------------------
 1 file changed, 37 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 22e7c5bb2f7d..7371ae499b77 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -4,42 +4,26 @@
 #include "hclge_err.h"
 
 static const struct hclge_hw_error hclge_imp_tcm_ecc_int[] = {
-	{ .int_msk = BIT(0), .msg = "imp_itcm0_ecc_1bit_err" },
 	{ .int_msk = BIT(1), .msg = "imp_itcm0_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "imp_itcm1_ecc_1bit_err" },
 	{ .int_msk = BIT(3), .msg = "imp_itcm1_ecc_mbit_err" },
-	{ .int_msk = BIT(4), .msg = "imp_itcm2_ecc_1bit_err" },
 	{ .int_msk = BIT(5), .msg = "imp_itcm2_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "imp_itcm3_ecc_1bit_err" },
 	{ .int_msk = BIT(7), .msg = "imp_itcm3_ecc_mbit_err" },
-	{ .int_msk = BIT(8), .msg = "imp_dtcm0_mem0_ecc_1bit_err" },
 	{ .int_msk = BIT(9), .msg = "imp_dtcm0_mem0_ecc_mbit_err" },
-	{ .int_msk = BIT(10), .msg = "imp_dtcm0_mem1_ecc_1bit_err" },
 	{ .int_msk = BIT(11), .msg = "imp_dtcm0_mem1_ecc_mbit_err" },
-	{ .int_msk = BIT(12), .msg = "imp_dtcm1_mem0_ecc_1bit_err" },
 	{ .int_msk = BIT(13), .msg = "imp_dtcm1_mem0_ecc_mbit_err" },
-	{ .int_msk = BIT(14), .msg = "imp_dtcm1_mem1_ecc_1bit_err" },
 	{ .int_msk = BIT(15), .msg = "imp_dtcm1_mem1_ecc_mbit_err" },
 	{ .int_msk = BIT(17), .msg = "imp_itcm4_ecc_mbit_err" },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_cmdq_nic_mem_ecc_int[] = {
-	{ .int_msk = BIT(0), .msg = "cmdq_nic_rx_depth_ecc_1bit_err" },
 	{ .int_msk = BIT(1), .msg = "cmdq_nic_rx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "cmdq_nic_tx_depth_ecc_1bit_err" },
 	{ .int_msk = BIT(3), .msg = "cmdq_nic_tx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(4), .msg = "cmdq_nic_rx_tail_ecc_1bit_err" },
 	{ .int_msk = BIT(5), .msg = "cmdq_nic_rx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "cmdq_nic_tx_tail_ecc_1bit_err" },
 	{ .int_msk = BIT(7), .msg = "cmdq_nic_tx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(8), .msg = "cmdq_nic_rx_head_ecc_1bit_err" },
 	{ .int_msk = BIT(9), .msg = "cmdq_nic_rx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(10), .msg = "cmdq_nic_tx_head_ecc_1bit_err" },
 	{ .int_msk = BIT(11), .msg = "cmdq_nic_tx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(12), .msg = "cmdq_nic_rx_addr_ecc_1bit_err" },
 	{ .int_msk = BIT(13), .msg = "cmdq_nic_rx_addr_ecc_mbit_err" },
-	{ .int_msk = BIT(14), .msg = "cmdq_nic_tx_addr_ecc_1bit_err" },
 	{ .int_msk = BIT(15), .msg = "cmdq_nic_tx_addr_ecc_mbit_err" },
 	{ .int_msk = BIT(17), .msg = "cmdq_rocee_rx_depth_ecc_mbit_err" },
 	{ .int_msk = BIT(19), .msg = "cmdq_rocee_tx_depth_ecc_mbit_err" },
@@ -53,12 +37,6 @@ static const struct hclge_hw_error hclge_cmdq_nic_mem_ecc_int[] = {
 };
 
 static const struct hclge_hw_error hclge_tqp_int_ecc_int[] = {
-	{ .int_msk = BIT(0), .msg = "tqp_int_cfg_even_ecc_1bit_err" },
-	{ .int_msk = BIT(1), .msg = "tqp_int_cfg_odd_ecc_1bit_err" },
-	{ .int_msk = BIT(2), .msg = "tqp_int_ctrl_even_ecc_1bit_err" },
-	{ .int_msk = BIT(3), .msg = "tqp_int_ctrl_odd_ecc_1bit_err" },
-	{ .int_msk = BIT(4), .msg = "tx_que_scan_int_ecc_1bit_err" },
-	{ .int_msk = BIT(5), .msg = "rx_que_scan_int_ecc_1bit_err" },
 	{ .int_msk = BIT(6), .msg = "tqp_int_cfg_even_ecc_mbit_err" },
 	{ .int_msk = BIT(7), .msg = "tqp_int_cfg_odd_ecc_mbit_err" },
 	{ .int_msk = BIT(8), .msg = "tqp_int_ctrl_even_ecc_mbit_err" },
@@ -76,9 +54,7 @@ static const struct hclge_hw_error hclge_msix_sram_ecc_int[] = {
 
 static const struct hclge_hw_error hclge_igu_int[] = {
 	{ .int_msk = BIT(0), .msg = "igu_rx_buf0_ecc_mbit_err" },
-	{ .int_msk = BIT(1), .msg = "igu_rx_buf0_ecc_1bit_err" },
 	{ .int_msk = BIT(2), .msg = "igu_rx_buf1_ecc_mbit_err" },
-	{ .int_msk = BIT(3), .msg = "igu_rx_buf1_ecc_1bit_err" },
 	{ /* sentinel */ }
 };
 
@@ -93,7 +69,6 @@ static const struct hclge_hw_error hclge_igu_egu_tnl_int[] = {
 };
 
 static const struct hclge_hw_error hclge_ncsi_err_int[] = {
-	{ .int_msk = BIT(0), .msg = "ncsi_tx_ecc_1bit_err" },
 	{ .int_msk = BIT(1), .msg = "ncsi_tx_ecc_mbit_err" },
 	{ /* sentinel */ }
 };
@@ -154,7 +129,6 @@ static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st3[] = {
 };
 
 static const struct hclge_hw_error hclge_tm_sch_rint[] = {
-	{ .int_msk = BIT(0), .msg = "tm_sch_ecc_1bit_err" },
 	{ .int_msk = BIT(1), .msg = "tm_sch_ecc_mbit_err" },
 	{ .int_msk = BIT(2), .msg = "tm_sch_port_shap_sub_fifo_wr_err" },
 	{ .int_msk = BIT(3), .msg = "tm_sch_port_shap_sub_fifo_rd_err" },
@@ -222,27 +196,16 @@ static const struct hclge_hw_error hclge_qcn_fifo_rint[] = {
 };
 
 static const struct hclge_hw_error hclge_qcn_ecc_rint[] = {
-	{ .int_msk = BIT(0), .msg = "qcn_byte_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(1), .msg = "qcn_byte_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "qcn_time_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(3), .msg = "qcn_time_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(4), .msg = "qcn_fb_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(5), .msg = "qcn_fb_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "qcn_link_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(7), .msg = "qcn_link_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(8), .msg = "qcn_rate_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(9), .msg = "qcn_rate_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(10), .msg = "qcn_tmplt_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(11), .msg = "qcn_tmplt_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(12), .msg = "qcn_shap_cfg_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(13), .msg = "qcn_shap_cfg_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(14), .msg = "qcn_gp0_barrel_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(15), .msg = "qcn_gp0_barrel_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(16), .msg = "qcn_gp1_barrel_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(17), .msg = "qcn_gp1_barrel_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(18), .msg = "qcn_gp2_barrel_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(19), .msg = "qcn_gp2_barrel_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(20), .msg = "qcn_gp3_barral_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(21), .msg = "qcn_gp3_barral_mem_ecc_mbit_err" },
 	{ /* sentinel */ }
 };
-- 
cgit v1.2.3


From f6162d44126ce0f601f92afc770648b73924eb6c Mon Sep 17 00:00:00 2001
From: Salil Mehta <salil.mehta@huawei.com>
Date: Fri, 7 Dec 2018 21:08:06 +0000
Subject: net: hns3: add handling of hw errors reported through MSIX

This patch adds handling for HNS3 hardware errors(non-standard)
which are reported through MSIX interrupts and not through
PCIe AER channel.

These MSIX reported hardware errors are handled using common
misc. interrupt handler. Hardware error related registers
cannot be cleared in context to the interrupt received as
they require *heavy* access to hardware using IMP(Integrated
Mangement Processor) commands. Hence, we defer the clearing
of such error events till later time.

Since, we have defered exact identification of errors we
will have to defer the level of receovery/reset which
might be required. Hence, a new reset type UNKNOWN reset
has been introduced which effectively defers the assertion
of the reset till we get hold of kind of errors at later
time.

Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  1 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |  3 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 92 ++++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h |  5 ++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 39 ++++++++-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  1 +
 6 files changed, 139 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 9d9f4f9c873f..294e725c7c44 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -136,6 +136,7 @@ enum hnae3_reset_type {
 	HNAE3_CORE_RESET,
 	HNAE3_GLOBAL_RESET,
 	HNAE3_IMP_RESET,
+	HNAE3_UNKNOWN_RESET,
 	HNAE3_NONE_RESET,
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 0a0eb6c154c5..08d02b928552 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -220,6 +220,9 @@ enum hclge_opcode_type {
 	HCLGE_QUERY_RAS_INT_STS_BD_NUM	= 0x1510,
 	HCLGE_QUERY_CLEAR_MPF_RAS_INT	= 0x1511,
 	HCLGE_QUERY_CLEAR_PF_RAS_INT	= 0x1512,
+	HCLGE_QUERY_MSIX_INT_STS_BD_NUM	= 0x1513,
+	HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT	= 0x1514,
+	HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT	= 0x1515,
 	HCLGE_IGU_EGU_TNL_INT_EN	= 0x1803,
 	HCLGE_IGU_COMMON_INT_EN		= 0x1806,
 	HCLGE_TM_QCN_MEM_INT_CFG	= 0x1A14,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 7371ae499b77..465c76e174ba 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -727,3 +727,95 @@ pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev)
 
 	return PCI_ERS_RESULT_RECOVERED;
 }
+
+int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
+			       unsigned long *reset_requests)
+{
+	struct device *dev = &hdev->pdev->dev;
+	u32 mpf_bd_num, pf_bd_num, bd_num;
+	struct hclge_desc desc_bd;
+	struct hclge_desc *desc;
+	int ret = 0;
+
+	/* set default handling */
+	set_bit(HNAE3_FUNC_RESET, reset_requests);
+
+	/* query the number of bds for the MSIx int status */
+	hclge_cmd_setup_basic_desc(&desc_bd, HCLGE_QUERY_MSIX_INT_STS_BD_NUM,
+				   true);
+	ret = hclge_cmd_send(&hdev->hw, &desc_bd, 1);
+	if (ret) {
+		dev_err(dev, "fail(%d) to query msix int status bd num\n",
+			ret);
+		/* reset everything for now */
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+		return ret;
+	}
+
+	mpf_bd_num = le32_to_cpu(desc_bd.data[0]);
+	pf_bd_num = le32_to_cpu(desc_bd.data[1]);
+	bd_num = max_t(u32, mpf_bd_num, pf_bd_num);
+
+	desc = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	if (!desc)
+		goto out;
+
+	/* query all main PF MSIx errors */
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT,
+				   true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], mpf_bd_num);
+	if (ret) {
+		dev_err(dev, "query all mpf msix int cmd failed (%d)\n",
+			ret);
+		/* reset everything for now */
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+		goto msi_error;
+	}
+
+	/* clear all main PF MSIx errors */
+	hclge_cmd_reuse_desc(&desc[0], false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], mpf_bd_num);
+	if (ret) {
+		dev_err(dev, "clear all mpf msix int cmd failed (%d)\n",
+			ret);
+		/* reset everything for now */
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+		goto msi_error;
+	}
+
+	/* query all PF MSIx errors */
+	memset(desc, 0, bd_num * sizeof(struct hclge_desc));
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT,
+				   true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], pf_bd_num);
+	if (ret) {
+		dev_err(dev, "query all pf msix int cmd failed (%d)\n",
+			ret);
+		/* reset everything for now */
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+		goto msi_error;
+	}
+
+	/* clear all PF MSIx errors */
+	hclge_cmd_reuse_desc(&desc[0], false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], pf_bd_num);
+	if (ret) {
+		dev_err(dev, "clear all pf msix int cmd failed (%d)\n",
+			ret);
+		/* reset everything for now */
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+	}
+
+msi_error:
+	kfree(desc);
+out:
+	return ret;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 809e6981aa8b..05adccbd04ab 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -9,6 +9,9 @@
 #define HCLGE_RAS_PF_OTHER_INT_STS_REG   0x20B00
 #define HCLGE_RAS_REG_NFE_MASK   0xFF00
 
+#define HCLGE_VECTOR0_PF_OTHER_INT_STS_REG   0x20800
+#define HCLGE_VECTOR0_REG_MSIX_MASK   0x1FF00
+
 #define HCLGE_IMP_TCM_ECC_ERR_INT_EN	0xFFFF0000
 #define HCLGE_IMP_TCM_ECC_ERR_INT_EN_MASK	0xFFFF0000
 #define HCLGE_IMP_ITCM4_ECC_ERR_INT_EN	0x300
@@ -69,4 +72,6 @@ struct hclge_hw_error {
 
 int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state);
 pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev);
+int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
+			       unsigned long *reset_requests);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 354ac5fa2af2..22380202ba83 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2200,12 +2200,13 @@ static void hclge_service_complete(struct hclge_dev *hdev)
 
 static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 {
-	u32 rst_src_reg;
-	u32 cmdq_src_reg;
+	u32 rst_src_reg, cmdq_src_reg, msix_src_reg;
 
 	/* fetch the events from their corresponding regs */
 	rst_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS);
 	cmdq_src_reg = hclge_read_dev(&hdev->hw, HCLGE_VECTOR0_CMDQ_SRC_REG);
+	msix_src_reg = hclge_read_dev(&hdev->hw,
+				      HCLGE_VECTOR0_PF_OTHER_INT_STS_REG);
 
 	/* Assumption: If by any chance reset and mailbox events are reported
 	 * together then we will only process reset event in this go and will
@@ -2239,6 +2240,10 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 		return HCLGE_VECTOR0_EVENT_RST;
 	}
 
+	/* check for vector0 msix event source */
+	if (msix_src_reg & HCLGE_VECTOR0_REG_MSIX_MASK)
+		return HCLGE_VECTOR0_EVENT_ERR;
+
 	/* check for vector0 mailbox(=CMDQ RX) event source */
 	if (BIT(HCLGE_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) {
 		cmdq_src_reg &= ~BIT(HCLGE_VECTOR0_RX_CMDQ_INT_B);
@@ -2289,6 +2294,19 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
 
 	/* vector 0 interrupt is shared with reset and mailbox source events.*/
 	switch (event_cause) {
+	case HCLGE_VECTOR0_EVENT_ERR:
+		/* we do not know what type of reset is required now. This could
+		 * only be decided after we fetch the type of errors which
+		 * caused this event. Therefore, we will do below for now:
+		 * 1. Assert HNAE3_UNKNOWN_RESET type of reset. This means we
+		 *    have defered type of reset to be used.
+		 * 2. Schedule the reset serivce task.
+		 * 3. When service task receives  HNAE3_UNKNOWN_RESET type it
+		 *    will fetch the correct type of reset.  This would be done
+		 *    by first decoding the types of errors.
+		 */
+		set_bit(HNAE3_UNKNOWN_RESET, &hdev->reset_request);
+		/* fall through */
 	case HCLGE_VECTOR0_EVENT_RST:
 		hclge_reset_task_schedule(hdev);
 		break;
@@ -2593,6 +2611,23 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hclge_dev *hdev,
 {
 	enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
 
+	/* first, resolve any unknown reset type to the known type(s) */
+	if (test_bit(HNAE3_UNKNOWN_RESET, addr)) {
+		/* we will intentionally ignore any errors from this function
+		 *  as we will end up in *some* reset request in any case
+		 */
+		hclge_handle_hw_msix_error(hdev, addr);
+		clear_bit(HNAE3_UNKNOWN_RESET, addr);
+		/* We defered the clearing of the error event which caused
+		 * interrupt since it was not posssible to do that in
+		 * interrupt context (and this is the reason we introduced
+		 * new UNKNOWN reset type). Now, the errors have been
+		 * handled and cleared in hardware we can safely enable
+		 * interrupts. This is an exception to the norm.
+		 */
+		hclge_enable_vector(&hdev->misc_vector, true);
+	}
+
 	/* return the highest priority reset level amongst all */
 	if (test_bit(HNAE3_IMP_RESET, addr)) {
 		rst_level = HNAE3_IMP_RESET;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index ee6024270d5a..106fce172563 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -205,6 +205,7 @@ enum HCLGE_DEV_STATE {
 enum hclge_evt_cause {
 	HCLGE_VECTOR0_EVENT_RST,
 	HCLGE_VECTOR0_EVENT_MBX,
+	HCLGE_VECTOR0_EVENT_ERR,
 	HCLGE_VECTOR0_EVENT_OTHER,
 };
 
-- 
cgit v1.2.3


From 7838f908e251497502092e625f2053398c23516b Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:08:07 +0000
Subject: net: hns3: add handling of hw errors of MAC

This patch adds enable and handling of hw errors of
the MAC block.

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |  1 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 48 ++++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h |  2 +
 3 files changed, 51 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 08d02b928552..46af5673fec2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -215,6 +215,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_SFP_GET_SPEED		= 0x7104,
 
 	/* Error INT commands */
+	HCLGE_MAC_COMMON_INT_EN		= 0x030E,
 	HCLGE_TM_SCH_ECC_INT_EN		= 0x0829,
 	HCLGE_COMMON_ECC_INT_CFG	= 0x1505,
 	HCLGE_QUERY_RAS_INT_STS_BD_NUM	= 0x1510,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 465c76e174ba..e48d45fce101 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -210,6 +210,18 @@ static const struct hclge_hw_error hclge_qcn_ecc_rint[] = {
 	{ /* sentinel */ }
 };
 
+static const struct hclge_hw_error hclge_mac_afifo_tnl_int[] = {
+	{ .int_msk = BIT(0), .msg = "egu_cge_afifo_ecc_1bit_err" },
+	{ .int_msk = BIT(1), .msg = "egu_cge_afifo_ecc_mbit_err" },
+	{ .int_msk = BIT(2), .msg = "egu_lge_afifo_ecc_1bit_err" },
+	{ .int_msk = BIT(3), .msg = "egu_lge_afifo_ecc_mbit_err" },
+	{ .int_msk = BIT(4), .msg = "cge_igu_afifo_ecc_1bit_err" },
+	{ .int_msk = BIT(5), .msg = "cge_igu_afifo_ecc_mbit_err" },
+	{ .int_msk = BIT(6), .msg = "lge_igu_afifo_ecc_1bit_err" },
+	{ .int_msk = BIT(7), .msg = "lge_igu_afifo_ecc_mbit_err" },
+	{ /* sentinel */ }
+};
+
 static void hclge_log_error(struct device *dev, char *reg,
 			    const struct hclge_hw_error *err,
 			    u32 err_sts)
@@ -452,6 +464,27 @@ static int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
+static int hclge_config_mac_err_int(struct hclge_dev *hdev, bool en)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc;
+	int ret;
+
+	/* configure MAC common error interrupts */
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_MAC_COMMON_INT_EN, false);
+	if (en)
+		desc.data[0] = cpu_to_le32(HCLGE_MAC_COMMON_ERR_INT_EN);
+
+	desc.data[1] = cpu_to_le32(HCLGE_MAC_COMMON_ERR_INT_EN_MASK);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(dev,
+			"fail(%d) to configure MAC COMMON error intr\n", ret);
+
+	return ret;
+}
+
 #define HCLGE_SET_DEFAULT_RESET_REQUEST(reset_type) \
 	do { \
 		if (ae_dev->ops->set_default_reset_request) \
@@ -688,6 +721,10 @@ static const struct hclge_hw_blk hw_blk[] = {
 	  .msk = BIT(5), .name = "COMMON",
 	  .config_err_int = hclge_config_common_hw_err_int,
 	},
+	{
+	  .msk = BIT(8), .name = "MAC",
+	  .config_err_int = hclge_config_mac_err_int,
+	},
 	{ /* sentinel */ }
 };
 
@@ -735,7 +772,9 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 	u32 mpf_bd_num, pf_bd_num, bd_num;
 	struct hclge_desc desc_bd;
 	struct hclge_desc *desc;
+	__le32 *desc_data;
 	int ret = 0;
+	u32 status;
 
 	/* set default handling */
 	set_bit(HNAE3_FUNC_RESET, reset_requests);
@@ -774,6 +813,15 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 		goto msi_error;
 	}
 
+	/* log MAC errors */
+	desc_data = (__le32 *)&desc[1];
+	status = le32_to_cpu(*desc_data);
+	if (status) {
+		hclge_log_error(dev, "MAC_AFIFO_TNL_INT_R",
+				&hclge_mac_afifo_tnl_int[0], status);
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+	}
+
 	/* clear all main PF MSIx errors */
 	hclge_cmd_reuse_desc(&desc[0], false);
 	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 05adccbd04ab..8e7d151aa039 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -44,6 +44,8 @@
 #define HCLGE_TM_QCN_MEM_ERR_INT_EN	0xFFFFFF
 #define HCLGE_NCSI_ERR_INT_EN	0x3
 #define HCLGE_NCSI_ERR_INT_TYPE	0x9
+#define HCLGE_MAC_COMMON_ERR_INT_EN		GENMASK(7, 0)
+#define HCLGE_MAC_COMMON_ERR_INT_EN_MASK	GENMASK(7, 0)
 
 #define HCLGE_IGU_INT_MASK		GENMASK(3, 0)
 #define HCLGE_IGU_EGU_TNL_INT_MASK	GENMASK(5, 0)
-- 
cgit v1.2.3


From 8fc9d3e3b46b1aa881d897c1405516ee8c7c6f43 Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:08:08 +0000
Subject: net: hns3: handle hw errors of PPP PF

This patch handles PF hw errors of PPP(Programmable Packet Processor).

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index e48d45fce101..33efa99e23f9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -112,8 +112,8 @@ static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st1[] = {
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_ppp_pf_int[] = {
-	{ .int_msk = BIT(0), .msg = "Tx_vlan_tag_err" },
+static const struct hclge_hw_error hclge_ppp_pf_abnormal_int[] = {
+	{ .int_msk = BIT(0), .msg = "tx_vlan_tag_err" },
 	{ .int_msk = BIT(1), .msg = "rss_list_tc_unassigned_queue_err" },
 	{ /* sentinel */ }
 };
@@ -385,12 +385,16 @@ static int hclge_config_ppp_error_interrupt(struct hclge_dev *hdev, u32 cmd,
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT0_EN);
 			desc[0].data[1] =
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT1_EN);
+			desc[0].data[4] = cpu_to_le32(HCLGE_PPP_PF_ERR_INT_EN);
 		}
 
 		desc[1].data[0] =
 			cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT0_EN_MASK);
 		desc[1].data[1] =
 			cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT1_EN_MASK);
+		if (hdev->pdev->revision >= 0x21)
+			desc[1].data[2] =
+				cpu_to_le32(HCLGE_PPP_PF_ERR_INT_EN_MASK);
 	} else if (cmd == HCLGE_PPP_CMD1_INT_CMD) {
 		if (en) {
 			desc[0].data[0] =
@@ -850,6 +854,13 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 		goto msi_error;
 	}
 
+	/* read and log PPP PF errors */
+	desc_data = (__le32 *)&desc[2];
+	status = le32_to_cpu(*desc_data);
+	if (status)
+		hclge_log_error(dev, "PPP_PF_ABNORMAL_INT_ST0",
+				&hclge_ppp_pf_abnormal_int[0], status);
+
 	/* clear all PF MSIx errors */
 	hclge_cmd_reuse_desc(&desc[0], false);
 	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-- 
cgit v1.2.3


From f69b10b317f9dd286b6f03f2d6d8d5980b8ca9bc Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:08:09 +0000
Subject: net: hns3: handle hw errors of PPU(RCB)

This patch enables and handles hw RAS and MSIx errors of PPU(RCB).

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |   3 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 162 +++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h |  15 ++
 3 files changed, 180 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 46af5673fec2..0223e83d60f1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -217,6 +217,9 @@ enum hclge_opcode_type {
 	/* Error INT commands */
 	HCLGE_MAC_COMMON_INT_EN		= 0x030E,
 	HCLGE_TM_SCH_ECC_INT_EN		= 0x0829,
+	HCLGE_PPU_MPF_ECC_INT_CMD	= 0x0B40,
+	HCLGE_PPU_MPF_OTHER_INT_CMD	= 0x0B41,
+	HCLGE_PPU_PF_OTHER_INT_CMD	= 0x0B42,
 	HCLGE_COMMON_ECC_INT_CFG	= 0x1505,
 	HCLGE_QUERY_RAS_INT_STS_BD_NUM	= 0x1510,
 	HCLGE_QUERY_CLEAR_MPF_RAS_INT	= 0x1511,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 33efa99e23f9..c53a8c78893a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -222,6 +222,47 @@ static const struct hclge_hw_error hclge_mac_afifo_tnl_int[] = {
 	{ /* sentinel */ }
 };
 
+static const struct hclge_hw_error hclge_ppu_mpf_abnormal_int_st2[] = {
+	{ .int_msk = BIT(13), .msg = "rpu_rx_pkt_bit32_ecc_mbit_err" },
+	{ .int_msk = BIT(14), .msg = "rpu_rx_pkt_bit33_ecc_mbit_err" },
+	{ .int_msk = BIT(15), .msg = "rpu_rx_pkt_bit34_ecc_mbit_err" },
+	{ .int_msk = BIT(16), .msg = "rpu_rx_pkt_bit35_ecc_mbit_err" },
+	{ .int_msk = BIT(17), .msg = "rcb_tx_ring_ecc_mbit_err" },
+	{ .int_msk = BIT(18), .msg = "rcb_rx_ring_ecc_mbit_err" },
+	{ .int_msk = BIT(19), .msg = "rcb_tx_fbd_ecc_mbit_err" },
+	{ .int_msk = BIT(20), .msg = "rcb_rx_ebd_ecc_mbit_err" },
+	{ .int_msk = BIT(21), .msg = "rcb_tso_info_ecc_mbit_err" },
+	{ .int_msk = BIT(22), .msg = "rcb_tx_int_info_ecc_mbit_err" },
+	{ .int_msk = BIT(23), .msg = "rcb_rx_int_info_ecc_mbit_err" },
+	{ .int_msk = BIT(24), .msg = "tpu_tx_pkt_0_ecc_mbit_err" },
+	{ .int_msk = BIT(25), .msg = "tpu_tx_pkt_1_ecc_mbit_err" },
+	{ .int_msk = BIT(26), .msg = "rd_bus_err" },
+	{ .int_msk = BIT(27), .msg = "wr_bus_err" },
+	{ .int_msk = BIT(28), .msg = "reg_search_miss" },
+	{ .int_msk = BIT(29), .msg = "rx_q_search_miss" },
+	{ .int_msk = BIT(30), .msg = "ooo_ecc_err_detect" },
+	{ .int_msk = BIT(31), .msg = "ooo_ecc_err_multpl" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ppu_mpf_abnormal_int_st3[] = {
+	{ .int_msk = BIT(4), .msg = "gro_bd_ecc_mbit_err" },
+	{ .int_msk = BIT(5), .msg = "gro_context_ecc_mbit_err" },
+	{ .int_msk = BIT(6), .msg = "rx_stash_cfg_ecc_mbit_err" },
+	{ .int_msk = BIT(7), .msg = "axi_rd_fbd_ecc_mbit_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ppu_pf_abnormal_int[] = {
+	{ .int_msk = BIT(0), .msg = "over_8bd_no_fe" },
+	{ .int_msk = BIT(1), .msg = "tso_mss_cmp_min_err" },
+	{ .int_msk = BIT(2), .msg = "tso_mss_cmp_max_err" },
+	{ .int_msk = BIT(3), .msg = "tx_rd_fbd_poison" },
+	{ .int_msk = BIT(4), .msg = "rx_rd_ebd_poison" },
+	{ .int_msk = BIT(5), .msg = "buf_wait_timeout" },
+	{ /* sentinel */ }
+};
+
 static void hclge_log_error(struct device *dev, char *reg,
 			    const struct hclge_hw_error *err,
 			    u32 err_sts)
@@ -489,6 +530,82 @@ static int hclge_config_mac_err_int(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
+static int hclge_config_ppu_error_interrupts(struct hclge_dev *hdev, u32 cmd,
+					     bool en)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc[2];
+	int num = 1;
+	int ret;
+
+	/* configure PPU error interrupts */
+	if (cmd == HCLGE_PPU_MPF_ECC_INT_CMD) {
+		hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
+		desc[0].flag |= HCLGE_CMD_FLAG_NEXT;
+		hclge_cmd_setup_basic_desc(&desc[1], cmd, false);
+		if (en) {
+			desc[0].data[0] = HCLGE_PPU_MPF_ABNORMAL_INT0_EN;
+			desc[0].data[1] = HCLGE_PPU_MPF_ABNORMAL_INT1_EN;
+			desc[1].data[3] = HCLGE_PPU_MPF_ABNORMAL_INT3_EN;
+			desc[1].data[4] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN;
+		}
+
+		desc[1].data[0] = HCLGE_PPU_MPF_ABNORMAL_INT0_EN_MASK;
+		desc[1].data[1] = HCLGE_PPU_MPF_ABNORMAL_INT1_EN_MASK;
+		desc[1].data[2] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN_MASK;
+		desc[1].data[3] |= HCLGE_PPU_MPF_ABNORMAL_INT3_EN_MASK;
+		num = 2;
+	} else if (cmd == HCLGE_PPU_MPF_OTHER_INT_CMD) {
+		hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
+		if (en)
+			desc[0].data[0] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN2;
+
+		desc[0].data[2] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN2_MASK;
+	} else if (cmd == HCLGE_PPU_PF_OTHER_INT_CMD) {
+		hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
+		if (en)
+			desc[0].data[0] = HCLGE_PPU_PF_ABNORMAL_INT_EN;
+
+		desc[0].data[2] = HCLGE_PPU_PF_ABNORMAL_INT_EN_MASK;
+	} else {
+		dev_err(dev, "Invalid cmd to configure PPU error interrupts\n");
+		return -EINVAL;
+	}
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+
+	return ret;
+}
+
+static int hclge_config_ppu_hw_err_int(struct hclge_dev *hdev, bool en)
+{
+	struct device *dev = &hdev->pdev->dev;
+	int ret;
+
+	ret = hclge_config_ppu_error_interrupts(hdev, HCLGE_PPU_MPF_ECC_INT_CMD,
+						en);
+	if (ret) {
+		dev_err(dev, "fail(%d) to configure PPU MPF ECC error intr\n",
+			ret);
+		return ret;
+	}
+
+	ret = hclge_config_ppu_error_interrupts(hdev,
+						HCLGE_PPU_MPF_OTHER_INT_CMD,
+						en);
+	if (ret) {
+		dev_err(dev, "fail(%d) to configure PPU MPF other intr\n", ret);
+		return ret;
+	}
+
+	ret = hclge_config_ppu_error_interrupts(hdev,
+						HCLGE_PPU_PF_OTHER_INT_CMD, en);
+	if (ret)
+		dev_err(dev, "fail(%d) to configure PPU PF error interrupts\n",
+			ret);
+	return ret;
+}
+
 #define HCLGE_SET_DEFAULT_RESET_REQUEST(reset_type) \
 	do { \
 		if (ae_dev->ops->set_default_reset_request) \
@@ -578,6 +695,29 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev,
 		hclge_log_error(dev, "PPP_MPF_ABNORMAL_INT_ST3",
 				&hclge_ppp_mpf_abnormal_int_st3[0], status);
 
+	/* log PPU(RCB) errors */
+	desc_data = (__le32 *)&desc[5];
+	status = le32_to_cpu(*(desc_data + 1));
+	if (status) {
+		dev_warn(dev, "PPU_MPF_ABNORMAL_INT_ST1 %s found\n",
+			 "rpu_rx_pkt_ecc_mbit_err");
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	status = le32_to_cpu(*(desc_data + 2));
+	if (status) {
+		hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST2",
+				&hclge_ppu_mpf_abnormal_int_st2[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	status = le32_to_cpu(*(desc_data + 3)) & HCLGE_PPU_MPF_INT_ST3_MASK;
+	if (status) {
+		hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST3",
+				&hclge_ppu_mpf_abnormal_int_st3[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
 	/* log TM(Traffic Manager) errors */
 	desc_data = (__le32 *)&desc[6];
 	status = le32_to_cpu(*desc_data);
@@ -717,6 +857,10 @@ static const struct hclge_hw_blk hw_blk[] = {
 	  .msk = BIT(1), .name = "PPP",
 	  .config_err_int = hclge_config_ppp_hw_err_int,
 	},
+	{
+	  .msk = BIT(3), .name = "PPU",
+	  .config_err_int = hclge_config_ppu_hw_err_int,
+	},
 	{
 	  .msk = BIT(4), .name = "TM",
 	  .config_err_int = hclge_config_tm_hw_err_int,
@@ -826,6 +970,17 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
 	}
 
+	/* log PPU(RCB) errors */
+	desc_data = (__le32 *)&desc[5];
+	status = le32_to_cpu(*(desc_data + 2)) &
+			HCLGE_PPU_MPF_INT_ST2_MSIX_MASK;
+	if (status) {
+		dev_warn(dev,
+			 "PPU_MPF_ABNORMAL_INT_ST2[28:29], err_status(0x%x)\n",
+			 status);
+		set_bit(HNAE3_CORE_RESET, reset_requests);
+	}
+
 	/* clear all main PF MSIx errors */
 	hclge_cmd_reuse_desc(&desc[0], false);
 	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
@@ -861,6 +1016,13 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 		hclge_log_error(dev, "PPP_PF_ABNORMAL_INT_ST0",
 				&hclge_ppp_pf_abnormal_int[0], status);
 
+	/* PPU(RCB) PF errors */
+	desc_data = (__le32 *)&desc[3];
+	status = le32_to_cpu(*desc_data) & HCLGE_PPU_PF_INT_MSIX_MASK;
+	if (status)
+		hclge_log_error(dev, "PPU_PF_ABNORMAL_INT_ST",
+				&hclge_ppu_pf_abnormal_int[0], status);
+
 	/* clear all PF MSIx errors */
 	hclge_cmd_reuse_desc(&desc[0], false);
 	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 8e7d151aa039..970d35642f87 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -46,10 +46,25 @@
 #define HCLGE_NCSI_ERR_INT_TYPE	0x9
 #define HCLGE_MAC_COMMON_ERR_INT_EN		GENMASK(7, 0)
 #define HCLGE_MAC_COMMON_ERR_INT_EN_MASK	GENMASK(7, 0)
+#define HCLGE_PPU_MPF_ABNORMAL_INT0_EN		GENMASK(31, 0)
+#define HCLGE_PPU_MPF_ABNORMAL_INT0_EN_MASK	GENMASK(31, 0)
+#define HCLGE_PPU_MPF_ABNORMAL_INT1_EN		GENMASK(31, 0)
+#define HCLGE_PPU_MPF_ABNORMAL_INT1_EN_MASK	GENMASK(31, 0)
+#define HCLGE_PPU_MPF_ABNORMAL_INT2_EN		0x3FFF3FFF
+#define HCLGE_PPU_MPF_ABNORMAL_INT2_EN_MASK	0x3FFF3FFF
+#define HCLGE_PPU_MPF_ABNORMAL_INT2_EN2		0xB
+#define HCLGE_PPU_MPF_ABNORMAL_INT2_EN2_MASK	0xB
+#define HCLGE_PPU_MPF_ABNORMAL_INT3_EN		GENMASK(7, 0)
+#define HCLGE_PPU_MPF_ABNORMAL_INT3_EN_MASK	GENMASK(23, 16)
+#define HCLGE_PPU_PF_ABNORMAL_INT_EN		GENMASK(5, 0)
+#define HCLGE_PPU_PF_ABNORMAL_INT_EN_MASK	GENMASK(5, 0)
 
 #define HCLGE_IGU_INT_MASK		GENMASK(3, 0)
 #define HCLGE_IGU_EGU_TNL_INT_MASK	GENMASK(5, 0)
 #define HCLGE_PPP_MPF_INT_ST3_MASK	GENMASK(5, 0)
+#define HCLGE_PPU_MPF_INT_ST3_MASK	GENMASK(7, 0)
+#define HCLGE_PPU_MPF_INT_ST2_MSIX_MASK	GENMASK(29, 28)
+#define HCLGE_PPU_PF_INT_MSIX_MASK	0x27
 #define HCLGE_QCN_FIFO_INT_MASK		GENMASK(17, 0)
 #define HCLGE_QCN_ECC_INT_MASK		GENMASK(21, 0)
 #define HCLGE_NCSI_ECC_INT_MASK		GENMASK(1, 0)
-- 
cgit v1.2.3


From c3529177db471b964fbe327ffb801266f0482d64 Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:08:10 +0000
Subject: net: hns3: handle hw errors of SSU

This patch enables and handles hw errors of the Storage Switch Unit(SSU).

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |   2 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 187 +++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h |  14 ++
 3 files changed, 203 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 0223e83d60f1..eb91519aacd7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -217,6 +217,8 @@ enum hclge_opcode_type {
 	/* Error INT commands */
 	HCLGE_MAC_COMMON_INT_EN		= 0x030E,
 	HCLGE_TM_SCH_ECC_INT_EN		= 0x0829,
+	HCLGE_SSU_ECC_INT_CMD		= 0x0989,
+	HCLGE_SSU_COMMON_INT_CMD	= 0x098C,
 	HCLGE_PPU_MPF_ECC_INT_CMD	= 0x0B40,
 	HCLGE_PPU_MPF_OTHER_INT_CMD	= 0x0B41,
 	HCLGE_PPU_PF_OTHER_INT_CMD	= 0x0B42,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index c53a8c78893a..81ad9b415556 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -263,6 +263,80 @@ static const struct hclge_hw_error hclge_ppu_pf_abnormal_int[] = {
 	{ /* sentinel */ }
 };
 
+static const struct hclge_hw_error hclge_ssu_com_err_int[] = {
+	{ .int_msk = BIT(0), .msg = "buf_sum_err" },
+	{ .int_msk = BIT(1), .msg = "ppp_mb_num_err" },
+	{ .int_msk = BIT(2), .msg = "ppp_mbid_err" },
+	{ .int_msk = BIT(3), .msg = "ppp_rlt_mac_err" },
+	{ .int_msk = BIT(4), .msg = "ppp_rlt_host_err" },
+	{ .int_msk = BIT(5), .msg = "cks_edit_position_err" },
+	{ .int_msk = BIT(6), .msg = "cks_edit_condition_err" },
+	{ .int_msk = BIT(7), .msg = "vlan_edit_condition_err" },
+	{ .int_msk = BIT(8), .msg = "vlan_num_ot_err" },
+	{ .int_msk = BIT(9), .msg = "vlan_num_in_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ssu_port_based_err_int[] = {
+	{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port" },
+	{ .int_msk = BIT(1), .msg = "tpu_pkt_without_key_port" },
+	{ .int_msk = BIT(2), .msg = "igu_pkt_without_key_port" },
+	{ .int_msk = BIT(3), .msg = "roc_eof_mis_match_port" },
+	{ .int_msk = BIT(4), .msg = "tpu_eof_mis_match_port" },
+	{ .int_msk = BIT(5), .msg = "igu_eof_mis_match_port" },
+	{ .int_msk = BIT(6), .msg = "roc_sof_mis_match_port" },
+	{ .int_msk = BIT(7), .msg = "tpu_sof_mis_match_port" },
+	{ .int_msk = BIT(8), .msg = "igu_sof_mis_match_port" },
+	{ .int_msk = BIT(11), .msg = "ets_rd_int_rx_port" },
+	{ .int_msk = BIT(12), .msg = "ets_wr_int_rx_port" },
+	{ .int_msk = BIT(13), .msg = "ets_rd_int_tx_port" },
+	{ .int_msk = BIT(14), .msg = "ets_wr_int_tx_port" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ssu_fifo_overflow_int[] = {
+	{ .int_msk = BIT(0), .msg = "ig_mac_inf_int" },
+	{ .int_msk = BIT(1), .msg = "ig_host_inf_int" },
+	{ .int_msk = BIT(2), .msg = "ig_roc_buf_int" },
+	{ .int_msk = BIT(3), .msg = "ig_host_data_fifo_int" },
+	{ .int_msk = BIT(4), .msg = "ig_host_key_fifo_int" },
+	{ .int_msk = BIT(5), .msg = "tx_qcn_fifo_int" },
+	{ .int_msk = BIT(6), .msg = "rx_qcn_fifo_int" },
+	{ .int_msk = BIT(7), .msg = "tx_pf_rd_fifo_int" },
+	{ .int_msk = BIT(8), .msg = "rx_pf_rd_fifo_int" },
+	{ .int_msk = BIT(9), .msg = "qm_eof_fifo_int" },
+	{ .int_msk = BIT(10), .msg = "mb_rlt_fifo_int" },
+	{ .int_msk = BIT(11), .msg = "dup_uncopy_fifo_int" },
+	{ .int_msk = BIT(12), .msg = "dup_cnt_rd_fifo_int" },
+	{ .int_msk = BIT(13), .msg = "dup_cnt_drop_fifo_int" },
+	{ .int_msk = BIT(14), .msg = "dup_cnt_wrb_fifo_int" },
+	{ .int_msk = BIT(15), .msg = "host_cmd_fifo_int" },
+	{ .int_msk = BIT(16), .msg = "mac_cmd_fifo_int" },
+	{ .int_msk = BIT(17), .msg = "host_cmd_bitmap_empty_int" },
+	{ .int_msk = BIT(18), .msg = "mac_cmd_bitmap_empty_int" },
+	{ .int_msk = BIT(19), .msg = "dup_bitmap_empty_int" },
+	{ .int_msk = BIT(20), .msg = "out_queue_bitmap_empty_int" },
+	{ .int_msk = BIT(21), .msg = "bank2_bitmap_empty_int" },
+	{ .int_msk = BIT(22), .msg = "bank1_bitmap_empty_int" },
+	{ .int_msk = BIT(23), .msg = "bank0_bitmap_empty_int" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ssu_ets_tcg_int[] = {
+	{ .int_msk = BIT(0), .msg = "ets_rd_int_rx_tcg" },
+	{ .int_msk = BIT(1), .msg = "ets_wr_int_rx_tcg" },
+	{ .int_msk = BIT(2), .msg = "ets_rd_int_tx_tcg" },
+	{ .int_msk = BIT(3), .msg = "ets_wr_int_tx_tcg" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ssu_port_based_pf_int[] = {
+	{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port" },
+	{ .int_msk = BIT(9), .msg = "low_water_line_err_port" },
+	{ .int_msk = BIT(10), .msg = "hi_water_line_err_port" },
+	{ /* sentinel */ }
+};
+
 static void hclge_log_error(struct device *dev, char *reg,
 			    const struct hclge_hw_error *err,
 			    u32 err_sts)
@@ -606,6 +680,63 @@ static int hclge_config_ppu_hw_err_int(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
+static int hclge_config_ssu_hw_err_int(struct hclge_dev *hdev, bool en)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc[2];
+	int ret;
+
+	/* configure SSU ecc error interrupts */
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_SSU_ECC_INT_CMD, false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_SSU_ECC_INT_CMD, false);
+	if (en) {
+		desc[0].data[0] = cpu_to_le32(HCLGE_SSU_1BIT_ECC_ERR_INT_EN);
+		desc[0].data[1] =
+			cpu_to_le32(HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN);
+		desc[0].data[4] = cpu_to_le32(HCLGE_SSU_BIT32_ECC_ERR_INT_EN);
+	}
+
+	desc[1].data[0] = cpu_to_le32(HCLGE_SSU_1BIT_ECC_ERR_INT_EN_MASK);
+	desc[1].data[1] = cpu_to_le32(HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN_MASK);
+	desc[1].data[2] = cpu_to_le32(HCLGE_SSU_BIT32_ECC_ERR_INT_EN_MASK);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], 2);
+	if (ret) {
+		dev_err(dev,
+			"fail(%d) to configure SSU ECC error interrupt\n", ret);
+		return ret;
+	}
+
+	/* configure SSU common error interrupts */
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_SSU_COMMON_INT_CMD, false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_SSU_COMMON_INT_CMD, false);
+
+	if (en) {
+		if (hdev->pdev->revision >= 0x21)
+			desc[0].data[0] =
+				cpu_to_le32(HCLGE_SSU_COMMON_INT_EN);
+		else
+			desc[0].data[0] =
+				cpu_to_le32(HCLGE_SSU_COMMON_INT_EN & ~BIT(5));
+		desc[0].data[1] = cpu_to_le32(HCLGE_SSU_PORT_BASED_ERR_INT_EN);
+		desc[0].data[2] =
+			cpu_to_le32(HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN);
+	}
+
+	desc[1].data[0] = cpu_to_le32(HCLGE_SSU_COMMON_INT_EN_MASK |
+				HCLGE_SSU_PORT_BASED_ERR_INT_EN_MASK);
+	desc[1].data[1] = cpu_to_le32(HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN_MASK);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], 2);
+	if (ret)
+		dev_err(dev,
+			"fail(%d) to configure SSU COMMON error intr\n", ret);
+
+	return ret;
+}
+
 #define HCLGE_SET_DEFAULT_RESET_REQUEST(reset_type) \
 	do { \
 		if (ae_dev->ops->set_default_reset_request) \
@@ -676,6 +807,27 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev,
 		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
 	}
 
+	/* log SSU(Storage Switch Unit) errors */
+	desc_data = (__le32 *)&desc[2];
+	status = le32_to_cpu(*(desc_data + 2));
+	if (status) {
+		dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_0 ssu_ecc_mbit_int[31:0]\n");
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	status = le32_to_cpu(*(desc_data + 3)) & BIT(0);
+	if (status) {
+		dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_ecc_mbit_int[32]\n");
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	status = le32_to_cpu(*(desc_data + 4)) & HCLGE_SSU_COMMON_ERR_INT_MASK;
+	if (status) {
+		hclge_log_error(dev, "SSU_COMMON_ERR_INT",
+				&hclge_ssu_com_err_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+	}
+
 	/* log IGU(Ingress Unit) errors */
 	desc_data = (__le32 *)&desc[3];
 	status = le32_to_cpu(*desc_data) & HCLGE_IGU_INT_MASK;
@@ -775,6 +927,7 @@ static int hclge_handle_pf_ras_error(struct hclge_dev *hdev,
 				     struct hclge_desc *desc,
 				     int num)
 {
+	struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
 	struct device *dev = &hdev->pdev->dev;
 	__le32 *desc_data;
 	u32 status;
@@ -791,6 +944,28 @@ static int hclge_handle_pf_ras_error(struct hclge_dev *hdev,
 		return ret;
 	}
 
+	/* log SSU(Storage Switch Unit) errors */
+	status = le32_to_cpu(desc[0].data[0]);
+	if (status) {
+		hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT",
+				&hclge_ssu_port_based_err_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+	}
+
+	status = le32_to_cpu(desc[0].data[1]);
+	if (status) {
+		hclge_log_error(dev, "SSU_FIFO_OVERFLOW_INT",
+				&hclge_ssu_fifo_overflow_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+	}
+
+	status = le32_to_cpu(desc[0].data[2]);
+	if (status) {
+		hclge_log_error(dev, "SSU_ETS_TCG_INT",
+				&hclge_ssu_ets_tcg_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+	}
+
 	/* log IGU(Ingress Unit) EGU(Egress Unit) TNL errors */
 	desc_data = (__le32 *)&desc[1];
 	status = le32_to_cpu(*desc_data) & HCLGE_IGU_EGU_TNL_INT_MASK;
@@ -857,6 +1032,10 @@ static const struct hclge_hw_blk hw_blk[] = {
 	  .msk = BIT(1), .name = "PPP",
 	  .config_err_int = hclge_config_ppp_hw_err_int,
 	},
+	{
+	  .msk = BIT(2), .name = "SSU",
+	  .config_err_int = hclge_config_ssu_hw_err_int,
+	},
 	{
 	  .msk = BIT(3), .name = "PPU",
 	  .config_err_int = hclge_config_ppu_hw_err_int,
@@ -1009,6 +1188,14 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 		goto msi_error;
 	}
 
+	/* log SSU PF errors */
+	status = le32_to_cpu(desc[0].data[0]) & HCLGE_SSU_PORT_INT_MSIX_MASK;
+	if (status) {
+		hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT",
+				&hclge_ssu_port_based_pf_int[0], status);
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+	}
+
 	/* read and log PPP PF errors */
 	desc_data = (__le32 *)&desc[2];
 	status = le32_to_cpu(*desc_data);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 970d35642f87..d2077f2795fa 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -58,7 +58,21 @@
 #define HCLGE_PPU_MPF_ABNORMAL_INT3_EN_MASK	GENMASK(23, 16)
 #define HCLGE_PPU_PF_ABNORMAL_INT_EN		GENMASK(5, 0)
 #define HCLGE_PPU_PF_ABNORMAL_INT_EN_MASK	GENMASK(5, 0)
+#define HCLGE_SSU_1BIT_ECC_ERR_INT_EN		GENMASK(31, 0)
+#define HCLGE_SSU_1BIT_ECC_ERR_INT_EN_MASK	GENMASK(31, 0)
+#define HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN	GENMASK(31, 0)
+#define HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN_MASK	GENMASK(31, 0)
+#define HCLGE_SSU_BIT32_ECC_ERR_INT_EN		0x0101
+#define HCLGE_SSU_BIT32_ECC_ERR_INT_EN_MASK	0x0101
+#define HCLGE_SSU_COMMON_INT_EN			GENMASK(9, 0)
+#define HCLGE_SSU_COMMON_INT_EN_MASK		GENMASK(9, 0)
+#define HCLGE_SSU_PORT_BASED_ERR_INT_EN		0x0BFF
+#define HCLGE_SSU_PORT_BASED_ERR_INT_EN_MASK	0x0BFF0000
+#define HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN	GENMASK(23, 0)
+#define HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN_MASK	GENMASK(23, 0)
 
+#define HCLGE_SSU_COMMON_ERR_INT_MASK	GENMASK(9, 0)
+#define HCLGE_SSU_PORT_INT_MSIX_MASK	0x7BFF
 #define HCLGE_IGU_INT_MASK		GENMASK(3, 0)
 #define HCLGE_IGU_EGU_TNL_INT_MASK	GENMASK(5, 0)
 #define HCLGE_PPP_MPF_INT_ST3_MASK	GENMASK(5, 0)
-- 
cgit v1.2.3


From 630ba007f4750722bc56dfebfaf1c0316c2fcb69 Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Fri, 7 Dec 2018 21:08:11 +0000
Subject: net: hns3: add handling of RDMA RAS errors

This patch handles the RDMA RAS errors.
1. Enable RAS interrupt, print error detail info and clear error status.
2. Do CORE reset to recovery when these non-fatal errors happened.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |   3 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 185 ++++++++++++++++++++-
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h |  12 ++
 3 files changed, 199 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index eb91519aacd7..b1ee6feb0caf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -229,6 +229,9 @@ enum hclge_opcode_type {
 	HCLGE_QUERY_MSIX_INT_STS_BD_NUM	= 0x1513,
 	HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT	= 0x1514,
 	HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT	= 0x1515,
+	HCLGE_CONFIG_ROCEE_RAS_INT_EN	= 0x1580,
+	HCLGE_QUERY_CLEAR_ROCEE_RAS_INT = 0x1581,
+	HCLGE_ROCEE_PF_RAS_INT_CMD	= 0x1584,
 	HCLGE_IGU_EGU_TNL_INT_EN	= 0x1803,
 	HCLGE_IGU_COMMON_INT_EN		= 0x1806,
 	HCLGE_TM_QCN_MEM_INT_CFG	= 0x1A14,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 81ad9b415556..77deea0beeba 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -337,6 +337,30 @@ static const struct hclge_hw_error hclge_ssu_port_based_pf_int[] = {
 	{ /* sentinel */ }
 };
 
+static const struct hclge_hw_error hclge_rocee_qmm_ovf_err_int[] = {
+	{ .int_msk = 0, .msg = "rocee qmm ovf: sgid invalid err" },
+	{ .int_msk = 0x4, .msg = "rocee qmm ovf: sgid ovf err" },
+	{ .int_msk = 0x8, .msg = "rocee qmm ovf: smac invalid err" },
+	{ .int_msk = 0xC, .msg = "rocee qmm ovf: smac ovf err" },
+	{ .int_msk = 0x10, .msg = "rocee qmm ovf: cqc invalid err" },
+	{ .int_msk = 0x11, .msg = "rocee qmm ovf: cqc ovf err" },
+	{ .int_msk = 0x12, .msg = "rocee qmm ovf: cqc hopnum err" },
+	{ .int_msk = 0x13, .msg = "rocee qmm ovf: cqc ba0 err" },
+	{ .int_msk = 0x14, .msg = "rocee qmm ovf: srqc invalid err" },
+	{ .int_msk = 0x15, .msg = "rocee qmm ovf: srqc ovf err" },
+	{ .int_msk = 0x16, .msg = "rocee qmm ovf: srqc hopnum err" },
+	{ .int_msk = 0x17, .msg = "rocee qmm ovf: srqc ba0 err" },
+	{ .int_msk = 0x18, .msg = "rocee qmm ovf: mpt invalid err" },
+	{ .int_msk = 0x19, .msg = "rocee qmm ovf: mpt ovf err" },
+	{ .int_msk = 0x1A, .msg = "rocee qmm ovf: mpt hopnum err" },
+	{ .int_msk = 0x1B, .msg = "rocee qmm ovf: mpt ba0 err" },
+	{ .int_msk = 0x1C, .msg = "rocee qmm ovf: qpc invalid err" },
+	{ .int_msk = 0x1D, .msg = "rocee qmm ovf: qpc ovf err" },
+	{ .int_msk = 0x1E, .msg = "rocee qmm ovf: qpc hopnum err" },
+	{ .int_msk = 0x1F, .msg = "rocee qmm ovf: qpc ba0 err" },
+	{ /* sentinel */ }
+};
+
 static void hclge_log_error(struct device *dev, char *reg,
 			    const struct hclge_hw_error *err,
 			    u32 err_sts)
@@ -1023,6 +1047,148 @@ static int hclge_handle_all_ras_errors(struct hclge_dev *hdev)
 	return ret;
 }
 
+static int hclge_log_rocee_ovf_error(struct hclge_dev *hdev)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc[2];
+	int ret;
+
+	/* read overflow error status */
+	ret = hclge_cmd_query_error(hdev, &desc[0],
+				    HCLGE_ROCEE_PF_RAS_INT_CMD,
+				    0, 0, 0);
+	if (ret) {
+		dev_err(dev, "failed(%d) to query ROCEE OVF error sts\n", ret);
+		return ret;
+	}
+
+	/* log overflow error */
+	if (le32_to_cpu(desc[0].data[0]) & HCLGE_ROCEE_OVF_ERR_INT_MASK) {
+		const struct hclge_hw_error *err;
+		u32 err_sts;
+
+		err = &hclge_rocee_qmm_ovf_err_int[0];
+		err_sts = HCLGE_ROCEE_OVF_ERR_TYPE_MASK &
+			  le32_to_cpu(desc[0].data[0]);
+		while (err->msg) {
+			if (err->int_msk == err_sts) {
+				dev_warn(dev, "%s [error status=0x%x] found\n",
+					 err->msg,
+					 le32_to_cpu(desc[0].data[0]));
+				break;
+			}
+			err++;
+		}
+	}
+
+	if (le32_to_cpu(desc[0].data[1]) & HCLGE_ROCEE_OVF_ERR_INT_MASK) {
+		dev_warn(dev, "ROCEE TSP OVF [error status=0x%x] found\n",
+			 le32_to_cpu(desc[0].data[1]));
+	}
+
+	if (le32_to_cpu(desc[0].data[2]) & HCLGE_ROCEE_OVF_ERR_INT_MASK) {
+		dev_warn(dev, "ROCEE SCC OVF [error status=0x%x] found\n",
+			 le32_to_cpu(desc[0].data[2]));
+	}
+
+	return 0;
+}
+
+static int hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev)
+{
+	enum hnae3_reset_type reset_type = HNAE3_FUNC_RESET;
+	struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc[2];
+	unsigned int status;
+	int ret;
+
+	/* read RAS error interrupt status */
+	ret = hclge_cmd_query_error(hdev, &desc[0],
+				    HCLGE_QUERY_CLEAR_ROCEE_RAS_INT,
+				    0, 0, 0);
+	if (ret) {
+		dev_err(dev, "failed(%d) to query ROCEE RAS INT SRC\n", ret);
+		/* reset everything for now */
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+		return ret;
+	}
+
+	status = le32_to_cpu(desc[0].data[0]);
+
+	if (status & HCLGE_ROCEE_RERR_INT_MASK)
+		dev_warn(dev, "ROCEE RAS AXI rresp error\n");
+
+	if (status & HCLGE_ROCEE_BERR_INT_MASK)
+		dev_warn(dev, "ROCEE RAS AXI bresp error\n");
+
+	if (status & HCLGE_ROCEE_ECC_INT_MASK) {
+		dev_warn(dev, "ROCEE RAS 2bit ECC error\n");
+		reset_type = HNAE3_GLOBAL_RESET;
+	}
+
+	if (status & HCLGE_ROCEE_OVF_INT_MASK) {
+		ret = hclge_log_rocee_ovf_error(hdev);
+		if (ret) {
+			dev_err(dev, "failed(%d) to process ovf error\n", ret);
+			/* reset everything for now */
+			HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+			return ret;
+		}
+	}
+
+	/* clear error status */
+	hclge_cmd_reuse_desc(&desc[0], false);
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], 1);
+	if (ret) {
+		dev_err(dev, "failed(%d) to clear ROCEE RAS error\n", ret);
+		/* reset everything for now */
+		reset_type = HNAE3_GLOBAL_RESET;
+	}
+
+	HCLGE_SET_DEFAULT_RESET_REQUEST(reset_type);
+
+	return ret;
+}
+
+static int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc;
+	int ret;
+
+	if (hdev->pdev->revision < 0x21 || !hnae3_dev_roce_supported(hdev))
+		return 0;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_CONFIG_ROCEE_RAS_INT_EN, false);
+	if (en) {
+		/* enable ROCEE hw error interrupts */
+		desc.data[0] = cpu_to_le32(HCLGE_ROCEE_RAS_NFE_INT_EN);
+		desc.data[1] = cpu_to_le32(HCLGE_ROCEE_RAS_CE_INT_EN);
+
+		hclge_log_and_clear_rocee_ras_error(hdev);
+	}
+	desc.data[2] = cpu_to_le32(HCLGE_ROCEE_RAS_NFE_INT_EN_MASK);
+	desc.data[3] = cpu_to_le32(HCLGE_ROCEE_RAS_CE_INT_EN_MASK);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(dev, "failed(%d) to config ROCEE RAS interrupt\n", ret);
+
+	return ret;
+}
+
+static int hclge_handle_rocee_ras_error(struct hnae3_ae_dev *ae_dev)
+{
+	struct hclge_dev *hdev = ae_dev->priv;
+
+	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
+	    hdev->pdev->revision < 0x21)
+		return HNAE3_NONE_RESET;
+
+	return hclge_log_and_clear_rocee_ras_error(hdev);
+}
+
 static const struct hclge_hw_blk hw_blk[] = {
 	{
 	  .msk = BIT(0), .name = "IGU_EGU",
@@ -1058,6 +1224,7 @@ static const struct hclge_hw_blk hw_blk[] = {
 int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state)
 {
 	const struct hclge_hw_blk *module = hw_blk;
+	struct device *dev = &hdev->pdev->dev;
 	int ret = 0;
 
 	while (module->name) {
@@ -1069,6 +1236,10 @@ int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state)
 		module++;
 	}
 
+	ret = hclge_config_rocee_ras_interrupt(hdev, state);
+	if (ret)
+		dev_err(dev, "fail(%d) to configure ROCEE err int\n", ret);
+
 	return ret;
 }
 
@@ -1086,9 +1257,21 @@ pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev)
 			 "HNS Non-Fatal RAS error(status=0x%x) identified\n",
 			 status);
 		hclge_handle_all_ras_errors(hdev);
-		return PCI_ERS_RESULT_NEED_RESET;
+	} else {
+		if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
+		    hdev->pdev->revision < 0x21)
+			return PCI_ERS_RESULT_RECOVERED;
+	}
+
+	if (status & HCLGE_RAS_REG_ROCEE_ERR_MASK) {
+		dev_warn(dev, "ROCEE uncorrected RAS error identified\n");
+		hclge_handle_rocee_ras_error(ae_dev);
 	}
 
+	if (status & HCLGE_RAS_REG_NFE_MASK ||
+	    status & HCLGE_RAS_REG_ROCEE_ERR_MASK)
+		return PCI_ERS_RESULT_NEED_RESET;
+
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index d2077f2795fa..51a7d4eb066a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -8,6 +8,7 @@
 
 #define HCLGE_RAS_PF_OTHER_INT_STS_REG   0x20B00
 #define HCLGE_RAS_REG_NFE_MASK   0xFF00
+#define HCLGE_RAS_REG_ROCEE_ERR_MASK   0x3000000
 
 #define HCLGE_VECTOR0_PF_OTHER_INT_STS_REG   0x20800
 #define HCLGE_VECTOR0_REG_MSIX_MASK   0x1FF00
@@ -83,6 +84,17 @@
 #define HCLGE_QCN_ECC_INT_MASK		GENMASK(21, 0)
 #define HCLGE_NCSI_ECC_INT_MASK		GENMASK(1, 0)
 
+#define HCLGE_ROCEE_RAS_NFE_INT_EN		0xF
+#define HCLGE_ROCEE_RAS_CE_INT_EN		0x1
+#define HCLGE_ROCEE_RAS_NFE_INT_EN_MASK		0xF
+#define HCLGE_ROCEE_RAS_CE_INT_EN_MASK		0x1
+#define HCLGE_ROCEE_RERR_INT_MASK		BIT(0)
+#define HCLGE_ROCEE_BERR_INT_MASK		BIT(1)
+#define HCLGE_ROCEE_ECC_INT_MASK		BIT(2)
+#define HCLGE_ROCEE_OVF_INT_MASK		BIT(3)
+#define HCLGE_ROCEE_OVF_ERR_INT_MASK		0x10000
+#define HCLGE_ROCEE_OVF_ERR_TYPE_MASK		0x3F
+
 enum hclge_err_int_type {
 	HCLGE_ERR_INT_MSIX = 0,
 	HCLGE_ERR_INT_RAS_CE = 1,
-- 
cgit v1.2.3


From 58956317c8de52009d1a38a721474c24aef74fe7 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 7 Dec 2018 12:24:57 -0800
Subject: neighbor: Improve garbage collection

The existing garbage collection algorithm has a number of problems:

1. The gc algorithm will not evict PERMANENT entries as those entries
   are managed by userspace, yet the existing algorithm walks the entire
   hash table which means it always considers PERMANENT entries when
   looking for entries to evict. In some use cases (e.g., EVPN) there
   can be tens of thousands of PERMANENT entries leading to wasted
   CPU cycles when gc kicks in. As an example, with 32k permanent
   entries, neigh_alloc has been observed taking more than 4 msec per
   invocation.

2. Currently, when the number of neighbor entries hits gc_thresh2 and
   the last flush for the table was more than 5 seconds ago gc kicks in
   walks the entire hash table evicting *all* entries not in PERMANENT
   or REACHABLE state and not marked as externally learned. There is no
   discriminator on when the neigh entry was created or if it just moved
   from REACHABLE to another NUD_VALID state (e.g., NUD_STALE).

   It is possible for entries to be created or for established neighbor
   entries to be moved to STALE (e.g., an external node sends an ARP
   request) right before the 5 second window lapses:

        -----|---------x|----------|-----
            t-5         t         t+5

   If that happens those entries are evicted during gc causing unnecessary
   thrashing on neighbor entries and userspace caches trying to track them.

   Further, this contradicts the description of gc_thresh2 which says
   "Entries older than 5 seconds will be cleared".

   One workaround is to make gc_thresh2 == gc_thresh3 but that negates the
   whole point of having separate thresholds.

3. Clearing *all* neigh non-PERMANENT/REACHABLE/externally learned entries
   when gc_thresh2 is exceeded is over kill and contributes to trashing
   especially during startup.

This patch addresses these problems as follows:

1. Use of a separate list_head to track entries that can be garbage
   collected along with a separate counter. PERMANENT entries are not
   added to this list.

   The gc_thresh parameters are only compared to the new counter, not the
   total entries in the table. The forced_gc function is updated to only
   walk this new gc_list looking for entries to evict.

2. Entries are added to the list head at the tail and removed from the
   front.

3. Entries are only evicted if they were last updated more than 5 seconds
   ago, adhering to the original intent of gc_thresh2.

4. Forced gc is stopped once the number of gc_entries drops below
   gc_thresh2.

5. Since gc checks do not apply to PERMANENT entries, gc levels are skipped
   when allocating a new neighbor for a PERMANENT entry. By extension this
   means there are no explicit limits on the number of PERMANENT entries
   that can be created, but this is no different than FIB entries or FDB
   entries.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |   4 +-
 include/net/neighbour.h                |   3 +
 net/core/neighbour.c                   | 119 +++++++++++++++++++++++----------
 3 files changed, 90 insertions(+), 36 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index af2a69439b93..acdfb5d2bcaa 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -108,8 +108,8 @@ neigh/default/gc_thresh2 - INTEGER
 	Default: 512
 
 neigh/default/gc_thresh3 - INTEGER
-	Maximum number of neighbor entries allowed.  Increase this
-	when using large numbers of interfaces and when communicating
+	Maximum number of non-PERMANENT neighbor entries allowed.  Increase
+	this when using large numbers of interfaces and when communicating
 	with large numbers of directly-connected peers.
 	Default: 1024
 
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index f58b384aa6c9..6c13072910ab 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -154,6 +154,7 @@ struct neighbour {
 	struct hh_cache		hh;
 	int			(*output)(struct neighbour *, struct sk_buff *);
 	const struct neigh_ops	*ops;
+	struct list_head	gc_list;
 	struct rcu_head		rcu;
 	struct net_device	*dev;
 	u8			primary_key[0];
@@ -214,6 +215,8 @@ struct neigh_table {
 	struct timer_list 	proxy_timer;
 	struct sk_buff_head	proxy_queue;
 	atomic_t		entries;
+	atomic_t		gc_entries;
+	struct list_head	gc_list;
 	rwlock_t		lock;
 	unsigned long		last_rand;
 	struct neigh_statistics	__percpu *stats;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 6d479b5562be..c3b58712e98b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -118,6 +118,34 @@ unsigned long neigh_rand_reach_time(unsigned long base)
 }
 EXPORT_SYMBOL(neigh_rand_reach_time);
 
+static void neigh_mark_dead(struct neighbour *n)
+{
+	n->dead = 1;
+	if (!list_empty(&n->gc_list)) {
+		list_del_init(&n->gc_list);
+		atomic_dec(&n->tbl->gc_entries);
+	}
+}
+
+static void neigh_change_state(struct neighbour *n, u8 new)
+{
+	bool on_gc_list = !list_empty(&n->gc_list);
+	bool new_is_perm = new & NUD_PERMANENT;
+
+	n->nud_state = new;
+
+	/* remove from the gc list if new state is permanent;
+	 * add to the gc list if new state is not permanent
+	 */
+	if (new_is_perm && on_gc_list) {
+		list_del_init(&n->gc_list);
+		atomic_dec(&n->tbl->gc_entries);
+	} else if (!new_is_perm && !on_gc_list) {
+		/* add entries to the tail; cleaning removes from the front */
+		list_add_tail(&n->gc_list, &n->tbl->gc_list);
+		atomic_inc(&n->tbl->gc_entries);
+	}
+}
 
 static bool neigh_del(struct neighbour *n, __u8 state, __u8 flags,
 		      struct neighbour __rcu **np, struct neigh_table *tbl)
@@ -132,7 +160,7 @@ static bool neigh_del(struct neighbour *n, __u8 state, __u8 flags,
 		neigh = rcu_dereference_protected(n->next,
 						  lockdep_is_held(&tbl->lock));
 		rcu_assign_pointer(*np, neigh);
-		n->dead = 1;
+		neigh_mark_dead(n);
 		retval = true;
 	}
 	write_unlock(&n->lock);
@@ -166,32 +194,31 @@ bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl)
 
 static int neigh_forced_gc(struct neigh_table *tbl)
 {
+	int max_clean = atomic_read(&tbl->gc_entries) - tbl->gc_thresh2;
+	unsigned long tref = jiffies - 5 * HZ;
+	u8 flags = NTF_EXT_LEARNED;
+	struct neighbour *n, *tmp;
+	u8 state = NUD_PERMANENT;
 	int shrunk = 0;
-	int i;
-	struct neigh_hash_table *nht;
 
 	NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);
 
 	write_lock_bh(&tbl->lock);
-	nht = rcu_dereference_protected(tbl->nht,
-					lockdep_is_held(&tbl->lock));
-	for (i = 0; i < (1 << nht->hash_shift); i++) {
-		struct neighbour *n;
-		struct neighbour __rcu **np;
 
-		np = &nht->hash_buckets[i];
-		while ((n = rcu_dereference_protected(*np,
-					lockdep_is_held(&tbl->lock))) != NULL) {
-			/* Neighbour record may be discarded if:
-			 * - nobody refers to it.
-			 * - it is not permanent
-			 */
-			if (neigh_del(n, NUD_PERMANENT, NTF_EXT_LEARNED, np,
-				      tbl)) {
-				shrunk = 1;
-				continue;
-			}
-			np = &n->next;
+	list_for_each_entry_safe(n, tmp, &tbl->gc_list, gc_list) {
+		if (refcount_read(&n->refcnt) == 1) {
+			bool remove = false;
+
+			write_lock(&n->lock);
+			if (!(n->nud_state & state) && !(n->flags & flags) &&
+			    time_after(tref, n->updated))
+				remove = true;
+			write_unlock(&n->lock);
+
+			if (remove && neigh_remove_one(n, tbl))
+				shrunk++;
+			if (shrunk >= max_clean)
+				break;
 		}
 	}
 
@@ -260,8 +287,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev,
 						lockdep_is_held(&tbl->lock)));
 			write_lock(&n->lock);
 			neigh_del_timer(n);
-			n->dead = 1;
-
+			neigh_mark_dead(n);
 			if (refcount_read(&n->refcnt) != 1) {
 				/* The most unpleasant situation.
 				   We must destroy neighbour entry,
@@ -321,13 +347,18 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
 }
 EXPORT_SYMBOL(neigh_ifdown);
 
-static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev)
+static struct neighbour *neigh_alloc(struct neigh_table *tbl,
+				     struct net_device *dev,
+				     bool permanent)
 {
 	struct neighbour *n = NULL;
 	unsigned long now = jiffies;
 	int entries;
 
-	entries = atomic_inc_return(&tbl->entries) - 1;
+	if (permanent)
+		goto do_alloc;
+
+	entries = atomic_inc_return(&tbl->gc_entries) - 1;
 	if (entries >= tbl->gc_thresh3 ||
 	    (entries >= tbl->gc_thresh2 &&
 	     time_after(now, tbl->last_flush + 5 * HZ))) {
@@ -340,6 +371,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device
 		}
 	}
 
+do_alloc:
 	n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC);
 	if (!n)
 		goto out_entries;
@@ -358,11 +390,19 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device
 	n->tbl		  = tbl;
 	refcount_set(&n->refcnt, 1);
 	n->dead		  = 1;
+
+	if (!permanent)
+		list_add_tail(&n->gc_list, &n->tbl->gc_list);
+	else
+		INIT_LIST_HEAD(&n->gc_list);
+
+	atomic_inc(&tbl->entries);
 out:
 	return n;
 
 out_entries:
-	atomic_dec(&tbl->entries);
+	if (!permanent)
+		atomic_dec(&tbl->gc_entries);
 	goto out;
 }
 
@@ -505,13 +545,15 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
 }
 EXPORT_SYMBOL(neigh_lookup_nodev);
 
-struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
-				 struct net_device *dev, bool want_ref)
+static struct neighbour *___neigh_create(struct neigh_table *tbl,
+					 const void *pkey,
+					 struct net_device *dev,
+					 bool permanent, bool want_ref)
 {
+	struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev, permanent);
 	u32 hash_val;
 	unsigned int key_len = tbl->key_len;
 	int error;
-	struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev);
 	struct neigh_hash_table *nht;
 
 	if (!n) {
@@ -591,6 +633,12 @@ out_neigh_release:
 	neigh_release(n);
 	goto out;
 }
+
+struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
+				 struct net_device *dev, bool want_ref)
+{
+	return ___neigh_create(tbl, pkey, dev, false, want_ref);
+}
 EXPORT_SYMBOL(__neigh_create);
 
 static u32 pneigh_hash(const void *pkey, unsigned int key_len)
@@ -854,7 +902,7 @@ static void neigh_periodic_work(struct work_struct *work)
 			    (state == NUD_FAILED ||
 			     time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) {
 				*np = n->next;
-				n->dead = 1;
+				neigh_mark_dead(n);
 				write_unlock(&n->lock);
 				neigh_cleanup_and_release(n);
 				continue;
@@ -1167,7 +1215,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
 		neigh_del_timer(neigh);
 		if (old & NUD_CONNECTED)
 			neigh_suspect(neigh);
-		neigh->nud_state = new;
+		neigh_change_state(neigh, new);
 		err = 0;
 		notify = old & NUD_VALID;
 		if ((old & (NUD_INCOMPLETE | NUD_PROBE)) &&
@@ -1246,7 +1294,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
 						((new & NUD_REACHABLE) ?
 						 neigh->parms->reachable_time :
 						 0)));
-		neigh->nud_state = new;
+		neigh_change_state(neigh, new);
 		notify = 1;
 	}
 
@@ -1582,6 +1630,7 @@ void neigh_table_init(int index, struct neigh_table *tbl)
 	unsigned long phsize;
 
 	INIT_LIST_HEAD(&tbl->parms_list);
+	INIT_LIST_HEAD(&tbl->gc_list);
 	list_add(&tbl->parms.list, &tbl->parms_list);
 	write_pnet(&tbl->parms.net, &init_net);
 	refcount_set(&tbl->parms.refcnt, 1);
@@ -1813,7 +1862,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 			goto out;
 		}
 
-		neigh = __neigh_lookup_errno(tbl, dst, dev);
+		neigh = ___neigh_create(tbl, dst, dev,
+					ndm->ndm_state & NUD_PERMANENT,
+					true);
 		if (IS_ERR(neigh)) {
 			err = PTR_ERR(neigh);
 			goto out;
@@ -2654,7 +2705,7 @@ void __neigh_for_each_release(struct neigh_table *tbl,
 				rcu_assign_pointer(*np,
 					rcu_dereference_protected(n->next,
 						lockdep_is_held(&tbl->lock)));
-				n->dead = 1;
+				neigh_mark_dead(n);
 			} else
 				np = &n->next;
 			write_unlock(&n->lock);
-- 
cgit v1.2.3


From 0fbe82e628c817e292ff588cd5847fc935e025f2 Mon Sep 17 00:00:00 2001
From: yupeng <yupeng0921@gmail.com>
Date: Wed, 5 Dec 2018 18:56:28 -0800
Subject: net: call sk_dst_reset when set SO_DONTROUTE

after set SO_DONTROUTE to 1, the IP layer should not route packets if
the dest IP address is not in link scope. But if the socket has cached
the dst_entry, such packets would be routed until the sk_dst_cache
expires. So we should clean the sk_dst_cache when a user set
SO_DONTROUTE option. Below are server/client python scripts which
could reprodue this issue:

server side code:

==========================================================================
import socket
import struct
import time

s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.bind(('0.0.0.0', 9000))
s.listen(1)
sock, addr = s.accept()
sock.setsockopt(socket.SOL_SOCKET, socket.SO_DONTROUTE, struct.pack('i', 1))
while True:
    sock.send(b'foo')
    time.sleep(1)
==========================================================================

client side code:
==========================================================================
import socket
import time

s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.connect(('server_address', 9000))
while True:
    data = s.recv(1024)
    print(data)
==========================================================================

Signed-off-by: yupeng <yupeng0921@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/sock.c b/net/core/sock.c
index f5bb89785e47..f00902c532cc 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -700,6 +700,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		break;
 	case SO_DONTROUTE:
 		sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool);
+		sk_dst_reset(sk);
 		break;
 	case SO_BROADCAST:
 		sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
-- 
cgit v1.2.3


From d37e56df23f9e5916f95b60388c3f179c53c7102 Mon Sep 17 00:00:00 2001
From: Lucas Bates <lucasb@mojatatu.com>
Date: Thu, 6 Dec 2018 17:42:24 -0500
Subject: tc-testing: Add command timeout feature to tdc

Using an attribute set in the tdc_config.py file, limit the
amount of time tdc will wait for an executed command to
complete and prevent the script from hanging entirely.

This timeout will be applied to all executed commands.

Signed-off-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tdc.py        | 16 +++++++++++-----
 tools/testing/selftests/tc-testing/tdc_config.py |  2 ++
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index 7607ba3e3cbe..b862ee5c44b5 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -131,12 +131,16 @@ def exec_cmd(args, pm, stage, command):
         stdout=subprocess.PIPE,
         stderr=subprocess.PIPE,
         env=ENVIR)
-    (rawout, serr) = proc.communicate()
 
-    if proc.returncode != 0 and len(serr) > 0:
-        foutput = serr.decode("utf-8", errors="ignore")
-    else:
-        foutput = rawout.decode("utf-8", errors="ignore")
+    try:
+        (rawout, serr) = proc.communicate(timeout=NAMES['TIMEOUT'])
+        if proc.returncode != 0 and len(serr) > 0:
+            foutput = serr.decode("utf-8", errors="ignore")
+        else:
+            foutput = rawout.decode("utf-8", errors="ignore")
+    except subprocess.TimeoutExpired:
+        foutput = "Command \"{}\" timed out\n".format(command)
+        proc.returncode = 255
 
     proc.stdout.close()
     proc.stderr.close()
@@ -438,6 +442,8 @@ def check_default_settings(args, remaining, pm):
         NAMES['TC'] = args.path
     if args.device != None:
         NAMES['DEV2'] = args.device
+    if 'TIMEOUT' not in NAMES:
+        NAMES['TIMEOUT'] = None
     if not os.path.isfile(NAMES['TC']):
         print("The specified tc path " + NAMES['TC'] + " does not exist.")
         exit(1)
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index d651bc1501bd..6d91e48c2625 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -15,6 +15,8 @@ NAMES = {
           'DEV1': 'v0p1',
           'DEV2': '',
           'BATCH_FILE': './batch.txt',
+          # Length of time in seconds to wait before terminating a command
+          'TIMEOUT': 12,
           # Name of the namespace to use
           'NS': 'tcut',
           # Directory containing eBPF test programs
-- 
cgit v1.2.3


From dfe465d33e7fce145746d836ddb31f0e27f28e28 Mon Sep 17 00:00:00 2001
From: Lucas Bates <lucasb@mojatatu.com>
Date: Thu, 6 Dec 2018 17:42:25 -0500
Subject: tc-testing: Add new TdcResults module

This module includes new classes for tdc to use in keeping track
of test case results, instead of generating and tracking a lengthy
string.

The new module can be extended to support multiple formal
test result formats to be friendlier to automation.

Signed-off-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/TdcResults.py | 132 +++++++++++++++++++++++
 1 file changed, 132 insertions(+)
 create mode 100644 tools/testing/selftests/tc-testing/TdcResults.py

diff --git a/tools/testing/selftests/tc-testing/TdcResults.py b/tools/testing/selftests/tc-testing/TdcResults.py
new file mode 100644
index 000000000000..1e4d95fdf8d0
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/TdcResults.py
@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+
+from enum import Enum
+
+class ResultState(Enum):
+    noresult = -1
+    skip = 0
+    success = 1
+    fail = 2
+
+class TestResult:
+    def __init__(self, test_id="", test_name=""):
+       self.test_id = test_id
+       self.test_name = test_name
+       self.result = ResultState.noresult
+       self.failmsg = ""
+       self.errormsg = ""
+       self.steps = []
+
+    def set_result(self, result):
+        if (isinstance(result, ResultState)):
+            self.result = result
+            return True
+        else:
+            raise TypeError('Unknown result type, must be type ResultState')
+
+    def get_result(self):
+        return self.result
+
+    def set_errormsg(self, errormsg):
+        self.errormsg = errormsg
+        return True
+
+    def append_errormsg(self, errormsg):
+        self.errormsg = '{}\n{}'.format(self.errormsg, errormsg)
+
+    def get_errormsg(self):
+        return self.errormsg
+
+    def set_failmsg(self, failmsg):
+        self.failmsg = failmsg
+        return True
+
+    def append_failmsg(self, failmsg):
+        self.failmsg = '{}\n{}'.format(self.failmsg, failmsg)
+
+    def get_failmsg(self):
+        return self.failmsg
+
+    def add_steps(self, newstep):
+        if type(newstep) == list:
+            self.steps.extend(newstep)
+        elif type(newstep) == str:
+            self.steps.append(step)
+        else:
+            raise TypeError('TdcResults.add_steps() requires a list or str')
+
+    def get_executed_steps(self):
+        return self.steps
+
+class TestSuiteReport():
+    _testsuite = []
+
+    def add_resultdata(self, result_data):
+        if isinstance(result_data, TestResult):
+            self._testsuite.append(result_data)
+            return True
+
+    def count_tests(self):
+        return len(self._testsuite)
+
+    def count_failures(self):
+        return sum(1 for t in self._testsuite if t.result == ResultState.fail)
+
+    def count_skips(self):
+        return sum(1 for t in self._testsuite if t.result == ResultState.skip)
+
+    def find_result(self, test_id):
+        return next((tr for tr in self._testsuite if tr.test_id == test_id), None)
+
+    def update_result(self, result_data):
+        orig = self.find_result(result_data.test_id)
+        if orig != None:
+            idx = self._testsuite.index(orig)
+            self._testsuite[idx] = result_data
+        else:
+            self.add_resultdata(result_data)
+
+    def format_tap(self):
+        ftap = ""
+        ftap += '1..{}\n'.format(self.count_tests())
+        index = 1
+        for t in self._testsuite:
+            if t.result == ResultState.fail:
+                ftap += 'not '
+            ftap += 'ok {} {} - {}'.format(str(index), t.test_id, t.test_name)
+            if t.result == ResultState.skip or t.result == ResultState.noresult:
+                ftap += ' # skipped - {}\n'.format(t.errormsg)
+            elif t.result == ResultState.fail:
+                if len(t.steps) > 0:
+                    ftap += '\tCommands executed in this test case:'
+                    for step in t.steps:
+                        ftap += '\n\t\t{}'.format(step)
+                ftap += '\n\t{}'.format(t.failmsg)
+            ftap += '\n'
+            index += 1
+        return ftap
+
+    def format_xunit(self):
+        from xml.sax.saxutils import escape
+        xunit = "<testsuites>\n"
+        xunit += '\t<testsuite tests=\"{}\" skips=\"{}\">\n'.format(self.count_tests(), self.count_skips())
+        for t in self._testsuite:
+            xunit += '\t\t<testcase classname=\"{}\" '.format(escape(t.test_id))
+            xunit += 'name=\"{}\">\n'.format(escape(t.test_name))
+            if t.failmsg:
+                xunit += '\t\t\t<failure>\n'
+                if len(t.steps) > 0:
+                    xunit += 'Commands executed in this test case:\n'
+                    for step in t.steps:
+                        xunit += '\t{}\n'.format(escape(step))
+                xunit += 'FAILURE: {}\n'.format(escape(t.failmsg))
+                xunit += '\t\t\t</failure>\n'
+            if t.errormsg:
+                xunit += '\t\t\t<error>\n{}\n'.format(escape(t.errormsg))
+                xunit += '\t\t\t</error>\n'
+            if t.result == ResultState.skip:
+                xunit += '\t\t\t<skipped/>\n'
+            xunit += '\t\t</testcase>\n'
+        xunit += '\t</testsuite>\n'
+        xunit += '</testsuites>\n'
+        return xunit
-- 
cgit v1.2.3


From 915c158deaf97be49e71250f43e1539542217962 Mon Sep 17 00:00:00 2001
From: Lucas Bates <lucasb@mojatatu.com>
Date: Thu, 6 Dec 2018 17:42:26 -0500
Subject: tc-testing: Implement the TdcResults module in tdc

In tdc and the valgrind plugin, begin using the TdcResults module
to track executed test cases.

Signed-off-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/TdcPlugin.py    |   3 +-
 .../tc-testing/plugin-lib/valgrindPlugin.py        |  22 +++-
 tools/testing/selftests/tc-testing/tdc.py          | 117 ++++++++++++---------
 3 files changed, 91 insertions(+), 51 deletions(-)

diff --git a/tools/testing/selftests/tc-testing/TdcPlugin.py b/tools/testing/selftests/tc-testing/TdcPlugin.py
index 3ee9a6dacb52..1d9e279331eb 100644
--- a/tools/testing/selftests/tc-testing/TdcPlugin.py
+++ b/tools/testing/selftests/tc-testing/TdcPlugin.py
@@ -18,11 +18,12 @@ class TdcPlugin:
         if self.args.verbose > 1:
             print(' -- {}.post_suite'.format(self.sub_class))
 
-    def pre_case(self, test_ordinal, testid):
+    def pre_case(self, test_ordinal, testid, test_name):
         '''run commands before test_runner does one test'''
         if self.args.verbose > 1:
             print(' -- {}.pre_case'.format(self.sub_class))
         self.args.testid = testid
+        self.args.test_name = test_name
         self.args.test_ordinal = test_ordinal
 
     def post_case(self):
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
index 477a7bd7d7fb..e00c798de0bb 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
@@ -11,6 +11,7 @@ from string import Template
 import subprocess
 import time
 from TdcPlugin import TdcPlugin
+from TdcResults import *
 
 from tdc_config import *
 
@@ -21,6 +22,7 @@ class SubPlugin(TdcPlugin):
     def __init__(self):
         self.sub_class = 'valgrind/SubPlugin'
         self.tap = ''
+        self._tsr = TestSuiteReport()
         super().__init__()
 
     def pre_suite(self, testcount, testidlist):
@@ -34,10 +36,14 @@ class SubPlugin(TdcPlugin):
     def post_suite(self, index):
         '''run commands after test_runner goes into a test loop'''
         super().post_suite(index)
-        self._add_to_tap('\n|---\n')
         if self.args.verbose > 1:
             print('{}.post_suite'.format(self.sub_class))
-        print('{}'.format(self.tap))
+        #print('{}'.format(self.tap))
+        for xx in range(index - 1, self.testcount):
+            res = TestResult('{}-mem'.format(self.testidlist[xx]), 'Test skipped')
+            res.set_result(ResultState.skip)
+            res.set_errormsg('Skipped because of prior setup/teardown failure')
+            self._add_results(res)
         if self.args.verbose < 4:
             subprocess.check_output('rm -f vgnd-*.log', shell=True)
 
@@ -128,8 +134,17 @@ class SubPlugin(TdcPlugin):
                 nle_num = int(nle_mo.group(1))
 
         mem_results = ''
+        res = TestResult('{}-mem'.format(self.args.testid),
+              '{} memory leak check'.format(self.args.test_name))
         if (def_num > 0) or (ind_num > 0) or (pos_num > 0) or (nle_num > 0):
             mem_results += 'not '
+            res.set_result(ResultState.fail)
+            res.set_failmsg('Memory leak detected')
+            res.append_failmsg(content)
+        else:
+            res.set_result(ResultState.success)
+
+        self._add_results(res)
 
         mem_results += 'ok {} - {}-mem # {}\n'.format(
             self.args.test_ordinal, self.args.testid, 'memory leak check')
@@ -138,5 +153,8 @@ class SubPlugin(TdcPlugin):
             print('{}'.format(content))
             self._add_to_tap(content)
 
+    def _add_results(self, res):
+        self._tsr.add_resultdata(res)
+
     def _add_to_tap(self, more_tap_output):
         self.tap += more_tap_output
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index b862ee5c44b5..e6e4ce80a726 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -23,6 +23,7 @@ from tdc_config import *
 from tdc_helper import *
 
 import TdcPlugin
+from TdcResults import *
 
 
 class PluginMgrTestFail(Exception):
@@ -60,10 +61,10 @@ class PluginMgr:
         for pgn_inst in reversed(self.plugin_instances):
             pgn_inst.post_suite(index)
 
-    def call_pre_case(self, test_ordinal, testid):
+    def call_pre_case(self, test_ordinal, testid, test_name):
         for pgn_inst in self.plugin_instances:
             try:
-                pgn_inst.pre_case(test_ordinal, testid)
+                pgn_inst.pre_case(test_ordinal, testid, test_name)
             except Exception as ee:
                 print('exception {} in call to pre_case for {} plugin'.
                       format(ee, pgn_inst.__class__))
@@ -102,7 +103,6 @@ class PluginMgr:
         self.argparser = argparse.ArgumentParser(
             description='Linux TC unit tests')
 
-
 def replace_keywords(cmd):
     """
     For a given executable command, substitute any known
@@ -187,6 +187,7 @@ def run_one_test(pm, args, index, tidx):
     result = True
     tresult = ""
     tap = ""
+    res = TestResult(tidx['id'], tidx['name'])
     if args.verbose > 0:
         print("\t====================\n=====> ", end="")
     print("Test " + tidx["id"] + ": " + tidx["name"])
@@ -194,7 +195,7 @@ def run_one_test(pm, args, index, tidx):
     # populate NAMES with TESTID for this test
     NAMES['TESTID'] = tidx['id']
 
-    pm.call_pre_case(index, tidx['id'])
+    pm.call_pre_case(index, tidx['id'], tidx['name'])
     prepare_env(args, pm, 'setup', "-----> prepare stage", tidx["setup"])
 
     if (args.verbose > 0):
@@ -209,10 +210,11 @@ def run_one_test(pm, args, index, tidx):
     pm.call_post_execute()
 
     if (exit_code is None or exit_code != int(tidx["expExitCode"])):
-        result = False
         print("exit: {!r}".format(exit_code))
         print("exit: {}".format(int(tidx["expExitCode"])))
         #print("exit: {!r} {}".format(exit_code, int(tidx["expExitCode"])))
+        res.set_result(ResultState.fail)
+        res.set_failmsg('Command exited with {}, expected {}\n{}'.format(exit_code, tidx["expExitCode"], procout))
         print(procout)
     else:
         if args.verbose > 0:
@@ -223,20 +225,15 @@ def run_one_test(pm, args, index, tidx):
         if procout:
             match_index = re.findall(match_pattern, procout)
             if len(match_index) != int(tidx["matchCount"]):
-                result = False
+                res.set_result(ResultState.fail)
+                res.set_failmsg('Could not match regex pattern. Verify command output:\n{}'.format(procout))
+            else:
+                res.set_result(ResultState.success)
         elif int(tidx["matchCount"]) != 0:
-            result = False
-
-    if not result:
-        tresult += 'not '
-    tresult += 'ok {} - {} # {}\n'.format(str(index), tidx['id'], tidx['name'])
-    tap += tresult
-
-    if result == False:
-        if procout:
-            tap += procout
+            res.set_result(ResultState.fail)
+            res.set_failmsg('No output generated by verify command.')
         else:
-            tap += 'No output!\n'
+            res.set_result(ResultState.success)
 
     prepare_env(args, pm, 'teardown', '-----> teardown stage', tidx['teardown'], procout)
     pm.call_post_case()
@@ -245,7 +242,7 @@ def run_one_test(pm, args, index, tidx):
 
     # remove TESTID from NAMES
     del(NAMES['TESTID'])
-    return tap
+    return res
 
 def test_runner(pm, args, filtered_tests):
     """
@@ -265,25 +262,15 @@ def test_runner(pm, args, filtered_tests):
     emergency_exit = False
     emergency_exit_message = ''
 
-    if args.notap:
-        if args.verbose:
-            tap = 'notap requested:  omitting test plan\n'
-    else:
-        tap = str(index) + ".." + str(tcount) + "\n"
+    tsr = TestSuiteReport()
+
     try:
         pm.call_pre_suite(tcount, [tidx['id'] for tidx in testlist])
     except Exception as ee:
         ex_type, ex, ex_tb = sys.exc_info()
         print('Exception {} {} (caught in pre_suite).'.
               format(ex_type, ex))
-        # when the extra print statements are uncommented,
-        # the traceback does not appear between them
-        # (it appears way earlier in the tdc.py output)
-        # so don't bother ...
-        # print('--------------------(')
-        # print('traceback')
         traceback.print_tb(ex_tb)
-        # print('--------------------)')
         emergency_exit_message = 'EMERGENCY EXIT, call_pre_suite failed with exception {} {}\n'.format(ex_type, ex)
         emergency_exit = True
         stage = 'pre-SUITE'
@@ -299,15 +286,26 @@ def test_runner(pm, args, filtered_tests):
             if args.verbose > 1:
                 print('Not executing test {} {} because DEV2 not defined'.
                       format(tidx['id'], tidx['name']))
+            res = TestResult(tidx['id'], tidx['name'])
+            res.set_result(ResultState.skip)
+            res.set_errormsg('Not executed because DEV2 is not defined')
+            tsr.add_resultdata(res)
             continue
         try:
             badtest = tidx  # in case it goes bad
-            tap += run_one_test(pm, args, index, tidx)
+            res = run_one_test(pm, args, index, tidx)
+            tsr.add_resultdata(res)
         except PluginMgrTestFail as pmtf:
             ex_type, ex, ex_tb = sys.exc_info()
             stage = pmtf.stage
             message = pmtf.message
             output = pmtf.output
+            res = TestResult(tidx['id'], tidx['name'])
+            res.set_result(ResultState.skip)
+            res.set_errormsg(pmtf.message)
+            res.set_failmsg(pmtf.output)
+            tsr.add_resultdata(res)
+            index += 1
             print(message)
             print('Exception {} {} (caught in test_runner, running test {} {} {} stage {})'.
                   format(ex_type, ex, index, tidx['id'], tidx['name'], stage))
@@ -326,16 +324,16 @@ def test_runner(pm, args, filtered_tests):
     # if we failed in setup or teardown,
     # fill in the remaining tests with ok-skipped
     count = index
-    if not args.notap:
-        tap += 'about to flush the tap output if tests need to be skipped\n'
-        if tcount + 1 != index:
-            for tidx in testlist[index - 1:]:
-                msg = 'skipped - previous {} failed'.format(stage)
-                tap += 'ok {} - {} # {} {} {}\n'.format(
-                    count, tidx['id'], msg, index, badtest.get('id', '--Unknown--'))
-                count += 1
 
-        tap += 'done flushing skipped test tap output\n'
+    if tcount + 1 != count:
+        for tidx in testlist[count - 1:]:
+            res = TestResult(tidx['id'], tidx['name'])
+            res.set_result(ResultState.skip)
+            msg = 'skipped - previous {} failed {} {}'.format(stage,
+                index, badtest.get('id', '--Unknown--'))
+            res.set_errormsg(msg)
+            tsr.add_resultdata(res)
+            count += 1
 
     if args.pause:
         print('Want to pause\nPress enter to continue ...')
@@ -344,7 +342,7 @@ def test_runner(pm, args, filtered_tests):
 
     pm.call_post_suite(index)
 
-    return tap
+    return tsr
 
 def has_blank_ids(idlist):
     """
@@ -384,6 +382,10 @@ def set_args(parser):
     """
     Set the command line arguments for tdc.
     """
+    parser.add_argument(
+        '--outfile', type=str,
+        help='Path to the file in which results should be saved. ' +
+        'Default target is the current directory.')
     parser.add_argument(
         '-p', '--path', type=str,
         help='The full path to the tc executable to use')
@@ -420,8 +422,9 @@ def set_args(parser):
         '-v', '--verbose', action='count', default=0,
         help='Show the commands that are being run')
     parser.add_argument(
-        '-N', '--notap', action='store_true',
-        help='Suppress tap results for command under test')
+        '--format', default='tap', const='tap', nargs='?',
+        choices=['none', 'xunit', 'tap'],
+        help='Specify the format for test results. (Default: TAP)')
     parser.add_argument('-d', '--device',
                         help='Execute the test case in flower category')
     parser.add_argument(
@@ -638,12 +641,30 @@ def set_operation_mode(pm, args):
 
     if len(alltests):
         catresults = test_runner(pm, args, alltests)
+        if args.format == 'none':
+            print('Test results output suppression requested\n')
+        else:
+            print('\nAll test results: \n')
+            if args.format == 'xunit':
+                suffix = 'xml'
+                res = catresults.format_xunit()
+            elif args.format == 'tap':
+                suffix = 'tap'
+                res = catresults.format_tap()
+            print(res)
+            print('\n\n')
+            if not args.outfile:
+                fname = 'test-results.{}'.format(suffix)
+            else:
+                fname = args.outfile
+            with open(fname, 'w') as fh:
+                fh.write(res)
+                fh.close()
+                if os.getenv('SUDO_UID') is not None:
+                    os.chown(fname, uid=int(os.getenv('SUDO_UID')),
+                        gid=int(os.getenv('SUDO_GID')))
     else:
-        catresults = 'No tests found\n'
-    if args.notap:
-        print('Tap output suppression requested\n')
-    else:
-        print('All test results: \n\n{}'.format(catresults))
+        print('No tests found\n')
 
 def main():
     """
-- 
cgit v1.2.3


From 8d189159ac1e8dc6d491840b3b2a9ede762269bc Mon Sep 17 00:00:00 2001
From: Lucas Bates <lucasb@mojatatu.com>
Date: Thu, 6 Dec 2018 17:42:27 -0500
Subject: tc-testing: gitignore, ignore generated test results

Ignore any .tap or .xml test result files generated by tdc.

Additionally, ignore plugin symlinks.

Signed-off-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/.gitignore | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/.gitignore b/tools/testing/selftests/tc-testing/.gitignore
index 7a60b85e148f..c5cc160948b3 100644
--- a/tools/testing/selftests/tc-testing/.gitignore
+++ b/tools/testing/selftests/tc-testing/.gitignore
@@ -1,2 +1,5 @@
 __pycache__/
 *.pyc
+plugins/
+*.xml
+*.tap
-- 
cgit v1.2.3


From 97ef7b4c5501b081c6144a08bba6d87baf69b6e5 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 8 Dec 2018 06:22:46 -0500
Subject: ip: silence udp zerocopy smatch false positive

extra_uref is used in __ip(6)_append_data only if uarg is set.

Smatch sees that the variable is passed to sock_zerocopy_put_abort.
This function accesses it only when uarg is set, but smatch cannot
infer this.

Make this dependency explicit.

Fixes: 52900d22288e ("udp: elide zerocopy operation in hot path")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 3 ++-
 net/ipv6/ip6_output.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 78f028bdad30..ab6618036afe 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1130,7 +1130,8 @@ alloc_new_skb:
 error_efault:
 	err = -EFAULT;
 error:
-	sock_zerocopy_put_abort(uarg, extra_uref);
+	if (uarg)
+		sock_zerocopy_put_abort(uarg, extra_uref);
 	cork->length -= length;
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6592a39e5ec1..be25b34dc5c2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1575,7 +1575,8 @@ alloc_new_skb:
 error_efault:
 	err = -EFAULT;
 error:
-	sock_zerocopy_put_abort(uarg, extra_uref);
+	if (uarg)
+		sock_zerocopy_put_abort(uarg, extra_uref);
 	cork->length -= length;
 	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
-- 
cgit v1.2.3


From 04fa26bab06d9335f15a5d529c4bba25cd507a34 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 8 Dec 2018 16:12:12 +0100
Subject: net: phy: mdio-gpio: Add platform_data support for phy_mask

It is sometimes necessary to instantiate a bit-banging MDIO bus as a
platform device, without the aid of device tree.

When device tree is being used, the bus is not scanned for devices,
only those devices which are in device tree are probed. Without device
tree, by default, all addresses on the bus are scanned. This may then
find a device which is not a PHY, e.g. a switch. And the switch may
have registers containing values which look like a PHY. So during the
scan, a PHY device is wrongly created.

After the bus has been registered, a search is made for
mdio_board_info structures which indicates devices on the bus, and the
driver which should be used for them. This is typically used to
instantiate Ethernet switches from platform drivers.  However, if the
scanning of the bus has created a PHY device at the same location as
indicated into the board info for a switch, the switch device is not
created, since the address is already busy.

This can be avoided by setting the phy_mask of the mdio bus. This mask
prevents addresses on the bus being scanned.

v2
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                             |  1 +
 drivers/net/phy/mdio-gpio.c             |  5 +++++
 include/linux/platform_data/mdio-gpio.h | 13 +++++++++++++
 3 files changed, 19 insertions(+)
 create mode 100644 include/linux/platform_data/mdio-gpio.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 6db870b9d681..59bf56fa2a86 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5610,6 +5610,7 @@ F:	include/linux/of_net.h
 F:	include/linux/phy.h
 F:	include/linux/phy_fixed.h
 F:	include/linux/platform_data/mdio-bcm-unimac.h
+F:	include/linux/platform_data/mdio-gpio.h
 F:	include/trace/events/mdio.h
 F:	include/uapi/linux/mdio.h
 F:	include/uapi/linux/mii.h
diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c
index 0fbcedcdf6e2..1e296dd4067a 100644
--- a/drivers/net/phy/mdio-gpio.c
+++ b/drivers/net/phy/mdio-gpio.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/mdio-gpio.h>
 #include <linux/mdio-bitbang.h>
 #include <linux/mdio-gpio.h>
 #include <linux/gpio/consumer.h>
@@ -112,6 +113,7 @@ static struct mii_bus *mdio_gpio_bus_init(struct device *dev,
 					  struct mdio_gpio_info *bitbang,
 					  int bus_id)
 {
+	struct mdio_gpio_platform_data *pdata = dev_get_platdata(dev);
 	struct mii_bus *new_bus;
 
 	bitbang->ctrl.ops = &mdio_gpio_ops;
@@ -128,6 +130,9 @@ static struct mii_bus *mdio_gpio_bus_init(struct device *dev,
 	else
 		strncpy(new_bus->id, "gpio", MII_BUS_ID_SIZE);
 
+	if (pdata)
+		new_bus->phy_mask = pdata->phy_mask;
+
 	dev_set_drvdata(dev, new_bus);
 
 	return new_bus;
diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h
new file mode 100644
index 000000000000..a5d5ff5e174c
--- /dev/null
+++ b/include/linux/platform_data/mdio-gpio.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * MDIO-GPIO bus platform data structure
+ */
+
+#ifndef __LINUX_MDIO_GPIO_PDATA_H
+#define __LINUX_MDIO_GPIO_PDATA_H
+
+struct mdio_gpio_platform_data {
+	u32 phy_mask;
+};
+
+#endif /* __LINUX_MDIO_GPIO_PDATA_H */
-- 
cgit v1.2.3


From dc9d38cec71c508963b8f41c9d6d9cfd7e4ee393 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 8 Dec 2018 16:12:13 +0100
Subject: net: phy: mdio-gpio: Add phy_ignore_ta_mask to platform data

The Marvell 6390 Ethernet switch family does not perform MDIO
turnaround correctly. Many hardware MDIO bus masters don't care about
this, but the bitbangging implementation in Linux does by default. Add
phy_ignore_ta_mask to the platform data so that the bitbangging code
can be told which devices are known to get TA wrong.

v2
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-gpio.c             | 4 +++-
 include/linux/platform_data/mdio-gpio.h | 1 +
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c
index 1e296dd4067a..ea9a0e339778 100644
--- a/drivers/net/phy/mdio-gpio.c
+++ b/drivers/net/phy/mdio-gpio.c
@@ -130,8 +130,10 @@ static struct mii_bus *mdio_gpio_bus_init(struct device *dev,
 	else
 		strncpy(new_bus->id, "gpio", MII_BUS_ID_SIZE);
 
-	if (pdata)
+	if (pdata) {
 		new_bus->phy_mask = pdata->phy_mask;
+		new_bus->phy_ignore_ta_mask = pdata->phy_ignore_ta_mask;
+	}
 
 	dev_set_drvdata(dev, new_bus);
 
diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h
index a5d5ff5e174c..13874fa6e767 100644
--- a/include/linux/platform_data/mdio-gpio.h
+++ b/include/linux/platform_data/mdio-gpio.h
@@ -8,6 +8,7 @@
 
 struct mdio_gpio_platform_data {
 	u32 phy_mask;
+	u32 phy_ignore_ta_mask;
 };
 
 #endif /* __LINUX_MDIO_GPIO_PDATA_H */
-- 
cgit v1.2.3


From 91ba479573792e1f375e6c2b587c6eab882baa20 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 8 Dec 2018 17:05:18 +0100
Subject: net: dsa: Restore MTU on master device on unload

A previous change tries to set the MTU on the master device to take
into account the DSA overheads. This patch tries to reset the master
device back to the default MTU.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/master.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/dsa/master.c b/net/dsa/master.c
index 42f525bc68e2..a25242e71fb2 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -172,6 +172,18 @@ void dsa_master_set_mtu(struct net_device *dev, struct dsa_port *cpu_dp)
 	rtnl_unlock();
 }
 
+static void dsa_master_reset_mtu(struct net_device *dev)
+{
+	int err;
+
+	rtnl_lock();
+	err = dev_set_mtu(dev, ETH_DATA_LEN);
+	if (err)
+		netdev_dbg(dev,
+			   "Unable to reset MTU to exclude DSA overheads\n");
+	rtnl_unlock();
+}
+
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 {
 	dsa_master_set_mtu(dev,  cpu_dp);
@@ -190,6 +202,7 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 void dsa_master_teardown(struct net_device *dev)
 {
 	dsa_master_ethtool_teardown(dev);
+	dsa_master_reset_mtu(dev);
 
 	dev->dsa_ptr = NULL;
 
-- 
cgit v1.2.3


From a60956ed72f7b715e9918df93fcf2f63a30fdda1 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 8 Dec 2018 17:06:31 +0100
Subject: net: dsa: Make dsa_master_set_mtu() static

Add the missing static keyword.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/master.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/dsa/master.c b/net/dsa/master.c
index a25242e71fb2..d7d5145aa235 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -158,7 +158,7 @@ static void dsa_master_ethtool_teardown(struct net_device *dev)
 	cpu_dp->orig_ethtool_ops = NULL;
 }
 
-void dsa_master_set_mtu(struct net_device *dev, struct dsa_port *cpu_dp)
+static void dsa_master_set_mtu(struct net_device *dev, struct dsa_port *cpu_dp)
 {
 	unsigned int mtu = ETH_DATA_LEN + cpu_dp->tag_ops->overhead;
 	int err;
-- 
cgit v1.2.3


From c454a46b5efd8eff8880e88ece2976e60a26bf35 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 7 Dec 2018 16:42:25 -0800
Subject: bpf: Add bpf_line_info support

This patch adds bpf_line_info support.

It accepts an array of bpf_line_info objects during BPF_PROG_LOAD.
The "line_info", "line_info_cnt" and "line_info_rec_size" are added
to the "union bpf_attr".  The "line_info_rec_size" makes
bpf_line_info extensible in the future.

The new "check_btf_line()" ensures the userspace line_info is valid
for the kernel to use.

When the verifier is translating/patching the bpf_prog (through
"bpf_patch_insn_single()"), the line_infos' insn_off is also
adjusted by the newly added "bpf_adj_linfo()".

If the bpf_prog is jited, this patch also provides the jited addrs (in
aux->jited_linfo) for the corresponding line_info.insn_off.
"bpf_prog_fill_jited_linfo()" is added to fill the aux->jited_linfo.
It is currently called by the x86 jit.  Other jits can also use
"bpf_prog_fill_jited_linfo()" and it will be done in the followup patches.
In the future, if it deemed necessary, a particular jit could also provide
its own "bpf_prog_fill_jited_linfo()" implementation.

A few "*line_info*" fields are added to the bpf_prog_info such
that the user can get the xlated line_info back (i.e. the line_info
with its insn_off reflecting the translated prog).  The jited_line_info
is available if the prog is jited.  It is an array of __u64.
If the prog is not jited, jited_line_info_cnt is 0.

The verifier's verbose log with line_info will be done in
a follow up patch.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c  |   2 +
 include/linux/bpf.h          |  21 +++++
 include/linux/bpf_verifier.h |   1 +
 include/linux/btf.h          |   1 +
 include/linux/filter.h       |   7 ++
 include/uapi/linux/bpf.h     |  19 +++++
 kernel/bpf/btf.c             |   2 +-
 kernel/bpf/core.c            | 118 +++++++++++++++++++++++++-
 kernel/bpf/syscall.c         |  83 ++++++++++++++++--
 kernel/bpf/verifier.c        | 198 +++++++++++++++++++++++++++++++++++++------
 10 files changed, 419 insertions(+), 33 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 2580cd2e98b1..5542303c43d9 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1181,6 +1181,8 @@ out_image:
 	}
 
 	if (!image || !prog->is_func || extra_pass) {
+		if (image)
+			bpf_prog_fill_jited_linfo(prog, addrs);
 out_addrs:
 		kfree(addrs);
 		kfree(jit_data);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e82b7039fc66..0c992b86eb2c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -319,7 +319,28 @@ struct bpf_prog_aux {
 	struct bpf_prog_offload *offload;
 	struct btf *btf;
 	struct bpf_func_info *func_info;
+	/* bpf_line_info loaded from userspace.  linfo->insn_off
+	 * has the xlated insn offset.
+	 * Both the main and sub prog share the same linfo.
+	 * The subprog can access its first linfo by
+	 * using the linfo_idx.
+	 */
+	struct bpf_line_info *linfo;
+	/* jited_linfo is the jited addr of the linfo.  It has a
+	 * one to one mapping to linfo:
+	 * jited_linfo[i] is the jited addr for the linfo[i]->insn_off.
+	 * Both the main and sub prog share the same jited_linfo.
+	 * The subprog can access its first jited_linfo by
+	 * using the linfo_idx.
+	 */
+	void **jited_linfo;
 	u32 func_info_cnt;
+	u32 nr_linfo;
+	/* subprog can use linfo_idx to access its first linfo and
+	 * jited_linfo.
+	 * main prog always has linfo_idx == 0
+	 */
+	u32 linfo_idx;
 	union {
 		struct work_struct work;
 		struct rcu_head	rcu;
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 11f5df1092d9..c736945be7c5 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -203,6 +203,7 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 
 struct bpf_subprog_info {
 	u32 start; /* insn idx of function entry point */
+	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
 };
 
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 8c2199b5d250..b98405a56383 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -46,6 +46,7 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
 int btf_get_fd_by_id(u32 id);
 u32 btf_id(const struct btf *btf);
+bool btf_name_offset_valid(const struct btf *btf, u32 offset);
 
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index d16deead65c6..29f21f9d7f68 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -718,6 +718,13 @@ void bpf_prog_free(struct bpf_prog *fp);
 
 bool bpf_opcode_in_insntable(u8 code);
 
+void bpf_prog_free_linfo(struct bpf_prog *prog);
+void bpf_prog_fill_jited_linfo(struct bpf_prog *prog,
+			       const u32 *insn_to_jit_off);
+int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog);
+void bpf_prog_free_jited_linfo(struct bpf_prog *prog);
+void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog);
+
 struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);
 struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 				  gfp_t gfp_extra_flags);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a84fd232d934..7a66db8d15d5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -356,6 +356,9 @@ union bpf_attr {
 		__u32		func_info_rec_size;	/* userspace bpf_func_info size */
 		__aligned_u64	func_info;	/* func info */
 		__u32		func_info_cnt;	/* number of bpf_func_info records */
+		__u32		line_info_rec_size;	/* userspace bpf_line_info size */
+		__aligned_u64	line_info;	/* line info */
+		__u32		line_info_cnt;	/* number of bpf_line_info records */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -2679,6 +2682,12 @@ struct bpf_prog_info {
 	__u32 func_info_rec_size;
 	__aligned_u64 func_info;
 	__u32 func_info_cnt;
+	__u32 line_info_cnt;
+	__aligned_u64 line_info;
+	__aligned_u64 jited_line_info;
+	__u32 jited_line_info_cnt;
+	__u32 line_info_rec_size;
+	__u32 jited_line_info_rec_size;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -2995,4 +3004,14 @@ struct bpf_func_info {
 	__u32	type_id;
 };
 
+#define BPF_LINE_INFO_LINE_NUM(line_col)	((line_col) >> 10)
+#define BPF_LINE_INFO_LINE_COL(line_col)	((line_col) & 0x3ff)
+
+struct bpf_line_info {
+	__u32	insn_off;
+	__u32	file_name_off;
+	__u32	line_off;
+	__u32	line_col;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a09b2f94ab25..e0a827f95e19 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -444,7 +444,7 @@ static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
 	return kind_ops[BTF_INFO_KIND(t->info)];
 }
 
-static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
+bool btf_name_offset_valid(const struct btf *btf, u32 offset)
 {
 	return BTF_STR_OFFSET_VALID(offset) &&
 		offset < btf->hdr.str_len;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a5b223ef7131..5cdd8da0e7f2 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -105,6 +105,91 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_alloc);
 
+int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog)
+{
+	if (!prog->aux->nr_linfo || !prog->jit_requested)
+		return 0;
+
+	prog->aux->jited_linfo = kcalloc(prog->aux->nr_linfo,
+					 sizeof(*prog->aux->jited_linfo),
+					 GFP_KERNEL | __GFP_NOWARN);
+	if (!prog->aux->jited_linfo)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void bpf_prog_free_jited_linfo(struct bpf_prog *prog)
+{
+	kfree(prog->aux->jited_linfo);
+	prog->aux->jited_linfo = NULL;
+}
+
+void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog)
+{
+	if (prog->aux->jited_linfo && !prog->aux->jited_linfo[0])
+		bpf_prog_free_jited_linfo(prog);
+}
+
+/* The jit engine is responsible to provide an array
+ * for insn_off to the jited_off mapping (insn_to_jit_off).
+ *
+ * The idx to this array is the insn_off.  Hence, the insn_off
+ * here is relative to the prog itself instead of the main prog.
+ * This array has one entry for each xlated bpf insn.
+ *
+ * jited_off is the byte off to the last byte of the jited insn.
+ *
+ * Hence, with
+ * insn_start:
+ *      The first bpf insn off of the prog.  The insn off
+ *      here is relative to the main prog.
+ *      e.g. if prog is a subprog, insn_start > 0
+ * linfo_idx:
+ *      The prog's idx to prog->aux->linfo and jited_linfo
+ *
+ * jited_linfo[linfo_idx] = prog->bpf_func
+ *
+ * For i > linfo_idx,
+ *
+ * jited_linfo[i] = prog->bpf_func +
+ *	insn_to_jit_off[linfo[i].insn_off - insn_start - 1]
+ */
+void bpf_prog_fill_jited_linfo(struct bpf_prog *prog,
+			       const u32 *insn_to_jit_off)
+{
+	u32 linfo_idx, insn_start, insn_end, nr_linfo, i;
+	const struct bpf_line_info *linfo;
+	void **jited_linfo;
+
+	if (!prog->aux->jited_linfo)
+		/* Userspace did not provide linfo */
+		return;
+
+	linfo_idx = prog->aux->linfo_idx;
+	linfo = &prog->aux->linfo[linfo_idx];
+	insn_start = linfo[0].insn_off;
+	insn_end = insn_start + prog->len;
+
+	jited_linfo = &prog->aux->jited_linfo[linfo_idx];
+	jited_linfo[0] = prog->bpf_func;
+
+	nr_linfo = prog->aux->nr_linfo - linfo_idx;
+
+	for (i = 1; i < nr_linfo && linfo[i].insn_off < insn_end; i++)
+		/* The verifier ensures that linfo[i].insn_off is
+		 * strictly increasing
+		 */
+		jited_linfo[i] = prog->bpf_func +
+			insn_to_jit_off[linfo[i].insn_off - insn_start - 1];
+}
+
+void bpf_prog_free_linfo(struct bpf_prog *prog)
+{
+	bpf_prog_free_jited_linfo(prog);
+	kvfree(prog->aux->linfo);
+}
+
 struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 				  gfp_t gfp_extra_flags)
 {
@@ -294,6 +379,26 @@ static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta,
 	return ret;
 }
 
+static void bpf_adj_linfo(struct bpf_prog *prog, u32 off, u32 delta)
+{
+	struct bpf_line_info *linfo;
+	u32 i, nr_linfo;
+
+	nr_linfo = prog->aux->nr_linfo;
+	if (!nr_linfo || !delta)
+		return;
+
+	linfo = prog->aux->linfo;
+
+	for (i = 0; i < nr_linfo; i++)
+		if (off < linfo[i].insn_off)
+			break;
+
+	/* Push all off < linfo[i].insn_off by delta */
+	for (; i < nr_linfo; i++)
+		linfo[i].insn_off += delta;
+}
+
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len)
 {
@@ -349,6 +454,8 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 	 */
 	BUG_ON(bpf_adj_branches(prog_adj, off, insn_delta, false));
 
+	bpf_adj_linfo(prog_adj, off, insn_delta);
+
 	return prog_adj;
 }
 
@@ -1591,13 +1698,20 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	 * be JITed, but falls back to the interpreter.
 	 */
 	if (!bpf_prog_is_dev_bound(fp->aux)) {
+		*err = bpf_prog_alloc_jited_linfo(fp);
+		if (*err)
+			return fp;
+
 		fp = bpf_int_jit_compile(fp);
-#ifdef CONFIG_BPF_JIT_ALWAYS_ON
 		if (!fp->jited) {
+			bpf_prog_free_jited_linfo(fp);
+#ifdef CONFIG_BPF_JIT_ALWAYS_ON
 			*err = -ENOTSUPP;
 			return fp;
-		}
 #endif
+		} else {
+			bpf_prog_free_unused_jited_linfo(fp);
+		}
 	} else {
 		*err = bpf_prog_offload_compile(fp);
 		if (*err)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index aa05aa38f4a8..19c88cff7880 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1215,6 +1215,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 		bpf_prog_kallsyms_del_all(prog);
 		btf_put(prog->aux->btf);
 		kvfree(prog->aux->func_info);
+		bpf_prog_free_linfo(prog);
 
 		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
 	}
@@ -1439,7 +1440,7 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD func_info_cnt
+#define	BPF_PROG_LOAD_LAST_FIELD line_info_cnt
 
 static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 {
@@ -1560,6 +1561,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	return err;
 
 free_used_maps:
+	bpf_prog_free_linfo(prog);
 	kvfree(prog->aux->func_info);
 	btf_put(prog->aux->btf);
 	bpf_prog_kallsyms_del_subprogs(prog);
@@ -2041,6 +2043,37 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
 	return insns;
 }
 
+static int set_info_rec_size(struct bpf_prog_info *info)
+{
+	/*
+	 * Ensure info.*_rec_size is the same as kernel expected size
+	 *
+	 * or
+	 *
+	 * Only allow zero *_rec_size if both _rec_size and _cnt are
+	 * zero.  In this case, the kernel will set the expected
+	 * _rec_size back to the info.
+	 */
+
+	if ((info->func_info_cnt || info->func_info_rec_size) &&
+	    info->func_info_rec_size != sizeof(struct bpf_func_info))
+		return -EINVAL;
+
+	if ((info->line_info_cnt || info->line_info_rec_size) &&
+	    info->line_info_rec_size != sizeof(struct bpf_line_info))
+		return -EINVAL;
+
+	if ((info->jited_line_info_cnt || info->jited_line_info_rec_size) &&
+	    info->jited_line_info_rec_size != sizeof(__u64))
+		return -EINVAL;
+
+	info->func_info_rec_size = sizeof(struct bpf_func_info);
+	info->line_info_rec_size = sizeof(struct bpf_line_info);
+	info->jited_line_info_rec_size = sizeof(__u64);
+
+	return 0;
+}
+
 static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 				   const union bpf_attr *attr,
 				   union bpf_attr __user *uattr)
@@ -2083,11 +2116,9 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 				return -EFAULT;
 	}
 
-	if ((info.func_info_cnt || info.func_info_rec_size) &&
-	    info.func_info_rec_size != sizeof(struct bpf_func_info))
-		return -EINVAL;
-
-	info.func_info_rec_size = sizeof(struct bpf_func_info);
+	err = set_info_rec_size(&info);
+	if (err)
+		return err;
 
 	if (!capable(CAP_SYS_ADMIN)) {
 		info.jited_prog_len = 0;
@@ -2095,6 +2126,8 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		info.nr_jited_ksyms = 0;
 		info.nr_jited_func_lens = 0;
 		info.func_info_cnt = 0;
+		info.line_info_cnt = 0;
+		info.jited_line_info_cnt = 0;
 		goto done;
 	}
 
@@ -2251,6 +2284,44 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		}
 	}
 
+	ulen = info.line_info_cnt;
+	info.line_info_cnt = prog->aux->nr_linfo;
+	if (info.line_info_cnt && ulen) {
+		if (bpf_dump_raw_ok()) {
+			__u8 __user *user_linfo;
+
+			user_linfo = u64_to_user_ptr(info.line_info);
+			ulen = min_t(u32, info.line_info_cnt, ulen);
+			if (copy_to_user(user_linfo, prog->aux->linfo,
+					 info.line_info_rec_size * ulen))
+				return -EFAULT;
+		} else {
+			info.line_info = 0;
+		}
+	}
+
+	ulen = info.jited_line_info_cnt;
+	if (prog->aux->jited_linfo)
+		info.jited_line_info_cnt = prog->aux->nr_linfo;
+	else
+		info.jited_line_info_cnt = 0;
+	if (info.jited_line_info_cnt && ulen) {
+		if (bpf_dump_raw_ok()) {
+			__u64 __user *user_linfo;
+			u32 i;
+
+			user_linfo = u64_to_user_ptr(info.jited_line_info);
+			ulen = min_t(u32, info.jited_line_info_cnt, ulen);
+			for (i = 0; i < ulen; i++) {
+				if (put_user((__u64)(long)prog->aux->jited_linfo[i],
+					     &user_linfo[i]))
+					return -EFAULT;
+			}
+		} else {
+			info.jited_line_info = 0;
+		}
+	}
+
 done:
 	if (copy_to_user(uinfo, &info, info_len) ||
 	    put_user(info_len, &uattr->info.info_len))
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2752d35ad073..9d25506bd55a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4640,15 +4640,17 @@ err_free:
 #define MIN_BPF_FUNCINFO_SIZE	8
 #define MAX_FUNCINFO_REC_SIZE	252
 
-static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
-			  union bpf_attr *attr, union bpf_attr __user *uattr)
+static int check_btf_func(struct bpf_verifier_env *env,
+			  const union bpf_attr *attr,
+			  union bpf_attr __user *uattr)
 {
 	u32 i, nfuncs, urec_size, min_size, prev_offset;
 	u32 krec_size = sizeof(struct bpf_func_info);
-	struct bpf_func_info *krecord = NULL;
+	struct bpf_func_info *krecord;
 	const struct btf_type *type;
+	struct bpf_prog *prog;
+	const struct btf *btf;
 	void __user *urecord;
-	struct btf *btf;
 	int ret = 0;
 
 	nfuncs = attr->func_info_cnt;
@@ -4668,20 +4670,15 @@ static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	btf = btf_get_by_fd(attr->prog_btf_fd);
-	if (IS_ERR(btf)) {
-		verbose(env, "unable to get btf from fd\n");
-		return PTR_ERR(btf);
-	}
+	prog = env->prog;
+	btf = prog->aux->btf;
 
 	urecord = u64_to_user_ptr(attr->func_info);
 	min_size = min_t(u32, krec_size, urec_size);
 
 	krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
-	if (!krecord) {
-		ret = -ENOMEM;
-		goto free_btf;
-	}
+	if (!krecord)
+		return -ENOMEM;
 
 	for (i = 0; i < nfuncs; i++) {
 		ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
@@ -4694,12 +4691,12 @@ static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
 				if (put_user(min_size, &uattr->func_info_rec_size))
 					ret = -EFAULT;
 			}
-			goto free_btf;
+			goto err_free;
 		}
 
 		if (copy_from_user(&krecord[i], urecord, min_size)) {
 			ret = -EFAULT;
-			goto free_btf;
+			goto err_free;
 		}
 
 		/* check insn_off */
@@ -4709,20 +4706,20 @@ static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
 					"nonzero insn_off %u for the first func info record",
 					krecord[i].insn_off);
 				ret = -EINVAL;
-				goto free_btf;
+				goto err_free;
 			}
 		} else if (krecord[i].insn_off <= prev_offset) {
 			verbose(env,
 				"same or smaller insn offset (%u) than previous func info record (%u)",
 				krecord[i].insn_off, prev_offset);
 			ret = -EINVAL;
-			goto free_btf;
+			goto err_free;
 		}
 
 		if (env->subprog_info[i].start != krecord[i].insn_off) {
 			verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
 			ret = -EINVAL;
-			goto free_btf;
+			goto err_free;
 		}
 
 		/* check type_id */
@@ -4731,20 +4728,18 @@ static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
 			verbose(env, "invalid type id %d in func info",
 				krecord[i].type_id);
 			ret = -EINVAL;
-			goto free_btf;
+			goto err_free;
 		}
 
 		prev_offset = krecord[i].insn_off;
 		urecord += urec_size;
 	}
 
-	prog->aux->btf = btf;
 	prog->aux->func_info = krecord;
 	prog->aux->func_info_cnt = nfuncs;
 	return 0;
 
-free_btf:
-	btf_put(btf);
+err_free:
 	kvfree(krecord);
 	return ret;
 }
@@ -4760,6 +4755,150 @@ static void adjust_btf_func(struct bpf_verifier_env *env)
 		env->prog->aux->func_info[i].insn_off = env->subprog_info[i].start;
 }
 
+#define MIN_BPF_LINEINFO_SIZE	(offsetof(struct bpf_line_info, line_col) + \
+		sizeof(((struct bpf_line_info *)(0))->line_col))
+#define MAX_LINEINFO_REC_SIZE	MAX_FUNCINFO_REC_SIZE
+
+static int check_btf_line(struct bpf_verifier_env *env,
+			  const union bpf_attr *attr,
+			  union bpf_attr __user *uattr)
+{
+	u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0;
+	struct bpf_subprog_info *sub;
+	struct bpf_line_info *linfo;
+	struct bpf_prog *prog;
+	const struct btf *btf;
+	void __user *ulinfo;
+	int err;
+
+	nr_linfo = attr->line_info_cnt;
+	if (!nr_linfo)
+		return 0;
+
+	rec_size = attr->line_info_rec_size;
+	if (rec_size < MIN_BPF_LINEINFO_SIZE ||
+	    rec_size > MAX_LINEINFO_REC_SIZE ||
+	    rec_size & (sizeof(u32) - 1))
+		return -EINVAL;
+
+	/* Need to zero it in case the userspace may
+	 * pass in a smaller bpf_line_info object.
+	 */
+	linfo = kvcalloc(nr_linfo, sizeof(struct bpf_line_info),
+			 GFP_KERNEL | __GFP_NOWARN);
+	if (!linfo)
+		return -ENOMEM;
+
+	prog = env->prog;
+	btf = prog->aux->btf;
+
+	s = 0;
+	sub = env->subprog_info;
+	ulinfo = u64_to_user_ptr(attr->line_info);
+	expected_size = sizeof(struct bpf_line_info);
+	ncopy = min_t(u32, expected_size, rec_size);
+	for (i = 0; i < nr_linfo; i++) {
+		err = bpf_check_uarg_tail_zero(ulinfo, expected_size, rec_size);
+		if (err) {
+			if (err == -E2BIG) {
+				verbose(env, "nonzero tailing record in line_info");
+				if (put_user(expected_size,
+					     &uattr->line_info_rec_size))
+					err = -EFAULT;
+			}
+			goto err_free;
+		}
+
+		if (copy_from_user(&linfo[i], ulinfo, ncopy)) {
+			err = -EFAULT;
+			goto err_free;
+		}
+
+		/*
+		 * Check insn_off to ensure
+		 * 1) strictly increasing AND
+		 * 2) bounded by prog->len
+		 *
+		 * The linfo[0].insn_off == 0 check logically falls into
+		 * the later "missing bpf_line_info for func..." case
+		 * because the first linfo[0].insn_off must be the
+		 * first sub also and the first sub must have
+		 * subprog_info[0].start == 0.
+		 */
+		if ((i && linfo[i].insn_off <= prev_offset) ||
+		    linfo[i].insn_off >= prog->len) {
+			verbose(env, "Invalid line_info[%u].insn_off:%u (prev_offset:%u prog->len:%u)\n",
+				i, linfo[i].insn_off, prev_offset,
+				prog->len);
+			err = -EINVAL;
+			goto err_free;
+		}
+
+		if (!btf_name_offset_valid(btf, linfo[i].line_off) ||
+		    !btf_name_offset_valid(btf, linfo[i].file_name_off)) {
+			verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i);
+			err = -EINVAL;
+			goto err_free;
+		}
+
+		if (s != env->subprog_cnt) {
+			if (linfo[i].insn_off == sub[s].start) {
+				sub[s].linfo_idx = i;
+				s++;
+			} else if (sub[s].start < linfo[i].insn_off) {
+				verbose(env, "missing bpf_line_info for func#%u\n", s);
+				err = -EINVAL;
+				goto err_free;
+			}
+		}
+
+		prev_offset = linfo[i].insn_off;
+		ulinfo += rec_size;
+	}
+
+	if (s != env->subprog_cnt) {
+		verbose(env, "missing bpf_line_info for %u funcs starting from func#%u\n",
+			env->subprog_cnt - s, s);
+		err = -EINVAL;
+		goto err_free;
+	}
+
+	prog->aux->linfo = linfo;
+	prog->aux->nr_linfo = nr_linfo;
+
+	return 0;
+
+err_free:
+	kvfree(linfo);
+	return err;
+}
+
+static int check_btf_info(struct bpf_verifier_env *env,
+			  const union bpf_attr *attr,
+			  union bpf_attr __user *uattr)
+{
+	struct btf *btf;
+	int err;
+
+	if (!attr->func_info_cnt && !attr->line_info_cnt)
+		return 0;
+
+	btf = btf_get_by_fd(attr->prog_btf_fd);
+	if (IS_ERR(btf))
+		return PTR_ERR(btf);
+	env->prog->aux->btf = btf;
+
+	err = check_btf_func(env, attr, uattr);
+	if (err)
+		return err;
+
+	err = check_btf_line(env, attr, uattr);
+	if (err)
+		return err;
+
+	return 0;
+}
+
 /* check %cur's range satisfies %old's */
 static bool range_within(struct bpf_reg_state *old,
 			 struct bpf_reg_state *cur)
@@ -6004,7 +6143,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	int i, j, subprog_start, subprog_end = 0, len, subprog;
 	struct bpf_insn *insn;
 	void *old_bpf_func;
-	int err = -ENOMEM;
+	int err;
 
 	if (env->subprog_cnt <= 1)
 		return 0;
@@ -6035,6 +6174,11 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		insn->imm = 1;
 	}
 
+	err = bpf_prog_alloc_jited_linfo(prog);
+	if (err)
+		goto out_undo_insn;
+
+	err = -ENOMEM;
 	func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
 	if (!func)
 		goto out_undo_insn;
@@ -6065,6 +6209,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->name[0] = 'F';
 		func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
 		func[i]->jit_requested = 1;
+		func[i]->aux->linfo = prog->aux->linfo;
+		func[i]->aux->nr_linfo = prog->aux->nr_linfo;
+		func[i]->aux->jited_linfo = prog->aux->jited_linfo;
+		func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx;
 		func[i] = bpf_int_jit_compile(func[i]);
 		if (!func[i]->jited) {
 			err = -ENOTSUPP;
@@ -6138,6 +6286,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	prog->bpf_func = func[0]->bpf_func;
 	prog->aux->func = func;
 	prog->aux->func_cnt = env->subprog_cnt;
+	bpf_prog_free_unused_jited_linfo(prog);
 	return 0;
 out_free:
 	for (i = 0; i < env->subprog_cnt; i++)
@@ -6154,6 +6303,7 @@ out_undo_insn:
 		insn->off = 0;
 		insn->imm = env->insn_aux_data[i].call_imm;
 	}
+	bpf_prog_free_jited_linfo(prog);
 	return err;
 }
 
@@ -6526,7 +6676,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (ret < 0)
 		goto skip_full_check;
 
-	ret = check_btf_func(env->prog, env, attr, uattr);
+	ret = check_btf_info(env, attr, uattr);
 	if (ret < 0)
 		goto skip_full_check;
 
-- 
cgit v1.2.3


From ee491d8dbe496c510fa06a786460638d78428147 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 7 Dec 2018 16:42:26 -0800
Subject: bpf: tools: Sync uapi bpf.h

Sync uapi bpf.h to tools/include/uapi/linux for
the new bpf_line_info.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 16263e8827fc..7973c28b24a0 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -356,6 +356,9 @@ union bpf_attr {
 		__u32		func_info_rec_size;	/* userspace bpf_func_info size */
 		__aligned_u64	func_info;	/* func info */
 		__u32		func_info_cnt;	/* number of bpf_func_info records */
+		__u32		line_info_rec_size;	/* userspace bpf_line_info size */
+		__aligned_u64	line_info;	/* line info */
+		__u32		line_info_cnt;	/* number of bpf_line_info records */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -2679,6 +2682,12 @@ struct bpf_prog_info {
 	__u32 func_info_rec_size;
 	__aligned_u64 func_info;
 	__u32 func_info_cnt;
+	__u32 line_info_cnt;
+	__aligned_u64 line_info;
+	__aligned_u64 jited_line_info;
+	__u32 jited_line_info_cnt;
+	__u32 line_info_rec_size;
+	__u32 jited_line_info_rec_size;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -2995,4 +3004,14 @@ struct bpf_func_info {
 	__u32	type_id;
 };
 
+#define BPF_LINE_INFO_LINE_NUM(line_col)	((line_col) >> 10)
+#define BPF_LINE_INFO_LINE_COL(line_col)	((line_col) & 0x3ff)
+
+struct bpf_line_info {
+	__u32	insn_off;
+	__u32	file_name_off;
+	__u32	line_off;
+	__u32	line_col;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
-- 
cgit v1.2.3


From 05687352c600930058ca4c68048302502e07a572 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 7 Dec 2018 16:42:27 -0800
Subject: bpf: Refactor and bug fix in test_func_type in test_btf.c

1) bpf_load_program_xattr() is absorbing the EBIG error
   which makes testing this case impossible.  It is replaced
   with a direct syscall(__NR_bpf, BPF_PROG_LOAD,...).
2) The test_func_type() is renamed to test_info_raw() to
   prepare for the new line_info test in the next patch.
3) The bpf_obj_get_info_by_fd() testing for func_info
   is refactored to test_get_finfo().  A new
   test_get_linfo() will be added in the next patch
   for testing line_info purpose.
4) The test->func_info_cnt is checked instead of
   a static value "2".
5) Remove unnecessary "\n" in error message.
6) Adding back info_raw_test_num to the cmd arg such
   that a specific test case can be tested, like
   all other existing tests.

7) Fix a bug in handling expected_prog_load_failure.
   A test could pass even if prog_fd != -1 while
   expected_prog_load_failure is true.
8) The min rec_size check should be < 8 instead of < 4.

Fixes: 4798c4ba3ba9 ("tools/bpf: extends test_btf to test load/retrieve func_type info")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_btf.c | 211 +++++++++++++++++++--------------
 1 file changed, 125 insertions(+), 86 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index ff0952ea757a..8d5777c89620 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -6,6 +6,7 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/filter.h>
+#include <linux/unistd.h>
 #include <bpf/bpf.h>
 #include <sys/resource.h>
 #include <libelf.h>
@@ -114,12 +115,13 @@ static struct args {
 	unsigned int raw_test_num;
 	unsigned int file_test_num;
 	unsigned int get_info_test_num;
+	unsigned int info_raw_test_num;
 	bool raw_test;
 	bool file_test;
 	bool get_info_test;
 	bool pprint_test;
 	bool always_log;
-	bool func_type_test;
+	bool info_raw_test;
 } args;
 
 static char btf_log_buf[BTF_LOG_BUF_SIZE];
@@ -3051,7 +3053,7 @@ static int test_pprint(void)
 	return err;
 }
 
-static struct btf_func_type_test {
+static struct prog_info_raw_test {
 	const char *descr;
 	const char *str_sec;
 	__u32 raw_types[MAX_NR_RAW_TYPES];
@@ -3062,7 +3064,7 @@ static struct btf_func_type_test {
 	__u32 func_info_rec_size;
 	__u32 func_info_cnt;
 	bool expected_prog_load_failure;
-} func_type_test[] = {
+} info_raw_tests[] = {
 {
 	.descr = "func_type (main func + one sub)",
 	.raw_types = {
@@ -3198,90 +3200,44 @@ static size_t probe_prog_length(const struct bpf_insn *fp)
 	return len + 1;
 }
 
-static int do_test_func_type(int test_num)
+static int test_get_finfo(const struct prog_info_raw_test *test,
+			  int prog_fd)
 {
-	const struct btf_func_type_test *test = &func_type_test[test_num];
-	unsigned int raw_btf_size, info_len, rec_size;
-	int i, btf_fd = -1, prog_fd = -1, err = 0;
-	struct bpf_load_program_attr attr = {};
-	void *raw_btf, *func_info = NULL;
 	struct bpf_prog_info info = {};
 	struct bpf_func_info *finfo;
-
-	fprintf(stderr, "%s......", test->descr);
-	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
-				 test->str_sec, test->str_sec_size,
-				 &raw_btf_size);
-
-	if (!raw_btf)
-		return -1;
-
-	*btf_log_buf = '\0';
-	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
-			      btf_log_buf, BTF_LOG_BUF_SIZE,
-			      args.always_log);
-	free(raw_btf);
-
-	if (CHECK(btf_fd == -1, "invalid btf_fd errno:%d", errno)) {
-		err = -1;
-		goto done;
-	}
-
-	if (*btf_log_buf && args.always_log)
-		fprintf(stderr, "\n%s", btf_log_buf);
-
-	attr.prog_type = test->prog_type;
-	attr.insns = test->insns;
-	attr.insns_cnt = probe_prog_length(attr.insns);
-	attr.license = "GPL";
-	attr.prog_btf_fd = btf_fd;
-	attr.func_info_rec_size = test->func_info_rec_size;
-	attr.func_info_cnt = test->func_info_cnt;
-	attr.func_info = test->func_info;
-
-	*btf_log_buf = '\0';
-	prog_fd = bpf_load_program_xattr(&attr, btf_log_buf,
-					 BTF_LOG_BUF_SIZE);
-	if (test->expected_prog_load_failure && prog_fd == -1) {
-		err = 0;
-		goto done;
-	}
-	if (CHECK(prog_fd == -1, "invalid prog_id errno:%d", errno)) {
-		fprintf(stderr, "%s\n", btf_log_buf);
-		err = -1;
-		goto done;
-	}
+	__u32 info_len, rec_size, i;
+	void *func_info = NULL;
+	int err;
 
 	/* get necessary lens */
 	info_len = sizeof(struct bpf_prog_info);
 	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
 	if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) {
 		fprintf(stderr, "%s\n", btf_log_buf);
-		err = -1;
-		goto done;
+		return -1;
 	}
-	if (CHECK(info.func_info_cnt != 2,
-		  "incorrect info.func_info_cnt (1st) %d\n",
+	if (CHECK(info.func_info_cnt != test->func_info_cnt,
+		  "incorrect info.func_info_cnt (1st) %d",
 		  info.func_info_cnt)) {
-		err = -1;
-		goto done;
+		return -1;
 	}
+
 	rec_size = info.func_info_rec_size;
-	if (CHECK(rec_size < 4,
-		  "incorrect info.func_info_rec_size (1st) %d\n", rec_size)) {
-		err = -1;
-		goto done;
+	if (CHECK(rec_size < 8,
+		  "incorrect info.func_info_rec_size (1st) %d", rec_size)) {
+		return -1;
 	}
 
+	if (!info.func_info_cnt)
+		return 0;
+
 	func_info = malloc(info.func_info_cnt * rec_size);
-	if (CHECK(!func_info, "out of memory")) {
-		err = -1;
-		goto done;
-	}
+	if (CHECK(!func_info, "out of memory"))
+		return -1;
 
 	/* reset info to only retrieve func_info related data */
 	memset(&info, 0, sizeof(info));
-	info.func_info_cnt = 2;
+	info.func_info_cnt = test->func_info_cnt;
 	info.func_info_rec_size = rec_size;
 	info.func_info = ptr_to_u64(func_info);
 	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
@@ -3290,14 +3246,14 @@ static int do_test_func_type(int test_num)
 		err = -1;
 		goto done;
 	}
-	if (CHECK(info.func_info_cnt != 2,
-		  "incorrect info.func_info_cnt (2nd) %d\n",
+	if (CHECK(info.func_info_cnt != test->func_info_cnt,
+		  "incorrect info.func_info_cnt (2nd) %d",
 		  info.func_info_cnt)) {
 		err = -1;
 		goto done;
 	}
-	if (CHECK(info.func_info_rec_size != rec_size,
-		  "incorrect info.func_info_rec_size (2nd) %d\n",
+	if (CHECK(info.func_info_rec_size < 8,
+		  "incorrect info.func_info_rec_size (2nd) %d",
 		  info.func_info_rec_size)) {
 		err = -1;
 		goto done;
@@ -3310,7 +3266,7 @@ static int do_test_func_type(int test_num)
 	}
 
 	finfo = func_info;
-	for (i = 0; i < 2; i++) {
+	for (i = 0; i < test->func_info_cnt; i++) {
 		if (CHECK(finfo->type_id != test->func_info[i][1],
 			  "incorrect func_type %u expected %u",
 			  finfo->type_id, test->func_info[i][1])) {
@@ -3320,7 +3276,75 @@ static int do_test_func_type(int test_num)
 		finfo = (void *)finfo + rec_size;
 	}
 
+	err = 0;
+
+done:
+	free(func_info);
+	return err;
+}
+
+static int do_test_info_raw(unsigned int test_num)
+{
+	const struct prog_info_raw_test *test = &info_raw_tests[test_num - 1];
+	int btf_fd = -1, prog_fd = -1, err = 0;
+	unsigned int raw_btf_size;
+	union bpf_attr attr = {};
+	void *raw_btf;
+
+	fprintf(stderr, "BTF prog info raw test[%u] (%s): ", test_num, test->descr);
+	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
+				 test->str_sec, test->str_sec_size,
+				 &raw_btf_size);
+
+	if (!raw_btf)
+		return -1;
+
+	*btf_log_buf = '\0';
+	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
+			      btf_log_buf, BTF_LOG_BUF_SIZE,
+			      args.always_log);
+	free(raw_btf);
+
+	if (CHECK(btf_fd == -1, "invalid btf_fd errno:%d", errno)) {
+		err = -1;
+		goto done;
+	}
+
+	if (*btf_log_buf && args.always_log)
+		fprintf(stderr, "\n%s", btf_log_buf);
+	*btf_log_buf = '\0';
+
+	attr.prog_type = test->prog_type;
+	attr.insns = ptr_to_u64(test->insns);
+	attr.insn_cnt = probe_prog_length(test->insns);
+	attr.license = ptr_to_u64("GPL");
+	attr.prog_btf_fd = btf_fd;
+	attr.func_info_rec_size = test->func_info_rec_size;
+	attr.func_info_cnt = test->func_info_cnt;
+	attr.func_info = ptr_to_u64(test->func_info);
+	attr.log_buf = ptr_to_u64(btf_log_buf);
+	attr.log_size = BTF_LOG_BUF_SIZE;
+	attr.log_level = 1;
+
+	prog_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
+	err = ((prog_fd == -1) != test->expected_prog_load_failure);
+	if (CHECK(err, "prog_fd:%d expected_prog_load_failure:%u errno:%d",
+		  prog_fd, test->expected_prog_load_failure, errno)) {
+		err = -1;
+		goto done;
+	}
+
+	if (prog_fd == -1)
+		goto done;
+
+	err = test_get_finfo(test, prog_fd);
+	if (err)
+		goto done;
+
 done:
+	if (!err)
+		fprintf(stderr, "OK");
+
 	if (*btf_log_buf && (err || args.always_log))
 		fprintf(stderr, "\n%s", btf_log_buf);
 
@@ -3328,33 +3352,38 @@ done:
 		close(btf_fd);
 	if (prog_fd != -1)
 		close(prog_fd);
-	free(func_info);
+
 	return err;
 }
 
-static int test_func_type(void)
+static int test_info_raw(void)
 {
 	unsigned int i;
 	int err = 0;
 
-	for (i = 0; i < ARRAY_SIZE(func_type_test); i++)
-		err |= count_result(do_test_func_type(i));
+	if (args.info_raw_test_num)
+		return count_result(do_test_info_raw(args.info_raw_test_num));
+
+	for (i = 1; i <= ARRAY_SIZE(info_raw_tests); i++)
+		err |= count_result(do_test_info_raw(i));
 
 	return err;
 }
 
 static void usage(const char *cmd)
 {
-	fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] |"
-			" [-g test_num (1 - %zu)] |"
-			" [-f test_num (1 - %zu)] | [-p] | [-k] ]\n",
+	fprintf(stderr, "Usage: %s [-l] [[-r btf_raw_test_num (1 - %zu)] |\n"
+			"\t[-g btf_get_info_test_num (1 - %zu)] |\n"
+			"\t[-f btf_file_test_num (1 - %zu)] |\n"
+			"\t[-k btf_prog_info_raw_test_num (1 - %zu)] |\n"
+			"\t[-p (pretty print test)]]\n",
 		cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests),
-		ARRAY_SIZE(file_tests));
+		ARRAY_SIZE(file_tests), ARRAY_SIZE(info_raw_tests));
 }
 
 static int parse_args(int argc, char **argv)
 {
-	const char *optstr = "lpkf:r:g:";
+	const char *optstr = "lpk:f:r:g:";
 	int opt;
 
 	while ((opt = getopt(argc, argv, optstr)) != -1) {
@@ -3378,7 +3407,8 @@ static int parse_args(int argc, char **argv)
 			args.pprint_test = true;
 			break;
 		case 'k':
-			args.func_type_test = true;
+			args.info_raw_test_num = atoi(optarg);
+			args.info_raw_test = true;
 			break;
 		case 'h':
 			usage(argv[0]);
@@ -3413,6 +3443,14 @@ static int parse_args(int argc, char **argv)
 		return -1;
 	}
 
+	if (args.info_raw_test_num &&
+	    (args.info_raw_test_num < 1 ||
+	     args.info_raw_test_num > ARRAY_SIZE(info_raw_tests))) {
+		fprintf(stderr, "BTF prog info raw test number must be [1 - %zu]\n",
+			ARRAY_SIZE(info_raw_tests));
+		return -1;
+	}
+
 	return 0;
 }
 
@@ -3445,16 +3483,17 @@ int main(int argc, char **argv)
 	if (args.pprint_test)
 		err |= test_pprint();
 
-	if (args.func_type_test)
-		err |= test_func_type();
+	if (args.info_raw_test)
+		err |= test_info_raw();
 
 	if (args.raw_test || args.get_info_test || args.file_test ||
-	    args.pprint_test || args.func_type_test)
+	    args.pprint_test || args.info_raw_test)
 		goto done;
 
 	err |= test_raw();
 	err |= test_get_info();
 	err |= test_file();
+	err |= test_info_raw();
 
 done:
 	print_summary();
-- 
cgit v1.2.3


From 4d6304c763551cdb420201b1b754cc625d56bdd6 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 7 Dec 2018 16:42:28 -0800
Subject: bpf: Add unit tests for bpf_line_info

Add unit tests for bpf_line_info for both BPF_PROG_LOAD and
BPF_OBJ_GET_INFO_BY_FD.

jit enabled:
[root@arch-fb-vm1 bpf]# ./test_btf -k 0
BTF prog info raw test[5] (line_info (No subprog)): OK
BTF prog info raw test[6] (line_info (No subprog. insn_off >= prog->len)): OK
BTF prog info raw test[7] (line_info (No subprog. zero tailing line_info): OK
BTF prog info raw test[8] (line_info (No subprog. nonzero tailing line_info)): OK
BTF prog info raw test[9] (line_info (subprog)): OK
BTF prog info raw test[10] (line_info (subprog + func_info)): OK
BTF prog info raw test[11] (line_info (subprog. missing 1st func line info)): OK
BTF prog info raw test[12] (line_info (subprog. missing 2nd func line info)): OK
BTF prog info raw test[13] (line_info (subprog. unordered insn offset)): OK

jit disabled:
BTF prog info raw test[5] (line_info (No subprog)): not jited. skipping jited_line_info check. OK
BTF prog info raw test[6] (line_info (No subprog. insn_off >= prog->len)): OK
BTF prog info raw test[7] (line_info (No subprog. zero tailing line_info): not jited. skipping jited_line_info check. OK
BTF prog info raw test[8] (line_info (No subprog. nonzero tailing line_info)): OK
BTF prog info raw test[9] (line_info (subprog)): not jited. skipping jited_line_info check. OK
BTF prog info raw test[10] (line_info (subprog + func_info)): not jited. skipping jited_line_info check. OK
BTF prog info raw test[11] (line_info (subprog. missing 1st func line info)): OK
BTF prog info raw test[12] (line_info (subprog. missing 2nd func line info)): OK
BTF prog info raw test[13] (line_info (subprog. unordered insn offset)): OK

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_btf.c | 597 ++++++++++++++++++++++++++++++++-
 1 file changed, 580 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 8d5777c89620..7707273736ac 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -108,7 +108,7 @@ static int __base_pr(const char *format, ...)
 #define BTF_END_RAW 0xdeadbeef
 #define NAME_TBD 0xdeadb33f
 
-#define MAX_NR_RAW_TYPES 1024
+#define MAX_NR_RAW_U32 1024
 #define BTF_LOG_BUF_SIZE 65535
 
 static struct args {
@@ -137,7 +137,7 @@ struct btf_raw_test {
 	const char *str_sec;
 	const char *map_name;
 	const char *err_str;
-	__u32 raw_types[MAX_NR_RAW_TYPES];
+	__u32 raw_types[MAX_NR_RAW_U32];
 	__u32 str_sec_size;
 	enum bpf_map_type map_type;
 	__u32 key_size;
@@ -156,6 +156,9 @@ struct btf_raw_test {
 	int str_len_delta;
 };
 
+#define BTF_STR_SEC(str) \
+	.str_sec = str, .str_sec_size = sizeof(str)
+
 static struct btf_raw_test raw_tests[] = {
 /* enum E {
  *     E0,
@@ -1858,11 +1861,11 @@ static const char *get_next_str(const char *start, const char *end)
 	return start < end - 1 ? start + 1 : NULL;
 }
 
-static int get_type_sec_size(const __u32 *raw_types)
+static int get_raw_sec_size(const __u32 *raw_types)
 {
 	int i;
 
-	for (i = MAX_NR_RAW_TYPES - 1;
+	for (i = MAX_NR_RAW_U32 - 1;
 	     i >= 0 && raw_types[i] != BTF_END_RAW;
 	     i--)
 		;
@@ -1874,7 +1877,8 @@ static void *btf_raw_create(const struct btf_header *hdr,
 			    const __u32 *raw_types,
 			    const char *str,
 			    unsigned int str_sec_size,
-			    unsigned int *btf_size)
+			    unsigned int *btf_size,
+			    const char **ret_next_str)
 {
 	const char *next_str = str, *end_str = str + str_sec_size;
 	unsigned int size_needed, offset;
@@ -1883,7 +1887,7 @@ static void *btf_raw_create(const struct btf_header *hdr,
 	uint32_t *ret_types;
 	void *raw_btf;
 
-	type_sec_size = get_type_sec_size(raw_types);
+	type_sec_size = get_raw_sec_size(raw_types);
 	if (CHECK(type_sec_size < 0, "Cannot get nr_raw_types"))
 		return NULL;
 
@@ -1922,6 +1926,8 @@ static void *btf_raw_create(const struct btf_header *hdr,
 	ret_hdr->str_len = str_sec_size;
 
 	*btf_size = size_needed;
+	if (ret_next_str)
+		*ret_next_str = next_str;
 
 	return raw_btf;
 }
@@ -1941,7 +1947,7 @@ static int do_test_raw(unsigned int test_num)
 				 test->raw_types,
 				 test->str_sec,
 				 test->str_sec_size,
-				 &raw_btf_size);
+				 &raw_btf_size, NULL);
 
 	if (!raw_btf)
 		return -1;
@@ -2018,7 +2024,7 @@ static int test_raw(void)
 struct btf_get_info_test {
 	const char *descr;
 	const char *str_sec;
-	__u32 raw_types[MAX_NR_RAW_TYPES];
+	__u32 raw_types[MAX_NR_RAW_U32];
 	__u32 str_sec_size;
 	int btf_size_delta;
 	int (*special_test)(unsigned int test_num);
@@ -2098,7 +2104,7 @@ static int test_big_btf_info(unsigned int test_num)
 				 test->raw_types,
 				 test->str_sec,
 				 test->str_sec_size,
-				 &raw_btf_size);
+				 &raw_btf_size, NULL);
 
 	if (!raw_btf)
 		return -1;
@@ -2182,7 +2188,7 @@ static int test_btf_id(unsigned int test_num)
 				 test->raw_types,
 				 test->str_sec,
 				 test->str_sec_size,
-				 &raw_btf_size);
+				 &raw_btf_size, NULL);
 
 	if (!raw_btf)
 		return -1;
@@ -2320,7 +2326,7 @@ static int do_test_get_info(unsigned int test_num)
 				 test->raw_types,
 				 test->str_sec,
 				 test->str_sec_size,
-				 &raw_btf_size);
+				 &raw_btf_size, NULL);
 
 	if (!raw_btf)
 		return -1;
@@ -2849,7 +2855,7 @@ static int do_test_pprint(void)
 	fprintf(stderr, "%s......", test->descr);
 	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
 				 test->str_sec, test->str_sec_size,
-				 &raw_btf_size);
+				 &raw_btf_size, NULL);
 
 	if (!raw_btf)
 		return -1;
@@ -3053,16 +3059,23 @@ static int test_pprint(void)
 	return err;
 }
 
+#define BPF_LINE_INFO_ENC(insn_off, file_off, line_off, line_num, line_col) \
+	(insn_off), (file_off), (line_off), ((line_num) << 10 | ((line_col) & 0x3ff))
+
 static struct prog_info_raw_test {
 	const char *descr;
 	const char *str_sec;
-	__u32 raw_types[MAX_NR_RAW_TYPES];
+	const char *err_str;
+	__u32 raw_types[MAX_NR_RAW_U32];
 	__u32 str_sec_size;
 	struct bpf_insn insns[MAX_INSNS];
 	__u32 prog_type;
 	__u32 func_info[MAX_SUBPROGS][2];
 	__u32 func_info_rec_size;
 	__u32 func_info_cnt;
+	__u32 line_info[MAX_NR_RAW_U32];
+	__u32 line_info_rec_size;
+	__u32 nr_jited_ksyms;
 	bool expected_prog_load_failure;
 } info_raw_tests[] = {
 {
@@ -3093,6 +3106,7 @@ static struct prog_info_raw_test {
 	.func_info = { {0, 5}, {3, 6} },
 	.func_info_rec_size = 8,
 	.func_info_cnt = 2,
+	.line_info = { BTF_END_RAW },
 },
 
 {
@@ -3123,6 +3137,7 @@ static struct prog_info_raw_test {
 	.func_info = { {0, 5}, {3, 6} },
 	.func_info_rec_size = 4,
 	.func_info_cnt = 2,
+	.line_info = { BTF_END_RAW },
 	.expected_prog_load_failure = true,
 },
 
@@ -3154,6 +3169,7 @@ static struct prog_info_raw_test {
 	.func_info = { {0, 5}, {3, 6} },
 	.func_info_rec_size = 8,
 	.func_info_cnt = 1,
+	.line_info = { BTF_END_RAW },
 	.expected_prog_load_failure = true,
 },
 
@@ -3185,6 +3201,278 @@ static struct prog_info_raw_test {
 	.func_info = { {0, 5}, {2, 6} },
 	.func_info_rec_size = 8,
 	.func_info_cnt = 2,
+	.line_info = { BTF_END_RAW },
+	.expected_prog_load_failure = true,
+},
+
+{
+	.descr = "line_info (No subprog)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0int a=1;\0int b=2;\0return a + b;\0return a + b;"),
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_MOV64_IMM(BPF_REG_1, 2),
+		BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info_cnt = 0,
+	.line_info = {
+		BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+		BPF_LINE_INFO_ENC(1, 0, NAME_TBD, 2, 9),
+		BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8),
+		BPF_LINE_INFO_ENC(3, 0, NAME_TBD, 4, 7),
+		BTF_END_RAW,
+	},
+	.line_info_rec_size = sizeof(struct bpf_line_info),
+	.nr_jited_ksyms = 1,
+},
+
+{
+	.descr = "line_info (No subprog. insn_off >= prog->len)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0int a=1;\0int b=2;\0return a + b;\0return a + b;"),
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_MOV64_IMM(BPF_REG_1, 2),
+		BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info_cnt = 0,
+	.line_info = {
+		BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+		BPF_LINE_INFO_ENC(1, 0, NAME_TBD, 2, 9),
+		BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8),
+		BPF_LINE_INFO_ENC(3, 0, NAME_TBD, 4, 7),
+		BPF_LINE_INFO_ENC(4, 0, 0, 5, 6),
+		BTF_END_RAW,
+	},
+	.line_info_rec_size = sizeof(struct bpf_line_info),
+	.nr_jited_ksyms = 1,
+	.err_str = "line_info[4].insn_off",
+	.expected_prog_load_failure = true,
+},
+
+{
+	.descr = "line_info (No subprog. zero tailing line_info",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0int a=1;\0int b=2;\0return a + b;\0return a + b;"),
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_MOV64_IMM(BPF_REG_1, 2),
+		BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info_cnt = 0,
+	.line_info = {
+		BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10), 0,
+		BPF_LINE_INFO_ENC(1, 0, NAME_TBD, 2, 9), 0,
+		BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8), 0,
+		BPF_LINE_INFO_ENC(3, 0, NAME_TBD, 4, 7), 0,
+		BTF_END_RAW,
+	},
+	.line_info_rec_size = sizeof(struct bpf_line_info) + sizeof(__u32),
+	.nr_jited_ksyms = 1,
+},
+
+{
+	.descr = "line_info (No subprog. nonzero tailing line_info)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0int a=1;\0int b=2;\0return a + b;\0return a + b;"),
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_MOV64_IMM(BPF_REG_1, 2),
+		BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info_cnt = 0,
+	.line_info = {
+		BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10), 0,
+		BPF_LINE_INFO_ENC(1, 0, NAME_TBD, 2, 9), 0,
+		BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8), 0,
+		BPF_LINE_INFO_ENC(3, 0, NAME_TBD, 4, 7), 1,
+		BTF_END_RAW,
+	},
+	.line_info_rec_size = sizeof(struct bpf_line_info) + sizeof(__u32),
+	.nr_jited_ksyms = 1,
+	.err_str = "nonzero tailing record in line_info",
+	.expected_prog_load_failure = true,
+},
+
+{
+	.descr = "line_info (subprog)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0int a=1+1;\0return func(a);\0b+=1;\0return b;"),
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_2, 1),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+		BPF_CALL_REL(1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info_cnt = 0,
+	.line_info = {
+		BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+		BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 2, 9),
+		BPF_LINE_INFO_ENC(5, 0, NAME_TBD, 3, 8),
+		BPF_LINE_INFO_ENC(7, 0, NAME_TBD, 4, 7),
+		BTF_END_RAW,
+	},
+	.line_info_rec_size = sizeof(struct bpf_line_info),
+	.nr_jited_ksyms = 2,
+},
+
+{
+	.descr = "line_info (subprog + func_info)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_FUNC_PROTO_ENC(1, 1),			/* [2] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 2),			/* [3] */
+		BTF_FUNC_ENC(NAME_TBD, 2),			/* [4] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0x\0sub\0main\0int a=1+1;\0return func(a);\0b+=1;\0return b;"),
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_2, 1),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+		BPF_CALL_REL(1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info_cnt = 2,
+	.func_info_rec_size = 8,
+	.func_info = { {0, 4}, {5, 3} },
+	.line_info = {
+		BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+		BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 2, 9),
+		BPF_LINE_INFO_ENC(5, 0, NAME_TBD, 3, 8),
+		BPF_LINE_INFO_ENC(7, 0, NAME_TBD, 4, 7),
+		BTF_END_RAW,
+	},
+	.line_info_rec_size = sizeof(struct bpf_line_info),
+	.nr_jited_ksyms = 2,
+},
+
+{
+	.descr = "line_info (subprog. missing 1st func line info)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0int a=1+1;\0return func(a);\0b+=1;\0return b;"),
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_2, 1),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+		BPF_CALL_REL(1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info_cnt = 0,
+	.line_info = {
+		BPF_LINE_INFO_ENC(1, 0, NAME_TBD, 1, 10),
+		BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 2, 9),
+		BPF_LINE_INFO_ENC(5, 0, NAME_TBD, 3, 8),
+		BPF_LINE_INFO_ENC(7, 0, NAME_TBD, 4, 7),
+		BTF_END_RAW,
+	},
+	.line_info_rec_size = sizeof(struct bpf_line_info),
+	.nr_jited_ksyms = 2,
+	.err_str = "missing bpf_line_info for func#0",
+	.expected_prog_load_failure = true,
+},
+
+{
+	.descr = "line_info (subprog. missing 2nd func line info)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0int a=1+1;\0return func(a);\0b+=1;\0return b;"),
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_2, 1),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+		BPF_CALL_REL(1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info_cnt = 0,
+	.line_info = {
+		BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+		BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 2, 9),
+		BPF_LINE_INFO_ENC(6, 0, NAME_TBD, 3, 8),
+		BPF_LINE_INFO_ENC(7, 0, NAME_TBD, 4, 7),
+		BTF_END_RAW,
+	},
+	.line_info_rec_size = sizeof(struct bpf_line_info),
+	.nr_jited_ksyms = 2,
+	.err_str = "missing bpf_line_info for func#1",
+	.expected_prog_load_failure = true,
+},
+
+{
+	.descr = "line_info (subprog. unordered insn offset)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0int a=1+1;\0return func(a);\0b+=1;\0return b;"),
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_2, 1),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+		BPF_CALL_REL(1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info_cnt = 0,
+	.line_info = {
+		BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+		BPF_LINE_INFO_ENC(5, 0, NAME_TBD, 2, 9),
+		BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8),
+		BPF_LINE_INFO_ENC(7, 0, NAME_TBD, 4, 7),
+		BTF_END_RAW,
+	},
+	.line_info_rec_size = sizeof(struct bpf_line_info),
+	.nr_jited_ksyms = 2,
+	.err_str = "Invalid line_info[2].insn_off",
 	.expected_prog_load_failure = true,
 },
 
@@ -3200,6 +3488,46 @@ static size_t probe_prog_length(const struct bpf_insn *fp)
 	return len + 1;
 }
 
+static __u32 *patch_name_tbd(const __u32 *raw_u32,
+			     const char *str, __u32 str_off,
+			     unsigned int str_sec_size,
+			     unsigned int *ret_size)
+{
+	int i, raw_u32_size = get_raw_sec_size(raw_u32);
+	const char *end_str = str + str_sec_size;
+	const char *next_str = str + str_off;
+	__u32 *new_u32 = NULL;
+
+	if (raw_u32_size == -1)
+		return ERR_PTR(-EINVAL);
+
+	if (!raw_u32_size) {
+		*ret_size = 0;
+		return NULL;
+	}
+
+	new_u32 = malloc(raw_u32_size);
+	if (!new_u32)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < raw_u32_size / sizeof(raw_u32[0]); i++) {
+		if (raw_u32[i] == NAME_TBD) {
+			next_str = get_next_str(next_str, end_str);
+			if (CHECK(!next_str, "Error in getting next_str\n")) {
+				free(new_u32);
+				return ERR_PTR(-EINVAL);
+			}
+			new_u32[i] = next_str - str;
+			next_str += strlen(next_str);
+		} else {
+			new_u32[i] = raw_u32[i];
+		}
+	}
+
+	*ret_size = raw_u32_size;
+	return new_u32;
+}
+
 static int test_get_finfo(const struct prog_info_raw_test *test,
 			  int prog_fd)
 {
@@ -3283,18 +3611,229 @@ done:
 	return err;
 }
 
+static int test_get_linfo(const struct prog_info_raw_test *test,
+			  const void *patched_linfo,
+			  __u32 cnt, int prog_fd)
+{
+	__u32 i, info_len, nr_jited_ksyms, nr_jited_func_lens;
+	__u64 *jited_linfo = NULL, *jited_ksyms = NULL;
+	__u32 rec_size, jited_rec_size, jited_cnt;
+	struct bpf_line_info *linfo = NULL;
+	__u32 cur_func_len, ksyms_found;
+	struct bpf_prog_info info = {};
+	__u32 *jited_func_lens = NULL;
+	__u64 cur_func_ksyms;
+	int err;
+
+	jited_cnt = cnt;
+	rec_size = sizeof(*linfo);
+	jited_rec_size = sizeof(*jited_linfo);
+	if (test->nr_jited_ksyms)
+		nr_jited_ksyms = test->nr_jited_ksyms;
+	else
+		nr_jited_ksyms = test->func_info_cnt;
+	nr_jited_func_lens = nr_jited_ksyms;
+
+	info_len = sizeof(struct bpf_prog_info);
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	if (CHECK(err == -1, "err:%d errno:%d", err, errno)) {
+		err = -1;
+		goto done;
+	}
+
+	if (!info.jited_prog_len) {
+		/* prog is not jited */
+		jited_cnt = 0;
+		nr_jited_ksyms = 1;
+		nr_jited_func_lens = 1;
+	}
+
+	if (CHECK(info.line_info_cnt != cnt ||
+		  info.jited_line_info_cnt != jited_cnt ||
+		  info.nr_jited_ksyms != nr_jited_ksyms ||
+		  info.nr_jited_func_lens != nr_jited_func_lens ||
+		  (!info.line_info_cnt && info.jited_line_info_cnt),
+		  "info: line_info_cnt:%u(expected:%u) jited_line_info_cnt:%u(expected:%u) nr_jited_ksyms:%u(expected:%u) nr_jited_func_lens:%u(expected:%u)",
+		  info.line_info_cnt, cnt,
+		  info.jited_line_info_cnt, jited_cnt,
+		  info.nr_jited_ksyms, nr_jited_ksyms,
+		  info.nr_jited_func_lens, nr_jited_func_lens)) {
+		err = -1;
+		goto done;
+	}
+
+	if (CHECK(info.line_info_rec_size < 16 ||
+		  info.jited_line_info_rec_size < 8,
+		  "info: line_info_rec_size:%u(userspace expected:%u) jited_line_info_rec_size:%u(userspace expected:%u)",
+		  info.line_info_rec_size, rec_size,
+		  info.jited_line_info_rec_size, jited_rec_size)) {
+		err = -1;
+		goto done;
+	}
+
+	if (!cnt)
+		return 0;
+
+	rec_size = info.line_info_rec_size;
+	jited_rec_size = info.jited_line_info_rec_size;
+
+	memset(&info, 0, sizeof(info));
+
+	linfo = calloc(cnt, rec_size);
+	if (CHECK(!linfo, "!linfo")) {
+		err = -1;
+		goto done;
+	}
+	info.line_info_cnt = cnt;
+	info.line_info_rec_size = rec_size;
+	info.line_info = ptr_to_u64(linfo);
+
+	if (jited_cnt) {
+		jited_linfo = calloc(jited_cnt, jited_rec_size);
+		jited_ksyms = calloc(nr_jited_ksyms, sizeof(*jited_ksyms));
+		jited_func_lens = calloc(nr_jited_func_lens,
+					 sizeof(*jited_func_lens));
+		if (CHECK(!jited_linfo || !jited_ksyms || !jited_func_lens,
+			  "jited_linfo:%p jited_ksyms:%p jited_func_lens:%p",
+			  jited_linfo, jited_ksyms, jited_func_lens)) {
+			err = -1;
+			goto done;
+		}
+
+		info.jited_line_info_cnt = jited_cnt;
+		info.jited_line_info_rec_size = jited_rec_size;
+		info.jited_line_info = ptr_to_u64(jited_linfo);
+		info.nr_jited_ksyms = nr_jited_ksyms;
+		info.jited_ksyms = ptr_to_u64(jited_ksyms);
+		info.nr_jited_func_lens = nr_jited_func_lens;
+		info.jited_func_lens = ptr_to_u64(jited_func_lens);
+	}
+
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+
+	/*
+	 * Only recheck the info.*line_info* fields.
+	 * Other fields are not the concern of this test.
+	 */
+	if (CHECK(err == -1 ||
+		  !info.line_info ||
+		  info.line_info_cnt != cnt ||
+		  (jited_cnt && !info.jited_line_info) ||
+		  info.jited_line_info_cnt != jited_cnt ||
+		  info.line_info_rec_size != rec_size ||
+		  info.jited_line_info_rec_size != jited_rec_size,
+		  "err:%d errno:%d info: line_info_cnt:%u(expected:%u) jited_line_info_cnt:%u(expected:%u) line_info_rec_size:%u(expected:%u) jited_linfo_rec_size:%u(expected:%u) line_info:%p jited_line_info:%p",
+		  err, errno,
+		  info.line_info_cnt, cnt,
+		  info.jited_line_info_cnt, jited_cnt,
+		  info.line_info_rec_size, rec_size,
+		  info.jited_line_info_rec_size, jited_rec_size,
+		  (void *)(long)info.line_info,
+		  (void *)(long)info.jited_line_info)) {
+		err = -1;
+		goto done;
+	}
+
+	CHECK(linfo[0].insn_off, "linfo[0].insn_off:%u",
+	      linfo[0].insn_off);
+	for (i = 1; i < cnt; i++) {
+		const struct bpf_line_info *expected_linfo;
+
+		expected_linfo = patched_linfo + (i * test->line_info_rec_size);
+		if (CHECK(linfo[i].insn_off <= linfo[i - 1].insn_off,
+			  "linfo[%u].insn_off:%u <= linfo[%u].insn_off:%u",
+			  i, linfo[i].insn_off,
+			  i - 1, linfo[i - 1].insn_off)) {
+			err = -1;
+			goto done;
+		}
+		if (CHECK(linfo[i].file_name_off != expected_linfo->file_name_off ||
+			  linfo[i].line_off != expected_linfo->line_off ||
+			  linfo[i].line_col != expected_linfo->line_col,
+			  "linfo[%u] (%u, %u, %u) != (%u, %u, %u)", i,
+			  linfo[i].file_name_off,
+			  linfo[i].line_off,
+			  linfo[i].line_col,
+			  expected_linfo->file_name_off,
+			  expected_linfo->line_off,
+			  expected_linfo->line_col)) {
+			err = -1;
+			goto done;
+		}
+	}
+
+	if (!jited_cnt) {
+		fprintf(stderr, "not jited. skipping jited_line_info check. ");
+		err = 0;
+		goto done;
+	}
+
+	if (CHECK(jited_linfo[0] != jited_ksyms[0],
+		  "jited_linfo[0]:%lx != jited_ksyms[0]:%lx",
+		  (long)(jited_linfo[0]), (long)(jited_ksyms[0]))) {
+		err = -1;
+		goto done;
+	}
+
+	ksyms_found = 1;
+	cur_func_len = jited_func_lens[0];
+	cur_func_ksyms = jited_ksyms[0];
+	for (i = 1; i < jited_cnt; i++) {
+		if (ksyms_found < nr_jited_ksyms &&
+		    jited_linfo[i] == jited_ksyms[ksyms_found]) {
+			cur_func_ksyms = jited_ksyms[ksyms_found];
+			cur_func_len = jited_ksyms[ksyms_found];
+			ksyms_found++;
+			continue;
+		}
+
+		if (CHECK(jited_linfo[i] <= jited_linfo[i - 1],
+			  "jited_linfo[%u]:%lx <= jited_linfo[%u]:%lx",
+			  i, (long)jited_linfo[i],
+			  i - 1, (long)(jited_linfo[i - 1]))) {
+			err = -1;
+			goto done;
+		}
+
+		if (CHECK(jited_linfo[i] - cur_func_ksyms > cur_func_len,
+			  "jited_linfo[%u]:%lx - %lx > %u",
+			  i, (long)jited_linfo[i], (long)cur_func_ksyms,
+			  cur_func_len)) {
+			err = -1;
+			goto done;
+		}
+	}
+
+	if (CHECK(ksyms_found != nr_jited_ksyms,
+		  "ksyms_found:%u != nr_jited_ksyms:%u",
+		  ksyms_found, nr_jited_ksyms)) {
+		err = -1;
+		goto done;
+	}
+
+	err = 0;
+
+done:
+	free(linfo);
+	free(jited_linfo);
+	free(jited_ksyms);
+	free(jited_func_lens);
+	return err;
+}
+
 static int do_test_info_raw(unsigned int test_num)
 {
 	const struct prog_info_raw_test *test = &info_raw_tests[test_num - 1];
+	unsigned int raw_btf_size, linfo_str_off, linfo_size;
 	int btf_fd = -1, prog_fd = -1, err = 0;
-	unsigned int raw_btf_size;
+	void *raw_btf, *patched_linfo = NULL;
+	const char *ret_next_str;
 	union bpf_attr attr = {};
-	void *raw_btf;
 
 	fprintf(stderr, "BTF prog info raw test[%u] (%s): ", test_num, test->descr);
 	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
 				 test->str_sec, test->str_sec_size,
-				 &raw_btf_size);
+				 &raw_btf_size, &ret_next_str);
 
 	if (!raw_btf)
 		return -1;
@@ -3314,6 +3853,16 @@ static int do_test_info_raw(unsigned int test_num)
 		fprintf(stderr, "\n%s", btf_log_buf);
 	*btf_log_buf = '\0';
 
+	linfo_str_off = ret_next_str - test->str_sec;
+	patched_linfo = patch_name_tbd(test->line_info,
+				       test->str_sec, linfo_str_off,
+				       test->str_sec_size, &linfo_size);
+	if (IS_ERR(patched_linfo)) {
+		fprintf(stderr, "error in creating raw bpf_line_info");
+		err = -1;
+		goto done;
+	}
+
 	attr.prog_type = test->prog_type;
 	attr.insns = ptr_to_u64(test->insns);
 	attr.insn_cnt = probe_prog_length(test->insns);
@@ -3325,11 +3874,18 @@ static int do_test_info_raw(unsigned int test_num)
 	attr.log_buf = ptr_to_u64(btf_log_buf);
 	attr.log_size = BTF_LOG_BUF_SIZE;
 	attr.log_level = 1;
+	if (linfo_size) {
+		attr.line_info_rec_size = test->line_info_rec_size;
+		attr.line_info = ptr_to_u64(patched_linfo);
+		attr.line_info_cnt = linfo_size / attr.line_info_rec_size;
+	}
 
 	prog_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
 	err = ((prog_fd == -1) != test->expected_prog_load_failure);
 	if (CHECK(err, "prog_fd:%d expected_prog_load_failure:%u errno:%d",
-		  prog_fd, test->expected_prog_load_failure, errno)) {
+		  prog_fd, test->expected_prog_load_failure, errno) ||
+	    CHECK(test->err_str && !strstr(btf_log_buf, test->err_str),
+		  "expected err_str:%s", test->err_str)) {
 		err = -1;
 		goto done;
 	}
@@ -3341,6 +3897,10 @@ static int do_test_info_raw(unsigned int test_num)
 	if (err)
 		goto done;
 
+	err = test_get_linfo(test, patched_linfo, attr.line_info_cnt, prog_fd);
+	if (err)
+		goto done;
+
 done:
 	if (!err)
 		fprintf(stderr, "OK");
@@ -3353,6 +3913,9 @@ done:
 	if (prog_fd != -1)
 		close(prog_fd);
 
+	if (!IS_ERR(patched_linfo))
+		free(patched_linfo);
+
 	return err;
 }
 
-- 
cgit v1.2.3


From f0187f0b17fad7439f510eff4d65606c9ea1190f Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 7 Dec 2018 16:42:29 -0800
Subject: bpf: libbpf: Refactor and bug fix on the bpf_func_info loading logic

This patch refactor and fix a bug in the libbpf's bpf_func_info loading
logic.  The bug fix and refactoring are targeting the same
commit 2993e0515bb4 ("tools/bpf: add support to read .BTF.ext sections")
which is in the bpf-next branch.

1) In bpf_load_program_xattr(), it should retry when errno == E2BIG
   regardless of log_buf and log_buf_sz.  This patch fixes it.

2) btf_ext__reloc_init() and btf_ext__reloc() are essentially
   the same except btf_ext__reloc_init() always has insns_cnt == 0.
   Hence, btf_ext__reloc_init() is removed.

   btf_ext__reloc() is also renamed to btf_ext__reloc_func_info()
   to get ready for the line_info support in the next patch.

3) Consolidate func_info section logic from "btf_ext_parse_hdr()",
   "btf_ext_validate_func_info()" and "btf_ext__new()" to
   a new function "btf_ext_copy_func_info()" such that similar
   logic can be reused by the later libbpf's line_info patch.

4) The next line_info patch will store line_info_cnt instead of
   line_info_len in the bpf_program because the kernel is taking
   line_info_cnt also.  It will save a few "len" to "cnt" conversions
   and will also save some function args.

   Hence, this patch also makes bpf_program to store func_info_cnt
   instead of func_info_len.

5) btf_ext depends on btf.  e.g. the func_info's type_id
   in ".BTF.ext" is not useful when ".BTF" is absent.
   This patch only init the obj->btf_ext pointer after
   it has successfully init the obj->btf pointer.

   This can avoid always checking "obj->btf && obj->btf_ext"
   together for accessing ".BTF.ext".  Checking "obj->btf_ext"
   alone will do.

6) Move "struct btf_sec_func_info" from btf.h to btf.c.
   There is no external usage outside btf.c.

Fixes: 2993e0515bb4 ("tools/bpf: add support to read .BTF.ext sections")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    |   7 +-
 tools/lib/bpf/btf.c    | 191 +++++++++++++++++++------------------------------
 tools/lib/bpf/btf.h    |  17 ++---
 tools/lib/bpf/libbpf.c | 139 +++++++++++++++++++++++------------
 4 files changed, 177 insertions(+), 177 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5c3be06bf0dd..9fbbc0ed5952 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -205,7 +205,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	       min(name_len, BPF_OBJ_NAME_LEN - 1));
 
 	fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
-	if (fd >= 0 || !log_buf || !log_buf_sz)
+	if (fd >= 0)
 		return fd;
 
 	/* After bpf_prog_load, the kernel may modify certain attributes
@@ -244,10 +244,13 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 
 		fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 
-		if (fd >= 0 || !log_buf || !log_buf_sz)
+		if (fd >= 0)
 			goto done;
 	}
 
+	if (!log_buf || !log_buf_sz)
+		goto done;
+
 	/* Try again with log */
 	attr.log_buf = ptr_to_u64(log_buf);
 	attr.log_size = log_buf_sz;
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 85d6446cf832..aa4fa02b13fc 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -43,6 +43,13 @@ struct btf_ext {
 	__u32 func_info_len;
 };
 
+struct btf_sec_func_info {
+	__u32	sec_name_off;
+	__u32	num_func_info;
+	/* Followed by num_func_info number of bpf func_info records */
+	__u8	data[0];
+};
+
 /* The minimum bpf_func_info checked by the loader */
 struct bpf_func_info_min {
 	__u32   insn_off;
@@ -479,41 +486,66 @@ exit_free:
 	return err;
 }
 
-static int btf_ext_validate_func_info(const void *finfo, __u32 size,
-				      btf_print_fn_t err_log)
+static int btf_ext_copy_func_info(struct btf_ext *btf_ext,
+				  __u8 *data, __u32 data_size,
+				  btf_print_fn_t err_log)
 {
-	int sec_hdrlen = sizeof(struct btf_sec_func_info);
-	__u32 size_left, num_records, record_size;
+	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
 	const struct btf_sec_func_info *sinfo;
-	__u64 total_record_size;
+	__u32 info_left, record_size;
+	/* The start of the info sec (including the __u32 record_size). */
+	const void *info;
+
+	/* data and data_size do not include btf_ext_header from now on */
+	data = data + hdr->hdr_len;
+	data_size -= hdr->hdr_len;
+
+	if (hdr->func_info_off & 0x03) {
+		elog("BTF.ext func_info section is not aligned to 4 bytes\n");
+		return -EINVAL;
+	}
+
+	if (data_size < hdr->func_info_off ||
+	    hdr->func_info_len > data_size - hdr->func_info_off) {
+		elog("func_info section (off:%u len:%u) is beyond the end of the ELF section .BTF.ext\n",
+		     hdr->func_info_off, hdr->func_info_len);
+		return -EINVAL;
+	}
+
+	info = data + hdr->func_info_off;
+	info_left = hdr->func_info_len;
 
 	/* At least a func_info record size */
-	if (size < sizeof(__u32)) {
+	if (info_left < sizeof(__u32)) {
 		elog("BTF.ext func_info record size not found");
 		return -EINVAL;
 	}
 
-	/* The record size needs to meet below minimum standard */
-	record_size = *(__u32 *)finfo;
+	/* The record size needs to meet the minimum standard */
+	record_size = *(__u32 *)info;
 	if (record_size < sizeof(struct bpf_func_info_min) ||
-	    record_size % sizeof(__u32)) {
+	    record_size & 0x03) {
 		elog("BTF.ext func_info invalid record size");
 		return -EINVAL;
 	}
 
-	sinfo = finfo + sizeof(__u32);
-	size_left = size - sizeof(__u32);
+	sinfo = info + sizeof(__u32);
+	info_left -= sizeof(__u32);
 
 	/* If no func_info records, return failure now so .BTF.ext
 	 * won't be used.
 	 */
-	if (!size_left) {
+	if (!info_left) {
 		elog("BTF.ext no func info records");
 		return -EINVAL;
 	}
 
-	while (size_left) {
-		if (size_left < sec_hdrlen) {
+	while (info_left) {
+		unsigned int sec_hdrlen = sizeof(struct btf_sec_func_info);
+		__u64 total_record_size;
+		__u32 num_records;
+
+		if (info_left < sec_hdrlen) {
 			elog("BTF.ext func_info header not found");
 			return -EINVAL;
 		}
@@ -526,15 +558,23 @@ static int btf_ext_validate_func_info(const void *finfo, __u32 size,
 
 		total_record_size = sec_hdrlen +
 				    (__u64)num_records * record_size;
-		if (size_left < total_record_size) {
+		if (info_left < total_record_size) {
 			elog("incorrect BTF.ext num_func_info");
 			return -EINVAL;
 		}
 
-		size_left -= total_record_size;
+		info_left -= total_record_size;
 		sinfo = (void *)sinfo + total_record_size;
 	}
 
+	btf_ext->func_info_len = hdr->func_info_len - sizeof(__u32);
+	btf_ext->func_info_rec_size = record_size;
+	btf_ext->func_info = malloc(btf_ext->func_info_len);
+	if (!btf_ext->func_info)
+		return -ENOMEM;
+	memcpy(btf_ext->func_info, info + sizeof(__u32),
+	       btf_ext->func_info_len);
+
 	return 0;
 }
 
@@ -542,8 +582,6 @@ static int btf_ext_parse_hdr(__u8 *data, __u32 data_size,
 			     btf_print_fn_t err_log)
 {
 	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
-	__u32 meta_left, last_func_info_pos;
-	void *finfo;
 
 	if (data_size < offsetof(struct btf_ext_header, func_info_off) ||
 	    data_size < hdr->hdr_len) {
@@ -566,34 +604,12 @@ static int btf_ext_parse_hdr(__u8 *data, __u32 data_size,
 		return -ENOTSUP;
 	}
 
-	meta_left = data_size - hdr->hdr_len;
-	if (!meta_left) {
+	if (data_size == hdr->hdr_len) {
 		elog("BTF.ext has no data\n");
 		return -EINVAL;
 	}
 
-	if (meta_left < hdr->func_info_off) {
-		elog("Invalid BTF.ext func_info section offset:%u\n",
-		     hdr->func_info_off);
-		return -EINVAL;
-	}
-
-	if (hdr->func_info_off & 0x03) {
-		elog("BTF.ext func_info section is not aligned to 4 bytes\n");
-		return -EINVAL;
-	}
-
-	last_func_info_pos = hdr->hdr_len + hdr->func_info_off +
-			     hdr->func_info_len;
-	if (last_func_info_pos > data_size) {
-		elog("Invalid BTF.ext func_info section size:%u\n",
-		     hdr->func_info_len);
-		return -EINVAL;
-	}
-
-	finfo = data + hdr->hdr_len + hdr->func_info_off;
-	return btf_ext_validate_func_info(finfo, hdr->func_info_len,
-					  err_log);
+	return 0;
 }
 
 void btf_ext__free(struct btf_ext *btf_ext)
@@ -607,10 +623,7 @@ void btf_ext__free(struct btf_ext *btf_ext)
 
 struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
 {
-	const struct btf_ext_header *hdr;
 	struct btf_ext *btf_ext;
-	void *org_fdata, *fdata;
-	__u32 hdrlen, size_u32;
 	int err;
 
 	err = btf_ext_parse_hdr(data, size, err_log);
@@ -621,81 +634,18 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
 	if (!btf_ext)
 		return ERR_PTR(-ENOMEM);
 
-	hdr = (const struct btf_ext_header *)data;
-	hdrlen = hdr->hdr_len;
-	size_u32 = sizeof(__u32);
-	fdata = malloc(hdr->func_info_len - size_u32);
-	if (!fdata) {
-		free(btf_ext);
-		return ERR_PTR(-ENOMEM);
+	err = btf_ext_copy_func_info(btf_ext, data, size, err_log);
+	if (err) {
+		btf_ext__free(btf_ext);
+		return ERR_PTR(err);
 	}
 
-	/* remember record size and copy rest of func_info data */
-	org_fdata = data + hdrlen + hdr->func_info_off;
-	btf_ext->func_info_rec_size = *(__u32 *)org_fdata;
-	memcpy(fdata, org_fdata + size_u32, hdr->func_info_len - size_u32);
-	btf_ext->func_info = fdata;
-	btf_ext->func_info_len = hdr->func_info_len - size_u32;
-
 	return btf_ext;
 }
 
-int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext,
-			const char *sec_name, void **func_info,
-			__u32 *func_info_rec_size, __u32 *func_info_len)
-{
-	__u32 sec_hdrlen = sizeof(struct btf_sec_func_info);
-	__u32 i, record_size, records_len;
-	struct btf_sec_func_info *sinfo;
-	const char *info_sec_name;
-	__s64 remain_len;
-	void *data;
-
-	record_size = btf_ext->func_info_rec_size;
-	sinfo = btf_ext->func_info;
-	remain_len = btf_ext->func_info_len;
-
-	while (remain_len > 0) {
-		records_len = sinfo->num_func_info * record_size;
-		info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off);
-		if (strcmp(info_sec_name, sec_name)) {
-			remain_len -= sec_hdrlen + records_len;
-			sinfo = (void *)sinfo + sec_hdrlen + records_len;
-			continue;
-		}
-
-		data = malloc(records_len);
-		if (!data)
-			return -ENOMEM;
-
-		memcpy(data, sinfo->data, records_len);
-
-		/* adjust the insn_off, the data in .BTF.ext is
-		 * the actual byte offset, and the kernel expects
-		 * the offset in term of bpf_insn.
-		 *
-		 * adjust the insn offset only, the rest data will
-		 * be passed to kernel.
-		 */
-		for (i = 0; i < sinfo->num_func_info; i++) {
-			struct bpf_func_info_min *record;
-
-			record = data + i * record_size;
-			record->insn_off /= sizeof(struct bpf_insn);
-		}
-
-		*func_info = data;
-		*func_info_len = records_len;
-		*func_info_rec_size = record_size;
-		return 0;
-	}
-
-	return -EINVAL;
-}
-
-int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
-		   const char *sec_name, __u32 insns_cnt,
-		   void **func_info, __u32 *func_info_len)
+int btf_ext__reloc_func_info(struct btf *btf, struct btf_ext *btf_ext,
+			     const char *sec_name, __u32 insns_cnt,
+			     void **func_info, __u32 *cnt)
 {
 	__u32 sec_hdrlen = sizeof(struct btf_sec_func_info);
 	__u32 i, record_size, existing_flen, records_len;
@@ -716,7 +666,7 @@ int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
 			continue;
 		}
 
-		existing_flen = *func_info_len;
+		existing_flen = (*cnt) * record_size;
 		data = realloc(*func_info, existing_flen + records_len);
 		if (!data)
 			return -ENOMEM;
@@ -734,9 +684,14 @@ int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
 				insns_cnt;
 		}
 		*func_info = data;
-		*func_info_len = existing_flen + records_len;
+		*cnt += sinfo->num_func_info;
 		return 0;
 	}
 
-	return -EINVAL;
+	return -ENOENT;
+}
+
+__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext)
+{
+	return btf_ext->func_info_rec_size;
 }
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 5336b2f37293..936177a538cd 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -53,13 +53,6 @@ struct btf_ext_header {
 	__u32	func_info_len;
 };
 
-struct btf_sec_func_info {
-	__u32	sec_name_off;
-	__u32	num_func_info;
-	/* Followed by num_func_info number of bpf func_info records */
-	__u8	data[0];
-};
-
 typedef int (*btf_print_fn_t)(const char *, ...)
 	__attribute__((format(printf, 1, 2)));
 
@@ -77,12 +70,10 @@ LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
 
 struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
 void btf_ext__free(struct btf_ext *btf_ext);
-int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext,
-			const char *sec_name, void **func_info,
-			__u32 *func_info_rec_size, __u32 *func_info_len);
-int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
-		   const char *sec_name, __u32 insns_cnt, void **func_info,
-		   __u32 *func_info_len);
+int btf_ext__reloc_func_info(struct btf *btf, struct btf_ext *btf_ext,
+			     const char *sec_name, __u32 insns_cnt,
+			     void **func_info, __u32 *func_info_len);
+__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
 
 #ifdef __cplusplus
 } /* extern "C" */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 59b748ebd15f..4ea3368bf803 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -167,7 +167,7 @@ struct bpf_program {
 	int btf_fd;
 	void *func_info;
 	__u32 func_info_rec_size;
-	__u32 func_info_len;
+	__u32 func_info_cnt;
 
 	struct bpf_capabilities *caps;
 };
@@ -779,6 +779,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 {
 	Elf *elf = obj->efile.elf;
 	GElf_Ehdr *ep = &obj->efile.ehdr;
+	Elf_Data *btf_ext_data = NULL;
 	Elf_Scn *scn = NULL;
 	int idx = 0, err = 0;
 
@@ -841,14 +842,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 				obj->btf = NULL;
 			}
 		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
-			obj->btf_ext = btf_ext__new(data->d_buf, data->d_size,
-						    __pr_debug);
-			if (IS_ERR(obj->btf_ext)) {
-				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
-					   BTF_EXT_ELF_SEC,
-					   PTR_ERR(obj->btf_ext));
-				obj->btf_ext = NULL;
-			}
+			btf_ext_data = data;
 		} else if (sh.sh_type == SHT_SYMTAB) {
 			if (obj->efile.symbols) {
 				pr_warning("bpf: multiple SYMTAB in %s\n",
@@ -910,6 +904,22 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 		pr_warning("Corrupted ELF file: index of strtab invalid\n");
 		return LIBBPF_ERRNO__FORMAT;
 	}
+	if (btf_ext_data) {
+		if (!obj->btf) {
+			pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n",
+				 BTF_EXT_ELF_SEC, BTF_ELF_SEC);
+		} else {
+			obj->btf_ext = btf_ext__new(btf_ext_data->d_buf,
+						    btf_ext_data->d_size,
+						    __pr_debug);
+			if (IS_ERR(obj->btf_ext)) {
+				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
+					   BTF_EXT_ELF_SEC,
+					   PTR_ERR(obj->btf_ext));
+				obj->btf_ext = NULL;
+			}
+		}
+	}
 	if (obj->efile.maps_shndx >= 0) {
 		err = bpf_object__init_maps(obj, flags);
 		if (err)
@@ -1275,6 +1285,69 @@ bpf_object__create_maps(struct bpf_object *obj)
 	return 0;
 }
 
+static int
+check_btf_ext_reloc_err(struct bpf_program *prog, int err,
+			void *btf_prog_info, const char *info_name)
+{
+	if (err != -ENOENT) {
+		pr_warning("Error in loading %s for sec %s.\n",
+			   info_name, prog->section_name);
+		return err;
+	}
+
+	/* err == -ENOENT (i.e. prog->section_name not found in btf_ext) */
+
+	if (btf_prog_info) {
+		/*
+		 * Some info has already been found but has problem
+		 * in the last btf_ext reloc.  Must have to error
+		 * out.
+		 */
+		pr_warning("Error in relocating %s for sec %s.\n",
+			   info_name, prog->section_name);
+		return err;
+	}
+
+	/*
+	 * Have problem loading the very first info.  Ignore
+	 * the rest.
+	 */
+	pr_warning("Cannot find %s for main program sec %s. Ignore all %s.\n",
+		   info_name, prog->section_name, info_name);
+	return 0;
+}
+
+static int
+bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj,
+			  const char *section_name,  __u32 insn_offset)
+{
+	int err;
+
+	if (!insn_offset || prog->func_info) {
+		/*
+		 * !insn_offset => main program
+		 *
+		 * For sub prog, the main program's func_info has to
+		 * be loaded first (i.e. prog->func_info != NULL)
+		 */
+		err = btf_ext__reloc_func_info(obj->btf, obj->btf_ext,
+					       section_name, insn_offset,
+					       &prog->func_info,
+					       &prog->func_info_cnt);
+		if (err)
+			return check_btf_ext_reloc_err(prog, err,
+						       prog->func_info,
+						       "bpf_func_info");
+
+		prog->func_info_rec_size = btf_ext__func_info_rec_size(obj->btf_ext);
+	}
+
+	if (!insn_offset)
+		prog->btf_fd = btf__fd(obj->btf);
+
+	return 0;
+}
+
 static int
 bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			struct reloc_desc *relo)
@@ -1306,17 +1379,12 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			return -ENOMEM;
 		}
 
-		if (obj->btf && obj->btf_ext) {
-			err = btf_ext__reloc(obj->btf, obj->btf_ext,
-					     text->section_name,
-					     prog->insns_cnt,
-					     &prog->func_info,
-					     &prog->func_info_len);
-			if (err) {
-				pr_warning("error in btf_ext__reloc for sec %s\n",
-					   text->section_name);
+		if (obj->btf_ext) {
+			err = bpf_program_reloc_btf_ext(prog, obj,
+							text->section_name,
+							prog->insns_cnt);
+			if (err)
 				return err;
-			}
 		}
 
 		memcpy(new_insn + prog->insns_cnt, text->insns,
@@ -1341,18 +1409,11 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 	if (!prog)
 		return 0;
 
-	if (obj->btf && obj->btf_ext) {
-		err = btf_ext__reloc_init(obj->btf, obj->btf_ext,
-					  prog->section_name,
-					  &prog->func_info,
-					  &prog->func_info_rec_size,
-					  &prog->func_info_len);
-		if (err) {
-			pr_warning("err in btf_ext__reloc_init for sec %s\n",
-				   prog->section_name);
+	if (obj->btf_ext) {
+		err = bpf_program_reloc_btf_ext(prog, obj,
+						prog->section_name, 0);
+		if (err)
 			return err;
-		}
-		prog->btf_fd = btf__fd(obj->btf);
 	}
 
 	if (!prog->reloc_desc)
@@ -1444,8 +1505,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 
 static int
 load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
-	     char *license, __u32 kern_version, int *pfd,
-	     __u32 func_info_cnt)
+	     char *license, __u32 kern_version, int *pfd)
 {
 	struct bpf_load_program_attr load_attr;
 	char *cp, errmsg[STRERR_BUFSIZE];
@@ -1465,8 +1525,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
 	load_attr.func_info = prog->func_info;
 	load_attr.func_info_rec_size = prog->func_info_rec_size;
-	load_attr.func_info_cnt = func_info_cnt;
-
+	load_attr.func_info_cnt = prog->func_info_cnt;
 	if (!load_attr.insns || !load_attr.insns_cnt)
 		return -EINVAL;
 
@@ -1523,14 +1582,8 @@ int
 bpf_program__load(struct bpf_program *prog,
 		  char *license, __u32 kern_version)
 {
-	__u32 func_info_cnt;
 	int err = 0, fd, i;
 
-	if (prog->func_info_len == 0)
-		func_info_cnt = 0;
-	else
-		func_info_cnt = prog->func_info_len / prog->func_info_rec_size;
-
 	if (prog->instances.nr < 0 || !prog->instances.fds) {
 		if (prog->preprocessor) {
 			pr_warning("Internal error: can't load program '%s'\n",
@@ -1553,8 +1606,7 @@ bpf_program__load(struct bpf_program *prog,
 				   prog->section_name, prog->instances.nr);
 		}
 		err = load_program(prog, prog->insns, prog->insns_cnt,
-				   license, kern_version, &fd,
-				   func_info_cnt);
+				   license, kern_version, &fd);
 		if (!err)
 			prog->instances.fds[0] = fd;
 		goto out;
@@ -1584,8 +1636,7 @@ bpf_program__load(struct bpf_program *prog,
 
 		err = load_program(prog, result.new_insn_ptr,
 				   result.new_insn_cnt,
-				   license, kern_version, &fd,
-				   func_info_cnt);
+				   license, kern_version, &fd);
 
 		if (err) {
 			pr_warning("Loading the %dth instance of program '%s' failed\n",
-- 
cgit v1.2.3


From 3d65014146c69bbc4d2947f60dbd722d352cdc46 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 7 Dec 2018 16:42:31 -0800
Subject: bpf: libbpf: Add btf_line_info support to libbpf

This patch adds bpf_line_info support to libbpf:
1) Parsing the line_info sec from ".BTF.ext"
2) Relocating the line_info.  If the main prog *_info relocation
   fails, it will ignore the remaining subprog line_info and continue.
   If the subprog *_info relocation fails, it will bail out.
3) BPF_PROG_LOAD a prog with line_info

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    |  86 +++++++++++++-------
 tools/lib/bpf/bpf.h    |   3 +
 tools/lib/bpf/btf.c    | 209 +++++++++++++++++++++++++++++++++++--------------
 tools/lib/bpf/btf.h    |  10 ++-
 tools/lib/bpf/libbpf.c |  20 +++++
 5 files changed, 239 insertions(+), 89 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9fbbc0ed5952..3caaa3428774 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -173,11 +173,36 @@ int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
 					  -1);
 }
 
+static void *
+alloc_zero_tailing_info(const void *orecord, __u32 cnt,
+			__u32 actual_rec_size, __u32 expected_rec_size)
+{
+	__u64 info_len = actual_rec_size * cnt;
+	void *info, *nrecord;
+	int i;
+
+	info = malloc(info_len);
+	if (!info)
+		return NULL;
+
+	/* zero out bytes kernel does not understand */
+	nrecord = info;
+	for (i = 0; i < cnt; i++) {
+		memcpy(nrecord, orecord, expected_rec_size);
+		memset(nrecord + expected_rec_size, 0,
+		       actual_rec_size - expected_rec_size);
+		orecord += actual_rec_size;
+		nrecord += actual_rec_size;
+	}
+
+	return info;
+}
+
 int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 			   char *log_buf, size_t log_buf_sz)
 {
+	void *finfo = NULL, *linfo = NULL;
 	union bpf_attr attr;
-	void *finfo = NULL;
 	__u32 name_len;
 	int fd;
 
@@ -201,6 +226,9 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	attr.func_info_rec_size = load_attr->func_info_rec_size;
 	attr.func_info_cnt = load_attr->func_info_cnt;
 	attr.func_info = ptr_to_u64(load_attr->func_info);
+	attr.line_info_rec_size = load_attr->line_info_rec_size;
+	attr.line_info_cnt = load_attr->line_info_cnt;
+	attr.line_info = ptr_to_u64(load_attr->line_info);
 	memcpy(attr.prog_name, load_attr->name,
 	       min(name_len, BPF_OBJ_NAME_LEN - 1));
 
@@ -212,36 +240,35 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	 * to give user space a hint how to deal with loading failure.
 	 * Check to see whether we can make some changes and load again.
 	 */
-	if (errno == E2BIG && attr.func_info_cnt &&
-	    attr.func_info_rec_size < load_attr->func_info_rec_size) {
-		__u32 actual_rec_size = load_attr->func_info_rec_size;
-		__u32 expected_rec_size = attr.func_info_rec_size;
-		__u32 finfo_cnt = load_attr->func_info_cnt;
-		__u64 finfo_len = actual_rec_size * finfo_cnt;
-		const void *orecord;
-		void *nrecord;
-		int i;
-
-		finfo = malloc(finfo_len);
-		if (!finfo)
-			/* further try with log buffer won't help */
-			return fd;
-
-		/* zero out bytes kernel does not understand */
-		orecord = load_attr->func_info;
-		nrecord = finfo;
-		for (i = 0; i < load_attr->func_info_cnt; i++) {
-			memcpy(nrecord, orecord, expected_rec_size);
-			memset(nrecord + expected_rec_size, 0,
-			       actual_rec_size - expected_rec_size);
-			orecord += actual_rec_size;
-			nrecord += actual_rec_size;
+	while (errno == E2BIG && (!finfo || !linfo)) {
+		if (!finfo && attr.func_info_cnt &&
+		    attr.func_info_rec_size < load_attr->func_info_rec_size) {
+			/* try with corrected func info records */
+			finfo = alloc_zero_tailing_info(load_attr->func_info,
+							load_attr->func_info_cnt,
+							load_attr->func_info_rec_size,
+							attr.func_info_rec_size);
+			if (!finfo)
+				goto done;
+
+			attr.func_info = ptr_to_u64(finfo);
+			attr.func_info_rec_size = load_attr->func_info_rec_size;
+		} else if (!linfo && attr.line_info_cnt &&
+			   attr.line_info_rec_size <
+			   load_attr->line_info_rec_size) {
+			linfo = alloc_zero_tailing_info(load_attr->line_info,
+							load_attr->line_info_cnt,
+							load_attr->line_info_rec_size,
+							attr.line_info_rec_size);
+			if (!linfo)
+				goto done;
+
+			attr.line_info = ptr_to_u64(linfo);
+			attr.line_info_rec_size = load_attr->line_info_rec_size;
+		} else {
+			break;
 		}
 
-		/* try with corrected func info records */
-		attr.func_info = ptr_to_u64(finfo);
-		attr.func_info_rec_size = load_attr->func_info_rec_size;
-
 		fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 
 		if (fd >= 0)
@@ -259,6 +286,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 done:
 	free(finfo);
+	free(linfo);
 	return fd;
 }
 
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 098e6f793b76..8f09de482839 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -82,6 +82,9 @@ struct bpf_load_program_attr {
 	__u32 func_info_rec_size;
 	const void *func_info;
 	__u32 func_info_cnt;
+	__u32 line_info_rec_size;
+	const void *line_info;
+	__u32 line_info_cnt;
 };
 
 /* Flags to direct loading requirements */
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index aa4fa02b13fc..d682d3b8f7b9 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -37,16 +37,26 @@ struct btf {
 	int fd;
 };
 
+struct btf_ext_info {
+	/*
+	 * info points to a deep copy of the individual info section
+	 * (e.g. func_info and line_info) from the .BTF.ext.
+	 * It does not include the __u32 rec_size.
+	 */
+	void *info;
+	__u32 rec_size;
+	__u32 len;
+};
+
 struct btf_ext {
-	void *func_info;
-	__u32 func_info_rec_size;
-	__u32 func_info_len;
+	struct btf_ext_info func_info;
+	struct btf_ext_info line_info;
 };
 
-struct btf_sec_func_info {
+struct btf_ext_info_sec {
 	__u32	sec_name_off;
-	__u32	num_func_info;
-	/* Followed by num_func_info number of bpf func_info records */
+	__u32	num_info;
+	/* Followed by num_info * record_size number of bytes */
 	__u8	data[0];
 };
 
@@ -56,6 +66,14 @@ struct bpf_func_info_min {
 	__u32   type_id;
 };
 
+/* The minimum bpf_line_info checked by the loader */
+struct bpf_line_info_min {
+	__u32	insn_off;
+	__u32	file_name_off;
+	__u32	line_off;
+	__u32	line_col;
+};
+
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -486,12 +504,22 @@ exit_free:
 	return err;
 }
 
-static int btf_ext_copy_func_info(struct btf_ext *btf_ext,
-				  __u8 *data, __u32 data_size,
-				  btf_print_fn_t err_log)
+struct btf_ext_sec_copy_param {
+	__u32 off;
+	__u32 len;
+	__u32 min_rec_size;
+	struct btf_ext_info *ext_info;
+	const char *desc;
+};
+
+static int btf_ext_copy_info(struct btf_ext *btf_ext,
+			     __u8 *data, __u32 data_size,
+			     struct btf_ext_sec_copy_param *ext_sec,
+			     btf_print_fn_t err_log)
 {
 	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
-	const struct btf_sec_func_info *sinfo;
+	const struct btf_ext_info_sec *sinfo;
+	struct btf_ext_info *ext_info;
 	__u32 info_left, record_size;
 	/* The start of the info sec (including the __u32 record_size). */
 	const void *info;
@@ -500,66 +528,69 @@ static int btf_ext_copy_func_info(struct btf_ext *btf_ext,
 	data = data + hdr->hdr_len;
 	data_size -= hdr->hdr_len;
 
-	if (hdr->func_info_off & 0x03) {
-		elog("BTF.ext func_info section is not aligned to 4 bytes\n");
+	if (ext_sec->off & 0x03) {
+		elog(".BTF.ext %s section is not aligned to 4 bytes\n",
+		     ext_sec->desc);
 		return -EINVAL;
 	}
 
-	if (data_size < hdr->func_info_off ||
-	    hdr->func_info_len > data_size - hdr->func_info_off) {
-		elog("func_info section (off:%u len:%u) is beyond the end of the ELF section .BTF.ext\n",
-		     hdr->func_info_off, hdr->func_info_len);
+	if (data_size < ext_sec->off ||
+	    ext_sec->len > data_size - ext_sec->off) {
+		elog("%s section (off:%u len:%u) is beyond the end of the ELF section .BTF.ext\n",
+		     ext_sec->desc, ext_sec->off, ext_sec->len);
 		return -EINVAL;
 	}
 
-	info = data + hdr->func_info_off;
-	info_left = hdr->func_info_len;
+	info = data + ext_sec->off;
+	info_left = ext_sec->len;
 
-	/* At least a func_info record size */
+	/* At least a record size */
 	if (info_left < sizeof(__u32)) {
-		elog("BTF.ext func_info record size not found");
+		elog(".BTF.ext %s record size not found\n", ext_sec->desc);
 		return -EINVAL;
 	}
 
 	/* The record size needs to meet the minimum standard */
 	record_size = *(__u32 *)info;
-	if (record_size < sizeof(struct bpf_func_info_min) ||
+	if (record_size < ext_sec->min_rec_size ||
 	    record_size & 0x03) {
-		elog("BTF.ext func_info invalid record size");
+		elog("%s section in .BTF.ext has invalid record size %u\n",
+		     ext_sec->desc, record_size);
 		return -EINVAL;
 	}
 
 	sinfo = info + sizeof(__u32);
 	info_left -= sizeof(__u32);
 
-	/* If no func_info records, return failure now so .BTF.ext
-	 * won't be used.
-	 */
+	/* If no records, return failure now so .BTF.ext won't be used. */
 	if (!info_left) {
-		elog("BTF.ext no func info records");
+		elog("%s section in .BTF.ext has no records", ext_sec->desc);
 		return -EINVAL;
 	}
 
 	while (info_left) {
-		unsigned int sec_hdrlen = sizeof(struct btf_sec_func_info);
+		unsigned int sec_hdrlen = sizeof(struct btf_ext_info_sec);
 		__u64 total_record_size;
 		__u32 num_records;
 
 		if (info_left < sec_hdrlen) {
-			elog("BTF.ext func_info header not found");
+			elog("%s section header is not found in .BTF.ext\n",
+			     ext_sec->desc);
 			return -EINVAL;
 		}
 
-		num_records = sinfo->num_func_info;
+		num_records = sinfo->num_info;
 		if (num_records == 0) {
-			elog("incorrect BTF.ext num_func_info");
+			elog("%s section has incorrect num_records in .BTF.ext\n",
+			     ext_sec->desc);
 			return -EINVAL;
 		}
 
 		total_record_size = sec_hdrlen +
 				    (__u64)num_records * record_size;
 		if (info_left < total_record_size) {
-			elog("incorrect BTF.ext num_func_info");
+			elog("%s section has incorrect num_records in .BTF.ext\n",
+			     ext_sec->desc);
 			return -EINVAL;
 		}
 
@@ -567,17 +598,49 @@ static int btf_ext_copy_func_info(struct btf_ext *btf_ext,
 		sinfo = (void *)sinfo + total_record_size;
 	}
 
-	btf_ext->func_info_len = hdr->func_info_len - sizeof(__u32);
-	btf_ext->func_info_rec_size = record_size;
-	btf_ext->func_info = malloc(btf_ext->func_info_len);
-	if (!btf_ext->func_info)
+	ext_info = ext_sec->ext_info;
+	ext_info->len = ext_sec->len - sizeof(__u32);
+	ext_info->rec_size = record_size;
+	ext_info->info = malloc(ext_info->len);
+	if (!ext_info->info)
 		return -ENOMEM;
-	memcpy(btf_ext->func_info, info + sizeof(__u32),
-	       btf_ext->func_info_len);
+	memcpy(ext_info->info, info + sizeof(__u32), ext_info->len);
 
 	return 0;
 }
 
+static int btf_ext_copy_func_info(struct btf_ext *btf_ext,
+				  __u8 *data, __u32 data_size,
+				  btf_print_fn_t err_log)
+{
+	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
+	struct btf_ext_sec_copy_param param = {
+		.off = hdr->func_info_off,
+		.len = hdr->func_info_len,
+		.min_rec_size = sizeof(struct bpf_func_info_min),
+		.ext_info = &btf_ext->func_info,
+		.desc = "func_info"
+	};
+
+	return btf_ext_copy_info(btf_ext, data, data_size, &param, err_log);
+}
+
+static int btf_ext_copy_line_info(struct btf_ext *btf_ext,
+				  __u8 *data, __u32 data_size,
+				  btf_print_fn_t err_log)
+{
+	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
+	struct btf_ext_sec_copy_param param = {
+		.off = hdr->line_info_off,
+		.len = hdr->line_info_len,
+		.min_rec_size = sizeof(struct bpf_line_info_min),
+		.ext_info = &btf_ext->line_info,
+		.desc = "line_info",
+	};
+
+	return btf_ext_copy_info(btf_ext, data, data_size, &param, err_log);
+}
+
 static int btf_ext_parse_hdr(__u8 *data, __u32 data_size,
 			     btf_print_fn_t err_log)
 {
@@ -617,7 +680,8 @@ void btf_ext__free(struct btf_ext *btf_ext)
 	if (!btf_ext)
 		return;
 
-	free(btf_ext->func_info);
+	free(btf_ext->func_info.info);
+	free(btf_ext->line_info.info);
 	free(btf_ext);
 }
 
@@ -640,25 +704,32 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
 		return ERR_PTR(err);
 	}
 
+	err = btf_ext_copy_line_info(btf_ext, data, size, err_log);
+	if (err) {
+		btf_ext__free(btf_ext);
+		return ERR_PTR(err);
+	}
+
 	return btf_ext;
 }
 
-int btf_ext__reloc_func_info(struct btf *btf, struct btf_ext *btf_ext,
-			     const char *sec_name, __u32 insns_cnt,
-			     void **func_info, __u32 *cnt)
+static int btf_ext_reloc_info(const struct btf *btf,
+			      const struct btf_ext_info *ext_info,
+			      const char *sec_name, __u32 insns_cnt,
+			      void **info, __u32 *cnt)
 {
-	__u32 sec_hdrlen = sizeof(struct btf_sec_func_info);
-	__u32 i, record_size, existing_flen, records_len;
-	struct btf_sec_func_info *sinfo;
+	__u32 sec_hdrlen = sizeof(struct btf_ext_info_sec);
+	__u32 i, record_size, existing_len, records_len;
+	struct btf_ext_info_sec *sinfo;
 	const char *info_sec_name;
 	__u64 remain_len;
 	void *data;
 
-	record_size = btf_ext->func_info_rec_size;
-	sinfo = btf_ext->func_info;
-	remain_len = btf_ext->func_info_len;
+	record_size = ext_info->rec_size;
+	sinfo = ext_info->info;
+	remain_len = ext_info->len;
 	while (remain_len > 0) {
-		records_len = sinfo->num_func_info * record_size;
+		records_len = sinfo->num_info * record_size;
 		info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off);
 		if (strcmp(info_sec_name, sec_name)) {
 			remain_len -= sec_hdrlen + records_len;
@@ -666,32 +737,52 @@ int btf_ext__reloc_func_info(struct btf *btf, struct btf_ext *btf_ext,
 			continue;
 		}
 
-		existing_flen = (*cnt) * record_size;
-		data = realloc(*func_info, existing_flen + records_len);
+		existing_len = (*cnt) * record_size;
+		data = realloc(*info, existing_len + records_len);
 		if (!data)
 			return -ENOMEM;
 
-		memcpy(data + existing_flen, sinfo->data, records_len);
+		memcpy(data + existing_len, sinfo->data, records_len);
 		/* adjust insn_off only, the rest data will be passed
 		 * to the kernel.
 		 */
-		for (i = 0; i < sinfo->num_func_info; i++) {
-			struct bpf_func_info_min *record;
+		for (i = 0; i < sinfo->num_info; i++) {
+			__u32 *insn_off;
 
-			record = data + existing_flen + i * record_size;
-			record->insn_off =
-				record->insn_off / sizeof(struct bpf_insn) +
+			insn_off = data + existing_len + (i * record_size);
+			*insn_off = *insn_off / sizeof(struct bpf_insn) +
 				insns_cnt;
 		}
-		*func_info = data;
-		*cnt += sinfo->num_func_info;
+		*info = data;
+		*cnt += sinfo->num_info;
 		return 0;
 	}
 
 	return -ENOENT;
 }
 
+int btf_ext__reloc_func_info(const struct btf *btf, const struct btf_ext *btf_ext,
+			     const char *sec_name, __u32 insns_cnt,
+			     void **func_info, __u32 *cnt)
+{
+	return btf_ext_reloc_info(btf, &btf_ext->func_info, sec_name,
+				  insns_cnt, func_info, cnt);
+}
+
+int btf_ext__reloc_line_info(const struct btf *btf, const struct btf_ext *btf_ext,
+			     const char *sec_name, __u32 insns_cnt,
+			     void **line_info, __u32 *cnt)
+{
+	return btf_ext_reloc_info(btf, &btf_ext->line_info, sec_name,
+				  insns_cnt, line_info, cnt);
+}
+
 __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext)
 {
-	return btf_ext->func_info_rec_size;
+	return btf_ext->func_info.rec_size;
+}
+
+__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext)
+{
+	return btf_ext->line_info.rec_size;
 }
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 936177a538cd..b0610dcdae6b 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -51,6 +51,8 @@ struct btf_ext_header {
 	/* All offsets are in bytes relative to the end of this header */
 	__u32	func_info_off;
 	__u32	func_info_len;
+	__u32	line_info_off;
+	__u32	line_info_len;
 };
 
 typedef int (*btf_print_fn_t)(const char *, ...)
@@ -70,10 +72,16 @@ LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
 
 struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
 void btf_ext__free(struct btf_ext *btf_ext);
-int btf_ext__reloc_func_info(struct btf *btf, struct btf_ext *btf_ext,
+int btf_ext__reloc_func_info(const struct btf *btf,
+			     const struct btf_ext *btf_ext,
 			     const char *sec_name, __u32 insns_cnt,
 			     void **func_info, __u32 *func_info_len);
+int btf_ext__reloc_line_info(const struct btf *btf,
+			     const struct btf_ext *btf_ext,
+			     const char *sec_name, __u32 insns_cnt,
+			     void **line_info, __u32 *cnt);
 __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
+__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
 
 #ifdef __cplusplus
 } /* extern "C" */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4ea3368bf803..e2bc75ee1614 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -170,6 +170,10 @@ struct bpf_program {
 	__u32 func_info_cnt;
 
 	struct bpf_capabilities *caps;
+
+	void *line_info;
+	__u32 line_info_rec_size;
+	__u32 line_info_cnt;
 };
 
 struct bpf_map {
@@ -1342,6 +1346,19 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj,
 		prog->func_info_rec_size = btf_ext__func_info_rec_size(obj->btf_ext);
 	}
 
+	if (!insn_offset || prog->line_info) {
+		err = btf_ext__reloc_line_info(obj->btf, obj->btf_ext,
+					       section_name, insn_offset,
+					       &prog->line_info,
+					       &prog->line_info_cnt);
+		if (err)
+			return check_btf_ext_reloc_err(prog, err,
+						       prog->line_info,
+						       "bpf_line_info");
+
+		prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext);
+	}
+
 	if (!insn_offset)
 		prog->btf_fd = btf__fd(obj->btf);
 
@@ -1526,6 +1543,9 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.func_info = prog->func_info;
 	load_attr.func_info_rec_size = prog->func_info_rec_size;
 	load_attr.func_info_cnt = prog->func_info_cnt;
+	load_attr.line_info = prog->line_info;
+	load_attr.line_info_rec_size = prog->line_info_rec_size;
+	load_attr.line_info_cnt = prog->line_info_cnt;
 	if (!load_attr.insns || !load_attr.insns_cnt)
 		return -EINVAL;
 
-- 
cgit v1.2.3


From b053b439b72ad152257ecc3f71cfb4c619b0137e Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 7 Dec 2018 16:42:32 -0800
Subject: bpf: libbpf: bpftool: Print bpf_line_info during prog dump

This patch adds print bpf_line_info function in 'prog dump jitted'
and 'prog dump xlated':

[root@arch-fb-vm1 bpf]# ~/devshare/fb-kernel/linux/tools/bpf/bpftool/bpftool prog dump jited pinned /sys/fs/bpf/test_btf_haskv
[...]
int test_long_fname_2(struct dummy_tracepoint_args * arg):
bpf_prog_44a040bf25481309_test_long_fname_2:
; static int test_long_fname_2(struct dummy_tracepoint_args *arg)
   0:	push   %rbp
   1:	mov    %rsp,%rbp
   4:	sub    $0x30,%rsp
   b:	sub    $0x28,%rbp
   f:	mov    %rbx,0x0(%rbp)
  13:	mov    %r13,0x8(%rbp)
  17:	mov    %r14,0x10(%rbp)
  1b:	mov    %r15,0x18(%rbp)
  1f:	xor    %eax,%eax
  21:	mov    %rax,0x20(%rbp)
  25:	xor    %esi,%esi
; int key = 0;
  27:	mov    %esi,-0x4(%rbp)
; if (!arg->sock)
  2a:	mov    0x8(%rdi),%rdi
; if (!arg->sock)
  2e:	cmp    $0x0,%rdi
  32:	je     0x0000000000000070
  34:	mov    %rbp,%rsi
; counts = bpf_map_lookup_elem(&btf_map, &key);
  37:	add    $0xfffffffffffffffc,%rsi
  3b:	movabs $0xffff8881139d7480,%rdi
  45:	add    $0x110,%rdi
  4c:	mov    0x0(%rsi),%eax
  4f:	cmp    $0x4,%rax
  53:	jae    0x000000000000005e
  55:	shl    $0x3,%rax
  59:	add    %rdi,%rax
  5c:	jmp    0x0000000000000060
  5e:	xor    %eax,%eax
; if (!counts)
  60:	cmp    $0x0,%rax
  64:	je     0x0000000000000070
; counts->v6++;
  66:	mov    0x4(%rax),%edi
  69:	add    $0x1,%rdi
  6d:	mov    %edi,0x4(%rax)
  70:	mov    0x0(%rbp),%rbx
  74:	mov    0x8(%rbp),%r13
  78:	mov    0x10(%rbp),%r14
  7c:	mov    0x18(%rbp),%r15
  80:	add    $0x28,%rbp
  84:	leaveq
  85:	retq
[...]

With linum:
[root@arch-fb-vm1 bpf]# ~/devshare/fb-kernel/linux/tools/bpf/bpftool/bpftool prog dump jited pinned /sys/fs/bpf/test_btf_haskv linum
int _dummy_tracepoint(struct dummy_tracepoint_args * arg):
bpf_prog_b07ccb89267cf242__dummy_tracepoint:
; return test_long_fname_1(arg); [file:/data/users/kafai/fb-kernel/linux/tools/testing/selftests/bpf/test_btf_haskv.c line_num:54 line_col:9]
   0:	push   %rbp
   1:	mov    %rsp,%rbp
   4:	sub    $0x28,%rsp
   b:	sub    $0x28,%rbp
   f:	mov    %rbx,0x0(%rbp)
  13:	mov    %r13,0x8(%rbp)
  17:	mov    %r14,0x10(%rbp)
  1b:	mov    %r15,0x18(%rbp)
  1f:	xor    %eax,%eax
  21:	mov    %rax,0x20(%rbp)
  25:	callq  0x000000000000851e
; return test_long_fname_1(arg); [file:/data/users/kafai/fb-kernel/linux/tools/testing/selftests/bpf/test_btf_haskv.c line_num:54 line_col:2]
  2a:	xor    %eax,%eax
  2c:	mov    0x0(%rbp),%rbx
  30:	mov    0x8(%rbp),%r13
  34:	mov    0x10(%rbp),%r14
  38:	mov    0x18(%rbp),%r15
  3c:	add    $0x28,%rbp
  40:	leaveq
  41:	retq
[...]

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst |  16 +-
 tools/bpf/bpftool/bash-completion/bpftool        |   6 +-
 tools/bpf/bpftool/btf_dumper.c                   |  64 ++++++
 tools/bpf/bpftool/jit_disasm.c                   |  23 ++-
 tools/bpf/bpftool/main.h                         |  23 ++-
 tools/bpf/bpftool/prog.c                         | 100 ++++++++-
 tools/bpf/bpftool/xlated_dumper.c                |  30 ++-
 tools/bpf/bpftool/xlated_dumper.h                |   7 +-
 tools/lib/bpf/Build                              |   2 +-
 tools/lib/bpf/bpf_prog_linfo.c                   | 253 +++++++++++++++++++++++
 tools/lib/bpf/libbpf.h                           |  13 ++
 tools/lib/bpf/libbpf.map                         |   4 +
 12 files changed, 516 insertions(+), 25 deletions(-)
 create mode 100644 tools/lib/bpf/bpf_prog_linfo.c

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 5524b6dccd85..7c30731a9b73 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -22,8 +22,8 @@ MAP COMMANDS
 =============
 
 |	**bpftool** **prog { show | list }** [*PROG*]
-|	**bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
-|	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
+|	**bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual** | **linum**}]
+|	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes** | **linum**}]
 |	**bpftool** **prog pin** *PROG* *FILE*
 |	**bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
 |	**bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*]
@@ -56,7 +56,7 @@ DESCRIPTION
 		  Output will start with program ID followed by program type and
 		  zero or more named attributes (depending on kernel version).
 
-	**bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** }]
+	**bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }]
 		  Dump eBPF instructions of the program from the kernel. By
 		  default, eBPF will be disassembled and printed to standard
 		  output in human-readable format. In this case, **opcodes**
@@ -69,13 +69,21 @@ DESCRIPTION
 		  built instead, and eBPF instructions will be presented with
 		  CFG in DOT format, on standard output.
 
-	**bpftool prog dump jited**  *PROG* [{ **file** *FILE* | **opcodes** }]
+		  If the prog has line_info available, the source line will
+		  be displayed by default.  If **linum** is specified,
+		  the filename, line number and line column will also be
+		  displayed on top of the source line.
+	**bpftool prog dump jited**  *PROG* [{ **file** *FILE* | **opcodes** | **linum** }]
 		  Dump jited image (host machine code) of the program.
 		  If *FILE* is specified image will be written to a file,
 		  otherwise it will be disassembled and printed to stdout.
 
 		  **opcodes** controls if raw opcodes will be printed.
 
+		  If the prog has line_info available, the source line will
+		  be displayed by default.  If **linum** is specified,
+		  the filename, line number and line column will also be
+		  displayed on top of the source line.
 	**bpftool prog pin** *PROG* *FILE*
 		  Pin program *PROG* as *FILE*.
 
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 44c189ba072a..a57febd6abb1 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -191,7 +191,7 @@ _bpftool()
 
     # Deal with simplest keywords
     case $prev in
-        help|hex|opcodes|visual)
+        help|hex|opcodes|visual|linum)
             return 0
             ;;
         tag)
@@ -278,10 +278,10 @@ _bpftool()
                     *)
                         _bpftool_once_attr 'file'
                         if _bpftool_search_list 'xlated'; then
-                            COMPREPLY+=( $( compgen -W 'opcodes visual' -- \
+                            COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \
                                 "$cur" ) )
                         else
-                            COMPREPLY+=( $( compgen -W 'opcodes' -- \
+                            COMPREPLY+=( $( compgen -W 'opcodes linum' -- \
                                 "$cur" ) )
                         fi
                         return 0
diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index c3fd3a7cb787..dbbf6ece6760 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -385,3 +385,67 @@ void btf_dumper_type_only(const struct btf *btf, __u32 type_id, char *func_sig,
 	if (err < 0)
 		func_sig[0] = '\0';
 }
+
+static const char *ltrim(const char *s)
+{
+	while (isspace(*s))
+		s++;
+
+	return s;
+}
+
+void btf_dump_linfo_plain(const struct btf *btf,
+			  const struct bpf_line_info *linfo,
+			  const char *prefix, bool linum)
+{
+	const char *line = btf__name_by_offset(btf, linfo->line_off);
+
+	if (!line)
+		return;
+	line = ltrim(line);
+
+	if (!prefix)
+		prefix = "";
+
+	if (linum) {
+		const char *file = btf__name_by_offset(btf, linfo->file_name_off);
+
+		/* More forgiving on file because linum option is
+		 * expected to provide more info than the already
+		 * available src line.
+		 */
+		if (!file)
+			file = "";
+
+		printf("%s%s [file:%s line_num:%u line_col:%u]\n",
+		       prefix, line, file,
+		       BPF_LINE_INFO_LINE_NUM(linfo->line_col),
+		       BPF_LINE_INFO_LINE_COL(linfo->line_col));
+	} else {
+		printf("%s%s\n", prefix, line);
+	}
+}
+
+void btf_dump_linfo_json(const struct btf *btf,
+			 const struct bpf_line_info *linfo, bool linum)
+{
+	const char *line = btf__name_by_offset(btf, linfo->line_off);
+
+	if (line)
+		jsonw_string_field(json_wtr, "src", ltrim(line));
+
+	if (linum) {
+		const char *file = btf__name_by_offset(btf, linfo->file_name_off);
+
+		if (file)
+			jsonw_string_field(json_wtr, "file", file);
+
+		if (BPF_LINE_INFO_LINE_NUM(linfo->line_col))
+			jsonw_int_field(json_wtr, "line_num",
+					BPF_LINE_INFO_LINE_NUM(linfo->line_col));
+
+		if (BPF_LINE_INFO_LINE_COL(linfo->line_col))
+			jsonw_int_field(json_wtr, "line_col",
+					BPF_LINE_INFO_LINE_COL(linfo->line_col));
+	}
+}
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index 545a92471c33..f381f8628ce9 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -21,6 +21,7 @@
 #include <dis-asm.h>
 #include <sys/stat.h>
 #include <limits.h>
+#include <libbpf.h>
 
 #include "json_writer.h"
 #include "main.h"
@@ -68,10 +69,16 @@ static int fprintf_json(void *out, const char *fmt, ...)
 }
 
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
-		       const char *arch, const char *disassembler_options)
+		       const char *arch, const char *disassembler_options,
+		       const struct btf *btf,
+		       const struct bpf_prog_linfo *prog_linfo,
+		       __u64 func_ksym, unsigned int func_idx,
+		       bool linum)
 {
+	const struct bpf_line_info *linfo = NULL;
 	disassembler_ftype disassemble;
 	struct disassemble_info info;
+	unsigned int nr_skip = 0;
 	int count, i, pc = 0;
 	char tpath[PATH_MAX];
 	bfd *bfdf;
@@ -127,12 +134,26 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 	if (json_output)
 		jsonw_start_array(json_wtr);
 	do {
+		if (prog_linfo) {
+			linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo,
+								func_ksym + pc,
+								func_idx,
+								nr_skip);
+			if (linfo)
+				nr_skip++;
+		}
+
 		if (json_output) {
 			jsonw_start_object(json_wtr);
 			oper_count = 0;
+			if (linfo)
+				btf_dump_linfo_json(btf, linfo, linum);
 			jsonw_name(json_wtr, "pc");
 			jsonw_printf(json_wtr, "\"0x%x\"", pc);
 		} else {
+			if (linfo)
+				btf_dump_linfo_plain(btf, linfo, "; ",
+						     linum);
 			printf("%4x:\t", pc);
 		}
 
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 0be0dd8f467f..d9393abdba78 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -138,6 +138,9 @@ struct pinned_obj {
 	struct hlist_node hash;
 };
 
+struct btf;
+struct bpf_line_info;
+
 int build_pinned_obj_table(struct pinned_obj_table *table,
 			   enum bpf_obj_type type);
 void delete_pinned_obj_table(struct pinned_obj_table *tab);
@@ -175,13 +178,23 @@ int map_parse_fd(int *argc, char ***argv);
 int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
 
 #ifdef HAVE_LIBBFD_SUPPORT
+struct bpf_prog_linfo;
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
-		       const char *arch, const char *disassembler_options);
+		       const char *arch, const char *disassembler_options,
+		       const struct btf *btf,
+		       const struct bpf_prog_linfo *prog_linfo,
+		       __u64 func_ksym, unsigned int func_idx,
+		       bool linum);
 int disasm_init(void);
 #else
 static inline
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
-		       const char *arch, const char *disassembler_options)
+		       const char *arch, const char *disassembler_options,
+		       const struct btf *btf,
+		       const struct bpf_prog_linfo *prog_linfo,
+		       __u64 func_ksym, unsigned int func_idx,
+		       bool linum)
+
 {
 }
 static inline int disasm_init(void)
@@ -217,6 +230,12 @@ int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
 void btf_dumper_type_only(const struct btf *btf, __u32 func_type_id,
 			  char *func_only, int size);
 
+void btf_dump_linfo_plain(const struct btf *btf,
+			  const struct bpf_line_info *linfo,
+			  const char *prefix, bool linum);
+void btf_dump_linfo_json(const struct btf *btf,
+			 const struct bpf_line_info *linfo, bool linum);
+
 struct nlattr;
 struct ifinfomsg;
 struct tcmsg;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index a9a51123454c..65b921ffd10a 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -423,24 +423,26 @@ static int do_show(int argc, char **argv)
 
 static int do_dump(int argc, char **argv)
 {
+	unsigned int finfo_rec_size, linfo_rec_size, jited_linfo_rec_size;
+	void *func_info = NULL, *linfo = NULL, *jited_linfo = NULL;
+	unsigned int finfo_cnt, linfo_cnt = 0, jited_linfo_cnt = 0;
+	struct bpf_prog_linfo *prog_linfo = NULL;
 	unsigned long *func_ksyms = NULL;
 	struct bpf_prog_info info = {};
 	unsigned int *func_lens = NULL;
 	const char *disasm_opt = NULL;
-	unsigned int finfo_rec_size;
 	unsigned int nr_func_ksyms;
 	unsigned int nr_func_lens;
 	struct dump_data dd = {};
 	__u32 len = sizeof(info);
 	struct btf *btf = NULL;
-	void *func_info = NULL;
-	unsigned int finfo_cnt;
 	unsigned int buf_size;
 	char *filepath = NULL;
 	bool opcodes = false;
 	bool visual = false;
 	char func_sig[1024];
 	unsigned char *buf;
+	bool linum = false;
 	__u32 *member_len;
 	__u64 *member_ptr;
 	ssize_t n;
@@ -484,6 +486,9 @@ static int do_dump(int argc, char **argv)
 	} else if (is_prefix(*argv, "visual")) {
 		visual = true;
 		NEXT_ARG();
+	} else if (is_prefix(*argv, "linum")) {
+		linum = true;
+		NEXT_ARG();
 	}
 
 	if (argc) {
@@ -543,6 +548,32 @@ static int do_dump(int argc, char **argv)
 		}
 	}
 
+	linfo_rec_size = info.line_info_rec_size;
+	if (info.line_info_cnt && linfo_rec_size && info.btf_id) {
+		linfo_cnt = info.line_info_cnt;
+		linfo = malloc(linfo_cnt * linfo_rec_size);
+		if (!linfo) {
+			p_err("mem alloc failed");
+			close(fd);
+			goto err_free;
+		}
+	}
+
+	jited_linfo_rec_size = info.jited_line_info_rec_size;
+	if (info.jited_line_info_cnt &&
+	    jited_linfo_rec_size &&
+	    info.nr_jited_ksyms &&
+	    info.nr_jited_func_lens &&
+	    info.btf_id) {
+		jited_linfo_cnt = info.jited_line_info_cnt;
+		jited_linfo = malloc(jited_linfo_cnt * jited_linfo_rec_size);
+		if (!jited_linfo) {
+			p_err("mem alloc failed");
+			close(fd);
+			goto err_free;
+		}
+	}
+
 	memset(&info, 0, sizeof(info));
 
 	*member_ptr = ptr_to_u64(buf);
@@ -554,6 +585,13 @@ static int do_dump(int argc, char **argv)
 	info.func_info_cnt = finfo_cnt;
 	info.func_info_rec_size = finfo_rec_size;
 	info.func_info = ptr_to_u64(func_info);
+	info.line_info_cnt = linfo_cnt;
+	info.line_info_rec_size = linfo_rec_size;
+	info.line_info = ptr_to_u64(linfo);
+	info.jited_line_info_cnt = jited_linfo_cnt;
+	info.jited_line_info_rec_size = jited_linfo_rec_size;
+	info.jited_line_info = ptr_to_u64(jited_linfo);
+
 
 	err = bpf_obj_get_info_by_fd(fd, &info, &len);
 	close(fd);
@@ -596,6 +634,30 @@ static int do_dump(int argc, char **argv)
 		finfo_cnt = 0;
 	}
 
+	if (linfo && info.line_info_cnt != linfo_cnt) {
+		p_err("incorrect line_info_cnt %u vs. expected %u",
+		      info.line_info_cnt, linfo_cnt);
+		goto err_free;
+	}
+
+	if (info.line_info_rec_size != linfo_rec_size) {
+		p_err("incorrect line_info_rec_size %u vs. expected %u",
+		      info.line_info_rec_size, linfo_rec_size);
+		goto err_free;
+	}
+
+	if (jited_linfo && info.jited_line_info_cnt != jited_linfo_cnt) {
+		p_err("incorrect jited_line_info_cnt %u vs. expected %u",
+		      info.jited_line_info_cnt, jited_linfo_cnt);
+		goto err_free;
+	}
+
+	if (info.jited_line_info_rec_size != jited_linfo_rec_size) {
+		p_err("incorrect jited_line_info_rec_size %u vs. expected %u",
+		      info.jited_line_info_rec_size, jited_linfo_rec_size);
+		goto err_free;
+	}
+
 	if ((member_len == &info.jited_prog_len &&
 	     info.jited_prog_insns == 0) ||
 	    (member_len == &info.xlated_prog_len &&
@@ -609,6 +671,12 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
+	if (linfo_cnt) {
+		prog_linfo = bpf_prog_linfo__new(&info);
+		if (!prog_linfo)
+			p_err("error in processing bpf_line_info.  continue without it.");
+	}
+
 	if (filepath) {
 		fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600);
 		if (fd < 0) {
@@ -690,8 +758,11 @@ static int do_dump(int argc, char **argv)
 					printf("%s:\n", sym_name);
 				}
 
-				disasm_print_insn(img, lens[i], opcodes, name,
-						  disasm_opt);
+				disasm_print_insn(img, lens[i], opcodes,
+						  name, disasm_opt, btf,
+						  prog_linfo, ksyms[i], i,
+						  linum);
+
 				img += lens[i];
 
 				if (json_output)
@@ -704,7 +775,7 @@ static int do_dump(int argc, char **argv)
 				jsonw_end_array(json_wtr);
 		} else {
 			disasm_print_insn(buf, *member_len, opcodes, name,
-					  disasm_opt);
+					  disasm_opt, btf, NULL, 0, 0, false);
 		}
 	} else if (visual) {
 		if (json_output)
@@ -718,11 +789,14 @@ static int do_dump(int argc, char **argv)
 		dd.btf = btf;
 		dd.func_info = func_info;
 		dd.finfo_rec_size = finfo_rec_size;
+		dd.prog_linfo = prog_linfo;
 
 		if (json_output)
-			dump_xlated_json(&dd, buf, *member_len, opcodes);
+			dump_xlated_json(&dd, buf, *member_len, opcodes,
+					 linum);
 		else
-			dump_xlated_plain(&dd, buf, *member_len, opcodes);
+			dump_xlated_plain(&dd, buf, *member_len, opcodes,
+					  linum);
 		kernel_syms_destroy(&dd);
 	}
 
@@ -730,6 +804,9 @@ static int do_dump(int argc, char **argv)
 	free(func_ksyms);
 	free(func_lens);
 	free(func_info);
+	free(linfo);
+	free(jited_linfo);
+	bpf_prog_linfo__free(prog_linfo);
 	return 0;
 
 err_free:
@@ -737,6 +814,9 @@ err_free:
 	free(func_ksyms);
 	free(func_lens);
 	free(func_info);
+	free(linfo);
+	free(jited_linfo);
+	bpf_prog_linfo__free(prog_linfo);
 	return -1;
 }
 
@@ -1138,8 +1218,8 @@ static int do_help(int argc, char **argv)
 
 	fprintf(stderr,
 		"Usage: %s %s { show | list } [PROG]\n"
-		"       %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
-		"       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
+		"       %s %s dump xlated PROG [{ file FILE | opcodes | visual | linum }]\n"
+		"       %s %s dump jited  PROG [{ file FILE | opcodes | linum }]\n"
 		"       %s %s pin   PROG FILE\n"
 		"       %s %s { load | loadall } OBJ  PATH \\\n"
 		"                         [type TYPE] [dev NAME] \\\n"
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 131ecd175533..aef628dcccb6 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -41,6 +41,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
+#include <libbpf.h>
 
 #include "disasm.h"
 #include "json_writer.h"
@@ -234,8 +235,9 @@ static const char *print_imm(void *private_data,
 }
 
 void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len,
-		      bool opcodes)
+		      bool opcodes, bool linum)
 {
+	const struct bpf_prog_linfo *prog_linfo = dd->prog_linfo;
 	const struct bpf_insn_cbs cbs = {
 		.cb_print	= print_insn_json,
 		.cb_call	= print_call,
@@ -246,6 +248,7 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len,
 	struct bpf_insn *insn = buf;
 	struct btf *btf = dd->btf;
 	bool double_insn = false;
+	unsigned int nr_skip = 0;
 	char func_sig[1024];
 	unsigned int i;
 
@@ -273,6 +276,16 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len,
 			}
 		}
 
+		if (prog_linfo) {
+			const struct bpf_line_info *linfo;
+
+			linfo = bpf_prog_linfo__lfind(prog_linfo, i, nr_skip);
+			if (linfo) {
+				btf_dump_linfo_json(btf, linfo, linum);
+				nr_skip++;
+			}
+		}
+
 		jsonw_name(json_wtr, "disasm");
 		print_bpf_insn(&cbs, insn + i, true);
 
@@ -307,8 +320,9 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len,
 }
 
 void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len,
-		       bool opcodes)
+		       bool opcodes, bool linum)
 {
+	const struct bpf_prog_linfo *prog_linfo = dd->prog_linfo;
 	const struct bpf_insn_cbs cbs = {
 		.cb_print	= print_insn,
 		.cb_call	= print_call,
@@ -318,6 +332,7 @@ void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len,
 	struct bpf_func_info *record;
 	struct bpf_insn *insn = buf;
 	struct btf *btf = dd->btf;
+	unsigned int nr_skip = 0;
 	bool double_insn = false;
 	char func_sig[1024];
 	unsigned int i;
@@ -340,6 +355,17 @@ void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len,
 			}
 		}
 
+		if (prog_linfo) {
+			const struct bpf_line_info *linfo;
+
+			linfo = bpf_prog_linfo__lfind(prog_linfo, i, nr_skip);
+			if (linfo) {
+				btf_dump_linfo_plain(btf, linfo, "; ",
+						     linum);
+				nr_skip++;
+			}
+		}
+
 		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
 
 		printf("% 4d: ", i);
diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h
index aec31723e1e5..a24f89df8cb2 100644
--- a/tools/bpf/bpftool/xlated_dumper.h
+++ b/tools/bpf/bpftool/xlated_dumper.h
@@ -40,6 +40,8 @@
 
 #define SYM_MAX_NAME	256
 
+struct bpf_prog_linfo;
+
 struct kernel_sym {
 	unsigned long address;
 	char name[SYM_MAX_NAME];
@@ -54,6 +56,7 @@ struct dump_data {
 	struct btf *btf;
 	void *func_info;
 	__u32 finfo_rec_size;
+	const struct bpf_prog_linfo *prog_linfo;
 	char scratch_buff[SYM_MAX_NAME + 8];
 };
 
@@ -61,9 +64,9 @@ void kernel_syms_load(struct dump_data *dd);
 void kernel_syms_destroy(struct dump_data *dd);
 struct kernel_sym *kernel_syms_search(struct dump_data *dd, unsigned long key);
 void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len,
-		      bool opcodes);
+		       bool opcodes, bool linum);
 void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len,
-		       bool opcodes);
+		       bool opcodes, bool linum);
 void dump_xlated_for_graph(struct dump_data *dd, void *buf, void *buf_end,
 			   unsigned int start_index);
 
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 7bc31c905018..197b40f5b5c6 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o bpf_prog_linfo.o
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
new file mode 100644
index 000000000000..b8af65145408
--- /dev/null
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -0,0 +1,253 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2018 Facebook */
+
+#include <string.h>
+#include <stdlib.h>
+#include <linux/err.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+
+#ifndef min
+#define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
+
+struct bpf_prog_linfo {
+	void *raw_linfo;
+	void *raw_jited_linfo;
+	__u32 *nr_jited_linfo_per_func;
+	__u32 *jited_linfo_func_idx;
+	__u32 nr_linfo;
+	__u32 nr_jited_func;
+	__u32 rec_size;
+	__u32 jited_rec_size;
+};
+
+static int dissect_jited_func(struct bpf_prog_linfo *prog_linfo,
+			      const __u64 *ksym_func, const __u32 *ksym_len)
+{
+	__u32 nr_jited_func, nr_linfo;
+	const void *raw_jited_linfo;
+	const __u64 *jited_linfo;
+	__u64 last_jited_linfo;
+	/*
+	 * Index to raw_jited_linfo:
+	 *      i: Index for searching the next ksym_func
+	 * prev_i: Index to the last found ksym_func
+	 */
+	__u32 i, prev_i;
+	__u32 f; /* Index to ksym_func */
+
+	raw_jited_linfo = prog_linfo->raw_jited_linfo;
+	jited_linfo = raw_jited_linfo;
+	if (ksym_func[0] != *jited_linfo)
+		goto errout;
+
+	prog_linfo->jited_linfo_func_idx[0] = 0;
+	nr_jited_func = prog_linfo->nr_jited_func;
+	nr_linfo = prog_linfo->nr_linfo;
+
+	for (prev_i = 0, i = 1, f = 1;
+	     i < nr_linfo && f < nr_jited_func;
+	     i++) {
+		raw_jited_linfo += prog_linfo->jited_rec_size;
+		last_jited_linfo = *jited_linfo;
+		jited_linfo = raw_jited_linfo;
+
+		if (ksym_func[f] == *jited_linfo) {
+			prog_linfo->jited_linfo_func_idx[f] = i;
+
+			/* Sanity check */
+			if (last_jited_linfo - ksym_func[f - 1] + 1 >
+			    ksym_len[f - 1])
+				goto errout;
+
+			prog_linfo->nr_jited_linfo_per_func[f - 1] =
+				i - prev_i;
+			prev_i = i;
+
+			/*
+			 * The ksym_func[f] is found in jited_linfo.
+			 * Look for the next one.
+			 */
+			f++;
+		} else if (*jited_linfo <= last_jited_linfo) {
+			/* Ensure the addr is increasing _within_ a func */
+			goto errout;
+		}
+	}
+
+	if (f != nr_jited_func)
+		goto errout;
+
+	prog_linfo->nr_jited_linfo_per_func[nr_jited_func - 1] =
+		nr_linfo - prev_i;
+
+	return 0;
+
+errout:
+	return -EINVAL;
+}
+
+void bpf_prog_linfo__free(struct bpf_prog_linfo *prog_linfo)
+{
+	if (!prog_linfo)
+		return;
+
+	free(prog_linfo->raw_linfo);
+	free(prog_linfo->raw_jited_linfo);
+	free(prog_linfo->nr_jited_linfo_per_func);
+	free(prog_linfo->jited_linfo_func_idx);
+	free(prog_linfo);
+}
+
+struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
+{
+	struct bpf_prog_linfo *prog_linfo;
+	__u32 nr_linfo, nr_jited_func;
+
+	nr_linfo = info->line_info_cnt;
+
+	/*
+	 * Test !info->line_info because the kernel may NULL
+	 * the ptr if kernel.kptr_restrict is set.
+	 */
+	if (!nr_linfo || !info->line_info)
+		return NULL;
+
+	/*
+	 * The min size that bpf_prog_linfo has to access for
+	 * searching purpose.
+	 */
+	if (info->line_info_rec_size <
+	    offsetof(struct bpf_line_info, file_name_off))
+		return NULL;
+
+	prog_linfo = calloc(1, sizeof(*prog_linfo));
+	if (!prog_linfo)
+		return NULL;
+
+	/* Copy xlated line_info */
+	prog_linfo->nr_linfo = nr_linfo;
+	prog_linfo->rec_size = info->line_info_rec_size;
+	prog_linfo->raw_linfo = malloc(nr_linfo * prog_linfo->rec_size);
+	if (!prog_linfo->raw_linfo)
+		goto err_free;
+	memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info,
+	       nr_linfo * prog_linfo->rec_size);
+
+	nr_jited_func = info->nr_jited_ksyms;
+	if (!nr_jited_func ||
+	    !info->jited_line_info ||
+	    info->jited_line_info_cnt != nr_linfo ||
+	    info->jited_line_info_rec_size < sizeof(__u64) ||
+	    info->nr_jited_func_lens != nr_jited_func ||
+	    !info->jited_ksyms ||
+	    !info->jited_func_lens)
+		/* Not enough info to provide jited_line_info */
+		return prog_linfo;
+
+	/* Copy jited_line_info */
+	prog_linfo->nr_jited_func = nr_jited_func;
+	prog_linfo->jited_rec_size = info->jited_line_info_rec_size;
+	prog_linfo->raw_jited_linfo = malloc(nr_linfo *
+					     prog_linfo->jited_rec_size);
+	if (!prog_linfo->raw_jited_linfo)
+		goto err_free;
+	memcpy(prog_linfo->raw_jited_linfo,
+	       (void *)(long)info->jited_line_info,
+	       nr_linfo * prog_linfo->jited_rec_size);
+
+	/* Number of jited_line_info per jited func */
+	prog_linfo->nr_jited_linfo_per_func = malloc(nr_jited_func *
+						     sizeof(__u32));
+	if (!prog_linfo->nr_jited_linfo_per_func)
+		goto err_free;
+
+	/*
+	 * For each jited func,
+	 * the start idx to the "linfo" and "jited_linfo" array,
+	 */
+	prog_linfo->jited_linfo_func_idx = malloc(nr_jited_func *
+						  sizeof(__u32));
+	if (!prog_linfo->jited_linfo_func_idx)
+		goto err_free;
+
+	if (dissect_jited_func(prog_linfo,
+			       (__u64 *)(long)info->jited_ksyms,
+			       (__u32 *)(long)info->jited_func_lens))
+		goto err_free;
+
+	return prog_linfo;
+
+err_free:
+	bpf_prog_linfo__free(prog_linfo);
+	return NULL;
+}
+
+const struct bpf_line_info *
+bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo,
+				__u64 addr, __u32 func_idx, __u32 nr_skip)
+{
+	__u32 jited_rec_size, rec_size, nr_linfo, start, i;
+	const void *raw_jited_linfo, *raw_linfo;
+	const __u64 *jited_linfo;
+
+	if (func_idx >= prog_linfo->nr_jited_func)
+		return NULL;
+
+	nr_linfo = prog_linfo->nr_jited_linfo_per_func[func_idx];
+	if (nr_skip >= nr_linfo)
+		return NULL;
+
+	start = prog_linfo->jited_linfo_func_idx[func_idx] + nr_skip;
+	jited_rec_size = prog_linfo->jited_rec_size;
+	raw_jited_linfo = prog_linfo->raw_jited_linfo +
+		(start * jited_rec_size);
+	jited_linfo = raw_jited_linfo;
+	if (addr < *jited_linfo)
+		return NULL;
+
+	nr_linfo -= nr_skip;
+	rec_size = prog_linfo->rec_size;
+	raw_linfo = prog_linfo->raw_linfo + (start * rec_size);
+	for (i = 0; i < nr_linfo; i++) {
+		if (addr < *jited_linfo)
+			break;
+
+		raw_linfo += rec_size;
+		raw_jited_linfo += jited_rec_size;
+		jited_linfo = raw_jited_linfo;
+	}
+
+	return raw_linfo - rec_size;
+}
+
+const struct bpf_line_info *
+bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
+		      __u32 insn_off, __u32 nr_skip)
+{
+	const struct bpf_line_info *linfo;
+	__u32 rec_size, nr_linfo, i;
+	const void *raw_linfo;
+
+	nr_linfo = prog_linfo->nr_linfo;
+	if (nr_skip >= nr_linfo)
+		return NULL;
+
+	rec_size = prog_linfo->rec_size;
+	raw_linfo = prog_linfo->raw_linfo + (nr_skip * rec_size);
+	linfo = raw_linfo;
+	if (insn_off < linfo->insn_off)
+		return NULL;
+
+	nr_linfo -= nr_skip;
+	for (i = 0; i < nr_linfo; i++) {
+		if (insn_off < linfo->insn_off)
+			break;
+
+		raw_linfo += rec_size;
+		linfo = raw_linfo;
+	}
+
+	return raw_linfo - rec_size;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index f30c3d07bb7d..5f68d7b75215 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -342,6 +342,19 @@ int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
 int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
 			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie);
 
+struct bpf_prog_linfo;
+struct bpf_prog_info;
+
+LIBBPF_API void bpf_prog_linfo__free(struct bpf_prog_linfo *prog_linfo);
+LIBBPF_API struct bpf_prog_linfo *
+bpf_prog_linfo__new(const struct bpf_prog_info *info);
+LIBBPF_API const struct bpf_line_info *
+bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo,
+				__u64 addr, __u32 func_idx, __u32 nr_skip);
+LIBBPF_API const struct bpf_line_info *
+bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
+		      __u32 insn_off, __u32 nr_skip);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 8deff22d61bb..cd02cd4e2cc3 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -99,6 +99,10 @@ LIBBPF_0.0.1 {
 		bpf_program__unload;
 		bpf_program__unpin;
 		bpf_program__unpin_instance;
+		bpf_prog_linfo__free;
+		bpf_prog_linfo__new;
+		bpf_prog_linfo__lfind_addr_func;
+		bpf_prog_linfo__lfind;
 		bpf_raw_tracepoint_open;
 		bpf_set_link_xdp_fd;
 		bpf_task_fd_query;
-- 
cgit v1.2.3


From 01d3240a04f4c09392e13c77b54d4423ebce2d72 Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Thu, 6 Dec 2018 13:01:03 +0000
Subject: media: bpf: add bpf function to report mouse movement

Some IR remotes have a directional pad or other pointer-like thing that
can be used as a mouse. Make it possible to decode these types of IR
protocols in BPF.

Cc: netdev@vger.kernel.org
Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/media/rc/bpf-lirc.c                        | 24 ++++++++
 include/uapi/linux/bpf.h                           | 17 +++++-
 tools/include/uapi/linux/bpf.h                     | 18 +++++-
 tools/testing/selftests/bpf/bpf_helpers.h          |  2 +
 tools/testing/selftests/bpf/test_lirc_mode2.sh     |  3 +-
 tools/testing/selftests/bpf/test_lirc_mode2_kern.c |  3 +
 tools/testing/selftests/bpf/test_lirc_mode2_user.c | 65 +++++++++++++++-------
 7 files changed, 109 insertions(+), 23 deletions(-)

diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index 8b97fd1f0cea..390a722e6211 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -59,6 +59,28 @@ static const struct bpf_func_proto rc_keydown_proto = {
 	.arg4_type = ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_rc_pointer_rel, u32*, sample, s32, rel_x, s32, rel_y)
+{
+	struct ir_raw_event_ctrl *ctrl;
+
+	ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample);
+
+	input_report_rel(ctrl->dev->input_dev, REL_X, rel_x);
+	input_report_rel(ctrl->dev->input_dev, REL_Y, rel_y);
+	input_sync(ctrl->dev->input_dev);
+
+	return 0;
+}
+
+static const struct bpf_func_proto rc_pointer_rel_proto = {
+	.func	   = bpf_rc_pointer_rel,
+	.gpl_only  = true,
+	.ret_type  = RET_INTEGER,
+	.arg1_type = ARG_PTR_TO_CTX,
+	.arg2_type = ARG_ANYTHING,
+	.arg3_type = ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -67,6 +89,8 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &rc_repeat_proto;
 	case BPF_FUNC_rc_keydown:
 		return &rc_keydown_proto;
+	case BPF_FUNC_rc_pointer_rel:
+		return &rc_pointer_rel_proto;
 	case BPF_FUNC_map_lookup_elem:
 		return &bpf_map_lookup_elem_proto;
 	case BPF_FUNC_map_update_elem:
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7a66db8d15d5..1bee1135866a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2301,6 +2301,20 @@ union bpf_attr {
  *		payload and/or *pop* value being to large.
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y)
+ *	Description
+ *		This helper is used in programs implementing IR decoding, to
+ *		report a successfully decoded pointer movement.
+ *
+ *		The *ctx* should point to the lirc sample as passed into
+ *		the program.
+ *
+ *		This helper is only available is the kernel was compiled with
+ *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ *		"**y**".
+ *	Return
+ *		0
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2394,7 +2408,8 @@ union bpf_attr {
 	FN(map_pop_elem),		\
 	FN(map_peek_elem),		\
 	FN(msg_push_data),		\
-	FN(msg_pop_data),
+	FN(msg_pop_data),		\
+	FN(rc_pointer_rel),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7973c28b24a0..6ad50b6471d3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2298,9 +2298,22 @@ union bpf_attr {
  *		if possible. Other errors can occur if input parameters are
  *		invalid either due to *start* byte not being valid part of msg
  *		payload and/or *pop* value being to large.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y)
+ *	Description
+ *		This helper is used in programs implementing IR decoding, to
+ *		report a successfully decoded pointer movement.
+ *
+ *		The *ctx* should point to the lirc sample as passed into
+ *		the program.
  *
+ *		This helper is only available is the kernel was compiled with
+ *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ *		"**y**".
  *	Return
- *		0 on success, or a negative erro in case of failure.
+ *		0
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2394,7 +2407,8 @@ union bpf_attr {
 	FN(map_pop_elem),		\
 	FN(map_peek_elem),		\
 	FN(msg_push_data),		\
-	FN(msg_pop_data),
+	FN(msg_pop_data),		\
+	FN(rc_pointer_rel),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 7b69519a09b1..04c060e8f10a 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -170,6 +170,8 @@ static int (*bpf_skb_vlan_push)(void *ctx, __be16 vlan_proto, __u16 vlan_tci) =
 	(void *) BPF_FUNC_skb_vlan_push;
 static int (*bpf_skb_vlan_pop)(void *ctx) =
 	(void *) BPF_FUNC_skb_vlan_pop;
+static int (*bpf_rc_pointer_rel)(void *ctx, int rel_x, int rel_y) =
+	(void *) BPF_FUNC_rc_pointer_rel;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh
index 677686198df3..ec4e15948e40 100755
--- a/tools/testing/selftests/bpf/test_lirc_mode2.sh
+++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh
@@ -21,13 +21,14 @@ do
 	if grep -q DRV_NAME=rc-loopback $i/uevent
 	then
 		LIRCDEV=$(grep DEVNAME= $i/lirc*/uevent | sed sQDEVNAME=Q/dev/Q)
+		INPUTDEV=$(grep DEVNAME= $i/input*/event*/uevent | sed sQDEVNAME=Q/dev/Q)
 	fi
 done
 
 if [ -n $LIRCDEV ];
 then
 	TYPE=lirc_mode2
-	./test_lirc_mode2_user $LIRCDEV
+	./test_lirc_mode2_user $LIRCDEV $INPUTDEV
 	ret=$?
 	if [ $ret -ne 0 ]; then
 		echo -e ${RED}"FAIL: $TYPE"${NC}
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c
index ba26855563a5..4147130cc3b7 100644
--- a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c
@@ -15,6 +15,9 @@ int bpf_decoder(unsigned int *sample)
 
 		if (duration & 0x10000)
 			bpf_rc_keydown(sample, 0x40, duration & 0xffff, 0);
+		if (duration & 0x20000)
+			bpf_rc_pointer_rel(sample, (duration >> 8) & 0xff,
+					   duration & 0xff);
 	}
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
index d470d63c33db..fb5fd6841ef3 100644
--- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
@@ -29,6 +29,7 @@
 
 #include <linux/bpf.h>
 #include <linux/lirc.h>
+#include <linux/input.h>
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -47,12 +48,13 @@
 int main(int argc, char **argv)
 {
 	struct bpf_object *obj;
-	int ret, lircfd, progfd, mode;
-	int testir = 0x1dead;
+	int ret, lircfd, progfd, inputfd;
+	int testir1 = 0x1dead;
+	int testir2 = 0x20101;
 	u32 prog_ids[10], prog_flags[10], prog_cnt;
 
-	if (argc != 2) {
-		printf("Usage: %s /dev/lircN\n", argv[0]);
+	if (argc != 3) {
+		printf("Usage: %s /dev/lircN /dev/input/eventM\n", argv[0]);
 		return 2;
 	}
 
@@ -76,9 +78,9 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	mode = LIRC_MODE_SCANCODE;
-	if (ioctl(lircfd, LIRC_SET_REC_MODE, &mode)) {
-		printf("failed to set rec mode: %m\n");
+	inputfd = open(argv[2], O_RDONLY | O_NONBLOCK);
+	if (inputfd == -1) {
+		printf("failed to open input device %s: %m\n", argv[1]);
 		return 1;
 	}
 
@@ -102,29 +104,54 @@ int main(int argc, char **argv)
 	}
 
 	/* Write raw IR */
-	ret = write(lircfd, &testir, sizeof(testir));
-	if (ret != sizeof(testir)) {
+	ret = write(lircfd, &testir1, sizeof(testir1));
+	if (ret != sizeof(testir1)) {
 		printf("Failed to send test IR message: %m\n");
 		return 1;
 	}
 
-	struct pollfd pfd = { .fd = lircfd, .events = POLLIN };
-	struct lirc_scancode lsc;
+	struct pollfd pfd = { .fd = inputfd, .events = POLLIN };
+	struct input_event event;
 
-	poll(&pfd, 1, 100);
+	for (;;) {
+		poll(&pfd, 1, 100);
 
-	/* Read decoded IR */
-	ret = read(lircfd, &lsc, sizeof(lsc));
-	if (ret != sizeof(lsc)) {
-		printf("Failed to read decoded IR: %m\n");
-		return 1;
+		/* Read decoded IR */
+		ret = read(inputfd, &event, sizeof(event));
+		if (ret != sizeof(event)) {
+			printf("Failed to read decoded IR: %m\n");
+			return 1;
+		}
+
+		if (event.type == EV_MSC && event.code == MSC_SCAN &&
+		    event.value == 0xdead) {
+			break;
+		}
 	}
 
-	if (lsc.scancode != 0xdead || lsc.rc_proto != 64) {
-		printf("Incorrect scancode decoded\n");
+	/* Write raw IR */
+	ret = write(lircfd, &testir2, sizeof(testir2));
+	if (ret != sizeof(testir2)) {
+		printf("Failed to send test IR message: %m\n");
 		return 1;
 	}
 
+	for (;;) {
+		poll(&pfd, 1, 100);
+
+		/* Read decoded IR */
+		ret = read(inputfd, &event, sizeof(event));
+		if (ret != sizeof(event)) {
+			printf("Failed to read decoded IR: %m\n");
+			return 1;
+		}
+
+		if (event.type == EV_REL && event.code == REL_Y &&
+		    event.value == 1 ) {
+			break;
+		}
+	}
+
 	prog_cnt = 10;
 	ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
 			     &prog_cnt);
-- 
cgit v1.2.3


From fe206c209314f3cebe232518db9b5ad2606e34f1 Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@mellanox.com>
Date: Tue, 4 Dec 2018 18:03:00 -0800
Subject: net/mlx5: When fetching CQEs return CQE instead of void pointer

The function is only used to retrieve CQEs, use the proper type as the
return value.

Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/wq.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index b1293d153a58..9bc2184a46bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -177,7 +177,7 @@ static inline u32 mlx5_cqwq_get_ci(struct mlx5_cqwq *wq)
 	return mlx5_cqwq_ctr2ix(wq, wq->cc);
 }
 
-static inline void *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix)
+static inline struct mlx5_cqe64 *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix)
 {
 	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
 }
-- 
cgit v1.2.3


From 6254adeb1f6943a66cbed892a5f683400b9db194 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 4 Dec 2018 18:03:01 -0800
Subject: net/mlx5: Use helper to get CQE opcode

Introduce and use a helper that extracts the opcode
from a CQE (completion queue entry) structure.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c     | 10 +++++-----
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c     |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c |  2 +-
 include/linux/mlx5/device.h                         |  5 +++++
 4 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 79638dcbae78..31956ddd394e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -554,9 +554,9 @@ static inline void mlx5e_poll_ico_single_cqe(struct mlx5e_cq *cq,
 
 	mlx5_cqwq_pop(&cq->wq);
 
-	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_REQ)) {
+	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
 		netdev_WARN_ONCE(cq->channel->netdev,
-				 "Bad OP in ICOSQ CQE: 0x%x\n", cqe->op_own);
+				 "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
 		return;
 	}
 
@@ -898,7 +898,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	prefetchw(va); /* xdp_frame data area */
 	prefetch(data);
 
-	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
+	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
 		rq->stats->wqe_err++;
 		return NULL;
 	}
@@ -930,7 +930,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	u16 byte_cnt     = cqe_bcnt - headlen;
 	struct sk_buff *skb;
 
-	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
+	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
 		rq->stats->wqe_err++;
 		return NULL;
 	}
@@ -1148,7 +1148,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 
 	wi->consumed_strides += cstrides;
 
-	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
+	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
 		rq->stats->wqe_err++;
 		goto mpwrq_cqe_out;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 6dacaeba2fbf..46b5a6914d71 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -507,7 +507,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
-		if (unlikely(cqe->op_own >> 4 == MLX5_CQE_REQ_ERR)) {
+		if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) {
 			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING,
 					      &sq->state)) {
 				mlx5e_dump_error_cqe(sq,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 8ca1d1949d93..873541ef4c1b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -334,7 +334,7 @@ static void mlx5_fpga_conn_handle_cqe(struct mlx5_fpga_conn *conn,
 {
 	u8 opcode, status = 0;
 
-	opcode = cqe->op_own >> 4;
+	opcode = get_cqe_opcode(cqe);
 
 	switch (opcode) {
 	case MLX5_CQE_REQ_ERR:
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index f7c8bebfe472..c66867c8fc2f 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -781,6 +781,11 @@ static inline u8 mlx5_get_cqe_format(struct mlx5_cqe64 *cqe)
 	return (cqe->op_own >> 2) & 0x3;
 }
 
+static inline u8 get_cqe_opcode(struct mlx5_cqe64 *cqe)
+{
+	return cqe->op_own >> 4;
+}
+
 static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe)
 {
 	return (cqe->lro_tcppsh_abort_dupack >> 6) & 1;
-- 
cgit v1.2.3


From bdefffd13bf294a5a0c16255650020bff98954c7 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 4 Dec 2018 18:03:02 -0800
Subject: IB/mlx5: Use helper to get CQE opcode

Use the new helper that extracts the opcode
from a CQE (completion queue entry) structure.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/cq.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 0b99f7d0630d..26ab9041f94a 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -82,7 +82,7 @@ static void *get_sw_cqe(struct mlx5_ib_cq *cq, int n)
 
 	cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;
 
-	if (likely((cqe64->op_own) >> 4 != MLX5_CQE_INVALID) &&
+	if (likely(get_cqe_opcode(cqe64) != MLX5_CQE_INVALID) &&
 	    !((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^ !!(n & (cq->ibcq.cqe + 1)))) {
 		return cqe;
 	} else {
@@ -197,7 +197,7 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
 	}
 	wc->byte_len = be32_to_cpu(cqe->byte_cnt);
 
-	switch (cqe->op_own >> 4) {
+	switch (get_cqe_opcode(cqe)) {
 	case MLX5_CQE_RESP_WR_IMM:
 		wc->opcode	= IB_WC_RECV_RDMA_WITH_IMM;
 		wc->wc_flags	= IB_WC_WITH_IMM;
@@ -537,7 +537,7 @@ repoll:
 	 */
 	rmb();
 
-	opcode = cqe64->op_own >> 4;
+	opcode = get_cqe_opcode(cqe64);
 	if (unlikely(opcode == MLX5_CQE_RESIZE_CQ)) {
 		if (likely(cq->resize_buf)) {
 			free_cq_buf(dev, &cq->buf);
@@ -1295,7 +1295,7 @@ static int copy_resize_cqes(struct mlx5_ib_cq *cq)
 		return -EINVAL;
 	}
 
-	while ((scqe64->op_own >> 4) != MLX5_CQE_RESIZE_CQ) {
+	while (get_cqe_opcode(scqe64) != MLX5_CQE_RESIZE_CQ) {
 		dcqe = mlx5_frag_buf_get_wqe(&cq->resize_buf->fbc,
 					     (i + 1) & cq->resize_buf->nent);
 		dcqe64 = dsize == 64 ? dcqe : dcqe + 64;
-- 
cgit v1.2.3


From 7300375f181e06ba98183509065c6b71bead442d Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 4 Dec 2018 18:03:03 -0800
Subject: net/mlx5: Move flow counters data structures from flow steering
 header

After the following flow counters API refactoring:
("net/mlx5: Use flow counter IDs and not the wrapping cache object")
flow counters private data structures mlx5_fc_cache and mlx5_fc are
redundantly exposed in fs_core.h, they have nothing to do with flow
steering core and they are private to fs_counter.c, this patch moves them
to where they belong and reduces their exposure in the driver.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h  | 23 ----------------------
 .../net/ethernet/mellanox/mlx5/core/fs_counters.c  | 23 ++++++++++++++++++++++
 2 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index b51ad217da32..2dc86347af58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -145,29 +145,6 @@ struct mlx5_flow_table {
 	struct rhltable			fgs_hash;
 };
 
-struct mlx5_fc_cache {
-	u64 packets;
-	u64 bytes;
-	u64 lastuse;
-};
-
-struct mlx5_fc {
-	struct list_head list;
-	struct llist_node addlist;
-	struct llist_node dellist;
-
-	/* last{packets,bytes} members are used when calculating the delta since
-	 * last reading
-	 */
-	u64 lastpackets;
-	u64 lastbytes;
-
-	u32 id;
-	bool aging;
-
-	struct mlx5_fc_cache cache ____cacheline_aligned_in_smp;
-};
-
 struct mlx5_ft_underlay_qp {
 	struct list_head list;
 	u32 qpn;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 32accd6b041b..c6c28f56aa29 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -41,6 +41,29 @@
 /* Max number of counters to query in bulk read is 32K */
 #define MLX5_SW_MAX_COUNTERS_BULK BIT(15)
 
+struct mlx5_fc_cache {
+	u64 packets;
+	u64 bytes;
+	u64 lastuse;
+};
+
+struct mlx5_fc {
+	struct list_head list;
+	struct llist_node addlist;
+	struct llist_node dellist;
+
+	/* last{packets,bytes} members are used when calculating the delta since
+	 * last reading
+	 */
+	u64 lastpackets;
+	u64 lastbytes;
+
+	u32 id;
+	bool aging;
+
+	struct mlx5_fc_cache cache ____cacheline_aligned_in_smp;
+};
+
 /* locking scheme:
  *
  * It is the responsibility of the user to prevent concurrent calls or bad
-- 
cgit v1.2.3


From 77990464bb39eb0f5cd41e4f9e3d6411f2883cac Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 6 Dec 2018 17:52:28 +0000
Subject: xfrm: clean an indentation issue, remove a space

Trivial fix to clean up indentation issue, remove an extraneous
space.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index fa4b3c877fcf..0a8d70d16918 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1970,7 +1970,7 @@ static inline void xfrm_dev_state_delete(struct xfrm_state *x)
 static inline void xfrm_dev_state_free(struct xfrm_state *x)
 {
 	struct xfrm_state_offload *xso = &x->xso;
-	 struct net_device *dev = xso->dev;
+	struct net_device *dev = xso->dev;
 
 	if (dev && dev->xfrmdev_ops) {
 		if (dev->xfrmdev_ops->xdo_dev_state_free)
-- 
cgit v1.2.3


From e434b8cdf788568ba65a0a0fd9f3cb41f3ca1803 Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Fri, 7 Dec 2018 12:16:18 -0500
Subject: bpf: relax verifier restriction on BPF_MOV | BPF_ALU

Currently, the destination register is marked as unknown for 32-bit
sub-register move (BPF_MOV | BPF_ALU) whenever the source register type is
SCALAR_VALUE.

This is too conservative that some valid cases will be rejected.
Especially, this may turn a constant scalar value into unknown value that
could break some assumptions of verifier.

For example, test_l4lb_noinline.c has the following C code:

    struct real_definition *dst

1:  if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6))
2:    return TC_ACT_SHOT;
3:
4:  if (dst->flags & F_IPV6) {

get_packet_dst is responsible for initializing "dst" into valid pointer and
return true (1), otherwise return false (0). The compiled instruction
sequence using alu32 will be:

  412: (54) (u32) r7 &= (u32) 1
  413: (bc) (u32) r0 = (u32) r7
  414: (95) exit

insn 413, a BPF_MOV | BPF_ALU, however will turn r0 into unknown value even
r7 contains SCALAR_VALUE 1.

This causes trouble when verifier is walking the code path that hasn't
initialized "dst" inside get_packet_dst, for which case 0 is returned and
we would then expect verifier concluding line 1 in the above C code pass
the "if" check, therefore would skip fall through path starting at line 4.
Now, because r0 returned from callee has became unknown value, so verifier
won't skip analyzing path starting at line 4 and "dst->flags" requires
dereferencing the pointer "dst" which actually hasn't be initialized for
this path.

This patch relaxed the code marking sub-register move destination. For a
SCALAR_VALUE, it is safe to just copy the value from source then truncate
it into 32-bit.

A unit test also included to demonstrate this issue. This test will fail
before this patch.

This relaxation could let verifier skipping more paths for conditional
comparison against immediate. It also let verifier recording a more
accurate/strict value for one register at one state, if this state end up
with going through exit without rejection and it is used for state
comparison later, then it is possible an inaccurate/permissive value is
better. So the real impact on verifier processed insn number is complex.
But in all, without this fix, valid program could be rejected.

>From real benchmarking on kernel selftests and Cilium bpf tests, there is
no impact on processed instruction number when tests ares compiled with
default compilation options. There is slightly improvements when they are
compiled with -mattr=+alu32 after this patch.

Also, test_xdp_noinline/-mattr=+alu32 now passed verification. It is
rejected before this fix.

Insn processed before/after this patch:

                        default     -mattr=+alu32

Kernel selftest

===
test_xdp.o              371/371      369/369
test_l4lb.o             6345/6345    5623/5623
test_xdp_noinline.o     2971/2971    rejected/2727
test_tcp_estates.o      429/429      430/430

Cilium bpf
===
bpf_lb-DLB_L3.o:        2085/2085     1685/1687
bpf_lb-DLB_L4.o:        2287/2287     1986/1982
bpf_lb-DUNKNOWN.o:      690/690       622/622
bpf_lxc.o:              95033/95033   N/A
bpf_netdev.o:           7245/7245     N/A
bpf_overlay.o:          2898/2898     3085/2947

NOTE:
  - bpf_lxc.o and bpf_netdev.o compiled by -mattr=+alu32 are rejected by
    verifier due to another issue inside verifier on supporting alu32
    binary.
  - Each cilium bpf program could generate several processed insn number,
    above number is sum of them.

v1->v2:
 - Restrict the change on SCALAR_VALUE.
 - Update benchmark numbers on Cilium bpf tests.

Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                       | 16 ++++++++++++----
 tools/testing/selftests/bpf/test_verifier.c | 13 +++++++++++++
 2 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9d25506bd55a..2e70b813a1a7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3583,12 +3583,15 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			return err;
 
 		if (BPF_SRC(insn->code) == BPF_X) {
+			struct bpf_reg_state *src_reg = regs + insn->src_reg;
+			struct bpf_reg_state *dst_reg = regs + insn->dst_reg;
+
 			if (BPF_CLASS(insn->code) == BPF_ALU64) {
 				/* case: R1 = R2
 				 * copy register state to dest reg
 				 */
-				regs[insn->dst_reg] = regs[insn->src_reg];
-				regs[insn->dst_reg].live |= REG_LIVE_WRITTEN;
+				*dst_reg = *src_reg;
+				dst_reg->live |= REG_LIVE_WRITTEN;
 			} else {
 				/* R1 = (u32) R2 */
 				if (is_pointer_value(env, insn->src_reg)) {
@@ -3596,9 +3599,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 						"R%d partial copy of pointer\n",
 						insn->src_reg);
 					return -EACCES;
+				} else if (src_reg->type == SCALAR_VALUE) {
+					*dst_reg = *src_reg;
+					dst_reg->live |= REG_LIVE_WRITTEN;
+				} else {
+					mark_reg_unknown(env, regs,
+							 insn->dst_reg);
 				}
-				mark_reg_unknown(env, regs, insn->dst_reg);
-				coerce_reg_to_size(&regs[insn->dst_reg], 4);
+				coerce_reg_to_size(dst_reg, 4);
 			}
 		} else {
 			/* case: R = imm
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 36ce58b4933e..957e4711c46c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -2959,6 +2959,19 @@ static struct bpf_test tests[] = {
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
 	},
+	{
+		"alu32: mov u32 const",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_7, 0),
+			BPF_ALU32_IMM(BPF_AND, BPF_REG_7, 1),
+			BPF_MOV32_REG(BPF_REG_0, BPF_REG_7),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 0,
+	},
 	{
 		"unpriv: partial copy of pointer",
 		.insns = {
-- 
cgit v1.2.3


From c1c8c27701b8fcc0cbbe4af0f9304df466b0123e Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 10 Dec 2018 09:29:48 +0000
Subject: net: hns3: fix spelling mistake "offser" -> "offset"

There is a spelling mistake in a msg string, fix this.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 77deea0beeba..d0f654123b9b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -183,7 +183,7 @@ static const struct hclge_hw_error hclge_qcn_fifo_rint[] = {
 	{ .int_msk = BIT(6), .msg = "qcn_shap_gp3_sch_fifo_rd_err" },
 	{ .int_msk = BIT(7), .msg = "qcn_shap_gp3_sch_fifo_wr_err" },
 	{ .int_msk = BIT(8), .msg = "qcn_shap_gp0_offset_fifo_rd_err" },
-	{ .int_msk = BIT(9), .msg = "qcn_shap_gp0_offser_fifo_wr_err" },
+	{ .int_msk = BIT(9), .msg = "qcn_shap_gp0_offset_fifo_wr_err" },
 	{ .int_msk = BIT(10), .msg = "qcn_shap_gp1_offset_fifo_rd_err" },
 	{ .int_msk = BIT(11), .msg = "qcn_shap_gp1_offset_fifo_wr_err" },
 	{ .int_msk = BIT(12), .msg = "qcn_shap_gp2_offset_fifo_rd_err" },
-- 
cgit v1.2.3


From b1dd054dbb72551d42686862f935f96c3e2a53ea Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 10 Dec 2018 19:25:38 +0800
Subject: ipvlan: Remove a useless comparison

Fix following gcc warning:

drivers/net/ipvlan/ipvlan_main.c:543:12: warning:
 comparison is always false due to limited range of data type [-Wtype-limits]

'mode' is a u16 variable, IPVLAN_MODE_L2 is zero,
the comparison is always false

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index c3d3e458f541..723a3f663c06 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -540,7 +540,7 @@ static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[],
 	if (data[IFLA_IPVLAN_MODE]) {
 		u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
 
-		if (mode < IPVLAN_MODE_L2 || mode >= IPVLAN_MODE_MAX)
+		if (mode >= IPVLAN_MODE_MAX)
 			return -EINVAL;
 	}
 	if (data[IFLA_IPVLAN_FLAGS]) {
-- 
cgit v1.2.3


From f578e6764958704960e78daf624887da1d3e6d90 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Mon, 10 Dec 2018 10:46:03 -0500
Subject: ieee802154: at86rf230: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ieee802154/at86rf230.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 3d9e91579866..0253eb502153 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -1632,18 +1632,7 @@ static int at86rf230_stats_show(struct seq_file *file, void *offset)
 	seq_printf(file, "INVALID:\t\t%8llu\n", lp->trac.invalid);
 	return 0;
 }
-
-static int at86rf230_stats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, at86rf230_stats_show, inode->i_private);
-}
-
-static const struct file_operations at86rf230_stats_fops = {
-	.open		= at86rf230_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(at86rf230_stats);
 
 static int at86rf230_debugfs_init(struct at86rf230_local *lp)
 {
-- 
cgit v1.2.3


From 5061e3f43b7da28e1fe13c300b66fc5a4f98b0e8 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Mon, 10 Dec 2018 10:53:29 -0500
Subject: net: xenbus: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/xenbus.c | 18 +++---------------
 1 file changed, 3 insertions(+), 15 deletions(-)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index fe1d52247bbe..2625740bdc4a 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -186,7 +186,7 @@ static const struct file_operations xenvif_dbg_io_ring_ops_fops = {
 	.write = xenvif_write_io_ring,
 };
 
-static int xenvif_read_ctrl(struct seq_file *m, void *v)
+static int xenvif_ctrl_show(struct seq_file *m, void *v)
 {
 	struct xenvif *vif = m->private;
 
@@ -194,19 +194,7 @@ static int xenvif_read_ctrl(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int xenvif_ctrl_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, xenvif_read_ctrl, inode->i_private);
-}
-
-static const struct file_operations xenvif_dbg_ctrl_ops_fops = {
-	.owner = THIS_MODULE,
-	.open = xenvif_ctrl_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(xenvif_ctrl);
 
 static void xenvif_debugfs_addif(struct xenvif *vif)
 {
@@ -238,7 +226,7 @@ static void xenvif_debugfs_addif(struct xenvif *vif)
 						    0400,
 						    vif->xenvif_dbg_root,
 						    vif,
-						    &xenvif_dbg_ctrl_ops_fops);
+						    &xenvif_ctrl_fops);
 			if (IS_ERR_OR_NULL(pfile))
 				pr_warn("Creation of ctrl file returned %ld!\n",
 					PTR_ERR(pfile));
-- 
cgit v1.2.3


From a93f5b56962538b85aa0594492aa27d539295d5e Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Mon, 10 Dec 2018 10:57:38 -0500
Subject: fjes: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/fjes/fjes_debugfs.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/net/fjes/fjes_debugfs.c b/drivers/net/fjes/fjes_debugfs.c
index 30052ebd52bf..7fed88ea27a5 100644
--- a/drivers/net/fjes/fjes_debugfs.c
+++ b/drivers/net/fjes/fjes_debugfs.c
@@ -62,19 +62,7 @@ static int fjes_dbg_status_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int fjes_dbg_status_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, fjes_dbg_status_show, inode->i_private);
-}
-
-static const struct file_operations fjes_dbg_status_fops = {
-	.owner		= THIS_MODULE,
-	.open		= fjes_dbg_status_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(fjes_dbg_status);
 
 void fjes_dbg_adapter_init(struct fjes_adapter *adapter)
 {
-- 
cgit v1.2.3


From 4e6feb7adb9a69e51271eae4715d546507c1e998 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Mon, 10 Dec 2018 11:08:45 -0500
Subject: bonding: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_debugfs.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index 3868e1a5126d..1360f1ffe070 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -45,19 +45,7 @@ static int bond_debug_rlb_hash_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int bond_debug_rlb_hash_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, bond_debug_rlb_hash_show, inode->i_private);
-}
-
-static const struct file_operations bond_debug_rlb_hash_fops = {
-	.owner		= THIS_MODULE,
-	.open		= bond_debug_rlb_hash_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(bond_debug_rlb_hash);
 
 void bond_debug_register(struct bonding *bond)
 {
-- 
cgit v1.2.3


From a324d6e454aa986d64cb650caa8ed7150023b3f3 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Mon, 10 Dec 2018 14:43:05 +0100
Subject: net: dsa: ksz: Add optional reset GPIO to Microchip KSZ switch
 binding

Add optional reset GPIO, as such a signal is available on the KSZ switches.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Woojung Huh <Woojung.Huh@microchip.com>
Cc: David S. Miller <davem@davemloft.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/dsa/ksz.txt | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/dsa/ksz.txt b/Documentation/devicetree/bindings/net/dsa/ksz.txt
index ac145b885e95..0f407fb371ce 100644
--- a/Documentation/devicetree/bindings/net/dsa/ksz.txt
+++ b/Documentation/devicetree/bindings/net/dsa/ksz.txt
@@ -8,6 +8,10 @@ Required properties:
   - "microchip,ksz9477"
   - "microchip,ksz9897"
 
+Optional properties:
+
+- reset-gpios		: Should be a gpio specifier for a reset line
+
 See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of additional
 required and optional properties.
 
-- 
cgit v1.2.3


From 924352c3d6347d96528cebcef9461cebe928c117 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Mon, 10 Dec 2018 14:43:06 +0100
Subject: net: dsa: ksz: Add reset GPIO handling

Add code to handle optional reset GPIO in the KSZ switch driver. The switch
has a reset GPIO line which can be controlled by the CPU, so make sure it is
configured correctly in such setups.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz_common.c | 17 +++++++++++++++++
 drivers/net/dsa/microchip/ksz_priv.h   |  2 ++
 2 files changed, 19 insertions(+)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 9705808c3af7..3b12e2dcff31 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -8,12 +8,14 @@
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/platform_data/microchip-ksz.h>
 #include <linux/phy.h>
 #include <linux/etherdevice.h>
 #include <linux/if_bridge.h>
+#include <linux/of_gpio.h>
 #include <linux/of_net.h>
 #include <net/dsa.h>
 #include <net/switchdev.h>
@@ -294,6 +296,17 @@ int ksz_switch_register(struct ksz_device *dev,
 	if (dev->pdata)
 		dev->chip_id = dev->pdata->chip_id;
 
+	dev->reset_gpio = devm_gpiod_get_optional(dev->dev, "reset",
+						  GPIOD_OUT_LOW);
+	if (IS_ERR(dev->reset_gpio))
+		return PTR_ERR(dev->reset_gpio);
+
+	if (dev->reset_gpio) {
+		gpiod_set_value(dev->reset_gpio, 1);
+		mdelay(10);
+		gpiod_set_value(dev->reset_gpio, 0);
+	}
+
 	mutex_init(&dev->reg_mutex);
 	mutex_init(&dev->stats_mutex);
 	mutex_init(&dev->alu_mutex);
@@ -329,6 +342,10 @@ void ksz_switch_remove(struct ksz_device *dev)
 {
 	dev->dev_ops->exit(dev);
 	dsa_unregister_switch(dev->ds);
+
+	if (dev->reset_gpio)
+		gpiod_set_value(dev->reset_gpio, 1);
+
 }
 EXPORT_SYMBOL(ksz_switch_remove);
 
diff --git a/drivers/net/dsa/microchip/ksz_priv.h b/drivers/net/dsa/microchip/ksz_priv.h
index a38ff0841ed4..60b49010904b 100644
--- a/drivers/net/dsa/microchip/ksz_priv.h
+++ b/drivers/net/dsa/microchip/ksz_priv.h
@@ -59,6 +59,8 @@ struct ksz_device {
 
 	void *priv;
 
+	struct gpio_desc *reset_gpio;	/* Optional reset GPIO */
+
 	/* chip specific data */
 	u32 chip_id;
 	int num_vlans;
-- 
cgit v1.2.3


From d8ed257f313f64e9835e61d1365dea95a0a1c9c6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 10 Dec 2018 06:10:02 -0800
Subject: tcp: handle EOR and FIN conditions the same in tcp_tso_should_defer()

In commit f9bfe4e6a9d0 ("tcp: lack of available data can also cause
TSO defer") we moved the test in tcp_tso_should_defer() for packets
with a FIN flag, and we mentioned that the same would be done
later for EOR flag.

Both flags should be handled at the same time, after all other
heuristics have been considered. They both mean that no more bytes
can be added to this skb by an application.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c31badfee806..730bc44dbad9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1947,10 +1947,6 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
 		goto send_now;
 
-	/* If this packet won't get more data, do not wait. */
-	if (TCP_SKB_CB(skb)->eor)
-		goto send_now;
-
 	win_divisor = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_win_divisor);
 	if (win_divisor) {
 		u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
@@ -1999,7 +1995,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	}
 
 	/* If this packet won't get more data, do not wait. */
-	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+	if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) ||
+	    TCP_SKB_CB(skb)->eor)
 		goto send_now;
 
 	return true;
-- 
cgit v1.2.3


From 10a5ce98539948affbdc28dc0f39a1b6b2307f9d Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 10 Dec 2018 10:53:24 -0800
Subject: bpf: bpftool: Fix newline and p_err issue

This patch fixes a few newline issues and also
replaces p_err with p_info in prog.c

Fixes: b053b439b72a ("bpf: libbpf: bpftool: Print bpf_line_info during prog dump")
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 2 ++
 tools/bpf/bpftool/main.h                         | 1 -
 tools/bpf/bpftool/prog.c                         | 3 +--
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 7c30731a9b73..bb1aeb98b6da 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -73,6 +73,7 @@ DESCRIPTION
 		  be displayed by default.  If **linum** is specified,
 		  the filename, line number and line column will also be
 		  displayed on top of the source line.
+
 	**bpftool prog dump jited**  *PROG* [{ **file** *FILE* | **opcodes** | **linum** }]
 		  Dump jited image (host machine code) of the program.
 		  If *FILE* is specified image will be written to a file,
@@ -84,6 +85,7 @@ DESCRIPTION
 		  be displayed by default.  If **linum** is specified,
 		  the filename, line number and line column will also be
 		  displayed on top of the source line.
+
 	**bpftool prog pin** *PROG* *FILE*
 		  Pin program *PROG* as *FILE*.
 
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index d9393abdba78..0b37599f8cda 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -194,7 +194,6 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 		       const struct bpf_prog_linfo *prog_linfo,
 		       __u64 func_ksym, unsigned int func_idx,
 		       bool linum)
-
 {
 }
 static inline int disasm_init(void)
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 65b921ffd10a..9a78ebbcea1d 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -592,7 +592,6 @@ static int do_dump(int argc, char **argv)
 	info.jited_line_info_rec_size = jited_linfo_rec_size;
 	info.jited_line_info = ptr_to_u64(jited_linfo);
 
-
 	err = bpf_obj_get_info_by_fd(fd, &info, &len);
 	close(fd);
 	if (err) {
@@ -674,7 +673,7 @@ static int do_dump(int argc, char **argv)
 	if (linfo_cnt) {
 		prog_linfo = bpf_prog_linfo__new(&info);
 		if (!prog_linfo)
-			p_err("error in processing bpf_line_info.  continue without it.");
+			p_info("error in processing bpf_line_info.  continue without it.");
 	}
 
 	if (filepath) {
-- 
cgit v1.2.3


From c2fb3db22d35f01774d0547b1d8e5085df193646 Mon Sep 17 00:00:00 2001
From: Mikhael Goikhman <migo@mellanox.com>
Date: Mon, 10 Dec 2018 13:15:09 -0800
Subject: net/mlx5: Rework handling of port module events

Add explicit HW defined error values. For simplicity, keep counters for all
statuses starting from 0, although currently status=0 is not used.

Additionally, when HW signals an unexpected cable status, it is reported
now rather than ignored. And status counter is now updated on errors.

Signed-off-by: Mikhael Goikhman <migo@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c |  8 +--
 drivers/net/ethernet/mellanox/mlx5/core/events.c   | 83 ++++++++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h | 19 +++--
 3 files changed, 65 insertions(+), 45 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 748d23806391..881c54c12e19 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -1087,13 +1087,13 @@ static void mlx5e_grp_per_prio_update_stats(struct mlx5e_priv *priv)
 }
 
 static const struct counter_desc mlx5e_pme_status_desc[] = {
-	{ "module_unplug", 8 },
+	{ "module_unplug",       sizeof(u64) * MLX5_MODULE_STATUS_UNPLUGGED },
 };
 
 static const struct counter_desc mlx5e_pme_error_desc[] = {
-	{ "module_bus_stuck", 16 },       /* bus stuck (I2C or data shorted) */
-	{ "module_high_temp", 48 },       /* high temperature */
-	{ "module_bad_shorted", 56 },    /* bad or shorted cable/module */
+	{ "module_bus_stuck",    sizeof(u64) * MLX5_MODULE_EVENT_ERROR_BUS_STUCK },
+	{ "module_high_temp",    sizeof(u64) * MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE },
+	{ "module_bad_shorted",  sizeof(u64) * MLX5_MODULE_EVENT_ERROR_BAD_CABLE },
 };
 
 #define NUM_PME_STATUS_STATS		ARRAY_SIZE(mlx5e_pme_status_desc)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index e92df7020a26..587d93ec905f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -157,23 +157,43 @@ static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
 }
 
 /* MLX5_EVENT_TYPE_PORT_MODULE_EVENT */
-static const char *mlx5_pme_status[MLX5_MODULE_STATUS_NUM] = {
-	"Cable plugged",   /* MLX5_MODULE_STATUS_PLUGGED    = 0x1 */
-	"Cable unplugged", /* MLX5_MODULE_STATUS_UNPLUGGED  = 0x2 */
-	"Cable error",     /* MLX5_MODULE_STATUS_ERROR      = 0x3 */
-};
+static const char *mlx5_pme_status_to_string(enum port_module_event_status_type status)
+{
+	switch (status) {
+	case MLX5_MODULE_STATUS_PLUGGED:
+		return "Cable plugged";
+	case MLX5_MODULE_STATUS_UNPLUGGED:
+		return "Cable unplugged";
+	case MLX5_MODULE_STATUS_ERROR:
+		return "Cable error";
+	default:
+		return "Unknown status";
+	}
+}
 
-static const char *mlx5_pme_error[MLX5_MODULE_EVENT_ERROR_NUM] = {
-	"Power budget exceeded",
-	"Long Range for non MLNX cable",
-	"Bus stuck(I2C or data shorted)",
-	"No EEPROM/retry timeout",
-	"Enforce part number list",
-	"Unknown identifier",
-	"High Temperature",
-	"Bad or shorted cable/module",
-	"Unknown status",
-};
+static const char *mlx5_pme_error_to_string(enum port_module_event_error_type error)
+{
+	switch (error) {
+	case MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED:
+		return "Power budget exceeded";
+	case MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX:
+		return "Long Range for non MLNX cable";
+	case MLX5_MODULE_EVENT_ERROR_BUS_STUCK:
+		return "Bus stuck (I2C or data shorted)";
+	case MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT:
+		return "No EEPROM/retry timeout";
+	case MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST:
+		return "Enforce part number list";
+	case MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER:
+		return "Unknown identifier";
+	case MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE:
+		return "High Temperature";
+	case MLX5_MODULE_EVENT_ERROR_BAD_CABLE:
+		return "Bad or shorted cable/module";
+	default:
+		return "Unknown error";
+	}
+}
 
 /* type == MLX5_EVENT_TYPE_PORT_MODULE_EVENT */
 static int port_module(struct notifier_block *nb, unsigned long type, void *data)
@@ -185,6 +205,7 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data
 	enum port_module_event_status_type module_status;
 	enum port_module_event_error_type error_type;
 	struct mlx5_eqe_port_module *module_event_eqe;
+	const char *status_str, *error_str;
 	u8 module_num;
 
 	module_event_eqe = &eqe->data.port_module;
@@ -193,28 +214,28 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data
 			PORT_MODULE_EVENT_MODULE_STATUS_MASK;
 	error_type = module_event_eqe->error_type &
 		     PORT_MODULE_EVENT_ERROR_TYPE_MASK;
-	if (module_status < MLX5_MODULE_STATUS_ERROR) {
-		events->pme_stats.status_counters[module_status - 1]++;
-	} else if (module_status == MLX5_MODULE_STATUS_ERROR) {
-		if (error_type >= MLX5_MODULE_EVENT_ERROR_UNKNOWN)
-			/* Unknown error type */
-			error_type = MLX5_MODULE_EVENT_ERROR_UNKNOWN;
-		events->pme_stats.error_counters[error_type]++;
+
+	if (module_status < MLX5_MODULE_STATUS_NUM)
+		events->pme_stats.status_counters[module_status]++;
+	status_str = mlx5_pme_status_to_string(module_status);
+
+	if (module_status == MLX5_MODULE_STATUS_ERROR) {
+		if (error_type < MLX5_MODULE_EVENT_ERROR_NUM)
+			events->pme_stats.error_counters[error_type]++;
+		error_str = mlx5_pme_error_to_string(error_type);
 	}
 
 	if (!printk_ratelimit())
 		return NOTIFY_OK;
 
-	if (module_status < MLX5_MODULE_STATUS_ERROR)
+	if (module_status == MLX5_MODULE_STATUS_ERROR)
+		mlx5_core_err(events->dev,
+			      "Port module event[error]: module %u, %s, %s\n",
+			      module_num, status_str, error_str);
+	else
 		mlx5_core_info(events->dev,
 			       "Port module event: module %u, %s\n",
-			       module_num, mlx5_pme_status[module_status - 1]);
-
-	else if (module_status == MLX5_MODULE_STATUS_ERROR)
-		mlx5_core_info(events->dev,
-			       "Port module event[error]: module %u, %s, %s\n",
-			       module_num, mlx5_pme_status[module_status - 1],
-			       mlx5_pme_error[error_type]);
+			       module_num, status_str);
 
 	return NOTIFY_OK;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 4d78a459676e..af19fa61e9ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -51,19 +51,18 @@ enum port_module_event_status_type {
 	MLX5_MODULE_STATUS_PLUGGED   = 0x1,
 	MLX5_MODULE_STATUS_UNPLUGGED = 0x2,
 	MLX5_MODULE_STATUS_ERROR     = 0x3,
-	MLX5_MODULE_STATUS_NUM       = 0x3,
+	MLX5_MODULE_STATUS_NUM,
 };
 
 enum  port_module_event_error_type {
-	MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED,
-	MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX_CABLE_MODULE,
-	MLX5_MODULE_EVENT_ERROR_BUS_STUCK,
-	MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT,
-	MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST,
-	MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER,
-	MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE,
-	MLX5_MODULE_EVENT_ERROR_BAD_CABLE,
-	MLX5_MODULE_EVENT_ERROR_UNKNOWN,
+	MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED    = 0x0,
+	MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX  = 0x1,
+	MLX5_MODULE_EVENT_ERROR_BUS_STUCK                = 0x2,
+	MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT  = 0x3,
+	MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST = 0x4,
+	MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER       = 0x5,
+	MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE         = 0x6,
+	MLX5_MODULE_EVENT_ERROR_BAD_CABLE                = 0x7,
 	MLX5_MODULE_EVENT_ERROR_NUM,
 };
 
-- 
cgit v1.2.3


From 37a12aae06fda00f36eadb168d5d7ba0be3a8c86 Mon Sep 17 00:00:00 2001
From: Mikhael Goikhman <migo@mellanox.com>
Date: Mon, 10 Dec 2018 13:15:10 -0800
Subject: net/mlx5: Add support for PCIe power slot exceeded error in PME

Support a new hardware error type in port module events:
- error_type=0xc (PCIe system power slot exceeded)

Signed-off-by: Mikhael Goikhman <migo@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c   | 2 ++
 drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 587d93ec905f..ba9249bcfcba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -190,6 +190,8 @@ static const char *mlx5_pme_error_to_string(enum port_module_event_error_type er
 		return "High Temperature";
 	case MLX5_MODULE_EVENT_ERROR_BAD_CABLE:
 		return "Bad or shorted cable/module";
+	case MLX5_MODULE_EVENT_ERROR_PCIE_POWER_SLOT_EXCEEDED:
+		return "One or more network ports have been powered down due to insufficient/unadvertised power on the PCIe slot";
 	default:
 		return "Unknown error";
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index af19fa61e9ef..979970f8fa0f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -63,6 +63,7 @@ enum  port_module_event_error_type {
 	MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER       = 0x5,
 	MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE         = 0x6,
 	MLX5_MODULE_EVENT_ERROR_BAD_CABLE                = 0x7,
+	MLX5_MODULE_EVENT_ERROR_PCIE_POWER_SLOT_EXCEEDED = 0xc,
 	MLX5_MODULE_EVENT_ERROR_NUM,
 };
 
-- 
cgit v1.2.3


From 8d6b57e6445989e9f34077ef1aac80b621029b08 Mon Sep 17 00:00:00 2001
From: Mikhael Goikhman <migo@mellanox.com>
Date: Mon, 10 Dec 2018 13:15:11 -0800
Subject: net/mlx5: Add support for plugged-disabled cable status in PME

Support a new hardware module status in port module events:
- module_status=0x4 (Cable plugged, but disabled)

Signed-off-by: Mikhael Goikhman <migo@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c   | 2 ++
 drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index ba9249bcfcba..900fdd235ba0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -166,6 +166,8 @@ static const char *mlx5_pme_status_to_string(enum port_module_event_status_type
 		return "Cable unplugged";
 	case MLX5_MODULE_STATUS_ERROR:
 		return "Cable error";
+	case MLX5_MODULE_STATUS_DISABLED:
+		return "Cable disabled";
 	default:
 		return "Unknown status";
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 979970f8fa0f..397a2847867a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -51,6 +51,7 @@ enum port_module_event_status_type {
 	MLX5_MODULE_STATUS_PLUGGED   = 0x1,
 	MLX5_MODULE_STATUS_UNPLUGGED = 0x2,
 	MLX5_MODULE_STATUS_ERROR     = 0x3,
+	MLX5_MODULE_STATUS_DISABLED  = 0x4,
 	MLX5_MODULE_STATUS_NUM,
 };
 
-- 
cgit v1.2.3


From fd4572b3ff3ff57ca7fa612f9ea42b90afdd8bff Mon Sep 17 00:00:00 2001
From: Eyal Davidovich <eyald@mellanox.com>
Date: Mon, 10 Dec 2018 13:15:12 -0800
Subject: net/mlx5: Add monitor commands layout and event data

Will be used in downstream patch to monitor counter changes
by the HCA and report it to the driver by an event.
The driver will update its counters cached data accordingly.

Signed-off-by: Eyal Davidovich <eyald@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c    |  4 ++
 drivers/net/ethernet/mellanox/mlx5/core/eq.c     |  3 +
 drivers/net/ethernet/mellanox/mlx5/core/events.c |  2 +
 include/linux/mlx5/device.h                      |  1 +
 include/linux/mlx5/mlx5_ifc.h                    | 87 +++++++++++++++++++++++-
 5 files changed, 96 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 8ab636d59edb..d3125cdf69db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -373,6 +373,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
 	case MLX5_CMD_OP_ALLOC_Q_COUNTER:
 	case MLX5_CMD_OP_QUERY_Q_COUNTER:
+	case MLX5_CMD_OP_SET_MONITOR_COUNTER:
+	case MLX5_CMD_OP_ARM_MONITOR_COUNTER:
 	case MLX5_CMD_OP_SET_PP_RATE_LIMIT:
 	case MLX5_CMD_OP_QUERY_RATE_LIMIT:
 	case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
@@ -522,6 +524,8 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
+	MLX5_COMMAND_STR_CASE(SET_MONITOR_COUNTER);
+	MLX5_COMMAND_STR_CASE(ARM_MONITOR_COUNTER);
 	MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 4aa39a1fe23f..ee04aab65a9f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -527,6 +527,9 @@ static u64 gather_async_events_mask(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_MCAM_REG(dev, tracer_registers))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_DEVICE_TRACER);
 
+	if (MLX5_CAP_GEN(dev, max_num_of_monitor_counters))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_MONITOR_COUNTER);
+
 	return async_event_mask;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 900fdd235ba0..fbc42b7252a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -117,6 +117,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_FPGA_QP_ERROR";
 	case MLX5_EVENT_TYPE_GENERAL_EVENT:
 		return "MLX5_EVENT_TYPE_GENERAL_EVENT";
+	case MLX5_EVENT_TYPE_MONITOR_COUNTER:
+		return "MLX5_EVENT_TYPE_MONITOR_COUNTER";
 	case MLX5_EVENT_TYPE_DEVICE_TRACER:
 		return "MLX5_EVENT_TYPE_DEVICE_TRACER";
 	default:
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index c66867c8fc2f..4674b9e99f45 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -330,6 +330,7 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_TEMP_WARN_EVENT    = 0x17,
 	MLX5_EVENT_TYPE_REMOTE_CONFIG	   = 0x19,
 	MLX5_EVENT_TYPE_GENERAL_EVENT	   = 0x22,
+	MLX5_EVENT_TYPE_MONITOR_COUNTER    = 0x24,
 	MLX5_EVENT_TYPE_PPS_EVENT          = 0x25,
 
 	MLX5_EVENT_TYPE_DB_BF_CONGESTION   = 0x1a,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 91d6e85e3cef..9f7cc26bfb3b 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -161,6 +161,8 @@ enum {
 	MLX5_CMD_OP_ALLOC_Q_COUNTER               = 0x771,
 	MLX5_CMD_OP_DEALLOC_Q_COUNTER             = 0x772,
 	MLX5_CMD_OP_QUERY_Q_COUNTER               = 0x773,
+	MLX5_CMD_OP_SET_MONITOR_COUNTER           = 0x774,
+	MLX5_CMD_OP_ARM_MONITOR_COUNTER           = 0x775,
 	MLX5_CMD_OP_SET_PP_RATE_LIMIT             = 0x780,
 	MLX5_CMD_OP_QUERY_RATE_LIMIT              = 0x781,
 	MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT      = 0x782,
@@ -1200,7 +1202,13 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   sw_owner_id[0x1];
 	u8         reserved_at_61f[0x1];
 
-	u8         reserved_at_620[0x80];
+	u8         max_num_of_monitor_counters[0x10];
+	u8         num_ppcnt_monitor_counters[0x10];
+
+	u8         reserved_at_640[0x10];
+	u8         num_q_monitor_counters[0x10];
+
+	u8         reserved_at_660[0x40];
 
 	u8         uctx_cap[0x20];
 
@@ -3808,6 +3816,83 @@ enum {
 	MLX5_VPORT_STATE_OP_MOD_ESW_VPORT   = 0x1,
 };
 
+struct mlx5_ifc_arm_monitor_counter_in_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_arm_monitor_counter_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+enum {
+	MLX5_QUERY_MONITOR_CNT_TYPE_PPCNT     = 0x0,
+	MLX5_QUERY_MONITOR_CNT_TYPE_Q_COUNTER = 0x1,
+};
+
+enum mlx5_monitor_counter_ppcnt {
+	MLX5_QUERY_MONITOR_PPCNT_IN_RANGE_LENGTH_ERRORS      = 0X0,
+	MLX5_QUERY_MONITOR_PPCNT_OUT_OF_RANGE_LENGTH_FIELD   = 0X1,
+	MLX5_QUERY_MONITOR_PPCNT_FRAME_TOO_LONG_ERRORS       = 0X2,
+	MLX5_QUERY_MONITOR_PPCNT_FRAME_CHECK_SEQUENCE_ERRORS = 0X3,
+	MLX5_QUERY_MONITOR_PPCNT_ALIGNMENT_ERRORS            = 0X4,
+	MLX5_QUERY_MONITOR_PPCNT_IF_OUT_DISCARDS             = 0X5,
+};
+
+enum {
+	MLX5_QUERY_MONITOR_Q_COUNTER_RX_OUT_OF_BUFFER     = 0X4,
+};
+
+struct mlx5_ifc_monitor_counter_output_bits {
+	u8         reserved_at_0[0x4];
+	u8         type[0x4];
+	u8         reserved_at_8[0x8];
+	u8         counter[0x10];
+
+	u8         counter_group_id[0x20];
+};
+
+#define MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1 (6)
+#define MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1    (1)
+#define MLX5_CMD_SET_MONITOR_NUM_COUNTER (MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1 +\
+					  MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1)
+
+struct mlx5_ifc_set_monitor_counter_in_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x10];
+	u8         num_of_counters[0x10];
+
+	u8         reserved_at_60[0x20];
+
+	struct mlx5_ifc_monitor_counter_output_bits monitor_counter[MLX5_CMD_SET_MONITOR_NUM_COUNTER];
+};
+
+struct mlx5_ifc_set_monitor_counter_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
 struct mlx5_ifc_query_vport_state_in_bits {
 	u8         opcode[0x10];
 	u8         reserved_at_10[0x10];
-- 
cgit v1.2.3


From 5886a96ad19dacebe6c4f7f8c001d489b06125dc Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Mon, 10 Dec 2018 13:15:13 -0800
Subject: net/mlx5: Revise gre and nvgre key formats

GRE RFC defines a 32 bit key field. NVGRE RFC splits the 32 bit
key field to 24 bit VSID (gre_key_h) and 8 bit flow entropy (gre_key_l).

Define the two key parsing alternatives in a union, thus enabling both
access methods.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c                           |  4 ++--
 .../net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c    |  8 ++++----
 include/linux/mlx5/mlx5_ifc.h                               | 13 +++++++++++--
 3 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 96515a8c9d2c..2560996fce79 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2680,11 +2680,11 @@ static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c,
 			 ntohs(ib_spec->gre.val.protocol));
 
 		memcpy(MLX5_ADDR_OF(fte_match_set_misc, misc_params_c,
-				    gre_key_h),
+				    gre_key.nvgre.hi),
 		       &ib_spec->gre.mask.key,
 		       sizeof(ib_spec->gre.mask.key));
 		memcpy(MLX5_ADDR_OF(fte_match_set_misc, misc_params_v,
-				    gre_key_h),
+				    gre_key.nvgre.hi),
 		       &ib_spec->gre.val.key,
 		       sizeof(ib_spec->gre.val.key));
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
index 0f11fff32a9b..424457ff9759 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
@@ -161,10 +161,10 @@ static void print_misc_parameters_hdrs(struct trace_seq *p,
 	PRINT_MASKED_VAL(name, p, format);		   \
 }
 	DECLARE_MASK_VAL(u64, gre_key) = {
-		.m = MLX5_GET(fte_match_set_misc, mask, gre_key_h) << 8 |
-		     MLX5_GET(fte_match_set_misc, mask, gre_key_l),
-		.v = MLX5_GET(fte_match_set_misc, value, gre_key_h) << 8 |
-		     MLX5_GET(fte_match_set_misc, value, gre_key_l)};
+		.m = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.hi) << 8 |
+		     MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.lo),
+		.v = MLX5_GET(fte_match_set_misc, value, gre_key.nvgre.hi) << 8 |
+		     MLX5_GET(fte_match_set_misc, value, gre_key.nvgre.lo)};
 
 	PRINT_MASKED_VAL(gre_key, p, "%llu");
 	PRINT_MASKED_VAL_MISC(u32, source_sqn, source_sqn, p, "%u");
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 9f7cc26bfb3b..688a549e74f1 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -423,6 +423,16 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
 	union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6;
 };
 
+struct mlx5_ifc_nvgre_key_bits {
+	u8 hi[0x18];
+	u8 lo[0x8];
+};
+
+union mlx5_ifc_gre_key_bits {
+	struct mlx5_ifc_nvgre_key_bits nvgre;
+	u8 key[0x20];
+};
+
 struct mlx5_ifc_fte_match_set_misc_bits {
 	u8         reserved_at_0[0x8];
 	u8         source_sqn[0x18];
@@ -444,8 +454,7 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 	u8         reserved_at_64[0xc];
 	u8         gre_protocol[0x10];
 
-	u8         gre_key_h[0x18];
-	u8         gre_key_l[0x8];
+	union mlx5_ifc_gre_key_bits gre_key;
 
 	u8         vxlan_vni[0x18];
 	u8         reserved_at_b8[0x8];
-- 
cgit v1.2.3


From 1b115498598f25d578cfc0df7b7aea9772bae0a1 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Mon, 10 Dec 2018 13:15:14 -0800
Subject: net/mlx5: Introduce extended destination fields

Extended destinations provide the ability to configure different
encapsulation properties per destination on a single FTE. This is
needed for use-cases such as remote mirroring over tunneled networks.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 688a549e74f1..60c1d49eb40c 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -621,7 +621,9 @@ struct mlx5_ifc_e_switch_cap_bits {
 
 	u8         vxlan_encap_decap[0x1];
 	u8         nvgre_encap_decap[0x1];
-	u8         reserved_at_22[0x9];
+	u8         reserved_at_22[0x1];
+	u8         log_max_fdb_encap_uplink[0x5];
+	u8         reserved_at_21[0x3];
 	u8         log_max_packet_reformat_context[0x5];
 	u8         reserved_2b[0x6];
 	u8         max_encap_header_size[0xa];
@@ -1237,8 +1239,10 @@ enum mlx5_flow_destination_type {
 struct mlx5_ifc_dest_format_struct_bits {
 	u8         destination_type[0x8];
 	u8         destination_id[0x18];
+
 	u8         destination_eswitch_owner_vhca_id_valid[0x1];
-	u8         reserved_at_21[0xf];
+	u8         packet_reformat[0x1];
+	u8         reserved_at_22[0xe];
 	u8         destination_eswitch_owner_vhca_id[0x10];
 };
 
@@ -1248,6 +1252,14 @@ struct mlx5_ifc_flow_counter_list_bits {
 	u8         reserved_at_20[0x20];
 };
 
+struct mlx5_ifc_extended_dest_format_bits {
+	struct mlx5_ifc_dest_format_struct_bits destination_entry;
+
+	u8         packet_reformat_id[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
 union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits {
 	struct mlx5_ifc_dest_format_struct_bits dest_format_struct;
 	struct mlx5_ifc_flow_counter_list_bits flow_counter_list;
@@ -2469,7 +2481,8 @@ struct mlx5_ifc_flow_context_bits {
 	u8         reserved_at_60[0x10];
 	u8         action[0x10];
 
-	u8         reserved_at_80[0x8];
+	u8         extended_destination[0x1];
+	u8         reserved_at_80[0x7];
 	u8         destination_list_size[0x18];
 
 	u8         reserved_at_a0[0x8];
-- 
cgit v1.2.3


From aa39c2c0e44d16b5804f8fb6b5350cdf4e33b4c3 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Mon, 10 Dec 2018 13:15:15 -0800
Subject: net/mlx5: E-Switch, Change vhca id valid bool field to bit flag

Change the driver flow destination struct to use bit flags with the vhca
id valid being the 1st one. The flags field is more extendable and will
be used in downstream patch.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 8 +++++---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c           | 3 ++-
 include/linux/mlx5/fs.h                                    | 6 +++++-
 3 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 9eac137790f5..4d7b65df32ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -125,8 +125,9 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 				dest[i].vport.num = attr->out_rep[j]->vport;
 				dest[i].vport.vhca_id =
 					MLX5_CAP_GEN(attr->out_mdev[j], vhca_id);
-				dest[i].vport.vhca_id_valid =
-					!!MLX5_CAP_ESW(esw->dev, merged_eswitch);
+				if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+					dest[i].vport.flags |=
+						MLX5_FLOW_DEST_VPORT_VHCA_ID;
 				i++;
 			}
 		}
@@ -220,7 +221,8 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 		dest[i].vport.num = attr->out_rep[i]->vport;
 		dest[i].vport.vhca_id =
 			MLX5_CAP_GEN(attr->out_mdev[i], vhca_id);
-		dest[i].vport.vhca_id_valid = !!MLX5_CAP_ESW(esw->dev, merged_eswitch);
+		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	}
 	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest[i].ft = fwd_fdb,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 08a891f9aade..dda63dedaa49 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -387,7 +387,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				id = dst->dest_attr.vport.num;
 				MLX5_SET(dest_format_struct, in_dests,
 					 destination_eswitch_owner_vhca_id_valid,
-					 dst->dest_attr.vport.vhca_id_valid);
+					 !!(dst->dest_attr.vport.flags &
+					    MLX5_FLOW_DEST_VPORT_VHCA_ID));
 				MLX5_SET(dest_format_struct, in_dests,
 					 destination_eswitch_owner_vhca_id,
 					 dst->dest_attr.vport.vhca_id);
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 5660f07d3be0..25ffd8018b72 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -86,6 +86,10 @@ struct mlx5_flow_spec {
 	u32  match_value[MLX5_ST_SZ_DW(fte_match_param)];
 };
 
+enum {
+	MLX5_FLOW_DEST_VPORT_VHCA_ID      = BIT(0),
+};
+
 struct mlx5_flow_destination {
 	enum mlx5_flow_destination_type	type;
 	union {
@@ -96,7 +100,7 @@ struct mlx5_flow_destination {
 		struct {
 			u16		num;
 			u16		vhca_id;
-			bool		vhca_id_valid;
+			u8		flags;
 		} vport;
 	};
 };
-- 
cgit v1.2.3


From a2c6162b12f15fbbbe38d0eb3a38186bcfc79c0f Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Mon, 10 Dec 2018 13:15:16 -0800
Subject: net/mlx5: Support extended destination format in flow steering
 command

Update the flow steering command formatting according to the extended
destination API.
Note that the FW dictates that multi destination FTEs that involve at
least one encap must use the extended destination format, while single
destination ones must use the legacy format.
Using extended destination format requires FW support. Check for its
capabilities and return error if not supported.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 80 +++++++++++++++++++++---
 include/linux/mlx5/fs.h                          |  2 +
 2 files changed, 75 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index dda63dedaa49..c44ccb67c4a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -308,22 +308,68 @@ static int mlx5_cmd_destroy_flow_group(struct mlx5_core_dev *dev,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
+static int mlx5_set_extended_dest(struct mlx5_core_dev *dev,
+				  struct fs_fte *fte, bool *extended_dest)
+{
+	int fw_log_max_fdb_encap_uplink =
+		MLX5_CAP_ESW(dev, log_max_fdb_encap_uplink);
+	int num_fwd_destinations = 0;
+	struct mlx5_flow_rule *dst;
+	int num_encap = 0;
+
+	*extended_dest = false;
+	if (!(fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
+		return 0;
+
+	list_for_each_entry(dst, &fte->node.children, node.list) {
+		if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+			continue;
+		if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
+		    dst->dest_attr.vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID)
+			num_encap++;
+		num_fwd_destinations++;
+	}
+	if (num_fwd_destinations > 1 && num_encap > 0)
+		*extended_dest = true;
+
+	if (*extended_dest && !fw_log_max_fdb_encap_uplink) {
+		mlx5_core_warn(dev, "FW does not support extended destination");
+		return -EOPNOTSUPP;
+	}
+	if (num_encap > (1 << fw_log_max_fdb_encap_uplink)) {
+		mlx5_core_warn(dev, "FW does not support more than %d encaps",
+			       1 << fw_log_max_fdb_encap_uplink);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
 static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 			    int opmod, int modify_mask,
 			    struct mlx5_flow_table *ft,
 			    unsigned group_id,
 			    struct fs_fte *fte)
 {
-	unsigned int inlen = MLX5_ST_SZ_BYTES(set_fte_in) +
-		fte->dests_size * MLX5_ST_SZ_BYTES(dest_format_struct);
 	u32 out[MLX5_ST_SZ_DW(set_fte_out)] = {0};
+	bool extended_dest = false;
 	struct mlx5_flow_rule *dst;
 	void *in_flow_context, *vlan;
 	void *in_match_value;
+	unsigned int inlen;
+	int dst_cnt_size;
 	void *in_dests;
 	u32 *in;
 	int err;
 
+	if (mlx5_set_extended_dest(dev, fte, &extended_dest))
+		return -EOPNOTSUPP;
+
+	if (!extended_dest)
+		dst_cnt_size = MLX5_ST_SZ_BYTES(dest_format_struct);
+	else
+		dst_cnt_size = MLX5_ST_SZ_BYTES(extended_dest_format);
+
+	inlen = MLX5_ST_SZ_BYTES(set_fte_in) + fte->dests_size * dst_cnt_size;
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -343,9 +389,20 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(flow_context, in_flow_context, group_id, group_id);
 
 	MLX5_SET(flow_context, in_flow_context, flow_tag, fte->action.flow_tag);
-	MLX5_SET(flow_context, in_flow_context, action, fte->action.action);
-	MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
-		 fte->action.reformat_id);
+	MLX5_SET(flow_context, in_flow_context, extended_destination,
+		 extended_dest);
+	if (extended_dest) {
+		u32 action;
+
+		action = fte->action.action &
+			~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+		MLX5_SET(flow_context, in_flow_context, action, action);
+	} else {
+		MLX5_SET(flow_context, in_flow_context, action,
+			 fte->action.action);
+		MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
+			 fte->action.reformat_id);
+	}
 	MLX5_SET(flow_context, in_flow_context, modify_header_id,
 		 fte->action.modify_id);
 
@@ -392,6 +449,15 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				MLX5_SET(dest_format_struct, in_dests,
 					 destination_eswitch_owner_vhca_id,
 					 dst->dest_attr.vport.vhca_id);
+				if (extended_dest) {
+					MLX5_SET(dest_format_struct, in_dests,
+						 packet_reformat,
+						 !!(dst->dest_attr.vport.flags &
+						    MLX5_FLOW_DEST_VPORT_REFORMAT_ID));
+					MLX5_SET(extended_dest_format, in_dests,
+						 packet_reformat_id,
+						 dst->dest_attr.vport.reformat_id);
+				}
 				break;
 			default:
 				id = dst->dest_attr.tir_num;
@@ -400,7 +466,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 			MLX5_SET(dest_format_struct, in_dests, destination_type,
 				 type);
 			MLX5_SET(dest_format_struct, in_dests, destination_id, id);
-			in_dests += MLX5_ST_SZ_BYTES(dest_format_struct);
+			in_dests += dst_cnt_size;
 			list_size++;
 		}
 
@@ -421,7 +487,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 
 			MLX5_SET(flow_counter_list, in_dests, flow_counter_id,
 				 dst->dest_attr.counter_id);
-			in_dests += MLX5_ST_SZ_BYTES(dest_format_struct);
+			in_dests += dst_cnt_size;
 			list_size++;
 		}
 		if (list_size > max_list_size) {
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 25ffd8018b72..9df51da04621 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -88,6 +88,7 @@ struct mlx5_flow_spec {
 
 enum {
 	MLX5_FLOW_DEST_VPORT_VHCA_ID      = BIT(0),
+	MLX5_FLOW_DEST_VPORT_REFORMAT_ID  = BIT(1),
 };
 
 struct mlx5_flow_destination {
@@ -100,6 +101,7 @@ struct mlx5_flow_destination {
 		struct {
 			u16		num;
 			u16		vhca_id;
+			u32		reformat_id;
 			u8		flags;
 		} vport;
 	};
-- 
cgit v1.2.3


From 6c22a11957f46ca7e9b8db20ac7c6b05441c55ed Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Mon, 10 Dec 2018 13:15:17 -0800
Subject: net/mlx5: Remove the get protocol device interface entry

This isn't used anywhere across the mlx5 driver stack,
remove it.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c     | 22 ----------------------
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |  8 --------
 include/linux/mlx5/driver.h                       |  2 --
 3 files changed, 32 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index d2ed14bc37c3..ebc046fa97d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -256,28 +256,6 @@ void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol)
 	mutex_unlock(&mlx5_intf_mutex);
 }
 
-void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol)
-{
-	struct mlx5_priv *priv = &mdev->priv;
-	struct mlx5_device_context *dev_ctx;
-	unsigned long flags;
-	void *result = NULL;
-
-	spin_lock_irqsave(&priv->ctx_lock, flags);
-
-	list_for_each_entry(dev_ctx, &mdev->priv.ctx_list, list)
-		if ((dev_ctx->intf->protocol == protocol) &&
-		    dev_ctx->intf->get_dev) {
-			result = dev_ctx->intf->get_dev(dev_ctx->context);
-			break;
-		}
-
-	spin_unlock_irqrestore(&priv->ctx_lock, flags);
-
-	return result;
-}
-EXPORT_SYMBOL(mlx5_get_protocol_dev);
-
 /* Must be called with intf_mutex held */
 void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 56bc41b1c31f..a43092de3cc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5160,20 +5160,12 @@ static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 	kfree(ppriv);
 }
 
-static void *mlx5e_get_netdev(void *vpriv)
-{
-	struct mlx5e_priv *priv = vpriv;
-
-	return priv->netdev;
-}
-
 static struct mlx5_interface mlx5e_interface = {
 	.add       = mlx5e_add,
 	.remove    = mlx5e_remove,
 	.attach    = mlx5e_attach,
 	.detach    = mlx5e_detach,
 	.protocol  = MLX5_INTERFACE_PROTOCOL_ETH,
-	.get_dev   = mlx5e_get_netdev,
 };
 
 void mlx5e_init(void)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 584d8a5df7eb..cc29e880c733 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1004,12 +1004,10 @@ struct mlx5_interface {
 	void			(*remove)(struct mlx5_core_dev *dev, void *context);
 	int			(*attach)(struct mlx5_core_dev *dev, void *context);
 	void			(*detach)(struct mlx5_core_dev *dev, void *context);
-	void *                  (*get_dev)(void *context);
 	int			protocol;
 	struct list_head	list;
 };
 
-void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol);
 int mlx5_register_interface(struct mlx5_interface *intf);
 void mlx5_unregister_interface(struct mlx5_interface *intf);
 int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb);
-- 
cgit v1.2.3


From 7a5725ddc6e18aab61f647c0996d3b7eb03ff5cb Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Mon, 10 Dec 2018 11:17:50 -0800
Subject: bpf: clean up bpf_prog_get_info_by_fd()

info.nr_jited_ksyms and info.nr_jited_func_lens cannot be 0 in these two
statements, so we don't need to check them.

Signed-off-by: Song Liu <songliubraving@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/syscall.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 19c88cff7880..a99a23bf5910 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2209,7 +2209,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 
 	ulen = info.nr_jited_ksyms;
 	info.nr_jited_ksyms = prog->aux->func_cnt ? : 1;
-	if (info.nr_jited_ksyms && ulen) {
+	if (ulen) {
 		if (bpf_dump_raw_ok()) {
 			unsigned long ksym_addr;
 			u64 __user *user_ksyms;
@@ -2240,7 +2240,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 
 	ulen = info.nr_jited_func_lens;
 	info.nr_jited_func_lens = prog->aux->func_cnt ? : 1;
-	if (info.nr_jited_func_lens && ulen) {
+	if (ulen) {
 		if (bpf_dump_raw_ok()) {
 			u32 __user *user_lens;
 			u32 func_len, i;
-- 
cgit v1.2.3


From 11d8b82d2222cade12caad2c125f23023777dcbc Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 10 Dec 2018 14:14:08 -0800
Subject: bpf: rename *_info_cnt to nr_*_info in bpf_prog_info

In uapi bpf.h, currently we have the following fields in
the struct bpf_prog_info:
	__u32 func_info_cnt;
	__u32 line_info_cnt;
	__u32 jited_line_info_cnt;
The above field names "func_info_cnt" and "line_info_cnt"
also appear in union bpf_attr for program loading.

The original intention is to keep the names the same
between bpf_prog_info and bpf_attr
so it will imply what we returned to user space will be
the same as what the user space passed to the kernel.

Such a naming convention in bpf_prog_info is not consistent
with other fields like:
        __u32 nr_jited_ksyms;
        __u32 nr_jited_func_lens;

This patch made this adjustment so in bpf_prog_info
newly introduced *_info_cnt becomes nr_*_info.

Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h |  6 +++---
 kernel/bpf/syscall.c     | 38 +++++++++++++++++++-------------------
 2 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1bee1135866a..f943ed803309 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2696,11 +2696,11 @@ struct bpf_prog_info {
 	__u32 btf_id;
 	__u32 func_info_rec_size;
 	__aligned_u64 func_info;
-	__u32 func_info_cnt;
-	__u32 line_info_cnt;
+	__u32 nr_func_info;
+	__u32 nr_line_info;
 	__aligned_u64 line_info;
 	__aligned_u64 jited_line_info;
-	__u32 jited_line_info_cnt;
+	__u32 nr_jited_line_info;
 	__u32 line_info_rec_size;
 	__u32 jited_line_info_rec_size;
 } __attribute__((aligned(8)));
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a99a23bf5910..5745c7837621 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2055,15 +2055,15 @@ static int set_info_rec_size(struct bpf_prog_info *info)
 	 * _rec_size back to the info.
 	 */
 
-	if ((info->func_info_cnt || info->func_info_rec_size) &&
+	if ((info->nr_func_info || info->func_info_rec_size) &&
 	    info->func_info_rec_size != sizeof(struct bpf_func_info))
 		return -EINVAL;
 
-	if ((info->line_info_cnt || info->line_info_rec_size) &&
+	if ((info->nr_line_info || info->line_info_rec_size) &&
 	    info->line_info_rec_size != sizeof(struct bpf_line_info))
 		return -EINVAL;
 
-	if ((info->jited_line_info_cnt || info->jited_line_info_rec_size) &&
+	if ((info->nr_jited_line_info || info->jited_line_info_rec_size) &&
 	    info->jited_line_info_rec_size != sizeof(__u64))
 		return -EINVAL;
 
@@ -2125,9 +2125,9 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		info.xlated_prog_len = 0;
 		info.nr_jited_ksyms = 0;
 		info.nr_jited_func_lens = 0;
-		info.func_info_cnt = 0;
-		info.line_info_cnt = 0;
-		info.jited_line_info_cnt = 0;
+		info.nr_func_info = 0;
+		info.nr_line_info = 0;
+		info.nr_jited_line_info = 0;
 		goto done;
 	}
 
@@ -2268,14 +2268,14 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	if (prog->aux->btf)
 		info.btf_id = btf_id(prog->aux->btf);
 
-	ulen = info.func_info_cnt;
-	info.func_info_cnt = prog->aux->func_info_cnt;
-	if (info.func_info_cnt && ulen) {
+	ulen = info.nr_func_info;
+	info.nr_func_info = prog->aux->func_info_cnt;
+	if (info.nr_func_info && ulen) {
 		if (bpf_dump_raw_ok()) {
 			char __user *user_finfo;
 
 			user_finfo = u64_to_user_ptr(info.func_info);
-			ulen = min_t(u32, info.func_info_cnt, ulen);
+			ulen = min_t(u32, info.nr_func_info, ulen);
 			if (copy_to_user(user_finfo, prog->aux->func_info,
 					 info.func_info_rec_size * ulen))
 				return -EFAULT;
@@ -2284,14 +2284,14 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		}
 	}
 
-	ulen = info.line_info_cnt;
-	info.line_info_cnt = prog->aux->nr_linfo;
-	if (info.line_info_cnt && ulen) {
+	ulen = info.nr_line_info;
+	info.nr_line_info = prog->aux->nr_linfo;
+	if (info.nr_line_info && ulen) {
 		if (bpf_dump_raw_ok()) {
 			__u8 __user *user_linfo;
 
 			user_linfo = u64_to_user_ptr(info.line_info);
-			ulen = min_t(u32, info.line_info_cnt, ulen);
+			ulen = min_t(u32, info.nr_line_info, ulen);
 			if (copy_to_user(user_linfo, prog->aux->linfo,
 					 info.line_info_rec_size * ulen))
 				return -EFAULT;
@@ -2300,18 +2300,18 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		}
 	}
 
-	ulen = info.jited_line_info_cnt;
+	ulen = info.nr_jited_line_info;
 	if (prog->aux->jited_linfo)
-		info.jited_line_info_cnt = prog->aux->nr_linfo;
+		info.nr_jited_line_info = prog->aux->nr_linfo;
 	else
-		info.jited_line_info_cnt = 0;
-	if (info.jited_line_info_cnt && ulen) {
+		info.nr_jited_line_info = 0;
+	if (info.nr_jited_line_info && ulen) {
 		if (bpf_dump_raw_ok()) {
 			__u64 __user *user_linfo;
 			u32 i;
 
 			user_linfo = u64_to_user_ptr(info.jited_line_info);
-			ulen = min_t(u32, info.jited_line_info_cnt, ulen);
+			ulen = min_t(u32, info.nr_jited_line_info, ulen);
 			for (i = 0; i < ulen; i++) {
 				if (put_user((__u64)(long)prog->aux->jited_linfo[i],
 					     &user_linfo[i]))
-- 
cgit v1.2.3


From b4f8623c0cefdfb818f99b3eb3c1e4c7708dd84e Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 10 Dec 2018 14:14:09 -0800
Subject: tools/bpf: sync kernel uapi bpf.h to tools directory

Sync kernel uapi bpf.h "*_info_cnt => nr_*_info"
changes to tools directory.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6ad50b6471d3..620ee1f919cf 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2695,11 +2695,11 @@ struct bpf_prog_info {
 	__u32 btf_id;
 	__u32 func_info_rec_size;
 	__aligned_u64 func_info;
-	__u32 func_info_cnt;
-	__u32 line_info_cnt;
+	__u32 nr_func_info;
+	__u32 nr_line_info;
 	__aligned_u64 line_info;
 	__aligned_u64 jited_line_info;
-	__u32 jited_line_info_cnt;
+	__u32 nr_jited_line_info;
 	__u32 line_info_rec_size;
 	__u32 jited_line_info_rec_size;
 } __attribute__((aligned(8)));
-- 
cgit v1.2.3


From cfc542411bd40ff4f8a70b3d061bd6acdfb05629 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 10 Dec 2018 14:14:10 -0800
Subject: tools/bpf: rename *_info_cnt to nr_*_info

Rename all occurances of *_info_cnt field access
to nr_*_info in tools directory.

The local variables finfo_cnt, linfo_cnt and jited_linfo_cnt
in function do_dump() of tools/bpf/bpftool/prog.c are also
changed to nr_finfo, nr_linfo and nr_jited_linfo to
keep naming convention consistent.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/prog.c               | 48 +++++++++++++--------------
 tools/lib/bpf/bpf_prog_linfo.c         |  4 +--
 tools/testing/selftests/bpf/test_btf.c | 60 +++++++++++++++++-----------------
 3 files changed, 56 insertions(+), 56 deletions(-)

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 9a78ebbcea1d..b73b4e473948 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -425,7 +425,7 @@ static int do_dump(int argc, char **argv)
 {
 	unsigned int finfo_rec_size, linfo_rec_size, jited_linfo_rec_size;
 	void *func_info = NULL, *linfo = NULL, *jited_linfo = NULL;
-	unsigned int finfo_cnt, linfo_cnt = 0, jited_linfo_cnt = 0;
+	unsigned int nr_finfo, nr_linfo = 0, nr_jited_linfo = 0;
 	struct bpf_prog_linfo *prog_linfo = NULL;
 	unsigned long *func_ksyms = NULL;
 	struct bpf_prog_info info = {};
@@ -537,10 +537,10 @@ static int do_dump(int argc, char **argv)
 		}
 	}
 
-	finfo_cnt = info.func_info_cnt;
+	nr_finfo = info.nr_func_info;
 	finfo_rec_size = info.func_info_rec_size;
-	if (finfo_cnt && finfo_rec_size) {
-		func_info = malloc(finfo_cnt * finfo_rec_size);
+	if (nr_finfo && finfo_rec_size) {
+		func_info = malloc(nr_finfo * finfo_rec_size);
 		if (!func_info) {
 			p_err("mem alloc failed");
 			close(fd);
@@ -549,9 +549,9 @@ static int do_dump(int argc, char **argv)
 	}
 
 	linfo_rec_size = info.line_info_rec_size;
-	if (info.line_info_cnt && linfo_rec_size && info.btf_id) {
-		linfo_cnt = info.line_info_cnt;
-		linfo = malloc(linfo_cnt * linfo_rec_size);
+	if (info.nr_line_info && linfo_rec_size && info.btf_id) {
+		nr_linfo = info.nr_line_info;
+		linfo = malloc(nr_linfo * linfo_rec_size);
 		if (!linfo) {
 			p_err("mem alloc failed");
 			close(fd);
@@ -560,13 +560,13 @@ static int do_dump(int argc, char **argv)
 	}
 
 	jited_linfo_rec_size = info.jited_line_info_rec_size;
-	if (info.jited_line_info_cnt &&
+	if (info.nr_jited_line_info &&
 	    jited_linfo_rec_size &&
 	    info.nr_jited_ksyms &&
 	    info.nr_jited_func_lens &&
 	    info.btf_id) {
-		jited_linfo_cnt = info.jited_line_info_cnt;
-		jited_linfo = malloc(jited_linfo_cnt * jited_linfo_rec_size);
+		nr_jited_linfo = info.nr_jited_line_info;
+		jited_linfo = malloc(nr_jited_linfo * jited_linfo_rec_size);
 		if (!jited_linfo) {
 			p_err("mem alloc failed");
 			close(fd);
@@ -582,13 +582,13 @@ static int do_dump(int argc, char **argv)
 	info.nr_jited_ksyms = nr_func_ksyms;
 	info.jited_func_lens = ptr_to_u64(func_lens);
 	info.nr_jited_func_lens = nr_func_lens;
-	info.func_info_cnt = finfo_cnt;
+	info.nr_func_info = nr_finfo;
 	info.func_info_rec_size = finfo_rec_size;
 	info.func_info = ptr_to_u64(func_info);
-	info.line_info_cnt = linfo_cnt;
+	info.nr_line_info = nr_linfo;
 	info.line_info_rec_size = linfo_rec_size;
 	info.line_info = ptr_to_u64(linfo);
-	info.jited_line_info_cnt = jited_linfo_cnt;
+	info.nr_jited_line_info = nr_jited_linfo;
 	info.jited_line_info_rec_size = jited_linfo_rec_size;
 	info.jited_line_info = ptr_to_u64(jited_linfo);
 
@@ -614,9 +614,9 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
-	if (info.func_info_cnt != finfo_cnt) {
-		p_err("incorrect func_info_cnt %d vs. expected %d",
-		      info.func_info_cnt, finfo_cnt);
+	if (info.nr_func_info != nr_finfo) {
+		p_err("incorrect nr_func_info %d vs. expected %d",
+		      info.nr_func_info, nr_finfo);
 		goto err_free;
 	}
 
@@ -630,12 +630,12 @@ static int do_dump(int argc, char **argv)
 		/* kernel.kptr_restrict is set.  No func_info available. */
 		free(func_info);
 		func_info = NULL;
-		finfo_cnt = 0;
+		nr_finfo = 0;
 	}
 
-	if (linfo && info.line_info_cnt != linfo_cnt) {
-		p_err("incorrect line_info_cnt %u vs. expected %u",
-		      info.line_info_cnt, linfo_cnt);
+	if (linfo && info.nr_line_info != nr_linfo) {
+		p_err("incorrect nr_line_info %u vs. expected %u",
+		      info.nr_line_info, nr_linfo);
 		goto err_free;
 	}
 
@@ -645,9 +645,9 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
-	if (jited_linfo && info.jited_line_info_cnt != jited_linfo_cnt) {
-		p_err("incorrect jited_line_info_cnt %u vs. expected %u",
-		      info.jited_line_info_cnt, jited_linfo_cnt);
+	if (jited_linfo && info.nr_jited_line_info != nr_jited_linfo) {
+		p_err("incorrect nr_jited_line_info %u vs. expected %u",
+		      info.nr_jited_line_info, nr_jited_linfo);
 		goto err_free;
 	}
 
@@ -670,7 +670,7 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
-	if (linfo_cnt) {
+	if (nr_linfo) {
 		prog_linfo = bpf_prog_linfo__new(&info);
 		if (!prog_linfo)
 			p_info("error in processing bpf_line_info.  continue without it.");
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index b8af65145408..addd6e9971cc 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -105,7 +105,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	struct bpf_prog_linfo *prog_linfo;
 	__u32 nr_linfo, nr_jited_func;
 
-	nr_linfo = info->line_info_cnt;
+	nr_linfo = info->nr_line_info;
 
 	/*
 	 * Test !info->line_info because the kernel may NULL
@@ -138,7 +138,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	nr_jited_func = info->nr_jited_ksyms;
 	if (!nr_jited_func ||
 	    !info->jited_line_info ||
-	    info->jited_line_info_cnt != nr_linfo ||
+	    info->nr_jited_line_info != nr_linfo ||
 	    info->jited_line_info_rec_size < sizeof(__u64) ||
 	    info->nr_jited_func_lens != nr_jited_func ||
 	    !info->jited_ksyms ||
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 7707273736ac..d4c63316c862 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -2548,9 +2548,9 @@ static int do_test_file(unsigned int test_num)
 		err = -1;
 		goto done;
 	}
-	if (CHECK(info.func_info_cnt != 3,
-		  "incorrect info.func_info_cnt (1st) %d",
-		  info.func_info_cnt)) {
+	if (CHECK(info.nr_func_info != 3,
+		  "incorrect info.nr_func_info (1st) %d",
+		  info.nr_func_info)) {
 		err = -1;
 		goto done;
 	}
@@ -2561,7 +2561,7 @@ static int do_test_file(unsigned int test_num)
 		goto done;
 	}
 
-	func_info = malloc(info.func_info_cnt * rec_size);
+	func_info = malloc(info.nr_func_info * rec_size);
 	if (CHECK(!func_info, "out of memory")) {
 		err = -1;
 		goto done;
@@ -2569,7 +2569,7 @@ static int do_test_file(unsigned int test_num)
 
 	/* reset info to only retrieve func_info related data */
 	memset(&info, 0, sizeof(info));
-	info.func_info_cnt = 3;
+	info.nr_func_info = 3;
 	info.func_info_rec_size = rec_size;
 	info.func_info = ptr_to_u64(func_info);
 
@@ -2580,9 +2580,9 @@ static int do_test_file(unsigned int test_num)
 		err = -1;
 		goto done;
 	}
-	if (CHECK(info.func_info_cnt != 3,
-		  "incorrect info.func_info_cnt (2nd) %d",
-		  info.func_info_cnt)) {
+	if (CHECK(info.nr_func_info != 3,
+		  "incorrect info.nr_func_info (2nd) %d",
+		  info.nr_func_info)) {
 		err = -1;
 		goto done;
 	}
@@ -3544,9 +3544,9 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 		fprintf(stderr, "%s\n", btf_log_buf);
 		return -1;
 	}
-	if (CHECK(info.func_info_cnt != test->func_info_cnt,
-		  "incorrect info.func_info_cnt (1st) %d",
-		  info.func_info_cnt)) {
+	if (CHECK(info.nr_func_info != test->func_info_cnt,
+		  "incorrect info.nr_func_info (1st) %d",
+		  info.nr_func_info)) {
 		return -1;
 	}
 
@@ -3556,16 +3556,16 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 		return -1;
 	}
 
-	if (!info.func_info_cnt)
+	if (!info.nr_func_info)
 		return 0;
 
-	func_info = malloc(info.func_info_cnt * rec_size);
+	func_info = malloc(info.nr_func_info * rec_size);
 	if (CHECK(!func_info, "out of memory"))
 		return -1;
 
 	/* reset info to only retrieve func_info related data */
 	memset(&info, 0, sizeof(info));
-	info.func_info_cnt = test->func_info_cnt;
+	info.nr_func_info = test->func_info_cnt;
 	info.func_info_rec_size = rec_size;
 	info.func_info = ptr_to_u64(func_info);
 	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
@@ -3574,9 +3574,9 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 		err = -1;
 		goto done;
 	}
-	if (CHECK(info.func_info_cnt != test->func_info_cnt,
-		  "incorrect info.func_info_cnt (2nd) %d",
-		  info.func_info_cnt)) {
+	if (CHECK(info.nr_func_info != test->func_info_cnt,
+		  "incorrect info.nr_func_info (2nd) %d",
+		  info.nr_func_info)) {
 		err = -1;
 		goto done;
 	}
@@ -3648,14 +3648,14 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 		nr_jited_func_lens = 1;
 	}
 
-	if (CHECK(info.line_info_cnt != cnt ||
-		  info.jited_line_info_cnt != jited_cnt ||
+	if (CHECK(info.nr_line_info != cnt ||
+		  info.nr_jited_line_info != jited_cnt ||
 		  info.nr_jited_ksyms != nr_jited_ksyms ||
 		  info.nr_jited_func_lens != nr_jited_func_lens ||
-		  (!info.line_info_cnt && info.jited_line_info_cnt),
-		  "info: line_info_cnt:%u(expected:%u) jited_line_info_cnt:%u(expected:%u) nr_jited_ksyms:%u(expected:%u) nr_jited_func_lens:%u(expected:%u)",
-		  info.line_info_cnt, cnt,
-		  info.jited_line_info_cnt, jited_cnt,
+		  (!info.nr_line_info && info.nr_jited_line_info),
+		  "info: nr_line_info:%u(expected:%u) nr_jited_line_info:%u(expected:%u) nr_jited_ksyms:%u(expected:%u) nr_jited_func_lens:%u(expected:%u)",
+		  info.nr_line_info, cnt,
+		  info.nr_jited_line_info, jited_cnt,
 		  info.nr_jited_ksyms, nr_jited_ksyms,
 		  info.nr_jited_func_lens, nr_jited_func_lens)) {
 		err = -1;
@@ -3684,7 +3684,7 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 		err = -1;
 		goto done;
 	}
-	info.line_info_cnt = cnt;
+	info.nr_line_info = cnt;
 	info.line_info_rec_size = rec_size;
 	info.line_info = ptr_to_u64(linfo);
 
@@ -3700,7 +3700,7 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 			goto done;
 		}
 
-		info.jited_line_info_cnt = jited_cnt;
+		info.nr_jited_line_info = jited_cnt;
 		info.jited_line_info_rec_size = jited_rec_size;
 		info.jited_line_info = ptr_to_u64(jited_linfo);
 		info.nr_jited_ksyms = nr_jited_ksyms;
@@ -3717,15 +3717,15 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 	 */
 	if (CHECK(err == -1 ||
 		  !info.line_info ||
-		  info.line_info_cnt != cnt ||
+		  info.nr_line_info != cnt ||
 		  (jited_cnt && !info.jited_line_info) ||
-		  info.jited_line_info_cnt != jited_cnt ||
+		  info.nr_jited_line_info != jited_cnt ||
 		  info.line_info_rec_size != rec_size ||
 		  info.jited_line_info_rec_size != jited_rec_size,
-		  "err:%d errno:%d info: line_info_cnt:%u(expected:%u) jited_line_info_cnt:%u(expected:%u) line_info_rec_size:%u(expected:%u) jited_linfo_rec_size:%u(expected:%u) line_info:%p jited_line_info:%p",
+		  "err:%d errno:%d info: nr_line_info:%u(expected:%u) nr_jited_line_info:%u(expected:%u) line_info_rec_size:%u(expected:%u) jited_linfo_rec_size:%u(expected:%u) line_info:%p jited_line_info:%p",
 		  err, errno,
-		  info.line_info_cnt, cnt,
-		  info.jited_line_info_cnt, jited_cnt,
+		  info.nr_line_info, cnt,
+		  info.nr_jited_line_info, jited_cnt,
 		  info.line_info_rec_size, rec_size,
 		  info.jited_line_info_rec_size, jited_rec_size,
 		  (void *)(long)info.line_info,
-- 
cgit v1.2.3


From ec1366c20721157cc2d077e84d2a062f93175ce5 Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Thu, 25 Oct 2018 21:51:11 +0300
Subject: net/mlx5e: Store eswitch uplink representor state on a dedicated
 struct

Currently only a single field in the representor private structure
is relevant for uplink representors.  As a pre-step to allow adding
additional uplink representor fields, introduce uplink representor
private structure.

This is prepration step towards replacing egdev logic with the
indirect block notification mechanism. This patch doesn't change
any functionality.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Acked-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h | 9 ++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c  | 2 +-
 3 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index a137540b84bf..25a656b50264 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1244,7 +1244,7 @@ mlx5e_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
 	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
 	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
-
+	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
 	int err;
 
 	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
@@ -1258,7 +1258,7 @@ mlx5e_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 		goto err_remove_sqs;
 
 	/* init shared tc flow table */
-	err = mlx5e_tc_esw_init(&rpriv->tc_ht);
+	err = mlx5e_tc_esw_init(&uplink_priv->tc_ht);
 	if (err)
 		goto  err_neigh_cleanup;
 
@@ -1281,7 +1281,7 @@ mlx5e_nic_rep_unload(struct mlx5_eswitch_rep *rep)
 		mlx5e_remove_sqs_fwd_rules(priv);
 
 	/* clean uplink offloaded TC rules, delete shared tc flow table */
-	mlx5e_tc_esw_cleanup(&rpriv->tc_ht);
+	mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht);
 
 	mlx5e_rep_neigh_cleanup(rpriv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 844d32d5c29f..8d39c5c59aeb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -53,13 +53,20 @@ struct mlx5e_neigh_update_table {
 	unsigned long           min_interval; /* jiffies */
 };
 
+struct mlx5_rep_uplink_priv {
+	/* Filters DB - instantiated by the uplink representor and shared by
+	 * the uplink's VFs
+	 */
+	struct rhashtable  tc_ht;
+};
+
 struct mlx5e_rep_priv {
 	struct mlx5_eswitch_rep *rep;
 	struct mlx5e_neigh_update_table neigh_update;
 	struct net_device      *netdev;
 	struct mlx5_flow_handle *vport_rx_rule;
 	struct list_head       vport_sqs_list;
-	struct rhashtable      tc_ht; /* valid for uplink rep */
+	struct mlx5_rep_uplink_priv uplink_priv; /* valid for uplink rep */
 };
 
 static inline
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index a3ff2492646d..42eb6ee37754 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3018,7 +3018,7 @@ static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv)
 
 	if (MLX5_VPORT_MANAGER(priv->mdev) && esw->mode == SRIOV_OFFLOADS) {
 		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-		return &uplink_rpriv->tc_ht;
+		return &uplink_rpriv->uplink_priv.tc_ht;
 	} else
 		return &priv->fs.tc.ht;
 }
-- 
cgit v1.2.3


From f5bc2c5de1015caf7e49b0bf9e7e97077736045a Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Sun, 28 Oct 2018 08:34:51 +0200
Subject: net/mlx5e: Support TC indirect block notifications for eswitch uplink
 reprs

Towards using this mechanism as the means to offload tunnel decap rules
set on SW tunnel devices instead of egdev, add the supporting structures
and functions.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 184 +++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h |  13 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c  |  10 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h  |   3 +
 4 files changed, 210 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 25a656b50264..3aab3ce9119d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -49,6 +49,15 @@
 
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
+struct mlx5e_rep_indr_block_priv {
+	struct net_device *netdev;
+	struct mlx5e_rep_priv *rpriv;
+
+	struct list_head list;
+};
+
+static void mlx5e_rep_indr_unregister_block(struct net_device *netdev);
+
 static void mlx5e_rep_get_drvinfo(struct net_device *dev,
 				  struct ethtool_drvinfo *drvinfo)
 {
@@ -518,6 +527,166 @@ static void mlx5e_rep_neigh_update(struct work_struct *work)
 	neigh_release(n);
 }
 
+static struct mlx5e_rep_indr_block_priv *
+mlx5e_rep_indr_block_priv_lookup(struct mlx5e_rep_priv *rpriv,
+				 struct net_device *netdev)
+{
+	struct mlx5e_rep_indr_block_priv *cb_priv;
+
+	/* All callback list access should be protected by RTNL. */
+	ASSERT_RTNL();
+
+	list_for_each_entry(cb_priv,
+			    &rpriv->uplink_priv.tc_indr_block_priv_list,
+			    list)
+		if (cb_priv->netdev == netdev)
+			return cb_priv;
+
+	return NULL;
+}
+
+static void mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5e_rep_indr_block_priv *cb_priv, *temp;
+	struct list_head *head = &rpriv->uplink_priv.tc_indr_block_priv_list;
+
+	list_for_each_entry_safe(cb_priv, temp, head, list) {
+		mlx5e_rep_indr_unregister_block(cb_priv->netdev);
+		kfree(cb_priv);
+	}
+}
+
+static int
+mlx5e_rep_indr_offload(struct net_device *netdev,
+		       struct tc_cls_flower_offload *flower,
+		       struct mlx5e_rep_indr_block_priv *indr_priv)
+{
+	return -EOPNOTSUPP;
+}
+
+static int mlx5e_rep_indr_setup_block_cb(enum tc_setup_type type,
+					 void *type_data, void *indr_priv)
+{
+	struct mlx5e_rep_indr_block_priv *priv = indr_priv;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return mlx5e_rep_indr_offload(priv->netdev, type_data, priv);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+mlx5e_rep_indr_setup_tc_block(struct net_device *netdev,
+			      struct mlx5e_rep_priv *rpriv,
+			      struct tc_block_offload *f)
+{
+	struct mlx5e_rep_indr_block_priv *indr_priv;
+	int err = 0;
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
+		if (indr_priv)
+			return -EEXIST;
+
+		indr_priv = kmalloc(sizeof(*indr_priv), GFP_KERNEL);
+		if (!indr_priv)
+			return -ENOMEM;
+
+		indr_priv->netdev = netdev;
+		indr_priv->rpriv = rpriv;
+		list_add(&indr_priv->list,
+			 &rpriv->uplink_priv.tc_indr_block_priv_list);
+
+		err = tcf_block_cb_register(f->block,
+					    mlx5e_rep_indr_setup_block_cb,
+					    netdev, indr_priv, f->extack);
+		if (err) {
+			list_del(&indr_priv->list);
+			kfree(indr_priv);
+		}
+
+		return err;
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block,
+					mlx5e_rep_indr_setup_block_cb,
+					netdev);
+		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
+		if (indr_priv) {
+			list_del(&indr_priv->list);
+			kfree(indr_priv);
+		}
+
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static
+int mlx5e_rep_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
+			       enum tc_setup_type type, void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return mlx5e_rep_indr_setup_tc_block(netdev, cb_priv,
+						      type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv,
+					 struct net_device *netdev)
+{
+	int err;
+
+	err = __tc_indr_block_cb_register(netdev, rpriv,
+					  mlx5e_rep_indr_setup_tc_cb,
+					  netdev);
+	if (err) {
+		struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+
+		mlx5_core_err(priv->mdev, "Failed to register remote block notifier for %s err=%d\n",
+			      netdev_name(netdev), err);
+	}
+	return err;
+}
+
+static void mlx5e_rep_indr_unregister_block(struct net_device *netdev)
+{
+	__tc_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_tc_cb,
+				      netdev);
+}
+
+static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb,
+					 unsigned long event, void *ptr)
+{
+	struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv,
+						     uplink_priv.netdevice_nb);
+	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+	if (!mlx5e_tc_tun_device_to_offload(priv, netdev))
+		return NOTIFY_OK;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		mlx5e_rep_indr_register_block(rpriv, netdev);
+		break;
+	case NETDEV_UNREGISTER:
+		mlx5e_rep_indr_unregister_block(netdev);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
 static struct mlx5e_neigh_hash_entry *
 mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
 			     struct mlx5e_neigh *m_neigh);
@@ -1262,8 +1431,19 @@ mlx5e_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	if (err)
 		goto  err_neigh_cleanup;
 
+	/* init indirect block notifications */
+	INIT_LIST_HEAD(&uplink_priv->tc_indr_block_priv_list);
+	uplink_priv->netdevice_nb.notifier_call = mlx5e_nic_rep_netdevice_event;
+	err = register_netdevice_notifier(&uplink_priv->netdevice_nb);
+	if (err) {
+		mlx5_core_err(priv->mdev, "Failed to register netdev notifier\n");
+		goto err_indirect_block_cleanup;
+	}
+
 	return 0;
 
+err_indirect_block_cleanup:
+	mlx5e_tc_esw_cleanup(&uplink_priv->tc_ht);
 err_neigh_cleanup:
 	mlx5e_rep_neigh_cleanup(rpriv);
 err_remove_sqs:
@@ -1280,6 +1460,10 @@ mlx5e_nic_rep_unload(struct mlx5_eswitch_rep *rep)
 	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
 		mlx5e_remove_sqs_fwd_rules(priv);
 
+	/* clean indirect TC block notifications */
+	unregister_netdevice_notifier(&rpriv->uplink_priv.netdevice_nb);
+	mlx5e_rep_indr_clean_block_privs(rpriv);
+
 	/* clean uplink offloaded TC rules, delete shared tc flow table */
 	mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 8d39c5c59aeb..c078c6703dc7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -58,6 +58,19 @@ struct mlx5_rep_uplink_priv {
 	 * the uplink's VFs
 	 */
 	struct rhashtable  tc_ht;
+
+	/* indirect block callbacks are invoked on bind/unbind events
+	 * on registered higher level devices (e.g. tunnel devices)
+	 *
+	 * tc_indr_block_cb_priv_list is used to lookup indirect callback
+	 * private data
+	 *
+	 * netdevice_nb is the netdev events notifier - used to register
+	 * tunnel devices for block events
+	 *
+	 */
+	struct list_head	    tc_indr_block_priv_list;
+	struct notifier_block	    netdevice_nb;
 };
 
 struct mlx5e_rep_priv {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 42eb6ee37754..cb5bd3eaf738 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2704,6 +2704,16 @@ out:
 	return err;
 }
 
+bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
+				    struct net_device *netdev)
+{
+	if (netif_is_vxlan(netdev) &&
+	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
+		return true;
+
+	return false;
+}
+
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct ip_tunnel_info *tun_info,
 			      struct net_device *mirred_dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 49436bf3b80a..378507988a32 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -70,6 +70,9 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe);
 
 int mlx5e_tc_num_filters(struct mlx5e_priv *priv);
 
+bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
+				    struct net_device *netdev);
+
 #else /* CONFIG_MLX5_ESWITCH */
 static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}
-- 
cgit v1.2.3


From 71d82d2a90327c9c816e65471b7859b601993f89 Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Sun, 28 Oct 2018 09:14:50 +0200
Subject: net/mlx5e: Provide the TC filter netdev as parameter to flower
 callbacks

Currently the driver controls flower filters that are installed on its
devices. However, with the introduction of the indirect block
notifications platform the driver may receive control events for filters
that are installed on higher level net devices (e.g. tunnel devices).
Therefore, the driver filter control API will not be able to implicitly
assume the filter's net device.

Explicitly specify the filter's net device, no functional change

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 9 ++++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  | 9 ++++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c   | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h   | 6 +++---
 4 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 06b1c0172a7b..88116a4750b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3386,11 +3386,14 @@ static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
 {
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		return mlx5e_configure_flower(priv, cls_flower, flags);
+		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
+					      flags);
 	case TC_CLSFLOWER_DESTROY:
-		return mlx5e_delete_flower(priv, cls_flower, flags);
+		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
+					   flags);
 	case TC_CLSFLOWER_STATS:
-		return mlx5e_stats_flower(priv, cls_flower, flags);
+		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
+					  flags);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 3aab3ce9119d..ab9c7ec77520 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1007,11 +1007,14 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
 {
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		return mlx5e_configure_flower(priv, cls_flower, flags);
+		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
+					      flags);
 	case TC_CLSFLOWER_DESTROY:
-		return mlx5e_delete_flower(priv, cls_flower, flags);
+		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
+					   flags);
 	case TC_CLSFLOWER_STATS:
-		return mlx5e_stats_flower(priv, cls_flower, flags);
+		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
+					  flags);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index cb5bd3eaf738..b614513df127 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3178,7 +3178,7 @@ mlx5e_tc_add_flow(struct mlx5e_priv *priv,
 	return err;
 }
 
-int mlx5e_configure_flower(struct mlx5e_priv *priv,
+int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			   struct tc_cls_flower_offload *f, int flags)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
@@ -3224,7 +3224,7 @@ static bool same_flow_direction(struct mlx5e_tc_flow *flow, int flags)
 	return false;
 }
 
-int mlx5e_delete_flower(struct mlx5e_priv *priv,
+int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			struct tc_cls_flower_offload *f, int flags)
 {
 	struct rhashtable *tc_ht = get_tc_ht(priv);
@@ -3243,7 +3243,7 @@ int mlx5e_delete_flower(struct mlx5e_priv *priv,
 	return 0;
 }
 
-int mlx5e_stats_flower(struct mlx5e_priv *priv,
+int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		       struct tc_cls_flower_offload *f, int flags)
 {
 	struct rhashtable *tc_ht = get_tc_ht(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 378507988a32..004e679a4f53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -51,12 +51,12 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv);
 int mlx5e_tc_esw_init(struct rhashtable *tc_ht);
 void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht);
 
-int mlx5e_configure_flower(struct mlx5e_priv *priv,
+int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			   struct tc_cls_flower_offload *f, int flags);
-int mlx5e_delete_flower(struct mlx5e_priv *priv,
+int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			struct tc_cls_flower_offload *f, int flags);
 
-int mlx5e_stats_flower(struct mlx5e_priv *priv,
+int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		       struct tc_cls_flower_offload *f, int flags);
 
 struct mlx5e_encap_entry;
-- 
cgit v1.2.3


From d11afc2600377c6775abcbc1fd410f199c5bf458 Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Sun, 28 Oct 2018 10:46:34 +0200
Subject: net/mlx5e: Propagate the filter's net device to mlx5e structures

Propagate the filter's net_device parameter to the tc flower parsed
attributes structure so that it can later be used in tunnel decap
offloading sequences.

Pre-step for replacing egdev logic with the indirect block
notification mechanism.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 26 ++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b614513df127..3271eda8098b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -96,6 +96,7 @@ struct mlx5e_tc_flow {
 
 struct mlx5e_tc_flow_parse_attr {
 	struct ip_tunnel_info tun_info;
+	struct net_device *filter_dev;
 	struct mlx5_flow_spec spec;
 	int num_mod_hdr_actions;
 	void *mod_hdr_actions;
@@ -3054,10 +3055,6 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size,
 	flow->flags = flow_flags;
 	flow->priv = priv;
 
-	err = parse_cls_flower(priv, flow, &parse_attr->spec, f);
-	if (err)
-		goto err_free;
-
 	*__flow = flow;
 	*__parse_attr = parse_attr;
 
@@ -3073,6 +3070,7 @@ static int
 mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 		   struct tc_cls_flower_offload *f,
 		   u16 flow_flags,
+		   struct net_device *filter_dev,
 		   struct mlx5e_tc_flow **__flow)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
@@ -3086,6 +3084,11 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 			       &parse_attr, &flow);
 	if (err)
 		goto out;
+	parse_attr->filter_dev = filter_dev;
+	flow->esw_attr->parse_attr = parse_attr;
+	err = parse_cls_flower(flow->priv, flow, &parse_attr->spec, f);
+	if (err)
+		goto err_free;
 
 	flow->esw_attr->chain = f->common.chain_index;
 	flow->esw_attr->prio = TC_H_MAJ(f->common.prio) >> 16;
@@ -3116,6 +3119,7 @@ static int
 mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 		   struct tc_cls_flower_offload *f,
 		   u16 flow_flags,
+		   struct net_device *filter_dev,
 		   struct mlx5e_tc_flow **__flow)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
@@ -3134,6 +3138,11 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto out;
 
+	parse_attr->filter_dev = filter_dev;
+	err = parse_cls_flower(flow->priv, flow, &parse_attr->spec, f);
+	if (err)
+		goto err_free;
+
 	err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow, extack);
 	if (err)
 		goto err_free;
@@ -3159,6 +3168,7 @@ static int
 mlx5e_tc_add_flow(struct mlx5e_priv *priv,
 		  struct tc_cls_flower_offload *f,
 		  int flags,
+		  struct net_device *filter_dev,
 		  struct mlx5e_tc_flow **flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -3171,9 +3181,11 @@ mlx5e_tc_add_flow(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 
 	if (esw && esw->mode == SRIOV_OFFLOADS)
-		err = mlx5e_add_fdb_flow(priv, f, flow_flags, flow);
+		err = mlx5e_add_fdb_flow(priv, f, flow_flags,
+					 filter_dev, flow);
 	else
-		err = mlx5e_add_nic_flow(priv, f, flow_flags, flow);
+		err = mlx5e_add_nic_flow(priv, f, flow_flags,
+					 filter_dev, flow);
 
 	return err;
 }
@@ -3196,7 +3208,7 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	err = mlx5e_tc_add_flow(priv, f, flags, &flow);
+	err = mlx5e_tc_add_flow(priv, f, flags, dev, &flow);
 	if (err)
 		goto out;
 
-- 
cgit v1.2.3


From ef381359e3a81422cee85ddee1f7dc3ac90f3c38 Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Sun, 28 Oct 2018 13:03:54 +0200
Subject: net/mlx5e: Replace egdev with indirect block notifications

Use TC indirect block notifications to offload filters that
are configured on higher level device interfaces (e.g. tunnel
devices). This mechanism replaces the current egdev implementation.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 47 +++++++++++-------------
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c  | 14 +++++++
 2 files changed, 36 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index ab9c7ec77520..5cac4de435c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -561,7 +561,27 @@ mlx5e_rep_indr_offload(struct net_device *netdev,
 		       struct tc_cls_flower_offload *flower,
 		       struct mlx5e_rep_indr_block_priv *indr_priv)
 {
-	return -EOPNOTSUPP;
+	int err = 0;
+	struct mlx5e_priv *priv = netdev_priv(indr_priv->rpriv->netdev);
+
+	switch (flower->command) {
+	case TC_CLSFLOWER_REPLACE:
+		err = mlx5e_configure_flower(netdev, priv,
+					     flower, MLX5E_TC_EGRESS);
+		break;
+	case TC_CLSFLOWER_DESTROY:
+		err = mlx5e_delete_flower(netdev, priv,
+					  flower, MLX5E_TC_EGRESS);
+		break;
+	case TC_CLSFLOWER_STATS:
+		err = mlx5e_stats_flower(netdev, priv,
+					 flower, MLX5E_TC_EGRESS);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
 }
 
 static int mlx5e_rep_indr_setup_block_cb(enum tc_setup_type type,
@@ -1020,19 +1040,6 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
 	}
 }
 
-static int mlx5e_rep_setup_tc_cb_egdev(enum tc_setup_type type, void *type_data,
-				       void *cb_priv)
-{
-	struct mlx5e_priv *priv = cb_priv;
-
-	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_EGRESS);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 				 void *cb_priv)
 {
@@ -1516,24 +1523,16 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 
 	uplink_rpriv = mlx5_eswitch_get_uplink_priv(dev->priv.eswitch, REP_ETH);
 	upriv = netdev_priv(uplink_rpriv->netdev);
-	err = tc_setup_cb_egdev_register(netdev, mlx5e_rep_setup_tc_cb_egdev,
-					 upriv);
-	if (err)
-		goto err_neigh_cleanup;
 
 	err = register_netdev(netdev);
 	if (err) {
 		pr_warn("Failed to register representor netdev for vport %d\n",
 			rep->vport);
-		goto err_egdev_cleanup;
+		goto err_neigh_cleanup;
 	}
 
 	return 0;
 
-err_egdev_cleanup:
-	tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev,
-				     upriv);
-
 err_neigh_cleanup:
 	mlx5e_rep_neigh_cleanup(rpriv);
 
@@ -1560,8 +1559,6 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	uplink_rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch,
 						    REP_ETH);
 	upriv = netdev_priv(uplink_rpriv->netdev);
-	tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev,
-				     upriv);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_detach_netdev(priv);
 	mlx5e_destroy_netdev(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3271eda8098b..6ca94a2f167f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2906,6 +2906,13 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			struct net_device *out_dev;
 
 			out_dev = tcf_mirred_dev(a);
+			if (!out_dev) {
+				/* out_dev is NULL when filters with
+				 * non-existing mirred device are replayed to
+				 * the driver.
+				 */
+				return -EINVAL;
+			}
 
 			if (attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) {
 				NL_SET_ERR_MSG_MOD(extack,
@@ -2932,6 +2939,13 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 					  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 					  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 				/* attr->out_rep is resolved when we handle encap */
+			} else if (parse_attr->filter_dev != priv->netdev) {
+				/* All mlx5 devices are called to configure
+				 * high level device filters. Therefore, the
+				 * *attempt* to  install a filter on invalid
+				 * eswitch should not trigger an explicit error
+				 */
+				return -EINVAL;
 			} else {
 				NL_SET_ERR_MSG_MOD(extack,
 						   "devices are not on same switch HW, can't offload forwarding");
-- 
cgit v1.2.3


From ea7162ac3a33a44a7bb0b5793057015d25617e68 Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Wed, 14 Nov 2018 15:41:50 +0200
Subject: net/mlx5e: Refactor VXLAN tunnel encap offloading code

Separates the vxlan header encap logic from the general ipv4/6
encapsulation methods, thus allowing the common IP encap/decap code to
branch in downstream patch to multiple IP tunnels.

Code refactoring with no functional change.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 189 +++++++++---------------
 1 file changed, 70 insertions(+), 119 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 6ca94a2f167f..ed04ab8287e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2416,70 +2416,25 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	return 0;
 }
 
-static void gen_vxlan_header_ipv4(struct net_device *out_dev,
-				  char buf[], int encap_size,
-				  unsigned char h_dest[ETH_ALEN],
-				  u8 tos, u8 ttl,
-				  __be32 daddr,
-				  __be32 saddr,
-				  __be16 udp_dst_port,
-				  __be32 vx_vni)
-{
-	struct ethhdr *eth = (struct ethhdr *)buf;
-	struct iphdr  *ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr));
-	struct udphdr *udp = (struct udphdr *)((char *)ip + sizeof(struct iphdr));
-	struct vxlanhdr *vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
-
-	memset(buf, 0, encap_size);
-
-	ether_addr_copy(eth->h_dest, h_dest);
-	ether_addr_copy(eth->h_source, out_dev->dev_addr);
-	eth->h_proto = htons(ETH_P_IP);
-
-	ip->daddr = daddr;
-	ip->saddr = saddr;
-
-	ip->tos = tos;
-	ip->ttl = ttl;
-	ip->protocol = IPPROTO_UDP;
-	ip->version = 0x4;
-	ip->ihl = 0x5;
+static int mlx5e_gen_vxlan_header(char buf[], struct ip_tunnel_key *tun_key)
+{
+	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
+	struct udphdr *udp = (struct udphdr *)(buf);
+	struct vxlanhdr *vxh = (struct vxlanhdr *)
+			       ((char *)udp + sizeof(struct udphdr));
 
-	udp->dest = udp_dst_port;
+	udp->dest = tun_key->tp_dst;
 	vxh->vx_flags = VXLAN_HF_VNI;
-	vxh->vx_vni = vxlan_vni_field(vx_vni);
+	vxh->vx_vni = vxlan_vni_field(tun_id);
+
+	return 0;
 }
 
-static void gen_vxlan_header_ipv6(struct net_device *out_dev,
-				  char buf[], int encap_size,
-				  unsigned char h_dest[ETH_ALEN],
-				  u8 tos, u8 ttl,
-				  struct in6_addr *daddr,
-				  struct in6_addr *saddr,
-				  __be16 udp_dst_port,
-				  __be32 vx_vni)
+static int mlx5e_gen_ip_tunnel_header(char buf[], __u8 *ip_proto,
+				      struct ip_tunnel_key *tun_key)
 {
-	struct ethhdr *eth = (struct ethhdr *)buf;
-	struct ipv6hdr *ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr));
-	struct udphdr *udp = (struct udphdr *)((char *)ip6h + sizeof(struct ipv6hdr));
-	struct vxlanhdr *vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
-
-	memset(buf, 0, encap_size);
-
-	ether_addr_copy(eth->h_dest, h_dest);
-	ether_addr_copy(eth->h_source, out_dev->dev_addr);
-	eth->h_proto = htons(ETH_P_IPV6);
-
-	ip6_flow_hdr(ip6h, tos, 0);
-	/* the HW fills up ipv6 payload len */
-	ip6h->nexthdr     = IPPROTO_UDP;
-	ip6h->hop_limit   = ttl;
-	ip6h->daddr	  = *daddr;
-	ip6h->saddr	  = *saddr;
-
-	udp->dest = udp_dst_port;
-	vxh->vx_flags = VXLAN_HF_VNI;
-	vxh->vx_vni = vxlan_vni_field(vx_vni);
+	*ip_proto = IPPROTO_UDP;
+	return mlx5e_gen_vxlan_header(buf, tun_key);
 }
 
 static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
@@ -2487,13 +2442,17 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 					  struct mlx5e_encap_entry *e)
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	int ipv4_encap_size = ETH_HLEN + sizeof(struct iphdr) + VXLAN_HLEN;
+	int ipv4_encap_size = ETH_HLEN +
+			      sizeof(struct iphdr) +
+			      VXLAN_HLEN;
 	struct ip_tunnel_key *tun_key = &e->tun_info.key;
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
-	u8 nud_state, tos, ttl;
 	char *encap_header;
+	struct ethhdr *eth;
+	u8 nud_state, ttl;
+	struct iphdr *ip;
 	int err;
 
 	if (max_encap_size < ipv4_encap_size) {
@@ -2506,22 +2465,11 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	if (!encap_header)
 		return -ENOMEM;
 
-	switch (e->tunnel_type) {
-	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
-		fl4.flowi4_proto = IPPROTO_UDP;
-		fl4.fl4_dport = tun_key->tp_dst;
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		goto free_encap;
-	}
-
-	tos = tun_key->tos;
-	ttl = tun_key->ttl;
-
+	/* add the IP fields */
 	fl4.flowi4_tos = tun_key->tos;
 	fl4.daddr = tun_key->u.ipv4.dst;
 	fl4.saddr = tun_key->u.ipv4.src;
+	ttl = tun_key->ttl;
 
 	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev,
 				      &fl4, &n, &ttl);
@@ -2536,7 +2484,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
 	e->out_dev = out_dev;
 
-	/* It's importent to add the neigh to the hash table before checking
+	/* It's important to add the neigh to the hash table before checking
 	 * the neigh validity state. So if we'll get a notification, in case the
 	 * neigh changes it's validity state, we would find the relevant neigh
 	 * in the hash.
@@ -2550,18 +2498,27 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	ether_addr_copy(e->h_dest, n->ha);
 	read_unlock_bh(&n->lock);
 
-	switch (e->tunnel_type) {
-	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
-		gen_vxlan_header_ipv4(out_dev, encap_header,
-				      ipv4_encap_size, e->h_dest, tos, ttl,
-				      fl4.daddr,
-				      fl4.saddr, tun_key->tp_dst,
-				      tunnel_id_to_key32(tun_key->tun_id));
-		break;
-	default:
-		err = -EOPNOTSUPP;
+	/* add ethernet header */
+	eth = (struct ethhdr *)encap_header;
+	ether_addr_copy(eth->h_dest, e->h_dest);
+	ether_addr_copy(eth->h_source, out_dev->dev_addr);
+	eth->h_proto = htons(ETH_P_IP);
+
+	/* add ip header */
+	ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr));
+	ip->tos = tun_key->tos;
+	ip->version = 0x4;
+	ip->ihl = 0x5;
+	ip->ttl = ttl;
+	ip->daddr = fl4.daddr;
+	ip->saddr = fl4.saddr;
+
+	/* add tunneling protocol header */
+	err = mlx5e_gen_ip_tunnel_header((char *)ip + sizeof(struct iphdr),
+					 &ip->protocol, tun_key);
+	if (err)
 		goto destroy_neigh_entry;
-	}
+
 	e->encap_size = ipv4_encap_size;
 	e->encap_header = encap_header;
 
@@ -2598,13 +2555,17 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 					  struct mlx5e_encap_entry *e)
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	int ipv6_encap_size = ETH_HLEN + sizeof(struct ipv6hdr) + VXLAN_HLEN;
+	int ipv6_encap_size = ETH_HLEN +
+			      sizeof(struct ipv6hdr) +
+			      VXLAN_HLEN;
 	struct ip_tunnel_key *tun_key = &e->tun_info.key;
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi6 fl6 = {};
-	u8 nud_state, tos, ttl;
+	struct ipv6hdr *ip6h;
 	char *encap_header;
+	struct ethhdr *eth;
+	u8 nud_state, ttl;
 	int err;
 
 	if (max_encap_size < ipv6_encap_size) {
@@ -2617,17 +2578,6 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	if (!encap_header)
 		return -ENOMEM;
 
-	switch (e->tunnel_type) {
-	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
-		fl6.flowi6_proto = IPPROTO_UDP;
-		fl6.fl6_dport = tun_key->tp_dst;
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		goto free_encap;
-	}
-
-	tos = tun_key->tos;
 	ttl = tun_key->ttl;
 
 	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
@@ -2661,18 +2611,25 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	ether_addr_copy(e->h_dest, n->ha);
 	read_unlock_bh(&n->lock);
 
-	switch (e->tunnel_type) {
-	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
-		gen_vxlan_header_ipv6(out_dev, encap_header,
-				      ipv6_encap_size, e->h_dest, tos, ttl,
-				      &fl6.daddr,
-				      &fl6.saddr, tun_key->tp_dst,
-				      tunnel_id_to_key32(tun_key->tun_id));
-		break;
-	default:
-		err = -EOPNOTSUPP;
+	/* add ethernet header */
+	eth = (struct ethhdr *)encap_header;
+	ether_addr_copy(eth->h_dest, e->h_dest);
+	ether_addr_copy(eth->h_source, out_dev->dev_addr);
+	eth->h_proto = htons(ETH_P_IPV6);
+
+	/* add ip header */
+	ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr));
+	ip6_flow_hdr(ip6h, tun_key->tos, 0);
+	/* the HW fills up ipv6 payload len */
+	ip6h->hop_limit   = ttl;
+	ip6h->daddr	  = fl6.daddr;
+	ip6h->saddr	  = fl6.saddr;
+
+	/* add tunneling protocol header */
+	err = mlx5e_gen_ip_tunnel_header((char *)ip6h + sizeof(struct ipv6hdr),
+					 &ip6h->nexthdr, tun_key);
+	if (err)
 		goto destroy_neigh_entry;
-	}
 
 	e->encap_size = ipv6_encap_size;
 	e->encap_header = encap_header;
@@ -2731,17 +2688,11 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	uintptr_t hash_key;
 	bool found = false;
 
-	/* udp dst port must be set */
-	if (!memchr_inv(&key->tp_dst, 0, sizeof(key->tp_dst)))
-		goto vxlan_encap_offload_err;
-
-	/* setting udp src port isn't supported */
-	if (memchr_inv(&key->tp_src, 0, sizeof(key->tp_src))) {
-vxlan_encap_offload_err:
+	if (!MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "must set udp dst port and not set udp src port");
+				   "vxlan HW offloading is not supported");
 		netdev_warn(priv->netdev,
-			    "must set udp dst port and not set udp src port\n");
+			    "vxlan HW offloading is not supported\n");
 		return -EOPNOTSUPP;
 	}
 
-- 
cgit v1.2.3


From 4d70564d1c9e812b83f30c8dc23cd506abfcfc08 Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Wed, 14 Nov 2018 15:41:50 +0200
Subject: net/mlx5e: Refactor VXLAN tunnel decap offloading code

Separates the vxlan header match handling from the matching on the
general fields of ipv4/6 tunnels, thus allowing the common IP tunnel
match code to branch in down stream patch, to multiple IP tunnels.

This patch doesn't add any functionality.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 90 ++++++++++++++-----------
 1 file changed, 51 insertions(+), 39 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index ed04ab8287e9..74823cab1d16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1193,21 +1193,59 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 		mlx5e_tc_del_nic_flow(priv, flow);
 }
 
-static void parse_vxlan_attr(struct mlx5_flow_spec *spec,
-			     struct tc_cls_flower_offload *f)
+static int parse_tunnel_vxlan_attr(struct mlx5e_priv *priv,
+				   struct mlx5_flow_spec *spec,
+				   struct tc_cls_flower_offload *f,
+				   void *headers_c,
+				   void *headers_v)
 {
-	void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-				       outer_headers);
-	void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
-				       outer_headers);
-	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct flow_dissector_key_ports *key =
+		skb_flow_dissector_target(f->dissector,
+					  FLOW_DISSECTOR_KEY_ENC_PORTS,
+					  f->key);
+	struct flow_dissector_key_ports *mask =
+		skb_flow_dissector_target(f->dissector,
+					  FLOW_DISSECTOR_KEY_ENC_PORTS,
+					  f->mask);
+	void *misc_c = MLX5_ADDR_OF(fte_match_param,
+				    spec->match_criteria,
 				    misc_parameters);
-	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+	void *misc_v = MLX5_ADDR_OF(fte_match_param,
+				    spec->match_value,
 				    misc_parameters);
 
+	/* Full udp dst port must be given */
+	if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) ||
+	    memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "VXLAN decap filter must include enc_dst_port condition");
+		netdev_warn(priv->netdev,
+			    "VXLAN decap filter must include enc_dst_port condition\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* udp dst port must be knonwn as a VXLAN port */
+	if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matched UDP port is not registered as a VXLAN port");
+		netdev_warn(priv->netdev,
+			    "UDP port %d is not registered as a VXLAN port\n",
+			    be16_to_cpu(key->dst));
+		return -EOPNOTSUPP;
+	}
+
+	/* dst UDP port is valid here */
 	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol);
 	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP);
 
+	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, ntohs(mask->dst));
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, ntohs(key->dst));
+
+	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport, ntohs(mask->src));
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport, ntohs(key->src));
+
+	/* match on VNI */
 	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
 		struct flow_dissector_key_keyid *key =
 			skb_flow_dissector_target(f->dissector,
@@ -1222,6 +1260,7 @@ static void parse_vxlan_attr(struct mlx5_flow_spec *spec,
 		MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
 			 be32_to_cpu(key->keyid));
 	}
+	return 0;
 }
 
 static int parse_tunnel_attr(struct mlx5e_priv *priv,
@@ -1240,39 +1279,12 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 					  f->key);
 
 	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_PORTS,
-						  f->key);
-		struct flow_dissector_key_ports *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_PORTS,
-						  f->mask);
+		int err = 0;
 
-		/* Full udp dst port must be given */
-		if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
+		err = parse_tunnel_vxlan_attr(priv, spec, f,
+					      headers_c, headers_v);
+		if (err)
 			goto vxlan_match_offload_err;
-
-		if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst)) &&
-		    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
-			parse_vxlan_attr(spec, f);
-		else {
-			NL_SET_ERR_MSG_MOD(extack,
-					   "port isn't an offloaded vxlan udp dport");
-			netdev_warn(priv->netdev,
-				    "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->dst));
-			return -EOPNOTSUPP;
-		}
-
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-			 udp_dport, ntohs(mask->dst));
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-			 udp_dport, ntohs(key->dst));
-
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-			 udp_sport, ntohs(mask->src));
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-			 udp_sport, ntohs(key->src));
 	} else { /* udp dst port must be given */
 vxlan_match_offload_err:
 		NL_SET_ERR_MSG_MOD(extack,
-- 
cgit v1.2.3


From 54c177ca9c6efe5df516eefb886761b89a82eaf0 Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Wed, 14 Nov 2018 15:21:27 +0200
Subject: net/mlx5e: Branch according to classified tunnel type

Currently the tunnel offloading encap/decap methods assumes that VXLAN
is the sole tunneling protocol. Lay the infrastructure for supporting
multiple tunneling protocols by branching according to the tunnel
net device kind.

Encap filters tunnel type is determined according to the egress/mirred
net device. Decap filters classify the tunnel type according to the
filter's ingress net device kind.

Distinguish between the tunnel type as defined by the SW model and
the FW reformat type that specifies the HW operation being made.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h |   2 +
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c  | 160 ++++++++++++++++-------
 2 files changed, 114 insertions(+), 48 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index c078c6703dc7..2c8798332c32 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -149,6 +149,8 @@ struct mlx5e_encap_entry {
 
 	struct net_device *out_dev;
 	int tunnel_type;
+	int tunnel_hlen;
+	int reformat_type;
 	u8 flags;
 	char *encap_header;
 	int encap_size;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 74823cab1d16..7d7f490d8ff1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -79,6 +79,13 @@ enum {
 
 #define MLX5E_TC_MAX_SPLITS 1
 
+enum {
+	MLX5E_TC_TUNNEL_TYPE_UNKNOWN,
+	MLX5E_TC_TUNNEL_TYPE_VXLAN
+};
+
+static int mlx5e_get_tunnel_type(struct net_device *tunnel_dev);
+
 struct mlx5e_tc_flow {
 	struct rhash_head	node;
 	struct mlx5e_priv	*priv;
@@ -677,6 +684,14 @@ static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv,
 	}
 }
 
+static const char *mlx5e_netdev_kind(struct net_device *dev)
+{
+	if (dev->rtnl_link_ops)
+		return dev->rtnl_link_ops->kind;
+	else
+		return "";
+}
+
 static int
 mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 		      struct mlx5e_tc_flow_parse_attr *parse_attr,
@@ -1037,7 +1052,8 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 	struct mlx5e_tc_flow *flow;
 	int err;
 
-	err = mlx5_packet_reformat_alloc(priv->mdev, e->tunnel_type,
+	err = mlx5_packet_reformat_alloc(priv->mdev,
+					 e->reformat_type,
 					 e->encap_size, e->encap_header,
 					 MLX5_FLOW_NAMESPACE_FDB,
 					 &e->encap_id);
@@ -1265,7 +1281,8 @@ static int parse_tunnel_vxlan_attr(struct mlx5e_priv *priv,
 
 static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			     struct mlx5_flow_spec *spec,
-			     struct tc_cls_flower_offload *f)
+			     struct tc_cls_flower_offload *f,
+			     struct net_device *filter_dev)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
 	void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
@@ -1277,20 +1294,28 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 		skb_flow_dissector_target(f->dissector,
 					  FLOW_DISSECTOR_KEY_ENC_CONTROL,
 					  f->key);
+	int tunnel_type;
+	int err = 0;
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
-		int err = 0;
-
+	tunnel_type = mlx5e_get_tunnel_type(filter_dev);
+	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
 		err = parse_tunnel_vxlan_attr(priv, spec, f,
 					      headers_c, headers_v);
-		if (err)
-			goto vxlan_match_offload_err;
-	} else { /* udp dst port must be given */
-vxlan_match_offload_err:
+	} else {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "IP tunnel decap offload supported only for vxlan, must set UDP dport");
+				   "decapsulation offload is not supported");
 		netdev_warn(priv->netdev,
-			    "IP tunnel decap offload supported only for vxlan, must set UDP dport\n");
+			    "decapsulation offload is not supported for %s net device (%d)\n",
+			    mlx5e_netdev_kind(filter_dev), tunnel_type);
+		return -EOPNOTSUPP;
+	}
+
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "failed to parse tunnel attributes");
+		netdev_warn(priv->netdev,
+			    "failed to parse %s tunnel attributes (%d)\n",
+			    mlx5e_netdev_kind(filter_dev), tunnel_type);
 		return -EOPNOTSUPP;
 	}
 
@@ -1395,6 +1420,7 @@ vxlan_match_offload_err:
 static int __parse_cls_flower(struct mlx5e_priv *priv,
 			      struct mlx5_flow_spec *spec,
 			      struct tc_cls_flower_offload *f,
+			      struct net_device *filter_dev,
 			      u8 *match_level)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
@@ -1446,7 +1472,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		switch (key->addr_type) {
 		case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
 		case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
-			if (parse_tunnel_attr(priv, spec, f))
+			if (parse_tunnel_attr(priv, spec, f, filter_dev))
 				return -EOPNOTSUPP;
 			break;
 		default:
@@ -1788,7 +1814,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 static int parse_cls_flower(struct mlx5e_priv *priv,
 			    struct mlx5e_tc_flow *flow,
 			    struct mlx5_flow_spec *spec,
-			    struct tc_cls_flower_offload *f)
+			    struct tc_cls_flower_offload *f,
+			    struct net_device *filter_dev)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct mlx5_core_dev *dev = priv->mdev;
@@ -1798,7 +1825,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 	u8 match_level;
 	int err;
 
-	err = __parse_cls_flower(priv, spec, f, &match_level);
+	err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level);
 
 	if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) {
 		rep = rpriv->rep;
@@ -2443,10 +2470,21 @@ static int mlx5e_gen_vxlan_header(char buf[], struct ip_tunnel_key *tun_key)
 }
 
 static int mlx5e_gen_ip_tunnel_header(char buf[], __u8 *ip_proto,
-				      struct ip_tunnel_key *tun_key)
+				      struct mlx5e_encap_entry *e)
 {
-	*ip_proto = IPPROTO_UDP;
-	return mlx5e_gen_vxlan_header(buf, tun_key);
+	int err = 0;
+	struct ip_tunnel_key *key = &e->tun_info.key;
+
+	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
+		*ip_proto = IPPROTO_UDP;
+		err = mlx5e_gen_vxlan_header(buf, key);
+	} else {
+		pr_warn("mlx5: Cannot generate tunnel header for tunnel type (%d)\n"
+			, e->tunnel_type);
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
 }
 
 static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
@@ -2456,7 +2494,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
 	int ipv4_encap_size = ETH_HLEN +
 			      sizeof(struct iphdr) +
-			      VXLAN_HLEN;
+			      e->tunnel_hlen;
 	struct ip_tunnel_key *tun_key = &e->tun_info.key;
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
@@ -2527,7 +2565,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 
 	/* add tunneling protocol header */
 	err = mlx5e_gen_ip_tunnel_header((char *)ip + sizeof(struct iphdr),
-					 &ip->protocol, tun_key);
+					  &ip->protocol, e);
 	if (err)
 		goto destroy_neigh_entry;
 
@@ -2540,7 +2578,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	err = mlx5_packet_reformat_alloc(priv->mdev, e->tunnel_type,
+	err = mlx5_packet_reformat_alloc(priv->mdev,
+					 e->reformat_type,
 					 ipv4_encap_size, encap_header,
 					 MLX5_FLOW_NAMESPACE_FDB,
 					 &e->encap_id);
@@ -2569,7 +2608,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
 	int ipv6_encap_size = ETH_HLEN +
 			      sizeof(struct ipv6hdr) +
-			      VXLAN_HLEN;
+			      e->tunnel_hlen;
 	struct ip_tunnel_key *tun_key = &e->tun_info.key;
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
@@ -2639,7 +2678,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 
 	/* add tunneling protocol header */
 	err = mlx5e_gen_ip_tunnel_header((char *)ip6h + sizeof(struct ipv6hdr),
-					 &ip6h->nexthdr, tun_key);
+					 &ip6h->nexthdr, e);
 	if (err)
 		goto destroy_neigh_entry;
 
@@ -2652,7 +2691,8 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	err = mlx5_packet_reformat_alloc(priv->mdev, e->tunnel_type,
+	err = mlx5_packet_reformat_alloc(priv->mdev,
+					 e->reformat_type,
 					 ipv6_encap_size, encap_header,
 					 MLX5_FLOW_NAMESPACE_FDB,
 					 &e->encap_id);
@@ -2674,14 +2714,52 @@ out:
 	return err;
 }
 
+static int mlx5e_get_tunnel_type(struct net_device *tunnel_dev)
+{
+	if (netif_is_vxlan(tunnel_dev))
+		return MLX5E_TC_TUNNEL_TYPE_VXLAN;
+	else
+		return MLX5E_TC_TUNNEL_TYPE_UNKNOWN;
+}
+
 bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
 				    struct net_device *netdev)
 {
-	if (netif_is_vxlan(netdev) &&
+	int tunnel_type = mlx5e_get_tunnel_type(netdev);
+
+	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN &&
 	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
 		return true;
+	else
+		return false;
+}
 
-	return false;
+static int mlx5e_init_tunnel_attr(struct net_device *tunnel_dev,
+				  struct mlx5e_priv *priv,
+				  struct mlx5e_encap_entry *e,
+				  struct netlink_ext_ack *extack)
+{
+	e->tunnel_type = mlx5e_get_tunnel_type(tunnel_dev);
+
+	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
+		int dst_port =  be16_to_cpu(e->tun_info.key.tp_dst);
+
+		if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, dst_port)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "vxlan udp dport was not registered with the HW");
+			netdev_warn(priv->netdev,
+				    "%d isn't an offloaded vxlan udp dport\n",
+				    dst_port);
+			return -EOPNOTSUPP;
+		}
+		e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
+		e->tunnel_hlen = VXLAN_HLEN;
+	} else {
+		e->reformat_type = -1;
+		e->tunnel_hlen = -1;
+		return -EOPNOTSUPP;
+	}
+	return 0;
 }
 
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
@@ -2696,28 +2774,9 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct ip_tunnel_key *key = &tun_info->key;
 	struct mlx5e_encap_entry *e;
-	int tunnel_type, err = 0;
 	uintptr_t hash_key;
 	bool found = false;
-
-	if (!MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "vxlan HW offloading is not supported");
-		netdev_warn(priv->netdev,
-			    "vxlan HW offloading is not supported\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->tp_dst)) &&
-	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
-		tunnel_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
-	} else {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "port isn't an offloaded vxlan udp dport");
-		netdev_warn(priv->netdev,
-			    "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->tp_dst));
-		return -EOPNOTSUPP;
-	}
+	int err = 0;
 
 	hash_key = hash_encap_info(key);
 
@@ -2738,7 +2797,10 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 		return -ENOMEM;
 
 	e->tun_info = *tun_info;
-	e->tunnel_type = tunnel_type;
+	err = mlx5e_init_tunnel_attr(mirred_dev, priv, e, extack);
+	if (err)
+		goto out_err;
+
 	INIT_LIST_HEAD(&e->flows);
 
 	if (family == AF_INET)
@@ -3063,7 +3125,8 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 		goto out;
 	parse_attr->filter_dev = filter_dev;
 	flow->esw_attr->parse_attr = parse_attr;
-	err = parse_cls_flower(flow->priv, flow, &parse_attr->spec, f);
+	err = parse_cls_flower(flow->priv, flow, &parse_attr->spec,
+			       f, filter_dev);
 	if (err)
 		goto err_free;
 
@@ -3116,7 +3179,8 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 		goto out;
 
 	parse_attr->filter_dev = filter_dev;
-	err = parse_cls_flower(flow->priv, flow, &parse_attr->spec, f);
+	err = parse_cls_flower(flow->priv, flow, &parse_attr->spec,
+			       f, filter_dev);
 	if (err)
 		goto err_free;
 
-- 
cgit v1.2.3


From 101f4de9dd521c6d06dfdacaa35e506a8db8494b Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Sun, 2 Dec 2018 14:43:27 +0200
Subject: net/mlx5e: Move TC tunnel offloading code to separate source file

Move tunnel offloading related code to a separate source file for better
code maintainability.

Code refactoring with no functional change.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    | 496 ++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.h    |  43 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 500 +--------------------
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h    |   2 -
 6 files changed, 548 insertions(+), 496 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index d499b3d00348..40764d87413a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -30,7 +30,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
 mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
-mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o
 
 #
 # Core extra
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
new file mode 100644
index 000000000000..eaa43477e0ea
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -0,0 +1,496 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#include <net/vxlan.h>
+#include "lib/vxlan.h"
+#include "en/tc_tun.h"
+
+static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
+				   struct net_device *mirred_dev,
+				   struct net_device **out_dev,
+				   struct flowi4 *fl4,
+				   struct neighbour **out_n,
+				   u8 *out_ttl)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5e_rep_priv *uplink_rpriv;
+	struct rtable *rt;
+	struct neighbour *n = NULL;
+
+#if IS_ENABLED(CONFIG_INET)
+	int ret;
+
+	rt = ip_route_output_key(dev_net(mirred_dev), fl4);
+	ret = PTR_ERR_OR_ZERO(rt);
+	if (ret)
+		return ret;
+#else
+	return -EOPNOTSUPP;
+#endif
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	/* if the egress device isn't on the same HW e-switch, we use the uplink */
+	if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev))
+		*out_dev = uplink_rpriv->netdev;
+	else
+		*out_dev = rt->dst.dev;
+
+	if (!(*out_ttl))
+		*out_ttl = ip4_dst_hoplimit(&rt->dst);
+	n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
+	ip_rt_put(rt);
+	if (!n)
+		return -ENOMEM;
+
+	*out_n = n;
+	return 0;
+}
+
+static const char *mlx5e_netdev_kind(struct net_device *dev)
+{
+	if (dev->rtnl_link_ops)
+		return dev->rtnl_link_ops->kind;
+	else
+		return "";
+}
+
+static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
+				   struct net_device *mirred_dev,
+				   struct net_device **out_dev,
+				   struct flowi6 *fl6,
+				   struct neighbour **out_n,
+				   u8 *out_ttl)
+{
+	struct neighbour *n = NULL;
+	struct dst_entry *dst;
+
+#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
+	struct mlx5e_rep_priv *uplink_rpriv;
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	int ret;
+
+	ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst,
+					 fl6);
+	if (ret < 0)
+		return ret;
+
+	if (!(*out_ttl))
+		*out_ttl = ip6_dst_hoplimit(dst);
+
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	/* if the egress device isn't on the same HW e-switch, we use the uplink */
+	if (!switchdev_port_same_parent_id(priv->netdev, dst->dev))
+		*out_dev = uplink_rpriv->netdev;
+	else
+		*out_dev = dst->dev;
+#else
+	return -EOPNOTSUPP;
+#endif
+
+	n = dst_neigh_lookup(dst, &fl6->daddr);
+	dst_release(dst);
+	if (!n)
+		return -ENOMEM;
+
+	*out_n = n;
+	return 0;
+}
+
+static int mlx5e_gen_vxlan_header(char buf[], struct ip_tunnel_key *tun_key)
+{
+	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
+	struct udphdr *udp = (struct udphdr *)(buf);
+	struct vxlanhdr *vxh = (struct vxlanhdr *)
+			       ((char *)udp + sizeof(struct udphdr));
+
+	udp->dest = tun_key->tp_dst;
+	vxh->vx_flags = VXLAN_HF_VNI;
+	vxh->vx_vni = vxlan_vni_field(tun_id);
+
+	return 0;
+}
+
+static int mlx5e_gen_ip_tunnel_header(char buf[], __u8 *ip_proto,
+				      struct mlx5e_encap_entry *e)
+{
+	int err = 0;
+	struct ip_tunnel_key *key = &e->tun_info.key;
+
+	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
+		*ip_proto = IPPROTO_UDP;
+		err = mlx5e_gen_vxlan_header(buf, key);
+	} else {
+		pr_warn("mlx5: Cannot generate tunnel header for tunnel type (%d)\n"
+			, e->tunnel_type);
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
+				    struct net_device *mirred_dev,
+				    struct mlx5e_encap_entry *e)
+{
+	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
+	int ipv4_encap_size = ETH_HLEN +
+			      sizeof(struct iphdr) +
+			      e->tunnel_hlen;
+	struct ip_tunnel_key *tun_key = &e->tun_info.key;
+	struct net_device *out_dev;
+	struct neighbour *n = NULL;
+	struct flowi4 fl4 = {};
+	char *encap_header;
+	struct ethhdr *eth;
+	u8 nud_state, ttl;
+	struct iphdr *ip;
+	int err;
+
+	if (max_encap_size < ipv4_encap_size) {
+		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
+			       ipv4_encap_size, max_encap_size);
+		return -EOPNOTSUPP;
+	}
+
+	encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL);
+	if (!encap_header)
+		return -ENOMEM;
+
+	/* add the IP fields */
+	fl4.flowi4_tos = tun_key->tos;
+	fl4.daddr = tun_key->u.ipv4.dst;
+	fl4.saddr = tun_key->u.ipv4.src;
+	ttl = tun_key->ttl;
+
+	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev,
+				      &fl4, &n, &ttl);
+	if (err)
+		goto free_encap;
+
+	/* used by mlx5e_detach_encap to lookup a neigh hash table
+	 * entry in the neigh hash table when a user deletes a rule
+	 */
+	e->m_neigh.dev = n->dev;
+	e->m_neigh.family = n->ops->family;
+	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
+	e->out_dev = out_dev;
+
+	/* It's important to add the neigh to the hash table before checking
+	 * the neigh validity state. So if we'll get a notification, in case the
+	 * neigh changes it's validity state, we would find the relevant neigh
+	 * in the hash.
+	 */
+	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
+	if (err)
+		goto free_encap;
+
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	ether_addr_copy(e->h_dest, n->ha);
+	read_unlock_bh(&n->lock);
+
+	/* add ethernet header */
+	eth = (struct ethhdr *)encap_header;
+	ether_addr_copy(eth->h_dest, e->h_dest);
+	ether_addr_copy(eth->h_source, out_dev->dev_addr);
+	eth->h_proto = htons(ETH_P_IP);
+
+	/* add ip header */
+	ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr));
+	ip->tos = tun_key->tos;
+	ip->version = 0x4;
+	ip->ihl = 0x5;
+	ip->ttl = ttl;
+	ip->daddr = fl4.daddr;
+	ip->saddr = fl4.saddr;
+
+	/* add tunneling protocol header */
+	err = mlx5e_gen_ip_tunnel_header((char *)ip + sizeof(struct iphdr),
+					 &ip->protocol, e);
+	if (err)
+		goto destroy_neigh_entry;
+
+	e->encap_size = ipv4_encap_size;
+	e->encap_header = encap_header;
+
+	if (!(nud_state & NUD_VALID)) {
+		neigh_event_send(n, NULL);
+		err = -EAGAIN;
+		goto out;
+	}
+
+	err = mlx5_packet_reformat_alloc(priv->mdev,
+					 e->reformat_type,
+					 ipv4_encap_size, encap_header,
+					 MLX5_FLOW_NAMESPACE_FDB,
+					 &e->encap_id);
+	if (err)
+		goto destroy_neigh_entry;
+
+	e->flags |= MLX5_ENCAP_ENTRY_VALID;
+	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
+	neigh_release(n);
+	return err;
+
+destroy_neigh_entry:
+	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
+free_encap:
+	kfree(encap_header);
+out:
+	if (n)
+		neigh_release(n);
+	return err;
+}
+
+int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
+				    struct net_device *mirred_dev,
+				    struct mlx5e_encap_entry *e)
+{
+	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
+	int ipv6_encap_size = ETH_HLEN +
+			      sizeof(struct ipv6hdr) +
+			      e->tunnel_hlen;
+	struct ip_tunnel_key *tun_key = &e->tun_info.key;
+	struct net_device *out_dev;
+	struct neighbour *n = NULL;
+	struct flowi6 fl6 = {};
+	struct ipv6hdr *ip6h;
+	char *encap_header;
+	struct ethhdr *eth;
+	u8 nud_state, ttl;
+	int err;
+
+	if (max_encap_size < ipv6_encap_size) {
+		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
+			       ipv6_encap_size, max_encap_size);
+		return -EOPNOTSUPP;
+	}
+
+	encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL);
+	if (!encap_header)
+		return -ENOMEM;
+
+	ttl = tun_key->ttl;
+
+	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
+	fl6.daddr = tun_key->u.ipv6.dst;
+	fl6.saddr = tun_key->u.ipv6.src;
+
+	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev,
+				      &fl6, &n, &ttl);
+	if (err)
+		goto free_encap;
+
+	/* used by mlx5e_detach_encap to lookup a neigh hash table
+	 * entry in the neigh hash table when a user deletes a rule
+	 */
+	e->m_neigh.dev = n->dev;
+	e->m_neigh.family = n->ops->family;
+	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
+	e->out_dev = out_dev;
+
+	/* It's importent to add the neigh to the hash table before checking
+	 * the neigh validity state. So if we'll get a notification, in case the
+	 * neigh changes it's validity state, we would find the relevant neigh
+	 * in the hash.
+	 */
+	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
+	if (err)
+		goto free_encap;
+
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	ether_addr_copy(e->h_dest, n->ha);
+	read_unlock_bh(&n->lock);
+
+	/* add ethernet header */
+	eth = (struct ethhdr *)encap_header;
+	ether_addr_copy(eth->h_dest, e->h_dest);
+	ether_addr_copy(eth->h_source, out_dev->dev_addr);
+	eth->h_proto = htons(ETH_P_IPV6);
+
+	/* add ip header */
+	ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr));
+	ip6_flow_hdr(ip6h, tun_key->tos, 0);
+	/* the HW fills up ipv6 payload len */
+	ip6h->hop_limit   = ttl;
+	ip6h->daddr	  = fl6.daddr;
+	ip6h->saddr	  = fl6.saddr;
+
+	/* add tunneling protocol header */
+	err = mlx5e_gen_ip_tunnel_header((char *)ip6h + sizeof(struct ipv6hdr),
+					 &ip6h->nexthdr, e);
+	if (err)
+		goto destroy_neigh_entry;
+
+	e->encap_size = ipv6_encap_size;
+	e->encap_header = encap_header;
+
+	if (!(nud_state & NUD_VALID)) {
+		neigh_event_send(n, NULL);
+		err = -EAGAIN;
+		goto out;
+	}
+
+	err = mlx5_packet_reformat_alloc(priv->mdev,
+					 e->reformat_type,
+					 ipv6_encap_size, encap_header,
+					 MLX5_FLOW_NAMESPACE_FDB,
+					 &e->encap_id);
+	if (err)
+		goto destroy_neigh_entry;
+
+	e->flags |= MLX5_ENCAP_ENTRY_VALID;
+	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
+	neigh_release(n);
+	return err;
+
+destroy_neigh_entry:
+	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
+free_encap:
+	kfree(encap_header);
+out:
+	if (n)
+		neigh_release(n);
+	return err;
+}
+
+int mlx5e_tc_tun_get_type(struct net_device *tunnel_dev)
+{
+	if (netif_is_vxlan(tunnel_dev))
+		return MLX5E_TC_TUNNEL_TYPE_VXLAN;
+	else
+		return MLX5E_TC_TUNNEL_TYPE_UNKNOWN;
+}
+
+bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
+				    struct net_device *netdev)
+{
+	int tunnel_type = mlx5e_tc_tun_get_type(netdev);
+
+	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN &&
+	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
+		return true;
+	else
+		return false;
+}
+
+int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev,
+				 struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e,
+				 struct netlink_ext_ack *extack)
+{
+	e->tunnel_type = mlx5e_tc_tun_get_type(tunnel_dev);
+
+	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
+		int dst_port =  be16_to_cpu(e->tun_info.key.tp_dst);
+
+		if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, dst_port)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "vxlan udp dport was not registered with the HW");
+			netdev_warn(priv->netdev,
+				    "%d isn't an offloaded vxlan udp dport\n",
+				    dst_port);
+			return -EOPNOTSUPP;
+		}
+		e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
+		e->tunnel_hlen = VXLAN_HLEN;
+	} else {
+		e->reformat_type = -1;
+		e->tunnel_hlen = -1;
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
+				    struct mlx5_flow_spec *spec,
+				    struct tc_cls_flower_offload *f,
+				    void *headers_c,
+				    void *headers_v)
+{
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct flow_dissector_key_ports *key =
+		skb_flow_dissector_target(f->dissector,
+					  FLOW_DISSECTOR_KEY_ENC_PORTS,
+					  f->key);
+	struct flow_dissector_key_ports *mask =
+		skb_flow_dissector_target(f->dissector,
+					  FLOW_DISSECTOR_KEY_ENC_PORTS,
+					  f->mask);
+	void *misc_c = MLX5_ADDR_OF(fte_match_param,
+				    spec->match_criteria,
+				    misc_parameters);
+	void *misc_v = MLX5_ADDR_OF(fte_match_param,
+				    spec->match_value,
+				    misc_parameters);
+
+	/* Full udp dst port must be given */
+	if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) ||
+	    memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "VXLAN decap filter must include enc_dst_port condition");
+		netdev_warn(priv->netdev,
+			    "VXLAN decap filter must include enc_dst_port condition\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* udp dst port must be knonwn as a VXLAN port */
+	if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matched UDP port is not registered as a VXLAN port");
+		netdev_warn(priv->netdev,
+			    "UDP port %d is not registered as a VXLAN port\n",
+			    be16_to_cpu(key->dst));
+		return -EOPNOTSUPP;
+	}
+
+	/* dst UDP port is valid here */
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol);
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP);
+
+	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, ntohs(mask->dst));
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, ntohs(key->dst));
+
+	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport, ntohs(mask->src));
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport, ntohs(key->src));
+
+	/* match on VNI */
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_dissector_key_keyid *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_KEYID,
+						  f->key);
+		struct flow_dissector_key_keyid *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_KEYID,
+						  f->mask);
+		MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
+			 be32_to_cpu(mask->keyid));
+		MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
+			 be32_to_cpu(key->keyid));
+	}
+	return 0;
+}
+
+int mlx5e_tc_tun_parse(struct net_device *filter_dev,
+		       struct mlx5e_priv *priv,
+		       struct mlx5_flow_spec *spec,
+		       struct tc_cls_flower_offload *f,
+		       void *headers_c,
+		       void *headers_v)
+{
+	int tunnel_type;
+	int err = 0;
+
+	tunnel_type = mlx5e_tc_tun_get_type(filter_dev);
+	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
+		err = mlx5e_tc_tun_parse_vxlan(priv, spec, f,
+					       headers_c, headers_v);
+	} else {
+		netdev_warn(priv->netdev,
+			    "decapsulation offload is not supported for %s net device (%d)\n",
+			    mlx5e_netdev_kind(filter_dev), tunnel_type);
+		return -EOPNOTSUPP;
+	}
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
new file mode 100644
index 000000000000..ad4fc93b17a1
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_TC_TUNNEL_H__
+#define __MLX5_EN_TC_TUNNEL_H__
+
+#include <linux/netdevice.h>
+#include <linux/mlx5/fs.h>
+#include <net/pkt_cls.h>
+#include <linux/netlink.h>
+#include "en.h"
+#include "en_rep.h"
+
+enum {
+	MLX5E_TC_TUNNEL_TYPE_UNKNOWN,
+	MLX5E_TC_TUNNEL_TYPE_VXLAN
+};
+
+int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev,
+				 struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e,
+				 struct netlink_ext_ack *extack);
+
+int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
+				    struct net_device *mirred_dev,
+				    struct mlx5e_encap_entry *e);
+
+int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
+				    struct net_device *mirred_dev,
+				    struct mlx5e_encap_entry *e);
+
+int mlx5e_tc_tun_get_type(struct net_device *tunnel_dev);
+bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
+				    struct net_device *netdev);
+
+int mlx5e_tc_tun_parse(struct net_device *filter_dev,
+		       struct mlx5e_priv *priv,
+		       struct mlx5_flow_spec *spec,
+		       struct tc_cls_flower_offload *f,
+		       void *headers_c,
+		       void *headers_v);
+
+#endif //__MLX5_EN_TC_TUNNEL_H__
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 5cac4de435c9..85e51bd4147f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -42,6 +42,7 @@
 #include "en.h"
 #include "en_rep.h"
 #include "en_tc.h"
+#include "en/tc_tun.h"
 #include "fs_core.h"
 
 #define MLX5E_REP_PARAMS_LOG_SQ_SIZE \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 7d7f490d8ff1..abc200947e84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -44,15 +44,14 @@
 #include <net/tc_act/tc_tunnel_key.h>
 #include <net/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_csum.h>
-#include <net/vxlan.h>
 #include <net/arp.h>
 #include "en.h"
 #include "en_rep.h"
 #include "en_tc.h"
 #include "eswitch.h"
-#include "lib/vxlan.h"
 #include "fs_core.h"
 #include "en/port.h"
+#include "en/tc_tun.h"
 
 struct mlx5_nic_flow_attr {
 	u32 action;
@@ -79,13 +78,6 @@ enum {
 
 #define MLX5E_TC_MAX_SPLITS 1
 
-enum {
-	MLX5E_TC_TUNNEL_TYPE_UNKNOWN,
-	MLX5E_TC_TUNNEL_TYPE_VXLAN
-};
-
-static int mlx5e_get_tunnel_type(struct net_device *tunnel_dev);
-
 struct mlx5e_tc_flow {
 	struct rhash_head	node;
 	struct mlx5e_priv	*priv;
@@ -684,14 +676,6 @@ static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv,
 	}
 }
 
-static const char *mlx5e_netdev_kind(struct net_device *dev)
-{
-	if (dev->rtnl_link_ops)
-		return dev->rtnl_link_ops->kind;
-	else
-		return "";
-}
-
 static int
 mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 		      struct mlx5e_tc_flow_parse_attr *parse_attr,
@@ -1209,75 +1193,6 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 		mlx5e_tc_del_nic_flow(priv, flow);
 }
 
-static int parse_tunnel_vxlan_attr(struct mlx5e_priv *priv,
-				   struct mlx5_flow_spec *spec,
-				   struct tc_cls_flower_offload *f,
-				   void *headers_c,
-				   void *headers_v)
-{
-	struct netlink_ext_ack *extack = f->common.extack;
-	struct flow_dissector_key_ports *key =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_ENC_PORTS,
-					  f->key);
-	struct flow_dissector_key_ports *mask =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_ENC_PORTS,
-					  f->mask);
-	void *misc_c = MLX5_ADDR_OF(fte_match_param,
-				    spec->match_criteria,
-				    misc_parameters);
-	void *misc_v = MLX5_ADDR_OF(fte_match_param,
-				    spec->match_value,
-				    misc_parameters);
-
-	/* Full udp dst port must be given */
-	if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) ||
-	    memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "VXLAN decap filter must include enc_dst_port condition");
-		netdev_warn(priv->netdev,
-			    "VXLAN decap filter must include enc_dst_port condition\n");
-		return -EOPNOTSUPP;
-	}
-
-	/* udp dst port must be knonwn as a VXLAN port */
-	if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst))) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Matched UDP port is not registered as a VXLAN port");
-		netdev_warn(priv->netdev,
-			    "UDP port %d is not registered as a VXLAN port\n",
-			    be16_to_cpu(key->dst));
-		return -EOPNOTSUPP;
-	}
-
-	/* dst UDP port is valid here */
-	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol);
-	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP);
-
-	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, ntohs(mask->dst));
-	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, ntohs(key->dst));
-
-	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport, ntohs(mask->src));
-	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport, ntohs(key->src));
-
-	/* match on VNI */
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->key);
-		struct flow_dissector_key_keyid *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->mask);
-		MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
-			 be32_to_cpu(mask->keyid));
-		MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
-			 be32_to_cpu(key->keyid));
-	}
-	return 0;
-}
 
 static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			     struct mlx5_flow_spec *spec,
@@ -1294,29 +1209,14 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 		skb_flow_dissector_target(f->dissector,
 					  FLOW_DISSECTOR_KEY_ENC_CONTROL,
 					  f->key);
-	int tunnel_type;
 	int err = 0;
 
-	tunnel_type = mlx5e_get_tunnel_type(filter_dev);
-	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
-		err = parse_tunnel_vxlan_attr(priv, spec, f,
-					      headers_c, headers_v);
-	} else {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "decapsulation offload is not supported");
-		netdev_warn(priv->netdev,
-			    "decapsulation offload is not supported for %s net device (%d)\n",
-			    mlx5e_netdev_kind(filter_dev), tunnel_type);
-		return -EOPNOTSUPP;
-	}
-
+	err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f,
+				 headers_c, headers_v);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "failed to parse tunnel attributes");
-		netdev_warn(priv->netdev,
-			    "failed to parse %s tunnel attributes (%d)\n",
-			    mlx5e_netdev_kind(filter_dev), tunnel_type);
-		return -EOPNOTSUPP;
+		return err;
 	}
 
 	if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
@@ -2359,45 +2259,6 @@ static inline int hash_encap_info(struct ip_tunnel_key *key)
 	return jhash(key, sizeof(*key), 0);
 }
 
-static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
-				   struct net_device *mirred_dev,
-				   struct net_device **out_dev,
-				   struct flowi4 *fl4,
-				   struct neighbour **out_n,
-				   u8 *out_ttl)
-{
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5e_rep_priv *uplink_rpriv;
-	struct rtable *rt;
-	struct neighbour *n = NULL;
-
-#if IS_ENABLED(CONFIG_INET)
-	int ret;
-
-	rt = ip_route_output_key(dev_net(mirred_dev), fl4);
-	ret = PTR_ERR_OR_ZERO(rt);
-	if (ret)
-		return ret;
-#else
-	return -EOPNOTSUPP;
-#endif
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-	/* if the egress device isn't on the same HW e-switch, we use the uplink */
-	if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev))
-		*out_dev = uplink_rpriv->netdev;
-	else
-		*out_dev = rt->dst.dev;
-
-	if (!(*out_ttl))
-		*out_ttl = ip4_dst_hoplimit(&rt->dst);
-	n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
-	ip_rt_put(rt);
-	if (!n)
-		return -ENOMEM;
-
-	*out_n = n;
-	return 0;
-}
 
 static bool is_merged_eswitch_dev(struct mlx5e_priv *priv,
 				  struct net_device *peer_netdev)
@@ -2413,354 +2274,7 @@ static bool is_merged_eswitch_dev(struct mlx5e_priv *priv,
 		(peer_priv->mdev->priv.eswitch->mode == SRIOV_OFFLOADS));
 }
 
-static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
-				   struct net_device *mirred_dev,
-				   struct net_device **out_dev,
-				   struct flowi6 *fl6,
-				   struct neighbour **out_n,
-				   u8 *out_ttl)
-{
-	struct neighbour *n = NULL;
-	struct dst_entry *dst;
-
-#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
-	struct mlx5e_rep_priv *uplink_rpriv;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	int ret;
-
-	ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst,
-					 fl6);
-	if (ret < 0)
-		return ret;
-
-	if (!(*out_ttl))
-		*out_ttl = ip6_dst_hoplimit(dst);
-
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-	/* if the egress device isn't on the same HW e-switch, we use the uplink */
-	if (!switchdev_port_same_parent_id(priv->netdev, dst->dev))
-		*out_dev = uplink_rpriv->netdev;
-	else
-		*out_dev = dst->dev;
-#else
-	return -EOPNOTSUPP;
-#endif
-
-	n = dst_neigh_lookup(dst, &fl6->daddr);
-	dst_release(dst);
-	if (!n)
-		return -ENOMEM;
-
-	*out_n = n;
-	return 0;
-}
-
-static int mlx5e_gen_vxlan_header(char buf[], struct ip_tunnel_key *tun_key)
-{
-	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
-	struct udphdr *udp = (struct udphdr *)(buf);
-	struct vxlanhdr *vxh = (struct vxlanhdr *)
-			       ((char *)udp + sizeof(struct udphdr));
-
-	udp->dest = tun_key->tp_dst;
-	vxh->vx_flags = VXLAN_HF_VNI;
-	vxh->vx_vni = vxlan_vni_field(tun_id);
-
-	return 0;
-}
-
-static int mlx5e_gen_ip_tunnel_header(char buf[], __u8 *ip_proto,
-				      struct mlx5e_encap_entry *e)
-{
-	int err = 0;
-	struct ip_tunnel_key *key = &e->tun_info.key;
-
-	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
-		*ip_proto = IPPROTO_UDP;
-		err = mlx5e_gen_vxlan_header(buf, key);
-	} else {
-		pr_warn("mlx5: Cannot generate tunnel header for tunnel type (%d)\n"
-			, e->tunnel_type);
-		err = -EOPNOTSUPP;
-	}
-
-	return err;
-}
-
-static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
-					  struct net_device *mirred_dev,
-					  struct mlx5e_encap_entry *e)
-{
-	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	int ipv4_encap_size = ETH_HLEN +
-			      sizeof(struct iphdr) +
-			      e->tunnel_hlen;
-	struct ip_tunnel_key *tun_key = &e->tun_info.key;
-	struct net_device *out_dev;
-	struct neighbour *n = NULL;
-	struct flowi4 fl4 = {};
-	char *encap_header;
-	struct ethhdr *eth;
-	u8 nud_state, ttl;
-	struct iphdr *ip;
-	int err;
-
-	if (max_encap_size < ipv4_encap_size) {
-		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
-			       ipv4_encap_size, max_encap_size);
-		return -EOPNOTSUPP;
-	}
-
-	encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL);
-	if (!encap_header)
-		return -ENOMEM;
-
-	/* add the IP fields */
-	fl4.flowi4_tos = tun_key->tos;
-	fl4.daddr = tun_key->u.ipv4.dst;
-	fl4.saddr = tun_key->u.ipv4.src;
-	ttl = tun_key->ttl;
-
-	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev,
-				      &fl4, &n, &ttl);
-	if (err)
-		goto free_encap;
-
-	/* used by mlx5e_detach_encap to lookup a neigh hash table
-	 * entry in the neigh hash table when a user deletes a rule
-	 */
-	e->m_neigh.dev = n->dev;
-	e->m_neigh.family = n->ops->family;
-	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
-	e->out_dev = out_dev;
-
-	/* It's important to add the neigh to the hash table before checking
-	 * the neigh validity state. So if we'll get a notification, in case the
-	 * neigh changes it's validity state, we would find the relevant neigh
-	 * in the hash.
-	 */
-	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
-	if (err)
-		goto free_encap;
-
-	read_lock_bh(&n->lock);
-	nud_state = n->nud_state;
-	ether_addr_copy(e->h_dest, n->ha);
-	read_unlock_bh(&n->lock);
-
-	/* add ethernet header */
-	eth = (struct ethhdr *)encap_header;
-	ether_addr_copy(eth->h_dest, e->h_dest);
-	ether_addr_copy(eth->h_source, out_dev->dev_addr);
-	eth->h_proto = htons(ETH_P_IP);
-
-	/* add ip header */
-	ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr));
-	ip->tos = tun_key->tos;
-	ip->version = 0x4;
-	ip->ihl = 0x5;
-	ip->ttl = ttl;
-	ip->daddr = fl4.daddr;
-	ip->saddr = fl4.saddr;
-
-	/* add tunneling protocol header */
-	err = mlx5e_gen_ip_tunnel_header((char *)ip + sizeof(struct iphdr),
-					  &ip->protocol, e);
-	if (err)
-		goto destroy_neigh_entry;
-
-	e->encap_size = ipv4_encap_size;
-	e->encap_header = encap_header;
-
-	if (!(nud_state & NUD_VALID)) {
-		neigh_event_send(n, NULL);
-		err = -EAGAIN;
-		goto out;
-	}
-
-	err = mlx5_packet_reformat_alloc(priv->mdev,
-					 e->reformat_type,
-					 ipv4_encap_size, encap_header,
-					 MLX5_FLOW_NAMESPACE_FDB,
-					 &e->encap_id);
-	if (err)
-		goto destroy_neigh_entry;
-
-	e->flags |= MLX5_ENCAP_ENTRY_VALID;
-	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
-	neigh_release(n);
-	return err;
-
-destroy_neigh_entry:
-	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
-free_encap:
-	kfree(encap_header);
-out:
-	if (n)
-		neigh_release(n);
-	return err;
-}
-
-static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
-					  struct net_device *mirred_dev,
-					  struct mlx5e_encap_entry *e)
-{
-	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	int ipv6_encap_size = ETH_HLEN +
-			      sizeof(struct ipv6hdr) +
-			      e->tunnel_hlen;
-	struct ip_tunnel_key *tun_key = &e->tun_info.key;
-	struct net_device *out_dev;
-	struct neighbour *n = NULL;
-	struct flowi6 fl6 = {};
-	struct ipv6hdr *ip6h;
-	char *encap_header;
-	struct ethhdr *eth;
-	u8 nud_state, ttl;
-	int err;
-
-	if (max_encap_size < ipv6_encap_size) {
-		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
-			       ipv6_encap_size, max_encap_size);
-		return -EOPNOTSUPP;
-	}
-
-	encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL);
-	if (!encap_header)
-		return -ENOMEM;
-
-	ttl = tun_key->ttl;
-
-	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
-	fl6.daddr = tun_key->u.ipv6.dst;
-	fl6.saddr = tun_key->u.ipv6.src;
-
-	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev,
-				      &fl6, &n, &ttl);
-	if (err)
-		goto free_encap;
-
-	/* used by mlx5e_detach_encap to lookup a neigh hash table
-	 * entry in the neigh hash table when a user deletes a rule
-	 */
-	e->m_neigh.dev = n->dev;
-	e->m_neigh.family = n->ops->family;
-	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
-	e->out_dev = out_dev;
-
-	/* It's importent to add the neigh to the hash table before checking
-	 * the neigh validity state. So if we'll get a notification, in case the
-	 * neigh changes it's validity state, we would find the relevant neigh
-	 * in the hash.
-	 */
-	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
-	if (err)
-		goto free_encap;
-
-	read_lock_bh(&n->lock);
-	nud_state = n->nud_state;
-	ether_addr_copy(e->h_dest, n->ha);
-	read_unlock_bh(&n->lock);
-
-	/* add ethernet header */
-	eth = (struct ethhdr *)encap_header;
-	ether_addr_copy(eth->h_dest, e->h_dest);
-	ether_addr_copy(eth->h_source, out_dev->dev_addr);
-	eth->h_proto = htons(ETH_P_IPV6);
-
-	/* add ip header */
-	ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr));
-	ip6_flow_hdr(ip6h, tun_key->tos, 0);
-	/* the HW fills up ipv6 payload len */
-	ip6h->hop_limit   = ttl;
-	ip6h->daddr	  = fl6.daddr;
-	ip6h->saddr	  = fl6.saddr;
-
-	/* add tunneling protocol header */
-	err = mlx5e_gen_ip_tunnel_header((char *)ip6h + sizeof(struct ipv6hdr),
-					 &ip6h->nexthdr, e);
-	if (err)
-		goto destroy_neigh_entry;
-
-	e->encap_size = ipv6_encap_size;
-	e->encap_header = encap_header;
-
-	if (!(nud_state & NUD_VALID)) {
-		neigh_event_send(n, NULL);
-		err = -EAGAIN;
-		goto out;
-	}
-
-	err = mlx5_packet_reformat_alloc(priv->mdev,
-					 e->reformat_type,
-					 ipv6_encap_size, encap_header,
-					 MLX5_FLOW_NAMESPACE_FDB,
-					 &e->encap_id);
-	if (err)
-		goto destroy_neigh_entry;
-
-	e->flags |= MLX5_ENCAP_ENTRY_VALID;
-	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
-	neigh_release(n);
-	return err;
-
-destroy_neigh_entry:
-	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
-free_encap:
-	kfree(encap_header);
-out:
-	if (n)
-		neigh_release(n);
-	return err;
-}
-
-static int mlx5e_get_tunnel_type(struct net_device *tunnel_dev)
-{
-	if (netif_is_vxlan(tunnel_dev))
-		return MLX5E_TC_TUNNEL_TYPE_VXLAN;
-	else
-		return MLX5E_TC_TUNNEL_TYPE_UNKNOWN;
-}
-
-bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
-				    struct net_device *netdev)
-{
-	int tunnel_type = mlx5e_get_tunnel_type(netdev);
-
-	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN &&
-	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
-		return true;
-	else
-		return false;
-}
 
-static int mlx5e_init_tunnel_attr(struct net_device *tunnel_dev,
-				  struct mlx5e_priv *priv,
-				  struct mlx5e_encap_entry *e,
-				  struct netlink_ext_ack *extack)
-{
-	e->tunnel_type = mlx5e_get_tunnel_type(tunnel_dev);
-
-	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
-		int dst_port =  be16_to_cpu(e->tun_info.key.tp_dst);
-
-		if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, dst_port)) {
-			NL_SET_ERR_MSG_MOD(extack,
-					   "vxlan udp dport was not registered with the HW");
-			netdev_warn(priv->netdev,
-				    "%d isn't an offloaded vxlan udp dport\n",
-				    dst_port);
-			return -EOPNOTSUPP;
-		}
-		e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
-		e->tunnel_hlen = VXLAN_HLEN;
-	} else {
-		e->reformat_type = -1;
-		e->tunnel_hlen = -1;
-		return -EOPNOTSUPP;
-	}
-	return 0;
-}
 
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct ip_tunnel_info *tun_info,
@@ -2797,16 +2311,16 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 		return -ENOMEM;
 
 	e->tun_info = *tun_info;
-	err = mlx5e_init_tunnel_attr(mirred_dev, priv, e, extack);
+	err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack);
 	if (err)
 		goto out_err;
 
 	INIT_LIST_HEAD(&e->flows);
 
 	if (family == AF_INET)
-		err = mlx5e_create_encap_header_ipv4(priv, mirred_dev, e);
+		err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e);
 	else if (family == AF_INET6)
-		err = mlx5e_create_encap_header_ipv6(priv, mirred_dev, e);
+		err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e);
 
 	if (err && err != -EAGAIN)
 		goto out_err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 004e679a4f53..a15c08a35054 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -70,8 +70,6 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe);
 
 int mlx5e_tc_num_filters(struct mlx5e_priv *priv);
 
-bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
-				    struct net_device *netdev);
 
 #else /* CONFIG_MLX5_ESWITCH */
 static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
-- 
cgit v1.2.3


From 0621e6fc5ed2b6e58a2ba6904074e366f290b1d8 Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Wed, 21 Nov 2018 12:15:34 +0200
Subject: net: Add netif_is_gretap()/netif_is_ip6gretap()

Changed the is_gretap_dev and is_ip6gretap_dev logic from structure
comparison to string comparison of the rtnl_link_ops kind field.

This approach aligns with the current identification methods and function
names of vxlan and geneve network devices.

Convert mlxsw to use these helpers and use them in downstream mlx5 patch.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c |  4 ++--
 include/net/gre.h                                   | 13 +++++++++++--
 net/ipv4/ip_gre.c                                   |  6 ------
 net/ipv6/ip6_gre.c                                  |  6 ------
 4 files changed, 13 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index d965fd275c90..ad5a9b9e1466 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -383,7 +383,7 @@ mlxsw_sp_span_entry_gretap4_deconfigure(struct mlxsw_sp_span_entry *span_entry)
 }
 
 static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap4 = {
-	.can_handle = is_gretap_dev,
+	.can_handle = netif_is_gretap,
 	.parms = mlxsw_sp_span_entry_gretap4_parms,
 	.configure = mlxsw_sp_span_entry_gretap4_configure,
 	.deconfigure = mlxsw_sp_span_entry_gretap4_deconfigure,
@@ -484,7 +484,7 @@ mlxsw_sp_span_entry_gretap6_deconfigure(struct mlxsw_sp_span_entry *span_entry)
 
 static const
 struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap6 = {
-	.can_handle = is_ip6gretap_dev,
+	.can_handle = netif_is_ip6gretap,
 	.parms = mlxsw_sp_span_entry_gretap6_parms,
 	.configure = mlxsw_sp_span_entry_gretap6_configure,
 	.deconfigure = mlxsw_sp_span_entry_gretap6_deconfigure,
diff --git a/include/net/gre.h b/include/net/gre.h
index 797142eee9cd..b60f212c16c6 100644
--- a/include/net/gre.h
+++ b/include/net/gre.h
@@ -37,8 +37,17 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		     bool *csum_err, __be16 proto, int nhs);
 
-bool is_gretap_dev(const struct net_device *dev);
-bool is_ip6gretap_dev(const struct net_device *dev);
+static inline bool netif_is_gretap(const struct net_device *dev)
+{
+	return dev->rtnl_link_ops &&
+	       !strcmp(dev->rtnl_link_ops->kind, "gretap");
+}
+
+static inline bool netif_is_ip6gretap(const struct net_device *dev)
+{
+	return dev->rtnl_link_ops &&
+	       !strcmp(dev->rtnl_link_ops->kind, "ip6gretap");
+}
 
 static inline int gre_calc_hlen(__be16 o_flags)
 {
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 76a9a5f7a40e..c7a7bd58a23c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1341,12 +1341,6 @@ static void ipgre_tap_setup(struct net_device *dev)
 	ip_tunnel_setup(dev, gre_tap_net_id);
 }
 
-bool is_gretap_dev(const struct net_device *dev)
-{
-	return dev->netdev_ops == &gre_tap_netdev_ops;
-}
-EXPORT_SYMBOL_GPL(is_gretap_dev);
-
 static int ipgre_newlink(struct net *src_net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[],
 			 struct netlink_ext_ack *extack)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 81b69bcee714..229e55c99021 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1885,12 +1885,6 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	netif_keep_dst(dev);
 }
 
-bool is_ip6gretap_dev(const struct net_device *dev)
-{
-	return dev->netdev_ops == &ip6gre_tap_netdev_ops;
-}
-EXPORT_SYMBOL_GPL(is_ip6gretap_dev);
-
 static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
 				       struct ip_tunnel_encap *ipencap)
 {
-- 
cgit v1.2.3


From df2ef3bff193229973830fd3fd8acf29fa92715e Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Mon, 29 Oct 2018 08:54:42 +0200
Subject: net/mlx5e: Add GRE protocol offloading

Add HW offloading support for TC flower filters configured on
gretap/ip6gretap net devices.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    | 87 ++++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.h    |  3 +-
 2 files changed, 89 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index eaa43477e0ea..c1515f013501 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2018 Mellanox Technologies. */
 
 #include <net/vxlan.h>
+#include <net/gre.h>
 #include "lib/vxlan.h"
 #include "en/tc_tun.h"
 
@@ -109,6 +110,30 @@ static int mlx5e_gen_vxlan_header(char buf[], struct ip_tunnel_key *tun_key)
 	return 0;
 }
 
+static int mlx5e_gen_gre_header(char buf[], struct ip_tunnel_key *tun_key)
+{
+	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
+	int hdr_len;
+	struct gre_base_hdr *greh = (struct gre_base_hdr *)(buf);
+
+	/* the HW does not calculate GRE csum or sequences */
+	if (tun_key->tun_flags & (TUNNEL_CSUM | TUNNEL_SEQ))
+		return -EOPNOTSUPP;
+
+	greh->protocol = htons(ETH_P_TEB);
+
+	/* GRE key */
+	hdr_len = gre_calc_hlen(tun_key->tun_flags);
+	greh->flags = gre_tnl_flags_to_gre_flags(tun_key->tun_flags);
+	if (tun_key->tun_flags & TUNNEL_KEY) {
+		__be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
+
+		*ptr = tun_id;
+	}
+
+	return 0;
+}
+
 static int mlx5e_gen_ip_tunnel_header(char buf[], __u8 *ip_proto,
 				      struct mlx5e_encap_entry *e)
 {
@@ -118,6 +143,9 @@ static int mlx5e_gen_ip_tunnel_header(char buf[], __u8 *ip_proto,
 	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
 		*ip_proto = IPPROTO_UDP;
 		err = mlx5e_gen_vxlan_header(buf, key);
+	} else if  (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
+		*ip_proto = IPPROTO_GRE;
+		err = mlx5e_gen_gre_header(buf, key);
 	} else {
 		pr_warn("mlx5: Cannot generate tunnel header for tunnel type (%d)\n"
 			, e->tunnel_type);
@@ -358,6 +386,9 @@ int mlx5e_tc_tun_get_type(struct net_device *tunnel_dev)
 {
 	if (netif_is_vxlan(tunnel_dev))
 		return MLX5E_TC_TUNNEL_TYPE_VXLAN;
+	else if (netif_is_gretap(tunnel_dev) ||
+		 netif_is_ip6gretap(tunnel_dev))
+		return MLX5E_TC_TUNNEL_TYPE_GRETAP;
 	else
 		return MLX5E_TC_TUNNEL_TYPE_UNKNOWN;
 }
@@ -370,6 +401,9 @@ bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
 	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN &&
 	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
 		return true;
+	else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP &&
+		 MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap))
+		return true;
 	else
 		return false;
 }
@@ -394,6 +428,9 @@ int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev,
 		}
 		e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
 		e->tunnel_hlen = VXLAN_HLEN;
+	} else if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
+		e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_NVGRE;
+		e->tunnel_hlen = gre_calc_hlen(e->tun_info.key.tun_flags);
 	} else {
 		e->reformat_type = -1;
 		e->tunnel_hlen = -1;
@@ -472,6 +509,53 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 	return 0;
 }
 
+static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv,
+				     struct mlx5_flow_spec *spec,
+				     struct tc_cls_flower_offload *f,
+				     void *outer_headers_c,
+				     void *outer_headers_v)
+{
+	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters);
+	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters);
+
+	if (!MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "GRE HW offloading is not supported");
+		netdev_warn(priv->netdev, "GRE HW offloading is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol);
+	MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
+		 ip_protocol, IPPROTO_GRE);
+
+	/* gre protocol*/
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, gre_protocol);
+	MLX5_SET(fte_match_set_misc, misc_v, gre_protocol, ETH_P_TEB);
+
+	/* gre key */
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_dissector_key_keyid *mask = NULL;
+		struct flow_dissector_key_keyid *key = NULL;
+
+		mask = skb_flow_dissector_target(f->dissector,
+						 FLOW_DISSECTOR_KEY_ENC_KEYID,
+						 f->mask);
+		MLX5_SET(fte_match_set_misc, misc_c,
+			 gre_key.key, be32_to_cpu(mask->keyid));
+
+		key = skb_flow_dissector_target(f->dissector,
+						FLOW_DISSECTOR_KEY_ENC_KEYID,
+						f->key);
+		MLX5_SET(fte_match_set_misc, misc_v,
+			 gre_key.key, be32_to_cpu(key->keyid));
+	}
+
+	return 0;
+}
+
 int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 		       struct mlx5e_priv *priv,
 		       struct mlx5_flow_spec *spec,
@@ -486,6 +570,9 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
 		err = mlx5e_tc_tun_parse_vxlan(priv, spec, f,
 					       headers_c, headers_v);
+	} else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
+		err = mlx5e_tc_tun_parse_gretap(priv, spec, f,
+						headers_c, headers_v);
 	} else {
 		netdev_warn(priv->netdev,
 			    "decapsulation offload is not supported for %s net device (%d)\n",
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
index ad4fc93b17a1..706ce7bf15e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -13,7 +13,8 @@
 
 enum {
 	MLX5E_TC_TUNNEL_TYPE_UNKNOWN,
-	MLX5E_TC_TUNNEL_TYPE_VXLAN
+	MLX5E_TC_TUNNEL_TYPE_VXLAN,
+	MLX5E_TC_TUNNEL_TYPE_GRETAP
 };
 
 int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev,
-- 
cgit v1.2.3


From 69bd48404f251b9c45a15799fdcfc87a7ad6ab8a Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Tue, 6 Nov 2018 09:58:37 +0200
Subject: net/sched: Remove egdev mechanism

The egdev mechanism was replaced by the TC indirect block notifications
platform.

Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Cc: John Hurley <john.hurley@netronome.com>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/net/act_api.h |  30 -------
 net/sched/act_api.c   | 221 --------------------------------------------------
 net/sched/cls_api.c   |  47 +----------
 3 files changed, 1 insertion(+), 297 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 05c7df41d737..dbc795ec659e 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -194,35 +194,5 @@ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
 #endif
 }
 
-#ifdef CONFIG_NET_CLS_ACT
-int tc_setup_cb_egdev_register(const struct net_device *dev,
-			       tc_setup_cb_t *cb, void *cb_priv);
-void tc_setup_cb_egdev_unregister(const struct net_device *dev,
-				  tc_setup_cb_t *cb, void *cb_priv);
-int tc_setup_cb_egdev_call(const struct net_device *dev,
-			   enum tc_setup_type type, void *type_data,
-			   bool err_stop);
-#else
-static inline
-int tc_setup_cb_egdev_register(const struct net_device *dev,
-			       tc_setup_cb_t *cb, void *cb_priv)
-{
-	return 0;
-}
-
-static inline
-void tc_setup_cb_egdev_unregister(const struct net_device *dev,
-				  tc_setup_cb_t *cb, void *cb_priv)
-{
-}
-
-static inline
-int tc_setup_cb_egdev_call(const struct net_device *dev,
-			   enum tc_setup_type type, void *type_data,
-			   bool err_stop)
-{
-	return 0;
-}
-#endif
 
 #endif
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 9c1b0729aebf..d4b8355737d8 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -21,8 +21,6 @@
 #include <linux/kmod.h>
 #include <linux/err.h>
 #include <linux/module.h>
-#include <linux/rhashtable.h>
-#include <linux/list.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/sch_generic.h>
@@ -1522,227 +1520,8 @@ out_module_put:
 	return skb->len;
 }
 
-struct tcf_action_net {
-	struct rhashtable egdev_ht;
-};
-
-static unsigned int tcf_action_net_id;
-
-struct tcf_action_egdev_cb {
-	struct list_head list;
-	tc_setup_cb_t *cb;
-	void *cb_priv;
-};
-
-struct tcf_action_egdev {
-	struct rhash_head ht_node;
-	const struct net_device *dev;
-	unsigned int refcnt;
-	struct list_head cb_list;
-};
-
-static const struct rhashtable_params tcf_action_egdev_ht_params = {
-	.key_offset = offsetof(struct tcf_action_egdev, dev),
-	.head_offset = offsetof(struct tcf_action_egdev, ht_node),
-	.key_len = sizeof(const struct net_device *),
-};
-
-static struct tcf_action_egdev *
-tcf_action_egdev_lookup(const struct net_device *dev)
-{
-	struct net *net = dev_net(dev);
-	struct tcf_action_net *tan = net_generic(net, tcf_action_net_id);
-
-	return rhashtable_lookup_fast(&tan->egdev_ht, &dev,
-				      tcf_action_egdev_ht_params);
-}
-
-static struct tcf_action_egdev *
-tcf_action_egdev_get(const struct net_device *dev)
-{
-	struct tcf_action_egdev *egdev;
-	struct tcf_action_net *tan;
-
-	egdev = tcf_action_egdev_lookup(dev);
-	if (egdev)
-		goto inc_ref;
-
-	egdev = kzalloc(sizeof(*egdev), GFP_KERNEL);
-	if (!egdev)
-		return NULL;
-	INIT_LIST_HEAD(&egdev->cb_list);
-	egdev->dev = dev;
-	tan = net_generic(dev_net(dev), tcf_action_net_id);
-	rhashtable_insert_fast(&tan->egdev_ht, &egdev->ht_node,
-			       tcf_action_egdev_ht_params);
-
-inc_ref:
-	egdev->refcnt++;
-	return egdev;
-}
-
-static void tcf_action_egdev_put(struct tcf_action_egdev *egdev)
-{
-	struct tcf_action_net *tan;
-
-	if (--egdev->refcnt)
-		return;
-	tan = net_generic(dev_net(egdev->dev), tcf_action_net_id);
-	rhashtable_remove_fast(&tan->egdev_ht, &egdev->ht_node,
-			       tcf_action_egdev_ht_params);
-	kfree(egdev);
-}
-
-static struct tcf_action_egdev_cb *
-tcf_action_egdev_cb_lookup(struct tcf_action_egdev *egdev,
-			   tc_setup_cb_t *cb, void *cb_priv)
-{
-	struct tcf_action_egdev_cb *egdev_cb;
-
-	list_for_each_entry(egdev_cb, &egdev->cb_list, list)
-		if (egdev_cb->cb == cb && egdev_cb->cb_priv == cb_priv)
-			return egdev_cb;
-	return NULL;
-}
-
-static int tcf_action_egdev_cb_call(struct tcf_action_egdev *egdev,
-				    enum tc_setup_type type,
-				    void *type_data, bool err_stop)
-{
-	struct tcf_action_egdev_cb *egdev_cb;
-	int ok_count = 0;
-	int err;
-
-	list_for_each_entry(egdev_cb, &egdev->cb_list, list) {
-		err = egdev_cb->cb(type, type_data, egdev_cb->cb_priv);
-		if (err) {
-			if (err_stop)
-				return err;
-		} else {
-			ok_count++;
-		}
-	}
-	return ok_count;
-}
-
-static int tcf_action_egdev_cb_add(struct tcf_action_egdev *egdev,
-				   tc_setup_cb_t *cb, void *cb_priv)
-{
-	struct tcf_action_egdev_cb *egdev_cb;
-
-	egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv);
-	if (WARN_ON(egdev_cb))
-		return -EEXIST;
-	egdev_cb = kzalloc(sizeof(*egdev_cb), GFP_KERNEL);
-	if (!egdev_cb)
-		return -ENOMEM;
-	egdev_cb->cb = cb;
-	egdev_cb->cb_priv = cb_priv;
-	list_add(&egdev_cb->list, &egdev->cb_list);
-	return 0;
-}
-
-static void tcf_action_egdev_cb_del(struct tcf_action_egdev *egdev,
-				    tc_setup_cb_t *cb, void *cb_priv)
-{
-	struct tcf_action_egdev_cb *egdev_cb;
-
-	egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv);
-	if (WARN_ON(!egdev_cb))
-		return;
-	list_del(&egdev_cb->list);
-	kfree(egdev_cb);
-}
-
-static int __tc_setup_cb_egdev_register(const struct net_device *dev,
-					tc_setup_cb_t *cb, void *cb_priv)
-{
-	struct tcf_action_egdev *egdev = tcf_action_egdev_get(dev);
-	int err;
-
-	if (!egdev)
-		return -ENOMEM;
-	err = tcf_action_egdev_cb_add(egdev, cb, cb_priv);
-	if (err)
-		goto err_cb_add;
-	return 0;
-
-err_cb_add:
-	tcf_action_egdev_put(egdev);
-	return err;
-}
-int tc_setup_cb_egdev_register(const struct net_device *dev,
-			       tc_setup_cb_t *cb, void *cb_priv)
-{
-	int err;
-
-	rtnl_lock();
-	err = __tc_setup_cb_egdev_register(dev, cb, cb_priv);
-	rtnl_unlock();
-	return err;
-}
-EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_register);
-
-static void __tc_setup_cb_egdev_unregister(const struct net_device *dev,
-					   tc_setup_cb_t *cb, void *cb_priv)
-{
-	struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev);
-
-	if (WARN_ON(!egdev))
-		return;
-	tcf_action_egdev_cb_del(egdev, cb, cb_priv);
-	tcf_action_egdev_put(egdev);
-}
-void tc_setup_cb_egdev_unregister(const struct net_device *dev,
-				  tc_setup_cb_t *cb, void *cb_priv)
-{
-	rtnl_lock();
-	__tc_setup_cb_egdev_unregister(dev, cb, cb_priv);
-	rtnl_unlock();
-}
-EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_unregister);
-
-int tc_setup_cb_egdev_call(const struct net_device *dev,
-			   enum tc_setup_type type, void *type_data,
-			   bool err_stop)
-{
-	struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev);
-
-	if (!egdev)
-		return 0;
-	return tcf_action_egdev_cb_call(egdev, type, type_data, err_stop);
-}
-EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_call);
-
-static __net_init int tcf_action_net_init(struct net *net)
-{
-	struct tcf_action_net *tan = net_generic(net, tcf_action_net_id);
-
-	return rhashtable_init(&tan->egdev_ht, &tcf_action_egdev_ht_params);
-}
-
-static void __net_exit tcf_action_net_exit(struct net *net)
-{
-	struct tcf_action_net *tan = net_generic(net, tcf_action_net_id);
-
-	rhashtable_destroy(&tan->egdev_ht);
-}
-
-static struct pernet_operations tcf_action_net_ops = {
-	.init = tcf_action_net_init,
-	.exit = tcf_action_net_exit,
-	.id = &tcf_action_net_id,
-	.size = sizeof(struct tcf_action_net),
-};
-
 static int __init tc_action_init(void)
 {
-	int err;
-
-	err = register_pernet_subsys(&tcf_action_net_ops);
-	if (err)
-		return err;
-
 	rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index d92f44ac4c39..6207f265b87c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2515,55 +2515,10 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
 }
 EXPORT_SYMBOL(tcf_exts_dump_stats);
 
-static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
-				       enum tc_setup_type type,
-				       void *type_data, bool err_stop)
-{
-	int ok_count = 0;
-#ifdef CONFIG_NET_CLS_ACT
-	const struct tc_action *a;
-	struct net_device *dev;
-	int i, ret;
-
-	if (!tcf_exts_has_actions(exts))
-		return 0;
-
-	for (i = 0; i < exts->nr_actions; i++) {
-		a = exts->actions[i];
-		if (!a->ops->get_dev)
-			continue;
-		dev = a->ops->get_dev(a);
-		if (!dev)
-			continue;
-		ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop);
-		a->ops->put_dev(dev);
-		if (ret < 0)
-			return ret;
-		ok_count += ret;
-	}
-#endif
-	return ok_count;
-}
-
 int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
 		     enum tc_setup_type type, void *type_data, bool err_stop)
 {
-	int ok_count;
-	int ret;
-
-	ret = tcf_block_cb_call(block, type, type_data, err_stop);
-	if (ret < 0)
-		return ret;
-	ok_count = ret;
-
-	if (!exts || ok_count)
-		return ok_count;
-	ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
-	if (ret < 0)
-		return ret;
-	ok_count += ret;
-
-	return ok_count;
+	return tcf_block_cb_call(block, type, type_data, err_stop);
 }
 EXPORT_SYMBOL(tc_setup_cb_call);
 
-- 
cgit v1.2.3


From 8cc196d6ef86bbab01dbf16f6c596cf56aa0839e Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 10 Dec 2018 13:54:07 -0800
Subject: neighbor: gc_list changes should be protected by table lock

Adding and removing neighbor entries to / from the gc_list need to be
done while holding the table lock; a couple of places were missed in the
original patch.

Move the list_add_tail in neigh_alloc to ___neigh_create where the lock
is already obtained. Since neighbor entries should rarely be moved
to/from PERMANENT state, add lock/unlock around the gc_list changes in
neigh_change_state rather than extending the lock hold around all
neighbor updates.

Fixes: 58956317c8de ("neighbor: Improve garbage collection")
Reported-by: Andrei Vagin <avagin@gmail.com>
Reported-by: syzbot+6cc2fd1d3bdd2e007363@syzkaller.appspotmail.com
Reported-by: syzbot+35e87b87c00f386b041f@syzkaller.appspotmail.com
Reported-by: syzbot+b354d1fb59091ea73c37@syzkaller.appspotmail.com
Reported-by: syzbot+3ddead5619658537909b@syzkaller.appspotmail.com
Reported-by: syzbot+424d47d5c456ce8b2bbe@syzkaller.appspotmail.com
Reported-by: syzbot+e4d42eb35f6a27b0a628@syzkaller.appspotmail.com
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index c3b58712e98b..03fdc5ae66b0 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -138,11 +138,17 @@ static void neigh_change_state(struct neighbour *n, u8 new)
 	 * add to the gc list if new state is not permanent
 	 */
 	if (new_is_perm && on_gc_list) {
+		write_lock_bh(&n->tbl->lock);
 		list_del_init(&n->gc_list);
+		write_unlock_bh(&n->tbl->lock);
+
 		atomic_dec(&n->tbl->gc_entries);
 	} else if (!new_is_perm && !on_gc_list) {
 		/* add entries to the tail; cleaning removes from the front */
+		write_lock_bh(&n->tbl->lock);
 		list_add_tail(&n->gc_list, &n->tbl->gc_list);
+		write_unlock_bh(&n->tbl->lock);
+
 		atomic_inc(&n->tbl->gc_entries);
 	}
 }
@@ -390,11 +396,7 @@ do_alloc:
 	n->tbl		  = tbl;
 	refcount_set(&n->refcnt, 1);
 	n->dead		  = 1;
-
-	if (!permanent)
-		list_add_tail(&n->gc_list, &n->tbl->gc_list);
-	else
-		INIT_LIST_HEAD(&n->gc_list);
+	INIT_LIST_HEAD(&n->gc_list);
 
 	atomic_inc(&tbl->entries);
 out:
@@ -616,6 +618,9 @@ static struct neighbour *___neigh_create(struct neigh_table *tbl,
 	}
 
 	n->dead = 0;
+	if (!permanent)
+		list_add_tail(&n->gc_list, &n->tbl->gc_list);
+
 	if (want_ref)
 		neigh_hold(n);
 	rcu_assign_pointer(n->next,
-- 
cgit v1.2.3


From 0bd72117fba2dd51a65eaa7b480adc0eea9a4409 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 11 Dec 2018 10:26:33 +0100
Subject: bpf: fix up uapi helper description and sync bpf header with tools

Minor markup fixup from bpf-next into net-next merge in the BPF helper
description of bpf_sk_lookup_tcp() and bpf_sk_lookup_udp(). Also sync
up the copy of bpf.h from tooling infrastructure.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/bpf.h       | 12 +++---
 tools/include/uapi/linux/bpf.h | 87 +++++++++++++++++++++---------------------
 2 files changed, 50 insertions(+), 49 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 92e962ba0c47..aa582cd5bfcf 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2218,9 +2218,9 @@ union bpf_attr {
  *		This helper is available only if the kernel was compiled with
  *		**CONFIG_NET** configuration option.
  *	Return
- *		Pointer to *struct bpf_sock*, or NULL in case of failure.
- *		For sockets with reuseport option, the *struct bpf_sock*
- *		result is from reuse->socks[] using the hash of the tuple.
+ *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ *		For sockets with reuseport option, the **struct bpf_sock**
+ *		result is from **reuse->socks**\ [] using the hash of the tuple.
  *
  * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *	Description
@@ -2254,9 +2254,9 @@ union bpf_attr {
  *		This helper is available only if the kernel was compiled with
  *		**CONFIG_NET** configuration option.
  *	Return
- *		Pointer to *struct bpf_sock*, or NULL in case of failure.
- *		For sockets with reuseport option, the *struct bpf_sock*
- *		result is from reuse->socks[] using the hash of the tuple.
+ *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ *		For sockets with reuseport option, the **struct bpf_sock**
+ *		result is from **reuse->socks**\ [] using the hash of the tuple.
  *
  * int bpf_sk_release(struct bpf_sock *sock)
  *	Description
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 94c002584068..aa582cd5bfcf 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -502,18 +502,6 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_map_pop_elem(struct bpf_map *map, void *value)
- * 	Description
- * 		Pop an element from *map*.
- * Return
- * 		0 on success, or a negative error in case of failure.
- *
- * int bpf_map_peek_elem(struct bpf_map *map, void *value)
- * 	Description
- * 		Get an element from *map* without removing it.
- * Return
- * 		0 on success, or a negative error in case of failure.
- *
  * int bpf_probe_read(void *dst, u32 size, const void *src)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
@@ -1937,9 +1925,9 @@ union bpf_attr {
  *		is set to metric from route (IPv4/IPv6 only), and ifindex
  *		is set to the device index of the nexthop from the FIB lookup.
  *
- *             *plen* argument is the size of the passed in struct.
- *             *flags* argument can be a combination of one or more of the
- *             following values:
+ *		*plen* argument is the size of the passed in struct.
+ *		*flags* argument can be a combination of one or more of the
+ *		following values:
  *
  *		**BPF_FIB_LOOKUP_DIRECT**
  *			Do a direct table lookup vs full lookup using FIB
@@ -1948,9 +1936,9 @@ union bpf_attr {
  *			Perform lookup from an egress perspective (default is
  *			ingress).
  *
- *             *ctx* is either **struct xdp_md** for XDP programs or
- *             **struct sk_buff** tc cls_act programs.
- *     Return
+ *		*ctx* is either **struct xdp_md** for XDP programs or
+ *		**struct sk_buff** tc cls_act programs.
+ *	Return
  *		* < 0 if any input argument is invalid
  *		*   0 on success (packet is forwarded, nexthop neighbor exists)
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
@@ -2095,8 +2083,8 @@ union bpf_attr {
  *		translated to a keycode using the rc keymap, and reported as
  *		an input key down event. After a period a key up event is
  *		generated. This period can be extended by calling either
- *		**bpf_rc_keydown** () again with the same values, or calling
- *		**bpf_rc_repeat** ().
+ *		**bpf_rc_keydown**\ () again with the same values, or calling
+ *		**bpf_rc_repeat**\ ().
  *
  *		Some protocols include a toggle bit, in case the button	was
  *		released and pressed again between consecutive scancodes.
@@ -2179,21 +2167,22 @@ union bpf_attr {
  *		The *flags* meaning is specific for each map type,
  *		and has to be 0 for cgroup local storage.
  *
- *		Depending on the bpf program type, a local storage area
- *		can be shared between multiple instances of the bpf program,
+ *		Depending on the BPF program type, a local storage area
+ *		can be shared between multiple instances of the BPF program,
  *		running simultaneously.
  *
  *		A user should care about the synchronization by himself.
- *		For example, by using the BPF_STX_XADD instruction to alter
+ *		For example, by using the **BPF_STX_XADD** instruction to alter
  *		the shared data.
  *	Return
- *		Pointer to the local storage area.
+ *		A pointer to the local storage area.
  *
  * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
  *	Description
- *		Select a SO_REUSEPORT sk from a	BPF_MAP_TYPE_REUSEPORT_ARRAY map
- *		It checks the selected sk is matching the incoming
- *		request in the skb.
+ *		Select a **SO_REUSEPORT** socket from a
+ *		**BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*.
+ *		It checks the selected socket is matching the incoming
+ *		request in the socket buffer.
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
@@ -2201,7 +2190,7 @@ union bpf_attr {
  *	Description
  *		Look for TCP socket matching *tuple*, optionally in a child
  *		network namespace *netns*. The return value must be checked,
- *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *		and if non-**NULL**, released via **bpf_sk_release**\ ().
  *
  *		The *ctx* should point to the context of the program, such as
  *		the skb or socket (depending on the hook in use). This is used
@@ -2229,15 +2218,15 @@ union bpf_attr {
  *		This helper is available only if the kernel was compiled with
  *		**CONFIG_NET** configuration option.
  *	Return
- *		Pointer to *struct bpf_sock*, or NULL in case of failure.
- *		For sockets with reuseport option, the *struct bpf_sock*
- *		result is from reuse->socks[] using the hash of the tuple.
+ *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ *		For sockets with reuseport option, the **struct bpf_sock**
+ *		result is from **reuse->socks**\ [] using the hash of the tuple.
  *
  * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *	Description
  *		Look for UDP socket matching *tuple*, optionally in a child
  *		network namespace *netns*. The return value must be checked,
- *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *		and if non-**NULL**, released via **bpf_sk_release**\ ().
  *
  *		The *ctx* should point to the context of the program, such as
  *		the skb or socket (depending on the hook in use). This is used
@@ -2265,42 +2254,54 @@ union bpf_attr {
  *		This helper is available only if the kernel was compiled with
  *		**CONFIG_NET** configuration option.
  *	Return
- *		Pointer to *struct bpf_sock*, or NULL in case of failure.
- *		For sockets with reuseport option, the *struct bpf_sock*
- *		result is from reuse->socks[] using the hash of the tuple.
+ *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ *		For sockets with reuseport option, the **struct bpf_sock**
+ *		result is from **reuse->socks**\ [] using the hash of the tuple.
  *
- * int bpf_sk_release(struct bpf_sock *sk)
+ * int bpf_sk_release(struct bpf_sock *sock)
  *	Description
- *		Release the reference held by *sock*. *sock* must be a non-NULL
- *		pointer that was returned from bpf_sk_lookup_xxx\ ().
+ *		Release the reference held by *sock*. *sock* must be a
+ *		non-**NULL** pointer that was returned from
+ *		**bpf_sk_lookup_xxx**\ ().
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
+ * int bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Pop an element from *map*.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Get an element from *map* without removing it.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
  *	Description
- *		For socket policies, insert *len* bytes into msg at offset
+ *		For socket policies, insert *len* bytes into *msg* at offset
  *		*start*.
  *
  *		If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
- *		*msg* it may want to insert metadata or options into the msg.
+ *		*msg* it may want to insert metadata or options into the *msg*.
  *		This can later be read and used by any of the lower layer BPF
  *		hooks.
  *
  *		This helper may fail if under memory pressure (a malloc
  *		fails) in these cases BPF programs will get an appropriate
  *		error and BPF programs will need to handle them.
- *
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
  * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags)
- *	 Description
+ *	Description
  *		Will remove *pop* bytes from a *msg* starting at byte *start*.
  *		This may result in **ENOMEM** errors under certain situations if
  *		an allocation and copy are required due to a full ring buffer.
  *		However, the helper will try to avoid doing the allocation
  *		if possible. Other errors can occur if input parameters are
- *		invalid either due to *start* byte not being valid part of msg
+ *		invalid either due to *start* byte not being valid part of *msg*
  *		payload and/or *pop* value being to large.
  *	Return
  *		0 on success, or a negative error in case of failure.
-- 
cgit v1.2.3


From 1228e912c9343d35b21663af82dea39dd8a575b8 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sun, 18 Nov 2018 08:25:17 +0200
Subject: net/mlx5: Consider encapsulation properties when comparing
 destinations

Currently the driver identifies identical vport destinations by
comparing the vport ID. The FW extended destination feature enables the
driver to forward the packet to the same vport with multiple
encapsulation properties.

Change the vport destination comparison logic to compare
the encapsulation properties in addition to the vport ID.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Acked-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 9d73eb955f75..f21277e636a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1373,7 +1373,10 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
 {
 	if (d1->type == d2->type) {
 		if ((d1->type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
-		     d1->vport.num == d2->vport.num) ||
+		     d1->vport.num == d2->vport.num &&
+		     d1->vport.flags == d2->vport.flags &&
+		     ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ?
+		      (d1->vport.reformat_id == d2->vport.reformat_id) : true)) ||
 		    (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
 		     d1->ft == d2->ft) ||
 		    (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
-- 
cgit v1.2.3


From e85e02bad29e822c3ebde80e7c9e7428329c4a5b Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Fri, 23 Nov 2018 09:38:27 +0200
Subject: net/mlx5: E-Switch, Rename esw attr mirror count field

The mirror count esw attributes field is used to determine if splitting
the rule to two FTEs is required while programming e-switch mirroring.
Rename it to split count, making it clearer with no functional change.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c            | 14 +++++++-------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h          |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 14 +++++++-------
 3 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index abc200947e84..342f807543a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -838,7 +838,7 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
 	if (IS_ERR(rule))
 		return rule;
 
-	if (attr->mirror_count) {
+	if (attr->split_count) {
 		flow->rule[1] = mlx5_eswitch_add_fwd_rule(esw, spec, attr);
 		if (IS_ERR(flow->rule[1])) {
 			mlx5_eswitch_del_offloaded_rule(esw, rule, attr);
@@ -857,7 +857,7 @@ mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw,
 {
 	flow->flags &= ~MLX5E_TC_FLOW_OFFLOADED;
 
-	if (attr->mirror_count)
+	if (attr->split_count)
 		mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr);
 
 	mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr);
@@ -873,7 +873,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
 
 	memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr));
 	slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
-	slow_attr->mirror_count = 0,
+	slow_attr->split_count = 0,
 	slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN,
 
 	rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr);
@@ -2427,7 +2427,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				return err;
 
 			action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-			attr->mirror_count = attr->out_count;
+			attr->split_count = attr->out_count;
 			continue;
 		}
 
@@ -2501,7 +2501,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				encap = true;
 			else
 				return -EOPNOTSUPP;
-			attr->mirror_count = attr->out_count;
+			attr->split_count = attr->out_count;
 			continue;
 		}
 
@@ -2511,7 +2511,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			if (err)
 				return err;
 
-			attr->mirror_count = attr->out_count;
+			attr->split_count = attr->out_count;
 			continue;
 		}
 
@@ -2546,7 +2546,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 	if (!actions_match_supported(priv, exts, parse_attr, flow, extack))
 		return -EOPNOTSUPP;
 
-	if (attr->mirror_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) {
+	if (attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "current firmware doesn't support split rule for port mirroring");
 		netdev_warn_once(priv->netdev, "current firmware doesn't support split rule for port mirroring\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 480ffa294867..c28ff6487dfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -287,7 +287,7 @@ struct mlx5_esw_flow_attr {
 	struct mlx5_core_dev	*out_mdev[MLX5_MAX_FLOW_FWD_VPORTS];
 	struct mlx5_core_dev	*in_mdev;
 
-	int mirror_count;
+	int split_count;
 	int out_count;
 
 	int	action;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 4d7b65df32ef..63ac9d3d1690 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -81,7 +81,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 {
 	struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {};
 	struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, };
-	bool mirror = !!(attr->mirror_count);
+	bool split = !!(attr->split_count);
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_table *fdb;
 	int j, i = 0;
@@ -120,7 +120,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 			dest[i].ft = ft;
 			i++;
 		} else {
-			for (j = attr->mirror_count; j < attr->out_count; j++) {
+			for (j = attr->split_count; j < attr->out_count; j++) {
 				dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
 				dest[i].vport.num = attr->out_rep[j]->vport;
 				dest[i].vport.vhca_id =
@@ -167,7 +167,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT)
 		flow_act.reformat_id = attr->encap_id;
 
-	fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!mirror);
+	fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!split);
 	if (IS_ERR(fdb)) {
 		rule = ERR_CAST(fdb);
 		goto err_esw_get;
@@ -182,7 +182,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	return rule;
 
 err_add_rule:
-	esw_put_prio_table(esw, attr->chain, attr->prio, !!mirror);
+	esw_put_prio_table(esw, attr->chain, attr->prio, !!split);
 err_esw_get:
 	if (attr->dest_chain)
 		esw_put_prio_table(esw, attr->dest_chain, 1, 0);
@@ -216,7 +216,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 	}
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-	for (i = 0; i < attr->mirror_count; i++) {
+	for (i = 0; i < attr->split_count; i++) {
 		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
 		dest[i].vport.num = attr->out_rep[i]->vport;
 		dest[i].vport.vhca_id =
@@ -270,7 +270,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
 			struct mlx5_esw_flow_attr *attr,
 			bool fwd_rule)
 {
-	bool mirror = (attr->mirror_count > 0);
+	bool split = (attr->split_count > 0);
 
 	mlx5_del_flow_rules(rule);
 	esw->offloads.num_flows--;
@@ -279,7 +279,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
 		esw_put_prio_table(esw, attr->chain, attr->prio, 1);
 		esw_put_prio_table(esw, attr->chain, attr->prio, 0);
 	} else {
-		esw_put_prio_table(esw, attr->chain, attr->prio, !!mirror);
+		esw_put_prio_table(esw, attr->chain, attr->prio, !!split);
 		if (attr->dest_chain)
 			esw_put_prio_table(esw, attr->dest_chain, 1, 0);
 	}
-- 
cgit v1.2.3


From df65a573eab28059e5dd1d5c32ad270dcf9cbf24 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sat, 1 Dec 2018 09:40:43 +0200
Subject: net/mlx5e: Refactor eswitch flow attr for destination specific
 properties

Currently the eswitch flow attr structure stores each destination
specific property in its own specific array.
Group them in an array of destination structures as a pre-step towards
adding additional destination specific field properties.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c          | 13 ++++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h        |  6 ++++--
 .../net/ethernet/mellanox/mlx5/core/eswitch_offloads.c   | 16 ++++++++--------
 3 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 342f807543a0..b24b758f467d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -939,8 +939,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		}
 		out_priv = netdev_priv(encap_dev);
 		rpriv = out_priv->ppriv;
-		attr->out_rep[attr->out_count] = rpriv->rep;
-		attr->out_mdev[attr->out_count++] = out_priv->mdev;
+		attr->dests[attr->out_count].rep = rpriv->rep;
+		attr->dests[attr->out_count++].mdev = out_priv->mdev;
 	}
 
 	err = mlx5_eswitch_add_vlan_action(esw, attr);
@@ -2468,8 +2468,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 					  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 				out_priv = netdev_priv(out_dev);
 				rpriv = out_priv->ppriv;
-				attr->out_rep[attr->out_count] = rpriv->rep;
-				attr->out_mdev[attr->out_count++] = out_priv->mdev;
+				attr->dests[attr->out_count].rep = rpriv->rep;
+				attr->dests[attr->out_count].mdev = out_priv->mdev;
+				attr->out_count++;
 			} else if (encap) {
 				parse_attr->mirred_ifindex = out_dev->ifindex;
 				parse_attr->tun_info = *info;
@@ -2477,7 +2478,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
 					  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 					  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-				/* attr->out_rep is resolved when we handle encap */
+				/* attr->dests[].rep is resolved when we
+				 * handle encap
+				 */
 			} else if (parse_attr->filter_dev != priv->netdev) {
 				/* All mlx5 devices are called to configure
 				 * high level device filters. Therefore, the
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index c28ff6487dfd..5468975a1bdb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -283,8 +283,6 @@ enum mlx5_flow_match_level {
 
 struct mlx5_esw_flow_attr {
 	struct mlx5_eswitch_rep *in_rep;
-	struct mlx5_eswitch_rep *out_rep[MLX5_MAX_FLOW_FWD_VPORTS];
-	struct mlx5_core_dev	*out_mdev[MLX5_MAX_FLOW_FWD_VPORTS];
 	struct mlx5_core_dev	*in_mdev;
 
 	int split_count;
@@ -297,6 +295,10 @@ struct mlx5_esw_flow_attr {
 	u8	total_vlan;
 	bool	vlan_handled;
 	u32	encap_id;
+	struct {
+		struct mlx5_eswitch_rep *rep;
+		struct mlx5_core_dev *mdev;
+	} dests[MLX5_MAX_FLOW_FWD_VPORTS];
 	u32	mod_hdr_id;
 	u8	match_level;
 	struct mlx5_fc *counter;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 63ac9d3d1690..7cbe602129b7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -122,9 +122,9 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		} else {
 			for (j = attr->split_count; j < attr->out_count; j++) {
 				dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-				dest[i].vport.num = attr->out_rep[j]->vport;
+				dest[i].vport.num = attr->dests[j].rep->vport;
 				dest[i].vport.vhca_id =
-					MLX5_CAP_GEN(attr->out_mdev[j], vhca_id);
+					MLX5_CAP_GEN(attr->dests[j].mdev, vhca_id);
 				if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
 					dest[i].vport.flags |=
 						MLX5_FLOW_DEST_VPORT_VHCA_ID;
@@ -218,9 +218,9 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	for (i = 0; i < attr->split_count; i++) {
 		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-		dest[i].vport.num = attr->out_rep[i]->vport;
+		dest[i].vport.num = attr->dests[i].rep->vport;
 		dest[i].vport.vhca_id =
-			MLX5_CAP_GEN(attr->out_mdev[i], vhca_id);
+			MLX5_CAP_GEN(attr->dests[i].mdev, vhca_id);
 		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
 			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	}
@@ -327,7 +327,7 @@ esw_vlan_action_get_vport(struct mlx5_esw_flow_attr *attr, bool push, bool pop)
 	struct mlx5_eswitch_rep *in_rep, *out_rep, *vport = NULL;
 
 	in_rep  = attr->in_rep;
-	out_rep = attr->out_rep[0];
+	out_rep = attr->dests[0].rep;
 
 	if (push)
 		vport = in_rep;
@@ -348,7 +348,7 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
 		goto out_notsupp;
 
 	in_rep  = attr->in_rep;
-	out_rep = attr->out_rep[0];
+	out_rep = attr->dests[0].rep;
 
 	if (push && in_rep->vport == FDB_UPLINK_VPORT)
 		goto out_notsupp;
@@ -400,7 +400,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->out_rep[0]->vport == FDB_UPLINK_VPORT) {
+		if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT) {
 			vport->vlan_refcount++;
 			attr->vlan_handled = true;
 		}
@@ -460,7 +460,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->out_rep[0]->vport == FDB_UPLINK_VPORT)
+		if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT)
 			vport->vlan_refcount--;
 
 		return 0;
-- 
cgit v1.2.3


From f493f15534ecb5c2c295ba49a2add5822d05ae19 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sat, 1 Dec 2018 09:40:43 +0200
Subject: net/mlx5e: Move flow attr reformat action bit to per dest flags

Flow attr reformat action bit is moved from the global action bits to a
per destination flags field, as a pre-step for adding additional flags
to support encapsulation properties per destination, with no
functionality change.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 37 ++++++++++++----------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  5 +++
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c |  7 ++--
 3 files changed, 30 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b24b758f467d..e48fbb7d9735 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -908,6 +908,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	struct mlx5e_rep_priv *rpriv;
 	struct mlx5e_priv *out_priv;
 	int err = 0, encap_err = 0;
+	int out_index;
 
 	/* if prios are not supported, keep the old behaviour of using same prio
 	 * for all offloaded rules.
@@ -927,7 +928,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		goto err_max_prio_chain;
 	}
 
-	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) {
+	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
+		if (!(attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
+			continue;
+
 		out_dev = __dev_get_by_index(dev_net(priv->netdev),
 					     attr->parse_attr->mirred_ifindex);
 		encap_err = mlx5e_attach_encap(priv, &parse_attr->tun_info,
@@ -991,8 +995,11 @@ err_create_counter:
 err_mod_hdr:
 	mlx5_eswitch_del_vlan_action(esw, attr);
 err_add_vlan:
-	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT)
-		mlx5e_detach_encap(priv, flow);
+	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
+		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) {
+			mlx5e_detach_encap(priv, flow);
+			break;
+		}
 err_attach_encap:
 err_max_prio_chain:
 	return err;
@@ -1004,6 +1011,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct mlx5_esw_flow_attr slow_attr;
+	int out_index;
 
 	if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
 		if (flow->flags & MLX5E_TC_FLOW_SLOW)
@@ -1014,10 +1022,12 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 
 	mlx5_eswitch_del_vlan_action(esw, attr);
 
-	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) {
-		mlx5e_detach_encap(priv, flow);
-		kvfree(attr->parse_attr);
-	}
+	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
+		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) {
+			mlx5e_detach_encap(priv, flow);
+			break;
+		}
+	kvfree(attr->parse_attr);
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		mlx5e_detach_mod_hdr(priv, flow);
@@ -2461,11 +2471,11 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				return -EOPNOTSUPP;
 			}
 
+			action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+				  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 			if (switchdev_port_same_parent_id(priv->netdev,
 							  out_dev) ||
 			    is_merged_eswitch_dev(priv, out_dev)) {
-				action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
-					  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 				out_priv = netdev_priv(out_dev);
 				rpriv = out_priv->ppriv;
 				attr->dests[attr->out_count].rep = rpriv->rep;
@@ -2475,9 +2485,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				parse_attr->mirred_ifindex = out_dev->ifindex;
 				parse_attr->tun_info = *info;
 				attr->parse_attr = parse_attr;
-				action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
-					  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
-					  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+				attr->dests[attr->out_count].flags |=
+					MLX5_ESW_DEST_ENCAP;
 				/* attr->dests[].rep is resolved when we
 				 * handle encap
 				 */
@@ -2657,10 +2666,6 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto err_free;
 
-	if (!(flow->esw_attr->action &
-	      MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT))
-		kvfree(parse_attr);
-
 	*__flow = flow;
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 5468975a1bdb..39363d4662b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -281,6 +281,10 @@ enum mlx5_flow_match_level {
 /* current maximum for flow based vport multicasting */
 #define MLX5_MAX_FLOW_FWD_VPORTS 2
 
+enum {
+	MLX5_ESW_DEST_ENCAP         = BIT(0),
+};
+
 struct mlx5_esw_flow_attr {
 	struct mlx5_eswitch_rep *in_rep;
 	struct mlx5_core_dev	*in_mdev;
@@ -296,6 +300,7 @@ struct mlx5_esw_flow_attr {
 	bool	vlan_handled;
 	u32	encap_id;
 	struct {
+		u32 flags;
 		struct mlx5_eswitch_rep *rep;
 		struct mlx5_core_dev *mdev;
 	} dests[MLX5_MAX_FLOW_FWD_VPORTS];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 7cbe602129b7..0387b5068be6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -128,6 +128,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 				if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
 					dest[i].vport.flags |=
 						MLX5_FLOW_DEST_VPORT_VHCA_ID;
+				if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) {
+					flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+					flow_act.reformat_id = attr->encap_id;
+				}
 				i++;
 			}
 		}
@@ -164,9 +168,6 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		flow_act.modify_id = attr->mod_hdr_id;
 
-	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT)
-		flow_act.reformat_id = attr->encap_id;
-
 	fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!split);
 	if (IS_ERR(fdb)) {
 		rule = ERR_CAST(fdb);
-- 
cgit v1.2.3


From a18e879d4e45b6aef73f42c765cd0da4b26f4260 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Tue, 4 Dec 2018 08:06:41 +0200
Subject: net/mlx5e: Annul encap action ordering requirement

Currently a FW syndrome is emitted if the driver configures a
multi-destination FTE where the first destination is a tunneled uplink
port and the second destination is a local vPort.

Support this scenario by creating a multi-destination FTE using the
firmware's extended destination capabilities.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 0387b5068be6..bb96c4661e26 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -131,6 +131,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 				if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) {
 					flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
 					flow_act.reformat_id = attr->encap_id;
+					dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
+					dest[i].vport.reformat_id = attr->encap_id;
 				}
 				i++;
 			}
-- 
cgit v1.2.3


From 38c9d2697b9c0d928875ea45b5e2fd706df7ad7e Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Thu, 22 Nov 2018 14:04:33 +0200
Subject: net/mlx5e: Replace the split logic with extended destination

Currently the FTE encap flag applies to all destinations.
To support mirroring encapsulated traffic to a local port the driver
split the two destinations to two flow table entries:
Table#0: - FWD to the local vport
         - Goto table#1
Table#1: - Encap and FWD to wire
The firmware extended destination capabilities enable the driver to set
an encapsulation flag per destination.

Remove the split logic and use the extended destination mechanism
instead.

Note that split technique is still required for pedit and VLAN push
scenarios.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e48fbb7d9735..1e3688a0c4f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2513,7 +2513,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				encap = true;
 			else
 				return -EOPNOTSUPP;
-			attr->split_count = attr->out_count;
 			continue;
 		}
 
-- 
cgit v1.2.3


From 1cc26d74bb98bd9693f0e630ee1cac87d5ba9f20 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Mon, 26 Nov 2018 07:24:08 +0200
Subject: net/mlx5e: Support header rewrite actions with remote port mirroring

A rule with the following actions is split to a two level FDB:
1. Forward to local mirror vport
2. Header rewrite
3. Forward to local vport
In the first level flow table, forward the packet to the local port and
forward the packet to the second level flow table for header rewrite and
local port forwarding. This configuration fails when mirroring to a
remote encapsulated destination because currently an FTE cannot support
encap and table destinations.

Use the extended destination capabilities to configure the first level
flow table with a multi-destination FTE to the uplink and second level
table and the second level flow table for the header rewrite and local
port forwarding.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c            | 5 +++--
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 4 ++++
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 1e3688a0c4f9..4030462f56dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -943,8 +943,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		}
 		out_priv = netdev_priv(encap_dev);
 		rpriv = out_priv->ppriv;
-		attr->dests[attr->out_count].rep = rpriv->rep;
-		attr->dests[attr->out_count++].mdev = out_priv->mdev;
+		attr->dests[out_index].rep = rpriv->rep;
+		attr->dests[out_index].mdev = out_priv->mdev;
 	}
 
 	err = mlx5_eswitch_add_vlan_action(esw, attr);
@@ -2487,6 +2487,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				attr->parse_attr = parse_attr;
 				attr->dests[attr->out_count].flags |=
 					MLX5_ESW_DEST_ENCAP;
+				attr->out_count++;
 				/* attr->dests[].rep is resolved when we
 				 * handle encap
 				 */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index bb96c4661e26..b0652e44a68d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -226,6 +226,10 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 			MLX5_CAP_GEN(attr->dests[i].mdev, vhca_id);
 		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
 			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
+		if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) {
+			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
+			dest[i].vport.reformat_id = attr->encap_id;
+		}
 	}
 	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest[i].ft = fwd_fdb,
-- 
cgit v1.2.3


From 98b66cb1c9ff6ffbc6133ed649b2731638520992 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sun, 18 Nov 2018 13:16:52 +0200
Subject: net/mlx5e: Change parse attr struct to accommodate multiple tunnel
 infos

Currently the driver can support only a single TC tunnel_set action.
Change the tunnel info fields to arrays, as a pre-step to support
multiple encapsulations for a single flow, with no functional change.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 4030462f56dc..67b3c6f1aeae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -94,12 +94,12 @@ struct mlx5e_tc_flow {
 };
 
 struct mlx5e_tc_flow_parse_attr {
-	struct ip_tunnel_info tun_info;
+	struct ip_tunnel_info tun_info[MLX5_MAX_FLOW_FWD_VPORTS];
 	struct net_device *filter_dev;
 	struct mlx5_flow_spec spec;
 	int num_mod_hdr_actions;
 	void *mod_hdr_actions;
-	int mirred_ifindex;
+	int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS];
 };
 
 #define MLX5E_TC_TABLE_NUM_GROUPS 4
@@ -571,7 +571,7 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 				  struct mlx5e_tc_flow_parse_attr *parse_attr,
 				  struct netlink_ext_ack *extack)
 {
-	int peer_ifindex = parse_attr->mirred_ifindex;
+	int peer_ifindex = parse_attr->mirred_ifindex[0];
 	struct mlx5_hairpin_params params;
 	struct mlx5_core_dev *peer_mdev;
 	struct mlx5e_hairpin_entry *hpe;
@@ -933,8 +933,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 			continue;
 
 		out_dev = __dev_get_by_index(dev_net(priv->netdev),
-					     attr->parse_attr->mirred_ifindex);
-		encap_err = mlx5e_attach_encap(priv, &parse_attr->tun_info,
+					     attr->parse_attr->mirred_ifindex[0]);
+		encap_err = mlx5e_attach_encap(priv, &parse_attr->tun_info[0],
 					       out_dev, &encap_dev, flow,
 					       extack);
 		if (encap_err && encap_err != -EAGAIN) {
@@ -2220,7 +2220,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 
 			if (priv->netdev->netdev_ops == peer_dev->netdev_ops &&
 			    same_hw_devs(priv, netdev_priv(peer_dev))) {
-				parse_attr->mirred_ifindex = peer_dev->ifindex;
+				parse_attr->mirred_ifindex[0] = peer_dev->ifindex;
 				flow->flags |= MLX5E_TC_FLOW_HAIRPIN;
 				action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 					  MLX5_FLOW_CONTEXT_ACTION_COUNT;
@@ -2482,8 +2482,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				attr->dests[attr->out_count].mdev = out_priv->mdev;
 				attr->out_count++;
 			} else if (encap) {
-				parse_attr->mirred_ifindex = out_dev->ifindex;
-				parse_attr->tun_info = *info;
+				parse_attr->mirred_ifindex[0] = out_dev->ifindex;
+				parse_attr->tun_info[0] = *info;
 				attr->parse_attr = parse_attr;
 				attr->dests[attr->out_count].flags |=
 					MLX5_ESW_DEST_ENCAP;
-- 
cgit v1.2.3


From 79baaec71989afa805a0f2dd532451a6103e11b4 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sun, 2 Dec 2018 09:44:13 +0200
Subject: net/mlx5e: Allow association of a flow to multiple encaps

Currently a flow can be associated with a single encap entry. The
extended destination feature enables the driver to configure multiple
encap entries per flow.

Change the encap flow association field to array as a pre-step towards
supporting multiple encap destinations. Use only the first array
element, with no functional change.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 48 +++++++++++++++++++++----
 1 file changed, 41 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 67b3c6f1aeae..58b83489a6d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -78,13 +78,39 @@ enum {
 
 #define MLX5E_TC_MAX_SPLITS 1
 
+/* Helper struct for accessing a struct containing list_head array.
+ * Containing struct
+ *   |- Helper array
+ *      [0] Helper item 0
+ *          |- list_head item 0
+ *          |- index (0)
+ *      [1] Helper item 1
+ *          |- list_head item 1
+ *          |- index (1)
+ * To access the containing struct from one of the list_head items:
+ * 1. Get the helper item from the list_head item using
+ *    helper item =
+ *        container_of(list_head item, helper struct type, list_head field)
+ * 2. Get the contining struct from the helper item and its index in the array:
+ *    containing struct =
+ *        container_of(helper item, containing struct type, helper field[index])
+ */
+struct encap_flow_item {
+	struct list_head list;
+	int index;
+};
+
 struct mlx5e_tc_flow {
 	struct rhash_head	node;
 	struct mlx5e_priv	*priv;
 	u64			cookie;
 	u16			flags;
 	struct mlx5_flow_handle *rule[MLX5E_TC_MAX_SPLITS + 1];
-	struct list_head	encap;   /* flows sharing the same encap ID */
+	/* Flow can be associated with multiple encap IDs.
+	 * The number of encaps is bounded by the number of supported
+	 * destinations.
+	 */
+	struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS];
 	struct list_head	mod_hdr; /* flows sharing the same mod hdr ID */
 	struct list_head	hairpin; /* flows sharing the same hairpin */
 	union {
@@ -1043,6 +1069,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 	struct mlx5_esw_flow_attr slow_attr, *esw_attr;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
+	struct encap_flow_item *efi;
 	struct mlx5e_tc_flow *flow;
 	int err;
 
@@ -1059,7 +1086,8 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
 	mlx5e_rep_queue_neigh_stats_work(priv);
 
-	list_for_each_entry(flow, &e->flows, encap) {
+	list_for_each_entry(efi, &e->flows, list) {
+		flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]);
 		esw_attr = flow->esw_attr;
 		esw_attr->encap_id = e->encap_id;
 		spec = &esw_attr->parse_attr->spec;
@@ -1086,10 +1114,12 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 	struct mlx5_esw_flow_attr slow_attr;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
+	struct encap_flow_item *efi;
 	struct mlx5e_tc_flow *flow;
 	int err;
 
-	list_for_each_entry(flow, &e->flows, encap) {
+	list_for_each_entry(efi, &e->flows, list) {
+		flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]);
 		spec = &flow->esw_attr->parse_attr->spec;
 
 		/* update from encap rule to slow path rule */
@@ -1142,9 +1172,12 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 		return;
 
 	list_for_each_entry(e, &nhe->encap_list, encap_list) {
+		struct encap_flow_item *efi;
 		if (!(e->flags & MLX5_ENCAP_ENTRY_VALID))
 			continue;
-		list_for_each_entry(flow, &e->flows, encap) {
+		list_for_each_entry(efi, &e->flows, list) {
+			flow = container_of(efi, struct mlx5e_tc_flow,
+					    encaps[efi->index]);
 			if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
 				counter = mlx5e_tc_get_counter(flow);
 				mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
@@ -1176,9 +1209,9 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 			       struct mlx5e_tc_flow *flow)
 {
-	struct list_head *next = flow->encap.next;
+	struct list_head *next = flow->encaps[0].list.next;
 
-	list_del(&flow->encap);
+	list_del(&flow->encaps[0].list);
 	if (list_empty(next)) {
 		struct mlx5e_encap_entry *e;
 
@@ -2338,7 +2371,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
 
 attach_flow:
-	list_add(&flow->encap, &e->flows);
+	list_add(&flow->encaps[0].list, &e->flows);
+	flow->encaps[0].index = 0;
 	*encap_dev = e->out_dev;
 	if (e->flags & MLX5_ENCAP_ENTRY_VALID)
 		attr->encap_id = e->encap_id;
-- 
cgit v1.2.3


From 8c4dc42bf6e4ffeda49cf5e26bfc991b548fc0aa Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sun, 18 Nov 2018 14:21:46 +0200
Subject: net/mlx5e: Support multiple encapsulations for a TC flow

Currently a flow is associated with a single encap structure. The FW
extended destination features enables the driver to associate a flow
with multiple encap instances.

Change the encap id field from a flow scope to a per destination value
in the flow attributes struct. Use the encaps array to associate a flow
table entry with multiple encap entries.

Update the neigh logic to offload only if all encapsulations used in a
flow are connected, and un-offload upon the first one disconnected.

Note that the driver can now support up to two encap destinations.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 85 ++++++++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  3 +-
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c |  7 +-
 3 files changed, 62 insertions(+), 33 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 58b83489a6d6..0921213561cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -843,14 +843,15 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
-			       struct mlx5e_tc_flow *flow);
+			       struct mlx5e_tc_flow *flow, int out_index);
 
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct ip_tunnel_info *tun_info,
 			      struct net_device *mirred_dev,
 			      struct net_device **encap_dev,
 			      struct mlx5e_tc_flow *flow,
-			      struct netlink_ext_ack *extack);
+			      struct netlink_ext_ack *extack,
+			      int out_index);
 
 static struct mlx5_flow_handle *
 mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
@@ -955,18 +956,22 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	}
 
 	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
+		int mirred_ifindex;
+
 		if (!(attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
 			continue;
 
+		mirred_ifindex = attr->parse_attr->mirred_ifindex[out_index];
 		out_dev = __dev_get_by_index(dev_net(priv->netdev),
-					     attr->parse_attr->mirred_ifindex[0]);
-		encap_err = mlx5e_attach_encap(priv, &parse_attr->tun_info[0],
-					       out_dev, &encap_dev, flow,
-					       extack);
-		if (encap_err && encap_err != -EAGAIN) {
-			err = encap_err;
+					     mirred_ifindex);
+		err = mlx5e_attach_encap(priv,
+					 &parse_attr->tun_info[out_index],
+					 out_dev, &encap_dev, flow,
+					 extack, out_index);
+		if (err && err != -EAGAIN)
 			goto err_attach_encap;
-		}
+		if (err == -EAGAIN)
+			encap_err = err;
 		out_priv = netdev_priv(encap_dev);
 		rpriv = out_priv->ppriv;
 		attr->dests[out_index].rep = rpriv->rep;
@@ -1022,10 +1027,8 @@ err_mod_hdr:
 	mlx5_eswitch_del_vlan_action(esw, attr);
 err_add_vlan:
 	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
-		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) {
-			mlx5e_detach_encap(priv, flow);
-			break;
-		}
+		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)
+			mlx5e_detach_encap(priv, flow, out_index);
 err_attach_encap:
 err_max_prio_chain:
 	return err;
@@ -1049,10 +1052,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	mlx5_eswitch_del_vlan_action(esw, attr);
 
 	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
-		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) {
-			mlx5e_detach_encap(priv, flow);
-			break;
-		}
+		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)
+			mlx5e_detach_encap(priv, flow, out_index);
 	kvfree(attr->parse_attr);
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
@@ -1087,11 +1088,30 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 	mlx5e_rep_queue_neigh_stats_work(priv);
 
 	list_for_each_entry(efi, &e->flows, list) {
+		bool all_flow_encaps_valid = true;
+		int i;
+
 		flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]);
 		esw_attr = flow->esw_attr;
-		esw_attr->encap_id = e->encap_id;
 		spec = &esw_attr->parse_attr->spec;
 
+		esw_attr->dests[efi->index].encap_id = e->encap_id;
+		esw_attr->dests[efi->index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
+		/* Flow can be associated with multiple encap entries.
+		 * Before offloading the flow verify that all of them have
+		 * a valid neighbour.
+		 */
+		for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) {
+			if (!(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP))
+				continue;
+			if (!(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID)) {
+				all_flow_encaps_valid = false;
+				break;
+			}
+		}
+		/* Do not offload flows with unresolved neighbors */
+		if (!all_flow_encaps_valid)
+			continue;
 		/* update from slow path rule to encap rule */
 		rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, esw_attr);
 		if (IS_ERR(rule)) {
@@ -1124,6 +1144,8 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 
 		/* update from encap rule to slow path rule */
 		rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec, &slow_attr);
+		/* mark the flow's encap dest as non-valid */
+		flow->esw_attr->dests[efi->index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID;
 
 		if (IS_ERR(rule)) {
 			err = PTR_ERR(rule);
@@ -1207,11 +1229,11 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 }
 
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
-			       struct mlx5e_tc_flow *flow)
+			       struct mlx5e_tc_flow *flow, int out_index)
 {
-	struct list_head *next = flow->encaps[0].list.next;
+	struct list_head *next = flow->encaps[out_index].list.next;
 
-	list_del(&flow->encaps[0].list);
+	list_del(&flow->encaps[out_index].list);
 	if (list_empty(next)) {
 		struct mlx5e_encap_entry *e;
 
@@ -2324,7 +2346,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct net_device *mirred_dev,
 			      struct net_device **encap_dev,
 			      struct mlx5e_tc_flow *flow,
-			      struct netlink_ext_ack *extack)
+			      struct netlink_ext_ack *extack,
+			      int out_index)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	unsigned short family = ip_tunnel_info_af(tun_info);
@@ -2371,13 +2394,15 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
 
 attach_flow:
-	list_add(&flow->encaps[0].list, &e->flows);
-	flow->encaps[0].index = 0;
+	list_add(&flow->encaps[out_index].list, &e->flows);
+	flow->encaps[out_index].index = out_index;
 	*encap_dev = e->out_dev;
-	if (e->flags & MLX5_ENCAP_ENTRY_VALID)
-		attr->encap_id = e->encap_id;
-	else
+	if (e->flags & MLX5_ENCAP_ENTRY_VALID) {
+		attr->dests[out_index].encap_id = e->encap_id;
+		attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
+	} else {
 		err = -EAGAIN;
+	}
 
 	return err;
 
@@ -2516,8 +2541,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				attr->dests[attr->out_count].mdev = out_priv->mdev;
 				attr->out_count++;
 			} else if (encap) {
-				parse_attr->mirred_ifindex[0] = out_dev->ifindex;
-				parse_attr->tun_info[0] = *info;
+				parse_attr->mirred_ifindex[attr->out_count] =
+					out_dev->ifindex;
+				parse_attr->tun_info[attr->out_count] = *info;
+				encap = false;
 				attr->parse_attr = parse_attr;
 				attr->dests[attr->out_count].flags |=
 					MLX5_ESW_DEST_ENCAP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 39363d4662b3..87c9dea9bccf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -283,6 +283,7 @@ enum mlx5_flow_match_level {
 
 enum {
 	MLX5_ESW_DEST_ENCAP         = BIT(0),
+	MLX5_ESW_DEST_ENCAP_VALID   = BIT(1),
 };
 
 struct mlx5_esw_flow_attr {
@@ -298,11 +299,11 @@ struct mlx5_esw_flow_attr {
 	u8	vlan_prio[MLX5_FS_VLAN_DEPTH];
 	u8	total_vlan;
 	bool	vlan_handled;
-	u32	encap_id;
 	struct {
 		u32 flags;
 		struct mlx5_eswitch_rep *rep;
 		struct mlx5_core_dev *mdev;
+		u32 encap_id;
 	} dests[MLX5_MAX_FLOW_FWD_VPORTS];
 	u32	mod_hdr_id;
 	u8	match_level;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b0652e44a68d..bde1fb8c284b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -130,9 +130,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 						MLX5_FLOW_DEST_VPORT_VHCA_ID;
 				if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) {
 					flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
-					flow_act.reformat_id = attr->encap_id;
+					flow_act.reformat_id = attr->dests[j].encap_id;
 					dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
-					dest[i].vport.reformat_id = attr->encap_id;
+					dest[i].vport.reformat_id =
+						attr->dests[j].encap_id;
 				}
 				i++;
 			}
@@ -228,7 +229,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 		if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) {
 			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
-			dest[i].vport.reformat_id = attr->encap_id;
+			dest[i].vport.reformat_id = attr->dests[i].encap_id;
 		}
 	}
 	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-- 
cgit v1.2.3


From 939de57d30344ce728b0de61be87984e75af420e Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@mellanox.com>
Date: Mon, 5 Nov 2018 16:05:37 -0600
Subject: net/mlx5e: Use CQE padding for Ethernet CQs

Writing 64B CQEs to 128B cache lines results in a RMW operation. Padding
the CQEs to 128B if possible improves performance on 128B cache line
systems like PPC.

Testing on PPC showed up to a 24% improvement in small packet throughput
vs the default behavior, depending on the workload and system topology.

Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |  2 ++
 drivers/net/ethernet/mellanox/mlx5/core/wq.c      |  3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/wq.h      |  7 ++++++-
 include/linux/mlx5/cq.h                           | 10 +++++-----
 4 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 88116a4750b0..2188e5ba908f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2224,6 +2224,8 @@ static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
 	void *cqc = param->cqc;
 
 	MLX5_SET(cqc, cqc, uar_page, priv->mdev->priv.uar->index);
+	if (MLX5_CAP_GEN(priv->mdev, cqe_128_always) && cache_line_size() >= 128)
+		MLX5_SET(cqc, cqc, cqe_sz, CQE_STRIDE_128_PAD);
 }
 
 static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index 2dcbf1ebfd6a..953cc8efba69 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -155,7 +155,8 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		     void *cqc, struct mlx5_cqwq *wq,
 		     struct mlx5_wq_ctrl *wq_ctrl)
 {
-	u8 log_wq_stride = MLX5_GET(cqc, cqc, cqe_sz) + 6;
+	/* CQE_STRIDE_128 and CQE_STRIDE_128_PAD both mean 128B stride */
+	u8 log_wq_stride = MLX5_GET(cqc, cqc, cqe_sz) == CQE_STRIDE_64 ? 6 : 7;
 	u8 log_wq_sz     = MLX5_GET(cqc, cqc, log_cq_size);
 	int err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index 9bc2184a46bc..ea934a48c90a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -179,7 +179,12 @@ static inline u32 mlx5_cqwq_get_ci(struct mlx5_cqwq *wq)
 
 static inline struct mlx5_cqe64 *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix)
 {
-	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
+	struct mlx5_cqe64 *cqe = mlx5_frag_buf_get_wqe(&wq->fbc, ix);
+
+	/* For 128B CQEs the data is in the last 64B */
+	cqe += wq->fbc.log_stride == 7;
+
+	return cqe;
 }
 
 static inline u32 mlx5_cqwq_get_ctr_wrap_cnt(struct mlx5_cqwq *wq, u32 ctr)
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 28b757a64029..612c8c2f2466 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -125,9 +125,9 @@ struct mlx5_cq_modify_params {
 };
 
 enum {
-	CQE_SIZE_64 = 0,
-	CQE_SIZE_128 = 1,
-	CQE_SIZE_128_PAD = 2,
+	CQE_STRIDE_64 = 0,
+	CQE_STRIDE_128 = 1,
+	CQE_STRIDE_128_PAD = 2,
 };
 
 #define MLX5_MAX_CQ_PERIOD (BIT(__mlx5_bit_sz(cqc, cq_period)) - 1)
@@ -135,8 +135,8 @@ enum {
 
 static inline int cqe_sz_to_mlx_sz(u8 size, int padding_128_en)
 {
-	return padding_128_en ? CQE_SIZE_128_PAD :
-				size == 64 ? CQE_SIZE_64 : CQE_SIZE_128;
+	return padding_128_en ? CQE_STRIDE_128_PAD :
+				size == 64 ? CQE_STRIDE_64 : CQE_STRIDE_128;
 }
 
 static inline void mlx5_cq_set_ci(struct mlx5_core_cq *cq)
-- 
cgit v1.2.3


From 75370eb0d3b802f54600f2fc3ae5255fe9270112 Mon Sep 17 00:00:00 2001
From: Eyal Davidovich <eyald@mellanox.com>
Date: Sun, 7 Oct 2018 15:18:37 +0300
Subject: net/mlx5e: Avoid query PPCNT register if not supported by the device

PPCNT is not supported if PCAM access reg is supported and ppcnt bit is clear.

Signed-off-by: Eyal Davidovich <eyald@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 12 ++++++++++++
 include/linux/mlx5/mlx5_ifc.h                      |  4 +++-
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 75d30fa637d6..8224f1e062a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -483,6 +483,9 @@ static int mlx5e_grp_802_3_fill_stats(struct mlx5e_priv *priv, u64 *data,
 	return idx;
 }
 
+#define MLX5_BASIC_PPCNT_SUPPORTED(mdev) \
+	(MLX5_CAP_GEN(mdev, pcam_reg) ? MLX5_CAP_PCAM_REG(mdev, ppcnt) : 1)
+
 static void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv)
 {
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
@@ -491,6 +494,9 @@ static void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv)
 	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
 	void *out;
 
+	if (!MLX5_BASIC_PPCNT_SUPPORTED(mdev))
+		return;
+
 	MLX5_SET(ppcnt_reg, in, local_port, 1);
 	out = pstats->IEEE_802_3_counters;
 	MLX5_SET(ppcnt_reg, in, grp, MLX5_IEEE_802_3_COUNTERS_GROUP);
@@ -603,6 +609,9 @@ static void mlx5e_grp_2819_update_stats(struct mlx5e_priv *priv)
 	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
 	void *out;
 
+	if (!MLX5_BASIC_PPCNT_SUPPORTED(mdev))
+		return;
+
 	MLX5_SET(ppcnt_reg, in, local_port, 1);
 	out = pstats->RFC_2819_counters;
 	MLX5_SET(ppcnt_reg, in, grp, MLX5_RFC_2819_COUNTERS_GROUP);
@@ -1078,6 +1087,9 @@ static void mlx5e_grp_per_prio_update_stats(struct mlx5e_priv *priv)
 	int prio;
 	void *out;
 
+	if (!MLX5_BASIC_PPCNT_SUPPORTED(mdev))
+		return;
+
 	MLX5_SET(ppcnt_reg, in, local_port, 1);
 	MLX5_SET(ppcnt_reg, in, grp, MLX5_PER_PRIORITY_COUNTERS_GROUP);
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 60c1d49eb40c..c12b0dec2889 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -8283,7 +8283,9 @@ struct mlx5_ifc_pcam_regs_5000_to_507f_bits {
 	u8         port_access_reg_cap_mask_31_to_13[0x13];
 	u8         pbmc[0x1];
 	u8         pptb[0x1];
-	u8         port_access_reg_cap_mask_10_to_0[0xb];
+	u8         port_access_reg_cap_mask_10_to_09[0x2];
+	u8         ppcnt[0x1];
+	u8         port_access_reg_cap_mask_07_to_00[0x8];
 };
 
 struct mlx5_ifc_pcam_reg_bits {
-- 
cgit v1.2.3


From 2f8bc4917a86f4504f85f0e24d67d17bd2a9bfc1 Mon Sep 17 00:00:00 2001
From: Eyal Davidovich <eyald@mellanox.com>
Date: Mon, 8 Oct 2018 12:16:01 +0300
Subject: net/mlx5e: Monitor counters commands support

new file monitor_stats.c for the new API.
add arm_monitor_counter new command support.
add set_monitor_counter new command support.

The device can monitor specific counters and provide an event to notify
when these counters are changed.
The monitoring is done in best effort manner where the minimum
notification period is 200 ms, however when the device is loaded, the
notification might be delayed.
To configure the required counters to be monitored, the
SET_MONITOR_COUNTER command shall be used with a list of counters to be
monitored.
The device firmware can monitor up to HCA_CAP.max_num_of_monitor_counters.
The configuration is done based on counter type (such as ppcnt, q counter,
etc) and additional param according to the type of counter selected.
Upon monitor counter change, the device will generate
Monitor_Counter_Change event.
The device will not generate new events unless the driver re-arms the
monitoring functionality, using the ARM_MONITOR_COUNTER command.

Signed-off-by: Eyal Davidovich <eyald@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 .../ethernet/mellanox/mlx5/core/en/monitor_stats.c | 126 +++++++++++++++++++++
 .../ethernet/mellanox/mlx5/core/en/monitor_stats.h |  12 ++
 3 files changed, 139 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 40764d87413a..9678051b8ff1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -22,7 +22,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 #
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
-		en_selftest.o en/port.o
+		en_selftest.o en/port.o en/monitor_stats.o
 
 #
 # Netdev extra
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
new file mode 100644
index 000000000000..0f010efa1375
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#include "en.h"
+#include "monitor_stats.h"
+
+/* Driver will set the following watch counters list:
+ * Ppcnt.802_3:
+ * a_in_range_length_errors      Type: 0x0, Counter:  0x0, group_id = N/A
+ * a_out_of_range_length_field   Type: 0x0, Counter:  0x1, group_id = N/A
+ * a_frame_too_long_errors       Type: 0x0, Counter:  0x2, group_id = N/A
+ * a_frame_check_sequence_errors Type: 0x0, Counter:  0x3, group_id = N/A
+ * a_alignment_errors            Type: 0x0, Counter:  0x4, group_id = N/A
+ * if_out_discards               Type: 0x0, Counter:  0x5, group_id = N/A
+ * Q_Counters:
+ * Q[index].rx_out_of_buffer   Type: 0x1, Counter:  0x4, group_id = counter_ix
+ */
+
+#define NUM_REQ_PPCNT_COUNTER_S1 MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1
+#define NUM_REQ_Q_COUNTERS_S1    MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1
+
+int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	if (!MLX5_CAP_GEN(mdev, max_num_of_monitor_counters))
+		return false;
+	if (MLX5_CAP_PCAM_REG(mdev, ppcnt) &&
+	    MLX5_CAP_GEN(mdev, num_ppcnt_monitor_counters) <
+	    NUM_REQ_PPCNT_COUNTER_S1)
+		return false;
+	if (MLX5_CAP_GEN(mdev, num_q_monitor_counters) <
+	    NUM_REQ_Q_COUNTERS_S1)
+		return false;
+	return true;
+}
+
+void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv)
+{
+	u32  in[MLX5_ST_SZ_DW(arm_monitor_counter_in)]  = {};
+	u32 out[MLX5_ST_SZ_DW(arm_monitor_counter_out)] = {};
+
+	MLX5_SET(arm_monitor_counter_in, in, opcode,
+		 MLX5_CMD_OP_ARM_MONITOR_COUNTER);
+	mlx5_cmd_exec(priv->mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static int fill_monitor_counter_ppcnt_set1(int cnt, u32 *in)
+{
+	enum mlx5_monitor_counter_ppcnt ppcnt_cnt;
+
+	for (ppcnt_cnt = 0;
+	     ppcnt_cnt < NUM_REQ_PPCNT_COUNTER_S1;
+	     ppcnt_cnt++, cnt++) {
+		MLX5_SET(set_monitor_counter_in, in,
+			 monitor_counter[cnt].type,
+			 MLX5_QUERY_MONITOR_CNT_TYPE_PPCNT);
+		MLX5_SET(set_monitor_counter_in, in,
+			 monitor_counter[cnt].counter,
+			 ppcnt_cnt);
+	}
+	return ppcnt_cnt;
+}
+
+static int fill_monitor_counter_q_counter_set1(int cnt, int q_counter, u32 *in)
+{
+	MLX5_SET(set_monitor_counter_in, in,
+		 monitor_counter[cnt].type,
+		 MLX5_QUERY_MONITOR_CNT_TYPE_Q_COUNTER);
+	MLX5_SET(set_monitor_counter_in, in,
+		 monitor_counter[cnt].counter,
+		 MLX5_QUERY_MONITOR_Q_COUNTER_RX_OUT_OF_BUFFER);
+	MLX5_SET(set_monitor_counter_in, in,
+		 monitor_counter[cnt].counter_group_id,
+		 q_counter);
+	return 1;
+}
+
+/* check if mlx5e_monitor_counter_supported before calling this function*/
+static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int max_num_of_counters = MLX5_CAP_GEN(mdev, max_num_of_monitor_counters);
+	int num_q_counters      = MLX5_CAP_GEN(mdev, num_q_monitor_counters);
+	int num_ppcnt_counters  = !MLX5_CAP_PCAM_REG(mdev, ppcnt) ? 0 :
+				  MLX5_CAP_GEN(mdev, num_ppcnt_monitor_counters);
+	u32  in[MLX5_ST_SZ_DW(set_monitor_counter_in)]  = {};
+	u32 out[MLX5_ST_SZ_DW(set_monitor_counter_out)] = {};
+	int q_counter = priv->q_counter;
+	int cnt	= 0;
+
+	if (num_ppcnt_counters  >=  NUM_REQ_PPCNT_COUNTER_S1 &&
+	    max_num_of_counters >= (NUM_REQ_PPCNT_COUNTER_S1 + cnt))
+		cnt += fill_monitor_counter_ppcnt_set1(cnt, in);
+
+	if (num_q_counters      >=  NUM_REQ_Q_COUNTERS_S1 &&
+	    max_num_of_counters >= (NUM_REQ_Q_COUNTERS_S1 + cnt) &&
+	    q_counter)
+		cnt += fill_monitor_counter_q_counter_set1(cnt, q_counter, in);
+
+	MLX5_SET(set_monitor_counter_in, in, num_of_counters, cnt);
+	MLX5_SET(set_monitor_counter_in, in, opcode,
+		 MLX5_CMD_OP_SET_MONITOR_COUNTER);
+
+	mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+/* check if mlx5e_monitor_counter_supported before calling this function*/
+void mlx5e_monitor_counter_init(struct mlx5e_priv *priv)
+{
+	mlx5e_set_monitor_counter(priv);
+	mlx5e_monitor_counter_arm(priv);
+}
+
+/* check if mlx5e_monitor_counter_supported before calling this function*/
+void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv)
+{
+	u32  in[MLX5_ST_SZ_DW(set_monitor_counter_in)]  = {};
+	u32 out[MLX5_ST_SZ_DW(set_monitor_counter_out)] = {};
+
+	MLX5_SET(set_monitor_counter_in, in, num_of_counters, 0);
+	MLX5_SET(set_monitor_counter_in, in, opcode,
+		 MLX5_CMD_OP_SET_MONITOR_COUNTER);
+
+	mlx5_cmd_exec(priv->mdev, in, sizeof(in), out, sizeof(out));
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h
new file mode 100644
index 000000000000..e1ac4b3d22fb
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef __MLX5_MONITOR_H__
+#define __MLX5_MONITOR_H__
+
+int  mlx5e_monitor_counter_supported(struct mlx5e_priv *priv);
+void mlx5e_monitor_counter_init(struct mlx5e_priv *priv);
+void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv);
+void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv);
+
+#endif /* __MLX5_MONITOR_H__ */
-- 
cgit v1.2.3


From 5c7e8bbb025726f9cb9b2bc050509a94262426f8 Mon Sep 17 00:00:00 2001
From: Eyal Davidovich <eyald@mellanox.com>
Date: Sat, 20 Oct 2018 16:18:00 +0300
Subject: net/mlx5e: Use monitor counters for update stats

- Adding new notifier block (struct mlx5_nb) monitor_counters_nb
  for handeling MONITOR_COUNTER new event type.
- Adding work queue element: monitor_counters_work for re-arm and
  update stats.
- We re-queue the update stat work, only when working over firmware
  that doesn't support the monitored counters.

Signed-off-by: Eyal Davidovich <eyald@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  3 ++
 .../ethernet/mellanox/mlx5/core/en/monitor_stats.c | 47 +++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 14 +++++--
 3 files changed, 59 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 9ea0f853c3bb..1c4e033b7509 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -685,6 +685,8 @@ struct mlx5e_priv {
 	struct work_struct         set_rx_mode_work;
 	struct work_struct         tx_timeout_work;
 	struct work_struct         update_stats_work;
+	struct work_struct         monitor_counters_work;
+	struct mlx5_nb             monitor_counters_nb;
 
 	struct mlx5_core_dev      *mdev;
 	struct net_device         *netdev;
@@ -940,6 +942,7 @@ int mlx5e_create_tises(struct mlx5e_priv *priv);
 void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
 int mlx5e_open(struct net_device *netdev);
+void mlx5e_update_ndo_stats(struct mlx5e_priv *priv);
 
 void mlx5e_queue_update_stats(struct mlx5e_priv *priv);
 int mlx5e_bits_invert(unsigned long a, int size);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
index 0f010efa1375..2ce420851e77 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
@@ -3,6 +3,7 @@
 
 #include "en.h"
 #include "monitor_stats.h"
+#include "lib/eq.h"
 
 /* Driver will set the following watch counters list:
  * Ppcnt.802_3:
@@ -45,6 +46,39 @@ void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv)
 	mlx5_cmd_exec(priv->mdev, in, sizeof(in), out, sizeof(out));
 }
 
+static void mlx5e_monitor_counters_work(struct work_struct *work)
+{
+	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
+					       monitor_counters_work);
+
+	mutex_lock(&priv->state_lock);
+	mlx5e_update_ndo_stats(priv);
+	mutex_unlock(&priv->state_lock);
+	mlx5e_monitor_counter_arm(priv);
+}
+
+static int mlx5e_monitor_event_handler(struct notifier_block *nb,
+				       unsigned long event, void *eqe)
+{
+	struct mlx5e_priv *priv = mlx5_nb_cof(nb, struct mlx5e_priv,
+					      monitor_counters_nb);
+	queue_work(priv->wq, &priv->monitor_counters_work);
+	return NOTIFY_OK;
+}
+
+void mlx5e_monitor_counter_start(struct mlx5e_priv *priv)
+{
+	MLX5_NB_INIT(&priv->monitor_counters_nb, mlx5e_monitor_event_handler,
+		     MONITOR_COUNTER);
+	mlx5_eq_notifier_register(priv->mdev, &priv->monitor_counters_nb);
+}
+
+static void mlx5e_monitor_counter_stop(struct mlx5e_priv *priv)
+{
+	mlx5_eq_notifier_unregister(priv->mdev, &priv->monitor_counters_nb);
+	cancel_work_sync(&priv->monitor_counters_work);
+}
+
 static int fill_monitor_counter_ppcnt_set1(int cnt, u32 *in)
 {
 	enum mlx5_monitor_counter_ppcnt ppcnt_cnt;
@@ -108,12 +142,14 @@ static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv)
 /* check if mlx5e_monitor_counter_supported before calling this function*/
 void mlx5e_monitor_counter_init(struct mlx5e_priv *priv)
 {
+	INIT_WORK(&priv->monitor_counters_work, mlx5e_monitor_counters_work);
+	mlx5e_monitor_counter_start(priv);
 	mlx5e_set_monitor_counter(priv);
 	mlx5e_monitor_counter_arm(priv);
+	queue_work(priv->wq, &priv->update_stats_work);
 }
 
-/* check if mlx5e_monitor_counter_supported before calling this function*/
-void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv)
+static void mlx5e_monitor_counter_disable(struct mlx5e_priv *priv)
 {
 	u32  in[MLX5_ST_SZ_DW(set_monitor_counter_in)]  = {};
 	u32 out[MLX5_ST_SZ_DW(set_monitor_counter_out)] = {};
@@ -124,3 +160,10 @@ void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv)
 
 	mlx5_cmd_exec(priv->mdev, in, sizeof(in), out, sizeof(out));
 }
+
+/* check if mlx5e_monitor_counter_supported before calling this function*/
+void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv)
+{
+	mlx5e_monitor_counter_disable(priv);
+	mlx5e_monitor_counter_stop(priv);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2188e5ba908f..59745851b5ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -50,6 +50,7 @@
 #include "en/port.h"
 #include "en/xdp.h"
 #include "lib/eq.h"
+#include "en/monitor_stats.h"
 
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
@@ -263,7 +264,7 @@ void mlx5e_update_stats(struct mlx5e_priv *priv)
 			mlx5e_stats_grps[i].update_stats(priv);
 }
 
-static void mlx5e_update_ndo_stats(struct mlx5e_priv *priv)
+void mlx5e_update_ndo_stats(struct mlx5e_priv *priv)
 {
 	int i;
 
@@ -3459,8 +3460,10 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
-	/* update HW stats in background for next time */
-	mlx5e_queue_update_stats(priv);
+	if (!mlx5e_monitor_counter_supported(priv)) {
+		/* update HW stats in background for next time */
+		mlx5e_queue_update_stats(priv);
+	}
 
 	if (mlx5e_is_uplink_rep(priv)) {
 		stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
@@ -4901,6 +4904,8 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	mlx5_lag_add(mdev, netdev);
 
 	mlx5e_enable_async_events(priv);
+	if (mlx5e_monitor_counter_supported(priv))
+		mlx5e_monitor_counter_init(priv);
 
 	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_register_vport_reps(priv);
@@ -4940,6 +4945,9 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_unregister_vport_reps(priv);
 
+	if (mlx5e_monitor_counter_supported(priv))
+		mlx5e_monitor_counter_cleanup(priv);
+
 	mlx5e_disable_async_events(priv);
 	mlx5_lag_remove(mdev);
 }
-- 
cgit v1.2.3


From 37ab566c178d79807b2d20b4c999133780355c6c Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 11 Dec 2018 16:02:05 -0800
Subject: bpf: arm64: Enable arm64 jit to provide bpf_line_info

This patch enables arm64's bpf_int_jit_compile() to provide
bpf_line_info by calling bpf_prog_fill_jited_linfo().

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm64/net/bpf_jit_comp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 0a7371a86139..1542df00b23c 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -932,6 +932,7 @@ skip_init_ctx:
 	prog->jited_len = image_size;
 
 	if (!prog->is_func || extra_pass) {
+		bpf_prog_fill_jited_linfo(prog, ctx.offset);
 out_off:
 		kfree(ctx.offset);
 		kfree(jit_data);
-- 
cgit v1.2.3


From e1a76515b0c20c3477200c1345c477cc0e68c4ad Mon Sep 17 00:00:00 2001
From: Xue Chaojing <xuechaojing@huawei.com>
Date: Sun, 9 Dec 2018 19:14:19 +0000
Subject: hinic: optmize rx refill buffer mechanism

There is no need to schedule a different tasklet for refill,
This patch remove it.

Suggested-by: Neil Horman <nhorman@redhat.com>
Signed-off-by: Xue Chaojing <xuechaojing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_rx.c | 23 +++++------------------
 drivers/net/ethernet/huawei/hinic/hinic_rx.h |  2 --
 2 files changed, 5 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index f86f2e693224..0098b206e7e9 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -43,6 +43,7 @@
 #define RX_IRQ_NO_LLI_TIMER             0
 #define RX_IRQ_NO_CREDIT                0
 #define RX_IRQ_NO_RESEND_TIMER          0
+#define HINIC_RX_BUFFER_WRITE           16
 
 /**
  * hinic_rxq_clean_stats - Clean the statistics of specific queue
@@ -229,7 +230,6 @@ skb_out:
 		wmb();  /* write all the wqes before update PI */
 
 		hinic_rq_update(rxq->rq, prod_idx);
-		tasklet_schedule(&rxq->rx_task);
 	}
 
 	return i;
@@ -258,17 +258,6 @@ static void free_all_rx_skbs(struct hinic_rxq *rxq)
 	}
 }
 
-/**
- * rx_alloc_task - tasklet for queue allocation
- * @data: rx queue
- **/
-static void rx_alloc_task(unsigned long data)
-{
-	struct hinic_rxq *rxq = (struct hinic_rxq *)data;
-
-	(void)rx_alloc_pkts(rxq);
-}
-
 /**
  * rx_recv_jumbo_pkt - Rx handler for jumbo pkt
  * @rxq: rx queue
@@ -333,6 +322,7 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 	struct hinic_qp *qp = container_of(rxq->rq, struct hinic_qp, rq);
 	u64 pkt_len = 0, rx_bytes = 0;
 	struct hinic_rq_wqe *rq_wqe;
+	unsigned int free_wqebbs;
 	int num_wqes, pkts = 0;
 	struct hinic_sge sge;
 	struct sk_buff *skb;
@@ -376,8 +366,9 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 		rx_bytes += pkt_len;
 	}
 
-	if (pkts)
-		tasklet_schedule(&rxq->rx_task); /* rx_alloc_pkts */
+	free_wqebbs = hinic_get_rq_free_wqebbs(rxq->rq);
+	if (free_wqebbs > HINIC_RX_BUFFER_WRITE)
+		rx_alloc_pkts(rxq);
 
 	u64_stats_update_begin(&rxq->rxq_stats.syncp);
 	rxq->rxq_stats.pkts += pkts;
@@ -494,8 +485,6 @@ int hinic_init_rxq(struct hinic_rxq *rxq, struct hinic_rq *rq,
 
 	sprintf(rxq->irq_name, "hinic_rxq%d", qp->q_id);
 
-	tasklet_init(&rxq->rx_task, rx_alloc_task, (unsigned long)rxq);
-
 	pkts = rx_alloc_pkts(rxq);
 	if (!pkts) {
 		err = -ENOMEM;
@@ -512,7 +501,6 @@ int hinic_init_rxq(struct hinic_rxq *rxq, struct hinic_rq *rq,
 
 err_req_rx_irq:
 err_rx_pkts:
-	tasklet_kill(&rxq->rx_task);
 	free_all_rx_skbs(rxq);
 	devm_kfree(&netdev->dev, rxq->irq_name);
 	return err;
@@ -528,7 +516,6 @@ void hinic_clean_rxq(struct hinic_rxq *rxq)
 
 	rx_free_irq(rxq);
 
-	tasklet_kill(&rxq->rx_task);
 	free_all_rx_skbs(rxq);
 	devm_kfree(&netdev->dev, rxq->irq_name);
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.h b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
index ab3fabab91b2..f8ed3fa6c8ee 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
@@ -42,8 +42,6 @@ struct hinic_rxq {
 
 	char                    *irq_name;
 
-	struct tasklet_struct   rx_task;
-
 	struct napi_struct      napi;
 };
 
-- 
cgit v1.2.3


From a75e41d37a7ac5a8020f9fec54656c71209075fd Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Mon, 10 Dec 2018 07:11:33 +0000
Subject: mlxsw: reg: Add Policy Engine Multicast Router Binding Table Register

In Spectrum-2, multicast routing is implemented explicitly using policy
engine (ACL) block. PEMRBT register is used to bind a dedicated ACL group
to a specific IP protocol.
Add the register to be later used in multicast router implementation.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 38 +++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index b9c37b0bb175..ace3a897b3f0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2495,6 +2495,43 @@ static inline void mlxsw_reg_pefa_unpack(char *payload, bool *p_a)
 	*p_a = mlxsw_reg_pefa_a_get(payload);
 }
 
+/* PEMRBT - Policy-Engine Multicast Router Binding Table Register
+ * --------------------------------------------------------------
+ * This register is used for binding Multicast router to an ACL group
+ * that serves the MC router.
+ * This register is not supported by SwitchX/-2 and Spectrum.
+ */
+#define MLXSW_REG_PEMRBT_ID 0x3014
+#define MLXSW_REG_PEMRBT_LEN 0x14
+
+MLXSW_REG_DEFINE(pemrbt, MLXSW_REG_PEMRBT_ID, MLXSW_REG_PEMRBT_LEN);
+
+enum mlxsw_reg_pemrbt_protocol {
+	MLXSW_REG_PEMRBT_PROTO_IPV4,
+	MLXSW_REG_PEMRBT_PROTO_IPV6,
+};
+
+/* reg_pemrbt_protocol
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pemrbt, protocol, 0x00, 0, 1);
+
+/* reg_pemrbt_group_id
+ * ACL group identifier.
+ * Range 0..cap_max_acl_groups-1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pemrbt, group_id, 0x10, 0, 16);
+
+static inline void
+mlxsw_reg_pemrbt_pack(char *payload, enum mlxsw_reg_pemrbt_protocol protocol,
+		      u16 group_id)
+{
+	MLXSW_REG_ZERO(pemrbt, payload);
+	mlxsw_reg_pemrbt_protocol_set(payload, protocol);
+	mlxsw_reg_pemrbt_group_id_set(payload, group_id);
+}
+
 /* PTCE-V2 - Policy-Engine TCAM Entry Register Version 2
  * -----------------------------------------------------
  * This register is used for accessing rules within a TCAM region.
@@ -9568,6 +9605,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(ppbs),
 	MLXSW_REG(prcr),
 	MLXSW_REG(pefa),
+	MLXSW_REG(pemrbt),
 	MLXSW_REG(ptce2),
 	MLXSW_REG(perpt),
 	MLXSW_REG(perar),
-- 
cgit v1.2.3


From 254cec14649ebdb891d75fc69be6c801762a9a09 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Mon, 10 Dec 2018 07:11:37 +0000
Subject: mlxsw: spectrum: Change stage of ACL initialization

In Spectrum-2, MC routing is implemented using ACL block explicitly, so
router initialization should take place after ACL initialization.
Set the initialization of the ACL block before IP router initizalization
takes place, so multicast router will be able to allocate ACL data
structures and create its required chains.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 0f37b203103a..6929dbf04a1f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4002,6 +4002,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_nve_init;
 	}
 
+	err = mlxsw_sp_acl_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize ACL\n");
+		goto err_acl_init;
+	}
+
 	err = mlxsw_sp_router_init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n");
@@ -4019,12 +4025,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_netdev_notifier;
 	}
 
-	err = mlxsw_sp_acl_init(mlxsw_sp);
-	if (err) {
-		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize ACL\n");
-		goto err_acl_init;
-	}
-
 	err = mlxsw_sp_dpipe_init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to init pipeline debug\n");
@@ -4042,12 +4042,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 err_ports_create:
 	mlxsw_sp_dpipe_fini(mlxsw_sp);
 err_dpipe_init:
-	mlxsw_sp_acl_fini(mlxsw_sp);
-err_acl_init:
 	unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb);
 err_netdev_notifier:
 	mlxsw_sp_router_fini(mlxsw_sp);
 err_router_init:
+	mlxsw_sp_acl_fini(mlxsw_sp);
+err_acl_init:
 	mlxsw_sp_nve_fini(mlxsw_sp);
 err_nve_init:
 	mlxsw_sp_afa_fini(mlxsw_sp);
@@ -4108,9 +4108,9 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 
 	mlxsw_sp_ports_remove(mlxsw_sp);
 	mlxsw_sp_dpipe_fini(mlxsw_sp);
-	mlxsw_sp_acl_fini(mlxsw_sp);
 	unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb);
 	mlxsw_sp_router_fini(mlxsw_sp);
+	mlxsw_sp_acl_fini(mlxsw_sp);
 	mlxsw_sp_nve_fini(mlxsw_sp);
 	mlxsw_sp_afa_fini(mlxsw_sp);
 	mlxsw_sp_counter_pool_fini(mlxsw_sp);
-- 
cgit v1.2.3


From add4550fca4018f74dd8a8e98fc49f6141f96177 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Mon, 10 Dec 2018 07:11:39 +0000
Subject: mlxsw: spectrum_acl: Add Spectrum-2 keys

Add virtual router ID fields to Spectrum-2 key blocks set, as the field is
required for multicast routing.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h     | 4 ++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c | 6 ++++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index bcd264135af7..4a625cdf3e7c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -33,6 +33,8 @@ enum mlxsw_afk_element {
 	MLXSW_AFK_ELEMENT_IP_TTL_,
 	MLXSW_AFK_ELEMENT_IP_ECN,
 	MLXSW_AFK_ELEMENT_IP_DSCP,
+	MLXSW_AFK_ELEMENT_VIRT_ROUTER_8_10,
+	MLXSW_AFK_ELEMENT_VIRT_ROUTER_0_7,
 	MLXSW_AFK_ELEMENT_MAX,
 };
 
@@ -87,6 +89,8 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6),
+	MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_8_10, 0x18, 17, 3),
+	MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_0_7, 0x18, 20, 8),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_96_127, 0x20, 4),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_64_95, 0x24, 4),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_32_63, 0x28, 4),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index 2e1e8c4b3922..2a998dea4f39 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -167,6 +167,11 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_2[] = {
 	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x04, 16, 8),
 };
 
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_0_7, 0x04, 24, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_8_10, 0x00, 0, 3),
+};
+
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_0[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_32_63, 0x04, 4),
 };
@@ -210,6 +215,7 @@ static const struct mlxsw_afk_block mlxsw_sp2_afk_blocks[] = {
 	MLXSW_AFK_BLOCK(0x38, mlxsw_sp_afk_element_info_ipv4_0),
 	MLXSW_AFK_BLOCK(0x39, mlxsw_sp_afk_element_info_ipv4_1),
 	MLXSW_AFK_BLOCK(0x3A, mlxsw_sp_afk_element_info_ipv4_2),
+	MLXSW_AFK_BLOCK(0x3C, mlxsw_sp_afk_element_info_ipv4_4),
 	MLXSW_AFK_BLOCK(0x40, mlxsw_sp_afk_element_info_ipv6_0),
 	MLXSW_AFK_BLOCK(0x41, mlxsw_sp_afk_element_info_ipv6_1),
 	MLXSW_AFK_BLOCK(0x42, mlxsw_sp_afk_element_info_ipv6_2),
-- 
cgit v1.2.3


From 1a29d29394c79648928f4a2b82cf2fafc460dc55 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Mon, 10 Dec 2018 07:11:40 +0000
Subject: mlxsw: spectrum_acl: Add multicast router profile operations

Add specific ACL operations needed for programming multicast routing ACL
groups and routes.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |   1 +
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c    | 129 +++++++++++++++++++++
 2 files changed, 130 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 2d8f3692a949..fa60c74a1659 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -572,6 +572,7 @@ struct mlxsw_sp_acl_ruleset;
 /* spectrum_acl.c */
 enum mlxsw_sp_acl_profile {
 	MLXSW_SP_ACL_PROFILE_FLOWER,
+	MLXSW_SP_ACL_PROFILE_MR,
 };
 
 struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index e171513bb32a..015cf9acf445 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -848,6 +848,15 @@ struct mlxsw_sp_acl_tcam_flower_rule {
 	struct mlxsw_sp_acl_tcam_entry entry;
 };
 
+struct mlxsw_sp_acl_tcam_mr_ruleset {
+	struct mlxsw_sp_acl_tcam_chunk *chunk;
+	struct mlxsw_sp_acl_tcam_group group;
+};
+
+struct mlxsw_sp_acl_tcam_mr_rule {
+	struct mlxsw_sp_acl_tcam_entry entry;
+};
+
 static int
 mlxsw_sp_acl_tcam_flower_ruleset_add(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_acl_tcam *tcam,
@@ -952,9 +961,129 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
 	.rule_activity_get	= mlxsw_sp_acl_tcam_flower_rule_activity_get,
 };
 
+static int
+mlxsw_sp_acl_tcam_mr_ruleset_add(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam *tcam,
+				 void *ruleset_priv,
+				 struct mlxsw_afk_element_usage *tmplt_elusage)
+{
+	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
+	int err;
+
+	err = mlxsw_sp_acl_tcam_group_add(mlxsw_sp, tcam, &ruleset->group,
+					  mlxsw_sp_acl_tcam_patterns,
+					  MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
+					  tmplt_elusage);
+	if (err)
+		return err;
+
+	/* For most of the TCAM clients it would make sense to take a tcam chunk
+	 * only when the first rule is written. This is not the case for
+	 * multicast router as it is required to bind the multicast router to a
+	 * specific ACL Group ID which must exist in HW before multicast router
+	 * is initialized.
+	 */
+	ruleset->chunk = mlxsw_sp_acl_tcam_chunk_get(mlxsw_sp, &ruleset->group,
+						     1, tmplt_elusage);
+	if (IS_ERR(ruleset->chunk)) {
+		err = PTR_ERR(ruleset->chunk);
+		goto err_chunk_get;
+	}
+
+	return 0;
+
+err_chunk_get:
+	mlxsw_sp_acl_tcam_group_del(mlxsw_sp, &ruleset->group);
+	return err;
+}
+
+static void
+mlxsw_sp_acl_tcam_mr_ruleset_del(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv)
+{
+	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
+
+	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, ruleset->chunk);
+	mlxsw_sp_acl_tcam_group_del(mlxsw_sp, &ruleset->group);
+}
+
+static int
+mlxsw_sp_acl_tcam_mr_ruleset_bind(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
+				  struct mlxsw_sp_port *mlxsw_sp_port,
+				  bool ingress)
+{
+	/* Binding is done when initializing multicast router */
+	return 0;
+}
+
+static void
+mlxsw_sp_acl_tcam_mr_ruleset_unbind(struct mlxsw_sp *mlxsw_sp,
+				    void *ruleset_priv,
+				    struct mlxsw_sp_port *mlxsw_sp_port,
+				    bool ingress)
+{
+}
+
+static u16
+mlxsw_sp_acl_tcam_mr_ruleset_group_id(void *ruleset_priv)
+{
+	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
+
+	return mlxsw_sp_acl_tcam_group_id(&ruleset->group);
+}
+
+static size_t mlxsw_sp_acl_tcam_mr_rule_priv_size(struct mlxsw_sp *mlxsw_sp)
+{
+	return sizeof(struct mlxsw_sp_acl_tcam_mr_rule) +
+	       mlxsw_sp_acl_tcam_entry_priv_size(mlxsw_sp);
+}
+
+static int
+mlxsw_sp_acl_tcam_mr_rule_add(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
+			      void *rule_priv,
+			      struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
+	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
+
+	return mlxsw_sp_acl_tcam_entry_add(mlxsw_sp, &ruleset->group,
+					   &rule->entry, rulei);
+}
+
+static void
+mlxsw_sp_acl_tcam_mr_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv)
+{
+	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
+
+	mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry);
+}
+
+static int
+mlxsw_sp_acl_tcam_mr_rule_activity_get(struct mlxsw_sp *mlxsw_sp,
+				       void *rule_priv, bool *activity)
+{
+	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
+
+	return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry,
+						    activity);
+}
+
+static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_mr_ops = {
+	.ruleset_priv_size	= sizeof(struct mlxsw_sp_acl_tcam_mr_ruleset),
+	.ruleset_add		= mlxsw_sp_acl_tcam_mr_ruleset_add,
+	.ruleset_del		= mlxsw_sp_acl_tcam_mr_ruleset_del,
+	.ruleset_bind		= mlxsw_sp_acl_tcam_mr_ruleset_bind,
+	.ruleset_unbind		= mlxsw_sp_acl_tcam_mr_ruleset_unbind,
+	.ruleset_group_id	= mlxsw_sp_acl_tcam_mr_ruleset_group_id,
+	.rule_priv_size		= mlxsw_sp_acl_tcam_mr_rule_priv_size,
+	.rule_add		= mlxsw_sp_acl_tcam_mr_rule_add,
+	.rule_del		= mlxsw_sp_acl_tcam_mr_rule_del,
+	.rule_activity_get	= mlxsw_sp_acl_tcam_mr_rule_activity_get,
+};
+
 static const struct mlxsw_sp_acl_profile_ops *
 mlxsw_sp_acl_tcam_profile_ops_arr[] = {
 	[MLXSW_SP_ACL_PROFILE_FLOWER] = &mlxsw_sp_acl_tcam_flower_ops,
+	[MLXSW_SP_ACL_PROFILE_MR] = &mlxsw_sp_acl_tcam_mr_ops,
 };
 
 const struct mlxsw_sp_acl_profile_ops *
-- 
cgit v1.2.3


From 2507a64c17e646800025dfeb508d5c406bf24ec4 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Mon, 10 Dec 2018 07:11:41 +0000
Subject: mlxsw: spectrum_acl: Add replace rule action operation

Multicast routes actions may be updated after creation. An example for that
is an addition of an egress interface to an existing route.
So far, as tc flower API dictated, ACL rules were either created or
deleted. Since multicast routes in Spectrum-2 are written to ACL as any
rule, it is required to allow the update of a rule's action as it may
change.

Add methods and operations to support updating rule's action. This is
supported only for Spectrum-2.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  7 +++
 .../ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c   | 10 ++++
 .../ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c   | 18 +++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 15 ++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c   | 61 ++++++++++++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c   | 33 ++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c    | 37 +++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    | 13 +++++
 8 files changed, 194 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index fa60c74a1659..edd397f42228 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -658,6 +658,9 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
 			  struct mlxsw_sp_acl_rule *rule);
 void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
 			   struct mlxsw_sp_acl_rule *rule);
+int mlxsw_sp_acl_rule_action_replace(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_rule *rule,
+				     struct mlxsw_afa_block *afa_block);
 struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_lookup(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
@@ -702,6 +705,10 @@ struct mlxsw_sp_acl_tcam_ops {
 	void (*entry_del)(struct mlxsw_sp *mlxsw_sp,
 			  void *region_priv, void *chunk_priv,
 			  void *entry_priv);
+	int (*entry_action_replace)(struct mlxsw_sp *mlxsw_sp,
+				    void *region_priv, void *chunk_priv,
+				    void *entry_priv,
+				    struct mlxsw_sp_acl_rule_info *rulei);
 	int (*entry_activity_get)(struct mlxsw_sp *mlxsw_sp,
 				  void *region_priv, void *entry_priv,
 				  bool *activity);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index 2a9eac90002e..677526e58750 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -192,6 +192,15 @@ static void mlxsw_sp1_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 				     &chunk->cchunk, &entry->centry);
 }
 
+static int
+mlxsw_sp1_acl_tcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					void *region_priv, void *chunk_priv,
+					void *entry_priv,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	return -EOPNOTSUPP;
+}
+
 static int
 mlxsw_sp1_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
 					     struct mlxsw_sp_acl_tcam_region *_region,
@@ -240,5 +249,6 @@ const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops = {
 	.entry_priv_size	= sizeof(struct mlxsw_sp1_acl_tcam_entry),
 	.entry_add		= mlxsw_sp1_acl_tcam_entry_add,
 	.entry_del		= mlxsw_sp1_acl_tcam_entry_del,
+	.entry_action_replace	= mlxsw_sp1_acl_tcam_entry_action_replace,
 	.entry_activity_get	= mlxsw_sp1_acl_tcam_entry_activity_get,
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 62e6cf4bc16e..234ab51916db 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -210,6 +210,23 @@ static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 				     &entry->aentry);
 }
 
+static int
+mlxsw_sp2_acl_tcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					void *region_priv, void *chunk_priv,
+					void *entry_priv,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
+	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
+
+	entry->act_block = rulei->act_block;
+	return mlxsw_sp_acl_atcam_entry_action_replace(mlxsw_sp,
+						       &region->aregion,
+						       &chunk->achunk,
+						       &entry->aentry, rulei);
+}
+
 static int
 mlxsw_sp2_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
 				      void *region_priv, void *entry_priv,
@@ -235,5 +252,6 @@ const struct mlxsw_sp_acl_tcam_ops mlxsw_sp2_acl_tcam_ops = {
 	.entry_priv_size	= sizeof(struct mlxsw_sp2_acl_tcam_entry),
 	.entry_add		= mlxsw_sp2_acl_tcam_entry_add,
 	.entry_del		= mlxsw_sp2_acl_tcam_entry_del,
+	.entry_action_replace	= mlxsw_sp2_acl_tcam_entry_action_replace,
 	.entry_activity_get	= mlxsw_sp2_acl_tcam_entry_activity_get,
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index c4f9238591e6..44bbe7c9b68c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -721,6 +721,21 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
 	ops->rule_del(mlxsw_sp, rule->priv);
 }
 
+int mlxsw_sp_acl_rule_action_replace(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_rule *rule,
+				     struct mlxsw_afa_block *afa_block)
+{
+	struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
+	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
+	struct mlxsw_sp_acl_rule_info *rulei;
+
+	rulei = mlxsw_sp_acl_rule_rulei(rule);
+	rulei->act_block = afa_block;
+
+	return ops->rule_action_replace(mlxsw_sp, ruleset->priv, rule->priv,
+					rule->rulei);
+}
+
 struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_lookup(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index e7bd8733e58e..75f11c2d7b97 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -437,6 +437,34 @@ mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 	aregion->ops->lkey_id_put(aregion, lkey_id);
 }
 
+static int
+mlxsw_sp_acl_atcam_region_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					       struct mlxsw_sp_acl_atcam_region *aregion,
+					       struct mlxsw_sp_acl_atcam_entry *aentry,
+					       struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id = aentry->lkey_id;
+	u8 erp_id = mlxsw_sp_acl_erp_mask_erp_id(aentry->erp_mask);
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
+	u32 kvdl_index, priority;
+	int err;
+
+	err = mlxsw_sp_acl_tcam_priority_get(mlxsw_sp, rulei, &priority, true);
+	if (err)
+		return err;
+	kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
+	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_UPDATE,
+			     priority, region->tcam_region_info,
+			     aentry->ht_key.enc_key, erp_id,
+			     aentry->delta_info.start,
+			     aentry->delta_info.mask,
+			     aentry->delta_info.value,
+			     refcount_read(&lkey_id->refcnt) != 1, lkey_id->id,
+			     kvdl_index);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl);
+}
+
 static int
 __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_atcam_region *aregion,
@@ -506,6 +534,16 @@ __mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_erp_mask_put(aregion, aentry->erp_mask);
 }
 
+static int
+__mlxsw_sp_acl_atcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					  struct mlxsw_sp_acl_atcam_region *aregion,
+					  struct mlxsw_sp_acl_atcam_entry *aentry,
+					  struct mlxsw_sp_acl_rule_info *rulei)
+{
+	return mlxsw_sp_acl_atcam_region_entry_action_replace(mlxsw_sp, aregion,
+							      aentry, rulei);
+}
+
 int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_atcam_region *aregion,
 				 struct mlxsw_sp_acl_atcam_chunk *achunk,
@@ -542,6 +580,29 @@ void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 		__mlxsw_sp_acl_atcam_entry_del(mlxsw_sp, aregion, aentry);
 }
 
+int
+mlxsw_sp_acl_atcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_atcam_region *aregion,
+					struct mlxsw_sp_acl_atcam_chunk *achunk,
+					struct mlxsw_sp_acl_atcam_entry *aentry,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	int err;
+
+	if (mlxsw_sp_acl_atcam_is_centry(aentry))
+		err = mlxsw_sp_acl_ctcam_entry_action_replace(mlxsw_sp,
+							      &aregion->cregion,
+							      &achunk->cchunk,
+							      &aentry->centry,
+							      rulei);
+	else
+		err = __mlxsw_sp_acl_atcam_entry_action_replace(mlxsw_sp,
+								aregion, aentry,
+								rulei);
+
+	return err;
+}
+
 int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_atcam *atcam)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index f3e834bfea1a..b0f2d8e8ded0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -89,6 +89,27 @@ mlxsw_sp_acl_ctcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 	cregion->ops->entry_remove(cregion, centry);
 }
 
+static int
+mlxsw_sp_acl_ctcam_region_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					       struct mlxsw_sp_acl_ctcam_region *cregion,
+					       struct mlxsw_sp_acl_ctcam_entry *centry,
+					       struct mlxsw_afa_block *afa_block,
+					       unsigned int priority)
+{
+	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+	char *act_set;
+
+	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_UPDATE,
+			     cregion->region->tcam_region_info,
+			     centry->parman_item.index, priority);
+
+	act_set = mlxsw_afa_block_first_set(afa_block);
+	mlxsw_reg_ptce2_flex_action_set_memcpy_to(ptce2_pl, act_set);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+}
+
+
 static int mlxsw_sp_acl_ctcam_region_parman_resize(void *priv,
 						   unsigned long new_count)
 {
@@ -191,3 +212,15 @@ void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 	parman_item_remove(cregion->parman, &cchunk->parman_prio,
 			   &centry->parman_item);
 }
+
+int mlxsw_sp_acl_ctcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					    struct mlxsw_sp_acl_ctcam_region *cregion,
+					    struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+					    struct mlxsw_sp_acl_ctcam_entry *centry,
+					    struct mlxsw_sp_acl_rule_info *rulei)
+{
+	return mlxsw_sp_acl_ctcam_region_entry_action_replace(mlxsw_sp, cregion,
+							      centry,
+							      rulei->act_block,
+							      rulei->priority);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 015cf9acf445..f1f98a1770d2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -778,6 +778,20 @@ static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
 }
 
+static int
+mlxsw_sp_acl_tcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_tcam_group *group,
+				       struct mlxsw_sp_acl_tcam_entry *entry,
+				       struct mlxsw_sp_acl_rule_info *rulei)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
+	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
+
+	return ops->entry_action_replace(mlxsw_sp, region->priv, chunk->priv,
+					 entry->priv, rulei);
+}
+
 static int
 mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_acl_tcam_entry *entry,
@@ -938,6 +952,15 @@ mlxsw_sp_acl_tcam_flower_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv)
 	mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry);
 }
 
+static int
+mlxsw_sp_acl_tcam_flower_rule_action_replace(struct mlxsw_sp *mlxsw_sp,
+					     void *ruleset_priv,
+					     void *rule_priv,
+					     struct mlxsw_sp_acl_rule_info *rulei)
+{
+	return -EOPNOTSUPP;
+}
+
 static int
 mlxsw_sp_acl_tcam_flower_rule_activity_get(struct mlxsw_sp *mlxsw_sp,
 					   void *rule_priv, bool *activity)
@@ -958,6 +981,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
 	.rule_priv_size		= mlxsw_sp_acl_tcam_flower_rule_priv_size,
 	.rule_add		= mlxsw_sp_acl_tcam_flower_rule_add,
 	.rule_del		= mlxsw_sp_acl_tcam_flower_rule_del,
+	.rule_action_replace	= mlxsw_sp_acl_tcam_flower_rule_action_replace,
 	.rule_activity_get	= mlxsw_sp_acl_tcam_flower_rule_activity_get,
 };
 
@@ -1057,6 +1081,18 @@ mlxsw_sp_acl_tcam_mr_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv)
 	mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry);
 }
 
+static int
+mlxsw_sp_acl_tcam_mr_rule_action_replace(struct mlxsw_sp *mlxsw_sp,
+					 void *ruleset_priv, void *rule_priv,
+					 struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
+	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
+
+	return mlxsw_sp_acl_tcam_entry_action_replace(mlxsw_sp, &ruleset->group,
+						      &rule->entry, rulei);
+}
+
 static int
 mlxsw_sp_acl_tcam_mr_rule_activity_get(struct mlxsw_sp *mlxsw_sp,
 				       void *rule_priv, bool *activity)
@@ -1077,6 +1113,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_mr_ops = {
 	.rule_priv_size		= mlxsw_sp_acl_tcam_mr_rule_priv_size,
 	.rule_add		= mlxsw_sp_acl_tcam_mr_rule_add,
 	.rule_del		= mlxsw_sp_acl_tcam_mr_rule_del,
+	.rule_action_replace	= mlxsw_sp_acl_tcam_mr_rule_action_replace,
 	.rule_activity_get	= mlxsw_sp_acl_tcam_mr_rule_activity_get,
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 9a73759d901f..95929b9039ec 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -48,6 +48,9 @@ struct mlxsw_sp_acl_profile_ops {
 			void *ruleset_priv, void *rule_priv,
 			struct mlxsw_sp_acl_rule_info *rulei);
 	void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
+	int (*rule_action_replace)(struct mlxsw_sp *mlxsw_sp,
+				   void *ruleset_priv, void *rule_priv,
+				   struct mlxsw_sp_acl_rule_info *rulei);
 	int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
 				 bool *activity);
 };
@@ -121,6 +124,11 @@ void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_ctcam_region *cregion,
 				  struct mlxsw_sp_acl_ctcam_chunk *cchunk,
 				  struct mlxsw_sp_acl_ctcam_entry *centry);
+int mlxsw_sp_acl_ctcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					    struct mlxsw_sp_acl_ctcam_region *cregion,
+					    struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+					    struct mlxsw_sp_acl_ctcam_entry *centry,
+					    struct mlxsw_sp_acl_rule_info *rulei);
 static inline unsigned int
 mlxsw_sp_acl_ctcam_entry_offset(struct mlxsw_sp_acl_ctcam_entry *centry)
 {
@@ -212,6 +220,11 @@ void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_atcam_region *aregion,
 				  struct mlxsw_sp_acl_atcam_chunk *achunk,
 				  struct mlxsw_sp_acl_atcam_entry *aentry);
+int mlxsw_sp_acl_atcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					    struct mlxsw_sp_acl_atcam_region *aregion,
+					    struct mlxsw_sp_acl_atcam_chunk *achunk,
+					    struct mlxsw_sp_acl_atcam_entry *aentry,
+					    struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_atcam *atcam);
 void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
-- 
cgit v1.2.3


From c20580c21f80d676f6e128eea4dc482c4e51b265 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Mon, 10 Dec 2018 07:11:43 +0000
Subject: mlxsw: spectrum_acl: Support rule creation without action creation

Up until now, when ACL rule was created its action was created with it.
It suits well for tc flower where ACL rule always needs an action, however
it does not suit multicast router, where the action is created prior to
setting a route, which in Spectrum-2 is actually an ACL rule.

Add support for rule creation without action creation. Do it by adding
afa_block argument to mlxsw_sp_acl_rule_create, which if NULL then an
action would be created, also add an indication within struct
mlxsw_sp_acl_rule_info that tells if the action should be destroyed when
the rule is destroyed.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           |  5 ++++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c       | 16 +++++++++++++---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c    |  2 +-
 4 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index edd397f42228..41a5de4a0965 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -563,6 +563,7 @@ struct mlxsw_sp_acl_rule_info {
 	unsigned int priority;
 	struct mlxsw_afk_element_values values;
 	struct mlxsw_afa_block *act_block;
+	u8 action_created:1;
 	unsigned int counter_index;
 };
 
@@ -607,7 +608,8 @@ void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
 u16 mlxsw_sp_acl_ruleset_group_id(struct mlxsw_sp_acl_ruleset *ruleset);
 
 struct mlxsw_sp_acl_rule_info *
-mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl);
+mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl,
+			  struct mlxsw_afa_block *afa_block);
 void mlxsw_sp_acl_rulei_destroy(struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_rulei_commit(struct mlxsw_sp_acl_rule_info *rulei);
 void mlxsw_sp_acl_rulei_priority(struct mlxsw_sp_acl_rule_info *rulei,
@@ -651,6 +653,7 @@ struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
 			 unsigned long cookie,
+			 struct mlxsw_afa_block *afa_block,
 			 struct netlink_ext_ack *extack);
 void mlxsw_sp_acl_rule_destroy(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_rule *rule);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index 677526e58750..fe270c1a26a6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -67,7 +67,7 @@ mlxsw_sp1_acl_ctcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_ctcam_chunk_init(&region->cregion,
 				      &region->catchall.cchunk,
 				      MLXSW_SP_ACL_TCAM_CATCHALL_PRIO);
-	rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl);
+	rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl, NULL);
 	if (IS_ERR(rulei)) {
 		err = PTR_ERR(rulei);
 		goto err_rulei_create;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 44bbe7c9b68c..695d33358988 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -435,7 +435,8 @@ u16 mlxsw_sp_acl_ruleset_group_id(struct mlxsw_sp_acl_ruleset *ruleset)
 }
 
 struct mlxsw_sp_acl_rule_info *
-mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl)
+mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl,
+			  struct mlxsw_afa_block *afa_block)
 {
 	struct mlxsw_sp_acl_rule_info *rulei;
 	int err;
@@ -443,11 +444,18 @@ mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl)
 	rulei = kzalloc(sizeof(*rulei), GFP_KERNEL);
 	if (!rulei)
 		return NULL;
+
+	if (afa_block) {
+		rulei->act_block = afa_block;
+		return rulei;
+	}
+
 	rulei->act_block = mlxsw_afa_block_create(acl->mlxsw_sp->afa);
 	if (IS_ERR(rulei->act_block)) {
 		err = PTR_ERR(rulei->act_block);
 		goto err_afa_block_create;
 	}
+	rulei->action_created = 1;
 	return rulei;
 
 err_afa_block_create:
@@ -457,7 +465,8 @@ err_afa_block_create:
 
 void mlxsw_sp_acl_rulei_destroy(struct mlxsw_sp_acl_rule_info *rulei)
 {
-	mlxsw_afa_block_destroy(rulei->act_block);
+	if (rulei->action_created)
+		mlxsw_afa_block_destroy(rulei->act_block);
 	kfree(rulei);
 }
 
@@ -623,6 +632,7 @@ struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
 			 unsigned long cookie,
+			 struct mlxsw_afa_block *afa_block,
 			 struct netlink_ext_ack *extack)
 {
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
@@ -639,7 +649,7 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 	rule->cookie = cookie;
 	rule->ruleset = ruleset;
 
-	rule->rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl);
+	rule->rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl, afa_block);
 	if (IS_ERR(rule->rulei)) {
 		err = PTR_ERR(rule->rulei);
 		goto err_rulei_create;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 8d211972c5e9..ff072358d950 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -406,7 +406,7 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 	if (IS_ERR(ruleset))
 		return PTR_ERR(ruleset);
 
-	rule = mlxsw_sp_acl_rule_create(mlxsw_sp, ruleset, f->cookie,
+	rule = mlxsw_sp_acl_rule_create(mlxsw_sp, ruleset, f->cookie, NULL,
 					f->common.extack);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-- 
cgit v1.2.3


From d7263ab35be25505ab57ebecd93cbc5dba8be717 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Mon, 10 Dec 2018 07:11:44 +0000
Subject: mlxsw: spectrum_acl: Limit priority value

In Spectrum-2, higher priority value wins and priority valid values are in
the range of {1,cap_kvd_size-1}. mlxsw_sp_acl_tcam_priority_get converts
from lower-bound priorities alike tc flower to Spectrum-2 HW range. Up
until now tc flower did not provide priority 0 or reached the maximal
value, however multicast routing does provide priority 0.

Therefore, Change mlxsw_sp_acl_tcam_priority_get to verify priority is in
the correct range. Make sure priority is never set to zero and never
exceeds the maximal allowed value.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index f1f98a1770d2..fe230acf92a9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -95,8 +95,9 @@ int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
 	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, KVD_SIZE))
 		return -EIO;
 
-	max_priority = MLXSW_CORE_RES_GET(mlxsw_sp->core, KVD_SIZE);
-	if (rulei->priority > max_priority)
+	/* Priority range is 1..cap_kvd_size-1. */
+	max_priority = MLXSW_CORE_RES_GET(mlxsw_sp->core, KVD_SIZE) - 1;
+	if (rulei->priority >= max_priority)
 		return -EINVAL;
 
 	/* Unlike in TC, in HW, higher number means higher priority. */
-- 
cgit v1.2.3


From cf7221a4f5a53f4975bdf55a9fa5de7a32acfc6d Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Mon, 10 Dec 2018 07:11:45 +0000
Subject: mlxsw: spectrum_router: Add Multicast routing support for Spectrum-2

Add implementation of Spectrum-2 multicast routes for both IPv4 and IPv6 by
using ACL module explicitly.
In Spectrum-2, multicast routes are set as ACL rules, so initialization
takes care of creating dedicated ACL groups and binding them to the
appropriate multicast routing protocol IPv4/IPv6, and afterwards routes
configuration translates to setting explicit ACL rules.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c    | 281 ++++++++++++++++++++-
 1 file changed, 280 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
index 4dd62478162e..e31ec75ac035 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
@@ -7,6 +7,201 @@
 #include "spectrum.h"
 #include "spectrum_mr.h"
 
+struct mlxsw_sp2_mr_tcam {
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_acl_block *acl_block;
+	struct mlxsw_sp_acl_ruleset *ruleset4;
+	struct mlxsw_sp_acl_ruleset *ruleset6;
+};
+
+struct mlxsw_sp2_mr_route {
+	struct mlxsw_sp2_mr_tcam *mr_tcam;
+};
+
+static struct mlxsw_sp_acl_ruleset *
+mlxsw_sp2_mr_tcam_proto_ruleset(struct mlxsw_sp2_mr_tcam *mr_tcam,
+				enum mlxsw_sp_l3proto proto)
+{
+	switch (proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		return mr_tcam->ruleset4;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		return mr_tcam->ruleset6;
+	}
+	return NULL;
+}
+
+static int mlxsw_sp2_mr_tcam_bind_group(struct mlxsw_sp *mlxsw_sp,
+					enum mlxsw_reg_pemrbt_protocol protocol,
+					struct mlxsw_sp_acl_ruleset *ruleset)
+{
+	char pemrbt_pl[MLXSW_REG_PEMRBT_LEN];
+	u16 group_id;
+
+	group_id = mlxsw_sp_acl_ruleset_group_id(ruleset);
+
+	mlxsw_reg_pemrbt_pack(pemrbt_pl, protocol, group_id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pemrbt), pemrbt_pl);
+}
+
+static const enum mlxsw_afk_element mlxsw_sp2_mr_tcam_usage_ipv4[] = {
+		MLXSW_AFK_ELEMENT_VIRT_ROUTER_8_10,
+		MLXSW_AFK_ELEMENT_VIRT_ROUTER_0_7,
+		MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+		MLXSW_AFK_ELEMENT_DST_IP_0_31,
+};
+
+static int mlxsw_sp2_mr_tcam_ipv4_init(struct mlxsw_sp2_mr_tcam *mr_tcam)
+{
+	struct mlxsw_afk_element_usage elusage;
+	int err;
+
+	/* Initialize IPv4 ACL group. */
+	mlxsw_afk_element_usage_fill(&elusage,
+				     mlxsw_sp2_mr_tcam_usage_ipv4,
+				     ARRAY_SIZE(mlxsw_sp2_mr_tcam_usage_ipv4));
+	mr_tcam->ruleset4 = mlxsw_sp_acl_ruleset_get(mr_tcam->mlxsw_sp,
+						     mr_tcam->acl_block,
+						     MLXSW_SP_L3_PROTO_IPV4,
+						     MLXSW_SP_ACL_PROFILE_MR,
+						     &elusage);
+
+	if (IS_ERR(mr_tcam->ruleset4))
+		return PTR_ERR(mr_tcam->ruleset4);
+
+	/* MC Router groups should be bound before routes are inserted. */
+	err = mlxsw_sp2_mr_tcam_bind_group(mr_tcam->mlxsw_sp,
+					   MLXSW_REG_PEMRBT_PROTO_IPV4,
+					   mr_tcam->ruleset4);
+	if (err)
+		goto err_bind_group;
+
+	return 0;
+
+err_bind_group:
+	mlxsw_sp_acl_ruleset_put(mr_tcam->mlxsw_sp, mr_tcam->ruleset4);
+	return err;
+}
+
+static void mlxsw_sp2_mr_tcam_ipv4_fini(struct mlxsw_sp2_mr_tcam *mr_tcam)
+{
+	mlxsw_sp_acl_ruleset_put(mr_tcam->mlxsw_sp, mr_tcam->ruleset4);
+}
+
+static const enum mlxsw_afk_element mlxsw_sp2_mr_tcam_usage_ipv6[] = {
+		MLXSW_AFK_ELEMENT_VIRT_ROUTER_8_10,
+		MLXSW_AFK_ELEMENT_VIRT_ROUTER_0_7,
+		MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+		MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+		MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+		MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+		MLXSW_AFK_ELEMENT_DST_IP_96_127,
+		MLXSW_AFK_ELEMENT_DST_IP_64_95,
+		MLXSW_AFK_ELEMENT_DST_IP_32_63,
+		MLXSW_AFK_ELEMENT_DST_IP_0_31,
+};
+
+static int mlxsw_sp2_mr_tcam_ipv6_init(struct mlxsw_sp2_mr_tcam *mr_tcam)
+{
+	struct mlxsw_afk_element_usage elusage;
+	int err;
+
+	/* Initialize IPv6 ACL group */
+	mlxsw_afk_element_usage_fill(&elusage,
+				     mlxsw_sp2_mr_tcam_usage_ipv6,
+				     ARRAY_SIZE(mlxsw_sp2_mr_tcam_usage_ipv6));
+	mr_tcam->ruleset6 = mlxsw_sp_acl_ruleset_get(mr_tcam->mlxsw_sp,
+						     mr_tcam->acl_block,
+						     MLXSW_SP_L3_PROTO_IPV6,
+						     MLXSW_SP_ACL_PROFILE_MR,
+						     &elusage);
+
+	if (IS_ERR(mr_tcam->ruleset6))
+		return PTR_ERR(mr_tcam->ruleset6);
+
+	/* MC Router groups should be bound before routes are inserted. */
+	err = mlxsw_sp2_mr_tcam_bind_group(mr_tcam->mlxsw_sp,
+					   MLXSW_REG_PEMRBT_PROTO_IPV6,
+					   mr_tcam->ruleset6);
+	if (err)
+		goto err_bind_group;
+
+	return 0;
+
+err_bind_group:
+	mlxsw_sp_acl_ruleset_put(mr_tcam->mlxsw_sp, mr_tcam->ruleset6);
+	return err;
+}
+
+static void mlxsw_sp2_mr_tcam_ipv6_fini(struct mlxsw_sp2_mr_tcam *mr_tcam)
+{
+	mlxsw_sp_acl_ruleset_put(mr_tcam->mlxsw_sp, mr_tcam->ruleset6);
+}
+
+static void
+mlxsw_sp2_mr_tcam_rule_parse4(struct mlxsw_sp_acl_rule_info *rulei,
+			      struct mlxsw_sp_mr_route_key *key)
+{
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+				       (char *) &key->source.addr4,
+				       (char *) &key->source_mask.addr4, 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
+				       (char *) &key->group.addr4,
+				       (char *) &key->group_mask.addr4, 4);
+}
+
+static void
+mlxsw_sp2_mr_tcam_rule_parse6(struct mlxsw_sp_acl_rule_info *rulei,
+			      struct mlxsw_sp_mr_route_key *key)
+{
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+				       &key->source.addr6.s6_addr[0x0],
+				       &key->source_mask.addr6.s6_addr[0x0], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+				       &key->source.addr6.s6_addr[0x4],
+				       &key->source_mask.addr6.s6_addr[0x4], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+				       &key->source.addr6.s6_addr[0x8],
+				       &key->source_mask.addr6.s6_addr[0x8], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+				       &key->source.addr6.s6_addr[0xc],
+				       &key->source_mask.addr6.s6_addr[0xc], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_96_127,
+				       &key->group.addr6.s6_addr[0x0],
+				       &key->group_mask.addr6.s6_addr[0x0], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_64_95,
+				       &key->group.addr6.s6_addr[0x4],
+				       &key->group_mask.addr6.s6_addr[0x4], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_32_63,
+				       &key->group.addr6.s6_addr[0x8],
+				       &key->group_mask.addr6.s6_addr[0x8], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
+				       &key->group.addr6.s6_addr[0xc],
+				       &key->group_mask.addr6.s6_addr[0xc], 4);
+}
+
+static void
+mlxsw_sp2_mr_tcam_rule_parse(struct mlxsw_sp_acl_rule *rule,
+			     struct mlxsw_sp_mr_route_key *key,
+			     unsigned int priority)
+{
+	struct mlxsw_sp_acl_rule_info *rulei;
+
+	rulei = mlxsw_sp_acl_rule_rulei(rule);
+	rulei->priority = priority;
+	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_VIRT_ROUTER_0_7,
+				       key->vrid, GENMASK(7, 0));
+	mlxsw_sp_acl_rulei_keymask_u32(rulei,
+				       MLXSW_AFK_ELEMENT_VIRT_ROUTER_8_10,
+				       key->vrid >> 8, GENMASK(2, 0));
+	switch (key->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		return mlxsw_sp2_mr_tcam_rule_parse4(rulei, key);
+	case MLXSW_SP_L3_PROTO_IPV6:
+		return mlxsw_sp2_mr_tcam_rule_parse6(rulei, key);
+	}
+}
+
 static int
 mlxsw_sp2_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
 			       void *route_priv,
@@ -14,7 +209,33 @@ mlxsw_sp2_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
 			       struct mlxsw_afa_block *afa_block,
 			       enum mlxsw_sp_mr_route_prio prio)
 {
+	struct mlxsw_sp2_mr_route *mr_route = route_priv;
+	struct mlxsw_sp2_mr_tcam *mr_tcam = priv;
+	struct mlxsw_sp_acl_ruleset *ruleset;
+	struct mlxsw_sp_acl_rule *rule;
+	int err;
+
+	mr_route->mr_tcam = mr_tcam;
+	ruleset = mlxsw_sp2_mr_tcam_proto_ruleset(mr_tcam, key->proto);
+	if (WARN_ON(!ruleset))
+		return -EINVAL;
+
+	rule = mlxsw_sp_acl_rule_create(mlxsw_sp, ruleset,
+					(unsigned long) route_priv, afa_block,
+					NULL);
+	if (IS_ERR(rule))
+		return PTR_ERR(rule);
+
+	mlxsw_sp2_mr_tcam_rule_parse(rule, key, prio);
+	err = mlxsw_sp_acl_rule_add(mlxsw_sp, rule);
+	if (err)
+		goto err_rule_add;
+
 	return 0;
+
+err_rule_add:
+	mlxsw_sp_acl_rule_destroy(mlxsw_sp, rule);
+	return err;
 }
 
 static void
@@ -22,6 +243,21 @@ mlxsw_sp2_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp, void *priv,
 				void *route_priv,
 				struct mlxsw_sp_mr_route_key *key)
 {
+	struct mlxsw_sp2_mr_tcam *mr_tcam = priv;
+	struct mlxsw_sp_acl_ruleset *ruleset;
+	struct mlxsw_sp_acl_rule *rule;
+
+	ruleset = mlxsw_sp2_mr_tcam_proto_ruleset(mr_tcam, key->proto);
+	if (WARN_ON(!ruleset))
+		return;
+
+	rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset,
+					(unsigned long) route_priv);
+	if (WARN_ON(!rule))
+		return;
+
+	mlxsw_sp_acl_rule_del(mlxsw_sp, rule);
+	mlxsw_sp_acl_rule_destroy(mlxsw_sp, rule);
 }
 
 static int
@@ -30,21 +266,64 @@ mlxsw_sp2_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_mr_route_key *key,
 			       struct mlxsw_afa_block *afa_block)
 {
-	return 0;
+	struct mlxsw_sp2_mr_route *mr_route = route_priv;
+	struct mlxsw_sp2_mr_tcam *mr_tcam = mr_route->mr_tcam;
+	struct mlxsw_sp_acl_ruleset *ruleset;
+	struct mlxsw_sp_acl_rule *rule;
+
+	ruleset = mlxsw_sp2_mr_tcam_proto_ruleset(mr_tcam, key->proto);
+	if (WARN_ON(!ruleset))
+		return -EINVAL;
+
+	rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset,
+					(unsigned long) route_priv);
+	if (WARN_ON(!rule))
+		return -EINVAL;
+
+	return mlxsw_sp_acl_rule_action_replace(mlxsw_sp, rule, afa_block);
 }
 
 static int mlxsw_sp2_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
 {
+	struct mlxsw_sp2_mr_tcam *mr_tcam = priv;
+	int err;
+
+	mr_tcam->mlxsw_sp = mlxsw_sp;
+	mr_tcam->acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, NULL);
+	if (!mr_tcam->acl_block)
+		return -ENOMEM;
+
+	err = mlxsw_sp2_mr_tcam_ipv4_init(mr_tcam);
+	if (err)
+		goto err_ipv4_init;
+
+	err = mlxsw_sp2_mr_tcam_ipv6_init(mr_tcam);
+	if (err)
+		goto err_ipv6_init;
+
 	return 0;
+
+err_ipv6_init:
+	mlxsw_sp2_mr_tcam_ipv4_fini(mr_tcam);
+err_ipv4_init:
+	mlxsw_sp_acl_block_destroy(mr_tcam->acl_block);
+	return err;
 }
 
 static void mlxsw_sp2_mr_tcam_fini(void *priv)
 {
+	struct mlxsw_sp2_mr_tcam *mr_tcam = priv;
+
+	mlxsw_sp2_mr_tcam_ipv6_fini(mr_tcam);
+	mlxsw_sp2_mr_tcam_ipv4_fini(mr_tcam);
+	mlxsw_sp_acl_block_destroy(mr_tcam->acl_block);
 }
 
 const struct mlxsw_sp_mr_tcam_ops mlxsw_sp2_mr_tcam_ops = {
+	.priv_size = sizeof(struct mlxsw_sp2_mr_tcam),
 	.init = mlxsw_sp2_mr_tcam_init,
 	.fini = mlxsw_sp2_mr_tcam_fini,
+	.route_priv_size = sizeof(struct mlxsw_sp2_mr_route),
 	.route_create = mlxsw_sp2_mr_tcam_route_create,
 	.route_destroy = mlxsw_sp2_mr_tcam_route_destroy,
 	.route_update = mlxsw_sp2_mr_tcam_route_update,
-- 
cgit v1.2.3


From 6d4efada3b823b3e9019e50c40114abca43a677b Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Mon, 10 Dec 2018 07:11:46 +0000
Subject: selftests: forwarding: Add multicast routing test

Introduce basic testing for both IPv4 and IPv6 multicast. The test creates
an (S,G) type route, sends traffic and verifies traffic arrives when the
route is present and then verifies traffic does not arrive after deleting
the route.
This test requires smcroute - https://github.com/troglobit/smcroute which
is a tool that allows creation of static multicast routes.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh      |   2 +
 .../selftests/net/forwarding/router_multicast.sh   | 311 +++++++++++++++++++++
 2 files changed, 313 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_multicast.sh

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 7af5a03bcb32..3f248d1f5b91 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -15,6 +15,8 @@ PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
 PAUSE_ON_CLEANUP=${PAUSE_ON_CLEANUP:=no}
 NETIF_TYPE=${NETIF_TYPE:=veth}
 NETIF_CREATE=${NETIF_CREATE:=yes}
+MCD=${MCD:=smcrouted}
+MC_CLI=${MC_CLI:=smcroutectl}
 
 relative_path="${BASH_SOURCE%/*}"
 if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
diff --git a/tools/testing/selftests/net/forwarding/router_multicast.sh b/tools/testing/selftests/net/forwarding/router_multicast.sh
new file mode 100755
index 000000000000..109e6d785169
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_multicast.sh
@@ -0,0 +1,311 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +------------------+
+# | H1 (v$h1)        |
+# | 2001:db8:1::2/64 |
+# | 198.51.100.2/28  |
+# |         $h1 +    |
+# +-------------|----+
+#               |
+# +-------------|-------------------------------+
+# | SW1         |                               |
+# |        $rp1 +                               |
+# | 198.51.100.1/28                             |
+# | 2001:db8:1::1/64                            |
+# |                                             |
+# | 2001:db8:2::1/64           2001:db8:3::1/64 |
+# | 198.51.100.17/28           198.51.100.33/28 |
+# |         $rp2 +                     $rp3 +   |
+# +--------------|--------------------------|---+
+#                |                          |
+#                |                          |
+# +--------------|---+       +--------------|---+
+# | H2 (v$h2)    |   |       | H3 (v$h3)    |   |
+# |          $h2 +   |       |          $h3 +   |
+# | 198.51.100.18/28 |       | 198.51.100.34/28 |
+# | 2001:db8:2::2/64 |       | 2001:db8:3::2/64 |
+# +------------------+       +------------------+
+#
+
+ALL_TESTS="mcast_v4 mcast_v6"
+NUM_NETIFS=6
+source lib.sh
+source tc_common.sh
+
+require_command $MCD
+require_command $MC_CLI
+table_name=selftests
+
+h1_create()
+{
+	simple_if_init $h1 198.51.100.2/28 2001:db8:1::2/64
+
+	ip route add 198.51.100.16/28 vrf v$h1 nexthop via 198.51.100.1
+	ip route add 198.51.100.32/28 vrf v$h1 nexthop via 198.51.100.1
+
+	ip route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::1
+	ip route add 2001:db8:3::/64 vrf v$h1 nexthop via 2001:db8:1::1
+}
+
+h1_destroy()
+{
+	ip route del 2001:db8:3::/64 vrf v$h1
+	ip route del 2001:db8:2::/64 vrf v$h1
+
+	ip route del 198.51.100.32/28 vrf v$h1
+	ip route del 198.51.100.16/28 vrf v$h1
+
+	simple_if_fini $h1 198.51.100.2/28 2001:db8:1::2/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 198.51.100.18/28 2001:db8:2::2/64
+
+	ip route add 198.51.100.0/28 vrf v$h2 nexthop via 198.51.100.17
+	ip route add 198.51.100.32/28 vrf v$h2 nexthop via 198.51.100.17
+
+	ip route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+	ip route add 2001:db8:3::/64 vrf v$h2 nexthop via 2001:db8:2::1
+
+	tc qdisc add dev $h2 ingress
+}
+
+h2_destroy()
+{
+	tc qdisc del dev $h2 ingress
+
+	ip route del 2001:db8:3::/64 vrf v$h2
+	ip route del 2001:db8:1::/64 vrf v$h2
+
+	ip route del 198.51.100.32/28 vrf v$h2
+	ip route del 198.51.100.0/28 vrf v$h2
+
+	simple_if_fini $h2 198.51.100.18/28 2001:db8:2::2/64
+}
+
+h3_create()
+{
+	simple_if_init $h3 198.51.100.34/28 2001:db8:3::2/64
+
+	ip route add 198.51.100.0/28 vrf v$h3 nexthop via 198.51.100.33
+	ip route add 198.51.100.16/28 vrf v$h3 nexthop via 198.51.100.33
+
+	ip route add 2001:db8:1::/64 vrf v$h3 nexthop via 2001:db8:3::1
+	ip route add 2001:db8:2::/64 vrf v$h3 nexthop via 2001:db8:3::1
+
+	tc qdisc add dev $h3 ingress
+}
+
+h3_destroy()
+{
+	tc qdisc del dev $h3 ingress
+
+	ip route del 2001:db8:2::/64 vrf v$h3
+	ip route del 2001:db8:1::/64 vrf v$h3
+
+	ip route del 198.51.100.16/28 vrf v$h3
+	ip route del 198.51.100.0/28 vrf v$h3
+
+	simple_if_fini $h3 198.51.100.34/28 2001:db8:3::2/64
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	ip link set dev $rp2 up
+	ip link set dev $rp3 up
+
+	ip address add 198.51.100.1/28 dev $rp1
+	ip address add 198.51.100.17/28 dev $rp2
+	ip address add 198.51.100.33/28 dev $rp3
+
+	ip address add 2001:db8:1::1/64 dev $rp1
+	ip address add 2001:db8:2::1/64 dev $rp2
+	ip address add 2001:db8:3::1/64 dev $rp3
+}
+
+router_destroy()
+{
+	ip address del 2001:db8:3::1/64 dev $rp3
+	ip address del 2001:db8:2::1/64 dev $rp2
+	ip address del 2001:db8:1::1/64 dev $rp1
+
+	ip address del 198.51.100.33/28 dev $rp3
+	ip address del 198.51.100.17/28 dev $rp2
+	ip address del 198.51.100.1/28 dev $rp1
+
+	ip link set dev $rp3 down
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
+}
+
+start_mcd()
+{
+	SMCROUTEDIR="$(mktemp -d)"
+
+	for ((i = 1; i <= $NUM_NETIFS; ++i)); do
+		echo "phyint ${NETIFS[p$i]} enable" >> \
+			$SMCROUTEDIR/$table_name.conf
+	done
+
+	$MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \
+		-P $SMCROUTEDIR/$table_name.pid
+}
+
+kill_mcd()
+{
+	pkill $MCD
+	rm -rf $SMCROUTEDIR
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	start_mcd
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+	h3_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h3_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+
+	kill_mcd
+}
+
+create_mcast_sg()
+{
+	local if_name=$1; shift
+	local s_addr=$1; shift
+	local mcast=$1; shift
+	local dest_ifs=${@}
+
+	$MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs
+}
+
+delete_mcast_sg()
+{
+	local if_name=$1; shift
+	local s_addr=$1; shift
+	local mcast=$1; shift
+	local dest_ifs=${@}
+
+        $MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs
+}
+
+mcast_v4()
+{
+	# Add two interfaces to an MC group, send a packet to the MC group and
+	# verify packets are received on both. Then delete the route and verify
+	# packets are no longer received.
+
+	RET=0
+
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 122 flower \
+		dst_ip 225.1.2.3 action drop
+	tc filter add dev $h3 ingress protocol ip pref 1 handle 133 flower \
+		dst_ip 225.1.2.3 action drop
+
+	create_mcast_sg $rp1 198.51.100.2 225.1.2.3 $rp2 $rp3
+
+	# Send frames with the corresponding L2 destination address.
+	$MZ $h1 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 -b 01:00:5e:01:02:03 \
+		-A 198.51.100.2 -B 225.1.2.3 -q
+
+	tc_check_packets "dev $h2 ingress" 122 5
+	check_err $? "Multicast not received on first host"
+	tc_check_packets "dev $h3 ingress" 133 5
+	check_err $? "Multicast not received on second host"
+
+	delete_mcast_sg $rp1 198.51.100.2 225.1.2.3 $rp2 $rp3
+
+	$MZ $h1 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 -b 01:00:5e:01:02:03 \
+		-A 198.51.100.2 -B 225.1.2.3 -q
+
+	tc_check_packets "dev $h2 ingress" 122 5
+	check_err $? "Multicast received on host although deleted"
+	tc_check_packets "dev $h3 ingress" 133 5
+	check_err $? "Multicast received on second host although deleted"
+
+	tc filter del dev $h3 ingress protocol ip pref 1 handle 133 flower
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 122 flower
+
+	log_test "mcast IPv4"
+}
+
+mcast_v6()
+{
+	# Add two interfaces to an MC group, send a packet to the MC group and
+	# verify packets are received on both. Then delete the route and verify
+	# packets are no longer received.
+
+	RET=0
+
+	tc filter add dev $h2 ingress protocol ipv6 pref 1 handle 122 flower \
+		dst_ip ff0e::3 action drop
+	tc filter add dev $h3 ingress protocol ipv6 pref 1 handle 133 flower \
+		dst_ip ff0e::3 action drop
+
+	create_mcast_sg $rp1 2001:db8:1::2 ff0e::3 $rp2 $rp3
+
+	# Send frames with the corresponding L2 destination address.
+	$MZ $h1 -6 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 \
+		-b 33:33:00:00:00:03 -A 2001:db8:1::2 -B ff0e::3 -q
+
+	tc_check_packets "dev $h2 ingress" 122 5
+	check_err $? "Multicast not received on first host"
+	tc_check_packets "dev $h3 ingress" 133 5
+	check_err $? "Multicast not received on second host"
+
+	delete_mcast_sg $rp1 2001:db8:1::2 ff0e::3 $rp2 $rp3
+
+	$MZ $h1 -6 -c 5 -p 128 -t udp -a 00:11:22:33:44:55 \
+		-b 33:33:00:00:00:03 -A 2001:db8:1::2 -B ff0e::3 -q
+
+	tc_check_packets "dev $h2 ingress" 122 5
+	check_err $? "Multicast received on first host although deleted"
+	tc_check_packets "dev $h3 ingress" 133 5
+	check_err $? "Multicast received on second host although deleted"
+
+	tc filter del dev $h3 ingress protocol ipv6 pref 1 handle 133 flower
+	tc filter del dev $h2 ingress protocol ipv6 pref 1 handle 122 flower
+
+	log_test "mcast IPv6"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 9992f37e346bb00369c261981f2839a5926bf2eb Mon Sep 17 00:00:00 2001
From: Biao Huang <biao.huang@mediatek.com>
Date: Wed, 12 Dec 2018 17:35:31 +0800
Subject: stmmac: dwmac-mediatek: add support for mt2712

Add Ethernet support for MediaTek SoCs from the mt2712 family

Signed-off-by: Biao Huang <biao.huang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/Kconfig        |   8 +
 drivers/net/ethernet/stmicro/stmmac/Makefile       |   1 +
 .../net/ethernet/stmicro/stmmac/dwmac-mediatek.c   | 408 +++++++++++++++++++++
 3 files changed, 417 insertions(+)
 create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c

diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 324049eebb9b..6209cc1fb305 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -75,6 +75,14 @@ config DWMAC_LPC18XX
 	---help---
 	  Support for NXP LPC18xx/43xx DWMAC Ethernet.
 
+config DWMAC_MEDIATEK
+	tristate "MediaTek MT27xx GMAC support"
+	depends on OF && (ARCH_MEDIATEK || COMPILE_TEST)
+	help
+	  Support for MediaTek GMAC Ethernet controller.
+
+	  This selects the MT2712 SoC support for the stmmac driver.
+
 config DWMAC_MESON
 	tristate "Amlogic Meson dwmac support"
 	default ARCH_MESON
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 99967a80a8c8..bf09701d2623 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_STMMAC_PLATFORM)	+= stmmac-platform.o
 obj-$(CONFIG_DWMAC_ANARION)	+= dwmac-anarion.o
 obj-$(CONFIG_DWMAC_IPQ806X)	+= dwmac-ipq806x.o
 obj-$(CONFIG_DWMAC_LPC18XX)	+= dwmac-lpc18xx.o
+obj-$(CONFIG_DWMAC_MEDIATEK)	+= dwmac-mediatek.o
 obj-$(CONFIG_DWMAC_MESON)	+= dwmac-meson.o dwmac-meson8b.o
 obj-$(CONFIG_DWMAC_OXNAS)	+= dwmac-oxnas.o
 obj-$(CONFIG_DWMAC_ROCKCHIP)	+= dwmac-rk.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
new file mode 100644
index 000000000000..b5db85d298e7
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 MediaTek Inc.
+ */
+#include <linux/bitfield.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_net.h>
+#include <linux/regmap.h>
+#include <linux/stmmac.h>
+
+#include "stmmac.h"
+#include "stmmac_platform.h"
+
+/* Peri Configuration register for mt2712 */
+#define PERI_ETH_PHY_INTF_SEL	0x418
+#define PHY_INTF_MII		0
+#define PHY_INTF_RGMII		1
+#define PHY_INTF_RMII		4
+#define RMII_CLK_SRC_RXC	BIT(4)
+#define RMII_CLK_SRC_INTERNAL	BIT(5)
+
+#define PERI_ETH_DLY	0x428
+#define ETH_DLY_GTXC_INV	BIT(6)
+#define ETH_DLY_GTXC_ENABLE	BIT(5)
+#define ETH_DLY_GTXC_STAGES	GENMASK(4, 0)
+#define ETH_DLY_TXC_INV		BIT(20)
+#define ETH_DLY_TXC_ENABLE	BIT(19)
+#define ETH_DLY_TXC_STAGES	GENMASK(18, 14)
+#define ETH_DLY_RXC_INV		BIT(13)
+#define ETH_DLY_RXC_ENABLE	BIT(12)
+#define ETH_DLY_RXC_STAGES	GENMASK(11, 7)
+
+#define PERI_ETH_DLY_FINE	0x800
+#define ETH_RMII_DLY_TX_INV	BIT(2)
+#define ETH_FINE_DLY_GTXC	BIT(1)
+#define ETH_FINE_DLY_RXC	BIT(0)
+
+struct mac_delay_struct {
+	u32 tx_delay;
+	u32 rx_delay;
+	bool tx_inv;
+	bool rx_inv;
+	bool fine_tune;
+};
+
+struct mediatek_dwmac_plat_data {
+	const struct mediatek_dwmac_variant *variant;
+	struct mac_delay_struct mac_delay;
+	struct clk_bulk_data *clks;
+	struct device_node *np;
+	struct regmap *peri_regmap;
+	struct device *dev;
+	int phy_mode;
+	bool rmii_rxc;
+};
+
+struct mediatek_dwmac_variant {
+	int (*dwmac_set_phy_interface)(struct mediatek_dwmac_plat_data *plat);
+	int (*dwmac_set_delay)(struct mediatek_dwmac_plat_data *plat);
+
+	/* clock ids to be requested */
+	const char * const *clk_list;
+	int num_clks;
+
+	u32 dma_bit_mask;
+	u32 rx_delay_max;
+	u32 tx_delay_max;
+};
+
+/* list of clocks required for mac */
+static const char * const mt2712_dwmac_clk_l[] = {
+	"axi", "apb", "mac_main", "ptp_ref"
+};
+
+static int mt2712_set_interface(struct mediatek_dwmac_plat_data *plat)
+{
+	int rmii_rxc = plat->rmii_rxc ? RMII_CLK_SRC_RXC : 0;
+	u32 intf_val = 0;
+
+	/* select phy interface in top control domain */
+	switch (plat->phy_mode) {
+	case PHY_INTERFACE_MODE_MII:
+		intf_val |= PHY_INTF_MII;
+		break;
+	case PHY_INTERFACE_MODE_RMII:
+		intf_val |= (PHY_INTF_RMII | rmii_rxc);
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		intf_val |= PHY_INTF_RGMII;
+		break;
+	default:
+		dev_err(plat->dev, "phy interface not supported\n");
+		return -EINVAL;
+	}
+
+	regmap_write(plat->peri_regmap, PERI_ETH_PHY_INTF_SEL, intf_val);
+
+	return 0;
+}
+
+static void mt2712_delay_ps2stage(struct mac_delay_struct *mac_delay)
+{
+	if (mac_delay->fine_tune) {
+		/* 170ps per stage for fine tune delay macro circuit*/
+		mac_delay->tx_delay /= 170;
+		mac_delay->rx_delay /= 170;
+	} else {
+		/* 550ps per stage for coarse tune delay macro circuit*/
+		mac_delay->tx_delay /= 550;
+		mac_delay->rx_delay /= 550;
+	}
+}
+
+static int mt2712_set_delay(struct mediatek_dwmac_plat_data *plat)
+{
+	struct mac_delay_struct *mac_delay = &plat->mac_delay;
+	u32 delay_val = 0, fine_val = 0;
+
+	mt2712_delay_ps2stage(mac_delay);
+
+	switch (plat->phy_mode) {
+	case PHY_INTERFACE_MODE_MII:
+		delay_val |= FIELD_PREP(ETH_DLY_TXC_ENABLE, !!mac_delay->tx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_TXC_STAGES, mac_delay->tx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_TXC_INV, mac_delay->tx_inv);
+
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_ENABLE, !!mac_delay->rx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_STAGES, mac_delay->rx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_INV, mac_delay->rx_inv);
+		break;
+	case PHY_INTERFACE_MODE_RMII:
+		/* the rmii reference clock is from external phy,
+		 * and the property "rmii_rxc" indicates which pin(TXC/RXC)
+		 * the reference clk is connected to. The reference clock is a
+		 * received signal, so rx_delay/rx_inv are used to indicate
+		 * the reference clock timing adjustment
+		 */
+		if (plat->rmii_rxc) {
+			/* the rmii reference clock from outside is connected
+			 * to RXC pin, the reference clock will be adjusted
+			 * by RXC delay macro circuit.
+			 */
+			delay_val |= FIELD_PREP(ETH_DLY_RXC_ENABLE, !!mac_delay->rx_delay);
+			delay_val |= FIELD_PREP(ETH_DLY_RXC_STAGES, mac_delay->rx_delay);
+			delay_val |= FIELD_PREP(ETH_DLY_RXC_INV, mac_delay->rx_inv);
+		} else {
+			/* the rmii reference clock from outside is connected
+			 * to TXC pin, the reference clock will be adjusted
+			 * by TXC delay macro circuit.
+			 */
+			delay_val |= FIELD_PREP(ETH_DLY_TXC_ENABLE, !!mac_delay->rx_delay);
+			delay_val |= FIELD_PREP(ETH_DLY_TXC_STAGES, mac_delay->rx_delay);
+			delay_val |= FIELD_PREP(ETH_DLY_TXC_INV, mac_delay->rx_inv);
+		}
+		/* tx_inv will inverse the tx clock inside mac relateive to
+		 * reference clock from external phy,
+		 * and this bit is located in the same register with fine-tune
+		 */
+		if (mac_delay->tx_inv)
+			fine_val = ETH_RMII_DLY_TX_INV;
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+		/* the PHY is not responsible for inserting any internal
+		 * delay by itself in PHY_INTERFACE_MODE_RGMII case,
+		 * so Ethernet MAC will insert delays for both transmit
+		 * and receive path here.
+		 */
+		if (mac_delay->fine_tune)
+			fine_val = ETH_FINE_DLY_GTXC | ETH_FINE_DLY_RXC;
+
+		delay_val |= FIELD_PREP(ETH_DLY_GTXC_ENABLE, !!mac_delay->tx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_GTXC_STAGES, mac_delay->tx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_GTXC_INV, mac_delay->tx_inv);
+
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_ENABLE, !!mac_delay->rx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_STAGES, mac_delay->rx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_INV, mac_delay->rx_inv);
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		/* the PHY should insert an internal delay for the transmit
+		 * path in PHY_INTERFACE_MODE_RGMII_TXID case,
+		 * so Ethernet MAC will insert the delay for receive path here.
+		 */
+		if (mac_delay->fine_tune)
+			fine_val = ETH_FINE_DLY_RXC;
+
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_ENABLE, !!mac_delay->rx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_STAGES, mac_delay->rx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_INV, mac_delay->rx_inv);
+		break;
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		/* the PHY should insert an internal delay for the receive
+		 * path in PHY_INTERFACE_MODE_RGMII_RXID case,
+		 * so Ethernet MAC will insert the delay for transmit path here.
+		 */
+		if (mac_delay->fine_tune)
+			fine_val = ETH_FINE_DLY_GTXC;
+
+		delay_val |= FIELD_PREP(ETH_DLY_GTXC_ENABLE, !!mac_delay->tx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_GTXC_STAGES, mac_delay->tx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_GTXC_INV, mac_delay->tx_inv);
+		break;
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		/* the PHY should insert internal delays for both transmit
+		 * and receive path in PHY_INTERFACE_MODE_RGMII_RXID case,
+		 * so Ethernet MAC will NOT insert any delay here.
+		 */
+		break;
+	default:
+		dev_err(plat->dev, "phy interface not supported\n");
+		return -EINVAL;
+	}
+	regmap_write(plat->peri_regmap, PERI_ETH_DLY, delay_val);
+	regmap_write(plat->peri_regmap, PERI_ETH_DLY_FINE, fine_val);
+
+	return 0;
+}
+
+static const struct mediatek_dwmac_variant mt2712_gmac_variant = {
+		.dwmac_set_phy_interface = mt2712_set_interface,
+		.dwmac_set_delay = mt2712_set_delay,
+		.clk_list = mt2712_dwmac_clk_l,
+		.num_clks = ARRAY_SIZE(mt2712_dwmac_clk_l),
+		.dma_bit_mask = 33,
+		.rx_delay_max = 17600,
+		.tx_delay_max = 17600,
+};
+
+static int mediatek_dwmac_config_dt(struct mediatek_dwmac_plat_data *plat)
+{
+	struct mac_delay_struct *mac_delay = &plat->mac_delay;
+	u32 tx_delay_ps, rx_delay_ps;
+
+	plat->peri_regmap = syscon_regmap_lookup_by_phandle(plat->np, "mediatek,pericfg");
+	if (IS_ERR(plat->peri_regmap)) {
+		dev_err(plat->dev, "Failed to get pericfg syscon\n");
+		return PTR_ERR(plat->peri_regmap);
+	}
+
+	plat->phy_mode = of_get_phy_mode(plat->np);
+	if (plat->phy_mode < 0) {
+		dev_err(plat->dev, "not find phy-mode\n");
+		return -EINVAL;
+	}
+
+	if (!of_property_read_u32(plat->np, "mediatek,tx-delay-ps", &tx_delay_ps)) {
+		if (tx_delay_ps < plat->variant->tx_delay_max) {
+			mac_delay->tx_delay = tx_delay_ps;
+		} else {
+			dev_err(plat->dev, "Invalid TX clock delay: %dps\n", tx_delay_ps);
+			return -EINVAL;
+		}
+	}
+
+	if (!of_property_read_u32(plat->np, "mediatek,rx-delay-ps", &rx_delay_ps)) {
+		if (rx_delay_ps < plat->variant->rx_delay_max) {
+			mac_delay->rx_delay = rx_delay_ps;
+		} else {
+			dev_err(plat->dev, "Invalid RX clock delay: %dps\n", rx_delay_ps);
+			return -EINVAL;
+		}
+	}
+
+	mac_delay->tx_inv = of_property_read_bool(plat->np, "mediatek,txc-inverse");
+	mac_delay->rx_inv = of_property_read_bool(plat->np, "mediatek,rxc-inverse");
+	mac_delay->fine_tune = of_property_read_bool(plat->np, "mediatek,fine-tune");
+	plat->rmii_rxc = of_property_read_bool(plat->np, "mediatek,rmii-rxc");
+
+	return 0;
+}
+
+static int mediatek_dwmac_clk_init(struct mediatek_dwmac_plat_data *plat)
+{
+	const struct mediatek_dwmac_variant *variant = plat->variant;
+	int i, num = variant->num_clks;
+
+	plat->clks = devm_kcalloc(plat->dev, num, sizeof(*plat->clks), GFP_KERNEL);
+	if (!plat->clks)
+		return -ENOMEM;
+
+	for (i = 0; i < num; i++)
+		plat->clks[i].id = variant->clk_list[i];
+
+	return devm_clk_bulk_get(plat->dev, num, plat->clks);
+}
+
+static int mediatek_dwmac_init(struct platform_device *pdev, void *priv)
+{
+	struct mediatek_dwmac_plat_data *plat = priv;
+	const struct mediatek_dwmac_variant *variant = plat->variant;
+	int ret;
+
+	ret = dma_set_mask_and_coherent(plat->dev, DMA_BIT_MASK(variant->dma_bit_mask));
+	if (ret) {
+		dev_err(plat->dev, "No suitable DMA available, err = %d\n", ret);
+		return ret;
+	}
+
+	ret = variant->dwmac_set_phy_interface(plat);
+	if (ret) {
+		dev_err(plat->dev, "failed to set phy interface, err = %d\n", ret);
+		return ret;
+	}
+
+	ret = variant->dwmac_set_delay(plat);
+	if (ret) {
+		dev_err(plat->dev, "failed to set delay value, err = %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_bulk_prepare_enable(variant->num_clks, plat->clks);
+	if (ret) {
+		dev_err(plat->dev, "failed to enable clks, err = %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void mediatek_dwmac_exit(struct platform_device *pdev, void *priv)
+{
+	struct mediatek_dwmac_plat_data *plat = priv;
+	const struct mediatek_dwmac_variant *variant = plat->variant;
+
+	clk_bulk_disable_unprepare(variant->num_clks, plat->clks);
+}
+
+static int mediatek_dwmac_probe(struct platform_device *pdev)
+{
+	struct mediatek_dwmac_plat_data *priv_plat;
+	struct plat_stmmacenet_data *plat_dat;
+	struct stmmac_resources stmmac_res;
+	int ret;
+
+	priv_plat = devm_kzalloc(&pdev->dev, sizeof(*priv_plat), GFP_KERNEL);
+	if (!priv_plat)
+		return -ENOMEM;
+
+	priv_plat->variant = of_device_get_match_data(&pdev->dev);
+	if (!priv_plat->variant) {
+		dev_err(&pdev->dev, "Missing dwmac-mediatek variant\n");
+		return -EINVAL;
+	}
+
+	priv_plat->dev = &pdev->dev;
+	priv_plat->np = pdev->dev.of_node;
+
+	ret = mediatek_dwmac_config_dt(priv_plat);
+	if (ret)
+		return ret;
+
+	ret = mediatek_dwmac_clk_init(priv_plat);
+	if (ret)
+		return ret;
+
+	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
+	if (ret)
+		return ret;
+
+	plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
+	if (IS_ERR(plat_dat))
+		return PTR_ERR(plat_dat);
+
+	plat_dat->interface = priv_plat->phy_mode;
+	/* clk_csr_i = 250-300MHz & MDC = clk_csr_i/124 */
+	plat_dat->clk_csr = 5;
+	plat_dat->has_gmac4 = 1;
+	plat_dat->has_gmac = 0;
+	plat_dat->pmt = 0;
+	plat_dat->maxmtu = ETH_DATA_LEN;
+	plat_dat->bsp_priv = priv_plat;
+	plat_dat->init = mediatek_dwmac_init;
+	plat_dat->exit = mediatek_dwmac_exit;
+	mediatek_dwmac_init(pdev, priv_plat);
+
+	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+	if (ret) {
+		stmmac_remove_config_dt(pdev, plat_dat);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id mediatek_dwmac_match[] = {
+	{ .compatible = "mediatek,mt2712-gmac",
+	  .data = &mt2712_gmac_variant },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, mediatek_dwmac_match);
+
+static struct platform_driver mediatek_dwmac_driver = {
+	.probe  = mediatek_dwmac_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name           = "dwmac-mediatek",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = mediatek_dwmac_match,
+	},
+};
+module_platform_driver(mediatek_dwmac_driver);
-- 
cgit v1.2.3


From 58ee90284ffa495b04d56d643001d6f64a13a580 Mon Sep 17 00:00:00 2001
From: Biao Huang <biao.huang@mediatek.com>
Date: Wed, 12 Dec 2018 17:35:32 +0800
Subject: dt-binding: mediatek-dwmac: add binding document for MediaTek MT2712
 DWMAC

The commit adds the device tree binding documentation for the MediaTek DWMAC
found on MediaTek MT2712.

Signed-off-by: Biao Huang <biao.huang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../devicetree/bindings/net/mediatek-dwmac.txt     | 87 ++++++++++++++++++++++
 1 file changed, 87 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/mediatek-dwmac.txt

diff --git a/Documentation/devicetree/bindings/net/mediatek-dwmac.txt b/Documentation/devicetree/bindings/net/mediatek-dwmac.txt
new file mode 100644
index 000000000000..4de479b4d44d
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/mediatek-dwmac.txt
@@ -0,0 +1,87 @@
+MediaTek DWMAC glue layer controller
+
+This file documents platform glue layer for stmmac.
+Please see stmmac.txt for the other unchanged properties.
+
+The device node has following properties.
+
+Required properties:
+- compatible:  Should be "mediatek,mt2712-gmac" for MT2712 SoC
+- reg:  Address and length of the register set for the device
+- interrupts:  Should contain the MAC interrupts
+- interrupt-names: Should contain a list of interrupt names corresponding to
+	the interrupts in the interrupts property, if available.
+	Should be "macirq" for the main MAC IRQ
+- clocks: Must contain a phandle for each entry in clock-names.
+- clock-names: The name of the clock listed in the clocks property. These are
+	"axi", "apb", "mac_main", "ptp_ref" for MT2712 SoC
+- mac-address: See ethernet.txt in the same directory
+- phy-mode: See ethernet.txt in the same directory
+- mediatek,pericfg: A phandle to the syscon node that control ethernet
+	interface and timing delay.
+
+Optional properties:
+- mediatek,tx-delay-ps: TX clock delay macro value. Default is 0.
+	It should be defined for rgmii/rgmii-rxid/mii interface.
+- mediatek,rx-delay-ps: RX clock delay macro value. Default is 0.
+	It should be defined for rgmii/rgmii-txid/mii/rmii interface.
+Both delay properties need to be a multiple of 170 for fine-tune rgmii,
+range 0~31*170.
+Both delay properties need to be a multiple of 550 for coarse-tune rgmii,
+range 0~31*550.
+Both delay properties need to be a multiple of 550 for mii/rmii,
+range 0~31*550.
+
+- mediatek,fine-tune: boolean property, if present indicates that fine delay
+	is selected for rgmii interface.
+	If present, tx-delay-ps/rx-delay-ps is 170+/-50ps per stage.
+	Else tx-delay-ps/rx-delay-ps of coarse delay macro is 0.55+/-0.2ns per stage.
+	This property do not apply to non-rgmii PHYs.
+	Only coarse-tune delay is supported for mii/rmii PHYs.
+- mediatek,rmii-rxc: boolean property, if present indicates that the rmii
+	reference clock, which is from external PHYs, is connected to RXC pin
+	on MT2712 SoC.
+	Otherwise, is connected to TXC pin.
+- mediatek,txc-inverse: boolean property, if present indicates that
+	1. tx clock will be inversed in mii/rgmii case,
+	2. tx clock inside MAC will be inversed relative to reference clock
+	   which is from external PHYs in rmii case, and it rarely happen.
+- mediatek,rxc-inverse: boolean property, if present indicates that
+	1. rx clock will be inversed in mii/rgmii case.
+	2. reference clock will be inversed when arrived at MAC in rmii case.
+- assigned-clocks: mac_main and ptp_ref clocks
+- assigned-clock-parents: parent clocks of the assigned clocks
+
+Example:
+	eth: ethernet@1101c000 {
+		compatible = "mediatek,mt2712-gmac";
+		reg = <0 0x1101c000 0 0x1300>;
+		interrupts = <GIC_SPI 237 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-names = "macirq";
+		phy-mode ="rgmii";
+		mac-address = [00 55 7b b5 7d f7];
+		clock-names = "axi",
+			      "apb",
+			      "mac_main",
+			      "ptp_ref",
+			      "ptp_top";
+		clocks = <&pericfg CLK_PERI_GMAC>,
+			 <&pericfg CLK_PERI_GMAC_PCLK>,
+			 <&topckgen CLK_TOP_ETHER_125M_SEL>,
+			 <&topckgen CLK_TOP_ETHER_50M_SEL>;
+		assigned-clocks = <&topckgen CLK_TOP_ETHER_125M_SEL>,
+				  <&topckgen CLK_TOP_ETHER_50M_SEL>;
+		assigned-clock-parents = <&topckgen CLK_TOP_ETHERPLL_125M>,
+					 <&topckgen CLK_TOP_APLL1_D3>;
+		mediatek,pericfg = <&pericfg>;
+		mediatek,tx-delay-ps = <1530>;
+		mediatek,rx-delay-ps = <1530>;
+		mediatek,fine-tune;
+		mediatek,rmii-rxc;
+		mediatek,txc-inverse;
+		mediatek,rxc-inverse;
+		snps,txpbl = <32>;
+		snps,rxpbl = <32>;
+		snps,reset-gpio = <&pio 87 GPIO_ACTIVE_LOW>;
+		snps,reset-active-low;
+	};
-- 
cgit v1.2.3


From a0517a0f7ef23550b4484c37e2b9c2d32abebf64 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Tue, 11 Dec 2018 19:20:52 -0800
Subject: selftests/bpf: use __bpf_constant_htons in test_prog.c

For some reason, my older GCC (< 4.8) isn't smart enough to optimize the
!__builtin_constant_p() branch in bpf_htons, I see:
  error: implicit declaration of function '__builtin_bswap16'

Let's use __bpf_constant_htons as suggested by Daniel Borkmann.

I tried to use simple htons, but it produces the following:
  test_progs.c:54:17: error: braced-group within expression allowed only
  inside a function
    .eth.h_proto = htons(ETH_P_IP),

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_progs.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 26f1fdf3e2bf..126fc624290d 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -51,10 +51,10 @@ static struct {
 	struct iphdr iph;
 	struct tcphdr tcp;
 } __packed pkt_v4 = {
-	.eth.h_proto = bpf_htons(ETH_P_IP),
+	.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
 	.iph.ihl = 5,
 	.iph.protocol = 6,
-	.iph.tot_len = bpf_htons(MAGIC_BYTES),
+	.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
 	.tcp.urg_ptr = 123,
 };
 
@@ -64,9 +64,9 @@ static struct {
 	struct ipv6hdr iph;
 	struct tcphdr tcp;
 } __packed pkt_v6 = {
-	.eth.h_proto = bpf_htons(ETH_P_IPV6),
+	.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
 	.iph.nexthdr = 6,
-	.iph.payload_len = bpf_htons(MAGIC_BYTES),
+	.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
 	.tcp.urg_ptr = 123,
 };
 
-- 
cgit v1.2.3


From 1b2b234b1318afb3775d4c6624fd5a96558f19df Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guroan@gmail.com>
Date: Mon, 10 Dec 2018 15:43:00 -0800
Subject: bpf: pass struct btf pointer to the map_check_btf() callback

If key_type or value_type are of non-trivial data types
(e.g. structure or typedef), it's not possible to check them without
the additional information, which can't be obtained without a pointer
to the btf structure.

So, let's pass btf pointer to the map_check_btf() callbacks.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h   | 3 +++
 kernel/bpf/arraymap.c | 1 +
 kernel/bpf/lpm_trie.c | 1 +
 kernel/bpf/syscall.c  | 3 ++-
 4 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0c992b86eb2c..e734f163bd0b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -23,6 +23,7 @@ struct bpf_prog;
 struct bpf_map;
 struct sock;
 struct seq_file;
+struct btf;
 struct btf_type;
 
 /* map is generic key/value storage optionally accesible by eBPF programs */
@@ -52,6 +53,7 @@ struct bpf_map_ops {
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
 				  struct seq_file *m);
 	int (*map_check_btf)(const struct bpf_map *map,
+			     const struct btf *btf,
 			     const struct btf_type *key_type,
 			     const struct btf_type *value_type);
 };
@@ -126,6 +128,7 @@ static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
 }
 
 int map_check_no_btf(const struct bpf_map *map,
+		     const struct btf *btf,
 		     const struct btf_type *key_type,
 		     const struct btf_type *value_type);
 
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 24583da9ffd1..25632a75d630 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -382,6 +382,7 @@ static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key,
 }
 
 static int array_map_check_btf(const struct bpf_map *map,
+			       const struct btf *btf,
 			       const struct btf_type *key_type,
 			       const struct btf_type *value_type)
 {
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index bfd4882e1106..abf1002080df 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -728,6 +728,7 @@ free_stack:
 }
 
 static int trie_check_btf(const struct bpf_map *map,
+			  const struct btf *btf,
 			  const struct btf_type *key_type,
 			  const struct btf_type *value_type)
 {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5745c7837621..70fb11106fc2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -456,6 +456,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
 }
 
 int map_check_no_btf(const struct bpf_map *map,
+		     const struct btf *btf,
 		     const struct btf_type *key_type,
 		     const struct btf_type *value_type)
 {
@@ -478,7 +479,7 @@ static int map_check_btf(const struct bpf_map *map, const struct btf *btf,
 		return -EINVAL;
 
 	if (map->ops->map_check_btf)
-		ret = map->ops->map_check_btf(map, key_type, value_type);
+		ret = map->ops->map_check_btf(map, btf, key_type, value_type);
 
 	return ret;
 }
-- 
cgit v1.2.3


From 9a1126b63190e2541dd5d643f4bfeb5a7f493729 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guroan@gmail.com>
Date: Mon, 10 Dec 2018 15:43:01 -0800
Subject: bpf: add bpffs pretty print for cgroup local storage maps

Implement bpffs pretty printing for cgroup local storage maps
(both shared and per-cpu).
Output example (captured for tools/testing/selftests/bpf/netcnt_prog.c):

Shared:
  $ cat /sys/fs/bpf/map_2
  # WARNING!! The output is for debug purpose only
  # WARNING!! The output format will change
  {4294968594,1}: {9999,1039896}

Per-cpu:
  $ cat /sys/fs/bpf/map_1
  # WARNING!! The output is for debug purpose only
  # WARNING!! The output format will change
  {4294968594,1}: {
  	cpu0: {0,0,0,0,0}
  	cpu1: {0,0,0,0,0}
  	cpu2: {1,104,0,0,0}
  	cpu3: {0,0,0,0,0}
  }

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/btf.h        |  1 +
 kernel/bpf/btf.c           | 22 +++++++++++
 kernel/bpf/local_storage.c | 93 +++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 115 insertions(+), 1 deletion(-)

diff --git a/include/linux/btf.h b/include/linux/btf.h
index b98405a56383..a4cf075b89eb 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -47,6 +47,7 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 int btf_get_fd_by_id(u32 id);
 u32 btf_id(const struct btf *btf);
 bool btf_name_offset_valid(const struct btf *btf, u32 offset);
+bool btf_type_is_reg_int(const struct btf_type *t, u32 expected_size);
 
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index bf34933cc413..1545ddfb6fa5 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -514,6 +514,28 @@ static bool btf_type_int_is_regular(const struct btf_type *t)
 	return true;
 }
 
+/*
+ * Check that given type is a regular int and has the expected size.
+ */
+bool btf_type_is_reg_int(const struct btf_type *t, u32 expected_size)
+{
+	u8 nr_bits, nr_bytes;
+	u32 int_data;
+
+	if (!btf_type_is_int(t))
+		return false;
+
+	int_data = btf_type_int(t);
+	nr_bits = BTF_INT_BITS(int_data);
+	nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
+	if (BITS_PER_BYTE_MASKED(nr_bits) ||
+	    BTF_INT_OFFSET(int_data) ||
+	    nr_bytes != expected_size)
+		return false;
+
+	return true;
+}
+
 __printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log,
 					      const char *fmt, ...)
 {
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index b65017dead44..5eca03da0989 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -1,11 +1,13 @@
 //SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf-cgroup.h>
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/bug.h>
 #include <linux/filter.h>
 #include <linux/mm.h>
 #include <linux/rbtree.h>
 #include <linux/slab.h>
+#include <uapi/linux/btf.h>
 
 DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
 
@@ -308,6 +310,94 @@ static int cgroup_storage_delete_elem(struct bpf_map *map, void *key)
 	return -EINVAL;
 }
 
+static int cgroup_storage_check_btf(const struct bpf_map *map,
+				    const struct btf *btf,
+				    const struct btf_type *key_type,
+				    const struct btf_type *value_type)
+{
+	const struct btf_type *t;
+	struct btf_member *m;
+	u32 id, size;
+
+	/* Key is expected to be of struct bpf_cgroup_storage_key type,
+	 * which is:
+	 * struct bpf_cgroup_storage_key {
+	 *	__u64	cgroup_inode_id;
+	 *	__u32	attach_type;
+	 * };
+	 */
+
+	/*
+	 * Key_type must be a structure with two fields.
+	 */
+	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ||
+	    BTF_INFO_VLEN(key_type->info) != 2)
+		return -EINVAL;
+
+	/*
+	 * The first field must be a 64 bit integer at 0 offset.
+	 */
+	m = (struct btf_member *)(key_type + 1);
+	if (m->offset)
+		return -EINVAL;
+	id = m->type;
+	t = btf_type_id_size(btf, &id, NULL);
+	size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, cgroup_inode_id);
+	if (!t || !btf_type_is_reg_int(t, size))
+		return -EINVAL;
+
+	/*
+	 * The second field must be a 32 bit integer at 64 bit offset.
+	 */
+	m++;
+	if (m->offset != offsetof(struct bpf_cgroup_storage_key, attach_type) *
+	    BITS_PER_BYTE)
+		return -EINVAL;
+	id = m->type;
+	t = btf_type_id_size(btf, &id, NULL);
+	size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, attach_type);
+	if (!t || !btf_type_is_reg_int(t, size))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *_key,
+					 struct seq_file *m)
+{
+	enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
+	struct bpf_cgroup_storage_key *key = _key;
+	struct bpf_cgroup_storage *storage;
+	int cpu;
+
+	rcu_read_lock();
+	storage = cgroup_storage_lookup(map_to_storage(map), key, false);
+	if (!storage) {
+		rcu_read_unlock();
+		return;
+	}
+
+	btf_type_seq_show(map->btf, map->btf_key_type_id, key, m);
+	stype = cgroup_storage_type(map);
+	if (stype == BPF_CGROUP_STORAGE_SHARED) {
+		seq_puts(m, ": ");
+		btf_type_seq_show(map->btf, map->btf_value_type_id,
+				  &READ_ONCE(storage->buf)->data[0], m);
+		seq_puts(m, "\n");
+	} else {
+		seq_puts(m, ": {\n");
+		for_each_possible_cpu(cpu) {
+			seq_printf(m, "\tcpu%d: ", cpu);
+			btf_type_seq_show(map->btf, map->btf_value_type_id,
+					  per_cpu_ptr(storage->percpu_buf, cpu),
+					  m);
+			seq_puts(m, "\n");
+		}
+		seq_puts(m, "}\n");
+	}
+	rcu_read_unlock();
+}
+
 const struct bpf_map_ops cgroup_storage_map_ops = {
 	.map_alloc = cgroup_storage_map_alloc,
 	.map_free = cgroup_storage_map_free,
@@ -315,7 +405,8 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
 	.map_lookup_elem = cgroup_storage_lookup_elem,
 	.map_update_elem = cgroup_storage_update_elem,
 	.map_delete_elem = cgroup_storage_delete_elem,
-	.map_check_btf = map_check_no_btf,
+	.map_check_btf = cgroup_storage_check_btf,
+	.map_seq_show_elem = cgroup_storage_seq_show_elem,
 };
 
 int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
-- 
cgit v1.2.3


From 8f9a8a61931197d32ae31960f4179ff60ccbe3db Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guroan@gmail.com>
Date: Mon, 10 Dec 2018 15:43:02 -0800
Subject: selftests/bpf: add btf annotations for cgroup_local_storage maps

Add btf annotations to cgroup local storage maps (per-cpu and shared)
in the network packet counting example.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/netcnt_prog.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/testing/selftests/bpf/netcnt_prog.c b/tools/testing/selftests/bpf/netcnt_prog.c
index 1198abca1360..9f741e69cebe 100644
--- a/tools/testing/selftests/bpf/netcnt_prog.c
+++ b/tools/testing/selftests/bpf/netcnt_prog.c
@@ -16,12 +16,18 @@ struct bpf_map_def SEC("maps") percpu_netcnt = {
 	.value_size = sizeof(struct percpu_net_cnt),
 };
 
+BPF_ANNOTATE_KV_PAIR(percpu_netcnt, struct bpf_cgroup_storage_key,
+		     struct percpu_net_cnt);
+
 struct bpf_map_def SEC("maps") netcnt = {
 	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
 	.key_size = sizeof(struct bpf_cgroup_storage_key),
 	.value_size = sizeof(struct net_cnt),
 };
 
+BPF_ANNOTATE_KV_PAIR(netcnt, struct bpf_cgroup_storage_key,
+		     struct net_cnt);
+
 SEC("cgroup/skb")
 int bpf_nextcnt(struct __sk_buff *skb)
 {
-- 
cgit v1.2.3


From e6652f0ff037d3cad81b82afd4f75c964ef611ec Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Wed, 12 Dec 2018 11:40:07 -0500
Subject: netdevsim: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/bpf.c | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index a1b29173ca1c..172b271c8bd2 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -48,7 +48,7 @@ struct nsim_bpf_bound_map {
 	struct list_head l;
 };
 
-static int nsim_debugfs_bpf_string_read(struct seq_file *file, void *data)
+static int nsim_bpf_string_show(struct seq_file *file, void *data)
 {
 	const char **str = file->private;
 
@@ -57,19 +57,7 @@ static int nsim_debugfs_bpf_string_read(struct seq_file *file, void *data)
 
 	return 0;
 }
-
-static int nsim_debugfs_bpf_string_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, nsim_debugfs_bpf_string_read, inode->i_private);
-}
-
-static const struct file_operations nsim_bpf_string_fops = {
-	.owner = THIS_MODULE,
-	.open = nsim_debugfs_bpf_string_open,
-	.release = single_release,
-	.read = seq_read,
-	.llseek = seq_lseek
-};
+DEFINE_SHOW_ATTRIBUTE(nsim_bpf_string);
 
 static int
 nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn)
-- 
cgit v1.2.3


From 351cbde969230a072cabca9969c68ab04e58e6b3 Mon Sep 17 00:00:00 2001
From: Jonathan Toppins <jtoppins@redhat.com>
Date: Wed, 12 Dec 2018 11:58:51 -0500
Subject: bnxt: remove printing of hwrm message

bnxt_en 0000:19:00.0 (unregistered net_device) (uninitialized): hwrm
req_type 0x190 seq id 0x6 error 0xffff

The message above is commonly seen when a newer driver is used on
hardware with older firmware. The issue is this message means nothing to
anyone except Broadcom. Remove the message to not confuse users as this
message is really not very informative.

Signed-off-by: Jonathan Toppins <jtoppins@redhat.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5d21c14853ac..f4f29939ba72 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6190,7 +6190,8 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 	req.fid = cpu_to_le16(0xffff);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = _hwrm_send_message_silent(bp, &req, sizeof(req),
+				       HWRM_CMD_TIMEOUT);
 	if (rc) {
 		rc = -EIO;
 		goto hwrm_func_resc_qcaps_exit;
-- 
cgit v1.2.3


From 2fd527b72bb6f95dfe8a1902e998cb76390c431e Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 12 Dec 2018 17:02:48 +0000
Subject: net: ndo_bridge_setlink: Add extack

Drivers may not be able to implement a VLAN addition or reconfiguration.
In those cases it's desirable to explain to the user that it was
rejected (and why).

To that end, add extack argument to ndo_bridge_setlink. Adapt all users
to that change.

Following patches will use the new argument in the bridge driver.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 2 +-
 drivers/net/ethernet/emulex/benet/be_main.c   | 2 +-
 drivers/net/ethernet/intel/i40e/i40e_main.c   | 4 +++-
 drivers/net/ethernet/intel/ice/ice_main.c     | 3 ++-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 ++-
 include/linux/netdevice.h                     | 5 +++--
 net/bridge/br_netlink.c                       | 3 ++-
 net/bridge/br_private.h                       | 3 ++-
 net/core/rtnetlink.c                          | 6 ++++--
 9 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index f4f29939ba72..8a2e9cdd38ee 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9618,7 +9618,7 @@ static int bnxt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 }
 
 static int bnxt_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
-			       u16 flags)
+			       u16 flags, struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct nlattr *attr, *br_spec;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 245abf0d19c0..852f5bfe5f6d 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4955,7 +4955,7 @@ fw_exit:
 }
 
 static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
-				 u16 flags)
+				 u16 flags, struct netlink_ext_ack *extack)
 {
 	struct be_adapter *adapter = netdev_priv(dev);
 	struct nlattr *attr, *br_spec;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 6d5b13f69dec..fbb21ac06c98 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11685,6 +11685,7 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
  * @dev: the netdev being configured
  * @nlh: RTNL message
  * @flags: bridge flags
+ * @extack: netlink extended ack
  *
  * Inserts a new hardware bridge if not already created and
  * enables the bridging mode requested (VEB or VEPA). If the
@@ -11697,7 +11698,8 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
  **/
 static int i40e_ndo_bridge_setlink(struct net_device *dev,
 				   struct nlmsghdr *nlh,
-				   u16 flags)
+				   u16 flags,
+				   struct netlink_ext_ack *extack)
 {
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_vsi *vsi = np->vsi;
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index e45e57499d91..f9f0d470412b 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3624,6 +3624,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
  * @dev: the netdev being configured
  * @nlh: RTNL message
  * @flags: bridge setlink flags
+ * @extack: netlink extended ack
  *
  * Sets the bridge mode (VEB/VEPA) of the switch to which the netdev (VSI) is
  * hooked up to. Iterates through the PF VSI list and sets the loopback mode (if
@@ -3632,7 +3633,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
  */
 static int
 ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
-		   u16 __always_unused flags)
+		   u16 __always_unused flags, struct netlink_ext_ack *extack)
 {
 	struct ice_netdev_priv *np = netdev_priv(dev);
 	struct ice_pf *pf = np->vsi->back;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 49a4ea38eb07..f1e40734c975 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9979,7 +9979,8 @@ static int ixgbe_configure_bridge_mode(struct ixgbe_adapter *adapter,
 }
 
 static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
-				    struct nlmsghdr *nlh, u16 flags)
+				    struct nlmsghdr *nlh, u16 flags,
+				    struct netlink_ext_ack *extack)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct nlattr *attr, *br_spec;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fc6ba71513be..36ca5f50f822 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1165,7 +1165,7 @@ struct dev_ifalias {
  *	entries to skb and update idx with the number of entries.
  *
  * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh,
- *			     u16 flags)
+ *			     u16 flags, struct netlink_ext_ack *extack)
  * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq,
  *			     struct net_device *dev, u32 filter_mask,
  *			     int nlflags)
@@ -1390,7 +1390,8 @@ struct net_device_ops {
 
 	int			(*ndo_bridge_setlink)(struct net_device *dev,
 						      struct nlmsghdr *nlh,
-						      u16 flags);
+						      u16 flags,
+						      struct netlink_ext_ack *extack);
 	int			(*ndo_bridge_getlink)(struct sk_buff *skb,
 						      u32 pid, u32 seq,
 						      struct net_device *dev,
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index ff2c10d47529..f9be70b26091 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -850,7 +850,8 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 }
 
 /* Change state and parameters on port. */
-int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
+int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags,
+	       struct netlink_ext_ack *extack)
 {
 	struct net_bridge *br = (struct net_bridge *)netdev_priv(dev);
 	struct nlattr *tb[IFLA_BRPORT_MAX + 1];
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 5719b4d3e466..090dfacdc438 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -1138,7 +1138,8 @@ int br_netlink_init(void);
 void br_netlink_fini(void);
 void br_ifinfo_notify(int event, const struct net_bridge *br,
 		      const struct net_bridge_port *port);
-int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
+int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags,
+	       struct netlink_ext_ack *extack);
 int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
 int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev,
 	       u32 filter_mask, int nlflags);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c9c0407a7ee0..3b6e551f9e69 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4332,7 +4332,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 			goto out;
 		}
 
-		err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh, flags);
+		err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh, flags,
+							     extack);
 		if (err)
 			goto out;
 
@@ -4344,7 +4345,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 			err = -EOPNOTSUPP;
 		else
 			err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh,
-								  flags);
+								  flags,
+								  extack);
 		if (!err) {
 			flags &= ~BRIDGE_FLAGS_SELF;
 
-- 
cgit v1.2.3


From 169327d5850cb80d98d095cfaf8dfbb63d576864 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 12 Dec 2018 17:02:50 +0000
Subject: net: bridge: Propagate extack to switchdev

ndo_bridge_setlink has been updated in the previous patch to have extack
available, and changelink RTNL op has had this argument since the time
extack was added. Propagate both through the bridge driver to eventually
reach br_switchdev_port_vlan_add(), where it will be used by subsequent
patches.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Ivan Vecera <ivecera@redhat.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_if.c        |  2 +-
 net/bridge/br_netlink.c   | 27 +++++++++++++---------
 net/bridge/br_private.h   | 22 ++++++++++--------
 net/bridge/br_switchdev.c |  3 ++-
 net/bridge/br_vlan.c      | 59 ++++++++++++++++++++++++++---------------------
 5 files changed, 65 insertions(+), 48 deletions(-)

diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index d4863f5679ac..3b945d6369c4 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -650,7 +650,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
 	if (br_fdb_insert(br, p, dev->dev_addr, 0))
 		netdev_err(dev, "failed insert local address bridge forwarding table\n");
 
-	err = nbp_vlan_init(p);
+	err = nbp_vlan_init(p, extack);
 	if (err) {
 		netdev_err(dev, "failed to initialize vlan filtering on this port\n");
 		goto err7;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index f9be70b26091..935495b93a99 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -525,7 +525,8 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 }
 
 static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
-			int cmd, struct bridge_vlan_info *vinfo, bool *changed)
+			int cmd, struct bridge_vlan_info *vinfo, bool *changed,
+			struct netlink_ext_ack *extack)
 {
 	bool curr_change;
 	int err = 0;
@@ -537,11 +538,11 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
 			 * per-VLAN entry as well
 			 */
 			err = nbp_vlan_add(p, vinfo->vid, vinfo->flags,
-					   &curr_change);
+					   &curr_change, extack);
 		} else {
 			vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY;
 			err = br_vlan_add(br, vinfo->vid, vinfo->flags,
-					  &curr_change);
+					  &curr_change, extack);
 		}
 		if (curr_change)
 			*changed = true;
@@ -568,7 +569,8 @@ static int br_process_vlan_info(struct net_bridge *br,
 				struct net_bridge_port *p, int cmd,
 				struct bridge_vlan_info *vinfo_curr,
 				struct bridge_vlan_info **vinfo_last,
-				bool *changed)
+				bool *changed,
+				struct netlink_ext_ack *extack)
 {
 	if (!vinfo_curr->vid || vinfo_curr->vid >= VLAN_VID_MASK)
 		return -EINVAL;
@@ -598,7 +600,8 @@ static int br_process_vlan_info(struct net_bridge *br,
 		       sizeof(struct bridge_vlan_info));
 		for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) {
 			tmp_vinfo.vid = v;
-			err = br_vlan_info(br, p, cmd, &tmp_vinfo, changed);
+			err = br_vlan_info(br, p, cmd, &tmp_vinfo, changed,
+					   extack);
 			if (err)
 				break;
 		}
@@ -607,13 +610,14 @@ static int br_process_vlan_info(struct net_bridge *br,
 		return err;
 	}
 
-	return br_vlan_info(br, p, cmd, vinfo_curr, changed);
+	return br_vlan_info(br, p, cmd, vinfo_curr, changed, extack);
 }
 
 static int br_afspec(struct net_bridge *br,
 		     struct net_bridge_port *p,
 		     struct nlattr *af_spec,
-		     int cmd, bool *changed)
+		     int cmd, bool *changed,
+		     struct netlink_ext_ack *extack)
 {
 	struct bridge_vlan_info *vinfo_curr = NULL;
 	struct bridge_vlan_info *vinfo_last = NULL;
@@ -643,7 +647,8 @@ static int br_afspec(struct net_bridge *br,
 				return -EINVAL;
 			vinfo_curr = nla_data(attr);
 			err = br_process_vlan_info(br, p, cmd, vinfo_curr,
-						   &vinfo_last, changed);
+						   &vinfo_last, changed,
+						   extack);
 			if (err)
 				return err;
 			break;
@@ -898,7 +903,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags,
 	}
 
 	if (afspec)
-		err = br_afspec(br, p, afspec, RTM_SETLINK, &changed);
+		err = br_afspec(br, p, afspec, RTM_SETLINK, &changed, extack);
 
 	if (changed)
 		br_ifinfo_notify(RTM_NEWLINK, br, p);
@@ -924,7 +929,7 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
 	if (!p && !(dev->priv_flags & IFF_EBRIDGE))
 		return -EINVAL;
 
-	err = br_afspec(br, p, afspec, RTM_DELLINK, &changed);
+	err = br_afspec(br, p, afspec, RTM_DELLINK, &changed, NULL);
 	if (changed)
 		/* Send RTM_NEWLINK because userspace
 		 * expects RTM_NEWLINK for vlan dels
@@ -1106,7 +1111,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	if (data[IFLA_BR_VLAN_DEFAULT_PVID]) {
 		__u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]);
 
-		err = __br_vlan_set_default_pvid(br, defpvid);
+		err = __br_vlan_set_default_pvid(br, defpvid, extack);
 		if (err)
 			return err;
 	}
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 090dfacdc438..ff3dfb2a78b8 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -868,7 +868,7 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
 			       struct net_bridge_vlan_group *vg,
 			       struct sk_buff *skb);
 int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags,
-		bool *changed);
+		bool *changed, struct netlink_ext_ack *extack);
 int br_vlan_delete(struct net_bridge *br, u16 vid);
 void br_vlan_flush(struct net_bridge *br);
 struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid);
@@ -881,12 +881,13 @@ int br_vlan_set_stats(struct net_bridge *br, unsigned long val);
 int br_vlan_set_stats_per_port(struct net_bridge *br, unsigned long val);
 int br_vlan_init(struct net_bridge *br);
 int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val);
-int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid);
+int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid,
+			       struct netlink_ext_ack *extack);
 int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
-		 bool *changed);
+		 bool *changed, struct netlink_ext_ack *extack);
 int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
 void nbp_vlan_flush(struct net_bridge_port *port);
-int nbp_vlan_init(struct net_bridge_port *port);
+int nbp_vlan_init(struct net_bridge_port *port, struct netlink_ext_ack *extack);
 int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask);
 void br_vlan_get_stats(const struct net_bridge_vlan *v,
 		       struct br_vlan_stats *stats);
@@ -971,7 +972,7 @@ static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
 }
 
 static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags,
-			      bool *changed)
+			      bool *changed, struct netlink_ext_ack *extack)
 {
 	*changed = false;
 	return -EOPNOTSUPP;
@@ -996,7 +997,7 @@ static inline int br_vlan_init(struct net_bridge *br)
 }
 
 static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
-			       bool *changed)
+			       bool *changed, struct netlink_ext_ack *extack)
 {
 	*changed = false;
 	return -EOPNOTSUPP;
@@ -1017,7 +1018,8 @@ static inline struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group
 	return NULL;
 }
 
-static inline int nbp_vlan_init(struct net_bridge_port *port)
+static inline int nbp_vlan_init(struct net_bridge_port *port,
+				struct netlink_ext_ack *extack)
 {
 	return 0;
 }
@@ -1174,7 +1176,8 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p,
 			       unsigned long mask);
 void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb,
 			     int type);
-int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags);
+int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags,
+			       struct netlink_ext_ack *extack);
 int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid);
 
 static inline void br_switchdev_frame_unmark(struct sk_buff *skb)
@@ -1206,7 +1209,8 @@ static inline int br_switchdev_set_port_flag(struct net_bridge_port *p,
 }
 
 static inline int br_switchdev_port_vlan_add(struct net_device *dev,
-					     u16 vid, u16 flags)
+					     u16 vid, u16 flags,
+					     struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index b993df770675..99ba32177b31 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -140,7 +140,8 @@ br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
 	}
 }
 
-int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags)
+int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags,
+			       struct netlink_ext_ack *extack)
 {
 	struct switchdev_obj_port_vlan v = {
 		.obj.orig_dev = dev,
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 48f50d7ac624..4a2f31157ef5 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -80,14 +80,14 @@ static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
 }
 
 static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br,
-			  u16 vid, u16 flags)
+			  u16 vid, u16 flags, struct netlink_ext_ack *extack)
 {
 	int err;
 
 	/* Try switchdev op first. In case it is not supported, fallback to
 	 * 8021q add.
 	 */
-	err = br_switchdev_port_vlan_add(dev, vid, flags);
+	err = br_switchdev_port_vlan_add(dev, vid, flags, extack);
 	if (err == -EOPNOTSUPP)
 		return vlan_vid_add(dev, br->vlan_proto, vid);
 	return err;
@@ -139,7 +139,9 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br,
 /* Returns a master vlan, if it didn't exist it gets created. In all cases a
  * a reference is taken to the master vlan before returning.
  */
-static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid)
+static struct net_bridge_vlan *
+br_vlan_get_master(struct net_bridge *br, u16 vid,
+		   struct netlink_ext_ack *extack)
 {
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_vlan *masterv;
@@ -150,7 +152,7 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid
 		bool changed;
 
 		/* missing global ctx, create it now */
-		if (br_vlan_add(br, vid, 0, &changed))
+		if (br_vlan_add(br, vid, 0, &changed, extack))
 			return NULL;
 		masterv = br_vlan_find(vg, vid);
 		if (WARN_ON(!masterv))
@@ -214,7 +216,8 @@ static void nbp_vlan_rcu_free(struct rcu_head *rcu)
  * 4. same as 3 but with both master and brentry flags set so the entry
  *    will be used for filtering in both the port and the bridge
  */
-static int __vlan_add(struct net_bridge_vlan *v, u16 flags)
+static int __vlan_add(struct net_bridge_vlan *v, u16 flags,
+		      struct netlink_ext_ack *extack)
 {
 	struct net_bridge_vlan *masterv = NULL;
 	struct net_bridge_port *p = NULL;
@@ -239,7 +242,7 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags)
 		 * This ensures tagged traffic enters the bridge when
 		 * promiscuous mode is disabled by br_manage_promisc().
 		 */
-		err = __vlan_vid_add(dev, br, v->vid, flags);
+		err = __vlan_vid_add(dev, br, v->vid, flags, extack);
 		if (err)
 			goto out;
 
@@ -249,12 +252,12 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags)
 
 			err = br_vlan_add(br, v->vid,
 					  flags | BRIDGE_VLAN_INFO_BRENTRY,
-					  &changed);
+					  &changed, extack);
 			if (err)
 				goto out_filt;
 		}
 
-		masterv = br_vlan_get_master(br, v->vid);
+		masterv = br_vlan_get_master(br, v->vid, extack);
 		if (!masterv)
 			goto out_filt;
 		v->brvlan = masterv;
@@ -269,7 +272,7 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags)
 			v->stats = masterv->stats;
 		}
 	} else {
-		err = br_switchdev_port_vlan_add(dev, v->vid, flags);
+		err = br_switchdev_port_vlan_add(dev, v->vid, flags, extack);
 		if (err && err != -EOPNOTSUPP)
 			goto out;
 	}
@@ -591,11 +594,12 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
 static int br_vlan_add_existing(struct net_bridge *br,
 				struct net_bridge_vlan_group *vg,
 				struct net_bridge_vlan *vlan,
-				u16 flags, bool *changed)
+				u16 flags, bool *changed,
+				struct netlink_ext_ack *extack)
 {
 	int err;
 
-	err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags);
+	err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags, extack);
 	if (err && err != -EOPNOTSUPP)
 		return err;
 
@@ -634,7 +638,8 @@ err_flags:
  * Must be called with vid in range from 1 to 4094 inclusive.
  * changed must be true only if the vlan was created or updated
  */
-int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed)
+int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed,
+		struct netlink_ext_ack *extack)
 {
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_vlan *vlan;
@@ -646,7 +651,8 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed)
 	vg = br_vlan_group(br);
 	vlan = br_vlan_find(vg, vid);
 	if (vlan)
-		return br_vlan_add_existing(br, vg, vlan, flags, changed);
+		return br_vlan_add_existing(br, vg, vlan, flags, changed,
+					    extack);
 
 	vlan = kzalloc(sizeof(*vlan), GFP_KERNEL);
 	if (!vlan)
@@ -663,7 +669,7 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed)
 	vlan->br = br;
 	if (flags & BRIDGE_VLAN_INFO_BRENTRY)
 		refcount_set(&vlan->refcnt, 1);
-	ret = __vlan_add(vlan, flags);
+	ret = __vlan_add(vlan, flags, extack);
 	if (ret) {
 		free_percpu(vlan->stats);
 		kfree(vlan);
@@ -914,7 +920,8 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br)
 	br->default_pvid = 0;
 }
 
-int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
+int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid,
+			       struct netlink_ext_ack *extack)
 {
 	const struct net_bridge_vlan *pvent;
 	struct net_bridge_vlan_group *vg;
@@ -946,7 +953,7 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
 				  BRIDGE_VLAN_INFO_PVID |
 				  BRIDGE_VLAN_INFO_UNTAGGED |
 				  BRIDGE_VLAN_INFO_BRENTRY,
-				  &vlchange);
+				  &vlchange, extack);
 		if (err)
 			goto out;
 		br_vlan_delete(br, old_pvid);
@@ -966,7 +973,7 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
 		err = nbp_vlan_add(p, pvid,
 				   BRIDGE_VLAN_INFO_PVID |
 				   BRIDGE_VLAN_INFO_UNTAGGED,
-				   &vlchange);
+				   &vlchange, extack);
 		if (err)
 			goto err_port;
 		nbp_vlan_delete(p, old_pvid);
@@ -988,7 +995,7 @@ err_port:
 			nbp_vlan_add(p, old_pvid,
 				     BRIDGE_VLAN_INFO_PVID |
 				     BRIDGE_VLAN_INFO_UNTAGGED,
-				     &vlchange);
+				     &vlchange, NULL);
 		nbp_vlan_delete(p, pvid);
 	}
 
@@ -998,7 +1005,7 @@ err_port:
 				    BRIDGE_VLAN_INFO_PVID |
 				    BRIDGE_VLAN_INFO_UNTAGGED |
 				    BRIDGE_VLAN_INFO_BRENTRY,
-				    &vlchange);
+				    &vlchange, NULL);
 		br_vlan_delete(br, pvid);
 	}
 	goto out;
@@ -1021,7 +1028,7 @@ int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val)
 		err = -EPERM;
 		goto out;
 	}
-	err = __br_vlan_set_default_pvid(br, pvid);
+	err = __br_vlan_set_default_pvid(br, pvid, NULL);
 out:
 	return err;
 }
@@ -1047,7 +1054,7 @@ int br_vlan_init(struct net_bridge *br)
 	rcu_assign_pointer(br->vlgrp, vg);
 	ret = br_vlan_add(br, 1,
 			  BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED |
-			  BRIDGE_VLAN_INFO_BRENTRY, &changed);
+			  BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL);
 	if (ret)
 		goto err_vlan_add;
 
@@ -1064,7 +1071,7 @@ err_rhtbl:
 	goto out;
 }
 
-int nbp_vlan_init(struct net_bridge_port *p)
+int nbp_vlan_init(struct net_bridge_port *p, struct netlink_ext_ack *extack)
 {
 	struct switchdev_attr attr = {
 		.orig_dev = p->br->dev,
@@ -1097,7 +1104,7 @@ int nbp_vlan_init(struct net_bridge_port *p)
 		ret = nbp_vlan_add(p, p->br->default_pvid,
 				   BRIDGE_VLAN_INFO_PVID |
 				   BRIDGE_VLAN_INFO_UNTAGGED,
-				   &changed);
+				   &changed, extack);
 		if (ret)
 			goto err_vlan_add;
 	}
@@ -1122,7 +1129,7 @@ err_vlan_enabled:
  * changed must be true only if the vlan was created or updated
  */
 int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
-		 bool *changed)
+		 bool *changed, struct netlink_ext_ack *extack)
 {
 	struct net_bridge_vlan *vlan;
 	int ret;
@@ -1133,7 +1140,7 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
 	vlan = br_vlan_find(nbp_vlan_group(port), vid);
 	if (vlan) {
 		/* Pass the flags to the hardware bridge */
-		ret = br_switchdev_port_vlan_add(port->dev, vid, flags);
+		ret = br_switchdev_port_vlan_add(port->dev, vid, flags, extack);
 		if (ret && ret != -EOPNOTSUPP)
 			return ret;
 		*changed = __vlan_add_flags(vlan, flags);
@@ -1147,7 +1154,7 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
 
 	vlan->vid = vid;
 	vlan->port = port;
-	ret = __vlan_add(vlan, flags);
+	ret = __vlan_add(vlan, flags, extack);
 	if (ret)
 		kfree(vlan);
 	else
-- 
cgit v1.2.3


From 69b7320e14e6e8c7a77fa5803cecc86434a1162d Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 12 Dec 2018 17:02:52 +0000
Subject: net: switchdev: Add extack argument to switchdev_port_obj_add()

After the previous patch, bridge driver has extack argument available to
pass to switchdev. Therefore extend switchdev_port_obj_add() with this
argument, updating all callers, and passing the argument through to
switchdev_port_obj_notify().

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h   |  6 ++++--
 net/bridge/br_mdb.c       |  4 ++--
 net/bridge/br_switchdev.c |  2 +-
 net/switchdev/switchdev.c | 19 +++++++++++--------
 4 files changed, 18 insertions(+), 13 deletions(-)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 866b6d148b77..69016305ad58 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -180,7 +180,8 @@ int switchdev_port_attr_get(struct net_device *dev,
 int switchdev_port_attr_set(struct net_device *dev,
 			    const struct switchdev_attr *attr);
 int switchdev_port_obj_add(struct net_device *dev,
-			   const struct switchdev_obj *obj);
+			   const struct switchdev_obj *obj,
+			   struct netlink_ext_ack *extack);
 int switchdev_port_obj_del(struct net_device *dev,
 			   const struct switchdev_obj *obj);
 
@@ -233,7 +234,8 @@ static inline int switchdev_port_attr_set(struct net_device *dev,
 }
 
 static inline int switchdev_port_obj_add(struct net_device *dev,
-					 const struct switchdev_obj *obj)
+					 const struct switchdev_obj *obj,
+					 struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 79d4c9d253e0..f69c8d91dc81 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -331,7 +331,7 @@ static void br_mdb_switchdev_host_port(struct net_device *dev,
 	mdb.obj.orig_dev = dev;
 	switch (type) {
 	case RTM_NEWMDB:
-		switchdev_port_obj_add(lower_dev, &mdb.obj);
+		switchdev_port_obj_add(lower_dev, &mdb.obj, NULL);
 		break;
 	case RTM_DELMDB:
 		switchdev_port_obj_del(lower_dev, &mdb.obj);
@@ -381,7 +381,7 @@ static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p,
 			__mdb_entry_to_br_ip(entry, &complete_info->ip);
 			mdb.obj.complete_priv = complete_info;
 			mdb.obj.complete = br_mdb_complete;
-			if (switchdev_port_obj_add(port_dev, &mdb.obj))
+			if (switchdev_port_obj_add(port_dev, &mdb.obj, NULL))
 				kfree(complete_info);
 		}
 	} else if (p && port_dev && type == RTM_DELMDB) {
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index 99ba32177b31..035ff59d9cbd 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -151,7 +151,7 @@ int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags,
 		.vid_end = vid,
 	};
 
-	return switchdev_port_obj_add(dev, &v.obj);
+	return switchdev_port_obj_add(dev, &v.obj, extack);
 }
 
 int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid)
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index fe23fac4dc4b..cb20669bf6ce 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -356,7 +356,8 @@ static size_t switchdev_obj_size(const struct switchdev_obj *obj)
 static int switchdev_port_obj_notify(enum switchdev_notifier_type nt,
 				     struct net_device *dev,
 				     const struct switchdev_obj *obj,
-				     struct switchdev_trans *trans)
+				     struct switchdev_trans *trans,
+				     struct netlink_ext_ack *extack)
 {
 	int rc;
 	int err;
@@ -379,7 +380,8 @@ static int switchdev_port_obj_notify(enum switchdev_notifier_type nt,
 }
 
 static int switchdev_port_obj_add_now(struct net_device *dev,
-				      const struct switchdev_obj *obj)
+				      const struct switchdev_obj *obj,
+				      struct netlink_ext_ack *extack)
 {
 	struct switchdev_trans trans;
 	int err;
@@ -397,7 +399,7 @@ static int switchdev_port_obj_add_now(struct net_device *dev,
 
 	trans.ph_prepare = true;
 	err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD,
-					dev, obj, &trans);
+					dev, obj, &trans, extack);
 	if (err) {
 		/* Prepare phase failed: abort the transaction.  Any
 		 * resources reserved in the prepare phase are
@@ -417,7 +419,7 @@ static int switchdev_port_obj_add_now(struct net_device *dev,
 
 	trans.ph_prepare = false;
 	err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD,
-					dev, obj, &trans);
+					dev, obj, &trans, extack);
 	WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id);
 	switchdev_trans_items_warn_destroy(dev, &trans);
 
@@ -430,7 +432,7 @@ static void switchdev_port_obj_add_deferred(struct net_device *dev,
 	const struct switchdev_obj *obj = data;
 	int err;
 
-	err = switchdev_port_obj_add_now(dev, obj);
+	err = switchdev_port_obj_add_now(dev, obj, NULL);
 	if (err && err != -EOPNOTSUPP)
 		netdev_err(dev, "failed (err=%d) to add object (id=%d)\n",
 			   err, obj->id);
@@ -460,12 +462,13 @@ static int switchdev_port_obj_add_defer(struct net_device *dev,
  *	in case SWITCHDEV_F_DEFER flag is not set.
  */
 int switchdev_port_obj_add(struct net_device *dev,
-			   const struct switchdev_obj *obj)
+			   const struct switchdev_obj *obj,
+			   struct netlink_ext_ack *extack)
 {
 	if (obj->flags & SWITCHDEV_F_DEFER)
 		return switchdev_port_obj_add_defer(dev, obj);
 	ASSERT_RTNL();
-	return switchdev_port_obj_add_now(dev, obj);
+	return switchdev_port_obj_add_now(dev, obj, extack);
 }
 EXPORT_SYMBOL_GPL(switchdev_port_obj_add);
 
@@ -473,7 +476,7 @@ static int switchdev_port_obj_del_now(struct net_device *dev,
 				      const struct switchdev_obj *obj)
 {
 	return switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_DEL,
-					 dev, obj, NULL);
+					 dev, obj, NULL, NULL);
 }
 
 static void switchdev_port_obj_del_deferred(struct net_device *dev,
-- 
cgit v1.2.3


From 479c86dc551c9720765ed19433990eae6a1f899f Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 12 Dec 2018 17:02:54 +0000
Subject: net: switchdev: Add extack to struct switchdev_notifier_info

In order to pass extack to the drivers that need it, add an extack field
to struct switchdev_notifier_info, and an extack argument to the
function call_switchdev_blocking_notifiers(). Also add a helper function
switchdev_notifier_info_to_extack().

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c       |  1 +
 include/net/switchdev.h   | 13 +++++++++++--
 net/switchdev/switchdev.c |  7 +++++--
 3 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index b56ef684ecac..49d4b5854c62 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -364,6 +364,7 @@ static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan,
 			    struct switchdev_notifier_vxlan_fdb_info *fdb_info)
 {
 	fdb_info->info.dev = vxlan->dev;
+	fdb_info->info.extack = NULL;
 	fdb_info->remote_ip = rd->remote_ip;
 	fdb_info->remote_port = rd->remote_port;
 	fdb_info->remote_vni = rd->remote_vni;
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 69016305ad58..4facfa6775e8 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -149,6 +149,7 @@ enum switchdev_notifier_type {
 
 struct switchdev_notifier_info {
 	struct net_device *dev;
+	struct netlink_ext_ack *extack;
 };
 
 struct switchdev_notifier_fdb_info {
@@ -172,6 +173,12 @@ switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info)
 	return info->dev;
 }
 
+static inline struct netlink_ext_ack *
+switchdev_notifier_info_to_extack(const struct switchdev_notifier_info *info)
+{
+	return info->extack;
+}
+
 #ifdef CONFIG_NET_SWITCHDEV
 
 void switchdev_deferred_process(void);
@@ -193,7 +200,8 @@ int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
 int register_switchdev_blocking_notifier(struct notifier_block *nb);
 int unregister_switchdev_blocking_notifier(struct notifier_block *nb);
 int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev,
-				      struct switchdev_notifier_info *info);
+				      struct switchdev_notifier_info *info,
+				      struct netlink_ext_ack *extack);
 
 void switchdev_port_fwd_mark_set(struct net_device *dev,
 				 struct net_device *group_dev,
@@ -278,7 +286,8 @@ unregister_switchdev_blocking_notifier(struct notifier_block *nb)
 static inline int
 call_switchdev_blocking_notifiers(unsigned long val,
 				  struct net_device *dev,
-				  struct switchdev_notifier_info *info)
+				  struct switchdev_notifier_info *info,
+				  struct netlink_ext_ack *extack)
 {
 	return NOTIFY_DONE;
 }
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index cb20669bf6ce..aa84acfb6632 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -368,7 +368,7 @@ static int switchdev_port_obj_notify(enum switchdev_notifier_type nt,
 		.handled = false,
 	};
 
-	rc = call_switchdev_blocking_notifiers(nt, dev, &obj_info.info);
+	rc = call_switchdev_blocking_notifiers(nt, dev, &obj_info.info, extack);
 	err = notifier_to_errno(rc);
 	if (err) {
 		WARN_ON(!obj_info.handled);
@@ -559,6 +559,7 @@ int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
 			     struct switchdev_notifier_info *info)
 {
 	info->dev = dev;
+	info->extack = NULL;
 	return atomic_notifier_call_chain(&switchdev_notif_chain, val, info);
 }
 EXPORT_SYMBOL_GPL(call_switchdev_notifiers);
@@ -580,9 +581,11 @@ int unregister_switchdev_blocking_notifier(struct notifier_block *nb)
 EXPORT_SYMBOL_GPL(unregister_switchdev_blocking_notifier);
 
 int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev,
-				      struct switchdev_notifier_info *info)
+				      struct switchdev_notifier_info *info,
+				      struct netlink_ext_ack *extack)
 {
 	info->dev = dev;
+	info->extack = extack;
 	return blocking_notifier_call_chain(&switchdev_blocking_notif_chain,
 					    val, info);
 }
-- 
cgit v1.2.3


From 6921351359395a6c6ac72cd275a8393f399cecc7 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 12 Dec 2018 17:02:56 +0000
Subject: net: switchdev: Add extack to switchdev_handle_port_obj_add()
 callback

Drivers use switchdev_handle_port_obj_add() to handle recursive descent
through lower devices. Change this function prototype to take add_cb
that itself takes an extack argument. Decode extack from
switchdev_notifier_port_obj_info and pass it to add_cb.

Update mlxsw and ocelot drivers which use this helper.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c |  3 ++-
 drivers/net/ethernet/mscc/ocelot.c                       |  3 ++-
 include/net/switchdev.h                                  |  6 ++++--
 net/switchdev/switchdev.c                                | 12 +++++++++---
 4 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 5ad1fcebf788..4b9292289256 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1777,7 +1777,8 @@ static void mlxsw_sp_span_respin_schedule(struct mlxsw_sp *mlxsw_sp)
 
 static int mlxsw_sp_port_obj_add(struct net_device *dev,
 				 const struct switchdev_obj *obj,
-				 struct switchdev_trans *trans)
+				 struct switchdev_trans *trans,
+				 struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	const struct switchdev_obj_port_vlan *vlan;
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 7f8da8873a96..ea3eec263875 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1293,7 +1293,8 @@ static int ocelot_port_obj_del_mdb(struct net_device *dev,
 
 static int ocelot_port_obj_add(struct net_device *dev,
 			       const struct switchdev_obj *obj,
-			       struct switchdev_trans *trans)
+			       struct switchdev_trans *trans,
+			       struct netlink_ext_ack *extack)
 {
 	int ret = 0;
 
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 4facfa6775e8..a7fdab5ee6c3 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -215,7 +215,8 @@ int switchdev_handle_port_obj_add(struct net_device *dev,
 			bool (*check_cb)(const struct net_device *dev),
 			int (*add_cb)(struct net_device *dev,
 				      const struct switchdev_obj *obj,
-				      struct switchdev_trans *trans));
+				      struct switchdev_trans *trans,
+				      struct netlink_ext_ack *extack));
 int switchdev_handle_port_obj_del(struct net_device *dev,
 			struct switchdev_notifier_port_obj_info *port_obj_info,
 			bool (*check_cb)(const struct net_device *dev),
@@ -304,7 +305,8 @@ switchdev_handle_port_obj_add(struct net_device *dev,
 			bool (*check_cb)(const struct net_device *dev),
 			int (*add_cb)(struct net_device *dev,
 				      const struct switchdev_obj *obj,
-				      struct switchdev_trans *trans))
+				      struct switchdev_trans *trans,
+				      struct netlink_ext_ack *extack))
 {
 	return 0;
 }
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index aa84acfb6632..5df9d1138ac9 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -616,16 +616,21 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev,
 			bool (*check_cb)(const struct net_device *dev),
 			int (*add_cb)(struct net_device *dev,
 				      const struct switchdev_obj *obj,
-				      struct switchdev_trans *trans))
+				      struct switchdev_trans *trans,
+				      struct netlink_ext_ack *extack))
 {
+	struct netlink_ext_ack *extack;
 	struct net_device *lower_dev;
 	struct list_head *iter;
 	int err = -EOPNOTSUPP;
 
+	extack = switchdev_notifier_info_to_extack(&port_obj_info->info);
+
 	if (check_cb(dev)) {
 		/* This flag is only checked if the return value is success. */
 		port_obj_info->handled = true;
-		return add_cb(dev, port_obj_info->obj, port_obj_info->trans);
+		return add_cb(dev, port_obj_info->obj, port_obj_info->trans,
+			      extack);
 	}
 
 	/* Switch ports might be stacked under e.g. a LAG. Ignore the
@@ -650,7 +655,8 @@ int switchdev_handle_port_obj_add(struct net_device *dev,
 			bool (*check_cb)(const struct net_device *dev),
 			int (*add_cb)(struct net_device *dev,
 				      const struct switchdev_obj *obj,
-				      struct switchdev_trans *trans))
+				      struct switchdev_trans *trans,
+				      struct netlink_ext_ack *extack))
 {
 	int err;
 
-- 
cgit v1.2.3


From 0a5a2aee6f38073b6ae5d946bc668e965f29f3b0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 12 Dec 2018 17:03:00 +0000
Subject: mlxsw: spectrum_switchdev: Propagate extack on VXLAN VLAN events

Now that VLAN port object addition notifications carry an extack,
propagate it from mlxsw_sp_switchdev_vxlan_vlans_add() through
mlxsw_sp_switchdev_vxlan_vlan_add() to
mlxsw_sp_bridge_8021q_vxlan_join().

This code path is used when a VLAN is added to a VXLAN netdevice that
cannot be offloaded.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 4b9292289256..906dfded3098 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -3205,7 +3205,8 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_bridge_device *bridge_device,
 				  const struct net_device *vxlan_dev, u16 vid,
 				  bool flag_untagged, bool flag_pvid,
-				  struct switchdev_trans *trans)
+				  struct switchdev_trans *trans,
+				  struct netlink_ext_ack *extack)
 {
 	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
 	__be32 vni = vxlan->cfg.vni;
@@ -3237,7 +3238,7 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
 		if (!flag_untagged || !flag_pvid)
 			return 0;
 		return mlxsw_sp_bridge_8021q_vxlan_join(bridge_device,
-							vxlan_dev, vid, NULL);
+							vxlan_dev, vid, extack);
 	}
 
 	/* Second case: FID is associated with the VNI and the VLAN associated
@@ -3277,7 +3278,7 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 
 	err = mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, vxlan_dev, vid,
-					       NULL);
+					       extack);
 	if (err)
 		goto err_vxlan_join;
 
@@ -3326,10 +3327,12 @@ mlxsw_sp_switchdev_vxlan_vlans_add(struct net_device *vxlan_dev,
 	bool flag_pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
 	struct switchdev_trans *trans = port_obj_info->trans;
 	struct mlxsw_sp_bridge_device *bridge_device;
+	struct netlink_ext_ack *extack;
 	struct mlxsw_sp *mlxsw_sp;
 	struct net_device *br_dev;
 	u16 vid;
 
+	extack = switchdev_notifier_info_to_extack(&port_obj_info->info);
 	br_dev = netdev_master_upper_dev_get(vxlan_dev);
 	if (!br_dev)
 		return 0;
@@ -3353,7 +3356,8 @@ mlxsw_sp_switchdev_vxlan_vlans_add(struct net_device *vxlan_dev,
 		err = mlxsw_sp_switchdev_vxlan_vlan_add(mlxsw_sp, bridge_device,
 							vxlan_dev, vid,
 							flag_untagged,
-							flag_pvid, trans);
+							flag_pvid, trans,
+							extack);
 		if (err)
 			return err;
 	}
-- 
cgit v1.2.3


From 7357eb3d4b3e33e3a08fb5916d6ae0dbb389a96a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 12 Dec 2018 17:03:02 +0000
Subject: mlxsw: spectrum_switchdev: Propagate extack on port VLAN events

After switchdev_handle_port_obj_add() was extended in a preceding patch,
mlxsw_sp_port_obj_add() now takes an extack argument. Propagate it
further by extending a callee chain from mlxsw_sp_port_vlans_add(), via
mlxsw_sp_bridge_port_vlan_add() via mlxsw_sp_port_vlan_bridge_join() via
mlxsw_sp_port_vlan_fid_join() to mlxsw_sp_bridge_ops.fid_get, adding an
extack argument for each of them.

This code path is used when a VLAN is added to a port netdevice if there
already is an unoffloadable VXLAN device with that VLAN mapped.

mlxsw_sp_bridge_8021d_port_join() is updated to obey the new interfaces
changed by the abovementioned code, propagating extack ultimately from
NETDEV_CHANGEUPPER events.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 38 +++++++++++++---------
 1 file changed, 23 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 906dfded3098..627efe7a6eef 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -89,7 +89,7 @@ struct mlxsw_sp_bridge_ops {
 			  struct netlink_ext_ack *extack);
 	struct mlxsw_sp_fid *
 		(*fid_get)(struct mlxsw_sp_bridge_device *bridge_device,
-			   u16 vid);
+			   u16 vid, struct netlink_ext_ack *extack);
 	struct mlxsw_sp_fid *
 		(*fid_lookup)(struct mlxsw_sp_bridge_device *bridge_device,
 			      u16 vid);
@@ -933,7 +933,8 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
 
 static int
 mlxsw_sp_port_vlan_fid_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
-			    struct mlxsw_sp_bridge_port *bridge_port)
+			    struct mlxsw_sp_bridge_port *bridge_port,
+			    struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp_bridge_device *bridge_device;
@@ -943,7 +944,7 @@ mlxsw_sp_port_vlan_fid_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 	int err;
 
 	bridge_device = bridge_port->bridge_device;
-	fid = bridge_device->ops->fid_get(bridge_device, vid);
+	fid = bridge_device->ops->fid_get(bridge_device, vid, extack);
 	if (IS_ERR(fid))
 		return PTR_ERR(fid);
 
@@ -1011,7 +1012,8 @@ mlxsw_sp_port_pvid_determine(const struct mlxsw_sp_port *mlxsw_sp_port,
 
 static int
 mlxsw_sp_port_vlan_bridge_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
-			       struct mlxsw_sp_bridge_port *bridge_port)
+			       struct mlxsw_sp_bridge_port *bridge_port,
+			       struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp_bridge_vlan *bridge_vlan;
@@ -1024,7 +1026,8 @@ mlxsw_sp_port_vlan_bridge_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 		return 0;
 	}
 
-	err = mlxsw_sp_port_vlan_fid_join(mlxsw_sp_port_vlan, bridge_port);
+	err = mlxsw_sp_port_vlan_fid_join(mlxsw_sp_port_vlan, bridge_port,
+					  extack);
 	if (err)
 		return err;
 
@@ -1101,7 +1104,8 @@ mlxsw_sp_port_vlan_bridge_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 static int
 mlxsw_sp_bridge_port_vlan_add(struct mlxsw_sp_port *mlxsw_sp_port,
 			      struct mlxsw_sp_bridge_port *bridge_port,
-			      u16 vid, bool is_untagged, bool is_pvid)
+			      u16 vid, bool is_untagged, bool is_pvid,
+			      struct netlink_ext_ack *extack)
 {
 	u16 pvid = mlxsw_sp_port_pvid_determine(mlxsw_sp_port, vid, is_pvid);
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
@@ -1121,7 +1125,8 @@ mlxsw_sp_bridge_port_vlan_add(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (err)
 		goto err_port_pvid_set;
 
-	err = mlxsw_sp_port_vlan_bridge_join(mlxsw_sp_port_vlan, bridge_port);
+	err = mlxsw_sp_port_vlan_bridge_join(mlxsw_sp_port_vlan, bridge_port,
+					     extack);
 	if (err)
 		goto err_port_vlan_bridge_join;
 
@@ -1171,7 +1176,8 @@ mlxsw_sp_br_ban_rif_pvid_change(struct mlxsw_sp *mlxsw_sp,
 
 static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 				   const struct switchdev_obj_port_vlan *vlan,
-				   struct switchdev_trans *trans)
+				   struct switchdev_trans *trans,
+				   struct netlink_ext_ack *extack)
 {
 	bool flag_untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
 	bool flag_pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
@@ -1208,7 +1214,7 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 
 		err = mlxsw_sp_bridge_port_vlan_add(mlxsw_sp_port, bridge_port,
 						    vid, flag_untagged,
-						    flag_pvid);
+						    flag_pvid, extack);
 		if (err)
 			return err;
 	}
@@ -1787,7 +1793,8 @@ static int mlxsw_sp_port_obj_add(struct net_device *dev,
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
 		vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
-		err = mlxsw_sp_port_vlans_add(mlxsw_sp_port, vlan, trans);
+		err = mlxsw_sp_port_vlans_add(mlxsw_sp_port, vlan, trans,
+					      extack);
 
 		if (switchdev_trans_ph_prepare(trans)) {
 			/* The event is emitted before the changes are actually
@@ -2087,7 +2094,7 @@ mlxsw_sp_bridge_8021q_vxlan_dev_find(struct net_device *br_dev, u16 vid)
 
 static struct mlxsw_sp_fid *
 mlxsw_sp_bridge_8021q_fid_get(struct mlxsw_sp_bridge_device *bridge_device,
-			      u16 vid)
+			      u16 vid, struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
 	struct net_device *vxlan_dev;
@@ -2113,7 +2120,7 @@ mlxsw_sp_bridge_8021q_fid_get(struct mlxsw_sp_bridge_device *bridge_device,
 		return fid;
 
 	err = mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, vxlan_dev, vid,
-					       NULL);
+					       extack);
 	if (err)
 		goto err_vxlan_join;
 
@@ -2190,7 +2197,8 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 	if (mlxsw_sp_port_vlan->fid)
 		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
 
-	return mlxsw_sp_port_vlan_bridge_join(mlxsw_sp_port_vlan, bridge_port);
+	return mlxsw_sp_port_vlan_bridge_join(mlxsw_sp_port_vlan, bridge_port,
+					      extack);
 }
 
 static void
@@ -2253,7 +2261,7 @@ err_vni_exists:
 
 static struct mlxsw_sp_fid *
 mlxsw_sp_bridge_8021d_fid_get(struct mlxsw_sp_bridge_device *bridge_device,
-			      u16 vid)
+			      u16 vid, struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
 	struct net_device *vxlan_dev;
@@ -2275,7 +2283,7 @@ mlxsw_sp_bridge_8021d_fid_get(struct mlxsw_sp_bridge_device *bridge_device,
 		return fid;
 
 	err = mlxsw_sp_bridge_8021d_vxlan_join(bridge_device, vxlan_dev, 0,
-					       NULL);
+					       extack);
 	if (err)
 		goto err_vxlan_join;
 
-- 
cgit v1.2.3


From b498dc7d29bd6b4a108451671f81d712fba008ec Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 12 Dec 2018 17:03:04 +0000
Subject: selftests: mlxsw: extack: Test VLAN add on a VXLAN device

Test mapping a VLAN at a VXLAN device that can't be offloaded.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/drivers/net/mlxsw/extack.sh  | 31 ++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/extack.sh b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
index 101a5508bdfd..d9e02624c70b 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/extack.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
@@ -7,6 +7,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding
 
 ALL_TESTS="
 	netdev_pre_up_test
+	vxlan_vlan_add_test
 "
 NUM_NETIFS=2
 source $lib_dir/lib.sh
@@ -74,6 +75,36 @@ netdev_pre_up_test()
 	ip link del dev br1
 }
 
+vxlan_vlan_add_test()
+{
+	RET=0
+
+	ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0
+
+	# Unsupported configuration: mlxsw demands VXLAN with "noudpcsum".
+	ip link add name vx1 up type vxlan id 1000 \
+		local 192.0.2.17 remote 192.0.2.18 \
+		dstport 4789 tos inherit ttl 100
+
+	ip link set dev vx1 master br1
+	check_err $?
+
+	bridge vlan add dev vx1 vid 1
+	check_err $?
+
+	ip link set dev $swp1 master br1
+	check_err $?
+
+	bridge vlan add dev vx1 vid 1 pvid untagged 2>&1 >/dev/null \
+		| grep -q mlxsw_spectrum
+	check_err $?
+
+	log_test "extack - map VLAN at VXLAN device"
+
+	ip link del dev vx1
+	ip link del dev br1
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
cgit v1.2.3


From 06a2fc8f1498dc978e856ef5ded6667b476a3b5b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 12 Dec 2018 17:03:06 +0000
Subject: selftests: mlxsw: extack: Test VLAN add on a port device

Test mapping a VLAN at a port device such that on the same VLAN, there
already is an unoffloadable VXLAN device.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/drivers/net/mlxsw/extack.sh  | 30 ++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/extack.sh b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
index d9e02624c70b..d72d8488a3b2 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/extack.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
@@ -8,6 +8,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding
 ALL_TESTS="
 	netdev_pre_up_test
 	vxlan_vlan_add_test
+	port_vlan_add_test
 "
 NUM_NETIFS=2
 source $lib_dir/lib.sh
@@ -105,6 +106,35 @@ vxlan_vlan_add_test()
 	ip link del dev br1
 }
 
+port_vlan_add_test()
+{
+	RET=0
+
+	ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0
+
+	# Unsupported configuration: mlxsw demands VXLAN with "noudpcsum".
+	ip link add name vx1 up type vxlan id 1000 \
+		local 192.0.2.17 remote 192.0.2.18 \
+		dstport 4789 tos inherit ttl 100
+
+	ip link set dev $swp1 master br1
+	check_err $?
+
+	bridge vlan del dev $swp1 vid 1
+
+	ip link set dev vx1 master br1
+	check_err $?
+
+	bridge vlan add dev $swp1 vid 1 pvid untagged 2>&1 >/dev/null \
+		| grep -q mlxsw_spectrum
+	check_err $?
+
+	log_test "extack - map VLAN at port"
+
+	ip link del dev vx1
+	ip link del dev br1
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
cgit v1.2.3


From 186599f89ea57e9b444dcb0793723b9148770161 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 12 Dec 2018 08:03:38 +0000
Subject: net/mlx5: Remove duplicated include from eswitch.c

Remove duplicated include.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index e6a9b19d8626..4f9dd0d4a081 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -39,7 +39,6 @@
 #include "lib/eq.h"
 #include "eswitch.h"
 #include "fs_core.h"
-#include "lib/eq.h"
 
 #define UPLINK_VPORT 0xFFFF
 
-- 
cgit v1.2.3


From c784a28b025a22f8c791e14096fb7079236739c0 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 12 Dec 2018 08:33:53 +0000
Subject: net/mlx5e: Remove set but not used variable 'upriv'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/mellanox/mlx5/core/en_rep.c: In function 'mlx5e_vport_rep_load':
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c:1490:21: warning:
 variable 'upriv' set but not used [-Wunused-but-set-variable]

drivers/net/ethernet/mellanox/mlx5/core/en_rep.c: In function 'mlx5e_vport_rep_unload':
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c:1557:21: warning:
 variable 'upriv' set but not used [-Wunused-but-set-variable]

It not used any more since commit ef381359e3a8 ("net/mlx5e: Replace egdev with
indirect block notifications"). Also remove unused variable 'uplink_rpriv'
after this change.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 85e51bd4147f..e5230049612f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1484,10 +1484,8 @@ mlx5e_nic_rep_unload(struct mlx5_eswitch_rep *rep)
 static int
 mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
-	struct mlx5e_rep_priv *uplink_rpriv;
 	struct mlx5e_rep_priv *rpriv;
 	struct net_device *netdev;
-	struct mlx5e_priv *upriv;
 	int nch, err;
 
 	rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL);
@@ -1522,9 +1520,6 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 		goto err_detach_netdev;
 	}
 
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(dev->priv.eswitch, REP_ETH);
-	upriv = netdev_priv(uplink_rpriv->netdev);
-
 	err = register_netdev(netdev);
 	if (err) {
 		pr_warn("Failed to register representor netdev for vport %d\n",
@@ -1552,14 +1547,9 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
 	struct net_device *netdev = rpriv->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_rep_priv *uplink_rpriv;
 	void *ppriv = priv->ppriv;
-	struct mlx5e_priv *upriv;
 
 	unregister_netdev(netdev);
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch,
-						    REP_ETH);
-	upriv = netdev_priv(uplink_rpriv->netdev);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_detach_netdev(priv);
 	mlx5e_destroy_netdev(priv);
-- 
cgit v1.2.3


From 43d4b2971810edded68098b996e917ed768d3dbb Mon Sep 17 00:00:00 2001
From: Biao Huang <biao.huang@mediatek.com>
Date: Thu, 13 Dec 2018 10:41:37 +0800
Subject: net-next: stmmac: dwmac-mediatek: add module license info

Add MODULE_LICENSE info to fix this:
WARNING: modpost: missing MODULE_LICENSE() in drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.o

Signed-off-by: Biao Huang <biao.huang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index b5db85d298e7..e400cbdc3419 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -5,6 +5,7 @@
 #include <linux/bitfield.h>
 #include <linux/io.h>
 #include <linux/mfd/syscon.h>
+#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_net.h>
@@ -406,3 +407,7 @@ static struct platform_driver mediatek_dwmac_driver = {
 	},
 };
 module_platform_driver(mediatek_dwmac_driver);
+
+MODULE_AUTHOR("Biao Huang <biao.huang@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek DWMAC specific glue layer");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From afc7c944ef828b431c564818f8cbc80f3e16f0d6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 12 Dec 2018 19:59:24 -0800
Subject: tools: bpftool: fix SPDX format in headers

Documentation/process/license-rules.rst sayeth:

2. Style:

The SPDX license identifier is added in form of a comment.  The comment
style depends on the file type::

   C source: // SPDX-License-Identifier: <SPDX License Expression>
   C header: /* SPDX-License-Identifier: <SPDX License Expression> */

Headers should use C comment style.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Sean Young <sean@mess.org>
Acked-by: Jiri Benc <jbenc@redhat.com>
Acked-by: David Calavera <david.calavera@gmail.com>
Acked-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Joe Stringer <joe@wand.net.nz>
Acked-by: David Ahern <dsahern@gmail.com>
Acked-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Acked-by: Petar Penkov <ppenkov@stanford.edu>
Acked-by: Sandipan Das <sandipan@linux.ibm.com>
Acked-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Taeung Song <treeze.taeung@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
CC: okash.khawaja@gmail.com
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/cfg.h            | 2 +-
 tools/bpf/bpftool/netlink_dumper.h | 2 +-
 tools/bpf/bpftool/xlated_dumper.h  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/bpf/bpftool/cfg.h b/tools/bpf/bpftool/cfg.h
index 2cc9bd990b13..493e2389d3cc 100644
--- a/tools/bpf/bpftool/cfg.h
+++ b/tools/bpf/bpftool/cfg.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
 /*
  * Copyright (C) 2018 Netronome Systems, Inc.
  *
diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
index e3516b586a34..fb1b1a685f7e 100644
--- a/tools/bpf/bpftool/netlink_dumper.h
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (C) 2018 Facebook
 
 #ifndef _NETLINK_DUMPER_H_
diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h
index a24f89df8cb2..f950ab2dafbf 100644
--- a/tools/bpf/bpftool/xlated_dumper.h
+++ b/tools/bpf/bpftool/xlated_dumper.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
 /*
  * Copyright (C) 2018 Netronome Systems, Inc.
  *
-- 
cgit v1.2.3


From 02ff58dcf70ad7d11b01523dc404166ed11021da Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 12 Dec 2018 19:59:25 -0800
Subject: tools: bpftool: replace Netronome boilerplate with SPDX license
 headers

Replace the repeated license text with SDPX identifiers.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Sean Young <sean@mess.org>
Acked-by: Jiri Benc <jbenc@redhat.com>
Acked-by: David Calavera <david.calavera@gmail.com>
Acked-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Joe Stringer <joe@wand.net.nz>
Acked-by: David Ahern <dsahern@gmail.com>
Acked-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Acked-by: Petar Penkov <ppenkov@stanford.edu>
Acked-by: Sandipan Das <sandipan@linux.ibm.com>
Acked-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Taeung Song <treeze.taeung@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
CC: okash.khawaja@gmail.com
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/bash-completion/bpftool | 31 +-------------------------
 tools/bpf/bpftool/cfg.c                   | 36 +------------------------------
 tools/bpf/bpftool/cfg.h                   | 36 +------------------------------
 tools/bpf/bpftool/common.c                | 34 ++---------------------------
 tools/bpf/bpftool/main.c                  | 34 ++---------------------------
 tools/bpf/bpftool/main.h                  | 34 ++---------------------------
 tools/bpf/bpftool/map.c                   | 34 ++---------------------------
 tools/bpf/bpftool/prog.c                  | 34 ++---------------------------
 tools/bpf/bpftool/xlated_dumper.c         | 36 +------------------------------
 tools/bpf/bpftool/xlated_dumper.h         | 36 +------------------------------
 10 files changed, 15 insertions(+), 330 deletions(-)

diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index a57febd6abb1..e4e4fab1b8c7 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -1,37 +1,8 @@
 # bpftool(8) bash completion                               -*- shell-script -*-
 #
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 # Copyright (C) 2017-2018 Netronome Systems, Inc.
 #
-# This software is dual licensed under the GNU General License
-# Version 2, June 1991 as shown in the file COPYING in the top-level
-# directory of this source tree or the BSD 2-Clause License provided
-# below.  You have the option to license this software under the
-# complete terms of either license.
-#
-# The BSD 2-Clause License:
-#
-#     Redistribution and use in source and binary forms, with or
-#     without modification, are permitted provided that the following
-#     conditions are met:
-#
-#      1. Redistributions of source code must retain the above
-#         copyright notice, this list of conditions and the following
-#         disclaimer.
-#
-#      2. Redistributions in binary form must reproduce the above
-#         copyright notice, this list of conditions and the following
-#         disclaimer in the documentation and/or other materials
-#         provided with the distribution.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-#
 # Author: Quentin Monnet <quentin.monnet@netronome.com>
 
 # Takes a list of words in argument; each one of them is added to COMPREPLY if
diff --git a/tools/bpf/bpftool/cfg.c b/tools/bpf/bpftool/cfg.c
index f30b3a4a840b..31f0db41513f 100644
--- a/tools/bpf/bpftool/cfg.c
+++ b/tools/bpf/bpftool/cfg.c
@@ -1,39 +1,5 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-/*
- * Copyright (C) 2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* Copyright (C) 2018 Netronome Systems, Inc. */
 
 #include <linux/list.h>
 #include <stdlib.h>
diff --git a/tools/bpf/bpftool/cfg.h b/tools/bpf/bpftool/cfg.h
index 493e2389d3cc..e144257ea6d2 100644
--- a/tools/bpf/bpftool/cfg.h
+++ b/tools/bpf/bpftool/cfg.h
@@ -1,39 +1,5 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
-/*
- * Copyright (C) 2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* Copyright (C) 2018 Netronome Systems, Inc. */
 
 #ifndef __BPF_TOOL_CFG_H
 #define __BPF_TOOL_CFG_H
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 172d3761d9ab..99e4027dde75 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -1,35 +1,5 @@
-/*
- * Copyright (C) 2017-2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
 
 #include <ctype.h>
 #include <errno.h>
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 5c4c1cd5a7ba..9e657e7d5172 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -1,35 +1,5 @@
-/*
- * Copyright (C) 2017-2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
 
 #include <ctype.h>
 #include <errno.h>
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 0b37599f8cda..d2beb88f0e2e 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -1,35 +1,5 @@
-/*
- * Copyright (C) 2017-2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
 
 #ifndef __BPF_TOOL_H
 #define __BPF_TOOL_H
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 8469ea6cf1c8..2037e3dc864b 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -1,35 +1,5 @@
-/*
- * Copyright (C) 2017-2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
 
 #include <assert.h>
 #include <errno.h>
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index b73b4e473948..eddf7fba41c6 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -1,35 +1,5 @@
-/*
- * Copyright (C) 2017-2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
 
 #define _GNU_SOURCE
 #include <errno.h>
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index aef628dcccb6..640ffe86a655 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -1,39 +1,5 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-/*
- * Copyright (C) 2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* Copyright (C) 2018 Netronome Systems, Inc. */
 
 #define _GNU_SOURCE
 #include <stdarg.h>
diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h
index f950ab2dafbf..54847e174273 100644
--- a/tools/bpf/bpftool/xlated_dumper.h
+++ b/tools/bpf/bpftool/xlated_dumper.h
@@ -1,39 +1,5 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
-/*
- * Copyright (C) 2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* Copyright (C) 2018 Netronome Systems, Inc. */
 
 #ifndef __BPF_TOOL_XLATED_DUMPER_H
 #define __BPF_TOOL_XLATED_DUMPER_H
-- 
cgit v1.2.3


From 907b22365115fb86196152909915108d7c8243d1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 12 Dec 2018 19:59:26 -0800
Subject: tools: bpftool: dual license all files

Currently bpftool contains a mix of GPL-only and GPL or BSD2
licensed files.  Make sure all files are dual licensed under
GPLv2 and BSD-2-Clause.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Sean Young <sean@mess.org>
Acked-by: Jiri Benc <jbenc@redhat.com>
Acked-by: David Calavera <david.calavera@gmail.com>
Acked-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Joe Stringer <joe@wand.net.nz>
Acked-by: David Ahern <dsahern@gmail.com>
Acked-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Acked-by: Petar Penkov <ppenkov@stanford.edu>
Acked-by: Sandipan Das <sandipan@linux.ibm.com>
Acked-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Taeung Song <treeze.taeung@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
CC: okash.khawaja@gmail.com
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/btf_dumper.c     | 2 +-
 tools/bpf/bpftool/cgroup.c         | 2 +-
 tools/bpf/bpftool/jit_disasm.c     | 1 +
 tools/bpf/bpftool/json_writer.c    | 1 +
 tools/bpf/bpftool/json_writer.h    | 1 +
 tools/bpf/bpftool/map_perf_ring.c  | 2 +-
 tools/bpf/bpftool/net.c            | 2 +-
 tools/bpf/bpftool/netlink_dumper.c | 2 +-
 tools/bpf/bpftool/netlink_dumper.h | 2 +-
 tools/bpf/bpftool/perf.c           | 2 +-
 10 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index 2392ccdc918f..5cdb2ef8b6f1 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
 #include <ctype.h>
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index ee7a9765c6b3..4b5c8da2a7c0 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (C) 2017 Facebook
 // Author: Roman Gushchin <guro@fb.com>
 
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index f381f8628ce9..3ef3093560ba 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /*
  * Based on:
  *
diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c
index c6eef76322ae..a07d17918725 100644
--- a/tools/bpf/bpftool/json_writer.c
+++ b/tools/bpf/bpftool/json_writer.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /*
  * Simple streaming JSON writer
  *
diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h
index 0fa2fb1b6351..c1ab51aed99c 100644
--- a/tools/bpf/bpftool/json_writer.h
+++ b/tools/bpf/bpftool/json_writer.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
 /*
  * Simple streaming JSON writer
  *
diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c
index bdaf4062e26e..0507dfaf7a8f 100644
--- a/tools/bpf/bpftool/map_perf_ring.c
+++ b/tools/bpf/bpftool/map_perf_ring.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0-only
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (C) 2018 Netronome Systems, Inc. */
 /* This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index d441bb7035ca..db0e7de49d49 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (C) 2018 Facebook
 
 #define _GNU_SOURCE
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
index 4e9f4531269f..550a0f537eed 100644
--- a/tools/bpf/bpftool/netlink_dumper.c
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (C) 2018 Facebook
 
 #include <stdlib.h>
diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
index fb1b1a685f7e..774af6c62ef5 100644
--- a/tools/bpf/bpftool/netlink_dumper.h
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0+ */
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
 // Copyright (C) 2018 Facebook
 
 #ifndef _NETLINK_DUMPER_H_
diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c
index b76b77dcfd1f..f2a545e667c4 100644
--- a/tools/bpf/bpftool/perf.c
+++ b/tools/bpf/bpftool/perf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (C) 2018 Facebook
 // Author: Yonghong Song <yhs@fb.com>
 
-- 
cgit v1.2.3


From 9e794163a69c103633fefb10a3879408d4e4e2c8 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 12 Dec 2018 10:18:21 -0800
Subject: bpf: Remove bpf_dump_raw_ok() check for func_info and line_info

The func_info and line_info have the bpf insn offset but
they do not contain kernel address.  They will still be useful
for the userspace tool to annotate the xlated insn.

This patch removes the bpf_dump_raw_ok() guard for the
func_info and line_info during bpf_prog_get_info_by_fd().

The guard stays for jited_line_info which contains the kernel
address.

Although this bpf_dump_raw_ok() guard behavior has started since
the earlier func_info patch series, I marked the Fixes tag to the
latest line_info patch series which contains both func_info and
line_info and this patch is fixing for both of them.

Fixes: c454a46b5efd ("bpf: Add bpf_line_info support")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/syscall.c | 32 ++++++++++++--------------------
 1 file changed, 12 insertions(+), 20 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 70fb11106fc2..b7c585838c72 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2272,33 +2272,25 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	ulen = info.nr_func_info;
 	info.nr_func_info = prog->aux->func_info_cnt;
 	if (info.nr_func_info && ulen) {
-		if (bpf_dump_raw_ok()) {
-			char __user *user_finfo;
+		char __user *user_finfo;
 
-			user_finfo = u64_to_user_ptr(info.func_info);
-			ulen = min_t(u32, info.nr_func_info, ulen);
-			if (copy_to_user(user_finfo, prog->aux->func_info,
-					 info.func_info_rec_size * ulen))
-				return -EFAULT;
-		} else {
-			info.func_info = 0;
-		}
+		user_finfo = u64_to_user_ptr(info.func_info);
+		ulen = min_t(u32, info.nr_func_info, ulen);
+		if (copy_to_user(user_finfo, prog->aux->func_info,
+				 info.func_info_rec_size * ulen))
+			return -EFAULT;
 	}
 
 	ulen = info.nr_line_info;
 	info.nr_line_info = prog->aux->nr_linfo;
 	if (info.nr_line_info && ulen) {
-		if (bpf_dump_raw_ok()) {
-			__u8 __user *user_linfo;
+		__u8 __user *user_linfo;
 
-			user_linfo = u64_to_user_ptr(info.line_info);
-			ulen = min_t(u32, info.nr_line_info, ulen);
-			if (copy_to_user(user_linfo, prog->aux->linfo,
-					 info.line_info_rec_size * ulen))
-				return -EFAULT;
-		} else {
-			info.line_info = 0;
-		}
+		user_linfo = u64_to_user_ptr(info.line_info);
+		ulen = min_t(u32, info.nr_line_info, ulen);
+		if (copy_to_user(user_linfo, prog->aux->linfo,
+				 info.line_info_rec_size * ulen))
+			return -EFAULT;
 	}
 
 	ulen = info.nr_jited_line_info;
-- 
cgit v1.2.3


From 177e77169b0b71587c74382d5f2207a16da34790 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 12 Dec 2018 10:18:22 -0800
Subject: bpf: Remove !func_info and !line_info check from test_btf and bpftool

kernel can provide the func_info and line_info even
it fails the btf_dump_raw_ok() test because they don't contain
kernel address.  This patch removes the corresponding '== 0'
test.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/prog.c               | 7 -------
 tools/lib/bpf/bpf_prog_linfo.c         | 6 +-----
 tools/testing/selftests/bpf/test_btf.c | 7 -------
 3 files changed, 1 insertion(+), 19 deletions(-)

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index eddf7fba41c6..ee51279be9c7 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -596,13 +596,6 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
-	if (func_info && !info.func_info) {
-		/* kernel.kptr_restrict is set.  No func_info available. */
-		free(func_info);
-		func_info = NULL;
-		nr_finfo = 0;
-	}
-
 	if (linfo && info.nr_line_info != nr_linfo) {
 		p_err("incorrect nr_line_info %u vs. expected %u",
 		      info.nr_line_info, nr_linfo);
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index addd6e9971cc..6978314ea7f6 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -107,11 +107,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 
 	nr_linfo = info->nr_line_info;
 
-	/*
-	 * Test !info->line_info because the kernel may NULL
-	 * the ptr if kernel.kptr_restrict is set.
-	 */
-	if (!nr_linfo || !info->line_info)
+	if (!nr_linfo)
 		return NULL;
 
 	/*
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index f570e0a39959..8478316aaf9a 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -3948,12 +3948,6 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 		goto done;
 	}
 
-	if (CHECK(!info.func_info,
-		  "info.func_info == 0. kernel.kptr_restrict is set?")) {
-		err = -1;
-		goto done;
-	}
-
 	finfo = func_info;
 	for (i = 0; i < test->func_info_cnt; i++) {
 		if (CHECK(finfo->type_id != test->func_info[i][1],
@@ -4077,7 +4071,6 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 	 * Other fields are not the concern of this test.
 	 */
 	if (CHECK(err == -1 ||
-		  !info.line_info ||
 		  info.nr_line_info != cnt ||
 		  (jited_cnt && !info.jited_line_info) ||
 		  info.nr_jited_line_info != jited_cnt ||
-- 
cgit v1.2.3


From c872bdb38febb4c31ece3599c52cf1f833b89f4e Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Wed, 12 Dec 2018 09:37:46 -0800
Subject: bpf: include sub program tags in bpf_prog_info

Changes v2 -> v3:
1. remove check for bpf_dump_raw_ok().

Changes v1 -> v2:
1. Fix error path as Martin suggested.

This patch adds nr_prog_tags and prog_tags to bpf_prog_info. This is a
reliable way for user space to get tags of all sub programs. Before this
patch, user space need to find sub program tags via kallsyms.

This feature will be used in BPF introspection, where user space queries
information about BPF programs via sys_bpf.

Signed-off-by: Song Liu <songliubraving@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h |  2 ++
 kernel/bpf/syscall.c     | 22 ++++++++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index aa582cd5bfcf..e7d57e89f25f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2717,6 +2717,8 @@ struct bpf_prog_info {
 	__u32 nr_jited_line_info;
 	__u32 line_info_rec_size;
 	__u32 jited_line_info_rec_size;
+	__u32 nr_prog_tags;
+	__aligned_u64 prog_tags;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b7c585838c72..7f1410d6fbe9 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2315,6 +2315,28 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		}
 	}
 
+	ulen = info.nr_prog_tags;
+	info.nr_prog_tags = prog->aux->func_cnt ? : 1;
+	if (ulen) {
+		__u8 __user (*user_prog_tags)[BPF_TAG_SIZE];
+		u32 i;
+
+		user_prog_tags = u64_to_user_ptr(info.prog_tags);
+		ulen = min_t(u32, info.nr_prog_tags, ulen);
+		if (prog->aux->func_cnt) {
+			for (i = 0; i < ulen; i++) {
+				if (copy_to_user(user_prog_tags[i],
+						 prog->aux->func[i]->tag,
+						 BPF_TAG_SIZE))
+					return -EFAULT;
+			}
+		} else {
+			if (copy_to_user(user_prog_tags[0],
+					 prog->tag, BPF_TAG_SIZE))
+				return -EFAULT;
+		}
+	}
+
 done:
 	if (copy_to_user(uinfo, &info, info_len) ||
 	    put_user(info_len, &uattr->info.info_len))
-- 
cgit v1.2.3


From eb896a69a0cf3afa69f0983470cc41f9cb04c017 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Wed, 12 Dec 2018 09:37:47 -0800
Subject: bpf: sync tools/include/uapi/linux/bpf.h

Sync bpf.h for nr_prog_tags and prog_tags.

Signed-off-by: Song Liu <songliubraving@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index aa582cd5bfcf..e7d57e89f25f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2717,6 +2717,8 @@ struct bpf_prog_info {
 	__u32 nr_jited_line_info;
 	__u32 line_info_rec_size;
 	__u32 jited_line_info_rec_size;
+	__u32 nr_prog_tags;
+	__aligned_u64 prog_tags;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
-- 
cgit v1.2.3


From 1dcd9429212b98bea87fc6ec92fb50bf5953eb47 Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Thu, 29 Nov 2018 18:25:19 +0800
Subject: mwifiex: fix potential NULL dereference and use after free

There are two defects: (1) passing a NULL bss to
mwifiex_save_hidden_ssid_channels will result in NULL dereference,
(2) using bss after dropping the reference to it via cfg80211_put_bss.
To fix them, the patch moves the buggy code to the branch that bss is
not NULL and puts it before cfg80211_put_bss.

Signed-off-by: Pan Bian <bianpan2016@163.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/mwifiex/scan.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index 8e483b0bc3b1..935778ec9a1b 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -1882,15 +1882,17 @@ mwifiex_parse_single_response_buf(struct mwifiex_private *priv, u8 **bss_info,
 					    ETH_ALEN))
 					mwifiex_update_curr_bss_params(priv,
 								       bss);
-				cfg80211_put_bss(priv->wdev.wiphy, bss);
-			}
 
-			if ((chan->flags & IEEE80211_CHAN_RADAR) ||
-			    (chan->flags & IEEE80211_CHAN_NO_IR)) {
-				mwifiex_dbg(adapter, INFO,
-					    "radar or passive channel %d\n",
-					    channel);
-				mwifiex_save_hidden_ssid_channels(priv, bss);
+				if ((chan->flags & IEEE80211_CHAN_RADAR) ||
+				    (chan->flags & IEEE80211_CHAN_NO_IR)) {
+					mwifiex_dbg(adapter, INFO,
+						    "radar or passive channel %d\n",
+						    channel);
+					mwifiex_save_hidden_ssid_channels(priv,
+									  bss);
+				}
+
+				cfg80211_put_bss(priv->wdev.wiphy, bss);
 			}
 		}
 	} else {
-- 
cgit v1.2.3


From 4cb777c64e030778c569f605398d7604d8aabc0f Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 3 Dec 2018 14:26:55 -0800
Subject: mwifiex: debugfs: correct histogram spacing, formatting

Currently, snippets of this file look like:

rx rates (in Mbps): 0=1M   1=2M2=5.5M  3=11M   4=6M   5=9M  6=12M
7=18M  8=24M  9=36M  10=48M  11=54M12-27=MCS0-15(BW20) 28-43=MCS0-15(BW40)
44-53=MCS0-9(VHT:BW20)54-63=MCS0-9(VHT:BW40)64-73=MCS0-9(VHT:BW80)
...
noise_flr[--96dBm] = 22
noise_flr[--95dBm] = 149
noise_flr[--94dBm] = 9
noise_flr[--93dBm] = 2

We're missing some spaces, and we're adding a minus sign ('-') on values
that are already negative signed integers.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/mwifiex/debugfs.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c
index cce70252fd96..cbe4493b3266 100644
--- a/drivers/net/wireless/marvell/mwifiex/debugfs.c
+++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c
@@ -273,15 +273,13 @@ mwifiex_histogram_read(struct file *file, char __user *ubuf,
 		     "total samples = %d\n",
 		     atomic_read(&phist_data->num_samples));
 
-	p += sprintf(p, "rx rates (in Mbps): 0=1M   1=2M");
-	p += sprintf(p, "2=5.5M  3=11M   4=6M   5=9M  6=12M\n");
-	p += sprintf(p, "7=18M  8=24M  9=36M  10=48M  11=54M");
-	p += sprintf(p, "12-27=MCS0-15(BW20) 28-43=MCS0-15(BW40)\n");
+	p += sprintf(p,
+		     "rx rates (in Mbps): 0=1M   1=2M 2=5.5M  3=11M   4=6M   5=9M  6=12M\n"
+		     "7=18M  8=24M  9=36M  10=48M  11=54M 12-27=MCS0-15(BW20) 28-43=MCS0-15(BW40)\n");
 
 	if (ISSUPP_11ACENABLED(priv->adapter->fw_cap_info)) {
-		p += sprintf(p, "44-53=MCS0-9(VHT:BW20)");
-		p += sprintf(p, "54-63=MCS0-9(VHT:BW40)");
-		p += sprintf(p, "64-73=MCS0-9(VHT:BW80)\n\n");
+		p += sprintf(p,
+			     "44-53=MCS0-9(VHT:BW20) 54-63=MCS0-9(VHT:BW40) 64-73=MCS0-9(VHT:BW80)\n\n");
 	} else {
 		p += sprintf(p, "\n");
 	}
@@ -310,7 +308,7 @@ mwifiex_histogram_read(struct file *file, char __user *ubuf,
 	for (i = 0; i < MWIFIEX_MAX_NOISE_FLR; i++) {
 		value = atomic_read(&phist_data->noise_flr[i]);
 		if (value)
-			p += sprintf(p, "noise_flr[-%02ddBm] = %d\n",
+			p += sprintf(p, "noise_flr[%02ddBm] = %d\n",
 				(int)(i-128), value);
 	}
 	for (i = 0; i < MWIFIEX_MAX_SIG_STRENGTH; i++) {
-- 
cgit v1.2.3


From a256707fbd4b1d153d0152c502aa5b87837aeb6c Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Thu, 6 Dec 2018 16:12:48 -0800
Subject: mwifiex: refactor mwifiex_parse_htinfo() for reuse

This function converts some firmware-specific parameters into cfg80211
'rate_info' structures. It currently assumes it's dealing only with TX
bitrate, but the RX bitrate looks to be the same, so refactor this
function to be reusable.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c | 36 +++++++++++++------------
 1 file changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index adc88433faa8..02b80ea232a7 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -1275,27 +1275,27 @@ mwifiex_cfg80211_change_virtual_intf(struct wiphy *wiphy,
 }
 
 static void
-mwifiex_parse_htinfo(struct mwifiex_private *priv, u8 tx_htinfo,
+mwifiex_parse_htinfo(struct mwifiex_private *priv, u8 rateinfo, u8 htinfo,
 		     struct rate_info *rate)
 {
 	struct mwifiex_adapter *adapter = priv->adapter;
 
 	if (adapter->is_hw_11ac_capable) {
 		/* bit[1-0]: 00=LG 01=HT 10=VHT */
-		if (tx_htinfo & BIT(0)) {
+		if (htinfo & BIT(0)) {
 			/* HT */
-			rate->mcs = priv->tx_rate;
+			rate->mcs = rateinfo;
 			rate->flags |= RATE_INFO_FLAGS_MCS;
 		}
-		if (tx_htinfo & BIT(1)) {
+		if (htinfo & BIT(1)) {
 			/* VHT */
-			rate->mcs = priv->tx_rate & 0x0F;
+			rate->mcs = rateinfo & 0x0F;
 			rate->flags |= RATE_INFO_FLAGS_VHT_MCS;
 		}
 
-		if (tx_htinfo & (BIT(1) | BIT(0))) {
+		if (htinfo & (BIT(1) | BIT(0))) {
 			/* HT or VHT */
-			switch (tx_htinfo & (BIT(3) | BIT(2))) {
+			switch (htinfo & (BIT(3) | BIT(2))) {
 			case 0:
 				rate->bw = RATE_INFO_BW_20;
 				break;
@@ -1310,26 +1310,26 @@ mwifiex_parse_htinfo(struct mwifiex_private *priv, u8 tx_htinfo,
 				break;
 			}
 
-			if (tx_htinfo & BIT(4))
+			if (htinfo & BIT(4))
 				rate->flags |= RATE_INFO_FLAGS_SHORT_GI;
 
-			if ((priv->tx_rate >> 4) == 1)
+			if ((rateinfo >> 4) == 1)
 				rate->nss = 2;
 			else
 				rate->nss = 1;
 		}
 	} else {
 		/*
-		 * Bit 0 in tx_htinfo indicates that current Tx rate
-		 * is 11n rate. Valid MCS index values for us are 0 to 15.
+		 * Bit 0 in htinfo indicates that current rate is 11n. Valid
+		 * MCS index values for us are 0 to 15.
 		 */
-		if ((tx_htinfo & BIT(0)) && (priv->tx_rate < 16)) {
-			rate->mcs = priv->tx_rate;
+		if ((htinfo & BIT(0)) && (rateinfo < 16)) {
+			rate->mcs = rateinfo;
 			rate->flags |= RATE_INFO_FLAGS_MCS;
 			rate->bw = RATE_INFO_BW_20;
-			if (tx_htinfo & BIT(1))
+			if (htinfo & BIT(1))
 				rate->bw = RATE_INFO_BW_40;
-			if (tx_htinfo & BIT(2))
+			if (htinfo & BIT(2))
 				rate->flags |= RATE_INFO_FLAGS_SHORT_GI;
 		}
 	}
@@ -1375,7 +1375,8 @@ mwifiex_dump_station_info(struct mwifiex_private *priv,
 		sinfo->tx_packets = node->stats.tx_packets;
 		sinfo->tx_failed = node->stats.tx_failed;
 
-		mwifiex_parse_htinfo(priv, node->stats.last_tx_htinfo,
+		mwifiex_parse_htinfo(priv, priv->tx_rate,
+				     node->stats.last_tx_htinfo,
 				     &sinfo->txrate);
 		sinfo->txrate.legacy = node->stats.last_tx_rate * 5;
 
@@ -1401,7 +1402,8 @@ mwifiex_dump_station_info(struct mwifiex_private *priv,
 			 HostCmd_ACT_GEN_GET, DTIM_PERIOD_I,
 			 &priv->dtim_period, true);
 
-	mwifiex_parse_htinfo(priv, priv->tx_htinfo, &sinfo->txrate);
+	mwifiex_parse_htinfo(priv, priv->tx_rate, priv->tx_htinfo,
+			     &sinfo->txrate);
 
 	sinfo->signal_avg = priv->bcn_rssi_avg;
 	sinfo->rx_bytes = priv->stats.rx_bytes;
-- 
cgit v1.2.3


From ed0b2b067bad9d923842ac4c68c6b652b5885b84 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Thu, 6 Dec 2018 16:12:49 -0800
Subject: mwifiex: add NL80211_STA_INFO_RX_BITRATE support

Comparing the existing TX_BITRATE parsing code (in
mwifiex_parse_htinfo()) with the RX bitrate histograms in debugfs.c, it
appears that the rxpd_rate and rxpd_htinfo fields have the same format.
At least, they give reasonable results when I parse them this way.

So this patch adds support for RX_BITRATE to our station info dump.

Along the way, I add legacy bitrate parsing into the same function,
using the debugfs code (mwifiex_histogram_read() and
mwifiex_adjust_data_rate()) as reference.

Additionally, to satisfy the requirements of
NL80211_STA_INFO_RX_BITRATE, I skip logging the bitrate of multicast
packets. This shouldn't add a lot of overhead to the RX path, as there
are already several similar 802.3 header checks in this same codepath.
We can also bias the branch behavior to favor unicast, as that's the
common performance-sensitive case.

I'd consider this support somewhat experimental, as I have zero
documentation from Marvell. But the existing driver code gives me good
reason to think this is correct.

I've tested this on a few different 802.11{a,b,g,n,ac} networks, and the
reported bitrates look good to me.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c | 26 +++++++++++++++++++++++++
 drivers/net/wireless/marvell/mwifiex/sta_rx.c   | 13 ++++++++-----
 2 files changed, 34 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 02b80ea232a7..1467af22e394 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -1333,6 +1333,28 @@ mwifiex_parse_htinfo(struct mwifiex_private *priv, u8 rateinfo, u8 htinfo,
 				rate->flags |= RATE_INFO_FLAGS_SHORT_GI;
 		}
 	}
+
+	/* Decode legacy rates for non-HT. */
+	if (!(htinfo & (BIT(0) | BIT(1)))) {
+		/* Bitrates in multiples of 100kb/s. */
+		static const int legacy_rates[] = {
+			[0] = 10,
+			[1] = 20,
+			[2] = 55,
+			[3] = 110,
+			[4] = 60, /* MWIFIEX_RATE_INDEX_OFDM0 */
+			[5] = 60,
+			[6] = 90,
+			[7] = 120,
+			[8] = 180,
+			[9] = 240,
+			[10] = 360,
+			[11] = 480,
+			[12] = 540,
+		};
+		if (rateinfo < ARRAY_SIZE(legacy_rates))
+			rate->legacy = legacy_rates[rateinfo];
+	}
 }
 
 /*
@@ -1414,6 +1436,10 @@ mwifiex_dump_station_info(struct mwifiex_private *priv,
 	/* bit rate is in 500 kb/s units. Convert it to 100kb/s units */
 	sinfo->txrate.legacy = rate * 5;
 
+	sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE);
+	mwifiex_parse_htinfo(priv, priv->rxpd_rate, priv->rxpd_htinfo,
+			     &sinfo->rxrate);
+
 	if (priv->bss_mode == NL80211_IFTYPE_STATION) {
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BSS_PARAM);
 		sinfo->bss_param.flags = 0;
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_rx.c b/drivers/net/wireless/marvell/mwifiex/sta_rx.c
index 00fcbda09349..fb28a5c7f441 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_rx.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_rx.c
@@ -152,14 +152,17 @@ int mwifiex_process_rx_packet(struct mwifiex_private *priv,
 		mwifiex_process_tdls_action_frame(priv, offset, rx_pkt_len);
 	}
 
-	priv->rxpd_rate = local_rx_pd->rx_rate;
-
-	priv->rxpd_htinfo = local_rx_pd->ht_info;
+	/* Only stash RX bitrate for unicast packets. */
+	if (likely(!is_multicast_ether_addr(rx_pkt_hdr->eth803_hdr.h_dest))) {
+		priv->rxpd_rate = local_rx_pd->rx_rate;
+		priv->rxpd_htinfo = local_rx_pd->ht_info;
+	}
 
 	if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_STA ||
 	    GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP) {
-		adj_rx_rate = mwifiex_adjust_data_rate(priv, priv->rxpd_rate,
-						       priv->rxpd_htinfo);
+		adj_rx_rate = mwifiex_adjust_data_rate(priv,
+						       local_rx_pd->rx_rate,
+						       local_rx_pd->ht_info);
 		mwifiex_hist_data_add(priv, adj_rx_rate, local_rx_pd->snr,
 				      local_rx_pd->nf);
 	}
-- 
cgit v1.2.3


From 153e22c0ff1260035cd7fe72c8aeead1f5fac757 Mon Sep 17 00:00:00 2001
From: Wright Feng <Wright.Feng@cypress.com>
Date: Mon, 5 Nov 2018 05:51:54 +0000
Subject: brcmfmac: add credit numbers updating support

The credit numbers are static and tunable per chip in firmware side.
However the credit number may be changed that is based on packet pool
length and will send BRCMF_E_FIFO_CREDIT_MAP event to notify host driver
updates the credit numbers during interface up.
The purpose of this patch is making host driver has ability of updating
the credit numbers when receiving the BRCMF_E_FIFO_CREDIT_MAP event.

Signed-off-by: Wright Feng <wright.feng@cypress.com>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../broadcom/brcm80211/brcmfmac/fwsignal.c         | 23 ++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
index f3cbf78c8899..c75be2703b3e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
@@ -511,6 +511,7 @@ struct brcmf_fws_info {
 	struct work_struct fws_dequeue_work;
 	u32 fifo_enqpkt[BRCMF_FWS_FIFO_COUNT];
 	int fifo_credit[BRCMF_FWS_FIFO_COUNT];
+	int init_fifo_credit[BRCMF_FWS_FIFO_COUNT];
 	int credits_borrowed[BRCMF_FWS_FIFO_AC_VO + 1];
 	int deq_node_pos[BRCMF_FWS_FIFO_COUNT];
 	u32 fifo_credit_map;
@@ -1237,6 +1238,9 @@ static void brcmf_fws_return_credits(struct brcmf_fws_info *fws,
 	}
 
 	fws->fifo_credit[fifo] += credits;
+	if (fws->fifo_credit[fifo] > fws->init_fifo_credit[fifo])
+		fws->fifo_credit[fifo] = fws->init_fifo_credit[fifo];
+
 }
 
 static void brcmf_fws_schedule_deq(struct brcmf_fws_info *fws)
@@ -1595,19 +1599,21 @@ static int brcmf_fws_notify_credit_map(struct brcmf_if *ifp,
 		brcmf_err("event payload too small (%d)\n", e->datalen);
 		return -EINVAL;
 	}
-	if (fws->creditmap_received)
-		return 0;
 
 	fws->creditmap_received = true;
 
 	brcmf_dbg(TRACE, "enter: credits %pM\n", credits);
 	brcmf_fws_lock(fws);
 	for (i = 0; i < ARRAY_SIZE(fws->fifo_credit); i++) {
-		if (*credits)
+		fws->fifo_credit[i] += credits[i] - fws->init_fifo_credit[i];
+		fws->init_fifo_credit[i] = credits[i];
+		if (fws->fifo_credit[i] > 0)
 			fws->fifo_credit_map |= 1 << i;
 		else
 			fws->fifo_credit_map &= ~(1 << i);
-		fws->fifo_credit[i] = *credits++;
+		WARN_ONCE(fws->fifo_credit[i] < 0,
+			  "fifo_credit[%d] is negative(%d)\n", i,
+			  fws->fifo_credit[i]);
 	}
 	brcmf_fws_schedule_deq(fws);
 	brcmf_fws_unlock(fws);
@@ -2013,7 +2019,7 @@ static int brcmf_fws_borrow_credit(struct brcmf_fws_info *fws)
 	}
 
 	for (lender_ac = 0; lender_ac <= BRCMF_FWS_FIFO_AC_VO; lender_ac++) {
-		if (fws->fifo_credit[lender_ac]) {
+		if (fws->fifo_credit[lender_ac] > 0) {
 			fws->credits_borrowed[lender_ac]++;
 			fws->fifo_credit[lender_ac]--;
 			if (fws->fifo_credit[lender_ac] == 0)
@@ -2210,8 +2216,9 @@ static void brcmf_fws_dequeue_worker(struct work_struct *worker)
 			}
 			continue;
 		}
-		while ((fws->fifo_credit[fifo]) || ((!fws->bcmc_credit_check) &&
-		       (fifo == BRCMF_FWS_FIFO_BCMC))) {
+		while ((fws->fifo_credit[fifo] > 0) ||
+		       ((!fws->bcmc_credit_check) &&
+			(fifo == BRCMF_FWS_FIFO_BCMC))) {
 			skb = brcmf_fws_deq(fws, fifo);
 			if (!skb)
 				break;
@@ -2222,7 +2229,7 @@ static void brcmf_fws_dequeue_worker(struct work_struct *worker)
 				break;
 		}
 		if ((fifo == BRCMF_FWS_FIFO_AC_BE) &&
-		    (fws->fifo_credit[fifo] == 0) &&
+		    (fws->fifo_credit[fifo] <= 0) &&
 		    (!fws->bus_flow_blocked)) {
 			while (brcmf_fws_borrow_credit(fws) == 0) {
 				skb = brcmf_fws_deq(fws, fifo);
-- 
cgit v1.2.3


From a3bdc6deb60bf6be4405058ca49a686c4db08c39 Mon Sep 17 00:00:00 2001
From: Wright Feng <Wright.Feng@cypress.com>
Date: Mon, 5 Nov 2018 05:51:59 +0000
Subject: brcmfmac: enable frameburst mode in default firmware setting

The frameburst feature can enable per-packet framebursting in firmware
side and get higher TX throughput in High Throughput(HT) mode. To enhance
TX throughput, we enable frameburst mode in default firmware setting.

Signed-off-by: Wright Feng <wright.feng@cypress.com>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 6 ++++++
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h     | 1 +
 2 files changed, 7 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 7f0a5bade70a..648fdeabce02 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -6639,6 +6639,12 @@ static s32 brcmf_config_dongle(struct brcmf_cfg80211_info *cfg)
 
 	brcmf_configure_arp_nd_offload(ifp, true);
 
+	err = brcmf_fil_cmd_int_set(ifp, BRCMF_C_SET_FAKEFRAG, 1);
+	if (err) {
+		brcmf_err("failed to set frameburst mode\n");
+		goto default_conf_out;
+	}
+
 	cfg->dongle_up = true;
 default_conf_out:
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
index 63b1287e2e6d..b6b183b18413 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
@@ -80,6 +80,7 @@
 #define BRCMF_C_SCB_DEAUTHENTICATE_FOR_REASON	201
 #define BRCMF_C_SET_ASSOC_PREFER		205
 #define BRCMF_C_GET_VALID_CHANNELS		217
+#define BRCMF_C_SET_FAKEFRAG			219
 #define BRCMF_C_GET_KEY_PRIMARY			235
 #define BRCMF_C_SET_KEY_PRIMARY			236
 #define BRCMF_C_SET_SCAN_PASSIVE_TIME		258
-- 
cgit v1.2.3


From e4af3ffb43d50f070134aa1b40d5c3573f57deb1 Mon Sep 17 00:00:00 2001
From: Chung-Hsien Hsu <stanley.hsu@cypress.com>
Date: Mon, 5 Nov 2018 05:52:05 +0000
Subject: brcmfmac: handle compressed tx status signal

Firmware inform the driver about tx status by normal tx status signal
or compressed tx status signal. This patch adds support to handle the
compressed tx status signal.

Signed-off-by: Chung-Hsien Hsu <stanley.hsu@cypress.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../broadcom/brcm80211/brcmfmac/fwsignal.c         | 121 ++++++++++++---------
 1 file changed, 71 insertions(+), 50 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
index c75be2703b3e..02759ebd207c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
@@ -1455,9 +1455,10 @@ static int brcmf_fws_txstatus_suppressed(struct brcmf_fws_info *fws, int fifo,
 
 static int
 brcmf_fws_txs_process(struct brcmf_fws_info *fws, u8 flags, u32 hslot,
-		      u32 genbit, u16 seq)
+		      u32 genbit, u16 seq, u8 compcnt)
 {
 	u32 fifo;
+	u8 cnt = 0;
 	int ret;
 	bool remove_from_hanger = true;
 	struct sk_buff *skb;
@@ -1468,60 +1469,71 @@ brcmf_fws_txs_process(struct brcmf_fws_info *fws, u8 flags, u32 hslot,
 	brcmf_dbg(DATA, "flags %d\n", flags);
 
 	if (flags == BRCMF_FWS_TXSTATUS_DISCARD)
-		fws->stats.txs_discard++;
+		fws->stats.txs_discard += compcnt;
 	else if (flags == BRCMF_FWS_TXSTATUS_CORE_SUPPRESS) {
-		fws->stats.txs_supp_core++;
+		fws->stats.txs_supp_core += compcnt;
 		remove_from_hanger = false;
 	} else if (flags == BRCMF_FWS_TXSTATUS_FW_PS_SUPPRESS) {
-		fws->stats.txs_supp_ps++;
+		fws->stats.txs_supp_ps += compcnt;
 		remove_from_hanger = false;
 	} else if (flags == BRCMF_FWS_TXSTATUS_FW_TOSSED)
-		fws->stats.txs_tossed++;
+		fws->stats.txs_tossed += compcnt;
 	else if (flags == BRCMF_FWS_TXSTATUS_HOST_TOSSED)
-		fws->stats.txs_host_tossed++;
+		fws->stats.txs_host_tossed += compcnt;
 	else
 		brcmf_err("unexpected txstatus\n");
 
-	ret = brcmf_fws_hanger_poppkt(&fws->hanger, hslot, &skb,
-				      remove_from_hanger);
-	if (ret != 0) {
-		brcmf_err("no packet in hanger slot: hslot=%d\n", hslot);
-		return ret;
-	}
+	while (cnt < compcnt) {
+		ret = brcmf_fws_hanger_poppkt(&fws->hanger, hslot, &skb,
+					      remove_from_hanger);
+		if (ret != 0) {
+			brcmf_err("no packet in hanger slot: hslot=%d\n",
+				  hslot);
+			goto cont;
+		}
 
-	skcb = brcmf_skbcb(skb);
-	entry = skcb->mac;
-	if (WARN_ON(!entry)) {
-		brcmu_pkt_buf_free_skb(skb);
-		return -EINVAL;
-	}
-	entry->transit_count--;
-	if (entry->suppressed && entry->suppr_transit_count)
-		entry->suppr_transit_count--;
+		skcb = brcmf_skbcb(skb);
+		entry = skcb->mac;
+		if (WARN_ON(!entry)) {
+			brcmu_pkt_buf_free_skb(skb);
+			goto cont;
+		}
+		entry->transit_count--;
+		if (entry->suppressed && entry->suppr_transit_count)
+			entry->suppr_transit_count--;
 
-	brcmf_dbg(DATA, "%s flags %d htod %X seq %X\n", entry->name, flags,
-		  skcb->htod, seq);
+		brcmf_dbg(DATA, "%s flags %d htod %X seq %X\n", entry->name,
+			  flags, skcb->htod, seq);
 
-	/* pick up the implicit credit from this packet */
-	fifo = brcmf_skb_htod_tag_get_field(skb, FIFO);
-	if ((fws->fcmode == BRCMF_FWS_FCMODE_IMPLIED_CREDIT) ||
-	    (brcmf_skb_if_flags_get_field(skb, REQ_CREDIT)) ||
-	    (flags == BRCMF_FWS_TXSTATUS_HOST_TOSSED)) {
-		brcmf_fws_return_credits(fws, fifo, 1);
-		brcmf_fws_schedule_deq(fws);
-	}
-	brcmf_fws_macdesc_return_req_credit(skb);
+		/* pick up the implicit credit from this packet */
+		fifo = brcmf_skb_htod_tag_get_field(skb, FIFO);
+		if (fws->fcmode == BRCMF_FWS_FCMODE_IMPLIED_CREDIT ||
+		    (brcmf_skb_if_flags_get_field(skb, REQ_CREDIT)) ||
+		    flags == BRCMF_FWS_TXSTATUS_HOST_TOSSED) {
+			brcmf_fws_return_credits(fws, fifo, 1);
+			brcmf_fws_schedule_deq(fws);
+		}
+		brcmf_fws_macdesc_return_req_credit(skb);
 
-	ret = brcmf_proto_hdrpull(fws->drvr, false, skb, &ifp);
-	if (ret) {
-		brcmu_pkt_buf_free_skb(skb);
-		return -EINVAL;
+		ret = brcmf_proto_hdrpull(fws->drvr, false, skb, &ifp);
+		if (ret) {
+			brcmu_pkt_buf_free_skb(skb);
+			goto cont;
+		}
+		if (!remove_from_hanger)
+			ret = brcmf_fws_txstatus_suppressed(fws, fifo, skb,
+							    genbit, seq);
+		if (remove_from_hanger || ret)
+			brcmf_txfinalize(ifp, skb, true);
+
+cont:
+		hslot = (hslot + 1) & (BRCMF_FWS_TXSTAT_HSLOT_MASK >>
+				       BRCMF_FWS_TXSTAT_HSLOT_SHIFT);
+		if (BRCMF_FWS_MODE_GET_REUSESEQ(fws->mode))
+			seq = (seq + 1) & BRCMF_SKB_HTOD_SEQ_NR_MASK;
+
+		cnt++;
 	}
-	if (!remove_from_hanger)
-		ret = brcmf_fws_txstatus_suppressed(fws, fifo, skb,
-						    genbit, seq);
-	if (remove_from_hanger || ret)
-		brcmf_txfinalize(ifp, skb, true);
 
 	return 0;
 }
@@ -1547,7 +1559,8 @@ static int brcmf_fws_fifocreditback_indicate(struct brcmf_fws_info *fws,
 	return BRCMF_FWS_RET_OK_SCHEDULE;
 }
 
-static int brcmf_fws_txstatus_indicate(struct brcmf_fws_info *fws, u8 *data)
+static int brcmf_fws_txstatus_indicate(struct brcmf_fws_info *fws, u8 type,
+				       u8 *data)
 {
 	__le32 status_le;
 	__le16 seq_le;
@@ -1556,23 +1569,31 @@ static int brcmf_fws_txstatus_indicate(struct brcmf_fws_info *fws, u8 *data)
 	u32 genbit;
 	u8 flags;
 	u16 seq;
+	u8 compcnt;
+	u8 compcnt_offset = BRCMF_FWS_TYPE_TXSTATUS_LEN;
 
-	fws->stats.txs_indicate++;
 	memcpy(&status_le, data, sizeof(status_le));
 	status = le32_to_cpu(status_le);
 	flags = brcmf_txstatus_get_field(status, FLAGS);
 	hslot = brcmf_txstatus_get_field(status, HSLOT);
 	genbit = brcmf_txstatus_get_field(status, GENERATION);
 	if (BRCMF_FWS_MODE_GET_REUSESEQ(fws->mode)) {
-		memcpy(&seq_le, &data[BRCMF_FWS_TYPE_PKTTAG_LEN],
+		memcpy(&seq_le, &data[BRCMF_FWS_TYPE_TXSTATUS_LEN],
 		       sizeof(seq_le));
 		seq = le16_to_cpu(seq_le);
+		compcnt_offset += BRCMF_FWS_TYPE_SEQ_LEN;
 	} else {
 		seq = 0;
 	}
 
+	if (type == BRCMF_FWS_TYPE_COMP_TXSTATUS)
+		compcnt = data[compcnt_offset];
+	else
+		compcnt = 1;
+	fws->stats.txs_indicate += compcnt;
+
 	brcmf_fws_lock(fws);
-	brcmf_fws_txs_process(fws, flags, hslot, genbit, seq);
+	brcmf_fws_txs_process(fws, flags, hslot, genbit, seq, compcnt);
 	brcmf_fws_unlock(fws);
 	return BRCMF_FWS_RET_OK_NOSCHEDULE;
 }
@@ -1888,8 +1909,6 @@ void brcmf_fws_hdrpull(struct brcmf_if *ifp, s16 siglen, struct sk_buff *skb)
 
 		err = BRCMF_FWS_RET_OK_NOSCHEDULE;
 		switch (type) {
-		case BRCMF_FWS_TYPE_COMP_TXSTATUS:
-			break;
 		case BRCMF_FWS_TYPE_HOST_REORDER_RXPKTS:
 			rd = (struct brcmf_skb_reorder_data *)skb->cb;
 			rd->reorder = data;
@@ -1912,7 +1931,8 @@ void brcmf_fws_hdrpull(struct brcmf_if *ifp, s16 siglen, struct sk_buff *skb)
 			err = brcmf_fws_request_indicate(fws, type, data);
 			break;
 		case BRCMF_FWS_TYPE_TXSTATUS:
-			brcmf_fws_txstatus_indicate(fws, data);
+		case BRCMF_FWS_TYPE_COMP_TXSTATUS:
+			brcmf_fws_txstatus_indicate(fws, type, data);
 			break;
 		case BRCMF_FWS_TYPE_FIFO_CREDITBACK:
 			err = brcmf_fws_fifocreditback_indicate(fws, data);
@@ -2001,7 +2021,7 @@ static void brcmf_fws_rollback_toq(struct brcmf_fws_info *fws,
 		fws->stats.rollback_failed++;
 		hslot = brcmf_skb_htod_tag_get_field(skb, HSLOT);
 		brcmf_fws_txs_process(fws, BRCMF_FWS_TXSTATUS_HOST_TOSSED,
-				      hslot, 0, 0);
+				      hslot, 0, 0, 1);
 	} else {
 		fws->stats.rollback_success++;
 		brcmf_fws_return_credits(fws, fifo, 1);
@@ -2462,7 +2482,8 @@ void brcmf_fws_bustxfail(struct brcmf_fws_info *fws, struct sk_buff *skb)
 	}
 	brcmf_fws_lock(fws);
 	hslot = brcmf_skb_htod_tag_get_field(skb, HSLOT);
-	brcmf_fws_txs_process(fws, BRCMF_FWS_TXSTATUS_HOST_TOSSED, hslot, 0, 0);
+	brcmf_fws_txs_process(fws, BRCMF_FWS_TXSTATUS_HOST_TOSSED, hslot, 0, 0,
+			      1);
 	brcmf_fws_unlock(fws);
 }
 
-- 
cgit v1.2.3


From eb6b33bfb8f56859df7264dccc2ca8ab7c57342a Mon Sep 17 00:00:00 2001
From: Winnie Chang <winnie.chang@cypress.com>
Date: Wed, 21 Nov 2018 07:53:42 +0000
Subject: brcmfmac: add 4354 raw pcie device id

Add the raw 4354 PCIe device ID for unprogrammed Cypress boards.

Reviewed-by: Arend Van Spriel <arend@broadcom.com>
Signed-off-by: Winnie Chang <winnie.chang@cypress.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c       | 1 +
 drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index 956a8b236836..16d7dda965d8 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -2019,6 +2019,7 @@ static const struct dev_pm_ops brcmf_pciedrvr_pm = {
 static const struct pci_device_id brcmf_pcie_devid_table[] = {
 	BRCMF_PCIE_DEVICE(BRCM_PCIE_4350_DEVICE_ID),
 	BRCMF_PCIE_DEVICE_SUB(0x4355, BRCM_PCIE_VENDOR_ID_BROADCOM, 0x4355),
+	BRCMF_PCIE_DEVICE(BRCM_PCIE_4354_RAW_DEVICE_ID),
 	BRCMF_PCIE_DEVICE(BRCM_PCIE_4356_DEVICE_ID),
 	BRCMF_PCIE_DEVICE(BRCM_PCIE_43567_DEVICE_ID),
 	BRCMF_PCIE_DEVICE(BRCM_PCIE_43570_DEVICE_ID),
diff --git a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
index 686f7a85a045..acb87238922f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
+++ b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
@@ -74,6 +74,7 @@
 /* PCIE Device IDs */
 #define BRCM_PCIE_4350_DEVICE_ID	0x43a3
 #define BRCM_PCIE_4354_DEVICE_ID	0x43df
+#define BRCM_PCIE_4354_RAW_DEVICE_ID	0x4354
 #define BRCM_PCIE_4356_DEVICE_ID	0x43ec
 #define BRCM_PCIE_43567_DEVICE_ID	0x43d3
 #define BRCM_PCIE_43570_DEVICE_ID	0x43d9
-- 
cgit v1.2.3


From e1a08730eeb0bad4d82c3bc40e74854872de618d Mon Sep 17 00:00:00 2001
From: Wright Feng <wright.feng@cypress.com>
Date: Wed, 21 Nov 2018 07:53:44 +0000
Subject: brcmfmac: set F2 watermark to 256 for 4373

We got SDIO_CRC_ERROR with 4373 on SDR104 when doing bi-directional
throughput test. Enable watermark to 256 to guarantee the operation
stability.

Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../wireless/broadcom/brcm80211/brcmfmac/sdio.c    | 26 ++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 22646a3b911e..c833e24c751c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -49,6 +49,10 @@
 #define DCMD_RESP_TIMEOUT	msecs_to_jiffies(2500)
 #define CTL_DONE_TIMEOUT	msecs_to_jiffies(2500)
 
+/* watermark expressed in number of words */
+#define DEFAULT_F2_WATERMARK    0x8
+#define CY_4373_F2_WATERMARK    0x40
+
 #ifdef DEBUG
 
 #define BRCMF_TRAP_INFO_SIZE	80
@@ -138,6 +142,8 @@ struct rte_console {
 /* 1: isolate internal sdio signals, put external pads in tri-state; requires
  * sdio bus power cycle to clear (rev 9) */
 #define SBSDIO_DEVCTL_PADS_ISO		0x08
+/* 1: enable F2 Watermark */
+#define SBSDIO_DEVCTL_F2WM_ENAB		0x10
 /* Force SD->SB reset mapping (rev 11) */
 #define SBSDIO_DEVCTL_SB_RST_CTL	0x30
 /*   Determined by CoreControl bit */
@@ -4046,6 +4052,7 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 	void *nvram;
 	u32 nvram_len;
 	u8 saveclk;
+	u8 devctl;
 
 	brcmf_dbg(TRACE, "Enter: dev=%s, err=%d\n", dev_name(dev), err);
 
@@ -4101,8 +4108,23 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 		brcmf_sdiod_writel(sdiod, core->base + SD_REG(hostintmask),
 				   bus->hostintmask, NULL);
 
-
-		brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK, 8, &err);
+		switch (sdiod->func1->device) {
+		case SDIO_DEVICE_ID_CYPRESS_4373:
+			brcmf_dbg(INFO, "set F2 watermark to 0x%x*4 bytes\n",
+				  CY_4373_F2_WATERMARK);
+			brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK,
+					   CY_4373_F2_WATERMARK, &err);
+			devctl = brcmf_sdiod_readb(sdiod, SBSDIO_DEVICE_CTL,
+						   &err);
+			devctl |= SBSDIO_DEVCTL_F2WM_ENAB;
+			brcmf_sdiod_writeb(sdiod, SBSDIO_DEVICE_CTL, devctl,
+					   &err);
+			break;
+		default:
+			brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK,
+					   DEFAULT_F2_WATERMARK, &err);
+			break;
+		}
 	} else {
 		/* Disable F2 again */
 		sdio_disable_func(sdiod->func2);
-- 
cgit v1.2.3


From 58e4bbea0c1d9b5ace11df968c5dc096ce052a73 Mon Sep 17 00:00:00 2001
From: Madhan Mohan R <MadhanMohan.R@cypress.com>
Date: Wed, 21 Nov 2018 07:53:45 +0000
Subject: brcmfmac: set SDIO F1 MesBusyCtrl for CYW4373

Along with F2 watermark (existing) configuration, F1 MesBusyCtrl
should be enabled & sdio device RX FIFO watermark should be
configured to avoid overflow errors.

Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Madhan Mohan R <madhanmohan.r@cypress.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c | 3 +++
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h | 9 ++++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index c833e24c751c..7a0601543dff 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4119,6 +4119,9 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 			devctl |= SBSDIO_DEVCTL_F2WM_ENAB;
 			brcmf_sdiod_writeb(sdiod, SBSDIO_DEVICE_CTL, devctl,
 					   &err);
+			brcmf_sdiod_writeb(sdiod, SBSDIO_FUNC1_MESBUSYCTRL,
+					   CY_4373_F2_WATERMARK |
+					   SBSDIO_MESBUSYCTRL_ENAB, &err);
 			break;
 		default:
 			brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
index 7faed831f07d..34b031154da9 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
@@ -77,7 +77,7 @@
 #define SBSDIO_GPIO_OUT			0x10006
 /* gpio enable */
 #define SBSDIO_GPIO_EN			0x10007
-/* rev < 7, watermark for sdio device */
+/* rev < 7, watermark for sdio device TX path */
 #define SBSDIO_WATERMARK		0x10008
 /* control busy signal generation */
 #define SBSDIO_DEVICE_CTL		0x10009
@@ -104,6 +104,13 @@
 #define SBSDIO_FUNC1_RFRAMEBCHI		0x1001C
 /* MesBusyCtl (rev 11) */
 #define SBSDIO_FUNC1_MESBUSYCTRL	0x1001D
+/* Watermark for sdio device RX path */
+#define SBSDIO_MESBUSY_RXFIFO_WM_MASK	0x7F
+#define SBSDIO_MESBUSY_RXFIFO_WM_SHIFT	0
+/* Enable busy capability for MES access */
+#define SBSDIO_MESBUSYCTRL_ENAB		0x80
+#define SBSDIO_MESBUSYCTRL_ENAB_SHIFT	7
+
 /* Sdio Core Rev 12 */
 #define SBSDIO_FUNC1_WAKEUPCTRL		0x1001E
 #define SBSDIO_FUNC1_WCTRL_ALPWAIT_MASK		0x1
-- 
cgit v1.2.3


From 35cb51b2162a1a7c5cd977f92595e60ab14d3b22 Mon Sep 17 00:00:00 2001
From: Chi-Hsien Lin <Chi-Hsien.Lin@cypress.com>
Date: Wed, 21 Nov 2018 07:53:47 +0000
Subject: brcmfmac: add support for CYW43012 SDIO chipset

CYW43012 is a 1x1 802.11a/b/g/n Dual-Band HT20, 256-QAM/Turbo QAM. It
is an Ultra Low Power WLAN+BT combo chip.

Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Praveen Babu C <praveen.chandran@cypress.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c  |  1 +
 .../wireless/broadcom/brcm80211/brcmfmac/chip.c    | 14 +++-
 .../wireless/broadcom/brcm80211/brcmfmac/sdio.c    | 74 ++++++++++++++++++----
 .../broadcom/brcm80211/include/brcm_hw_ids.h       |  1 +
 include/linux/mmc/sdio_ids.h                       |  1 +
 5 files changed, 78 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index b2ad2122c8c4..d64bf233b12c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -983,6 +983,7 @@ static const struct sdio_device_id brcmf_sdmmc_ids[] = {
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4354),
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4356),
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_CYPRESS_4373),
+	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_CYPRESS_43012),
 	{ /* end: all zeroes */ }
 };
 MODULE_DEVICE_TABLE(sdio, brcmf_sdmmc_ids);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
index 927d62b3d41b..a3c857721446 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
@@ -165,6 +165,7 @@ struct sbconfig {
 #define SRCI_LSS_MASK		0x00f00000
 #define SRCI_LSS_SHIFT		20
 #define	SRCI_SRNB_MASK		0xf0
+#define	SRCI_SRNB_MASK_EXT	0x100
 #define	SRCI_SRNB_SHIFT		4
 #define	SRCI_SRBSZ_MASK		0xf
 #define	SRCI_SRBSZ_SHIFT	0
@@ -592,7 +593,13 @@ static void brcmf_chip_socram_ramsize(struct brcmf_core_priv *sr, u32 *ramsize,
 		if (lss != 0)
 			*ramsize += (1 << ((lss - 1) + SR_BSZ_BASE));
 	} else {
-		nb = (coreinfo & SRCI_SRNB_MASK) >> SRCI_SRNB_SHIFT;
+		/* length of SRAM Banks increased for corerev greater than 23 */
+		if (sr->pub.rev >= 23) {
+			nb = (coreinfo & (SRCI_SRNB_MASK | SRCI_SRNB_MASK_EXT))
+				>> SRCI_SRNB_SHIFT;
+		} else {
+			nb = (coreinfo & SRCI_SRNB_MASK) >> SRCI_SRNB_SHIFT;
+		}
 		for (i = 0; i < nb; i++) {
 			retent = brcmf_chip_socram_banksize(sr, i, &banksize);
 			*ramsize += banksize;
@@ -1356,6 +1363,11 @@ bool brcmf_chip_sr_capable(struct brcmf_chip *pub)
 		addr = CORE_CC_REG(base, sr_control1);
 		reg = chip->ops->read32(chip->ctx, addr);
 		return reg != 0;
+	case CY_CC_43012_CHIP_ID:
+		addr = CORE_CC_REG(pmu->base, retention_ctl);
+		reg = chip->ops->read32(chip->ctx, addr);
+		return (reg & (PMU_RCTL_MACPHY_DISABLE_MASK |
+			       PMU_RCTL_LOGIC_DISABLE_MASK)) == 0;
 	default:
 		addr = CORE_CC_REG(pmu->base, pmucapabilities_ext);
 		reg = chip->ops->read32(chip->ctx, addr);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 7a0601543dff..73a034172c4c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -624,6 +624,7 @@ BRCMF_FW_DEF(43455, "brcmfmac43455-sdio");
 BRCMF_FW_DEF(4354, "brcmfmac4354-sdio");
 BRCMF_FW_DEF(4356, "brcmfmac4356-sdio");
 BRCMF_FW_DEF(4373, "brcmfmac4373-sdio");
+BRCMF_FW_DEF(43012, "brcmfmac43012-sdio");
 
 static const struct brcmf_firmware_mapping brcmf_sdio_fwnames[] = {
 	BRCMF_FW_ENTRY(BRCM_CC_43143_CHIP_ID, 0xFFFFFFFF, 43143),
@@ -643,7 +644,8 @@ static const struct brcmf_firmware_mapping brcmf_sdio_fwnames[] = {
 	BRCMF_FW_ENTRY(BRCM_CC_4345_CHIP_ID, 0xFFFFFFC0, 43455),
 	BRCMF_FW_ENTRY(BRCM_CC_4354_CHIP_ID, 0xFFFFFFFF, 4354),
 	BRCMF_FW_ENTRY(BRCM_CC_4356_CHIP_ID, 0xFFFFFFFF, 4356),
-	BRCMF_FW_ENTRY(CY_CC_4373_CHIP_ID, 0xFFFFFFFF, 4373)
+	BRCMF_FW_ENTRY(CY_CC_4373_CHIP_ID, 0xFFFFFFFF, 4373),
+	BRCMF_FW_ENTRY(CY_CC_43012_CHIP_ID, 0xFFFFFFFF, 43012)
 };
 
 static void pkt_align(struct sk_buff *p, int len, int align)
@@ -677,6 +679,14 @@ brcmf_sdio_kso_control(struct brcmf_sdio *bus, bool on)
 	/* 1st KSO write goes to AOS wake up core if device is asleep  */
 	brcmf_sdiod_writeb(bus->sdiodev, SBSDIO_FUNC1_SLEEPCSR, wr_val, &err);
 
+	/* In case of 43012 chip, the chip could go down immediately after
+	 * KSO bit is cleared. So the further reads of KSO register could
+	 * fail. Thereby just bailing out immediately after clearing KSO
+	 * bit, to avoid polling of KSO bit.
+	 */
+	if (!on && bus->ci->chip == CY_CC_43012_CHIP_ID)
+		return err;
+
 	if (on) {
 		/* device WAKEUP through KSO:
 		 * write bit 0 & read back until
@@ -2402,6 +2412,14 @@ static int brcmf_sdio_tx_ctrlframe(struct brcmf_sdio *bus, u8 *frame, u16 len)
 	return ret;
 }
 
+static bool brcmf_chip_is_ulp(struct brcmf_chip *ci)
+{
+	if (ci->chip == CY_CC_43012_CHIP_ID)
+		return true;
+	else
+		return false;
+}
+
 static void brcmf_sdio_bus_stop(struct device *dev)
 {
 	struct brcmf_bus *bus_if = dev_get_drvdata(dev);
@@ -2409,7 +2427,7 @@ static void brcmf_sdio_bus_stop(struct device *dev)
 	struct brcmf_sdio *bus = sdiodev->bus;
 	struct brcmf_core *core = bus->sdio_core;
 	u32 local_hostintmask;
-	u8 saveclk;
+	u8 saveclk, bpreq;
 	int err;
 
 	brcmf_dbg(TRACE, "Enter\n");
@@ -2436,9 +2454,14 @@ static void brcmf_sdio_bus_stop(struct device *dev)
 		/* Force backplane clocks to assure F2 interrupt propagates */
 		saveclk = brcmf_sdiod_readb(sdiodev, SBSDIO_FUNC1_CHIPCLKCSR,
 					    &err);
-		if (!err)
-			brcmf_sdiod_writeb(sdiodev, SBSDIO_FUNC1_CHIPCLKCSR,
-					   (saveclk | SBSDIO_FORCE_HT), &err);
+		if (!err) {
+			bpreq = saveclk;
+			bpreq |= brcmf_chip_is_ulp(bus->ci) ?
+				SBSDIO_HT_AVAIL_REQ : SBSDIO_FORCE_HT;
+			brcmf_sdiod_writeb(sdiodev,
+					   SBSDIO_FUNC1_CHIPCLKCSR,
+					   bpreq, &err);
+		}
 		if (err)
 			brcmf_err("Failed to force clock for F2: err %d\n",
 				  err);
@@ -3328,20 +3351,45 @@ err:
 	return bcmerror;
 }
 
+static bool brcmf_sdio_aos_no_decode(struct brcmf_sdio *bus)
+{
+	if (bus->ci->chip == CY_CC_43012_CHIP_ID)
+		return true;
+	else
+		return false;
+}
+
 static void brcmf_sdio_sr_init(struct brcmf_sdio *bus)
 {
 	int err = 0;
 	u8 val;
+	u8 wakeupctrl;
+	u8 cardcap;
+	u8 chipclkcsr;
 
 	brcmf_dbg(TRACE, "Enter\n");
 
+	if (brcmf_chip_is_ulp(bus->ci)) {
+		wakeupctrl = SBSDIO_FUNC1_WCTRL_ALPWAIT_SHIFT;
+		chipclkcsr = SBSDIO_HT_AVAIL_REQ;
+	} else {
+		wakeupctrl = SBSDIO_FUNC1_WCTRL_HTWAIT_SHIFT;
+		chipclkcsr = SBSDIO_FORCE_HT;
+	}
+
+	if (brcmf_sdio_aos_no_decode(bus)) {
+		cardcap = SDIO_CCCR_BRCM_CARDCAP_CMD_NODEC;
+	} else {
+		cardcap = (SDIO_CCCR_BRCM_CARDCAP_CMD14_SUPPORT |
+			   SDIO_CCCR_BRCM_CARDCAP_CMD14_EXT);
+	}
+
 	val = brcmf_sdiod_readb(bus->sdiodev, SBSDIO_FUNC1_WAKEUPCTRL, &err);
 	if (err) {
 		brcmf_err("error reading SBSDIO_FUNC1_WAKEUPCTRL\n");
 		return;
 	}
-
-	val |= 1 << SBSDIO_FUNC1_WCTRL_HTWAIT_SHIFT;
+	val |= 1 << wakeupctrl;
 	brcmf_sdiod_writeb(bus->sdiodev, SBSDIO_FUNC1_WAKEUPCTRL, val, &err);
 	if (err) {
 		brcmf_err("error writing SBSDIO_FUNC1_WAKEUPCTRL\n");
@@ -3350,8 +3398,7 @@ static void brcmf_sdio_sr_init(struct brcmf_sdio *bus)
 
 	/* Add CMD14 Support */
 	brcmf_sdiod_func0_wb(bus->sdiodev, SDIO_CCCR_BRCM_CARDCAP,
-			     (SDIO_CCCR_BRCM_CARDCAP_CMD14_SUPPORT |
-			      SDIO_CCCR_BRCM_CARDCAP_CMD14_EXT),
+			     cardcap,
 			     &err);
 	if (err) {
 		brcmf_err("error writing SDIO_CCCR_BRCM_CARDCAP\n");
@@ -3359,7 +3406,7 @@ static void brcmf_sdio_sr_init(struct brcmf_sdio *bus)
 	}
 
 	brcmf_sdiod_writeb(bus->sdiodev, SBSDIO_FUNC1_CHIPCLKCSR,
-			   SBSDIO_FORCE_HT, &err);
+			   chipclkcsr, &err);
 	if (err) {
 		brcmf_err("error writing SBSDIO_FUNC1_CHIPCLKCSR\n");
 		return;
@@ -4051,7 +4098,7 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 	const struct firmware *code;
 	void *nvram;
 	u32 nvram_len;
-	u8 saveclk;
+	u8 saveclk, bpreq;
 	u8 devctl;
 
 	brcmf_dbg(TRACE, "Enter: dev=%s, err=%d\n", dev_name(dev), err);
@@ -4085,8 +4132,11 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 	/* Force clocks on backplane to be sure F2 interrupt propagates */
 	saveclk = brcmf_sdiod_readb(sdiod, SBSDIO_FUNC1_CHIPCLKCSR, &err);
 	if (!err) {
+		bpreq = saveclk;
+		bpreq |= brcmf_chip_is_ulp(bus->ci) ?
+			SBSDIO_HT_AVAIL_REQ : SBSDIO_FORCE_HT;
 		brcmf_sdiod_writeb(sdiod, SBSDIO_FUNC1_CHIPCLKCSR,
-				   (saveclk | SBSDIO_FORCE_HT), &err);
+				   bpreq, &err);
 	}
 	if (err) {
 		brcmf_err("Failed to force clock for F2: err %d\n", err);
diff --git a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
index acb87238922f..839980da9643 100644
--- a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
+++ b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
@@ -60,6 +60,7 @@
 #define BRCM_CC_43664_CHIP_ID		43664
 #define BRCM_CC_4371_CHIP_ID		0x4371
 #define CY_CC_4373_CHIP_ID		0x4373
+#define CY_CC_43012_CHIP_ID		43012
 
 /* USB Device IDs */
 #define BRCM_USB_43143_DEVICE_ID	0xbd1e
diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index 4224902a8e22..4332199c71c2 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -42,6 +42,7 @@
 #define SDIO_DEVICE_ID_BROADCOM_4354		0x4354
 #define SDIO_DEVICE_ID_BROADCOM_4356		0x4356
 #define SDIO_DEVICE_ID_CYPRESS_4373		0x4373
+#define SDIO_DEVICE_ID_CYPRESS_43012		43012
 
 #define SDIO_VENDOR_ID_INTEL			0x0089
 #define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX	0x1402
-- 
cgit v1.2.3


From b021a6bc1175442609af0b66d64f850883e155fb Mon Sep 17 00:00:00 2001
From: Chi-Hsien Lin <Chi-Hsien.Lin@cypress.com>
Date: Wed, 21 Nov 2018 07:53:48 +0000
Subject: brcmfmac: allow GCI core enumuration

GCI core is needed for ULP operation. Allow GCI core enumuration with
below changes:
 - Allow GCI to be added to core list even when it doesn't have a wrapper.
 - Allow 8K address space size.
 - Don't overwrite the address value when an additional size descriptor
   is in place.

Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
index a3c857721446..a8d3b96b727f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
@@ -786,7 +786,7 @@ static int brcmf_chip_dmp_get_regaddr(struct brcmf_chip_priv *ci, u32 *eromaddr,
 				      u32 *regbase, u32 *wrapbase)
 {
 	u8 desc;
-	u32 val;
+	u32 val, szdesc;
 	u8 mpnum = 0;
 	u8 stype, sztype, wraptype;
 
@@ -832,14 +832,15 @@ static int brcmf_chip_dmp_get_regaddr(struct brcmf_chip_priv *ci, u32 *eromaddr,
 
 		/* next size descriptor can be skipped */
 		if (sztype == DMP_SLAVE_SIZE_DESC) {
-			val = brcmf_chip_dmp_get_desc(ci, eromaddr, NULL);
+			szdesc = brcmf_chip_dmp_get_desc(ci, eromaddr, NULL);
 			/* skip upper size descriptor if present */
-			if (val & DMP_DESC_ADDRSIZE_GT32)
+			if (szdesc & DMP_DESC_ADDRSIZE_GT32)
 				brcmf_chip_dmp_get_desc(ci, eromaddr, NULL);
 		}
 
-		/* only look for 4K register regions */
-		if (sztype != DMP_SLAVE_SIZE_4K)
+		/* look for 4K or 8K register regions */
+		if (sztype != DMP_SLAVE_SIZE_4K &&
+		    sztype != DMP_SLAVE_SIZE_8K)
 			continue;
 
 		stype = (val & DMP_SLAVE_TYPE) >> DMP_SLAVE_TYPE_S;
@@ -896,7 +897,8 @@ int brcmf_chip_dmp_erom_scan(struct brcmf_chip_priv *ci)
 
 		/* need core with ports */
 		if (nmw + nsw == 0 &&
-		    id != BCMA_CORE_PMU)
+		    id != BCMA_CORE_PMU &&
+		    id != BCMA_CORE_GCI)
 			continue;
 
 		/* try to obtain register address info */
-- 
cgit v1.2.3


From f95a8d9c6aca196f1ace5b2e53a3dd3bc491b1b3 Mon Sep 17 00:00:00 2001
From: Naveen Gupta <naveen.gupta@cypress.com>
Date: Wed, 21 Nov 2018 07:53:49 +0000
Subject: brcmfmac: update 43012 F2 watermark setting to fix DMA Error during
 UDP RX Traffic

The number of words that the read FIFO has to contain except
the end of frame before sends data back to the host.
Max watermark = (512B - 2* (BurstLength))/4 =
(512 - 128)/4 = 384/4 = 0x60
so if burst length (i.e. BurstLength = 64) is increased,
watermark has to be reduced. This is the optimal setting for this chip.

Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Naveen Gupta <naveen.gupta@cypress.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 73a034172c4c..fe0cb398ab44 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -52,6 +52,7 @@
 /* watermark expressed in number of words */
 #define DEFAULT_F2_WATERMARK    0x8
 #define CY_4373_F2_WATERMARK    0x40
+#define CY_43012_F2_WATERMARK    0x60
 
 #ifdef DEBUG
 
@@ -4173,6 +4174,17 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 					   CY_4373_F2_WATERMARK |
 					   SBSDIO_MESBUSYCTRL_ENAB, &err);
 			break;
+		case SDIO_DEVICE_ID_CYPRESS_43012:
+			brcmf_dbg(INFO, "set F2 watermark to 0x%x*4 bytes\n",
+				  CY_43012_F2_WATERMARK);
+			brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK,
+					   CY_43012_F2_WATERMARK, &err);
+			devctl = brcmf_sdiod_readb(sdiod, SBSDIO_DEVICE_CTL,
+						   &err);
+			devctl |= SBSDIO_DEVCTL_F2WM_ENAB;
+			brcmf_sdiod_writeb(sdiod, SBSDIO_DEVICE_CTL, devctl,
+					   &err);
+			break;
 		default:
 			brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK,
 					   DEFAULT_F2_WATERMARK, &err);
-- 
cgit v1.2.3


From 2f2d389efda4caa4c1b69cb4fa2ab217f0fe6d6f Mon Sep 17 00:00:00 2001
From: Chi-Hsien Lin <Chi-Hsien.Lin@cypress.com>
Date: Wed, 21 Nov 2018 07:53:50 +0000
Subject: brcmfmac: 4373 save-restore support

Use chipcommon sr_control0 register to check 4373 sr support.

Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../net/wireless/broadcom/brcm80211/brcmfmac/chip.c   |  5 +++++
 .../wireless/broadcom/brcm80211/include/chipcommon.h  | 19 +++++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
index a8d3b96b727f..22534bf2a90c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
@@ -1365,6 +1365,11 @@ bool brcmf_chip_sr_capable(struct brcmf_chip *pub)
 		addr = CORE_CC_REG(base, sr_control1);
 		reg = chip->ops->read32(chip->ctx, addr);
 		return reg != 0;
+	case CY_CC_4373_CHIP_ID:
+		/* explicitly check SR engine enable bit */
+		addr = CORE_CC_REG(base, sr_control0);
+		reg = chip->ops->read32(chip->ctx, addr);
+		return (reg & CC_SR_CTL0_ENABLE_MASK) != 0;
 	case CY_CC_43012_CHIP_ID:
 		addr = CORE_CC_REG(pmu->base, retention_ctl);
 		reg = chip->ops->read32(chip->ctx, addr);
diff --git a/drivers/net/wireless/broadcom/brcm80211/include/chipcommon.h b/drivers/net/wireless/broadcom/brcm80211/include/chipcommon.h
index e1fd499930a0..de8225e6248b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/include/chipcommon.h
+++ b/drivers/net/wireless/broadcom/brcm80211/include/chipcommon.h
@@ -269,6 +269,25 @@ struct chipcregs {
 /* GSIO (spi/i2c) present, rev >= 37 */
 #define	CC_CAP2_GSIO		0x00000002
 
+/* sr_control0, rev >= 48 */
+#define CC_SR_CTL0_ENABLE_MASK			BIT(0)
+#define CC_SR_CTL0_ENABLE_SHIFT		0
+#define CC_SR_CTL0_EN_SR_ENG_CLK_SHIFT	1 /* sr_clk to sr_memory enable */
+#define CC_SR_CTL0_RSRC_TRIGGER_SHIFT	2 /* Rising edge resource trigger 0 to
+					   * sr_engine
+					   */
+#define CC_SR_CTL0_MIN_DIV_SHIFT	6 /* Min division value for fast clk
+					   * in sr_engine
+					   */
+#define CC_SR_CTL0_EN_SBC_STBY_SHIFT		16
+#define CC_SR_CTL0_EN_SR_ALP_CLK_MASK_SHIFT	18
+#define CC_SR_CTL0_EN_SR_HT_CLK_SHIFT		19
+#define CC_SR_CTL0_ALLOW_PIC_SHIFT	20 /* Allow pic to separate power
+					    * domains
+					    */
+#define CC_SR_CTL0_MAX_SR_LQ_CLK_CNT_SHIFT	25
+#define CC_SR_CTL0_EN_MEM_DISABLE_FOR_SLEEP	30
+
 /* pmucapabilities */
 #define PCAP_REV_MASK	0x000000ff
 #define PCAP_RC_MASK	0x00001f00
-- 
cgit v1.2.3


From 29f6589140a10ece8c1d73f58043ea5b3473ab3e Mon Sep 17 00:00:00 2001
From: Wright Feng <wright.feng@cypress.com>
Date: Wed, 21 Nov 2018 07:53:52 +0000
Subject: brcmfmac: disable command decode in sdio_aos

AOS is a part of the SDIOD core that becomes active when the rest of
SDIOD is sleeping to keep SDIO bus alive responding to reduced set of
commands.

Transaction between AOS and SDIOD is not protected, and if cmd 52 is
received in AOS and in the middle of response state changed from AOS to
SDIOD, response is corrupted and it causes to SDIO Host controller to
hang.

Command decode for below chips are disabled in this commit:
 - 4339
 - 4345
 - 4354
 - 4373

Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Signed-off-by: Double Lo <double.lo@cypress.com>
Signed-off-by: Madhan Mohan R <madhanmohan.r@cypress.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index fe0cb398ab44..0cd5b8d970d7 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -3354,7 +3354,11 @@ err:
 
 static bool brcmf_sdio_aos_no_decode(struct brcmf_sdio *bus)
 {
-	if (bus->ci->chip == CY_CC_43012_CHIP_ID)
+	if (bus->ci->chip == CY_CC_43012_CHIP_ID ||
+	    bus->ci->chip == CY_CC_4373_CHIP_ID ||
+	    bus->ci->chip == BRCM_CC_4339_CHIP_ID ||
+	    bus->ci->chip == BRCM_CC_4345_CHIP_ID ||
+	    bus->ci->chip == BRCM_CC_4354_CHIP_ID)
 		return true;
 	else
 		return false;
-- 
cgit v1.2.3


From 412dd15c8177d93abe0c8787b83b31c5eb061405 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 10 Dec 2018 21:55:37 +0100
Subject: brcmfmac: fix false-positive -Wmaybe-unintialized warning

When CONFIG_NO_AUTO_INLINE is set, we get a false-postive warning
for the brcmf_fw_request_nvram_done() function, after gcc figures
out that brcmf_fw_nvram_from_efi() might not set the 'data_len'
variable, but fails to notice that it always returns NULL:

drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c: In function 'brcmf_fw_request_nvram_done':
drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c:560:11: error: 'data_len' may be used uninitialized in this function [-Werror=maybe-uninitialized]

Mark it 'inline' to force gcc to understand this.

Fixes: ce2e6db554fa ("brcmfmac: Add support for getting nvram contents from EFI variables")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
index dad3c1c79038..14b948917a1a 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
@@ -512,7 +512,7 @@ fail:
 	return NULL;
 }
 #else
-static u8 *brcmf_fw_nvram_from_efi(size_t *data_len) { return NULL; }
+static inline u8 *brcmf_fw_nvram_from_efi(size_t *data_len) { return NULL; }
 #endif
 
 static void brcmf_fw_free_request(struct brcmf_fw_request *req)
-- 
cgit v1.2.3


From 662a7b078cff6ab246d875775af7affedcf6e2d5 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 5 Dec 2018 07:26:06 +0000
Subject: b43: remove set but not used variables 'tx_pwr_state,tmp2'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/wireless/broadcom/b43/phy_n.c: In function 'b43_nphy_op_recalc_txpower':
drivers/net/wireless/broadcom/b43/phy_n.c:5898:7: warning:
 variable 'tx_pwr_state' set but not used [-Wunused-but-set-variable]

drivers/net/wireless/broadcom/b43/phy_n.c:6047:20: warning:
 variable 'tmp2' set but not used [-Wunused-but-set-variable]

'tx_pwr_state' never used since introduction in commit
8615eb2870f1 ("b43: N-PHY: support setting custom TX power")

'tmp2' not used any more since commit c002831a07dd ("b43: N-PHY: use helper
for checking IPA")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/b43/phy_n.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/wireless/broadcom/b43/phy_n.c b/drivers/net/wireless/broadcom/b43/phy_n.c
index 7d300362b933..77d7cd5563c4 100644
--- a/drivers/net/wireless/broadcom/b43/phy_n.c
+++ b/drivers/net/wireless/broadcom/b43/phy_n.c
@@ -5895,7 +5895,6 @@ static enum b43_txpwr_result b43_nphy_op_recalc_txpower(struct b43_wldev *dev,
 	struct ieee80211_channel *channel = dev->wl->hw->conf.chandef.chan;
 	struct b43_ppr *ppr = &nphy->tx_pwr_max_ppr;
 	u8 max; /* qdBm */
-	bool tx_pwr_state;
 
 	if (nphy->tx_pwr_last_recalc_freq == channel->center_freq &&
 	    nphy->tx_pwr_last_recalc_limit == phy->desired_txpower)
@@ -5931,7 +5930,6 @@ static enum b43_txpwr_result b43_nphy_op_recalc_txpower(struct b43_wldev *dev,
 	b43_ppr_apply_min(dev, ppr, INT_TO_Q52(8));
 
 	/* Apply */
-	tx_pwr_state = nphy->txpwrctrl;
 	b43_mac_suspend(dev);
 	b43_nphy_tx_power_ctl_setup(dev);
 	if (dev->dev->core_rev == 11 || dev->dev->core_rev == 12) {
@@ -6044,7 +6042,6 @@ static int b43_phy_initn(struct b43_wldev *dev)
 	u8 tx_pwr_state;
 	struct nphy_txgains target;
 	u16 tmp;
-	enum nl80211_band tmp2;
 	bool do_rssi_cal;
 
 	u16 clip[2];
@@ -6138,7 +6135,6 @@ static int b43_phy_initn(struct b43_wldev *dev)
 		b43_phy_write(dev, B43_NPHY_DUP40_BL, 0x9A4);
 	}
 
-	tmp2 = b43_current_band(dev->wl);
 	if (b43_nphy_ipa(dev)) {
 		b43_phy_set(dev, B43_NPHY_PAPD_EN0, 0x1);
 		b43_phy_maskset(dev, B43_NPHY_EPS_TABLE_ADJ0, 0x007F,
-- 
cgit v1.2.3


From afbb1947db94eacc5a13302eee88a9772fb78935 Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Thu, 29 Nov 2018 18:48:10 +0800
Subject: rtl818x: fix potential use after free

entry is released via usb_put_urb just after calling usb_submit_urb.
However, entry is used if the submission fails, resulting in a use after
free bug. The patch fixes this.

Signed-off-by: Pan Bian <bianpan2016@163.com>
ACKed-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
index cec37787ecf8..1a2ea8b47714 100644
--- a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
+++ b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
@@ -444,12 +444,13 @@ static int rtl8187_init_urbs(struct ieee80211_hw *dev)
 		skb_queue_tail(&priv->rx_queue, skb);
 		usb_anchor_urb(entry, &priv->anchored);
 		ret = usb_submit_urb(entry, GFP_KERNEL);
-		usb_put_urb(entry);
 		if (ret) {
 			skb_unlink(skb, &priv->rx_queue);
 			usb_unanchor_urb(entry);
+			usb_put_urb(entry);
 			goto err;
 		}
+		usb_put_urb(entry);
 	}
 	return ret;
 
-- 
cgit v1.2.3


From e3e454b7047a8bb11c0311ab1708e040481a6044 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 6 Dec 2018 12:06:08 +0000
Subject: rtlwifi: rtl8821ae: remove set but not used variable 'type' in
 translate_rx_signal_stuff

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c: In function 'translate_rx_signal_stuff':
drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c:309:6: warning:
 variable 'type' set but not used [-Wunused-but-set-variable]

It never used since commit 21e4b0726dc6 ("rtlwifi: rtl8821ae: Move driver from
staging to regular tree")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
index b01c3c5e21c7..0f2b7c619918 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
@@ -306,14 +306,12 @@ static void translate_rx_signal_stuff(struct ieee80211_hw *hw,
 	u8 *praddr;
 	u8 *psaddr;
 	__le16 fc;
-	u16 type;
 	bool packet_matchbssid, packet_toself, packet_beacon;
 
 	tmp_buf = skb->data + pstatus->rx_drvinfo_size + pstatus->rx_bufshift;
 
 	hdr = (struct ieee80211_hdr *)tmp_buf;
 	fc = hdr->frame_control;
-	type = WLAN_FC_GET_TYPE(hdr->frame_control);
 	praddr = hdr->addr1;
 	psaddr = ieee80211_get_SA(hdr);
 	ether_addr_copy(pstatus->psaddr, psaddr);
-- 
cgit v1.2.3


From 9f8c1c5712954f9d8877ac55b18adbdf03e51e1f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 12 Dec 2018 10:45:38 +0100
Subject: bpf: remove obsolete prog->aux sanitation in bpf_insn_prepare_dump

This logic is not needed anymore since we got rid of the verifier
rewrite that was using prog->aux address in f6069b9aa993 ("bpf:
fix redirect to map under tail calls").

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/syscall.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7f1410d6fbe9..6ae062f1cf20 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2032,13 +2032,6 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
 			insns[i + 1].imm = 0;
 			continue;
 		}
-
-		if (!bpf_dump_raw_ok() &&
-		    imm == (unsigned long)prog->aux) {
-			insns[i].imm = 0;
-			insns[i + 1].imm = 0;
-			continue;
-		}
 	}
 
 	return insns;
-- 
cgit v1.2.3


From 28c1272914613b6c5a0129d6d502c790d4f23d6c Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Thu, 13 Dec 2018 13:19:01 -0800
Subject: selftests/bpf: Fix sk lookup usage in test_sock_addr

Semantic of netns_id argument of bpf_sk_lookup_tcp and bpf_sk_lookup_udp
was changed (fixed) in f71c6143c203. Corresponding changes have to be
applied to all call sites in selftests. The patch fixes corresponding
call sites in test_sock_addr test: pass BPF_F_CURRENT_NETNS instead of 0
in netns_id argument.

Fixes: f71c6143c203 ("bpf: Support sk lookup in netns with id 0")
Reported-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Joe Stringer <joe@wand.net.nz>
Tested-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/connect4_prog.c | 6 ++++--
 tools/testing/selftests/bpf/connect6_prog.c | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/connect4_prog.c b/tools/testing/selftests/bpf/connect4_prog.c
index b8395f3c43e9..1fd244d35ba9 100644
--- a/tools/testing/selftests/bpf/connect4_prog.c
+++ b/tools/testing/selftests/bpf/connect4_prog.c
@@ -35,9 +35,11 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
 	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
 		return 0;
 	else if (ctx->type == SOCK_STREAM)
-		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv4), 0, 0);
+		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv4),
+				       BPF_F_CURRENT_NETNS, 0);
 	else
-		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv4), 0, 0);
+		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv4),
+				       BPF_F_CURRENT_NETNS, 0);
 
 	if (!sk)
 		return 0;
diff --git a/tools/testing/selftests/bpf/connect6_prog.c b/tools/testing/selftests/bpf/connect6_prog.c
index 25f5dc7b7aa0..26397ab7b3c7 100644
--- a/tools/testing/selftests/bpf/connect6_prog.c
+++ b/tools/testing/selftests/bpf/connect6_prog.c
@@ -47,9 +47,11 @@ int connect_v6_prog(struct bpf_sock_addr *ctx)
 	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
 		return 0;
 	else if (ctx->type == SOCK_STREAM)
-		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv6), 0, 0);
+		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv6),
+				       BPF_F_CURRENT_NETNS, 0);
 	else
-		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv6), 0, 0);
+		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv6),
+				       BPF_F_CURRENT_NETNS, 0);
 
 	if (!sk)
 		return 0;
-- 
cgit v1.2.3


From 8e350ce1f78ef5a7d8250b9b4bdf733ce2fa5b1f Mon Sep 17 00:00:00 2001
From: Florent Fourcot <florent.fourcot@wifirst.fr>
Date: Tue, 27 Nov 2018 17:15:56 +0100
Subject: netfilter: ipset: fix ip_set_byindex function

New function added by "Introduction of new commands and protocol
version 7" is not working, since we return skb2 to user

Signed-off-by: Victorien Molle <victorien.molle@wifirst.fr>
Signed-off-by: Florent Fourcot <florent.fourcot@wifirst.fr>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipset/ip_set_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 1c3614aca34e..e3113aa1a975 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1949,7 +1949,7 @@ static int ip_set_byindex(struct net *net, struct sock *ctnl,
 	if (!nlh2)
 		goto nlmsg_failure;
 	if (nla_put_u8(skb2, IPSET_ATTR_PROTOCOL, protocol(attr)) ||
-	    nla_put_string(skb, IPSET_ATTR_SETNAME, set->name))
+	    nla_put_string(skb2, IPSET_ATTR_SETNAME, set->name))
 		goto nla_put_failure;
 	nlmsg_end(skb2, nlh2);
 
-- 
cgit v1.2.3


From 00ec3ab0601280d00978ac4245a62b470cfa81bb Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@gmx.us>
Date: Mon, 10 Dec 2018 14:39:38 +0100
Subject: netfilter: ipset: replace a strncpy() with strscpy()

To make overflows as obvious as possible and to prevent code from blithely
proceeding with a truncated string. This also has a side-effect to fix a
compilation warning when using GCC 8.2.1.

net/netfilter/ipset/ip_set_core.c: In function 'ip_set_sockfn_get':
net/netfilter/ipset/ip_set_core.c:2027:3: warning: 'strncpy' writing 32 bytes into a region of size 2 overflows the destination [-Wstringop-overflow=]

Signed-off-by: Qian Cai <cai@gmx.us>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipset/ip_set_core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index e3113aa1a975..45a257695bef 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -2154,9 +2154,11 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 		}
 		nfnl_lock(NFNL_SUBSYS_IPSET);
 		set = ip_set(inst, req_get->set.index);
-		strncpy(req_get->set.name, set ? set->name : "",
-			IPSET_MAXNAMELEN);
+		ret = strscpy(req_get->set.name, set ? set->name : "",
+			      IPSET_MAXNAMELEN);
 		nfnl_unlock(NFNL_SUBSYS_IPSET);
+		if (ret < 0)
+			goto done;
 		goto copy;
 	}
 	default:
-- 
cgit v1.2.3


From 3a37a9636cf3a1af2621a33f7eef8a2a3da81030 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:30 +0000
Subject: net: dev: Add extack argument to dev_set_mac_address()

A follow-up patch will add a notifier type NETDEV_PRE_CHANGEADDR, which
allows vetoing of MAC address changes. One prominent path to that
notification is through dev_set_mac_address(). Therefore give this
function an extack argument, so that it can be packed together with the
notification. Thus a textual reason for rejection (or a warning) can be
communicated back to the user.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_alb.c        |  9 +++++----
 drivers/net/bonding/bond_main.c       | 15 ++++++++-------
 drivers/net/hyperv/netvsc_drv.c       |  4 ++--
 drivers/net/macvlan.c                 |  4 ++--
 drivers/net/tap.c                     |  2 +-
 drivers/net/team/team.c               |  2 +-
 drivers/net/tun.c                     |  2 +-
 drivers/usb/gadget/function/u_ether.c |  2 +-
 include/linux/netdevice.h             |  3 ++-
 net/core/dev.c                        |  4 +++-
 net/core/dev_ioctl.c                  |  2 +-
 net/core/rtnetlink.c                  |  2 +-
 net/ieee802154/nl-phy.c               |  2 +-
 13 files changed, 29 insertions(+), 24 deletions(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index e82108c917a6..9431127bbc60 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1031,7 +1031,7 @@ static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[],
 	 */
 	memcpy(ss.__data, addr, len);
 	ss.ss_family = dev->type;
-	if (dev_set_mac_address(dev, (struct sockaddr *)&ss)) {
+	if (dev_set_mac_address(dev, (struct sockaddr *)&ss, NULL)) {
 		netdev_err(slave->bond->dev, "dev_set_mac_address of dev %s failed! ALB mode requires that the base driver support setting the hw address also when the network device's interface is open\n",
 			   dev->name);
 		return -EOPNOTSUPP;
@@ -1250,7 +1250,7 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
 		bond_hw_addr_copy(tmp_addr, slave->dev->dev_addr,
 				  slave->dev->addr_len);
 
-		res = dev_set_mac_address(slave->dev, addr);
+		res = dev_set_mac_address(slave->dev, addr, NULL);
 
 		/* restore net_device's hw address */
 		bond_hw_addr_copy(slave->dev->dev_addr, tmp_addr,
@@ -1273,7 +1273,7 @@ unwind:
 		bond_hw_addr_copy(tmp_addr, rollback_slave->dev->dev_addr,
 				  rollback_slave->dev->addr_len);
 		dev_set_mac_address(rollback_slave->dev,
-				    (struct sockaddr *)&ss);
+				    (struct sockaddr *)&ss, NULL);
 		bond_hw_addr_copy(rollback_slave->dev->dev_addr, tmp_addr,
 				  rollback_slave->dev->addr_len);
 	}
@@ -1732,7 +1732,8 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 				  bond->dev->addr_len);
 		ss.ss_family = bond->dev->type;
 		/* we don't care if it can't change its mac, best effort */
-		dev_set_mac_address(new_slave->dev, (struct sockaddr *)&ss);
+		dev_set_mac_address(new_slave->dev, (struct sockaddr *)&ss,
+				    NULL);
 
 		bond_hw_addr_copy(new_slave->dev->dev_addr, tmp_addr,
 				  new_slave->dev->addr_len);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 6b34dbefa7dd..06039be63034 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -680,7 +680,7 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 		}
 
 		rv = dev_set_mac_address(new_active->dev,
-					 (struct sockaddr *)&ss);
+					 (struct sockaddr *)&ss, NULL);
 		if (rv) {
 			netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
 				   -rv, new_active->dev->name);
@@ -695,7 +695,7 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 		ss.ss_family = old_active->dev->type;
 
 		rv = dev_set_mac_address(old_active->dev,
-					 (struct sockaddr *)&ss);
+					 (struct sockaddr *)&ss, NULL);
 		if (rv)
 			netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
 				   -rv, new_active->dev->name);
@@ -1527,7 +1527,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		 */
 		memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
 		ss.ss_family = slave_dev->type;
-		res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
+		res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss,
+					  extack);
 		if (res) {
 			netdev_dbg(bond_dev, "Error %d calling set_mac_address\n", res);
 			goto err_restore_mtu;
@@ -1818,7 +1819,7 @@ err_restore_mac:
 		bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr,
 				  new_slave->dev->addr_len);
 		ss.ss_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
+		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL);
 	}
 
 err_restore_mtu:
@@ -1999,7 +2000,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 		bond_hw_addr_copy(ss.__data, slave->perm_hwaddr,
 				  slave->dev->addr_len);
 		ss.ss_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
+		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL);
 	}
 
 	if (unregister)
@@ -3732,7 +3733,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 
 	bond_for_each_slave(bond, slave, iter) {
 		netdev_dbg(bond_dev, "slave %p %s\n", slave, slave->dev->name);
-		res = dev_set_mac_address(slave->dev, addr);
+		res = dev_set_mac_address(slave->dev, addr, NULL);
 		if (res) {
 			/* TODO: consider downing the slave
 			 * and retry ?
@@ -3761,7 +3762,7 @@ unwind:
 			break;
 
 		tmp_res = dev_set_mac_address(rollback_slave->dev,
-					      (struct sockaddr *)&tmp_ss);
+					      (struct sockaddr *)&tmp_ss, NULL);
 		if (tmp_res) {
 			netdev_dbg(bond_dev, "unwind err %d dev %s\n",
 				   tmp_res, rollback_slave->dev->name);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 18b5584d6377..91ed15ea5883 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1247,7 +1247,7 @@ static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
 		return -ENODEV;
 
 	if (vf_netdev) {
-		err = dev_set_mac_address(vf_netdev, addr);
+		err = dev_set_mac_address(vf_netdev, addr, NULL);
 		if (err)
 			return err;
 	}
@@ -1258,7 +1258,7 @@ static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
 	} else if (vf_netdev) {
 		/* rollback change on VF */
 		memcpy(addr->sa_data, ndev->dev_addr, ETH_ALEN);
-		dev_set_mac_address(vf_netdev, addr);
+		dev_set_mac_address(vf_netdev, addr, NULL);
 	}
 
 	return err;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 0da3d36b283b..fc726ce4c164 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -744,7 +744,7 @@ static int macvlan_set_mac_address(struct net_device *dev, void *p)
 
 	if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
 		macvlan_set_addr_change(vlan->port);
-		return dev_set_mac_address(vlan->lowerdev, addr);
+		return dev_set_mac_address(vlan->lowerdev, addr, NULL);
 	}
 
 	if (macvlan_addr_busy(vlan->port, addr->sa_data))
@@ -1213,7 +1213,7 @@ static void macvlan_port_destroy(struct net_device *dev)
 
 		sa.sa_family = port->dev->type;
 		memcpy(&sa.sa_data, port->perm_addr, port->dev->addr_len);
-		dev_set_mac_address(port->dev, &sa);
+		dev_set_mac_address(port->dev, &sa, NULL);
 	}
 
 	kfree(port);
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index f03004f37eca..443b2694130c 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1113,7 +1113,7 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
 			rtnl_unlock();
 			return -ENOLINK;
 		}
-		ret = dev_set_mac_address(tap->dev, &sa);
+		ret = dev_set_mac_address(tap->dev, &sa, NULL);
 		tap_put_tap_dev(tap);
 		rtnl_unlock();
 		return ret;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 93576e0240dd..afd9d25d1992 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -59,7 +59,7 @@ static int __set_port_dev_addr(struct net_device *port_dev,
 
 	memcpy(addr.__data, dev_addr, port_dev->addr_len);
 	addr.ss_family = port_dev->type;
-	return dev_set_mac_address(port_dev, (struct sockaddr *)&addr);
+	return dev_set_mac_address(port_dev, (struct sockaddr *)&addr, NULL);
 }
 
 static int team_port_set_orig_dev_addr(struct team_port *port)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ea528248d7d0..72577aa35b06 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -3202,7 +3202,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		tun_debug(KERN_DEBUG, tun, "set hw address: %pM\n",
 			  ifr.ifr_hwaddr.sa_data);
 
-		ret = dev_set_mac_address(tun->dev, &ifr.ifr_hwaddr);
+		ret = dev_set_mac_address(tun->dev, &ifr.ifr_hwaddr, NULL);
 		break;
 
 	case TUNGETSNDBUF:
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 0f026d445e31..737bd77a575d 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -879,7 +879,7 @@ int gether_register_netdev(struct net_device *net)
 	sa.sa_family = net->type;
 	memcpy(sa.sa_data, dev->dev_mac, ETH_ALEN);
 	rtnl_lock();
-	status = dev_set_mac_address(net, &sa);
+	status = dev_set_mac_address(net, &sa, NULL);
 	rtnl_unlock();
 	if (status)
 		pr_warn("cannot set self ethernet address: %d\n", status);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 36ca5f50f822..d89875ec21ac 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3628,7 +3628,8 @@ int dev_set_mtu_ext(struct net_device *dev, int mtu,
 int dev_set_mtu(struct net_device *, int);
 int dev_change_tx_queue_len(struct net_device *, unsigned long);
 void dev_set_group(struct net_device *, int);
-int dev_set_mac_address(struct net_device *, struct sockaddr *);
+int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
+			struct netlink_ext_ack *extack);
 int dev_change_carrier(struct net_device *, bool new_carrier);
 int dev_get_phys_port_id(struct net_device *dev,
 			 struct netdev_phys_item_id *ppid);
diff --git a/net/core/dev.c b/net/core/dev.c
index 754284873355..7250a3a73fa4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7759,10 +7759,12 @@ EXPORT_SYMBOL(dev_set_group);
  *	dev_set_mac_address - Change Media Access Control Address
  *	@dev: device
  *	@sa: new address
+ *	@extack: netlink extended ack
  *
  *	Change the hardware (MAC) address of the device
  */
-int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
+int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
+			struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int err;
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index da273ec3cc57..31380fd5a4e2 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -246,7 +246,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 	case SIOCSIFHWADDR:
 		if (dev->addr_len > sizeof(struct sockaddr))
 			return -EINVAL;
-		return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
+		return dev_set_mac_address(dev, &ifr->ifr_hwaddr, NULL);
 
 	case SIOCSIFHWBROADCAST:
 		if (ifr->ifr_hwaddr.sa_family != dev->type)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 3b6e551f9e69..f8bdb8adab2c 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2444,7 +2444,7 @@ static int do_setlink(const struct sk_buff *skb,
 		sa->sa_family = dev->type;
 		memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
 		       dev->addr_len);
-		err = dev_set_mac_address(dev, sa);
+		err = dev_set_mac_address(dev, sa, extack);
 		kfree(sa);
 		if (err)
 			goto errout;
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index b231e40f006a..0c25c0bcc4da 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -242,7 +242,7 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 		 * dev_set_mac_address require RTNL_LOCK
 		 */
 		rtnl_lock();
-		rc = dev_set_mac_address(dev, &addr);
+		rc = dev_set_mac_address(dev, &addr, NULL);
 		rtnl_unlock();
 		if (rc)
 			goto dev_unregister;
-- 
cgit v1.2.3


From 1570415f0810fce085066fb39827397452c3965a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:33 +0000
Subject: net: dev: Add NETDEV_PRE_CHANGEADDR

The NETDEV_CHANGEADDR notification is emitted after a device address
changes. Extending this message to allow vetoing is certainly possible,
but several other notification types have instead adopted a simple
two-stage approach: first a "pre" notification is sent to make sure all
interested parties are OK with a change that's about to be done. Then
the change is done, and afterwards a "post" notification is sent.

This dual approach is easier to use: when the change is vetoed, nothing
has changed yet, and it's therefore unnecessary to roll anything back.
Therefore adopt it for NETDEV_CHANGEADDR as well.

To that end, add NETDEV_PRE_CHANGEADDR and an info structure to go along
with it.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 8 +++++++-
 net/core/dev.c            | 1 +
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d89875ec21ac..1d5ad053ccf7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2450,7 +2450,8 @@ enum netdev_cmd {
 	NETDEV_REGISTER,
 	NETDEV_UNREGISTER,
 	NETDEV_CHANGEMTU,	/* notify after mtu change happened */
-	NETDEV_CHANGEADDR,
+	NETDEV_CHANGEADDR,	/* notify after the address change */
+	NETDEV_PRE_CHANGEADDR,	/* notify before the address change */
 	NETDEV_GOING_DOWN,
 	NETDEV_CHANGENAME,
 	NETDEV_FEAT_CHANGE,
@@ -2512,6 +2513,11 @@ struct netdev_notifier_changelowerstate_info {
 	void *lower_state_info; /* is lower dev state */
 };
 
+struct netdev_notifier_pre_changeaddr_info {
+	struct netdev_notifier_info info; /* must be first */
+	const unsigned char *dev_addr;
+};
+
 static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
 					     struct net_device *dev)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index 7250a3a73fa4..01497b7d1bdf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1589,6 +1589,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd)
 	N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
 	N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO)
 	N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
+	N(PRE_CHANGEADDR)
 	}
 #undef N
 	return "UNKNOWN_NETDEV_EVENT";
-- 
cgit v1.2.3


From d59cdf9475ad84d1f57cab1d162cf289702cfb15 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:35 +0000
Subject: net: dev: Issue NETDEV_PRE_CHANGEADDR

When a device address is about to be changed, or an address added to the
list of device HW addresses, it is necessary to ensure that all
interested parties can support the address. Therefore, send the
NETDEV_PRE_CHANGEADDR notification, and if anyone bails on it, do not
change the address.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  2 ++
 net/core/dev.c            | 24 ++++++++++++++++++++++++
 net/core/dev_addr_lists.c |  3 +++
 3 files changed, 29 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1d5ad053ccf7..811632d4d8b1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3634,6 +3634,8 @@ int dev_set_mtu_ext(struct net_device *dev, int mtu,
 int dev_set_mtu(struct net_device *, int);
 int dev_change_tx_queue_len(struct net_device *, unsigned long);
 void dev_set_group(struct net_device *, int);
+int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
+			      struct netlink_ext_ack *extack);
 int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 			struct netlink_ext_ack *extack);
 int dev_change_carrier(struct net_device *, bool new_carrier);
diff --git a/net/core/dev.c b/net/core/dev.c
index 01497b7d1bdf..ed9aa4a91f1f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7756,6 +7756,27 @@ void dev_set_group(struct net_device *dev, int new_group)
 }
 EXPORT_SYMBOL(dev_set_group);
 
+/**
+ *	dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR.
+ *	@dev: device
+ *	@addr: new address
+ *	@extack: netlink extended ack
+ */
+int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
+			      struct netlink_ext_ack *extack)
+{
+	struct netdev_notifier_pre_changeaddr_info info = {
+		.info.dev = dev,
+		.info.extack = extack,
+		.dev_addr = addr,
+	};
+	int rc;
+
+	rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info);
+	return notifier_to_errno(rc);
+}
+EXPORT_SYMBOL(dev_pre_changeaddr_notify);
+
 /**
  *	dev_set_mac_address - Change Media Access Control Address
  *	@dev: device
@@ -7776,6 +7797,9 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 		return -EINVAL;
 	if (!netif_device_present(dev))
 		return -ENODEV;
+	err = dev_pre_changeaddr_notify(dev, sa->sa_data, extack);
+	if (err)
+		return err;
 	err = ops->ndo_set_mac_address(dev, sa);
 	if (err)
 		return err;
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 81a8cd4ea3bd..a6723b306717 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -498,6 +498,9 @@ int dev_addr_add(struct net_device *dev, const unsigned char *addr,
 
 	ASSERT_RTNL();
 
+	err = dev_pre_changeaddr_notify(dev, addr, NULL);
+	if (err)
+		return err;
 	err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type);
 	if (!err)
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
-- 
cgit v1.2.3


From ca935da7f41bb2186f2a007ae183b27f37c8f5a3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:37 +0000
Subject: net: bridge: Issue NETDEV_PRE_CHANGEADDR

When a port is attached to a bridge, the address of the bridge in
question may change as well. Even if it would not change at this
point (because the current bridge address is lower), it might end up
changing later as a result of detach of another port, which can't be
vetoed.

Therefore issue NETDEV_PRE_CHANGEADDR regardless of whether the address
will be used at this point or not, and make sure all involved parties
would agree with the change.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_if.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 3b945d6369c4..41f0a696a65f 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -650,6 +650,15 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
 	if (br_fdb_insert(br, p, dev->dev_addr, 0))
 		netdev_err(dev, "failed insert local address bridge forwarding table\n");
 
+	if (br->dev->addr_assign_type != NET_ADDR_SET) {
+		/* Ask for permission to use this MAC address now, even if we
+		 * don't end up choosing it below.
+		 */
+		err = dev_pre_changeaddr_notify(br->dev, dev->dev_addr, extack);
+		if (err)
+			goto err7;
+	}
+
 	err = nbp_vlan_init(p, extack);
 	if (err) {
 		netdev_err(dev, "failed to initialize vlan filtering on this port\n");
-- 
cgit v1.2.3


From b89df65c5e2ab2ce674997e44e87452f4d2e9b05 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:39 +0000
Subject: net: bridge: Handle NETDEV_PRE_CHANGEADDR from ports

When a port device seeks approval of a potential new MAC address, make
sure that should the bridge device end up using this address, all
interested parties would agree with it.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/bridge/br.c b/net/bridge/br.c
index 4e7cd993ce94..a5174e5001d8 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -31,6 +31,8 @@
  */
 static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr)
 {
+	struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr);
+	struct netdev_notifier_pre_changeaddr_info *prechaddr_info;
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct net_bridge_port *p;
 	struct net_bridge *br;
@@ -56,6 +58,17 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v
 		br_mtu_auto_adjust(br);
 		break;
 
+	case NETDEV_PRE_CHANGEADDR:
+		if (br->dev->addr_assign_type == NET_ADDR_SET)
+			break;
+		prechaddr_info = ptr;
+		err = dev_pre_changeaddr_notify(br->dev,
+						prechaddr_info->dev_addr,
+						extack);
+		if (err)
+			return notifier_from_errno(err);
+		break;
+
 	case NETDEV_CHANGEADDR:
 		spin_lock_bh(&br->lock);
 		br_fdb_changeaddr(p, dev->dev_addr);
-- 
cgit v1.2.3


From 61345fab484b97cca47149c90396c74ac76072f5 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:41 +0000
Subject: net: ipvlan: Issue NETDEV_PRE_CHANGEADDR

A NETDEV_CHANGEADDR event implies a change of address of each of the
IPVLANs of this IPVLAN device. Therefore propagate NETDEV_PRE_CHANGEADDR
to all the IPVLANs.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 723a3f663c06..19bdde60680c 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -759,10 +759,13 @@ EXPORT_SYMBOL_GPL(ipvlan_link_register);
 static int ipvlan_device_event(struct notifier_block *unused,
 			       unsigned long event, void *ptr)
 {
+	struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr);
+	struct netdev_notifier_pre_changeaddr_info *prechaddr_info;
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct ipvl_dev *ipvlan, *next;
 	struct ipvl_port *port;
 	LIST_HEAD(lst_kill);
+	int err;
 
 	if (!netif_is_ipvlan_port(dev))
 		return NOTIFY_DONE;
@@ -818,6 +821,17 @@ static int ipvlan_device_event(struct notifier_block *unused,
 			ipvlan_adjust_mtu(ipvlan, dev);
 		break;
 
+	case NETDEV_PRE_CHANGEADDR:
+		prechaddr_info = ptr;
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+			err = dev_pre_changeaddr_notify(ipvlan->dev,
+						    prechaddr_info->dev_addr,
+						    extack);
+			if (err)
+				return notifier_from_errno(err);
+		}
+		break;
+
 	case NETDEV_CHANGEADDR:
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
 			ether_addr_copy(ipvlan->dev->dev_addr, dev->dev_addr);
-- 
cgit v1.2.3


From b9245914282c3ddf86e60ff5dbb3136c2298f842 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:44 +0000
Subject: net: bonding: Give bond_set_dev_addr() a return value

Before NETDEV_CHANGEADDR, bond driver should emit NETDEV_PRE_CHANGEADDR,
and allow consumers to veto the address change. To propagate further the
return code from NETDEV_PRE_CHANGEADDR, give the function that
implements address change a return value.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 06039be63034..66d9a6c7b9c5 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -609,14 +609,15 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
  *
  * Should be called with RTNL held.
  */
-static void bond_set_dev_addr(struct net_device *bond_dev,
-			      struct net_device *slave_dev)
+static int bond_set_dev_addr(struct net_device *bond_dev,
+			     struct net_device *slave_dev)
 {
 	netdev_dbg(bond_dev, "bond_dev=%p slave_dev=%p slave_dev->name=%s slave_dev->addr_len=%d\n",
 		   bond_dev, slave_dev, slave_dev->name, slave_dev->addr_len);
 	memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len);
 	bond_dev->addr_assign_type = NET_ADDR_STOLEN;
 	call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
+	return 0;
 }
 
 static struct slave *bond_get_old_active(struct bonding *bond,
@@ -652,8 +653,12 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 
 	switch (bond->params.fail_over_mac) {
 	case BOND_FOM_ACTIVE:
-		if (new_active)
-			bond_set_dev_addr(bond->dev, new_active->dev);
+		if (new_active) {
+			rv = bond_set_dev_addr(bond->dev, new_active->dev);
+			if (rv)
+				netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
+					   -rv, bond->dev->name);
+		}
 		break;
 	case BOND_FOM_FOLLOW:
 		/* if new_active && old_active, swap them
@@ -1489,8 +1494,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	 * address to be the same as the slave's.
 	 */
 	if (!bond_has_slaves(bond) &&
-	    bond->dev->addr_assign_type == NET_ADDR_RANDOM)
-		bond_set_dev_addr(bond->dev, slave_dev);
+	    bond->dev->addr_assign_type == NET_ADDR_RANDOM) {
+		res = bond_set_dev_addr(bond->dev, slave_dev);
+		if (res)
+			goto err_undo_flags;
+	}
 
 	new_slave = bond_alloc_slave(bond);
 	if (!new_slave) {
@@ -3545,8 +3553,7 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 		break;
 	case BOND_SETHWADDR_OLD:
 	case SIOCBONDSETHWADDR:
-		bond_set_dev_addr(bond_dev, slave_dev);
-		res = 0;
+		res = bond_set_dev_addr(bond_dev, slave_dev);
 		break;
 	case BOND_CHANGE_ACTIVE_OLD:
 	case SIOCBONDCHANGEACTIVE:
-- 
cgit v1.2.3


From 1caf40dec1e2098d5f0bef3a627f0b08b2f65f9c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:46 +0000
Subject: net: bonding: Issue NETDEV_PRE_CHANGEADDR

Give interested parties an opportunity to veto an impending HW address
change.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 66d9a6c7b9c5..a9d597f28023 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -612,8 +612,14 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
 static int bond_set_dev_addr(struct net_device *bond_dev,
 			     struct net_device *slave_dev)
 {
+	int err;
+
 	netdev_dbg(bond_dev, "bond_dev=%p slave_dev=%p slave_dev->name=%s slave_dev->addr_len=%d\n",
 		   bond_dev, slave_dev, slave_dev->name, slave_dev->addr_len);
+	err = dev_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL);
+	if (err)
+		return err;
+
 	memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len);
 	bond_dev->addr_assign_type = NET_ADDR_STOLEN;
 	call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
-- 
cgit v1.2.3


From 9735f2d2fe2c0078684c1ed17e53b7640af1c21b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:48 +0000
Subject: mlxsw: spectrum_router: Generalize
 mlxsw_sp_netdevice_router_port_event()

Prepare mlxsw_sp_netdevice_router_port_event() for handling of
NETDEV_PRE_CHANGEADDR. Split out the part that deals with the actual
changes and call it for the two events currently handled.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  3 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 37 ++++++++++++++++------
 3 files changed, 30 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 6929dbf04a1f..0fb7772c7a00 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -5326,7 +5326,7 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *nb,
 		err = mlxsw_sp_netdevice_ipip_ul_event(mlxsw_sp, dev,
 						       event, ptr);
 	else if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU)
-		err = mlxsw_sp_netdevice_router_port_event(dev);
+		err = mlxsw_sp_netdevice_router_port_event(dev, event, ptr);
 	else if (mlxsw_sp_is_vrf_event(event, ptr))
 		err = mlxsw_sp_netdevice_vrf_event(dev, event, ptr);
 	else if (mlxsw_sp_port_dev_check(dev))
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 41a5de4a0965..373d648b0976 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -454,7 +454,8 @@ union mlxsw_sp_l3addr {
 
 int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp);
-int mlxsw_sp_netdevice_router_port_event(struct net_device *dev);
+int mlxsw_sp_netdevice_router_port_event(struct net_device *dev,
+					 unsigned long event, void *ptr);
 void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
 			      const struct net_device *macvlan_dev);
 int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index f49a220582da..0cf641ae5e9a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6863,20 +6863,14 @@ static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
 }
 
-int mlxsw_sp_netdevice_router_port_event(struct net_device *dev)
+static int
+mlxsw_sp_router_port_change_event(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_rif *rif)
 {
-	struct mlxsw_sp *mlxsw_sp;
-	struct mlxsw_sp_rif *rif;
+	struct net_device *dev = rif->dev;
 	u16 fid_index;
 	int err;
 
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		return 0;
-
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!rif)
-		return 0;
 	fid_index = mlxsw_sp_fid_index(rif->fid);
 
 	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, fid_index, false);
@@ -6920,6 +6914,29 @@ err_rif_edit:
 	return err;
 }
 
+int mlxsw_sp_netdevice_router_port_event(struct net_device *dev,
+					 unsigned long event, void *ptr)
+{
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_rif *rif;
+
+	mlxsw_sp = mlxsw_sp_lower_get(dev);
+	if (!mlxsw_sp)
+		return 0;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!rif)
+		return 0;
+
+	switch (event) {
+	case NETDEV_CHANGEMTU: /* fall through */
+	case NETDEV_CHANGEADDR:
+		return mlxsw_sp_router_port_change_event(mlxsw_sp, rif);
+	}
+
+	return 0;
+}
+
 static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp,
 				  struct net_device *l3_dev,
 				  struct netlink_ext_ack *extack)
-- 
cgit v1.2.3


From 9329b8162b95200d046b7ef5c9830af9dc74d2ca Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:50 +0000
Subject: mlxsw: spectrum: Add mlxsw_sp.mac_mask

The Spectrum hardware demands that all router interfaces in the system
have the same first 38 resp. 36 bits of MAC address: the former limit
holds on Spectrum, the latter on Spectrum-2. Add a field that refers to
the required prefix mask and initialize in mlxsw_sp1_init() and
mlxsw_sp2_init().

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 9 +++++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 1 +
 2 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 0fb7772c7a00..955f7bbe1986 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -65,6 +65,13 @@ static const char mlxsw_sp1_driver_name[] = "mlxsw_spectrum";
 static const char mlxsw_sp2_driver_name[] = "mlxsw_spectrum2";
 static const char mlxsw_sp_driver_version[] = "1.0";
 
+static const unsigned char mlxsw_sp1_mac_mask[ETH_ALEN] = {
+	0xff, 0xff, 0xff, 0xff, 0xfc, 0x00
+};
+static const unsigned char mlxsw_sp2_mac_mask[ETH_ALEN] = {
+	0xff, 0xff, 0xff, 0xff, 0xf0, 0x00
+};
+
 /* tx_hdr_version
  * Tx header version.
  * Must be set to 1.
@@ -4083,6 +4090,7 @@ static int mlxsw_sp1_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->mr_tcam_ops = &mlxsw_sp1_mr_tcam_ops;
 	mlxsw_sp->acl_tcam_ops = &mlxsw_sp1_acl_tcam_ops;
 	mlxsw_sp->nve_ops_arr = mlxsw_sp1_nve_ops_arr;
+	mlxsw_sp->mac_mask = mlxsw_sp1_mac_mask;
 
 	return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info);
 }
@@ -4098,6 +4106,7 @@ static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->mr_tcam_ops = &mlxsw_sp2_mr_tcam_ops;
 	mlxsw_sp->acl_tcam_ops = &mlxsw_sp2_acl_tcam_ops;
 	mlxsw_sp->nve_ops_arr = mlxsw_sp2_nve_ops_arr;
+	mlxsw_sp->mac_mask = mlxsw_sp2_mac_mask;
 
 	return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 373d648b0976..64cae57bfbc8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -132,6 +132,7 @@ struct mlxsw_sp {
 	struct mlxsw_core *core;
 	const struct mlxsw_bus_info *bus_info;
 	unsigned char base_mac[ETH_ALEN];
+	const unsigned char *mac_mask;
 	struct mlxsw_sp_upper *lags;
 	int *port_to_module;
 	struct mlxsw_sp_sb *sb;
-- 
cgit v1.2.3


From 74bc99397438352bf063329bf22c7a7b4f7e8220 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:52 +0000
Subject: mlxsw: spectrum_router: Veto unsupported RIF MAC addresses

On NETDEV_PRE_CHANGEADDR, if the change is related to a RIF interface,
verify that it satisfies the criterion that all RIF interfaces have the
same MAC address prefix, as indicated by mlxsw_sp.mac_mask.

Additionally, besides explicit address changes, check that the address
of an interface for which a RIF is about to be added matches the
required pattern as well.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  4 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 49 ++++++++++++++++++++++
 2 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 955f7bbe1986..5fbb4b75f472 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -5334,7 +5334,9 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *nb,
 	else if (mlxsw_sp_netdev_is_ipip_ul(mlxsw_sp, dev))
 		err = mlxsw_sp_netdevice_ipip_ul_event(mlxsw_sp, dev,
 						       event, ptr);
-	else if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU)
+	else if (event == NETDEV_PRE_CHANGEADDR ||
+		 event == NETDEV_CHANGEADDR ||
+		 event == NETDEV_CHANGEMTU)
 		err = mlxsw_sp_netdevice_router_port_event(dev, event, ptr);
 	else if (mlxsw_sp_is_vrf_event(event, ptr))
 		err = mlxsw_sp_netdevice_vrf_event(dev, event, ptr);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 0cf641ae5e9a..b33ba8b66861 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6699,6 +6699,33 @@ static int mlxsw_sp_inetaddr_macvlan_event(struct net_device *macvlan_dev,
 	return 0;
 }
 
+static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp,
+					       struct net_device *dev,
+					       const unsigned char *dev_addr,
+					       struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_rif *rif;
+	int i;
+
+	/* A RIF is not created for macvlan netdevs. Their MAC is used to
+	 * populate the FDB
+	 */
+	if (netif_is_macvlan(dev))
+		return 0;
+
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
+		rif = mlxsw_sp->router->rifs[i];
+		if (rif && rif->dev != dev &&
+		    !ether_addr_equal_masked(rif->dev->dev_addr, dev_addr,
+					     mlxsw_sp->mac_mask)) {
+			NL_SET_ERR_MSG_MOD(extack, "All router interface MAC addresses must have the same prefix");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
 				     unsigned long event,
 				     struct netlink_ext_ack *extack)
@@ -6760,6 +6787,11 @@ int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
+	err = mlxsw_sp_router_port_check_rif_addr(mlxsw_sp, dev, dev->dev_addr,
+						  ivi->extack);
+	if (err)
+		goto out;
+
 	err = __mlxsw_sp_inetaddr_event(dev, event, ivi->extack);
 out:
 	return notifier_from_errno(err);
@@ -6841,6 +6873,11 @@ int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused,
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
+	err = mlxsw_sp_router_port_check_rif_addr(mlxsw_sp, dev, dev->dev_addr,
+						  i6vi->extack);
+	if (err)
+		goto out;
+
 	err = __mlxsw_sp_inetaddr_event(dev, event, i6vi->extack);
 out:
 	return notifier_from_errno(err);
@@ -6914,6 +6951,16 @@ err_rif_edit:
 	return err;
 }
 
+static int mlxsw_sp_router_port_pre_changeaddr_event(struct mlxsw_sp_rif *rif,
+			    struct netdev_notifier_pre_changeaddr_info *info)
+{
+	struct netlink_ext_ack *extack;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+	return mlxsw_sp_router_port_check_rif_addr(rif->mlxsw_sp, rif->dev,
+						   info->dev_addr, extack);
+}
+
 int mlxsw_sp_netdevice_router_port_event(struct net_device *dev,
 					 unsigned long event, void *ptr)
 {
@@ -6932,6 +6979,8 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev,
 	case NETDEV_CHANGEMTU: /* fall through */
 	case NETDEV_CHANGEADDR:
 		return mlxsw_sp_router_port_change_event(mlxsw_sp, rif);
+	case NETDEV_PRE_CHANGEADDR:
+		return mlxsw_sp_router_port_pre_changeaddr_event(rif, ptr);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 555afaae121ada40d10e538e888c6ecf3cd731eb Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:54 +0000
Subject: selftests: mlxsw: Test RIF MAC vetoing

Test that attempts to change address in a way that violates Spectrum
requirements are vetoed with extack.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/rtnetlink.sh       | 91 ++++++++++++++++++++++
 1 file changed, 91 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
new file mode 100755
index 000000000000..bc8b44c77108
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -0,0 +1,91 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test various interface configuration scenarios. Observe that configurations
+# deemed valid by mlxsw succeed, invalid configurations fail and that no traces
+# are produced. To prevent the test from passing in case traces are produced,
+# the user can set the 'kernel.panic_on_warn' and 'kernel.panic_on_oops'
+# sysctls in its environment.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	rif_set_addr_test
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+
+	ip link set dev $swp1 up
+	ip link set dev $swp2 up
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link set dev $swp2 down
+	ip link set dev $swp1 down
+}
+
+rif_set_addr_test()
+{
+	local swp1_mac=$(mac_get $swp1)
+	local swp2_mac=$(mac_get $swp2)
+
+	RET=0
+
+	# $swp1 and $swp2 likely got their IPv6 local addresses already, but
+	# here we need to test the transition to RIF.
+	ip addr flush dev $swp1
+	ip addr flush dev $swp2
+	sleep .1
+
+	ip addr add dev $swp1 192.0.2.1/28
+	check_err $?
+
+	ip link set dev $swp1 addr 00:11:22:33:44:55
+	check_err $?
+
+	# IP address enablement should be rejected if the MAC address prefix
+	# doesn't match other RIFs.
+	ip addr add dev $swp2 192.0.2.2/28 &>/dev/null
+	check_fail $? "IP address addition passed for a device with a wrong MAC"
+	ip addr add dev $swp2 192.0.2.2/28 2>&1 >/dev/null \
+	    | grep -q mlxsw_spectrum
+	check_err $? "no extack for IP address addition"
+
+	ip link set dev $swp2 addr 00:11:22:33:44:66
+	check_err $?
+	ip addr add dev $swp2 192.0.2.2/28 &>/dev/null
+	check_err $?
+
+	# Change of MAC address of a RIF should be forbidden if the new MAC
+	# doesn't share the prefix with other MAC addresses.
+	ip link set dev $swp2 addr 00:11:22:33:00:66 &>/dev/null
+	check_fail $? "change of MAC address passed for a wrong MAC"
+	ip link set dev $swp2 addr 00:11:22:33:00:66 2>&1 >/dev/null \
+	    | grep -q mlxsw_spectrum
+	check_err $? "no extack for MAC address change"
+
+	log_test "RIF - bad MAC change"
+
+	ip addr del dev $swp2 192.0.2.2/28
+	ip addr del dev $swp1 192.0.2.1/28
+
+	ip link set dev $swp2 addr $swp2_mac
+	ip link set dev $swp1 addr $swp1_mac
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 9651ee10ce3bc1e7a71242727711da93441602ac Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 13 Dec 2018 11:54:56 +0000
Subject: selftests: mlxsw: Test FID RIF MAC vetoing

When a FID RIF is created for a bridge with IP address, its MAC address
must obey the same requirements as other RIFs. Test that attempts to
change the address incompatibly by attaching a device are vetoed with
extack.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/rtnetlink.sh       | 79 ++++++++++++++++++++++
 1 file changed, 79 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index bc8b44c77108..7f78b96279f3 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -11,6 +11,8 @@ lib_dir=$(dirname $0)/../../../net/forwarding
 
 ALL_TESTS="
 	rif_set_addr_test
+	rif_inherit_bridge_addr_test
+	rif_non_inherit_bridge_addr_test
 "
 NUM_NETIFS=2
 source $lib_dir/lib.sh
@@ -81,6 +83,83 @@ rif_set_addr_test()
 	ip link set dev $swp1 addr $swp1_mac
 }
 
+rif_inherit_bridge_addr_test()
+{
+	RET=0
+
+	# Create first RIF
+	ip addr add dev $swp1 192.0.2.1/28
+	check_err $?
+
+	# Create a FID RIF
+	ip link add name br1 up type bridge vlan_filtering 0
+	ip link set dev $swp2 master br1
+	ip addr add dev br1 192.0.2.17/28
+	check_err $?
+
+	# Prepare a device with a low MAC address
+	ip link add name d up type dummy
+	ip link set dev d addr 00:11:22:33:44:55
+
+	# Attach the device to br1. That prompts bridge address change, which
+	# should be vetoed, thus preventing the attachment.
+	ip link set dev d master br1 &>/dev/null
+	check_fail $? "Device with low MAC was permitted to attach a bridge with RIF"
+	ip link set dev d master br1 2>&1 >/dev/null \
+	    | grep -q mlxsw_spectrum
+	check_err $? "no extack for bridge attach rejection"
+
+	ip link set dev $swp2 addr 00:11:22:33:44:55 &>/dev/null
+	check_fail $? "Changing swp2's MAC address permitted"
+	ip link set dev $swp2 addr 00:11:22:33:44:55 2>&1 >/dev/null \
+	    | grep -q mlxsw_spectrum
+	check_err $? "no extack for bridge port MAC address change rejection"
+
+	log_test "RIF - attach port with bad MAC to bridge"
+
+	ip link del dev d
+	ip link del dev br1
+	ip addr del dev $swp1 192.0.2.1/28
+}
+
+rif_non_inherit_bridge_addr_test()
+{
+	local swp2_mac=$(mac_get $swp2)
+
+	RET=0
+
+	# Create first RIF
+	ip addr add dev $swp1 192.0.2.1/28
+	check_err $?
+
+	# Create a FID RIF
+	ip link add name br1 up type bridge vlan_filtering 0
+	ip link set dev br1 addr $swp2_mac
+	ip link set dev $swp2 master br1
+	ip addr add dev br1 192.0.2.17/28
+	check_err $?
+
+	# Prepare a device with a low MAC address
+	ip link add name d up type dummy
+	ip link set dev d addr 00:11:22:33:44:55
+
+	# Attach the device to br1. Since the bridge address was set, it should
+	# work.
+	ip link set dev d master br1 &>/dev/null
+	check_err $? "Could not attach a device with low MAC to a bridge with RIF"
+
+	# Port MAC address change should be allowed for a bridge with set MAC.
+	ip link set dev $swp2 addr 00:11:22:33:44:55
+	check_err $? "Changing swp2's MAC address not permitted"
+
+	log_test "RIF - attach port with bad MAC to bridge with set MAC"
+
+	ip link set dev $swp2 addr $swp2_mac
+	ip link del dev d
+	ip link del dev br1
+	ip addr del dev $swp1 192.0.2.1/28
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
cgit v1.2.3


From 09b0b99007ff4e250a479de731d897bea34f0b4e Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Thu, 9 Aug 2018 13:51:08 +0300
Subject: iwlwifi: move common 9000 cfg parameters to common macro

The ht_params, nvm_ver, nvm_calib_ver and max_ht_ampdu_exponent
elements in 9000 devices are always the same.  Move them to the common
macro.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/9000.c | 79 ++-------------------------
 1 file changed, 6 insertions(+), 73 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
index d55fd23cafe6..baaaf2a5dc7b 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
@@ -157,17 +157,18 @@ static const struct iwl_tt_params iwl9000_tt_params = {
 	.min_umac_error_event_table = 0x800000,				\
 	.csr = &iwl_csr_v1,						\
 	.d3_debug_data_base_addr = 0x401000,				\
-	.d3_debug_data_length = 92 * 1024
+	.d3_debug_data_length = 92 * 1024,				\
+	.ht_params = &iwl9000_ht_params,				\
+	.nvm_ver = IWL9000_NVM_VERSION,					\
+	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,			\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+
 
 const struct iwl_cfg iwl9160_2ac_cfg = {
 	.name = "Intel(R) Dual Band Wireless AC 9160",
 	.fw_name_pre = IWL9260A_FW_PRE,
 	.fw_name_pre_b_or_c_step = IWL9260B_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 const struct iwl_cfg iwl9260_2ac_cfg = {
@@ -175,10 +176,6 @@ const struct iwl_cfg iwl9260_2ac_cfg = {
 	.fw_name_pre = IWL9260A_FW_PRE,
 	.fw_name_pre_b_or_c_step = IWL9260B_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 const struct iwl_cfg iwl9260_killer_2ac_cfg = {
@@ -186,10 +183,6 @@ const struct iwl_cfg iwl9260_killer_2ac_cfg = {
 	.fw_name_pre = IWL9260A_FW_PRE,
 	.fw_name_pre_b_or_c_step = IWL9260B_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 const struct iwl_cfg iwl9270_2ac_cfg = {
@@ -197,10 +190,6 @@ const struct iwl_cfg iwl9270_2ac_cfg = {
 	.fw_name_pre = IWL9260A_FW_PRE,
 	.fw_name_pre_b_or_c_step = IWL9260B_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 const struct iwl_cfg iwl9460_2ac_cfg = {
@@ -208,10 +197,6 @@ const struct iwl_cfg iwl9460_2ac_cfg = {
 	.fw_name_pre = IWL9260A_FW_PRE,
 	.fw_name_pre_b_or_c_step = IWL9260B_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 const struct iwl_cfg iwl9460_2ac_cfg_soc = {
@@ -220,10 +205,6 @@ const struct iwl_cfg iwl9460_2ac_cfg_soc = {
 	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.integrated = true,
 	.soc_latency = 5000,
 };
@@ -234,10 +215,6 @@ const struct iwl_cfg iwl9461_2ac_cfg_soc = {
 		.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 		.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 		IWL_DEVICE_9000,
-		.ht_params = &iwl9000_ht_params,
-		.nvm_ver = IWL9000_NVM_VERSION,
-		.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-		.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 		.integrated = true,
 		.soc_latency = 5000,
 };
@@ -248,10 +225,6 @@ const struct iwl_cfg iwl9462_2ac_cfg_soc = {
 		.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 		.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 		IWL_DEVICE_9000,
-		.ht_params = &iwl9000_ht_params,
-		.nvm_ver = IWL9000_NVM_VERSION,
-		.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-		.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 		.integrated = true,
 		.soc_latency = 5000,
 };
@@ -261,10 +234,6 @@ const struct iwl_cfg iwl9560_2ac_cfg = {
 	.fw_name_pre = IWL9260A_FW_PRE,
 	.fw_name_pre_b_or_c_step = IWL9260B_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 const struct iwl_cfg iwl9560_2ac_cfg_soc = {
@@ -273,10 +242,6 @@ const struct iwl_cfg iwl9560_2ac_cfg_soc = {
 	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.integrated = true,
 	.soc_latency = 5000,
 };
@@ -287,10 +252,6 @@ const struct iwl_cfg iwl9560_killer_2ac_cfg_soc = {
 	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.integrated = true,
 	.soc_latency = 5000,
 };
@@ -301,10 +262,6 @@ const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc = {
 	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.integrated = true,
 	.soc_latency = 5000,
 };
@@ -315,10 +272,6 @@ const struct iwl_cfg iwl9460_2ac_cfg_shared_clk = {
 	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.integrated = true,
 	.soc_latency = 5000,
 	.extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
@@ -330,10 +283,6 @@ const struct iwl_cfg iwl9461_2ac_cfg_shared_clk = {
 	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.integrated = true,
 	.soc_latency = 5000,
 	.extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
@@ -345,10 +294,6 @@ const struct iwl_cfg iwl9462_2ac_cfg_shared_clk = {
 	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.integrated = true,
 	.soc_latency = 5000,
 	.extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
@@ -360,10 +305,6 @@ const struct iwl_cfg iwl9560_2ac_cfg_shared_clk = {
 	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.integrated = true,
 	.soc_latency = 5000,
 	.extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
@@ -375,10 +316,6 @@ const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk = {
 	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.integrated = true,
 	.soc_latency = 5000,
 	.extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
@@ -390,10 +327,6 @@ const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk = {
 	.fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
 	.fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
 	IWL_DEVICE_9000,
-	.ht_params = &iwl9000_ht_params,
-	.nvm_ver = IWL9000_NVM_VERSION,
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.integrated = true,
 	.soc_latency = 5000,
 	.extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
-- 
cgit v1.2.3


From 7a14c23dcdee68782acb90be29590ad683c3aeb4 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Wed, 13 Jun 2018 15:24:13 +0300
Subject: iwlwifi: dbg: dump data according to the new ini TLVs

When ini TLVs are loaded, dump data according to the
stored configuration.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c        | 263 ++++++++++++++++++++-
 drivers/net/wireless/intel/iwlwifi/fw/dbg.h        |   2 +-
 drivers/net/wireless/intel/iwlwifi/fw/error-dump.h |  17 ++
 drivers/net/wireless/intel/iwlwifi/iwl-prph.h      |   6 +
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c        |  12 +-
 .../wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c   |  13 +-
 .../net/wireless/intel/iwlwifi/pcie/ctxt-info.c    |   2 +-
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h |   5 +
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c    |  71 ++++--
 9 files changed, 355 insertions(+), 36 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 76050cc3532a..58771e253396 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -605,6 +605,28 @@ static void iwl_fw_dump_mem(struct iwl_fw_runtime *fwrt,
 	IWL_DEBUG_INFO(fwrt, "WRT memory dump. Type=%u\n", dump_mem->type);
 }
 
+static void iwl_fw_dump_named_mem(struct iwl_fw_runtime *fwrt,
+				  struct iwl_fw_error_dump_data **dump_data,
+				  u32 len, u32 ofs, u8 *name, u8 name_len)
+{
+	struct iwl_fw_error_dump_named_mem *dump_mem;
+
+	if (!len)
+		return;
+
+	(*dump_data)->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM);
+	(*dump_data)->len = cpu_to_le32(len + sizeof(*dump_mem));
+	dump_mem = (void *)(*dump_data)->data;
+	dump_mem->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM_NAMED_MEM);
+	dump_mem->offset = cpu_to_le32(ofs);
+	dump_mem->name_len = name_len;
+	memcpy(dump_mem->name, name, name_len);
+	iwl_trans_read_mem_bytes(fwrt->trans, ofs, dump_mem->data, len);
+	*dump_data = iwl_fw_error_next_data(*dump_data);
+
+	IWL_DEBUG_INFO(fwrt, "WRT memory dump. Type=%u\n", dump_mem->type);
+}
+
 #define ADD_LEN(len, item_len, const_len) \
 	do {size_t item = item_len; len += (!!item) * const_len + item; } \
 	while (0)
@@ -928,6 +950,238 @@ out:
 	return dump_file;
 }
 
+static void iwl_dump_prph_ini(struct iwl_trans *trans,
+			      struct iwl_fw_error_dump_data **data,
+			      struct iwl_fw_ini_region_cfg *reg)
+{
+	struct iwl_fw_error_dump_prph *prph;
+	unsigned long flags;
+	u32 i, size = le32_to_cpu(reg->num_regions);
+
+	IWL_DEBUG_INFO(trans, "WRT PRPH dump\n");
+
+	if (!iwl_trans_grab_nic_access(trans, &flags))
+		return;
+
+	for (i = 0; i < size; i++) {
+		(*data)->type = cpu_to_le32(IWL_FW_ERROR_DUMP_PRPH);
+		(*data)->len = cpu_to_le32(le32_to_cpu(reg->size) +
+					   sizeof(*prph));
+		prph = (void *)(*data)->data;
+		prph->prph_start = reg->start_addr[i];
+		prph->data[0] = cpu_to_le32(iwl_read_prph_no_grab(trans,
+								  le32_to_cpu(prph->prph_start)));
+		*data = iwl_fw_error_next_data(*data);
+	}
+	iwl_trans_release_nic_access(trans, &flags);
+}
+
+static void iwl_dump_csr_ini(struct iwl_trans *trans,
+			     struct iwl_fw_error_dump_data **data,
+			     struct iwl_fw_ini_region_cfg *reg)
+{
+	int i, num = le32_to_cpu(reg->num_regions);
+	u32 size = le32_to_cpu(reg->size);
+
+	IWL_DEBUG_INFO(trans, "WRT CSR dump\n");
+
+	for (i = 0; i < num; i++) {
+		u32 add = le32_to_cpu(reg->start_addr[i]);
+		__le32 *val;
+		int j;
+
+		(*data)->type = cpu_to_le32(IWL_FW_ERROR_DUMP_CSR);
+		(*data)->len = cpu_to_le32(size);
+		val = (void *)(*data)->data;
+
+		for (j = 0; j < size; j += 4)
+			*val++ = cpu_to_le32(iwl_trans_read32(trans, j + add));
+
+		*data = iwl_fw_error_next_data(*data);
+	}
+}
+
+static int iwl_fw_ini_get_trigger_len(struct iwl_fw_runtime *fwrt,
+				      struct iwl_fw_ini_trigger *trigger)
+{
+	int i, num, size = 0, hdr_len = sizeof(struct iwl_fw_error_dump_data);
+
+	if (!trigger || !trigger->num_regions)
+		return 0;
+
+	num = le32_to_cpu(trigger->num_regions);
+	for (i = 0; i < num; i++) {
+		u32 reg_id = le32_to_cpu(trigger->data[i]);
+		struct iwl_fw_ini_region_cfg *reg;
+		enum iwl_fw_ini_region_type type;
+		u32 num_entries;
+
+		if (WARN_ON(reg_id >= ARRAY_SIZE(fwrt->dump.active_regs)))
+			continue;
+
+		reg = fwrt->dump.active_regs[reg_id].reg;
+		if (WARN(!reg, "Unassigned region %d\n", reg_id))
+			continue;
+
+		type = le32_to_cpu(reg->region_type);
+		num_entries = le32_to_cpu(reg->num_regions);
+
+		switch (type) {
+		case IWL_FW_INI_REGION_DEVICE_MEMORY:
+			size += hdr_len +
+				sizeof(struct iwl_fw_error_dump_named_mem) +
+				le32_to_cpu(reg->size);
+			break;
+		case IWL_FW_INI_REGION_PERIPHERY_MAC:
+		case IWL_FW_INI_REGION_PERIPHERY_PHY:
+		case IWL_FW_INI_REGION_PERIPHERY_AUX:
+			size += num_entries *
+				(hdr_len +
+				 sizeof(struct iwl_fw_error_dump_prph) +
+				 sizeof(u32));
+			break;
+		case IWL_FW_INI_REGION_TXF:
+			size += iwl_fw_txf_len(fwrt, &fwrt->smem_cfg);
+			break;
+		case IWL_FW_INI_REGION_RXF:
+			size += iwl_fw_rxf_len(fwrt, &fwrt->smem_cfg);
+			break;
+		case IWL_FW_INI_REGION_PAGING:
+			if (!iwl_fw_dbg_is_paging_enabled(fwrt))
+				break;
+			size += fwrt->num_of_paging_blk *
+				(hdr_len +
+				 sizeof(struct iwl_fw_error_dump_paging) +
+				 PAGING_BLOCK_SIZE);
+			break;
+		case IWL_FW_INI_REGION_CSR:
+			size += num_entries *
+				(hdr_len + le32_to_cpu(reg->size));
+			break;
+		case IWL_FW_INI_REGION_DRAM_BUFFER:
+			/* Transport takes care of DRAM dumping */
+		case IWL_FW_INI_REGION_INTERNAL_BUFFER:
+		case IWL_FW_INI_REGION_DRAM_IMR:
+			/* Undefined yet */
+		default:
+			break;
+		}
+	}
+	return size;
+}
+
+static void iwl_fw_ini_dump_trigger(struct iwl_fw_runtime *fwrt,
+				    struct iwl_fw_ini_trigger *trigger,
+				    struct iwl_fw_error_dump_data **data,
+				    u32 *dump_mask)
+{
+	int i, num = le32_to_cpu(trigger->num_regions);
+
+	for (i = 0; i < num; i++) {
+		u32 reg_id = le32_to_cpu(trigger->data[i]);
+		enum iwl_fw_ini_region_type type;
+		struct iwl_fw_ini_region_cfg *reg;
+
+		if (reg_id >= ARRAY_SIZE(fwrt->dump.active_regs))
+			continue;
+
+		reg = fwrt->dump.active_regs[reg_id].reg;
+		/* Don't warn, get_trigger_len already warned */
+		if (!reg)
+			continue;
+
+		type = le32_to_cpu(reg->region_type);
+		switch (type) {
+		case IWL_FW_INI_REGION_DEVICE_MEMORY:
+			if (WARN_ON(le32_to_cpu(reg->num_regions) > 1))
+				continue;
+			iwl_fw_dump_named_mem(fwrt, data,
+					      le32_to_cpu(reg->size),
+					      le32_to_cpu(reg->start_addr[0]),
+					      reg->name,
+					      le32_to_cpu(reg->name_len));
+			break;
+		case IWL_FW_INI_REGION_PERIPHERY_MAC:
+		case IWL_FW_INI_REGION_PERIPHERY_PHY:
+		case IWL_FW_INI_REGION_PERIPHERY_AUX:
+			iwl_dump_prph_ini(fwrt->trans, data, reg);
+			break;
+		case IWL_FW_INI_REGION_DRAM_BUFFER:
+			*dump_mask |= IWL_FW_ERROR_DUMP_FW_MONITOR;
+			break;
+		case IWL_FW_INI_REGION_PAGING:
+			if (iwl_fw_dbg_is_paging_enabled(fwrt))
+				iwl_dump_paging(fwrt, data);
+			else
+				*dump_mask |= IWL_FW_ERROR_DUMP_PAGING;
+			break;
+		case IWL_FW_INI_REGION_TXF:
+			iwl_fw_dump_txf(fwrt, data);
+			break;
+		case IWL_FW_INI_REGION_RXF:
+			iwl_fw_dump_rxf(fwrt, data);
+			break;
+		case IWL_FW_INI_REGION_CSR:
+			iwl_dump_csr_ini(fwrt->trans, data, reg);
+			break;
+		case IWL_FW_INI_REGION_DRAM_IMR:
+		case IWL_FW_INI_REGION_INTERNAL_BUFFER:
+			/* This is undefined yet */
+		default:
+			break;
+		}
+	}
+}
+
+static struct iwl_fw_error_dump_file *
+_iwl_fw_error_ini_dump(struct iwl_fw_runtime *fwrt,
+		       struct iwl_fw_dump_ptrs *fw_error_dump,
+		       u32 *dump_mask)
+{
+	int size, id = le32_to_cpu(fwrt->dump.desc->trig_desc.type);
+	struct iwl_fw_error_dump_data *dump_data;
+	struct iwl_fw_error_dump_file *dump_file;
+	struct iwl_fw_ini_trigger *trigger, *ext;
+
+	if (id == FW_DBG_TRIGGER_FW_ASSERT)
+		id = IWL_FW_TRIGGER_ID_FW_ASSERT;
+	else if (id == FW_DBG_TRIGGER_USER)
+		id = IWL_FW_TRIGGER_ID_USER_TRIGGER;
+	else if (id < FW_DBG_TRIGGER_MAX)
+		return NULL;
+
+	if (WARN_ON(id >= ARRAY_SIZE(fwrt->dump.active_trigs)))
+		return NULL;
+
+	trigger = fwrt->dump.active_trigs[id].conf;
+	ext = fwrt->dump.active_trigs[id].conf_ext;
+
+	size = sizeof(*dump_file);
+	size += iwl_fw_ini_get_trigger_len(fwrt, trigger);
+	size += iwl_fw_ini_get_trigger_len(fwrt, ext);
+
+	if (!size)
+		return NULL;
+
+	dump_file = vzalloc(size);
+	if (!dump_file)
+		return NULL;
+
+	fw_error_dump->fwrt_ptr = dump_file;
+
+	dump_file->barker = cpu_to_le32(IWL_FW_ERROR_DUMP_BARKER);
+	dump_data = (void *)dump_file->data;
+	dump_file->file_len = cpu_to_le32(size);
+
+	*dump_mask = 0;
+	if (trigger)
+		iwl_fw_ini_dump_trigger(fwrt, trigger, &dump_data, dump_mask);
+	if (ext)
+		iwl_fw_ini_dump_trigger(fwrt, ext, &dump_data, dump_mask);
+
+	return dump_file;
+}
+
 void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 {
 	struct iwl_fw_dump_ptrs *fw_error_dump;
@@ -948,13 +1202,18 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	if (!fw_error_dump)
 		goto out;
 
-	dump_file = _iwl_fw_error_dump(fwrt, fw_error_dump);
+	if (fwrt->trans->ini_valid)
+		dump_file = _iwl_fw_error_ini_dump(fwrt, fw_error_dump,
+						   &dump_mask);
+	else
+		dump_file = _iwl_fw_error_dump(fwrt, fw_error_dump);
+
 	if (!dump_file) {
 		kfree(fw_error_dump);
 		goto out;
 	}
 
-	if (fwrt->dump.monitor_only)
+	if (!fwrt->trans->ini_valid && fwrt->dump.monitor_only)
 		dump_mask &= IWL_FW_ERROR_DUMP_FW_MONITOR;
 
 	fw_error_dump->trans_ptr = iwl_trans_dump_data(fwrt->trans, dump_mask);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index ab81ea8b636f..324ee063224d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -329,7 +329,7 @@ void iwl_fw_error_dump_wk(struct work_struct *work);
 
 static inline bool iwl_fw_dbg_type_on(struct iwl_fw_runtime *fwrt, u32 type)
 {
-	return (fwrt->fw->dbg.dump_mask & BIT(type));
+	return (fwrt->fw->dbg.dump_mask & BIT(type) || fwrt->trans->ini_valid);
 }
 
 static inline bool iwl_fw_dbg_is_d3_debug_enabled(struct iwl_fw_runtime *fwrt)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
index 6fede174c664..cefafc9a082f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
@@ -249,6 +249,7 @@ struct iwl_fw_error_dump_prph {
 enum iwl_fw_error_dump_mem_type {
 	IWL_FW_ERROR_DUMP_MEM_SRAM,
 	IWL_FW_ERROR_DUMP_MEM_SMEM,
+	IWL_FW_ERROR_DUMP_MEM_NAMED_MEM = 10,
 };
 
 /**
@@ -263,6 +264,22 @@ struct iwl_fw_error_dump_mem {
 	u8 data[];
 };
 
+/**
+ * struct iwl_fw_error_dump_named_mem - chunk of memory
+ * @type: &enum iwl_fw_error_dump_mem_type
+ * @offset: the offset from which the memory was read
+ * @name_len: name length
+ * @name: file name
+ * @data: the content of the memory
+ */
+struct iwl_fw_error_dump_named_mem {
+	__le32 type;
+	__le32 offset;
+	u8 name_len;
+	u8 name[32];
+	u8 data[];
+};
+
 /**
  * struct iwl_fw_error_dump_rb - content of an Receive Buffer
  * @index: the index of the Receive Buffer in the Rx queue
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
index 2084c63dc670..9d89b7d7f9fa 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
@@ -362,6 +362,12 @@
 #define MON_BUFF_END_ADDR		(0xa03c40)
 #define MON_BUFF_WRPTR			(0xa03c44)
 #define MON_BUFF_CYCLE_CNT		(0xa03c48)
+/* FW monitor family 8000 and on */
+#define MON_BUFF_BASE_ADDR_VER2		(0xa03c3c)
+#define MON_BUFF_END_ADDR_VER2		(0xa03c20)
+#define MON_BUFF_WRPTR_VER2		(0xa03c24)
+#define MON_BUFF_CYCLE_CNT_VER2		(0xa03c28)
+#define MON_BUFF_SHIFT_VER2		(0x8)
 
 #define MON_DMARB_RD_CTL_ADDR		(0xa03c60)
 #define MON_DMARB_RD_DATA_ADDR		(0xa03c5c)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index c5168abe107c..443a7df684bd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1050,11 +1050,13 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	if (ret)
 		IWL_ERR(mvm, "Failed to initialize Smart Fifo\n");
 
-	mvm->fwrt.dump.conf = FW_DBG_INVALID;
-	/* if we have a destination, assume EARLY START */
-	if (mvm->fw->dbg.dest_tlv)
-		mvm->fwrt.dump.conf = FW_DBG_START_FROM_ALIVE;
-	iwl_fw_start_dbg_conf(&mvm->fwrt, FW_DBG_START_FROM_ALIVE);
+	if (!mvm->trans->ini_valid) {
+		mvm->fwrt.dump.conf = FW_DBG_INVALID;
+		/* if we have a destination, assume EARLY START */
+		if (mvm->fw->dbg.dest_tlv)
+			mvm->fwrt.dump.conf = FW_DBG_START_FROM_ALIVE;
+		iwl_fw_start_dbg_conf(&mvm->fwrt, FW_DBG_START_FROM_ALIVE);
+	}
 
 	ret = iwl_send_tx_ant_cfg(mvm, iwl_mvm_get_valid_tx_ant(mvm));
 	if (ret)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
index 05ed4fb88e0c..ceb3aa03d561 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
@@ -94,11 +94,14 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 		cpu_to_le64(trans_pcie->rxq->bd_dma);
 
 	/* Configure debug, for integration */
-	iwl_pcie_alloc_fw_monitor(trans, 0);
-	prph_sc_ctrl->hwm_cfg.hwm_base_addr =
-		cpu_to_le64(trans->fw_mon[0].physical);
-	prph_sc_ctrl->hwm_cfg.hwm_size =
-		cpu_to_le32(trans->fw_mon[0].size);
+	if (!trans->ini_valid)
+		iwl_pcie_alloc_fw_monitor(trans, 0);
+	if (trans->num_blocks) {
+		prph_sc_ctrl->hwm_cfg.hwm_base_addr =
+			cpu_to_le64(trans->fw_mon[0].physical);
+		prph_sc_ctrl->hwm_cfg.hwm_size =
+			cpu_to_le32(trans->fw_mon[0].size);
+	}
 
 	/* allocate ucode sections in dram and set addresses */
 	ret = iwl_pcie_init_fw_sec(trans, fw, &prph_scratch->dram);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
index 6f45a0303ddd..7f4aaa810ea1 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -227,7 +227,7 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 	iwl_enable_interrupts(trans);
 
 	/* Configure debug, if exists */
-	if (trans->dbg_dest_tlv)
+	if (iwl_pcie_dbg_on(trans))
 		iwl_pcie_apply_destination(trans);
 
 	/* kick FW self load */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 0f816761ca45..d6fc6ce73e0a 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -1009,6 +1009,11 @@ static inline void __iwl_trans_pcie_set_bit(struct iwl_trans *trans,
 	__iwl_trans_pcie_set_bits_mask(trans, reg, mask, mask);
 }
 
+static inline bool iwl_pcie_dbg_on(struct iwl_trans *trans)
+{
+	return (trans->dbg_dest_tlv || trans->ini_valid);
+}
+
 void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state);
 void iwl_trans_pcie_dump_regs(struct iwl_trans *trans);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 166bacc5ea54..f97aea5ffc44 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -924,6 +924,20 @@ void iwl_pcie_apply_destination(struct iwl_trans *trans)
 	const struct iwl_fw_dbg_dest_tlv_v1 *dest = trans->dbg_dest_tlv;
 	int i;
 
+	if (trans->ini_valid) {
+		if (!trans->num_blocks)
+			return;
+
+		iwl_write_prph(trans, MON_BUFF_BASE_ADDR_VER2,
+			       trans->fw_mon[0].physical >>
+			       MON_BUFF_SHIFT_VER2);
+		iwl_write_prph(trans, MON_BUFF_END_ADDR_VER2,
+			       (trans->fw_mon[0].physical +
+				trans->fw_mon[0].size - 256) >>
+			       MON_BUFF_SHIFT_VER2);
+		return;
+	}
+
 	IWL_INFO(trans, "Applying debug destination %s\n",
 		 get_fw_dbg_mode_string(dest->monitor_mode));
 
@@ -1026,7 +1040,7 @@ static int iwl_pcie_load_given_ucode(struct iwl_trans *trans,
 				       (trans->fw_mon[0].physical +
 					trans->fw_mon[0].size) >> 4);
 		}
-	} else if (trans->dbg_dest_tlv) {
+	} else if (iwl_pcie_dbg_on(trans)) {
 		iwl_pcie_apply_destination(trans);
 	}
 
@@ -1047,7 +1061,7 @@ static int iwl_pcie_load_given_ucode_8000(struct iwl_trans *trans,
 	IWL_DEBUG_FW(trans, "working with %s CPU\n",
 		     image->is_dual_cpus ? "Dual" : "Single");
 
-	if (trans->dbg_dest_tlv)
+	if (iwl_pcie_dbg_on(trans))
 		iwl_pcie_apply_destination(trans);
 
 	IWL_DEBUG_POWER(trans, "Original WFPM value = 0x%08X\n",
@@ -3015,6 +3029,34 @@ iwl_trans_pci_dump_marbh_monitor(struct iwl_trans *trans,
 	return monitor_len;
 }
 
+static void
+iwl_trans_pcie_dump_pointers(struct iwl_trans *trans,
+			     struct iwl_fw_error_dump_fw_mon *fw_mon_data)
+{
+	u32 base, write_ptr, wrap_cnt;
+
+	/* If there was a dest TLV - use the values from there */
+	if (trans->ini_valid) {
+		base = MON_BUFF_BASE_ADDR_VER2;
+		write_ptr = MON_BUFF_WRPTR_VER2;
+		wrap_cnt = MON_BUFF_CYCLE_CNT_VER2;
+	} else if (trans->dbg_dest_tlv) {
+		write_ptr = le32_to_cpu(trans->dbg_dest_tlv->write_ptr_reg);
+		wrap_cnt = le32_to_cpu(trans->dbg_dest_tlv->wrap_count);
+		base = le32_to_cpu(trans->dbg_dest_tlv->base_reg);
+	} else {
+		base = MON_BUFF_BASE_ADDR;
+		write_ptr = MON_BUFF_WRPTR;
+		wrap_cnt = MON_BUFF_CYCLE_CNT;
+	}
+	fw_mon_data->fw_mon_wr_ptr =
+		cpu_to_le32(iwl_read_prph(trans, write_ptr));
+	fw_mon_data->fw_mon_cycle_cnt =
+		cpu_to_le32(iwl_read_prph(trans, wrap_cnt));
+	fw_mon_data->fw_mon_base_ptr =
+		cpu_to_le32(iwl_read_prph(trans, base));
+}
+
 static u32
 iwl_trans_pcie_dump_monitor(struct iwl_trans *trans,
 			    struct iwl_fw_error_dump_data **data,
@@ -3024,30 +3066,14 @@ iwl_trans_pcie_dump_monitor(struct iwl_trans *trans,
 
 	if ((trans->num_blocks &&
 	     trans->cfg->device_family == IWL_DEVICE_FAMILY_7000) ||
-	    trans->dbg_dest_tlv) {
+	     (trans->dbg_dest_tlv && !trans->ini_valid) ||
+	     (trans->ini_valid && trans->num_blocks)) {
 		struct iwl_fw_error_dump_fw_mon *fw_mon_data;
-		u32 base, write_ptr, wrap_cnt;
-
-		/* If there was a dest TLV - use the values from there */
-		if (trans->dbg_dest_tlv) {
-			write_ptr =
-				le32_to_cpu(trans->dbg_dest_tlv->write_ptr_reg);
-			wrap_cnt = le32_to_cpu(trans->dbg_dest_tlv->wrap_count);
-			base = le32_to_cpu(trans->dbg_dest_tlv->base_reg);
-		} else {
-			base = MON_BUFF_BASE_ADDR;
-			write_ptr = MON_BUFF_WRPTR;
-			wrap_cnt = MON_BUFF_CYCLE_CNT;
-		}
 
 		(*data)->type = cpu_to_le32(IWL_FW_ERROR_DUMP_FW_MONITOR);
 		fw_mon_data = (void *)(*data)->data;
-		fw_mon_data->fw_mon_wr_ptr =
-			cpu_to_le32(iwl_read_prph(trans, write_ptr));
-		fw_mon_data->fw_mon_cycle_cnt =
-			cpu_to_le32(iwl_read_prph(trans, wrap_cnt));
-		fw_mon_data->fw_mon_base_ptr =
-			cpu_to_le32(iwl_read_prph(trans, base));
+
+		iwl_trans_pcie_dump_pointers(trans, fw_mon_data);
 
 		len += sizeof(**data) + sizeof(*fw_mon_data);
 		if (trans->num_blocks) {
@@ -3057,6 +3083,7 @@ iwl_trans_pcie_dump_monitor(struct iwl_trans *trans,
 
 			monitor_len = trans->fw_mon[0].size;
 		} else if (trans->dbg_dest_tlv->monitor_mode == SMEM_MODE) {
+			u32 base = le32_to_cpu(fw_mon_data->fw_mon_base_ptr);
 			/*
 			 * Update pointers to reflect actual values after
 			 * shifting
-- 
cgit v1.2.3


From fe1b7d6c28885642dc3dd59d3710ae2b283aa486 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Thu, 21 Jun 2018 09:42:12 +0300
Subject: iwlwifi: add support for triggering ini triggers

Add support for ini triggers.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c      | 59 +++++++++++++++++++++---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.h      | 39 ++++++++++++++--
 drivers/net/wireless/intel/iwlwifi/fw/runtime.h  |  2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c |  2 +-
 4 files changed, 91 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 58771e253396..b17298ba7dc0 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1329,10 +1329,10 @@ int iwl_fw_dbg_collect_desc(struct iwl_fw_runtime *fwrt,
 }
 IWL_EXPORT_SYMBOL(iwl_fw_dbg_collect_desc);
 
-int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
-		       enum iwl_fw_dbg_trigger trig,
-		       const char *str, size_t len,
-		       struct iwl_fw_dbg_trigger_tlv *trigger)
+int _iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
+			enum iwl_fw_dbg_trigger trig,
+			const char *str, size_t len,
+			struct iwl_fw_dbg_trigger_tlv *trigger)
 {
 	struct iwl_fw_dump_desc *desc;
 	unsigned int delay = 0;
@@ -1367,6 +1367,47 @@ int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
 
 	return iwl_fw_dbg_collect_desc(fwrt, desc, monitor_only, delay);
 }
+IWL_EXPORT_SYMBOL(_iwl_fw_dbg_collect);
+
+int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
+		       u32 id, const char *str, size_t len)
+{
+	struct iwl_fw_dump_desc *desc;
+	u32 occur, delay;
+
+	if (!fwrt->trans->ini_valid)
+		return _iwl_fw_dbg_collect(fwrt, id, str, len, NULL);
+
+	if (id == FW_DBG_TRIGGER_USER)
+		id = IWL_FW_TRIGGER_ID_USER_TRIGGER;
+
+	if (WARN_ON(!fwrt->dump.active_trigs[id].active))
+		return -EINVAL;
+
+	delay = le32_to_cpu(fwrt->dump.active_trigs[id].conf->ignore_consec);
+	occur = le32_to_cpu(fwrt->dump.active_trigs[id].conf->occurrences);
+	if (!occur)
+		return 0;
+
+	if (le32_to_cpu(fwrt->dump.active_trigs[id].conf->force_restart)) {
+		IWL_WARN(fwrt, "Force restart: trigger %d fired.\n", id);
+		iwl_force_nmi(fwrt->trans);
+		return 0;
+	}
+
+	desc = kzalloc(sizeof(*desc) + len, GFP_ATOMIC);
+	if (!desc)
+		return -ENOMEM;
+
+	occur--;
+	fwrt->dump.active_trigs[id].conf->occurrences = cpu_to_le32(occur);
+
+	desc->len = len;
+	desc->trig_desc.type = cpu_to_le32(id);
+	memcpy(desc->trig_desc.data, str, len);
+
+	return iwl_fw_dbg_collect_desc(fwrt, desc, true, delay);
+}
 IWL_EXPORT_SYMBOL(iwl_fw_dbg_collect);
 
 int iwl_fw_dbg_collect_trig(struct iwl_fw_runtime *fwrt,
@@ -1395,8 +1436,8 @@ int iwl_fw_dbg_collect_trig(struct iwl_fw_runtime *fwrt,
 		len = strlen(buf) + 1;
 	}
 
-	ret = iwl_fw_dbg_collect(fwrt, le32_to_cpu(trigger->id), buf, len,
-				 trigger);
+	ret = _iwl_fw_dbg_collect(fwrt, le32_to_cpu(trigger->id), buf, len,
+				  trigger);
 
 	if (ret)
 		return ret;
@@ -1668,6 +1709,12 @@ static void iwl_fw_dbg_update_triggers(struct iwl_fw_runtime *fwrt,
 			active->conf = trig;
 		}
 
+		/* Since zero means infinity - just set to -1 */
+		if (!le32_to_cpu(trig->occurrences))
+			trig->occurrences = cpu_to_le32(-1);
+		if (!le32_to_cpu(trig->ignore_consec))
+			trig->ignore_consec = cpu_to_le32(-1);
+
 		iter += sizeof(*trig) +
 			le32_to_cpu(trig->num_regions) * sizeof(__le32);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index 324ee063224d..c14e4614a2ea 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -108,10 +108,12 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt);
 int iwl_fw_dbg_collect_desc(struct iwl_fw_runtime *fwrt,
 			    const struct iwl_fw_dump_desc *desc,
 			    bool monitor_only, unsigned int delay);
+int _iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
+			enum iwl_fw_dbg_trigger trig,
+			const char *str, size_t len,
+			struct iwl_fw_dbg_trigger_tlv *trigger);
 int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
-		       enum iwl_fw_dbg_trigger trig,
-		       const char *str, size_t len,
-		       struct iwl_fw_dbg_trigger_tlv *trigger);
+		       u32 id, const char *str, size_t len);
 int iwl_fw_dbg_collect_trig(struct iwl_fw_runtime *fwrt,
 			    struct iwl_fw_dbg_trigger_tlv *trigger,
 			    const char *fmt, ...) __printf(3, 4);
@@ -213,6 +215,37 @@ _iwl_fw_dbg_trigger_on(struct iwl_fw_runtime *fwrt,
 	_iwl_fw_dbg_trigger_on((fwrt), (wdev), (id));		\
 })
 
+static inline bool
+_iwl_fw_ini_trigger_on(struct iwl_fw_runtime *fwrt,
+		       const enum iwl_fw_dbg_trigger id)
+{
+	struct iwl_fw_ini_active_triggers *trig = &fwrt->dump.active_trigs[id];
+	u32 ms;
+
+	if (!fwrt->trans->ini_valid)
+		return false;
+
+	if (!trig || !trig->active)
+		return false;
+
+	ms = le32_to_cpu(trig->conf->ignore_consec);
+	if (ms)
+		ms /= USEC_PER_MSEC;
+
+	if (iwl_fw_dbg_no_trig_window(fwrt, id, ms)) {
+		IWL_WARN(fwrt, "Trigger %d fired in no-collect window\n", id);
+		return false;
+	}
+
+	return true;
+}
+
+#define iwl_fw_ini_trigger_on(fwrt, wdev, id) ({		\
+	BUILD_BUG_ON(!__builtin_constant_p(id));		\
+	BUILD_BUG_ON((id) >= IWL_FW_TRIGGER_ID_NUM);		\
+	_iwl_fw_ini_trigger_on((fwrt), (wdev), (id));		\
+})
+
 static inline void
 _iwl_fw_dbg_trigger_simple_stop(struct iwl_fw_runtime *fwrt,
 				struct wireless_dev *wdev,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index 204ad5bfd506..77845de30c5c 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -138,7 +138,7 @@ struct iwl_fw_runtime {
 		u8 conf;
 
 		/* ts of the beginning of a non-collect fw dbg data period */
-		unsigned long non_collect_ts_start[FW_DBG_TRIGGER_MAX - 1];
+		unsigned long non_collect_ts_start[IWL_FW_TRIGGER_ID_NUM - 1];
 		u32 *d3_debug_data;
 		struct iwl_fw_ini_active_regs active_regs[IWL_FW_INI_MAX_REGION_ID];
 		struct iwl_fw_ini_active_triggers active_trigs[IWL_FW_TRIGGER_ID_NUM];
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 3b6b3d8fb961..52c361a6124c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1284,7 +1284,7 @@ static ssize_t iwl_dbgfs_fw_dbg_collect_write(struct iwl_mvm *mvm,
 		return 0;
 
 	iwl_fw_dbg_collect(&mvm->fwrt, FW_DBG_TRIGGER_USER, buf,
-			   (count - 1), NULL);
+			   (count - 1));
 
 	iwl_mvm_unref(mvm, IWL_MVM_REF_PRPH_WRITE);
 
-- 
cgit v1.2.3


From da2eb669c2c9cc8ece953d4d249791ce139dd05c Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Wed, 13 Jun 2018 15:22:48 +0300
Subject: iwlwifi: mvm: activate apply points

Call the previously introduced apply points entry
point when reaching an apply point.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c       | 4 ++++
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 2 ++
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 2 ++
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c     | 2 ++
 4 files changed, 10 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 443a7df684bd..3659a2c6500a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1018,10 +1018,14 @@ static int iwl_mvm_load_rt_fw(struct iwl_mvm *mvm)
 	if (ret)
 		return ret;
 
+	iwl_fw_dbg_apply_point(&mvm->fwrt, IWL_FW_INI_APPLY_EARLY);
+
 	ret = iwl_mvm_load_ucode_wait_alive(mvm, IWL_UCODE_REGULAR);
 	if (ret)
 		return ret;
 
+	iwl_fw_dbg_apply_point(&mvm->fwrt, IWL_FW_INI_APPLY_AFTER_ALIVE);
+
 	return iwl_init_paging(&mvm->fwrt, mvm->fwrt.cur_fw_img);
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index e049d34a3553..7779951a9533 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1532,6 +1532,8 @@ void iwl_mvm_rx_missed_beacons_notif(struct iwl_mvm *mvm,
 						   IEEE80211_IFACE_ITER_NORMAL,
 						   iwl_mvm_beacon_loss_iterator,
 						   mb);
+
+	iwl_fw_dbg_apply_point(&mvm->fwrt, IWL_FW_INI_APPLY_MISSED_BEACONS);
 }
 
 void iwl_mvm_rx_stored_beacon_notif(struct iwl_mvm *mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 675c52aa36a4..65c225a54076 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1129,6 +1129,8 @@ int __iwl_mvm_mac_start(struct iwl_mvm *mvm)
 	}
 	ret = iwl_mvm_up(mvm);
 
+	iwl_fw_dbg_apply_point(&mvm->fwrt, IWL_FW_INI_APPLY_POST_INIT);
+
 	if (ret && test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) {
 		/* Something went wrong - we need to finish some cleanup
 		 * that normally iwl_mvm_mac_restart_complete() below
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index cb376e869144..86d598d5b68f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1893,6 +1893,8 @@ void iwl_mvm_rx_umac_scan_complete_notif(struct iwl_mvm *mvm,
 		mvm->last_ebs_successful = false;
 
 	mvm->scan_uid_status[uid] = 0;
+
+	iwl_fw_dbg_apply_point(&mvm->fwrt, IWL_FW_INI_APPLY_SCAN_COMPLETE);
 }
 
 void iwl_mvm_rx_umac_scan_iter_complete_notif(struct iwl_mvm *mvm,
-- 
cgit v1.2.3


From 3e2b49d66f2eef7f01eb8b2c74589015c72c006c Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Thu, 16 Aug 2018 08:53:10 +0300
Subject: iwlwifi: don't define OTP_LOW_IMAGE_SIZE per family, but per size

Using OTP_LOW_IMAGE_SIZE_FAMILY_8000/9000/22000 only obfuscates the
actual values, since these 3 are the same.  Redefine the values per
size so it's easier to understand and compare the different
configurations.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/1000.c   | 2 +-
 drivers/net/wireless/intel/iwlwifi/cfg/2000.c   | 4 ++--
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c  | 4 ++--
 drivers/net/wireless/intel/iwlwifi/cfg/6000.c   | 6 +++---
 drivers/net/wireless/intel/iwlwifi/cfg/7000.c   | 2 +-
 drivers/net/wireless/intel/iwlwifi/cfg/8000.c   | 2 +-
 drivers/net/wireless/intel/iwlwifi/cfg/9000.c   | 2 +-
 drivers/net/wireless/intel/iwlwifi/iwl-config.h | 8 +++-----
 8 files changed, 14 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/1000.c b/drivers/net/wireless/intel/iwlwifi/cfg/1000.c
index 76b5ddb20248..1ff388b593ad 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/1000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/1000.c
@@ -48,7 +48,7 @@
 static const struct iwl_base_params iwl1000_base_params = {
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
-	.eeprom_size = OTP_LOW_IMAGE_SIZE,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
 	.pll_cfg = true,
 	.max_ll_items = OTP_MAX_LL_ITEMS_1000,
 	.shadow_ram_support = false,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/2000.c b/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
index e7e45846dd07..a6ec7ad39dcb 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
@@ -57,7 +57,7 @@
 #define IWL135_MODULE_FIRMWARE(api) IWL135_FW_PRE __stringify(api) ".ucode"
 
 static const struct iwl_base_params iwl2000_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_2x00,
@@ -71,7 +71,7 @@ static const struct iwl_base_params iwl2000_base_params = {
 
 
 static const struct iwl_base_params iwl2030_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_2x00,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index 8b2339165bca..2d395a4a5375 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -109,7 +109,7 @@
 #define NVM_HW_SECTION_NUM_FAMILY_22000		10
 
 static const struct iwl_base_params iwl_22000_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_22000,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
 	.num_of_queues = 512,
 	.max_tfd_queue_size = 256,
 	.shadow_ram_support = true,
@@ -121,7 +121,7 @@ static const struct iwl_base_params iwl_22000_base_params = {
 };
 
 static const struct iwl_base_params iwl_22560_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_22000,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
 	.num_of_queues = 512,
 	.max_tfd_queue_size = 65536,
 	.shadow_ram_support = true,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/6000.c b/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
index 30e62a7c9d52..fbb18d066cd0 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
@@ -66,7 +66,7 @@
 #define IWL6030_MODULE_FIRMWARE(api) IWL6030_FW_PRE __stringify(api) ".ucode"
 
 static const struct iwl_base_params iwl6000_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_6x00,
@@ -79,7 +79,7 @@ static const struct iwl_base_params iwl6000_base_params = {
 };
 
 static const struct iwl_base_params iwl6050_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_6x50,
@@ -92,7 +92,7 @@ static const struct iwl_base_params iwl6050_base_params = {
 };
 
 static const struct iwl_base_params iwl6000_g2_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_6x00,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
index c973bfaa3414..38d5db50b1ed 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
@@ -116,7 +116,7 @@
 #define NVM_HW_SECTION_NUM_FAMILY_7000		0
 
 static const struct iwl_base_params iwl7000_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_7000,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_16K,
 	.num_of_queues = 31,
 	.max_tfd_queue_size = 256,
 	.shadow_ram_support = true,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
index 348c40fcddcb..dd2785e65f80 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
@@ -97,7 +97,7 @@
 #define DEFAULT_NVM_FILE_FAMILY_8000C		"nvmData-8000C"
 
 static const struct iwl_base_params iwl8000_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_8000,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
 	.num_of_queues = 31,
 	.max_tfd_queue_size = 256,
 	.shadow_ram_support = true,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
index baaaf2a5dc7b..1bc12f8b716d 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
@@ -93,7 +93,7 @@
 #define NVM_HW_SECTION_NUM_FAMILY_9000		10
 
 static const struct iwl_base_params iwl9000_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_9000,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
 	.num_of_queues = 31,
 	.max_tfd_queue_size = 256,
 	.shadow_ram_support = true,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 5eb906a0d0d2..91861a9cbe57 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -265,11 +265,9 @@ struct iwl_tt_params {
 #define EEPROM_REGULATORY_BAND_NO_HT40		0
 
 /* lower blocks contain EEPROM image and calibration data */
-#define OTP_LOW_IMAGE_SIZE		(2 * 512 * sizeof(u16)) /* 2 KB */
-#define OTP_LOW_IMAGE_SIZE_FAMILY_7000	(16 * 512 * sizeof(u16)) /* 16 KB */
-#define OTP_LOW_IMAGE_SIZE_FAMILY_8000	(32 * 512 * sizeof(u16)) /* 32 KB */
-#define OTP_LOW_IMAGE_SIZE_FAMILY_9000	OTP_LOW_IMAGE_SIZE_FAMILY_8000
-#define OTP_LOW_IMAGE_SIZE_FAMILY_22000	OTP_LOW_IMAGE_SIZE_FAMILY_9000
+#define OTP_LOW_IMAGE_SIZE_2K		(2 * 512 * sizeof(u16))  /*  2 KB */
+#define OTP_LOW_IMAGE_SIZE_16K		(16 * 512 * sizeof(u16)) /* 16 KB */
+#define OTP_LOW_IMAGE_SIZE_32K		(32 * 512 * sizeof(u16)) /* 32 KB */
 
 struct iwl_eeprom_params {
 	const u8 regulatory_bands[7];
-- 
cgit v1.2.3


From 4aeaccd6b5f05a20fd3154581f1ec2e6793cd998 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Thu, 16 Aug 2018 09:01:31 +0300
Subject: iwlwifi: remove useless NVM_HW_SECTION_NUM_FAMILY_* macros

These macros are useless because each one of them is used only once
and the element they are assigned to is already pretty clear about
what they mean, "nvm_hw_section_num".

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c | 4 +---
 drivers/net/wireless/intel/iwlwifi/cfg/7000.c  | 4 +---
 drivers/net/wireless/intel/iwlwifi/cfg/8000.c  | 3 +--
 drivers/net/wireless/intel/iwlwifi/cfg/9000.c  | 4 +---
 4 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index 2d395a4a5375..157ff1f76ba6 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -106,8 +106,6 @@
 #define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \
 	IWL_QU_B_JF_B_FW_PRE __stringify(api) ".ucode"
 
-#define NVM_HW_SECTION_NUM_FAMILY_22000		10
-
 static const struct iwl_base_params iwl_22000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
 	.num_of_queues = 512,
@@ -142,7 +140,7 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 	.ucode_api_max = IWL_22000_UCODE_API_MAX,			\
 	.ucode_api_min = IWL_22000_UCODE_API_MIN,			\
 	.led_mode = IWL_LED_RF_STATE,					\
-	.nvm_hw_section_num = NVM_HW_SECTION_NUM_FAMILY_22000,		\
+	.nvm_hw_section_num = 10,					\
 	.non_shared_ant = ANT_B,					\
 	.dccm_offset = IWL_22000_DCCM_OFFSET,				\
 	.dccm_len = IWL_22000_DCCM_LEN,					\
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
index 38d5db50b1ed..5b4efa8ddffb 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
@@ -113,8 +113,6 @@
 #define IWL7265D_FW_PRE "iwlwifi-7265D-"
 #define IWL7265D_MODULE_FIRMWARE(api) IWL7265D_FW_PRE __stringify(api) ".ucode"
 
-#define NVM_HW_SECTION_NUM_FAMILY_7000		0
-
 static const struct iwl_base_params iwl7000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_16K,
 	.num_of_queues = 31,
@@ -159,7 +157,7 @@ static const struct iwl_ht_params iwl7000_ht_params = {
 	.device_family = IWL_DEVICE_FAMILY_7000,		\
 	.base_params = &iwl7000_base_params,			\
 	.led_mode = IWL_LED_RF_STATE,				\
-	.nvm_hw_section_num = NVM_HW_SECTION_NUM_FAMILY_7000,	\
+	.nvm_hw_section_num = 0,				\
 	.non_shared_ant = ANT_A,				\
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,	\
 	.dccm_offset = IWL7000_DCCM_OFFSET,			\
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
index dd2785e65f80..5b1da5206336 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
@@ -93,7 +93,6 @@
 #define IWL8265_MODULE_FIRMWARE(api) \
 	IWL8265_FW_PRE __stringify(api) ".ucode"
 
-#define NVM_HW_SECTION_NUM_FAMILY_8000		10
 #define DEFAULT_NVM_FILE_FAMILY_8000C		"nvmData-8000C"
 
 static const struct iwl_base_params iwl8000_base_params = {
@@ -139,7 +138,7 @@ static const struct iwl_tt_params iwl8000_tt_params = {
 	.device_family = IWL_DEVICE_FAMILY_8000,			\
 	.base_params = &iwl8000_base_params,				\
 	.led_mode = IWL_LED_RF_STATE,					\
-	.nvm_hw_section_num = NVM_HW_SECTION_NUM_FAMILY_8000,		\
+	.nvm_hw_section_num = 10,					\
 	.features = NETIF_F_RXCSUM,					\
 	.non_shared_ant = ANT_A,					\
 	.dccm_offset = IWL8260_DCCM_OFFSET,				\
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
index 1bc12f8b716d..b589b0e9d515 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
@@ -90,8 +90,6 @@
 #define IWL9260B_MODULE_FIRMWARE(api) \
 	IWL9260B_FW_PRE __stringify(api) ".ucode"
 
-#define NVM_HW_SECTION_NUM_FAMILY_9000		10
-
 static const struct iwl_base_params iwl9000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
 	.num_of_queues = 31,
@@ -137,7 +135,7 @@ static const struct iwl_tt_params iwl9000_tt_params = {
 	.device_family = IWL_DEVICE_FAMILY_9000,			\
 	.base_params = &iwl9000_base_params,				\
 	.led_mode = IWL_LED_RF_STATE,					\
-	.nvm_hw_section_num = NVM_HW_SECTION_NUM_FAMILY_9000,		\
+	.nvm_hw_section_num = 10,					\
 	.non_shared_ant = ANT_B,					\
 	.dccm_offset = IWL9000_DCCM_OFFSET,				\
 	.dccm_len = IWL9000_DCCM_LEN,					\
-- 
cgit v1.2.3


From 64866e5da1eabd0c52ff45029b245f5465920031 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Thu, 16 Aug 2018 09:23:08 +0300
Subject: iwlwifi: move iwl_nvm_check_version() into dvm

This function is only half-used by mvm (i.e. only the nvm_version part
matters, since the calibration version is irrelevant), so it's
pointless to export it from iwlwifi.  If mvm uses this function, it
has the additional complexity of setting the calib version to a bogus
value on all cfg structs.

To avoid this, move the function to dvm and make a simple comparison
of the nvm_version in mvm instead.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/dvm/main.c         | 17 +++++++++++++++++
 drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c | 19 -------------------
 drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h |  5 ++---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c           |  4 +++-
 4 files changed, 22 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index 1088ff036e13..c219bca5cff4 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -1224,6 +1224,23 @@ static int iwl_eeprom_init_hw_params(struct iwl_priv *priv)
 	return 0;
 }
 
+static int iwl_nvm_check_version(struct iwl_nvm_data *data,
+				 struct iwl_trans *trans)
+{
+	if (data->nvm_version >= trans->cfg->nvm_ver ||
+	    data->calib_version >= trans->cfg->nvm_calib_ver) {
+		IWL_DEBUG_INFO(trans, "device EEPROM VER=0x%x, CALIB=0x%x\n",
+			       data->nvm_version, data->calib_version);
+		return 0;
+	}
+
+	IWL_ERR(trans,
+		"Unsupported (too old) EEPROM VER=0x%x < 0x%x CALIB=0x%x < 0x%x\n",
+		data->nvm_version, trans->cfg->nvm_ver,
+		data->calib_version,  trans->cfg->nvm_calib_ver);
+	return -EINVAL;
+}
+
 static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 						 const struct iwl_cfg *cfg,
 						 const struct iwl_fw *fw,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
index 4e3422a1c7bb..75940ac406b9 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
@@ -927,22 +927,3 @@ iwl_parse_eeprom_data(struct device *dev, const struct iwl_cfg *cfg,
 	return NULL;
 }
 IWL_EXPORT_SYMBOL(iwl_parse_eeprom_data);
-
-/* helper functions */
-int iwl_nvm_check_version(struct iwl_nvm_data *data,
-			     struct iwl_trans *trans)
-{
-	if (data->nvm_version >= trans->cfg->nvm_ver ||
-	    data->calib_version >= trans->cfg->nvm_calib_ver) {
-		IWL_DEBUG_INFO(trans, "device EEPROM VER=0x%x, CALIB=0x%x\n",
-			       data->nvm_version, data->calib_version);
-		return 0;
-	}
-
-	IWL_ERR(trans,
-		"Unsupported (too old) EEPROM VER=0x%x < 0x%x CALIB=0x%x < 0x%x\n",
-		data->nvm_version, trans->cfg->nvm_ver,
-		data->calib_version,  trans->cfg->nvm_calib_ver);
-	return -EINVAL;
-}
-IWL_EXPORT_SYMBOL(iwl_nvm_check_version);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h
index d910bda087f7..2375d300a7cd 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Mobile Communications GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -28,6 +29,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Mobile Communications GmbH
+ * Copyright (C) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -117,9 +119,6 @@ struct iwl_nvm_data *
 iwl_parse_eeprom_data(struct device *dev, const struct iwl_cfg *cfg,
 		      const u8 *eeprom, size_t eeprom_size);
 
-int iwl_nvm_check_version(struct iwl_nvm_data *data,
-			  struct iwl_trans *trans);
-
 int iwl_init_sband_channels(struct iwl_nvm_data *data,
 			    struct ieee80211_supported_band *sband,
 			    int n_channels, enum nl80211_band band);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 3659a2c6500a..6adc1ead704a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -547,7 +547,9 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm)
 	if (mvm->nvm_file_name)
 		iwl_mvm_load_nvm_to_nic(mvm);
 
-	WARN_ON(iwl_nvm_check_version(mvm->nvm_data, mvm->trans));
+	WARN_ONCE(mvm->nvm_data->nvm_version < mvm->trans->cfg->nvm_ver,
+		  "Too old NVM version (0x%0x, required = 0x%0x)",
+		  mvm->nvm_data->nvm_version, mvm->trans->cfg->nvm_ver);
 
 	/*
 	 * abort after reading the nvm in case RF Kill is on, we will complete
-- 
cgit v1.2.3


From cc2af963f5dac19e1f0a9725c52927be98a80193 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Thu, 16 Aug 2018 10:01:00 +0300
Subject: iwlwifi: remove all unnecessary occurrences of nvm_calib_ver

Now that nvm_calib_ver is not checked in opmodes other than dvm, we
can remove it from all irrelevant configurations.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c |  2 --
 drivers/net/wireless/intel/iwlwifi/cfg/7000.c  | 21 ---------------------
 drivers/net/wireless/intel/iwlwifi/cfg/8000.c  |  6 ------
 drivers/net/wireless/intel/iwlwifi/cfg/9000.c  |  2 --
 4 files changed, 31 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index 157ff1f76ba6..a03d0b5617af 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -63,7 +63,6 @@
 
 /* NVM versions */
 #define IWL_22000_NVM_VERSION		0x0a1d
-#define IWL_22000_TX_POWER_VERSION	0xffff /* meaningless */
 
 /* Memory offsets and lengths */
 #define IWL_22000_DCCM_OFFSET		0x800000 /* LMAC1 */
@@ -155,7 +154,6 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 	.mac_addr_from_csr = true,					\
 	.ht_params = &iwl_22000_ht_params,				\
 	.nvm_ver = IWL_22000_NVM_VERSION,				\
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,			\
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,		\
 	.use_tfh = true,						\
 	.rf_id = true,							\
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
index 5b4efa8ddffb..289e3c398a12 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
@@ -80,17 +80,11 @@
 
 /* NVM versions */
 #define IWL7260_NVM_VERSION		0x0a1d
-#define IWL7260_TX_POWER_VERSION	0xffff /* meaningless */
 #define IWL3160_NVM_VERSION		0x709
-#define IWL3160_TX_POWER_VERSION	0xffff /* meaningless */
 #define IWL3165_NVM_VERSION		0x709
-#define IWL3165_TX_POWER_VERSION	0xffff /* meaningless */
 #define IWL3168_NVM_VERSION		0xd01
-#define IWL3168_TX_POWER_VERSION	0xffff /* meaningless */
 #define IWL7265_NVM_VERSION		0x0a1d
-#define IWL7265_TX_POWER_VERSION	0xffff /* meaningless */
 #define IWL7265D_NVM_VERSION		0x0c11
-#define IWL7265_TX_POWER_VERSION	0xffff /* meaningless */
 
 /* DCCM offsets and lengths */
 #define IWL7000_DCCM_OFFSET		0x800000
@@ -189,7 +183,6 @@ const struct iwl_cfg iwl7260_2ac_cfg = {
 	IWL_DEVICE_7000,
 	.ht_params = &iwl7000_ht_params,
 	.nvm_ver = IWL7260_NVM_VERSION,
-	.nvm_calib_ver = IWL7260_TX_POWER_VERSION,
 	.host_interrupt_operation_mode = true,
 	.lp_xtal_workaround = true,
 	.dccm_len = IWL7260_DCCM_LEN,
@@ -201,7 +194,6 @@ const struct iwl_cfg iwl7260_2ac_cfg_high_temp = {
 	IWL_DEVICE_7000,
 	.ht_params = &iwl7000_ht_params,
 	.nvm_ver = IWL7260_NVM_VERSION,
-	.nvm_calib_ver = IWL7260_TX_POWER_VERSION,
 	.high_temp = true,
 	.host_interrupt_operation_mode = true,
 	.lp_xtal_workaround = true,
@@ -215,7 +207,6 @@ const struct iwl_cfg iwl7260_2n_cfg = {
 	IWL_DEVICE_7000,
 	.ht_params = &iwl7000_ht_params,
 	.nvm_ver = IWL7260_NVM_VERSION,
-	.nvm_calib_ver = IWL7260_TX_POWER_VERSION,
 	.host_interrupt_operation_mode = true,
 	.lp_xtal_workaround = true,
 	.dccm_len = IWL7260_DCCM_LEN,
@@ -227,7 +218,6 @@ const struct iwl_cfg iwl7260_n_cfg = {
 	IWL_DEVICE_7000,
 	.ht_params = &iwl7000_ht_params,
 	.nvm_ver = IWL7260_NVM_VERSION,
-	.nvm_calib_ver = IWL7260_TX_POWER_VERSION,
 	.host_interrupt_operation_mode = true,
 	.lp_xtal_workaround = true,
 	.dccm_len = IWL7260_DCCM_LEN,
@@ -239,7 +229,6 @@ const struct iwl_cfg iwl3160_2ac_cfg = {
 	IWL_DEVICE_7000,
 	.ht_params = &iwl7000_ht_params,
 	.nvm_ver = IWL3160_NVM_VERSION,
-	.nvm_calib_ver = IWL3160_TX_POWER_VERSION,
 	.host_interrupt_operation_mode = true,
 	.dccm_len = IWL3160_DCCM_LEN,
 };
@@ -250,7 +239,6 @@ const struct iwl_cfg iwl3160_2n_cfg = {
 	IWL_DEVICE_7000,
 	.ht_params = &iwl7000_ht_params,
 	.nvm_ver = IWL3160_NVM_VERSION,
-	.nvm_calib_ver = IWL3160_TX_POWER_VERSION,
 	.host_interrupt_operation_mode = true,
 	.dccm_len = IWL3160_DCCM_LEN,
 };
@@ -261,7 +249,6 @@ const struct iwl_cfg iwl3160_n_cfg = {
 	IWL_DEVICE_7000,
 	.ht_params = &iwl7000_ht_params,
 	.nvm_ver = IWL3160_NVM_VERSION,
-	.nvm_calib_ver = IWL3160_TX_POWER_VERSION,
 	.host_interrupt_operation_mode = true,
 	.dccm_len = IWL3160_DCCM_LEN,
 };
@@ -289,7 +276,6 @@ const struct iwl_cfg iwl3165_2ac_cfg = {
 	IWL_DEVICE_7005D,
 	.ht_params = &iwl7000_ht_params,
 	.nvm_ver = IWL3165_NVM_VERSION,
-	.nvm_calib_ver = IWL3165_TX_POWER_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
 };
@@ -300,7 +286,6 @@ const struct iwl_cfg iwl3168_2ac_cfg = {
 	IWL_DEVICE_3008,
 	.ht_params = &iwl7000_ht_params,
 	.nvm_ver = IWL3168_NVM_VERSION,
-	.nvm_calib_ver = IWL3168_TX_POWER_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
 	.nvm_type = IWL_NVM_SDP,
@@ -312,7 +297,6 @@ const struct iwl_cfg iwl7265_2ac_cfg = {
 	IWL_DEVICE_7005,
 	.ht_params = &iwl7265_ht_params,
 	.nvm_ver = IWL7265_NVM_VERSION,
-	.nvm_calib_ver = IWL7265_TX_POWER_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
 };
@@ -323,7 +307,6 @@ const struct iwl_cfg iwl7265_2n_cfg = {
 	IWL_DEVICE_7005,
 	.ht_params = &iwl7265_ht_params,
 	.nvm_ver = IWL7265_NVM_VERSION,
-	.nvm_calib_ver = IWL7265_TX_POWER_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
 };
@@ -334,7 +317,6 @@ const struct iwl_cfg iwl7265_n_cfg = {
 	IWL_DEVICE_7005,
 	.ht_params = &iwl7265_ht_params,
 	.nvm_ver = IWL7265_NVM_VERSION,
-	.nvm_calib_ver = IWL7265_TX_POWER_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
 };
@@ -345,7 +327,6 @@ const struct iwl_cfg iwl7265d_2ac_cfg = {
 	IWL_DEVICE_7005D,
 	.ht_params = &iwl7265_ht_params,
 	.nvm_ver = IWL7265D_NVM_VERSION,
-	.nvm_calib_ver = IWL7265_TX_POWER_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
 };
@@ -356,7 +337,6 @@ const struct iwl_cfg iwl7265d_2n_cfg = {
 	IWL_DEVICE_7005D,
 	.ht_params = &iwl7265_ht_params,
 	.nvm_ver = IWL7265D_NVM_VERSION,
-	.nvm_calib_ver = IWL7265_TX_POWER_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
 };
@@ -367,7 +347,6 @@ const struct iwl_cfg iwl7265d_n_cfg = {
 	IWL_DEVICE_7005D,
 	.ht_params = &iwl7265_ht_params,
 	.nvm_ver = IWL7265D_NVM_VERSION,
-	.nvm_calib_ver = IWL7265_TX_POWER_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
 };
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
index 5b1da5206336..d7d17c1cceea 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
@@ -75,7 +75,6 @@
 
 /* NVM versions */
 #define IWL8000_NVM_VERSION		0x0a1d
-#define IWL8000_TX_POWER_VERSION	0xffff /* meaningless */
 
 /* Memory offsets and lengths */
 #define IWL8260_DCCM_OFFSET		0x800000
@@ -176,7 +175,6 @@ const struct iwl_cfg iwl8260_2n_cfg = {
 	IWL_DEVICE_8260,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
-	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
 };
 
 const struct iwl_cfg iwl8260_2ac_cfg = {
@@ -185,7 +183,6 @@ const struct iwl_cfg iwl8260_2ac_cfg = {
 	IWL_DEVICE_8260,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
-	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
@@ -195,7 +192,6 @@ const struct iwl_cfg iwl8265_2ac_cfg = {
 	IWL_DEVICE_8265,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
-	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.vht_mu_mimo_supported = true,
 };
@@ -206,7 +202,6 @@ const struct iwl_cfg iwl8275_2ac_cfg = {
 	IWL_DEVICE_8265,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
-	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	.vht_mu_mimo_supported = true,
 };
@@ -217,7 +212,6 @@ const struct iwl_cfg iwl4165_2ac_cfg = {
 	IWL_DEVICE_8000,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
-	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
index b589b0e9d515..c73460684a0c 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
@@ -64,7 +64,6 @@
 
 /* NVM versions */
 #define IWL9000_NVM_VERSION		0x0a1d
-#define IWL9000_TX_POWER_VERSION	0xffff /* meaningless */
 
 /* Memory offsets and lengths */
 #define IWL9000_DCCM_OFFSET		0x800000
@@ -158,7 +157,6 @@ static const struct iwl_tt_params iwl9000_tt_params = {
 	.d3_debug_data_length = 92 * 1024,				\
 	.ht_params = &iwl9000_ht_params,				\
 	.nvm_ver = IWL9000_NVM_VERSION,					\
-	.nvm_calib_ver = IWL9000_TX_POWER_VERSION,			\
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 
-- 
cgit v1.2.3


From 7bc2468277033e05401d5f8fd48a772f407338c2 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Wed, 15 Aug 2018 12:23:39 +0300
Subject: iwlwifi: mvm: force TCM re-evaluation on TCM resume

When traffic load is not low or low latency is active, TCM schedules
re-evaluation work so in case traffic stops TCM will detect that
traffic load has become low or that low latency is no longer active.
However, if TCM is paused when the re-evaluation work runs, it does
not re-evaluate and the re-evaluation work is no longer scheduled.
As a result, TCM will not indicate that low latency is no longer
active or that traffic load is low when traffic stops.

Fix this by forcing TCM re-evaluation when TCM is resumed in case
low latency is active or traffic load is not low.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/utils.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index 3761fbfff292..5ad352ef8e9b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -1378,6 +1378,7 @@ void iwl_mvm_pause_tcm(struct iwl_mvm *mvm, bool with_cancel)
 void iwl_mvm_resume_tcm(struct iwl_mvm *mvm)
 {
 	int mac;
+	bool low_latency = false;
 
 	spin_lock_bh(&mvm->tcm.lock);
 	mvm->tcm.ts = jiffies;
@@ -1389,10 +1390,23 @@ void iwl_mvm_resume_tcm(struct iwl_mvm *mvm)
 		memset(&mdata->tx.pkts, 0, sizeof(mdata->tx.pkts));
 		memset(&mdata->rx.airtime, 0, sizeof(mdata->rx.airtime));
 		memset(&mdata->tx.airtime, 0, sizeof(mdata->tx.airtime));
+
+		if (mvm->tcm.result.low_latency[mac])
+			low_latency = true;
 	}
 	/* The TCM data needs to be reset before "paused" flag changes */
 	smp_mb();
 	mvm->tcm.paused = false;
+
+	/*
+	 * if the current load is not low or low latency is active, force
+	 * re-evaluation to cover the case of no traffic.
+	 */
+	if (mvm->tcm.result.global_load > IWL_MVM_TRAFFIC_LOW)
+		schedule_delayed_work(&mvm->tcm.work, MVM_TCM_PERIOD);
+	else if (low_latency)
+		schedule_delayed_work(&mvm->tcm.work, MVM_LL_PERIOD);
+
 	spin_unlock_bh(&mvm->tcm.lock);
 }
 
-- 
cgit v1.2.3


From 0916224eaa77bff0fbbc747961d550ff8db45457 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Thu, 16 Aug 2018 13:01:09 +0300
Subject: iwlwifi: pcie: fix erroneous print

When removing the driver, the following flow can happen:
1. host command is in progress, for example at index 68.
2. RX interrupt is received with the response.
3. Before it is processed, the remove flow kicks in, and
   calls iwl_pcie_txq_unmap. The function cleans all DMA,
   and promotes the read pointer to 69.
4. RX thread proceeds with the processing, and is calling
   iwl_pcie_cmdq_reclaim, which will print this error:
   iwl_pcie_cmdq_reclaim: Read index for DMA queue txq id (0),
   index 4 is out of range [0-256] 69 69.

Detect this situation, and avoid the print. Change it to
warning while at it, to make such issues more noticeable
in the future.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 87b7225fe289..3d53842ee60e 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1245,11 +1245,11 @@ void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx)
 
 	if (idx >= trans->cfg->base_params->max_tfd_queue_size ||
 	    (!iwl_queue_used(txq, idx))) {
-		IWL_ERR(trans,
-			"%s: Read index for DMA queue txq id (%d), index %d is out of range [0-%d] %d %d.\n",
-			__func__, txq_id, idx,
-			trans->cfg->base_params->max_tfd_queue_size,
-			txq->write_ptr, txq->read_ptr);
+		WARN_ONCE(test_bit(txq_id, trans_pcie->queue_used),
+			  "%s: Read index for DMA queue txq id (%d), index %d is out of range [0-%d] %d %d.\n",
+			  __func__, txq_id, idx,
+			  trans->cfg->base_params->max_tfd_queue_size,
+			  txq->write_ptr, txq->read_ptr);
 		return;
 	}
 
-- 
cgit v1.2.3


From bdf180c8d375ee75493d79ae384dd1f9686fc974 Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Mon, 2 Jul 2018 14:35:26 +0200
Subject: iwlwifi: mvm: change PHY data RX for HE radiotap

The firmware changed the PHY data API, so follow suit.
Some data is now available even for HT/VHT frames, so
the info type in the metadata was changed. This change
isn't backwards compatible, but
 1) the firmware with the old API was never released;
 2) the only overlap in the info type field is from the
    old type of TB to the new of HT, so this basically
    just means that with older FW and newer driver the
    data will be considered missing.

While at it, remove the extra code to set the LTF syms
corresponding to the streams and use the data from the
device instead - we don't really need this in any case
other than when we have it from the device.

As the new API gives use the spatial reuse 1-4 fields
for trigger-based PPDUs, also expose that to radiotap.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/rx.h | 190 ++++++++-----
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c  | 367 ++++++++++++-------------
 2 files changed, 296 insertions(+), 261 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
index 0537496b6eb1..8961227ff44d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
@@ -345,66 +345,98 @@ enum iwl_rx_mpdu_mac_info {
 	IWL_RX_MPDU_PHY_PHY_INDEX_MASK		= 0xf0,
 };
 
-/*
- * enum iwl_rx_he_phy - HE PHY data
- */
-enum iwl_rx_he_phy {
-	IWL_RX_HE_PHY_BEAM_CHNG			= BIT(0),
-	IWL_RX_HE_PHY_UPLINK			= BIT(1),
-	IWL_RX_HE_PHY_BSS_COLOR_MASK		= 0xfc,
-	IWL_RX_HE_PHY_SPATIAL_REUSE_MASK	= 0xf00,
-	IWL_RX_HE_PHY_SU_EXT_BW10		= BIT(12),
-	IWL_RX_HE_PHY_TXOP_DUR_MASK		= 0xfe000,
-	IWL_RX_HE_PHY_LDPC_EXT_SYM		= BIT(20),
-	IWL_RX_HE_PHY_PRE_FEC_PAD_MASK		= 0x600000,
-	IWL_RX_HE_PHY_PE_DISAMBIG		= BIT(23),
-	IWL_RX_HE_PHY_DOPPLER			= BIT(24),
+/* TSF overload low dword */
+enum iwl_rx_phy_data0 {
+	/* info type: HE any */
+	IWL_RX_PHY_DATA0_HE_BEAM_CHNG				= 0x00000001,
+	IWL_RX_PHY_DATA0_HE_UPLINK				= 0x00000002,
+	IWL_RX_PHY_DATA0_HE_BSS_COLOR_MASK			= 0x000000fc,
+	IWL_RX_PHY_DATA0_HE_SPATIAL_REUSE_MASK			= 0x00000f00,
+	/* 1 bit reserved */
+	IWL_RX_PHY_DATA0_HE_TXOP_DUR_MASK			= 0x000fe000,
+	IWL_RX_PHY_DATA0_HE_LDPC_EXT_SYM			= 0x00100000,
+	IWL_RX_PHY_DATA0_HE_PRE_FEC_PAD_MASK			= 0x00600000,
+	IWL_RX_PHY_DATA0_HE_PE_DISAMBIG				= 0x00800000,
+	IWL_RX_PHY_DATA0_HE_DOPPLER				= 0x01000000,
 	/* 6 bits reserved */
-	IWL_RX_HE_PHY_DELIM_EOF			= BIT(31),
+	IWL_RX_PHY_DATA0_HE_DELIM_EOF				= 0x80000000,
+};
+
+enum iwl_rx_phy_info_type {
+	IWL_RX_PHY_INFO_TYPE_NONE				= 0,
+	IWL_RX_PHY_INFO_TYPE_CCK				= 1,
+	IWL_RX_PHY_INFO_TYPE_OFDM_LGCY				= 2,
+	IWL_RX_PHY_INFO_TYPE_HT					= 3,
+	IWL_RX_PHY_INFO_TYPE_VHT_SU				= 4,
+	IWL_RX_PHY_INFO_TYPE_VHT_MU				= 5,
+	IWL_RX_PHY_INFO_TYPE_HE_SU				= 6,
+	IWL_RX_PHY_INFO_TYPE_HE_MU				= 7,
+	IWL_RX_PHY_INFO_TYPE_HE_TB				= 8,
+	IWL_RX_PHY_INFO_TYPE_HE_MU_EXT				= 9,
+	IWL_RX_PHY_INFO_TYPE_HE_TB_EXT				= 10,
+};
+
+/* TSF overload high dword */
+enum iwl_rx_phy_data1 {
+	/*
+	 * check this first - if TSF overload is set,
+	 * see &enum iwl_rx_phy_info_type
+	 */
+	IWL_RX_PHY_DATA1_INFO_TYPE_MASK				= 0xf0000000,
+
+	/* info type: HT/VHT/HE any */
+	IWL_RX_PHY_DATA1_LSIG_LEN_MASK				= 0x0fff0000,
 
-	/* second dword - common data */
-	IWL_RX_HE_PHY_HE_LTF_NUM_MASK		= 0xe000000000ULL,
-	IWL_RX_HE_PHY_RU_ALLOC_SEC80		= BIT_ULL(32 + 8),
+	/* info type: HE MU/MU-EXT */
+	IWL_RX_PHY_DATA1_HE_MU_SIGB_COMPRESSION			= 0x00000001,
+	IWL_RX_PHY_DATA1_HE_MU_SIBG_SYM_OR_USER_NUM_MASK	= 0x0000001e,
+
+	/* info type: HE any */
+	IWL_RX_PHY_DATA1_HE_LTF_NUM_MASK			= 0x000000e0,
+	IWL_RX_PHY_DATA1_HE_RU_ALLOC_SEC80			= 0x00000100,
 	/* trigger encoded */
-	IWL_RX_HE_PHY_RU_ALLOC_MASK		= 0xfe0000000000ULL,
-	IWL_RX_HE_PHY_INFO_TYPE_MASK		= 0xf000000000000000ULL,
-	IWL_RX_HE_PHY_INFO_TYPE_SU		= 0x0, /* TSF low valid (first DW) */
-	IWL_RX_HE_PHY_INFO_TYPE_MU		= 0x1, /* TSF low/high valid (both DWs) */
-	IWL_RX_HE_PHY_INFO_TYPE_MU_EXT_INFO	= 0x2, /* same + SIGB-common0/1/2 valid */
-	IWL_RX_HE_PHY_INFO_TYPE_TB		= 0x3, /* TSF low/high valid (both DWs) */
-
-	/* second dword - MU data */
-	IWL_RX_HE_PHY_MU_SIGB_COMPRESSION		= BIT_ULL(32 + 0),
-	IWL_RX_HE_PHY_MU_SIBG_SYM_OR_USER_NUM_MASK	= 0x1e00000000ULL,
-	IWL_RX_HE_PHY_MU_SIGB_MCS_MASK			= 0xf000000000000ULL,
-	IWL_RX_HE_PHY_MU_SIGB_DCM			= BIT_ULL(32 + 21),
-	IWL_RX_HE_PHY_MU_PREAMBLE_PUNC_TYPE_MASK	= 0xc0000000000000ULL,
-
-	/* second dword - TB data */
-	IWL_RX_HE_PHY_TB_PILOT_TYPE			= BIT_ULL(32 + 0),
-	IWL_RX_HE_PHY_TB_LOW_SS_MASK			= 0xe00000000ULL
+	IWL_RX_PHY_DATA1_HE_RU_ALLOC_MASK			= 0x0000fe00,
+
+	/* info type: HE TB/TX-EXT */
+	IWL_RX_PHY_DATA1_HE_TB_PILOT_TYPE			= 0x00000001,
+	IWL_RX_PHY_DATA1_HE_TB_LOW_SS_MASK			= 0x0000000e,
 };
 
-enum iwl_rx_he_sigb_common0 {
+/* goes into Metadata DW 7 */
+enum iwl_rx_phy_data2 {
+	/* info type: HE MU-EXT */
 	/* the a1/a2/... is what the PHY/firmware calls the values */
-	IWL_RX_HE_SIGB_COMMON0_CH1_RU0		= 0x000000ff, /* a1 */
-	IWL_RX_HE_SIGB_COMMON0_CH1_RU2		= 0x0000ff00, /* a2 */
-	IWL_RX_HE_SIGB_COMMON0_CH2_RU0		= 0x00ff0000, /* b1 */
-	IWL_RX_HE_SIGB_COMMON0_CH2_RU2		= 0xff000000, /* b2 */
+	IWL_RX_PHY_DATA2_HE_MU_EXT_CH1_RU0		= 0x000000ff, /* a1 */
+	IWL_RX_PHY_DATA2_HE_MU_EXT_CH1_RU2		= 0x0000ff00, /* a2 */
+	IWL_RX_PHY_DATA2_HE_MU_EXT_CH2_RU0		= 0x00ff0000, /* b1 */
+	IWL_RX_PHY_DATA2_HE_MU_EXT_CH2_RU2		= 0xff000000, /* b2 */
+
+	/* info type: HE TB-EXT */
+	IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE1		= 0x0000000f,
+	IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE2		= 0x000000f0,
+	IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE3		= 0x00000f00,
+	IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE4		= 0x0000f000,
 };
 
-enum iwl_rx_he_sigb_common1 {
-	IWL_RX_HE_SIGB_COMMON1_CH1_RU1		= 0x000000ff, /* c1 */
-	IWL_RX_HE_SIGB_COMMON1_CH1_RU3		= 0x0000ff00, /* c2 */
-	IWL_RX_HE_SIGB_COMMON1_CH2_RU1		= 0x00ff0000, /* d1 */
-	IWL_RX_HE_SIGB_COMMON1_CH2_RU3		= 0xff000000, /* d2 */
+/* goes into Metadata DW 8 */
+enum iwl_rx_phy_data3 {
+	/* info type: HE MU-EXT */
+	IWL_RX_PHY_DATA3_HE_MU_EXT_CH1_RU1		= 0x000000ff, /* c1 */
+	IWL_RX_PHY_DATA3_HE_MU_EXT_CH1_RU3		= 0x0000ff00, /* c2 */
+	IWL_RX_PHY_DATA3_HE_MU_EXT_CH2_RU1		= 0x00ff0000, /* d1 */
+	IWL_RX_PHY_DATA3_HE_MU_EXT_CH2_RU3		= 0xff000000, /* d2 */
 };
 
-enum iwl_rx_he_sigb_common2 {
-	IWL_RX_HE_SIGB_COMMON2_CH1_CTR_RU	= 0x0001,
-	IWL_RX_HE_SIGB_COMMON2_CH2_CTR_RU	= 0x0002,
-	IWL_RX_HE_SIGB_COMMON2_CH1_CRC_OK	= 0x0004,
-	IWL_RX_HE_SIGB_COMMON2_CH2_CRC_OK	= 0x0008,
+/* goes into Metadata DW 4 high 16 bits */
+enum iwl_rx_phy_data4 {
+	/* info type: HE MU-EXT */
+	IWL_RX_PHY_DATA4_HE_MU_EXT_CH1_CTR_RU			= 0x0001,
+	IWL_RX_PHY_DATA4_HE_MU_EXT_CH2_CTR_RU			= 0x0002,
+	IWL_RX_PHY_DATA4_HE_MU_EXT_CH1_CRC_OK			= 0x0004,
+	IWL_RX_PHY_DATA4_HE_MU_EXT_CH2_CRC_OK			= 0x0008,
+	IWL_RX_PHY_DATA4_HE_MU_EXT_SIGB_MCS_MASK		= 0x00f0,
+	IWL_RX_PHY_DATA4_HE_MU_EXT_SIGB_DCM			= 0x0100,
+	IWL_RX_PHY_DATA4_HE_MU_EXT_PREAMBLE_PUNC_TYPE_MASK	= 0x0600,
 };
 
 /**
@@ -419,9 +451,9 @@ struct iwl_rx_mpdu_desc_v1 {
 		__le32 rss_hash;
 
 		/**
-		 * @sigb_common0: for HE sniffer, HE-SIG-B common part 0
+		 * @phy_data2: depends on info type (see @phy_data1)
 		 */
-		__le32 sigb_common0;
+		__le32 phy_data2;
 	};
 
 	/* DW8 - carries filter_match only when rpa_en == 1 */
@@ -432,9 +464,9 @@ struct iwl_rx_mpdu_desc_v1 {
 		__le32 filter_match;
 
 		/**
-		 * @sigb_common1: for HE sniffer, HE-SIG-B common part 1
+		 * @phy_data3: depends on info type (see @phy_data1)
 		 */
-		__le32 sigb_common1;
+		__le32 phy_data3;
 	};
 
 	/* DW9 */
@@ -472,12 +504,19 @@ struct iwl_rx_mpdu_desc_v1 {
 		 * %IWL_RX_MPDU_PHY_TSF_OVERLOAD isn't set
 		 */
 		__le64 tsf_on_air_rise;
-		/**
-		 * @he_phy_data:
-		 * HE PHY data, see &enum iwl_rx_he_phy, valid
-		 * only if %IWL_RX_MPDU_PHY_TSF_OVERLOAD is set
-		 */
-		__le64 he_phy_data;
+
+		struct {
+			/**
+			 * @phy_data0: depends on info_type, see @phy_data1
+			 */
+			__le32 phy_data0;
+			/**
+			 * @phy_data1: valid only if
+			 * %IWL_RX_MPDU_PHY_TSF_OVERLOAD is set,
+			 * see &enum iwl_rx_phy_data1.
+			 */
+			__le32 phy_data1;
+		};
 	};
 } __packed;
 
@@ -493,9 +532,9 @@ struct iwl_rx_mpdu_desc_v3 {
 		__le32 filter_match;
 
 		/**
-		 * @sigb_common0: for HE sniffer, HE-SIG-B common part 0
+		 * @phy_data2: depends on info type (see @phy_data1)
 		 */
-		__le32 sigb_common0;
+		__le32 phy_data2;
 	};
 
 	/* DW8 - carries rss_hash only when rpa_en == 1 */
@@ -506,9 +545,9 @@ struct iwl_rx_mpdu_desc_v3 {
 		__le32 rss_hash;
 
 		/**
-		 * @sigb_common1: for HE sniffer, HE-SIG-B common part 1
+		 * @phy_data3: depends on info type (see @phy_data1)
 		 */
-		__le32 sigb_common1;
+		__le32 phy_data3;
 	};
 	/* DW9 */
 	/**
@@ -556,12 +595,19 @@ struct iwl_rx_mpdu_desc_v3 {
 		 * %IWL_RX_MPDU_PHY_TSF_OVERLOAD isn't set
 		 */
 		__le64 tsf_on_air_rise;
-		/**
-		 * @he_phy_data:
-		 * HE PHY data, see &enum iwl_rx_he_phy, valid
-		 * only if %IWL_RX_MPDU_PHY_TSF_OVERLOAD is set
-		 */
-		__le64 he_phy_data;
+
+		struct {
+			/**
+			 * @phy_data0: depends on info_type, see @phy_data1
+			 */
+			__le32 phy_data0;
+			/**
+			 * @phy_data1: valid only if
+			 * %IWL_RX_MPDU_PHY_TSF_OVERLOAD is set,
+			 * see &enum iwl_rx_phy_data1.
+			 */
+			__le32 phy_data1;
+		};
 	};
 	/* DW16 & DW17 */
 	/**
@@ -613,9 +659,9 @@ struct iwl_rx_mpdu_desc {
 		__le16 l3l4_flags;
 
 		/**
-		 * @sigb_common2: for HE sniffer, HE-SIG-B common part 2
+		 * @phy_data4: depends on info type, see phy_data1
 		 */
-		__le16 sigb_common2;
+		__le16 phy_data4;
 	};
 	/* DW5 */
 	/**
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index d5ad390da8f0..d7f6b7aec981 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -863,68 +863,65 @@ static void iwl_mvm_flip_address(u8 *addr)
 	ether_addr_copy(addr, mac_addr);
 }
 
-static void iwl_mvm_decode_he_sigb(struct iwl_mvm *mvm,
-				   struct iwl_rx_mpdu_desc *desc,
-				   u32 rate_n_flags,
-				   struct ieee80211_radiotap_he_mu *he_mu)
+struct iwl_mvm_rx_phy_data {
+	__le32 d0, d1, d2, d3;
+	__le16 d4;
+};
+
+static void iwl_mvm_decode_he_mu_ext(struct iwl_mvm *mvm,
+				     struct iwl_mvm_rx_phy_data *phy_data,
+				     u32 rate_n_flags,
+				     struct ieee80211_radiotap_he_mu *he_mu)
 {
-	u32 sigb0, sigb1;
-	u16 sigb2;
+	u32 phy_data2 = le32_to_cpu(phy_data->d2);
+	u32 phy_data3 = le32_to_cpu(phy_data->d3);
+	u16 phy_data4 = le16_to_cpu(phy_data->d4);
 
-	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
-		sigb0 = le32_to_cpu(desc->v3.sigb_common0);
-		sigb1 = le32_to_cpu(desc->v3.sigb_common1);
-	} else {
-		sigb0 = le32_to_cpu(desc->v1.sigb_common0);
-		sigb1 = le32_to_cpu(desc->v1.sigb_common1);
-	}
-
-	sigb2 = le16_to_cpu(desc->sigb_common2);
-
-	if (FIELD_GET(IWL_RX_HE_SIGB_COMMON2_CH1_CRC_OK, sigb2)) {
+	if (FIELD_GET(IWL_RX_PHY_DATA4_HE_MU_EXT_CH1_CRC_OK, phy_data4)) {
 		he_mu->flags1 |=
 			cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_RU_KNOWN |
 				    IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU_KNOWN);
 
 		he_mu->flags1 |=
-			le16_encode_bits(FIELD_GET(IWL_RX_HE_SIGB_COMMON2_CH1_CTR_RU,
-						   sigb2),
+			le16_encode_bits(FIELD_GET(IWL_RX_PHY_DATA4_HE_MU_EXT_CH1_CTR_RU,
+						   phy_data4),
 					 IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU);
 
-		he_mu->ru_ch1[0] = FIELD_GET(IWL_RX_HE_SIGB_COMMON0_CH1_RU0,
-					     sigb0);
-		he_mu->ru_ch1[1] = FIELD_GET(IWL_RX_HE_SIGB_COMMON1_CH1_RU1,
-					     sigb1);
-		he_mu->ru_ch1[2] = FIELD_GET(IWL_RX_HE_SIGB_COMMON0_CH1_RU2,
-					     sigb0);
-		he_mu->ru_ch1[3] = FIELD_GET(IWL_RX_HE_SIGB_COMMON1_CH1_RU3,
-					     sigb1);
+		he_mu->ru_ch1[0] = FIELD_GET(IWL_RX_PHY_DATA2_HE_MU_EXT_CH1_RU0,
+					     phy_data2);
+		he_mu->ru_ch1[1] = FIELD_GET(IWL_RX_PHY_DATA3_HE_MU_EXT_CH1_RU1,
+					     phy_data3);
+		he_mu->ru_ch1[2] = FIELD_GET(IWL_RX_PHY_DATA2_HE_MU_EXT_CH1_RU2,
+					     phy_data2);
+		he_mu->ru_ch1[3] = FIELD_GET(IWL_RX_PHY_DATA3_HE_MU_EXT_CH1_RU3,
+					     phy_data3);
 	}
 
-	if (FIELD_GET(IWL_RX_HE_SIGB_COMMON2_CH2_CRC_OK, sigb2) &&
+	if (FIELD_GET(IWL_RX_PHY_DATA4_HE_MU_EXT_CH2_CRC_OK, phy_data4) &&
 	    (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) != RATE_MCS_CHAN_WIDTH_20) {
 		he_mu->flags1 |=
 			cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_RU_KNOWN |
 				    IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_CTR_26T_RU_KNOWN);
 
 		he_mu->flags2 |=
-			le16_encode_bits(FIELD_GET(IWL_RX_HE_SIGB_COMMON2_CH2_CTR_RU,
-						   sigb2),
+			le16_encode_bits(FIELD_GET(IWL_RX_PHY_DATA4_HE_MU_EXT_CH2_CTR_RU,
+						   phy_data4),
 					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_CH2_CTR_26T_RU);
 
-		he_mu->ru_ch2[0] = FIELD_GET(IWL_RX_HE_SIGB_COMMON0_CH2_RU0,
-					     sigb0);
-		he_mu->ru_ch2[1] = FIELD_GET(IWL_RX_HE_SIGB_COMMON1_CH2_RU1,
-					     sigb1);
-		he_mu->ru_ch2[2] = FIELD_GET(IWL_RX_HE_SIGB_COMMON0_CH2_RU2,
-					     sigb0);
-		he_mu->ru_ch2[3] = FIELD_GET(IWL_RX_HE_SIGB_COMMON1_CH2_RU3,
-					     sigb1);
+		he_mu->ru_ch2[0] = FIELD_GET(IWL_RX_PHY_DATA2_HE_MU_EXT_CH2_RU0,
+					     phy_data2);
+		he_mu->ru_ch2[1] = FIELD_GET(IWL_RX_PHY_DATA3_HE_MU_EXT_CH2_RU1,
+					     phy_data3);
+		he_mu->ru_ch2[2] = FIELD_GET(IWL_RX_PHY_DATA2_HE_MU_EXT_CH2_RU2,
+					     phy_data2);
+		he_mu->ru_ch2[3] = FIELD_GET(IWL_RX_PHY_DATA3_HE_MU_EXT_CH2_RU3,
+					     phy_data3);
 	}
 }
 
 static void
-iwl_mvm_decode_he_phy_ru_alloc(u64 he_phy_data, u32 rate_n_flags,
+iwl_mvm_decode_he_phy_ru_alloc(struct iwl_mvm_rx_phy_data *phy_data,
+			       u32 rate_n_flags,
 			       struct ieee80211_radiotap_he *he,
 			       struct ieee80211_radiotap_he_mu *he_mu,
 			       struct ieee80211_rx_status *rx_status)
@@ -937,7 +934,7 @@ iwl_mvm_decode_he_phy_ru_alloc(u64 he_phy_data, u32 rate_n_flags,
 	 * happen though as management frames where we need
 	 * the TSF/timers are not be transmitted in HE-MU.
 	 */
-	u8 ru = FIELD_GET(IWL_RX_HE_PHY_RU_ALLOC_MASK, he_phy_data);
+	u8 ru = le32_get_bits(phy_data->d1, IWL_RX_PHY_DATA1_HE_RU_ALLOC_MASK);
 	u8 offs = 0;
 
 	rx_status->bw = RATE_INFO_BW_HE_RU;
@@ -976,7 +973,7 @@ iwl_mvm_decode_he_phy_ru_alloc(u64 he_phy_data, u32 rate_n_flags,
 				      IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET);
 	he->data2 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_KNOWN |
 				 IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET_KNOWN);
-	if (he_phy_data & IWL_RX_HE_PHY_RU_ALLOC_SEC80)
+	if (phy_data->d1 & cpu_to_le32(IWL_RX_PHY_DATA1_HE_RU_ALLOC_SEC80))
 		he->data2 |=
 			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_SEC);
 
@@ -996,106 +993,125 @@ iwl_mvm_decode_he_phy_ru_alloc(u64 he_phy_data, u32 rate_n_flags,
 }
 
 static void iwl_mvm_decode_he_phy_data(struct iwl_mvm *mvm,
-				       struct iwl_rx_mpdu_desc *desc,
+				       struct iwl_mvm_rx_phy_data *phy_data,
 				       struct ieee80211_radiotap_he *he,
 				       struct ieee80211_radiotap_he_mu *he_mu,
 				       struct ieee80211_rx_status *rx_status,
-				       u64 he_phy_data, u32 rate_n_flags,
-				       int queue)
+				       u32 rate_n_flags, int queue)
 {
-	u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
-	bool sigb_data;
-	u16 d1known = IEEE80211_RADIOTAP_HE_DATA1_LDPC_XSYMSEG_KNOWN |
-		      IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN |
-		      IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN |
-		      IEEE80211_RADIOTAP_HE_DATA1_DOPPLER_KNOWN |
-		      IEEE80211_RADIOTAP_HE_DATA1_BSS_COLOR_KNOWN;
-	u16 d2known = IEEE80211_RADIOTAP_HE_DATA2_PRE_FEC_PAD_KNOWN |
-		      IEEE80211_RADIOTAP_HE_DATA2_PE_DISAMBIG_KNOWN |
-		      IEEE80211_RADIOTAP_HE_DATA2_TXOP_KNOWN;
-
-	he->data1 |= cpu_to_le16(d1known);
-	he->data2 |= cpu_to_le16(d2known);
-	he->data3 |= le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_BSS_COLOR_MASK,
-						he_phy_data),
-				      IEEE80211_RADIOTAP_HE_DATA3_BSS_COLOR);
-	he->data3 |= le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_UPLINK,
-						he_phy_data),
-				      IEEE80211_RADIOTAP_HE_DATA3_UL_DL);
-	he->data3 |= le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_LDPC_EXT_SYM,
-						he_phy_data),
-				      IEEE80211_RADIOTAP_HE_DATA3_LDPC_XSYMSEG);
-	he->data4 |= le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_SPATIAL_REUSE_MASK,
-						he_phy_data),
-				      IEEE80211_RADIOTAP_HE_DATA4_SU_MU_SPTL_REUSE);
-	he->data5 |= le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_PRE_FEC_PAD_MASK,
-						he_phy_data),
-				      IEEE80211_RADIOTAP_HE_DATA5_PRE_FEC_PAD);
-	he->data5 |= le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_PE_DISAMBIG,
-						he_phy_data),
-				      IEEE80211_RADIOTAP_HE_DATA5_PE_DISAMBIG);
-	he->data6 |= le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_TXOP_DUR_MASK,
-						he_phy_data),
-				      IEEE80211_RADIOTAP_HE_DATA6_TXOP);
-	he->data6 |= le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_DOPPLER,
-						he_phy_data),
-				      IEEE80211_RADIOTAP_HE_DATA6_DOPPLER);
-
-	switch (he_type) {
-	case RATE_MCS_HE_TYPE_MU:
+	enum iwl_rx_phy_info_type info_type;
+
+	info_type = le32_get_bits(phy_data->d1, IWL_RX_PHY_DATA1_INFO_TYPE_MASK);
+
+	switch (info_type) {
+	case IWL_RX_PHY_INFO_TYPE_NONE:
+	case IWL_RX_PHY_INFO_TYPE_CCK:
+	case IWL_RX_PHY_INFO_TYPE_OFDM_LGCY:
+		return;
+	case IWL_RX_PHY_INFO_TYPE_HT:
+	case IWL_RX_PHY_INFO_TYPE_VHT_SU:
+	case IWL_RX_PHY_INFO_TYPE_VHT_MU:
+		/* TODO: we have LSIG-LEN, where do we put it? */
+		return;
+	case IWL_RX_PHY_INFO_TYPE_HE_TB_EXT:
+		he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE2_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE3_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE4_KNOWN);
+		he->data4 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE1),
+					      IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE1);
+		he->data4 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE2),
+					      IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE2);
+		he->data4 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE3),
+					      IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE3);
+		he->data4 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE4),
+					      IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE4);
+		/* fall through */
+	case IWL_RX_PHY_INFO_TYPE_HE_SU:
+	case IWL_RX_PHY_INFO_TYPE_HE_MU:
+	case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT:
+	case IWL_RX_PHY_INFO_TYPE_HE_TB:
+		/* HE common */
+		he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_LDPC_XSYMSEG_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_DOPPLER_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_BSS_COLOR_KNOWN);
+		he->data2 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRE_FEC_PAD_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA2_PE_DISAMBIG_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA2_TXOP_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN);
+		he->data3 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA0_HE_BSS_COLOR_MASK),
+					      IEEE80211_RADIOTAP_HE_DATA3_BSS_COLOR);
+		he->data3 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA0_HE_UPLINK),
+					      IEEE80211_RADIOTAP_HE_DATA3_UL_DL);
+		he->data3 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA0_HE_LDPC_EXT_SYM),
+					      IEEE80211_RADIOTAP_HE_DATA3_LDPC_XSYMSEG);
+		he->data4 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA0_HE_SPATIAL_REUSE_MASK),
+					      IEEE80211_RADIOTAP_HE_DATA4_SU_MU_SPTL_REUSE);
+		he->data5 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA0_HE_PRE_FEC_PAD_MASK),
+					      IEEE80211_RADIOTAP_HE_DATA5_PRE_FEC_PAD);
+		he->data5 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA0_HE_PE_DISAMBIG),
+					      IEEE80211_RADIOTAP_HE_DATA5_PE_DISAMBIG);
+		he->data5 |= le16_encode_bits(le32_get_bits(phy_data->d1,
+							    IWL_RX_PHY_DATA1_HE_LTF_NUM_MASK),
+					      IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS);
+		he->data6 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA0_HE_TXOP_DUR_MASK),
+					      IEEE80211_RADIOTAP_HE_DATA6_TXOP);
+		he->data6 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA0_HE_DOPPLER),
+					      IEEE80211_RADIOTAP_HE_DATA6_DOPPLER);
+		break;
+	}
+
+	switch (info_type) {
+	case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT:
 		he_mu->flags1 |=
-			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_MU_SIGB_DCM,
-						   he_phy_data),
+			le16_encode_bits(le16_get_bits(phy_data->d4,
+						       IWL_RX_PHY_DATA4_HE_MU_EXT_SIGB_DCM),
 					 IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM);
 		he_mu->flags1 |=
-			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_MU_SIGB_MCS_MASK,
-						   he_phy_data),
+			le16_encode_bits(le16_get_bits(phy_data->d4,
+						       IWL_RX_PHY_DATA4_HE_MU_EXT_SIGB_MCS_MASK),
 					 IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS);
 		he_mu->flags2 |=
-			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_MU_SIBG_SYM_OR_USER_NUM_MASK,
-						  he_phy_data),
-					IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_SYMS_USERS);
+			le16_encode_bits(le16_get_bits(phy_data->d4,
+						       IWL_RX_PHY_DATA4_HE_MU_EXT_PREAMBLE_PUNC_TYPE_MASK),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW);
+		iwl_mvm_decode_he_mu_ext(mvm, phy_data, rate_n_flags, he_mu);
+		/* fall through */
+	case IWL_RX_PHY_INFO_TYPE_HE_MU:
 		he_mu->flags2 |=
-			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_MU_SIGB_COMPRESSION,
-						   he_phy_data),
-					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_COMP);
+			le16_encode_bits(le32_get_bits(phy_data->d1,
+						       IWL_RX_PHY_DATA1_HE_MU_SIBG_SYM_OR_USER_NUM_MASK),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_SYMS_USERS);
 		he_mu->flags2 |=
-			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_MU_PREAMBLE_PUNC_TYPE_MASK,
-						   he_phy_data),
-					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW);
-
-		sigb_data = FIELD_GET(IWL_RX_HE_PHY_INFO_TYPE_MASK,
-				      he_phy_data) ==
-				IWL_RX_HE_PHY_INFO_TYPE_MU_EXT_INFO;
-		if (sigb_data)
-			iwl_mvm_decode_he_sigb(mvm, desc, rate_n_flags, he_mu);
+			le16_encode_bits(le32_get_bits(phy_data->d1,
+						       IWL_RX_PHY_DATA1_HE_MU_SIGB_COMPRESSION),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_COMP);
 		/* fall through */
-	case RATE_MCS_HE_TYPE_TRIG:
-		he->data2 |=
-			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN);
-		he->data5 |=
-			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_HE_LTF_NUM_MASK,
-						   he_phy_data),
-					 IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS);
-		break;
-	case RATE_MCS_HE_TYPE_SU:
-	case RATE_MCS_HE_TYPE_EXT_SU:
-		he->data1 |=
-			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_BEAM_CHANGE_KNOWN);
-		he->data3 |=
-			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_BEAM_CHNG,
-						   he_phy_data),
-					 IEEE80211_RADIOTAP_HE_DATA3_BEAM_CHANGE);
-		break;
-	}
-
-	switch (FIELD_GET(IWL_RX_HE_PHY_INFO_TYPE_MASK, he_phy_data)) {
-	case IWL_RX_HE_PHY_INFO_TYPE_MU:
-	case IWL_RX_HE_PHY_INFO_TYPE_MU_EXT_INFO:
-	case IWL_RX_HE_PHY_INFO_TYPE_TB:
-		iwl_mvm_decode_he_phy_ru_alloc(he_phy_data, rate_n_flags,
+	case IWL_RX_PHY_INFO_TYPE_HE_TB:
+	case IWL_RX_PHY_INFO_TYPE_HE_TB_EXT:
+		iwl_mvm_decode_he_phy_ru_alloc(phy_data, rate_n_flags,
 					       he, he_mu, rx_status);
 		break;
+	case IWL_RX_PHY_INFO_TYPE_HE_SU:
+		he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_BEAM_CHANGE_KNOWN);
+		he->data3 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+							    IWL_RX_PHY_DATA0_HE_BEAM_CHNG),
+					      IEEE80211_RADIOTAP_HE_DATA3_BEAM_CHANGE);
+		break;
 	default:
 		/* nothing */
 		break;
@@ -1107,9 +1123,6 @@ static void iwl_mvm_rx_he(struct iwl_mvm *mvm, struct sk_buff *skb,
 			  u32 rate_n_flags, u16 phy_info, int queue)
 {
 	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
-	/* this is invalid e.g. because puncture type doesn't allow 0b11 */
-#define HE_PHY_DATA_INVAL ((u64)-1)
-	u64 he_phy_data = HE_PHY_DATA_INVAL;
 	struct ieee80211_radiotap_he *he = NULL;
 	struct ieee80211_radiotap_he_mu *he_mu = NULL;
 	u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
@@ -1131,54 +1144,66 @@ static void iwl_mvm_rx_he(struct iwl_mvm *mvm, struct sk_buff *skb,
 				      IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_KNOWN),
 	};
 	unsigned int radiotap_len = 0;
+	struct iwl_mvm_rx_phy_data phy_data = {
+		.d4 = desc->phy_data4,
+	};
+	enum iwl_rx_phy_info_type info_type = IWL_RX_PHY_INFO_TYPE_NONE;
+
+	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		phy_data.d0 = desc->v3.phy_data0;
+		phy_data.d1 = desc->v3.phy_data1;
+		phy_data.d2 = desc->v3.phy_data2;
+		phy_data.d3 = desc->v3.phy_data3;
+	} else {
+		phy_data.d0 = desc->v1.phy_data0;
+		phy_data.d1 = desc->v1.phy_data1;
+		phy_data.d2 = desc->v1.phy_data2;
+		phy_data.d3 = desc->v1.phy_data3;
+	}
+
+	if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD)
+		info_type = le32_get_bits(phy_data.d1,
+					  IWL_RX_PHY_DATA1_INFO_TYPE_MASK);
 
 	he = skb_put_data(skb, &known, sizeof(known));
 	radiotap_len += sizeof(known);
 	rx_status->flag |= RX_FLAG_RADIOTAP_HE;
 
-	if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) {
-		if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
-			he_phy_data = le64_to_cpu(desc->v3.he_phy_data);
-		else
-			he_phy_data = le64_to_cpu(desc->v1.he_phy_data);
-
-		if (he_type == RATE_MCS_HE_TYPE_MU) {
-			he_mu = skb_put_data(skb, &mu_known, sizeof(mu_known));
-			radiotap_len += sizeof(mu_known);
-			rx_status->flag |= RX_FLAG_RADIOTAP_HE_MU;
-		}
+	if (info_type == IWL_RX_PHY_INFO_TYPE_HE_MU ||
+	    info_type == IWL_RX_PHY_INFO_TYPE_HE_MU_EXT) {
+		he_mu = skb_put_data(skb, &mu_known, sizeof(mu_known));
+		radiotap_len += sizeof(mu_known);
+		rx_status->flag |= RX_FLAG_RADIOTAP_HE_MU;
 	}
 
 	/* temporarily hide the radiotap data */
 	__skb_pull(skb, radiotap_len);
 
-	if (he_phy_data != HE_PHY_DATA_INVAL &&
-	    he_type == RATE_MCS_HE_TYPE_SU) {
+	if (info_type == IWL_RX_PHY_INFO_TYPE_HE_SU) {
 		/* report the AMPDU-EOF bit on single frames */
 		if (!queue && !(phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
 			rx_status->flag |= RX_FLAG_AMPDU_DETAILS;
 			rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
-			if (FIELD_GET(IWL_RX_HE_PHY_DELIM_EOF, he_phy_data))
+			if (phy_data.d0 & cpu_to_le32(IWL_RX_PHY_DATA0_HE_DELIM_EOF))
 				rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT;
 		}
 	}
 
-	if (he_phy_data != HE_PHY_DATA_INVAL)
-		iwl_mvm_decode_he_phy_data(mvm, desc, he, he_mu, rx_status,
-					   he_phy_data, rate_n_flags, queue);
+	if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD)
+		iwl_mvm_decode_he_phy_data(mvm, &phy_data, he, he_mu, rx_status,
+					   rate_n_flags, queue);
 
 	/* update aggregation data for monitor sake on default queue */
-	if (!queue && (phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
+	if (!queue && (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) &&
+	    (phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
 		bool toggle_bit = phy_info & IWL_RX_MPDU_PHY_AMPDU_TOGGLE;
 
 		/* toggle is switched whenever new aggregation starts */
 		if (toggle_bit != mvm->ampdu_toggle &&
-		    he_phy_data != HE_PHY_DATA_INVAL &&
 		    (he_type == RATE_MCS_HE_TYPE_MU ||
 		     he_type == RATE_MCS_HE_TYPE_SU)) {
 			rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
-			if (FIELD_GET(IWL_RX_HE_PHY_DELIM_EOF,
-				      he_phy_data))
+			if (phy_data.d0 & cpu_to_le32(IWL_RX_PHY_DATA0_HE_DELIM_EOF))
 				rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT;
 		}
 	}
@@ -1261,44 +1286,8 @@ static void iwl_mvm_rx_he(struct iwl_mvm *mvm, struct sk_buff *skb,
 		break;
 	}
 
-	he->data5 |= le16_encode_bits(ltf, IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE);
-
-	if (he_type == RATE_MCS_HE_TYPE_SU ||
-	    he_type == RATE_MCS_HE_TYPE_EXT_SU) {
-		u16 val;
-
-		/* LTF syms correspond to streams */
-		he->data2 |=
-			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN);
-		switch (rx_status->nss) {
-		case 1:
-			val = 0;
-			break;
-		case 2:
-			val = 1;
-			break;
-		case 3:
-		case 4:
-			val = 2;
-			break;
-		case 5:
-		case 6:
-			val = 3;
-			break;
-		case 7:
-		case 8:
-			val = 4;
-			break;
-		default:
-			WARN_ONCE(1, "invalid nss: %d\n",
-				  rx_status->nss);
-			val = 0;
-		}
-
-		he->data5 |=
-			le16_encode_bits(val,
-					 IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS);
-	}
+	he->data5 |= le16_encode_bits(ltf,
+				      IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE);
 }
 
 void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
-- 
cgit v1.2.3


From 6721039d5b8adfd57291c54e96eaa9f54da23753 Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Mon, 2 Jul 2018 17:16:48 +0200
Subject: iwlwifi: mvm: add L-SIG length to radiotap

We may have the L-SIG length depending on the phy_data info type;
add it to radiotap when we do.

Move getting the phy_data out one layer up and the info type into
it so we can use this data more generically. We need to call the
iwl_mvm_rx_he() function for other reasons as well, so can't just
combine all of that into something like iwl_mvm_parse_phy_data().

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 96 +++++++++++++++++----------
 1 file changed, 60 insertions(+), 36 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index d7f6b7aec981..87c245c85d9c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -864,6 +864,7 @@ static void iwl_mvm_flip_address(u8 *addr)
 }
 
 struct iwl_mvm_rx_phy_data {
+	enum iwl_rx_phy_info_type info_type;
 	__le32 d0, d1, d2, d3;
 	__le16 d4;
 };
@@ -999,19 +1000,13 @@ static void iwl_mvm_decode_he_phy_data(struct iwl_mvm *mvm,
 				       struct ieee80211_rx_status *rx_status,
 				       u32 rate_n_flags, int queue)
 {
-	enum iwl_rx_phy_info_type info_type;
-
-	info_type = le32_get_bits(phy_data->d1, IWL_RX_PHY_DATA1_INFO_TYPE_MASK);
-
-	switch (info_type) {
+	switch (phy_data->info_type) {
 	case IWL_RX_PHY_INFO_TYPE_NONE:
 	case IWL_RX_PHY_INFO_TYPE_CCK:
 	case IWL_RX_PHY_INFO_TYPE_OFDM_LGCY:
-		return;
 	case IWL_RX_PHY_INFO_TYPE_HT:
 	case IWL_RX_PHY_INFO_TYPE_VHT_SU:
 	case IWL_RX_PHY_INFO_TYPE_VHT_MU:
-		/* TODO: we have LSIG-LEN, where do we put it? */
 		return;
 	case IWL_RX_PHY_INFO_TYPE_HE_TB_EXT:
 		he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN |
@@ -1075,7 +1070,7 @@ static void iwl_mvm_decode_he_phy_data(struct iwl_mvm *mvm,
 		break;
 	}
 
-	switch (info_type) {
+	switch (phy_data->info_type) {
 	case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT:
 		he_mu->flags1 |=
 			le16_encode_bits(le16_get_bits(phy_data->d4,
@@ -1119,7 +1114,7 @@ static void iwl_mvm_decode_he_phy_data(struct iwl_mvm *mvm,
 }
 
 static void iwl_mvm_rx_he(struct iwl_mvm *mvm, struct sk_buff *skb,
-			  struct iwl_rx_mpdu_desc *desc,
+			  struct iwl_mvm_rx_phy_data *phy_data,
 			  u32 rate_n_flags, u16 phy_info, int queue)
 {
 	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
@@ -1144,33 +1139,13 @@ static void iwl_mvm_rx_he(struct iwl_mvm *mvm, struct sk_buff *skb,
 				      IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_KNOWN),
 	};
 	unsigned int radiotap_len = 0;
-	struct iwl_mvm_rx_phy_data phy_data = {
-		.d4 = desc->phy_data4,
-	};
-	enum iwl_rx_phy_info_type info_type = IWL_RX_PHY_INFO_TYPE_NONE;
-
-	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
-		phy_data.d0 = desc->v3.phy_data0;
-		phy_data.d1 = desc->v3.phy_data1;
-		phy_data.d2 = desc->v3.phy_data2;
-		phy_data.d3 = desc->v3.phy_data3;
-	} else {
-		phy_data.d0 = desc->v1.phy_data0;
-		phy_data.d1 = desc->v1.phy_data1;
-		phy_data.d2 = desc->v1.phy_data2;
-		phy_data.d3 = desc->v1.phy_data3;
-	}
-
-	if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD)
-		info_type = le32_get_bits(phy_data.d1,
-					  IWL_RX_PHY_DATA1_INFO_TYPE_MASK);
 
 	he = skb_put_data(skb, &known, sizeof(known));
 	radiotap_len += sizeof(known);
 	rx_status->flag |= RX_FLAG_RADIOTAP_HE;
 
-	if (info_type == IWL_RX_PHY_INFO_TYPE_HE_MU ||
-	    info_type == IWL_RX_PHY_INFO_TYPE_HE_MU_EXT) {
+	if (phy_data->info_type == IWL_RX_PHY_INFO_TYPE_HE_MU ||
+	    phy_data->info_type == IWL_RX_PHY_INFO_TYPE_HE_MU_EXT) {
 		he_mu = skb_put_data(skb, &mu_known, sizeof(mu_known));
 		radiotap_len += sizeof(mu_known);
 		rx_status->flag |= RX_FLAG_RADIOTAP_HE_MU;
@@ -1179,18 +1154,18 @@ static void iwl_mvm_rx_he(struct iwl_mvm *mvm, struct sk_buff *skb,
 	/* temporarily hide the radiotap data */
 	__skb_pull(skb, radiotap_len);
 
-	if (info_type == IWL_RX_PHY_INFO_TYPE_HE_SU) {
+	if (phy_data->info_type == IWL_RX_PHY_INFO_TYPE_HE_SU) {
 		/* report the AMPDU-EOF bit on single frames */
 		if (!queue && !(phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
 			rx_status->flag |= RX_FLAG_AMPDU_DETAILS;
 			rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
-			if (phy_data.d0 & cpu_to_le32(IWL_RX_PHY_DATA0_HE_DELIM_EOF))
+			if (phy_data->d0 & cpu_to_le32(IWL_RX_PHY_DATA0_HE_DELIM_EOF))
 				rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT;
 		}
 	}
 
 	if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD)
-		iwl_mvm_decode_he_phy_data(mvm, &phy_data, he, he_mu, rx_status,
+		iwl_mvm_decode_he_phy_data(mvm, phy_data, he, he_mu, rx_status,
 					   rate_n_flags, queue);
 
 	/* update aggregation data for monitor sake on default queue */
@@ -1203,7 +1178,7 @@ static void iwl_mvm_rx_he(struct iwl_mvm *mvm, struct sk_buff *skb,
 		    (he_type == RATE_MCS_HE_TYPE_MU ||
 		     he_type == RATE_MCS_HE_TYPE_SU)) {
 			rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
-			if (phy_data.d0 & cpu_to_le32(IWL_RX_PHY_DATA0_HE_DELIM_EOF))
+			if (phy_data->d0 & cpu_to_le32(IWL_RX_PHY_DATA0_HE_DELIM_EOF))
 				rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT;
 		}
 	}
@@ -1290,6 +1265,33 @@ static void iwl_mvm_rx_he(struct iwl_mvm *mvm, struct sk_buff *skb,
 				      IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE);
 }
 
+static void iwl_mvm_decode_lsig(struct sk_buff *skb,
+				struct iwl_mvm_rx_phy_data *phy_data)
+{
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_radiotap_lsig *lsig;
+
+	switch (phy_data->info_type) {
+	case IWL_RX_PHY_INFO_TYPE_HT:
+	case IWL_RX_PHY_INFO_TYPE_VHT_SU:
+	case IWL_RX_PHY_INFO_TYPE_VHT_MU:
+	case IWL_RX_PHY_INFO_TYPE_HE_TB_EXT:
+	case IWL_RX_PHY_INFO_TYPE_HE_SU:
+	case IWL_RX_PHY_INFO_TYPE_HE_MU:
+	case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT:
+	case IWL_RX_PHY_INFO_TYPE_HE_TB:
+		lsig = skb_put(skb, sizeof(*lsig));
+		lsig->data1 = cpu_to_le16(IEEE80211_RADIOTAP_LSIG_DATA1_LENGTH_KNOWN);
+		lsig->data2 = le16_encode_bits(le32_get_bits(phy_data->d1,
+							     IWL_RX_PHY_DATA1_LSIG_LEN_MASK),
+					       IEEE80211_RADIOTAP_LSIG_DATA2_LENGTH);
+		rx_status->flag |= RX_FLAG_RADIOTAP_LSIG;
+		break;
+	default:
+		break;
+	}
+}
+
 void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 			struct iwl_rx_cmd_buffer *rxb, int queue)
 {
@@ -1304,6 +1306,10 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	struct sk_buff *skb;
 	u8 crypt_len = 0, channel, energy_a, energy_b;
 	size_t desc_size;
+	struct iwl_mvm_rx_phy_data phy_data = {
+		.d4 = desc->phy_data4,
+		.info_type = IWL_RX_PHY_INFO_TYPE_NONE,
+	};
 
 	if (unlikely(test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)))
 		return;
@@ -1315,6 +1321,11 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		energy_a = desc->v3.energy_a;
 		energy_b = desc->v3.energy_b;
 		desc_size = sizeof(*desc);
+
+		phy_data.d0 = desc->v3.phy_data0;
+		phy_data.d1 = desc->v3.phy_data1;
+		phy_data.d2 = desc->v3.phy_data2;
+		phy_data.d3 = desc->v3.phy_data3;
 	} else {
 		rate_n_flags = le32_to_cpu(desc->v1.rate_n_flags);
 		channel = desc->v1.channel;
@@ -1322,8 +1333,18 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		energy_a = desc->v1.energy_a;
 		energy_b = desc->v1.energy_b;
 		desc_size = IWL_RX_DESC_SIZE_V1;
+
+		phy_data.d0 = desc->v1.phy_data0;
+		phy_data.d1 = desc->v1.phy_data1;
+		phy_data.d2 = desc->v1.phy_data2;
+		phy_data.d3 = desc->v1.phy_data3;
 	}
 
+	if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD)
+		phy_data.info_type =
+			le32_get_bits(phy_data.d1,
+				      IWL_RX_PHY_DATA1_INFO_TYPE_MASK);
+
 	hdr = (void *)(pkt->data + desc_size);
 	/* Dont use dev_alloc_skb(), we'll have enough headroom once
 	 * ieee80211_hdr pulled.
@@ -1362,7 +1383,10 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	}
 
 	if (rate_n_flags & RATE_MCS_HE_MSK)
-		iwl_mvm_rx_he(mvm, skb, desc, rate_n_flags, phy_info, queue);
+		iwl_mvm_rx_he(mvm, skb, &phy_data, rate_n_flags,
+			      phy_info, queue);
+
+	iwl_mvm_decode_lsig(skb, &phy_data);
 
 	rx_status = IEEE80211_SKB_RXCB(skb);
 
-- 
cgit v1.2.3


From 7969454b37f25d38a48bdbd9932e8aa49ed2ed77 Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Wed, 25 Jul 2018 22:11:52 +0300
Subject: iwlwifi: mvm: radiotap: remove UL_DL bit in HE TRIG_BASED

UL_DL is irrelevant to HE TRIG_BASED PPDU.

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 87c245c85d9c..8b014456e6d8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -1032,7 +1032,6 @@ static void iwl_mvm_decode_he_phy_data(struct iwl_mvm *mvm,
 	case IWL_RX_PHY_INFO_TYPE_HE_TB:
 		/* HE common */
 		he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_LDPC_XSYMSEG_KNOWN |
-					 IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN |
 					 IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN |
 					 IEEE80211_RADIOTAP_HE_DATA1_DOPPLER_KNOWN |
 					 IEEE80211_RADIOTAP_HE_DATA1_BSS_COLOR_KNOWN);
@@ -1043,9 +1042,13 @@ static void iwl_mvm_decode_he_phy_data(struct iwl_mvm *mvm,
 		he->data3 |= le16_encode_bits(le32_get_bits(phy_data->d0,
 							    IWL_RX_PHY_DATA0_HE_BSS_COLOR_MASK),
 					      IEEE80211_RADIOTAP_HE_DATA3_BSS_COLOR);
-		he->data3 |= le16_encode_bits(le32_get_bits(phy_data->d0,
+		if (phy_data->info_type != IWL_RX_PHY_INFO_TYPE_HE_TB &&
+		    phy_data->info_type != IWL_RX_PHY_INFO_TYPE_HE_TB_EXT) {
+			he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN);
+			he->data3 |= le16_encode_bits(le32_get_bits(phy_data->d0,
 							    IWL_RX_PHY_DATA0_HE_UPLINK),
-					      IEEE80211_RADIOTAP_HE_DATA3_UL_DL);
+						      IEEE80211_RADIOTAP_HE_DATA3_UL_DL);
+		}
 		he->data3 |= le16_encode_bits(le32_get_bits(phy_data->d0,
 							    IWL_RX_PHY_DATA0_HE_LDPC_EXT_SYM),
 					      IEEE80211_RADIOTAP_HE_DATA3_LDPC_XSYMSEG);
-- 
cgit v1.2.3


From 956343a61226e1af3d146386f70a059feb567d0c Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 20 Aug 2018 10:07:32 +0300
Subject: iwlwifi: pcie: set cmd_len in the correct place

command len is set too early in the code, since when building
AMSDU, the size changes. This causes the byte count table to
have the wrong size.

Fixes: a0ec0169b7a9 ("iwlwifi: support new tx api")
Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 24 +++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 0c5f11d2c5da..16e8c3eb09b8 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -583,18 +583,6 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
 	spin_lock(&txq->lock);
 
-	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
-		struct iwl_tx_cmd_gen3 *tx_cmd_gen3 =
-			(void *)dev_cmd->payload;
-
-		cmd_len = le16_to_cpu(tx_cmd_gen3->len);
-	} else {
-		struct iwl_tx_cmd_gen2 *tx_cmd_gen2 =
-			(void *)dev_cmd->payload;
-
-		cmd_len = le16_to_cpu(tx_cmd_gen2->len);
-	}
-
 	if (iwl_queue_space(trans, txq) < txq->high_mark) {
 		iwl_stop_queue(trans, txq);
 
@@ -632,6 +620,18 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 		return -1;
 	}
 
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		struct iwl_tx_cmd_gen3 *tx_cmd_gen3 =
+			(void *)dev_cmd->payload;
+
+		cmd_len = le16_to_cpu(tx_cmd_gen3->len);
+	} else {
+		struct iwl_tx_cmd_gen2 *tx_cmd_gen2 =
+			(void *)dev_cmd->payload;
+
+		cmd_len = le16_to_cpu(tx_cmd_gen2->len);
+	}
+
 	/* Set up entry for this TFD in Tx byte-count array */
 	iwl_pcie_gen2_update_byte_tbl(trans_pcie, txq, cmd_len,
 				      iwl_pcie_gen2_get_num_tbs(trans, tfd));
-- 
cgit v1.2.3


From 55ed14cdaec503bfe6a94f0524d0d2c9b7226aed Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Tue, 14 Aug 2018 16:49:30 +0300
Subject: iwlwifi: mvm: don't check if a pointer is set if it can't be unset

We used to have many versions of statistics notification
coming from the firmware. In one of the cleanup patches,
we forgot to clean the code that checks if data->general
is set. Since it is always set, remove the check.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rx.c | 37 +++++++++++++----------------
 1 file changed, 17 insertions(+), 20 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
index ef624833cf1b..6653a238f32e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
@@ -593,31 +593,28 @@ static void iwl_mvm_stat_iterator(void *_data, u8 *mac,
 	int hyst = vif->bss_conf.cqm_rssi_hyst;
 	u16 id = le32_to_cpu(data->mac_id);
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	u16 vif_id = mvmvif->id;
 
 	/* This doesn't need the MAC ID check since it's not taking the
 	 * data copied into the "data" struct, but rather the data from
 	 * the notification directly.
 	 */
-	if (data->general) {
-		u16 vif_id = mvmvif->id;
-
-		if (iwl_mvm_is_cdb_supported(mvm)) {
-			struct mvm_statistics_general_cdb *general =
-				data->general;
-
-			mvmvif->beacon_stats.num_beacons =
-				le32_to_cpu(general->beacon_counter[vif_id]);
-			mvmvif->beacon_stats.avg_signal =
-				-general->beacon_average_energy[vif_id];
-		} else {
-			struct mvm_statistics_general_v8 *general =
-				data->general;
-
-			mvmvif->beacon_stats.num_beacons =
-				le32_to_cpu(general->beacon_counter[vif_id]);
-			mvmvif->beacon_stats.avg_signal =
-				-general->beacon_average_energy[vif_id];
-		}
+	if (iwl_mvm_is_cdb_supported(mvm)) {
+		struct mvm_statistics_general_cdb *general =
+			data->general;
+
+		mvmvif->beacon_stats.num_beacons =
+			le32_to_cpu(general->beacon_counter[vif_id]);
+		mvmvif->beacon_stats.avg_signal =
+			-general->beacon_average_energy[vif_id];
+	} else {
+		struct mvm_statistics_general_v8 *general =
+			data->general;
+
+		mvmvif->beacon_stats.num_beacons =
+			le32_to_cpu(general->beacon_counter[vif_id]);
+		mvmvif->beacon_stats.avg_signal =
+			-general->beacon_average_energy[vif_id];
 	}
 
 	if (mvmvif->id != id)
-- 
cgit v1.2.3


From 4c8b85187c22ee65637035efd2ae0cb10836d8e8 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 12 Dec 2018 19:11:36 -0800
Subject: net/mlx5: Use lowercase 'X' for hex values

Apparently gcc is cool with upper case '0X' but it is not commonly used.
Replace '0X' with lowercase '0x' in mlx5_ifc.h file.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 60c1d49eb40c..a56bd3b1f579 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -3865,16 +3865,16 @@ enum {
 };
 
 enum mlx5_monitor_counter_ppcnt {
-	MLX5_QUERY_MONITOR_PPCNT_IN_RANGE_LENGTH_ERRORS      = 0X0,
-	MLX5_QUERY_MONITOR_PPCNT_OUT_OF_RANGE_LENGTH_FIELD   = 0X1,
-	MLX5_QUERY_MONITOR_PPCNT_FRAME_TOO_LONG_ERRORS       = 0X2,
-	MLX5_QUERY_MONITOR_PPCNT_FRAME_CHECK_SEQUENCE_ERRORS = 0X3,
-	MLX5_QUERY_MONITOR_PPCNT_ALIGNMENT_ERRORS            = 0X4,
-	MLX5_QUERY_MONITOR_PPCNT_IF_OUT_DISCARDS             = 0X5,
+	MLX5_QUERY_MONITOR_PPCNT_IN_RANGE_LENGTH_ERRORS      = 0x0,
+	MLX5_QUERY_MONITOR_PPCNT_OUT_OF_RANGE_LENGTH_FIELD   = 0x1,
+	MLX5_QUERY_MONITOR_PPCNT_FRAME_TOO_LONG_ERRORS       = 0x2,
+	MLX5_QUERY_MONITOR_PPCNT_FRAME_CHECK_SEQUENCE_ERRORS = 0x3,
+	MLX5_QUERY_MONITOR_PPCNT_ALIGNMENT_ERRORS            = 0x4,
+	MLX5_QUERY_MONITOR_PPCNT_IF_OUT_DISCARDS             = 0x5,
 };
 
 enum {
-	MLX5_QUERY_MONITOR_Q_COUNTER_RX_OUT_OF_BUFFER     = 0X4,
+	MLX5_QUERY_MONITOR_Q_COUNTER_RX_OUT_OF_BUFFER     = 0x4,
 };
 
 struct mlx5_ifc_monitor_counter_output_bits {
@@ -4780,7 +4780,7 @@ enum {
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS    = 0x0,
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS  = 0x1,
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_INNER_HEADERS    = 0x2,
-	MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0X3,
+	MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0x3,
 };
 
 struct mlx5_ifc_query_flow_group_out_bits {
-- 
cgit v1.2.3


From 06cc74af05c33091a9877b54f1821966b446003c Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Wed, 12 Dec 2018 19:11:37 -0800
Subject: IB/mlx5: Unify e-switch representors load approach between uplink and
 VFs

When in switchdev mode and the add function is called by the core
level driver, make sure we only register the callbacks, but don't
create the mlx5 IB device or initialize anything. With this change
all the IB devices in switchdev mode are created only once the load
callback is invoked by the e-switch core sub-module. This follows
the design paradigm under which the all the Eth representors must
be loaded before any of IB reprs is loaded.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Acked-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/ib_rep.c  | 11 ++++++++++-
 drivers/infiniband/hw/mlx5/main.c    | 29 +++++++++--------------------
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  1 -
 3 files changed, 19 insertions(+), 22 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index 8a682d86d634..46a9ddc8ca56 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -48,13 +48,21 @@ static const struct mlx5_ib_profile rep_profile = {
 static int
 mlx5_ib_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
+	struct mlx5_ib_dev *ibdev;
+
+	ibdev = mlx5_ib_rep_to_dev(rep);
+	if (!__mlx5_ib_add(ibdev, ibdev->profile))
+		return -EINVAL;
 	return 0;
 }
 
 static void
 mlx5_ib_nic_rep_unload(struct mlx5_eswitch_rep *rep)
 {
-	rep->rep_if[REP_IB].priv = NULL;
+	struct mlx5_ib_dev *ibdev;
+
+	ibdev = mlx5_ib_rep_to_dev(rep);
+	__mlx5_ib_remove(ibdev, ibdev->profile, MLX5_IB_STAGE_MAX);
 }
 
 static int
@@ -89,6 +97,7 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	dev = mlx5_ib_rep_to_dev(rep);
 	__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
 	rep->rep_if[REP_IB].priv = NULL;
+	ib_dealloc_device(&dev->ib_dev);
 }
 
 static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 2560996fce79..4a4200a88957 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -6214,18 +6214,6 @@ static void mlx5_ib_stage_delay_drop_cleanup(struct mlx5_ib_dev *dev)
 	cancel_delay_drop(dev);
 }
 
-static int mlx5_ib_stage_rep_reg_init(struct mlx5_ib_dev *dev)
-{
-	mlx5_ib_register_vport_reps(dev);
-
-	return 0;
-}
-
-static void mlx5_ib_stage_rep_reg_cleanup(struct mlx5_ib_dev *dev)
-{
-	mlx5_ib_unregister_vport_reps(dev);
-}
-
 static int mlx5_ib_stage_dev_notifier_init(struct mlx5_ib_dev *dev)
 {
 	dev->mdev_events.notifier_call = mlx5_ib_event;
@@ -6264,8 +6252,6 @@ void __mlx5_ib_remove(struct mlx5_ib_dev *dev,
 		if (profile->stage[stage].cleanup)
 			profile->stage[stage].cleanup(dev);
 	}
-
-	ib_dealloc_device((struct ib_device *)dev);
 }
 
 void *__mlx5_ib_add(struct mlx5_ib_dev *dev,
@@ -6399,9 +6385,6 @@ static const struct mlx5_ib_profile nic_rep_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_POST_IB_REG_UMR,
 		     mlx5_ib_stage_post_ib_reg_umr_init,
 		     NULL),
-	STAGE_CREATE(MLX5_IB_STAGE_REP_REG,
-		     mlx5_ib_stage_rep_reg_init,
-		     mlx5_ib_stage_rep_reg_cleanup),
 };
 
 static void *mlx5_ib_add_slave_port(struct mlx5_core_dev *mdev)
@@ -6469,8 +6452,9 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	if (MLX5_ESWITCH_MANAGER(mdev) &&
 	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
 		dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0);
-
-		return __mlx5_ib_add(dev, &nic_rep_profile);
+		dev->profile = &nic_rep_profile;
+		mlx5_ib_register_vport_reps(dev);
+		return dev;
 	}
 
 	return __mlx5_ib_add(dev, &pf_profile);
@@ -6492,7 +6476,12 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 	}
 
 	dev = context;
-	__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
+	if (dev->profile == &nic_rep_profile)
+		mlx5_ib_unregister_vport_reps(dev);
+	else
+		__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
+
+	ib_dealloc_device((struct ib_device *)dev);
 }
 
 static struct mlx5_interface mlx5_ib_interface = {
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 861b68f2e330..c89b3b44b22e 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -790,7 +790,6 @@ enum mlx5_ib_stages {
 	MLX5_IB_STAGE_POST_IB_REG_UMR,
 	MLX5_IB_STAGE_DELAY_DROP,
 	MLX5_IB_STAGE_CLASS_ATTR,
-	MLX5_IB_STAGE_REP_REG,
 	MLX5_IB_STAGE_MAX,
 };
 
-- 
cgit v1.2.3


From 8bb957d2557db072b46f6a1339c2dd709bb25ef6 Mon Sep 17 00:00:00 2001
From: Shahar Klein <shahark@mellanox.com>
Date: Wed, 12 Dec 2018 19:11:38 -0800
Subject: net/mlx5: E-Switch, Introduce flow counter affinity

This dictates the device affinity for eswitch flow counters, set by the FW
according to the HW device capabilities.

Under "source eswitch" affinity, the counter should be allocated on the
device related to the source vport in the match. This covers both non
merged e-switch mode as well as old FW that does not advertise this cap.

Under "flow eswitch" affinity, the counter should be allocated on the
device where the eswitch rule is set.

Signed-off-by: Shahar Klein <shahark@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index a56bd3b1f579..f48d7ee345ff 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -608,13 +608,19 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 	u8      reserved_at_800[0x7800];
 };
 
+enum {
+	MLX5_COUNTER_SOURCE_ESWITCH = 0x0,
+	MLX5_COUNTER_FLOW_ESWITCH   = 0x1,
+};
+
 struct mlx5_ifc_e_switch_cap_bits {
 	u8         vport_svlan_strip[0x1];
 	u8         vport_cvlan_strip[0x1];
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert_if_not_exist[0x1];
 	u8         vport_cvlan_insert_overwrite[0x1];
-	u8         reserved_at_5[0x18];
+	u8         reserved_at_5[0x17];
+	u8         counter_eswitch_affinity[0x1];
 	u8         merged_eswitch[0x1];
 	u8         nic_vport_node_guid_modify[0x1];
 	u8         nic_vport_port_guid_modify[0x1];
-- 
cgit v1.2.3


From 8252cf728ce230bab2f5898449ffe94ff02c3622 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Wed, 12 Dec 2018 19:11:39 -0800
Subject: net/mlx5: Split the activate lag function into two routines

Split the activate lag function in order to be symmetric with
the deactivate lag function.

Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Shahar Klein <shahark@mellanox.com>
Reviewed-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 582b2f18010a..75f7c8efaab5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -186,14 +186,12 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 		*port2 = 1;
 }
 
-static void mlx5_activate_lag(struct mlx5_lag *ldev,
-			      struct lag_tracker *tracker)
+static int mlx5_create_lag(struct mlx5_lag *ldev,
+			   struct lag_tracker *tracker)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
 	int err;
 
-	ldev->flags |= MLX5_LAG_FLAG_BONDED;
-
 	mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[0],
 				       &ldev->v2p_map[1]);
 
@@ -202,6 +200,14 @@ static void mlx5_activate_lag(struct mlx5_lag *ldev,
 		mlx5_core_err(dev0,
 			      "Failed to create LAG (%d)\n",
 			      err);
+	return err;
+}
+
+static void mlx5_activate_lag(struct mlx5_lag *ldev,
+			      struct lag_tracker *tracker)
+{
+	ldev->flags |= MLX5_LAG_FLAG_BONDED;
+	mlx5_create_lag(ldev, tracker);
 }
 
 static void mlx5_deactivate_lag(struct mlx5_lag *ldev)
-- 
cgit v1.2.3


From 3cfe432e1b3a6f5b48f146f72d6dde029a1640a1 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Wed, 12 Dec 2018 19:11:40 -0800
Subject: net/mlx5: Add lag affinity info to log

Report the initial LAG port affinity upon LAG creation.

Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Shahar Klein <shahark@mellanox.com>
Reviewed-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 75f7c8efaab5..448d9d5c689c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -195,6 +195,9 @@ static int mlx5_create_lag(struct mlx5_lag *ldev,
 	mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[0],
 				       &ldev->v2p_map[1]);
 
+	mlx5_core_info(dev0, "lag map port 1:%d port 2:%d",
+		       ldev->v2p_map[0], ldev->v2p_map[1]);
+
 	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[0], ldev->v2p_map[1]);
 	if (err)
 		mlx5_core_err(dev0,
-- 
cgit v1.2.3


From 4c283e6155988486e2c83a2f273f919ecd3ce721 Mon Sep 17 00:00:00 2001
From: Shahar Klein <shahark@mellanox.com>
Date: Wed, 12 Dec 2018 19:11:41 -0800
Subject: net/mlx5: Fold the modify lag code into function

Handle the code of modifying the lag affinity within a separate function.

Signed-off-by: Shahar Klein <shahark@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 44 +++++++++++++++++----------
 1 file changed, 28 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 448d9d5c689c..8c5c5e418d61 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -186,6 +186,32 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 		*port2 = 1;
 }
 
+static void mlx5_modify_lag(struct mlx5_lag *ldev,
+			    struct lag_tracker *tracker)
+{
+	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	u8 v2p_port1, v2p_port2;
+	int err;
+
+	mlx5_infer_tx_affinity_mapping(tracker, &v2p_port1,
+				       &v2p_port2);
+
+	if (v2p_port1 != ldev->v2p_map[0] ||
+	    v2p_port2 != ldev->v2p_map[1]) {
+		ldev->v2p_map[0] = v2p_port1;
+		ldev->v2p_map[1] = v2p_port2;
+
+		mlx5_core_info(dev0, "modify lag map port 1:%d port 2:%d",
+			       ldev->v2p_map[0], ldev->v2p_map[1]);
+
+		err = mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2);
+		if (err)
+			mlx5_core_err(dev0,
+				      "Failed to modify LAG (%d)\n",
+				      err);
+	}
+}
+
 static int mlx5_create_lag(struct mlx5_lag *ldev,
 			   struct lag_tracker *tracker)
 {
@@ -232,8 +258,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
 	struct mlx5_core_dev *dev1 = ldev->pf[1].dev;
 	struct lag_tracker tracker;
-	u8 v2p_port1, v2p_port2;
-	int i, err;
+	int i;
 	bool do_bond;
 
 	if (!dev0 || !dev1)
@@ -255,20 +280,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 		mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
 		mlx5_nic_vport_enable_roce(dev1);
 	} else if (do_bond && mlx5_lag_is_bonded(ldev)) {
-		mlx5_infer_tx_affinity_mapping(&tracker, &v2p_port1,
-					       &v2p_port2);
-
-		if ((v2p_port1 != ldev->v2p_map[0]) ||
-		    (v2p_port2 != ldev->v2p_map[1])) {
-			ldev->v2p_map[0] = v2p_port1;
-			ldev->v2p_map[1] = v2p_port2;
-
-			err = mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2);
-			if (err)
-				mlx5_core_err(dev0,
-					      "Failed to modify LAG (%d)\n",
-					      err);
-		}
+		mlx5_modify_lag(ldev, &tracker);
 	} else if (!do_bond && mlx5_lag_is_bonded(ldev)) {
 		mlx5_remove_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
 		mlx5_nic_vport_disable_roce(dev1);
-- 
cgit v1.2.3


From 2aa55dccf83d7ca9f1da59ae005426c44fbeb890 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 10 Dec 2018 21:44:34 +0100
Subject: hns3: prevent building without CONFIG_INET

We now get a link failure when CONFIG_INET is disabled, since
tcp_gro_complete is unavailable:

drivers/net/ethernet/hisilicon/hns3/hns3_enet.o: In function `hns3_set_gro_param':
hns3_enet.c:(.text+0x230c): undefined reference to `tcp_gro_complete'

Add an explicit CONFIG_INET dependency here to avoid the broken
configuration.

Fixes: a6d53b97a2e7 ("net: hns3: Adds GRO params to SKB for the stack")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 25152715396b..fee4664c9189 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -118,6 +118,7 @@ config HNS3_ENET
 	tristate "Hisilicon HNS3 Ethernet Device Support"
 	default m
 	depends on 64BIT && PCI
+	depends on INET
 	---help---
 	  This selects the Ethernet Driver for Hisilicon Network Subsystem 3 for hip08
 	  family of SoCs. This module depends upon HNAE3 driver to access the HNAE3
-- 
cgit v1.2.3


From c2c79a32fb860ee374afe58fee6d67ab6aa83081 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 10 Dec 2018 22:52:56 +0100
Subject: hamradio, ppp: change semaphore to completion

ppp and hamradio have copies of the same code that uses a semaphore
in place of a completion for historic reasons. Make it use the
proper interface instead in all copies.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hamradio/6pack.c | 10 +++++-----
 drivers/net/hamradio/mkiss.c |  8 ++++----
 drivers/net/ppp/ppp_async.c  |  8 ++++----
 3 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 17e6dcd2eb42..28c749980359 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -120,7 +120,7 @@ struct sixpack {
 	struct timer_list	tx_t;
 	struct timer_list	resync_t;
 	refcount_t		refcnt;
-	struct semaphore	dead_sem;
+	struct completion	dead;
 	spinlock_t		lock;
 };
 
@@ -389,7 +389,7 @@ static struct sixpack *sp_get(struct tty_struct *tty)
 static void sp_put(struct sixpack *sp)
 {
 	if (refcount_dec_and_test(&sp->refcnt))
-		up(&sp->dead_sem);
+		complete(&sp->dead);
 }
 
 /*
@@ -576,7 +576,7 @@ static int sixpack_open(struct tty_struct *tty)
 
 	spin_lock_init(&sp->lock);
 	refcount_set(&sp->refcnt, 1);
-	sema_init(&sp->dead_sem, 0);
+	init_completion(&sp->dead);
 
 	/* !!! length of the buffers. MTU is IP MTU, not PACLEN!  */
 
@@ -670,10 +670,10 @@ static void sixpack_close(struct tty_struct *tty)
 	 * we have to wait for all existing users to finish.
 	 */
 	if (!refcount_dec_and_test(&sp->refcnt))
-		down(&sp->dead_sem);
+		wait_for_completion(&sp->dead);
 
 	/* We must stop the queue to avoid potentially scribbling
-	 * on the free buffers. The sp->dead_sem is not sufficient
+	 * on the free buffers. The sp->dead completion is not sufficient
 	 * to protect us from sp->xbuff access.
 	 */
 	netif_stop_queue(sp->dev);
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 802233d41b25..4938cf4c184c 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -81,7 +81,7 @@ struct mkiss {
 #define CRC_MODE_SMACK_TEST	4
 
 	atomic_t		refcnt;
-	struct semaphore	dead_sem;
+	struct completion	dead;
 };
 
 /*---------------------------------------------------------------------------*/
@@ -687,7 +687,7 @@ static struct mkiss *mkiss_get(struct tty_struct *tty)
 static void mkiss_put(struct mkiss *ax)
 {
 	if (atomic_dec_and_test(&ax->refcnt))
-		up(&ax->dead_sem);
+		complete(&ax->dead);
 }
 
 static int crc_force = 0;	/* Can be overridden with insmod */
@@ -715,7 +715,7 @@ static int mkiss_open(struct tty_struct *tty)
 
 	spin_lock_init(&ax->buflock);
 	atomic_set(&ax->refcnt, 1);
-	sema_init(&ax->dead_sem, 0);
+	init_completion(&ax->dead);
 
 	ax->tty = tty;
 	tty->disc_data = ax;
@@ -795,7 +795,7 @@ static void mkiss_close(struct tty_struct *tty)
 	 * we have to wait for all existing users to finish.
 	 */
 	if (!atomic_dec_and_test(&ax->refcnt))
-		down(&ax->dead_sem);
+		wait_for_completion(&ax->dead);
 	/*
 	 * Halt the transmit queue so that a new transmit cannot scribble
 	 * on our buffers
diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index bdc4d23627c5..288cf099876b 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -70,7 +70,7 @@ struct asyncppp {
 	struct tasklet_struct tsk;
 
 	refcount_t	refcnt;
-	struct semaphore dead_sem;
+	struct completion dead;
 	struct ppp_channel chan;	/* interface to generic ppp layer */
 	unsigned char	obuf[OBUFSIZE];
 };
@@ -148,7 +148,7 @@ static struct asyncppp *ap_get(struct tty_struct *tty)
 static void ap_put(struct asyncppp *ap)
 {
 	if (refcount_dec_and_test(&ap->refcnt))
-		up(&ap->dead_sem);
+		complete(&ap->dead);
 }
 
 /*
@@ -186,7 +186,7 @@ ppp_asynctty_open(struct tty_struct *tty)
 	tasklet_init(&ap->tsk, ppp_async_process, (unsigned long) ap);
 
 	refcount_set(&ap->refcnt, 1);
-	sema_init(&ap->dead_sem, 0);
+	init_completion(&ap->dead);
 
 	ap->chan.private = ap;
 	ap->chan.ops = &async_ops;
@@ -235,7 +235,7 @@ ppp_asynctty_close(struct tty_struct *tty)
 	 * by the time it returns.
 	 */
 	if (!refcount_dec_and_test(&ap->refcnt))
-		down(&ap->dead_sem);
+		wait_for_completion(&ap->dead);
 	tasklet_kill(&ap->tsk);
 
 	ppp_unregister_channel(&ap->chan);
-- 
cgit v1.2.3


From fadd59fc50d010145f251db583c7ccef37393d19 Mon Sep 17 00:00:00 2001
From: Aviv Heller <avivh@mellanox.com>
Date: Tue, 4 Dec 2018 21:24:46 +0200
Subject: net/mlx5: Introduce inter-device communication mechanism

This introduces devcom, a generic mechanism for performing operations
on both physical functions of the same Connect-X card.

The first user of this API is merged eswitch, which will be introduced
in subsequent patches.

Signed-off-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 .../net/ethernet/mellanox/mlx5/core/lib/devcom.c   | 255 +++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/lib/devcom.h   |  44 ++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  14 +-
 include/linux/mlx5/driver.h                        |   2 +
 5 files changed, 313 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 9678051b8ff1..9de9abacf7f6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -15,7 +15,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \
 		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
 		fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
-		diag/fs_tracepoint.o diag/fw_tracer.o
+		lib/devcom.o diag/fs_tracepoint.o diag/fw_tracer.o
 
 #
 # Netdev basic
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
new file mode 100644
index 000000000000..bced2efe9bef
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
@@ -0,0 +1,255 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2018 Mellanox Technologies */
+
+#include <linux/mlx5/vport.h>
+#include "lib/devcom.h"
+
+static LIST_HEAD(devcom_list);
+
+#define devcom_for_each_component(priv, comp, iter) \
+	for (iter = 0; \
+	     comp = &(priv)->components[iter], iter < MLX5_DEVCOM_NUM_COMPONENTS; \
+	     iter++)
+
+struct mlx5_devcom_component {
+	struct {
+		void *data;
+	} device[MLX5_MAX_PORTS];
+
+	mlx5_devcom_event_handler_t handler;
+	struct rw_semaphore sem;
+	bool paired;
+};
+
+struct mlx5_devcom_list {
+	struct list_head list;
+
+	struct mlx5_devcom_component components[MLX5_DEVCOM_NUM_COMPONENTS];
+	struct mlx5_core_dev *devs[MLX5_MAX_PORTS];
+};
+
+struct mlx5_devcom {
+	struct mlx5_devcom_list *priv;
+	int idx;
+};
+
+static struct mlx5_devcom_list *mlx5_devcom_list_alloc(void)
+{
+	struct mlx5_devcom_component *comp;
+	struct mlx5_devcom_list *priv;
+	int i;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return NULL;
+
+	devcom_for_each_component(priv, comp, i)
+		init_rwsem(&comp->sem);
+
+	return priv;
+}
+
+static struct mlx5_devcom *mlx5_devcom_alloc(struct mlx5_devcom_list *priv,
+					     u8 idx)
+{
+	struct mlx5_devcom *devcom;
+
+	devcom = kzalloc(sizeof(*devcom), GFP_KERNEL);
+	if (!devcom)
+		return NULL;
+
+	devcom->priv = priv;
+	devcom->idx = idx;
+	return devcom;
+}
+
+/* Must be called with intf_mutex held */
+struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev)
+{
+	struct mlx5_devcom_list *priv = NULL, *iter;
+	struct mlx5_devcom *devcom = NULL;
+	bool new_priv = false;
+	u64 sguid0, sguid1;
+	int idx, i;
+
+	if (!mlx5_core_is_pf(dev))
+		return NULL;
+
+	sguid0 = mlx5_query_nic_system_image_guid(dev);
+	list_for_each_entry(iter, &devcom_list, list) {
+		struct mlx5_core_dev *tmp_dev = NULL;
+
+		idx = -1;
+		for (i = 0; i < MLX5_MAX_PORTS; i++) {
+			if (iter->devs[i])
+				tmp_dev = iter->devs[i];
+			else
+				idx = i;
+		}
+
+		if (idx == -1)
+			continue;
+
+		sguid1 = mlx5_query_nic_system_image_guid(tmp_dev);
+		if (sguid0 != sguid1)
+			continue;
+
+		priv = iter;
+		break;
+	}
+
+	if (!priv) {
+		priv = mlx5_devcom_list_alloc();
+		if (!priv)
+			return ERR_PTR(-ENOMEM);
+
+		idx = 0;
+		new_priv = true;
+	}
+
+	priv->devs[idx] = dev;
+	devcom = mlx5_devcom_alloc(priv, idx);
+	if (!devcom) {
+		kfree(priv);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	if (new_priv)
+		list_add(&priv->list, &devcom_list);
+
+	return devcom;
+}
+
+/* Must be called with intf_mutex held */
+void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom)
+{
+	struct mlx5_devcom_list *priv;
+	int i;
+
+	if (IS_ERR_OR_NULL(devcom))
+		return;
+
+	priv = devcom->priv;
+	priv->devs[devcom->idx] = NULL;
+
+	kfree(devcom);
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (priv->devs[i])
+			break;
+
+	if (i != MLX5_MAX_PORTS)
+		return;
+
+	list_del(&priv->list);
+	kfree(priv);
+}
+
+void mlx5_devcom_register_component(struct mlx5_devcom *devcom,
+				    enum mlx5_devcom_components id,
+				    mlx5_devcom_event_handler_t handler,
+				    void *data)
+{
+	struct mlx5_devcom_component *comp;
+
+	if (IS_ERR_OR_NULL(devcom))
+		return;
+
+	WARN_ON(!data);
+
+	comp = &devcom->priv->components[id];
+	down_write(&comp->sem);
+	comp->handler = handler;
+	comp->device[devcom->idx].data = data;
+	up_write(&comp->sem);
+}
+
+void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom,
+				      enum mlx5_devcom_components id)
+{
+	struct mlx5_devcom_component *comp;
+
+	if (IS_ERR_OR_NULL(devcom))
+		return;
+
+	comp = &devcom->priv->components[id];
+	down_write(&comp->sem);
+	comp->device[devcom->idx].data = NULL;
+	up_write(&comp->sem);
+}
+
+int mlx5_devcom_send_event(struct mlx5_devcom *devcom,
+			   enum mlx5_devcom_components id,
+			   int event,
+			   void *event_data)
+{
+	struct mlx5_devcom_component *comp;
+	int err = -ENODEV, i;
+
+	if (IS_ERR_OR_NULL(devcom))
+		return err;
+
+	comp = &devcom->priv->components[id];
+	down_write(&comp->sem);
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (i != devcom->idx && comp->device[i].data) {
+			err = comp->handler(event, comp->device[i].data,
+					    event_data);
+			break;
+		}
+
+	up_write(&comp->sem);
+	return err;
+}
+
+void mlx5_devcom_set_paired(struct mlx5_devcom *devcom,
+			    enum mlx5_devcom_components id,
+			    bool paired)
+{
+	struct mlx5_devcom_component *comp;
+
+	comp = &devcom->priv->components[id];
+	WARN_ON(!rwsem_is_locked(&comp->sem));
+
+	comp->paired = paired;
+}
+
+bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom,
+			   enum mlx5_devcom_components id)
+{
+	if (IS_ERR_OR_NULL(devcom))
+		return false;
+
+	return devcom->priv->components[id].paired;
+}
+
+void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom,
+				enum mlx5_devcom_components id)
+{
+	struct mlx5_devcom_component *comp;
+	int i;
+
+	if (IS_ERR_OR_NULL(devcom))
+		return NULL;
+
+	comp = &devcom->priv->components[id];
+	down_read(&comp->sem);
+	if (!comp->paired) {
+		up_read(&comp->sem);
+		return NULL;
+	}
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (i != devcom->idx)
+			break;
+
+	return comp->device[i].data;
+}
+
+void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom,
+				   enum mlx5_devcom_components id)
+{
+	struct mlx5_devcom_component *comp = &devcom->priv->components[id];
+
+	up_read(&comp->sem);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
new file mode 100644
index 000000000000..f2d338b187a6
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies */
+
+#ifndef __LIB_MLX5_DEVCOM_H__
+#define __LIB_MLX5_DEVCOM_H__
+
+#include <linux/mlx5/driver.h>
+
+enum mlx5_devcom_components {
+	MLX5_DEVCOM_NUM_COMPONENTS,
+};
+
+typedef int (*mlx5_devcom_event_handler_t)(int event,
+					   void *my_data,
+					   void *event_data);
+
+struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev);
+void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom);
+
+void mlx5_devcom_register_component(struct mlx5_devcom *devcom,
+				    enum mlx5_devcom_components id,
+				    mlx5_devcom_event_handler_t handler,
+				    void *data);
+void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom,
+				      enum mlx5_devcom_components id);
+
+int mlx5_devcom_send_event(struct mlx5_devcom *devcom,
+			   enum mlx5_devcom_components id,
+			   int event,
+			   void *event_data);
+
+void mlx5_devcom_set_paired(struct mlx5_devcom *devcom,
+			    enum mlx5_devcom_components id,
+			    bool paired);
+bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom,
+			   enum mlx5_devcom_components id);
+
+void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom,
+				enum mlx5_devcom_components id);
+void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom,
+				   enum mlx5_devcom_components id);
+
+#endif
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 778995573812..c23553164e0d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -63,6 +63,7 @@
 #include "accel/tls.h"
 #include "lib/clock.h"
 #include "lib/vxlan.h"
+#include "lib/devcom.h"
 #include "diag/fw_tracer.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
@@ -722,16 +723,21 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	struct pci_dev *pdev = dev->pdev;
 	int err;
 
+	priv->devcom = mlx5_devcom_register_device(dev);
+	if (IS_ERR(priv->devcom))
+		dev_err(&pdev->dev, "failed to register with devcom (0x%p)\n",
+			priv->devcom);
+
 	err = mlx5_query_board_id(dev);
 	if (err) {
 		dev_err(&pdev->dev, "query board id failed\n");
-		goto out;
+		goto err_devcom;
 	}
 
 	err = mlx5_eq_table_init(dev);
 	if (err) {
 		dev_err(&pdev->dev, "failed to initialize eq\n");
-		goto out;
+		goto err_devcom;
 	}
 
 	err = mlx5_events_init(dev);
@@ -807,8 +813,9 @@ err_events_cleanup:
 	mlx5_events_cleanup(dev);
 err_eq_cleanup:
 	mlx5_eq_table_cleanup(dev);
+err_devcom:
+	mlx5_devcom_unregister_device(dev->priv.devcom);
 
-out:
 	return err;
 }
 
@@ -828,6 +835,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
+	mlx5_devcom_unregister_device(dev->priv.devcom);
 }
 
 static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index cc29e880c733..cd7af5d0311b 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -486,6 +486,7 @@ struct mlx5_events;
 struct mlx5_mpfs;
 struct mlx5_eswitch;
 struct mlx5_lag;
+struct mlx5_devcom;
 struct mlx5_eq_table;
 
 struct mlx5_rate_limit {
@@ -560,6 +561,7 @@ struct mlx5_priv {
 	struct mlx5_eswitch     *eswitch;
 	struct mlx5_core_sriov	sriov;
 	struct mlx5_lag		*lag;
+	struct mlx5_devcom	*devcom;
 	unsigned long		pci_dev_data;
 	struct mlx5_fc_stats		fc_stats;
 	struct mlx5_rl_table            rl_table;
-- 
cgit v1.2.3


From ac004b8321281b9da7d9a99674241e60e49ffc8a Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Sun, 11 Nov 2018 17:50:16 +0200
Subject: net/mlx5e: E-Switch, Add peer miss rules

In the sriov offloads mode, packets that are not matched by any
other rule are sent towards the e-switch vport manager for further
processing.

Under upcoming patches (e.g for uplink LAG), packets sent from VF
vports belonging to esw0 (e-switch related to PF0) might end up in
esw1 (e-switch related to PF1) due to muxing logic applied by the
FW.

In such a case we still want the missed packet to be sent to the
"base" esw manager vport in order to present the control plane a
consistent view of the source (VF reresentor) port.

Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Shahar Klein <shahark@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |   2 +
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 222 ++++++++++++++++++++-
 .../net/ethernet/mellanox/mlx5/core/lib/devcom.h   |   2 +
 3 files changed, 225 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 87c9dea9bccf..9dba6ad5744d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -143,6 +143,8 @@ struct mlx5_eswitch_fdb {
 		struct offloads_fdb {
 			struct mlx5_flow_table *slow_fdb;
 			struct mlx5_flow_group *send_to_vport_grp;
+			struct mlx5_flow_group *peer_miss_grp;
+			struct mlx5_flow_handle **peer_miss_rules;
 			struct mlx5_flow_group *miss_grp;
 			struct mlx5_flow_handle *miss_rule_uni;
 			struct mlx5_flow_handle *miss_rule_multi;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index bde1fb8c284b..a6927ca3d4ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -39,6 +39,7 @@
 #include "eswitch.h"
 #include "en.h"
 #include "fs_core.h"
+#include "lib/devcom.h"
 
 enum {
 	FDB_FAST_PATH = 0,
@@ -541,6 +542,98 @@ void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule)
 	mlx5_del_flow_rules(rule);
 }
 
+static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
+				  struct mlx5_flow_spec *spec,
+				  struct mlx5_flow_destination *dest)
+{
+	void *misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				  misc_parameters);
+
+	MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
+		 MLX5_CAP_GEN(peer_dev, vhca_id));
+
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			    misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+			 source_eswitch_owner_vhca_id);
+
+	dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+	dest->vport.num = 0;
+	dest->vport.vhca_id = MLX5_CAP_GEN(peer_dev, vhca_id);
+	dest->vport.vhca_id_valid = 1;
+}
+
+static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
+				       struct mlx5_core_dev *peer_dev)
+{
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {0};
+	struct mlx5_flow_handle **flows;
+	struct mlx5_flow_handle *flow;
+	struct mlx5_flow_spec *spec;
+	/* total vports is the same for both e-switches */
+	int nvports = esw->total_vports;
+	void *misc;
+	int err, i;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	peer_miss_rules_setup(peer_dev, spec, &dest);
+
+	flows = kvzalloc(nvports * sizeof(*flows), GFP_KERNEL);
+	if (!flows) {
+		err = -ENOMEM;
+		goto alloc_flows_err;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			    misc_parameters);
+
+	for (i = 1; i < nvports; i++) {
+		MLX5_SET(fte_match_set_misc, misc, source_port, i);
+		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
+			goto add_flow_err;
+		}
+		flows[i] = flow;
+	}
+
+	esw->fdb_table.offloads.peer_miss_rules = flows;
+
+	kvfree(spec);
+	return 0;
+
+add_flow_err:
+	for (i--; i > 0; i--)
+		mlx5_del_flow_rules(flows[i]);
+	kvfree(flows);
+alloc_flows_err:
+	kvfree(spec);
+	return err;
+}
+
+static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw)
+{
+	struct mlx5_flow_handle **flows;
+	int i;
+
+	flows = esw->fdb_table.offloads.peer_miss_rules;
+
+	for (i = 1; i < esw->total_vports; i++)
+		mlx5_del_flow_rules(flows[i]);
+
+	kvfree(flows);
+}
+
 static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
 {
 	struct mlx5_flow_act flow_act = {0};
@@ -811,7 +904,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 		esw->fdb_table.offloads.fdb_left[i] =
 			ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0;
 
-	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + 2;
+	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + 2 +
+		esw->total_vports;
 
 	/* create the slow path fdb with encap set, so further table instances
 	 * can be created at run time while VFs are probed if the FW allows that.
@@ -866,6 +960,34 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	}
 	esw->fdb_table.offloads.send_to_vport_grp = g;
 
+	/* create peer esw miss group */
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS);
+
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
+				      match_criteria);
+
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters.source_port);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters.source_eswitch_owner_vhca_id);
+
+	MLX5_SET(create_flow_group_in, flow_group_in,
+		 source_eswitch_owner_vhca_id_valid, 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+		 ix + esw->total_vports - 1);
+	ix += esw->total_vports;
+
+	g = mlx5_create_flow_group(fdb, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
+		goto peer_miss_err;
+	}
+	esw->fdb_table.offloads.peer_miss_grp = g;
+
 	/* create miss group */
 	memset(flow_group_in, 0, inlen);
 	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
@@ -898,6 +1020,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 miss_rule_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 miss_err:
+	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+peer_miss_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
 send_vport_err:
 	esw_destroy_offloads_fast_fdb_tables(esw);
@@ -917,6 +1041,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi);
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
+	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
@@ -1173,6 +1298,99 @@ err_reps:
 	return err;
 }
 
+#define ESW_OFFLOADS_DEVCOM_PAIR	(0)
+#define ESW_OFFLOADS_DEVCOM_UNPAIR	(1)
+
+static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw,
+				  struct mlx5_eswitch *peer_esw)
+{
+	int err;
+
+	err = esw_add_fdb_peer_miss_rules(esw, peer_esw->dev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
+{
+	esw_del_fdb_peer_miss_rules(esw);
+}
+
+static int mlx5_esw_offloads_devcom_event(int event,
+					  void *my_data,
+					  void *event_data)
+{
+	struct mlx5_eswitch *esw = my_data;
+	struct mlx5_eswitch *peer_esw = event_data;
+	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
+	int err;
+
+	switch (event) {
+	case ESW_OFFLOADS_DEVCOM_PAIR:
+		err = mlx5_esw_offloads_pair(esw, peer_esw);
+		if (err)
+			goto err_out;
+
+		err = mlx5_esw_offloads_pair(peer_esw, esw);
+		if (err)
+			goto err_pair;
+
+		mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, true);
+		break;
+
+	case ESW_OFFLOADS_DEVCOM_UNPAIR:
+		if (!mlx5_devcom_is_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS))
+			break;
+
+		mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false);
+		mlx5_esw_offloads_unpair(peer_esw);
+		mlx5_esw_offloads_unpair(esw);
+		break;
+	}
+
+	return 0;
+
+err_pair:
+	mlx5_esw_offloads_unpair(esw);
+
+err_out:
+	mlx5_core_err(esw->dev, "esw offloads devcom event failure, event %u err %d",
+		      event, err);
+	return err;
+}
+
+static void esw_offloads_devcom_init(struct mlx5_eswitch *esw)
+{
+	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
+
+	if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		return;
+
+	mlx5_devcom_register_component(devcom,
+				       MLX5_DEVCOM_ESW_OFFLOADS,
+				       mlx5_esw_offloads_devcom_event,
+				       esw);
+
+	mlx5_devcom_send_event(devcom,
+			       MLX5_DEVCOM_ESW_OFFLOADS,
+			       ESW_OFFLOADS_DEVCOM_PAIR, esw);
+}
+
+static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
+{
+	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
+
+	if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		return;
+
+	mlx5_devcom_send_event(devcom, MLX5_DEVCOM_ESW_OFFLOADS,
+			       ESW_OFFLOADS_DEVCOM_UNPAIR, esw);
+
+	mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+}
+
 int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
 {
 	int err;
@@ -1195,6 +1413,7 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
 	if (err)
 		goto err_reps;
 
+	esw_offloads_devcom_init(esw);
 	return 0;
 
 err_reps:
@@ -1233,6 +1452,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 
 void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports)
 {
+	esw_offloads_devcom_cleanup(esw);
 	esw_offloads_unload_reps(esw, nvports);
 	esw_destroy_vport_rx_group(esw);
 	esw_destroy_offloads_table(esw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
index f2d338b187a6..939d5bf1581b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -7,6 +7,8 @@
 #include <linux/mlx5/driver.h>
 
 enum mlx5_devcom_components {
+	MLX5_DEVCOM_ESW_OFFLOADS,
+
 	MLX5_DEVCOM_NUM_COMPONENTS,
 };
 
-- 
cgit v1.2.3


From 04de7dda7394fa9c2b0fc9cec65661d9b4f0d04d Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Sun, 11 Nov 2018 22:24:03 +0200
Subject: net/mlx5e: Infrastructure for duplicated offloading of TC flows

Under uplink LAG or multipath schemes, traffic that matches one flow
might arrive on both uplink ports and transmitted through both
as part of supporting aggregation and high-availability.

To cope with the fact that the SW model might use logical SW port
(e.g uplink team or bond) but we have two HW ports with e-switch on
each, there are cases where in order to offload a SW TC rule we
need to duplicate it to two HW flows.

Since each HW rule has its own counter we also aggregate the counter
of both rules when a flow stats query is executed from user-space.

Introduce the changes for the different elements (add/delete/stats),
currently nothing is duplicated.

Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Shahar Klein <shahark@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 174 ++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |   2 +
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c |   8 +-
 3 files changed, 176 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 0921213561cb..eacccac05dda 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -52,6 +52,7 @@
 #include "fs_core.h"
 #include "en/port.h"
 #include "en/tc_tun.h"
+#include "lib/devcom.h"
 
 struct mlx5_nic_flow_attr {
 	u32 action;
@@ -74,6 +75,7 @@ enum {
 	MLX5E_TC_FLOW_HAIRPIN	= BIT(MLX5E_TC_FLOW_BASE + 3),
 	MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(MLX5E_TC_FLOW_BASE + 4),
 	MLX5E_TC_FLOW_SLOW	  = BIT(MLX5E_TC_FLOW_BASE + 5),
+	MLX5E_TC_FLOW_DUP         = BIT(MLX5E_TC_FLOW_BASE + 6),
 };
 
 #define MLX5E_TC_MAX_SPLITS 1
@@ -111,8 +113,10 @@ struct mlx5e_tc_flow {
 	 * destinations.
 	 */
 	struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS];
+	struct mlx5e_tc_flow    *peer_flow;
 	struct list_head	mod_hdr; /* flows sharing the same mod hdr ID */
 	struct list_head	hairpin; /* flows sharing the same hairpin */
+	struct list_head	peer;    /* flows with peer flow */
 	union {
 		struct mlx5_esw_flow_attr esw_attr[0];
 		struct mlx5_nic_flow_attr nic_attr[0];
@@ -1249,13 +1253,48 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 	}
 }
 
+static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch;
+
+	if (!(flow->flags & MLX5E_TC_FLOW_ESWITCH) ||
+	    !(flow->flags & MLX5E_TC_FLOW_DUP))
+		return;
+
+	mutex_lock(&esw->offloads.peer_mutex);
+	list_del(&flow->peer);
+	mutex_unlock(&esw->offloads.peer_mutex);
+
+	flow->flags &= ~MLX5E_TC_FLOW_DUP;
+
+	mlx5e_tc_del_fdb_flow(flow->peer_flow->priv, flow->peer_flow);
+	kvfree(flow->peer_flow);
+	flow->peer_flow = NULL;
+}
+
+static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_core_dev *dev = flow->priv->mdev;
+	struct mlx5_devcom *devcom = dev->priv.devcom;
+	struct mlx5_eswitch *peer_esw;
+
+	peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	if (!peer_esw)
+		return;
+
+	__mlx5e_tc_del_fdb_peer_flow(flow);
+	mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+}
+
 static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow)
 {
-	if (flow->flags & MLX5E_TC_FLOW_ESWITCH)
+	if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
+		mlx5e_tc_del_fdb_peer_flow(flow);
 		mlx5e_tc_del_fdb_flow(priv, flow);
-	else
+	} else {
 		mlx5e_tc_del_nic_flow(priv, flow);
+	}
 }
 
 
@@ -2660,6 +2699,11 @@ static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv)
 		return &priv->fs.tc.ht;
 }
 
+static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow)
+{
+	return false;
+}
+
 static int
 mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size,
 		 struct tc_cls_flower_offload *f, u16 flow_flags,
@@ -2693,11 +2737,13 @@ err_free:
 }
 
 static int
-mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
-		   struct tc_cls_flower_offload *f,
-		   u16 flow_flags,
-		   struct net_device *filter_dev,
-		   struct mlx5e_tc_flow **__flow)
+__mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
+		     struct tc_cls_flower_offload *f,
+		     u16 flow_flags,
+		     struct net_device *filter_dev,
+		     struct mlx5_eswitch_rep *in_rep,
+		     struct mlx5_core_dev *in_mdev,
+		     struct mlx5e_tc_flow **__flow)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
@@ -2723,6 +2769,8 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto err_free;
 
+	flow->esw_attr->in_rep = in_rep;
+	flow->esw_attr->in_mdev = in_mdev;
 	err = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow, extack);
 	if (err)
 		goto err_free;
@@ -2738,6 +2786,87 @@ out:
 	return err;
 }
 
+static int mlx5e_tc_add_fdb_peer_flow(struct tc_cls_flower_offload *f,
+				      struct mlx5e_tc_flow *flow)
+{
+	struct mlx5e_priv *priv = flow->priv, *peer_priv;
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch, *peer_esw;
+	struct mlx5_devcom *devcom = priv->mdev->priv.devcom;
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
+	struct mlx5e_rep_priv *peer_urpriv;
+	struct mlx5e_tc_flow *peer_flow;
+	struct mlx5_core_dev *in_mdev;
+	int err = 0;
+
+	peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	if (!peer_esw)
+		return -ENODEV;
+
+	peer_urpriv = mlx5_eswitch_get_uplink_priv(peer_esw, REP_ETH);
+	peer_priv = netdev_priv(peer_urpriv->netdev);
+
+	/* in_mdev is assigned of which the packet originated from.
+	 * So packets redirected to uplink use the same mdev of the
+	 * original flow and packets redirected from uplink use the
+	 * peer mdev.
+	 */
+	if (flow->esw_attr->in_rep->vport == FDB_UPLINK_VPORT)
+		in_mdev = peer_priv->mdev;
+	else
+		in_mdev = priv->mdev;
+
+	parse_attr = flow->esw_attr->parse_attr;
+	err = __mlx5e_add_fdb_flow(peer_priv, f, flow->flags,
+				   parse_attr->filter_dev,
+				   flow->esw_attr->in_rep, in_mdev, &peer_flow);
+	if (err)
+		goto out;
+
+	flow->peer_flow = peer_flow;
+	flow->flags |= MLX5E_TC_FLOW_DUP;
+	mutex_lock(&esw->offloads.peer_mutex);
+	list_add_tail(&flow->peer, &esw->offloads.peer_flows);
+	mutex_unlock(&esw->offloads.peer_mutex);
+
+out:
+	mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	return err;
+}
+
+static int
+mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
+		   struct tc_cls_flower_offload *f,
+		   u16 flow_flags,
+		   struct net_device *filter_dev,
+		   struct mlx5e_tc_flow **__flow)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *in_rep = rpriv->rep;
+	struct mlx5_core_dev *in_mdev = priv->mdev;
+	struct mlx5e_tc_flow *flow;
+	int err;
+
+	err = __mlx5e_add_fdb_flow(priv, f, flow_flags, filter_dev, in_rep,
+				   in_mdev, &flow);
+	if (err)
+		goto out;
+
+	if (is_peer_flow_needed(flow)) {
+		err = mlx5e_tc_add_fdb_peer_flow(f, flow);
+		if (err) {
+			mlx5e_tc_del_fdb_flow(priv, flow);
+			goto out;
+		}
+	}
+
+	*__flow = flow;
+
+	return 0;
+
+out:
+	return err;
+}
+
 static int
 mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 		   struct tc_cls_flower_offload *f,
@@ -2882,7 +3011,9 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		       struct tc_cls_flower_offload *f, int flags)
 {
+	struct mlx5_devcom *devcom = priv->mdev->priv.devcom;
 	struct rhashtable *tc_ht = get_tc_ht(priv);
+	struct mlx5_eswitch *peer_esw;
 	struct mlx5e_tc_flow *flow;
 	struct mlx5_fc *counter;
 	u64 bytes;
@@ -2902,6 +3033,27 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 
 	mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
 
+	peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	if (!peer_esw)
+		goto out;
+
+	if ((flow->flags & MLX5E_TC_FLOW_DUP) &&
+	    (flow->peer_flow->flags & MLX5E_TC_FLOW_OFFLOADED)) {
+		u64 bytes2;
+		u64 packets2;
+		u64 lastuse2;
+
+		counter = mlx5e_tc_get_counter(flow->peer_flow);
+		mlx5_fc_query_cached(counter, &bytes2, &packets2, &lastuse2);
+
+		bytes += bytes2;
+		packets += packets2;
+		lastuse = max_t(u64, lastuse, lastuse2);
+	}
+
+	mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+
+out:
 	tcf_exts_stats_update(f->exts, bytes, packets, lastuse);
 
 	return 0;
@@ -3014,3 +3166,11 @@ int mlx5e_tc_num_filters(struct mlx5e_priv *priv)
 
 	return atomic_read(&tc_ht->nelems);
 }
+
+void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw)
+{
+	struct mlx5e_tc_flow *flow, *tmp;
+
+	list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows, peer)
+		__mlx5e_tc_del_fdb_peer_flow(flow);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 9dba6ad5744d..4d048f7e703b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -167,6 +167,8 @@ struct mlx5_esw_offload {
 	struct mlx5_flow_table *ft_offloads;
 	struct mlx5_flow_group *vport_rx_group;
 	struct mlx5_eswitch_rep *vport_reps;
+	struct list_head peer_flows;
+	struct mutex peer_mutex;
 	DECLARE_HASHTABLE(encap_tbl, 8);
 	DECLARE_HASHTABLE(mod_hdr_tbl, 8);
 	u8 inline_mode;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index a6927ca3d4ca..76cb57202474 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -563,7 +563,7 @@ static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
 	dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
 	dest->vport.num = 0;
 	dest->vport.vhca_id = MLX5_CAP_GEN(peer_dev, vhca_id);
-	dest->vport.vhca_id_valid = 1;
+	dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 }
 
 static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
@@ -1313,8 +1313,11 @@ static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw,
 	return 0;
 }
 
+void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw);
+
 static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
 {
+	mlx5e_tc_clean_fdb_peer_flows(esw);
 	esw_del_fdb_peer_miss_rules(esw);
 }
 
@@ -1365,6 +1368,9 @@ static void esw_offloads_devcom_init(struct mlx5_eswitch *esw)
 {
 	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
 
+	INIT_LIST_HEAD(&esw->offloads.peer_flows);
+	mutex_init(&esw->offloads.peer_mutex);
+
 	if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))
 		return;
 
-- 
cgit v1.2.3


From f9392795e2e35449a7dca46574b1a86eace20e9c Mon Sep 17 00:00:00 2001
From: Shahar Klein <shahark@mellanox.com>
Date: Thu, 30 Nov 2017 17:55:46 +0200
Subject: net/mlx5e: Enhance flow counter scheme for offloaded TC eswitch rules

Assign a counter dev attribute according to device capability and use
it for management of counters related to offloaded eswitch TC flows.

With upcoming support for uplink LAG, we have two HW rules per one
logical SW (TC) rule. Although the HW supports attaching one counter
to multiple rules, we are allocating counter per HW rule.

We need this separation for two reasons:

1. "flow eswitch" counter affinity HW require the counter to be
allocated on the device where the eswitch rule is set.

2. for some use-cases (multi-path routing) each HW flow relates to
different neighbour, hence our neigh update logic must have a per-rule
HW accountant in order to provide the proper feedback to the kernel.

Signed-off-by: Shahar Klein <shahark@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c   | 14 +++++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h |  1 +
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index eacccac05dda..779ca3a43bec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -994,7 +994,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	}
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
-		counter = mlx5_fc_create(esw->dev, true);
+		counter = mlx5_fc_create(attr->counter_dev, true);
 		if (IS_ERR(counter)) {
 			err = PTR_ERR(counter);
 			goto err_create_counter;
@@ -1023,7 +1023,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	return 0;
 
 err_add_rule:
-	mlx5_fc_destroy(esw->dev, counter);
+	mlx5_fc_destroy(attr->counter_dev, counter);
 err_create_counter:
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		mlx5e_detach_mod_hdr(priv, flow);
@@ -1064,7 +1064,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 		mlx5e_detach_mod_hdr(priv, flow);
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
-		mlx5_fc_destroy(esw->dev, attr->counter);
+		mlx5_fc_destroy(attr->counter_dev, attr->counter);
 }
 
 void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
@@ -2746,6 +2746,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 		     struct mlx5e_tc_flow **__flow)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_tc_flow *flow;
 	int attr_size, err;
@@ -2771,6 +2772,13 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 
 	flow->esw_attr->in_rep = in_rep;
 	flow->esw_attr->in_mdev = in_mdev;
+
+	if (MLX5_CAP_ESW(esw->dev, counter_eswitch_affinity) ==
+	    MLX5_COUNTER_SOURCE_ESWITCH)
+		flow->esw_attr->counter_dev = in_mdev;
+	else
+		flow->esw_attr->counter_dev = priv->mdev;
+
 	err = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow, extack);
 	if (err)
 		goto err_free;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 4d048f7e703b..701abd794dab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -293,6 +293,7 @@ enum {
 struct mlx5_esw_flow_attr {
 	struct mlx5_eswitch_rep *in_rep;
 	struct mlx5_core_dev	*in_mdev;
+	struct mlx5_core_dev    *counter_dev;
 
 	int split_count;
 	int out_count;
-- 
cgit v1.2.3


From 491c37e49b48e7a18dc79e29f3ac13e0c3d0fb54 Mon Sep 17 00:00:00 2001
From: Rabie Loulou <rabiel@mellanox.com>
Date: Wed, 6 Jun 2018 15:49:27 +0300
Subject: net/mlx5e: In case of LAG, one switch parent id is used for all
 representors

When the uplink representors are put into lag, set all the
representors (VFs and uplinks) of the same NIC to return the same
switchdev id.

Currently, the route lookup code on the encapsulation offload path
assumes that same switchdev id for the source and dest devices means
that the dest is also mlx5 HW netdev. This doesn't hold anymore when we
align the switchdev Id of the uplinks to be same, which in turn causes
the bond/team to return that id to the caller. As such, enhance the
relevant check to take into account the uplink lag case.

Signed-off-by: Rabie Loulou <rabiel@mellanox.com>
Signed-off-by: Aviv Heller <avivh@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    | 41 ++++++++++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   | 20 +++++++++--
 2 files changed, 48 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index c1515f013501..d5d161ab0dbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -14,7 +14,8 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 				   u8 *out_ttl)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5e_rep_priv *uplink_rpriv;
+	struct net_device *uplink_dev, *uplink_upper;
+	bool dst_is_lag_dev;
 	struct rtable *rt;
 	struct neighbour *n = NULL;
 
@@ -28,10 +29,20 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 #else
 	return -EOPNOTSUPP;
 #endif
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-	/* if the egress device isn't on the same HW e-switch, we use the uplink */
-	if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev))
-		*out_dev = uplink_rpriv->netdev;
+
+	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
+	uplink_upper = netdev_master_upper_dev_get(uplink_dev);
+	dst_is_lag_dev = (uplink_upper &&
+			  netif_is_lag_master(uplink_upper) &&
+			  rt->dst.dev == uplink_upper &&
+			  mlx5_lag_is_active(priv->mdev));
+
+	/* if the egress device isn't on the same HW e-switch or
+	 * it's a LAG device, use the uplink
+	 */
+	if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev) ||
+	    dst_is_lag_dev)
+		*out_dev = uplink_dev;
 	else
 		*out_dev = rt->dst.dev;
 
@@ -65,8 +76,9 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	struct dst_entry *dst;
 
 #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
-	struct mlx5e_rep_priv *uplink_rpriv;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct net_device *uplink_dev, *uplink_upper;
+	bool dst_is_lag_dev;
 	int ret;
 
 	ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst,
@@ -77,10 +89,19 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	if (!(*out_ttl))
 		*out_ttl = ip6_dst_hoplimit(dst);
 
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-	/* if the egress device isn't on the same HW e-switch, we use the uplink */
-	if (!switchdev_port_same_parent_id(priv->netdev, dst->dev))
-		*out_dev = uplink_rpriv->netdev;
+	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
+	uplink_upper = netdev_master_upper_dev_get(uplink_dev);
+	dst_is_lag_dev = (uplink_upper &&
+			  netif_is_lag_master(uplink_upper) &&
+			  dst->dev == uplink_upper &&
+			  mlx5_lag_is_active(priv->mdev));
+
+	/* if the egress device isn't on the same HW e-switch or
+	 * it's a LAG device, use the uplink
+	 */
+	if (!switchdev_port_same_parent_id(priv->netdev, dst->dev) ||
+	    dst_is_lag_dev)
+		*out_dev = uplink_dev;
 	else
 		*out_dev = dst->dev;
 #else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index e5230049612f..17f24127a3ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -297,17 +297,31 @@ static const struct ethtool_ops mlx5e_rep_ethtool_ops = {
 int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct net_device *uplink_upper = NULL;
+	struct mlx5e_priv *uplink_priv = NULL;
+	struct net_device *uplink_dev;
 
 	if (esw->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
 
+	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
+	if (uplink_dev) {
+		uplink_upper = netdev_master_upper_dev_get(uplink_dev);
+		uplink_priv = netdev_priv(uplink_dev);
+	}
+
 	switch (attr->id) {
 	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
 		attr->u.ppid.id_len = ETH_ALEN;
-		ether_addr_copy(attr->u.ppid.id, rep->hw_id);
+		if (uplink_upper && mlx5_lag_is_active(uplink_priv->mdev)) {
+			ether_addr_copy(attr->u.ppid.id, uplink_upper->dev_addr);
+		} else {
+			struct mlx5e_rep_priv *rpriv = priv->ppriv;
+			struct mlx5_eswitch_rep *rep = rpriv->rep;
+
+			ether_addr_copy(attr->u.ppid.id, rep->hw_id);
+		}
 		break;
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 7ba58ba7ba5e19324b3879000ef341966b19727b Mon Sep 17 00:00:00 2001
From: Rabie Loulou <rabiel@mellanox.com>
Date: Wed, 6 Jun 2018 16:27:08 +0300
Subject: net/mlx5e: Offload TC e-switch rules with egress LAG device

When parsing TC FDB actions, if the egress device is a bond/team
net-device which enslaved the uplink representor of the e-switch,
use the uplink representor as the destination in the HW rule.

Signed-off-by: Rabie Loulou <rabiel@mellanox.com>
Signed-off-by: Aviv Heller <avivh@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 779ca3a43bec..cede77fd208f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2574,6 +2574,15 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			if (switchdev_port_same_parent_id(priv->netdev,
 							  out_dev) ||
 			    is_merged_eswitch_dev(priv, out_dev)) {
+				struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+				struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
+				struct net_device *uplink_upper = netdev_master_upper_dev_get(uplink_dev);
+
+				if (uplink_upper &&
+				    netif_is_lag_master(uplink_upper) &&
+				    uplink_upper == out_dev)
+					out_dev = uplink_dev;
+
 				out_priv = netdev_priv(out_dev);
 				rpriv = out_priv->ppriv;
 				attr->dests[attr->out_count].rep = rpriv->rep;
-- 
cgit v1.2.3


From 1418ddd96afdb097ab9a2fe09c94e820d596321a Mon Sep 17 00:00:00 2001
From: Aviv Heller <avivh@mellanox.com>
Date: Tue, 2 Oct 2018 17:18:44 +0300
Subject: net/mlx5e: Duplicate offloaded TC eswitch rules under uplink LAG

Under uplink LAG, packets that match a flow might arrive on both uplink
ports and transmitted through both as part of supporting aggregation and
high-availability.

When the netdevs representing the uplinks are set into LAG (bonding,
teaming), duplicate the TC flow offloading into each of the per-uplink
e-switches.

Duplication is not required if the source is the bond device, since in
this case it is assumed that the bond and the uplink netdevs share the
same TC block, and thus duplication will occur naturally by the stack.

Note that under encapsulation scheme, both flows will use the same
neighbour and hence both will contribute to the last-used feedback
towards the stack.

Signed-off-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Rabie Loulou <rabiel@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index cede77fd208f..864f3b00d09d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2710,7 +2710,16 @@ static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv)
 
 static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow)
 {
-	return false;
+	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	bool is_rep_ingress = attr->in_rep->vport != FDB_UPLINK_VPORT &&
+			      flow->flags & MLX5E_TC_FLOW_INGRESS;
+	bool act_is_encap = !!(attr->action &
+			       MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT);
+	bool esw_paired = mlx5_devcom_is_paired(attr->in_mdev->priv.devcom,
+						MLX5_DEVCOM_ESW_OFFLOADS);
+
+	return esw_paired && mlx5_lag_is_active(attr->in_mdev) &&
+	       (is_rep_ingress || act_is_encap);
 }
 
 static int
-- 
cgit v1.2.3


From 3b5ff59fd851d8e8c7c3ba08b01011baffa60cb6 Mon Sep 17 00:00:00 2001
From: Rabie Loulou <rabiel@mellanox.com>
Date: Thu, 26 Apr 2018 16:45:41 +0300
Subject: net/mlx5: Adjustments for the activate LAG logic to run under sriov

When HW lag is set/unset, roce must not be enabled on the port, as such
we wrap such changes with roce enable/disable either directly or through
re-creation of IB device.

Currently, lag and sriov are mutually exclusive, so by definition this
code doesn't run under sriov.

Towards changing this exclusion, we need to make sure that roce will not
be enabled on the eswitch manager port under sriov since this is
requirement of the switchdev mode.

We are going strict here and avoiding this all together under sriov.

Signed-off-by: Rabie Loulou <rabiel@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 33 +++++++++++++++++----------
 1 file changed, 21 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 8c5c5e418d61..8127d907e1ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -34,6 +34,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/vport.h>
 #include "mlx5_core.h"
+#include "eswitch.h"
 
 enum {
 	MLX5_LAG_FLAG_BONDED = 1 << 0,
@@ -257,13 +258,15 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
 	struct mlx5_core_dev *dev1 = ldev->pf[1].dev;
+	bool do_bond, sriov_enabled;
 	struct lag_tracker tracker;
 	int i;
-	bool do_bond;
 
 	if (!dev0 || !dev1)
 		return;
 
+	sriov_enabled = mlx5_sriov_is_enabled(dev0) || mlx5_sriov_is_enabled(dev1);
+
 	mutex_lock(&lag_mutex);
 	tracker = ldev->tracker;
 	mutex_unlock(&lag_mutex);
@@ -271,26 +274,32 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	do_bond = tracker.is_bonded && ldev->allowed;
 
 	if (do_bond && !mlx5_lag_is_bonded(ldev)) {
-		for (i = 0; i < MLX5_MAX_PORTS; i++)
-			mlx5_remove_dev_by_protocol(ldev->pf[i].dev,
-						    MLX5_INTERFACE_PROTOCOL_IB);
+		if (!sriov_enabled)
+			for (i = 0; i < MLX5_MAX_PORTS; i++)
+				mlx5_remove_dev_by_protocol(ldev->pf[i].dev,
+							    MLX5_INTERFACE_PROTOCOL_IB);
 
 		mlx5_activate_lag(ldev, &tracker);
 
-		mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
-		mlx5_nic_vport_enable_roce(dev1);
+		if (!sriov_enabled) {
+			mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
+			mlx5_nic_vport_enable_roce(dev1);
+		}
 	} else if (do_bond && mlx5_lag_is_bonded(ldev)) {
 		mlx5_modify_lag(ldev, &tracker);
 	} else if (!do_bond && mlx5_lag_is_bonded(ldev)) {
-		mlx5_remove_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
-		mlx5_nic_vport_disable_roce(dev1);
+		if (!sriov_enabled) {
+			mlx5_remove_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
+			mlx5_nic_vport_disable_roce(dev1);
+		}
 
 		mlx5_deactivate_lag(ldev);
 
-		for (i = 0; i < MLX5_MAX_PORTS; i++)
-			if (ldev->pf[i].dev)
-				mlx5_add_dev_by_protocol(ldev->pf[i].dev,
-							 MLX5_INTERFACE_PROTOCOL_IB);
+		if (!sriov_enabled)
+			for (i = 0; i < MLX5_MAX_PORTS; i++)
+				if (ldev->pf[i].dev)
+					mlx5_add_dev_by_protocol(ldev->pf[i].dev,
+								 MLX5_INTERFACE_PROTOCOL_IB);
 	}
 }
 
-- 
cgit v1.2.3


From eff849b2c669ebf0df88762f082bcb252f8e883c Mon Sep 17 00:00:00 2001
From: Rabie Loulou <rabiel@mellanox.com>
Date: Wed, 6 Jun 2018 16:31:34 +0300
Subject: net/mlx5: Allow/disallow LAG according to pre-req only

Remove the lag forbid/allow functions, change the lag prereq check to
run in the do-bond logic, so every change in the prereq state will
cause LAG to be disabled/enabled accordingly after the next do-bond run.

Add lag update function, so every component which changes the prereq
state and want the LAG to re-calc the conditions can call the update
function.

Signed-off-by: Rabie Loulou <rabiel@mellanox.com>
Signed-off-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  | 13 +++++
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  4 ++
 drivers/net/ethernet/mellanox/mlx5/core/lag.c      | 62 ++++++----------------
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |  4 +-
 drivers/net/ethernet/mellanox/mlx5/core/sriov.c    | 14 +----
 5 files changed, 36 insertions(+), 61 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 4f9dd0d4a081..70d0d9aa6b5d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1632,6 +1632,8 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode);
 	esw->mode = mode;
 
+	mlx5_lag_update(esw->dev);
+
 	if (mode == SRIOV_LEGACY) {
 		err = esw_create_legacy_fdb_table(esw);
 	} else {
@@ -1708,6 +1710,8 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 	old_mode = esw->mode;
 	esw->mode = SRIOV_NONE;
 
+	mlx5_lag_update(esw->dev);
+
 	if (old_mode == SRIOV_OFFLOADS)
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 }
@@ -2225,3 +2229,12 @@ u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
 	return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE;
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
+
+bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1)
+{
+	if (dev0->priv.eswitch->mode == SRIOV_NONE &&
+	    dev1->priv.eswitch->mode == SRIOV_NONE)
+		return true;
+
+	return false;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 701abd794dab..9c89eea9b2c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -351,6 +351,9 @@ static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev
 		MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan_2);
 }
 
+bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0,
+			 struct mlx5_core_dev *dev1);
+
 #define MLX5_DEBUG_ESWITCH_MASK BIT(3)
 
 #define esw_info(dev, format, ...)				\
@@ -367,6 +370,7 @@ static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
 static inline int  mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; }
 static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) {}
+static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; }
 
 #define FDB_MAX_CHAIN 1
 #define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 8127d907e1ef..3b1dcd2969d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -62,11 +62,6 @@ struct mlx5_lag {
 	struct lag_tracker        tracker;
 	struct delayed_work       bond_work;
 	struct notifier_block     nb;
-
-	/* Admin state. Allow lag only if allowed is true
-	 * even if network conditions for lag were met
-	 */
-	bool                      allowed;
 };
 
 /* General purpose, use for short periods of time.
@@ -254,6 +249,16 @@ static void mlx5_deactivate_lag(struct mlx5_lag *ldev)
 			      err);
 }
 
+static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
+{
+	if (ldev->pf[0].dev &&
+	    ldev->pf[1].dev &&
+	    mlx5_esw_lag_prereq(ldev->pf[0].dev, ldev->pf[1].dev))
+		return true;
+	else
+		return false;
+}
+
 static void mlx5_do_bond(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
@@ -271,7 +276,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	tracker = ldev->tracker;
 	mutex_unlock(&lag_mutex);
 
-	do_bond = tracker.is_bonded && ldev->allowed;
+	do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);
 
 	if (do_bond && !mlx5_lag_is_bonded(ldev)) {
 		if (!sriov_enabled)
@@ -449,15 +454,6 @@ static int mlx5_lag_netdev_event(struct notifier_block *this,
 	return NOTIFY_DONE;
 }
 
-static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
-{
-	if ((ldev->pf[0].dev && mlx5_sriov_is_enabled(ldev->pf[0].dev)) ||
-	    (ldev->pf[1].dev && mlx5_sriov_is_enabled(ldev->pf[1].dev)))
-		return false;
-	else
-		return true;
-}
-
 static struct mlx5_lag *mlx5_lag_dev_alloc(void)
 {
 	struct mlx5_lag *ldev;
@@ -467,7 +463,6 @@ static struct mlx5_lag *mlx5_lag_dev_alloc(void)
 		return NULL;
 
 	INIT_DELAYED_WORK(&ldev->bond_work, mlx5_do_bond_work);
-	ldev->allowed = mlx5_lag_check_prereq(ldev);
 
 	return ldev;
 }
@@ -492,7 +487,6 @@ static void mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
 	ldev->tracker.netdev_state[fn].link_up = 0;
 	ldev->tracker.netdev_state[fn].tx_enabled = 0;
 
-	ldev->allowed = mlx5_lag_check_prereq(ldev);
 	dev->priv.lag = ldev;
 
 	mutex_unlock(&lag_mutex);
@@ -514,7 +508,6 @@ static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev,
 	memset(&ldev->pf[i], 0, sizeof(*ldev->pf));
 
 	dev->priv.lag = NULL;
-	ldev->allowed = mlx5_lag_check_prereq(ldev);
 	mutex_unlock(&lag_mutex);
 }
 
@@ -593,42 +586,19 @@ bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_lag_is_active);
 
-static int mlx5_lag_set_state(struct mlx5_core_dev *dev, bool allow)
+void mlx5_lag_update(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
-	int ret = 0;
-	bool lag_active;
 
 	mlx5_dev_list_lock();
-
 	ldev = mlx5_lag_dev_get(dev);
-	if (!ldev) {
-		ret = -ENODEV;
-		goto unlock;
-	}
-	lag_active = mlx5_lag_is_bonded(ldev);
-	if (!mlx5_lag_check_prereq(ldev) && allow) {
-		ret = -EINVAL;
-		goto unlock;
-	}
-	if (ldev->allowed == allow)
+	if (!ldev)
 		goto unlock;
-	ldev->allowed = allow;
-	if ((lag_active && !allow) || allow)
-		mlx5_do_bond(ldev);
-unlock:
-	mlx5_dev_list_unlock();
-	return ret;
-}
 
-int mlx5_lag_forbid(struct mlx5_core_dev *dev)
-{
-	return mlx5_lag_set_state(dev, false);
-}
+	mlx5_do_bond(ldev);
 
-int mlx5_lag_allow(struct mlx5_core_dev *dev)
-{
-	return mlx5_lag_set_state(dev, true);
+unlock:
+	mlx5_dev_list_unlock();
 }
 
 struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index fd3141a4b3f1..73bf46599ec6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -185,10 +185,8 @@ static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev)
 		    MLX5_CAP_GEN(dev, lag_master);
 }
 
-int mlx5_lag_allow(struct mlx5_core_dev *dev);
-int mlx5_lag_forbid(struct mlx5_core_dev *dev);
-
 void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol);
+void mlx5_lag_update(struct mlx5_core_dev *dev);
 
 enum {
 	MLX5_NIC_IFC_FULL		= 0,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index a0674962f02c..6e178030d8fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -216,20 +216,10 @@ int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	if (!mlx5_core_is_pf(dev))
 		return -EPERM;
 
-	if (num_vfs) {
-		int ret;
-
-		ret = mlx5_lag_forbid(dev);
-		if (ret && (ret != -ENODEV))
-			return ret;
-	}
-
-	if (num_vfs) {
+	if (num_vfs)
 		err = mlx5_sriov_enable(pdev, num_vfs);
-	} else {
+	else
 		mlx5_sriov_disable(pdev);
-		mlx5_lag_allow(dev);
-	}
 
 	return err ? err : num_vfs;
 }
-- 
cgit v1.2.3


From 8aaca1976e2757e15edf43866a0549b321a4222f Mon Sep 17 00:00:00 2001
From: Rabie Loulou <rabiel@mellanox.com>
Date: Wed, 23 May 2018 14:19:07 +0300
Subject: net/mlx5: Allow co-enablement of uplink LAG and SRIOV

Enable setting uplink LAG if sriov is enabled on both ports in switchdev
mode.

Once the sriov mode is changed from switchdev for any of the ports, the
LAG instance is disabled.

Signed-off-by: Rabie Loulou <rabiel@mellanox.com>
Signed-off-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 70d0d9aa6b5d..ef2bec50423d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2232,8 +2232,10 @@ EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
 
 bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1)
 {
-	if (dev0->priv.eswitch->mode == SRIOV_NONE &&
-	    dev1->priv.eswitch->mode == SRIOV_NONE)
+	if ((dev0->priv.eswitch->mode == SRIOV_NONE &&
+	     dev1->priv.eswitch->mode == SRIOV_NONE) ||
+	    (dev0->priv.eswitch->mode == SRIOV_OFFLOADS &&
+	     dev1->priv.eswitch->mode == SRIOV_OFFLOADS))
 		return true;
 
 	return false;
-- 
cgit v1.2.3


From 292612d68c4ed3063cdc99512e865a819b8c9423 Mon Sep 17 00:00:00 2001
From: Aviv Heller <avivh@mellanox.com>
Date: Thu, 23 Aug 2018 13:34:10 +0300
Subject: net/mlx5: Rename mlx5_lag_is_bonded() to __mlx5_lag_is_active()

The new name better represents the function's aim, and sets a precedent
for a '__' prefix for internal, non-locked versions of LAG APIs.

Signed-off-by: Aviv Heller <avivh@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 3b1dcd2969d7..db5ef7023371 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -161,7 +161,7 @@ static int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 	return -1;
 }
 
-static bool mlx5_lag_is_bonded(struct mlx5_lag *ldev)
+static bool __mlx5_lag_is_active(struct mlx5_lag *ldev)
 {
 	return !!(ldev->flags & MLX5_LAG_FLAG_BONDED);
 }
@@ -278,7 +278,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 
 	do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);
 
-	if (do_bond && !mlx5_lag_is_bonded(ldev)) {
+	if (do_bond && !__mlx5_lag_is_active(ldev)) {
 		if (!sriov_enabled)
 			for (i = 0; i < MLX5_MAX_PORTS; i++)
 				mlx5_remove_dev_by_protocol(ldev->pf[i].dev,
@@ -290,9 +290,9 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 			mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
 			mlx5_nic_vport_enable_roce(dev1);
 		}
-	} else if (do_bond && mlx5_lag_is_bonded(ldev)) {
+	} else if (do_bond && __mlx5_lag_is_active(ldev)) {
 		mlx5_modify_lag(ldev, &tracker);
-	} else if (!do_bond && mlx5_lag_is_bonded(ldev)) {
+	} else if (!do_bond && __mlx5_lag_is_active(ldev)) {
 		if (!sriov_enabled) {
 			mlx5_remove_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
 			mlx5_nic_vport_disable_roce(dev1);
@@ -555,7 +555,7 @@ void mlx5_lag_remove(struct mlx5_core_dev *dev)
 	if (!ldev)
 		return;
 
-	if (mlx5_lag_is_bonded(ldev))
+	if (__mlx5_lag_is_active(ldev))
 		mlx5_deactivate_lag(ldev);
 
 	mlx5_lag_dev_remove_pf(ldev, dev);
@@ -579,7 +579,7 @@ bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
 
 	mutex_lock(&lag_mutex);
 	ldev = mlx5_lag_dev_get(dev);
-	res  = ldev && mlx5_lag_is_bonded(ldev);
+	res  = ldev && __mlx5_lag_is_active(ldev);
 	mutex_unlock(&lag_mutex);
 
 	return res;
@@ -609,7 +609,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 	mutex_lock(&lag_mutex);
 	ldev = mlx5_lag_dev_get(dev);
 
-	if (!(ldev && mlx5_lag_is_bonded(ldev)))
+	if (!(ldev && __mlx5_lag_is_active(ldev)))
 		goto unlock;
 
 	if (ldev->tracker.tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
@@ -638,7 +638,7 @@ bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv)
 		return true;
 
 	ldev = mlx5_lag_dev_get(dev);
-	if (!ldev || !mlx5_lag_is_bonded(ldev) || ldev->pf[0].dev == dev)
+	if (!ldev || !__mlx5_lag_is_active(ldev) || ldev->pf[0].dev == dev)
 		return true;
 
 	/* If bonded, we do not add an IB device for PF1. */
@@ -665,7 +665,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 
 	mutex_lock(&lag_mutex);
 	ldev = mlx5_lag_dev_get(dev);
-	if (ldev && mlx5_lag_is_bonded(ldev)) {
+	if (ldev && __mlx5_lag_is_active(ldev)) {
 		num_ports = MLX5_MAX_PORTS;
 		mdev[0] = ldev->pf[0].dev;
 		mdev[1] = ldev->pf[1].dev;
-- 
cgit v1.2.3


From 7c34ec19e10c0d13ca2f3435fb85d2dddccad917 Mon Sep 17 00:00:00 2001
From: Aviv Heller <avivh@mellanox.com>
Date: Thu, 23 Aug 2018 13:47:53 +0300
Subject: net/mlx5: Make RoCE and SR-IOV LAG modes explicit

With the introduction of SR-IOV LAG, checking whether LAG is active
is no longer good enough, since RoCE and SR-IOV LAG each entails
different behavior by both the core and infiniband drivers.

This patch introduces facilities to discern LAG type, in addition to
mlx5_lag_is_active(). These are implemented in such a way as to allow
more complex mode combinations in the future.

Signed-off-by: Aviv Heller <avivh@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c                  | 13 ++--
 drivers/infiniband/hw/mlx5/mlx5_ib.h               |  1 +
 drivers/infiniband/hw/mlx5/qp.c                    |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    |  4 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/lag.c      | 79 +++++++++++++++++-----
 include/linux/mlx5/driver.h                        |  2 +
 8 files changed, 79 insertions(+), 26 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index d66457e6ffba..e85974ab06c0 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -445,7 +445,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	if (!ndev)
 		goto out;
 
-	if (mlx5_lag_is_active(dev->mdev)) {
+	if (dev->lag_active) {
 		rcu_read_lock();
 		upper = netdev_master_upper_dev_get_rcu(ndev);
 		if (upper) {
@@ -1848,7 +1848,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	context->lib_caps = req.lib_caps;
 	print_lib_caps(dev, context->lib_caps);
 
-	if (mlx5_lag_is_active(dev->mdev)) {
+	if (dev->lag_active) {
 		u8 port = mlx5_core_native_port_num(dev->mdev);
 
 		atomic_set(&context->tx_port_affinity,
@@ -4841,7 +4841,7 @@ static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev)
 	struct mlx5_flow_table *ft;
 	int err;
 
-	if (!ns || !mlx5_lag_is_active(mdev))
+	if (!ns || !mlx5_lag_is_roce(mdev))
 		return 0;
 
 	err = mlx5_cmd_create_vport_lag(mdev);
@@ -4855,6 +4855,7 @@ static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev)
 	}
 
 	dev->flow_db->lag_demux_ft = ft;
+	dev->lag_active = true;
 	return 0;
 
 err_destroy_vport_lag:
@@ -4866,7 +4867,9 @@ static void mlx5_eth_lag_cleanup(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_core_dev *mdev = dev->mdev;
 
-	if (dev->flow_db->lag_demux_ft) {
+	if (dev->lag_active) {
+		dev->lag_active = false;
+
 		mlx5_destroy_flow_table(dev->flow_db->lag_demux_ft);
 		dev->flow_db->lag_demux_ft = NULL;
 
@@ -6173,7 +6176,7 @@ int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev)
 	const char *name;
 
 	rdma_set_device_sysfs_group(&dev->ib_dev, &mlx5_attr_group);
-	if (!mlx5_lag_is_active(dev->mdev))
+	if (!mlx5_lag_is_roce(dev->mdev))
 		name = "mlx5_%d";
 	else
 		name = "mlx5_bond_%d";
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index c89b3b44b22e..e507b6eb7c09 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -936,6 +936,7 @@ struct mlx5_ib_dev {
 	struct mlx5_ib_delay_drop	delay_drop;
 	const struct mlx5_ib_profile	*profile;
 	struct mlx5_eswitch_rep		*rep;
+	int				lag_active;
 
 	struct mlx5_ib_lb_state		lb;
 	u8			umr_fence;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 3747cc681b18..a0e9ff763d42 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3258,7 +3258,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 		    (ibqp->qp_type == IB_QPT_RAW_PACKET) ||
 		    (ibqp->qp_type == IB_QPT_XRC_INI) ||
 		    (ibqp->qp_type == IB_QPT_XRC_TGT)) {
-			if (mlx5_lag_is_active(dev->mdev)) {
+			if (dev->lag_active) {
 				u8 p = mlx5_core_native_port_num(dev->mdev);
 				tx_affinity = get_tx_affinity(dev, pd, base, p);
 				context->flags |= cpu_to_be32(tx_affinity << 24);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index d5d161ab0dbc..b92f8b3ff6b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -35,7 +35,7 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	dst_is_lag_dev = (uplink_upper &&
 			  netif_is_lag_master(uplink_upper) &&
 			  rt->dst.dev == uplink_upper &&
-			  mlx5_lag_is_active(priv->mdev));
+			  mlx5_lag_is_sriov(priv->mdev));
 
 	/* if the egress device isn't on the same HW e-switch or
 	 * it's a LAG device, use the uplink
@@ -94,7 +94,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	dst_is_lag_dev = (uplink_upper &&
 			  netif_is_lag_master(uplink_upper) &&
 			  dst->dev == uplink_upper &&
-			  mlx5_lag_is_active(priv->mdev));
+			  mlx5_lag_is_sriov(priv->mdev));
 
 	/* if the egress device isn't on the same HW e-switch or
 	 * it's a LAG device, use the uplink
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 17f24127a3ba..e4a34c9ef700 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -314,7 +314,7 @@ int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
 	switch (attr->id) {
 	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
 		attr->u.ppid.id_len = ETH_ALEN;
-		if (uplink_upper && mlx5_lag_is_active(uplink_priv->mdev)) {
+		if (uplink_upper && mlx5_lag_is_sriov(uplink_priv->mdev)) {
 			ether_addr_copy(attr->u.ppid.id, uplink_upper->dev_addr);
 		} else {
 			struct mlx5e_rep_priv *rpriv = priv->ppriv;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 864f3b00d09d..53ebb5a48018 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2718,7 +2718,7 @@ static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow)
 	bool esw_paired = mlx5_devcom_is_paired(attr->in_mdev->priv.devcom,
 						MLX5_DEVCOM_ESW_OFFLOADS);
 
-	return esw_paired && mlx5_lag_is_active(attr->in_mdev) &&
+	return esw_paired && mlx5_lag_is_sriov(attr->in_mdev) &&
 	       (is_rep_ingress || act_is_encap);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index db5ef7023371..feb8230d3f86 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -37,9 +37,12 @@
 #include "eswitch.h"
 
 enum {
-	MLX5_LAG_FLAG_BONDED = 1 << 0,
+	MLX5_LAG_FLAG_ROCE   = 1 << 0,
+	MLX5_LAG_FLAG_SRIOV  = 1 << 1,
 };
 
+#define MLX5_LAG_MODE_FLAGS (MLX5_LAG_FLAG_ROCE | MLX5_LAG_FLAG_SRIOV)
+
 struct lag_func {
 	struct mlx5_core_dev *dev;
 	struct net_device    *netdev;
@@ -161,9 +164,19 @@ static int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 	return -1;
 }
 
+static bool __mlx5_lag_is_roce(struct mlx5_lag *ldev)
+{
+	return !!(ldev->flags & MLX5_LAG_FLAG_ROCE);
+}
+
+static bool __mlx5_lag_is_sriov(struct mlx5_lag *ldev)
+{
+	return !!(ldev->flags & MLX5_LAG_FLAG_SRIOV);
+}
+
 static bool __mlx5_lag_is_active(struct mlx5_lag *ldev)
 {
-	return !!(ldev->flags & MLX5_LAG_FLAG_BONDED);
+	return !!(ldev->flags & MLX5_LAG_MODE_FLAGS);
 }
 
 static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
@@ -229,9 +242,10 @@ static int mlx5_create_lag(struct mlx5_lag *ldev,
 }
 
 static void mlx5_activate_lag(struct mlx5_lag *ldev,
-			      struct lag_tracker *tracker)
+			      struct lag_tracker *tracker,
+			      u8 flags)
 {
-	ldev->flags |= MLX5_LAG_FLAG_BONDED;
+	ldev->flags |= flags;
 	mlx5_create_lag(ldev, tracker);
 }
 
@@ -240,7 +254,7 @@ static void mlx5_deactivate_lag(struct mlx5_lag *ldev)
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
 	int err;
 
-	ldev->flags &= ~MLX5_LAG_FLAG_BONDED;
+	ldev->flags &= ~MLX5_LAG_MODE_FLAGS;
 
 	err = mlx5_cmd_destroy_lag(dev0);
 	if (err)
@@ -263,15 +277,13 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
 	struct mlx5_core_dev *dev1 = ldev->pf[1].dev;
-	bool do_bond, sriov_enabled;
 	struct lag_tracker tracker;
+	bool do_bond, roce_lag;
 	int i;
 
 	if (!dev0 || !dev1)
 		return;
 
-	sriov_enabled = mlx5_sriov_is_enabled(dev0) || mlx5_sriov_is_enabled(dev1);
-
 	mutex_lock(&lag_mutex);
 	tracker = ldev->tracker;
 	mutex_unlock(&lag_mutex);
@@ -279,28 +291,35 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);
 
 	if (do_bond && !__mlx5_lag_is_active(ldev)) {
-		if (!sriov_enabled)
+		roce_lag = !mlx5_sriov_is_enabled(dev0) &&
+			   !mlx5_sriov_is_enabled(dev1);
+
+		if (roce_lag)
 			for (i = 0; i < MLX5_MAX_PORTS; i++)
 				mlx5_remove_dev_by_protocol(ldev->pf[i].dev,
 							    MLX5_INTERFACE_PROTOCOL_IB);
 
-		mlx5_activate_lag(ldev, &tracker);
+		mlx5_activate_lag(ldev, &tracker,
+				  roce_lag ? MLX5_LAG_FLAG_ROCE :
+				  MLX5_LAG_FLAG_SRIOV);
 
-		if (!sriov_enabled) {
+		if (roce_lag) {
 			mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
 			mlx5_nic_vport_enable_roce(dev1);
 		}
 	} else if (do_bond && __mlx5_lag_is_active(ldev)) {
 		mlx5_modify_lag(ldev, &tracker);
 	} else if (!do_bond && __mlx5_lag_is_active(ldev)) {
-		if (!sriov_enabled) {
+		roce_lag = __mlx5_lag_is_roce(ldev);
+
+		if (roce_lag) {
 			mlx5_remove_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
 			mlx5_nic_vport_disable_roce(dev1);
 		}
 
 		mlx5_deactivate_lag(ldev);
 
-		if (!sriov_enabled)
+		if (roce_lag)
 			for (i = 0; i < MLX5_MAX_PORTS; i++)
 				if (ldev->pf[i].dev)
 					mlx5_add_dev_by_protocol(ldev->pf[i].dev,
@@ -572,6 +591,20 @@ void mlx5_lag_remove(struct mlx5_core_dev *dev)
 	}
 }
 
+bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev;
+	bool res;
+
+	mutex_lock(&lag_mutex);
+	ldev = mlx5_lag_dev_get(dev);
+	res  = ldev && __mlx5_lag_is_roce(ldev);
+	mutex_unlock(&lag_mutex);
+
+	return res;
+}
+EXPORT_SYMBOL(mlx5_lag_is_roce);
+
 bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
@@ -586,6 +619,20 @@ bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_lag_is_active);
 
+bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev;
+	bool res;
+
+	mutex_lock(&lag_mutex);
+	ldev = mlx5_lag_dev_get(dev);
+	res  = ldev && __mlx5_lag_is_sriov(ldev);
+	mutex_unlock(&lag_mutex);
+
+	return res;
+}
+EXPORT_SYMBOL(mlx5_lag_is_sriov);
+
 void mlx5_lag_update(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
@@ -609,7 +656,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 	mutex_lock(&lag_mutex);
 	ldev = mlx5_lag_dev_get(dev);
 
-	if (!(ldev && __mlx5_lag_is_active(ldev)))
+	if (!(ldev && __mlx5_lag_is_roce(ldev)))
 		goto unlock;
 
 	if (ldev->tracker.tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
@@ -638,7 +685,7 @@ bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv)
 		return true;
 
 	ldev = mlx5_lag_dev_get(dev);
-	if (!ldev || !__mlx5_lag_is_active(ldev) || ldev->pf[0].dev == dev)
+	if (!ldev || !__mlx5_lag_is_roce(ldev) || ldev->pf[0].dev == dev)
 		return true;
 
 	/* If bonded, we do not add an IB device for PF1. */
@@ -665,7 +712,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 
 	mutex_lock(&lag_mutex);
 	ldev = mlx5_lag_dev_get(dev);
-	if (ldev && __mlx5_lag_is_active(ldev)) {
+	if (ldev && __mlx5_lag_is_roce(ldev)) {
 		num_ports = MLX5_MAX_PORTS;
 		mdev[0] = ldev->pf[0].dev;
 		mdev[1] = ldev->pf[1].dev;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index cd7af5d0311b..4d16ba04790e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1019,6 +1019,8 @@ int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id);
 
 int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev);
 int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev);
+bool mlx5_lag_is_roce(struct mlx5_core_dev *dev);
+bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_active(struct mlx5_core_dev *dev);
 struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev);
 int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
-- 
cgit v1.2.3


From 9582466640432c86fb060a4fa4d9d3c48e708ca6 Mon Sep 17 00:00:00 2001
From: Aviv Heller <avivh@mellanox.com>
Date: Mon, 27 Aug 2018 15:39:40 +0300
Subject: net/mlx5: Handle LAG FW commands failure gracefully

When create_lag or destroy_lag FW commands fail, display an appropriate
error message, and try to recover, if possible.

Signed-off-by: Aviv Heller <avivh@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 91 ++++++++++++++++++++-------
 1 file changed, 70 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index feb8230d3f86..5187dc7a72a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -241,26 +241,52 @@ static int mlx5_create_lag(struct mlx5_lag *ldev,
 	return err;
 }
 
-static void mlx5_activate_lag(struct mlx5_lag *ldev,
-			      struct lag_tracker *tracker,
-			      u8 flags)
+static int mlx5_activate_lag(struct mlx5_lag *ldev,
+			     struct lag_tracker *tracker,
+			     u8 flags)
 {
+	bool roce_lag = !!(flags & MLX5_LAG_FLAG_ROCE);
+	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	int err;
+
+	err = mlx5_create_lag(ldev, tracker);
+	if (err) {
+		if (roce_lag) {
+			mlx5_core_err(dev0,
+				      "Failed to activate RoCE LAG\n");
+		} else {
+			mlx5_core_err(dev0,
+				      "Failed to activate VF LAG\n"
+				      "Make sure all VFs are unbound prior to VF LAG activation or deactivation\n");
+		}
+		return err;
+	}
+
 	ldev->flags |= flags;
-	mlx5_create_lag(ldev, tracker);
+	return 0;
 }
 
-static void mlx5_deactivate_lag(struct mlx5_lag *ldev)
+static int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	bool roce_lag = __mlx5_lag_is_roce(ldev);
 	int err;
 
 	ldev->flags &= ~MLX5_LAG_MODE_FLAGS;
 
 	err = mlx5_cmd_destroy_lag(dev0);
-	if (err)
-		mlx5_core_err(dev0,
-			      "Failed to destroy LAG (%d)\n",
-			      err);
+	if (err) {
+		if (roce_lag) {
+			mlx5_core_err(dev0,
+				      "Failed to deactivate RoCE LAG; driver restart required\n");
+		} else {
+			mlx5_core_err(dev0,
+				      "Failed to deactivate VF LAG; driver restart required\n"
+				      "Make sure all VFs are unbound prior to VF LAG activation or deactivation\n");
+		}
+	}
+
+	return err;
 }
 
 static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
@@ -273,13 +299,33 @@ static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
 		return false;
 }
 
+static void mlx5_lag_add_ib_devices(struct mlx5_lag *ldev)
+{
+	int i;
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (ldev->pf[i].dev)
+			mlx5_add_dev_by_protocol(ldev->pf[i].dev,
+						 MLX5_INTERFACE_PROTOCOL_IB);
+}
+
+static void mlx5_lag_remove_ib_devices(struct mlx5_lag *ldev)
+{
+	int i;
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (ldev->pf[i].dev)
+			mlx5_remove_dev_by_protocol(ldev->pf[i].dev,
+						    MLX5_INTERFACE_PROTOCOL_IB);
+}
+
 static void mlx5_do_bond(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
 	struct mlx5_core_dev *dev1 = ldev->pf[1].dev;
 	struct lag_tracker tracker;
 	bool do_bond, roce_lag;
-	int i;
+	int err;
 
 	if (!dev0 || !dev1)
 		return;
@@ -295,13 +341,17 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 			   !mlx5_sriov_is_enabled(dev1);
 
 		if (roce_lag)
-			for (i = 0; i < MLX5_MAX_PORTS; i++)
-				mlx5_remove_dev_by_protocol(ldev->pf[i].dev,
-							    MLX5_INTERFACE_PROTOCOL_IB);
+			mlx5_lag_remove_ib_devices(ldev);
+
+		err = mlx5_activate_lag(ldev, &tracker,
+					roce_lag ? MLX5_LAG_FLAG_ROCE :
+					MLX5_LAG_FLAG_SRIOV);
+		if (err) {
+			if (roce_lag)
+				mlx5_lag_add_ib_devices(ldev);
 
-		mlx5_activate_lag(ldev, &tracker,
-				  roce_lag ? MLX5_LAG_FLAG_ROCE :
-				  MLX5_LAG_FLAG_SRIOV);
+			return;
+		}
 
 		if (roce_lag) {
 			mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
@@ -317,13 +367,12 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 			mlx5_nic_vport_disable_roce(dev1);
 		}
 
-		mlx5_deactivate_lag(ldev);
+		err = mlx5_deactivate_lag(ldev);
+		if (err)
+			return;
 
 		if (roce_lag)
-			for (i = 0; i < MLX5_MAX_PORTS; i++)
-				if (ldev->pf[i].dev)
-					mlx5_add_dev_by_protocol(ldev->pf[i].dev,
-								 MLX5_INTERFACE_PROTOCOL_IB);
+			mlx5_lag_add_ib_devices(ldev);
 	}
 }
 
-- 
cgit v1.2.3


From 6342ca644713601b42dcb8f35e3751afc0943373 Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Tue, 11 Dec 2018 11:43:07 +0900
Subject: tun: replace get_cpu_ptr with this_cpu_ptr when bh disabled

tun_xdp_one() runs with local bh disabled. So there is no need to
disable preemption by calling get_cpu_ptr while updating stats. This
patch replaces the use of get_cpu_ptr() with this_cpu_ptr() as a
micro-optimization. Also removes related put_cpu_ptr call.

Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 72577aa35b06..a4fdad475594 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2495,12 +2495,14 @@ build:
 	skb_record_rx_queue(skb, tfile->queue_index);
 	netif_receive_skb(skb);
 
-	stats = get_cpu_ptr(tun->pcpu_stats);
+	/* No need for get_cpu_ptr() here since this function is
+	 * always called with bh disabled
+	 */
+	stats = this_cpu_ptr(tun->pcpu_stats);
 	u64_stats_update_begin(&stats->syncp);
 	stats->rx_packets++;
 	stats->rx_bytes += datasize;
 	u64_stats_update_end(&stats->syncp);
-	put_cpu_ptr(stats);
 
 	if (rxhash)
 		tun_flow_update(tun, rxhash, tfile);
-- 
cgit v1.2.3


From 390de1940441a72625283098dd0d9303d0ceb8fb Mon Sep 17 00:00:00 2001
From: Wen Yang <wen.yang99@zte.com.cn>
Date: Tue, 11 Dec 2018 12:20:46 +0800
Subject: net/ibmvnic: Remove tests of member address

The driver was checking for non-NULL address.
- adapter->napi[i]

This is pointless as these will be always non-NULL, since the
'dapter->napi' is allocated in init_napi().
It is safe to get rid of useless checks for addresses to fix the
coccinelle warning:
>>drivers/net/ethernet/ibm/ibmvnic.c: test of a variable/field address
Since such statements always return true, they are redundant.

Signed-off-by: Wen Yang <wen.yang99@zte.com.cn>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: Michael Ellerman <mpe@ellerman.id.au>
CC: Thomas Falcon <tlfalcon@linux.ibm.com>
CC: John Allen <jallen@linux.ibm.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: linuxppc-dev@lists.ozlabs.org
CC: netdev@vger.kernel.org
CC: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index ed50b8dee44f..14d00985f087 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -773,11 +773,8 @@ static void release_napi(struct ibmvnic_adapter *adapter)
 		return;
 
 	for (i = 0; i < adapter->num_active_rx_napi; i++) {
-		if (&adapter->napi[i]) {
-			netdev_dbg(adapter->netdev,
-				   "Releasing napi[%d]\n", i);
-			netif_napi_del(&adapter->napi[i]);
-		}
+		netdev_dbg(adapter->netdev, "Releasing napi[%d]\n", i);
+		netif_napi_del(&adapter->napi[i]);
 	}
 
 	kfree(adapter->napi);
-- 
cgit v1.2.3


From 23127b33ec80e656921362d7dc82a0064bac20a2 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 13 Dec 2018 10:41:46 -0800
Subject: bpf: Create a new btf_name_by_offset() for non type name use case

The current btf_name_by_offset() is returning "(anon)" type name for
the offset == 0 case and "(invalid-name-offset)" for the out-of-bound
offset case.

It fits well for the internal BTF verbose log purpose which
is focusing on type.  For example,
offset == 0 => "(anon)" => anonymous type/name.
Returning non-NULL for the bad offset case is needed
during the BTF verification process because the BTF verifier may
complain about another field first before discovering the name_off
is invalid.

However, it may not be ideal for the newer use case which does not
necessary mean type name.  For example, when logging line_info
in the BPF verifier in the next patch, it is better to log an
empty src line instead of logging "(anon)".

The existing bpf_name_by_offset() is renamed to __bpf_name_by_offset()
and static to btf.c.

A new bpf_name_by_offset() is added for generic context usage.  It
returns "\0" for name_off == 0 (note that btf->strings[0] is "\0")
and NULL for invalid offset.  It allows the caller to decide
what is the best output in its context.

The new btf_name_by_offset() is overlapped with btf_name_offset_valid().
Hence, btf_name_offset_valid() is removed from btf.h to keep the btf.h API
minimal.  The existing btf_name_offset_valid() usage in btf.c could also be
replaced later.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/btf.h   |  1 -
 kernel/bpf/btf.c      | 31 ++++++++++++++++++++-----------
 kernel/bpf/verifier.c |  4 ++--
 3 files changed, 22 insertions(+), 14 deletions(-)

diff --git a/include/linux/btf.h b/include/linux/btf.h
index a4cf075b89eb..58000d7e06e3 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -46,7 +46,6 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
 int btf_get_fd_by_id(u32 id);
 u32 btf_id(const struct btf *btf);
-bool btf_name_offset_valid(const struct btf *btf, u32 offset);
 bool btf_type_is_reg_int(const struct btf_type *t, u32 expected_size);
 
 #ifdef CONFIG_BPF_SYSCALL
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 1545ddfb6fa5..8fa0bf1c33fd 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -474,7 +474,7 @@ static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
 	return !*src;
 }
 
-const char *btf_name_by_offset(const struct btf *btf, u32 offset)
+static const char *__btf_name_by_offset(const struct btf *btf, u32 offset)
 {
 	if (!offset)
 		return "(anon)";
@@ -484,6 +484,14 @@ const char *btf_name_by_offset(const struct btf *btf, u32 offset)
 		return "(invalid-name-offset)";
 }
 
+const char *btf_name_by_offset(const struct btf *btf, u32 offset)
+{
+	if (offset < btf->hdr.str_len)
+		return &btf->strings[offset];
+
+	return NULL;
+}
+
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
 {
 	if (type_id > btf->nr_types)
@@ -576,7 +584,7 @@ __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env,
 	__btf_verifier_log(log, "[%u] %s %s%s",
 			   env->log_type_id,
 			   btf_kind_str[kind],
-			   btf_name_by_offset(btf, t->name_off),
+			   __btf_name_by_offset(btf, t->name_off),
 			   log_details ? " " : "");
 
 	if (log_details)
@@ -620,7 +628,7 @@ static void btf_verifier_log_member(struct btf_verifier_env *env,
 		btf_verifier_log_type(env, struct_type, NULL);
 
 	__btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
-			   btf_name_by_offset(btf, member->name_off),
+			   __btf_name_by_offset(btf, member->name_off),
 			   member->type, member->offset);
 
 	if (fmt && *fmt) {
@@ -1872,7 +1880,7 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
 
 
 		btf_verifier_log(env, "\t%s val=%d\n",
-				 btf_name_by_offset(btf, enums[i].name_off),
+				 __btf_name_by_offset(btf, enums[i].name_off),
 				 enums[i].val);
 	}
 
@@ -1896,7 +1904,8 @@ static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t,
 	for (i = 0; i < nr_enums; i++) {
 		if (v == enums[i].val) {
 			seq_printf(m, "%s",
-				   btf_name_by_offset(btf, enums[i].name_off));
+				   __btf_name_by_offset(btf,
+							enums[i].name_off));
 			return;
 		}
 	}
@@ -1954,20 +1963,20 @@ static void btf_func_proto_log(struct btf_verifier_env *env,
 	}
 
 	btf_verifier_log(env, "%u %s", args[0].type,
-			 btf_name_by_offset(env->btf,
-					    args[0].name_off));
+			 __btf_name_by_offset(env->btf,
+					      args[0].name_off));
 	for (i = 1; i < nr_args - 1; i++)
 		btf_verifier_log(env, ", %u %s", args[i].type,
-				 btf_name_by_offset(env->btf,
-						    args[i].name_off));
+				 __btf_name_by_offset(env->btf,
+						      args[i].name_off));
 
 	if (nr_args > 1) {
 		const struct btf_param *last_arg = &args[nr_args - 1];
 
 		if (last_arg->type)
 			btf_verifier_log(env, ", %u %s", last_arg->type,
-					 btf_name_by_offset(env->btf,
-							    last_arg->name_off));
+					 __btf_name_by_offset(env->btf,
+							      last_arg->name_off));
 		else
 			btf_verifier_log(env, ", vararg");
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8b511a4fe84a..89ce2613fdb0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4910,8 +4910,8 @@ static int check_btf_line(struct bpf_verifier_env *env,
 			goto err_free;
 		}
 
-		if (!btf_name_offset_valid(btf, linfo[i].line_off) ||
-		    !btf_name_offset_valid(btf, linfo[i].file_name_off)) {
+		if (!btf_name_by_offset(btf, linfo[i].line_off) ||
+		    !btf_name_by_offset(btf, linfo[i].file_name_off)) {
 			verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i);
 			err = -EINVAL;
 			goto err_free;
-- 
cgit v1.2.3


From d9762e84ede3eae9636f5dbbe0c8f0390d37e114 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 13 Dec 2018 10:41:48 -0800
Subject: bpf: verbose log bpf_line_info in verifier

This patch adds bpf_line_info during the verifier's verbose.
It can give error context for debug purpose.

~~~~~~~~~~
Here is the verbose log for backedge:
	while (a) {
		a += bpf_get_smp_processor_id();
		bpf_trace_printk(fmt, sizeof(fmt), a);
	}

~> bpftool prog load ./test_loop.o /sys/fs/bpf/test_loop type tracepoint
13: while (a) {
3: a += bpf_get_smp_processor_id();
back-edge from insn 13 to 3

~~~~~~~~~~
Here is the verbose log for invalid pkt access:
Modification to test_xdp_noinline.c:

	data = (void *)(long)xdp->data;
	data_end = (void *)(long)xdp->data_end;
/*
	if (data + 4 > data_end)
		return XDP_DROP;
*/
	*(u32 *)data = dst->dst;

~> bpftool prog load ./test_xdp_noinline.o /sys/fs/bpf/test_xdp_noinline type xdp
; data = (void *)(long)xdp->data;
224: (79) r2 = *(u64 *)(r10 -112)
225: (61) r2 = *(u32 *)(r2 +0)
; *(u32 *)data = dst->dst;
226: (63) *(u32 *)(r2 +0) = r1
invalid access to packet, off=0 size=4, R2(id=0,off=0,r=0)
R2 offset is outside of the packet

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  1 +
 kernel/bpf/verifier.c        | 74 +++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 70 insertions(+), 5 deletions(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index c736945be7c5..548dcbdb7111 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -224,6 +224,7 @@ struct bpf_verifier_env {
 	bool allow_ptr_leaks;
 	bool seen_direct_write;
 	struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
+	const struct bpf_line_info *prev_linfo;
 	struct bpf_verifier_log log;
 	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
 	u32 subprog_cnt;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 89ce2613fdb0..ba8e3134bbc2 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -26,6 +26,7 @@
 #include <linux/bsearch.h>
 #include <linux/sort.h>
 #include <linux/perf_event.h>
+#include <linux/ctype.h>
 
 #include "disasm.h"
 
@@ -216,6 +217,27 @@ struct bpf_call_arg_meta {
 
 static DEFINE_MUTEX(bpf_verifier_lock);
 
+static const struct bpf_line_info *
+find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
+{
+	const struct bpf_line_info *linfo;
+	const struct bpf_prog *prog;
+	u32 i, nr_linfo;
+
+	prog = env->prog;
+	nr_linfo = prog->aux->nr_linfo;
+
+	if (!nr_linfo || insn_off >= prog->len)
+		return NULL;
+
+	linfo = prog->aux->linfo;
+	for (i = 1; i < nr_linfo; i++)
+		if (insn_off < linfo[i].insn_off)
+			break;
+
+	return &linfo[i - 1];
+}
+
 void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
 		       va_list args)
 {
@@ -266,6 +288,42 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
 	va_end(args);
 }
 
+static const char *ltrim(const char *s)
+{
+	while (isspace(*s))
+		s++;
+
+	return s;
+}
+
+__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env,
+					 u32 insn_off,
+					 const char *prefix_fmt, ...)
+{
+	const struct bpf_line_info *linfo;
+
+	if (!bpf_verifier_log_needed(&env->log))
+		return;
+
+	linfo = find_linfo(env, insn_off);
+	if (!linfo || linfo == env->prev_linfo)
+		return;
+
+	if (prefix_fmt) {
+		va_list args;
+
+		va_start(args, prefix_fmt);
+		bpf_verifier_vlog(&env->log, prefix_fmt, args);
+		va_end(args);
+	}
+
+	verbose(env, "%s\n",
+		ltrim(btf_name_by_offset(env->prog->aux->btf,
+					 linfo->line_off)));
+
+	env->prev_linfo = linfo;
+}
+
 static bool type_is_pkt_pointer(enum bpf_reg_type type)
 {
 	return type == PTR_TO_PACKET ||
@@ -4561,6 +4619,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 		return 0;
 
 	if (w < 0 || w >= env->prog->len) {
+		verbose_linfo(env, t, "%d: ", t);
 		verbose(env, "jump out of range from insn %d to %d\n", t, w);
 		return -EINVAL;
 	}
@@ -4578,6 +4637,8 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 		insn_stack[cur_stack++] = w;
 		return 1;
 	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
+		verbose_linfo(env, t, "%d: ", t);
+		verbose_linfo(env, w, "%d: ", w);
 		verbose(env, "back-edge from insn %d to %d\n", t, w);
 		return -EINVAL;
 	} else if (insn_state[w] == EXPLORED) {
@@ -4600,10 +4661,6 @@ static int check_cfg(struct bpf_verifier_env *env)
 	int ret = 0;
 	int i, t;
 
-	ret = check_subprogs(env);
-	if (ret < 0)
-		return ret;
-
 	insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
 	if (!insn_state)
 		return -ENOMEM;
@@ -5448,6 +5505,8 @@ static int do_check(struct bpf_verifier_env *env)
 	int insn_processed = 0;
 	bool do_print_state = false;
 
+	env->prev_linfo = NULL;
+
 	state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
 	if (!state)
 		return -ENOMEM;
@@ -5521,6 +5580,7 @@ static int do_check(struct bpf_verifier_env *env)
 				.private_data	= env,
 			};
 
+			verbose_linfo(env, insn_idx, "; ");
 			verbose(env, "%d: ", insn_idx);
 			print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
 		}
@@ -6755,7 +6815,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 
 	env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
 
-	ret = check_cfg(env);
+	ret = check_subprogs(env);
 	if (ret < 0)
 		goto skip_full_check;
 
@@ -6763,6 +6823,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (ret < 0)
 		goto skip_full_check;
 
+	ret = check_cfg(env);
+	if (ret < 0)
+		goto skip_full_check;
+
 	ret = do_check(env);
 	if (env->cur_state) {
 		free_verifier_state(env->cur_state, true);
-- 
cgit v1.2.3


From aeb3fecde811d5392ed481d8558f5751ac542e77 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 11 Dec 2018 11:15:46 -0800
Subject: net_sched: fold tcf_block_cb_call() into tc_setup_cb_call()

After commit 69bd48404f25 ("net/sched: Remove egdev mechanism"),
tc_setup_cb_call() is nearly identical to tcf_block_cb_call(),
so we can just fold tcf_block_cb_call() into tc_setup_cb_call()
and remove its unused parameter 'exts'.

Fixes: 69bd48404f25 ("net/sched: Remove egdev mechanism")
Cc: Oz Shlomo <ozsh@mellanox.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h    |  4 ++--
 net/sched/cls_api.c      | 46 ++++++++++++++++++++--------------------------
 net/sched/cls_bpf.c      |  4 ++--
 net/sched/cls_flower.c   | 15 +++++----------
 net/sched/cls_matchall.c |  5 ++---
 net/sched/cls_u32.c      |  8 ++++----
 6 files changed, 35 insertions(+), 47 deletions(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index ea191d8cfcc9..40965fbbcd31 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -619,8 +619,8 @@ tcf_match_indev(struct sk_buff *skb, int ifindex)
 }
 #endif /* CONFIG_NET_CLS_IND */
 
-int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
-		     enum tc_setup_type type, void *type_data, bool err_stop);
+int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
+		     void *type_data, bool err_stop);
 
 enum tc_block_command {
 	TC_BLOCK_BIND,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 6207f265b87c..8ce2a0507970 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1270,29 +1270,6 @@ void tcf_block_cb_unregister(struct tcf_block *block,
 }
 EXPORT_SYMBOL(tcf_block_cb_unregister);
 
-static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type,
-			     void *type_data, bool err_stop)
-{
-	struct tcf_block_cb *block_cb;
-	int ok_count = 0;
-	int err;
-
-	/* Make sure all netdevs sharing this block are offload-capable. */
-	if (block->nooffloaddevcnt && err_stop)
-		return -EOPNOTSUPP;
-
-	list_for_each_entry(block_cb, &block->cb_list, list) {
-		err = block_cb->cb(type, type_data, block_cb->cb_priv);
-		if (err) {
-			if (err_stop)
-				return err;
-		} else {
-			ok_count++;
-		}
-	}
-	return ok_count;
-}
-
 /* Main classifier routine: scans classifier chain attached
  * to this qdisc, (optionally) tests for protocol and asks
  * specific classifiers.
@@ -2515,10 +2492,27 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
 }
 EXPORT_SYMBOL(tcf_exts_dump_stats);
 
-int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
-		     enum tc_setup_type type, void *type_data, bool err_stop)
+int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
+		     void *type_data, bool err_stop)
 {
-	return tcf_block_cb_call(block, type, type_data, err_stop);
+	struct tcf_block_cb *block_cb;
+	int ok_count = 0;
+	int err;
+
+	/* Make sure all netdevs sharing this block are offload-capable. */
+	if (block->nooffloaddevcnt && err_stop)
+		return -EOPNOTSUPP;
+
+	list_for_each_entry(block_cb, &block->cb_list, list) {
+		err = block_cb->cb(type, type_data, block_cb->cb_priv);
+		if (err) {
+			if (err_stop)
+				return err;
+		} else {
+			ok_count++;
+		}
+	}
+	return ok_count;
 }
 EXPORT_SYMBOL(tc_setup_cb_call);
 
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index fa6fe2fe0f32..a95cb240a606 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -169,7 +169,7 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 	if (oldprog)
 		tcf_block_offload_dec(block, &oldprog->gen_flags);
 
-	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, skip_sw);
+	err = tc_setup_cb_call(block, TC_SETUP_CLSBPF, &cls_bpf, skip_sw);
 	if (prog) {
 		if (err < 0) {
 			cls_bpf_offload_cmd(tp, oldprog, prog, extack);
@@ -234,7 +234,7 @@ static void cls_bpf_offload_update_stats(struct tcf_proto *tp,
 	cls_bpf.name = prog->bpf_name;
 	cls_bpf.exts_integrated = prog->exts_integrated;
 
-	tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSBPF, &cls_bpf, false);
 }
 
 static int cls_bpf_init(struct tcf_proto *tp)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 544811dded60..1eb2e2c31dd5 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -368,8 +368,7 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f,
 	cls_flower.command = TC_CLSFLOWER_DESTROY;
 	cls_flower.cookie = (unsigned long) f;
 
-	tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
-			 &cls_flower, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false);
 	tcf_block_offload_dec(block, &f->flags);
 }
 
@@ -391,8 +390,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 	cls_flower.exts = &f->exts;
 	cls_flower.classid = f->res.classid;
 
-	err = tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
-			       &cls_flower, skip_sw);
+	err = tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, skip_sw);
 	if (err < 0) {
 		fl_hw_destroy_filter(tp, f, NULL);
 		return err;
@@ -418,8 +416,7 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
 	cls_flower.exts = &f->exts;
 	cls_flower.classid = f->res.classid;
 
-	tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
-			 &cls_flower, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false);
 }
 
 static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f,
@@ -1502,8 +1499,7 @@ static void fl_hw_create_tmplt(struct tcf_chain *chain,
 	/* We don't care if driver (any of them) fails to handle this
 	 * call. It serves just as a hint for it.
 	 */
-	tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER,
-			 &cls_flower, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false);
 }
 
 static void fl_hw_destroy_tmplt(struct tcf_chain *chain,
@@ -1516,8 +1512,7 @@ static void fl_hw_destroy_tmplt(struct tcf_chain *chain,
 	cls_flower.command = TC_CLSFLOWER_TMPLT_DESTROY;
 	cls_flower.cookie = (unsigned long) tmplt;
 
-	tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER,
-			 &cls_flower, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false);
 }
 
 static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 856fa79d4ffd..0e408ee9dcec 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -71,7 +71,7 @@ static void mall_destroy_hw_filter(struct tcf_proto *tp,
 	cls_mall.command = TC_CLSMATCHALL_DESTROY;
 	cls_mall.cookie = cookie;
 
-	tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL, &cls_mall, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false);
 	tcf_block_offload_dec(block, &head->flags);
 }
 
@@ -90,8 +90,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 	cls_mall.exts = &head->exts;
 	cls_mall.cookie = cookie;
 
-	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL,
-			       &cls_mall, skip_sw);
+	err = tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, skip_sw);
 	if (err < 0) {
 		mall_destroy_hw_filter(tp, head, cookie, NULL);
 		return err;
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 4c54bc440798..dcea21004604 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -491,7 +491,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
 	cls_u32.hnode.handle = h->handle;
 	cls_u32.hnode.prio = h->prio;
 
-	tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, false);
 }
 
 static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
@@ -509,7 +509,7 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
 	cls_u32.hnode.handle = h->handle;
 	cls_u32.hnode.prio = h->prio;
 
-	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw);
+	err = tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, skip_sw);
 	if (err < 0) {
 		u32_clear_hw_hnode(tp, h, NULL);
 		return err;
@@ -533,7 +533,7 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	cls_u32.command = TC_CLSU32_DELETE_KNODE;
 	cls_u32.knode.handle = n->handle;
 
-	tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, false);
 	tcf_block_offload_dec(block, &n->flags);
 }
 
@@ -563,7 +563,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	if (n->ht_down)
 		cls_u32.knode.link_handle = ht->handle;
 
-	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw);
+	err = tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, skip_sw);
 	if (err < 0) {
 		u32_remove_hw_knode(tp, n, NULL);
 		return err;
-- 
cgit v1.2.3


From 9c29a2f55ec05cc8b525ee3b2d75d3cd37911123 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 11 Dec 2018 18:57:21 -0700
Subject: neighbor: Fix locking order for gc_list changes

Lock checker noted an inverted lock order between neigh_change_state
(neighbor lock then table lock) and neigh_periodic_work (table lock and
then neighbor lock) resulting in:

[  121.057652] ======================================================
[  121.058740] WARNING: possible circular locking dependency detected
[  121.059861] 4.20.0-rc6+ #43 Not tainted
[  121.060546] ------------------------------------------------------
[  121.061630] kworker/0:2/65 is trying to acquire lock:
[  121.062519] (____ptrval____) (&n->lock){++--}, at: neigh_periodic_work+0x237/0x324
[  121.063894]
[  121.063894] but task is already holding lock:
[  121.064920] (____ptrval____) (&tbl->lock){+.-.}, at: neigh_periodic_work+0x194/0x324
[  121.066274]
[  121.066274] which lock already depends on the new lock.
[  121.066274]
[  121.067693]
[  121.067693] the existing dependency chain (in reverse order) is:
...

Fix by renaming neigh_change_state to neigh_update_gc_list, changing
it to only manage whether an entry should be on the gc_list and taking
locks in the same order as neigh_periodic_work. Invoke at the end of
neigh_update only if diff between old or new states has the PERMANENT
flag set.

Fixes: 8cc196d6ef86 ("neighbor: gc_list changes should be protected by table lock")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 27 +++++++++++++++------------
 1 file changed, 15 insertions(+), 12 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 03fdc5ae66b0..010784123bc1 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -127,30 +127,30 @@ static void neigh_mark_dead(struct neighbour *n)
 	}
 }
 
-static void neigh_change_state(struct neighbour *n, u8 new)
+static void neigh_update_gc_list(struct neighbour *n)
 {
-	bool on_gc_list = !list_empty(&n->gc_list);
-	bool new_is_perm = new & NUD_PERMANENT;
+	bool on_gc_list, new_is_perm;
 
-	n->nud_state = new;
+	write_lock_bh(&n->tbl->lock);
+	write_lock(&n->lock);
 
 	/* remove from the gc list if new state is permanent;
 	 * add to the gc list if new state is not permanent
 	 */
+	new_is_perm = n->nud_state & NUD_PERMANENT;
+	on_gc_list = !list_empty(&n->gc_list);
+
 	if (new_is_perm && on_gc_list) {
-		write_lock_bh(&n->tbl->lock);
 		list_del_init(&n->gc_list);
-		write_unlock_bh(&n->tbl->lock);
-
 		atomic_dec(&n->tbl->gc_entries);
 	} else if (!new_is_perm && !on_gc_list) {
 		/* add entries to the tail; cleaning removes from the front */
-		write_lock_bh(&n->tbl->lock);
 		list_add_tail(&n->gc_list, &n->tbl->gc_list);
-		write_unlock_bh(&n->tbl->lock);
-
 		atomic_inc(&n->tbl->gc_entries);
 	}
+
+	write_unlock(&n->lock);
+	write_unlock_bh(&n->tbl->lock);
 }
 
 static bool neigh_del(struct neighbour *n, __u8 state, __u8 flags,
@@ -1220,7 +1220,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
 		neigh_del_timer(neigh);
 		if (old & NUD_CONNECTED)
 			neigh_suspect(neigh);
-		neigh_change_state(neigh, new);
+		neigh->nud_state = new;
 		err = 0;
 		notify = old & NUD_VALID;
 		if ((old & (NUD_INCOMPLETE | NUD_PROBE)) &&
@@ -1299,7 +1299,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
 						((new & NUD_REACHABLE) ?
 						 neigh->parms->reachable_time :
 						 0)));
-		neigh_change_state(neigh, new);
+		neigh->nud_state = new;
 		notify = 1;
 	}
 
@@ -1360,6 +1360,9 @@ out:
 		neigh_update_is_router(neigh, flags, &notify);
 	write_unlock_bh(&neigh->lock);
 
+	if ((new ^ old) & NUD_PERMANENT)
+		neigh_update_gc_list(neigh);
+
 	if (notify)
 		neigh_update_notify(neigh, nlmsg_pid);
 
-- 
cgit v1.2.3


From 758a7f0b32ab890831d321145c3fe72bb85c0350 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 11 Dec 2018 18:57:22 -0700
Subject: neighbor: Fix state check in neigh_forced_gc

PERMANENT entries are not on the gc_list so the state check is now
redundant. Also, the move to not purge entries until after 5 seconds
should not apply to FAILED entries; those can be removed immediately
to make way for newer ones. This restores the previous logic prior to
the gc_list.

Fixes: 58956317c8de ("neighbor: Improve garbage collection")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 010784123bc1..acaa1a64150d 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -204,7 +204,6 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 	unsigned long tref = jiffies - 5 * HZ;
 	u8 flags = NTF_EXT_LEARNED;
 	struct neighbour *n, *tmp;
-	u8 state = NUD_PERMANENT;
 	int shrunk = 0;
 
 	NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);
@@ -216,8 +215,8 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 			bool remove = false;
 
 			write_lock(&n->lock);
-			if (!(n->nud_state & state) && !(n->flags & flags) &&
-			    time_after(tref, n->updated))
+			if ((n->nud_state == NUD_FAILED) ||
+			    (!(n->flags & flags) && time_after(tref, n->updated)))
 				remove = true;
 			write_unlock(&n->lock);
 
-- 
cgit v1.2.3


From 7e6f182bec7debb420a2c12ae0ea1813645a7ac4 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 11 Dec 2018 18:57:23 -0700
Subject: neighbor: Remove state and flags arguments to neigh_del

neigh_del now only has 1 caller, and the state and flags arguments
are both 0. Remove them and simplify neigh_del.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index acaa1a64150d..bb6f9ca7a3ce 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -153,14 +153,13 @@ static void neigh_update_gc_list(struct neighbour *n)
 	write_unlock_bh(&n->tbl->lock);
 }
 
-static bool neigh_del(struct neighbour *n, __u8 state, __u8 flags,
-		      struct neighbour __rcu **np, struct neigh_table *tbl)
+static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np,
+		      struct neigh_table *tbl)
 {
 	bool retval = false;
 
 	write_lock(&n->lock);
-	if (refcount_read(&n->refcnt) == 1 && !(n->nud_state & state) &&
-	    !(n->flags & flags)) {
+	if (refcount_read(&n->refcnt) == 1) {
 		struct neighbour *neigh;
 
 		neigh = rcu_dereference_protected(n->next,
@@ -192,7 +191,7 @@ bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl)
 	while ((n = rcu_dereference_protected(*np,
 					      lockdep_is_held(&tbl->lock)))) {
 		if (n == ndel)
-			return neigh_del(n, 0, 0, np, tbl);
+			return neigh_del(n, np, tbl);
 		np = &n->next;
 	}
 	return false;
-- 
cgit v1.2.3


From 526f1b587cf826d78c3e522428ce6b24a8da0d65 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 11 Dec 2018 18:57:24 -0700
Subject: neighbor: Move neigh_update_ext_learned to core file

neigh_update_ext_learned has one caller in neighbour.c so does not need
to be defined in the header. Move it and in the process remove the
intialization of ndm_flags and just set it based on the flags check.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h | 18 ------------------
 net/core/neighbour.c    | 18 ++++++++++++++++++
 2 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index f886b58956a6..ef0a60448a96 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -549,24 +549,6 @@ static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n,
 	} while (read_seqretry(&n->ha_lock, seq));
 }
 
-static inline void neigh_update_ext_learned(struct neighbour *neigh, u32 flags,
-					    int *notify)
-{
-	u8 ndm_flags = 0;
-
-	if (!(flags & NEIGH_UPDATE_F_ADMIN))
-		return;
-
-	ndm_flags |= (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0;
-	if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) {
-		if (ndm_flags & NTF_EXT_LEARNED)
-			neigh->flags |= NTF_EXT_LEARNED;
-		else
-			neigh->flags &= ~NTF_EXT_LEARNED;
-		*notify = 1;
-	}
-}
-
 static inline void neigh_update_is_router(struct neighbour *neigh, u32 flags,
 					  int *notify)
 {
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index bb6f9ca7a3ce..2401040f799b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -153,6 +153,24 @@ static void neigh_update_gc_list(struct neighbour *n)
 	write_unlock_bh(&n->tbl->lock);
 }
 
+static void neigh_update_ext_learned(struct neighbour *neigh, u32 flags,
+				     int *notify)
+{
+	u8 ndm_flags;
+
+	if (!(flags & NEIGH_UPDATE_F_ADMIN))
+		return;
+
+	ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0;
+	if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) {
+		if (ndm_flags & NTF_EXT_LEARNED)
+			neigh->flags |= NTF_EXT_LEARNED;
+		else
+			neigh->flags &= ~NTF_EXT_LEARNED;
+		*notify = 1;
+	}
+}
+
 static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np,
 		      struct neigh_table *tbl)
 {
-- 
cgit v1.2.3


From e997f8a20a57cae16ed0c7a2bff6d3ab75f58123 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 11 Dec 2018 18:57:25 -0700
Subject: neighbor: Remove externally learned entries from gc_list

Externally learned entries are similar to PERMANENT entries in the
sense they are managed by userspace and can not be garbage collected.
As such remove them from the gc_list, remove the flags check from
neigh_forced_gc and skip threshold checks in neigh_alloc. As with
PERMANENT entries, this allows unlimited number of NTF_EXT_LEARNED
entries.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 49 ++++++++++++++++++++++++++++---------------------
 1 file changed, 28 insertions(+), 21 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 2401040f799b..42b413774370 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -129,21 +129,22 @@ static void neigh_mark_dead(struct neighbour *n)
 
 static void neigh_update_gc_list(struct neighbour *n)
 {
-	bool on_gc_list, new_is_perm;
+	bool on_gc_list, exempt_from_gc;
 
 	write_lock_bh(&n->tbl->lock);
 	write_lock(&n->lock);
 
-	/* remove from the gc list if new state is permanent;
-	 * add to the gc list if new state is not permanent
+	/* remove from the gc list if new state is permanent or if neighbor
+	 * is externally learned; otherwise entry should be on the gc list
 	 */
-	new_is_perm = n->nud_state & NUD_PERMANENT;
+	exempt_from_gc = n->nud_state & NUD_PERMANENT ||
+			 n->flags & NTF_EXT_LEARNED;
 	on_gc_list = !list_empty(&n->gc_list);
 
-	if (new_is_perm && on_gc_list) {
+	if (exempt_from_gc && on_gc_list) {
 		list_del_init(&n->gc_list);
 		atomic_dec(&n->tbl->gc_entries);
-	} else if (!new_is_perm && !on_gc_list) {
+	} else if (!exempt_from_gc && !on_gc_list) {
 		/* add entries to the tail; cleaning removes from the front */
 		list_add_tail(&n->gc_list, &n->tbl->gc_list);
 		atomic_inc(&n->tbl->gc_entries);
@@ -153,13 +154,14 @@ static void neigh_update_gc_list(struct neighbour *n)
 	write_unlock_bh(&n->tbl->lock);
 }
 
-static void neigh_update_ext_learned(struct neighbour *neigh, u32 flags,
+static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags,
 				     int *notify)
 {
+	bool rc = false;
 	u8 ndm_flags;
 
 	if (!(flags & NEIGH_UPDATE_F_ADMIN))
-		return;
+		return rc;
 
 	ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0;
 	if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) {
@@ -167,8 +169,11 @@ static void neigh_update_ext_learned(struct neighbour *neigh, u32 flags,
 			neigh->flags |= NTF_EXT_LEARNED;
 		else
 			neigh->flags &= ~NTF_EXT_LEARNED;
+		rc = true;
 		*notify = 1;
 	}
+
+	return rc;
 }
 
 static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np,
@@ -219,7 +224,6 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 {
 	int max_clean = atomic_read(&tbl->gc_entries) - tbl->gc_thresh2;
 	unsigned long tref = jiffies - 5 * HZ;
-	u8 flags = NTF_EXT_LEARNED;
 	struct neighbour *n, *tmp;
 	int shrunk = 0;
 
@@ -233,7 +237,7 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 
 			write_lock(&n->lock);
 			if ((n->nud_state == NUD_FAILED) ||
-			    (!(n->flags & flags) && time_after(tref, n->updated)))
+			    time_after(tref, n->updated))
 				remove = true;
 			write_unlock(&n->lock);
 
@@ -371,13 +375,13 @@ EXPORT_SYMBOL(neigh_ifdown);
 
 static struct neighbour *neigh_alloc(struct neigh_table *tbl,
 				     struct net_device *dev,
-				     bool permanent)
+				     bool exempt_from_gc)
 {
 	struct neighbour *n = NULL;
 	unsigned long now = jiffies;
 	int entries;
 
-	if (permanent)
+	if (exempt_from_gc)
 		goto do_alloc;
 
 	entries = atomic_inc_return(&tbl->gc_entries) - 1;
@@ -419,7 +423,7 @@ out:
 	return n;
 
 out_entries:
-	if (!permanent)
+	if (!exempt_from_gc)
 		atomic_dec(&tbl->gc_entries);
 	goto out;
 }
@@ -566,9 +570,9 @@ EXPORT_SYMBOL(neigh_lookup_nodev);
 static struct neighbour *___neigh_create(struct neigh_table *tbl,
 					 const void *pkey,
 					 struct net_device *dev,
-					 bool permanent, bool want_ref)
+					 bool exempt_from_gc, bool want_ref)
 {
-	struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev, permanent);
+	struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev, exempt_from_gc);
 	u32 hash_val;
 	unsigned int key_len = tbl->key_len;
 	int error;
@@ -634,7 +638,7 @@ static struct neighbour *___neigh_create(struct neigh_table *tbl,
 	}
 
 	n->dead = 0;
-	if (!permanent)
+	if (!exempt_from_gc)
 		list_add_tail(&n->gc_list, &n->tbl->gc_list);
 
 	if (want_ref)
@@ -1210,6 +1214,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
 			  u8 new, u32 flags, u32 nlmsg_pid,
 			  struct netlink_ext_ack *extack)
 {
+	bool ext_learn_change = false;
 	u8 old;
 	int err;
 	int notify = 0;
@@ -1230,7 +1235,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
 		goto out;
 	}
 
-	neigh_update_ext_learned(neigh, flags, &notify);
+	ext_learn_change = neigh_update_ext_learned(neigh, flags, &notify);
 
 	if (!(new & NUD_VALID)) {
 		neigh_del_timer(neigh);
@@ -1376,7 +1381,7 @@ out:
 		neigh_update_is_router(neigh, flags, &notify);
 	write_unlock_bh(&neigh->lock);
 
-	if ((new ^ old) & NUD_PERMANENT)
+	if (((new ^ old) & NUD_PERMANENT) || ext_learn_change)
 		neigh_update_gc_list(neigh);
 
 	if (notify)
@@ -1881,14 +1886,16 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	neigh = neigh_lookup(tbl, dst, dev);
 	if (neigh == NULL) {
+		bool exempt_from_gc;
+
 		if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
 			err = -ENOENT;
 			goto out;
 		}
 
-		neigh = ___neigh_create(tbl, dst, dev,
-					ndm->ndm_state & NUD_PERMANENT,
-					true);
+		exempt_from_gc = ndm->ndm_state & NUD_PERMANENT ||
+				 ndm->ndm_flags & NTF_EXT_LEARNED;
+		neigh = ___neigh_create(tbl, dst, dev, exempt_from_gc, true);
 		if (IS_ERR(neigh)) {
 			err = PTR_ERR(neigh);
 			goto out;
-- 
cgit v1.2.3


From 8e2ea53a83dfb4b892ba35ddd9e78e6091202fa6 Mon Sep 17 00:00:00 2001
From: yupeng <yupeng0921@gmail.com>
Date: Wed, 12 Dec 2018 00:14:10 -0800
Subject: add snmp counters document

Add explainations for some general IP counters, SACK and DSACK related
counters

Signed-off-by: yupeng <yupeng0921@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/snmp_counter.rst | 245 +++++++++++++++++++++++++++++-
 1 file changed, 244 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/snmp_counter.rst b/Documentation/networking/snmp_counter.rst
index 918a1374af30..f8eb77ddbd44 100644
--- a/Documentation/networking/snmp_counter.rst
+++ b/Documentation/networking/snmp_counter.rst
@@ -17,7 +17,9 @@ Defined in `RFC1213 ipInReceives`_
 
 The number of packets received by the IP layer. It gets increasing at the
 beginning of ip_rcv function, always be updated together with
-IpExtInOctets. It indicates the number of aggregated segments after
+IpExtInOctets. It will be increased even if the packet is dropped
+later (e.g. due to the IP header is invalid or the checksum is wrong
+and so on).  It indicates the number of aggregated segments after
 GRO/LRO.
 
 * IpInDelivers
@@ -57,6 +59,58 @@ status. They count the real frame number regardless the LRO/GRO. So
 for the same packet, you might find that IpInReceives count 1, but
 IpExtInNoECTPkts counts 2 or more.
 
+* IpInHdrErrors
+Defined in `RFC1213 ipInHdrErrors`_. It indicates the packet is
+dropped due to the IP header error. It might happen in both IP input
+and IP forward paths.
+
+.. _RFC1213 ipInHdrErrors: https://tools.ietf.org/html/rfc1213#page-27
+
+* IpInAddrErrors
+Defined in `RFC1213 ipInAddrErrors`_. It will be increased in two
+scenarios: (1) The IP address is invalid. (2) The destination IP
+address is not a local address and IP forwarding is not enabled
+
+.. _RFC1213 ipInAddrErrors: https://tools.ietf.org/html/rfc1213#page-27
+
+* IpExtInNoRoutes
+This counter means the packet is dropped when the IP stack receives a
+packet and can't find a route for it from the route table. It might
+happen when IP forwarding is enabled and the destination IP address is
+not a local address and there is no route for the destination IP
+address.
+
+* IpInUnknownProtos
+Defined in `RFC1213 ipInUnknownProtos`_. It will be increased if the
+layer 4 protocol is unsupported by kernel. If an application is using
+raw socket, kernel will always deliver the packet to the raw socket
+and this counter won't be increased.
+
+.. _RFC1213 ipInUnknownProtos: https://tools.ietf.org/html/rfc1213#page-27
+
+* IpExtInTruncatedPkts
+For IPv4 packet, it means the actual data size is smaller than the
+"Total Length" field in the IPv4 header.
+
+* IpInDiscards
+Defined in `RFC1213 ipInDiscards`_. It indicates the packet is dropped
+in the IP receiving path and due to kernel internal reasons (e.g. no
+enough memory).
+
+.. _RFC1213 ipInDiscards: https://tools.ietf.org/html/rfc1213#page-28
+
+* IpOutDiscards
+Defined in `RFC1213 ipOutDiscards`_. It indicates the packet is
+dropped in the IP sending path and due to kernel internal reasons.
+
+.. _RFC1213 ipOutDiscards: https://tools.ietf.org/html/rfc1213#page-28
+
+* IpOutNoRoutes
+Defined in `RFC1213 ipOutNoRoutes`_. It indicates the packet is
+dropped in the IP sending path and no route is found for it.
+
+.. _RFC1213 ipOutNoRoutes: https://tools.ietf.org/html/rfc1213#page-29
+
 ICMP counters
 ============
 * IcmpInMsgs and IcmpOutMsgs
@@ -425,6 +479,100 @@ The sum of CWND detected by packet delay. Dividing this value by
 TcpExtTCPHystartDelayDetect is the average CWND which detected by the
 packet delay.
 
+TCP retransmission and congestion control
+======================================
+The TCP protocol has two retransmission mechanisms: SACK and fast
+recovery. They are exclusive with each other. When SACK is enabled,
+the kernel TCP stack would use SACK, or kernel would use fast
+recovery. The SACK is a TCP option, which is defined in `RFC2018`_,
+the fast recovery is defined in `RFC6582`_, which is also called
+'Reno'.
+
+The TCP congestion control is a big and complex topic. To understand
+the related snmp counter, we need to know the states of the congestion
+control state machine. There are 5 states: Open, Disorder, CWR,
+Recovery and Loss. For details about these states, please refer page 5
+and page 6 of this document:
+https://pdfs.semanticscholar.org/0e9c/968d09ab2e53e24c4dca5b2d67c7f7140f8e.pdf
+
+.. _RFC2018: https://tools.ietf.org/html/rfc2018
+.. _RFC6582: https://tools.ietf.org/html/rfc6582
+
+* TcpExtTCPRenoRecovery and TcpExtTCPSackRecovery
+When the congestion control comes into Recovery state, if sack is
+used, TcpExtTCPSackRecovery increases 1, if sack is not used,
+TcpExtTCPRenoRecovery increases 1. These two counters mean the TCP
+stack begins to retransmit the lost packets.
+
+* TcpExtTCPSACKReneging
+A packet was acknowledged by SACK, but the receiver has dropped this
+packet, so the sender needs to retransmit this packet. In this
+situation, the sender adds 1 to TcpExtTCPSACKReneging. A receiver
+could drop a packet which has been acknowledged by SACK, although it is
+unusual, it is allowed by the TCP protocol. The sender doesn't really
+know what happened on the receiver side. The sender just waits until
+the RTO expires for this packet, then the sender assumes this packet
+has been dropped by the receiver.
+
+* TcpExtTCPRenoReorder
+The reorder packet is detected by fast recovery. It would only be used
+if SACK is disabled. The fast recovery algorithm detects recorder by
+the duplicate ACK number. E.g., if retransmission is triggered, and
+the original retransmitted packet is not lost, it is just out of
+order, the receiver would acknowledge multiple times, one for the
+retransmitted packet, another for the arriving of the original out of
+order packet. Thus the sender would find more ACks than its
+expectation, and the sender knows out of order occurs.
+
+* TcpExtTCPTSReorder
+The reorder packet is detected when a hole is filled. E.g., assume the
+sender sends packet 1,2,3,4,5, and the receiving order is
+1,2,4,5,3. When the sender receives the ACK of packet 3 (which will
+fill the hole), two conditions will let TcpExtTCPTSReorder increase
+1: (1) if the packet 3 is not re-retransmitted yet. (2) if the packet
+3 is retransmitted but the timestamp of the packet 3's ACK is earlier
+than the retransmission timestamp.
+
+* TcpExtTCPSACKReorder
+The reorder packet detected by SACK. The SACK has two methods to
+detect reorder: (1) DSACK is received by the sender. It means the
+sender sends the same packet more than one times. And the only reason
+is the sender believes an out of order packet is lost so it sends the
+packet again. (2) Assume packet 1,2,3,4,5 are sent by the sender, and
+the sender has received SACKs for packet 2 and 5, now the sender
+receives SACK for packet 4 and the sender doesn't retransmit the
+packet yet, the sender would know packet 4 is out of order. The TCP
+stack of kernel will increase TcpExtTCPSACKReorder for both of the
+above scenarios.
+
+
+DSACK
+=====
+The DSACK is defined in `RFC2883`_. The receiver uses DSACK to report
+duplicate packets to the sender. There are two kinds of
+duplications: (1) a packet which has been acknowledged is
+duplicate. (2) an out of order packet is duplicate. The TCP stack
+counts these two kinds of duplications on both receiver side and
+sender side.
+
+.. _RFC2883 : https://tools.ietf.org/html/rfc2883
+
+* TcpExtTCPDSACKOldSent
+The TCP stack receives a duplicate packet which has been acked, so it
+sends a DSACK to the sender.
+
+* TcpExtTCPDSACKOfoSent
+The TCP stack receives an out of order duplicate packet, so it sends a
+DSACK to the sender.
+
+* TcpExtTCPDSACKRecv
+The TCP stack receives a DSACK, which indicate an acknowledged
+duplicate packet is received.
+
+* TcpExtTCPDSACKOfoRecv
+The TCP stack receives a DSACK, which indicate an out of order
+duplciate packet is received.
+
 examples
 =======
 
@@ -945,3 +1093,98 @@ Both TcpExtListenOverflows and TcpExtListenDrops were 4. If the time
 between the 4th nc and the nstat was longer, the value of
 TcpExtListenOverflows and TcpExtListenDrops would be larger, because
 the SYN of the 4th nc was dropped, the client was retrying.
+
+IpInAddrErrors, IpExtInNoRoutes and IpOutNoRoutes
+----------------------------------------------
+server A IP address: 192.168.122.250
+server B IP address: 192.168.122.251
+Prepare on server A, add a route to server B::
+
+  $ sudo ip route add 8.8.8.8/32 via 192.168.122.251
+
+Prepare on server B, disable send_redirects for all interfaces::
+
+  $ sudo sysctl -w net.ipv4.conf.all.send_redirects=0
+  $ sudo sysctl -w net.ipv4.conf.ens3.send_redirects=0
+  $ sudo sysctl -w net.ipv4.conf.lo.send_redirects=0
+  $ sudo sysctl -w net.ipv4.conf.default.send_redirects=0
+
+We want to let sever A send a packet to 8.8.8.8, and route the packet
+to server B. When server B receives such packet, it might send a ICMP
+Redirect message to server A, set send_redirects to 0 will disable
+this behavior.
+
+First, generate InAddrErrors. On server B, we disable IP forwarding::
+
+  $ sudo sysctl -w net.ipv4.conf.all.forwarding=0
+
+On server A, we send packets to 8.8.8.8::
+
+  $ nc -v 8.8.8.8 53
+
+On server B, we check the output of nstat::
+
+  $ nstat
+  #kernel
+  IpInReceives                    3                  0.0
+  IpInAddrErrors                  3                  0.0
+  IpExtInOctets                   180                0.0
+  IpExtInNoECTPkts                3                  0.0
+
+As we have let server A route 8.8.8.8 to server B, and we disabled IP
+forwarding on server B, Server A sent packets to server B, then server B
+dropped packets and increased IpInAddrErrors. As the nc command would
+re-send the SYN packet if it didn't receive a SYN+ACK, we could find
+multiple IpInAddrErrors.
+
+Second, generate IpExtInNoRoutes. On server B, we enable IP
+forwarding::
+
+  $ sudo sysctl -w net.ipv4.conf.all.forwarding=1
+
+Check the route table of server B and remove the default route::
+
+  $ ip route show
+  default via 192.168.122.1 dev ens3 proto static
+  192.168.122.0/24 dev ens3 proto kernel scope link src 192.168.122.251
+  $ sudo ip route delete default via 192.168.122.1 dev ens3 proto static
+
+On server A, we contact 8.8.8.8 again::
+
+  $ nc -v 8.8.8.8 53
+  nc: connect to 8.8.8.8 port 53 (tcp) failed: Network is unreachable
+
+On server B, run nstat::
+
+  $ nstat
+  #kernel
+  IpInReceives                    1                  0.0
+  IpOutRequests                   1                  0.0
+  IcmpOutMsgs                     1                  0.0
+  IcmpOutDestUnreachs             1                  0.0
+  IcmpMsgOutType3                 1                  0.0
+  IpExtInNoRoutes                 1                  0.0
+  IpExtInOctets                   60                 0.0
+  IpExtOutOctets                  88                 0.0
+  IpExtInNoECTPkts                1                  0.0
+
+We enabled IP forwarding on server B, when server B received a packet
+which destination IP address is 8.8.8.8, server B will try to forward
+this packet. We have deleted the default route, there was no route for
+8.8.8.8, so server B increase IpExtInNoRoutes and sent the "ICMP
+Destination Unreachable" message to server A.
+
+Third, generate IpOutNoRoutes. Run ping command on server B::
+
+  $ ping -c 1 8.8.8.8
+  connect: Network is unreachable
+
+Run nstat on server B::
+
+  $ nstat
+  #kernel
+  IpOutNoRoutes                   1                  0.0
+
+We have deleted the default route on server B. Server B couldn't find
+a route for the 8.8.8.8 IP address, so server B increased
+IpOutNoRoutes.
-- 
cgit v1.2.3


From 4cdeeee9252af1ba50482f91d615f326365306bd Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Wed, 12 Dec 2018 13:15:33 -0800
Subject: net: udp: prefer listeners bound to an address

A relatively common use case is to have several IPs configured
on a host, and have different listeners for each of them. We would
like to add a "catch all" listener on addr_any, to match incoming
connections not served by any of the listeners bound to a specific
address.

However, port-only lookups can match addr_any sockets when sockets
listening on specific addresses are present if so_reuseport flag
is set. This patch eliminates lookups into port-only hashtable,
as lookups by (addr,port) tuple are easily available.

In addition, compute_score() is tweaked to _not_ match
addr_any sockets to specific addresses, as hash collisions
could result in the unwanted behavior described above.

Tested: the patch compiles; full test in the last patch in this
patchset. Existing reuseport_* selftests also pass.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 76 +++++++++++++++-------------------------------------------
 1 file changed, 19 insertions(+), 57 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index aff2a8e99e01..3fb0ed5e4789 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -380,15 +380,12 @@ static int compute_score(struct sock *sk, struct net *net,
 	    ipv6_only_sock(sk))
 		return -1;
 
-	score = (sk->sk_family == PF_INET) ? 2 : 1;
-	inet = inet_sk(sk);
+	if (sk->sk_rcv_saddr != daddr)
+		return -1;
 
-	if (inet->inet_rcv_saddr) {
-		if (inet->inet_rcv_saddr != daddr)
-			return -1;
-		score += 4;
-	}
+	score = (sk->sk_family == PF_INET) ? 2 : 1;
 
+	inet = inet_sk(sk);
 	if (inet->inet_daddr) {
 		if (inet->inet_daddr != saddr)
 			return -1;
@@ -464,65 +461,30 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 		__be16 sport, __be32 daddr, __be16 dport, int dif,
 		int sdif, struct udp_table *udptable, struct sk_buff *skb)
 {
-	struct sock *sk, *result;
+	struct sock *result;
 	unsigned short hnum = ntohs(dport);
-	unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
-	struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
+	unsigned int hash2, slot2;
+	struct udp_hslot *hslot2;
 	bool exact_dif = udp_lib_exact_dif_match(net, skb);
-	int score, badness;
-	u32 hash = 0;
 
-	if (hslot->count > 10) {
-		hash2 = ipv4_portaddr_hash(net, daddr, hnum);
+	hash2 = ipv4_portaddr_hash(net, daddr, hnum);
+	slot2 = hash2 & udptable->mask;
+	hslot2 = &udptable->hash2[slot2];
+
+	result = udp4_lib_lookup2(net, saddr, sport,
+				  daddr, hnum, dif, sdif,
+				  exact_dif, hslot2, skb);
+	if (!result) {
+		hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
 		slot2 = hash2 & udptable->mask;
 		hslot2 = &udptable->hash2[slot2];
-		if (hslot->count < hslot2->count)
-			goto begin;
 
 		result = udp4_lib_lookup2(net, saddr, sport,
-					  daddr, hnum, dif, sdif,
+					  htonl(INADDR_ANY), hnum, dif, sdif,
 					  exact_dif, hslot2, skb);
-		if (!result) {
-			unsigned int old_slot2 = slot2;
-			hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
-			slot2 = hash2 & udptable->mask;
-			/* avoid searching the same slot again. */
-			if (unlikely(slot2 == old_slot2))
-				return result;
-
-			hslot2 = &udptable->hash2[slot2];
-			if (hslot->count < hslot2->count)
-				goto begin;
-
-			result = udp4_lib_lookup2(net, saddr, sport,
-						  daddr, hnum, dif, sdif,
-						  exact_dif, hslot2, skb);
-		}
-		if (unlikely(IS_ERR(result)))
-			return NULL;
-		return result;
-	}
-begin:
-	result = NULL;
-	badness = 0;
-	sk_for_each_rcu(sk, &hslot->head) {
-		score = compute_score(sk, net, saddr, sport,
-				      daddr, hnum, dif, sdif, exact_dif);
-		if (score > badness) {
-			if (sk->sk_reuseport) {
-				hash = udp_ehashfn(net, daddr, hnum,
-						   saddr, sport);
-				result = reuseport_select_sock(sk, hash, skb,
-							sizeof(struct udphdr));
-				if (unlikely(IS_ERR(result)))
-					return NULL;
-				if (result)
-					return result;
-			}
-			result = sk;
-			badness = score;
-		}
 	}
+	if (unlikely(IS_ERR(result)))
+		return NULL;
 	return result;
 }
 EXPORT_SYMBOL_GPL(__udp4_lib_lookup);
-- 
cgit v1.2.3


From 23b0269e58aee1165133b9696e43992f969b5088 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Wed, 12 Dec 2018 13:15:34 -0800
Subject: net: udp6: prefer listeners bound to an address

A relatively common use case is to have several IPs configured
on a host, and have different listeners for each of them. We would
like to add a "catch all" listener on addr_any, to match incoming
connections not served by any of the listeners bound to a specific
address.

However, port-only lookups can match addr_any sockets when sockets
listening on specific addresses are present if so_reuseport flag
is set. This patch eliminates lookups into port-only hashtable,
as lookups by (addr,port) tuple are easily available.

In addition, compute_score() is tweaked to _not_ match
addr_any sockets to specific addresses, as hash collisions
could result in the unwanted behavior described above.

Tested: the patch compiles; full test in the last patch in this
patchset. Existing reuseport_* selftests also pass.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 79 ++++++++++++++++------------------------------------------
 1 file changed, 21 insertions(+), 58 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 09cba4cfe31f..9cbf363172bd 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -125,6 +125,9 @@ static int compute_score(struct sock *sk, struct net *net,
 	    sk->sk_family != PF_INET6)
 		return -1;
 
+	if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+		return -1;
+
 	score = 0;
 	inet = inet_sk(sk);
 
@@ -134,12 +137,6 @@ static int compute_score(struct sock *sk, struct net *net,
 		score++;
 	}
 
-	if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
-		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
-			return -1;
-		score++;
-	}
-
 	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
 		if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
 			return -1;
@@ -197,66 +194,32 @@ struct sock *__udp6_lib_lookup(struct net *net,
 			       int dif, int sdif, struct udp_table *udptable,
 			       struct sk_buff *skb)
 {
-	struct sock *sk, *result;
 	unsigned short hnum = ntohs(dport);
-	unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
-	struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
+	unsigned int hash2, slot2;
+	struct udp_hslot *hslot2;
+	struct sock *result;
 	bool exact_dif = udp6_lib_exact_dif_match(net, skb);
-	int score, badness;
-	u32 hash = 0;
 
-	if (hslot->count > 10) {
-		hash2 = ipv6_portaddr_hash(net, daddr, hnum);
+	hash2 = ipv6_portaddr_hash(net, daddr, hnum);
+	slot2 = hash2 & udptable->mask;
+	hslot2 = &udptable->hash2[slot2];
+
+	result = udp6_lib_lookup2(net, saddr, sport,
+				  daddr, hnum, dif, sdif, exact_dif,
+				  hslot2, skb);
+	if (!result) {
+		hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
 		slot2 = hash2 & udptable->mask;
+
 		hslot2 = &udptable->hash2[slot2];
-		if (hslot->count < hslot2->count)
-			goto begin;
 
 		result = udp6_lib_lookup2(net, saddr, sport,
-					  daddr, hnum, dif, sdif, exact_dif,
-					  hslot2, skb);
-		if (!result) {
-			unsigned int old_slot2 = slot2;
-			hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
-			slot2 = hash2 & udptable->mask;
-			/* avoid searching the same slot again. */
-			if (unlikely(slot2 == old_slot2))
-				return result;
-
-			hslot2 = &udptable->hash2[slot2];
-			if (hslot->count < hslot2->count)
-				goto begin;
-
-			result = udp6_lib_lookup2(net, saddr, sport,
-						  daddr, hnum, dif, sdif,
-						  exact_dif, hslot2,
-						  skb);
-		}
-		if (unlikely(IS_ERR(result)))
-			return NULL;
-		return result;
-	}
-begin:
-	result = NULL;
-	badness = -1;
-	sk_for_each_rcu(sk, &hslot->head) {
-		score = compute_score(sk, net, saddr, sport, daddr, hnum, dif,
-				      sdif, exact_dif);
-		if (score > badness) {
-			if (sk->sk_reuseport) {
-				hash = udp6_ehashfn(net, daddr, hnum,
-						    saddr, sport);
-				result = reuseport_select_sock(sk, hash, skb,
-							sizeof(struct udphdr));
-				if (unlikely(IS_ERR(result)))
-					return NULL;
-				if (result)
-					return result;
-			}
-			result = sk;
-			badness = score;
-		}
+					  &in6addr_any, hnum, dif, sdif,
+					  exact_dif, hslot2,
+					  skb);
 	}
+	if (unlikely(IS_ERR(result)))
+		return NULL;
 	return result;
 }
 EXPORT_SYMBOL_GPL(__udp6_lib_lookup);
-- 
cgit v1.2.3


From d9fbc7f6431fc0e5c0ddedf72206d7c5175c5c9a Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Wed, 12 Dec 2018 13:15:35 -0800
Subject: net: tcp: prefer listeners bound to an address

A relatively common use case is to have several IPs configured
on a host, and have different listeners for each of them. We would
like to add a "catch all" listener on addr_any, to match incoming
connections not served by any of the listeners bound to a specific
address.

However, port-only lookups can match addr_any sockets when sockets
listening on specific addresses are present if so_reuseport flag
is set. This patch eliminates lookups into port-only hashtable,
as lookups by (addr,port) tuple are easily available.

In addition, compute_score() is tweaked to _not_ match
addr_any sockets to specific addresses, as hash collisions
could result in the unwanted behavior described above.

Tested: the patch compiles; full test in the last patch in this
patchset. Existing reuseport_* selftests also pass.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_hashtables.c | 60 +++++++---------------------------------------
 1 file changed, 8 insertions(+), 52 deletions(-)

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 13890d5bfc34..cd03ab42705b 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -234,24 +234,16 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				const int dif, const int sdif, bool exact_dif)
 {
 	int score = -1;
-	struct inet_sock *inet = inet_sk(sk);
-	bool dev_match;
 
-	if (net_eq(sock_net(sk), net) && inet->inet_num == hnum &&
+	if (net_eq(sock_net(sk), net) && sk->sk_num == hnum &&
 			!ipv6_only_sock(sk)) {
-		__be32 rcv_saddr = inet->inet_rcv_saddr;
-		score = sk->sk_family == PF_INET ? 2 : 1;
-		if (rcv_saddr) {
-			if (rcv_saddr != daddr)
-				return -1;
-			score += 4;
-		}
-		dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
-						 dif, sdif);
-		if (!dev_match)
+		if (sk->sk_rcv_saddr != daddr)
+			return -1;
+
+		if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
 			return -1;
-		score += 4;
 
+		score = sk->sk_family == PF_INET ? 2 : 1;
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())
 			score++;
 	}
@@ -307,26 +299,12 @@ struct sock *__inet_lookup_listener(struct net *net,
 				    const __be32 daddr, const unsigned short hnum,
 				    const int dif, const int sdif)
 {
-	unsigned int hash = inet_lhashfn(net, hnum);
-	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
-	bool exact_dif = inet_exact_dif_match(net, skb);
 	struct inet_listen_hashbucket *ilb2;
-	struct sock *sk, *result = NULL;
-	int score, hiscore = 0;
+	struct sock *result = NULL;
 	unsigned int hash2;
-	u32 phash = 0;
-
-	if (ilb->count <= 10 || !hashinfo->lhash2)
-		goto port_lookup;
-
-	/* Too many sk in the ilb bucket (which is hashed by port alone).
-	 * Try lhash2 (which is hashed by port and addr) instead.
-	 */
 
 	hash2 = ipv4_portaddr_hash(net, daddr, hnum);
 	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
-	if (ilb2->count > ilb->count)
-		goto port_lookup;
 
 	result = inet_lhash2_lookup(net, ilb2, skb, doff,
 				    saddr, sport, daddr, hnum,
@@ -335,34 +313,12 @@ struct sock *__inet_lookup_listener(struct net *net,
 		goto done;
 
 	/* Lookup lhash2 with INADDR_ANY */
-
 	hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
 	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
-	if (ilb2->count > ilb->count)
-		goto port_lookup;
 
 	result = inet_lhash2_lookup(net, ilb2, skb, doff,
-				    saddr, sport, daddr, hnum,
+				    saddr, sport, htonl(INADDR_ANY), hnum,
 				    dif, sdif);
-	goto done;
-
-port_lookup:
-	sk_for_each_rcu(sk, &ilb->head) {
-		score = compute_score(sk, net, hnum, daddr,
-				      dif, sdif, exact_dif);
-		if (score > hiscore) {
-			if (sk->sk_reuseport) {
-				phash = inet_ehashfn(net, daddr, hnum,
-						     saddr, sport);
-				result = reuseport_select_sock(sk, phash,
-							       skb, doff);
-				if (result)
-					goto done;
-			}
-			result = sk;
-			hiscore = score;
-		}
-	}
 done:
 	if (unlikely(IS_ERR(result)))
 		return NULL;
-- 
cgit v1.2.3


From 0ee58dad5b065f5910c2c926d8c9f07cbe2db86c Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Wed, 12 Dec 2018 13:15:36 -0800
Subject: net: tcp6: prefer listeners bound to an address

A relatively common use case is to have several IPs configured
on a host, and have different listeners for each of them. We would
like to add a "catch all" listener on addr_any, to match incoming
connections not served by any of the listeners bound to a specific
address.

However, port-only lookups can match addr_any sockets when sockets
listening on specific addresses are present if so_reuseport flag
is set. This patch eliminates lookups into port-only hashtable,
as lookups by (addr,port) tuple are easily available.

In addition, compute_score() is tweaked to _not_ match
addr_any sockets to specific addresses, as hash collisions
could result in the unwanted behavior described above.

Tested: the patch compiles; full test in the last patch in this
patchset. Existing reuseport_* selftests also pass.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/inet6_hashtables.c | 54 +++++----------------------------------------
 1 file changed, 6 insertions(+), 48 deletions(-)

diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 5eeeba7181a1..f3515ebe9b3a 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -99,23 +99,16 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				const int dif, const int sdif, bool exact_dif)
 {
 	int score = -1;
-	bool dev_match;
 
 	if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
 	    sk->sk_family == PF_INET6) {
+		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+			return -1;
 
-		score = 1;
-		if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
-			if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
-				return -1;
-			score++;
-		}
-		dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
-						 dif, sdif);
-		if (!dev_match)
+		if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
 			return -1;
-		score++;
 
+		score = 1;
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())
 			score++;
 	}
@@ -164,26 +157,12 @@ struct sock *inet6_lookup_listener(struct net *net,
 		const __be16 sport, const struct in6_addr *daddr,
 		const unsigned short hnum, const int dif, const int sdif)
 {
-	unsigned int hash = inet_lhashfn(net, hnum);
-	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
-	bool exact_dif = inet6_exact_dif_match(net, skb);
 	struct inet_listen_hashbucket *ilb2;
-	struct sock *sk, *result = NULL;
-	int score, hiscore = 0;
+	struct sock *result = NULL;
 	unsigned int hash2;
-	u32 phash = 0;
-
-	if (ilb->count <= 10 || !hashinfo->lhash2)
-		goto port_lookup;
-
-	/* Too many sk in the ilb bucket (which is hashed by port alone).
-	 * Try lhash2 (which is hashed by port and addr) instead.
-	 */
 
 	hash2 = ipv6_portaddr_hash(net, daddr, hnum);
 	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
-	if (ilb2->count > ilb->count)
-		goto port_lookup;
 
 	result = inet6_lhash2_lookup(net, ilb2, skb, doff,
 				     saddr, sport, daddr, hnum,
@@ -192,33 +171,12 @@ struct sock *inet6_lookup_listener(struct net *net,
 		goto done;
 
 	/* Lookup lhash2 with in6addr_any */
-
 	hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
 	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
-	if (ilb2->count > ilb->count)
-		goto port_lookup;
 
 	result = inet6_lhash2_lookup(net, ilb2, skb, doff,
-				     saddr, sport, daddr, hnum,
+				     saddr, sport, &in6addr_any, hnum,
 				     dif, sdif);
-	goto done;
-
-port_lookup:
-	sk_for_each(sk, &ilb->head) {
-		score = compute_score(sk, net, hnum, daddr, dif, sdif, exact_dif);
-		if (score > hiscore) {
-			if (sk->sk_reuseport) {
-				phash = inet6_ehashfn(net, daddr, hnum,
-						      saddr, sport);
-				result = reuseport_select_sock(sk, phash,
-							       skb, doff);
-				if (result)
-					goto done;
-			}
-			result = sk;
-			hiscore = score;
-		}
-	}
 done:
 	if (unlikely(IS_ERR(result)))
 		return NULL;
-- 
cgit v1.2.3


From 6254e5c6a8d7c19e51e671e2648de2db06f8d504 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Wed, 12 Dec 2018 13:15:37 -0800
Subject: selftests: net: test that listening sockets match on address properly

This patch adds a selftest that verifies that a socket listening
on a specific address is chosen in preference over sockets
that listen on any address. The test covers UDP/UDP6/TCP/TCP6.

It is based on, and similar to, reuseport_dualstack.c selftest.

Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/.gitignore            |   1 +
 tools/testing/selftests/net/Makefile              |   4 +-
 tools/testing/selftests/net/reuseport_addr_any.c  | 264 ++++++++++++++++++++++
 tools/testing/selftests/net/reuseport_addr_any.sh |   4 +
 4 files changed, 271 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/net/reuseport_addr_any.c
 create mode 100755 tools/testing/selftests/net/reuseport_addr_any.sh

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 7f57b916e6b2..6f81130605d7 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -3,6 +3,7 @@ socket
 psock_fanout
 psock_snd
 psock_tpacket
+reuseport_addr_any
 reuseport_bpf
 reuseport_bpf_cpu
 reuseport_bpf_numa
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index ee2e27b1cd0d..aeecc3ef53d0 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -7,10 +7,10 @@ CFLAGS += -I../../../../usr/include/
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
-TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh
+TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
-TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
+TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
 TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
diff --git a/tools/testing/selftests/net/reuseport_addr_any.c b/tools/testing/selftests/net/reuseport_addr_any.c
new file mode 100644
index 000000000000..f5e01d989519
--- /dev/null
+++ b/tools/testing/selftests/net/reuseport_addr_any.c
@@ -0,0 +1,264 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Test that sockets listening on a specific address are preferred
+ * over sockets listening on addr_any.
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/in.h>
+#include <linux/unistd.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/epoll.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+static const char *IP4_ADDR = "127.0.0.1";
+static const char *IP6_ADDR = "::1";
+static const char *IP4_MAPPED6 = "::ffff:127.0.0.1";
+
+static const int PORT = 8888;
+
+static void build_rcv_fd(int family, int proto, int *rcv_fds, int count,
+			 const char *addr_str)
+{
+	struct sockaddr_in  addr4 = {0};
+	struct sockaddr_in6 addr6 = {0};
+	struct sockaddr *addr;
+	int opt, i, sz;
+
+	memset(&addr, 0, sizeof(addr));
+
+	switch (family) {
+	case AF_INET:
+		addr4.sin_family = family;
+		if (!addr_str)
+			addr4.sin_addr.s_addr = htonl(INADDR_ANY);
+		else if (!inet_pton(family, addr_str, &addr4.sin_addr.s_addr))
+			error(1, errno, "inet_pton failed: %s", addr_str);
+		addr4.sin_port = htons(PORT);
+		sz = sizeof(addr4);
+		addr = (struct sockaddr *)&addr4;
+		break;
+	case AF_INET6:
+		addr6.sin6_family = AF_INET6;
+		if (!addr_str)
+			addr6.sin6_addr = in6addr_any;
+		else if (!inet_pton(family, addr_str, &addr6.sin6_addr))
+			error(1, errno, "inet_pton failed: %s", addr_str);
+		addr6.sin6_port = htons(PORT);
+		sz = sizeof(addr6);
+		addr = (struct sockaddr *)&addr6;
+		break;
+	default:
+		error(1, 0, "Unsupported family %d", family);
+	}
+
+	for (i = 0; i < count; ++i) {
+		rcv_fds[i] = socket(family, proto, 0);
+		if (rcv_fds[i] < 0)
+			error(1, errno, "failed to create receive socket");
+
+		opt = 1;
+		if (setsockopt(rcv_fds[i], SOL_SOCKET, SO_REUSEPORT, &opt,
+			       sizeof(opt)))
+			error(1, errno, "failed to set SO_REUSEPORT");
+
+		if (bind(rcv_fds[i], addr, sz))
+			error(1, errno, "failed to bind receive socket");
+
+		if (proto == SOCK_STREAM && listen(rcv_fds[i], 10))
+			error(1, errno, "failed to listen on receive port");
+	}
+}
+
+static int connect_and_send(int family, int proto)
+{
+	struct sockaddr_in  saddr4 = {0};
+	struct sockaddr_in  daddr4 = {0};
+	struct sockaddr_in6 saddr6 = {0};
+	struct sockaddr_in6 daddr6 = {0};
+	struct sockaddr *saddr, *daddr;
+	int fd, sz;
+
+	switch (family) {
+	case AF_INET:
+		saddr4.sin_family = AF_INET;
+		saddr4.sin_addr.s_addr = htonl(INADDR_ANY);
+		saddr4.sin_port = 0;
+
+		daddr4.sin_family = AF_INET;
+		if (!inet_pton(family, IP4_ADDR, &daddr4.sin_addr.s_addr))
+			error(1, errno, "inet_pton failed: %s", IP4_ADDR);
+		daddr4.sin_port = htons(PORT);
+
+		sz = sizeof(saddr4);
+		saddr = (struct sockaddr *)&saddr4;
+		daddr = (struct sockaddr *)&daddr4;
+	break;
+	case AF_INET6:
+		saddr6.sin6_family = AF_INET6;
+		saddr6.sin6_addr = in6addr_any;
+
+		daddr6.sin6_family = AF_INET6;
+		if (!inet_pton(family, IP6_ADDR, &daddr6.sin6_addr))
+			error(1, errno, "inet_pton failed: %s", IP6_ADDR);
+		daddr6.sin6_port = htons(PORT);
+
+		sz = sizeof(saddr6);
+		saddr = (struct sockaddr *)&saddr6;
+		daddr = (struct sockaddr *)&daddr6;
+	break;
+	default:
+		error(1, 0, "Unsupported family %d", family);
+	}
+
+	fd = socket(family, proto, 0);
+	if (fd < 0)
+		error(1, errno, "failed to create send socket");
+
+	if (bind(fd, saddr, sz))
+		error(1, errno, "failed to bind send socket");
+
+	if (connect(fd, daddr, sz))
+		error(1, errno, "failed to connect send socket");
+
+	if (send(fd, "a", 1, 0) < 0)
+		error(1, errno, "failed to send message");
+
+	return fd;
+}
+
+static int receive_once(int epfd, int proto)
+{
+	struct epoll_event ev;
+	int i, fd;
+	char buf[8];
+
+	i = epoll_wait(epfd, &ev, 1, 3);
+	if (i < 0)
+		error(1, errno, "epoll_wait failed");
+
+	if (proto == SOCK_STREAM) {
+		fd = accept(ev.data.fd, NULL, NULL);
+		if (fd < 0)
+			error(1, errno, "failed to accept");
+		i = recv(fd, buf, sizeof(buf), 0);
+		close(fd);
+	} else {
+		i = recv(ev.data.fd, buf, sizeof(buf), 0);
+	}
+
+	if (i < 0)
+		error(1, errno, "failed to recv");
+
+	return ev.data.fd;
+}
+
+static void test(int *rcv_fds, int count, int family, int proto, int fd)
+{
+	struct epoll_event ev;
+	int epfd, i, send_fd, recv_fd;
+
+	epfd = epoll_create(1);
+	if (epfd < 0)
+		error(1, errno, "failed to create epoll");
+
+	ev.events = EPOLLIN;
+	for (i = 0; i < count; ++i) {
+		ev.data.fd = rcv_fds[i];
+		if (epoll_ctl(epfd, EPOLL_CTL_ADD, rcv_fds[i], &ev))
+			error(1, errno, "failed to register sock epoll");
+	}
+
+	send_fd = connect_and_send(family, proto);
+
+	recv_fd = receive_once(epfd, proto);
+	if (recv_fd != fd)
+		error(1, 0, "received on an unexpected socket");
+
+	close(send_fd);
+	close(epfd);
+}
+
+int main(void)
+{
+	/* Below we test that a socket listening on a specific address
+	 * is always selected in preference over a socket listening
+	 * on addr_any. Bugs where this is not the case often result
+	 * in sockets created first or last to get picked. So below
+	 * we make sure that there are always addr_any sockets created
+	 * before and after a specific socket is created.
+	 */
+	int rcv_fds[10], i;
+
+	fprintf(stderr, "---- UDP IPv4 ----\n");
+	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 2, 2, NULL);
+	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds + 4, 1, IP4_ADDR);
+	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds + 5, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 7, 2, NULL);
+	test(rcv_fds, 9, AF_INET, SOCK_DGRAM, rcv_fds[4]);
+	for (i = 0; i < 9; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- UDP IPv6 ----\n");
+	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 2, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 4, 1, IP6_ADDR);
+	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds + 5, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 7, 2, NULL);
+	test(rcv_fds, 9, AF_INET6, SOCK_DGRAM, rcv_fds[4]);
+	for (i = 0; i < 9; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- UDP IPv4 mapped to IPv6 ----\n");
+	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 2, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 4, 1, IP4_MAPPED6);
+	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds + 5, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 7, 2, NULL);
+	test(rcv_fds, 9, AF_INET, SOCK_DGRAM, rcv_fds[4]);
+	for (i = 0; i < 9; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- TCP IPv4 ----\n");
+	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 2, 2, NULL);
+	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds + 4, 1, IP4_ADDR);
+	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds + 5, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 7, 2, NULL);
+	test(rcv_fds, 9, AF_INET, SOCK_STREAM, rcv_fds[4]);
+	for (i = 0; i < 9; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- TCP IPv6 ----\n");
+	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 2, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 4, 1, IP6_ADDR);
+	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds + 5, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 7, 2, NULL);
+	test(rcv_fds, 9, AF_INET6, SOCK_STREAM, rcv_fds[4]);
+	for (i = 0; i < 9; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- TCP IPv4 mapped to IPv6 ----\n");
+	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 2, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 4, 1, IP4_MAPPED6);
+	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds + 5, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 7, 2, NULL);
+	test(rcv_fds, 9, AF_INET, SOCK_STREAM, rcv_fds[4]);
+	for (i = 0; i < 9; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "SUCCESS\n");
+	return 0;
+}
diff --git a/tools/testing/selftests/net/reuseport_addr_any.sh b/tools/testing/selftests/net/reuseport_addr_any.sh
new file mode 100755
index 000000000000..104592f62ad4
--- /dev/null
+++ b/tools/testing/selftests/net/reuseport_addr_any.sh
@@ -0,0 +1,4 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+./in_netns.sh ./reuseport_addr_any
-- 
cgit v1.2.3


From b233920c97a6201eb47fbafd78365c6946e6d7b6 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 13 Dec 2018 11:42:31 -0800
Subject: bpf: speed up stacksafe check

Don't check the same stack liveness condition 8 times.
once is enough.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Edward Cree <ecree@solarflare.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ba8e3134bbc2..0c6deb3f2be4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5204,9 +5204,11 @@ static bool stacksafe(struct bpf_func_state *old,
 	for (i = 0; i < old->allocated_stack; i++) {
 		spi = i / BPF_REG_SIZE;
 
-		if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ))
+		if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) {
+			i += BPF_REG_SIZE - 1;
 			/* explored state didn't use this */
 			continue;
+		}
 
 		if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
 			continue;
-- 
cgit v1.2.3


From 730ff40f80c5b09b2402958321f2762a3f852e30 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 13 Dec 2018 11:42:32 -0800
Subject: selftests/bpf: check insn processed in test_verifier

Teach test_verifier to parse verifier output for insn processed
and compare with expected number.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Edward Cree <ecree@solarflare.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index a08c67c8767e..82359cdbc805 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -76,7 +76,7 @@ struct bpf_test {
 	int fixup_percpu_cgroup_storage[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
-	uint32_t retval, retval_unpriv;
+	uint32_t retval, retval_unpriv, insn_processed;
 	enum {
 		UNDEF,
 		ACCEPT,
@@ -14444,6 +14444,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		}
 	}
 
+	if (test->insn_processed) {
+		uint32_t insn_processed;
+		char *proc;
+
+		proc = strstr(bpf_vlog, "processed ");
+		insn_processed = atoi(proc + 10);
+		if (test->insn_processed != insn_processed) {
+			printf("FAIL\nUnexpected insn_processed %u vs %u\n",
+			       insn_processed, test->insn_processed);
+			goto fail_log;
+		}
+	}
+
 	if (fd_prog >= 0) {
 		__u8 tmp[TEST_DATA_LEN << 2];
 		__u32 size_tmp = sizeof(tmp);
-- 
cgit v1.2.3


From 19e2dbb7dd978d24505e918ac54d6f7dfdc88b1d Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 13 Dec 2018 11:42:33 -0800
Subject: bpf: improve stacksafe state comparison

"if (old->allocated_stack > cur->allocated_stack)" check is too conservative.
In some cases explored stack could have allocated more space,
but that stack space was not live.
The test case improves from 19 to 15 processed insns
and improvement on real programs is significant as well:

                       before    after
bpf_lb-DLB_L3.o        1940      1831
bpf_lb-DLB_L4.o        3089      3029
bpf_lb-DUNKNOWN.o      1065      1064
bpf_lxc-DDROP_ALL.o    28052     26309
bpf_lxc-DUNKNOWN.o     35487     33517
bpf_netdev.o           10864     9713
bpf_overlay.o          6643      6184
bpf_lcx_jit.o          38437     37335

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Edward Cree <ecree@solarflare.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c                       | 13 +++++++------
 tools/testing/selftests/bpf/test_verifier.c | 22 ++++++++++++++++++++++
 2 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0c6deb3f2be4..e4724fe8120f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5191,12 +5191,6 @@ static bool stacksafe(struct bpf_func_state *old,
 {
 	int i, spi;
 
-	/* if explored stack has more populated slots than current stack
-	 * such stacks are not equivalent
-	 */
-	if (old->allocated_stack > cur->allocated_stack)
-		return false;
-
 	/* walk slots of the explored stack and ignore any additional
 	 * slots in the current stack, since explored(safe) state
 	 * didn't use them
@@ -5212,6 +5206,13 @@ static bool stacksafe(struct bpf_func_state *old,
 
 		if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
 			continue;
+
+		/* explored stack has more populated slots than current stack
+		 * and these slots were used
+		 */
+		if (i >= cur->allocated_stack)
+			return false;
+
 		/* if old state was safe with misc data in the stack
 		 * it will be safe with zero-initialized stack.
 		 * The opposite is not true
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 82359cdbc805..f9de7fe0c26d 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -13647,6 +13647,28 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 	},
+	{
+		"allocated_stack",
+		.insns = {
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_7, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, -8),
+			BPF_STX_MEM(BPF_B, BPF_REG_10, BPF_REG_7, -9),
+			BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_10, -9),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.result_unpriv = ACCEPT,
+		.insn_processed = 15,
+	},
 	{
 		"reference tracking in call: free reference in subprog and outside",
 		.insns = {
-- 
cgit v1.2.3


From 9242b5f5615c823bfc1e9aea284617ff25a55f10 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 13 Dec 2018 11:42:34 -0800
Subject: bpf: add self-check logic to liveness analysis

Introduce REG_LIVE_DONE to check the liveness propagation
and prepare the states for merging.
See algorithm description in clean_live_states().

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf_verifier.h |   1 +
 kernel/bpf/verifier.c        | 108 ++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 108 insertions(+), 1 deletion(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 548dcbdb7111..c233efc106c6 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -38,6 +38,7 @@ enum bpf_reg_liveness {
 	REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */
 	REG_LIVE_READ, /* reg was read, so we're sensitive to initial value */
 	REG_LIVE_WRITTEN, /* reg was written first, screening off later reads */
+	REG_LIVE_DONE = 4, /* liveness won't be updating this register anymore */
 };
 
 struct bpf_reg_state {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e4724fe8120f..0125731e2512 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -397,12 +397,14 @@ static char slot_type_char[] = {
 static void print_liveness(struct bpf_verifier_env *env,
 			   enum bpf_reg_liveness live)
 {
-	if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN))
+	if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
 	    verbose(env, "_");
 	if (live & REG_LIVE_READ)
 		verbose(env, "r");
 	if (live & REG_LIVE_WRITTEN)
 		verbose(env, "w");
+	if (live & REG_LIVE_DONE)
+		verbose(env, "D");
 }
 
 static struct bpf_func_state *func(struct bpf_verifier_env *env,
@@ -1132,6 +1134,12 @@ static int mark_reg_read(struct bpf_verifier_env *env,
 		/* if read wasn't screened by an earlier write ... */
 		if (writes && state->live & REG_LIVE_WRITTEN)
 			break;
+		if (parent->live & REG_LIVE_DONE) {
+			verbose(env, "verifier BUG type %s var_off %lld off %d\n",
+				reg_type_str[parent->type],
+				parent->var_off.value, parent->off);
+			return -EFAULT;
+		}
 		/* ... then we depend on parent's value */
 		parent->live |= REG_LIVE_READ;
 		state = parent;
@@ -5078,6 +5086,102 @@ static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap)
 	return false;
 }
 
+static void clean_func_state(struct bpf_verifier_env *env,
+			     struct bpf_func_state *st)
+{
+	enum bpf_reg_liveness live;
+	int i, j;
+
+	for (i = 0; i < BPF_REG_FP; i++) {
+		live = st->regs[i].live;
+		/* liveness must not touch this register anymore */
+		st->regs[i].live |= REG_LIVE_DONE;
+		if (!(live & REG_LIVE_READ))
+			/* since the register is unused, clear its state
+			 * to make further comparison simpler
+			 */
+			__mark_reg_not_init(&st->regs[i]);
+	}
+
+	for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) {
+		live = st->stack[i].spilled_ptr.live;
+		/* liveness must not touch this stack slot anymore */
+		st->stack[i].spilled_ptr.live |= REG_LIVE_DONE;
+		if (!(live & REG_LIVE_READ)) {
+			__mark_reg_not_init(&st->stack[i].spilled_ptr);
+			for (j = 0; j < BPF_REG_SIZE; j++)
+				st->stack[i].slot_type[j] = STACK_INVALID;
+		}
+	}
+}
+
+static void clean_verifier_state(struct bpf_verifier_env *env,
+				 struct bpf_verifier_state *st)
+{
+	int i;
+
+	if (st->frame[0]->regs[0].live & REG_LIVE_DONE)
+		/* all regs in this state in all frames were already marked */
+		return;
+
+	for (i = 0; i <= st->curframe; i++)
+		clean_func_state(env, st->frame[i]);
+}
+
+/* the parentage chains form a tree.
+ * the verifier states are added to state lists at given insn and
+ * pushed into state stack for future exploration.
+ * when the verifier reaches bpf_exit insn some of the verifer states
+ * stored in the state lists have their final liveness state already,
+ * but a lot of states will get revised from liveness point of view when
+ * the verifier explores other branches.
+ * Example:
+ * 1: r0 = 1
+ * 2: if r1 == 100 goto pc+1
+ * 3: r0 = 2
+ * 4: exit
+ * when the verifier reaches exit insn the register r0 in the state list of
+ * insn 2 will be seen as !REG_LIVE_READ. Then the verifier pops the other_branch
+ * of insn 2 and goes exploring further. At the insn 4 it will walk the
+ * parentage chain from insn 4 into insn 2 and will mark r0 as REG_LIVE_READ.
+ *
+ * Since the verifier pushes the branch states as it sees them while exploring
+ * the program the condition of walking the branch instruction for the second
+ * time means that all states below this branch were already explored and
+ * their final liveness markes are already propagated.
+ * Hence when the verifier completes the search of state list in is_state_visited()
+ * we can call this clean_live_states() function to mark all liveness states
+ * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state'
+ * will not be used.
+ * This function also clears the registers and stack for states that !READ
+ * to simplify state merging.
+ *
+ * Important note here that walking the same branch instruction in the callee
+ * doesn't meant that the states are DONE. The verifier has to compare
+ * the callsites
+ */
+static void clean_live_states(struct bpf_verifier_env *env, int insn,
+			      struct bpf_verifier_state *cur)
+{
+	struct bpf_verifier_state_list *sl;
+	int i;
+
+	sl = env->explored_states[insn];
+	if (!sl)
+		return;
+
+	while (sl != STATE_LIST_MARK) {
+		if (sl->state.curframe != cur->curframe)
+			goto next;
+		for (i = 0; i <= cur->curframe; i++)
+			if (sl->state.frame[i]->callsite != cur->frame[i]->callsite)
+				goto next;
+		clean_verifier_state(env, &sl->state);
+next:
+		sl = sl->next;
+	}
+}
+
 /* Returns true if (rold safe implies rcur safe) */
 static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
 		    struct idpair *idmap)
@@ -5396,6 +5500,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 		 */
 		return 0;
 
+	clean_live_states(env, insn_idx, cur);
+
 	while (sl != STATE_LIST_MARK) {
 		if (states_equal(env, &sl->state, cur)) {
 			/* reached equivalent register/stack state,
-- 
cgit v1.2.3


From bc6cd664609b92aa437ed3f384e332faab5949c8 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 14 Dec 2018 13:55:57 +0000
Subject: tools: bpftool: add doc for -m option to bpftool-prog.rst

The --mapcompat|-m option has been documented on the main bpftool.rst
page, and on the interactive help. As this option is useful for loading
programs with maps with the "bpftool prog load" command, it should also
appear in the related bpftool-prog.rst documentation page. Let's add it.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index bb1aeb98b6da..b41e96ac0dfe 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -158,6 +158,9 @@ OPTIONS
 		  When showing BPF programs, show file names of pinned
 		  programs.
 
+	-m, --mapcompat
+		  Allow loading maps with unknown map definitions.
+
 EXAMPLES
 ========
 **# bpftool prog show**
-- 
cgit v1.2.3


From 32870ba4078c3b4deac7ccb35b078c9ab69488a3 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 14 Dec 2018 13:55:58 +0000
Subject: tools: bpftool: fix examples in documentation for bpftool prog

Bring various fixes to the manual page for "bpftool prog" set of
commands:

- Fix typos ("dum" -> "dump")
- Harmonise indentation and format for command output
- Update date format for program load time
- Add instruction numbers on program dumps
- Fix JSON format for the example program listing

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 98 +++++++++++++-----------
 1 file changed, 53 insertions(+), 45 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index b41e96ac0dfe..53920ffc48dd 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -164,80 +164,88 @@ OPTIONS
 EXAMPLES
 ========
 **# bpftool prog show**
+
 ::
 
-  10: xdp  name some_prog  tag 005a3d2123620c8b  gpl
-	loaded_at Sep 29/20:11  uid 0
-	xlated 528B  jited 370B  memlock 4096B  map_ids 10
+    10: xdp  name some_prog  tag 005a3d2123620c8b  gpl
+            loaded_at 2017-09-29T20:11:00+0000  uid 0
+            xlated 528B  jited 370B  memlock 4096B  map_ids 10
 
 **# bpftool --json --pretty prog show**
 
 ::
 
-    {
-        "programs": [{
-                "id": 10,
-                "type": "xdp",
-                "tag": "005a3d2123620c8b",
-                "gpl_compatible": true,
-                "loaded_at": "Sep 29/20:11",
-                "uid": 0,
-                "bytes_xlated": 528,
-                "jited": true,
-                "bytes_jited": 370,
-                "bytes_memlock": 4096,
-                "map_ids": [10
-                ]
-            }
-        ]
-    }
+    [{
+            "id": 10,
+            "type": "xdp",
+            "tag": "005a3d2123620c8b",
+            "gpl_compatible": true,
+            "loaded_at": 1506715860,
+            "uid": 0,
+            "bytes_xlated": 528,
+            "jited": true,
+            "bytes_jited": 370,
+            "bytes_memlock": 4096,
+            "map_ids": [10
+            ]
+        }
+    ]
 
 |
 | **# bpftool prog dump xlated id 10 file /tmp/t**
 | **# ls -l /tmp/t**
-|   -rw------- 1 root root 560 Jul 22 01:42 /tmp/t
 
-**# bpftool prog dum jited tag 005a3d2123620c8b**
+::
+
+    -rw------- 1 root root 560 Jul 22 01:42 /tmp/t
+
+**# bpftool prog dump jited tag 005a3d2123620c8b**
 
 ::
 
-    push   %rbp
-    mov    %rsp,%rbp
-    sub    $0x228,%rsp
-    sub    $0x28,%rbp
-    mov    %rbx,0x0(%rbp)
+    0:   push   %rbp
+    1:   mov    %rsp,%rbp
+    2:   sub    $0x228,%rsp
+    3:   sub    $0x28,%rbp
+    4:   mov    %rbx,0x0(%rbp)
 
 |
 | **# mount -t bpf none /sys/fs/bpf/**
 | **# bpftool prog pin id 10 /sys/fs/bpf/prog**
 | **# bpftool prog load ./my_prog.o /sys/fs/bpf/prog2**
 | **# ls -l /sys/fs/bpf/**
-|   -rw------- 1 root root 0 Jul 22 01:43 prog
-|   -rw------- 1 root root 0 Jul 22 01:44 prog2
 
-**# bpftool prog dum jited pinned /sys/fs/bpf/prog opcodes**
+::
+
+    -rw------- 1 root root 0 Jul 22 01:43 prog
+    -rw------- 1 root root 0 Jul 22 01:44 prog2
+
+**# bpftool prog dump jited pinned /sys/fs/bpf/prog opcodes**
 
 ::
 
-    push   %rbp
-    55
-    mov    %rsp,%rbp
-    48 89 e5
-    sub    $0x228,%rsp
-    48 81 ec 28 02 00 00
-    sub    $0x28,%rbp
-    48 83 ed 28
-    mov    %rbx,0x0(%rbp)
-    48 89 5d 00
+   0:   push   %rbp
+        55
+   1:   mov    %rsp,%rbp
+        48 89 e5
+   4:   sub    $0x228,%rsp
+        48 81 ec 28 02 00 00
+   b:   sub    $0x28,%rbp
+        48 83 ed 28
+   f:   mov    %rbx,0x0(%rbp)
+        48 89 5d 00
 
 |
 | **# bpftool prog load xdp1_kern.o /sys/fs/bpf/xdp1 type xdp map name rxcnt id 7**
 | **# bpftool prog show pinned /sys/fs/bpf/xdp1**
-|   9: xdp  name xdp_prog1  tag 539ec6ce11b52f98  gpl
-|	loaded_at 2018-06-25T16:17:31-0700  uid 0
-|	xlated 488B  jited 336B  memlock 4096B  map_ids 7
-| **# rm /sys/fs/bpf/xdp1**
-|
+
+::
+
+    9: xdp  name xdp_prog1  tag 539ec6ce11b52f98  gpl
+            loaded_at 2018-06-25T16:17:31-0700  uid 0
+            xlated 488B  jited 336B  memlock 4096B  map_ids 7
+
+**# rm /sys/fs/bpf/xdp1**
 
 SEE ALSO
 ========
-- 
cgit v1.2.3


From bd0fb9d0078edbfa2c983ad61901d90f1c0f5747 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 14 Dec 2018 13:55:59 +0000
Subject: tools: bpftool: add a prog array map update example to documentation

Add an example in map documentation to show how to use bpftool in order
to update the references to programs hold by prog array maps.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-map.rst | 55 +++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index 5318dcb2085e..3221be1b9ccc 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -170,6 +170,61 @@ The following three commands are equivalent:
 | **# bpftool map pin id 10 /sys/fs/bpf/map**
 | **# bpftool map del pinned /sys/fs/bpf/map key 13 00 07 00**
 
+Note that map update can also be used in order to change the program references
+hold by a program array map. This can be used, for example, to change the
+programs used for tail-call jumps at runtime, without having to reload the
+entry-point program. Below is an example for this use case: we load a program
+defining a prog array map, and with a main function that contains a tail call
+to other programs that can be used either to "process" packets or to "debug"
+processing. Note that the prog array map MUST be pinned into the BPF virtual
+file system for the map update to work successfully, as kernel flushes prog
+array maps when they have no more references from user space (and the update
+would be lost as soon as bpftool exits).
+
+|
+| **# bpftool prog loadall tail_calls.o /sys/fs/bpf/foo type xdp**
+| **# bpftool prog --bpffs**
+
+::
+
+  545: xdp  name main_func  tag 674b4b5597193dc3  gpl
+          loaded_at 2018-12-12T15:02:58+0000  uid 0
+          xlated 240B  jited 257B  memlock 4096B  map_ids 294
+          pinned /sys/fs/bpf/foo/xdp
+  546: xdp  name bpf_func_process  tag e369a529024751fc  gpl
+          loaded_at 2018-12-12T15:02:58+0000  uid 0
+          xlated 200B  jited 164B  memlock 4096B
+          pinned /sys/fs/bpf/foo/process
+  547: xdp  name bpf_func_debug  tag 0b597868bc7f0976  gpl
+          loaded_at 2018-12-12T15:02:58+0000  uid 0
+          xlated 200B  jited 164B  memlock 4096B
+          pinned /sys/fs/bpf/foo/debug
+
+**# bpftool map**
+
+::
+
+  294: prog_array  name jmp_table  flags 0x0
+          key 4B  value 4B  max_entries 1  memlock 4096B
+          owner_prog_type xdp  owner jited
+
+|
+| **# bpftool map pin id 294 /sys/fs/bpf/bar**
+| **# bpftool map dump pinned /sys/fs/bpf/bar**
+
+::
+
+  Found 0 elements
+
+|
+| **# bpftool map update pinned /sys/fs/bpf/bar key 0 0 0 0 value pinned /sys/fs/bpf/foo/debug**
+| **# bpftool map dump pinned /sys/fs/bpf/bar**
+
+::
+
+  key: 00 00 00 00  value: 22 02 00 00
+  Found 1 element
+
 SEE ALSO
 ========
 	**bpf**\ (2),
-- 
cgit v1.2.3


From 8c03ecf712f5bbbb9d353ed69715aef3cc2b4029 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 14 Dec 2018 13:56:00 +0000
Subject: tools: bpftool: fix warning on struct bpf_prog_linfo definition

The following warning appears when compiling bpftool without BFD
support:

main.h:198:23: warning: 'struct bpf_prog_linfo' declared inside
    parameter list will not be visible outside of this definition or
    declaration
          const struct bpf_prog_linfo *prog_linfo,

Fix it by declaring struct bpf_prog_linfo even in the case BFD is not
supported.

Fixes: b053b439b72a ("bpf: libbpf: bpftool: Print bpf_line_info during prog dump")
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/main.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index d2beb88f0e2e..9487345b04a7 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -147,8 +147,8 @@ int prog_parse_fd(int *argc, char ***argv);
 int map_parse_fd(int *argc, char ***argv);
 int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
 
-#ifdef HAVE_LIBBFD_SUPPORT
 struct bpf_prog_linfo;
+#ifdef HAVE_LIBBFD_SUPPORT
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 		       const char *arch, const char *disassembler_options,
 		       const struct btf *btf,
-- 
cgit v1.2.3


From c101189bc9680675a2686bafe908015a07a0da51 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Fri, 14 Dec 2018 13:56:01 +0000
Subject: tools: bpftool: fix -Wmissing declaration warnings

Help compiler check arguments for several utility functions used to
print items to the console by adding the "printf" attribute when
declaring those functions.

Also, declare as "static" two functions that are only used in prog.c.

All of them discovered by compiling bpftool with
-Wmissing-format-attribute -Wmissing-declarations.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/common.c        | 4 ++--
 tools/bpf/bpftool/json_writer.c   | 6 ++++--
 tools/bpf/bpftool/prog.c          | 4 ++--
 tools/bpf/bpftool/xlated_dumper.c | 7 ++++---
 4 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 99e4027dde75..24582e8a96fb 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -28,7 +28,7 @@
 #define BPF_FS_MAGIC		0xcafe4a11
 #endif
 
-void p_err(const char *fmt, ...)
+void __printf(1, 2) p_err(const char *fmt, ...)
 {
 	va_list ap;
 
@@ -46,7 +46,7 @@ void p_err(const char *fmt, ...)
 	va_end(ap);
 }
 
-void p_info(const char *fmt, ...)
+void __printf(1, 2) p_info(const char *fmt, ...)
 {
 	va_list ap;
 
diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c
index a07d17918725..bff7ee026680 100644
--- a/tools/bpf/bpftool/json_writer.c
+++ b/tools/bpf/bpftool/json_writer.c
@@ -20,6 +20,7 @@
 #include <malloc.h>
 #include <inttypes.h>
 #include <stdint.h>
+#include <linux/compiler.h>
 
 #include "json_writer.h"
 
@@ -157,7 +158,8 @@ void jsonw_name(json_writer_t *self, const char *name)
 		putc(' ', self->out);
 }
 
-void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap)
+void __printf(2, 0)
+jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap)
 {
 	jsonw_eor(self);
 	putc('"', self->out);
@@ -165,7 +167,7 @@ void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap)
 	putc('"', self->out);
 }
 
-void jsonw_printf(json_writer_t *self, const char *fmt, ...)
+void __printf(2, 3) jsonw_printf(json_writer_t *self, const char *fmt, ...)
 {
 	va_list ap;
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index ee51279be9c7..2d1bb7d6ff51 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -32,7 +32,7 @@ static const char * const attach_type_strings[] = {
 	[__MAX_BPF_ATTACH_TYPE] = NULL,
 };
 
-enum bpf_attach_type parse_attach_type(const char *str)
+static enum bpf_attach_type parse_attach_type(const char *str)
 {
 	enum bpf_attach_type type;
 
@@ -798,7 +798,7 @@ struct map_replace {
 	char *name;
 };
 
-int map_replace_compar(const void *p1, const void *p2)
+static int map_replace_compar(const void *p1, const void *p2)
 {
 	const struct map_replace *a = p1, *b = p2;
 
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 640ffe86a655..7073dbe1ff27 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -81,7 +81,7 @@ struct kernel_sym *kernel_syms_search(struct dump_data *dd,
 		       sizeof(*dd->sym_mapping), kernel_syms_cmp) : NULL;
 }
 
-static void print_insn(void *private_data, const char *fmt, ...)
+static void __printf(2, 3) print_insn(void *private_data, const char *fmt, ...)
 {
 	va_list args;
 
@@ -90,7 +90,7 @@ static void print_insn(void *private_data, const char *fmt, ...)
 	va_end(args);
 }
 
-static void
+static void __printf(2, 3)
 print_insn_for_graph(void *private_data, const char *fmt, ...)
 {
 	char buf[64], *p;
@@ -121,7 +121,8 @@ print_insn_for_graph(void *private_data, const char *fmt, ...)
 	printf("%s", buf);
 }
 
-static void print_insn_json(void *private_data, const char *fmt, ...)
+static void __printf(2, 3)
+print_insn_json(void *private_data, const char *fmt, ...)
 {
 	unsigned int l = strlen(fmt);
 	char chomped_fmt[l];
-- 
cgit v1.2.3


From 122bedc56a6c4f5be3bc56fdc59d4b3a25097ead Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Sat, 15 Dec 2018 15:31:53 +0000
Subject: net: hns3: Add "bd info" query function

This patch prints Sending and receiving
package descriptor information.

debugfs command:
echo dump bd info 1 > cmd

Sample Command:
root@(none)# echo bd info 1 > cmd
hns3 0000:7d:00.0: TX Queue Num: 0, BD Index: 0
hns3 0000:7d:00.0: (TX) addr: 0x0
hns3 0000:7d:00.0: (TX)vlan_tag: 0
hns3 0000:7d:00.0: (TX)send_size: 0
hns3 0000:7d:00.0: (TX)vlan_tso: 0
hns3 0000:7d:00.0: (TX)l2_len: 0
hns3 0000:7d:00.0: (TX)l3_len: 0
hns3 0000:7d:00.0: (TX)l4_len: 0
hns3 0000:7d:00.0: (TX)vlan_tag: 0
hns3 0000:7d:00.0: (TX)tv: 0
hns3 0000:7d:00.0: (TX)vlan_msec: 0
hns3 0000:7d:00.0: (TX)ol2_len: 0
hns3 0000:7d:00.0: (TX)ol3_len: 0
hns3 0000:7d:00.0: (TX)ol4_len: 0
hns3 0000:7d:00.0: (TX)paylen: 0
hns3 0000:7d:00.0: (TX)vld_ra_ri: 0
hns3 0000:7d:00.0: (TX)mss: 0
hns3 0000:7d:00.0: RX Queue Num: 0, BD Index: 120
hns3 0000:7d:00.0: (RX)addr: 0xffee7000
hns3 0000:7d:00.0: (RX)pkt_len: 0
hns3 0000:7d:00.0: (RX)size: 0
hns3 0000:7d:00.0: (RX)rss_hash: 0
hns3 0000:7d:00.0: (RX)fd_id: 0
hns3 0000:7d:00.0: (RX)vlan_tag: 0
hns3 0000:7d:00.0: (RX)o_dm_vlan_id_fb: 0
hns3 0000:7d:00.0: (RX)ot_vlan_tag: 0
hns3 0000:7d:00.0: (RX)bd_base_info: 0

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 79 +++++++++++++++++++++-
 1 file changed, 78 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 86d667a3730a..9a026556df0e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -52,7 +52,7 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h, char *cmd_buf)
 		    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
 			return -EPERM;
 
-		ring = ring_data[i + h->kinfo.num_tqps].ring;
+		ring = ring_data[(u32)(i + h->kinfo.num_tqps)].ring;
 		base_add_h = readl_relaxed(ring->tqp->io_base +
 					   HNS3_RING_RX_RING_BASEADDR_H_REG);
 		base_add_l = readl_relaxed(ring->tqp->io_base +
@@ -125,10 +125,85 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h, char *cmd_buf)
 	return 0;
 }
 
+static int hns3_dbg_bd_info(struct hnae3_handle *h, char *cmd_buf)
+{
+	struct hns3_nic_priv *priv = h->priv;
+	struct hns3_nic_ring_data *ring_data;
+	struct hns3_desc *rx_desc, *tx_desc;
+	struct device *dev = &h->pdev->dev;
+	struct hns3_enet_ring *ring;
+	u32 tx_index, rx_index;
+	u32 q_num, value;
+	int cnt;
+
+	cnt = sscanf(&cmd_buf[8], "%u %u", &q_num, &tx_index);
+	if (cnt == 2) {
+		rx_index = tx_index;
+	} else if (cnt != 1) {
+		dev_err(dev, "bd info: bad command string, cnt=%d\n", cnt);
+		return -EINVAL;
+	}
+
+	if (q_num >= h->kinfo.num_tqps) {
+		dev_err(dev, "Queue number(%u) is out of range(%u)\n", q_num,
+			h->kinfo.num_tqps - 1);
+		return -EINVAL;
+	}
+
+	ring_data = priv->ring_data;
+	ring  = ring_data[q_num].ring;
+	value = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG);
+	tx_index = (cnt == 1) ? value : tx_index;
+
+	if (tx_index >= ring->desc_num) {
+		dev_err(dev, "bd index (%u) is out of range(%u)\n", tx_index,
+			ring->desc_num - 1);
+		return -EINVAL;
+	}
+
+	tx_desc = &ring->desc[tx_index];
+	dev_info(dev, "TX Queue Num: %u, BD Index: %u\n", q_num, tx_index);
+	dev_info(dev, "(TX) addr: 0x%llx\n", tx_desc->addr);
+	dev_info(dev, "(TX)vlan_tag: %u\n", tx_desc->tx.vlan_tag);
+	dev_info(dev, "(TX)send_size: %u\n", tx_desc->tx.send_size);
+	dev_info(dev, "(TX)vlan_tso: %u\n", tx_desc->tx.type_cs_vlan_tso);
+	dev_info(dev, "(TX)l2_len: %u\n", tx_desc->tx.l2_len);
+	dev_info(dev, "(TX)l3_len: %u\n", tx_desc->tx.l3_len);
+	dev_info(dev, "(TX)l4_len: %u\n", tx_desc->tx.l4_len);
+	dev_info(dev, "(TX)vlan_tag: %u\n", tx_desc->tx.outer_vlan_tag);
+	dev_info(dev, "(TX)tv: %u\n", tx_desc->tx.tv);
+	dev_info(dev, "(TX)vlan_msec: %u\n", tx_desc->tx.ol_type_vlan_msec);
+	dev_info(dev, "(TX)ol2_len: %u\n", tx_desc->tx.ol2_len);
+	dev_info(dev, "(TX)ol3_len: %u\n", tx_desc->tx.ol3_len);
+	dev_info(dev, "(TX)ol4_len: %u\n", tx_desc->tx.ol4_len);
+	dev_info(dev, "(TX)paylen: %u\n", tx_desc->tx.paylen);
+	dev_info(dev, "(TX)vld_ra_ri: %u\n", tx_desc->tx.bdtp_fe_sc_vld_ra_ri);
+	dev_info(dev, "(TX)mss: %u\n", tx_desc->tx.mss);
+
+	ring  = ring_data[q_num + h->kinfo.num_tqps].ring;
+	value = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG);
+	rx_index = (cnt == 1) ? value : tx_index;
+	rx_desc	 = &ring->desc[rx_index];
+
+	dev_info(dev, "RX Queue Num: %u, BD Index: %u\n", q_num, rx_index);
+	dev_info(dev, "(RX)addr: 0x%llx\n", rx_desc->addr);
+	dev_info(dev, "(RX)pkt_len: %u\n", rx_desc->rx.pkt_len);
+	dev_info(dev, "(RX)size: %u\n", rx_desc->rx.size);
+	dev_info(dev, "(RX)rss_hash: %u\n", rx_desc->rx.rss_hash);
+	dev_info(dev, "(RX)fd_id: %u\n", rx_desc->rx.fd_id);
+	dev_info(dev, "(RX)vlan_tag: %u\n", rx_desc->rx.vlan_tag);
+	dev_info(dev, "(RX)o_dm_vlan_id_fb: %u\n", rx_desc->rx.o_dm_vlan_id_fb);
+	dev_info(dev, "(RX)ot_vlan_tag: %u\n", rx_desc->rx.ot_vlan_tag);
+	dev_info(dev, "(RX)bd_base_info: %u\n", rx_desc->rx.bd_base_info);
+
+	return 0;
+}
+
 static void hns3_dbg_help(struct hnae3_handle *h)
 {
 	dev_info(&h->pdev->dev, "available commands\n");
 	dev_info(&h->pdev->dev, "queue info [number]\n");
+	dev_info(&h->pdev->dev, "bd info [q_num] <bd index>\n");
 	dev_info(&h->pdev->dev, "dump fd tcam\n");
 	dev_info(&h->pdev->dev, "dump tc\n");
 	dev_info(&h->pdev->dev, "dump tm\n");
@@ -205,6 +280,8 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
 		hns3_dbg_help(handle);
 	else if (strncmp(cmd_buf, "queue info", 10) == 0)
 		ret = hns3_dbg_queue_info(handle, cmd_buf);
+	else if (strncmp(cmd_buf, "bd info", 7) == 0)
+		ret = hns3_dbg_bd_info(handle, cmd_buf);
 	else if (handle->ae_algo->ops->dbg_run_cmd)
 		ret = handle->ae_algo->ops->dbg_run_cmd(handle, cmd_buf);
 
-- 
cgit v1.2.3


From 7737f1fbb5ba1581e8b77ed4b2302485fa237f1e Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Sat, 15 Dec 2018 15:31:54 +0000
Subject: net: hns3: Add "manager table" information query function

This patch prints manager table information.

debugfs command:
echo dump mng tbl > cmd

Sample Command:
root@(none)# echo dump mng tbl > cmd
 entry|mac_addr         |mask|ether|mask|vlan|mask|i_map|i_dir|e_type
 00   |01:00:5e:00:00:01|0   |00000|0   |0000|0   |00   |00   |0
 01   |c2:f1:c5:82:68:17|0   |00000|0   |0000|0   |00   |00   |0
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |  5 +-
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 19 +++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 66 ++++++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h | 12 ++++
 4 files changed, 100 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 9a026556df0e..4c5a421456b7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -48,7 +48,7 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h, char *cmd_buf)
 		 * to prevent reference to invalid memory. And need to ensure
 		 * that the following code is executed within 100ms.
 		 */
-		if (test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
+		if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
 		    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
 			return -EPERM;
 
@@ -210,6 +210,7 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "dump qos pause cfg\n");
 	dev_info(&h->pdev->dev, "dump qos pri map\n");
 	dev_info(&h->pdev->dev, "dump qos buf cfg\n");
+	dev_info(&h->pdev->dev, "dump mng tbl\n");
 }
 
 static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
@@ -254,7 +255,7 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
 		return 0;
 
 	/* Judge if the instance is being reset. */
-	if (test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
+	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
 	    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
 		return 0;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index b1ee6feb0caf..dcacfa089b74 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -237,6 +237,7 @@ enum hclge_opcode_type {
 	HCLGE_TM_QCN_MEM_INT_CFG	= 0x1A14,
 	HCLGE_PPP_CMD0_INT_CMD		= 0x2100,
 	HCLGE_PPP_CMD1_INT_CMD		= 0x2101,
+	HCLGE_MAC_ETHERTYPE_IDX_RD      = 0x2105,
 	HCLGE_NCSI_INT_EN		= 0x2401,
 };
 
@@ -744,6 +745,24 @@ struct hclge_cfg_tx_queue_pointer_cmd {
 	u8 rsv[14];
 };
 
+#pragma pack(1)
+struct hclge_mac_ethertype_idx_rd_cmd {
+	u8	flags;
+	u8	resp_code;
+	__le16  vlan_tag;
+	u8      mac_add[6];
+	__le16  index;
+	__le16	ethter_type;
+	__le16  egress_port;
+	__le16  egress_queue;
+	__le16  rev0;
+	u8	i_port_bitmap;
+	u8	i_port_direction;
+	u8	rev1[2];
+};
+
+#pragma pack()
+
 #define HCLGE_TSO_MSS_MIN_S	0
 #define HCLGE_TSO_MSS_MIN_M	GENMASK(13, 0)
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 14577bbf3e11..77a11618040d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -407,6 +407,70 @@ err_qos_cmd_send:
 		"dump qos buf cfg fail(0x%x), status is %d\n", cmd, ret);
 }
 
+static void hclge_dbg_dump_mng_table(struct hclge_dev *hdev)
+{
+	struct hclge_mac_ethertype_idx_rd_cmd *req0;
+	char printf_buf[HCLGE_DBG_BUF_LEN];
+	struct hclge_desc desc;
+	int ret, i;
+
+	dev_info(&hdev->pdev->dev, "mng tab:\n");
+	memset(printf_buf, 0, HCLGE_DBG_BUF_LEN);
+	strncat(printf_buf,
+		"entry|mac_addr         |mask|ether|mask|vlan|mask",
+		HCLGE_DBG_BUF_LEN - 1);
+	strncat(printf_buf + strlen(printf_buf),
+		"|i_map|i_dir|e_type|pf_id|vf_id|q_id|drop\n",
+		HCLGE_DBG_BUF_LEN - strlen(printf_buf) - 1);
+
+	dev_info(&hdev->pdev->dev, "%s", printf_buf);
+
+	for (i = 0; i < HCLGE_DBG_MNG_TBL_MAX; i++) {
+		hclge_cmd_setup_basic_desc(&desc, HCLGE_MAC_ETHERTYPE_IDX_RD,
+					   true);
+		req0 = (struct hclge_mac_ethertype_idx_rd_cmd *)&desc.data;
+		req0->index = cpu_to_le16(i);
+
+		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"call hclge_cmd_send fail, ret = %d\n", ret);
+			return;
+		}
+
+		if (!req0->resp_code)
+			continue;
+
+		memset(printf_buf, 0, HCLGE_DBG_BUF_LEN);
+		snprintf(printf_buf, HCLGE_DBG_BUF_LEN,
+			 "%02u   |%02x:%02x:%02x:%02x:%02x:%02x|",
+			 req0->index, req0->mac_add[0], req0->mac_add[1],
+			 req0->mac_add[2], req0->mac_add[3], req0->mac_add[4],
+			 req0->mac_add[5]);
+
+		snprintf(printf_buf + strlen(printf_buf),
+			 HCLGE_DBG_BUF_LEN - strlen(printf_buf),
+			 "%x   |%04x |%x   |%04x|%x   |%02x   |%02x   |",
+			 !!(req0->flags & HCLGE_DBG_MNG_MAC_MASK_B),
+			 req0->ethter_type,
+			 !!(req0->flags & HCLGE_DBG_MNG_ETHER_MASK_B),
+			 req0->vlan_tag & HCLGE_DBG_MNG_VLAN_TAG,
+			 !!(req0->flags & HCLGE_DBG_MNG_VLAN_MASK_B),
+			 req0->i_port_bitmap, req0->i_port_direction);
+
+		snprintf(printf_buf + strlen(printf_buf),
+			 HCLGE_DBG_BUF_LEN - strlen(printf_buf),
+			 "%d     |%d    |%02d   |%04d|%x\n",
+			 !!(req0->egress_port & HCLGE_DBG_MNG_E_TYPE_B),
+			 req0->egress_port & HCLGE_DBG_MNG_PF_ID,
+			 (req0->egress_port >> 3) & HCLGE_DBG_MNG_VF_ID,
+			 req0->egress_queue,
+			 !!(req0->egress_port & HCLGE_DBG_MNG_DROP_B));
+
+		dev_info(&hdev->pdev->dev, "%s", printf_buf);
+	}
+}
+
 static void hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage,
 				   bool sel_x, u32 loc)
 {
@@ -478,6 +542,8 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
 		hclge_dbg_dump_qos_pri_map(hdev);
 	} else if (strncmp(cmd_buf, "dump qos buf cfg", 16) == 0) {
 		hclge_dbg_dump_qos_buf_cfg(hdev);
+	} else if (strncmp(cmd_buf, "dump mng tbl", 12) == 0) {
+		hclge_dbg_dump_mng_table(hdev);
 	} else {
 		dev_info(&hdev->pdev->dev, "unknown command\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
index 50fd0b15fb8e..6097cd858081 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
@@ -4,6 +4,18 @@
 #ifndef __HCLGE_DEBUGFS_H
 #define __HCLGE_DEBUGFS_H
 
+#define HCLGE_DBG_BUF_LEN	   256
+#define HCLGE_DBG_MNG_TBL_MAX	   64
+
+#define HCLGE_DBG_MNG_VLAN_MASK_B  BIT(0)
+#define HCLGE_DBG_MNG_MAC_MASK_B   BIT(1)
+#define HCLGE_DBG_MNG_ETHER_MASK_B BIT(2)
+#define HCLGE_DBG_MNG_E_TYPE_B	   BIT(11)
+#define HCLGE_DBG_MNG_DROP_B	   BIT(13)
+#define HCLGE_DBG_MNG_VLAN_TAG	   0x0FFF
+#define HCLGE_DBG_MNG_PF_ID	   0x0007
+#define HCLGE_DBG_MNG_VF_ID	   0x00FF
+
 #pragma pack(1)
 
 struct hclge_qos_pri_map_cmd {
-- 
cgit v1.2.3


From 27cf979a15841eed5de06b6f46ae490ce2fda46b Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Sat, 15 Dec 2018 15:31:55 +0000
Subject: net: hns3: Add "status register" information query function

This patch prints status register information by module.

debugfs command:
echo dump reg [mode name] > cmd

Sample Command:
root@(none)# echo dump reg bios common > cmd
 BP_CPU_STATE: 0x0
 DFX_MSIX_INFO_NIC_0: 0xc000
 DFX_MSIX_INFO_NIC_1: 0xf
 DFX_MSIX_INFO_NIC_2: 0x2
 DFX_MSIX_INFO_NIC_3: 0x2
 DFX_MSIX_INFO_ROC_0: 0xc000
 DFX_MSIX_INFO_ROC_1: 0x0
 DFX_MSIX_INFO_ROC_2: 0x0
 DFX_MSIX_INFO_ROC_3: 0x0
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |  15 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |  14 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 194 ++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h | 662 +++++++++++++++++++++
 4 files changed, 885 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 4c5a421456b7..e6268e03d221 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -201,6 +201,10 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, char *cmd_buf)
 
 static void hns3_dbg_help(struct hnae3_handle *h)
 {
+#define HNS3_DBG_BUF_LEN 256
+
+	char printf_buf[HNS3_DBG_BUF_LEN];
+
 	dev_info(&h->pdev->dev, "available commands\n");
 	dev_info(&h->pdev->dev, "queue info [number]\n");
 	dev_info(&h->pdev->dev, "bd info [q_num] <bd index>\n");
@@ -211,6 +215,17 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "dump qos pri map\n");
 	dev_info(&h->pdev->dev, "dump qos buf cfg\n");
 	dev_info(&h->pdev->dev, "dump mng tbl\n");
+
+	memset(printf_buf, 0, HNS3_DBG_BUF_LEN);
+	strncat(printf_buf, "dump reg [[bios common] [ssu <prt_id>]",
+		HNS3_DBG_BUF_LEN - 1);
+	strncat(printf_buf + strlen(printf_buf),
+		" [igu egu <prt_id>] [rpu <tc_queue_num>]",
+		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
+	strncat(printf_buf + strlen(printf_buf),
+		" [rtc] [ppp] [rcb] [tqp <q_num>]]\n",
+		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
+	dev_info(&h->pdev->dev, "%s", printf_buf);
 }
 
 static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index dcacfa089b74..2b281d909f51 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -86,6 +86,20 @@ enum hclge_opcode_type {
 	HCLGE_OPC_QUERY_REG_NUM		= 0x0040,
 	HCLGE_OPC_QUERY_32_BIT_REG	= 0x0041,
 	HCLGE_OPC_QUERY_64_BIT_REG	= 0x0042,
+	HCLGE_OPC_DFX_BD_NUM		= 0x0043,
+	HCLGE_OPC_DFX_BIOS_COMMON_REG	= 0x0044,
+	HCLGE_OPC_DFX_SSU_REG_0		= 0x0045,
+	HCLGE_OPC_DFX_SSU_REG_1		= 0x0046,
+	HCLGE_OPC_DFX_IGU_EGU_REG	= 0x0047,
+	HCLGE_OPC_DFX_RPU_REG_0		= 0x0048,
+	HCLGE_OPC_DFX_RPU_REG_1		= 0x0049,
+	HCLGE_OPC_DFX_NCSI_REG		= 0x004A,
+	HCLGE_OPC_DFX_RTC_REG		= 0x004B,
+	HCLGE_OPC_DFX_PPP_REG		= 0x004C,
+	HCLGE_OPC_DFX_RCB_REG		= 0x004D,
+	HCLGE_OPC_DFX_TQP_REG		= 0x004E,
+	HCLGE_OPC_DFX_SSU_REG_2		= 0x004F,
+	HCLGE_OPC_DFX_QUERY_CHIP_CAP	= 0x0050,
 
 	/* MAC command */
 	HCLGE_OPC_CONFIG_MAC_MODE	= 0x0301,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 77a11618040d..7d18ed8e17f0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -9,6 +9,198 @@
 #include "hclge_tm.h"
 #include "hnae3.h"
 
+static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset)
+{
+	struct hclge_desc desc[4];
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true);
+
+	ret = hclge_cmd_send(&hdev->hw, desc, 4);
+	if (ret != HCLGE_CMD_EXEC_SUCCESS) {
+		dev_err(&hdev->pdev->dev,
+			"get dfx bdnum fail, status is %d.\n", ret);
+		return ret;
+	}
+
+	return (int)desc[offset / 6].data[offset % 6];
+}
+
+static int hclge_dbg_cmd_send(struct hclge_dev *hdev,
+			      struct hclge_desc *desc_src,
+			      int index, int bd_num,
+			      enum hclge_opcode_type cmd)
+{
+	struct hclge_desc *desc = desc_src;
+	int ret, i;
+
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	desc->data[0] = cpu_to_le32(index);
+
+	for (i = 1; i < bd_num; i++) {
+		desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+		desc++;
+		hclge_cmd_setup_basic_desc(desc, cmd, true);
+	}
+
+	ret = hclge_cmd_send(&hdev->hw, desc_src, bd_num);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"read reg cmd send fail, status is %d.\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
+				      struct hclge_dbg_dfx_message *dfx_message,
+				      char *cmd_buf, int msg_num, int offset,
+				      enum hclge_opcode_type cmd)
+{
+	struct hclge_desc *desc_src;
+	struct hclge_desc *desc;
+	int bd_num, buf_len;
+	int ret, i;
+	int index;
+	int max;
+
+	ret = kstrtouint(cmd_buf, 10, &index);
+	index = (ret != 0) ? 0 : index;
+
+	bd_num = hclge_dbg_get_dfx_bd_num(hdev, offset);
+	if (bd_num <= 0)
+		return;
+
+	buf_len	 = sizeof(struct hclge_desc) * bd_num;
+	desc_src = kzalloc(buf_len, GFP_KERNEL);
+	if (!desc_src) {
+		dev_err(&hdev->pdev->dev, "call kzalloc failed\n");
+		return;
+	}
+
+	desc = desc_src;
+	ret  = hclge_dbg_cmd_send(hdev, desc, index, bd_num, cmd);
+	if (ret != HCLGE_CMD_EXEC_SUCCESS) {
+		kfree(desc_src);
+		return;
+	}
+
+	max = (bd_num * 6) <= msg_num ? (bd_num * 6) : msg_num;
+
+	desc = desc_src;
+	for (i = 0; i < max; i++) {
+		(((i / 6) > 0) && ((i % 6) == 0)) ? desc++ : desc;
+		if (dfx_message->flag)
+			dev_info(&hdev->pdev->dev, "%s: 0x%x\n",
+				 dfx_message->message, desc->data[i % 6]);
+
+		dfx_message++;
+	}
+
+	kfree(desc_src);
+}
+
+static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, char *cmd_buf)
+{
+	int msg_num;
+
+	if (strncmp(&cmd_buf[9], "bios common", 11) == 0) {
+		msg_num = sizeof(hclge_dbg_bios_common_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_bios_common_reg,
+					  &cmd_buf[21], msg_num,
+					  HCLGE_DBG_DFX_BIOS_OFFSET,
+					  HCLGE_OPC_DFX_BIOS_COMMON_REG);
+	} else if (strncmp(&cmd_buf[9], "ssu", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_ssu_reg_0) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_ssu_reg_0,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_SSU_0_OFFSET,
+					  HCLGE_OPC_DFX_SSU_REG_0);
+
+		msg_num = sizeof(hclge_dbg_ssu_reg_1) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_ssu_reg_1,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_SSU_1_OFFSET,
+					  HCLGE_OPC_DFX_SSU_REG_1);
+
+		msg_num = sizeof(hclge_dbg_ssu_reg_2) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_ssu_reg_2,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_SSU_2_OFFSET,
+					  HCLGE_OPC_DFX_SSU_REG_2);
+	} else if (strncmp(&cmd_buf[9], "igu egu", 7) == 0) {
+		msg_num = sizeof(hclge_dbg_igu_egu_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_igu_egu_reg,
+					  &cmd_buf[17], msg_num,
+					  HCLGE_DBG_DFX_IGU_OFFSET,
+					  HCLGE_OPC_DFX_IGU_EGU_REG);
+	} else if (strncmp(&cmd_buf[9], "rpu", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_rpu_reg_0) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_rpu_reg_0,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_RPU_0_OFFSET,
+					  HCLGE_OPC_DFX_RPU_REG_0);
+
+		msg_num = sizeof(hclge_dbg_rpu_reg_1) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_rpu_reg_1,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_RPU_1_OFFSET,
+					  HCLGE_OPC_DFX_RPU_REG_1);
+	} else if (strncmp(&cmd_buf[9], "ncsi", 4) == 0) {
+		msg_num = sizeof(hclge_dbg_ncsi_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_ncsi_reg,
+					  &cmd_buf[14], msg_num,
+					  HCLGE_DBG_DFX_NCSI_OFFSET,
+					  HCLGE_OPC_DFX_NCSI_REG);
+	} else if (strncmp(&cmd_buf[9], "rtc", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_rtc_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_rtc_reg,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_RTC_OFFSET,
+					  HCLGE_OPC_DFX_RTC_REG);
+	} else if (strncmp(&cmd_buf[9], "ppp", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_ppp_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_ppp_reg,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_PPP_OFFSET,
+					  HCLGE_OPC_DFX_PPP_REG);
+	} else if (strncmp(&cmd_buf[9], "rcb", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_rcb_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_rcb_reg,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_RCB_OFFSET,
+					  HCLGE_OPC_DFX_RCB_REG);
+	} else if (strncmp(&cmd_buf[9], "tqp", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_tqp_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_tqp_reg,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_TQP_OFFSET,
+					  HCLGE_OPC_DFX_TQP_REG);
+	} else {
+		dev_info(&hdev->pdev->dev, "unknown command\n");
+		return;
+	}
+}
+
 static void hclge_title_idx_print(struct hclge_dev *hdev, bool flag, int index,
 				  char *title_buf, char *true_buf,
 				  char *false_buf)
@@ -544,6 +736,8 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
 		hclge_dbg_dump_qos_buf_cfg(hdev);
 	} else if (strncmp(cmd_buf, "dump mng tbl", 12) == 0) {
 		hclge_dbg_dump_mng_table(hdev);
+	} else if (strncmp(cmd_buf, "dump reg", 8) == 0) {
+		hclge_dbg_dump_reg_cmd(hdev, cmd_buf);
 	} else {
 		dev_info(&hdev->pdev->dev, "unknown command\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
index 6097cd858081..7a6fbfd38527 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
@@ -16,6 +16,22 @@
 #define HCLGE_DBG_MNG_PF_ID	   0x0007
 #define HCLGE_DBG_MNG_VF_ID	   0x00FF
 
+/* Get DFX BD number offset */
+#define HCLGE_DBG_DFX_BIOS_OFFSET  1
+#define HCLGE_DBG_DFX_SSU_0_OFFSET 2
+#define HCLGE_DBG_DFX_SSU_1_OFFSET 3
+#define HCLGE_DBG_DFX_IGU_OFFSET   4
+#define HCLGE_DBG_DFX_RPU_0_OFFSET 5
+
+#define HCLGE_DBG_DFX_RPU_1_OFFSET 6
+#define HCLGE_DBG_DFX_NCSI_OFFSET  7
+#define HCLGE_DBG_DFX_RTC_OFFSET   8
+#define HCLGE_DBG_DFX_PPP_OFFSET   9
+#define HCLGE_DBG_DFX_RCB_OFFSET   10
+#define HCLGE_DBG_DFX_TQP_OFFSET   11
+
+#define HCLGE_DBG_DFX_SSU_2_OFFSET 12
+
 #pragma pack(1)
 
 struct hclge_qos_pri_map_cmd {
@@ -31,5 +47,651 @@ struct hclge_qos_pri_map_cmd {
 	   rev	    : 4;
 };
 
+struct hclge_dbg_dfx_message {
+	int flag;
+	char message[60];
+};
+
 #pragma pack()
+
+static struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = {
+	{false, "Reserved"},
+	{true,	"BP_CPU_STATE"},
+	{true,	"DFX_MSIX_INFO_NIC_0"},
+	{true,	"DFX_MSIX_INFO_NIC_1"},
+	{true,	"DFX_MSIX_INFO_NIC_2"},
+	{true,	"DFX_MSIX_INFO_NIC_3"},
+
+	{true,	"DFX_MSIX_INFO_ROC_0"},
+	{true,	"DFX_MSIX_INFO_ROC_1"},
+	{true,	"DFX_MSIX_INFO_ROC_2"},
+	{true,	"DFX_MSIX_INFO_ROC_3"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_0[] = {
+	{false, "Reserved"},
+	{true,	"SSU_ETS_PORT_STATUS"},
+	{true,	"SSU_ETS_TCG_STATUS"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{true,	"SSU_BP_STATUS_0"},
+
+	{true,	"SSU_BP_STATUS_1"},
+	{true,	"SSU_BP_STATUS_2"},
+	{true,	"SSU_BP_STATUS_3"},
+	{true,	"SSU_BP_STATUS_4"},
+	{true,	"SSU_BP_STATUS_5"},
+	{true,	"SSU_MAC_TX_PFC_IND"},
+
+	{true,	"MAC_SSU_RX_PFC_IND"},
+	{true,	"BTMP_AGEING_ST_B0"},
+	{true,	"BTMP_AGEING_ST_B1"},
+	{true,	"BTMP_AGEING_ST_B2"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"FULL_DROP_NUM"},
+	{true,	"PART_DROP_NUM"},
+	{true,	"PPP_KEY_DROP_NUM"},
+	{true,	"PPP_RLT_DROP_NUM"},
+	{true,	"LO_PRI_UNICAST_RLT_DROP_NUM"},
+	{true,	"HI_PRI_MULTICAST_RLT_DROP_NUM"},
+
+	{true,	"LO_PRI_MULTICAST_RLT_DROP_NUM"},
+	{true,	"NCSI_PACKET_CURR_BUFFER_CNT"},
+	{true,	"BTMP_AGEING_RLS_CNT_BANK0"},
+	{true,	"BTMP_AGEING_RLS_CNT_BANK1"},
+	{true,	"BTMP_AGEING_RLS_CNT_BANK2"},
+	{true,	"SSU_MB_RD_RLT_DROP_CNT"},
+
+	{true,	"SSU_PPP_MAC_KEY_NUM_L"},
+	{true,	"SSU_PPP_MAC_KEY_NUM_H"},
+	{true,	"SSU_PPP_HOST_KEY_NUM_L"},
+	{true,	"SSU_PPP_HOST_KEY_NUM_H"},
+	{true,	"PPP_SSU_MAC_RLT_NUM_L"},
+	{true,	"PPP_SSU_MAC_RLT_NUM_H"},
+
+	{true,	"PPP_SSU_HOST_RLT_NUM_L"},
+	{true,	"PPP_SSU_HOST_RLT_NUM_H"},
+	{true,	"NCSI_RX_PACKET_IN_CNT_L"},
+	{true,	"NCSI_RX_PACKET_IN_CNT_H"},
+	{true,	"NCSI_TX_PACKET_OUT_CNT_L"},
+	{true,	"NCSI_TX_PACKET_OUT_CNT_H"},
+
+	{true,	"SSU_KEY_DROP_NUM"},
+	{true,	"MB_UNCOPY_NUM"},
+	{true,	"RX_OQ_DROP_PKT_CNT"},
+	{true,	"TX_OQ_DROP_PKT_CNT"},
+	{true,	"BANK_UNBALANCE_DROP_CNT"},
+	{true,	"BANK_UNBALANCE_RX_DROP_CNT"},
+
+	{true,	"NIC_L2_ERR_DROP_PKT_CNT"},
+	{true,	"ROC_L2_ERR_DROP_PKT_CNT"},
+	{true,	"NIC_L2_ERR_DROP_PKT_CNT_RX"},
+	{true,	"ROC_L2_ERR_DROP_PKT_CNT_RX"},
+	{true,	"RX_OQ_GLB_DROP_PKT_CNT"},
+	{false, "Reserved"},
+
+	{true,	"LO_PRI_UNICAST_CUR_CNT"},
+	{true,	"HI_PRI_MULTICAST_CUR_CNT"},
+	{true,	"LO_PRI_MULTICAST_CUR_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_1[] = {
+	{true,	"prt_id"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_0"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_1"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_2"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_3"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_4"},
+
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_5"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_6"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_7"},
+	{true,	"PACKET_CURR_BUFFER_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"RX_PACKET_IN_CNT_L"},
+	{true,	"RX_PACKET_IN_CNT_H"},
+	{true,	"RX_PACKET_OUT_CNT_L"},
+	{true,	"RX_PACKET_OUT_CNT_H"},
+	{true,	"TX_PACKET_IN_CNT_L"},
+	{true,	"TX_PACKET_IN_CNT_H"},
+
+	{true,	"TX_PACKET_OUT_CNT_L"},
+	{true,	"TX_PACKET_OUT_CNT_H"},
+	{true,	"ROC_RX_PACKET_IN_CNT_L"},
+	{true,	"ROC_RX_PACKET_IN_CNT_H"},
+	{true,	"ROC_TX_PACKET_OUT_CNT_L"},
+	{true,	"ROC_TX_PACKET_OUT_CNT_H"},
+
+	{true,	"RX_PACKET_TC_IN_CNT_0_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_0_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_1_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_1_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_2_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_2_H"},
+
+	{true,	"RX_PACKET_TC_IN_CNT_3_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_3_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_4_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_4_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_5_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_5_H"},
+
+	{true,	"RX_PACKET_TC_IN_CNT_6_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_6_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_7_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_7_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_0_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_0_H"},
+
+	{true,	"RX_PACKET_TC_OUT_CNT_1_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_1_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_2_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_2_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_3_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_3_H"},
+
+	{true,	"RX_PACKET_TC_OUT_CNT_4_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_4_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_5_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_5_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_6_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_6_H"},
+
+	{true,	"RX_PACKET_TC_OUT_CNT_7_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_7_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_0_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_0_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_1_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_1_H"},
+
+	{true,	"TX_PACKET_TC_IN_CNT_2_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_2_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_3_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_3_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_4_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_4_H"},
+
+	{true,	"TX_PACKET_TC_IN_CNT_5_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_5_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_6_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_6_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_7_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_7_H"},
+
+	{true,	"TX_PACKET_TC_OUT_CNT_0_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_0_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_1_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_1_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_2_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_2_H"},
+
+	{true,	"TX_PACKET_TC_OUT_CNT_3_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_3_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_4_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_4_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_5_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_5_H"},
+
+	{true,	"TX_PACKET_TC_OUT_CNT_6_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_6_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_7_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_7_H"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_2[] = {
+	{true,	"OQ_INDEX"},
+	{true,	"QUEUE_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_igu_egu_reg[] = {
+	{true,	"prt_id"},
+	{true,	"IGU_RX_ERR_PKT"},
+	{true,	"IGU_RX_NO_SOF_PKT"},
+	{true,	"EGU_TX_1588_SHORT_PKT"},
+	{true,	"EGU_TX_1588_PKT"},
+	{true,	"EGU_TX_ERR_PKT"},
+
+	{true,	"IGU_RX_OUT_L2_PKT"},
+	{true,	"IGU_RX_OUT_L3_PKT"},
+	{true,	"IGU_RX_OUT_L4_PKT"},
+	{true,	"IGU_RX_IN_L2_PKT"},
+	{true,	"IGU_RX_IN_L3_PKT"},
+	{true,	"IGU_RX_IN_L4_PKT"},
+
+	{true,	"IGU_RX_EL3E_PKT"},
+	{true,	"IGU_RX_EL4E_PKT"},
+	{true,	"IGU_RX_L3E_PKT"},
+	{true,	"IGU_RX_L4E_PKT"},
+	{true,	"IGU_RX_ROCEE_PKT"},
+	{true,	"IGU_RX_OUT_UDP0_PKT"},
+
+	{true,	"IGU_RX_IN_UDP0_PKT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"IGU_RX_OVERSIZE_PKT_L"},
+	{true,	"IGU_RX_OVERSIZE_PKT_H"},
+	{true,	"IGU_RX_UNDERSIZE_PKT_L"},
+	{true,	"IGU_RX_UNDERSIZE_PKT_H"},
+	{true,	"IGU_RX_OUT_ALL_PKT_L"},
+	{true,	"IGU_RX_OUT_ALL_PKT_H"},
+
+	{true,	"IGU_TX_OUT_ALL_PKT_L"},
+	{true,	"IGU_TX_OUT_ALL_PKT_H"},
+	{true,	"IGU_RX_UNI_PKT_L"},
+	{true,	"IGU_RX_UNI_PKT_H"},
+	{true,	"IGU_RX_MULTI_PKT_L"},
+	{true,	"IGU_RX_MULTI_PKT_H"},
+
+	{true,	"IGU_RX_BROAD_PKT_L"},
+	{true,	"IGU_RX_BROAD_PKT_H"},
+	{true,	"EGU_TX_OUT_ALL_PKT_L"},
+	{true,	"EGU_TX_OUT_ALL_PKT_H"},
+	{true,	"EGU_TX_UNI_PKT_L"},
+	{true,	"EGU_TX_UNI_PKT_H"},
+
+	{true,	"EGU_TX_MULTI_PKT_L"},
+	{true,	"EGU_TX_MULTI_PKT_H"},
+	{true,	"EGU_TX_BROAD_PKT_L"},
+	{true,	"EGU_TX_BROAD_PKT_H"},
+	{true,	"IGU_TX_KEY_NUM_L"},
+	{true,	"IGU_TX_KEY_NUM_H"},
+
+	{true,	"IGU_RX_NON_TUN_PKT_L"},
+	{true,	"IGU_RX_NON_TUN_PKT_H"},
+	{true,	"IGU_RX_TUN_PKT_L"},
+	{true,	"IGU_RX_TUN_PKT_H"},
+	{false,	"Reserved"},
+	{false,	"Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_0[] = {
+	{true, "tc_queue_num"},
+	{true, "FSM_DFX_ST0"},
+	{true, "FSM_DFX_ST1"},
+	{true, "RPU_RX_PKT_DROP_CNT"},
+	{true, "BUF_WAIT_TIMEOUT"},
+	{true, "BUF_WAIT_TIMEOUT_QID"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_1[] = {
+	{false, "Reserved"},
+	{true,	"FIFO_DFX_ST0"},
+	{true,	"FIFO_DFX_ST1"},
+	{true,	"FIFO_DFX_ST2"},
+	{true,	"FIFO_DFX_ST3"},
+	{true,	"FIFO_DFX_ST4"},
+
+	{true,	"FIFO_DFX_ST5"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_ncsi_reg[] = {
+	{false, "Reserved"},
+	{true,	"NCSI_EGU_TX_FIFO_STS"},
+	{true,	"NCSI_PAUSE_STATUS"},
+	{true,	"NCSI_RX_CTRL_DMAC_ERR_CNT"},
+	{true,	"NCSI_RX_CTRL_SMAC_ERR_CNT"},
+	{true,	"NCSI_RX_CTRL_CKS_ERR_CNT"},
+
+	{true,	"NCSI_RX_CTRL_PKT_CNT"},
+	{true,	"NCSI_RX_PT_DMAC_ERR_CNT"},
+	{true,	"NCSI_RX_PT_SMAC_ERR_CNT"},
+	{true,	"NCSI_RX_PT_PKT_CNT"},
+	{true,	"NCSI_RX_FCS_ERR_CNT"},
+	{true,	"NCSI_TX_CTRL_DMAC_ERR_CNT"},
+
+	{true,	"NCSI_TX_CTRL_SMAC_ERR_CNT"},
+	{true,	"NCSI_TX_CTRL_PKT_CNT"},
+	{true,	"NCSI_TX_PT_DMAC_ERR_CNT"},
+	{true,	"NCSI_TX_PT_SMAC_ERR_CNT"},
+	{true,	"NCSI_TX_PT_PKT_CNT"},
+	{true,	"NCSI_TX_PT_PKT_TRUNC_CNT"},
+
+	{true,	"NCSI_TX_PT_PKT_ERR_CNT"},
+	{true,	"NCSI_TX_CTRL_PKT_ERR_CNT"},
+	{true,	"NCSI_RX_CTRL_PKT_TRUNC_CNT"},
+	{true,	"NCSI_RX_CTRL_PKT_CFLIT_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"NCSI_MAC_RX_OCTETS_OK"},
+	{true,	"NCSI_MAC_RX_OCTETS_BAD"},
+	{true,	"NCSI_MAC_RX_UC_PKTS"},
+	{true,	"NCSI_MAC_RX_MC_PKTS"},
+	{true,	"NCSI_MAC_RX_BC_PKTS"},
+	{true,	"NCSI_MAC_RX_PKTS_64OCTETS"},
+
+	{true,	"NCSI_MAC_RX_PKTS_65TO127OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_128TO255OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_255TO511OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_512TO1023OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_1024TO1518OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_1519TOMAXOCTETS"},
+
+	{true,	"NCSI_MAC_RX_FCS_ERRORS"},
+	{true,	"NCSI_MAC_RX_LONG_ERRORS"},
+	{true,	"NCSI_MAC_RX_JABBER_ERRORS"},
+	{true,	"NCSI_MAC_RX_RUNT_ERR_CNT"},
+	{true,	"NCSI_MAC_RX_SHORT_ERR_CNT"},
+	{true,	"NCSI_MAC_RX_FILT_PKT_CNT"},
+
+	{true,	"NCSI_MAC_RX_OCTETS_TOTAL_FILT"},
+	{true,	"NCSI_MAC_TX_OCTETS_OK"},
+	{true,	"NCSI_MAC_TX_OCTETS_BAD"},
+	{true,	"NCSI_MAC_TX_UC_PKTS"},
+	{true,	"NCSI_MAC_TX_MC_PKTS"},
+	{true,	"NCSI_MAC_TX_BC_PKTS"},
+
+	{true,	"NCSI_MAC_TX_PKTS_64OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_65TO127OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_128TO255OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_256TO511OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_512TO1023OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_1024TO1518OCTETS"},
+
+	{true,	"NCSI_MAC_TX_PKTS_1519TOMAXOCTETS"},
+	{true,	"NCSI_MAC_TX_UNDERRUN"},
+	{true,	"NCSI_MAC_TX_CRC_ERROR"},
+	{true,	"NCSI_MAC_TX_PAUSE_FRAMES"},
+	{true,	"NCSI_MAC_RX_PAD_PKTS"},
+	{true,	"NCSI_MAC_RX_PAUSE_FRAMES"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_rtc_reg[] = {
+	{false, "Reserved"},
+	{true,	"LGE_IGU_AFIFO_DFX_0"},
+	{true,	"LGE_IGU_AFIFO_DFX_1"},
+	{true,	"LGE_IGU_AFIFO_DFX_2"},
+	{true,	"LGE_IGU_AFIFO_DFX_3"},
+	{true,	"LGE_IGU_AFIFO_DFX_4"},
+
+	{true,	"LGE_IGU_AFIFO_DFX_5"},
+	{true,	"LGE_IGU_AFIFO_DFX_6"},
+	{true,	"LGE_IGU_AFIFO_DFX_7"},
+	{true,	"LGE_EGU_AFIFO_DFX_0"},
+	{true,	"LGE_EGU_AFIFO_DFX_1"},
+	{true,	"LGE_EGU_AFIFO_DFX_2"},
+
+	{true,	"LGE_EGU_AFIFO_DFX_3"},
+	{true,	"LGE_EGU_AFIFO_DFX_4"},
+	{true,	"LGE_EGU_AFIFO_DFX_5"},
+	{true,	"LGE_EGU_AFIFO_DFX_6"},
+	{true,	"LGE_EGU_AFIFO_DFX_7"},
+	{true,	"CGE_IGU_AFIFO_DFX_0"},
+
+	{true,	"CGE_IGU_AFIFO_DFX_1"},
+	{true,	"CGE_EGU_AFIFO_DFX_0"},
+	{true,	"CGE_EGU_AFIFO_DFX_1"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_ppp_reg[] = {
+	{false, "Reserved"},
+	{true,	"DROP_FROM_PRT_PKT_CNT"},
+	{true,	"DROP_FROM_HOST_PKT_CNT"},
+	{true,	"DROP_TX_VLAN_PROC_CNT"},
+	{true,	"DROP_MNG_CNT"},
+	{true,	"DROP_FD_CNT"},
+
+	{true,	"DROP_NO_DST_CNT"},
+	{true,	"DROP_MC_MBID_FULL_CNT"},
+	{true,	"DROP_SC_FILTERED"},
+	{true,	"PPP_MC_DROP_PKT_CNT"},
+	{true,	"DROP_PT_CNT"},
+	{true,	"DROP_MAC_ANTI_SPOOF_CNT"},
+
+	{true,	"DROP_IG_VFV_CNT"},
+	{true,	"DROP_IG_PRTV_CNT"},
+	{true,	"DROP_CNM_PFC_PAUSE_CNT"},
+	{true,	"DROP_TORUS_TC_CNT"},
+	{true,	"DROP_TORUS_LPBK_CNT"},
+	{true,	"PPP_HFS_STS"},
+
+	{true,	"PPP_MC_RSLT_STS"},
+	{true,	"PPP_P3U_STS"},
+	{true,	"PPP_RSLT_DESCR_STS"},
+	{true,	"PPP_UMV_STS_0"},
+	{true,	"PPP_UMV_STS_1"},
+	{true,	"PPP_VFV_STS"},
+
+	{true,	"PPP_GRO_KEY_CNT"},
+	{true,	"PPP_GRO_INFO_CNT"},
+	{true,	"PPP_GRO_DROP_CNT"},
+	{true,	"PPP_GRO_OUT_CNT"},
+	{true,	"PPP_GRO_KEY_MATCH_DATA_CNT"},
+	{true,	"PPP_GRO_KEY_MATCH_TCAM_CNT"},
+
+	{true,	"PPP_GRO_INFO_MATCH_CNT"},
+	{true,	"PPP_GRO_FREE_ENTRY_CNT"},
+	{true,	"PPP_GRO_INNER_DFX_SIGNAL"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"GET_RX_PKT_CNT_L"},
+	{true,	"GET_RX_PKT_CNT_H"},
+	{true,	"GET_TX_PKT_CNT_L"},
+	{true,	"GET_TX_PKT_CNT_H"},
+	{true,	"SEND_UC_PRT2HOST_PKT_CNT_L"},
+	{true,	"SEND_UC_PRT2HOST_PKT_CNT_H"},
+
+	{true,	"SEND_UC_PRT2PRT_PKT_CNT_L"},
+	{true,	"SEND_UC_PRT2PRT_PKT_CNT_H"},
+	{true,	"SEND_UC_HOST2HOST_PKT_CNT_L"},
+	{true,	"SEND_UC_HOST2HOST_PKT_CNT_H"},
+	{true,	"SEND_UC_HOST2PRT_PKT_CNT_L"},
+	{true,	"SEND_UC_HOST2PRT_PKT_CNT_H"},
+
+	{true,	"SEND_MC_FROM_PRT_CNT_L"},
+	{true,	"SEND_MC_FROM_PRT_CNT_H"},
+	{true,	"SEND_MC_FROM_HOST_CNT_L"},
+	{true,	"SEND_MC_FROM_HOST_CNT_H"},
+	{true,	"SSU_MC_RD_CNT_L"},
+	{true,	"SSU_MC_RD_CNT_H"},
+
+	{true,	"SSU_MC_DROP_CNT_L"},
+	{true,	"SSU_MC_DROP_CNT_H"},
+	{true,	"SSU_MC_RD_PKT_CNT_L"},
+	{true,	"SSU_MC_RD_PKT_CNT_H"},
+	{true,	"PPP_MC_2HOST_PKT_CNT_L"},
+	{true,	"PPP_MC_2HOST_PKT_CNT_H"},
+
+	{true,	"PPP_MC_2PRT_PKT_CNT_L"},
+	{true,	"PPP_MC_2PRT_PKT_CNT_H"},
+	{true,	"NTSNOS_PKT_CNT_L"},
+	{true,	"NTSNOS_PKT_CNT_H"},
+	{true,	"NTUP_PKT_CNT_L"},
+	{true,	"NTUP_PKT_CNT_H"},
+
+	{true,	"NTLCL_PKT_CNT_L"},
+	{true,	"NTLCL_PKT_CNT_H"},
+	{true,	"NTTGT_PKT_CNT_L"},
+	{true,	"NTTGT_PKT_CNT_H"},
+	{true,	"RTNS_PKT_CNT_L"},
+	{true,	"RTNS_PKT_CNT_H"},
+
+	{true,	"RTLPBK_PKT_CNT_L"},
+	{true,	"RTLPBK_PKT_CNT_H"},
+	{true,	"NR_PKT_CNT_L"},
+	{true,	"NR_PKT_CNT_H"},
+	{true,	"RR_PKT_CNT_L"},
+	{true,	"RR_PKT_CNT_H"},
+
+	{true,	"MNG_TBL_HIT_CNT_L"},
+	{true,	"MNG_TBL_HIT_CNT_H"},
+	{true,	"FD_TBL_HIT_CNT_L"},
+	{true,	"FD_TBL_HIT_CNT_H"},
+	{true,	"FD_LKUP_CNT_L"},
+	{true,	"FD_LKUP_CNT_H"},
+
+	{true,	"BC_HIT_CNT_L"},
+	{true,	"BC_HIT_CNT_H"},
+	{true,	"UM_TBL_UC_HIT_CNT_L"},
+	{true,	"UM_TBL_UC_HIT_CNT_H"},
+	{true,	"UM_TBL_MC_HIT_CNT_L"},
+	{true,	"UM_TBL_MC_HIT_CNT_H"},
+
+	{true,	"UM_TBL_VMDQ1_HIT_CNT_L"},
+	{true,	"UM_TBL_VMDQ1_HIT_CNT_H"},
+	{true,	"MTA_TBL_HIT_CNT_L"},
+	{true,	"MTA_TBL_HIT_CNT_H"},
+	{true,	"FWD_BONDING_HIT_CNT_L"},
+	{true,	"FWD_BONDING_HIT_CNT_H"},
+
+	{true,	"PROMIS_TBL_HIT_CNT_L"},
+	{true,	"PROMIS_TBL_HIT_CNT_H"},
+	{true,	"GET_TUNL_PKT_CNT_L"},
+	{true,	"GET_TUNL_PKT_CNT_H"},
+	{true,	"GET_BMC_PKT_CNT_L"},
+	{true,	"GET_BMC_PKT_CNT_H"},
+
+	{true,	"SEND_UC_PRT2BMC_PKT_CNT_L"},
+	{true,	"SEND_UC_PRT2BMC_PKT_CNT_H"},
+	{true,	"SEND_UC_HOST2BMC_PKT_CNT_L"},
+	{true,	"SEND_UC_HOST2BMC_PKT_CNT_H"},
+	{true,	"SEND_UC_BMC2HOST_PKT_CNT_L"},
+	{true,	"SEND_UC_BMC2HOST_PKT_CNT_H"},
+
+	{true,	"SEND_UC_BMC2PRT_PKT_CNT_L"},
+	{true,	"SEND_UC_BMC2PRT_PKT_CNT_H"},
+	{true,	"PPP_MC_2BMC_PKT_CNT_L"},
+	{true,	"PPP_MC_2BMC_PKT_CNT_H"},
+	{true,	"VLAN_MIRR_CNT_L"},
+	{true,	"VLAN_MIRR_CNT_H"},
+
+	{true,	"IG_MIRR_CNT_L"},
+	{true,	"IG_MIRR_CNT_H"},
+	{true,	"EG_MIRR_CNT_L"},
+	{true,	"EG_MIRR_CNT_H"},
+	{true,	"RX_DEFAULT_HOST_HIT_CNT_L"},
+	{true,	"RX_DEFAULT_HOST_HIT_CNT_H"},
+
+	{true,	"LAN_PAIR_CNT_L"},
+	{true,	"LAN_PAIR_CNT_H"},
+	{true,	"UM_TBL_MC_HIT_PKT_CNT_L"},
+	{true,	"UM_TBL_MC_HIT_PKT_CNT_H"},
+	{true,	"MTA_TBL_HIT_PKT_CNT_L"},
+	{true,	"MTA_TBL_HIT_PKT_CNT_H"},
+
+	{true,	"PROMIS_TBL_HIT_PKT_CNT_L"},
+	{true,	"PROMIS_TBL_HIT_PKT_CNT_H"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_rcb_reg[] = {
+	{false, "Reserved"},
+	{true,	"FSM_DFX_ST0"},
+	{true,	"FSM_DFX_ST1"},
+	{true,	"FSM_DFX_ST2"},
+	{true,	"FIFO_DFX_ST0"},
+	{true,	"FIFO_DFX_ST1"},
+
+	{true,	"FIFO_DFX_ST2"},
+	{true,	"FIFO_DFX_ST3"},
+	{true,	"FIFO_DFX_ST4"},
+	{true,	"FIFO_DFX_ST5"},
+	{true,	"FIFO_DFX_ST6"},
+	{true,	"FIFO_DFX_ST7"},
+
+	{true,	"FIFO_DFX_ST8"},
+	{true,	"FIFO_DFX_ST9"},
+	{true,	"FIFO_DFX_ST10"},
+	{true,	"FIFO_DFX_ST11"},
+	{true,	"Q_CREDIT_VLD_0"},
+	{true,	"Q_CREDIT_VLD_1"},
+
+	{true,	"Q_CREDIT_VLD_2"},
+	{true,	"Q_CREDIT_VLD_3"},
+	{true,	"Q_CREDIT_VLD_4"},
+	{true,	"Q_CREDIT_VLD_5"},
+	{true,	"Q_CREDIT_VLD_6"},
+	{true,	"Q_CREDIT_VLD_7"},
+
+	{true,	"Q_CREDIT_VLD_8"},
+	{true,	"Q_CREDIT_VLD_9"},
+	{true,	"Q_CREDIT_VLD_10"},
+	{true,	"Q_CREDIT_VLD_11"},
+	{true,	"Q_CREDIT_VLD_12"},
+	{true,	"Q_CREDIT_VLD_13"},
+
+	{true,	"Q_CREDIT_VLD_14"},
+	{true,	"Q_CREDIT_VLD_15"},
+	{true,	"Q_CREDIT_VLD_16"},
+	{true,	"Q_CREDIT_VLD_17"},
+	{true,	"Q_CREDIT_VLD_18"},
+	{true,	"Q_CREDIT_VLD_19"},
+
+	{true,	"Q_CREDIT_VLD_20"},
+	{true,	"Q_CREDIT_VLD_21"},
+	{true,	"Q_CREDIT_VLD_22"},
+	{true,	"Q_CREDIT_VLD_23"},
+	{true,	"Q_CREDIT_VLD_24"},
+	{true,	"Q_CREDIT_VLD_25"},
+
+	{true,	"Q_CREDIT_VLD_26"},
+	{true,	"Q_CREDIT_VLD_27"},
+	{true,	"Q_CREDIT_VLD_28"},
+	{true,	"Q_CREDIT_VLD_29"},
+	{true,	"Q_CREDIT_VLD_30"},
+	{true,	"Q_CREDIT_VLD_31"},
+
+	{true,	"GRO_BD_SERR_CNT"},
+	{true,	"GRO_CONTEXT_SERR_CNT"},
+	{true,	"RX_STASH_CFG_SERR_CNT"},
+	{true,	"AXI_RD_FBD_SERR_CNT"},
+	{true,	"GRO_BD_MERR_CNT"},
+	{true,	"GRO_CONTEXT_MERR_CNT"},
+
+	{true,	"RX_STASH_CFG_MERR_CNT"},
+	{true,	"AXI_RD_FBD_MERR_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_tqp_reg[] = {
+	{true, "q_num"},
+	{true, "RCB_CFG_RX_RING_TAIL"},
+	{true, "RCB_CFG_RX_RING_HEAD"},
+	{true, "RCB_CFG_RX_RING_FBDNUM"},
+	{true, "RCB_CFG_RX_RING_OFFSET"},
+	{true, "RCB_CFG_RX_RING_FBDOFFSET"},
+
+	{true, "RCB_CFG_RX_RING_PKTNUM_RECORD"},
+	{true, "RCB_CFG_TX_RING_TAIL"},
+	{true, "RCB_CFG_TX_RING_HEAD"},
+	{true, "RCB_CFG_TX_RING_FBDNUM"},
+	{true, "RCB_CFG_TX_RING_OFFSET"},
+	{true, "RCB_CFG_TX_RING_EBDNUM"},
+};
+
 #endif
-- 
cgit v1.2.3


From c0ebebb9ccc1363e117b52189e93d6ec646b33df Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Sat, 15 Dec 2018 15:31:56 +0000
Subject: net: hns3: Add "dcb register" status information query function

This patch prints dcb register status  information by module.

debugfs command:
root@(none)# echo dump reg dcb > cmd
 roce_qset_mask: 0x0
 nic_qs_mask: 0x0
 qs_shaping_pass: 0x0
 qs_bp_sts: 0x0
 pri_mask: 0x0
 pri_cshaping_pass: 0x0
 pri_pshaping_pass: 0x0
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |   7 ++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |   9 ++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 102 +++++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h |  16 ++++
 4 files changed, 134 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index e6268e03d221..005b7e77c3f3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -226,6 +226,13 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 		" [rtc] [ppp] [rcb] [tqp <q_num>]]\n",
 		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
 	dev_info(&h->pdev->dev, "%s", printf_buf);
+
+	memset(printf_buf, 0, HNS3_DBG_BUF_LEN);
+	strncat(printf_buf, "dump reg dcb [port_id] [pri_id] [pg_id]",
+		HNS3_DBG_BUF_LEN - 1);
+	strncat(printf_buf + strlen(printf_buf), " [rq_id] [nq_id] [qset_id]\n",
+		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
+	dev_info(&h->pdev->dev, "%s", printf_buf);
 }
 
 static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 2b281d909f51..c3758f7cb9a0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -140,6 +140,15 @@ enum hclge_opcode_type {
 	HCLGE_OPC_TM_QS_SCH_MODE_CFG    = 0x0814,
 	HCLGE_OPC_TM_BP_TO_QSET_MAPPING = 0x0815,
 	HCLGE_OPC_ETS_TC_WEIGHT		= 0x0843,
+	HCLGE_OPC_QSET_DFX_STS		= 0x0844,
+	HCLGE_OPC_PRI_DFX_STS		= 0x0845,
+	HCLGE_OPC_PG_DFX_STS		= 0x0846,
+	HCLGE_OPC_PORT_DFX_STS		= 0x0847,
+	HCLGE_OPC_SCH_NQ_CNT		= 0x0848,
+	HCLGE_OPC_SCH_RQ_CNT		= 0x0849,
+	HCLGE_OPC_TM_INTERNAL_STS	= 0x0850,
+	HCLGE_OPC_TM_INTERNAL_CNT	= 0x0851,
+	HCLGE_OPC_TM_INTERNAL_STS_1	= 0x0852,
 
 	/* Packet buffer allocate commands */
 	HCLGE_OPC_TX_BUFF_ALLOC		= 0x0901,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 7d18ed8e17f0..2d43d347ddfd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -107,6 +107,106 @@ static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
 	kfree(desc_src);
 }
 
+static void hclge_dbg_dump_dcb(struct hclge_dev *hdev, char *cmd_buf)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_dbg_bitmap_cmd *bitmap;
+	int rq_id, pri_id, qset_id;
+	int port_id, nq_id, pg_id;
+	struct hclge_desc desc[2];
+
+	int cnt, ret;
+
+	cnt = sscanf(cmd_buf, "%i %i %i %i %i %i",
+		     &port_id, &pri_id, &pg_id, &rq_id, &nq_id, &qset_id);
+	if (cnt != 6) {
+		dev_err(&hdev->pdev->dev,
+			"dump dcb: bad command parameter, cnt=%d\n", cnt);
+		return;
+	}
+
+	ret = hclge_dbg_cmd_send(hdev, desc, qset_id, 1,
+				 HCLGE_OPC_QSET_DFX_STS);
+	if (ret)
+		return;
+
+	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
+	dev_info(dev, "roce_qset_mask: 0x%x\n", bitmap->bit0);
+	dev_info(dev, "nic_qs_mask: 0x%x\n", bitmap->bit1);
+	dev_info(dev, "qs_shaping_pass: 0x%x\n", bitmap->bit2);
+	dev_info(dev, "qs_bp_sts: 0x%x\n", bitmap->bit3);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, pri_id, 1, HCLGE_OPC_PRI_DFX_STS);
+	if (ret)
+		return;
+
+	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
+	dev_info(dev, "pri_mask: 0x%x\n", bitmap->bit0);
+	dev_info(dev, "pri_cshaping_pass: 0x%x\n", bitmap->bit1);
+	dev_info(dev, "pri_pshaping_pass: 0x%x\n", bitmap->bit2);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, pg_id, 1, HCLGE_OPC_PG_DFX_STS);
+	if (ret)
+		return;
+
+	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
+	dev_info(dev, "pg_mask: 0x%x\n", bitmap->bit0);
+	dev_info(dev, "pg_cshaping_pass: 0x%x\n", bitmap->bit1);
+	dev_info(dev, "pg_pshaping_pass: 0x%x\n", bitmap->bit2);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1,
+				 HCLGE_OPC_PORT_DFX_STS);
+	if (ret)
+		return;
+
+	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
+	dev_info(dev, "port_mask: 0x%x\n", bitmap->bit0);
+	dev_info(dev, "port_shaping_pass: 0x%x\n", bitmap->bit1);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, nq_id, 1, HCLGE_OPC_SCH_NQ_CNT);
+	if (ret)
+		return;
+
+	dev_info(dev, "sch_nq_cnt: 0x%x\n", desc[0].data[1]);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, nq_id, 1, HCLGE_OPC_SCH_RQ_CNT);
+	if (ret)
+		return;
+
+	dev_info(dev, "sch_rq_cnt: 0x%x\n", desc[0].data[1]);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, 0, 2, HCLGE_OPC_TM_INTERNAL_STS);
+	if (ret)
+		return;
+
+	dev_info(dev, "pri_bp: 0x%x\n", desc[0].data[1]);
+	dev_info(dev, "fifo_dfx_info: 0x%x\n", desc[0].data[2]);
+	dev_info(dev, "sch_roce_fifo_afull_gap: 0x%x\n", desc[0].data[3]);
+	dev_info(dev, "tx_private_waterline: 0x%x\n", desc[0].data[4]);
+	dev_info(dev, "tm_bypass_en: 0x%x\n", desc[0].data[5]);
+	dev_info(dev, "SSU_TM_BYPASS_EN: 0x%x\n", desc[1].data[0]);
+	dev_info(dev, "SSU_RESERVE_CFG: 0x%x\n", desc[1].data[1]);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1,
+				 HCLGE_OPC_TM_INTERNAL_CNT);
+	if (ret)
+		return;
+
+	dev_info(dev, "SCH_NIC_NUM: 0x%x\n", desc[0].data[1]);
+	dev_info(dev, "SCH_ROCE_NUM: 0x%x\n", desc[0].data[2]);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1,
+				 HCLGE_OPC_TM_INTERNAL_STS_1);
+	if (ret)
+		return;
+
+	dev_info(dev, "TC_MAP_SEL: 0x%x\n", desc[0].data[1]);
+	dev_info(dev, "IGU_PFC_PRI_EN: 0x%x\n", desc[0].data[2]);
+	dev_info(dev, "MAC_PFC_PRI_EN: 0x%x\n", desc[0].data[3]);
+	dev_info(dev, "IGU_PRI_MAP_TC_CFG: 0x%x\n", desc[0].data[4]);
+	dev_info(dev, "IGU_TX_PRI_MAP_TC_CFG: 0x%x\n", desc[0].data[5]);
+}
+
 static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, char *cmd_buf)
 {
 	int msg_num;
@@ -195,6 +295,8 @@ static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, char *cmd_buf)
 					  &cmd_buf[13], msg_num,
 					  HCLGE_DBG_DFX_TQP_OFFSET,
 					  HCLGE_OPC_DFX_TQP_REG);
+	} else if (strncmp(&cmd_buf[9], "dcb", 3) == 0) {
+		hclge_dbg_dump_dcb(hdev, &cmd_buf[13]);
 	} else {
 		dev_info(&hdev->pdev->dev, "unknown command\n");
 		return;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
index 7a6fbfd38527..d055fda41775 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
@@ -47,6 +47,22 @@ struct hclge_qos_pri_map_cmd {
 	   rev	    : 4;
 };
 
+struct hclge_dbg_bitmap_cmd {
+	union {
+		u8 bitmap;
+		struct {
+			u8 bit0 : 1,
+			   bit1 : 1,
+			   bit2 : 1,
+			   bit3 : 1,
+			   bit4 : 1,
+			   bit5 : 1,
+			   bit6 : 1,
+			   bit7 : 1;
+		};
+	};
+};
+
 struct hclge_dbg_dfx_message {
 	int flag;
 	char message[60];
-- 
cgit v1.2.3


From 0c29d1912b81a0d8ab7eb46ce7036a8c0fb073e3 Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Sat, 15 Dec 2018 15:31:57 +0000
Subject: net: hns3: Add "queue map" information query function

This patch prints queue map information.

debugfs command:
echo dump queue map > cmd

Sample Command:
root@(none)# echo queue map > cmd
 local queue id | global queue id | vector id
          0              32             769
          1              33             770
          2              34             771
          3              35             772
          4              36             773
          5              37             774
          6              38             775
          7              39             776
          8              40             777
          9              41             778
         10              42             779
         11              43             780
         12              44             781
         13              45             782
         14              46             783
         15              47             784
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h    |  1 +
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  1 +
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 33 ++++++++++++++++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    |  4 +--
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  1 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 20 +++++++++++++
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 18 ++++++++++++
 7 files changed, 76 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index 4d9cf39da48c..691d12174902 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -39,6 +39,7 @@ enum HCLGE_MBX_OPCODE {
 	HCLGE_MBX_KEEP_ALIVE,		/* (VF -> PF) send keep alive cmd */
 	HCLGE_MBX_SET_ALIVE,		/* (VF -> PF) set alive state */
 	HCLGE_MBX_SET_MTU,		/* (VF -> PF) set mtu */
+	HCLGE_MBX_GET_QID_IN_PF,	/* (VF -> PF) get queue id in pf */
 };
 
 /* below are per-VF mac-vlan subcodes */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 294e725c7c44..845d43d3a920 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -460,6 +460,7 @@ struct hnae3_ae_ops {
 	bool (*ae_dev_resetting)(struct hnae3_handle *handle);
 	unsigned long (*ae_dev_reset_cnt)(struct hnae3_handle *handle);
 	int (*set_gro_en)(struct hnae3_handle *handle, int enable);
+	u16 (*get_global_queue_id)(struct hnae3_handle *handle, u16 queue_id);
 };
 
 struct hnae3_dcb_ops {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 005b7e77c3f3..76c74b4b9777 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -125,6 +125,36 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h, char *cmd_buf)
 	return 0;
 }
 
+static int hns3_dbg_queue_map(struct hnae3_handle *h)
+{
+	struct hns3_nic_priv *priv = h->priv;
+	struct hns3_nic_ring_data *ring_data;
+	int i;
+
+	if (!h->ae_algo->ops->get_global_queue_id)
+		return -EOPNOTSUPP;
+
+	dev_info(&h->pdev->dev, "map info for queue id and vector id\n");
+	dev_info(&h->pdev->dev,
+		 "local queue id | global queue id | vector id\n");
+	for (i = 0; i < h->kinfo.num_tqps; i++) {
+		u16 global_qid;
+
+		global_qid = h->ae_algo->ops->get_global_queue_id(h, i);
+		ring_data = &priv->ring_data[i];
+		if (!ring_data || !ring_data->ring ||
+		    !ring_data->ring->tqp_vector)
+			continue;
+
+		dev_info(&h->pdev->dev,
+			 "      %4d            %4d            %4d\n",
+			 i, global_qid,
+			 ring_data->ring->tqp_vector->vector_irq);
+	}
+
+	return 0;
+}
+
 static int hns3_dbg_bd_info(struct hnae3_handle *h, char *cmd_buf)
 {
 	struct hns3_nic_priv *priv = h->priv;
@@ -207,6 +237,7 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 
 	dev_info(&h->pdev->dev, "available commands\n");
 	dev_info(&h->pdev->dev, "queue info [number]\n");
+	dev_info(&h->pdev->dev, "queue map\n");
 	dev_info(&h->pdev->dev, "bd info [q_num] <bd index>\n");
 	dev_info(&h->pdev->dev, "dump fd tcam\n");
 	dev_info(&h->pdev->dev, "dump tc\n");
@@ -303,6 +334,8 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
 		hns3_dbg_help(handle);
 	else if (strncmp(cmd_buf, "queue info", 10) == 0)
 		ret = hns3_dbg_queue_info(handle, cmd_buf);
+	else if (strncmp(cmd_buf, "queue map", 9) == 0)
+		ret = hns3_dbg_queue_map(handle);
 	else if (strncmp(cmd_buf, "bd info", 7) == 0)
 		ret = hns3_dbg_bd_info(handle, cmd_buf);
 	else if (handle->ae_algo->ops->dbg_run_cmd)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 22380202ba83..3fe08cf477f9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6602,8 +6602,7 @@ static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id)
 	return hnae3_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B);
 }
 
-static u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle,
-					  u16 queue_id)
+u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id)
 {
 	struct hnae3_queue *queue;
 	struct hclge_tqp *tqp;
@@ -7975,6 +7974,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.ae_dev_resetting = hclge_ae_dev_resetting,
 	.ae_dev_reset_cnt = hclge_ae_dev_reset_cnt,
 	.set_gro_en = hclge_gro_en,
+	.get_global_queue_id = hclge_covert_handle_qid_global,
 };
 
 static struct hnae3_ae_algo ae_algo = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 106fce172563..9571e228ab42 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -874,4 +874,5 @@ int hclge_vport_start(struct hclge_vport *vport);
 void hclge_vport_stop(struct hclge_vport *vport);
 int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu);
 int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf);
+u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index e16a730a5f54..a1de451a85df 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -413,6 +413,19 @@ static int hclge_set_vf_mtu(struct hclge_vport *vport,
 	return hclge_gen_resp_to_vf(vport, mbx_req, ret, NULL, 0);
 }
 
+static int hclge_get_queue_id_in_pf(struct hclge_vport *vport,
+				    struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+	u16 queue_id, qid_in_pf;
+	u8 resp_data[2];
+
+	memcpy(&queue_id, &mbx_req->msg[2], sizeof(queue_id));
+	qid_in_pf = hclge_covert_handle_qid_global(&vport->nic, queue_id);
+	memcpy(resp_data, &qid_in_pf, sizeof(qid_in_pf));
+
+	return hclge_gen_resp_to_vf(vport, mbx_req, 0, resp_data, 2);
+}
+
 static bool hclge_cmd_crq_empty(struct hclge_hw *hw)
 {
 	u32 tail = hclge_read_dev(hw, HCLGE_NIC_CRQ_TAIL_REG);
@@ -533,6 +546,13 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 				dev_err(&hdev->pdev->dev,
 					"VF fail(%d) to set mtu\n", ret);
 			break;
+		case HCLGE_MBX_GET_QID_IN_PF:
+			ret = hclge_get_queue_id_in_pf(vport, req);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"PF failed(%d) to get qid for VF\n",
+					ret);
+			break;
 		default:
 			dev_err(&hdev->pdev->dev,
 				"un-supported mailbox message, code = %d\n",
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 417e078eac62..75327dcda3b0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -256,6 +256,23 @@ static int hclgevf_get_queue_info(struct hclgevf_dev *hdev)
 	return 0;
 }
 
+static u16 hclgevf_get_qid_global(struct hnae3_handle *handle, u16 queue_id)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	u8 msg_data[2], resp_data[2];
+	u16 qid_in_pf = 0;
+	int ret;
+
+	memcpy(&msg_data[0], &queue_id, sizeof(queue_id));
+
+	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_QID_IN_PF, 0, msg_data,
+				   2, true, resp_data, 2);
+	if (!ret)
+		qid_in_pf = *(u16 *)resp_data;
+
+	return qid_in_pf;
+}
+
 static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev)
 {
 	struct hclgevf_tqp *tqp;
@@ -2642,6 +2659,7 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.ae_dev_reset_cnt = hclgevf_ae_dev_reset_cnt,
 	.set_gro_en = hclgevf_gro_en,
 	.set_mtu = hclgevf_set_mtu,
+	.get_global_queue_id = hclgevf_get_qid_global,
 };
 
 static struct hnae3_ae_algo ae_algovf = {
-- 
cgit v1.2.3


From 82e00b86a5b60d21e85564ec7dccaddc37ec2b00 Mon Sep 17 00:00:00 2001
From: liuzhongzhu <liuzhongzhu@huawei.com>
Date: Sat, 15 Dec 2018 15:31:58 +0000
Subject: net: hns3: Add "tm map" status information query function

This patch prints dcb register status  information by module.

debugfs command:
root@(none)# echo dump tm map 100 > cmd
queue_id | qset_id | pri_id | tc_id
0100     | 0065    | 08     | 00
root@(none)#

Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |  1 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |  1 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 84 ++++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h  |  7 ++
 4 files changed, 93 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 76c74b4b9777..0de543faa5b1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -241,6 +241,7 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "bd info [q_num] <bd index>\n");
 	dev_info(&h->pdev->dev, "dump fd tcam\n");
 	dev_info(&h->pdev->dev, "dump tc\n");
+	dev_info(&h->pdev->dev, "dump tm map [q_num]\n");
 	dev_info(&h->pdev->dev, "dump tm\n");
 	dev_info(&h->pdev->dev, "dump qos pause cfg\n");
 	dev_info(&h->pdev->dev, "dump qos pri map\n");
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index c3758f7cb9a0..47717800e0b5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -165,6 +165,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_CFG_TX_QUEUE		= 0x0B01,
 	HCLGE_OPC_QUERY_TX_POINTER	= 0x0B02,
 	HCLGE_OPC_QUERY_TX_STATUS	= 0x0B03,
+	HCLGE_OPC_TQP_TX_QUEUE_TC	= 0x0B04,
 	HCLGE_OPC_CFG_RX_QUEUE		= 0x0B11,
 	HCLGE_OPC_QUERY_RX_POINTER	= 0x0B12,
 	HCLGE_OPC_QUERY_RX_STATUS	= 0x0B13,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 2d43d347ddfd..26d80504c730 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -537,6 +537,88 @@ err_tm_cmd_send:
 		cmd, ret);
 }
 
+static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev, char *cmd_buf)
+{
+	struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd;
+	struct hclge_nq_to_qs_link_cmd *nq_to_qs_map;
+	struct hclge_qs_to_pri_link_cmd *map;
+	struct hclge_tqp_tx_queue_tc_cmd *tc;
+	enum hclge_opcode_type cmd;
+	struct hclge_desc desc;
+	int queue_id, group_id;
+	u32 qset_maping[32];
+	int tc_id, qset_id;
+	int pri_id, ret;
+	u32 i;
+
+	ret = kstrtouint(&cmd_buf[12], 10, &queue_id);
+	queue_id = (ret != 0) ? 0 : queue_id;
+
+	cmd = HCLGE_OPC_TM_NQ_TO_QS_LINK;
+	nq_to_qs_map = (struct hclge_nq_to_qs_link_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	nq_to_qs_map->nq_id = cpu_to_le16(queue_id);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_map_cmd_send;
+	qset_id = nq_to_qs_map->qset_id & 0x3FF;
+
+	cmd = HCLGE_OPC_TM_QS_TO_PRI_LINK;
+	map = (struct hclge_qs_to_pri_link_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	map->qs_id = cpu_to_le16(qset_id);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_map_cmd_send;
+	pri_id = map->priority;
+
+	cmd = HCLGE_OPC_TQP_TX_QUEUE_TC;
+	tc = (struct hclge_tqp_tx_queue_tc_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	tc->queue_id = cpu_to_le16(queue_id);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_map_cmd_send;
+	tc_id = tc->tc_id & 0x7;
+
+	dev_info(&hdev->pdev->dev, "queue_id | qset_id | pri_id | tc_id\n");
+	dev_info(&hdev->pdev->dev, "%04d     | %04d    | %02d     | %02d\n",
+		 queue_id, qset_id, pri_id, tc_id);
+
+	cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING;
+	bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data;
+	for (group_id = 0; group_id < 32; group_id++) {
+		hclge_cmd_setup_basic_desc(&desc, cmd, true);
+		bp_to_qs_map_cmd->tc_id = tc_id;
+		bp_to_qs_map_cmd->qs_group_id = group_id;
+		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+		if (ret)
+			goto err_tm_map_cmd_send;
+
+		qset_maping[group_id] = bp_to_qs_map_cmd->qs_bit_map;
+	}
+
+	dev_info(&hdev->pdev->dev, "index | tm bp qset maping:\n");
+
+	i = 0;
+	for (group_id = 0; group_id < 4; group_id++) {
+		dev_info(&hdev->pdev->dev,
+			 "%04d  | %08x:%08x:%08x:%08x:%08x:%08x:%08x:%08x\n",
+			 group_id * 256, qset_maping[(u32)(i + 7)],
+			 qset_maping[(u32)(i + 6)], qset_maping[(u32)(i + 5)],
+			 qset_maping[(u32)(i + 4)], qset_maping[(u32)(i + 3)],
+			 qset_maping[(u32)(i + 2)], qset_maping[(u32)(i + 1)],
+			 qset_maping[i]);
+		i += 8;
+	}
+
+	return;
+
+err_tm_map_cmd_send:
+	dev_err(&hdev->pdev->dev, "dump tqp map fail(0x%x), status is %d\n",
+		cmd, ret);
+}
+
 static void hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev)
 {
 	struct hclge_cfg_pause_param_cmd *pause_param;
@@ -828,6 +910,8 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
 		hclge_dbg_fd_tcam(hdev);
 	} else if (strncmp(cmd_buf, "dump tc", 7) == 0) {
 		hclge_dbg_dump_tc(hdev);
+	} else if (strncmp(cmd_buf, "dump tm map", 11) == 0) {
+		hclge_dbg_dump_tm_map(hdev, cmd_buf);
 	} else if (strncmp(cmd_buf, "dump tm", 7) == 0) {
 		hclge_dbg_dump_tm(hdev);
 	} else if (strncmp(cmd_buf, "dump qos pause cfg", 18) == 0) {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 9c6192c46aa6..b6496a439304 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -40,6 +40,13 @@ struct hclge_nq_to_qs_link_cmd {
 	__le16 qset_id;
 };
 
+struct hclge_tqp_tx_queue_tc_cmd {
+	__le16 queue_id;
+	__le16 rsvd;
+	u8 tc_id;
+	u8 rev[3];
+};
+
 struct hclge_pg_weight_cmd {
 	u8 pg_id;
 	u8 dwrr;
-- 
cgit v1.2.3


From 70f98d7c7d51402e7b40c9ec0299bd46b7890da9 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Sat, 15 Dec 2018 02:19:53 -0500
Subject: ipconfig: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipconfig.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 55757764c381..208a5b4419c6 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1361,18 +1361,7 @@ static int ntp_servers_seq_show(struct seq_file *seq, void *v)
 	}
 	return 0;
 }
-
-static int ntp_servers_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ntp_servers_seq_show, NULL);
-}
-
-static const struct file_operations ntp_servers_seq_fops = {
-	.open		= ntp_servers_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(ntp_servers_seq);
 #endif /* CONFIG_PROC_FS */
 
 /*
-- 
cgit v1.2.3


From b09026c6913eeef1b21914a9d441ba275df40f27 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Sat, 15 Dec 2018 02:59:30 -0500
Subject: cxgb4: remove DEFINE_SIMPLE_DEBUGFS_FILE()

We already have the DEFINE_SHOW_ATTRIBUTE. There is no need to define
such a macro, so remove DEFINE_SIMPLE_DEBUGFS_FILE. Also use the
DEFINE_SHOW_ATTRIBUTE macro to simplify some code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 113 +++++----------------
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h |  13 ---
 .../net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c    |  16 +--
 3 files changed, 25 insertions(+), 117 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index cab492ec8f59..b0ff9fa183f4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -378,19 +378,7 @@ static int cim_qcfg_show(struct seq_file *seq, void *v)
 			   QUEREMFLITS_G(p[2]) * 16);
 	return 0;
 }
-
-static int cim_qcfg_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, cim_qcfg_show, inode->i_private);
-}
-
-static const struct file_operations cim_qcfg_fops = {
-	.owner   = THIS_MODULE,
-	.open    = cim_qcfg_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(cim_qcfg);
 
 static int cimq_show(struct seq_file *seq, void *v, int idx)
 {
@@ -860,8 +848,7 @@ static int tx_rate_show(struct seq_file *seq, void *v)
 	}
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(tx_rate);
+DEFINE_SHOW_ATTRIBUTE(tx_rate);
 
 static int cctrl_tbl_show(struct seq_file *seq, void *v)
 {
@@ -893,8 +880,7 @@ static int cctrl_tbl_show(struct seq_file *seq, void *v)
 	kfree(incr);
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(cctrl_tbl);
+DEFINE_SHOW_ATTRIBUTE(cctrl_tbl);
 
 /* Format a value in a unit that differs from the value's native unit by the
  * given factor.
@@ -955,8 +941,7 @@ static int clk_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(clk);
+DEFINE_SHOW_ATTRIBUTE(clk);
 
 /* Firmware Device Log dump. */
 static const char * const devlog_level_strings[] = {
@@ -1990,22 +1975,10 @@ static int sensors_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(sensors);
+DEFINE_SHOW_ATTRIBUTE(sensors);
 
 #if IS_ENABLED(CONFIG_IPV6)
-static int clip_tbl_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, clip_tbl_show, inode->i_private);
-}
-
-static const struct file_operations clip_tbl_debugfs_fops = {
-	.owner   = THIS_MODULE,
-	.open    = clip_tbl_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release
-};
+DEFINE_SHOW_ATTRIBUTE(clip_tbl);
 #endif
 
 /*RSS Table.
@@ -2208,8 +2181,7 @@ static int rss_config_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(rss_config);
+DEFINE_SHOW_ATTRIBUTE(rss_config);
 
 /* RSS Secret Key.
  */
@@ -2628,19 +2600,7 @@ static int resources_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-static int resources_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, resources_show, inode->i_private);
-}
-
-static const struct file_operations resources_debugfs_fops = {
-	.owner   = THIS_MODULE,
-	.open    = resources_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release,
-};
+DEFINE_SHOW_ATTRIBUTE(resources);
 
 /**
  * ethqset2pinfo - return port_info of an Ethernet Queue Set
@@ -3233,8 +3193,7 @@ static int tid_info_show(struct seq_file *seq, void *v)
 			   t4_read_reg(adap, LE_DB_ACT_CNT_IPV6_A));
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(tid_info);
+DEFINE_SHOW_ATTRIBUTE(tid_info);
 
 static void add_debugfs_mem(struct adapter *adap, const char *name,
 			    unsigned int idx, unsigned int size_mb)
@@ -3364,21 +3323,9 @@ static int meminfo_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
+DEFINE_SHOW_ATTRIBUTE(meminfo);
 
-static int meminfo_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, meminfo_show, inode->i_private);
-}
-
-static const struct file_operations meminfo_fops = {
-	.owner   = THIS_MODULE,
-	.open    = meminfo_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release,
-};
-
-static int chcr_show(struct seq_file *seq, void *v)
+static int chcr_stats_show(struct seq_file *seq, void *v)
 {
 	struct adapter *adap = seq->private;
 
@@ -3399,20 +3346,7 @@ static int chcr_show(struct seq_file *seq, void *v)
 		   atomic_read(&adap->chcr_stats.ipsec_cnt));
 	return 0;
 }
-
-
-static int chcr_stats_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, chcr_show, inode->i_private);
-}
-
-static const struct file_operations chcr_stats_debugfs_fops = {
-        .owner   = THIS_MODULE,
-        .open    = chcr_stats_open,
-        .read    = seq_read,
-        .llseek  = seq_lseek,
-        .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(chcr_stats);
 
 #define PRINT_ADAP_STATS(string, value) \
 	seq_printf(seq, "%-25s %-20llu\n", (string), \
@@ -3573,8 +3507,7 @@ static int tp_stats_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(tp_stats);
+DEFINE_SHOW_ATTRIBUTE(tp_stats);
 
 /* Add an array of Debug FS files.
  */
@@ -3603,7 +3536,7 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "cim_pif_la", &cim_pif_la_fops, 0400, 0 },
 		{ "cim_ma_la", &cim_ma_la_fops, 0400, 0 },
 		{ "cim_qcfg", &cim_qcfg_fops, 0400, 0 },
-		{ "clk", &clk_debugfs_fops, 0400, 0 },
+		{ "clk", &clk_fops, 0400, 0 },
 		{ "devlog", &devlog_fops, 0400, 0 },
 		{ "mboxlog", &mboxlog_fops, 0400, 0 },
 		{ "mbox0", &mbox_debugfs_fops, 0600, 0 },
@@ -3621,11 +3554,11 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "l2t", &t4_l2t_fops, 0400, 0},
 		{ "mps_tcam", &mps_tcam_debugfs_fops, 0400, 0 },
 		{ "rss", &rss_debugfs_fops, 0400, 0 },
-		{ "rss_config", &rss_config_debugfs_fops, 0400, 0 },
+		{ "rss_config", &rss_config_fops, 0400, 0 },
 		{ "rss_key", &rss_key_debugfs_fops, 0400, 0 },
 		{ "rss_pf_config", &rss_pf_config_debugfs_fops, 0400, 0 },
 		{ "rss_vf_config", &rss_vf_config_debugfs_fops, 0400, 0 },
-		{ "resources", &resources_debugfs_fops, 0400, 0 },
+		{ "resources", &resources_fops, 0400, 0 },
 #ifdef CONFIG_CHELSIO_T4_DCB
 		{ "dcb_info", &dcb_info_debugfs_fops, 0400, 0 },
 #endif
@@ -3644,18 +3577,18 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "obq_ncsi", &cim_obq_fops, 0400, 5 },
 		{ "tp_la", &tp_la_fops, 0400, 0 },
 		{ "ulprx_la", &ulprx_la_fops, 0400, 0 },
-		{ "sensors", &sensors_debugfs_fops, 0400, 0 },
+		{ "sensors", &sensors_fops, 0400, 0 },
 		{ "pm_stats", &pm_stats_debugfs_fops, 0400, 0 },
-		{ "tx_rate", &tx_rate_debugfs_fops, 0400, 0 },
-		{ "cctrl", &cctrl_tbl_debugfs_fops, 0400, 0 },
+		{ "tx_rate", &tx_rate_fops, 0400, 0 },
+		{ "cctrl", &cctrl_tbl_fops, 0400, 0 },
 #if IS_ENABLED(CONFIG_IPV6)
-		{ "clip_tbl", &clip_tbl_debugfs_fops, 0400, 0 },
+		{ "clip_tbl", &clip_tbl_fops, 0400, 0 },
 #endif
-		{ "tids", &tid_info_debugfs_fops, 0400, 0},
+		{ "tids", &tid_info_fops, 0400, 0},
 		{ "blocked_fl", &blocked_fl_fops, 0600, 0 },
 		{ "meminfo", &meminfo_fops, 0400, 0 },
-		{ "crypto", &chcr_stats_debugfs_fops, 0400, 0 },
-		{ "tp_stats", &tp_stats_debugfs_fops, 0400, 0 },
+		{ "crypto", &chcr_stats_fops, 0400, 0 },
+		{ "tp_stats", &tp_stats_fops, 0400, 0 },
 	};
 
 	/* Debug FS nodes common to all T5 and later adapters.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h
index 23f43a0f8950..ba95e13d52da 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h
@@ -37,19 +37,6 @@
 
 #include <linux/export.h>
 
-#define DEFINE_SIMPLE_DEBUGFS_FILE(name) \
-static int name##_open(struct inode *inode, struct file *file) \
-{ \
-	return single_open(file, name##_show, inode->i_private); \
-} \
-static const struct file_operations name##_debugfs_fops = { \
-	.owner   = THIS_MODULE, \
-	.open    = name##_open, \
-	.read    = seq_read, \
-	.llseek  = seq_lseek, \
-	.release = single_release \
-}
-
 struct t4_debugfs_entry {
 	const char *name;
 	const struct file_operations *ops;
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 8a2ad6b387ea..2fab87e86561 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -2323,19 +2323,7 @@ static int resources_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-static int resources_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, resources_show, inode->i_private);
-}
-
-static const struct file_operations resources_proc_fops = {
-	.owner   = THIS_MODULE,
-	.open    = resources_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(resources);
 
 /*
  * Show Virtual Interfaces.
@@ -2419,7 +2407,7 @@ static struct cxgb4vf_debugfs_entry debugfs_files[] = {
 	{ "mboxlog",    0444, &mboxlog_fops },
 	{ "sge_qinfo",  0444, &sge_qinfo_debugfs_fops },
 	{ "sge_qstats", 0444, &sge_qstats_proc_fops },
-	{ "resources",  0444, &resources_proc_fops },
+	{ "resources",  0444, &resources_fops },
 	{ "interfaces", 0444, &interfaces_proc_fops },
 };
 
-- 
cgit v1.2.3


From e782410ed2378a2ddac58d944c3cf0c6f96b1ff3 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 15 Dec 2018 16:25:05 +0100
Subject: r8169: improve spurious interrupt detection

Improve detection of spurious interrupts by checking against the
interrupt mask as currently set in the chip.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index e26c48bd54a2..18e39e5e447b 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6405,8 +6405,9 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 {
 	struct rtl8169_private *tp = dev_instance;
 	u16 status = rtl_get_events(tp);
+	u16 irq_mask = RTL_R16(tp, IntrMask);
 
-	if (status == 0xffff || !(status & tp->irq_mask))
+	if (status == 0xffff || !(status & irq_mask))
 		return IRQ_NONE;
 
 	if (unlikely(status & SYSErr)) {
-- 
cgit v1.2.3


From c2027d1e17582903e368abf5d4838b22a98f2b7b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 12 Dec 2018 15:27:38 -0800
Subject: ipv6: Fix handling of LLA with VRF and sockets bound to VRF

A recent commit allows sockets bound to a VRF to receive ipv6 link local
packets. However, it only works for UDP and worse TCP connection attempts
to the LLA with the only listener bound to the VRF just hang where as
before the client gets a reset and connection refused. Fix by adjusting
ir_iif for LL addresses and packets received through a device enslaved
to a VRF.

Fixes: 6f12fa775530 ("vrf: mark skb for multicast or link-local as enslaved to VRF")
Reported-by: Donald Sharp <sharpd@cumulusnetworks.com>
Cc: Mike Manning <mmanning@vyatta.att-mail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a3f559162521..b81eb7cb815e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -737,6 +737,7 @@ static void tcp_v6_init_req(struct request_sock *req,
 			    const struct sock *sk_listener,
 			    struct sk_buff *skb)
 {
+	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
 	struct inet_request_sock *ireq = inet_rsk(req);
 	const struct ipv6_pinfo *np = inet6_sk(sk_listener);
 
@@ -744,7 +745,7 @@ static void tcp_v6_init_req(struct request_sock *req,
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
 
 	/* So that link locals have meaning */
-	if (!sk_listener->sk_bound_dev_if &&
+	if ((!sk_listener->sk_bound_dev_if || l3_slave) &&
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
 		ireq->ir_iif = tcp_v6_iif(skb);
 
-- 
cgit v1.2.3


From 2561f97267d656c9b2c62b32614870abb3eabfe6 Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Thu, 13 Dec 2018 00:43:23 -0800
Subject: net: sched: simplify the qdisc_leaf code

Except for returning, the var leaf is not
used in the qdisc_leaf(). For simplicity, remove it.

Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 9c88cec7e8a2..187a57e7d601 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -335,7 +335,6 @@ out:
 static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid)
 {
 	unsigned long cl;
-	struct Qdisc *leaf;
 	const struct Qdisc_class_ops *cops = p->ops->cl_ops;
 
 	if (cops == NULL)
@@ -344,8 +343,7 @@ static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid)
 
 	if (cl == 0)
 		return NULL;
-	leaf = cops->leaf(p, cl);
-	return leaf;
+	return cops->leaf(p, cl);
 }
 
 /* Find queueing discipline by name */
-- 
cgit v1.2.3


From 4b7cd11f22e5e62b68c543ee74ed3c9f9e70baba Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 13 Dec 2018 08:16:50 -0800
Subject: neighbor: Improve neighbour struct layout

Move arp_queue_len_bytes ahead of arp_queue to remove two 4-byte holes.
Ensure ha element is always 8-byte aligned.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index ef0a60448a96..30fd50adf234 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -140,8 +140,8 @@ struct neighbour {
 	unsigned long		updated;
 	rwlock_t		lock;
 	refcount_t		refcnt;
-	struct sk_buff_head	arp_queue;
 	unsigned int		arp_queue_len_bytes;
+	struct sk_buff_head	arp_queue;
 	struct timer_list	timer;
 	unsigned long		used;
 	atomic_t		probes;
@@ -150,7 +150,7 @@ struct neighbour {
 	__u8			type;
 	__u8			dead;
 	seqlock_t		ha_lock;
-	unsigned char		ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))];
+	unsigned char		ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8);
 	struct hh_cache		hh;
 	int			(*output)(struct neighbour *, struct sk_buff *);
 	const struct neigh_ops	*ops;
-- 
cgit v1.2.3


From 1811caa0cf91320baff40c82cbb157c772cfd365 Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro@bp.renesas.com>
Date: Thu, 13 Dec 2018 20:18:34 +0000
Subject: dt-bindings: net: ravb: Add support for r8a774c0 SoC

Document RZ/G2E (R8A774C0) SoC bindings.

Signed-off-by: Fabrizio Castro <fabrizio.castro@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Reviewed-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/renesas,ravb.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index 3530256a879c..7ad36213093e 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -18,6 +18,7 @@ Required properties:
 		R-Car Gen2 and RZ/G1 devices.
 
       - "renesas,etheravb-r8a774a1" for the R8A774A1 SoC.
+      - "renesas,etheravb-r8a774c0" for the R8A774C0 SoC.
       - "renesas,etheravb-r8a7795" for the R8A7795 SoC.
       - "renesas,etheravb-r8a7796" for the R8A7796 SoC.
       - "renesas,etheravb-r8a77965" for the R8A77965 SoC.
-- 
cgit v1.2.3


From 17a12eaaf09a2fa3ea6997e3b5be8bc05fc60ee4 Mon Sep 17 00:00:00 2001
From: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Date: Fri, 14 Dec 2018 10:59:00 +0200
Subject: net: socionext: correctly recover txq after being full

Running pktgen with packets sizes > 512b ends up in the interface Txq
getting stuck.
"netsec 522d0000.ethernet eth0: netsec_netdev_start_xmit: TxQFull!"
appears on dmesg but the interface never recovers. It requires an
ifconfig down/up to make the interface usable again.

The reason that triggers this, is a race condition between
.ndo_start_xmit and the napi completion. The available budget is
calculated first and indicates the queue is full. Due to a costly
netif_err() the queue is not stopped in time while the napi completion
runs, clears the irq and frees up descriptors, thus the queue never wakes
up again.

Fix this by moving the print after stopping the queue, make the print
ratelimited, add barriers and check for cleaned descriptors..

Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 56 ++++++++++++++++++++++++++-------
 1 file changed, 45 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index bba9733b5119..584a6b3f6542 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -656,8 +656,13 @@ static int netsec_process_tx(struct netsec_priv *priv, int budget)
 		budget -= new;
 	} while (new);
 
-	if (done && netif_queue_stopped(ndev))
+	if (done && netif_queue_stopped(ndev)) {
+		/* Make sure we update the value, anyone stopping the queue
+		 * after this will read the proper consumer idx
+		 */
+		smp_wmb();
 		netif_wake_queue(ndev);
+	}
 
 	return done;
 }
@@ -877,6 +882,41 @@ static void netsec_set_tx_de(struct netsec_priv *priv,
 	dring->head = (dring->head + 1) % DESC_NUM;
 }
 
+static int netsec_desc_used(struct netsec_desc_ring *dring)
+{
+	int used;
+
+	if (dring->head >= dring->tail)
+		used = dring->head - dring->tail;
+	else
+		used = dring->head + DESC_NUM - dring->tail;
+
+	return used;
+}
+
+static int netsec_check_stop_tx(struct netsec_priv *priv, int used)
+{
+	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX];
+
+	/* keep tail from touching the queue */
+	if (DESC_NUM - used < 2) {
+		netif_stop_queue(priv->ndev);
+
+		/* Make sure we read the updated value in case
+		 * descriptors got freed
+		 */
+		smp_rmb();
+
+		used = netsec_desc_used(dring);
+		if (DESC_NUM - used < 2)
+			return NETDEV_TX_BUSY;
+
+		netif_wake_queue(priv->ndev);
+	}
+
+	return 0;
+}
+
 static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 					    struct net_device *ndev)
 {
@@ -887,16 +927,10 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 	u16 tso_seg_len = 0;
 	int filled;
 
-	/* differentiate between full/emtpy ring */
-	if (dring->head >= dring->tail)
-		filled = dring->head - dring->tail;
-	else
-		filled = dring->head + DESC_NUM - dring->tail;
-
-	if (DESC_NUM - filled < 2) { /* if less than 2 available */
-		netif_err(priv, drv, priv->ndev, "%s: TxQFull!\n", __func__);
-		netif_stop_queue(priv->ndev);
-		dma_wmb();
+	filled = netsec_desc_used(dring);
+	if (netsec_check_stop_tx(priv, filled)) {
+		net_warn_ratelimited("%s %s Tx queue full\n",
+				     dev_name(priv->dev), ndev->name);
 		return NETDEV_TX_BUSY;
 	}
 
-- 
cgit v1.2.3


From 35e07d23473972b8876f98bcfc631ebcf779e870 Mon Sep 17 00:00:00 2001
From: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Date: Fri, 14 Dec 2018 10:59:01 +0200
Subject: net: socionext: remove mmio reads on Tx

Currently the driver issues 2 mmio reads to figure out the number of
transmitted packets and clean them. We can get rid of the expensive
reads since BIT 31 of the Tx descriptor can be used for that.
We can also remove the budget counting of Tx completions since all of
the descriptors are not deliberately processed.

Performance numbers using pktgen are:
size  pre-patch(pps)  post-patch(pps)
64       362483           427916
128      358315           411686
256      352725           389683
512      215675           216464
1024     113812           114442

Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 97 ++++++++++++++++++---------------
 1 file changed, 54 insertions(+), 43 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 584a6b3f6542..05a0948ad929 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -257,7 +257,6 @@ struct netsec_desc_ring {
 	dma_addr_t desc_dma;
 	struct netsec_desc *desc;
 	void *vaddr;
-	u16 pkt_cnt;
 	u16 head, tail;
 };
 
@@ -598,33 +597,26 @@ static void netsec_set_rx_de(struct netsec_priv *priv,
 	dring->desc[idx].len = desc->len;
 }
 
-static int netsec_clean_tx_dring(struct netsec_priv *priv, int budget)
+static bool netsec_clean_tx_dring(struct netsec_priv *priv)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX];
 	unsigned int pkts, bytes;
-
-	dring->pkt_cnt += netsec_read(priv, NETSEC_REG_NRM_TX_DONE_PKTCNT);
-
-	if (dring->pkt_cnt < budget)
-		budget = dring->pkt_cnt;
+	struct netsec_de *entry;
+	int tail = dring->tail;
+	int cnt = 0;
 
 	pkts = 0;
 	bytes = 0;
+	entry = dring->vaddr + DESC_SZ * tail;
 
-	while (pkts < budget) {
+	while (!(entry->attr & (1U << NETSEC_TX_SHIFT_OWN_FIELD)) &&
+	       cnt < DESC_NUM) {
 		struct netsec_desc *desc;
-		struct netsec_de *entry;
-		int tail, eop;
-
-		tail = dring->tail;
-
-		/* move tail ahead */
-		dring->tail = (tail + 1) % DESC_NUM;
+		int eop;
 
 		desc = &dring->desc[tail];
-		entry = dring->vaddr + DESC_SZ * tail;
-
 		eop = (entry->attr >> NETSEC_TX_LAST) & 1;
+		dma_rmb();
 
 		dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
 				 DMA_TO_DEVICE);
@@ -633,38 +625,51 @@ static int netsec_clean_tx_dring(struct netsec_priv *priv, int budget)
 			bytes += desc->skb->len;
 			dev_kfree_skb(desc->skb);
 		}
+		/* clean up so netsec_uninit_pkt_dring() won't free the skb
+		 * again
+		 */
 		*desc = (struct netsec_desc){};
+
+		/* entry->attr is not going to be accessed by the NIC until
+		 * netsec_set_tx_de() is called. No need for a dma_wmb() here
+		 */
+		entry->attr = 1U << NETSEC_TX_SHIFT_OWN_FIELD;
+		/* move tail ahead */
+		dring->tail = (tail + 1) % DESC_NUM;
+
+		tail = dring->tail;
+		entry = dring->vaddr + DESC_SZ * tail;
+		cnt++;
 	}
-	dring->pkt_cnt -= budget;
 
-	priv->ndev->stats.tx_packets += budget;
+	if (!cnt)
+		return false;
+
+	/* reading the register clears the irq */
+	netsec_read(priv, NETSEC_REG_NRM_TX_DONE_PKTCNT);
+
+	priv->ndev->stats.tx_packets += cnt;
 	priv->ndev->stats.tx_bytes += bytes;
 
-	netdev_completed_queue(priv->ndev, budget, bytes);
+	netdev_completed_queue(priv->ndev, cnt, bytes);
 
-	return budget;
+	return true;
 }
 
-static int netsec_process_tx(struct netsec_priv *priv, int budget)
+static void netsec_process_tx(struct netsec_priv *priv)
 {
 	struct net_device *ndev = priv->ndev;
-	int new, done = 0;
+	bool cleaned;
 
-	do {
-		new = netsec_clean_tx_dring(priv, budget);
-		done += new;
-		budget -= new;
-	} while (new);
+	cleaned = netsec_clean_tx_dring(priv);
 
-	if (done && netif_queue_stopped(ndev)) {
+	if (cleaned && netif_queue_stopped(ndev)) {
 		/* Make sure we update the value, anyone stopping the queue
 		 * after this will read the proper consumer idx
 		 */
 		smp_wmb();
 		netif_wake_queue(ndev);
 	}
-
-	return done;
 }
 
 static void *netsec_alloc_rx_data(struct netsec_priv *priv,
@@ -813,24 +818,17 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 static int netsec_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct netsec_priv *priv;
-	int tx, rx, done, todo;
+	int rx, done, todo;
 
 	priv = container_of(napi, struct netsec_priv, napi);
 
+	netsec_process_tx(priv);
+
 	todo = budget;
 	do {
-		if (!todo)
-			break;
-
-		tx = netsec_process_tx(priv, todo);
-		todo -= tx;
-
-		if (!todo)
-			break;
-
 		rx = netsec_process_rx(priv, todo);
 		todo -= rx;
-	} while (rx || tx);
+	} while (rx);
 
 	done = budget - todo;
 
@@ -1007,7 +1005,6 @@ static void netsec_uninit_pkt_dring(struct netsec_priv *priv, int id)
 
 	dring->head = 0;
 	dring->tail = 0;
-	dring->pkt_cnt = 0;
 
 	if (id == NETSEC_RING_TX)
 		netdev_reset_queue(priv->ndev);
@@ -1030,6 +1027,7 @@ static void netsec_free_dring(struct netsec_priv *priv, int id)
 static int netsec_alloc_dring(struct netsec_priv *priv, enum ring_id id)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[id];
+	int i;
 
 	dring->vaddr = dma_zalloc_coherent(priv->dev, DESC_SZ * DESC_NUM,
 					   &dring->desc_dma, GFP_KERNEL);
@@ -1040,6 +1038,19 @@ static int netsec_alloc_dring(struct netsec_priv *priv, enum ring_id id)
 	if (!dring->desc)
 		goto err;
 
+	if (id == NETSEC_RING_TX) {
+		for (i = 0; i < DESC_NUM; i++) {
+			struct netsec_de *de;
+
+			de = dring->vaddr + (DESC_SZ * i);
+			/* de->attr is not going to be accessed by the NIC
+			 * until netsec_set_tx_de() is called.
+			 * No need for a dma_wmb() here
+			 */
+			de->attr = 1U << NETSEC_TX_SHIFT_OWN_FIELD;
+		}
+	}
+
 	return 0;
 err:
 	netsec_free_dring(priv, id);
-- 
cgit v1.2.3


From 283c16a2dfd332bf5610c874f7b9f9c8b601ce53 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 14 Dec 2018 11:51:57 +0100
Subject: indirect call wrappers: helpers to speed-up indirect calls of builtin

This header define a bunch of helpers that allow avoiding the
retpoline overhead when calling builtin functions via function pointers.
It boils down to explicitly comparing the function pointers to
known builtin functions and eventually invoke directly the latter.

The macros defined here implement the boilerplate for the above schema
and will be used by the next patches.

rfc -> v1:
 - use branch prediction hint, as suggested by Eric
v1  -> v2:
 - list explicitly the builtin function names in INDIRECT_CALL_*(),
   as suggested by Ed Cree

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/indirect_call_wrapper.h | 51 +++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
 create mode 100644 include/linux/indirect_call_wrapper.h

diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
new file mode 100644
index 000000000000..7c8b7f4948af
--- /dev/null
+++ b/include/linux/indirect_call_wrapper.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_INDIRECT_CALL_WRAPPER_H
+#define _LINUX_INDIRECT_CALL_WRAPPER_H
+
+#ifdef CONFIG_RETPOLINE
+
+/*
+ * INDIRECT_CALL_$NR - wrapper for indirect calls with $NR known builtin
+ *  @f: function pointer
+ *  @f$NR: builtin functions names, up to $NR of them
+ *  @__VA_ARGS__: arguments for @f
+ *
+ * Avoid retpoline overhead for known builtin, checking @f vs each of them and
+ * eventually invoking directly the builtin function. The functions are check
+ * in the given order. Fallback to the indirect call.
+ */
+#define INDIRECT_CALL_1(f, f1, ...)					\
+	({								\
+		likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__);	\
+	})
+#define INDIRECT_CALL_2(f, f2, f1, ...)					\
+	({								\
+		likely(f == f2) ? f2(__VA_ARGS__) :			\
+				  INDIRECT_CALL_1(f, f1, __VA_ARGS__);	\
+	})
+
+#define INDIRECT_CALLABLE_DECLARE(f)	f
+#define INDIRECT_CALLABLE_SCOPE
+
+#else
+#define INDIRECT_CALL_1(f, name, ...) f(__VA_ARGS__)
+#define INDIRECT_CALL_2(f, name, ...) f(__VA_ARGS__)
+#define INDIRECT_CALLABLE_DECLARE(f)
+#define INDIRECT_CALLABLE_SCOPE		static
+#endif
+
+/*
+ * We can use INDIRECT_CALL_$NR for ipv6 related functions only if ipv6 is
+ * builtin, this macro simplify dealing with indirect calls with only ipv4/ipv6
+ * alternatives
+ */
+#if IS_BUILTIN(CONFIG_IPV6)
+#define INDIRECT_CALL_INET(f, f2, f1, ...) \
+	INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__)
+#elif IS_ENABLED(CONFIG_INET)
+#define INDIRECT_CALL_INET(f, f2, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__)
+#else
+#define INDIRECT_CALL_INET(f, f2, f1, ...) f(__VA_ARGS__)
+#endif
+
+#endif
-- 
cgit v1.2.3


From aaa5d90b395a72faff797b00d815165ee0e664c0 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 14 Dec 2018 11:51:58 +0100
Subject: net: use indirect call wrappers at GRO network layer

This avoids an indirect calls for L3 GRO receive path, both
for ipv4 and ipv6, if the latter is not compiled as a module.

Note that when IPv6 is compiled as builtin, it will be checked first,
so we have a single additional compare for the more common path.

v1 -> v2:
 - adapted to INDIRECT_CALL_ changes

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_common.h |  2 ++
 net/core/dev.c            | 15 +++++++++++++--
 net/ipv6/ip6_offload.c    |  6 +++---
 3 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 3ca969cbd161..56e7592811ea 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -2,6 +2,8 @@
 #ifndef _INET_COMMON_H
 #define _INET_COMMON_H
 
+#include <linux/indirect_call_wrapper.h>
+
 extern const struct proto_ops inet_stream_ops;
 extern const struct proto_ops inet_dgram_ops;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index ed9aa4a91f1f..1b5a4410be0e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -145,6 +145,7 @@
 #include <linux/sctp.h>
 #include <net/udp_tunnel.h>
 #include <linux/net_namespace.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include "net-sysfs.h"
 
@@ -5338,6 +5339,8 @@ static void flush_all_backlogs(void)
 	put_online_cpus();
 }
 
+INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int));
+INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int));
 static int napi_gro_complete(struct sk_buff *skb)
 {
 	struct packet_offload *ptype;
@@ -5357,7 +5360,9 @@ static int napi_gro_complete(struct sk_buff *skb)
 		if (ptype->type != type || !ptype->callbacks.gro_complete)
 			continue;
 
-		err = ptype->callbacks.gro_complete(skb, 0);
+		err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete,
+					 ipv6_gro_complete, inet_gro_complete,
+					 skb, 0);
 		break;
 	}
 	rcu_read_unlock();
@@ -5504,6 +5509,10 @@ static void gro_flush_oldest(struct list_head *head)
 	napi_gro_complete(oldest);
 }
 
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *,
+							   struct sk_buff *));
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *,
+							   struct sk_buff *));
 static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	u32 hash = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1);
@@ -5553,7 +5562,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 			NAPI_GRO_CB(skb)->csum_valid = 0;
 		}
 
-		pp = ptype->callbacks.gro_receive(gro_head, skb);
+		pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive,
+					ipv6_gro_receive, inet_gro_receive,
+					gro_head, skb);
 		break;
 	}
 	rcu_read_unlock();
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 70f525c33cb6..ff8b484d2258 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -164,8 +164,8 @@ static int ipv6_exthdrs_len(struct ipv6hdr *iph,
 	return len;
 }
 
-static struct sk_buff *ipv6_gro_receive(struct list_head *head,
-					struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
+							 struct sk_buff *skb)
 {
 	const struct net_offload *ops;
 	struct sk_buff *pp = NULL;
@@ -301,7 +301,7 @@ static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
 	return inet_gro_receive(head, skb);
 }
 
-static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
+INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct net_offload *ops;
 	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
-- 
cgit v1.2.3


From 028e0a4766844e7eeb31b93479ea6dd40cfc2895 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 14 Dec 2018 11:51:59 +0100
Subject: net: use indirect call wrappers at GRO transport layer

This avoids an indirect call in the receive path for TCP and UDP
packets. TCP takes precedence on UDP, so that we have a single
additional conditional in the common case.

When IPV6 is build as module, all gro symbols except UDPv6 are
builtin, while the latter belong to the ipv6 module, so we
need some special care.

v1 -> v2:
 - adapted to INDIRECT_CALL_ changes
v2 -> v3:
 - fix build issue with CONFIG_IPV6=m

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_common.h |  7 +++++++
 net/ipv4/af_inet.c        | 13 +++++++++++--
 net/ipv4/tcp_offload.c    |  6 ++++--
 net/ipv4/udp_offload.c    |  7 ++++---
 net/ipv6/ip6_offload.c    | 29 +++++++++++++++++++++++++++--
 net/ipv6/tcpv6_offload.c  |  7 ++++---
 net/ipv6/udp_offload.c    |  7 ++++---
 7 files changed, 61 insertions(+), 15 deletions(-)

diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 56e7592811ea..975901a95c0f 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -56,4 +56,11 @@ static inline void inet_ctl_sock_destroy(struct sock *sk)
 		sock_release(sk->sk_socket);
 }
 
+#define indirect_call_gro_receive(f2, f1, cb, head, skb)	\
+({								\
+	unlikely(gro_recursion_inc_test(skb)) ?			\
+		NAPI_GRO_CB(skb)->flush |= 1, NULL :		\
+		INDIRECT_CALL_2(cb, f2, f1, head, skb);		\
+})
+
 #endif
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 326c422c22f8..0dfb72c46671 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1385,6 +1385,10 @@ out:
 }
 EXPORT_SYMBOL(inet_gso_segment);
 
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *,
+							   struct sk_buff *));
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *,
+							   struct sk_buff *));
 struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	const struct net_offload *ops;
@@ -1494,7 +1498,8 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 	skb_gro_pull(skb, sizeof(*iph));
 	skb_set_transport_header(skb, skb_gro_offset(skb));
 
-	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
+	pp = indirect_call_gro_receive(tcp4_gro_receive, udp4_gro_receive,
+				       ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -1556,6 +1561,8 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	return -EINVAL;
 }
 
+INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *, int));
+INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int));
 int inet_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	__be16 newlen = htons(skb->len - nhoff);
@@ -1581,7 +1588,9 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)
 	 * because any hdr with option will have been flushed in
 	 * inet_gro_receive().
 	 */
-	err = ops->callbacks.gro_complete(skb, nhoff + sizeof(*iph));
+	err = INDIRECT_CALL_2(ops->callbacks.gro_complete,
+			      tcp4_gro_complete, udp4_gro_complete,
+			      skb, nhoff + sizeof(*iph));
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 870b0a335061..0fbf7d4df9da 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -10,6 +10,7 @@
  *	TCPv4 GSO/GRO support
  */
 
+#include <linux/indirect_call_wrapper.h>
 #include <linux/skbuff.h>
 #include <net/tcp.h>
 #include <net/protocol.h>
@@ -305,7 +306,8 @@ int tcp_gro_complete(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_gro_complete);
 
-static struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE
+struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	/* Don't bother verifying checksum if we're going to flush anyway. */
 	if (!NAPI_GRO_CB(skb)->flush &&
@@ -318,7 +320,7 @@ static struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *
 	return tcp_gro_receive(head, skb);
 }
 
-static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
+INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct tcphdr *th = tcp_hdr(skb);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0646d61f4fa8..9a141a6cf1a0 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -13,6 +13,7 @@
 #include <linux/skbuff.h>
 #include <net/udp.h>
 #include <net/protocol.h>
+#include <net/inet_common.h>
 
 static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	netdev_features_t features,
@@ -451,8 +452,8 @@ out_unlock:
 }
 EXPORT_SYMBOL(udp_gro_receive);
 
-static struct sk_buff *udp4_gro_receive(struct list_head *head,
-					struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE
+struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
@@ -525,7 +526,7 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
 }
 EXPORT_SYMBOL(udp_gro_complete);
 
-static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
+INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index ff8b484d2258..5c045691c302 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -20,6 +20,23 @@
 
 #include "ip6_offload.h"
 
+/* All GRO functions are always builtin, except UDP over ipv6, which lays in
+ * ipv6 module, as it depends on UDPv6 lookup function, so we need special care
+ * when ipv6 is built as a module
+ */
+#if IS_BUILTIN(CONFIG_IPV6)
+#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__)
+#else
+#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__)
+#endif
+
+#define indirect_call_gro_receive_l4(f2, f1, cb, head, skb)	\
+({								\
+	unlikely(gro_recursion_inc_test(skb)) ?			\
+		NAPI_GRO_CB(skb)->flush |= 1, NULL :		\
+		INDIRECT_CALL_L4(cb, f2, f1, head, skb);	\
+})
+
 static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
 {
 	const struct net_offload *ops = NULL;
@@ -164,6 +181,10 @@ static int ipv6_exthdrs_len(struct ipv6hdr *iph,
 	return len;
 }
 
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *,
+							   struct sk_buff *));
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *,
+							   struct sk_buff *));
 INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
 							 struct sk_buff *skb)
 {
@@ -260,7 +281,8 @@ not_same_flow:
 
 	skb_gro_postpull_rcsum(skb, iph, nlen);
 
-	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
+	pp = indirect_call_gro_receive_l4(tcp6_gro_receive, udp6_gro_receive,
+					 ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -301,6 +323,8 @@ static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
 	return inet_gro_receive(head, skb);
 }
 
+INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *, int));
+INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int));
 INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct net_offload *ops;
@@ -320,7 +344,8 @@ INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
 		goto out_unlock;
 
-	err = ops->callbacks.gro_complete(skb, nhoff);
+	err = INDIRECT_CALL_L4(ops->callbacks.gro_complete, tcp6_gro_complete,
+			       udp6_gro_complete, skb, nhoff);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index e72947c99454..3179c425d7ff 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -9,14 +9,15 @@
  *
  *      TCPv6 GSO/GRO support
  */
+#include <linux/indirect_call_wrapper.h>
 #include <linux/skbuff.h>
 #include <net/protocol.h>
 #include <net/tcp.h>
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
-static struct sk_buff *tcp6_gro_receive(struct list_head *head,
-					struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE
+struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	/* Don't bother verifying checksum if we're going to flush anyway. */
 	if (!NAPI_GRO_CB(skb)->flush &&
@@ -29,7 +30,7 @@ static struct sk_buff *tcp6_gro_receive(struct list_head *head,
 	return tcp_gro_receive(head, skb);
 }
 
-static int tcp6_gro_complete(struct sk_buff *skb, int thoff)
+INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct tcphdr *th = tcp_hdr(skb);
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 828b2457f97b..83b11d0ac091 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -11,6 +11,7 @@
  */
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
+#include <linux/indirect_call_wrapper.h>
 #include <net/protocol.h>
 #include <net/ipv6.h>
 #include <net/udp.h>
@@ -114,8 +115,8 @@ out:
 	return segs;
 }
 
-static struct sk_buff *udp6_gro_receive(struct list_head *head,
-					struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE
+struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
@@ -142,7 +143,7 @@ flush:
 	return NULL;
 }
 
-static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
+INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
-- 
cgit v1.2.3


From 4f24ed77dec9b067d08f7958a287cbf48665f35e Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 14 Dec 2018 11:52:00 +0100
Subject: udp: use indirect call wrappers for GRO socket lookup

This avoids another indirect call for UDP GRO. Again, the test
for the IPv6 variant is performed first.

v1 -> v2:
 - adapted to INDIRECT_CALL_ changes

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp_offload.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 9a141a6cf1a0..64f9715173ac 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -392,6 +392,8 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 	return NULL;
 }
 
+INDIRECT_CALLABLE_DECLARE(struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
+						   __be16 sport, __be16 dport));
 struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 				struct udphdr *uh, udp_lookup_t lookup)
 {
@@ -403,7 +405,8 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 	struct sock *sk;
 
 	rcu_read_lock();
-	sk = (*lookup)(skb, uh->source, uh->dest);
+	sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb,
+				udp4_lib_lookup_skb, skb, uh->source, uh->dest);
 	if (!sk)
 		goto out_unlock;
 
@@ -503,7 +506,8 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
 	uh->len = newlen;
 
 	rcu_read_lock();
-	sk = (*lookup)(skb, uh->source, uh->dest);
+	sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb,
+				udp4_lib_lookup_skb, skb, uh->source, uh->dest);
 	if (sk && udp_sk(sk)->gro_enabled) {
 		err = udp_gro_complete_segment(skb);
 	} else if (sk && udp_sk(sk)->gro_complete) {
-- 
cgit v1.2.3


From c151acc6e9ffa08972aa20d8bc07a66081922c1e Mon Sep 17 00:00:00 2001
From: Sam Protsenko <semen.protsenko@linaro.org>
Date: Fri, 14 Dec 2018 19:59:21 +0200
Subject: l2tp: Add protocol field decompression

When Protocol Field Compression (PFC) is enabled, the "Protocol" field
in PPP packet will be received without leading 0x00. See section 6.5 in
RFC 1661 for details. So let's decompress protocol field if needed, the
same way it's done in drivers/net/ppp/pptp.c.

In case when "nopcomp" pppd option is not enabled, PFC (pcomp) can be
negotiated during LCP handshake, and L2TP driver in kernel will receive
PPP packets with compressed Protocol field, which in turn leads to next
error:

    Protocol Rejected (unsupported protocol 0x2145)

because instead of Protocol=0x0021 in PPP packet there will be
Protocol=0x21. This patch unwraps it back to 0x0021, which fixes the
issue.

Sending the compressed Protocol field will be implemented in subsequent
patch, this one is self-sufficient.

Signed-off-by: Sam Protsenko <semen.protsenko@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 04d9946dcdba..c03c6461f236 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -236,6 +236,10 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
 	    skb->data[1] == PPP_UI)
 		skb_pull(skb, 2);
 
+	/* Decompress protocol field if PFC is enabled */
+	if ((*skb->data) & 0x1)
+		*(u8 *)skb_push(skb, 1) = 0;
+
 	if (sk->sk_state & PPPOX_BOUND) {
 		struct pppox_sock *po;
 
-- 
cgit v1.2.3


From ec49d83f245453515a9b6e88324e27bbcb69fbae Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Sat, 15 Dec 2018 14:27:23 -0800
Subject: net: dccp: initialize (addr,port) listening hashtable

Commit d9fbc7f6431f "net: tcp: prefer listeners bound to an address"
removes port-only listener lookups. This caused segfaults in DCCP
lookups because DCCP did not initialize the (addr,port) hashtable.

This patch adds said initialization.

The only non-trivial issue here is the size of the new hashtable.
It seemed reasonable to make it match the size of the port-only
hashtable (= INET_LHTABLE_SIZE) that was used previously. Other
parameters to inet_hashinfo2_init() match those used in TCP.

Tested: syzcaller issues fixed; the second patch in the patchset
        tests that DCCP lookups work correctly.

Fixes: d9fbc7f6431f "net: tcp: prefer listeners bound to an address"
Reported-by: syzcaller <syzkaller@googlegroups.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 658cd32bb7b3..be0b223aa862 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1141,6 +1141,9 @@ static int __init dccp_init(void)
 		goto out_fail;
 	rc = -ENOBUFS;
 	inet_hashinfo_init(&dccp_hashinfo);
+	inet_hashinfo2_init(&dccp_hashinfo, "dccp_listen_portaddr_hash",
+			    INET_LHTABLE_SIZE, 21,  /* one slot per 2 MB*/
+			    0, 64 * 1024);
 	dccp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("dccp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
-- 
cgit v1.2.3


From 11fb60d1089f52dd9003d02cf2590c9b56eda840 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Sat, 15 Dec 2018 14:27:24 -0800
Subject: selftests: net: reuseport_addr_any: add DCCP

This patch adds coverage of DCCP to reuseport_addr_any selftest.

Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/reuseport_addr_any.c | 49 +++++++++++++++++++++++-
 1 file changed, 47 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/reuseport_addr_any.c b/tools/testing/selftests/net/reuseport_addr_any.c
index f5e01d989519..4ac3e24b7cfc 100644
--- a/tools/testing/selftests/net/reuseport_addr_any.c
+++ b/tools/testing/selftests/net/reuseport_addr_any.c
@@ -9,6 +9,7 @@
 #include <arpa/inet.h>
 #include <errno.h>
 #include <error.h>
+#include <linux/dccp.h>
 #include <linux/in.h>
 #include <linux/unistd.h>
 #include <stdbool.h>
@@ -75,7 +76,16 @@ static void build_rcv_fd(int family, int proto, int *rcv_fds, int count,
 			error(1, errno, "failed to bind receive socket");
 
 		if (proto == SOCK_STREAM && listen(rcv_fds[i], 10))
-			error(1, errno, "failed to listen on receive port");
+			error(1, errno, "tcp: failed to listen on receive port");
+		else if (proto == SOCK_DCCP) {
+			if (setsockopt(rcv_fds[i], SOL_DCCP,
+					DCCP_SOCKOPT_SERVICE,
+					&(int) {htonl(42)}, sizeof(int)))
+				error(1, errno, "failed to setsockopt");
+
+			if (listen(rcv_fds[i], 10))
+				error(1, errno, "dccp: failed to listen on receive port");
+		}
 	}
 }
 
@@ -124,6 +134,11 @@ static int connect_and_send(int family, int proto)
 	if (fd < 0)
 		error(1, errno, "failed to create send socket");
 
+	if (proto == SOCK_DCCP &&
+		setsockopt(fd, SOL_DCCP, DCCP_SOCKOPT_SERVICE,
+				&(int){htonl(42)}, sizeof(int)))
+		error(1, errno, "failed to setsockopt");
+
 	if (bind(fd, saddr, sz))
 		error(1, errno, "failed to bind send socket");
 
@@ -146,7 +161,7 @@ static int receive_once(int epfd, int proto)
 	if (i < 0)
 		error(1, errno, "epoll_wait failed");
 
-	if (proto == SOCK_STREAM) {
+	if (proto == SOCK_STREAM || proto == SOCK_DCCP) {
 		fd = accept(ev.data.fd, NULL, NULL);
 		if (fd < 0)
 			error(1, errno, "failed to accept");
@@ -259,6 +274,36 @@ int main(void)
 	for (i = 0; i < 9; ++i)
 		close(rcv_fds[i]);
 
+	fprintf(stderr, "---- DCCP IPv4 ----\n");
+	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 2, 2, NULL);
+	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds + 4, 1, IP4_ADDR);
+	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds + 5, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 7, 2, NULL);
+	test(rcv_fds, 9, AF_INET, SOCK_DCCP, rcv_fds[4]);
+	for (i = 0; i < 9; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- DCCP IPv6 ----\n");
+	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 2, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 4, 1, IP6_ADDR);
+	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds + 5, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 7, 2, NULL);
+	test(rcv_fds, 9, AF_INET6, SOCK_DCCP, rcv_fds[4]);
+	for (i = 0; i < 9; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- DCCP IPv4 mapped to IPv6 ----\n");
+	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 2, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 4, 1, IP4_MAPPED6);
+	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds + 5, 2, NULL);
+	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 7, 2, NULL);
+	test(rcv_fds, 9, AF_INET, SOCK_DCCP, rcv_fds[4]);
+	for (i = 0; i < 9; ++i)
+		close(rcv_fds[i]);
+
 	fprintf(stderr, "SUCCESS\n");
 	return 0;
 }
-- 
cgit v1.2.3


From df9b0e30d44c901ac27c0f38cd54511b3f130c6d Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sat, 15 Dec 2018 14:09:06 -0800
Subject: neighbor: Add protocol attribute

Similar to routes and rules, add protocol attribute to neighbor entries
for easier tracking of how each was created.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h        |  2 ++
 include/uapi/linux/neighbour.h |  1 +
 net/core/neighbour.c           | 24 +++++++++++++++++++++++-
 3 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 30fd50adf234..66221f1991c0 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -149,6 +149,7 @@ struct neighbour {
 	__u8			nud_state;
 	__u8			type;
 	__u8			dead;
+	u8			protocol;
 	seqlock_t		ha_lock;
 	unsigned char		ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8);
 	struct hh_cache		hh;
@@ -173,6 +174,7 @@ struct pneigh_entry {
 	possible_net_t		net;
 	struct net_device	*dev;
 	u8			flags;
+	u8			protocol;
 	u8			key[0];
 };
 
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index 998155444e0d..cd144e3099a3 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -28,6 +28,7 @@ enum {
 	NDA_MASTER,
 	NDA_LINK_NETNSID,
 	NDA_SRC_VNI,
+	NDA_PROTOCOL,  /* Originator of entry */
 	__NDA_MAX
 };
 
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 42b413774370..fb4372cb1de1 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1828,6 +1828,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net_device *dev = NULL;
 	struct neighbour *neigh;
 	void *dst, *lladdr;
+	u8 protocol = 0;
 	int err;
 
 	ASSERT_RTNL();
@@ -1867,6 +1868,14 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	dst = nla_data(tb[NDA_DST]);
 	lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
 
+	if (tb[NDA_PROTOCOL]) {
+		if (nla_len(tb[NDA_PROTOCOL]) != sizeof(u8)) {
+			NL_SET_ERR_MSG(extack, "Invalid protocol attribute");
+			goto out;
+		}
+		protocol = nla_get_u8(tb[NDA_PROTOCOL]);
+	}
+
 	if (ndm->ndm_flags & NTF_PROXY) {
 		struct pneigh_entry *pn;
 
@@ -1874,6 +1883,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		pn = pneigh_lookup(tbl, net, dst, dev, 1);
 		if (pn) {
 			pn->flags = ndm->ndm_flags;
+			if (protocol)
+				pn->protocol = protocol;
 			err = 0;
 		}
 		goto out;
@@ -1924,6 +1935,10 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	} else
 		err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags,
 				     NETLINK_CB(skb).portid, extack);
+
+	if (protocol)
+		neigh->protocol = protocol;
+
 	neigh_release(neigh);
 
 out:
@@ -2417,6 +2432,9 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
 	    nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
 		goto nla_put_failure;
 
+	if (neigh->protocol && nla_put_u8(skb, NDA_PROTOCOL, neigh->protocol))
+		goto nla_put_failure;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -2448,6 +2466,9 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
 	if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
 		goto nla_put_failure;
 
+	if (pn->protocol && nla_put_u8(skb, NDA_PROTOCOL, pn->protocol))
+		goto nla_put_failure;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -3103,7 +3124,8 @@ static inline size_t neigh_nlmsg_size(void)
 	       + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */
 	       + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */
 	       + nla_total_size(sizeof(struct nda_cacheinfo))
-	       + nla_total_size(4); /* NDA_PROBES */
+	       + nla_total_size(4)  /* NDA_PROBES */
+	       + nla_total_size(1); /* NDA_PROTOCOL */
 }
 
 static void __neigh_notify(struct neighbour *n, int type, int flags,
-- 
cgit v1.2.3


From 9c46ae0ea1ee84012737c3da3af2930b494d56f7 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 16 Dec 2018 12:36:41 -0800
Subject: Revert "net: dccp: initialize (addr,port) listening hashtable"

This reverts commit ec49d83f245453515a9b6e88324e27bbcb69fbae.

Cause build failures when DCCP is modular.

ERROR: "inet_hashinfo2_init" [net/dccp/dccp.ko] undefined!

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index be0b223aa862..658cd32bb7b3 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1141,9 +1141,6 @@ static int __init dccp_init(void)
 		goto out_fail;
 	rc = -ENOBUFS;
 	inet_hashinfo_init(&dccp_hashinfo);
-	inet_hashinfo2_init(&dccp_hashinfo, "dccp_listen_portaddr_hash",
-			    INET_LHTABLE_SIZE, 21,  /* one slot per 2 MB*/
-			    0, 64 * 1024);
 	dccp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("dccp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
-- 
cgit v1.2.3


From 036b9e7caeb09598afb297a6d4fb36b477a4f6b2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 14 Dec 2018 15:01:54 -0800
Subject: nfp: abm: allow to opt-out of RED offload

FW team asks to be able to not support RED even if NIC is capable
of buffering for testing and experimentation.  Add an opt-out flag.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/ctrl.c | 11 +++++++++++
 drivers/net/ethernet/netronome/nfp/abm/main.c | 25 +++++++++++++++++++------
 drivers/net/ethernet/netronome/nfp/abm/main.h |  2 ++
 3 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index ad6c2a621c7a..9584f03f3efa 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -17,6 +17,8 @@
 #define NFP_NUM_BANDS_SYM_NAME	"_abi_pci_dscp_num_band_%u"
 #define NFP_ACT_MASK_SYM_NAME	"_abi_nfd_out_q_actions_%u"
 
+#define NFP_RED_SUPPORT_SYM_NAME	"_abi_nfd_out_red_offload_%u"
+
 #define NFP_QLVL_SYM_NAME	"_abi_nfd_out_q_lvls_%u%s"
 #define NFP_QLVL_STRIDE		16
 #define NFP_QLVL_BLOG_BYTES	0
@@ -358,6 +360,12 @@ int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm)
 
 	abm->pf_id = nfp_cppcore_pcie_unit(pf->cpp);
 
+	/* Check if Qdisc offloads are supported */
+	res = nfp_pf_rtsym_read_optional(pf, NFP_RED_SUPPORT_SYM_NAME, 1);
+	if (res < 0)
+		return res;
+	abm->red_support = res;
+
 	/* Read count of prios and prio bands */
 	res = nfp_pf_rtsym_read_optional(pf, NFP_NUM_BANDS_SYM_NAME, 1);
 	if (res < 0)
@@ -390,6 +398,9 @@ int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm)
 	}
 
 	/* Find level and stat symbols */
+	if (!abm->red_support)
+		return 0;
+
 	sym = nfp_abm_ctrl_find_q_rtsym(abm, NFP_QLVL_SYM_NAME,
 					NFP_QLVL_STRIDE);
 	if (IS_ERR(sym))
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 80e79447b644..4d4ff5844c47 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -207,6 +207,9 @@ static int nfp_abm_eswitch_set_switchdev(struct nfp_abm *abm)
 	struct nfp_net *nn;
 	int err;
 
+	if (!abm->red_support)
+		return -EOPNOTSUPP;
+
 	err = nfp_abm_ctrl_qm_enable(abm);
 	if (err)
 		return err;
@@ -418,12 +421,26 @@ nfp_abm_port_get_stats_strings(struct nfp_app *app, struct nfp_port *port,
 	return data;
 }
 
+static int nfp_abm_fw_init_reset(struct nfp_abm *abm)
+{
+	unsigned int i;
+
+	if (!abm->red_support)
+		return 0;
+
+	for (i = 0; i < abm->num_bands * NFP_NET_MAX_RX_RINGS; i++) {
+		__nfp_abm_ctrl_set_q_lvl(abm, i, NFP_ABM_LVL_INFINITY);
+		__nfp_abm_ctrl_set_q_act(abm, i, NFP_ABM_ACT_DROP);
+	}
+
+	return nfp_abm_ctrl_qm_disable(abm);
+}
+
 static int nfp_abm_init(struct nfp_app *app)
 {
 	struct nfp_pf *pf = app->pf;
 	struct nfp_reprs *reprs;
 	struct nfp_abm *abm;
-	unsigned int i;
 	int err;
 
 	if (!pf->eth_tbl) {
@@ -460,18 +477,14 @@ static int nfp_abm_init(struct nfp_app *app)
 				   sizeof(*abm->thresholds), GFP_KERNEL);
 	if (!abm->thresholds)
 		goto err_free_thresh_umap;
-	for (i = 0; i < abm->num_bands * NFP_NET_MAX_RX_RINGS; i++)
-		__nfp_abm_ctrl_set_q_lvl(abm, i, NFP_ABM_LVL_INFINITY);
 
 	abm->actions = kvcalloc(abm->num_thresholds, sizeof(*abm->actions),
 				GFP_KERNEL);
 	if (!abm->actions)
 		goto err_free_thresh;
-	for (i = 0; i < abm->num_bands * NFP_NET_MAX_RX_RINGS; i++)
-		__nfp_abm_ctrl_set_q_act(abm, i, NFP_ABM_ACT_DROP);
 
 	/* We start in legacy mode, make sure advanced queuing is disabled */
-	err = nfp_abm_ctrl_qm_disable(abm);
+	err = nfp_abm_fw_init_reset(abm);
 	if (err)
 		goto err_free_act;
 
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 4dcf5881fb4b..49749c60885e 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -40,6 +40,7 @@ enum nfp_abm_q_action {
  * @app:	back pointer to nfp_app
  * @pf_id:	ID of our PF link
  *
+ * @red_support:	is RED offload supported
  * @num_prios:	number of supported DSCP priorities
  * @num_bands:	number of supported DSCP priority bands
  * @action_mask:	bitmask of supported actions
@@ -63,6 +64,7 @@ struct nfp_abm {
 	struct nfp_app *app;
 	unsigned int pf_id;
 
+	unsigned int red_support;
 	unsigned int num_prios;
 	unsigned int num_bands;
 	unsigned int action_mask;
-- 
cgit v1.2.3


From 39d6b96f9fc2d99c4619954f462ba32e5d48502e Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Sat, 15 Dec 2018 01:58:04 +0100
Subject: net: dsa: ksz: Rename NET_DSA_TAG_KSZ to _KSZ9477

Rename the tag Kconfig option and related macros in preparation for
addition of new KSZ family switches with different tag formats.

Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Cc: David S. Miller <davem@davemloft.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/Kconfig   | 2 +-
 drivers/net/dsa/microchip/ksz9477.c | 2 +-
 include/net/dsa.h                   | 2 +-
 net/dsa/Kconfig                     | 4 ++++
 net/dsa/dsa.c                       | 8 ++++----
 net/dsa/dsa_priv.h                  | 2 +-
 net/dsa/tag_ksz.c                   | 2 +-
 7 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig
index a8caf9249d50..bea29fde9f3d 100644
--- a/drivers/net/dsa/microchip/Kconfig
+++ b/drivers/net/dsa/microchip/Kconfig
@@ -4,7 +4,7 @@ config NET_DSA_MICROCHIP_KSZ_COMMON
 menuconfig NET_DSA_MICROCHIP_KSZ9477
 	tristate "Microchip KSZ9477 series switch support"
 	depends on NET_DSA
-	select NET_DSA_TAG_KSZ
+	select NET_DSA_TAG_KSZ9477
 	select NET_DSA_MICROCHIP_KSZ_COMMON
 	help
 	  This driver adds support for Microchip KSZ9477 switch chips.
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 0684657fbf9a..57a146a0dd4a 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -262,7 +262,7 @@ static int ksz9477_reset_switch(struct ksz_device *dev)
 static enum dsa_tag_protocol ksz9477_get_tag_protocol(struct dsa_switch *ds,
 						      int port)
 {
-	return DSA_TAG_PROTO_KSZ;
+	return DSA_TAG_PROTO_KSZ9477;
 }
 
 static int ksz9477_phy_read16(struct dsa_switch *ds, int addr, int reg)
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 6ee2e24e0a6e..b3eefe8e18fd 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -36,7 +36,7 @@ enum dsa_tag_protocol {
 	DSA_TAG_PROTO_DSA,
 	DSA_TAG_PROTO_EDSA,
 	DSA_TAG_PROTO_GSWIP,
-	DSA_TAG_PROTO_KSZ,
+	DSA_TAG_PROTO_KSZ9477,
 	DSA_TAG_PROTO_LAN9303,
 	DSA_TAG_PROTO_MTK,
 	DSA_TAG_PROTO_QCA,
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 48c41918fb35..91e52973ee13 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -44,6 +44,10 @@ config NET_DSA_TAG_GSWIP
 config NET_DSA_TAG_KSZ
 	bool
 
+config NET_DSA_TAG_KSZ9477
+	bool
+	select NET_DSA_TAG_KSZ
+
 config NET_DSA_TAG_LAN9303
 	bool
 
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index a69c1790bbfc..aee909bcddc4 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -55,8 +55,8 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = {
 #ifdef CONFIG_NET_DSA_TAG_GSWIP
 	[DSA_TAG_PROTO_GSWIP] = &gswip_netdev_ops,
 #endif
-#ifdef CONFIG_NET_DSA_TAG_KSZ
-	[DSA_TAG_PROTO_KSZ] = &ksz_netdev_ops,
+#ifdef CONFIG_NET_DSA_TAG_KSZ9477
+	[DSA_TAG_PROTO_KSZ9477] = &ksz9477_netdev_ops,
 #endif
 #ifdef CONFIG_NET_DSA_TAG_LAN9303
 	[DSA_TAG_PROTO_LAN9303] = &lan9303_netdev_ops,
@@ -91,8 +91,8 @@ const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops)
 #ifdef CONFIG_NET_DSA_TAG_GSWIP
 		[DSA_TAG_PROTO_GSWIP] = "gswip",
 #endif
-#ifdef CONFIG_NET_DSA_TAG_KSZ
-		[DSA_TAG_PROTO_KSZ] = "ksz",
+#ifdef CONFIG_NET_DSA_TAG_KSZ9477
+		[DSA_TAG_PROTO_KSZ9477] = "ksz9477",
 #endif
 #ifdef CONFIG_NET_DSA_TAG_LAN9303
 		[DSA_TAG_PROTO_LAN9303] = "lan9303",
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 9e4fd04ab53c..026a05774bf7 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -210,7 +210,7 @@ extern const struct dsa_device_ops edsa_netdev_ops;
 extern const struct dsa_device_ops gswip_netdev_ops;
 
 /* tag_ksz.c */
-extern const struct dsa_device_ops ksz_netdev_ops;
+extern const struct dsa_device_ops ksz9477_netdev_ops;
 
 /* tag_lan9303.c */
 extern const struct dsa_device_ops lan9303_netdev_ops;
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 96411f70ab9f..c24a333e55bd 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -96,7 +96,7 @@ static struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-const struct dsa_device_ops ksz_netdev_ops = {
+const struct dsa_device_ops ksz9477_netdev_ops = {
 	.xmit	= ksz_xmit,
 	.rcv	= ksz_rcv,
 	.overhead = KSZ_INGRESS_TAG_LEN,
-- 
cgit v1.2.3


From bafe9ba7d908f6240b3ca898b167072c55502609 Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Sat, 15 Dec 2018 01:58:05 +0100
Subject: net: dsa: ksz: Factor out common tag code

Factor out common code from the tag_ksz , so that the code can be used
with other KSZ family switches which use differenly sized tags.

Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Cc: David S. Miller <davem@davemloft.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_ksz.c | 112 +++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 73 insertions(+), 39 deletions(-)

diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index c24a333e55bd..c98b53f691bd 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -14,34 +14,18 @@
 #include <net/dsa.h>
 #include "dsa_priv.h"
 
-/* For Ingress (Host -> KSZ), 2 bytes are added before FCS.
- * ---------------------------------------------------------------------------
- * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes)
- * ---------------------------------------------------------------------------
- * tag0 : Prioritization (not used now)
- * tag1 : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x10=port5)
- *
- * For Egress (KSZ -> Host), 1 byte is added before FCS.
- * ---------------------------------------------------------------------------
- * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes)
- * ---------------------------------------------------------------------------
- * tag0 : zero-based value represents port
- *	  (eg, 0x00=port1, 0x02=port3, 0x06=port7)
- */
+/* Typically only one byte is used for tail tag. */
+#define KSZ_EGRESS_TAG_LEN		1
 
-#define	KSZ_INGRESS_TAG_LEN	2
-#define	KSZ_EGRESS_TAG_LEN	1
-
-static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev)
+static struct sk_buff *ksz_common_xmit(struct sk_buff *skb,
+				       struct net_device *dev, int len)
 {
-	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct sk_buff *nskb;
 	int padlen;
-	u8 *tag;
 
 	padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len;
 
-	if (skb_tailroom(skb) >= padlen + KSZ_INGRESS_TAG_LEN) {
+	if (skb_tailroom(skb) >= padlen + len) {
 		/* Let dsa_slave_xmit() free skb */
 		if (__skb_put_padto(skb, skb->len + padlen, false))
 			return NULL;
@@ -49,7 +33,7 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev)
 		nskb = skb;
 	} else {
 		nskb = alloc_skb(NET_IP_ALIGN + skb->len +
-				 padlen + KSZ_INGRESS_TAG_LEN, GFP_ATOMIC);
+				 padlen + len, GFP_ATOMIC);
 		if (!nskb)
 			return NULL;
 		skb_reserve(nskb, NET_IP_ALIGN);
@@ -70,34 +54,84 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev)
 		consume_skb(skb);
 	}
 
-	tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN);
-	tag[0] = 0;
-	tag[1] = 1 << dp->index; /* destination port */
-
 	return nskb;
 }
 
-static struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev,
-			       struct packet_type *pt)
+static struct sk_buff *ksz_common_rcv(struct sk_buff *skb,
+				      struct net_device *dev,
+				      unsigned int port, unsigned int len)
 {
-	u8 *tag;
-	int source_port;
+	skb->dev = dsa_master_find_slave(dev, 0, port);
+	if (!skb->dev)
+		return NULL;
 
-	tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
+	pskb_trim_rcsum(skb, skb->len - len);
 
-	source_port = tag[0] & 7;
+	return skb;
+}
 
-	skb->dev = dsa_master_find_slave(dev, 0, source_port);
-	if (!skb->dev)
+/*
+ * For Ingress (Host -> KSZ9477), 2 bytes are added before FCS.
+ * ---------------------------------------------------------------------------
+ * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes)
+ * ---------------------------------------------------------------------------
+ * tag0 : Prioritization (not used now)
+ * tag1 : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x10=port5)
+ *
+ * For Egress (KSZ9477 -> Host), 1 byte is added before FCS.
+ * ---------------------------------------------------------------------------
+ * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes)
+ * ---------------------------------------------------------------------------
+ * tag0 : zero-based value represents port
+ *	  (eg, 0x00=port1, 0x02=port3, 0x06=port7)
+ */
+
+#define KSZ9477_INGRESS_TAG_LEN		2
+#define KSZ9477_PTP_TAG_LEN		4
+#define KSZ9477_PTP_TAG_INDICATION	0x80
+
+#define KSZ9477_TAIL_TAG_OVERRIDE	BIT(9)
+#define KSZ9477_TAIL_TAG_LOOKUP		BIT(10)
+
+static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
+				    struct net_device *dev)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct sk_buff *nskb;
+	u16 *tag;
+	u8 *addr;
+
+	nskb = ksz_common_xmit(skb, dev, KSZ9477_INGRESS_TAG_LEN);
+	if (!nskb)
 		return NULL;
 
-	pskb_trim_rcsum(skb, skb->len - KSZ_EGRESS_TAG_LEN);
+	/* Tag encoding */
+	tag = skb_put(nskb, KSZ9477_INGRESS_TAG_LEN);
+	addr = skb_mac_header(nskb);
 
-	return skb;
+	*tag = BIT(dp->index);
+	*tag = cpu_to_be16(*tag);
+
+	return nskb;
+}
+
+static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev,
+				   struct packet_type *pt)
+{
+	/* Tag decoding */
+	u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
+	unsigned int port = tag[0] & 7;
+	unsigned int len = KSZ_EGRESS_TAG_LEN;
+
+	/* Extra 4-bytes PTP timestamp */
+	if (tag[0] & KSZ9477_PTP_TAG_INDICATION)
+		len += KSZ9477_PTP_TAG_LEN;
+
+	return ksz_common_rcv(skb, dev, port, len);
 }
 
 const struct dsa_device_ops ksz9477_netdev_ops = {
-	.xmit	= ksz_xmit,
-	.rcv	= ksz_rcv,
-	.overhead = KSZ_INGRESS_TAG_LEN,
+	.xmit	= ksz9477_xmit,
+	.rcv	= ksz9477_rcv,
+	.overhead = KSZ9477_INGRESS_TAG_LEN,
 };
-- 
cgit v1.2.3


From 8a75b9d4c9d32c88b487bd98bf8019f029215165 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Sat, 15 Dec 2018 01:58:06 +0100
Subject: net: dsa: ksz: Add STP multicast handling

In case the destination address is link local, add override bit into the
switch tag to let such a packet through the switch even if the port is
blocked.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Cc: David S. Miller <davem@davemloft.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_ksz.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index c98b53f691bd..da71b9e2af52 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -110,6 +110,10 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
 	addr = skb_mac_header(nskb);
 
 	*tag = BIT(dp->index);
+
+	if (is_link_local_ether_addr(addr))
+		*tag |= KSZ9477_TAIL_TAG_OVERRIDE;
+
 	*tag = cpu_to_be16(*tag);
 
 	return nskb;
-- 
cgit v1.2.3


From 5b2f94b27622d5b92d1cebf4bb5a627db4444607 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Sat, 15 Dec 2018 22:35:08 -0800
Subject: net: rtnetlink: support for fdb get

This patch adds support for fdb get similar to
route get. arguments can be any of the following (similar to fdb add/del/dump):
[bridge, mac, vlan] or
[bridge_port, mac, vlan, flags=[NTF_MASTER]] or
[dev, mac, [vni|vlan], flags=[NTF_SELF]]

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |   7 +-
 net/core/rtnetlink.c      | 168 +++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 173 insertions(+), 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 811632d4d8b1..1377d085ef99 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1387,7 +1387,12 @@ struct net_device_ops {
 						struct net_device *dev,
 						struct net_device *filter_dev,
 						int *idx);
-
+	int			(*ndo_fdb_get)(struct sk_buff *skb,
+					       struct nlattr *tb[],
+					       struct net_device *dev,
+					       const unsigned char *addr,
+					       u16 vid, u32 portid, u32 seq,
+					       struct netlink_ext_ack *extack);
 	int			(*ndo_bridge_setlink)(struct net_device *dev,
 						      struct nlmsghdr *nlh,
 						      u16 flags,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f8bdb8adab2c..baf2685b4da2 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3460,6 +3460,18 @@ void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change,
 			   new_nsid, new_ifindex);
 }
 
+static const struct nla_policy nda_policy[NDA_MAX+1] = {
+	[NDA_DST]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+	[NDA_LLADDR]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+	[NDA_CACHEINFO]		= { .len = sizeof(struct nda_cacheinfo) },
+	[NDA_PROBES]		= { .type = NLA_U32 },
+	[NDA_VLAN]		= { .type = NLA_U16 },
+	[NDA_PORT]		= { .type = NLA_U16 },
+	[NDA_VNI]		= { .type = NLA_U32 },
+	[NDA_IFINDEX]		= { .type = NLA_U32 },
+	[NDA_MASTER]		= { .type = NLA_U32 },
+};
+
 static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
 				   struct net_device *dev,
 				   u8 *addr, u16 vid, u32 pid, u32 seq,
@@ -4021,6 +4033,160 @@ out:
 	return skb->len;
 }
 
+static int valid_fdb_get_strict(const struct nlmsghdr *nlh,
+				struct nlattr **tb, u8 *ndm_flags,
+				int *br_idx, int *brport_idx, u8 **addr,
+				u16 *vid, struct netlink_ext_ack *extack)
+{
+	struct ndmsg *ndm;
+	int err, i;
+
+	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+		NL_SET_ERR_MSG(extack, "Invalid header for fdb get request");
+		return -EINVAL;
+	}
+
+	ndm = nlmsg_data(nlh);
+	if (ndm->ndm_pad1  || ndm->ndm_pad2  || ndm->ndm_state ||
+	    ndm->ndm_type) {
+		NL_SET_ERR_MSG(extack, "Invalid values in header for fdb get request");
+		return -EINVAL;
+	}
+
+	if (ndm->ndm_flags & ~(NTF_MASTER | NTF_SELF)) {
+		NL_SET_ERR_MSG(extack, "Invalid flags in header for fdb get request");
+		return -EINVAL;
+	}
+
+	err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
+				 nda_policy, extack);
+	if (err < 0)
+		return err;
+
+	*ndm_flags = ndm->ndm_flags;
+	*brport_idx = ndm->ndm_ifindex;
+	for (i = 0; i <= NDA_MAX; ++i) {
+		if (!tb[i])
+			continue;
+
+		switch (i) {
+		case NDA_MASTER:
+			*br_idx = nla_get_u32(tb[i]);
+			break;
+		case NDA_LLADDR:
+			if (nla_len(tb[i]) != ETH_ALEN) {
+				NL_SET_ERR_MSG(extack, "Invalid address in fdb get request");
+				return -EINVAL;
+			}
+			*addr = nla_data(tb[i]);
+			break;
+		case NDA_VLAN:
+			err = fdb_vid_parse(tb[i], vid, extack);
+			if (err)
+				return err;
+			break;
+		case NDA_VNI:
+			break;
+		default:
+			NL_SET_ERR_MSG(extack, "Unsupported attribute in fdb get request");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int rtnl_fdb_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+			struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = NULL, *br_dev = NULL;
+	const struct net_device_ops *ops = NULL;
+	struct net *net = sock_net(in_skb->sk);
+	struct nlattr *tb[NDA_MAX + 1];
+	struct sk_buff *skb;
+	int brport_idx = 0;
+	u8 ndm_flags = 0;
+	int br_idx = 0;
+	u8 *addr = NULL;
+	u16 vid = 0;
+	int err;
+
+	err = valid_fdb_get_strict(nlh, tb, &ndm_flags, &br_idx,
+				   &brport_idx, &addr, &vid, extack);
+	if (err < 0)
+		return err;
+
+	if (brport_idx) {
+		dev = __dev_get_by_index(net, brport_idx);
+		if (!dev) {
+			NL_SET_ERR_MSG(extack, "Unknown device ifindex");
+			return -ENODEV;
+		}
+	}
+
+	if (br_idx) {
+		if (dev) {
+			NL_SET_ERR_MSG(extack, "Master and device are mutually exclusive");
+			return -EINVAL;
+		}
+
+		br_dev = __dev_get_by_index(net, br_idx);
+		if (!br_dev) {
+			NL_SET_ERR_MSG(extack, "Invalid master ifindex");
+			return -EINVAL;
+		}
+		ops = br_dev->netdev_ops;
+	}
+
+	if (dev) {
+		if (!ndm_flags || (ndm_flags & NTF_MASTER)) {
+			if (!(dev->priv_flags & IFF_BRIDGE_PORT)) {
+				NL_SET_ERR_MSG(extack, "Device is not a bridge port");
+				return -EINVAL;
+			}
+			br_dev = netdev_master_upper_dev_get(dev);
+			if (!br_dev) {
+				NL_SET_ERR_MSG(extack, "Master of device not found");
+				return -EINVAL;
+			}
+			ops = br_dev->netdev_ops;
+		} else {
+			if (!(ndm_flags & NTF_SELF)) {
+				NL_SET_ERR_MSG(extack, "Missing NTF_SELF");
+				return -EINVAL;
+			}
+			ops = dev->netdev_ops;
+		}
+	}
+
+	if (!br_dev && !dev) {
+		NL_SET_ERR_MSG(extack, "No device specified");
+		return -ENODEV;
+	}
+
+	if (!ops || !ops->ndo_fdb_get) {
+		NL_SET_ERR_MSG(extack, "Fdb get operation not supported by device");
+		return -EOPNOTSUPP;
+	}
+
+	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	if (br_dev)
+		dev = br_dev;
+	err = ops->ndo_fdb_get(skb, tb, dev, addr, vid,
+			       NETLINK_CB(in_skb).portid,
+			       nlh->nlmsg_seq, extack);
+	if (err)
+		goto out;
+
+	return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
+out:
+	kfree_skb(skb);
+	return err;
+}
+
 static int brport_nla_put_flag(struct sk_buff *skb, u32 flags, u32 mask,
 			       unsigned int attrnum, unsigned int flag)
 {
@@ -5081,7 +5247,7 @@ void __init rtnetlink_init(void)
 
 	rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, 0);
 	rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, 0);
-	rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, 0);
+	rtnl_register(PF_BRIDGE, RTM_GETNEIGH, rtnl_fdb_get, rtnl_fdb_dump, 0);
 
 	rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, 0);
 	rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, 0);
-- 
cgit v1.2.3


From 4767456212f8cd70775dc55d9bc72e184ff84642 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Sat, 15 Dec 2018 22:35:09 -0800
Subject: bridge: support for ndo_fdb_get

This patch implements ndo_fdb_get for the bridge
fdb.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_device.c  |  1 +
 net/bridge/br_fdb.c     | 26 ++++++++++++++++++++++++++
 net/bridge/br_private.h |  3 +++
 3 files changed, 30 insertions(+)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 9f41a5d4da3f..013323b6dbe4 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -403,6 +403,7 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_fdb_add		 = br_fdb_add,
 	.ndo_fdb_del		 = br_fdb_delete,
 	.ndo_fdb_dump		 = br_fdb_dump,
+	.ndo_fdb_get		 = br_fdb_get,
 	.ndo_bridge_getlink	 = br_getlink,
 	.ndo_bridge_setlink	 = br_setlink,
 	.ndo_bridge_dellink	 = br_dellink,
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 38b1d0dd0529..fe3c758791ca 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -773,6 +773,32 @@ skip:
 	return err;
 }
 
+int br_fdb_get(struct sk_buff *skb,
+	       struct nlattr *tb[],
+	       struct net_device *dev,
+	       const unsigned char *addr,
+	       u16 vid, u32 portid, u32 seq,
+	       struct netlink_ext_ack *extack)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct net_bridge_fdb_entry *f;
+	int err = 0;
+
+	rcu_read_lock();
+	f = br_fdb_find_rcu(br, addr, vid);
+	if (!f) {
+		NL_SET_ERR_MSG(extack, "Fdb entry not found");
+		err = -ENOENT;
+		goto errout;
+	}
+
+	err = fdb_fill_info(skb, br, f, portid, seq,
+			    RTM_NEWNEIGH, 0);
+errout:
+	rcu_read_unlock();
+	return err;
+}
+
 /* Update (create or replace) forwarding database entry */
 static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
 			 const u8 *addr, u16 state, u16 flags, u16 vid,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index ff3dfb2a78b8..d240b3e7919f 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -575,6 +575,9 @@ int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev,
 	       const unsigned char *addr, u16 vid, u16 nlh_flags);
 int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		struct net_device *dev, struct net_device *fdev, int *idx);
+int br_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev,
+	       const unsigned char *addr, u16 vid, u32 portid, u32 seq,
+	       struct netlink_ext_ack *extack);
 int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p);
 void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p);
 int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
-- 
cgit v1.2.3


From 474c3c896ff29fbd69b13d99f2f66dd6da3b6634 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Sat, 15 Dec 2018 22:35:10 -0800
Subject: vxlan: support for ndo_fdb_get

This patch implements ndo_fdb_get for a vxlan device.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 49d4b5854c62..71c3b7b6b1ab 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1152,6 +1152,39 @@ out:
 	return err;
 }
 
+static int vxlan_fdb_get(struct sk_buff *skb,
+			 struct nlattr *tb[],
+			 struct net_device *dev,
+			 const unsigned char *addr,
+			 u16 vid, u32 portid, u32 seq,
+			 struct netlink_ext_ack *extack)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_fdb *f;
+	__be32 vni;
+	int err;
+
+	if (tb[NDA_VNI])
+		vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI]));
+	else
+		vni = vxlan->default_dst.remote_vni;
+
+	rcu_read_lock();
+
+	f = __vxlan_find_mac(vxlan, addr, vni);
+	if (!f) {
+		NL_SET_ERR_MSG(extack, "Fdb entry not found");
+		err = -ENOENT;
+		goto errout;
+	}
+
+	err = vxlan_fdb_info(skb, vxlan, f, portid, seq,
+			     RTM_NEWNEIGH, 0, first_remote_rcu(f));
+errout:
+	rcu_read_unlock();
+	return err;
+}
+
 /* Watch incoming packets to learn mapping between Ethernet address
  * and Tunnel endpoint.
  * Return true if packet is bogus and should be dropped.
@@ -2805,6 +2838,7 @@ static const struct net_device_ops vxlan_netdev_ether_ops = {
 	.ndo_fdb_add		= vxlan_fdb_add,
 	.ndo_fdb_del		= vxlan_fdb_delete,
 	.ndo_fdb_dump		= vxlan_fdb_dump,
+	.ndo_fdb_get		= vxlan_fdb_get,
 	.ndo_fill_metadata_dst	= vxlan_fill_metadata_dst,
 };
 
-- 
cgit v1.2.3


From 31d31951d00a3ec6335dad36cd49a4767e2bb304 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Sat, 15 Dec 2018 22:35:11 -0800
Subject: selftests: net: rtnetlink.sh: add fdb get test

tests the below three cases of bridge fdb get:
[bridge, mac, vlan]
[bridge_port, mac, vlan, flags=[NTF_MASTER]]
[vxlandev, mac, flags=NTF_SELF]

depends on iproute2 support for bridge fdb get.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 53 ++++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index e101af52d1d6..bb3436f8807f 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -955,6 +955,58 @@ kci_test_ip6erspan()
 	ip netns del "$testns"
 }
 
+kci_test_fdb_get()
+{
+	IP="ip -netns testns"
+	BRIDGE="bridge -netns testns"
+	brdev="test-br0"
+	vxlandev="vxlan10"
+	test_mac=de:ad:be:ef:13:37
+	localip="10.0.2.2"
+	dstip="10.0.2.3"
+	ret=0
+
+	bridge fdb help 2>&1 |grep -q 'bridge fdb get'
+	if [ $? -ne 0 ];then
+		echo "SKIP: fdb get tests: iproute2 too old"
+		return $ksft_skip
+	fi
+
+	ip netns add testns
+	if [ $? -ne 0 ]; then
+		echo "SKIP fdb get tests: cannot add net namespace $testns"
+		return $ksft_skip
+	fi
+
+	$IP link add "$vxlandev" type vxlan id 10 local $localip \
+                dstport 4789 2>/dev/null
+	check_err $?
+	$IP link add name "$brdev" type bridge &>/dev/null
+	check_err $?
+	$IP link set dev "$vxlandev" master "$brdev" &>/dev/null
+	check_err $?
+	$BRIDGE fdb add $test_mac dev "$vxlandev" master &>/dev/null
+	check_err $?
+	$BRIDGE fdb add $test_mac dev "$vxlandev" dst $dstip self &>/dev/null
+	check_err $?
+
+	$BRIDGE fdb get $test_mac brport "$vxlandev" 2>/dev/null | grep -q "dev $vxlandev master $brdev"
+	check_err $?
+	$BRIDGE fdb get $test_mac br "$brdev" 2>/dev/null | grep -q "dev $vxlandev master $brdev"
+	check_err $?
+	$BRIDGE fdb get $test_mac dev "$vxlandev" self 2>/dev/null | grep -q "dev $vxlandev dst $dstip"
+	check_err $?
+
+	ip netns del testns &>/dev/null
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: bridge fdb get"
+		return 1
+	fi
+
+	echo "PASS: bridge fdb get"
+}
+
 kci_test_rtnl()
 {
 	kci_add_dummy
@@ -979,6 +1031,7 @@ kci_test_rtnl()
 	kci_test_macsec
 	kci_test_ipsec
 	kci_test_ipsec_offload
+	kci_test_fdb_get
 
 	kci_del_dummy
 }
-- 
cgit v1.2.3


From 418089a850c751ada5e3535d0e71c3312fe3c432 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:24 +0000
Subject: mlxsw: reg: Add Policy Engine Algorithmic Bloom Filter Entries
 Register

Bloom filter is a bit vector which allows the HW a fast lookup on a
small size bit vector, that may reduce the number of lookups on the
A-TCAM memory. PEABFE register allows setting values to the bits of
the bit vector mentioned above.
Add the register to be later used in A-TCAM optimizations.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 67 +++++++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index ace3a897b3f0..8e1f7ae4342a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3095,6 +3095,72 @@ static inline void mlxsw_reg_pererp_pack(char *payload, u16 region_id,
 	mlxsw_reg_pererp_master_rp_id_set(payload, master_rp_id);
 }
 
+/* PEABFE - Policy-Engine Algorithmic Bloom Filter Entries Register
+ * ----------------------------------------------------------------
+ * This register configures the Bloom filter entries.
+ */
+#define MLXSW_REG_PEABFE_ID 0x3022
+#define MLXSW_REG_PEABFE_BASE_LEN 0x10
+#define MLXSW_REG_PEABFE_BF_REC_LEN 0x4
+#define MLXSW_REG_PEABFE_BF_REC_MAX_COUNT 256
+#define MLXSW_REG_PEABFE_LEN (MLXSW_REG_PEABFE_BASE_LEN + \
+			      MLXSW_REG_PEABFE_BF_REC_LEN * \
+			      MLXSW_REG_PEABFE_BF_REC_MAX_COUNT)
+
+MLXSW_REG_DEFINE(peabfe, MLXSW_REG_PEABFE_ID, MLXSW_REG_PEABFE_LEN);
+
+/* reg_peabfe_size
+ * Number of BF entries to be updated.
+ * Range 1..256
+ * Access: Op
+ */
+MLXSW_ITEM32(reg, peabfe, size, 0x00, 0, 9);
+
+/* reg_peabfe_bf_entry_state
+ * Bloom filter state
+ * 0 - Clear
+ * 1 - Set
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, peabfe, bf_entry_state,
+		     MLXSW_REG_PEABFE_BASE_LEN,	31, 1,
+		     MLXSW_REG_PEABFE_BF_REC_LEN, 0x00, false);
+
+/* reg_peabfe_bf_entry_bank
+ * Bloom filter bank ID
+ * Range 0..cap_max_erp_table_banks-1
+ * Access: Index
+ */
+MLXSW_ITEM32_INDEXED(reg, peabfe, bf_entry_bank,
+		     MLXSW_REG_PEABFE_BASE_LEN,	24, 4,
+		     MLXSW_REG_PEABFE_BF_REC_LEN, 0x00, false);
+
+/* reg_peabfe_bf_entry_index
+ * Bloom filter entry index
+ * Range 0..2^cap_max_bf_log-1
+ * Access: Index
+ */
+MLXSW_ITEM32_INDEXED(reg, peabfe, bf_entry_index,
+		     MLXSW_REG_PEABFE_BASE_LEN,	0, 24,
+		     MLXSW_REG_PEABFE_BF_REC_LEN, 0x00, false);
+
+static inline void mlxsw_reg_peabfe_pack(char *payload)
+{
+	MLXSW_REG_ZERO(peabfe, payload);
+}
+
+static inline void mlxsw_reg_peabfe_rec_pack(char *payload, int rec_index,
+					     u8 state, u8 bank, u32 bf_index)
+{
+	u8 num_rec = mlxsw_reg_peabfe_size_get(payload);
+
+	if (rec_index >= num_rec)
+		mlxsw_reg_peabfe_size_set(payload, rec_index + 1);
+	mlxsw_reg_peabfe_bf_entry_state_set(payload, rec_index, state);
+	mlxsw_reg_peabfe_bf_entry_bank_set(payload, rec_index, bank);
+	mlxsw_reg_peabfe_bf_entry_index_set(payload, rec_index, bf_index);
+}
+
 /* IEDR - Infrastructure Entry Delete Register
  * ----------------------------------------------------
  * This register is used for deleting entries from the entry tables.
@@ -9608,6 +9674,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(pemrbt),
 	MLXSW_REG(ptce2),
 	MLXSW_REG(perpt),
+	MLXSW_REG(peabfe),
 	MLXSW_REG(perar),
 	MLXSW_REG(ptce3),
 	MLXSW_REG(percr),
-- 
cgit v1.2.3


From 944068582fe6e69fd76cb7b90ba2fd5cac04d78e Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:25 +0000
Subject: mlxsw: resources: Add Spectrum-2 Bloom filter resource

Add the maximum Bloom filter logarithmic size per eRP table bank.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/resources.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index 99b341539870..b8b3a01c2a9e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -41,6 +41,7 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_ACL_ERPT_ENTRIES_4KB,
 	MLXSW_RES_ID_ACL_ERPT_ENTRIES_8KB,
 	MLXSW_RES_ID_ACL_ERPT_ENTRIES_12KB,
+	MLXSW_RES_ID_ACL_MAX_BF_LOG,
 	MLXSW_RES_ID_MAX_CPU_POLICERS,
 	MLXSW_RES_ID_MAX_VRS,
 	MLXSW_RES_ID_MAX_RIFS,
@@ -93,6 +94,7 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_4KB] = 0x2951,
 	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_8KB] = 0x2952,
 	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_12KB] = 0x2953,
+	[MLXSW_RES_ID_ACL_MAX_BF_LOG] = 0x2960,
 	[MLXSW_RES_ID_MAX_CPU_POLICERS] = 0x2A13,
 	[MLXSW_RES_ID_MAX_VRS] = 0x2C01,
 	[MLXSW_RES_ID_MAX_RIFS] = 0x2C02,
-- 
cgit v1.2.3


From 0487cfba866a7f985c51ce7553d37439e10e71c1 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:26 +0000
Subject: mlxsw: spectrum_acl: Introduce Bloom filter

Lay the foundations for Bloom filter handling. Introduce a new file for
Bloom filter actions.

Add struct mlxsw_sp_acl_bf to struct mlxsw_sp_acl_erp_core and initialize
the Bloom filter data structure. Also take care of proper destruction when
terminating.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Makefile       |  2 +-
 .../mellanox/mlxsw/spectrum_acl_bloom_filter.c     | 42 ++++++++++++++++++++++
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 10 ++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |  6 ++++
 4 files changed, 59 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 1f77e97e2d7a..bbf45f10c208 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -20,7 +20,7 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_acl_tcam.o spectrum_acl_ctcam.o \
 				   spectrum_acl_atcam.o spectrum_acl_erp.o \
 				   spectrum1_acl_tcam.o spectrum2_acl_tcam.o \
-				   spectrum_acl.o \
+				   spectrum_acl_bloom_filter.o spectrum_acl.o \
 				   spectrum_flower.o spectrum_cnt.o \
 				   spectrum_fid.o spectrum_ipip.o \
 				   spectrum_acl_flex_actions.o \
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
new file mode 100644
index 000000000000..4685b730e703
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/refcount.h>
+
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+
+struct mlxsw_sp_acl_bf {
+	unsigned int bank_size;
+	refcount_t refcnt[0];
+};
+
+struct mlxsw_sp_acl_bf *
+mlxsw_sp_acl_bf_init(struct mlxsw_sp *mlxsw_sp, unsigned int num_erp_banks)
+{
+	struct mlxsw_sp_acl_bf *bf;
+	unsigned int bf_bank_size;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_BF_LOG))
+		return ERR_PTR(-EIO);
+
+	/* Bloom filter size per erp_table_bank
+	 * is 2^ACL_MAX_BF_LOG
+	 */
+	bf_bank_size = 1 << MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_BF_LOG);
+	bf = kzalloc(sizeof(*bf) + bf_bank_size * num_erp_banks *
+		     sizeof(*bf->refcnt), GFP_KERNEL);
+	if (!bf)
+		return ERR_PTR(-ENOMEM);
+
+	bf->bank_size = bf_bank_size;
+	return bf;
+}
+
+void mlxsw_sp_acl_bf_fini(struct mlxsw_sp_acl_bf *bf)
+{
+	kfree(bf);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index d9a4b7e8434b..bc3c731f06a1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -24,6 +24,7 @@ struct mlxsw_sp_acl_erp_core {
 	unsigned int erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX + 1];
 	struct gen_pool *erp_tables;
 	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_acl_bf *bf;
 	unsigned int num_erp_banks;
 };
 
@@ -1320,6 +1321,12 @@ static int mlxsw_sp_acl_erp_tables_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_gen_pool_add;
 
+	erp_core->bf = mlxsw_sp_acl_bf_init(mlxsw_sp, erp_core->num_erp_banks);
+	if (IS_ERR(erp_core->bf)) {
+		err = PTR_ERR(erp_core->bf);
+		goto err_bf_init;
+	}
+
 	/* Different regions require masks of different sizes */
 	err = mlxsw_sp_acl_erp_tables_sizes_query(mlxsw_sp, erp_core);
 	if (err)
@@ -1328,6 +1335,8 @@ static int mlxsw_sp_acl_erp_tables_init(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 
 err_erp_tables_sizes_query:
+	mlxsw_sp_acl_bf_fini(erp_core->bf);
+err_bf_init:
 err_gen_pool_add:
 	gen_pool_destroy(erp_core->erp_tables);
 	return err;
@@ -1336,6 +1345,7 @@ err_gen_pool_add:
 static void mlxsw_sp_acl_erp_tables_fini(struct mlxsw_sp *mlxsw_sp,
 					 struct mlxsw_sp_acl_erp_core *erp_core)
 {
+	mlxsw_sp_acl_bf_fini(erp_core->bf);
 	gen_pool_destroy(erp_core->erp_tables);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 95929b9039ec..c65c902cb56a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -258,4 +258,10 @@ int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp,
 void mlxsw_sp_acl_erps_fini(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_atcam *atcam);
 
+struct mlxsw_sp_acl_bf;
+
+struct mlxsw_sp_acl_bf *
+mlxsw_sp_acl_bf_init(struct mlxsw_sp *mlxsw_sp, unsigned int num_erp_banks);
+void mlxsw_sp_acl_bf_fini(struct mlxsw_sp_acl_bf *bf);
+
 #endif
-- 
cgit v1.2.3


From 7585cacdb978a0cd8d47bff9e5dcecdc9d903add Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:28 +0000
Subject: mlxsw: spectrum_acl: Add Bloom filter handling

Spectrum-2 HW uses Bloom filter in order to skip lookups on specific
eRPs. It uses crc-16-Msbit-first calculation over a specific layout
of a rule's key fields combined with eRP ID as well as region ID.
Per potential lookup, iff the Bloom filter entry of the calculated
index is empty, then the lookup can be skipped. Hence, the mlxsw
driver should update the Bloom filter entry per each rule insertion
or deletion when rules are part of an eRP.

Add functions for adding and deleting entries in the Bloom filter.
In order to do so also add crc-16 computation based on the specific
Spectrum-2 polynomial and a function for encoding the crc-16 input
in the manner dictated by HW implementation.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlxsw/spectrum_acl_bloom_filter.c     | 207 +++++++++++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |  12 ++
 2 files changed, 219 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
index 4685b730e703..505b87846acc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
@@ -14,6 +14,213 @@ struct mlxsw_sp_acl_bf {
 	refcount_t refcnt[0];
 };
 
+/* Bloom filter uses a crc-16 hash over chunks of data which contain 4 key
+ * blocks, eRP ID and region ID. In Spectrum-2, region key is combined of up to
+ * 12 key blocks, so there can be up to 3 chunks in the Bloom filter key,
+ * depending on the actual number of key blocks used in the region.
+ * The layout of the Bloom filter key is as follows:
+ *
+ * +-------------------------+------------------------+------------------------+
+ * | Chunk 2 Key blocks 11-8 | Chunk 1 Key blocks 7-4 | Chunk 0 Key blocks 3-0 |
+ * +-------------------------+------------------------+------------------------+
+ */
+#define MLXSW_BLOOM_KEY_CHUNKS 3
+#define MLXSW_BLOOM_KEY_LEN 69
+
+/* Each chunk size is 23 bytes. 18 bytes of it contain 4 key blocks, each is
+ * 36 bits, 2 bytes which hold eRP ID and region ID, and 3 bytes of zero
+ * padding.
+ * The layout of each chunk is as follows:
+ *
+ * +---------+----------------------+-----------------------------------+
+ * | 3 bytes |        2 bytes       |              18 bytes             |
+ * +---------+-----------+----------+-----------------------------------+
+ * | 183:158 |  157:148  | 147:144  |               143:0               |
+ * +---------+-----------+----------+-----------------------------------+
+ * |    0    | region ID |  eRP ID  |      4 Key blocks (18 Bytes)      |
+ * +---------+-----------+----------+-----------------------------------+
+ */
+#define MLXSW_BLOOM_CHUNK_PAD_BYTES 3
+#define MLXSW_BLOOM_CHUNK_KEY_BYTES 18
+#define MLXSW_BLOOM_KEY_CHUNK_BYTES 23
+
+/* The offset of the key block within a chunk is 5 bytes as it comes after
+ * 3 bytes of zero padding and 16 bits of region ID and eRP ID.
+ */
+#define MLXSW_BLOOM_CHUNK_KEY_OFFSET 5
+
+/* Each chunk contains 4 key blocks. Chunk 2 uses key blocks 11-8,
+ * and we need to populate it with 4 key blocks copied from the entry encoded
+ * key. Since the encoded key contains a padding, key block 11 starts at offset
+ * 2. block 7 that is used in chunk 1 starts at offset 20 as 4 key blocks take
+ * 18 bytes.
+ * This array defines key offsets for easy access when copying key blocks from
+ * entry key to Bloom filter chunk.
+ */
+static const u8 chunk_key_offsets[MLXSW_BLOOM_KEY_CHUNKS] = {2, 20, 38};
+
+/* This table is just the CRC of each possible byte. It is
+ * computed, Msbit first, for the Bloom filter polynomial
+ * which is 0x8529 (1 + x^3 + x^5 + x^8 + x^10 + x^15 and
+ * the implicit x^16).
+ */
+static const u16 mlxsw_sp_acl_bf_crc_tab[256] = {
+0x0000, 0x8529, 0x8f7b, 0x0a52, 0x9bdf, 0x1ef6, 0x14a4, 0x918d,
+0xb297, 0x37be, 0x3dec, 0xb8c5, 0x2948, 0xac61, 0xa633, 0x231a,
+0xe007, 0x652e, 0x6f7c, 0xea55, 0x7bd8, 0xfef1, 0xf4a3, 0x718a,
+0x5290, 0xd7b9, 0xddeb, 0x58c2, 0xc94f, 0x4c66, 0x4634, 0xc31d,
+0x4527, 0xc00e, 0xca5c, 0x4f75, 0xdef8, 0x5bd1, 0x5183, 0xd4aa,
+0xf7b0, 0x7299, 0x78cb, 0xfde2, 0x6c6f, 0xe946, 0xe314, 0x663d,
+0xa520, 0x2009, 0x2a5b, 0xaf72, 0x3eff, 0xbbd6, 0xb184, 0x34ad,
+0x17b7, 0x929e, 0x98cc, 0x1de5, 0x8c68, 0x0941, 0x0313, 0x863a,
+0x8a4e, 0x0f67, 0x0535, 0x801c, 0x1191, 0x94b8, 0x9eea, 0x1bc3,
+0x38d9, 0xbdf0, 0xb7a2, 0x328b, 0xa306, 0x262f, 0x2c7d, 0xa954,
+0x6a49, 0xef60, 0xe532, 0x601b, 0xf196, 0x74bf, 0x7eed, 0xfbc4,
+0xd8de, 0x5df7, 0x57a5, 0xd28c, 0x4301, 0xc628, 0xcc7a, 0x4953,
+0xcf69, 0x4a40, 0x4012, 0xc53b, 0x54b6, 0xd19f, 0xdbcd, 0x5ee4,
+0x7dfe, 0xf8d7, 0xf285, 0x77ac, 0xe621, 0x6308, 0x695a, 0xec73,
+0x2f6e, 0xaa47, 0xa015, 0x253c, 0xb4b1, 0x3198, 0x3bca, 0xbee3,
+0x9df9, 0x18d0, 0x1282, 0x97ab, 0x0626, 0x830f, 0x895d, 0x0c74,
+0x91b5, 0x149c, 0x1ece, 0x9be7, 0x0a6a, 0x8f43, 0x8511, 0x0038,
+0x2322, 0xa60b, 0xac59, 0x2970, 0xb8fd, 0x3dd4, 0x3786, 0xb2af,
+0x71b2, 0xf49b, 0xfec9, 0x7be0, 0xea6d, 0x6f44, 0x6516, 0xe03f,
+0xc325, 0x460c, 0x4c5e, 0xc977, 0x58fa, 0xddd3, 0xd781, 0x52a8,
+0xd492, 0x51bb, 0x5be9, 0xdec0, 0x4f4d, 0xca64, 0xc036, 0x451f,
+0x6605, 0xe32c, 0xe97e, 0x6c57, 0xfdda, 0x78f3, 0x72a1, 0xf788,
+0x3495, 0xb1bc, 0xbbee, 0x3ec7, 0xaf4a, 0x2a63, 0x2031, 0xa518,
+0x8602, 0x032b, 0x0979, 0x8c50, 0x1ddd, 0x98f4, 0x92a6, 0x178f,
+0x1bfb, 0x9ed2, 0x9480, 0x11a9, 0x8024, 0x050d, 0x0f5f, 0x8a76,
+0xa96c, 0x2c45, 0x2617, 0xa33e, 0x32b3, 0xb79a, 0xbdc8, 0x38e1,
+0xfbfc, 0x7ed5, 0x7487, 0xf1ae, 0x6023, 0xe50a, 0xef58, 0x6a71,
+0x496b, 0xcc42, 0xc610, 0x4339, 0xd2b4, 0x579d, 0x5dcf, 0xd8e6,
+0x5edc, 0xdbf5, 0xd1a7, 0x548e, 0xc503, 0x402a, 0x4a78, 0xcf51,
+0xec4b, 0x6962, 0x6330, 0xe619, 0x7794, 0xf2bd, 0xf8ef, 0x7dc6,
+0xbedb, 0x3bf2, 0x31a0, 0xb489, 0x2504, 0xa02d, 0xaa7f, 0x2f56,
+0x0c4c, 0x8965, 0x8337, 0x061e, 0x9793, 0x12ba, 0x18e8, 0x9dc1,
+};
+
+static u16 mlxsw_sp_acl_bf_crc_byte(u16 crc, u8 c)
+{
+	return (crc << 8) ^ mlxsw_sp_acl_bf_crc_tab[(crc >> 8) ^ c];
+}
+
+static u16 mlxsw_sp_acl_bf_crc(const u8 *buffer, size_t len)
+{
+	u16 crc = 0;
+
+	while (len--)
+		crc = mlxsw_sp_acl_bf_crc_byte(crc, *buffer++);
+	return crc;
+}
+
+static void
+mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
+			   struct mlxsw_sp_acl_atcam_entry *aentry,
+			   char *output, u8 *len)
+{
+	struct mlxsw_afk_key_info *key_info = aregion->region->key_info;
+	u8 chunk_index, chunk_count, block_count;
+	char *chunk = output;
+	__be16 erp_region_id;
+
+	block_count = mlxsw_afk_key_info_blocks_count_get(key_info);
+	chunk_count = 1 + ((block_count - 1) >> 2);
+	erp_region_id = cpu_to_be16(aentry->ht_key.erp_id |
+				   (aregion->region->id << 4));
+	for (chunk_index = MLXSW_BLOOM_KEY_CHUNKS - chunk_count;
+	     chunk_index < MLXSW_BLOOM_KEY_CHUNKS; chunk_index++) {
+		memset(chunk, 0, MLXSW_BLOOM_CHUNK_PAD_BYTES);
+		memcpy(chunk + MLXSW_BLOOM_CHUNK_PAD_BYTES, &erp_region_id,
+		       sizeof(erp_region_id));
+		memcpy(chunk + MLXSW_BLOOM_CHUNK_KEY_OFFSET,
+		       &aentry->ht_key.enc_key[chunk_key_offsets[chunk_index]],
+		       MLXSW_BLOOM_CHUNK_KEY_BYTES);
+		chunk += MLXSW_BLOOM_KEY_CHUNK_BYTES;
+	}
+	*len = chunk_count * MLXSW_BLOOM_KEY_CHUNK_BYTES;
+}
+
+static unsigned int
+mlxsw_sp_acl_bf_rule_count_index_get(struct mlxsw_sp_acl_bf *bf,
+				     unsigned int erp_bank,
+				     unsigned int bf_index)
+{
+	return erp_bank * bf->bank_size + bf_index;
+}
+
+static unsigned int
+mlxsw_sp_acl_bf_index_get(struct mlxsw_sp_acl_bf *bf,
+			  struct mlxsw_sp_acl_atcam_region *aregion,
+			  struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	char bf_key[MLXSW_BLOOM_KEY_LEN];
+	u8 bf_size;
+
+	mlxsw_sp_acl_bf_key_encode(aregion, aentry, bf_key, &bf_size);
+	return mlxsw_sp_acl_bf_crc(bf_key, bf_size);
+}
+
+int
+mlxsw_sp_acl_bf_entry_add(struct mlxsw_sp *mlxsw_sp,
+			  struct mlxsw_sp_acl_bf *bf,
+			  struct mlxsw_sp_acl_atcam_region *aregion,
+			  unsigned int erp_bank,
+			  struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	unsigned int rule_index;
+	char *peabfe_pl;
+	u16 bf_index;
+	int err;
+
+	bf_index = mlxsw_sp_acl_bf_index_get(bf, aregion, aentry);
+	rule_index = mlxsw_sp_acl_bf_rule_count_index_get(bf, erp_bank,
+							  bf_index);
+
+	if (refcount_inc_not_zero(&bf->refcnt[rule_index]))
+		return 0;
+
+	peabfe_pl = kmalloc(MLXSW_REG_PEABFE_LEN, GFP_KERNEL);
+	if (!peabfe_pl)
+		return -ENOMEM;
+
+	mlxsw_reg_peabfe_pack(peabfe_pl);
+	mlxsw_reg_peabfe_rec_pack(peabfe_pl, 0, 1, erp_bank, bf_index);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(peabfe), peabfe_pl);
+	kfree(peabfe_pl);
+	if (err)
+		return err;
+
+	refcount_set(&bf->refcnt[rule_index], 1);
+	return 0;
+}
+
+void
+mlxsw_sp_acl_bf_entry_del(struct mlxsw_sp *mlxsw_sp,
+			  struct mlxsw_sp_acl_bf *bf,
+			  struct mlxsw_sp_acl_atcam_region *aregion,
+			  unsigned int erp_bank,
+			  struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	unsigned int rule_index;
+	char *peabfe_pl;
+	u16 bf_index;
+
+	bf_index = mlxsw_sp_acl_bf_index_get(bf, aregion, aentry);
+	rule_index = mlxsw_sp_acl_bf_rule_count_index_get(bf, erp_bank,
+							  bf_index);
+
+	if (refcount_dec_and_test(&bf->refcnt[rule_index])) {
+		peabfe_pl = kmalloc(MLXSW_REG_PEABFE_LEN, GFP_KERNEL);
+		if (!peabfe_pl)
+			return;
+
+		mlxsw_reg_peabfe_pack(peabfe_pl);
+		mlxsw_reg_peabfe_rec_pack(peabfe_pl, 0, 0, erp_bank, bf_index);
+		mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(peabfe), peabfe_pl);
+		kfree(peabfe_pl);
+	}
+}
+
 struct mlxsw_sp_acl_bf *
 mlxsw_sp_acl_bf_init(struct mlxsw_sp *mlxsw_sp, unsigned int num_erp_banks)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index c65c902cb56a..30ac4d0132de 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -260,6 +260,18 @@ void mlxsw_sp_acl_erps_fini(struct mlxsw_sp *mlxsw_sp,
 
 struct mlxsw_sp_acl_bf;
 
+int
+mlxsw_sp_acl_bf_entry_add(struct mlxsw_sp *mlxsw_sp,
+			  struct mlxsw_sp_acl_bf *bf,
+			  struct mlxsw_sp_acl_atcam_region *aregion,
+			  unsigned int erp_bank,
+			  struct mlxsw_sp_acl_atcam_entry *aentry);
+void
+mlxsw_sp_acl_bf_entry_del(struct mlxsw_sp *mlxsw_sp,
+			  struct mlxsw_sp_acl_bf *bf,
+			  struct mlxsw_sp_acl_atcam_region *aregion,
+			  unsigned int erp_bank,
+			  struct mlxsw_sp_acl_atcam_entry *aentry);
 struct mlxsw_sp_acl_bf *
 mlxsw_sp_acl_bf_init(struct mlxsw_sp *mlxsw_sp, unsigned int num_erp_banks);
 void mlxsw_sp_acl_bf_fini(struct mlxsw_sp_acl_bf *bf);
-- 
cgit v1.2.3


From f5a2852ed0d74a9b6d9c92bc1ad5124e5e4a703c Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:29 +0000
Subject: mlxsw: spectrum_acl: Add Bloom filter update

Add Bloom filter update for rule insertion and rule removal scenarios.
This is done within eRP module in order to assure that Bloom filter
updates are done only for rules which are part of an eRP, as HW does not
consult Bloom filter for entries when there is a single (master) mask in
the region.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 54 +++++++++++++++++++++-
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |  8 ++++
 2 files changed, 60 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index bc3c731f06a1..1315619974e0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -115,6 +115,19 @@ static const struct mlxsw_sp_acl_erp_table_ops erp_no_mask_ops = {
 	.erp_destroy = mlxsw_sp_acl_erp_no_mask_destroy,
 };
 
+static bool
+mlxsw_sp_acl_erp_table_is_used(const struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	return erp_table->ops != &erp_single_mask_ops &&
+	       erp_table->ops != &erp_no_mask_ops;
+}
+
+static unsigned int
+mlxsw_sp_acl_erp_bank_get(const struct mlxsw_sp_acl_erp *erp)
+{
+	return erp->index % erp->erp_table->erp_core->num_erp_banks;
+}
+
 static unsigned int
 mlxsw_sp_acl_erp_table_entry_size(const struct mlxsw_sp_acl_erp_table *erp_table)
 {
@@ -636,8 +649,7 @@ __mlxsw_sp_acl_erp_table_other_inc(struct mlxsw_sp_acl_erp_table *erp_table,
 	/* If there are C-TCAM eRP or deltas in use we need to transition
 	 * the region to use eRP table, if it is not already done
 	 */
-	if (erp_table->ops != &erp_two_masks_ops &&
-	    erp_table->ops != &erp_multiple_masks_ops) {
+	if (!mlxsw_sp_acl_erp_table_is_used(erp_table)) {
 		err = mlxsw_sp_acl_erp_region_table_trans(erp_table);
 		if (err)
 			return err;
@@ -961,6 +973,44 @@ void mlxsw_sp_acl_erp_mask_put(struct mlxsw_sp_acl_atcam_region *aregion,
 	objagg_obj_put(aregion->erp_table->objagg, objagg_obj);
 }
 
+int mlxsw_sp_acl_erp_bf_insert(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_erp_mask *erp_mask,
+			       struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	const struct mlxsw_sp_acl_erp *erp = objagg_obj_root_priv(objagg_obj);
+	unsigned int erp_bank;
+
+	ASSERT_RTNL();
+	if (!mlxsw_sp_acl_erp_table_is_used(erp->erp_table))
+		return 0;
+
+	erp_bank = mlxsw_sp_acl_erp_bank_get(erp);
+	return mlxsw_sp_acl_bf_entry_add(mlxsw_sp,
+					erp->erp_table->erp_core->bf,
+					aregion, erp_bank, aentry);
+}
+
+void mlxsw_sp_acl_erp_bf_remove(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_atcam_region *aregion,
+				struct mlxsw_sp_acl_erp_mask *erp_mask,
+				struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	const struct mlxsw_sp_acl_erp *erp = objagg_obj_root_priv(objagg_obj);
+	unsigned int erp_bank;
+
+	ASSERT_RTNL();
+	if (!mlxsw_sp_acl_erp_table_is_used(erp->erp_table))
+		return;
+
+	erp_bank = mlxsw_sp_acl_erp_bank_get(erp);
+	mlxsw_sp_acl_bf_entry_del(mlxsw_sp,
+				  erp->erp_table->erp_core->bf,
+				  aregion, erp_bank, aentry);
+}
+
 bool
 mlxsw_sp_acl_erp_mask_is_ctcam(const struct mlxsw_sp_acl_erp_mask *erp_mask)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 30ac4d0132de..b649a4f97558 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -251,6 +251,14 @@ mlxsw_sp_acl_erp_mask_get(struct mlxsw_sp_acl_atcam_region *aregion,
 			  const char *mask, bool ctcam);
 void mlxsw_sp_acl_erp_mask_put(struct mlxsw_sp_acl_atcam_region *aregion,
 			       struct mlxsw_sp_acl_erp_mask *erp_mask);
+int mlxsw_sp_acl_erp_bf_insert(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_erp_mask *erp_mask,
+			       struct mlxsw_sp_acl_atcam_entry *aentry);
+void mlxsw_sp_acl_erp_bf_remove(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_atcam_region *aregion,
+				struct mlxsw_sp_acl_erp_mask *erp_mask,
+				struct mlxsw_sp_acl_atcam_entry *aentry);
 int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion);
 void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
 int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp,
-- 
cgit v1.2.3


From 8c81b7438bf6abb035ee3009394a837ac8af64a8 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:30 +0000
Subject: mlxsw: spectrum_acl: Set A-TCAM rules in Bloom filter

Add calls to eRP module for updating Bloom filter when a rule is
added or removed from the A-TCAM. eRP module will update the Bloom
filter only for cases in which the region has an active eRP table.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index 75f11c2d7b97..aedfece86121 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -508,6 +508,13 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_rhashtable_insert;
 
+	/* Bloom filter must be updated here, before inserting the rule into
+	 * the A-TCAM.
+	 */
+	err = mlxsw_sp_acl_erp_bf_insert(mlxsw_sp, aregion, erp_mask, aentry);
+	if (err)
+		goto err_bf_insert;
+
 	err = mlxsw_sp_acl_atcam_region_entry_insert(mlxsw_sp, aregion, aentry,
 						     rulei);
 	if (err)
@@ -516,6 +523,8 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 
 err_rule_insert:
+	mlxsw_sp_acl_erp_bf_remove(mlxsw_sp, aregion, erp_mask, aentry);
+err_bf_insert:
 	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
 			       mlxsw_sp_acl_atcam_entries_ht_params);
 err_rhashtable_insert:
@@ -529,6 +538,7 @@ __mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_atcam_entry *aentry)
 {
 	mlxsw_sp_acl_atcam_region_entry_remove(mlxsw_sp, aregion, aentry);
+	mlxsw_sp_acl_erp_bf_remove(mlxsw_sp, aregion, aentry->erp_mask, aentry);
 	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
 			       mlxsw_sp_acl_atcam_entries_ht_params);
 	mlxsw_sp_acl_erp_mask_put(aregion, aentry->erp_mask);
-- 
cgit v1.2.3


From 135fd957288ed5f6a4ae490373a7910b3e7f7722 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:32 +0000
Subject: mlxsw: spectrum_acl: Update Bloom filter on eRP transitions

Bloom filter update is required only for rules which reside on an
eRP. When the region has only a single rule pattern then eRP table
is not used, however insertion of another pattern would trigger a
move to an active eRP table so it is imperative to update the Bloom
filter with all previously configured rules.

Add a method that updates Bloom filter entries for all rules
currently configured in the region, on the event of a transition
from master mask to eRP, or vice versa. For that purpose, maintain
a list of all A-TCAM rules within mlxsw_sp_acl_atcam_region.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c   | 10 ++++
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 53 ++++++++++++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |  2 +
 3 files changed, 65 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index aedfece86121..80fb268d51a5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -323,6 +323,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 	aregion->region = region;
 	aregion->atcam = atcam;
 	mlxsw_sp_acl_atcam_region_type_init(aregion);
+	INIT_LIST_HEAD(&aregion->entries_list);
 
 	err = rhashtable_init(&aregion->entries_ht,
 			      &mlxsw_sp_acl_atcam_entries_ht_params);
@@ -356,6 +357,7 @@ void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion)
 	mlxsw_sp_acl_erp_region_fini(aregion);
 	aregion->ops->fini(aregion);
 	rhashtable_destroy(&aregion->entries_ht);
+	WARN_ON(!list_empty(&aregion->entries_list));
 }
 
 void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion,
@@ -499,6 +501,12 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 		mlxsw_sp_acl_erp_delta_value(delta, aentry->full_enc_key);
 	mlxsw_sp_acl_erp_delta_clear(delta, aentry->ht_key.enc_key);
 
+	/* Add rule to the list of A-TCAM rules, assuming this
+	 * rule is intended to A-TCAM. In case this rule does
+	 * not fit into A-TCAM it will be removed from the list.
+	 */
+	list_add(&aentry->list, &aregion->entries_list);
+
 	/* We can't insert identical rules into the A-TCAM, so fail and
 	 * let the rule spill into C-TCAM
 	 */
@@ -528,6 +536,7 @@ err_bf_insert:
 	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
 			       mlxsw_sp_acl_atcam_entries_ht_params);
 err_rhashtable_insert:
+	list_del(&aentry->list);
 	mlxsw_sp_acl_erp_mask_put(aregion, erp_mask);
 	return err;
 }
@@ -541,6 +550,7 @@ __mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_erp_bf_remove(mlxsw_sp, aregion, aentry->erp_mask, aentry);
 	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
 			       mlxsw_sp_acl_atcam_entries_ht_params);
+	list_del(&aentry->list);
 	mlxsw_sp_acl_erp_mask_put(aregion, aentry->erp_mask);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 1315619974e0..3326c930f3fa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -517,6 +517,48 @@ err_table_relocate:
 	return err;
 }
 
+static int
+mlxsw_acl_erp_table_bf_add(struct mlxsw_sp_acl_erp_table *erp_table,
+			   struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion = erp_table->aregion;
+	unsigned int erp_bank = mlxsw_sp_acl_erp_bank_get(erp);
+	struct mlxsw_sp_acl_atcam_entry *aentry;
+	int err;
+
+	list_for_each_entry(aentry, &aregion->entries_list, list) {
+		err = mlxsw_sp_acl_bf_entry_add(aregion->region->mlxsw_sp,
+						erp_table->erp_core->bf,
+						aregion, erp_bank, aentry);
+		if (err)
+			goto bf_entry_add_err;
+	}
+
+	return 0;
+
+bf_entry_add_err:
+	list_for_each_entry_continue_reverse(aentry, &aregion->entries_list,
+					     list)
+		mlxsw_sp_acl_bf_entry_del(aregion->region->mlxsw_sp,
+					  erp_table->erp_core->bf,
+					  aregion, erp_bank, aentry);
+	return err;
+}
+
+static void
+mlxsw_acl_erp_table_bf_del(struct mlxsw_sp_acl_erp_table *erp_table,
+			   struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion = erp_table->aregion;
+	unsigned int erp_bank = mlxsw_sp_acl_erp_bank_get(erp);
+	struct mlxsw_sp_acl_atcam_entry *aentry;
+
+	list_for_each_entry_reverse(aentry, &aregion->entries_list, list)
+		mlxsw_sp_acl_bf_entry_del(aregion->region->mlxsw_sp,
+					  erp_table->erp_core->bf,
+					  aregion, erp_bank, aentry);
+}
+
 static int
 mlxsw_sp_acl_erp_region_table_trans(struct mlxsw_sp_acl_erp_table *erp_table)
 {
@@ -551,6 +593,14 @@ mlxsw_sp_acl_erp_region_table_trans(struct mlxsw_sp_acl_erp_table *erp_table)
 	if (err)
 		goto err_table_master_rp_add;
 
+	/* Update Bloom filter before enabling eRP table, as rules
+	 * on the master RP were not set to Bloom filter up to this
+	 * point.
+	 */
+	err = mlxsw_acl_erp_table_bf_add(erp_table, master_rp);
+	if (err)
+		goto err_table_bf_add;
+
 	err = mlxsw_sp_acl_erp_table_enable(erp_table, false);
 	if (err)
 		goto err_table_enable;
@@ -558,6 +608,8 @@ mlxsw_sp_acl_erp_region_table_trans(struct mlxsw_sp_acl_erp_table *erp_table)
 	return 0;
 
 err_table_enable:
+	mlxsw_acl_erp_table_bf_del(erp_table, master_rp);
+err_table_bf_add:
 	mlxsw_sp_acl_erp_table_erp_del(master_rp);
 err_table_master_rp_add:
 	__clear_bit(master_rp->index, erp_table->erp_index_bitmap);
@@ -578,6 +630,7 @@ mlxsw_sp_acl_erp_region_master_mask_trans(struct mlxsw_sp_acl_erp_table *erp_tab
 	master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table);
 	if (!master_rp)
 		return;
+	mlxsw_acl_erp_table_bf_del(erp_table, master_rp);
 	mlxsw_sp_acl_erp_table_erp_del(master_rp);
 	__clear_bit(master_rp->index, erp_table->erp_index_bitmap);
 	mlxsw_sp_acl_erp_table_free(erp_core, erp_table->num_max_atcam_erps,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index b649a4f97558..0f1a9dee63de 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -152,6 +152,7 @@ struct mlxsw_sp_acl_atcam {
 
 struct mlxsw_sp_acl_atcam_region {
 	struct rhashtable entries_ht; /* A-TCAM only */
+	struct list_head entries_list; /* A-TCAM only */
 	struct mlxsw_sp_acl_ctcam_region cregion;
 	const struct mlxsw_sp_acl_atcam_region_ops *ops;
 	struct mlxsw_sp_acl_tcam_region *region;
@@ -174,6 +175,7 @@ struct mlxsw_sp_acl_atcam_chunk {
 
 struct mlxsw_sp_acl_atcam_entry {
 	struct rhash_head ht_node;
+	struct list_head list; /* Member in entries_list */
 	struct mlxsw_sp_acl_atcam_entry_ht_key ht_key;
 	char full_enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key */
 	struct {
-- 
cgit v1.2.3


From dd97d85f1e4daaa86d7a2813d718b91e5261df57 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:33 +0000
Subject: mlxsw: spectrum_acl: Set master RP index on transition to eRP

Bloom filter is updated on transitions from a single rule pattern,
also called master RP, to eRP table and vice versa. Since rules are
being written to or deleted from the Bloom filter on such transitions,
it is not required to keep the same eRP bank ID for the master RP.

Change master RP index assignment so it will be assigned with zero.
This is consistent with the assignment of the first available spot
that is used for allocating eRP's indices.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 3326c930f3fa..1c19feefa5f2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -583,10 +583,10 @@ mlxsw_sp_acl_erp_region_table_trans(struct mlxsw_sp_acl_erp_table *erp_table)
 		goto err_table_master_rp;
 	}
 
-	/* Maintain the same eRP bank for the master RP, so that we
-	 * wouldn't need to update the bloom filter
+	/* Make sure the master RP is using a valid index, as
+	 * only a single eRP row is currently allocated.
 	 */
-	master_rp->index = master_rp->index % erp_core->num_erp_banks;
+	master_rp->index = 0;
 	__set_bit(master_rp->index, erp_table->erp_index_bitmap);
 
 	err = mlxsw_sp_acl_erp_table_erp_add(erp_table, master_rp);
-- 
cgit v1.2.3


From 03ce5bd187603ca916ca53843426526f38eab659 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:34 +0000
Subject: mlxsw: reg: Activate Bloom filter

Now that mlxsw driver handles all aspects of updating
the Bloom filter mechanism, set bf_bypass value to false
and allow HW to use Bloom filter.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 8e1f7ae4342a..9b48dffc9f63 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2743,7 +2743,7 @@ mlxsw_reg_perpt_pack(char *payload, u8 erpt_bank, u8 erpt_index,
 	mlxsw_reg_perpt_erpt_bank_set(payload, erpt_bank);
 	mlxsw_reg_perpt_erpt_index_set(payload, erpt_index);
 	mlxsw_reg_perpt_key_size_set(payload, key_size);
-	mlxsw_reg_perpt_bf_bypass_set(payload, true);
+	mlxsw_reg_perpt_bf_bypass_set(payload, false);
 	mlxsw_reg_perpt_erp_id_set(payload, erp_id);
 	mlxsw_reg_perpt_erpt_base_bank_set(payload, erpt_base_bank);
 	mlxsw_reg_perpt_erpt_base_index_set(payload, erpt_base_index);
@@ -3006,7 +3006,7 @@ static inline void mlxsw_reg_percr_pack(char *payload, u16 region_id)
 	mlxsw_reg_percr_region_id_set(payload, region_id);
 	mlxsw_reg_percr_atcam_ignore_prune_set(payload, false);
 	mlxsw_reg_percr_ctcam_ignore_prune_set(payload, false);
-	mlxsw_reg_percr_bf_bypass_set(payload, true);
+	mlxsw_reg_percr_bf_bypass_set(payload, false);
 }
 
 /* PERERP - Policy-Engine Region eRP Register
-- 
cgit v1.2.3


From 095c720807499953b7e16528f705d09675c96c0c Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:35 +0000
Subject: selftests: mlxsw: Add Bloom filter simple test

Add a test that exercises Bloom filter code.
Activate eRP table in the region by adding multiple rule patterns which
with very high probability use different entries in the Bloom filter.
Then send packets in order to check lookup hits on all relevant rules.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/spectrum-2/tc_flower.sh      | 57 +++++++++++++++++++++-
 1 file changed, 56 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index 00ae99fbc253..ad66e3e94cc9 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -8,7 +8,8 @@
 lib_dir=$(dirname $0)/../../../../net/forwarding
 
 ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
-	multiple_masks_test ctcam_edge_cases_test delta_simple_test"
+	multiple_masks_test ctcam_edge_cases_test delta_simple_test \
+	bloom_simple_test"
 NUM_NETIFS=2
 source $lib_dir/tc_common.sh
 source $lib_dir/lib.sh
@@ -404,6 +405,60 @@ delta_simple_test()
 	log_test "delta simple test ($tcflags)"
 }
 
+bloom_simple_test()
+{
+	# Bloom filter requires that the eRP table is used. This test
+	# verifies that Bloom filter is not harming correctness of ACLs.
+	# First, make sure that eRP table is used and then set rule patterns
+	# which are distant enough and will result skipping a lookup after
+	# consulting the Bloom filter. Although some eRP lookups are skipped,
+	# the correct filter should be hit.
+
+	RET=0
+
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+	tc filter add dev $h2 ingress protocol ip pref 5 handle 104 flower \
+		$tcflags dst_ip 198.51.100.2 action drop
+	tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+		$tcflags dst_ip 192.0.0.0/8 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 101 1
+	check_err $? "Two filters - did not match highest priority"
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 198.51.100.1 -B 198.51.100.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 104 1
+	check_err $? "Single filter - did not match"
+
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 103 1
+	check_err $? "Low prio filter - did not match"
+
+	tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+		$tcflags dst_ip 198.0.0.0/8 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 198.51.100.1 -B 198.51.100.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 102 1
+	check_err $? "Two filters - did not match highest priority after add"
+
+	tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+	tc filter del dev $h2 ingress protocol ip pref 5 handle 104 flower
+
+	log_test "bloom simple test ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
cgit v1.2.3


From 5118ca4edf9939ed3812ffbfabe7b97164f29635 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:36 +0000
Subject: selftests: mlxsw: Add Bloom filter complex test

Bloom filter index computation is based on the values of
{rule & mask, mask ID, region ID} and the computation also varies
according to the region key size.

Add a test that exercises the possible combinations by creating
multiple chains using different key sizes and then pass a frame that
is supposed to to produce a hit on all of the regions.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/spectrum-2/tc_flower.sh      | 85 +++++++++++++++++++++-
 1 file changed, 84 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index ad66e3e94cc9..a7667ebc578f 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -9,7 +9,7 @@ lib_dir=$(dirname $0)/../../../../net/forwarding
 
 ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
 	multiple_masks_test ctcam_edge_cases_test delta_simple_test \
-	bloom_simple_test"
+	bloom_simple_test bloom_complex_test"
 NUM_NETIFS=2
 source $lib_dir/tc_common.sh
 source $lib_dir/lib.sh
@@ -459,6 +459,89 @@ bloom_simple_test()
 	log_test "bloom simple test ($tcflags)"
 }
 
+bloom_complex_test()
+{
+	# Bloom filter index computation is affected from region ID, eRP
+	# ID and from the region key size. In order to excercise those parts
+	# of the Bloom filter code, use a series of regions, each with a
+	# different key size and send packet that should hit all of them.
+	local index
+
+	RET=0
+	NUM_CHAINS=4
+	BASE_INDEX=100
+
+	# Create chain with up to 2 key blocks (ip_proto only)
+	tc chain add dev $h2 ingress chain 1 protocol ip flower \
+		ip_proto tcp &> /dev/null
+	# Create chain with 2-4 key blocks (ip_proto, src MAC)
+	tc chain add dev $h2 ingress chain 2 protocol ip flower \
+		ip_proto tcp \
+		src_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF &> /dev/null
+	# Create chain with 4-8 key blocks (ip_proto, src & dst MAC, IPv4 dest)
+	tc chain add dev $h2 ingress chain 3 protocol ip flower \
+		ip_proto tcp \
+		dst_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF \
+		src_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF \
+		dst_ip 0.0.0.0/32 &> /dev/null
+	# Default chain contains all fields and therefore is 8-12 key blocks
+	tc chain add dev $h2 ingress chain 4
+
+	# We need at least 2 rules in every region to have eRP table active
+	# so create a dummy rule per chain using a different pattern
+	for i in $(eval echo {0..$NUM_CHAINS}); do
+		index=$((BASE_INDEX - 1 - i))
+		tc filter add dev $h2 ingress chain $i protocol ip \
+			pref 2 handle $index flower \
+			$tcflags ip_proto tcp action drop
+	done
+
+	# Add rules to test Bloom filter, each in a different chain
+	index=$BASE_INDEX
+	tc filter add dev $h2 ingress protocol ip \
+		pref 1 handle $((++index)) flower \
+		$tcflags dst_ip 192.0.0.0/16 action goto chain 1
+	tc filter add dev $h2 ingress chain 1 protocol ip \
+		pref 1 handle $((++index)) flower \
+		$tcflags action goto chain 2
+	tc filter add dev $h2 ingress chain 2 protocol ip \
+		pref 1 handle $((++index)) flower \
+		$tcflags src_mac $h1mac action goto chain 3
+	tc filter add dev $h2 ingress chain 3 protocol ip \
+		pref 1 handle $((++index)) flower \
+		$tcflags dst_ip 192.0.0.0/8 action goto chain 4
+	tc filter add dev $h2 ingress chain 4 protocol ip \
+		pref 1 handle $((++index)) flower \
+		$tcflags src_ip 192.0.2.0/24 action drop
+
+	# Send a packet that is supposed to hit all chains
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	for i in $(eval echo {0..$NUM_CHAINS}); do
+		index=$((BASE_INDEX + i + 1))
+		tc_check_packets "dev $h2 ingress" $index 1
+		check_err $? "Did not match chain $i"
+	done
+
+	# Rules cleanup
+	for i in $(eval echo {$NUM_CHAINS..0}); do
+		index=$((BASE_INDEX - i - 1))
+		tc filter del dev $h2 ingress chain $i \
+			pref 2 handle $index flower
+		index=$((BASE_INDEX + i + 1))
+		tc filter del dev $h2 ingress chain $i \
+			pref 1 handle $index flower
+	done
+
+	# Chains cleanup
+	for i in $(eval echo {$NUM_CHAINS..1}); do
+		tc chain del dev $h2 ingress chain $i
+	done
+
+	log_test "bloom complex test ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
cgit v1.2.3


From 5d06a76d9e6d2d00eadba72548636ff0ff6fabde Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 16 Dec 2018 08:49:37 +0000
Subject: selftests: mlxsw: Add Bloom delta test

The eRP table is active when there is more than a single rule
pattern. It may be that the patterns are close enough and use delta
mechanism. Bloom filter index computation is based on the values of
{rule & mask, mask ID, region ID} where the rule delta bits must be
cleared.

Add a test that exercises Bloom filter with delta mechanism.
Configure rules within delta range and pass a packet which is
supposed to hit the correct rule.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/spectrum-2/tc_flower.sh      | 37 +++++++++++++++++++++-
 1 file changed, 36 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index a7667ebc578f..b41d6256b2d0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -9,7 +9,7 @@ lib_dir=$(dirname $0)/../../../../net/forwarding
 
 ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
 	multiple_masks_test ctcam_edge_cases_test delta_simple_test \
-	bloom_simple_test bloom_complex_test"
+	bloom_simple_test bloom_complex_test bloom_delta_test"
 NUM_NETIFS=2
 source $lib_dir/tc_common.sh
 source $lib_dir/lib.sh
@@ -542,6 +542,41 @@ bloom_complex_test()
 	log_test "bloom complex test ($tcflags)"
 }
 
+
+bloom_delta_test()
+{
+	# When multiple masks are used, the eRP table is activated. When
+	# masks are close enough (delta) the masks reside on the same
+	# eRP table. This test verifies that the eRP table is correctly
+	# allocated and used in delta condition and that Bloom filter is
+	# still functional with delta.
+
+	RET=0
+
+	tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+		$tcflags dst_ip 192.1.0.0/16 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.1.2.1 -B 192.1.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 103 1
+	check_err $? "Single filter - did not match"
+
+	tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+		$tcflags dst_ip 192.2.1.0/24 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.2.1.1 -B 192.2.1.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 102 1
+	check_err $? "Delta filters - did not match second filter"
+
+	tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+	log_test "bloom delta test ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
cgit v1.2.3


From c03b0358ab60504151b35587c88205c7b7fe22be Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 17 Dec 2018 12:39:02 +0100
Subject: net: unbreak CONFIG_RETPOLINE=n builds

The kbuild bot reported a build breakage with CONFIG_RETPOLINE=n
due to commit aaa5d90b395a ("net: use indirect call wrappers at
GRO network layer").
I screwed the wrapper implementation for such config.
Fix the issue properly ignoring the builtin symbols arguments,
when retpoline is not enabled.

Reported-by: kbuild test robot <lkp@intel.com>
Fixes: aaa5d90b395a ("net: use indirect call wrappers at GRO network layer")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/indirect_call_wrapper.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
index 7c8b7f4948af..00d7e8e919c6 100644
--- a/include/linux/indirect_call_wrapper.h
+++ b/include/linux/indirect_call_wrapper.h
@@ -28,8 +28,8 @@
 #define INDIRECT_CALLABLE_SCOPE
 
 #else
-#define INDIRECT_CALL_1(f, name, ...) f(__VA_ARGS__)
-#define INDIRECT_CALL_2(f, name, ...) f(__VA_ARGS__)
+#define INDIRECT_CALL_1(f, f1, ...) f(__VA_ARGS__)
+#define INDIRECT_CALL_2(f, f2, f1, ...) f(__VA_ARGS__)
 #define INDIRECT_CALLABLE_DECLARE(f)
 #define INDIRECT_CALLABLE_SCOPE		static
 #endif
-- 
cgit v1.2.3


From 915fe1a0d9cbf6d7657b388833dbcae13d22a567 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 13 Nov 2018 11:09:30 +0200
Subject: net/mlx5: E-Switch, Remove redundant reloading of the IB interface

The reload of the IB interface done on the offloads stop call is
redundant b/c we do that on mlx5_eswitch_disable_sriov(), remove it.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 76cb57202474..53065b6ae593 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1450,9 +1450,6 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 		}
 	}
 
-	/* enable back PF RoCE */
-	mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-
 	return err;
 }
 
-- 
cgit v1.2.3


From 025380b20dc2a3b92a36394799157a63a2fe5814 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Wed, 28 Nov 2018 18:56:41 +0200
Subject: net/mlx5e: Use single argument for the esw representor build params
 helper

This is prep step towards adding dedicated uplink representor.

The patch doesn't change any functionality.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index e4a34c9ef700..996a03de9171 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1205,17 +1205,19 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
 	.ndo_change_mtu          = mlx5e_change_rep_mtu,
 };
 
-static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
-				   struct mlx5e_params *params,
-				   struct mlx5e_rss_params *rss_params,
-				   u16 mtu)
+static void mlx5e_build_rep_params(struct net_device *netdev)
 {
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_params *params;
+
 	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
 					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
+	params = &priv->channels.params;
 	params->hard_mtu    = MLX5E_ETH_HARD_MTU;
-	params->sw_mtu      = mtu;
+	params->sw_mtu      = netdev->mtu;
 	params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
 
 	/* RQ */
@@ -1230,7 +1232,7 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
 	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
 
 	/* RSS */
-	mlx5e_build_rss_params(rss_params, params->num_channels);
+	mlx5e_build_rss_params(&priv->rss_params, params->num_channels);
 }
 
 static void mlx5e_build_rep_netdev(struct net_device *netdev)
@@ -1283,8 +1285,7 @@ static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
 	priv->channels.params.num_channels =
 				mlx5e_get_netdev_max_channels(netdev);
 
-	mlx5e_build_rep_params(mdev, &priv->channels.params,
-			       &priv->rss_params, netdev->mtu);
+	mlx5e_build_rep_params(netdev);
 	mlx5e_build_rep_netdev(netdev);
 
 	mlx5e_timestamp_init(priv);
-- 
cgit v1.2.3


From d9ee0491c2ffbb5bc8bc418dd857a045d0d0130f Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 13 Feb 2018 15:48:30 +0200
Subject: net/mlx5e: Use dedicated uplink vport netdev representor

Currently, when running in sriov switchdev mode, we are using the PF
netdevice as the uplink representor, this is problematic from few aspects:

- will break when the PF isn't eswitch manager (e.g smart NIC env)
- misalignment with other NIC switchdev drivers
- makes us have and maintain special code, hurts the driver quality/robustness
- which in turn opens the door for future bugs

As of each and all of the above, we move to have a dedicated netdev representor
for the uplink vport in a similar manner done for for the VF vports.

This includes the following:

1. have an uplink rep netdev as we have for VF reps
2. all reps use same load/unload functions
3. HW stats for uplink based on physical port counters and not vport counters
4. link state for the uplink managed through PAOS and not vport state
5. the uplink rep has sysfs link to the PF PCI function && uses the PF MAC address

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   3 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  31 +--
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   | 236 ++++++++++++++-------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h   |  13 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    |  39 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h    |   8 +-
 8 files changed, 212 insertions(+), 121 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 1c4e033b7509..31deafecf679 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -775,6 +775,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 			     struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt);
 
 void mlx5e_update_stats(struct mlx5e_priv *priv);
+void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
 
 void mlx5e_init_l2_addr(struct mlx5e_priv *priv);
 int mlx5e_self_test_num(struct mlx5e_priv *priv);
@@ -939,7 +940,6 @@ int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
 
 int mlx5e_create_tises(struct mlx5e_priv *priv);
-void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
 int mlx5e_open(struct net_device *netdev);
 void mlx5e_update_ndo_stats(struct mlx5e_priv *priv);
@@ -948,6 +948,7 @@ void mlx5e_queue_update_stats(struct mlx5e_priv *priv);
 int mlx5e_bits_invert(unsigned long a, int size);
 
 typedef int (*change_hw_mtu_cb)(struct mlx5e_priv *priv);
+int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv);
 int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 		     change_hw_mtu_cb set_mtu_cb);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 59745851b5ba..cdd8b5efd96a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2821,7 +2821,7 @@ static void mlx5e_query_mtu(struct mlx5_core_dev *mdev,
 	*mtu = MLX5E_HW2SW_MTU(params, hw_mtu);
 }
 
-static int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
+int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 {
 	struct mlx5e_params *params = &priv->channels.params;
 	struct net_device *netdev = priv->netdev;
@@ -2901,7 +2901,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	mlx5e_activate_channels(&priv->channels);
 	netif_tx_start_all_queues(priv->netdev);
 
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
+	if (mlx5e_is_vport_rep(priv))
 		mlx5e_add_sqs_fwd_rules(priv);
 
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
@@ -2912,7 +2912,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
 	mlx5e_redirect_rqts_to_drop(priv);
 
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
+	if (mlx5e_is_vport_rep(priv))
 		mlx5e_remove_sqs_fwd_rules(priv);
 
 	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
@@ -3164,7 +3164,7 @@ err_close_tises:
 	return err;
 }
 
-void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
+static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 {
 	int tc;
 
@@ -3409,7 +3409,8 @@ static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
-		return mlx5e_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS);
+		return mlx5e_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS |
+						 MLX5E_TC_NIC_OFFLOAD);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -3452,7 +3453,7 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	}
 }
 
-static void
+void
 mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
@@ -3596,7 +3597,7 @@ static int set_feature_tc_num_filters(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	if (!enable && mlx5e_tc_num_filters(priv)) {
+	if (!enable && mlx5e_tc_num_filters(priv, MLX5E_TC_NIC_OFFLOAD)) {
 		netdev_err(netdev,
 			   "Active offloaded tc filters, can't turn hw_tc_offload off\n");
 		return -EINVAL;
@@ -4607,12 +4608,6 @@ static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
 	}
 }
 
-#if IS_ENABLED(CONFIG_MLX5_ESWITCH)
-static const struct switchdev_ops mlx5e_switchdev_ops = {
-	.switchdev_port_attr_get	= mlx5e_attr_get,
-};
-#endif
-
 static void mlx5e_build_nic_netdev(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -4722,12 +4717,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
 	mlx5e_set_netdev_dev_addr(netdev);
-
-#if IS_ENABLED(CONFIG_MLX5_ESWITCH)
-	if (MLX5_ESWITCH_MANAGER(mdev))
-		netdev->switchdev_ops = &mlx5e_switchdev_ops;
-#endif
-
 	mlx5e_ipsec_build_netdev(priv);
 	mlx5e_tls_build_netdev(priv);
 }
@@ -4908,7 +4897,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 		mlx5e_monitor_counter_init(priv);
 
 	if (MLX5_ESWITCH_MANAGER(priv->mdev))
-		mlx5e_register_vport_reps(priv);
+		mlx5e_rep_register_vport_reps(priv);
 
 	if (netdev->reg_state != NETREG_REGISTERED)
 		return;
@@ -4943,7 +4932,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
 	if (MLX5_ESWITCH_MANAGER(priv->mdev))
-		mlx5e_unregister_vport_reps(priv);
+		mlx5e_rep_unregister_vport_reps(priv);
 
 	if (mlx5e_monitor_counter_supported(priv))
 		mlx5e_monitor_counter_cleanup(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 996a03de9171..b48ba3234ac5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -108,7 +108,7 @@ static void mlx5e_rep_get_strings(struct net_device *dev,
 	}
 }
 
-static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
+static void mlx5e_vf_rep_update_hw_counters(struct mlx5e_priv *priv)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -131,6 +131,32 @@ static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
 	vport_stats->tx_bytes   = vf_stats.rx_bytes;
 }
 
+static void mlx5e_uplink_rep_update_hw_counters(struct mlx5e_priv *priv)
+{
+	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
+	struct rtnl_link_stats64 *vport_stats;
+
+	mlx5e_grp_802_3_update_stats(priv);
+
+	vport_stats = &priv->stats.vf_vport;
+
+	vport_stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
+	vport_stats->rx_bytes   = PPORT_802_3_GET(pstats, a_octets_received_ok);
+	vport_stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok);
+	vport_stats->tx_bytes   = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
+}
+
+static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
+
+	if (rep->vport == FDB_UPLINK_VPORT)
+		mlx5e_uplink_rep_update_hw_counters(priv);
+	else
+		mlx5e_vf_rep_update_hw_counters(priv);
+}
+
 static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
 {
 	struct mlx5e_sw_stats *s = &priv->stats.sw;
@@ -294,7 +320,7 @@ static const struct ethtool_ops mlx5e_rep_ethtool_ops = {
 	.get_rxfh_indir_size = mlx5e_rep_get_rxfh_indir_size,
 };
 
-int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+static int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -576,21 +602,19 @@ mlx5e_rep_indr_offload(struct net_device *netdev,
 		       struct tc_cls_flower_offload *flower,
 		       struct mlx5e_rep_indr_block_priv *indr_priv)
 {
-	int err = 0;
 	struct mlx5e_priv *priv = netdev_priv(indr_priv->rpriv->netdev);
+	int flags = MLX5E_TC_EGRESS | MLX5E_TC_ESW_OFFLOAD;
+	int err = 0;
 
 	switch (flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		err = mlx5e_configure_flower(netdev, priv,
-					     flower, MLX5E_TC_EGRESS);
+		err = mlx5e_configure_flower(netdev, priv, flower, flags);
 		break;
 	case TC_CLSFLOWER_DESTROY:
-		err = mlx5e_delete_flower(netdev, priv,
-					  flower, MLX5E_TC_EGRESS);
+		err = mlx5e_delete_flower(netdev, priv, flower, flags);
 		break;
 	case TC_CLSFLOWER_STATS:
-		err = mlx5e_stats_flower(netdev, priv,
-					 flower, MLX5E_TC_EGRESS);
+		err = mlx5e_stats_flower(netdev, priv, flower, flags);
 		break;
 	default:
 		err = -EOPNOTSUPP;
@@ -983,7 +1007,7 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
 		mlx5e_rep_neigh_entry_destroy(priv, nhe);
 }
 
-static int mlx5e_rep_open(struct net_device *dev)
+static int mlx5e_vf_rep_open(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -1005,7 +1029,7 @@ unlock:
 	return err;
 }
 
-static int mlx5e_rep_close(struct net_device *dev)
+static int mlx5e_vf_rep_close(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -1062,7 +1086,8 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
-		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS);
+		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS |
+						     MLX5E_TC_ESW_OFFLOAD);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1101,19 +1126,17 @@ static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 
 bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 {
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep;
 
 	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
 		return false;
 
-	rep = rpriv->rep;
-	if (esw->mode == SRIOV_OFFLOADS &&
-	    rep && rep->vport == FDB_UPLINK_VPORT)
-		return true;
+	if (!rpriv) /* non vport rep mlx5e instances don't use this field */
+		return false;
 
-	return false;
+	rep = rpriv->rep;
+	return (rep->vport == FDB_UPLINK_VPORT);
 }
 
 static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
@@ -1133,11 +1156,8 @@ static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
 
 bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id)
 {
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
 	switch (attr_id) {
 	case IFLA_OFFLOAD_XSTATS_CPU_HIT:
-		if (mlx5e_is_vf_vport_rep(priv) || mlx5e_is_uplink_rep(priv))
 			return true;
 	}
 
@@ -1175,7 +1195,7 @@ int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev,
 }
 
 static void
-mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
+mlx5e_vf_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
@@ -1184,30 +1204,59 @@ mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
 }
 
+static int mlx5e_vf_rep_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	return mlx5e_change_mtu(netdev, new_mtu, NULL);
+}
+
+static int mlx5e_uplink_rep_open(struct net_device *dev)
+{
+	int err;
+
+	err = mlx5e_open(dev);
+	if (!err)
+		netif_carrier_on(dev);
+	return err;
+}
+
+static int mlx5e_uplink_rep_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu);
+}
+
 static const struct switchdev_ops mlx5e_rep_switchdev_ops = {
 	.switchdev_port_attr_get	= mlx5e_attr_get,
 };
 
-static int mlx5e_change_rep_mtu(struct net_device *netdev, int new_mtu)
-{
-	return mlx5e_change_mtu(netdev, new_mtu, NULL);
-}
+static const struct net_device_ops mlx5e_netdev_ops_vf_rep = {
+	.ndo_open                = mlx5e_vf_rep_open,
+	.ndo_stop                = mlx5e_vf_rep_close,
+	.ndo_start_xmit          = mlx5e_xmit,
+	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
+	.ndo_setup_tc            = mlx5e_rep_setup_tc,
+	.ndo_get_stats64         = mlx5e_vf_rep_get_stats,
+	.ndo_has_offload_stats	 = mlx5e_has_offload_stats,
+	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
+	.ndo_change_mtu          = mlx5e_vf_rep_change_mtu,
+};
 
-static const struct net_device_ops mlx5e_netdev_ops_rep = {
-	.ndo_open                = mlx5e_rep_open,
-	.ndo_stop                = mlx5e_rep_close,
+static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = {
+	.ndo_open                = mlx5e_uplink_rep_open,
+	.ndo_stop                = mlx5e_close,
 	.ndo_start_xmit          = mlx5e_xmit,
 	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
 	.ndo_setup_tc            = mlx5e_rep_setup_tc,
-	.ndo_get_stats64         = mlx5e_rep_get_stats,
+	.ndo_get_stats64         = mlx5e_get_stats,
 	.ndo_has_offload_stats	 = mlx5e_has_offload_stats,
 	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
-	.ndo_change_mtu          = mlx5e_change_rep_mtu,
+	.ndo_change_mtu          = mlx5e_uplink_rep_change_mtu,
 };
 
 static void mlx5e_build_rep_params(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_params *params;
 
@@ -1218,7 +1267,12 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	params = &priv->channels.params;
 	params->hard_mtu    = MLX5E_ETH_HARD_MTU;
 	params->sw_mtu      = netdev->mtu;
-	params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
+
+	/* SQ */
+	if (rep->vport == FDB_UPLINK_VPORT)
+		params->log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
+	else
+		params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
 
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
@@ -1238,10 +1292,20 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 static void mlx5e_build_rep_netdev(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u16 max_mtu;
 
-	netdev->netdev_ops = &mlx5e_netdev_ops_rep;
+	if (rep->vport == FDB_UPLINK_VPORT) {
+		SET_NETDEV_DEV(netdev, &priv->mdev->pdev->dev);
+		netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep;
+		/* we want a persistent mac for the uplink rep */
+		mlx5_query_nic_vport_mac_address(mdev, 0, netdev->dev_addr);
+	} else {
+		netdev->netdev_ops = &mlx5e_netdev_ops_vf_rep;
+		eth_hw_addr_random(netdev);
+	}
 
 	netdev->watchdog_timeo    = 15 * HZ;
 
@@ -1262,28 +1326,35 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 
 	netdev->features |= netdev->hw_features;
 
-	eth_hw_addr_random(netdev);
-
 	netdev->min_mtu = ETH_MIN_MTU;
 	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
 	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
 }
 
+static int mlx5e_rep_get_default_num_channels(struct mlx5_eswitch_rep *rep,
+					      struct net_device *netdev)
+{
+	if (rep->vport == FDB_UPLINK_VPORT)
+		return mlx5e_get_netdev_max_channels(netdev);
+	else
+		return 1;
+}
+
 static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
 			  struct net_device *netdev,
 			  const struct mlx5e_profile *profile,
 			  void *ppriv)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rep_priv *rpriv = ppriv;
 	int err;
 
 	err = mlx5e_netdev_init(netdev, priv, mdev, profile, ppriv);
 	if (err)
 		return err;
 
-
 	priv->channels.params.num_channels =
-				mlx5e_get_netdev_max_channels(netdev);
+			mlx5e_rep_get_default_num_channels(rpriv->rep, netdev);
 
 	mlx5e_build_rep_params(netdev);
 	mlx5e_build_rep_netdev(netdev);
@@ -1408,14 +1479,60 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 
 static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
 {
-	int err;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	int tc, err;
 
 	err = mlx5e_create_tises(priv);
 	if (err) {
 		mlx5_core_warn(priv->mdev, "create tises failed, %d\n", err);
 		return err;
 	}
+
+	if (rpriv->rep->vport == FDB_UPLINK_VPORT) {
+		uplink_priv = &rpriv->uplink_priv;
+
+		/* init shared tc flow table */
+		err = mlx5e_tc_esw_init(&uplink_priv->tc_ht);
+		if (err)
+			goto destroy_tises;
+
+		/* init indirect block notifications */
+		INIT_LIST_HEAD(&uplink_priv->tc_indr_block_priv_list);
+		uplink_priv->netdevice_nb.notifier_call = mlx5e_nic_rep_netdevice_event;
+		err = register_netdevice_notifier(&uplink_priv->netdevice_nb);
+		if (err) {
+			mlx5_core_err(priv->mdev, "Failed to register netdev notifier\n");
+			goto tc_esw_cleanup;
+		}
+	}
+
 	return 0;
+
+tc_esw_cleanup:
+	mlx5e_tc_esw_cleanup(&uplink_priv->tc_ht);
+destroy_tises:
+	for (tc = 0; tc < priv->profile->max_tc; tc++)
+		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
+	return err;
+}
+
+static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	int tc;
+
+	for (tc = 0; tc < priv->profile->max_tc; tc++)
+		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
+
+	if (rpriv->rep->vport == FDB_UPLINK_VPORT) {
+		/* clean indirect TC block notifications */
+		unregister_netdevice_notifier(&rpriv->uplink_priv.netdevice_nb);
+		mlx5e_rep_indr_clean_block_privs(rpriv);
+
+		/* delete shared tc flow table */
+		mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht);
+	}
 }
 
 static const struct mlx5e_profile mlx5e_rep_profile = {
@@ -1424,7 +1541,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = {
 	.init_rx		= mlx5e_init_rep_rx,
 	.cleanup_rx		= mlx5e_cleanup_rep_rx,
 	.init_tx		= mlx5e_init_rep_tx,
-	.cleanup_tx		= mlx5e_cleanup_nic_tx,
+	.cleanup_tx		= mlx5e_cleanup_rep_tx,
 	.update_stats           = mlx5e_rep_update_hw_counters,
 	.update_carrier		= NULL,
 	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
@@ -1507,6 +1624,9 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	if (!rpriv)
 		return -ENOMEM;
 
+	/* rpriv->rep to be looked up when profile->init() is called */
+	rpriv->rep = rep;
+
 	nch = mlx5e_get_max_num_channels(dev);
 	netdev = mlx5e_create_netdev(dev, &mlx5e_rep_profile, nch, rpriv);
 	if (!netdev) {
@@ -1517,7 +1637,6 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	}
 
 	rpriv->netdev = netdev;
-	rpriv->rep = rep;
 	rep->rep_if[REP_ETH].priv = rpriv;
 	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
 
@@ -1580,14 +1699,14 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep)
 	return rpriv->netdev;
 }
 
-static void mlx5e_rep_register_vf_vports(struct mlx5e_priv *priv)
+void mlx5e_rep_register_vport_reps(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
 	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
 	int vport;
 
-	for (vport = 1; vport < total_vfs; vport++) {
+	for (vport = 0; vport < total_vfs; vport++) {
 		struct mlx5_eswitch_rep_if rep_if = {};
 
 		rep_if.load = mlx5e_vport_rep_load;
@@ -1597,46 +1716,17 @@ static void mlx5e_rep_register_vf_vports(struct mlx5e_priv *priv)
 	}
 }
 
-static void mlx5e_rep_unregister_vf_vports(struct mlx5e_priv *priv)
+void mlx5e_rep_unregister_vport_reps(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
 	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
 	int vport;
 
-	for (vport = 1; vport < total_vfs; vport++)
+	for (vport = total_vfs - 1; vport >= 0; vport--)
 		mlx5_eswitch_unregister_vport_rep(esw, vport, REP_ETH);
 }
 
-void mlx5e_register_vport_reps(struct mlx5e_priv *priv)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
-	struct mlx5_eswitch_rep_if rep_if;
-	struct mlx5e_rep_priv *rpriv;
-
-	rpriv = priv->ppriv;
-	rpriv->netdev = priv->netdev;
-
-	rep_if.load = mlx5e_nic_rep_load;
-	rep_if.unload = mlx5e_nic_rep_unload;
-	rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev;
-	rep_if.priv = rpriv;
-	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
-	mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_ETH); /* UPLINK PF vport*/
-
-	mlx5e_rep_register_vf_vports(priv); /* VFs vports */
-}
-
-void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
-
-	mlx5e_rep_unregister_vf_vports(priv); /* VFs vports */
-	mlx5_eswitch_unregister_vport_rep(esw, 0, REP_ETH); /* UPLINK PF*/
-}
-
 void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 2c8798332c32..07d5964356f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -162,8 +162,8 @@ struct mlx5e_rep_sq {
 };
 
 void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev);
-void mlx5e_register_vport_reps(struct mlx5e_priv *priv);
-void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv);
+void mlx5e_rep_register_vport_reps(struct mlx5e_priv *priv);
+void mlx5e_rep_unregister_vport_reps(struct mlx5e_priv *priv);
 bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
 int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
 void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
@@ -171,7 +171,6 @@ void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
 int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev, void *sp);
 bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id);
 
-int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr);
 void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 
 int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
@@ -181,11 +180,15 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
 
 void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
 #else /* CONFIG_MLX5_ESWITCH */
-static inline void mlx5e_register_vport_reps(struct mlx5e_priv *priv) {}
-static inline void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv) {}
+static inline void mlx5e_rep_register_vport_reps(struct mlx5e_priv *priv) {}
+static inline void mlx5e_rep_unregister_vport_reps(struct mlx5e_priv *priv) {}
 static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; }
 static inline int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv) {}
 #endif
 
+static inline bool mlx5e_is_vport_rep(struct mlx5e_priv *priv)
+{
+	return (MLX5_ESWITCH_MANAGER(priv->mdev) && priv->ppriv);
+}
 #endif /* __MLX5E_REP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 8224f1e062a8..3071a44e2f30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -486,7 +486,7 @@ static int mlx5e_grp_802_3_fill_stats(struct mlx5e_priv *priv, u64 *data,
 #define MLX5_BASIC_PPCNT_SUPPORTED(mdev) \
 	(MLX5_CAP_GEN(mdev, pcam_reg) ? MLX5_CAP_PCAM_REG(mdev, ppcnt) : 1)
 
-static void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv)
+void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv)
 {
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 	struct mlx5_core_dev *mdev = priv->mdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 3f8e870ef4c9..807e60582a6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -280,5 +280,6 @@ extern const struct mlx5e_stats_grp mlx5e_stats_grps[];
 extern const int mlx5e_num_stats_grps;
 
 void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv);
+void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv);
 
 #endif /* __MLX5_EN_STATS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 53ebb5a48018..c1a9120412b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -69,13 +69,13 @@ struct mlx5_nic_flow_attr {
 enum {
 	MLX5E_TC_FLOW_INGRESS	= MLX5E_TC_INGRESS,
 	MLX5E_TC_FLOW_EGRESS	= MLX5E_TC_EGRESS,
-	MLX5E_TC_FLOW_ESWITCH	= BIT(MLX5E_TC_FLOW_BASE),
-	MLX5E_TC_FLOW_NIC	= BIT(MLX5E_TC_FLOW_BASE + 1),
-	MLX5E_TC_FLOW_OFFLOADED	= BIT(MLX5E_TC_FLOW_BASE + 2),
-	MLX5E_TC_FLOW_HAIRPIN	= BIT(MLX5E_TC_FLOW_BASE + 3),
-	MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(MLX5E_TC_FLOW_BASE + 4),
-	MLX5E_TC_FLOW_SLOW	  = BIT(MLX5E_TC_FLOW_BASE + 5),
-	MLX5E_TC_FLOW_DUP         = BIT(MLX5E_TC_FLOW_BASE + 6),
+	MLX5E_TC_FLOW_ESWITCH	= MLX5E_TC_ESW_OFFLOAD,
+	MLX5E_TC_FLOW_NIC	= MLX5E_TC_NIC_OFFLOAD,
+	MLX5E_TC_FLOW_OFFLOADED	= BIT(MLX5E_TC_FLOW_BASE),
+	MLX5E_TC_FLOW_HAIRPIN	= BIT(MLX5E_TC_FLOW_BASE + 1),
+	MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(MLX5E_TC_FLOW_BASE + 2),
+	MLX5E_TC_FLOW_SLOW	  = BIT(MLX5E_TC_FLOW_BASE + 3),
+	MLX5E_TC_FLOW_DUP         = BIT(MLX5E_TC_FLOW_BASE + 4),
 };
 
 #define MLX5E_TC_MAX_SPLITS 1
@@ -834,7 +834,7 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
 	mlx5_del_flow_rules(flow->rule[0]);
 	mlx5_fc_destroy(priv->mdev, counter);
 
-	if (!mlx5e_tc_num_filters(priv) && priv->fs.tc.t) {
+	if (!mlx5e_tc_num_filters(priv, MLX5E_TC_NIC_OFFLOAD)  && priv->fs.tc.t) {
 		mlx5_destroy_flow_table(priv->fs.tc.t);
 		priv->fs.tc.t = NULL;
 	}
@@ -2686,6 +2686,11 @@ static void get_flags(int flags, u16 *flow_flags)
 	if (flags & MLX5E_TC_EGRESS)
 		__flow_flags |= MLX5E_TC_FLOW_EGRESS;
 
+	if (flags & MLX5E_TC_ESW_OFFLOAD)
+		__flow_flags |= MLX5E_TC_FLOW_ESWITCH;
+	if (flags & MLX5E_TC_NIC_OFFLOAD)
+		__flow_flags |= MLX5E_TC_FLOW_NIC;
+
 	*flow_flags = __flow_flags;
 }
 
@@ -2696,15 +2701,15 @@ static const struct rhashtable_params tc_ht_params = {
 	.automatic_shrinking = true,
 };
 
-static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv)
+static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv, int flags)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_rep_priv *uplink_rpriv;
 
-	if (MLX5_VPORT_MANAGER(priv->mdev) && esw->mode == SRIOV_OFFLOADS) {
+	if (flags & MLX5E_TC_ESW_OFFLOAD) {
 		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
 		return &uplink_rpriv->uplink_priv.tc_ht;
-	} else
+	} else /* NIC offload */
 		return &priv->fs.tc.ht;
 }
 
@@ -2973,7 +2978,7 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			   struct tc_cls_flower_offload *f, int flags)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
-	struct rhashtable *tc_ht = get_tc_ht(priv);
+	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
 	struct mlx5e_tc_flow *flow;
 	int err = 0;
 
@@ -3018,7 +3023,7 @@ static bool same_flow_direction(struct mlx5e_tc_flow *flow, int flags)
 int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			struct tc_cls_flower_offload *f, int flags)
 {
-	struct rhashtable *tc_ht = get_tc_ht(priv);
+	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
 	struct mlx5e_tc_flow *flow;
 
 	flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params);
@@ -3038,7 +3043,7 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		       struct tc_cls_flower_offload *f, int flags)
 {
 	struct mlx5_devcom *devcom = priv->mdev->priv.devcom;
-	struct rhashtable *tc_ht = get_tc_ht(priv);
+	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
 	struct mlx5_eswitch *peer_esw;
 	struct mlx5e_tc_flow *flow;
 	struct mlx5_fc *counter;
@@ -3168,7 +3173,7 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv)
 	if (tc->netdevice_nb.notifier_call)
 		unregister_netdevice_notifier(&tc->netdevice_nb);
 
-	rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, NULL);
+	rhashtable_destroy(&tc->ht);
 
 	if (!IS_ERR_OR_NULL(tc->t)) {
 		mlx5_destroy_flow_table(tc->t);
@@ -3186,9 +3191,9 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht)
 	rhashtable_free_and_destroy(tc_ht, _mlx5e_tc_del_flow, NULL);
 }
 
-int mlx5e_tc_num_filters(struct mlx5e_priv *priv)
+int mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags)
 {
-	struct rhashtable *tc_ht = get_tc_ht(priv);
+	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
 
 	return atomic_read(&tc_ht->nelems);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index a15c08a35054..d2d87f978c06 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -42,7 +42,9 @@
 enum {
 	MLX5E_TC_INGRESS = BIT(0),
 	MLX5E_TC_EGRESS  = BIT(1),
-	MLX5E_TC_LAST_EXPORTED_BIT = 1,
+	MLX5E_TC_NIC_OFFLOAD = BIT(2),
+	MLX5E_TC_ESW_OFFLOAD = BIT(3),
+	MLX5E_TC_LAST_EXPORTED_BIT = 3,
 };
 
 int mlx5e_tc_nic_init(struct mlx5e_priv *priv);
@@ -68,13 +70,13 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 struct mlx5e_neigh_hash_entry;
 void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe);
 
-int mlx5e_tc_num_filters(struct mlx5e_priv *priv);
+int mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags);
 
 
 #else /* CONFIG_MLX5_ESWITCH */
 static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}
-static inline int  mlx5e_tc_num_filters(struct mlx5e_priv *priv) { return 0; }
+static inline int  mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags) { return 0; }
 #endif
 
 #endif /* __MLX5_EN_TC_H__ */
-- 
cgit v1.2.3


From 13e509a4c1949855ddd5ef2e23bafdfb27b8337a Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 13 Feb 2018 18:14:42 +0200
Subject: net/mlx5e: Remove leftover code from the PF netdev being uplink rep

Remove some last leftovers from using the PF netdev as
the e-switch uplink representor.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |  20 +----
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  | 105 ++--------------------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h  |   3 -
 3 files changed, 9 insertions(+), 119 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cdd8b5efd96a..9ee50de4de33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4381,8 +4381,6 @@ const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_get_vf_config       = mlx5e_get_vf_config,
 	.ndo_set_vf_link_state   = mlx5e_set_vf_link_state,
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
-	.ndo_has_offload_stats	 = mlx5e_has_offload_stats,
-	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
 #endif
 };
 
@@ -5132,7 +5130,6 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv)
 static void *mlx5e_add(struct mlx5_core_dev *mdev)
 {
 	struct net_device *netdev;
-	void *rpriv = NULL;
 	void *priv;
 	int err;
 	int nch;
@@ -5141,21 +5138,11 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 	if (err)
 		return NULL;
 
-#ifdef CONFIG_MLX5_ESWITCH
-	if (MLX5_ESWITCH_MANAGER(mdev)) {
-		rpriv = mlx5e_alloc_nic_rep_priv(mdev);
-		if (!rpriv) {
-			mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n");
-			return NULL;
-		}
-	}
-#endif
-
 	nch = mlx5e_get_max_num_channels(mdev);
-	netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, nch, rpriv);
+	netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, nch, NULL);
 	if (!netdev) {
 		mlx5_core_err(mdev, "mlx5e_create_netdev failed\n");
-		goto err_free_rpriv;
+		return NULL;
 	}
 
 	priv = netdev_priv(netdev);
@@ -5181,8 +5168,6 @@ err_detach:
 	mlx5e_detach(mdev, priv);
 err_destroy_netdev:
 	mlx5e_destroy_netdev(priv);
-err_free_rpriv:
-	kfree(rpriv);
 	return NULL;
 }
 
@@ -5197,7 +5182,6 @@ static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 	unregister_netdev(priv->netdev);
 	mlx5e_detach(mdev, vpriv);
 	mlx5e_destroy_netdev(priv);
-	kfree(ppriv);
 }
 
 static struct mlx5_interface mlx5e_interface = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index b48ba3234ac5..73c6f24771bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1139,22 +1139,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 	return (rep->vport == FDB_UPLINK_VPORT);
 }
 
-static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
-{
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep;
-
-	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
-		return false;
-
-	rep = rpriv->rep;
-	if (rep && rep->vport != FDB_UPLINK_VPORT)
-		return true;
-
-	return false;
-}
-
-bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id)
+static bool mlx5e_rep_has_offload_stats(const struct net_device *dev, int attr_id)
 {
 	switch (attr_id) {
 	case IFLA_OFFLOAD_XSTATS_CPU_HIT:
@@ -1183,8 +1168,8 @@ mlx5e_get_sw_stats64(const struct net_device *dev,
 	return 0;
 }
 
-int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev,
-			    void *sp)
+static int mlx5e_rep_get_offload_stats(int attr_id, const struct net_device *dev,
+				       void *sp)
 {
 	switch (attr_id) {
 	case IFLA_OFFLOAD_XSTATS_CPU_HIT:
@@ -1235,8 +1220,8 @@ static const struct net_device_ops mlx5e_netdev_ops_vf_rep = {
 	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
 	.ndo_setup_tc            = mlx5e_rep_setup_tc,
 	.ndo_get_stats64         = mlx5e_vf_rep_get_stats,
-	.ndo_has_offload_stats	 = mlx5e_has_offload_stats,
-	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
+	.ndo_has_offload_stats	 = mlx5e_rep_has_offload_stats,
+	.ndo_get_offload_stats	 = mlx5e_rep_get_offload_stats,
 	.ndo_change_mtu          = mlx5e_vf_rep_change_mtu,
 };
 
@@ -1247,8 +1232,8 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = {
 	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
 	.ndo_setup_tc            = mlx5e_rep_setup_tc,
 	.ndo_get_stats64         = mlx5e_get_stats,
-	.ndo_has_offload_stats	 = mlx5e_has_offload_stats,
-	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
+	.ndo_has_offload_stats	 = mlx5e_rep_has_offload_stats,
+	.ndo_get_offload_stats	 = mlx5e_rep_get_offload_stats,
 	.ndo_change_mtu          = mlx5e_uplink_rep_change_mtu,
 };
 
@@ -1550,69 +1535,6 @@ static const struct mlx5e_profile mlx5e_rep_profile = {
 };
 
 /* e-Switch vport representors */
-
-static int
-mlx5e_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
-{
-	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
-	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
-	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
-	int err;
-
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		err = mlx5e_add_sqs_fwd_rules(priv);
-		if (err)
-			return err;
-	}
-
-	err = mlx5e_rep_neigh_init(rpriv);
-	if (err)
-		goto err_remove_sqs;
-
-	/* init shared tc flow table */
-	err = mlx5e_tc_esw_init(&uplink_priv->tc_ht);
-	if (err)
-		goto  err_neigh_cleanup;
-
-	/* init indirect block notifications */
-	INIT_LIST_HEAD(&uplink_priv->tc_indr_block_priv_list);
-	uplink_priv->netdevice_nb.notifier_call = mlx5e_nic_rep_netdevice_event;
-	err = register_netdevice_notifier(&uplink_priv->netdevice_nb);
-	if (err) {
-		mlx5_core_err(priv->mdev, "Failed to register netdev notifier\n");
-		goto err_indirect_block_cleanup;
-	}
-
-	return 0;
-
-err_indirect_block_cleanup:
-	mlx5e_tc_esw_cleanup(&uplink_priv->tc_ht);
-err_neigh_cleanup:
-	mlx5e_rep_neigh_cleanup(rpriv);
-err_remove_sqs:
-	mlx5e_remove_sqs_fwd_rules(priv);
-	return err;
-}
-
-static void
-mlx5e_nic_rep_unload(struct mlx5_eswitch_rep *rep)
-{
-	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
-	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
-
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
-		mlx5e_remove_sqs_fwd_rules(priv);
-
-	/* clean indirect TC block notifications */
-	unregister_netdevice_notifier(&rpriv->uplink_priv.netdevice_nb);
-	mlx5e_rep_indr_clean_block_privs(rpriv);
-
-	/* clean uplink offloaded TC rules, delete shared tc flow table */
-	mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht);
-
-	mlx5e_rep_neigh_cleanup(rpriv);
-}
-
 static int
 mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
@@ -1726,16 +1648,3 @@ void mlx5e_rep_unregister_vport_reps(struct mlx5e_priv *priv)
 	for (vport = total_vfs - 1; vport >= 0; vport--)
 		mlx5_eswitch_unregister_vport_rep(esw, vport, REP_ETH);
 }
-
-void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev)
-{
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	struct mlx5e_rep_priv *rpriv;
-
-	rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL);
-	if (!rpriv)
-		return NULL;
-
-	rpriv->rep = &esw->offloads.vport_reps[0];
-	return rpriv;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 07d5964356f1..bb2d2484eb64 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -168,9 +168,6 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
 int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
 void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
 
-int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev, void *sp);
-bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id);
-
 void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 
 int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
-- 
cgit v1.2.3


From aec002f6f82cbfb39f92605614a88dd7a200a766 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Wed, 7 Nov 2018 16:34:52 +0200
Subject: net/mlx5e: Uninstantiate esw manager vport netdev on switchdev mode

Now, when we have a dedicated uplink representor, the netdev instance
set over the esw manager vport (PF) is of no-use. As such, remove it
once we're on switchdev mode and get it back to life when off switchdev.

This is done by reloading the Ethernet interface as well (we already
do that for the IB interface) from the eswitch code while going in/out
of switchdev mode.

The Eth add/remove entries are modified to act differently when called in
switchdev mode. In this case we only deal with registration of the eth
vport representors. The rep netdevices are created from the eswitch call
to load the registered eth representors.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 24 +++++++++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  | 22 +++++++++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h  |  6 ++----
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 11 ++++++++---
 4 files changed, 42 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9ee50de4de33..0fd5752fb181 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4894,9 +4894,6 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	if (mlx5e_monitor_counter_supported(priv))
 		mlx5e_monitor_counter_init(priv);
 
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
-		mlx5e_rep_register_vport_reps(priv);
-
 	if (netdev->reg_state != NETREG_REGISTERED)
 		return;
 #ifdef CONFIG_MLX5_CORE_EN_DCB
@@ -4929,9 +4926,6 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
-		mlx5e_rep_unregister_vport_reps(priv);
-
 	if (mlx5e_monitor_counter_supported(priv))
 		mlx5e_monitor_counter_cleanup(priv);
 
@@ -5138,6 +5132,14 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 	if (err)
 		return NULL;
 
+#ifdef CONFIG_MLX5_ESWITCH
+	if (MLX5_ESWITCH_MANAGER(mdev) &&
+	    mlx5_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
+		mlx5e_rep_register_vport_reps(mdev);
+		return mdev;
+	}
+#endif
+
 	nch = mlx5e_get_max_num_channels(mdev);
 	netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, nch, NULL);
 	if (!netdev) {
@@ -5173,9 +5175,15 @@ err_destroy_netdev:
 
 static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 {
-	struct mlx5e_priv *priv = vpriv;
-	void *ppriv = priv->ppriv;
+	struct mlx5e_priv *priv;
 
+#ifdef CONFIG_MLX5_ESWITCH
+	if (MLX5_ESWITCH_MANAGER(mdev) && vpriv == mdev) {
+		mlx5e_rep_unregister_vport_reps(mdev);
+		return;
+	}
+#endif
+	priv = vpriv;
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_delete_app(priv);
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 73c6f24771bd..e4f8f639dea0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1562,11 +1562,17 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	rep->rep_if[REP_ETH].priv = rpriv;
 	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
 
+	if (rep->vport == FDB_UPLINK_VPORT) {
+		err = mlx5e_create_mdev_resources(dev);
+		if (err)
+			goto err_destroy_netdev;
+	}
+
 	err = mlx5e_attach_netdev(netdev_priv(netdev));
 	if (err) {
 		pr_warn("Failed to attach representor netdev for vport %d\n",
 			rep->vport);
-		goto err_destroy_netdev;
+		goto err_destroy_mdev_resources;
 	}
 
 	err = mlx5e_rep_neigh_init(rpriv);
@@ -1591,6 +1597,10 @@ err_neigh_cleanup:
 err_detach_netdev:
 	mlx5e_detach_netdev(netdev_priv(netdev));
 
+err_destroy_mdev_resources:
+	if (rep->vport == FDB_UPLINK_VPORT)
+		mlx5e_destroy_mdev_resources(dev);
+
 err_destroy_netdev:
 	mlx5e_destroy_netdev(netdev_priv(netdev));
 	kfree(rpriv);
@@ -1608,6 +1618,8 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	unregister_netdev(netdev);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_detach_netdev(priv);
+	if (rep->vport == FDB_UPLINK_VPORT)
+		mlx5e_destroy_mdev_resources(priv->mdev);
 	mlx5e_destroy_netdev(priv);
 	kfree(ppriv); /* mlx5e_rep_priv */
 }
@@ -1621,10 +1633,9 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep)
 	return rpriv->netdev;
 }
 
-void mlx5e_rep_register_vport_reps(struct mlx5e_priv *priv)
+void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
 	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
 	int vport;
 
@@ -1638,9 +1649,8 @@ void mlx5e_rep_register_vport_reps(struct mlx5e_priv *priv)
 	}
 }
 
-void mlx5e_rep_unregister_vport_reps(struct mlx5e_priv *priv)
+void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
 	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
 	int vport;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index bb2d2484eb64..5645d3cef1bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -162,8 +162,8 @@ struct mlx5e_rep_sq {
 };
 
 void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev);
-void mlx5e_rep_register_vport_reps(struct mlx5e_priv *priv);
-void mlx5e_rep_unregister_vport_reps(struct mlx5e_priv *priv);
+void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev);
+void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev);
 bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
 int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
 void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
@@ -177,8 +177,6 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
 
 void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
 #else /* CONFIG_MLX5_ESWITCH */
-static inline void mlx5e_rep_register_vport_reps(struct mlx5e_priv *priv) {}
-static inline void mlx5e_rep_unregister_vport_reps(struct mlx5e_priv *priv) {}
 static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; }
 static inline int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv) {}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index ef2bec50423d..a44ea7b85614 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1630,6 +1630,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 		esw_warn(esw->dev, "E-Switch engress ACL is not supported by FW\n");
 
 	esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode);
+
 	esw->mode = mode;
 
 	mlx5_lag_update(esw->dev);
@@ -1637,8 +1638,8 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	if (mode == SRIOV_LEGACY) {
 		err = esw_create_legacy_fdb_table(esw);
 	} else {
+		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-
 		err = esw_offloads_init(esw, nvfs + 1);
 	}
 
@@ -1669,8 +1670,10 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 abort:
 	esw->mode = SRIOV_NONE;
 
-	if (mode == SRIOV_OFFLOADS)
+	if (mode == SRIOV_OFFLOADS) {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
+	}
 
 	return err;
 }
@@ -1712,8 +1715,10 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 
 	mlx5_lag_update(esw->dev);
 
-	if (old_mode == SRIOV_OFFLOADS)
+	if (old_mode == SRIOV_OFFLOADS) {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
+	}
 }
 
 int mlx5_eswitch_init(struct mlx5_core_dev *dev)
-- 
cgit v1.2.3


From b36cdb42ad4b114d4b9bbba8770d7a4b8e1a62f6 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 8 Nov 2018 20:42:55 +0200
Subject: net/mlx5e: Handle port mtu/link, dcb and lag for uplink reps

Take care of setup/teardown for the port link, dcb, lag as well as
dealing with port mtu and carrier for e-switch uplink representors.

This is achieved by adding a dedicated profile instance for uplink
representors which includes the enable/disable and more profile routines
which are invoked by the general mlx5e code for netdev attach/detach.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  | 119 ++++++++++++++++++----
 3 files changed, 102 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 31deafecf679..71c0646c8108 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -940,6 +940,7 @@ int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
 
 int mlx5e_create_tises(struct mlx5e_priv *priv);
+void mlx5e_update_carrier(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
 int mlx5e_open(struct net_device *netdev);
 void mlx5e_update_ndo_stats(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0fd5752fb181..0af61ef3cebb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -225,7 +225,7 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 		MLX5_WQ_TYPE_CYCLIC;
 }
 
-static void mlx5e_update_carrier(struct mlx5e_priv *priv)
+void mlx5e_update_carrier(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 port_state;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index e4f8f639dea0..e676660826fc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1194,19 +1194,20 @@ static int mlx5e_vf_rep_change_mtu(struct net_device *netdev, int new_mtu)
 	return mlx5e_change_mtu(netdev, new_mtu, NULL);
 }
 
-static int mlx5e_uplink_rep_open(struct net_device *dev)
+static int mlx5e_uplink_rep_change_mtu(struct net_device *netdev, int new_mtu)
 {
-	int err;
-
-	err = mlx5e_open(dev);
-	if (!err)
-		netif_carrier_on(dev);
-	return err;
+	return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu);
 }
 
-static int mlx5e_uplink_rep_change_mtu(struct net_device *netdev, int new_mtu)
+static int mlx5e_uplink_rep_set_mac(struct net_device *netdev, void *addr)
 {
-	return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu);
+	struct sockaddr *saddr = addr;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	ether_addr_copy(netdev->dev_addr, saddr->sa_data);
+	return 0;
 }
 
 static const struct switchdev_ops mlx5e_rep_switchdev_ops = {
@@ -1226,9 +1227,10 @@ static const struct net_device_ops mlx5e_netdev_ops_vf_rep = {
 };
 
 static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = {
-	.ndo_open                = mlx5e_uplink_rep_open,
+	.ndo_open                = mlx5e_open,
 	.ndo_stop                = mlx5e_close,
 	.ndo_start_xmit          = mlx5e_xmit,
+	.ndo_set_mac_address     = mlx5e_uplink_rep_set_mac,
 	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
 	.ndo_setup_tc            = mlx5e_rep_setup_tc,
 	.ndo_get_stats64         = mlx5e_get_stats,
@@ -1280,13 +1282,16 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 max_mtu;
 
 	if (rep->vport == FDB_UPLINK_VPORT) {
 		SET_NETDEV_DEV(netdev, &priv->mdev->pdev->dev);
 		netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep;
 		/* we want a persistent mac for the uplink rep */
 		mlx5_query_nic_vport_mac_address(mdev, 0, netdev->dev_addr);
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+		if (MLX5_CAP_GEN(mdev, qos))
+			netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
+#endif
 	} else {
 		netdev->netdev_ops = &mlx5e_netdev_ops_vf_rep;
 		eth_hw_addr_random(netdev);
@@ -1310,10 +1315,6 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	netdev->hw_features    |= NETIF_F_RXCSUM;
 
 	netdev->features |= netdev->hw_features;
-
-	netdev->min_mtu = ETH_MIN_MTU;
-	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
-	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
 }
 
 static int mlx5e_rep_get_default_num_channels(struct mlx5_eswitch_rep *rep,
@@ -1520,24 +1521,103 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
 	}
 }
 
-static const struct mlx5e_profile mlx5e_rep_profile = {
+static void mlx5e_vf_rep_enable(struct mlx5e_priv *priv)
+{
+	struct net_device *netdev = priv->netdev;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u16 max_mtu;
+
+	netdev->min_mtu = ETH_MIN_MTU;
+	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
+	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+}
+
+static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event, void *data)
+{
+	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
+	struct mlx5_eqe   *eqe = data;
+
+	if (event != MLX5_EVENT_TYPE_PORT_CHANGE)
+		return NOTIFY_DONE;
+
+	switch (eqe->sub_type) {
+	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+		queue_work(priv->wq, &priv->update_carrier_work);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
+{
+	struct net_device *netdev = priv->netdev;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u16 max_mtu;
+
+	netdev->min_mtu = ETH_MIN_MTU;
+	mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
+	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+	mlx5e_set_dev_port_mtu(priv);
+
+	mlx5_lag_add(mdev, netdev);
+	priv->events_nb.notifier_call = uplink_rep_async_event;
+	mlx5_notifier_register(mdev, &priv->events_nb);
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+	mlx5e_dcbnl_initialize(priv);
+	mlx5e_dcbnl_init_app(priv);
+#endif
+}
+
+static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+	mlx5e_dcbnl_delete_app(priv);
+#endif
+	mlx5_notifier_unregister(mdev, &priv->events_nb);
+	mlx5_lag_remove(mdev);
+}
+
+static const struct mlx5e_profile mlx5e_vf_rep_profile = {
 	.init			= mlx5e_init_rep,
 	.cleanup		= mlx5e_cleanup_rep,
 	.init_rx		= mlx5e_init_rep_rx,
 	.cleanup_rx		= mlx5e_cleanup_rep_rx,
 	.init_tx		= mlx5e_init_rep_tx,
 	.cleanup_tx		= mlx5e_cleanup_rep_tx,
-	.update_stats           = mlx5e_rep_update_hw_counters,
-	.update_carrier		= NULL,
+	.enable		        = mlx5e_vf_rep_enable,
+	.update_stats           = mlx5e_vf_rep_update_hw_counters,
 	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
 	.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
 	.max_tc			= 1,
 };
 
+static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
+	.init			= mlx5e_init_rep,
+	.cleanup		= mlx5e_cleanup_rep,
+	.init_rx		= mlx5e_init_rep_rx,
+	.cleanup_rx		= mlx5e_cleanup_rep_rx,
+	.init_tx		= mlx5e_init_rep_tx,
+	.cleanup_tx		= mlx5e_cleanup_rep_tx,
+	.enable		        = mlx5e_uplink_rep_enable,
+	.disable	        = mlx5e_uplink_rep_disable,
+	.update_stats           = mlx5e_uplink_rep_update_hw_counters,
+	.update_carrier	        = mlx5e_update_carrier,
+	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
+	.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
+	.max_tc			= MLX5E_MAX_NUM_TC,
+};
+
 /* e-Switch vport representors */
 static int
 mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
+	const struct mlx5e_profile *profile;
 	struct mlx5e_rep_priv *rpriv;
 	struct net_device *netdev;
 	int nch, err;
@@ -1550,7 +1630,8 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	rpriv->rep = rep;
 
 	nch = mlx5e_get_max_num_channels(dev);
-	netdev = mlx5e_create_netdev(dev, &mlx5e_rep_profile, nch, rpriv);
+	profile = (rep->vport == FDB_UPLINK_VPORT) ? &mlx5e_uplink_rep_profile : &mlx5e_vf_rep_profile;
+	netdev = mlx5e_create_netdev(dev, profile, nch, rpriv);
 	if (!netdev) {
 		pr_warn("Failed to create representor netdev for vport %d\n",
 			rep->vport);
-- 
cgit v1.2.3


From 073caf508822750cde02086a6ac1b9131e69692c Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 1 Nov 2018 19:14:21 +0200
Subject: net/mlx5e: Add sriov and udp tunnel ndo support for the uplink rep

Some of the sriov ndo calls are needed also on the switchdev mode -
e.g setup VF mac and reading vport stats. Add them to the uplink rep
netdev ops. Same for the UDP tunnel ones, need them there to identify
offloaded udp tunnel ports.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 12 +++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 26 +++++++++++------------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  |  7 ++++++
 3 files changed, 31 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 71c0646c8108..16fe9e9a14c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1004,4 +1004,16 @@ void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
 u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
 void mlx5e_rx_dim_work(struct work_struct *work);
 void mlx5e_tx_dim_work(struct work_struct *work);
+
+void mlx5e_add_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti);
+void mlx5e_del_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti);
+netdev_features_t mlx5e_features_check(struct sk_buff *skb,
+				       struct net_device *netdev,
+				       netdev_features_t features);
+#ifdef CONFIG_MLX5_ESWITCH
+int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac);
+int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate);
+int mlx5e_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi);
+int mlx5e_get_vf_stats(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats);
+#endif
 #endif /* __MLX5_EN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0af61ef3cebb..cd6872a9e4dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3899,7 +3899,7 @@ static int mlx5e_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 }
 
 #ifdef CONFIG_MLX5_ESWITCH
-static int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
+int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -3936,8 +3936,8 @@ static int mlx5e_set_vf_trust(struct net_device *dev, int vf, bool setting)
 	return mlx5_eswitch_set_vport_trust(mdev->priv.eswitch, vf + 1, setting);
 }
 
-static int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
-			     int max_tx_rate)
+int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
+		      int max_tx_rate)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -3978,8 +3978,8 @@ static int mlx5e_set_vf_link_state(struct net_device *dev, int vf,
 					    mlx5_ifla_link2vport(link_state));
 }
 
-static int mlx5e_get_vf_config(struct net_device *dev,
-			       int vf, struct ifla_vf_info *ivi)
+int mlx5e_get_vf_config(struct net_device *dev,
+			int vf, struct ifla_vf_info *ivi)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -3992,8 +3992,8 @@ static int mlx5e_get_vf_config(struct net_device *dev,
 	return 0;
 }
 
-static int mlx5e_get_vf_stats(struct net_device *dev,
-			      int vf, struct ifla_vf_stats *vf_stats)
+int mlx5e_get_vf_stats(struct net_device *dev,
+		       int vf, struct ifla_vf_stats *vf_stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -4054,8 +4054,7 @@ static void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, u16 port, int add)
 	queue_work(priv->wq, &vxlan_work->work);
 }
 
-static void mlx5e_add_vxlan_port(struct net_device *netdev,
-				 struct udp_tunnel_info *ti)
+void mlx5e_add_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -4068,8 +4067,7 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev,
 	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 1);
 }
 
-static void mlx5e_del_vxlan_port(struct net_device *netdev,
-				 struct udp_tunnel_info *ti)
+void mlx5e_del_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -4119,9 +4117,9 @@ out:
 	return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
 }
 
-static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
-					      struct net_device *netdev,
-					      netdev_features_t features)
+netdev_features_t mlx5e_features_check(struct sk_buff *skb,
+				       struct net_device *netdev,
+				       netdev_features_t features)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index e676660826fc..f557aed54564 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1237,6 +1237,13 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = {
 	.ndo_has_offload_stats	 = mlx5e_rep_has_offload_stats,
 	.ndo_get_offload_stats	 = mlx5e_rep_get_offload_stats,
 	.ndo_change_mtu          = mlx5e_uplink_rep_change_mtu,
+	.ndo_udp_tunnel_add      = mlx5e_add_vxlan_port,
+	.ndo_udp_tunnel_del      = mlx5e_del_vxlan_port,
+	.ndo_features_check      = mlx5e_features_check,
+	.ndo_set_vf_mac          = mlx5e_set_vf_mac,
+	.ndo_set_vf_rate         = mlx5e_set_vf_rate,
+	.ndo_get_vf_config       = mlx5e_get_vf_config,
+	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
 };
 
 static void mlx5e_build_rep_params(struct net_device *netdev)
-- 
cgit v1.2.3


From 371289b61ac1ac890c7e98b1bfd3b8f32e38efae Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 6 Nov 2018 19:31:10 +0200
Subject: net/mlx5e: Expose ethtool pause and link functions to mlx5e callers

Towards supporting set/get of global pause for the port
and get of the port link ksetting from the uplink representor,
expose the relevant entries to other mlx5 callers.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  8 +++
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   | 68 +++++++++++++++-------
 2 files changed, 56 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 16fe9e9a14c6..72cc204f9a34 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -973,12 +973,20 @@ int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv,
 			       struct ethtool_coalesce *coal);
 int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 			       struct ethtool_coalesce *coal);
+int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
+				     struct ethtool_link_ksettings *link_ksettings);
+int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
+				     const struct ethtool_link_ksettings *link_ksettings);
 u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv);
 u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv);
 int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 			      struct ethtool_ts_info *info);
 int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 			       struct ethtool_flash *flash);
+void mlx5e_ethtool_get_pauseparam(struct mlx5e_priv *priv,
+				  struct ethtool_pauseparam *pauseparam);
+int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv,
+				 struct ethtool_pauseparam *pauseparam);
 
 /* mlx5e generic netdev management API */
 int mlx5e_netdev_init(struct net_device *netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index da4bb62ac528..6af587cf147f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -787,10 +787,9 @@ static void get_lp_advertising(u32 eth_proto_lp,
 	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp);
 }
 
-static int mlx5e_get_link_ksettings(struct net_device *netdev,
-				    struct ethtool_link_ksettings *link_ksettings)
+int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
+				     struct ethtool_link_ksettings *link_ksettings)
 {
-	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
 	u32 rx_pause = 0;
@@ -806,7 +805,7 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 
 	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1);
 	if (err) {
-		netdev_err(netdev, "%s: query port ptys failed: %d\n",
+		netdev_err(priv->netdev, "%s: query port ptys failed: %d\n",
 			   __func__, err);
 		goto err_query_regs;
 	}
@@ -826,7 +825,7 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 
 	get_supported(eth_proto_cap, link_ksettings);
 	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings);
-	get_speed_duplex(netdev, eth_proto_oper, link_ksettings);
+	get_speed_duplex(priv->netdev, eth_proto_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
 
@@ -846,7 +845,7 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 					     Autoneg);
 
 	if (get_fec_supported_advertised(mdev, link_ksettings))
-		netdev_dbg(netdev, "%s: FEC caps query failed: %d\n",
+		netdev_dbg(priv->netdev, "%s: FEC caps query failed: %d\n",
 			   __func__, err);
 
 	if (!an_disable_admin)
@@ -857,6 +856,14 @@ err_query_regs:
 	return err;
 }
 
+static int mlx5e_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings *link_ksettings)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_get_link_ksettings(priv, link_ksettings);
+}
+
 static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 {
 	u32 i, ptys_modes = 0;
@@ -871,10 +878,9 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 	return ptys_modes;
 }
 
-static int mlx5e_set_link_ksettings(struct net_device *netdev,
-				    const struct ethtool_link_ksettings *link_ksettings)
+int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
+				     const struct ethtool_link_ksettings *link_ksettings)
 {
-	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 eth_proto_cap, eth_proto_admin;
 	bool an_changes = false;
@@ -894,14 +900,14 @@ static int mlx5e_set_link_ksettings(struct net_device *netdev,
 
 	err = mlx5_query_port_proto_cap(mdev, &eth_proto_cap, MLX5_PTYS_EN);
 	if (err) {
-		netdev_err(netdev, "%s: query port eth proto cap failed: %d\n",
+		netdev_err(priv->netdev, "%s: query port eth proto cap failed: %d\n",
 			   __func__, err);
 		goto out;
 	}
 
 	link_modes = link_modes & eth_proto_cap;
 	if (!link_modes) {
-		netdev_err(netdev, "%s: Not supported link mode(s) requested",
+		netdev_err(priv->netdev, "%s: Not supported link mode(s) requested",
 			   __func__);
 		err = -EINVAL;
 		goto out;
@@ -909,7 +915,7 @@ static int mlx5e_set_link_ksettings(struct net_device *netdev,
 
 	err = mlx5_query_port_proto_admin(mdev, &eth_proto_admin, MLX5_PTYS_EN);
 	if (err) {
-		netdev_err(netdev, "%s: query port eth proto admin failed: %d\n",
+		netdev_err(priv->netdev, "%s: query port eth proto admin failed: %d\n",
 			   __func__, err);
 		goto out;
 	}
@@ -931,6 +937,14 @@ out:
 	return err;
 }
 
+static int mlx5e_set_link_ksettings(struct net_device *netdev,
+				    const struct ethtool_link_ksettings *link_ksettings)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_set_link_ksettings(priv, link_ksettings);
+}
+
 u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv)
 {
 	return sizeof(priv->rss_params.toeplitz_hash_key);
@@ -1127,25 +1141,31 @@ static int mlx5e_set_tunable(struct net_device *dev,
 	return err;
 }
 
-static void mlx5e_get_pauseparam(struct net_device *netdev,
-				 struct ethtool_pauseparam *pauseparam)
+void mlx5e_ethtool_get_pauseparam(struct mlx5e_priv *priv,
+				  struct ethtool_pauseparam *pauseparam)
 {
-	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
 	err = mlx5_query_port_pause(mdev, &pauseparam->rx_pause,
 				    &pauseparam->tx_pause);
 	if (err) {
-		netdev_err(netdev, "%s: mlx5_query_port_pause failed:0x%x\n",
+		netdev_err(priv->netdev, "%s: mlx5_query_port_pause failed:0x%x\n",
 			   __func__, err);
 	}
 }
 
-static int mlx5e_set_pauseparam(struct net_device *netdev,
-				struct ethtool_pauseparam *pauseparam)
+static void mlx5e_get_pauseparam(struct net_device *netdev,
+				 struct ethtool_pauseparam *pauseparam)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	mlx5e_ethtool_get_pauseparam(priv, pauseparam);
+}
+
+int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv,
+				 struct ethtool_pauseparam *pauseparam)
 {
-	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
@@ -1156,13 +1176,21 @@ static int mlx5e_set_pauseparam(struct net_device *netdev,
 				  pauseparam->rx_pause ? 1 : 0,
 				  pauseparam->tx_pause ? 1 : 0);
 	if (err) {
-		netdev_err(netdev, "%s: mlx5_set_port_pause failed:0x%x\n",
+		netdev_err(priv->netdev, "%s: mlx5_set_port_pause failed:0x%x\n",
 			   __func__, err);
 	}
 
 	return err;
 }
 
+static int mlx5e_set_pauseparam(struct net_device *netdev,
+				struct ethtool_pauseparam *pauseparam)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_set_pauseparam(priv, pauseparam);
+}
+
 int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 			      struct ethtool_ts_info *info)
 {
-- 
cgit v1.2.3


From ff9b85de5d5d292fa07869f194fd9e3966f1e720 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 6 Nov 2018 19:49:22 +0200
Subject: net/mlx5e: Add some ethtool port control entries to the uplink rep
 netdev

Some of the ethtool entries to control the port should be supported by
the uplink rep netdev in switchdev mode, add them.

While here, add also the get/set coalesce entries for all reps.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 75 +++++++++++++++++++++++-
 1 file changed, 73 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index f557aed54564..ed1158b58798 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -292,6 +292,22 @@ static int mlx5e_rep_set_channels(struct net_device *dev,
 	return 0;
 }
 
+static int mlx5e_rep_get_coalesce(struct net_device *netdev,
+				  struct ethtool_coalesce *coal)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_get_coalesce(priv, coal);
+}
+
+static int mlx5e_rep_set_coalesce(struct net_device *netdev,
+				  struct ethtool_coalesce *coal)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_set_coalesce(priv, coal);
+}
+
 static u32 mlx5e_rep_get_rxfh_key_size(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -306,7 +322,55 @@ static u32 mlx5e_rep_get_rxfh_indir_size(struct net_device *netdev)
 	return mlx5e_ethtool_get_rxfh_indir_size(priv);
 }
 
-static const struct ethtool_ops mlx5e_rep_ethtool_ops = {
+static void mlx5e_uplink_rep_get_pauseparam(struct net_device *netdev,
+					    struct ethtool_pauseparam *pauseparam)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	mlx5e_ethtool_get_pauseparam(priv, pauseparam);
+}
+
+static int mlx5e_uplink_rep_set_pauseparam(struct net_device *netdev,
+					   struct ethtool_pauseparam *pauseparam)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_set_pauseparam(priv, pauseparam);
+}
+
+static int mlx5e_uplink_rep_get_link_ksettings(struct net_device *netdev,
+					       struct ethtool_link_ksettings *link_ksettings)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_get_link_ksettings(priv, link_ksettings);
+}
+
+static int mlx5e_uplink_rep_set_link_ksettings(struct net_device *netdev,
+					       const struct ethtool_link_ksettings *link_ksettings)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_set_link_ksettings(priv, link_ksettings);
+}
+
+static const struct ethtool_ops mlx5e_vf_rep_ethtool_ops = {
+	.get_drvinfo	   = mlx5e_rep_get_drvinfo,
+	.get_link	   = ethtool_op_get_link,
+	.get_strings       = mlx5e_rep_get_strings,
+	.get_sset_count    = mlx5e_rep_get_sset_count,
+	.get_ethtool_stats = mlx5e_rep_get_ethtool_stats,
+	.get_ringparam     = mlx5e_rep_get_ringparam,
+	.set_ringparam     = mlx5e_rep_set_ringparam,
+	.get_channels      = mlx5e_rep_get_channels,
+	.set_channels      = mlx5e_rep_set_channels,
+	.get_coalesce      = mlx5e_rep_get_coalesce,
+	.set_coalesce      = mlx5e_rep_set_coalesce,
+	.get_rxfh_key_size   = mlx5e_rep_get_rxfh_key_size,
+	.get_rxfh_indir_size = mlx5e_rep_get_rxfh_indir_size,
+};
+
+static const struct ethtool_ops mlx5e_uplink_rep_ethtool_ops = {
 	.get_drvinfo	   = mlx5e_rep_get_drvinfo,
 	.get_link	   = ethtool_op_get_link,
 	.get_strings       = mlx5e_rep_get_strings,
@@ -316,8 +380,14 @@ static const struct ethtool_ops mlx5e_rep_ethtool_ops = {
 	.set_ringparam     = mlx5e_rep_set_ringparam,
 	.get_channels      = mlx5e_rep_get_channels,
 	.set_channels      = mlx5e_rep_set_channels,
+	.get_coalesce      = mlx5e_rep_get_coalesce,
+	.set_coalesce      = mlx5e_rep_set_coalesce,
+	.get_link_ksettings = mlx5e_uplink_rep_get_link_ksettings,
+	.set_link_ksettings = mlx5e_uplink_rep_set_link_ksettings,
 	.get_rxfh_key_size   = mlx5e_rep_get_rxfh_key_size,
 	.get_rxfh_indir_size = mlx5e_rep_get_rxfh_indir_size,
+	.get_pauseparam    = mlx5e_uplink_rep_get_pauseparam,
+	.set_pauseparam    = mlx5e_uplink_rep_set_pauseparam,
 };
 
 static int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
@@ -1295,6 +1365,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 		netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep;
 		/* we want a persistent mac for the uplink rep */
 		mlx5_query_nic_vport_mac_address(mdev, 0, netdev->dev_addr);
+		netdev->ethtool_ops = &mlx5e_uplink_rep_ethtool_ops;
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 		if (MLX5_CAP_GEN(mdev, qos))
 			netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
@@ -1302,11 +1373,11 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	} else {
 		netdev->netdev_ops = &mlx5e_netdev_ops_vf_rep;
 		eth_hw_addr_random(netdev);
+		netdev->ethtool_ops = &mlx5e_vf_rep_ethtool_ops;
 	}
 
 	netdev->watchdog_timeo    = 15 * HZ;
 
-	netdev->ethtool_ops	  = &mlx5e_rep_ethtool_ops;
 
 	netdev->switchdev_ops = &mlx5e_rep_switchdev_ops;
 
-- 
cgit v1.2.3


From 4beaacc6fea5a5ec43c55c22a6c83c03a5ecc775 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 13 Dec 2018 03:03:37 -0800
Subject: net/mlx4_en: remove fallback after kzalloc_node()

kzalloc_node(..., GFP_KERNEL, node) will attempt to allocate
memory as close as possible to the node.

There is no need to fallback to kzalloc() if this has failed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_cq.c | 7 ++-----
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 7 ++-----
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 7 ++-----
 3 files changed, 6 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 062a88fcc5d6..74d466796b7c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -54,11 +54,8 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 
 	cq = kzalloc_node(sizeof(*cq), GFP_KERNEL, node);
 	if (!cq) {
-		cq = kzalloc(sizeof(*cq), GFP_KERNEL);
-		if (!cq) {
-			en_err(priv, "Failed to allocate CQ structure\n");
-			return -ENOMEM;
-		}
+		en_err(priv, "Failed to allocate CQ structure\n");
+		return -ENOMEM;
 	}
 
 	cq->size = entries;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index fd09ba98c0a6..9a0881cb7f51 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -271,11 +271,8 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 
 	ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, node);
 	if (!ring) {
-		ring = kzalloc(sizeof(*ring), GFP_KERNEL);
-		if (!ring) {
-			en_err(priv, "Failed to allocate RX ring structure\n");
-			return -ENOMEM;
-		}
+		en_err(priv, "Failed to allocate RX ring structure\n");
+		return -ENOMEM;
 	}
 
 	ring->prod = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 6f5153afcab4..2cbd2bd7c67c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -57,11 +57,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 
 	ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, node);
 	if (!ring) {
-		ring = kzalloc(sizeof(*ring), GFP_KERNEL);
-		if (!ring) {
-			en_err(priv, "Failed allocating TX ring\n");
-			return -ENOMEM;
-		}
+		en_err(priv, "Failed allocating TX ring\n");
+		return -ENOMEM;
 	}
 
 	ring->size = size;
-- 
cgit v1.2.3


From b3e5464e36c07dba70b544044a297d5819351765 Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@infinera.com>
Date: Fri, 14 Dec 2018 15:17:05 +0100
Subject: Fixed PHY: Add fixed_phy_change_carrier()

Drivers can use this as .ndo_change_carrier() to change carrier
via /sys/class/net/ethX/carrier.

Signed-off-by: Joakim Tjernlund <joakim.tjernlund@infinera.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/fixed_phy.c | 24 +++++++++++++++++++++++-
 include/linux/phy_fixed.h   |  5 +++++
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index f7fb62712cd8..72d43c88e6ff 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -25,6 +25,7 @@
 #include <linux/gpio.h>
 #include <linux/seqlock.h>
 #include <linux/idr.h>
+#include <linux/netdevice.h>
 
 #include "swphy.h"
 
@@ -38,6 +39,7 @@ struct fixed_phy {
 	struct phy_device *phydev;
 	seqcount_t seqcount;
 	struct fixed_phy_status status;
+	bool no_carrier;
 	int (*link_update)(struct net_device *, struct fixed_phy_status *);
 	struct list_head node;
 	int link_gpio;
@@ -48,9 +50,28 @@ static struct fixed_mdio_bus platform_fmb = {
 	.phys = LIST_HEAD_INIT(platform_fmb.phys),
 };
 
+int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier)
+{
+	struct fixed_mdio_bus *fmb = &platform_fmb;
+	struct phy_device *phydev = dev->phydev;
+	struct fixed_phy *fp;
+
+	if (!phydev || !phydev->mdio.bus)
+		return -EINVAL;
+
+	list_for_each_entry(fp, &fmb->phys, node) {
+		if (fp->addr == phydev->mdio.addr) {
+			fp->no_carrier = !new_carrier;
+			return 0;
+		}
+	}
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(fixed_phy_change_carrier);
+
 static void fixed_phy_update(struct fixed_phy *fp)
 {
-	if (gpio_is_valid(fp->link_gpio))
+	if (!fp->no_carrier && gpio_is_valid(fp->link_gpio))
 		fp->status.link = !!gpio_get_value_cansleep(fp->link_gpio);
 }
 
@@ -66,6 +87,7 @@ static int fixed_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num)
 
 			do {
 				s = read_seqcount_begin(&fp->seqcount);
+				fp->status.link = !fp->no_carrier;
 				/* Issue callback if user registered it. */
 				if (fp->link_update) {
 					fp->link_update(fp->phydev->attached_dev,
diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h
index ee54453a40a0..9525567b1951 100644
--- a/include/linux/phy_fixed.h
+++ b/include/linux/phy_fixed.h
@@ -13,6 +13,7 @@ struct fixed_phy_status {
 struct device_node;
 
 #if IS_ENABLED(CONFIG_FIXED_PHY)
+extern int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier);
 extern int fixed_phy_add(unsigned int irq, int phy_id,
 			 struct fixed_phy_status *status,
 			 int link_gpio);
@@ -47,6 +48,10 @@ static inline int fixed_phy_set_link_update(struct phy_device *phydev,
 {
 	return -ENODEV;
 }
+static inline int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_FIXED_PHY */
 
 #endif /* __PHY_FIXED_H */
-- 
cgit v1.2.3


From 6e8b0ff1ba4cc145a8fb13a3212de0f75d5f043c Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@infinera.com>
Date: Fri, 14 Dec 2018 15:17:06 +0100
Subject: dpaa_eth: Add change_carrier() for Fixed PHYs

This allows to control carrier from /sys/class/net/ethX/carrier
for Fixed PHYs.

Signed-off-by: Joakim Tjernlund <joakim.tjernlund@infinera.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 9510c9d78858..f53090cde041 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -51,9 +51,9 @@
 #include <linux/percpu.h>
 #include <linux/dma-mapping.h>
 #include <linux/sort.h>
+#include <linux/phy_fixed.h>
 #include <soc/fsl/bman.h>
 #include <soc/fsl/qman.h>
-
 #include "fman.h"
 #include "fman_port.h"
 #include "mac.h"
@@ -2616,6 +2616,7 @@ static const struct net_device_ops dpaa_ops = {
 	.ndo_stop = dpaa_eth_stop,
 	.ndo_tx_timeout = dpaa_tx_timeout,
 	.ndo_get_stats64 = dpaa_get_stats64,
+	.ndo_change_carrier = fixed_phy_change_carrier,
 	.ndo_set_mac_address = dpaa_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_set_rx_mode = dpaa_set_rx_mode,
-- 
cgit v1.2.3


From 6211d46713c5dc62bb87dff208134b253ff5e128 Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@infinera.com>
Date: Fri, 14 Dec 2018 15:17:07 +0100
Subject: gianfar: Add change_carrier() for Fixed PHYs

This allows to control carrier from /sys/class/net/ethX/carrier
for Fixed PHYs.

Signed-off-by: Joakim Tjernlund <joakim.tjernlund@infinera.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/gianfar.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index a831086601eb..45fcc96be90e 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -500,6 +500,7 @@ static const struct net_device_ops gfar_netdev_ops = {
 	.ndo_tx_timeout = gfar_timeout,
 	.ndo_do_ioctl = gfar_ioctl,
 	.ndo_get_stats = gfar_get_stats,
+	.ndo_change_carrier = fixed_phy_change_carrier,
 	.ndo_set_mac_address = gfar_set_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
-- 
cgit v1.2.3


From a28777f250311ac574237e6145ac72c7b3b7b049 Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@infinera.com>
Date: Fri, 14 Dec 2018 15:17:08 +0100
Subject: ucc_geth: Add change_carrier() for Fixed PHYs

This allows to control carrier from /sys/class/net/ethX/carrier
for Fixed PHYs.

Signed-off-by: Joakim Tjernlund <joakim.tjernlund@infinera.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/ucc_geth.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 2e978cb8b28c..c3d539e209ed 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -30,6 +30,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/mii.h>
 #include <linux/phy.h>
+#include <linux/phy_fixed.h>
 #include <linux/workqueue.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -3676,6 +3677,7 @@ static const struct net_device_ops ucc_geth_netdev_ops = {
 	.ndo_stop		= ucc_geth_close,
 	.ndo_start_xmit		= ucc_geth_start_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_change_carrier     = fixed_phy_change_carrier,
 	.ndo_set_mac_address	= ucc_geth_set_mac_addr,
 	.ndo_set_rx_mode	= ucc_geth_set_multi,
 	.ndo_tx_timeout		= ucc_geth_timeout,
-- 
cgit v1.2.3


From 6c4fc209fcf9d27efbaa48368773e4d2bfbd59aa Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 16 Dec 2018 00:49:47 +0100
Subject: bpf: remove useless version check for prog load

Existing libraries and tracing frameworks work around this kernel
version check by automatically deriving the kernel version from
uname(3) or similar such that the user does not need to do it
manually; these workarounds also make the version check useless
at the same time.

Moreover, most other BPF tracing types enabling bpf_probe_read()-like
functionality have /not/ adapted this check, and in general these
days it is well understood anyway that all the tracing programs are
not stable with regards to future kernels as kernel internal data
structures are subject to change from release to release.

Back at last netconf we discussed [0] and agreed to remove this
check from bpf_prog_load() and instead document it here in the uapi
header that there is no such guarantee for stable API for these
programs.

  [0] http://vger.kernel.org/netconf2018_files/DanielBorkmann_netconf2018.pdf

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       | 10 +++++++++-
 kernel/bpf/syscall.c           |  5 -----
 tools/include/uapi/linux/bpf.h | 10 +++++++++-
 3 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e7d57e89f25f..1d324c2cbca2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -133,6 +133,14 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_STACK,
 };
 
+/* Note that tracing related programs such as
+ * BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT}
+ * are not subject to a stable API since kernel internal data
+ * structures can change from release to release and may
+ * therefore break existing tracing BPF programs. Tracing BPF
+ * programs correspond to /a/ specific kernel which is to be
+ * analyzed, and not /a/ specific kernel /and/ all future ones.
+ */
 enum bpf_prog_type {
 	BPF_PROG_TYPE_UNSPEC,
 	BPF_PROG_TYPE_SOCKET_FILTER,
@@ -343,7 +351,7 @@ union bpf_attr {
 		__u32		log_level;	/* verbosity level of verifier */
 		__u32		log_size;	/* size of user buffer */
 		__aligned_u64	log_buf;	/* user supplied buffer */
-		__u32		kern_version;	/* checked when prog_type=kprobe */
+		__u32		kern_version;	/* not used */
 		__u32		prog_flags;
 		char		prog_name[BPF_OBJ_NAME_LEN];
 		__u32		prog_ifindex;	/* ifindex of netdev to prep for */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6ae062f1cf20..5db31067d85e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1473,11 +1473,6 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS)
 		return -E2BIG;
-
-	if (type == BPF_PROG_TYPE_KPROBE &&
-	    attr->kern_version != LINUX_VERSION_CODE)
-		return -EINVAL;
-
 	if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
 	    type != BPF_PROG_TYPE_CGROUP_SKB &&
 	    !capable(CAP_SYS_ADMIN))
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e7d57e89f25f..1d324c2cbca2 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -133,6 +133,14 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_STACK,
 };
 
+/* Note that tracing related programs such as
+ * BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT}
+ * are not subject to a stable API since kernel internal data
+ * structures can change from release to release and may
+ * therefore break existing tracing BPF programs. Tracing BPF
+ * programs correspond to /a/ specific kernel which is to be
+ * analyzed, and not /a/ specific kernel /and/ all future ones.
+ */
 enum bpf_prog_type {
 	BPF_PROG_TYPE_UNSPEC,
 	BPF_PROG_TYPE_SOCKET_FILTER,
@@ -343,7 +351,7 @@ union bpf_attr {
 		__u32		log_level;	/* verbosity level of verifier */
 		__u32		log_size;	/* size of user buffer */
 		__aligned_u64	log_buf;	/* user supplied buffer */
-		__u32		kern_version;	/* checked when prog_type=kprobe */
+		__u32		kern_version;	/* not used */
 		__u32		prog_flags;
 		char		prog_name[BPF_OBJ_NAME_LEN];
 		__u32		prog_ifindex;	/* ifindex of netdev to prep for */
-- 
cgit v1.2.3


From b635cbf68ff35817d5a1634b0ade41f96ef70daf Mon Sep 17 00:00:00 2001
From: Xiaozhou Liu <liuxiaozhou@bytedance.com>
Date: Wed, 5 Dec 2018 23:50:15 +0800
Subject: netfilter: nat: remove unnecessary 'else if' branch

Since a pseudo-random starting point is used in finding a port in
the default case, that 'else if' branch above is no longer a necessity.
So remove it to simplify code.

Signed-off-by: Xiaozhou Liu <liuxiaozhou@bytedance.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_nat_proto_common.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c
index a7de939fa5a9..136ab65c4082 100644
--- a/net/netfilter/nf_nat_proto_common.c
+++ b/net/netfilter/nf_nat_proto_common.c
@@ -80,8 +80,6 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		off = l3proto->secure_port(tuple, maniptype == NF_NAT_MANIP_SRC
 						  ? tuple->dst.u.all
 						  : tuple->src.u.all);
-	} else if (range->flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY) {
-		off = prandom_u32();
 	} else if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) {
 		off = (ntohs(*portptr) - ntohs(range->base_proto.all));
 	} else {
-- 
cgit v1.2.3


From a504b703bb1da526a01593da0e4be2af9d9f5fa8 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 10 Dec 2018 17:18:46 +0100
Subject: netfilter: nat: limit port clash resolution attempts

In case almost or all available ports are taken, clash resolution can
take a very long time, resulting in soft lockup.

This can happen when many to-be-natted hosts connect to same
destination:port (e.g. a proxy) and all connections pass the same SNAT.

Pick a random offset in the acceptable range, then try ever smaller
number of adjacent port numbers, until either the limit is reached or a
useable port was found.  This results in at most 248 attempts
(128 + 64 + 32 + 16 + 8, i.e. 4 restarts with new search offset)
instead of 64000+,

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_nat_proto_common.c | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c
index 136ab65c4082..dcb5d11688a1 100644
--- a/net/netfilter/nf_nat_proto_common.c
+++ b/net/netfilter/nf_nat_proto_common.c
@@ -40,9 +40,10 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
 				 enum nf_nat_manip_type maniptype,
 				 const struct nf_conn *ct)
 {
-	unsigned int range_size, min, max, i;
+	unsigned int range_size, min, max, i, attempts;
 	__be16 *portptr;
-	u_int16_t off;
+	u16 off;
+	static const unsigned int max_attempts = 128;
 
 	if (maniptype == NF_NAT_MANIP_SRC)
 		portptr = &tuple->src.u.all;
@@ -86,12 +87,28 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		off = prandom_u32();
 	}
 
-	for (i = 0; ; ++off) {
+	attempts = range_size;
+	if (attempts > max_attempts)
+		attempts = max_attempts;
+
+	/* We are in softirq; doing a search of the entire range risks
+	 * soft lockup when all tuples are already used.
+	 *
+	 * If we can't find any free port from first offset, pick a new
+	 * one and try again, with ever smaller search window.
+	 */
+another_round:
+	for (i = 0; i < attempts; i++, off++) {
 		*portptr = htons(min + off % range_size);
-		if (++i != range_size && nf_nat_used_tuple(tuple, ct))
-			continue;
-		return;
+		if (!nf_nat_used_tuple(tuple, ct))
+			return;
 	}
+
+	if (attempts >= range_size || attempts < 16)
+		return;
+	attempts /= 2;
+	off = prandom_u32();
+	goto another_round;
 }
 EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple);
 
-- 
cgit v1.2.3


From df7043bed47e0f525224c55c2e005c97f958d80d Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Thu, 13 Dec 2018 22:39:21 +0800
Subject: netfilter: remove unused parameters in
 nf_ct_l4proto_[un]register_sysctl()

These parameters aren't used now.
So remove them.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_proto.c | 21 +++++++--------------
 1 file changed, 7 insertions(+), 14 deletions(-)

diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 40643af7137e..859f5d07a915 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -175,8 +175,7 @@ static struct nf_proto_net *nf_ct_l4proto_net(struct net *net,
 
 static
 int nf_ct_l4proto_register_sysctl(struct net *net,
-				  struct nf_proto_net *pn,
-				  const struct nf_conntrack_l4proto *l4proto)
+				  struct nf_proto_net *pn)
 {
 	int err = 0;
 
@@ -198,9 +197,7 @@ int nf_ct_l4proto_register_sysctl(struct net *net,
 }
 
 static
-void nf_ct_l4proto_unregister_sysctl(struct net *net,
-				struct nf_proto_net *pn,
-				const struct nf_conntrack_l4proto *l4proto)
+void nf_ct_l4proto_unregister_sysctl(struct nf_proto_net *pn)
 {
 #ifdef CONFIG_SYSCTL
 	if (pn->ctl_table_header != NULL)
@@ -252,7 +249,7 @@ int nf_ct_l4proto_pernet_register_one(struct net *net,
 	if (pn == NULL)
 		goto out;
 
-	ret = nf_ct_l4proto_register_sysctl(net, pn, l4proto);
+	ret = nf_ct_l4proto_register_sysctl(net, pn);
 	if (ret < 0)
 		goto out;
 
@@ -296,7 +293,7 @@ void nf_ct_l4proto_pernet_unregister_one(struct net *net,
 		return;
 
 	pn->users--;
-	nf_ct_l4proto_unregister_sysctl(net, pn, l4proto);
+	nf_ct_l4proto_unregister_sysctl(pn);
 }
 EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister_one);
 
@@ -946,16 +943,14 @@ int nf_conntrack_proto_pernet_init(struct net *net)
 	if (err < 0)
 		return err;
 	err = nf_ct_l4proto_register_sysctl(net,
-					    pn,
-					    &nf_conntrack_l4proto_generic);
+					    pn);
 	if (err < 0)
 		return err;
 
 	err = nf_ct_l4proto_pernet_register(net, builtin_l4proto,
 					    ARRAY_SIZE(builtin_l4proto));
 	if (err < 0) {
-		nf_ct_l4proto_unregister_sysctl(net, pn,
-						&nf_conntrack_l4proto_generic);
+		nf_ct_l4proto_unregister_sysctl(pn);
 		return err;
 	}
 
@@ -971,9 +966,7 @@ void nf_conntrack_proto_pernet_fini(struct net *net)
 	nf_ct_l4proto_pernet_unregister(net, builtin_l4proto,
 					ARRAY_SIZE(builtin_l4proto));
 	pn->users--;
-	nf_ct_l4proto_unregister_sysctl(net,
-					pn,
-					&nf_conntrack_l4proto_generic);
+	nf_ct_l4proto_unregister_sysctl(pn);
 }
 
 
-- 
cgit v1.2.3


From 912da924a29fc6bd466b98a8791d6f7cf74caf61 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 13 Dec 2018 16:01:27 +0100
Subject: netfilter: remove NF_NAT_RANGE_PROTO_RANDOM support

Historically this was net_random() based, and was then converted to
a hash based algorithm (private boot seed + hash of endpoint addresses)
due to concerns of leaking net_random() bits.

RANDOM_FULLY mode was added later to avoid problems with hash
based mode (see commit 34ce324019e76,
"netfilter: nf_nat: add full port randomization support" for details).

Just make prandom_u32() the default search starting point and get rid of
->secure_port() altogether.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l3proto.h   | 2 --
 net/ipv4/netfilter/nf_nat_l3proto_ipv4.c | 7 -------
 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 7 -------
 net/netfilter/nf_nat_proto_common.c      | 9 ++-------
 4 files changed, 2 insertions(+), 23 deletions(-)

diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h
index d300b8f03972..f8b3fbe7a1bf 100644
--- a/include/net/netfilter/nf_nat_l3proto.h
+++ b/include/net/netfilter/nf_nat_l3proto.h
@@ -9,8 +9,6 @@ struct nf_nat_l3proto {
 	bool	(*in_range)(const struct nf_conntrack_tuple *t,
 			    const struct nf_nat_range2 *range);
 
-	u32 	(*secure_port)(const struct nf_conntrack_tuple *t, __be16);
-
 	bool	(*manip_pkt)(struct sk_buff *skb,
 			     unsigned int iphdroff,
 			     const struct nf_nat_l4proto *l4proto,
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index 78a67f961d86..4d755a6f73ad 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -69,12 +69,6 @@ static bool nf_nat_ipv4_in_range(const struct nf_conntrack_tuple *t,
 	       ntohl(t->src.u3.ip) <= ntohl(range->max_addr.ip);
 }
 
-static u32 nf_nat_ipv4_secure_port(const struct nf_conntrack_tuple *t,
-				   __be16 dport)
-{
-	return secure_ipv4_port_ephemeral(t->src.u3.ip, t->dst.u3.ip, dport);
-}
-
 static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb,
 				  unsigned int iphdroff,
 				  const struct nf_nat_l4proto *l4proto,
@@ -162,7 +156,6 @@ static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[],
 static const struct nf_nat_l3proto nf_nat_l3proto_ipv4 = {
 	.l3proto		= NFPROTO_IPV4,
 	.in_range		= nf_nat_ipv4_in_range,
-	.secure_port		= nf_nat_ipv4_secure_port,
 	.manip_pkt		= nf_nat_ipv4_manip_pkt,
 	.csum_update		= nf_nat_ipv4_csum_update,
 	.csum_recalc		= nf_nat_ipv4_csum_recalc,
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index ca6d38698b1a..290bb0142192 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -68,12 +68,6 @@ static bool nf_nat_ipv6_in_range(const struct nf_conntrack_tuple *t,
 	       ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0;
 }
 
-static u32 nf_nat_ipv6_secure_port(const struct nf_conntrack_tuple *t,
-				   __be16 dport)
-{
-	return secure_ipv6_port_ephemeral(t->src.u3.ip6, t->dst.u3.ip6, dport);
-}
-
 static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
 				  unsigned int iphdroff,
 				  const struct nf_nat_l4proto *l4proto,
@@ -171,7 +165,6 @@ static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[],
 
 static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = {
 	.l3proto		= NFPROTO_IPV6,
-	.secure_port		= nf_nat_ipv6_secure_port,
 	.in_range		= nf_nat_ipv6_in_range,
 	.manip_pkt		= nf_nat_ipv6_manip_pkt,
 	.csum_update		= nf_nat_ipv6_csum_update,
diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c
index dcb5d11688a1..dabfe9a2c041 100644
--- a/net/netfilter/nf_nat_proto_common.c
+++ b/net/netfilter/nf_nat_proto_common.c
@@ -77,15 +77,10 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		range_size = max - min + 1;
 	}
 
-	if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) {
-		off = l3proto->secure_port(tuple, maniptype == NF_NAT_MANIP_SRC
-						  ? tuple->dst.u.all
-						  : tuple->src.u.all);
-	} else if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) {
+	if (range->flags & NF_NAT_RANGE_PROTO_OFFSET)
 		off = (ntohs(*portptr) - ntohs(range->base_proto.all));
-	} else {
+	else
 		off = prandom_u32();
-	}
 
 	attempts = range_size;
 	if (attempts > max_attempts)
-- 
cgit v1.2.3


From 716b23c19edd47134104d39e3537d21c0b68d7d1 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 13 Dec 2018 16:01:28 +0100
Subject: netfilter: nat: un-export nf_nat_l4proto_unique_tuple

almost all l4proto->unique_tuple implementations just call this helper,
so make ->unique_tuple() optional and call its helper directly if the
l4proto doesn't override it.

This is an intermediate step to get rid of ->unique_tuple completely.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l4proto.h |  6 ---
 net/netfilter/nf_nat_core.c            | 76 +++++++++++++++++++++++++++++++++-
 net/netfilter/nf_nat_proto_common.c    | 73 --------------------------------
 net/netfilter/nf_nat_proto_dccp.c      | 11 -----
 net/netfilter/nf_nat_proto_sctp.c      | 11 -----
 net/netfilter/nf_nat_proto_tcp.c       | 11 -----
 net/netfilter/nf_nat_proto_udp.c       | 22 ----------
 7 files changed, 75 insertions(+), 135 deletions(-)

diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h
index 7ecac2cd1020..96f0794bb1f8 100644
--- a/include/net/netfilter/nf_nat_l4proto.h
+++ b/include/net/netfilter/nf_nat_l4proto.h
@@ -70,12 +70,6 @@ bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple,
 			     const union nf_conntrack_man_proto *min,
 			     const union nf_conntrack_man_proto *max);
 
-void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
-				 struct nf_conntrack_tuple *tuple,
-				 const struct nf_nat_range2 *range,
-				 enum nf_nat_manip_type maniptype,
-				 const struct nf_conn *ct);
-
 int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
 				   struct nf_nat_range2 *range);
 
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index e2b196054dfc..0c0f012343b1 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -310,6 +310,77 @@ find_best_ips_proto(const struct nf_conntrack_zone *zone,
 	}
 }
 
+static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
+					const struct nf_nat_range2 *range,
+					enum nf_nat_manip_type maniptype,
+					const struct nf_conn *ct)
+{
+	unsigned int range_size, min, max, i, attempts;
+	__be16 *portptr;
+	u16 off;
+	static const unsigned int max_attempts = 128;
+
+	if (maniptype == NF_NAT_MANIP_SRC)
+		portptr = &tuple->src.u.all;
+	else
+		portptr = &tuple->dst.u.all;
+
+	/* If no range specified... */
+	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
+		/* If it's dst rewrite, can't change port */
+		if (maniptype == NF_NAT_MANIP_DST)
+			return;
+
+		if (ntohs(*portptr) < 1024) {
+			/* Loose convention: >> 512 is credential passing */
+			if (ntohs(*portptr) < 512) {
+				min = 1;
+				range_size = 511 - min + 1;
+			} else {
+				min = 600;
+				range_size = 1023 - min + 1;
+			}
+		} else {
+			min = 1024;
+			range_size = 65535 - 1024 + 1;
+		}
+	} else {
+		min = ntohs(range->min_proto.all);
+		max = ntohs(range->max_proto.all);
+		if (unlikely(max < min))
+			swap(max, min);
+		range_size = max - min + 1;
+	}
+
+	if (range->flags & NF_NAT_RANGE_PROTO_OFFSET)
+		off = (ntohs(*portptr) - ntohs(range->base_proto.all));
+	else
+		off = prandom_u32();
+
+	attempts = range_size;
+	if (attempts > max_attempts)
+		attempts = max_attempts;
+
+	/* We are in softirq; doing a search of the entire range risks
+	 * soft lockup when all tuples are already used.
+	 *
+	 * If we can't find any free port from first offset, pick a new
+	 * one and try again, with ever smaller search window.
+	 */
+another_round:
+	for (i = 0; i < attempts; i++, off++) {
+		*portptr = htons(min + off % range_size);
+		if (!nf_nat_used_tuple(tuple, ct))
+			return;
+	}
+
+	if (attempts >= range_size || attempts < 16)
+		return;
+	attempts /= 2;
+	off = prandom_u32();
+	goto another_round;
+}
+
 /* Manipulate the tuple into the range given. For NF_INET_POST_ROUTING,
  * we change the source to map into the range. For NF_INET_PRE_ROUTING
  * and NF_INET_LOCAL_OUT, we change the destination to map into the
@@ -383,7 +454,10 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	}
 
 	/* Last chance: get protocol to try to obtain unique tuple. */
-	l4proto->unique_tuple(l3proto, tuple, range, maniptype, ct);
+	if (l4proto->unique_tuple)
+		l4proto->unique_tuple(l3proto, tuple, range, maniptype, ct);
+	else
+		nf_nat_l4proto_unique_tuple(tuple, range, maniptype, ct);
 out:
 	rcu_read_unlock();
 }
diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c
index dabfe9a2c041..ef14d86f0f5b 100644
--- a/net/netfilter/nf_nat_proto_common.c
+++ b/net/netfilter/nf_nat_proto_common.c
@@ -34,79 +34,6 @@ bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple,
 }
 EXPORT_SYMBOL_GPL(nf_nat_l4proto_in_range);
 
-void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
-				 struct nf_conntrack_tuple *tuple,
-				 const struct nf_nat_range2 *range,
-				 enum nf_nat_manip_type maniptype,
-				 const struct nf_conn *ct)
-{
-	unsigned int range_size, min, max, i, attempts;
-	__be16 *portptr;
-	u16 off;
-	static const unsigned int max_attempts = 128;
-
-	if (maniptype == NF_NAT_MANIP_SRC)
-		portptr = &tuple->src.u.all;
-	else
-		portptr = &tuple->dst.u.all;
-
-	/* If no range specified... */
-	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
-		/* If it's dst rewrite, can't change port */
-		if (maniptype == NF_NAT_MANIP_DST)
-			return;
-
-		if (ntohs(*portptr) < 1024) {
-			/* Loose convention: >> 512 is credential passing */
-			if (ntohs(*portptr) < 512) {
-				min = 1;
-				range_size = 511 - min + 1;
-			} else {
-				min = 600;
-				range_size = 1023 - min + 1;
-			}
-		} else {
-			min = 1024;
-			range_size = 65535 - 1024 + 1;
-		}
-	} else {
-		min = ntohs(range->min_proto.all);
-		max = ntohs(range->max_proto.all);
-		if (unlikely(max < min))
-			swap(max, min);
-		range_size = max - min + 1;
-	}
-
-	if (range->flags & NF_NAT_RANGE_PROTO_OFFSET)
-		off = (ntohs(*portptr) - ntohs(range->base_proto.all));
-	else
-		off = prandom_u32();
-
-	attempts = range_size;
-	if (attempts > max_attempts)
-		attempts = max_attempts;
-
-	/* We are in softirq; doing a search of the entire range risks
-	 * soft lockup when all tuples are already used.
-	 *
-	 * If we can't find any free port from first offset, pick a new
-	 * one and try again, with ever smaller search window.
-	 */
-another_round:
-	for (i = 0; i < attempts; i++, off++) {
-		*portptr = htons(min + off % range_size);
-		if (!nf_nat_used_tuple(tuple, ct))
-			return;
-	}
-
-	if (attempts >= range_size || attempts < 16)
-		return;
-	attempts /= 2;
-	off = prandom_u32();
-	goto another_round;
-}
-EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple);
-
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
 				   struct nf_nat_range2 *range)
diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c
index 7d4d2c124990..8dbba7b20177 100644
--- a/net/netfilter/nf_nat_proto_dccp.c
+++ b/net/netfilter/nf_nat_proto_dccp.c
@@ -18,16 +18,6 @@
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static void
-dccp_unique_tuple(const struct nf_nat_l3proto *l3proto,
-		  struct nf_conntrack_tuple *tuple,
-		  const struct nf_nat_range2 *range,
-		  enum nf_nat_manip_type maniptype,
-		  const struct nf_conn *ct)
-{
-	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct);
-}
-
 static bool
 dccp_manip_pkt(struct sk_buff *skb,
 	       const struct nf_nat_l3proto *l3proto,
@@ -72,7 +62,6 @@ const struct nf_nat_l4proto nf_nat_l4proto_dccp = {
 	.l4proto		= IPPROTO_DCCP,
 	.manip_pkt		= dccp_manip_pkt,
 	.in_range		= nf_nat_l4proto_in_range,
-	.unique_tuple		= dccp_unique_tuple,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c
index f05ad8fa7b20..da86475d0db6 100644
--- a/net/netfilter/nf_nat_proto_sctp.c
+++ b/net/netfilter/nf_nat_proto_sctp.c
@@ -12,16 +12,6 @@
 
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static void
-sctp_unique_tuple(const struct nf_nat_l3proto *l3proto,
-		  struct nf_conntrack_tuple *tuple,
-		  const struct nf_nat_range2 *range,
-		  enum nf_nat_manip_type maniptype,
-		  const struct nf_conn *ct)
-{
-	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct);
-}
-
 static bool
 sctp_manip_pkt(struct sk_buff *skb,
 	       const struct nf_nat_l3proto *l3proto,
@@ -67,7 +57,6 @@ const struct nf_nat_l4proto nf_nat_l4proto_sctp = {
 	.l4proto		= IPPROTO_SCTP,
 	.manip_pkt		= sctp_manip_pkt,
 	.in_range		= nf_nat_l4proto_in_range,
-	.unique_tuple		= sctp_unique_tuple,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c
index c312e6b3e2ea..666a4b3303f7 100644
--- a/net/netfilter/nf_nat_proto_tcp.c
+++ b/net/netfilter/nf_nat_proto_tcp.c
@@ -18,16 +18,6 @@
 #include <net/netfilter/nf_nat_l4proto.h>
 #include <net/netfilter/nf_nat_core.h>
 
-static void
-tcp_unique_tuple(const struct nf_nat_l3proto *l3proto,
-		 struct nf_conntrack_tuple *tuple,
-		 const struct nf_nat_range2 *range,
-		 enum nf_nat_manip_type maniptype,
-		 const struct nf_conn *ct)
-{
-	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct);
-}
-
 static bool
 tcp_manip_pkt(struct sk_buff *skb,
 	      const struct nf_nat_l3proto *l3proto,
@@ -75,7 +65,6 @@ const struct nf_nat_l4proto nf_nat_l4proto_tcp = {
 	.l4proto		= IPPROTO_TCP,
 	.manip_pkt		= tcp_manip_pkt,
 	.in_range		= nf_nat_l4proto_in_range,
-	.unique_tuple		= tcp_unique_tuple,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c
index 208c14316359..26f3715a457a 100644
--- a/net/netfilter/nf_nat_proto_udp.c
+++ b/net/netfilter/nf_nat_proto_udp.c
@@ -17,16 +17,6 @@
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static void
-udp_unique_tuple(const struct nf_nat_l3proto *l3proto,
-		 struct nf_conntrack_tuple *tuple,
-		 const struct nf_nat_range2 *range,
-		 enum nf_nat_manip_type maniptype,
-		 const struct nf_conn *ct)
-{
-	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct);
-}
-
 static void
 __udp_manip_pkt(struct sk_buff *skb,
 	        const struct nf_nat_l3proto *l3proto,
@@ -92,21 +82,10 @@ static bool udplite_manip_pkt(struct sk_buff *skb,
 	return true;
 }
 
-static void
-udplite_unique_tuple(const struct nf_nat_l3proto *l3proto,
-		     struct nf_conntrack_tuple *tuple,
-		     const struct nf_nat_range2 *range,
-		     enum nf_nat_manip_type maniptype,
-		     const struct nf_conn *ct)
-{
-	nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct);
-}
-
 const struct nf_nat_l4proto nf_nat_l4proto_udplite = {
 	.l4proto		= IPPROTO_UDPLITE,
 	.manip_pkt		= udplite_manip_pkt,
 	.in_range		= nf_nat_l4proto_in_range,
-	.unique_tuple		= udplite_unique_tuple,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
@@ -117,7 +96,6 @@ const struct nf_nat_l4proto nf_nat_l4proto_udp = {
 	.l4proto		= IPPROTO_UDP,
 	.manip_pkt		= udp_manip_pkt,
 	.in_range		= nf_nat_l4proto_in_range,
-	.unique_tuple		= udp_unique_tuple,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
-- 
cgit v1.2.3


From 203f2e78200c27e42e9f7d063091f950bf5fe4a0 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 13 Dec 2018 16:01:29 +0100
Subject: netfilter: nat: remove l4proto->unique_tuple

fold remaining users (icmp, icmpv6, gre) into nf_nat_l4proto_unique_tuple.
The static-save of old incarnation of resolved key in gre and icmp is
removed as well, just use the prandom based offset like the others.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l4proto.h   | 11 -----
 net/ipv4/netfilter/nf_nat_proto_gre.c    | 44 --------------------
 net/ipv4/netfilter/nf_nat_proto_icmp.c   | 27 -------------
 net/ipv6/netfilter/nf_nat_proto_icmpv6.c | 26 ------------
 net/netfilter/nf_nat_core.c              | 69 ++++++++++++++++++++++++++------
 net/netfilter/nf_nat_proto_unknown.c     | 13 ------
 6 files changed, 56 insertions(+), 134 deletions(-)

diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h
index 96f0794bb1f8..4a0e4f0623a0 100644
--- a/include/net/netfilter/nf_nat_l4proto.h
+++ b/include/net/netfilter/nf_nat_l4proto.h
@@ -27,17 +27,6 @@ struct nf_nat_l4proto {
 			 const union nf_conntrack_man_proto *min,
 			 const union nf_conntrack_man_proto *max);
 
-	/* Alter the per-proto part of the tuple (depending on
-	 * maniptype), to give a unique tuple in the given range if
-	 * possible.  Per-protocol part of tuple is initialized to the
-	 * incoming packet.
-	 */
-	void (*unique_tuple)(const struct nf_nat_l3proto *l3proto,
-			     struct nf_conntrack_tuple *tuple,
-			     const struct nf_nat_range2 *range,
-			     enum nf_nat_manip_type maniptype,
-			     const struct nf_conn *ct);
-
 	int (*nlattr_to_range)(struct nlattr *tb[],
 			       struct nf_nat_range2 *range);
 };
diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c
index 00fda6331ce5..a04ff7665e4c 100644
--- a/net/ipv4/netfilter/nf_nat_proto_gre.c
+++ b/net/ipv4/netfilter/nf_nat_proto_gre.c
@@ -37,49 +37,6 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>");
 MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE");
 
-/* generate unique tuple ... */
-static void
-gre_unique_tuple(const struct nf_nat_l3proto *l3proto,
-		 struct nf_conntrack_tuple *tuple,
-		 const struct nf_nat_range2 *range,
-		 enum nf_nat_manip_type maniptype,
-		 const struct nf_conn *ct)
-{
-	static u_int16_t key;
-	__be16 *keyptr;
-	unsigned int min, i, range_size;
-
-	/* If there is no master conntrack we are not PPTP,
-	   do not change tuples */
-	if (!ct->master)
-		return;
-
-	if (maniptype == NF_NAT_MANIP_SRC)
-		keyptr = &tuple->src.u.gre.key;
-	else
-		keyptr = &tuple->dst.u.gre.key;
-
-	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
-		pr_debug("%p: NATing GRE PPTP\n", ct);
-		min = 1;
-		range_size = 0xffff;
-	} else {
-		min = ntohs(range->min_proto.gre.key);
-		range_size = ntohs(range->max_proto.gre.key) - min + 1;
-	}
-
-	pr_debug("min = %u, range_size = %u\n", min, range_size);
-
-	for (i = 0; ; ++key) {
-		*keyptr = htons(min + key % range_size);
-		if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
-			return;
-	}
-
-	pr_debug("%p: no NAT mapping\n", ct);
-	return;
-}
-
 /* manipulate a GRE packet according to maniptype */
 static bool
 gre_manip_pkt(struct sk_buff *skb,
@@ -124,7 +81,6 @@ static const struct nf_nat_l4proto gre = {
 	.l4proto		= IPPROTO_GRE,
 	.manip_pkt		= gre_manip_pkt,
 	.in_range		= nf_nat_l4proto_in_range,
-	.unique_tuple		= gre_unique_tuple,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c
index 6d7cf1d79baf..70d7fabdbb01 100644
--- a/net/ipv4/netfilter/nf_nat_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c
@@ -27,32 +27,6 @@ icmp_in_range(const struct nf_conntrack_tuple *tuple,
 	       ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id);
 }
 
-static void
-icmp_unique_tuple(const struct nf_nat_l3proto *l3proto,
-		  struct nf_conntrack_tuple *tuple,
-		  const struct nf_nat_range2 *range,
-		  enum nf_nat_manip_type maniptype,
-		  const struct nf_conn *ct)
-{
-	static u_int16_t id;
-	unsigned int range_size;
-	unsigned int i;
-
-	range_size = ntohs(range->max_proto.icmp.id) -
-		     ntohs(range->min_proto.icmp.id) + 1;
-	/* If no range specified... */
-	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED))
-		range_size = 0xFFFF;
-
-	for (i = 0; ; ++id) {
-		tuple->src.u.icmp.id = htons(ntohs(range->min_proto.icmp.id) +
-					     (id % range_size));
-		if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
-			return;
-	}
-	return;
-}
-
 static bool
 icmp_manip_pkt(struct sk_buff *skb,
 	       const struct nf_nat_l3proto *l3proto,
@@ -76,7 +50,6 @@ const struct nf_nat_l4proto nf_nat_l4proto_icmp = {
 	.l4proto		= IPPROTO_ICMP,
 	.manip_pkt		= icmp_manip_pkt,
 	.in_range		= icmp_in_range,
-	.unique_tuple		= icmp_unique_tuple,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
index d9bf42ba44fa..491361b7a721 100644
--- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
@@ -29,31 +29,6 @@ icmpv6_in_range(const struct nf_conntrack_tuple *tuple,
 	       ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id);
 }
 
-static void
-icmpv6_unique_tuple(const struct nf_nat_l3proto *l3proto,
-		    struct nf_conntrack_tuple *tuple,
-		    const struct nf_nat_range2 *range,
-		    enum nf_nat_manip_type maniptype,
-		    const struct nf_conn *ct)
-{
-	static u16 id;
-	unsigned int range_size;
-	unsigned int i;
-
-	range_size = ntohs(range->max_proto.icmp.id) -
-		     ntohs(range->min_proto.icmp.id) + 1;
-
-	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED))
-		range_size = 0xffff;
-
-	for (i = 0; ; ++id) {
-		tuple->src.u.icmp.id = htons(ntohs(range->min_proto.icmp.id) +
-					     (id % range_size));
-		if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
-			return;
-	}
-}
-
 static bool
 icmpv6_manip_pkt(struct sk_buff *skb,
 		 const struct nf_nat_l3proto *l3proto,
@@ -83,7 +58,6 @@ const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = {
 	.l4proto		= IPPROTO_ICMPV6,
 	.manip_pkt		= icmpv6_manip_pkt,
 	.in_range		= icmpv6_in_range,
-	.unique_tuple		= icmpv6_unique_tuple,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 0c0f012343b1..763a92e82755 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -310,20 +310,65 @@ find_best_ips_proto(const struct nf_conntrack_zone *zone,
 	}
 }
 
+/* Alter the per-proto part of the tuple (depending on maniptype), to
+ * give a unique tuple in the given range if possible.
+ *
+ * Per-protocol part of tuple is initialized to the incoming packet.
+ */
 static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 					const struct nf_nat_range2 *range,
 					enum nf_nat_manip_type maniptype,
 					const struct nf_conn *ct)
 {
 	unsigned int range_size, min, max, i, attempts;
-	__be16 *portptr;
+	__be16 *keyptr;
 	u16 off;
 	static const unsigned int max_attempts = 128;
 
-	if (maniptype == NF_NAT_MANIP_SRC)
-		portptr = &tuple->src.u.all;
-	else
-		portptr = &tuple->dst.u.all;
+	switch (tuple->dst.protonum) {
+	case IPPROTO_ICMP: /* fallthrough */
+	case IPPROTO_ICMPV6:
+		/* id is same for either direction... */
+		keyptr = &tuple->src.u.icmp.id;
+		min = range->min_proto.icmp.id;
+		range_size = ntohs(range->max_proto.icmp.id) -
+			     ntohs(range->min_proto.icmp.id) + 1;
+		goto find_free_id;
+#if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE)
+	case IPPROTO_GRE:
+		/* If there is no master conntrack we are not PPTP,
+		   do not change tuples */
+		if (!ct->master)
+			return;
+
+		if (maniptype == NF_NAT_MANIP_SRC)
+			keyptr = &tuple->src.u.gre.key;
+		else
+			keyptr = &tuple->dst.u.gre.key;
+
+		if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
+			min = 1;
+			range_size = 65535;
+		} else {
+			min = ntohs(range->min_proto.gre.key);
+			range_size = ntohs(range->max_proto.gre.key) - min + 1;
+		}
+		goto find_free_id;
+#endif
+	case IPPROTO_UDP:	/* fallthrough */
+	case IPPROTO_UDPLITE:	/* fallthrough */
+	case IPPROTO_TCP:	/* fallthrough */
+	case IPPROTO_SCTP:	/* fallthrough */
+	case IPPROTO_DCCP:	/* fallthrough */
+		if (maniptype == NF_NAT_MANIP_SRC)
+			keyptr = &tuple->src.u.all;
+		else
+			keyptr = &tuple->dst.u.all;
+
+		break;
+	default:
+		return;
+	}
 
 	/* If no range specified... */
 	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
@@ -331,9 +376,9 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 		if (maniptype == NF_NAT_MANIP_DST)
 			return;
 
-		if (ntohs(*portptr) < 1024) {
+		if (ntohs(*keyptr) < 1024) {
 			/* Loose convention: >> 512 is credential passing */
-			if (ntohs(*portptr) < 512) {
+			if (ntohs(*keyptr) < 512) {
 				min = 1;
 				range_size = 511 - min + 1;
 			} else {
@@ -352,8 +397,9 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 		range_size = max - min + 1;
 	}
 
+find_free_id:
 	if (range->flags & NF_NAT_RANGE_PROTO_OFFSET)
-		off = (ntohs(*portptr) - ntohs(range->base_proto.all));
+		off = (ntohs(*keyptr) - ntohs(range->base_proto.all));
 	else
 		off = prandom_u32();
 
@@ -369,7 +415,7 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 	 */
 another_round:
 	for (i = 0; i < attempts; i++, off++) {
-		*portptr = htons(min + off % range_size);
+		*keyptr = htons(min + off % range_size);
 		if (!nf_nat_used_tuple(tuple, ct))
 			return;
 	}
@@ -454,10 +500,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	}
 
 	/* Last chance: get protocol to try to obtain unique tuple. */
-	if (l4proto->unique_tuple)
-		l4proto->unique_tuple(l3proto, tuple, range, maniptype, ct);
-	else
-		nf_nat_l4proto_unique_tuple(tuple, range, maniptype, ct);
+	nf_nat_l4proto_unique_tuple(tuple, range, maniptype, ct);
 out:
 	rcu_read_unlock();
 }
diff --git a/net/netfilter/nf_nat_proto_unknown.c b/net/netfilter/nf_nat_proto_unknown.c
index c5db3e251232..16b66785ea5b 100644
--- a/net/netfilter/nf_nat_proto_unknown.c
+++ b/net/netfilter/nf_nat_proto_unknown.c
@@ -25,18 +25,6 @@ static bool unknown_in_range(const struct nf_conntrack_tuple *tuple,
 	return true;
 }
 
-static void unknown_unique_tuple(const struct nf_nat_l3proto *l3proto,
-				 struct nf_conntrack_tuple *tuple,
-				 const struct nf_nat_range2 *range,
-				 enum nf_nat_manip_type maniptype,
-				 const struct nf_conn *ct)
-{
-	/* Sorry: we can't help you; if it's not unique, we can't frob
-	 * anything.
-	 */
-	return;
-}
-
 static bool
 unknown_manip_pkt(struct sk_buff *skb,
 		  const struct nf_nat_l3proto *l3proto,
@@ -50,5 +38,4 @@ unknown_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_unknown = {
 	.manip_pkt		= unknown_manip_pkt,
 	.in_range		= unknown_in_range,
-	.unique_tuple		= unknown_unique_tuple,
 };
-- 
cgit v1.2.3


From 40e786bd296d5517b1f6c4bcc9ed13e502606ced Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 13 Dec 2018 16:01:30 +0100
Subject: netfilter: nat: fold in_range indirection into caller

No need for indirections here, we only support ipv4 and ipv6
and the called functions are very small.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l3proto.h   |  3 ---
 net/ipv4/netfilter/nf_nat_l3proto_ipv4.c |  8 --------
 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c |  8 --------
 net/netfilter/nf_nat_core.c              | 23 ++++++++++++++++-------
 4 files changed, 16 insertions(+), 26 deletions(-)

diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h
index f8b3fbe7a1bf..1ce0980da638 100644
--- a/include/net/netfilter/nf_nat_l3proto.h
+++ b/include/net/netfilter/nf_nat_l3proto.h
@@ -6,9 +6,6 @@ struct nf_nat_l4proto;
 struct nf_nat_l3proto {
 	u8	l3proto;
 
-	bool	(*in_range)(const struct nf_conntrack_tuple *t,
-			    const struct nf_nat_range2 *range);
-
 	bool	(*manip_pkt)(struct sk_buff *skb,
 			     unsigned int iphdroff,
 			     const struct nf_nat_l4proto *l4proto,
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index 4d755a6f73ad..00904e605e85 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -62,13 +62,6 @@ static void nf_nat_ipv4_decode_session(struct sk_buff *skb,
 }
 #endif /* CONFIG_XFRM */
 
-static bool nf_nat_ipv4_in_range(const struct nf_conntrack_tuple *t,
-				 const struct nf_nat_range2 *range)
-{
-	return ntohl(t->src.u3.ip) >= ntohl(range->min_addr.ip) &&
-	       ntohl(t->src.u3.ip) <= ntohl(range->max_addr.ip);
-}
-
 static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb,
 				  unsigned int iphdroff,
 				  const struct nf_nat_l4proto *l4proto,
@@ -155,7 +148,6 @@ static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[],
 
 static const struct nf_nat_l3proto nf_nat_l3proto_ipv4 = {
 	.l3proto		= NFPROTO_IPV4,
-	.in_range		= nf_nat_ipv4_in_range,
 	.manip_pkt		= nf_nat_ipv4_manip_pkt,
 	.csum_update		= nf_nat_ipv4_csum_update,
 	.csum_recalc		= nf_nat_ipv4_csum_recalc,
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index 290bb0142192..016ab74ac1c6 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -61,13 +61,6 @@ static void nf_nat_ipv6_decode_session(struct sk_buff *skb,
 }
 #endif
 
-static bool nf_nat_ipv6_in_range(const struct nf_conntrack_tuple *t,
-				 const struct nf_nat_range2 *range)
-{
-	return ipv6_addr_cmp(&t->src.u3.in6, &range->min_addr.in6) >= 0 &&
-	       ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0;
-}
-
 static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
 				  unsigned int iphdroff,
 				  const struct nf_nat_l4proto *l4proto,
@@ -165,7 +158,6 @@ static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[],
 
 static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = {
 	.l3proto		= NFPROTO_IPV6,
-	.in_range		= nf_nat_ipv6_in_range,
 	.manip_pkt		= nf_nat_ipv6_manip_pkt,
 	.csum_update		= nf_nat_ipv6_csum_update,
 	.csum_recalc		= nf_nat_ipv6_csum_recalc,
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 763a92e82755..e1d9903a1e40 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -172,11 +172,21 @@ nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
 }
 EXPORT_SYMBOL(nf_nat_used_tuple);
 
+static bool nf_nat_inet_in_range(const struct nf_conntrack_tuple *t,
+				 const struct nf_nat_range2 *range)
+{
+	if (t->src.l3num == NFPROTO_IPV4)
+		return ntohl(t->src.u3.ip) >= ntohl(range->min_addr.ip) &&
+		       ntohl(t->src.u3.ip) <= ntohl(range->max_addr.ip);
+
+	return ipv6_addr_cmp(&t->src.u3.in6, &range->min_addr.in6) >= 0 &&
+	       ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0;
+}
+
 /* If we source map this tuple so reply looks like reply_tuple, will
  * that meet the constraints of range.
  */
-static int in_range(const struct nf_nat_l3proto *l3proto,
-		    const struct nf_nat_l4proto *l4proto,
+static int in_range(const struct nf_nat_l4proto *l4proto,
 		    const struct nf_conntrack_tuple *tuple,
 		    const struct nf_nat_range2 *range)
 {
@@ -184,7 +194,7 @@ static int in_range(const struct nf_nat_l3proto *l3proto,
 	 * range specified, otherwise let this drag us onto a new src IP.
 	 */
 	if (range->flags & NF_NAT_RANGE_MAP_IPS &&
-	    !l3proto->in_range(tuple, range))
+	    !nf_nat_inet_in_range(tuple, range))
 		return 0;
 
 	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) ||
@@ -211,7 +221,6 @@ same_src(const struct nf_conn *ct,
 static int
 find_appropriate_src(struct net *net,
 		     const struct nf_conntrack_zone *zone,
-		     const struct nf_nat_l3proto *l3proto,
 		     const struct nf_nat_l4proto *l4proto,
 		     const struct nf_conntrack_tuple *tuple,
 		     struct nf_conntrack_tuple *result,
@@ -229,7 +238,7 @@ find_appropriate_src(struct net *net,
 				       &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
 			result->dst = tuple->dst;
 
-			if (in_range(l3proto, l4proto, result, range))
+			if (in_range(l4proto, result, range))
 				return 1;
 		}
 	}
@@ -463,12 +472,12 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	if (maniptype == NF_NAT_MANIP_SRC &&
 	    !(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) {
 		/* try the original tuple first */
-		if (in_range(l3proto, l4proto, orig_tuple, range)) {
+		if (in_range(l4proto, orig_tuple, range)) {
 			if (!nf_nat_used_tuple(orig_tuple, ct)) {
 				*tuple = *orig_tuple;
 				goto out;
 			}
-		} else if (find_appropriate_src(net, zone, l3proto, l4proto,
+		} else if (find_appropriate_src(net, zone, l4proto,
 						orig_tuple, tuple, range)) {
 			pr_debug("get_unique_tuple: Found current src map\n");
 			if (!nf_nat_used_tuple(tuple, ct))
-- 
cgit v1.2.3


From fe2d0020994cd9d4f451e3024109319af287413b Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 13 Dec 2018 16:01:31 +0100
Subject: netfilter: nat: remove l4proto->in_range

With exception of icmp, all of the l4 nat protocols set this to
nf_nat_l4proto_in_range.

Get rid of this and just check the l4proto in the caller.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l4proto.h   | 11 ------
 net/ipv4/netfilter/nf_nat_proto_gre.c    |  1 -
 net/ipv4/netfilter/nf_nat_proto_icmp.c   | 11 ------
 net/ipv6/netfilter/nf_nat_proto_icmpv6.c | 11 ------
 net/netfilter/nf_nat_core.c              | 67 ++++++++++++++++++++------------
 net/netfilter/nf_nat_proto_common.c      | 17 --------
 net/netfilter/nf_nat_proto_dccp.c        |  1 -
 net/netfilter/nf_nat_proto_sctp.c        |  1 -
 net/netfilter/nf_nat_proto_tcp.c         |  1 -
 net/netfilter/nf_nat_proto_udp.c         |  2 -
 net/netfilter/nf_nat_proto_unknown.c     |  9 -----
 11 files changed, 43 insertions(+), 89 deletions(-)

diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h
index 4a0e4f0623a0..ebf7cbf605cb 100644
--- a/include/net/netfilter/nf_nat_l4proto.h
+++ b/include/net/netfilter/nf_nat_l4proto.h
@@ -21,12 +21,6 @@ struct nf_nat_l4proto {
 			  const struct nf_conntrack_tuple *tuple,
 			  enum nf_nat_manip_type maniptype);
 
-	/* Is the manipable part of the tuple between min and max incl? */
-	bool (*in_range)(const struct nf_conntrack_tuple *tuple,
-			 enum nf_nat_manip_type maniptype,
-			 const union nf_conntrack_man_proto *min,
-			 const union nf_conntrack_man_proto *max);
-
 	int (*nlattr_to_range)(struct nlattr *tb[],
 			       struct nf_nat_range2 *range);
 };
@@ -54,11 +48,6 @@ extern const struct nf_nat_l4proto nf_nat_l4proto_sctp;
 extern const struct nf_nat_l4proto nf_nat_l4proto_udplite;
 #endif
 
-bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple,
-			     enum nf_nat_manip_type maniptype,
-			     const union nf_conntrack_man_proto *min,
-			     const union nf_conntrack_man_proto *max);
-
 int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
 				   struct nf_nat_range2 *range);
 
diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c
index a04ff7665e4c..94b735dd570d 100644
--- a/net/ipv4/netfilter/nf_nat_proto_gre.c
+++ b/net/ipv4/netfilter/nf_nat_proto_gre.c
@@ -80,7 +80,6 @@ gre_manip_pkt(struct sk_buff *skb,
 static const struct nf_nat_l4proto gre = {
 	.l4proto		= IPPROTO_GRE,
 	.manip_pkt		= gre_manip_pkt,
-	.in_range		= nf_nat_l4proto_in_range,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c
index 70d7fabdbb01..f532e2215970 100644
--- a/net/ipv4/netfilter/nf_nat_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c
@@ -17,16 +17,6 @@
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static bool
-icmp_in_range(const struct nf_conntrack_tuple *tuple,
-	      enum nf_nat_manip_type maniptype,
-	      const union nf_conntrack_man_proto *min,
-	      const union nf_conntrack_man_proto *max)
-{
-	return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) &&
-	       ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id);
-}
-
 static bool
 icmp_manip_pkt(struct sk_buff *skb,
 	       const struct nf_nat_l3proto *l3proto,
@@ -49,7 +39,6 @@ icmp_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_icmp = {
 	.l4proto		= IPPROTO_ICMP,
 	.manip_pkt		= icmp_manip_pkt,
-	.in_range		= icmp_in_range,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
index 491361b7a721..ffae55c1fb8d 100644
--- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
@@ -19,16 +19,6 @@
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static bool
-icmpv6_in_range(const struct nf_conntrack_tuple *tuple,
-		enum nf_nat_manip_type maniptype,
-		const union nf_conntrack_man_proto *min,
-		const union nf_conntrack_man_proto *max)
-{
-	return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) &&
-	       ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id);
-}
-
 static bool
 icmpv6_manip_pkt(struct sk_buff *skb,
 		 const struct nf_nat_l3proto *l3proto,
@@ -57,7 +47,6 @@ icmpv6_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = {
 	.l4proto		= IPPROTO_ICMPV6,
 	.manip_pkt		= icmpv6_manip_pkt,
-	.in_range		= icmpv6_in_range,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index e1d9903a1e40..d0351e0f21ad 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -183,11 +183,41 @@ static bool nf_nat_inet_in_range(const struct nf_conntrack_tuple *t,
 	       ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0;
 }
 
+/* Is the manipable part of the tuple between min and max incl? */
+static bool l4proto_in_range(const struct nf_conntrack_tuple *tuple,
+			     enum nf_nat_manip_type maniptype,
+			     const union nf_conntrack_man_proto *min,
+			     const union nf_conntrack_man_proto *max)
+{
+	__be16 port;
+
+	switch (tuple->dst.protonum) {
+	case IPPROTO_ICMP: /* fallthrough */
+	case IPPROTO_ICMPV6:
+		return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) &&
+		       ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id);
+	case IPPROTO_GRE: /* all fall though */
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE:
+	case IPPROTO_DCCP:
+	case IPPROTO_SCTP:
+		if (maniptype == NF_NAT_MANIP_SRC)
+			port = tuple->src.u.all;
+		else
+			port = tuple->dst.u.all;
+
+		return ntohs(port) >= ntohs(min->all) &&
+		       ntohs(port) <= ntohs(max->all);
+	default:
+		return true;
+	}
+}
+
 /* If we source map this tuple so reply looks like reply_tuple, will
  * that meet the constraints of range.
  */
-static int in_range(const struct nf_nat_l4proto *l4proto,
-		    const struct nf_conntrack_tuple *tuple,
+static int in_range(const struct nf_conntrack_tuple *tuple,
 		    const struct nf_nat_range2 *range)
 {
 	/* If we are supposed to map IPs, then we must be in the
@@ -197,12 +227,11 @@ static int in_range(const struct nf_nat_l4proto *l4proto,
 	    !nf_nat_inet_in_range(tuple, range))
 		return 0;
 
-	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) ||
-	    l4proto->in_range(tuple, NF_NAT_MANIP_SRC,
-			      &range->min_proto, &range->max_proto))
+	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED))
 		return 1;
 
-	return 0;
+	return l4proto_in_range(tuple, NF_NAT_MANIP_SRC,
+				&range->min_proto, &range->max_proto);
 }
 
 static inline int
@@ -221,7 +250,6 @@ same_src(const struct nf_conn *ct,
 static int
 find_appropriate_src(struct net *net,
 		     const struct nf_conntrack_zone *zone,
-		     const struct nf_nat_l4proto *l4proto,
 		     const struct nf_conntrack_tuple *tuple,
 		     struct nf_conntrack_tuple *result,
 		     const struct nf_nat_range2 *range)
@@ -238,7 +266,7 @@ find_appropriate_src(struct net *net,
 				       &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
 			result->dst = tuple->dst;
 
-			if (in_range(l4proto, result, range))
+			if (in_range(result, range))
 				return 1;
 		}
 	}
@@ -450,17 +478,10 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 		 enum nf_nat_manip_type maniptype)
 {
 	const struct nf_conntrack_zone *zone;
-	const struct nf_nat_l3proto *l3proto;
-	const struct nf_nat_l4proto *l4proto;
 	struct net *net = nf_ct_net(ct);
 
 	zone = nf_ct_zone(ct);
 
-	rcu_read_lock();
-	l3proto = __nf_nat_l3proto_find(orig_tuple->src.l3num);
-	l4proto = __nf_nat_l4proto_find(orig_tuple->src.l3num,
-					orig_tuple->dst.protonum);
-
 	/* 1) If this srcip/proto/src-proto-part is currently mapped,
 	 * and that same mapping gives a unique tuple within the given
 	 * range, use that.
@@ -472,16 +493,16 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	if (maniptype == NF_NAT_MANIP_SRC &&
 	    !(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) {
 		/* try the original tuple first */
-		if (in_range(l4proto, orig_tuple, range)) {
+		if (in_range(orig_tuple, range)) {
 			if (!nf_nat_used_tuple(orig_tuple, ct)) {
 				*tuple = *orig_tuple;
-				goto out;
+				return;
 			}
-		} else if (find_appropriate_src(net, zone, l4proto,
+		} else if (find_appropriate_src(net, zone,
 						orig_tuple, tuple, range)) {
 			pr_debug("get_unique_tuple: Found current src map\n");
 			if (!nf_nat_used_tuple(tuple, ct))
-				goto out;
+				return;
 		}
 	}
 
@@ -497,21 +518,19 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) {
 		if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
 			if (!(range->flags & NF_NAT_RANGE_PROTO_OFFSET) &&
-			    l4proto->in_range(tuple, maniptype,
+			    l4proto_in_range(tuple, maniptype,
 			          &range->min_proto,
 			          &range->max_proto) &&
 			    (range->min_proto.all == range->max_proto.all ||
 			     !nf_nat_used_tuple(tuple, ct)))
-				goto out;
+				return;
 		} else if (!nf_nat_used_tuple(tuple, ct)) {
-			goto out;
+			return;
 		}
 	}
 
 	/* Last chance: get protocol to try to obtain unique tuple. */
 	nf_nat_l4proto_unique_tuple(tuple, range, maniptype, ct);
-out:
-	rcu_read_unlock();
 }
 
 struct nf_conn_nat *nf_ct_nat_ext_add(struct nf_conn *ct)
diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c
index ef14d86f0f5b..a155cfa1cc13 100644
--- a/net/netfilter/nf_nat_proto_common.c
+++ b/net/netfilter/nf_nat_proto_common.c
@@ -17,23 +17,6 @@
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple,
-			     enum nf_nat_manip_type maniptype,
-			     const union nf_conntrack_man_proto *min,
-			     const union nf_conntrack_man_proto *max)
-{
-	__be16 port;
-
-	if (maniptype == NF_NAT_MANIP_SRC)
-		port = tuple->src.u.all;
-	else
-		port = tuple->dst.u.all;
-
-	return ntohs(port) >= ntohs(min->all) &&
-	       ntohs(port) <= ntohs(max->all);
-}
-EXPORT_SYMBOL_GPL(nf_nat_l4proto_in_range);
-
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
 				   struct nf_nat_range2 *range)
diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c
index 8dbba7b20177..a5ed1e3e4f22 100644
--- a/net/netfilter/nf_nat_proto_dccp.c
+++ b/net/netfilter/nf_nat_proto_dccp.c
@@ -61,7 +61,6 @@ dccp_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_dccp = {
 	.l4proto		= IPPROTO_DCCP,
 	.manip_pkt		= dccp_manip_pkt,
-	.in_range		= nf_nat_l4proto_in_range,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c
index da86475d0db6..ff5f5bbd2ff1 100644
--- a/net/netfilter/nf_nat_proto_sctp.c
+++ b/net/netfilter/nf_nat_proto_sctp.c
@@ -56,7 +56,6 @@ sctp_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_sctp = {
 	.l4proto		= IPPROTO_SCTP,
 	.manip_pkt		= sctp_manip_pkt,
-	.in_range		= nf_nat_l4proto_in_range,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c
index 666a4b3303f7..c938ecf7e0b0 100644
--- a/net/netfilter/nf_nat_proto_tcp.c
+++ b/net/netfilter/nf_nat_proto_tcp.c
@@ -64,7 +64,6 @@ tcp_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_tcp = {
 	.l4proto		= IPPROTO_TCP,
 	.manip_pkt		= tcp_manip_pkt,
-	.in_range		= nf_nat_l4proto_in_range,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c
index 26f3715a457a..6703eb005c67 100644
--- a/net/netfilter/nf_nat_proto_udp.c
+++ b/net/netfilter/nf_nat_proto_udp.c
@@ -85,7 +85,6 @@ static bool udplite_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_udplite = {
 	.l4proto		= IPPROTO_UDPLITE,
 	.manip_pkt		= udplite_manip_pkt,
-	.in_range		= nf_nat_l4proto_in_range,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
@@ -95,7 +94,6 @@ const struct nf_nat_l4proto nf_nat_l4proto_udplite = {
 const struct nf_nat_l4proto nf_nat_l4proto_udp = {
 	.l4proto		= IPPROTO_UDP,
 	.manip_pkt		= udp_manip_pkt,
-	.in_range		= nf_nat_l4proto_in_range,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
diff --git a/net/netfilter/nf_nat_proto_unknown.c b/net/netfilter/nf_nat_proto_unknown.c
index 16b66785ea5b..ba178b02fc1a 100644
--- a/net/netfilter/nf_nat_proto_unknown.c
+++ b/net/netfilter/nf_nat_proto_unknown.c
@@ -17,14 +17,6 @@
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static bool unknown_in_range(const struct nf_conntrack_tuple *tuple,
-			     enum nf_nat_manip_type manip_type,
-			     const union nf_conntrack_man_proto *min,
-			     const union nf_conntrack_man_proto *max)
-{
-	return true;
-}
-
 static bool
 unknown_manip_pkt(struct sk_buff *skb,
 		  const struct nf_nat_l3proto *l3proto,
@@ -37,5 +29,4 @@ unknown_manip_pkt(struct sk_buff *skb,
 
 const struct nf_nat_l4proto nf_nat_l4proto_unknown = {
 	.manip_pkt		= unknown_manip_pkt,
-	.in_range		= unknown_in_range,
 };
-- 
cgit v1.2.3


From 76b90019e03d866eab85cb57c2a6416ab94284dc Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 13 Dec 2018 16:01:32 +0100
Subject: netfilter: nat: remove l4proto->nlattr_to_range

all protocols did set this to nf_nat_l4proto_nlattr_to_range, so
just call it directly.

The important difference is that we'll now also call it for
protocols that we don't support (i.e., nf_nat_proto_unknown did
not provide .nlattr_to_range).

However, there should be no harm, even icmp provided this callback.
If we don't implement a specific l4nat for this, nothing would make
use of this information, so adding a big switch/case construct listing
all supported l4protocols seems a bit pointless.

This change leaves a single function pointer in the l4proto struct.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l4proto.h   |  6 ------
 net/ipv4/netfilter/nf_nat_proto_gre.c    |  3 ---
 net/ipv4/netfilter/nf_nat_proto_icmp.c   |  3 ---
 net/ipv6/netfilter/nf_nat_proto_icmpv6.c |  3 ---
 net/netfilter/Makefile                   |  2 +-
 net/netfilter/nf_nat_core.c              | 22 +++++++++++++------
 net/netfilter/nf_nat_proto_common.c      | 36 --------------------------------
 net/netfilter/nf_nat_proto_dccp.c        |  3 ---
 net/netfilter/nf_nat_proto_sctp.c        |  3 ---
 net/netfilter/nf_nat_proto_tcp.c         |  3 ---
 net/netfilter/nf_nat_proto_udp.c         |  6 ------
 11 files changed, 17 insertions(+), 73 deletions(-)
 delete mode 100644 net/netfilter/nf_nat_proto_common.c

diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h
index ebf7cbf605cb..406f7effeb8e 100644
--- a/include/net/netfilter/nf_nat_l4proto.h
+++ b/include/net/netfilter/nf_nat_l4proto.h
@@ -20,9 +20,6 @@ struct nf_nat_l4proto {
 			  unsigned int iphdroff, unsigned int hdroff,
 			  const struct nf_conntrack_tuple *tuple,
 			  enum nf_nat_manip_type maniptype);
-
-	int (*nlattr_to_range)(struct nlattr *tb[],
-			       struct nf_nat_range2 *range);
 };
 
 /* Protocol registration. */
@@ -48,7 +45,4 @@ extern const struct nf_nat_l4proto nf_nat_l4proto_sctp;
 extern const struct nf_nat_l4proto nf_nat_l4proto_udplite;
 #endif
 
-int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
-				   struct nf_nat_range2 *range);
-
 #endif /*_NF_NAT_L4PROTO_H*/
diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c
index 94b735dd570d..86af36651edd 100644
--- a/net/ipv4/netfilter/nf_nat_proto_gre.c
+++ b/net/ipv4/netfilter/nf_nat_proto_gre.c
@@ -80,9 +80,6 @@ gre_manip_pkt(struct sk_buff *skb,
 static const struct nf_nat_l4proto gre = {
 	.l4proto		= IPPROTO_GRE,
 	.manip_pkt		= gre_manip_pkt,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
-#endif
 };
 
 static int __init nf_nat_proto_gre_init(void)
diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c
index f532e2215970..4fecb3f2c55a 100644
--- a/net/ipv4/netfilter/nf_nat_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c
@@ -39,7 +39,4 @@ icmp_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_icmp = {
 	.l4proto		= IPPROTO_ICMP,
 	.manip_pkt		= icmp_manip_pkt,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
-#endif
 };
diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
index ffae55c1fb8d..14717c226cec 100644
--- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
@@ -47,7 +47,4 @@ icmpv6_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = {
 	.l4proto		= IPPROTO_ICMPV6,
 	.manip_pkt		= icmpv6_manip_pkt,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
-#endif
 };
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 4ddf3ef51ece..852e47cd769b 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -47,7 +47,7 @@ obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o
 obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
 obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o
 
-nf_nat-y	:= nf_nat_core.o nf_nat_proto_unknown.o nf_nat_proto_common.o \
+nf_nat-y	:= nf_nat_core.o nf_nat_proto_unknown.o \
 		   nf_nat_proto_udp.o nf_nat_proto_tcp.o nf_nat_helper.o
 
 # NAT protocols (nf_nat)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index d0351e0f21ad..2d7fac80341b 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -946,12 +946,26 @@ static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = {
 	[CTA_PROTONAT_PORT_MAX]	= { .type = NLA_U16 },
 };
 
+static int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
+					  struct nf_nat_range2 *range)
+{
+	if (tb[CTA_PROTONAT_PORT_MIN]) {
+		range->min_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]);
+		range->max_proto.all = range->min_proto.all;
+		range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+	}
+	if (tb[CTA_PROTONAT_PORT_MAX]) {
+		range->max_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MAX]);
+		range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+	}
+	return 0;
+}
+
 static int nfnetlink_parse_nat_proto(struct nlattr *attr,
 				     const struct nf_conn *ct,
 				     struct nf_nat_range2 *range)
 {
 	struct nlattr *tb[CTA_PROTONAT_MAX+1];
-	const struct nf_nat_l4proto *l4proto;
 	int err;
 
 	err = nla_parse_nested(tb, CTA_PROTONAT_MAX, attr,
@@ -959,11 +973,7 @@ static int nfnetlink_parse_nat_proto(struct nlattr *attr,
 	if (err < 0)
 		return err;
 
-	l4proto = __nf_nat_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
-	if (l4proto->nlattr_to_range)
-		err = l4proto->nlattr_to_range(tb, range);
-
-	return err;
+	return nf_nat_l4proto_nlattr_to_range(tb, range);
 }
 
 static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = {
diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c
deleted file mode 100644
index a155cfa1cc13..000000000000
--- a/net/netfilter/nf_nat_proto_common.c
+++ /dev/null
@@ -1,36 +0,0 @@
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
- * (C) 2008 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/types.h>
-#include <linux/random.h>
-#include <linux/netfilter.h>
-#include <linux/export.h>
-
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_core.h>
-#include <net/netfilter/nf_nat_l3proto.h>
-#include <net/netfilter/nf_nat_l4proto.h>
-
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
-				   struct nf_nat_range2 *range)
-{
-	if (tb[CTA_PROTONAT_PORT_MIN]) {
-		range->min_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]);
-		range->max_proto.all = range->min_proto.all;
-		range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
-	}
-	if (tb[CTA_PROTONAT_PORT_MAX]) {
-		range->max_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MAX]);
-		range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(nf_nat_l4proto_nlattr_to_range);
-#endif
diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c
index a5ed1e3e4f22..ab0b1384717d 100644
--- a/net/netfilter/nf_nat_proto_dccp.c
+++ b/net/netfilter/nf_nat_proto_dccp.c
@@ -61,7 +61,4 @@ dccp_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_dccp = {
 	.l4proto		= IPPROTO_DCCP,
 	.manip_pkt		= dccp_manip_pkt,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
-#endif
 };
diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c
index ff5f5bbd2ff1..37a9d347a029 100644
--- a/net/netfilter/nf_nat_proto_sctp.c
+++ b/net/netfilter/nf_nat_proto_sctp.c
@@ -56,7 +56,4 @@ sctp_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_sctp = {
 	.l4proto		= IPPROTO_SCTP,
 	.manip_pkt		= sctp_manip_pkt,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
-#endif
 };
diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c
index c938ecf7e0b0..d378b6c31d34 100644
--- a/net/netfilter/nf_nat_proto_tcp.c
+++ b/net/netfilter/nf_nat_proto_tcp.c
@@ -64,7 +64,4 @@ tcp_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_tcp = {
 	.l4proto		= IPPROTO_TCP,
 	.manip_pkt		= tcp_manip_pkt,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
-#endif
 };
diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c
index 6703eb005c67..25fc6138fbf7 100644
--- a/net/netfilter/nf_nat_proto_udp.c
+++ b/net/netfilter/nf_nat_proto_udp.c
@@ -85,16 +85,10 @@ static bool udplite_manip_pkt(struct sk_buff *skb,
 const struct nf_nat_l4proto nf_nat_l4proto_udplite = {
 	.l4proto		= IPPROTO_UDPLITE,
 	.manip_pkt		= udplite_manip_pkt,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
-#endif
 };
 #endif /* CONFIG_NF_NAT_PROTO_UDPLITE */
 
 const struct nf_nat_l4proto nf_nat_l4proto_udp = {
 	.l4proto		= IPPROTO_UDP,
 	.manip_pkt		= udp_manip_pkt,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
-#endif
 };
-- 
cgit v1.2.3


From faec18dbb0405c7d4dda025054511dc3a6696918 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 13 Dec 2018 16:01:33 +0100
Subject: netfilter: nat: remove l4proto->manip_pkt

This removes the last l4proto indirection, the two callers, the l3proto
packet mangling helpers for ipv4 and ipv6, now call the
nf_nat_l4proto_manip_pkt() helper.

nf_nat_proto_{dccp,tcp,sctp,gre,icmp,icmpv6} are left behind, even though
they contain no functionality anymore to not clutter this patch.

Next patch will remove the empty files and the nf_nat_l4proto
struct.

nf_nat_proto_udp.c is renamed to nf_nat_proto.c, as it now contains the
other nat manip functionality as well, not just udp and udplite.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l4proto.h   |  15 +-
 net/ipv4/netfilter/Kconfig               |   5 -
 net/ipv4/netfilter/nf_nat_l3proto_ipv4.c |   4 +-
 net/ipv4/netfilter/nf_nat_pptp.c         |   2 -
 net/ipv4/netfilter/nf_nat_proto_gre.c    |  41 ----
 net/ipv4/netfilter/nf_nat_proto_icmp.c   |  21 --
 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c |   4 +-
 net/ipv6/netfilter/nf_nat_proto_icmpv6.c |  26 ---
 net/netfilter/Kconfig                    |  15 --
 net/netfilter/Makefile                   |   2 +-
 net/netfilter/nf_nat_proto.c             | 353 +++++++++++++++++++++++++++++++
 net/netfilter/nf_nat_proto_dccp.c        |  42 ----
 net/netfilter/nf_nat_proto_sctp.c        |  43 ----
 net/netfilter/nf_nat_proto_tcp.c         |  44 ----
 net/netfilter/nf_nat_proto_udp.c         |  94 --------
 net/netfilter/nf_nat_proto_unknown.c     |  11 -
 16 files changed, 365 insertions(+), 357 deletions(-)
 create mode 100644 net/netfilter/nf_nat_proto.c
 delete mode 100644 net/netfilter/nf_nat_proto_udp.c

diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h
index 406f7effeb8e..7b57bd302107 100644
--- a/include/net/netfilter/nf_nat_l4proto.h
+++ b/include/net/netfilter/nf_nat_l4proto.h
@@ -12,14 +12,6 @@ struct nf_nat_l4proto {
 	/* Protocol number. */
 	u8 l4proto;
 
-	/* Translate a packet to the target according to manip type.
-	 * Return true if succeeded.
-	 */
-	bool (*manip_pkt)(struct sk_buff *skb,
-			  const struct nf_nat_l3proto *l3proto,
-			  unsigned int iphdroff, unsigned int hdroff,
-			  const struct nf_conntrack_tuple *tuple,
-			  enum nf_nat_manip_type maniptype);
 };
 
 /* Protocol registration. */
@@ -29,6 +21,13 @@ void nf_nat_l4proto_unregister(u8 l3proto,
 
 const struct nf_nat_l4proto *__nf_nat_l4proto_find(u8 l3proto, u8 l4proto);
 
+/* Translate a packet to the target according to manip type.  Return on success. */
+bool nf_nat_l4proto_manip_pkt(struct sk_buff *skb,
+			      const struct nf_nat_l3proto *l3proto,
+			      unsigned int iphdroff, unsigned int hdroff,
+			      const struct nf_conntrack_tuple *tuple,
+			      enum nf_nat_manip_type maniptype);
+
 /* Built-in protocols. */
 extern const struct nf_nat_l4proto nf_nat_l4proto_tcp;
 extern const struct nf_nat_l4proto nf_nat_l4proto_udp;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 184bf2e0a1ed..80f72cc5ca8d 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -156,15 +156,10 @@ config NF_NAT_SNMP_BASIC
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
-config NF_NAT_PROTO_GRE
-	tristate
-	depends on NF_CT_PROTO_GRE
-
 config NF_NAT_PPTP
 	tristate
 	depends on NF_CONNTRACK
 	default NF_CONNTRACK_PPTP
-	select NF_NAT_PROTO_GRE
 
 config NF_NAT_H323
 	tristate
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index 00904e605e85..65fdb7a74621 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -77,8 +77,8 @@ static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb,
 	iph = (void *)skb->data + iphdroff;
 	hdroff = iphdroff + iph->ihl * 4;
 
-	if (!l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv4, iphdroff, hdroff,
-				target, maniptype))
+	if (!nf_nat_l4proto_manip_pkt(skb, &nf_nat_l3proto_ipv4, iphdroff,
+				      hdroff, target, maniptype))
 		return false;
 	iph = (void *)skb->data + iphdroff;
 
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 5d259a12e25f..68b4d450391b 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -299,8 +299,6 @@ pptp_inbound_pkt(struct sk_buff *skb,
 
 static int __init nf_nat_helper_pptp_init(void)
 {
-	nf_nat_need_gre();
-
 	BUG_ON(nf_nat_pptp_hook_outbound != NULL);
 	RCU_INIT_POINTER(nf_nat_pptp_hook_outbound, pptp_outbound_pkt);
 
diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c
index 86af36651edd..25849295d537 100644
--- a/net/ipv4/netfilter/nf_nat_proto_gre.c
+++ b/net/ipv4/netfilter/nf_nat_proto_gre.c
@@ -37,49 +37,8 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>");
 MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE");
 
-/* manipulate a GRE packet according to maniptype */
-static bool
-gre_manip_pkt(struct sk_buff *skb,
-	      const struct nf_nat_l3proto *l3proto,
-	      unsigned int iphdroff, unsigned int hdroff,
-	      const struct nf_conntrack_tuple *tuple,
-	      enum nf_nat_manip_type maniptype)
-{
-	const struct gre_base_hdr *greh;
-	struct pptp_gre_header *pgreh;
-
-	/* pgreh includes two optional 32bit fields which are not required
-	 * to be there.  That's where the magic '8' comes from */
-	if (!skb_make_writable(skb, hdroff + sizeof(*pgreh) - 8))
-		return false;
-
-	greh = (void *)skb->data + hdroff;
-	pgreh = (struct pptp_gre_header *)greh;
-
-	/* we only have destination manip of a packet, since 'source key'
-	 * is not present in the packet itself */
-	if (maniptype != NF_NAT_MANIP_DST)
-		return true;
-
-	switch (greh->flags & GRE_VERSION) {
-	case GRE_VERSION_0:
-		/* We do not currently NAT any GREv0 packets.
-		 * Try to behave like "nf_nat_proto_unknown" */
-		break;
-	case GRE_VERSION_1:
-		pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key));
-		pgreh->call_id = tuple->dst.u.gre.key;
-		break;
-	default:
-		pr_debug("can't nat unknown GRE version\n");
-		return false;
-	}
-	return true;
-}
-
 static const struct nf_nat_l4proto gre = {
 	.l4proto		= IPPROTO_GRE,
-	.manip_pkt		= gre_manip_pkt,
 };
 
 static int __init nf_nat_proto_gre_init(void)
diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c
index 4fecb3f2c55a..c2b7fd1a997b 100644
--- a/net/ipv4/netfilter/nf_nat_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c
@@ -10,33 +10,12 @@
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/ip.h>
-#include <linux/icmp.h>
 
 #include <linux/netfilter.h>
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static bool
-icmp_manip_pkt(struct sk_buff *skb,
-	       const struct nf_nat_l3proto *l3proto,
-	       unsigned int iphdroff, unsigned int hdroff,
-	       const struct nf_conntrack_tuple *tuple,
-	       enum nf_nat_manip_type maniptype)
-{
-	struct icmphdr *hdr;
-
-	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
-		return false;
-
-	hdr = (struct icmphdr *)(skb->data + hdroff);
-	inet_proto_csum_replace2(&hdr->checksum, skb,
-				 hdr->un.echo.id, tuple->src.u.icmp.id, false);
-	hdr->un.echo.id = tuple->src.u.icmp.id;
-	return true;
-}
-
 const struct nf_nat_l4proto nf_nat_l4proto_icmp = {
 	.l4proto		= IPPROTO_ICMP,
-	.manip_pkt		= icmp_manip_pkt,
 };
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index 016ab74ac1c6..6ff1375799c7 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -83,8 +83,8 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
 		goto manip_addr;
 
 	if ((frag_off & htons(~0x7)) == 0 &&
-	    !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff,
-				target, maniptype))
+	    !nf_nat_l4proto_manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff,
+				      target, maniptype))
 		return false;
 
 	/* must reload, offset might have changed */
diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
index 14717c226cec..fcbe7e750420 100644
--- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
@@ -19,32 +19,6 @@
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static bool
-icmpv6_manip_pkt(struct sk_buff *skb,
-		 const struct nf_nat_l3proto *l3proto,
-		 unsigned int iphdroff, unsigned int hdroff,
-		 const struct nf_conntrack_tuple *tuple,
-		 enum nf_nat_manip_type maniptype)
-{
-	struct icmp6hdr *hdr;
-
-	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
-		return false;
-
-	hdr = (struct icmp6hdr *)(skb->data + hdroff);
-	l3proto->csum_update(skb, iphdroff, &hdr->icmp6_cksum,
-			     tuple, maniptype);
-	if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST ||
-	    hdr->icmp6_type == ICMPV6_ECHO_REPLY) {
-		inet_proto_csum_replace2(&hdr->icmp6_cksum, skb,
-					 hdr->icmp6_identifier,
-					 tuple->src.u.icmp.id, false);
-		hdr->icmp6_identifier = tuple->src.u.icmp.id;
-	}
-	return true;
-}
-
 const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = {
 	.l4proto		= IPPROTO_ICMPV6,
-	.manip_pkt		= icmpv6_manip_pkt,
 };
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 2ab870ef233a..beb3a69ce1d4 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -403,21 +403,6 @@ config NF_NAT_NEEDED
 	depends on NF_NAT
 	default y
 
-config NF_NAT_PROTO_DCCP
-	bool
-	depends on NF_NAT && NF_CT_PROTO_DCCP
-	default NF_NAT && NF_CT_PROTO_DCCP
-
-config NF_NAT_PROTO_UDPLITE
-	bool
-	depends on NF_NAT && NF_CT_PROTO_UDPLITE
-	default NF_NAT && NF_CT_PROTO_UDPLITE
-
-config NF_NAT_PROTO_SCTP
-	bool
-	default NF_NAT && NF_CT_PROTO_SCTP
-	depends on NF_NAT && NF_CT_PROTO_SCTP
-
 config NF_NAT_AMANDA
 	tristate
 	depends on NF_CONNTRACK && NF_NAT
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 852e47cd769b..ed4a912c5484 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -48,7 +48,7 @@ obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
 obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o
 
 nf_nat-y	:= nf_nat_core.o nf_nat_proto_unknown.o \
-		   nf_nat_proto_udp.o nf_nat_proto_tcp.o nf_nat_helper.o
+		   nf_nat_proto.o nf_nat_proto_tcp.o nf_nat_helper.o
 
 # NAT protocols (nf_nat)
 nf_nat-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
new file mode 100644
index 000000000000..1042706827cb
--- /dev/null
+++ b/net/netfilter/nf_nat_proto.c
@@ -0,0 +1,353 @@
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+
+#include <linux/dccp.h>
+#include <linux/sctp.h>
+#include <net/sctp/checksum.h>
+
+#include <linux/netfilter.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+#include <net/netfilter/nf_nat_l4proto.h>
+
+static void
+__udp_manip_pkt(struct sk_buff *skb,
+	        const struct nf_nat_l3proto *l3proto,
+	        unsigned int iphdroff, struct udphdr *hdr,
+	        const struct nf_conntrack_tuple *tuple,
+	        enum nf_nat_manip_type maniptype, bool do_csum)
+{
+	__be16 *portptr, newport;
+
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		/* Get rid of src port */
+		newport = tuple->src.u.udp.port;
+		portptr = &hdr->source;
+	} else {
+		/* Get rid of dst port */
+		newport = tuple->dst.u.udp.port;
+		portptr = &hdr->dest;
+	}
+	if (do_csum) {
+		l3proto->csum_update(skb, iphdroff, &hdr->check,
+				     tuple, maniptype);
+		inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport,
+					 false);
+		if (!hdr->check)
+			hdr->check = CSUM_MANGLED_0;
+	}
+	*portptr = newport;
+}
+
+static bool udp_manip_pkt(struct sk_buff *skb,
+			  const struct nf_nat_l3proto *l3proto,
+			  unsigned int iphdroff, unsigned int hdroff,
+			  const struct nf_conntrack_tuple *tuple,
+			  enum nf_nat_manip_type maniptype)
+{
+	struct udphdr *hdr;
+	bool do_csum;
+
+	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
+		return false;
+
+	hdr = (struct udphdr *)(skb->data + hdroff);
+	do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL;
+
+	__udp_manip_pkt(skb, l3proto, iphdroff, hdr, tuple, maniptype, do_csum);
+	return true;
+}
+
+static bool udplite_manip_pkt(struct sk_buff *skb,
+			      const struct nf_nat_l3proto *l3proto,
+			      unsigned int iphdroff, unsigned int hdroff,
+			      const struct nf_conntrack_tuple *tuple,
+			      enum nf_nat_manip_type maniptype)
+{
+#ifdef CONFIG_NF_CT_PROTO_UDPLITE
+	struct udphdr *hdr;
+
+	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
+		return false;
+
+	hdr = (struct udphdr *)(skb->data + hdroff);
+	__udp_manip_pkt(skb, l3proto, iphdroff, hdr, tuple, maniptype, true);
+#endif
+	return true;
+}
+
+static bool
+sctp_manip_pkt(struct sk_buff *skb,
+	       const struct nf_nat_l3proto *l3proto,
+	       unsigned int iphdroff, unsigned int hdroff,
+	       const struct nf_conntrack_tuple *tuple,
+	       enum nf_nat_manip_type maniptype)
+{
+#ifdef CONFIG_NF_CT_PROTO_SCTP
+	struct sctphdr *hdr;
+	int hdrsize = 8;
+
+	/* This could be an inner header returned in imcp packet; in such
+	 * cases we cannot update the checksum field since it is outside
+	 * of the 8 bytes of transport layer headers we are guaranteed.
+	 */
+	if (skb->len >= hdroff + sizeof(*hdr))
+		hdrsize = sizeof(*hdr);
+
+	if (!skb_make_writable(skb, hdroff + hdrsize))
+		return false;
+
+	hdr = (struct sctphdr *)(skb->data + hdroff);
+
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		/* Get rid of src port */
+		hdr->source = tuple->src.u.sctp.port;
+	} else {
+		/* Get rid of dst port */
+		hdr->dest = tuple->dst.u.sctp.port;
+	}
+
+	if (hdrsize < sizeof(*hdr))
+		return true;
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		hdr->checksum = sctp_compute_cksum(skb, hdroff);
+		skb->ip_summed = CHECKSUM_NONE;
+	}
+
+#endif
+	return true;
+}
+
+static bool
+tcp_manip_pkt(struct sk_buff *skb,
+	      const struct nf_nat_l3proto *l3proto,
+	      unsigned int iphdroff, unsigned int hdroff,
+	      const struct nf_conntrack_tuple *tuple,
+	      enum nf_nat_manip_type maniptype)
+{
+	struct tcphdr *hdr;
+	__be16 *portptr, newport, oldport;
+	int hdrsize = 8; /* TCP connection tracking guarantees this much */
+
+	/* this could be a inner header returned in icmp packet; in such
+	   cases we cannot update the checksum field since it is outside of
+	   the 8 bytes of transport layer headers we are guaranteed */
+	if (skb->len >= hdroff + sizeof(struct tcphdr))
+		hdrsize = sizeof(struct tcphdr);
+
+	if (!skb_make_writable(skb, hdroff + hdrsize))
+		return false;
+
+	hdr = (struct tcphdr *)(skb->data + hdroff);
+
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		/* Get rid of src port */
+		newport = tuple->src.u.tcp.port;
+		portptr = &hdr->source;
+	} else {
+		/* Get rid of dst port */
+		newport = tuple->dst.u.tcp.port;
+		portptr = &hdr->dest;
+	}
+
+	oldport = *portptr;
+	*portptr = newport;
+
+	if (hdrsize < sizeof(*hdr))
+		return true;
+
+	l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype);
+	inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, false);
+	return true;
+}
+
+static bool
+dccp_manip_pkt(struct sk_buff *skb,
+	       const struct nf_nat_l3proto *l3proto,
+	       unsigned int iphdroff, unsigned int hdroff,
+	       const struct nf_conntrack_tuple *tuple,
+	       enum nf_nat_manip_type maniptype)
+{
+#ifdef CONFIG_NF_CT_PROTO_DCCP
+	struct dccp_hdr *hdr;
+	__be16 *portptr, oldport, newport;
+	int hdrsize = 8; /* DCCP connection tracking guarantees this much */
+
+	if (skb->len >= hdroff + sizeof(struct dccp_hdr))
+		hdrsize = sizeof(struct dccp_hdr);
+
+	if (!skb_make_writable(skb, hdroff + hdrsize))
+		return false;
+
+	hdr = (struct dccp_hdr *)(skb->data + hdroff);
+
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		newport = tuple->src.u.dccp.port;
+		portptr = &hdr->dccph_sport;
+	} else {
+		newport = tuple->dst.u.dccp.port;
+		portptr = &hdr->dccph_dport;
+	}
+
+	oldport = *portptr;
+	*portptr = newport;
+
+	if (hdrsize < sizeof(*hdr))
+		return true;
+
+	l3proto->csum_update(skb, iphdroff, &hdr->dccph_checksum,
+			     tuple, maniptype);
+	inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport,
+				 false);
+#endif
+	return true;
+}
+
+static bool
+icmp_manip_pkt(struct sk_buff *skb,
+	       const struct nf_nat_l3proto *l3proto,
+	       unsigned int iphdroff, unsigned int hdroff,
+	       const struct nf_conntrack_tuple *tuple,
+	       enum nf_nat_manip_type maniptype)
+{
+	struct icmphdr *hdr;
+
+	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
+		return false;
+
+	hdr = (struct icmphdr *)(skb->data + hdroff);
+	inet_proto_csum_replace2(&hdr->checksum, skb,
+				 hdr->un.echo.id, tuple->src.u.icmp.id, false);
+	hdr->un.echo.id = tuple->src.u.icmp.id;
+	return true;
+}
+
+static bool
+icmpv6_manip_pkt(struct sk_buff *skb,
+		 const struct nf_nat_l3proto *l3proto,
+		 unsigned int iphdroff, unsigned int hdroff,
+		 const struct nf_conntrack_tuple *tuple,
+		 enum nf_nat_manip_type maniptype)
+{
+	struct icmp6hdr *hdr;
+
+	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
+		return false;
+
+	hdr = (struct icmp6hdr *)(skb->data + hdroff);
+	l3proto->csum_update(skb, iphdroff, &hdr->icmp6_cksum,
+			     tuple, maniptype);
+	if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST ||
+	    hdr->icmp6_type == ICMPV6_ECHO_REPLY) {
+		inet_proto_csum_replace2(&hdr->icmp6_cksum, skb,
+					 hdr->icmp6_identifier,
+					 tuple->src.u.icmp.id, false);
+		hdr->icmp6_identifier = tuple->src.u.icmp.id;
+	}
+	return true;
+}
+
+/* manipulate a GRE packet according to maniptype */
+static bool
+gre_manip_pkt(struct sk_buff *skb,
+	      const struct nf_nat_l3proto *l3proto,
+	      unsigned int iphdroff, unsigned int hdroff,
+	      const struct nf_conntrack_tuple *tuple,
+	      enum nf_nat_manip_type maniptype)
+{
+#if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE)
+	const struct gre_base_hdr *greh;
+	struct pptp_gre_header *pgreh;
+
+	/* pgreh includes two optional 32bit fields which are not required
+	 * to be there.  That's where the magic '8' comes from */
+	if (!skb_make_writable(skb, hdroff + sizeof(*pgreh) - 8))
+		return false;
+
+	greh = (void *)skb->data + hdroff;
+	pgreh = (struct pptp_gre_header *)greh;
+
+	/* we only have destination manip of a packet, since 'source key'
+	 * is not present in the packet itself */
+	if (maniptype != NF_NAT_MANIP_DST)
+		return true;
+
+	switch (greh->flags & GRE_VERSION) {
+	case GRE_VERSION_0:
+		/* We do not currently NAT any GREv0 packets.
+		 * Try to behave like "nf_nat_proto_unknown" */
+		break;
+	case GRE_VERSION_1:
+		pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key));
+		pgreh->call_id = tuple->dst.u.gre.key;
+		break;
+	default:
+		pr_debug("can't nat unknown GRE version\n");
+		return false;
+	}
+#endif
+	return true;
+}
+
+bool nf_nat_l4proto_manip_pkt(struct sk_buff *skb,
+			      const struct nf_nat_l3proto *l3proto,
+			      unsigned int iphdroff, unsigned int hdroff,
+			      const struct nf_conntrack_tuple *tuple,
+			      enum nf_nat_manip_type maniptype)
+{
+	switch (tuple->dst.protonum) {
+	case IPPROTO_TCP:
+		return tcp_manip_pkt(skb, l3proto, iphdroff, hdroff,
+				     tuple, maniptype);
+	case IPPROTO_UDP:
+		return udp_manip_pkt(skb, l3proto, iphdroff, hdroff,
+				     tuple, maniptype);
+	case IPPROTO_UDPLITE:
+		return udplite_manip_pkt(skb, l3proto, iphdroff, hdroff,
+					 tuple, maniptype);
+	case IPPROTO_SCTP:
+		return sctp_manip_pkt(skb, l3proto, iphdroff, hdroff,
+				      tuple, maniptype);
+	case IPPROTO_ICMP:
+		return icmp_manip_pkt(skb, l3proto, iphdroff, hdroff,
+				      tuple, maniptype);
+	case IPPROTO_ICMPV6:
+		return icmpv6_manip_pkt(skb, l3proto, iphdroff, hdroff,
+					tuple, maniptype);
+	case IPPROTO_DCCP:
+		return dccp_manip_pkt(skb, l3proto, iphdroff, hdroff,
+				      tuple, maniptype);
+	case IPPROTO_GRE:
+		return gre_manip_pkt(skb, l3proto, iphdroff, hdroff,
+				     tuple, maniptype);
+	}
+
+	/* If we don't know protocol -- no error, pass it unmodified. */
+	return true;
+}
+EXPORT_SYMBOL_GPL(nf_nat_l4proto_manip_pkt);
+
+#ifdef CONFIG_NF_NAT_PROTO_UDPLITE
+const struct nf_nat_l4proto nf_nat_l4proto_udplite = {
+	.l4proto		= IPPROTO_UDPLITE,
+};
+#endif /* CONFIG_NF_NAT_PROTO_UDPLITE */
+
+const struct nf_nat_l4proto nf_nat_l4proto_udp = {
+	.l4proto		= IPPROTO_UDP,
+};
diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c
index ab0b1384717d..dace808d4a23 100644
--- a/net/netfilter/nf_nat_proto_dccp.c
+++ b/net/netfilter/nf_nat_proto_dccp.c
@@ -11,54 +11,12 @@
 
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
-#include <linux/dccp.h>
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static bool
-dccp_manip_pkt(struct sk_buff *skb,
-	       const struct nf_nat_l3proto *l3proto,
-	       unsigned int iphdroff, unsigned int hdroff,
-	       const struct nf_conntrack_tuple *tuple,
-	       enum nf_nat_manip_type maniptype)
-{
-	struct dccp_hdr *hdr;
-	__be16 *portptr, oldport, newport;
-	int hdrsize = 8; /* DCCP connection tracking guarantees this much */
-
-	if (skb->len >= hdroff + sizeof(struct dccp_hdr))
-		hdrsize = sizeof(struct dccp_hdr);
-
-	if (!skb_make_writable(skb, hdroff + hdrsize))
-		return false;
-
-	hdr = (struct dccp_hdr *)(skb->data + hdroff);
-
-	if (maniptype == NF_NAT_MANIP_SRC) {
-		newport = tuple->src.u.dccp.port;
-		portptr = &hdr->dccph_sport;
-	} else {
-		newport = tuple->dst.u.dccp.port;
-		portptr = &hdr->dccph_dport;
-	}
-
-	oldport = *portptr;
-	*portptr = newport;
-
-	if (hdrsize < sizeof(*hdr))
-		return true;
-
-	l3proto->csum_update(skb, iphdroff, &hdr->dccph_checksum,
-			     tuple, maniptype);
-	inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport,
-				 false);
-	return true;
-}
-
 const struct nf_nat_l4proto nf_nat_l4proto_dccp = {
 	.l4proto		= IPPROTO_DCCP,
-	.manip_pkt		= dccp_manip_pkt,
 };
diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c
index 37a9d347a029..e555cb7a248c 100644
--- a/net/netfilter/nf_nat_proto_sctp.c
+++ b/net/netfilter/nf_nat_proto_sctp.c
@@ -7,53 +7,10 @@
  */
 
 #include <linux/types.h>
-#include <linux/sctp.h>
-#include <net/sctp/checksum.h>
 
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static bool
-sctp_manip_pkt(struct sk_buff *skb,
-	       const struct nf_nat_l3proto *l3proto,
-	       unsigned int iphdroff, unsigned int hdroff,
-	       const struct nf_conntrack_tuple *tuple,
-	       enum nf_nat_manip_type maniptype)
-{
-	struct sctphdr *hdr;
-	int hdrsize = 8;
-
-	/* This could be an inner header returned in imcp packet; in such
-	 * cases we cannot update the checksum field since it is outside
-	 * of the 8 bytes of transport layer headers we are guaranteed.
-	 */
-	if (skb->len >= hdroff + sizeof(*hdr))
-		hdrsize = sizeof(*hdr);
-
-	if (!skb_make_writable(skb, hdroff + hdrsize))
-		return false;
-
-	hdr = (struct sctphdr *)(skb->data + hdroff);
-
-	if (maniptype == NF_NAT_MANIP_SRC) {
-		/* Get rid of src port */
-		hdr->source = tuple->src.u.sctp.port;
-	} else {
-		/* Get rid of dst port */
-		hdr->dest = tuple->dst.u.sctp.port;
-	}
-
-	if (hdrsize < sizeof(*hdr))
-		return true;
-
-	if (skb->ip_summed != CHECKSUM_PARTIAL) {
-		hdr->checksum = sctp_compute_cksum(skb, hdroff);
-		skb->ip_summed = CHECKSUM_NONE;
-	}
-
-	return true;
-}
 
 const struct nf_nat_l4proto nf_nat_l4proto_sctp = {
 	.l4proto		= IPPROTO_SCTP,
-	.manip_pkt		= sctp_manip_pkt,
 };
diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c
index d378b6c31d34..04d2dc100048 100644
--- a/net/netfilter/nf_nat_proto_tcp.c
+++ b/net/netfilter/nf_nat_proto_tcp.c
@@ -18,50 +18,6 @@
 #include <net/netfilter/nf_nat_l4proto.h>
 #include <net/netfilter/nf_nat_core.h>
 
-static bool
-tcp_manip_pkt(struct sk_buff *skb,
-	      const struct nf_nat_l3proto *l3proto,
-	      unsigned int iphdroff, unsigned int hdroff,
-	      const struct nf_conntrack_tuple *tuple,
-	      enum nf_nat_manip_type maniptype)
-{
-	struct tcphdr *hdr;
-	__be16 *portptr, newport, oldport;
-	int hdrsize = 8; /* TCP connection tracking guarantees this much */
-
-	/* this could be a inner header returned in icmp packet; in such
-	   cases we cannot update the checksum field since it is outside of
-	   the 8 bytes of transport layer headers we are guaranteed */
-	if (skb->len >= hdroff + sizeof(struct tcphdr))
-		hdrsize = sizeof(struct tcphdr);
-
-	if (!skb_make_writable(skb, hdroff + hdrsize))
-		return false;
-
-	hdr = (struct tcphdr *)(skb->data + hdroff);
-
-	if (maniptype == NF_NAT_MANIP_SRC) {
-		/* Get rid of src port */
-		newport = tuple->src.u.tcp.port;
-		portptr = &hdr->source;
-	} else {
-		/* Get rid of dst port */
-		newport = tuple->dst.u.tcp.port;
-		portptr = &hdr->dest;
-	}
-
-	oldport = *portptr;
-	*portptr = newport;
-
-	if (hdrsize < sizeof(*hdr))
-		return true;
-
-	l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype);
-	inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, false);
-	return true;
-}
-
 const struct nf_nat_l4proto nf_nat_l4proto_tcp = {
 	.l4proto		= IPPROTO_TCP,
-	.manip_pkt		= tcp_manip_pkt,
 };
diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c
deleted file mode 100644
index 25fc6138fbf7..000000000000
--- a/net/netfilter/nf_nat_proto_udp.c
+++ /dev/null
@@ -1,94 +0,0 @@
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/types.h>
-#include <linux/export.h>
-#include <linux/init.h>
-#include <linux/udp.h>
-
-#include <linux/netfilter.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_core.h>
-#include <net/netfilter/nf_nat_l3proto.h>
-#include <net/netfilter/nf_nat_l4proto.h>
-
-static void
-__udp_manip_pkt(struct sk_buff *skb,
-	        const struct nf_nat_l3proto *l3proto,
-	        unsigned int iphdroff, struct udphdr *hdr,
-	        const struct nf_conntrack_tuple *tuple,
-	        enum nf_nat_manip_type maniptype, bool do_csum)
-{
-	__be16 *portptr, newport;
-
-	if (maniptype == NF_NAT_MANIP_SRC) {
-		/* Get rid of src port */
-		newport = tuple->src.u.udp.port;
-		portptr = &hdr->source;
-	} else {
-		/* Get rid of dst port */
-		newport = tuple->dst.u.udp.port;
-		portptr = &hdr->dest;
-	}
-	if (do_csum) {
-		l3proto->csum_update(skb, iphdroff, &hdr->check,
-				     tuple, maniptype);
-		inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport,
-					 false);
-		if (!hdr->check)
-			hdr->check = CSUM_MANGLED_0;
-	}
-	*portptr = newport;
-}
-
-static bool udp_manip_pkt(struct sk_buff *skb,
-			  const struct nf_nat_l3proto *l3proto,
-			  unsigned int iphdroff, unsigned int hdroff,
-			  const struct nf_conntrack_tuple *tuple,
-			  enum nf_nat_manip_type maniptype)
-{
-	struct udphdr *hdr;
-	bool do_csum;
-
-	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
-		return false;
-
-	hdr = (struct udphdr *)(skb->data + hdroff);
-	do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL;
-
-	__udp_manip_pkt(skb, l3proto, iphdroff, hdr, tuple, maniptype, do_csum);
-	return true;
-}
-
-#ifdef CONFIG_NF_NAT_PROTO_UDPLITE
-static bool udplite_manip_pkt(struct sk_buff *skb,
-			      const struct nf_nat_l3proto *l3proto,
-			      unsigned int iphdroff, unsigned int hdroff,
-			      const struct nf_conntrack_tuple *tuple,
-			      enum nf_nat_manip_type maniptype)
-{
-	struct udphdr *hdr;
-
-	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
-		return false;
-
-	hdr = (struct udphdr *)(skb->data + hdroff);
-	__udp_manip_pkt(skb, l3proto, iphdroff, hdr, tuple, maniptype, true);
-	return true;
-}
-
-const struct nf_nat_l4proto nf_nat_l4proto_udplite = {
-	.l4proto		= IPPROTO_UDPLITE,
-	.manip_pkt		= udplite_manip_pkt,
-};
-#endif /* CONFIG_NF_NAT_PROTO_UDPLITE */
-
-const struct nf_nat_l4proto nf_nat_l4proto_udp = {
-	.l4proto		= IPPROTO_UDP,
-	.manip_pkt		= udp_manip_pkt,
-};
diff --git a/net/netfilter/nf_nat_proto_unknown.c b/net/netfilter/nf_nat_proto_unknown.c
index ba178b02fc1a..7f6201208a32 100644
--- a/net/netfilter/nf_nat_proto_unknown.c
+++ b/net/netfilter/nf_nat_proto_unknown.c
@@ -17,16 +17,5 @@
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_l4proto.h>
 
-static bool
-unknown_manip_pkt(struct sk_buff *skb,
-		  const struct nf_nat_l3proto *l3proto,
-		  unsigned int iphdroff, unsigned int hdroff,
-		  const struct nf_conntrack_tuple *tuple,
-		  enum nf_nat_manip_type maniptype)
-{
-	return true;
-}
-
 const struct nf_nat_l4proto nf_nat_l4proto_unknown = {
-	.manip_pkt		= unknown_manip_pkt,
 };
-- 
cgit v1.2.3


From 5cbabeec1eb758233b35683123de446a57852932 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 13 Dec 2018 16:01:34 +0100
Subject: netfilter: nat: remove nf_nat_l4proto struct

This removes the (now empty) nf_nat_l4proto struct, all its instances
and all the no longer needed runtime (un)register functionality.

nf_nat_need_gre() can be axed as well: the module that calls it (to
load the no-longer-existing nat_gre module) also calls other nat core
functions. GRE nat is now always available if kernel is built with it.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nf_conntrack_proto_gre.h |   2 -
 include/net/netfilter/nf_nat_l3proto.h           |   2 -
 include/net/netfilter/nf_nat_l4proto.h           |  31 -------
 net/ipv4/netfilter/Makefile                      |   5 +-
 net/ipv4/netfilter/nf_nat_l3proto_ipv4.c         |  24 +-----
 net/ipv4/netfilter/nf_nat_proto_gre.c            |  61 -------------
 net/ipv4/netfilter/nf_nat_proto_icmp.c           |  21 -----
 net/ipv6/netfilter/Makefile                      |   2 +-
 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c         |  24 +-----
 net/ipv6/netfilter/nf_nat_proto_icmpv6.c         |  24 ------
 net/netfilter/Makefile                           |   7 +-
 net/netfilter/nf_conntrack_netlink.c             |   1 -
 net/netfilter/nf_nat_core.c                      | 104 +----------------------
 net/netfilter/nf_nat_proto.c                     |  10 ---
 net/netfilter/nf_nat_proto_dccp.c                |  22 -----
 net/netfilter/nf_nat_proto_sctp.c                |  16 ----
 net/netfilter/nf_nat_proto_tcp.c                 |  23 -----
 net/netfilter/nf_nat_proto_unknown.c             |  21 -----
 18 files changed, 10 insertions(+), 390 deletions(-)
 delete mode 100644 net/ipv4/netfilter/nf_nat_proto_gre.c
 delete mode 100644 net/ipv4/netfilter/nf_nat_proto_icmp.c
 delete mode 100644 net/ipv6/netfilter/nf_nat_proto_icmpv6.c
 delete mode 100644 net/netfilter/nf_nat_proto_dccp.c
 delete mode 100644 net/netfilter/nf_nat_proto_sctp.c
 delete mode 100644 net/netfilter/nf_nat_proto_tcp.c
 delete mode 100644 net/netfilter/nf_nat_proto_unknown.c

diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h
index b8d95564bd53..f76efa5f2996 100644
--- a/include/linux/netfilter/nf_conntrack_proto_gre.h
+++ b/include/linux/netfilter/nf_conntrack_proto_gre.h
@@ -28,7 +28,5 @@ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir,
 /* delete keymap entries */
 void nf_ct_gre_keymap_destroy(struct nf_conn *ct);
 
-void nf_nat_need_gre(void);
-
 #endif /* __KERNEL__ */
 #endif /* _CONNTRACK_PROTO_GRE_H */
diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h
index 1ce0980da638..d774ca0c4c5e 100644
--- a/include/net/netfilter/nf_nat_l3proto.h
+++ b/include/net/netfilter/nf_nat_l3proto.h
@@ -2,13 +2,11 @@
 #ifndef _NF_NAT_L3PROTO_H
 #define _NF_NAT_L3PROTO_H
 
-struct nf_nat_l4proto;
 struct nf_nat_l3proto {
 	u8	l3proto;
 
 	bool	(*manip_pkt)(struct sk_buff *skb,
 			     unsigned int iphdroff,
-			     const struct nf_nat_l4proto *l4proto,
 			     const struct nf_conntrack_tuple *target,
 			     enum nf_nat_manip_type maniptype);
 
diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h
index 7b57bd302107..95a4655bd1ad 100644
--- a/include/net/netfilter/nf_nat_l4proto.h
+++ b/include/net/netfilter/nf_nat_l4proto.h
@@ -5,43 +5,12 @@
 #include <net/netfilter/nf_nat.h>
 #include <linux/netfilter/nfnetlink_conntrack.h>
 
-struct nf_nat_range;
 struct nf_nat_l3proto;
 
-struct nf_nat_l4proto {
-	/* Protocol number. */
-	u8 l4proto;
-
-};
-
-/* Protocol registration. */
-int nf_nat_l4proto_register(u8 l3proto, const struct nf_nat_l4proto *l4proto);
-void nf_nat_l4proto_unregister(u8 l3proto,
-			       const struct nf_nat_l4proto *l4proto);
-
-const struct nf_nat_l4proto *__nf_nat_l4proto_find(u8 l3proto, u8 l4proto);
-
 /* Translate a packet to the target according to manip type.  Return on success. */
 bool nf_nat_l4proto_manip_pkt(struct sk_buff *skb,
 			      const struct nf_nat_l3proto *l3proto,
 			      unsigned int iphdroff, unsigned int hdroff,
 			      const struct nf_conntrack_tuple *tuple,
 			      enum nf_nat_manip_type maniptype);
-
-/* Built-in protocols. */
-extern const struct nf_nat_l4proto nf_nat_l4proto_tcp;
-extern const struct nf_nat_l4proto nf_nat_l4proto_udp;
-extern const struct nf_nat_l4proto nf_nat_l4proto_icmp;
-extern const struct nf_nat_l4proto nf_nat_l4proto_icmpv6;
-extern const struct nf_nat_l4proto nf_nat_l4proto_unknown;
-#ifdef CONFIG_NF_NAT_PROTO_DCCP
-extern const struct nf_nat_l4proto nf_nat_l4proto_dccp;
-#endif
-#ifdef CONFIG_NF_NAT_PROTO_SCTP
-extern const struct nf_nat_l4proto nf_nat_l4proto_sctp;
-#endif
-#ifdef CONFIG_NF_NAT_PROTO_UDPLITE
-extern const struct nf_nat_l4proto nf_nat_l4proto_udplite;
-#endif
-
 #endif /*_NF_NAT_L4PROTO_H*/
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 367993adf4d3..fd7122e0e2c9 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the netfilter modules on top of IPv4.
 #
 
-nf_nat_ipv4-y		:= nf_nat_l3proto_ipv4.o nf_nat_proto_icmp.o
+nf_nat_ipv4-y		:= nf_nat_l3proto_ipv4.o
 nf_nat_ipv4-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o
 obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o
 
@@ -28,9 +28,6 @@ nf_nat_snmp_basic-y := nf_nat_snmp_basic.asn1.o nf_nat_snmp_basic_main.o
 $(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic.asn1.h
 obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
 
-# NAT protocols (nf_nat)
-obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
-
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index 65fdb7a74621..2687db015b6f 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -64,7 +64,6 @@ static void nf_nat_ipv4_decode_session(struct sk_buff *skb,
 
 static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb,
 				  unsigned int iphdroff,
-				  const struct nf_nat_l4proto *l4proto,
 				  const struct nf_conntrack_tuple *target,
 				  enum nf_nat_manip_type maniptype)
 {
@@ -171,7 +170,6 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
 	enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);
 	unsigned int hdrlen = ip_hdrlen(skb);
-	const struct nf_nat_l4proto *l4proto;
 	struct nf_conntrack_tuple target;
 	unsigned long statusbit;
 
@@ -202,9 +200,8 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 	if (!(ct->status & statusbit))
 		return 1;
 
-	l4proto = __nf_nat_l4proto_find(NFPROTO_IPV4, inside->ip.protocol);
 	if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp),
-				   l4proto, &ct->tuplehash[!dir].tuple, !manip))
+				   &ct->tuplehash[!dir].tuple, !manip))
 		return 0;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL) {
@@ -218,8 +215,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 
 	/* Change outer to look like the reply to an incoming packet */
 	nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
-	l4proto = __nf_nat_l4proto_find(NFPROTO_IPV4, 0);
-	if (!nf_nat_ipv4_manip_pkt(skb, 0, l4proto, &target, manip))
+	if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip))
 		return 0;
 
 	return 1;
@@ -376,26 +372,12 @@ EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_unregister_fn);
 
 static int __init nf_nat_l3proto_ipv4_init(void)
 {
-	int err;
-
-	err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_icmp);
-	if (err < 0)
-		goto err1;
-	err = nf_nat_l3proto_register(&nf_nat_l3proto_ipv4);
-	if (err < 0)
-		goto err2;
-	return err;
-
-err2:
-	nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_icmp);
-err1:
-	return err;
+	return nf_nat_l3proto_register(&nf_nat_l3proto_ipv4);
 }
 
 static void __exit nf_nat_l3proto_ipv4_exit(void)
 {
 	nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv4);
-	nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_icmp);
 }
 
 MODULE_LICENSE("GPL");
diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c
deleted file mode 100644
index 25849295d537..000000000000
--- a/net/ipv4/netfilter/nf_nat_proto_gre.c
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * nf_nat_proto_gre.c
- *
- * NAT protocol helper module for GRE.
- *
- * GRE is a generic encapsulation protocol, which is generally not very
- * suited for NAT, as it has no protocol-specific part as port numbers.
- *
- * It has an optional key field, which may help us distinguishing two
- * connections between the same two hosts.
- *
- * GRE is defined in RFC 1701 and RFC 1702, as well as RFC 2784
- *
- * PPTP is built on top of a modified version of GRE, and has a mandatory
- * field called "CallID", which serves us for the same purpose as the key
- * field in plain GRE.
- *
- * Documentation about PPTP can be found in RFC 2637
- *
- * (C) 2000-2005 by Harald Welte <laforge@gnumonks.org>
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- *
- * (C) 2006-2012 Patrick McHardy <kaber@trash.net>
- *
- */
-
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/ip.h>
-
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_l4proto.h>
-#include <linux/netfilter/nf_conntrack_proto_gre.h>
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>");
-MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE");
-
-static const struct nf_nat_l4proto gre = {
-	.l4proto		= IPPROTO_GRE,
-};
-
-static int __init nf_nat_proto_gre_init(void)
-{
-	return nf_nat_l4proto_register(NFPROTO_IPV4, &gre);
-}
-
-static void __exit nf_nat_proto_gre_fini(void)
-{
-	nf_nat_l4proto_unregister(NFPROTO_IPV4, &gre);
-}
-
-module_init(nf_nat_proto_gre_init);
-module_exit(nf_nat_proto_gre_fini);
-
-void nf_nat_need_gre(void)
-{
-	return;
-}
-EXPORT_SYMBOL_GPL(nf_nat_need_gre);
diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c
deleted file mode 100644
index c2b7fd1a997b..000000000000
--- a/net/ipv4/netfilter/nf_nat_proto_icmp.c
+++ /dev/null
@@ -1,21 +0,0 @@
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/export.h>
-#include <linux/ip.h>
-
-#include <linux/netfilter.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_core.h>
-#include <net/netfilter/nf_nat_l4proto.h>
-
-const struct nf_nat_l4proto nf_nat_l4proto_icmp = {
-	.l4proto		= IPPROTO_ICMP,
-};
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 200c0c235565..9ea43d5256e0 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -11,7 +11,7 @@ obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o
 obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o
 obj-$(CONFIG_IP6_NF_NAT) += ip6table_nat.o
 
-nf_nat_ipv6-y		:= nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o
+nf_nat_ipv6-y		:= nf_nat_l3proto_ipv6.o
 nf_nat_ipv6-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o
 obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
 
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index 6ff1375799c7..23022447eb49 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -63,7 +63,6 @@ static void nf_nat_ipv6_decode_session(struct sk_buff *skb,
 
 static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
 				  unsigned int iphdroff,
-				  const struct nf_nat_l4proto *l4proto,
 				  const struct nf_conntrack_tuple *target,
 				  enum nf_nat_manip_type maniptype)
 {
@@ -181,7 +180,6 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
 	} *inside;
 	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
 	enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);
-	const struct nf_nat_l4proto *l4proto;
 	struct nf_conntrack_tuple target;
 	unsigned long statusbit;
 
@@ -212,9 +210,8 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
 	if (!(ct->status & statusbit))
 		return 1;
 
-	l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, inside->ip6.nexthdr);
 	if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6),
-				   l4proto, &ct->tuplehash[!dir].tuple, !manip))
+				   &ct->tuplehash[!dir].tuple, !manip))
 		return 0;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL) {
@@ -229,8 +226,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
 	}
 
 	nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
-	l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, IPPROTO_ICMPV6);
-	if (!nf_nat_ipv6_manip_pkt(skb, 0, l4proto, &target, manip))
+	if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip))
 		return 0;
 
 	return 1;
@@ -400,26 +396,12 @@ EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv6_unregister_fn);
 
 static int __init nf_nat_l3proto_ipv6_init(void)
 {
-	int err;
-
-	err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6);
-	if (err < 0)
-		goto err1;
-	err = nf_nat_l3proto_register(&nf_nat_l3proto_ipv6);
-	if (err < 0)
-		goto err2;
-	return err;
-
-err2:
-	nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6);
-err1:
-	return err;
+	return nf_nat_l3proto_register(&nf_nat_l3proto_ipv6);
 }
 
 static void __exit nf_nat_l3proto_ipv6_exit(void)
 {
 	nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv6);
-	nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6);
 }
 
 MODULE_LICENSE("GPL");
diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
deleted file mode 100644
index fcbe7e750420..000000000000
--- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * Copyright (c) 2011 Patrick Mchardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Based on Rusty Russell's IPv4 ICMP NAT code. Development of IPv6
- * NAT funded by Astaro.
- */
-
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/icmpv6.h>
-
-#include <linux/netfilter.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_core.h>
-#include <net/netfilter/nf_nat_l3proto.h>
-#include <net/netfilter/nf_nat_l4proto.h>
-
-const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = {
-	.l4proto		= IPPROTO_ICMPV6,
-};
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index ed4a912c5484..1ae65a314d7a 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -47,12 +47,7 @@ obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o
 obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
 obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o
 
-nf_nat-y	:= nf_nat_core.o nf_nat_proto_unknown.o \
-		   nf_nat_proto.o nf_nat_proto_tcp.o nf_nat_helper.o
-
-# NAT protocols (nf_nat)
-nf_nat-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o
-nf_nat-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o
+nf_nat-y	:= nf_nat_core.o nf_nat_proto.o nf_nat_helper.o
 
 # generic transport layer logging
 obj-$(CONFIG_NF_LOG_COMMON) += nf_log_common.o
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 4f54c4355d33..1213beb5a714 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -47,7 +47,6 @@
 #include <net/netfilter/nf_conntrack_synproxy.h>
 #ifdef CONFIG_NF_NAT_NEEDED
 #include <net/netfilter/nf_nat_core.h>
-#include <net/netfilter/nf_nat_l4proto.h>
 #include <net/netfilter/nf_nat_helper.h>
 #endif
 
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 2d7fac80341b..9935b66427e6 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -23,7 +23,6 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_l3proto.h>
-#include <net/netfilter/nf_nat_l4proto.h>
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_helper.h>
 #include <net/netfilter/nf_conntrack_helper.h>
@@ -38,8 +37,6 @@ static spinlock_t nf_nat_locks[CONNTRACK_LOCKS];
 static DEFINE_MUTEX(nf_nat_proto_mutex);
 static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO]
 						__read_mostly;
-static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO]
-						__read_mostly;
 static unsigned int nat_net_id __read_mostly;
 
 static struct hlist_head *nf_nat_bysource __read_mostly;
@@ -67,13 +64,6 @@ __nf_nat_l3proto_find(u8 family)
 	return rcu_dereference(nf_nat_l3protos[family]);
 }
 
-inline const struct nf_nat_l4proto *
-__nf_nat_l4proto_find(u8 family, u8 protonum)
-{
-	return rcu_dereference(nf_nat_l4protos[family][protonum]);
-}
-EXPORT_SYMBOL_GPL(__nf_nat_l4proto_find);
-
 #ifdef CONFIG_XFRM
 static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl)
 {
@@ -646,16 +636,13 @@ static unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct,
 				     enum ip_conntrack_dir dir)
 {
 	const struct nf_nat_l3proto *l3proto;
-	const struct nf_nat_l4proto *l4proto;
 	struct nf_conntrack_tuple target;
 
 	/* We are aiming to look like inverse of other direction. */
 	nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
 
 	l3proto = __nf_nat_l3proto_find(target.src.l3num);
-	l4proto = __nf_nat_l4proto_find(target.src.l3num,
-					target.dst.protonum);
-	if (!l3proto->manip_pkt(skb, 0, l4proto, &target, mtype))
+	if (!l3proto->manip_pkt(skb, 0, &target, mtype))
 		return NF_DROP;
 
 	return NF_ACCEPT;
@@ -811,16 +798,6 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
 	return 0;
 }
 
-static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
-{
-	struct nf_nat_proto_clean clean = {
-		.l3proto = l3proto,
-		.l4proto = l4proto,
-	};
-
-	nf_ct_iterate_destroy(nf_nat_proto_remove, &clean);
-}
-
 static void nf_nat_l3proto_clean(u8 l3proto)
 {
 	struct nf_nat_proto_clean clean = {
@@ -830,82 +807,8 @@ static void nf_nat_l3proto_clean(u8 l3proto)
 	nf_ct_iterate_destroy(nf_nat_proto_remove, &clean);
 }
 
-/* Protocol registration. */
-int nf_nat_l4proto_register(u8 l3proto, const struct nf_nat_l4proto *l4proto)
-{
-	const struct nf_nat_l4proto **l4protos;
-	unsigned int i;
-	int ret = 0;
-
-	mutex_lock(&nf_nat_proto_mutex);
-	if (nf_nat_l4protos[l3proto] == NULL) {
-		l4protos = kmalloc_array(IPPROTO_MAX,
-					 sizeof(struct nf_nat_l4proto *),
-					 GFP_KERNEL);
-		if (l4protos == NULL) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		for (i = 0; i < IPPROTO_MAX; i++)
-			RCU_INIT_POINTER(l4protos[i], &nf_nat_l4proto_unknown);
-
-		/* Before making proto_array visible to lockless readers,
-		 * we must make sure its content is committed to memory.
-		 */
-		smp_wmb();
-
-		nf_nat_l4protos[l3proto] = l4protos;
-	}
-
-	if (rcu_dereference_protected(
-			nf_nat_l4protos[l3proto][l4proto->l4proto],
-			lockdep_is_held(&nf_nat_proto_mutex)
-			) != &nf_nat_l4proto_unknown) {
-		ret = -EBUSY;
-		goto out;
-	}
-	RCU_INIT_POINTER(nf_nat_l4protos[l3proto][l4proto->l4proto], l4proto);
- out:
-	mutex_unlock(&nf_nat_proto_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(nf_nat_l4proto_register);
-
-/* No one stores the protocol anywhere; simply delete it. */
-void nf_nat_l4proto_unregister(u8 l3proto, const struct nf_nat_l4proto *l4proto)
-{
-	mutex_lock(&nf_nat_proto_mutex);
-	RCU_INIT_POINTER(nf_nat_l4protos[l3proto][l4proto->l4proto],
-			 &nf_nat_l4proto_unknown);
-	mutex_unlock(&nf_nat_proto_mutex);
-	synchronize_rcu();
-
-	nf_nat_l4proto_clean(l3proto, l4proto->l4proto);
-}
-EXPORT_SYMBOL_GPL(nf_nat_l4proto_unregister);
-
 int nf_nat_l3proto_register(const struct nf_nat_l3proto *l3proto)
 {
-	mutex_lock(&nf_nat_proto_mutex);
-	RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_TCP],
-			 &nf_nat_l4proto_tcp);
-	RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_UDP],
-			 &nf_nat_l4proto_udp);
-#ifdef CONFIG_NF_NAT_PROTO_DCCP
-	RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_DCCP],
-			 &nf_nat_l4proto_dccp);
-#endif
-#ifdef CONFIG_NF_NAT_PROTO_SCTP
-	RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_SCTP],
-			 &nf_nat_l4proto_sctp);
-#endif
-#ifdef CONFIG_NF_NAT_PROTO_UDPLITE
-	RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_UDPLITE],
-			 &nf_nat_l4proto_udplite);
-#endif
-	mutex_unlock(&nf_nat_proto_mutex);
-
 	RCU_INIT_POINTER(nf_nat_l3protos[l3proto->l3proto], l3proto);
 	return 0;
 }
@@ -1236,7 +1139,6 @@ static int __init nf_nat_init(void)
 static void __exit nf_nat_cleanup(void)
 {
 	struct nf_nat_proto_clean clean = {};
-	unsigned int i;
 
 	nf_ct_iterate_destroy(nf_nat_proto_clean, &clean);
 
@@ -1244,10 +1146,6 @@ static void __exit nf_nat_cleanup(void)
 	nf_ct_helper_expectfn_unregister(&follow_master_nat);
 	RCU_INIT_POINTER(nf_nat_hook, NULL);
 
-	synchronize_rcu();
-
-	for (i = 0; i < NFPROTO_NUMPROTO; i++)
-		kfree(nf_nat_l4protos[i]);
 	synchronize_net();
 	kvfree(nf_nat_bysource);
 	unregister_pernet_subsys(&nat_net_ops);
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 1042706827cb..f83bf9d8c9f5 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -341,13 +341,3 @@ bool nf_nat_l4proto_manip_pkt(struct sk_buff *skb,
 	return true;
 }
 EXPORT_SYMBOL_GPL(nf_nat_l4proto_manip_pkt);
-
-#ifdef CONFIG_NF_NAT_PROTO_UDPLITE
-const struct nf_nat_l4proto nf_nat_l4proto_udplite = {
-	.l4proto		= IPPROTO_UDPLITE,
-};
-#endif /* CONFIG_NF_NAT_PROTO_UDPLITE */
-
-const struct nf_nat_l4proto nf_nat_l4proto_udp = {
-	.l4proto		= IPPROTO_UDP,
-};
diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c
deleted file mode 100644
index dace808d4a23..000000000000
--- a/net/netfilter/nf_nat_proto_dccp.c
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * DCCP NAT protocol helper
- *
- * Copyright (c) 2005, 2006, 2008 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/skbuff.h>
-
-#include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_l3proto.h>
-#include <net/netfilter/nf_nat_l4proto.h>
-
-const struct nf_nat_l4proto nf_nat_l4proto_dccp = {
-	.l4proto		= IPPROTO_DCCP,
-};
diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c
deleted file mode 100644
index e555cb7a248c..000000000000
--- a/net/netfilter/nf_nat_proto_sctp.c
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/types.h>
-
-#include <net/netfilter/nf_nat_l4proto.h>
-
-
-const struct nf_nat_l4proto nf_nat_l4proto_sctp = {
-	.l4proto		= IPPROTO_SCTP,
-};
diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c
deleted file mode 100644
index 04d2dc100048..000000000000
--- a/net/netfilter/nf_nat_proto_tcp.c
+++ /dev/null
@@ -1,23 +0,0 @@
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/export.h>
-#include <linux/tcp.h>
-
-#include <linux/netfilter.h>
-#include <linux/netfilter/nfnetlink_conntrack.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_l3proto.h>
-#include <net/netfilter/nf_nat_l4proto.h>
-#include <net/netfilter/nf_nat_core.h>
-
-const struct nf_nat_l4proto nf_nat_l4proto_tcp = {
-	.l4proto		= IPPROTO_TCP,
-};
diff --git a/net/netfilter/nf_nat_proto_unknown.c b/net/netfilter/nf_nat_proto_unknown.c
deleted file mode 100644
index 7f6201208a32..000000000000
--- a/net/netfilter/nf_nat_proto_unknown.c
+++ /dev/null
@@ -1,21 +0,0 @@
-/* The "unknown" protocol.  This is what is used for protocols we
- * don't understand.  It's returned by ip_ct_find_proto().
- */
-
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/types.h>
-#include <linux/init.h>
-
-#include <linux/netfilter.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_l4proto.h>
-
-const struct nf_nat_l4proto nf_nat_l4proto_unknown = {
-};
-- 
cgit v1.2.3


From 8294059931448aa1ca112615bdffa3eab552c382 Mon Sep 17 00:00:00 2001
From: Alin Nastac <alin.nastac@gmail.com>
Date: Thu, 13 Dec 2018 11:10:37 +0100
Subject: netfilter: nf_nat_sip: fix RTP/RTCP source port translations

Each media stream negotiation between 2 SIP peers will trigger creation
of 4 different expectations (2 RTP and 2 RTCP):
 - INVITE will create expectations for the media packets sent by the
   called peer
 - reply to the INVITE will create expectations for media packets sent
   by the caller

The dport used by these expectations usually match the ones selected
by the SIP peers, but they might get translated due to conflicts with
another expectation. When such event occur, it is important to do
this translation in both directions, dport translation on the receiving
path and sport translation on the sending path.

This commit fixes the sport translation when the peer requiring it is
also the one that starts the media stream. In this scenario, first media
stream packet is forwarded from LAN to WAN and will rely on
nf_nat_sip_expected() to do the necessary sport translation. However, the
expectation matched by this packet does not contain the necessary information
for doing SNAT, this data being stored in the paired expectation created by
the sender's SIP message (INVITE or reply to it).

Signed-off-by: Alin Nastac <alin.nastac@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_nat_sip.c | 39 +++++++++++++++++++++++++++++++++++----
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c
index 1f3086074981..aa1be643d7a0 100644
--- a/net/netfilter/nf_nat_sip.c
+++ b/net/netfilter/nf_nat_sip.c
@@ -18,6 +18,7 @@
 
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_helper.h>
+#include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
@@ -316,6 +317,9 @@ static void nf_nat_sip_seq_adjust(struct sk_buff *skb, unsigned int protoff,
 static void nf_nat_sip_expected(struct nf_conn *ct,
 				struct nf_conntrack_expect *exp)
 {
+	struct nf_conn_help *help = nfct_help(ct->master);
+	struct nf_conntrack_expect *pair_exp;
+	int range_set_for_snat = 0;
 	struct nf_nat_range2 range;
 
 	/* This must be a fresh one. */
@@ -327,15 +331,42 @@ static void nf_nat_sip_expected(struct nf_conn *ct,
 	range.min_addr = range.max_addr = exp->saved_addr;
 	nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST);
 
-	/* Change src to where master sends to, but only if the connection
-	 * actually came from the same source. */
-	if (nf_inet_addr_cmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3,
+	/* Do media streams SRC manip according with the parameters
+	 * found in the paired expectation.
+	 */
+	if (exp->class != SIP_EXPECT_SIGNALLING) {
+		spin_lock_bh(&nf_conntrack_expect_lock);
+		hlist_for_each_entry(pair_exp, &help->expectations, lnode) {
+			if (pair_exp->tuple.src.l3num == nf_ct_l3num(ct) &&
+			    pair_exp->tuple.dst.protonum == ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum &&
+			    nf_inet_addr_cmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3, &pair_exp->saved_addr) &&
+			    ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.all == pair_exp->saved_proto.all) {
+				range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
+				range.min_proto.all = range.max_proto.all = pair_exp->tuple.dst.u.all;
+				range.min_addr = range.max_addr = pair_exp->tuple.dst.u3;
+				range_set_for_snat = 1;
+				break;
+			}
+		}
+		spin_unlock_bh(&nf_conntrack_expect_lock);
+	}
+
+	/* When no paired expectation has been found, change src to
+	 * where master sends to, but only if the connection actually came
+	 * from the same source.
+	 */
+	if (!range_set_for_snat &&
+	    nf_inet_addr_cmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3,
 			     &ct->master->tuplehash[exp->dir].tuple.src.u3)) {
 		range.flags = NF_NAT_RANGE_MAP_IPS;
 		range.min_addr = range.max_addr
 			= ct->master->tuplehash[!exp->dir].tuple.dst.u3;
-		nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
+		range_set_for_snat = 1;
 	}
+
+	/* Perform SRC manip. */
+	if (range_set_for_snat)
+		nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
 }
 
 static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff,
-- 
cgit v1.2.3


From 241faeceb849cb02c6439ecb2a08f14bf409dd30 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Wed, 12 Dec 2018 19:29:07 +0100
Subject: netfilter: nf_tables: Speed up selective rule dumps

If just a table name was given, nf_tables_dump_rules() continued over
the list of tables even after a match was found. The simple fix is to
exit the loop if it reached the bottom and ctx->table was not NULL.

When iterating over the table's chains, the same problem as above
existed. But worse than that, if a chain name was given the hash table
wasn't used to find the corresponding chain. Fix this by introducing a
helper function iterating over a chain's rules (and taking care of the
cb->args handling), then introduce a shortcut to it if a chain name was
given.

Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 90 +++++++++++++++++++++++++++++--------------
 1 file changed, 62 insertions(+), 28 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 42487d01a3ed..200751a49745 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2291,15 +2291,52 @@ struct nft_rule_dump_ctx {
 	char *chain;
 };
 
+static int __nf_tables_dump_rules(struct sk_buff *skb,
+				  unsigned int *idx,
+				  struct netlink_callback *cb,
+				  const struct nft_table *table,
+				  const struct nft_chain *chain)
+{
+	struct net *net = sock_net(skb->sk);
+	unsigned int s_idx = cb->args[0];
+	const struct nft_rule *rule;
+	int rc = 1;
+
+	list_for_each_entry_rcu(rule, &chain->rules, list) {
+		if (!nft_is_active(net, rule))
+			goto cont;
+		if (*idx < s_idx)
+			goto cont;
+		if (*idx > s_idx) {
+			memset(&cb->args[1], 0,
+					sizeof(cb->args) - sizeof(cb->args[0]));
+		}
+		if (nf_tables_fill_rule_info(skb, net, NETLINK_CB(cb->skb).portid,
+					cb->nlh->nlmsg_seq,
+					NFT_MSG_NEWRULE,
+					NLM_F_MULTI | NLM_F_APPEND,
+					table->family,
+					table, chain, rule) < 0)
+			goto out_unfinished;
+
+		nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+cont:
+		(*idx)++;
+	}
+	rc = 0;
+out_unfinished:
+	cb->args[0] = *idx;
+	return rc;
+}
+
 static int nf_tables_dump_rules(struct sk_buff *skb,
 				struct netlink_callback *cb)
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
 	const struct nft_rule_dump_ctx *ctx = cb->data;
-	const struct nft_table *table;
+	struct nft_table *table;
 	const struct nft_chain *chain;
-	const struct nft_rule *rule;
-	unsigned int idx = 0, s_idx = cb->args[0];
+	unsigned int idx = 0;
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 
@@ -2313,37 +2350,34 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 		if (ctx && ctx->table && strcmp(ctx->table, table->name) != 0)
 			continue;
 
-		list_for_each_entry_rcu(chain, &table->chains, list) {
-			if (ctx && ctx->chain &&
-			    strcmp(ctx->chain, chain->name) != 0)
-				continue;
+		if (ctx && ctx->chain) {
+			struct rhlist_head *list, *tmp;
 
-			list_for_each_entry_rcu(rule, &chain->rules, list) {
-				if (!nft_is_active(net, rule))
-					goto cont;
-				if (idx < s_idx)
-					goto cont;
-				if (idx > s_idx)
-					memset(&cb->args[1], 0,
-					       sizeof(cb->args) - sizeof(cb->args[0]));
-				if (nf_tables_fill_rule_info(skb, net, NETLINK_CB(cb->skb).portid,
-							      cb->nlh->nlmsg_seq,
-							      NFT_MSG_NEWRULE,
-							      NLM_F_MULTI | NLM_F_APPEND,
-							      table->family,
-							      table, chain, rule) < 0)
-					goto done;
-
-				nl_dump_check_consistent(cb, nlmsg_hdr(skb));
-cont:
-				idx++;
+			list = rhltable_lookup(&table->chains_ht, ctx->chain,
+					       nft_chain_ht_params);
+			if (!list)
+				goto done;
+
+			rhl_for_each_entry_rcu(chain, tmp, list, rhlhead) {
+				if (!nft_is_active(net, chain))
+					continue;
+				__nf_tables_dump_rules(skb, &idx,
+						       cb, table, chain);
+				break;
 			}
+			goto done;
 		}
+
+		list_for_each_entry_rcu(chain, &table->chains, list) {
+			if (__nf_tables_dump_rules(skb, &idx, cb, table, chain))
+				goto done;
+		}
+
+		if (ctx && ctx->table)
+			break;
 	}
 done:
 	rcu_read_unlock();
-
-	cb->args[0] = idx;
 	return skb->len;
 }
 
-- 
cgit v1.2.3


From f97be3ab044cf6dd342fed7668c977ba07a7cd95 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 15 Dec 2018 22:13:50 -0800
Subject: bpf: btf: refactor btf_int_bits_seq_show()

Refactor function btf_int_bits_seq_show() by creating
function btf_bitfield_seq_show() which has no dependence
on btf and btf_type. The function btf_bitfield_seq_show()
will be in later patch to directly dump bitfield member values.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/btf.c | 35 +++++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 14 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 8fa0bf1c33fd..72caa799e82f 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1068,26 +1068,16 @@ static void btf_int_log(struct btf_verifier_env *env,
 			 btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
 }
 
-static void btf_int_bits_seq_show(const struct btf *btf,
-				  const struct btf_type *t,
-				  void *data, u8 bits_offset,
-				  struct seq_file *m)
+static void btf_bitfield_seq_show(void *data, u8 bits_offset,
+				  u8 nr_bits, struct seq_file *m)
 {
 	u16 left_shift_bits, right_shift_bits;
-	u32 int_data = btf_type_int(t);
-	u8 nr_bits = BTF_INT_BITS(int_data);
-	u8 total_bits_offset;
 	u8 nr_copy_bytes;
 	u8 nr_copy_bits;
 	u64 print_num;
 
-	/*
-	 * bits_offset is at most 7.
-	 * BTF_INT_OFFSET() cannot exceed 64 bits.
-	 */
-	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
-	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
-	bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
+	data += BITS_ROUNDDOWN_BYTES(bits_offset);
+	bits_offset = BITS_PER_BYTE_MASKED(bits_offset);
 	nr_copy_bits = nr_bits + bits_offset;
 	nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
 
@@ -1107,6 +1097,23 @@ static void btf_int_bits_seq_show(const struct btf *btf,
 	seq_printf(m, "0x%llx", print_num);
 }
 
+static void btf_int_bits_seq_show(const struct btf *btf,
+				  const struct btf_type *t,
+				  void *data, u8 bits_offset,
+				  struct seq_file *m)
+{
+	u32 int_data = btf_type_int(t);
+	u8 nr_bits = BTF_INT_BITS(int_data);
+	u8 total_bits_offset;
+
+	/*
+	 * bits_offset is at most 7.
+	 * BTF_INT_OFFSET() cannot exceed 64 bits.
+	 */
+	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
+	btf_bitfield_seq_show(data, total_bits_offset, nr_bits, m);
+}
+
 static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
 			     u32 type_id, void *data, u8 bits_offset,
 			     struct seq_file *m)
-- 
cgit v1.2.3


From 9d5f9f701b1891466fb3dbb1806ad97716f95cc3 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 15 Dec 2018 22:13:51 -0800
Subject: bpf: btf: fix struct/union/fwd types with kind_flag

This patch fixed two issues with BTF. One is related to
struct/union bitfield encoding and the other is related to
forward type.

Issue #1 and solution:

======================

Current btf encoding of bitfield follows what pahole generates.
For each bitfield, pahole will duplicate the type chain and
put the bitfield size at the final int or enum type.
Since the BTF enum type cannot encode bit size,
pahole workarounds the issue by generating
an int type whenever the enum bit size is not 32.

For example,
  -bash-4.4$ cat t.c
  typedef int ___int;
  enum A { A1, A2, A3 };
  struct t {
    int a[5];
    ___int b:4;
    volatile enum A c:4;
  } g;
  -bash-4.4$ gcc -c -O2 -g t.c
The current kernel supports the following BTF encoding:
  $ pahole -JV t.o
  [1] TYPEDEF ___int type_id=2
  [2] INT int size=4 bit_offset=0 nr_bits=32 encoding=SIGNED
  [3] ENUM A size=4 vlen=3
        A1 val=0
        A2 val=1
        A3 val=2
  [4] STRUCT t size=24 vlen=3
        a type_id=5 bits_offset=0
        b type_id=9 bits_offset=160
        c type_id=11 bits_offset=164
  [5] ARRAY (anon) type_id=2 index_type_id=2 nr_elems=5
  [6] INT sizetype size=8 bit_offset=0 nr_bits=64 encoding=(none)
  [7] VOLATILE (anon) type_id=3
  [8] INT int size=1 bit_offset=0 nr_bits=4 encoding=(none)
  [9] TYPEDEF ___int type_id=8
  [10] INT (anon) size=1 bit_offset=0 nr_bits=4 encoding=SIGNED
  [11] VOLATILE (anon) type_id=10

Two issues are in the above:
  . by changing enum type to int, we lost the original
    type information and this will not be ideal later
    when we try to convert BTF to a header file.
  . the type duplication for bitfields will cause
    BTF bloat. Duplicated types cannot be deduplicated
    later if the bitfield size is different.

To fix this issue, this patch implemented a compatible
change for BTF struct type encoding:
  . the bit 31 of struct_type->info, previously reserved,
    now is used to indicate whether bitfield_size is
    encoded in btf_member or not.
  . if bit 31 of struct_type->info is set,
    btf_member->offset will encode like:
      bit 0 - 23: bit offset
      bit 24 - 31: bitfield size
    if bit 31 is not set, the old behavior is preserved:
      bit 0 - 31: bit offset

So if the struct contains a bit field, the maximum bit offset
will be reduced to (2^24 - 1) instead of MAX_UINT. The maximum
bitfield size will be 256 which is enough for today as maximum
bitfield in compiler can be 128 where int128 type is supported.

This kernel patch intends to support the new BTF encoding:
  $ pahole -JV t.o
  [1] TYPEDEF ___int type_id=2
  [2] INT int size=4 bit_offset=0 nr_bits=32 encoding=SIGNED
  [3] ENUM A size=4 vlen=3
        A1 val=0
        A2 val=1
        A3 val=2
  [4] STRUCT t kind_flag=1 size=24 vlen=3
        a type_id=5 bitfield_size=0 bits_offset=0
        b type_id=1 bitfield_size=4 bits_offset=160
        c type_id=7 bitfield_size=4 bits_offset=164
  [5] ARRAY (anon) type_id=2 index_type_id=2 nr_elems=5
  [6] INT sizetype size=8 bit_offset=0 nr_bits=64 encoding=(none)
  [7] VOLATILE (anon) type_id=3

Issue #2 and solution:
======================

Current forward type in BTF does not specify whether the original
type is struct or union. This will not work for type pretty print
and BTF-to-header-file conversion as struct/union must be specified.
  $ cat tt.c
  struct t;
  union u;
  int foo(struct t *t, union u *u) { return 0; }
  $ gcc -c -g -O2 tt.c
  $ pahole -JV tt.o
  [1] INT int size=4 bit_offset=0 nr_bits=32 encoding=SIGNED
  [2] FWD t type_id=0
  [3] PTR (anon) type_id=2
  [4] FWD u type_id=0
  [5] PTR (anon) type_id=4

To fix this issue, similar to issue #1, type->info bit 31
is used. If the bit is set, it is union type. Otherwise, it is
a struct type.

  $ pahole -JV tt.o
  [1] INT int size=4 bit_offset=0 nr_bits=32 encoding=SIGNED
  [2] FWD t kind_flag=0 type_id=0
  [3] PTR (anon) kind_flag=0 type_id=2
  [4] FWD u kind_flag=1 type_id=0
  [5] PTR (anon) kind_flag=0 type_id=4

Pahole/LLVM change:
===================

The new kind_flag functionality has been implemented in pahole
and llvm:
  https://github.com/yonghong-song/pahole/tree/bitfield
  https://github.com/yonghong-song/llvm/tree/bitfield

Note that pahole hasn't implemented func/func_proto kind
and .BTF.ext. So to print function signature with bpftool,
the llvm compiler should be used.

Fixes: 69b693f0aefa ("bpf: btf: Introduce BPF Type Format (BTF)")
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/btf.h |  20 +++-
 kernel/bpf/btf.c         | 280 +++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 278 insertions(+), 22 deletions(-)

diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
index 14f66948fc95..7b7475ef2f17 100644
--- a/include/uapi/linux/btf.h
+++ b/include/uapi/linux/btf.h
@@ -34,7 +34,9 @@ struct btf_type {
 	 * bits  0-15: vlen (e.g. # of struct's members)
 	 * bits 16-23: unused
 	 * bits 24-27: kind (e.g. int, ptr, array...etc)
-	 * bits 28-31: unused
+	 * bits 28-30: unused
+	 * bit     31: kind_flag, currently used by
+	 *             struct, union and fwd
 	 */
 	__u32 info;
 	/* "size" is used by INT, ENUM, STRUCT and UNION.
@@ -52,6 +54,7 @@ struct btf_type {
 
 #define BTF_INFO_KIND(info)	(((info) >> 24) & 0x0f)
 #define BTF_INFO_VLEN(info)	((info) & 0xffff)
+#define BTF_INFO_KFLAG(info)	((info) >> 31)
 
 #define BTF_KIND_UNKN		0	/* Unknown	*/
 #define BTF_KIND_INT		1	/* Integer	*/
@@ -110,9 +113,22 @@ struct btf_array {
 struct btf_member {
 	__u32	name_off;
 	__u32	type;
-	__u32	offset;	/* offset in bits */
+	/* If the type info kind_flag is set, the btf_member offset
+	 * contains both member bitfield size and bit offset. The
+	 * bitfield size is set for bitfield members. If the type
+	 * info kind_flag is not set, the offset contains only bit
+	 * offset.
+	 */
+	__u32	offset;
 };
 
+/* If the struct/union type info kind_flag is set, the
+ * following two macros are used to access bitfield_size
+ * and bit_offset from btf_member.offset.
+ */
+#define BTF_MEMBER_BITFIELD_SIZE(val)	((val) >> 24)
+#define BTF_MEMBER_BIT_OFFSET(val)	((val) & 0xffffff)
+
 /* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
  * The exact number of btf_param is stored in the vlen (of the
  * info in "struct btf_type").
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 72caa799e82f..93b6905e3a9b 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -164,7 +164,7 @@
 #define BITS_ROUNDUP_BYTES(bits) \
 	(BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits))
 
-#define BTF_INFO_MASK 0x0f00ffff
+#define BTF_INFO_MASK 0x8f00ffff
 #define BTF_INT_MASK 0x0fffffff
 #define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE)
 #define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET)
@@ -274,6 +274,10 @@ struct btf_kind_operations {
 			    const struct btf_type *struct_type,
 			    const struct btf_member *member,
 			    const struct btf_type *member_type);
+	int (*check_kflag_member)(struct btf_verifier_env *env,
+				  const struct btf_type *struct_type,
+				  const struct btf_member *member,
+				  const struct btf_type *member_type);
 	void (*log_details)(struct btf_verifier_env *env,
 			    const struct btf_type *t);
 	void (*seq_show)(const struct btf *btf, const struct btf_type *t,
@@ -419,6 +423,25 @@ static u16 btf_type_vlen(const struct btf_type *t)
 	return BTF_INFO_VLEN(t->info);
 }
 
+static bool btf_type_kflag(const struct btf_type *t)
+{
+	return BTF_INFO_KFLAG(t->info);
+}
+
+static u32 btf_member_bit_offset(const struct btf_type *struct_type,
+			     const struct btf_member *member)
+{
+	return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset)
+					   : member->offset;
+}
+
+static u32 btf_member_bitfield_size(const struct btf_type *struct_type,
+				    const struct btf_member *member)
+{
+	return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset)
+					   : 0;
+}
+
 static u32 btf_type_int(const struct btf_type *t)
 {
 	return *(u32 *)(t + 1);
@@ -627,9 +650,17 @@ static void btf_verifier_log_member(struct btf_verifier_env *env,
 	if (env->phase != CHECK_META)
 		btf_verifier_log_type(env, struct_type, NULL);
 
-	__btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
-			   __btf_name_by_offset(btf, member->name_off),
-			   member->type, member->offset);
+	if (btf_type_kflag(struct_type))
+		__btf_verifier_log(log,
+				   "\t%s type_id=%u bitfield_size=%u bits_offset=%u",
+				   __btf_name_by_offset(btf, member->name_off),
+				   member->type,
+				   BTF_MEMBER_BITFIELD_SIZE(member->offset),
+				   BTF_MEMBER_BIT_OFFSET(member->offset));
+	else
+		__btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
+				   __btf_name_by_offset(btf, member->name_off),
+				   member->type, member->offset);
 
 	if (fmt && *fmt) {
 		__btf_verifier_log(log, " ");
@@ -945,6 +976,38 @@ static int btf_df_check_member(struct btf_verifier_env *env,
 	return -EINVAL;
 }
 
+static int btf_df_check_kflag_member(struct btf_verifier_env *env,
+				     const struct btf_type *struct_type,
+				     const struct btf_member *member,
+				     const struct btf_type *member_type)
+{
+	btf_verifier_log_basic(env, struct_type,
+			       "Unsupported check_kflag_member");
+	return -EINVAL;
+}
+
+/* Used for ptr, array and struct/union type members.
+ * int, enum and modifier types have their specific callback functions.
+ */
+static int btf_generic_check_kflag_member(struct btf_verifier_env *env,
+					  const struct btf_type *struct_type,
+					  const struct btf_member *member,
+					  const struct btf_type *member_type)
+{
+	if (BTF_MEMBER_BITFIELD_SIZE(member->offset)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Invalid member bitfield_size");
+		return -EINVAL;
+	}
+
+	/* bitfield size is 0, so member->offset represents bit offset only.
+	 * It is safe to call non kflag check_member variants.
+	 */
+	return btf_type_ops(member_type)->check_member(env, struct_type,
+						       member,
+						       member_type);
+}
+
 static int btf_df_resolve(struct btf_verifier_env *env,
 			  const struct resolve_vertex *v)
 {
@@ -997,6 +1060,62 @@ static int btf_int_check_member(struct btf_verifier_env *env,
 	return 0;
 }
 
+static int btf_int_check_kflag_member(struct btf_verifier_env *env,
+				      const struct btf_type *struct_type,
+				      const struct btf_member *member,
+				      const struct btf_type *member_type)
+{
+	u32 struct_bits_off, nr_bits, nr_int_data_bits, bytes_offset;
+	u32 int_data = btf_type_int(member_type);
+	u32 struct_size = struct_type->size;
+	u32 nr_copy_bits;
+
+	/* a regular int type is required for the kflag int member */
+	if (!btf_type_int_is_regular(member_type)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Invalid member base type");
+		return -EINVAL;
+	}
+
+	/* check sanity of bitfield size */
+	nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset);
+	struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset);
+	nr_int_data_bits = BTF_INT_BITS(int_data);
+	if (!nr_bits) {
+		/* Not a bitfield member, member offset must be at byte
+		 * boundary.
+		 */
+		if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+			btf_verifier_log_member(env, struct_type, member,
+						"Invalid member offset");
+			return -EINVAL;
+		}
+
+		nr_bits = nr_int_data_bits;
+	} else if (nr_bits > nr_int_data_bits) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Invalid member bitfield_size");
+		return -EINVAL;
+	}
+
+	bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+	nr_copy_bits = nr_bits + BITS_PER_BYTE_MASKED(struct_bits_off);
+	if (nr_copy_bits > BITS_PER_U64) {
+		btf_verifier_log_member(env, struct_type, member,
+					"nr_copy_bits exceeds 64");
+		return -EINVAL;
+	}
+
+	if (struct_size < bytes_offset ||
+	    struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member exceeds struct_size");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static s32 btf_int_check_meta(struct btf_verifier_env *env,
 			      const struct btf_type *t,
 			      u32 meta_left)
@@ -1016,6 +1135,11 @@ static s32 btf_int_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	int_data = btf_type_int(t);
 	if (int_data & ~BTF_INT_MASK) {
 		btf_verifier_log_basic(env, t, "Invalid int_data:%x",
@@ -1097,6 +1221,7 @@ static void btf_bitfield_seq_show(void *data, u8 bits_offset,
 	seq_printf(m, "0x%llx", print_num);
 }
 
+
 static void btf_int_bits_seq_show(const struct btf *btf,
 				  const struct btf_type *t,
 				  void *data, u8 bits_offset,
@@ -1163,6 +1288,7 @@ static const struct btf_kind_operations int_ops = {
 	.check_meta = btf_int_check_meta,
 	.resolve = btf_df_resolve,
 	.check_member = btf_int_check_member,
+	.check_kflag_member = btf_int_check_kflag_member,
 	.log_details = btf_int_log,
 	.seq_show = btf_int_seq_show,
 };
@@ -1192,6 +1318,31 @@ static int btf_modifier_check_member(struct btf_verifier_env *env,
 							 resolved_type);
 }
 
+static int btf_modifier_check_kflag_member(struct btf_verifier_env *env,
+					   const struct btf_type *struct_type,
+					   const struct btf_member *member,
+					   const struct btf_type *member_type)
+{
+	const struct btf_type *resolved_type;
+	u32 resolved_type_id = member->type;
+	struct btf_member resolved_member;
+	struct btf *btf = env->btf;
+
+	resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL);
+	if (!resolved_type) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Invalid member");
+		return -EINVAL;
+	}
+
+	resolved_member = *member;
+	resolved_member.type = resolved_type_id;
+
+	return btf_type_ops(resolved_type)->check_kflag_member(env, struct_type,
+							       &resolved_member,
+							       resolved_type);
+}
+
 static int btf_ptr_check_member(struct btf_verifier_env *env,
 				const struct btf_type *struct_type,
 				const struct btf_member *member,
@@ -1227,6 +1378,11 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	if (!BTF_TYPE_ID_VALID(t->type)) {
 		btf_verifier_log_type(env, t, "Invalid type_id");
 		return -EINVAL;
@@ -1380,6 +1536,7 @@ static struct btf_kind_operations modifier_ops = {
 	.check_meta = btf_ref_type_check_meta,
 	.resolve = btf_modifier_resolve,
 	.check_member = btf_modifier_check_member,
+	.check_kflag_member = btf_modifier_check_kflag_member,
 	.log_details = btf_ref_type_log,
 	.seq_show = btf_modifier_seq_show,
 };
@@ -1388,6 +1545,7 @@ static struct btf_kind_operations ptr_ops = {
 	.check_meta = btf_ref_type_check_meta,
 	.resolve = btf_ptr_resolve,
 	.check_member = btf_ptr_check_member,
+	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_ref_type_log,
 	.seq_show = btf_ptr_seq_show,
 };
@@ -1422,6 +1580,7 @@ static struct btf_kind_operations fwd_ops = {
 	.check_meta = btf_fwd_check_meta,
 	.resolve = btf_df_resolve,
 	.check_member = btf_df_check_member,
+	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_ref_type_log,
 	.seq_show = btf_df_seq_show,
 };
@@ -1480,6 +1639,11 @@ static s32 btf_array_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	if (t->size) {
 		btf_verifier_log_type(env, t, "size != 0");
 		return -EINVAL;
@@ -1603,6 +1767,7 @@ static struct btf_kind_operations array_ops = {
 	.check_meta = btf_array_check_meta,
 	.resolve = btf_array_resolve,
 	.check_member = btf_array_check_member,
+	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_array_log,
 	.seq_show = btf_array_seq_show,
 };
@@ -1641,6 +1806,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 	u32 meta_needed, last_offset;
 	struct btf *btf = env->btf;
 	u32 struct_size = t->size;
+	u32 offset;
 	u16 i;
 
 	meta_needed = btf_type_vlen(t) * sizeof(*member);
@@ -1682,7 +1848,8 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
-		if (is_union && member->offset) {
+		offset = btf_member_bit_offset(t, member);
+		if (is_union && offset) {
 			btf_verifier_log_member(env, t, member,
 						"Invalid member bits_offset");
 			return -EINVAL;
@@ -1692,20 +1859,20 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 		 * ">" instead of ">=" because the last member could be
 		 * "char a[0];"
 		 */
-		if (last_offset > member->offset) {
+		if (last_offset > offset) {
 			btf_verifier_log_member(env, t, member,
 						"Invalid member bits_offset");
 			return -EINVAL;
 		}
 
-		if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
+		if (BITS_ROUNDUP_BYTES(offset) > struct_size) {
 			btf_verifier_log_member(env, t, member,
 						"Member bits_offset exceeds its struct size");
 			return -EINVAL;
 		}
 
 		btf_verifier_log_member(env, t, member, NULL);
-		last_offset = member->offset;
+		last_offset = offset;
 	}
 
 	return meta_needed;
@@ -1735,9 +1902,14 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
 
 		last_member_type = btf_type_by_id(env->btf,
 						  last_member_type_id);
-		err = btf_type_ops(last_member_type)->check_member(env, v->t,
-							last_member,
-							last_member_type);
+		if (btf_type_kflag(v->t))
+			err = btf_type_ops(last_member_type)->check_kflag_member(env, v->t,
+								last_member,
+								last_member_type);
+		else
+			err = btf_type_ops(last_member_type)->check_member(env, v->t,
+								last_member,
+								last_member_type);
 		if (err)
 			return err;
 	}
@@ -1759,9 +1931,14 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
 			return env_stack_push(env, member_type, member_type_id);
 		}
 
-		err = btf_type_ops(member_type)->check_member(env, v->t,
-							      member,
-							      member_type);
+		if (btf_type_kflag(v->t))
+			err = btf_type_ops(member_type)->check_kflag_member(env, v->t,
+									    member,
+									    member_type);
+		else
+			err = btf_type_ops(member_type)->check_member(env, v->t,
+								      member,
+								      member_type);
 		if (err)
 			return err;
 	}
@@ -1789,17 +1966,26 @@ static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
 	for_each_member(i, t, member) {
 		const struct btf_type *member_type = btf_type_by_id(btf,
 								member->type);
-		u32 member_offset = member->offset;
-		u32 bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
-		u8 bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
 		const struct btf_kind_operations *ops;
+		u32 member_offset, bitfield_size;
+		u32 bytes_offset;
+		u8 bits8_offset;
 
 		if (i)
 			seq_puts(m, seq);
 
-		ops = btf_type_ops(member_type);
-		ops->seq_show(btf, member_type, member->type,
-			      data + bytes_offset, bits8_offset, m);
+		member_offset = btf_member_bit_offset(t, member);
+		bitfield_size = btf_member_bitfield_size(t, member);
+		if (bitfield_size) {
+			btf_bitfield_seq_show(data, member_offset,
+					      bitfield_size, m);
+		} else {
+			bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
+			bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
+			ops = btf_type_ops(member_type);
+			ops->seq_show(btf, member_type, member->type,
+				      data + bytes_offset, bits8_offset, m);
+		}
 	}
 	seq_puts(m, "}");
 }
@@ -1808,6 +1994,7 @@ static struct btf_kind_operations struct_ops = {
 	.check_meta = btf_struct_check_meta,
 	.resolve = btf_struct_resolve,
 	.check_member = btf_struct_check_member,
+	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_struct_log,
 	.seq_show = btf_struct_seq_show,
 };
@@ -1837,6 +2024,41 @@ static int btf_enum_check_member(struct btf_verifier_env *env,
 	return 0;
 }
 
+static int btf_enum_check_kflag_member(struct btf_verifier_env *env,
+				       const struct btf_type *struct_type,
+				       const struct btf_member *member,
+				       const struct btf_type *member_type)
+{
+	u32 struct_bits_off, nr_bits, bytes_end, struct_size;
+	u32 int_bitsize = sizeof(int) * BITS_PER_BYTE;
+
+	struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset);
+	nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset);
+	if (!nr_bits) {
+		if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+			btf_verifier_log_member(env, struct_type, member,
+						"Member is not byte aligned");
+				return -EINVAL;
+		}
+
+		nr_bits = int_bitsize;
+	} else if (nr_bits > int_bitsize) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Invalid member bitfield_size");
+		return -EINVAL;
+	}
+
+	struct_size = struct_type->size;
+	bytes_end = BITS_ROUNDUP_BYTES(struct_bits_off + nr_bits);
+	if (struct_size < bytes_end) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member exceeds struct_size");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static s32 btf_enum_check_meta(struct btf_verifier_env *env,
 			       const struct btf_type *t,
 			       u32 meta_left)
@@ -1856,6 +2078,11 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	if (t->size != sizeof(int)) {
 		btf_verifier_log_type(env, t, "Expected size:%zu",
 				      sizeof(int));
@@ -1924,6 +2151,7 @@ static struct btf_kind_operations enum_ops = {
 	.check_meta = btf_enum_check_meta,
 	.resolve = btf_df_resolve,
 	.check_member = btf_enum_check_member,
+	.check_kflag_member = btf_enum_check_kflag_member,
 	.log_details = btf_enum_log,
 	.seq_show = btf_enum_seq_show,
 };
@@ -1946,6 +2174,11 @@ static s32 btf_func_proto_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	btf_verifier_log_type(env, t, NULL);
 
 	return meta_needed;
@@ -2005,6 +2238,7 @@ static struct btf_kind_operations func_proto_ops = {
 	 * Hence, there is no btf_func_check_member().
 	 */
 	.check_member = btf_df_check_member,
+	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_func_proto_log,
 	.seq_show = btf_df_seq_show,
 };
@@ -2024,6 +2258,11 @@ static s32 btf_func_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	btf_verifier_log_type(env, t, NULL);
 
 	return 0;
@@ -2033,6 +2272,7 @@ static struct btf_kind_operations func_ops = {
 	.check_meta = btf_func_check_meta,
 	.resolve = btf_df_resolve,
 	.check_member = btf_df_check_member,
+	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_ref_type_log,
 	.seq_show = btf_df_seq_show,
 };
-- 
cgit v1.2.3


From ffa0c1cf59596fba54546ea828305acfcc2cf55e Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 15 Dec 2018 22:13:52 -0800
Subject: bpf: enable cgroup local storage map pretty print with kind_flag

Commit 970289fc0a83 ("bpf: add bpffs pretty print for cgroup
local storage maps") added bpffs pretty print for cgroup
local storage maps. The commit worked for struct without kind_flag
set.

This patch refactored and made pretty print also work
with kind_flag set for the struct.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/btf.h        |  5 ++++-
 kernel/bpf/btf.c           | 37 ++++++++++++++++++++++++++++---------
 kernel/bpf/local_storage.c | 17 ++++-------------
 3 files changed, 36 insertions(+), 23 deletions(-)

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 58000d7e06e3..12502e25e767 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -7,6 +7,7 @@
 #include <linux/types.h>
 
 struct btf;
+struct btf_member;
 struct btf_type;
 union bpf_attr;
 
@@ -46,7 +47,9 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
 int btf_get_fd_by_id(u32 id);
 u32 btf_id(const struct btf *btf);
-bool btf_type_is_reg_int(const struct btf_type *t, u32 expected_size);
+bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
+			   const struct btf_member *m,
+			   u32 expected_offset, u32 expected_size);
 
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 93b6905e3a9b..e804b26a0506 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -546,22 +546,41 @@ static bool btf_type_int_is_regular(const struct btf_type *t)
 }
 
 /*
- * Check that given type is a regular int and has the expected size.
+ * Check that given struct member is a regular int with expected
+ * offset and size.
  */
-bool btf_type_is_reg_int(const struct btf_type *t, u32 expected_size)
+bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
+			   const struct btf_member *m,
+			   u32 expected_offset, u32 expected_size)
 {
-	u8 nr_bits, nr_bytes;
-	u32 int_data;
+	const struct btf_type *t;
+	u32 id, int_data;
+	u8 nr_bits;
 
-	if (!btf_type_is_int(t))
+	id = m->type;
+	t = btf_type_id_size(btf, &id, NULL);
+	if (!t || !btf_type_is_int(t))
 		return false;
 
 	int_data = btf_type_int(t);
 	nr_bits = BTF_INT_BITS(int_data);
-	nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
-	if (BITS_PER_BYTE_MASKED(nr_bits) ||
-	    BTF_INT_OFFSET(int_data) ||
-	    nr_bytes != expected_size)
+	if (btf_type_kflag(s)) {
+		u32 bitfield_size = BTF_MEMBER_BITFIELD_SIZE(m->offset);
+		u32 bit_offset = BTF_MEMBER_BIT_OFFSET(m->offset);
+
+		/* if kflag set, int should be a regular int and
+		 * bit offset should be at byte boundary.
+		 */
+		return !bitfield_size &&
+		       BITS_ROUNDUP_BYTES(bit_offset) == expected_offset &&
+		       BITS_ROUNDUP_BYTES(nr_bits) == expected_size;
+	}
+
+	if (BTF_INT_OFFSET(int_data) ||
+	    BITS_PER_BYTE_MASKED(m->offset) ||
+	    BITS_ROUNDUP_BYTES(m->offset) != expected_offset ||
+	    BITS_PER_BYTE_MASKED(nr_bits) ||
+	    BITS_ROUNDUP_BYTES(nr_bits) != expected_size)
 		return false;
 
 	return true;
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 5eca03da0989..07a34ef562a0 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -315,9 +315,8 @@ static int cgroup_storage_check_btf(const struct bpf_map *map,
 				    const struct btf_type *key_type,
 				    const struct btf_type *value_type)
 {
-	const struct btf_type *t;
 	struct btf_member *m;
-	u32 id, size;
+	u32 offset, size;
 
 	/* Key is expected to be of struct bpf_cgroup_storage_key type,
 	 * which is:
@@ -338,25 +337,17 @@ static int cgroup_storage_check_btf(const struct bpf_map *map,
 	 * The first field must be a 64 bit integer at 0 offset.
 	 */
 	m = (struct btf_member *)(key_type + 1);
-	if (m->offset)
-		return -EINVAL;
-	id = m->type;
-	t = btf_type_id_size(btf, &id, NULL);
 	size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, cgroup_inode_id);
-	if (!t || !btf_type_is_reg_int(t, size))
+	if (!btf_member_is_reg_int(btf, key_type, m, 0, size))
 		return -EINVAL;
 
 	/*
 	 * The second field must be a 32 bit integer at 64 bit offset.
 	 */
 	m++;
-	if (m->offset != offsetof(struct bpf_cgroup_storage_key, attach_type) *
-	    BITS_PER_BYTE)
-		return -EINVAL;
-	id = m->type;
-	t = btf_type_id_size(btf, &id, NULL);
+	offset = offsetof(struct bpf_cgroup_storage_key, attach_type);
 	size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, attach_type);
-	if (!t || !btf_type_is_reg_int(t, size))
+	if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
 		return -EINVAL;
 
 	return 0;
-- 
cgit v1.2.3


From 128b343dbef543e75793deed5cb3e5eeb9b69d0e Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 15 Dec 2018 22:13:53 -0800
Subject: tools/bpf: sync btf.h header from kernel to tools

Sync include/uapi/linux/btf.h to tools/include/uapi/linux/btf.h.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/btf.h | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 14f66948fc95..7b7475ef2f17 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -34,7 +34,9 @@ struct btf_type {
 	 * bits  0-15: vlen (e.g. # of struct's members)
 	 * bits 16-23: unused
 	 * bits 24-27: kind (e.g. int, ptr, array...etc)
-	 * bits 28-31: unused
+	 * bits 28-30: unused
+	 * bit     31: kind_flag, currently used by
+	 *             struct, union and fwd
 	 */
 	__u32 info;
 	/* "size" is used by INT, ENUM, STRUCT and UNION.
@@ -52,6 +54,7 @@ struct btf_type {
 
 #define BTF_INFO_KIND(info)	(((info) >> 24) & 0x0f)
 #define BTF_INFO_VLEN(info)	((info) & 0xffff)
+#define BTF_INFO_KFLAG(info)	((info) >> 31)
 
 #define BTF_KIND_UNKN		0	/* Unknown	*/
 #define BTF_KIND_INT		1	/* Integer	*/
@@ -110,9 +113,22 @@ struct btf_array {
 struct btf_member {
 	__u32	name_off;
 	__u32	type;
-	__u32	offset;	/* offset in bits */
+	/* If the type info kind_flag is set, the btf_member offset
+	 * contains both member bitfield size and bit offset. The
+	 * bitfield size is set for bitfield members. If the type
+	 * info kind_flag is not set, the offset contains only bit
+	 * offset.
+	 */
+	__u32	offset;
 };
 
+/* If the struct/union type info kind_flag is set, the
+ * following two macros are used to access bitfield_size
+ * and bit_offset from btf_member.offset.
+ */
+#define BTF_MEMBER_BITFIELD_SIZE(val)	((val) >> 24)
+#define BTF_MEMBER_BIT_OFFSET(val)	((val) & 0xffffff)
+
 /* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
  * The exact number of btf_param is stored in the vlen (of the
  * info in "struct btf_type").
-- 
cgit v1.2.3


From cd9de5d3d64b472f67a5ac8520f79ce42f7583b8 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 15 Dec 2018 22:13:55 -0800
Subject: tools/bpf: add test_btf unit tests for kind_flag

This patch added unit tests for different types handling
type->info.kind_flag. The following new tests are added:
  $ test_btf
  ...
  BTF raw test[82] (invalid int kind_flag): OK
  BTF raw test[83] (invalid ptr kind_flag): OK
  BTF raw test[84] (invalid array kind_flag): OK
  BTF raw test[85] (invalid enum kind_flag): OK
  BTF raw test[86] (valid fwd kind_flag): OK
  BTF raw test[87] (invalid typedef kind_flag): OK
  BTF raw test[88] (invalid volatile kind_flag): OK
  BTF raw test[89] (invalid const kind_flag): OK
  BTF raw test[90] (invalid restrict kind_flag): OK
  BTF raw test[91] (invalid func kind_flag): OK
  BTF raw test[92] (invalid func_proto kind_flag): OK
  BTF raw test[93] (valid struct kind_flag, bitfield_size = 0): OK
  BTF raw test[94] (valid struct kind_flag, int member, bitfield_size != 0): OK
  BTF raw test[95] (valid union kind_flag, int member, bitfield_size != 0): OK
  BTF raw test[96] (valid struct kind_flag, enum member, bitfield_size != 0): OK
  BTF raw test[97] (valid union kind_flag, enum member, bitfield_size != 0): OK
  BTF raw test[98] (valid struct kind_flag, typedef member, bitfield_size != 0): OK
  BTF raw test[99] (valid union kind_flag, typedef member, bitfield_size != 0): OK
  BTF raw test[100] (invalid struct type, bitfield_size greater than struct size): OK
  BTF raw test[101] (invalid struct type, kind_flag bitfield base_type int not regular): OK
  BTF raw test[102] (invalid struct type, kind_flag base_type int not regular): OK
  BTF raw test[103] (invalid union type, bitfield_size greater than struct size): OK
  ...
  PASS:122 SKIP:0 FAIL:0

The second parameter name of macro
  BTF_INFO_ENC(kind, root, vlen)
in selftests test_btf.c is also renamed from "root" to "kind_flag".
Note that before this patch "root" is not used and always 0.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_btf.c | 496 ++++++++++++++++++++++++++++++++-
 1 file changed, 494 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 8478316aaf9a..5346d1fa8a4d 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -65,8 +65,8 @@ static int __base_pr(const char *format, ...)
 	return err;
 }
 
-#define BTF_INFO_ENC(kind, root, vlen)			\
-	((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
+#define BTF_INFO_ENC(kind, kind_flag, vlen)			\
+	((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
 
 #define BTF_TYPE_ENC(name, info, size_or_type)	\
 	(name), (info), (size_or_type)
@@ -86,6 +86,8 @@ static int __base_pr(const char *format, ...)
 #define BTF_MEMBER_ENC(name, type, bits_offset)	\
 	(name), (type), (bits_offset)
 #define BTF_ENUM_ENC(name, val) (name), (val)
+#define BTF_MEMBER_OFFSET(bitfield_size, bits_offset) \
+	((bitfield_size) << 24 | (bits_offset))
 
 #define BTF_TYPEDEF_ENC(name, type) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type)
@@ -2215,6 +2217,496 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid type_id",
 },
 
+{
+	.descr = "invalid int kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_INT, 1, 0), 4),	/* [2] */
+		BTF_INT_ENC(0, 0, 32),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "int_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid ptr kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 1, 0), 1),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "ptr_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid array kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 1, 0), 0),	/* [2] */
+		BTF_ARRAY_ENC(1, 1, 1),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "array_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid enum kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 1, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "enum_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "valid fwd kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(NAME_TBD,
+			     BTF_INFO_ENC(BTF_KIND_FWD, 1, 0), 0),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "fwd_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "invalid typedef kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(NAME_TBD,
+			     BTF_INFO_ENC(BTF_KIND_TYPEDEF, 1, 0), 1),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "typedef_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid volatile kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 1, 0), 1),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "volatile_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid const kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 1, 0), 1),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "const_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid restrict kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_RESTRICT, 1, 0), 1),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "restrict_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid func kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 0), 0),	/* [2] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FUNC, 1, 0), 2),	/* [3] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid func_proto kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 1, 0), 0),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "valid struct, kind_flag, bitfield_size = 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 8),	/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(0, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(0, 32)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid struct, kind_flag, int member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),	/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 4)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid union, kind_flag, int member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 4),	/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "union_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid struct, kind_flag, enum member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 4)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B\0C"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid union, kind_flag, enum member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 4),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B\0C"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "union_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid struct, kind_flag, typedef member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 4, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 5, BTF_MEMBER_OFFSET(4, 4)),
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),				/* [4] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 2),				/* [5] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B\0C\0D\0E"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid union, kind_flag, typedef member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 4),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 4, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 5, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),				/* [4] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 2),				/* [5] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B\0C\0D\0E"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "union_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "invalid struct, kind_flag, bitfield_size greater than struct size",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),	/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(20, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(20, 20)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Member exceeds struct_size",
+},
+
+{
+	.descr = "invalid struct, kind_flag, bitfield base_type int not regular",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 20, 4),			/* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(20, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(20, 20)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid member base type",
+},
+
+{
+	.descr = "invalid struct, kind_flag, base_type int not regular",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 12, 4),			/* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(8, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(8, 8)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid member base type",
+},
+
+{
+	.descr = "invalid union, kind_flag, bitfield_size greater than struct size",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 2),	/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(8, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(20, 0)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "union_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Member exceeds struct_size",
+},
+
+{
+	.descr = "invalid struct, kind_flag, int member, bitfield_size = 0, wrong byte alignment",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 12),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 36)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid member offset",
+},
+
+{
+	.descr = "invalid struct, kind_flag, enum member, bitfield_size = 0, wrong byte alignment",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 12),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 36)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B\0C"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid member offset",
+},
+
 }; /* struct btf_raw_test raw_tests[] */
 
 static const char *get_next_str(const char *start, const char *end)
-- 
cgit v1.2.3


From d0ebce687edc5d5a899b3de6b1adbfa0c5b64021 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 15 Dec 2018 22:13:56 -0800
Subject: tools/bpf: test kernel bpffs map pretty print with struct kind_flag

The new tests are added to test bpffs map pretty print in kernel with kind_flag
for structure type.

  $ test_btf -p
  ......
  BTF pretty print array(#1)......OK
  BTF pretty print array(#2)......OK
  PASS:8 SKIP:0 FAIL:0

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_btf.c | 168 ++++++++++++++++++++++++++++++---
 1 file changed, 154 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 5346d1fa8a4d..b783aa2212cc 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -3528,7 +3528,8 @@ struct pprint_mapv {
 	} aenum;
 };
 
-static struct btf_raw_test pprint_test_template = {
+static struct btf_raw_test pprint_test_template[] = {
+{
 	.raw_types = {
 		/* unsighed char */			/* [1] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
@@ -3578,13 +3579,140 @@ static struct btf_raw_test pprint_test_template = {
 		BTF_MEMBER_ENC(NAME_TBD, 15, 192),	/* aenum */
 		BTF_END_RAW,
 	},
-	.str_sec = "\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum",
-	.str_sec_size = sizeof("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
+	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
+	.key_size = sizeof(unsigned int),
+	.value_size = sizeof(struct pprint_mapv),
+	.key_type_id = 3,	/* unsigned int */
+	.value_type_id = 16,	/* struct pprint_mapv */
+	.max_entries = 128 * 1024,
+},
+
+{
+	/* this type will have the same type as the
+	 * first .raw_types definition, but struct type will
+	 * be encoded with kind_flag set.
+	 */
+	.raw_types = {
+		/* unsighed char */			/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
+		/* unsigned short */			/* [2] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
+		/* unsigned int */			/* [3] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),
+		/* int */				/* [4] */
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+		/* unsigned long long */		/* [5] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8),
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),	/* [6] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),	/* [7] */
+		/* uint8_t[8] */			/* [8] */
+		BTF_TYPE_ARRAY_ENC(9, 1, 8),
+		/* typedef unsigned char uint8_t */	/* [9] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),
+		/* typedef unsigned short uint16_t */	/* [10] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 2),
+		/* typedef unsigned int uint32_t */	/* [11] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 3),
+		/* typedef int int32_t */		/* [12] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 4),
+		/* typedef unsigned long long uint64_t *//* [13] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 5),
+		/* union (anon) */			/* [14] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 0, 2), 8),
+		BTF_MEMBER_ENC(NAME_TBD, 13, 0),/* uint64_t ui64; */
+		BTF_MEMBER_ENC(NAME_TBD, 8, 0),	/* uint8_t ui8a[8]; */
+		/* enum (anon) */			/* [15] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 4), 4),
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_ENUM_ENC(NAME_TBD, 1),
+		BTF_ENUM_ENC(NAME_TBD, 2),
+		BTF_ENUM_ENC(NAME_TBD, 3),
+		/* struct pprint_mapv */		/* [16] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 8), 32),
+		BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)),	/* uint32_t ui32 */
+		BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)),	/* uint16_t ui16 */
+		BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)),	/* int32_t si32 */
+		BTF_MEMBER_ENC(NAME_TBD, 6, BTF_MEMBER_OFFSET(2, 96)),	/* unused_bits2a */
+		BTF_MEMBER_ENC(NAME_TBD, 7, BTF_MEMBER_OFFSET(28, 98)),	/* bits28 */
+		BTF_MEMBER_ENC(NAME_TBD, 6, BTF_MEMBER_OFFSET(2, 126)),	/* unused_bits2b */
+		BTF_MEMBER_ENC(0, 14, BTF_MEMBER_OFFSET(0, 128)),	/* union (anon) */
+		BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)),	/* aenum */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
 	.key_size = sizeof(unsigned int),
 	.value_size = sizeof(struct pprint_mapv),
 	.key_type_id = 3,	/* unsigned int */
 	.value_type_id = 16,	/* struct pprint_mapv */
 	.max_entries = 128 * 1024,
+},
+
+{
+	/* this type will have the same layout as the
+	 * first .raw_types definition. The struct type will
+	 * be encoded with kind_flag set, bitfield members
+	 * are added typedef/const/volatile, and bitfield members
+	 * will have both int and enum types.
+	 */
+	.raw_types = {
+		/* unsighed char */			/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
+		/* unsigned short */			/* [2] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
+		/* unsigned int */			/* [3] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),
+		/* int */				/* [4] */
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+		/* unsigned long long */		/* [5] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8),
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),	/* [6] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),	/* [7] */
+		/* uint8_t[8] */			/* [8] */
+		BTF_TYPE_ARRAY_ENC(9, 1, 8),
+		/* typedef unsigned char uint8_t */	/* [9] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),
+		/* typedef unsigned short uint16_t */	/* [10] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 2),
+		/* typedef unsigned int uint32_t */	/* [11] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 3),
+		/* typedef int int32_t */		/* [12] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 4),
+		/* typedef unsigned long long uint64_t *//* [13] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 5),
+		/* union (anon) */			/* [14] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 0, 2), 8),
+		BTF_MEMBER_ENC(NAME_TBD, 13, 0),/* uint64_t ui64; */
+		BTF_MEMBER_ENC(NAME_TBD, 8, 0),	/* uint8_t ui8a[8]; */
+		/* enum (anon) */			/* [15] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 4), 4),
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_ENUM_ENC(NAME_TBD, 1),
+		BTF_ENUM_ENC(NAME_TBD, 2),
+		BTF_ENUM_ENC(NAME_TBD, 3),
+		/* struct pprint_mapv */		/* [16] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 8), 32),
+		BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)),	/* uint32_t ui32 */
+		BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)),	/* uint16_t ui16 */
+		BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)),	/* int32_t si32 */
+		BTF_MEMBER_ENC(NAME_TBD, 17, BTF_MEMBER_OFFSET(2, 96)),	/* unused_bits2a */
+		BTF_MEMBER_ENC(NAME_TBD, 7, BTF_MEMBER_OFFSET(28, 98)),	/* bits28 */
+		BTF_MEMBER_ENC(NAME_TBD, 19, BTF_MEMBER_OFFSET(2, 126)),/* unused_bits2b */
+		BTF_MEMBER_ENC(0, 14, BTF_MEMBER_OFFSET(0, 128)),	/* union (anon) */
+		BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)),	/* aenum */
+		/* typedef unsigned int ___int */	/* [17] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 18),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), 6),	/* [18] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 15),	/* [19] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0___int"),
+	.key_size = sizeof(unsigned int),
+	.value_size = sizeof(struct pprint_mapv),
+	.key_type_id = 3,	/* unsigned int */
+	.value_type_id = 16,	/* struct pprint_mapv */
+	.max_entries = 128 * 1024,
+},
+
 };
 
 static struct btf_pprint_test_meta {
@@ -3687,9 +3815,9 @@ static int check_line(const char *expected_line, int nexpected_line,
 }
 
 
-static int do_test_pprint(void)
+static int do_test_pprint(int test_num)
 {
-	const struct btf_raw_test *test = &pprint_test_template;
+	const struct btf_raw_test *test = &pprint_test_template[test_num];
 	struct bpf_create_map_attr create_attr = {};
 	bool ordered_map, lossless_map, percpu_map;
 	int err, ret, num_cpus, rounded_value_size;
@@ -3705,7 +3833,7 @@ static int do_test_pprint(void)
 	uint8_t *raw_btf;
 	ssize_t nread;
 
-	fprintf(stderr, "%s......", test->descr);
+	fprintf(stderr, "%s(#%d)......", test->descr, test_num);
 	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
 				 test->str_sec, test->str_sec_size,
 				 &raw_btf_size, NULL);
@@ -3898,15 +4026,27 @@ static int test_pprint(void)
 	unsigned int i;
 	int err = 0;
 
+	/* test various maps with the first test template */
 	for (i = 0; i < ARRAY_SIZE(pprint_tests_meta); i++) {
-		pprint_test_template.descr = pprint_tests_meta[i].descr;
-		pprint_test_template.map_type = pprint_tests_meta[i].map_type;
-		pprint_test_template.map_name = pprint_tests_meta[i].map_name;
-		pprint_test_template.ordered_map = pprint_tests_meta[i].ordered_map;
-		pprint_test_template.lossless_map = pprint_tests_meta[i].lossless_map;
-		pprint_test_template.percpu_map = pprint_tests_meta[i].percpu_map;
-
-		err |= count_result(do_test_pprint());
+		pprint_test_template[0].descr = pprint_tests_meta[i].descr;
+		pprint_test_template[0].map_type = pprint_tests_meta[i].map_type;
+		pprint_test_template[0].map_name = pprint_tests_meta[i].map_name;
+		pprint_test_template[0].ordered_map = pprint_tests_meta[i].ordered_map;
+		pprint_test_template[0].lossless_map = pprint_tests_meta[i].lossless_map;
+		pprint_test_template[0].percpu_map = pprint_tests_meta[i].percpu_map;
+
+		err |= count_result(do_test_pprint(0));
+	}
+
+	/* test rest test templates with the first map */
+	for (i = 1; i < ARRAY_SIZE(pprint_test_template); i++) {
+		pprint_test_template[i].descr = pprint_tests_meta[0].descr;
+		pprint_test_template[i].map_type = pprint_tests_meta[0].map_type;
+		pprint_test_template[i].map_name = pprint_tests_meta[0].map_name;
+		pprint_test_template[i].ordered_map = pprint_tests_meta[0].ordered_map;
+		pprint_test_template[i].lossless_map = pprint_tests_meta[0].lossless_map;
+		pprint_test_template[i].percpu_map = pprint_tests_meta[0].percpu_map;
+		err |= count_result(do_test_pprint(i));
 	}
 
 	return err;
-- 
cgit v1.2.3


From 9f95e37e31a4eabd7c8152f2ddcdbea5eafdb7c8 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 15 Dec 2018 22:13:57 -0800
Subject: tools: bpftool: refactor btf_dumper_int_bits()

The core dump funcitonality in btf_dumper_int_bits() is
refactored into a separate function btf_dumper_bitfield()
which will be used by the next patch.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/btf_dumper.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index 5cdb2ef8b6f1..06e3d2bbf6d1 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -73,20 +73,17 @@ static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id,
 	return ret;
 }
 
-static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset,
+static void btf_dumper_bitfield(__u32 nr_bits, __u8 bit_offset,
 				const void *data, json_writer_t *jw,
 				bool is_plain_text)
 {
 	int left_shift_bits, right_shift_bits;
-	int nr_bits = BTF_INT_BITS(int_type);
-	int total_bits_offset;
 	int bytes_to_copy;
 	int bits_to_copy;
 	__u64 print_num;
 
-	total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type);
-	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
-	bit_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
+	data += BITS_ROUNDDOWN_BYTES(bit_offset);
+	bit_offset = BITS_PER_BYTE_MASKED(bit_offset);
 	bits_to_copy = bit_offset + nr_bits;
 	bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy);
 
@@ -109,6 +106,22 @@ static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset,
 		jsonw_printf(jw, "%llu", print_num);
 }
 
+
+static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset,
+				const void *data, json_writer_t *jw,
+				bool is_plain_text)
+{
+	int nr_bits = BTF_INT_BITS(int_type);
+	int total_bits_offset;
+
+	/* bits_offset is at most 7.
+	 * BTF_INT_OFFSET() cannot exceed 64 bits.
+	 */
+	total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type);
+	btf_dumper_bitfield(nr_bits, total_bits_offset, data, jw,
+			    is_plain_text);
+}
+
 static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset,
 			  const void *data, json_writer_t *jw,
 			  bool is_plain_text)
-- 
cgit v1.2.3


From 8772c8bc093b2d5823125475e1206b80664f8acb Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 15 Dec 2018 22:13:58 -0800
Subject: tools: bpftool: support pretty print with kind_flag set

The following example shows map pretty print with structures
which include bitfield members.

  enum A { A1, A2, A3, A4, A5 };
  typedef enum A ___A;
  struct tmp_t {
       char a1:4;
       int  a2:4;
       int  :4;
       __u32 a3:4;
       int b;
       ___A b1:4;
       enum A b2:4;
  };
  struct bpf_map_def SEC("maps") tmpmap = {
       .type = BPF_MAP_TYPE_ARRAY,
       .key_size = sizeof(__u32),
       .value_size = sizeof(struct tmp_t),
       .max_entries = 1,
  };
  BPF_ANNOTATE_KV_PAIR(tmpmap, int, struct tmp_t);

and the following map update in the bpf program:

  key = 0;
  struct tmp_t t = {};
  t.a1 = 2;
  t.a2 = 4;
  t.a3 = 6;
  t.b = 7;
  t.b1 = 8;
  t.b2 = 10;
  bpf_map_update_elem(&tmpmap, &key, &t, 0);

With this patch, I am able to print out the map values
correctly with this patch:
bpftool map dump id 187
  [{
        "key": 0,
        "value": {
            "a1": 0x2,
            "a2": 0x4,
            "a3": 0x6,
            "b": 7,
            "b1": 0x8,
            "b2": 0xa
        }
    }
  ]

Previously, if a function prototype argument has a typedef
type, the prototype is not printed since
function __btf_dumper_type_only() bailed out with error
if the type is a typedef. This commit corrected this
behavior by printing out typedef properly.

The following example shows forward type and
typedef type can be properly printed in function prototype
with modified test_btf_haskv.c.

  struct t;
  union  u;

  __attribute__((noinline))
  static int test_long_fname_1(struct dummy_tracepoint_args *arg,
                               struct t *p1, union u *p2,
                               __u32 unused)
  ...
  int _dummy_tracepoint(struct dummy_tracepoint_args *arg) {
    return test_long_fname_1(arg, 0, 0, 0);
  }

  $ bpftool p d xlated id 24
  ...
  int test_long_fname_1(struct dummy_tracepoint_args * arg,
                        struct t * p1, union u * p2,
                        __u32 unused)
  ...

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/btf_dumper.c | 36 +++++++++++++++++++++++++++---------
 1 file changed, 27 insertions(+), 9 deletions(-)

diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index 06e3d2bbf6d1..3f0629edbca5 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -193,6 +193,7 @@ static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id,
 	const struct btf_type *t;
 	struct btf_member *m;
 	const void *data_off;
+	int kind_flag;
 	int ret = 0;
 	int i, vlen;
 
@@ -200,18 +201,32 @@ static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id,
 	if (!t)
 		return -EINVAL;
 
+	kind_flag = BTF_INFO_KFLAG(t->info);
 	vlen = BTF_INFO_VLEN(t->info);
 	jsonw_start_object(d->jw);
 	m = (struct btf_member *)(t + 1);
 
 	for (i = 0; i < vlen; i++) {
-		data_off = data + BITS_ROUNDDOWN_BYTES(m[i].offset);
+		__u32 bit_offset = m[i].offset;
+		__u32 bitfield_size = 0;
+
+		if (kind_flag) {
+			bitfield_size = BTF_MEMBER_BITFIELD_SIZE(bit_offset);
+			bit_offset = BTF_MEMBER_BIT_OFFSET(bit_offset);
+		}
+
 		jsonw_name(d->jw, btf__name_by_offset(d->btf, m[i].name_off));
-		ret = btf_dumper_do_type(d, m[i].type,
-					 BITS_PER_BYTE_MASKED(m[i].offset),
-					 data_off);
-		if (ret)
-			break;
+		if (bitfield_size) {
+			btf_dumper_bitfield(bitfield_size, bit_offset,
+					    data, d->jw, d->is_plain_text);
+		} else {
+			data_off = data + BITS_ROUNDDOWN_BYTES(bit_offset);
+			ret = btf_dumper_do_type(d, m[i].type,
+						 BITS_PER_BYTE_MASKED(bit_offset),
+						 data_off);
+			if (ret)
+				break;
+		}
 	}
 
 	jsonw_end_object(d->jw);
@@ -298,6 +313,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
 
 	switch (BTF_INFO_KIND(t->info)) {
 	case BTF_KIND_INT:
+	case BTF_KIND_TYPEDEF:
 		BTF_PRINT_ARG("%s ", btf__name_by_offset(btf, t->name_off));
 		break;
 	case BTF_KIND_STRUCT:
@@ -321,10 +337,11 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
 		BTF_PRINT_TYPE(t->type);
 		BTF_PRINT_ARG("* ");
 		break;
-	case BTF_KIND_UNKN:
 	case BTF_KIND_FWD:
-	case BTF_KIND_TYPEDEF:
-		return -1;
+		BTF_PRINT_ARG("%s %s ",
+			      BTF_INFO_KFLAG(t->info) ? "union" : "struct",
+			      btf__name_by_offset(btf, t->name_off));
+		break;
 	case BTF_KIND_VOLATILE:
 		BTF_PRINT_ARG("volatile ");
 		BTF_PRINT_TYPE(t->type);
@@ -348,6 +365,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
 		if (pos == -1)
 			return -1;
 		break;
+	case BTF_KIND_UNKN:
 	default:
 		return -1;
 	}
-- 
cgit v1.2.3


From 07a09d1b73c9651289d35449460d10e195e2f197 Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Mon, 17 Dec 2018 16:57:50 +0900
Subject: bpf: libbpf: fix memleak by freeing line_info

This patch fixes a memory leak in libbpf by freeing up line_info
member of struct bpf_program while unloading a program.

Fixes: 3d65014146c6 ("bpf: libbpf: Add btf_line_info support to libbpf")
Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e2bc75ee1614..169e347c76f6 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -266,6 +266,7 @@ void bpf_program__unload(struct bpf_program *prog)
 
 	zclose(prog->btf_fd);
 	zfree(&prog->func_info);
+	zfree(&prog->line_info);
 }
 
 static void bpf_program__exit(struct bpf_program *prog)
-- 
cgit v1.2.3


From 5a86d68bcf02f2d1e9a5897dd482079fd5f75e7f Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 5 Nov 2018 18:22:44 +0900
Subject: netfilter: ipt_CLUSTERIP: fix deadlock in netns exit routine

When network namespace is destroyed, cleanup_net() is called.
cleanup_net() holds pernet_ops_rwsem then calls each ->exit callback.
So that clusterip_tg_destroy() is called by cleanup_net().
And clusterip_tg_destroy() calls unregister_netdevice_notifier().

But both cleanup_net() and clusterip_tg_destroy() hold same
lock(pernet_ops_rwsem). hence deadlock occurrs.

After this patch, only 1 notifier is registered when module is inserted.
And all of configs are added to per-net list.

test commands:
   %ip netns add vm1
   %ip netns exec vm1 bash
   %ip link set lo up
   %iptables -A INPUT -p tcp -i lo -d 192.168.0.5 --dport 80 \
	-j CLUSTERIP --new --hashmode sourceip \
	--clustermac 01:00:5e:00:00:20 --total-nodes 2 --local-node 1
   %exit
   %ip netns del vm1

splat looks like:
[  341.809674] ============================================
[  341.809674] WARNING: possible recursive locking detected
[  341.809674] 4.19.0-rc5+ #16 Tainted: G        W
[  341.809674] --------------------------------------------
[  341.809674] kworker/u4:2/87 is trying to acquire lock:
[  341.809674] 000000005da2d519 (pernet_ops_rwsem){++++}, at: unregister_netdevice_notifier+0x8c/0x460
[  341.809674]
[  341.809674] but task is already holding lock:
[  341.809674] 000000005da2d519 (pernet_ops_rwsem){++++}, at: cleanup_net+0x119/0x900
[  341.809674]
[  341.809674] other info that might help us debug this:
[  341.809674]  Possible unsafe locking scenario:
[  341.809674]
[  341.809674]        CPU0
[  341.809674]        ----
[  341.809674]   lock(pernet_ops_rwsem);
[  341.809674]   lock(pernet_ops_rwsem);
[  341.809674]
[  341.809674]  *** DEADLOCK ***
[  341.809674]
[  341.809674]  May be due to missing lock nesting notation
[  341.809674]
[  341.809674] 3 locks held by kworker/u4:2/87:
[  341.809674]  #0: 00000000d9df6c92 ((wq_completion)"%s""netns"){+.+.}, at: process_one_work+0xafe/0x1de0
[  341.809674]  #1: 00000000c2cbcee2 (net_cleanup_work){+.+.}, at: process_one_work+0xb60/0x1de0
[  341.809674]  #2: 000000005da2d519 (pernet_ops_rwsem){++++}, at: cleanup_net+0x119/0x900
[  341.809674]
[  341.809674] stack backtrace:
[  341.809674] CPU: 1 PID: 87 Comm: kworker/u4:2 Tainted: G        W         4.19.0-rc5+ #16
[  341.809674] Workqueue: netns cleanup_net
[  341.809674] Call Trace:
[ ... ]
[  342.070196]  down_write+0x93/0x160
[  342.070196]  ? unregister_netdevice_notifier+0x8c/0x460
[  342.070196]  ? down_read+0x1e0/0x1e0
[  342.070196]  ? sched_clock_cpu+0x126/0x170
[  342.070196]  ? find_held_lock+0x39/0x1c0
[  342.070196]  unregister_netdevice_notifier+0x8c/0x460
[  342.070196]  ? register_netdevice_notifier+0x790/0x790
[  342.070196]  ? __local_bh_enable_ip+0xe9/0x1b0
[  342.070196]  ? __local_bh_enable_ip+0xe9/0x1b0
[  342.070196]  ? clusterip_tg_destroy+0x372/0x650 [ipt_CLUSTERIP]
[  342.070196]  ? trace_hardirqs_on+0x93/0x210
[  342.070196]  ? __bpf_trace_preemptirq_template+0x10/0x10
[  342.070196]  ? clusterip_tg_destroy+0x372/0x650 [ipt_CLUSTERIP]
[  342.123094]  clusterip_tg_destroy+0x3ad/0x650 [ipt_CLUSTERIP]
[  342.123094]  ? clusterip_net_init+0x3d0/0x3d0 [ipt_CLUSTERIP]
[  342.123094]  ? cleanup_match+0x17d/0x200 [ip_tables]
[  342.123094]  ? xt_unregister_table+0x215/0x300 [x_tables]
[  342.123094]  ? kfree+0xe2/0x2a0
[  342.123094]  cleanup_entry+0x1d5/0x2f0 [ip_tables]
[  342.123094]  ? cleanup_match+0x200/0x200 [ip_tables]
[  342.123094]  __ipt_unregister_table+0x9b/0x1a0 [ip_tables]
[  342.123094]  iptable_filter_net_exit+0x43/0x80 [iptable_filter]
[  342.123094]  ops_exit_list.isra.10+0x94/0x140
[  342.123094]  cleanup_net+0x45b/0x900
[ ... ]

Fixes: 202f59afd441 ("netfilter: ipt_CLUSTERIP: do not hold dev")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/ipt_CLUSTERIP.c | 155 +++++++++++++++++++++----------------
 1 file changed, 87 insertions(+), 68 deletions(-)

diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 5b0c1ee6ae26..091d163d215b 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -57,17 +57,14 @@ struct clusterip_config {
 	enum clusterip_hashmode hash_mode;	/* which hashing mode */
 	u_int32_t hash_initval;			/* hash initialization */
 	struct rcu_head rcu;
-
+	struct net *net;			/* netns for pernet list */
 	char ifname[IFNAMSIZ];			/* device ifname */
-	struct notifier_block notifier;		/* refresh c->ifindex in it */
 };
 
 #ifdef CONFIG_PROC_FS
 static const struct file_operations clusterip_proc_fops;
 #endif
 
-static unsigned int clusterip_net_id __read_mostly;
-
 struct clusterip_net {
 	struct list_head configs;
 	/* lock protects the configs list */
@@ -78,16 +75,30 @@ struct clusterip_net {
 #endif
 };
 
+static unsigned int clusterip_net_id __read_mostly;
+static inline struct clusterip_net *clusterip_pernet(struct net *net)
+{
+	return net_generic(net, clusterip_net_id);
+}
+
 static inline void
 clusterip_config_get(struct clusterip_config *c)
 {
 	refcount_inc(&c->refcount);
 }
 
-
 static void clusterip_config_rcu_free(struct rcu_head *head)
 {
-	kfree(container_of(head, struct clusterip_config, rcu));
+	struct clusterip_config *config;
+	struct net_device *dev;
+
+	config = container_of(head, struct clusterip_config, rcu);
+	dev = dev_get_by_name(config->net, config->ifname);
+	if (dev) {
+		dev_mc_del(dev, config->clustermac);
+		dev_put(dev);
+	}
+	kfree(config);
 }
 
 static inline void
@@ -101,9 +112,9 @@ clusterip_config_put(struct clusterip_config *c)
  * entry(rule) is removed, remove the config from lists, but don't free it
  * yet, since proc-files could still be holding references */
 static inline void
-clusterip_config_entry_put(struct net *net, struct clusterip_config *c)
+clusterip_config_entry_put(struct clusterip_config *c)
 {
-	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
+	struct clusterip_net *cn = clusterip_pernet(c->net);
 
 	local_bh_disable();
 	if (refcount_dec_and_lock(&c->entries, &cn->lock)) {
@@ -118,8 +129,6 @@ clusterip_config_entry_put(struct net *net, struct clusterip_config *c)
 		spin_unlock(&cn->lock);
 		local_bh_enable();
 
-		unregister_netdevice_notifier(&c->notifier);
-
 		return;
 	}
 	local_bh_enable();
@@ -129,7 +138,7 @@ static struct clusterip_config *
 __clusterip_config_find(struct net *net, __be32 clusterip)
 {
 	struct clusterip_config *c;
-	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
+	struct clusterip_net *cn = clusterip_pernet(net);
 
 	list_for_each_entry_rcu(c, &cn->configs, list) {
 		if (c->clusterip == clusterip)
@@ -181,32 +190,37 @@ clusterip_netdev_event(struct notifier_block *this, unsigned long event,
 		       void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(dev);
+	struct clusterip_net *cn = clusterip_pernet(net);
 	struct clusterip_config *c;
 
-	c = container_of(this, struct clusterip_config, notifier);
-	switch (event) {
-	case NETDEV_REGISTER:
-		if (!strcmp(dev->name, c->ifname)) {
-			c->ifindex = dev->ifindex;
-			dev_mc_add(dev, c->clustermac);
-		}
-		break;
-	case NETDEV_UNREGISTER:
-		if (dev->ifindex == c->ifindex) {
-			dev_mc_del(dev, c->clustermac);
-			c->ifindex = -1;
-		}
-		break;
-	case NETDEV_CHANGENAME:
-		if (!strcmp(dev->name, c->ifname)) {
-			c->ifindex = dev->ifindex;
-			dev_mc_add(dev, c->clustermac);
-		} else if (dev->ifindex == c->ifindex) {
-			dev_mc_del(dev, c->clustermac);
-			c->ifindex = -1;
+	spin_lock_bh(&cn->lock);
+	list_for_each_entry_rcu(c, &cn->configs, list) {
+		switch (event) {
+		case NETDEV_REGISTER:
+			if (!strcmp(dev->name, c->ifname)) {
+				c->ifindex = dev->ifindex;
+				dev_mc_add(dev, c->clustermac);
+			}
+			break;
+		case NETDEV_UNREGISTER:
+			if (dev->ifindex == c->ifindex) {
+				dev_mc_del(dev, c->clustermac);
+				c->ifindex = -1;
+			}
+			break;
+		case NETDEV_CHANGENAME:
+			if (!strcmp(dev->name, c->ifname)) {
+				c->ifindex = dev->ifindex;
+				dev_mc_add(dev, c->clustermac);
+			} else if (dev->ifindex == c->ifindex) {
+				dev_mc_del(dev, c->clustermac);
+				c->ifindex = -1;
+			}
+			break;
 		}
-		break;
 	}
+	spin_unlock_bh(&cn->lock);
 
 	return NOTIFY_DONE;
 }
@@ -215,30 +229,44 @@ static struct clusterip_config *
 clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i,
 		      __be32 ip, const char *iniface)
 {
-	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
+	struct clusterip_net *cn = clusterip_pernet(net);
 	struct clusterip_config *c;
+	struct net_device *dev;
 	int err;
 
+	if (iniface[0] == '\0') {
+		pr_info("Please specify an interface name\n");
+		return ERR_PTR(-EINVAL);
+	}
+
 	c = kzalloc(sizeof(*c), GFP_ATOMIC);
 	if (!c)
 		return ERR_PTR(-ENOMEM);
 
-	strcpy(c->ifname, iniface);
-	c->ifindex = -1;
-	c->clusterip = ip;
+	dev = dev_get_by_name(net, iniface);
+	if (!dev) {
+		pr_info("no such interface %s\n", iniface);
+		kfree(c);
+		return ERR_PTR(-ENOENT);
+	}
+	c->ifindex = dev->ifindex;
+	strcpy(c->ifname, dev->name);
 	memcpy(&c->clustermac, &i->clustermac, ETH_ALEN);
+	dev_mc_add(dev, c->clustermac);
+	dev_put(dev);
+
+	c->clusterip = ip;
 	c->num_total_nodes = i->num_total_nodes;
 	clusterip_config_init_nodelist(c, i);
 	c->hash_mode = i->hash_mode;
 	c->hash_initval = i->hash_initval;
+	c->net = net;
 	refcount_set(&c->refcount, 1);
 
 	spin_lock_bh(&cn->lock);
 	if (__clusterip_config_find(net, ip)) {
-		spin_unlock_bh(&cn->lock);
-		kfree(c);
-
-		return ERR_PTR(-EBUSY);
+		err = -EBUSY;
+		goto out_config_put;
 	}
 
 	list_add_rcu(&c->list, &cn->configs);
@@ -260,22 +288,17 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i,
 	}
 #endif
 
-	c->notifier.notifier_call = clusterip_netdev_event;
-	err = register_netdevice_notifier(&c->notifier);
-	if (!err) {
-		refcount_set(&c->entries, 1);
-		return c;
-	}
+	refcount_set(&c->entries, 1);
+	return c;
 
 #ifdef CONFIG_PROC_FS
-	proc_remove(c->pde);
 err:
 #endif
 	spin_lock_bh(&cn->lock);
 	list_del_rcu(&c->list);
+out_config_put:
 	spin_unlock_bh(&cn->lock);
 	clusterip_config_put(c);
-
 	return ERR_PTR(err);
 }
 
@@ -475,21 +498,6 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
 				&e->ip.dst.s_addr);
 			return -EINVAL;
 		} else {
-			struct net_device *dev;
-
-			if (e->ip.iniface[0] == '\0') {
-				pr_info("Please specify an interface name\n");
-				return -EINVAL;
-			}
-
-			dev = dev_get_by_name(par->net, e->ip.iniface);
-			if (!dev) {
-				pr_info("no such interface %s\n",
-					e->ip.iniface);
-				return -ENOENT;
-			}
-			dev_put(dev);
-
 			config = clusterip_config_init(par->net, cipinfo,
 						       e->ip.dst.s_addr,
 						       e->ip.iniface);
@@ -502,7 +510,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
 	if (ret < 0) {
 		pr_info("cannot load conntrack support for proto=%u\n",
 			par->family);
-		clusterip_config_entry_put(par->net, config);
+		clusterip_config_entry_put(config);
 		clusterip_config_put(config);
 		return ret;
 	}
@@ -524,7 +532,7 @@ static void clusterip_tg_destroy(const struct xt_tgdtor_param *par)
 
 	/* if no more entries are referencing the config, remove it
 	 * from the list and destroy the proc entry */
-	clusterip_config_entry_put(par->net, cipinfo->config);
+	clusterip_config_entry_put(cipinfo->config);
 
 	clusterip_config_put(cipinfo->config);
 
@@ -806,7 +814,7 @@ static const struct file_operations clusterip_proc_fops = {
 
 static int clusterip_net_init(struct net *net)
 {
-	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
+	struct clusterip_net *cn = clusterip_pernet(net);
 	int ret;
 
 	INIT_LIST_HEAD(&cn->configs);
@@ -831,7 +839,7 @@ static int clusterip_net_init(struct net *net)
 
 static void clusterip_net_exit(struct net *net)
 {
-	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
+	struct clusterip_net *cn = clusterip_pernet(net);
 #ifdef CONFIG_PROC_FS
 	proc_remove(cn->procdir);
 	cn->procdir = NULL;
@@ -847,6 +855,10 @@ static struct pernet_operations clusterip_net_ops = {
 	.size = sizeof(struct clusterip_net),
 };
 
+struct notifier_block cip_netdev_notifier = {
+	.notifier_call = clusterip_netdev_event
+};
+
 static int __init clusterip_tg_init(void)
 {
 	int ret;
@@ -859,11 +871,17 @@ static int __init clusterip_tg_init(void)
 	if (ret < 0)
 		goto cleanup_subsys;
 
+	ret = register_netdevice_notifier(&cip_netdev_notifier);
+	if (ret < 0)
+		goto unregister_target;
+
 	pr_info("ClusterIP Version %s loaded successfully\n",
 		CLUSTERIP_VERSION);
 
 	return 0;
 
+unregister_target:
+	xt_unregister_target(&clusterip_tg_reg);
 cleanup_subsys:
 	unregister_pernet_subsys(&clusterip_net_ops);
 	return ret;
@@ -873,6 +891,7 @@ static void __exit clusterip_tg_exit(void)
 {
 	pr_info("ClusterIP Version %s unloading\n", CLUSTERIP_VERSION);
 
+	unregister_netdevice_notifier(&cip_netdev_notifier);
 	xt_unregister_target(&clusterip_tg_reg);
 	unregister_pernet_subsys(&clusterip_net_ops);
 
-- 
cgit v1.2.3


From b12f7bad5ad3724d19754390a3e80928525c0769 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 5 Nov 2018 18:22:55 +0900
Subject: netfilter: ipt_CLUSTERIP: remove wrong WARN_ON_ONCE in netns exit
 routine

When network namespace is destroyed, both clusterip_tg_destroy() and
clusterip_net_exit() are called. and clusterip_net_exit() is called
before clusterip_tg_destroy().
Hence cleanup check code in clusterip_net_exit() doesn't make sense.

test commands:
   %ip netns add vm1
   %ip netns exec vm1 bash
   %ip link set lo up
   %iptables -A INPUT -p tcp -i lo -d 192.168.0.5 --dport 80 \
	-j CLUSTERIP --new --hashmode sourceip \
	--clustermac 01:00:5e:00:00:20 --total-nodes 2 --local-node 1
   %exit
   %ip netns del vm1

splat looks like:
[  341.184508] WARNING: CPU: 1 PID: 87 at net/ipv4/netfilter/ipt_CLUSTERIP.c:840 clusterip_net_exit+0x319/0x380 [ipt_CLUSTERIP]
[  341.184850] Modules linked in: ipt_CLUSTERIP nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_tcpudp iptable_filter bpfilter ip_tables x_tables
[  341.184850] CPU: 1 PID: 87 Comm: kworker/u4:2 Not tainted 4.19.0-rc5+ #16
[  341.227509] Workqueue: netns cleanup_net
[  341.227509] RIP: 0010:clusterip_net_exit+0x319/0x380 [ipt_CLUSTERIP]
[  341.227509] Code: 0f 85 7f fe ff ff 48 c7 c2 80 64 2c c0 be a8 02 00 00 48 c7 c7 a0 63 2c c0 c6 05 18 6e 00 00 01 e8 bc 38 ff f5 e9 5b fe ff ff <0f> 0b e9 33 ff ff ff e8 4b 90 50 f6 e9 2d fe ff ff 48 89 df e8 de
[  341.227509] RSP: 0018:ffff88011086f408 EFLAGS: 00010202
[  341.227509] RAX: dffffc0000000000 RBX: 1ffff1002210de85 RCX: 0000000000000000
[  341.227509] RDX: 1ffff1002210de85 RSI: ffff880110813be8 RDI: ffffed002210de58
[  341.227509] RBP: ffff88011086f4d0 R08: 0000000000000000 R09: 0000000000000000
[  341.227509] R10: 0000000000000000 R11: 0000000000000000 R12: 1ffff1002210de81
[  341.227509] R13: ffff880110625a48 R14: ffff880114cec8c8 R15: 0000000000000014
[  341.227509] FS:  0000000000000000(0000) GS:ffff880116600000(0000) knlGS:0000000000000000
[  341.227509] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  341.227509] CR2: 00007f11fd38e000 CR3: 000000013ca16000 CR4: 00000000001006e0
[  341.227509] Call Trace:
[  341.227509]  ? __clusterip_config_find+0x460/0x460 [ipt_CLUSTERIP]
[  341.227509]  ? default_device_exit+0x1ca/0x270
[  341.227509]  ? remove_proc_entry+0x1cd/0x390
[  341.227509]  ? dev_change_net_namespace+0xd00/0xd00
[  341.227509]  ? __init_waitqueue_head+0x130/0x130
[  341.227509]  ops_exit_list.isra.10+0x94/0x140
[  341.227509]  cleanup_net+0x45b/0x900
[ ... ]

Fixes: 613d0776d3fe ("netfilter: exit_net cleanup check added")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/ipt_CLUSTERIP.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 091d163d215b..ddf9a878932a 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -845,7 +845,6 @@ static void clusterip_net_exit(struct net *net)
 	cn->procdir = NULL;
 #endif
 	nf_unregister_net_hook(net, &cip_arp_ops);
-	WARN_ON_ONCE(!list_empty(&cn->configs));
 }
 
 static struct pernet_operations clusterip_net_ops = {
-- 
cgit v1.2.3


From 2a61d8b883bbad26b06d2e6cc3777a697e78830d Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 5 Nov 2018 18:23:13 +0900
Subject: netfilter: ipt_CLUSTERIP: fix sleep-in-atomic bug in
 clusterip_config_entry_put()

A proc_remove() can sleep. so that it can't be inside of spin_lock.
Hence proc_remove() is moved to outside of spin_lock. and it also
adds mutex to sync create and remove of proc entry(config->pde).

test commands:
SHELL#1
   %while :; do iptables -A INPUT -p udp -i enp2s0 -d 192.168.1.100 \
	   --dport 9000  -j CLUSTERIP --new --hashmode sourceip \
	   --clustermac 01:00:5e:00:00:21 --total-nodes 3 --local-node 3; \
	   iptables -F; done

SHELL#2
   %while :; do echo +1 > /proc/net/ipt_CLUSTERIP/192.168.1.100; \
	   echo -1 > /proc/net/ipt_CLUSTERIP/192.168.1.100; done

[ 2949.569864] BUG: sleeping function called from invalid context at kernel/sched/completion.c:99
[ 2949.579944] in_atomic(): 1, irqs_disabled(): 0, pid: 5472, name: iptables
[ 2949.587920] 1 lock held by iptables/5472:
[ 2949.592711]  #0: 000000008f0ebcf2 (&(&cn->lock)->rlock){+...}, at: refcount_dec_and_lock+0x24/0x50
[ 2949.603307] CPU: 1 PID: 5472 Comm: iptables Tainted: G        W         4.19.0-rc5+ #16
[ 2949.604212] Hardware name: To be filled by O.E.M. To be filled by O.E.M./Aptio CRB, BIOS 5.6.5 07/08/2015
[ 2949.604212] Call Trace:
[ 2949.604212]  dump_stack+0xc9/0x16b
[ 2949.604212]  ? show_regs_print_info+0x5/0x5
[ 2949.604212]  ___might_sleep+0x2eb/0x420
[ 2949.604212]  ? set_rq_offline.part.87+0x140/0x140
[ 2949.604212]  ? _rcu_barrier_trace+0x400/0x400
[ 2949.604212]  wait_for_completion+0x94/0x710
[ 2949.604212]  ? wait_for_completion_interruptible+0x780/0x780
[ 2949.604212]  ? __kernel_text_address+0xe/0x30
[ 2949.604212]  ? __lockdep_init_map+0x10e/0x5c0
[ 2949.604212]  ? __lockdep_init_map+0x10e/0x5c0
[ 2949.604212]  ? __init_waitqueue_head+0x86/0x130
[ 2949.604212]  ? init_wait_entry+0x1a0/0x1a0
[ 2949.604212]  proc_entry_rundown+0x208/0x270
[ 2949.604212]  ? proc_reg_get_unmapped_area+0x370/0x370
[ 2949.604212]  ? __lock_acquire+0x4500/0x4500
[ 2949.604212]  ? complete+0x18/0x70
[ 2949.604212]  remove_proc_subtree+0x143/0x2a0
[ 2949.708655]  ? remove_proc_entry+0x390/0x390
[ 2949.708655]  clusterip_tg_destroy+0x27a/0x630 [ipt_CLUSTERIP]
[ ... ]

Fixes: b3e456fce9f5 ("netfilter: ipt_CLUSTERIP: fix a race condition of proc file creation")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/ipt_CLUSTERIP.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index ddf9a878932a..d4d549a46c04 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -56,7 +56,7 @@ struct clusterip_config {
 #endif
 	enum clusterip_hashmode hash_mode;	/* which hashing mode */
 	u_int32_t hash_initval;			/* hash initialization */
-	struct rcu_head rcu;
+	struct rcu_head rcu;			/* for call_rcu_bh */
 	struct net *net;			/* netns for pernet list */
 	char ifname[IFNAMSIZ];			/* device ifname */
 };
@@ -72,6 +72,8 @@ struct clusterip_net {
 
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry *procdir;
+	/* mutex protects the config->pde*/
+	struct mutex mutex;
 #endif
 };
 
@@ -118,17 +120,18 @@ clusterip_config_entry_put(struct clusterip_config *c)
 
 	local_bh_disable();
 	if (refcount_dec_and_lock(&c->entries, &cn->lock)) {
+		list_del_rcu(&c->list);
+		spin_unlock(&cn->lock);
+		local_bh_enable();
 		/* In case anyone still accesses the file, the open/close
 		 * functions are also incrementing the refcount on their own,
 		 * so it's safe to remove the entry even if it's in use. */
 #ifdef CONFIG_PROC_FS
+		mutex_lock(&cn->mutex);
 		if (cn->procdir)
 			proc_remove(c->pde);
+		mutex_unlock(&cn->mutex);
 #endif
-		list_del_rcu(&c->list);
-		spin_unlock(&cn->lock);
-		local_bh_enable();
-
 		return;
 	}
 	local_bh_enable();
@@ -278,9 +281,11 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i,
 
 		/* create proc dir entry */
 		sprintf(buffer, "%pI4", &ip);
+		mutex_lock(&cn->mutex);
 		c->pde = proc_create_data(buffer, 0600,
 					  cn->procdir,
 					  &clusterip_proc_fops, c);
+		mutex_unlock(&cn->mutex);
 		if (!c->pde) {
 			err = -ENOMEM;
 			goto err;
@@ -832,6 +837,7 @@ static int clusterip_net_init(struct net *net)
 		pr_err("Unable to proc dir entry\n");
 		return -ENOMEM;
 	}
+	mutex_init(&cn->mutex);
 #endif /* CONFIG_PROC_FS */
 
 	return 0;
@@ -840,9 +846,12 @@ static int clusterip_net_init(struct net *net)
 static void clusterip_net_exit(struct net *net)
 {
 	struct clusterip_net *cn = clusterip_pernet(net);
+
 #ifdef CONFIG_PROC_FS
+	mutex_lock(&cn->mutex);
 	proc_remove(cn->procdir);
 	cn->procdir = NULL;
+	mutex_unlock(&cn->mutex);
 #endif
 	nf_unregister_net_hook(net, &cip_arp_ops);
 }
-- 
cgit v1.2.3


From 06aa151ad1fc74a49b45336672515774a678d78d Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 5 Nov 2018 18:23:25 +0900
Subject: netfilter: ipt_CLUSTERIP: check MAC address when duplicate config is
 set

If same destination IP address config is already existing, that config is
just used. MAC address also should be same.
However, there is no MAC address checking routine.
So that MAC address checking routine is added.

test commands:
   %iptables -A INPUT -p tcp -i lo -d 192.168.0.5 --dport 80 \
	   -j CLUSTERIP --new --hashmode sourceip \
	   --clustermac 01:00:5e:00:00:20 --total-nodes 2 --local-node 1
   %iptables -A INPUT -p tcp -i lo -d 192.168.0.5 --dport 80 \
	   -j CLUSTERIP --new --hashmode sourceip \
	   --clustermac 01:00:5e:00:00:21 --total-nodes 2 --local-node 1

After this patch, above commands are disallowed.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/ipt_CLUSTERIP.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index d4d549a46c04..b61977db9b7f 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -509,7 +509,8 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
 			if (IS_ERR(config))
 				return PTR_ERR(config);
 		}
-	}
+	} else if (memcmp(&config->clustermac, &cipinfo->clustermac, ETH_ALEN))
+		return -EINVAL;
 
 	ret = nf_ct_netns_get(par->net, par->family);
 	if (ret < 0) {
-- 
cgit v1.2.3


From 11789039da536fea96c98a40c2b441decf2e7323 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Tue, 18 Dec 2018 00:13:17 +0100
Subject: fou: Prevent unbounded recursion in GUE error handler

Handling exceptions for direct UDP encapsulation in GUE (that is,
UDP-in-UDP) leads to unbounded recursion in the GUE exception handler,
syzbot reported.

While draft-ietf-intarea-gue-06 doesn't explicitly forbid direct
encapsulation of UDP in GUE, it probably doesn't make sense to set up GUE
this way, and it's currently not even possible to configure this.

Skip exception handling if the GUE proto/ctype field is set to the UDP
protocol number. Should we need to handle exceptions for UDP-in-GUE one
day, we might need to either explicitly set a bound for recursion, or
implement a special iterative handling for these cases.

Reported-and-tested-by: syzbot+43f6755d1c2e62743468@syzkaller.appspotmail.com
Fixes: b8a51b38e4d4 ("fou, fou6: ICMP error handlers for FoU and GUE")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fou.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 0d0ad19ecb87..0c9f171fb085 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -1061,6 +1061,13 @@ static int gue_err(struct sk_buff *skb, u32 info)
 	if (validate_gue_flags(guehdr, optlen))
 		return -EINVAL;
 
+	/* Handling exceptions for direct UDP encapsulation in GUE would lead to
+	 * recursion. Besides, this kind of encapsulation can't even be
+	 * configured currently. Discard this.
+	 */
+	if (guehdr->proto_ctype == IPPROTO_UDP)
+		return -EOPNOTSUPP;
+
 	skb_set_transport_header(skb, -(int)sizeof(struct icmphdr));
 	ret = gue_err_proto_handler(guehdr->proto_ctype, skb, info);
 
-- 
cgit v1.2.3


From f7588cd89331211e2c4f0fdb94bb0ed4f92847be Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:19 -0500
Subject: bnxt_en: Store the maximum NQs available on the PF.

The PF has a pool of NQs and MSIX vectors assigned to it based on
NVRAM configurations.  The number of usable MSIX vectors on the PF
is the minimum of the NQs and MSIX vectors.  Any excess NQs without
associated MSIX may be used for the VFs, so we need to store this
max_nqs value.  max_nqs minus the NQs used by the PF will be the
available NQs for the VFs.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 ++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 +
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8a2e9cdd38ee..c65b5fe41abd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6221,7 +6221,7 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 	if (bp->flags & BNXT_FLAG_CHIP_P5) {
 		u16 max_msix = le16_to_cpu(resp->max_msix);
 
-		hw_resc->max_irqs = min_t(u16, hw_resc->max_irqs, max_msix);
+		hw_resc->max_nqs = max_msix;
 		hw_resc->max_hw_ring_grps = hw_resc->max_rx_rings;
 	}
 
@@ -7059,6 +7059,9 @@ static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
+	if (bp->flags & BNXT_FLAG_CHIP_P5)
+		return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_nqs);
+
 	return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_cp_rings);
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 3030931ccaf8..d45cbb488e9d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -927,6 +927,7 @@ struct bnxt_hw_resc {
 	u16	resv_vnics;
 	u16	min_stat_ctxs;
 	u16	max_stat_ctxs;
+	u16	max_nqs;
 	u16	max_irqs;
 	u16	resv_irqs;
 };
-- 
cgit v1.2.3


From e916b0815a11c6cbc82f2d8510982ea022628880 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:20 -0500
Subject: bnxt_en: Add bnxt_get_avail_cp_rings_for_en() helper function.

The available CP rings are calculated differently on the new 57500
chips, so add this helper to do this calculation correctly.  The
VFs will be assigned these available CP rings.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c       | 13 ++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h       |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c |  7 +++----
 3 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c65b5fe41abd..bf228cf10bb3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7045,7 +7045,7 @@ unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp)
 	return bp->hw_resc.max_cp_rings;
 }
 
-unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp)
+static unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp)
 {
 	unsigned int cp = bp->hw_resc.max_cp_rings;
 
@@ -7070,6 +7070,17 @@ static void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
 	bp->hw_resc.max_irqs = max_irqs;
 }
 
+unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp)
+{
+	unsigned int cp;
+
+	cp = bnxt_get_max_func_cp_rings_for_en(bp);
+	if (bp->flags & BNXT_FLAG_CHIP_P5)
+		return cp - bp->rx_nr_rings - bp->tx_nr_rings;
+	else
+		return cp - bp->cp_nr_rings;
+}
+
 int bnxt_get_avail_msix(struct bnxt *bp, int num)
 {
 	int max_cp = bnxt_get_max_func_cp_rings(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index d45cbb488e9d..adce7fb37148 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1691,7 +1691,7 @@ int bnxt_hwrm_set_coal(struct bnxt *);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
 void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
-unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp);
+unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp);
 int bnxt_get_avail_msix(struct bnxt *bp, int num);
 int bnxt_reserve_rings(struct bnxt *bp);
 void bnxt_tx_disable(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 3962f6fd543c..5a09f03b23e1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -451,7 +451,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1);
 
-	vf_cp_rings = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings;
+	vf_cp_rings = bnxt_get_avail_cp_rings_for_en(bp);
 	vf_stat_ctx = hw_resc->max_stat_ctxs - bp->num_stat_ctxs;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = hw_resc->max_rx_rings - bp->rx_nr_rings * 2;
@@ -549,8 +549,7 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 	max_stat_ctxs = hw_resc->max_stat_ctxs;
 
 	/* Remaining rings are distributed equally amongs VF's for now */
-	vf_cp_rings = (bnxt_get_max_func_cp_rings_for_en(bp) -
-		       bp->cp_nr_rings) / num_vfs;
+	vf_cp_rings = bnxt_get_avail_cp_rings_for_en(bp) / num_vfs;
 	vf_stat_ctx = (max_stat_ctxs - bp->num_stat_ctxs) / num_vfs;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = (hw_resc->max_rx_rings - bp->rx_nr_rings * 2) /
@@ -644,7 +643,7 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 	 */
 	vfs_supported = *num_vfs;
 
-	avail_cp = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings;
+	avail_cp = bnxt_get_avail_cp_rings_for_en(bp);
 	avail_stat = hw_resc->max_stat_ctxs - bp->num_stat_ctxs;
 	avail_cp = min_t(int, avail_cp, avail_stat);
 
-- 
cgit v1.2.3


From c027c6b4e91f21dfa4feab91e2155c8403f49f5c Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:21 -0500
Subject: bnxt_en: get rid of num_stat_ctxs variable

For bnxt_en driver, stat_ctxs created will always be same as
cp_nr_rings. Remove extra variable that duplicates the value.
Also introduce bnxt_get_avail_stat_ctxs_for_en() helper to get
available stat_ctxs and bnxt_get_ulp_stat_ctxs() helper to return
number of stat_ctxs used by RDMA.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 14 ++++++++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |  3 +--
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c |  2 --
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c   | 10 ++++------
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c     | 10 +++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h     |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c     |  1 -
 7 files changed, 25 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index bf228cf10bb3..8d6c811b5428 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7081,6 +7081,15 @@ unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp)
 		return cp - bp->cp_nr_rings;
 }
 
+unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp)
+{
+	unsigned int stat;
+
+	stat = bnxt_get_max_func_stat_ctxs(bp) - bnxt_get_ulp_stat_ctxs(bp);
+	stat -= bp->cp_nr_rings;
+	return stat;
+}
+
 int bnxt_get_avail_msix(struct bnxt *bp, int num)
 {
 	int max_cp = bnxt_get_max_func_cp_rings(bp);
@@ -7242,7 +7251,6 @@ int bnxt_reserve_rings(struct bnxt *bp)
 		bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
 		return -ENOMEM;
 	}
-	bp->num_stat_ctxs = bp->cp_nr_rings;
 	return 0;
 }
 
@@ -9309,7 +9317,6 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
 	bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
 			       bp->tx_nr_rings + bp->rx_nr_rings;
-	bp->num_stat_ctxs = bp->cp_nr_rings;
 
 	if (netif_running(bp->dev))
 		return bnxt_open_nic(bp, true, false);
@@ -9849,7 +9856,7 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 	*max_cp = bnxt_get_max_func_cp_rings_for_en(bp);
 	max_irq = min_t(int, bnxt_get_max_func_irqs(bp) -
 			bnxt_get_ulp_msix_num(bp),
-			bnxt_get_max_func_stat_ctxs(bp));
+			hw_resc->max_stat_ctxs - bnxt_get_ulp_stat_ctxs(bp));
 	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
 		*max_cp = min_t(int, *max_cp, max_irq);
 	max_ring_grps = hw_resc->max_hw_ring_grps;
@@ -9980,7 +9987,6 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 			netdev_warn(bp->dev, "2nd rings reservation failed.\n");
 		bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
 	}
-	bp->num_stat_ctxs = bp->cp_nr_rings;
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		bp->rx_nr_rings++;
 		bp->cp_nr_rings++;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index adce7fb37148..df9a80973258 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1417,8 +1417,6 @@ struct bnxt {
 	int			cp_nr_pages;
 	int			cp_nr_rings;
 
-	int			num_stat_ctxs;
-
 	/* grp_info indexed by completion ring index */
 	struct bnxt_ring_grp_info	*grp_info;
 	struct bnxt_vnic_info	*vnic_info;
@@ -1690,6 +1688,7 @@ int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings);
 int bnxt_hwrm_set_coal(struct bnxt *);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
 void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
+unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
 unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp);
 int bnxt_get_avail_msix(struct bnxt *bp, int num);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 6cc69a58478a..5a746aed7f3c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -663,8 +663,6 @@ static int bnxt_set_channels(struct net_device *dev,
 	bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
 			       bp->tx_nr_rings + bp->rx_nr_rings;
 
-	bp->num_stat_ctxs = bp->cp_nr_rings;
-
 	/* After changing number of rx channels, update NTUPLE feature. */
 	netdev_update_features(dev);
 	if (netif_running(dev)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 5a09f03b23e1..e7fdcb289072 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -452,7 +452,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1);
 
 	vf_cp_rings = bnxt_get_avail_cp_rings_for_en(bp);
-	vf_stat_ctx = hw_resc->max_stat_ctxs - bp->num_stat_ctxs;
+	vf_stat_ctx = bnxt_get_avail_stat_ctxs_for_en(bp);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = hw_resc->max_rx_rings - bp->rx_nr_rings * 2;
 	else
@@ -539,18 +539,16 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 	u32 rc = 0, mtu, i;
 	u16 vf_tx_rings, vf_rx_rings, vf_cp_rings, vf_stat_ctx, vf_vnics;
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
-	u16 vf_ring_grps, max_stat_ctxs;
 	struct hwrm_func_cfg_input req = {0};
 	struct bnxt_pf_info *pf = &bp->pf;
 	int total_vf_tx_rings = 0;
+	u16 vf_ring_grps;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 
-	max_stat_ctxs = hw_resc->max_stat_ctxs;
-
 	/* Remaining rings are distributed equally amongs VF's for now */
 	vf_cp_rings = bnxt_get_avail_cp_rings_for_en(bp) / num_vfs;
-	vf_stat_ctx = (max_stat_ctxs - bp->num_stat_ctxs) / num_vfs;
+	vf_stat_ctx = bnxt_get_avail_stat_ctxs_for_en(bp) / num_vfs;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = (hw_resc->max_rx_rings - bp->rx_nr_rings * 2) /
 			      num_vfs;
@@ -644,7 +642,7 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 	vfs_supported = *num_vfs;
 
 	avail_cp = bnxt_get_avail_cp_rings_for_en(bp);
-	avail_stat = hw_resc->max_stat_ctxs - bp->num_stat_ctxs;
+	avail_stat = bnxt_get_avail_stat_ctxs_for_en(bp);
 	avail_cp = min_t(int, avail_cp, avail_stat);
 
 	while (vfs_supported) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 0a3097baafde..8ef71a001ebc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -48,7 +48,7 @@ static int bnxt_register_dev(struct bnxt_en_dev *edev, int ulp_id,
 
 		max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp);
 		if (max_stat_ctxs <= BNXT_MIN_ROCE_STAT_CTXS ||
-		    bp->num_stat_ctxs == max_stat_ctxs)
+		    bp->cp_nr_rings == max_stat_ctxs)
 			return -ENOMEM;
 		bnxt_set_max_func_stat_ctxs(bp, max_stat_ctxs -
 					    BNXT_MIN_ROCE_STAT_CTXS);
@@ -218,6 +218,14 @@ int bnxt_get_ulp_msix_base(struct bnxt *bp)
 	return 0;
 }
 
+int bnxt_get_ulp_stat_ctxs(struct bnxt *bp)
+{
+	if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP))
+		return BNXT_MIN_ROCE_STAT_CTXS;
+
+	return 0;
+}
+
 static int bnxt_send_msg(struct bnxt_en_dev *edev, int ulp_id,
 			 struct bnxt_fw_msg *fw_msg)
 {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index d9bea37cd211..cd78453d0bf0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -90,6 +90,7 @@ static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev, int ulp_id)
 
 int bnxt_get_ulp_msix_num(struct bnxt *bp);
 int bnxt_get_ulp_msix_base(struct bnxt *bp);
+int bnxt_get_ulp_stat_ctxs(struct bnxt *bp);
 void bnxt_ulp_stop(struct bnxt *bp);
 void bnxt_ulp_start(struct bnxt *bp);
 void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index bf6de02be396..0184ef6f05a7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -199,7 +199,6 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	bp->tx_nr_rings_xdp = tx_xdp;
 	bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp;
 	bp->cp_nr_rings = max_t(int, bp->tx_nr_rings, bp->rx_nr_rings);
-	bp->num_stat_ctxs = bp->cp_nr_rings;
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
 
-- 
cgit v1.2.3


From f4e896142de8304b433fd94f7eed55750c34defd Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:22 -0500
Subject: bnxt_en: Do not modify max_stat_ctxs after RDMA driver requests/frees
 stat_ctxs

Calling bnxt_set_max_func_stat_ctxs() to modify max stat_ctxs requested
or freed by the RDMA driver is wrong. After introducing reservation of
resources recently, the driver has to keep track of all stat_ctxs
including the ones used by the RDMA driver.  This will provide a better
foundation for accurate accounting of the stat_ctxs.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     |  5 -----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  1 -
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 11 ++---------
 3 files changed, 2 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8d6c811b5428..a3410e5efe96 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7035,11 +7035,6 @@ unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp)
 	return bp->hw_resc.max_stat_ctxs;
 }
 
-void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max)
-{
-	bp->hw_resc.max_stat_ctxs = max;
-}
-
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp)
 {
 	return bp->hw_resc.max_cp_rings;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index df9a80973258..4f4dfe8e227a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1687,7 +1687,6 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id);
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings);
 int bnxt_hwrm_set_coal(struct bnxt *);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
-void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
 unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
 unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 8ef71a001ebc..ea45a9b8179e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -50,8 +50,6 @@ static int bnxt_register_dev(struct bnxt_en_dev *edev, int ulp_id,
 		if (max_stat_ctxs <= BNXT_MIN_ROCE_STAT_CTXS ||
 		    bp->cp_nr_rings == max_stat_ctxs)
 			return -ENOMEM;
-		bnxt_set_max_func_stat_ctxs(bp, max_stat_ctxs -
-					    BNXT_MIN_ROCE_STAT_CTXS);
 	}
 
 	atomic_set(&ulp->ref_count, 0);
@@ -82,14 +80,9 @@ static int bnxt_unregister_dev(struct bnxt_en_dev *edev, int ulp_id)
 		netdev_err(bp->dev, "ulp id %d not registered\n", ulp_id);
 		return -EINVAL;
 	}
-	if (ulp_id == BNXT_ROCE_ULP) {
-		unsigned int max_stat_ctxs;
+	if (ulp_id == BNXT_ROCE_ULP && ulp->msix_requested)
+		edev->en_ops->bnxt_free_msix(edev, ulp_id);
 
-		max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp);
-		bnxt_set_max_func_stat_ctxs(bp, max_stat_ctxs + 1);
-		if (ulp->msix_requested)
-			edev->en_ops->bnxt_free_msix(edev, ulp_id);
-	}
 	if (ulp->max_async_event_id)
 		bnxt_hwrm_func_rgtr_async_events(bp, NULL, 0);
 
-- 
cgit v1.2.3


From 780baad44f0f1e87df5508d1ad5a87d359fb96d1 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:23 -0500
Subject: bnxt_en: Reserve 1 stat_ctx for RDMA driver.

bnxt_en requires same number of stat_ctxs as CP rings but RDMA
requires only 1 stat_ctx.  Also add a new parameter resv_stat_ctxs
to better keep track of stat_ctxs reserved including resources used
by RDMA.  Add a stat_ctxs parameter to all the relevant resource
reservation functions so we can reserve the correct number of
stat_ctxs.

Prior to this patch, we were not reserving the extra stat_ctx for
RDMA and RDMA would not work on the new 57500 chips.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 79 ++++++++++++++++++++-----------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 52 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a3410e5efe96..7722df2cd7ea 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5161,7 +5161,6 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 		hw_resc->resv_vnics = le16_to_cpu(resp->alloc_vnics);
 		cp = le16_to_cpu(resp->alloc_cmpl_rings);
 		stats = le16_to_cpu(resp->alloc_stat_ctx);
-		cp = min_t(u16, cp, stats);
 		hw_resc->resv_irqs = cp;
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
 			int rx = hw_resc->resv_rx_rings;
@@ -5180,6 +5179,7 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 			hw_resc->resv_hw_ring_grps = rx;
 		}
 		hw_resc->resv_cp_rings = cp;
+		hw_resc->resv_stat_ctxs = stats;
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return 0;
@@ -5209,7 +5209,7 @@ static bool bnxt_rfs_supported(struct bnxt *bp);
 static void
 __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 			     int tx_rings, int rx_rings, int ring_grps,
-			     int cp_rings, int vnics)
+			     int cp_rings, int stats, int vnics)
 {
 	u32 enables = 0;
 
@@ -5251,7 +5251,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 				req->num_rsscos_ctxs =
 					cpu_to_le16(ring_grps + 1);
 		}
-		req->num_stat_ctxs = req->num_cmpl_rings;
+		req->num_stat_ctxs = cpu_to_le16(stats);
 		req->num_vnics = cpu_to_le16(vnics);
 	}
 	req->enables = cpu_to_le32(enables);
@@ -5261,7 +5261,7 @@ static void
 __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 			     struct hwrm_func_vf_cfg_input *req, int tx_rings,
 			     int rx_rings, int ring_grps, int cp_rings,
-			     int vnics)
+			     int stats, int vnics)
 {
 	u32 enables = 0;
 
@@ -5294,7 +5294,7 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 		req->num_hw_ring_grps = cpu_to_le16(ring_grps);
 		req->num_rsscos_ctxs = cpu_to_le16(BNXT_VF_MAX_RSS_CTX);
 	}
-	req->num_stat_ctxs = req->num_cmpl_rings;
+	req->num_stat_ctxs = cpu_to_le16(stats);
 	req->num_vnics = cpu_to_le16(vnics);
 
 	req->enables = cpu_to_le32(enables);
@@ -5302,13 +5302,13 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 
 static int
 bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
-			   int ring_grps, int cp_rings, int vnics)
+			   int ring_grps, int cp_rings, int stats, int vnics)
 {
 	struct hwrm_func_cfg_input req = {0};
 	int rc;
 
 	__bnxt_hwrm_reserve_pf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, vnics);
+				     cp_rings, stats, vnics);
 	if (!req.enables)
 		return 0;
 
@@ -5325,7 +5325,7 @@ bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 
 static int
 bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
-			   int ring_grps, int cp_rings, int vnics)
+			   int ring_grps, int cp_rings, int stats, int vnics)
 {
 	struct hwrm_func_vf_cfg_input req = {0};
 	int rc;
@@ -5336,7 +5336,7 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	}
 
 	__bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, vnics);
+				     cp_rings, stats, vnics);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
 		return -ENOMEM;
@@ -5346,12 +5346,14 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 }
 
 static int bnxt_hwrm_reserve_rings(struct bnxt *bp, int tx, int rx, int grp,
-				   int cp, int vnic)
+				   int cp, int stat, int vnic)
 {
 	if (BNXT_PF(bp))
-		return bnxt_hwrm_reserve_pf_rings(bp, tx, rx, grp, cp, vnic);
+		return bnxt_hwrm_reserve_pf_rings(bp, tx, rx, grp, cp, stat,
+						  vnic);
 	else
-		return bnxt_hwrm_reserve_vf_rings(bp, tx, rx, grp, cp, vnic);
+		return bnxt_hwrm_reserve_vf_rings(bp, tx, rx, grp, cp, stat,
+						  vnic);
 }
 
 static int bnxt_nq_rings_in_use(struct bnxt *bp)
@@ -5380,12 +5382,17 @@ static int bnxt_cp_rings_in_use(struct bnxt *bp)
 	return cp;
 }
 
+static int bnxt_get_func_stat_ctxs(struct bnxt *bp)
+{
+	return bp->cp_nr_rings + bnxt_get_ulp_stat_ctxs(bp);
+}
+
 static bool bnxt_need_reserve_rings(struct bnxt *bp)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 	int cp = bnxt_cp_rings_in_use(bp);
 	int nq = bnxt_nq_rings_in_use(bp);
-	int rx = bp->rx_nr_rings;
+	int rx = bp->rx_nr_rings, stat;
 	int vnic = 1, grp = rx;
 
 	if (bp->hwrm_spec_code < 0x10601)
@@ -5398,9 +5405,11 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp)
 		vnic = rx + 1;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
+	stat = bnxt_get_func_stat_ctxs(bp);
 	if (BNXT_NEW_RM(bp) &&
 	    (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp ||
 	     hw_resc->resv_irqs < nq || hw_resc->resv_vnics != vnic ||
+	     hw_resc->resv_stat_ctxs != stat ||
 	     (hw_resc->resv_hw_ring_grps != grp &&
 	      !(bp->flags & BNXT_FLAG_CHIP_P5))))
 		return true;
@@ -5414,8 +5423,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	int tx = bp->tx_nr_rings;
 	int rx = bp->rx_nr_rings;
 	int grp, rx_rings, rc;
+	int vnic = 1, stat;
 	bool sh = false;
-	int vnic = 1;
 
 	if (!bnxt_need_reserve_rings(bp))
 		return 0;
@@ -5427,8 +5436,9 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
 	grp = bp->rx_nr_rings;
+	stat = bnxt_get_func_stat_ctxs(bp);
 
-	rc = bnxt_hwrm_reserve_rings(bp, tx, rx, grp, cp, vnic);
+	rc = bnxt_hwrm_reserve_rings(bp, tx, rx, grp, cp, stat, vnic);
 	if (rc)
 		return rc;
 
@@ -5438,6 +5448,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		cp = hw_resc->resv_irqs;
 		grp = hw_resc->resv_hw_ring_grps;
 		vnic = hw_resc->resv_vnics;
+		stat = hw_resc->resv_stat_ctxs;
 	}
 
 	rx_rings = rx;
@@ -5456,6 +5467,10 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		}
 	}
 	rx_rings = min_t(int, rx_rings, grp);
+	cp = min_t(int, cp, bp->cp_nr_rings);
+	if (stat > bnxt_get_ulp_stat_ctxs(bp))
+		stat -= bnxt_get_ulp_stat_ctxs(bp);
+	cp = min_t(int, cp, stat);
 	rc = bnxt_trim_rings(bp, &rx_rings, &tx, cp, sh);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx = rx_rings << 1;
@@ -5464,14 +5479,15 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	bp->rx_nr_rings = rx_rings;
 	bp->cp_nr_rings = cp;
 
-	if (!tx || !rx || !cp || !grp || !vnic)
+	if (!tx || !rx || !cp || !grp || !vnic || !stat)
 		return -ENOMEM;
 
 	return rc;
 }
 
 static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
-				    int ring_grps, int cp_rings, int vnics)
+				    int ring_grps, int cp_rings, int stats,
+				    int vnics)
 {
 	struct hwrm_func_vf_cfg_input req = {0};
 	u32 flags;
@@ -5481,7 +5497,7 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 		return 0;
 
 	__bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, vnics);
+				     cp_rings, stats, vnics);
 	flags = FUNC_VF_CFG_REQ_FLAGS_TX_ASSETS_TEST |
 		FUNC_VF_CFG_REQ_FLAGS_RX_ASSETS_TEST |
 		FUNC_VF_CFG_REQ_FLAGS_CMPL_ASSETS_TEST |
@@ -5499,14 +5515,15 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 }
 
 static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
-				    int ring_grps, int cp_rings, int vnics)
+				    int ring_grps, int cp_rings, int stats,
+				    int vnics)
 {
 	struct hwrm_func_cfg_input req = {0};
 	u32 flags;
 	int rc;
 
 	__bnxt_hwrm_reserve_pf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, vnics);
+				     cp_rings, stats, vnics);
 	flags = FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST;
 	if (BNXT_NEW_RM(bp)) {
 		flags |= FUNC_CFG_REQ_FLAGS_RX_ASSETS_TEST |
@@ -5527,17 +5544,19 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 }
 
 static int bnxt_hwrm_check_rings(struct bnxt *bp, int tx_rings, int rx_rings,
-				 int ring_grps, int cp_rings, int vnics)
+				 int ring_grps, int cp_rings, int stats,
+				 int vnics)
 {
 	if (bp->hwrm_spec_code < 0x10801)
 		return 0;
 
 	if (BNXT_PF(bp))
 		return bnxt_hwrm_check_pf_rings(bp, tx_rings, rx_rings,
-						ring_grps, cp_rings, vnics);
+						ring_grps, cp_rings, stats,
+						vnics);
 
 	return bnxt_hwrm_check_vf_rings(bp, tx_rings, rx_rings, ring_grps,
-					cp_rings, vnics);
+					cp_rings, stats, vnics);
 }
 
 static void bnxt_hwrm_coal_params_qcaps(struct bnxt *bp)
@@ -7839,6 +7858,7 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 
 		rc = bnxt_hwrm_func_resc_qcaps(bp, true);
 		hw_resc->resv_cp_rings = 0;
+		hw_resc->resv_stat_ctxs = 0;
 		hw_resc->resv_irqs = 0;
 		hw_resc->resv_tx_rings = 0;
 		hw_resc->resv_rx_rings = 0;
@@ -8644,12 +8664,12 @@ static bool bnxt_rfs_capable(struct bnxt *bp)
 	if (vnics == bp->hw_resc.resv_vnics)
 		return true;
 
-	bnxt_hwrm_reserve_rings(bp, 0, 0, 0, 0, vnics);
+	bnxt_hwrm_reserve_rings(bp, 0, 0, 0, 0, 0, vnics);
 	if (vnics <= bp->hw_resc.resv_vnics)
 		return true;
 
 	netdev_warn(bp->dev, "Unable to reserve resources to support NTUPLE filters.\n");
-	bnxt_hwrm_reserve_rings(bp, 0, 0, 0, 0, 1);
+	bnxt_hwrm_reserve_rings(bp, 0, 0, 0, 0, 0, 1);
 	return false;
 #else
 	return false;
@@ -9060,7 +9080,7 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		     int tx_xdp)
 {
 	int max_rx, max_tx, tx_sets = 1;
-	int tx_rings_needed;
+	int tx_rings_needed, stats;
 	int rx_rings = rx;
 	int cp, vnics, rc;
 
@@ -9085,10 +9105,13 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx_rings <<= 1;
 	cp = sh ? max_t(int, tx_rings_needed, rx) : tx_rings_needed + rx;
-	if (BNXT_NEW_RM(bp))
+	stats = cp;
+	if (BNXT_NEW_RM(bp)) {
 		cp += bnxt_get_ulp_msix_num(bp);
+		stats += bnxt_get_ulp_stat_ctxs(bp);
+	}
 	return bnxt_hwrm_check_rings(bp, tx_rings_needed, rx_rings, rx, cp,
-				     vnics);
+				     stats, vnics);
 }
 
 static void bnxt_unmap_bars(struct bnxt *bp, struct pci_dev *pdev)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 4f4dfe8e227a..71e353363a1d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -927,6 +927,7 @@ struct bnxt_hw_resc {
 	u16	resv_vnics;
 	u16	min_stat_ctxs;
 	u16	max_stat_ctxs;
+	u16	resv_stat_ctxs;
 	u16	max_nqs;
 	u16	max_irqs;
 	u16	resv_irqs;
-- 
cgit v1.2.3


From 36d65be9a88052cdfc8524eb591baf0e6c878408 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:24 -0500
Subject: bnxt_en: Disable MSIX before re-reserving NQs/CMPL rings.

When bringing up a device, the code checks to see if the number of
MSIX has changed.  pci_disable_msix() should be called first before
changing the number of reserved NQs/CMPL rings.  This ensures that
the MSIX vectors associated with the NQs/CMPL rings are still
properly mapped when pci_disable_msix() masks the vectors.

This patch will prevent errors when RDMA support is added for the new
57500 chips.  When the RDMA driver shuts down, the number of NQs is
decreased and we must use the new sequence to prevent MSIX errors.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7722df2cd7ea..313a940bd50c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7241,23 +7241,26 @@ static void bnxt_clear_int_mode(struct bnxt *bp)
 int bnxt_reserve_rings(struct bnxt *bp)
 {
 	int tcs = netdev_get_num_tc(bp->dev);
+	bool reinit_irq = false;
 	int rc;
 
 	if (!bnxt_need_reserve_rings(bp))
 		return 0;
 
-	rc = __bnxt_reserve_rings(bp);
-	if (rc) {
-		netdev_err(bp->dev, "ring reservation failure rc: %d\n", rc);
-		return rc;
-	}
 	if (BNXT_NEW_RM(bp) && (bnxt_get_num_msix(bp) != bp->total_irqs)) {
 		bnxt_ulp_irq_stop(bp);
 		bnxt_clear_int_mode(bp);
-		rc = bnxt_init_int_mode(bp);
+		reinit_irq = true;
+	}
+	rc = __bnxt_reserve_rings(bp);
+	if (reinit_irq) {
+		if (!rc)
+			rc = bnxt_init_int_mode(bp);
 		bnxt_ulp_irq_restart(bp, rc);
-		if (rc)
-			return rc;
+	}
+	if (rc) {
+		netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc);
+		return rc;
 	}
 	if (tcs && (bp->tx_nr_rings_per_tc * tcs != bp->tx_nr_rings)) {
 		netdev_err(bp->dev, "tx ring reservation failure\n");
-- 
cgit v1.2.3


From b16b68918674af5e7beccb567fe7ebd8b44744b8 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:25 -0500
Subject: bnxt_en: Add SR-IOV support for 57500 chips.

There are some minor differences when assigning VF resources on the
new chips.  The MSIX (NQ) resource has to be assigned and ring group
is not needed on the new chips.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c       |  7 +++++--
 drivers/net/ethernet/broadcom/bnxt/bnxt.h       |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 15 +++++++++++++--
 3 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 313a940bd50c..6f407a6f9432 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -118,6 +118,7 @@ enum board_idx {
 	NETXTREME_E_VF,
 	NETXTREME_C_VF,
 	NETXTREME_S_VF,
+	NETXTREME_E_P5_VF,
 };
 
 /* indexed by enum above */
@@ -160,6 +161,7 @@ static const struct {
 	[NETXTREME_E_VF] = { "Broadcom NetXtreme-E Ethernet Virtual Function" },
 	[NETXTREME_C_VF] = { "Broadcom NetXtreme-C Ethernet Virtual Function" },
 	[NETXTREME_S_VF] = { "Broadcom NetXtreme-S Ethernet Virtual Function" },
+	[NETXTREME_E_P5_VF] = { "Broadcom BCM5750X NetXtreme-E Ethernet Virtual Function" },
 };
 
 static const struct pci_device_id bnxt_pci_tbl[] = {
@@ -210,6 +212,7 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16dc), .driver_data = NETXTREME_E_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16e1), .driver_data = NETXTREME_C_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16e5), .driver_data = NETXTREME_C_VF },
+	{ PCI_VDEVICE(BROADCOM, 0x1807), .driver_data = NETXTREME_E_P5_VF },
 	{ PCI_VDEVICE(BROADCOM, 0xd800), .driver_data = NETXTREME_S_VF },
 #endif
 	{ 0 }
@@ -237,7 +240,7 @@ static struct workqueue_struct *bnxt_pf_wq;
 static bool bnxt_vf_pciid(enum board_idx idx)
 {
 	return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF ||
-		idx == NETXTREME_S_VF);
+		idx == NETXTREME_S_VF || idx == NETXTREME_E_P5_VF);
 }
 
 #define DB_CP_REARM_FLAGS	(DB_KEY_CP | DB_IDX_VALID)
@@ -5356,7 +5359,7 @@ static int bnxt_hwrm_reserve_rings(struct bnxt *bp, int tx, int rx, int grp,
 						  vnic);
 }
 
-static int bnxt_nq_rings_in_use(struct bnxt *bp)
+int bnxt_nq_rings_in_use(struct bnxt *bp)
 {
 	int cp = bp->cp_nr_rings;
 	int ulp_msix, ulp_base;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 71e353363a1d..fdc600cd5da7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1686,6 +1686,7 @@ int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
 				     int bmap_size);
 int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id);
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings);
+int bnxt_nq_rings_in_use(struct bnxt *bp);
 int bnxt_hwrm_set_coal(struct bnxt *);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
 unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index e7fdcb289072..d80f5c981d90 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -448,16 +448,22 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 	u16 vf_stat_ctx, vf_vnics, vf_ring_grps;
 	struct bnxt_pf_info *pf = &bp->pf;
 	int i, rc = 0, min = 1;
+	u16 vf_msix = 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1);
 
+	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		vf_msix = hw_resc->max_nqs - bnxt_nq_rings_in_use(bp);
+		vf_ring_grps = 0;
+	} else {
+		vf_ring_grps = hw_resc->max_hw_ring_grps - bp->rx_nr_rings;
+	}
 	vf_cp_rings = bnxt_get_avail_cp_rings_for_en(bp);
 	vf_stat_ctx = bnxt_get_avail_stat_ctxs_for_en(bp);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = hw_resc->max_rx_rings - bp->rx_nr_rings * 2;
 	else
 		vf_rx_rings = hw_resc->max_rx_rings - bp->rx_nr_rings;
-	vf_ring_grps = hw_resc->max_hw_ring_grps - bp->rx_nr_rings;
 	vf_tx_rings = hw_resc->max_tx_rings - bp->tx_nr_rings;
 	vf_vnics = hw_resc->max_vnics - bp->nr_vnics;
 	vf_vnics = min_t(u16, vf_vnics, vf_rx_rings);
@@ -476,7 +482,8 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 		req.min_l2_ctxs = cpu_to_le16(min);
 		req.min_vnics = cpu_to_le16(min);
 		req.min_stat_ctx = cpu_to_le16(min);
-		req.min_hw_ring_grps = cpu_to_le16(min);
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+			req.min_hw_ring_grps = cpu_to_le16(min);
 	} else {
 		vf_cp_rings /= num_vfs;
 		vf_tx_rings /= num_vfs;
@@ -500,6 +507,8 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 	req.max_vnics = cpu_to_le16(vf_vnics);
 	req.max_stat_ctx = cpu_to_le16(vf_stat_ctx);
 	req.max_hw_ring_grps = cpu_to_le16(vf_ring_grps);
+	if (bp->flags & BNXT_FLAG_CHIP_P5)
+		req.max_msix = cpu_to_le16(vf_msix / num_vfs);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	for (i = 0; i < num_vfs; i++) {
@@ -525,6 +534,8 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 		hw_resc->max_rsscos_ctxs -= pf->active_vfs;
 		hw_resc->max_stat_ctxs -= le16_to_cpu(req.min_stat_ctx) * n;
 		hw_resc->max_vnics -= le16_to_cpu(req.min_vnics) * n;
+		if (bp->flags & BNXT_FLAG_CHIP_P5)
+			hw_resc->max_irqs -= vf_msix * n;
 
 		rc = pf->active_vfs;
 	}
-- 
cgit v1.2.3


From e37fed790335631c57477e7bee952a039ccb7a50 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:26 -0500
Subject: bnxt_en: Add ethtool -S priority counters.

Display the CoS counters as additional priority counters by looking up
the priority to CoS queue mapping.  If the TX extended port statistics
block size returned by firmware is big enough to cover the CoS counters,
then we will display the new priority counters.  We call firmware to get
the up-to-date pri2cos mapping to convert the CoS counters to
priority counters.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         |  29 ++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |   2 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 114 +++++++++++++++++++++-
 3 files changed, 144 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6f407a6f9432..a57f4409153b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6511,6 +6511,7 @@ static int bnxt_hwrm_port_qstats(struct bnxt *bp)
 static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 {
 	struct hwrm_port_qstats_ext_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_queue_pri2cos_qcfg_input req2 = {0};
 	struct hwrm_port_qstats_ext_input req = {0};
 	struct bnxt_pf_info *pf = &bp->pf;
 	int rc;
@@ -6533,6 +6534,34 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 		bp->fw_rx_stats_ext_size = 0;
 		bp->fw_tx_stats_ext_size = 0;
 	}
+	if (bp->fw_tx_stats_ext_size <=
+	    offsetof(struct tx_port_stats_ext, pfc_pri0_tx_duration_us) / 8) {
+		mutex_unlock(&bp->hwrm_cmd_lock);
+		bp->pri2cos_valid = 0;
+		return rc;
+	}
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req2, HWRM_QUEUE_PRI2COS_QCFG, -1, -1);
+	req2.flags = cpu_to_le32(QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN);
+
+	rc = _hwrm_send_message(bp, &req2, sizeof(req2), HWRM_CMD_TIMEOUT);
+	if (!rc) {
+		struct hwrm_queue_pri2cos_qcfg_output *resp2;
+		u8 *pri2cos;
+		int i, j;
+
+		resp2 = bp->hwrm_cmd_resp_addr;
+		pri2cos = &resp2->pri0_cos_queue_id;
+		for (i = 0; i < 8; i++) {
+			u8 queue_id = pri2cos[i];
+
+			for (j = 0; j < bp->max_q; j++) {
+				if (bp->q_ids[j] == queue_id)
+					bp->pri2cos[i] = j;
+			}
+		}
+		bp->pri2cos_valid = 1;
+	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index fdc600cd5da7..3c6a39d99f1f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1483,6 +1483,8 @@ struct bnxt {
 	int			hw_port_stats_size;
 	u16			fw_rx_stats_ext_size;
 	u16			fw_tx_stats_ext_size;
+	u8			pri2cos[8];
+	u8			pri2cos_valid;
 
 	u16			hwrm_max_req_len;
 	u16			hwrm_max_ext_req_len;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 5a746aed7f3c..475b4792c7bb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -207,6 +207,34 @@ reset_coalesce:
 	BNXT_TX_STATS_EXT_COS_ENTRY(6),				\
 	BNXT_TX_STATS_EXT_COS_ENTRY(7)				\
 
+#define BNXT_RX_STATS_PRI_ENTRY(counter, n)		\
+	{ BNXT_RX_STATS_EXT_OFFSET(counter##_cos0),	\
+	  __stringify(counter##_pri##n) }
+
+#define BNXT_TX_STATS_PRI_ENTRY(counter, n)		\
+	{ BNXT_TX_STATS_EXT_OFFSET(counter##_cos0),	\
+	  __stringify(counter##_pri##n) }
+
+#define BNXT_RX_STATS_PRI_ENTRIES(counter)		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 0),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 1),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 2),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 3),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 4),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 5),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 6),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 7)
+
+#define BNXT_TX_STATS_PRI_ENTRIES(counter)		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 0),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 1),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 2),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 3),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 4),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 5),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 6),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 7)
+
 enum {
 	RX_TOTAL_DISCARDS,
 	TX_TOTAL_DISCARDS,
@@ -327,8 +355,41 @@ static const struct {
 	BNXT_TX_STATS_EXT_PFC_ENTRIES,
 };
 
+static const struct {
+	long base_off;
+	char string[ETH_GSTRING_LEN];
+} bnxt_rx_bytes_pri_arr[] = {
+	BNXT_RX_STATS_PRI_ENTRIES(rx_bytes),
+};
+
+static const struct {
+	long base_off;
+	char string[ETH_GSTRING_LEN];
+} bnxt_rx_pkts_pri_arr[] = {
+	BNXT_RX_STATS_PRI_ENTRIES(rx_packets),
+};
+
+static const struct {
+	long base_off;
+	char string[ETH_GSTRING_LEN];
+} bnxt_tx_bytes_pri_arr[] = {
+	BNXT_TX_STATS_PRI_ENTRIES(tx_bytes),
+};
+
+static const struct {
+	long base_off;
+	char string[ETH_GSTRING_LEN];
+} bnxt_tx_pkts_pri_arr[] = {
+	BNXT_TX_STATS_PRI_ENTRIES(tx_packets),
+};
+
 #define BNXT_NUM_SW_FUNC_STATS	ARRAY_SIZE(bnxt_sw_func_stats)
 #define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr)
+#define BNXT_NUM_STATS_PRI			\
+	(ARRAY_SIZE(bnxt_rx_bytes_pri_arr) +	\
+	 ARRAY_SIZE(bnxt_rx_pkts_pri_arr) +	\
+	 ARRAY_SIZE(bnxt_tx_bytes_pri_arr) +	\
+	 ARRAY_SIZE(bnxt_tx_pkts_pri_arr))
 
 static int bnxt_get_num_stats(struct bnxt *bp)
 {
@@ -339,9 +400,12 @@ static int bnxt_get_num_stats(struct bnxt *bp)
 	if (bp->flags & BNXT_FLAG_PORT_STATS)
 		num_stats += BNXT_NUM_PORT_STATS;
 
-	if (bp->flags & BNXT_FLAG_PORT_STATS_EXT)
+	if (bp->flags & BNXT_FLAG_PORT_STATS_EXT) {
 		num_stats += bp->fw_rx_stats_ext_size +
 			     bp->fw_tx_stats_ext_size;
+		if (bp->pri2cos_valid)
+			num_stats += BNXT_NUM_STATS_PRI;
+	}
 
 	return num_stats;
 }
@@ -415,6 +479,32 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 			buf[j] = le64_to_cpu(*(tx_port_stats_ext +
 					bnxt_tx_port_stats_ext_arr[i].offset));
 		}
+		if (bp->pri2cos_valid) {
+			for (i = 0; i < 8; i++, j++) {
+				long n = bnxt_rx_bytes_pri_arr[i].base_off +
+					 bp->pri2cos[i];
+
+				buf[j] = le64_to_cpu(*(rx_port_stats_ext + n));
+			}
+			for (i = 0; i < 8; i++, j++) {
+				long n = bnxt_rx_pkts_pri_arr[i].base_off +
+					 bp->pri2cos[i];
+
+				buf[j] = le64_to_cpu(*(rx_port_stats_ext + n));
+			}
+			for (i = 0; i < 8; i++, j++) {
+				long n = bnxt_tx_bytes_pri_arr[i].base_off +
+					 bp->pri2cos[i];
+
+				buf[j] = le64_to_cpu(*(tx_port_stats_ext + n));
+			}
+			for (i = 0; i < 8; i++, j++) {
+				long n = bnxt_tx_pkts_pri_arr[i].base_off +
+					 bp->pri2cos[i];
+
+				buf[j] = le64_to_cpu(*(tx_port_stats_ext + n));
+			}
+		}
 	}
 }
 
@@ -493,6 +583,28 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 				       bnxt_tx_port_stats_ext_arr[i].string);
 				buf += ETH_GSTRING_LEN;
 			}
+			if (bp->pri2cos_valid) {
+				for (i = 0; i < 8; i++) {
+					strcpy(buf,
+					       bnxt_rx_bytes_pri_arr[i].string);
+					buf += ETH_GSTRING_LEN;
+				}
+				for (i = 0; i < 8; i++) {
+					strcpy(buf,
+					       bnxt_rx_pkts_pri_arr[i].string);
+					buf += ETH_GSTRING_LEN;
+				}
+				for (i = 0; i < 8; i++) {
+					strcpy(buf,
+					       bnxt_tx_bytes_pri_arr[i].string);
+					buf += ETH_GSTRING_LEN;
+				}
+				for (i = 0; i < 8; i++) {
+					strcpy(buf,
+					       bnxt_tx_pkts_pri_arr[i].string);
+					buf += ETH_GSTRING_LEN;
+				}
+			}
 		}
 		break;
 	case ETH_SS_TEST:
-- 
cgit v1.2.3


From 24654f095ed68eafcdfdbfccbe6324ad1475c1bb Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:27 -0500
Subject: bnxt_en: Don't set ETS on unused TCs.

Currently, the code allows ETS bandwidth weight 0 to be set on unused TCs.
We should not set any DCB parameters on unused TCs at all.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index a85d2be986af..15c7041e937b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -471,7 +471,10 @@ static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 	if (total_ets_bw > 100)
 		return -EINVAL;
 
-	*tc = max_tc + 1;
+	if (max_tc >= bp->max_tc)
+		*tc = bp->max_tc;
+	else
+		*tc = max_tc + 1;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 7c675421afef18253a86ffc383f57bc15ef32ea8 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:28 -0500
Subject: bnxt_en: Return linux standard errors in bnxt_ethtool.c

Currently firmware specific errors are returned directly in flash_device
and reset ethtool hooks. Modify it to return linux standard errors
to userspace when flashing operations fail.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 56 ++++++++++++++++-------
 1 file changed, 39 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 475b4792c7bb..333054caf30c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1636,14 +1636,22 @@ static int bnxt_flash_nvram(struct net_device *dev,
 	rc = hwrm_send_message(bp, &req, sizeof(req), FLASH_NVRAM_TIMEOUT);
 	dma_free_coherent(&bp->pdev->dev, data_len, kmem, dma_handle);
 
+	if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
+		netdev_info(dev,
+			    "PF does not have admin privileges to flash the device\n");
+		rc = -EACCES;
+	} else if (rc) {
+		rc = -EIO;
+	}
 	return rc;
 }
 
 static int bnxt_firmware_reset(struct net_device *dev,
 			       u16 dir_type)
 {
-	struct bnxt *bp = netdev_priv(dev);
 	struct hwrm_fw_reset_input req = {0};
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_RESET, -1, -1);
 
@@ -1683,7 +1691,15 @@ static int bnxt_firmware_reset(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
+		netdev_info(dev,
+			    "PF does not have admin privileges to reset the device\n");
+		rc = -EACCES;
+	} else if (rc) {
+		rc = -EIO;
+	}
+	return rc;
 }
 
 static int bnxt_flash_firmware(struct net_device *dev,
@@ -1890,9 +1906,9 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	struct hwrm_nvm_install_update_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_nvm_install_update_input install = {0};
 	const struct firmware *fw;
+	int rc, hwrm_err = 0;
 	u32 item_len;
 	u16 index;
-	int rc;
 
 	bnxt_hwrm_fw_set_time(bp);
 
@@ -1935,15 +1951,16 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 			memcpy(kmem, fw->data, fw->size);
 			modify.host_src_addr = cpu_to_le64(dma_handle);
 
-			rc = hwrm_send_message(bp, &modify, sizeof(modify),
-					       FLASH_PACKAGE_TIMEOUT);
+			hwrm_err = hwrm_send_message(bp, &modify,
+						     sizeof(modify),
+						     FLASH_PACKAGE_TIMEOUT);
 			dma_free_coherent(&bp->pdev->dev, fw->size, kmem,
 					  dma_handle);
 		}
 	}
 	release_firmware(fw);
-	if (rc)
-		return rc;
+	if (rc || hwrm_err)
+		goto err_exit;
 
 	if ((install_type & 0xffff) == 0)
 		install_type >>= 16;
@@ -1951,12 +1968,10 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	install.install_type = cpu_to_le32(install_type);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &install, sizeof(install),
-				INSTALL_PACKAGE_TIMEOUT);
-	if (rc) {
-		rc = -EOPNOTSUPP;
+	hwrm_err = _hwrm_send_message(bp, &install, sizeof(install),
+				      INSTALL_PACKAGE_TIMEOUT);
+	if (hwrm_err)
 		goto flash_pkg_exit;
-	}
 
 	if (resp->error_code) {
 		u8 error_code = ((struct hwrm_err_output *)resp)->cmd_err;
@@ -1964,12 +1979,11 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 		if (error_code == NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
 			install.flags |= cpu_to_le16(
 			       NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG);
-			rc = _hwrm_send_message(bp, &install, sizeof(install),
-						INSTALL_PACKAGE_TIMEOUT);
-			if (rc) {
-				rc = -EOPNOTSUPP;
+			hwrm_err = _hwrm_send_message(bp, &install,
+						      sizeof(install),
+						      INSTALL_PACKAGE_TIMEOUT);
+			if (hwrm_err)
 				goto flash_pkg_exit;
-			}
 		}
 	}
 
@@ -1980,6 +1994,14 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	}
 flash_pkg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
+err_exit:
+	if (hwrm_err == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
+		netdev_info(dev,
+			    "PF does not have admin privileges to flash the device\n");
+		rc = -EACCES;
+	} else if (hwrm_err) {
+		rc = -EOPNOTSUPP;
+	}
 	return rc;
 }
 
-- 
cgit v1.2.3


From b8875ca356f1c0b17ec68be6666269373a62288e Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:29 -0500
Subject: bnxt_en: Save ring statistics before reset.

With the current driver, the statistics reported by .ndo_get_stats64()
are reset when the device goes down.  Store a snapshot of the
rtnl_link_stats64 before shutdown.  This snapshot is added to the
current counters in .ndo_get_stats64() so that the counters will not
get reset when the device is down.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 57 +++++++++++++++++++++++--------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 44 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a57f4409153b..939c22812e72 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8333,6 +8333,9 @@ static bool bnxt_drv_busy(struct bnxt *bp)
 		test_bit(BNXT_STATE_READ_STATS, &bp->state));
 }
 
+static void bnxt_get_ring_stats(struct bnxt *bp,
+				struct rtnl_link_stats64 *stats);
+
 static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 			     bool link_re_init)
 {
@@ -8358,6 +8361,9 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	del_timer_sync(&bp->timer);
 	bnxt_free_skbs(bp);
 
+	/* Save ring stats before shutdown */
+	if (bp->bnapi)
+		bnxt_get_ring_stats(bp, &bp->net_stats_prev);
 	if (irq_re_init) {
 		bnxt_free_irq(bp);
 		bnxt_del_napi(bp);
@@ -8419,23 +8425,12 @@ static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return -EOPNOTSUPP;
 }
 
-static void
-bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+static void bnxt_get_ring_stats(struct bnxt *bp,
+				struct rtnl_link_stats64 *stats)
 {
-	u32 i;
-	struct bnxt *bp = netdev_priv(dev);
+	int i;
 
-	set_bit(BNXT_STATE_READ_STATS, &bp->state);
-	/* Make sure bnxt_close_nic() sees that we are reading stats before
-	 * we check the BNXT_STATE_OPEN flag.
-	 */
-	smp_mb__after_atomic();
-	if (!test_bit(BNXT_STATE_OPEN, &bp->state)) {
-		clear_bit(BNXT_STATE_READ_STATS, &bp->state);
-		return;
-	}
 
-	/* TODO check if we need to synchronize with bnxt_close path */
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
@@ -8464,6 +8459,40 @@ bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 
 		stats->tx_dropped += le64_to_cpu(hw_stats->tx_drop_pkts);
 	}
+}
+
+static void bnxt_add_prev_stats(struct bnxt *bp,
+				struct rtnl_link_stats64 *stats)
+{
+	struct rtnl_link_stats64 *prev_stats = &bp->net_stats_prev;
+
+	stats->rx_packets += prev_stats->rx_packets;
+	stats->tx_packets += prev_stats->tx_packets;
+	stats->rx_bytes += prev_stats->rx_bytes;
+	stats->tx_bytes += prev_stats->tx_bytes;
+	stats->rx_missed_errors += prev_stats->rx_missed_errors;
+	stats->multicast += prev_stats->multicast;
+	stats->tx_dropped += prev_stats->tx_dropped;
+}
+
+static void
+bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	set_bit(BNXT_STATE_READ_STATS, &bp->state);
+	/* Make sure bnxt_close_nic() sees that we are reading stats before
+	 * we check the BNXT_STATE_OPEN flag.
+	 */
+	smp_mb__after_atomic();
+	if (!test_bit(BNXT_STATE_OPEN, &bp->state)) {
+		clear_bit(BNXT_STATE_READ_STATS, &bp->state);
+		*stats = bp->net_stats_prev;
+		return;
+	}
+
+	bnxt_get_ring_stats(bp, stats);
+	bnxt_add_prev_stats(bp, stats);
 
 	if (bp->flags & BNXT_FLAG_PORT_STATS) {
 		struct rx_port_stats *rx = bp->hw_rx_port_stats;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 3c6a39d99f1f..4fdfd7a87805 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1472,6 +1472,7 @@ struct bnxt {
 	void			*hwrm_cmd_resp_addr;
 	dma_addr_t		hwrm_cmd_resp_dma_addr;
 
+	struct rtnl_link_stats64	net_stats_prev;
 	struct rx_port_stats	*hw_rx_port_stats;
 	struct tx_port_stats	*hw_tx_port_stats;
 	struct rx_port_stats_ext	*hw_rx_port_stats_ext;
-- 
cgit v1.2.3


From fd3ab1c70e0b953f4f772142051d215bffada718 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:30 -0500
Subject: bnxt_en: Do not free port statistics buffer when device is down.

Port statistics which include RDMA counters are useful even when the
netdevice is down.  Do not free the port statistics DMA buffers
when the netdevice is down.  This is keep the snapshot of the port
statistics and counters will just continue counting when the
netdevice goes back up.

Split the bnxt_free_stats() function into 2 functions.  The port
statistics buffers will only be freed when the netdevice is
removed.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 23 ++++++++++++++++++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c |  7 +++++--
 2 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 939c22812e72..218a6dff3efc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3320,9 +3320,8 @@ static int bnxt_alloc_hwrm_short_cmd_req(struct bnxt *bp)
 	return 0;
 }
 
-static void bnxt_free_stats(struct bnxt *bp)
+static void bnxt_free_port_stats(struct bnxt *bp)
 {
-	u32 size, i;
 	struct pci_dev *pdev = bp->pdev;
 
 	bp->flags &= ~BNXT_FLAG_PORT_STATS;
@@ -3348,6 +3347,12 @@ static void bnxt_free_stats(struct bnxt *bp)
 				  bp->hw_rx_port_stats_ext_map);
 		bp->hw_rx_port_stats_ext = NULL;
 	}
+}
+
+static void bnxt_free_ring_stats(struct bnxt *bp)
+{
+	struct pci_dev *pdev = bp->pdev;
+	int size, i;
 
 	if (!bp->bnapi)
 		return;
@@ -3387,6 +3392,9 @@ static int bnxt_alloc_stats(struct bnxt *bp)
 	}
 
 	if (BNXT_PF(bp) && bp->chip_num != CHIP_NUM_58700) {
+		if (bp->hw_rx_port_stats)
+			goto alloc_ext_stats;
+
 		bp->hw_port_stats_size = sizeof(struct rx_port_stats) +
 					 sizeof(struct tx_port_stats) + 1024;
 
@@ -3403,11 +3411,15 @@ static int bnxt_alloc_stats(struct bnxt *bp)
 					   sizeof(struct rx_port_stats) + 512;
 		bp->flags |= BNXT_FLAG_PORT_STATS;
 
+alloc_ext_stats:
 		/* Display extended statistics only if FW supports it */
 		if (bp->hwrm_spec_code < 0x10804 ||
 		    bp->hwrm_spec_code == 0x10900)
 			return 0;
 
+		if (bp->hw_rx_port_stats_ext)
+			goto alloc_tx_ext_stats;
+
 		bp->hw_rx_port_stats_ext =
 			dma_zalloc_coherent(&pdev->dev,
 					    sizeof(struct rx_port_stats_ext),
@@ -3416,6 +3428,10 @@ static int bnxt_alloc_stats(struct bnxt *bp)
 		if (!bp->hw_rx_port_stats_ext)
 			return 0;
 
+alloc_tx_ext_stats:
+		if (bp->hw_tx_port_stats_ext)
+			return 0;
+
 		if (bp->hwrm_spec_code >= 0x10902) {
 			bp->hw_tx_port_stats_ext =
 				dma_zalloc_coherent(&pdev->dev,
@@ -3523,7 +3539,7 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init)
 	bnxt_free_cp_rings(bp);
 	bnxt_free_ntp_fltrs(bp, irq_re_init);
 	if (irq_re_init) {
-		bnxt_free_stats(bp);
+		bnxt_free_ring_stats(bp);
 		bnxt_free_ring_grps(bp);
 		bnxt_free_vnics(bp);
 		kfree(bp->tx_ring_map);
@@ -9864,6 +9880,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	kfree(bp->ctx);
 	bp->ctx = NULL;
 	bnxt_cleanup_pci(bp);
+	bnxt_free_port_stats(bp);
 	free_netdev(dev);
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 333054caf30c..14e9b73bbfa9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -433,8 +433,10 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 	struct bnxt *bp = netdev_priv(dev);
 	u32 stat_fields = sizeof(struct ctx_hw_stats) / 8;
 
-	if (!bp->bnapi)
-		return;
+	if (!bp->bnapi) {
+		j += BNXT_NUM_STATS * bp->cp_nr_rings + BNXT_NUM_SW_FUNC_STATS;
+		goto skip_ring_stats;
+	}
 
 	for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++)
 		bnxt_sw_func_stats[i].counter = 0;
@@ -459,6 +461,7 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 	for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++, j++)
 		buf[j] = bnxt_sw_func_stats[i].counter;
 
+skip_ring_stats:
 	if (bp->flags & BNXT_FLAG_PORT_STATS) {
 		__le64 *port_stats = (__le64 *)bp->hw_rx_port_stats;
 
-- 
cgit v1.2.3


From 56d374624778652d2a999e18c87a25338b127b41 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 16 Dec 2018 18:46:31 -0500
Subject: bnxt_en: query force speeds before disabling autoneg mode.

With autoneg enabled, PHY loopback test fails. To disable autoneg,
driver needs to send a valid forced speed to FW. FW is not sending
async event for invalid speeds. To fix this, query forced speeds
and send the correct speed when disabling autoneg mode.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 14e9b73bbfa9..997775777dbe 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2585,17 +2585,37 @@ static int bnxt_hwrm_mac_loopback(struct bnxt *bp, bool enable)
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 }
 
+static int bnxt_query_force_speeds(struct bnxt *bp, u16 *force_speeds)
+{
+	struct hwrm_port_phy_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_port_phy_qcaps_input req = {0};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_QCAPS, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*force_speeds = le16_to_cpu(resp->supported_speeds_force_mode);
+
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
 static int bnxt_disable_an_for_lpbk(struct bnxt *bp,
 				    struct hwrm_port_phy_cfg_input *req)
 {
 	struct bnxt_link_info *link_info = &bp->link_info;
-	u16 fw_advertising = link_info->advertising;
+	u16 fw_advertising;
 	u16 fw_speed;
 	int rc;
 
 	if (!link_info->autoneg)
 		return 0;
 
+	rc = bnxt_query_force_speeds(bp, &fw_advertising);
+	if (rc)
+		return rc;
+
 	fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB;
 	if (netif_carrier_ok(bp->dev))
 		fw_speed = bp->link_info.link_speed;
-- 
cgit v1.2.3


From eedbbb0d98b2a89250a8bb83d9c71b77881e5247 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Sun, 16 Dec 2018 15:42:48 -0800
Subject: net: dccp: initialize (addr,port) listening hashtable

Commit d9fbc7f6431f "net: tcp: prefer listeners bound to an address"
removes port-only listener lookups. This caused segfaults in DCCP
lookups because DCCP did not initialize the (addr,port) hashtable.

This patch adds said initialization.

The only non-trivial issue here is the size of the new hashtable.
It seemed reasonable to make it match the size of the port-only
hashtable (= INET_LHTABLE_SIZE) that was used previously. Other
parameters to inet_hashinfo2_init() match those used in TCP.

V2 changes: marked inet_hashinfo2_init as an exported symbol
so that DCCP compiles when configured as a module.

Tested: syzcaller issues fixed; the second patch in the patchset
        tests that DCCP lookups work correctly.

Fixes: d9fbc7f6431f "net: tcp: prefer listeners bound to an address"
Reported-by: syzcaller <syzkaller@googlegroups.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c           | 3 +++
 net/ipv4/inet_hashtables.c | 1 +
 2 files changed, 4 insertions(+)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 658cd32bb7b3..be0b223aa862 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1141,6 +1141,9 @@ static int __init dccp_init(void)
 		goto out_fail;
 	rc = -ENOBUFS;
 	inet_hashinfo_init(&dccp_hashinfo);
+	inet_hashinfo2_init(&dccp_hashinfo, "dccp_listen_portaddr_hash",
+			    INET_LHTABLE_SIZE, 21,  /* one slot per 2 MB*/
+			    0, 64 * 1024);
 	dccp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("dccp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index cd03ab42705b..2445614de6a7 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -785,6 +785,7 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
 		h->lhash2[i].count = 0;
 	}
 }
+EXPORT_SYMBOL_GPL(inet_hashinfo2_init);
 
 int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
 {
-- 
cgit v1.2.3


From 6e0735d1f7e573da0976d8b7447a82b09d8ec949 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 17 Dec 2018 15:34:48 -0800
Subject: ipmr: Drop mfc_cache argument to ipmr_queue_xmit

mfc_cache is not needed by ipmr_queue_xmit so drop it from the input
argument list.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index ea04e38f56e9..75c654924532 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1820,8 +1820,7 @@ static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt,
 /* Processing handlers for ipmr_forward */
 
 static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
-			    int in_vifi, struct sk_buff *skb,
-			    struct mfc_cache *c, int vifi)
+			    int in_vifi, struct sk_buff *skb, int vifi)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct vif_device *vif = &mrt->vif_table[vifi];
@@ -2027,7 +2026,7 @@ forward:
 
 				if (skb2)
 					ipmr_queue_xmit(net, mrt, true_vifi,
-							skb2, c, psend);
+							skb2, psend);
 			}
 			psend = ct;
 		}
@@ -2039,9 +2038,9 @@ last_forward:
 
 			if (skb2)
 				ipmr_queue_xmit(net, mrt, true_vifi, skb2,
-						c, psend);
+						psend);
 		} else {
-			ipmr_queue_xmit(net, mrt, true_vifi, skb, c, psend);
+			ipmr_queue_xmit(net, mrt, true_vifi, skb, psend);
 			return;
 		}
 	}
-- 
cgit v1.2.3


From f5c6dfdefb21708aa0f382c1dc36d4e82c6c3ed5 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 17 Dec 2018 15:36:11 -0800
Subject: ip6mr: Drop mfc6_cache argument to ip6mr_forward2

mfc6_cache is not needed by ip6mr_forward2 so drop it from the input
argument list.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 8c63494400c4..34b8a90e6be2 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1968,7 +1968,7 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct
  */
 
 static int ip6mr_forward2(struct net *net, struct mr_table *mrt,
-			  struct sk_buff *skb, struct mfc6_cache *c, int vifi)
+			  struct sk_buff *skb, int vifi)
 {
 	struct ipv6hdr *ipv6h;
 	struct vif_device *vif = &mrt->vif_table[vifi];
@@ -2134,15 +2134,14 @@ forward:
 			if (psend != -1) {
 				struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 				if (skb2)
-					ip6mr_forward2(net, mrt, skb2,
-						       c, psend);
+					ip6mr_forward2(net, mrt, skb2, psend);
 			}
 			psend = ct;
 		}
 	}
 last_forward:
 	if (psend != -1) {
-		ip6mr_forward2(net, mrt, skb, c, psend);
+		ip6mr_forward2(net, mrt, skb, psend);
 		return;
 	}
 
-- 
cgit v1.2.3


From d1675a16029610505895b60fc3e96c9dbac02d97 Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Tue, 18 Dec 2018 07:31:31 +0000
Subject: mlxsw: spectrum: Update the supported firmware to version 13.1910.622

This new firmware contains:
 * New packet traps for discarded packets
 * Secure firmware flash bug fix
 * Fence mechanism bug fix
 * TCAM RMA bug fix

Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 5fbb4b75f472..eb8db9fae237 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -45,8 +45,8 @@
 #define MLXSW_SP_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
 
 #define MLXSW_SP1_FWREV_MAJOR 13
-#define MLXSW_SP1_FWREV_MINOR 1703
-#define MLXSW_SP1_FWREV_SUBMINOR 4
+#define MLXSW_SP1_FWREV_MINOR 1910
+#define MLXSW_SP1_FWREV_SUBMINOR 622
 #define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702
 
 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
-- 
cgit v1.2.3


From b12c97d45cd061862b79fe02aa41a73d685ec7a1 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Mon, 17 Dec 2018 19:18:39 -0800
Subject: nfp: flower: fix cb_ident duplicate in indirect block register

Previously the identifier used for indirect block callback registry and
for block rule cb registry (when done via indirect blocks) was the pointer
to the netdev we were interested in receiving updates on. This worked fine
if a single app existed that registered one callback per netdev of
interest. However, if multiple cards are in place and, in turn, multiple
apps, then each app may register the same callback with the same
identifier to both the netdev's indirect block cb list and to a block's cb
list. This can lead to EEXIST errors and/or incorrect cb deletions.

Prevent this conflict by using the app pointer as the identifier for
netdev indirect block cb registry, allowing each app to register a unique
callback per netdev. For block cb registry, the same app may register
multiple cbs to the same block if using TC shared blocks. Instead of the
app, use the pointer to the allocated cb_priv data as the identifier here.
This means that there can be a unique block callback for each app/netdev
combo.

Fixes: 3166dd07a9cb ("nfp: flower: offload tunnel decap rules via indirect TC blocks")
Reported-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/offload.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 21499a5b3b6b..c642fd84eb02 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -718,7 +718,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 
 		err = tcf_block_cb_register(f->block,
 					    nfp_flower_setup_indr_block_cb,
-					    netdev, cb_priv, f->extack);
+					    cb_priv, cb_priv, f->extack);
 		if (err) {
 			list_del(&cb_priv->list);
 			kfree(cb_priv);
@@ -726,13 +726,15 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 
 		return err;
 	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block,
-					nfp_flower_setup_indr_block_cb, netdev);
 		cb_priv = nfp_flower_indr_block_cb_priv_lookup(app, netdev);
-		if (cb_priv) {
-			list_del(&cb_priv->list);
-			kfree(cb_priv);
-		}
+		if (!cb_priv)
+			return -ENOENT;
+
+		tcf_block_cb_unregister(f->block,
+					nfp_flower_setup_indr_block_cb,
+					cb_priv);
+		list_del(&cb_priv->list);
+		kfree(cb_priv);
 
 		return 0;
 	default:
@@ -766,15 +768,14 @@ int nfp_flower_reg_indir_block_handler(struct nfp_app *app,
 	if (event == NETDEV_REGISTER) {
 		err = __tc_indr_block_cb_register(netdev, app,
 						  nfp_flower_indr_setup_tc_cb,
-						  netdev);
+						  app);
 		if (err)
 			nfp_flower_cmsg_warn(app,
 					     "Indirect block reg failed - %s\n",
 					     netdev->name);
 	} else if (event == NETDEV_UNREGISTER) {
 		__tc_indr_block_cb_unregister(netdev,
-					      nfp_flower_indr_setup_tc_cb,
-					      netdev);
+					      nfp_flower_indr_setup_tc_cb, app);
 	}
 
 	return NOTIFY_OK;
-- 
cgit v1.2.3


From 68406a9807e4db562a157df9a958b3b6e2cedb38 Mon Sep 17 00:00:00 2001
From: James Prestwood <james.prestwood@linux.intel.com>
Date: Tue, 11 Dec 2018 16:52:14 -0800
Subject: mac80211_hwsim: fix overwriting of if_combination

Moved setting if_combination.num_different_channels/radar_detect_widths
into an else after use_chanctx. In the case of use_chanctx, these two
settings were getting overwritten.

Signed-off-by: James Prestwood <james.prestwood@linux.intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 2a5a133f23cf..e4db8e2b2b54 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2751,17 +2751,18 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 		hw->wiphy->max_remain_on_channel_duration = 1000;
 		data->if_combination.radar_detect_widths = 0;
 		data->if_combination.num_different_channels = data->channels;
-	}
-
-	data->if_combination.n_limits = n_limits;
-	data->if_combination.max_interfaces = 2048;
-	data->if_combination.num_different_channels = 1;
-	data->if_combination.radar_detect_widths =
+	} else {
+		data->if_combination.num_different_channels = 1;
+		data->if_combination.radar_detect_widths =
 					BIT(NL80211_CHAN_WIDTH_20_NOHT) |
 					BIT(NL80211_CHAN_WIDTH_20) |
 					BIT(NL80211_CHAN_WIDTH_40) |
 					BIT(NL80211_CHAN_WIDTH_80) |
 					BIT(NL80211_CHAN_WIDTH_160);
+	}
+
+	data->if_combination.n_limits = n_limits;
+	data->if_combination.max_interfaces = 2048;
 	data->if_combination.limits = data->if_limits;
 
 	hw->wiphy->iface_combinations = &data->if_combination;
-- 
cgit v1.2.3


From 3e8bf5234e4e23b66e49da636dc2ab165c8c91a0 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 12 Dec 2018 10:19:50 +0100
Subject: rfkill: gpio: Remove unused include

The legacy <linux/gpio.h> header is no longer in use by the
rfkill driver, so drop this include.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/rfkill/rfkill-gpio.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index 0f8465852254..41a5cd4b5c0e 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -16,7 +16,6 @@
  * 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  */
 
-#include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-- 
cgit v1.2.3


From 3453de98145fa1a9453d18a42406bb7a47bec269 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Thu, 6 Dec 2018 12:58:30 -0800
Subject: wireless: FTM: fix kernel-doc "cannot understand" warnings

Fix kernel-doc warnings in FTM due to missing "struct" keyword.

Fixes 109 warnings from <net/cfg80211.h>:
../include/net/cfg80211.h:2838: warning: cannot understand function prototype: 'struct cfg80211_ftm_responder_stats '

and fixes 88 warnings from <net/mac80211.h>:
../include/net/mac80211.h:477: warning: cannot understand function prototype: 'struct ieee80211_ftm_responder_params '

Fixes: 81e54d08d9d8 ("cfg80211: support FTM responder configuration/statistics")
Fixes: bc847970f432 ("mac80211: support FTM responder configuration/statistics")

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Pradeep Kumar Chitrapu <pradeepc@codeaurora.org>
Cc: Johannes Berg <johannes.berg@intel.com>
Cc: David Spinadel <david.spinadel@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 2 +-
 include/net/mac80211.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index ede7fcd68348..569b128aade8 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2823,7 +2823,7 @@ struct cfg80211_external_auth_params {
 };
 
 /**
- * cfg80211_ftm_responder_stats - FTM responder statistics
+ * struct cfg80211_ftm_responder_stats - FTM responder statistics
  *
  * @filled: bitflag of flags using the bits of &enum nl80211_ftm_stats to
  *	indicate the relevant values in this struct for them
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 9386cf9fe714..6f19cf48dd6a 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -467,7 +467,7 @@ struct ieee80211_mu_group_data {
 };
 
 /**
- * ieee80211_ftm_responder_params - FTM responder parameters
+ * struct ieee80211_ftm_responder_params - FTM responder parameters
  *
  * @lci: LCI subelement content
  * @civicloc: CIVIC location subelement content
-- 
cgit v1.2.3


From 554be8333088e4a40f4b522c2b36ab23fb22f4be Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 15 Dec 2018 11:03:24 +0200
Subject: mac80211: ftm responder: remove pointless defensive coding

The pointer and corresponding length is always set in pairs
in cfg80211, so no need to have this strange defensive check
that also confuses static checkers. Clean it up.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index cf8f946ae724..567c63ff830f 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -800,8 +800,8 @@ static int ieee80211_set_ftm_responder_params(
 	u8 *pos;
 	int len;
 
-	if ((!lci || !lci_len) && (!civicloc || !civicloc_len))
-		return 1;
+	if (!lci_len && !civicloc_len)
+		return 0;
 
 	bss_conf = &sdata->vif.bss_conf;
 	old = bss_conf->ftmr_params;
-- 
cgit v1.2.3


From 30db641ef4f68054db9b191b6c0200fb1a96d458 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 15 Dec 2018 11:03:23 +0200
Subject: cfg80211: clarify LCI/civic location documentation

The older code and current userspace assumed that this data
is the content of the Measurement Report element, starting
with the Measurement Token. Clarify this in the documentation.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  6 ++++--
 include/uapi/linux/nl80211.h | 16 ++++++++++++----
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 569b128aade8..e0c41eb1c860 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -777,8 +777,10 @@ struct cfg80211_crypto_settings {
  * @probe_resp: probe response template (AP mode only)
  * @ftm_responder: enable FTM responder functionality; -1 for no change
  *	(which also implies no change in LCI/civic location data)
- * @lci: LCI subelement content
- * @civicloc: Civic location subelement content
+ * @lci: Measurement Report element content, starting with Measurement Token
+ *	(measurement type 8)
+ * @civicloc: Measurement Report element content, starting with Measurement
+ *	Token (measurement type 11)
  * @lci_len: LCI data length
  * @civicloc_len: Civic location data length
  */
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 2b53c0e949c7..4625a8624ba2 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -5893,9 +5893,11 @@ enum nl80211_external_auth_action {
  * @__NL80211_FTM_RESP_ATTR_INVALID: Invalid
  * @NL80211_FTM_RESP_ATTR_ENABLED: FTM responder is enabled
  * @NL80211_FTM_RESP_ATTR_LCI: The content of Measurement Report Element
- *	(9.4.2.22 in 802.11-2016) with type 8 - LCI (9.4.2.22.10)
+ *	(9.4.2.22 in 802.11-2016) with type 8 - LCI (9.4.2.22.10),
+ *	i.e. starting with the measurement token
  * @NL80211_FTM_RESP_ATTR_CIVIC: The content of Measurement Report Element
- *	(9.4.2.22 in 802.11-2016) with type 11 - Civic (Section 9.4.2.22.13)
+ *	(9.4.2.22 in 802.11-2016) with type 11 - Civic (Section 9.4.2.22.13),
+ *	i.e. starting with the measurement token
  * @__NL80211_FTM_RESP_ATTR_LAST: Internal
  * @NL80211_FTM_RESP_ATTR_MAX: highest FTM responder attribute.
  */
@@ -6295,9 +6297,15 @@ enum nl80211_peer_measurement_ftm_failure_reasons {
  * @NL80211_PMSR_FTM_RESP_ATTR_DIST_VARIANCE: distance variance (u64, mm^2, note
  *	that standard deviation is the square root of variance, optional)
  * @NL80211_PMSR_FTM_RESP_ATTR_DIST_SPREAD: distance spread (u64, mm, optional)
- * @NL80211_PMSR_FTM_RESP_ATTR_LCI: LCI data from peer (binary, optional)
+ * @NL80211_PMSR_FTM_RESP_ATTR_LCI: LCI data from peer (binary, optional);
+ *	this is the contents of the Measurement Report Element (802.11-2016
+ *	9.4.2.22.1) starting with the Measurement Token, with Measurement
+ *	Type 8.
  * @NL80211_PMSR_FTM_RESP_ATTR_CIVICLOC: civic location data from peer
- *	(binary, optional)
+ *	(binary, optional);
+ *	this is the contents of the Measurement Report Element (802.11-2016
+ *	9.4.2.22.1) starting with the Measurement Token, with Measurement
+ *	Type 11.
  * @NL80211_PMSR_FTM_RESP_ATTR_PAD: ignore, for u64/s64 padding only
  *
  * @NUM_NL80211_PMSR_FTM_RESP_ATTR: internal
-- 
cgit v1.2.3


From 925b5978cdc7287ba08ed21bf27970131f147720 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Sat, 15 Dec 2018 11:03:21 +0200
Subject: cfg80211: add some missing fall through annotations

There are talks about enabling -Wimplicit-fallthrough warnings in the
mainline and it is already enabled in linux-next.  Add all the
missing annotations to prevent warnings when this happens.

And in one case, remove the extra text from the annotation so that the
compiler recognizes it.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/chan.c    | 3 +++
 net/wireless/nl80211.c | 9 +++++++++
 net/wireless/scan.c    | 2 +-
 3 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 2db713d18f71..7dc1bbd0888f 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -6,6 +6,7 @@
  *
  * Copyright 2009	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
+ * Copyright 2018       Intel Corporation
  */
 
 #include <linux/export.h>
@@ -747,6 +748,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 	case NL80211_CHAN_WIDTH_20:
 		if (!ht_cap->ht_supported)
 			return false;
+		/* fall through */
 	case NL80211_CHAN_WIDTH_20_NOHT:
 		prohibited_flags |= IEEE80211_CHAN_NO_20MHZ;
 		width = 20;
@@ -769,6 +771,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 		cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
 		if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)
 			return false;
+		/* fall through */
 	case NL80211_CHAN_WIDTH_80:
 		if (!vht_cap->vht_supported)
 			return false;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e20329b34840..4e9133e4587b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1851,6 +1851,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
+		/* fall through */
 	case 1:
 		if (nla_put(msg, NL80211_ATTR_CIPHER_SUITES,
 			    sizeof(u32) * rdev->wiphy.n_cipher_suites,
@@ -1897,6 +1898,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
+		/* fall through */
 	case 2:
 		if (nl80211_put_iftypes(msg, NL80211_ATTR_SUPPORTED_IFTYPES,
 					rdev->wiphy.interface_modes))
@@ -1904,6 +1906,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
+		/* fall through */
 	case 3:
 		nl_bands = nla_nest_start(msg, NL80211_ATTR_WIPHY_BANDS);
 		if (!nl_bands)
@@ -1929,6 +1932,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 				state->chan_start++;
 				if (state->split)
 					break;
+				/* fall through */
 			default:
 				/* add frequencies */
 				nl_freqs = nla_nest_start(
@@ -1982,6 +1986,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			state->split_start++;
 		if (state->split)
 			break;
+		/* fall through */
 	case 4:
 		nl_cmds = nla_nest_start(msg, NL80211_ATTR_SUPPORTED_COMMANDS);
 		if (!nl_cmds)
@@ -2008,6 +2013,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
+		/* fall through */
 	case 5:
 		if (rdev->ops->remain_on_channel &&
 		    (rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL) &&
@@ -2025,6 +2031,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
+		/* fall through */
 	case 6:
 #ifdef CONFIG_PM
 		if (nl80211_send_wowlan(msg, rdev, state->split))
@@ -2035,6 +2042,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 #else
 		state->split_start++;
 #endif
+		/* fall through */
 	case 7:
 		if (nl80211_put_iftypes(msg, NL80211_ATTR_SOFTWARE_IFTYPES,
 					rdev->wiphy.software_iftypes))
@@ -2047,6 +2055,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		state->split_start++;
 		if (state->split)
 			break;
+		/* fall through */
 	case 8:
 		if ((rdev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME) &&
 		    nla_put_u32(msg, NL80211_ATTR_DEVICE_AP_SME,
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index d0e7472dd9fd..5123667f4569 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1183,7 +1183,7 @@ cfg80211_inform_bss_data(struct wiphy *wiphy,
 	switch (ftype) {
 	case CFG80211_BSS_FTYPE_BEACON:
 		ies->from_beacon = true;
-		/* fall through to assign */
+		/* fall through */
 	case CFG80211_BSS_FTYPE_UNKNOWN:
 		rcu_assign_pointer(tmp.pub.beacon_ies, ies);
 		break;
-- 
cgit v1.2.3


From 8020919a9b99d6c990dc6a50e8215e291fbbe5a6 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sat, 15 Dec 2018 11:03:17 +0200
Subject: mac80211: Properly handle SKB with radiotap only

The monitor interface Rx handling of SKBs that contain only
radiotap information was buggy as it tried to access the
SKB assuming it contains a frame.

To fix this, check the RX_FLAG_NO_PSDU flag in the Rx status
(indicting that the SKB contains only radiotap information),
and do not perform data path specific processing when the flag
is set.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/rx.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 3bd3b5769797..8327440aa24b 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -753,6 +753,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 	struct ieee80211_sub_if_data *monitor_sdata =
 		rcu_dereference(local->monitor_sdata);
 	bool only_monitor = false;
+	unsigned int min_head_len;
 
 	if (status->flag & RX_FLAG_RADIOTAP_HE)
 		rtap_space += sizeof(struct ieee80211_radiotap_he);
@@ -766,6 +767,8 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 		rtap_space += sizeof(*rtap) + rtap->len + rtap->pad;
 	}
 
+	min_head_len = rtap_space;
+
 	/*
 	 * First, we may need to make a copy of the skb because
 	 *  (1) we need to modify it for radiotap (if not present), and
@@ -775,18 +778,23 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 	 * the SKB because it has a bad FCS/PLCP checksum.
 	 */
 
-	if (ieee80211_hw_check(&local->hw, RX_INCLUDES_FCS)) {
-		if (unlikely(origskb->len <= FCS_LEN)) {
-			/* driver bug */
-			WARN_ON(1);
-			dev_kfree_skb(origskb);
-			return NULL;
+	if (!(status->flag & RX_FLAG_NO_PSDU)) {
+		if (ieee80211_hw_check(&local->hw, RX_INCLUDES_FCS)) {
+			if (unlikely(origskb->len <= FCS_LEN + rtap_space)) {
+				/* driver bug */
+				WARN_ON(1);
+				dev_kfree_skb(origskb);
+				return NULL;
+			}
+			present_fcs_len = FCS_LEN;
 		}
-		present_fcs_len = FCS_LEN;
+
+		/* also consider the hdr->frame_control */
+		min_head_len += 2;
 	}
 
-	/* ensure hdr->frame_control and vendor radiotap data are in skb head */
-	if (!pskb_may_pull(origskb, 2 + rtap_space)) {
+	/* ensure that the expected data elements are in skb head */
+	if (!pskb_may_pull(origskb, min_head_len)) {
 		dev_kfree_skb(origskb);
 		return NULL;
 	}
-- 
cgit v1.2.3


From dd665d23c1e94ad81d8720e90666030c5714a158 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 15 Dec 2018 11:03:11 +0200
Subject: mac80211: never pass NULL params to ieee80211_if_add()

This isn't really a problem now, but it means that the function
has a few NULL checks that are only relevant when coming from
the initial interface added in mac80211, and that's confusing.
Just pass non-NULL (but equivalently empty) in that case and
remove all the NULL checks.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/iface.c | 10 ++++------
 net/mac80211/main.c  |  4 +++-
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 5836ddeac9e3..6944ec7b6245 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1799,7 +1799,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 		}
 
 		ieee80211_assign_perm_addr(local, ndev->perm_addr, type);
-		if (params && is_valid_ether_addr(params->macaddr))
+		if (is_valid_ether_addr(params->macaddr))
 			memcpy(ndev->dev_addr, params->macaddr, ETH_ALEN);
 		else
 			memcpy(ndev->dev_addr, ndev->perm_addr, ETH_ALEN);
@@ -1868,11 +1868,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 	ieee80211_setup_sdata(sdata, type);
 
 	if (ndev) {
-		if (params) {
-			ndev->ieee80211_ptr->use_4addr = params->use_4addr;
-			if (type == NL80211_IFTYPE_STATION)
-				sdata->u.mgd.use_4addr = params->use_4addr;
-		}
+		ndev->ieee80211_ptr->use_4addr = params->use_4addr;
+		if (type == NL80211_IFTYPE_STATION)
+			sdata->u.mgd.use_4addr = params->use_4addr;
 
 		ndev->features |= local->hw.netdev_features;
 
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 83e71e6b2ebe..ada8e16d52d2 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1221,8 +1221,10 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	/* add one default STA interface if supported */
 	if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) &&
 	    !ieee80211_hw_check(hw, NO_AUTO_VIF)) {
+		struct vif_params params = {0};
+
 		result = ieee80211_if_add(local, "wlan%d", NET_NAME_ENUM, NULL,
-					  NL80211_IFTYPE_STATION, NULL);
+					  NL80211_IFTYPE_STATION, &params);
 		if (result)
 			wiphy_warn(local->hw.wiphy,
 				   "Failed to add default virtual iface\n");
-- 
cgit v1.2.3


From 233e98dc9c3009943aa34d58925d94ac9330e17b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 15 Dec 2018 11:03:09 +0200
Subject: mac80211: remove superfluous NULL check

At the place where this code lives now, the skb can never be
NULL, so we can remove the pointless NULL check.

It seems to exist because this code was moved around a few times
and originally came from a place where it could in fact be NULL.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 582b3d49f891..4919881c6a86 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3583,7 +3583,7 @@ begin:
 			skb_queue_splice_tail(&tx.skbs, &txqi->frags);
 	}
 
-	if (skb && skb_has_frag_list(skb) &&
+	if (skb_has_frag_list(skb) &&
 	    !ieee80211_hw_check(&local->hw, TX_FRAG_LIST)) {
 		if (skb_linearize(skb)) {
 			ieee80211_free_txskb(&local->hw, skb);
-- 
cgit v1.2.3


From fca1279f090b8e38eadb95c3914d51e544142e74 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 15 Dec 2018 11:03:08 +0200
Subject: mac80211: document RCU requirements for ieee80211_tx_dequeue()

In the iwlwifi conversion, we sometimes call this from outside
of the wake_tx_queue() method, and in those cases must be in an
RCU critical section. Document this requirement.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 6f19cf48dd6a..aecbdf38b4c2 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -6103,6 +6103,14 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid);
  * @txq: pointer obtained from station or virtual interface
  *
  * Returns the skb if successful, %NULL if no frame was available.
+ *
+ * Note that this must be called in an rcu_read_lock() critical section,
+ * which can only be released after the SKB was handled. Some pointers in
+ * skb->cb, e.g. the key pointer, are protected by by RCU and thus the
+ * critical section must persist not just for the duration of this call
+ * but for the duration of the frame handling.
+ * However, also note that while in the wake_tx_queue() method,
+ * rcu_read_lock() is already held.
  */
 struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 				     struct ieee80211_txq *txq);
-- 
cgit v1.2.3


From 344f8e00933da8c275fa293caadfc62680d46d21 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Sat, 15 Dec 2018 11:03:07 +0200
Subject: mac80211: don't build AMSDU from GSO packets

If we build AMSDU from GSO packets, it can lead to
bad results if anyone tries to call skb_gso_segment
on the packets.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/tx.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 4919881c6a86..4f348b116549 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3218,6 +3218,9 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	if (!ieee80211_hw_check(&local->hw, TX_AMSDU))
 		return false;
 
+	if (skb_is_gso(skb))
+		return false;
+
 	if (!txq)
 		return false;
 
@@ -3242,7 +3245,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	tin = &txqi->tin;
 	flow = fq_flow_classify(fq, tin, skb, fq_flow_get_default_func);
 	head = skb_peek_tail(&flow->queue);
-	if (!head)
+	if (!head || skb_is_gso(head))
 		goto out;
 
 	orig_len = head->len;
-- 
cgit v1.2.3


From 30c63115e20b70f89b7cfb66b35e2a0ef4b0ef07 Mon Sep 17 00:00:00 2001
From: Sriram R <srirrama@codeaurora.org>
Date: Tue, 4 Dec 2018 17:46:52 +0530
Subject: nl80211: Add support to notify radar event info received from STA

Currently radar detection and corresponding channel switch is handled
at the AP device. STA ignores these detected radar events since the
radar signal can be seen mostly by the AP as well. But in scenarios where
a radar signal is seen only at STA, notifying this event to the AP which
can trigger a channel switch can be useful.
Stations can report such radar events autonomously through Spectrum
management (Measurement Report) action frame to its AP. The userspace on
processing the report can notify the kernel with the use of the added
NL80211_CMD_NOTIFY_RADAR to indicate the detected event and inturn adding
the reported channel to NOL.

Signed-off-by: Sriram R <srirrama@codeaurora.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h |  7 +++++
 net/wireless/nl80211.c       | 62 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 69 insertions(+)

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 4625a8624ba2..31ae5c7f10e3 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1060,6 +1060,11 @@
  *	the measurement completed, using the measurement cookie
  *	(%NL80211_ATTR_COOKIE).
  *
+ * @NL80211_CMD_NOTIFY_RADAR: Notify the kernel that a radar signal was
+ *	detected and reported by a neighboring device on the channel
+ *	indicated by %NL80211_ATTR_WIPHY_FREQ and other attributes
+ *	determining the width and type.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -1278,6 +1283,8 @@ enum nl80211_commands {
 	NL80211_CMD_PEER_MEASUREMENT_RESULT,
 	NL80211_CMD_PEER_MEASUREMENT_COMPLETE,
 
+	NL80211_CMD_NOTIFY_RADAR,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 4e9133e4587b..71a54ada377b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -7990,6 +7990,60 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 	return err;
 }
 
+static int nl80211_notify_radar_detection(struct sk_buff *skb,
+					  struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct wiphy *wiphy = wdev->wiphy;
+	struct cfg80211_chan_def chandef;
+	enum nl80211_dfs_regions dfs_region;
+	int err;
+
+	dfs_region = reg_get_dfs_region(wiphy);
+	if (dfs_region == NL80211_DFS_UNSET) {
+		GENL_SET_ERR_MSG(info,
+				 "DFS Region is not set. Unexpected Radar indication");
+		return -EINVAL;
+	}
+
+	err = nl80211_parse_chandef(rdev, info, &chandef);
+	if (err) {
+		GENL_SET_ERR_MSG(info, "Unable to extract chandef info");
+		return err;
+	}
+
+	err = cfg80211_chandef_dfs_required(wiphy, &chandef, wdev->iftype);
+	if (err < 0) {
+		GENL_SET_ERR_MSG(info, "chandef is invalid");
+		return err;
+	}
+
+	if (err == 0) {
+		GENL_SET_ERR_MSG(info,
+				 "Unexpected Radar indication for chandef/iftype");
+		return -EINVAL;
+	}
+
+	/* Do not process this notification if radar is already detected
+	 * by kernel on this channel, and return success.
+	 */
+	if (chandef.chan->dfs_state == NL80211_DFS_UNAVAILABLE)
+		return 0;
+
+	cfg80211_set_dfs_state(wiphy, &chandef, NL80211_DFS_UNAVAILABLE);
+
+	cfg80211_sched_dfs_chan_update(rdev);
+
+	memcpy(&rdev->radar_chandef, &chandef, sizeof(chandef));
+
+	/* Propagate this notification to other radios as well */
+	queue_work(cfg80211_wq, &rdev->propagate_radar_detect_wk);
+
+	return 0;
+}
+
 static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -14074,6 +14128,14 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_NOTIFY_RADAR,
+		.doit = nl80211_notify_radar_detection,
+		.policy = nl80211_policy,
+		.flags = GENL_UNS_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 static struct genl_family nl80211_fam __ro_after_init = {
-- 
cgit v1.2.3


From fdb313e3182094939b34234bdade0fbce28dfb2c Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sat, 15 Dec 2018 11:03:03 +0200
Subject: ieee80211: add bits for TWT in Extended Capabilities IE

These bits are defined in ieee802.11ax to advertise support
for TWT in addition to the bits in the HE IE.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 407d6fd66fa9..a9484b3e898d 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2687,6 +2687,10 @@ enum ieee80211_tdls_actioncode {
  */
 #define WLAN_EXT_CAPA9_FTM_INITIATOR	BIT(7)
 
+/* Defines support for TWT Requester and TWT Responder */
+#define WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT	BIT(5)
+#define WLAN_EXT_CAPA10_TWT_RESPONDER_SUPPORT	BIT(6)
+
 /* TDLS specific payload type in the LLC/SNAP header */
 #define WLAN_TDLS_SNAP_RFTYPE	0x2
 
-- 
cgit v1.2.3


From 55ebd6e6c765cce4697a6fbb97acf6eec9ad7a51 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sat, 15 Dec 2018 11:03:04 +0200
Subject: mac80211: propagate the support for TWT to the driver

TWT is a feature that was added in 11ah and enhanced in
11ax. There are two bits that need to be set if we want
to use the feature in 11ax: one in the HE Capability IE
and one in the Extended Capability IE. This is because
of backward compatibility between 11ah and 11ax.

In order to simplify the flow for the low level driver
in managed mode, aggregate the two bits and add a boolean
that tells whether TWT is supported or not, but only if
11ax is supported.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  3 +++
 net/mac80211/mlme.c    | 16 ++++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index aecbdf38b4c2..88219cc137c3 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -496,6 +496,8 @@ struct ieee80211_ftm_responder_params {
  * @uora_ocw_range: UORA element's OCW Range field
  * @frame_time_rts_th: HE duration RTS threshold, in units of 32us
  * @he_support: does this BSS support HE
+ * @twt_requester: does this BSS support TWT requester (relevant for managed
+ *	mode only, set if the AP advertises TWT responder role)
  * @assoc: association status
  * @ibss_joined: indicates whether this station is part of an IBSS
  *	or not
@@ -594,6 +596,7 @@ struct ieee80211_bss_conf {
 	u8 uora_ocw_range;
 	u16 frame_time_rts_th;
 	bool he_support;
+	bool twt_requester;
 	/* association related data */
 	bool assoc, ibss_joined;
 	bool ibss_creator;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index d2bc8d57c87e..3d1334a4a264 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3058,6 +3058,19 @@ static void ieee80211_get_rates(struct ieee80211_supported_band *sband,
 	}
 }
 
+static bool ieee80211_twt_req_supported(const struct sta_info *sta,
+					const struct ieee802_11_elems *elems)
+{
+	if (elems->ext_capab_len < 10)
+		return false;
+
+	if (!(elems->ext_capab[9] & WLAN_EXT_CAPA10_TWT_RESPONDER_SUPPORT))
+		return false;
+
+	return sta->sta.he_cap.he_cap_elem.mac_cap_info[0] &
+		IEEE80211_HE_MAC_CAP0_TWT_RES;
+}
+
 static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 				    struct cfg80211_bss *cbss,
 				    struct ieee80211_mgmt *mgmt, size_t len)
@@ -3247,8 +3260,11 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 						  sta);
 
 		bss_conf->he_support = sta->sta.he_cap.has_he;
+		bss_conf->twt_requester =
+			ieee80211_twt_req_supported(sta, &elems);
 	} else {
 		bss_conf->he_support = false;
+		bss_conf->twt_requester = false;
 	}
 
 	if (bss_conf->he_support) {
-- 
cgit v1.2.3


From daa5b83513a7a85491ffa03e7aabd9d7348e97d5 Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Sat, 15 Dec 2018 11:03:05 +0200
Subject: mac80211: update HE operation fields to D3.0

HE Operation element has changed in 11ax D3.0.  Update the fields
accordingly.

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index a9484b3e898d..3b04e72315e1 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1619,7 +1619,7 @@ struct ieee80211_he_mcs_nss_supp {
  * struct ieee80211_he_operation - HE capabilities element
  *
  * This structure is the "HE operation element" fields as
- * described in P802.11ax_D2.0 section 9.4.2.238
+ * described in P802.11ax_D3.0 section 9.4.2.238
  */
 struct ieee80211_he_operation {
 	__le32 he_oper_params;
@@ -2011,17 +2011,17 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info)
 }
 
 /* HE Operation defines */
-#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK			0x0000003f
-#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK		0x000001c0
-#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET		6
-#define IEEE80211_HE_OPERATION_TWT_REQUIRED			0x00000200
-#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK		0x000ffc00
-#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET		10
-#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR		0x00100000
-#define IEEE80211_HE_OPERATION_VHT_OPER_INFO			0x00200000
-#define IEEE80211_HE_OPERATION_MULTI_BSSID_AP			0x10000000
-#define IEEE80211_HE_OPERATION_TX_BSSID_INDICATOR		0x20000000
-#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED		0x40000000
+#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK		0x00000003
+#define IEEE80211_HE_OPERATION_TWT_REQUIRED			0x00000008
+#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK		0x00003ff0
+#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET		4
+#define IEEE80211_HE_OPERATION_VHT_OPER_INFO			0x00004000
+#define IEEE80211_HE_OPERATION_CO_LOCATED_BSS			0x00008000
+#define IEEE80211_HE_OPERATION_ER_SU_DISABLE			0x00010000
+#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK			0x3f000000
+#define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET		24
+#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR		0x40000000
+#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED		0x80000000
 
 /*
  * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size
@@ -2046,7 +2046,7 @@ ieee80211_he_oper_size(const u8 *he_oper_ie)
 	he_oper_params = le32_to_cpu(he_oper->he_oper_params);
 	if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO)
 		oper_len += 3;
-	if (he_oper_params & IEEE80211_HE_OPERATION_MULTI_BSSID_AP)
+	if (he_oper_params & IEEE80211_HE_OPERATION_CO_LOCATED_BSS)
 		oper_len++;
 
 	/* Add the first byte (extension ID) to the total length */
-- 
cgit v1.2.3


From 2e249fc320862e3f75fd255a21554d6de90fb55a Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Sat, 15 Dec 2018 11:03:15 +0200
Subject: mac80211: update driver when MU EDCA params change

Similar to WMM IE, if MU_EDCA IE parameters changed (or ceased to exist)
tell the Driver about it.

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ieee80211_i.h |  1 +
 net/mac80211/mlme.c        | 12 ++++++++++--
 net/mac80211/util.c        |  2 ++
 3 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 10a05062e4a0..7dfb4e2f98b2 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -500,6 +500,7 @@ struct ieee80211_if_managed {
 	unsigned int uapsd_max_sp_len;
 
 	int wmm_last_param_set;
+	int mu_edca_last_param_set;
 
 	u8 use_4addr;
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 3d1334a4a264..975315b5689a 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1869,7 +1869,7 @@ ieee80211_sta_wmm_params(struct ieee80211_local *local,
 	struct ieee80211_tx_queue_params params[IEEE80211_NUM_ACS];
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	size_t left;
-	int count, ac;
+	int count, mu_edca_count, ac;
 	const u8 *pos;
 	u8 uapsd_queues = 0;
 
@@ -1889,9 +1889,16 @@ ieee80211_sta_wmm_params(struct ieee80211_local *local,
 		uapsd_queues = ifmgd->uapsd_queues;
 
 	count = wmm_param[6] & 0x0f;
-	if (count == ifmgd->wmm_last_param_set)
+	/* -1 is the initial value of ifmgd->mu_edca_last_param_set.
+	 * if mu_edca was preset before and now it disappeared tell
+	 * the driver about it.
+	 */
+	mu_edca_count = mu_edca ? mu_edca->mu_qos_info & 0x0f : -1;
+	if (count == ifmgd->wmm_last_param_set &&
+	    mu_edca_count == ifmgd->mu_edca_last_param_set)
 		return false;
 	ifmgd->wmm_last_param_set = count;
+	ifmgd->mu_edca_last_param_set = mu_edca_count;
 
 	pos = wmm_param + 8;
 	left = wmm_param_len - 8;
@@ -3349,6 +3356,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 	 * 4-bit value.
 	 */
 	ifmgd->wmm_last_param_set = -1;
+	ifmgd->mu_edca_last_param_set = -1;
 
 	if (ifmgd->flags & IEEE80211_STA_DISABLE_WMM) {
 		ieee80211_set_wmm_default(sdata, false, false);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index dddfff7cf44f..d0eb38b890aa 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1223,6 +1223,8 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 			if (pos[0] == WLAN_EID_EXT_HE_MU_EDCA &&
 			    elen >= (sizeof(*elems->mu_edca_param_set) + 1)) {
 				elems->mu_edca_param_set = (void *)&pos[1];
+				if (calc_crc)
+					crc = crc32_be(crc, pos - 2, elen + 2);
 			} else if (pos[0] == WLAN_EID_EXT_HE_CAPABILITY) {
 				elems->he_cap = (void *)&pos[1];
 				elems->he_cap_len = elen - 1;
-- 
cgit v1.2.3


From 002245ec20b273bc1e31ed8fbee01396955a0f19 Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Sat, 15 Dec 2018 11:03:19 +0200
Subject: mac80211: set STA flag DISABLE_HE if HE is not supported

Up until now, the IEEE80211_STA_DISABLE_HE flag was set only based
on whether the AP has advertised HE capabilities.
This flag should be set also if STA does not support HE
(regardless of the AP support).

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 975315b5689a..8c6a4dc017a5 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4680,8 +4680,10 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
-	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) &&
-	    ieee80211_get_he_sta_cap(sband)) {
+	if (!ieee80211_get_he_sta_cap(sband))
+		ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
+
+	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) {
 		const struct cfg80211_bss_ies *ies;
 		const u8 *he_oper_ie;
 
-- 
cgit v1.2.3


From dc7eb0f2c23f58bc0e15574bda2dc8498d30a833 Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Sat, 15 Dec 2018 11:03:20 +0200
Subject: mac80211: do not advertise HE cap IE if HE disabled

When disabling HE due to the lack of HT/VHT, do it
at an earlier stage to avoid advertising HE capabilities IE.
Also, at this point, no need to check if AP supports HE, since
it is already checked earlier (in ieee80211_prep_channel).

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 8c6a4dc017a5..54e511dbbc12 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -916,6 +916,15 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		ieee80211_add_vht_ie(sdata, skb, sband,
 				     &assoc_data->ap_vht_cap);
 
+	/*
+	 * If AP doesn't support HT, mark HE as disabled.
+	 * If on the 5GHz band, make sure it supports VHT.
+	 */
+	if (ifmgd->flags & IEEE80211_STA_DISABLE_HT ||
+	    (sband->band == NL80211_BAND_5GHZ &&
+	     ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
+		ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
+
 	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE))
 		ieee80211_add_he_ie(sdata, skb, sband);
 
@@ -3231,16 +3240,6 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		goto out;
 	}
 
-	/*
-	 * If AP doesn't support HT, or it doesn't have HE mandatory IEs, mark
-	 * HE as disabled. If on the 5GHz band, make sure it supports VHT.
-	 */
-	if (ifmgd->flags & IEEE80211_STA_DISABLE_HT ||
-	    (sband->band == NL80211_BAND_5GHZ &&
-	     ifmgd->flags & IEEE80211_STA_DISABLE_VHT) ||
-	    (!elems.he_cap && !elems.he_operation))
-		ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
-
 	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) &&
 	    (!elems.he_cap || !elems.he_operation)) {
 		mutex_unlock(&sdata->local->sta_mtx);
-- 
cgit v1.2.3


From 0d7410ea6efcdfda56773999f692bbd5d4e4bc00 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 17 Dec 2018 17:31:57 -0800
Subject: tools/bpf: check precise {func, line, jited_line}_info_rec_size in
 test_btf

Current btf func_info, line_info and jited_line are designed to be
extensible. The record sizes for {func,line}_info are passed to kernel,
and the record sizes for {func,line,jited_line}_info are returned to
userspace during bpf_prog_info query.

In bpf selftests test_btf.c, when testing whether kernel returns
a legitimate {func,line, jited_line)_info rec_size, the test only
compares to the minimum allowed size. If the returned rec_size is smaller
than the minimum allowed size, it is considered incorrect.
The minimum allowed size for these three info sizes are equal to
current value of sizeof(struct bpf_func_info), sizeof(struct bpf_line_info)
and sizeof(__u64).

The original thinking was that in the future when rec_size is increased
in kernel, the same test should run correctly. But this sacrificed
the precision of testing under the very kernel the test is shipped with,
and bpf selftest is typically run with the same repo kernel.

So this patch changed the testing of rec_size such that the
kernel returned value should be equal to the size defined by
tools uapi header bpf.h which syncs with kernel uapi header.

Martin discovered a bug in one of rec_size comparisons.
Instead of comparing to minimum func_info rec_size 8, it compares to 4.
This patch fixed that issue as well.

Fixes: 999d82cbc044 ("tools/bpf: enhance test_btf file testing to test func info")
Fixes: 05687352c600 ("bpf: Refactor and bug fix in test_func_type in test_btf.c")
Fixes: 4d6304c76355 ("bpf: Add unit tests for bpf_line_info")
Suggested-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_btf.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index b783aa2212cc..8024b7d4c354 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -3408,7 +3408,7 @@ static int do_test_file(unsigned int test_num)
 		goto done;
 	}
 	rec_size = info.func_info_rec_size;
-	if (CHECK(rec_size < 4,
+	if (CHECK(rec_size != sizeof(struct bpf_func_info),
 		  "incorrect info.func_info_rec_size (1st) %d\n", rec_size)) {
 		err = -1;
 		goto done;
@@ -4544,7 +4544,7 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 	}
 
 	rec_size = info.func_info_rec_size;
-	if (CHECK(rec_size < 8,
+	if (CHECK(rec_size != sizeof(struct bpf_func_info),
 		  "incorrect info.func_info_rec_size (1st) %d", rec_size)) {
 		return -1;
 	}
@@ -4573,7 +4573,7 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 		err = -1;
 		goto done;
 	}
-	if (CHECK(info.func_info_rec_size < 8,
+	if (CHECK(info.func_info_rec_size != rec_size,
 		  "incorrect info.func_info_rec_size (2nd) %d",
 		  info.func_info_rec_size)) {
 		err = -1;
@@ -4649,8 +4649,8 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 		goto done;
 	}
 
-	if (CHECK(info.line_info_rec_size < 16 ||
-		  info.jited_line_info_rec_size < 8,
+	if (CHECK(info.line_info_rec_size != sizeof(struct bpf_line_info) ||
+		  info.jited_line_info_rec_size != sizeof(__u64),
 		  "info: line_info_rec_size:%u(userspace expected:%u) jited_line_info_rec_size:%u(userspace expected:%u)",
 		  info.line_info_rec_size, rec_size,
 		  info.jited_line_info_rec_size, jited_rec_size)) {
-- 
cgit v1.2.3


From be3245e22d227ad68ab97785d506561374daa028 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Tue, 18 Dec 2018 10:13:18 +0000
Subject: tools: bpftool: attempt to mount tracefs if required for tracelog cmd

As a follow-up to commit 30da46b5dc3a ("tools: bpftool: add a command to
dump the trace pipe"), attempt to mount the tracefs virtual file system
if it is not detected on the system before trying to dump content of the
tracing pipe on an invocation of "bpftool prog tracelog".

Usually, tracefs in automatically mounted by debugfs when the user tries
to access it (e.g. "ls /sys/kernel/debug/tracing" mounts the tracefs).
So if we failed to find it, it is probably that debugfs is not here
either. Therefore, we just attempt a single mount, at a location that
does not involve debugfs: /sys/kernel/tracing.

Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/common.c   | 25 ++++++++++++++++++++-----
 tools/bpf/bpftool/main.h     |  2 ++
 tools/bpf/bpftool/tracelog.c | 20 +++++++++++++-------
 3 files changed, 35 insertions(+), 12 deletions(-)

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 24582e8a96fb..1bad6602a282 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -76,7 +76,8 @@ void set_max_rlimit(void)
 	setrlimit(RLIMIT_MEMLOCK, &rinf);
 }
 
-static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
+static int
+mnt_fs(const char *target, const char *type, char *buff, size_t bufflen)
 {
 	bool bind_done = false;
 
@@ -98,15 +99,29 @@ static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
 		bind_done = true;
 	}
 
-	if (mount("bpf", target, "bpf", 0, "mode=0700")) {
-		snprintf(buff, bufflen, "mount -t bpf bpf %s failed: %s",
-			 target, strerror(errno));
+	if (mount(type, target, type, 0, "mode=0700")) {
+		snprintf(buff, bufflen, "mount -t %s %s %s failed: %s",
+			 type, type, target, strerror(errno));
 		return -1;
 	}
 
 	return 0;
 }
 
+int mount_tracefs(const char *target)
+{
+	char err_str[ERR_MAX_LEN];
+	int err;
+
+	err = mnt_fs(target, "tracefs", err_str, ERR_MAX_LEN);
+	if (err) {
+		err_str[ERR_MAX_LEN - 1] = '\0';
+		p_err("can't mount tracefs: %s", err_str);
+	}
+
+	return err;
+}
+
 int open_obj_pinned(char *path, bool quiet)
 {
 	int fd;
@@ -162,7 +177,7 @@ int mount_bpffs_for_pin(const char *name)
 		/* nothing to do if already mounted */
 		goto out_free;
 
-	err = mnt_bpffs(dir, err_str, ERR_MAX_LEN);
+	err = mnt_fs(dir, "bpf", err_str, ERR_MAX_LEN);
 	if (err) {
 		err_str[ERR_MAX_LEN - 1] = '\0';
 		p_err("can't mount BPF file system to pin the object (%s): %s",
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 9487345b04a7..9e4499c926fa 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -98,6 +98,8 @@ void usage(void) __noreturn;
 
 void set_max_rlimit(void);
 
+int mount_tracefs(const char *target);
+
 struct pinned_obj_table {
 	DECLARE_HASHTABLE(table, 16);
 };
diff --git a/tools/bpf/bpftool/tracelog.c b/tools/bpf/bpftool/tracelog.c
index 1fa8e513f590..2dc36dfa0896 100644
--- a/tools/bpf/bpftool/tracelog.c
+++ b/tools/bpf/bpftool/tracelog.c
@@ -54,7 +54,7 @@ find_tracefs_mnt_single(unsigned long magic, char *mnt, const char *mntpt)
 	return true;
 }
 
-static bool find_tracefs_pipe(char *mnt)
+static bool get_tracefs_pipe(char *mnt)
 {
 	static const char * const known_mnts[] = {
 		"/sys/kernel/debug/tracing",
@@ -88,7 +88,17 @@ static bool find_tracefs_pipe(char *mnt)
 	fclose(fp);
 
 	/* The string from fscanf() might be truncated, check mnt is valid */
-	if (!found || validate_tracefs_mnt(mnt, TRACEFS_MAGIC))
+	if (found && validate_tracefs_mnt(mnt, TRACEFS_MAGIC))
+		goto exit_found;
+
+	p_info("could not find tracefs, attempting to mount it now");
+	/* Most of the time, tracefs is automatically mounted by debugfs at
+	 * /sys/kernel/debug/tracing when we try to access it. If we could not
+	 * find it, it is likely that debugfs is not mounted. Let's give one
+	 * attempt at mounting just tracefs at /sys/kernel/tracing.
+	 */
+	strcpy(mnt, known_mnts[1]);
+	if (mount_tracefs(mnt))
 		return false;
 
 exit_found:
@@ -115,17 +125,13 @@ int do_tracelog(int argc, char **argv)
 		.sa_handler = exit_tracelog
 	};
 	char trace_pipe[PATH_MAX];
-	bool found_trace_pipe;
 	size_t buff_len = 0;
 
 	if (json_output)
 		jsonw_start_array(json_wtr);
 
-	found_trace_pipe = find_tracefs_pipe(trace_pipe);
-	if (!found_trace_pipe) {
-		p_err("could not find trace pipe, tracefs not mounted?");
+	if (!get_tracefs_pipe(trace_pipe))
 		return -1;
-	}
 
 	trace_pipe_fd = fopen(trace_pipe, "r");
 	if (!trace_pipe_fd) {
-- 
cgit v1.2.3


From 33221307c3f993500a9cfc6900811058c6bfc152 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Tue, 18 Dec 2018 10:13:19 +0000
Subject: tools: bpftool: add an option to prevent auto-mount of bpffs, tracefs

In order to make life easier for users, bpftool automatically attempts
to mount the BPF virtual file system, if it is not mounted already,
before trying to pin objects in it. Similarly, it attempts to mount
tracefs if necessary before trying to dump the trace pipe to the
console.

While mounting file systems on-the-fly can improve user experience, some
administrators might prefer to avoid that. Let's add an option to block
these mount attempts. Note that it does not prevent automatic mounting
of tracefs by debugfs for the "bpftool prog tracelog" command.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-map.rst  | 4 ++++
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 4 ++++
 tools/bpf/bpftool/Documentation/bpftool.rst      | 4 ++++
 tools/bpf/bpftool/common.c                       | 6 ++++++
 tools/bpf/bpftool/main.c                         | 8 +++++++-
 tools/bpf/bpftool/main.h                         | 4 +++-
 tools/bpf/bpftool/tracelog.c                     | 3 +++
 7 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index 3221be1b9ccc..64b001b4f777 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -128,6 +128,10 @@ OPTIONS
 	-f, --bpffs
 		  Show file names of pinned maps.
 
+	-n, --nomount
+		  Do not automatically attempt to mount any virtual file system
+		  (such as tracefs or BPF virtual file system) when necessary.
+
 EXAMPLES
 ========
 **# bpftool map show**
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 53920ffc48dd..58c8369b77dd 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -161,6 +161,10 @@ OPTIONS
 	-m, --mapcompat
 		  Allow loading maps with unknown map definitions.
 
+	-n, --nomount
+		  Do not automatically attempt to mount any virtual file system
+		  (such as tracefs or BPF virtual file system) when necessary.
+
 EXAMPLES
 ========
 **# bpftool prog show**
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 129b7a9c0f9b..e1677e81ed59 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -60,6 +60,10 @@ OPTIONS
 	-m, --mapcompat
 		  Allow loading maps with unknown map definitions.
 
+	-n, --nomount
+		  Do not automatically attempt to mount any virtual file system
+		  (such as tracefs or BPF virtual file system) when necessary.
+
 
 SEE ALSO
 ========
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 1bad6602a282..897483457bf0 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -177,6 +177,12 @@ int mount_bpffs_for_pin(const char *name)
 		/* nothing to do if already mounted */
 		goto out_free;
 
+	if (block_mount) {
+		p_err("no BPF file system found, not mounting it due to --nomount option");
+		err = -1;
+		goto out_free;
+	}
+
 	err = mnt_fs(dir, "bpf", err_str, ERR_MAX_LEN);
 	if (err) {
 		err_str[ERR_MAX_LEN - 1] = '\0';
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 9e657e7d5172..f44a1c2c4ea0 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -24,6 +24,7 @@ json_writer_t *json_wtr;
 bool pretty_output;
 bool json_output;
 bool show_pinned;
+bool block_mount;
 int bpf_flags;
 struct pinned_obj_table prog_table;
 struct pinned_obj_table map_table;
@@ -313,6 +314,7 @@ int main(int argc, char **argv)
 		{ "version",	no_argument,	NULL,	'V' },
 		{ "bpffs",	no_argument,	NULL,	'f' },
 		{ "mapcompat",	no_argument,	NULL,	'm' },
+		{ "nomount",	no_argument,	NULL,	'n' },
 		{ 0 }
 	};
 	int opt, ret;
@@ -321,13 +323,14 @@ int main(int argc, char **argv)
 	pretty_output = false;
 	json_output = false;
 	show_pinned = false;
+	block_mount = false;
 	bin_name = argv[0];
 
 	hash_init(prog_table.table);
 	hash_init(map_table.table);
 
 	opterr = 0;
-	while ((opt = getopt_long(argc, argv, "Vhpjfm",
+	while ((opt = getopt_long(argc, argv, "Vhpjfmn",
 				  options, NULL)) >= 0) {
 		switch (opt) {
 		case 'V':
@@ -354,6 +357,9 @@ int main(int argc, char **argv)
 		case 'm':
 			bpf_flags = MAPS_RELAX_COMPAT;
 			break;
+		case 'n':
+			block_mount = true;
+			break;
 		default:
 			p_err("unrecognized option '%s'", argv[optind - 1]);
 			if (json_output)
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 9e4499c926fa..052c91d4dc55 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -44,7 +44,8 @@
 #define HELP_SPEC_PROGRAM						\
 	"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
 #define HELP_SPEC_OPTIONS						\
-	"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} | {-m|--mapcompat}"
+	"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} |\n"	\
+	"\t            {-m|--mapcompat} | {-n|--nomount} }"
 #define HELP_SPEC_MAP							\
 	"MAP := { id MAP_ID | pinned FILE }"
 
@@ -85,6 +86,7 @@ extern const char *bin_name;
 extern json_writer_t *json_wtr;
 extern bool json_output;
 extern bool show_pinned;
+extern bool block_mount;
 extern int bpf_flags;
 extern struct pinned_obj_table prog_table;
 extern struct pinned_obj_table map_table;
diff --git a/tools/bpf/bpftool/tracelog.c b/tools/bpf/bpftool/tracelog.c
index 2dc36dfa0896..e80a5c79b38f 100644
--- a/tools/bpf/bpftool/tracelog.c
+++ b/tools/bpf/bpftool/tracelog.c
@@ -91,6 +91,9 @@ static bool get_tracefs_pipe(char *mnt)
 	if (found && validate_tracefs_mnt(mnt, TRACEFS_MAGIC))
 		goto exit_found;
 
+	if (block_mount)
+		return false;
+
 	p_info("could not find tracefs, attempting to mount it now");
 	/* Most of the time, tracefs is automatically mounted by debugfs at
 	 * /sys/kernel/debug/tracing when we try to access it. If we could not
-- 
cgit v1.2.3


From cda69d244585bc4497d3bb878c22fe2b6ad647c1 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Tue, 18 Dec 2018 19:37:48 +0800
Subject: net: hns3: fix error handling int the hns3_get_vector_ring_chain

When hns3_get_vector_ring_chain() failed in the
hns3_nic_init_vector_data(), it should do the error handling instead
of return directly.

Also, cur_chain should be freed instead of chain and head->next should
be set to NULL in error handling of hns3_get_vector_ring_chain.

This patch fixes them.

Fixes: 73b907a083b8 ("net: hns3: bugfix for buffer not free problem during resetting")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 69142a381064..2081e2eb18fd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2993,9 +2993,10 @@ err_free_chain:
 	cur_chain = head->next;
 	while (cur_chain) {
 		chain = cur_chain->next;
-		devm_kfree(&pdev->dev, chain);
+		devm_kfree(&pdev->dev, cur_chain);
 		cur_chain = chain;
 	}
+	head->next = NULL;
 
 	return -ENOMEM;
 }
@@ -3086,7 +3087,7 @@ static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv)
 		ret = hns3_get_vector_ring_chain(tqp_vector,
 						 &vector_ring_chain);
 		if (ret)
-			return ret;
+			goto map_ring_fail;
 
 		ret = h->ae_algo->ops->map_ring_to_vector(h,
 			tqp_vector->vector_irq, &vector_ring_chain);
-- 
cgit v1.2.3


From e3338205f0c700caae52a36cd0e3a815e6efd281 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Tue, 18 Dec 2018 19:37:49 +0800
Subject: net: hns3: uninitialize pci in the hclgevf_uninit

In the hclgevf_pci_reset(), it only uninitialize and initialize
the msi, so if the initialization fails, hclgevf_uninit_hdev()
does not need to uninitialize the msi, but needs to uninitialize
the pci, otherwise it will cause pci resource not free.

Fixes: 862d969a3a4d ("net: hns3: do VF's pci re-initialization while PF doing FLR")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 75327dcda3b0..86596ee18d90 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2401,9 +2401,9 @@ static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev)
 	if (test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) {
 		hclgevf_misc_irq_uninit(hdev);
 		hclgevf_uninit_msi(hdev);
-		hclgevf_pci_uninit(hdev);
 	}
 
+	hclgevf_pci_uninit(hdev);
 	hclgevf_cmd_uninit(hdev);
 }
 
-- 
cgit v1.2.3


From 531eba0fe2b5172ed0ab1cc6a311b2b6b9e6b402 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Tue, 18 Dec 2018 19:37:50 +0800
Subject: net: hns3: fix napi_disable not return problem

While doing DOWN, the calling of napi_disable() may not return, since the
napi_complete() in the hns3_nic_common_poll() will never be called when
HNS3_NIC_STATE_DOWN is set. So we need to call napi_complete() before
checking HNS3_NIC_STETE_DOWN.

Fixes: ff0699e04b97 ("net: hns3: stop napi polling when HNS3_NIC_STATE_DOWN is set")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 2081e2eb18fd..e7cde084ef33 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2909,8 +2909,8 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 
-	if (likely(!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) &&
-	    napi_complete(napi)) {
+	if (napi_complete(napi) &&
+	    likely(!test_bit(HNS3_NIC_STATE_DOWN, &priv->state))) {
 		hns3_update_new_int_gl(tqp_vector);
 		hns3_mask_vector_irq(tqp_vector, 1);
 	}
-- 
cgit v1.2.3


From b644a8d4cb18305d31383188da75615490b2c6ef Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Tue, 18 Dec 2018 19:37:51 +0800
Subject: net: hns3: update some variables while hclge_reset()/hclgevf_reset()
 done

When hclge_reset() completes successfully, it should update the
last_reset_time, set reset_fail_cnt to 0, and set reset_type of
hnae3_ae_dev to HNAE3_NONE_RESET.

Also when hclgevf_reset() completes successfully, it should update
the last_reset_time, and set reset_type of hnae3_ae_dev to
HNAE3_NONE_RESET.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c   | 5 ++++-
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 3 +++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 3fe08cf477f9..a8a2ccf150d9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2810,7 +2810,6 @@ static void hclge_reset(struct hclge_dev *hdev)
 	 */
 	ae_dev->reset_type = hdev->reset_type;
 	hdev->reset_count++;
-	hdev->last_reset_time = jiffies;
 	/* perform reset of the stack & ae device for a client */
 	ret = hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
 	if (ret)
@@ -2873,6 +2872,10 @@ static void hclge_reset(struct hclge_dev *hdev)
 	if (ret)
 		goto err_reset;
 
+	hdev->last_reset_time = jiffies;
+	hdev->reset_fail_cnt = 0;
+	ae_dev->reset_type = HNAE3_NONE_RESET;
+
 	return;
 
 err_reset_lock:
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 86596ee18d90..54ba93ac24dd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1342,6 +1342,9 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
 
 	rtnl_unlock();
 
+	hdev->last_reset_time = jiffies;
+	ae_dev->reset_type = HNAE3_NONE_RESET;
+
 	return ret;
 err_reset_lock:
 	rtnl_unlock();
-- 
cgit v1.2.3


From b51c366df70da0100193d13975980f1990a2d47b Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Tue, 18 Dec 2018 19:37:52 +0800
Subject: net: hns3: remove unnecessary configuration recapture while resetting

When doing reset, it is unnecessary to get the hardware's default
configuration again, otherwise, the user's configuration will be
overwritten.

Fixes: 4ed340ab8f49 ("net: hns3: Add reset process in hclge_main")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index a8a2ccf150d9..b66eee9ca6d5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7380,19 +7380,6 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
-	ret = hclge_get_cap(hdev);
-	if (ret) {
-		dev_err(&pdev->dev, "get hw capability error, ret = %d.\n",
-			ret);
-		return ret;
-	}
-
-	ret = hclge_configure(hdev);
-	if (ret) {
-		dev_err(&pdev->dev, "Configure dev error, ret = %d.\n", ret);
-		return ret;
-	}
-
 	ret = hclge_map_tqp(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "Map tqp error, ret = %d.\n", ret);
-- 
cgit v1.2.3


From ae6017a71115ebc4e5c1a3f0f451319ab3f5c447 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Tue, 18 Dec 2018 19:37:53 +0800
Subject: net: hns3: fix incomplete uninitialization of IRQ in the
 hns3_nic_uninit_vector_data()

In the hns3_nic_uninit_vector_data(), the procedure of uninitializing
the tqp_vector's IRQ has not set affinity_notify to NULL and changes
its init flag. This patch fixes it. And for simplificaton, local
variable tqp_vector is used instead of priv->tqp_vector[i].

Fixes: 424eb834a9be ("net: hns3: Unified HNS3 {VF|PF} Ethernet Driver for hip08 SoC")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index e7cde084ef33..354eca864229 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3181,12 +3181,12 @@ static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv)
 
 		hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain);
 
-		if (priv->tqp_vector[i].irq_init_flag == HNS3_VECTOR_INITED) {
-			(void)irq_set_affinity_hint(
-				priv->tqp_vector[i].vector_irq,
-						    NULL);
-			free_irq(priv->tqp_vector[i].vector_irq,
-				 &priv->tqp_vector[i]);
+		if (tqp_vector->irq_init_flag == HNS3_VECTOR_INITED) {
+			irq_set_affinity_notifier(tqp_vector->vector_irq,
+						  NULL);
+			irq_set_affinity_hint(tqp_vector->vector_irq, NULL);
+			free_irq(tqp_vector->vector_irq, tqp_vector);
+			tqp_vector->irq_init_flag = HNS3_VECTOR_NOT_INITED;
 		}
 
 		priv->ring_data[i].ring->irq_init_flag = HNS3_VECTOR_NOT_INITED;
-- 
cgit v1.2.3


From 7445565cd064679421e3cf4d440589ee723f6c08 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Tue, 18 Dec 2018 19:37:54 +0800
Subject: net: hns3: update coalesce param per second

coalesce param updates every 100 napi times, it may update a little
late if ping test after a high rate flow, may over napi poll is called
100 times as ping test sends packets every second.

This patch updates coalesce param every second, instead with every
100 napi times. It can not update the param 100% in time, but the
lag time is very short.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 8 +++-----
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 4 ----
 2 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 354eca864229..d060029ce142 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -240,7 +240,6 @@ static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector,
 	tqp_vector->tx_group.coal.int_gl = HNS3_INT_GL_50K;
 	tqp_vector->rx_group.coal.int_gl = HNS3_INT_GL_50K;
 
-	tqp_vector->int_adapt_down = HNS3_INT_ADAPT_DOWN_START;
 	tqp_vector->rx_group.coal.flow_level = HNS3_FLOW_LOW;
 	tqp_vector->tx_group.coal.flow_level = HNS3_FLOW_LOW;
 }
@@ -2846,10 +2845,10 @@ static void hns3_update_new_int_gl(struct hns3_enet_tqp_vector *tqp_vector)
 	struct hns3_enet_ring_group *tx_group = &tqp_vector->tx_group;
 	bool rx_update, tx_update;
 
-	if (tqp_vector->int_adapt_down > 0) {
-		tqp_vector->int_adapt_down--;
+	/* update param every 1000ms */
+	if (time_before(jiffies,
+			tqp_vector->last_jiffies + msecs_to_jiffies(1000)))
 		return;
-	}
 
 	if (rx_group->coal.gl_adapt_enable) {
 		rx_update = hns3_get_new_int_gl(rx_group);
@@ -2866,7 +2865,6 @@ static void hns3_update_new_int_gl(struct hns3_enet_tqp_vector *tqp_vector)
 	}
 
 	tqp_vector->last_jiffies = jiffies;
-	tqp_vector->int_adapt_down = HNS3_INT_ADAPT_DOWN_START;
 }
 
 static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 4e4b48ba78e3..e55995e93bb0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -476,8 +476,6 @@ enum hns3_link_mode_bits {
 #define HNS3_INT_RL_MAX			0x00EC
 #define HNS3_INT_RL_ENABLE_MASK		0x40
 
-#define HNS3_INT_ADAPT_DOWN_START	100
-
 struct hns3_enet_coalesce {
 	u16 int_gl;
 	u8 gl_adapt_enable;
@@ -512,8 +510,6 @@ struct hns3_enet_tqp_vector {
 
 	char name[HNAE3_INT_NAME_LEN];
 
-	/* when 0 should adjust interrupt coalesce parameter */
-	u8 int_adapt_down;
 	unsigned long last_jiffies;
 } ____cacheline_internodealigned_in_smp;
 
-- 
cgit v1.2.3


From 8362089d787724bb252f13f942921051943369c7 Mon Sep 17 00:00:00 2001
From: Fuyun Liang <liangfuyun1@huawei.com>
Date: Tue, 18 Dec 2018 19:37:55 +0800
Subject: net: hns3: remove 1000M/half support of phy

Our phy does not support 1000M/half, this patch removes 1000M/half from
PHY_SUPPORTED_FEATURES.

Signed-off-by: Fuyun Liang <liangfuyun1@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 741cb3b9519d..d8ef436ab2b9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -12,7 +12,7 @@
 					 SUPPORTED_TP | \
 					 PHY_10BT_FEATURES | \
 					 PHY_100BT_FEATURES | \
-					 PHY_1000BT_FEATURES)
+					 SUPPORTED_1000baseT_Full)
 
 enum hclge_mdio_c22_op_seq {
 	HCLGE_MDIO_C22_WRITE = 1,
-- 
cgit v1.2.3


From 0ad5ea5dbd6cb1e62bac547db5e61bab15af4f44 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Tue, 18 Dec 2018 19:37:56 +0800
Subject: net: hns3: synchronize speed and duplex from phy when phy link up

Driver calls phy_connect_direct and registers hclge_mac_adjust_link
to synchronize mac speed and duplex from phy. It is better to
synchronize mac speed and duplex from phy when phy link up.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index d8ef436ab2b9..dabb8437f8dc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -179,6 +179,10 @@ static void hclge_mac_adjust_link(struct net_device *netdev)
 	int duplex, speed;
 	int ret;
 
+	/* When phy link down, do nothing */
+	if (netdev->phydev->link == 0)
+		return;
+
 	speed = netdev->phydev->speed;
 	duplex = netdev->phydev->duplex;
 
-- 
cgit v1.2.3


From 368686be234daf365ef184a6ee1c4a6c18ede3b1 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Tue, 18 Dec 2018 19:37:57 +0800
Subject: net: hns3: getting tx and dv buffer size through firmware

This patch adds support of getting tx and dv buffer size through
firmware, because different version of hardware requires different
size of tx and dv buffer.

This patch also add dv_buf_size to tc' private buffer size even if
pfc is not enable for the tc.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |  5 ++-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 41 ++++++++++++++++------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  3 ++
 3 files changed, 38 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 47717800e0b5..f23042b24c09 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -420,7 +420,9 @@ struct hclge_pf_res_cmd {
 #define HCLGE_PF_VEC_NUM_M		GENMASK(7, 0)
 	__le16 pf_intr_vector_number;
 	__le16 pf_own_fun_number;
-	__le32 rsv[3];
+	__le16 tx_buf_size;
+	__le16 dv_buf_size;
+	__le32 rsv[2];
 };
 
 #define HCLGE_CFG_OFFSET_S	0
@@ -839,6 +841,7 @@ struct hclge_serdes_lb_cmd {
 #define HCLGE_TOTAL_PKT_BUF		0x108000 /* 1.03125M bytes */
 #define HCLGE_DEFAULT_DV		0xA000	 /* 40k byte */
 #define HCLGE_DEFAULT_NON_DCB_DV	0x7800	/* 30K byte */
+#define HCLGE_NON_DCB_ADDITIONAL_BUF	0x200	/* 512 byte */
 
 #define HCLGE_TYPE_CRQ			0
 #define HCLGE_TYPE_CSQ			1
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b66eee9ca6d5..c52e90333ab1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -687,6 +687,18 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 	hdev->num_tqps = __le16_to_cpu(req->tqp_num);
 	hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S;
 
+	if (req->tx_buf_size)
+		hdev->tx_buf_size =
+			__le16_to_cpu(req->tx_buf_size) << HCLGE_BUF_UNIT_S;
+	else
+		hdev->tx_buf_size = HCLGE_DEFAULT_TX_BUF;
+
+	if (req->dv_buf_size)
+		hdev->dv_buf_size =
+			__le16_to_cpu(req->dv_buf_size) << HCLGE_BUF_UNIT_S;
+	else
+		hdev->dv_buf_size = HCLGE_DEFAULT_DV;
+
 	if (hnae3_dev_roce_supported(hdev)) {
 		hdev->roce_base_msix_offset =
 		hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
@@ -1376,9 +1388,10 @@ static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev,
 	pfc_enable_num = hclge_get_pfc_enalbe_num(hdev);
 
 	if (hnae3_dev_dcb_supported(hdev))
-		shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_DV;
+		shared_buf_min = 2 * hdev->mps + hdev->dv_buf_size;
 	else
-		shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_NON_DCB_DV;
+		shared_buf_min = hdev->mps + HCLGE_NON_DCB_ADDITIONAL_BUF
+					+ hdev->dv_buf_size;
 
 	shared_buf_tc = pfc_enable_num * hdev->mps +
 			(tc_num - pfc_enable_num) * hdev->mps / 2 +
@@ -1391,8 +1404,15 @@ static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev,
 
 	shared_buf = rx_all - rx_priv;
 	buf_alloc->s_buf.buf_size = shared_buf;
-	buf_alloc->s_buf.self.high = shared_buf;
-	buf_alloc->s_buf.self.low =  2 * hdev->mps;
+	if (hnae3_dev_dcb_supported(hdev)) {
+		buf_alloc->s_buf.self.high = shared_buf - hdev->dv_buf_size;
+		buf_alloc->s_buf.self.low = buf_alloc->s_buf.self.high
+						- hdev->mps / 2;
+	} else {
+		buf_alloc->s_buf.self.high = hdev->mps +
+						HCLGE_NON_DCB_ADDITIONAL_BUF;
+		buf_alloc->s_buf.self.low = hdev->mps / 2;
+	}
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		if ((hdev->hw_tc_map & BIT(i)) &&
@@ -1419,11 +1439,11 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev,
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
 
-		if (total_size < HCLGE_DEFAULT_TX_BUF)
+		if (total_size < hdev->tx_buf_size)
 			return -ENOMEM;
 
 		if (hdev->hw_tc_map & BIT(i))
-			priv->tx_buf_size = HCLGE_DEFAULT_TX_BUF;
+			priv->tx_buf_size = hdev->tx_buf_size;
 		else
 			priv->tx_buf_size = 0;
 
@@ -1469,11 +1489,12 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
 				priv->wl.low = aligned_mps;
 				priv->wl.high = priv->wl.low + aligned_mps;
 				priv->buf_size = priv->wl.high +
-						HCLGE_DEFAULT_DV;
+						hdev->dv_buf_size;
 			} else {
 				priv->wl.low = 0;
 				priv->wl.high = 2 * aligned_mps;
-				priv->buf_size = priv->wl.high;
+				priv->buf_size = priv->wl.high +
+						hdev->dv_buf_size;
 			}
 		} else {
 			priv->enable = 0;
@@ -1505,11 +1526,11 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
 		if (hdev->tm_info.hw_pfc_map & BIT(i)) {
 			priv->wl.low = 128;
 			priv->wl.high = priv->wl.low + aligned_mps;
-			priv->buf_size = priv->wl.high + HCLGE_DEFAULT_DV;
+			priv->buf_size = priv->wl.high + hdev->dv_buf_size;
 		} else {
 			priv->wl.low = 0;
 			priv->wl.high = aligned_mps;
-			priv->buf_size = priv->wl.high;
+			priv->buf_size = priv->wl.high + hdev->dv_buf_size;
 		}
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 9571e228ab42..6615b85a1c52 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -736,6 +736,9 @@ struct hclge_dev {
 	u32 flag;
 
 	u32 pkt_buf_size; /* Total pf buf size for tx/rx */
+	u32 tx_buf_size; /* Tx buffer size for each TC */
+	u32 dv_buf_size; /* Dv buffer size for each TC */
+
 	u32 mps; /* Max packet size */
 	/* vport_lock protect resource shared by vports */
 	struct mutex vport_lock;
-- 
cgit v1.2.3


From b9a400ac295728b2d47445e09814e1880409b311 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Tue, 18 Dec 2018 19:37:58 +0800
Subject: net: hns3: aligning buffer size in SSU to 256 bytes

The hardware expects the buffer size set to SSU is aligned to
256 bytes, this patch aligns the buffer size to 256 byte using
roundup or rounddown function.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 43 +++++++++++++---------
 1 file changed, 26 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index c52e90333ab1..f847fdebf64e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -26,6 +26,8 @@
 #define HCLGE_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset))))
 #define HCLGE_MAC_STATS_FIELD_OFF(f) (offsetof(struct hclge_mac_stats, f))
 
+#define HCLGE_BUF_SIZE_UNIT	256
+
 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps);
 static int hclge_init_vlan_config(struct hclge_dev *hdev);
 static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev);
@@ -693,12 +695,16 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 	else
 		hdev->tx_buf_size = HCLGE_DEFAULT_TX_BUF;
 
+	hdev->tx_buf_size = roundup(hdev->tx_buf_size, HCLGE_BUF_SIZE_UNIT);
+
 	if (req->dv_buf_size)
 		hdev->dv_buf_size =
 			__le16_to_cpu(req->dv_buf_size) << HCLGE_BUF_UNIT_S;
 	else
 		hdev->dv_buf_size = HCLGE_DEFAULT_DV;
 
+	hdev->dv_buf_size = roundup(hdev->dv_buf_size, HCLGE_BUF_SIZE_UNIT);
+
 	if (hnae3_dev_roce_supported(hdev)) {
 		hdev->roce_base_msix_offset =
 		hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
@@ -1380,48 +1386,50 @@ static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev,
 {
 	u32 shared_buf_min, shared_buf_tc, shared_std;
 	int tc_num, pfc_enable_num;
-	u32 shared_buf;
+	u32 shared_buf, aligned_mps;
 	u32 rx_priv;
 	int i;
 
 	tc_num = hclge_get_tc_num(hdev);
 	pfc_enable_num = hclge_get_pfc_enalbe_num(hdev);
+	aligned_mps = roundup(hdev->mps, HCLGE_BUF_SIZE_UNIT);
 
 	if (hnae3_dev_dcb_supported(hdev))
-		shared_buf_min = 2 * hdev->mps + hdev->dv_buf_size;
+		shared_buf_min = 2 * aligned_mps + hdev->dv_buf_size;
 	else
-		shared_buf_min = hdev->mps + HCLGE_NON_DCB_ADDITIONAL_BUF
+		shared_buf_min = aligned_mps + HCLGE_NON_DCB_ADDITIONAL_BUF
 					+ hdev->dv_buf_size;
 
-	shared_buf_tc = pfc_enable_num * hdev->mps +
-			(tc_num - pfc_enable_num) * hdev->mps / 2 +
-			hdev->mps;
+	shared_buf_tc = pfc_enable_num * aligned_mps +
+			(tc_num - pfc_enable_num) * aligned_mps / 2 +
+			aligned_mps;
 	shared_std = max_t(u32, shared_buf_min, shared_buf_tc);
 
 	rx_priv = hclge_get_rx_priv_buff_alloced(buf_alloc);
 	if (rx_all <= rx_priv + shared_std)
 		return false;
 
-	shared_buf = rx_all - rx_priv;
+	shared_buf = rounddown(rx_all - rx_priv, HCLGE_BUF_SIZE_UNIT);
 	buf_alloc->s_buf.buf_size = shared_buf;
 	if (hnae3_dev_dcb_supported(hdev)) {
 		buf_alloc->s_buf.self.high = shared_buf - hdev->dv_buf_size;
 		buf_alloc->s_buf.self.low = buf_alloc->s_buf.self.high
-						- hdev->mps / 2;
+			- roundup(aligned_mps / 2, HCLGE_BUF_SIZE_UNIT);
 	} else {
-		buf_alloc->s_buf.self.high = hdev->mps +
+		buf_alloc->s_buf.self.high = aligned_mps +
 						HCLGE_NON_DCB_ADDITIONAL_BUF;
-		buf_alloc->s_buf.self.low = hdev->mps / 2;
+		buf_alloc->s_buf.self.low =
+			roundup(aligned_mps / 2, HCLGE_BUF_SIZE_UNIT);
 	}
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		if ((hdev->hw_tc_map & BIT(i)) &&
 		    (hdev->tm_info.hw_pfc_map & BIT(i))) {
-			buf_alloc->s_buf.tc_thrd[i].low = hdev->mps;
-			buf_alloc->s_buf.tc_thrd[i].high = 2 * hdev->mps;
+			buf_alloc->s_buf.tc_thrd[i].low = aligned_mps;
+			buf_alloc->s_buf.tc_thrd[i].high = 2 * aligned_mps;
 		} else {
 			buf_alloc->s_buf.tc_thrd[i].low = 0;
-			buf_alloc->s_buf.tc_thrd[i].high = hdev->mps;
+			buf_alloc->s_buf.tc_thrd[i].high = aligned_mps;
 		}
 	}
 
@@ -1461,7 +1469,6 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev,
 static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
 				struct hclge_pkt_buf_alloc *buf_alloc)
 {
-#define HCLGE_BUF_SIZE_UNIT	128
 	u32 rx_all = hdev->pkt_buf_size, aligned_mps;
 	int no_pfc_priv_num, pfc_priv_num;
 	struct hclge_priv_buf *priv;
@@ -1487,9 +1494,11 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
 			priv->enable = 1;
 			if (hdev->tm_info.hw_pfc_map & BIT(i)) {
 				priv->wl.low = aligned_mps;
-				priv->wl.high = priv->wl.low + aligned_mps;
+				priv->wl.high =
+					roundup(priv->wl.low + aligned_mps,
+						HCLGE_BUF_SIZE_UNIT);
 				priv->buf_size = priv->wl.high +
-						hdev->dv_buf_size;
+					hdev->dv_buf_size;
 			} else {
 				priv->wl.low = 0;
 				priv->wl.high = 2 * aligned_mps;
@@ -1524,7 +1533,7 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
 		priv->enable = 1;
 
 		if (hdev->tm_info.hw_pfc_map & BIT(i)) {
-			priv->wl.low = 128;
+			priv->wl.low = 256;
 			priv->wl.high = priv->wl.low + aligned_mps;
 			priv->buf_size = priv->wl.high + hdev->dv_buf_size;
 		} else {
-- 
cgit v1.2.3


From af854724e51e4047f534ac6d19b3ef9fb3c35c49 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Tue, 18 Dec 2018 19:37:59 +0800
Subject: net: hns3: fix a SSU buffer checking bug

When caculating the SSU buffer, it first allocate tx and
rx private buffer, then the remaining buffer is for rx
shared buffer. The remaining buffer size should be at
least bigger than or equal to the shared_std, which is the
minimum shared buffer size required by the driver, but
currently if the remaining buffer size is equal to the
shared_std, it returns failure, which causes SSU buffer
allocation failure problem.

This patch fixes this problem by rounding up shared_std before
checking the the remaining buffer size bigger than or equal to
the shared_std.

Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index f847fdebf64e..d0e84de39fa3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1403,10 +1403,11 @@ static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev,
 	shared_buf_tc = pfc_enable_num * aligned_mps +
 			(tc_num - pfc_enable_num) * aligned_mps / 2 +
 			aligned_mps;
-	shared_std = max_t(u32, shared_buf_min, shared_buf_tc);
+	shared_std = roundup(max_t(u32, shared_buf_min, shared_buf_tc),
+			     HCLGE_BUF_SIZE_UNIT);
 
 	rx_priv = hclge_get_rx_priv_buff_alloced(buf_alloc);
-	if (rx_all <= rx_priv + shared_std)
+	if (rx_all < rx_priv + shared_std)
 		return false;
 
 	shared_buf = rounddown(rx_all - rx_priv, HCLGE_BUF_SIZE_UNIT);
-- 
cgit v1.2.3


From a38d1107f937ca95dcf820161ef44ea683d6a0b1 Mon Sep 17 00:00:00 2001
From: Matt Mullins <mmullins@fb.com>
Date: Wed, 12 Dec 2018 16:42:37 -0800
Subject: bpf: support raw tracepoints in modules

Distributions build drivers as modules, including network and filesystem
drivers which export numerous tracepoints.  This enables
bpf(BPF_RAW_TRACEPOINT_OPEN) to attach to those tracepoints.

Signed-off-by: Matt Mullins <mmullins@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/module.h       |  4 ++
 include/linux/trace_events.h |  8 +++-
 kernel/bpf/syscall.c         | 11 +++--
 kernel/module.c              |  5 +++
 kernel/trace/bpf_trace.c     | 99 +++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 120 insertions(+), 7 deletions(-)

diff --git a/include/linux/module.h b/include/linux/module.h
index fce6b4335e36..5f147dd5e709 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -432,6 +432,10 @@ struct module {
 	unsigned int num_tracepoints;
 	tracepoint_ptr_t *tracepoints_ptrs;
 #endif
+#ifdef CONFIG_BPF_EVENTS
+	unsigned int num_bpf_raw_events;
+	struct bpf_raw_event_map *bpf_raw_events;
+#endif
 #ifdef HAVE_JUMP_LABEL
 	struct jump_entry *jump_entries;
 	unsigned int num_jump_entries;
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 4130a5497d40..8a62731673f7 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -471,7 +471,8 @@ void perf_event_detach_bpf_prog(struct perf_event *event);
 int perf_event_query_prog_array(struct perf_event *event, void __user *info);
 int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
 int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
-struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name);
+struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name);
+void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp);
 int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 			    u32 *fd_type, const char **buf,
 			    u64 *probe_offset, u64 *probe_addr);
@@ -502,10 +503,13 @@ static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf
 {
 	return -EOPNOTSUPP;
 }
-static inline struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
+static inline struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name)
 {
 	return NULL;
 }
+static inline void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
+{
+}
 static inline int bpf_get_perf_event_info(const struct perf_event *event,
 					  u32 *prog_id, u32 *fd_type,
 					  const char **buf, u64 *probe_offset,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5db31067d85e..0607db304def 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1604,6 +1604,7 @@ static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp)
 		bpf_probe_unregister(raw_tp->btp, raw_tp->prog);
 		bpf_prog_put(raw_tp->prog);
 	}
+	bpf_put_raw_tracepoint(raw_tp->btp);
 	kfree(raw_tp);
 	return 0;
 }
@@ -1629,13 +1630,15 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 		return -EFAULT;
 	tp_name[sizeof(tp_name) - 1] = 0;
 
-	btp = bpf_find_raw_tracepoint(tp_name);
+	btp = bpf_get_raw_tracepoint(tp_name);
 	if (!btp)
 		return -ENOENT;
 
 	raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER);
-	if (!raw_tp)
-		return -ENOMEM;
+	if (!raw_tp) {
+		err = -ENOMEM;
+		goto out_put_btp;
+	}
 	raw_tp->btp = btp;
 
 	prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd,
@@ -1663,6 +1666,8 @@ out_put_prog:
 	bpf_prog_put(prog);
 out_free_tp:
 	kfree(raw_tp);
+out_put_btp:
+	bpf_put_raw_tracepoint(btp);
 	return err;
 }
 
diff --git a/kernel/module.c b/kernel/module.c
index 49a405891587..06ec68f08387 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3093,6 +3093,11 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 					     sizeof(*mod->tracepoints_ptrs),
 					     &mod->num_tracepoints);
 #endif
+#ifdef CONFIG_BPF_EVENTS
+	mod->bpf_raw_events = section_objs(info, "__bpf_raw_tp_map",
+					   sizeof(*mod->bpf_raw_events),
+					   &mod->num_bpf_raw_events);
+#endif
 #ifdef HAVE_JUMP_LABEL
 	mod->jump_entries = section_objs(info, "__jump_table",
 					sizeof(*mod->jump_entries),
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 9864a35c8bb5..9ddb6fddb4e0 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -17,6 +17,43 @@
 #include "trace_probe.h"
 #include "trace.h"
 
+#ifdef CONFIG_MODULES
+struct bpf_trace_module {
+	struct module *module;
+	struct list_head list;
+};
+
+static LIST_HEAD(bpf_trace_modules);
+static DEFINE_MUTEX(bpf_module_mutex);
+
+static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name)
+{
+	struct bpf_raw_event_map *btp, *ret = NULL;
+	struct bpf_trace_module *btm;
+	unsigned int i;
+
+	mutex_lock(&bpf_module_mutex);
+	list_for_each_entry(btm, &bpf_trace_modules, list) {
+		for (i = 0; i < btm->module->num_bpf_raw_events; ++i) {
+			btp = &btm->module->bpf_raw_events[i];
+			if (!strcmp(btp->tp->name, name)) {
+				if (try_module_get(btm->module))
+					ret = btp;
+				goto out;
+			}
+		}
+	}
+out:
+	mutex_unlock(&bpf_module_mutex);
+	return ret;
+}
+#else
+static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name)
+{
+	return NULL;
+}
+#endif /* CONFIG_MODULES */
+
 u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 
@@ -1076,7 +1113,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 extern struct bpf_raw_event_map __start__bpf_raw_tp[];
 extern struct bpf_raw_event_map __stop__bpf_raw_tp[];
 
-struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
+struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name)
 {
 	struct bpf_raw_event_map *btp = __start__bpf_raw_tp;
 
@@ -1084,7 +1121,16 @@ struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
 		if (!strcmp(btp->tp->name, name))
 			return btp;
 	}
-	return NULL;
+
+	return bpf_get_raw_tracepoint_module(name);
+}
+
+void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
+{
+	struct module *mod = __module_address((unsigned long)btp);
+
+	if (mod)
+		module_put(mod);
 }
 
 static __always_inline
@@ -1222,3 +1268,52 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 
 	return err;
 }
+
+#ifdef CONFIG_MODULES
+int bpf_event_notify(struct notifier_block *nb, unsigned long op, void *module)
+{
+	struct bpf_trace_module *btm, *tmp;
+	struct module *mod = module;
+
+	if (mod->num_bpf_raw_events == 0 ||
+	    (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING))
+		return 0;
+
+	mutex_lock(&bpf_module_mutex);
+
+	switch (op) {
+	case MODULE_STATE_COMING:
+		btm = kzalloc(sizeof(*btm), GFP_KERNEL);
+		if (btm) {
+			btm->module = module;
+			list_add(&btm->list, &bpf_trace_modules);
+		}
+		break;
+	case MODULE_STATE_GOING:
+		list_for_each_entry_safe(btm, tmp, &bpf_trace_modules, list) {
+			if (btm->module == module) {
+				list_del(&btm->list);
+				kfree(btm);
+				break;
+			}
+		}
+		break;
+	}
+
+	mutex_unlock(&bpf_module_mutex);
+
+	return 0;
+}
+
+static struct notifier_block bpf_module_nb = {
+	.notifier_call = bpf_event_notify,
+};
+
+int __init bpf_event_init(void)
+{
+	register_module_notifier(&bpf_module_nb);
+	return 0;
+}
+
+fs_initcall(bpf_event_init);
+#endif /* CONFIG_MODULES */
-- 
cgit v1.2.3


From 0bae2d4d62d523f06ff1a8e88ce38b45400acd28 Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Sat, 15 Dec 2018 03:34:40 -0500
Subject: bpf: correct slot_type marking logic to allow more stack slot sharing

Verifier is supposed to support sharing stack slot allocated to ptr with
SCALAR_VALUE for privileged program. However this doesn't happen for some
cases.

The reason is verifier is not clearing slot_type STACK_SPILL for all bytes,
it only clears part of them, while verifier is using:

  slot_type[0] == STACK_SPILL

as a convention to check one slot is ptr type.

So, the consequence of partial clearing slot_type is verifier could treat a
partially overridden ptr slot, which should now be a SCALAR_VALUE slot,
still as ptr slot, and rejects some valid programs.

Before this patch, test_xdp_noinline.o under bpf selftests, bpf_lxc.o and
bpf_netdev.o under Cilium bpf repo, when built with -mattr=+alu32 are
rejected due to this issue. After this patch, they all accepted.

There is no processed insn number change before and after this patch on
Cilium bpf programs.

Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                       |  5 +++++
 tools/testing/selftests/bpf/test_verifier.c | 34 +++++++++++++++++++++++++++--
 2 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0125731e2512..e0e77ffeefb8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1286,6 +1286,10 @@ static int check_stack_write(struct bpf_verifier_env *env,
 
 		/* regular write of data into stack destroys any spilled ptr */
 		state->stack[spi].spilled_ptr.type = NOT_INIT;
+		/* Mark slots as STACK_MISC if they belonged to spilled ptr. */
+		if (state->stack[spi].slot_type[0] == STACK_SPILL)
+			for (i = 0; i < BPF_REG_SIZE; i++)
+				state->stack[spi].slot_type[i] = STACK_MISC;
 
 		/* only mark the slot as written if all 8 bytes were written
 		 * otherwise read propagation may incorrectly stop too soon
@@ -1303,6 +1307,7 @@ static int check_stack_write(struct bpf_verifier_env *env,
 		    register_is_null(&cur->regs[value_regno]))
 			type = STACK_ZERO;
 
+		/* Mark slots affected by this stack write. */
 		for (i = 0; i < size; i++)
 			state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
 				type;
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index f9de7fe0c26d..cf242734e2eb 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1001,14 +1001,44 @@ static struct bpf_test tests[] = {
 			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
 			/* mess up with R1 pointer on stack */
 			BPF_ST_MEM(BPF_B, BPF_REG_10, -7, 0x23),
-			/* fill back into R0 should fail */
+			/* fill back into R0 is fine for priv.
+			 * R0 now becomes SCALAR_VALUE.
+			 */
 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+			/* Load from R0 should fail. */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8),
 			BPF_EXIT_INSN(),
 		},
 		.errstr_unpriv = "attempt to corrupt spilled",
-		.errstr = "corrupted spill",
+		.errstr = "R0 invalid mem access 'inv",
 		.result = REJECT,
 	},
+	{
+		"check corrupted spill/fill, LSB",
+		.insns = {
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+			BPF_ST_MEM(BPF_H, BPF_REG_10, -8, 0xcafe),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+			BPF_EXIT_INSN(),
+		},
+		.errstr_unpriv = "attempt to corrupt spilled",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+		.retval = POINTER_VALUE,
+	},
+	{
+		"check corrupted spill/fill, MSB",
+		.insns = {
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+			BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0x12345678),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+			BPF_EXIT_INSN(),
+		},
+		.errstr_unpriv = "attempt to corrupt spilled",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+		.retval = POINTER_VALUE,
+	},
 	{
 		"invalid src register in STX",
 		.insns = {
-- 
cgit v1.2.3


From 3379b3bfb71de154f44bca297f3aa039c5b12852 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sun, 16 Dec 2018 13:33:15 +0000
Subject: bonding: fix indentation issues, remove extra spaces

There are two statements that are indented too much by one space each,
fix these.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_3ad.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 93dfcef8afc4..7c46d9f4fefd 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -1220,7 +1220,7 @@ static void ad_churn_machine(struct port *port)
 		port->sm_churn_partner_state = AD_CHURN_MONITOR;
 		port->sm_churn_actor_timer_counter =
 			__ad_timer_to_ticks(AD_ACTOR_CHURN_TIMER, 0);
-		 port->sm_churn_partner_timer_counter =
+		port->sm_churn_partner_timer_counter =
 			 __ad_timer_to_ticks(AD_PARTNER_CHURN_TIMER, 0);
 		return;
 	}
@@ -2128,7 +2128,7 @@ void bond_3ad_unbind_slave(struct slave *slave)
 				if ((new_aggregator->lag_ports == port) &&
 				    new_aggregator->is_active) {
 					netdev_info(bond->dev, "Removing an active aggregator\n");
-					 select_new_active_agg = 1;
+					select_new_active_agg = 1;
 				}
 
 				new_aggregator->is_individual = aggregator->is_individual;
-- 
cgit v1.2.3


From 2429f13870d3d2abbe200807d0462272e16ec830 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 16 Dec 2018 15:00:40 +0100
Subject: net: fec: remove workaround to restart phylib state machine on MDIO
 timeout

There's a workaround to restart the phylib state machine in case of a
MDIO access timeout. Seems it was introduced to deal with the
consequences of a too small MDIO timeout. See also commit message of
c3b084c24c8a ("net: fec: Adjust ENET MDIO timeouts") which increased
the timeout value later. Due to the later timeout value fix it seems
to be safe to remove the workaround.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec.h      |  1 -
 drivers/net/ethernet/freescale/fec_main.c | 12 ------------
 2 files changed, 13 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index bf80855dd0dd..f79e57f735b3 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -531,7 +531,6 @@ struct fec_enet_private {
 
 	/* Phylib and MDIO interface */
 	struct	mii_bus *mii_bus;
-	int	mii_timeout;
 	uint	phy_speed;
 	phy_interface_t	phy_interface;
 	struct device_node *phy_node;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 6db69ba30dcd..ae0f88bce9aa 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1714,12 +1714,6 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 	struct phy_device *phy_dev = ndev->phydev;
 	int status_change = 0;
 
-	/* Prevent a state halted on mii error */
-	if (fep->mii_timeout && phy_dev->state == PHY_HALTED) {
-		phy_dev->state = PHY_RESUMING;
-		return;
-	}
-
 	/*
 	 * If the netdev is down, or is going down, we're not interested
 	 * in link state events, so just mark our idea of the link as down
@@ -1779,7 +1773,6 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	if (ret < 0)
 		return ret;
 
-	fep->mii_timeout = 0;
 	reinit_completion(&fep->mdio_done);
 
 	/* start a read op */
@@ -1791,7 +1784,6 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	time_left = wait_for_completion_timeout(&fep->mdio_done,
 			usecs_to_jiffies(FEC_MII_TIMEOUT));
 	if (time_left == 0) {
-		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO read timeout\n");
 		ret = -ETIMEDOUT;
 		goto out;
@@ -1820,7 +1812,6 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	else
 		ret = 0;
 
-	fep->mii_timeout = 0;
 	reinit_completion(&fep->mdio_done);
 
 	/* start a write op */
@@ -1833,7 +1824,6 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	time_left = wait_for_completion_timeout(&fep->mdio_done,
 			usecs_to_jiffies(FEC_MII_TIMEOUT));
 	if (time_left == 0) {
-		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO write timeout\n");
 		ret  = -ETIMEDOUT;
 	}
@@ -2001,8 +1991,6 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
-	fep->mii_timeout = 0;
-
 	/*
 	 * Set MII speed to 2.5 MHz (= clk_get_rate() / 2 * phy_speed)
 	 *
-- 
cgit v1.2.3


From 2b3e88ea65287ba738a798622405b15344871085 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 16 Dec 2018 18:30:14 +0100
Subject: net: phy: improve phy state checking

Add helpers phy_is_started() and __phy_is_started() to avoid open-coded
checks whether PHY has been started. To make the check easier move
PHY_HALTED before PHY_UP in enum phy_state. Further improvements:

phy_start_aneg():
Return -EBUSY and print warning if function is called from a non-started
state (DOWN, READY, HALTED). Better check because function is exported
and drivers may use it incorrectly.

phy_interrupt():
Return IRQ_NONE also if state is DOWN or READY. We should never receive
an interrupt in one of these states, but better play safe.

phy_stop():
Just return and print a warning if PHY is in a non-started state.
This warning should help to identify drivers with unbalanced calls to
phy_start() / phy_stop().

phy_state_machine():
Schedule state machine run only if PHY is in a started state.
E.g. if state is READY we don't need the state machine, it will be
started by phy_start().

v2:
- don't use __func__ within phy_warn_state
v3:
- use WARN() instead of printing error message to facilitate debugging

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 34 +++++++++++++++++++++-------------
 include/linux/phy.h   | 24 +++++++++++++++++++++++-
 2 files changed, 44 insertions(+), 14 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index e24708f1fc16..21df28b9882c 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -543,6 +543,13 @@ int phy_start_aneg(struct phy_device *phydev)
 
 	mutex_lock(&phydev->lock);
 
+	if (!__phy_is_started(phydev)) {
+		WARN(1, "called from state %s\n",
+		     phy_state_to_str(phydev->state));
+		err = -EBUSY;
+		goto out_unlock;
+	}
+
 	if (AUTONEG_DISABLE == phydev->autoneg)
 		phy_sanitize_settings(phydev);
 
@@ -553,13 +560,11 @@ int phy_start_aneg(struct phy_device *phydev)
 	if (err < 0)
 		goto out_unlock;
 
-	if (phydev->state != PHY_HALTED) {
-		if (AUTONEG_ENABLE == phydev->autoneg) {
-			err = phy_check_link_status(phydev);
-		} else {
-			phydev->state = PHY_FORCING;
-			phydev->link_timeout = PHY_FORCE_TIMEOUT;
-		}
+	if (phydev->autoneg == AUTONEG_ENABLE) {
+		err = phy_check_link_status(phydev);
+	} else {
+		phydev->state = PHY_FORCING;
+		phydev->link_timeout = PHY_FORCE_TIMEOUT;
 	}
 
 out_unlock:
@@ -709,7 +714,7 @@ void phy_stop_machine(struct phy_device *phydev)
 	cancel_delayed_work_sync(&phydev->state_queue);
 
 	mutex_lock(&phydev->lock);
-	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
+	if (__phy_is_started(phydev))
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
 }
@@ -760,7 +765,7 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 {
 	struct phy_device *phydev = phy_dat;
 
-	if (PHY_HALTED == phydev->state)
+	if (!phy_is_started(phydev))
 		return IRQ_NONE;		/* It can't be ours.  */
 
 	if (phydev->drv->did_interrupt && !phydev->drv->did_interrupt(phydev))
@@ -842,15 +847,18 @@ void phy_stop(struct phy_device *phydev)
 {
 	mutex_lock(&phydev->lock);
 
-	if (PHY_HALTED == phydev->state)
-		goto out_unlock;
+	if (!__phy_is_started(phydev)) {
+		WARN(1, "called from state %s\n",
+		     phy_state_to_str(phydev->state));
+		mutex_unlock(&phydev->lock);
+		return;
+	}
 
 	if (phy_interrupt_is_valid(phydev))
 		phy_disable_interrupts(phydev);
 
 	phydev->state = PHY_HALTED;
 
-out_unlock:
 	mutex_unlock(&phydev->lock);
 
 	phy_state_machine(&phydev->state_queue.work);
@@ -984,7 +992,7 @@ void phy_state_machine(struct work_struct *work)
 	 * state machine would be pointless and possibly error prone when
 	 * called from phy_disconnect() synchronously.
 	 */
-	if (phy_polling_mode(phydev) && old_state != PHY_HALTED)
+	if (phy_polling_mode(phydev) && phy_is_started(phydev))
 		phy_queue_state_machine(phydev, PHY_STATE_TIME);
 }
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 8f927246acdb..da039f211c22 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -319,12 +319,12 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
 enum phy_state {
 	PHY_DOWN = 0,
 	PHY_READY,
+	PHY_HALTED,
 	PHY_UP,
 	PHY_RUNNING,
 	PHY_NOLINK,
 	PHY_FORCING,
 	PHY_CHANGELINK,
-	PHY_HALTED,
 	PHY_RESUMING
 };
 
@@ -669,6 +669,28 @@ phy_lookup_setting(int speed, int duplex, const unsigned long *mask,
 size_t phy_speeds(unsigned int *speeds, size_t size,
 		  unsigned long *mask);
 
+static inline bool __phy_is_started(struct phy_device *phydev)
+{
+	WARN_ON(!mutex_is_locked(&phydev->lock));
+
+	return phydev->state >= PHY_UP;
+}
+
+/**
+ * phy_is_started - Convenience function to check whether PHY is started
+ * @phydev: The phy_device struct
+ */
+static inline bool phy_is_started(struct phy_device *phydev)
+{
+	bool started;
+
+	mutex_lock(&phydev->lock);
+	started = __phy_is_started(phydev);
+	mutex_unlock(&phydev->lock);
+
+	return started;
+}
+
 void phy_resolve_aneg_linkmode(struct phy_device *phydev);
 
 /**
-- 
cgit v1.2.3


From fa7b28c11bbf389617327ad4dd69bbbbbc16a8b4 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 16 Dec 2018 19:18:26 +0100
Subject: net: phy: print stack trace in phy_error

So far phy_error() silently stops the PHY state machine. If the network
driver doesn't inform about a  MDIO error then the user may wonder why
his network is down. Let's print the stack trace to facilitate search
for the root cause of the error.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 21df28b9882c..d33e7b3caf03 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -730,6 +730,8 @@ void phy_stop_machine(struct phy_device *phydev)
  */
 static void phy_error(struct phy_device *phydev)
 {
+	WARN_ON(1);
+
 	mutex_lock(&phydev->lock);
 	phydev->state = PHY_HALTED;
 	mutex_unlock(&phydev->lock);
-- 
cgit v1.2.3


From 809c67059162e7ba85c61a83ad7547b4ffbb1e6e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Sun, 16 Dec 2018 20:48:21 +0100
Subject: test_rhashtable: remove semaphore usage

This is one of only two files that initialize a semaphore to a negative
value. We don't really need the two semaphores here at all, but can do
the same thing in more conventional and more effient way, by using a
single waitqueue and an atomic thread counter.

This gets us a little bit closer to eliminating classic semaphores from
the kernel. It also fixes a corner case where we fail to continue after
one of the threads fails to start up.

An alternative would be to use a split kthread_create()+wake_up_process()
and completely eliminate the separate synchronization.

Acked-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/test_rhashtable.c | 32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 82ac39ce5310..6a8ac7626797 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -20,11 +20,11 @@
 #include <linux/module.h>
 #include <linux/rcupdate.h>
 #include <linux/rhashtable.h>
-#include <linux/semaphore.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/random.h>
 #include <linux/vmalloc.h>
+#include <linux/wait.h>
 
 #define MAX_ENTRIES	1000000
 #define TEST_INSERT_FAIL INT_MAX
@@ -112,8 +112,8 @@ static struct rhashtable_params test_rht_params_dup = {
 	.automatic_shrinking = false,
 };
 
-static struct semaphore prestart_sem;
-static struct semaphore startup_sem = __SEMAPHORE_INITIALIZER(startup_sem, 0);
+static atomic_t startup_count;
+static DECLARE_WAIT_QUEUE_HEAD(startup_wait);
 
 static int insert_retry(struct rhashtable *ht, struct test_obj *obj,
                         const struct rhashtable_params params)
@@ -634,9 +634,12 @@ static int threadfunc(void *data)
 	int i, step, err = 0, insert_retries = 0;
 	struct thread_data *tdata = data;
 
-	up(&prestart_sem);
-	if (down_interruptible(&startup_sem))
-		pr_err("  thread[%d]: down_interruptible failed\n", tdata->id);
+	if (atomic_dec_and_test(&startup_count))
+		wake_up(&startup_wait);
+	if (wait_event_interruptible(startup_wait, atomic_read(&startup_count) == -1)) {
+		pr_err("  thread[%d]: interrupted\n", tdata->id);
+		goto out;
+	}
 
 	for (i = 0; i < tdata->entries; i++) {
 		tdata->objs[i].value.id = i;
@@ -755,7 +758,7 @@ static int __init test_rht_init(void)
 
 	pr_info("Testing concurrent rhashtable access from %d threads\n",
 	        tcount);
-	sema_init(&prestart_sem, 1 - tcount);
+	atomic_set(&startup_count, tcount);
 	tdata = vzalloc(array_size(tcount, sizeof(struct thread_data)));
 	if (!tdata)
 		return -ENOMEM;
@@ -781,15 +784,18 @@ static int __init test_rht_init(void)
 		tdata[i].objs = objs + i * entries;
 		tdata[i].task = kthread_run(threadfunc, &tdata[i],
 		                            "rhashtable_thrad[%d]", i);
-		if (IS_ERR(tdata[i].task))
+		if (IS_ERR(tdata[i].task)) {
 			pr_err(" kthread_run failed for thread %d\n", i);
-		else
+			atomic_dec(&startup_count);
+		} else {
 			started_threads++;
+		}
 	}
-	if (down_interruptible(&prestart_sem))
-		pr_err("  down interruptible failed\n");
-	for (i = 0; i < tcount; i++)
-		up(&startup_sem);
+	if (wait_event_interruptible(startup_wait, atomic_read(&startup_count) == 0))
+		pr_err("  wait_event interruptible failed\n");
+	/* count is 0 now, set it to -1 and wake up all threads together */
+	atomic_dec(&startup_count);
+	wake_up_all(&startup_wait);
 	for (i = 0; i < tcount; i++) {
 		if (IS_ERR(tdata[i].task))
 			continue;
-- 
cgit v1.2.3


From 3bdbd0228e7555ec745e08469b98e5a0966409d6 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 16 Dec 2018 15:47:04 -0800
Subject: bpf: sockmap, metadata support for reporting size of msg

This adds metadata to sk_msg_md for BPF programs to read the sk_msg
size.

When the SK_MSG program is running under an application that is using
sendfile the data is not copied into sk_msg buffers by default. Rather
the BPF program uses sk_msg_pull_data to read the bytes in. This
avoids doing the costly memcopy instructions when they are not in
fact needed. However, if we don't know the size of the sk_msg we
have to guess if needed bytes are available by doing a pull request
which may fail. By including the size of the sk_msg BPF programs can
check the size before issuing sk_msg_pull_data requests.

Additionally, the same applies for sendmsg calls when the application
provides multiple iovs. Here the BPF program needs to pull in data
to update data pointers but its not clear where the data ends without
a size parameter. In many cases "guessing" is not easy to do
and results in multiple calls to pull and without bounded loops
everything gets fairly tricky.

Clean this up by including a u32 size field. Note, all writes into
sk_msg_md are rejected already from sk_msg_is_valid_access so nothing
additional is needed there.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/skmsg.h    | 3 +++
 include/uapi/linux/bpf.h | 1 +
 net/core/filter.c        | 6 ++++++
 3 files changed, 10 insertions(+)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 2a11e9d91dfa..eb8f6cb84c10 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -36,6 +36,9 @@ struct sk_msg_sg {
 	struct scatterlist		data[MAX_MSG_FRAGS + 1];
 };
 
+/* UAPI in filter.c depends on struct sk_msg_sg being first element. If
+ * this is moved filter.c also must be updated.
+ */
 struct sk_msg {
 	struct sk_msg_sg		sg;
 	void				*data;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1d324c2cbca2..91c43884f295 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2665,6 +2665,7 @@ struct sk_msg_md {
 	__u32 local_ip6[4];	/* Stored in network byte order */
 	__u32 remote_port;	/* Stored in network byte order */
 	__u32 local_port;	/* stored in host byte order */
+	__u32 size;		/* Total size of sk_msg */
 };
 
 struct sk_reuseport_md {
diff --git a/net/core/filter.c b/net/core/filter.c
index f9348806e843..3a3b21726fb5 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7530,6 +7530,12 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type,
 		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg,
 				      offsetof(struct sock_common, skc_num));
 		break;
+
+	case offsetof(struct sk_msg_md, size):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_sg, size),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct sk_msg_sg, size));
+		break;
 	}
 
 	return insn - insn_buf;
-- 
cgit v1.2.3


From 584e46813e689ff1a348343b73122c43d81d0ef7 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 16 Dec 2018 15:47:05 -0800
Subject: bpf: add tools lib/include support sk_msg_md size field

Add the size field to sk_msg_md for tools.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1d324c2cbca2..91c43884f295 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2665,6 +2665,7 @@ struct sk_msg_md {
 	__u32 local_ip6[4];	/* Stored in network byte order */
 	__u32 remote_port;	/* Stored in network byte order */
 	__u32 local_port;	/* stored in host byte order */
+	__u32 size;		/* Total size of sk_msg */
 };
 
 struct sk_reuseport_md {
-- 
cgit v1.2.3


From 945a47d87cee24a95e11fdc0cd868b872f9b9616 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 16 Dec 2018 15:47:06 -0800
Subject: bpf: sk_msg, add tests for size field

This adds tests to read the size field to test_verifier.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index cf242734e2eb..7865b94c02c4 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1843,10 +1843,20 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SK_SKB,
 	},
 	{
-		"invalid 64B read of family in SK_MSG",
+		"valid access size in SK_MSG",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct sk_msg_md, size)),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SK_MSG,
+	},
+	{
+		"invalid 64B read of size in SK_MSG",
 		.insns = {
 			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1,
-				    offsetof(struct sk_msg_md, family)),
+				    offsetof(struct sk_msg_md, size)),
 			BPF_EXIT_INSN(),
 		},
 		.errstr = "invalid bpf_context access",
@@ -1857,7 +1867,7 @@ static struct bpf_test tests[] = {
 		"invalid read past end of SK_MSG",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-				    offsetof(struct sk_msg_md, local_port) + 4),
+				    offsetof(struct sk_msg_md, size) + 4),
 			BPF_EXIT_INSN(),
 		},
 		.errstr = "R0 !read_ok",
-- 
cgit v1.2.3


From f79ba4300202210eb10b3d41f70ef2b8538fa5c4 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Sat, 15 Dec 2018 02:22:17 -0500
Subject: 6lowpan: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/6lowpan/debugfs.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/net/6lowpan/debugfs.c b/net/6lowpan/debugfs.c
index 24915e0bb9ea..6c152f9ea26e 100644
--- a/net/6lowpan/debugfs.c
+++ b/net/6lowpan/debugfs.c
@@ -232,18 +232,7 @@ static int lowpan_context_show(struct seq_file *file, void *offset)
 
 	return 0;
 }
-
-static int lowpan_context_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, lowpan_context_show, inode->i_private);
-}
-
-static const struct file_operations lowpan_context_fops = {
-	.open		= lowpan_context_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(lowpan_context);
 
 static int lowpan_short_addr_get(void *data, u64 *val)
 {
-- 
cgit v1.2.3


From 8e2924e383b714748e5891ac9ff2f5c945666891 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Mon, 5 Nov 2018 09:56:19 -0500
Subject: Bluetooth: Change to use DEFINE_SHOW_ATTRIBUTE macro

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/bluetooth/l2cap_core.c  | 12 +-----------
 net/bluetooth/rfcomm/core.c | 12 +-----------
 net/bluetooth/rfcomm/sock.c | 12 +-----------
 net/bluetooth/sco.c         | 12 +-----------
 4 files changed, 4 insertions(+), 44 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 2146e0f3b6f8..2a7fb517d460 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -7650,17 +7650,7 @@ static int l2cap_debugfs_show(struct seq_file *f, void *p)
 	return 0;
 }
 
-static int l2cap_debugfs_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, l2cap_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations l2cap_debugfs_fops = {
-	.open		= l2cap_debugfs_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(l2cap_debugfs);
 
 static struct dentry *l2cap_debugfs;
 
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index b98225d65e87..1a635df80643 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -2166,17 +2166,7 @@ static int rfcomm_dlc_debugfs_show(struct seq_file *f, void *x)
 	return 0;
 }
 
-static int rfcomm_dlc_debugfs_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, rfcomm_dlc_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations rfcomm_dlc_debugfs_fops = {
-	.open		= rfcomm_dlc_debugfs_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(rfcomm_dlc_debugfs);
 
 static struct dentry *rfcomm_dlc_debugfs;
 
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index d606e9212291..aa0db1d1bd9b 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -1020,17 +1020,7 @@ static int rfcomm_sock_debugfs_show(struct seq_file *f, void *p)
 	return 0;
 }
 
-static int rfcomm_sock_debugfs_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, rfcomm_sock_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations rfcomm_sock_debugfs_fops = {
-	.open		= rfcomm_sock_debugfs_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(rfcomm_sock_debugfs);
 
 static struct dentry *rfcomm_sock_debugfs;
 
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 8f0f9279eac9..529b38996d8b 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1173,17 +1173,7 @@ static int sco_debugfs_show(struct seq_file *f, void *p)
 	return 0;
 }
 
-static int sco_debugfs_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, sco_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations sco_debugfs_fops = {
-	.open		= sco_debugfs_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(sco_debugfs);
 
 static struct dentry *sco_debugfs;
 
-- 
cgit v1.2.3


From 6ae81eebdef97109c32e545e90865bc5b14178f1 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:35 +0800
Subject: dt-bindings: net: broadcom-bluetooth: Fix external clock names

The Broadcom Bluetooth controllers can take up to two external clocks:
an external frequency reference, substituting the main crystal, and a
LPO clock at 32.768 kHz substituting the internal LPO clock.

In particular, the external LPO clock must be used when the controller
does not have NVRAM connected, and the main reference frequency is not
the default 20 MHz. This is described in detail in the datasheet.

The original "extclk" clock name is ambiguous as to which of these it
refers to, and some designs might even require both.

This patch deprecates the existing name, and adds "txco" and "lpo".

Tested-by: Ondrej Jirman <megous@megous.com>
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 Documentation/devicetree/bindings/net/broadcom-bluetooth.txt | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt b/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
index 4194ff7e6ee6..711c75ac2bb5 100644
--- a/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
+++ b/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
@@ -18,8 +18,11 @@ Optional properties:
  - shutdown-gpios: GPIO specifier, used to enable the BT module
  - device-wakeup-gpios: GPIO specifier, used to wakeup the controller
  - host-wakeup-gpios: GPIO specifier, used to wakeup the host processor
- - clocks: clock specifier if external clock provided to the controller
- - clock-names: should be "extclk"
+ - clocks: 1 or 2 clocks as defined in clock-names below, in that order
+ - clock-names: names for clock inputs, matching the clocks given
+   - "extclk": deprecated, replaced by "txco"
+   - "txco": external reference clock (not a standalone crystal)
+   - "lpo": external low power 32.768 kHz clock
 
 
 Example:
-- 
cgit v1.2.3


From 061a8aaf4c0f2885f1fa1dd6bf8ea27ab5059fa9 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:36 +0800
Subject: dt-bindings: net: broadcom-bluetooth: Add VBAT and VDDIO supplies

The Broadcom Bluetooth chips have two power inputs, VBAT and VDDIO.
The former provides overall power for the chip, while the latter powers
the I/O pins and buffers.

This patch adds properties for the two so we can describe the power
supply relationships.

Reviewed-by: Rob Herring <robh@kernel.org>
Tested-by: Ondrej Jirman <megous@megous.com>
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 Documentation/devicetree/bindings/net/broadcom-bluetooth.txt | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt b/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
index 711c75ac2bb5..78cfa0fbece9 100644
--- a/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
+++ b/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
@@ -23,6 +23,8 @@ Optional properties:
    - "extclk": deprecated, replaced by "txco"
    - "txco": external reference clock (not a standalone crystal)
    - "lpo": external low power 32.768 kHz clock
+ - vbat-supply: phandle to regulator supply for VBAT
+ - vddio-supply: phandle to regulator supply for VDDIO
 
 
 Example:
-- 
cgit v1.2.3


From bfbc47bd5901168f0fdb337e9be1759bedf8ff4e Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:37 +0800
Subject: dt-bindings: net: broadcom-bluetooth: Add BCM20702A1 compatible
 string

The BCM20702A1 is a Bluetooth 4.0 chip from Broadcom. It is found in the
Ampak AP6210 WiFi+BT module, identified from the read verbose config info
command response. However the Bluetooth firmware provided by vendors uses
the name BCM20710. This patch elects to use the chip ID returned by the
chip for the compatible string.

Reviewed-by: Rob Herring <robh@kernel.org>
Tested-by: Ondrej Jirman <megous@megous.com>
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 Documentation/devicetree/bindings/net/broadcom-bluetooth.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt b/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
index 78cfa0fbece9..d9d734a07faf 100644
--- a/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
+++ b/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
@@ -10,6 +10,7 @@ device the slave device is attached to.
 Required properties:
 
  - compatible: should contain one of the following:
+   * "brcm,bcm20702a1"
    * "brcm,bcm43438-bt"
 
 Optional properties:
-- 
cgit v1.2.3


From 31f20f5f6d14ffe8d9a87c0ef58ee7ed72a3db63 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:38 +0800
Subject: dt-bindings: net: broadcom-bluetooth: Add BCM4330 compatible string

The BCM4330 is a 802.11 a/b/g/n WiFi + Bluetooth 4.0 chip from Broadcom.
It is found in the Ampak AP6330 WiFi+BT module. The partiular one I have
identifies as BCM4330B1 for Bluetooth and BCM4330/4 for WiFi.

It is unclear if the AP6330 module uses this revision of the BCM4330, or
if there are multiple revisions. The module does not have revision
markings. This patch elects to use just BCM4330 for the compatible
string.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 Documentation/devicetree/bindings/net/broadcom-bluetooth.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt b/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
index d9d734a07faf..c26f4e11037c 100644
--- a/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
+++ b/Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
@@ -11,6 +11,7 @@ Required properties:
 
  - compatible: should contain one of the following:
    * "brcm,bcm20702a1"
+   * "brcm,bcm4330-bt"
    * "brcm,bcm43438-bt"
 
 Optional properties:
-- 
cgit v1.2.3


From 28ac03b9ac3f784c2f048a910c8d0a7a87483b66 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:39 +0800
Subject: Bluetooth: hci_bcm: Handle deferred probing for the clock supply

On some systems that actually have the bluetooth controller wired up
with an extra clock signal, it's possible the bluetooth controller
probes before the clock provider. clk_get would return a defer probe
error, which was not handled by this driver.

Handle this properly, so that these systems can work reliably.

Tested-by: Ondrej Jirman <megous@megous.com>
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_bcm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index ddbd8c6a0ceb..800132369134 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -907,6 +907,10 @@ static int bcm_get_resources(struct bcm_device *dev)
 
 	dev->clk = devm_clk_get(dev->dev, NULL);
 
+	/* Handle deferred probing */
+	if (dev->clk == ERR_PTR(-EPROBE_DEFER))
+		return PTR_ERR(dev->clk);
+
 	dev->device_wakeup = devm_gpiod_get_optional(dev->dev, "device-wakeup",
 						     GPIOD_OUT_LOW);
 	if (IS_ERR(dev->device_wakeup))
-- 
cgit v1.2.3


From 8c08947b7c4f4496e7c23be970121280fcb6cbf5 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:40 +0800
Subject: Bluetooth: hci_bcm: Simplify clk_get error handling

The driver currently checks the clk pointer for an error condition, as
returned by clk_get, before every invocation of the clk consumer API.
This is redundant if the goal is simply to ignore the errors, thereby
making the clk optional. The clk consumer API already checks if the
pointer is NULL or not.

Simplify the code a bit by assigning NULL to the clk pointer if the
error condition is one we want to ignore, which is every error except
deferred probing.

Tested-by: Ondrej Jirman <megous@megous.com>
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_bcm.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 800132369134..ff73ecb8215f 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -214,7 +214,7 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 {
 	int err;
 
-	if (powered && !IS_ERR(dev->clk) && !dev->clk_enabled) {
+	if (powered && !dev->clk_enabled) {
 		err = clk_prepare_enable(dev->clk);
 		if (err)
 			return err;
@@ -228,7 +228,7 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 	if (err)
 		goto err_revert_shutdown;
 
-	if (!powered && !IS_ERR(dev->clk) && dev->clk_enabled)
+	if (!powered && dev->clk_enabled)
 		clk_disable_unprepare(dev->clk);
 
 	dev->clk_enabled = powered;
@@ -238,7 +238,7 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 err_revert_shutdown:
 	dev->set_shutdown(dev, !powered);
 err_clk_disable:
-	if (powered && !IS_ERR(dev->clk) && !dev->clk_enabled)
+	if (powered && !dev->clk_enabled)
 		clk_disable_unprepare(dev->clk);
 	return err;
 }
@@ -911,6 +911,10 @@ static int bcm_get_resources(struct bcm_device *dev)
 	if (dev->clk == ERR_PTR(-EPROBE_DEFER))
 		return PTR_ERR(dev->clk);
 
+	/* Ignore all other errors as before */
+	if (IS_ERR(dev->clk))
+		dev->clk = NULL;
+
 	dev->device_wakeup = devm_gpiod_get_optional(dev->dev, "device-wakeup",
 						     GPIOD_OUT_LOW);
 	if (IS_ERR(dev->device_wakeup))
-- 
cgit v1.2.3


From 55dbfcd0f621a745acfd8e3221c41be181b5b128 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:41 +0800
Subject: Bluetooth: hci_bcm: Use "txco" and "extclk" to get clock reference

Originally the device tree binding only specified one clock reference,
with the name "extclk". The driver simply retrieves the clock without
bothering to specify a name.

Since we added a second clock to the binding, we need to fetch the
clocks by name now. First we try the new name "txco", then fall back
to the old name "extclk", and finally try retrieving a clock without
using any name, to cover any instances where a bad device tree or
firmware worked by accident.

In the last case, we should take care that we don't get the same
clock twice when we add support for the "lpo" clock.

Tested-by: Ondrej Jirman <megous@megous.com>
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_bcm.c | 41 ++++++++++++++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index ff73ecb8215f..1584c95c9c34 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -71,8 +71,8 @@
  * @btlp: Apple ACPI method to toggle BT_WAKE pin ("Bluetooth Low Power")
  * @btpu: Apple ACPI method to drive BT_REG_ON pin high ("Bluetooth Power Up")
  * @btpd: Apple ACPI method to drive BT_REG_ON pin low ("Bluetooth Power Down")
- * @clk: clock used by Bluetooth device
- * @clk_enabled: whether @clk is prepared and enabled
+ * @txco_clk: external reference frequency clock used by Bluetooth device
+ * @clk_enabled: whether @txco_clk is prepared and enabled
  * @init_speed: default baudrate of Bluetooth device;
  *	the host UART is initially set to this baudrate so that
  *	it can configure the Bluetooth device for @oper_speed
@@ -102,7 +102,7 @@ struct bcm_device {
 	int			gpio_int_idx;
 #endif
 
-	struct clk		*clk;
+	struct clk		*txco_clk;
 	bool			clk_enabled;
 
 	u32			init_speed;
@@ -215,7 +215,7 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 	int err;
 
 	if (powered && !dev->clk_enabled) {
-		err = clk_prepare_enable(dev->clk);
+		err = clk_prepare_enable(dev->txco_clk);
 		if (err)
 			return err;
 	}
@@ -229,7 +229,7 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 		goto err_revert_shutdown;
 
 	if (!powered && dev->clk_enabled)
-		clk_disable_unprepare(dev->clk);
+		clk_disable_unprepare(dev->txco_clk);
 
 	dev->clk_enabled = powered;
 
@@ -239,7 +239,7 @@ err_revert_shutdown:
 	dev->set_shutdown(dev, !powered);
 err_clk_disable:
 	if (powered && !dev->clk_enabled)
-		clk_disable_unprepare(dev->clk);
+		clk_disable_unprepare(dev->txco_clk);
 	return err;
 }
 
@@ -896,6 +896,25 @@ static int bcm_gpio_set_shutdown(struct bcm_device *dev, bool powered)
 	return 0;
 }
 
+/* Try a bunch of names for TXCO */
+static struct clk *bcm_get_txco(struct device *dev)
+{
+	struct clk *clk;
+
+	/* New explicit name */
+	clk = devm_clk_get(dev, "txco");
+	if (!IS_ERR(clk) || PTR_ERR(clk) == -EPROBE_DEFER)
+		return clk;
+
+	/* Deprecated name */
+	clk = devm_clk_get(dev, "extclk");
+	if (!IS_ERR(clk) || PTR_ERR(clk) == -EPROBE_DEFER)
+		return clk;
+
+	/* Original code used no name at all */
+	return devm_clk_get(dev, NULL);
+}
+
 static int bcm_get_resources(struct bcm_device *dev)
 {
 	const struct dmi_system_id *dmi_id;
@@ -905,15 +924,15 @@ static int bcm_get_resources(struct bcm_device *dev)
 	if (x86_apple_machine && !bcm_apple_get_resources(dev))
 		return 0;
 
-	dev->clk = devm_clk_get(dev->dev, NULL);
+	dev->txco_clk = bcm_get_txco(dev->dev);
 
 	/* Handle deferred probing */
-	if (dev->clk == ERR_PTR(-EPROBE_DEFER))
-		return PTR_ERR(dev->clk);
+	if (dev->txco_clk == ERR_PTR(-EPROBE_DEFER))
+		return PTR_ERR(dev->txco_clk);
 
 	/* Ignore all other errors as before */
-	if (IS_ERR(dev->clk))
-		dev->clk = NULL;
+	if (IS_ERR(dev->txco_clk))
+		dev->txco_clk = NULL;
 
 	dev->device_wakeup = devm_gpiod_get_optional(dev->dev, "device-wakeup",
 						     GPIOD_OUT_LOW);
-- 
cgit v1.2.3


From 90bc07cc59ac32f37d6de78a501246575c8866bf Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:42 +0800
Subject: Bluetooth: hci_bcm: Add support for LPO clock

The Broadcom Bluetooth controllers support a secondary LPO clock at
32.768 kHz. This external clock provides low power timing, and also
a way to detect the frequency of the main reference clock. On many
designs without NVRAM and a non-default reference clock, this must
be used or the controller will not function correctly.

Tested-by: Ondrej Jirman <megous@megous.com>
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_bcm.c | 41 ++++++++++++++++++++++++++++++++++++-----
 1 file changed, 36 insertions(+), 5 deletions(-)

diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 1584c95c9c34..345d728a5434 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -72,7 +72,8 @@
  * @btpu: Apple ACPI method to drive BT_REG_ON pin high ("Bluetooth Power Up")
  * @btpd: Apple ACPI method to drive BT_REG_ON pin low ("Bluetooth Power Down")
  * @txco_clk: external reference frequency clock used by Bluetooth device
- * @clk_enabled: whether @txco_clk is prepared and enabled
+ * @lpo_clk: external LPO clock used by Bluetooth device
+ * @clk_enabled: whether clocks are prepared and enabled
  * @init_speed: default baudrate of Bluetooth device;
  *	the host UART is initially set to this baudrate so that
  *	it can configure the Bluetooth device for @oper_speed
@@ -103,6 +104,7 @@ struct bcm_device {
 #endif
 
 	struct clk		*txco_clk;
+	struct clk		*lpo_clk;
 	bool			clk_enabled;
 
 	u32			init_speed;
@@ -215,21 +217,34 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 	int err;
 
 	if (powered && !dev->clk_enabled) {
-		err = clk_prepare_enable(dev->txco_clk);
+		/* LPO clock needs to be 32.768 kHz */
+		err = clk_set_rate(dev->lpo_clk, 32768);
+		if (err) {
+			dev_err(dev->dev, "Could not set LPO clock rate\n");
+			return err;
+		}
+
+		err = clk_prepare_enable(dev->lpo_clk);
 		if (err)
 			return err;
+
+		err = clk_prepare_enable(dev->txco_clk);
+		if (err)
+			goto err_lpo_clk_disable;
 	}
 
 	err = dev->set_shutdown(dev, powered);
 	if (err)
-		goto err_clk_disable;
+		goto err_txco_clk_disable;
 
 	err = dev->set_device_wakeup(dev, powered);
 	if (err)
 		goto err_revert_shutdown;
 
-	if (!powered && dev->clk_enabled)
+	if (!powered && dev->clk_enabled) {
 		clk_disable_unprepare(dev->txco_clk);
+		clk_disable_unprepare(dev->lpo_clk);
+	}
 
 	dev->clk_enabled = powered;
 
@@ -237,9 +252,12 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 
 err_revert_shutdown:
 	dev->set_shutdown(dev, !powered);
-err_clk_disable:
+err_txco_clk_disable:
 	if (powered && !dev->clk_enabled)
 		clk_disable_unprepare(dev->txco_clk);
+err_lpo_clk_disable:
+	if (powered && !dev->clk_enabled)
+		clk_disable_unprepare(dev->lpo_clk);
 	return err;
 }
 
@@ -934,6 +952,19 @@ static int bcm_get_resources(struct bcm_device *dev)
 	if (IS_ERR(dev->txco_clk))
 		dev->txco_clk = NULL;
 
+	dev->lpo_clk = devm_clk_get(dev->dev, "lpo");
+	if (dev->lpo_clk == ERR_PTR(-EPROBE_DEFER))
+		return PTR_ERR(dev->lpo_clk);
+
+	if (IS_ERR(dev->lpo_clk))
+		dev->lpo_clk = NULL;
+
+	/* Check if we accidentally fetched the lpo clock twice */
+	if (dev->lpo_clk && clk_is_match(dev->lpo_clk, dev->txco_clk)) {
+		devm_clk_put(dev->dev, dev->txco_clk);
+		dev->txco_clk = NULL;
+	}
+
 	dev->device_wakeup = devm_gpiod_get_optional(dev->dev, "device-wakeup",
 						     GPIOD_OUT_LOW);
 	if (IS_ERR(dev->device_wakeup))
-- 
cgit v1.2.3


From 75d11676dccb643de1e850c8a29f5e9aa58157c0 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:43 +0800
Subject: Bluetooth: hci_bcm: Add support for regulator supplies

The Broadcom Bluetooth chips have two power inputs, VBAT and VDDIO.
The former provides overall power for the chip, while the latter powers
the I/O pins and buffers.

Model these two as regulator supplies, and let the driver manage them
in the same way as it does the clock supply.

Tested-by: Ondrej Jirman <megous@megous.com>
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_bcm.c | 39 ++++++++++++++++++++++++++++++---------
 1 file changed, 30 insertions(+), 9 deletions(-)

diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 345d728a5434..f2101038284e 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -31,6 +31,7 @@
 #include <linux/property.h>
 #include <linux/platform_data/x86/apple.h>
 #include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
 #include <linux/clk.h>
 #include <linux/gpio/consumer.h>
 #include <linux/tty.h>
@@ -53,6 +54,8 @@
 
 #define BCM_AUTOSUSPEND_DELAY	5000 /* default autosleep delay */
 
+#define BCM_NUM_SUPPLIES 2
+
 /**
  * struct bcm_device - device driver resources
  * @serdev_hu: HCI UART controller struct
@@ -73,7 +76,8 @@
  * @btpd: Apple ACPI method to drive BT_REG_ON pin low ("Bluetooth Power Down")
  * @txco_clk: external reference frequency clock used by Bluetooth device
  * @lpo_clk: external LPO clock used by Bluetooth device
- * @clk_enabled: whether clocks are prepared and enabled
+ * @supplies: VBAT and VDDIO supplies used by Bluetooth device
+ * @res_enabled: whether clocks and supplies are prepared and enabled
  * @init_speed: default baudrate of Bluetooth device;
  *	the host UART is initially set to this baudrate so that
  *	it can configure the Bluetooth device for @oper_speed
@@ -105,7 +109,8 @@ struct bcm_device {
 
 	struct clk		*txco_clk;
 	struct clk		*lpo_clk;
-	bool			clk_enabled;
+	struct regulator_bulk_data supplies[BCM_NUM_SUPPLIES];
+	bool			res_enabled;
 
 	u32			init_speed;
 	u32			oper_speed;
@@ -216,17 +221,21 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 {
 	int err;
 
-	if (powered && !dev->clk_enabled) {
+	if (powered && !dev->res_enabled) {
+		err = regulator_bulk_enable(BCM_NUM_SUPPLIES, dev->supplies);
+		if (err)
+			return err;
+
 		/* LPO clock needs to be 32.768 kHz */
 		err = clk_set_rate(dev->lpo_clk, 32768);
 		if (err) {
 			dev_err(dev->dev, "Could not set LPO clock rate\n");
-			return err;
+			goto err_regulator_disable;
 		}
 
 		err = clk_prepare_enable(dev->lpo_clk);
 		if (err)
-			return err;
+			goto err_regulator_disable;
 
 		err = clk_prepare_enable(dev->txco_clk);
 		if (err)
@@ -241,23 +250,27 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 	if (err)
 		goto err_revert_shutdown;
 
-	if (!powered && dev->clk_enabled) {
+	if (!powered && dev->res_enabled) {
 		clk_disable_unprepare(dev->txco_clk);
 		clk_disable_unprepare(dev->lpo_clk);
+		regulator_bulk_disable(BCM_NUM_SUPPLIES, dev->supplies);
 	}
 
-	dev->clk_enabled = powered;
+	dev->res_enabled = powered;
 
 	return 0;
 
 err_revert_shutdown:
 	dev->set_shutdown(dev, !powered);
 err_txco_clk_disable:
-	if (powered && !dev->clk_enabled)
+	if (powered && !dev->res_enabled)
 		clk_disable_unprepare(dev->txco_clk);
 err_lpo_clk_disable:
-	if (powered && !dev->clk_enabled)
+	if (powered && !dev->res_enabled)
 		clk_disable_unprepare(dev->lpo_clk);
+err_regulator_disable:
+	if (powered && !dev->res_enabled)
+		regulator_bulk_disable(BCM_NUM_SUPPLIES, dev->supplies);
 	return err;
 }
 
@@ -936,6 +949,7 @@ static struct clk *bcm_get_txco(struct device *dev)
 static int bcm_get_resources(struct bcm_device *dev)
 {
 	const struct dmi_system_id *dmi_id;
+	int err;
 
 	dev->name = dev_name(dev->dev);
 
@@ -978,6 +992,13 @@ static int bcm_get_resources(struct bcm_device *dev)
 	dev->set_device_wakeup = bcm_gpio_set_device_wakeup;
 	dev->set_shutdown = bcm_gpio_set_shutdown;
 
+	dev->supplies[0].supply = "vbat";
+	dev->supplies[1].supply = "vddio";
+	err = devm_regulator_bulk_get(dev->dev, BCM_NUM_SUPPLIES,
+				      dev->supplies);
+	if (err)
+		return err;
+
 	/* IRQ can be declared in ACPI table as Interrupt or GpioInt */
 	if (dev->irq <= 0) {
 		struct gpio_desc *gpio;
-- 
cgit v1.2.3


From 91927a9b351f9779e323be1fb4e219a5951b1649 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:44 +0800
Subject: Bluetooth: hci_bcm: Wait for device to come out of reset after power
 on

The datasheets for BCM20702 and BCM43438 both have power up time
sequence graphs, however they are slightly different. Both chips
also have an internal power-on-reset, which holds the chip in reset
for a short time after the regulators are enabled.

For the BCM20702, the time period from when the regulators are enabled,
until the chip settles and comes out of sleep state, is 6564 ~ 8171 us.

For the BCM43438, the graph only shows the time period from when the
regulators are enabled until the chip responds by driving the host's
CTS line low, assuming the host has already driven its RTS line low.
This is shown to be 6.5 sleep cycles, with the sleep clock at 32.768
kHz. This is around 2 ms.

Wait a full 10 ms after the regulators are enabled to account for signal
rising times.

Tested-by: Ondrej Jirman <megous@megous.com>
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_bcm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index f2101038284e..538ce8059bff 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -256,6 +256,9 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered)
 		regulator_bulk_disable(BCM_NUM_SUPPLIES, dev->supplies);
 	}
 
+	/* wait for device to power on and come out of reset */
+	usleep_range(10000, 20000);
+
 	dev->res_enabled = powered;
 
 	return 0;
-- 
cgit v1.2.3


From 92ffe0db3c858ca568cf480899396e63344eab86 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@bootlin.com>
Date: Mon, 17 Dec 2018 12:04:45 +0800
Subject: Bluetooth: hci_bcm: Add BCM20702A1 variant

The BCM20702A1 chip is a single-chip Bluetooth 4.0 controller and
transceiver. It is found in the AMPAK AP6210 WiFi+BT package.

Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Tested-by: Ondrej Jirman <megous@megous.com>
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btbcm.c   | 6 ++++++
 drivers/bluetooth/hci_bcm.c | 1 +
 2 files changed, 7 insertions(+)

diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index e3e4d929e74f..22d4b530da03 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -33,6 +33,7 @@
 #define VERSION "0.1"
 
 #define BDADDR_BCM20702A0 (&(bdaddr_t) {{0x00, 0xa0, 0x02, 0x70, 0x20, 0x00}})
+#define BDADDR_BCM20702A1 (&(bdaddr_t) {{0x00, 0x00, 0xa0, 0x02, 0x70, 0x20}})
 #define BDADDR_BCM4324B3 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb3, 0x24, 0x43}})
 #define BDADDR_BCM4330B1 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb1, 0x30, 0x43}})
 
@@ -64,6 +65,9 @@ int btbcm_check_bdaddr(struct hci_dev *hdev)
 	 * The address 00:20:70:02:A0:00 indicates a BCM20702A0 controller
 	 * with no configured address.
 	 *
+	 * The address 20:70:02:A0:00:00 indicates a BCM20702A1 controller
+	 * with no configured address.
+	 *
 	 * The address 43:24:B3:00:00:00 indicates a BCM4324B3 controller
 	 * with waiting for configuration state.
 	 *
@@ -71,6 +75,7 @@ int btbcm_check_bdaddr(struct hci_dev *hdev)
 	 * with waiting for configuration state.
 	 */
 	if (!bacmp(&bda->bdaddr, BDADDR_BCM20702A0) ||
+	    !bacmp(&bda->bdaddr, BDADDR_BCM20702A1) ||
 	    !bacmp(&bda->bdaddr, BDADDR_BCM4324B3) ||
 	    !bacmp(&bda->bdaddr, BDADDR_BCM4330B1)) {
 		bt_dev_info(hdev, "BCM: Using default device address (%pMR)",
@@ -330,6 +335,7 @@ static const struct bcm_subver_table bcm_uart_subver_table[] = {
 	{ 0x2209, "BCM43430A1"  },	/* 001.002.009 */
 	{ 0x6119, "BCM4345C0"	},	/* 003.001.025 */
 	{ 0x230f, "BCM4356A2"	},	/* 001.003.015 */
+	{ 0x220e, "BCM20702A1"  },	/* 001.002.014 */
 	{ }
 };
 
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 538ce8059bff..8c75e7a67379 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -1396,6 +1396,7 @@ static void bcm_serdev_remove(struct serdev_device *serdev)
 
 #ifdef CONFIG_OF
 static const struct of_device_id bcm_bluetooth_of_match[] = {
+	{ .compatible = "brcm,bcm20702a1" },
 	{ .compatible = "brcm,bcm43438-bt" },
 	{ },
 };
-- 
cgit v1.2.3


From 66904555191cbcefa8aa552df018b4f56d94e3ae Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:46 +0800
Subject: Bluetooth: hci_bcm: Add compatible string for BCM4330

The BCM4330 chip is a 802.11 a/b/g/n + Bluetooth 4.0 + HS controller.
This patch adds a compatible string match to the serdev driver for the
Bluetooth part of the chip.

Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_bcm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 8c75e7a67379..a5cb580a07de 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -1397,6 +1397,7 @@ static void bcm_serdev_remove(struct serdev_device *serdev)
 #ifdef CONFIG_OF
 static const struct of_device_id bcm_bluetooth_of_match[] = {
 	{ .compatible = "brcm,bcm20702a1" },
+	{ .compatible = "brcm,bcm4330-bt" },
 	{ .compatible = "brcm,bcm43438-bt" },
 	{ },
 };
-- 
cgit v1.2.3


From 0697607acab976723bf67de95d7b87167c30abf8 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 17 Dec 2018 12:04:47 +0800
Subject: Bluetooth: btbcm: Add default address for BCM43430A0

The BCM43430A0 has the default MAC address 43:43:A0:12:1F:AC if none
is given. This address was found when enabling Bluetooth on a bunch of
boards with the AMPAK AP6210 module, all sharing the same address. It
also contains the sequence 4343A0, which is suspicious as that is also
the name the chip identifies itself as.

Add this to the list of default MAC addresses and leave it to the user
to configure a valid one.

Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btbcm.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index 22d4b530da03..08e1f3dd4e03 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -34,6 +34,7 @@
 
 #define BDADDR_BCM20702A0 (&(bdaddr_t) {{0x00, 0xa0, 0x02, 0x70, 0x20, 0x00}})
 #define BDADDR_BCM20702A1 (&(bdaddr_t) {{0x00, 0x00, 0xa0, 0x02, 0x70, 0x20}})
+#define BDADDR_BCM43430A0 (&(bdaddr_t) {{0xac, 0x1f, 0x12, 0xa0, 0x43, 0x43}})
 #define BDADDR_BCM4324B3 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb3, 0x24, 0x43}})
 #define BDADDR_BCM4330B1 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb1, 0x30, 0x43}})
 
@@ -73,11 +74,15 @@ int btbcm_check_bdaddr(struct hci_dev *hdev)
 	 *
 	 * The address 43:30:B1:00:00:00 indicates a BCM4330B1 controller
 	 * with waiting for configuration state.
+	 *
+	 * The address 43:43:A0:12:1F:AC indicates a BCM43430A0 controller
+	 * with no configured address.
 	 */
 	if (!bacmp(&bda->bdaddr, BDADDR_BCM20702A0) ||
 	    !bacmp(&bda->bdaddr, BDADDR_BCM20702A1) ||
 	    !bacmp(&bda->bdaddr, BDADDR_BCM4324B3) ||
-	    !bacmp(&bda->bdaddr, BDADDR_BCM4330B1)) {
+	    !bacmp(&bda->bdaddr, BDADDR_BCM4330B1) ||
+	    !bacmp(&bda->bdaddr, BDADDR_BCM43430A0)) {
 		bt_dev_info(hdev, "BCM: Using default device address (%pMR)",
 			    &bda->bdaddr);
 		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
-- 
cgit v1.2.3


From dff6d593b10fc04a24e07650c459947e9d6ff3c3 Mon Sep 17 00:00:00 2001
From: Andrea Parri <andrea.parri@amarulasolutions.com>
Date: Tue, 27 Nov 2018 12:22:25 +0100
Subject: Bluetooth: Remove unnecessary smp_mb__after_atomic() barriers

The barriers are redundant because atomic_test_and_clear_bit() already
provides the required full ordering for the cases in question (that is,
when the bit is cleared).

Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btusb.c     |  8 ++------
 drivers/bluetooth/hci_intel.c | 16 ++++------------
 2 files changed, 6 insertions(+), 18 deletions(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 7439a7eb50ac..885e17a1a9a5 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -1935,10 +1935,8 @@ static void btusb_intel_bootup(struct btusb_data *data, const void *ptr,
 	if (len != sizeof(*evt))
 		return;
 
-	if (test_and_clear_bit(BTUSB_BOOTING, &data->flags)) {
-		smp_mb__after_atomic();
+	if (test_and_clear_bit(BTUSB_BOOTING, &data->flags))
 		wake_up_bit(&data->flags, BTUSB_BOOTING);
-	}
 }
 
 static void btusb_intel_secure_send_result(struct btusb_data *data,
@@ -1953,10 +1951,8 @@ static void btusb_intel_secure_send_result(struct btusb_data *data,
 		set_bit(BTUSB_FIRMWARE_FAILED, &data->flags);
 
 	if (test_and_clear_bit(BTUSB_DOWNLOADING, &data->flags) &&
-	    test_bit(BTUSB_FIRMWARE_LOADED, &data->flags)) {
-		smp_mb__after_atomic();
+	    test_bit(BTUSB_FIRMWARE_LOADED, &data->flags))
 		wake_up_bit(&data->flags, BTUSB_DOWNLOADING);
-	}
 }
 
 static int btusb_recv_event_intel(struct hci_dev *hdev, struct sk_buff *skb)
diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c
index 46ace321bf60..8caa1a6619ce 100644
--- a/drivers/bluetooth/hci_intel.c
+++ b/drivers/bluetooth/hci_intel.c
@@ -909,10 +909,8 @@ static int intel_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
 			set_bit(STATE_FIRMWARE_FAILED, &intel->flags);
 
 		if (test_and_clear_bit(STATE_DOWNLOADING, &intel->flags) &&
-		    test_bit(STATE_FIRMWARE_LOADED, &intel->flags)) {
-			smp_mb__after_atomic();
+		    test_bit(STATE_FIRMWARE_LOADED, &intel->flags))
 			wake_up_bit(&intel->flags, STATE_DOWNLOADING);
-		}
 
 	/* When switching to the operational firmware the device
 	 * sends a vendor specific event indicating that the bootup
@@ -920,10 +918,8 @@ static int intel_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
 	 */
 	} else if (skb->len == 9 && hdr->evt == 0xff && hdr->plen == 0x07 &&
 		   skb->data[2] == 0x02) {
-		if (test_and_clear_bit(STATE_BOOTING, &intel->flags)) {
-			smp_mb__after_atomic();
+		if (test_and_clear_bit(STATE_BOOTING, &intel->flags))
 			wake_up_bit(&intel->flags, STATE_BOOTING);
-		}
 	}
 recv:
 	return hci_recv_frame(hdev, skb);
@@ -960,17 +956,13 @@ static int intel_recv_lpm(struct hci_dev *hdev, struct sk_buff *skb)
 		break;
 	case LPM_OP_SUSPEND_ACK:
 		set_bit(STATE_SUSPENDED, &intel->flags);
-		if (test_and_clear_bit(STATE_LPM_TRANSACTION, &intel->flags)) {
-			smp_mb__after_atomic();
+		if (test_and_clear_bit(STATE_LPM_TRANSACTION, &intel->flags))
 			wake_up_bit(&intel->flags, STATE_LPM_TRANSACTION);
-		}
 		break;
 	case LPM_OP_RESUME_ACK:
 		clear_bit(STATE_SUSPENDED, &intel->flags);
-		if (test_and_clear_bit(STATE_LPM_TRANSACTION, &intel->flags)) {
-			smp_mb__after_atomic();
+		if (test_and_clear_bit(STATE_LPM_TRANSACTION, &intel->flags))
 			wake_up_bit(&intel->flags, STATE_LPM_TRANSACTION);
-		}
 		break;
 	default:
 		bt_dev_err(hdev, "Unknown LPM opcode (%02x)", lpm->opcode);
-- 
cgit v1.2.3


From cba736465e5cbae22027789de748b8500e647555 Mon Sep 17 00:00:00 2001
From: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Date: Thu, 22 Nov 2018 18:20:47 +0530
Subject: Bluetooth: hci_serdev: Remove setting of HCI_QUIRK_RESET_ON_CLOSE.

HCI_QUIRK_RESET_ON_CLOSE quirk is required for BT v1.0 based devices,
to send a reset command to the chip during hci device close. Serdev
architecture is used for the latest BT chips, which doesn't require to
send the reset command during close. If still chips required reset
command during close, it would be better enabling it in the vendor
probes or in proto setup.

Signed-off-by: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_serdev.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c
index c445aa9ac511..490abba94363 100644
--- a/drivers/bluetooth/hci_serdev.c
+++ b/drivers/bluetooth/hci_serdev.c
@@ -333,9 +333,6 @@ int hci_uart_register_device(struct hci_uart *hu,
 	if (test_bit(HCI_UART_EXT_CONFIG, &hu->hdev_flags))
 		set_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks);
 
-	if (!test_bit(HCI_UART_RESET_ON_INIT, &hu->hdev_flags))
-		set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks);
-
 	if (test_bit(HCI_UART_CREATE_AMP, &hu->hdev_flags))
 		hdev->dev_type = HCI_AMP;
 	else
-- 
cgit v1.2.3


From 75edd1f2f916f06248cd6a6e8ea706b44431d3eb Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 9 Nov 2018 13:27:36 +0000
Subject: Bluetooth: clean an indentation issue, remove extraneous space

Trivial fix to clean up an indentation issue

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/bluetooth/hci_request.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index e8c9ef1e1922..ca73d36cc149 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -1556,7 +1556,7 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 	connectable = (flags & MGMT_ADV_FLAG_CONNECTABLE) ||
 		      mgmt_get_connectable(hdev);
 
-	 if (!is_advertising_allowed(hdev, connectable))
+	if (!is_advertising_allowed(hdev, connectable))
 		return -EPERM;
 
 	/* Set require_privacy to true only when non-connectable
-- 
cgit v1.2.3


From 7086b36b8080e6252162cf5d681f521738e7ced5 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 30 Oct 2018 11:34:19 +0000
Subject: Bluetooth: hci_intel: clean an indentation issue, remove extraneous
 spaces

Trivial fix to clean up an indentation issue, remove spaces

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_intel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c
index 8caa1a6619ce..f31410526c57 100644
--- a/drivers/bluetooth/hci_intel.c
+++ b/drivers/bluetooth/hci_intel.c
@@ -596,8 +596,8 @@ static int intel_setup(struct hci_uart *hu)
 	 * is in bootloader mode or if it already has operational firmware
 	 * loaded.
 	 */
-	 err = btintel_read_version(hdev, &ver);
-	 if (err)
+	err = btintel_read_version(hdev, &ver);
+	if (err)
 		return err;
 
 	/* The hardware platform number has a fixed value of 0x37 and
-- 
cgit v1.2.3


From 76c43ae84e3f455e0b460ed0c43799e018d09ee9 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 18 Dec 2018 13:43:58 -0800
Subject: bpf: log struct/union attribute for forward type

Current btf internal verbose logger logs fwd type as
  [2] FWD A type_id=0
where A is the type name.

Commit 9d5f9f701b18 ("bpf: btf: fix struct/union/fwd types
with kind_flag") introduced kind_flag which can be used
to distinguish whether a forward type is a struct or
union.

Also, "type_id=0" does not carry any meaningful
information for fwd type as btf_type.type = 0 is simply
enforced during btf verification and is not used
anywhere else.

This commit changed the log to
  [2] FWD A struct
if kind_flag = 0, or
  [2] FWD A union
if kind_flag = 1.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/btf.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index e804b26a0506..715f9fcf4712 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1595,12 +1595,18 @@ static s32 btf_fwd_check_meta(struct btf_verifier_env *env,
 	return 0;
 }
 
+static void btf_fwd_type_log(struct btf_verifier_env *env,
+			     const struct btf_type *t)
+{
+	btf_verifier_log(env, "%s", btf_type_kflag(t) ? "union" : "struct");
+}
+
 static struct btf_kind_operations fwd_ops = {
 	.check_meta = btf_fwd_check_meta,
 	.resolve = btf_df_resolve,
 	.check_member = btf_df_check_member,
 	.check_kflag_member = btf_df_check_kflag_member,
-	.log_details = btf_ref_type_log,
+	.log_details = btf_fwd_type_log,
 	.seq_show = btf_df_seq_show,
 };
 
-- 
cgit v1.2.3


From 28a75e4c813c7ae7de5b4baf4c29369769247cc6 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 30 Oct 2018 14:17:22 +0100
Subject: Bluetooth: hci_h5: Add suspend / resume ops

Add support for vendor specific suspend / resume callbacks.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_h5.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index 8eede1197cd2..beddb89a00f2 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -115,6 +115,8 @@ struct h5_vnd {
 	int (*setup)(struct h5 *h5);
 	void (*open)(struct h5 *h5);
 	void (*close)(struct h5 *h5);
+	int (*suspend)(struct h5 *h5);
+	int (*resume)(struct h5 *h5);
 	const struct acpi_gpio_mapping *acpi_gpio_map;
 };
 
@@ -841,6 +843,28 @@ static void h5_serdev_remove(struct serdev_device *serdev)
 	hci_uart_unregister_device(&h5->serdev_hu);
 }
 
+static int __maybe_unused h5_serdev_suspend(struct device *dev)
+{
+	struct h5 *h5 = dev_get_drvdata(dev);
+	int ret = 0;
+
+	if (h5->vnd && h5->vnd->suspend)
+		ret = h5->vnd->suspend(h5);
+
+	return ret;
+}
+
+static int __maybe_unused h5_serdev_resume(struct device *dev)
+{
+	struct h5 *h5 = dev_get_drvdata(dev);
+	int ret = 0;
+
+	if (h5->vnd && h5->vnd->resume)
+		ret = h5->vnd->resume(h5);
+
+	return ret;
+}
+
 #ifdef CONFIG_BT_HCIUART_RTL
 static int h5_btrtl_setup(struct h5 *h5)
 {
@@ -935,12 +959,17 @@ static const struct acpi_device_id h5_acpi_match[] = {
 MODULE_DEVICE_TABLE(acpi, h5_acpi_match);
 #endif
 
+static const struct dev_pm_ops h5_serdev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(h5_serdev_suspend, h5_serdev_resume)
+};
+
 static struct serdev_device_driver h5_serdev_driver = {
 	.probe = h5_serdev_probe,
 	.remove = h5_serdev_remove,
 	.driver = {
 		.name = "hci_uart_h5",
 		.acpi_match_table = ACPI_PTR(h5_acpi_match),
+		.pm = &h5_serdev_pm_ops,
 	},
 };
 
-- 
cgit v1.2.3


From 8589086f4efd5756d20cedd844b865e5d20164ec Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 30 Oct 2018 14:17:23 +0100
Subject: Bluetooth: hci_h5: Turn off RTL8723BS on suspend, reprobe on resume

On many devices the RTL8723BS device gets reset during suspend/resume,
causing it to lose its firmware and all state.

Testing has shown it drops back to communicating at 115200 bps and sends
sync-request packages, indicating it has been fully reset.

This commit fixes this by queueing a reprobe on resume.

This mirrors how USB RTL BT devices, which have the same problem, are
handled in the btusb driver, there we set the USB_QUIRK_RESET_RESUME for
all RTL devices, which also causes a reprobe on resume. The only difference
is that here we need to do the reprobe ourselves.

Since we are doing a full reprobe on resume now, we can also turn off the
device on suspend to save power while suspended.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_h5.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index beddb89a00f2..069d1c8fde73 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -931,6 +931,56 @@ static void h5_btrtl_close(struct h5 *h5)
 	gpiod_set_value_cansleep(h5->enable_gpio, 0);
 }
 
+/* Suspend/resume support. On many devices the RTL BT device loses power during
+ * suspend/resume, causing it to lose its firmware and all state. So we simply
+ * turn it off on suspend and reprobe on resume.  This mirrors how RTL devices
+ * are handled in the USB driver, where the USB_QUIRK_RESET_RESUME is used which
+ * also causes a reprobe on resume.
+ */
+static int h5_btrtl_suspend(struct h5 *h5)
+{
+	serdev_device_set_flow_control(h5->hu->serdev, false);
+	gpiod_set_value_cansleep(h5->device_wake_gpio, 0);
+	gpiod_set_value_cansleep(h5->enable_gpio, 0);
+	return 0;
+}
+
+struct h5_btrtl_reprobe {
+	struct device *dev;
+	struct work_struct work;
+};
+
+static void h5_btrtl_reprobe_worker(struct work_struct *work)
+{
+	struct h5_btrtl_reprobe *reprobe =
+		container_of(work, struct h5_btrtl_reprobe, work);
+	int ret;
+
+	ret = device_reprobe(reprobe->dev);
+	if (ret && ret != -EPROBE_DEFER)
+		dev_err(reprobe->dev, "Reprobe error %d\n", ret);
+
+	put_device(reprobe->dev);
+	kfree(reprobe);
+	module_put(THIS_MODULE);
+}
+
+static int h5_btrtl_resume(struct h5 *h5)
+{
+	struct h5_btrtl_reprobe *reprobe;
+
+	reprobe = kzalloc(sizeof(*reprobe), GFP_KERNEL);
+	if (!reprobe)
+		return -ENOMEM;
+
+	__module_get(THIS_MODULE);
+
+	INIT_WORK(&reprobe->work, h5_btrtl_reprobe_worker);
+	reprobe->dev = get_device(&h5->hu->serdev->dev);
+	queue_work(system_long_wq, &reprobe->work);
+	return 0;
+}
+
 static const struct acpi_gpio_params btrtl_device_wake_gpios = { 0, 0, false };
 static const struct acpi_gpio_params btrtl_enable_gpios = { 1, 0, false };
 static const struct acpi_gpio_params btrtl_host_wake_gpios = { 2, 0, false };
@@ -945,6 +995,8 @@ static struct h5_vnd rtl_vnd = {
 	.setup		= h5_btrtl_setup,
 	.open		= h5_btrtl_open,
 	.close		= h5_btrtl_close,
+	.suspend	= h5_btrtl_suspend,
+	.resume		= h5_btrtl_resume,
 	.acpi_gpio_map	= acpi_btrtl_gpios,
 };
 #endif
-- 
cgit v1.2.3


From 8937388acb09d6bf0f263fa8551d3e2b4e84de25 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 17 Dec 2018 17:27:16 +0800
Subject: qlcnic: remove set but not used variables 'op, cmd_op'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:1070:5: warning:
 variable 'op' set but not used [-Wunused-but-set-variable]
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:1342:5: warning:
 variable 'cmd_op' set but not used [-Wunused-but-set-variable]

'op' never used since introduction in commit 7cb03b2347d5 ("qlcnic:
Support VF-PF communication channel commands.")
'cmd_op' not used since commit 6226204bcf20 ("qlcnic: Fix operation
type and command type.")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index 50eaafa3eaba..af3b037fa442 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -1067,9 +1067,6 @@ static int qlcnic_sriov_pf_cfg_ip_cmd(struct qlcnic_bc_trans *trans,
 	struct qlcnic_vf_info *vf = trans->vf;
 	struct qlcnic_adapter *adapter = vf->adapter;
 	int err = -EIO;
-	u8 op;
-
-	op =  cmd->req.arg[1] & 0xff;
 
 	cmd->req.arg[1] |= vf->vp->handle << 16;
 	cmd->req.arg[1] |= BIT_31;
@@ -1339,14 +1336,13 @@ static int qlcnic_sriov_pf_get_acl_cmd(struct qlcnic_bc_trans *trans,
 {
 	struct qlcnic_vf_info *vf = trans->vf;
 	struct qlcnic_vport *vp = vf->vp;
-	u8 cmd_op, mode = vp->vlan_mode;
+	u8 mode = vp->vlan_mode;
 	struct qlcnic_adapter *adapter;
 	struct qlcnic_sriov *sriov;
 
 	adapter = vf->adapter;
 	sriov = adapter->ahw->sriov;
 
-	cmd_op = trans->req_hdr->cmd_op;
 	cmd->rsp.arg[0] |= 1 << 25;
 
 	/* For 84xx adapter in case of PVID , PFD should send vlan mode as
-- 
cgit v1.2.3


From a26d94bff4d5af7c9bf5d5e779282e2258966ec3 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 17 Dec 2018 17:46:23 +0800
Subject: net: bridge: remove unneeded variable 'err'

function br_multicast_toggle now always return 0,
so the variable 'err' is unneeded.
Also cleanup dead branch in br_changelink.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 3 +--
 net/bridge/br_netlink.c   | 4 +---
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 879cd2315769..3aeff0895669 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1937,7 +1937,6 @@ static void br_multicast_start_querier(struct net_bridge *br,
 int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 {
 	struct net_bridge_port *port;
-	int err = 0;
 
 	spin_lock_bh(&br->multicast_lock);
 	if (!!br_opt_get(br, BROPT_MULTICAST_ENABLED) == !!val)
@@ -1958,7 +1957,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 unlock:
 	spin_unlock_bh(&br->multicast_lock);
 
-	return err;
+	return 0;
 }
 
 bool br_multicast_enabled(const struct net_device *dev)
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 935495b93a99..9c07591b0232 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1175,9 +1175,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	if (data[IFLA_BR_MCAST_SNOOPING]) {
 		u8 mcast_snooping = nla_get_u8(data[IFLA_BR_MCAST_SNOOPING]);
 
-		err = br_multicast_toggle(br, mcast_snooping);
-		if (err)
-			return err;
+		br_multicast_toggle(br, mcast_snooping);
 	}
 
 	if (data[IFLA_BR_MCAST_QUERY_USE_IFADDR]) {
-- 
cgit v1.2.3


From 935b8a59ac80bf3d3caae6460fb95d028f7c92c8 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 17 Dec 2018 23:43:25 +0100
Subject: net: phy: remove unused code in phy_probe

3c1bcc8614db ("net: ethernet: Convert phydev advertize and supported
from u32 to link mode") left some unused code in phy_probe(), remove it.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 7d5d698604aa..54af2bde6682 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2138,7 +2138,6 @@ static int phy_probe(struct device *dev)
 	struct phy_device *phydev = to_phy_device(dev);
 	struct device_driver *drv = phydev->mdio.dev.driver;
 	struct phy_driver *phydrv = to_phy_driver(drv);
-	u32 features;
 	int err = 0;
 
 	phydev->drv = phydrv;
@@ -2158,7 +2157,6 @@ static int phy_probe(struct device *dev)
 	 * a controller will attach, and may modify one
 	 * or both of these values
 	 */
-	ethtool_convert_link_mode_to_legacy_u32(&features, phydrv->features);
 	linkmode_copy(phydev->supported, phydrv->features);
 	of_set_phy_supported(phydev);
 	linkmode_copy(phydev->advertising, phydev->supported);
-- 
cgit v1.2.3


From 5679ee784c89793537d233022b55a331a64aed9d Mon Sep 17 00:00:00 2001
From: Zhenbo Gao <zhenbo.gao@windriver.com>
Date: Tue, 18 Dec 2018 17:43:52 +0800
Subject: tipc: handle broadcast NAME_DISTRIBUTOR packet when receiving it

NAME_DISTRIBUTOR messages are transmitted through unicast link on TIPC
2.0, by contrast, the messages are delivered through broadcast link on
TIPC 1.7. But at present, NAME_DISTRIBUTOR messages received by
broadcast link cannot be handled in tipc_rcv() until an unicast message
arrives, which may lead to a significant delay to update name table.

To avoid this delay, we will also deal with broadcast NAME_DISTRIBUTOR
message on broadcast receive path.

Signed-off-by: Zhenbo Gao <zhenbo.gao@windriver.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 32556f480a60..5980abb7839b 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1549,6 +1549,10 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id
 	if (!skb_queue_empty(&be->inputq1))
 		tipc_node_mcast_rcv(n);
 
+	/* Handle NAME_DISTRIBUTOR messages sent from 1.7 nodes */
+	if (!skb_queue_empty(&n->bc_entry.namedq))
+		tipc_named_rcv(net, &n->bc_entry.namedq);
+
 	/* If reassembly or retransmission failure => reset all links to peer */
 	if (rc & TIPC_LINK_DOWN_EVT)
 		tipc_node_reset_links(n);
-- 
cgit v1.2.3


From 624b66f8c9945504232c253e64f7c28e5a5c04d6 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 18 Dec 2018 15:25:39 +0100
Subject: MAINTAINERS: Add a maintainer for Microsemi switches

Microsemi has been bought by Microchip and Microchip is supporting those
switches.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Acked-by: Woojung Huh <Woojung.Huh@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index a676b40ac1d6..95baadb0b62b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9906,6 +9906,7 @@ F:	Documentation/scsi/smartpqi.txt
 
 MICROSEMI ETHERNET SWITCH DRIVER
 M:	Alexandre Belloni <alexandre.belloni@bootlin.com>
+M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/mscc/
-- 
cgit v1.2.3


From 33f18c96afdf4da20014f834874e2820ee880cde Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 19 Dec 2018 00:43:58 +0100
Subject: net: ethernet: don't set phylib state CHANGELINK in drivers

After phy_start() phylib takes care of all needed actions, including
aneg settings and checking link state. There's no need to set state
PHY_CHANGELINK in drivers.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/au1000_eth.c | 5 +----
 drivers/net/ethernet/ti/cpmac.c       | 1 -
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index 7c1eb304c27e..e833d1b3fe18 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -940,11 +940,8 @@ static int au1000_open(struct net_device *dev)
 		return retval;
 	}
 
-	if (dev->phydev) {
-		/* cause the PHY state machine to schedule a link state check */
-		dev->phydev->state = PHY_CHANGELINK;
+	if (dev->phydev)
 		phy_start(dev->phydev);
-	}
 
 	netif_start_queue(dev);
 
diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c
index 9b8a30bf939b..810dfc7de1f9 100644
--- a/drivers/net/ethernet/ti/cpmac.c
+++ b/drivers/net/ethernet/ti/cpmac.c
@@ -991,7 +991,6 @@ static int cpmac_open(struct net_device *dev)
 	cpmac_hw_start(dev);
 
 	napi_enable(&priv->napi);
-	dev->phydev->state = PHY_CHANGELINK;
 	phy_start(dev->phydev);
 
 	return 0;
-- 
cgit v1.2.3


From 2da711bcebe81209a9f2f90e145600eb1bae2b71 Mon Sep 17 00:00:00 2001
From: Raghuram Hegde <raghuram.hegde@intel.com>
Date: Wed, 19 Dec 2018 11:42:18 +0530
Subject: Bluetooth: btusb: Add support for Intel bluetooth device 8087:0029

Include the new USB product ID for Intel Bluetooth device 22260
family(CcPeak)

The /sys/kernel/debug/usb/devices portion for this device is:

T:  Bus=01 Lev=01 Prnt=01 Port=02 Cnt=02 Dev#=  2 Spd=12   MxCh= 0
D:  Ver= 2.00 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=8087 ProdID=0029 Rev= 0.01
C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=1ms
E:  Ad=02(O) Atr=02(Bulk) MxPS=  64 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS=  64 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms

Signed-off-by: Raghuram Hegde <raghuram.hegde@intel.com>
Signed-off-by: Chethan T N <chethan.tumkur.narayan@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btusb.c | 72 ++++++++++++++++++++++++-----------------------
 1 file changed, 37 insertions(+), 35 deletions(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 885e17a1a9a5..4761499db9ee 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -344,6 +344,7 @@ static const struct usb_device_id blacklist_table[] = {
 	/* Intel Bluetooth devices */
 	{ USB_DEVICE(0x8087, 0x0025), .driver_info = BTUSB_INTEL_NEW },
 	{ USB_DEVICE(0x8087, 0x0026), .driver_info = BTUSB_INTEL_NEW },
+	{ USB_DEVICE(0x8087, 0x0029), .driver_info = BTUSB_INTEL_NEW },
 	{ USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR },
 	{ USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL },
 	{ USB_DEVICE(0x8087, 0x0a2a), .driver_info = BTUSB_INTEL },
@@ -2051,6 +2052,35 @@ static int btusb_send_frame_intel(struct hci_dev *hdev, struct sk_buff *skb)
 	return -EILSEQ;
 }
 
+static bool btusb_setup_intel_new_get_fw_name(struct intel_version *ver,
+					     struct intel_boot_params *params,
+					     char *fw_name, size_t len,
+					     const char *suffix)
+{
+	switch (ver->hw_variant) {
+	case 0x0b:	/* SfP */
+	case 0x0c:	/* WsP */
+		snprintf(fw_name, len, "intel/ibt-%u-%u.%s",
+			le16_to_cpu(ver->hw_variant),
+			le16_to_cpu(params->dev_revid),
+			suffix);
+		break;
+	case 0x11:	/* JfP */
+	case 0x12:	/* ThP */
+	case 0x13:	/* HrP */
+	case 0x14:	/* CcP */
+		snprintf(fw_name, len, "intel/ibt-%u-%u-%u.%s",
+			le16_to_cpu(ver->hw_variant),
+			le16_to_cpu(ver->hw_revision),
+			le16_to_cpu(ver->fw_revision),
+			suffix);
+		break;
+	default:
+		return false;
+	}
+	return true;
+}
+
 static int btusb_setup_intel_new(struct hci_dev *hdev)
 {
 	struct btusb_data *data = hci_get_drvdata(hdev);
@@ -2102,7 +2132,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	case 0x11:	/* JfP */
 	case 0x12:	/* ThP */
 	case 0x13:	/* HrP */
-	case 0x14:	/* QnJ, IcP */
+	case 0x14:	/* CcP */
 		break;
 	default:
 		bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)",
@@ -2186,23 +2216,9 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	 * ibt-<hw_variant>-<hw_revision>-<fw_revision>.sfi.
 	 *
 	 */
-	switch (ver.hw_variant) {
-	case 0x0b:	/* SfP */
-	case 0x0c:	/* WsP */
-		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi",
-			 le16_to_cpu(ver.hw_variant),
-			 le16_to_cpu(params.dev_revid));
-		break;
-	case 0x11:	/* JfP */
-	case 0x12:	/* ThP */
-	case 0x13:	/* HrP */
-	case 0x14:	/* QnJ, IcP */
-		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.sfi",
-			 le16_to_cpu(ver.hw_variant),
-			 le16_to_cpu(ver.hw_revision),
-			 le16_to_cpu(ver.fw_revision));
-		break;
-	default:
+	err = btusb_setup_intel_new_get_fw_name(&ver, &params, fwname,
+						sizeof(fwname), "sfi");
+	if (!err) {
 		bt_dev_err(hdev, "Unsupported Intel firmware naming");
 		return -EINVAL;
 	}
@@ -2218,23 +2234,9 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	/* Save the DDC file name for later use to apply once the firmware
 	 * downloading is done.
 	 */
-	switch (ver.hw_variant) {
-	case 0x0b:	/* SfP */
-	case 0x0c:	/* WsP */
-		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.ddc",
-			 le16_to_cpu(ver.hw_variant),
-			 le16_to_cpu(params.dev_revid));
-		break;
-	case 0x11:	/* JfP */
-	case 0x12:	/* ThP */
-	case 0x13:	/* HrP */
-	case 0x14:	/* QnJ, IcP */
-		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.ddc",
-			 le16_to_cpu(ver.hw_variant),
-			 le16_to_cpu(ver.hw_revision),
-			 le16_to_cpu(ver.fw_revision));
-		break;
-	default:
+	err = btusb_setup_intel_new_get_fw_name(&ver, &params, fwname,
+						sizeof(fwname), "ddc");
+	if (!err) {
 		bt_dev_err(hdev, "Unsupported Intel firmware naming");
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From efc38dd7d5fa5c8cdd0c917c5d00947aa0539443 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 15 Dec 2018 11:03:12 +0200
Subject: mac80211: fix radiotap vendor presence bitmap handling

Due to the alignment handling, it actually matters where in the code
we add the 4 bytes for the presence bitmap to the length; the first
field is the timestamp with 8 byte alignment so we need to add the
space for the extra vendor namespace presence bitmap *before* we do
any alignment for the fields.

Move the presence bitmap length accounting to the right place to fix
the alignment for the data properly.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/rx.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 8327440aa24b..c90904ce6e99 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -143,6 +143,9 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local,
 	/* allocate extra bitmaps */
 	if (status->chains)
 		len += 4 * hweight8(status->chains);
+	/* vendor presence bitmap */
+	if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA)
+		len += 4;
 
 	if (ieee80211_have_rx_timestamp(status)) {
 		len = ALIGN(len, 8);
@@ -207,8 +210,6 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local,
 	if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) {
 		struct ieee80211_vendor_radiotap *rtap = (void *)skb->data;
 
-		/* vendor presence bitmap */
-		len += 4;
 		/* alignment for fixed 6-byte vendor data header */
 		len = ALIGN(len, 2);
 		/* vendor data header */
-- 
cgit v1.2.3


From 93bc8ac49e82a329160604556b805b7fa614ff9e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 15 Dec 2018 11:03:16 +0200
Subject: cfg80211: fix ieee80211_get_vht_max_nss()

Fix two bugs in ieee80211_get_vht_max_nss():
 * the spec says we should round down
   (reported by Nissim)
 * there's a double condition, the first one is wrong,
   supp_width == 0 / ext_nss_bw == 2 is valid in 80+80
   (found by smatch)

Fixes: b0aa75f0b1b2 ("ieee80211: add new VHT capability fields/parsing")
Reported-by: Nissim Bendanan <nissimx.bendanan@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/util.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/net/wireless/util.c b/net/wireless/util.c
index ef14d80ca03e..06a084236841 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -2013,33 +2013,32 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap,
 	case IEEE80211_VHT_CHANWIDTH_160MHZ:
 		if (supp_width == 0 &&
 		    (ext_nss_bw == 1 || ext_nss_bw == 2))
-			return DIV_ROUND_UP(max_vht_nss, 2);
+			return max_vht_nss / 2;
 		if (supp_width == 0 &&
 		    ext_nss_bw == 3)
-			return DIV_ROUND_UP(3 * max_vht_nss, 4);
+			return (3 * max_vht_nss) / 4;
 		if (supp_width == 1 &&
 		    ext_nss_bw == 3)
 			return 2 * max_vht_nss;
 		break;
 	case IEEE80211_VHT_CHANWIDTH_80P80MHZ:
-		if (supp_width == 0 &&
-		    (ext_nss_bw == 1 || ext_nss_bw == 2))
+		if (supp_width == 0 && ext_nss_bw == 1)
 			return 0; /* not possible */
 		if (supp_width == 0 &&
 		    ext_nss_bw == 2)
-			return DIV_ROUND_UP(max_vht_nss, 2);
+			return max_vht_nss / 2;
 		if (supp_width == 0 &&
 		    ext_nss_bw == 3)
-			return DIV_ROUND_UP(3 * max_vht_nss, 4);
+			return (3 * max_vht_nss) / 4;
 		if (supp_width == 1 &&
 		    ext_nss_bw == 0)
 			return 0; /* not possible */
 		if (supp_width == 1 &&
 		    ext_nss_bw == 1)
-			return DIV_ROUND_UP(max_vht_nss, 2);
+			return max_vht_nss / 2;
 		if (supp_width == 1 &&
 		    ext_nss_bw == 2)
-			return DIV_ROUND_UP(3 * max_vht_nss, 4);
+			return (3 * max_vht_nss) / 4;
 		break;
 	}
 
-- 
cgit v1.2.3


From d359bbce0601c6a19203a4b813a7e3910fcba282 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sat, 15 Dec 2018 11:03:25 +0200
Subject: mac80211: Properly access radiotap vendor data

The radiotap vendor data might be placed after some other
radiotap elements, and thus when accessing it, need to access
the correct offset in the skb data. Fix the code accordingly.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/rx.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index c90904ce6e99..b33d37186576 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -762,8 +762,12 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 	if (status->flag & RX_FLAG_RADIOTAP_HE_MU)
 		rtap_space += sizeof(struct ieee80211_radiotap_he_mu);
 
+	if (status->flag & RX_FLAG_RADIOTAP_LSIG)
+		rtap_space += sizeof(struct ieee80211_radiotap_lsig);
+
 	if (unlikely(status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA)) {
-		struct ieee80211_vendor_radiotap *rtap = (void *)origskb->data;
+		struct ieee80211_vendor_radiotap *rtap =
+			(void *)(origskb->data + rtap_space);
 
 		rtap_space += sizeof(*rtap) + rtap->len + rtap->pad;
 	}
-- 
cgit v1.2.3


From cc4acb1b6a86563ef5b6dc7c35d99f66d7b82557 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 19 Dec 2018 01:12:20 +0000
Subject: xfrm: policy: remove set but not used variable 'priority'

Fixes gcc '-Wunused-but-set-variable' warning:

net/xfrm/xfrm_policy.c: In function 'xfrm_policy_lookup_bytype':
net/xfrm/xfrm_policy.c:2079:6: warning:
 variable 'priority' set but not used [-Wunused-but-set-variable]

It not used since commit 6be3b0db6db8 ("xfrm: policy: add inexact policy
search tree infrastructure")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index be04091eb7db..537b7eec623c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2076,7 +2076,6 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 	struct xfrm_policy *pol, *ret;
 	struct hlist_head *chain;
 	unsigned int sequence;
-	u32 priority;
 	int err;
 
 	daddr = xfrm_flowi_daddr(fl, family);
@@ -2091,7 +2090,6 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 		chain = policy_hash_direct(net, daddr, saddr, family, dir);
 	} while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence));
 
-	priority = ~0U;
 	ret = NULL;
 	hlist_for_each_entry_rcu(pol, chain, bydst) {
 		err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
@@ -2104,7 +2102,6 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 			}
 		} else {
 			ret = pol;
-			priority = ret->priority;
 			break;
 		}
 	}
-- 
cgit v1.2.3


From fa89a4593b927b3f59c3b69379f31d3b22272e4e Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 19 Dec 2018 14:45:09 +0800
Subject: xfrm6_tunnel: Fix spi check in __xfrm6_tunnel_alloc_spi

gcc warn this:

net/ipv6/xfrm6_tunnel.c:143 __xfrm6_tunnel_alloc_spi() warn:
 always true condition '(spi <= 4294967295) => (0-u32max <= u32max)'

'spi' is u32, which always not greater than XFRM6_TUNNEL_SPI_MAX
because of wrap around. So the second forloop will never reach.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv6/xfrm6_tunnel.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 4a46df8441c9..f5b4febeaa25 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -144,6 +144,9 @@ static u32 __xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr)
 		index = __xfrm6_tunnel_spi_check(net, spi);
 		if (index >= 0)
 			goto alloc_spi;
+
+		if (spi == XFRM6_TUNNEL_SPI_MAX)
+			break;
 	}
 	for (spi = XFRM6_TUNNEL_SPI_MIN; spi < xfrm6_tn->spi; spi++) {
 		index = __xfrm6_tunnel_spi_check(net, spi);
-- 
cgit v1.2.3


From e3ca60d06cf37ea57d77eb834dca418f9c2dea81 Mon Sep 17 00:00:00 2001
From: Paweł Chmiel <pawel.mikolaj.chmiel@gmail.com>
Date: Wed, 19 Dec 2018 12:22:46 +0100
Subject: Bluetooth: btbcm: Add entry for BCM4329B1 UART bluetooth
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds the device ID for the BCM 4329 combo module used
in the Samsung Aries based phones (Galaxy S and it's variants).

```
[   11.508980] Bluetooth: hci0: BCM: chip id 41
[   11.518975] Bluetooth: hci0: BCM: features 0x04
[   11.550132] Bluetooth: hci0: BCM4329B1
[   11.557046] Bluetooth: hci0: BCM4329B1 (002.002.023) build 0000
[   13.737071] Bluetooth: hci0: BCM4329B1 (002.002.023) build 0744
```

Output from hciconfig

```
hci0:   Type: Primary  Bus: UART
        BD Address: 43:29:B1:55:00:00  ACL MTU: 1021:6  SCO MTU: 64:1
        UP RUNNING
        RX bytes:1675 acl:0 sco:0 events:145 errors:0
        TX bytes:20426 acl:0 sco:0 commands:146 errors:0
        Features: 0xbf 0xfe 0x8f 0xfe 0x9b 0xff 0x79 0x83
        Packet type: DM1 DM3 DM5 DH1 DH3 DH5 HV1 HV2 HV3
        Link policy: RSWITCH SNIFF
        Link mode: SLAVE ACCEPT
        Name: 'aries'
        Class: 0x000000
        Service Classes: Unspecified
        Device Class: Miscellaneous,
        HCI Version: 2.1 (0x4)  Revision: 0x2e8
        LMP Version: 2.1 (0x4)  Subversion: 0x4217
        Manufacturer: Broadcom Corporation (15)
```

Signed-off-by: Paweł Chmiel <pawel.mikolaj.chmiel@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btbcm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index 08e1f3dd4e03..d5d6e6e5da3b 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -341,6 +341,7 @@ static const struct bcm_subver_table bcm_uart_subver_table[] = {
 	{ 0x6119, "BCM4345C0"	},	/* 003.001.025 */
 	{ 0x230f, "BCM4356A2"	},	/* 001.003.015 */
 	{ 0x220e, "BCM20702A1"  },	/* 001.002.014 */
+	{ 0x4217, "BCM4329B1"   },	/* 002.002.023 */
 	{ }
 };
 
-- 
cgit v1.2.3


From 22bba80500fdf624a7cfbb65fdfa97a038ae224d Mon Sep 17 00:00:00 2001
From: Jonathan Bakker <xc-racer2@live.ca>
Date: Wed, 19 Dec 2018 12:22:28 +0100
Subject: Bluetooth: hci_bcm: Handle specific unknown packets after firmware
 loading
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Broadcom controller on aries S5PV210 boards sends out a couple of
unknown packets after the firmware is loaded.  This will cause
logging of errors such as:
	Bluetooth: hci0: Frame reassembly failed (-84)

This is probably also the case with other boards, as there are related
Android userspace patches for custom ROMs such as
https://review.lineageos.org/#/c/LineageOS/android_system_bt/+/142721/
Since this appears to be intended behaviour, treated them as diagnostic
packets.

Note that this is another variant of commit 01d5e44ace8a
("Bluetooth: hci_bcm: Handle empty packet after firmware loading")

Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Signed-off-by: Paweł Chmiel <pawel.mikolaj.chmiel@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_bcm.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index a5cb580a07de..ddbe518c3e5b 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -52,6 +52,12 @@
 #define BCM_LM_DIAG_PKT 0x07
 #define BCM_LM_DIAG_SIZE 63
 
+#define BCM_TYPE49_PKT 0x31
+#define BCM_TYPE49_SIZE 0
+
+#define BCM_TYPE52_PKT 0x34
+#define BCM_TYPE52_SIZE 0
+
 #define BCM_AUTOSUSPEND_DELAY	5000 /* default autosleep delay */
 
 #define BCM_NUM_SUPPLIES 2
@@ -595,12 +601,28 @@ finalize:
 	.lsize = 0, \
 	.maxlen = BCM_NULL_SIZE
 
+#define BCM_RECV_TYPE49 \
+	.type = BCM_TYPE49_PKT, \
+	.hlen = BCM_TYPE49_SIZE, \
+	.loff = 0, \
+	.lsize = 0, \
+	.maxlen = BCM_TYPE49_SIZE
+
+#define BCM_RECV_TYPE52 \
+	.type = BCM_TYPE52_PKT, \
+	.hlen = BCM_TYPE52_SIZE, \
+	.loff = 0, \
+	.lsize = 0, \
+	.maxlen = BCM_TYPE52_SIZE
+
 static const struct h4_recv_pkt bcm_recv_pkts[] = {
 	{ H4_RECV_ACL,      .recv = hci_recv_frame },
 	{ H4_RECV_SCO,      .recv = hci_recv_frame },
 	{ H4_RECV_EVENT,    .recv = hci_recv_frame },
 	{ BCM_RECV_LM_DIAG, .recv = hci_recv_diag  },
 	{ BCM_RECV_NULL,    .recv = hci_recv_diag  },
+	{ BCM_RECV_TYPE49,  .recv = hci_recv_diag  },
+	{ BCM_RECV_TYPE52,  .recv = hci_recv_diag  },
 };
 
 static int bcm_recv(struct hci_uart *hu, const void *data, int count)
-- 
cgit v1.2.3


From 1629db9c75342325868243d6bca5853017d91cf8 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Tue, 27 Nov 2018 11:37:46 +0200
Subject: Bluetooth: Fix unnecessary error message for HCI request completion

In case a command which completes in Command Status was sent using the
hci_cmd_send-family of APIs there would be a misleading error in the
hci_get_cmd_complete function, since the code would be trying to fetch
the Command Complete parameters when there are none.

Avoid the misleading error and silently bail out from the function in
case the received event is a command status.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/bluetooth/hci_event.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index ef9928d7b4fb..ac2826ce162b 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -5711,6 +5711,12 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
 		return true;
 	}
 
+	/* Check if request ended in Command Status - no way to retreive
+	 * any extra parameters in this case.
+	 */
+	if (hdr->evt == HCI_EV_CMD_STATUS)
+		return false;
+
 	if (hdr->evt != HCI_EV_CMD_COMPLETE) {
 		bt_dev_err(hdev, "last event is not cmd complete (0x%2.2x)",
 			   hdr->evt);
-- 
cgit v1.2.3


From 7b98f63ea777d90abaca41beadf71e3f62d180e0 Mon Sep 17 00:00:00 2001
From: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Date: Tue, 18 Dec 2018 14:57:56 +0530
Subject: net: phy: mscc: Fix the VSC 8531/41 Chip Init sequence

- Turn on Broadcast writes
- UNH 1.8.1 clear bias for UNH 1000BT distortion
- UNH 1.8.7 optimize pre-emphasis for 100BasTx UNH 100W fix
- Enable Token-ring during 'Coma Mode'

Signed-off-by: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mscc.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 54 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c
index cfe680f78a3f..3949fe299b18 100644
--- a/drivers/net/phy/mscc.c
+++ b/drivers/net/phy/mscc.c
@@ -853,6 +853,51 @@ static void vsc85xx_tr_write(struct phy_device *phydev, u16 addr, u32 val)
 	__phy_write(phydev, MSCC_PHY_TR_CNTL, TR_WRITE | TR_ADDR(addr));
 }
 
+static int vsc8531_pre_init_seq_set(struct phy_device *phydev)
+{
+	int rc;
+	const struct reg_val init_seq[] = {
+		{0x0f90, 0x00688980},
+		{0x0696, 0x00000003},
+		{0x07fa, 0x0050100f},
+		{0x1686, 0x00000004},
+	};
+	unsigned int i;
+	int oldpage;
+
+	rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_STANDARD,
+			      MSCC_PHY_EXT_CNTL_STATUS, SMI_BROADCAST_WR_EN,
+			      SMI_BROADCAST_WR_EN);
+	if (rc < 0)
+		return rc;
+	rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_TEST,
+			      MSCC_PHY_TEST_PAGE_24, 0, 0x0400);
+	if (rc < 0)
+		return rc;
+	rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_TEST,
+			      MSCC_PHY_TEST_PAGE_5, 0x0a00, 0x0e00);
+	if (rc < 0)
+		return rc;
+	rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_TEST,
+			      MSCC_PHY_TEST_PAGE_8, 0x8000, 0x8000);
+	if (rc < 0)
+		return rc;
+
+	mutex_lock(&phydev->lock);
+	oldpage = phy_select_page(phydev, MSCC_PHY_PAGE_TR);
+	if (oldpage < 0)
+		goto out_unlock;
+
+	for (i = 0; i < ARRAY_SIZE(init_seq); i++)
+		vsc85xx_tr_write(phydev, init_seq[i].reg, init_seq[i].val);
+
+out_unlock:
+	oldpage = phy_restore_page(phydev, oldpage, oldpage);
+	mutex_unlock(&phydev->lock);
+
+	return oldpage;
+}
+
 static int vsc85xx_eee_init_seq_set(struct phy_device *phydev)
 {
 	const struct reg_val init_eee[] = {
@@ -1650,7 +1695,7 @@ err:
 
 static int vsc85xx_config_init(struct phy_device *phydev)
 {
-	int rc, i;
+	int rc, i, phy_id;
 	struct vsc8531_private *vsc8531 = phydev->priv;
 
 	rc = vsc85xx_default_config(phydev);
@@ -1665,6 +1710,14 @@ static int vsc85xx_config_init(struct phy_device *phydev)
 	if (rc)
 		return rc;
 
+	phy_id = phydev->drv->phy_id & phydev->drv->phy_id_mask;
+	if (PHY_ID_VSC8531 == phy_id || PHY_ID_VSC8541 == phy_id ||
+	    PHY_ID_VSC8530 == phy_id || PHY_ID_VSC8540 == phy_id) {
+		rc = vsc8531_pre_init_seq_set(phydev);
+		if (rc)
+			return rc;
+	}
+
 	rc = vsc85xx_eee_init_seq_set(phydev);
 	if (rc)
 		return rc;
-- 
cgit v1.2.3


From e80081c34b03587cf6e89c0a1ea16c71b40bccca Mon Sep 17 00:00:00 2001
From: Roy Pledge <roy.pledge@nxp.com>
Date: Tue, 18 Dec 2018 15:23:01 +0000
Subject: soc: fsl: dpio: Add BP and FQ query APIs

Add FQ (Frame Queue) and BP (Buffer Pool) query APIs that
users of QBMan can invoke to see the status of the queues
and pools that they are using.

Signed-off-by: Roy Pledge <roy.pledge@nxp.com>
Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/soc/fsl/dpio/dpio-service.c | 68 ++++++++++++++++++++++++++
 drivers/soc/fsl/dpio/qbman-portal.c | 96 +++++++++++++++++++++++++++++++++++++
 drivers/soc/fsl/dpio/qbman-portal.h | 58 ++++++++++++++++++++++
 include/soc/fsl/dpaa2-io.h          |  4 ++
 4 files changed, 226 insertions(+)

diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c
index 321a92613a7e..ec0837ff039a 100644
--- a/drivers/soc/fsl/dpio/dpio-service.c
+++ b/drivers/soc/fsl/dpio/dpio-service.c
@@ -601,3 +601,71 @@ struct dpaa2_dq *dpaa2_io_store_next(struct dpaa2_io_store *s, int *is_last)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dpaa2_io_store_next);
+
+/**
+ * dpaa2_io_query_fq_count() - Get the frame and byte count for a given fq.
+ * @d: the given DPIO object.
+ * @fqid: the id of frame queue to be queried.
+ * @fcnt: the queried frame count.
+ * @bcnt: the queried byte count.
+ *
+ * Knowing the FQ count at run-time can be useful in debugging situations.
+ * The instantaneous frame- and byte-count are hereby returned.
+ *
+ * Return 0 for a successful query, and negative error code if query fails.
+ */
+int dpaa2_io_query_fq_count(struct dpaa2_io *d, u32 fqid,
+			    u32 *fcnt, u32 *bcnt)
+{
+	struct qbman_fq_query_np_rslt state;
+	struct qbman_swp *swp;
+	unsigned long irqflags;
+	int ret;
+
+	d = service_select(d);
+	if (!d)
+		return -ENODEV;
+
+	swp = d->swp;
+	spin_lock_irqsave(&d->lock_mgmt_cmd, irqflags);
+	ret = qbman_fq_query_state(swp, fqid, &state);
+	spin_unlock_irqrestore(&d->lock_mgmt_cmd, irqflags);
+	if (ret)
+		return ret;
+	*fcnt = qbman_fq_state_frame_count(&state);
+	*bcnt = qbman_fq_state_byte_count(&state);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dpaa2_io_query_fq_count);
+
+/**
+ * dpaa2_io_query_bp_count() - Query the number of buffers currently in a
+ * buffer pool.
+ * @d: the given DPIO object.
+ * @bpid: the index of buffer pool to be queried.
+ * @num: the queried number of buffers in the buffer pool.
+ *
+ * Return 0 for a successful query, and negative error code if query fails.
+ */
+int dpaa2_io_query_bp_count(struct dpaa2_io *d, u16 bpid, u32 *num)
+{
+	struct qbman_bp_query_rslt state;
+	struct qbman_swp *swp;
+	unsigned long irqflags;
+	int ret;
+
+	d = service_select(d);
+	if (!d)
+		return -ENODEV;
+
+	swp = d->swp;
+	spin_lock_irqsave(&d->lock_mgmt_cmd, irqflags);
+	ret = qbman_bp_query(swp, bpid, &state);
+	spin_unlock_irqrestore(&d->lock_mgmt_cmd, irqflags);
+	if (ret)
+		return ret;
+	*num = qbman_bp_info_num_free_bufs(&state);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dpaa2_io_query_bp_count);
diff --git a/drivers/soc/fsl/dpio/qbman-portal.c b/drivers/soc/fsl/dpio/qbman-portal.c
index cf1d448ea468..0bddb85c0ae5 100644
--- a/drivers/soc/fsl/dpio/qbman-portal.c
+++ b/drivers/soc/fsl/dpio/qbman-portal.c
@@ -1003,3 +1003,99 @@ int qbman_swp_CDAN_set(struct qbman_swp *s, u16 channelid,
 
 	return 0;
 }
+
+#define QBMAN_RESPONSE_VERB_MASK	0x7f
+#define QBMAN_FQ_QUERY_NP		0x45
+#define QBMAN_BP_QUERY			0x32
+
+struct qbman_fq_query_desc {
+	u8 verb;
+	u8 reserved[3];
+	__le32 fqid;
+	u8 reserved2[56];
+};
+
+int qbman_fq_query_state(struct qbman_swp *s, u32 fqid,
+			 struct qbman_fq_query_np_rslt *r)
+{
+	struct qbman_fq_query_desc *p;
+	void *resp;
+
+	p = (struct qbman_fq_query_desc *)qbman_swp_mc_start(s);
+	if (!p)
+		return -EBUSY;
+
+	/* FQID is a 24 bit value */
+	p->fqid = cpu_to_le32(fqid & 0x00FFFFFF);
+	resp = qbman_swp_mc_complete(s, p, QBMAN_FQ_QUERY_NP);
+	if (!resp) {
+		pr_err("qbman: Query FQID %d NP fields failed, no response\n",
+		       fqid);
+		return -EIO;
+	}
+	*r = *(struct qbman_fq_query_np_rslt *)resp;
+	/* Decode the outcome */
+	WARN_ON((r->verb & QBMAN_RESPONSE_VERB_MASK) != QBMAN_FQ_QUERY_NP);
+
+	/* Determine success or failure */
+	if (r->rslt != QBMAN_MC_RSLT_OK) {
+		pr_err("Query NP fields of FQID 0x%x failed, code=0x%02x\n",
+		       p->fqid, r->rslt);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+u32 qbman_fq_state_frame_count(const struct qbman_fq_query_np_rslt *r)
+{
+	return (le32_to_cpu(r->frm_cnt) & 0x00FFFFFF);
+}
+
+u32 qbman_fq_state_byte_count(const struct qbman_fq_query_np_rslt *r)
+{
+	return le32_to_cpu(r->byte_cnt);
+}
+
+struct qbman_bp_query_desc {
+	u8 verb;
+	u8 reserved;
+	__le16 bpid;
+	u8 reserved2[60];
+};
+
+int qbman_bp_query(struct qbman_swp *s, u16 bpid,
+		   struct qbman_bp_query_rslt *r)
+{
+	struct qbman_bp_query_desc *p;
+	void *resp;
+
+	p = (struct qbman_bp_query_desc *)qbman_swp_mc_start(s);
+	if (!p)
+		return -EBUSY;
+
+	p->bpid = cpu_to_le16(bpid);
+	resp = qbman_swp_mc_complete(s, p, QBMAN_BP_QUERY);
+	if (!resp) {
+		pr_err("qbman: Query BPID %d fields failed, no response\n",
+		       bpid);
+		return -EIO;
+	}
+	*r = *(struct qbman_bp_query_rslt *)resp;
+	/* Decode the outcome */
+	WARN_ON((r->verb & QBMAN_RESPONSE_VERB_MASK) != QBMAN_BP_QUERY);
+
+	/* Determine success or failure */
+	if (r->rslt != QBMAN_MC_RSLT_OK) {
+		pr_err("Query fields of BPID 0x%x failed, code=0x%02x\n",
+		       bpid, r->rslt);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+u32 qbman_bp_info_num_free_bufs(struct qbman_bp_query_rslt *a)
+{
+	return le32_to_cpu(a->fill);
+}
diff --git a/drivers/soc/fsl/dpio/qbman-portal.h b/drivers/soc/fsl/dpio/qbman-portal.h
index 89d1dd9969b6..fa35fc1afeaa 100644
--- a/drivers/soc/fsl/dpio/qbman-portal.h
+++ b/drivers/soc/fsl/dpio/qbman-portal.h
@@ -441,4 +441,62 @@ static inline void *qbman_swp_mc_complete(struct qbman_swp *swp, void *cmd,
 	return cmd;
 }
 
+/* Query APIs */
+struct qbman_fq_query_np_rslt {
+	u8 verb;
+	u8 rslt;
+	u8 st1;
+	u8 st2;
+	u8 reserved[2];
+	__le16 od1_sfdr;
+	__le16 od2_sfdr;
+	__le16 od3_sfdr;
+	__le16 ra1_sfdr;
+	__le16 ra2_sfdr;
+	__le32 pfdr_hptr;
+	__le32 pfdr_tptr;
+	__le32 frm_cnt;
+	__le32 byte_cnt;
+	__le16 ics_surp;
+	u8 is;
+	u8 reserved2[29];
+};
+
+int qbman_fq_query_state(struct qbman_swp *s, u32 fqid,
+			 struct qbman_fq_query_np_rslt *r);
+u32 qbman_fq_state_frame_count(const struct qbman_fq_query_np_rslt *r);
+u32 qbman_fq_state_byte_count(const struct qbman_fq_query_np_rslt *r);
+
+struct qbman_bp_query_rslt {
+	u8 verb;
+	u8 rslt;
+	u8 reserved[4];
+	u8 bdi;
+	u8 state;
+	__le32 fill;
+	__le32 hdotr;
+	__le16 swdet;
+	__le16 swdxt;
+	__le16 hwdet;
+	__le16 hwdxt;
+	__le16 swset;
+	__le16 swsxt;
+	__le16 vbpid;
+	__le16 icid;
+	__le64 bpscn_addr;
+	__le64 bpscn_ctx;
+	__le16 hw_targ;
+	u8 dbe;
+	u8 reserved2;
+	u8 sdcnt;
+	u8 hdcnt;
+	u8 sscnt;
+	u8 reserved3[9];
+};
+
+int qbman_bp_query(struct qbman_swp *s, u16 bpid,
+		   struct qbman_bp_query_rslt *r);
+
+u32 qbman_bp_info_num_free_bufs(struct qbman_bp_query_rslt *a);
+
 #endif /* __FSL_QBMAN_PORTAL_H */
diff --git a/include/soc/fsl/dpaa2-io.h b/include/soc/fsl/dpaa2-io.h
index 70997ab2146c..3fbd71c27ba3 100644
--- a/include/soc/fsl/dpaa2-io.h
+++ b/include/soc/fsl/dpaa2-io.h
@@ -116,4 +116,8 @@ struct dpaa2_io_store *dpaa2_io_store_create(unsigned int max_frames,
 void dpaa2_io_store_destroy(struct dpaa2_io_store *s);
 struct dpaa2_dq *dpaa2_io_store_next(struct dpaa2_io_store *s, int *is_last);
 
+int dpaa2_io_query_fq_count(struct dpaa2_io *d, u32 fqid,
+			    u32 *fcnt, u32 *bcnt);
+int dpaa2_io_query_bp_count(struct dpaa2_io *d, u16 bpid,
+			    u32 *num);
 #endif /* __FSL_DPAA2_IO_H */
-- 
cgit v1.2.3


From 610febc68ab79863eccaf829946a3d9278666772 Mon Sep 17 00:00:00 2001
From: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Date: Tue, 18 Dec 2018 15:23:01 +0000
Subject: dpaa2-eth: Add QBMAN related stats

Add statistics for pending frames in Rx/Tx conf FQs and
number of buffers in pool. Available through ethtool -S.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: Ioana ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/freescale/dpaa2/dpaa2-ethtool.c   | 41 ++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 0c831bffeb92..a7389e722c49 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -48,6 +48,12 @@ static char dpaa2_ethtool_extras[][ETH_GSTRING_LEN] = {
 	"[drv] xdp drop",
 	"[drv] xdp tx",
 	"[drv] xdp tx errors",
+	/* FQ stats */
+	"[qbman] rx pending frames",
+	"[qbman] rx pending bytes",
+	"[qbman] tx conf pending frames",
+	"[qbman] tx conf pending bytes",
+	"[qbman] buffer count",
 };
 
 #define DPAA2_ETH_NUM_EXTRA_STATS	ARRAY_SIZE(dpaa2_ethtool_extras)
@@ -177,6 +183,10 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 	int j, k, err;
 	int num_cnt;
 	union dpni_statistics dpni_stats;
+	u32 fcnt, bcnt;
+	u32 fcnt_rx_total = 0, fcnt_tx_total = 0;
+	u32 bcnt_rx_total = 0, bcnt_tx_total = 0;
+	u32 buf_cnt;
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	struct dpaa2_eth_drv_stats *extras;
 	struct dpaa2_eth_ch_stats *ch_stats;
@@ -219,6 +229,37 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 		for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64); j++)
 			*((__u64 *)data + i + j) += *((__u64 *)ch_stats + j);
 	}
+	i += j;
+
+	for (j = 0; j < priv->num_fqs; j++) {
+		/* Print FQ instantaneous counts */
+		err = dpaa2_io_query_fq_count(NULL, priv->fq[j].fqid,
+					      &fcnt, &bcnt);
+		if (err) {
+			netdev_warn(net_dev, "FQ query error %d", err);
+			return;
+		}
+
+		if (priv->fq[j].type == DPAA2_TX_CONF_FQ) {
+			fcnt_tx_total += fcnt;
+			bcnt_tx_total += bcnt;
+		} else {
+			fcnt_rx_total += fcnt;
+			bcnt_rx_total += bcnt;
+		}
+	}
+
+	*(data + i++) = fcnt_rx_total;
+	*(data + i++) = bcnt_rx_total;
+	*(data + i++) = fcnt_tx_total;
+	*(data + i++) = bcnt_tx_total;
+
+	err = dpaa2_io_query_bp_count(NULL, priv->bpid, &buf_cnt);
+	if (err) {
+		netdev_warn(net_dev, "Buffer count query error %d\n", err);
+		return;
+	}
+	*(data + i++) = buf_cnt;
 }
 
 static int prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask,
-- 
cgit v1.2.3


From c4b0e771f906f5beb7d90c3d28fe55ff9dbd038c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:15 +0100
Subject: netfilter: avoid using skb->nf_bridge directly

This pointer is going to be removed soon, so use the existing helpers in
more places to avoid noise when the removal happens.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netfilter_bridge.h     | 33 +++++++++++++++++-------
 include/net/netfilter/br_netfilter.h |  6 -----
 net/bridge/br_netfilter_hooks.c      | 19 ++++++++++----
 net/ipv4/netfilter/nf_reject_ipv4.c  |  6 +++--
 net/ipv6/netfilter/nf_reject_ipv6.c  | 10 +++++---
 net/netfilter/nf_log_common.c        | 20 +++++++--------
 net/netfilter/nf_queue.c             | 50 ++++++++++++++++++++++++------------
 net/netfilter/nfnetlink_queue.c      | 23 ++++++++---------
 net/netfilter/xt_physdev.c           |  2 +-
 9 files changed, 103 insertions(+), 66 deletions(-)

diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index fa0686500970..0a65a422587c 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -17,43 +17,58 @@ static inline void br_drop_fake_rtable(struct sk_buff *skb)
 		skb_dst_drop(skb);
 }
 
+static inline struct nf_bridge_info *
+nf_bridge_info_get(const struct sk_buff *skb)
+{
+	return skb->nf_bridge;
+}
+
+static inline bool nf_bridge_info_exists(const struct sk_buff *skb)
+{
+	return skb->nf_bridge != NULL;
+}
+
 static inline int nf_bridge_get_physinif(const struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge;
+	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
-	if (skb->nf_bridge == NULL)
+	if (!nf_bridge)
 		return 0;
 
-	nf_bridge = skb->nf_bridge;
 	return nf_bridge->physindev ? nf_bridge->physindev->ifindex : 0;
 }
 
 static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge;
+	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
-	if (skb->nf_bridge == NULL)
+	if (!nf_bridge)
 		return 0;
 
-	nf_bridge = skb->nf_bridge;
 	return nf_bridge->physoutdev ? nf_bridge->physoutdev->ifindex : 0;
 }
 
 static inline struct net_device *
 nf_bridge_get_physindev(const struct sk_buff *skb)
 {
-	return skb->nf_bridge ? skb->nf_bridge->physindev : NULL;
+	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+
+	return nf_bridge ? nf_bridge->physindev : NULL;
 }
 
 static inline struct net_device *
 nf_bridge_get_physoutdev(const struct sk_buff *skb)
 {
-	return skb->nf_bridge ? skb->nf_bridge->physoutdev : NULL;
+	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+
+	return nf_bridge ? nf_bridge->physoutdev : NULL;
 }
 
 static inline bool nf_bridge_in_prerouting(const struct sk_buff *skb)
 {
-	return skb->nf_bridge && skb->nf_bridge->in_prerouting;
+	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+
+	return nf_bridge && nf_bridge->in_prerouting;
 }
 #else
 #define br_drop_fake_rtable(skb)	        do { } while (0)
diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h
index 74af19c3a8f7..6efc0153987b 100644
--- a/include/net/netfilter/br_netfilter.h
+++ b/include/net/netfilter/br_netfilter.h
@@ -22,12 +22,6 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net, struct sock *sk,
 		      int (*okfn)(struct net *, struct sock *,
 				  struct sk_buff *));
 
-static inline struct nf_bridge_info *
-nf_bridge_info_get(const struct sk_buff *skb)
-{
-	return skb->nf_bridge;
-}
-
 unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb);
 
 static inline void nf_bridge_push_encap_header(struct sk_buff *skb)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index c9383c470a83..c58cf68b45c5 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -247,7 +247,9 @@ drop:
 
 void nf_bridge_update_protocol(struct sk_buff *skb)
 {
-	switch (skb->nf_bridge->orig_proto) {
+	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+
+	switch (nf_bridge->orig_proto) {
 	case BRNF_PROTO_8021Q:
 		skb->protocol = htons(ETH_P_8021Q);
 		break;
@@ -569,7 +571,8 @@ static unsigned int br_nf_forward_ip(void *priv,
 	struct net_device *parent;
 	u_int8_t pf;
 
-	if (!skb->nf_bridge)
+	nf_bridge = nf_bridge_info_get(skb);
+	if (!nf_bridge)
 		return NF_ACCEPT;
 
 	/* Need exclusive nf_bridge_info since we might have multiple
@@ -701,7 +704,9 @@ br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 
 static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
 {
-	if (skb->nf_bridge->orig_proto == BRNF_PROTO_PPPOE)
+	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+
+	if (nf_bridge->orig_proto == BRNF_PROTO_PPPOE)
 		return PPPOE_SES_HLEN;
 	return 0;
 }
@@ -839,7 +844,9 @@ static unsigned int ip_sabotage_in(void *priv,
 				   struct sk_buff *skb,
 				   const struct nf_hook_state *state)
 {
-	if (skb->nf_bridge && !skb->nf_bridge->in_prerouting &&
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+
+	if (nf_bridge && !nf_bridge->in_prerouting &&
 	    !netif_is_l3_master(skb->dev)) {
 		state->okfn(state->net, state->sk, skb);
 		return NF_STOLEN;
@@ -877,7 +884,9 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 
 static int br_nf_dev_xmit(struct sk_buff *skb)
 {
-	if (skb->nf_bridge && skb->nf_bridge->bridged_dnat) {
+	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+
+	if (nf_bridge && nf_bridge->bridged_dnat) {
 		br_nf_pre_routing_finish_bridge_slow(skb);
 		return 1;
 	}
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 5cd06ba3535d..aa8304c618b8 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -102,6 +102,7 @@ EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put);
 /* Send RST reply */
 void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 {
+	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
 	struct iphdr *niph;
 	const struct tcphdr *oth;
@@ -147,10 +148,11 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	if (oldskb->nf_bridge) {
+	br_indev = nf_bridge_get_physindev(oldskb);
+	if (br_indev) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
 
-		nskb->dev = nf_bridge_get_physindev(oldskb);
+		nskb->dev = br_indev;
 		niph->tot_len = htons(nskb->len);
 		ip_send_check(niph);
 		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 24858402e374..b9c8a763c863 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -131,6 +131,7 @@ EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_put);
 
 void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 {
+	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
 	struct tcphdr _otcph;
 	const struct tcphdr *otcph;
@@ -197,15 +198,18 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	if (oldskb->nf_bridge) {
+	br_indev = nf_bridge_get_physindev(oldskb);
+	if (br_indev) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
 
-		nskb->dev = nf_bridge_get_physindev(oldskb);
+		nskb->dev = br_indev;
 		nskb->protocol = htons(ETH_P_IPV6);
 		ip6h->payload_len = htons(sizeof(struct tcphdr));
 		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
-				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
+				    oeth->h_source, oeth->h_dest, nskb->len) < 0) {
+			kfree_skb(nskb);
 			return;
+		}
 		dev_queue_xmit(nskb);
 	} else
 #endif
diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c
index a8c5c846aec1..3a0d6880b7c9 100644
--- a/net/netfilter/nf_log_common.c
+++ b/net/netfilter/nf_log_common.c
@@ -156,22 +156,20 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf,
 			  const struct net_device *out,
 			  const struct nf_loginfo *loginfo, const char *prefix)
 {
+	const struct net_device *physoutdev __maybe_unused;
+	const struct net_device *physindev __maybe_unused;
+
 	nf_log_buf_add(m, KERN_SOH "%c%sIN=%s OUT=%s ",
 	       '0' + loginfo->u.log.level, prefix,
 	       in ? in->name : "",
 	       out ? out->name : "");
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	if (skb->nf_bridge) {
-		const struct net_device *physindev;
-		const struct net_device *physoutdev;
-
-		physindev = nf_bridge_get_physindev(skb);
-		if (physindev && in != physindev)
-			nf_log_buf_add(m, "PHYSIN=%s ", physindev->name);
-		physoutdev = nf_bridge_get_physoutdev(skb);
-		if (physoutdev && out != physoutdev)
-			nf_log_buf_add(m, "PHYSOUT=%s ", physoutdev->name);
-	}
+	physindev = nf_bridge_get_physindev(skb);
+	if (physindev && in != physindev)
+		nf_log_buf_add(m, "PHYSIN=%s ", physindev->name);
+	physoutdev = nf_bridge_get_physoutdev(skb);
+	if (physoutdev && out != physoutdev)
+		nf_log_buf_add(m, "PHYSOUT=%s ", physoutdev->name);
 #endif
 }
 EXPORT_SYMBOL_GPL(nf_log_dump_packet_common);
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index d67a96a25a68..a36a77bae1d6 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -46,6 +46,24 @@ void nf_unregister_queue_handler(struct net *net)
 }
 EXPORT_SYMBOL(nf_unregister_queue_handler);
 
+static void nf_queue_entry_release_br_nf_refs(struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+
+	if (nf_bridge) {
+		struct net_device *physdev;
+
+		physdev = nf_bridge_get_physindev(skb);
+		if (physdev)
+			dev_put(physdev);
+		physdev = nf_bridge_get_physoutdev(skb);
+		if (physdev)
+			dev_put(physdev);
+	}
+#endif
+}
+
 void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
 {
 	struct nf_hook_state *state = &entry->state;
@@ -57,20 +75,28 @@ void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
 		dev_put(state->out);
 	if (state->sk)
 		sock_put(state->sk);
+
+	nf_queue_entry_release_br_nf_refs(entry->skb);
+}
+EXPORT_SYMBOL_GPL(nf_queue_entry_release_refs);
+
+static void nf_queue_entry_get_br_nf_refs(struct sk_buff *skb)
+{
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	if (entry->skb->nf_bridge) {
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+
+	if (nf_bridge) {
 		struct net_device *physdev;
 
-		physdev = nf_bridge_get_physindev(entry->skb);
+		physdev = nf_bridge_get_physindev(skb);
 		if (physdev)
-			dev_put(physdev);
-		physdev = nf_bridge_get_physoutdev(entry->skb);
+			dev_hold(physdev);
+		physdev = nf_bridge_get_physoutdev(skb);
 		if (physdev)
-			dev_put(physdev);
+			dev_hold(physdev);
 	}
 #endif
 }
-EXPORT_SYMBOL_GPL(nf_queue_entry_release_refs);
 
 /* Bump dev refs so they don't vanish while packet is out */
 void nf_queue_entry_get_refs(struct nf_queue_entry *entry)
@@ -83,18 +109,8 @@ void nf_queue_entry_get_refs(struct nf_queue_entry *entry)
 		dev_hold(state->out);
 	if (state->sk)
 		sock_hold(state->sk);
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	if (entry->skb->nf_bridge) {
-		struct net_device *physdev;
 
-		physdev = nf_bridge_get_physindev(entry->skb);
-		if (physdev)
-			dev_hold(physdev);
-		physdev = nf_bridge_get_physoutdev(entry->skb);
-		if (physdev)
-			dev_hold(physdev);
-	}
-#endif
+	nf_queue_entry_get_br_nf_refs(entry->skb);
 }
 EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs);
 
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 1ce30efe6854..0dcc3592d053 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -727,13 +727,13 @@ nf_queue_entry_dup(struct nf_queue_entry *e)
  */
 static void nf_bridge_adjust_skb_data(struct sk_buff *skb)
 {
-	if (skb->nf_bridge)
+	if (nf_bridge_info_get(skb))
 		__skb_push(skb, skb->network_header - skb->mac_header);
 }
 
 static void nf_bridge_adjust_segmented_data(struct sk_buff *skb)
 {
-	if (skb->nf_bridge)
+	if (nf_bridge_info_get(skb))
 		__skb_pull(skb, skb->network_header - skb->mac_header);
 }
 #else
@@ -904,23 +904,22 @@ nfqnl_set_mode(struct nfqnl_instance *queue,
 static int
 dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex)
 {
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	int physinif, physoutif;
+
+	physinif = nf_bridge_get_physinif(entry->skb);
+	physoutif = nf_bridge_get_physoutif(entry->skb);
+
+	if (physinif == ifindex || physoutif == ifindex)
+		return 1;
+#endif
 	if (entry->state.in)
 		if (entry->state.in->ifindex == ifindex)
 			return 1;
 	if (entry->state.out)
 		if (entry->state.out->ifindex == ifindex)
 			return 1;
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	if (entry->skb->nf_bridge) {
-		int physinif, physoutif;
 
-		physinif = nf_bridge_get_physinif(entry->skb);
-		physoutif = nf_bridge_get_physoutif(entry->skb);
-
-		if (physinif == ifindex || physoutif == ifindex)
-			return 1;
-	}
-#endif
 	return 0;
 }
 
diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c
index 9d6d67b953ac..4034d70bff39 100644
--- a/net/netfilter/xt_physdev.c
+++ b/net/netfilter/xt_physdev.c
@@ -33,7 +33,7 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	/* Not a bridged IP packet or no info available yet:
 	 * LOCAL_OUT/mangle and LOCAL_OUT/nat don't know if
 	 * the destination device will be a bridge. */
-	if (!skb->nf_bridge) {
+	if (!nf_bridge_info_exists(skb)) {
 		/* Return MATCH if the invert flags of the used options are on */
 		if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) &&
 		    !(info->invert & XT_PHYSDEV_OP_BRIDGED))
-- 
cgit v1.2.3


From df5042f4c5b9326c593bf2e31ed859ebc3b4130a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:16 +0100
Subject: sk_buff: add skb extension infrastructure

This adds an optional extension infrastructure, with ispec (xfrm) and
bridge netfilter as first users.
objdiff shows no changes if kernel is built without xfrm and br_netfilter
support.

The third (planned future) user is Multipath TCP which is still
out-of-tree.
MPTCP needs to map logical mptcp sequence numbers to the tcp sequence
numbers used by individual subflows.

This DSS mapping is read/written from tcp option space on receive and
written to tcp option space on transmitted tcp packets that are part of
and MPTCP connection.

Extending skb_shared_info or adding a private data field to skb fclones
doesn't work for incoming skb, so a different DSS propagation method would
be required for the receive side.

mptcp has same requirements as secpath/bridge netfilter:

1. extension memory is released when the sk_buff is free'd.
2. data is shared after cloning an skb (clone inherits extension)
3. adding extension to an skb will COW the extension buffer if needed.

The "MPTCP upstreaming" effort adds SKB_EXT_MPTCP extension to store the
mapping for tx and rx processing.

Two new members are added to sk_buff:
1. 'active_extensions' byte (filling a hole), telling which extensions
   are available for this skb.
   This has two purposes.
   a) avoids the need to initialize the pointer.
   b) allows to "delete" an extension by clearing its bit
   value in ->active_extensions.

   While it would be possible to store the active_extensions byte
   in the extension struct instead of sk_buff, there is one problem
   with this:
    When an extension has to be disabled, we can always clear the
    bit in skb->active_extensions.  But in case it would be stored in the
    extension buffer itself, we might have to COW it first, if
    we are dealing with a cloned skb.  On kmalloc failure we would
    be unable to turn an extension off.

2. extension pointer, located at the end of the sk_buff.
   If the active_extensions byte is 0, the pointer is undefined,
   it is not initialized on skb allocation.

This adds extra code to skb clone and free paths (to deal with
refcount/free of extension area) but this replaces similar code that
manages skb->nf_bridge and skb->sp structs in the followup patches of
the series.

It is possible to add support for extensions that are not preseved on
clones/copies.

To do this, it would be needed to define a bitmask of all extensions that
need copy/cow semantics, and change __skb_ext_copy() to check
->active_extensions & SKB_EXT_PRESERVE_ON_CLONE, then just set
->active_extensions to 0 on the new clone.

This isn't done here because all extensions that get added here
need the copy/cow semantics.

v2:
Allocate entire extension space using kmem_cache.
Upside is that this allows better tracking of used memory,
downside is that we will allocate more space than strictly needed in
most cases (its unlikely that all extensions are active/needed at same
time for same skb).
The allocated memory (except the small extension header) is not cleared,
so no additonal overhead aside from memory usage.

Avoid atomic_dec_and_test operation on skb_ext_put()
by using similar trick as kfree_skbmem() does with fclone_ref:
If recount is 1, there is no concurrent user and we can free right away.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 111 ++++++++++++++++++++++++++++++++++-
 net/Kconfig            |   3 +
 net/core/skbuff.c      | 155 +++++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/ip_output.c   |   1 +
 net/ipv6/ip6_output.c  |   1 +
 5 files changed, 270 insertions(+), 1 deletion(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b1831a5ca173..88f7541837e3 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -245,6 +245,7 @@ struct iov_iter;
 struct napi_struct;
 struct bpf_prog;
 union bpf_attr;
+struct skb_ext;
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 struct nf_conntrack {
@@ -636,6 +637,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@queue_mapping: Queue mapping for multiqueue devices
  *	@xmit_more: More SKBs are pending for this queue
  *	@pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
+ *	@active_extensions: active extensions (skb_ext_id types)
  *	@ndisc_nodetype: router type (from link layer)
  *	@ooo_okay: allow the mapping of a socket to a queue to be changed
  *	@l4_hash: indicate hash is a canonical 4-tuple hash over transport
@@ -665,6 +667,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@data: Data head pointer
  *	@truesize: Buffer size
  *	@users: User count - see {datagram,tcp}.c
+ *	@extensions: allocated extensions, valid if active_extensions is nonzero
  */
 
 struct sk_buff {
@@ -747,7 +750,9 @@ struct sk_buff {
 				head_frag:1,
 				xmit_more:1,
 				pfmemalloc:1;
-
+#ifdef CONFIG_SKB_EXTENSIONS
+	__u8			active_extensions;
+#endif
 	/* fields enclosed in headers_start/headers_end are copied
 	 * using a single memcpy() in __copy_skb_header()
 	 */
@@ -869,6 +874,11 @@ struct sk_buff {
 				*data;
 	unsigned int		truesize;
 	refcount_t		users;
+
+#ifdef CONFIG_SKB_EXTENSIONS
+	/* only useable after checking ->active_extensions != 0 */
+	struct skb_ext		*extensions;
+#endif
 };
 
 #ifdef __KERNEL__
@@ -3896,6 +3906,105 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct)
 		atomic_inc(&nfct->use);
 }
 #endif
+
+#ifdef CONFIG_SKB_EXTENSIONS
+enum skb_ext_id {
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	SKB_EXT_BRIDGE_NF,
+#endif
+	SKB_EXT_NUM, /* must be last */
+};
+
+/**
+ *	struct skb_ext - sk_buff extensions
+ *	@refcnt: 1 on allocation, deallocated on 0
+ *	@offset: offset to add to @data to obtain extension address
+ *	@chunks: size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units
+ *	@data: start of extension data, variable sized
+ *
+ *	Note: offsets/lengths are stored in chunks of 8 bytes, this allows
+ *	to use 'u8' types while allowing up to 2kb worth of extension data.
+ */
+struct skb_ext {
+	refcount_t refcnt;
+	u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */
+	u8 chunks;		/* same */
+	char data[0] __aligned(8);
+};
+
+void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id);
+void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id);
+void __skb_ext_put(struct skb_ext *ext);
+
+static inline void skb_ext_put(struct sk_buff *skb)
+{
+	if (skb->active_extensions)
+		__skb_ext_put(skb->extensions);
+}
+
+static inline void skb_ext_get(struct sk_buff *skb)
+{
+	if (skb->active_extensions) {
+		struct skb_ext *ext = skb->extensions;
+
+		if (ext)
+			refcount_inc(&ext->refcnt);
+	}
+}
+
+static inline void __skb_ext_copy(struct sk_buff *dst,
+				  const struct sk_buff *src)
+{
+	dst->active_extensions = src->active_extensions;
+
+	if (src->active_extensions) {
+		struct skb_ext *ext = src->extensions;
+
+		refcount_inc(&ext->refcnt);
+		dst->extensions = ext;
+	}
+}
+
+static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src)
+{
+	skb_ext_put(dst);
+	__skb_ext_copy(dst, src);
+}
+
+static inline bool __skb_ext_exist(const struct skb_ext *ext, enum skb_ext_id i)
+{
+	return !!ext->offset[i];
+}
+
+static inline bool skb_ext_exist(const struct sk_buff *skb, enum skb_ext_id id)
+{
+	return skb->active_extensions & (1 << id);
+}
+
+static inline void skb_ext_del(struct sk_buff *skb, enum skb_ext_id id)
+{
+	if (skb_ext_exist(skb, id))
+		__skb_ext_del(skb, id);
+}
+
+static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id)
+{
+	if (skb_ext_exist(skb, id)) {
+		struct skb_ext *ext = skb->extensions;
+
+		return (void *)ext + (ext->offset[id] << 3);
+	}
+
+	return NULL;
+}
+#else
+static inline void skb_ext_put(struct sk_buff *skb) {}
+static inline void skb_ext_get(struct sk_buff *skb) {}
+static inline void skb_ext_del(struct sk_buff *skb, int unused) {}
+static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {}
+static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {}
+#endif /* CONFIG_SKB_EXTENSIONS */
+
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge)
 {
diff --git a/net/Kconfig b/net/Kconfig
index f235edb593ba..93b291292860 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -51,6 +51,9 @@ config NET_INGRESS
 config NET_EGRESS
 	bool
 
+config SKB_EXTENSIONS
+	bool
+
 menu "Networking options"
 
 source "net/packet/Kconfig"
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 40552547c69a..d2dfad33e686 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -79,6 +79,9 @@
 
 struct kmem_cache *skbuff_head_cache __ro_after_init;
 static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
+#ifdef CONFIG_SKB_EXTENSIONS
+static struct kmem_cache *skbuff_ext_cache __ro_after_init;
+#endif
 int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
 EXPORT_SYMBOL(sysctl_max_skb_frags);
 
@@ -617,6 +620,7 @@ void skb_release_head_state(struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	nf_bridge_put(skb->nf_bridge);
 #endif
+	skb_ext_put(skb);
 }
 
 /* Free everything but the sk_buff shell. */
@@ -796,6 +800,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->dev		= old->dev;
 	memcpy(new->cb, old->cb, sizeof(old->cb));
 	skb_dst_copy(new, old);
+	__skb_ext_copy(new, old);
 #ifdef CONFIG_XFRM
 	new->sp			= secpath_get(old->sp);
 #endif
@@ -3902,6 +3907,40 @@ done:
 }
 EXPORT_SYMBOL_GPL(skb_gro_receive);
 
+#ifdef CONFIG_SKB_EXTENSIONS
+#define SKB_EXT_ALIGN_VALUE	8
+#define SKB_EXT_CHUNKSIZEOF(x)	(ALIGN((sizeof(x)), SKB_EXT_ALIGN_VALUE) / SKB_EXT_ALIGN_VALUE)
+
+static const u8 skb_ext_type_len[] = {
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	[SKB_EXT_BRIDGE_NF] = SKB_EXT_CHUNKSIZEOF(struct nf_bridge_info),
+#endif
+};
+
+static __always_inline unsigned int skb_ext_total_length(void)
+{
+	return SKB_EXT_CHUNKSIZEOF(struct skb_ext) +
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+		skb_ext_type_len[SKB_EXT_BRIDGE_NF] +
+#endif
+		0;
+}
+
+static void skb_extensions_init(void)
+{
+	BUILD_BUG_ON(SKB_EXT_NUM >= 8);
+	BUILD_BUG_ON(skb_ext_total_length() > 255);
+
+	skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache",
+					     SKB_EXT_ALIGN_VALUE * skb_ext_total_length(),
+					     0,
+					     SLAB_HWCACHE_ALIGN|SLAB_PANIC,
+					     NULL);
+}
+#else
+static void skb_extensions_init(void) {}
+#endif
+
 void __init skb_init(void)
 {
 	skbuff_head_cache = kmem_cache_create_usercopy("skbuff_head_cache",
@@ -3916,6 +3955,7 @@ void __init skb_init(void)
 						0,
 						SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 						NULL);
+	skb_extensions_init();
 }
 
 static int
@@ -5554,3 +5594,118 @@ void skb_condense(struct sk_buff *skb)
 	 */
 	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
 }
+
+#ifdef CONFIG_SKB_EXTENSIONS
+static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id)
+{
+	return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE);
+}
+
+static struct skb_ext *skb_ext_alloc(void)
+{
+	struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC);
+
+	if (new) {
+		memset(new->offset, 0, sizeof(new->offset));
+		refcount_set(&new->refcnt, 1);
+	}
+
+	return new;
+}
+
+static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old)
+{
+	struct skb_ext *new;
+
+	if (refcount_read(&old->refcnt) == 1)
+		return old;
+
+	new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC);
+	if (!new)
+		return NULL;
+
+	memcpy(new, old, old->chunks * SKB_EXT_ALIGN_VALUE);
+	refcount_set(&new->refcnt, 1);
+
+	__skb_ext_put(old);
+	return new;
+}
+
+/**
+ * skb_ext_add - allocate space for given extension, COW if needed
+ * @skb: buffer
+ * @id: extension to allocate space for
+ *
+ * Allocates enough space for the given extension.
+ * If the extension is already present, a pointer to that extension
+ * is returned.
+ *
+ * If the skb was cloned, COW applies and the returned memory can be
+ * modified without changing the extension space of clones buffers.
+ *
+ * Returns pointer to the extension or NULL on allocation failure.
+ */
+void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id)
+{
+	struct skb_ext *new, *old = NULL;
+	unsigned int newlen, newoff;
+
+	if (skb->active_extensions) {
+		old = skb->extensions;
+
+		new = skb_ext_maybe_cow(old);
+		if (!new)
+			return NULL;
+
+		if (__skb_ext_exist(old, id)) {
+			if (old != new)
+				skb->extensions = new;
+			goto set_active;
+		}
+
+		newoff = old->chunks;
+	} else {
+		newoff = SKB_EXT_CHUNKSIZEOF(*new);
+
+		new = skb_ext_alloc();
+		if (!new)
+			return NULL;
+	}
+
+	newlen = newoff + skb_ext_type_len[id];
+	new->chunks = newlen;
+	new->offset[id] = newoff;
+	skb->extensions = new;
+set_active:
+	skb->active_extensions |= 1 << id;
+	return skb_ext_get_ptr(new, id);
+}
+EXPORT_SYMBOL(skb_ext_add);
+
+void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id)
+{
+	struct skb_ext *ext = skb->extensions;
+
+	skb->active_extensions &= ~(1 << id);
+	if (skb->active_extensions == 0) {
+		skb->extensions = NULL;
+		__skb_ext_put(ext);
+	}
+}
+EXPORT_SYMBOL(__skb_ext_del);
+
+void __skb_ext_put(struct skb_ext *ext)
+{
+	/* If this is last clone, nothing can increment
+	 * it after check passes.  Avoids one atomic op.
+	 */
+	if (refcount_read(&ext->refcnt) == 1)
+		goto free_now;
+
+	if (!refcount_dec_and_test(&ext->refcnt))
+		return;
+free_now:
+	kmem_cache_free(skbuff_ext_cache, ext);
+}
+EXPORT_SYMBOL(__skb_ext_put);
+#endif /* CONFIG_SKB_EXTENSIONS */
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index ab6618036afe..c80188875f39 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -533,6 +533,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->tc_index = from->tc_index;
 #endif
 	nf_copy(to, from);
+	skb_ext_copy(to, from);
 #if IS_ENABLED(CONFIG_IP_VS)
 	to->ipvs_property = from->ipvs_property;
 #endif
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9d55ee33b7f9..703a8e801c5c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -581,6 +581,7 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->tc_index = from->tc_index;
 #endif
 	nf_copy(to, from);
+	skb_ext_copy(to, from);
 	skb_copy_secmark(to, from);
 }
 
-- 
cgit v1.2.3


From de8bda1d22d38b7d5cd08b33f86efd94d4c86630 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:17 +0100
Subject: net: convert bridge_nf to use skb extension infrastructure

This converts the bridge netfilter (calling iptables hooks from bridge)
facility to use the extension infrastructure.

The bridge_nf specific hooks in skb clone and free paths are removed, they
have been replaced by the skb_ext hooks that do the same as the bridge nf
allocations hooks did.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netfilter_bridge.h     |  4 ++--
 include/linux/skbuff.h               | 28 ++--------------------------
 include/net/netfilter/br_netfilter.h |  8 ++++----
 net/Kconfig                          |  1 +
 net/bridge/br_netfilter_hooks.c      | 20 ++------------------
 net/bridge/br_netfilter_ipv6.c       |  4 ++--
 net/core/skbuff.c                    |  3 ---
 7 files changed, 13 insertions(+), 55 deletions(-)

diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index 0a65a422587c..5f2614d02e03 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -20,12 +20,12 @@ static inline void br_drop_fake_rtable(struct sk_buff *skb)
 static inline struct nf_bridge_info *
 nf_bridge_info_get(const struct sk_buff *skb)
 {
-	return skb->nf_bridge;
+	return skb_ext_find(skb, SKB_EXT_BRIDGE_NF);
 }
 
 static inline bool nf_bridge_info_exists(const struct sk_buff *skb)
 {
-	return skb->nf_bridge != NULL;
+	return skb_ext_exist(skb, SKB_EXT_BRIDGE_NF);
 }
 
 static inline int nf_bridge_get_physinif(const struct sk_buff *skb)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 88f7541837e3..2f42d2e99f17 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -255,7 +255,6 @@ struct nf_conntrack {
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 struct nf_bridge_info {
-	refcount_t		use;
 	enum {
 		BRNF_PROTO_UNCHANGED,
 		BRNF_PROTO_8021Q,
@@ -720,9 +719,6 @@ struct sk_buff {
 #endif
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	unsigned long		 _nfct;
-#endif
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	struct nf_bridge_info	*nf_bridge;
 #endif
 	unsigned int		len,
 				data_len;
@@ -4005,18 +4001,6 @@ static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {}
 static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {}
 #endif /* CONFIG_SKB_EXTENSIONS */
 
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge)
-{
-	if (nf_bridge && refcount_dec_and_test(&nf_bridge->use))
-		kfree(nf_bridge);
-}
-static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge)
-{
-	if (nf_bridge)
-		refcount_inc(&nf_bridge->use);
-}
-#endif /* CONFIG_BRIDGE_NETFILTER */
 static inline void nf_reset(struct sk_buff *skb)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
@@ -4024,8 +4008,7 @@ static inline void nf_reset(struct sk_buff *skb)
 	skb->_nfct = 0;
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	nf_bridge_put(skb->nf_bridge);
-	skb->nf_bridge = NULL;
+	skb_ext_del(skb, SKB_EXT_BRIDGE_NF);
 #endif
 }
 
@@ -4043,7 +4026,7 @@ static inline void ipvs_reset(struct sk_buff *skb)
 #endif
 }
 
-/* Note: This doesn't put any conntrack and bridge info in dst. */
+/* Note: This doesn't put any conntrack info in dst. */
 static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src,
 			     bool copy)
 {
@@ -4051,10 +4034,6 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src,
 	dst->_nfct = src->_nfct;
 	nf_conntrack_get(skb_nfct(src));
 #endif
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	dst->nf_bridge  = src->nf_bridge;
-	nf_bridge_get(src->nf_bridge);
-#endif
 #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES)
 	if (copy)
 		dst->nf_trace = src->nf_trace;
@@ -4065,9 +4044,6 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(skb_nfct(dst));
-#endif
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	nf_bridge_put(dst->nf_bridge);
 #endif
 	__nf_copy(dst, src, true);
 }
diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h
index 6efc0153987b..4cd56808ac4e 100644
--- a/include/net/netfilter/br_netfilter.h
+++ b/include/net/netfilter/br_netfilter.h
@@ -6,12 +6,12 @@
 
 static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb)
 {
-	skb->nf_bridge = kzalloc(sizeof(struct nf_bridge_info), GFP_ATOMIC);
+	struct nf_bridge_info *b = skb_ext_add(skb, SKB_EXT_BRIDGE_NF);
 
-	if (likely(skb->nf_bridge))
-		refcount_set(&(skb->nf_bridge->use), 1);
+	if (b)
+		memset(b, 0, sizeof(*b));
 
-	return skb->nf_bridge;
+	return b;
 }
 
 void nf_bridge_update_protocol(struct sk_buff *skb);
diff --git a/net/Kconfig b/net/Kconfig
index 93b291292860..5cb9de1aaf88 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -187,6 +187,7 @@ config BRIDGE_NETFILTER
 	depends on NETFILTER && INET
 	depends on NETFILTER_ADVANCED
 	select NETFILTER_FAMILY_BRIDGE
+	select SKB_EXTENSIONS
 	default m
 	---help---
 	  Enabling this option will let arptables resp. iptables see bridged
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index c58cf68b45c5..d21a23698410 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -132,10 +132,7 @@ static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage);
 
 static void nf_bridge_info_free(struct sk_buff *skb)
 {
-	if (skb->nf_bridge) {
-		nf_bridge_put(skb->nf_bridge);
-		skb->nf_bridge = NULL;
-	}
+	skb_ext_del(skb, SKB_EXT_BRIDGE_NF);
 }
 
 static inline struct net_device *bridge_parent(const struct net_device *dev)
@@ -148,19 +145,7 @@ static inline struct net_device *bridge_parent(const struct net_device *dev)
 
 static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
-
-	if (refcount_read(&nf_bridge->use) > 1) {
-		struct nf_bridge_info *tmp = nf_bridge_alloc(skb);
-
-		if (tmp) {
-			memcpy(tmp, nf_bridge, sizeof(struct nf_bridge_info));
-			refcount_set(&tmp->use, 1);
-		}
-		nf_bridge_put(nf_bridge);
-		nf_bridge = tmp;
-	}
-	return nf_bridge;
+	return skb_ext_add(skb, SKB_EXT_BRIDGE_NF);
 }
 
 unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb)
@@ -508,7 +493,6 @@ static unsigned int br_nf_pre_routing(void *priv,
 	if (br_validate_ipv4(state->net, skb))
 		return NF_DROP;
 
-	nf_bridge_put(skb->nf_bridge);
 	if (!nf_bridge_alloc(skb))
 		return NF_DROP;
 	if (!setup_pre_routing(skb))
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 96c072e71ea2..94039f588f1d 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -224,8 +224,8 @@ unsigned int br_nf_pre_routing_ipv6(void *priv,
 	if (br_validate_ipv6(state->net, skb))
 		return NF_DROP;
 
-	nf_bridge_put(skb->nf_bridge);
-	if (!nf_bridge_alloc(skb))
+	nf_bridge = nf_bridge_alloc(skb);
+	if (!nf_bridge)
 		return NF_DROP;
 	if (!setup_pre_routing(skb))
 		return NF_DROP;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d2dfad33e686..0c65723591d7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -616,9 +616,6 @@ void skb_release_head_state(struct sk_buff *skb)
 	}
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	nf_conntrack_put(skb_nfct(skb));
-#endif
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	nf_bridge_put(skb->nf_bridge);
 #endif
 	skb_ext_put(skb);
 }
-- 
cgit v1.2.3


From 0ca64da128b816b2826e9b469f47239c47f1df31 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:18 +0100
Subject: xfrm: change secpath_set to return secpath struct, not error value

It can only return 0 (success) or -ENOMEM.
Change return value to a pointer to secpath struct.

This avoids direct access to skb->sp:

err = secpath_set(skb);
if (!err) ..
skb->sp-> ...

Becomes:
sp = secpath_set(skb)
if (!sp) ..
sp-> ..

This reduces noise in followup patch which is going to remove skb->sp.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h      |  2 +-
 net/ipv4/esp4_offload.c | 11 ++++++-----
 net/ipv6/esp6_offload.c | 11 ++++++-----
 net/ipv6/xfrm6_input.c  |  6 ++++--
 net/xfrm/xfrm_input.c   | 16 +++++++++-------
 5 files changed, 26 insertions(+), 20 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 0a8d70d16918..62ca62177bc6 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1131,7 +1131,7 @@ secpath_put(struct sec_path *sp)
 }
 
 struct sec_path *secpath_dup(struct sec_path *src);
-int secpath_set(struct sk_buff *skb);
+struct sec_path *secpath_set(struct sk_buff *skb);
 
 static inline void
 secpath_reset(struct sk_buff *skb)
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 58834a10c0be..19bd22aa05f9 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -46,11 +46,12 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 
 	xo = xfrm_offload(skb);
 	if (!xo || !(xo->flags & CRYPTO_DONE)) {
-		err = secpath_set(skb);
-		if (err)
+		struct sec_path *sp = secpath_set(skb);
+
+		if (!sp)
 			goto out;
 
-		if (skb->sp->len == XFRM_MAX_DEPTH)
+		if (sp->len == XFRM_MAX_DEPTH)
 			goto out;
 
 		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
@@ -59,8 +60,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 		if (!x)
 			goto out;
 
-		skb->sp->xvec[skb->sp->len++] = x;
-		skb->sp->olen++;
+		sp->xvec[sp->len++] = x;
+		sp->olen++;
 
 		xo = xfrm_offload(skb);
 		if (!xo) {
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 6177e2171171..01a97f5dfa4e 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -68,11 +68,12 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 
 	xo = xfrm_offload(skb);
 	if (!xo || !(xo->flags & CRYPTO_DONE)) {
-		err = secpath_set(skb);
-		if (err)
+		struct sec_path *sp = secpath_set(skb);
+
+		if (!sp)
 			goto out;
 
-		if (skb->sp->len == XFRM_MAX_DEPTH)
+		if (sp->len == XFRM_MAX_DEPTH)
 			goto out;
 
 		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
@@ -81,8 +82,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 		if (!x)
 			goto out;
 
-		skb->sp->xvec[skb->sp->len++] = x;
-		skb->sp->olen++;
+		sp->xvec[sp->len++] = x;
+		sp->olen++;
 
 		xo = xfrm_offload(skb);
 		if (!xo) {
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 9ef490dddcea..97c69df1b329 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -86,14 +86,16 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
 {
 	struct net *net = dev_net(skb->dev);
 	struct xfrm_state *x = NULL;
+	struct sec_path *sp;
 	int i = 0;
 
-	if (secpath_set(skb)) {
+	sp = secpath_set(skb);
+	if (!sp) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR);
 		goto drop;
 	}
 
-	if (1 + skb->sp->len == XFRM_MAX_DEPTH) {
+	if (1 + sp->len == XFRM_MAX_DEPTH) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
 		goto drop;
 	}
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 684c0bc01e2c..bda929b9ff35 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -145,21 +145,22 @@ struct sec_path *secpath_dup(struct sec_path *src)
 }
 EXPORT_SYMBOL(secpath_dup);
 
-int secpath_set(struct sk_buff *skb)
+struct sec_path *secpath_set(struct sk_buff *skb)
 {
-	struct sec_path *sp;
+	struct sec_path *sp = skb->sp;
 
 	/* Allocate new secpath or COW existing one. */
-	if (!skb->sp || refcount_read(&skb->sp->refcnt) != 1) {
+	if (!sp || refcount_read(&sp->refcnt) != 1) {
 		sp = secpath_dup(skb->sp);
 		if (!sp)
-			return -ENOMEM;
+			return NULL;
 
 		if (skb->sp)
 			secpath_put(skb->sp);
 		skb->sp = sp;
 	}
-	return 0;
+
+	return sp;
 }
 EXPORT_SYMBOL(secpath_set);
 
@@ -236,6 +237,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 	bool xfrm_gro = false;
 	bool crypto_done = false;
 	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct sec_path *sp;
 
 	if (encap_type < 0) {
 		x = xfrm_input_state(skb);
@@ -312,8 +314,8 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		break;
 	}
 
-	err = secpath_set(skb);
-	if (err) {
+	sp = secpath_set(skb);
+	if (!sp) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR);
 		goto drop;
 	}
-- 
cgit v1.2.3


From 7af8f4ca314a592e2ba49cb5ea1de1325974998e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:19 +0100
Subject: net: move secpath_exist helper to sk_buff.h

Future patch will remove skb->sp pointer.
To reduce noise in those patches, move existing helper to
sk_buff and use it in more places to ease skb->sp replacement later.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h   | 13 ++++++++++---
 include/net/xfrm.h       |  9 ---------
 net/netfilter/nft_meta.c |  2 +-
 3 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2f42d2e99f17..70ac58240ec0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4066,12 +4066,19 @@ static inline void skb_init_secmark(struct sk_buff *skb)
 { }
 #endif
 
+static inline int secpath_exists(const struct sk_buff *skb)
+{
+#ifdef CONFIG_XFRM
+	return skb->sp != NULL;
+#else
+	return 0;
+#endif
+}
+
 static inline bool skb_irq_freeable(const struct sk_buff *skb)
 {
 	return !skb->destructor &&
-#if IS_ENABLED(CONFIG_XFRM)
-		!skb->sp &&
-#endif
+		!secpath_exists(skb) &&
 		!skb_nfct(skb) &&
 		!skb->_skb_refdst &&
 		!skb_has_frag_list(skb);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 62ca62177bc6..9cb506d09b98 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1104,15 +1104,6 @@ struct sec_path {
 	struct xfrm_offload	ovec[XFRM_MAX_OFFLOAD_DEPTH];
 };
 
-static inline int secpath_exists(struct sk_buff *skb)
-{
-#ifdef CONFIG_XFRM
-	return skb->sp != NULL;
-#else
-	return 0;
-#endif
-}
-
 static inline struct sec_path *
 secpath_get(struct sec_path *sp)
 {
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 6180626c3f80..6df486c5ebd3 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -229,7 +229,7 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 	}
 #ifdef CONFIG_XFRM
 	case NFT_META_SECPATH:
-		nft_reg_store8(dest, !!skb->sp);
+		nft_reg_store8(dest, secpath_exists(skb));
 		break;
 #endif
 #ifdef CONFIG_NF_TABLES_BRIDGE
-- 
cgit v1.2.3


From 2294be0f11e22b6197d025e5d3ab42888879ec4e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:20 +0100
Subject: net: use skb_sec_path helper in more places

skb_sec_path gains 'const' qualifier to avoid
xt_policy.c: 'skb_sec_path' discards 'const' qualifier from pointer target type

same reasoning as previous conversions: Won't need to touch these
spots anymore when skb->sp is removed.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    |  2 +-
 include/net/xfrm.h        |  6 ++++--
 net/ipv4/esp4.c           |  9 ++++++---
 net/ipv4/esp4_offload.c   |  4 +++-
 net/ipv6/esp6.c           |  9 ++++++---
 net/ipv6/esp6_offload.c   |  4 +++-
 net/ipv6/xfrm6_input.c    |  2 +-
 net/netfilter/nft_xfrm.c  |  2 +-
 net/netfilter/xt_policy.c |  2 +-
 net/xfrm/xfrm_device.c    |  4 +++-
 net/xfrm/xfrm_input.c     | 16 ++++++++++------
 net/xfrm/xfrm_policy.c    | 19 +++++++++++--------
 security/selinux/xfrm.c   |  4 ++--
 13 files changed, 52 insertions(+), 31 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 70ac58240ec0..d0f254a016bf 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4124,7 +4124,7 @@ static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb)
 	return skb->dst_pending_confirm != 0;
 }
 
-static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
+static inline struct sec_path *skb_sec_path(const struct sk_buff *skb)
 {
 #ifdef CONFIG_XFRM
 	return skb->sp;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 9cb506d09b98..af723448c972 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1896,14 +1896,16 @@ static inline void xfrm_states_delete(struct xfrm_state **states, int n)
 #ifdef CONFIG_XFRM
 static inline struct xfrm_state *xfrm_input_state(struct sk_buff *skb)
 {
-	return skb->sp->xvec[skb->sp->len - 1];
+	struct sec_path *sp = skb_sec_path(skb);
+
+	return sp->xvec[sp->len - 1];
 }
 #endif
 
 static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb)
 {
 #ifdef CONFIG_XFRM
-	struct sec_path *sp = skb->sp;
+	struct sec_path *sp = skb_sec_path(skb);
 
 	if (!sp || !sp->olen || sp->len != sp->olen)
 		return NULL;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 9e1c840596c5..5459f41fc26f 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -125,10 +125,13 @@ static void esp_output_done(struct crypto_async_request *base, int err)
 	void *tmp;
 	struct xfrm_state *x;
 
-	if (xo && (xo->flags & XFRM_DEV_RESUME))
-		x = skb->sp->xvec[skb->sp->len - 1];
-	else
+	if (xo && (xo->flags & XFRM_DEV_RESUME)) {
+		struct sec_path *sp = skb_sec_path(skb);
+
+		x = sp->xvec[sp->len - 1];
+	} else {
 		x = skb_dst(skb)->xfrm;
+	}
 
 	tmp = ESP_SKB_CB(skb)->tmp;
 	esp_ssg_unref(x, tmp);
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 19bd22aa05f9..8756e0e790d2 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -115,6 +115,7 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
 	struct crypto_aead *aead;
 	netdev_features_t esp_features = features;
 	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct sec_path *sp;
 
 	if (!xo)
 		return ERR_PTR(-EINVAL);
@@ -122,7 +123,8 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
 	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_ESP))
 		return ERR_PTR(-EINVAL);
 
-	x = skb->sp->xvec[skb->sp->len - 1];
+	sp = skb_sec_path(skb);
+	x = sp->xvec[sp->len - 1];
 	aead = x->data;
 	esph = ip_esp_hdr(skb);
 
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 63b2b66f9dfa..5afe9f83374d 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -145,10 +145,13 @@ static void esp_output_done(struct crypto_async_request *base, int err)
 	void *tmp;
 	struct xfrm_state *x;
 
-	if (xo && (xo->flags & XFRM_DEV_RESUME))
-		x = skb->sp->xvec[skb->sp->len - 1];
-	else
+	if (xo && (xo->flags & XFRM_DEV_RESUME)) {
+		struct sec_path *sp = skb_sec_path(skb);
+
+		x = sp->xvec[sp->len - 1];
+	} else {
 		x = skb_dst(skb)->xfrm;
+	}
 
 	tmp = ESP_SKB_CB(skb)->tmp;
 	esp_ssg_unref(x, tmp);
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 01a97f5dfa4e..d46b4eb645c2 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -142,6 +142,7 @@ static struct sk_buff *esp6_gso_segment(struct sk_buff *skb,
 	struct crypto_aead *aead;
 	netdev_features_t esp_features = features;
 	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct sec_path *sp;
 
 	if (!xo)
 		return ERR_PTR(-EINVAL);
@@ -149,7 +150,8 @@ static struct sk_buff *esp6_gso_segment(struct sk_buff *skb,
 	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_ESP))
 		return ERR_PTR(-EINVAL);
 
-	x = skb->sp->xvec[skb->sp->len - 1];
+	sp = skb_sec_path(skb);
+	x = sp->xvec[sp->len - 1];
 	aead = x->data;
 	esph = ip_esp_hdr(skb);
 
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 97c69df1b329..a52cb3fc6df5 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -147,7 +147,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
 		goto drop;
 	}
 
-	skb->sp->xvec[skb->sp->len++] = x;
+	sp->xvec[sp->len++] = x;
 
 	spin_lock(&x->lock);
 
diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c
index 5322609f7662..b08865ec5ed3 100644
--- a/net/netfilter/nft_xfrm.c
+++ b/net/netfilter/nft_xfrm.c
@@ -161,7 +161,7 @@ static void nft_xfrm_get_eval_in(const struct nft_xfrm *priv,
 				    struct nft_regs *regs,
 				    const struct nft_pktinfo *pkt)
 {
-	const struct sec_path *sp = pkt->skb->sp;
+	const struct sec_path *sp = skb_sec_path(pkt->skb);
 	const struct xfrm_state *state;
 
 	if (sp == NULL || sp->len <= priv->spnum) {
diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c
index 13f8ccf946d6..aa84e8121c93 100644
--- a/net/netfilter/xt_policy.c
+++ b/net/netfilter/xt_policy.c
@@ -56,7 +56,7 @@ match_policy_in(const struct sk_buff *skb, const struct xt_policy_info *info,
 		unsigned short family)
 {
 	const struct xt_policy_elem *e;
-	const struct sec_path *sp = skb->sp;
+	const struct sec_path *sp = skb_sec_path(skb);
 	int strict = info->flags & XT_POLICY_MATCH_STRICT;
 	int i, pos;
 
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 144c137886b1..b8736f56e7f7 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -32,6 +32,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 	struct softnet_data *sd;
 	netdev_features_t esp_features = features;
 	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct sec_path *sp;
 
 	if (!xo)
 		return skb;
@@ -39,7 +40,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 	if (!(features & NETIF_F_HW_ESP))
 		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
 
-	x = skb->sp->xvec[skb->sp->len - 1];
+	sp = skb_sec_path(skb);
+	x = sp->xvec[sp->len - 1];
 	if (xo->flags & XFRM_GRO || x->xso.flags & XFRM_OFFLOAD_INBOUND)
 		return skb;
 
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index bda929b9ff35..b4db25b244fa 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -330,7 +330,9 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 	daddr = (xfrm_address_t *)(skb_network_header(skb) +
 				   XFRM_SPI_SKB_CB(skb)->daddroff);
 	do {
-		if (skb->sp->len == XFRM_MAX_DEPTH) {
+		sp = skb_sec_path(skb);
+
+		if (sp->len == XFRM_MAX_DEPTH) {
 			secpath_reset(skb);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
 			goto drop;
@@ -346,7 +348,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		skb->mark = xfrm_smark_get(skb->mark, x);
 
-		skb->sp->xvec[skb->sp->len++] = x;
+		sp->xvec[sp->len++] = x;
 
 lock:
 		spin_lock(&x->lock);
@@ -470,8 +472,9 @@ resume:
 	nf_reset(skb);
 
 	if (decaps) {
-		if (skb->sp)
-			skb->sp->olen = 0;
+		sp = skb_sec_path(skb);
+		if (sp)
+			sp->olen = 0;
 		skb_dst_drop(skb);
 		gro_cells_receive(&gro_cells, skb);
 		return 0;
@@ -482,8 +485,9 @@ resume:
 
 		err = x->inner_mode->afinfo->transport_finish(skb, xfrm_gro || async);
 		if (xfrm_gro) {
-			if (skb->sp)
-				skb->sp->olen = 0;
+			sp = skb_sec_path(skb);
+			if (sp)
+				sp->olen = 0;
 			skb_dst_drop(skb);
 			gro_cells_receive(&gro_cells, skb);
 			return err;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index be04091eb7db..d6acba07bdc9 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3200,11 +3200,12 @@ EXPORT_SYMBOL(xfrm_lookup_route);
 static inline int
 xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl)
 {
+	struct sec_path *sp = skb_sec_path(skb);
 	struct xfrm_state *x;
 
-	if (!skb->sp || idx < 0 || idx >= skb->sp->len)
+	if (!sp || idx < 0 || idx >= sp->len)
 		return 0;
-	x = skb->sp->xvec[idx];
+	x = sp->xvec[idx];
 	if (!x->type->reject)
 		return 0;
 	return x->type->reject(x, skb, fl);
@@ -3304,6 +3305,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	struct flowi fl;
 	int xerr_idx = -1;
 	const struct xfrm_if_cb *ifcb;
+	struct sec_path *sp;
 	struct xfrm_if *xi;
 	u32 if_id = 0;
 
@@ -3328,11 +3330,12 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	nf_nat_decode_session(skb, &fl, family);
 
 	/* First, check used SA against their selectors. */
-	if (skb->sp) {
+	sp = skb_sec_path(skb);
+	if (sp) {
 		int i;
 
-		for (i = skb->sp->len-1; i >= 0; i--) {
-			struct xfrm_state *x = skb->sp->xvec[i];
+		for (i = sp->len - 1; i >= 0; i--) {
+			struct xfrm_state *x = sp->xvec[i];
 			if (!xfrm_selector_match(&x->sel, &fl, family)) {
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH);
 				return 0;
@@ -3359,7 +3362,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	}
 
 	if (!pol) {
-		if (skb->sp && secpath_has_nontransport(skb->sp, 0, &xerr_idx)) {
+		if (sp && secpath_has_nontransport(sp, 0, &xerr_idx)) {
 			xfrm_secpath_reject(xerr_idx, skb, &fl);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS);
 			return 0;
@@ -3388,7 +3391,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 #endif
 
 	if (pol->action == XFRM_POLICY_ALLOW) {
-		struct sec_path *sp;
 		static struct sec_path dummy;
 		struct xfrm_tmpl *tp[XFRM_MAX_DEPTH];
 		struct xfrm_tmpl *stp[XFRM_MAX_DEPTH];
@@ -3396,7 +3398,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		int ti = 0;
 		int i, k;
 
-		if ((sp = skb->sp) == NULL)
+		sp = skb_sec_path(skb);
+		if (!sp)
 			sp = &dummy;
 
 		for (pi = 0; pi < npols; pi++) {
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index 91dc3783ed94..bd7d18bdb147 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -230,7 +230,7 @@ static int selinux_xfrm_skb_sid_ingress(struct sk_buff *skb,
 					u32 *sid, int ckall)
 {
 	u32 sid_session = SECSID_NULL;
-	struct sec_path *sp = skb->sp;
+	struct sec_path *sp = skb_sec_path(skb);
 
 	if (sp) {
 		int i;
@@ -408,7 +408,7 @@ int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb,
 			      struct common_audit_data *ad)
 {
 	int i;
-	struct sec_path *sp = skb->sp;
+	struct sec_path *sp = skb_sec_path(skb);
 	u32 peer_sid = SECINITSID_UNLABELED;
 
 	if (sp) {
-- 
cgit v1.2.3


From 2fdb435bc0d7492b8137d4c9db6a465511154e29 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:21 +0100
Subject: drivers: net: intel: use secpath helpers in more places

Use skb_sec_path and secpath_exists helpers where possible.
This reduces noise in followup patch that removes skb->sp pointer.

v2: no changes, preseve acks from v1.

Acked-by: Shannon Nelson <shannon.lee.nelson@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c    | 6 ++++--
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c     | 5 +++--
 drivers/net/ethernet/intel/ixgbevf/ipsec.c        | 6 ++++--
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 +-
 4 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 4d77f42e035c..8befc7a50f8c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -1065,11 +1065,13 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring,
 	struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct xfrm_state *xs;
+	struct sec_path *sp;
 	struct tx_sa *tsa;
 
-	if (unlikely(!first->skb->sp->len)) {
+	sp = skb_sec_path(first->skb);
+	if (unlikely(!sp->len)) {
 		netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n",
-			   __func__, first->skb->sp->len);
+			   __func__, sp->len);
 		return 0;
 	}
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index f1e40734c975..2cd8c42d1403 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8695,7 +8695,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 #endif /* IXGBE_FCOE */
 
 #ifdef CONFIG_IXGBE_IPSEC
-	if (skb->sp && !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
+	if (secpath_exists(skb) &&
+	    !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
 		goto out_drop;
 #endif
 	tso = ixgbe_tso(tx_ring, first, &hdr_len, &ipsec_tx);
@@ -10192,7 +10193,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev,
 	 */
 	if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) {
 #ifdef CONFIG_IXGBE_IPSEC
-		if (!skb->sp)
+		if (!secpath_exists(skb))
 #endif
 			features &= ~NETIF_F_TSO;
 	}
diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
index e8a3231be0bf..07644e6bf498 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
@@ -450,12 +450,14 @@ int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring,
 	struct ixgbevf_adapter *adapter = netdev_priv(tx_ring->netdev);
 	struct ixgbevf_ipsec *ipsec = adapter->ipsec;
 	struct xfrm_state *xs;
+	struct sec_path *sp;
 	struct tx_sa *tsa;
 	u16 sa_idx;
 
-	if (unlikely(!first->skb->sp->len)) {
+	sp = skb_sec_path(first->skb);
+	if (unlikely(!sp->len)) {
 		netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n",
-			   __func__, first->skb->sp->len);
+			   __func__, sp->len);
 		return 0;
 	}
 
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 2de81f046fb5..49e23afa05a2 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4157,7 +4157,7 @@ static int ixgbevf_xmit_frame_ring(struct sk_buff *skb,
 	first->protocol = vlan_get_protocol(skb);
 
 #ifdef CONFIG_IXGBEVF_IPSEC
-	if (skb->sp && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx))
+	if (secpath_exists(skb) && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx))
 		goto out_drop;
 #endif
 	tso = ixgbevf_tso(tx_ring, first, &hdr_len, &ipsec_tx);
-- 
cgit v1.2.3


From 6362a6a04031cacc8ff54b65b84385d9fbab853d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:22 +0100
Subject: drivers: net: ethernet: mellanox: use skb_sec_path helper

Will avoid touching this when sp pointer is removed from sk_buff struct.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 128a82b1dbfc..f6717c287ff4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -254,11 +254,13 @@ struct sk_buff *mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
 	struct mlx5e_ipsec_metadata *mdata;
 	struct mlx5e_ipsec_sa_entry *sa_entry;
 	struct xfrm_state *x;
+	struct sec_path *sp;
 
 	if (!xo)
 		return skb;
 
-	if (unlikely(skb->sp->len != 1)) {
+	sp = skb_sec_path(skb);
+	if (unlikely(sp->len != 1)) {
 		atomic64_inc(&priv->ipsec->sw_stats.ipsec_tx_drop_bundle);
 		goto drop;
 	}
@@ -372,10 +374,11 @@ struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
 bool mlx5e_ipsec_feature_check(struct sk_buff *skb, struct net_device *netdev,
 			       netdev_features_t features)
 {
+	struct sec_path *sp = skb_sec_path(skb);
 	struct xfrm_state *x;
 
-	if (skb->sp && skb->sp->len) {
-		x = skb->sp->xvec[0];
+	if (sp && sp->len) {
+		x = sp->xvec[0];
 		if (x && x->xso.offload_handle)
 			return true;
 	}
-- 
cgit v1.2.3


From 56d1ac3260dadfc66c81ef2689bd1a09b05731a2 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:23 +0100
Subject: drivers: net: netdevsim: use skb_sec_path helper

... so this won't have to be changed when skb->sp goes away.

v2: no changes, preserve ack.

Acked-by: Shannon Nelson <shannon.lee.nelson@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/ipsec.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c
index 2dcf6cc269d0..76e11d889bb6 100644
--- a/drivers/net/netdevsim/ipsec.c
+++ b/drivers/net/netdevsim/ipsec.c
@@ -227,18 +227,19 @@ static const struct xfrmdev_ops nsim_xfrmdev_ops = {
 
 bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
 {
+	struct sec_path *sp = skb_sec_path(skb);
 	struct nsim_ipsec *ipsec = &ns->ipsec;
 	struct xfrm_state *xs;
 	struct nsim_sa *tsa;
 	u32 sa_idx;
 
 	/* do we even need to check this packet? */
-	if (!skb->sp)
+	if (!sp)
 		return true;
 
-	if (unlikely(!skb->sp->len)) {
+	if (unlikely(!sp->len)) {
 		netdev_err(ns->netdev, "no xfrm state len = %d\n",
-			   skb->sp->len);
+			   sp->len);
 		return false;
 	}
 
-- 
cgit v1.2.3


From 26912e3756d0a13b188142d1ba0ab279cd3b657a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:24 +0100
Subject: xfrm: use secpath_exist where applicable

Will reduce noise when skb->sp is removed later in this series.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h        | 2 +-
 net/xfrm/xfrm_interface.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index af723448c972..31220edcce95 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1185,7 +1185,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir,
 	if (sk && sk->sk_policy[XFRM_POLICY_IN])
 		return __xfrm_policy_check(sk, ndir, skb, family);
 
-	return	(!net->xfrm.policy_count[dir] && !skb->sp) ||
+	return	(!net->xfrm.policy_count[dir] && !secpath_exists(skb)) ||
 		(skb_dst(skb)->flags & DST_NOPOLICY) ||
 		__xfrm_policy_check(sk, ndir, skb, family);
 }
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index d679fa0f44b3..6be8c7df15bb 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -251,7 +251,7 @@ static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
 	struct xfrm_if *xi;
 	bool xnet;
 
-	if (err && !skb->sp)
+	if (err && !secpath_exists(skb))
 		return 0;
 
 	x = xfrm_input_state(skb);
-- 
cgit v1.2.3


From a053c866496d0c3647727f6a282a1db3afea3ed7 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:25 +0100
Subject: drivers: chelsio: use skb_sec_path helper

reduce noise when skb->sp is removed later in the series.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/crypto/chelsio/chcr_ipsec.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/crypto/chelsio/chcr_ipsec.c b/drivers/crypto/chelsio/chcr_ipsec.c
index 461b97e2f1fd..ceaa16b8f72e 100644
--- a/drivers/crypto/chelsio/chcr_ipsec.c
+++ b/drivers/crypto/chelsio/chcr_ipsec.c
@@ -570,6 +570,7 @@ int chcr_ipsec_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct sge_eth_txq *q;
 	struct port_info *pi;
 	dma_addr_t addr[MAX_SKB_FRAGS + 1];
+	struct sec_path *sp;
 	bool immediate = false;
 
 	if (!x->xso.offload_handle)
@@ -578,7 +579,8 @@ int chcr_ipsec_xmit(struct sk_buff *skb, struct net_device *dev)
 	sa_entry = (struct ipsec_sa_entry *)x->xso.offload_handle;
 	kctx_len = sa_entry->kctx_len;
 
-	if (skb->sp->len != 1) {
+	sp = skb_sec_path(skb);
+	if (sp->len != 1) {
 out_free:       dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
-- 
cgit v1.2.3


From a84e3f533324e40e4a99f50dee2188bf140d8098 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:26 +0100
Subject: xfrm: prefer secpath_set over secpath_dup

secpath_set is a wrapper for secpath_dup that will not perform
an allocation if the secpath attached to the skb has a reference count
of one, i.e., it doesn't need to be COW'ed.

Also, secpath_dup doesn't attach the secpath to the skb, it leaves
this to the caller.

Use secpath_set in places that immediately assign the return value to
skb.

This allows to remove skb->sp without touching these spots again.

secpath_dup can eventually be removed in followup patch.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c                |  9 +++++----
 drivers/net/ethernet/intel/ixgbevf/ipsec.c                    |  9 +++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 10 ++++++----
 net/xfrm/Kconfig                                              |  1 +
 net/xfrm/xfrm_output.c                                        |  7 ++-----
 5 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 8befc7a50f8c..ff85ce5791a3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -1161,6 +1161,7 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
 	struct xfrm_state *xs = NULL;
 	struct ipv6hdr *ip6 = NULL;
 	struct iphdr *ip4 = NULL;
+	struct sec_path *sp;
 	void *daddr;
 	__be32 spi;
 	u8 *c_hdr;
@@ -1200,12 +1201,12 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
 	if (unlikely(!xs))
 		return;
 
-	skb->sp = secpath_dup(skb->sp);
-	if (unlikely(!skb->sp))
+	sp = secpath_set(skb);
+	if (unlikely(!sp))
 		return;
 
-	skb->sp->xvec[skb->sp->len++] = xs;
-	skb->sp->olen++;
+	sp->xvec[sp->len++] = xs;
+	sp->olen++;
 	xo = xfrm_offload(skb);
 	xo->flags = CRYPTO_DONE;
 	xo->status = CRYPTO_SUCCESS;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
index 07644e6bf498..5170dd9d8705 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
@@ -548,6 +548,7 @@ void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring,
 	struct xfrm_state *xs = NULL;
 	struct ipv6hdr *ip6 = NULL;
 	struct iphdr *ip4 = NULL;
+	struct sec_path *sp;
 	void *daddr;
 	__be32 spi;
 	u8 *c_hdr;
@@ -587,12 +588,12 @@ void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring,
 	if (unlikely(!xs))
 		return;
 
-	skb->sp = secpath_dup(skb->sp);
-	if (unlikely(!skb->sp))
+	sp = secpath_set(skb);
+	if (unlikely(!sp))
 		return;
 
-	skb->sp->xvec[skb->sp->len++] = xs;
-	skb->sp->olen++;
+	sp->xvec[sp->len++] = xs;
+	sp->olen++;
 	xo = xfrm_offload(skb);
 	xo->flags = CRYPTO_DONE;
 	xo->status = CRYPTO_SUCCESS;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index f6717c287ff4..53608afd39b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -307,10 +307,11 @@ mlx5e_ipsec_build_sp(struct net_device *netdev, struct sk_buff *skb,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct xfrm_offload *xo;
 	struct xfrm_state *xs;
+	struct sec_path *sp;
 	u32 sa_handle;
 
-	skb->sp = secpath_dup(skb->sp);
-	if (unlikely(!skb->sp)) {
+	sp = secpath_set(skb);
+	if (unlikely(!sp)) {
 		atomic64_inc(&priv->ipsec->sw_stats.ipsec_rx_drop_sp_alloc);
 		return NULL;
 	}
@@ -322,8 +323,9 @@ mlx5e_ipsec_build_sp(struct net_device *netdev, struct sk_buff *skb,
 		return NULL;
 	}
 
-	skb->sp->xvec[skb->sp->len++] = xs;
-	skb->sp->olen++;
+	sp = skb_sec_path(skb);
+	sp->xvec[sp->len++] = xs;
+	sp->olen++;
 
 	xo = xfrm_offload(skb);
 	xo->flags = CRYPTO_DONE;
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index 140270a13d54..5d43aaa17027 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -5,6 +5,7 @@ config XFRM
        bool
        depends on NET
        select GRO_CELLS
+       select SKB_EXTENSIONS
 
 config XFRM_OFFLOAD
        bool
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 4ae87c5ce2e3..757c4d11983b 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -218,19 +218,16 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 	if (xfrm_dev_offload_ok(skb, x)) {
 		struct sec_path *sp;
 
-		sp = secpath_dup(skb->sp);
+		sp = secpath_set(skb);
 		if (!sp) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
 			kfree_skb(skb);
 			return -ENOMEM;
 		}
-		if (skb->sp)
-			secpath_put(skb->sp);
-		skb->sp = sp;
 		skb->encapsulation = 1;
 
 		sp->olen++;
-		sp->xvec[skb->sp->len++] = x;
+		sp->xvec[sp->len++] = x;
 		xfrm_state_hold(x);
 
 		if (skb_is_gso(skb)) {
-- 
cgit v1.2.3


From 4165079ba328dd47262a2183049d3591f0a750b1 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 17:15:27 +0100
Subject: net: switch secpath to use skb extension infrastructure

Remove skb->sp and allocate secpath storage via extension
infrastructure.  This also reduces sk_buff by 8 bytes on x86_64.

Total size of allyesconfig kernel is reduced slightly, as there is
less inlined code (one conditional atomic op instead of two on
skb_clone).

No differences in throughput in following ipsec performance tests:
- transport mode with aes on 10GB link
- tunnel mode between two network namespaces with aes and null cipher

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/xfrm_device.txt |  7 ++--
 include/linux/skbuff.h                   | 10 +++---
 include/net/xfrm.h                       | 22 +------------
 net/core/skbuff.c                        | 47 +++++++++++++++++++++++----
 net/xfrm/xfrm_input.c                    | 56 +++++---------------------------
 5 files changed, 59 insertions(+), 83 deletions(-)

diff --git a/Documentation/networking/xfrm_device.txt b/Documentation/networking/xfrm_device.txt
index 267f55b5f54a..a1c904dc70dc 100644
--- a/Documentation/networking/xfrm_device.txt
+++ b/Documentation/networking/xfrm_device.txt
@@ -111,9 +111,10 @@ the stack in xfrm_input().
 		xfrm_state_hold(xs);
 
 	store the state information into the skb
-		skb->sp = secpath_dup(skb->sp);
-		skb->sp->xvec[skb->sp->len++] = xs;
-		skb->sp->olen++;
+		sp = secpath_set(skb);
+		if (!sp) return;
+		sp->xvec[sp->len++] = xs;
+		sp->olen++;
 
 	indicate the success and/or error status of the offload
 		xo = xfrm_offload(skb);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d0f254a016bf..3f741b04e55d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -714,9 +714,6 @@ struct sk_buff {
 		struct list_head	tcp_tsorted_anchor;
 	};
 
-#ifdef CONFIG_XFRM
-	struct	sec_path	*sp;
-#endif
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	unsigned long		 _nfct;
 #endif
@@ -3907,6 +3904,9 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct)
 enum skb_ext_id {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	SKB_EXT_BRIDGE_NF,
+#endif
+#ifdef CONFIG_XFRM
+	SKB_EXT_SEC_PATH,
 #endif
 	SKB_EXT_NUM, /* must be last */
 };
@@ -4069,7 +4069,7 @@ static inline void skb_init_secmark(struct sk_buff *skb)
 static inline int secpath_exists(const struct sk_buff *skb)
 {
 #ifdef CONFIG_XFRM
-	return skb->sp != NULL;
+	return skb_ext_exist(skb, SKB_EXT_SEC_PATH);
 #else
 	return 0;
 #endif
@@ -4127,7 +4127,7 @@ static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb)
 static inline struct sec_path *skb_sec_path(const struct sk_buff *skb)
 {
 #ifdef CONFIG_XFRM
-	return skb->sp;
+	return skb_ext_find(skb, SKB_EXT_SEC_PATH);
 #else
 	return NULL;
 #endif
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 31220edcce95..38c232861a64 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1096,7 +1096,6 @@ struct xfrm_offload {
 };
 
 struct sec_path {
-	refcount_t		refcnt;
 	int			len;
 	int			olen;
 
@@ -1104,32 +1103,13 @@ struct sec_path {
 	struct xfrm_offload	ovec[XFRM_MAX_OFFLOAD_DEPTH];
 };
 
-static inline struct sec_path *
-secpath_get(struct sec_path *sp)
-{
-	if (sp)
-		refcount_inc(&sp->refcnt);
-	return sp;
-}
-
-void __secpath_destroy(struct sec_path *sp);
-
-static inline void
-secpath_put(struct sec_path *sp)
-{
-	if (sp && refcount_dec_and_test(&sp->refcnt))
-		__secpath_destroy(sp);
-}
-
-struct sec_path *secpath_dup(struct sec_path *src);
 struct sec_path *secpath_set(struct sk_buff *skb);
 
 static inline void
 secpath_reset(struct sk_buff *skb)
 {
 #ifdef CONFIG_XFRM
-	secpath_put(skb->sp);
-	skb->sp = NULL;
+	skb_ext_del(skb, SKB_EXT_SEC_PATH);
 #endif
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 0c65723591d7..cb0bf4215745 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -609,7 +609,6 @@ fastpath:
 void skb_release_head_state(struct sk_buff *skb)
 {
 	skb_dst_drop(skb);
-	secpath_reset(skb);
 	if (skb->destructor) {
 		WARN_ON(in_irq());
 		skb->destructor(skb);
@@ -798,9 +797,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	memcpy(new->cb, old->cb, sizeof(old->cb));
 	skb_dst_copy(new, old);
 	__skb_ext_copy(new, old);
-#ifdef CONFIG_XFRM
-	new->sp			= secpath_get(old->sp);
-#endif
 	__nf_copy(new, old, false);
 
 	/* Note : this field could be in headers_start/headers_end section
@@ -3912,6 +3908,9 @@ static const u8 skb_ext_type_len[] = {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	[SKB_EXT_BRIDGE_NF] = SKB_EXT_CHUNKSIZEOF(struct nf_bridge_info),
 #endif
+#ifdef CONFIG_XFRM
+	[SKB_EXT_SEC_PATH] = SKB_EXT_CHUNKSIZEOF(struct sec_path),
+#endif
 };
 
 static __always_inline unsigned int skb_ext_total_length(void)
@@ -3919,6 +3918,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
 	return SKB_EXT_CHUNKSIZEOF(struct skb_ext) +
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		skb_ext_type_len[SKB_EXT_BRIDGE_NF] +
+#endif
+#ifdef CONFIG_XFRM
+		skb_ext_type_len[SKB_EXT_SEC_PATH] +
 #endif
 		0;
 }
@@ -5610,7 +5612,8 @@ static struct skb_ext *skb_ext_alloc(void)
 	return new;
 }
 
-static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old)
+static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old,
+					 unsigned int old_active)
 {
 	struct skb_ext *new;
 
@@ -5624,6 +5627,15 @@ static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old)
 	memcpy(new, old, old->chunks * SKB_EXT_ALIGN_VALUE);
 	refcount_set(&new->refcnt, 1);
 
+#ifdef CONFIG_XFRM
+	if (old_active & (1 << SKB_EXT_SEC_PATH)) {
+		struct sec_path *sp = skb_ext_get_ptr(old, SKB_EXT_SEC_PATH);
+		unsigned int i;
+
+		for (i = 0; i < sp->len; i++)
+			xfrm_state_hold(sp->xvec[i]);
+	}
+#endif
 	__skb_ext_put(old);
 	return new;
 }
@@ -5650,7 +5662,7 @@ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id)
 	if (skb->active_extensions) {
 		old = skb->extensions;
 
-		new = skb_ext_maybe_cow(old);
+		new = skb_ext_maybe_cow(old, skb->active_extensions);
 		if (!new)
 			return NULL;
 
@@ -5679,6 +5691,16 @@ set_active:
 }
 EXPORT_SYMBOL(skb_ext_add);
 
+#ifdef CONFIG_XFRM
+static void skb_ext_put_sp(struct sec_path *sp)
+{
+	unsigned int i;
+
+	for (i = 0; i < sp->len; i++)
+		xfrm_state_put(sp->xvec[i]);
+}
+#endif
+
 void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id)
 {
 	struct skb_ext *ext = skb->extensions;
@@ -5687,6 +5709,14 @@ void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id)
 	if (skb->active_extensions == 0) {
 		skb->extensions = NULL;
 		__skb_ext_put(ext);
+#ifdef CONFIG_XFRM
+	} else if (id == SKB_EXT_SEC_PATH &&
+		   refcount_read(&ext->refcnt) == 1) {
+		struct sec_path *sp = skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH);
+
+		skb_ext_put_sp(sp);
+		sp->len = 0;
+#endif
 	}
 }
 EXPORT_SYMBOL(__skb_ext_del);
@@ -5702,6 +5732,11 @@ void __skb_ext_put(struct skb_ext *ext)
 	if (!refcount_dec_and_test(&ext->refcnt))
 		return;
 free_now:
+#ifdef CONFIG_XFRM
+	if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH))
+		skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH));
+#endif
+
 	kmem_cache_free(skbuff_ext_cache, ext);
 }
 EXPORT_SYMBOL(__skb_ext_put);
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index b4db25b244fa..6bc817359b58 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -38,8 +38,6 @@ struct xfrm_trans_cb {
 
 #define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0]))
 
-static struct kmem_cache *secpath_cachep __ro_after_init;
-
 static DEFINE_SPINLOCK(xfrm_input_afinfo_lock);
 static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[AF_INET6 + 1];
 
@@ -111,54 +109,21 @@ static int xfrm_rcv_cb(struct sk_buff *skb, unsigned int family, u8 protocol,
 	return ret;
 }
 
-void __secpath_destroy(struct sec_path *sp)
-{
-	int i;
-	for (i = 0; i < sp->len; i++)
-		xfrm_state_put(sp->xvec[i]);
-	kmem_cache_free(secpath_cachep, sp);
-}
-EXPORT_SYMBOL(__secpath_destroy);
-
-struct sec_path *secpath_dup(struct sec_path *src)
+struct sec_path *secpath_set(struct sk_buff *skb)
 {
-	struct sec_path *sp;
+	struct sec_path *sp, *tmp = skb_ext_find(skb, SKB_EXT_SEC_PATH);
 
-	sp = kmem_cache_alloc(secpath_cachep, GFP_ATOMIC);
+	sp = skb_ext_add(skb, SKB_EXT_SEC_PATH);
 	if (!sp)
 		return NULL;
 
-	sp->len = 0;
-	sp->olen = 0;
+	if (tmp) /* reused existing one (was COW'd if needed) */
+		return sp;
 
+	/* allocated new secpath */
 	memset(sp->ovec, 0, sizeof(sp->ovec));
-
-	if (src) {
-		int i;
-
-		memcpy(sp, src, sizeof(*sp));
-		for (i = 0; i < sp->len; i++)
-			xfrm_state_hold(sp->xvec[i]);
-	}
-	refcount_set(&sp->refcnt, 1);
-	return sp;
-}
-EXPORT_SYMBOL(secpath_dup);
-
-struct sec_path *secpath_set(struct sk_buff *skb)
-{
-	struct sec_path *sp = skb->sp;
-
-	/* Allocate new secpath or COW existing one. */
-	if (!sp || refcount_read(&sp->refcnt) != 1) {
-		sp = secpath_dup(skb->sp);
-		if (!sp)
-			return NULL;
-
-		if (skb->sp)
-			secpath_put(skb->sp);
-		skb->sp = sp;
-	}
+	sp->olen = 0;
+	sp->len = 0;
 
 	return sp;
 }
@@ -552,11 +517,6 @@ void __init xfrm_input_init(void)
 	if (err)
 		gro_cells.cells = NULL;
 
-	secpath_cachep = kmem_cache_create("secpath_cache",
-					   sizeof(struct sec_path),
-					   0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
-					   NULL);
-
 	for_each_possible_cpu(i) {
 		struct xfrm_trans_tasklet *trans;
 
-- 
cgit v1.2.3


From b4b9771bcbbd5839b0f77aba55e2f85989ed6779 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Wed, 19 Dec 2018 09:17:56 +0700
Subject: tipc: enable tracepoints in tipc

As for the sake of debugging/tracing, the commit enables tracepoints in
TIPC along with some general trace_events as shown below. It also
defines some 'tipc_*_dump()' functions that allow to dump TIPC object
data whenever needed, that is, for general debug purposes, ie. not just
for the trace_events.

The following trace_events are now available:

- trace_tipc_skb_dump(): allows to trace and dump TIPC msg & skb data,
  e.g. message type, user, droppable, skb truesize, cloned skb, etc.

- trace_tipc_list_dump(): allows to trace and dump any TIPC buffers or
  queues, e.g. TIPC link transmq, socket receive queue, etc.

- trace_tipc_sk_dump(): allows to trace and dump TIPC socket data, e.g.
  sk state, sk type, connection type, rmem_alloc, socket queues, etc.

- trace_tipc_link_dump(): allows to trace and dump TIPC link data, e.g.
  link state, silent_intv_cnt, gap, bc_gap, link queues, etc.

- trace_tipc_node_dump(): allows to trace and dump TIPC node data, e.g.
  node state, active links, capabilities, link entries, etc.

How to use:
Put the trace functions at any places where we want to dump TIPC data
or events.

Note:
a) The dump functions will generate raw data only, that is, to offload
the trace event's processing, it can require a tool or script to parse
the data but this should be simple.

b) The trace_tipc_*_dump() should be reserved for a failure cases only
(e.g. the retransmission failure case) or where we do not expect to
happen too often, then we can consider enabling these events by default
since they will almost not take any effects under normal conditions,
but once the rare condition or failure occurs, we get the dumped data
fully for post-analysis.

For other trace purposes, we can reuse these trace classes as template
but different events.

c) A trace_event is only effective when we enable it. To enable the
TIPC trace_events, echo 1 to 'enable' files in the events/tipc/
directory in the 'debugfs' file system. Normally, they are located at:

/sys/kernel/debug/tracing/events/tipc/

For example:

To enable the tipc_link_dump event:

echo 1 > /sys/kernel/debug/tracing/events/tipc/tipc_link_dump/enable

To enable all the TIPC trace_events:

echo 1 > /sys/kernel/debug/tracing/events/tipc/enable

To collect the trace data:

cat trace

or

cat trace_pipe > /trace.out &

To disable all the TIPC trace_events:

echo 0 > /sys/kernel/debug/tracing/events/tipc/enable

To clear the trace buffer:

echo > trace

d) Like the other trace_events, the feature like 'filter' or 'trigger'
is also usable for the tipc trace_events.
For more details, have a look at:

Documentation/trace/ftrace.txt

MAINTAINERS | add two new files 'trace.h' & 'trace.c' in tipc

Acked-by: Ying Xue <ying.xue@windriver.com>
Tested-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/Makefile |   4 +-
 net/tipc/bearer.c |   7 +-
 net/tipc/bearer.h |   2 +-
 net/tipc/link.c   | 120 ++++++++++++++++++++++++++++
 net/tipc/link.h   |   1 +
 net/tipc/node.c   |  63 +++++++++++++++
 net/tipc/node.h   |   1 +
 net/tipc/socket.c |  90 +++++++++++++++++++++
 net/tipc/socket.h |   2 +
 net/tipc/trace.c  | 200 ++++++++++++++++++++++++++++++++++++++++++++++
 net/tipc/trace.h  | 231 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 11 files changed, 716 insertions(+), 5 deletions(-)
 create mode 100644 net/tipc/trace.c
 create mode 100644 net/tipc/trace.h

diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index aca168f2abb1..c86aba0282af 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -9,7 +9,9 @@ tipc-y	+= addr.o bcast.o bearer.o \
 	   core.o link.o discover.o msg.o  \
 	   name_distr.o  subscr.o monitor.o name_table.o net.o  \
 	   netlink.o netlink_compat.o node.o socket.o eth_media.o \
-	   topsrv.o socket.o group.o
+	   topsrv.o socket.o group.o trace.o
+
+CFLAGS_trace.o += -I$(src)
 
 tipc-$(CONFIG_TIPC_MEDIA_UDP)	+= udp_media.o
 tipc-$(CONFIG_TIPC_MEDIA_IB)	+= ib_media.o
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index e65c3a8551e4..e32294f37c29 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -99,7 +99,7 @@ static struct tipc_media *media_find_id(u8 type)
 /**
  * tipc_media_addr_printf - record media address in print buffer
  */
-void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a)
+int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a)
 {
 	char addr_str[MAX_ADDR_STR];
 	struct tipc_media *m;
@@ -114,9 +114,10 @@ void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a)
 
 		ret = scnprintf(buf, len, "UNKNOWN(%u)", a->media_id);
 		for (i = 0; i < sizeof(a->value); i++)
-			ret += scnprintf(buf - ret, len + ret,
-					    "-%02x", a->value[i]);
+			ret += scnprintf(buf + ret, len - ret,
+					    "-%x", a->value[i]);
 	}
+	return ret;
 }
 
 /**
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 394290cbbb1d..7f4c569594a5 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -207,7 +207,7 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info);
 
 int tipc_media_set_priority(const char *name, u32 new_value);
 int tipc_media_set_window(const char *name, u32 new_value);
-void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a);
+int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a);
 int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
 			 struct nlattr *attrs[]);
 void tipc_disable_l2_media(struct tipc_bearer *b);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 9e265eb89726..668dab529021 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -43,6 +43,7 @@
 #include "discover.h"
 #include "netlink.h"
 #include "monitor.h"
+#include "trace.h"
 
 #include <linux/pkt_sched.h>
 
@@ -2222,3 +2223,122 @@ void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit)
 {
 	l->abort_limit = limit;
 }
+
+char *tipc_link_name_ext(struct tipc_link *l, char *buf)
+{
+	if (!l)
+		scnprintf(buf, TIPC_MAX_LINK_NAME, "null");
+	else if (link_is_bc_sndlink(l))
+		scnprintf(buf, TIPC_MAX_LINK_NAME, "broadcast-sender");
+	else if (link_is_bc_rcvlink(l))
+		scnprintf(buf, TIPC_MAX_LINK_NAME,
+			  "broadcast-receiver, peer %x", l->addr);
+	else
+		memcpy(buf, l->name, TIPC_MAX_LINK_NAME);
+
+	return buf;
+}
+
+/**
+ * tipc_link_dump - dump TIPC link data
+ * @l: tipc link to be dumped
+ * @dqueues: bitmask to decide if any link queue to be dumped?
+ *           - TIPC_DUMP_NONE: don't dump link queues
+ *           - TIPC_DUMP_TRANSMQ: dump link transmq queue
+ *           - TIPC_DUMP_BACKLOGQ: dump link backlog queue
+ *           - TIPC_DUMP_DEFERDQ: dump link deferd queue
+ *           - TIPC_DUMP_INPUTQ: dump link input queue
+ *           - TIPC_DUMP_WAKEUP: dump link wakeup queue
+ *           - TIPC_DUMP_ALL: dump all the link queues above
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf)
+{
+	int i = 0;
+	size_t sz = (dqueues) ? LINK_LMAX : LINK_LMIN;
+	struct sk_buff_head *list;
+	struct sk_buff *hskb, *tskb;
+	u32 len;
+
+	if (!l) {
+		i += scnprintf(buf, sz, "link data: (null)\n");
+		return i;
+	}
+
+	i += scnprintf(buf, sz, "link data: %x", l->addr);
+	i += scnprintf(buf + i, sz - i, " %x", l->state);
+	i += scnprintf(buf + i, sz - i, " %u", l->in_session);
+	i += scnprintf(buf + i, sz - i, " %u", l->session);
+	i += scnprintf(buf + i, sz - i, " %u", l->peer_session);
+	i += scnprintf(buf + i, sz - i, " %u", l->snd_nxt);
+	i += scnprintf(buf + i, sz - i, " %u", l->rcv_nxt);
+	i += scnprintf(buf + i, sz - i, " %u", l->snd_nxt_state);
+	i += scnprintf(buf + i, sz - i, " %u", l->rcv_nxt_state);
+	i += scnprintf(buf + i, sz - i, " %x", l->peer_caps);
+	i += scnprintf(buf + i, sz - i, " %u", l->silent_intv_cnt);
+	i += scnprintf(buf + i, sz - i, " %u", l->rst_cnt);
+	i += scnprintf(buf + i, sz - i, " %u", l->prev_from);
+	i += scnprintf(buf + i, sz - i, " %u", l->stale_cnt);
+	i += scnprintf(buf + i, sz - i, " %u", l->acked);
+
+	list = &l->transmq;
+	len = skb_queue_len(list);
+	hskb = skb_peek(list);
+	tskb = skb_peek_tail(list);
+	i += scnprintf(buf + i, sz - i, " | %u %u %u", len,
+		       (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+		       (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+	list = &l->deferdq;
+	len = skb_queue_len(list);
+	hskb = skb_peek(list);
+	tskb = skb_peek_tail(list);
+	i += scnprintf(buf + i, sz - i, " | %u %u %u", len,
+		       (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+		       (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+	list = &l->backlogq;
+	len = skb_queue_len(list);
+	hskb = skb_peek(list);
+	tskb = skb_peek_tail(list);
+	i += scnprintf(buf + i, sz - i, " | %u %u %u", len,
+		       (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+		       (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+	list = l->inputq;
+	len = skb_queue_len(list);
+	hskb = skb_peek(list);
+	tskb = skb_peek_tail(list);
+	i += scnprintf(buf + i, sz - i, " | %u %u %u\n", len,
+		       (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+		       (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+	if (dqueues & TIPC_DUMP_TRANSMQ) {
+		i += scnprintf(buf + i, sz - i, "transmq: ");
+		i += tipc_list_dump(&l->transmq, false, buf + i);
+	}
+	if (dqueues & TIPC_DUMP_BACKLOGQ) {
+		i += scnprintf(buf + i, sz - i,
+			       "backlogq: <%u %u %u %u %u>, ",
+			       l->backlog[TIPC_LOW_IMPORTANCE].len,
+			       l->backlog[TIPC_MEDIUM_IMPORTANCE].len,
+			       l->backlog[TIPC_HIGH_IMPORTANCE].len,
+			       l->backlog[TIPC_CRITICAL_IMPORTANCE].len,
+			       l->backlog[TIPC_SYSTEM_IMPORTANCE].len);
+		i += tipc_list_dump(&l->backlogq, false, buf + i);
+	}
+	if (dqueues & TIPC_DUMP_DEFERDQ) {
+		i += scnprintf(buf + i, sz - i, "deferdq: ");
+		i += tipc_list_dump(&l->deferdq, false, buf + i);
+	}
+	if (dqueues & TIPC_DUMP_INPUTQ) {
+		i += scnprintf(buf + i, sz - i, "inputq: ");
+		i += tipc_list_dump(l->inputq, false, buf + i);
+	}
+	if (dqueues & TIPC_DUMP_WAKEUP) {
+		i += scnprintf(buf + i, sz - i, "wakeup: ");
+		i += tipc_list_dump(&l->wakeupq, false, buf + i);
+	}
+
+	return i;
+}
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 90488c538a4e..e8f692598e4d 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -109,6 +109,7 @@ u16 tipc_link_rcv_nxt(struct tipc_link *l);
 u16 tipc_link_acked(struct tipc_link *l);
 u32 tipc_link_id(struct tipc_link *l);
 char *tipc_link_name(struct tipc_link *l);
+char *tipc_link_name_ext(struct tipc_link *l, char *buf);
 u32 tipc_link_state(struct tipc_link *l);
 char tipc_link_plane(struct tipc_link *l);
 int tipc_link_prio(struct tipc_link *l);
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 5980abb7839b..4fd6e2887818 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -43,6 +43,7 @@
 #include "monitor.h"
 #include "discover.h"
 #include "netlink.h"
+#include "trace.h"
 
 #define INVALID_NODE_SIG	0x10000
 #define NODE_CLEANUP_AFTER	300000
@@ -2435,3 +2436,65 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb,
 
 	return skb->len;
 }
+
+u32 tipc_node_get_addr(struct tipc_node *node)
+{
+	return (node) ? node->addr : 0;
+}
+
+/**
+ * tipc_node_dump - dump TIPC node data
+ * @n: tipc node to be dumped
+ * @more: dump more?
+ *        - false: dump only tipc node data
+ *        - true: dump node link data as well
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_node_dump(struct tipc_node *n, bool more, char *buf)
+{
+	int i = 0;
+	size_t sz = (more) ? NODE_LMAX : NODE_LMIN;
+
+	if (!n) {
+		i += scnprintf(buf, sz, "node data: (null)\n");
+		return i;
+	}
+
+	i += scnprintf(buf, sz, "node data: %x", n->addr);
+	i += scnprintf(buf + i, sz - i, " %x", n->state);
+	i += scnprintf(buf + i, sz - i, " %d", n->active_links[0]);
+	i += scnprintf(buf + i, sz - i, " %d", n->active_links[1]);
+	i += scnprintf(buf + i, sz - i, " %x", n->action_flags);
+	i += scnprintf(buf + i, sz - i, " %u", n->failover_sent);
+	i += scnprintf(buf + i, sz - i, " %u", n->sync_point);
+	i += scnprintf(buf + i, sz - i, " %d", n->link_cnt);
+	i += scnprintf(buf + i, sz - i, " %u", n->working_links);
+	i += scnprintf(buf + i, sz - i, " %x", n->capabilities);
+	i += scnprintf(buf + i, sz - i, " %lu\n", n->keepalive_intv);
+
+	if (!more)
+		return i;
+
+	i += scnprintf(buf + i, sz - i, "link_entry[0]:\n");
+	i += scnprintf(buf + i, sz - i, " mtu: %u\n", n->links[0].mtu);
+	i += scnprintf(buf + i, sz - i, " media: ");
+	i += tipc_media_addr_printf(buf + i, sz - i, &n->links[0].maddr);
+	i += scnprintf(buf + i, sz - i, "\n");
+	i += tipc_link_dump(n->links[0].link, TIPC_DUMP_NONE, buf + i);
+	i += scnprintf(buf + i, sz - i, " inputq: ");
+	i += tipc_list_dump(&n->links[0].inputq, false, buf + i);
+
+	i += scnprintf(buf + i, sz - i, "link_entry[1]:\n");
+	i += scnprintf(buf + i, sz - i, " mtu: %u\n", n->links[1].mtu);
+	i += scnprintf(buf + i, sz - i, " media: ");
+	i += tipc_media_addr_printf(buf + i, sz - i, &n->links[1].maddr);
+	i += scnprintf(buf + i, sz - i, "\n");
+	i += tipc_link_dump(n->links[1].link, TIPC_DUMP_NONE, buf + i);
+	i += scnprintf(buf + i, sz - i, " inputq: ");
+	i += tipc_list_dump(&n->links[1].inputq, false, buf + i);
+
+	i += scnprintf(buf + i, sz - i, "bclink:\n ");
+	i += tipc_link_dump(n->bc_entry.link, TIPC_DUMP_NONE, buf + i);
+
+	return i;
+}
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 03f5efb62cfb..4f59a30e989a 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -65,6 +65,7 @@ enum {
 
 void tipc_node_stop(struct net *net);
 bool tipc_node_get_id(struct net *net, u32 addr, u8 *id);
+u32 tipc_node_get_addr(struct tipc_node *node);
 u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr);
 void tipc_node_check_dest(struct net *net, u32 onode, u8 *peer_id128,
 			  struct tipc_bearer *bearer,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index b57b1be7252b..b6b2a94eb54e 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -46,6 +46,7 @@
 #include "bcast.h"
 #include "netlink.h"
 #include "group.h"
+#include "trace.h"
 
 #define CONN_TIMEOUT_DEFAULT    8000    /* default connect timeout = 8s */
 #define CONN_PROBING_INTV	msecs_to_jiffies(3600000)  /* [ms] => 1 h */
@@ -3564,3 +3565,92 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 	return skb->len;
 }
+
+u32 tipc_sock_get_portid(struct sock *sk)
+{
+	return (sk) ? (tipc_sk(sk))->portid : 0;
+}
+
+/**
+ * tipc_sk_dump - dump TIPC socket
+ * @sk: tipc sk to be dumped
+ * @dqueues: bitmask to decide if any socket queue to be dumped?
+ *           - TIPC_DUMP_NONE: don't dump socket queues
+ *           - TIPC_DUMP_SK_SNDQ: dump socket send queue
+ *           - TIPC_DUMP_SK_RCVQ: dump socket rcv queue
+ *           - TIPC_DUMP_SK_BKLGQ: dump socket backlog queue
+ *           - TIPC_DUMP_ALL: dump all the socket queues above
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf)
+{
+	int i = 0;
+	size_t sz = (dqueues) ? SK_LMAX : SK_LMIN;
+	struct tipc_sock *tsk;
+	struct publication *p;
+	bool tsk_connected;
+
+	if (!sk) {
+		i += scnprintf(buf, sz, "sk data: (null)\n");
+		return i;
+	}
+
+	tsk = tipc_sk(sk);
+	tsk_connected = !tipc_sk_type_connectionless(sk);
+
+	i += scnprintf(buf, sz, "sk data: %u", sk->sk_type);
+	i += scnprintf(buf + i, sz - i, " %d", sk->sk_state);
+	i += scnprintf(buf + i, sz - i, " %x", tsk_own_node(tsk));
+	i += scnprintf(buf + i, sz - i, " %u", tsk->portid);
+	i += scnprintf(buf + i, sz - i, " | %u", tsk_connected);
+	if (tsk_connected) {
+		i += scnprintf(buf + i, sz - i, " %x", tsk_peer_node(tsk));
+		i += scnprintf(buf + i, sz - i, " %u", tsk_peer_port(tsk));
+		i += scnprintf(buf + i, sz - i, " %u", tsk->conn_type);
+		i += scnprintf(buf + i, sz - i, " %u", tsk->conn_instance);
+	}
+	i += scnprintf(buf + i, sz - i, " | %u", tsk->published);
+	if (tsk->published) {
+		p = list_first_entry_or_null(&tsk->publications,
+					     struct publication, binding_sock);
+		i += scnprintf(buf + i, sz - i, " %u", (p) ? p->type : 0);
+		i += scnprintf(buf + i, sz - i, " %u", (p) ? p->lower : 0);
+		i += scnprintf(buf + i, sz - i, " %u", (p) ? p->upper : 0);
+	}
+	i += scnprintf(buf + i, sz - i, " | %u", tsk->snd_win);
+	i += scnprintf(buf + i, sz - i, " %u", tsk->rcv_win);
+	i += scnprintf(buf + i, sz - i, " %u", tsk->max_pkt);
+	i += scnprintf(buf + i, sz - i, " %x", tsk->peer_caps);
+	i += scnprintf(buf + i, sz - i, " %u", tsk->cong_link_cnt);
+	i += scnprintf(buf + i, sz - i, " %u", tsk->snt_unacked);
+	i += scnprintf(buf + i, sz - i, " %u", tsk->rcv_unacked);
+	i += scnprintf(buf + i, sz - i, " %u", atomic_read(&tsk->dupl_rcvcnt));
+	i += scnprintf(buf + i, sz - i, " %u", sk->sk_shutdown);
+	i += scnprintf(buf + i, sz - i, " | %d", sk_wmem_alloc_get(sk));
+	i += scnprintf(buf + i, sz - i, " %d", sk->sk_sndbuf);
+	i += scnprintf(buf + i, sz - i, " | %d", sk_rmem_alloc_get(sk));
+	i += scnprintf(buf + i, sz - i, " %d", sk->sk_rcvbuf);
+	i += scnprintf(buf + i, sz - i, " | %d\n", sk->sk_backlog.len);
+
+	if (dqueues & TIPC_DUMP_SK_SNDQ) {
+		i += scnprintf(buf + i, sz - i, "sk_write_queue: ");
+		i += tipc_list_dump(&sk->sk_write_queue, false, buf + i);
+	}
+
+	if (dqueues & TIPC_DUMP_SK_RCVQ) {
+		i += scnprintf(buf + i, sz - i, "sk_receive_queue: ");
+		i += tipc_list_dump(&sk->sk_receive_queue, false, buf + i);
+	}
+
+	if (dqueues & TIPC_DUMP_SK_BKLGQ) {
+		i += scnprintf(buf + i, sz - i, "sk_backlog:\n  head ");
+		i += tipc_skb_dump(sk->sk_backlog.head, false, buf + i);
+		if (sk->sk_backlog.tail != sk->sk_backlog.head) {
+			i += scnprintf(buf + i, sz - i, "  tail ");
+			i += tipc_skb_dump(sk->sk_backlog.tail, false,
+					   buf + i);
+		}
+	}
+
+	return i;
+}
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
index 5e575f205afe..07e36545b696 100644
--- a/net/tipc/socket.h
+++ b/net/tipc/socket.h
@@ -71,4 +71,6 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb,
 int tipc_dump_start(struct netlink_callback *cb);
 int __tipc_dump_start(struct netlink_callback *cb, struct net *net);
 int tipc_dump_done(struct netlink_callback *cb);
+u32 tipc_sock_get_portid(struct sock *sk);
+
 #endif
diff --git a/net/tipc/trace.c b/net/tipc/trace.c
new file mode 100644
index 000000000000..846196f0e810
--- /dev/null
+++ b/net/tipc/trace.c
@@ -0,0 +1,200 @@
+/*
+ * net/tipc/trace.c: TIPC tracepoints code
+ *
+ * Copyright (c) 2018, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "ASIS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
+/**
+ * tipc_skb_dump - dump TIPC skb data
+ * @skb: skb to be dumped
+ * @more: dump more?
+ *        - false: dump only tipc msg data
+ *        - true: dump kernel-related skb data and tipc cb[] array as well
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf)
+{
+	int i = 0;
+	size_t sz = (more) ? SKB_LMAX : SKB_LMIN;
+	struct tipc_msg *hdr;
+	struct tipc_skb_cb *skbcb;
+
+	if (!skb) {
+		i += scnprintf(buf, sz, "msg: (null)\n");
+		return i;
+	}
+
+	hdr = buf_msg(skb);
+	skbcb = TIPC_SKB_CB(skb);
+
+	/* tipc msg data section */
+	i += scnprintf(buf, sz, "msg: %u", msg_user(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_type(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_hdr_sz(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_data_sz(hdr));
+	i += scnprintf(buf + i, sz - i, " %x", msg_orignode(hdr));
+	i += scnprintf(buf + i, sz - i, " %x", msg_destnode(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_seqno(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_ack(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_bcast_ack(hdr));
+	switch (msg_user(hdr)) {
+	case LINK_PROTOCOL:
+		i += scnprintf(buf + i, sz - i, " %c", msg_net_plane(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_probe(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_peer_stopping(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_session(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_next_sent(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_seq_gap(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_bc_snd_nxt(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_bc_gap(hdr));
+		break;
+	case TIPC_LOW_IMPORTANCE:
+	case TIPC_MEDIUM_IMPORTANCE:
+	case TIPC_HIGH_IMPORTANCE:
+	case TIPC_CRITICAL_IMPORTANCE:
+	case CONN_MANAGER:
+	case SOCK_WAKEUP:
+		i += scnprintf(buf + i, sz - i, " | %u", msg_origport(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_destport(hdr));
+		switch (msg_type(hdr)) {
+		case TIPC_NAMED_MSG:
+			i += scnprintf(buf + i, sz - i, " %u",
+				       msg_nametype(hdr));
+			i += scnprintf(buf + i, sz - i, " %u",
+				       msg_nameinst(hdr));
+			break;
+		case TIPC_MCAST_MSG:
+			i += scnprintf(buf + i, sz - i, " %u",
+				       msg_nametype(hdr));
+			i += scnprintf(buf + i, sz - i, " %u",
+				       msg_namelower(hdr));
+			i += scnprintf(buf + i, sz - i, " %u",
+				       msg_nameupper(hdr));
+			break;
+		default:
+			break;
+		};
+		i += scnprintf(buf + i, sz - i, " | %u",
+			       msg_src_droppable(hdr));
+		i += scnprintf(buf + i, sz - i, " %u",
+			       msg_dest_droppable(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_errcode(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_reroute_cnt(hdr));
+		break;
+	default:
+		/* need more? */
+		break;
+	};
+
+	i += scnprintf(buf + i, sz - i, "\n");
+	if (!more)
+		return i;
+
+	/* kernel-related skb data section */
+	i += scnprintf(buf + i, sz - i, "skb: %s",
+		       (skb->dev) ? skb->dev->name : "n/a");
+	i += scnprintf(buf + i, sz - i, " %u", skb->len);
+	i += scnprintf(buf + i, sz - i, " %u", skb->data_len);
+	i += scnprintf(buf + i, sz - i, " %u", skb->hdr_len);
+	i += scnprintf(buf + i, sz - i, " %u", skb->truesize);
+	i += scnprintf(buf + i, sz - i, " %u", skb_cloned(skb));
+	i += scnprintf(buf + i, sz - i, " %p", skb->sk);
+	i += scnprintf(buf + i, sz - i, " %u", skb_shinfo(skb)->nr_frags);
+	i += scnprintf(buf + i, sz - i, " %llx",
+		       ktime_to_ms(skb_get_ktime(skb)));
+	i += scnprintf(buf + i, sz - i, " %llx\n",
+		       ktime_to_ms(skb_hwtstamps(skb)->hwtstamp));
+
+	/* tipc skb cb[] data section */
+	i += scnprintf(buf + i, sz - i, "cb[]: %u", skbcb->bytes_read);
+	i += scnprintf(buf + i, sz - i, " %u", skbcb->orig_member);
+	i += scnprintf(buf + i, sz - i, " %u",
+		       jiffies_to_msecs(skbcb->nxt_retr));
+	i += scnprintf(buf + i, sz - i, " %u", skbcb->validated);
+	i += scnprintf(buf + i, sz - i, " %u", skbcb->chain_imp);
+	i += scnprintf(buf + i, sz - i, " %u\n", skbcb->ackers);
+
+	return i;
+}
+
+/**
+ * tipc_list_dump - dump TIPC skb list/queue
+ * @list: list of skbs to be dumped
+ * @more: dump more?
+ *        - false: dump only the head & tail skbs
+ *        - true: dump the first & last 5 skbs
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_list_dump(struct sk_buff_head *list, bool more, char *buf)
+{
+	int i = 0;
+	size_t sz = (more) ? LIST_LMAX : LIST_LMIN;
+	u32 count, len;
+	struct sk_buff *hskb, *tskb, *skb, *tmp;
+
+	if (!list) {
+		i += scnprintf(buf, sz, "(null)\n");
+		return i;
+	}
+
+	len = skb_queue_len(list);
+	i += scnprintf(buf, sz, "len = %d\n", len);
+
+	if (!len)
+		return i;
+
+	if (!more) {
+		hskb = skb_peek(list);
+		i += scnprintf(buf + i, sz - i, "  head ");
+		i += tipc_skb_dump(hskb, false, buf + i);
+		if (len > 1) {
+			tskb = skb_peek_tail(list);
+			i += scnprintf(buf + i, sz - i, "  tail ");
+			i += tipc_skb_dump(tskb, false, buf + i);
+		}
+	} else {
+		count = 0;
+		skb_queue_walk_safe(list, skb, tmp) {
+			count++;
+			if (count == 6)
+				i += scnprintf(buf + i, sz - i, "  .\n  .\n");
+			if (count > 5 && count <= len - 5)
+				continue;
+			i += scnprintf(buf + i, sz - i, "  #%d ", count);
+			i += tipc_skb_dump(skb, false, buf + i);
+		}
+	}
+	return i;
+}
diff --git a/net/tipc/trace.h b/net/tipc/trace.h
new file mode 100644
index 000000000000..4c74927df685
--- /dev/null
+++ b/net/tipc/trace.h
@@ -0,0 +1,231 @@
+/*
+ * net/tipc/trace.h: TIPC tracepoints
+ *
+ * Copyright (c) 2018, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "ASIS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM tipc
+
+#if !defined(_TIPC_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TIPC_TRACE_H
+
+#include <linux/tracepoint.h>
+#include "core.h"
+#include "link.h"
+#include "socket.h"
+#include "node.h"
+
+#define SKB_LMIN	(100)
+#define SKB_LMAX	(SKB_LMIN * 2)
+#define LIST_LMIN	(SKB_LMIN * 3)
+#define LIST_LMAX	(SKB_LMIN * 11)
+#define SK_LMIN		(SKB_LMIN * 2)
+#define SK_LMAX		(SKB_LMIN * 11)
+#define LINK_LMIN	(SKB_LMIN)
+#define LINK_LMAX	(SKB_LMIN * 16)
+#define NODE_LMIN	(SKB_LMIN)
+#define NODE_LMAX	(SKB_LMIN * 11)
+
+#ifndef __TIPC_TRACE_ENUM
+#define __TIPC_TRACE_ENUM
+enum {
+	TIPC_DUMP_NONE		= 0,
+
+	TIPC_DUMP_TRANSMQ	= 1,
+	TIPC_DUMP_BACKLOGQ	= (1 << 1),
+	TIPC_DUMP_DEFERDQ	= (1 << 2),
+	TIPC_DUMP_INPUTQ	= (1 << 3),
+	TIPC_DUMP_WAKEUP        = (1 << 4),
+
+	TIPC_DUMP_SK_SNDQ	= (1 << 8),
+	TIPC_DUMP_SK_RCVQ	= (1 << 9),
+	TIPC_DUMP_SK_BKLGQ	= (1 << 10),
+	TIPC_DUMP_ALL		= 0xffffu
+};
+#endif
+
+int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf);
+int tipc_list_dump(struct sk_buff_head *list, bool more, char *buf);
+int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf);
+int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf);
+int tipc_node_dump(struct tipc_node *n, bool more, char *buf);
+
+DECLARE_EVENT_CLASS(tipc_skb_class,
+
+	TP_PROTO(struct sk_buff *skb, bool more, const char *header),
+
+	TP_ARGS(skb, more, header),
+
+	TP_STRUCT__entry(
+		__string(header, header)
+		__dynamic_array(char, buf, (more) ? SKB_LMAX : SKB_LMIN)
+	),
+
+	TP_fast_assign(
+		__assign_str(header, header);
+		tipc_skb_dump(skb, more, __get_str(buf));
+	),
+
+	TP_printk("%s\n%s", __get_str(header), __get_str(buf))
+)
+
+#define DEFINE_SKB_EVENT(name) \
+DEFINE_EVENT(tipc_skb_class, name, \
+	TP_PROTO(struct sk_buff *skb, bool more, const char *header), \
+	TP_ARGS(skb, more, header))
+DEFINE_SKB_EVENT(tipc_skb_dump);
+
+DECLARE_EVENT_CLASS(tipc_list_class,
+
+	TP_PROTO(struct sk_buff_head *list, bool more, const char *header),
+
+	TP_ARGS(list, more, header),
+
+	TP_STRUCT__entry(
+		__string(header, header)
+		__dynamic_array(char, buf, (more) ? LIST_LMAX : LIST_LMIN)
+	),
+
+	TP_fast_assign(
+		__assign_str(header, header);
+		tipc_list_dump(list, more, __get_str(buf));
+	),
+
+	TP_printk("%s\n%s", __get_str(header), __get_str(buf))
+);
+
+#define DEFINE_LIST_EVENT(name) \
+DEFINE_EVENT(tipc_list_class, name, \
+	TP_PROTO(struct sk_buff_head *list, bool more, const char *header), \
+	TP_ARGS(list, more, header))
+DEFINE_LIST_EVENT(tipc_list_dump);
+
+DECLARE_EVENT_CLASS(tipc_sk_class,
+
+	TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues,
+		 const char *header),
+
+	TP_ARGS(sk, skb, dqueues, header),
+
+	TP_STRUCT__entry(
+		__string(header, header)
+		__field(u32, portid)
+		__dynamic_array(char, buf, (dqueues) ? SK_LMAX : SK_LMIN)
+		__dynamic_array(char, skb_buf, (skb) ? SKB_LMIN : 1)
+	),
+
+	TP_fast_assign(
+		__assign_str(header, header);
+		__entry->portid = tipc_sock_get_portid(sk);
+		tipc_sk_dump(sk, dqueues, __get_str(buf));
+		if (skb)
+			tipc_skb_dump(skb, false, __get_str(skb_buf));
+		else
+			*(__get_str(skb_buf)) = '\0';
+	),
+
+	TP_printk("<%u> %s\n%s%s", __entry->portid, __get_str(header),
+		  __get_str(skb_buf), __get_str(buf))
+);
+
+#define DEFINE_SK_EVENT(name) \
+DEFINE_EVENT(tipc_sk_class, name, \
+	TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, \
+		 const char *header), \
+	TP_ARGS(sk, skb, dqueues, header))
+DEFINE_SK_EVENT(tipc_sk_dump);
+
+DECLARE_EVENT_CLASS(tipc_link_class,
+
+	TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header),
+
+	TP_ARGS(l, dqueues, header),
+
+	TP_STRUCT__entry(
+		__string(header, header)
+		__array(char, name, TIPC_MAX_LINK_NAME)
+		__dynamic_array(char, buf, (dqueues) ? LINK_LMAX : LINK_LMIN)
+	),
+
+	TP_fast_assign(
+		__assign_str(header, header);
+		tipc_link_name_ext(l, __entry->name);
+		tipc_link_dump(l, dqueues, __get_str(buf));
+	),
+
+	TP_printk("<%s> %s\n%s", __entry->name, __get_str(header),
+		  __get_str(buf))
+);
+
+#define DEFINE_LINK_EVENT(name) \
+DEFINE_EVENT(tipc_link_class, name, \
+	TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header), \
+	TP_ARGS(l, dqueues, header))
+DEFINE_LINK_EVENT(tipc_link_dump);
+
+DECLARE_EVENT_CLASS(tipc_node_class,
+
+	TP_PROTO(struct tipc_node *n, bool more, const char *header),
+
+	TP_ARGS(n, more, header),
+
+	TP_STRUCT__entry(
+		__string(header, header)
+		__field(u32, addr)
+		__dynamic_array(char, buf, (more) ? NODE_LMAX : NODE_LMIN)
+	),
+
+	TP_fast_assign(
+		__assign_str(header, header);
+		__entry->addr = tipc_node_get_addr(n);
+		tipc_node_dump(n, more, __get_str(buf));
+	),
+
+	TP_printk("<%x> %s\n%s", __entry->addr, __get_str(header),
+		  __get_str(buf))
+);
+
+#define DEFINE_NODE_EVENT(name) \
+DEFINE_EVENT(tipc_node_class, name, \
+	TP_PROTO(struct tipc_node *n, bool more, const char *header), \
+	TP_ARGS(n, more, header))
+DEFINE_NODE_EVENT(tipc_node_dump);
+
+#endif /* _TIPC_TRACE_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>
-- 
cgit v1.2.3


From 26574db0c17fb29fac8b57f94ed1dfd46cc89887 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Wed, 19 Dec 2018 09:17:57 +0700
Subject: tipc: add trace_events for tipc link

The commit adds the new trace_events for TIPC link object:

trace_tipc_link_timeout()
trace_tipc_link_fsm()
trace_tipc_link_reset()
trace_tipc_link_too_silent()
trace_tipc_link_retrans()
trace_tipc_link_bc_ack()
trace_tipc_link_conges()

And the traces for PROTOCOL messages at building and receiving:

trace_tipc_proto_build()
trace_tipc_proto_rcv()

Note:
a) The 'tipc_link_too_silent' event will only happen when the
'silent_intv_cnt' is about to reach the 'abort_limit' value (and the
event is enabled). The benefit for this kind of event is that we can
get an early indication about TIPC link loss issue due to timeout, then
can do some necessary actions for troubleshooting.

For example: To trigger the 'tipc_proto_rcv' when the 'too_silent'
event occurs:

echo 'enable_event:tipc:tipc_proto_rcv' > \
      events/tipc/tipc_link_too_silent/trigger

And disable it when TIPC link is reset:

echo 'disable_event:tipc:tipc_proto_rcv' > \
      events/tipc/tipc_link_reset/trigger

b) The 'tipc_link_retrans' or 'tipc_link_bc_ack' event is useful to
trace TIPC retransmission issues.

In addition, the commit adds the 'trace_tipc_list/link_dump()' at the
'retransmission failure' case. Then, if the issue occurs, the link
'transmq' along with the link data can be dumped for post-analysis.
These dump events should be enabled by default since it will only take
effect when the failure happens.

The same approach is also applied for the faulty case that the
validation of protocol message is failed.

Acked-by: Ying Xue <ying.xue@windriver.com>
Tested-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c  |  33 ++++++++++++++-
 net/tipc/link.h  |   1 +
 net/tipc/node.c  |   8 +++-
 net/tipc/trace.h | 124 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 164 insertions(+), 2 deletions(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 668dab529021..55c44d867d4b 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -357,9 +357,11 @@ void tipc_link_remove_bc_peer(struct tipc_link *snd_l,
 	rcv_l->bc_peer_is_up = true;
 	rcv_l->state = LINK_ESTABLISHED;
 	tipc_link_bc_ack_rcv(rcv_l, ack, xmitq);
+	trace_tipc_link_reset(rcv_l, TIPC_DUMP_ALL, "bclink removed!");
 	tipc_link_reset(rcv_l);
 	rcv_l->state = LINK_RESET;
 	if (!snd_l->ackers) {
+		trace_tipc_link_reset(snd_l, TIPC_DUMP_ALL, "zero ackers!");
 		tipc_link_reset(snd_l);
 		snd_l->state = LINK_RESET;
 		__skb_queue_purge(xmitq);
@@ -523,6 +525,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
 
 	l = *link;
 	strcpy(l->name, tipc_bclink_name);
+	trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!");
 	tipc_link_reset(l);
 	l->state = LINK_RESET;
 	l->ackers = 0;
@@ -547,6 +550,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
 int tipc_link_fsm_evt(struct tipc_link *l, int evt)
 {
 	int rc = 0;
+	int old_state = l->state;
 
 	switch (l->state) {
 	case LINK_RESETTING:
@@ -693,10 +697,12 @@ int tipc_link_fsm_evt(struct tipc_link *l, int evt)
 	default:
 		pr_err("Unknown FSM state %x in %s\n", l->state, l->name);
 	}
+	trace_tipc_link_fsm(l->name, old_state, l->state, evt);
 	return rc;
 illegal_evt:
 	pr_err("Illegal FSM event %x in state %x on link %s\n",
 	       evt, l->state, l->name);
+	trace_tipc_link_fsm(l->name, old_state, l->state, evt);
 	return rc;
 }
 
@@ -741,6 +747,18 @@ static void link_profile_stats(struct tipc_link *l)
 		l->stats.msg_length_profile[6]++;
 }
 
+/**
+ * tipc_link_too_silent - check if link is "too silent"
+ * @l: tipc link to be checked
+ *
+ * Returns true if the link 'silent_intv_cnt' is about to reach the
+ * 'abort_limit' value, otherwise false
+ */
+bool tipc_link_too_silent(struct tipc_link *l)
+{
+	return (l->silent_intv_cnt + 2 > l->abort_limit);
+}
+
 /* tipc_link_timeout - perform periodic task as instructed from node timeout
  */
 int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
@@ -754,6 +772,8 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
 	u16 bc_acked = l->bc_rcvlink->acked;
 	struct tipc_mon_state *mstate = &l->mon_state;
 
+	trace_tipc_link_timeout(l, TIPC_DUMP_NONE, " ");
+	trace_tipc_link_too_silent(l, TIPC_DUMP_ALL, " ");
 	switch (l->state) {
 	case LINK_ESTABLISHED:
 	case LINK_SYNCHING:
@@ -816,6 +836,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr)
 	TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr);
 	skb_queue_tail(&l->wakeupq, skb);
 	l->stats.link_congs++;
+	trace_tipc_link_conges(l, TIPC_DUMP_ALL, "wakeup scheduled!");
 	return -ELINKCONG;
 }
 
@@ -1037,6 +1058,7 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
 	if (less(to, from))
 		return 0;
 
+	trace_tipc_link_retrans(r, from, to, &l->transmq);
 	/* Detect repeated retransmit failures on same packet */
 	if (r->prev_from != from) {
 		r->prev_from = from;
@@ -1044,6 +1066,9 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
 		r->stale_cnt = 0;
 	} else if (++r->stale_cnt > 99 && time_after(jiffies, r->stale_limit)) {
 		link_retransmit_failure(l, skb);
+		trace_tipc_list_dump(&l->transmq, true, "retrans failure!");
+		trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!");
+		trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!");
 		if (link_is_bc_sndlink(l))
 			return TIPC_LINK_DOWN_EVT;
 		return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
@@ -1403,6 +1428,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 		l->stats.sent_nacks++;
 	skb->priority = TC_PRIO_CONTROL;
 	__skb_queue_tail(xmitq, skb);
+	trace_tipc_proto_build(skb, false, l->name);
 }
 
 void tipc_link_create_dummy_tnl_msg(struct tipc_link *l,
@@ -1566,6 +1592,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 	char *if_name;
 	int rc = 0;
 
+	trace_tipc_proto_rcv(skb, false, l->name);
 	if (tipc_link_is_blocked(l) || !xmitq)
 		goto exit;
 
@@ -1576,8 +1603,11 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 	hdr = buf_msg(skb);
 	data = msg_data(hdr);
 
-	if (!tipc_link_validate_msg(l, hdr))
+	if (!tipc_link_validate_msg(l, hdr)) {
+		trace_tipc_skb_dump(skb, false, "PROTO invalid (1)!");
+		trace_tipc_link_dump(l, TIPC_DUMP_NONE, "PROTO invalid (1)!");
 		goto exit;
+	}
 
 	switch (mtyp) {
 	case RESET_MSG:
@@ -1820,6 +1850,7 @@ void tipc_link_bc_ack_rcv(struct tipc_link *l, u16 acked,
 	if (!more(acked, l->acked))
 		return;
 
+	trace_tipc_link_bc_ack(l, l->acked, acked, &snd_l->transmq);
 	/* Skip over packets peer has already acked */
 	skb_queue_walk(&snd_l->transmq, skb) {
 		if (more(buf_seqno(skb), l->acked))
diff --git a/net/tipc/link.h b/net/tipc/link.h
index e8f692598e4d..8439e0ee53a8 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -148,4 +148,5 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l,   struct tipc_msg *hdr,
 			  struct sk_buff_head *xmitq);
 int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb,
 			  struct sk_buff_head *xmitq);
+bool tipc_link_too_silent(struct tipc_link *l);
 #endif
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 4fd6e2887818..1e13ea98b96c 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -784,6 +784,7 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
 		if (tipc_link_peer_is_down(l))
 			tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT);
 		tipc_node_fsm_evt(n, SELF_LOST_CONTACT_EVT);
+		trace_tipc_link_reset(l, TIPC_DUMP_ALL, "link down!");
 		tipc_link_fsm_evt(l, LINK_RESET_EVT);
 		tipc_link_reset(l);
 		tipc_link_build_reset_msg(l, xmitq);
@@ -801,6 +802,7 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
 	tipc_node_fsm_evt(n, NODE_SYNCH_END_EVT);
 	n->sync_point = tipc_link_rcv_nxt(tnl) + (U16_MAX / 2 - 1);
 	tipc_link_tnl_prepare(l, tnl, FAILOVER_MSG, xmitq);
+	trace_tipc_link_reset(l, TIPC_DUMP_ALL, "link down -> failover!");
 	tipc_link_reset(l);
 	tipc_link_fsm_evt(l, LINK_RESET_EVT);
 	tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);
@@ -1022,6 +1024,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
 			*respond = false;
 			goto exit;
 		}
+		trace_tipc_link_reset(l, TIPC_DUMP_ALL, "link created!");
 		tipc_link_reset(l);
 		tipc_link_fsm_evt(l, LINK_RESET_EVT);
 		if (n->state == NODE_FAILINGOVER)
@@ -1599,8 +1602,11 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
 		}
 	}
 
-	if (!tipc_link_validate_msg(l, hdr))
+	if (!tipc_link_validate_msg(l, hdr)) {
+		trace_tipc_skb_dump(skb, false, "PROTO invalid (2)!");
+		trace_tipc_link_dump(l, TIPC_DUMP_NONE, "PROTO invalid (2)!");
 		return false;
+	}
 
 	/* Check and update node accesibility if applicable */
 	if (state == SELF_UP_PEER_COMING) {
diff --git a/net/tipc/trace.h b/net/tipc/trace.h
index 4c74927df685..535c8958651f 100644
--- a/net/tipc/trace.h
+++ b/net/tipc/trace.h
@@ -74,6 +74,45 @@ enum {
 };
 #endif
 
+/* Link & Node FSM states: */
+#define state_sym(val)							  \
+	__print_symbolic(val,						  \
+			{(0xe),		"ESTABLISHED"			},\
+			{(0xe << 4),	"ESTABLISHING"			},\
+			{(0x1 << 8),	"RESET"				},\
+			{(0x2 << 12),	"RESETTING"			},\
+			{(0xd << 16),	"PEER_RESET"			},\
+			{(0xf << 20),	"FAILINGOVER"			},\
+			{(0xc << 24),	"SYNCHING"			},\
+			{(0xdd),	"SELF_DOWN_PEER_DOWN"		},\
+			{(0xaa),	"SELF_UP_PEER_UP"		},\
+			{(0xd1),	"SELF_DOWN_PEER_LEAVING"	},\
+			{(0xac),	"SELF_UP_PEER_COMING"		},\
+			{(0xca),	"SELF_COMING_PEER_UP"		},\
+			{(0x1d),	"SELF_LEAVING_PEER_DOWN"	},\
+			{(0xf0),	"FAILINGOVER"			},\
+			{(0xcc),	"SYNCHING"			})
+
+/* Link & Node FSM events: */
+#define evt_sym(val)							  \
+	__print_symbolic(val,						  \
+			{(0xec1ab1e),	"ESTABLISH_EVT"			},\
+			{(0x9eed0e),	"PEER_RESET_EVT"		},\
+			{(0xfa110e),	"FAILURE_EVT"			},\
+			{(0x10ca1d0e),	"RESET_EVT"			},\
+			{(0xfa110bee),	"FAILOVER_BEGIN_EVT"		},\
+			{(0xfa110ede),	"FAILOVER_END_EVT"		},\
+			{(0xc1ccbee),	"SYNCH_BEGIN_EVT"		},\
+			{(0xc1ccede),	"SYNCH_END_EVT"			},\
+			{(0xece),	"SELF_ESTABL_CONTACT_EVT"	},\
+			{(0x1ce),	"SELF_LOST_CONTACT_EVT"		},\
+			{(0x9ece),	"PEER_ESTABL_CONTACT_EVT"	},\
+			{(0x91ce),	"PEER_LOST_CONTACT_EVT"		},\
+			{(0xfbe),	"FAILOVER_BEGIN_EVT"		},\
+			{(0xfee),	"FAILOVER_END_EVT"		},\
+			{(0xcbe),	"SYNCH_BEGIN_EVT"		},\
+			{(0xcee),	"SYNCH_END_EVT"			})
+
 int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf);
 int tipc_list_dump(struct sk_buff_head *list, bool more, char *buf);
 int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf);
@@ -104,6 +143,8 @@ DEFINE_EVENT(tipc_skb_class, name, \
 	TP_PROTO(struct sk_buff *skb, bool more, const char *header), \
 	TP_ARGS(skb, more, header))
 DEFINE_SKB_EVENT(tipc_skb_dump);
+DEFINE_SKB_EVENT(tipc_proto_build);
+DEFINE_SKB_EVENT(tipc_proto_rcv);
 
 DECLARE_EVENT_CLASS(tipc_list_class,
 
@@ -192,6 +233,58 @@ DEFINE_EVENT(tipc_link_class, name, \
 	TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header), \
 	TP_ARGS(l, dqueues, header))
 DEFINE_LINK_EVENT(tipc_link_dump);
+DEFINE_LINK_EVENT(tipc_link_conges);
+DEFINE_LINK_EVENT(tipc_link_timeout);
+DEFINE_LINK_EVENT(tipc_link_reset);
+
+#define DEFINE_LINK_EVENT_COND(name, cond) \
+DEFINE_EVENT_CONDITION(tipc_link_class, name, \
+	TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header), \
+	TP_ARGS(l, dqueues, header), \
+	TP_CONDITION(cond))
+DEFINE_LINK_EVENT_COND(tipc_link_too_silent, tipc_link_too_silent(l));
+
+DECLARE_EVENT_CLASS(tipc_link_transmq_class,
+
+	TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq),
+
+	TP_ARGS(r, f, t, tq),
+
+	TP_STRUCT__entry(
+		__array(char, name, TIPC_MAX_LINK_NAME)
+		__field(u16, from)
+		__field(u16, to)
+		__field(u32, len)
+		__field(u16, fseqno)
+		__field(u16, lseqno)
+	),
+
+	TP_fast_assign(
+		tipc_link_name_ext(r, __entry->name);
+		__entry->from = f;
+		__entry->to = t;
+		__entry->len = skb_queue_len(tq);
+		__entry->fseqno = msg_seqno(buf_msg(skb_peek(tq)));
+		__entry->lseqno = msg_seqno(buf_msg(skb_peek_tail(tq)));
+	),
+
+	TP_printk("<%s> retrans req: [%u-%u] transmq: %u [%u-%u]\n",
+		  __entry->name, __entry->from, __entry->to,
+		  __entry->len, __entry->fseqno, __entry->lseqno)
+);
+
+DEFINE_EVENT(tipc_link_transmq_class, tipc_link_retrans,
+	TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq),
+	TP_ARGS(r, f, t, tq)
+);
+
+DEFINE_EVENT_PRINT(tipc_link_transmq_class, tipc_link_bc_ack,
+	TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq),
+	TP_ARGS(r, f, t, tq),
+	TP_printk("<%s> acked: [%u-%u] transmq: %u [%u-%u]\n",
+		  __entry->name, __entry->from, __entry->to,
+		  __entry->len, __entry->fseqno, __entry->lseqno)
+);
 
 DECLARE_EVENT_CLASS(tipc_node_class,
 
@@ -221,6 +314,37 @@ DEFINE_EVENT(tipc_node_class, name, \
 	TP_ARGS(n, more, header))
 DEFINE_NODE_EVENT(tipc_node_dump);
 
+DECLARE_EVENT_CLASS(tipc_fsm_class,
+
+	TP_PROTO(const char *name, u32 os, u32 ns, int evt),
+
+	TP_ARGS(name, os, ns, evt),
+
+	TP_STRUCT__entry(
+		__string(name, name)
+		__field(u32, os)
+		__field(u32, ns)
+		__field(u32, evt)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->os = os;
+		__entry->ns = ns;
+		__entry->evt = evt;
+	),
+
+	TP_printk("<%s> %s--(%s)->%s\n", __get_str(name),
+		  state_sym(__entry->os), evt_sym(__entry->evt),
+		  state_sym(__entry->ns))
+);
+
+#define DEFINE_FSM_EVENT(fsm_name) \
+DEFINE_EVENT(tipc_fsm_class, fsm_name, \
+	TP_PROTO(const char *name, u32 os, u32 ns, int evt), \
+	TP_ARGS(name, os, ns, evt))
+DEFINE_FSM_EVENT(tipc_link_fsm);
+
 #endif /* _TIPC_TRACE_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From 01e661ebfbad40e6280fb8ec25f2861d39ba4387 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Wed, 19 Dec 2018 09:17:58 +0700
Subject: tipc: add trace_events for tipc socket

The commit adds the new trace_events for TIPC socket object:

trace_tipc_sk_create()
trace_tipc_sk_poll()
trace_tipc_sk_sendmsg()
trace_tipc_sk_sendmcast()
trace_tipc_sk_sendstream()
trace_tipc_sk_filter_rcv()
trace_tipc_sk_advance_rx()
trace_tipc_sk_rej_msg()
trace_tipc_sk_drop_msg()
trace_tipc_sk_release()
trace_tipc_sk_shutdown()
trace_tipc_sk_overlimit1()
trace_tipc_sk_overlimit2()

Also, enables the traces for the following cases:
- When user creates a TIPC socket;
- When user calls poll() on TIPC socket;
- When user sends a dgram/mcast/stream message.
- When a message is put into the socket 'sk_receive_queue';
- When a message is released from the socket 'sk_receive_queue';
- When a message is rejected (e.g. due to no port, invalid, etc.);
- When a message is dropped (e.g. due to wrong message type);
- When socket is released;
- When socket is shutdown;
- When socket rcvq's allocation is overlimit (> 90%);
- When socket rcvq + bklq's allocation is overlimit (> 90%);
- When the 'TIPC_ERR_OVERLOAD/2' issue happens;

Note:
a) All the socket traces are designed to be able to trace on a specific
socket by either using the 'event filtering' feature on a known socket
'portid' value or the sysctl file:

/proc/sys/net/tipc/sk_filter

The file determines a 'tuple' for what socket should be traced:

(portid, sock type, name type, name lower, name upper)

where:
+ 'portid' is the socket portid generated at socket creating, can be
found in the trace outputs or the 'tipc socket list' command printouts;
+ 'sock type' is the socket type (1 = SOCK_TREAM, ...);
+ 'name type', 'name lower' and 'name upper' are the service name being
connected to or published by the socket.

Value '0' means 'ANY', the default tuple value is (0, 0, 0, 0, 0) i.e.
the traces happen for every sockets with no filter.

b) The 'tipc_sk_overlimit1/2' event is also a conditional trace_event
which happens when the socket receive queue (and backlog queue) is
about to be overloaded, when the queue allocation is > 90%. Then, when
the trace is enabled, the last skbs leading to the TIPC_ERR_OVERLOAD/2
issue can be traced.

The trace event is designed as an 'upper watermark' notification that
the other traces (e.g. 'tipc_sk_advance_rx' vs 'tipc_sk_filter_rcv') or
actions can be triggerred in the meanwhile to see what is going on with
the socket queue.

In addition, the 'trace_tipc_sk_dump()' is also placed at the
'TIPC_ERR_OVERLOAD/2' case, so the socket and last skb can be dumped
for post-analysis.

Acked-by: Ying Xue <ying.xue@windriver.com>
Tested-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 137 ++++++++++++++++++++++++++++++++++++++++++++++++++++--
 net/tipc/socket.h |   2 +
 net/tipc/sysctl.c |   8 ++++
 net/tipc/trace.c  |   6 +++
 net/tipc/trace.h  |  32 +++++++++++--
 5 files changed, 176 insertions(+), 9 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index b6b2a94eb54e..291d6bbe85f4 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -234,6 +234,7 @@ static u16 tsk_inc(struct tipc_sock *tsk, int msglen)
  */
 static void tsk_advance_rx_queue(struct sock *sk)
 {
+	trace_tipc_sk_advance_rx(sk, NULL, TIPC_DUMP_SK_RCVQ, " ");
 	kfree_skb(__skb_dequeue(&sk->sk_receive_queue));
 }
 
@@ -248,6 +249,7 @@ static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err)
 	if (!tipc_msg_reverse(onode, &skb, err))
 		return;
 
+	trace_tipc_sk_rej_msg(sk, skb, TIPC_DUMP_NONE, "@sk_respond!");
 	dnode = msg_destnode(buf_msg(skb));
 	selector = msg_origport(buf_msg(skb));
 	tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
@@ -483,6 +485,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 			tsk_set_unreliable(tsk, true);
 	}
 
+	trace_tipc_sk_create(sk, NULL, TIPC_DUMP_NONE, " ");
 	return 0;
 }
 
@@ -572,6 +575,7 @@ static int tipc_release(struct socket *sock)
 	tsk = tipc_sk(sk);
 	lock_sock(sk);
 
+	trace_tipc_sk_release(sk, NULL, TIPC_DUMP_ALL, " ");
 	__tipc_shutdown(sock, TIPC_ERR_NO_PORT);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 	tipc_sk_leave(tsk);
@@ -719,6 +723,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
 	__poll_t revents = 0;
 
 	sock_poll_wait(file, sock, wait);
+	trace_tipc_sk_poll(sk, NULL, TIPC_DUMP_ALL, " ");
 
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
@@ -805,9 +810,12 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 	rc = tipc_msg_build(hdr, msg, 0, dlen, mtu, &pkts);
 
 	/* Send message if build was successful */
-	if (unlikely(rc == dlen))
+	if (unlikely(rc == dlen)) {
+		trace_tipc_sk_sendmcast(sk, skb_peek(&pkts),
+					TIPC_DUMP_SK_SNDQ, " ");
 		rc = tipc_mcast_xmit(net, &pkts, method, &dsts,
 				     &tsk->cong_link_cnt);
+	}
 
 	tipc_nlist_purge(&dsts);
 
@@ -1209,8 +1217,10 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
 	bool conn_cong;
 
 	/* Ignore if connection cannot be validated: */
-	if (!tsk_peer_msg(tsk, hdr))
+	if (!tsk_peer_msg(tsk, hdr)) {
+		trace_tipc_sk_drop_msg(sk, skb, TIPC_DUMP_NONE, "@proto_rcv!");
 		goto exit;
+	}
 
 	if (unlikely(msg_errcode(hdr))) {
 		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
@@ -1378,6 +1388,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	if (unlikely(syn && !tipc_msg_skb_clone(&pkts, &sk->sk_write_queue)))
 		return -ENOMEM;
 
+	trace_tipc_sk_sendmsg(sk, skb_peek(&pkts), TIPC_DUMP_SK_SNDQ, " ");
 	rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
 	if (unlikely(rc == -ELINKCONG)) {
 		tipc_dest_push(clinks, dnode, 0);
@@ -1455,6 +1466,8 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
 		if (unlikely(rc != send))
 			break;
 
+		trace_tipc_sk_sendstream(sk, skb_peek(&pkts),
+					 TIPC_DUMP_SK_SNDQ, " ");
 		rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
 		if (unlikely(rc == -ELINKCONG)) {
 			tsk->cong_link_cnt = 1;
@@ -2129,6 +2142,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
 	struct sk_buff_head inputq;
 	int limit, err = TIPC_OK;
 
+	trace_tipc_sk_filter_rcv(sk, skb, TIPC_DUMP_ALL, " ");
 	TIPC_SKB_CB(skb)->bytes_read = 0;
 	__skb_queue_head_init(&inputq);
 	__skb_queue_tail(&inputq, skb);
@@ -2148,17 +2162,25 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
 		    (!grp && msg_in_group(hdr)))
 			err = TIPC_ERR_NO_PORT;
 		else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit) {
+			trace_tipc_sk_dump(sk, skb, TIPC_DUMP_ALL,
+					   "err_overload2!");
 			atomic_inc(&sk->sk_drops);
 			err = TIPC_ERR_OVERLOAD;
 		}
 
 		if (unlikely(err)) {
-			tipc_skb_reject(net, err, skb, xmitq);
+			if (tipc_msg_reverse(tipc_own_addr(net), &skb, err)) {
+				trace_tipc_sk_rej_msg(sk, skb, TIPC_DUMP_NONE,
+						      "@filter_rcv!");
+				__skb_queue_tail(xmitq, skb);
+			}
 			err = TIPC_OK;
 			continue;
 		}
 		__skb_queue_tail(&sk->sk_receive_queue, skb);
 		skb_set_owner_r(skb, sk);
+		trace_tipc_sk_overlimit2(sk, skb, TIPC_DUMP_ALL,
+					 "rcvq >90% allocated!");
 		sk->sk_data_ready(sk);
 	}
 }
@@ -2224,14 +2246,21 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
 		if (!sk->sk_backlog.len)
 			atomic_set(dcnt, 0);
 		lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt);
-		if (likely(!sk_add_backlog(sk, skb, lim)))
+		if (likely(!sk_add_backlog(sk, skb, lim))) {
+			trace_tipc_sk_overlimit1(sk, skb, TIPC_DUMP_ALL,
+						 "bklg & rcvq >90% allocated!");
 			continue;
+		}
 
+		trace_tipc_sk_dump(sk, skb, TIPC_DUMP_ALL, "err_overload!");
 		/* Overload => reject message back to sender */
 		onode = tipc_own_addr(sock_net(sk));
 		atomic_inc(&sk->sk_drops);
-		if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD))
+		if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD)) {
+			trace_tipc_sk_rej_msg(sk, skb, TIPC_DUMP_ALL,
+					      "@sk_enqueue!");
 			__skb_queue_tail(xmitq, skb);
+		}
 		break;
 	}
 }
@@ -2280,6 +2309,8 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
 		/* Prepare for message rejection */
 		if (!tipc_msg_reverse(tipc_own_addr(net), &skb, err))
 			continue;
+
+		trace_tipc_sk_rej_msg(NULL, skb, TIPC_DUMP_NONE, "@sk_rcv!");
 xmit:
 		dnode = msg_destnode(buf_msg(skb));
 		tipc_node_xmit_skb(net, skb, dnode, dport);
@@ -2553,6 +2584,7 @@ static int tipc_shutdown(struct socket *sock, int how)
 
 	lock_sock(sk);
 
+	trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " ");
 	__tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
 	sk->sk_shutdown = SEND_SHUTDOWN;
 
@@ -3566,11 +3598,106 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+/**
+ * tipc_sk_filtering - check if a socket should be traced
+ * @sk: the socket to be examined
+ * @sysctl_tipc_sk_filter[]: the socket tuple for filtering,
+ *  (portid, sock type, name type, name lower, name upper)
+ *
+ * Returns true if the socket meets the socket tuple data
+ * (value 0 = 'any') or when there is no tuple set (all = 0),
+ * otherwise false
+ */
+bool tipc_sk_filtering(struct sock *sk)
+{
+	struct tipc_sock *tsk;
+	struct publication *p;
+	u32 _port, _sktype, _type, _lower, _upper;
+	u32 type = 0, lower = 0, upper = 0;
+
+	if (!sk)
+		return true;
+
+	tsk = tipc_sk(sk);
+
+	_port = sysctl_tipc_sk_filter[0];
+	_sktype = sysctl_tipc_sk_filter[1];
+	_type = sysctl_tipc_sk_filter[2];
+	_lower = sysctl_tipc_sk_filter[3];
+	_upper = sysctl_tipc_sk_filter[4];
+
+	if (!_port && !_sktype && !_type && !_lower && !_upper)
+		return true;
+
+	if (_port)
+		return (_port == tsk->portid);
+
+	if (_sktype && _sktype != sk->sk_type)
+		return false;
+
+	if (tsk->published) {
+		p = list_first_entry_or_null(&tsk->publications,
+					     struct publication, binding_sock);
+		if (p) {
+			type = p->type;
+			lower = p->lower;
+			upper = p->upper;
+		}
+	}
+
+	if (!tipc_sk_type_connectionless(sk)) {
+		type = tsk->conn_type;
+		lower = tsk->conn_instance;
+		upper = tsk->conn_instance;
+	}
+
+	if ((_type && _type != type) || (_lower && _lower != lower) ||
+	    (_upper && _upper != upper))
+		return false;
+
+	return true;
+}
+
 u32 tipc_sock_get_portid(struct sock *sk)
 {
 	return (sk) ? (tipc_sk(sk))->portid : 0;
 }
 
+/**
+ * tipc_sk_overlimit1 - check if socket rx queue is about to be overloaded,
+ *			both the rcv and backlog queues are considered
+ * @sk: tipc sk to be checked
+ * @skb: tipc msg to be checked
+ *
+ * Returns true if the socket rx queue allocation is > 90%, otherwise false
+ */
+
+bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb)
+{
+	atomic_t *dcnt = &tipc_sk(sk)->dupl_rcvcnt;
+	unsigned int lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt);
+	unsigned int qsize = sk->sk_backlog.len + sk_rmem_alloc_get(sk);
+
+	return (qsize > lim * 90 / 100);
+}
+
+/**
+ * tipc_sk_overlimit2 - check if socket rx queue is about to be overloaded,
+ *			only the rcv queue is considered
+ * @sk: tipc sk to be checked
+ * @skb: tipc msg to be checked
+ *
+ * Returns true if the socket rx queue allocation is > 90%, otherwise false
+ */
+
+bool tipc_sk_overlimit2(struct sock *sk, struct sk_buff *skb)
+{
+	unsigned int lim = rcvbuf_limit(sk, skb);
+	unsigned int qsize = sk_rmem_alloc_get(sk);
+
+	return (qsize > lim * 90 / 100);
+}
+
 /**
  * tipc_sk_dump - dump TIPC socket
  * @sk: tipc sk to be dumped
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
index 07e36545b696..235b9679acee 100644
--- a/net/tipc/socket.h
+++ b/net/tipc/socket.h
@@ -72,5 +72,7 @@ int tipc_dump_start(struct netlink_callback *cb);
 int __tipc_dump_start(struct netlink_callback *cb, struct net *net);
 int tipc_dump_done(struct netlink_callback *cb);
 u32 tipc_sock_get_portid(struct sock *sk);
+bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb);
+bool tipc_sk_overlimit2(struct sock *sk, struct sk_buff *skb);
 
 #endif
diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c
index 1a779b1e8510..3481e4906bd6 100644
--- a/net/tipc/sysctl.c
+++ b/net/tipc/sysctl.c
@@ -34,6 +34,7 @@
  */
 
 #include "core.h"
+#include "trace.h"
 
 #include <linux/sysctl.h>
 
@@ -54,6 +55,13 @@ static struct ctl_table tipc_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname       = "sk_filter",
+		.data           = &sysctl_tipc_sk_filter,
+		.maxlen         = sizeof(sysctl_tipc_sk_filter),
+		.mode           = 0644,
+		.proc_handler   = proc_doulongvec_minmax,
+	},
 	{}
 };
 
diff --git a/net/tipc/trace.c b/net/tipc/trace.c
index 846196f0e810..964823841efe 100644
--- a/net/tipc/trace.c
+++ b/net/tipc/trace.c
@@ -36,6 +36,12 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
+/**
+ * socket tuples for filtering in socket traces:
+ * (portid, sock type, name type, name lower, name upper)
+ */
+unsigned long sysctl_tipc_sk_filter[5] __read_mostly = {0, };
+
 /**
  * tipc_skb_dump - dump TIPC skb data
  * @skb: skb to be dumped
diff --git a/net/tipc/trace.h b/net/tipc/trace.h
index 535c8958651f..ebbfcd14627e 100644
--- a/net/tipc/trace.h
+++ b/net/tipc/trace.h
@@ -113,11 +113,14 @@ enum {
 			{(0xcbe),	"SYNCH_BEGIN_EVT"		},\
 			{(0xcee),	"SYNCH_END_EVT"			})
 
+extern unsigned long sysctl_tipc_sk_filter[5] __read_mostly;
+
 int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf);
 int tipc_list_dump(struct sk_buff_head *list, bool more, char *buf);
 int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf);
 int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf);
 int tipc_node_dump(struct tipc_node *n, bool more, char *buf);
+bool tipc_sk_filtering(struct sock *sk);
 
 DECLARE_EVENT_CLASS(tipc_skb_class,
 
@@ -199,12 +202,33 @@ DECLARE_EVENT_CLASS(tipc_sk_class,
 		  __get_str(skb_buf), __get_str(buf))
 );
 
-#define DEFINE_SK_EVENT(name) \
-DEFINE_EVENT(tipc_sk_class, name, \
+#define DEFINE_SK_EVENT_FILTER(name) \
+DEFINE_EVENT_CONDITION(tipc_sk_class, name, \
+	TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, \
+		 const char *header), \
+	TP_ARGS(sk, skb, dqueues, header), \
+	TP_CONDITION(tipc_sk_filtering(sk)))
+DEFINE_SK_EVENT_FILTER(tipc_sk_dump);
+DEFINE_SK_EVENT_FILTER(tipc_sk_create);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendmcast);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendmsg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendstream);
+DEFINE_SK_EVENT_FILTER(tipc_sk_poll);
+DEFINE_SK_EVENT_FILTER(tipc_sk_filter_rcv);
+DEFINE_SK_EVENT_FILTER(tipc_sk_advance_rx);
+DEFINE_SK_EVENT_FILTER(tipc_sk_rej_msg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_drop_msg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_release);
+DEFINE_SK_EVENT_FILTER(tipc_sk_shutdown);
+
+#define DEFINE_SK_EVENT_FILTER_COND(name, cond) \
+DEFINE_EVENT_CONDITION(tipc_sk_class, name, \
 	TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, \
 		 const char *header), \
-	TP_ARGS(sk, skb, dqueues, header))
-DEFINE_SK_EVENT(tipc_sk_dump);
+	TP_ARGS(sk, skb, dqueues, header), \
+	TP_CONDITION(tipc_sk_filtering(sk) && (cond)))
+DEFINE_SK_EVENT_FILTER_COND(tipc_sk_overlimit1, tipc_sk_overlimit1(sk, skb));
+DEFINE_SK_EVENT_FILTER_COND(tipc_sk_overlimit2, tipc_sk_overlimit2(sk, skb));
 
 DECLARE_EVENT_CLASS(tipc_link_class,
 
-- 
cgit v1.2.3


From eb18a510b5cd4daeb9736ad8db57a9fc49db185b Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Wed, 19 Dec 2018 09:17:59 +0700
Subject: tipc: add trace_events for tipc node

The commit adds the new trace_events for TIPC node object:

trace_tipc_node_create()
trace_tipc_node_delete()
trace_tipc_node_lost_contact()
trace_tipc_node_timeout()
trace_tipc_node_link_up()
trace_tipc_node_link_down()
trace_tipc_node_reset_links()
trace_tipc_node_fsm_evt()
trace_tipc_node_check_state()

Also, enables the traces for the following cases:
- When a node is created/deleted;
- When a node contact is lost;
- When a node timer is timed out;
- When a node link is up/down;
- When all node links are reset;
- When node state is changed;
- When a skb comes and node state needs to be checked/updated.

Acked-by: Ying Xue <ying.xue@windriver.com>
Tested-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c  | 15 +++++++++++++++
 net/tipc/trace.h |  9 +++++++++
 2 files changed, 24 insertions(+)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 1e13ea98b96c..db2a6c3e0be9 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -433,6 +433,7 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr,
 			break;
 	}
 	list_add_tail_rcu(&n->list, &temp_node->list);
+	trace_tipc_node_create(n, true, " ");
 exit:
 	spin_unlock_bh(&tn->node_list_lock);
 	return n;
@@ -460,6 +461,7 @@ static void tipc_node_delete_from_list(struct tipc_node *node)
 
 static void tipc_node_delete(struct tipc_node *node)
 {
+	trace_tipc_node_delete(node, true, " ");
 	tipc_node_delete_from_list(node);
 
 	del_timer_sync(&node->timer);
@@ -617,6 +619,7 @@ static void tipc_node_timeout(struct timer_list *t)
 	int bearer_id;
 	int rc = 0;
 
+	trace_tipc_node_timeout(n, false, " ");
 	if (!node_is_up(n) && tipc_node_cleanup(n)) {
 		/*Removing the reference of Timer*/
 		tipc_node_put(n);
@@ -682,6 +685,7 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id,
 
 	pr_debug("Established link <%s> on network plane %c\n",
 		 tipc_link_name(nl), tipc_link_plane(nl));
+	trace_tipc_node_link_up(n, true, " ");
 
 	/* Ensure that a STATE message goes first */
 	tipc_link_build_state_msg(nl, xmitq);
@@ -835,6 +839,7 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
 		/* Defuse pending tipc_node_link_up() */
 		tipc_link_fsm_evt(l, LINK_RESET_EVT);
 	}
+	trace_tipc_node_link_down(n, true, "node link down or deleted!");
 	tipc_node_write_unlock(n);
 	if (delete)
 		tipc_mon_remove_peer(n->net, n->addr, old_bearer_id);
@@ -1064,6 +1069,7 @@ static void tipc_node_reset_links(struct tipc_node *n)
 
 	pr_warn("Resetting all links to %x\n", n->addr);
 
+	trace_tipc_node_reset_links(n, true, " ");
 	for (i = 0; i < MAX_BEARERS; i++) {
 		tipc_node_link_down(n, i, false);
 	}
@@ -1239,11 +1245,13 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt)
 		pr_err("Unknown node fsm state %x\n", state);
 		break;
 	}
+	trace_tipc_node_fsm(n->peer_id, n->state, state, evt);
 	n->state = state;
 	return;
 
 illegal_evt:
 	pr_err("Illegal node fsm evt %x in state %x\n", evt, state);
+	trace_tipc_node_fsm(n->peer_id, n->state, state, evt);
 }
 
 static void node_lost_contact(struct tipc_node *n,
@@ -1257,6 +1265,7 @@ static void node_lost_contact(struct tipc_node *n,
 
 	pr_debug("Lost contact with %x\n", n->addr);
 	n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER);
+	trace_tipc_node_lost_contact(n, true, " ");
 
 	/* Clean up broadcast state */
 	tipc_bcast_remove_peer(n->net, n->bc_entry.link);
@@ -1585,6 +1594,10 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
 	struct tipc_media_addr *maddr;
 	int pb_id;
 
+	if (trace_tipc_node_check_state_enabled()) {
+		trace_tipc_skb_dump(skb, false, "skb for node state check");
+		trace_tipc_node_check_state(n, true, " ");
+	}
 	l = n->links[bearer_id].link;
 	if (!l)
 		return false;
@@ -1636,6 +1649,8 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
 		syncpt = oseqno + exp_pkts - 1;
 		if (pl && tipc_link_is_up(pl)) {
 			__tipc_node_link_down(n, &pb_id, xmitq, &maddr);
+			trace_tipc_node_link_down(n, true,
+						  "node link down <- failover!");
 			tipc_skb_queue_splice_tail_init(tipc_link_inputq(pl),
 							tipc_link_inputq(l));
 		}
diff --git a/net/tipc/trace.h b/net/tipc/trace.h
index ebbfcd14627e..4d05141866aa 100644
--- a/net/tipc/trace.h
+++ b/net/tipc/trace.h
@@ -337,6 +337,14 @@ DEFINE_EVENT(tipc_node_class, name, \
 	TP_PROTO(struct tipc_node *n, bool more, const char *header), \
 	TP_ARGS(n, more, header))
 DEFINE_NODE_EVENT(tipc_node_dump);
+DEFINE_NODE_EVENT(tipc_node_create);
+DEFINE_NODE_EVENT(tipc_node_delete);
+DEFINE_NODE_EVENT(tipc_node_lost_contact);
+DEFINE_NODE_EVENT(tipc_node_timeout);
+DEFINE_NODE_EVENT(tipc_node_link_up);
+DEFINE_NODE_EVENT(tipc_node_link_down);
+DEFINE_NODE_EVENT(tipc_node_reset_links);
+DEFINE_NODE_EVENT(tipc_node_check_state);
 
 DECLARE_EVENT_CLASS(tipc_fsm_class,
 
@@ -368,6 +376,7 @@ DEFINE_EVENT(tipc_fsm_class, fsm_name, \
 	TP_PROTO(const char *name, u32 os, u32 ns, int evt), \
 	TP_ARGS(name, os, ns, evt))
 DEFINE_FSM_EVENT(tipc_link_fsm);
+DEFINE_FSM_EVENT(tipc_node_fsm);
 
 #endif /* _TIPC_TRACE_H */
 
-- 
cgit v1.2.3


From cf5f55f7f01397015dfa390256f2c20ceaabfcfb Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Wed, 19 Dec 2018 09:18:00 +0700
Subject: tipc: add trace_events for tipc bearer

The commit adds the new trace_event for TIPC bearer, L2 device event:

trace_tipc_l2_device_event()

Also, it puts the trace at the tipc_l2_device_event() function, then
the device/bearer events and related info can be traced out during
runtime when needed.

Acked-by: Ying Xue <ying.xue@windriver.com>
Tested-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/bearer.c |  2 ++
 net/tipc/trace.h  | 43 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)

diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index e32294f37c29..fb2c0d8f359f 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -43,6 +43,7 @@
 #include "bcast.h"
 #include "netlink.h"
 #include "udp_media.h"
+#include "trace.h"
 
 #define MAX_ADDR_STR 60
 
@@ -608,6 +609,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
 	if (!b)
 		return NOTIFY_DONE;
 
+	trace_tipc_l2_device_event(dev, b, evt);
 	switch (evt) {
 	case NETDEV_CHANGE:
 		if (netif_carrier_ok(dev) && netif_oper_up(dev)) {
diff --git a/net/tipc/trace.h b/net/tipc/trace.h
index 4d05141866aa..4d8e00483afc 100644
--- a/net/tipc/trace.h
+++ b/net/tipc/trace.h
@@ -113,6 +113,17 @@ enum {
 			{(0xcbe),	"SYNCH_BEGIN_EVT"		},\
 			{(0xcee),	"SYNCH_END_EVT"			})
 
+/* Bearer, net device events: */
+#define dev_evt_sym(val)						  \
+	__print_symbolic(val,						  \
+			{(NETDEV_CHANGE),	"NETDEV_CHANGE"		},\
+			{(NETDEV_GOING_DOWN),	"NETDEV_GOING_DOWN"	},\
+			{(NETDEV_UP),		"NETDEV_UP"		},\
+			{(NETDEV_CHANGEMTU),	"NETDEV_CHANGEMTU"	},\
+			{(NETDEV_CHANGEADDR),	"NETDEV_CHANGEADDR"	},\
+			{(NETDEV_UNREGISTER),	"NETDEV_UNREGISTER"	},\
+			{(NETDEV_CHANGENAME),	"NETDEV_CHANGENAME"	})
+
 extern unsigned long sysctl_tipc_sk_filter[5] __read_mostly;
 
 int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf);
@@ -378,6 +389,38 @@ DEFINE_EVENT(tipc_fsm_class, fsm_name, \
 DEFINE_FSM_EVENT(tipc_link_fsm);
 DEFINE_FSM_EVENT(tipc_node_fsm);
 
+TRACE_EVENT(tipc_l2_device_event,
+
+	TP_PROTO(struct net_device *dev, struct tipc_bearer *b,
+		 unsigned long evt),
+
+	TP_ARGS(dev, b, evt),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev->name)
+		__string(b_name, b->name)
+		__field(unsigned long, evt)
+		__field(u8, b_up)
+		__field(u8, carrier)
+		__field(u8, oper)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev->name);
+		__assign_str(b_name, b->name);
+		__entry->evt = evt;
+		__entry->b_up = test_bit(0, &b->up);
+		__entry->carrier = netif_carrier_ok(dev);
+		__entry->oper = netif_oper_up(dev);
+	),
+
+	TP_printk("%s on: <%s>/<%s> oper: %s carrier: %s bearer: %s\n",
+		  dev_evt_sym(__entry->evt), __get_str(dev_name),
+		  __get_str(b_name), (__entry->oper) ? "up" : "down",
+		  (__entry->carrier) ? "ok" : "notok",
+		  (__entry->b_up) ? "up" : "down")
+);
+
 #endif /* _TIPC_TRACE_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From 055722716c396ac1c7fd36a828250a78db1f22bc Mon Sep 17 00:00:00 2001
From: Hoang Le <hoang.h.le@dektech.com.au>
Date: Wed, 19 Dec 2018 11:42:19 +0700
Subject: tipc: fix uninitialized value for broadcast retransmission

When sending broadcast message on high load system, there are a lot of
unnecessary packets restranmission. That issue was caused by missing in
initial criteria for retransmission.

To prevent this happen, just initialize this criteria for retransmission
in next 10 milliseconds.

Fixes: 31c4f4cc32f7 ("tipc: improve broadcast retransmission algorithm")
Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Hoang Le <hoang.h.le@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 55c44d867d4b..2792a3cae682 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -967,6 +967,10 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 			}
 			__skb_dequeue(list);
 			__skb_queue_tail(transmq, skb);
+			/* next retransmit attempt */
+			if (link_is_bc_sndlink(l))
+				TIPC_SKB_CB(skb)->nxt_retr =
+					jiffies + TIPC_BC_RETR_LIM;
 			__skb_queue_tail(xmitq, _skb);
 			TIPC_SKB_CB(skb)->ackers = l->ackers;
 			l->rcv_unacked = 0;
@@ -1014,6 +1018,10 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
 		hdr = buf_msg(skb);
 		l->backlog[msg_importance(hdr)].len--;
 		__skb_queue_tail(&l->transmq, skb);
+		/* next retransmit attempt */
+		if (link_is_bc_sndlink(l))
+			TIPC_SKB_CB(skb)->nxt_retr = jiffies + TIPC_BC_RETR_LIM;
+
 		__skb_queue_tail(xmitq, _skb);
 		TIPC_SKB_CB(skb)->ackers = l->ackers;
 		msg_set_seqno(hdr, seqno);
-- 
cgit v1.2.3


From 927d0ef10a1071fba491b4858267fbb87ff19ed1 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 19 Dec 2018 06:08:37 +0000
Subject: mlxsw: spectrum: Sanitize VLAN interface's uppers

Currently, only VRF and macvlan uppers are supported on top of VLAN
device configured over a bridge, so make sure the driver forbids other
uppers.

Note that enslavement to a VRF is handled earlier in the notification
block, so there is no need to check for a VRF upper here.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 45 ++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index eb8db9fae237..891cf099fdd5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -5156,6 +5156,48 @@ static int mlxsw_sp_netdevice_lag_port_vlan_event(struct net_device *vlan_dev,
 	return 0;
 }
 
+static int mlxsw_sp_netdevice_bridge_vlan_event(struct net_device *vlan_dev,
+						struct net_device *br_dev,
+						unsigned long event, void *ptr,
+						u16 vid)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct netlink_ext_ack *extack;
+	struct net_device *upper_dev;
+
+	if (!mlxsw_sp)
+		return 0;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+
+	switch (event) {
+	case NETDEV_PRECHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (!netif_is_macvlan(upper_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
+			return -EOPNOTSUPP;
+		}
+		if (!info->linking)
+			break;
+		if (netif_is_macvlan(upper_dev) &&
+		    !mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+			return -EOPNOTSUPP;
+		}
+		break;
+	case NETDEV_CHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (info->linking)
+			break;
+		if (netif_is_macvlan(upper_dev))
+			mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
+		break;
+	}
+
+	return 0;
+}
+
 static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 					 unsigned long event, void *ptr)
 {
@@ -5169,6 +5211,9 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 		return mlxsw_sp_netdevice_lag_port_vlan_event(vlan_dev,
 							      real_dev, event,
 							      ptr, vid);
+	else if (netif_is_bridge_master(real_dev))
+		return mlxsw_sp_netdevice_bridge_vlan_event(vlan_dev, real_dev,
+							    event, ptr, vid);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 32fd4b49a372bee72aab82ebf8e866fc3756896c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 19 Dec 2018 06:08:38 +0000
Subject: mlxsw: spectrum_router: Do not destroy RIFs based on FID's reference
 count

Currently, when a RIF is constructed on top of a FID, the RIF increments
the FID's reference count and the RIF is destroyed when the FID's
reference count drops to 1. This effectively means that when no local
ports are member in the FID, the FID is destroyed regardless if the
router port is a member in the FID or not.

The above can lead to the unexpected behavior in which routes using a
VLAN interface as their nexthop device are no longer offloaded after the
last local port leaves the corresponding VLAN (FID).

Example:
# ip -4 route show dev br0.10
192.0.2.0/24 proto kernel scope link src 192.0.2.1 offload
# bridge vlan del vid 10 dev swp3
# ip -4 route show dev br0.10
192.0.2.0/24 proto kernel scope link src 192.0.2.1

After the patch, the route is offloaded before and after the VLAN is
removed from local port 'swp3', as the RIF corresponding to 'br0.10'
continues to exists.

In order to remove RIFs' reliance on the underlying FID's reference
count, we need to add a reference count to sub-port RIFs, which are RIFs
that correspond to physical ports and their uppers (e.g., LAG devices).

In this case, each {Port, VID} ('struct mlxsw_sp_port_vlan') needs to
hold a reference on the RIF. For example:

                       bond0.10
                          |
                        bond0
                          |
                      +-------+
                      |       |
                    swp1    swp2

Both {Port 1, VID 10} and {Port 2, VID 10} will hold a reference on the
RIF corresponding to 'bond0.10'. When the last reference is dropped, the
RIF will be destroyed.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c | 29 ++++-----
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 70 +++++++++++++++-------
 3 files changed, 65 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 64cae57bfbc8..92faae006480 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -484,7 +484,6 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp,
 				 struct netdev_notifier_info *info);
 void
 mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
-void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp,
 				 struct net_device *dev);
 struct mlxsw_sp_rif *mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
@@ -789,6 +788,7 @@ enum mlxsw_sp_rif_type mlxsw_sp_fid_rif_type(const struct mlxsw_sp_fid *fid);
 u16 mlxsw_sp_fid_index(const struct mlxsw_sp_fid *fid);
 enum mlxsw_sp_fid_type mlxsw_sp_fid_type(const struct mlxsw_sp_fid *fid);
 void mlxsw_sp_fid_rif_set(struct mlxsw_sp_fid *fid, struct mlxsw_sp_rif *rif);
+struct mlxsw_sp_rif *mlxsw_sp_fid_rif(const struct mlxsw_sp_fid *fid);
 enum mlxsw_sp_rif_type
 mlxsw_sp_fid_type_rif_type(const struct mlxsw_sp *mlxsw_sp,
 			   enum mlxsw_sp_fid_type type);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index 7adb1494ebba..ee3b8db5d9e0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -369,6 +369,11 @@ void mlxsw_sp_fid_rif_set(struct mlxsw_sp_fid *fid, struct mlxsw_sp_rif *rif)
 	fid->rif = rif;
 }
 
+struct mlxsw_sp_rif *mlxsw_sp_fid_rif(const struct mlxsw_sp_fid *fid)
+{
+	return fid->rif;
+}
+
 enum mlxsw_sp_rif_type
 mlxsw_sp_fid_type_rif_type(const struct mlxsw_sp *mlxsw_sp,
 			   enum mlxsw_sp_fid_type type)
@@ -1083,20 +1088,16 @@ void mlxsw_sp_fid_put(struct mlxsw_sp_fid *fid)
 	struct mlxsw_sp_fid_family *fid_family = fid->fid_family;
 	struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp;
 
-	if (--fid->ref_count == 1 && fid->rif) {
-		/* Destroy the associated RIF and let it drop the last
-		 * reference on the FID.
-		 */
-		return mlxsw_sp_rif_destroy(fid->rif);
-	} else if (fid->ref_count == 0) {
-		list_del(&fid->list);
-		rhashtable_remove_fast(&mlxsw_sp->fid_core->fid_ht,
-				       &fid->ht_node, mlxsw_sp_fid_ht_params);
-		fid->fid_family->ops->deconfigure(fid);
-		__clear_bit(fid->fid_index - fid_family->start_index,
-			    fid_family->fids_bitmap);
-		kfree(fid);
-	}
+	if (--fid->ref_count != 0)
+		return;
+
+	list_del(&fid->list);
+	rhashtable_remove_fast(&mlxsw_sp->fid_core->fid_ht,
+			       &fid->ht_node, mlxsw_sp_fid_ht_params);
+	fid->fid_family->ops->deconfigure(fid);
+	__clear_bit(fid->fid_index - fid_family->start_index,
+		    fid_family->fids_bitmap);
+	kfree(fid);
 }
 
 struct mlxsw_sp_fid *mlxsw_sp_fid_8021q_get(struct mlxsw_sp *mlxsw_sp, u16 vid)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index b33ba8b66861..8a0011a610d6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -15,6 +15,7 @@
 #include <linux/gcd.h>
 #include <linux/random.h>
 #include <linux/if_macvlan.h>
+#include <linux/refcount.h>
 #include <net/netevent.h>
 #include <net/neighbour.h>
 #include <net/arp.h>
@@ -104,6 +105,7 @@ struct mlxsw_sp_rif_params {
 
 struct mlxsw_sp_rif_subport {
 	struct mlxsw_sp_rif common;
+	refcount_t ref_count;
 	union {
 		u16 system_port;
 		u16 lag_id;
@@ -136,6 +138,7 @@ struct mlxsw_sp_rif_ops {
 	void (*fdb_del)(struct mlxsw_sp_rif *rif, const char *mac);
 };
 
+static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree);
 static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_lpm_tree *lpm_tree);
@@ -6343,7 +6346,7 @@ err_rif_index_alloc:
 	return ERR_PTR(err);
 }
 
-void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
+static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 {
 	const struct mlxsw_sp_rif_ops *ops = rif->ops;
 	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
@@ -6392,6 +6395,40 @@ mlxsw_sp_rif_subport_params_init(struct mlxsw_sp_rif_params *params,
 		params->system_port = mlxsw_sp_port->local_port;
 }
 
+static struct mlxsw_sp_rif_subport *
+mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
+{
+	return container_of(rif, struct mlxsw_sp_rif_subport, common);
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_subport_get(struct mlxsw_sp *mlxsw_sp,
+			 const struct mlxsw_sp_rif_params *params,
+			 struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_rif_subport *rif_subport;
+	struct mlxsw_sp_rif *rif;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, params->dev);
+	if (!rif)
+		return mlxsw_sp_rif_create(mlxsw_sp, params, extack);
+
+	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	refcount_inc(&rif_subport->ref_count);
+	return rif;
+}
+
+static void mlxsw_sp_rif_subport_put(struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_rif_subport *rif_subport;
+
+	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	if (!refcount_dec_and_test(&rif_subport->ref_count))
+		return;
+
+	mlxsw_sp_rif_destroy(rif);
+}
+
 static int
 mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 			       struct net_device *l3_dev,
@@ -6399,22 +6436,18 @@ mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_rif_params params = {
+		.dev = l3_dev,
+	};
 	u16 vid = mlxsw_sp_port_vlan->vid;
 	struct mlxsw_sp_rif *rif;
 	struct mlxsw_sp_fid *fid;
 	int err;
 
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
-	if (!rif) {
-		struct mlxsw_sp_rif_params params = {
-			.dev = l3_dev,
-		};
-
-		mlxsw_sp_rif_subport_params_init(&params, mlxsw_sp_port_vlan);
-		rif = mlxsw_sp_rif_create(mlxsw_sp, &params, extack);
-		if (IS_ERR(rif))
-			return PTR_ERR(rif);
-	}
+	mlxsw_sp_rif_subport_params_init(&params, mlxsw_sp_port_vlan);
+	rif = mlxsw_sp_rif_subport_get(mlxsw_sp, &params, extack);
+	if (IS_ERR(rif))
+		return PTR_ERR(rif);
 
 	/* FID was already created, just take a reference */
 	fid = rif->ops->fid_get(rif, extack);
@@ -6441,6 +6474,7 @@ err_port_vid_learning_set:
 	mlxsw_sp_fid_port_vid_unmap(fid, mlxsw_sp_port, vid);
 err_fid_port_vid_map:
 	mlxsw_sp_fid_put(fid);
+	mlxsw_sp_rif_subport_put(rif);
 	return err;
 }
 
@@ -6449,6 +6483,7 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp_fid *fid = mlxsw_sp_port_vlan->fid;
+	struct mlxsw_sp_rif *rif = mlxsw_sp_fid_rif(fid);
 	u16 vid = mlxsw_sp_port_vlan->vid;
 
 	if (WARN_ON(mlxsw_sp_fid_type(fid) != MLXSW_SP_FID_TYPE_RFID))
@@ -6458,10 +6493,8 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 	mlxsw_sp_port_vid_stp_set(mlxsw_sp_port, vid, BR_STATE_BLOCKING);
 	mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true);
 	mlxsw_sp_fid_port_vid_unmap(fid, mlxsw_sp_port, vid);
-	/* If router port holds the last reference on the rFID, then the
-	 * associated Sub-port RIF will be destroyed.
-	 */
 	mlxsw_sp_fid_put(fid);
+	mlxsw_sp_rif_subport_put(rif);
 }
 
 static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev,
@@ -7064,18 +7097,13 @@ static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif)
 					     __mlxsw_sp_rif_macvlan_flush, rif);
 }
 
-static struct mlxsw_sp_rif_subport *
-mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
-{
-	return container_of(rif, struct mlxsw_sp_rif_subport, common);
-}
-
 static void mlxsw_sp_rif_subport_setup(struct mlxsw_sp_rif *rif,
 				       const struct mlxsw_sp_rif_params *params)
 {
 	struct mlxsw_sp_rif_subport *rif_subport;
 
 	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	refcount_set(&rif_subport->ref_count, 1);
 	rif_subport->vid = params->vid;
 	rif_subport->lag = params->lag;
 	if (params->lag)
-- 
cgit v1.2.3


From f1d7c33d6ab585aba831a73a322070eb89724072 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 19 Dec 2018 06:08:40 +0000
Subject: mlxsw: spectrum_fid: Remove unused function

This function is no longer used. Remove it.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     | 1 -
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c | 5 -----
 2 files changed, 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 92faae006480..9b7ba4c3d334 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -784,7 +784,6 @@ int mlxsw_sp_fid_port_vid_map(struct mlxsw_sp_fid *fid,
 			      struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
 void mlxsw_sp_fid_port_vid_unmap(struct mlxsw_sp_fid *fid,
 				 struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
-enum mlxsw_sp_rif_type mlxsw_sp_fid_rif_type(const struct mlxsw_sp_fid *fid);
 u16 mlxsw_sp_fid_index(const struct mlxsw_sp_fid *fid);
 enum mlxsw_sp_fid_type mlxsw_sp_fid_type(const struct mlxsw_sp_fid *fid);
 void mlxsw_sp_fid_rif_set(struct mlxsw_sp_fid *fid, struct mlxsw_sp_rif *rif);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index ee3b8db5d9e0..055cc6943b34 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -349,11 +349,6 @@ void mlxsw_sp_fid_port_vid_unmap(struct mlxsw_sp_fid *fid,
 	fid->fid_family->ops->port_vid_unmap(fid, mlxsw_sp_port, vid);
 }
 
-enum mlxsw_sp_rif_type mlxsw_sp_fid_rif_type(const struct mlxsw_sp_fid *fid)
-{
-	return fid->fid_family->rif_type;
-}
-
 u16 mlxsw_sp_fid_index(const struct mlxsw_sp_fid *fid)
 {
 	return fid->fid_index;
-- 
cgit v1.2.3


From e149113a74c35f0a28d1bfe17d2505a03563c1d5 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 19 Dec 2018 06:08:41 +0000
Subject: mlxsw: spectrum: Handle VLAN device unlinking

In commit 993107fea5ee ("mlxsw: spectrum_switchdev: Fix VLAN device
deletion via ioctl") I fixed a bug caused by the fact that the driver
views differently the deletion of a VLAN device when it is deleted via
an ioctl and netlink.

Instead of relying on a specific order of events (device being
unregistered vs. VLAN filter being updated), simply make sure that the
driver performs the necessary cleanup when the VLAN device is unlinked,
which always happens before the other two events.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 891cf099fdd5..3b5d0850278f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -5000,6 +5000,16 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 		} else if (netif_is_macvlan(upper_dev)) {
 			if (!info->linking)
 				mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
+		} else if (is_vlan_dev(upper_dev)) {
+			struct net_device *br_dev;
+
+			if (!netif_is_bridge_port(upper_dev))
+				break;
+			if (info->linking)
+				break;
+			br_dev = netdev_master_upper_dev_get(upper_dev);
+			mlxsw_sp_port_bridge_leave(mlxsw_sp_port, upper_dev,
+						   br_dev);
 		}
 		break;
 	}
-- 
cgit v1.2.3


From 635c8c8bba670db6b3b03890d4e24fc4b745aed7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 19 Dec 2018 06:08:43 +0000
Subject: mlxsw: spectrum: Remove reference count from VLAN entries

Commit b3529af6bb0d ("spectrum: Reference count VLAN entries") started
reference counting port-VLAN entries in a similar fashion to the 8021q
driver.

However, this is not actually needed and only complicates things.
Instead, the driver should forbid the creation of a VLAN on a port if
this VLAN already exists. This would also solve the issue fixed by the
mentioned commit.

Therefore, remove the get()/put() API and use create()/destroy()
instead.

One place that needs special attention is VLAN addition in a VLAN-aware
bridge via switchdev operations. In case the VLAN flags (e.g., 'pvid')
are toggled, then the VLAN entry already exists. To prevent the driver
from wrongly returning EEXIST, the driver is changed to check in the
prepare phase whether the entry already exists and only returns an error
in case it is not associated with the correct bridge port.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 58 +++++++---------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  5 +-
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 41 +++++++++------
 3 files changed, 46 insertions(+), 58 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3b5d0850278f..7777528f67fb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1141,16 +1141,20 @@ static void mlxsw_sp_port_vlan_flush(struct mlxsw_sp_port *mlxsw_sp_port)
 
 	list_for_each_entry_safe(mlxsw_sp_port_vlan, tmp,
 				 &mlxsw_sp_port->vlans_list, list)
-		mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+		mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 }
 
-static struct mlxsw_sp_port_vlan *
+struct mlxsw_sp_port_vlan *
 mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 {
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 	bool untagged = vid == 1;
 	int err;
 
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
+	if (mlxsw_sp_port_vlan)
+		return ERR_PTR(-EEXIST);
+
 	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, true, untagged);
 	if (err)
 		return ERR_PTR(err);
@@ -1162,7 +1166,6 @@ mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 	}
 
 	mlxsw_sp_port_vlan->mlxsw_sp_port = mlxsw_sp_port;
-	mlxsw_sp_port_vlan->ref_count = 1;
 	mlxsw_sp_port_vlan->vid = vid;
 	list_add(&mlxsw_sp_port_vlan->list, &mlxsw_sp_port->vlans_list);
 
@@ -1173,44 +1176,19 @@ err_port_vlan_alloc:
 	return ERR_PTR(err);
 }
 
-static void
-mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
+void mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	u16 vid = mlxsw_sp_port_vlan->vid;
 
-	list_del(&mlxsw_sp_port_vlan->list);
-	kfree(mlxsw_sp_port_vlan);
-	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
-}
-
-struct mlxsw_sp_port_vlan *
-mlxsw_sp_port_vlan_get(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
-{
-	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
-
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
-	if (mlxsw_sp_port_vlan) {
-		mlxsw_sp_port_vlan->ref_count++;
-		return mlxsw_sp_port_vlan;
-	}
-
-	return mlxsw_sp_port_vlan_create(mlxsw_sp_port, vid);
-}
-
-void mlxsw_sp_port_vlan_put(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
-{
-	struct mlxsw_sp_fid *fid = mlxsw_sp_port_vlan->fid;
-
-	if (--mlxsw_sp_port_vlan->ref_count != 0)
-		return;
-
 	if (mlxsw_sp_port_vlan->bridge_port)
 		mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
-	else if (fid)
+	else if (mlxsw_sp_port_vlan->fid)
 		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
 
-	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
+	list_del(&mlxsw_sp_port_vlan->list);
+	kfree(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
 }
 
 static int mlxsw_sp_port_add_vid(struct net_device *dev,
@@ -1224,7 +1202,7 @@ static int mlxsw_sp_port_add_vid(struct net_device *dev,
 	if (!vid)
 		return 0;
 
-	return PTR_ERR_OR_ZERO(mlxsw_sp_port_vlan_get(mlxsw_sp_port, vid));
+	return PTR_ERR_OR_ZERO(mlxsw_sp_port_vlan_create(mlxsw_sp_port, vid));
 }
 
 static int mlxsw_sp_port_kill_vid(struct net_device *dev,
@@ -1242,7 +1220,7 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev,
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
 	if (!mlxsw_sp_port_vlan)
 		return 0;
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 
 	return 0;
 }
@@ -3198,12 +3176,12 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_port_nve_init;
 	}
 
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_get(mlxsw_sp_port, 1);
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_create(mlxsw_sp_port, 1);
 	if (IS_ERR(mlxsw_sp_port_vlan)) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to create VID 1\n",
 			mlxsw_sp_port->local_port);
 		err = PTR_ERR(mlxsw_sp_port_vlan);
-		goto err_port_vlan_get;
+		goto err_port_vlan_create;
 	}
 
 	mlxsw_sp_port_switchdev_init(mlxsw_sp_port);
@@ -3224,8 +3202,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 err_register_netdev:
 	mlxsw_sp->ports[local_port] = NULL;
 	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
-err_port_vlan_get:
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
+err_port_vlan_create:
 	mlxsw_sp_port_nve_fini(mlxsw_sp_port);
 err_port_nve_init:
 	mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port);
@@ -4721,7 +4699,7 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->lagged = 0;
 	lag->ref_count--;
 
-	mlxsw_sp_port_vlan_get(mlxsw_sp_port, 1);
+	mlxsw_sp_port_vlan_create(mlxsw_sp_port, 1);
 	/* Make sure untagged frames are allowed to ingress */
 	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 9b7ba4c3d334..cb1d37df87ea 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -190,7 +190,6 @@ struct mlxsw_sp_port_vlan {
 	struct list_head list;
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct mlxsw_sp_fid *fid;
-	unsigned int ref_count;
 	u16 vid;
 	struct mlxsw_sp_bridge_port *bridge_port;
 	struct list_head bridge_vlan_node;
@@ -410,8 +409,8 @@ int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
 				   bool learn_enable);
 int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
 struct mlxsw_sp_port_vlan *
-mlxsw_sp_port_vlan_get(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
-void mlxsw_sp_port_vlan_put(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
+mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
+void mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin,
 			   u16 vid_end, bool is_member, bool untagged);
 int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 627efe7a6eef..0b2f724d9a0c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1021,10 +1021,8 @@ mlxsw_sp_port_vlan_bridge_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 	int err;
 
 	/* No need to continue if only VLAN flags were changed */
-	if (mlxsw_sp_port_vlan->bridge_port) {
-		mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	if (mlxsw_sp_port_vlan->bridge_port)
 		return 0;
-	}
 
 	err = mlxsw_sp_port_vlan_fid_join(mlxsw_sp_port_vlan, bridge_port,
 					  extack);
@@ -1105,16 +1103,32 @@ static int
 mlxsw_sp_bridge_port_vlan_add(struct mlxsw_sp_port *mlxsw_sp_port,
 			      struct mlxsw_sp_bridge_port *bridge_port,
 			      u16 vid, bool is_untagged, bool is_pvid,
-			      struct netlink_ext_ack *extack)
+			      struct netlink_ext_ack *extack,
+			      struct switchdev_trans *trans)
 {
 	u16 pvid = mlxsw_sp_port_pvid_determine(mlxsw_sp_port, vid, is_pvid);
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 	u16 old_pvid = mlxsw_sp_port->pvid;
 	int err;
 
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_get(mlxsw_sp_port, vid);
-	if (IS_ERR(mlxsw_sp_port_vlan))
-		return PTR_ERR(mlxsw_sp_port_vlan);
+	/* The only valid scenario in which a port-vlan already exists, is if
+	 * the VLAN flags were changed and the port-vlan is associated with the
+	 * correct bridge port
+	 */
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
+	if (mlxsw_sp_port_vlan &&
+	    mlxsw_sp_port_vlan->bridge_port != bridge_port)
+		return -EEXIST;
+
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
+	if (!mlxsw_sp_port_vlan) {
+		mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_create(mlxsw_sp_port,
+							       vid);
+		if (IS_ERR(mlxsw_sp_port_vlan))
+			return PTR_ERR(mlxsw_sp_port_vlan);
+	}
 
 	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, true,
 				     is_untagged);
@@ -1137,7 +1151,7 @@ err_port_vlan_bridge_join:
 err_port_pvid_set:
 	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
 err_port_vlan_set:
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 	return err;
 }
 
@@ -1199,9 +1213,6 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 		return err;
 	}
 
-	if (switchdev_trans_ph_prepare(trans))
-		return 0;
-
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
 	if (WARN_ON(!bridge_port))
 		return -EINVAL;
@@ -1214,7 +1225,7 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 
 		err = mlxsw_sp_bridge_port_vlan_add(mlxsw_sp_port, bridge_port,
 						    vid, flag_untagged,
-						    flag_pvid, extack);
+						    flag_pvid, extack, trans);
 		if (err)
 			return err;
 	}
@@ -1832,7 +1843,7 @@ mlxsw_sp_bridge_port_vlan_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
 	mlxsw_sp_port_pvid_set(mlxsw_sp_port, pvid);
 	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 }
 
 static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -2000,7 +2011,7 @@ mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 		return -EINVAL;
 
 	/* Let VLAN-aware bridge take care of its own VLANs */
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 
 	return 0;
 }
@@ -2010,7 +2021,7 @@ mlxsw_sp_bridge_8021q_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
 				 struct mlxsw_sp_bridge_port *bridge_port,
 				 struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	mlxsw_sp_port_vlan_get(mlxsw_sp_port, 1);
+	mlxsw_sp_port_vlan_create(mlxsw_sp_port, 1);
 	/* Make sure untagged frames are allowed to ingress */
 	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
 }
-- 
cgit v1.2.3


From be2d6f421f680e01d58f7cd452646e0d8586d49b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 19 Dec 2018 06:08:45 +0000
Subject: mlxsw: spectrum: Properly cleanup LAG uppers when removing port from
 LAG

When a LAG device or a VLAN device on top of it is enslaved to a bridge,
the driver propagates the CHANGEUPPER event to the LAG's slaves.

This causes each physical port to increase the reference count of the
internal representation of the bridge port by calling
mlxsw_sp_port_bridge_join().

However, when a port is removed from a LAG, the corresponding leave()
function is not called and the reference count is not decremented. This
leads to ugly hacks such as mlxsw_sp_bridge_port_should_destroy() that
try to understand if the bridge port should be destroyed even when its
reference count is not 0.

Instead, make sure that when a port is unlinked from a LAG it would see
the same events as if the LAG (or its uppers) were unlinked from a
bridge.

The above is achieved by walking the LAG's uppers when a port is
unlinked and calling mlxsw_sp_port_bridge_leave() for each upper that is
enslaved to a bridge.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 23 ++++++++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 27 +---------------------
 2 files changed, 24 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 7777528f67fb..d0235aa2aebc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4498,6 +4498,25 @@ void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port)
 	dev_put(mlxsw_sp_port->dev);
 }
 
+static void
+mlxsw_sp_port_lag_uppers_cleanup(struct mlxsw_sp_port *mlxsw_sp_port,
+				 struct net_device *lag_dev)
+{
+	struct net_device *br_dev = netdev_master_upper_dev_get(lag_dev);
+	struct net_device *upper_dev;
+	struct list_head *iter;
+
+	if (netif_is_bridge_port(lag_dev))
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, lag_dev, br_dev);
+
+	netdev_for_each_upper_dev_rcu(lag_dev, upper_dev, iter) {
+		if (!netif_is_bridge_port(upper_dev))
+			continue;
+		br_dev = netdev_master_upper_dev_get(upper_dev);
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, upper_dev, br_dev);
+	}
+}
+
 static int mlxsw_sp_lag_create(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
 {
 	char sldr_pl[MLXSW_REG_SLDR_LEN];
@@ -4690,6 +4709,10 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	/* Any VLANs configured on the port are no longer valid */
 	mlxsw_sp_port_vlan_flush(mlxsw_sp_port);
+	/* Make the LAG and its directly linked uppers leave bridges they
+	 * are memeber in
+	 */
+	mlxsw_sp_port_lag_uppers_cleanup(mlxsw_sp_port, lag_dev);
 
 	if (lag->ref_count == 1)
 		mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 0b2f724d9a0c..4b7ef83c19c4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -290,30 +290,6 @@ mlxsw_sp_bridge_port_destroy(struct mlxsw_sp_bridge_port *bridge_port)
 	kfree(bridge_port);
 }
 
-static bool
-mlxsw_sp_bridge_port_should_destroy(const struct mlxsw_sp_bridge_port *
-				    bridge_port)
-{
-	struct net_device *dev = bridge_port->dev;
-	struct mlxsw_sp *mlxsw_sp;
-
-	if (is_vlan_dev(dev))
-		mlxsw_sp = mlxsw_sp_lower_get(vlan_dev_real_dev(dev));
-	else
-		mlxsw_sp = mlxsw_sp_lower_get(dev);
-
-	/* In case ports were pulled from out of a bridged LAG, then
-	 * it's possible the reference count isn't zero, yet the bridge
-	 * port should be destroyed, as it's no longer an upper of ours.
-	 */
-	if (!mlxsw_sp && list_empty(&bridge_port->vlans_list))
-		return true;
-	else if (bridge_port->ref_count == 0)
-		return true;
-	else
-		return false;
-}
-
 static struct mlxsw_sp_bridge_port *
 mlxsw_sp_bridge_port_get(struct mlxsw_sp_bridge *bridge,
 			 struct net_device *brport_dev)
@@ -351,8 +327,7 @@ static void mlxsw_sp_bridge_port_put(struct mlxsw_sp_bridge *bridge,
 {
 	struct mlxsw_sp_bridge_device *bridge_device;
 
-	bridge_port->ref_count--;
-	if (!mlxsw_sp_bridge_port_should_destroy(bridge_port))
+	if (--bridge_port->ref_count != 0)
 		return;
 	bridge_device = bridge_port->bridge_device;
 	mlxsw_sp_bridge_port_destroy(bridge_port);
-- 
cgit v1.2.3


From 21ffedb6db5ac80b2081f425be358a976f5c14b7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 19 Dec 2018 06:08:47 +0000
Subject: mlxsw: spectrum_router: Propagate 'struct mlxsw_sp' further

Next patch is going to make RIF deletion more robust by removing
reliance on fragile mlxsw_sp_lower_get(). This is because a netdev is
not necessarily our upper anymore when its IP addresses are flushed.

The inet{,6}addr notification blocks are going to resolve 'struct
mlxsw_sp' using container_of(), but the functions they call still use
mlxsw_sp_lower_get().

As a preparation for the next patch, propagate 'struct mlxsw_sp' down to
the functions called from the notification blocks and remove reliance on
mlxsw_sp_lower_get().

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 46 +++++++++++-----------
 1 file changed, 24 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 8a0011a610d6..a80e15b98937 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6568,11 +6568,11 @@ static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
 					     extack);
 }
 
-static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
+static int mlxsw_sp_inetaddr_bridge_event(struct mlxsw_sp *mlxsw_sp,
+					  struct net_device *l3_dev,
 					  unsigned long event,
 					  struct netlink_ext_ack *extack)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
 	struct mlxsw_sp_rif_params params = {
 		.dev = l3_dev,
 	};
@@ -6593,7 +6593,8 @@ static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
 	return 0;
 }
 
-static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
+static int mlxsw_sp_inetaddr_vlan_event(struct mlxsw_sp *mlxsw_sp,
+					struct net_device *vlan_dev,
 					unsigned long event,
 					struct netlink_ext_ack *extack)
 {
@@ -6610,7 +6611,8 @@ static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
 		return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
 						     vid, extack);
 	else if (netif_is_bridge_master(real_dev) && br_vlan_enabled(real_dev))
-		return mlxsw_sp_inetaddr_bridge_event(vlan_dev, event, extack);
+		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, vlan_dev, event,
+						      extack);
 
 	return 0;
 }
@@ -6711,16 +6713,11 @@ void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
 			    mlxsw_sp_fid_index(rif->fid), false);
 }
 
-static int mlxsw_sp_inetaddr_macvlan_event(struct net_device *macvlan_dev,
+static int mlxsw_sp_inetaddr_macvlan_event(struct mlxsw_sp *mlxsw_sp,
+					   struct net_device *macvlan_dev,
 					   unsigned long event,
 					   struct netlink_ext_ack *extack)
 {
-	struct mlxsw_sp *mlxsw_sp;
-
-	mlxsw_sp = mlxsw_sp_lower_get(macvlan_dev);
-	if (!mlxsw_sp)
-		return 0;
-
 	switch (event) {
 	case NETDEV_UP:
 		return mlxsw_sp_rif_macvlan_add(mlxsw_sp, macvlan_dev, extack);
@@ -6759,7 +6756,8 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
-static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
+static int __mlxsw_sp_inetaddr_event(struct mlxsw_sp *mlxsw_sp,
+				     struct net_device *dev,
 				     unsigned long event,
 				     struct netlink_ext_ack *extack)
 {
@@ -6768,11 +6766,14 @@ static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
 	else if (netif_is_lag_master(dev))
 		return mlxsw_sp_inetaddr_lag_event(dev, event, extack);
 	else if (netif_is_bridge_master(dev))
-		return mlxsw_sp_inetaddr_bridge_event(dev, event, extack);
+		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, dev, event,
+						      extack);
 	else if (is_vlan_dev(dev))
-		return mlxsw_sp_inetaddr_vlan_event(dev, event, extack);
+		return mlxsw_sp_inetaddr_vlan_event(mlxsw_sp, dev, event,
+						    extack);
 	else if (netif_is_macvlan(dev))
-		return mlxsw_sp_inetaddr_macvlan_event(dev, event, extack);
+		return mlxsw_sp_inetaddr_macvlan_event(mlxsw_sp, dev, event,
+						       extack);
 	else
 		return 0;
 }
@@ -6798,7 +6799,7 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(dev, event, NULL);
+	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, NULL);
 out:
 	return notifier_from_errno(err);
 }
@@ -6825,7 +6826,7 @@ int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
 	if (err)
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(dev, event, ivi->extack);
+	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, ivi->extack);
 out:
 	return notifier_from_errno(err);
 }
@@ -6854,7 +6855,7 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work)
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	__mlxsw_sp_inetaddr_event(dev, event, NULL);
+	__mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, NULL);
 out:
 	rtnl_unlock();
 	dev_put(dev);
@@ -6911,7 +6912,7 @@ int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused,
 	if (err)
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(dev, event, i6vi->extack);
+	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, i6vi->extack);
 out:
 	return notifier_from_errno(err);
 }
@@ -7030,9 +7031,10 @@ static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp,
 	 */
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
 	if (rif)
-		__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN, extack);
+		__mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_DOWN,
+					  extack);
 
-	return __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_UP, extack);
+	return __mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_UP, extack);
 }
 
 static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp,
@@ -7043,7 +7045,7 @@ static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp,
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
 	if (!rif)
 		return;
-	__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN, NULL);
+	__mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_DOWN, NULL);
 }
 
 int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
-- 
cgit v1.2.3


From 965fa8e600d28d98e7e0c7340517a9c139843ee3 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 19 Dec 2018 06:08:48 +0000
Subject: mlxsw: spectrum_router: Make RIF deletion more robust

In the past we had multiple instances where RIFs were not properly
deleted.

One of the reasons for leaking a RIF was that at the time when IP
addresses were flushed from the respective netdev (prompting the
destruction of the RIF), the netdev was no longer a mlxsw upper. This
caused the inet{,6}addr notification blocks to ignore the NETDEV_DOWN
event and leak the RIF.

Instead of checking whether the netdev is our upper when an IP address
is removed, we can instead check if the netdev has a RIF configured.

To look up a RIF we need to access mlxsw private data, so the patch
stores the notification blocks inside a mlxsw struct. This then allows
us to use container_of() and extract the required private data.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 14 -------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  4 --
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 49 ++++++++++++++--------
 3 files changed, 31 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index d0235aa2aebc..4197b29a9bda 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -5414,18 +5414,10 @@ static struct notifier_block mlxsw_sp_inetaddr_valid_nb __read_mostly = {
 	.notifier_call = mlxsw_sp_inetaddr_valid_event,
 };
 
-static struct notifier_block mlxsw_sp_inetaddr_nb __read_mostly = {
-	.notifier_call = mlxsw_sp_inetaddr_event,
-};
-
 static struct notifier_block mlxsw_sp_inet6addr_valid_nb __read_mostly = {
 	.notifier_call = mlxsw_sp_inet6addr_valid_event,
 };
 
-static struct notifier_block mlxsw_sp_inet6addr_nb __read_mostly = {
-	.notifier_call = mlxsw_sp_inet6addr_event,
-};
-
 static const struct pci_device_id mlxsw_sp1_pci_id_table[] = {
 	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM), 0},
 	{0, },
@@ -5451,9 +5443,7 @@ static int __init mlxsw_sp_module_init(void)
 	int err;
 
 	register_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
-	register_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
 	register_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
-	register_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 
 	err = mlxsw_core_driver_register(&mlxsw_sp1_driver);
 	if (err)
@@ -5480,9 +5470,7 @@ err_sp1_pci_driver_register:
 err_sp2_core_driver_register:
 	mlxsw_core_driver_unregister(&mlxsw_sp1_driver);
 err_sp1_core_driver_register:
-	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
-	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
 	unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
 	return err;
 }
@@ -5493,9 +5481,7 @@ static void __exit mlxsw_sp_module_exit(void)
 	mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver);
 	mlxsw_core_driver_unregister(&mlxsw_sp2_driver);
 	mlxsw_core_driver_unregister(&mlxsw_sp1_driver);
-	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
-	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
 	unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index cb1d37df87ea..f022e9e24085 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -458,12 +458,8 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev,
 					 unsigned long event, void *ptr);
 void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
 			      const struct net_device *macvlan_dev);
-int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
-			    unsigned long event, void *ptr);
 int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
 				  unsigned long event, void *ptr);
-int mlxsw_sp_inet6addr_event(struct notifier_block *unused,
-			     unsigned long event, void *ptr);
 int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused,
 				   unsigned long event, void *ptr);
 int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index a80e15b98937..08b60d4b9492 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -71,6 +71,8 @@ struct mlxsw_sp_router {
 	bool aborted;
 	struct notifier_block fib_nb;
 	struct notifier_block netevent_nb;
+	struct notifier_block inetaddr_nb;
+	struct notifier_block inet6addr_nb;
 	const struct mlxsw_sp_rif_ops **rif_ops_arr;
 	const struct mlxsw_sp_ipip_ops **ipip_ops_arr;
 };
@@ -6778,12 +6780,12 @@ static int __mlxsw_sp_inetaddr_event(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 }
 
-int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
-			    unsigned long event, void *ptr)
+static int mlxsw_sp_inetaddr_event(struct notifier_block *nb,
+				   unsigned long event, void *ptr)
 {
 	struct in_ifaddr *ifa = (struct in_ifaddr *) ptr;
 	struct net_device *dev = ifa->ifa_dev->dev;
-	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_router *router;
 	struct mlxsw_sp_rif *rif;
 	int err = 0;
 
@@ -6791,15 +6793,12 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
 	if (event == NETDEV_UP)
 		goto out;
 
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		goto out;
-
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	router = container_of(nb, struct mlxsw_sp_router, inetaddr_nb);
+	rif = mlxsw_sp_rif_find_by_dev(router->mlxsw_sp, dev);
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, NULL);
+	err = __mlxsw_sp_inetaddr_event(router->mlxsw_sp, dev, event, NULL);
 out:
 	return notifier_from_errno(err);
 }
@@ -6833,6 +6832,7 @@ out:
 
 struct mlxsw_sp_inet6addr_event_work {
 	struct work_struct work;
+	struct mlxsw_sp *mlxsw_sp;
 	struct net_device *dev;
 	unsigned long event;
 };
@@ -6841,15 +6841,12 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work)
 {
 	struct mlxsw_sp_inet6addr_event_work *inet6addr_work =
 		container_of(work, struct mlxsw_sp_inet6addr_event_work, work);
+	struct mlxsw_sp *mlxsw_sp = inet6addr_work->mlxsw_sp;
 	struct net_device *dev = inet6addr_work->dev;
 	unsigned long event = inet6addr_work->event;
-	struct mlxsw_sp *mlxsw_sp;
 	struct mlxsw_sp_rif *rif;
 
 	rtnl_lock();
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		goto out;
 
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
@@ -6863,25 +6860,25 @@ out:
 }
 
 /* Called with rcu_read_lock() */
-int mlxsw_sp_inet6addr_event(struct notifier_block *unused,
-			     unsigned long event, void *ptr)
+static int mlxsw_sp_inet6addr_event(struct notifier_block *nb,
+				    unsigned long event, void *ptr)
 {
 	struct inet6_ifaddr *if6 = (struct inet6_ifaddr *) ptr;
 	struct mlxsw_sp_inet6addr_event_work *inet6addr_work;
 	struct net_device *dev = if6->idev->dev;
+	struct mlxsw_sp_router *router;
 
 	/* NETDEV_UP event is handled by mlxsw_sp_inet6addr_valid_event */
 	if (event == NETDEV_UP)
 		return NOTIFY_DONE;
 
-	if (!mlxsw_sp_port_dev_lower_find_rcu(dev))
-		return NOTIFY_DONE;
-
 	inet6addr_work = kzalloc(sizeof(*inet6addr_work), GFP_ATOMIC);
 	if (!inet6addr_work)
 		return NOTIFY_BAD;
 
+	router = container_of(nb, struct mlxsw_sp_router, inet6addr_nb);
 	INIT_WORK(&inet6addr_work->work, mlxsw_sp_inet6addr_event_work);
+	inet6addr_work->mlxsw_sp = router->mlxsw_sp;
 	inet6addr_work->dev = dev;
 	inet6addr_work->event = event;
 	dev_hold(dev);
@@ -7657,6 +7654,16 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 	mlxsw_sp->router = router;
 	router->mlxsw_sp = mlxsw_sp;
 
+	router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event;
+	err = register_inetaddr_notifier(&router->inetaddr_nb);
+	if (err)
+		goto err_register_inetaddr_notifier;
+
+	router->inet6addr_nb.notifier_call = mlxsw_sp_inet6addr_event;
+	err = register_inet6addr_notifier(&router->inet6addr_nb);
+	if (err)
+		goto err_register_inet6addr_notifier;
+
 	INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_neighs_list);
 	err = __mlxsw_sp_router_init(mlxsw_sp);
 	if (err)
@@ -7742,6 +7749,10 @@ err_ipips_init:
 err_rifs_init:
 	__mlxsw_sp_router_fini(mlxsw_sp);
 err_router_init:
+	unregister_inet6addr_notifier(&router->inet6addr_nb);
+err_register_inet6addr_notifier:
+	unregister_inetaddr_notifier(&router->inetaddr_nb);
+err_register_inetaddr_notifier:
 	kfree(mlxsw_sp->router);
 	return err;
 }
@@ -7759,5 +7770,7 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
 	mlxsw_sp_ipips_fini(mlxsw_sp);
 	mlxsw_sp_rifs_fini(mlxsw_sp);
 	__mlxsw_sp_router_fini(mlxsw_sp);
+	unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb);
+	unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb);
 	kfree(mlxsw_sp->router);
 }
-- 
cgit v1.2.3


From b61cd7c6f992cca57166d0cabe242c49b93609eb Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 19 Dec 2018 06:08:50 +0000
Subject: mlxsw: spectrum_router: Hold a reference on RIF's netdev

Previous patches tried to make RIF deletion more robust and avoid
use-after-free situations.

As another precaution, hold a reference on a RIF's netdev and release it
when the RIF is deleted.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 08b60d4b9492..673950933dac 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6302,6 +6302,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 		err = -ENOMEM;
 		goto err_rif_alloc;
 	}
+	dev_hold(rif->dev);
 	rif->mlxsw_sp = mlxsw_sp;
 	rif->ops = ops;
 
@@ -6340,6 +6341,7 @@ err_configure:
 	if (fid)
 		mlxsw_sp_fid_put(fid);
 err_fid_get:
+	dev_put(rif->dev);
 	kfree(rif);
 err_rif_alloc:
 err_rif_index_alloc:
@@ -6367,6 +6369,7 @@ static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 	if (fid)
 		/* Loopback RIFs are not associated with a FID. */
 		mlxsw_sp_fid_put(fid);
+	dev_put(rif->dev);
 	kfree(rif);
 	vr->rif_count--;
 	mlxsw_sp_vr_put(mlxsw_sp, vr);
-- 
cgit v1.2.3


From 489c25f9a375ba1e780dcf445ca74f6b3766d1b5 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 19 Dec 2018 06:08:51 +0000
Subject: selftests: mlxsw: Add rtnetlink tests

Add a new test that is focused on rtnetlink configuration. Its purpose
is to test valid and invalid (as deemed by mlxsw) configurations and
make sure that they succeed / fail without producing a trace.

Some of the test cases are derived from recent fixes in order to make
sure that the fixed bugs are not introduced again.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/rtnetlink.sh       | 392 +++++++++++++++++++++
 1 file changed, 392 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index 7f78b96279f3..9040bfbddfba 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -13,9 +13,23 @@ ALL_TESTS="
 	rif_set_addr_test
 	rif_inherit_bridge_addr_test
 	rif_non_inherit_bridge_addr_test
+	vlan_interface_deletion_test
+	bridge_deletion_test
+	bridge_vlan_flags_test
+	vlan_1_test
+	lag_bridge_upper_test
+	duplicate_vlans_test
+	vlan_rif_refcount_test
+	subport_rif_refcount_test
+	vlan_dev_deletion_test
+	lag_unlink_slaves_test
+	lag_dev_deletion_test
+	vlan_interface_uppers_test
+	devlink_reload_test
 "
 NUM_NETIFS=2
 source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
 
 setup_prepare()
 {
@@ -160,6 +174,384 @@ rif_non_inherit_bridge_addr_test()
 	ip addr del dev $swp1 192.0.2.1/28
 }
 
+vlan_interface_deletion_test()
+{
+	# Test that when a VLAN interface is deleted, its associated router
+	# interface (RIF) is correctly deleted and not leaked. See commit
+	# c360867ec46a ("mlxsw: spectrum: Delete RIF when VLAN device is
+	# removed") for more details
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+
+	ip link add link br0 name br0.10 type vlan id 10
+	ip -6 address add 2001:db8:1::1/64 dev br0.10
+	ip link del dev br0.10
+
+	# If we leaked the previous RIF, then this should produce a trace
+	ip link add link br0 name br0.20 type vlan id 20
+	ip -6 address add 2001:db8:1::1/64 dev br0.20
+	ip link del dev br0.20
+
+	log_test "vlan interface deletion"
+
+	ip link del dev br0
+}
+
+bridge_deletion_test()
+{
+	# Test that when a bridge with VLAN interfaces is deleted, we correctly
+	# delete the associated RIFs. See commit 602b74eda813 ("mlxsw:
+	# spectrum_switchdev: Do not leak RIFs when removing bridge") for more
+	# details
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+	ip -6 address add 2001:db8::1/64 dev br0
+
+	ip link add link br0 name br0.10 type vlan id 10
+	ip -6 address add 2001:db8:1::1/64 dev br0.10
+
+	ip link add link br0 name br0.20 type vlan id 20
+	ip -6 address add 2001:db8:2::1/64 dev br0.20
+
+	ip link del dev br0
+
+	# If we leaked previous RIFs, then this should produce a trace
+	ip -6 address add 2001:db8:1::1/64 dev $swp1
+	ip -6 address del 2001:db8:1::1/64 dev $swp1
+
+	log_test "bridge deletion"
+}
+
+bridge_vlan_flags_test()
+{
+	# Test that when bridge VLAN flags are toggled, we do not take
+	# unnecessary references on related structs. See commit 9e25826ffc94
+	# ("mlxsw: spectrum_switchdev: Fix port_vlan refcounting") for more
+	# details
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+
+	bridge vlan add vid 10 dev $swp1 pvid untagged
+	bridge vlan add vid 10 dev $swp1 untagged
+	bridge vlan add vid 10 dev $swp1 pvid
+	bridge vlan add vid 10 dev $swp1
+	ip link del dev br0
+
+	# If we did not handle references correctly, then this should produce a
+	# trace
+	devlink dev reload "$DEVLINK_DEV"
+
+	# Allow netdevices to be re-created following the reload
+	sleep 20
+
+	log_test "bridge vlan flags"
+}
+
+vlan_1_test()
+{
+	# Test that VLAN 1 cannot be configured, as it is used internally for
+	# untagged traffic. See commit 47bf9df2e820 ("mlxsw: spectrum: Forbid
+	# creation of VLAN 1 over port/LAG") for more details
+	RET=0
+
+	ip link add link $swp1 name $swp1.1 type vlan id 1 &> /dev/null
+	check_fail $? "managed to create vlan 1 when should not"
+
+	log_test "vlan 1"
+}
+
+lag_bridge_upper_test()
+{
+	# Test that ports cannot be enslaved to LAG devices that have uppers
+	# and that failure is handled gracefully. See commit b3529af6bb0d
+	# ("spectrum: Reference count VLAN entries") for more details
+	RET=0
+
+	ip link add name bond1 type bond mode 802.3ad
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev bond1 master br0
+
+	ip link set dev $swp1 down
+	ip link set dev $swp1 master bond1 &> /dev/null
+	check_fail $? "managed to enslave port to lag when should not"
+
+	# This might generate a trace, if we did not handle the failure
+	# correctly
+	ip -6 address add 2001:db8:1::1/64 dev $swp1
+	ip -6 address del 2001:db8:1::1/64 dev $swp1
+
+	log_test "lag with bridge upper"
+
+	ip link del dev br0
+	ip link del dev bond1
+}
+
+duplicate_vlans_test()
+{
+	# Test that on a given port a VLAN is only used once. Either as VLAN
+	# in a VLAN-aware bridge or as a VLAN device
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+	bridge vlan add vid 10 dev $swp1
+
+	ip link add link $swp1 name $swp1.10 type vlan id 10 &> /dev/null
+	check_fail $? "managed to create vlan device when should not"
+
+	bridge vlan del vid 10 dev $swp1
+	ip link add link $swp1 name $swp1.10 type vlan id 10
+	check_err $? "did not manage to create vlan device when should"
+	bridge vlan add vid 10 dev $swp1 &> /dev/null
+	check_fail $? "managed to add bridge vlan when should not"
+
+	log_test "duplicate vlans"
+
+	ip link del dev $swp1.10
+	ip link del dev br0
+}
+
+vlan_rif_refcount_test()
+{
+	# Test that RIFs representing VLAN interfaces are not affected from
+	# ports member in the VLAN. We use the offload indication on routes
+	# configured on the RIF to understand if it was created / destroyed
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+
+	ip link set dev $swp1 up
+	ip link set dev br0 up
+
+	ip link add link br0 name br0.10 up type vlan id 10
+	ip -6 address add 2001:db8:1::1/64 dev br0.10
+
+	ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+	check_err $? "vlan rif was not created before adding port to vlan"
+
+	bridge vlan add vid 10 dev $swp1
+	ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+	check_err $? "vlan rif was destroyed after adding port to vlan"
+
+	bridge vlan del vid 10 dev $swp1
+	ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+	check_err $? "vlan rif was destroyed after removing port from vlan"
+
+	ip link set dev $swp1 nomaster
+	ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+	check_fail $? "vlan rif was not destroyed after unlinking port from bridge"
+
+	log_test "vlan rif refcount"
+
+	ip link del dev br0.10
+	ip link set dev $swp1 down
+	ip link del dev br0
+}
+
+subport_rif_refcount_test()
+{
+	# Test that RIFs representing upper devices of physical ports are
+	# reference counted correctly and destroyed when should. We use the
+	# offload indication on routes configured on the RIF to understand if
+	# it was created / destroyed
+	RET=0
+
+	ip link add name bond1 type bond mode 802.3ad
+	ip link set dev $swp1 down
+	ip link set dev $swp2 down
+	ip link set dev $swp1 master bond1
+	ip link set dev $swp2 master bond1
+
+	ip link set dev bond1 up
+	ip link add link bond1 name bond1.10 up type vlan id 10
+	ip -6 address add 2001:db8:1::1/64 dev bond1
+	ip -6 address add 2001:db8:2::1/64 dev bond1.10
+
+	ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
+	check_err $? "subport rif was not created on lag device"
+	ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
+	check_err $? "subport rif was not created on vlan device"
+
+	ip link set dev $swp1 nomaster
+	ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
+	check_err $? "subport rif of lag device was destroyed when should not"
+	ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
+	check_err $? "subport rif of vlan device was destroyed when should not"
+
+	ip link set dev $swp2 nomaster
+	ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
+	check_fail $? "subport rif of lag device was not destroyed when should"
+	ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
+	check_fail $? "subport rif of vlan device was not destroyed when should"
+
+	log_test "subport rif refcount"
+
+	ip link del dev bond1.10
+	ip link del dev bond1
+}
+
+vlan_dev_deletion_test()
+{
+	# Test that VLAN devices are correctly deleted / unlinked when enslaved
+	# to bridge
+	RET=0
+
+	ip link add name br10 type bridge
+	ip link add name br20 type bridge
+	ip link add name br30 type bridge
+	ip link add link $swp1 name $swp1.10 type vlan id 10
+	ip link add link $swp1 name $swp1.20 type vlan id 20
+	ip link add link $swp1 name $swp1.30 type vlan id 30
+	ip link set dev $swp1.10 master br10
+	ip link set dev $swp1.20 master br20
+	ip link set dev $swp1.30 master br30
+
+	# If we did not handle the situation correctly, then these operations
+	# might produce a trace
+	ip link set dev $swp1.30 nomaster
+	ip link del dev $swp1.20
+	# Deletion via ioctl uses different code paths from netlink
+	vconfig rem $swp1.10 &> /dev/null
+
+	log_test "vlan device deletion"
+
+	ip link del dev $swp1.30
+	ip link del dev br30
+	ip link del dev br20
+	ip link del dev br10
+}
+
+lag_create()
+{
+	ip link add name bond1 type bond mode 802.3ad
+	ip link set dev $swp1 down
+	ip link set dev $swp2 down
+	ip link set dev $swp1 master bond1
+	ip link set dev $swp2 master bond1
+
+	ip link add link bond1 name bond1.10 type vlan id 10
+	ip link add link bond1 name bond1.20 type vlan id 20
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev bond1 master br0
+
+	ip link add name br10 type bridge
+	ip link set dev bond1.10 master br10
+
+	ip link add name br20 type bridge
+	ip link set dev bond1.20 master br20
+}
+
+lag_unlink_slaves_test()
+{
+	# Test that ports are correctly unlinked from their LAG master, when
+	# the LAG and its VLAN uppers are enslaved to bridges
+	RET=0
+
+	lag_create
+
+	ip link set dev $swp1 nomaster
+	check_err $? "lag slave $swp1 was not unlinked from master"
+	ip link set dev $swp2 nomaster
+	check_err $? "lag slave $swp2 was not unlinked from master"
+
+	# Try to configure corresponding VLANs as router interfaces
+	ip -6 address add 2001:db8:1::1/64 dev $swp1
+	check_err $? "failed to configure ip address on $swp1"
+
+	ip link add link $swp1 name $swp1.10 type vlan id 10
+	ip -6 address add 2001:db8:10::1/64 dev $swp1.10
+	check_err $? "failed to configure ip address on $swp1.10"
+
+	ip link add link $swp1 name $swp1.20 type vlan id 20
+	ip -6 address add 2001:db8:20::1/64 dev $swp1.20
+	check_err $? "failed to configure ip address on $swp1.20"
+
+	log_test "lag slaves unlinking"
+
+	ip link del dev $swp1.20
+	ip link del dev $swp1.10
+	ip address flush dev $swp1
+
+	ip link del dev br20
+	ip link del dev br10
+	ip link del dev br0
+	ip link del dev bond1
+}
+
+lag_dev_deletion_test()
+{
+	# Test that LAG device is correctly deleted, when the LAG and its VLAN
+	# uppers are enslaved to bridges
+	RET=0
+
+	lag_create
+
+	ip link del dev bond1
+
+	log_test "lag device deletion"
+
+	ip link del dev br20
+	ip link del dev br10
+	ip link del dev br0
+}
+
+vlan_interface_uppers_test()
+{
+	# Test that uppers of a VLAN interface are correctly sanitized
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+
+	ip link add link br0 name br0.10 type vlan id 10
+	ip link add link br0.10 name macvlan0 \
+		type macvlan mode private &> /dev/null
+	check_fail $? "managed to create a macvlan when should not"
+
+	ip -6 address add 2001:db8:1::1/64 dev br0.10
+	ip link add link br0.10 name macvlan0 type macvlan mode private
+	check_err $? "did not manage to create a macvlan when should"
+
+	ip link del dev macvlan0
+
+	ip link add name vrf-test type vrf table 10
+	ip link set dev br0.10 master vrf-test
+	check_err $? "did not manage to enslave vlan interface to vrf"
+	ip link del dev vrf-test
+
+	ip link add name br-test type bridge
+	ip link set dev br0.10 master br-test &> /dev/null
+	check_fail $? "managed to enslave vlan interface to bridge when should not"
+	ip link del dev br-test
+
+	log_test "vlan interface uppers"
+
+	ip link del dev br0
+}
+
+devlink_reload_test()
+{
+	# Test that after executing all the above configuration tests, a
+	# devlink reload can be performed without errors
+	RET=0
+
+	devlink dev reload "$DEVLINK_DEV"
+	check_err $? "devlink reload failed"
+
+	log_test "devlink reload - last test"
+
+	sleep 20
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
cgit v1.2.3


From e2ce3674883ecba2605370404208c9d4a07ae1c3 Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Wed, 19 Dec 2018 13:09:31 +0100
Subject: xsk: simplify AF_XDP socket teardown
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prior this commit, when the struct socket object was being released,
the UMEM did not have its reference count decreased. Instead, this was
done in the struct sock sk_destruct function.

There is no reason to keep the UMEM reference around when the socket
is being orphaned, so in this patch the xdp_put_mem is called in the
xsk_release function. This results in that the xsk_destruct function
can be removed!

Note that, it still holds that a struct xsk_sock reference might still
linger in the XSKMAP after the UMEM is released, e.g. if a user does
not clear the XSKMAP prior to closing the process. This sock will be
in a "released" zombie like state, until the XSKMAP is removed.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/xdp/xsk.c | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 07156f43d295..a03268454a27 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -366,6 +366,7 @@ static int xsk_release(struct socket *sock)
 
 	xskq_destroy(xs->rx);
 	xskq_destroy(xs->tx);
+	xdp_put_umem(xs->umem);
 
 	sock_orphan(sk);
 	sock->sk = NULL;
@@ -713,18 +714,6 @@ static const struct proto_ops xsk_proto_ops = {
 	.sendpage	= sock_no_sendpage,
 };
 
-static void xsk_destruct(struct sock *sk)
-{
-	struct xdp_sock *xs = xdp_sk(sk);
-
-	if (!sock_flag(sk, SOCK_DEAD))
-		return;
-
-	xdp_put_umem(xs->umem);
-
-	sk_refcnt_debug_dec(sk);
-}
-
 static int xsk_create(struct net *net, struct socket *sock, int protocol,
 		      int kern)
 {
@@ -751,9 +740,6 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 
 	sk->sk_family = PF_XDP;
 
-	sk->sk_destruct = xsk_destruct;
-	sk_refcnt_debug_inc(sk);
-
 	sock_set_flag(sk, SOCK_RCU_FREE);
 
 	xs = xdp_sk(sk);
-- 
cgit v1.2.3


From 9e88b9312acb9b80554c48b58668fb144720333a Mon Sep 17 00:00:00 2001
From: Ivan Babrou <ivan@cloudflare.com>
Date: Wed, 19 Dec 2018 12:08:03 -0800
Subject: tools: bpftool: do not force gcc as CC

This allows transparent cross-compilation with CROSS_COMPILE by
relying on 7ed1c1901fe5 ("tools: fix cross-compile var clobbering").

Signed-off-by: Ivan Babrou <ivan@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Makefile | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 1bea6b979082..492f0f24e2d3 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -35,8 +35,6 @@ $(LIBBPF)-clean:
 prefix ?= /usr/local
 bash_compdir ?= /usr/share/bash-completion/completions
 
-CC = gcc
-
 CFLAGS += -O2
 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -Wno-missing-field-initializers
 CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \
-- 
cgit v1.2.3


From 82cbb5c631a07b3aa6df6eab644d55da9de5a645 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Wed, 19 Dec 2018 12:51:38 -0800
Subject: neighbour: register rtnl doit handler

this patch registers neigh doit handler. The doit handler
returns a neigh entry given dst and dev. This is similar
to route and fdb doit (get) handlers. Also moves nda_policy
declaration from rtnetlink.c to neighbour.c

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h |   1 +
 net/core/neighbour.c    | 204 +++++++++++++++++++++++++++++++++++++++++++++---
 net/core/rtnetlink.c    |  12 ---
 3 files changed, 194 insertions(+), 23 deletions(-)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 66221f1991c0..7c1ab9edba03 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -255,6 +255,7 @@ static inline void *neighbour_priv(const struct neighbour *n)
 #define NEIGH_UPDATE_F_ISROUTER			0x40000000
 #define NEIGH_UPDATE_F_ADMIN			0x80000000
 
+extern const struct nla_policy nda_policy[];
 
 static inline bool neigh_key_eq16(const struct neighbour *n, const void *pkey)
 {
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index fb4372cb1de1..43687c9abe1d 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1751,6 +1751,18 @@ static struct neigh_table *neigh_find_table(int family)
 	return tbl;
 }
 
+const struct nla_policy nda_policy[NDA_MAX+1] = {
+	[NDA_DST]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+	[NDA_LLADDR]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+	[NDA_CACHEINFO]		= { .len = sizeof(struct nda_cacheinfo) },
+	[NDA_PROBES]		= { .type = NLA_U32 },
+	[NDA_VLAN]		= { .type = NLA_U16 },
+	[NDA_PORT]		= { .type = NLA_U16 },
+	[NDA_VNI]		= { .type = NLA_U32 },
+	[NDA_IFINDEX]		= { .type = NLA_U32 },
+	[NDA_MASTER]		= { .type = NLA_U32 },
+};
+
 static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct netlink_ext_ack *extack)
 {
@@ -2711,6 +2723,186 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+static int neigh_valid_get_req(const struct nlmsghdr *nlh,
+			       struct neigh_table **tbl,
+			       void **dst, int *dev_idx, u8 *ndm_flags,
+			       struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[NDA_MAX + 1];
+	struct ndmsg *ndm;
+	int err, i;
+
+	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+		NL_SET_ERR_MSG(extack, "Invalid header for neighbor get request");
+		return -EINVAL;
+	}
+
+	ndm = nlmsg_data(nlh);
+	if (ndm->ndm_pad1  || ndm->ndm_pad2  || ndm->ndm_state ||
+	    ndm->ndm_type) {
+		NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor get request");
+		return -EINVAL;
+	}
+
+	if (ndm->ndm_flags & ~NTF_PROXY) {
+		NL_SET_ERR_MSG(extack, "Invalid flags in header for neighbor get request");
+		return -EINVAL;
+	}
+
+	err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
+				 nda_policy, extack);
+	if (err < 0)
+		return err;
+
+	*ndm_flags = ndm->ndm_flags;
+	*dev_idx = ndm->ndm_ifindex;
+	*tbl = neigh_find_table(ndm->ndm_family);
+	if (*tbl == NULL) {
+		NL_SET_ERR_MSG(extack, "Unsupported family in header for neighbor get request");
+		return -EAFNOSUPPORT;
+	}
+
+	for (i = 0; i <= NDA_MAX; ++i) {
+		if (!tb[i])
+			continue;
+
+		switch (i) {
+		case NDA_DST:
+			if (nla_len(tb[i]) != (int)(*tbl)->key_len) {
+				NL_SET_ERR_MSG(extack, "Invalid network address in neighbor get request");
+				return -EINVAL;
+			}
+			*dst = nla_data(tb[i]);
+			break;
+		default:
+			NL_SET_ERR_MSG(extack, "Unsupported attribute in neighbor get request");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static inline size_t neigh_nlmsg_size(void)
+{
+	return NLMSG_ALIGN(sizeof(struct ndmsg))
+	       + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */
+	       + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */
+	       + nla_total_size(sizeof(struct nda_cacheinfo))
+	       + nla_total_size(4)  /* NDA_PROBES */
+	       + nla_total_size(1); /* NDA_PROTOCOL */
+}
+
+static int neigh_get_reply(struct net *net, struct neighbour *neigh,
+			   u32 pid, u32 seq)
+{
+	struct sk_buff *skb;
+	int err = 0;
+
+	skb = nlmsg_new(neigh_nlmsg_size(), GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	err = neigh_fill_info(skb, neigh, pid, seq, RTM_NEWNEIGH, 0);
+	if (err) {
+		kfree_skb(skb);
+		goto errout;
+	}
+
+	err = rtnl_unicast(skb, net, pid);
+errout:
+	return err;
+}
+
+static inline size_t pneigh_nlmsg_size(void)
+{
+	return NLMSG_ALIGN(sizeof(struct ndmsg))
+	       + nla_total_size(MAX_ADDR_LEN); /* NDA_DST */
+	       + nla_total_size(1); /* NDA_PROTOCOL */
+}
+
+static int pneigh_get_reply(struct net *net, struct pneigh_entry *neigh,
+			    u32 pid, u32 seq, struct neigh_table *tbl)
+{
+	struct sk_buff *skb;
+	int err = 0;
+
+	skb = nlmsg_new(pneigh_nlmsg_size(), GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	err = pneigh_fill_info(skb, neigh, pid, seq, RTM_NEWNEIGH, 0, tbl);
+	if (err) {
+		kfree_skb(skb);
+		goto errout;
+	}
+
+	err = rtnl_unicast(skb, net, pid);
+errout:
+	return err;
+}
+
+static int neigh_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+		     struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(in_skb->sk);
+	struct net_device *dev = NULL;
+	struct neigh_table *tbl = NULL;
+	struct neighbour *neigh;
+	void *dst = NULL;
+	u8 ndm_flags = 0;
+	int dev_idx = 0;
+	int err;
+
+	err = neigh_valid_get_req(nlh, &tbl, &dst, &dev_idx, &ndm_flags,
+				  extack);
+	if (err < 0)
+		return err;
+
+	if (dev_idx) {
+		dev = __dev_get_by_index(net, dev_idx);
+		if (!dev) {
+			NL_SET_ERR_MSG(extack, "Unknown device ifindex");
+			return -ENODEV;
+		}
+	}
+
+	if (!dst) {
+		NL_SET_ERR_MSG(extack, "Network address not specified");
+		return -EINVAL;
+	}
+
+	if (ndm_flags & NTF_PROXY) {
+		struct pneigh_entry *pn;
+
+		pn = pneigh_lookup(tbl, net, dst, dev, 0);
+		if (!pn) {
+			NL_SET_ERR_MSG(extack, "Proxy neighbour entry not found");
+			return -ENOENT;
+		}
+		return pneigh_get_reply(net, pn, NETLINK_CB(in_skb).portid,
+					nlh->nlmsg_seq, tbl);
+	}
+
+	if (!dev) {
+		NL_SET_ERR_MSG(extack, "No device specified");
+		return -EINVAL;
+	}
+
+	neigh = neigh_lookup(tbl, dst, dev);
+	if (!neigh) {
+		NL_SET_ERR_MSG(extack, "Neighbour entry not found");
+		return -ENOENT;
+	}
+
+	err = neigh_get_reply(net, neigh, NETLINK_CB(in_skb).portid,
+			      nlh->nlmsg_seq);
+
+	neigh_release(neigh);
+
+	return err;
+}
+
 void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie)
 {
 	int chain;
@@ -3118,16 +3310,6 @@ static const struct seq_operations neigh_stat_seq_ops = {
 };
 #endif /* CONFIG_PROC_FS */
 
-static inline size_t neigh_nlmsg_size(void)
-{
-	return NLMSG_ALIGN(sizeof(struct ndmsg))
-	       + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */
-	       + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */
-	       + nla_total_size(sizeof(struct nda_cacheinfo))
-	       + nla_total_size(4)  /* NDA_PROBES */
-	       + nla_total_size(1); /* NDA_PROTOCOL */
-}
-
 static void __neigh_notify(struct neighbour *n, int type, int flags,
 			   u32 pid)
 {
@@ -3511,7 +3693,7 @@ static int __init neigh_init(void)
 {
 	rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, 0);
-	rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info, 0);
+	rtnl_register(PF_UNSPEC, RTM_GETNEIGH, neigh_get, neigh_dump_info, 0);
 
 	rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info,
 		      0);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index baf2685b4da2..48f61885fd6f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3460,18 +3460,6 @@ void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change,
 			   new_nsid, new_ifindex);
 }
 
-static const struct nla_policy nda_policy[NDA_MAX+1] = {
-	[NDA_DST]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
-	[NDA_LLADDR]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
-	[NDA_CACHEINFO]		= { .len = sizeof(struct nda_cacheinfo) },
-	[NDA_PROBES]		= { .type = NLA_U32 },
-	[NDA_VLAN]		= { .type = NLA_U16 },
-	[NDA_PORT]		= { .type = NLA_U16 },
-	[NDA_VNI]		= { .type = NLA_U32 },
-	[NDA_IFINDEX]		= { .type = NLA_U32 },
-	[NDA_MASTER]		= { .type = NLA_U32 },
-};
-
 static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
 				   struct net_device *dev,
 				   u8 *addr, u16 vid, u32 pid, u32 seq,
-- 
cgit v1.2.3


From 8deecf3557cca7d80fb5157f0858b738f8eebbc7 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Wed, 19 Dec 2018 12:51:39 -0800
Subject: selftests: rtnetlink.sh: add testcase for neigh get

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 54 ++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index bb3436f8807f..c5cbea9b317d 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -1007,6 +1007,59 @@ kci_test_fdb_get()
 	echo "PASS: bridge fdb get"
 }
 
+kci_test_neigh_get()
+{
+	dstmac=de:ad:be:ef:13:37
+	dstip=10.0.2.4
+	dstip6=dead::2
+	ret=0
+
+	ip neigh help 2>&1 |grep -q 'ip neigh get'
+	if [ $? -ne 0 ];then
+		echo "SKIP: fdb get tests: iproute2 too old"
+		return $ksft_skip
+	fi
+
+	# ipv4
+	ip neigh add $dstip lladdr $dstmac dev "$devdummy"  > /dev/null
+	check_err $?
+	ip neigh get $dstip dev "$devdummy" 2> /dev/null | grep -q "$dstmac"
+	check_err $?
+	ip neigh del $dstip lladdr $dstmac dev "$devdummy"  > /dev/null
+	check_err $?
+
+	# ipv4 proxy
+	ip neigh add proxy $dstip dev "$devdummy" > /dev/null
+	check_err $?
+	ip neigh get proxy $dstip dev "$devdummy" 2>/dev/null | grep -q "$dstip"
+	check_err $?
+	ip neigh del proxy $dstip dev "$devdummy" > /dev/null
+	check_err $?
+
+	# ipv6
+	ip neigh add $dstip6 lladdr $dstmac dev "$devdummy"  > /dev/null
+	check_err $?
+	ip neigh get $dstip6 dev "$devdummy" 2> /dev/null | grep -q "$dstmac"
+	check_err $?
+	ip neigh del $dstip6 lladdr $dstmac dev "$devdummy"  > /dev/null
+	check_err $?
+
+	# ipv6 proxy
+	ip neigh add proxy $dstip6 dev "$devdummy" > /dev/null
+	check_err $?
+	ip neigh get proxy $dstip6 dev "$devdummy" 2>/dev/null | grep -q "$dstip6"
+	check_err $?
+	ip neigh del proxy $dstip6 dev "$devdummy" > /dev/null
+	check_err $?
+
+	if [ $ret -ne 0 ];then
+		echo "FAIL: neigh get"
+		return 1
+	fi
+
+	echo "PASS: neigh get"
+}
+
 kci_test_rtnl()
 {
 	kci_add_dummy
@@ -1032,6 +1085,7 @@ kci_test_rtnl()
 	kci_test_ipsec
 	kci_test_ipsec_offload
 	kci_test_fdb_get
+	kci_test_neigh_get
 
 	kci_del_dummy
 }
-- 
cgit v1.2.3


From fdbaa0beb78b7c8847e261fe2c32816e9d1c54cc Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 19 Dec 2018 13:01:01 -0800
Subject: bpf: Ensure line_info.insn_off cannot point to insn with zero code

This patch rejects a line_info if the bpf insn code referred by
line_info.insn_off is 0. F.e. a broken userspace tool might generate
a line_info.insn_off that points to the second 8 bytes of a BPF_LD_IMM64.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e0e77ffeefb8..5c64281d566e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4980,6 +4980,14 @@ static int check_btf_line(struct bpf_verifier_env *env,
 			goto err_free;
 		}
 
+		if (!prog->insnsi[linfo[i].insn_off].code) {
+			verbose(env,
+				"Invalid insn code at line_info[%u].insn_off\n",
+				i);
+			err = -EINVAL;
+			goto err_free;
+		}
+
 		if (!btf_name_by_offset(btf, linfo[i].line_off) ||
 		    !btf_name_by_offset(btf, linfo[i].file_name_off)) {
 			verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i);
-- 
cgit v1.2.3


From e30f5640e32455e02ba08983ebe0b46054f1f6f0 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 19 Dec 2018 13:01:02 -0800
Subject: bpf: Add BPF_LD_IMM64 to the line_info test

This patch adds a BPF_LD_IMM64 case to the line_info test
to ensure the kernel rejects linfo_info.insn_off pointing
to the 2nd 8 bytes of the BPF_LD_IMM64.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_btf.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 8024b7d4c354..8bcd38010582 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -4253,6 +4253,33 @@ static struct prog_info_raw_test {
 	.expected_prog_load_failure = true,
 },
 
+{
+	.descr = "line_info (Zero bpf insn code)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8),	/* [2] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 2),			/* [3] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0unsigned long\0u64\0u64 a=1;\0return a;"),
+	.insns = {
+		BPF_LD_IMM64(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info_cnt = 0,
+	.line_info = {
+		BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+		BPF_LINE_INFO_ENC(1, 0, 0, 2, 9),
+		BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8),
+		BTF_END_RAW,
+	},
+	.line_info_rec_size = sizeof(struct bpf_line_info),
+	.nr_jited_ksyms = 1,
+	.err_str = "Invalid insn code at line_info[1]",
+	.expected_prog_load_failure = true,
+},
+
 {
 	.descr = "line_info (No subprog. zero tailing line_info",
 	.raw_types = {
-- 
cgit v1.2.3


From a32ed90be22aa565cf623da5a211b4a968dec6e0 Mon Sep 17 00:00:00 2001
From: Biao Huang <biao.huang@mediatek.com>
Date: Wed, 19 Dec 2018 15:22:40 +0800
Subject: net-next: dt-binding: dwmac-mediatek: remove fine-tune property

remove fine-tune property in device tree, modify
the corresponding description in dt-binding.

Signed-off-by: Biao Huang <biao.huang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../devicetree/bindings/net/mediatek-dwmac.txt     | 31 ++++++++--------------
 1 file changed, 11 insertions(+), 20 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/mediatek-dwmac.txt b/Documentation/devicetree/bindings/net/mediatek-dwmac.txt
index 4de479b4d44d..8a08621a5b54 100644
--- a/Documentation/devicetree/bindings/net/mediatek-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/mediatek-dwmac.txt
@@ -22,33 +22,25 @@ Required properties:
 
 Optional properties:
 - mediatek,tx-delay-ps: TX clock delay macro value. Default is 0.
-	It should be defined for rgmii/rgmii-rxid/mii interface.
+	It should be defined for RGMII/MII interface.
 - mediatek,rx-delay-ps: RX clock delay macro value. Default is 0.
-	It should be defined for rgmii/rgmii-txid/mii/rmii interface.
-Both delay properties need to be a multiple of 170 for fine-tune rgmii,
-range 0~31*170.
-Both delay properties need to be a multiple of 550 for coarse-tune rgmii,
-range 0~31*550.
-Both delay properties need to be a multiple of 550 for mii/rmii,
-range 0~31*550.
+	It should be defined for RGMII/MII/RMII interface.
+Both delay properties need to be a multiple of 170 for RGMII interface,
+or will round down. Range 0~31*170.
+Both delay properties need to be a multiple of 550 for MII/RMII interface,
+or will round down. Range 0~31*550.
 
-- mediatek,fine-tune: boolean property, if present indicates that fine delay
-	is selected for rgmii interface.
-	If present, tx-delay-ps/rx-delay-ps is 170+/-50ps per stage.
-	Else tx-delay-ps/rx-delay-ps of coarse delay macro is 0.55+/-0.2ns per stage.
-	This property do not apply to non-rgmii PHYs.
-	Only coarse-tune delay is supported for mii/rmii PHYs.
-- mediatek,rmii-rxc: boolean property, if present indicates that the rmii
+- mediatek,rmii-rxc: boolean property, if present indicates that the RMII
 	reference clock, which is from external PHYs, is connected to RXC pin
 	on MT2712 SoC.
 	Otherwise, is connected to TXC pin.
 - mediatek,txc-inverse: boolean property, if present indicates that
-	1. tx clock will be inversed in mii/rgmii case,
+	1. tx clock will be inversed in MII/RGMII case,
 	2. tx clock inside MAC will be inversed relative to reference clock
-	   which is from external PHYs in rmii case, and it rarely happen.
+	   which is from external PHYs in RMII case, and it rarely happen.
 - mediatek,rxc-inverse: boolean property, if present indicates that
-	1. rx clock will be inversed in mii/rgmii case.
-	2. reference clock will be inversed when arrived at MAC in rmii case.
+	1. rx clock will be inversed in MII/RGMII case.
+	2. reference clock will be inversed when arrived at MAC in RMII case.
 - assigned-clocks: mac_main and ptp_ref clocks
 - assigned-clock-parents: parent clocks of the assigned clocks
 
@@ -76,7 +68,6 @@ Example:
 		mediatek,pericfg = <&pericfg>;
 		mediatek,tx-delay-ps = <1530>;
 		mediatek,rx-delay-ps = <1530>;
-		mediatek,fine-tune;
 		mediatek,rmii-rxc;
 		mediatek,txc-inverse;
 		mediatek,rxc-inverse;
-- 
cgit v1.2.3


From 22a3a5403bbefd520e19bb251ce49ce705b1e5e4 Mon Sep 17 00:00:00 2001
From: Biao Huang <biao.huang@mediatek.com>
Date: Wed, 19 Dec 2018 15:22:41 +0800
Subject: net-next: stmmac: dwmac-mediatek: remove fine-tune property

1. remove fine-tune property and related setting to simplify
the timing adjustment flow.
2. set timing value according to the value from device tree,
and will not care whether PHY insert internal delay.

Signed-off-by: Biao Huang <biao.huang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/dwmac-mediatek.c   | 71 ++++++++--------------
 1 file changed, 24 insertions(+), 47 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index e400cbdc3419..bf2562995fc8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -44,7 +44,6 @@ struct mac_delay_struct {
 	u32 rx_delay;
 	bool tx_inv;
 	bool rx_inv;
-	bool fine_tune;
 };
 
 struct mediatek_dwmac_plat_data {
@@ -105,16 +104,28 @@ static int mt2712_set_interface(struct mediatek_dwmac_plat_data *plat)
 	return 0;
 }
 
-static void mt2712_delay_ps2stage(struct mac_delay_struct *mac_delay)
+static void mt2712_delay_ps2stage(struct mediatek_dwmac_plat_data *plat)
 {
-	if (mac_delay->fine_tune) {
-		/* 170ps per stage for fine tune delay macro circuit*/
-		mac_delay->tx_delay /= 170;
-		mac_delay->rx_delay /= 170;
-	} else {
-		/* 550ps per stage for coarse tune delay macro circuit*/
+	struct mac_delay_struct *mac_delay = &plat->mac_delay;
+
+	switch (plat->phy_mode) {
+	case PHY_INTERFACE_MODE_MII:
+	case PHY_INTERFACE_MODE_RMII:
+		/* 550ps per stage for MII/RMII */
 		mac_delay->tx_delay /= 550;
 		mac_delay->rx_delay /= 550;
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		/* 170ps per stage for RGMII */
+		mac_delay->tx_delay /= 170;
+		mac_delay->rx_delay /= 170;
+		break;
+	default:
+		dev_err(plat->dev, "phy interface not supported\n");
+		break;
 	}
 }
 
@@ -123,7 +134,7 @@ static int mt2712_set_delay(struct mediatek_dwmac_plat_data *plat)
 	struct mac_delay_struct *mac_delay = &plat->mac_delay;
 	u32 delay_val = 0, fine_val = 0;
 
-	mt2712_delay_ps2stage(mac_delay);
+	mt2712_delay_ps2stage(plat);
 
 	switch (plat->phy_mode) {
 	case PHY_INTERFACE_MODE_MII:
@@ -167,13 +178,10 @@ static int mt2712_set_delay(struct mediatek_dwmac_plat_data *plat)
 			fine_val = ETH_RMII_DLY_TX_INV;
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
-		/* the PHY is not responsible for inserting any internal
-		 * delay by itself in PHY_INTERFACE_MODE_RGMII case,
-		 * so Ethernet MAC will insert delays for both transmit
-		 * and receive path here.
-		 */
-		if (mac_delay->fine_tune)
-			fine_val = ETH_FINE_DLY_GTXC | ETH_FINE_DLY_RXC;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		fine_val = ETH_FINE_DLY_GTXC | ETH_FINE_DLY_RXC;
 
 		delay_val |= FIELD_PREP(ETH_DLY_GTXC_ENABLE, !!mac_delay->tx_delay);
 		delay_val |= FIELD_PREP(ETH_DLY_GTXC_STAGES, mac_delay->tx_delay);
@@ -183,36 +191,6 @@ static int mt2712_set_delay(struct mediatek_dwmac_plat_data *plat)
 		delay_val |= FIELD_PREP(ETH_DLY_RXC_STAGES, mac_delay->rx_delay);
 		delay_val |= FIELD_PREP(ETH_DLY_RXC_INV, mac_delay->rx_inv);
 		break;
-	case PHY_INTERFACE_MODE_RGMII_TXID:
-		/* the PHY should insert an internal delay for the transmit
-		 * path in PHY_INTERFACE_MODE_RGMII_TXID case,
-		 * so Ethernet MAC will insert the delay for receive path here.
-		 */
-		if (mac_delay->fine_tune)
-			fine_val = ETH_FINE_DLY_RXC;
-
-		delay_val |= FIELD_PREP(ETH_DLY_RXC_ENABLE, !!mac_delay->rx_delay);
-		delay_val |= FIELD_PREP(ETH_DLY_RXC_STAGES, mac_delay->rx_delay);
-		delay_val |= FIELD_PREP(ETH_DLY_RXC_INV, mac_delay->rx_inv);
-		break;
-	case PHY_INTERFACE_MODE_RGMII_RXID:
-		/* the PHY should insert an internal delay for the receive
-		 * path in PHY_INTERFACE_MODE_RGMII_RXID case,
-		 * so Ethernet MAC will insert the delay for transmit path here.
-		 */
-		if (mac_delay->fine_tune)
-			fine_val = ETH_FINE_DLY_GTXC;
-
-		delay_val |= FIELD_PREP(ETH_DLY_GTXC_ENABLE, !!mac_delay->tx_delay);
-		delay_val |= FIELD_PREP(ETH_DLY_GTXC_STAGES, mac_delay->tx_delay);
-		delay_val |= FIELD_PREP(ETH_DLY_GTXC_INV, mac_delay->tx_inv);
-		break;
-	case PHY_INTERFACE_MODE_RGMII_ID:
-		/* the PHY should insert internal delays for both transmit
-		 * and receive path in PHY_INTERFACE_MODE_RGMII_RXID case,
-		 * so Ethernet MAC will NOT insert any delay here.
-		 */
-		break;
 	default:
 		dev_err(plat->dev, "phy interface not supported\n");
 		return -EINVAL;
@@ -270,7 +248,6 @@ static int mediatek_dwmac_config_dt(struct mediatek_dwmac_plat_data *plat)
 
 	mac_delay->tx_inv = of_property_read_bool(plat->np, "mediatek,txc-inverse");
 	mac_delay->rx_inv = of_property_read_bool(plat->np, "mediatek,rxc-inverse");
-	mac_delay->fine_tune = of_property_read_bool(plat->np, "mediatek,fine-tune");
 	plat->rmii_rxc = of_property_read_bool(plat->np, "mediatek,rmii-rxc");
 
 	return 0;
-- 
cgit v1.2.3


From 9c7f37e5ca14f5b04894b1b699a9903885cdafa6 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 19 Dec 2018 18:28:54 +0100
Subject: net: dsa: mv88e6xxx: Add missing watchdog ops for 6320 family

The 6320 family of switches uses the same watchdog registers as the
6390.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index b603f8d6ee3e..0f749d1ef53b 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3478,6 +3478,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.stats_get_stats = mv88e6320_stats_get_stats,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
+	.watchdog_ops = &mv88e6390_watchdog_ops,
 	.mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu,
 	.pot_clear = mv88e6xxx_g2_pot_clear,
 	.reset = mv88e6352_g1_reset,
@@ -3520,6 +3521,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.stats_get_stats = mv88e6320_stats_get_stats,
 	.set_cpu_port = mv88e6095_g1_set_cpu_port,
 	.set_egress_port = mv88e6095_g1_set_egress_port,
+	.watchdog_ops = &mv88e6390_watchdog_ops,
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6185_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
-- 
cgit v1.2.3


From 3f2eadb10886340f4d67fe683c2e53b4df005461 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Wed, 19 Dec 2018 10:20:09 -0800
Subject: selftests: net: refactor reuseport_addr_any test

This patch refactors reuseport_add_any selftest a bit:
- makes it more modular (eliminates several copy/pasted blocks);
- skips DCCP tests if DCCP is not supported

V2: added "Signed-off-by" tag.

Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/reuseport_addr_any.c | 121 +++++++----------------
 1 file changed, 38 insertions(+), 83 deletions(-)

diff --git a/tools/testing/selftests/net/reuseport_addr_any.c b/tools/testing/selftests/net/reuseport_addr_any.c
index 4ac3e24b7cfc..6f54d425dba9 100644
--- a/tools/testing/selftests/net/reuseport_addr_any.c
+++ b/tools/testing/selftests/net/reuseport_addr_any.c
@@ -203,7 +203,9 @@ static void test(int *rcv_fds, int count, int family, int proto, int fd)
 	close(epfd);
 }
 
-int main(void)
+
+static void run_one_test(int fam_send, int fam_rcv, int proto,
+			 const char *addr_str)
 {
 	/* Below we test that a socket listening on a specific address
 	 * is always selected in preference over a socket listening
@@ -214,95 +216,48 @@ int main(void)
 	 */
 	int rcv_fds[10], i;
 
-	fprintf(stderr, "---- UDP IPv4 ----\n");
-	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 2, 2, NULL);
-	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds + 4, 1, IP4_ADDR);
-	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds + 5, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 7, 2, NULL);
-	test(rcv_fds, 9, AF_INET, SOCK_DGRAM, rcv_fds[4]);
-	for (i = 0; i < 9; ++i)
-		close(rcv_fds[i]);
-
-	fprintf(stderr, "---- UDP IPv6 ----\n");
-	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 2, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 4, 1, IP6_ADDR);
-	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds + 5, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 7, 2, NULL);
-	test(rcv_fds, 9, AF_INET6, SOCK_DGRAM, rcv_fds[4]);
-	for (i = 0; i < 9; ++i)
-		close(rcv_fds[i]);
-
-	fprintf(stderr, "---- UDP IPv4 mapped to IPv6 ----\n");
-	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 2, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 4, 1, IP4_MAPPED6);
-	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds + 5, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds + 7, 2, NULL);
-	test(rcv_fds, 9, AF_INET, SOCK_DGRAM, rcv_fds[4]);
-	for (i = 0; i < 9; ++i)
-		close(rcv_fds[i]);
-
-	fprintf(stderr, "---- TCP IPv4 ----\n");
-	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 2, 2, NULL);
-	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds + 4, 1, IP4_ADDR);
-	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds + 5, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 7, 2, NULL);
-	test(rcv_fds, 9, AF_INET, SOCK_STREAM, rcv_fds[4]);
+	build_rcv_fd(AF_INET, proto, rcv_fds, 2, NULL);
+	build_rcv_fd(AF_INET6, proto, rcv_fds + 2, 2, NULL);
+	build_rcv_fd(fam_rcv, proto, rcv_fds + 4, 1, addr_str);
+	build_rcv_fd(AF_INET, proto, rcv_fds + 5, 2, NULL);
+	build_rcv_fd(AF_INET6, proto, rcv_fds + 7, 2, NULL);
+	test(rcv_fds, 9, fam_send, proto, rcv_fds[4]);
 	for (i = 0; i < 9; ++i)
 		close(rcv_fds[i]);
+	fprintf(stderr, "pass\n");
+}
 
-	fprintf(stderr, "---- TCP IPv6 ----\n");
-	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 2, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 4, 1, IP6_ADDR);
-	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds + 5, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 7, 2, NULL);
-	test(rcv_fds, 9, AF_INET6, SOCK_STREAM, rcv_fds[4]);
-	for (i = 0; i < 9; ++i)
-		close(rcv_fds[i]);
+static void test_proto(int proto, const char *proto_str)
+{
+	if (proto == SOCK_DCCP) {
+		int test_fd;
+
+		test_fd = socket(AF_INET, proto, 0);
+		if (test_fd < 0) {
+			if (errno == ESOCKTNOSUPPORT) {
+				fprintf(stderr, "DCCP not supported: skipping DCCP tests\n");
+				return;
+			} else
+				error(1, errno, "failed to create a DCCP socket");
+		}
+		close(test_fd);
+	}
 
-	fprintf(stderr, "---- TCP IPv4 mapped to IPv6 ----\n");
-	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 2, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 4, 1, IP4_MAPPED6);
-	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds + 5, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds + 7, 2, NULL);
-	test(rcv_fds, 9, AF_INET, SOCK_STREAM, rcv_fds[4]);
-	for (i = 0; i < 9; ++i)
-		close(rcv_fds[i]);
+	fprintf(stderr, "%s IPv4 ... ", proto_str);
+	run_one_test(AF_INET, AF_INET, proto, IP4_ADDR);
 
-	fprintf(stderr, "---- DCCP IPv4 ----\n");
-	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 2, 2, NULL);
-	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds + 4, 1, IP4_ADDR);
-	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds + 5, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 7, 2, NULL);
-	test(rcv_fds, 9, AF_INET, SOCK_DCCP, rcv_fds[4]);
-	for (i = 0; i < 9; ++i)
-		close(rcv_fds[i]);
+	fprintf(stderr, "%s IPv6 ... ", proto_str);
+	run_one_test(AF_INET6, AF_INET6, proto, IP6_ADDR);
 
-	fprintf(stderr, "---- DCCP IPv6 ----\n");
-	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 2, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 4, 1, IP6_ADDR);
-	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds + 5, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 7, 2, NULL);
-	test(rcv_fds, 9, AF_INET6, SOCK_DCCP, rcv_fds[4]);
-	for (i = 0; i < 9; ++i)
-		close(rcv_fds[i]);
+	fprintf(stderr, "%s IPv4 mapped to IPv6 ... ", proto_str);
+	run_one_test(AF_INET, AF_INET6, proto, IP4_MAPPED6);
+}
 
-	fprintf(stderr, "---- DCCP IPv4 mapped to IPv6 ----\n");
-	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 2, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 4, 1, IP4_MAPPED6);
-	build_rcv_fd(AF_INET, SOCK_DCCP, rcv_fds + 5, 2, NULL);
-	build_rcv_fd(AF_INET6, SOCK_DCCP, rcv_fds + 7, 2, NULL);
-	test(rcv_fds, 9, AF_INET, SOCK_DCCP, rcv_fds[4]);
-	for (i = 0; i < 9; ++i)
-		close(rcv_fds[i]);
+int main(void)
+{
+	test_proto(SOCK_DGRAM, "UDP");
+	test_proto(SOCK_STREAM, "TCP");
+	test_proto(SOCK_DCCP, "DCCP");
 
 	fprintf(stderr, "SUCCESS\n");
 	return 0;
-- 
cgit v1.2.3


From 9df95e8ec568f98d89fe2c72342714296ac6ce27 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 19 Dec 2018 13:30:54 -0800
Subject: bpf: sparc64: Enable sparc64 jit to provide bpf_line_info

This patch enables sparc64's bpf_int_jit_compile() to provide
bpf_line_info by calling bpf_prog_fill_jited_linfo().

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/sparc/net/bpf_jit_comp_64.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 5fda4f7bf15d..65428e79b2f3 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -1575,6 +1575,7 @@ skip_init_ctx:
 	prog->jited_len = image_size;
 
 	if (!prog->is_func || extra_pass) {
+		bpf_prog_fill_jited_linfo(prog, ctx.offset);
 out_off:
 		kfree(ctx.offset);
 		kfree(jit_data);
-- 
cgit v1.2.3


From 754d5da63145852736f34cfc762164f5d8d6537b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 19 Dec 2018 15:53:22 -0800
Subject: neighbor: Initialize protocol when new pneigh_entry are created

pneigh_lookup uses kmalloc versus kzalloc when new entries are allocated.
Given that the newly added protocol field needs to be initialized.

Fixes: df9b0e30d44c ("neighbor: Add protocol attribute")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 43687c9abe1d..d9fa101b0e41 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -725,6 +725,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
 	if (!n)
 		goto out;
 
+	n->protocol = 0;
 	write_pnet(&n->net, net);
 	memcpy(n->key, pkey, key_len);
 	n->dev = dev;
-- 
cgit v1.2.3


From cc4dc97ffc69c253d5aa2c0068545ed6c8bc0bde Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Mon, 3 Dec 2018 08:31:45 -0500
Subject: cw1200: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/st/cw1200/debug.c | 32 ++++----------------------------
 1 file changed, 4 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/st/cw1200/debug.c b/drivers/net/wireless/st/cw1200/debug.c
index 295cb1a29f25..2231ba08bc1f 100644
--- a/drivers/net/wireless/st/cw1200/debug.c
+++ b/drivers/net/wireless/st/cw1200/debug.c
@@ -289,19 +289,7 @@ static int cw1200_status_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int cw1200_status_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, &cw1200_status_show,
-		inode->i_private);
-}
-
-static const struct file_operations fops_status = {
-	.open = cw1200_status_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-	.owner = THIS_MODULE,
-};
+DEFINE_SHOW_ATTRIBUTE(cw1200_status);
 
 static int cw1200_counters_show(struct seq_file *seq, void *v)
 {
@@ -345,19 +333,7 @@ static int cw1200_counters_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int cw1200_counters_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, &cw1200_counters_show,
-		inode->i_private);
-}
-
-static const struct file_operations fops_counters = {
-	.open = cw1200_counters_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-	.owner = THIS_MODULE,
-};
+DEFINE_SHOW_ATTRIBUTE(cw1200_counters);
 
 static ssize_t cw1200_wsm_dumps(struct file *file,
 	const char __user *user_buf, size_t count, loff_t *ppos)
@@ -399,11 +375,11 @@ int cw1200_debug_init(struct cw1200_common *priv)
 		goto err;
 
 	if (!debugfs_create_file("status", 0400, d->debugfs_phy,
-				 priv, &fops_status))
+				 priv, &cw1200_status_fops))
 		goto err;
 
 	if (!debugfs_create_file("counters", 0400, d->debugfs_phy,
-				 priv, &fops_counters))
+				 priv, &cw1200_counters_fops))
 		goto err;
 
 	if (!debugfs_create_file("wsm_dumps", 0200, d->debugfs_phy,
-- 
cgit v1.2.3


From 8c892df41500469729e0d662816300196e4f463d Mon Sep 17 00:00:00 2001
From: Stijn Tintel <stijn@linux-ipv6.be>
Date: Tue, 4 Dec 2018 20:29:05 +0200
Subject: brcmfmac: fix roamoff=1 modparam

When the update_connect_param callback is set, nl80211 expects the flag
WIPHY_FLAG_SUPPORTS_FW_ROAM to be set as well. However, this flag is
only set when modparam roamoff=0, while the callback is set
unconditionally. Since commit 7f9a3e150ec7 this causes a warning in
wiphy_register, which breaks brcmfmac.

Disable the update_connect_param callback when roamoff=0 to fix this.

Fixes: 7f9a3e150ec7 ("nl80211: Update ERP info using NL80211_CMD_UPDATE_CONNECT_PARAMS")
Cc: Stable <stable@vger.kernel.org> # 4.19+
Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Signed-off-by: Stijn Tintel <stijn@linux-ipv6.be>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 11 +++++++++--
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h |  2 +-
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c     |  2 +-
 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 648fdeabce02..f88b42f185ac 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -5196,10 +5196,17 @@ static struct cfg80211_ops brcmf_cfg80211_ops = {
 	.del_pmk = brcmf_cfg80211_del_pmk,
 };
 
-struct cfg80211_ops *brcmf_cfg80211_get_ops(void)
+struct cfg80211_ops *brcmf_cfg80211_get_ops(struct brcmf_mp_device *settings)
 {
-	return kmemdup(&brcmf_cfg80211_ops, sizeof(brcmf_cfg80211_ops),
+	struct cfg80211_ops *ops;
+
+	ops = kmemdup(&brcmf_cfg80211_ops, sizeof(brcmf_cfg80211_ops),
 		       GFP_KERNEL);
+
+	if (ops && settings->roamoff)
+		ops->update_connect_params = NULL;
+
+	return ops;
 }
 
 struct brcmf_cfg80211_vif *brcmf_alloc_vif(struct brcmf_cfg80211_info *cfg,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
index a4aec0004e4f..9a6287f084a9 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
@@ -404,7 +404,7 @@ struct brcmf_cfg80211_info *brcmf_cfg80211_attach(struct brcmf_pub *drvr,
 void brcmf_cfg80211_detach(struct brcmf_cfg80211_info *cfg);
 s32 brcmf_cfg80211_up(struct net_device *ndev);
 s32 brcmf_cfg80211_down(struct net_device *ndev);
-struct cfg80211_ops *brcmf_cfg80211_get_ops(void);
+struct cfg80211_ops *brcmf_cfg80211_get_ops(struct brcmf_mp_device *settings);
 enum nl80211_iftype brcmf_cfg80211_get_iftype(struct brcmf_if *ifp);
 
 struct brcmf_cfg80211_vif *brcmf_alloc_vif(struct brcmf_cfg80211_info *cfg,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index b1f702faff4f..860a4372cb56 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -1130,7 +1130,7 @@ int brcmf_attach(struct device *dev, struct brcmf_mp_device *settings)
 
 	brcmf_dbg(TRACE, "Enter\n");
 
-	ops = brcmf_cfg80211_get_ops();
+	ops = brcmf_cfg80211_get_ops(settings);
 	if (!ops)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From 861cb5eb467f5e38dce1aabe4e8db379255bd89b Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Wed, 12 Dec 2018 20:20:06 +0100
Subject: brcmfmac: Fix access point mode

Since commit 1204aa17f3b4 ("brcmfmac: set WIPHY_FLAG_HAVE_AP_SME flag")
the Raspberry Pi 3 A+ (BCM43455) isn't able to operate in AP mode with
hostapd (device_ap_sme=1 use_monitor=0):

brcmfmac: brcmf_cfg80211_stop_ap: setting AP mode failed -52

So add the missing mgmt_stypes for AP mode to fix this.

Fixes: 1204aa17f3b4 ("brcmfmac: set WIPHY_FLAG_HAVE_AP_SME flag")
Suggested-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index f88b42f185ac..35301237d435 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -6316,6 +6316,16 @@ brcmf_txrx_stypes[NUM_NL80211_IFTYPES] = {
 		.tx = 0xffff,
 		.rx = BIT(IEEE80211_STYPE_ACTION >> 4) |
 		      BIT(IEEE80211_STYPE_PROBE_REQ >> 4)
+	},
+	[NL80211_IFTYPE_AP] = {
+		.tx = 0xffff,
+		.rx = BIT(IEEE80211_STYPE_ASSOC_REQ >> 4) |
+		      BIT(IEEE80211_STYPE_REASSOC_REQ >> 4) |
+		      BIT(IEEE80211_STYPE_PROBE_REQ >> 4) |
+		      BIT(IEEE80211_STYPE_DISASSOC >> 4) |
+		      BIT(IEEE80211_STYPE_AUTH >> 4) |
+		      BIT(IEEE80211_STYPE_DEAUTH >> 4) |
+		      BIT(IEEE80211_STYPE_ACTION >> 4)
 	}
 };
 
-- 
cgit v1.2.3


From 4f68ef64cd7feb1220232bd8f501d8aad340a099 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 14 Dec 2018 11:55:21 +0800
Subject: cw1200: Fix concurrency use-after-free bugs in cw1200_hw_scan()

The function cw1200_bss_info_changed() and cw1200_hw_scan() can be
concurrently executed.
The two functions both access a possible shared variable "frame.skb".

This shared variable is freed by dev_kfree_skb() in cw1200_upload_beacon(),
which is called by cw1200_bss_info_changed(). The free operation is
protected by a mutex lock "priv->conf_mutex" in cw1200_bss_info_changed().

In cw1200_hw_scan(), this shared variable is accessed without the
protection of the mutex lock "priv->conf_mutex".
Thus, concurrency use-after-free bugs may occur.

To fix these bugs, the original calls to mutex_lock(&priv->conf_mutex) and
mutex_unlock(&priv->conf_mutex) are moved to the places, which can
protect the accesses to the shared variable.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/st/cw1200/scan.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/st/cw1200/scan.c b/drivers/net/wireless/st/cw1200/scan.c
index 67213f11acbd..0a9eac93dd01 100644
--- a/drivers/net/wireless/st/cw1200/scan.c
+++ b/drivers/net/wireless/st/cw1200/scan.c
@@ -78,6 +78,10 @@ int cw1200_hw_scan(struct ieee80211_hw *hw,
 	if (req->n_ssids > WSM_SCAN_MAX_NUM_OF_SSIDS)
 		return -EINVAL;
 
+	/* will be unlocked in cw1200_scan_work() */
+	down(&priv->scan.lock);
+	mutex_lock(&priv->conf_mutex);
+
 	frame.skb = ieee80211_probereq_get(hw, priv->vif->addr, NULL, 0,
 		req->ie_len);
 	if (!frame.skb)
@@ -86,19 +90,15 @@ int cw1200_hw_scan(struct ieee80211_hw *hw,
 	if (req->ie_len)
 		skb_put_data(frame.skb, req->ie, req->ie_len);
 
-	/* will be unlocked in cw1200_scan_work() */
-	down(&priv->scan.lock);
-	mutex_lock(&priv->conf_mutex);
-
 	ret = wsm_set_template_frame(priv, &frame);
 	if (!ret) {
 		/* Host want to be the probe responder. */
 		ret = wsm_set_probe_responder(priv, true);
 	}
 	if (ret) {
+		dev_kfree_skb(frame.skb);
 		mutex_unlock(&priv->conf_mutex);
 		up(&priv->scan.lock);
-		dev_kfree_skb(frame.skb);
 		return ret;
 	}
 
@@ -120,10 +120,9 @@ int cw1200_hw_scan(struct ieee80211_hw *hw,
 		++priv->scan.n_ssids;
 	}
 
-	mutex_unlock(&priv->conf_mutex);
-
 	if (frame.skb)
 		dev_kfree_skb(frame.skb);
+	mutex_unlock(&priv->conf_mutex);
 	queue_work(priv->workqueue, &priv->scan.work);
 	return 0;
 }
-- 
cgit v1.2.3


From 90a8c74a8d7b0f3fdceadadb155da137e3b157cf Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 19 Dec 2018 11:00:13 +0800
Subject: ipw2x00: cleanup dead code

Fix smatch warning:

drivers/net/wireless/intel/ipw2x00/ipw2100.c:5606
 shim__set_security() warn: always true condition '(sec->active_key <= 3) => (0-3 <= 3)'
drivers/net/wireless/intel/ipw2x00/ipw2200.c:10725
 shim__set_security() warn: always true condition '(sec->active_key <= 3) => (0-3 <= 3)'

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/ipw2x00/ipw2100.c | 8 ++------
 drivers/net/wireless/intel/ipw2x00/ipw2200.c | 7 ++-----
 2 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index 910db46db6a1..b58ef8dd1e47 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -5603,12 +5603,8 @@ static void shim__set_security(struct net_device *dev,
 
 	if ((sec->flags & SEC_ACTIVE_KEY) &&
 	    priv->ieee->sec.active_key != sec->active_key) {
-		if (sec->active_key <= 3) {
-			priv->ieee->sec.active_key = sec->active_key;
-			priv->ieee->sec.flags |= SEC_ACTIVE_KEY;
-		} else
-			priv->ieee->sec.flags &= ~SEC_ACTIVE_KEY;
-
+		priv->ieee->sec.active_key = sec->active_key;
+		priv->ieee->sec.flags |= SEC_ACTIVE_KEY;
 		priv->status |= STATUS_SECURITY_UPDATED;
 	}
 
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
index bbdca13c5a9f..fa400f92d7e2 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
@@ -10722,11 +10722,8 @@ static void shim__set_security(struct net_device *dev,
 	}
 
 	if (sec->flags & SEC_ACTIVE_KEY) {
-		if (sec->active_key <= 3) {
-			priv->ieee->sec.active_key = sec->active_key;
-			priv->ieee->sec.flags |= SEC_ACTIVE_KEY;
-		} else
-			priv->ieee->sec.flags &= ~SEC_ACTIVE_KEY;
+		priv->ieee->sec.active_key = sec->active_key;
+		priv->ieee->sec.flags |= SEC_ACTIVE_KEY;
 		priv->status |= STATUS_SECURITY_UPDATED;
 	} else
 		priv->ieee->sec.flags &= ~SEC_ACTIVE_KEY;
-- 
cgit v1.2.3


From dabb0983349d6320197b88eeb9bb91d3fa0ed855 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 20 Aug 2018 10:34:04 +0300
Subject: iwlwifi: pcie: use iwl_tx_cmd_gen2 and not iwl_tx_cmd

When building AMSDU for gen2, code uses iwl_tx_cmd. The only
updated field is len, which is in the same location, so it
is not a bug. However, it is a bit confusing and error prone,
so change it.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 16e8c3eb09b8..156ca1b1f621 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -238,7 +238,7 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
 {
 #ifdef CONFIG_INET
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
+	struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload;
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room;
 	unsigned int mss = skb_shinfo(skb)->gso_size;
-- 
cgit v1.2.3


From 70dc179dd98622eda9809d02fa73b708d60e5e23 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Thu, 23 Aug 2018 12:10:01 +0300
Subject: iwlwifi: mvm: remove dead code

In iwl_mvm_tx_skb_non_sta(), in case of managed interface,
the AP station was supposed to be used for multicast frames
instead of the auxiliary station to avoid frames possibly
sent to an absent P2P GO. However, when moving to DQA mode,
this was broken as no valid queue was assigned. This is fixed
by a recent patch that directs all non-offchannel traffic to
ap station earlier in the TX path. However, the broken, and
now dead code, remained. Remove it.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 09cabf336310..7a9ec6810395 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -763,12 +763,6 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 							   hdr->frame_control);
 			if (queue < 0)
 				return -1;
-		} else if (info.control.vif->type == NL80211_IFTYPE_STATION &&
-			   is_multicast_ether_addr(hdr->addr1)) {
-			u8 ap_sta_id = READ_ONCE(mvmvif->ap_sta_id);
-
-			if (ap_sta_id != IWL_MVM_INVALID_STA)
-				sta_id = ap_sta_id;
 		} else if (info.control.vif->type == NL80211_IFTYPE_MONITOR) {
 			queue = mvm->snif_queue;
 			sta_id = mvm->snif_sta.sta_id;
-- 
cgit v1.2.3


From a124caf8f3166cf1488bf606ccf70469ac76a9de Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Thu, 23 Aug 2018 11:03:17 +0300
Subject: iwlwifi: mvm: remove pointless NULL assignment

Assigning mvmsta to be NULL when we are about to exit the
function is pointless. Remove it. Move the variable declaration
to the scope it is used.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 7a9ec6810395..2738cd307765 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1472,7 +1472,6 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 		iwl_mvm_get_agg_status(mvm, tx_resp);
 	u32 status = le16_to_cpu(agg_status->status);
 	u16 ssn = iwl_mvm_get_scd_ssn(mvm, tx_resp);
-	struct iwl_mvm_sta *mvmsta;
 	struct sk_buff_head skbs;
 	u8 skb_freed = 0;
 	u8 lq_color;
@@ -1620,7 +1619,7 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 		goto out;
 
 	if (!IS_ERR(sta)) {
-		mvmsta = iwl_mvm_sta_from_mac80211(sta);
+		struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
 
 		iwl_mvm_tx_airtime(mvm, mvmsta,
 				   le16_to_cpu(tx_resp->wireless_media_time));
@@ -1683,10 +1682,7 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 			mvmsta->next_status_eosp = false;
 			ieee80211_sta_eosp(sta);
 		}
-	} else {
-		mvmsta = NULL;
 	}
-
 out:
 	rcu_read_unlock();
 }
-- 
cgit v1.2.3


From 4120e4a119ed8c8e28d20524713ab2e3df67a34d Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Thu, 23 Aug 2018 13:40:16 +0300
Subject: iwlwifi: mvm: cleanup iwl_mvm_tx_skb_non_sta

Make the coupling of station id and queue id clear. Group code
together. Remove outdated comment. Never use an undefined hw
queue as given from mac80211.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 42 ++++++++++++-----------------
 1 file changed, 17 insertions(+), 25 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 2738cd307765..4ebfd41dadc9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -708,22 +708,12 @@ out:
 int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
-	struct ieee80211_tx_info *skb_info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_tx_info info;
 	struct iwl_device_cmd *dev_cmd;
 	u8 sta_id;
 	int hdrlen = ieee80211_hdrlen(hdr->frame_control);
 	__le16 fc = hdr->frame_control;
-	int queue;
-
-	/* IWL_MVM_OFFCHANNEL_QUEUE is used for ROC packets that can be used
-	 * in 2 different types of vifs, P2P & STATION. P2P uses the offchannel
-	 * queue. STATION (HS2.0) uses the auxiliary context of the FW,
-	 * and hence needs to be sent on the aux queue
-	 */
-	if (skb_info->hw_queue == IWL_MVM_OFFCHANNEL_QUEUE &&
-	    skb_info->control.vif->type == NL80211_IFTYPE_STATION)
-		skb_info->hw_queue = mvm->aux_queue;
+	int queue = -1;
 
 	memcpy(&info, skb->cb, sizeof(info));
 
@@ -735,18 +725,6 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 			  info.hw_queue != info.control.vif->cab_queue)))
 		return -1;
 
-	queue = info.hw_queue;
-
-	/*
-	 * If the interface on which the frame is sent is the P2P_DEVICE
-	 * or an AP/GO interface use the broadcast station associated
-	 * with it; otherwise if the interface is a managed interface
-	 * use the AP station associated with it for multicast traffic
-	 * (this is not possible for unicast packets as a TLDS discovery
-	 * response are sent without a station entry); otherwise use the
-	 * AUX station.
-	 */
-	sta_id = mvm->aux_sta.sta_id;
 	if (info.control.vif) {
 		struct iwl_mvm_vif *mvmvif =
 			iwl_mvm_vif_from_mac80211(info.control.vif);
@@ -761,14 +739,28 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 
 			queue = iwl_mvm_get_ctrl_vif_queue(mvm, &info,
 							   hdr->frame_control);
-			if (queue < 0)
-				return -1;
+
 		} else if (info.control.vif->type == NL80211_IFTYPE_MONITOR) {
 			queue = mvm->snif_queue;
 			sta_id = mvm->snif_sta.sta_id;
+		} else if (info.control.vif->type == NL80211_IFTYPE_STATION &&
+			   info.hw_queue == IWL_MVM_OFFCHANNEL_QUEUE) {
+			/*
+			 * IWL_MVM_OFFCHANNEL_QUEUE is used for ROC packets
+			 * that can be used in 2 different types of vifs, P2P &
+			 * STATION.
+			 * P2P uses the offchannel queue.
+			 * STATION (HS2.0) uses the auxiliary context of the FW,
+			 * and hence needs to be sent on the aux queue.
+			 */
+			sta_id = mvm->aux_sta.sta_id;
+			queue = mvm->aux_queue;
 		}
 	}
 
+	if (queue < 0)
+		return -1;
+
 	if (unlikely(ieee80211_is_probe_resp(fc)))
 		iwl_mvm_probe_resp_set_noa(mvm, skb);
 
-- 
cgit v1.2.3


From 189b8d441b0f7825f0b4278851c52afaa0515ed2 Mon Sep 17 00:00:00 2001
From: Naftali Goldstein <naftali.goldstein@intel.com>
Date: Wed, 22 Aug 2018 12:18:19 +0300
Subject: iwlwifi: mvm: fix setting HE ppe FW config

The FW expects to get the ppe value for each NSS-BW pair in the same
format as in the he phy capabilities IE, which means that a value of 0
implies ppe should be used for BPSK (mcs 0). If there are no PPE
thresholds in the IE, or if for some NSS-RU pair there's no threshold
set for it (this could happen because it's a variable-sized field), it
means no PPE should not be used for that pair, so the value sent to FW
should be 7 which corresponds to "none".

Fixes: 514c30696fbc ("iwlwifi: add support for IEEE802.11ax")
Signed-off-by: Naftali Goldstein <naftali.goldstein@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/mac.h   | 2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 8 +++++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
index 2c9e40eedef5..7a3f7b7e6358 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
@@ -443,7 +443,7 @@ struct iwl_he_backoff_conf {
  * Support for Nss x BW (or RU) matrix:
  *	(0=SISO, 1=MIMO2) x (0-20MHz, 1-40MHz, 2-80MHz, 3-160MHz)
  * Each entry contains 2 QAM thresholds for 8us and 16us:
- *	0=BPSK, 1=QPSK, 2=16QAM, 3=64QAM, 4=256QAM, 5=1024QAM, 6/7=RES
+ *	0=BPSK, 1=QPSK, 2=16QAM, 3=64QAM, 4=256QAM, 5=1024QAM, 6=RES, 7=NONE
  * i.e. QAM_th1 < QAM_th2 such if TX uses QAM_tx:
  *	QAM_tx < QAM_th1            --> PPE=0us
  *	QAM_th1 <= QAM_tx < QAM_th2 --> PPE=8us
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 65c225a54076..99a0dafde382 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -2023,7 +2023,13 @@ static void iwl_mvm_cfg_he_sta(struct iwl_mvm *mvm,
 	if (sta->he_cap.he_cap_elem.mac_cap_info[4] & IEEE80211_HE_MAC_CAP4_BQR)
 		sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_BQR_SUPP);
 
-	/* If PPE Thresholds exist, parse them into a FW-familiar format */
+	/*
+	 * Initialize the PPE thresholds to "None" (7), as described in Table
+	 * 9-262ac of 80211.ax/D3.0.
+	 */
+	memset(&sta_ctxt_cmd.pkt_ext, 7, sizeof(sta_ctxt_cmd.pkt_ext));
+
+	/* If PPE Thresholds exist, parse them into a FW-familiar format. */
 	if (sta->he_cap.he_cap_elem.phy_cap_info[6] &
 	    IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) {
 		u8 nss = (sta->he_cap.ppe_thres[0] &
-- 
cgit v1.2.3


From aca432f06b8a60a92b27fb46e6518a19b28ca93f Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Mon, 27 Aug 2018 13:02:19 +0300
Subject: iwlwifi: make MVM and DVM depend on MAC80211

It's not the iwlwifi module that depends on mac80211, but iwlmvm and
iwldvm.  To reflect this better, make MVM and DVM Kconfig options
depend on MAC80211 instead.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/Kconfig | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig
index e5a2fc738ac3..491ca3c8b43c 100644
--- a/drivers/net/wireless/intel/iwlwifi/Kconfig
+++ b/drivers/net/wireless/intel/iwlwifi/Kconfig
@@ -1,6 +1,6 @@
 config IWLWIFI
 	tristate "Intel Wireless WiFi Next Gen AGN - Wireless-N/Advanced-N/Ultimate-N (iwlwifi) "
-	depends on PCI && MAC80211 && HAS_IOMEM
+	depends on PCI && HAS_IOMEM
 	select FW_LOADER
 	---help---
 	  Select to build the driver supporting the:
@@ -53,6 +53,7 @@ config IWLWIFI_LEDS
 
 config IWLDVM
 	tristate "Intel Wireless WiFi DVM Firmware support"
+	depends on MAC80211
 	help
 	  This is the driver that supports the DVM firmware. The list
 	  of the devices that use this firmware is available here:
@@ -61,6 +62,7 @@ config IWLDVM
 config IWLMVM
 	tristate "Intel Wireless WiFi MVM Firmware support"
 	select WANT_DEV_COREDUMP
+	depends on MAC80211
 	help
 	  This is the driver that supports the MVM firmware. The list
 	  of the devices that use this firmware is available here:
-- 
cgit v1.2.3


From 57a3a454f30368f9b52ef406feff09571448e84e Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Mon, 20 Aug 2018 16:07:26 +0300
Subject: iwlwifi: split HE capabilities between AP and STA

HE capabilities differ between AP and STA.

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 289 ++++++++++++++-------
 1 file changed, 188 insertions(+), 101 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 96e101d79662..173ade96f119 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -465,101 +465,184 @@ static void iwl_init_vht_hw_capab(const struct iwl_cfg *cfg,
 	vht_cap->vht_mcs.tx_mcs_map = vht_cap->vht_mcs.rx_mcs_map;
 }
 
-static struct ieee80211_sband_iftype_data iwl_he_capa = {
-	.types_mask = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP),
-	.he_cap = {
-		.has_he = true,
-		.he_cap_elem = {
-			.mac_cap_info[0] =
-				IEEE80211_HE_MAC_CAP0_HTC_HE |
-				IEEE80211_HE_MAC_CAP0_TWT_REQ,
-			.mac_cap_info[1] =
-				IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
-				IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8,
-			.mac_cap_info[2] =
-				IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP |
-				IEEE80211_HE_MAC_CAP2_MU_CASCADING |
-				IEEE80211_HE_MAC_CAP2_ACK_EN,
-			.mac_cap_info[3] =
-				IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
-				IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2,
-			.mac_cap_info[4] =
-				IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU |
-				IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39,
-			.mac_cap_info[5] =
-				IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 |
-				IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 |
-				IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU,
-			.phy_cap_info[0] =
-				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G |
-				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
-				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G,
-			.phy_cap_info[1] =
-				IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK |
-				IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
-				IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD |
-				IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS,
-			.phy_cap_info[2] =
-				IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US |
-				IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ |
-				IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ |
-				IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO |
-				IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO,
-			.phy_cap_info[3] =
-				IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK |
-				IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 |
-				IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK |
-				IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1,
-			.phy_cap_info[4] =
-				IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE |
-				IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 |
-				IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8,
-			.phy_cap_info[5] =
-				IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 |
-				IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 |
-				IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK |
-				IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK,
-			.phy_cap_info[6] =
-				IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU |
-				IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU |
-				IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMER_FB |
-				IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMER_FB |
-				IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB |
-				IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO |
-				IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT,
-			.phy_cap_info[7] =
-				IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR |
-				IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI |
-				IEEE80211_HE_PHY_CAP7_MAX_NC_1,
-			.phy_cap_info[8] =
-				IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI |
-				IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G |
-				IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU |
-				IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU |
-				IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ,
-			.phy_cap_info[9] =
-				IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK |
-				IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB |
-				IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB,
+static struct ieee80211_sband_iftype_data iwl_he_capa[] = {
+	{
+		.types_mask = BIT(NL80211_IFTYPE_STATION),
+		.he_cap = {
+			.has_he = true,
+			.he_cap_elem = {
+				.mac_cap_info[0] =
+					IEEE80211_HE_MAC_CAP0_HTC_HE |
+					IEEE80211_HE_MAC_CAP0_TWT_REQ,
+				.mac_cap_info[1] =
+					IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
+					IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8,
+				.mac_cap_info[2] =
+					IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP |
+					IEEE80211_HE_MAC_CAP2_MU_CASCADING |
+					IEEE80211_HE_MAC_CAP2_ACK_EN,
+				.mac_cap_info[3] =
+					IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
+					IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2,
+				.mac_cap_info[4] =
+					IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU |
+					IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39,
+				.mac_cap_info[5] =
+					IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 |
+					IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 |
+					IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU,
+				.phy_cap_info[0] =
+					IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G |
+					IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
+					IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G,
+				.phy_cap_info[1] =
+					IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK |
+					IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
+					IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD |
+					IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS,
+				.phy_cap_info[2] =
+					IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US |
+					IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ |
+					IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ |
+					IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO |
+					IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO,
+				.phy_cap_info[3] =
+					IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK |
+					IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 |
+					IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK |
+					IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1,
+				.phy_cap_info[4] =
+					IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE |
+					IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 |
+					IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8,
+				.phy_cap_info[5] =
+					IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 |
+					IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 |
+					IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK |
+					IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK,
+				.phy_cap_info[6] =
+					IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU |
+					IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU |
+					IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMER_FB |
+					IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMER_FB |
+					IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB |
+					IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO |
+					IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT,
+				.phy_cap_info[7] =
+					IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR |
+					IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI |
+					IEEE80211_HE_PHY_CAP7_MAX_NC_1,
+				.phy_cap_info[8] =
+					IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI |
+					IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G |
+					IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU |
+					IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU |
+					IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ,
+				.phy_cap_info[9] =
+					IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK |
+					IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB |
+					IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB,
+			},
+			/*
+			 * Set default Tx/Rx HE MCS NSS Support field.
+			 * Indicate support for up to 2 spatial streams and all
+			 * MCS, without any special cases
+			 */
+			.he_mcs_nss_supp = {
+				.rx_mcs_80 = cpu_to_le16(0xfffa),
+				.tx_mcs_80 = cpu_to_le16(0xfffa),
+				.rx_mcs_160 = cpu_to_le16(0xfffa),
+				.tx_mcs_160 = cpu_to_le16(0xfffa),
+				.rx_mcs_80p80 = cpu_to_le16(0xffff),
+				.tx_mcs_80p80 = cpu_to_le16(0xffff),
+			},
+			/*
+			 * Set default PPE thresholds, with PPET16 set to 0,
+			 * PPET8 set to 7
+			 */
+			.ppe_thres = {0x61, 0x1c, 0xc7, 0x71},
 		},
-		/*
-		 * Set default Tx/Rx HE MCS NSS Support field. Indicate support
-		 * for up to 2 spatial streams and all MCS, without any special
-		 * cases
-		 */
-		.he_mcs_nss_supp = {
-			.rx_mcs_80 = cpu_to_le16(0xfffa),
-			.tx_mcs_80 = cpu_to_le16(0xfffa),
-			.rx_mcs_160 = cpu_to_le16(0xfffa),
-			.tx_mcs_160 = cpu_to_le16(0xfffa),
-			.rx_mcs_80p80 = cpu_to_le16(0xffff),
-			.tx_mcs_80p80 = cpu_to_le16(0xffff),
+	},
+	{
+		.types_mask = BIT(NL80211_IFTYPE_AP),
+		.he_cap = {
+			.has_he = true,
+			.he_cap_elem = {
+				.mac_cap_info[0] =
+					IEEE80211_HE_MAC_CAP0_HTC_HE,
+				.mac_cap_info[1] =
+					IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
+					IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8,
+				.mac_cap_info[2] =
+					IEEE80211_HE_MAC_CAP2_BSR |
+					IEEE80211_HE_MAC_CAP2_MU_CASCADING |
+					IEEE80211_HE_MAC_CAP2_ACK_EN,
+				.mac_cap_info[3] =
+					IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
+					IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2,
+				.mac_cap_info[4] =
+					IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU,
+				.phy_cap_info[0] =
+					IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G |
+					IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
+					IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G,
+				.phy_cap_info[1] =
+					IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD |
+					IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS,
+				.phy_cap_info[2] =
+					IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US |
+					IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ |
+					IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ,
+				.phy_cap_info[3] =
+					IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK |
+					IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 |
+					IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK |
+					IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1,
+				.phy_cap_info[4] =
+					IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE |
+					IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 |
+					IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8,
+				.phy_cap_info[5] =
+					IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 |
+					IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 |
+					IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK |
+					IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK,
+				.phy_cap_info[6] =
+					IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU |
+					IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU |
+					IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT,
+				.phy_cap_info[7] =
+					IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI |
+					IEEE80211_HE_PHY_CAP7_MAX_NC_1,
+				.phy_cap_info[8] =
+					IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI |
+					IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G |
+					IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU |
+					IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU |
+					IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ,
+				.phy_cap_info[9] =
+					IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB |
+					IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB,
+			},
+			/*
+			 * Set default Tx/Rx HE MCS NSS Support field.
+			 * Indicate support for up to 2 spatial streams and all
+			 * MCS, without any special cases
+			 */
+			.he_mcs_nss_supp = {
+				.rx_mcs_80 = cpu_to_le16(0xfffa),
+				.tx_mcs_80 = cpu_to_le16(0xfffa),
+				.rx_mcs_160 = cpu_to_le16(0xfffa),
+				.tx_mcs_160 = cpu_to_le16(0xfffa),
+				.rx_mcs_80p80 = cpu_to_le16(0xffff),
+				.tx_mcs_80p80 = cpu_to_le16(0xffff),
+			},
+			/*
+			 * Set default PPE thresholds, with PPET16 set to 0,
+			 * PPET8 set to 7
+			 */
+			.ppe_thres = {0x61, 0x1c, 0xc7, 0x71},
 		},
-		/*
-		 * Set default PPE thresholds, with PPET16 set to 0, PPET8 set
-		 * to 7
-		 */
-		.ppe_thres = {0x61, 0x1c, 0xc7, 0x71},
 	},
 };
 
@@ -568,20 +651,24 @@ static void iwl_init_he_hw_capab(struct ieee80211_supported_band *sband,
 {
 	if (sband->band == NL80211_BAND_2GHZ ||
 	    sband->band == NL80211_BAND_5GHZ)
-		sband->iftype_data = &iwl_he_capa;
+		sband->iftype_data = iwl_he_capa;
 	else
 		return;
 
-	sband->n_iftype_data = 1;
+	sband->n_iftype_data = ARRAY_SIZE(iwl_he_capa);
 
 	/* If not 2x2, we need to indicate 1x1 in the Midamble RX Max NSTS */
 	if ((tx_chains & rx_chains) != ANT_AB) {
-		iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[1] &=
-			~IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS;
-		iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[2] &=
-			~IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS;
-		iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[7] &=
-			~IEEE80211_HE_PHY_CAP7_MAX_NC_MASK;
+		int i;
+
+		for (i = 0; i < sband->n_iftype_data; i++) {
+			iwl_he_capa[i].he_cap.he_cap_elem.phy_cap_info[1] &=
+				~IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS;
+			iwl_he_capa[i].he_cap.he_cap_elem.phy_cap_info[2] &=
+				~IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS;
+			iwl_he_capa[i].he_cap.he_cap_elem.phy_cap_info[7] &=
+				~IEEE80211_HE_PHY_CAP7_MAX_NC_MASK;
+		}
 	}
 }
 
-- 
cgit v1.2.3


From bf9dfedaad9e65f2f580d3a573401d521d48b932 Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Mon, 23 Jul 2018 11:40:30 +0300
Subject: iwlwifi: mvm: handle RX no data notification

Handle RX no data notification, which is used for advertising NDP to
radiotap.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../net/wireless/intel/iwlwifi/fw/api/datapath.h   |   5 +
 drivers/net/wireless/intel/iwlwifi/fw/api/rx.h     |  49 ++++++++
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h       |   2 +
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c       |   2 +
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c      | 126 ++++++++++++++++++++-
 5 files changed, 183 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
index eff3249af48a..fdc54a5dc9de 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
@@ -104,6 +104,11 @@ enum iwl_data_path_subcmd_ids {
 	 */
 	HE_AIR_SNIFFER_CONFIG_CMD = 0x13,
 
+	/**
+	 * @RX_NO_DATA_NOTIF: &struct iwl_rx_no_data
+	 */
+	RX_NO_DATA_NOTIF = 0xF5,
+
 	/**
 	 * @TLC_MNG_UPDATE_NOTIF: &struct iwl_tlc_update_notif
 	 */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
index 8961227ff44d..0791a854fc8f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
@@ -697,6 +697,55 @@ struct iwl_rx_mpdu_desc {
 #define IWL_CD_STTS_WIFI_STATUS_POS	4
 #define IWL_CD_STTS_WIFI_STATUS_MSK	0xF0
 
+#define RX_NO_DATA_CHAIN_A_POS		0
+#define RX_NO_DATA_CHAIN_A_MSK		(0xff << RX_NO_DATA_CHAIN_A_POS)
+#define RX_NO_DATA_CHAIN_B_POS		8
+#define RX_NO_DATA_CHAIN_B_MSK		(0xff << RX_NO_DATA_CHAIN_B_POS)
+#define RX_NO_DATA_CHANNEL_POS		16
+#define RX_NO_DATA_CHANNEL_MSK		(0xff << RX_NO_DATA_CHANNEL_POS)
+
+#define RX_NO_DATA_INFO_TYPE_POS	0
+#define RX_NO_DATA_INFO_TYPE_MSK	(0xff << RX_NO_DATA_INFO_TYPE_POS)
+#define RX_NO_DATA_INFO_TYPE_NONE	0
+#define RX_NO_DATA_INFO_TYPE_RX_ERR	1
+#define RX_NO_DATA_INFO_TYPE_NDP	2
+#define RX_NO_DATA_INFO_TYPE_MU_UNMATCHED	3
+#define RX_NO_DATA_INFO_TYPE_HE_TB_UNMATCHED	4
+
+#define RX_NO_DATA_INFO_ERR_POS		8
+#define RX_NO_DATA_INFO_ERR_MSK		(0xff << RX_NO_DATA_INFO_ERR_POS)
+#define RX_NO_DATA_INFO_ERR_NONE	0
+#define RX_NO_DATA_INFO_ERR_BAD_PLCP	1
+#define RX_NO_DATA_INFO_ERR_UNSUPPORTED_RATE	2
+#define RX_NO_DATA_INFO_ERR_NO_DELIM		3
+#define RX_NO_DATA_INFO_ERR_BAD_MAC_HDR	4
+
+#define RX_NO_DATA_FRAME_TIME_POS	0
+#define RX_NO_DATA_FRAME_TIME_MSK	(0xfffff << RX_NO_DATA_FRAME_TIME_POS)
+
+/**
+ * struct iwl_rx_no_data - RX no data descriptor
+ * @info: 7:0 frame type, 15:8 RX error type
+ * @rssi: 7:0 energy chain-A,
+ *	15:8 chain-B, measured at FINA time (FINA_ENERGY), 16:23 channel
+ * @on_air_rise_time: GP2 during on air rise
+ * @fr_time: frame time
+ * @rate: rate/mcs of frame
+ * @phy_info: &enum iwl_rx_phy_data0 and &enum iwl_rx_phy_info_type
+ * @rx_vec: DW-12:9 raw RX vectors from DSP according to modulation type.
+ *	for VHT: OFDM_RX_VECTOR_SIGA1_OUT, OFDM_RX_VECTOR_SIGA2_OUT
+ *	for HE: OFDM_RX_VECTOR_HE_SIGA1_OUT, OFDM_RX_VECTOR_HE_SIGA2_OUT
+ */
+struct iwl_rx_no_data {
+	__le32 info;
+	__le32 rssi;
+	__le32 on_air_rise_time;
+	__le32 fr_time;
+	__le32 rate;
+	__le32 phy_info[2];
+	__le32 rx_vec[3];
+} __packed; /* RX_NO_DATA_NTFY_API_S_VER_1 */
+
 /**
  * enum iwl_completion_desc_transfer_status -  transfer status (bits 1-3)
  * @IWL_CD_STTS_UNUSED: unused
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 707bc7d1f37f..1aa690e081ff 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1556,6 +1556,8 @@ void iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct napi_struct *napi,
 			struct iwl_rx_cmd_buffer *rxb);
 void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 			struct iwl_rx_cmd_buffer *rxb, int queue);
+void iwl_mvm_rx_monitor_ndp(struct iwl_mvm *mvm, struct napi_struct *napi,
+			    struct iwl_rx_cmd_buffer *rxb, int queue);
 void iwl_mvm_rx_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi,
 			      struct iwl_rx_cmd_buffer *rxb, int queue);
 int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index a31dc99b63f7..30c5127034a0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -1073,6 +1073,8 @@ static void iwl_mvm_rx_mq(struct iwl_op_mode *op_mode,
 		iwl_mvm_rx_queue_notif(mvm, rxb, 0);
 	else if (cmd == WIDE_ID(LEGACY_GROUP, FRAME_RELEASE))
 		iwl_mvm_rx_frame_release(mvm, napi, rxb, 0);
+	else if (cmd == WIDE_ID(DATA_PATH_GROUP, RX_NO_DATA_NOTIF))
+		iwl_mvm_rx_monitor_ndp(mvm, napi, rxb, 0);
 	else
 		iwl_mvm_rx_common(mvm, rxb, pkt);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 8b014456e6d8..7bd8676508f5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -200,7 +200,8 @@ static void iwl_mvm_pass_packet_to_mac80211(struct iwl_mvm *mvm,
 {
 	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
 
-	if (iwl_mvm_check_pn(mvm, skb, queue, sta)) {
+	if (!(rx_status->flag & RX_FLAG_NO_PSDU) &&
+	    iwl_mvm_check_pn(mvm, skb, queue, sta)) {
 		kfree_skb(skb);
 	} else {
 		unsigned int radiotap_len = 0;
@@ -1606,6 +1607,129 @@ out:
 	rcu_read_unlock();
 }
 
+void iwl_mvm_rx_monitor_ndp(struct iwl_mvm *mvm, struct napi_struct *napi,
+			    struct iwl_rx_cmd_buffer *rxb, int queue)
+{
+	struct ieee80211_rx_status *rx_status;
+	struct iwl_rx_packet *pkt = rxb_addr(rxb);
+	struct iwl_rx_no_data *desc = (void *)pkt->data;
+	u32 rate_n_flags = le32_to_cpu(desc->rate);
+	u32 gp2_on_air_rise = le32_to_cpu(desc->on_air_rise_time);
+	u32 rssi = le32_to_cpu(desc->rssi);
+	u32 info_type = le32_to_cpu(desc->info) & RX_NO_DATA_INFO_TYPE_MSK;
+	u16 phy_info = IWL_RX_MPDU_PHY_TSF_OVERLOAD;
+	struct ieee80211_sta *sta = NULL;
+	struct sk_buff *skb;
+	u8 channel, energy_a, energy_b;
+	struct iwl_mvm_rx_phy_data phy_data = {
+		.d0 = desc->phy_info[0],
+		.info_type = IWL_RX_PHY_INFO_TYPE_NONE,
+	};
+
+	if (unlikely(test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)))
+		return;
+
+	/* Currently only NDP type is supported */
+	if (info_type != RX_NO_DATA_INFO_TYPE_NDP)
+		return;
+
+	energy_a = (rssi & RX_NO_DATA_CHAIN_A_MSK) >> RX_NO_DATA_CHAIN_A_POS;
+	energy_b = (rssi & RX_NO_DATA_CHAIN_B_MSK) >> RX_NO_DATA_CHAIN_B_POS;
+	channel = (rssi & RX_NO_DATA_CHANNEL_MSK) >> RX_NO_DATA_CHANNEL_POS;
+
+	phy_data.info_type =
+		le32_get_bits(desc->phy_info[1],
+			      IWL_RX_PHY_DATA1_INFO_TYPE_MASK);
+
+	/* Dont use dev_alloc_skb(), we'll have enough headroom once
+	 * ieee80211_hdr pulled.
+	 */
+	skb = alloc_skb(128, GFP_ATOMIC);
+	if (!skb) {
+		IWL_ERR(mvm, "alloc_skb failed\n");
+		return;
+	}
+
+	rx_status = IEEE80211_SKB_RXCB(skb);
+
+	/* 0-length PSDU */
+	rx_status->flag |= RX_FLAG_NO_PSDU;
+	/* currently this is the only type for which we get this notif */
+	rx_status->zero_length_psdu_type =
+		IEEE80211_RADIOTAP_ZERO_LEN_PSDU_SOUNDING;
+
+	/* This may be overridden by iwl_mvm_rx_he() to HE_RU */
+	switch (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) {
+	case RATE_MCS_CHAN_WIDTH_20:
+		break;
+	case RATE_MCS_CHAN_WIDTH_40:
+		rx_status->bw = RATE_INFO_BW_40;
+		break;
+	case RATE_MCS_CHAN_WIDTH_80:
+		rx_status->bw = RATE_INFO_BW_80;
+		break;
+	case RATE_MCS_CHAN_WIDTH_160:
+		rx_status->bw = RATE_INFO_BW_160;
+		break;
+	}
+
+	if (rate_n_flags & RATE_MCS_HE_MSK)
+		iwl_mvm_rx_he(mvm, skb, &phy_data, rate_n_flags,
+			      phy_info, queue);
+
+	iwl_mvm_decode_lsig(skb, &phy_data);
+
+	rx_status->device_timestamp = gp2_on_air_rise;
+	rx_status->band = channel > 14 ? NL80211_BAND_5GHZ :
+		NL80211_BAND_2GHZ;
+	rx_status->freq = ieee80211_channel_to_frequency(channel,
+							 rx_status->band);
+	iwl_mvm_get_signal_strength(mvm, rx_status, rate_n_flags, energy_a,
+				    energy_b);
+
+	rcu_read_lock();
+
+	if (!(rate_n_flags & RATE_MCS_CCK_MSK) &&
+	    rate_n_flags & RATE_MCS_SGI_MSK)
+		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
+	if (rate_n_flags & RATE_HT_MCS_GF_MSK)
+		rx_status->enc_flags |= RX_ENC_FLAG_HT_GF;
+	if (rate_n_flags & RATE_MCS_LDPC_MSK)
+		rx_status->enc_flags |= RX_ENC_FLAG_LDPC;
+	if (rate_n_flags & RATE_MCS_HT_MSK) {
+		u8 stbc = (rate_n_flags & RATE_MCS_STBC_MSK) >>
+				RATE_MCS_STBC_POS;
+		rx_status->encoding = RX_ENC_HT;
+		rx_status->rate_idx = rate_n_flags & RATE_HT_MCS_INDEX_MSK;
+		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
+	} else if (rate_n_flags & RATE_MCS_VHT_MSK) {
+		u8 stbc = (rate_n_flags & RATE_MCS_STBC_MSK) >>
+				RATE_MCS_STBC_POS;
+		rx_status->nss =
+			((rate_n_flags & RATE_VHT_MCS_NSS_MSK) >>
+						RATE_VHT_MCS_NSS_POS) + 1;
+		rx_status->rate_idx = rate_n_flags & RATE_VHT_MCS_RATE_CODE_MSK;
+		rx_status->encoding = RX_ENC_VHT;
+		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
+		if (rate_n_flags & RATE_MCS_BF_MSK)
+			rx_status->enc_flags |= RX_ENC_FLAG_BF;
+	} else if (!(rate_n_flags & RATE_MCS_HE_MSK)) {
+		int rate = iwl_mvm_legacy_rate_to_mac80211_idx(rate_n_flags,
+							       rx_status->band);
+
+		if (WARN(rate < 0 || rate > 0xFF,
+			 "Invalid rate flags 0x%x, band %d,\n",
+			 rate_n_flags, rx_status->band)) {
+			kfree_skb(skb);
+			goto out;
+		}
+		rx_status->rate_idx = rate;
+	}
+
+	iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue, sta);
+out:
+	rcu_read_unlock();
+}
 void iwl_mvm_rx_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi,
 			      struct iwl_rx_cmd_buffer *rxb, int queue)
 {
-- 
cgit v1.2.3


From 83eabf1e9810f3753d6dafd9a0dc3849924d4fc0 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 27 Aug 2018 13:56:41 +0300
Subject: iwlwifi: mvm: take station lock later in the code

There is no need to lock mvm station for transport reclaim.
Move the locking down, after the reclaim.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 4ebfd41dadc9..995fe2a6abbb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1817,8 +1817,6 @@ static void iwl_mvm_tx_reclaim(struct iwl_mvm *mvm, int sta_id, int tid,
 		return;
 	}
 
-	spin_lock_bh(&mvmsta->lock);
-
 	__skb_queue_head_init(&reclaimed_skbs);
 
 	/*
@@ -1828,6 +1826,8 @@ static void iwl_mvm_tx_reclaim(struct iwl_mvm *mvm, int sta_id, int tid,
 	 */
 	iwl_trans_reclaim(mvm->trans, txq, index, &reclaimed_skbs);
 
+	spin_lock_bh(&mvmsta->lock);
+
 	tid_data->next_reclaimed = index;
 
 	iwl_mvm_check_ratid_empty(mvm, sta, tid);
-- 
cgit v1.2.3


From 3681729429f4626c85a4eb62e5ce76be0b626f87 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 27 Aug 2018 14:07:20 +0300
Subject: iwlwifi: pcie: lock txq a bit later in reclaim code

In reclaim code, we don't need to take the queue lock for
waking the queue. The code section is executed only when
the tx path is stopped, and since the reclaim path is not
executed in parallel to itself, no one can update the queue
pointers, and accessing them is safe without a lock.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 3d53842ee60e..ee990a7a5411 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1160,10 +1160,11 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 			 */
 			iwl_trans_tx(trans, skb, dev_cmd_ptr, txq_id);
 		}
-		spin_lock_bh(&txq->lock);
 
 		if (iwl_queue_space(trans, txq) > txq->low_mark)
 			iwl_wake_queue(trans, txq);
+
+		spin_lock_bh(&txq->lock);
 	}
 
 	if (txq->read_ptr == txq->write_ptr) {
-- 
cgit v1.2.3


From 35739348ba07186a6b186e3aae5728721ff57a9a Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Wed, 22 Aug 2018 10:50:49 +0300
Subject: iwlwifi: mvm: clean up SSN incrementation

Sometimes, due to SCD bug, we need to start the queue with an
higher SSN. The queue allocation function currently increments
the SSN in the packet itself, but it is pointless, since this
value is overridden later by iwl_mvm_tx_mpdu with the value
from mvmsta->tid_data[tid].seq_number. Updating tid data is
sufficient.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index e82194836f03..e28009832da0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1254,6 +1254,7 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 
 	spin_lock_bh(&mvmsta->lock);
 	tfd_queue_mask = mvmsta->tfd_queue_msk;
+	ssn = IEEE80211_SEQ_TO_SN(mvmsta->tid_data[tid].seq_number);
 	spin_unlock_bh(&mvmsta->lock);
 
 	/*
@@ -1340,13 +1341,8 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 		}
 	}
 
-	ssn = IEEE80211_SEQ_TO_SN(le16_to_cpu(hdr->seq_ctrl));
 	inc_ssn = iwl_mvm_enable_txq(mvm, queue, mac_queue,
 				     ssn, &cfg, wdg_timeout);
-	if (inc_ssn) {
-		ssn = (ssn + 1) & IEEE80211_SCTL_SEQ;
-		le16_add_cpu(&hdr->seq_ctrl, 0x10);
-	}
 
 	/*
 	 * Mark queue as shared in transport if shared
@@ -1363,8 +1359,10 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 	 * this ra/tid in our Tx path since we stop the Qdisc when we
 	 * need to allocate a new TFD queue.
 	 */
-	if (inc_ssn)
+	if (inc_ssn) {
 		mvmsta->tid_data[tid].seq_number += 0x10;
+		ssn = (ssn + 1) & IEEE80211_SCTL_SEQ;
+	}
 	mvmsta->tid_data[tid].txq_id = queue;
 	mvmsta->tfd_queue_msk |= BIT(queue);
 	queue_state = mvmsta->tid_data[tid].state;
-- 
cgit v1.2.3


From a06875a7f8fae2d5b4891abb28c2c4a44ee1ffe8 Mon Sep 17 00:00:00 2001
From: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Date: Tue, 28 Aug 2018 16:15:55 +0300
Subject: iwlwifi: wrt: add rt status and num of rx/tx fifos to dump

Add the rt status of the last assert or 0 if the dump collection was
not initiated by an assert.  Add the number of rx and tx fifos in use.
These fields are added to dump info lst file.

Signed-off-by: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c        | 1 +
 drivers/net/wireless/intel/iwlwifi/fw/dbg.h        | 1 +
 drivers/net/wireless/intel/iwlwifi/fw/error-dump.h | 3 +++
 drivers/net/wireless/intel/iwlwifi/fw/runtime.h    | 1 +
 drivers/net/wireless/intel/iwlwifi/mvm/utils.c     | 3 +++
 5 files changed, 9 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index b17298ba7dc0..d1e6196a52a2 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -828,6 +828,7 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 			sizeof(dump_info->dev_human_readable) - 1);
 		strncpy(dump_info->bus_human_readable, fwrt->dev->bus->name,
 			sizeof(dump_info->bus_human_readable) - 1);
+		dump_info->rt_status = cpu_to_le32(fwrt->dump.rt_status);
 
 		dump_data = iwl_fw_error_next_data(dump_data);
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index c14e4614a2ea..6aabbdd72326 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -102,6 +102,7 @@ static inline void iwl_fw_free_dump_desc(struct iwl_fw_runtime *fwrt)
 	if (fwrt->dump.desc != &iwl_dump_desc_assert)
 		kfree(fwrt->dump.desc);
 	fwrt->dump.desc = NULL;
+	fwrt->dump.rt_status = 0;
 }
 
 void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
index cefafc9a082f..65faecf552cd 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
@@ -187,6 +187,8 @@ enum iwl_fw_error_dump_family {
  * @fw_human_readable: human readable FW version
  * @dev_human_readable: name of the device
  * @bus_human_readable: name of the bus used
+ * @rt_status: the error_id/rt_status that that triggered the latest dump
+ *	if the dump collection was not initiated by an assert, the value is 0
  */
 struct iwl_fw_error_dump_info {
 	__le32 device_family;
@@ -194,6 +196,7 @@ struct iwl_fw_error_dump_info {
 	u8 fw_human_readable[FW_VER_HUMAN_READABLE_SZ];
 	u8 dev_human_readable[64];
 	u8 bus_human_readable[8];
+	__le32 rt_status;
 } __packed;
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index 77845de30c5c..4f7090f88cb0 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -142,6 +142,7 @@ struct iwl_fw_runtime {
 		u32 *d3_debug_data;
 		struct iwl_fw_ini_active_regs active_regs[IWL_FW_INI_MAX_REGION_ID];
 		struct iwl_fw_ini_active_triggers active_trigs[IWL_FW_TRIGGER_ID_NUM];
+		u32 rt_status;
 	} dump;
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 	struct {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index 5ad352ef8e9b..d116c6ae18ff 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -540,6 +540,9 @@ static void iwl_mvm_dump_lmac_error_log(struct iwl_mvm *mvm, u32 base)
 
 	iwl_trans_read_mem_bytes(trans, base, &table, sizeof(table));
 
+	if (table.valid)
+		mvm->fwrt.dump.rt_status = table.error_id;
+
 	if (ERROR_START_OFFSET <= table.valid * ERROR_ELEM_SIZE) {
 		IWL_ERR(trans, "Start IWL Error Log Dump:\n");
 		IWL_ERR(trans, "Status: 0x%08lX, count: %d\n",
-- 
cgit v1.2.3


From 8804351c17f90eb13684d13ea994e7600d2be846 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Thu, 30 Aug 2018 15:07:03 +0300
Subject: iwlwifi: remove unused and wrong PHY_CFG_* macros

These macros are never used and are actually wrong, so it's very
confusing.  Remove them.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/config.h | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/config.h b/drivers/net/wireless/intel/iwlwifi/fw/api/config.h
index 7f645b62804e..5e88fa2e6fb7 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/config.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/config.h
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -127,17 +129,6 @@ struct iwl_phy_cfg_cmd {
 	struct iwl_calib_ctrl calib_control;
 } __packed;
 
-#define PHY_CFG_RADIO_TYPE	(BIT(0) | BIT(1))
-#define PHY_CFG_RADIO_STEP	(BIT(2) | BIT(3))
-#define PHY_CFG_RADIO_DASH	(BIT(4) | BIT(5))
-#define PHY_CFG_PRODUCT_NUMBER	(BIT(6) | BIT(7))
-#define PHY_CFG_TX_CHAIN_A	BIT(8)
-#define PHY_CFG_TX_CHAIN_B	BIT(9)
-#define PHY_CFG_TX_CHAIN_C	BIT(10)
-#define PHY_CFG_RX_CHAIN_A	BIT(12)
-#define PHY_CFG_RX_CHAIN_B	BIT(13)
-#define PHY_CFG_RX_CHAIN_C	BIT(14)
-
 /*
  * enum iwl_dc2dc_config_id - flag ids
  *
-- 
cgit v1.2.3


From 2c34be6c1fc8a0c90073dead7bce13937661eadf Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 3 Sep 2018 14:32:48 +0300
Subject: iwlwifi: mvm: set TWT responder capability bit in 11AX SoftAP mode

This is needed to test TWT requester on the client side.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 173ade96f119..d9afedc3d1d9 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -569,7 +569,8 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = {
 			.has_he = true,
 			.he_cap_elem = {
 				.mac_cap_info[0] =
-					IEEE80211_HE_MAC_CAP0_HTC_HE,
+					IEEE80211_HE_MAC_CAP0_HTC_HE |
+					IEEE80211_HE_MAC_CAP0_TWT_RES,
 				.mac_cap_info[1] =
 					IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
 					IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8,
-- 
cgit v1.2.3


From b71a9c35f214dbd9e9e33d36219bd0383f861677 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sun, 26 Aug 2018 23:31:17 +0100
Subject: iwlwifi: mvm: fix spelling mistake "Recieved" -> "Received"

Trivial fix to spelling mistake in debug message.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 99a0dafde382..97dc464379d2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -3394,7 +3394,7 @@ static bool iwl_mvm_rx_aux_roc(struct iwl_notif_wait_data *notif_wait,
 	resp = (void *)pkt->data;
 
 	IWL_DEBUG_TE(mvm,
-		     "Aux ROC: Recieved response from ucode: status=%d uid=%d\n",
+		     "Aux ROC: Received response from ucode: status=%d uid=%d\n",
 		     resp->status, resp->event_unique_id);
 
 	te_data->uid = le32_to_cpu(resp->event_unique_id);
-- 
cgit v1.2.3


From 83ea00d6873fd7a6b7e94cf40f6dd0007593fb1e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 23 Aug 2018 20:15:40 -0500
Subject: iwlwifi: mvm: d3: use struct_size() in kzalloc()

One of the more common cases of allocation size calculations is finding
the size of a structure that has a zero-sized array at the end, along
with memory for some number of elements for that array. For example:

struct foo {
	int stuff;
        void *entry[];
};

instance = kzalloc(sizeof(struct foo) + sizeof(void *) * count, GFP_KERNEL);

Instead of leaving these open-coded and prone to type mistakes, we can
now use the new struct_size() helper:

instance = kzalloc(struct_size(instance, entry, count), GFP_KERNEL);

This issue was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/d3.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 9b018d00f78f..01b5338201d6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -1811,8 +1811,7 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm,
 		n_matches = 0;
 	}
 
-	net_detect = kzalloc(sizeof(*net_detect) +
-			     (n_matches * sizeof(net_detect->matches[0])),
+	net_detect = kzalloc(struct_size(net_detect, matches, n_matches),
 			     GFP_KERNEL);
 	if (!net_detect || !n_matches)
 		goto out_report_nd;
@@ -1827,8 +1826,7 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm,
 		for (j = 0; j < SCAN_OFFLOAD_MATCHING_CHANNELS_LEN; j++)
 			n_channels += hweight8(fw_match->matching_channels[j]);
 
-		match = kzalloc(sizeof(*match) +
-				(n_channels * sizeof(*match->channels)),
+		match = kzalloc(struct_size(match, channels, n_channels),
 				GFP_KERNEL);
 		if (!match)
 			goto out_report_nd;
-- 
cgit v1.2.3


From 2c47e5a1f25b1c894c9fe2f77c156c054ae8ffb7 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Thu, 6 Sep 2018 10:03:22 +0300
Subject: iwlwifi: dbg: add debug data to warning

Add debug data to the warning issued when getting wrong region
id from firmware.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index d1e6196a52a2..2a19b178c5e8 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1647,7 +1647,8 @@ static void iwl_fw_dbg_update_regions(struct iwl_fw_runtime *fwrt,
 		int id = le32_to_cpu(reg->region_id);
 		struct iwl_fw_ini_active_regs *active;
 
-		if (WARN_ON(id >= ARRAY_SIZE(fwrt->dump.active_regs)))
+		if (WARN(id >= ARRAY_SIZE(fwrt->dump.active_regs),
+			 "Invalid region id %d for apply point %d\n", id, pnt))
 			break;
 
 		active = &fwrt->dump.active_regs[id];
-- 
cgit v1.2.3


From 9517d448d543d8bd0f83e4edc29b4b53d74a7f71 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Wed, 13 Jun 2018 15:26:37 +0300
Subject: iwlwifi: bump the API version to 43 for 9000 and 22000

Bump the API version to 43 for 9000 and 22000 devices.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c | 2 +-
 drivers/net/wireless/intel/iwlwifi/cfg/9000.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index a03d0b5617af..7e65073834b7 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -56,7 +56,7 @@
 #include "iwl-config.h"
 
 /* Highest firmware API version supported */
-#define IWL_22000_UCODE_API_MAX	41
+#define IWL_22000_UCODE_API_MAX	43
 
 /* Lowest firmware API version supported */
 #define IWL_22000_UCODE_API_MIN	39
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
index c73460684a0c..f2114137c13f 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
@@ -57,7 +57,7 @@
 #include "fw/file.h"
 
 /* Highest firmware API version supported */
-#define IWL9000_UCODE_API_MAX	41
+#define IWL9000_UCODE_API_MAX	43
 
 /* Lowest firmware API version supported */
 #define IWL9000_UCODE_API_MIN	30
-- 
cgit v1.2.3


From 19de2fa86e692e918eade4042989d7725039df89 Mon Sep 17 00:00:00 2001
From: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Date: Wed, 19 Dec 2018 11:36:19 +0200
Subject: iwlwifi: dbg_ini: fix bad ini tlv parsing

Add a break at the end of the ini tlv case.
Fix both the internal and external tlv parsing.

Signed-off-by: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c | 1 +
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c     | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index bc1e4d4bb42d..43d815cb3ce9 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -201,6 +201,7 @@ static int iwl_parse_fw_dbg_tlv(struct iwl_trans *trans, const u8 *data,
 		case IWL_UCODE_TLV_TYPE_TRIGGERS:
 		case IWL_UCODE_TLV_TYPE_DEBUG_FLOW:
 			iwl_fw_dbg_copy_tlv(trans, tlv, true);
+			break;
 		default:
 			WARN_ONCE(1, "Invalid TLV %x\n", tlv_type);
 			break;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index a65ba955783d..bf1be985f36b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1097,6 +1097,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 		case IWL_UCODE_TLV_TYPE_DEBUG_FLOW:
 			if (iwlwifi_mod_params.enable_ini)
 				iwl_fw_dbg_copy_tlv(drv->trans, tlv, false);
+			break;
 		default:
 			IWL_DEBUG_INFO(drv, "unknown TLV: %d\n", tlv_type);
 			break;
-- 
cgit v1.2.3


From fb376a495fbdb886f38cfaf5a3805401b9e46f13 Mon Sep 17 00:00:00 2001
From: Kyle Roeschley <kyle.roeschley@ni.com>
Date: Wed, 5 Dec 2018 09:43:11 +0200
Subject: ath6kl: Only use match sets when firmware supports it

Commit dd45b7598f1c ("ath6kl: Include match ssid list in scheduled scan")
merged the probed and matched SSID lists before sending them to the
firmware. In the process, it assumed match set support is always available
in ath6kl_set_probed_ssids, which breaks scans for hidden SSIDs. Now, check
that the firmware supports matching SSIDs in scheduled scans before setting
MATCH_SSID_FLAG.

Fixes: dd45b7598f1c ("ath6kl: Include match ssid list in scheduled scan")
Signed-off-by: Kyle Roeschley <kyle.roeschley@ni.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index e121187f371f..6c98d7903ffb 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -939,7 +939,7 @@ static int ath6kl_set_probed_ssids(struct ath6kl *ar,
 		else
 			ssid_list[i].flag = ANY_SSID_FLAG;
 
-		if (n_match_ssid == 0)
+		if (ar->wiphy->max_match_sets != 0 && n_match_ssid == 0)
 			ssid_list[i].flag |= MATCH_SSID_FLAG;
 	}
 
-- 
cgit v1.2.3


From 5803c12816c43bd09e5f4247dd9313c2d9a2c41b Mon Sep 17 00:00:00 2001
From: Kyle Roeschley <kyle.roeschley@ni.com>
Date: Wed, 5 Dec 2018 09:43:13 +0200
Subject: ath6kl: Fix off by one error in scan completion

When ath6kl was reworked to share code between regular and scheduled scans
in commit 3b8ffc6a22ba ("ath6kl: Configure probed SSID list consistently"),
probed SSID entry changed from 1-index to 0-indexed. However,
ath6kl_cfg80211_scan_complete_event() was missed in that change. Fix its
indexing so that we correctly clear out the probed SSID list.

Signed-off-by: Kyle Roeschley <kyle.roeschley@ni.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 6c98d7903ffb..d7c626d9594e 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -1093,7 +1093,7 @@ void ath6kl_cfg80211_scan_complete_event(struct ath6kl_vif *vif, bool aborted)
 	if (vif->scan_req->n_ssids && vif->scan_req->ssids[0].ssid_len) {
 		for (i = 0; i < vif->scan_req->n_ssids; i++) {
 			ath6kl_wmi_probedssid_cmd(ar->wmi, vif->fw_vif_idx,
-						  i + 1, DISABLE_SSID_FLAG,
+						  i, DISABLE_SSID_FLAG,
 						  0, NULL);
 		}
 	}
-- 
cgit v1.2.3


From 192a986d964c3ebd927da102adbf8bcc604c7cbc Mon Sep 17 00:00:00 2001
From: Kyle Roeschley <kyle.roeschley@ni.com>
Date: Wed, 5 Dec 2018 09:43:16 +0200
Subject: ath6kl: Use debug instead of error message when disabled

This is not an unexpected condition, so we don't need to be shouting to the
world about it.

Signed-off-by: Kyle Roeschley <kyle.roeschley@ni.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index d7c626d9594e..59dd50866932 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -291,7 +291,7 @@ static bool ath6kl_cfg80211_ready(struct ath6kl_vif *vif)
 	}
 
 	if (!test_bit(WLAN_ENABLED, &vif->flags)) {
-		ath6kl_err("wlan disabled\n");
+		ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "wlan disabled\n");
 		return false;
 	}
 
-- 
cgit v1.2.3


From 986b834884647e31dc5a78b8d0a6da210ebda0b0 Mon Sep 17 00:00:00 2001
From: Yangtao Li <tiny.windzz@gmail.com>
Date: Mon, 3 Dec 2018 08:25:57 -0500
Subject: wil6210: convert to DEFINE_SHOW_ATTRIBUTE

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/debugfs.c | 240 +++++------------------------
 1 file changed, 42 insertions(+), 198 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 20dd4d070911..835c902b84c1 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -124,7 +124,7 @@ static void wil_print_ring(struct seq_file *s, struct wil6210_priv *wil,
 	seq_puts(s, "}\n");
 }
 
-static int wil_ring_debugfs_show(struct seq_file *s, void *data)
+static int ring_show(struct seq_file *s, void *data)
 {
 	uint i;
 	struct wil6210_priv *wil = s->private;
@@ -183,18 +183,7 @@ static int wil_ring_debugfs_show(struct seq_file *s, void *data)
 
 	return 0;
 }
-
-static int wil_ring_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_ring_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_ring = {
-	.open		= wil_ring_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(ring);
 
 static void wil_print_sring(struct seq_file *s, struct wil6210_priv *wil,
 			    struct wil_status_ring *sring)
@@ -240,7 +229,7 @@ static void wil_print_sring(struct seq_file *s, struct wil6210_priv *wil,
 	seq_puts(s, "}\n");
 }
 
-static int wil_srings_debugfs_show(struct seq_file *s, void *data)
+static int srings_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	int i = 0;
@@ -251,18 +240,7 @@ static int wil_srings_debugfs_show(struct seq_file *s, void *data)
 
 	return 0;
 }
-
-static int wil_srings_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_srings_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_srings = {
-	.open		= wil_srings_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(srings);
 
 static void wil_seq_hexdump(struct seq_file *s, void *p, int len,
 			    const char *prefix)
@@ -348,7 +326,7 @@ static void wil_print_mbox_ring(struct seq_file *s, const char *prefix,
 	wil_halp_unvote(wil);
 }
 
-static int wil_mbox_debugfs_show(struct seq_file *s, void *data)
+static int mbox_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	int ret;
@@ -366,18 +344,7 @@ static int wil_mbox_debugfs_show(struct seq_file *s, void *data)
 
 	return 0;
 }
-
-static int wil_mbox_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_mbox_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_mbox = {
-	.open		= wil_mbox_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(mbox);
 
 static int wil_debugfs_iomem_x32_set(void *data, u64 val)
 {
@@ -624,7 +591,7 @@ static int wil6210_debugfs_create_ITR_CNT(struct wil6210_priv *wil,
 	return 0;
 }
 
-static int wil_memread_debugfs_show(struct seq_file *s, void *data)
+static int memread_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	void __iomem *a;
@@ -645,18 +612,7 @@ static int wil_memread_debugfs_show(struct seq_file *s, void *data)
 
 	return 0;
 }
-
-static int wil_memread_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_memread_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_memread = {
-	.open		= wil_memread_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(memread);
 
 static ssize_t wil_read_file_ioblob(struct file *file, char __user *user_buf,
 				    size_t count, loff_t *ppos)
@@ -1060,7 +1016,7 @@ static void wil_seq_print_skb(struct seq_file *s, struct sk_buff *skb)
 }
 
 /*---------Tx/Rx descriptor------------*/
-static int wil_txdesc_debugfs_show(struct seq_file *s, void *data)
+static int txdesc_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	struct wil_ring *ring;
@@ -1153,21 +1109,10 @@ static int wil_txdesc_debugfs_show(struct seq_file *s, void *data)
 
 	return 0;
 }
-
-static int wil_txdesc_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_txdesc_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_txdesc = {
-	.open		= wil_txdesc_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(txdesc);
 
 /*---------Tx/Rx status message------------*/
-static int wil_status_msg_debugfs_show(struct seq_file *s, void *data)
+static int status_msg_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	int sring_idx = dbg_sring_index;
@@ -1209,19 +1154,7 @@ static int wil_status_msg_debugfs_show(struct seq_file *s, void *data)
 
 	return 0;
 }
-
-static int wil_status_msg_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_status_msg_debugfs_show,
-			   inode->i_private);
-}
-
-static const struct file_operations fops_status_msg = {
-	.open		= wil_status_msg_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(status_msg);
 
 static int wil_print_rx_buff(struct seq_file *s, struct list_head *lh)
 {
@@ -1239,7 +1172,7 @@ static int wil_print_rx_buff(struct seq_file *s, struct list_head *lh)
 	return i;
 }
 
-static int wil_rx_buff_mgmt_debugfs_show(struct seq_file *s, void *data)
+static int rx_buff_mgmt_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	struct wil_rx_buff_mgmt *rbm = &wil->rx_buff_mgmt;
@@ -1264,19 +1197,7 @@ static int wil_rx_buff_mgmt_debugfs_show(struct seq_file *s, void *data)
 
 	return 0;
 }
-
-static int wil_rx_buff_mgmt_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_rx_buff_mgmt_debugfs_show,
-			   inode->i_private);
-}
-
-static const struct file_operations fops_rx_buff_mgmt = {
-	.open		= wil_rx_buff_mgmt_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(rx_buff_mgmt);
 
 /*---------beamforming------------*/
 static char *wil_bfstatus_str(u32 status)
@@ -1306,7 +1227,7 @@ static bool is_all_zeros(void * const x_, size_t sz)
 	return true;
 }
 
-static int wil_bf_debugfs_show(struct seq_file *s, void *data)
+static int bf_show(struct seq_file *s, void *data)
 {
 	int rc;
 	int i;
@@ -1360,18 +1281,7 @@ static int wil_bf_debugfs_show(struct seq_file *s, void *data)
 	}
 	return 0;
 }
-
-static int wil_bf_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_bf_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_bf = {
-	.open		= wil_bf_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(bf);
 
 /*---------temp------------*/
 static void print_temp(struct seq_file *s, const char *prefix, s32 t)
@@ -1388,7 +1298,7 @@ static void print_temp(struct seq_file *s, const char *prefix, s32 t)
 	}
 }
 
-static int wil_temp_debugfs_show(struct seq_file *s, void *data)
+static int temp_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	s32 t_m, t_r;
@@ -1404,21 +1314,10 @@ static int wil_temp_debugfs_show(struct seq_file *s, void *data)
 
 	return 0;
 }
-
-static int wil_temp_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_temp_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_temp = {
-	.open		= wil_temp_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(temp);
 
 /*---------freq------------*/
-static int wil_freq_debugfs_show(struct seq_file *s, void *data)
+static int freq_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	struct wireless_dev *wdev = wil->main_ndev->ieee80211_ptr;
@@ -1428,21 +1327,10 @@ static int wil_freq_debugfs_show(struct seq_file *s, void *data)
 
 	return 0;
 }
-
-static int wil_freq_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_freq_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_freq = {
-	.open		= wil_freq_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(freq);
 
 /*---------link------------*/
-static int wil_link_debugfs_show(struct seq_file *s, void *data)
+static int link_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	struct station_info *sinfo;
@@ -1494,21 +1382,10 @@ out:
 	kfree(sinfo);
 	return rc;
 }
-
-static int wil_link_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_link_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_link = {
-	.open		= wil_link_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(link);
 
 /*---------info------------*/
-static int wil_info_debugfs_show(struct seq_file *s, void *data)
+static int info_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	struct net_device *ndev = wil->main_ndev;
@@ -1543,18 +1420,7 @@ static int wil_info_debugfs_show(struct seq_file *s, void *data)
 #undef CHECK_QSTATE
 	return 0;
 }
-
-static int wil_info_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_info_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_info = {
-	.open		= wil_info_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(info);
 
 /*---------recovery------------*/
 /* mode = [manual|auto]
@@ -1670,7 +1536,7 @@ has_keys:
 	seq_puts(s, "\n");
 }
 
-static int wil_sta_debugfs_show(struct seq_file *s, void *data)
+static int sta_show(struct seq_file *s, void *data)
 __acquires(&p->tid_rx_lock) __releases(&p->tid_rx_lock)
 {
 	struct wil6210_priv *wil = s->private;
@@ -1752,20 +1618,9 @@ __acquires(&p->tid_rx_lock) __releases(&p->tid_rx_lock)
 
 	return 0;
 }
+DEFINE_SHOW_ATTRIBUTE(sta);
 
-static int wil_sta_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_sta_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_sta = {
-	.open		= wil_sta_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
-
-static int wil_mids_debugfs_show(struct seq_file *s, void *data)
+static int mids_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	struct wil6210_vif *vif;
@@ -1788,18 +1643,7 @@ static int wil_mids_debugfs_show(struct seq_file *s, void *data)
 
 	return 0;
 }
-
-static int wil_mids_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wil_mids_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations fops_mids = {
-	.open		= wil_mids_seq_open,
-	.release	= single_release,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+DEFINE_SHOW_ATTRIBUTE(mids);
 
 static int wil_tx_latency_debugfs_show(struct seq_file *s, void *data)
 __acquires(&p->tid_rx_lock) __releases(&p->tid_rx_lock)
@@ -2443,23 +2287,23 @@ static const struct {
 	umode_t mode;
 	const struct file_operations *fops;
 } dbg_files[] = {
-	{"mbox",	0444,		&fops_mbox},
-	{"rings",	0444,		&fops_ring},
-	{"stations", 0444,		&fops_sta},
-	{"mids",	0444,		&fops_mids},
-	{"desc",	0444,		&fops_txdesc},
-	{"bf",		0444,		&fops_bf},
-	{"mem_val",	0644,		&fops_memread},
+	{"mbox",	0444,		&mbox_fops},
+	{"rings",	0444,		&ring_fops},
+	{"stations", 0444,		&sta_fops},
+	{"mids",	0444,		&mids_fops},
+	{"desc",	0444,		&txdesc_fops},
+	{"bf",		0444,		&bf_fops},
+	{"mem_val",	0644,		&memread_fops},
 	{"rxon",	0244,		&fops_rxon},
 	{"tx_mgmt",	0244,		&fops_txmgmt},
 	{"wmi_send", 0244,		&fops_wmi},
 	{"back",	0644,		&fops_back},
 	{"pmccfg",	0644,		&fops_pmccfg},
 	{"pmcdata",	0444,		&fops_pmcdata},
-	{"temp",	0444,		&fops_temp},
-	{"freq",	0444,		&fops_freq},
-	{"link",	0444,		&fops_link},
-	{"info",	0444,		&fops_info},
+	{"temp",	0444,		&temp_fops},
+	{"freq",	0444,		&freq_fops},
+	{"link",	0444,		&link_fops},
+	{"info",	0444,		&info_fops},
 	{"recovery", 0644,		&fops_recovery},
 	{"led_cfg",	0644,		&fops_led_cfg},
 	{"led_blink_time",	0644,	&fops_led_blink_time},
@@ -2467,9 +2311,9 @@ static const struct {
 	{"fw_version",	0444,		&fops_fw_version},
 	{"suspend_stats",	0644,	&fops_suspend_stats},
 	{"compressed_rx_status", 0644,	&fops_compressed_rx_status},
-	{"srings",	0444,		&fops_srings},
-	{"status_msg",	0444,		&fops_status_msg},
-	{"rx_buff_mgmt",	0444,	&fops_rx_buff_mgmt},
+	{"srings",	0444,		&srings_fops},
+	{"status_msg",	0444,		&status_msg_fops},
+	{"rx_buff_mgmt",	0444,	&rx_buff_mgmt_fops},
 	{"tx_latency",	0644,		&fops_tx_latency},
 	{"link_stats",	0644,		&fops_link_stats},
 	{"link_stats_global",	0644,	&fops_link_stats_global},
-- 
cgit v1.2.3


From 3fe970e76b374bdb4a6232cb8b78945e3d2b478f Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 5 Dec 2018 07:59:03 +0000
Subject: wil6210: remove set but not used variable 'wdev'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/wireless/ath/wil6210/main.c: In function '_wil6210_disconnect':
drivers/net/wireless/ath/wil6210/main.c:407:23: warning:
 variable 'wdev' set but not used [-Wunused-but-set-variable]

It never used since commit ("e1b43407c034 wil6210: refactor disconnect flow")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index ba6a2eeedb65..5b7de00affe2 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -404,7 +404,6 @@ static void _wil6210_disconnect(struct wil6210_vif *vif, const u8 *bssid,
 {
 	struct wil6210_priv *wil;
 	struct net_device *ndev;
-	struct wireless_dev *wdev;
 	int cid = -ENOENT;
 
 	if (unlikely(!vif))
@@ -412,7 +411,6 @@ static void _wil6210_disconnect(struct wil6210_vif *vif, const u8 *bssid,
 
 	wil = vif_to_wil(vif);
 	ndev = vif_to_ndev(vif);
-	wdev = vif_to_wdev(vif);
 
 	might_sleep();
 	wil_info(wil, "disconnect bssid=%pM, reason=%d\n", bssid, reason_code);
-- 
cgit v1.2.3


From 8cdb992f0dc36d6382840b1a6320e0c327a7d644 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 20 Dec 2018 11:51:58 +0800
Subject: net: hns3: refine the handle for hns3_nic_net_open/stop()

When triggering nic down, there is a time window between bringing down
the protocol stack and stopping the work task. If the net is up in the
time window, it may bring up the protocol stack again.

This patch fixes it by stop the work task at the beginning of
hns3_nic_net_stop(). To keep symmetrical, start the work task at the
end of hns3_nic_net_open().

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  1 +
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    |  8 ++++++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 22 +++++++++++++++-------
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 18 ++++++++++++++----
 4 files changed, 38 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 845d43d3a920..36eab37d8a40 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -461,6 +461,7 @@ struct hnae3_ae_ops {
 	unsigned long (*ae_dev_reset_cnt)(struct hnae3_handle *handle);
 	int (*set_gro_en)(struct hnae3_handle *handle, int enable);
 	u16 (*get_global_queue_id)(struct hnae3_handle *handle, u16 queue_id);
+	void (*set_timer_task)(struct hnae3_handle *handle, bool enable);
 };
 
 struct hnae3_dcb_ops {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index d060029ce142..becbf866e21f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -379,6 +379,7 @@ out_start_err:
 
 static int hns3_nic_net_open(struct net_device *netdev)
 {
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct hnae3_knic_private_info *kinfo;
 	int i, ret;
@@ -405,6 +406,9 @@ static int hns3_nic_net_open(struct net_device *netdev)
 				       kinfo->prio_tc[i]);
 	}
 
+	if (h->ae_algo->ops->set_timer_task)
+		h->ae_algo->ops->set_timer_task(priv->ae_handle, true);
+
 	return 0;
 }
 
@@ -437,10 +441,14 @@ static void hns3_nic_net_down(struct net_device *netdev)
 static int hns3_nic_net_stop(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state))
 		return 0;
 
+	if (h->ae_algo->ops->set_timer_task)
+		h->ae_algo->ops->set_timer_task(priv->ae_handle, false);
+
 	netif_tx_stop_all_queues(netdev);
 	netif_carrier_off(netdev);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index d0e84de39fa3..a12cb1452651 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5295,6 +5295,20 @@ static void hclge_reset_tqp_stats(struct hnae3_handle *handle)
 	}
 }
 
+static void hclge_set_timer_task(struct hnae3_handle *handle, bool enable)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	if (enable) {
+		mod_timer(&hdev->service_timer, jiffies + HZ);
+	} else {
+		del_timer_sync(&hdev->service_timer);
+		cancel_work_sync(&hdev->service_task);
+		clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state);
+	}
+}
+
 static int hclge_ae_start(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
@@ -5303,7 +5317,6 @@ static int hclge_ae_start(struct hnae3_handle *handle)
 	/* mac enable */
 	hclge_cfg_mac_mode(hdev, true);
 	clear_bit(HCLGE_STATE_DOWN, &hdev->state);
-	mod_timer(&hdev->service_timer, jiffies + HZ);
 	hdev->hw.mac.link = 0;
 
 	/* reset tqp stats */
@@ -5321,10 +5334,6 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 
 	set_bit(HCLGE_STATE_DOWN, &hdev->state);
 
-	del_timer_sync(&hdev->service_timer);
-	cancel_work_sync(&hdev->service_task);
-	clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state);
-
 	/* If it is not PF reset, the firmware will disable the MAC,
 	 * so it only need to stop phy here.
 	 */
@@ -5341,8 +5350,6 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 
 	/* reset tqp stats */
 	hclge_reset_tqp_stats(handle);
-	del_timer_sync(&hdev->service_timer);
-	cancel_work_sync(&hdev->service_task);
 	hclge_update_link_status(hdev);
 }
 
@@ -7996,6 +8003,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.ae_dev_reset_cnt = hclge_ae_dev_reset_cnt,
 	.set_gro_en = hclge_gro_en,
 	.get_global_queue_id = hclge_covert_handle_qid_global,
+	.set_timer_task = hclge_set_timer_task,
 };
 
 static struct hnae3_ae_algo ae_algo = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 54ba93ac24dd..919c3aa87228 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1840,6 +1840,19 @@ static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
 				       false);
 }
 
+static void hclgevf_set_timer_task(struct hnae3_handle *handle, bool enable)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	if (enable) {
+		mod_timer(&hdev->service_timer, jiffies + HZ);
+	} else {
+		del_timer_sync(&hdev->service_timer);
+		cancel_work_sync(&hdev->service_task);
+		clear_bit(HCLGEVF_STATE_SERVICE_SCHED, &hdev->state);
+	}
+}
+
 static int hclgevf_ae_start(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
@@ -1850,7 +1863,6 @@ static int hclgevf_ae_start(struct hnae3_handle *handle)
 	hclgevf_request_link_info(hdev);
 
 	clear_bit(HCLGEVF_STATE_DOWN, &hdev->state);
-	mod_timer(&hdev->service_timer, jiffies + HZ);
 
 	return 0;
 }
@@ -1863,9 +1875,6 @@ static void hclgevf_ae_stop(struct hnae3_handle *handle)
 
 	/* reset tqp stats */
 	hclgevf_reset_tqp_stats(handle);
-	del_timer_sync(&hdev->service_timer);
-	cancel_work_sync(&hdev->service_task);
-	clear_bit(HCLGEVF_STATE_SERVICE_SCHED, &hdev->state);
 	hclgevf_update_link_status(hdev, 0);
 }
 
@@ -2663,6 +2672,7 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.set_gro_en = hclgevf_gro_en,
 	.set_mtu = hclgevf_set_mtu,
 	.get_global_queue_id = hclgevf_get_qid_global,
+	.set_timer_task = hclgevf_set_timer_task,
 };
 
 static struct hnae3_ae_algo ae_algovf = {
-- 
cgit v1.2.3


From a298797532d9dc244abf349d7c2ed063732c6ba3 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 20 Dec 2018 11:51:59 +0800
Subject: net: hns3: change default tc state to close

In original codes, default tc value is set to the max tc. It's more
reasonable to close tc by changing default tc value to 1. Users can
enable it with lldp tool when they want to use tc.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index a12cb1452651..0b04d0426332 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -960,7 +960,7 @@ static int hclge_configure(struct hclge_dev *hdev)
 		hdev->pfc_max = hdev->tc_max;
 	}
 
-	hdev->tm_info.num_tc = hdev->tc_max;
+	hdev->tm_info.num_tc = 1;
 
 	/* Currently not support uncontiuous tc */
 	for (i = 0; i < hdev->tm_info.num_tc; i++)
-- 
cgit v1.2.3


From 1b7d7b0581173219b82abbd81c88cf8aa7d402c2 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 20 Dec 2018 11:52:00 +0800
Subject: net: hns3: fix a bug caused by udelay

udelay() in driver may always occupancy processor. If there is only
one cpu in system, the VF driver may initialize fail when insmod
PF and VF driver in the same system. This patch use msleep() to free
cpu when VF wait PF message.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index ef9c8e6eca28..84653f58b2d1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -26,7 +26,7 @@ static int hclgevf_get_mbx_resp(struct hclgevf_dev *hdev, u16 code0, u16 code1,
 				u8 *resp_data, u16 resp_len)
 {
 #define HCLGEVF_MAX_TRY_TIMES	500
-#define HCLGEVF_SLEEP_USCOEND	1000
+#define HCLGEVF_SLEEP_USECOND	1000
 	struct hclgevf_mbx_resp_status *mbx_resp;
 	u16 r_code0, r_code1;
 	int i = 0;
@@ -43,7 +43,7 @@ static int hclgevf_get_mbx_resp(struct hclgevf_dev *hdev, u16 code0, u16 code1,
 		if (test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state))
 			return -EIO;
 
-		udelay(HCLGEVF_SLEEP_USCOEND);
+		usleep_range(HCLGEVF_SLEEP_USECOND, HCLGEVF_SLEEP_USECOND * 2);
 		i++;
 	}
 
-- 
cgit v1.2.3


From 75edb610860fda65ceedb017fc69afabd2806b8b Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 20 Dec 2018 11:52:01 +0800
Subject: net: hns3: add max vector number check for pf

Each pf supports max 64 vectors and 128 tqps. For 2p/4p core scenario,
there may be more than 64 cpus online. So the result of min_t(u16,
num_Online_cpus(), tqp_num) may be more than 64. This patch adds check
for the vector number.

Fixes: dd38c72604dc ("net: hns3: fix for coalesce configuration lost during reset")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index becbf866e21f..624b8a733db5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3118,6 +3118,8 @@ map_ring_fail:
 
 static int hns3_nic_alloc_vector_data(struct hns3_nic_priv *priv)
 {
+#define HNS3_VECTOR_PF_MAX_NUM		64
+
 	struct hnae3_handle *h = priv->ae_handle;
 	struct hns3_enet_tqp_vector *tqp_vector;
 	struct hnae3_vector_info *vector;
@@ -3130,6 +3132,8 @@ static int hns3_nic_alloc_vector_data(struct hns3_nic_priv *priv)
 	/* RSS size, cpu online and vector_num should be the same */
 	/* Should consider 2p/4p later */
 	vector_num = min_t(u16, num_online_cpus(), tqp_num);
+	vector_num = min_t(u16, vector_num, HNS3_VECTOR_PF_MAX_NUM);
+
 	vector = devm_kcalloc(&pdev->dev, vector_num, sizeof(*vector),
 			      GFP_KERNEL);
 	if (!vector)
-- 
cgit v1.2.3


From 39cfbc9c4fc4a2888548c2624789e42e3f775721 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 20 Dec 2018 11:52:02 +0800
Subject: net: hns3: reset tqp while doing DOWN operation

While doing DOWN operation, the driver will reclaim the memory which has
already used for TX. If the hardware is processing this memory, it will
cause a RCB error to the hardware. According the hardware's description,
the driver should reset the tqp before reclaim the memory during DOWN.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c   | 4 ++++
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 0b04d0426332..98ae2820e001 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5331,6 +5331,7 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
+	int i;
 
 	set_bit(HCLGE_STATE_DOWN, &hdev->state);
 
@@ -5343,6 +5344,9 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 		return;
 	}
 
+	for (i = 0; i < handle->kinfo.num_tqps; i++)
+		hclge_reset_tqp(handle, i);
+
 	/* Mac disable */
 	hclge_cfg_mac_mode(hdev, false);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 919c3aa87228..156242f96a8e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1870,9 +1870,13 @@ static int hclgevf_ae_start(struct hnae3_handle *handle)
 static void hclgevf_ae_stop(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int i;
 
 	set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
 
+	for (i = 0; i < handle->kinfo.num_tqps; i++)
+		hclgevf_reset_tqp(handle, i);
+
 	/* reset tqp stats */
 	hclgevf_reset_tqp_stats(handle);
 	hclgevf_update_link_status(hdev, 0);
-- 
cgit v1.2.3


From 0285dbae5db842862d49f148cdcedad986447f34 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 20 Dec 2018 11:52:03 +0800
Subject: net: hns3: fix vf id check issue when add flow director rule

When add flow director fule for vf, the vf id is used as array
subscript before valid checking, which may cause memory overflow.

Fixes: dd74f815dd41 ("net: hns3: Add support for rule add/delete for flow director")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 98ae2820e001..9f8985862ae7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -4677,6 +4677,13 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle,
 		u8 vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
 		u16 tqps;
 
+		if (vf > hdev->num_req_vfs) {
+			dev_err(&hdev->pdev->dev,
+				"Error: vf id (%d) > max vf num (%d)\n",
+				vf, hdev->num_req_vfs);
+			return -EINVAL;
+		}
+
 		dst_vport_id = vf ? hdev->vport[vf].vport_id : vport->vport_id;
 		tqps = vf ? hdev->vport[vf].alloc_tqps : vport->alloc_tqps;
 
@@ -4687,13 +4694,6 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle,
 			return -EINVAL;
 		}
 
-		if (vf > hdev->num_req_vfs) {
-			dev_err(&hdev->pdev->dev,
-				"Error: vf id (%d) > max vf num (%d)\n",
-				vf, hdev->num_req_vfs);
-			return -EINVAL;
-		}
-
 		action = HCLGE_FD_ACTION_ACCEPT_PACKET;
 		q_index = ring;
 	}
-- 
cgit v1.2.3


From 8edc2285b7285c5fbffe438dc8113260d3e76656 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 20 Dec 2018 11:52:04 +0800
Subject: net: hns3: don't restore rules when flow director is disabled

When user disables flow director, all the rules will be disabled. But
when reset happens, it will restore all the rules again. It's not
reasonable. This patch fixes it by add flow director status check before
restore fules.

Fixes: 6871af29b3ab ("net: hns3: Add reset handle for flow director")
Fixes: c17852a8932f ("net: hns3: Add support for enable/disable flow director")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 9f8985862ae7..f7637c08bb3a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -4808,6 +4808,10 @@ static int hclge_restore_fd_entries(struct hnae3_handle *handle)
 	if (!hnae3_dev_fd_supported(hdev))
 		return 0;
 
+	/* if fd is disabled, should not restore it when reset */
+	if (!hdev->fd_cfg.fd_en)
+		return 0;
+
 	hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list, rule_node) {
 		ret = hclge_config_action(hdev, HCLGE_FD_STAGE_1, rule);
 		if (!ret)
-- 
cgit v1.2.3


From 31a16f99e02c2e0b40a5fb05d66f5e56721027e2 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 20 Dec 2018 11:52:05 +0800
Subject: net: hns3: fix the descriptor index when get rss type

Driver gets rss information from the last descriptor of the packet.
When driver handle the rss type, ring->next_to_clean indicates the
first descriptor of next packet.

This patch fix the descriptor index with "ring->next_to_clean - 1".

Fixes: 232fc64b6e62 ("net: hns3: Add HW RSS hash information to RX skb")
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 624b8a733db5..d3b9aaf96c1c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2550,9 +2550,16 @@ static void hns3_set_gro_param(struct sk_buff *skb, u32 l234info,
 static void hns3_set_rx_skb_rss_type(struct hns3_enet_ring *ring,
 				     struct sk_buff *skb)
 {
-	struct hns3_desc *desc = &ring->desc[ring->next_to_clean];
 	struct hnae3_handle *handle = ring->tqp->handle;
 	enum pkt_hash_types rss_type;
+	struct hns3_desc *desc;
+	int last_bd;
+
+	/* When driver handle the rss type, ring->next_to_clean indicates the
+	 * first descriptor of next packet, need -1 here.
+	 */
+	last_bd = (ring->next_to_clean - 1 + ring->desc_num) % ring->desc_num;
+	desc = &ring->desc[last_bd];
 
 	if (le32_to_cpu(desc->rx.rss_hash))
 		rss_type = handle->kinfo.rss_type;
-- 
cgit v1.2.3


From 1154bb26c879fea51c20aee167ddce4345caa255 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 20 Dec 2018 11:52:06 +0800
Subject: net: hns3: remove redundant variable initialization

This patch removes the redundant variable initialization,
as driver will devm_kzalloc to set value to hdev soon.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 156242f96a8e..82103d5fa815 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1721,7 +1721,7 @@ static int hclgevf_configure(struct hclgevf_dev *hdev)
 static int hclgevf_alloc_hdev(struct hnae3_ae_dev *ae_dev)
 {
 	struct pci_dev *pdev = ae_dev->pdev;
-	struct hclgevf_dev *hdev = ae_dev->priv;
+	struct hclgevf_dev *hdev;
 
 	hdev = devm_kzalloc(&pdev->dev, sizeof(*hdev), GFP_KERNEL);
 	if (!hdev)
-- 
cgit v1.2.3


From a9cd3439e3c6d777a05c63b4d06c3500d1d4074e Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 19 Dec 2018 20:02:36 -0800
Subject: neighbor: Use nda_policy for validating attributes in adds and dump
 requests

Add NDA_PROTOCOL to nda_policy and use the policy for attribute parsing and
validation for adding neighbors and in dump requests. Remove the now duplicate
checks on nla_len.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 22 +++++-----------------
 1 file changed, 5 insertions(+), 17 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index d9fa101b0e41..8baa9ab01db6 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1762,6 +1762,7 @@ const struct nla_policy nda_policy[NDA_MAX+1] = {
 	[NDA_VNI]		= { .type = NLA_U32 },
 	[NDA_IFINDEX]		= { .type = NLA_U32 },
 	[NDA_MASTER]		= { .type = NLA_U32 },
+	[NDA_PROTOCOL]		= { .type = NLA_U8 },
 };
 
 static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -1845,7 +1846,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err;
 
 	ASSERT_RTNL();
-	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
+	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, nda_policy, extack);
 	if (err < 0)
 		goto out;
 
@@ -1881,13 +1882,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	dst = nla_data(tb[NDA_DST]);
 	lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
 
-	if (tb[NDA_PROTOCOL]) {
-		if (nla_len(tb[NDA_PROTOCOL]) != sizeof(u8)) {
-			NL_SET_ERR_MSG(extack, "Invalid protocol attribute");
-			goto out;
-		}
+	if (tb[NDA_PROTOCOL])
 		protocol = nla_get_u8(tb[NDA_PROTOCOL]);
-	}
 
 	if (ndm->ndm_flags & NTF_PROXY) {
 		struct pneigh_entry *pn;
@@ -2639,10 +2635,10 @@ static int neigh_valid_dump_req(const struct nlmsghdr *nlh,
 		}
 
 		err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
-					 NULL, extack);
+					 nda_policy, extack);
 	} else {
 		err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
-				  NULL, extack);
+				  nda_policy, extack);
 	}
 	if (err < 0)
 		return err;
@@ -2654,17 +2650,9 @@ static int neigh_valid_dump_req(const struct nlmsghdr *nlh,
 		/* all new attributes should require strict_check */
 		switch (i) {
 		case NDA_IFINDEX:
-			if (nla_len(tb[i]) != sizeof(u32)) {
-				NL_SET_ERR_MSG(extack, "Invalid IFINDEX attribute in neighbor dump request");
-				return -EINVAL;
-			}
 			filter->dev_idx = nla_get_u32(tb[i]);
 			break;
 		case NDA_MASTER:
-			if (nla_len(tb[i]) != sizeof(u32)) {
-				NL_SET_ERR_MSG(extack, "Invalid MASTER attribute in neighbor dump request");
-				return -EINVAL;
-			}
 			filter->master_idx = nla_get_u32(tb[i]);
 			break;
 		default:
-- 
cgit v1.2.3


From 5d8678365c90b9ce1fd2243ff5ea562609f6cec1 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Mon, 3 Dec 2018 13:59:41 +0100
Subject: mlx5: update timecounter at least twice per counter overflow

The timecounter needs to be updated at least once in half of the
cyclecounter interval to prevent timecounter_cyc2time() interpreting a
new timestamp as an old value and causing a backward jump.

This would be an issue if the timecounter multiplier was so small that
the update interval would not be limited by the 64-bit overflow in
multiplication.

Shorten the calculated interval to make sure the timecounter is updated
in time even when the system clock is slowed down by up to 10%, the
multiplier is increased by up to 10%, and the scheduled overflow check
is late by 15%.

Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Ariel Levkovich <lariel@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index d27c239e7d6c..53f021df4934 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -517,14 +517,14 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 			 ktime_to_ns(ktime_get_real()));
 
 	/* Calculate period in seconds to call the overflow watchdog - to make
-	 * sure counter is checked at least once every wrap around.
+	 * sure counter is checked at least twice every wrap around.
 	 * The period is calculated as the minimum between max HW cycles count
 	 * (The clock source mask) and max amount of cycles that can be
 	 * multiplied by clock multiplier where the result doesn't exceed
 	 * 64bits.
 	 */
 	overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult);
-	overflow_cycles = min(overflow_cycles, clock->cycles.mask >> 1);
+	overflow_cycles = min(overflow_cycles, div_u64(clock->cycles.mask, 3));
 
 	ns = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles,
 				 frac, &frac);
-- 
cgit v1.2.3


From 4a0475d57ad134429f9bb56068bb738b4afc5992 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Mon, 3 Dec 2018 13:59:42 +0100
Subject: mlx5: extend PTP gettime function to read system clock

Read the system time right before and immediately after reading the low
register of the internal timer. This adds support for the
PTP_SYS_OFFSET_EXTENDED ioctl.

Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c | 20 ++++++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/main.c      | 11 +++++++++--
 drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h |  4 +++-
 3 files changed, 24 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 53f021df4934..ca0ee9916e9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -72,7 +72,7 @@ static u64 read_internal_timer(const struct cyclecounter *cc)
 	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
 						  clock);
 
-	return mlx5_read_internal_timer(mdev) & cc->mask;
+	return mlx5_read_internal_timer(mdev, NULL) & cc->mask;
 }
 
 static void mlx5_update_clock_info_page(struct mlx5_core_dev *mdev)
@@ -156,15 +156,19 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp,
 	return 0;
 }
 
-static int mlx5_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
+			     struct ptp_system_timestamp *sts)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
 						ptp_info);
-	u64 ns;
+	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
+						  clock);
 	unsigned long flags;
+	u64 cycles, ns;
 
 	write_seqlock_irqsave(&clock->lock, flags);
-	ns = timecounter_read(&clock->tc);
+	cycles = mlx5_read_internal_timer(mdev, sts);
+	ns = timecounter_cyc2time(&clock->tc, cycles);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 	*ts = ns_to_timespec64(ns);
@@ -307,7 +311,7 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 		ts.tv_sec = rq->perout.start.sec;
 		ts.tv_nsec = rq->perout.start.nsec;
 		ns = timespec64_to_ns(&ts);
-		cycles_now = mlx5_read_internal_timer(mdev);
+		cycles_now = mlx5_read_internal_timer(mdev, NULL);
 		write_seqlock_irqsave(&clock->lock, flags);
 		nsec_now = timecounter_cyc2time(&clock->tc, cycles_now);
 		nsec_delta = ns - nsec_now;
@@ -384,7 +388,7 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = {
 	.pps		= 0,
 	.adjfreq	= mlx5_ptp_adjfreq,
 	.adjtime	= mlx5_ptp_adjtime,
-	.gettime64	= mlx5_ptp_gettime,
+	.gettimex64	= mlx5_ptp_gettimex,
 	.settime64	= mlx5_ptp_settime,
 	.enable		= NULL,
 	.verify		= NULL,
@@ -469,8 +473,8 @@ static int mlx5_pps_event(struct notifier_block *nb,
 		ptp_clock_event(clock->ptp, &ptp_event);
 		break;
 	case PTP_PF_PEROUT:
-		mlx5_ptp_gettime(&clock->ptp_info, &ts);
-		cycles_now = mlx5_read_internal_timer(mdev);
+		mlx5_ptp_gettimex(&clock->ptp_info, &ts, NULL);
+		cycles_now = mlx5_read_internal_timer(mdev, NULL);
 		ts.tv_sec += 1;
 		ts.tv_nsec = 0;
 		ns = timespec64_to_ns(&ts);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c23553164e0d..77896c11f6f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -580,15 +580,22 @@ int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id)
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
+u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
+			     struct ptp_system_timestamp *sts)
 {
 	u32 timer_h, timer_h1, timer_l;
 
 	timer_h = ioread32be(&dev->iseg->internal_timer_h);
+	ptp_read_system_prets(sts);
 	timer_l = ioread32be(&dev->iseg->internal_timer_l);
+	ptp_read_system_postts(sts);
 	timer_h1 = ioread32be(&dev->iseg->internal_timer_h);
-	if (timer_h != timer_h1) /* wrap around */
+	if (timer_h != timer_h1) {
+		/* wrap around */
+		ptp_read_system_prets(sts);
 		timer_l = ioread32be(&dev->iseg->internal_timer_l);
+		ptp_read_system_postts(sts);
+	}
 
 	return (u64)timer_l | (u64)timer_h1 << 32;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 73bf46599ec6..c68dcea5985b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -38,6 +38,7 @@
 #include <linux/sched.h>
 #include <linux/if_link.h>
 #include <linux/firmware.h>
+#include <linux/ptp_clock_kernel.h>
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/fs.h>
 
@@ -121,7 +122,8 @@ int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 					u32 element_id);
 int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
-u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
+u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
+			     struct ptp_system_timestamp *sts);
 
 void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev);
 int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev);
-- 
cgit v1.2.3


From 4c8fb2986d44c5a75949a88ac61deec0ed50a542 Mon Sep 17 00:00:00 2001
From: Gavi Teitz <gavi@mellanox.com>
Date: Wed, 12 Dec 2018 21:23:18 +0200
Subject: net/mlx5e: Increase VF representors' SQ size to 128

The default size for the VF representors' SQ was too small to handle high
packet rates. Doubling the size from 64 to 128 drastically improves the
packet rate under stress (by about 50%), whereas increasing the size
beyond 128 has not shown to make any further difference.

The impact of the SQ size was measured with UDP traffic, in the following
topology: TG <-> PF <-> TC forwarding <-> VF representor <-> VF in VM
over a single core processing bi-directional traffic, with the following
results:

                                  SQ size of 64:     SQ size of 128:
Packet rate for 64B UDP packets:    860 [Kpps]         1280 [Kpps]
Packet rate for 114B VxLan
encapsulated UDP packets:           320 [Kpps]          500 [Kpps]

Signed-off-by: Gavi Teitz <gavi@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index ed1158b58798..18d0f4f7537b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -45,8 +45,8 @@
 #include "en/tc_tun.h"
 #include "fs_core.h"
 
-#define MLX5E_REP_PARAMS_LOG_SQ_SIZE \
-	max(0x6, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
+#define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \
+	max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
 
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
@@ -1336,7 +1336,7 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	if (rep->vport == FDB_UPLINK_VPORT)
 		params->log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
 	else
-		params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
+		params->log_sq_size = MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE;;
 
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
-- 
cgit v1.2.3


From 1ee4457c5c2a6172893eb1f464860c753c9b4e96 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 18 Dec 2018 13:32:46 +0200
Subject: net/mlx5e: Allow vlans on e-switch uplink reps

There are cases (e.g tunneling with vlan on underlay and potentially
more) where this makes sense, so allow that.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 18d0f4f7537b..91c3eb85f32e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1381,7 +1381,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 
 	netdev->switchdev_ops = &mlx5e_rep_switchdev_ops;
 
-	netdev->features	 |= NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL;
+	netdev->features	 |= NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL;
 	netdev->hw_features      |= NETIF_F_HW_TC;
 
 	netdev->hw_features    |= NETIF_F_SG;
@@ -1392,6 +1392,9 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	netdev->hw_features    |= NETIF_F_TSO6;
 	netdev->hw_features    |= NETIF_F_RXCSUM;
 
+	if (rep->vport != FDB_UPLINK_VPORT)
+		netdev->features |= NETIF_F_VLAN_CHALLENGED;
+
 	netdev->features |= netdev->hw_features;
 }
 
-- 
cgit v1.2.3


From a0646c88ed3ac527b71cf365b03ff4fc729d35b6 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Wed, 19 Dec 2018 09:24:58 +0200
Subject: net/mlx5e: Fail attempt to offload e-switch TC flows with egress
 upper devices

We use the switchdev parent HW id helper to identify if the mirred device
shares the same ASIC/port with the ingress device. This can get us wrong
in the presence of upper devices such as vlan or bridge set over the HW
devices (VF or uplink representors), b/c the switchdev ID is retrieved
recursively.

To fail offload attempts in such cases, we condition the check on the
egress device to have not only the same switchdev ID but also the relevant
mlx5 netdev ops.

Fixes: 03a9d11e6eeb ('net/mlx5e: Add TC drop and mirred/redirect action parsing for SRIOV offloads')
Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Acked-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 9 +++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c  | 3 +++
 3 files changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 91c3eb85f32e..f414f19c1159 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1316,6 +1316,15 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = {
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
 };
 
+bool mlx5e_eswitch_rep(struct net_device *netdev)
+{
+	if (netdev->netdev_ops == &mlx5e_netdev_ops_vf_rep ||
+	    netdev->netdev_ops == &mlx5e_netdev_ops_uplink_rep)
+		return true;
+
+	return false;
+}
+
 static void mlx5e_build_rep_params(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 5645d3cef1bb..edd722824697 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -176,6 +176,9 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
 				  struct mlx5e_encap_entry *e);
 
 void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
+
+bool mlx5e_eswitch_rep(struct net_device *netdev);
+
 #else /* CONFIG_MLX5_ESWITCH */
 static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; }
 static inline int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index c1a9120412b8..9ba8ade3be47 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2583,6 +2583,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				    uplink_upper == out_dev)
 					out_dev = uplink_dev;
 
+				if (!mlx5e_eswitch_rep(out_dev))
+					return -EOPNOTSUPP;
+
 				out_priv = netdev_priv(out_dev);
 				rpriv = out_priv->ppriv;
 				attr->dests[attr->out_count].rep = rpriv->rep;
-- 
cgit v1.2.3


From 442e1228cbaccee8a9365624608544460155c5d1 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Tue, 18 Dec 2018 09:46:00 +0200
Subject: net/mlx5e: Tunnel routing output devs helper function

For tunnel we determine the output devs for IPv4/6 cases, in two
separate functions, with a duplicated code.

Move that code from IPv4/6 functions to a helper function, with no
functional change.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    | 70 +++++++++++-----------
 1 file changed, 34 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index b92f8b3ff6b2..c90a0f9cb6e1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -6,6 +6,34 @@
 #include "lib/vxlan.h"
 #include "en/tc_tun.h"
 
+static int get_route_and_out_devs(struct mlx5e_priv *priv,
+				  struct net_device *dev,
+				  struct net_device **route_dev,
+				  struct net_device **out_dev)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct net_device *uplink_dev, *uplink_upper;
+	bool dst_is_lag_dev;
+
+	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
+	uplink_upper = netdev_master_upper_dev_get(uplink_dev);
+	dst_is_lag_dev = (uplink_upper &&
+			  netif_is_lag_master(uplink_upper) &&
+			  dev == uplink_upper &&
+			  mlx5_lag_is_sriov(priv->mdev));
+
+	/* if the egress device isn't on the same HW e-switch or
+	 * it's a LAG device, use the uplink
+	 */
+	if (!switchdev_port_same_parent_id(priv->netdev, dev) ||
+	    dst_is_lag_dev)
+		*out_dev = uplink_dev;
+	else
+		*out_dev = dev;
+
+	return 0;
+}
+
 static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 				   struct net_device *mirred_dev,
 				   struct net_device **out_dev,
@@ -13,9 +41,6 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 				   struct neighbour **out_n,
 				   u8 *out_ttl)
 {
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct net_device *uplink_dev, *uplink_upper;
-	bool dst_is_lag_dev;
 	struct rtable *rt;
 	struct neighbour *n = NULL;
 
@@ -30,21 +55,9 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	return -EOPNOTSUPP;
 #endif
 
-	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
-	uplink_upper = netdev_master_upper_dev_get(uplink_dev);
-	dst_is_lag_dev = (uplink_upper &&
-			  netif_is_lag_master(uplink_upper) &&
-			  rt->dst.dev == uplink_upper &&
-			  mlx5_lag_is_sriov(priv->mdev));
-
-	/* if the egress device isn't on the same HW e-switch or
-	 * it's a LAG device, use the uplink
-	 */
-	if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev) ||
-	    dst_is_lag_dev)
-		*out_dev = uplink_dev;
-	else
-		*out_dev = rt->dst.dev;
+	ret = get_route_and_out_devs(priv, rt->dst.dev, NULL, out_dev);
+	if (ret < 0)
+		return ret;
 
 	if (!(*out_ttl))
 		*out_ttl = ip4_dst_hoplimit(&rt->dst);
@@ -76,9 +89,6 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	struct dst_entry *dst;
 
 #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct net_device *uplink_dev, *uplink_upper;
-	bool dst_is_lag_dev;
 	int ret;
 
 	ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst,
@@ -89,21 +99,9 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	if (!(*out_ttl))
 		*out_ttl = ip6_dst_hoplimit(dst);
 
-	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
-	uplink_upper = netdev_master_upper_dev_get(uplink_dev);
-	dst_is_lag_dev = (uplink_upper &&
-			  netif_is_lag_master(uplink_upper) &&
-			  dst->dev == uplink_upper &&
-			  mlx5_lag_is_sriov(priv->mdev));
-
-	/* if the egress device isn't on the same HW e-switch or
-	 * it's a LAG device, use the uplink
-	 */
-	if (!switchdev_port_same_parent_id(priv->netdev, dst->dev) ||
-	    dst_is_lag_dev)
-		*out_dev = uplink_dev;
-	else
-		*out_dev = dst->dev;
+	ret = get_route_and_out_devs(priv, dst->dev, NULL, out_dev);
+	if (ret < 0)
+		return ret;
 #else
 	return -EOPNOTSUPP;
 #endif
-- 
cgit v1.2.3


From b168cff0b9b216e68215cdb28db999f542482a56 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Wed, 19 Dec 2018 09:29:10 +0200
Subject: net/mlx5e: Fail attempt to offload e-switch TC encap flows with vlan
 on underlay

Currently we don't support nor fail attempts to offload encap flows routed
to vlan device on the underlay network. We wrongly consider a vlan underlay
device to be on the same e-switch b/c the switchdev ID is retrieved recursively.

Add explicit check for that and fail such attempts.

Also align to a more strict check for the ingress and the underlay devices
to practically be on the same eswitch.

Fixes: ce99f6b97fcd ('net/mlx5e: Support SRIOV TC encapsulation offloads for IPv6 tunnels')
Fixes: 3e621b19b0bb ('net/mlx5e: Support TC encapsulation offloads with upper devices')
Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index c90a0f9cb6e1..0d24e9648c21 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -15,6 +15,10 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 	struct net_device *uplink_dev, *uplink_upper;
 	bool dst_is_lag_dev;
 
+	/* we currently don't offload vlan on underlay */
+	if (is_vlan_dev(dev))
+		return -EOPNOTSUPP;
+
 	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
 	uplink_upper = netdev_master_upper_dev_get(uplink_dev);
 	dst_is_lag_dev = (uplink_upper &&
@@ -28,6 +32,8 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 	if (!switchdev_port_same_parent_id(priv->netdev, dev) ||
 	    dst_is_lag_dev)
 		*out_dev = uplink_dev;
+	else if (!mlx5e_eswitch_rep(dev))
+		return -EOPNOTSUPP;
 	else
 		*out_dev = dev;
 
-- 
cgit v1.2.3


From 05ada1adb65acd533f978651e7001e3568e7b98a Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sun, 9 Dec 2018 09:17:18 +0200
Subject: net/mlx5e: Tunnel encap ETH header helper function

In tunnel encap we prepare the encap header for IPv4/6 cases, in two
separate functions. For ETH header generation the code is almost
duplicated.

Move the ETH header generation code from IPv4/6 functions to a helper
function, with no functional change.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    | 29 +++++++++++++---------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 0d24e9648c21..f90c67c9add0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -180,6 +180,19 @@ static int mlx5e_gen_ip_tunnel_header(char buf[], __u8 *ip_proto,
 	return err;
 }
 
+static char *gen_eth_tnl_hdr(char *buf, struct net_device *dev,
+			     struct mlx5e_encap_entry *e,
+			     u16 proto)
+{
+	struct ethhdr *eth = (struct ethhdr *)buf;
+
+	ether_addr_copy(eth->h_dest, e->h_dest);
+	ether_addr_copy(eth->h_source, dev->dev_addr);
+	eth->h_proto = htons(proto);
+
+	return (char *)eth + ETH_HLEN;
+}
+
 int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 				    struct net_device *mirred_dev,
 				    struct mlx5e_encap_entry *e)
@@ -193,7 +206,6 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
 	char *encap_header;
-	struct ethhdr *eth;
 	u8 nud_state, ttl;
 	struct iphdr *ip;
 	int err;
@@ -242,13 +254,10 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	read_unlock_bh(&n->lock);
 
 	/* add ethernet header */
-	eth = (struct ethhdr *)encap_header;
-	ether_addr_copy(eth->h_dest, e->h_dest);
-	ether_addr_copy(eth->h_source, out_dev->dev_addr);
-	eth->h_proto = htons(ETH_P_IP);
+	ip = (struct iphdr *)gen_eth_tnl_hdr(encap_header, out_dev, e,
+					     ETH_P_IP);
 
 	/* add ip header */
-	ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr));
 	ip->tos = tun_key->tos;
 	ip->version = 0x4;
 	ip->ihl = 0x5;
@@ -308,7 +317,6 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	struct flowi6 fl6 = {};
 	struct ipv6hdr *ip6h;
 	char *encap_header;
-	struct ethhdr *eth;
 	u8 nud_state, ttl;
 	int err;
 
@@ -356,13 +364,10 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	read_unlock_bh(&n->lock);
 
 	/* add ethernet header */
-	eth = (struct ethhdr *)encap_header;
-	ether_addr_copy(eth->h_dest, e->h_dest);
-	ether_addr_copy(eth->h_source, out_dev->dev_addr);
-	eth->h_proto = htons(ETH_P_IPV6);
+	ip6h = (struct ipv6hdr *)gen_eth_tnl_hdr(encap_header, out_dev, e,
+						 ETH_P_IPV6);
 
 	/* add ip header */
-	ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr));
 	ip6_flow_hdr(ip6h, tun_key->tos, 0);
 	/* the HW fills up ipv6 payload len */
 	ip6h->hop_limit   = ttl;
-- 
cgit v1.2.3


From c7bcb277bda46d75819fb2d475fa817c10dc209b Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Mon, 3 Dec 2018 17:09:54 +0200
Subject: net/mlx5e: Re-order route and encap header memory allocation

Change the order to first route IPv4/6 and return if error. Only after
successful route continue to allocate an encap header, with no
functional change.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    | 62 ++++++++++++----------
 1 file changed, 34 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index f90c67c9add0..bcf08f5abc2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -198,28 +198,16 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 				    struct mlx5e_encap_entry *e)
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	int ipv4_encap_size = ETH_HLEN +
-			      sizeof(struct iphdr) +
-			      e->tunnel_hlen;
 	struct ip_tunnel_key *tun_key = &e->tun_info.key;
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
+	int ipv4_encap_size;
 	char *encap_header;
 	u8 nud_state, ttl;
 	struct iphdr *ip;
 	int err;
 
-	if (max_encap_size < ipv4_encap_size) {
-		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
-			       ipv4_encap_size, max_encap_size);
-		return -EOPNOTSUPP;
-	}
-
-	encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL);
-	if (!encap_header)
-		return -ENOMEM;
-
 	/* add the IP fields */
 	fl4.flowi4_tos = tun_key->tos;
 	fl4.daddr = tun_key->u.ipv4.dst;
@@ -229,7 +217,22 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev,
 				      &fl4, &n, &ttl);
 	if (err)
-		goto free_encap;
+		return err;
+
+	ipv4_encap_size =
+		ETH_HLEN +
+		sizeof(struct iphdr) +
+		e->tunnel_hlen;
+
+	if (max_encap_size < ipv4_encap_size) {
+		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
+			       ipv4_encap_size, max_encap_size);
+		return -EOPNOTSUPP;
+	}
+
+	encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL);
+	if (!encap_header)
+		return -ENOMEM;
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
 	 * entry in the neigh hash table when a user deletes a rule
@@ -308,28 +311,16 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 				    struct mlx5e_encap_entry *e)
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	int ipv6_encap_size = ETH_HLEN +
-			      sizeof(struct ipv6hdr) +
-			      e->tunnel_hlen;
 	struct ip_tunnel_key *tun_key = &e->tun_info.key;
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi6 fl6 = {};
 	struct ipv6hdr *ip6h;
+	int ipv6_encap_size;
 	char *encap_header;
 	u8 nud_state, ttl;
 	int err;
 
-	if (max_encap_size < ipv6_encap_size) {
-		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
-			       ipv6_encap_size, max_encap_size);
-		return -EOPNOTSUPP;
-	}
-
-	encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL);
-	if (!encap_header)
-		return -ENOMEM;
-
 	ttl = tun_key->ttl;
 
 	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
@@ -339,7 +330,22 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev,
 				      &fl6, &n, &ttl);
 	if (err)
-		goto free_encap;
+		return err;
+
+	ipv6_encap_size =
+		ETH_HLEN +
+		sizeof(struct ipv6hdr) +
+		e->tunnel_hlen;
+
+	if (max_encap_size < ipv6_encap_size) {
+		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
+			       ipv6_encap_size, max_encap_size);
+		return -EOPNOTSUPP;
+	}
+
+	encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL);
+	if (!encap_header)
+		return -ENOMEM;
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
 	 * entry in the neigh hash table when a user deletes a rule
-- 
cgit v1.2.3


From aa331450b81f071bc8d7b68d5baab1b78f93598a Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sun, 9 Dec 2018 09:17:18 +0200
Subject: net/mlx5e: Support VLAN encap ETH header generation

Support generation of native or tagged Ethernet header for encap
header, depending on provided net device.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index bcf08f5abc2f..a6990744730a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -185,12 +185,23 @@ static char *gen_eth_tnl_hdr(char *buf, struct net_device *dev,
 			     u16 proto)
 {
 	struct ethhdr *eth = (struct ethhdr *)buf;
+	char *ip;
 
 	ether_addr_copy(eth->h_dest, e->h_dest);
 	ether_addr_copy(eth->h_source, dev->dev_addr);
-	eth->h_proto = htons(proto);
+	if (is_vlan_dev(dev)) {
+		struct vlan_hdr *vlan = (struct vlan_hdr *)
+					((char *)eth + ETH_HLEN);
+		ip = (char *)vlan + VLAN_HLEN;
+		eth->h_proto = vlan_dev_vlan_proto(dev);
+		vlan->h_vlan_TCI = htons(vlan_dev_vlan_id(dev));
+		vlan->h_vlan_encapsulated_proto = htons(proto);
+	} else {
+		eth->h_proto = htons(proto);
+		ip = (char *)eth + ETH_HLEN;
+	}
 
-	return (char *)eth + ETH_HLEN;
+	return ip;
 }
 
 int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
-- 
cgit v1.2.3


From e32ee6c78efa6a32bff782bbe7a9970b018996ca Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Mon, 3 Dec 2018 17:09:54 +0200
Subject: net/mlx5e: Support tunnel encap over tagged Ethernet

Generate encap header depending on the routed device to support
native/tagged Ethernet header.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    | 44 ++++++++++++----------
 1 file changed, 24 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index a6990744730a..046948ead152 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -15,10 +15,6 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 	struct net_device *uplink_dev, *uplink_upper;
 	bool dst_is_lag_dev;
 
-	/* we currently don't offload vlan on underlay */
-	if (is_vlan_dev(dev))
-		return -EOPNOTSUPP;
-
 	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
 	uplink_upper = netdev_master_upper_dev_get(uplink_dev);
 	dst_is_lag_dev = (uplink_upper &&
@@ -30,12 +26,18 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 	 * it's a LAG device, use the uplink
 	 */
 	if (!switchdev_port_same_parent_id(priv->netdev, dev) ||
-	    dst_is_lag_dev)
-		*out_dev = uplink_dev;
-	else if (!mlx5e_eswitch_rep(dev))
-		return -EOPNOTSUPP;
-	else
-		*out_dev = dev;
+	    dst_is_lag_dev) {
+		*route_dev = uplink_dev;
+		*out_dev = *route_dev;
+	} else {
+		*route_dev = dev;
+		if (is_vlan_dev(*route_dev))
+			*out_dev = uplink_dev;
+		else if (mlx5e_eswitch_rep(dev))
+			*out_dev = *route_dev;
+		else
+			return -EOPNOTSUPP;
+	}
 
 	return 0;
 }
@@ -43,6 +45,7 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 				   struct net_device *mirred_dev,
 				   struct net_device **out_dev,
+				   struct net_device **route_dev,
 				   struct flowi4 *fl4,
 				   struct neighbour **out_n,
 				   u8 *out_ttl)
@@ -61,7 +64,7 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	return -EOPNOTSUPP;
 #endif
 
-	ret = get_route_and_out_devs(priv, rt->dst.dev, NULL, out_dev);
+	ret = get_route_and_out_devs(priv, rt->dst.dev, route_dev, out_dev);
 	if (ret < 0)
 		return ret;
 
@@ -87,6 +90,7 @@ static const char *mlx5e_netdev_kind(struct net_device *dev)
 static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 				   struct net_device *mirred_dev,
 				   struct net_device **out_dev,
+				   struct net_device **route_dev,
 				   struct flowi6 *fl6,
 				   struct neighbour **out_n,
 				   u8 *out_ttl)
@@ -105,7 +109,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	if (!(*out_ttl))
 		*out_ttl = ip6_dst_hoplimit(dst);
 
-	ret = get_route_and_out_devs(priv, dst->dev, NULL, out_dev);
+	ret = get_route_and_out_devs(priv, dst->dev, route_dev, out_dev);
 	if (ret < 0)
 		return ret;
 #else
@@ -210,7 +214,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
 	struct ip_tunnel_key *tun_key = &e->tun_info.key;
-	struct net_device *out_dev;
+	struct net_device *out_dev, *route_dev;
 	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
 	int ipv4_encap_size;
@@ -225,13 +229,13 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	fl4.saddr = tun_key->u.ipv4.src;
 	ttl = tun_key->ttl;
 
-	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev,
+	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, &route_dev,
 				      &fl4, &n, &ttl);
 	if (err)
 		return err;
 
 	ipv4_encap_size =
-		ETH_HLEN +
+		(is_vlan_dev(route_dev) ? VLAN_ETH_HLEN : ETH_HLEN) +
 		sizeof(struct iphdr) +
 		e->tunnel_hlen;
 
@@ -268,7 +272,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	read_unlock_bh(&n->lock);
 
 	/* add ethernet header */
-	ip = (struct iphdr *)gen_eth_tnl_hdr(encap_header, out_dev, e,
+	ip = (struct iphdr *)gen_eth_tnl_hdr(encap_header, route_dev, e,
 					     ETH_P_IP);
 
 	/* add ip header */
@@ -323,7 +327,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
 	struct ip_tunnel_key *tun_key = &e->tun_info.key;
-	struct net_device *out_dev;
+	struct net_device *out_dev, *route_dev;
 	struct neighbour *n = NULL;
 	struct flowi6 fl6 = {};
 	struct ipv6hdr *ip6h;
@@ -338,13 +342,13 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	fl6.daddr = tun_key->u.ipv6.dst;
 	fl6.saddr = tun_key->u.ipv6.src;
 
-	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev,
+	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, &route_dev,
 				      &fl6, &n, &ttl);
 	if (err)
 		return err;
 
 	ipv6_encap_size =
-		ETH_HLEN +
+		(is_vlan_dev(route_dev) ? VLAN_ETH_HLEN : ETH_HLEN) +
 		sizeof(struct ipv6hdr) +
 		e->tunnel_hlen;
 
@@ -381,7 +385,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	read_unlock_bh(&n->lock);
 
 	/* add ethernet header */
-	ip6h = (struct ipv6hdr *)gen_eth_tnl_hdr(encap_header, out_dev, e,
+	ip6h = (struct ipv6hdr *)gen_eth_tnl_hdr(encap_header, route_dev, e,
 						 ETH_P_IPV6);
 
 	/* add ip header */
-- 
cgit v1.2.3


From 0a5b589111c395f2b18c2a508e241207daaa8cca Mon Sep 17 00:00:00 2001
From: Aviv Heller <avivh@mellanox.com>
Date: Thu, 20 Dec 2018 01:37:17 +0200
Subject: net/mlx5: Fix query_nic_sys_image_guid() error during init

vport system image guid should be queried using vport nic API for
Ethernet ports, and vport hca API for Infiniband ports.

Fixes: fadd59fc50d0 ("net/mlx5: Introduce inter-device communication mechanism")
Signed-off-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vport.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index cfbea66b4879..9b150ce9d315 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -1204,9 +1204,19 @@ EXPORT_SYMBOL_GPL(mlx5_nic_vport_unaffiliate_multiport);
 
 u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev)
 {
-	if (!mdev->sys_image_guid)
-		mlx5_query_nic_vport_system_image_guid(mdev, &mdev->sys_image_guid);
+	int port_type_cap = MLX5_CAP_GEN(mdev, port_type);
+	u64 tmp = 0;
 
-	return mdev->sys_image_guid;
+	if (mdev->sys_image_guid)
+		return mdev->sys_image_guid;
+
+	if (port_type_cap == MLX5_CAP_PORT_TYPE_ETH)
+		mlx5_query_nic_vport_system_image_guid(mdev, &tmp);
+	else
+		mlx5_query_hca_vport_system_image_guid(mdev, &tmp);
+
+	mdev->sys_image_guid = tmp;
+
+	return tmp;
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid);
-- 
cgit v1.2.3


From a64917446eafc7212e962561622d697fce04e9a6 Mon Sep 17 00:00:00 2001
From: Aviv Heller <avivh@mellanox.com>
Date: Tue, 18 Dec 2018 19:03:27 +0200
Subject: net/mlx5: Fix LAG requirement when CONFIG_MLX5_ESWITCH is off

If CONFIG_MLX5_ESWITCH is not defined, test for SR-IOV being disabled,
instead of calling e-switch LAG prereq routine.

Since LAG with SRIOV is allowed only when switchdev mode is on.

Fixes: eff849b2c669 ("net/mlx5: Allow/disallow LAG according to pre-req only")
Signed-off-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 5187dc7a72a3..3a6baed722d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -291,12 +291,15 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 
 static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
 {
-	if (ldev->pf[0].dev &&
-	    ldev->pf[1].dev &&
-	    mlx5_esw_lag_prereq(ldev->pf[0].dev, ldev->pf[1].dev))
-		return true;
-	else
+	if (!ldev->pf[0].dev || !ldev->pf[1].dev)
 		return false;
+
+#ifdef CONFIG_MLX5_ESWITCH
+	return mlx5_esw_lag_prereq(ldev->pf[0].dev, ldev->pf[1].dev);
+#else
+	return (!mlx5_sriov_is_enabled(ldev->pf[0].dev) &&
+		!mlx5_sriov_is_enabled(ldev->pf[1].dev));
+#endif
 }
 
 static void mlx5_lag_add_ib_devices(struct mlx5_lag *ldev)
-- 
cgit v1.2.3


From 3322479e6d17ea17b75848fd7c7702ccf82c9c35 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 20 Dec 2018 03:38:43 -0500
Subject: bnxt_en: Update firmware interface spec. to 1.10.0.33.

The major changes are in the flow offload firmware APIs.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 614 +++++++++++++++++++++-----
 1 file changed, 502 insertions(+), 112 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 5dd086059568..f1aaac8e6268 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -194,6 +194,8 @@ struct cmd_nums {
 	#define HWRM_STAT_CTX_QUERY                       0xb2UL
 	#define HWRM_STAT_CTX_CLR_STATS                   0xb3UL
 	#define HWRM_PORT_QSTATS_EXT                      0xb4UL
+	#define HWRM_PORT_PHY_MDIO_WRITE                  0xb5UL
+	#define HWRM_PORT_PHY_MDIO_READ                   0xb6UL
 	#define HWRM_FW_RESET                             0xc0UL
 	#define HWRM_FW_QSTATUS                           0xc1UL
 	#define HWRM_FW_HEALTH_CHECK                      0xc2UL
@@ -213,6 +215,7 @@ struct cmd_nums {
 	#define HWRM_WOL_FILTER_FREE                      0xf1UL
 	#define HWRM_WOL_FILTER_QCFG                      0xf2UL
 	#define HWRM_WOL_REASON_QCFG                      0xf3UL
+	#define HWRM_CFA_METER_QCAPS                      0xf4UL
 	#define HWRM_CFA_METER_PROFILE_ALLOC              0xf5UL
 	#define HWRM_CFA_METER_PROFILE_FREE               0xf6UL
 	#define HWRM_CFA_METER_PROFILE_CFG                0xf7UL
@@ -239,6 +242,24 @@ struct cmd_nums {
 	#define HWRM_FW_IPC_MSG                           0x110UL
 	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_INFO        0x111UL
 	#define HWRM_CFA_REDIRECT_QUERY_TUNNEL_TYPE       0x112UL
+	#define HWRM_CFA_FLOW_AGING_TIMER_RESET           0x113UL
+	#define HWRM_CFA_FLOW_AGING_CFG                   0x114UL
+	#define HWRM_CFA_FLOW_AGING_QCFG                  0x115UL
+	#define HWRM_CFA_FLOW_AGING_QCAPS                 0x116UL
+	#define HWRM_CFA_CTX_MEM_RGTR                     0x117UL
+	#define HWRM_CFA_CTX_MEM_UNRGTR                   0x118UL
+	#define HWRM_CFA_CTX_MEM_QCTX                     0x119UL
+	#define HWRM_CFA_CTX_MEM_QCAPS                    0x11aUL
+	#define HWRM_CFA_COUNTER_QCAPS                    0x11bUL
+	#define HWRM_CFA_COUNTER_CFG                      0x11cUL
+	#define HWRM_CFA_COUNTER_QCFG                     0x11dUL
+	#define HWRM_CFA_COUNTER_QSTATS                   0x11eUL
+	#define HWRM_CFA_TCP_FLAG_PROCESS_QCFG            0x11fUL
+	#define HWRM_CFA_EEM_QCAPS                        0x120UL
+	#define HWRM_CFA_EEM_CFG                          0x121UL
+	#define HWRM_CFA_EEM_QCFG                         0x122UL
+	#define HWRM_CFA_EEM_OP                           0x123UL
+	#define HWRM_CFA_ADV_FLOW_MGNT_QCAPS              0x124UL
 	#define HWRM_ENGINE_CKV_HELLO                     0x12dUL
 	#define HWRM_ENGINE_CKV_STATUS                    0x12eUL
 	#define HWRM_ENGINE_CKV_CKEK_ADD                  0x12fUL
@@ -335,6 +356,8 @@ struct ret_codes {
 	#define HWRM_ERR_CODE_UNSUPPORTED_TLV           0x7UL
 	#define HWRM_ERR_CODE_NO_BUFFER                 0x8UL
 	#define HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR    0x9UL
+	#define HWRM_ERR_CODE_HOT_RESET_PROGRESS        0xaUL
+	#define HWRM_ERR_CODE_HOT_RESET_FAIL            0xbUL
 	#define HWRM_ERR_CODE_HWRM_ERROR                0xfUL
 	#define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE 0x8000UL
 	#define HWRM_ERR_CODE_UNKNOWN_ERR               0xfffeUL
@@ -363,8 +386,8 @@ struct hwrm_err_output {
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 10
 #define HWRM_VERSION_UPDATE 0
-#define HWRM_VERSION_RSVD 3
-#define HWRM_VERSION_STR "1.10.0.3"
+#define HWRM_VERSION_RSVD 33
+#define HWRM_VERSION_STR "1.10.0.33"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -411,6 +434,10 @@ struct hwrm_ver_get_output {
 	#define VER_GET_RESP_DEV_CAPS_CFG_L2_FILTER_TYPES_ROCE_OR_L2_SUPPORTED     0x40UL
 	#define VER_GET_RESP_DEV_CAPS_CFG_VIRTIO_VSWITCH_OFFLOAD_SUPPORTED         0x80UL
 	#define VER_GET_RESP_DEV_CAPS_CFG_TRUSTED_VF_SUPPORTED                     0x100UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_FLOW_AGING_SUPPORTED                     0x200UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_ADV_FLOW_COUNTERS_SUPPORTED              0x400UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_EEM_SUPPORTED                        0x800UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED              0x1000UL
 	u8	roce_fw_maj_8b;
 	u8	roce_fw_min_8b;
 	u8	roce_fw_bld_8b;
@@ -465,14 +492,27 @@ struct hwrm_ver_get_output {
 /* eject_cmpl (size:128b/16B) */
 struct eject_cmpl {
 	__le16	type;
-	#define EJECT_CMPL_TYPE_MASK      0x3fUL
-	#define EJECT_CMPL_TYPE_SFT       0
-	#define EJECT_CMPL_TYPE_STAT_EJECT  0x1aUL
-	#define EJECT_CMPL_TYPE_LAST       EJECT_CMPL_TYPE_STAT_EJECT
+	#define EJECT_CMPL_TYPE_MASK       0x3fUL
+	#define EJECT_CMPL_TYPE_SFT        0
+	#define EJECT_CMPL_TYPE_STAT_EJECT   0x1aUL
+	#define EJECT_CMPL_TYPE_LAST        EJECT_CMPL_TYPE_STAT_EJECT
+	#define EJECT_CMPL_FLAGS_MASK      0xffc0UL
+	#define EJECT_CMPL_FLAGS_SFT       6
+	#define EJECT_CMPL_FLAGS_ERROR      0x40UL
 	__le16	len;
 	__le32	opaque;
-	__le32	v;
-	#define EJECT_CMPL_V     0x1UL
+	__le16	v;
+	#define EJECT_CMPL_V                              0x1UL
+	#define EJECT_CMPL_ERRORS_MASK                    0xfffeUL
+	#define EJECT_CMPL_ERRORS_SFT                     1
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_MASK        0xeUL
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_SFT         1
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_NO_BUFFER     (0x0UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_DID_NOT_FIT   (0x1UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_BAD_FORMAT    (0x3UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH         (0x5UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_LAST         EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH
+	__le16	reserved16;
 	__le32	unused_2;
 };
 
@@ -552,6 +592,10 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LLFC_PFC_CHANGE            0x34UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFAULT_VNIC_CHANGE        0x35UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_FLOW_AGED               0x36UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DEBUG_NOTIFICATION         0x37UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_REQ        0x38UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_DONE       0x39UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG               0xfeUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                 0xffUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                      ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
 	__le32	event_data2;
@@ -647,6 +691,39 @@ struct hwrm_async_event_cmpl_link_speed_cfg_change {
 	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_ILLEGAL_LINK_SPEED_CFG           0x20000UL
 };
 
+/* hwrm_async_event_cmpl_reset_notify (size:128b/16B) */
+struct hwrm_async_event_cmpl_reset_notify {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_LAST             ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY 0x8UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_LAST        ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_V          0x1UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_MASK                  0xffUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_SFT                   0
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_STOP_TX_QUEUE    0x1UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN           0x2UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_LAST                   ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK                    0xff00UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_SFT                     8
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MANAGEMENT_RESET_REQUEST  (0x1UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL        (0x2UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_NON_FATAL    (0x3UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_LAST                     ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_NON_FATAL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_MASK           0xffff0000UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_SFT            16
+};
+
 /* hwrm_async_event_cmpl_vf_cfg_change (size:128b/16B) */
 struct hwrm_async_event_cmpl_vf_cfg_change {
 	__le16	type;
@@ -672,6 +749,74 @@ struct hwrm_async_event_cmpl_vf_cfg_change {
 	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_TRUSTED_VF_CFG_CHANGE     0x10UL
 };
 
+/* hwrm_async_event_cmpl_hw_flow_aged (size:128b/16B) */
+struct hwrm_async_event_cmpl_hw_flow_aged {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_LAST             ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED 0x36UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_LAST        ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_V          0x1UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_MASK       0x7fffffffUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_SFT        0
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION     0x80000000UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_RX    (0x0UL << 31)
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX    (0x1UL << 31)
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_LAST ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX
+};
+
+/* hwrm_async_event_cmpl_eem_cache_flush_req (size:128b/16B) */
+struct hwrm_async_event_cmpl_eem_cache_flush_req {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ 0x38UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_LAST               ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_V          0x1UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_eem_cache_flush_done (size:128b/16B) */
+struct hwrm_async_event_cmpl_eem_cache_flush_done {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE 0x39UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_LAST                ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_SFT 0
+};
+
 /* hwrm_func_reset_input (size:192b/24B) */
 struct hwrm_func_reset_input {
 	__le16	req_type;
@@ -867,6 +1012,8 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_FLAGS_ADMIN_PF_SUPPORTED              0x40000UL
 	#define FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED     0x80000UL
 	#define FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE                   0x100000UL
+	#define FUNC_QCAPS_RESP_FLAGS_DYNAMIC_TX_RING_ALLOC           0x200000UL
+	#define FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE               0x400000UL
 	u8	mac_address[6];
 	__le16	max_rsscos_ctx;
 	__le16	max_cmpl_rings;
@@ -902,7 +1049,7 @@ struct hwrm_func_qcfg_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_func_qcfg_output (size:640b/80B) */
+/* hwrm_func_qcfg_output (size:704b/88B) */
 struct hwrm_func_qcfg_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -919,6 +1066,7 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED        0x10UL
 	#define FUNC_QCFG_RESP_FLAGS_MULTI_HOST                   0x20UL
 	#define FUNC_QCFG_RESP_FLAGS_TRUSTED_VF                   0x40UL
+	#define FUNC_QCFG_RESP_FLAGS_SECURE_MODE_ENABLED          0x80UL
 	u8	mac_address[6];
 	__le16	pci_id;
 	__le16	alloc_rsscos_ctx;
@@ -1000,7 +1148,11 @@ struct hwrm_func_qcfg_output {
 	__le16	alloc_sp_tx_rings;
 	__le16	alloc_stat_ctx;
 	__le16	alloc_msix;
-	u8	unused_2[5];
+	__le16	registered_vfs;
+	u8	unused_1[3];
+	u8	always_1;
+	__le32	reset_addr_poll;
+	u8	unused_2[3];
 	u8	valid;
 };
 
@@ -1031,6 +1183,7 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_FLAGS_VNIC_ASSETS_TEST               0x80000UL
 	#define FUNC_CFG_REQ_FLAGS_L2_CTX_ASSETS_TEST             0x100000UL
 	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE              0x200000UL
+	#define FUNC_CFG_REQ_FLAGS_DYNAMIC_TX_RING_ALLOC          0x400000UL
 	__le32	enables;
 	#define FUNC_CFG_REQ_ENABLES_MTU                     0x1UL
 	#define FUNC_CFG_REQ_ENABLES_MRU                     0x2UL
@@ -1235,6 +1388,7 @@ struct hwrm_func_drv_rgtr_input {
 	#define FUNC_DRV_RGTR_REQ_FLAGS_FWD_NONE_MODE              0x2UL
 	#define FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE             0x4UL
 	#define FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE     0x8UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT          0x10UL
 	__le32	enables;
 	#define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE             0x1UL
 	#define FUNC_DRV_RGTR_REQ_ENABLES_VER                 0x2UL
@@ -1888,7 +2042,8 @@ struct hwrm_func_drv_if_change_output {
 	__le16	seq_id;
 	__le16	resp_len;
 	__le32	flags;
-	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE     0x1UL
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE           0x1UL
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE     0x2UL
 	u8	unused_0[3];
 	u8	valid;
 };
@@ -2864,6 +3019,60 @@ struct hwrm_port_phy_i2c_read_output {
 	u8	valid;
 };
 
+/* hwrm_port_phy_mdio_write_input (size:320b/40B) */
+struct hwrm_port_phy_mdio_write_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	unused_0[2];
+	__le16	port_id;
+	u8	phy_addr;
+	u8	dev_addr;
+	__le16	reg_addr;
+	__le16	reg_data;
+	u8	cl45_mdio;
+	u8	unused_1[7];
+};
+
+/* hwrm_port_phy_mdio_write_output (size:128b/16B) */
+struct hwrm_port_phy_mdio_write_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_phy_mdio_read_input (size:256b/32B) */
+struct hwrm_port_phy_mdio_read_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	unused_0[2];
+	__le16	port_id;
+	u8	phy_addr;
+	u8	dev_addr;
+	__le16	reg_addr;
+	u8	cl45_mdio;
+	u8	unused_1;
+};
+
+/* hwrm_port_phy_mdio_read_output (size:128b/16B) */
+struct hwrm_port_phy_mdio_read_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	reg_data;
+	u8	unused_0[5];
+	u8	valid;
+};
+
 /* hwrm_port_led_cfg_input (size:512b/64B) */
 struct hwrm_port_led_cfg_input {
 	__le16	req_type;
@@ -4869,6 +5078,10 @@ struct hwrm_ring_grp_free_output {
 	u8	unused_0[7];
 	u8	valid;
 };
+#define DEFAULT_FLOW_ID 0xFFFFFFFFUL
+#define ROCEV1_FLOW_ID 0xFFFFFFFEUL
+#define ROCEV2_FLOW_ID 0xFFFFFFFDUL
+#define ROCEV2_CNP_FLOW_ID 0xFFFFFFFCUL
 
 /* hwrm_cfa_l2_filter_alloc_input (size:768b/96B) */
 struct hwrm_cfa_l2_filter_alloc_input {
@@ -4937,20 +5150,21 @@ struct hwrm_cfa_l2_filter_alloc_input {
 	u8	unused_3;
 	__le32	src_id;
 	u8	tunnel_type;
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL 0x0UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN     0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE     0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE     0x3UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP      0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE    0x5UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1  0xaUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE  0xbUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST     CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
 	u8	unused_4;
 	__le16	dst_id;
 	__le16	mirror_vnic_id;
@@ -5108,20 +5322,21 @@ struct hwrm_cfa_tunnel_filter_alloc_input {
 	u8	l3_addr_type;
 	u8	t_l3_addr_type;
 	u8	tunnel_type;
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL 0x0UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN     0x1UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE     0x2UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE     0x3UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP      0x4UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE    0x5UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1  0xaUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE  0xbUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST     CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
 	u8	tunnel_flags;
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_OAM_CHECKSUM_EXPLHDR     0x1UL
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_CRITICAL_OPT_S1          0x2UL
@@ -5326,20 +5541,21 @@ struct hwrm_cfa_ntuple_filter_alloc_input {
 	__le16	dst_id;
 	__le16	mirror_vnic_id;
 	u8	tunnel_type;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL 0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN     0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE     0x2UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE     0x3UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP      0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE    0x5UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1  0xaUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE  0xbUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST     CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
 	u8	pri_hint;
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER 0x0UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_ABOVE     0x1UL
@@ -5459,20 +5675,21 @@ struct hwrm_cfa_decap_filter_alloc_input {
 	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID     0x10000UL
 	__be32	tunnel_id;
 	u8	tunnel_type;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL 0x0UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN     0x1UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE     0x2UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE     0x3UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP      0x4UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE    0x5UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1  0xaUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE  0xbUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST     CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
 	u8	unused_0;
 	__le16	unused_1;
 	u8	src_macaddr[6];
@@ -5559,20 +5776,23 @@ struct hwrm_cfa_flow_alloc_input {
 	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_TX                0x40UL
 	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_RX                0x80UL
 	#define CFA_FLOW_ALLOC_REQ_FLAGS_MATCH_VXLAN_IP_VNI     0x100UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_VHOST_ID_USE_VLAN      0x200UL
 	__le16	src_fid;
 	__le32	tunnel_handle;
 	__le16	action_flags;
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD                   0x1UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE               0x2UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP                  0x4UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER                 0x8UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL                0x10UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC               0x20UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST              0x40UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS      0x80UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE     0x100UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT         0x200UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL_IP             0x400UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD                    0x1UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE                0x2UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP                   0x4UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER                  0x8UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL                 0x10UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC                0x20UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST               0x40UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS       0x80UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE      0x100UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT          0x200UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL_IP              0x400UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FLOW_AGING_ENABLED     0x800UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_PRI_HINT               0x1000UL
 	__le16	dst_fid;
 	__be16	l2_rewrite_vlan_tpid;
 	__be16	l2_rewrite_vlan_tci;
@@ -5597,20 +5817,21 @@ struct hwrm_cfa_flow_alloc_input {
 	__be16	l2_rewrite_smac[3];
 	u8	ip_proto;
 	u8	tunnel_type;
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL 0x0UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN     0x1UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NVGRE     0x2UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2GRE     0x3UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPIP      0x4UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_GENEVE    0x5UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1  0xaUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE  0xbUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_LAST     CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
 };
 
 /* hwrm_cfa_flow_alloc_output (size:256b/32B) */
@@ -5623,7 +5844,8 @@ struct hwrm_cfa_flow_alloc_output {
 	u8	unused_0[2];
 	__le32	flow_id;
 	__le64	ext_flow_handle;
-	u8	unused_1[7];
+	__le32	flow_counter_id;
+	u8	unused_1[3];
 	u8	valid;
 };
 
@@ -5651,6 +5873,46 @@ struct hwrm_cfa_flow_free_output {
 	u8	valid;
 };
 
+/* hwrm_cfa_flow_info_input (size:256b/32B) */
+struct hwrm_cfa_flow_info_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	flow_handle;
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK       0xfffUL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_SFT        0
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_CNP_CNT        0x1000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV1_CNT     0x2000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT     0x4000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_DIR_RX         0x8000UL
+	u8	unused_0[6];
+	__le64	ext_flow_handle;
+};
+
+/* hwrm_cfa_flow_info_output (size:448b/56B) */
+struct hwrm_cfa_flow_info_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	u8	profile;
+	__le16	src_fid;
+	__le16	dst_fid;
+	__le16	l2_ctxt_id;
+	__le64	em_info;
+	__le64	tcam_info;
+	__le64	vfp_tcam_info;
+	__le16	ar_id;
+	__le16	flow_handle;
+	__le32	tunnel_handle;
+	__le16	flow_timer;
+	u8	unused_0[5];
+	u8	valid;
+};
+
 /* hwrm_cfa_flow_stats_input (size:640b/80B) */
 struct hwrm_cfa_flow_stats_input {
 	__le16	req_type;
@@ -5757,6 +6019,128 @@ struct hwrm_cfa_vfr_free_output {
 	u8	valid;
 };
 
+/* hwrm_cfa_eem_qcaps_input (size:192b/24B) */
+struct hwrm_cfa_eem_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	__le32	unused_0;
+};
+
+/* hwrm_cfa_eem_qcaps_output (size:256b/32B) */
+struct hwrm_cfa_eem_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_TX     0x1UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_RX     0x2UL
+	__le32	unused_0;
+	__le32	supported;
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY0_TABLE                       0x1UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY1_TABLE                       0x2UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_RECORD_TABLE            0x4UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_FLOW_COUNTERS_TABLE     0x8UL
+	__le32	max_entries_supported;
+	__le16	key_entry_size;
+	__le16	record_entry_size;
+	__le16	efc_entry_size;
+	u8	unused_1;
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_cfg_input (size:320b/40B) */
+struct hwrm_cfa_eem_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_CFG_REQ_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_CFG_REQ_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_CFG_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	__le32	unused_0;
+	__le32	num_entries;
+	__le32	unused_1;
+	__le16	key0_ctx_id;
+	__le16	key1_ctx_id;
+	__le16	record_ctx_id;
+	__le16	efc_ctx_id;
+};
+
+/* hwrm_cfa_eem_cfg_output (size:128b/16B) */
+struct hwrm_cfa_eem_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_qcfg_input (size:192b/24B) */
+struct hwrm_cfa_eem_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_TX     0x1UL
+	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_RX     0x2UL
+	__le32	unused_0;
+};
+
+/* hwrm_cfa_eem_qcfg_output (size:128b/16B) */
+struct hwrm_cfa_eem_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_QCFG_RESP_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	__le32	num_entries;
+};
+
+/* hwrm_cfa_eem_op_input (size:192b/24B) */
+struct hwrm_cfa_eem_op_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_OP_REQ_FLAGS_PATH_TX     0x1UL
+	#define CFA_EEM_OP_REQ_FLAGS_PATH_RX     0x2UL
+	__le16	unused_0;
+	__le16	op;
+	#define CFA_EEM_OP_REQ_OP_RESERVED    0x0UL
+	#define CFA_EEM_OP_REQ_OP_EEM_DISABLE 0x1UL
+	#define CFA_EEM_OP_REQ_OP_EEM_ENABLE  0x2UL
+	#define CFA_EEM_OP_REQ_OP_EEM_CLEANUP 0x3UL
+	#define CFA_EEM_OP_REQ_OP_LAST       CFA_EEM_OP_REQ_OP_EEM_CLEANUP
+};
+
+/* hwrm_cfa_eem_op_output (size:128b/16B) */
+struct hwrm_cfa_eem_op_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
 /* hwrm_tunnel_dst_port_query_input (size:192b/24B) */
 struct hwrm_tunnel_dst_port_query_input {
 	__le16	req_type;
@@ -5765,12 +6149,13 @@ struct hwrm_tunnel_dst_port_query_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN    0x1UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE   0x5UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6
 	u8	unused_0[7];
 };
 
@@ -5794,12 +6179,13 @@ struct hwrm_tunnel_dst_port_alloc_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN    0x1UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE   0x5UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6
 	u8	unused_0;
 	__be16	tunnel_dst_port_val;
 	u8	unused_1[4];
@@ -5824,12 +6210,13 @@ struct hwrm_tunnel_dst_port_free_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN    0x1UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE   0x5UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6
 	u8	unused_0;
 	__le16	tunnel_dst_port_id;
 	u8	unused_1[4];
@@ -6040,7 +6427,9 @@ struct hwrm_fw_reset_input {
 	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE 0x3UL
 	#define FW_RESET_REQ_SELFRST_STATUS_LAST            FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE
 	u8	host_idx;
-	u8	unused_0[5];
+	u8	flags;
+	#define FW_RESET_REQ_FLAGS_RESET_GRACEFUL     0x1UL
+	u8	unused_0[4];
 };
 
 /* hwrm_fw_reset_output (size:128b/16B) */
@@ -6137,6 +6526,7 @@ struct hwrm_struct_hdr {
 	#define STRUCT_HDR_STRUCT_ID_DCBX_FEATURE_STATE 0x422UL
 	#define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC       0x424UL
 	#define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE        0x426UL
+	#define STRUCT_HDR_STRUCT_ID_POWER_BKUP         0x427UL
 	#define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE         0x1UL
 	#define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION   0xaUL
 	#define STRUCT_HDR_STRUCT_ID_RSS_V2             0x64UL
-- 
cgit v1.2.3


From fc718bb2d1efa4348995b4811c243ec59f913a59 Mon Sep 17 00:00:00 2001
From: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Date: Thu, 20 Dec 2018 03:38:44 -0500
Subject: bnxt_en: Set hwrm_intr_seq_id value to its inverted value.

Set hwrm_intr_seq_id value to its inverted value instead of
HWRM_SEQ_INVALID, when an hwrm completion of type
CMPL_BASE_TYPE_HWRM_DONE is received. This will enable us to use
the complete 16-bit sequence ID space.

Signed-off-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 +++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 3 +--
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 218a6dff3efc..72ba07cb39d3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1812,7 +1812,7 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp)
 	case CMPL_BASE_TYPE_HWRM_DONE:
 		seq_id = le16_to_cpu(h_cmpl->sequence_id);
 		if (seq_id == bp->hwrm_intr_seq_id)
-			bp->hwrm_intr_seq_id = HWRM_SEQ_ID_INVALID;
+			bp->hwrm_intr_seq_id = (u16)~bp->hwrm_intr_seq_id;
 		else
 			netdev_err(bp->dev, "Invalid hwrm seq id %d\n", seq_id);
 		break;
@@ -3827,8 +3827,10 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	tmo_count += DIV_ROUND_UP(timeout, HWRM_MIN_TIMEOUT);
 	resp_len = bp->hwrm_cmd_resp_addr + HWRM_RESP_LEN_OFFSET;
 	if (intr_process) {
+		u16 seq_id = bp->hwrm_intr_seq_id;
+
 		/* Wait until hwrm response cmpl interrupt is processed */
-		while (bp->hwrm_intr_seq_id != HWRM_SEQ_ID_INVALID &&
+		while (bp->hwrm_intr_seq_id != (u16)~seq_id &&
 		       i++ < tmo_count) {
 			/* on first few passes, just barely sleep */
 			if (i < HWRM_SHORT_TIMEOUT_COUNTER)
@@ -3839,7 +3841,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 					     HWRM_MAX_TIMEOUT);
 		}
 
-		if (bp->hwrm_intr_seq_id != HWRM_SEQ_ID_INVALID) {
+		if (bp->hwrm_intr_seq_id != (u16)~seq_id) {
 			netdev_err(bp->dev, "Resp cmpl intr err msg: 0x%x\n",
 				   le16_to_cpu(req->req_type));
 			return -1;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 4fdfd7a87805..7a75977c1729 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -567,7 +567,6 @@ struct nqe_cn {
 #define HWRM_RESP_LEN_MASK		0xffff0000
 #define HWRM_RESP_LEN_SFT		16
 #define HWRM_RESP_VALID_MASK		0xff000000
-#define HWRM_SEQ_ID_INVALID		-1
 #define BNXT_HWRM_REQ_MAX_SIZE		128
 #define BNXT_HWRM_REQS_PER_PAGE		(BNXT_PAGE_SIZE /	\
 					 BNXT_HWRM_REQ_MAX_SIZE)
@@ -1466,7 +1465,7 @@ struct bnxt {
 #define BNXT_NEW_RM(bp)		((bp)->fw_cap & BNXT_FW_CAP_NEW_RM)
 	u32			hwrm_spec_code;
 	u16			hwrm_cmd_seq;
-	u32			hwrm_intr_seq_id;
+	u16			hwrm_intr_seq_id;
 	void			*hwrm_short_cmd_req_addr;
 	dma_addr_t		hwrm_short_cmd_req_dma_addr;
 	void			*hwrm_cmd_resp_addr;
-- 
cgit v1.2.3


From 2e9ee3987719148308ff1794aa91f8314f839ccd Mon Sep 17 00:00:00 2001
From: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Date: Thu, 20 Dec 2018 03:38:45 -0500
Subject: bnxt_en: Use macros for firmware message doorbell offsets.

In preparation for adding a 2nd communication channel to firmware.

Signed-off-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 +++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 8 +++++---
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 72ba07cb39d3..945e78b1d468 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3755,6 +3755,8 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	struct hwrm_err_output *resp = bp->hwrm_cmd_resp_addr;
 	u16 max_req_len = BNXT_HWRM_MAX_REQ_LEN;
 	struct hwrm_short_input short_input = {0};
+	u32 doorbell_offset = BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER;
+	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
 
 	req->seq_id = cpu_to_le16(bp->hwrm_cmd_seq++);
 	memset(resp, 0, PAGE_SIZE);
@@ -3800,17 +3802,17 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	}
 
 	/* Write request msg to hwrm channel */
-	__iowrite32_copy(bp->bar0, data, msg_len / 4);
+	__iowrite32_copy(bp->bar0 + bar_offset, data, msg_len / 4);
 
 	for (i = msg_len; i < max_req_len; i += 4)
-		writel(0, bp->bar0 + i);
+		writel(0, bp->bar0 + bar_offset + i);
 
 	/* currently supports only one outstanding message */
 	if (intr_process)
 		bp->hwrm_intr_seq_id = le16_to_cpu(req->seq_id);
 
 	/* Ring channel doorbell */
-	writel(1, bp->bar0 + 0x100);
+	writel(1, bp->bar0 + doorbell_offset);
 
 	if (!timeout)
 		timeout = DFLT_HWRM_CMD_TIMEOUT;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 7a75977c1729..57598164830c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1112,9 +1112,11 @@ struct bnxt_test_info {
 	char string[BNXT_MAX_TEST][ETH_GSTRING_LEN];
 };
 
-#define BNXT_GRCPF_REG_WINDOW_BASE_OUT	0x400
-#define BNXT_CAG_REG_LEGACY_INT_STATUS	0x4014
-#define BNXT_CAG_REG_BASE		0x300000
+#define BNXT_GRCPF_REG_CHIMP_COMM		0x0
+#define BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER	0x100
+#define BNXT_GRCPF_REG_WINDOW_BASE_OUT		0x400
+#define BNXT_CAG_REG_LEGACY_INT_STATUS		0x4014
+#define BNXT_CAG_REG_BASE			0x300000
 
 struct bnxt_tc_flow_stats {
 	u64		packets;
-- 
cgit v1.2.3


From 89455017fb8dd5dff0d088ecb82bccf9f9b715cd Mon Sep 17 00:00:00 2001
From: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Date: Thu, 20 Dec 2018 03:38:46 -0500
Subject: bnxt_en: Avoid arithmetic on void * pointer.

Typecast hwrm_cmd_resp_addr to (u8 *) from (void *) before doing
arithmetic.

Signed-off-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 945e78b1d468..079e1eefe33b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3756,6 +3756,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	u16 max_req_len = BNXT_HWRM_MAX_REQ_LEN;
 	struct hwrm_short_input short_input = {0};
 	u32 doorbell_offset = BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER;
+	u8 *resp_addr = (u8 *)bp->hwrm_cmd_resp_addr;
 	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
 
 	req->seq_id = cpu_to_le16(bp->hwrm_cmd_seq++);
@@ -3827,7 +3828,8 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	tmo_count = HWRM_SHORT_TIMEOUT_COUNTER;
 	timeout = timeout - HWRM_SHORT_MIN_TIMEOUT * HWRM_SHORT_TIMEOUT_COUNTER;
 	tmo_count += DIV_ROUND_UP(timeout, HWRM_MIN_TIMEOUT);
-	resp_len = bp->hwrm_cmd_resp_addr + HWRM_RESP_LEN_OFFSET;
+	resp_len = (__le32 *)(resp_addr + HWRM_RESP_LEN_OFFSET);
+
 	if (intr_process) {
 		u16 seq_id = bp->hwrm_intr_seq_id;
 
@@ -3850,7 +3852,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 		}
 		len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >>
 		      HWRM_RESP_LEN_SFT;
-		valid = bp->hwrm_cmd_resp_addr + len - 1;
+		valid = resp_addr + len - 1;
 	} else {
 		int j;
 
@@ -3878,7 +3880,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 		}
 
 		/* Last byte of resp contains valid bit */
-		valid = bp->hwrm_cmd_resp_addr + len - 1;
+		valid = resp_addr + len - 1;
 		for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; j++) {
 			/* make sure we read from updated DMA memory */
 			dma_rmb();
-- 
cgit v1.2.3


From 5c209fc82159f2f71e2772f28cd1d447b821e98d Mon Sep 17 00:00:00 2001
From: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Date: Thu, 20 Dec 2018 03:38:47 -0500
Subject: bnxt_en: Introduce bnxt_get_hwrm_resp_addr & bnxt_get_hwrm_seq_id
 routines.

These routines will be enhanced in the subsequent patch to
return the 2nd firmware comm. channel's hwrm response address &
sequence id respectively.

Signed-off-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c    | 13 ++++++-----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h    | 13 +++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 34 +++++++++++++++++-----------
 3 files changed, 41 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 079e1eefe33b..46bbe42412d3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3759,7 +3759,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	u8 *resp_addr = (u8 *)bp->hwrm_cmd_resp_addr;
 	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
 
-	req->seq_id = cpu_to_le16(bp->hwrm_cmd_seq++);
+	req->seq_id = cpu_to_le16(bnxt_get_hwrm_seq_id(bp));
 	memset(resp, 0, PAGE_SIZE);
 	cp_ring_id = le16_to_cpu(req->cmpl_ring);
 	intr_process = (cp_ring_id == INVALID_HW_RING_ID) ? 0 : 1;
@@ -4143,12 +4143,11 @@ static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 					     struct bnxt_ntuple_filter *fltr)
 {
-	int rc = 0;
+	struct bnxt_vnic_info *vnic = &bp->vnic_info[fltr->rxq + 1];
 	struct hwrm_cfa_ntuple_filter_alloc_input req = {0};
-	struct hwrm_cfa_ntuple_filter_alloc_output *resp =
-		bp->hwrm_cmd_resp_addr;
+	struct hwrm_cfa_ntuple_filter_alloc_output *resp;
 	struct flow_keys *keys = &fltr->fkeys;
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[fltr->rxq + 1];
+	int rc = 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_NTUPLE_FILTER_ALLOC, -1, -1);
 	req.l2_filter_id = bp->vnic_info[0].fw_l2_filter_id[fltr->l2_fltr_idx];
@@ -4194,8 +4193,10 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 	req.dst_id = cpu_to_le16(vnic->fw_vnic_id);
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc)
+	if (!rc) {
+		resp = bnxt_get_hwrm_resp_addr(bp, &req);
 		fltr->filter_id = resp->ntuple_filter_id;
+	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 57598164830c..214af8fe84c2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1673,6 +1673,19 @@ static inline void bnxt_db_write(struct bnxt *bp, struct bnxt_db_info *db,
 	}
 }
 
+static inline void *bnxt_get_hwrm_resp_addr(struct bnxt *bp, void *req)
+{
+	return bp->hwrm_cmd_resp_addr;
+}
+
+static inline u16 bnxt_get_hwrm_seq_id(struct bnxt *bp)
+{
+	u16 seq_id;
+
+	seq_id = bp->hwrm_cmd_seq++;
+	return seq_id;
+}
+
 extern const u16 bnxt_lhint_arr[];
 
 int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 749f63beddd8..b39584896392 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -420,11 +420,11 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 				    __le16 ref_flow_handle,
 				    __le32 tunnel_handle, __le16 *flow_handle)
 {
-	struct hwrm_cfa_flow_alloc_output *resp = bp->hwrm_cmd_resp_addr;
 	struct bnxt_tc_actions *actions = &flow->actions;
 	struct bnxt_tc_l3_key *l3_mask = &flow->l3_mask;
 	struct bnxt_tc_l3_key *l3_key = &flow->l3_key;
 	struct hwrm_cfa_flow_alloc_input req = { 0 };
+	struct hwrm_cfa_flow_alloc_output *resp;
 	u16 flow_flags = 0, action_flags = 0;
 	int rc;
 
@@ -527,8 +527,10 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc)
+	if (!rc) {
+		resp = bnxt_get_hwrm_resp_addr(bp, &req);
 		*flow_handle = resp->flow_handle;
+	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 
 	if (rc == HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR)
@@ -544,9 +546,8 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp,
 				       __le32 ref_decap_handle,
 				       __le32 *decap_filter_handle)
 {
-	struct hwrm_cfa_decap_filter_alloc_output *resp =
-						bp->hwrm_cmd_resp_addr;
 	struct hwrm_cfa_decap_filter_alloc_input req = { 0 };
+	struct hwrm_cfa_decap_filter_alloc_output *resp;
 	struct ip_tunnel_key *tun_key = &flow->tun_key;
 	u32 enables = 0;
 	int rc;
@@ -599,10 +600,12 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp,
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc)
+	if (!rc) {
+		resp = bnxt_get_hwrm_resp_addr(bp, &req);
 		*decap_filter_handle = resp->decap_filter_id;
-	else
+	} else {
 		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 
 	if (rc)
@@ -633,9 +636,8 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp,
 				       struct bnxt_tc_l2_key *l2_info,
 				       __le32 *encap_record_handle)
 {
-	struct hwrm_cfa_encap_record_alloc_output *resp =
-						bp->hwrm_cmd_resp_addr;
 	struct hwrm_cfa_encap_record_alloc_input req = { 0 };
+	struct hwrm_cfa_encap_record_alloc_output *resp;
 	struct hwrm_cfa_encap_data_vxlan *encap =
 			(struct hwrm_cfa_encap_data_vxlan *)&req.encap_data;
 	struct hwrm_vxlan_ipv4_hdr *encap_ipv4 =
@@ -667,10 +669,12 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp,
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc)
+	if (!rc) {
+		resp = bnxt_get_hwrm_resp_addr(bp, &req);
 		*encap_record_handle = resp->encap_record_id;
-	else
+	} else {
 		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 
 	if (rc)
@@ -1401,8 +1405,8 @@ static int
 bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
 			     struct bnxt_tc_stats_batch stats_batch[])
 {
-	struct hwrm_cfa_flow_stats_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_cfa_flow_stats_input req = { 0 };
+	struct hwrm_cfa_flow_stats_output *resp;
 	__le16 *req_flow_handles = &req.flow_handle_0;
 	int rc, i;
 
@@ -1417,8 +1421,12 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
-		__le64 *resp_packets = &resp->packet_0;
-		__le64 *resp_bytes = &resp->byte_0;
+		__le64 *resp_packets;
+		__le64 *resp_bytes;
+
+		resp = bnxt_get_hwrm_resp_addr(bp, &req);
+		resp_packets = &resp->packet_0;
+		resp_bytes = &resp->byte_0;
 
 		for (i = 0; i < num_flows; i++) {
 			stats_batch[i].hw_stats.packets =
-- 
cgit v1.2.3


From 760b6d33410cda351f236058585471cb0f417978 Mon Sep 17 00:00:00 2001
From: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Date: Thu, 20 Dec 2018 03:38:48 -0500
Subject: bnxt_en: Add support for 2nd firmware message channel.

Earlier, some of the firmware commands (ex: CFA_FLOW_*) which are processed
by KONG processor were sent to the CHIMP processor from the host. This
approach was taken as there was no direct message channel to KONG.
CHIMP in turn used to send them to KONG. Newer firmware supports a new
message channel which the host can send messages directly to the KONG
processor.

This patch adds support for required changes needed in the driver
to support direct KONG message channel.  This speeds up flow related
messages sent to the firmware for CLS_FLOWER offload.

Signed-off-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 62 +++++++++++++++++++++-----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 73 +++++++++++++++++++++++++++----
 2 files changed, 117 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 46bbe42412d3..79280c8f026b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3279,6 +3279,27 @@ static void bnxt_free_hwrm_resources(struct bnxt *bp)
 				  bp->hwrm_cmd_resp_dma_addr);
 		bp->hwrm_cmd_resp_addr = NULL;
 	}
+
+	if (bp->hwrm_cmd_kong_resp_addr) {
+		dma_free_coherent(&pdev->dev, PAGE_SIZE,
+				  bp->hwrm_cmd_kong_resp_addr,
+				  bp->hwrm_cmd_kong_resp_dma_addr);
+		bp->hwrm_cmd_kong_resp_addr = NULL;
+	}
+}
+
+static int bnxt_alloc_kong_hwrm_resources(struct bnxt *bp)
+{
+	struct pci_dev *pdev = bp->pdev;
+
+	bp->hwrm_cmd_kong_resp_addr =
+		dma_alloc_coherent(&pdev->dev, PAGE_SIZE,
+				   &bp->hwrm_cmd_kong_resp_dma_addr,
+				   GFP_KERNEL);
+	if (!bp->hwrm_cmd_kong_resp_addr)
+		return -ENOMEM;
+
+	return 0;
 }
 
 static int bnxt_alloc_hwrm_resources(struct bnxt *bp)
@@ -3740,7 +3761,10 @@ void bnxt_hwrm_cmd_hdr_init(struct bnxt *bp, void *request, u16 req_type,
 	req->req_type = cpu_to_le16(req_type);
 	req->cmpl_ring = cpu_to_le16(cmpl_ring);
 	req->target_id = cpu_to_le16(target_id);
-	req->resp_addr = cpu_to_le64(bp->hwrm_cmd_resp_dma_addr);
+	if (bnxt_kong_hwrm_message(bp, req))
+		req->resp_addr = cpu_to_le64(bp->hwrm_cmd_kong_resp_dma_addr);
+	else
+		req->resp_addr = cpu_to_le64(bp->hwrm_cmd_resp_dma_addr);
 }
 
 static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
@@ -3758,11 +3782,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	u32 doorbell_offset = BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER;
 	u8 *resp_addr = (u8 *)bp->hwrm_cmd_resp_addr;
 	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
-
-	req->seq_id = cpu_to_le16(bnxt_get_hwrm_seq_id(bp));
-	memset(resp, 0, PAGE_SIZE);
-	cp_ring_id = le16_to_cpu(req->cmpl_ring);
-	intr_process = (cp_ring_id == INVALID_HW_RING_ID) ? 0 : 1;
+	u16 dst = BNXT_HWRM_CHNL_CHIMP;
 
 	if (msg_len > BNXT_HWRM_MAX_REQ_LEN) {
 		if (msg_len > bp->hwrm_max_ext_req_len ||
@@ -3770,6 +3790,23 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 			return -EINVAL;
 	}
 
+	if (bnxt_hwrm_kong_chnl(bp, req)) {
+		dst = BNXT_HWRM_CHNL_KONG;
+		bar_offset = BNXT_GRCPF_REG_KONG_COMM;
+		doorbell_offset = BNXT_GRCPF_REG_KONG_COMM_TRIGGER;
+		resp = bp->hwrm_cmd_kong_resp_addr;
+		resp_addr = (u8 *)bp->hwrm_cmd_kong_resp_addr;
+	}
+
+	memset(resp, 0, PAGE_SIZE);
+	cp_ring_id = le16_to_cpu(req->cmpl_ring);
+	intr_process = (cp_ring_id == INVALID_HW_RING_ID) ? 0 : 1;
+
+	req->seq_id = cpu_to_le16(bnxt_get_hwrm_seq_id(bp, dst));
+	/* currently supports only one outstanding message */
+	if (intr_process)
+		bp->hwrm_intr_seq_id = le16_to_cpu(req->seq_id);
+
 	if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) ||
 	    msg_len > BNXT_HWRM_MAX_REQ_LEN) {
 		void *short_cmd_req = bp->hwrm_short_cmd_req_addr;
@@ -3808,10 +3845,6 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	for (i = msg_len; i < max_req_len; i += 4)
 		writel(0, bp->bar0 + bar_offset + i);
 
-	/* currently supports only one outstanding message */
-	if (intr_process)
-		bp->hwrm_intr_seq_id = le16_to_cpu(req->seq_id);
-
 	/* Ring channel doorbell */
 	writel(1, bp->bar0 + doorbell_offset);
 
@@ -6488,6 +6521,9 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	    (dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_REQUIRED))
 		bp->fw_cap |= BNXT_FW_CAP_SHORT_CMD;
 
+	if (dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_KONG_MB_CHNL_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_KONG_MB_CHNL;
+
 hwrm_ver_get_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -10226,6 +10262,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
+	if (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL) {
+		rc = bnxt_alloc_kong_hwrm_resources(bp);
+		if (rc)
+			bp->fw_cap &= ~BNXT_FW_CAP_KONG_MB_CHNL;
+	}
+
 	if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) ||
 	    bp->hwrm_max_ext_req_len > BNXT_HWRM_MAX_REQ_LEN) {
 		rc = bnxt_alloc_hwrm_short_cmd_req(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 214af8fe84c2..c3334c0d1e62 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -584,6 +584,9 @@ struct nqe_cn {
 
 #define HWRM_VALID_BIT_DELAY_USEC	20
 
+#define BNXT_HWRM_CHNL_CHIMP	0
+#define BNXT_HWRM_CHNL_KONG	1
+
 #define BNXT_RX_EVENT	1
 #define BNXT_AGG_EVENT	2
 #define BNXT_TX_EVENT	4
@@ -1118,6 +1121,9 @@ struct bnxt_test_info {
 #define BNXT_CAG_REG_LEGACY_INT_STATUS		0x4014
 #define BNXT_CAG_REG_BASE			0x300000
 
+#define BNXT_GRCPF_REG_KONG_COMM		0xA00
+#define BNXT_GRCPF_REG_KONG_COMM_TRIGGER	0xB00
+
 struct bnxt_tc_flow_stats {
 	u64		packets;
 	u64		bytes;
@@ -1458,20 +1464,24 @@ struct bnxt {
 	u32			msg_enable;
 
 	u32			fw_cap;
-	#define BNXT_FW_CAP_SHORT_CMD	0x00000001
-	#define BNXT_FW_CAP_LLDP_AGENT	0x00000002
-	#define BNXT_FW_CAP_DCBX_AGENT	0x00000004
-	#define BNXT_FW_CAP_NEW_RM	0x00000008
-	#define BNXT_FW_CAP_IF_CHANGE	0x00000010
+	#define BNXT_FW_CAP_SHORT_CMD			0x00000001
+	#define BNXT_FW_CAP_LLDP_AGENT			0x00000002
+	#define BNXT_FW_CAP_DCBX_AGENT			0x00000004
+	#define BNXT_FW_CAP_NEW_RM			0x00000008
+	#define BNXT_FW_CAP_IF_CHANGE			0x00000010
+	#define BNXT_FW_CAP_KONG_MB_CHNL		0x00000080
 
 #define BNXT_NEW_RM(bp)		((bp)->fw_cap & BNXT_FW_CAP_NEW_RM)
 	u32			hwrm_spec_code;
 	u16			hwrm_cmd_seq;
+	u16                     hwrm_cmd_kong_seq;
 	u16			hwrm_intr_seq_id;
 	void			*hwrm_short_cmd_req_addr;
 	dma_addr_t		hwrm_short_cmd_req_dma_addr;
 	void			*hwrm_cmd_resp_addr;
 	dma_addr_t		hwrm_cmd_resp_dma_addr;
+	void			*hwrm_cmd_kong_resp_addr;
+	dma_addr_t		hwrm_cmd_kong_resp_dma_addr;
 
 	struct rtnl_link_stats64	net_stats_prev;
 	struct rx_port_stats	*hw_rx_port_stats;
@@ -1673,16 +1683,63 @@ static inline void bnxt_db_write(struct bnxt *bp, struct bnxt_db_info *db,
 	}
 }
 
+static inline bool bnxt_cfa_hwrm_message(u16 req_type)
+{
+	switch (req_type) {
+	case HWRM_CFA_ENCAP_RECORD_ALLOC:
+	case HWRM_CFA_ENCAP_RECORD_FREE:
+	case HWRM_CFA_DECAP_FILTER_ALLOC:
+	case HWRM_CFA_DECAP_FILTER_FREE:
+	case HWRM_CFA_NTUPLE_FILTER_ALLOC:
+	case HWRM_CFA_NTUPLE_FILTER_FREE:
+	case HWRM_CFA_NTUPLE_FILTER_CFG:
+	case HWRM_CFA_EM_FLOW_ALLOC:
+	case HWRM_CFA_EM_FLOW_FREE:
+	case HWRM_CFA_EM_FLOW_CFG:
+	case HWRM_CFA_FLOW_ALLOC:
+	case HWRM_CFA_FLOW_FREE:
+	case HWRM_CFA_FLOW_INFO:
+	case HWRM_CFA_FLOW_FLUSH:
+	case HWRM_CFA_FLOW_STATS:
+	case HWRM_CFA_METER_PROFILE_ALLOC:
+	case HWRM_CFA_METER_PROFILE_FREE:
+	case HWRM_CFA_METER_PROFILE_CFG:
+	case HWRM_CFA_METER_INSTANCE_ALLOC:
+	case HWRM_CFA_METER_INSTANCE_FREE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline bool bnxt_kong_hwrm_message(struct bnxt *bp, struct input *req)
+{
+	return (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL &&
+		bnxt_cfa_hwrm_message(le16_to_cpu(req->req_type)));
+}
+
+static inline bool bnxt_hwrm_kong_chnl(struct bnxt *bp, struct input *req)
+{
+	return (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL &&
+		req->resp_addr == cpu_to_le64(bp->hwrm_cmd_kong_resp_dma_addr));
+}
+
 static inline void *bnxt_get_hwrm_resp_addr(struct bnxt *bp, void *req)
 {
-	return bp->hwrm_cmd_resp_addr;
+	if (bnxt_hwrm_kong_chnl(bp, (struct input *)req))
+		return bp->hwrm_cmd_kong_resp_addr;
+	else
+		return bp->hwrm_cmd_resp_addr;
 }
 
-static inline u16 bnxt_get_hwrm_seq_id(struct bnxt *bp)
+static inline u16 bnxt_get_hwrm_seq_id(struct bnxt *bp, u16 dst)
 {
 	u16 seq_id;
 
-	seq_id = bp->hwrm_cmd_seq++;
+	if (dst == BNXT_HWRM_CHNL_CHIMP)
+		seq_id = bp->hwrm_cmd_seq++;
+	else
+		seq_id = bp->hwrm_cmd_kong_seq++;
 	return seq_id;
 }
 
-- 
cgit v1.2.3


From 4f49b2b8d4167b712ce876bff08bd9606a44f7a6 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 20 Dec 2018 03:38:49 -0500
Subject: bnxt_en: Enhance bnxt_alloc_ring()/bnxt_free_ring().

To support level 2 context page memory structures, enhance the
bnxt_ring_mem_info structure with a "depth" field to specify the page
level and add a flag to specify using full pages for L1 and L2 page
tables.  This is needed to support RDMA functionality on 57500 chips
since RDMA requires more context memory.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 17 ++++++++++++-----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  5 ++++-
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 79280c8f026b..a46e2ff3a773 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2375,7 +2375,11 @@ static void bnxt_free_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 		rmem->pg_arr[i] = NULL;
 	}
 	if (rmem->pg_tbl) {
-		dma_free_coherent(&pdev->dev, rmem->nr_pages * 8,
+		size_t pg_tbl_size = rmem->nr_pages * 8;
+
+		if (rmem->flags & BNXT_RMEM_USE_FULL_PAGE_FLAG)
+			pg_tbl_size = rmem->page_size;
+		dma_free_coherent(&pdev->dev, pg_tbl_size,
 				  rmem->pg_tbl, rmem->pg_tbl_map);
 		rmem->pg_tbl = NULL;
 	}
@@ -2393,9 +2397,12 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 
 	if (rmem->flags & (BNXT_RMEM_VALID_PTE_FLAG | BNXT_RMEM_RING_PTE_FLAG))
 		valid_bit = PTU_PTE_VALID;
-	if (rmem->nr_pages > 1) {
-		rmem->pg_tbl = dma_alloc_coherent(&pdev->dev,
-						  rmem->nr_pages * 8,
+	if ((rmem->nr_pages > 1 || rmem->depth > 0) && !rmem->pg_tbl) {
+		size_t pg_tbl_size = rmem->nr_pages * 8;
+
+		if (rmem->flags & BNXT_RMEM_USE_FULL_PAGE_FLAG)
+			pg_tbl_size = rmem->page_size;
+		rmem->pg_tbl = dma_alloc_coherent(&pdev->dev, pg_tbl_size,
 						  &rmem->pg_tbl_map,
 						  GFP_KERNEL);
 		if (!rmem->pg_tbl)
@@ -2412,7 +2419,7 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 		if (!rmem->pg_arr[i])
 			return -ENOMEM;
 
-		if (rmem->nr_pages > 1) {
+		if (rmem->nr_pages > 1 || rmem->depth > 0) {
 			if (i == rmem->nr_pages - 2 &&
 			    (rmem->flags & BNXT_RMEM_RING_PTE_FLAG))
 				extra_bits |= PTU_PTE_NEXT_TO_LAST;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index c3334c0d1e62..1a5d02beee37 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -617,9 +617,12 @@ struct bnxt_sw_rx_agg_bd {
 struct bnxt_ring_mem_info {
 	int			nr_pages;
 	int			page_size;
-	u32			flags;
+	u16			flags;
 #define BNXT_RMEM_VALID_PTE_FLAG	1
 #define BNXT_RMEM_RING_PTE_FLAG		2
+#define BNXT_RMEM_USE_FULL_PAGE_FLAG	4
+
+	u16			depth;
 
 	void			**pg_arr;
 	dma_addr_t		*dma_arr;
-- 
cgit v1.2.3


From 08fe9d1816067170e167867d06009fb0f41cb411 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 20 Dec 2018 03:38:50 -0500
Subject: bnxt_en: Add Level 2 context memory paging support.

Add the new functions bnxt_alloc_ctx_pg_tbls()/bnxt_free_ctx_pg_tbls()
to allocate and free pages for context memory.  The new functions
will handle the different levels of paging support and allocate/free
the pages accordingly using the existing functions.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 128 ++++++++++++++++++++++++------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |   3 +
 2 files changed, 108 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a46e2ff3a773..ade2c6f4db1b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6047,8 +6047,11 @@ static void bnxt_hwrm_set_pg_attr(struct bnxt_ring_mem_info *rmem, u8 *pg_attr,
 		pg_size = 2 << 4;
 
 	*pg_attr = pg_size;
-	if (rmem->nr_pages > 1) {
-		*pg_attr |= 1;
+	if (rmem->depth >= 1) {
+		if (rmem->depth == 2)
+			*pg_attr |= 2;
+		else
+			*pg_attr |= 1;
 		*pg_dir = cpu_to_le64(rmem->pg_tbl_map);
 	} else {
 		*pg_dir = cpu_to_le64(rmem->dma_arr[0]);
@@ -6145,25 +6148,104 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 }
 
 static int bnxt_alloc_ctx_mem_blk(struct bnxt *bp,
-				  struct bnxt_ctx_pg_info *ctx_pg, u32 mem_size)
+				  struct bnxt_ctx_pg_info *ctx_pg)
 {
 	struct bnxt_ring_mem_info *rmem = &ctx_pg->ring_mem;
 
-	if (!mem_size)
-		return 0;
-
-	rmem->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
-	if (rmem->nr_pages > MAX_CTX_PAGES) {
-		rmem->nr_pages = 0;
-		return -EINVAL;
-	}
 	rmem->page_size = BNXT_PAGE_SIZE;
 	rmem->pg_arr = ctx_pg->ctx_pg_arr;
 	rmem->dma_arr = ctx_pg->ctx_dma_arr;
 	rmem->flags = BNXT_RMEM_VALID_PTE_FLAG;
+	if (rmem->depth >= 1)
+		rmem->flags |= BNXT_RMEM_USE_FULL_PAGE_FLAG;
 	return bnxt_alloc_ring(bp, rmem);
 }
 
+static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
+				  struct bnxt_ctx_pg_info *ctx_pg, u32 mem_size,
+				  u8 depth)
+{
+	struct bnxt_ring_mem_info *rmem = &ctx_pg->ring_mem;
+	int rc;
+
+	if (!mem_size)
+		return 0;
+
+	ctx_pg->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
+	if (ctx_pg->nr_pages > MAX_CTX_TOTAL_PAGES) {
+		ctx_pg->nr_pages = 0;
+		return -EINVAL;
+	}
+	if (ctx_pg->nr_pages > MAX_CTX_PAGES || depth > 1) {
+		int nr_tbls, i;
+
+		rmem->depth = 2;
+		ctx_pg->ctx_pg_tbl = kcalloc(MAX_CTX_PAGES, sizeof(ctx_pg),
+					     GFP_KERNEL);
+		if (!ctx_pg->ctx_pg_tbl)
+			return -ENOMEM;
+		nr_tbls = DIV_ROUND_UP(ctx_pg->nr_pages, MAX_CTX_PAGES);
+		rmem->nr_pages = nr_tbls;
+		rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg);
+		if (rc)
+			return rc;
+		for (i = 0; i < nr_tbls; i++) {
+			struct bnxt_ctx_pg_info *pg_tbl;
+
+			pg_tbl = kzalloc(sizeof(*pg_tbl), GFP_KERNEL);
+			if (!pg_tbl)
+				return -ENOMEM;
+			ctx_pg->ctx_pg_tbl[i] = pg_tbl;
+			rmem = &pg_tbl->ring_mem;
+			rmem->pg_tbl = ctx_pg->ctx_pg_arr[i];
+			rmem->pg_tbl_map = ctx_pg->ctx_dma_arr[i];
+			rmem->depth = 1;
+			rmem->nr_pages = MAX_CTX_PAGES;
+			if (i == (nr_tbls - 1))
+				rmem->nr_pages = ctx_pg->nr_pages %
+						 MAX_CTX_PAGES;
+			rc = bnxt_alloc_ctx_mem_blk(bp, pg_tbl);
+			if (rc)
+				break;
+		}
+	} else {
+		rmem->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
+		if (rmem->nr_pages > 1 || depth)
+			rmem->depth = 1;
+		rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg);
+	}
+	return rc;
+}
+
+static void bnxt_free_ctx_pg_tbls(struct bnxt *bp,
+				  struct bnxt_ctx_pg_info *ctx_pg)
+{
+	struct bnxt_ring_mem_info *rmem = &ctx_pg->ring_mem;
+
+	if (rmem->depth > 1 || ctx_pg->nr_pages > MAX_CTX_PAGES ||
+	    ctx_pg->ctx_pg_tbl) {
+		int i, nr_tbls = rmem->nr_pages;
+
+		for (i = 0; i < nr_tbls; i++) {
+			struct bnxt_ctx_pg_info *pg_tbl;
+			struct bnxt_ring_mem_info *rmem2;
+
+			pg_tbl = ctx_pg->ctx_pg_tbl[i];
+			if (!pg_tbl)
+				continue;
+			rmem2 = &pg_tbl->ring_mem;
+			bnxt_free_ring(bp, rmem2);
+			ctx_pg->ctx_pg_arr[i] = NULL;
+			kfree(pg_tbl);
+			ctx_pg->ctx_pg_tbl[i] = NULL;
+		}
+		kfree(ctx_pg->ctx_pg_tbl);
+		ctx_pg->ctx_pg_tbl = NULL;
+	}
+	bnxt_free_ring(bp, rmem);
+	ctx_pg->nr_pages = 0;
+}
+
 static void bnxt_free_ctx_mem(struct bnxt *bp)
 {
 	struct bnxt_ctx_mem_info *ctx = bp->ctx;
@@ -6174,16 +6256,16 @@ static void bnxt_free_ctx_mem(struct bnxt *bp)
 
 	if (ctx->tqm_mem[0]) {
 		for (i = 0; i < bp->max_q + 1; i++)
-			bnxt_free_ring(bp, &ctx->tqm_mem[i]->ring_mem);
+			bnxt_free_ctx_pg_tbls(bp, ctx->tqm_mem[i]);
 		kfree(ctx->tqm_mem[0]);
 		ctx->tqm_mem[0] = NULL;
 	}
 
-	bnxt_free_ring(bp, &ctx->stat_mem.ring_mem);
-	bnxt_free_ring(bp, &ctx->vnic_mem.ring_mem);
-	bnxt_free_ring(bp, &ctx->cq_mem.ring_mem);
-	bnxt_free_ring(bp, &ctx->srq_mem.ring_mem);
-	bnxt_free_ring(bp, &ctx->qp_mem.ring_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->stat_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->vnic_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->cq_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->srq_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->qp_mem);
 	ctx->flags &= ~BNXT_CTX_FLAG_INITED;
 }
 
@@ -6207,21 +6289,21 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	ctx_pg = &ctx->qp_mem;
 	ctx_pg->entries = ctx->qp_min_qp1_entries + ctx->qp_max_l2_entries;
 	mem_size = ctx->qp_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
 	if (rc)
 		return rc;
 
 	ctx_pg = &ctx->srq_mem;
 	ctx_pg->entries = ctx->srq_max_l2_entries;
 	mem_size = ctx->srq_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
 	if (rc)
 		return rc;
 
 	ctx_pg = &ctx->cq_mem;
 	ctx_pg->entries = ctx->cq_max_l2_entries;
 	mem_size = ctx->cq_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
 	if (rc)
 		return rc;
 
@@ -6229,14 +6311,14 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	ctx_pg->entries = ctx->vnic_max_vnic_entries +
 			  ctx->vnic_max_ring_table_entries;
 	mem_size = ctx->vnic_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
 	if (rc)
 		return rc;
 
 	ctx_pg = &ctx->stat_mem;
 	ctx_pg->entries = ctx->stat_max_entries;
 	mem_size = ctx->stat_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
 	if (rc)
 		return rc;
 
@@ -6248,7 +6330,7 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 		ctx_pg = ctx->tqm_mem[i];
 		ctx_pg->entries = entries;
 		mem_size = ctx->tqm_entry_size * entries;
-		rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
 		if (rc)
 			return rc;
 		ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP << i;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 1a5d02beee37..6b350cd91e32 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1193,12 +1193,15 @@ struct bnxt_vf_rep {
 #define PTU_PTE_NEXT_TO_LAST      0x4UL
 
 #define MAX_CTX_PAGES	(BNXT_PAGE_SIZE / 8)
+#define MAX_CTX_TOTAL_PAGES	(MAX_CTX_PAGES * MAX_CTX_PAGES)
 
 struct bnxt_ctx_pg_info {
 	u32		entries;
+	u32		nr_pages;
 	void		*ctx_pg_arr[MAX_CTX_PAGES];
 	dma_addr_t	ctx_dma_arr[MAX_CTX_PAGES];
 	struct bnxt_ring_mem_info ring_mem;
+	struct bnxt_ctx_pg_info **ctx_pg_tbl;
 };
 
 struct bnxt_ctx_mem_info {
-- 
cgit v1.2.3


From cf6daed098d14760d6605268d28bfdf7b3bfa375 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 20 Dec 2018 03:38:51 -0500
Subject: bnxt_en: Increase context memory allocations on 57500 chips for RDMA.

If RDMA is supported on the 57500 chip, increase context memory
allocations for the resources used by RDMA.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 65 +++++++++++++++++++++++++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  2 +
 2 files changed, 59 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ade2c6f4db1b..d3287641ce51 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6128,6 +6128,22 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 				      &req.stat_pg_size_stat_lvl,
 				      &req.stat_page_dir);
 	}
+	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV) {
+		ctx_pg = &ctx->mrav_mem;
+		req.mrav_num_entries = cpu_to_le32(ctx_pg->entries);
+		req.mrav_entry_size = cpu_to_le16(ctx->mrav_entry_size);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req.mrav_pg_size_mrav_lvl,
+				      &req.mrav_page_dir);
+	}
+	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM) {
+		ctx_pg = &ctx->tim_mem;
+		req.tim_num_entries = cpu_to_le32(ctx_pg->entries);
+		req.tim_entry_size = cpu_to_le16(ctx->tim_entry_size);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req.tim_pg_size_tim_lvl,
+				      &req.tim_page_dir);
+	}
 	for (i = 0, num_entries = &req.tqm_sp_num_entries,
 	     pg_attr = &req.tqm_sp_pg_size_tqm_sp_lvl,
 	     pg_dir = &req.tqm_sp_page_dir,
@@ -6261,6 +6277,8 @@ static void bnxt_free_ctx_mem(struct bnxt *bp)
 		ctx->tqm_mem[0] = NULL;
 	}
 
+	bnxt_free_ctx_pg_tbls(bp, &ctx->tim_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->mrav_mem);
 	bnxt_free_ctx_pg_tbls(bp, &ctx->stat_mem);
 	bnxt_free_ctx_pg_tbls(bp, &ctx->vnic_mem);
 	bnxt_free_ctx_pg_tbls(bp, &ctx->cq_mem);
@@ -6274,6 +6292,9 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	struct bnxt_ctx_pg_info *ctx_pg;
 	struct bnxt_ctx_mem_info *ctx;
 	u32 mem_size, ena, entries;
+	u32 extra_srqs = 0;
+	u32 extra_qps = 0;
+	u8 pg_lvl = 1;
 	int i, rc;
 
 	rc = bnxt_hwrm_func_backing_store_qcaps(bp);
@@ -6286,24 +6307,31 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	if (!ctx || (ctx->flags & BNXT_CTX_FLAG_INITED))
 		return 0;
 
+	if (bp->flags & BNXT_FLAG_ROCE_CAP) {
+		pg_lvl = 2;
+		extra_qps = 65536;
+		extra_srqs = 8192;
+	}
+
 	ctx_pg = &ctx->qp_mem;
-	ctx_pg->entries = ctx->qp_min_qp1_entries + ctx->qp_max_l2_entries;
+	ctx_pg->entries = ctx->qp_min_qp1_entries + ctx->qp_max_l2_entries +
+			  extra_qps;
 	mem_size = ctx->qp_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl);
 	if (rc)
 		return rc;
 
 	ctx_pg = &ctx->srq_mem;
-	ctx_pg->entries = ctx->srq_max_l2_entries;
+	ctx_pg->entries = ctx->srq_max_l2_entries + extra_srqs;
 	mem_size = ctx->srq_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl);
 	if (rc)
 		return rc;
 
 	ctx_pg = &ctx->cq_mem;
-	ctx_pg->entries = ctx->cq_max_l2_entries;
+	ctx_pg->entries = ctx->cq_max_l2_entries + extra_qps * 2;
 	mem_size = ctx->cq_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl);
 	if (rc)
 		return rc;
 
@@ -6322,11 +6350,32 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	if (rc)
 		return rc;
 
-	entries = ctx->qp_max_l2_entries;
+	ena = 0;
+	if (!(bp->flags & BNXT_FLAG_ROCE_CAP))
+		goto skip_rdma;
+
+	ctx_pg = &ctx->mrav_mem;
+	ctx_pg->entries = extra_qps * 4;
+	mem_size = ctx->mrav_entry_size * ctx_pg->entries;
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 2);
+	if (rc)
+		return rc;
+	ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV;
+
+	ctx_pg = &ctx->tim_mem;
+	ctx_pg->entries = ctx->qp_mem.entries;
+	mem_size = ctx->tim_entry_size * ctx_pg->entries;
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
+	if (rc)
+		return rc;
+	ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM;
+
+skip_rdma:
+	entries = ctx->qp_max_l2_entries + extra_qps;
 	entries = roundup(entries, ctx->tqm_entries_multiple);
 	entries = clamp_t(u32, entries, ctx->tqm_min_entries_per_ring,
 			  ctx->tqm_max_entries_per_ring);
-	for (i = 0, ena = 0; i < bp->max_q + 1; i++) {
+	for (i = 0; i < bp->max_q + 1; i++) {
 		ctx_pg = ctx->tqm_mem[i];
 		ctx_pg->entries = entries;
 		mem_size = ctx->tqm_entry_size * entries;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 6b350cd91e32..61d07a4165d8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1237,6 +1237,8 @@ struct bnxt_ctx_mem_info {
 	struct bnxt_ctx_pg_info cq_mem;
 	struct bnxt_ctx_pg_info vnic_mem;
 	struct bnxt_ctx_pg_info stat_mem;
+	struct bnxt_ctx_pg_info mrav_mem;
+	struct bnxt_ctx_pg_info tim_mem;
 	struct bnxt_ctx_pg_info *tqm_mem[9];
 };
 
-- 
cgit v1.2.3


From abd43a13525db70926999ebe3e272c38119fdfbe Mon Sep 17 00:00:00 2001
From: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Date: Thu, 20 Dec 2018 03:38:52 -0500
Subject: bnxt_en: Support for 64-bit flow handle.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Older firmware only supports 16-bit flow handle, because of which the
number of flows that can be offloaded can’t scale beyond a point.
Newer firmware supports 64-bit flow handle enabling the host to scale
upto millions of flows. With the new 64-bit flow handle support, driver
has to query flow stats in a different way compared to the older approach.

This patch adds support for 64-bit flow handle and new way to query
flow stats.

Signed-off-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Reviewed-by: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c    |  8 +++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h    |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 74 ++++++++++++++++++++++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h |  5 ++
 4 files changed, 78 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d3287641ce51..6872db9ac301 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4055,6 +4055,10 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 			cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD);
 	}
 
+	if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE)
+		req.flags |= cpu_to_le32(
+			FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE);
+
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
@@ -6662,6 +6666,10 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	if (dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_KONG_MB_CHNL_SUPPORTED)
 		bp->fw_cap |= BNXT_FW_CAP_KONG_MB_CHNL;
 
+	if (dev_caps_cfg &
+	    VER_GET_RESP_DEV_CAPS_CFG_FLOW_HANDLE_64BIT_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_OVS_64BIT_HANDLE;
+
 hwrm_ver_get_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 61d07a4165d8..a451796deefe 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1478,6 +1478,7 @@ struct bnxt {
 	#define BNXT_FW_CAP_NEW_RM			0x00000008
 	#define BNXT_FW_CAP_IF_CHANGE			0x00000010
 	#define BNXT_FW_CAP_KONG_MB_CHNL		0x00000080
+	#define BNXT_FW_CAP_OVS_64BIT_HANDLE		0x00000400
 
 #define BNXT_NEW_RM(bp)		((bp)->fw_cap & BNXT_FW_CAP_NEW_RM)
 	u32			hwrm_spec_code;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index b39584896392..c683b5e96b1d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -337,18 +337,21 @@ static int bnxt_tc_parse_flow(struct bnxt *bp,
 	return bnxt_tc_parse_actions(bp, &flow->actions, tc_flow_cmd->exts);
 }
 
-static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, __le16 flow_handle)
+static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp,
+				   struct bnxt_tc_flow_node *flow_node)
 {
 	struct hwrm_cfa_flow_free_input req = { 0 };
 	int rc;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_FREE, -1, -1);
-	req.flow_handle = flow_handle;
+	if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE)
+		req.ext_flow_handle = flow_node->ext_flow_handle;
+	else
+		req.flow_handle = flow_node->flow_handle;
 
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
-		netdev_info(bp->dev, "Error: %s: flow_handle=0x%x rc=%d",
-			    __func__, flow_handle, rc);
+		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
 
 	if (rc)
 		rc = -EIO;
@@ -418,7 +421,8 @@ static bool bits_set(void *key, int len)
 
 static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 				    __le16 ref_flow_handle,
-				    __le32 tunnel_handle, __le16 *flow_handle)
+				    __le32 tunnel_handle,
+				    struct bnxt_tc_flow_node *flow_node)
 {
 	struct bnxt_tc_actions *actions = &flow->actions;
 	struct bnxt_tc_l3_key *l3_mask = &flow->l3_mask;
@@ -529,7 +533,20 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
 		resp = bnxt_get_hwrm_resp_addr(bp, &req);
-		*flow_handle = resp->flow_handle;
+		/* CFA_FLOW_ALLOC response interpretation:
+		 *		    fw with	     fw with
+		 *		    16-bit	     64-bit
+		 *		    flow handle      flow handle
+		 *		    ===========	     ===========
+		 * flow_handle      flow handle      flow context id
+		 * ext_flow_handle  INVALID	     flow handle
+		 * flow_id	    INVALID	     flow counter id
+		 */
+		flow_node->flow_handle = resp->flow_handle;
+		if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE) {
+			flow_node->ext_flow_handle = resp->ext_flow_handle;
+			flow_node->flow_id = resp->flow_id;
+		}
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 
@@ -1228,7 +1245,7 @@ static int __bnxt_tc_del_flow(struct bnxt *bp,
 	int rc;
 
 	/* send HWRM cmd to free the flow-id */
-	bnxt_hwrm_cfa_flow_free(bp, flow_node->flow_handle);
+	bnxt_hwrm_cfa_flow_free(bp, flow_node);
 
 	mutex_lock(&tc_info->lock);
 
@@ -1250,6 +1267,12 @@ static int __bnxt_tc_del_flow(struct bnxt *bp,
 	return 0;
 }
 
+static void bnxt_tc_set_flow_dir(struct bnxt *bp, struct bnxt_tc_flow *flow,
+				 u16 src_fid)
+{
+	flow->dir = (bp->pf.fw_fid == src_fid) ? BNXT_DIR_RX : BNXT_DIR_TX;
+}
+
 static void bnxt_tc_set_src_fid(struct bnxt *bp, struct bnxt_tc_flow *flow,
 				u16 src_fid)
 {
@@ -1297,6 +1320,9 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 
 	bnxt_tc_set_src_fid(bp, flow, src_fid);
 
+	if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE)
+		bnxt_tc_set_flow_dir(bp, flow, src_fid);
+
 	if (!bnxt_tc_can_offload(bp, flow)) {
 		rc = -ENOSPC;
 		goto free_node;
@@ -1324,7 +1350,7 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 
 	/* send HWRM cmd to alloc the flow */
 	rc = bnxt_hwrm_cfa_flow_alloc(bp, flow, ref_flow_handle,
-				      tunnel_handle, &new_node->flow_handle);
+				      tunnel_handle, new_node);
 	if (rc)
 		goto put_tunnel;
 
@@ -1340,7 +1366,7 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 	return 0;
 
 hwrm_flow_free:
-	bnxt_hwrm_cfa_flow_free(bp, new_node->flow_handle);
+	bnxt_hwrm_cfa_flow_free(bp, new_node);
 put_tunnel:
 	bnxt_tc_put_tunnel_handle(bp, flow, new_node);
 put_l2:
@@ -1401,6 +1427,32 @@ static int bnxt_tc_get_flow_stats(struct bnxt *bp,
 	return 0;
 }
 
+static void bnxt_fill_cfa_stats_req(struct bnxt *bp,
+				    struct bnxt_tc_flow_node *flow_node,
+				    __le16 *flow_handle, __le32 *flow_id)
+{
+	u16 handle;
+
+	if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE) {
+		*flow_id = flow_node->flow_id;
+
+		/* If flow_id is used to fetch flow stats then:
+		 * 1. lower 12 bits of flow_handle must be set to all 1s.
+		 * 2. 15th bit of flow_handle must specify the flow
+		 *    direction (TX/RX).
+		 */
+		if (flow_node->flow.dir == BNXT_DIR_RX)
+			handle = CFA_FLOW_INFO_REQ_FLOW_HANDLE_DIR_RX |
+				 CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK;
+		else
+			handle = CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK;
+
+		*flow_handle = cpu_to_le16(handle);
+	} else {
+		*flow_handle = flow_node->flow_handle;
+	}
+}
+
 static int
 bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
 			     struct bnxt_tc_stats_batch stats_batch[])
@@ -1408,6 +1460,7 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
 	struct hwrm_cfa_flow_stats_input req = { 0 };
 	struct hwrm_cfa_flow_stats_output *resp;
 	__le16 *req_flow_handles = &req.flow_handle_0;
+	__le32 *req_flow_ids = &req.flow_id_0;
 	int rc, i;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_STATS, -1, -1);
@@ -1415,7 +1468,8 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
 	for (i = 0; i < num_flows; i++) {
 		struct bnxt_tc_flow_node *flow_node = stats_batch[i].flow_node;
 
-		req_flow_handles[i] = flow_node->flow_handle;
+		bnxt_fill_cfa_stats_req(bp, flow_node,
+					&req_flow_handles[i], &req_flow_ids[i]);
 	}
 
 	mutex_lock(&bp->hwrm_cmd_lock);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
index 97e09a880693..8a0968967bc5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
@@ -98,6 +98,9 @@ struct bnxt_tc_flow {
 
 	/* flow applicable to pkts ingressing on this fid */
 	u16				src_fid;
+	u8				dir;
+#define BNXT_DIR_RX	1
+#define BNXT_DIR_TX	0
 	struct bnxt_tc_l2_key		l2_key;
 	struct bnxt_tc_l2_key		l2_mask;
 	struct bnxt_tc_l3_key		l3_key;
@@ -170,7 +173,9 @@ struct bnxt_tc_flow_node {
 
 	struct bnxt_tc_flow		flow;
 
+	__le64				ext_flow_handle;
 	__le16				flow_handle;
+	__le32				flow_id;
 
 	/* L2 node in l2 hashtable that shares flow's l2 key */
 	struct bnxt_tc_l2_node		*l2_node;
-- 
cgit v1.2.3


From 0c2ff8d796895448b3a23c9cf7f37e721daeea48 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 20 Dec 2018 03:38:53 -0500
Subject: bnxt_en: Adjust default RX coalescing ticks to 10 us.

For a little better performance on faster machines and faster link
speeds.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6872db9ac301..3aa80da973d7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9416,7 +9416,7 @@ static void bnxt_init_dflt_coal(struct bnxt *bp)
 	 * 1 coal_buf x bufs_per_record = 1 completion record.
 	 */
 	coal = &bp->rx_coal;
-	coal->coal_ticks = 14;
+	coal->coal_ticks = 10;
 	coal->coal_bufs = 30;
 	coal->coal_ticks_irq = 1;
 	coal->coal_bufs_irq = 2;
-- 
cgit v1.2.3


From 5a8d5209ac0228c9cf8f335dfdfffa71c54b3201 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 19 Dec 2018 22:13:03 -0800
Subject: selftests: bpf: add trivial JSET tests

We seem to have no JSET instruction test, and LLVM does not
generate it at all, so let's add a simple hand-coded test
to make sure JIT implementations are correct.

v2:
 - extend test_verifier to handle multiple inputs and
   add the sample there (Daniel)
 - add a sign extension case

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 209 +++++++++++++++++++++++-----
 1 file changed, 178 insertions(+), 31 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 7865b94c02c4..580fc9429147 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -49,6 +49,7 @@
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_FIXUPS	8
 #define MAX_NR_MAPS	13
+#define MAX_TEST_RUNS	8
 #define POINTER_VALUE	0xcafe4all
 #define TEST_DATA_LEN	64
 
@@ -86,6 +87,14 @@ struct bpf_test {
 	uint8_t flags;
 	__u8 data[TEST_DATA_LEN];
 	void (*fill_helper)(struct bpf_test *self);
+	uint8_t runs;
+	struct {
+		uint32_t retval, retval_unpriv;
+		union {
+			__u8 data[TEST_DATA_LEN];
+			__u64 data64[TEST_DATA_LEN / 8];
+		};
+	} retvals[MAX_TEST_RUNS];
 };
 
 /* Note we want this to be 64 bit aligned so that the end of our array is
@@ -14161,6 +14170,101 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R1 leaks addr",
 		.result = REJECT,
 	},
+	{
+		"jset: functional",
+		.insns = {
+			/* r0 = 0 */
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			/* prep for direct packet access via r2 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_4, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_2, 0),
+
+			/* reg, bit 63 or bit 0 set, taken */
+			BPF_LD_IMM64(BPF_REG_8, 0x8000000000000001),
+			BPF_JMP_REG(BPF_JSET, BPF_REG_7, BPF_REG_8, 1),
+			BPF_EXIT_INSN(),
+
+			/* reg, bit 62, not taken */
+			BPF_LD_IMM64(BPF_REG_8, 0x4000000000000000),
+			BPF_JMP_REG(BPF_JSET, BPF_REG_7, BPF_REG_8, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_EXIT_INSN(),
+
+			/* imm, any bit set, taken */
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_7, -1, 1),
+			BPF_EXIT_INSN(),
+
+			/* imm, bit 31 set, taken */
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_7, 0x80000000, 1),
+			BPF_EXIT_INSN(),
+
+			/* all good - return r0 == 2 */
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.runs = 7,
+		.retvals = {
+			{ .retval = 2,
+			  .data64 = { (1ULL << 63) | (1U << 31) | (1U << 0), }
+			},
+			{ .retval = 2,
+			  .data64 = { (1ULL << 63) | (1U << 31), }
+			},
+			{ .retval = 2,
+			  .data64 = { (1ULL << 31) | (1U << 0), }
+			},
+			{ .retval = 2,
+			  .data64 = { (__u32)-1, }
+			},
+			{ .retval = 2,
+			  .data64 = { ~0x4000000000000000ULL, }
+			},
+			{ .retval = 0,
+			  .data64 = { 0, }
+			},
+			{ .retval = 0,
+			  .data64 = { ~0ULL, }
+			},
+		},
+	},
+	{
+		"jset: sign-extend",
+		.insns = {
+			/* r0 = 0 */
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			/* prep for direct packet access via r2 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_4, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_2, 0),
+
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_7, 0x80000000, 1),
+			BPF_EXIT_INSN(),
+
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 2,
+		.data = { 1, 0, 0, 0, 0, 0, 0, 1, },
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -14443,16 +14547,42 @@ out:
 	return ret;
 }
 
+static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val,
+			    void *data, size_t size_data)
+{
+	__u8 tmp[TEST_DATA_LEN << 2];
+	__u32 size_tmp = sizeof(tmp);
+	uint32_t retval;
+	int err;
+
+	if (unpriv)
+		set_admin(true);
+	err = bpf_prog_test_run(fd_prog, 1, data, size_data,
+				tmp, &size_tmp, &retval, NULL);
+	if (unpriv)
+		set_admin(false);
+	if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
+		printf("Unexpected bpf_prog_test_run error ");
+		return err;
+	}
+	if (!err && retval != expected_val &&
+	    expected_val != POINTER_VALUE) {
+		printf("FAIL retval %d != %d ", retval, expected_val);
+		return 1;
+	}
+
+	return 0;
+}
+
 static void do_test_single(struct bpf_test *test, bool unpriv,
 			   int *passes, int *errors)
 {
 	int fd_prog, expected_ret, alignment_prevented_execution;
 	int prog_len, prog_type = test->prog_type;
 	struct bpf_insn *prog = test->insns;
+	int run_errs, run_successes;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
-	uint32_t expected_val;
-	uint32_t retval;
 	__u32 pflags;
 	int i, err;
 
@@ -14476,8 +14606,6 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		       test->result_unpriv : test->result;
 	expected_err = unpriv && test->errstr_unpriv ?
 		       test->errstr_unpriv : test->errstr;
-	expected_val = unpriv && test->retval_unpriv ?
-		       test->retval_unpriv : test->retval;
 
 	alignment_prevented_execution = 0;
 
@@ -14489,10 +14617,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		}
 #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 		if (fd_prog >= 0 &&
-		    (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)) {
+		    (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS))
 			alignment_prevented_execution = 1;
-			goto test_ok;
-		}
 #endif
 	} else {
 		if (fd_prog >= 0) {
@@ -14519,33 +14645,54 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		}
 	}
 
-	if (fd_prog >= 0) {
-		__u8 tmp[TEST_DATA_LEN << 2];
-		__u32 size_tmp = sizeof(tmp);
-
-		if (unpriv)
-			set_admin(true);
-		err = bpf_prog_test_run(fd_prog, 1, test->data,
-					sizeof(test->data), tmp, &size_tmp,
-					&retval, NULL);
-		if (unpriv)
-			set_admin(false);
-		if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
-			printf("Unexpected bpf_prog_test_run error\n");
-			goto fail_log;
+	run_errs = 0;
+	run_successes = 0;
+	if (!alignment_prevented_execution && fd_prog >= 0) {
+		uint32_t expected_val;
+		int i;
+
+		if (!test->runs) {
+			expected_val = unpriv && test->retval_unpriv ?
+				test->retval_unpriv : test->retval;
+
+			err = do_prog_test_run(fd_prog, unpriv, expected_val,
+					       test->data, sizeof(test->data));
+			if (err)
+				run_errs++;
+			else
+				run_successes++;
 		}
-		if (!err && retval != expected_val &&
-		    expected_val != POINTER_VALUE) {
-			printf("FAIL retval %d != %d\n", retval, expected_val);
-			goto fail_log;
+
+		for (i = 0; i < test->runs; i++) {
+			if (unpriv && test->retvals[i].retval_unpriv)
+				expected_val = test->retvals[i].retval_unpriv;
+			else
+				expected_val = test->retvals[i].retval;
+
+			err = do_prog_test_run(fd_prog, unpriv, expected_val,
+					       test->retvals[i].data,
+					       sizeof(test->retvals[i].data));
+			if (err) {
+				printf("(run %d/%d) ", i + 1, test->runs);
+				run_errs++;
+			} else {
+				run_successes++;
+			}
 		}
 	}
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-test_ok:
-#endif
-	(*passes)++;
-	printf("OK%s\n", alignment_prevented_execution ?
-	       " (NOTE: not executed due to unknown alignment)" : "");
+
+	if (!run_errs) {
+		(*passes)++;
+		if (run_successes > 1)
+			printf("%d cases ", run_successes);
+		printf("OK");
+		if (alignment_prevented_execution)
+			printf(" (NOTE: not executed due to unknown alignment)");
+		printf("\n");
+	} else {
+		printf("\n");
+		goto fail_log;
+	}
 close_fds:
 	close(fd_prog);
 	for (i = 0; i < MAX_NR_MAPS; i++)
-- 
cgit v1.2.3


From 960ea056561a08e2b837b2f02d22c53226414a84 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 19 Dec 2018 22:13:04 -0800
Subject: bpf: verifier: teach the verifier to reason about the BPF_JSET
 instruction

Some JITs (nfp) try to optimize code on their own.  It could make
sense in case of BPF_JSET instruction which is currently not interpreted
by the verifier, meaning for instance that dead could would not be
detected if it was under BPF_JSET branch.

Teach the verifier basics of BPF_JSET, JIT optimizations will be
removed shortly.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Jiong Wang <jiong.wang@netronome.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5c64281d566e..98ed27bbd045 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3859,6 +3859,12 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
 		if (tnum_is_const(reg->var_off))
 			return !tnum_equals_const(reg->var_off, val);
 		break;
+	case BPF_JSET:
+		if ((~reg->var_off.mask & reg->var_off.value) & val)
+			return 1;
+		if (!((reg->var_off.mask | reg->var_off.value) & val))
+			return 0;
+		break;
 	case BPF_JGT:
 		if (reg->umin_value > val)
 			return 1;
@@ -3943,6 +3949,13 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 		 */
 		__mark_reg_known(false_reg, val);
 		break;
+	case BPF_JSET:
+		false_reg->var_off = tnum_and(false_reg->var_off,
+					      tnum_const(~val));
+		if (is_power_of_2(val))
+			true_reg->var_off = tnum_or(true_reg->var_off,
+						    tnum_const(val));
+		break;
 	case BPF_JGT:
 		false_reg->umax_value = min(false_reg->umax_value, val);
 		true_reg->umin_value = max(true_reg->umin_value, val + 1);
@@ -4015,6 +4028,13 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 		 */
 		__mark_reg_known(false_reg, val);
 		break;
+	case BPF_JSET:
+		false_reg->var_off = tnum_and(false_reg->var_off,
+					      tnum_const(~val));
+		if (is_power_of_2(val))
+			true_reg->var_off = tnum_or(true_reg->var_off,
+						    tnum_const(val));
+		break;
 	case BPF_JGT:
 		true_reg->umax_value = min(true_reg->umax_value, val - 1);
 		false_reg->umin_value = max(false_reg->umin_value, val);
-- 
cgit v1.2.3


From 14507e35bd9dedcd14c24f9e5e0e0dd48e972e53 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 19 Dec 2018 22:13:05 -0800
Subject: selftests: bpf: verifier: add tests for JSET interpretation

Validate that the verifier reasons correctly about the bounds
and removes dead code based on results of JSET instruction.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 96 +++++++++++++++++++++++++++++
 1 file changed, 96 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 580fc9429147..b246931c46ef 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -14265,6 +14265,102 @@ static struct bpf_test tests[] = {
 		.retval = 2,
 		.data = { 1, 0, 0, 0, 0, 0, 0, 1, },
 	},
+	{
+		"jset: known const compare",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.retval_unpriv = 1,
+		.result_unpriv = ACCEPT,
+		.retval = 1,
+		.result = ACCEPT,
+	},
+	{
+		"jset: known const compare bad",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.errstr_unpriv = "!read_ok",
+		.result_unpriv = REJECT,
+		.errstr = "!read_ok",
+		.result = REJECT,
+	},
+	{
+		"jset: unknown const compare taken",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_prandom_u32),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.errstr_unpriv = "!read_ok",
+		.result_unpriv = REJECT,
+		.errstr = "!read_ok",
+		.result = REJECT,
+	},
+	{
+		"jset: unknown const compare not taken",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_prandom_u32),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.errstr_unpriv = "!read_ok",
+		.result_unpriv = REJECT,
+		.errstr = "!read_ok",
+		.result = REJECT,
+	},
+	{
+		"jset: half-known const compare",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_prandom_u32),
+			BPF_ALU64_IMM(BPF_OR, BPF_REG_0, 2),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.result_unpriv = ACCEPT,
+		.result = ACCEPT,
+	},
+	{
+		"jset: range",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_prandom_u32),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xff),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0xf0, 3),
+			BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 0x10, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0x10, 1),
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0x10, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.result_unpriv = ACCEPT,
+		.result = ACCEPT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
-- 
cgit v1.2.3


From 9b38c4056b2736bb5902e8b0911832db666fd19b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 19 Dec 2018 22:13:06 -0800
Subject: bpf: verifier: reorder stack size check with dead code sanitization

Reorder the calls to check_max_stack_depth() and sanitize_dead_code()
to separate functions which can rewrite instructions from pure checks.

No functional changes.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 98ed27bbd045..d27d5a880015 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6983,10 +6983,11 @@ skip_full_check:
 	free_states(env);
 
 	if (ret == 0)
-		sanitize_dead_code(env);
+		ret = check_max_stack_depth(env);
 
+	/* instruction rewrites happen after this point */
 	if (ret == 0)
-		ret = check_max_stack_depth(env);
+		sanitize_dead_code(env);
 
 	if (ret == 0)
 		/* program is valid, convert *(u32*)(ctx + off) accesses */
-- 
cgit v1.2.3


From 6e774845b321e729966fed7de4aa8ea59c2c3b2e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 19 Dec 2018 22:13:07 -0800
Subject: nfp: bpf: remove the trivial JSET optimization

The verifier will now understand the JSET instruction, so don't
mark the dead branch in the JIT as noop.  We won't generate any
code, anyway.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/jit.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 662cbc21d909..f765e76e4924 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -3054,11 +3054,6 @@ static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u64 imm = insn->imm; /* sign extend */
 	swreg tmp_reg;
 
-	if (!imm) {
-		meta->skip = true;
-		return 0;
-	}
-
 	if (imm & ~0U) {
 		tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
 		emit_alu(nfp_prog, reg_none(),
-- 
cgit v1.2.3


From 4987eaccd2d1535eaa72d3bbe2b8bfc8267ba965 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 19 Dec 2018 22:13:08 -0800
Subject: nfp: bpf: optimize codegen for JSET with a constant

The top word of the constant can only have bits set if sign
extension set it to all-1, therefore we don't really have to
mask the top half of the register.  We can just OR it into
the result as is.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/jit.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index f765e76e4924..e23ca90289f7 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -3052,21 +3052,19 @@ static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 	u64 imm = insn->imm; /* sign extend */
+	u8 dst_gpr = insn->dst_reg * 2;
 	swreg tmp_reg;
 
-	if (imm & ~0U) {
-		tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
-		emit_alu(nfp_prog, reg_none(),
-			 reg_a(insn->dst_reg * 2), ALU_OP_AND, tmp_reg);
-		emit_br(nfp_prog, BR_BNE, insn->off, 0);
-	}
-
-	if (imm >> 32) {
-		tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
+	tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
+	emit_alu(nfp_prog, imm_b(nfp_prog),
+		 reg_a(dst_gpr), ALU_OP_AND, tmp_reg);
+	/* Upper word of the mask can only be 0 or ~0 from sign extension,
+	 * so either ignore it or OR the whole thing in.
+	 */
+	if (imm >> 32)
 		emit_alu(nfp_prog, reg_none(),
-			 reg_a(insn->dst_reg * 2 + 1), ALU_OP_AND, tmp_reg);
-		emit_br(nfp_prog, BR_BNE, insn->off, 0);
-	}
+			 reg_a(dst_gpr + 1), ALU_OP_OR, imm_b(nfp_prog));
+	emit_br(nfp_prog, BR_BNE, insn->off, 0);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 489c066cfdf1cad776c5e041f32a2e3cdb05050a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 19 Dec 2018 22:13:09 -0800
Subject: selftests: bpf: add missing executables to .gitignore

commit 435f90a338ae ("selftests/bpf: add a test case for sock_ops
perf-event notification") missed adding new test to gitignore.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/.gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 1b799e30c06d..4a9785043a39 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -27,3 +27,4 @@ test_flow_dissector
 flow_dissector_load
 test_netcnt
 test_section_names
+test_tcpnotify_user
-- 
cgit v1.2.3


From bff70e5f78e9708de18cbed003abe10349719ba5 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 20 Dec 2018 09:53:10 +0200
Subject: ath10k: remove set but not used variable 'num_tdls_vifs'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/wireless/ath/ath10k/mac.c: In function 'ath10k_sta_state':
drivers/net/wireless/ath/ath10k/mac.c:6238:7: warning:
 variable 'num_tdls_vifs' set but not used [-Wunused-but-set-variable]

'num_tdls_vifs' not used any more after
  9a993cc1ea95 ("ath10k: fix the logic of limiting tdls peer counts")

Also, remove the single called function ath10k_mac_tdls_vifs_count
and ath10k_mac_tdls_vifs_count_iter.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c | 26 --------------------------
 1 file changed, 26 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 1db2a308f81e..9d75de7b633b 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -5754,30 +5754,6 @@ static int ath10k_mac_tdls_vif_stations_count(struct ieee80211_hw *hw,
 	return data.num_tdls_stations;
 }
 
-static void ath10k_mac_tdls_vifs_count_iter(void *data, u8 *mac,
-					    struct ieee80211_vif *vif)
-{
-	struct ath10k_vif *arvif = (void *)vif->drv_priv;
-	int *num_tdls_vifs = data;
-
-	if (vif->type != NL80211_IFTYPE_STATION)
-		return;
-
-	if (ath10k_mac_tdls_vif_stations_count(arvif->ar->hw, vif) > 0)
-		(*num_tdls_vifs)++;
-}
-
-static int ath10k_mac_tdls_vifs_count(struct ieee80211_hw *hw)
-{
-	int num_tdls_vifs = 0;
-
-	ieee80211_iterate_active_interfaces_atomic(hw,
-						   IEEE80211_IFACE_ITER_NORMAL,
-						   ath10k_mac_tdls_vifs_count_iter,
-						   &num_tdls_vifs);
-	return num_tdls_vifs;
-}
-
 static int ath10k_hw_scan(struct ieee80211_hw *hw,
 			  struct ieee80211_vif *vif,
 			  struct ieee80211_scan_request *hw_req)
@@ -6285,7 +6261,6 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 		 */
 		enum wmi_peer_type peer_type = WMI_PEER_TYPE_DEFAULT;
 		u32 num_tdls_stations;
-		u32 num_tdls_vifs;
 
 		ath10k_dbg(ar, ATH10K_DBG_MAC,
 			   "mac vdev %d peer create %pM (new sta) sta %d / %d peer %d / %d\n",
@@ -6303,7 +6278,6 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 		}
 
 		num_tdls_stations = ath10k_mac_tdls_vif_stations_count(hw, vif);
-		num_tdls_vifs = ath10k_mac_tdls_vifs_count(hw);
 
 		if (sta->tdls) {
 			if (num_tdls_stations >= ar->max_num_tdls_vdevs) {
-- 
cgit v1.2.3


From 553a7cca769d551f1317186760631487c47e23bf Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <periyasa@codeaurora.org>
Date: Thu, 20 Dec 2018 09:53:17 +0200
Subject: ath10k: fix kernel panic due to use after free

This issue arise in a race condition between ath10k_sta_state() and
ath10k_htt_fetch_peer_stats(), explained in below scenario

Steps:
1. In ath10k_sta_state(), arsta->tx_stats get deallocated before peer deletion
   when the station moves from IEEE80211_STA_NONE to IEEE80211_STA_NOTEXIST
   state.
2. Meanwhile ath10k receive HTT_T2H_MSG_TYPE_PEER_STATS message.
   In ath10k_htt_fetch_peer_stats(), arsta->tx_stats get accessed after
   the peer validation check.

Since arsta->tx_stats get freed before the peer deletion [1].
ath10k_htt_fetch_peer_stats() ended up in "use after free" situation.

Fixed this issue by moving the arsta->tx_stats free handling after the
peer deletion. so that ath10k_htt_fetch_peer_stats() will not end up in
"use after free" situation.

Kernel Panic:

Unable to handle kernel NULL pointer dereference at virtual address 00000286
pgd = d8754000
[00000286] *pgd=00000000
Internal error: Oops: 5 [#1] PREEMPT SMP ARM
...
CPU: 0 PID: 6245 Comm: hostapd Not tainted
task: dc44cac0 ti: d4a38000 task.ti: d4a38000
PC is at kmem_cache_alloc+0x7c/0x114
LR is at ath10k_sta_state+0x190/0xd58 [ath10k_core]
pc : [<c02bdc50>]    lr : [<bf916b78>]    psr: 20000013
sp : d4a39b88  ip : 00000000  fp : 00000001
r10: 00000000  r9 : 1d3bc000  r8 : 00000dc0
r7 : 000080d0  r6 : d4a38000  r5 : dd401b00  r4 : 00000286
r3 : 00000000  r2 : d4a39ba0  r1 : 000080d0  r0 : dd401b00
Flags: nzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment user
Control: 10c5787d  Table: 5a75406a  DAC: 00000015
Process hostapd (pid: 6245, stack limit = 0xd4a38238)
Stack: (0xd4a39b88 to 0xd4a3a000)
...
[<c02bdc50>] (kmem_cache_alloc) from [<bf916b78>] (ath10k_sta_state+0x190/0xd58 [ath10k_core])
[<bf916b78>] (ath10k_sta_state [ath10k_core]) from [<bf870d4c>] (sta_info_insert_rcu+0x418/0x61c [mac80211])
[<bf870d4c>] (sta_info_insert_rcu [mac80211]) from [<bf88634c>] (ieee80211_add_station+0xf0/0x134 [mac80211])
[<bf88634c>] (ieee80211_add_station [mac80211]) from [<bf83f3c4>] (nl80211_new_station+0x330/0x36c [cfg80211])
[<bf83f3c4>] (nl80211_new_station [cfg80211]) from [<bf6c4040>] (extack_doit+0x2c/0x74 [compat])
[<bf6c4040>] (extack_doit [compat]) from [<c05c285c>] (genl_rcv_msg+0x274/0x30c)
[<c05c285c>] (genl_rcv_msg) from [<c05c1d98>] (netlink_rcv_skb+0x58/0xac)
[<c05c1d98>] (netlink_rcv_skb) from [<c05c25d4>] (genl_rcv+0x20/0x34)
[<c05c25d4>] (genl_rcv) from [<c05c1750>] (netlink_unicast+0x11c/0x204)
[<c05c1750>] (netlink_unicast) from [<c05c1be0>] (netlink_sendmsg+0x30c/0x370)
[<c05c1be0>] (netlink_sendmsg) from [<c0587e90>] (sock_sendmsg+0x70/0x84)
[<c0587e90>] (sock_sendmsg) from [<c058970c>] (___sys_sendmsg.part.3+0x188/0x228)
[<c058970c>] (___sys_sendmsg.part.3) from [<c058a594>] (__sys_sendmsg+0x4c/0x70)
[<c058a594>] (__sys_sendmsg) from [<c0208c80>] (ret_fast_syscall+0x0/0x44)
Code: ebfffec1 e1a04000 ea00001b e5953014 (e7940003)
ath10k_pci 0000:01:00.0: SWBA overrun on vdev 0, skipped old beacon

Hardware tested: QCA9984
Firmware tested: 10.4-3.6.0.1-00004

Fixes: a904417fc ("ath10k: add extended per sta tx statistics support")
Signed-off-by: Karthikeyan Periyasamy <periyasa@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 9d75de7b633b..3d539450f6c5 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -6361,11 +6361,6 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 			   "mac vdev %d peer delete %pM sta %pK (sta gone)\n",
 			   arvif->vdev_id, sta->addr, sta);
 
-		if (ath10k_debug_is_extd_tx_stats_enabled(ar)) {
-			kfree(arsta->tx_stats);
-			arsta->tx_stats = NULL;
-		}
-
 		if (sta->tdls) {
 			ret = ath10k_mac_tdls_peer_update(ar, arvif->vdev_id,
 							  sta,
@@ -6405,6 +6400,11 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 		}
 		spin_unlock_bh(&ar->data_lock);
 
+		if (ath10k_debug_is_extd_tx_stats_enabled(ar)) {
+			kfree(arsta->tx_stats);
+			arsta->tx_stats = NULL;
+		}
+
 		for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
 			ath10k_mac_txq_unref(ar, sta->txq[i]);
 
-- 
cgit v1.2.3


From 85bd0107c6cd445a33066a57658fc585244a1100 Mon Sep 17 00:00:00 2001
From: Yu Wang <yyuwang@codeaurora.org>
Date: Thu, 20 Dec 2018 09:53:26 +0200
Subject: ath10k: add amsdu support for monitor mode

When processing HTT_T2H_MSG_TYPE_RX_IN_ORD_PADDR_IND, if the length of a msdu
is larger than the tailroom of the rx skb, skb_over_panic issue will happen
when calling skb_put.  In monitor mode, amsdu will be handled in this path, and
msdu_len of the first msdu_desc is the length of the entire amsdu, which might
be larger than the maximum length of a skb, in such case, it will hit the issue
upon.

To fix this issue, process msdu list separately for monitor mode.

Successfully tested with:
QCA6174 (FW version: RM.4.4.1.c2-00057-QCARMSWP-1).

Signed-off-by: Yu Wang <yyuwang@codeaurora.org>
[kvalo@codeaurora.org: cosmetic cleanup]
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/htt_rx.c | 188 ++++++++++++++++++++++++++++++-
 1 file changed, 186 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index 984b0458d077..e04c080e6a37 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -469,6 +469,166 @@ static struct sk_buff *ath10k_htt_rx_pop_paddr(struct ath10k_htt *htt,
 	return msdu;
 }
 
+static inline void ath10k_htt_append_frag_list(struct sk_buff *skb_head,
+					       struct sk_buff *frag_list,
+					       unsigned int frag_len)
+{
+	skb_shinfo(skb_head)->frag_list = frag_list;
+	skb_head->data_len = frag_len;
+	skb_head->len += skb_head->data_len;
+}
+
+static int ath10k_htt_rx_handle_amsdu_mon_32(struct ath10k_htt *htt,
+					     struct sk_buff *msdu,
+					     struct htt_rx_in_ord_msdu_desc **msdu_desc)
+{
+	struct ath10k *ar = htt->ar;
+	u32 paddr;
+	struct sk_buff *frag_buf;
+	struct sk_buff *prev_frag_buf;
+	u8 last_frag;
+	struct htt_rx_in_ord_msdu_desc *ind_desc = *msdu_desc;
+	struct htt_rx_desc *rxd;
+	int amsdu_len = __le16_to_cpu(ind_desc->msdu_len);
+
+	rxd = (void *)msdu->data;
+	trace_ath10k_htt_rx_desc(ar, rxd, sizeof(*rxd));
+
+	skb_put(msdu, sizeof(struct htt_rx_desc));
+	skb_pull(msdu, sizeof(struct htt_rx_desc));
+	skb_put(msdu, min(amsdu_len, HTT_RX_MSDU_SIZE));
+	amsdu_len -= msdu->len;
+
+	last_frag = ind_desc->reserved;
+	if (last_frag) {
+		if (amsdu_len) {
+			ath10k_warn(ar, "invalid amsdu len %u, left %d",
+				    __le16_to_cpu(ind_desc->msdu_len),
+				    amsdu_len);
+		}
+		return 0;
+	}
+
+	ind_desc++;
+	paddr = __le32_to_cpu(ind_desc->msdu_paddr);
+	frag_buf = ath10k_htt_rx_pop_paddr(htt, paddr);
+	if (!frag_buf) {
+		ath10k_warn(ar, "failed to pop frag-1 paddr: 0x%x", paddr);
+		return -ENOENT;
+	}
+
+	skb_put(frag_buf, min(amsdu_len, HTT_RX_BUF_SIZE));
+	ath10k_htt_append_frag_list(msdu, frag_buf, amsdu_len);
+
+	amsdu_len -= frag_buf->len;
+	prev_frag_buf = frag_buf;
+	last_frag = ind_desc->reserved;
+	while (!last_frag) {
+		ind_desc++;
+		paddr = __le32_to_cpu(ind_desc->msdu_paddr);
+		frag_buf = ath10k_htt_rx_pop_paddr(htt, paddr);
+		if (!frag_buf) {
+			ath10k_warn(ar, "failed to pop frag-n paddr: 0x%x",
+				    paddr);
+			prev_frag_buf->next = NULL;
+			return -ENOENT;
+		}
+
+		skb_put(frag_buf, min(amsdu_len, HTT_RX_BUF_SIZE));
+		last_frag = ind_desc->reserved;
+		amsdu_len -= frag_buf->len;
+
+		prev_frag_buf->next = frag_buf;
+		prev_frag_buf = frag_buf;
+	}
+
+	if (amsdu_len) {
+		ath10k_warn(ar, "invalid amsdu len %u, left %d",
+			    __le16_to_cpu(ind_desc->msdu_len), amsdu_len);
+	}
+
+	*msdu_desc = ind_desc;
+
+	prev_frag_buf->next = NULL;
+	return 0;
+}
+
+static int
+ath10k_htt_rx_handle_amsdu_mon_64(struct ath10k_htt *htt,
+				  struct sk_buff *msdu,
+				  struct htt_rx_in_ord_msdu_desc_ext **msdu_desc)
+{
+	struct ath10k *ar = htt->ar;
+	u64 paddr;
+	struct sk_buff *frag_buf;
+	struct sk_buff *prev_frag_buf;
+	u8 last_frag;
+	struct htt_rx_in_ord_msdu_desc_ext *ind_desc = *msdu_desc;
+	struct htt_rx_desc *rxd;
+	int amsdu_len = __le16_to_cpu(ind_desc->msdu_len);
+
+	rxd = (void *)msdu->data;
+	trace_ath10k_htt_rx_desc(ar, rxd, sizeof(*rxd));
+
+	skb_put(msdu, sizeof(struct htt_rx_desc));
+	skb_pull(msdu, sizeof(struct htt_rx_desc));
+	skb_put(msdu, min(amsdu_len, HTT_RX_MSDU_SIZE));
+	amsdu_len -= msdu->len;
+
+	last_frag = ind_desc->reserved;
+	if (last_frag) {
+		if (amsdu_len) {
+			ath10k_warn(ar, "invalid amsdu len %u, left %d",
+				    __le16_to_cpu(ind_desc->msdu_len),
+				    amsdu_len);
+		}
+		return 0;
+	}
+
+	ind_desc++;
+	paddr = __le64_to_cpu(ind_desc->msdu_paddr);
+	frag_buf = ath10k_htt_rx_pop_paddr(htt, paddr);
+	if (!frag_buf) {
+		ath10k_warn(ar, "failed to pop frag-1 paddr: 0x%llx", paddr);
+		return -ENOENT;
+	}
+
+	skb_put(frag_buf, min(amsdu_len, HTT_RX_BUF_SIZE));
+	ath10k_htt_append_frag_list(msdu, frag_buf, amsdu_len);
+
+	amsdu_len -= frag_buf->len;
+	prev_frag_buf = frag_buf;
+	last_frag = ind_desc->reserved;
+	while (!last_frag) {
+		ind_desc++;
+		paddr = __le64_to_cpu(ind_desc->msdu_paddr);
+		frag_buf = ath10k_htt_rx_pop_paddr(htt, paddr);
+		if (!frag_buf) {
+			ath10k_warn(ar, "failed to pop frag-n paddr: 0x%llx",
+				    paddr);
+			prev_frag_buf->next = NULL;
+			return -ENOENT;
+		}
+
+		skb_put(frag_buf, min(amsdu_len, HTT_RX_BUF_SIZE));
+		last_frag = ind_desc->reserved;
+		amsdu_len -= frag_buf->len;
+
+		prev_frag_buf->next = frag_buf;
+		prev_frag_buf = frag_buf;
+	}
+
+	if (amsdu_len) {
+		ath10k_warn(ar, "invalid amsdu len %u, left %d",
+			    __le16_to_cpu(ind_desc->msdu_len), amsdu_len);
+	}
+
+	*msdu_desc = ind_desc;
+
+	prev_frag_buf->next = NULL;
+	return 0;
+}
+
 static int ath10k_htt_rx_pop_paddr32_list(struct ath10k_htt *htt,
 					  struct htt_rx_in_ord_ind *ev,
 					  struct sk_buff_head *list)
@@ -477,7 +637,7 @@ static int ath10k_htt_rx_pop_paddr32_list(struct ath10k_htt *htt,
 	struct htt_rx_in_ord_msdu_desc *msdu_desc = ev->msdu_descs32;
 	struct htt_rx_desc *rxd;
 	struct sk_buff *msdu;
-	int msdu_count;
+	int msdu_count, ret;
 	bool is_offload;
 	u32 paddr;
 
@@ -495,6 +655,18 @@ static int ath10k_htt_rx_pop_paddr32_list(struct ath10k_htt *htt,
 			return -ENOENT;
 		}
 
+		if (!is_offload && ar->monitor_arvif) {
+			ret = ath10k_htt_rx_handle_amsdu_mon_32(htt, msdu,
+								&msdu_desc);
+			if (ret) {
+				__skb_queue_purge(list);
+				return ret;
+			}
+			__skb_queue_tail(list, msdu);
+			msdu_desc++;
+			continue;
+		}
+
 		__skb_queue_tail(list, msdu);
 
 		if (!is_offload) {
@@ -527,7 +699,7 @@ static int ath10k_htt_rx_pop_paddr64_list(struct ath10k_htt *htt,
 	struct htt_rx_in_ord_msdu_desc_ext *msdu_desc = ev->msdu_descs64;
 	struct htt_rx_desc *rxd;
 	struct sk_buff *msdu;
-	int msdu_count;
+	int msdu_count, ret;
 	bool is_offload;
 	u64 paddr;
 
@@ -544,6 +716,18 @@ static int ath10k_htt_rx_pop_paddr64_list(struct ath10k_htt *htt,
 			return -ENOENT;
 		}
 
+		if (!is_offload && ar->monitor_arvif) {
+			ret = ath10k_htt_rx_handle_amsdu_mon_64(htt, msdu,
+								&msdu_desc);
+			if (ret) {
+				__skb_queue_purge(list);
+				return ret;
+			}
+			__skb_queue_tail(list, msdu);
+			msdu_desc++;
+			continue;
+		}
+
 		__skb_queue_tail(list, msdu);
 
 		if (!is_offload) {
-- 
cgit v1.2.3


From 9a9cf0e63f707303dd4bbd2e14f812b85116b8b5 Mon Sep 17 00:00:00 2001
From: Anilkumar Kolli <akolli@codeaurora.org>
Date: Thu, 20 Dec 2018 09:53:28 +0200
Subject: ath10k: report tx rate using ieee80211_tx_rate_update()

Mesh path metric needs tx rate information from ieee80211_tx_status()
call but in ath10k there is no mechanism to report tx rate information
via ieee80211_tx_status(), the tx rate is only accessible via
sta_statiscs() op.

Per peer tx stats has tx rate info available, Tx rate is available
to ath10k driver after every 4 PPDU sent in the air. For each PPDU,
ath10k driver updates rate informattion to mac80211 using
ieee80211_tx_rate_update().

Per peer txrate information is updated through per peer statistics
and is available for QCA9888/QCA9984/QCA4019/QCA998X only

Tested on QCA9984 with firmware-5.bin_10.4-3.5.3-00053
Tested on QCA998X with firmware-5.bin_10.2.4-1.0-00036

Signed-off-by: Anilkumar Kolli <akolli@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/core.h   |  1 +
 drivers/net/wireless/ath/ath10k/htt_rx.c | 67 +++++++++++++++++++++++++++++---
 drivers/net/wireless/ath/ath10k/wmi.h    |  1 +
 3 files changed, 64 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index d14a4f928218..46e9c8c97a4d 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -494,6 +494,7 @@ struct ath10k_sta {
 	u32 smps;
 	u16 peer_id;
 	struct rate_info txrate;
+	struct ieee80211_tx_info tx_info;
 
 	struct work_struct update_wk;
 	u64 rx_duration;
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index e04c080e6a37..d44a7d8f7fc1 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -2811,7 +2811,7 @@ void ath10k_htt_htc_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 		dev_kfree_skb_any(skb);
 }
 
-static inline int ath10k_get_legacy_rate_idx(struct ath10k *ar, u8 rate)
+static inline s8 ath10k_get_legacy_rate_idx(struct ath10k *ar, u8 rate)
 {
 	static const u8 legacy_rates[] = {1, 2, 5, 11, 6, 9, 12,
 					  18, 24, 36, 48, 54};
@@ -2830,7 +2830,7 @@ static void
 ath10k_accumulate_per_peer_tx_stats(struct ath10k *ar,
 				    struct ath10k_sta *arsta,
 				    struct ath10k_per_peer_tx_stats *pstats,
-				    u8 legacy_rate_idx)
+				    s8 legacy_rate_idx)
 {
 	struct rate_info *txrate = &arsta->txrate;
 	struct ath10k_htt_tx_stats *tx_stats;
@@ -2950,8 +2950,10 @@ ath10k_update_per_peer_tx_stats(struct ath10k *ar,
 				struct ath10k_per_peer_tx_stats *peer_stats)
 {
 	struct ath10k_sta *arsta = (struct ath10k_sta *)sta->drv_priv;
+	struct ieee80211_chanctx_conf *conf = NULL;
 	u8 rate = 0, sgi;
 	s8 rate_idx = 0;
+	bool skip_auto_rate;
 	struct rate_info txrate;
 
 	lockdep_assert_held(&ar->data_lock);
@@ -2961,6 +2963,13 @@ ath10k_update_per_peer_tx_stats(struct ath10k *ar,
 	txrate.nss = ATH10K_HW_NSS(peer_stats->ratecode);
 	txrate.mcs = ATH10K_HW_MCS_RATE(peer_stats->ratecode);
 	sgi = ATH10K_HW_GI(peer_stats->flags);
+	skip_auto_rate = ATH10K_FW_SKIPPED_RATE_CTRL(peer_stats->flags);
+
+	/* Firmware's rate control skips broadcast/management frames,
+	 * if host has configure fixed rates and in some other special cases.
+	 */
+	if (skip_auto_rate)
+		return;
 
 	if (txrate.flags == WMI_RATE_PREAMBLE_VHT && txrate.mcs > 9) {
 		ath10k_warn(ar, "Invalid VHT mcs %hhd peer stats",  txrate.mcs);
@@ -2975,7 +2984,7 @@ ath10k_update_per_peer_tx_stats(struct ath10k *ar,
 	}
 
 	memset(&arsta->txrate, 0, sizeof(arsta->txrate));
-
+	memset(&arsta->tx_info.status, 0, sizeof(arsta->tx_info.status));
 	if (txrate.flags == WMI_RATE_PREAMBLE_CCK ||
 	    txrate.flags == WMI_RATE_PREAMBLE_OFDM) {
 		rate = ATH10K_HW_LEGACY_RATE(peer_stats->ratecode);
@@ -2994,11 +3003,59 @@ ath10k_update_per_peer_tx_stats(struct ath10k *ar,
 		arsta->txrate.mcs = txrate.mcs;
 	}
 
-	if (sgi)
-		arsta->txrate.flags |= RATE_INFO_FLAGS_SHORT_GI;
+	switch (txrate.flags) {
+	case WMI_RATE_PREAMBLE_OFDM:
+		if (arsta->arvif && arsta->arvif->vif)
+			conf = rcu_dereference(arsta->arvif->vif->chanctx_conf);
+		if (conf && conf->def.chan->band == NL80211_BAND_5GHZ)
+			arsta->tx_info.status.rates[0].idx = rate_idx - 4;
+		break;
+	case WMI_RATE_PREAMBLE_CCK:
+		arsta->tx_info.status.rates[0].idx = rate_idx;
+		if (sgi)
+			arsta->tx_info.status.rates[0].flags |=
+				(IEEE80211_TX_RC_USE_SHORT_PREAMBLE |
+				 IEEE80211_TX_RC_SHORT_GI);
+		break;
+	case WMI_RATE_PREAMBLE_HT:
+		arsta->tx_info.status.rates[0].idx =
+				txrate.mcs + ((txrate.nss - 1) * 8);
+		if (sgi)
+			arsta->tx_info.status.rates[0].flags |=
+					IEEE80211_TX_RC_SHORT_GI;
+		arsta->tx_info.status.rates[0].flags |= IEEE80211_TX_RC_MCS;
+		break;
+	case WMI_RATE_PREAMBLE_VHT:
+		ieee80211_rate_set_vht(&arsta->tx_info.status.rates[0],
+				       txrate.mcs, txrate.nss);
+		if (sgi)
+			arsta->tx_info.status.rates[0].flags |=
+						IEEE80211_TX_RC_SHORT_GI;
+		arsta->tx_info.status.rates[0].flags |= IEEE80211_TX_RC_VHT_MCS;
+		break;
+	}
 
 	arsta->txrate.nss = txrate.nss;
 	arsta->txrate.bw = ath10k_bw_to_mac80211_bw(txrate.bw);
+	if (sgi)
+		arsta->txrate.flags |= RATE_INFO_FLAGS_SHORT_GI;
+
+	switch (arsta->txrate.bw) {
+	case RATE_INFO_BW_40:
+		arsta->tx_info.status.rates[0].flags |=
+				IEEE80211_TX_RC_40_MHZ_WIDTH;
+		break;
+	case RATE_INFO_BW_80:
+		arsta->tx_info.status.rates[0].flags |=
+				IEEE80211_TX_RC_80_MHZ_WIDTH;
+		break;
+	}
+
+	if (peer_stats->succ_pkts) {
+		arsta->tx_info.flags = IEEE80211_TX_STAT_ACK;
+		arsta->tx_info.status.rates[0].count = 1;
+		ieee80211_tx_rate_update(ar->hw, sta, &arsta->tx_info);
+	}
 
 	if (ath10k_debug_is_extd_tx_stats_enabled(ar))
 		ath10k_accumulate_per_peer_tx_stats(ar, arsta, peer_stats,
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index 58e33ab9e0e9..a8a88e81f403 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -4984,6 +4984,7 @@ enum wmi_rate_preamble {
 	(((preamble) << 6) | ((nss) << 4) | (rate))
 #define ATH10K_HW_AMPDU(flags)		((flags) & 0x1)
 #define ATH10K_HW_BA_FAIL(flags)	(((flags) >> 1) & 0x3)
+#define ATH10K_FW_SKIPPED_RATE_CTRL(flags)	(((flags) >> 6) & 0x1)
 
 #define ATH10K_VHT_MCS_NUM	10
 #define ATH10K_BW_NUM		4
-- 
cgit v1.2.3


From 68c295f21abc192163c416b333aca7c41a195075 Mon Sep 17 00:00:00 2001
From: Sathishkumar Muruganandam <murugana@codeaurora.org>
Date: Thu, 20 Dec 2018 09:53:30 +0200
Subject: ath10k: disable 4addr source port learning in 10.4 FW by default

Currently in 10.4 FW, all the received 4addr frames are processed for
source port learning which is enabled by default. This learning can't be
disabled by default in FW since it breaks backward compatibility.

Since ath10k uses mac80211 based 4addr mode, source port learning done in
10.4 FW is redundant and also causes issues when 3addr frames are
transmitted/received for a 4addr station.

One such visible functional impact is when GTK rekey frame from
hostapd based AP to 4addr STA is dropped in AP's 10.4 FW. This is since
GTK rekey EAPOL frame is 3addr frame on AP interface and STA enabled
with 4addr is already allowed for receiving 3addr EAPOL frames.

Source port learning implementation in 10.4 FW drops this 3addr GTK rekey
frame in AP destinated for 4addr STA causing disassociation and
re-association for every GTK rekey session. GTK rekey issue is not seen
when learning is disabled in FW.

To prevent such issues without breaking backward compatibility, FW
advertises new service bit making the source port learning configurable and
this learning is being currently disabled during ath10k vdev creation.

* Tested HW: QCA9984
* Tested FW: 10.4-3.6.0.1-00004

Signed-off-by: Sathishkumar Muruganandam <murugana@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c | 11 +++++++++++
 drivers/net/wireless/ath/ath10k/wmi.c |  4 ++++
 drivers/net/wireless/ath/ath10k/wmi.h | 21 ++++++++++++++++++++-
 3 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 3d539450f6c5..dc8968de012d 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -5154,6 +5154,17 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 		goto err;
 	}
 
+	if (test_bit(WMI_SERVICE_VDEV_DISABLE_4_ADDR_SRC_LRN_SUPPORT,
+		     ar->wmi.svc_map)) {
+		vdev_param = ar->wmi.vdev_param->disable_4addr_src_lrn;
+		ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id, vdev_param,
+						WMI_VDEV_DISABLE_4_ADDR_SRC_LRN);
+		if (ret && ret != -EOPNOTSUPP) {
+			ath10k_warn(ar, "failed to disable 4addr src lrn vdev %i: %d\n",
+				    arvif->vdev_id, ret);
+		}
+	}
+
 	ar->free_vdev_map &= ~(1LL << arvif->vdev_id);
 	spin_lock_bh(&ar->data_lock);
 	list_add(&arvif->list, &ar->arvifs);
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 659513bf4ddc..9b41cec6d887 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -825,6 +825,7 @@ static struct wmi_vdev_param_map wmi_vdev_param_map = {
 	.meru_vc = WMI_VDEV_PARAM_UNSUPPORTED,
 	.rx_decap_type = WMI_VDEV_PARAM_UNSUPPORTED,
 	.bw_nss_ratemask = WMI_VDEV_PARAM_UNSUPPORTED,
+	.disable_4addr_src_lrn = WMI_VDEV_PARAM_UNSUPPORTED,
 };
 
 /* 10.X WMI VDEV param map */
@@ -900,6 +901,7 @@ static struct wmi_vdev_param_map wmi_10x_vdev_param_map = {
 	.meru_vc = WMI_VDEV_PARAM_UNSUPPORTED,
 	.rx_decap_type = WMI_VDEV_PARAM_UNSUPPORTED,
 	.bw_nss_ratemask = WMI_VDEV_PARAM_UNSUPPORTED,
+	.disable_4addr_src_lrn = WMI_VDEV_PARAM_UNSUPPORTED,
 };
 
 static struct wmi_vdev_param_map wmi_10_2_4_vdev_param_map = {
@@ -974,6 +976,7 @@ static struct wmi_vdev_param_map wmi_10_2_4_vdev_param_map = {
 	.meru_vc = WMI_VDEV_PARAM_UNSUPPORTED,
 	.rx_decap_type = WMI_VDEV_PARAM_UNSUPPORTED,
 	.bw_nss_ratemask = WMI_VDEV_PARAM_UNSUPPORTED,
+	.disable_4addr_src_lrn = WMI_VDEV_PARAM_UNSUPPORTED,
 };
 
 static struct wmi_vdev_param_map wmi_10_4_vdev_param_map = {
@@ -1051,6 +1054,7 @@ static struct wmi_vdev_param_map wmi_10_4_vdev_param_map = {
 	.bw_nss_ratemask = WMI_10_4_VDEV_PARAM_BW_NSS_RATEMASK,
 	.inc_tsf = WMI_10_4_VDEV_PARAM_TSF_INCREMENT,
 	.dec_tsf = WMI_10_4_VDEV_PARAM_TSF_DECREMENT,
+	.disable_4addr_src_lrn = WMI_10_4_VDEV_PARAM_DISABLE_4_ADDR_SRC_LRN,
 };
 
 static struct wmi_pdev_param_map wmi_pdev_param_map = {
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index a8a88e81f403..69871e9a4b56 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -205,6 +205,7 @@ enum wmi_service {
 	WMI_SERVICE_SPOOF_MAC_SUPPORT,
 	WMI_SERVICE_TX_DATA_ACK_RSSI,
 	WMI_SERVICE_VDEV_DIFFERENT_BEACON_INTERVAL_SUPPORT,
+	WMI_SERVICE_VDEV_DISABLE_4_ADDR_SRC_LRN_SUPPORT,
 
 	/* keep last */
 	WMI_SERVICE_MAX,
@@ -359,6 +360,9 @@ enum wmi_10_4_service {
 	WMI_10_4_SERVICE_PEER_TID_CONFIGS_SUPPORT,
 	WMI_10_4_SERVICE_VDEV_BCN_RATE_CONTROL,
 	WMI_10_4_SERVICE_VDEV_DIFFERENT_BEACON_INTERVAL_SUPPORT,
+	WMI_10_4_SERVICE_HTT_ASSERT_TRIGGER_SUPPORT,
+	WMI_10_4_SERVICE_VDEV_FILTER_NEIGHBOR_RX_PACKETS,
+	WMI_10_4_SERVICE_VDEV_DISABLE_4_ADDR_SRC_LRN_SUPPORT,
 };
 
 static inline char *wmi_service_name(int service_id)
@@ -786,6 +790,8 @@ static inline void wmi_10_4_svc_map(const __le32 *in, unsigned long *out,
 	       WMI_SERVICE_TX_DATA_ACK_RSSI, len);
 	SVCMAP(WMI_10_4_SERVICE_VDEV_DIFFERENT_BEACON_INTERVAL_SUPPORT,
 	       WMI_SERVICE_VDEV_DIFFERENT_BEACON_INTERVAL_SUPPORT, len);
+	SVCMAP(WMI_10_4_SERVICE_VDEV_DISABLE_4_ADDR_SRC_LRN_SUPPORT,
+	       WMI_SERVICE_VDEV_DISABLE_4_ADDR_SRC_LRN_SUPPORT, len);
 }
 
 #undef SVCMAP
@@ -5066,6 +5072,7 @@ struct wmi_vdev_param_map {
 	u32 bw_nss_ratemask;
 	u32 inc_tsf;
 	u32 dec_tsf;
+	u32 disable_4addr_src_lrn;
 };
 
 #define WMI_VDEV_PARAM_UNSUPPORTED 0
@@ -5405,7 +5412,19 @@ enum wmi_10_4_vdev_param {
 	WMI_10_4_VDEV_PARAM_ATF_SSID_SCHED_POLICY,
 	WMI_10_4_VDEV_PARAM_DISABLE_DYN_BW_RTS,
 	WMI_10_4_VDEV_PARAM_TSF_DECREMENT,
-};
+	WMI_10_4_VDEV_PARAM_SELFGEN_FIXED_RATE,
+	WMI_10_4_VDEV_PARAM_AMPDU_SUBFRAME_SIZE_PER_AC,
+	WMI_10_4_VDEV_PARAM_NSS_VHT160,
+	WMI_10_4_VDEV_PARAM_NSS_VHT80_80,
+	WMI_10_4_VDEV_PARAM_AMSDU_SUBFRAME_SIZE_PER_AC,
+	WMI_10_4_VDEV_PARAM_DISABLE_CABQ,
+	WMI_10_4_VDEV_PARAM_SIFS_TRIGGER_RATE,
+	WMI_10_4_VDEV_PARAM_TX_POWER,
+	WMI_10_4_VDEV_PARAM_ENABLE_DISABLE_RTT_RESPONDER_ROLE,
+	WMI_10_4_VDEV_PARAM_DISABLE_4_ADDR_SRC_LRN,
+};
+
+#define WMI_VDEV_DISABLE_4_ADDR_SRC_LRN 1
 
 #define WMI_VDEV_PARAM_TXBF_SU_TX_BFEE BIT(0)
 #define WMI_VDEV_PARAM_TXBF_MU_TX_BFEE BIT(1)
-- 
cgit v1.2.3


From a2864772f33aa0f22914049b7fe777b7d4ec05ee Mon Sep 17 00:00:00 2001
From: Bhagavathi Perumal S <bperumal@codeaurora.org>
Date: Thu, 20 Dec 2018 09:53:34 +0200
Subject: ath10k: fix warning due to msdu limit error

Some hardwares variants (QCA99x0) are limiting msdu deaggregation with
some threshold value(default limit in QCA99x0 is 64 msdus), it was introduced to
avoid excessive MSDU-deaggregation in error cases. When number of sub frames
exceeds the limit, target hardware will send all msdus starting from present
msdu in RAW format as a single msdu packet and it will be indicated with
error status bit "RX_MSDU_END_INFO0_MSDU_LIMIT_ERR" set in rx descriptor.
This msdu frame is a partial raw MSDU and does't have first msdu and ieee80211
header. It caused below warning message.

[  320.151332] ------------[ cut here ]------------
[  320.155006] WARNING: CPU: 0 PID: 3 at drivers/net/wireless/ath/ath10k/htt_rx.c:1188

In our issue case, MSDU limit error happened due to FCS error and generated
this warning message.

This fixes the warning by handling the MSDU limit error. If msdu limit error
happens, driver adds first MSDU's ieee80211 header and sets A-MSDU present bit
in QOS header so that upper layer processes this frame if it is valid or drop it
if FCS error set. And removed the warning message, hence partial msdus without
first msdu is expected in msdu limit error cases.

Tested on QCA9984, Firmware 10.4-3.6-00104

Signed-off-by: Bhagavathi Perumal S <bperumal@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/htt_rx.c  | 41 ++++++++++++++++++++++++++++---
 drivers/net/wireless/ath/ath10k/hw.c      |  7 ++++++
 drivers/net/wireless/ath/ath10k/hw.h      | 10 ++++++++
 drivers/net/wireless/ath/ath10k/rx_desc.h |  7 ++++++
 4 files changed, 61 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index d44a7d8f7fc1..7bc1c9545e47 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -1343,7 +1343,8 @@ static void ath10k_htt_rx_h_undecap_raw(struct ath10k *ar,
 					struct sk_buff *msdu,
 					struct ieee80211_rx_status *status,
 					enum htt_rx_mpdu_encrypt_type enctype,
-					bool is_decrypted)
+					bool is_decrypted,
+					const u8 first_hdr[64])
 {
 	struct ieee80211_hdr *hdr;
 	struct htt_rx_desc *rxd;
@@ -1351,6 +1352,9 @@ static void ath10k_htt_rx_h_undecap_raw(struct ath10k *ar,
 	size_t crypto_len;
 	bool is_first;
 	bool is_last;
+	bool msdu_limit_err;
+	int bytes_aligned = ar->hw_params.decap_align_bytes;
+	u8 *qos;
 
 	rxd = (void *)msdu->data - sizeof(*rxd);
 	is_first = !!(rxd->msdu_end.common.info0 &
@@ -1368,16 +1372,45 @@ static void ath10k_htt_rx_h_undecap_raw(struct ath10k *ar,
 	 * [FCS] <-- at end, needs to be trimmed
 	 */
 
+	/* Some hardwares(QCA99x0 variants) limit number of msdus in a-msdu when
+	 * deaggregate, so that unwanted MSDU-deaggregation is avoided for
+	 * error packets. If limit exceeds, hw sends all remaining MSDUs as
+	 * a single last MSDU with this msdu limit error set.
+	 */
+	msdu_limit_err = ath10k_rx_desc_msdu_limit_error(&ar->hw_params, rxd);
+
+	/* If MSDU limit error happens, then don't warn on, the partial raw MSDU
+	 * without first MSDU is expected in that case, and handled later here.
+	 */
 	/* This probably shouldn't happen but warn just in case */
-	if (WARN_ON_ONCE(!is_first))
+	if (WARN_ON_ONCE(!is_first && !msdu_limit_err))
 		return;
 
 	/* This probably shouldn't happen but warn just in case */
-	if (WARN_ON_ONCE(!(is_first && is_last)))
+	if (WARN_ON_ONCE(!(is_first && is_last) && !msdu_limit_err))
 		return;
 
 	skb_trim(msdu, msdu->len - FCS_LEN);
 
+	/* Push original 80211 header */
+	if (unlikely(msdu_limit_err)) {
+		hdr = (struct ieee80211_hdr *)first_hdr;
+		hdr_len = ieee80211_hdrlen(hdr->frame_control);
+		crypto_len = ath10k_htt_rx_crypto_param_len(ar, enctype);
+
+		if (ieee80211_is_data_qos(hdr->frame_control)) {
+			qos = ieee80211_get_qos_ctl(hdr);
+			qos[0] |= IEEE80211_QOS_CTL_A_MSDU_PRESENT;
+		}
+
+		if (crypto_len)
+			memcpy(skb_push(msdu, crypto_len),
+			       (void *)hdr + round_up(hdr_len, bytes_aligned),
+			       crypto_len);
+
+		memcpy(skb_push(msdu, hdr_len), hdr, hdr_len);
+	}
+
 	/* In most cases this will be true for sniffed frames. It makes sense
 	 * to deliver them as-is without stripping the crypto param. This is
 	 * necessary for software based decryption.
@@ -1651,7 +1684,7 @@ static void ath10k_htt_rx_h_undecap(struct ath10k *ar,
 	switch (decap) {
 	case RX_MSDU_DECAP_RAW:
 		ath10k_htt_rx_h_undecap_raw(ar, msdu, status, enctype,
-					    is_decrypted);
+					    is_decrypted, first_hdr);
 		break;
 	case RX_MSDU_DECAP_NATIVE_WIFI:
 		ath10k_htt_rx_h_undecap_nwifi(ar, msdu, status, first_hdr,
diff --git a/drivers/net/wireless/ath/ath10k/hw.c b/drivers/net/wireless/ath/ath10k/hw.c
index af8ae8117c62..61ecf931ba4d 100644
--- a/drivers/net/wireless/ath/ath10k/hw.c
+++ b/drivers/net/wireless/ath/ath10k/hw.c
@@ -1119,8 +1119,15 @@ static int ath10k_qca99x0_rx_desc_get_l3_pad_bytes(struct htt_rx_desc *rxd)
 		  RX_MSDU_END_INFO1_L3_HDR_PAD);
 }
 
+static bool ath10k_qca99x0_rx_desc_msdu_limit_error(struct htt_rx_desc *rxd)
+{
+	return !!(rxd->msdu_end.common.info0 &
+		  __cpu_to_le32(RX_MSDU_END_INFO0_MSDU_LIMIT_ERR));
+}
+
 const struct ath10k_hw_ops qca99x0_ops = {
 	.rx_desc_get_l3_pad_bytes = ath10k_qca99x0_rx_desc_get_l3_pad_bytes,
+	.rx_desc_get_msdu_limit_error = ath10k_qca99x0_rx_desc_msdu_limit_error,
 };
 
 const struct ath10k_hw_ops qca6174_ops = {
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index 1b5da272d18c..e50a8dc5b093 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -624,6 +624,7 @@ struct ath10k_hw_ops {
 	int (*rx_desc_get_l3_pad_bytes)(struct htt_rx_desc *rxd);
 	void (*set_coverage_class)(struct ath10k *ar, s16 value);
 	int (*enable_pll_clk)(struct ath10k *ar);
+	bool (*rx_desc_get_msdu_limit_error)(struct htt_rx_desc *rxd);
 };
 
 extern const struct ath10k_hw_ops qca988x_ops;
@@ -642,6 +643,15 @@ ath10k_rx_desc_get_l3_pad_bytes(struct ath10k_hw_params *hw,
 	return 0;
 }
 
+static inline bool
+ath10k_rx_desc_msdu_limit_error(struct ath10k_hw_params *hw,
+				struct htt_rx_desc *rxd)
+{
+	if (hw->hw_ops->rx_desc_get_msdu_limit_error)
+		return hw->hw_ops->rx_desc_get_msdu_limit_error(rxd);
+	return false;
+}
+
 /* Target specific defines for MAIN firmware */
 #define TARGET_NUM_VDEVS			8
 #define TARGET_NUM_PEER_AST			2
diff --git a/drivers/net/wireless/ath/ath10k/rx_desc.h b/drivers/net/wireless/ath/ath10k/rx_desc.h
index 310674de3cb8..dfbfe674e11e 100644
--- a/drivers/net/wireless/ath/ath10k/rx_desc.h
+++ b/drivers/net/wireless/ath/ath10k/rx_desc.h
@@ -572,6 +572,7 @@ struct rx_msdu_start {
 #define RX_MSDU_END_INFO0_REPORTED_MPDU_LENGTH_LSB  0
 #define RX_MSDU_END_INFO0_FIRST_MSDU                BIT(14)
 #define RX_MSDU_END_INFO0_LAST_MSDU                 BIT(15)
+#define RX_MSDU_END_INFO0_MSDU_LIMIT_ERR            BIT(18)
 #define RX_MSDU_END_INFO0_PRE_DELIM_ERR             BIT(30)
 #define RX_MSDU_END_INFO0_RESERVED_3B               BIT(31)
 
@@ -676,6 +677,12 @@ struct rx_msdu_end {
  *		Indicates the last MSDU of the A-MSDU.  MPDU end status is
  *		only valid when last_msdu is set.
  *
+ *msdu_limit_error
+ *		Indicates that the MSDU threshold was exceeded and thus
+ *		all the rest of the MSDUs will not be scattered and
+ *		will not be decapsulated but will be received in RAW format
+ *		as a single MSDU buffer.
+ *
  *reserved_3a
  *		Reserved: HW should fill with zero.  FW should ignore.
  *
-- 
cgit v1.2.3


From 8765967592875f1b4b20a8541a325045e5f75a36 Mon Sep 17 00:00:00 2001
From: Govind Singh <govinds@codeaurora.org>
Date: Thu, 20 Dec 2018 09:53:36 +0200
Subject: ath10k: remove work in progress logs from snoc driver

All the necessary patches to make wifi running (over SNOC)
are merged and tested on SDM845/QCS404 platform with WCN3990
wifi module, hence remove work in progress debug from snoc
driver and Kconfig.

Signed-off-by: Govind Singh <govinds@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/Kconfig | 3 +--
 drivers/net/wireless/ath/ath10k/snoc.c  | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/Kconfig b/drivers/net/wireless/ath/ath10k/Kconfig
index e1ad6b9166a6..a7fb5441ced4 100644
--- a/drivers/net/wireless/ath/ath10k/Kconfig
+++ b/drivers/net/wireless/ath/ath10k/Kconfig
@@ -47,8 +47,7 @@ config ATH10K_SNOC
 	select QCOM_QMI_HELPERS
 	---help---
 	  This module adds support for integrated WCN3990 chip connected
-	  to system NOC(SNOC). Currently work in progress and will not
-	  fully work.
+	  to system NOC(SNOC).
 
 config ATH10K_DEBUG
 	bool "Atheros ath10k debugging"
diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index dad7e1ce79c0..54efe6be8f1d 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -1654,7 +1654,6 @@ static int ath10k_snoc_probe(struct platform_device *pdev)
 	}
 
 	ath10k_dbg(ar, ATH10K_DBG_SNOC, "snoc probe\n");
-	ath10k_warn(ar, "Warning: SNOC support is still work-in-progress, it will not work properly!");
 
 	return 0;
 
-- 
cgit v1.2.3


From c28dcbce0592a1a7e32975e28bdd80e5d8d2cfa3 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 20 Dec 2018 09:53:41 +0200
Subject: ath10k: fix a NULL vs IS_ERR() check

The devm_memremap() function doesn't return NULLs, it returns error
pointers.

Fixes: ba94c753ccb4 ("ath10k: add QMI message handshake for wcn3990 client")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/qmi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/qmi.c b/drivers/net/wireless/ath/ath10k/qmi.c
index f0429bee35c2..37b3bd629f48 100644
--- a/drivers/net/wireless/ath/ath10k/qmi.c
+++ b/drivers/net/wireless/ath/ath10k/qmi.c
@@ -931,9 +931,9 @@ static int ath10k_qmi_setup_msa_resources(struct ath10k_qmi *qmi, u32 msa_size)
 		qmi->msa_mem_size = resource_size(&r);
 		qmi->msa_va = devm_memremap(dev, qmi->msa_pa, qmi->msa_mem_size,
 					    MEMREMAP_WT);
-		if (!qmi->msa_va) {
+		if (IS_ERR(qmi->msa_va)) {
 			dev_err(dev, "failed to map memory region: %pa\n", &r.start);
-			return -EBUSY;
+			return PTR_ERR(qmi->msa_va);
 		}
 	} else {
 		qmi->msa_va = dmam_alloc_coherent(dev, msa_size,
-- 
cgit v1.2.3


From bd085be6ba9547795ddcbdc5cc0c78ea0201ba6e Mon Sep 17 00:00:00 2001
From: Govind Singh <govinds@codeaurora.org>
Date: Thu, 20 Dec 2018 09:53:43 +0200
Subject: ath10k: move non-fatal warn logs to dbg level

During driver load below warn logs are printed in the console.
Since driver may not implement all wmi events sent by fw and
all of them are non-fatal, move this log to debug level to
remove un-necessary warn message on console.

[  361.887230] ath10k_snoc a000000.wifi: Unknown eventid: 16393
[  361.907037] ath10k_snoc a000000.wifi: Unknown eventid: 237569

Signed-off-by: Govind Singh <govinds@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/wmi-tlv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index ad4114a88170..892bd8c30dd9 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -621,7 +621,7 @@ static void ath10k_wmi_tlv_op_rx(struct ath10k *ar, struct sk_buff *skb)
 		ath10k_wmi_event_mgmt_tx_compl(ar, skb);
 		break;
 	default:
-		ath10k_warn(ar, "Unknown eventid: %d\n", id);
+		ath10k_dbg(ar, ATH10K_DBG_WMI, "Unknown eventid: %d\n", id);
 		break;
 	}
 
-- 
cgit v1.2.3


From 27120f2ac995d83fef383fb20e492037ecf09259 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 20 Dec 2018 09:53:45 +0200
Subject: ath10k: remove an unnecessary NULL check

The "survey" pointer is the address of an array element.  We know that
it can't be NULL so this check can be removed.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/wmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 9b41cec6d887..3d59d7d73f4b 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -2582,7 +2582,7 @@ static void ath10k_wmi_event_chan_info_unpaired(struct ath10k *ar,
 
 	survey = &ar->survey[idx];
 
-	if (!params->mac_clk_mhz || !survey)
+	if (!params->mac_clk_mhz)
 		return;
 
 	memset(survey, 0, sizeof(*survey));
-- 
cgit v1.2.3


From 5fac78aac91d89b4a04c1cbd92254f62935c2711 Mon Sep 17 00:00:00 2001
From: Govind Singh <govinds@codeaurora.org>
Date: Thu, 20 Dec 2018 14:24:10 +0200
Subject: dt: bindings: ath10k: add missing dt properties for WCN3990 wifi node

Add missing optional properties in WCN3990 wifi node.

Signed-off-by: Govind Singh <govinds@codeaurora.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Brian Norris <briannorris@chromium.org>
Tested-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../bindings/net/wireless/qcom,ath10k.txt          | 57 +++++++++++++---------
 1 file changed, 35 insertions(+), 22 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
index 2196d1ab3c8c..51fcf93d743b 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
@@ -21,10 +21,22 @@ can be provided per device.
 
 SNOC based devices (i.e. wcn3990) uses compatible string "qcom,wcn3990-wifi".
 
-Optional properties:
 - reg: Address and length of the register set for the device.
 - reg-names: Must include the list of following reg names,
 	     "membase"
+- interrupts: reference to the list of 17 interrupt numbers for "qcom,ipq4019-wifi"
+	      compatible target.
+	      reference to the list of 12 interrupt numbers for "qcom,wcn3990-wifi"
+	      compatible target.
+	      Must contain interrupt-names property per entry for
+	      "qcom,ath10k", "qcom,ipq4019-wifi" compatible targets.
+
+- interrupt-names: Must include the entries for MSI interrupt
+		   names ("msi0" to "msi15") and legacy interrupt
+		   name ("legacy") for "qcom,ath10k", "qcom,ipq4019-wifi"
+		   compatible targets.
+
+Optional properties:
 - resets: Must contain an entry for each entry in reset-names.
           See ../reset/reseti.txt for details.
 - reset-names: Must include the list of following reset names,
@@ -37,12 +49,9 @@ Optional properties:
 - clocks: List of clock specifiers, must contain an entry for each required
           entry in clock-names.
 - clock-names: Should contain the clock names "wifi_wcss_cmd", "wifi_wcss_ref",
-               "wifi_wcss_rtc".
-- interrupts: List of interrupt lines. Must contain an entry
-	      for each entry in the interrupt-names property.
-- interrupt-names: Must include the entries for MSI interrupt
-		   names ("msi0" to "msi15") and legacy interrupt
-		   name ("legacy"),
+	       "wifi_wcss_rtc" for "qcom,ipq4019-wifi" compatible target and
+	       "cxo_ref_clk_pin" for "qcom,wcn3990-wifi"
+	       compatible target.
 - qcom,msi_addr: MSI interrupt address.
 - qcom,msi_base: Base value to add before writing MSI data into
 		MSI address register.
@@ -55,7 +64,8 @@ Optional properties:
 - qcom,ath10k-pre-calibration-data : pre calibration data as an array,
 				     the length can vary between hw versions.
 - <supply-name>-supply: handle to the regulator device tree node
-			   optional "supply-name" is "vdd-0.8-cx-mx".
+			   optional "supply-name" are "vdd-0.8-cx-mx",
+			   "vdd-1.8-xo", "vdd-1.3-rfa" and "vdd-3.3-ch0".
 - memory-region:
 	Usage: optional
 	Value type: <phandle>
@@ -138,21 +148,24 @@ wifi@18000000 {
 		compatible = "qcom,wcn3990-wifi";
 		reg = <0x18800000 0x800000>;
 		reg-names = "membase";
-		clocks = <&clock_gcc clk_aggre2_noc_clk>;
-		clock-names = "smmu_aggre2_noc_clk"
+		clocks = <&clock_gcc clk_rf_clk2_pin>;
+		clock-names = "cxo_ref_clk_pin";
 		interrupts =
-			   <0 130 0 /* CE0 */ >,
-			   <0 131 0 /* CE1 */ >,
-			   <0 132 0 /* CE2 */ >,
-			   <0 133 0 /* CE3 */ >,
-			   <0 134 0 /* CE4 */ >,
-			   <0 135 0 /* CE5 */ >,
-			   <0 136 0 /* CE6 */ >,
-			   <0 137 0 /* CE7 */ >,
-			   <0 138 0 /* CE8 */ >,
-			   <0 139 0 /* CE9 */ >,
-			   <0 140 0 /* CE10 */ >,
-			   <0 141 0 /* CE11 */ >;
+			<GIC_SPI 414 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 415 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 416 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 417 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 418 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 419 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 420 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 423 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 425 IRQ_TYPE_LEVEL_HIGH>;
 		vdd-0.8-cx-mx-supply = <&pm8998_l5>;
+		vdd-1.8-xo-supply = <&vreg_l7a_1p8>;
+		vdd-1.3-rfa-supply = <&vreg_l17a_1p3>;
+		vdd-3.3-ch0-supply = <&vreg_l25a_3p3>;
 		memory-region = <&wifi_msa_mem>;
 };
-- 
cgit v1.2.3


From a3542d0c73cec6a45bde512ea2b43666c05a8c54 Mon Sep 17 00:00:00 2001
From: Govind Singh <govinds@codeaurora.org>
Date: Thu, 20 Dec 2018 14:24:23 +0200
Subject: dt: bindings: ath10k: add bindings for wifi iommu node

WCN3990 wifi module can optionally make use of the IOMMU.
Add binding documentation for phandle to the IOMMU and
the stream id of wifi iommu block.

Signed-off-by: Govind Singh <govinds@codeaurora.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Brian Norris <briannorris@chromium.org>
Tested-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
index 51fcf93d743b..09ae59470f64 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
@@ -71,6 +71,10 @@ Optional properties:
 	Value type: <phandle>
 	Definition: reference to the reserved-memory for the msa region
 		    used by the wifi firmware running in Q6.
+- iommus:
+	Usage: optional
+	Value type: <prop-encoded-array>
+	Definition: A list of phandle and IOMMU specifier pairs.
 
 Example (to supply the calibration data alone):
 
@@ -168,4 +172,5 @@ wifi@18000000 {
 		vdd-1.3-rfa-supply = <&vreg_l17a_1p3>;
 		vdd-3.3-ch0-supply = <&vreg_l25a_3p3>;
 		memory-region = <&wifi_msa_mem>;
+		iommus = <&apps_smmu 0x0040 0x1>;
 };
-- 
cgit v1.2.3


From 2d3b55853b123c177037cf534c5aaa2650310094 Mon Sep 17 00:00:00 2001
From: Zhi Chen <zhichen@codeaurora.org>
Date: Thu, 20 Dec 2018 14:24:43 +0200
Subject: ath10k: fix peer stats null pointer dereference

There was a race condition in SMP that an ath10k_peer was created but its
member sta was null. Following are procedures of ath10k_peer creation and
member sta access in peer statistics path.

    1. Peer creation:
        ath10k_peer_create()
            =>ath10k_wmi_peer_create()
                =>ath10k_wait_for_peer_created()
                ...

        # another kernel path, RX from firmware
        ath10k_htt_t2h_msg_handler()
        =>ath10k_peer_map_event()
                =>wake_up()
                # ar->peer_map[id] = peer //add peer to map

        #wake up original path from waiting
                ...
                # peer->sta = sta //sta assignment

    2.  RX path of statistics
        ath10k_htt_t2h_msg_handler()
            =>ath10k_update_per_peer_tx_stats()
                =>ath10k_htt_fetch_peer_stats()
                # peer->sta //sta accessing

Any access of peer->sta after peer was added to peer_map but before sta was
assigned could cause a null pointer issue. And because these two steps are
asynchronous, no proper lock can protect them. So both peer and sta need to
be checked before access.

Tested: QCA9984 with firmware ver 10.4-3.9.0.1-00005
Signed-off-by: Zhi Chen <zhichen@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/debugfs_sta.c | 2 +-
 drivers/net/wireless/ath/ath10k/htt_rx.c      | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/debugfs_sta.c b/drivers/net/wireless/ath/ath10k/debugfs_sta.c
index 0f3fd65a459e..4778a455d81a 100644
--- a/drivers/net/wireless/ath/ath10k/debugfs_sta.c
+++ b/drivers/net/wireless/ath/ath10k/debugfs_sta.c
@@ -71,7 +71,7 @@ void ath10k_sta_update_rx_tid_stats_ampdu(struct ath10k *ar, u16 peer_id, u8 tid
 	spin_lock_bh(&ar->data_lock);
 
 	peer = ath10k_peer_find_by_id(ar, peer_id);
-	if (!peer)
+	if (!peer || !peer->sta)
 		goto out;
 
 	arsta = (struct ath10k_sta *)peer->sta->drv_priv;
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index 7bc1c9545e47..f42bac204ef8 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -3121,7 +3121,7 @@ static void ath10k_htt_fetch_peer_stats(struct ath10k *ar,
 	rcu_read_lock();
 	spin_lock_bh(&ar->data_lock);
 	peer = ath10k_peer_find_by_id(ar, peer_id);
-	if (!peer) {
+	if (!peer || !peer->sta) {
 		ath10k_warn(ar, "Invalid peer id %d peer stats buffer\n",
 			    peer_id);
 		goto out;
@@ -3174,7 +3174,7 @@ static void ath10k_fetch_10_2_tx_stats(struct ath10k *ar, u8 *data)
 	rcu_read_lock();
 	spin_lock_bh(&ar->data_lock);
 	peer = ath10k_peer_find_by_id(ar, peer_id);
-	if (!peer) {
+	if (!peer || !peer->sta) {
 		ath10k_warn(ar, "Invalid peer id %d in peer stats buffer\n",
 			    peer_id);
 		goto out;
-- 
cgit v1.2.3


From 386f97e3b201d18578abb0e7037b85a1ae50c0a3 Mon Sep 17 00:00:00 2001
From: Zhi Chen <zhichen@codeaurora.org>
Date: Thu, 20 Dec 2018 14:25:18 +0200
Subject: ath10k: fix tx_stats memory leak

Memory of tx_stats was allocated when a STA was added. But it's not freed
if the STA failed to be added to driver. This issue could be seen in MDK3
attack case when STA number reached the limit.

Tested: QCA9984 with firmware ver 10.4-3.9.0.1-00005
Signed-off-by: Zhi Chen <zhichen@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index dc8968de012d..43398e06454f 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -6279,15 +6279,6 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 			   ar->num_stations + 1, ar->max_num_stations,
 			   ar->num_peers + 1, ar->max_num_peers);
 
-		if (ath10k_debug_is_extd_tx_stats_enabled(ar)) {
-			arsta->tx_stats = kzalloc(sizeof(*arsta->tx_stats),
-						  GFP_KERNEL);
-			if (!arsta->tx_stats) {
-				ret = -ENOMEM;
-				goto exit;
-			}
-		}
-
 		num_tdls_stations = ath10k_mac_tdls_vif_stations_count(hw, vif);
 
 		if (sta->tdls) {
@@ -6308,12 +6299,22 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 			goto exit;
 		}
 
+		if (ath10k_debug_is_extd_tx_stats_enabled(ar)) {
+			arsta->tx_stats = kzalloc(sizeof(*arsta->tx_stats),
+						  GFP_KERNEL);
+			if (!arsta->tx_stats) {
+				ret = -ENOMEM;
+				goto exit;
+			}
+		}
+
 		ret = ath10k_peer_create(ar, vif, sta, arvif->vdev_id,
 					 sta->addr, peer_type);
 		if (ret) {
 			ath10k_warn(ar, "failed to add peer %pM for vdev %d when adding a new sta: %i\n",
 				    sta->addr, arvif->vdev_id, ret);
 			ath10k_mac_dec_num_stations(arvif, sta);
+			kfree(arsta->tx_stats);
 			goto exit;
 		}
 
@@ -6326,6 +6327,7 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 			spin_unlock_bh(&ar->data_lock);
 			ath10k_peer_delete(ar, arvif->vdev_id, sta->addr);
 			ath10k_mac_dec_num_stations(arvif, sta);
+			kfree(arsta->tx_stats);
 			ret = -ENOENT;
 			goto exit;
 		}
@@ -6346,6 +6348,7 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 			ath10k_peer_delete(ar, arvif->vdev_id,
 					   sta->addr);
 			ath10k_mac_dec_num_stations(arvif, sta);
+			kfree(arsta->tx_stats);
 			goto exit;
 		}
 
@@ -6357,6 +6360,7 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 				    sta->addr, arvif->vdev_id, ret);
 			ath10k_peer_delete(ar, arvif->vdev_id, sta->addr);
 			ath10k_mac_dec_num_stations(arvif, sta);
+			kfree(arsta->tx_stats);
 
 			if (num_tdls_stations != 0)
 				goto exit;
-- 
cgit v1.2.3


From e5404969a335e25e3eb822649a7f40e9c5ba2446 Mon Sep 17 00:00:00 2001
From: Bhagavathi Perumal S <bperumal@codeaurora.org>
Date: Thu, 20 Dec 2018 14:25:32 +0200
Subject: dt-bindings: net: ath10k: fix node name and device type in qcom
 ath10k example

In qcom,ath10k documentation, ath10k is used as node name in the example of
pci based device. Normally, node name should be class of device and not the
model name, so fix it to node name "wifi". And remove the property device_type
pci since only pci bridges should have this property.

Signed-off-by: Bhagavathi Perumal S <bperumal@codeaurora.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
index 09ae59470f64..bd6b276d078e 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
@@ -88,9 +88,8 @@ pci {
 		#address-cells = <3>;
 		device_type = "pci";
 
-		ath10k@0,0 {
+		wifi@0,0 {
 			reg = <0 0 0 0 0>;
-			device_type = "pci";
 			qcom,ath10k-calibration-data = [ 01 02 03 ... ];
 		};
 	};
-- 
cgit v1.2.3


From f3f587995c5af69b92693c2f5d40e3448ab6113d Mon Sep 17 00:00:00 2001
From: Bhagavathi Perumal S <bperumal@codeaurora.org>
Date: Thu, 20 Dec 2018 14:25:43 +0200
Subject: dt-bindings: net: ath10k: add new dt entry to identify external FEM

This adds new dt entry ext-fem-name, it is used by ath10k driver
to select correct timing parameters and configure it in target wifi hardware.
The Front End Module(FEM) normally includes tx power amplifier(PA) and
rx low noise amplifier(LNA). The default timing parameters like tx end to
PA off timing values were fine tuned for internal FEM used in reference
design. And these timing values can not be same if ODM modifies hardware
design with different external FEM. This DT entry helps to choose correct
timing values in driver if different external FEM hardware used.

Signed-off-by: Bhagavathi Perumal S <bperumal@codeaurora.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
index bd6b276d078e..ae661e65354e 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt
@@ -75,8 +75,14 @@ Optional properties:
 	Usage: optional
 	Value type: <prop-encoded-array>
 	Definition: A list of phandle and IOMMU specifier pairs.
+- ext-fem-name:
+	Usage: Optional
+	Value type: string
+	Definition: Name of external front end module used. Some valid FEM names
+		    for example: "microsemi-lx5586", "sky85703-11"
+		    and "sky85803" etc.
 
-Example (to supply the calibration data alone):
+Example (to supply PCI based wifi block details):
 
 In this example, the node is defined as child node of the PCI controller.
 
@@ -91,6 +97,7 @@ pci {
 		wifi@0,0 {
 			reg = <0 0 0 0 0>;
 			qcom,ath10k-calibration-data = [ 01 02 03 ... ];
+			ext-fem-name = "microsemi-lx5586";
 		};
 	};
 };
-- 
cgit v1.2.3


From 84758d4d43e9e38f2bf9b5130b5f7db1c44f1e0b Mon Sep 17 00:00:00 2001
From: Bhagavathi Perumal S <bperumal@codeaurora.org>
Date: Thu, 20 Dec 2018 14:26:00 +0200
Subject: ath10k: add support to configure BB timing over wmi

Add wmi configuration cmd to configure base band(BB) power amplifier(PA)
off timing values in hardware. The default PA off timings were fine tuned
to make proper DFS radar detection in QCA reference design. If ODM uses
different PA in their design, then the same default PA off timing values
cannot be used, it requires different settling time to detect radar pulses
very sooner and avoid radar detection problems. In that case it provides
provision to select proper PA off timing values based on the PA hardware used.
The PA component is part of FEM hardware and new device tree entry
"ext-fem-name" is used to indentify the FEM hardware. And this wmi configuration
cmd is enabled via wmi service flag "WMI_SERVICE_BB_TIMING_CONFIG_SUPPORT".

Other way is to apply these values through calibration data, but recalibration
of all boards out there might not be feasible.

This change tested on firmware ver 10.2.4-1.0-00042 in QCA988X chipset.

Signed-off-by: Bhagavathi Perumal S <bperumal@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c     | 47 +++++++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath10k/wmi-ops.h | 20 +++++++++++++
 drivers/net/wireless/ath/ath10k/wmi.c     | 23 +++++++++++++++
 drivers/net/wireless/ath/ath10k/wmi.h     | 26 +++++++++++++++++
 4 files changed, 116 insertions(+)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 43398e06454f..e49b36752ba2 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -22,6 +22,7 @@
 #include <net/mac80211.h>
 #include <linux/etherdevice.h>
 #include <linux/acpi.h>
+#include <linux/of.h>
 
 #include "hif.h"
 #include "core.h"
@@ -4637,11 +4638,44 @@ static int ath10k_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 	return ret;
 }
 
+static int __ath10k_fetch_bb_timing_dt(struct ath10k *ar,
+				       struct wmi_bb_timing_cfg_arg *bb_timing)
+{
+	struct device_node *node;
+	const char *fem_name;
+	int ret;
+
+	node = ar->dev->of_node;
+	if (!node)
+		return -ENOENT;
+
+	ret = of_property_read_string_index(node, "ext-fem-name", 0, &fem_name);
+	if (ret)
+		return -ENOENT;
+
+	/*
+	 * If external Front End module used in hardware, then default base band timing
+	 * parameter cannot be used since they were fine tuned for reference hardware,
+	 * so choosing different value suitable for that external FEM.
+	 */
+	if (!strcmp("microsemi-lx5586", fem_name)) {
+		bb_timing->bb_tx_timing = 0x00;
+		bb_timing->bb_xpa_timing = 0x0101;
+	} else {
+		return -ENOENT;
+	}
+
+	ath10k_dbg(ar, ATH10K_DBG_BOOT, "boot bb_tx_timing 0x%x bb_xpa_timing 0x%x\n",
+		   bb_timing->bb_tx_timing, bb_timing->bb_xpa_timing);
+	return 0;
+}
+
 static int ath10k_start(struct ieee80211_hw *hw)
 {
 	struct ath10k *ar = hw->priv;
 	u32 param;
 	int ret = 0;
+	struct wmi_bb_timing_cfg_arg bb_timing = {0};
 
 	/*
 	 * This makes sense only when restarting hw. It is harmless to call
@@ -4796,6 +4830,19 @@ static int ath10k_start(struct ieee80211_hw *hw)
 		clear_bit(ATH10K_FLAG_BTCOEX, &ar->dev_flags);
 	}
 
+	if (test_bit(WMI_SERVICE_BB_TIMING_CONFIG_SUPPORT, ar->wmi.svc_map)) {
+		ret = __ath10k_fetch_bb_timing_dt(ar, &bb_timing);
+		if (!ret) {
+			ret = ath10k_wmi_pdev_bb_timing(ar, &bb_timing);
+			if (ret) {
+				ath10k_warn(ar,
+					    "failed to set bb timings: %d\n",
+					    ret);
+				goto err_core_stop;
+			}
+		}
+	}
+
 	ar->num_started_vdevs = 0;
 	ath10k_regd_update(ar);
 
diff --git a/drivers/net/wireless/ath/ath10k/wmi-ops.h b/drivers/net/wireless/ath/ath10k/wmi-ops.h
index 7978a7783f90..04663076d27a 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-ops.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-ops.h
@@ -219,6 +219,9 @@ struct wmi_ops {
 	struct sk_buff *(*gen_echo)(struct ath10k *ar, u32 value);
 	struct sk_buff *(*gen_pdev_get_tpc_table_cmdid)(struct ath10k *ar,
 							u32 param);
+	struct sk_buff *(*gen_bb_timing)
+			(struct ath10k *ar,
+			 const struct wmi_bb_timing_cfg_arg *arg);
 
 };
 
@@ -1576,4 +1579,21 @@ ath10k_wmi_report_radar_found(struct ath10k *ar,
 				   ar->wmi.cmd->radar_found_cmdid);
 }
 
+static inline int
+ath10k_wmi_pdev_bb_timing(struct ath10k *ar,
+			  const struct wmi_bb_timing_cfg_arg *arg)
+{
+	struct sk_buff *skb;
+
+	if (!ar->wmi.ops->gen_bb_timing)
+		return -EOPNOTSUPP;
+
+	skb = ar->wmi.ops->gen_bb_timing(ar, arg);
+
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	return ath10k_wmi_cmd_send(ar, skb,
+				   ar->wmi.cmd->set_bb_timing_cmdid);
+}
 #endif
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 3d59d7d73f4b..ba837403e266 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -539,6 +539,7 @@ static struct wmi_cmd_map wmi_10_2_4_cmd_map = {
 		WMI_10_2_PDEV_BSS_CHAN_INFO_REQUEST_CMDID,
 	.pdev_get_tpc_table_cmdid = WMI_CMD_UNSUPPORTED,
 	.radar_found_cmdid = WMI_CMD_UNSUPPORTED,
+	.set_bb_timing_cmdid = WMI_10_2_PDEV_SET_BB_TIMING_CONFIG_CMDID,
 };
 
 /* 10.4 WMI cmd track */
@@ -8843,6 +8844,27 @@ ath10k_wmi_barrier(struct ath10k *ar)
 	return 0;
 }
 
+static struct sk_buff *
+ath10k_wmi_10_2_4_op_gen_bb_timing(struct ath10k *ar,
+				   const struct wmi_bb_timing_cfg_arg *arg)
+{
+	struct wmi_pdev_bb_timing_cfg_cmd *cmd;
+	struct sk_buff *skb;
+
+	skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd));
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	cmd = (struct wmi_pdev_bb_timing_cfg_cmd *)skb->data;
+	cmd->bb_tx_timing = __cpu_to_le32(arg->bb_tx_timing);
+	cmd->bb_xpa_timing = __cpu_to_le32(arg->bb_xpa_timing);
+
+	ath10k_dbg(ar, ATH10K_DBG_WMI,
+		   "wmi pdev bb_tx_timing 0x%x bb_xpa_timing 0x%x\n",
+		   arg->bb_tx_timing, arg->bb_xpa_timing);
+	return skb;
+}
+
 static const struct wmi_ops wmi_ops = {
 	.rx = ath10k_wmi_op_rx,
 	.map_svc = wmi_main_svc_map,
@@ -9116,6 +9138,7 @@ static const struct wmi_ops wmi_10_2_4_ops = {
 	.gen_pdev_enable_adaptive_cca =
 		ath10k_wmi_op_gen_pdev_enable_adaptive_cca,
 	.get_vdev_subtype = ath10k_wmi_10_2_4_op_get_vdev_subtype,
+	.gen_bb_timing = ath10k_wmi_10_2_4_op_gen_bb_timing,
 	/* .gen_bcn_tmpl not implemented */
 	/* .gen_prb_tmpl not implemented */
 	/* .gen_p2p_go_bcn_ie not implemented */
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index 69871e9a4b56..88210ddaedc4 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -206,6 +206,7 @@ enum wmi_service {
 	WMI_SERVICE_TX_DATA_ACK_RSSI,
 	WMI_SERVICE_VDEV_DIFFERENT_BEACON_INTERVAL_SUPPORT,
 	WMI_SERVICE_VDEV_DISABLE_4_ADDR_SRC_LRN_SUPPORT,
+	WMI_SERVICE_BB_TIMING_CONFIG_SUPPORT,
 
 	/* keep last */
 	WMI_SERVICE_MAX,
@@ -245,6 +246,9 @@ enum wmi_10x_service {
 	WMI_10X_SERVICE_PEER_STATS,
 	WMI_10X_SERVICE_RESET_CHIP,
 	WMI_10X_SERVICE_HTT_MGMT_TX_COMP_VALID_FLAGS,
+	WMI_10X_SERVICE_VDEV_BCN_RATE_CONTROL,
+	WMI_10X_SERVICE_PER_PACKET_SW_ENCRYPT,
+	WMI_10X_SERVICE_BB_TIMING_CONFIG_SUPPORT,
 };
 
 enum wmi_main_service {
@@ -572,6 +576,8 @@ static inline void wmi_10x_svc_map(const __le32 *in, unsigned long *out,
 	       WMI_SERVICE_RESET_CHIP, len);
 	SVCMAP(WMI_10X_SERVICE_HTT_MGMT_TX_COMP_VALID_FLAGS,
 	       WMI_SERVICE_HTT_MGMT_TX_COMP_VALID_FLAGS, len);
+	SVCMAP(WMI_10X_SERVICE_BB_TIMING_CONFIG_SUPPORT,
+	       WMI_SERVICE_BB_TIMING_CONFIG_SUPPORT, len);
 }
 
 static inline void wmi_main_svc_map(const __le32 *in, unsigned long *out,
@@ -992,6 +998,7 @@ struct wmi_cmd_map {
 	u32 pdev_wds_entry_list_cmdid;
 	u32 tdls_set_offchan_mode_cmdid;
 	u32 radar_found_cmdid;
+	u32 set_bb_timing_cmdid;
 };
 
 /*
@@ -1607,6 +1614,8 @@ enum wmi_10_2_cmd_id {
 	WMI_10_2_SET_LTEU_CONFIG_CMDID,
 	WMI_10_2_SET_CCA_PARAMS,
 	WMI_10_2_PDEV_BSS_CHAN_INFO_REQUEST_CMDID,
+	WMI_10_2_FWTEST_CMDID,
+	WMI_10_2_PDEV_SET_BB_TIMING_CONFIG_CMDID,
 	WMI_10_2_PDEV_UTF_CMDID = WMI_10_2_END_CMDID - 1,
 };
 
@@ -7173,6 +7182,23 @@ struct wmi_pdev_chan_info_req_cmd {
 	__le32 reserved;
 } __packed;
 
+/* bb timing register configurations */
+struct wmi_bb_timing_cfg_arg {
+	/* Tx_end to pa off timing */
+	u32 bb_tx_timing;
+
+	/* Tx_end to external pa off timing */
+	u32 bb_xpa_timing;
+};
+
+struct wmi_pdev_bb_timing_cfg_cmd {
+	/* Tx_end to pa off timing */
+	__le32 bb_tx_timing;
+
+	/* Tx_end to external pa off timing */
+	__le32 bb_xpa_timing;
+} __packed;
+
 struct ath10k;
 struct ath10k_vif;
 struct ath10k_fw_stats_pdev;
-- 
cgit v1.2.3


From 59361316afcb08569af21e1af83e89c7051c055a Mon Sep 17 00:00:00 2001
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Thu, 2 Aug 2018 10:13:10 -0700
Subject: igb: reduce CPU0 latency when updating statistics

This change is based off of the work and suggestion of Jan Jablonsky
<jan.jablonsky@thalesgroup.com>.

The Watchdog workqueue in igb driver is scheduled every 2s for each
network interface. That includes updating a statistics protected by
spinlock. Function igb_update_stats in this case will be protected
against preemption. According to number of a statistics registers
(cca 60), processing this function might cause additional cpu load
 on CPU0.

In case of statistics spinlock may be replaced with mutex, which
reduce latency on CPU0.

CC: Bernhard Kaindl  <bernhard.kaindl@thalesgroup.com>
CC: Jan Jablonsky <jan.jablonsky@thalesgroup.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igb/igb.h         |  2 +-
 drivers/net/ethernet/intel/igb/igb_ethtool.c |  4 ++--
 drivers/net/ethernet/intel/igb/igb_main.c    | 14 +++++++-------
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index ca54e268d157..fe1592ae8769 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -515,7 +515,7 @@ struct igb_adapter {
 	/* OS defined structs */
 	struct pci_dev *pdev;
 
-	spinlock_t stats64_lock;
+	struct mutex stats64_lock;
 	struct rtnl_link_stats64 stats64;
 
 	/* structs defined in e1000_hw.h */
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index c57671068245..7426060b678f 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -2295,7 +2295,7 @@ static void igb_get_ethtool_stats(struct net_device *netdev,
 	int i, j;
 	char *p;
 
-	spin_lock(&adapter->stats64_lock);
+	mutex_lock(&adapter->stats64_lock);
 	igb_update_stats(adapter);
 
 	for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++) {
@@ -2338,7 +2338,7 @@ static void igb_get_ethtool_stats(struct net_device *netdev,
 		} while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start));
 		i += IGB_RX_QUEUE_STATS_LEN;
 	}
-	spin_unlock(&adapter->stats64_lock);
+	mutex_unlock(&adapter->stats64_lock);
 }
 
 static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 453ae1d9e5f3..bb4f3f64fbf0 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2203,9 +2203,9 @@ void igb_down(struct igb_adapter *adapter)
 	del_timer_sync(&adapter->phy_info_timer);
 
 	/* record the stats before reset*/
-	spin_lock(&adapter->stats64_lock);
+	mutex_lock(&adapter->stats64_lock);
 	igb_update_stats(adapter);
-	spin_unlock(&adapter->stats64_lock);
+	mutex_unlock(&adapter->stats64_lock);
 
 	adapter->link_speed = 0;
 	adapter->link_duplex = 0;
@@ -3840,7 +3840,7 @@ static int igb_sw_init(struct igb_adapter *adapter)
 	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
 
 	spin_lock_init(&adapter->nfc_lock);
-	spin_lock_init(&adapter->stats64_lock);
+	mutex_init(&adapter->stats64_lock);
 #ifdef CONFIG_PCI_IOV
 	switch (hw->mac.type) {
 	case e1000_82576:
@@ -5406,9 +5406,9 @@ no_wait:
 		}
 	}
 
-	spin_lock(&adapter->stats64_lock);
+	mutex_lock(&adapter->stats64_lock);
 	igb_update_stats(adapter);
-	spin_unlock(&adapter->stats64_lock);
+	mutex_unlock(&adapter->stats64_lock);
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		struct igb_ring *tx_ring = adapter->tx_ring[i];
@@ -6235,10 +6235,10 @@ static void igb_get_stats64(struct net_device *netdev,
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 
-	spin_lock(&adapter->stats64_lock);
+	mutex_lock(&adapter->stats64_lock);
 	igb_update_stats(adapter);
 	memcpy(stats, &adapter->stats64, sizeof(*stats));
-	spin_unlock(&adapter->stats64_lock);
+	mutex_unlock(&adapter->stats64_lock);
 }
 
 /**
-- 
cgit v1.2.3


From 6f9ae17530f996e90268dae5ee843e432e40ccb3 Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Fri, 16 Nov 2018 16:19:23 -0800
Subject: igb: Change RXPBSIZE size when setting Qav mode

Section 4.5.9 of the datasheet says that the total size of all packet
buffers combined (TxPB 0 + 1 + 2 + 3 + RxPB + BMC2OS + OS2BMC) must not
exceed 60KB. Today we are configuring a total of 62KB, so reduce the
RxPB from 32KB to 30KB in order to respect that.

The choice of changing RxPBSIZE here is mainly because it seems more
correct to give more priority to the transmit packet buffers over the
receiver ones when running in Qav mode. Also, the BMC2OS and OS2BMC
sizes are already too short.

Signed-off-by: Jesus Sanchez-Palencia <jesus.s.palencia@gmail.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igb/e1000_defines.h | 1 +
 drivers/net/ethernet/intel/igb/igb_main.c      | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 8a28f3388f69..01fcfc6f3415 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -334,6 +334,7 @@
 
 #define I210_RXPBSIZE_DEFAULT		0x000000A2 /* RXPBSIZE default */
 #define I210_RXPBSIZE_MASK		0x0000003F
+#define I210_RXPBSIZE_PB_30KB		0x0000001E
 #define I210_RXPBSIZE_PB_32KB		0x00000020
 #define I210_TXPBSIZE_DEFAULT		0x04000014 /* TXPBSIZE default */
 #define I210_TXPBSIZE_MASK		0xC0FFFFFF
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index bb4f3f64fbf0..e135adf46980 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1934,7 +1934,7 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter)
 
 		val = rd32(E1000_RXPBS);
 		val &= ~I210_RXPBSIZE_MASK;
-		val |= I210_RXPBSIZE_PB_32KB;
+		val |= I210_RXPBSIZE_PB_30KB;
 		wr32(E1000_RXPBS, val);
 
 		/* Section 8.12.9 states that MAX_TPKT_SIZE from DTXMXPKTSZ
-- 
cgit v1.2.3


From bad87ee82f74707913a27f16d40cd8a1c340b47e Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Fri, 16 Nov 2018 16:19:24 -0800
Subject: Documentation: igb: Add a section about CBS

Add some pointers to the definition of the CBS algorithm, and some
notes about the limits of its implementation in the i210 family of
controllers.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 Documentation/networking/device_drivers/intel/igb.rst | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/Documentation/networking/device_drivers/intel/igb.rst b/Documentation/networking/device_drivers/intel/igb.rst
index ba16b86d5593..e87a4a72ea2d 100644
--- a/Documentation/networking/device_drivers/intel/igb.rst
+++ b/Documentation/networking/device_drivers/intel/igb.rst
@@ -177,6 +177,25 @@ rate limit using the IProute2 tool. Download the latest version of the
 IProute2 tool from Sourceforge if your version does not have all the features
 you require.
 
+Credit Based Shaper (Qav Mode)
+------------------------------
+When enabling the CBS qdisc in the hardware offload mode, traffic shaping using
+the CBS (described in the IEEE 802.1Q-2018 Section 8.6.8.2 and discussed in the
+Annex L) algorithm will run in the i210 controller, so it's more accurate and
+uses less CPU.
+
+When using offloaded CBS, and the traffic rate obeys the configured rate
+(doesn't go above it), CBS should have little to no effect in the latency.
+
+The offloaded version of the algorithm has some limits, caused by how the idle
+slope is expressed in the adapter's registers. It can only represent idle slopes
+in 16.38431 kbps units, which means that if a idle slope of 2576kbps is
+requested, the controller will be configured to use a idle slope of ~2589 kbps,
+because the driver rounds the value up. For more details, see the comments on
+:c:func:`igb_config_tx_modes()`.
+
+NOTE: This feature is exclusive to i210 models.
+
 
 Support
 =======
-- 
cgit v1.2.3


From cd0d465bb697a9c7bf66a9fe940f7981232f1676 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 19 Nov 2018 20:48:19 +0800
Subject: e100: Fix passing zero to 'PTR_ERR' warning in e100_load_ucode_wait

Fix a static code checker warning:
drivers/net/ethernet/intel/e100.c:1349
 e100_load_ucode_wait() warn: passing zero to 'PTR_ERR'

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e100.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 5e5c57db0d3f..0fd268070fb4 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -1345,8 +1345,8 @@ static inline int e100_load_ucode_wait(struct nic *nic)
 
 	fw = e100_request_firmware(nic);
 	/* If it's NULL, then no ucode is required */
-	if (!fw || IS_ERR(fw))
-		return PTR_ERR(fw);
+	if (IS_ERR_OR_NULL(fw))
+		return PTR_ERR_OR_ZERO(fw);
 
 	if ((err = e100_exec_cb(nic, (void *)fw, e100_setup_ucode)))
 		netif_err(nic, probe, nic->netdev,
-- 
cgit v1.2.3


From 31389b53b3e0b535867af9090a5d19ec64768d55 Mon Sep 17 00:00:00 2001
From: Konstantin Khorenko <khorenko@virtuozzo.com>
Date: Fri, 23 Nov 2018 19:10:28 +0300
Subject: i40e: define proper net_device::neigh_priv_len

Out of bound read reported by KASan.

i40iw_net_event() reads unconditionally 16 bytes from
neigh->primary_key while the memory allocated for
"neighbour" struct is evaluated in neigh_alloc() as

  tbl->entry_size + dev->neigh_priv_len

where "dev" is a net_device.

But the driver does not setup dev->neigh_priv_len and
we read beyond the neigh entry allocated memory,
so the patch in the next mail fixes this.

Signed-off-by: Konstantin Khorenko <khorenko@virtuozzo.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index fbb21ac06c98..5824d74bb8dc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -12339,6 +12339,9 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	ether_addr_copy(netdev->dev_addr, mac_addr);
 	ether_addr_copy(netdev->perm_addr, mac_addr);
 
+	/* i40iw_net_event() reads 16 bytes from neigh->primary_key */
+	netdev->neigh_priv_len = sizeof(u32) * 4;
+
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
 	/* Setup netdev TC information */
-- 
cgit v1.2.3


From 9a2d57a7a0626783a62d205f255d8227b212c14b Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Wed, 28 Nov 2018 17:07:49 +0100
Subject: i40e: extend PTP gettime function to read system clock

This adds support for the PTP_SYS_OFFSET_EXTENDED ioctl.

Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Acked-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ptp.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index e6fc0aff8c99..5fb4353c742b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -28,19 +28,23 @@
  * i40e_ptp_read - Read the PHC time from the device
  * @pf: Board private structure
  * @ts: timespec structure to hold the current time value
+ * @sts: structure to hold the system time before and after reading the PHC
  *
  * This function reads the PRTTSYN_TIME registers and stores them in a
  * timespec. However, since the registers are 64 bits of nanoseconds, we must
  * convert the result to a timespec before we can return.
  **/
-static void i40e_ptp_read(struct i40e_pf *pf, struct timespec64 *ts)
+static void i40e_ptp_read(struct i40e_pf *pf, struct timespec64 *ts,
+			  struct ptp_system_timestamp *sts)
 {
 	struct i40e_hw *hw = &pf->hw;
 	u32 hi, lo;
 	u64 ns;
 
 	/* The timer latches on the lowest register read. */
+	ptp_read_system_prets(sts);
 	lo = rd32(hw, I40E_PRTTSYN_TIME_L);
+	ptp_read_system_postts(sts);
 	hi = rd32(hw, I40E_PRTTSYN_TIME_H);
 
 	ns = (((u64)hi) << 32) | lo;
@@ -146,7 +150,7 @@ static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 
 	mutex_lock(&pf->tmreg_lock);
 
-	i40e_ptp_read(pf, &now);
+	i40e_ptp_read(pf, &now, NULL);
 	timespec64_add_ns(&now, delta);
 	i40e_ptp_write(pf, (const struct timespec64 *)&now);
 
@@ -156,19 +160,21 @@ static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 }
 
 /**
- * i40e_ptp_gettime - Get the time of the PHC
+ * i40e_ptp_gettimex - Get the time of the PHC
  * @ptp: The PTP clock structure
  * @ts: timespec structure to hold the current time value
+ * @sts: structure to hold the system time before and after reading the PHC
  *
  * Read the device clock and return the correct value on ns, after converting it
  * into a timespec struct.
  **/
-static int i40e_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int i40e_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
+			     struct ptp_system_timestamp *sts)
 {
 	struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
 
 	mutex_lock(&pf->tmreg_lock);
-	i40e_ptp_read(pf, ts);
+	i40e_ptp_read(pf, ts, sts);
 	mutex_unlock(&pf->tmreg_lock);
 
 	return 0;
@@ -702,7 +708,7 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf)
 	pf->ptp_caps.pps = 0;
 	pf->ptp_caps.adjfreq = i40e_ptp_adjfreq;
 	pf->ptp_caps.adjtime = i40e_ptp_adjtime;
-	pf->ptp_caps.gettime64 = i40e_ptp_gettime;
+	pf->ptp_caps.gettimex64 = i40e_ptp_gettimex;
 	pf->ptp_caps.settime64 = i40e_ptp_settime;
 	pf->ptp_caps.enable = i40e_ptp_feature_enable;
 
-- 
cgit v1.2.3


From eec903769b4ea476591ffff73bb7359f14f38c51 Mon Sep 17 00:00:00 2001
From: Young Xiao <YangX92@hotmail.com>
Date: Thu, 29 Nov 2018 01:54:10 +0000
Subject: ice: Do not enable NAPI on q_vectors that have no rings

If ice driver has q_vectors w/ active NAPI that has no rings,
then this will result in a divide by zero error. To correct it
I am updating the driver code so that we only support NAPI on
q_vectors that have 1 or more rings allocated to them.

See commit 13a8cd191a2b ("i40e: Do not enable NAPI on q_vectors
that have no rings") for detail.

Signed-off-by: Young Xiao <YangX92@hotmail.com>
Acked-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index f9f0d470412b..8725569d11f0 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2564,8 +2564,12 @@ static void ice_napi_enable_all(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
-		napi_enable(&vsi->q_vectors[q_idx]->napi);
+	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+		if (q_vector->rx.ring || q_vector->tx.ring)
+			napi_enable(&q_vector->napi);
+	}
 }
 
 /**
@@ -2932,8 +2936,12 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
-		napi_disable(&vsi->q_vectors[q_idx]->napi);
+	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+		if (q_vector->rx.ring || q_vector->tx.ring)
+			napi_disable(&q_vector->napi);
+	}
 }
 
 /**
-- 
cgit v1.2.3


From 1fb3a7a75e2efcc83ef21f2434069cddd6fae6f5 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Mon, 3 Dec 2018 13:54:38 +0800
Subject: igb: Fix an issue that PME is not enabled during runtime suspend

I210 ethernet card doesn't wakeup when a cable gets plugged. It's
because its PME is not set.

Since commit 42eca2302146 ("PCI: Don't touch card regs after runtime
suspend D3"), if the PCI state is saved, pci_pm_runtime_suspend() stops
calling pci_finish_runtime_suspend(), which enables the PCI PME.

To fix the issue, let's not to save PCI states when it's runtime
suspend, to let the PCI subsystem enables PME.

Fixes: 42eca2302146 ("PCI: Don't touch card regs after runtime suspend D3")
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index e135adf46980..87bdf1604ae2 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -8771,9 +8771,11 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 	rtnl_unlock();
 
 #ifdef CONFIG_PM
-	retval = pci_save_state(pdev);
-	if (retval)
-		return retval;
+	if (!runtime) {
+		retval = pci_save_state(pdev);
+		if (retval)
+			return retval;
+	}
 #endif
 
 	status = rd32(E1000_STATUS);
-- 
cgit v1.2.3


From 8fa10ef01260937eb540b4e9bbc3efa023595993 Mon Sep 17 00:00:00 2001
From: Steve Douthit <stephend@silicom-usa.com>
Date: Thu, 6 Dec 2018 15:50:39 +0000
Subject: ixgbe: register a mdiobus

Most dsa devices expect a 'struct mii_bus' pointer to talk to switches
via the MII interface.

While this works for dsa devices, it will not work safely with Linux
PHYs in all configurations since the firmware of the ixgbe device may
be polling some PHY addresses in the background.

Signed-off-by: Stephen Douthit <stephend@silicom-usa.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/Kconfig            |   1 +
 drivers/net/ethernet/intel/ixgbe/ixgbe.h      |   2 +
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c |   5 +
 drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c  | 299 ++++++++++++++++++++++++++
 drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h  |   2 +
 5 files changed, 309 insertions(+)

diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index f05c91d4c469..31fb76ee9d82 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -159,6 +159,7 @@ config IXGBE
 	tristate "Intel(R) 10GbE PCI Express adapters support"
 	depends on PCI
 	select MDIO
+	select MDIO_DEVICE
 	imply PTP_1588_CLOCK
 	---help---
 	  This driver supports Intel(R) 10GbE PCI Express family of
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 143bdd5ee2a0..08d85e336bd4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -12,6 +12,7 @@
 #include <linux/aer.h>
 #include <linux/if_vlan.h>
 #include <linux/jiffies.h>
+#include <linux/phy.h>
 
 #include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
@@ -561,6 +562,7 @@ struct ixgbe_adapter {
 	struct net_device *netdev;
 	struct bpf_prog *xdp_prog;
 	struct pci_dev *pdev;
+	struct mii_bus *mii_bus;
 
 	unsigned long state;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2cd8c42d1403..7a3798ff2366 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -39,6 +39,7 @@
 #include "ixgbe.h"
 #include "ixgbe_common.h"
 #include "ixgbe_dcb_82599.h"
+#include "ixgbe_phy.h"
 #include "ixgbe_sriov.h"
 #include "ixgbe_model.h"
 #include "ixgbe_txrx_common.h"
@@ -11122,6 +11123,8 @@ skip_sriov:
 			IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL,
 			true);
 
+	ixgbe_mii_bus_init(hw);
+
 	return 0;
 
 err_register:
@@ -11172,6 +11175,8 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	set_bit(__IXGBE_REMOVING, &adapter->state);
 	cancel_work_sync(&adapter->service_task);
 
+	if (adapter->mii_bus)
+		mdiobus_unregister(adapter->mii_bus);
 
 #ifdef CONFIG_IXGBE_DCA
 	if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 919a7af84b42..cc4907f9ff02 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -3,6 +3,7 @@
 
 #include <linux/pci.h>
 #include <linux/delay.h>
+#include <linux/iopoll.h>
 #include <linux/sched.h>
 
 #include "ixgbe.h"
@@ -658,6 +659,304 @@ s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr,
 	return status;
 }
 
+#define IXGBE_HW_READ_REG(addr) IXGBE_READ_REG(hw, addr)
+
+/**
+ *  ixgbe_msca_cmd - Write the command register and poll for completion/timeout
+ *  @hw: pointer to hardware structure
+ *  @cmd: command register value to write
+ **/
+static s32 ixgbe_msca_cmd(struct ixgbe_hw *hw, u32 cmd)
+{
+	IXGBE_WRITE_REG(hw, IXGBE_MSCA, cmd);
+
+	return readx_poll_timeout(IXGBE_HW_READ_REG, IXGBE_MSCA, cmd,
+				  !(cmd & IXGBE_MSCA_MDI_COMMAND), 10,
+				  10 * IXGBE_MDIO_COMMAND_TIMEOUT);
+}
+
+/**
+ *  ixgbe_mii_bus_read_generic - Read a clause 22/45 register with gssr flags
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ *  @gssr: semaphore flags to acquire
+ **/
+static s32 ixgbe_mii_bus_read_generic(struct ixgbe_hw *hw, int addr,
+				      int regnum, u32 gssr)
+{
+	u32 hwaddr, cmd;
+	s32 data;
+
+	if (hw->mac.ops.acquire_swfw_sync(hw, gssr))
+		return -EBUSY;
+
+	hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT;
+	if (regnum & MII_ADDR_C45) {
+		hwaddr |= regnum & GENMASK(21, 0);
+		cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND;
+	} else {
+		hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT;
+		cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL |
+			IXGBE_MSCA_READ_AUTOINC | IXGBE_MSCA_MDI_COMMAND;
+	}
+
+	data = ixgbe_msca_cmd(hw, cmd);
+	if (data < 0)
+		goto mii_bus_read_done;
+
+	/* For a clause 45 access the address cycle just completed, we still
+	 * need to do the read command, otherwise just get the data
+	 */
+	if (!(regnum & MII_ADDR_C45))
+		goto do_mii_bus_read;
+
+	cmd = hwaddr | IXGBE_MSCA_READ | IXGBE_MSCA_MDI_COMMAND;
+	data = ixgbe_msca_cmd(hw, cmd);
+	if (data < 0)
+		goto mii_bus_read_done;
+
+do_mii_bus_read:
+	data = IXGBE_READ_REG(hw, IXGBE_MSRWD);
+	data = (data >> IXGBE_MSRWD_READ_DATA_SHIFT) & GENMASK(16, 0);
+
+mii_bus_read_done:
+	hw->mac.ops.release_swfw_sync(hw, gssr);
+	return data;
+}
+
+/**
+ *  ixgbe_mii_bus_write_generic - Write a clause 22/45 register with gssr flags
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ *  @val: value to write
+ *  @gssr: semaphore flags to acquire
+ **/
+static s32 ixgbe_mii_bus_write_generic(struct ixgbe_hw *hw, int addr,
+				       int regnum, u16 val, u32 gssr)
+{
+	u32 hwaddr, cmd;
+	s32 err;
+
+	if (hw->mac.ops.acquire_swfw_sync(hw, gssr))
+		return -EBUSY;
+
+	IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)val);
+
+	hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT;
+	if (regnum & MII_ADDR_C45) {
+		hwaddr |= regnum & GENMASK(21, 0);
+		cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND;
+	} else {
+		hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT;
+		cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL | IXGBE_MSCA_WRITE |
+			IXGBE_MSCA_MDI_COMMAND;
+	}
+
+	/* For clause 45 this is an address cycle, for clause 22 this is the
+	 * entire transaction
+	 */
+	err = ixgbe_msca_cmd(hw, cmd);
+	if (err < 0 || !(regnum & MII_ADDR_C45))
+		goto mii_bus_write_done;
+
+	cmd = hwaddr | IXGBE_MSCA_WRITE | IXGBE_MSCA_MDI_COMMAND;
+	err = ixgbe_msca_cmd(hw, cmd);
+
+mii_bus_write_done:
+	hw->mac.ops.release_swfw_sync(hw, gssr);
+	return err;
+}
+
+/**
+ *  ixgbe_mii_bus_read - Read a clause 22/45 register
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ **/
+static s32 ixgbe_mii_bus_read(struct mii_bus *bus, int addr, int regnum)
+{
+	struct ixgbe_adapter *adapter = bus->priv;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 gssr = hw->phy.phy_semaphore_mask;
+
+	return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr);
+}
+
+/**
+ *  ixgbe_mii_bus_write - Write a clause 22/45 register
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ *  @val: value to write
+ **/
+static s32 ixgbe_mii_bus_write(struct mii_bus *bus, int addr, int regnum,
+			       u16 val)
+{
+	struct ixgbe_adapter *adapter = bus->priv;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 gssr = hw->phy.phy_semaphore_mask;
+
+	return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr);
+}
+
+/**
+ *  ixgbe_x550em_a_mii_bus_read - Read a clause 22/45 register on x550em_a
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ **/
+static s32 ixgbe_x550em_a_mii_bus_read(struct mii_bus *bus, int addr,
+				       int regnum)
+{
+	struct ixgbe_adapter *adapter = bus->priv;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 gssr = hw->phy.phy_semaphore_mask;
+
+	gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM;
+	return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr);
+}
+
+/**
+ *  ixgbe_x550em_a_mii_bus_write - Write a clause 22/45 register on x550em_a
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ *  @val: value to write
+ **/
+static s32 ixgbe_x550em_a_mii_bus_write(struct mii_bus *bus, int addr,
+					int regnum, u16 val)
+{
+	struct ixgbe_adapter *adapter = bus->priv;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 gssr = hw->phy.phy_semaphore_mask;
+
+	gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM;
+	return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr);
+}
+
+/**
+ * ixgbe_get_first_secondary_devfn - get first device downstream of root port
+ * @devfn: PCI_DEVFN of root port on domain 0, bus 0
+ *
+ * Returns pci_dev pointer to PCI_DEVFN(0, 0) on subordinate side of root
+ * on domain 0, bus 0, devfn = 'devfn'
+ **/
+static struct pci_dev *ixgbe_get_first_secondary_devfn(unsigned int devfn)
+{
+	struct pci_dev *rp_pdev;
+	int bus;
+
+	rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn);
+	if (rp_pdev && rp_pdev->subordinate) {
+		bus = rp_pdev->subordinate->number;
+		return pci_get_domain_bus_and_slot(0, bus, 0);
+	}
+
+	return NULL;
+}
+
+/**
+ * ixgbe_x550em_a_has_mii - is this the first ixgbe x550em_a PCI function?
+ * @hw: pointer to hardware structure
+ *
+ * Returns true if hw points to lowest numbered PCI B:D.F x550_em_a device in
+ * the SoC.  There are up to 4 MACs sharing a single MDIO bus on the x550em_a,
+ * but we only want to register one MDIO bus.
+ **/
+static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw)
+{
+	struct ixgbe_adapter *adapter = hw->back;
+	struct pci_dev *pdev = adapter->pdev;
+	struct pci_dev *func0_pdev;
+
+	/* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices
+	 * are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0
+	 * It's not valid for function 0 to be disabled and function 1 is up,
+	 * so the lowest numbered ixgbe dev will be device 0 function 0 on one
+	 * of those two root ports
+	 */
+	func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0));
+	if (func0_pdev) {
+		if (func0_pdev == pdev)
+			return true;
+		else
+			return false;
+	}
+	func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0));
+	if (func0_pdev == pdev)
+		return true;
+
+	return false;
+}
+
+/**
+ * ixgbe_mii_bus_init - mii_bus structure setup
+ * @hw: pointer to hardware structure
+ *
+ * Returns 0 on success, negative on failure
+ *
+ * ixgbe_mii_bus_init initializes a mii_bus structure in adapter
+ **/
+s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw)
+{
+	struct ixgbe_adapter *adapter = hw->back;
+	struct pci_dev *pdev = adapter->pdev;
+	struct device *dev = &adapter->netdev->dev;
+	struct mii_bus *bus;
+
+	adapter->mii_bus = devm_mdiobus_alloc(dev);
+	if (!adapter->mii_bus)
+		return -ENOMEM;
+
+	bus = adapter->mii_bus;
+
+	switch (hw->device_id) {
+	/* C3000 SoCs */
+	case IXGBE_DEV_ID_X550EM_A_KR:
+	case IXGBE_DEV_ID_X550EM_A_KR_L:
+	case IXGBE_DEV_ID_X550EM_A_SFP_N:
+	case IXGBE_DEV_ID_X550EM_A_SGMII:
+	case IXGBE_DEV_ID_X550EM_A_SGMII_L:
+	case IXGBE_DEV_ID_X550EM_A_10G_T:
+	case IXGBE_DEV_ID_X550EM_A_SFP:
+	case IXGBE_DEV_ID_X550EM_A_1G_T:
+	case IXGBE_DEV_ID_X550EM_A_1G_T_L:
+		if (!ixgbe_x550em_a_has_mii(hw))
+			goto ixgbe_no_mii_bus;
+		bus->read = &ixgbe_x550em_a_mii_bus_read;
+		bus->write = &ixgbe_x550em_a_mii_bus_write;
+		break;
+	default:
+		bus->read = &ixgbe_mii_bus_read;
+		bus->write = &ixgbe_mii_bus_write;
+		break;
+	}
+
+	/* Use the position of the device in the PCI hierarchy as the id */
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mdio-%s", ixgbe_driver_name,
+		 pci_name(pdev));
+
+	bus->name = "ixgbe-mdio";
+	bus->priv = adapter;
+	bus->parent = dev;
+	bus->phy_mask = GENMASK(31, 0);
+
+	/* Support clause 22/45 natively.  ixgbe_probe() sets MDIO_EMULATE_C22
+	 * unfortunately that causes some clause 22 frames to be sent with
+	 * clause 45 addressing.  We don't want that.
+	 */
+	hw->phy.mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22;
+
+	return mdiobus_register(bus);
+
+ixgbe_no_mii_bus:
+	devm_mdiobus_free(dev, bus);
+	adapter->mii_bus = NULL;
+	return -ENODEV;
+}
+
 /**
  *  ixgbe_setup_phy_link_generic - Set and restart autoneg
  *  @hw: pointer to hardware structure
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
index 64e44e01c973..214b01085718 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
@@ -120,6 +120,8 @@
 /* SFP+ SFF-8472 Compliance code */
 #define IXGBE_SFF_SFF_8472_UNSUP      0x00
 
+s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw);
+
 s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw);
 s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw);
 s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr,
-- 
cgit v1.2.3


From 643bae17fd4ccb503cdc6d99c1b4fbd2c4ca6a78 Mon Sep 17 00:00:00 2001
From: Steve Douthit <stephend@silicom-usa.com>
Date: Thu, 6 Dec 2018 15:50:43 +0000
Subject: ixgbe: use mii_bus to handle MII related ioctls

Use the mii_bus callbacks to address the entire clause 22/45 address
space.  Enables userspace to poke switch registers instead of a single
PHY address.

The ixgbe firmware may be polling PHYs in a way that is not protected by
the mii_bus lock.  This isn't new behavior, but as Andrew Lunn pointed
out there are more addresses available for conflicts.

Signed-off-by: Stephen Douthit <stephend@silicom-usa.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 7a3798ff2366..daff8183534b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8791,6 +8791,15 @@ ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr)
 	u16 value;
 	int rc;
 
+	if (adapter->mii_bus) {
+		int regnum = addr;
+
+		if (devad != MDIO_DEVAD_NONE)
+			regnum |= (devad << 16) | MII_ADDR_C45;
+
+		return mdiobus_read(adapter->mii_bus, prtad, regnum);
+	}
+
 	if (prtad != hw->phy.mdio.prtad)
 		return -EINVAL;
 	rc = hw->phy.ops.read_reg(hw, addr, devad, &value);
@@ -8805,6 +8814,15 @@ static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad,
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
+	if (adapter->mii_bus) {
+		int regnum = addr;
+
+		if (devad != MDIO_DEVAD_NONE)
+			regnum |= (devad << 16) | MII_ADDR_C45;
+
+		return mdiobus_write(adapter->mii_bus, prtad, regnum, value);
+	}
+
 	if (prtad != hw->phy.mdio.prtad)
 		return -EINVAL;
 	return hw->phy.ops.write_reg(hw, addr, devad, value);
-- 
cgit v1.2.3


From 77ea5f4cbe2084db9ab021ba73fb7eadf1610884 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Wed, 19 Dec 2018 17:00:23 +0100
Subject: bpf/cpumap: make sure frame_size for build_skb is aligned if headroom
 isn't

The frame_size passed to build_skb must be aligned, else it is
possible that the embedded struct skb_shared_info gets unaligned.

For correctness make sure that xdpf->headroom in included in the
alignment. No upstream drivers can hit this, as all XDP drivers provide
an aligned headroom.  This was discovered when playing with implementing
XDP support for mvneta, which have a 2 bytes DSA header, and this
Marvell ARM64 platform didn't like doing atomic operations on an
unaligned skb_shinfo(skb)->dataref addresses.

Fixes: 1c601d829ab0 ("bpf: cpumap xdp_buff to skb conversion and allocation")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/cpumap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 24aac0d0f412..8974b3755670 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -183,7 +183,7 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 	 * is not at a fixed memory location, with mixed length
 	 * packets, which is bad for cache-line hotness.
 	 */
-	frame_size = SKB_DATA_ALIGN(xdpf->len) + xdpf->headroom +
+	frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) +
 		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	pkt_data_start = xdpf->data - xdpf->headroom;
-- 
cgit v1.2.3


From 9ee79a65d176e5815877aa148acc956e4cc90c53 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 20 Dec 2018 11:35:29 -0800
Subject: bpf: sk_msg, fix sk_msg_md access past end test

Currently, the test to ensure reads past the end of the sk_msg_md
data structure fail is incorrectly expecting success. Fix this
typo and use correct expected error.

Fixes: 945a47d87cee ("bpf: sk_msg, add tests for size field")
Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index b246931c46ef..dbd31750b214 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1879,7 +1879,7 @@ static struct bpf_test tests[] = {
 				    offsetof(struct sk_msg_md, size) + 4),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "R0 !read_ok",
+		.errstr = "invalid bpf_context access",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SK_MSG,
 	},
-- 
cgit v1.2.3


From bc1b4f013b5029b4c8b63fb9ba8d084119486d7b Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 20 Dec 2018 11:35:30 -0800
Subject: bpf: sk_msg, improve offset chk in _is_valid_access

The check for max offset in sk_msg_is_valid_access uses sizeof()
which is incorrect because it would allow accessing possibly
past the end of the struct in the padded case. Further, it doesn't
preclude accessing any padding that may be added in the middle of
a struct. All told this makes it fragile to rely on.

To fix this explicitly check offsets with fields using the
bpf_ctx_range() and bpf_ctx_range_till() macros.

For reference the current structure layout looks as follows (reported
by pahole)

struct sk_msg_md {
	union {
		void *             data;                 /*           8 */
	};                                               /*     0     8 */
	union {
		void *             data_end;             /*           8 */
	};                                               /*     8     8 */
	__u32                      family;               /*    16     4 */
	__u32                      remote_ip4;           /*    20     4 */
	__u32                      local_ip4;            /*    24     4 */
	__u32                      remote_ip6[4];        /*    28    16 */
	__u32                      local_ip6[4];         /*    44    16 */
	__u32                      remote_port;          /*    60     4 */
	/* --- cacheline 1 boundary (64 bytes) --- */
	__u32                      local_port;           /*    64     4 */
	__u32                      size;                 /*    68     4 */

	/* size: 72, cachelines: 2, members: 10 */
	/* last cacheline: 8 bytes */
};

So there should be no padding at the moment but fixing this now
prevents future errors.

Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/core/filter.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 3a3b21726fb5..6bd9f08f6162 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6313,6 +6313,9 @@ static bool sk_msg_is_valid_access(int off, int size,
 	if (type == BPF_WRITE)
 		return false;
 
+	if (off % size != 0)
+		return false;
+
 	switch (off) {
 	case offsetof(struct sk_msg_md, data):
 		info->reg_type = PTR_TO_PACKET;
@@ -6324,16 +6327,20 @@ static bool sk_msg_is_valid_access(int off, int size,
 		if (size != sizeof(__u64))
 			return false;
 		break;
-	default:
+	case bpf_ctx_range(struct sk_msg_md, family):
+	case bpf_ctx_range(struct sk_msg_md, remote_ip4):
+	case bpf_ctx_range(struct sk_msg_md, local_ip4):
+	case bpf_ctx_range_till(struct sk_msg_md, remote_ip6[0], remote_ip6[3]):
+	case bpf_ctx_range_till(struct sk_msg_md, local_ip6[0], local_ip6[3]):
+	case bpf_ctx_range(struct sk_msg_md, remote_port):
+	case bpf_ctx_range(struct sk_msg_md, local_port):
+	case bpf_ctx_range(struct sk_msg_md, size):
 		if (size != sizeof(__u32))
 			return false;
-	}
-
-	if (off < 0 || off >= sizeof(struct sk_msg_md))
-		return false;
-	if (off % size != 0)
+		break;
+	default:
 		return false;
-
+	}
 	return true;
 }
 
-- 
cgit v1.2.3


From 7a69c0f250568e6ab72f401b2c69aa0e666c94f2 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 20 Dec 2018 11:35:31 -0800
Subject: bpf: skmsg, replace comments with BUILD bug

Enforce comment on structure layout dependency with a BUILD_BUG_ON
to ensure the condition is maintained.

Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/skmsg.h | 4 +---
 net/core/filter.c     | 3 +++
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index eb8f6cb84c10..dd57e6f408b1 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -36,9 +36,7 @@ struct sk_msg_sg {
 	struct scatterlist		data[MAX_MSG_FRAGS + 1];
 };
 
-/* UAPI in filter.c depends on struct sk_msg_sg being first element. If
- * this is moved filter.c also must be updated.
- */
+/* UAPI in filter.c depends on struct sk_msg_sg being first element. */
 struct sk_msg {
 	struct sk_msg_sg		sg;
 	void				*data;
diff --git a/net/core/filter.c b/net/core/filter.c
index 6bd9f08f6162..447dd1bad31f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7425,6 +7425,9 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type,
 	int off;
 #endif
 
+	/* convert ctx uses the fact sg element is first in struct */
+	BUILD_BUG_ON(offsetof(struct sk_msg, sg) != 0);
+
 	switch (si->off) {
 	case offsetof(struct sk_msg_md, data):
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data),
-- 
cgit v1.2.3


From 51199405f967207de372d9b60989eb87d7ae8809 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 20 Dec 2018 11:35:32 -0800
Subject: bpf: skb_verdict, support SK_PASS on RX BPF path

Add SK_PASS verdict support to SK_SKB_VERDICT programs. Now that
support for redirects exists we can implement SK_PASS as a redirect
to the same socket. This simplifies the BPF programs and avoids an
extra map lookup on RX path for simple visibility cases.

Further, reduces user (BPF programmer in this context) confusion
when their program drops skb due to lack of support.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/core/skmsg.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 56a99d0c9aa0..8a91a460de8f 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -669,6 +669,22 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 	bool ingress;
 
 	switch (verdict) {
+	case __SK_PASS:
+		sk_other = psock->sk;
+		if (sock_flag(sk_other, SOCK_DEAD) ||
+		    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
+			goto out_free;
+		}
+		if (atomic_read(&sk_other->sk_rmem_alloc) <=
+		    sk_other->sk_rcvbuf) {
+			struct tcp_skb_cb *tcp = TCP_SKB_CB(skb);
+
+			tcp->bpf.flags |= BPF_F_INGRESS;
+			skb_queue_tail(&psock->ingress_skb, skb);
+			schedule_work(&psock->work);
+			break;
+		}
+		goto out_free;
 	case __SK_REDIRECT:
 		sk_other = tcp_skb_bpf_redirect_fetch(skb);
 		if (unlikely(!sk_other))
-- 
cgit v1.2.3


From 552de91068828daef50a227a665068cf8dde835e Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 20 Dec 2018 11:35:33 -0800
Subject: bpf: sk_msg, fix socket data_ready events

When a skb verdict program is in-use and either another BPF program
redirects to that socket or the new SK_PASS support is used the
data_ready callback does not wake up application. Instead because
the stream parser/verdict is using the sk data_ready callback we wake
up the stream parser/verdict block.

Fix this by adding a helper to check if the stream parser block is
enabled on the sk and if so call the saved pointer which is the
upper layers wake up function.

This fixes application stalls observed when an application is waiting
for data in a blocking read().

Fixes: d829e9c4112b ("tls: convert to generic sk_msg interface")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/skmsg.h | 8 ++++++++
 net/core/skmsg.c      | 6 +++---
 net/ipv4/tcp_bpf.c    | 2 +-
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index dd57e6f408b1..178a3933a71b 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -417,6 +417,14 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock)
 		sk_psock_drop(sk, psock);
 }
 
+static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock)
+{
+	if (psock->parser.enabled)
+		psock->parser.saved_data_ready(sk);
+	else
+		sk->sk_data_ready(sk);
+}
+
 static inline void psock_set_prog(struct bpf_prog **pprog,
 				  struct bpf_prog *prog)
 {
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 8a91a460de8f..3df7627db4bb 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -403,7 +403,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
 	msg->skb = skb;
 
 	sk_psock_queue_msg(psock, msg);
-	sk->sk_data_ready(sk);
+	sk_psock_data_ready(sk, psock);
 	return copied;
 }
 
@@ -751,7 +751,7 @@ static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb)
 }
 
 /* Called with socket lock held. */
-static void sk_psock_data_ready(struct sock *sk)
+static void sk_psock_strp_data_ready(struct sock *sk)
 {
 	struct sk_psock *psock;
 
@@ -799,7 +799,7 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
 		return;
 
 	parser->saved_data_ready = sk->sk_data_ready;
-	sk->sk_data_ready = sk_psock_data_ready;
+	sk->sk_data_ready = sk_psock_strp_data_ready;
 	sk->sk_write_space = sk_psock_write_space;
 	parser->enabled = true;
 }
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index a47c1cdf90fc..87503343743d 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -198,7 +198,7 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 		msg->sg.start = i;
 		msg->sg.size -= apply_bytes;
 		sk_psock_queue_msg(psock, tmp);
-		sk->sk_data_ready(sk);
+		sk_psock_data_ready(sk, psock);
 	} else {
 		sk_msg_free(sk, tmp);
 		kfree(tmp);
-- 
cgit v1.2.3


From a136678c0bdbb650daff5df5eec1dab960e074a7 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 20 Dec 2018 11:35:34 -0800
Subject: bpf: sk_msg, zap ingress queue on psock down

In addition to releasing any cork'ed data on a psock when the psock
is removed we should also release any skb's in the ingress work queue.
Otherwise the skb's eventually get free'd but late in the tear
down process so we see the WARNING due to non-zero sk_forward_alloc.

  void sk_stream_kill_queues(struct sock *sk)
  {
	...
	WARN_ON(sk->sk_forward_alloc);
	...
  }

Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/core/skmsg.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 3df7627db4bb..86c9726fced8 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -572,6 +572,7 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 {
 	rcu_assign_sk_user_data(sk, NULL);
 	sk_psock_cork_free(psock);
+	sk_psock_zap_ingress(psock);
 	sk_psock_restore_proto(sk, psock);
 
 	write_lock_bh(&sk->sk_callback_lock);
-- 
cgit v1.2.3


From 0608c69c9a805c6264689d7eab4203eab88cf1da Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 20 Dec 2018 11:35:35 -0800
Subject: bpf: sk_msg, sock{map|hash} redirect through ULP

A sockmap program that redirects through a kTLS ULP enabled socket
will not work correctly because the ULP layer is skipped. This
fixes the behavior to call through the ULP layer on redirect to
ensure any operations required on the data stream at the ULP layer
continue to be applied.

To do this we add an internal flag MSG_SENDPAGE_NOPOLICY to avoid
calling the BPF layer on a redirected message. This is
required to avoid calling the BPF layer multiple times (possibly
recursively) which is not the current/expected behavior without
ULPs. In the future we may add a redirect flag if users _do_
want the policy applied again but this would need to work for both
ULP and non-ULP sockets and be opt-in to avoid breaking existing
programs.

Also to avoid polluting the flag space with an internal flag we
reuse the flag space overlapping MSG_SENDPAGE_NOPOLICY with
MSG_WAITFORONE. Here WAITFORONE is specific to recv path and
SENDPAGE_NOPOLICY is only used for sendpage hooks. The last thing
to verify is user space API is masked correctly to ensure the flag
can not be set by user. (Note this needs to be true regardless
because we have internal flags already in-use that user space
should not be able to set). But for completeness we have two UAPI
paths into sendpage, sendfile and splice.

In the sendfile case the function do_sendfile() zero's flags,

./fs/read_write.c:
 static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
		   	    size_t count, loff_t max)
 {
   ...
   fl = 0;
#if 0
   /*
    * We need to debate whether we can enable this or not. The
    * man page documents EAGAIN return for the output at least,
    * and the application is arguably buggy if it doesn't expect
    * EAGAIN on a non-blocking file descriptor.
    */
    if (in.file->f_flags & O_NONBLOCK)
	fl = SPLICE_F_NONBLOCK;
#endif
    file_start_write(out.file);
    retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl);
 }

In the splice case the pipe_to_sendpage "actor" is used which
masks flags with SPLICE_F_MORE.

./fs/splice.c:
 static int pipe_to_sendpage(struct pipe_inode_info *pipe,
			    struct pipe_buffer *buf, struct splice_desc *sd)
 {
   ...
   more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0;
   ...
 }

Confirming what we expect that internal flags  are in fact internal
to socket side.

Fixes: d3b18ad31f93 ("tls: add bpf support to sk_msg handling")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/socket.h |  1 +
 include/net/tls.h      |  9 +++++++++
 net/ipv4/tcp_bpf.c     | 13 ++++++++++++-
 net/tls/tls_sw.c       | 43 ++++++++++++++++++++++++++++++-------------
 4 files changed, 52 insertions(+), 14 deletions(-)

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 8b571e9b9f76..84c48a3c0227 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -286,6 +286,7 @@ struct ucred {
 #define MSG_NOSIGNAL	0x4000	/* Do not generate SIGPIPE */
 #define MSG_MORE	0x8000	/* Sender will send more */
 #define MSG_WAITFORONE	0x10000	/* recvmmsg(): block until 1+ packets avail */
+#define MSG_SENDPAGE_NOPOLICY 0x10000 /* sendpage() internal : do no apply policy */
 #define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */
 #define MSG_BATCH	0x40000 /* sendmmsg(): more messages coming */
 #define MSG_EOF         MSG_FIN
diff --git a/include/net/tls.h b/include/net/tls.h
index bab5627ff5e3..23601f3b02ee 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -454,6 +454,15 @@ tls_offload_ctx_tx(const struct tls_context *tls_ctx)
 	return (struct tls_offload_context_tx *)tls_ctx->priv_ctx_tx;
 }
 
+static inline bool tls_sw_has_ctx_tx(const struct sock *sk)
+{
+	struct tls_context *ctx = tls_get_ctx(sk);
+
+	if (!ctx)
+		return false;
+	return !!tls_sw_ctx_tx(ctx);
+}
+
 static inline struct tls_offload_context_rx *
 tls_offload_ctx_rx(const struct tls_context *tls_ctx)
 {
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 87503343743d..1bb7321a256d 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -8,6 +8,7 @@
 #include <linux/wait.h>
 
 #include <net/inet_common.h>
+#include <net/tls.h>
 
 static bool tcp_bpf_stream_read(const struct sock *sk)
 {
@@ -218,6 +219,8 @@ static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes,
 	u32 off;
 
 	while (1) {
+		bool has_tx_ulp;
+
 		sge = sk_msg_elem(msg, msg->sg.start);
 		size = (apply && apply_bytes < sge->length) ?
 			apply_bytes : sge->length;
@@ -226,7 +229,15 @@ static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes,
 
 		tcp_rate_check_app_limited(sk);
 retry:
-		ret = do_tcp_sendpages(sk, page, off, size, flags);
+		has_tx_ulp = tls_sw_has_ctx_tx(sk);
+		if (has_tx_ulp) {
+			flags |= MSG_SENDPAGE_NOPOLICY;
+			ret = kernel_sendpage_locked(sk,
+						     page, off, size, flags);
+		} else {
+			ret = do_tcp_sendpages(sk, page, off, size, flags);
+		}
+
 		if (ret <= 0)
 			return ret;
 		if (apply)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index d4ecc66464e6..5aee9ae5ca53 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -686,12 +686,13 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 	struct sk_psock *psock;
 	struct sock *sk_redir;
 	struct tls_rec *rec;
+	bool enospc, policy;
 	int err = 0, send;
 	u32 delta = 0;
-	bool enospc;
 
+	policy = !(flags & MSG_SENDPAGE_NOPOLICY);
 	psock = sk_psock_get(sk);
-	if (!psock)
+	if (!psock || !policy)
 		return tls_push_record(sk, flags, record_type);
 more_data:
 	enospc = sk_msg_full(msg);
@@ -1017,8 +1018,8 @@ send_end:
 	return copied ? copied : ret;
 }
 
-int tls_sw_sendpage(struct sock *sk, struct page *page,
-		    int offset, size_t size, int flags)
+int tls_sw_do_sendpage(struct sock *sk, struct page *page,
+		       int offset, size_t size, int flags)
 {
 	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
@@ -1033,15 +1034,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 	int ret = 0;
 	bool eor;
 
-	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
-		      MSG_SENDPAGE_NOTLAST))
-		return -ENOTSUPP;
-
-	/* No MSG_EOR from splice, only look at MSG_MORE */
 	eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST));
-
-	lock_sock(sk);
-
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	/* Wait till there is any pending write on socket */
@@ -1145,10 +1138,34 @@ wait_for_memory:
 	}
 sendpage_end:
 	ret = sk_stream_error(sk, flags, ret);
-	release_sock(sk);
 	return copied ? copied : ret;
 }
 
+int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
+			   int offset, size_t size, int flags)
+{
+	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
+		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
+		return -ENOTSUPP;
+
+	return tls_sw_do_sendpage(sk, page, offset, size, flags);
+}
+
+int tls_sw_sendpage(struct sock *sk, struct page *page,
+		    int offset, size_t size, int flags)
+{
+	int ret;
+
+	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
+		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
+		return -ENOTSUPP;
+
+	lock_sock(sk);
+	ret = tls_sw_do_sendpage(sk, page, offset, size, flags);
+	release_sock(sk);
+	return ret;
+}
+
 static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock,
 				     int flags, long timeo, int *err)
 {
-- 
cgit v1.2.3


From 28cb6f1eaffdc5a6a9707cac55f4a43aa3fd7895 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 20 Dec 2018 11:35:36 -0800
Subject: bpf: tls_sw, init TLS ULP removes BPF proto hooks

The existing code did not expect users would initialize the TLS ULP
without subsequently calling the TLS TX enabling socket option.
If the application tries to send data after the TLS ULP enable op
but before the TLS TX enable op the BPF sk_msg verdict program is
skipped. This patch resolves this by converting the ipv4 sock ops
to be calculated at init time the same way ipv6 ops are done. This
pulls in any changes to the sock ops structure that have been made
after the socket was created including the changes from adding the
socket to a sock{map|hash}.

This was discovered by running OpenSSL master branch which calls
the TLS ULP setsockopt early in TLS handshake but only enables
the TLS TX path once the handshake has completed. As a result the
datapath missed the initial handshake messages.

Fixes: 02c558b2d5d6 ("bpf: sockmap, support for msg_peek in sk_msg with redirect ingress")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/tls/tls_main.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 311cec8e533d..acff12999c06 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -55,6 +55,8 @@ enum {
 
 static struct proto *saved_tcpv6_prot;
 static DEFINE_MUTEX(tcpv6_prot_mutex);
+static struct proto *saved_tcpv4_prot;
+static DEFINE_MUTEX(tcpv4_prot_mutex);
 static LIST_HEAD(device_list);
 static DEFINE_MUTEX(device_mutex);
 static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG];
@@ -690,6 +692,16 @@ static int tls_init(struct sock *sk)
 		mutex_unlock(&tcpv6_prot_mutex);
 	}
 
+	if (ip_ver == TLSV4 &&
+	    unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv4_prot))) {
+		mutex_lock(&tcpv4_prot_mutex);
+		if (likely(sk->sk_prot != saved_tcpv4_prot)) {
+			build_protos(tls_prots[TLSV4], sk->sk_prot);
+			smp_store_release(&saved_tcpv4_prot, sk->sk_prot);
+		}
+		mutex_unlock(&tcpv4_prot_mutex);
+	}
+
 	ctx->tx_conf = TLS_BASE;
 	ctx->rx_conf = TLS_BASE;
 	update_sk_prot(sk, ctx);
@@ -721,8 +733,6 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = {
 
 static int __init tls_register(void)
 {
-	build_protos(tls_prots[TLSV4], &tcp_prot);
-
 	tls_sw_proto_ops = inet_stream_ops;
 	tls_sw_proto_ops.splice_read = tls_sw_splice_read;
 
-- 
cgit v1.2.3


From d535c8a69c1924e70186d80be0a9cecaf475f166 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 6 Dec 2018 11:50:49 +0100
Subject: netfilter: conntrack: udp: only extend timeout to stream mode after
 2s

Currently DNS resolvers that send both A and AAAA queries from same source port
can trigger stream mode prematurely, which results in non-early-evictable conntrack entry
for three minutes, even though DNS requests are done in a few milliseconds.

Add a two second grace period where we continue to use the ordinary
30-second default timeout.  Its enough for DNS request/response traffic,
even if two request/reply packets are involved.

ASSURED is still set, else conntrack (and thus a possible
NAT mapping ...) gets zapped too in case conntrack table runs full.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack.h   |  5 +++++
 net/netfilter/nf_conntrack_proto_udp.c | 16 +++++++++++++---
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 7e012312cd61..249d0a5b12b8 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -27,12 +27,17 @@
 
 #include <net/netfilter/nf_conntrack_tuple.h>
 
+struct nf_ct_udp {
+	unsigned long	stream_ts;
+};
+
 /* per conntrack: protocol private data */
 union nf_conntrack_proto {
 	/* insert conntrack proto private data here */
 	struct nf_ct_dccp dccp;
 	struct ip_ct_sctp sctp;
 	struct ip_ct_tcp tcp;
+	struct nf_ct_udp udp;
 	struct nf_ct_gre gre;
 	unsigned int tmpl_padto;
 };
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index c879d8d78cfd..9f2e05adba69 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -100,11 +100,21 @@ static int udp_packet(struct nf_conn *ct,
 	if (!timeouts)
 		timeouts = udp_get_timeouts(nf_ct_net(ct));
 
+	if (!nf_ct_is_confirmed(ct))
+		ct->proto.udp.stream_ts = 2 * HZ + jiffies;
+
 	/* If we've seen traffic both ways, this is some kind of UDP
-	   stream.  Extend timeout. */
+	 * stream. Set Assured.
+	 */
 	if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
-		nf_ct_refresh_acct(ct, ctinfo, skb,
-				   timeouts[UDP_CT_REPLIED]);
+		unsigned long extra = timeouts[UDP_CT_UNREPLIED];
+
+		/* Still active after two seconds? Extend timeout. */
+		if (time_after(jiffies, ct->proto.udp.stream_ts))
+			extra = timeouts[UDP_CT_REPLIED];
+
+		nf_ct_refresh_acct(ct, ctinfo, skb, extra);
+
 		/* Also, more likely to be important, and not a probe */
 		if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
 			nf_conntrack_event_cache(IPCT_ASSURED, ct);
-- 
cgit v1.2.3


From 294304e4c522d797b7ea8200ab74354843fa68e9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 00:05:29 +0100
Subject: netfilter: conntrack: udp: set stream timeout to 2 minutes

We have no explicit signal when a UDP stream has terminated, peers just
stop sending.

For suspected stream connections a timeout of two minutes is sane to keep
NAT mapping alive a while longer.

It matches tcp conntracks 'timewait' default timeout value.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 Documentation/networking/nf_conntrack-sysctl.txt | 2 +-
 net/netfilter/nf_conntrack_proto_udp.c           | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/networking/nf_conntrack-sysctl.txt b/Documentation/networking/nf_conntrack-sysctl.txt
index 1669dc2419fd..e69b2e6a4a29 100644
--- a/Documentation/networking/nf_conntrack-sysctl.txt
+++ b/Documentation/networking/nf_conntrack-sysctl.txt
@@ -157,7 +157,7 @@ nf_conntrack_udp_timeout - INTEGER (seconds)
 	default 30
 
 nf_conntrack_udp_timeout_stream - INTEGER (seconds)
-	default 180
+	default 120
 
 	This extended timeout will be used in case there is an UDP stream
 	detected.
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 9f2e05adba69..b4f5d5e82031 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -29,7 +29,7 @@
 
 static const unsigned int udp_timeouts[UDP_CT_MAX] = {
 	[UDP_CT_UNREPLIED]	= 30*HZ,
-	[UDP_CT_REPLIED]	= 180*HZ,
+	[UDP_CT_REPLIED]	= 120*HZ,
 };
 
 static unsigned int *udp_get_timeouts(struct net *net)
-- 
cgit v1.2.3


From f40be47a3e409724104d370385817d90215149b4 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 19:42:23 +0000
Subject: mlxsw: spectrum_router: Do not force specific configuration order

In symmetric routing, the only two members in the VLAN corresponding to
the L3 VNI are the router port and the VXLAN tunnel.

In case the VXLAN device is already enslaved to the bridge and only
later the VLAN interface is configured, the tunnel will not be
offloaded.

The reason for this is that when the router interface (RIF)
corresponding to the VLAN interface is configured, it calls the core
fid_get() API which does not check if NVE should be enabled on the FID.

Instead, call into the bridge code which will check if NVE should be
enabled on the FID.

This effectively means that the same code path is used to retrieve a FID
when either a local port or a router port joins the FID.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           |  4 ++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c    |  8 ++++++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 14 ++++++++++++++
 3 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index f022e9e24085..a7f8a4611baa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -387,6 +387,10 @@ int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 			       struct netlink_ext_ack *extack);
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 				 const struct net_device *vxlan_dev);
+struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
+					     const struct net_device *br_dev,
+					     u16 vid,
+					     struct netlink_ext_ack *extack);
 extern struct notifier_block mlxsw_sp_switchdev_notifier;
 
 /* spectrum.c */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 673950933dac..96e2904daf57 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -7260,11 +7260,15 @@ static struct mlxsw_sp_fid *
 mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
 			  struct netlink_ext_ack *extack)
 {
+	struct net_device *br_dev = rif->dev;
 	u16 vid;
 	int err;
 
 	if (is_vlan_dev(rif->dev)) {
 		vid = vlan_dev_vlan_id(rif->dev);
+		br_dev = vlan_dev_real_dev(rif->dev);
+		if (WARN_ON(!netif_is_bridge_master(br_dev)))
+			return ERR_PTR(-EINVAL);
 	} else {
 		err = br_vlan_get_pvid(rif->dev, &vid);
 		if (err < 0 || !vid) {
@@ -7273,7 +7277,7 @@ mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
 		}
 	}
 
-	return mlxsw_sp_fid_8021q_get(rif->mlxsw_sp, vid);
+	return mlxsw_sp_bridge_fid_get(rif->mlxsw_sp, br_dev, vid, extack);
 }
 
 static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
@@ -7363,7 +7367,7 @@ static struct mlxsw_sp_fid *
 mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif,
 			 struct netlink_ext_ack *extack)
 {
-	return mlxsw_sp_fid_8021d_get(rif->mlxsw_sp, rif->dev->ifindex);
+	return mlxsw_sp_bridge_fid_get(rif->mlxsw_sp, rif->dev, 0, extack);
 }
 
 static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 4b7ef83c19c4..7d89c8dedb4a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2386,6 +2386,20 @@ void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_fid_put(fid);
 }
 
+struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
+					     const struct net_device *br_dev,
+					     u16 vid,
+					     struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_bridge_device *bridge_device;
+
+	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
+	if (WARN_ON(!bridge_device))
+		return ERR_PTR(-EINVAL);
+
+	return bridge_device->ops->fid_get(bridge_device, vid, extack);
+}
+
 static void
 mlxsw_sp_switchdev_vxlan_addr_convert(const union vxlan_addr *vxlan_addr,
 				      enum mlxsw_sp_l3proto *proto,
-- 
cgit v1.2.3


From 9d15dceb8a36919897d52ec8e4a6e6efa57f9f19 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 19:42:25 +0000
Subject: selftests: mlxsw: Add a test case for L3 VNI

Previous patch added the ability to offload a VXLAN tunnel used for L3
VNI when it is present in the VLAN-aware bridge before the corresponding
VLAN interface is configured. This patch adds a test case to verify
that.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/vxlan.sh | 60 ++++++++++++++++++++++
 1 file changed, 60 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
index ea11535f5a6e..dcf9f4e913e0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
@@ -1021,6 +1021,65 @@ offload_indication_vlan_aware_join_vxlan_last()
 	ip link del dev br0
 }
 
+offload_indication_vlan_aware_l3vni_test()
+{
+	local zmac=00:00:00:00:00:00
+
+	RET=0
+
+	sysctl_set net.ipv6.conf.default.disable_ipv6 1
+	ip link add dev br0 up type bridge mcast_snooping 0 \
+		vlan_filtering 1 vlan_default_pvid 0
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	ip link set dev $swp1 master br0
+
+	# The test will use the offload indication on the FDB entry to
+	# understand if the tunnel is offloaded or not
+	bridge fdb append $zmac dev vxlan0 self dst 192.0.2.1
+
+	ip link set dev vxlan0 master br0
+	bridge vlan add dev vxlan0 vid 10 pvid untagged
+
+	# No local port or router port is member in the VLAN, so tunnel should
+	# not be offloaded
+	bridge fdb show brport vxlan0 | grep $zmac | grep self \
+		| grep -q offload
+	check_fail $? "vxlan tunnel offloaded when should not"
+
+	# Configure a VLAN interface and make sure tunnel is offloaded
+	ip link add link br0 name br10 up type vlan id 10
+	sysctl_set net.ipv6.conf.br10.disable_ipv6 0
+	ip -6 address add 2001:db8:1::1/64 dev br10
+	bridge fdb show brport vxlan0 | grep $zmac | grep self \
+		| grep -q offload
+	check_err $? "vxlan tunnel not offloaded when should"
+
+	# Unlink the VXLAN device, make sure tunnel is no longer offloaded,
+	# then add it back to the bridge and make sure it is offloaded
+	ip link set dev vxlan0 nomaster
+	bridge fdb show brport vxlan0 | grep $zmac | grep self \
+		| grep -q offload
+	check_fail $? "vxlan tunnel offloaded after unlinked from bridge"
+
+	ip link set dev vxlan0 master br0
+	bridge fdb show brport vxlan0 | grep $zmac | grep self \
+		| grep -q offload
+	check_fail $? "vxlan tunnel offloaded despite no matching vid"
+
+	bridge vlan add dev vxlan0 vid 10 pvid untagged
+	bridge fdb show brport vxlan0 | grep $zmac | grep self \
+		| grep -q offload
+	check_err $? "vxlan tunnel not offloaded after adding vid"
+
+	log_test "vxlan - l3 vni"
+
+	ip link del dev vxlan0
+	ip link del dev br0
+	sysctl_restore net.ipv6.conf.default.disable_ipv6
+}
+
 offload_indication_vlan_aware_test()
 {
 	offload_indication_vlan_aware_setup_create
@@ -1031,6 +1090,7 @@ offload_indication_vlan_aware_test()
 	log_info "offload indication - replay & cleanup - vlan aware"
 	offload_indication_vlan_aware_join_vxlan_first
 	offload_indication_vlan_aware_join_vxlan_last
+	offload_indication_vlan_aware_l3vni_test
 }
 
 trap cleanup EXIT
-- 
cgit v1.2.3


From a2d2a20553f0b74a2872fba58a152e93341eddd7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 19:42:26 +0000
Subject: mlxsw: spectrum: Replace hard-coded default VID with a define

Subsequent patches are going to replace the current default VID (1) with
VLAN_N_VID - 1 (4095).

Prepare for this conversion by replacing the hard-coded '1' with a
define.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c           | 14 ++++++++------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           |  2 ++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c    |  8 ++++----
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 11 ++++++-----
 4 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 9bfcb9c060a9..764d849a9c90 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1153,7 +1153,7 @@ struct mlxsw_sp_port_vlan *
 mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 {
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
-	bool untagged = vid == 1;
+	bool untagged = vid == MLXSW_SP_DEFAULT_VID;
 	int err;
 
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
@@ -3042,7 +3042,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	mlxsw_sp_port->dev = dev;
 	mlxsw_sp_port->mlxsw_sp = mlxsw_sp;
 	mlxsw_sp_port->local_port = local_port;
-	mlxsw_sp_port->pvid = 1;
+	mlxsw_sp_port->pvid = MLXSW_SP_DEFAULT_VID;
 	mlxsw_sp_port->split = split;
 	mlxsw_sp_port->mapping.module = module;
 	mlxsw_sp_port->mapping.width = width;
@@ -3181,7 +3181,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_port_nve_init;
 	}
 
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_create(mlxsw_sp_port, 1);
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_create(mlxsw_sp_port,
+						       MLXSW_SP_DEFAULT_VID);
 	if (IS_ERR(mlxsw_sp_port_vlan)) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to create VID 1\n",
 			mlxsw_sp_port->local_port);
@@ -4651,6 +4652,7 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
+	u16 vid = MLXSW_SP_DEFAULT_VID;
 	struct mlxsw_sp_upper *lag;
 	u16 lag_id;
 	u8 port_index;
@@ -4684,7 +4686,7 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	lag->ref_count++;
 
 	/* Port is no longer usable as a router interface */
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, 1);
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
 	if (mlxsw_sp_port_vlan->fid)
 		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
 
@@ -4728,9 +4730,9 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->lagged = 0;
 	lag->ref_count--;
 
-	mlxsw_sp_port_vlan_create(mlxsw_sp_port, 1);
+	mlxsw_sp_port_vlan_create(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
 	/* Make sure untagged frames are allowed to ingress */
-	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
+	mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
 }
 
 static int mlxsw_sp_lag_dist_port_add(struct mlxsw_sp_port *mlxsw_sp_port,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index a7f8a4611baa..a669aed690cb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -25,6 +25,8 @@
 #include "core_acl_flex_actions.h"
 #include "reg.h"
 
+#define MLXSW_SP_DEFAULT_VID 1
+
 #define MLXSW_SP_FID_8021D_MAX 1024
 
 #define MLXSW_SP_MID_MAX 7000
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 96e2904daf57..98e5ffd71b91 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6535,8 +6535,8 @@ static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev,
 	    netif_is_ovs_port(port_dev))
 		return 0;
 
-	return mlxsw_sp_inetaddr_port_vlan_event(port_dev, port_dev, event, 1,
-						 extack);
+	return mlxsw_sp_inetaddr_port_vlan_event(port_dev, port_dev, event,
+						 MLXSW_SP_DEFAULT_VID, extack);
 }
 
 static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
@@ -6569,8 +6569,8 @@ static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
 	if (netif_is_bridge_port(lag_dev))
 		return 0;
 
-	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1,
-					     extack);
+	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event,
+					     MLXSW_SP_DEFAULT_VID, extack);
 }
 
 static int mlxsw_sp_inetaddr_bridge_event(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 7d89c8dedb4a..b3a7cf2cf7d9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1975,13 +1975,14 @@ mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 				struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
+	u16 vid = MLXSW_SP_DEFAULT_VID;
 
 	if (is_vlan_dev(bridge_port->dev)) {
 		NL_SET_ERR_MSG_MOD(extack, "Can not enslave a VLAN device to a VLAN-aware bridge");
 		return -EINVAL;
 	}
 
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, 1);
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
 	if (WARN_ON(!mlxsw_sp_port_vlan))
 		return -EINVAL;
 
@@ -1996,9 +1997,9 @@ mlxsw_sp_bridge_8021q_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
 				 struct mlxsw_sp_bridge_port *bridge_port,
 				 struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	mlxsw_sp_port_vlan_create(mlxsw_sp_port, 1);
+	mlxsw_sp_port_vlan_create(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
 	/* Make sure untagged frames are allowed to ingress */
-	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
+	mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
 }
 
 static int
@@ -2169,7 +2170,7 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 	struct net_device *dev = bridge_port->dev;
 	u16 vid;
 
-	vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 1;
+	vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : MLXSW_SP_DEFAULT_VID;
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
 	if (WARN_ON(!mlxsw_sp_port_vlan))
 		return -EINVAL;
@@ -2196,7 +2197,7 @@ mlxsw_sp_bridge_8021d_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
 	struct net_device *dev = bridge_port->dev;
 	u16 vid;
 
-	vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 1;
+	vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : MLXSW_SP_DEFAULT_VID;
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
 	if (!mlxsw_sp_port_vlan)
 		return;
-- 
cgit v1.2.3


From 262e1ff91c3bc9d6b082c123fc7035c1e6347469 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 19:42:27 +0000
Subject: mlxsw: spectrum: Set PVID during port initialization

Currently, the driver does not set the port's PVID when initializing a
new port. This is because the driver is using VID 1 as PVID which is the
firmware default.

Subsequent patches are going to change the PVID the driver is setting
when initializing a new port.

Prepare for that by explicitly setting the port's PVID.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 764d849a9c90..80028cde00a7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3181,6 +3181,13 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_port_nve_init;
 	}
 
+	err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set PVID\n",
+			mlxsw_sp_port->local_port);
+		goto err_port_pvid_set;
+	}
+
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_create(mlxsw_sp_port,
 						       MLXSW_SP_DEFAULT_VID);
 	if (IS_ERR(mlxsw_sp_port_vlan)) {
@@ -3210,6 +3217,7 @@ err_register_netdev:
 	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
 	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 err_port_vlan_create:
+err_port_pvid_set:
 	mlxsw_sp_port_nve_fini(mlxsw_sp_port);
 err_port_nve_init:
 	mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port);
-- 
cgit v1.2.3


From ab6c3b79ec7b1d10cec411015eb5a7599e2b7e52 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 19:42:29 +0000
Subject: mlxsw: spectrum: Allow controlling destruction of default port VLAN

The function allows flushing all the existing VLAN entries on a port. It
is invoked when a port is destroyed and when it is unlinked from a LAG.
In the latter case, when moving to the new default VLAN, there will not
be a need to destroy the default VLAN entry.

Therefore, add an argument that allows to control whether the default
port VLAN should be destroyed or not. Currently it is always set to
'true'.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 80028cde00a7..c212e803a381 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1140,13 +1140,18 @@ int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin,
 	return 0;
 }
 
-static void mlxsw_sp_port_vlan_flush(struct mlxsw_sp_port *mlxsw_sp_port)
+static void mlxsw_sp_port_vlan_flush(struct mlxsw_sp_port *mlxsw_sp_port,
+				     bool flush_default)
 {
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan, *tmp;
 
 	list_for_each_entry_safe(mlxsw_sp_port_vlan, tmp,
-				 &mlxsw_sp_port->vlans_list, list)
+				 &mlxsw_sp_port->vlans_list, list) {
+		if (!flush_default &&
+		    mlxsw_sp_port_vlan->vid == MLXSW_SP_DEFAULT_VID)
+			continue;
 		mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
+	}
 }
 
 struct mlxsw_sp_port_vlan *
@@ -3258,7 +3263,7 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 	unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
 	mlxsw_sp->ports[local_port] = NULL;
 	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
-	mlxsw_sp_port_vlan_flush(mlxsw_sp_port);
+	mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true);
 	mlxsw_sp_port_nve_fini(mlxsw_sp_port);
 	mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port);
 	mlxsw_sp_port_fids_fini(mlxsw_sp_port);
@@ -4724,7 +4729,7 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
 
 	/* Any VLANs configured on the port are no longer valid */
-	mlxsw_sp_port_vlan_flush(mlxsw_sp_port);
+	mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true);
 	/* Make the LAG and its directly linked uppers leave bridges they
 	 * are memeber in
 	 */
-- 
cgit v1.2.3


From 346fca3b58cbe0505f4328276e46e22ffc9a11d8 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 19:42:30 +0000
Subject: mlxsw: spectrum: Store pointer to default port VLAN in port struct

Subsequent patches will need to access the default port VLAN. Since this
VLAN will exist throughout the lifetime of the port, simply store it in
the port's struct.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index c212e803a381..d74b254a6c52 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3201,6 +3201,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		err = PTR_ERR(mlxsw_sp_port_vlan);
 		goto err_port_vlan_create;
 	}
+	mlxsw_sp_port->default_vlan = mlxsw_sp_port_vlan;
 
 	mlxsw_sp_port_switchdev_init(mlxsw_sp_port);
 	mlxsw_sp->ports[local_port] = mlxsw_sp_port;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index a669aed690cb..4e11915d676a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -242,6 +242,7 @@ struct mlxsw_sp_port {
 	} periodic_hw_stats;
 	struct mlxsw_sp_port_sample *sample;
 	struct list_head vlans_list;
+	struct mlxsw_sp_port_vlan *default_vlan;
 	struct mlxsw_sp_qdisc *root_qdisc;
 	struct mlxsw_sp_qdisc *tclass_qdiscs;
 	unsigned acl_rule_count;
-- 
cgit v1.2.3


From 16f6aceb72e7e27efae092c1020c5f0b312a4745 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 19:42:32 +0000
Subject: mlxsw: spectrum: Add an helper function to cleanup VLAN entries

VLAN entries on a port can be associated with either a bridge VLAN or a
router port. Before the VLAN entry is destroyed these associations need
to be cleaned up.

Currently, this is always invoked from the function which destroys the
VLAN entry, but next patch is going to skip the destruction of the
default entry when a port in unlinked from a LAG.

The above does not mean that the associations should not be cleaned up,
so add a helper that will be invoked from both call sites.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index d74b254a6c52..61848db516c7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1154,6 +1154,15 @@ static void mlxsw_sp_port_vlan_flush(struct mlxsw_sp_port *mlxsw_sp_port,
 	}
 }
 
+static void
+mlxsw_sp_port_vlan_cleanup(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
+{
+	if (mlxsw_sp_port_vlan->bridge_port)
+		mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
+	else if (mlxsw_sp_port_vlan->fid)
+		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
+}
+
 struct mlxsw_sp_port_vlan *
 mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 {
@@ -1191,11 +1200,7 @@ void mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	u16 vid = mlxsw_sp_port_vlan->vid;
 
-	if (mlxsw_sp_port_vlan->bridge_port)
-		mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
-	else if (mlxsw_sp_port_vlan->fid)
-		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
-
+	mlxsw_sp_port_vlan_cleanup(mlxsw_sp_port_vlan);
 	list_del(&mlxsw_sp_port_vlan->list);
 	kfree(mlxsw_sp_port_vlan);
 	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
-- 
cgit v1.2.3


From 0417d25e7dad2ab61a42afb07bb0b9512fd0e6df Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 19:42:33 +0000
Subject: mlxsw: spectrum: Switch to VID 4095 as default VID

There is no need to abuse VID 1 anymore and we can instead use VID 4095
as the default VLAN, which will be configured on the port throughout its
lifetime.

The OVS join / leave functions are changed to enable VIDs 1-4094
(inclusive) instead of 2-4095. This because VID 4095 is now the default
VLAN instead of 1.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c           | 15 ++++++---------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 15 ++++-----------
 3 files changed, 11 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 61848db516c7..0aa8ec402fdc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4670,8 +4670,6 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 				  struct net_device *lag_dev)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
-	u16 vid = MLXSW_SP_DEFAULT_VID;
 	struct mlxsw_sp_upper *lag;
 	u16 lag_id;
 	u8 port_index;
@@ -4705,9 +4703,8 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	lag->ref_count++;
 
 	/* Port is no longer usable as a router interface */
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
-	if (mlxsw_sp_port_vlan->fid)
-		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
+	if (mlxsw_sp_port->default_vlan->fid)
+		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port->default_vlan);
 
 	return 0;
 
@@ -4735,7 +4732,8 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
 
 	/* Any VLANs configured on the port are no longer valid */
-	mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true);
+	mlxsw_sp_port_vlan_flush(mlxsw_sp_port, false);
+	mlxsw_sp_port_vlan_cleanup(mlxsw_sp_port->default_vlan);
 	/* Make the LAG and its directly linked uppers leave bridges they
 	 * are memeber in
 	 */
@@ -4749,7 +4747,6 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->lagged = 0;
 	lag->ref_count--;
 
-	mlxsw_sp_port_vlan_create(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
 	/* Make sure untagged frames are allowed to ingress */
 	mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
 }
@@ -4829,7 +4826,7 @@ static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)
 	err = mlxsw_sp_port_stp_set(mlxsw_sp_port, true);
 	if (err)
 		goto err_port_stp_set;
-	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1,
+	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, 1, VLAN_N_VID - 2,
 				     true, false);
 	if (err)
 		goto err_port_vlan_set;
@@ -4861,7 +4858,7 @@ static void mlxsw_sp_port_ovs_leave(struct mlxsw_sp_port *mlxsw_sp_port)
 		mlxsw_sp_port_vid_learning_set(mlxsw_sp_port,
 					       vid, true);
 
-	mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1,
+	mlxsw_sp_port_vlan_set(mlxsw_sp_port, 1, VLAN_N_VID - 2,
 			       false, false);
 	mlxsw_sp_port_stp_set(mlxsw_sp_port, false);
 	mlxsw_sp_port_vp_mode_set(mlxsw_sp_port, false);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 4e11915d676a..a1c32a81b011 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -25,7 +25,7 @@
 #include "core_acl_flex_actions.h"
 #include "reg.h"
 
-#define MLXSW_SP_DEFAULT_VID 1
+#define MLXSW_SP_DEFAULT_VID (VLAN_N_VID - 1)
 
 #define MLXSW_SP_FID_8021D_MAX 1024
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index b3a7cf2cf7d9..1bd2c6e15f8d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1974,20 +1974,14 @@ mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 				struct mlxsw_sp_port *mlxsw_sp_port,
 				struct netlink_ext_ack *extack)
 {
-	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
-	u16 vid = MLXSW_SP_DEFAULT_VID;
-
 	if (is_vlan_dev(bridge_port->dev)) {
 		NL_SET_ERR_MSG_MOD(extack, "Can not enslave a VLAN device to a VLAN-aware bridge");
 		return -EINVAL;
 	}
 
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
-	if (WARN_ON(!mlxsw_sp_port_vlan))
-		return -EINVAL;
-
-	/* Let VLAN-aware bridge take care of its own VLANs */
-	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
+	/* Port is no longer usable as a router interface */
+	if (mlxsw_sp_port->default_vlan->fid)
+		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port->default_vlan);
 
 	return 0;
 }
@@ -1997,7 +1991,6 @@ mlxsw_sp_bridge_8021q_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
 				 struct mlxsw_sp_bridge_port *bridge_port,
 				 struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	mlxsw_sp_port_vlan_create(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
 	/* Make sure untagged frames are allowed to ingress */
 	mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
 }
@@ -2199,7 +2192,7 @@ mlxsw_sp_bridge_8021d_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
 
 	vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : MLXSW_SP_DEFAULT_VID;
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
-	if (!mlxsw_sp_port_vlan)
+	if (!mlxsw_sp_port_vlan || !mlxsw_sp_port_vlan->bridge_port)
 		return;
 
 	mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
-- 
cgit v1.2.3


From d8a1f7ab2c1fb4ee53c16ad048ad045770d99f14 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 19:42:34 +0000
Subject: mlxsw: spectrum: Remove limitation regarding VID 1

VID 1 is not reserved anymore, so remove the check that prevented the
creation of VLAN devices with this VID over mlxsw ports.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 0aa8ec402fdc..c742a581f0d0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4992,11 +4992,6 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 			NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on an OVS port");
 			return -EINVAL;
 		}
-		if (is_vlan_dev(upper_dev) &&
-		    vlan_dev_vlan_id(upper_dev) == 1) {
-			NL_SET_ERR_MSG_MOD(extack, "Creating a VLAN device with VID 1 is unsupported: VLAN 1 carries untagged traffic");
-			return -EINVAL;
-		}
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
-- 
cgit v1.2.3


From 29b1e34efd39ee9f6bc2db3fafad0e4615f15475 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 19:42:35 +0000
Subject: selftests: mlxsw: Adjust test regarding VID 1

Previous patches made it possible to create VLAN devices with VID 1 over
mlxsw ports. Adjust the test to verify such an operation succeeds.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index 9040bfbddfba..94fdbf215c14 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -255,15 +255,18 @@ bridge_vlan_flags_test()
 
 vlan_1_test()
 {
-	# Test that VLAN 1 cannot be configured, as it is used internally for
-	# untagged traffic. See commit 47bf9df2e820 ("mlxsw: spectrum: Forbid
-	# creation of VLAN 1 over port/LAG") for more details
+	# Test that VLAN 1 can be configured over mlxsw ports. In the past it
+	# was used internally for untagged traffic. See commit 47bf9df2e820
+	# ("mlxsw: spectrum: Forbid creation of VLAN 1 over port/LAG") for more
+	# details
 	RET=0
 
-	ip link add link $swp1 name $swp1.1 type vlan id 1 &> /dev/null
-	check_fail $? "managed to create vlan 1 when should not"
+	ip link add link $swp1 name $swp1.1 type vlan id 1
+	check_err $? "did not manage to create vlan 1 when should"
 
 	log_test "vlan 1"
+
+	ip link del dev $swp1.1
 }
 
 lag_bridge_upper_test()
-- 
cgit v1.2.3


From 03a84ea3d8c537f04b862972e2132dff86a4e93d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 19:42:37 +0000
Subject: selftests: forwarding: Add router test with VID 1

Previous patches made it possible to setup VLAN devices with VID 1 over
mlxsw ports. Verify this functionality actually works by conducting a
simple router test over VID 1.

Adding this test as a generic test since it can be run using veth pairs
and it can also be useful for other physical devices where VID 1 was
considered reserved (knowingly or not).

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/router_vid_1.sh       | 135 +++++++++++++++++++++
 1 file changed, 135 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_vid_1.sh

diff --git a/tools/testing/selftests/net/forwarding/router_vid_1.sh b/tools/testing/selftests/net/forwarding/router_vid_1.sh
new file mode 100755
index 000000000000..a7306c7ac06d
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_vid_1.sh
@@ -0,0 +1,135 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="ping_ipv4 ping_ipv6"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+	vrf_create "vrf-h1"
+	ip link set dev vrf-h1 up
+
+	ip link set dev $h1 up
+	vlan_create $h1 1 vrf-h1 192.0.2.2/24 2001:db8:1::2/64
+
+	ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+	ip route add 2001:db8:2::/64 vrf vrf-h1 nexthop via 2001:db8:1::1
+}
+
+h1_destroy()
+{
+	ip route del 2001:db8:2::/64 vrf vrf-h1
+	ip route del 198.51.100.0/24 vrf vrf-h1
+
+	vlan_destroy $h1 1
+	ip link set dev $h1 down
+
+	ip link set dev vrf-h1 down
+	vrf_destroy "vrf-h1"
+}
+
+h2_create()
+{
+	vrf_create "vrf-h2"
+	ip link set dev vrf-h2 up
+
+	ip link set dev $h2 up
+	vlan_create $h2 1 vrf-h2 198.51.100.2/24 2001:db8:2::2/64
+
+	ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+	ip route add 2001:db8:1::/64 vrf vrf-h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip route del 2001:db8:1::/64 vrf vrf-h2
+	ip route del 192.0.2.0/24 vrf vrf-h2
+
+	vlan_destroy $h2 1
+	ip link set dev $h2 down
+
+	ip link set dev vrf-h2 down
+	vrf_destroy "vrf-h2"
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	ip link add link $rp1 name $rp1.1 up type vlan id 1
+
+	ip address add 192.0.2.1/24 dev $rp1.1
+	ip address add 2001:db8:1::1/64 dev $rp1.1
+
+	ip link set dev $rp2 up
+	ip link add link $rp2 name $rp2.1 up type vlan id 1
+
+	ip address add 198.51.100.1/24 dev $rp2.1
+	ip address add 2001:db8:2::1/64 dev $rp2.1
+}
+
+router_destroy()
+{
+	ip address del 2001:db8:2::1/64 dev $rp2.1
+	ip address del 198.51.100.1/24 dev $rp2.1
+
+	ip link del dev $rp2.1
+	ip link set dev $rp2 down
+
+	ip address del 2001:db8:1::1/64 dev $rp1.1
+	ip address del 192.0.2.1/24 dev $rp1.1
+
+	ip link del dev $rp1.1
+	ip link set dev $rp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1.1 198.51.100.2
+}
+
+ping_ipv6()
+{
+	ping6_test $h1.1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From a0badcc6652f9871a9908d67297f910cba657b0f Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Tue, 18 Dec 2018 21:14:07 +0800
Subject: netfilter: conntrack: register sysctl table for gre

This patch adds two sysctl knobs for GRE:

	net.netfilter.nf_conntrack_gre_timeout = 30
	net.netfilter.nf_conntrack_gre_timeout_stream = 180

Update the Documentation as well.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 Documentation/networking/nf_conntrack-sysctl.txt |  9 +++++
 net/netfilter/nf_conntrack_proto_gre.c           | 42 +++++++++++++++++++++++-
 2 files changed, 50 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/nf_conntrack-sysctl.txt b/Documentation/networking/nf_conntrack-sysctl.txt
index e69b2e6a4a29..f75c2ce6e136 100644
--- a/Documentation/networking/nf_conntrack-sysctl.txt
+++ b/Documentation/networking/nf_conntrack-sysctl.txt
@@ -161,3 +161,12 @@ nf_conntrack_udp_timeout_stream - INTEGER (seconds)
 
 	This extended timeout will be used in case there is an UDP stream
 	detected.
+
+nf_conntrack_gre_timeout - INTEGER (seconds)
+	default 30
+
+nf_conntrack_gre_timeout_stream - INTEGER (seconds)
+	default 180
+
+	This extended timeout will be used in case there is an GRE stream
+	detected.
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 9b48dc8b4b88..d5e76bc37b89 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -332,9 +332,49 @@ gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = {
 };
 #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table gre_sysctl_table[] = {
+	{
+		.procname       = "nf_conntrack_gre_timeout",
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec_jiffies,
+	},
+	{
+		.procname       = "nf_conntrack_gre_timeout_stream",
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec_jiffies,
+	},
+	{}
+};
+#endif
+
+static int gre_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *nf,
+				    struct netns_proto_gre *net_gre)
+{
+#ifdef CONFIG_SYSCTL
+	int i;
+
+	if (nf->ctl_table)
+		return 0;
+
+	nf->ctl_table = kmemdup(gre_sysctl_table,
+				sizeof(gre_sysctl_table),
+				GFP_KERNEL);
+	if (!nf->ctl_table)
+		return -ENOMEM;
+
+	for (i = 0; i < GRE_CT_MAX; i++)
+		nf->ctl_table[i].data = &net_gre->gre_timeouts[i];
+#endif
+	return 0;
+}
+
 static int gre_init_net(struct net *net)
 {
 	struct netns_proto_gre *net_gre = gre_pernet(net);
+	struct nf_proto_net *nf = &net_gre->nf;
 	int i;
 
 	rwlock_init(&net_gre->keymap_lock);
@@ -342,7 +382,7 @@ static int gre_init_net(struct net *net)
 	for (i = 0; i < GRE_CT_MAX; i++)
 		net_gre->gre_timeouts[i] = gre_timeouts[i];
 
-	return 0;
+	return gre_kmemdup_sysctl_table(net, nf, net_gre);
 }
 
 /* protocol helper struct */
-- 
cgit v1.2.3


From 4b216e21cfca77132ef0215f553eda91eb1d038b Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 23:04:45 +0100
Subject: netfilter: conntrack: un-export seq_print_acct

Only one caller, just place it where its needed.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_acct.h |  3 ---
 net/netfilter/nf_conntrack_acct.c         | 19 -------------------
 net/netfilter/nf_conntrack_standalone.c   | 18 ++++++++++++++++++
 3 files changed, 18 insertions(+), 22 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h
index 79d8d16732b4..ae5a1c37387e 100644
--- a/include/net/netfilter/nf_conntrack_acct.h
+++ b/include/net/netfilter/nf_conntrack_acct.h
@@ -46,9 +46,6 @@ struct nf_conn_acct *nf_ct_acct_ext_add(struct nf_conn *ct, gfp_t gfp)
 	return acct;
 };
 
-unsigned int seq_print_acct(struct seq_file *s, const struct nf_conn *ct,
-			    int dir);
-
 /* Check if connection tracking accounting is enabled */
 static inline bool nf_ct_acct_enabled(struct net *net)
 {
diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c
index 1d66de5151b2..a7ad0e19e0de 100644
--- a/net/netfilter/nf_conntrack_acct.c
+++ b/net/netfilter/nf_conntrack_acct.c
@@ -38,25 +38,6 @@ static struct ctl_table acct_sysctl_table[] = {
 };
 #endif /* CONFIG_SYSCTL */
 
-unsigned int
-seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir)
-{
-	struct nf_conn_acct *acct;
-	struct nf_conn_counter *counter;
-
-	acct = nf_conn_acct_find(ct);
-	if (!acct)
-		return 0;
-
-	counter = acct->counter;
-	seq_printf(s, "packets=%llu bytes=%llu ",
-		   (unsigned long long)atomic64_read(&counter[dir].packets),
-		   (unsigned long long)atomic64_read(&counter[dir].bytes));
-
-	return 0;
-};
-EXPORT_SYMBOL_GPL(seq_print_acct);
-
 static const struct nf_ct_ext_type acct_extend = {
 	.len	= sizeof(struct nf_conn_acct),
 	.align	= __alignof__(struct nf_conn_acct),
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 463d17d349c1..feeff346f946 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -267,6 +267,24 @@ static const char* l4proto_name(u16 proto)
 	return "unknown";
 }
 
+static unsigned int
+seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir)
+{
+	struct nf_conn_acct *acct;
+	struct nf_conn_counter *counter;
+
+	acct = nf_conn_acct_find(ct);
+	if (!acct)
+		return 0;
+
+	counter = acct->counter;
+	seq_printf(s, "packets=%llu bytes=%llu ",
+		   (unsigned long long)atomic64_read(&counter[dir].packets),
+		   (unsigned long long)atomic64_read(&counter[dir].bytes));
+
+	return 0;
+}
+
 /* return 0 on success, 1 in case of error */
 static int ct_seq_show(struct seq_file *s, void *v)
 {
-- 
cgit v1.2.3


From 4a65798a94089f31883eee705f580e4b2d734ecf Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 23:04:46 +0100
Subject: netfilter: conntrack: add mnemonics for sysctl table

Its a bit hard to see what table[3] really lines up with, so add
human-readable mnemonics and use them for initialisation.

This makes it easier to see e.g. which sysctls are not exported to
unprivileged userns.

objdiff shows no changes.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_standalone.c | 31 ++++++++++++++++++++-----------
 1 file changed, 20 insertions(+), 11 deletions(-)

diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index feeff346f946..f9fa825ddc62 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -532,36 +532,45 @@ nf_conntrack_hash_sysctl(struct ctl_table *table, int write,
 
 static struct ctl_table_header *nf_ct_netfilter_header;
 
+enum nf_ct_sysctl_index {
+	NF_SYSCTL_CT_MAX,
+	NF_SYSCTL_CT_COUNT,
+	NF_SYSCTL_CT_BUCKETS,
+	NF_SYSCTL_CT_CHECKSUM,
+	NF_SYSCTL_CT_LOG_INVALID,
+	NF_SYSCTL_CT_EXPECT_MAX,
+};
+
 static struct ctl_table nf_ct_sysctl_table[] = {
-	{
+	[NF_SYSCTL_CT_MAX] = {
 		.procname	= "nf_conntrack_max",
 		.data		= &nf_conntrack_max,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
+	[NF_SYSCTL_CT_COUNT] = {
 		.procname	= "nf_conntrack_count",
 		.data		= &init_net.ct.count,
 		.maxlen		= sizeof(int),
 		.mode		= 0444,
 		.proc_handler	= proc_dointvec,
 	},
-	{
+	[NF_SYSCTL_CT_BUCKETS] = {
 		.procname       = "nf_conntrack_buckets",
 		.data           = &nf_conntrack_htable_size_user,
 		.maxlen         = sizeof(unsigned int),
 		.mode           = 0644,
 		.proc_handler   = nf_conntrack_hash_sysctl,
 	},
-	{
+	[NF_SYSCTL_CT_CHECKSUM] = {
 		.procname	= "nf_conntrack_checksum",
 		.data		= &init_net.ct.sysctl_checksum,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
+	[NF_SYSCTL_CT_LOG_INVALID] = {
 		.procname	= "nf_conntrack_log_invalid",
 		.data		= &init_net.ct.sysctl_log_invalid,
 		.maxlen		= sizeof(unsigned int),
@@ -570,7 +579,7 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.extra1		= &log_invalid_proto_min,
 		.extra2		= &log_invalid_proto_max,
 	},
-	{
+	[NF_SYSCTL_CT_EXPECT_MAX] = {
 		.procname	= "nf_conntrack_expect_max",
 		.data		= &nf_ct_expect_max,
 		.maxlen		= sizeof(int),
@@ -600,16 +609,16 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 	if (!table)
 		goto out_kmemdup;
 
-	table[1].data = &net->ct.count;
-	table[3].data = &net->ct.sysctl_checksum;
-	table[4].data = &net->ct.sysctl_log_invalid;
+	table[NF_SYSCTL_CT_COUNT].data = &net->ct.count;
+	table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum;
+	table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid;
 
 	/* Don't export sysctls to unprivileged users */
 	if (net->user_ns != &init_user_ns)
-		table[0].procname = NULL;
+		table[NF_SYSCTL_CT_MAX].procname = NULL;
 
 	if (!net_eq(&init_net, net))
-		table[2].mode = 0444;
+		table[NF_SYSCTL_CT_BUCKETS].mode = 0444;
 
 	net->ct.sysctl_header = register_net_sysctl(net, "net/netfilter", table);
 	if (!net->ct.sysctl_header)
-- 
cgit v1.2.3


From d912dec124288553c734e25fef3ecfef92f894db Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 23:04:47 +0100
Subject: netfilter: conntrack: merge acct and helper sysctl table with main
 one

Needless copy&paste, just handle all in one.  Next patch will handle
acct and timestamp, which have similar functions.

Intentionally leaves cruft behind, will be cleaned up in a followup
patch.

The obsolete sysctl pointers in netns_ct struct are left in place and
removed in a single change, as changes to netns trigger rebuild of
almost all files.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_acct.c       | 65 +--------------------------------
 net/netfilter/nf_conntrack_helper.c     | 64 +-------------------------------
 net/netfilter/nf_conntrack_standalone.c | 21 ++++++++++-
 3 files changed, 22 insertions(+), 128 deletions(-)

diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c
index a7ad0e19e0de..89c58946ec61 100644
--- a/net/netfilter/nf_conntrack_acct.c
+++ b/net/netfilter/nf_conntrack_acct.c
@@ -25,83 +25,20 @@ static bool nf_ct_acct __read_mostly;
 module_param_named(acct, nf_ct_acct, bool, 0644);
 MODULE_PARM_DESC(acct, "Enable connection tracking flow accounting.");
 
-#ifdef CONFIG_SYSCTL
-static struct ctl_table acct_sysctl_table[] = {
-	{
-		.procname	= "nf_conntrack_acct",
-		.data		= &init_net.ct.sysctl_acct,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{}
-};
-#endif /* CONFIG_SYSCTL */
-
 static const struct nf_ct_ext_type acct_extend = {
 	.len	= sizeof(struct nf_conn_acct),
 	.align	= __alignof__(struct nf_conn_acct),
 	.id	= NF_CT_EXT_ACCT,
 };
 
-#ifdef CONFIG_SYSCTL
-static int nf_conntrack_acct_init_sysctl(struct net *net)
-{
-	struct ctl_table *table;
-
-	table = kmemdup(acct_sysctl_table, sizeof(acct_sysctl_table),
-			GFP_KERNEL);
-	if (!table)
-		goto out;
-
-	table[0].data = &net->ct.sysctl_acct;
-
-	/* Don't export sysctls to unprivileged users */
-	if (net->user_ns != &init_user_ns)
-		table[0].procname = NULL;
-
-	net->ct.acct_sysctl_header = register_net_sysctl(net, "net/netfilter",
-							 table);
-	if (!net->ct.acct_sysctl_header) {
-		pr_err("can't register to sysctl\n");
-		goto out_register;
-	}
-	return 0;
-
-out_register:
-	kfree(table);
-out:
-	return -ENOMEM;
-}
-
-static void nf_conntrack_acct_fini_sysctl(struct net *net)
-{
-	struct ctl_table *table;
-
-	table = net->ct.acct_sysctl_header->ctl_table_arg;
-	unregister_net_sysctl_table(net->ct.acct_sysctl_header);
-	kfree(table);
-}
-#else
-static int nf_conntrack_acct_init_sysctl(struct net *net)
-{
-	return 0;
-}
-
-static void nf_conntrack_acct_fini_sysctl(struct net *net)
-{
-}
-#endif
-
 int nf_conntrack_acct_pernet_init(struct net *net)
 {
 	net->ct.sysctl_acct = nf_ct_acct;
-	return nf_conntrack_acct_init_sysctl(net);
+	return 0;
 }
 
 void nf_conntrack_acct_pernet_fini(struct net *net)
 {
-	nf_conntrack_acct_fini_sysctl(net);
 }
 
 int nf_conntrack_acct_init(void)
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index e24b762ffa1d..8b6fab94501d 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -42,67 +42,6 @@ module_param_named(nf_conntrack_helper, nf_ct_auto_assign_helper, bool, 0644);
 MODULE_PARM_DESC(nf_conntrack_helper,
 		 "Enable automatic conntrack helper assignment (default 0)");
 
-#ifdef CONFIG_SYSCTL
-static struct ctl_table helper_sysctl_table[] = {
-	{
-		.procname	= "nf_conntrack_helper",
-		.data		= &init_net.ct.sysctl_auto_assign_helper,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{}
-};
-
-static int nf_conntrack_helper_init_sysctl(struct net *net)
-{
-	struct ctl_table *table;
-
-	table = kmemdup(helper_sysctl_table, sizeof(helper_sysctl_table),
-			GFP_KERNEL);
-	if (!table)
-		goto out;
-
-	table[0].data = &net->ct.sysctl_auto_assign_helper;
-
-	/* Don't export sysctls to unprivileged users */
-	if (net->user_ns != &init_user_ns)
-		table[0].procname = NULL;
-
-	net->ct.helper_sysctl_header =
-		register_net_sysctl(net, "net/netfilter", table);
-
-	if (!net->ct.helper_sysctl_header) {
-		pr_err("nf_conntrack_helper: can't register to sysctl.\n");
-		goto out_register;
-	}
-	return 0;
-
-out_register:
-	kfree(table);
-out:
-	return -ENOMEM;
-}
-
-static void nf_conntrack_helper_fini_sysctl(struct net *net)
-{
-	struct ctl_table *table;
-
-	table = net->ct.helper_sysctl_header->ctl_table_arg;
-	unregister_net_sysctl_table(net->ct.helper_sysctl_header);
-	kfree(table);
-}
-#else
-static int nf_conntrack_helper_init_sysctl(struct net *net)
-{
-	return 0;
-}
-
-static void nf_conntrack_helper_fini_sysctl(struct net *net)
-{
-}
-#endif /* CONFIG_SYSCTL */
-
 /* Stupid hash, but collision free for the default registrations of the
  * helpers currently in the kernel. */
 static unsigned int helper_hash(const struct nf_conntrack_tuple *tuple)
@@ -537,12 +476,11 @@ int nf_conntrack_helper_pernet_init(struct net *net)
 {
 	net->ct.auto_assign_helper_warned = false;
 	net->ct.sysctl_auto_assign_helper = nf_ct_auto_assign_helper;
-	return nf_conntrack_helper_init_sysctl(net);
+	return 0;
 }
 
 void nf_conntrack_helper_pernet_fini(struct net *net)
 {
-	nf_conntrack_helper_fini_sysctl(net);
 }
 
 int nf_conntrack_helper_init(void)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index f9fa825ddc62..9e2d9d5d824d 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -539,6 +539,8 @@ enum nf_ct_sysctl_index {
 	NF_SYSCTL_CT_CHECKSUM,
 	NF_SYSCTL_CT_LOG_INVALID,
 	NF_SYSCTL_CT_EXPECT_MAX,
+	NF_SYSCTL_CT_ACCT,
+	NF_SYSCTL_CT_HELPER,
 };
 
 static struct ctl_table nf_ct_sysctl_table[] = {
@@ -586,6 +588,20 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	[NF_SYSCTL_CT_ACCT] = {
+		.procname	= "nf_conntrack_acct",
+		.data		= &init_net.ct.sysctl_acct,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	[NF_SYSCTL_CT_HELPER] = {
+		.procname	= "nf_conntrack_helper",
+		.data		= &init_net.ct.sysctl_auto_assign_helper,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{ }
 };
 
@@ -614,8 +630,11 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 	table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid;
 
 	/* Don't export sysctls to unprivileged users */
-	if (net->user_ns != &init_user_ns)
+	if (net->user_ns != &init_user_ns) {
 		table[NF_SYSCTL_CT_MAX].procname = NULL;
+		table[NF_SYSCTL_CT_ACCT].procname = NULL;
+		table[NF_SYSCTL_CT_HELPER].procname = NULL;
+	}
 
 	if (!net_eq(&init_net, net))
 		table[NF_SYSCTL_CT_BUCKETS].mode = 0444;
-- 
cgit v1.2.3


From cb2833ed0044f910877b810077bc6da2ac5f09a2 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 23:04:48 +0100
Subject: netfilter: conntrack: merge ecache and timestamp sysctl tables with
 main one

Similar to previous change, this time for eache and timestamp.
Unlike helper and acct, these can be disabled at build time, so they
need ifdef guards.

Next patch will remove a few (now obsolete) functions.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_ecache.c     | 65 +--------------------------------
 net/netfilter/nf_conntrack_standalone.c | 33 +++++++++++++++++
 net/netfilter/nf_conntrack_timestamp.c  | 65 +--------------------------------
 3 files changed, 35 insertions(+), 128 deletions(-)

diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index c11822a7d2bf..75118b75aa50 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -336,85 +336,22 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier);
 #define NF_CT_EVENTS_DEFAULT 1
 static int nf_ct_events __read_mostly = NF_CT_EVENTS_DEFAULT;
 
-#ifdef CONFIG_SYSCTL
-static struct ctl_table event_sysctl_table[] = {
-	{
-		.procname	= "nf_conntrack_events",
-		.data		= &init_net.ct.sysctl_events,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{}
-};
-#endif /* CONFIG_SYSCTL */
-
 static const struct nf_ct_ext_type event_extend = {
 	.len	= sizeof(struct nf_conntrack_ecache),
 	.align	= __alignof__(struct nf_conntrack_ecache),
 	.id	= NF_CT_EXT_ECACHE,
 };
 
-#ifdef CONFIG_SYSCTL
-static int nf_conntrack_event_init_sysctl(struct net *net)
-{
-	struct ctl_table *table;
-
-	table = kmemdup(event_sysctl_table, sizeof(event_sysctl_table),
-			GFP_KERNEL);
-	if (!table)
-		goto out;
-
-	table[0].data = &net->ct.sysctl_events;
-
-	/* Don't export sysctls to unprivileged users */
-	if (net->user_ns != &init_user_ns)
-		table[0].procname = NULL;
-
-	net->ct.event_sysctl_header =
-		register_net_sysctl(net, "net/netfilter", table);
-	if (!net->ct.event_sysctl_header) {
-		pr_err("can't register to sysctl\n");
-		goto out_register;
-	}
-	return 0;
-
-out_register:
-	kfree(table);
-out:
-	return -ENOMEM;
-}
-
-static void nf_conntrack_event_fini_sysctl(struct net *net)
-{
-	struct ctl_table *table;
-
-	table = net->ct.event_sysctl_header->ctl_table_arg;
-	unregister_net_sysctl_table(net->ct.event_sysctl_header);
-	kfree(table);
-}
-#else
-static int nf_conntrack_event_init_sysctl(struct net *net)
-{
-	return 0;
-}
-
-static void nf_conntrack_event_fini_sysctl(struct net *net)
-{
-}
-#endif /* CONFIG_SYSCTL */
-
 int nf_conntrack_ecache_pernet_init(struct net *net)
 {
 	net->ct.sysctl_events = nf_ct_events;
 	INIT_DELAYED_WORK(&net->ct.ecache_dwork, ecache_work);
-	return nf_conntrack_event_init_sysctl(net);
+	return 0;
 }
 
 void nf_conntrack_ecache_pernet_fini(struct net *net)
 {
 	cancel_delayed_work_sync(&net->ct.ecache_dwork);
-	nf_conntrack_event_fini_sysctl(net);
 }
 
 int nf_conntrack_ecache_init(void)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 9e2d9d5d824d..b6177fd73304 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -541,6 +541,12 @@ enum nf_ct_sysctl_index {
 	NF_SYSCTL_CT_EXPECT_MAX,
 	NF_SYSCTL_CT_ACCT,
 	NF_SYSCTL_CT_HELPER,
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	NF_SYSCTL_CT_EVENTS,
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	NF_SYSCTL_CT_TIMESTAMP,
+#endif
 };
 
 static struct ctl_table nf_ct_sysctl_table[] = {
@@ -602,6 +608,24 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	[NF_SYSCTL_CT_EVENTS] = {
+		.procname	= "nf_conntrack_events",
+		.data		= &init_net.ct.sysctl_events,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	[NF_SYSCTL_CT_TIMESTAMP] = {
+		.procname	= "nf_conntrack_timestamp",
+		.data		= &init_net.ct.sysctl_tstamp,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#endif
 	{ }
 };
 
@@ -628,12 +652,21 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 	table[NF_SYSCTL_CT_COUNT].data = &net->ct.count;
 	table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum;
 	table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid;
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	table[NF_SYSCTL_CT_EVENTS].data = &net->ct.sysctl_events;
+#endif
 
 	/* Don't export sysctls to unprivileged users */
 	if (net->user_ns != &init_user_ns) {
 		table[NF_SYSCTL_CT_MAX].procname = NULL;
 		table[NF_SYSCTL_CT_ACCT].procname = NULL;
 		table[NF_SYSCTL_CT_HELPER].procname = NULL;
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+		table[NF_SYSCTL_CT_TIMESTAMP].procname = NULL;
+#endif
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+		table[NF_SYSCTL_CT_EVENTS].procname = NULL;
+#endif
 	}
 
 	if (!net_eq(&init_net, net))
diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c
index 56766cb26e40..bae151d93bea 100644
--- a/net/netfilter/nf_conntrack_timestamp.c
+++ b/net/netfilter/nf_conntrack_timestamp.c
@@ -22,83 +22,20 @@ static bool nf_ct_tstamp __read_mostly;
 module_param_named(tstamp, nf_ct_tstamp, bool, 0644);
 MODULE_PARM_DESC(tstamp, "Enable connection tracking flow timestamping.");
 
-#ifdef CONFIG_SYSCTL
-static struct ctl_table tstamp_sysctl_table[] = {
-	{
-		.procname	= "nf_conntrack_timestamp",
-		.data		= &init_net.ct.sysctl_tstamp,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{}
-};
-#endif /* CONFIG_SYSCTL */
-
 static const struct nf_ct_ext_type tstamp_extend = {
 	.len	= sizeof(struct nf_conn_tstamp),
 	.align	= __alignof__(struct nf_conn_tstamp),
 	.id	= NF_CT_EXT_TSTAMP,
 };
 
-#ifdef CONFIG_SYSCTL
-static int nf_conntrack_tstamp_init_sysctl(struct net *net)
-{
-	struct ctl_table *table;
-
-	table = kmemdup(tstamp_sysctl_table, sizeof(tstamp_sysctl_table),
-			GFP_KERNEL);
-	if (!table)
-		goto out;
-
-	table[0].data = &net->ct.sysctl_tstamp;
-
-	/* Don't export sysctls to unprivileged users */
-	if (net->user_ns != &init_user_ns)
-		table[0].procname = NULL;
-
-	net->ct.tstamp_sysctl_header = register_net_sysctl(net,	"net/netfilter",
-							   table);
-	if (!net->ct.tstamp_sysctl_header) {
-		pr_err("can't register to sysctl\n");
-		goto out_register;
-	}
-	return 0;
-
-out_register:
-	kfree(table);
-out:
-	return -ENOMEM;
-}
-
-static void nf_conntrack_tstamp_fini_sysctl(struct net *net)
-{
-	struct ctl_table *table;
-
-	table = net->ct.tstamp_sysctl_header->ctl_table_arg;
-	unregister_net_sysctl_table(net->ct.tstamp_sysctl_header);
-	kfree(table);
-}
-#else
-static int nf_conntrack_tstamp_init_sysctl(struct net *net)
-{
-	return 0;
-}
-
-static void nf_conntrack_tstamp_fini_sysctl(struct net *net)
-{
-}
-#endif
-
 int nf_conntrack_tstamp_pernet_init(struct net *net)
 {
 	net->ct.sysctl_tstamp = nf_ct_tstamp;
-	return nf_conntrack_tstamp_init_sysctl(net);
+	return 0;
 }
 
 void nf_conntrack_tstamp_pernet_fini(struct net *net)
 {
-	nf_conntrack_tstamp_fini_sysctl(net);
 }
 
 int nf_conntrack_tstamp_init(void)
-- 
cgit v1.2.3


From fc3893fd5cfc3c654ae4b9c8d7ee39ea70e4bdc6 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 23:04:49 +0100
Subject: netfilter: conntrack: remove empty pernet fini stubs

after moving sysctl handling into single place, the init functions
can't fail anymore and some of the fini functions are empty.

Remove them and change return type to void.
This also simplifies error unwinding in conntrack module init path.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_acct.h      |  3 +--
 include/net/netfilter/nf_conntrack_ecache.h    |  7 ++-----
 include/net/netfilter/nf_conntrack_helper.h    |  3 +--
 include/net/netfilter/nf_conntrack_timestamp.h | 13 ++----------
 net/netfilter/nf_conntrack_acct.c              |  7 +------
 net/netfilter/nf_conntrack_core.c              | 28 ++++++--------------------
 net/netfilter/nf_conntrack_ecache.c            |  3 +--
 net/netfilter/nf_conntrack_helper.c            |  7 +------
 net/netfilter/nf_conntrack_timestamp.c         |  7 +------
 9 files changed, 16 insertions(+), 62 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h
index ae5a1c37387e..bc6745d3010e 100644
--- a/include/net/netfilter/nf_conntrack_acct.h
+++ b/include/net/netfilter/nf_conntrack_acct.h
@@ -58,8 +58,7 @@ static inline void nf_ct_set_acct(struct net *net, bool enable)
 	net->ct.sysctl_acct = enable;
 }
 
-int nf_conntrack_acct_pernet_init(struct net *net);
-void nf_conntrack_acct_pernet_fini(struct net *net);
+void nf_conntrack_acct_pernet_init(struct net *net);
 
 int nf_conntrack_acct_init(void);
 void nf_conntrack_acct_fini(void);
diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index 3f1ce9a8776e..52b44192b43f 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -142,7 +142,7 @@ void nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
 			       struct nf_conntrack_expect *exp,
 			       u32 portid, int report);
 
-int nf_conntrack_ecache_pernet_init(struct net *net);
+void nf_conntrack_ecache_pernet_init(struct net *net);
 void nf_conntrack_ecache_pernet_fini(struct net *net);
 
 int nf_conntrack_ecache_init(void);
@@ -182,10 +182,7 @@ static inline void nf_ct_expect_event_report(enum ip_conntrack_expect_events e,
  					     u32 portid,
  					     int report) {}
 
-static inline int nf_conntrack_ecache_pernet_init(struct net *net)
-{
-	return 0;
-}
+static inline void nf_conntrack_ecache_pernet_init(struct net *net) {}
 
 static inline void nf_conntrack_ecache_pernet_fini(struct net *net)
 {
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 2492120b8097..ec52a8dc32fd 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -124,8 +124,7 @@ static inline void *nfct_help_data(const struct nf_conn *ct)
 	return (void *)help->data;
 }
 
-int nf_conntrack_helper_pernet_init(struct net *net);
-void nf_conntrack_helper_pernet_fini(struct net *net);
+void nf_conntrack_helper_pernet_init(struct net *net);
 
 int nf_conntrack_helper_init(void);
 void nf_conntrack_helper_fini(void);
diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h
index 3b661986be8f..0ed617bf0a3d 100644
--- a/include/net/netfilter/nf_conntrack_timestamp.h
+++ b/include/net/netfilter/nf_conntrack_timestamp.h
@@ -49,21 +49,12 @@ static inline void nf_ct_set_tstamp(struct net *net, bool enable)
 }
 
 #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
-int nf_conntrack_tstamp_pernet_init(struct net *net);
-void nf_conntrack_tstamp_pernet_fini(struct net *net);
+void nf_conntrack_tstamp_pernet_init(struct net *net);
 
 int nf_conntrack_tstamp_init(void);
 void nf_conntrack_tstamp_fini(void);
 #else
-static inline int nf_conntrack_tstamp_pernet_init(struct net *net)
-{
-	return 0;
-}
-
-static inline void nf_conntrack_tstamp_pernet_fini(struct net *net)
-{
-	return;
-}
+static inline void nf_conntrack_tstamp_pernet_init(struct net *net) {}
 
 static inline int nf_conntrack_tstamp_init(void)
 {
diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c
index 89c58946ec61..49e523cc49d0 100644
--- a/net/netfilter/nf_conntrack_acct.c
+++ b/net/netfilter/nf_conntrack_acct.c
@@ -31,14 +31,9 @@ static const struct nf_ct_ext_type acct_extend = {
 	.id	= NF_CT_EXT_ACCT,
 };
 
-int nf_conntrack_acct_pernet_init(struct net *net)
+void nf_conntrack_acct_pernet_init(struct net *net)
 {
 	net->ct.sysctl_acct = nf_ct_acct;
-	return 0;
-}
-
-void nf_conntrack_acct_pernet_fini(struct net *net)
-{
 }
 
 int nf_conntrack_acct_init(void)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index e92e749aff53..e87c21e47efe 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2110,10 +2110,7 @@ i_see_dead_people:
 
 	list_for_each_entry(net, net_exit_list, exit_list) {
 		nf_conntrack_proto_pernet_fini(net);
-		nf_conntrack_helper_pernet_fini(net);
 		nf_conntrack_ecache_pernet_fini(net);
-		nf_conntrack_tstamp_pernet_fini(net);
-		nf_conntrack_acct_pernet_fini(net);
 		nf_conntrack_expect_pernet_fini(net);
 		free_percpu(net->ct.stat);
 		free_percpu(net->ct.pcpu_lists);
@@ -2410,32 +2407,19 @@ int nf_conntrack_init_net(struct net *net)
 	ret = nf_conntrack_expect_pernet_init(net);
 	if (ret < 0)
 		goto err_expect;
-	ret = nf_conntrack_acct_pernet_init(net);
-	if (ret < 0)
-		goto err_acct;
-	ret = nf_conntrack_tstamp_pernet_init(net);
-	if (ret < 0)
-		goto err_tstamp;
-	ret = nf_conntrack_ecache_pernet_init(net);
-	if (ret < 0)
-		goto err_ecache;
-	ret = nf_conntrack_helper_pernet_init(net);
-	if (ret < 0)
-		goto err_helper;
+
+	nf_conntrack_acct_pernet_init(net);
+	nf_conntrack_tstamp_pernet_init(net);
+	nf_conntrack_ecache_pernet_init(net);
+	nf_conntrack_helper_pernet_init(net);
+
 	ret = nf_conntrack_proto_pernet_init(net);
 	if (ret < 0)
 		goto err_proto;
 	return 0;
 
 err_proto:
-	nf_conntrack_helper_pernet_fini(net);
-err_helper:
 	nf_conntrack_ecache_pernet_fini(net);
-err_ecache:
-	nf_conntrack_tstamp_pernet_fini(net);
-err_tstamp:
-	nf_conntrack_acct_pernet_fini(net);
-err_acct:
 	nf_conntrack_expect_pernet_fini(net);
 err_expect:
 	free_percpu(net->ct.stat);
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index 75118b75aa50..3d042f8ff183 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -342,11 +342,10 @@ static const struct nf_ct_ext_type event_extend = {
 	.id	= NF_CT_EXT_ECACHE,
 };
 
-int nf_conntrack_ecache_pernet_init(struct net *net)
+void nf_conntrack_ecache_pernet_init(struct net *net)
 {
 	net->ct.sysctl_events = nf_ct_events;
 	INIT_DELAYED_WORK(&net->ct.ecache_dwork, ecache_work);
-	return 0;
 }
 
 void nf_conntrack_ecache_pernet_fini(struct net *net)
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 8b6fab94501d..274baf1dab87 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -472,15 +472,10 @@ static const struct nf_ct_ext_type helper_extend = {
 	.id	= NF_CT_EXT_HELPER,
 };
 
-int nf_conntrack_helper_pernet_init(struct net *net)
+void nf_conntrack_helper_pernet_init(struct net *net)
 {
 	net->ct.auto_assign_helper_warned = false;
 	net->ct.sysctl_auto_assign_helper = nf_ct_auto_assign_helper;
-	return 0;
-}
-
-void nf_conntrack_helper_pernet_fini(struct net *net)
-{
 }
 
 int nf_conntrack_helper_init(void)
diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c
index bae151d93bea..705b912bd91f 100644
--- a/net/netfilter/nf_conntrack_timestamp.c
+++ b/net/netfilter/nf_conntrack_timestamp.c
@@ -28,14 +28,9 @@ static const struct nf_ct_ext_type tstamp_extend = {
 	.id	= NF_CT_EXT_TSTAMP,
 };
 
-int nf_conntrack_tstamp_pernet_init(struct net *net)
+void nf_conntrack_tstamp_pernet_init(struct net *net)
 {
 	net->ct.sysctl_tstamp = nf_ct_tstamp;
-	return 0;
-}
-
-void nf_conntrack_tstamp_pernet_fini(struct net *net)
-{
 }
 
 int nf_conntrack_tstamp_init(void)
-- 
cgit v1.2.3


From 8527f9df04a8b5f6ee24ae7bdda5a94d73c7d243 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Dec 2018 23:04:50 +0100
Subject: netfilter: netns: shrink netns_ct struct

remove the obsolete sysctl anchors and move auto_assign_helper_warned
to avoid/cover a hole.  Reduces size by 40 bytes on 64 bit.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netns/conntrack.h | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 9795d628a127..51cba0b8adf5 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -97,18 +97,14 @@ struct netns_ct {
 	struct delayed_work ecache_dwork;
 	bool ecache_dwork_pending;
 #endif
+	bool			auto_assign_helper_warned;
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*sysctl_header;
-	struct ctl_table_header	*acct_sysctl_header;
-	struct ctl_table_header	*tstamp_sysctl_header;
-	struct ctl_table_header	*event_sysctl_header;
-	struct ctl_table_header	*helper_sysctl_header;
 #endif
 	unsigned int		sysctl_log_invalid; /* Log invalid packets */
 	int			sysctl_events;
 	int			sysctl_acct;
 	int			sysctl_auto_assign_helper;
-	bool			auto_assign_helper_warned;
 	int			sysctl_tstamp;
 	int			sysctl_checksum;
 
-- 
cgit v1.2.3


From 3a6d528a5e0179b1e8b20033c5cb7384dd7a830d Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 20 Dec 2018 16:14:22 -0800
Subject: vxlan: Correct merge error.

When resolving the conflict wrt. the vxlan_fdb_update call
in vxlan_changelink() I made the last argument false instead
of true.

Fix this.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 3d773634a8e2..5209ee9aac47 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3768,7 +3768,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					       dst->remote_vni,
 					       dst->remote_vni,
 					       dst->remote_ifindex,
-					       NTF_SELF, false);
+					       NTF_SELF, true);
 			if (err) {
 				spin_unlock_bh(&vxlan->hash_lock);
 				return err;
-- 
cgit v1.2.3


From 962ad710f7d64d441c4e02c0e9e5fddd1aeb54b7 Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Wed, 19 Dec 2018 18:59:31 -0800
Subject: net: dsa: microchip: fix unicast frame leak

Port partitioning is done by enabling UNICAST_VLAN_BOUNDARY and changing
the default port membership of 0x7f to other values such that there is
no communication between ports.  In KSZ9477 the member for port 1 is
0x41; port 2, 0x42; port 3, 0x44; port 4, 0x48; port 5, 0x50; and port 7,
0x60.  Port 6 is the host port.

Setting a zero value can be used to stop port from receiving.

However, when UNICAST_VLAN_BOUNDARY is disabled and the unicast addresses
are already learned in the dynamic MAC table, setting zero still allows
devices connected to those ports to communicate.  This does not apply to
multicast and broadcast addresses though.  To prevent these leaks and
make the function of port membership consistent UNICAST_VLAN_BOUNDARY
should never be disabled.

Note that UNICAST_VLAN_BOUNDARY is enabled by default in KSZ9477.

Fixes: b987e98e50ab90e5 ("dsa: add DSA switch driver for Microchip KSZ9477")
Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz9477.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 57a146a0dd4a..89ed059bb576 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -500,13 +500,9 @@ static int ksz9477_port_vlan_filtering(struct dsa_switch *ds, int port,
 	if (flag) {
 		ksz_port_cfg(dev, port, REG_PORT_LUE_CTRL,
 			     PORT_VLAN_LOOKUP_VID_0, true);
-		ksz9477_cfg32(dev, REG_SW_QM_CTRL__4, UNICAST_VLAN_BOUNDARY,
-			      true);
 		ksz_cfg(dev, REG_SW_LUE_CTRL_0, SW_VLAN_ENABLE, true);
 	} else {
 		ksz_cfg(dev, REG_SW_LUE_CTRL_0, SW_VLAN_ENABLE, false);
-		ksz9477_cfg32(dev, REG_SW_QM_CTRL__4, UNICAST_VLAN_BOUNDARY,
-			      false);
 		ksz_port_cfg(dev, port, REG_PORT_LUE_CTRL,
 			     PORT_VLAN_LOOKUP_VID_0, false);
 	}
@@ -1130,6 +1126,10 @@ static int ksz9477_setup(struct dsa_switch *ds)
 		return ret;
 	}
 
+	/* Required for port partitioning. */
+	ksz9477_cfg32(dev, REG_SW_QM_CTRL__4, UNICAST_VLAN_BOUNDARY,
+		      true);
+
 	/* accept packet up to 2000bytes */
 	ksz_cfg(dev, REG_SW_MAC_CTRL_1, SW_LEGAL_PACKET_DISABLE, true);
 
-- 
cgit v1.2.3


From 463561e6b9facf93ef90b65d2c75a80c7262d778 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 20 Dec 2018 16:50:50 +0000
Subject: neighbour: remove stray semicolon

Currently the stray semicolon means that the final term in the addition
is being missed.  Fix this by removing it. Cleans up clang warning:

net/core/neighbour.c:2821:9: warning: expression result unused [-Wunused-value]

Fixes: 82cbb5c631a0 ("neighbour: register rtnl doit handler")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-By: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index fa384f775f1a..763a7b08df67 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2811,7 +2811,7 @@ errout:
 static inline size_t pneigh_nlmsg_size(void)
 {
 	return NLMSG_ALIGN(sizeof(struct ndmsg))
-	       + nla_total_size(MAX_ADDR_LEN); /* NDA_DST */
+	       + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */
 	       + nla_total_size(1); /* NDA_PROTOCOL */
 }
 
-- 
cgit v1.2.3


From 639c1b2625af66501b24c8082231a83d4f5ad56b Mon Sep 17 00:00:00 2001
From: Steen Hegelund <steen.hegelund@microchip.com>
Date: Thu, 20 Dec 2018 14:16:31 +0100
Subject: net: mscc: ocelot: Register poll timeout should be wall time not
 attempts

When doing indirect access in the Ocelot chip, a command is setup,
issued and then we need to poll until the result is ready. The polling
timeout is specified in milliseconds in the datasheet and not in
register access attempts.
It is not a bug on the currently supported platform, but we observed
that the code does not work properly on other platforms that we want to
support as the timing requirements there are different.

Signed-off-by: Steen Hegelund <steen.hegelund@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 55 +++++++++++++++++++-------------------
 1 file changed, 27 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index ea3eec263875..feb9ffced862 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -15,6 +15,7 @@
 #include <linux/netdevice.h>
 #include <linux/phy.h>
 #include <linux/skbuff.h>
+#include <linux/iopoll.h>
 #include <net/arp.h>
 #include <net/netevent.h>
 #include <net/rtnetlink.h>
@@ -22,6 +23,9 @@
 
 #include "ocelot.h"
 
+#define TABLE_UPDATE_SLEEP_US 10
+#define TABLE_UPDATE_TIMEOUT_US 100000
+
 /* MAC table entry types.
  * ENTRYTYPE_NORMAL is subject to aging.
  * ENTRYTYPE_LOCKED is not subject to aging.
@@ -41,23 +45,20 @@ struct ocelot_mact_entry {
 	enum macaccess_entry_type type;
 };
 
-static inline int ocelot_mact_wait_for_completion(struct ocelot *ocelot)
+static inline u32 ocelot_mact_read_macaccess(struct ocelot *ocelot)
 {
-	unsigned int val, timeout = 10;
-
-	/* Wait for the issued mac table command to be completed, or timeout.
-	 * When the command read from  ANA_TABLES_MACACCESS is
-	 * MACACCESS_CMD_IDLE, the issued command completed successfully.
-	 */
-	do {
-		val = ocelot_read(ocelot, ANA_TABLES_MACACCESS);
-		val &= ANA_TABLES_MACACCESS_MAC_TABLE_CMD_M;
-	} while (val != MACACCESS_CMD_IDLE && timeout--);
+	return ocelot_read(ocelot, ANA_TABLES_MACACCESS);
+}
 
-	if (!timeout)
-		return -ETIMEDOUT;
+static inline int ocelot_mact_wait_for_completion(struct ocelot *ocelot)
+{
+	u32 val;
 
-	return 0;
+	return readx_poll_timeout(ocelot_mact_read_macaccess,
+		ocelot, val,
+		(val & ANA_TABLES_MACACCESS_MAC_TABLE_CMD_M) ==
+		MACACCESS_CMD_IDLE,
+		TABLE_UPDATE_SLEEP_US, TABLE_UPDATE_TIMEOUT_US);
 }
 
 static void ocelot_mact_select(struct ocelot *ocelot,
@@ -129,23 +130,21 @@ static void ocelot_mact_init(struct ocelot *ocelot)
 	ocelot_write(ocelot, MACACCESS_CMD_INIT, ANA_TABLES_MACACCESS);
 }
 
-static inline int ocelot_vlant_wait_for_completion(struct ocelot *ocelot)
+static inline u32 ocelot_vlant_read_vlanaccess(struct ocelot *ocelot)
 {
-	unsigned int val, timeout = 10;
-
-	/* Wait for the issued vlan table command to be completed, or timeout.
-	 * When the command read from ANA_TABLES_VLANACCESS is
-	 * VLANACCESS_CMD_IDLE, the issued command completed successfully.
-	 */
-	do {
-		val = ocelot_read(ocelot, ANA_TABLES_VLANACCESS);
-		val &= ANA_TABLES_VLANACCESS_VLAN_TBL_CMD_M;
-	} while (val != ANA_TABLES_VLANACCESS_CMD_IDLE && timeout--);
+	return ocelot_read(ocelot, ANA_TABLES_VLANACCESS);
+}
 
-	if (!timeout)
-		return -ETIMEDOUT;
+static inline int ocelot_vlant_wait_for_completion(struct ocelot *ocelot)
+{
+	u32 val;
 
-	return 0;
+	return readx_poll_timeout(ocelot_vlant_read_vlanaccess,
+		ocelot,
+		val,
+		(val & ANA_TABLES_VLANACCESS_VLAN_TBL_CMD_M) ==
+		ANA_TABLES_VLANACCESS_CMD_IDLE,
+		TABLE_UPDATE_SLEEP_US, TABLE_UPDATE_TIMEOUT_US);
 }
 
 static int ocelot_vlant_set_mask(struct ocelot *ocelot, u16 vid, u32 mask)
-- 
cgit v1.2.3


From 21f9477537059344e4705719137f6695de93b662 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 17:03:27 +0000
Subject: net: ipv4: Set skb->dev for output route resolution

When user requests to resolve an output route, the kernel synthesizes
an skb where the relevant parameters (e.g., source address) are set. The
skb is then passed to ip_route_output_key_hash_rcu() which might call
into the flow dissector in case a multipath route was hit and a nexthop
needs to be selected based on the multipath hash.

Since both 'skb->dev' and 'skb->sk' are not set, a warning is triggered
in the flow dissector [1]. The warning is there to prevent codepaths
from silently falling back to the standard flow dissector instead of the
BPF one.

Therefore, instead of removing the warning, set 'skb->dev' to the
loopback device, as its not used for anything but resolving the correct
namespace.

[1]
WARNING: CPU: 1 PID: 24819 at net/core/flow_dissector.c:764 __skb_flow_dissect+0x314/0x16b0
...
RSP: 0018:ffffa0df41fdf650 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff8bcded232000 RCX: 0000000000000000
RDX: ffffa0df41fdf7e0 RSI: ffffffff98e415a0 RDI: ffff8bcded232000
RBP: ffffa0df41fdf760 R08: 0000000000000000 R09: 0000000000000000
R10: ffffa0df41fdf7e8 R11: ffff8bcdf27a3000 R12: ffffffff98e415a0
R13: ffffa0df41fdf7e0 R14: ffffffff98dd2980 R15: ffffa0df41fdf7e0
FS:  00007f46f6897680(0000) GS:ffff8bcdf7a80000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055933e95f9a0 CR3: 000000021e636000 CR4: 00000000001006e0
Call Trace:
 fib_multipath_hash+0x28c/0x2d0
 ? fib_multipath_hash+0x28c/0x2d0
 fib_select_path+0x241/0x32f
 ? __fib_lookup+0x6a/0xb0
 ip_route_output_key_hash_rcu+0x650/0xa30
 ? __alloc_skb+0x9b/0x1d0
 inet_rtm_getroute+0x3f7/0xb80
 ? __alloc_pages_nodemask+0x11c/0x2c0
 rtnetlink_rcv_msg+0x1d9/0x2f0
 ? rtnl_calcit.isra.24+0x120/0x120
 netlink_rcv_skb+0x54/0x130
 rtnetlink_rcv+0x15/0x20
 netlink_unicast+0x20a/0x2c0
 netlink_sendmsg+0x2d1/0x3d0
 sock_sendmsg+0x39/0x50
 ___sys_sendmsg+0x2a0/0x2f0
 ? filemap_map_pages+0x16b/0x360
 ? __handle_mm_fault+0x108e/0x13d0
 __sys_sendmsg+0x63/0xa0
 ? __sys_sendmsg+0x63/0xa0
 __x64_sys_sendmsg+0x1f/0x30
 do_syscall_64+0x5a/0x120
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: d0e13a1488ad ("flow_dissector: lookup netns by skb->sk if skb->dev is NULL")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c4ddbc5f01fc..ce92f73cf104 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2849,6 +2849,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 			err = -rt->dst.error;
 	} else {
 		fl4.flowi4_iif = LOOPBACK_IFINDEX;
+		skb->dev = net->loopback_dev;
 		rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb);
 		err = 0;
 		if (IS_ERR(rt))
-- 
cgit v1.2.3


From 676f4bb168ca855adb957ad7f470984d9391c320 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 20 Dec 2018 17:03:29 +0000
Subject: selftests: rtnetlink: Add a test case for multipath route get

Without previous patch a warning would be generated upon multipath route
get when FIB multipath hash policy is to use a 5-tuple for multipath
hash calculation.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index c5cbea9b317d..78fc593dfe40 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -205,6 +205,8 @@ kci_test_polrouting()
 
 kci_test_route_get()
 {
+	local hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy)
+
 	ret=0
 
 	ip route get 127.0.0.1 > /dev/null
@@ -223,6 +225,19 @@ kci_test_route_get()
 	check_err $?
 	ip route get 10.23.7.11 from 10.23.7.12 iif "$devdummy" > /dev/null
 	check_err $?
+	ip route add 10.23.8.0/24 \
+		nexthop via 10.23.7.13 dev "$devdummy" \
+		nexthop via 10.23.7.14 dev "$devdummy"
+	check_err $?
+	sysctl -wq net.ipv4.fib_multipath_hash_policy=0
+	ip route get 10.23.8.11 > /dev/null
+	check_err $?
+	sysctl -wq net.ipv4.fib_multipath_hash_policy=1
+	ip route get 10.23.8.11 > /dev/null
+	check_err $?
+	sysctl -wq net.ipv4.fib_multipath_hash_policy="$hash_policy"
+	ip route del 10.23.8.0/24
+	check_err $?
 	ip addr del dev "$devdummy" 10.23.7.11/24
 	check_err $?
 
-- 
cgit v1.2.3


From aa9d6e0f33aea8a1879e7e53fe0e436943f9ce0c Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Thu, 20 Dec 2018 09:52:28 -0800
Subject: linux/netlink.h: drop unnecessary extern prefix

Don't need extern prefix before function prototypes.
Checkpatch has complained about this for a couple of years.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netlink.h | 48 ++++++++++++++++++++++++------------------------
 1 file changed, 24 insertions(+), 24 deletions(-)

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 0b83dbae0a57..4e8add270200 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -34,8 +34,8 @@ struct netlink_skb_parms {
 #define NETLINK_CREDS(skb)	(&NETLINK_CB((skb)).creds)
 
 
-extern void netlink_table_grab(void);
-extern void netlink_table_ungrab(void);
+void netlink_table_grab(void);
+void netlink_table_ungrab(void);
 
 #define NL_CFG_F_NONROOT_RECV	(1 << 0)
 #define NL_CFG_F_NONROOT_SEND	(1 << 1)
@@ -51,7 +51,7 @@ struct netlink_kernel_cfg {
 	bool		(*compare)(struct net *net, struct sock *sk);
 };
 
-extern struct sock *__netlink_kernel_create(struct net *net, int unit,
+struct sock *__netlink_kernel_create(struct net *net, int unit,
 					    struct module *module,
 					    struct netlink_kernel_cfg *cfg);
 static inline struct sock *
@@ -119,24 +119,24 @@ static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack,
 	extack->cookie_len = sizeof(__cookie);
 }
 
-extern void netlink_kernel_release(struct sock *sk);
-extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups);
-extern int netlink_change_ngroups(struct sock *sk, unsigned int groups);
-extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group);
-extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
-			const struct netlink_ext_ack *extack);
-extern int netlink_has_listeners(struct sock *sk, unsigned int group);
-
-extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
-extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid,
-			     __u32 group, gfp_t allocation);
-extern int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
-	__u32 portid, __u32 group, gfp_t allocation,
-	int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data),
-	void *filter_data);
-extern int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code);
-extern int netlink_register_notifier(struct notifier_block *nb);
-extern int netlink_unregister_notifier(struct notifier_block *nb);
+void netlink_kernel_release(struct sock *sk);
+int __netlink_change_ngroups(struct sock *sk, unsigned int groups);
+int netlink_change_ngroups(struct sock *sk, unsigned int groups);
+void __netlink_clear_multicast_users(struct sock *sk, unsigned int group);
+void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
+		 const struct netlink_ext_ack *extack);
+int netlink_has_listeners(struct sock *sk, unsigned int group);
+
+int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
+int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid,
+		      __u32 group, gfp_t allocation);
+int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
+			       __u32 portid, __u32 group, gfp_t allocation,
+			       int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data),
+			       void *filter_data);
+int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code);
+int netlink_register_notifier(struct notifier_block *nb);
+int netlink_unregister_notifier(struct notifier_block *nb);
 
 /* finegrained unicast helpers: */
 struct sock *netlink_getsockbyfilp(struct file *filp);
@@ -212,7 +212,7 @@ struct netlink_dump_control {
 	u16 min_dump_alloc;
 };
 
-extern int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
+int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 				const struct nlmsghdr *nlh,
 				struct netlink_dump_control *control);
 static inline int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
@@ -231,8 +231,8 @@ struct netlink_tap {
 	struct list_head list;
 };
 
-extern int netlink_add_tap(struct netlink_tap *nt);
-extern int netlink_remove_tap(struct netlink_tap *nt);
+int netlink_add_tap(struct netlink_tap *nt);
+int netlink_remove_tap(struct netlink_tap *nt);
 
 bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
 			  struct user_namespace *ns, int cap);
-- 
cgit v1.2.3


From 7fb1b8ca8fa1ee34ffc328f17f78da68c7cc04e6 Mon Sep 17 00:00:00 2001
From: Sam Protsenko <semen.protsenko@linaro.org>
Date: Thu, 20 Dec 2018 20:29:20 +0200
Subject: ppp: Move PFC decompression to PPP generic layer

Extract "Protocol" field decompression code from transport protocols to
PPP generic layer, where it actually belongs. As a consequence, this
patch fixes incorrect place of PFC decompression in L2TP driver (when
it's not PPPOX_BOUND) and also enables this decompression for other
protocols, like PPPoE.

Protocol field decompression also happens in PPP Multilink Protocol
code and in PPP compression protocols implementations (bsd, deflate,
mppe). It looks like there is no easy way to get rid of that, so it was
decided to leave it as is, but provide those cases with appropriate
comments instead.

Changes in v2:
  - Fix the order of checking skb data room and proto decompression
  - Remove "inline" keyword from ppp_decompress_proto()
  - Don't split line before function name
  - Prefix ppp_decompress_proto() function with "__"
  - Add ppp_decompress_proto() function with skb data room checks
  - Add description for introduced functions
  - Fix comments (as per review on mailing list)

Signed-off-by: Sam Protsenko <semen.protsenko@linaro.org>
Reviewed-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_async.c   | 14 +++++------
 drivers/net/ppp/ppp_generic.c | 54 ++++++++++++++++++++++++++++++++++++++++---
 drivers/net/ppp/ppp_synctty.c |  9 ++++----
 drivers/net/ppp/pptp.c        |  5 ----
 net/l2tp/l2tp_ppp.c           |  4 ----
 5 files changed, 62 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index 288cf099876b..b287bb811875 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -770,7 +770,7 @@ process_input_packet(struct asyncppp *ap)
 {
 	struct sk_buff *skb;
 	unsigned char *p;
-	unsigned int len, fcs, proto;
+	unsigned int len, fcs;
 
 	skb = ap->rpkt;
 	if (ap->state & (SC_TOSS | SC_ESCAPE))
@@ -799,14 +799,14 @@ process_input_packet(struct asyncppp *ap)
 			goto err;
 		p = skb_pull(skb, 2);
 	}
-	proto = p[0];
-	if (proto & 1) {
-		/* protocol is compressed */
-		*(u8 *)skb_push(skb, 1) = 0;
-	} else {
+
+	/* If protocol field is not compressed, it can be LCP packet */
+	if (!(p[0] & 0x01)) {
+		unsigned int proto;
+
 		if (skb->len < 2)
 			goto err;
-		proto = (proto << 8) + p[1];
+		proto = (p[0] << 8) + p[1];
 		if (proto == PPP_LCP)
 			async_lcp_peek(ap, p, skb->len, 1);
 	}
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 500bc0027c1b..c708400fff4a 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1965,6 +1965,46 @@ ppp_do_recv(struct ppp *ppp, struct sk_buff *skb, struct channel *pch)
 	ppp_recv_unlock(ppp);
 }
 
+/**
+ * __ppp_decompress_proto - Decompress protocol field, slim version.
+ * @skb: Socket buffer where protocol field should be decompressed. It must have
+ *	 at least 1 byte of head room and 1 byte of linear data. First byte of
+ *	 data must be a protocol field byte.
+ *
+ * Decompress protocol field in PPP header if it's compressed, e.g. when
+ * Protocol-Field-Compression (PFC) was negotiated. No checks w.r.t. skb data
+ * length are done in this function.
+ */
+static void __ppp_decompress_proto(struct sk_buff *skb)
+{
+	if (skb->data[0] & 0x01)
+		*(u8 *)skb_push(skb, 1) = 0x00;
+}
+
+/**
+ * ppp_decompress_proto - Check skb data room and decompress protocol field.
+ * @skb: Socket buffer where protocol field should be decompressed. First byte
+ *	 of data must be a protocol field byte.
+ *
+ * Decompress protocol field in PPP header if it's compressed, e.g. when
+ * Protocol-Field-Compression (PFC) was negotiated. This function also makes
+ * sure that skb data room is sufficient for Protocol field, before and after
+ * decompression.
+ *
+ * Return: true - decompressed successfully, false - not enough room in skb.
+ */
+static bool ppp_decompress_proto(struct sk_buff *skb)
+{
+	/* At least one byte should be present (if protocol is compressed) */
+	if (!pskb_may_pull(skb, 1))
+		return false;
+
+	__ppp_decompress_proto(skb);
+
+	/* Protocol field should occupy 2 bytes when not compressed */
+	return pskb_may_pull(skb, 2);
+}
+
 void
 ppp_input(struct ppp_channel *chan, struct sk_buff *skb)
 {
@@ -1977,7 +2017,7 @@ ppp_input(struct ppp_channel *chan, struct sk_buff *skb)
 	}
 
 	read_lock_bh(&pch->upl);
-	if (!pskb_may_pull(skb, 2)) {
+	if (!ppp_decompress_proto(skb)) {
 		kfree_skb(skb);
 		if (pch->ppp) {
 			++pch->ppp->dev->stats.rx_length_errors;
@@ -2074,6 +2114,9 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
 	if (ppp->flags & SC_MUST_COMP && ppp->rstate & SC_DC_FERROR)
 		goto err;
 
+	/* At this point the "Protocol" field MUST be decompressed, either in
+	 * ppp_input(), ppp_decompress_frame() or in ppp_receive_mp_frame().
+	 */
 	proto = PPP_PROTO(skb);
 	switch (proto) {
 	case PPP_VJC_COMP:
@@ -2245,6 +2288,9 @@ ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb)
 		skb_put(skb, len);
 		skb_pull(skb, 2);	/* pull off the A/C bytes */
 
+		/* Don't call __ppp_decompress_proto() here, but instead rely on
+		 * corresponding algo (mppe/bsd/deflate) to decompress it.
+		 */
 	} else {
 		/* Uncompressed frame - pass to decompressor so it
 		   can update its dictionary if necessary. */
@@ -2290,9 +2336,11 @@ ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch)
 
 	/*
 	 * Do protocol ID decompression on the first fragment of each packet.
+	 * We have to do that here, because ppp_receive_nonmp_frame() expects
+	 * decompressed protocol field.
 	 */
-	if ((PPP_MP_CB(skb)->BEbits & B) && (skb->data[0] & 1))
-		*(u8 *)skb_push(skb, 1) = 0;
+	if (PPP_MP_CB(skb)->BEbits & B)
+		__ppp_decompress_proto(skb);
 
 	/*
 	 * Expand sequence number to 32 bits, making it as close
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index 047f6c68a441..d02ba2494d93 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -709,11 +709,10 @@ ppp_sync_input(struct syncppp *ap, const unsigned char *buf,
 		p = skb_pull(skb, 2);
 	}
 
-	/* decompress protocol field if compressed */
-	if (p[0] & 1) {
-		/* protocol is compressed */
-		*(u8 *)skb_push(skb, 1) = 0;
-	} else if (skb->len < 2)
+	/* PPP packet length should be >= 2 bytes when protocol field is not
+	 * compressed.
+	 */
+	if (!(p[0] & 0x01) && skb->len < 2)
 		goto err;
 
 	/* queue the frame to be processed */
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 67ffe74747a1..8f09edd811e9 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -325,11 +325,6 @@ allow_packet:
 			skb_pull(skb, 2);
 		}
 
-		if ((*skb->data) & 1) {
-			/* protocol is compressed */
-			*(u8 *)skb_push(skb, 1) = 0;
-		}
-
 		skb->ip_summed = CHECKSUM_NONE;
 		skb_set_network_header(skb, skb->head-skb->data);
 		ppp_input(&po->chan, skb);
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index c03c6461f236..04d9946dcdba 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -236,10 +236,6 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
 	    skb->data[1] == PPP_UI)
 		skb_pull(skb, 2);
 
-	/* Decompress protocol field if PFC is enabled */
-	if ((*skb->data) & 0x1)
-		*(u8 *)skb_push(skb, 1) = 0;
-
 	if (sk->sk_state & PPPOX_BOUND) {
 		struct pppox_sock *po;
 
-- 
cgit v1.2.3


From a6ae520defea9986a422032eda7f0bdbb1368a18 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Thu, 20 Dec 2018 10:51:49 -0800
Subject: net: seg6.h: remove an unused #include

A minor code cleanup.

Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/seg6.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/net/seg6.h b/include/net/seg6.h
index 2567941a2f32..8b2dc6869fd1 100644
--- a/include/net/seg6.h
+++ b/include/net/seg6.h
@@ -16,7 +16,6 @@
 
 #include <linux/net.h>
 #include <linux/ipv6.h>
-#include <net/lwtunnel.h>
 #include <linux/seg6.h>
 #include <linux/rhashtable-types.h>
 
-- 
cgit v1.2.3


From 7085f47fcdc599cb387a472e4cd9def739954119 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 20 Dec 2018 16:22:52 -0500
Subject: selftests: expand txtimestamp with cmsg support

Commit 3dd17e63f513 ("sock: accept SO_TIMESTAMPING flags in socket
cmsg") added support for passing tx timestamping options per-call
in sendmsg.

Expand the txtimestamp test with support for this feature.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../networking/timestamping/txtimestamp.c          | 67 +++++++++++++++++-----
 1 file changed, 53 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/networking/timestamping/txtimestamp.c b/tools/testing/selftests/networking/timestamping/txtimestamp.c
index 81a98a240456..ca5fad15a855 100644
--- a/tools/testing/selftests/networking/timestamping/txtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/txtimestamp.c
@@ -73,6 +73,7 @@ static bool cfg_show_payload;
 static bool cfg_do_pktinfo;
 static bool cfg_loop_nodata;
 static bool cfg_no_delay;
+static bool cfg_use_cmsg;
 static uint16_t dest_port = 9000;
 
 static struct sockaddr_in daddr;
@@ -269,8 +270,13 @@ static int recv_errmsg(int fd)
 	return ret == -1;
 }
 
-static void do_test(int family, unsigned int opt)
+static void do_test(int family, unsigned int report_opt)
 {
+	char control[CMSG_SPACE(sizeof(uint32_t))];
+	unsigned int sock_opt;
+	struct cmsghdr *cmsg;
+	struct msghdr msg;
+	struct iovec iov;
 	char *buf;
 	int fd, i, val = 1, total_len;
 
@@ -321,17 +327,22 @@ static void do_test(int family, unsigned int opt)
 		}
 	}
 
-	opt |= SOF_TIMESTAMPING_SOFTWARE |
-	       SOF_TIMESTAMPING_OPT_CMSG |
-	       SOF_TIMESTAMPING_OPT_ID;
+	sock_opt = SOF_TIMESTAMPING_SOFTWARE |
+		   SOF_TIMESTAMPING_OPT_CMSG |
+		   SOF_TIMESTAMPING_OPT_ID;
+
+	if (!cfg_use_cmsg)
+		sock_opt |= report_opt;
+
 	if (cfg_loop_nodata)
-		opt |= SOF_TIMESTAMPING_OPT_TSONLY;
+		sock_opt |= SOF_TIMESTAMPING_OPT_TSONLY;
 
 	if (setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING,
-		       (char *) &opt, sizeof(opt)))
+		       (char *) &sock_opt, sizeof(sock_opt)))
 		error(1, 0, "setsockopt timestamping");
 
 	for (i = 0; i < cfg_num_pkts; i++) {
+		memset(&msg, 0, sizeof(msg));
 		memset(&ts_prev, 0, sizeof(ts_prev));
 		memset(buf, 'a' + i, total_len);
 
@@ -361,14 +372,38 @@ static void do_test(int family, unsigned int opt)
 		}
 
 		print_timestamp_usr();
+
+		iov.iov_base = buf;
+		iov.iov_len = total_len;
+
 		if (cfg_proto != SOCK_STREAM) {
-			if (family == PF_INET)
-				val = sendto(fd, buf, total_len, 0, (void *) &daddr, sizeof(daddr));
-			else
-				val = sendto(fd, buf, total_len, 0, (void *) &daddr6, sizeof(daddr6));
-		} else {
-			val = send(fd, buf, cfg_payload_len, 0);
+			if (family == PF_INET) {
+				msg.msg_name = (void *)&daddr;
+				msg.msg_namelen = sizeof(daddr);
+			} else {
+				msg.msg_name = (void *)&daddr6;
+				msg.msg_namelen = sizeof(daddr6);
+			}
+		}
+
+		msg.msg_iov = &iov;
+		msg.msg_iovlen = 1;
+
+		if (cfg_use_cmsg) {
+			memset(control, 0, sizeof(control));
+
+			msg.msg_control = control;
+			msg.msg_controllen = sizeof(control);
+
+			cmsg = CMSG_FIRSTHDR(&msg);
+			cmsg->cmsg_level = SOL_SOCKET;
+			cmsg->cmsg_type = SO_TIMESTAMPING;
+			cmsg->cmsg_len = CMSG_LEN(sizeof(uint32_t));
+
+			*((uint32_t *) CMSG_DATA(cmsg)) = report_opt;
 		}
+
+		val = sendmsg(fd, &msg, 0);
 		if (val != total_len)
 			error(1, errno, "send");
 
@@ -396,6 +431,7 @@ static void __attribute__((noreturn)) usage(const char *filepath)
 			"  -6:   only IPv6\n"
 			"  -h:   show this message\n"
 			"  -c N: number of packets for each test\n"
+			"  -C:   use cmsg to set tstamp recording options\n"
 			"  -D:   no delay between packets\n"
 			"  -F:   poll() waits forever for an event\n"
 			"  -I:   request PKTINFO\n"
@@ -413,9 +449,9 @@ static void __attribute__((noreturn)) usage(const char *filepath)
 static void parse_opt(int argc, char **argv)
 {
 	int proto_count = 0;
-	char c;
+	int c;
 
-	while ((c = getopt(argc, argv, "46c:DFhIl:np:rRux")) != -1) {
+	while ((c = getopt(argc, argv, "46c:CDFhIl:np:rRux")) != -1) {
 		switch (c) {
 		case '4':
 			do_ipv6 = 0;
@@ -426,6 +462,9 @@ static void parse_opt(int argc, char **argv)
 		case 'c':
 			cfg_num_pkts = strtoul(optarg, NULL, 10);
 			break;
+		case 'C':
+			cfg_use_cmsg = true;
+			break;
 		case 'D':
 			cfg_no_delay = true;
 			break;
-- 
cgit v1.2.3


From b52354aa068ee362a58ebb92e8bd0d0e18008364 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 20 Dec 2018 16:22:53 -0500
Subject: selftests: expand txtimestamp with ipv6 dgram + raw and pf_packet

Expand the transmit timestamp regression test with support for
missing protocols: ipv6 datagram and raw and pf_packet.

Also refine resolve_hostname to independently request AF_INET or
AF_INET6 addresses. Else, ipv4 addresses may be returned as AF_INET6.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../networking/timestamping/txtimestamp.c          | 189 ++++++++++++++++-----
 1 file changed, 146 insertions(+), 43 deletions(-)

diff --git a/tools/testing/selftests/networking/timestamping/txtimestamp.c b/tools/testing/selftests/networking/timestamping/txtimestamp.c
index ca5fad15a855..ecc1db5dcfca 100644
--- a/tools/testing/selftests/networking/timestamping/txtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/txtimestamp.c
@@ -39,6 +39,7 @@
 #include <inttypes.h>
 #include <linux/errqueue.h>
 #include <linux/if_ether.h>
+#include <linux/ipv6.h>
 #include <linux/net_tstamp.h>
 #include <netdb.h>
 #include <net/if.h>
@@ -74,6 +75,7 @@ static bool cfg_do_pktinfo;
 static bool cfg_loop_nodata;
 static bool cfg_no_delay;
 static bool cfg_use_cmsg;
+static bool cfg_use_pf_packet;
 static uint16_t dest_port = 9000;
 
 static struct sockaddr_in daddr;
@@ -195,7 +197,9 @@ static void __recv_errmsg_cmsg(struct msghdr *msg, int payload_len)
 		} else if ((cm->cmsg_level == SOL_IP &&
 			    cm->cmsg_type == IP_RECVERR) ||
 			   (cm->cmsg_level == SOL_IPV6 &&
-			    cm->cmsg_type == IPV6_RECVERR)) {
+			    cm->cmsg_type == IPV6_RECVERR) ||
+			   (cm->cmsg_level = SOL_PACKET &&
+			    cm->cmsg_type == PACKET_TX_TIMESTAMP)) {
 			serr = (void *) CMSG_DATA(cm);
 			if (serr->ee_errno != ENOMSG ||
 			    serr->ee_origin != SO_EE_ORIGIN_TIMESTAMPING) {
@@ -270,9 +274,89 @@ static int recv_errmsg(int fd)
 	return ret == -1;
 }
 
+static uint16_t get_ip_csum(const uint16_t *start, int num_words,
+			    unsigned long sum)
+{
+	int i;
+
+	for (i = 0; i < num_words; i++)
+		sum += start[i];
+
+	while (sum >> 16)
+		sum = (sum & 0xFFFF) + (sum >> 16);
+
+	return ~sum;
+}
+
+static uint16_t get_udp_csum(const struct udphdr *udph, int alen)
+{
+	unsigned long pseudo_sum, csum_len;
+	const void *csum_start = udph;
+
+	pseudo_sum = htons(IPPROTO_UDP);
+	pseudo_sum += udph->len;
+
+	/* checksum ip(v6) addresses + udp header + payload */
+	csum_start -= alen * 2;
+	csum_len = ntohs(udph->len) + alen * 2;
+
+	return get_ip_csum(csum_start, csum_len >> 1, pseudo_sum);
+}
+
+static int fill_header_ipv4(void *p)
+{
+	struct iphdr *iph = p;
+
+	memset(iph, 0, sizeof(*iph));
+
+	iph->ihl	= 5;
+	iph->version	= 4;
+	iph->ttl	= 2;
+	iph->saddr	= daddr.sin_addr.s_addr;	/* set for udp csum calc */
+	iph->daddr	= daddr.sin_addr.s_addr;
+	iph->protocol	= IPPROTO_UDP;
+
+	/* kernel writes saddr, csum, len */
+
+	return sizeof(*iph);
+}
+
+static int fill_header_ipv6(void *p)
+{
+	struct ipv6hdr *ip6h = p;
+
+	memset(ip6h, 0, sizeof(*ip6h));
+
+	ip6h->version		= 6;
+	ip6h->payload_len	= htons(sizeof(struct udphdr) + cfg_payload_len);
+	ip6h->nexthdr		= IPPROTO_UDP;
+	ip6h->hop_limit		= 64;
+
+	ip6h->saddr             = daddr6.sin6_addr;
+	ip6h->daddr		= daddr6.sin6_addr;
+
+	/* kernel does not write saddr in case of ipv6 */
+
+	return sizeof(*ip6h);
+}
+
+static void fill_header_udp(void *p, bool is_ipv4)
+{
+	struct udphdr *udph = p;
+
+	udph->source = ntohs(dest_port + 1);	/* spoof */
+	udph->dest   = ntohs(dest_port);
+	udph->len    = ntohs(sizeof(*udph) + cfg_payload_len);
+	udph->check  = 0;
+
+	udph->check  = get_udp_csum(udph, is_ipv4 ? sizeof(struct in_addr) :
+						    sizeof(struct in6_addr));
+}
+
 static void do_test(int family, unsigned int report_opt)
 {
 	char control[CMSG_SPACE(sizeof(uint32_t))];
+	struct sockaddr_ll laddr;
 	unsigned int sock_opt;
 	struct cmsghdr *cmsg;
 	struct msghdr msg;
@@ -280,24 +364,28 @@ static void do_test(int family, unsigned int report_opt)
 	char *buf;
 	int fd, i, val = 1, total_len;
 
-	if (family == AF_INET6 && cfg_proto != SOCK_STREAM) {
-		/* due to lack of checksum generation code */
-		fprintf(stderr, "test: skipping datagram over IPv6\n");
-		return;
-	}
-
 	total_len = cfg_payload_len;
-	if (cfg_proto == SOCK_RAW) {
+	if (cfg_use_pf_packet || cfg_proto == SOCK_RAW) {
 		total_len += sizeof(struct udphdr);
-		if (cfg_ipproto == IPPROTO_RAW)
-			total_len += sizeof(struct iphdr);
+		if (cfg_use_pf_packet || cfg_ipproto == IPPROTO_RAW)
+			if (family == PF_INET)
+				total_len += sizeof(struct iphdr);
+			else
+				total_len += sizeof(struct ipv6hdr);
+
+		/* special case, only rawv6_sendmsg:
+		 * pass proto in sin6_port if not connected
+		 * also see ANK comment in net/ipv4/raw.c
+		 */
+		daddr6.sin6_port = htons(cfg_ipproto);
 	}
 
 	buf = malloc(total_len);
 	if (!buf)
 		error(1, 0, "malloc");
 
-	fd = socket(family, cfg_proto, cfg_ipproto);
+	fd = socket(cfg_use_pf_packet ? PF_PACKET : family,
+		    cfg_proto, cfg_ipproto);
 	if (fd < 0)
 		error(1, errno, "socket");
 
@@ -346,29 +434,17 @@ static void do_test(int family, unsigned int report_opt)
 		memset(&ts_prev, 0, sizeof(ts_prev));
 		memset(buf, 'a' + i, total_len);
 
-		if (cfg_proto == SOCK_RAW) {
-			struct udphdr *udph;
+		if (cfg_use_pf_packet || cfg_proto == SOCK_RAW) {
 			int off = 0;
 
-			if (cfg_ipproto == IPPROTO_RAW) {
-				struct iphdr *iph = (void *) buf;
-
-				memset(iph, 0, sizeof(*iph));
-				iph->ihl      = 5;
-				iph->version  = 4;
-				iph->ttl      = 2;
-				iph->daddr    = daddr.sin_addr.s_addr;
-				iph->protocol = IPPROTO_UDP;
-				/* kernel writes saddr, csum, len */
-
-				off = sizeof(*iph);
+			if (cfg_use_pf_packet || cfg_ipproto == IPPROTO_RAW) {
+				if (family == PF_INET)
+					off = fill_header_ipv4(buf);
+				else
+					off = fill_header_ipv6(buf);
 			}
 
-			udph = (void *) buf + off;
-			udph->source = ntohs(9000); 	/* random spoof */
-			udph->dest   = ntohs(dest_port);
-			udph->len    = ntohs(sizeof(*udph) + cfg_payload_len);
-			udph->check  = 0;	/* not allowed for IPv6 */
+			fill_header_udp(buf + off, family == PF_INET);
 		}
 
 		print_timestamp_usr();
@@ -377,7 +453,17 @@ static void do_test(int family, unsigned int report_opt)
 		iov.iov_len = total_len;
 
 		if (cfg_proto != SOCK_STREAM) {
-			if (family == PF_INET) {
+			if (cfg_use_pf_packet) {
+				memset(&laddr, 0, sizeof(laddr));
+
+				laddr.sll_family	= AF_PACKET;
+				laddr.sll_ifindex	= 1;
+				laddr.sll_protocol	= htons(family == AF_INET ? ETH_P_IP : ETH_P_IPV6);
+				laddr.sll_halen		= ETH_ALEN;
+
+				msg.msg_name = (void *)&laddr;
+				msg.msg_namelen = sizeof(laddr);
+			} else if (family == PF_INET) {
 				msg.msg_name = (void *)&daddr;
 				msg.msg_namelen = sizeof(daddr);
 			} else {
@@ -437,9 +523,10 @@ static void __attribute__((noreturn)) usage(const char *filepath)
 			"  -I:   request PKTINFO\n"
 			"  -l N: send N bytes at a time\n"
 			"  -n:   set no-payload option\n"
+			"  -p N: connect to port N\n"
+			"  -P:   use PF_PACKET\n"
 			"  -r:   use raw\n"
 			"  -R:   use raw (IP_HDRINCL)\n"
-			"  -p N: connect to port N\n"
 			"  -u:   use udp\n"
 			"  -x:   show payload (up to 70 bytes)\n",
 			filepath);
@@ -451,7 +538,7 @@ static void parse_opt(int argc, char **argv)
 	int proto_count = 0;
 	int c;
 
-	while ((c = getopt(argc, argv, "46c:CDFhIl:np:rRux")) != -1) {
+	while ((c = getopt(argc, argv, "46c:CDFhIl:np:PrRux")) != -1) {
 		switch (c) {
 		case '4':
 			do_ipv6 = 0;
@@ -474,9 +561,21 @@ static void parse_opt(int argc, char **argv)
 		case 'I':
 			cfg_do_pktinfo = true;
 			break;
+		case 'l':
+			cfg_payload_len = strtoul(optarg, NULL, 10);
+			break;
 		case 'n':
 			cfg_loop_nodata = true;
 			break;
+		case 'p':
+			dest_port = strtoul(optarg, NULL, 10);
+			break;
+		case 'P':
+			proto_count++;
+			cfg_use_pf_packet = true;
+			cfg_proto = SOCK_DGRAM;
+			cfg_ipproto = 0;
+			break;
 		case 'r':
 			proto_count++;
 			cfg_proto = SOCK_RAW;
@@ -492,12 +591,6 @@ static void parse_opt(int argc, char **argv)
 			cfg_proto = SOCK_DGRAM;
 			cfg_ipproto = IPPROTO_UDP;
 			break;
-		case 'l':
-			cfg_payload_len = strtoul(optarg, NULL, 10);
-			break;
-		case 'p':
-			dest_port = strtoul(optarg, NULL, 10);
-			break;
 		case 'x':
 			cfg_show_payload = true;
 			break;
@@ -514,7 +607,9 @@ static void parse_opt(int argc, char **argv)
 	if (!do_ipv4 && !do_ipv6)
 		error(1, 0, "pass -4 or -6, not both");
 	if (proto_count > 1)
-		error(1, 0, "pass -r, -R or -u, not multiple");
+		error(1, 0, "pass -P, -r, -R or -u, not multiple");
+	if (cfg_do_pktinfo && cfg_use_pf_packet)
+		error(1, 0, "cannot ask for pktinfo over pf_packet");
 
 	if (optind != argc - 1)
 		error(1, 0, "missing required hostname argument");
@@ -522,10 +617,12 @@ static void parse_opt(int argc, char **argv)
 
 static void resolve_hostname(const char *hostname)
 {
+	struct addrinfo hints = { .ai_family = do_ipv4 ? AF_INET : AF_INET6 };
 	struct addrinfo *addrs, *cur;
 	int have_ipv4 = 0, have_ipv6 = 0;
 
-	if (getaddrinfo(hostname, NULL, NULL, &addrs))
+retry:
+	if (getaddrinfo(hostname, NULL, &hints, &addrs))
 		error(1, errno, "getaddrinfo");
 
 	cur = addrs;
@@ -545,14 +642,20 @@ static void resolve_hostname(const char *hostname)
 	if (addrs)
 		freeaddrinfo(addrs);
 
+	if (do_ipv6 && hints.ai_family != AF_INET6) {
+		hints.ai_family = AF_INET6;
+		goto retry;
+	}
+
 	do_ipv4 &= have_ipv4;
 	do_ipv6 &= have_ipv6;
 }
 
 static void do_main(int family)
 {
-	fprintf(stderr, "family:       %s\n",
-			family == PF_INET ? "INET" : "INET6");
+	fprintf(stderr, "family:       %s %s\n",
+			family == PF_INET ? "INET" : "INET6",
+			cfg_use_pf_packet ? "(PF_PACKET)" : "");
 
 	fprintf(stderr, "test SND\n");
 	do_test(family, SOF_TIMESTAMPING_TX_SOFTWARE);
-- 
cgit v1.2.3


From cda261f421ba2682e25f46beb229172706fc7fcd Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 20 Dec 2018 16:22:54 -0500
Subject: selftests: add txtimestamp kselftest

Run the transmit timestamp tests as part of kselftests.

Add a txtimestamp.sh test script that runs most variants:
ipv4/ipv6, tcp/udp/raw/raw_ipproto/pf_packet, data/nodata,
setsockopt/cmsg. The script runs tests with netem delays.

Refine txtimestamp.c to validate results. Take expected
netem delays as input and compare against real timestamps.

To run without dependencies, add a listener socket to be
able to connect in the case of TCP.

Add the timestamping directory to the kselftests Makefile.
Build all the binaries. Only run verified txtimestamp.sh.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/Makefile                   |   1 +
 .../selftests/networking/timestamping/Makefile     |   5 +-
 .../selftests/networking/timestamping/config       |   2 +
 .../networking/timestamping/txtimestamp.c          | 136 +++++++++++++++++----
 .../networking/timestamping/txtimestamp.sh         |  57 +++++++++
 5 files changed, 173 insertions(+), 28 deletions(-)
 create mode 100644 tools/testing/selftests/networking/timestamping/config
 create mode 100755 tools/testing/selftests/networking/timestamping/txtimestamp.sh

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index f0017c831e57..24b9934fb269 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -25,6 +25,7 @@ TARGETS += mount
 TARGETS += mqueue
 TARGETS += net
 TARGETS += netfilter
+TARGETS += networking/timestamping
 TARGETS += nsfs
 TARGETS += powerpc
 TARGETS += proc
diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile
index 14cfcf006936..6c17a93c4e03 100644
--- a/tools/testing/selftests/networking/timestamping/Makefile
+++ b/tools/testing/selftests/networking/timestamping/Makefile
@@ -1,7 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS += -I../../../../../usr/include
 
-TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp
+TEST_GEN_FILES := hwtstamp_config rxtimestamp timestamping txtimestamp
+TEST_PROGS := txtimestamp.sh
 
 all: $(TEST_PROGS)
 
@@ -9,4 +10,4 @@ top_srcdir = ../../../../..
 include ../../lib.mk
 
 clean:
-	rm -fr $(TEST_PROGS)
+	rm -fr $(TEST_GEN_FILES)
diff --git a/tools/testing/selftests/networking/timestamping/config b/tools/testing/selftests/networking/timestamping/config
new file mode 100644
index 000000000000..a13e3169b0a4
--- /dev/null
+++ b/tools/testing/selftests/networking/timestamping/config
@@ -0,0 +1,2 @@
+CONFIG_IFB=y
+CONFIG_NET_SCH_NETEM=y
diff --git a/tools/testing/selftests/networking/timestamping/txtimestamp.c b/tools/testing/selftests/networking/timestamping/txtimestamp.c
index ecc1db5dcfca..2e563d17cf0c 100644
--- a/tools/testing/selftests/networking/timestamping/txtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/txtimestamp.c
@@ -70,17 +70,67 @@ static int do_ipv4 = 1;
 static int do_ipv6 = 1;
 static int cfg_payload_len = 10;
 static int cfg_poll_timeout = 100;
+static int cfg_delay_snd;
+static int cfg_delay_ack;
 static bool cfg_show_payload;
 static bool cfg_do_pktinfo;
 static bool cfg_loop_nodata;
 static bool cfg_no_delay;
 static bool cfg_use_cmsg;
 static bool cfg_use_pf_packet;
+static bool cfg_do_listen;
 static uint16_t dest_port = 9000;
 
 static struct sockaddr_in daddr;
 static struct sockaddr_in6 daddr6;
-static struct timespec ts_prev;
+static struct timespec ts_usr;
+
+static int saved_tskey = -1;
+static int saved_tskey_type = -1;
+
+static bool test_failed;
+
+static int64_t timespec_to_us64(struct timespec *ts)
+{
+	return ts->tv_sec * 1000 * 1000 + ts->tv_nsec / 1000;
+}
+
+static void validate_key(int tskey, int tstype)
+{
+	int stepsize;
+
+	/* compare key for each subsequent request
+	 * must only test for one type, the first one requested
+	 */
+	if (saved_tskey == -1)
+		saved_tskey_type = tstype;
+	else if (saved_tskey_type != tstype)
+		return;
+
+	stepsize = cfg_proto == SOCK_STREAM ? cfg_payload_len : 1;
+	if (tskey != saved_tskey + stepsize) {
+		fprintf(stderr, "ERROR: key %d, expected %d\n",
+				tskey, saved_tskey + stepsize);
+		test_failed = true;
+	}
+
+	saved_tskey = tskey;
+}
+
+static void validate_timestamp(struct timespec *cur, int min_delay)
+{
+	int max_delay = min_delay + 500 /* processing time upper bound */;
+	int64_t cur64, start64;
+
+	cur64 = timespec_to_us64(cur);
+	start64 = timespec_to_us64(&ts_usr);
+
+	if (cur64 < start64 + min_delay || cur64 > start64 + max_delay) {
+		fprintf(stderr, "ERROR: delay %lu expected between %d and %d\n",
+				cur64 - start64, min_delay, max_delay);
+		test_failed = true;
+	}
+}
 
 static void __print_timestamp(const char *name, struct timespec *cur,
 			      uint32_t key, int payload_len)
@@ -92,32 +142,19 @@ static void __print_timestamp(const char *name, struct timespec *cur,
 			name, cur->tv_sec, cur->tv_nsec / 1000,
 			key, payload_len);
 
-	if ((ts_prev.tv_sec | ts_prev.tv_nsec)) {
-		int64_t cur_ms, prev_ms;
-
-		cur_ms = (long) cur->tv_sec * 1000 * 1000;
-		cur_ms += cur->tv_nsec / 1000;
-
-		prev_ms = (long) ts_prev.tv_sec * 1000 * 1000;
-		prev_ms += ts_prev.tv_nsec / 1000;
+	if (cur != &ts_usr)
+		fprintf(stderr, "  (USR %+" PRId64 " us)",
+			timespec_to_us64(cur) - timespec_to_us64(&ts_usr));
 
-		fprintf(stderr, "  (%+" PRId64 " us)", cur_ms - prev_ms);
-	}
-
-	ts_prev = *cur;
 	fprintf(stderr, "\n");
 }
 
 static void print_timestamp_usr(void)
 {
-	struct timespec ts;
-	struct timeval tv;	/* avoid dependency on -lrt */
-
-	gettimeofday(&tv, NULL);
-	ts.tv_sec = tv.tv_sec;
-	ts.tv_nsec = tv.tv_usec * 1000;
+	if (clock_gettime(CLOCK_REALTIME, &ts_usr))
+		error(1, errno, "clock_gettime");
 
-	__print_timestamp("  USR", &ts, 0, 0);
+	__print_timestamp("  USR", &ts_usr, 0, 0);
 }
 
 static void print_timestamp(struct scm_timestamping *tss, int tstype,
@@ -125,15 +162,20 @@ static void print_timestamp(struct scm_timestamping *tss, int tstype,
 {
 	const char *tsname;
 
+	validate_key(tskey, tstype);
+
 	switch (tstype) {
 	case SCM_TSTAMP_SCHED:
 		tsname = "  ENQ";
+		validate_timestamp(&tss->ts[0], 0);
 		break;
 	case SCM_TSTAMP_SND:
 		tsname = "  SND";
+		validate_timestamp(&tss->ts[0], cfg_delay_snd);
 		break;
 	case SCM_TSTAMP_ACK:
 		tsname = "  ACK";
+		validate_timestamp(&tss->ts[0], cfg_delay_ack);
 		break;
 	default:
 		error(1, 0, "unknown timestamp type: %u",
@@ -389,6 +431,9 @@ static void do_test(int family, unsigned int report_opt)
 	if (fd < 0)
 		error(1, errno, "socket");
 
+	/* reset expected key on each new socket */
+	saved_tskey = -1;
+
 	if (cfg_proto == SOCK_STREAM) {
 		if (setsockopt(fd, IPPROTO_TCP, TCP_NODELAY,
 			       (char*) &val, sizeof(val)))
@@ -431,7 +476,6 @@ static void do_test(int family, unsigned int report_opt)
 
 	for (i = 0; i < cfg_num_pkts; i++) {
 		memset(&msg, 0, sizeof(msg));
-		memset(&ts_prev, 0, sizeof(ts_prev));
 		memset(buf, 'a' + i, total_len);
 
 		if (cfg_use_pf_packet || cfg_proto == SOCK_RAW) {
@@ -506,7 +550,7 @@ static void do_test(int family, unsigned int report_opt)
 		error(1, errno, "close");
 
 	free(buf);
-	usleep(400 * 1000);
+	usleep(100 * 1000);
 }
 
 static void __attribute__((noreturn)) usage(const char *filepath)
@@ -522,12 +566,15 @@ static void __attribute__((noreturn)) usage(const char *filepath)
 			"  -F:   poll() waits forever for an event\n"
 			"  -I:   request PKTINFO\n"
 			"  -l N: send N bytes at a time\n"
+			"  -L    listen on hostname and port\n"
 			"  -n:   set no-payload option\n"
 			"  -p N: connect to port N\n"
 			"  -P:   use PF_PACKET\n"
 			"  -r:   use raw\n"
 			"  -R:   use raw (IP_HDRINCL)\n"
 			"  -u:   use udp\n"
+			"  -v:   validate SND delay (usec)\n"
+			"  -V:   validate ACK delay (usec)\n"
 			"  -x:   show payload (up to 70 bytes)\n",
 			filepath);
 	exit(1);
@@ -538,7 +585,7 @@ static void parse_opt(int argc, char **argv)
 	int proto_count = 0;
 	int c;
 
-	while ((c = getopt(argc, argv, "46c:CDFhIl:np:PrRux")) != -1) {
+	while ((c = getopt(argc, argv, "46c:CDFhIl:Lnp:PrRuv:V:x")) != -1) {
 		switch (c) {
 		case '4':
 			do_ipv6 = 0;
@@ -564,6 +611,9 @@ static void parse_opt(int argc, char **argv)
 		case 'l':
 			cfg_payload_len = strtoul(optarg, NULL, 10);
 			break;
+		case 'L':
+			cfg_do_listen = true;
+			break;
 		case 'n':
 			cfg_loop_nodata = true;
 			break;
@@ -591,6 +641,12 @@ static void parse_opt(int argc, char **argv)
 			cfg_proto = SOCK_DGRAM;
 			cfg_ipproto = IPPROTO_UDP;
 			break;
+		case 'v':
+			cfg_delay_snd = strtoul(optarg, NULL, 10);
+			break;
+		case 'V':
+			cfg_delay_ack = strtoul(optarg, NULL, 10);
+			break;
 		case 'x':
 			cfg_show_payload = true;
 			break;
@@ -651,6 +707,27 @@ retry:
 	do_ipv6 &= have_ipv6;
 }
 
+static void do_listen(int family, void *addr, int alen)
+{
+	int fd, type;
+
+	type = cfg_proto == SOCK_RAW ? SOCK_DGRAM : cfg_proto;
+
+	fd = socket(family, type, 0);
+	if (fd == -1)
+		error(1, errno, "socket rx");
+
+	if (bind(fd, addr, alen))
+		error(1, errno, "bind rx");
+
+	if (type == SOCK_STREAM && listen(fd, 10))
+		error(1, errno, "listen rx");
+
+	/* leave fd open, will be closed on process exit.
+	 * this enables connect() to succeed and avoids icmp replies
+	 */
+}
+
 static void do_main(int family)
 {
 	fprintf(stderr, "family:       %s %s\n",
@@ -697,10 +774,17 @@ int main(int argc, char **argv)
 	fprintf(stderr, "server port:  %u\n", dest_port);
 	fprintf(stderr, "\n");
 
-	if (do_ipv4)
+	if (do_ipv4) {
+		if (cfg_do_listen)
+			do_listen(PF_INET, &daddr, sizeof(daddr));
 		do_main(PF_INET);
-	if (do_ipv6)
+	}
+
+	if (do_ipv6) {
+		if (cfg_do_listen)
+			do_listen(PF_INET6, &daddr6, sizeof(daddr6));
 		do_main(PF_INET6);
+	}
 
-	return 0;
+	return test_failed;
 }
diff --git a/tools/testing/selftests/networking/timestamping/txtimestamp.sh b/tools/testing/selftests/networking/timestamping/txtimestamp.sh
new file mode 100755
index 000000000000..df0d86ca72b7
--- /dev/null
+++ b/tools/testing/selftests/networking/timestamping/txtimestamp.sh
@@ -0,0 +1,57 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Send packets with transmit timestamps over loopback with netem
+# Verify that timestamps correspond to netem delay
+
+set -e
+
+setup() {
+	# set 1ms delay on lo egress
+	tc qdisc add dev lo root netem delay 1ms
+
+	# set 2ms delay on ifb0 egress
+	modprobe ifb
+	ip link add ifb_netem0 type ifb
+	ip link set dev ifb_netem0 up
+	tc qdisc add dev ifb_netem0 root netem delay 2ms
+
+	# redirect lo ingress through ifb0 egress
+	tc qdisc add dev lo handle ffff: ingress
+	tc filter add dev lo parent ffff: \
+		u32 match mark 0 0xffff \
+		action mirred egress redirect dev ifb_netem0
+}
+
+run_test_v4v6() {
+	# SND will be delayed 1000us
+	# ACK will be delayed 6000us: 1 + 2 ms round-trip
+	local -r args="$@ -v 1000 -V 6000"
+
+	./txtimestamp ${args} -4 -L 127.0.0.1
+	./txtimestamp ${args} -6 -L ::1
+}
+
+run_test_tcpudpraw() {
+	local -r args=$@
+
+	run_test_v4v6 ${args}		# tcp
+	run_test_v4v6 ${args} -u	# udp
+	run_test_v4v6 ${args} -r	# raw
+	run_test_v4v6 ${args} -R	# raw (IPPROTO_RAW)
+	run_test_v4v6 ${args} -P	# pf_packet
+}
+
+run_test_all() {
+	run_test_tcpudpraw		# setsockopt
+	run_test_tcpudpraw -C		# cmsg
+	run_test_tcpudpraw -n		# timestamp w/o data
+}
+
+if [[ "$(ip netns identify)" == "root" ]]; then
+	../../net/in_netns.sh $0 $@
+else
+	setup
+	run_test_all
+	echo "OK. All tests passed"
+fi
-- 
cgit v1.2.3


From a02e8964eaf9271a8a5fcc0c55bd13f933bafc56 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 20 Dec 2018 17:14:54 -0500
Subject: virtio-net: ethtool configurable LRO

Virtio-net devices negotiate LRO support with the host.
Display the initially negotiated state with ethtool -k.

Also allow configuring it with ethtool -K, reusing the existing
virtnet_set_guest_offloads helper that configures LRO for XDP.
This is conditional on VIRTIO_NET_F_CTRL_GUEST_OFFLOADS.

Virtio-net negotiates TSO4 and TSO6 separately, but ethtool does not
distinguish between the two. Display LRO as on only if any offload
is active.

RTNL is held while calling virtnet_set_features, same as on the path
from virtnet_xdp_set.

Changes v1 -> v2
  - allow ethtool config (-K) only if VIRTIO_NET_F_CTRL_GUEST_OFFLOADS
  - show LRO as enabled if any LRO variant is enabled
  - do not allow configuration while XDP is active
  - differentiate current features from the capable set, to restore
    on XDP down only those features that were active on XDP up
  - move test out of VIRTIO_NET_F_CSUM/TSO branch, which is tx only

Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ea672145f6a6..023725086046 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -236,6 +236,7 @@ struct virtnet_info {
 	u32 speed;
 
 	unsigned long guest_offloads;
+	unsigned long guest_offloads_capable;
 
 	/* failover when STANDBY feature enabled */
 	struct failover *failover;
@@ -2479,6 +2480,31 @@ static int virtnet_get_phys_port_name(struct net_device *dev, char *buf,
 	return 0;
 }
 
+static int virtnet_set_features(struct net_device *dev,
+				netdev_features_t features)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	u64 offloads;
+	int err;
+
+	if ((dev->features ^ features) & NETIF_F_LRO) {
+		if (vi->xdp_queue_pairs)
+			return -EBUSY;
+
+		if (features & NETIF_F_LRO)
+			offloads = vi->guest_offloads_capable;
+		else
+			offloads = 0;
+
+		err = virtnet_set_guest_offloads(vi, offloads);
+		if (err)
+			return err;
+		vi->guest_offloads = offloads;
+	}
+
+	return 0;
+}
+
 static const struct net_device_ops virtnet_netdev = {
 	.ndo_open            = virtnet_open,
 	.ndo_stop   	     = virtnet_close,
@@ -2493,6 +2519,7 @@ static const struct net_device_ops virtnet_netdev = {
 	.ndo_xdp_xmit		= virtnet_xdp_xmit,
 	.ndo_features_check	= passthru_features_check,
 	.ndo_get_phys_port_name	= virtnet_get_phys_port_name,
+	.ndo_set_features	= virtnet_set_features,
 };
 
 static void virtnet_config_changed_work(struct work_struct *work)
@@ -2951,6 +2978,11 @@ static int virtnet_probe(struct virtio_device *vdev)
 	}
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
 		dev->features |= NETIF_F_RXCSUM;
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6))
+		dev->features |= NETIF_F_LRO;
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS))
+		dev->hw_features |= NETIF_F_LRO;
 
 	dev->vlan_features = dev->features;
 
@@ -3080,6 +3112,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	for (i = 0; i < ARRAY_SIZE(guest_offloads); i++)
 		if (virtio_has_feature(vi->vdev, guest_offloads[i]))
 			set_bit(guest_offloads[i], &vi->guest_offloads);
+	vi->guest_offloads_capable = vi->guest_offloads;
 
 	pr_debug("virtnet: registered device %s with %d RX and TX vq's\n",
 		 dev->name, max_queue_pairs);
-- 
cgit v1.2.3


From fa2323325e8b0c61ded1e3d2c6f12f3aa43c4e30 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Thu, 20 Dec 2018 16:41:52 -0800
Subject: selftests: net: reuseport_addr_any: silence clang warning

Clang does not recognize that calls to error() terminate execution
and complains about uninitialized variable use that happens after calls
to error(). This noop patchset fixes this.

Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/reuseport_addr_any.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tools/testing/selftests/net/reuseport_addr_any.c b/tools/testing/selftests/net/reuseport_addr_any.c
index 6f54d425dba9..c6233935fed1 100644
--- a/tools/testing/selftests/net/reuseport_addr_any.c
+++ b/tools/testing/selftests/net/reuseport_addr_any.c
@@ -60,6 +60,11 @@ static void build_rcv_fd(int family, int proto, int *rcv_fds, int count,
 		break;
 	default:
 		error(1, 0, "Unsupported family %d", family);
+		/* clang does not recognize error() above as terminating
+		 * the program, so it complains that saddr, sz are
+		 * not initialized when this code path is taken. Silence it.
+		 */
+		return;
 	}
 
 	for (i = 0; i < count; ++i) {
@@ -128,6 +133,11 @@ static int connect_and_send(int family, int proto)
 	break;
 	default:
 		error(1, 0, "Unsupported family %d", family);
+		/* clang does not recognize error() above as terminating
+		 * the program, so it complains that saddr, daddr, sz are
+		 * not initialized when this code path is taken. Silence it.
+		 */
+		return -1;
 	}
 
 	fd = socket(family, proto, 0);
-- 
cgit v1.2.3


From e05b8d4fc30a68540e5c0eef3e2bacd1f27b8172 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Thu, 15 Nov 2018 11:48:41 +0200
Subject: net/mlx5e: TX, Print opcode in error CQE warning

The opcode indicates about the error reason.
Printing it helps in debug.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f201965b888f..598ad7e4d5c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -459,9 +459,10 @@ static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq,
 	u32 ci = mlx5_cqwq_get_ci(&sq->cq.wq);
 
 	netdev_err(sq->channel->netdev,
-		   "Error cqe on cqn 0x%x, ci 0x%x, sqn 0x%x, syndrome 0x%x, vendor syndrome 0x%x\n",
-		   sq->cq.mcq.cqn, ci, sq->sqn, err_cqe->syndrome,
-		   err_cqe->vendor_err_synd);
+		   "Error cqe on cqn 0x%x, ci 0x%x, sqn 0x%x, opcode 0x%x, syndrome 0x%x, vendor syndrome 0x%x\n",
+		   sq->cq.mcq.cqn, ci, sq->sqn,
+		   get_cqe_opcode((struct mlx5_cqe64 *)err_cqe),
+		   err_cqe->syndrome, err_cqe->vendor_err_synd);
 	mlx5_dump_err_cqe(sq->cq.mdev, err_cqe);
 }
 
-- 
cgit v1.2.3


From 4fb2f516186ea25dea326f97880431e14a5b9e9d Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 21 Nov 2018 13:56:17 +0200
Subject: net/mlx5e: XDP, Precede XDP-related operations in RQ poll by a loaded
 program check

At the end of the RQ polling loop, some XDP-related operations
might be required. Before checking them one by one, check if
an XDP program is even loaded.
Combine all the checks and operations in a single function in xdp files.

This saves unnecessary checks for non-XDP flows.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 15 +++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c  | 12 ++----------
 3 files changed, 18 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index ad6d471d00dd..cf22ea529c53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -305,3 +305,18 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 	return n - drops;
 }
+
+void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq)
+{
+	struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
+
+	if (xdpsq->doorbell) {
+		mlx5e_xmit_xdp_doorbell(xdpsq);
+		xdpsq->doorbell = false;
+	}
+
+	if (xdpsq->redirect_flush) {
+		xdp_do_flush_map();
+		xdpsq->redirect_flush = false;
+	}
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 6dfab045925f..eecc0392fcff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -44,7 +44,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      void *va, u16 *rx_headroom, u32 *len);
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
 void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
-
+void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq);
 bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi);
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index cdce30a95c60..1d0bb5ff8c26 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1190,7 +1190,6 @@ mpwrq_cqe_out:
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 {
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
-	struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
 	struct mlx5_cqe64 *cqe;
 	int work_done = 0;
 
@@ -1221,15 +1220,8 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
 out:
-	if (xdpsq->doorbell) {
-		mlx5e_xmit_xdp_doorbell(xdpsq);
-		xdpsq->doorbell = false;
-	}
-
-	if (xdpsq->redirect_flush) {
-		xdp_do_flush_map();
-		xdpsq->redirect_flush = false;
-	}
+	if (rq->xdp_prog)
+		mlx5e_xdp_rx_poll_complete(rq);
 
 	mlx5_cqwq_update_db_record(&cq->wq);
 
-- 
cgit v1.2.3


From feb2ff9d74f76a174e284255b7e537b6c090c13c Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 21 Nov 2018 14:04:45 +0200
Subject: net/mlx5e: XDP, Change the XDP SQ redirect indication

Do not maintain an SQ state bit to indicate whether an
XDP SQ serves redirect operations.

Instead, rely on the fact that such an XDP SQ doesn't reside
in an RQ instance, while the others do.
This info is not known to the XDP SQ functions themselves,
and they rely on their callers to distinguish between the cases.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  1 -
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c  | 14 ++++----------
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h  |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 12 +++++-------
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c | 13 +++++++------
 5 files changed, 18 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 72cc204f9a34..15cbf0c6e309 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -344,7 +344,6 @@ enum {
 	MLX5E_SQ_STATE_IPSEC,
 	MLX5E_SQ_STATE_AM,
 	MLX5E_SQ_STATE_TLS,
-	MLX5E_SQ_STATE_REDIRECT,
 };
 
 struct mlx5e_sq_wqe_info {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index cf22ea529c53..4961b8fea111 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -164,11 +164,10 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 	return true;
 }
 
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 {
 	struct mlx5e_xdpsq *sq;
 	struct mlx5_cqe64 *cqe;
-	struct mlx5e_rq *rq;
 	bool is_redirect;
 	u16 sqcc;
 	int i;
@@ -182,8 +181,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 	if (!cqe)
 		return false;
 
-	is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
-	rq = container_of(sq, struct mlx5e_rq, xdpsq);
+	is_redirect = !rq;
 
 	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
 	 * otherwise a cq overrun may occur
@@ -228,13 +226,9 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 	return (i == MLX5E_TX_CQ_POLL_BUDGET);
 }
 
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
 {
-	struct mlx5e_rq *rq;
-	bool is_redirect;
-
-	is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
-	rq = is_redirect ? NULL : container_of(sq, struct mlx5e_rq, xdpsq);
+	bool is_redirect = !rq;
 
 	while (sq->cc != sq->pc) {
 		u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index eecc0392fcff..37fcb17e7f27 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -42,8 +42,8 @@
 
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      void *va, u16 *rx_headroom, u32 *len);
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq);
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq);
 void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq);
 bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi);
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index bc791404f2e7..8a19f451fb7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1577,8 +1577,6 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = sq->min_inline_mode;
-	if (is_redirect)
-		set_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
 	if (err)
@@ -1612,7 +1610,7 @@ err_free_xdpsq:
 	return err;
 }
 
-static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
+static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
 {
 	struct mlx5e_channel *c = sq->channel;
 
@@ -1620,7 +1618,7 @@ static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
 	napi_synchronize(&c->napi);
 
 	mlx5e_destroy_sq(c->mdev, sq->sqn);
-	mlx5e_free_xdpsq_descs(sq);
+	mlx5e_free_xdpsq_descs(sq, rq);
 	mlx5e_free_xdpsq(sq);
 }
 
@@ -2008,7 +2006,7 @@ err_close_rq:
 
 err_close_xdp_sq:
 	if (c->xdp)
-		mlx5e_close_xdpsq(&c->rq.xdpsq);
+		mlx5e_close_xdpsq(&c->rq.xdpsq, &c->rq);
 
 err_close_sqs:
 	mlx5e_close_sqs(c);
@@ -2061,10 +2059,10 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 
 static void mlx5e_close_channel(struct mlx5e_channel *c)
 {
-	mlx5e_close_xdpsq(&c->xdpsq);
+	mlx5e_close_xdpsq(&c->xdpsq, NULL);
 	mlx5e_close_rq(&c->rq);
 	if (c->xdp)
-		mlx5e_close_xdpsq(&c->rq.xdpsq);
+		mlx5e_close_xdpsq(&c->rq.xdpsq, &c->rq);
 	mlx5e_close_sqs(c);
 	mlx5e_close_icosq(&c->icosq);
 	napi_disable(&c->napi);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 85d517360157..b4af5e19f6ac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -76,6 +76,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
 					       napi);
 	struct mlx5e_ch_stats *ch_stats = c->stats;
+	struct mlx5e_rq *rq = &c->rq;
 	bool busy = false;
 	int work_done = 0;
 	int i;
@@ -85,17 +86,17 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
-	busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq);
+	busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq, NULL);
 
 	if (c->xdp)
-		busy |= mlx5e_poll_xdpsq_cq(&c->rq.xdpsq.cq);
+		busy |= mlx5e_poll_xdpsq_cq(&rq->xdpsq.cq, rq);
 
 	if (likely(budget)) { /* budget=0 means: don't poll rx rings */
-		work_done = mlx5e_poll_rx_cq(&c->rq.cq, budget);
+		work_done = mlx5e_poll_rx_cq(&rq->cq, budget);
 		busy |= work_done == budget;
 	}
 
-	busy |= c->rq.post_wqes(&c->rq);
+	busy |= c->rq.post_wqes(rq);
 
 	if (busy) {
 		if (likely(mlx5e_channel_no_affinity_change(c)))
@@ -115,9 +116,9 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 		mlx5e_cq_arm(&c->sq[i].cq);
 	}
 
-	mlx5e_handle_rx_dim(&c->rq);
+	mlx5e_handle_rx_dim(rq);
 
-	mlx5e_cq_arm(&c->rq.cq);
+	mlx5e_cq_arm(&rq->cq);
 	mlx5e_cq_arm(&c->icosq.cq);
 	mlx5e_cq_arm(&c->xdpsq.cq);
 
-- 
cgit v1.2.3


From db02a308cd724fd37416012c8077d3e0ea2bf386 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Thu, 15 Nov 2018 11:48:41 +0200
Subject: net/mlx5e: XDP, Warn upon polling an error CQE

Do not ignore the CQE opcode.
This helps expose issues and debug them.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 4961b8fea111..407e285b0430 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -197,6 +197,11 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
+		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ))
+			netdev_WARN_ONCE(sq->channel->netdev,
+					 "Bad OP in XDPSQ CQE: 0x%x\n",
+					 get_cqe_opcode(cqe));
+
 		do {
 			u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
 			struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci];
-- 
cgit v1.2.3


From b8180392edd97cd5bfdf12270315a72fe601cf7e Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 21 Nov 2018 14:06:02 +0200
Subject: net/mlx5e: XDP, Replace boolean doorbell indication with segment
 pointer

Instead of calculating the control segment to be used upon an
XDP xmit doorbell, save it in SQ structure.
Nullify when no pending doorbell.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h     |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 14 ++++----------
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h | 11 ++++-------
 3 files changed, 9 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 15cbf0c6e309..35cd4099feda 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -413,7 +413,7 @@ struct mlx5e_xdpsq {
 
 	/* dirtied @xmit */
 	u16                        pc ____cacheline_aligned_in_smp;
-	bool                       doorbell;
+	struct mlx5_wqe_ctrl_seg   *doorbell_cseg;
 
 	struct mlx5e_cq            cq;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 407e285b0430..fb1cdf729efb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -126,11 +126,8 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 	}
 
 	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
-		if (sq->doorbell) {
-			/* SQ is full, ring doorbell */
-			mlx5e_xmit_xdp_doorbell(sq);
-			sq->doorbell = false;
-		}
+		/* SQ is full, ring doorbell */
+		mlx5e_xmit_xdp_doorbell(sq);
 		stats->full++;
 		return false;
 	}
@@ -158,7 +155,7 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 	sq->db.xdpi[pi] = *xdpi;
 	sq->pc++;
 
-	sq->doorbell = true;
+	sq->doorbell_cseg = cseg;
 
 	stats->xmit++;
 	return true;
@@ -309,10 +306,7 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq)
 {
 	struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
 
-	if (xdpsq->doorbell) {
-		mlx5e_xmit_xdp_doorbell(xdpsq);
-		xdpsq->doorbell = false;
-	}
+	mlx5e_xmit_xdp_doorbell(xdpsq);
 
 	if (xdpsq->redirect_flush) {
 		xdp_do_flush_map();
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 37fcb17e7f27..e2faf869e77c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -51,13 +51,10 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 {
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	struct mlx5e_tx_wqe *wqe;
-	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc - 1); /* last pi */
-
-	wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl);
+	if (sq->doorbell_cseg) {
+		mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, sq->doorbell_cseg);
+		sq->doorbell_cseg = NULL;
+	}
 }
 
 #endif
-- 
cgit v1.2.3


From fea28dd6a281045e18c1412ab5bba54436c11088 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 14 Oct 2018 14:37:48 +0300
Subject: net/mlx5e: XDP, Maintain a FIFO structure for xdp_info instances

This provides infrastructure to have multiple xdp_info instances
for the same consumer index.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 13 +++++++--
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c  | 32 +++++++++++------------
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h  | 15 +++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 29 +++++++++++++++-----
 4 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 35cd4099feda..fab49cbdb85d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -404,15 +404,24 @@ struct mlx5e_xdp_info {
 	struct mlx5e_dma_info di;
 };
 
+struct mlx5e_xdp_info_fifo {
+	struct mlx5e_xdp_info *xi;
+	u32 *cc;
+	u32 *pc;
+	u32 mask;
+};
+
 struct mlx5e_xdpsq {
 	/* data path */
 
 	/* dirtied @completion */
+	u32                        xdpi_fifo_cc;
 	u16                        cc;
 	bool                       redirect_flush;
 
 	/* dirtied @xmit */
-	u16                        pc ____cacheline_aligned_in_smp;
+	u32                        xdpi_fifo_pc ____cacheline_aligned_in_smp;
+	u16                        pc;
 	struct mlx5_wqe_ctrl_seg   *doorbell_cseg;
 
 	struct mlx5e_cq            cq;
@@ -421,7 +430,7 @@ struct mlx5e_xdpsq {
 	struct mlx5_wq_cyc         wq;
 	struct mlx5e_xdpsq_stats  *stats;
 	struct {
-		struct mlx5e_xdp_info     *xdpi;
+		struct mlx5e_xdp_info_fifo xdpi_fifo;
 	} db;
 	void __iomem              *uar_map;
 	u32                        sqn;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index fb1cdf729efb..fe8788a7744e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -149,20 +149,18 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
 
-	/* move page to reference to sq responsibility,
-	 * and mark so it's not put back in page-cache.
-	 */
-	sq->db.xdpi[pi] = *xdpi;
 	sq->pc++;
 
 	sq->doorbell_cseg = cseg;
 
+	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
 	stats->xmit++;
 	return true;
 }
 
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 {
+	struct mlx5e_xdp_info_fifo *xdpi_fifo;
 	struct mlx5e_xdpsq *sq;
 	struct mlx5_cqe64 *cqe;
 	bool is_redirect;
@@ -179,6 +177,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 		return false;
 
 	is_redirect = !rq;
+	xdpi_fifo = &sq->db.xdpi_fifo;
 
 	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
 	 * otherwise a cq overrun may occur
@@ -200,19 +199,19 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 					 get_cqe_opcode(cqe));
 
 		do {
-			u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
-			struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci];
+			struct mlx5e_xdp_info xdpi =
+				mlx5e_xdpi_fifo_pop(xdpi_fifo);
 
 			last_wqe = (sqcc == wqe_counter);
 			sqcc++;
 
 			if (is_redirect) {
-				xdp_return_frame(xdpi->xdpf);
-				dma_unmap_single(sq->pdev, xdpi->dma_addr,
-						 xdpi->xdpf->len, DMA_TO_DEVICE);
+				xdp_return_frame(xdpi.xdpf);
+				dma_unmap_single(sq->pdev, xdpi.dma_addr,
+						 xdpi.xdpf->len, DMA_TO_DEVICE);
 			} else {
 				/* Recycle RX page */
-				mlx5e_page_release(rq, &xdpi->di, true);
+				mlx5e_page_release(rq, &xdpi.di, true);
 			}
 		} while (!last_wqe);
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
@@ -230,21 +229,22 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 
 void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
 {
+	struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
 	bool is_redirect = !rq;
 
 	while (sq->cc != sq->pc) {
-		u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
-		struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci];
+		struct mlx5e_xdp_info xdpi =
+			mlx5e_xdpi_fifo_pop(xdpi_fifo);
 
 		sq->cc++;
 
 		if (is_redirect) {
-			xdp_return_frame(xdpi->xdpf);
-			dma_unmap_single(sq->pdev, xdpi->dma_addr,
-					 xdpi->xdpf->len, DMA_TO_DEVICE);
+			xdp_return_frame(xdpi.xdpf);
+			dma_unmap_single(sq->pdev, xdpi.dma_addr,
+					 xdpi.xdpf->len, DMA_TO_DEVICE);
 		} else {
 			/* Recycle RX page */
-			mlx5e_page_release(rq, &xdpi->di, false);
+			mlx5e_page_release(rq, &xdpi.di, false);
 		}
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index e2faf869e77c..fd689ed506af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -57,4 +57,19 @@ static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 	}
 }
 
+static inline void
+mlx5e_xdpi_fifo_push(struct mlx5e_xdp_info_fifo *fifo,
+		     struct mlx5e_xdp_info *xi)
+{
+	u32 i = (*fifo->pc)++ & fifo->mask;
+
+	fifo->xi[i] = *xi;
+}
+
+static inline struct mlx5e_xdp_info
+mlx5e_xdpi_fifo_pop(struct mlx5e_xdp_info_fifo *fifo)
+{
+	return fifo->xi[(*fifo->cc)++ & fifo->mask];
+}
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 8a19f451fb7a..a9f773f6d09a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -992,18 +992,35 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq)
 
 static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
-	kvfree(sq->db.xdpi);
+	kvfree(sq->db.xdpi_fifo.xi);
+}
+
+static int mlx5e_alloc_xdpsq_fifo(struct mlx5e_xdpsq *sq, int numa)
+{
+	struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
+	int wq_sz        = mlx5_wq_cyc_get_size(&sq->wq);
+	int dsegs_per_wq = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
+
+	xdpi_fifo->xi = kvzalloc_node(sizeof(*xdpi_fifo->xi) * dsegs_per_wq,
+				      GFP_KERNEL, numa);
+	if (!xdpi_fifo->xi)
+		return -ENOMEM;
+
+	xdpi_fifo->pc   = &sq->xdpi_fifo_pc;
+	xdpi_fifo->cc   = &sq->xdpi_fifo_cc;
+	xdpi_fifo->mask = dsegs_per_wq - 1;
+
+	return 0;
 }
 
 static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
-	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+	int err;
 
-	sq->db.xdpi = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.xdpi)),
-				    GFP_KERNEL, numa);
-	if (!sq->db.xdpi) {
+	err = mlx5e_alloc_xdpsq_fifo(sq, numa);
+	if (err) {
 		mlx5e_free_xdpsq_db(sq);
-		return -ENOMEM;
+		return err;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 1feeab80078078186b5080fe15c51a5cce724a0e Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 14 Oct 2018 14:46:57 +0300
Subject: net/mlx5e: XDP, Add array for WQE info descriptors

Each xdp_wqe_info instance describes the number of data-segments
and WQEBBs of the WQE.
This is useful for a downstream patch that adds support for
Multi-Packet TX WQE feature.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  6 +++
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c  | 58 +++++++++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 +++++
 3 files changed, 54 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index fab49cbdb85d..20b3432b35de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -411,6 +411,11 @@ struct mlx5e_xdp_info_fifo {
 	u32 mask;
 };
 
+struct mlx5e_xdp_wqe_info {
+	u8 num_wqebbs;
+	u8 num_ds;
+};
+
 struct mlx5e_xdpsq {
 	/* data path */
 
@@ -430,6 +435,7 @@ struct mlx5e_xdpsq {
 	struct mlx5_wq_cyc         wq;
 	struct mlx5e_xdpsq_stats  *stats;
 	struct {
+		struct mlx5e_xdp_wqe_info *wqe_info;
 		struct mlx5e_xdp_info_fifo xdpi_fifo;
 	} db;
 	void __iomem              *uar_map;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index fe8788a7744e..5e5e43ea9b53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -199,19 +199,27 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 					 get_cqe_opcode(cqe));
 
 		do {
-			struct mlx5e_xdp_info xdpi =
-				mlx5e_xdpi_fifo_pop(xdpi_fifo);
+			struct mlx5e_xdp_wqe_info *wi;
+			u16 ci, j;
 
 			last_wqe = (sqcc == wqe_counter);
-			sqcc++;
-
-			if (is_redirect) {
-				xdp_return_frame(xdpi.xdpf);
-				dma_unmap_single(sq->pdev, xdpi.dma_addr,
-						 xdpi.xdpf->len, DMA_TO_DEVICE);
-			} else {
-				/* Recycle RX page */
-				mlx5e_page_release(rq, &xdpi.di, true);
+			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
+			wi = &sq->db.wqe_info[ci];
+
+			sqcc += wi->num_wqebbs;
+
+			for (j = 0; j < wi->num_ds; j++) {
+				struct mlx5e_xdp_info xdpi =
+					mlx5e_xdpi_fifo_pop(xdpi_fifo);
+
+				if (is_redirect) {
+					xdp_return_frame(xdpi.xdpf);
+					dma_unmap_single(sq->pdev, xdpi.dma_addr,
+							 xdpi.xdpf->len, DMA_TO_DEVICE);
+				} else {
+					/* Recycle RX page */
+					mlx5e_page_release(rq, &xdpi.di, true);
+				}
 			}
 		} while (!last_wqe);
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
@@ -233,18 +241,26 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
 	bool is_redirect = !rq;
 
 	while (sq->cc != sq->pc) {
-		struct mlx5e_xdp_info xdpi =
-			mlx5e_xdpi_fifo_pop(xdpi_fifo);
+		struct mlx5e_xdp_wqe_info *wi;
+		u16 ci, i;
 
-		sq->cc++;
+		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
+		wi = &sq->db.wqe_info[ci];
 
-		if (is_redirect) {
-			xdp_return_frame(xdpi.xdpf);
-			dma_unmap_single(sq->pdev, xdpi.dma_addr,
-					 xdpi.xdpf->len, DMA_TO_DEVICE);
-		} else {
-			/* Recycle RX page */
-			mlx5e_page_release(rq, &xdpi.di, false);
+		sq->cc += wi->num_wqebbs;
+
+		for (i = 0; i < wi->num_ds; i++) {
+			struct mlx5e_xdp_info xdpi =
+				mlx5e_xdpi_fifo_pop(xdpi_fifo);
+
+			if (is_redirect) {
+				xdp_return_frame(xdpi.xdpf);
+				dma_unmap_single(sq->pdev, xdpi.dma_addr,
+						 xdpi.xdpf->len, DMA_TO_DEVICE);
+			} else {
+				/* Recycle RX page */
+				mlx5e_page_release(rq, &xdpi.di, false);
+			}
 		}
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a9f773f6d09a..7086c73d5915 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -993,6 +993,7 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq)
 static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
 	kvfree(sq->db.xdpi_fifo.xi);
+	kvfree(sq->db.wqe_info);
 }
 
 static int mlx5e_alloc_xdpsq_fifo(struct mlx5e_xdpsq *sq, int numa)
@@ -1015,8 +1016,14 @@ static int mlx5e_alloc_xdpsq_fifo(struct mlx5e_xdpsq *sq, int numa)
 
 static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
+	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 	int err;
 
+	sq->db.wqe_info = kvzalloc_node(sizeof(*sq->db.wqe_info) * wq_sz,
+					GFP_KERNEL, numa);
+	if (!sq->db.wqe_info)
+		return -ENOMEM;
+
 	err = mlx5e_alloc_xdpsq_fifo(sq, numa);
 	if (err) {
 		mlx5e_free_xdpsq_db(sq);
@@ -1606,6 +1613,7 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 
 	/* Pre initialize fixed WQE fields */
 	for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
+		struct mlx5e_xdp_wqe_info *wi  = &sq->db.wqe_info[i];
 		struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
 		struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
 		struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
@@ -1616,6 +1624,9 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 
 		dseg = (struct mlx5_wqe_data_seg *)cseg + (ds_cnt - 1);
 		dseg->lkey = sq->mkey_be;
+
+		wi->num_wqebbs = 1;
+		wi->num_ds     = 1;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 5e0d2eef771ee78b092bf93d040eac02a0965fea Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 21 Nov 2018 14:08:06 +0200
Subject: net/mlx5e: XDP, Support Enhanced Multi-Packet TX WQE

Add support for the HW feature of multi-packet WQE in XDP
xmit flow.

The conventional TX descriptor (WQE, Work Queue Element) serves
a single packet. Our HW has support for multi-packet WQE (MPWQE)
in which a single descriptor serves multiple TX packets.

This reduces both the PCI overhead and the CPU cycles wasted on
writing them.

In this patch we add support for the HW feature, which is supported
starting from ConnectX-5.

Performance:
Tested packet rate for UDP 64Byte multi-stream over ConnectX-5 NICs.
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz

XDP_TX:
We see a huge gain on single port ConnectX-5, and reach the 100 Mpps
milestone.
* Single-port HCA:
	Before:   70 Mpps
	After:   100 Mpps (+42.8%)

* Dual-port HCA:
	Before: 51.7 Mpps
	After:  57.3 Mpps (+10.8%)

* In both cases we tested traffic on one port and for now On Dual-port HCAs
  we see only small gain, we are working to overcome this bottleneck, but
  for the moment only with experimental firmware on dual port HCAs we can
  reach the wanted numbers as seen on Single-port HCAs.

XDP_REDIRECT:
Redirect from (A) ConnectX-5 to (B) ConnectX-5.
Due to a setup limitation, (A) and (B) are on different NUMA nodes,
so absolute performance numbers are not optimal.
Note:
  Below is the transmit rate of (B), not the redirect rate of (A)
  which is in some cases higher.

* (B) is single-port:
	Before:   77 Mpps
	After:    90 Mpps (+16.8%)

* (B) is dual-port:
	Before:  61 Mpps
	After:   72 Mpps (+18%)

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  12 +++
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c  | 112 +++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h  |  29 +++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |  47 +++++----
 include/linux/mlx5/device.h                       |   1 +
 5 files changed, 174 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 20b3432b35de..8f5545d317ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -416,6 +416,16 @@ struct mlx5e_xdp_wqe_info {
 	u8 num_ds;
 };
 
+struct mlx5e_xdp_mpwqe {
+	/* Current MPWQE session */
+	struct mlx5e_tx_wqe *wqe;
+	u8                   ds_count;
+	u8                   max_ds_count;
+};
+
+struct mlx5e_xdpsq;
+typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq*,
+					struct mlx5e_xdp_info*);
 struct mlx5e_xdpsq {
 	/* data path */
 
@@ -428,12 +438,14 @@ struct mlx5e_xdpsq {
 	u32                        xdpi_fifo_pc ____cacheline_aligned_in_smp;
 	u16                        pc;
 	struct mlx5_wqe_ctrl_seg   *doorbell_cseg;
+	struct mlx5e_xdp_mpwqe     mpwqe;
 
 	struct mlx5e_cq            cq;
 
 	/* read only */
 	struct mlx5_wq_cyc         wq;
 	struct mlx5e_xdpsq_stats  *stats;
+	mlx5e_fp_xmit_xdp_frame    xmit_xdp_frame;
 	struct {
 		struct mlx5e_xdp_wqe_info *wqe_info;
 		struct mlx5e_xdp_info_fifo xdpi_fifo;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 5e5e43ea9b53..3740177eed09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -47,7 +47,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
 				   xdpi.xdpf->len, PCI_DMA_TODEVICE);
 	xdpi.di = *di;
 
-	return mlx5e_xmit_xdp_frame(sq, &xdpi);
+	return sq->xmit_xdp_frame(sq, &xdpi);
 }
 
 /* returns true if packet was consumed by xdp */
@@ -102,7 +102,98 @@ xdp_abort:
 	}
 }
 
-bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
+static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u8  wqebbs;
+	u16 pi;
+
+	mlx5e_xdpsq_fetch_wqe(sq, &session->wqe);
+
+	prefetchw(session->wqe->data);
+	session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT;
+
+	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+
+/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS
+ * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment.
+ * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a
+ * full-session WQE be cache-aligned.
+ */
+#if L1_CACHE_BYTES < 128
+#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1)
+#else
+#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2)
+#endif
+
+	wqebbs = min_t(u16, mlx5_wq_cyc_get_contig_wqebbs(wq, pi),
+		       MLX5E_XDP_MPW_MAX_WQEBBS);
+
+	session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs;
+}
+
+static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5_wq_cyc       *wq    = &sq->wq;
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5_wqe_ctrl_seg *cseg = &session->wqe->ctrl;
+	u16 ds_count = session->ds_count;
+	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	struct mlx5e_xdp_wqe_info *wi = &sq->db.wqe_info[pi];
+
+	cseg->opmod_idx_opcode =
+		cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_ENHANCED_MPSW);
+	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_count);
+
+	wi->num_wqebbs = DIV_ROUND_UP(ds_count, MLX5_SEND_WQEBB_NUM_DS);
+	wi->num_ds     = ds_count - MLX5E_XDP_TX_EMPTY_DS_COUNT;
+
+	sq->pc += wi->num_wqebbs;
+
+	sq->doorbell_cseg = cseg;
+
+	session->wqe = NULL; /* Close session */
+}
+
+static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
+				       struct mlx5e_xdp_info *xdpi)
+{
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5e_xdpsq_stats *stats = sq->stats;
+
+	dma_addr_t dma_addr    = xdpi->dma_addr;
+	struct xdp_frame *xdpf = xdpi->xdpf;
+	unsigned int dma_len   = xdpf->len;
+
+	if (unlikely(sq->hw_mtu < dma_len)) {
+		stats->err++;
+		return false;
+	}
+
+	if (unlikely(!session->wqe)) {
+		if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
+						     MLX5_SEND_WQE_MAX_WQEBBS))) {
+			/* SQ is full, ring doorbell */
+			mlx5e_xmit_xdp_doorbell(sq);
+			stats->full++;
+			return false;
+		}
+
+		mlx5e_xdp_mpwqe_session_start(sq);
+	}
+
+	mlx5e_xdp_mpwqe_add_dseg(sq, dma_addr, dma_len);
+
+	if (unlikely(session->ds_count == session->max_ds_count))
+		mlx5e_xdp_mpwqe_complete(sq);
+
+	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
+	stats->xmit++;
+	return true;
+}
+
+static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 {
 	struct mlx5_wq_cyc       *wq   = &sq->wq;
 	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
@@ -304,7 +395,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 		xdpi.xdpf = xdpf;
 
-		if (unlikely(!mlx5e_xmit_xdp_frame(sq, &xdpi))) {
+		if (unlikely(!sq->xmit_xdp_frame(sq, &xdpi))) {
 			dma_unmap_single(sq->pdev, xdpi.dma_addr,
 					 xdpf->len, DMA_TO_DEVICE);
 			xdp_return_frame_rx_napi(xdpf);
@@ -312,8 +403,11 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		}
 	}
 
-	if (flags & XDP_XMIT_FLUSH)
+	if (flags & XDP_XMIT_FLUSH) {
+		if (sq->mpwqe.wqe)
+			mlx5e_xdp_mpwqe_complete(sq);
 		mlx5e_xmit_xdp_doorbell(sq);
+	}
 
 	return n - drops;
 }
@@ -322,6 +416,9 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq)
 {
 	struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
 
+	if (xdpsq->mpwqe.wqe)
+		mlx5e_xdp_mpwqe_complete(xdpsq);
+
 	mlx5e_xmit_xdp_doorbell(xdpsq);
 
 	if (xdpsq->redirect_flush) {
@@ -329,3 +426,10 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq)
 		xdpsq->redirect_flush = false;
 	}
 }
+
+void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw)
+{
+	sq->xmit_xdp_frame = is_mpw ?
+		mlx5e_xmit_xdp_frame_mpwqe : mlx5e_xmit_xdp_frame;
+}
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index fd689ed506af..3a67cb3cd179 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -37,15 +37,16 @@
 #define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
 				 MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
 #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
-#define MLX5E_XDP_TX_DS_COUNT \
-	((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
+#define MLX5E_XDP_TX_EMPTY_DS_COUNT \
+	(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
+#define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
 
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      void *va, u16 *rx_headroom, u32 *len);
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq);
 void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq);
+void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw);
 void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq);
-bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi);
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
 
@@ -57,6 +58,28 @@ static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 	}
 }
 
+static inline void
+mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, dma_addr_t dma_addr, u16 dma_len)
+{
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5_wqe_data_seg *dseg =
+		(struct mlx5_wqe_data_seg *)session->wqe + session->ds_count++;
+
+	dseg->addr       = cpu_to_be64(dma_addr);
+	dseg->byte_count = cpu_to_be32(dma_len);
+	dseg->lkey       = sq->mkey_be;
+}
+
+static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq,
+					 struct mlx5e_tx_wqe **wqe)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+
+	*wqe = mlx5_wq_cyc_get_wqe(wq, pi);
+	memset(*wqe, 0, sizeof(**wqe));
+}
+
 static inline void
 mlx5e_xdpi_fifo_push(struct mlx5e_xdp_info_fifo *fifo,
 		     struct mlx5e_xdp_info *xi)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7086c73d5915..07b16e5f02bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -61,6 +61,7 @@ struct mlx5e_rq_param {
 struct mlx5e_sq_param {
 	u32                        sqc[MLX5_ST_SZ_DW(sqc)];
 	struct mlx5_wq_param       wq;
+	bool                       is_mpw;
 };
 
 struct mlx5e_cq_param {
@@ -1586,11 +1587,8 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 			    struct mlx5e_xdpsq *sq,
 			    bool is_redirect)
 {
-	unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
 	struct mlx5e_create_sq_param csp = {};
-	unsigned int inline_hdr_sz = 0;
 	int err;
-	int i;
 
 	err = mlx5e_alloc_xdpsq(c, params, param, sq, is_redirect);
 	if (err)
@@ -1606,27 +1604,35 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 	if (err)
 		goto err_free_xdpsq;
 
-	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-		inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
-		ds_cnt++;
-	}
+	mlx5e_set_xmit_fp(sq, param->is_mpw);
+
+	if (!param->is_mpw) {
+		unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
+		unsigned int inline_hdr_sz = 0;
+		int i;
 
-	/* Pre initialize fixed WQE fields */
-	for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
-		struct mlx5e_xdp_wqe_info *wi  = &sq->db.wqe_info[i];
-		struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
-		struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-		struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-		struct mlx5_wqe_data_seg *dseg;
+		if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
+			inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
+			ds_cnt++;
+		}
+
+		/* Pre initialize fixed WQE fields */
+		for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
+			struct mlx5e_xdp_wqe_info *wi  = &sq->db.wqe_info[i];
+			struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
+			struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+			struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
+			struct mlx5_wqe_data_seg *dseg;
 
-		cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
-		eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
+			cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+			eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
 
-		dseg = (struct mlx5_wqe_data_seg *)cseg + (ds_cnt - 1);
-		dseg->lkey = sq->mkey_be;
+			dseg = (struct mlx5_wqe_data_seg *)cseg + (ds_cnt - 1);
+			dseg->lkey = sq->mkey_be;
 
-		wi->num_wqebbs = 1;
-		wi->num_ds     = 1;
+			wi->num_wqebbs = 1;
+			wi->num_ds     = 1;
+		}
 	}
 
 	return 0;
@@ -2335,6 +2341,7 @@ static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
 
 	mlx5e_build_sq_param_common(priv, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
+	param->is_mpw = MLX5_CAP_ETH(priv->mdev, enhanced_multi_pkt_send_wqe);
 }
 
 static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 4674b9e99f45..8c4a820bd4c1 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -421,6 +421,7 @@ enum {
 	MLX5_OPCODE_ATOMIC_MASKED_FA	= 0x15,
 	MLX5_OPCODE_BIND_MW		= 0x18,
 	MLX5_OPCODE_CONFIG_CMD		= 0x1f,
+	MLX5_OPCODE_ENHANCED_MPSW	= 0x29,
 
 	MLX5_RECV_OPCODE_RDMA_WRITE_IMM	= 0x00,
 	MLX5_RECV_OPCODE_SEND		= 0x01,
-- 
cgit v1.2.3


From 6277053afa34253eb8d8d147388e4426e615bae4 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 20 Nov 2018 11:50:30 +0200
Subject: net/mlx5e: XDP, Add user control for XDP TX MPWQE feature

Add ethtool private flag 'xdp_tx_mpwqe' to control the feature
from userspace.
Feature is set ON by default, if supported.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  1 +
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   | 28 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  6 ++++-
 3 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8f5545d317ba..8fa8fdd30b85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -216,6 +216,7 @@ enum mlx5e_priv_flag {
 	MLX5E_PFLAG_RX_CQE_COMPRESS,
 	MLX5E_PFLAG_RX_STRIDING_RQ,
 	MLX5E_PFLAG_RX_NO_CSUM_COMPLETE,
+	MLX5E_PFLAG_XDP_TX_MPWQE,
 	MLX5E_NUM_PFLAGS, /* Keep last */
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 6e101201dcbb..c9df08133718 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1672,12 +1672,40 @@ static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
 	return 0;
 }
 
+static int set_pflag_xdp_tx_mpwqe(struct net_device *netdev, bool enable)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_channels new_channels = {};
+	int err;
+
+	if (enable && !MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe))
+		return -EOPNOTSUPP;
+
+	new_channels.params = priv->channels.params;
+
+	MLX5E_SET_PFLAG(&new_channels.params, MLX5E_PFLAG_XDP_TX_MPWQE, enable);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		return 0;
+	}
+
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		return err;
+
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	return 0;
+}
+
 static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS] = {
 	{ "rx_cqe_moder",        set_pflag_rx_cqe_based_moder },
 	{ "tx_cqe_moder",        set_pflag_tx_cqe_based_moder },
 	{ "rx_cqe_compress",     set_pflag_rx_cqe_compress },
 	{ "rx_striding_rq",      set_pflag_rx_striding_rq },
 	{ "rx_no_csum_complete", set_pflag_rx_no_csum_complete },
+	{ "xdp_tx_mpwqe",        set_pflag_xdp_tx_mpwqe },
 };
 
 static int mlx5e_handle_pflag(struct net_device *netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 07b16e5f02bd..8cfd2ec7c0a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2341,7 +2341,7 @@ static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
 
 	mlx5e_build_sq_param_common(priv, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
-	param->is_mpw = MLX5_CAP_ETH(priv->mdev, enhanced_multi_pkt_send_wqe);
+	param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE);
 }
 
 static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
@@ -4595,6 +4595,10 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
 		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
 
+	/* XDP SQ */
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE,
+			MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe));
+
 	/* set CQE compression */
 	params->rx_cqe_compress_def = false;
 	if (MLX5_CAP_GEN(mdev, cqe_compression) &&
-- 
cgit v1.2.3


From 7fa4bd739fc0fa209fa5120383aab17f6e9600f7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 21 Dec 2018 14:04:46 +0100
Subject: bpf: fix segfault in test_verifier selftest

Minor fallout from merge resolution, test_verifier was segfaulting
because the REJECT result was correct, but errstr was NULL. Properly
fix it as in 339bbff2d6e0.

Fixes: 339bbff2d6e0 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index baafe5c76aca..33f7d38849b8 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -14194,7 +14194,8 @@ static struct bpf_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
 		.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
-                .result = REJECT,
+		.errstr = "!read_ok",
+		.result = REJECT,
 	},
 	{
 		"jset: functional",
-- 
cgit v1.2.3


From e94e50bd88f7ed2f2d40c32c06efd61c36c33ec8 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 21 Dec 2018 19:03:13 +0100
Subject: net: fix possible user-after-free in skb_ext_add()

On cow we can free the old extension: we must avoid dereferencing
such extension after skb_ext_maybe_cow(). Since 'new' contents
are always equal to 'old' after the copy, we can fix the above
accessing the relevant data using 'new'.

Fixes: df5042f4c5b9 ("sk_buff: add skb extension infrastructure")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index cb0bf4215745..e1d88762f659 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5666,13 +5666,13 @@ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id)
 		if (!new)
 			return NULL;
 
-		if (__skb_ext_exist(old, id)) {
+		if (__skb_ext_exist(new, id)) {
 			if (old != new)
 				skb->extensions = new;
 			goto set_active;
 		}
 
-		newoff = old->chunks;
+		newoff = new->chunks;
 	} else {
 		newoff = SKB_EXT_CHUNKSIZEOF(*new);
 
-- 
cgit v1.2.3


From d312d0a6846a4553bd955afd414f8f55398ece07 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 21 Dec 2018 19:03:14 +0100
Subject: net: drop the unused helper skb_ext_get()

Such helper is currently unused, and skb extension users are
better off using skb_ext_add()/skb_ext_del(). So let's drop
it.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3f741b04e55d..2a57a365c711 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3938,16 +3938,6 @@ static inline void skb_ext_put(struct sk_buff *skb)
 		__skb_ext_put(skb->extensions);
 }
 
-static inline void skb_ext_get(struct sk_buff *skb)
-{
-	if (skb->active_extensions) {
-		struct skb_ext *ext = skb->extensions;
-
-		if (ext)
-			refcount_inc(&ext->refcnt);
-	}
-}
-
 static inline void __skb_ext_copy(struct sk_buff *dst,
 				  const struct sk_buff *src)
 {
@@ -3995,7 +3985,6 @@ static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id)
 }
 #else
 static inline void skb_ext_put(struct sk_buff *skb) {}
-static inline void skb_ext_get(struct sk_buff *skb) {}
 static inline void skb_ext_del(struct sk_buff *skb, int unused) {}
 static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {}
 static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {}
-- 
cgit v1.2.3


From 682ec859518d73435cc924d816da2953343241c1 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 21 Dec 2018 19:03:15 +0100
Subject: net: minor cleanup in skb_ext_add()

When the extension to be added is already present, the only
skb field we may need to update is 'extensions': we can reorder
the code and avoid a branch.

v1 -> v2:
 - be sure to flag the newly added extension as active

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e1d88762f659..37317ffec146 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5666,11 +5666,8 @@ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id)
 		if (!new)
 			return NULL;
 
-		if (__skb_ext_exist(new, id)) {
-			if (old != new)
-				skb->extensions = new;
+		if (__skb_ext_exist(new, id))
 			goto set_active;
-		}
 
 		newoff = new->chunks;
 	} else {
@@ -5684,8 +5681,8 @@ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id)
 	newlen = newoff + skb_ext_type_len[id];
 	new->chunks = newlen;
 	new->offset[id] = newoff;
-	skb->extensions = new;
 set_active:
+	skb->extensions = new;
 	skb->active_extensions |= 1 << id;
 	return skb_ext_get_ptr(new, id);
 }
-- 
cgit v1.2.3


From 50d5258634aee2e62832aa086d2fb0de00e72b91 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 21 Dec 2018 14:49:01 -0600
Subject: net: core: Fix Spectre v1 vulnerability

flen is indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/core/filter.c:1101 bpf_check_classic() warn: potential spectre issue 'filter' [w]

Fix this by sanitizing flen before using it to index filter at line 1101:

	switch (filter[flen - 1].code) {

and through pc at line 1040:

	const struct sock_filter *ftest = &filter[pc];

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 8d2c629501e2..0c74c2f9776a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -73,6 +73,7 @@
 #include <linux/seg6_local.h>
 #include <net/seg6.h>
 #include <net/seg6_local.h>
+#include <linux/nospec.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -1038,6 +1039,7 @@ static int bpf_check_classic(const struct sock_filter *filter,
 	bool anc_found;
 	int pc;
 
+	flen = array_index_nospec(flen, BPF_MAXINSNS + 1);
 	/* Check the filter code now */
 	for (pc = 0; pc < flen; pc++) {
 		const struct sock_filter *ftest = &filter[pc];
-- 
cgit v1.2.3


From d686026b1e6ed4ea27d630d8f54f9a694db088b2 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 21 Dec 2018 15:41:17 -0600
Subject: phonet: af_phonet: Fix Spectre v1 vulnerability

protocol is indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/phonet/af_phonet.c:48 phonet_proto_get() warn: potential spectre issue 'proto_tab' [w] (local cap)

Fix this by sanitizing protocol before using it to index proto_tab.

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/phonet/af_phonet.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index 3b0ef691f5b1..d4b2abd78858 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -34,6 +34,8 @@
 #include <net/phonet/phonet.h>
 #include <net/phonet/pn_dev.h>
 
+#include <linux/nospec.h>
+
 /* Transport protocol registration */
 static const struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly;
 
@@ -43,6 +45,7 @@ static const struct phonet_protocol *phonet_proto_get(unsigned int protocol)
 
 	if (protocol >= PHONET_NPROTO)
 		return NULL;
+	protocol = array_index_nospec(protocol, PHONET_NPROTO);
 
 	rcu_read_lock();
 	pp = rcu_dereference(proto_tab[protocol]);
-- 
cgit v1.2.3


From a95386f0390ab602904d11fe6bd7ea5ef9b136f8 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 21 Dec 2018 15:47:53 -0600
Subject: nfc: af_nfc: Fix Spectre v1 vulnerability

proto is indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/nfc/af_nfc.c:42 nfc_sock_create() warn: potential spectre issue 'proto_tab' [w] (local cap)

Fix this by sanitizing proto before using it to index proto_tab.

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/af_nfc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c
index d3e594eb36d0..256f3c57059e 100644
--- a/net/nfc/af_nfc.c
+++ b/net/nfc/af_nfc.c
@@ -21,6 +21,7 @@
 
 #include <linux/nfc.h>
 #include <linux/module.h>
+#include <linux/nospec.h>
 
 #include "nfc.h"
 
@@ -37,6 +38,7 @@ static int nfc_sock_create(struct net *net, struct socket *sock, int proto,
 
 	if (proto < 0 || proto >= NFC_SOCKPROTO_MAX)
 		return -EINVAL;
+	proto = array_index_nospec(proto, NFC_SOCKPROTO_MAX);
 
 	read_lock(&proto_tab_lock);
 	if (proto_tab[proto] &&	try_module_get(proto_tab[proto]->owner)) {
-- 
cgit v1.2.3


From 6b8d95f1795c42161dc0984b6863e95d6acf24ed Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 22 Dec 2018 16:53:45 -0500
Subject: packet: validate address length if non-zero

Validate packet socket address length if a length is given. Zero
length is equivalent to not setting an address.

Fixes: 99137b7888f4 ("packet: validate address length")
Reported-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 5dda263b4a0a..eedacdebcd4c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2625,7 +2625,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 						sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_addr;
+		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
 			goto out;
@@ -2825,7 +2825,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_addr;
+		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
 			goto out;
-- 
cgit v1.2.3


From a3ac5817ffe8f81dbe6be1522b499b48bc322e3a Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 21 Dec 2018 15:22:29 -0600
Subject: can: af_can: Fix Spectre v1 vulnerability

protocol is indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/can/af_can.c:115 can_get_proto() warn: potential spectre issue 'proto_tab' [w]

Fix this by sanitizing protocol before using it to index proto_tab.

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/can/af_can.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/can/af_can.c b/net/can/af_can.c
index 1684ba5b51eb..cade7250c6d4 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -59,6 +59,7 @@
 #include <linux/can/core.h>
 #include <linux/can/skb.h>
 #include <linux/ratelimit.h>
+#include <linux/nospec.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 
@@ -136,6 +137,7 @@ static int can_create(struct net *net, struct socket *sock, int protocol,
 
 	if (protocol < 0 || protocol >= CAN_NPROTO)
 		return -EINVAL;
+	protocol = array_index_nospec(protocol, CAN_NPROTO);
 
 	cp = can_get_proto(protocol);
 
-- 
cgit v1.2.3


From f2ab95814103314af3239d322e382c61c69a788d Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 23 Dec 2018 16:01:35 -0800
Subject: net: Revert recent Spectre-v1 patches.

This reverts:

50d5258634ae ("net: core: Fix Spectre v1 vulnerability")
d686026b1e6e ("phonet: af_phonet: Fix Spectre v1 vulnerability")
a95386f0390a ("nfc: af_nfc: Fix Spectre v1 vulnerability")
a3ac5817ffe8 ("can: af_can: Fix Spectre v1 vulnerability")

After some discussion with Alexei Starovoitov these all seem to
be completely unnecessary.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/can/af_can.c       | 2 --
 net/core/filter.c      | 2 --
 net/nfc/af_nfc.c       | 2 --
 net/phonet/af_phonet.c | 3 ---
 4 files changed, 9 deletions(-)

diff --git a/net/can/af_can.c b/net/can/af_can.c
index cade7250c6d4..1684ba5b51eb 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -59,7 +59,6 @@
 #include <linux/can/core.h>
 #include <linux/can/skb.h>
 #include <linux/ratelimit.h>
-#include <linux/nospec.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 
@@ -137,7 +136,6 @@ static int can_create(struct net *net, struct socket *sock, int protocol,
 
 	if (protocol < 0 || protocol >= CAN_NPROTO)
 		return -EINVAL;
-	protocol = array_index_nospec(protocol, CAN_NPROTO);
 
 	cp = can_get_proto(protocol);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 0c74c2f9776a..8d2c629501e2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -73,7 +73,6 @@
 #include <linux/seg6_local.h>
 #include <net/seg6.h>
 #include <net/seg6_local.h>
-#include <linux/nospec.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -1039,7 +1038,6 @@ static int bpf_check_classic(const struct sock_filter *filter,
 	bool anc_found;
 	int pc;
 
-	flen = array_index_nospec(flen, BPF_MAXINSNS + 1);
 	/* Check the filter code now */
 	for (pc = 0; pc < flen; pc++) {
 		const struct sock_filter *ftest = &filter[pc];
diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c
index 256f3c57059e..d3e594eb36d0 100644
--- a/net/nfc/af_nfc.c
+++ b/net/nfc/af_nfc.c
@@ -21,7 +21,6 @@
 
 #include <linux/nfc.h>
 #include <linux/module.h>
-#include <linux/nospec.h>
 
 #include "nfc.h"
 
@@ -38,7 +37,6 @@ static int nfc_sock_create(struct net *net, struct socket *sock, int proto,
 
 	if (proto < 0 || proto >= NFC_SOCKPROTO_MAX)
 		return -EINVAL;
-	proto = array_index_nospec(proto, NFC_SOCKPROTO_MAX);
 
 	read_lock(&proto_tab_lock);
 	if (proto_tab[proto] &&	try_module_get(proto_tab[proto]->owner)) {
diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index d4b2abd78858..3b0ef691f5b1 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -34,8 +34,6 @@
 #include <net/phonet/phonet.h>
 #include <net/phonet/pn_dev.h>
 
-#include <linux/nospec.h>
-
 /* Transport protocol registration */
 static const struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly;
 
@@ -45,7 +43,6 @@ static const struct phonet_protocol *phonet_proto_get(unsigned int protocol)
 
 	if (protocol >= PHONET_NPROTO)
 		return NULL;
-	protocol = array_index_nospec(protocol, PHONET_NPROTO);
 
 	rcu_read_lock();
 	pp = rcu_dereference(proto_tab[protocol]);
-- 
cgit v1.2.3


From 8762cdcd1d5055017770a54e2755bed30dd4f8b6 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 21 Dec 2018 21:57:26 +0100
Subject: staging: octeon: fix build failure with XFRM enabled

skb->sp doesn't exist anymore in the next-next tree, so mips defconfig
no longer builds.  Use helper instead to reset the secpath.

Not even compile tested.

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Fixes: 4165079ba328d ("net: switch secpath to use skb extension infrastructure")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/staging/octeon/ethernet-tx.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c
index df3441b815bb..317c9720467c 100644
--- a/drivers/staging/octeon/ethernet-tx.c
+++ b/drivers/staging/octeon/ethernet-tx.c
@@ -359,8 +359,7 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 	dst_release(skb_dst(skb));
 	skb_dst_set(skb, NULL);
 #ifdef CONFIG_XFRM
-	secpath_put(skb->sp);
-	skb->sp = NULL;
+	secpath_reset(skb);
 #endif
 	nf_reset(skb);
 
-- 
cgit v1.2.3


From 5d1f7354faad4b6210fac9192d0ca4c16b00ae7e Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Sat, 22 Dec 2018 20:02:16 +0800
Subject: net/mlx5e: fix semicolon.cocci warnings

drivers/net/ethernet/mellanox/mlx5/core/en_rep.c:1339:57-58: Unneeded semicolon

 Remove unneeded semicolon.

Generated by: scripts/coccinelle/misc/semicolon.cocci

Fixes: 4c8fb2986d44 ("net/mlx5e: Increase VF representors' SQ size to 128")
CC: Gavi Teitz <gavi@mellanox.com>
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index dbbdbdff75e8..96cc0c6a4014 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1346,7 +1346,7 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	if (rep->vport == FDB_UPLINK_VPORT)
 		params->log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
 	else
-		params->log_sq_size = MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE;;
+		params->log_sq_size = MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE;
 
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
-- 
cgit v1.2.3


From 7bdca378b2301b1fc6a95c60d6d428408ae4e39e Mon Sep 17 00:00:00 2001
From: wenxu <wenxu@ucloud.cn>
Date: Sun, 23 Dec 2018 16:18:39 +0800
Subject: iptunnel: Set tun_flags in the iptunnel_metadata_reply from src

ip l add tun type gretap external
ip r a 10.0.0.2 encap ip id 1000 dst 172.168.0.2 key dev tun
ip a a 10.0.0.1/24 dev tun

The peer arp request to 10.0.0.1 with tunnel_id, but the arp reply
only set the tun_id but not the tun_flags with TUNNEL_KEY. The arp
reply packet don't contain tun_id field.

Signed-off-by: wenxu <wenxu@ucloud.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index c248e0dccbe1..43f519c9b318 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -151,6 +151,7 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 		       sizeof(struct in6_addr));
 	else
 		dst->key.u.ipv4.dst = src->key.u.ipv4.src;
+	dst->key.tun_flags = src->key.tun_flags;
 	dst->mode = src->mode | IP_TUNNEL_INFO_TX;
 
 	return res;
-- 
cgit v1.2.3


From 2534f14a94c1fe48928a4b00a0e241fa7132d00b Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@lip6.fr>
Date: Sun, 23 Dec 2018 09:56:57 +0100
Subject: net/mlx5e: drop useless LIST_HEAD

Drop LIST_HEAD where the variable it declares is never used.

These became useless in 244cd96adb5f ("net_sched: remove list_head
from tc_action")

The semantic patch that fixes this problem is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@@
identifier x;
@@
- LIST_HEAD(x);
  ... when != x
// </smpl>

Fixes: 244cd96adb5f ("net_sched: remove list_head from tc_action")
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 4d6c9757afad..cae6c6d48984 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2183,7 +2183,6 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 {
 	const struct tc_action *a;
 	bool modify_ip_header;
-	LIST_HEAD(actions);
 	u8 htype, ip_proto;
 	void *headers_v;
 	u16 ethertype;
@@ -2272,7 +2271,6 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 {
 	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
 	const struct tc_action *a;
-	LIST_HEAD(actions);
 	u32 action = 0;
 	int err, i;
 
@@ -2511,7 +2509,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct ip_tunnel_info *info = NULL;
 	const struct tc_action *a;
-	LIST_HEAD(actions);
 	bool encap = false;
 	u32 action = 0;
 	int err, i;
-- 
cgit v1.2.3


From d0863792f805ffad7d98fb6bd484bc2fad59c8ea Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@lip6.fr>
Date: Sun, 23 Dec 2018 09:57:11 +0100
Subject: mlxsw: spectrum: drop useless LIST_HEAD

Drop LIST_HEAD where the variable it declares is never used.

The uses were removed in 244cd96adb5f ("net_sched: remove
list_head from tc_action"), but not the declaration.

The semantic patch that fixes this problem is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@@
identifier x;
@@
- LIST_HEAD(x);
  ... when != x
// </smpl>

Fixes: 244cd96adb5f ("net_sched: remove list_head from tc_action")
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index c742a581f0d0..eed1045e4d96 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1347,7 +1347,6 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry;
 	__be16 protocol = f->common.protocol;
 	const struct tc_action *a;
-	LIST_HEAD(actions);
 	int err;
 
 	if (!tcf_exts_has_one_action(f->exts)) {
-- 
cgit v1.2.3


From 61988bd281c9b08e0cc084f0b2da3b109c4c39c8 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@lip6.fr>
Date: Sun, 23 Dec 2018 09:57:14 +0100
Subject: net/mlx4_core: drop useless LIST_HEAD

Drop LIST_HEAD where the variable it declares has never
been used.

The semantic patch that fixes this problem is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@@
identifier x;
@@
- LIST_HEAD(x);
  ... when != x
// </smpl>

Fixes: c82e9aa0a8bc ("mlx4_core: resource tracking for HCA resources used by guests")
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 31bd56727022..eb13d3618162 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -4729,7 +4729,6 @@ static void rem_slave_srqs(struct mlx4_dev *dev, int slave)
 	struct res_srq *tmp;
 	int state;
 	u64 in_param;
-	LIST_HEAD(tlist);
 	int srqn;
 	int err;
 
@@ -4795,7 +4794,6 @@ static void rem_slave_cqs(struct mlx4_dev *dev, int slave)
 	struct res_cq *tmp;
 	int state;
 	u64 in_param;
-	LIST_HEAD(tlist);
 	int cqn;
 	int err;
 
@@ -4858,7 +4856,6 @@ static void rem_slave_mrs(struct mlx4_dev *dev, int slave)
 	struct res_mpt *tmp;
 	int state;
 	u64 in_param;
-	LIST_HEAD(tlist);
 	int mptn;
 	int err;
 
@@ -4926,7 +4923,6 @@ static void rem_slave_mtts(struct mlx4_dev *dev, int slave)
 	struct res_mtt *mtt;
 	struct res_mtt *tmp;
 	int state;
-	LIST_HEAD(tlist);
 	int base;
 	int err;
 
@@ -5115,7 +5111,6 @@ static void rem_slave_eqs(struct mlx4_dev *dev, int slave)
 	struct res_eq *tmp;
 	int err;
 	int state;
-	LIST_HEAD(tlist);
 	int eqn;
 
 	err = move_all_busy(dev, slave, RES_EQ);
-- 
cgit v1.2.3


From 40c3ff6d5e0809505a067dd423c110c5658c478c Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sun, 23 Dec 2018 12:52:18 -0500
Subject: ieee802154: lowpan_header_create check must check daddr

Packet sockets may call dev_header_parse with NULL daddr. Make
lowpan_header_ops.create fail.

Fixes: 87a93e4eceb4 ("ieee802154: change needed headroom/tailroom")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ieee802154/6lowpan/tx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c
index ca53efa17be1..8bec827081cd 100644
--- a/net/ieee802154/6lowpan/tx.c
+++ b/net/ieee802154/6lowpan/tx.c
@@ -48,6 +48,9 @@ int lowpan_header_create(struct sk_buff *skb, struct net_device *ldev,
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct neighbour *n;
 
+	if (!daddr)
+		return -EINVAL;
+
 	/* TODO:
 	 * if this package isn't ipv6 one, where should it be routed?
 	 */
-- 
cgit v1.2.3


From 89dfd0083751d00d5d7ead36f6d8b045bf89c5e1 Mon Sep 17 00:00:00 2001
From: Aditya Pakki <pakki001@umn.edu>
Date: Sun, 23 Dec 2018 18:54:53 -0600
Subject: net/netlink_compat: Fix a missing check of nla_parse_nested

In tipc_nl_compat_sk_dump(), if nla_parse_nested() fails, it could return
an error. To be consistent with other invocations of the function call,
on error, the fix passes the return value upstream.

Signed-off-by: Aditya Pakki <pakki001@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 6376467e78f8..21f6ccc89401 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -951,8 +951,11 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg,
 		u32 node;
 		struct nlattr *con[TIPC_NLA_CON_MAX + 1];
 
-		nla_parse_nested(con, TIPC_NLA_CON_MAX,
-				 sock[TIPC_NLA_SOCK_CON], NULL, NULL);
+		err = nla_parse_nested(con, TIPC_NLA_CON_MAX,
+				       sock[TIPC_NLA_SOCK_CON], NULL, NULL);
+
+		if (err)
+			return err;
 
 		node = nla_get_u32(con[TIPC_NLA_CON_NODE]);
 		tipc_tlv_sprintf(msg->rep, "  connected to <%u.%u.%u:%u>",
-- 
cgit v1.2.3


From 0eb987c874dc93f9c9d85a6465dbde20fdd3884c Mon Sep 17 00:00:00 2001
From: Aditya Pakki <pakki001@umn.edu>
Date: Sun, 23 Dec 2018 19:42:38 -0600
Subject: net/net_namespace: Check the return value of register_pernet_subsys()

In net_ns_init(), register_pernet_subsys() could fail while registering
network namespace subsystems. The fix checks the return value and
sends a panic() on failure.

Signed-off-by: Aditya Pakki <pakki001@umn.edu>
Reviewed-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index fefe72774aeb..af8849a7a9c3 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -917,7 +917,8 @@ static int __init net_ns_init(void)
 	init_net_initialized = true;
 	up_write(&pernet_ops_rwsem);
 
-	register_pernet_subsys(&net_ns_ops);
+	if (register_pernet_subsys(&net_ns_ops))
+		panic("Could not register network namespace subsystems");
 
 	rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL,
 		      RTNL_FLAG_DOIT_UNLOCKED);
-- 
cgit v1.2.3


From 38355a5f9a22bfa5bd5b1bb79805aca39fa53729 Mon Sep 17 00:00:00 2001
From: Ivan Mironov <mironov.ivan@gmail.com>
Date: Mon, 24 Dec 2018 20:13:05 +0500
Subject: bnx2x: Fix NULL pointer dereference in bnx2x_del_all_vlans() on some
 hw

This happened when I tried to boot normal Fedora 29 system with latest
available kernel (from fedora rawhide, plus some unrelated custom
patches):

	BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
	PGD 0 P4D 0
	Oops: 0010 [#1] SMP PTI
	CPU: 6 PID: 1422 Comm: libvirtd Tainted: G          I       4.20.0-0.rc7.git3.hpsa2.1.fc29.x86_64 #1
	Hardware name: HP ProLiant BL460c G6, BIOS I24 05/21/2018
	RIP: 0010:          (null)
	Code: Bad RIP value.
	RSP: 0018:ffffa47ccdc9fbe0 EFLAGS: 00010246
	RAX: 0000000000000000 RBX: 00000000000003e8 RCX: ffffa47ccdc9fbf8
	RDX: ffffa47ccdc9fc00 RSI: ffff97d9ee7b01f8 RDI: ffff97d9f0150b80
	RBP: ffff97d9f0150b80 R08: 0000000000000000 R09: 0000000000000000
	R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000003
	R13: ffff97d9ef1e53e8 R14: 0000000000000009 R15: ffff97d9f0ac6730
	FS:  00007f4d224ef700(0000) GS:ffff97d9fa200000(0000) knlGS:0000000000000000
	CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
	CR2: ffffffffffffffd6 CR3: 00000011ece52006 CR4: 00000000000206e0
	Call Trace:
	 ? bnx2x_chip_cleanup+0x195/0x610 [bnx2x]
	 ? bnx2x_nic_unload+0x1e2/0x8f0 [bnx2x]
	 ? bnx2x_reload_if_running+0x24/0x40 [bnx2x]
	 ? bnx2x_set_features+0x79/0xa0 [bnx2x]
	 ? __netdev_update_features+0x244/0x9e0
	 ? netlink_broadcast_filtered+0x136/0x4b0
	 ? netdev_update_features+0x22/0x60
	 ? dev_disable_lro+0x1c/0xe0
	 ? devinet_sysctl_forward+0x1c6/0x211
	 ? proc_sys_call_handler+0xab/0x100
	 ? __vfs_write+0x36/0x1a0
	 ? rcu_read_lock_sched_held+0x79/0x80
	 ? rcu_sync_lockdep_assert+0x2e/0x60
	 ? __sb_start_write+0x14c/0x1b0
	 ? vfs_write+0x159/0x1c0
	 ? vfs_write+0xba/0x1c0
	 ? ksys_write+0x52/0xc0
	 ? do_syscall_64+0x60/0x1f0
	 ? entry_SYSCALL_64_after_hwframe+0x49/0xbe

After some investigation I figured out that recently added cleanup code
tries to call VLAN filtering de-initialization function which exist only
for newer hardware. Corresponding function pointer is not
set (== 0) for older hardware, namely these chips:

	#define CHIP_NUM_57710			0x164e
	#define CHIP_NUM_57711			0x164f
	#define CHIP_NUM_57711E			0x1650

And I have one of those in my test system:

	Broadcom Inc. and subsidiaries NetXtreme II BCM57711E 10-Gigabit PCIe [14e4:1650]

Function bnx2x_init_vlan_mac_fp_objs() from
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h decides whether to
initialize relevant pointers in bnx2x_sp_objs.vlan_obj or not.

This regression was introduced after v4.20-rc7, and still exists in v4.20
release.

Fixes: 04f05230c5c13 ("bnx2x: Remove configured vlans as part of unload sequence.")
Signed-off-by: Ivan Mironov <mironov.ivan@gmail.com>
Signed-off-by: Ivan Mironov <mironov.ivan@gmail.com>
Acked-by: Sudarsana Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index b164f705709d..3b5b47e98c73 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -9360,10 +9360,16 @@ void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link)
 		BNX2X_ERR("Failed to schedule DEL commands for UC MACs list: %d\n",
 			  rc);
 
-	/* Remove all currently configured VLANs */
-	rc = bnx2x_del_all_vlans(bp);
-	if (rc < 0)
-		BNX2X_ERR("Failed to delete all VLANs\n");
+	/* The whole *vlan_obj structure may be not initialized if VLAN
+	 * filtering offload is not supported by hardware. Currently this is
+	 * true for all hardware covered by CHIP_IS_E1x().
+	 */
+	if (!CHIP_IS_E1x(bp)) {
+		/* Remove all currently configured VLANs */
+		rc = bnx2x_del_all_vlans(bp);
+		if (rc < 0)
+			BNX2X_ERR("Failed to delete all VLANs\n");
+	}
 
 	/* Disable LLH */
 	if (!CHIP_IS_E1(bp))
-- 
cgit v1.2.3


From bd437c99cf63b8adaea51156db383f9dfdd57503 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 24 Dec 2018 19:41:46 +0000
Subject: drivers/net: appletalk/cops: remove redundant if statement and mask

The two different assignments for pkt_len are actually the same and
so the if statement is redundant and can be removed.  Masking a u8
return value from inb() with 0xFF is also redundant and can also be
emoved.

Similarly, the two different outb calls are identical as the mask
of 0xff on the second outb is redundant since a u8 is being written,
so the if statement is also redundant and can be also removed.

Detected by CoverityScan, CID#1475639 ("Identical code for different
branches")

V2: Remove the if statement for the outb calls, thanks to David
Miller for spotting this.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/appletalk/cops.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c
index bb49f6e40a19..f90bb723985f 100644
--- a/drivers/net/appletalk/cops.c
+++ b/drivers/net/appletalk/cops.c
@@ -777,10 +777,7 @@ static void cops_rx(struct net_device *dev)
         }
 
         /* Get response length. */
-	if(lp->board==DAYNA)
-        	pkt_len = inb(ioaddr) & 0xFF;
-	else
-		pkt_len = inb(ioaddr) & 0x00FF;
+	pkt_len = inb(ioaddr);
         pkt_len |= (inb(ioaddr) << 8);
         /* Input IO code. */
         rsp_type=inb(ioaddr);
@@ -892,10 +889,7 @@ static netdev_tx_t cops_send_packet(struct sk_buff *skb,
 
 	/* Output IO length. */
 	outb(skb->len, ioaddr);
-	if(lp->board == DAYNA)
-               	outb(skb->len >> 8, ioaddr);
-	else
-		outb((skb->len >> 8)&0x0FF, ioaddr);
+	outb(skb->len >> 8, ioaddr);
 
 	/* Output IO code. */
 	outb(LAP_WRITE, ioaddr);
-- 
cgit v1.2.3


From c92c81df93df95dafbf6926613ce0b436227b007 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Mon, 24 Dec 2018 12:57:17 -0800
Subject: net: dccp: fix kernel crash on module load

Patch eedbbb0d98b2 "net: dccp: initialize (addr,port) ..."
added calling to inet_hashinfo2_init() from dccp_init().

However, inet_hashinfo2_init() is marked as __init(), and
thus the kernel panics when dccp is loaded as module. Removing
__init() tag from inet_hashinfo2_init() is not feasible because
it calls into __init functions in mm.

This patch adds inet_hashinfo2_init_mod() function that can
be called after the init phase is done; changes dccp_init() to
call the new function; un-marks inet_hashinfo2_init() as
exported.

Fixes: eedbbb0d98b2 ("net: dccp: initialize (addr,port) ...")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h |  1 +
 net/dccp/proto.c              |  8 ++++----
 net/ipv4/inet_hashtables.c    | 34 ++++++++++++++++++++++++++--------
 3 files changed, 31 insertions(+), 12 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 0ce460e93dc4..babb14136705 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -237,6 +237,7 @@ void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
 			 unsigned long numentries, int scale,
 			 unsigned long low_limit,
 			 unsigned long high_limit);
+int inet_hashinfo2_init_mod(struct inet_hashinfo *h);
 
 bool inet_ehash_insert(struct sock *sk, struct sock *osk);
 bool inet_ehash_nolisten(struct sock *sk, struct sock *osk);
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index be0b223aa862..2cc5fbb1b29e 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1139,11 +1139,11 @@ static int __init dccp_init(void)
 	rc = percpu_counter_init(&dccp_orphan_count, 0, GFP_KERNEL);
 	if (rc)
 		goto out_fail;
-	rc = -ENOBUFS;
 	inet_hashinfo_init(&dccp_hashinfo);
-	inet_hashinfo2_init(&dccp_hashinfo, "dccp_listen_portaddr_hash",
-			    INET_LHTABLE_SIZE, 21,  /* one slot per 2 MB*/
-			    0, 64 * 1024);
+	rc = inet_hashinfo2_init_mod(&dccp_hashinfo);
+	if (rc)
+		goto out_fail;
+	rc = -ENOBUFS;
 	dccp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("dccp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 2445614de6a7..942265d65eb3 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -762,13 +762,22 @@ void inet_hashinfo_init(struct inet_hashinfo *h)
 }
 EXPORT_SYMBOL_GPL(inet_hashinfo_init);
 
+static void init_hashinfo_lhash2(struct inet_hashinfo *h)
+{
+	int i;
+
+	for (i = 0; i <= h->lhash2_mask; i++) {
+		spin_lock_init(&h->lhash2[i].lock);
+		INIT_HLIST_HEAD(&h->lhash2[i].head);
+		h->lhash2[i].count = 0;
+	}
+}
+
 void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
 				unsigned long numentries, int scale,
 				unsigned long low_limit,
 				unsigned long high_limit)
 {
-	unsigned int i;
-
 	h->lhash2 = alloc_large_system_hash(name,
 					    sizeof(*h->lhash2),
 					    numentries,
@@ -778,14 +787,23 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
 					    &h->lhash2_mask,
 					    low_limit,
 					    high_limit);
+	init_hashinfo_lhash2(h);
+}
 
-	for (i = 0; i <= h->lhash2_mask; i++) {
-		spin_lock_init(&h->lhash2[i].lock);
-		INIT_HLIST_HEAD(&h->lhash2[i].head);
-		h->lhash2[i].count = 0;
-	}
+int inet_hashinfo2_init_mod(struct inet_hashinfo *h)
+{
+	h->lhash2 = kmalloc_array(INET_LHTABLE_SIZE, sizeof(*h->lhash2), GFP_KERNEL);
+	if (!h->lhash2)
+		return -ENOMEM;
+
+	h->lhash2_mask = INET_LHTABLE_SIZE - 1;
+	/* INET_LHTABLE_SIZE must be a power of 2 */
+	BUG_ON(INET_LHTABLE_SIZE & h->lhash2_mask);
+
+	init_hashinfo_lhash2(h);
+	return 0;
 }
-EXPORT_SYMBOL_GPL(inet_hashinfo2_init);
+EXPORT_SYMBOL_GPL(inet_hashinfo2_init_mod);
 
 int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
 {
-- 
cgit v1.2.3